diff --git a/Documentation/ABI/testing/sysfs-class-net-statistics b/Documentation/ABI/testing/sysfs-class-net-statistics index 55db27815361b2d9ad511e026bee60a615ae03d5..53e508c6936a515216ad3af96ddfb170f6e50cf7 100644 --- a/Documentation/ABI/testing/sysfs-class-net-statistics +++ b/Documentation/ABI/testing/sysfs-class-net-statistics @@ -1,4 +1,4 @@ -What: /sys/class//statistics/collisions +What: /sys/class/net//statistics/collisions Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -6,7 +6,7 @@ Description: Indicates the number of collisions seen by this network device. This value might not be relevant with all MAC layers. -What: /sys/class//statistics/multicast +What: /sys/class/net//statistics/multicast Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -14,7 +14,7 @@ Description: Indicates the number of multicast packets received by this network device. -What: /sys/class//statistics/rx_bytes +What: /sys/class/net//statistics/rx_bytes Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -23,7 +23,7 @@ Description: See the network driver for the exact meaning of when this value is incremented. -What: /sys/class//statistics/rx_compressed +What: /sys/class/net//statistics/rx_compressed Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -32,7 +32,7 @@ Description: network device. This value might only be relevant for interfaces that support packet compression (e.g: PPP). -What: /sys/class//statistics/rx_crc_errors +What: /sys/class/net//statistics/rx_crc_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -41,7 +41,7 @@ Description: by this network device. Note that the specific meaning might depend on the MAC layer used by the interface. -What: /sys/class//statistics/rx_dropped +What: /sys/class/net//statistics/rx_dropped Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -51,7 +51,7 @@ Description: packet processing. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_errors +What: /sys/class/net//statistics/rx_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -59,7 +59,7 @@ Description: Indicates the number of receive errors on this network device. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_fifo_errors +What: /sys/class/net//statistics/rx_fifo_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -68,7 +68,7 @@ Description: network device. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_frame_errors +What: /sys/class/net//statistics/rx_frame_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -78,7 +78,7 @@ Description: on the MAC layer protocol used. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_length_errors +What: /sys/class/net//statistics/rx_length_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -87,7 +87,7 @@ Description: error, oversized or undersized. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_missed_errors +What: /sys/class/net//statistics/rx_missed_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -96,7 +96,7 @@ Description: due to lack of capacity in the receive side. See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_nohandler +What: /sys/class/net//statistics/rx_nohandler Date: February 2016 KernelVersion: 4.6 Contact: netdev@vger.kernel.org @@ -104,7 +104,7 @@ Description: Indicates the number of received packets that were dropped on an inactive device by the network core. -What: /sys/class//statistics/rx_over_errors +What: /sys/class/net//statistics/rx_over_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -114,7 +114,7 @@ Description: (e.g: larger than MTU). See the network driver for the exact meaning of this value. -What: /sys/class//statistics/rx_packets +What: /sys/class/net//statistics/rx_packets Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -122,7 +122,7 @@ Description: Indicates the total number of good packets received by this network device. -What: /sys/class//statistics/tx_aborted_errors +What: /sys/class/net//statistics/tx_aborted_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -132,7 +132,7 @@ Description: a medium collision). See the network driver for the exact meaning of this value. -What: /sys/class//statistics/tx_bytes +What: /sys/class/net//statistics/tx_bytes Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -143,7 +143,7 @@ Description: transmitted packets or all packets that have been queued for transmission. -What: /sys/class//statistics/tx_carrier_errors +What: /sys/class/net//statistics/tx_carrier_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -152,7 +152,7 @@ Description: because of carrier errors (e.g: physical link down). See the network driver for the exact meaning of this value. -What: /sys/class//statistics/tx_compressed +What: /sys/class/net//statistics/tx_compressed Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -161,7 +161,7 @@ Description: this might only be relevant for devices that support compression (e.g: PPP). -What: /sys/class//statistics/tx_dropped +What: /sys/class/net//statistics/tx_dropped Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -170,7 +170,7 @@ Description: See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class//statistics/tx_errors +What: /sys/class/net//statistics/tx_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -179,7 +179,7 @@ Description: a network device. See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class//statistics/tx_fifo_errors +What: /sys/class/net//statistics/tx_fifo_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -188,7 +188,7 @@ Description: FIFO error. See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class//statistics/tx_heartbeat_errors +What: /sys/class/net//statistics/tx_heartbeat_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -197,7 +197,7 @@ Description: reported as heartbeat errors. See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class//statistics/tx_packets +What: /sys/class/net//statistics/tx_packets Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -206,7 +206,7 @@ Description: device. See the driver for whether this reports the number of all attempted or successful transmissions. -What: /sys/class//statistics/tx_window_errors +What: /sys/class/net//statistics/tx_window_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 13c01b641dc70a8847cc37f8d2a31c683bf28c6d..78c26280c473befd8c07887e4ec1aa423ecaf348 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -519,6 +519,7 @@ What: /sys/devices/system/cpu/vulnerabilities /sys/devices/system/cpu/vulnerabilities/mds /sys/devices/system/cpu/vulnerabilities/meltdown /sys/devices/system/cpu/vulnerabilities/mmio_stale_data + /sys/devices/system/cpu/vulnerabilities/reg_file_data_sampling /sys/devices/system/cpu/vulnerabilities/retbleed /sys/devices/system/cpu/vulnerabilities/spec_store_bypass /sys/devices/system/cpu/vulnerabilities/spectre_v1 diff --git a/Documentation/admin-guide/hw-vuln/core-scheduling.rst b/Documentation/admin-guide/hw-vuln/core-scheduling.rst index cf1eeefdfc32f309cbcfc41b78f423b2e2e0cfc0..a92e10ec402e7d6a834976925f57847869771b6e 100644 --- a/Documentation/admin-guide/hw-vuln/core-scheduling.rst +++ b/Documentation/admin-guide/hw-vuln/core-scheduling.rst @@ -67,8 +67,8 @@ arg4: will be performed for all tasks in the task group of ``pid``. arg5: - userspace pointer to an unsigned long for storing the cookie returned by - ``PR_SCHED_CORE_GET`` command. Should be 0 for all other commands. + userspace pointer to an unsigned long long for storing the cookie returned + by ``PR_SCHED_CORE_GET`` command. Should be 0 for all other commands. In order for a process to push a cookie to, or pull a cookie from a process, it is required to have the ptrace access mode: `PTRACE_MODE_READ_REALCREDS` to the diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index 6828102baaa7ae6b2f32a4382d6d6e00c3ab293d..3e4a14e38b49e860b0b2dfebb6c0210e85518fb9 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -21,3 +21,4 @@ are configurable at compile, boot or run time. cross-thread-rsb.rst gather_data_sampling.rst srso + reg-file-data-sampling diff --git a/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst b/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst new file mode 100644 index 0000000000000000000000000000000000000000..0585d02b9a6cbc46a1c61d6d113e2df56f889527 --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst @@ -0,0 +1,104 @@ +================================== +Register File Data Sampling (RFDS) +================================== + +Register File Data Sampling (RFDS) is a microarchitectural vulnerability that +only affects Intel Atom parts(also branded as E-cores). RFDS may allow +a malicious actor to infer data values previously used in floating point +registers, vector registers, or integer registers. RFDS does not provide the +ability to choose which data is inferred. CVE-2023-28746 is assigned to RFDS. + +Affected Processors +=================== +Below is the list of affected Intel processors [#f1]_: + + =================== ============ + Common name Family_Model + =================== ============ + ATOM_GOLDMONT 06_5CH + ATOM_GOLDMONT_D 06_5FH + ATOM_GOLDMONT_PLUS 06_7AH + ATOM_TREMONT_D 06_86H + ATOM_TREMONT 06_96H + ALDERLAKE 06_97H + ALDERLAKE_L 06_9AH + ATOM_TREMONT_L 06_9CH + RAPTORLAKE 06_B7H + RAPTORLAKE_P 06_BAH + ATOM_GRACEMONT 06_BEH + RAPTORLAKE_S 06_BFH + =================== ============ + +As an exception to this table, Intel Xeon E family parts ALDERLAKE(06_97H) and +RAPTORLAKE(06_B7H) codenamed Catlow are not affected. They are reported as +vulnerable in Linux because they share the same family/model with an affected +part. Unlike their affected counterparts, they do not enumerate RFDS_CLEAR or +CPUID.HYBRID. This information could be used to distinguish between the +affected and unaffected parts, but it is deemed not worth adding complexity as +the reporting is fixed automatically when these parts enumerate RFDS_NO. + +Mitigation +========== +Intel released a microcode update that enables software to clear sensitive +information using the VERW instruction. Like MDS, RFDS deploys the same +mitigation strategy to force the CPU to clear the affected buffers before an +attacker can extract the secrets. This is achieved by using the otherwise +unused and obsolete VERW instruction in combination with a microcode update. +The microcode clears the affected CPU buffers when the VERW instruction is +executed. + +Mitigation points +----------------- +VERW is executed by the kernel before returning to user space, and by KVM +before VMentry. None of the affected cores support SMT, so VERW is not required +at C-state transitions. + +New bits in IA32_ARCH_CAPABILITIES +---------------------------------- +Newer processors and microcode update on existing affected processors added new +bits to IA32_ARCH_CAPABILITIES MSR. These bits can be used to enumerate +vulnerability and mitigation capability: + +- Bit 27 - RFDS_NO - When set, processor is not affected by RFDS. +- Bit 28 - RFDS_CLEAR - When set, processor is affected by RFDS, and has the + microcode that clears the affected buffers on VERW execution. + +Mitigation control on the kernel command line +--------------------------------------------- +The kernel command line allows to control RFDS mitigation at boot time with the +parameter "reg_file_data_sampling=". The valid arguments are: + + ========== ================================================================= + on If the CPU is vulnerable, enable mitigation; CPU buffer clearing + on exit to userspace and before entering a VM. + off Disables mitigation. + ========== ================================================================= + +Mitigation default is selected by CONFIG_MITIGATION_RFDS. + +Mitigation status information +----------------------------- +The Linux kernel provides a sysfs interface to enumerate the current +vulnerability status of the system: whether the system is vulnerable, and +which mitigations are active. The relevant sysfs file is: + + /sys/devices/system/cpu/vulnerabilities/reg_file_data_sampling + +The possible values in this file are: + + .. list-table:: + + * - 'Not affected' + - The processor is not vulnerable + * - 'Vulnerable' + - The processor is vulnerable, but no mitigation enabled + * - 'Vulnerable: No microcode' + - The processor is vulnerable but microcode is not updated. + * - 'Mitigation: Clear Register File' + - The processor is vulnerable and the CPU buffer clearing mitigation is + enabled. + +References +---------- +.. [#f1] Affected Processors + https://www.intel.com/content/www/us/en/developer/topic-technology/software-security-guidance/processors-affected-consolidated-product-cpu-model.html diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst index a39bbfe9526b606e4285642b02f556ca5870da1c..e0a1be97fa75985860bbec11d0be2db61ba64790 100644 --- a/Documentation/admin-guide/hw-vuln/spectre.rst +++ b/Documentation/admin-guide/hw-vuln/spectre.rst @@ -138,11 +138,10 @@ associated with the source address of the indirect branch. Specifically, the BHB might be shared across privilege levels even in the presence of Enhanced IBRS. -Currently the only known real-world BHB attack vector is via -unprivileged eBPF. Therefore, it's highly recommended to not enable -unprivileged eBPF, especially when eIBRS is used (without retpolines). -For a full mitigation against BHB attacks, it's recommended to use -retpolines (or eIBRS combined with retpolines). +Previously the only known real-world BHB attack vector was via unprivileged +eBPF. Further research has found attacks that don't require unprivileged eBPF. +For a full mitigation against BHB attacks it is recommended to set BHI_DIS_S or +use the BHB clearing sequence. Attack scenarios ---------------- @@ -430,6 +429,23 @@ The possible values in this file are: 'PBRSB-eIBRS: Not affected' CPU is not affected by PBRSB =========================== ======================================================= + - Branch History Injection (BHI) protection status: + +.. list-table:: + + * - BHI: Not affected + - System is not affected + * - BHI: Retpoline + - System is protected by retpoline + * - BHI: BHI_DIS_S + - System is protected by BHI_DIS_S + * - BHI: SW loop, KVM SW loop + - System is protected by software clearing sequence + * - BHI: Vulnerable + - System is vulnerable to BHI + * - BHI: Vulnerable, KVM: SW loop + - System is vulnerable; KVM is protected by software clearing sequence + Full mitigation might require a microcode update from the CPU vendor. When the necessary microcode is not available, the kernel will report vulnerability. @@ -484,11 +500,18 @@ Spectre variant 2 Systems which support enhanced IBRS (eIBRS) enable IBRS protection once at boot, by setting the IBRS bit, and they're automatically protected against - Spectre v2 variant attacks, including cross-thread branch target injections - on SMT systems (STIBP). In other words, eIBRS enables STIBP too. + some Spectre v2 variant attacks. The BHB can still influence the choice of + indirect branch predictor entry, and although branch predictor entries are + isolated between modes when eIBRS is enabled, the BHB itself is not isolated + between modes. Systems which support BHI_DIS_S will set it to protect against + BHI attacks. - Legacy IBRS systems clear the IBRS bit on exit to userspace and - therefore explicitly enable STIBP for that + On Intel's enhanced IBRS systems, this includes cross-thread branch target + injections on SMT systems (STIBP). In other words, Intel eIBRS enables + STIBP, too. + + AMD Automatic IBRS does not protect userspace, and Legacy IBRS systems clear + the IBRS bit on exit to userspace, therefore both explicitly enable STIBP. The retpoline mitigation is turned on by default on vulnerable CPUs. It can be forced on or off by the administrator @@ -621,9 +644,9 @@ kernel command line. retpoline,generic Retpolines retpoline,lfence LFENCE; indirect branch retpoline,amd alias for retpoline,lfence - eibrs enhanced IBRS - eibrs,retpoline enhanced IBRS + Retpolines - eibrs,lfence enhanced IBRS + LFENCE + eibrs Enhanced/Auto IBRS + eibrs,retpoline Enhanced/Auto IBRS + Retpolines + eibrs,lfence Enhanced/Auto IBRS + LFENCE ibrs use IBRS to protect kernel Not specifying this option is equivalent to @@ -635,6 +658,18 @@ kernel command line. spectre_v2=off. Spectre variant 1 mitigations cannot be disabled. + spectre_bhi= + + [X86] Control mitigation of Branch History Injection + (BHI) vulnerability. This setting affects the deployment + of the HW BHI control and the SW BHB clearing sequence. + + on + (default) Enable the HW or SW mitigation as + needed. + off + Disable the mitigation. + For spectre_v2_user see Documentation/admin-guide/kernel-parameters.txt Mitigation selection guide diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 4ad60e127e048628df61b2b8743f7dd58b60566b..e6f0570cf49002ecb2c91de9612030162bbd2bb9 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1107,6 +1107,26 @@ The filter can be disabled or changed to another driver later using sysfs. + reg_file_data_sampling= + [X86] Controls mitigation for Register File Data + Sampling (RFDS) vulnerability. RFDS is a CPU + vulnerability which may allow userspace to infer + kernel data values previously stored in floating point + registers, vector registers, or integer registers. + RFDS only affects Intel Atom processors. + + on: Turns ON the mitigation. + off: Turns OFF the mitigation. + + This parameter overrides the compile time default set + by CONFIG_MITIGATION_RFDS. Mitigation cannot be + disabled when other VERW based mitigations (like MDS) + are enabled. In order to disable RFDS mitigation all + VERW based mitigations need to be disabled. + + For details see: + Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst + driver_async_probe= [KNL] List of driver names to be probed asynchronously. * matches with all driver names. If * is specified, the @@ -3186,9 +3206,7 @@ mem_encrypt= [X86-64] AMD Secure Memory Encryption (SME) control Valid arguments: on, off - Default (depends on kernel configuration option): - on (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=y) - off (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=n) + Default: off mem_encrypt=on: Activate SME mem_encrypt=off: Do not activate SME @@ -3262,8 +3280,10 @@ nospectre_bhb [ARM64] nospectre_v1 [X86,PPC] nospectre_v2 [X86,PPC,S390,ARM64] + reg_file_data_sampling=off [X86] retbleed=off [X86] spec_store_bypass_disable=off [X86,PPC] + spectre_bhi=off [X86] spectre_v2_user=off [X86] srbds=off [X86,INTEL] ssbd=force-off [ARM64] @@ -5714,6 +5734,15 @@ sonypi.*= [HW] Sony Programmable I/O Control Device driver See Documentation/admin-guide/laptops/sonypi.rst + spectre_bhi= [X86] Control mitigation of Branch History Injection + (BHI) vulnerability. This setting affects the + deployment of the HW BHI control and the SW BHB + clearing sequence. + + on - (default) Enable the HW or SW mitigation + as needed. + off - Disable the mitigation. + spectre_v2= [X86] Control mitigation of Spectre variant 2 (indirect branch speculation) vulnerability. The default operation protects the kernel from @@ -5744,9 +5773,9 @@ retpoline,generic - Retpolines retpoline,lfence - LFENCE; indirect branch retpoline,amd - alias for retpoline,lfence - eibrs - enhanced IBRS - eibrs,retpoline - enhanced IBRS + Retpolines - eibrs,lfence - enhanced IBRS + LFENCE + eibrs - Enhanced/Auto IBRS + eibrs,retpoline - Enhanced/Auto IBRS + Retpolines + eibrs,lfence - Enhanced/Auto IBRS + LFENCE ibrs - use IBRS to protect kernel Not specifying this option is equivalent to @@ -6574,6 +6603,9 @@ pause after every control message); o = USB_QUIRK_HUB_SLOW_RESET (Hub needs extra delay after resetting its port); + p = USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT + (Reduce timeout of the SET_ADDRESS + request from 5000 ms to 500 ms); Example: quirks=0781:5580:bk,0a5c:5834:gij usbhid.mousepoll= diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 6394f5dc2303d4dc0fdb42acafdfce50fc01cef1..e3894c928118ce4a616bf940ebedba5894e182c4 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -205,6 +205,11 @@ Will increase power usage. Default: 0 (off) +mem_pcpu_rsv +------------ + +Per-cpu reserved forward alloc cache size in page units. Default 1MB per CPU. + rmem_default ------------ diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index d9fce65b2f047ca98878487e19e82441dac3f341..27135b9c07acb94741eb83eef69232ffbc414974 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -221,3 +221,10 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Fujitsu | A64FX | E#010001 | FUJITSU_ERRATUM_010001 | +----------------+-----------------+-----------------+-----------------------------+ ++----------------+-----------------+-----------------+-----------------------------+ +| Microsoft | Azure Cobalt 100| #2139208 | ARM64_ERRATUM_2139208 | ++----------------+-----------------+-----------------+-----------------------------+ +| Microsoft | Azure Cobalt 100| #2067961 | ARM64_ERRATUM_2067961 | ++----------------+-----------------+-----------------+-----------------------------+ +| Microsoft | Azure Cobalt 100| #2253138 | ARM64_ERRATUM_2253138 | ++----------------+-----------------+-----------------+-----------------------------+ diff --git a/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml b/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml index c13c10c8d65da26cfc7faa0517f28332a2c9d8ae..eed0df9d3a2322d9818709588ca4c335f5f689d5 100644 --- a/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml +++ b/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml @@ -42,7 +42,7 @@ allOf: properties: compatible: contains: - const: maxim,max30100 + const: maxim,max30102 then: properties: maxim,green-led-current-microamp: false diff --git a/Documentation/devicetree/bindings/net/wireless/marvell-8xxx.txt b/Documentation/devicetree/bindings/net/wireless/marvell-8xxx.txt index 9bf9bbac16e250fdc674c90a7074aa7724d0ce89..cdc303caf5f45cf276420b41cf0651898848b525 100644 --- a/Documentation/devicetree/bindings/net/wireless/marvell-8xxx.txt +++ b/Documentation/devicetree/bindings/net/wireless/marvell-8xxx.txt @@ -1,4 +1,4 @@ -Marvell 8787/8897/8997 (sd8787/sd8897/sd8997/pcie8997) SDIO/PCIE devices +Marvell 8787/8897/8978/8997 (sd8787/sd8897/sd8978/sd8997/pcie8997) SDIO/PCIE devices ------ This node provides properties for controlling the Marvell SDIO/PCIE wireless device. @@ -10,7 +10,9 @@ Required properties: - compatible : should be one of the following: * "marvell,sd8787" * "marvell,sd8897" + * "marvell,sd8978" * "marvell,sd8997" + * "nxp,iw416" * "pci11ab,2b42" * "pci1b4b,2b42" diff --git a/Documentation/sphinx/kernel_include.py b/Documentation/sphinx/kernel_include.py index abe7680883771d49b72d7f382b45ca3e2514df7f..6387624423363d45ec63c36cbe83754bf7b10d21 100755 --- a/Documentation/sphinx/kernel_include.py +++ b/Documentation/sphinx/kernel_include.py @@ -97,7 +97,6 @@ class KernelInclude(Include): # HINT: this is the only line I had to change / commented out: #path = utils.relative_path(None, path) - path = nodes.reprunicode(path) encoding = self.options.get( 'encoding', self.state.document.settings.input_encoding) e_handler=self.state.document.settings.input_encoding_error_handler diff --git a/Documentation/userspace-api/media/mediactl/media-types.rst b/Documentation/userspace-api/media/mediactl/media-types.rst index 0ffeece1e0c8e94c3b25185b1de5ccc15350db52..6332e8395263b04935758d42a17adfe690fcd042 100644 --- a/Documentation/userspace-api/media/mediactl/media-types.rst +++ b/Documentation/userspace-api/media/mediactl/media-types.rst @@ -375,12 +375,11 @@ Types and flags used to represent the media graph elements are origins of links. * - ``MEDIA_PAD_FL_MUST_CONNECT`` - - If this flag is set and the pad is linked to any other pad, then - at least one of those links must be enabled for the entity to be - able to stream. There could be temporary reasons (e.g. device - configuration dependent) for the pad to need enabled links even - when this flag isn't set; the absence of the flag doesn't imply - there is none. + - If this flag is set, then for this pad to be able to stream, it must + be connected by at least one enabled link. There could be temporary + reasons (e.g. device configuration dependent) for the pad to need + enabled links even when this flag isn't set; the absence of the flag + doesn't imply there is none. One and only one of ``MEDIA_PAD_FL_SINK`` and ``MEDIA_PAD_FL_SOURCE`` diff --git a/Documentation/x86/amd-memory-encryption.rst b/Documentation/x86/amd-memory-encryption.rst index 934310ce7258298008e4c6ba5be611105993e1c1..bace87cc9ca2ce74b0db8d3ac705dcf6d69cd999 100644 --- a/Documentation/x86/amd-memory-encryption.rst +++ b/Documentation/x86/amd-memory-encryption.rst @@ -87,14 +87,14 @@ The state of SME in the Linux kernel can be documented as follows: kernel is non-zero). SME can also be enabled and activated in the BIOS. If SME is enabled and -activated in the BIOS, then all memory accesses will be encrypted and it will -not be necessary to activate the Linux memory encryption support. If the BIOS -merely enables SME (sets bit 23 of the MSR_AMD64_SYSCFG), then Linux can activate -memory encryption by default (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=y) or -by supplying mem_encrypt=on on the kernel command line. However, if BIOS does -not enable SME, then Linux will not be able to activate memory encryption, even -if configured to do so by default or the mem_encrypt=on command line parameter -is specified. +activated in the BIOS, then all memory accesses will be encrypted and it +will not be necessary to activate the Linux memory encryption support. + +If the BIOS merely enables SME (sets bit 23 of the MSR_AMD64_SYSCFG), +then memory encryption can be enabled by supplying mem_encrypt=on on the +kernel command line. However, if BIOS does not enable SME, then Linux +will not be able to activate memory encryption, even if configured to do +so by default or the mem_encrypt=on command line parameter is specified. Secure Nested Paging (SNP) ========================== diff --git a/Documentation/x86/boot.rst b/Documentation/x86/boot.rst index 894a198970055a353586dd3b777392406ec232c0..bac3789f3e8fa299ce8304f302a46e8036221bef 100644 --- a/Documentation/x86/boot.rst +++ b/Documentation/x86/boot.rst @@ -1416,7 +1416,7 @@ execution context provided by the EFI firmware. The function prototype for the handover entry point looks like this:: - efi_main(void *handle, efi_system_table_t *table, struct boot_params *bp) + efi_stub_entry(void *handle, efi_system_table_t *table, struct boot_params *bp) 'handle' is the EFI image handle passed to the boot loader by the EFI firmware, 'table' is the EFI system table - these are the first two diff --git a/Documentation/x86/mds.rst b/Documentation/x86/mds.rst index 5d4330be200f980cf4ea7a8e17b9e89012dcc381..e801df0bb3a81a83c2d7676d72982c3d72c33fca 100644 --- a/Documentation/x86/mds.rst +++ b/Documentation/x86/mds.rst @@ -95,6 +95,9 @@ The kernel provides a function to invoke the buffer clearing: mds_clear_cpu_buffers() +Also macro CLEAR_CPU_BUFFERS can be used in ASM late in exit-to-user path. +Other than CFLAGS.ZF, this macro doesn't clobber any registers. + The mitigation is invoked on kernel/userspace, hypervisor/guest and C-state (idle) transitions. @@ -138,17 +141,30 @@ Mitigation points When transitioning from kernel to user space the CPU buffers are flushed on affected CPUs when the mitigation is not disabled on the kernel - command line. The migitation is enabled through the static key - mds_user_clear. - - The mitigation is invoked in prepare_exit_to_usermode() which covers - all but one of the kernel to user space transitions. The exception - is when we return from a Non Maskable Interrupt (NMI), which is - handled directly in do_nmi(). - - (The reason that NMI is special is that prepare_exit_to_usermode() can - enable IRQs. In NMI context, NMIs are blocked, and we don't want to - enable IRQs with NMIs blocked.) + command line. The mitigation is enabled through the feature flag + X86_FEATURE_CLEAR_CPU_BUF. + + The mitigation is invoked just before transitioning to userspace after + user registers are restored. This is done to minimize the window in + which kernel data could be accessed after VERW e.g. via an NMI after + VERW. + + **Corner case not handled** + Interrupts returning to kernel don't clear CPUs buffers since the + exit-to-user path is expected to do that anyways. But, there could be + a case when an NMI is generated in kernel after the exit-to-user path + has cleared the buffers. This case is not handled and NMI returning to + kernel don't clear CPU buffers because: + + 1. It is rare to get an NMI after VERW, but before returning to userspace. + 2. For an unprivileged user, there is no known way to make that NMI + less rare or target it. + 3. It would take a large number of these precisely-timed NMIs to mount + an actual attack. There's presumably not enough bandwidth. + 4. The NMI in question occurs after a VERW, i.e. when user state is + restored and most interesting data is already scrubbed. Whats left + is only the data that NMI touches, and that may or may not be of + any interest. 2. C-State transition diff --git a/MAINTAINERS b/MAINTAINERS index 4405712ba3bdfc35d619313a1e1125880898151d..290eaab35b8b385178de4a424f0758849ef0b15c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8070,7 +8070,7 @@ M: Geoffrey D. Bennett L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git -F: sound/usb/mixer_scarlett_gen2.c +F: sound/usb/mixer_scarlett2.c FORCEDETH GIGABIT ETHERNET DRIVER M: Rain River @@ -10090,6 +10090,7 @@ F: drivers/infiniband/ F: include/rdma/ F: include/trace/events/ib_mad.h F: include/trace/events/ib_umad.h +F: include/trace/misc/rdma.h F: include/uapi/linux/if_infiniband.h F: include/uapi/rdma/ F: samples/bpf/ibumad_kern.c @@ -11178,6 +11179,12 @@ F: fs/nfs_common/ F: fs/nfsd/ F: include/linux/lockd/ F: include/linux/sunrpc/ +F: include/trace/events/rpcgss.h +F: include/trace/events/rpcrdma.h +F: include/trace/events/sunrpc.h +F: include/trace/misc/fs.h +F: include/trace/misc/nfs.h +F: include/trace/misc/sunrpc.h F: include/uapi/linux/nfsd/ F: include/uapi/linux/sunrpc/ F: net/sunrpc/ @@ -22638,6 +22645,7 @@ F: include/xen/swiotlb-xen.h XFS FILESYSTEM C: irc://irc.oftc.net/xfs +M: Leah Rumancik M: Darrick J. Wong L: linux-xfs@vger.kernel.org S: Supported diff --git a/Makefile b/Makefile index f5598d90093f53895f17da57242663a1a5b87e7a..0be668057cb2ae4dd6bd4c851df426688766e2f0 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 77 +SUBLEVEL = 92 EXTRAVERSION = NAME = Curry Ramen @@ -459,8 +459,7 @@ HOSTRUSTC = rustc HOSTPKG_CONFIG = pkg-config KBUILD_USERHOSTCFLAGS := -Wall -Wmissing-prototypes -Wstrict-prototypes \ - -O2 -fomit-frame-pointer -std=gnu11 \ - -Wdeclaration-after-statement + -O2 -fomit-frame-pointer -std=gnu11 KBUILD_USERCFLAGS := $(KBUILD_USERHOSTCFLAGS) $(USERCFLAGS) KBUILD_USERLDFLAGS := $(USERLDFLAGS) @@ -1018,9 +1017,6 @@ endif # arch Makefile may override CC so keep this after arch Makefile is included NOSTDINC_FLAGS += -nostdinc -# warn about C99 declaration after statement -KBUILD_CFLAGS += -Wdeclaration-after-statement - # Variable Length Arrays (VLAs) should not be used anywhere in the kernel KBUILD_CFLAGS += -Wvla diff --git a/arch/Kconfig b/arch/Kconfig index 14273a6203dfcf759b8db02c9410392980571393..e959abf969ec319ed627b0b9b898435a07e50af0 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -9,6 +9,14 @@ # source "arch/$(SRCARCH)/Kconfig" +config ARCH_CONFIGURES_CPU_MITIGATIONS + bool + +if !ARCH_CONFIGURES_CPU_MITIGATIONS +config CPU_MITIGATIONS + def_bool y +endif + menu "General architecture-dependent options" config CRASH_CORE @@ -642,6 +650,7 @@ config SHADOW_CALL_STACK bool "Shadow Call Stack" depends on ARCH_SUPPORTS_SHADOW_CALL_STACK depends on DYNAMIC_FTRACE_WITH_ARGS || DYNAMIC_FTRACE_WITH_REGS || !FUNCTION_GRAPH_TRACER + depends on MMU help This option enables the compiler's Shadow Call Stack, which uses a shadow stack to protect function return addresses from diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index 6691f42550778853f2917a2d18347fd4c05f0488..41b980df862b14aa2a97867d05051f0f29434b65 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -205,7 +205,6 @@ }; gmac: ethernet@8000 { - #interrupt-cells = <1>; compatible = "snps,dwmac"; reg = <0x8000 0x2000>; interrupts = <10>; diff --git a/arch/arc/include/asm/jump_label.h b/arch/arc/include/asm/jump_label.h index 9d96180797396bba26ace54f047f7a47bf82dd5f..a339223d9e052b35ea678d6a3e60faf6e5673671 100644 --- a/arch/arc/include/asm/jump_label.h +++ b/arch/arc/include/asm/jump_label.h @@ -31,7 +31,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" + asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" "1: \n" "nop \n" ".pushsection __jump_table, \"aw\" \n" @@ -47,7 +47,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" + asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" "1: \n" "b %l[l_yes] \n" ".pushsection __jump_table, \"aw\" \n" diff --git a/arch/arm/boot/dts/arm-realview-pb1176.dts b/arch/arm/boot/dts/arm-realview-pb1176.dts index efed325af88d206fc5cc6f4d9b6e6d7f4f05cb77..d99bac02232b3703a04b8d03f36cf5eb12bd9f4e 100644 --- a/arch/arm/boot/dts/arm-realview-pb1176.dts +++ b/arch/arm/boot/dts/arm-realview-pb1176.dts @@ -451,7 +451,7 @@ /* Direct-mapped development chip ROM */ pb1176_rom@10200000 { - compatible = "direct-mapped"; + compatible = "mtd-rom"; reg = <0x10200000 0x4000>; bank-width = <1>; }; diff --git a/arch/arm/boot/dts/at91-sama7g5ek.dts b/arch/arm/boot/dts/at91-sama7g5ek.dts index 4af8a1c96ed6342371b5a12dd25fd1834f8dedce..bede6e88ae11020ab0c0016d074f21318063af13 100644 --- a/arch/arm/boot/dts/at91-sama7g5ek.dts +++ b/arch/arm/boot/dts/at91-sama7g5ek.dts @@ -293,7 +293,7 @@ regulator-state-standby { regulator-on-in-suspend; - regulator-suspend-voltage = <1150000>; + regulator-suspend-microvolt = <1150000>; regulator-mode = <4>; }; @@ -314,7 +314,7 @@ regulator-state-standby { regulator-on-in-suspend; - regulator-suspend-voltage = <1050000>; + regulator-suspend-microvolt = <1050000>; regulator-mode = <4>; }; @@ -331,7 +331,7 @@ regulator-always-on; regulator-state-standby { - regulator-suspend-voltage = <1800000>; + regulator-suspend-microvolt = <1800000>; regulator-on-in-suspend; }; @@ -346,7 +346,7 @@ regulator-max-microvolt = <3700000>; regulator-state-standby { - regulator-suspend-voltage = <1800000>; + regulator-suspend-microvolt = <1800000>; regulator-on-in-suspend; }; diff --git a/arch/arm/boot/dts/imx23.dtsi b/arch/arm/boot/dts/imx23.dtsi index ec476b15964961cbfef668427e31b7eea0654874..b236d23f8071590f4e1af94f5553a6aeecfa9393 100644 --- a/arch/arm/boot/dts/imx23.dtsi +++ b/arch/arm/boot/dts/imx23.dtsi @@ -59,7 +59,7 @@ reg = <0x80000000 0x2000>; }; - dma_apbh: dma-apbh@80004000 { + dma_apbh: dma-controller@80004000 { compatible = "fsl,imx23-dma-apbh"; reg = <0x80004000 0x2000>; interrupts = <0 14 20 0 diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi index b15df16ecb01a748ff99ae2ae00e38efd669640f..b81592a6131121ffc7fccaee2e87e1fa5c6a089c 100644 --- a/arch/arm/boot/dts/imx28.dtsi +++ b/arch/arm/boot/dts/imx28.dtsi @@ -78,7 +78,7 @@ status = "disabled"; }; - dma_apbh: dma-apbh@80004000 { + dma_apbh: dma-controller@80004000 { compatible = "fsl,imx28-dma-apbh"; reg = <0x80004000 0x2000>; interrupts = <82 83 84 85 diff --git a/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi b/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi index aacbf317feea61aca221d7005519f278988b55a3..4b7aee895892397025cf49f518cd7b9181886296 100644 --- a/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi +++ b/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi @@ -106,8 +106,6 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; phy-mode = "rgmii-id"; - phy-reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>; - phy-reset-duration = <20>; phy-supply = <&sw2_reg>; status = "okay"; @@ -120,17 +118,10 @@ #address-cells = <1>; #size-cells = <0>; - phy_port2: phy@1 { - reg = <1>; - }; - - phy_port3: phy@2 { - reg = <2>; - }; - switch@10 { compatible = "qca,qca8334"; - reg = <10>; + reg = <0x10>; + reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>; switch_ports: ports { #address-cells = <1>; @@ -151,15 +142,30 @@ eth2: port@2 { reg = <2>; label = "eth2"; + phy-mode = "internal"; phy-handle = <&phy_port2>; }; eth1: port@3 { reg = <3>; label = "eth1"; + phy-mode = "internal"; phy-handle = <&phy_port3>; }; }; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + phy_port2: ethernet-phy@1 { + reg = <1>; + }; + + phy_port3: ethernet-phy@2 { + reg = <2>; + }; + }; }; }; }; diff --git a/arch/arm/boot/dts/imx6q-apalis-ixora-v1.2.dts b/arch/arm/boot/dts/imx6q-apalis-ixora-v1.2.dts index f9f7d99bd4db8516716423927e455daea8db315e..76f3e07bc88266716dfb2c287ed13882dfd08c38 100644 --- a/arch/arm/boot/dts/imx6q-apalis-ixora-v1.2.dts +++ b/arch/arm/boot/dts/imx6q-apalis-ixora-v1.2.dts @@ -76,6 +76,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enable_can1_power>; regulator-name = "can1_supply"; + startup-delay-us = <1000>; }; reg_can2_supply: regulator-can2-supply { @@ -85,6 +86,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enable_can2_power>; regulator-name = "can2_supply"; + startup-delay-us = <1000>; }; }; diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi index ff1e0173b39be7d7986cc5a936a3d5513b6692b6..2c6eada01d7927db4e85b8a5c1a439a3fac922d8 100644 --- a/arch/arm/boot/dts/imx6qdl.dtsi +++ b/arch/arm/boot/dts/imx6qdl.dtsi @@ -150,7 +150,7 @@ interrupt-parent = <&gpc>; ranges; - dma_apbh: dma-apbh@110000 { + dma_apbh: dma-controller@110000 { compatible = "fsl,imx6q-dma-apbh", "fsl,imx28-dma-apbh"; reg = <0x00110000 0x2000>; interrupts = <0 13 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi index 1f1053a898fbf4608cbcf5b1c9a25997690b8f71..67d344ae76b515bd651b6354f6feb3615e3f57a7 100644 --- a/arch/arm/boot/dts/imx6sx.dtsi +++ b/arch/arm/boot/dts/imx6sx.dtsi @@ -209,7 +209,7 @@ power-domains = <&pd_pu>; }; - dma_apbh: dma-apbh@1804000 { + dma_apbh: dma-controller@1804000 { compatible = "fsl,imx6sx-dma-apbh", "fsl,imx28-dma-apbh"; reg = <0x01804000 0x2000>; interrupts = , diff --git a/arch/arm/boot/dts/imx6ul.dtsi b/arch/arm/boot/dts/imx6ul.dtsi index 2b5996395701a07b12a13b1294eb7d782d9ef25a..aac081b6daaac027e43fe25e27e6319a95da60fc 100644 --- a/arch/arm/boot/dts/imx6ul.dtsi +++ b/arch/arm/boot/dts/imx6ul.dtsi @@ -164,7 +164,7 @@ <0x00a06000 0x2000>; }; - dma_apbh: dma-apbh@1804000 { + dma_apbh: dma-controller@1804000 { compatible = "fsl,imx6q-dma-apbh", "fsl,imx28-dma-apbh"; reg = <0x01804000 0x2000>; interrupts = <0 13 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index 4b23630fc738d5e88de30adc188bed38c4362cba..69aebc691526f904fda9d9c4dd09beaf0ccbd00f 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -1267,14 +1267,13 @@ }; }; - dma_apbh: dma-apbh@33000000 { + dma_apbh: dma-controller@33000000 { compatible = "fsl,imx7d-dma-apbh", "fsl,imx28-dma-apbh"; reg = <0x33000000 0x2000>; interrupts = , , , ; - interrupt-names = "gpmi0", "gpmi1", "gpmi2", "gpmi3"; #dma-cells = <1>; dma-channels = <4>; clocks = <&clks IMX7D_NAND_USDHC_BUS_RAWNAND_CLK>; diff --git a/arch/arm/boot/dts/mmp2-brownstone.dts b/arch/arm/boot/dts/mmp2-brownstone.dts index 04f1ae1382e7a357ed51bd455154abf3f1a6de61..bc64348b8218519620bf22acbef2fd2f038ae608 100644 --- a/arch/arm/boot/dts/mmp2-brownstone.dts +++ b/arch/arm/boot/dts/mmp2-brownstone.dts @@ -28,7 +28,7 @@ &twsi1 { status = "okay"; pmic: max8925@3c { - compatible = "maxium,max8925"; + compatible = "maxim,max8925"; reg = <0x3c>; interrupts = <1>; interrupt-parent = <&intcmux4>; diff --git a/arch/arm/boot/dts/qcom-msm8974.dtsi b/arch/arm/boot/dts/qcom-msm8974.dtsi index c4b2e9ac24940c4b0942c1f4ef2aa7a37b8d8346..5ea45e486ed544daf0118dcb1d5176ac861a3a59 100644 --- a/arch/arm/boot/dts/qcom-msm8974.dtsi +++ b/arch/arm/boot/dts/qcom-msm8974.dtsi @@ -1134,7 +1134,7 @@ qfprom: qfprom@fc4bc000 { compatible = "qcom,msm8974-qfprom", "qcom,qfprom"; - reg = <0xfc4bc000 0x1000>; + reg = <0xfc4bc000 0x2100>; #address-cells = <1>; #size-cells = <1>; tsens_calib: calib@d0 { diff --git a/arch/arm/boot/dts/r8a73a4-ape6evm.dts b/arch/arm/boot/dts/r8a73a4-ape6evm.dts index e81a7213d3047753978e476cae8c1884c11360b1..4282bafbb504319a1d0aa58948aa58caea1b523a 100644 --- a/arch/arm/boot/dts/r8a73a4-ape6evm.dts +++ b/arch/arm/boot/dts/r8a73a4-ape6evm.dts @@ -209,6 +209,18 @@ status = "okay"; }; +&extal1_clk { + clock-frequency = <26000000>; +}; + +&extal2_clk { + clock-frequency = <48000000>; +}; + +&extalr_clk { + clock-frequency = <32768>; +}; + &pfc { scifa0_pins: scifa0 { groups = "scifa0_data"; diff --git a/arch/arm/boot/dts/r8a73a4.dtsi b/arch/arm/boot/dts/r8a73a4.dtsi index c39066967053f06b37e879ce4c147172ec249d7f..d1f4cbd099efb470fe3be42bd9e54c6acbbd5cf5 100644 --- a/arch/arm/boot/dts/r8a73a4.dtsi +++ b/arch/arm/boot/dts/r8a73a4.dtsi @@ -450,17 +450,20 @@ extalr_clk: extalr { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <32768>; + /* This value must be overridden by the board. */ + clock-frequency = <0>; }; extal1_clk: extal1 { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <25000000>; + /* This value must be overridden by the board. */ + clock-frequency = <0>; }; extal2_clk: extal2 { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <48000000>; + /* This value must be overridden by the board. */ + clock-frequency = <0>; }; fsiack_clk: fsiack { compatible = "fixed-clock"; diff --git a/arch/arm/crypto/sha256_glue.c b/arch/arm/crypto/sha256_glue.c index 433ee4ddce6c81721978306b547d08693adf4643..f85933fdec75fd3ab627ebb02641debfefe46668 100644 --- a/arch/arm/crypto/sha256_glue.c +++ b/arch/arm/crypto/sha256_glue.c @@ -24,8 +24,8 @@ #include "sha256_glue.h" -asmlinkage void sha256_block_data_order(u32 *digest, const void *data, - unsigned int num_blks); +asmlinkage void sha256_block_data_order(struct sha256_state *state, + const u8 *data, int num_blks); int crypto_sha256_arm_update(struct shash_desc *desc, const u8 *data, unsigned int len) @@ -33,23 +33,20 @@ int crypto_sha256_arm_update(struct shash_desc *desc, const u8 *data, /* make sure casting to sha256_block_fn() is safe */ BUILD_BUG_ON(offsetof(struct sha256_state, state) != 0); - return sha256_base_do_update(desc, data, len, - (sha256_block_fn *)sha256_block_data_order); + return sha256_base_do_update(desc, data, len, sha256_block_data_order); } EXPORT_SYMBOL(crypto_sha256_arm_update); static int crypto_sha256_arm_final(struct shash_desc *desc, u8 *out) { - sha256_base_do_finalize(desc, - (sha256_block_fn *)sha256_block_data_order); + sha256_base_do_finalize(desc, sha256_block_data_order); return sha256_base_finish(desc, out); } int crypto_sha256_arm_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { - sha256_base_do_update(desc, data, len, - (sha256_block_fn *)sha256_block_data_order); + sha256_base_do_update(desc, data, len, sha256_block_data_order); return crypto_sha256_arm_final(desc, out); } EXPORT_SYMBOL(crypto_sha256_arm_finup); diff --git a/arch/arm/crypto/sha512-glue.c b/arch/arm/crypto/sha512-glue.c index 0635a65aa488ba201a10f19fea35fe8e551ccf8f..1be5bd498af36fb710d671228326af983e811903 100644 --- a/arch/arm/crypto/sha512-glue.c +++ b/arch/arm/crypto/sha512-glue.c @@ -25,27 +25,25 @@ MODULE_ALIAS_CRYPTO("sha512"); MODULE_ALIAS_CRYPTO("sha384-arm"); MODULE_ALIAS_CRYPTO("sha512-arm"); -asmlinkage void sha512_block_data_order(u64 *state, u8 const *src, int blocks); +asmlinkage void sha512_block_data_order(struct sha512_state *state, + u8 const *src, int blocks); int sha512_arm_update(struct shash_desc *desc, const u8 *data, unsigned int len) { - return sha512_base_do_update(desc, data, len, - (sha512_block_fn *)sha512_block_data_order); + return sha512_base_do_update(desc, data, len, sha512_block_data_order); } static int sha512_arm_final(struct shash_desc *desc, u8 *out) { - sha512_base_do_finalize(desc, - (sha512_block_fn *)sha512_block_data_order); + sha512_base_do_finalize(desc, sha512_block_data_order); return sha512_base_finish(desc, out); } int sha512_arm_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { - sha512_base_do_update(desc, data, len, - (sha512_block_fn *)sha512_block_data_order); + sha512_base_do_update(desc, data, len, sha512_block_data_order); return sha512_arm_final(desc, out); } diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h index e12d7d096fc034058bfaa094bf9b314a2a7a983d..e4eb54f6cd9fef41fecad56e25c4136e75455756 100644 --- a/arch/arm/include/asm/jump_label.h +++ b/arch/arm/include/asm/jump_label.h @@ -11,7 +11,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" WASM(nop) "\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".word 1b, %l[l_yes], %c0\n\t" @@ -25,7 +25,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" WASM(b) " %l[l_yes]\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".word 1b, %l[l_yes], %c0\n\t" diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index a86a1d4f34618ce3a5b91157d209f8b879cb47ae..93afd1005b43c9ed7cc97c410b792c1fa877a38d 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -127,6 +127,10 @@ cpu_resume_after_mmu: instr_sync #endif bl cpu_init @ restore the und/abt/irq banked regs +#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK) + mov r0, sp + bl kasan_unpoison_task_stack_below +#endif mov r0, #0 @ return zero on success ldmfd sp!, {r4 - r11, pc} ENDPROC(cpu_resume_after_mmu) diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c index 95e731676cea4f1e84d300e245ce3655eb8010c0..961daac6532614ce930cc2588111e742d4a757c8 100644 --- a/arch/arm/mach-ep93xx/core.c +++ b/arch/arm/mach-ep93xx/core.c @@ -339,6 +339,7 @@ static struct gpiod_lookup_table ep93xx_i2c_gpiod_table = { GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN), GPIO_LOOKUP_IDX("G", 0, NULL, 1, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN), + { } }, }; diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c index 5e86145db0e2ac9e8b8ac769ea3ccc122e293935..8897364e550ba980f0c8b59c0884b42324df57ea 100644 --- a/arch/arm/mach-omap2/board-n8x0.c +++ b/arch/arm/mach-omap2/board-n8x0.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include @@ -567,10 +566,6 @@ struct menelaus_platform_data n8x0_menelaus_platform_data = { .late_init = n8x0_menelaus_late_init, }; -struct aic3x_pdata n810_aic33_data = { - .gpio_reset = 118, -}; - static int __init n8x0_late_initcall(void) { if (!board_caps) diff --git a/arch/arm/mach-omap2/common-board-devices.h b/arch/arm/mach-omap2/common-board-devices.h index b23962c38fb271a7841c629f6a019c748487f8a3..69694af7147514d562e85d02854fff91a21b6371 100644 --- a/arch/arm/mach-omap2/common-board-devices.h +++ b/arch/arm/mach-omap2/common-board-devices.h @@ -2,12 +2,10 @@ #ifndef __OMAP_COMMON_BOARD_DEVICES__ #define __OMAP_COMMON_BOARD_DEVICES__ -#include #include void *n8x0_legacy_init(void); extern struct menelaus_platform_data n8x0_menelaus_platform_data; -extern struct aic3x_pdata n810_aic33_data; #endif /* __OMAP_COMMON_BOARD_DEVICES__ */ diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c index 5b99d602c87bc9dd61aee6a292343768b50166ff..9deba798cc91916ba09cf21de1a806cc7c60c061 100644 --- a/arch/arm/mach-omap2/pdata-quirks.c +++ b/arch/arm/mach-omap2/pdata-quirks.c @@ -440,7 +440,6 @@ static struct of_dev_auxdata omap_auxdata_lookup[] = { #ifdef CONFIG_MACH_NOKIA_N8X0 OF_DEV_AUXDATA("ti,omap2420-mmc", 0x4809c000, "mmci-omap.0", NULL), OF_DEV_AUXDATA("menelaus", 0x72, "1-0072", &n8x0_menelaus_platform_data), - OF_DEV_AUXDATA("tlv320aic3x", 0x18, "2-0018", &n810_aic33_data), #endif #ifdef CONFIG_ARCH_OMAP3 OF_DEV_AUXDATA("ti,omap2-iommu", 0x5d000000, "5d000000.mmu", diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index c15f71501c6c2d7552ca86fb5753e22ba90b2679..044b98a62f7bbcdddb08d278311e28f1dae9c3d1 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1752,7 +1752,6 @@ config ARM64_LSE_ATOMICS config ARM64_USE_LSE_ATOMICS bool "Atomic instructions" - depends on JUMP_LABEL default y help As part of the Large System Extensions, ARMv8.1 introduces new diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts index 9ec49ac2f6fd5dbc13c8694473c66bcde10cff81..381d58cea092d9f8dadfe6f37ba2caa52d700c1c 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts @@ -291,6 +291,8 @@ }; &spdif { + pinctrl-names = "default"; + pinctrl-0 = <&spdif_tx_pin>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-tanix.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6-tanix.dtsi index 4903d6358112def0c27c224c9757e7505bda75be..855b7d43bc503ab3b2a042ef51f31d54a9dbaf1d 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-tanix.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-tanix.dtsi @@ -166,6 +166,8 @@ }; &spdif { + pinctrl-names = "default"; + pinctrl-0 = <&spdif_tx_pin>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi index ca1d287a0a01d981f12cccf5f990303085a60462..d11e5041bae9a470242e0226ecde743dd1b72fa7 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi @@ -406,6 +406,7 @@ function = "spi1"; }; + /omit-if-no-ref/ spdif_tx_pin: spdif-tx-pin { pins = "PH7"; function = "spdif"; @@ -655,10 +656,8 @@ clocks = <&ccu CLK_BUS_SPDIF>, <&ccu CLK_SPDIF>; clock-names = "apb", "spdif"; resets = <&ccu RST_BUS_SPDIF>; - dmas = <&dma 2>; - dma-names = "tx"; - pinctrl-names = "default"; - pinctrl-0 = <&spdif_tx_pin>; + dmas = <&dma 2>, <&dma 2>; + dma-names = "rx", "tx"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/amazon/alpine-v2.dtsi b/arch/arm64/boot/dts/amazon/alpine-v2.dtsi index 4eb2cd14e00b0f8e768ef74a6fb3a5d012bb55a0..9b6da84deae7a4b81d991f1700af97f4b1fbc08a 100644 --- a/arch/arm64/boot/dts/amazon/alpine-v2.dtsi +++ b/arch/arm64/boot/dts/amazon/alpine-v2.dtsi @@ -145,7 +145,6 @@ msix: msix@fbe00000 { compatible = "al,alpine-msix"; reg = <0x0 0xfbe00000 0x0 0x100000>; - interrupt-controller; msi-controller; al,msi-base-spi = <160>; al,msi-num-spis = <160>; diff --git a/arch/arm64/boot/dts/amazon/alpine-v3.dtsi b/arch/arm64/boot/dts/amazon/alpine-v3.dtsi index 73a352ea8fd5c2402e5ccbdee739f744e129d94c..b30014d4dc29c3efcdd55a0f18c59e76946110d5 100644 --- a/arch/arm64/boot/dts/amazon/alpine-v3.dtsi +++ b/arch/arm64/boot/dts/amazon/alpine-v3.dtsi @@ -351,7 +351,6 @@ msix: msix@fbe00000 { compatible = "al,alpine-msix"; reg = <0x0 0xfbe00000 0x0 0x100000>; - interrupt-controller; msi-controller; al,msi-base-spi = <336>; al,msi-num-spis = <959>; diff --git a/arch/arm64/boot/dts/broadcom/bcmbca/bcm4908.dtsi b/arch/arm64/boot/dts/broadcom/bcmbca/bcm4908.dtsi index df71348542064fbcc1863969d2e33d1a55218195..a4c5a38905b038ff6c345a18772e8115a8d9deca 100644 --- a/arch/arm64/boot/dts/broadcom/bcmbca/bcm4908.dtsi +++ b/arch/arm64/boot/dts/broadcom/bcmbca/bcm4908.dtsi @@ -180,9 +180,6 @@ brcm,num-gphy = <5>; brcm,num-rgmii-ports = <2>; - #address-cells = <1>; - #size-cells = <0>; - ports: ports { #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi index fda97c47f4e972532229455fc5ee413e19800d39..d5778417455c012841c332b8e387ebfe617f88f5 100644 --- a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi +++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi @@ -584,6 +584,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; interrupts = ; }; diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi index 8f8c25e51194de833aa75e4327100bc93967a01c..473d7d0ddf369c9e51cbb2da0ff89870b1ed116d 100644 --- a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi +++ b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi @@ -442,6 +442,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; interrupts = ; gpio-ranges = <&pinmux 0 0 16>, <&pinmux 16 71 2>, diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi index 10370d1a6c6defebd3b83e83f3188d79473eefc2..dbb298b907c1c08c3afcb7bf23dfbb0ae52b3fd5 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi @@ -38,8 +38,8 @@ conn_subsys: bus@5b000000 { interrupts = ; reg = <0x5b010000 0x10000>; clocks = <&sdhc0_lpcg IMX_LPCG_CLK_4>, - <&sdhc0_lpcg IMX_LPCG_CLK_0>, - <&sdhc0_lpcg IMX_LPCG_CLK_5>; + <&sdhc0_lpcg IMX_LPCG_CLK_5>, + <&sdhc0_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_0>; status = "disabled"; @@ -49,8 +49,8 @@ conn_subsys: bus@5b000000 { interrupts = ; reg = <0x5b020000 0x10000>; clocks = <&sdhc1_lpcg IMX_LPCG_CLK_4>, - <&sdhc1_lpcg IMX_LPCG_CLK_0>, - <&sdhc1_lpcg IMX_LPCG_CLK_5>; + <&sdhc1_lpcg IMX_LPCG_CLK_5>, + <&sdhc1_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_1>; fsl,tuning-start-tap = <20>; @@ -62,8 +62,8 @@ conn_subsys: bus@5b000000 { interrupts = ; reg = <0x5b030000 0x10000>; clocks = <&sdhc2_lpcg IMX_LPCG_CLK_4>, - <&sdhc2_lpcg IMX_LPCG_CLK_0>, - <&sdhc2_lpcg IMX_LPCG_CLK_5>; + <&sdhc2_lpcg IMX_LPCG_CLK_5>, + <&sdhc2_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_2>; status = "disabled"; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl-osm-s.dts b/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl-osm-s.dts index 8b16bd68576c0b51d67320ab4a015068834d881b..d9fa0deea7002e5e32a8f5106fd0516a83cfc009 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl-osm-s.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl-osm-s.dts @@ -294,8 +294,8 @@ pinctrl_i2c4: i2c4grp { fsl,pins = < - MX8MM_IOMUXC_I2C4_SCL_I2C4_SCL 0x400001c3 - MX8MM_IOMUXC_I2C4_SDA_I2C4_SDA 0x400001c3 + MX8MM_IOMUXC_I2C4_SCL_I2C4_SCL 0x40000083 + MX8MM_IOMUXC_I2C4_SDA_I2C4_SDA 0x40000083 >; }; @@ -313,19 +313,19 @@ pinctrl_uart1: uart1grp { fsl,pins = < - MX8MM_IOMUXC_SAI2_RXC_UART1_DCE_RX 0x140 - MX8MM_IOMUXC_SAI2_RXFS_UART1_DCE_TX 0x140 - MX8MM_IOMUXC_SAI2_RXD0_UART1_DCE_RTS_B 0x140 - MX8MM_IOMUXC_SAI2_TXFS_UART1_DCE_CTS_B 0x140 + MX8MM_IOMUXC_SAI2_RXC_UART1_DCE_RX 0x0 + MX8MM_IOMUXC_SAI2_RXFS_UART1_DCE_TX 0x0 + MX8MM_IOMUXC_SAI2_RXD0_UART1_DCE_RTS_B 0x0 + MX8MM_IOMUXC_SAI2_TXFS_UART1_DCE_CTS_B 0x0 >; }; pinctrl_uart2: uart2grp { fsl,pins = < - MX8MM_IOMUXC_SAI3_TXFS_UART2_DCE_RX 0x140 - MX8MM_IOMUXC_SAI3_TXC_UART2_DCE_TX 0x140 - MX8MM_IOMUXC_SAI3_RXD_UART2_DCE_RTS_B 0x140 - MX8MM_IOMUXC_SAI3_RXC_UART2_DCE_CTS_B 0x140 + MX8MM_IOMUXC_SAI3_TXFS_UART2_DCE_RX 0x0 + MX8MM_IOMUXC_SAI3_TXC_UART2_DCE_TX 0x0 + MX8MM_IOMUXC_SAI3_RXD_UART2_DCE_RTS_B 0x0 + MX8MM_IOMUXC_SAI3_RXC_UART2_DCE_CTS_B 0x0 >; }; @@ -337,40 +337,40 @@ pinctrl_usdhc2: usdhc2grp { fsl,pins = < - MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x190 + MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x90 MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x1d0 MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x1d0 MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1 0x1d0 MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2 0x1d0 MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3 0x1d0 - MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x019 - MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x1d0 + MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x19 + MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0xd0 >; }; pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp { fsl,pins = < - MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x194 + MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x94 MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x1d4 MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x1d4 MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1 0x1d4 MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2 0x1d4 MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3 0x1d4 - MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x019 - MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x1d0 + MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x19 + MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0xd0 >; }; pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp { fsl,pins = < - MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x196 + MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x96 MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x1d6 MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x1d6 MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1 0x1d6 MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2 0x1d6 MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3 0x1d6 - MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x019 - MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x1d0 + MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x19 + MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0xd0 >; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl.dts b/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl.dts index a079322a37931ec7726cd6bac4c5eb0e4c7bc64c..d54cddd65b526c465229143a6f1048dcee89c97c 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl.dts @@ -277,8 +277,8 @@ pinctrl_i2c4: i2c4grp { fsl,pins = < - MX8MM_IOMUXC_I2C4_SCL_I2C4_SCL 0x400001c3 - MX8MM_IOMUXC_I2C4_SDA_I2C4_SDA 0x400001c3 + MX8MM_IOMUXC_I2C4_SCL_I2C4_SCL 0x40000083 + MX8MM_IOMUXC_I2C4_SDA_I2C4_SDA 0x40000083 >; }; @@ -290,19 +290,19 @@ pinctrl_uart1: uart1grp { fsl,pins = < - MX8MM_IOMUXC_SAI2_RXC_UART1_DCE_RX 0x140 - MX8MM_IOMUXC_SAI2_RXFS_UART1_DCE_TX 0x140 - MX8MM_IOMUXC_SAI2_RXD0_UART1_DCE_RTS_B 0x140 - MX8MM_IOMUXC_SAI2_TXFS_UART1_DCE_CTS_B 0x140 + MX8MM_IOMUXC_SAI2_RXC_UART1_DCE_RX 0x0 + MX8MM_IOMUXC_SAI2_RXFS_UART1_DCE_TX 0x0 + MX8MM_IOMUXC_SAI2_RXD0_UART1_DCE_RTS_B 0x0 + MX8MM_IOMUXC_SAI2_TXFS_UART1_DCE_CTS_B 0x0 >; }; pinctrl_uart2: uart2grp { fsl,pins = < - MX8MM_IOMUXC_SAI3_TXFS_UART2_DCE_RX 0x140 - MX8MM_IOMUXC_SAI3_TXC_UART2_DCE_TX 0x140 - MX8MM_IOMUXC_SAI3_RXD_UART2_DCE_RTS_B 0x140 - MX8MM_IOMUXC_SAI3_RXC_UART2_DCE_CTS_B 0x140 + MX8MM_IOMUXC_SAI3_TXFS_UART2_DCE_RX 0x0 + MX8MM_IOMUXC_SAI3_TXC_UART2_DCE_TX 0x0 + MX8MM_IOMUXC_SAI3_RXD_UART2_DCE_RTS_B 0x0 + MX8MM_IOMUXC_SAI3_RXC_UART2_DCE_CTS_B 0x0 >; }; @@ -314,40 +314,40 @@ pinctrl_usdhc2: usdhc2grp { fsl,pins = < - MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x190 + MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x90 MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x1d0 MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x1d0 MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1 0x1d0 MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2 0x1d0 MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3 0x1d0 - MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x019 - MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x1d0 + MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x19 + MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0xd0 >; }; pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp { fsl,pins = < - MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x194 + MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x94 MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x1d4 MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x1d4 MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1 0x1d4 MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2 0x1d4 MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3 0x1d4 - MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x019 - MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x1d0 + MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x19 + MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0xd0 >; }; pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp { fsl,pins = < - MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x196 + MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x96 MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x1d6 MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x1d6 MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1 0x1d6 MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2 0x1d6 MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3 0x1d6 - MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x019 - MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x1d0 + MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x19 + MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0xd0 >; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-osm-s.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-kontron-osm-s.dtsi index 8d10f5b412978b017f42e63d5746b247f46667d5..d5199ecb3f6c1538c6a43b8cd7459728f45ab46f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-osm-s.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-osm-s.dtsi @@ -205,7 +205,7 @@ reg = <0x52>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_rtc>; - interrupts-extended = <&gpio4 1 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&gpio4 1 IRQ_TYPE_LEVEL_LOW>; trickle-diode-disable; }; }; @@ -247,8 +247,8 @@ pinctrl_i2c1: i2c1grp { fsl,pins = < - MX8MM_IOMUXC_I2C1_SCL_I2C1_SCL 0x400001c3 - MX8MM_IOMUXC_I2C1_SDA_I2C1_SDA 0x400001c3 + MX8MM_IOMUXC_I2C1_SCL_I2C1_SCL 0x40000083 + MX8MM_IOMUXC_I2C1_SDA_I2C1_SDA 0x40000083 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-sl.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-kontron-sl.dtsi index 0679728d2489919ab4ffd30bb1c8d807d3d63003..884ae2ad3511466bfc38b49d946f7efc519a18fd 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-sl.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-sl.dtsi @@ -237,8 +237,8 @@ pinctrl_i2c1: i2c1grp { fsl,pins = < - MX8MM_IOMUXC_I2C1_SCL_I2C1_SCL 0x400001c3 - MX8MM_IOMUXC_I2C1_SDA_I2C1_SDA 0x400001c3 + MX8MM_IOMUXC_I2C1_SCL_I2C1_SCL 0x40000083 + MX8MM_IOMUXC_I2C1_SDA_I2C1_SDA 0x40000083 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi index c557dbf4dcd609e22f879ef8b41e5b5c4d14909e..2e90466db89a0296a36cbca773e95448ec87e541 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi @@ -47,17 +47,6 @@ gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>; status = "okay"; }; - - reg_usb_otg1_vbus: regulator-usb-otg1 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_reg_usb1_en>; - compatible = "regulator-fixed"; - regulator-name = "usb_otg1_vbus"; - gpio = <&gpio1 10 GPIO_ACTIVE_HIGH>; - enable-active-high; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - }; }; /* off-board header */ @@ -146,9 +135,10 @@ }; &usbotg1 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_usbotg1>; dr_mode = "otg"; over-current-active-low; - vbus-supply = <®_usb_otg1_vbus>; status = "okay"; }; @@ -206,14 +196,6 @@ >; }; - pinctrl_reg_usb1_en: regusb1grp { - fsl,pins = < - MX8MM_IOMUXC_GPIO1_IO10_GPIO1_IO10 0x41 - MX8MM_IOMUXC_GPIO1_IO12_GPIO1_IO12 0x141 - MX8MM_IOMUXC_GPIO1_IO13_USB1_OTG_OC 0x41 - >; - }; - pinctrl_spi2: spi2grp { fsl,pins = < MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 @@ -236,4 +218,11 @@ MX8MM_IOMUXC_UART3_TXD_UART3_DCE_TX 0x140 >; }; + + pinctrl_usbotg1: usbotg1grp { + fsl,pins = < + MX8MM_IOMUXC_GPIO1_IO12_GPIO1_IO12 0x141 + MX8MM_IOMUXC_GPIO1_IO13_USB1_OTG_OC 0x41 + >; + }; }; diff --git a/arch/arm64/boot/dts/lg/lg1312.dtsi b/arch/arm64/boot/dts/lg/lg1312.dtsi index 78ae73d0cf3650bfd9792fac97a6368927a6e34b..98ff17b14b2a5461572ab8c148c708c547c74fd2 100644 --- a/arch/arm64/boot/dts/lg/lg1312.dtsi +++ b/arch/arm64/boot/dts/lg/lg1312.dtsi @@ -124,7 +124,6 @@ amba { #address-cells = <2>; #size-cells = <1>; - #interrupt-cells = <3>; compatible = "simple-bus"; interrupt-parent = <&gic>; diff --git a/arch/arm64/boot/dts/lg/lg1313.dtsi b/arch/arm64/boot/dts/lg/lg1313.dtsi index 2173316573bee530e09ea631cc63f5bc26bcde9a..8e9410d8f46c06b041edc426ed46b0ab4a7fb83d 100644 --- a/arch/arm64/boot/dts/lg/lg1313.dtsi +++ b/arch/arm64/boot/dts/lg/lg1313.dtsi @@ -124,7 +124,6 @@ amba { #address-cells = <2>; #size-cells = <1>; - #interrupt-cells = <3>; compatible = "simple-bus"; interrupt-parent = <&gic>; diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi index df152c72276b8f3a6e1db2517c4f063c1ffc0e25..cd28e1c45b70a360ab7882955b1ba3234e0eb58d 100644 --- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi @@ -426,14 +426,14 @@ crypto: crypto@90000 { compatible = "inside-secure,safexcel-eip97ies"; reg = <0x90000 0x20000>; - interrupts = , - , + interrupts = , , , , - ; - interrupt-names = "mem", "ring0", "ring1", - "ring2", "ring3", "eip"; + , + ; + interrupt-names = "ring0", "ring1", "ring2", + "ring3", "eip", "mem"; clocks = <&nb_periph_clk 15>; }; diff --git a/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi b/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi index a06a0a889c43f0e9d4008905ceaf43ae49d802f0..73d8803b54d8bd2d02daecae1343e5c146f01df2 100644 --- a/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi @@ -133,7 +133,6 @@ odmi: odmi@300000 { compatible = "marvell,odmi-controller"; - interrupt-controller; msi-controller; marvell,odmi-frames = <4>; reg = <0x300000 0x4000>, diff --git a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi index d6c0990a267d95d1652991c8147aec3d1073c949..218c059b16d9c67c40dc535d46f2e5b2c1027a42 100644 --- a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi @@ -506,14 +506,14 @@ CP11X_LABEL(crypto): crypto@800000 { compatible = "inside-secure,safexcel-eip197b"; reg = <0x800000 0x200000>; - interrupts = <87 IRQ_TYPE_LEVEL_HIGH>, - <88 IRQ_TYPE_LEVEL_HIGH>, + interrupts = <88 IRQ_TYPE_LEVEL_HIGH>, <89 IRQ_TYPE_LEVEL_HIGH>, <90 IRQ_TYPE_LEVEL_HIGH>, <91 IRQ_TYPE_LEVEL_HIGH>, - <92 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "mem", "ring0", "ring1", - "ring2", "ring3", "eip"; + <92 IRQ_TYPE_LEVEL_HIGH>, + <87 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "ring0", "ring1", "ring2", "ring3", + "eip", "mem"; clock-names = "core", "reg"; clocks = <&CP11X_LABEL(clk) 1 26>, <&CP11X_LABEL(clk) 1 17>; diff --git a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts index d31a194124c91a0b140da54a596be20ae3bed609..03fd9df16999ec66832af0497cd7795a8402cb8e 100644 --- a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts +++ b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts @@ -128,7 +128,7 @@ }; &pio { - eth_default: eth_default { + eth_default: eth-default-pins { tx_pins { pinmux = , , @@ -155,7 +155,7 @@ }; }; - eth_sleep: eth_sleep { + eth_sleep: eth-sleep-pins { tx_pins { pinmux = , , @@ -181,14 +181,14 @@ }; }; - usb0_id_pins_float: usb0_iddig { + usb0_id_pins_float: usb0-iddig-pins { pins_iddig { pinmux = ; bias-pull-up; }; }; - usb1_id_pins_float: usb1_iddig { + usb1_id_pins_float: usb1-iddig-pins { pins_iddig { pinmux = ; bias-pull-up; diff --git a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi index 1ac0b2cf3d406d1b20247b501a07afd99cc8e258..fde2b165f55d20ed3f764fed153b43197041488e 100644 --- a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi @@ -249,10 +249,11 @@ #clock-cells = <1>; }; - infracfg: syscon@10001000 { + infracfg: clock-controller@10001000 { compatible = "mediatek,mt2712-infracfg", "syscon"; reg = <0 0x10001000 0 0x1000>; #clock-cells = <1>; + #reset-cells = <1>; }; pericfg: syscon@10003000 { diff --git a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts index 2c35ed0734a4752985dfd2cff434331989b517f4..b1ddc491d29360a2255abbce4c0f4a19028ef1db 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts +++ b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts @@ -74,6 +74,7 @@ memory@40000000 { reg = <0 0x40000000 0 0x40000000>; + device_type = "memory"; }; reg_1p8v: regulator-1p8v { diff --git a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts index f9313b697ac125a93c8d5d67a1e5d7dd04839340..527dcb279ba520ce3099b4a53df0564c04e67bb0 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts +++ b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts @@ -56,6 +56,7 @@ memory@40000000 { reg = <0 0x40000000 0 0x20000000>; + device_type = "memory"; }; reg_1p8v: regulator-1p8v { diff --git a/arch/arm64/boot/dts/mediatek/mt7622.dtsi b/arch/arm64/boot/dts/mediatek/mt7622.dtsi index 7bb316922a3a93a38b407e8dc357be4e4790d142..f8a32006885bb4ce3faef482d68674d53d0449bc 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi @@ -251,7 +251,7 @@ clock-names = "hif_sel"; }; - cir: cir@10009000 { + cir: ir-receiver@10009000 { compatible = "mediatek,mt7622-cir"; reg = <0 0x10009000 0 0x1000>; interrupts = ; @@ -282,16 +282,14 @@ }; }; - apmixedsys: apmixedsys@10209000 { - compatible = "mediatek,mt7622-apmixedsys", - "syscon"; + apmixedsys: clock-controller@10209000 { + compatible = "mediatek,mt7622-apmixedsys"; reg = <0 0x10209000 0 0x1000>; #clock-cells = <1>; }; - topckgen: topckgen@10210000 { - compatible = "mediatek,mt7622-topckgen", - "syscon"; + topckgen: clock-controller@10210000 { + compatible = "mediatek,mt7622-topckgen"; reg = <0 0x10210000 0 0x1000>; #clock-cells = <1>; }; @@ -514,7 +512,6 @@ <&pericfg CLK_PERI_AUXADC_PD>; clock-names = "therm", "auxadc"; resets = <&pericfg MT7622_PERI_THERM_SW_RST>; - reset-names = "therm"; mediatek,auxadc = <&auxadc>; mediatek,apmixedsys = <&apmixedsys>; nvmem-cells = <&thermal_calibration>; @@ -734,9 +731,8 @@ power-domains = <&scpsys MT7622_POWER_DOMAIN_WB>; }; - ssusbsys: ssusbsys@1a000000 { - compatible = "mediatek,mt7622-ssusbsys", - "syscon"; + ssusbsys: clock-controller@1a000000 { + compatible = "mediatek,mt7622-ssusbsys"; reg = <0 0x1a000000 0 0x1000>; #clock-cells = <1>; #reset-cells = <1>; @@ -793,9 +789,8 @@ }; }; - pciesys: pciesys@1a100800 { - compatible = "mediatek,mt7622-pciesys", - "syscon"; + pciesys: clock-controller@1a100800 { + compatible = "mediatek,mt7622-pciesys"; reg = <0 0x1a100800 0 0x1000>; #clock-cells = <1>; #reset-cells = <1>; @@ -921,12 +916,13 @@ }; }; - hifsys: syscon@1af00000 { - compatible = "mediatek,mt7622-hifsys", "syscon"; + hifsys: clock-controller@1af00000 { + compatible = "mediatek,mt7622-hifsys"; reg = <0 0x1af00000 0 0x70>; + #clock-cells = <1>; }; - ethsys: syscon@1b000000 { + ethsys: clock-controller@1b000000 { compatible = "mediatek,mt7622-ethsys", "syscon"; reg = <0 0x1b000000 0 0x1000>; @@ -966,9 +962,7 @@ }; eth: ethernet@1b100000 { - compatible = "mediatek,mt7622-eth", - "mediatek,mt2701-eth", - "syscon"; + compatible = "mediatek,mt7622-eth"; reg = <0 0x1b100000 0 0x20000>; interrupts = , , diff --git a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi index fc338bd497f51938efb7e1d2fa5f26978f3d2ba7..108931e796465b175fa60feeca93228a7647a1bd 100644 --- a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi @@ -110,6 +110,7 @@ compatible = "mediatek,mt7986-infracfg", "syscon"; reg = <0 0x10001000 0 0x1000>; #clock-cells = <1>; + #reset-cells = <1>; }; wed_pcie: wed-pcie@10003000 { diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi index dccf367c7ec6cba401e5901ed369f9352bd2d4eb..3d95625f1b0b4df0d9558f9e1b0861ff000e7e5f 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi @@ -4,6 +4,8 @@ */ #include "mt8183-kukui.dtsi" +/* Must come after mt8183-kukui.dtsi to modify cros_ec */ +#include / { panel: panel { diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dtsi index 50a0dd36b5fb3010bfb2d968a283d03205a7552d..0d3c7b8162ff0bb7f01989dd4b7a0c329cd1de1e 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dtsi @@ -372,6 +372,16 @@ }; }; +&cros_ec { + cbas { + compatible = "google,cros-cbas"; + }; + + keyboard-controller { + compatible = "google,cros-ec-keyb-switches"; + }; +}; + &qca_wifi { qcom,ath10k-calibration-variant = "GO_KAKADU"; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kodama.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kodama.dtsi index 06f8c80bf553651e66ae49cbfffb567180617a73..e73113cb51f538faa5ab5b2874ab286030202e10 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kodama.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kodama.dtsi @@ -339,6 +339,16 @@ }; }; +&cros_ec { + cbas { + compatible = "google,cros-cbas"; + }; + + keyboard-controller { + compatible = "google,cros-ec-keyb-switches"; + }; +}; + &qca_wifi { qcom,ath10k-calibration-variant = "GO_KODAMA"; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-krane.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-krane.dtsi index a7b0cb3ff7b0aba4a135c6df770dcd1dad6b5e92..181da69d18f46a355fad6d9dc6b4d758ec159726 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-krane.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-krane.dtsi @@ -343,6 +343,16 @@ }; }; +&cros_ec { + cbas { + compatible = "google,cros-cbas"; + }; + + keyboard-controller { + compatible = "google,cros-ec-keyb-switches"; + }; +}; + &qca_wifi { qcom,ath10k-calibration-variant = "LE_Krane"; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi index a428a581c93a8d55a11073bd5733b8bb8755259d..1db97d94658b90d29394433b7f62e62d3839cc49 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi @@ -896,10 +896,6 @@ google,usb-port-id = <0>; }; - cbas { - compatible = "google,cros-cbas"; - }; - typec { compatible = "google,cros-ec-typec"; #address-cells = <1>; @@ -999,5 +995,4 @@ }; }; -#include #include diff --git a/arch/arm64/boot/dts/mediatek/mt8183.dtsi b/arch/arm64/boot/dts/mediatek/mt8183.dtsi index d5d9b954c449a97864c9ba09bd8570d31c884eb0..2147e152683bf05e61744a8965c29167f23f5f78 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183.dtsi @@ -1554,6 +1554,7 @@ compatible = "mediatek,mt8183-mfgcfg", "syscon"; reg = <0 0x13000000 0 0x1000>; #clock-cells = <1>; + power-domains = <&spm MT8183_POWER_DOMAIN_MFG_ASYNC>; }; gpu: gpu@13040000 { diff --git a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi index 50367da93cd79e98d4b0ad28db91bb604a5a6957..0814ed6a7272d7c8cd9bbe41ed478a146435ba23 100644 --- a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi @@ -819,10 +819,6 @@ #address-cells = <1>; #size-cells = <0>; - base_detection: cbas { - compatible = "google,cros-cbas"; - }; - cros_ec_pwm: pwm { compatible = "google,cros-ec-pwm"; #pwm-cells = <1>; @@ -907,7 +903,7 @@ mt6315_6_vbuck1: vbuck1 { regulator-compatible = "vbuck1"; regulator-name = "Vbcpu"; - regulator-min-microvolt = <300000>; + regulator-min-microvolt = <400000>; regulator-max-microvolt = <1193750>; regulator-enable-ramp-delay = <256>; regulator-allowed-modes = <0 1 2>; @@ -917,7 +913,7 @@ mt6315_6_vbuck3: vbuck3 { regulator-compatible = "vbuck3"; regulator-name = "Vlcpu"; - regulator-min-microvolt = <300000>; + regulator-min-microvolt = <400000>; regulator-max-microvolt = <1193750>; regulator-enable-ramp-delay = <256>; regulator-allowed-modes = <0 1 2>; @@ -934,7 +930,7 @@ mt6315_7_vbuck1: vbuck1 { regulator-compatible = "vbuck1"; regulator-name = "Vgpu"; - regulator-min-microvolt = <606250>; + regulator-min-microvolt = <400000>; regulator-max-microvolt = <800000>; regulator-enable-ramp-delay = <256>; regulator-allowed-modes = <0 1 2>; diff --git a/arch/arm64/boot/dts/mediatek/mt8192.dtsi b/arch/arm64/boot/dts/mediatek/mt8192.dtsi index 2f40c6cc407c1df2f0c4dc018f596bd5f2f1d3ec..7ecba8c7262da7ea1698d6e4c624ce64a4bb4e8f 100644 --- a/arch/arm64/boot/dts/mediatek/mt8192.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8192.dtsi @@ -1240,6 +1240,7 @@ reg = <0 0x14001000 0 0x1000>; interrupts = ; clocks = <&mmsys CLK_MM_DISP_MUTEX0>; + mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x1000 0x1000>; mediatek,gce-events = , ; power-domains = <&spm MT8192_POWER_DOMAIN_DISP>; @@ -1539,7 +1540,7 @@ mediatek,scp = <&scp>; power-domains = <&spm MT8192_POWER_DOMAIN_VENC>; clocks = <&vencsys CLK_VENC_SET1_VENC>; - clock-names = "venc-set1"; + clock-names = "venc_sel"; assigned-clocks = <&topckgen CLK_TOP_VENC_SEL>; assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D4>; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r1.dts b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r1.dts index 3348ba69ff6cf63abb62a68c33982472385ca050..d86d193e5a75e900b68541e9625a1170d65630f2 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r1.dts +++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r1.dts @@ -13,3 +13,7 @@ &ts_10 { status = "okay"; }; + +&watchdog { + /delete-property/ mediatek,disable-extrst; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r2.dts b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r2.dts index 4669e9d917f8cc8271691ba8a3bc54099b023737..5356f53308e245a5175bc18d95f474182d08d41b 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r2.dts +++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r2.dts @@ -33,3 +33,7 @@ &ts_10 { status = "okay"; }; + +&watchdog { + /delete-property/ mediatek,disable-extrst; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r3.dts b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r3.dts index 5021edd02f7c1a6952e7b87d6609518b441417c9..fca3606cb951ed8e9519957ee6c3c311024727a3 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r3.dts +++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r3.dts @@ -34,3 +34,7 @@ &ts_10 { status = "okay"; }; + +&watchdog { + /delete-property/ mediatek,disable-extrst; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi index 4b8a1c462906ed6edcd8b26b2b40a3f9d70b5f04..9180a73db066e27d623c77a1d4cf3b763f8535e1 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi @@ -845,7 +845,7 @@ mt6315_6_vbuck1: vbuck1 { regulator-compatible = "vbuck1"; regulator-name = "Vbcpu"; - regulator-min-microvolt = <300000>; + regulator-min-microvolt = <400000>; regulator-max-microvolt = <1193750>; regulator-enable-ramp-delay = <256>; regulator-ramp-delay = <6250>; @@ -863,7 +863,7 @@ mt6315_7_vbuck1: vbuck1 { regulator-compatible = "vbuck1"; regulator-name = "Vgpu"; - regulator-min-microvolt = <625000>; + regulator-min-microvolt = <400000>; regulator-max-microvolt = <1193750>; regulator-enable-ramp-delay = <256>; regulator-ramp-delay = <6250>; diff --git a/arch/arm64/boot/dts/mediatek/mt8195-demo.dts b/arch/arm64/boot/dts/mediatek/mt8195-demo.dts index 5117b2e7985afef6235dbce7af5b2ac83d04016e..998c2e78168a60649f0dda0f77a41be7ad3fd67e 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195-demo.dts +++ b/arch/arm64/boot/dts/mediatek/mt8195-demo.dts @@ -111,6 +111,7 @@ compatible = "mediatek,mt6360"; reg = <0x34>; interrupt-controller; + #interrupt-cells = <1>; interrupts-extended = <&pio 101 IRQ_TYPE_EDGE_FALLING>; interrupt-names = "IRQB"; diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi index 414cbe3451270c605c4687d4212b69274d2475b1..bdf002e9cece17162dd7347ede77a1a726e05634 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi @@ -1492,6 +1492,7 @@ compatible = "mediatek,mt8195-vppsys0"; reg = <0 0x14000000 0 0x1000>; #clock-cells = <1>; + mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0 0x1000>; }; smi_sub_common_vpp0_vpp1_2x1: smi@14010000 { @@ -1597,6 +1598,7 @@ compatible = "mediatek,mt8195-vppsys1"; reg = <0 0x14f00000 0 0x1000>; #clock-cells = <1>; + mediatek,gce-client-reg = <&gce1 SUBSYS_14f0XXXX 0 0x1000>; }; larb5: larb@14f02000 { @@ -1982,6 +1984,7 @@ reg = <0 0x1c01a000 0 0x1000>; mboxes = <&gce0 0 CMDQ_THR_PRIO_4>; #clock-cells = <1>; + mediatek,gce-client-reg = <&gce0 SUBSYS_1c01XXXX 0xa000 0x1000>; }; larb20: larb@1b010000 { @@ -2085,6 +2088,7 @@ interrupts = ; power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS0>; clocks = <&vdosys0 CLK_VDO0_DISP_MUTEX0>; + mediatek,gce-client-reg = <&gce0 SUBSYS_1c01XXXX 0x6000 0x1000>; mediatek,gce-events = ; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts b/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts index f094011be9ed90fdf87b23cdaab15609c945222e..8099dc04ed2e15f59f3153839cc39f59f2ff7e20 100644 --- a/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts +++ b/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts @@ -2024,7 +2024,7 @@ status = "okay"; phy-handle = <&mgbe0_phy>; - phy-mode = "usxgmii"; + phy-mode = "10gbase-r"; mdio { #address-cells = <1>; diff --git a/arch/arm64/boot/dts/qcom/apq8016-sbc.dts b/arch/arm64/boot/dts/qcom/apq8016-sbc.dts index 9d116e1fbe10c5df4ac37d1bd6652376721e662f..1ac4f8c24e2317f23ecc2f0fae0bc636b238185f 100644 --- a/arch/arm64/boot/dts/qcom/apq8016-sbc.dts +++ b/arch/arm64/boot/dts/qcom/apq8016-sbc.dts @@ -169,10 +169,6 @@ }; }; -&blsp_dma { - status = "okay"; -}; - &blsp_i2c2 { /* On Low speed expansion */ status = "okay"; diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi index bafac2cf7e3d6934739738493ce9b1a368383319..987cebbda057118a270b88288153b304315f5dfb 100644 --- a/arch/arm64/boot/dts/qcom/msm8916.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi @@ -1522,7 +1522,7 @@ clock-names = "bam_clk"; #dma-cells = <1>; qcom,ee = <0>; - status = "disabled"; + qcom,controlled-remotely; }; blsp1_uart1: serial@78af000 { diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi index eae22e6e97c15f185fac74a64b2efaf8b2815c3c..f55ce6f2fdc28cf90e4f7745e1fedc0bcae3491b 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi @@ -923,6 +923,8 @@ ap_spi_fp: &spi10 { vddrf-supply = <&pp1300_l2c>; vddch0-supply = <&pp3300_l10c>; max-speed = <3200000>; + + qcom,local-bd-address-broken; }; }; diff --git a/arch/arm64/boot/dts/qcom/sc7280.dtsi b/arch/arm64/boot/dts/qcom/sc7280.dtsi index 04106d725400045db18957e339b1bcb2438de586..b5cd24d59ad9af0071a2ed9ffee13597cb99d177 100644 --- a/arch/arm64/boot/dts/qcom/sc7280.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7280.dtsi @@ -2028,8 +2028,16 @@ ranges = <0x01000000 0x0 0x00000000 0x0 0x40200000 0x0 0x100000>, <0x02000000 0x0 0x40300000 0x0 0x40300000 0x0 0x1fd00000>; - interrupts = ; - interrupt-names = "msi"; + interrupts = , + , + , + , + , + , + , + ; + interrupt-names = "msi0", "msi1", "msi2", "msi3", + "msi4", "msi5", "msi6", "msi7"; #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0x7>; interrupt-map = <0 0 0 1 &intc 0 0 0 434 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts index 135ff4368c4a660d1371b3eb99215016c3c6b434..5c04c91b0ee2b4248945da1b1d0b909bf1a5fab1 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts @@ -532,7 +532,7 @@ &pcie0 { status = "okay"; perst-gpios = <&tlmm 35 GPIO_ACTIVE_LOW>; - enable-gpio = <&tlmm 134 GPIO_ACTIVE_HIGH>; + wake-gpios = <&tlmm 134 GPIO_ACTIVE_HIGH>; vddpe-3v3-supply = <&pcie0_3p3v_dual>; diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi index 4d5905ef0b41193dcc50eb9b8ea091a104683f14..95c515da9f2e07740ee121a556017fb25c1790f8 100644 --- a/arch/arm64/boot/dts/qcom/sdm845.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi @@ -4049,7 +4049,7 @@ assigned-clock-rates = <19200000>, <150000000>; interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, - <&intc GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>, + <&pdc_intc 6 IRQ_TYPE_LEVEL_HIGH>, <&pdc_intc 8 IRQ_TYPE_EDGE_BOTH>, <&pdc_intc 9 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", @@ -4100,7 +4100,7 @@ assigned-clock-rates = <19200000>, <150000000>; interrupts-extended = <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>, - <&intc GIC_SPI 487 IRQ_TYPE_LEVEL_HIGH>, + <&pdc_intc 7 IRQ_TYPE_LEVEL_HIGH>, <&pdc_intc 10 IRQ_TYPE_EDGE_BOTH>, <&pdc_intc 11 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", diff --git a/arch/arm64/boot/dts/qcom/sm8150.dtsi b/arch/arm64/boot/dts/qcom/sm8150.dtsi index 8efd0e227d780fd49d7d35fd6aaeabcb8c50b1a4..9dccecd9fcaef6fd0800a93e18b91bb438b49af4 100644 --- a/arch/arm64/boot/dts/qcom/sm8150.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8150.dtsi @@ -1822,8 +1822,8 @@ phys = <&pcie0_lane>; phy-names = "pciephy"; - perst-gpio = <&tlmm 35 GPIO_ACTIVE_HIGH>; - enable-gpio = <&tlmm 37 GPIO_ACTIVE_HIGH>; + perst-gpios = <&tlmm 35 GPIO_ACTIVE_HIGH>; + wake-gpios = <&tlmm 37 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; pinctrl-0 = <&pcie0_default_state>; @@ -1925,7 +1925,7 @@ phys = <&pcie1_lane>; phy-names = "pciephy"; - perst-gpio = <&tlmm 102 GPIO_ACTIVE_HIGH>; + perst-gpios = <&tlmm 102 GPIO_ACTIVE_HIGH>; enable-gpio = <&tlmm 104 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; @@ -3629,7 +3629,7 @@ assigned-clock-rates = <19200000>, <200000000>; interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, - <&intc GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 6 IRQ_TYPE_LEVEL_HIGH>, <&pdc 8 IRQ_TYPE_EDGE_BOTH>, <&pdc 9 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", @@ -3678,7 +3678,7 @@ assigned-clock-rates = <19200000>, <200000000>; interrupts-extended = <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>, - <&intc GIC_SPI 487 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 7 IRQ_TYPE_LEVEL_HIGH>, <&pdc 10 IRQ_TYPE_EDGE_BOTH>, <&pdc 11 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", diff --git a/arch/arm64/boot/dts/renesas/r8a779a0.dtsi b/arch/arm64/boot/dts/renesas/r8a779a0.dtsi index ed9400f903c9ecefde6a268fcb0b4d739b87303b..b677ef6705d94e0e9841c9aaf2ab54caf0c40bad 100644 --- a/arch/arm64/boot/dts/renesas/r8a779a0.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a779a0.dtsi @@ -656,8 +656,8 @@ avb0: ethernet@e6800000 { compatible = "renesas,etheravb-r8a779a0", - "renesas,etheravb-rcar-gen3"; - reg = <0 0xe6800000 0 0x800>; + "renesas,etheravb-rcar-gen4"; + reg = <0 0xe6800000 0 0x1000>; interrupts = , , , @@ -704,8 +704,8 @@ avb1: ethernet@e6810000 { compatible = "renesas,etheravb-r8a779a0", - "renesas,etheravb-rcar-gen3"; - reg = <0 0xe6810000 0 0x800>; + "renesas,etheravb-rcar-gen4"; + reg = <0 0xe6810000 0 0x1000>; interrupts = , , , @@ -752,7 +752,7 @@ avb2: ethernet@e6820000 { compatible = "renesas,etheravb-r8a779a0", - "renesas,etheravb-rcar-gen3"; + "renesas,etheravb-rcar-gen4"; reg = <0 0xe6820000 0 0x1000>; interrupts = , , @@ -800,7 +800,7 @@ avb3: ethernet@e6830000 { compatible = "renesas,etheravb-r8a779a0", - "renesas,etheravb-rcar-gen3"; + "renesas,etheravb-rcar-gen4"; reg = <0 0xe6830000 0 0x1000>; interrupts = , , @@ -848,7 +848,7 @@ avb4: ethernet@e6840000 { compatible = "renesas,etheravb-r8a779a0", - "renesas,etheravb-rcar-gen3"; + "renesas,etheravb-rcar-gen4"; reg = <0 0xe6840000 0 0x1000>; interrupts = , , @@ -896,7 +896,7 @@ avb5: ethernet@e6850000 { compatible = "renesas,etheravb-r8a779a0", - "renesas,etheravb-rcar-gen3"; + "renesas,etheravb-rcar-gen4"; reg = <0 0xe6850000 0 0x1000>; interrupts = , , @@ -1019,7 +1019,7 @@ msiof0: spi@e6e90000 { compatible = "renesas,msiof-r8a779a0", - "renesas,rcar-gen3-msiof"; + "renesas,rcar-gen4-msiof"; reg = <0 0xe6e90000 0 0x0064>; interrupts = ; clocks = <&cpg CPG_MOD 618>; @@ -1034,7 +1034,7 @@ msiof1: spi@e6ea0000 { compatible = "renesas,msiof-r8a779a0", - "renesas,rcar-gen3-msiof"; + "renesas,rcar-gen4-msiof"; reg = <0 0xe6ea0000 0 0x0064>; interrupts = ; clocks = <&cpg CPG_MOD 619>; @@ -1049,7 +1049,7 @@ msiof2: spi@e6c00000 { compatible = "renesas,msiof-r8a779a0", - "renesas,rcar-gen3-msiof"; + "renesas,rcar-gen4-msiof"; reg = <0 0xe6c00000 0 0x0064>; interrupts = ; clocks = <&cpg CPG_MOD 620>; @@ -1064,7 +1064,7 @@ msiof3: spi@e6c10000 { compatible = "renesas,msiof-r8a779a0", - "renesas,rcar-gen3-msiof"; + "renesas,rcar-gen4-msiof"; reg = <0 0xe6c10000 0 0x0064>; interrupts = ; clocks = <&cpg CPG_MOD 621>; @@ -1079,7 +1079,7 @@ msiof4: spi@e6c20000 { compatible = "renesas,msiof-r8a779a0", - "renesas,rcar-gen3-msiof"; + "renesas,rcar-gen4-msiof"; reg = <0 0xe6c20000 0 0x0064>; interrupts = ; clocks = <&cpg CPG_MOD 622>; @@ -1094,7 +1094,7 @@ msiof5: spi@e6c28000 { compatible = "renesas,msiof-r8a779a0", - "renesas,rcar-gen3-msiof"; + "renesas,rcar-gen4-msiof"; reg = <0 0xe6c28000 0 0x0064>; interrupts = ; clocks = <&cpg CPG_MOD 623>; diff --git a/arch/arm64/boot/dts/renesas/r8a779g0.dtsi b/arch/arm64/boot/dts/renesas/r8a779g0.dtsi index d58b18802cb0189da06129ecb1795cb8d1f89488..868d1a3cbdf61756e747c96dba7ff131e05f89c6 100644 --- a/arch/arm64/boot/dts/renesas/r8a779g0.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a779g0.dtsi @@ -337,7 +337,7 @@ avb0: ethernet@e6800000 { compatible = "renesas,etheravb-r8a779g0", "renesas,etheravb-rcar-gen4"; - reg = <0 0xe6800000 0 0x800>; + reg = <0 0xe6800000 0 0x1000>; interrupts = , , , @@ -384,7 +384,7 @@ avb1: ethernet@e6810000 { compatible = "renesas,etheravb-r8a779g0", "renesas,etheravb-rcar-gen4"; - reg = <0 0xe6810000 0 0x800>; + reg = <0 0xe6810000 0 0x1000>; interrupts = , , , diff --git a/arch/arm64/boot/dts/renesas/r9a07g043.dtsi b/arch/arm64/boot/dts/renesas/r9a07g043.dtsi index a4738842f0646e256f49fa1156f3561e620e0d4e..7f88395ff79975da14e384e02f0679c268f2246e 100644 --- a/arch/arm64/boot/dts/renesas/r9a07g043.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a07g043.dtsi @@ -1,6 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* - * Device Tree Source for the RZ/G2UL SoC + * Device Tree Source for the RZ/Five and RZ/G2UL SoCs * * Copyright (C) 2022 Renesas Electronics Corp. */ @@ -68,36 +68,8 @@ }; }; - cpus { - #address-cells = <1>; - #size-cells = <0>; - - cpu0: cpu@0 { - compatible = "arm,cortex-a55"; - reg = <0>; - device_type = "cpu"; - #cooling-cells = <2>; - next-level-cache = <&L3_CA55>; - enable-method = "psci"; - clocks = <&cpg CPG_CORE R9A07G043_CLK_I>; - operating-points-v2 = <&cluster0_opp>; - }; - - L3_CA55: cache-controller-0 { - compatible = "cache"; - cache-unified; - cache-size = <0x40000>; - }; - }; - - psci { - compatible = "arm,psci-1.0", "arm,psci-0.2"; - method = "smc"; - }; - soc: soc { compatible = "simple-bus"; - interrupt-parent = <&gic>; #address-cells = <2>; #size-cells = <2>; ranges; @@ -545,12 +517,6 @@ sysc: system-controller@11020000 { compatible = "renesas,r9a07g043-sysc"; reg = <0 0x11020000 0 0x10000>; - interrupts = , - , - , - ; - interrupt-names = "lpm_int", "ca55stbydone_int", - "cm33stbyr_int", "ca55_deny"; status = "disabled"; }; @@ -603,16 +569,6 @@ dma-channels = <16>; }; - gic: interrupt-controller@11900000 { - compatible = "arm,gic-v3"; - #interrupt-cells = <3>; - #address-cells = <0>; - interrupt-controller; - reg = <0x0 0x11900000 0 0x40000>, - <0x0 0x11940000 0 0x60000>; - interrupts = ; - }; - sdhi0: mmc@11c00000 { compatible = "renesas,sdhi-r9a07g043", "renesas,rcar-gen3-sdhi"; @@ -893,12 +849,4 @@ }; }; }; - - timer { - compatible = "arm,armv8-timer"; - interrupts-extended = <&gic GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>; - }; }; diff --git a/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi b/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi index 96f935bc2d4d1b5f4096724aac60935c9b4cc660..011d4c88f4ed9dee1022ad9ec25f3d4b7b7f7cc8 100644 --- a/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi @@ -10,3 +10,139 @@ #define SOC_PERIPHERAL_IRQ(nr) GIC_SPI nr #include "r9a07g043.dtsi" + +/ { + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + compatible = "arm,cortex-a55"; + reg = <0>; + device_type = "cpu"; + #cooling-cells = <2>; + next-level-cache = <&L3_CA55>; + enable-method = "psci"; + clocks = <&cpg CPG_CORE R9A07G043_CLK_I>; + operating-points-v2 = <&cluster0_opp>; + }; + + L3_CA55: cache-controller-0 { + compatible = "cache"; + cache-unified; + cache-size = <0x40000>; + }; + }; + + psci { + compatible = "arm,psci-1.0", "arm,psci-0.2"; + method = "smc"; + }; + + timer { + compatible = "arm,armv8-timer"; + interrupts-extended = <&gic GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, + <&gic GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, + <&gic GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, + <&gic GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>; + }; +}; + +&soc { + interrupt-parent = <&gic>; + + irqc: interrupt-controller@110a0000 { + compatible = "renesas,r9a07g043u-irqc", + "renesas,rzg2l-irqc"; + reg = <0 0x110a0000 0 0x10000>; + #interrupt-cells = <2>; + #address-cells = <0>; + interrupt-controller; + interrupts = , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + ; + interrupt-names = "nmi", + "irq0", "irq1", "irq2", "irq3", + "irq4", "irq5", "irq6", "irq7", + "tint0", "tint1", "tint2", "tint3", + "tint4", "tint5", "tint6", "tint7", + "tint8", "tint9", "tint10", "tint11", + "tint12", "tint13", "tint14", "tint15", + "tint16", "tint17", "tint18", "tint19", + "tint20", "tint21", "tint22", "tint23", + "tint24", "tint25", "tint26", "tint27", + "tint28", "tint29", "tint30", "tint31", + "bus-err", "ec7tie1-0", "ec7tie2-0", + "ec7tiovf-0", "ec7tie1-1", "ec7tie2-1", + "ec7tiovf-1"; + clocks = <&cpg CPG_MOD R9A07G043_IA55_CLK>, + <&cpg CPG_MOD R9A07G043_IA55_PCLK>; + clock-names = "clk", "pclk"; + power-domains = <&cpg>; + resets = <&cpg R9A07G043_IA55_RESETN>; + }; + + gic: interrupt-controller@11900000 { + compatible = "arm,gic-v3"; + #interrupt-cells = <3>; + #address-cells = <0>; + interrupt-controller; + reg = <0x0 0x11900000 0 0x40000>, + <0x0 0x11940000 0 0x60000>; + interrupts = ; + }; +}; + +&sysc { + interrupts = , + , + , + ; + interrupt-names = "lpm_int", "ca55stbydone_int", + "cm33stbyr_int", "ca55_deny"; +}; diff --git a/arch/arm64/boot/dts/renesas/r9a07g044.dtsi b/arch/arm64/boot/dts/renesas/r9a07g044.dtsi index 7dbf6a6292f493b996b6d1f3adfed1acd2dc8eae..d26488b5a82df10c39b1997f4cfbaecbb24b6bfc 100644 --- a/arch/arm64/boot/dts/renesas/r9a07g044.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a07g044.dtsi @@ -698,7 +698,27 @@ , , , - ; + , + , + , + , + , + , + , + ; + interrupt-names = "nmi", "irq0", "irq1", "irq2", "irq3", + "irq4", "irq5", "irq6", "irq7", + "tint0", "tint1", "tint2", "tint3", + "tint4", "tint5", "tint6", "tint7", + "tint8", "tint9", "tint10", "tint11", + "tint12", "tint13", "tint14", "tint15", + "tint16", "tint17", "tint18", "tint19", + "tint20", "tint21", "tint22", "tint23", + "tint24", "tint25", "tint26", "tint27", + "tint28", "tint29", "tint30", "tint31", + "bus-err", "ec7tie1-0", "ec7tie2-0", + "ec7tiovf-0", "ec7tie1-1", "ec7tie2-1", + "ec7tiovf-1"; clocks = <&cpg CPG_MOD R9A07G044_IA55_CLK>, <&cpg CPG_MOD R9A07G044_IA55_PCLK>; clock-names = "clk", "pclk"; diff --git a/arch/arm64/boot/dts/renesas/r9a07g054.dtsi b/arch/arm64/boot/dts/renesas/r9a07g054.dtsi index e000510b90a42cb1279b0aacb74ac887dd8ae34d..b3d37ca942ee3da38b02d0432d319179dec7d09a 100644 --- a/arch/arm64/boot/dts/renesas/r9a07g054.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a07g054.dtsi @@ -704,7 +704,27 @@ , , , - ; + , + , + , + , + , + , + , + ; + interrupt-names = "nmi", "irq0", "irq1", "irq2", "irq3", + "irq4", "irq5", "irq6", "irq7", + "tint0", "tint1", "tint2", "tint3", + "tint4", "tint5", "tint6", "tint7", + "tint8", "tint9", "tint10", "tint11", + "tint12", "tint13", "tint14", "tint15", + "tint16", "tint17", "tint18", "tint19", + "tint20", "tint21", "tint22", "tint23", + "tint24", "tint25", "tint26", "tint27", + "tint28", "tint29", "tint30", "tint31", + "bus-err", "ec7tie1-0", "ec7tie2-0", + "ec7tiovf-0", "ec7tie1-1", "ec7tie2-1", + "ec7tiovf-1"; clocks = <&cpg CPG_MOD R9A07G054_IA55_CLK>, <&cpg CPG_MOD R9A07G054_IA55_PCLK>; clock-names = "clk", "pclk"; diff --git a/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi b/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi index 588b14b66b6fb6d4466980f32cd4866881c3c994..f37abfc13fe592360ae3f1a80712c06b44c05ac2 100644 --- a/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi +++ b/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi @@ -251,6 +251,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&gpio6>; interrupts = <8 IRQ_TYPE_EDGE_FALLING>; @@ -311,6 +312,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&gpio6>; interrupts = <4 IRQ_TYPE_EDGE_FALLING>; }; @@ -331,6 +333,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&gpio7>; interrupts = <3 IRQ_TYPE_EDGE_FALLING>; }; @@ -341,6 +344,7 @@ gpio-controller; #gpio-cells = <2>; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&gpio5>; interrupts = <9 IRQ_TYPE_EDGE_FALLING>; }; diff --git a/arch/arm64/boot/dts/rockchip/px30.dtsi b/arch/arm64/boot/dts/rockchip/px30.dtsi index bfa3580429d10e010e736ad929243583287f0dea..61f0186447dadc03dc99aa5a5e264801b313229f 100644 --- a/arch/arm64/boot/dts/rockchip/px30.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30.dtsi @@ -607,6 +607,7 @@ clock-names = "spiclk", "apb_pclk"; dmas = <&dmac 12>, <&dmac 13>; dma-names = "tx", "rx"; + num-cs = <2>; pinctrl-names = "default"; pinctrl-0 = <&spi0_clk &spi0_csn &spi0_miso &spi0_mosi>; #address-cells = <1>; @@ -622,6 +623,7 @@ clock-names = "spiclk", "apb_pclk"; dmas = <&dmac 14>, <&dmac 15>; dma-names = "tx", "rx"; + num-cs = <2>; pinctrl-names = "default"; pinctrl-0 = <&spi1_clk &spi1_csn0 &spi1_csn1 &spi1_miso &spi1_mosi>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 905a50aa5dc38c8c31b441d6e55b605951e71958..d42846efff2fec46f697643a1b6dbfdd9aeae8bc 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -741,11 +741,20 @@ status = "disabled"; ports { - hdmi_in: port { + #address-cells = <1>; + #size-cells = <0>; + + hdmi_in: port@0 { + reg = <0>; + hdmi_in_vop: endpoint { remote-endpoint = <&vop_out_hdmi>; }; }; + + hdmi_out: port@1 { + reg = <1>; + }; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts index 194e48c755f6bc19d33f0736a0423d6205859450..a51e8d0493cabe59469b46de8b7dbc5e10f491f6 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts @@ -789,7 +789,6 @@ }; &pcie0 { - bus-scan-delay-ms = <1000>; ep-gpios = <&gpio2 RK_PD4 GPIO_ACTIVE_HIGH>; num-lanes = <4>; pinctrl-names = "default"; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi index aa3e21bd6c8f44ff5f9b249dd43b56316dbc2a60..937a15005eb0e9cd208b04aa8390f0970f0fe2ef 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi @@ -401,16 +401,22 @@ gpio1830-supply = <&vcc_1v8>; }; -&pmu_io_domains { - status = "okay"; - pmu1830-supply = <&vcc_1v8>; -}; - -&pwm2 { - status = "okay"; +&pcie_clkreqn_cpm { + rockchip,pins = + <2 RK_PD2 RK_FUNC_GPIO &pcfg_pull_up>; }; &pinctrl { + pinctrl-names = "default"; + pinctrl-0 = <&q7_thermal_pin>; + + gpios { + q7_thermal_pin: q7-thermal-pin { + rockchip,pins = + <0 RK_PA3 RK_FUNC_GPIO &pcfg_pull_up>; + }; + }; + i2c8 { i2c8_xfer_a: i2c8-xfer { rockchip,pins = @@ -443,11 +449,20 @@ usb3 { usb3_id: usb3-id { rockchip,pins = - <1 RK_PC2 RK_FUNC_GPIO &pcfg_pull_none>; + <1 RK_PC2 RK_FUNC_GPIO &pcfg_pull_up>; }; }; }; +&pmu_io_domains { + status = "okay"; + pmu1830-supply = <&vcc_1v8>; +}; + +&pwm2 { + status = "okay"; +}; + &sdhci { /* * Signal integrity isn't great at 200MHz but 100MHz has proven stable diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index a7e6eccb14cc6c427531c9d70393904982d897b8..8363cc13ec51757125058179ee620c3ca8346d53 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -1906,6 +1906,7 @@ hdmi: hdmi@ff940000 { compatible = "rockchip,rk3399-dw-hdmi"; reg = <0x0 0xff940000 0x0 0x20000>; + reg-io-width = <4>; interrupts = ; clocks = <&cru PCLK_HDMI_CTRL>, <&cru SCLK_HDMI_SFR>, @@ -1914,13 +1915,16 @@ <&cru PLL_VPLL>; clock-names = "iahb", "isfr", "cec", "grf", "ref"; power-domains = <&power RK3399_PD_HDCP>; - reg-io-width = <4>; rockchip,grf = <&grf>; #sound-dai-cells = <0>; status = "disabled"; ports { - hdmi_in: port { + #address-cells = <1>; + #size-cells = <0>; + + hdmi_in: port@0 { + reg = <0>; #address-cells = <1>; #size-cells = <0>; @@ -1933,6 +1937,10 @@ remote-endpoint = <&vopl_out_hdmi>; }; }; + + hdmi_out: port@1 { + reg = <1>; + }; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts index 26d7fda275edb69d4d0b11144320282b05c95655..856fe4b66a0b9e208995b69cd4ae8d8b241705b1 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts @@ -412,6 +412,8 @@ vccio_sd: LDO_REG5 { regulator-name = "vccio_sd"; + regulator-always-on; + regulator-boot-on; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; @@ -521,9 +523,9 @@ #address-cells = <1>; #size-cells = <0>; - switch@0 { + switch@1f { compatible = "mediatek,mt7531"; - reg = <0>; + reg = <0x1f>; ports { #address-cells = <1>; diff --git a/arch/arm64/boot/dts/rockchip/rk356x.dtsi b/arch/arm64/boot/dts/rockchip/rk356x.dtsi index f4d6dbbbddcd4c5ead7b2a6c1bd77775aa27f06f..99ad6fc51b584a3ae7b6319ddf93e6ec411b6310 100644 --- a/arch/arm64/boot/dts/rockchip/rk356x.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk356x.dtsi @@ -596,6 +596,7 @@ compatible = "rockchip,rk3568-vpu"; reg = <0x0 0xfdea0000 0x0 0x800>; interrupts = ; + interrupt-names = "vdpu"; clocks = <&cru ACLK_VPU>, <&cru HCLK_VPU>; clock-names = "aclk", "hclk"; iommus = <&vdpu_mmu>; diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c index 937189bc155c914741a7b11426adfd8808ad314c..813ae2bbbd525da523f6327419f1f37bbdda519c 100644 --- a/arch/arm64/crypto/aes-neonbs-glue.c +++ b/arch/arm64/crypto/aes-neonbs-glue.c @@ -222,8 +222,19 @@ static int ctr_encrypt(struct skcipher_request *req) src += blocks * AES_BLOCK_SIZE; } if (nbytes && walk.nbytes == walk.total) { + u8 buf[AES_BLOCK_SIZE]; + u8 *d = dst; + + if (unlikely(nbytes < AES_BLOCK_SIZE)) + src = dst = memcpy(buf + sizeof(buf) - nbytes, + src, nbytes); + neon_aes_ctr_encrypt(dst, src, ctx->enc, ctx->key.rounds, nbytes, walk.iv); + + if (unlikely(nbytes < AES_BLOCK_SIZE)) + memcpy(d, dst, nbytes); + nbytes = 0; } kernel_neon_end(); diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h index 3622e9f4fb442b9e8301568a2447b99f78beeea2..51738c56e96cd82bf249013c6ff283374db75902 100644 --- a/arch/arm64/include/asm/alternative-macros.h +++ b/arch/arm64/include/asm/alternative-macros.h @@ -229,7 +229,7 @@ alternative_has_feature_likely(unsigned long feature) compiletime_assert(feature < ARM64_NCAPS, "feature must be < ARM64_NCAPS"); - asm_volatile_goto( + asm goto( ALTERNATIVE_CB("b %l[l_no]", %[feature], alt_cb_patch_nops) : : [feature] "i" (feature) @@ -247,7 +247,7 @@ alternative_has_feature_unlikely(unsigned long feature) compiletime_assert(feature < ARM64_NCAPS, "feature must be < ARM64_NCAPS"); - asm_volatile_goto( + asm goto( ALTERNATIVE("nop", "b %l[l_yes]", %[feature]) : : [feature] "i" (feature) diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 7dce9c0aa78369f469d964c3459591f66d1879aa..af3a678a76b3ab3df91fd3dec6be39d0c504b2b7 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -61,6 +61,7 @@ #define ARM_CPU_IMP_HISI 0x48 #define ARM_CPU_IMP_APPLE 0x61 #define ARM_CPU_IMP_AMPERE 0xC0 +#define ARM_CPU_IMP_MICROSOFT 0x6D #define ARM_CPU_PART_AEM_V8 0xD0F #define ARM_CPU_PART_FOUNDATION 0xD00 @@ -128,6 +129,8 @@ #define AMPERE_CPU_PART_AMPERE1 0xAC3 +#define MICROSOFT_CPU_PART_AZURE_COBALT_100 0xD49 /* Based on r0p0 of ARM Neoverse N2 */ + #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72) @@ -179,6 +182,7 @@ #define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX) #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX) #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) +#define MIDR_MICROSOFT_AZURE_COBALT_100 MIDR_CPU_MODEL(ARM_CPU_IMP_MICROSOFT, MICROSOFT_CPU_PART_AZURE_COBALT_100) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ #define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 62c846be2d76ac60894289e1afa2ef25c4f4e7c9..a75c0772ecfcae54944333dce301e2595177c99f 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -103,6 +103,7 @@ static inline void free_screen_info(struct screen_info *si) } #define EFI_ALLOC_ALIGN SZ_64K +#define EFI_ALLOC_LIMIT ((1UL << 48) - 1) /* * On ARM systems, virtually remapped UEFI runtime services are set up in two diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index d720b6f7e5f9c6383b29c25ee21b05137da8951a..930b0e6c94622a0ce446577b397ff9ba3f2f60e8 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -36,13 +36,13 @@ * When we defined the maximum SVE vector length we defined the ABI so * that the maximum vector length included all the reserved for future * expansion bits in ZCR rather than those just currently defined by - * the architecture. While SME follows a similar pattern the fact that - * it includes a square matrix means that any allocations that attempt - * to cover the maximum potential vector length (such as happen with - * the regset used for ptrace) end up being extremely large. Define - * the much lower actual limit for use in such situations. + * the architecture. Using this length to allocate worst size buffers + * results in excessively large allocations, and this effect is even + * more pronounced for SME due to ZA. Define more suitable VLs for + * these situations. */ -#define SME_VQ_MAX 16 +#define ARCH_SVE_VQ_MAX ((ZCR_ELx_LEN_MASK >> ZCR_ELx_LEN_SHIFT) + 1) +#define SME_VQ_MAX ((SMCR_ELx_LEN_MASK >> SMCR_ELx_LEN_SHIFT) + 1) struct task_struct; @@ -343,6 +343,7 @@ extern void sme_alloc(struct task_struct *task, bool flush); extern unsigned int sme_get_vl(void); extern int sme_set_current_vl(unsigned long arg); extern int sme_get_current_vl(void); +extern void sme_suspend_exit(void); /* * Return how many bytes of memory are required to store the full SME @@ -372,6 +373,7 @@ static inline int sme_max_vl(void) { return 0; } static inline int sme_max_virtualisable_vl(void) { return 0; } static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; } static inline int sme_get_current_vl(void) { return -EINVAL; } +static inline void sme_suspend_exit(void) { } static inline size_t za_state_size(struct task_struct const *task) { diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h index cea441b6aa5dc63317f595a04eb745c4f0b3b8d7..b5bd3c38a01b2cf7b27f7447e934ba8f8d420eec 100644 --- a/arch/arm64/include/asm/jump_label.h +++ b/arch/arm64/include/asm/jump_label.h @@ -18,7 +18,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto( + asm goto( "1: nop \n\t" " .pushsection __jump_table, \"aw\" \n\t" " .align 3 \n\t" @@ -35,7 +35,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto( + asm goto( "1: b %l[l_yes] \n\t" " .pushsection __jump_table, \"aw\" \n\t" " .align 3 \n\t" diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h index c503db8e73b01710d935d556143272b846d5f786..f99d74826a7ef8a98314bc6c5fa7793d4aba63e6 100644 --- a/arch/arm64/include/asm/lse.h +++ b/arch/arm64/include/asm/lse.h @@ -10,7 +10,6 @@ #include #include -#include #include #include #include diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 61f22e9c92b4c10a20f8a1a8cbed27cfcdf22f70..74584597bfb821686d790b5ef44217baedc566d8 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -390,6 +390,7 @@ static const struct midr_range erratum_1463225[] = { static const struct midr_range trbe_overwrite_fill_mode_cpus[] = { #ifdef CONFIG_ARM64_ERRATUM_2139208 MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100), #endif #ifdef CONFIG_ARM64_ERRATUM_2119858 MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), @@ -403,6 +404,7 @@ static const struct midr_range trbe_overwrite_fill_mode_cpus[] = { static const struct midr_range tsb_flush_fail_cpus[] = { #ifdef CONFIG_ARM64_ERRATUM_2067961 MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100), #endif #ifdef CONFIG_ARM64_ERRATUM_2054223 MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), @@ -415,6 +417,7 @@ static const struct midr_range tsb_flush_fail_cpus[] = { static struct midr_range trbe_write_out_of_range_cpus[] = { #ifdef CONFIG_ARM64_ERRATUM_2253138 MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100), #endif #ifdef CONFIG_ARM64_ERRATUM_2224489 MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 8c226d79abdfceabbf43f9c167b6926a0a6cf4ce..59b5a16bab5d6b24d4539ca9d12677f536ba86e4 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1347,6 +1347,20 @@ void __init sme_setup(void) get_sme_default_vl()); } +void sme_suspend_exit(void) +{ + u64 smcr = 0; + + if (!system_supports_sme()) + return; + + if (system_supports_fa64()) + smcr |= SMCR_ELx_FA64; + + write_sysreg_s(smcr, SYS_SMCR_EL1); + write_sysreg_s(0, SYS_SMPRI_EL1); +} + #endif /* CONFIG_ARM64_SME */ static void sve_init_regs(void) diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index e1f6366b7ccdf07bc008ce379c0b1556070b5326..d02dd2be17b3b93d0b409f88ac4a8367e9390cb0 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1450,7 +1450,8 @@ static const struct user_regset aarch64_regsets[] = { #ifdef CONFIG_ARM64_SVE [REGSET_SVE] = { /* Scalable Vector Extension */ .core_note_type = NT_ARM_SVE, - .n = DIV_ROUND_UP(SVE_PT_SIZE(SVE_VQ_MAX, SVE_PT_REGS_SVE), + .n = DIV_ROUND_UP(SVE_PT_SIZE(ARCH_SVE_VQ_MAX, + SVE_PT_REGS_SVE), SVE_VQ_BYTES), .size = SVE_VQ_BYTES, .align = SVE_VQ_BYTES, diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 8b02d310838f92404c7d61a1083ffa8398194d20..064d996cc55b24b62ffe0f49e9f3af5188fef105 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -77,6 +78,8 @@ void notrace __cpu_suspend_exit(void) */ spectre_v4_enable_mitigation(NULL); + sme_suspend_exit(); + /* Restore additional feature-specific configuration */ ptrauth_suspend_exit(); } diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 36c8f66cad251ac3711f73f5b94d353311bde0b7..d513533cc922fa338fb427e431a0d1c4d2a1d30b 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -68,11 +68,9 @@ VDSO_CFLAGS += -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -fno-common \ -Werror-implicit-function-declaration \ -Wno-format-security \ - -Wdeclaration-after-statement \ -std=gnu11 VDSO_CFLAGS += -O2 # Some useful compiler-dependent flags from top-level Makefile -VDSO_CFLAGS += $(call cc32-option,-Wdeclaration-after-statement,) VDSO_CFLAGS += $(call cc32-option,-Wno-pointer-sign) VDSO_CFLAGS += -fno-strict-overflow VDSO_CFLAGS += $(call cc32-option,-Werror=strict-prototypes) diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 3c344e4cd4cadcbf0af0fdcdd7914153b6f2f928..092327665a6efe275557562813112380acbfbbc1 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -462,6 +462,9 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) } irq = vgic_get_irq(vcpu->kvm, NULL, intids[i]); + if (!irq) + continue; + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = pendmask & (1U << bit_nr); vgic_queue_irq_unlock(vcpu->kvm, irq, flags); @@ -1427,6 +1430,8 @@ static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its, for (i = 0; i < irq_count; i++) { irq = vgic_get_irq(kvm, NULL, intids[i]); + if (!irq) + continue; update_affinity(irq, vcpu2); diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c index bf4b3d9631ce14618bb39aedcec9e0627720af82..63731fb3d8f63c54456ae9c48430dfba51fa5869 100644 --- a/arch/arm64/kvm/vgic/vgic-kvm-device.c +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -337,16 +337,12 @@ int kvm_register_vgic_device(unsigned long type) int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, struct vgic_reg_attr *reg_attr) { - int cpuid; + int cpuid = FIELD_GET(KVM_DEV_ARM_VGIC_CPUID_MASK, attr->attr); - cpuid = (attr->attr & KVM_DEV_ARM_VGIC_CPUID_MASK) >> - KVM_DEV_ARM_VGIC_CPUID_SHIFT; - - if (cpuid >= atomic_read(&dev->kvm->online_vcpus)) - return -EINVAL; - - reg_attr->vcpu = kvm_get_vcpu(dev->kvm, cpuid); reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; + reg_attr->vcpu = kvm_get_vcpu_by_id(dev->kvm, cpuid); + if (!reg_attr->vcpu) + return -EINVAL; return 0; } diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 826cb200b204f293b337287a61cfb51fbbe76b91..425b398f8d4565e27eb58322a9782be809cc3f8b 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -220,9 +220,6 @@ bool kernel_page_present(struct page *page) pte_t *ptep; unsigned long addr = (unsigned long)page_address(page); - if (!can_set_direct_map()) - return true; - pgdp = pgd_offset_k(addr); if (pgd_none(READ_ONCE(*pgdp))) return false; diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 0ce5f13eabb1bb972a24c116cce56bea4a1aa56c..afb79209d41321017016ee06e71576440e33d20a 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1679,15 +1679,15 @@ static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l, emit_call(enter_prog, ctx); + /* save return value to callee saved register x20 */ + emit(A64_MOV(1, A64_R(20), A64_R(0)), ctx); + /* if (__bpf_prog_enter(prog) == 0) * goto skip_exec_of_prog; */ branch = ctx->image + ctx->idx; emit(A64_NOP, ctx); - /* save return value to callee saved register x20 */ - emit(A64_MOV(1, A64_R(20), A64_R(0)), ctx); - emit(A64_ADD_I(1, A64_R(0), A64_SP, args_off), ctx); if (!p->jited) emit_addr_mov_i64(A64_R(1), (const u64)p->insnsi, ctx); diff --git a/arch/csky/include/asm/jump_label.h b/arch/csky/include/asm/jump_label.h index 98a3f4b168bd2687f3e4828aa681d29e0c13b97e..ef2e37a10a0feb9af3543481cffddd75c5b3a8ef 100644 --- a/arch/csky/include/asm/jump_label.h +++ b/arch/csky/include/asm/jump_label.h @@ -12,7 +12,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto( + asm goto( "1: nop32 \n" " .pushsection __jump_table, \"aw\" \n" " .align 2 \n" @@ -29,7 +29,7 @@ label: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto( + asm goto( "1: bsr32 %l[label] \n" " .pushsection __jump_table, \"aw\" \n" " .align 2 \n" diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S index 57465bff1fe49717cbf0b68280bae499e337b9d7..df7f349c8d4f3c00a4186f154a587765ef0ac685 100644 --- a/arch/hexagon/kernel/vmlinux.lds.S +++ b/arch/hexagon/kernel/vmlinux.lds.S @@ -64,6 +64,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG ELF_DETAILS + .hexagon.attributes 0 : { *(.hexagon.attributes) } DISCARDS } diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index e737dc8cd660c2b5a4edfbb6e134f65e49524541..fa3171f56327451023ccca7906ecf4e48c9f76c7 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -9,6 +9,7 @@ config LOONGARCH select ARCH_BINFMT_ELF_STATE select ARCH_ENABLE_MEMORY_HOTPLUG select ARCH_ENABLE_MEMORY_HOTREMOVE + select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PTE_SPECIAL @@ -80,6 +81,7 @@ config LOONGARCH select GPIOLIB select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_MMAP_RND_BITS if MMU + select HAVE_ARCH_SECCOMP select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE @@ -461,23 +463,6 @@ config PHYSICAL_START specified in the "crashkernel=YM@XM" command line boot parameter passed to the panic-ed kernel). -config SECCOMP - bool "Enable seccomp to safely compute untrusted bytecode" - depends on PROC_FS - default y - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via /proc//seccomp, it cannot be disabled - and the task is only allowed to execute a few safe syscalls - defined by each seccomp mode. - - If unsure, say Y. Only embedded should say N here. - endmenu config ARCH_SELECT_MEMORY_MODEL @@ -495,10 +480,6 @@ config ARCH_SPARSEMEM_ENABLE or have huge holes in the physical address space for other reasons. See for more. -config ARCH_ENABLE_THP_MIGRATION - def_bool y - depends on TRANSPARENT_HUGEPAGE - config ARCH_MEMORY_PROBE def_bool y depends on MEMORY_HOTPLUG diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h index 402a7d9e3a53eafed41c4170de5627f673d142f4..427d147f30d7f6483b79988f064b2003396db35b 100644 --- a/arch/loongarch/include/asm/io.h +++ b/arch/loongarch/include/asm/io.h @@ -72,6 +72,8 @@ extern void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t #define memcpy_fromio(a, c, l) __memcpy_fromio((a), (c), (l)) #define memcpy_toio(c, a, l) __memcpy_toio((c), (a), (l)) +#define __io_aw() mmiowb() + #include #define ARCH_HAS_VALID_PHYS_ADDR_RANGE diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h index 302f0e33975a234fd4051a903bdbe6842284a003..c90c56094168575e3d146d4cd5101bad1ba682df 100644 --- a/arch/loongarch/include/asm/percpu.h +++ b/arch/loongarch/include/asm/percpu.h @@ -25,7 +25,12 @@ static inline void set_my_cpu_offset(unsigned long off) __my_cpu_offset = off; csr_write64(off, PERCPU_BASE_KS); } -#define __my_cpu_offset __my_cpu_offset + +#define __my_cpu_offset \ +({ \ + __asm__ __volatile__("":"+r"(__my_cpu_offset)); \ + __my_cpu_offset; \ +}) #define PERCPU_OP(op, asm_op, c_op) \ static __always_inline unsigned long __percpu_##op(void *ptr, \ diff --git a/arch/loongarch/include/asm/perf_event.h b/arch/loongarch/include/asm/perf_event.h index 2a35a0bc2aaabf128cb5336d25dcbec1738d646b..52b638059e40b31645a62243e467c09e7d7ce0cf 100644 --- a/arch/loongarch/include/asm/perf_event.h +++ b/arch/loongarch/include/asm/perf_event.h @@ -7,6 +7,14 @@ #ifndef __LOONGARCH_PERF_EVENT_H__ #define __LOONGARCH_PERF_EVENT_H__ +#include + #define perf_arch_bpf_user_pt_regs(regs) (struct user_pt_regs *)regs +#define perf_arch_fetch_caller_regs(regs, __ip) { \ + (regs)->csr_era = (__ip); \ + (regs)->regs[3] = current_stack_pointer; \ + (regs)->regs[22] = (unsigned long) __builtin_frame_address(0); \ +} + #endif /* __LOONGARCH_PERF_EVENT_H__ */ diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index e0404df2c952f573e9ef9292f6715358da670ac2..18a2b37f4aea37136e33da0fdc81dbd0e7e9763a 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -297,6 +297,7 @@ void play_dead(void) addr = iocsr_read64(LOONGARCH_IOCSR_MBUF0); } while (addr == 0); + local_irq_disable(); init_fn = (void *)TO_CACHE(addr); iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_CLEAR); diff --git a/arch/loongarch/mm/fault.c b/arch/loongarch/mm/fault.c index b829ab911a17b137d01f2754fdff1a35262b5e92..007718d51f0955e8d1bf63f509ea57379e3e15cf 100644 --- a/arch/loongarch/mm/fault.c +++ b/arch/loongarch/mm/fault.c @@ -193,10 +193,10 @@ good_area: if (!(vma->vm_flags & VM_WRITE)) goto bad_area; } else { - if (!(vma->vm_flags & VM_READ) && address != exception_era(regs)) - goto bad_area; if (!(vma->vm_flags & VM_EXEC) && address == exception_era(regs)) goto bad_area; + if (!(vma->vm_flags & (VM_READ | VM_WRITE)) && address != exception_era(regs)) + goto bad_area; } /* diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h index 4044eaf989ac7dad0f2094c5d4cfab05ac9fb5c3..0921ddda11a4b353c1c4d754417d3de4d003c12f 100644 --- a/arch/mips/include/asm/checksum.h +++ b/arch/mips/include/asm/checksum.h @@ -241,7 +241,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, " .set pop" : "=&r" (sum), "=&r" (tmp) : "r" (saddr), "r" (daddr), - "0" (htonl(len)), "r" (htonl(proto)), "r" (sum)); + "0" (htonl(len)), "r" (htonl(proto)), "r" (sum) + : "memory"); return csum_fold(sum); } diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h index c5c6864e64bc430a98b2acfce5e4eb13b16dee0a..405c85173f2c168353e91f498ee75ac7197b7514 100644 --- a/arch/mips/include/asm/jump_label.h +++ b/arch/mips/include/asm/jump_label.h @@ -36,7 +36,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\t" B_INSN " 2f\n\t" + asm goto("1:\t" B_INSN " 2f\n\t" "2:\t.insn\n\t" ".pushsection __jump_table, \"aw\"\n\t" WORD_INSN " 1b, %l[l_yes], %0\n\t" @@ -50,7 +50,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\t" J_INSN " %l[l_yes]\n\t" + asm goto("1:\t" J_INSN " %l[l_yes]\n\t" ".pushsection __jump_table, \"aw\"\n\t" WORD_INSN " 1b, %l[l_yes], %0\n\t" ".popsection\n\t" diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h index daf3cf244ea972c9a8bf134a09fa081931645425..428b9f1cf1de2770c4d58846e2de8b719e5fa3d9 100644 --- a/arch/mips/include/asm/ptrace.h +++ b/arch/mips/include/asm/ptrace.h @@ -60,6 +60,7 @@ static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long val) { regs->cp0_epc = val; + regs->cp0_cause &= ~CAUSEF_BD; } /* Query offset/name of register from its name/offset */ @@ -156,7 +157,7 @@ static inline long regs_return_value(struct pt_regs *regs) #define instruction_pointer(regs) ((regs)->cp0_epc) #define profile_pc(regs) instruction_pointer(regs) -extern asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall); +extern asmlinkage long syscall_trace_enter(struct pt_regs *regs); extern asmlinkage void syscall_trace_leave(struct pt_regs *regs); extern void die(const char *, struct pt_regs *) __noreturn; diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c index c4501897b870b76fda486b9c919bdaffbd39b353..08342b9eccdbd9120c5deb286ce912294b7368d8 100644 --- a/arch/mips/kernel/asm-offsets.c +++ b/arch/mips/kernel/asm-offsets.c @@ -98,6 +98,7 @@ void output_thread_info_defines(void) OFFSET(TI_CPU, thread_info, cpu); OFFSET(TI_PRE_COUNT, thread_info, preempt_count); OFFSET(TI_REGS, thread_info, regs); + OFFSET(TI_SYSCALL, thread_info, syscall); DEFINE(_THREAD_SIZE, THREAD_SIZE); DEFINE(_THREAD_MASK, THREAD_MASK); DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE); diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 567aec4abac0f4898083f77674cf26b1ad87265c..a8e569830ec8d679ef829889b0d483be365e3996 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -1309,16 +1309,13 @@ long arch_ptrace(struct task_struct *child, long request, * Notification of system call entry/exit * - triggered by current->work.syscall_trace */ -asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall) +asmlinkage long syscall_trace_enter(struct pt_regs *regs) { user_exit(); - current_thread_info()->syscall = syscall; - if (test_thread_flag(TIF_SYSCALL_TRACE)) { if (ptrace_report_syscall_entry(regs)) return -1; - syscall = current_thread_info()->syscall; } #ifdef CONFIG_SECCOMP @@ -1327,7 +1324,7 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall) struct seccomp_data sd; unsigned long args[6]; - sd.nr = syscall; + sd.nr = current_thread_info()->syscall; sd.arch = syscall_get_arch(current); syscall_get_arguments(current, regs, args); for (i = 0; i < 6; i++) @@ -1337,23 +1334,23 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall) ret = __secure_computing(&sd); if (ret == -1) return ret; - syscall = current_thread_info()->syscall; } #endif if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->regs[2]); - audit_syscall_entry(syscall, regs->regs[4], regs->regs[5], + audit_syscall_entry(current_thread_info()->syscall, + regs->regs[4], regs->regs[5], regs->regs[6], regs->regs[7]); /* * Negative syscall numbers are mistaken for rejected syscalls, but * won't have had the return value set appropriately, so we do so now. */ - if (syscall < 0) + if (current_thread_info()->syscall < 0) syscall_set_return_value(current, regs, -ENOSYS, 0); - return syscall; + return current_thread_info()->syscall; } /* diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index 18dc9b34505614d2bc84767479a3e9972c1ba8ad..2c604717e63080b1c1949a080bfadf1cab94acd6 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -77,6 +77,18 @@ loads_done: PTR_WD load_a7, bad_stack_a7 .previous + /* + * syscall number is in v0 unless we called syscall(__NR_###) + * where the real syscall number is in a0 + */ + subu t2, v0, __NR_O32_Linux + bnez t2, 1f /* __NR_syscall at offset 0 */ + LONG_S a0, TI_SYSCALL($28) # Save a0 as syscall number + b 2f +1: + LONG_S v0, TI_SYSCALL($28) # Save v0 as syscall number +2: + lw t0, TI_FLAGS($28) # syscall tracing enabled? li t1, _TIF_WORK_SYSCALL_ENTRY and t0, t1 @@ -114,16 +126,7 @@ syscall_trace_entry: SAVE_STATIC move a0, sp - /* - * syscall number is in v0 unless we called syscall(__NR_###) - * where the real syscall number is in a0 - */ - move a1, v0 - subu t2, v0, __NR_O32_Linux - bnez t2, 1f /* __NR_syscall at offset 0 */ - lw a1, PT_R4(sp) - -1: jal syscall_trace_enter + jal syscall_trace_enter bltz v0, 1f # seccomp failed? Skip syscall diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 97456b2ca7dc32f13cac9a5843a3adea89735318..97788859238c344a64d1f75f2fdd6c2a4bc58006 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -44,6 +44,8 @@ NESTED(handle_sysn32, PT_SIZE, sp) sd a3, PT_R26(sp) # save a3 for syscall restarting + LONG_S v0, TI_SYSCALL($28) # Store syscall number + li t1, _TIF_WORK_SYSCALL_ENTRY LONG_L t0, TI_FLAGS($28) # syscall tracing enabled? and t0, t1, t0 @@ -72,7 +74,6 @@ syscall_common: n32_syscall_trace_entry: SAVE_STATIC move a0, sp - move a1, v0 jal syscall_trace_enter bltz v0, 1f # seccomp failed? Skip syscall diff --git a/arch/mips/kernel/scall64-n64.S b/arch/mips/kernel/scall64-n64.S index e6264aa62e457f02b8a50df8b266a58b8361717d..be11ea5cc67e043c8a20fe0fecb4a0414b589ee9 100644 --- a/arch/mips/kernel/scall64-n64.S +++ b/arch/mips/kernel/scall64-n64.S @@ -46,6 +46,8 @@ NESTED(handle_sys64, PT_SIZE, sp) sd a3, PT_R26(sp) # save a3 for syscall restarting + LONG_S v0, TI_SYSCALL($28) # Store syscall number + li t1, _TIF_WORK_SYSCALL_ENTRY LONG_L t0, TI_FLAGS($28) # syscall tracing enabled? and t0, t1, t0 @@ -82,7 +84,6 @@ n64_syscall_exit: syscall_trace_entry: SAVE_STATIC move a0, sp - move a1, v0 jal syscall_trace_enter bltz v0, 1f # seccomp failed? Skip syscall diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index d3c2616cba22690bffd63b4521dc0f0ea7216315..7a5abb73e53127876af7e9d5f13dae2f8b08c3e8 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -79,6 +79,22 @@ loads_done: PTR_WD load_a7, bad_stack_a7 .previous + /* + * absolute syscall number is in v0 unless we called syscall(__NR_###) + * where the real syscall number is in a0 + * note: NR_syscall is the first O32 syscall but the macro is + * only defined when compiling with -mabi=32 (CONFIG_32BIT) + * therefore __NR_O32_Linux is used (4000) + */ + + subu t2, v0, __NR_O32_Linux + bnez t2, 1f /* __NR_syscall at offset 0 */ + LONG_S a0, TI_SYSCALL($28) # Save a0 as syscall number + b 2f +1: + LONG_S v0, TI_SYSCALL($28) # Save v0 as syscall number +2: + li t1, _TIF_WORK_SYSCALL_ENTRY LONG_L t0, TI_FLAGS($28) # syscall tracing enabled? and t0, t1, t0 @@ -113,22 +129,7 @@ trace_a_syscall: sd a7, PT_R11(sp) # For indirect syscalls move a0, sp - /* - * absolute syscall number is in v0 unless we called syscall(__NR_###) - * where the real syscall number is in a0 - * note: NR_syscall is the first O32 syscall but the macro is - * only defined when compiling with -mabi=32 (CONFIG_32BIT) - * therefore __NR_O32_Linux is used (4000) - */ - .set push - .set reorder - subu t1, v0, __NR_O32_Linux - move a1, v0 - bnez t1, 1f /* __NR_syscall at offset 0 */ - ld a1, PT_R4(sp) /* Arg1 for __NR_syscall case */ - .set pop - -1: jal syscall_trace_enter + jal syscall_trace_enter bltz v0, 1f # seccomp failed? Skip syscall diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 246c6a6b02614cdc396749ce1d21da3ee5763b74..5b778995d44831ea58ee23590237b5b401b4010a 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -2007,7 +2007,13 @@ unsigned long vi_handlers[64]; void reserve_exception_space(phys_addr_t addr, unsigned long size) { - memblock_reserve(addr, size); + /* + * reserve exception space on CPUs other than CPU0 + * is too late, since memblock is unavailable when APs + * up + */ + if (smp_processor_id() == 0) + memblock_reserve(addr, size); } void __init *set_except_vector(int n, void *addr) diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 345d5e021484c443fcaff304c33ab47a1f122fe6..abf39ecda6fb1b5f77f261258ffba4c96f0fa998 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -24,7 +24,6 @@ config PARISC select RTC_DRV_GENERIC select INIT_ALL_POSSIBLE select BUG - select BUILDTIME_TABLE_SORT select HAVE_PCI select HAVE_PERF_EVENTS select HAVE_KERNEL_BZIP2 diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h index 74d17d7e759da9dfa89aa1a504b94de4554db16d..000a28e1c5e8d43aba8ed5185e86c654cf5ad5a0 100644 --- a/arch/parisc/include/asm/assembly.h +++ b/arch/parisc/include/asm/assembly.h @@ -97,26 +97,28 @@ * version takes two arguments: a src and destination register. * However, the source and destination registers can not be * the same register. + * + * We use add,l to avoid clobbering the C/B bits in the PSW. */ .macro tophys grvirt, grphys - ldil L%(__PAGE_OFFSET), \grphys - sub \grvirt, \grphys, \grphys + ldil L%(-__PAGE_OFFSET), \grphys + addl \grvirt, \grphys, \grphys .endm - + .macro tovirt grphys, grvirt ldil L%(__PAGE_OFFSET), \grvirt - add \grphys, \grvirt, \grvirt + addl \grphys, \grvirt, \grvirt .endm .macro tophys_r1 gr - ldil L%(__PAGE_OFFSET), %r1 - sub \gr, %r1, \gr + ldil L%(-__PAGE_OFFSET), %r1 + addl \gr, %r1, \gr .endm - + .macro tovirt_r1 gr ldil L%(__PAGE_OFFSET), %r1 - add \gr, %r1, \gr + addl \gr, %r1, \gr .endm .macro delay value @@ -576,6 +578,7 @@ .section __ex_table,"aw" ! \ .align 4 ! \ .word (fault_addr - .), (except_addr - .) ! \ + or %r0,%r0,%r0 ! \ .previous diff --git a/arch/parisc/include/asm/checksum.h b/arch/parisc/include/asm/checksum.h index 3c43baca7b397ddd4b4b09c671066e9b9cca81e1..2aceebcd695c8057d14e8cf58f45e230a9f16d38 100644 --- a/arch/parisc/include/asm/checksum.h +++ b/arch/parisc/include/asm/checksum.h @@ -40,7 +40,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) " addc %0, %5, %0\n" " addc %0, %3, %0\n" "1: ldws,ma 4(%1), %3\n" -" addib,< 0, %2, 1b\n" +" addib,> -1, %2, 1b\n" " addc %0, %3, %0\n" "\n" " extru %0, 31, 16, %4\n" @@ -126,6 +126,7 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, ** Try to keep 4 registers with "live" values ahead of the ALU. */ +" depdi 0, 31, 32, %0\n"/* clear upper half of incoming checksum */ " ldd,ma 8(%1), %4\n" /* get 1st saddr word */ " ldd,ma 8(%2), %5\n" /* get 1st daddr word */ " add %4, %0, %0\n" @@ -137,8 +138,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, " add,dc %3, %0, %0\n" /* fold in proto+len | carry bit */ " extrd,u %0, 31, 32, %4\n"/* copy upper half down */ " depdi 0, 31, 32, %0\n"/* clear upper half */ -" add %4, %0, %0\n" /* fold into 32-bits */ -" addc 0, %0, %0\n" /* add carry */ +" add,dc %4, %0, %0\n" /* fold into 32-bits, plus carry */ +" addc 0, %0, %0\n" /* add final carry */ #else @@ -163,7 +164,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, " ldw,ma 4(%2), %7\n" /* 4th daddr */ " addc %6, %0, %0\n" " addc %7, %0, %0\n" -" addc %3, %0, %0\n" /* fold in proto+len, catch carry */ +" addc %3, %0, %0\n" /* fold in proto+len */ +" addc 0, %0, %0\n" /* add carry */ #endif : "=r" (sum), "=r" (saddr), "=r" (daddr), "=r" (len), diff --git a/arch/parisc/include/asm/extable.h b/arch/parisc/include/asm/extable.h new file mode 100644 index 0000000000000000000000000000000000000000..4ea23e3d79dc9034543465db2b0a4856324a4477 --- /dev/null +++ b/arch/parisc/include/asm/extable.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PARISC_EXTABLE_H +#define __PARISC_EXTABLE_H + +#include +#include + +/* + * The exception table consists of three addresses: + * + * - A relative address to the instruction that is allowed to fault. + * - A relative address at which the program should continue (fixup routine) + * - An asm statement which specifies which CPU register will + * receive -EFAULT when an exception happens if the lowest bit in + * the fixup address is set. + * + * Note: The register specified in the err_opcode instruction will be + * modified at runtime if a fault happens. Register %r0 will be ignored. + * + * Since relative addresses are used, 32bit values are sufficient even on + * 64bit kernel. + */ + +struct pt_regs; +int fixup_exception(struct pt_regs *regs); + +#define ARCH_HAS_RELATIVE_EXTABLE +struct exception_table_entry { + int insn; /* relative address of insn that is allowed to fault. */ + int fixup; /* relative address of fixup routine */ + int err_opcode; /* sample opcode with register which holds error code */ +}; + +#define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr, opcode )\ + ".section __ex_table,\"aw\"\n" \ + ".align 4\n" \ + ".word (" #fault_addr " - .), (" #except_addr " - .)\n" \ + opcode "\n" \ + ".previous\n" + +/* + * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() creates a special exception table entry + * (with lowest bit set) for which the fault handler in fixup_exception() will + * load -EFAULT on fault into the register specified by the err_opcode instruction, + * and zeroes the target register in case of a read fault in get_user(). + */ +#define ASM_EXCEPTIONTABLE_VAR(__err_var) \ + int __err_var = 0 +#define ASM_EXCEPTIONTABLE_ENTRY_EFAULT( fault_addr, except_addr, register )\ + ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1, "or %%r0,%%r0," register) + +static inline void swap_ex_entry_fixup(struct exception_table_entry *a, + struct exception_table_entry *b, + struct exception_table_entry tmp, + int delta) +{ + a->fixup = b->fixup + delta; + b->fixup = tmp.fixup - delta; + a->err_opcode = b->err_opcode; + b->err_opcode = tmp.err_opcode; +} +#define swap_ex_entry_fixup swap_ex_entry_fixup + +#endif diff --git a/arch/parisc/include/asm/jump_label.h b/arch/parisc/include/asm/jump_label.h index 94428798b6aa63e8d4b0878cc7555826cf080e47..317ebc5edc9fe99950f4efe55d989db453f46d0d 100644 --- a/arch/parisc/include/asm/jump_label.h +++ b/arch/parisc/include/asm/jump_label.h @@ -12,7 +12,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".align %1\n\t" @@ -29,7 +29,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "b,n %l[l_yes]\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".align %1\n\t" diff --git a/arch/parisc/include/asm/special_insns.h b/arch/parisc/include/asm/special_insns.h index c822bd0c0e3c6ccb86b4190d15500589c70f353a..51f40eaf7780659263f37b7c10fa7bd4ecf4ced7 100644 --- a/arch/parisc/include/asm/special_insns.h +++ b/arch/parisc/include/asm/special_insns.h @@ -8,7 +8,8 @@ "copy %%r0,%0\n" \ "8:\tlpa %%r0(%1),%0\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY(8b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY(8b, 9b, \ + "or %%r0,%%r0,%%r0") \ : "=&r" (pa) \ : "r" (va) \ : "memory" \ @@ -22,7 +23,8 @@ "copy %%r0,%0\n" \ "8:\tlpa %%r0(%%sr3,%1),%0\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY(8b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY(8b, 9b, \ + "or %%r0,%%r0,%%r0") \ : "=&r" (pa) \ : "r" (va) \ : "memory" \ diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 4165079898d9e7af239a31a1bc77821e6081706a..88d0ae5769dde54e29176e286da359eb6a54e7bf 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -7,6 +7,7 @@ */ #include #include +#include #include #include @@ -26,37 +27,6 @@ #define STD_USER(sr, x, ptr) __put_user_asm(sr, "std", x, ptr) #endif -/* - * The exception table contains two values: the first is the relative offset to - * the address of the instruction that is allowed to fault, and the second is - * the relative offset to the address of the fixup routine. Since relative - * addresses are used, 32bit values are sufficient even on 64bit kernel. - */ - -#define ARCH_HAS_RELATIVE_EXTABLE -struct exception_table_entry { - int insn; /* relative address of insn that is allowed to fault. */ - int fixup; /* relative address of fixup routine */ -}; - -#define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr )\ - ".section __ex_table,\"aw\"\n" \ - ".align 4\n" \ - ".word (" #fault_addr " - .), (" #except_addr " - .)\n\t" \ - ".previous\n" - -/* - * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() creates a special exception table entry - * (with lowest bit set) for which the fault handler in fixup_exception() will - * load -EFAULT into %r29 for a read or write fault, and zeroes the target - * register in case of a read fault in get_user(). - */ -#define ASM_EXCEPTIONTABLE_REG 29 -#define ASM_EXCEPTIONTABLE_VAR(__variable) \ - register long __variable __asm__ ("r29") = 0 -#define ASM_EXCEPTIONTABLE_ENTRY_EFAULT( fault_addr, except_addr )\ - ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1) - #define __get_user_internal(sr, val, ptr) \ ({ \ ASM_EXCEPTIONTABLE_VAR(__gu_err); \ @@ -83,7 +53,7 @@ struct exception_table_entry { \ __asm__("1: " ldx " 0(%%sr%2,%3),%0\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%1") \ : "=r"(__gu_val), "+r"(__gu_err) \ : "i"(sr), "r"(ptr)); \ \ @@ -115,8 +85,8 @@ struct exception_table_entry { "1: ldw 0(%%sr%2,%3),%0\n" \ "2: ldw 4(%%sr%2,%3),%R0\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%1") \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b, "%1") \ : "=&r"(__gu_tmp.l), "+r"(__gu_err) \ : "i"(sr), "r"(ptr)); \ \ @@ -174,7 +144,7 @@ struct exception_table_entry { __asm__ __volatile__ ( \ "1: " stx " %1,0(%%sr%2,%3)\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%0") \ : "+r"(__pu_err) \ : "r"(x), "i"(sr), "r"(ptr)) @@ -186,15 +156,14 @@ struct exception_table_entry { "1: stw %1,0(%%sr%2,%3)\n" \ "2: stw %R1,4(%%sr%2,%3)\n" \ "9:\n" \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \ - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b) \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%0") \ + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b, "%0") \ : "+r"(__pu_err) \ : "r"(__val), "i"(sr), "r"(ptr)); \ } while (0) #endif /* !defined(CONFIG_64BIT) */ - /* * Complex access routines -- external declarations */ @@ -216,7 +185,4 @@ unsigned long __must_check raw_copy_from_user(void *dst, const void __user *src, #define INLINE_COPY_TO_USER #define INLINE_COPY_FROM_USER -struct pt_regs; -int fixup_exception(struct pt_regs *regs); - #endif /* __PARISC_UACCESS_H */ diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c index 8f12b9f318ae6770457f5dc28dd5472efe27d7f0..a582928739dd5ed6eacc00e2afadf5a004ebc1e7 100644 --- a/arch/parisc/kernel/drivers.c +++ b/arch/parisc/kernel/drivers.c @@ -1003,6 +1003,9 @@ static __init int qemu_print_iodc_data(struct device *lin_dev, void *data) pr_info("\n"); + /* Prevent hung task messages when printing on serial console */ + cond_resched(); + pr_info("#define HPA_%08lx_DESCRIPTION \"%s\"\n", hpa, parisc_hardware_description(&dev->id)); diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index 4d392e4ed35847363b7f5f37836edaf607c64b3c..ac7253891d5ed92e491f0b5024b41256c6fd2d79 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -78,7 +78,7 @@ void notrace __hot ftrace_function_trampoline(unsigned long parent, #endif } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER +#if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_FUNCTION_GRAPH_TRACER) int ftrace_enable_ftrace_graph_caller(void) { static_key_enable(&ftrace_graph_enable.key); diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index 1f6c776d80813e2db2e76a274b1668d6a4e28b90..c67883487ecd34f59b48cfd3827fd5afa1ffa21f 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -171,7 +171,6 @@ static int __init processor_probe(struct parisc_device *dev) p->cpu_num = cpu_info.cpu_num; p->cpu_loc = cpu_info.cpu_loc; - set_cpu_possible(cpuid, true); store_cpu_topology(cpuid); #ifdef CONFIG_SMP @@ -466,13 +465,6 @@ static struct parisc_driver cpu_driver __refdata = { */ void __init processor_init(void) { - unsigned int cpu; - reset_cpu_topology(); - - /* reset possible mask. We will mark those which are possible. */ - for_each_possible_cpu(cpu) - set_cpu_possible(cpu, false); - register_parisc_driver(&cpu_driver); } diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c index e8a4d77cff53a77ee20d0e0319fa360d208cdd6d..782ee05e20889ac3742e0b8f735da5a92524b492 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -118,8 +118,8 @@ static int emulate_ldh(struct pt_regs *regs, int toreg) "2: ldbs 1(%%sr1,%3), %0\n" " depw %2, 23, 24, %0\n" "3: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1") : "+r" (val), "+r" (ret), "=&r" (temp1) : "r" (saddr), "r" (regs->isr) ); @@ -150,8 +150,8 @@ static int emulate_ldw(struct pt_regs *regs, int toreg, int flop) " mtctl %2,11\n" " vshd %0,%3,%0\n" "3: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1") : "+r" (val), "+r" (ret), "=&r" (temp1), "=&r" (temp2) : "r" (saddr), "r" (regs->isr) ); @@ -167,6 +167,7 @@ static int emulate_ldw(struct pt_regs *regs, int toreg, int flop) static int emulate_ldd(struct pt_regs *regs, int toreg, int flop) { unsigned long saddr = regs->ior; + unsigned long shift, temp1; __u64 val = 0; ASM_EXCEPTIONTABLE_VAR(ret); @@ -178,25 +179,22 @@ static int emulate_ldd(struct pt_regs *regs, int toreg, int flop) #ifdef CONFIG_64BIT __asm__ __volatile__ ( -" depd,z %3,60,3,%%r19\n" /* r19=(ofs&7)*8 */ -" mtsp %4, %%sr1\n" -" depd %%r0,63,3,%3\n" -"1: ldd 0(%%sr1,%3),%0\n" -"2: ldd 8(%%sr1,%3),%%r20\n" -" subi 64,%%r19,%%r19\n" -" mtsar %%r19\n" -" shrpd %0,%%r20,%%sar,%0\n" +" depd,z %2,60,3,%3\n" /* shift=(ofs&7)*8 */ +" mtsp %5, %%sr1\n" +" depd %%r0,63,3,%2\n" +"1: ldd 0(%%sr1,%2),%0\n" +"2: ldd 8(%%sr1,%2),%4\n" +" subi 64,%3,%3\n" +" mtsar %3\n" +" shrpd %0,%4,%%sar,%0\n" "3: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b) - : "=r" (val), "+r" (ret) - : "0" (val), "r" (saddr), "r" (regs->isr) - : "r19", "r20" ); + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1") + : "+r" (val), "+r" (ret), "+r" (saddr), "=&r" (shift), "=&r" (temp1) + : "r" (regs->isr) ); #else - { - unsigned long shift, temp1; __asm__ __volatile__ ( -" zdep %2,29,2,%3\n" /* r19=(ofs&3)*8 */ +" zdep %2,29,2,%3\n" /* shift=(ofs&3)*8 */ " mtsp %5, %%sr1\n" " dep %%r0,31,2,%2\n" "1: ldw 0(%%sr1,%2),%0\n" @@ -207,12 +205,11 @@ static int emulate_ldd(struct pt_regs *regs, int toreg, int flop) " vshd %0,%R0,%0\n" " vshd %R0,%4,%R0\n" "4: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 4b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 4b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 4b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 4b, "%1") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 4b, "%1") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 4b, "%1") : "+r" (val), "+r" (ret), "+r" (saddr), "=&r" (shift), "=&r" (temp1) : "r" (regs->isr) ); - } #endif DPRINTF("val = 0x%llx\n", val); @@ -242,8 +239,8 @@ static int emulate_sth(struct pt_regs *regs, int frreg) "1: stb %1, 0(%%sr1, %3)\n" "2: stb %2, 1(%%sr1, %3)\n" "3: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%0") : "+r" (ret), "=&r" (temp1) : "r" (val), "r" (regs->ior), "r" (regs->isr) ); @@ -283,8 +280,8 @@ static int emulate_stw(struct pt_regs *regs, int frreg, int flop) " stw %%r20,0(%%sr1,%2)\n" " stw %%r21,4(%%sr1,%2)\n" "3: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%0") : "+r" (ret) : "r" (val), "r" (regs->ior), "r" (regs->isr) : "r19", "r20", "r21", "r22", "r1" ); @@ -327,10 +324,10 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop) "3: std %%r20,0(%%sr1,%2)\n" "4: std %%r21,8(%%sr1,%2)\n" "5: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 5b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 5b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 5b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 5b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 5b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 5b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 5b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 5b, "%0") : "+r" (ret) : "r" (val), "r" (regs->ior), "r" (regs->isr) : "r19", "r20", "r21", "r22", "r1" ); @@ -356,11 +353,11 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop) "4: stw %%r1,4(%%sr1,%3)\n" "5: stw %2,8(%%sr1,%3)\n" "6: \n" - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 6b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 6b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 6b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 6b) - ASM_EXCEPTIONTABLE_ENTRY_EFAULT(5b, 6b) + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 6b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 6b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 6b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 6b, "%0") + ASM_EXCEPTIONTABLE_ENTRY_EFAULT(5b, 6b, "%0") : "+r" (ret) : "r" (valh), "r" (vall), "r" (regs->ior), "r" (regs->isr) : "r19", "r20", "r21", "r1" ); diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index b00aa98b582c2daabcb8e8e3e541f2e5657261bc..fbd9ada5e527e19a17c83a642ad9c5ced0a8d4c7 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -150,11 +150,16 @@ int fixup_exception(struct pt_regs *regs) * Fix up get_user() and put_user(). * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() sets the least-significant * bit in the relative address of the fixup routine to indicate - * that gr[ASM_EXCEPTIONTABLE_REG] should be loaded with - * -EFAULT to report a userspace access error. + * that the register encoded in the "or %r0,%r0,register" + * opcode should be loaded with -EFAULT to report a userspace + * access error. */ if (fix->fixup & 1) { - regs->gr[ASM_EXCEPTIONTABLE_REG] = -EFAULT; + int fault_error_reg = fix->err_opcode & 0x1f; + if (!WARN_ON(!fault_error_reg)) + regs->gr[fault_error_reg] = -EFAULT; + pr_debug("Unalignment fixup of register %d at %pS\n", + fault_error_reg, (void*)regs->iaoq[0]); /* zero target register for get_user() */ if (parisc_acctyp(0, regs->iir) == VM_READ) { diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h index 61a4736355c244448104080e144631a3cb8839b2..20d5052e22925c6692c2562222edbbf85cc4af3e 100644 --- a/arch/powerpc/include/asm/bug.h +++ b/arch/powerpc/include/asm/bug.h @@ -74,7 +74,7 @@ ##__VA_ARGS__) #define WARN_ENTRY(insn, flags, label, ...) \ - asm_volatile_goto( \ + asm goto( \ "1: " insn "\n" \ EX_TABLE(1b, %l[label]) \ _EMIT_BUG_ENTRY \ diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h index 93ce3ec253877d38da5e3f9c3ac76205354d3496..2f2a86ed2280aac66df0535d7938cf4a673446f7 100644 --- a/arch/powerpc/include/asm/jump_label.h +++ b/arch/powerpc/include/asm/jump_label.h @@ -17,7 +17,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "nop # arch_static_branch\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".long 1b - ., %l[l_yes] - .\n\t" @@ -32,7 +32,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "b %l[l_yes] # arch_static_branch_jump\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".long 1b - ., %l[l_yes] - .\n\t" diff --git a/arch/powerpc/include/asm/reg_fsl_emb.h b/arch/powerpc/include/asm/reg_fsl_emb.h index a21f529c43d96b548690aeff283820ce07a6e4a1..8359c06d92d9f8a486c027aad3b76dea1234a226 100644 --- a/arch/powerpc/include/asm/reg_fsl_emb.h +++ b/arch/powerpc/include/asm/reg_fsl_emb.h @@ -12,9 +12,16 @@ #ifndef __ASSEMBLY__ /* Performance Monitor Registers */ #define mfpmr(rn) ({unsigned int rval; \ - asm volatile("mfpmr %0," __stringify(rn) \ + asm volatile(".machine push; " \ + ".machine e300; " \ + "mfpmr %0," __stringify(rn) ";" \ + ".machine pop; " \ : "=r" (rval)); rval;}) -#define mtpmr(rn, v) asm volatile("mtpmr " __stringify(rn) ",%0" : : "r" (v)) +#define mtpmr(rn, v) asm volatile(".machine push; " \ + ".machine e300; " \ + "mtpmr " __stringify(rn) ",%0; " \ + ".machine pop; " \ + : : "r" (v)) #endif /* __ASSEMBLY__ */ /* Freescale Book E Performance Monitor APU Registers */ diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index af58f1ed3952e09b067dc2ff3b87c021db95f434..c4b798aa6ce80f0b6fc54d1a507d92fafc47479a 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -14,7 +14,7 @@ #ifdef __KERNEL__ -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN) && CONFIG_THREAD_SHIFT < 15 #define MIN_THREAD_SHIFT (CONFIG_THREAD_SHIFT + 1) #else #define MIN_THREAD_SHIFT CONFIG_THREAD_SHIFT diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 3ddc65c63a49e3e2b0a4f0f426453a32a49d8aac..45d4c9cf3f3a27437b77438d4406a24b54069b2c 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -72,7 +72,7 @@ __pu_failed: \ * are no aliasing issues. */ #define __put_user_asm_goto(x, addr, label, op) \ - asm_volatile_goto( \ + asm goto( \ "1: " op "%U1%X1 %0,%1 # put_user\n" \ EX_TABLE(1b, %l2) \ : \ @@ -85,7 +85,7 @@ __pu_failed: \ __put_user_asm_goto(x, ptr, label, "std") #else /* __powerpc64__ */ #define __put_user_asm2_goto(x, addr, label) \ - asm_volatile_goto( \ + asm goto( \ "1: stw%X1 %0, %1\n" \ "2: stw%X1 %L0, %L1\n" \ EX_TABLE(1b, %l2) \ @@ -132,7 +132,7 @@ do { \ #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define __get_user_asm_goto(x, addr, label, op) \ - asm_volatile_goto( \ + asm_goto_output( \ "1: "op"%U1%X1 %0, %1 # get_user\n" \ EX_TABLE(1b, %l2) \ : "=r" (x) \ @@ -145,7 +145,7 @@ do { \ __get_user_asm_goto(x, addr, label, "ld") #else /* __powerpc64__ */ #define __get_user_asm2_goto(x, addr, label) \ - asm_volatile_goto( \ + asm_goto_output( \ "1: lwz%X1 %0, %1\n" \ "2: lwz%X1 %L0, %L1\n" \ EX_TABLE(1b, %l2) \ diff --git a/arch/powerpc/include/asm/vmalloc.h b/arch/powerpc/include/asm/vmalloc.h index 4c69ece52a31e5ef874e4694fc94b2b0f6ec42d5..59ed89890c902bca0011611733f2cc219795bb20 100644 --- a/arch/powerpc/include/asm/vmalloc.h +++ b/arch/powerpc/include/asm/vmalloc.h @@ -7,14 +7,14 @@ #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP #define arch_vmap_pud_supported arch_vmap_pud_supported -static inline bool arch_vmap_pud_supported(pgprot_t prot) +static __always_inline bool arch_vmap_pud_supported(pgprot_t prot) { /* HPT does not cope with large pages in the vmalloc area */ return radix_enabled(); } #define arch_vmap_pmd_supported arch_vmap_pmd_supported -static inline bool arch_vmap_pmd_supported(pgprot_t prot) +static __always_inline bool arch_vmap_pmd_supported(pgprot_t prot) { return radix_enabled(); } diff --git a/arch/powerpc/kernel/cpu_specs_e500mc.h b/arch/powerpc/kernel/cpu_specs_e500mc.h index ceb06b109f831355a833a0e929ef68d86ccbc321..2ae8e9a7b461c8c35755bd4ac0ab48e29a4daf79 100644 --- a/arch/powerpc/kernel/cpu_specs_e500mc.h +++ b/arch/powerpc/kernel/cpu_specs_e500mc.h @@ -8,7 +8,8 @@ #ifdef CONFIG_PPC64 #define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ - PPC_FEATURE_HAS_FPU | PPC_FEATURE_64) + PPC_FEATURE_HAS_FPU | PPC_FEATURE_64 | \ + PPC_FEATURE_BOOKE) #else #define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ PPC_FEATURE_BOOKE) diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index a019ed6fc83937af635b1aa8c7206979d7c4c10e..26c151e2a7942587416b81cd2ee54fde6df9b191 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -52,7 +52,8 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name) mr r10,r1 ld r1,PACAKSAVE(r13) std r10,0(r1) - std r11,_NIP(r1) + std r11,_LINK(r1) + std r11,_NIP(r1) /* Saved LR is also the next instruction */ std r12,_MSR(r1) std r0,GPR0(r1) std r10,GPR1(r1) @@ -70,7 +71,6 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name) std r9,GPR13(r1) SAVE_NVGPRS(r1) std r11,_XER(r1) - std r11,_LINK(r1) std r11,_CTR(r1) li r11,\trapnr diff --git a/arch/powerpc/kernel/irq_64.c b/arch/powerpc/kernel/irq_64.c index 9dc0ad3c533a8f0f737f58fed9e6f41eae207cc1..5a6e44e4d36f55f1a79e969bee7a6b83a7c02f65 100644 --- a/arch/powerpc/kernel/irq_64.c +++ b/arch/powerpc/kernel/irq_64.c @@ -230,7 +230,7 @@ again: * This allows interrupts to be unmasked without hard disabling, and * also without new hard interrupts coming in ahead of pending ones. */ - asm_volatile_goto( + asm goto( "1: \n" " lbz 9,%0(13) \n" " cmpwi 9,0 \n" diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 8537c354c560b617869c6058ae53cf53f2288fed..9531ab90feb8a001108c2e1c45f7d94e8148446a 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -369,6 +369,18 @@ static int __init early_init_dt_scan_cpus(unsigned long node, if (IS_ENABLED(CONFIG_PPC64)) boot_cpu_hwid = be32_to_cpu(intserv[found_thread]); + if (nr_cpu_ids % nthreads != 0) { + set_nr_cpu_ids(ALIGN(nr_cpu_ids, nthreads)); + pr_warn("nr_cpu_ids was not a multiple of threads_per_core, adjusted to %d\n", + nr_cpu_ids); + } + + if (boot_cpuid >= nr_cpu_ids) { + set_nr_cpu_ids(min(CONFIG_NR_CPUS, ALIGN(boot_cpuid + 1, nthreads))); + pr_warn("Boot CPU %d >= nr_cpu_ids, adjusted nr_cpu_ids to %d\n", + boot_cpuid, nr_cpu_ids); + } + /* * PAPR defines "logical" PVR values for cpus that * meet various levels of the architecture: diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 9b394bab17eba5bd1a4066783a0ab2dc0cb1956b..374b82cf13d9d372ef92e471c5e8e06e36260c6a 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -72,7 +72,7 @@ obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o obj-$(CONFIG_FTR_FIXUP_SELFTEST) += feature-fixups-test.o obj-$(CONFIG_ALTIVEC) += xor_vmx.o xor_vmx_glue.o -CFLAGS_xor_vmx.o += -maltivec $(call cc-option,-mabi=altivec) +CFLAGS_xor_vmx.o += -mhard-float -maltivec $(call cc-option,-mabi=altivec) # Enable CFLAGS_xor_vmx.o += -isystem $(shell $(CC) -print-file-name=include) diff --git a/arch/powerpc/mm/kasan/init_32.c b/arch/powerpc/mm/kasan/init_32.c index a70828a6d9357d5fb399375f9624a7fb06d4a129..aa9aa11927b2f842718d98e7818fcd499efd0e54 100644 --- a/arch/powerpc/mm/kasan/init_32.c +++ b/arch/powerpc/mm/kasan/init_32.c @@ -64,6 +64,7 @@ int __init __weak kasan_init_region(void *start, size_t size) if (ret) return ret; + k_start = k_start & PAGE_MASK; block = memblock_alloc(k_end - k_start, PAGE_SIZE); if (!block) return -ENOMEM; diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index 7ff8ff3509f5f6f2f414b6475a86b051a30c335e..943248a0e9a9de0413be6d9f4ae1c9f1aa8336a9 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -164,6 +164,20 @@ static unsigned long single_gpci_request(u32 req, u32 starting_index, ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO, virt_to_phys(arg), HGPCI_REQ_BUFFER_SIZE); + + /* + * ret value as 'H_PARAMETER' with detail_rc as 'GEN_BUF_TOO_SMALL', + * specifies that the current buffer size cannot accommodate + * all the information and a partial buffer returned. + * Since in this function we are only accessing data for a given starting index, + * we don't need to accommodate whole data and can get required count by + * accessing first entry data. + * Hence hcall fails only incase the ret value is other than H_SUCCESS or + * H_PARAMETER with detail_rc value as GEN_BUF_TOO_SMALL(0x1B). + */ + if (ret == H_PARAMETER && be32_to_cpu(arg->params.detail_rc) == 0x1B) + ret = 0; + if (ret) { pr_devel("hcall failed: 0x%lx\n", ret); goto out; @@ -228,6 +242,7 @@ static int h_gpci_event_init(struct perf_event *event) { u64 count; u8 length; + unsigned long ret; /* Not our event */ if (event->attr.type != event->pmu->type) @@ -258,13 +273,23 @@ static int h_gpci_event_init(struct perf_event *event) } /* check if the request works... */ - if (single_gpci_request(event_get_request(event), + ret = single_gpci_request(event_get_request(event), event_get_starting_index(event), event_get_secondary_index(event), event_get_counter_info_version(event), event_get_offset(event), length, - &count)) { + &count); + + /* + * ret value as H_AUTHORITY implies that partition is not permitted to retrieve + * performance information, and required to set + * "Enable Performance Information Collection" option. + */ + if (ret == H_AUTHORITY) + return -EPERM; + + if (ret) { pr_devel("gpci hcall failed\n"); return -EINVAL; } diff --git a/arch/powerpc/platforms/embedded6xx/linkstation.c b/arch/powerpc/platforms/embedded6xx/linkstation.c index 1830e1ac1f8f01e4519c797d7033310be8e050fb..107a8b60ad0c9963797c49a0d3f3a70d3f8e279d 100644 --- a/arch/powerpc/platforms/embedded6xx/linkstation.c +++ b/arch/powerpc/platforms/embedded6xx/linkstation.c @@ -99,9 +99,6 @@ static void __init linkstation_init_IRQ(void) mpic_init(mpic); } -extern void avr_uart_configure(void); -extern void avr_uart_send(const char); - static void __noreturn linkstation_restart(char *cmd) { local_irq_disable(); diff --git a/arch/powerpc/platforms/embedded6xx/mpc10x.h b/arch/powerpc/platforms/embedded6xx/mpc10x.h index 5ad12023e56280171238e13cf5136f67df1cc0bc..ebc258fa4858d023bd528d6015e64a2df465166c 100644 --- a/arch/powerpc/platforms/embedded6xx/mpc10x.h +++ b/arch/powerpc/platforms/embedded6xx/mpc10x.h @@ -156,4 +156,7 @@ int mpc10x_disable_store_gathering(struct pci_controller *hose); /* For MPC107 boards that use the built-in openpic */ void mpc10x_set_openpic(void); +void avr_uart_configure(void); +void avr_uart_send(const char c); + #endif /* __PPC_KERNEL_MPC10X_H */ diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 97b026130c71b7802010d7168766c4d4cd027b89..5e00a3cde93b90ef0a216cd97db206aad4253a8d 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -569,29 +569,6 @@ static void iommu_table_setparms(struct pci_controller *phb, struct iommu_table_ops iommu_table_lpar_multi_ops; -/* - * iommu_table_setparms_lpar - * - * Function: On pSeries LPAR systems, return TCE table info, given a pci bus. - */ -static void iommu_table_setparms_lpar(struct pci_controller *phb, - struct device_node *dn, - struct iommu_table *tbl, - struct iommu_table_group *table_group, - const __be32 *dma_window) -{ - unsigned long offset, size, liobn; - - of_parse_dma_window(dn, dma_window, &liobn, &offset, &size); - - iommu_table_setparms_common(tbl, phb->bus->number, liobn, offset, size, IOMMU_PAGE_SHIFT_4K, NULL, - &iommu_table_lpar_multi_ops); - - - table_group->tce32_start = offset; - table_group->tce32_size = size; -} - struct iommu_table_ops iommu_table_pseries_ops = { .set = tce_build_pSeries, .clear = tce_free_pSeries, @@ -719,26 +696,71 @@ struct iommu_table_ops iommu_table_lpar_multi_ops = { * dynamic 64bit DMA window, walking up the device tree. */ static struct device_node *pci_dma_find(struct device_node *dn, - const __be32 **dma_window) + struct dynamic_dma_window_prop *prop) { - const __be32 *dw = NULL; + const __be32 *default_prop = NULL; + const __be32 *ddw_prop = NULL; + struct device_node *rdn = NULL; + bool default_win = false, ddw_win = false; for ( ; dn && PCI_DN(dn); dn = dn->parent) { - dw = of_get_property(dn, "ibm,dma-window", NULL); - if (dw) { - if (dma_window) - *dma_window = dw; - return dn; + default_prop = of_get_property(dn, "ibm,dma-window", NULL); + if (default_prop) { + rdn = dn; + default_win = true; } - dw = of_get_property(dn, DIRECT64_PROPNAME, NULL); - if (dw) - return dn; - dw = of_get_property(dn, DMA64_PROPNAME, NULL); - if (dw) - return dn; + ddw_prop = of_get_property(dn, DIRECT64_PROPNAME, NULL); + if (ddw_prop) { + rdn = dn; + ddw_win = true; + break; + } + ddw_prop = of_get_property(dn, DMA64_PROPNAME, NULL); + if (ddw_prop) { + rdn = dn; + ddw_win = true; + break; + } + + /* At least found default window, which is the case for normal boot */ + if (default_win) + break; } - return NULL; + /* For PCI devices there will always be a DMA window, either on the device + * or parent bus + */ + WARN_ON(!(default_win | ddw_win)); + + /* caller doesn't want to get DMA window property */ + if (!prop) + return rdn; + + /* parse DMA window property. During normal system boot, only default + * DMA window is passed in OF. But, for kdump, a dedicated adapter might + * have both default and DDW in FDT. In this scenario, DDW takes precedence + * over default window. + */ + if (ddw_win) { + struct dynamic_dma_window_prop *p; + + p = (struct dynamic_dma_window_prop *)ddw_prop; + prop->liobn = p->liobn; + prop->dma_base = p->dma_base; + prop->tce_shift = p->tce_shift; + prop->window_shift = p->window_shift; + } else if (default_win) { + unsigned long offset, size, liobn; + + of_parse_dma_window(rdn, default_prop, &liobn, &offset, &size); + + prop->liobn = cpu_to_be32((u32)liobn); + prop->dma_base = cpu_to_be64(offset); + prop->tce_shift = cpu_to_be32(IOMMU_PAGE_SHIFT_4K); + prop->window_shift = cpu_to_be32(order_base_2(size)); + } + + return rdn; } static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) @@ -746,17 +768,28 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) struct iommu_table *tbl; struct device_node *dn, *pdn; struct pci_dn *ppci; - const __be32 *dma_window = NULL; + struct dynamic_dma_window_prop prop; dn = pci_bus_to_OF_node(bus); pr_debug("pci_dma_bus_setup_pSeriesLP: setting up bus %pOF\n", dn); - pdn = pci_dma_find(dn, &dma_window); + pdn = pci_dma_find(dn, &prop); - if (dma_window == NULL) + /* In PPC architecture, there will always be DMA window on bus or one of the + * parent bus. During reboot, there will be ibm,dma-window property to + * define DMA window. For kdump, there will at least be default window or DDW + * or both. + * There is an exception to the above. In case the PE goes into frozen + * state, firmware may not provide ibm,dma-window property at the time + * of LPAR boot up. + */ + + if (!pdn) { pr_debug(" no ibm,dma-window property !\n"); + return; + } ppci = PCI_DN(pdn); @@ -766,13 +799,24 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) if (!ppci->table_group) { ppci->table_group = iommu_pseries_alloc_group(ppci->phb->node); tbl = ppci->table_group->tables[0]; - if (dma_window) { - iommu_table_setparms_lpar(ppci->phb, pdn, tbl, - ppci->table_group, dma_window); - if (!iommu_init_table(tbl, ppci->phb->node, 0, 0)) - panic("Failed to initialize iommu table"); - } + iommu_table_setparms_common(tbl, ppci->phb->bus->number, + be32_to_cpu(prop.liobn), + be64_to_cpu(prop.dma_base), + 1ULL << be32_to_cpu(prop.window_shift), + be32_to_cpu(prop.tce_shift), NULL, + &iommu_table_lpar_multi_ops); + + /* Only for normal boot with default window. Doesn't matter even + * if we set these with DDW which is 64bit during kdump, since + * these will not be used during kdump. + */ + ppci->table_group->tce32_start = be64_to_cpu(prop.dma_base); + ppci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift); + + if (!iommu_init_table(tbl, ppci->phb->node, 0, 0)) + panic("Failed to initialize iommu table"); + iommu_register_group(ppci->table_group, pci_domain_nr(bus), 0); pr_debug(" created table: %p\n", ppci->table_group); @@ -960,6 +1004,12 @@ static void find_existing_ddw_windows_named(const char *name) continue; } + /* If at the time of system initialization, there are DDWs in OF, + * it means this is during kexec. DDW could be direct or dynamic. + * We will just mark DDWs as "dynamic" since this is kdump path, + * no need to worry about perforance. ddw_list_new_entry() will + * set window->direct = false. + */ window = ddw_list_new_entry(pdn, dma64); if (!window) { of_node_put(pdn); @@ -1525,8 +1575,8 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) { struct device_node *pdn, *dn; struct iommu_table *tbl; - const __be32 *dma_window = NULL; struct pci_dn *pci; + struct dynamic_dma_window_prop prop; pr_debug("pci_dma_dev_setup_pSeriesLP: %s\n", pci_name(dev)); @@ -1539,7 +1589,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) dn = pci_device_to_OF_node(dev); pr_debug(" node is %pOF\n", dn); - pdn = pci_dma_find(dn, &dma_window); + pdn = pci_dma_find(dn, &prop); if (!pdn || !PCI_DN(pdn)) { printk(KERN_WARNING "pci_dma_dev_setup_pSeriesLP: " "no DMA window found for pci dev=%s dn=%pOF\n", @@ -1552,8 +1602,20 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) if (!pci->table_group) { pci->table_group = iommu_pseries_alloc_group(pci->phb->node); tbl = pci->table_group->tables[0]; - iommu_table_setparms_lpar(pci->phb, pdn, tbl, - pci->table_group, dma_window); + + iommu_table_setparms_common(tbl, pci->phb->bus->number, + be32_to_cpu(prop.liobn), + be64_to_cpu(prop.dma_base), + 1ULL << be32_to_cpu(prop.window_shift), + be32_to_cpu(prop.tce_shift), NULL, + &iommu_table_lpar_multi_ops); + + /* Only for normal boot with default window. Doesn't matter even + * if we set these with DDW which is 64bit during kdump, since + * these will not be used during kdump. + */ + pci->table_group->tce32_start = be64_to_cpu(prop.dma_base); + pci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift); iommu_init_table(tbl, pci->phb->node, 0, 0); iommu_register_group(pci->table_group, diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 541199c6a587d8ca50e247c3cd242212f2ca9e4d..5186d65d772e2e1e1f219c88d90aacef72f767e1 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -660,8 +660,12 @@ u64 pseries_paravirt_steal_clock(int cpu) { struct lppaca *lppaca = &lppaca_of(cpu); - return be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) + - be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb)); + /* + * VPA steal time counters are reported at TB frequency. Hence do a + * conversion to ns before returning + */ + return tb_to_ns(be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) + + be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb))); } #endif diff --git a/arch/powerpc/platforms/pseries/papr_platform_attributes.c b/arch/powerpc/platforms/pseries/papr_platform_attributes.c index 526c621b098bece600fdfe72de1c4f53697d33f5..eea2041b270b546477a34e3836662969d6dd25eb 100644 --- a/arch/powerpc/platforms/pseries/papr_platform_attributes.c +++ b/arch/powerpc/platforms/pseries/papr_platform_attributes.c @@ -101,10 +101,12 @@ retry: esi_buf_size = ESI_HDR_SIZE + (CURR_MAX_ESI_ATTRS * max_esi_attrs); temp_buf = krealloc(buf, esi_buf_size, GFP_KERNEL); - if (temp_buf) + if (temp_buf) { buf = temp_buf; - else - return -ENOMEM; + } else { + ret = -ENOMEM; + goto out_buf; + } goto retry; } diff --git a/arch/powerpc/platforms/pseries/plpks.c b/arch/powerpc/platforms/pseries/plpks.c index 63a1e1fe01851d884a0517752b0e1e46c060ddbf..25f95440a773b51ba257b19cbf5433eed7f45344 100644 --- a/arch/powerpc/platforms/pseries/plpks.c +++ b/arch/powerpc/platforms/pseries/plpks.c @@ -21,19 +21,6 @@ #include "plpks.h" -#define PKS_FW_OWNER 0x1 -#define PKS_BOOTLOADER_OWNER 0x2 -#define PKS_OS_OWNER 0x3 - -#define LABEL_VERSION 0 -#define MAX_LABEL_ATTR_SIZE 16 -#define MAX_NAME_SIZE 239 -#define MAX_DATA_SIZE 4000 - -#define PKS_FLUSH_MAX_TIMEOUT 5000 //msec -#define PKS_FLUSH_SLEEP 10 //msec -#define PKS_FLUSH_SLEEP_RANGE 400 - static u8 *ospassword; static u16 ospasswordlength; @@ -60,7 +47,7 @@ struct label_attr { struct label { struct label_attr attr; - u8 name[MAX_NAME_SIZE]; + u8 name[PLPKS_MAX_NAME_SIZE]; size_t size; }; @@ -123,7 +110,7 @@ static int pseries_status_to_err(int rc) static int plpks_gen_password(void) { unsigned long retbuf[PLPAR_HCALL_BUFSIZE] = { 0 }; - u8 *password, consumer = PKS_OS_OWNER; + u8 *password, consumer = PLPKS_OS_OWNER; int rc; password = kzalloc(maxpwsize, GFP_KERNEL); @@ -159,22 +146,18 @@ static struct plpks_auth *construct_auth(u8 consumer) { struct plpks_auth *auth; - if (consumer > PKS_OS_OWNER) + if (consumer > PLPKS_OS_OWNER) return ERR_PTR(-EINVAL); - auth = kmalloc(struct_size(auth, password, maxpwsize), GFP_KERNEL); + auth = kzalloc(struct_size(auth, password, maxpwsize), GFP_KERNEL); if (!auth) return ERR_PTR(-ENOMEM); auth->version = 1; auth->consumer = consumer; - auth->rsvd0 = 0; - auth->rsvd1 = 0; - if (consumer == PKS_FW_OWNER || consumer == PKS_BOOTLOADER_OWNER) { - auth->passwordlength = 0; + if (consumer == PLPKS_FW_OWNER || consumer == PLPKS_BOOTLOADER_OWNER) return auth; - } memcpy(auth->password, ospassword, ospasswordlength); @@ -193,7 +176,7 @@ static struct label *construct_label(char *component, u8 varos, u8 *name, struct label *label; size_t slen; - if (!name || namelen > MAX_NAME_SIZE) + if (!name || namelen > PLPKS_MAX_NAME_SIZE) return ERR_PTR(-EINVAL); slen = strlen(component); @@ -207,9 +190,9 @@ static struct label *construct_label(char *component, u8 varos, u8 *name, if (component) memcpy(&label->attr.prefix, component, slen); - label->attr.version = LABEL_VERSION; + label->attr.version = PLPKS_LABEL_VERSION; label->attr.os = varos; - label->attr.length = MAX_LABEL_ATTR_SIZE; + label->attr.length = PLPKS_MAX_LABEL_ATTR_SIZE; memcpy(&label->name, name, namelen); label->size = sizeof(struct label_attr) + namelen; @@ -271,10 +254,9 @@ static int plpks_confirm_object_flushed(struct label *label, if (!rc && status == 1) break; - usleep_range(PKS_FLUSH_SLEEP, - PKS_FLUSH_SLEEP + PKS_FLUSH_SLEEP_RANGE); - timeout = timeout + PKS_FLUSH_SLEEP; - } while (timeout < PKS_FLUSH_MAX_TIMEOUT); + fsleep(PLPKS_FLUSH_SLEEP); + timeout = timeout + PLPKS_FLUSH_SLEEP; + } while (timeout < PLPKS_MAX_TIMEOUT); rc = pseries_status_to_err(rc); @@ -289,13 +271,13 @@ int plpks_write_var(struct plpks_var var) int rc; if (!var.component || !var.data || var.datalen <= 0 || - var.namelen > MAX_NAME_SIZE || var.datalen > MAX_DATA_SIZE) + var.namelen > PLPKS_MAX_NAME_SIZE || var.datalen > PLPKS_MAX_DATA_SIZE) return -EINVAL; - if (var.policy & SIGNEDUPDATE) + if (var.policy & PLPKS_SIGNEDUPDATE) return -EINVAL; - auth = construct_auth(PKS_OS_OWNER); + auth = construct_auth(PLPKS_OS_OWNER); if (IS_ERR(auth)) return PTR_ERR(auth); @@ -331,10 +313,10 @@ int plpks_remove_var(char *component, u8 varos, struct plpks_var_name vname) struct label *label; int rc; - if (!component || vname.namelen > MAX_NAME_SIZE) + if (!component || vname.namelen > PLPKS_MAX_NAME_SIZE) return -EINVAL; - auth = construct_auth(PKS_OS_OWNER); + auth = construct_auth(PLPKS_OS_OWNER); if (IS_ERR(auth)) return PTR_ERR(auth); @@ -370,14 +352,14 @@ static int plpks_read_var(u8 consumer, struct plpks_var *var) u8 *output; int rc; - if (var->namelen > MAX_NAME_SIZE) + if (var->namelen > PLPKS_MAX_NAME_SIZE) return -EINVAL; auth = construct_auth(consumer); if (IS_ERR(auth)) return PTR_ERR(auth); - if (consumer == PKS_OS_OWNER) { + if (consumer == PLPKS_OS_OWNER) { label = construct_label(var->component, var->os, var->name, var->namelen); if (IS_ERR(label)) { @@ -392,7 +374,7 @@ static int plpks_read_var(u8 consumer, struct plpks_var *var) goto out_free_label; } - if (consumer == PKS_OS_OWNER) + if (consumer == PLPKS_OS_OWNER) rc = plpar_hcall(H_PKS_READ_OBJECT, retbuf, virt_to_phys(auth), virt_to_phys(label), label->size, virt_to_phys(output), maxobjsize); @@ -434,17 +416,17 @@ out_free_auth: int plpks_read_os_var(struct plpks_var *var) { - return plpks_read_var(PKS_OS_OWNER, var); + return plpks_read_var(PLPKS_OS_OWNER, var); } int plpks_read_fw_var(struct plpks_var *var) { - return plpks_read_var(PKS_FW_OWNER, var); + return plpks_read_var(PLPKS_FW_OWNER, var); } int plpks_read_bootloader_var(struct plpks_var *var) { - return plpks_read_var(PKS_BOOTLOADER_OWNER, var); + return plpks_read_var(PLPKS_BOOTLOADER_OWNER, var); } static __init int pseries_plpks_init(void) diff --git a/arch/powerpc/platforms/pseries/plpks.h b/arch/powerpc/platforms/pseries/plpks.h index 275ccd86bfb5e46ffff11c06e2adb4b992bc0657..07278a990c2df0c2eb80ec81f51e2bc991c88e4f 100644 --- a/arch/powerpc/platforms/pseries/plpks.h +++ b/arch/powerpc/platforms/pseries/plpks.h @@ -12,14 +12,39 @@ #include #include -#define OSSECBOOTAUDIT 0x40000000 -#define OSSECBOOTENFORCE 0x20000000 -#define WORLDREADABLE 0x08000000 -#define SIGNEDUPDATE 0x01000000 +// Object policy flags from supported_policies +#define PLPKS_OSSECBOOTAUDIT PPC_BIT32(1) // OS secure boot must be audit/enforce +#define PLPKS_OSSECBOOTENFORCE PPC_BIT32(2) // OS secure boot must be enforce +#define PLPKS_PWSET PPC_BIT32(3) // No access without password set +#define PLPKS_WORLDREADABLE PPC_BIT32(4) // Readable without authentication +#define PLPKS_IMMUTABLE PPC_BIT32(5) // Once written, object cannot be removed +#define PLPKS_TRANSIENT PPC_BIT32(6) // Object does not persist through reboot +#define PLPKS_SIGNEDUPDATE PPC_BIT32(7) // Object can only be modified by signed updates +#define PLPKS_HVPROVISIONED PPC_BIT32(28) // Hypervisor has provisioned this object -#define PLPKS_VAR_LINUX 0x02 +// Signature algorithm flags from signed_update_algorithms +#define PLPKS_ALG_RSA2048 PPC_BIT(0) +#define PLPKS_ALG_RSA4096 PPC_BIT(1) + +// Object label OS metadata flags +#define PLPKS_VAR_LINUX 0x02 #define PLPKS_VAR_COMMON 0x04 +// Flags for which consumer owns an object is owned by +#define PLPKS_FW_OWNER 0x1 +#define PLPKS_BOOTLOADER_OWNER 0x2 +#define PLPKS_OS_OWNER 0x3 + +// Flags for label metadata fields +#define PLPKS_LABEL_VERSION 0 +#define PLPKS_MAX_LABEL_ATTR_SIZE 16 +#define PLPKS_MAX_NAME_SIZE 239 +#define PLPKS_MAX_DATA_SIZE 4000 + +// Timeouts for PLPKS operations +#define PLPKS_MAX_TIMEOUT (5 * USEC_PER_SEC) +#define PLPKS_FLUSH_SLEEP 10000 // usec + struct plpks_var { char *component; u8 *name; diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts index 07387f9c135ca7e8ddf7d45de10ccdb933a2e4d4..72b87b08ab444ef1dc1ed200a6e8b3cbb9bfc73f 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts @@ -123,6 +123,7 @@ interrupt-parent = <&gpio>; interrupts = <1 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + #interrupt-cells = <2>; onkey { compatible = "dlg,da9063-onkey"; diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index d47d87c2d7e3d0f1393688527f3c72d589fdb907..dcf1bc9de5841e09800937299c85ca81528fd043 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -25,6 +25,11 @@ #define ARCH_SUPPORTS_FTRACE_OPS 1 #ifndef __ASSEMBLY__ + +extern void *return_address(unsigned int level); + +#define ftrace_return_address(n) return_address(n) + void MCOUNT_NAME(void); static inline unsigned long ftrace_call_adjust(unsigned long addr) { diff --git a/arch/riscv/include/asm/jump_label.h b/arch/riscv/include/asm/jump_label.h index 14a5ea8d8ef0f4a2f4477fb65778e4f8ea449e2a..4a35d787c0191475b3a5d8dc7452e448541dc8e9 100644 --- a/arch/riscv/include/asm/jump_label.h +++ b/arch/riscv/include/asm/jump_label.h @@ -17,7 +17,7 @@ static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( " .align 2 \n\t" " .option push \n\t" " .option norelax \n\t" @@ -39,7 +39,7 @@ label: static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { - asm_volatile_goto( + asm goto( " .align 2 \n\t" " .option push \n\t" " .option norelax \n\t" diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 59bb53da473dd6f0c2df8b129f6be5f91467b8d7..2d9416a6a070eaee5f3cd083a194c3ffb58845c9 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -79,7 +79,7 @@ * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled. */ -#define vmemmap ((struct page *)VMEMMAP_START) +#define vmemmap ((struct page *)VMEMMAP_START - (phys_ram_base >> PAGE_SHIFT)) #define PCI_IO_SIZE SZ_16M #define PCI_IO_END VMEMMAP_START @@ -799,8 +799,8 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, #define PAGE_SHARED __pgprot(0) #define PAGE_KERNEL __pgprot(0) #define swapper_pg_dir NULL -#define TASK_SIZE 0xffffffffUL -#define VMALLOC_START 0 +#define TASK_SIZE _AC(-1, UL) +#define VMALLOC_START _AC(0, UL) #define VMALLOC_END TASK_SIZE #endif /* !CONFIG_MMU */ diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index ec0cab9fbddd0da98cb415af2732a4ede083886b..72ec1d9bd3f312ec05c6dc5f2342f06e24c58468 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -319,7 +319,7 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n) #define __get_kernel_nofault(dst, src, type, err_label) \ do { \ - long __kr_err; \ + long __kr_err = 0; \ \ __get_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err); \ if (unlikely(__kr_err)) \ @@ -328,7 +328,7 @@ do { \ #define __put_kernel_nofault(dst, src, type, err_label) \ do { \ - long __kr_err; \ + long __kr_err = 0; \ \ __put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err); \ if (unlikely(__kr_err)) \ diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index ab333cb792fd9cd24001e373a6e01dc5fbf28ed1..4c0805d264ca89cb2c3cec7eaea7a20b6bd252b3 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -7,6 +7,7 @@ ifdef CONFIG_FTRACE CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE) endif CFLAGS_syscall_table.o += $(call cc-option,-Wno-override-init,) CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,) @@ -41,6 +42,7 @@ obj-y += irq.o obj-y += process.o obj-y += ptrace.o obj-y += reset.o +obj-y += return_address.o obj-y += setup.o obj-y += signal.o obj-y += syscall_table.o diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 8955f2432c2d844c7e37b6ee69eea95ceffd7076..6906cc0e578751c82f55b6dd94fad151778b9308 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -25,8 +25,6 @@ #include #include -register unsigned long gp_in_global __asm__("gp"); - #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK) #include unsigned long __stack_chk_guard __read_mostly; @@ -170,7 +168,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) if (unlikely(args->fn)) { /* Kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); - childregs->gp = gp_in_global; /* Supervisor/Machine, irqs on: */ childregs->status = SR_PP | SR_PIE; diff --git a/arch/riscv/kernel/return_address.c b/arch/riscv/kernel/return_address.c new file mode 100644 index 0000000000000000000000000000000000000000..c8115ec8fb304bb5b44fdbfc38c5d55605f3c5c2 --- /dev/null +++ b/arch/riscv/kernel/return_address.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This code come from arch/arm64/kernel/return_address.c + * + * Copyright (C) 2023 SiFive. + */ + +#include +#include +#include + +struct return_address_data { + unsigned int level; + void *addr; +}; + +static bool save_return_addr(void *d, unsigned long pc) +{ + struct return_address_data *data = d; + + if (!data->level) { + data->addr = (void *)pc; + return false; + } + + --data->level; + + return true; +} +NOKPROBE_SYMBOL(save_return_addr); + +noinline void *return_address(unsigned int level) +{ + struct return_address_data data; + + data.level = level + 3; + data.addr = NULL; + + arch_stack_walk(save_return_addr, &data, current, NULL); + + if (!data.level) + return data.addr; + else + return NULL; + +} +EXPORT_SYMBOL_GPL(return_address); +NOKPROBE_SYMBOL(return_address); diff --git a/arch/s390/include/asm/dwarf.h b/arch/s390/include/asm/dwarf.h index 4f21ae561e4ddc7af7bc7a21f848f0fe4315ab59..390906b8e386e609f760d891484133b1c0fbea79 100644 --- a/arch/s390/include/asm/dwarf.h +++ b/arch/s390/include/asm/dwarf.h @@ -9,6 +9,7 @@ #define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset #define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset #define CFI_RESTORE .cfi_restore +#define CFI_REL_OFFSET .cfi_rel_offset #ifdef CONFIG_AS_CFI_VAL_OFFSET #define CFI_VAL_OFFSET .cfi_val_offset diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h index 895f774bbcc55353cc7a3d302b009796a799446f..bf78cf381dfcdac92a170b754328acd16846eb2e 100644 --- a/arch/s390/include/asm/jump_label.h +++ b/arch/s390/include/asm/jump_label.h @@ -25,7 +25,7 @@ */ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("0: brcl 0,%l[label]\n" + asm goto("0: brcl 0,%l[label]\n" ".pushsection __jump_table,\"aw\"\n" ".balign 8\n" ".long 0b-.,%l[label]-.\n" @@ -39,7 +39,7 @@ label: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("0: brcl 15,%l[label]\n" + asm goto("0: brcl 15,%l[label]\n" ".pushsection __jump_table,\"aw\"\n" ".balign 8\n" ".long 0b-.,%l[label]-.\n" diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index b1e98a9ed152b91365f014c7a54b3b5cfbeff459..09abf000359f8d4f6b9dbae3a343d3755cd217ba 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -777,6 +777,13 @@ struct kvm_vm_stat { u64 inject_service_signal; u64 inject_virtio; u64 aen_forward; + u64 gmap_shadow_create; + u64 gmap_shadow_reuse; + u64 gmap_shadow_r1_entry; + u64 gmap_shadow_r2_entry; + u64 gmap_shadow_r3_entry; + u64 gmap_shadow_sg_entry; + u64 gmap_shadow_pg_entry; }; struct kvm_arch_memory_slot { diff --git a/arch/s390/include/uapi/asm/dasd.h b/arch/s390/include/uapi/asm/dasd.h index 93d1ccd3304c706f591d98932090eb994f200d4c..9c49c3d67cd56d79589126d5f5f1d15d514a999b 100644 --- a/arch/s390/include/uapi/asm/dasd.h +++ b/arch/s390/include/uapi/asm/dasd.h @@ -78,6 +78,7 @@ typedef struct dasd_information2_t { * 0x040: give access to raw eckd data * 0x080: enable discard support * 0x100: enable autodisable for IFCC errors (default) + * 0x200: enable requeue of all requests on autoquiesce */ #define DASD_FEATURE_READONLY 0x001 #define DASD_FEATURE_USEDIAG 0x002 @@ -88,6 +89,7 @@ typedef struct dasd_information2_t { #define DASD_FEATURE_USERAW 0x040 #define DASD_FEATURE_DISCARD 0x080 #define DASD_FEATURE_PATH_AUTODISABLE 0x100 +#define DASD_FEATURE_REQUEUEQUIESCE 0x200 #define DASD_FEATURE_DEFAULT DASD_FEATURE_PATH_AUTODISABLE #define DASD_PARTN_BITS 2 diff --git a/arch/s390/kernel/cache.c b/arch/s390/kernel/cache.c index 7ee3651d00abe8f4bd78cb739377ac53212189e2..732024ca005ad391471a939a82b1e2d3cd1fc68d 100644 --- a/arch/s390/kernel/cache.c +++ b/arch/s390/kernel/cache.c @@ -166,5 +166,6 @@ int populate_cache_leaves(unsigned int cpu) ci_leaf_init(this_leaf++, pvt, ctype, level, cpu); } } + this_cpu_ci->cpu_map_populated = true; return 0; } diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index d2a1f2f4f5b883edac8d4ae4d5c4afa6107bf80d..c9799dec92793fd55ffbd97784af79eea0ff557d 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -699,6 +699,7 @@ ENDPROC(stack_overflow) .Lthis_cpu: .short 0 .Lstosm_tmp: .byte 0 .section .rodata, "a" + .balign 8 #define SYSCALL(esame,emu) .quad __s390x_ ## esame .globl sys_call_table sys_call_table: diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c index 6826e2a69a21678aae0bd23bebaf96de0306ef04..f61a652046cfb810bf663fe274ec8b9af469b33c 100644 --- a/arch/s390/kernel/perf_pai_crypto.c +++ b/arch/s390/kernel/perf_pai_crypto.c @@ -647,7 +647,7 @@ static int __init attr_event_init(void) for (i = 0; i < ARRAY_SIZE(paicrypt_ctrnames); i++) { ret = attr_event_init_one(attrs, i); if (ret) { - attr_event_free(attrs, i - 1); + attr_event_free(attrs, i); return ret; } } diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c index 74b53c531e0cd41b6fd1183b465680fb27f67f6c..b4d89654183a2133ca3f403cac74808e8ee218ed 100644 --- a/arch/s390/kernel/perf_pai_ext.c +++ b/arch/s390/kernel/perf_pai_ext.c @@ -612,7 +612,7 @@ static int __init attr_event_init(void) for (i = 0; i < ARRAY_SIZE(paiext_ctrnames); i++) { ret = attr_event_init_one(attrs, i); if (ret) { - attr_event_free(attrs, i - 1); + attr_event_free(attrs, i); return ret; } } diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile index 245bddfe9bc0e6bfd8c1997bdef8f55924128f33..cc513add48eb5a60cebaa88d7603e189877cda67 100644 --- a/arch/s390/kernel/vdso32/Makefile +++ b/arch/s390/kernel/vdso32/Makefile @@ -22,7 +22,7 @@ KBUILD_AFLAGS_32 += -m31 -s KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_32 += -m31 -fPIC -shared -fno-common -fno-builtin -LDFLAGS_vdso32.so.dbg += -fPIC -shared -soname=linux-vdso32.so.1 \ +LDFLAGS_vdso32.so.dbg += -shared -soname=linux-vdso32.so.1 \ --hash-style=both --build-id=sha1 -melf_s390 -T $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32) diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index 1605ba45ac4c05207f97842dbe9750d8966008dd..42d918d50a1ff0fa3f875cb9a50fc4520acb5368 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -26,7 +26,7 @@ KBUILD_AFLAGS_64 += -m64 -s KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_64 += -m64 -fPIC -fno-common -fno-builtin -ldflags-y := -fPIC -shared -soname=linux-vdso64.so.1 \ +ldflags-y := -shared -soname=linux-vdso64.so.1 \ --hash-style=both --build-id=sha1 -T $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64) diff --git a/arch/s390/kernel/vdso64/vdso_user_wrapper.S b/arch/s390/kernel/vdso64/vdso_user_wrapper.S index 97f0c0a669a59cea3a63de2d04c5cb3089b720ac..0625381359df49b76abaa0055098daab8a48a698 100644 --- a/arch/s390/kernel/vdso64/vdso_user_wrapper.S +++ b/arch/s390/kernel/vdso64/vdso_user_wrapper.S @@ -23,8 +23,10 @@ __kernel_\func: CFI_DEF_CFA_OFFSET (STACK_FRAME_OVERHEAD + WRAPPER_FRAME_SIZE) CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD stg %r14,STACK_FRAME_OVERHEAD(%r15) + CFI_REL_OFFSET 14, STACK_FRAME_OVERHEAD brasl %r14,__s390_vdso_\func lg %r14,STACK_FRAME_OVERHEAD(%r15) + CFI_RESTORE 14 aghi %r15,WRAPPER_FRAME_SIZE CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD CFI_RESTORE 15 diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 9436f3053b88c3271f19dee899905e2ae442a16d..003c926a0f4de0601b2d10e96cb5074251e6b51f 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -210,13 +210,13 @@ void vtime_flush(struct task_struct *tsk) virt_timer_expire(); steal = S390_lowcore.steal_timer; - avg_steal = S390_lowcore.avg_steal_timer / 2; + avg_steal = S390_lowcore.avg_steal_timer; if ((s64) steal > 0) { S390_lowcore.steal_timer = 0; account_steal_time(cputime_to_nsecs(steal)); avg_steal += steal; } - S390_lowcore.avg_steal_timer = avg_steal; + S390_lowcore.avg_steal_timer = avg_steal / 2; } static u64 vtime_delta(void) diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 0243b6e38d364cf005d99803742d55d4c73631b0..3beceff5f1c09367c7a5566ff35d7a97cf440246 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -1273,6 +1273,7 @@ static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr, unsigned long *pgt, int *dat_protection, int *fake) { + struct kvm *kvm; struct gmap *parent; union asce asce; union vaddress vaddr; @@ -1281,6 +1282,7 @@ static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr, *fake = 0; *dat_protection = 0; + kvm = sg->private; parent = sg->parent; vaddr.addr = saddr; asce.val = sg->orig_asce; @@ -1341,6 +1343,7 @@ shadow_r2t: rc = gmap_shadow_r2t(sg, saddr, rfte.val, *fake); if (rc) return rc; + kvm->stat.gmap_shadow_r1_entry++; } fallthrough; case ASCE_TYPE_REGION2: { @@ -1369,6 +1372,7 @@ shadow_r3t: rc = gmap_shadow_r3t(sg, saddr, rste.val, *fake); if (rc) return rc; + kvm->stat.gmap_shadow_r2_entry++; } fallthrough; case ASCE_TYPE_REGION3: { @@ -1406,6 +1410,7 @@ shadow_sgt: rc = gmap_shadow_sgt(sg, saddr, rtte.val, *fake); if (rc) return rc; + kvm->stat.gmap_shadow_r3_entry++; } fallthrough; case ASCE_TYPE_SEGMENT: { @@ -1439,6 +1444,7 @@ shadow_pgt: rc = gmap_shadow_pgt(sg, saddr, ste.val, *fake); if (rc) return rc; + kvm->stat.gmap_shadow_sg_entry++; } } /* Return the parent address of the page table */ @@ -1509,6 +1515,7 @@ shadow_page: pte.p |= dat_protection; if (!rc) rc = gmap_shadow_page(sg, saddr, __pte(pte.val)); + vcpu->kvm->stat.gmap_shadow_pg_entry++; ipte_unlock(vcpu->kvm); mmap_read_unlock(sg->mm); return rc; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index f604946ab2c85e57545e799b4ec0da9eb80f33e7..348d49268a7ecccf2aca8ba608087a5b7a6e3a1a 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -66,7 +66,14 @@ const struct _kvm_stats_desc kvm_vm_stats_desc[] = { STATS_DESC_COUNTER(VM, inject_pfault_done), STATS_DESC_COUNTER(VM, inject_service_signal), STATS_DESC_COUNTER(VM, inject_virtio), - STATS_DESC_COUNTER(VM, aen_forward) + STATS_DESC_COUNTER(VM, aen_forward), + STATS_DESC_COUNTER(VM, gmap_shadow_reuse), + STATS_DESC_COUNTER(VM, gmap_shadow_create), + STATS_DESC_COUNTER(VM, gmap_shadow_r1_entry), + STATS_DESC_COUNTER(VM, gmap_shadow_r2_entry), + STATS_DESC_COUNTER(VM, gmap_shadow_r3_entry), + STATS_DESC_COUNTER(VM, gmap_shadow_sg_entry), + STATS_DESC_COUNTER(VM, gmap_shadow_pg_entry), }; const struct kvm_stats_header kvm_vm_stats_header = { diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 740f8b56e63f9eea17c67778d86379f1635b2be1..d90c818a9ae712e2378822e0e9fb0dc9eff6f770 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -1206,15 +1206,17 @@ static int acquire_gmap_shadow(struct kvm_vcpu *vcpu, * we're holding has been unshadowed. If the gmap is still valid, * we can safely reuse it. */ - if (vsie_page->gmap && gmap_shadow_valid(vsie_page->gmap, asce, edat)) + if (vsie_page->gmap && gmap_shadow_valid(vsie_page->gmap, asce, edat)) { + vcpu->kvm->stat.gmap_shadow_reuse++; return 0; + } /* release the old shadow - if any, and mark the prefix as unmapped */ release_gmap_shadow(vsie_page); gmap = gmap_shadow(vcpu->arch.gmap, asce, edat); if (IS_ERR(gmap)) return PTR_ERR(gmap); - gmap->private = vcpu->kvm; + vcpu->kvm->stat.gmap_shadow_create++; WRITE_ONCE(vsie_page->gmap, gmap); return 0; } diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 243f673fa65151b5c33217391b1b6b99f800c665..59657e0363e7c1ce047f19cad2a0a3efccd7acb2 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -1675,6 +1675,7 @@ struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, return ERR_PTR(-ENOMEM); new->mm = parent->mm; new->parent = gmap_get(parent); + new->private = parent->private; new->orig_asce = asce; new->edat_level = edat_level; new->initialized = false; @@ -2641,7 +2642,7 @@ static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr, return 0; start = pmd_val(*pmd) & HPAGE_MASK; - end = start + HPAGE_SIZE - 1; + end = start + HPAGE_SIZE; __storage_key_init_range(start, end); set_bit(PG_arch_1, &page->flags); cond_resched(); diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index c299a18273ffeca9c30f89d75f14b6fdfc5b49ed..33ef6790114ab6b1340b5e1a65e18bfa920ddaba 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -139,7 +139,7 @@ static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste) } if (!test_and_set_bit(PG_arch_1, &page->flags)) - __storage_key_init_range(paddr, paddr + size - 1); + __storage_key_init_range(paddr, paddr + size); } void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 2c99f9552b2f5c8d4dd913e86a8f654fe0e80aee..394c69fda399e1cde61b915ce561063f4772d6f4 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -241,7 +241,7 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res, /* combine single writes by using store-block insn */ void __iowrite64_copy(void __iomem *to, const void *from, size_t count) { - zpci_memcpy_toio(to, from, count); + zpci_memcpy_toio(to, from, count * 8); } static void __iomem *__ioremap(phys_addr_t addr, size_t size, pgprot_t prot) diff --git a/arch/sparc/crypto/crop_devid.c b/arch/sparc/crypto/crop_devid.c index 83fc4536dcd5764c966eb17020558a4dd678b026..93f4e0fdd38c1f3511675fa029299c955a3ce5b9 100644 --- a/arch/sparc/crypto/crop_devid.c +++ b/arch/sparc/crypto/crop_devid.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include -#include /* This is a dummy device table linked into all of the crypto * opcode drivers. It serves to trigger the module autoloading diff --git a/arch/sparc/include/asm/floppy_32.h b/arch/sparc/include/asm/floppy_32.h index e10ab9ad3097d966f02eb2720eeeb1476745cadb..836f6575aa1d71b1d2c118264e82979ea3cf1830 100644 --- a/arch/sparc/include/asm/floppy_32.h +++ b/arch/sparc/include/asm/floppy_32.h @@ -8,7 +8,7 @@ #define __ASM_SPARC_FLOPPY_H #include -#include +#include #include #include diff --git a/arch/sparc/include/asm/floppy_64.h b/arch/sparc/include/asm/floppy_64.h index 070c8c1f5c8fd4388d8ee4edc985ce583d4f955e..6efeb24b0a92cafe92c5c9231ff6f2cf7416d5f9 100644 --- a/arch/sparc/include/asm/floppy_64.h +++ b/arch/sparc/include/asm/floppy_64.h @@ -11,7 +11,7 @@ #define __ASM_SPARC64_FLOPPY_H #include -#include +#include #include #include diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h index 94eb529dcb77623caf637387e694d8e5ddc049a8..2718cbea826a7d13aefacd26fee3719b69856746 100644 --- a/arch/sparc/include/asm/jump_label.h +++ b/arch/sparc/include/asm/jump_label.h @@ -10,7 +10,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "nop\n\t" "nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" @@ -26,7 +26,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "b %l[l_yes]\n\t" "nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" diff --git a/arch/sparc/include/asm/parport.h b/arch/sparc/include/asm/parport.h index 03b27090c0c8cb637d63db12e23224da2308aaad..e2eed8f97665fb5029df9cc6969a3f44502de77f 100644 --- a/arch/sparc/include/asm/parport.h +++ b/arch/sparc/include/asm/parport.h @@ -1,255 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* parport.h: sparc64 specific parport initialization and dma. - * - * Copyright (C) 1999 Eddie C. Dost (ecd@skynet.be) - */ +#ifndef ___ASM_SPARC_PARPORT_H +#define ___ASM_SPARC_PARPORT_H -#ifndef _ASM_SPARC64_PARPORT_H -#define _ASM_SPARC64_PARPORT_H 1 - -#include - -#include -#include -#include - -#define PARPORT_PC_MAX_PORTS PARPORT_MAX - -/* - * While sparc64 doesn't have an ISA DMA API, we provide something that looks - * close enough to make parport_pc happy - */ -#define HAS_DMA - -#ifdef CONFIG_PARPORT_PC_FIFO -static DEFINE_SPINLOCK(dma_spin_lock); - -#define claim_dma_lock() \ -({ unsigned long flags; \ - spin_lock_irqsave(&dma_spin_lock, flags); \ - flags; \ -}) - -#define release_dma_lock(__flags) \ - spin_unlock_irqrestore(&dma_spin_lock, __flags); +#if defined(__sparc__) && defined(__arch64__) +#include +#else +#include +#endif #endif -static struct sparc_ebus_info { - struct ebus_dma_info info; - unsigned int addr; - unsigned int count; - int lock; - - struct parport *port; -} sparc_ebus_dmas[PARPORT_PC_MAX_PORTS]; - -static DECLARE_BITMAP(dma_slot_map, PARPORT_PC_MAX_PORTS); - -static inline int request_dma(unsigned int dmanr, const char *device_id) -{ - if (dmanr >= PARPORT_PC_MAX_PORTS) - return -EINVAL; - if (xchg(&sparc_ebus_dmas[dmanr].lock, 1) != 0) - return -EBUSY; - return 0; -} - -static inline void free_dma(unsigned int dmanr) -{ - if (dmanr >= PARPORT_PC_MAX_PORTS) { - printk(KERN_WARNING "Trying to free DMA%d\n", dmanr); - return; - } - if (xchg(&sparc_ebus_dmas[dmanr].lock, 0) == 0) { - printk(KERN_WARNING "Trying to free free DMA%d\n", dmanr); - return; - } -} - -static inline void enable_dma(unsigned int dmanr) -{ - ebus_dma_enable(&sparc_ebus_dmas[dmanr].info, 1); - - if (ebus_dma_request(&sparc_ebus_dmas[dmanr].info, - sparc_ebus_dmas[dmanr].addr, - sparc_ebus_dmas[dmanr].count)) - BUG(); -} - -static inline void disable_dma(unsigned int dmanr) -{ - ebus_dma_enable(&sparc_ebus_dmas[dmanr].info, 0); -} - -static inline void clear_dma_ff(unsigned int dmanr) -{ - /* nothing */ -} - -static inline void set_dma_mode(unsigned int dmanr, char mode) -{ - ebus_dma_prepare(&sparc_ebus_dmas[dmanr].info, (mode != DMA_MODE_WRITE)); -} - -static inline void set_dma_addr(unsigned int dmanr, unsigned int addr) -{ - sparc_ebus_dmas[dmanr].addr = addr; -} - -static inline void set_dma_count(unsigned int dmanr, unsigned int count) -{ - sparc_ebus_dmas[dmanr].count = count; -} - -static inline unsigned int get_dma_residue(unsigned int dmanr) -{ - return ebus_dma_residue(&sparc_ebus_dmas[dmanr].info); -} - -static int ecpp_probe(struct platform_device *op) -{ - unsigned long base = op->resource[0].start; - unsigned long config = op->resource[1].start; - unsigned long d_base = op->resource[2].start; - unsigned long d_len; - struct device_node *parent; - struct parport *p; - int slot, err; - - parent = op->dev.of_node->parent; - if (of_node_name_eq(parent, "dma")) { - p = parport_pc_probe_port(base, base + 0x400, - op->archdata.irqs[0], PARPORT_DMA_NOFIFO, - op->dev.parent->parent, 0); - if (!p) - return -ENOMEM; - dev_set_drvdata(&op->dev, p); - return 0; - } - - for (slot = 0; slot < PARPORT_PC_MAX_PORTS; slot++) { - if (!test_and_set_bit(slot, dma_slot_map)) - break; - } - err = -ENODEV; - if (slot >= PARPORT_PC_MAX_PORTS) - goto out_err; - - spin_lock_init(&sparc_ebus_dmas[slot].info.lock); - - d_len = (op->resource[2].end - d_base) + 1UL; - sparc_ebus_dmas[slot].info.regs = - of_ioremap(&op->resource[2], 0, d_len, "ECPP DMA"); - - if (!sparc_ebus_dmas[slot].info.regs) - goto out_clear_map; - - sparc_ebus_dmas[slot].info.flags = 0; - sparc_ebus_dmas[slot].info.callback = NULL; - sparc_ebus_dmas[slot].info.client_cookie = NULL; - sparc_ebus_dmas[slot].info.irq = 0xdeadbeef; - strcpy(sparc_ebus_dmas[slot].info.name, "parport"); - if (ebus_dma_register(&sparc_ebus_dmas[slot].info)) - goto out_unmap_regs; - - ebus_dma_irq_enable(&sparc_ebus_dmas[slot].info, 1); - - /* Configure IRQ to Push Pull, Level Low */ - /* Enable ECP, set bit 2 of the CTR first */ - outb(0x04, base + 0x02); - ns87303_modify(config, PCR, - PCR_EPP_ENABLE | - PCR_IRQ_ODRAIN, - PCR_ECP_ENABLE | - PCR_ECP_CLK_ENA | - PCR_IRQ_POLAR); - - /* CTR bit 5 controls direction of port */ - ns87303_modify(config, PTR, - 0, PTR_LPT_REG_DIR); - - p = parport_pc_probe_port(base, base + 0x400, - op->archdata.irqs[0], - slot, - op->dev.parent, - 0); - err = -ENOMEM; - if (!p) - goto out_disable_irq; - - dev_set_drvdata(&op->dev, p); - - return 0; - -out_disable_irq: - ebus_dma_irq_enable(&sparc_ebus_dmas[slot].info, 0); - ebus_dma_unregister(&sparc_ebus_dmas[slot].info); - -out_unmap_regs: - of_iounmap(&op->resource[2], sparc_ebus_dmas[slot].info.regs, d_len); - -out_clear_map: - clear_bit(slot, dma_slot_map); - -out_err: - return err; -} - -static int ecpp_remove(struct platform_device *op) -{ - struct parport *p = dev_get_drvdata(&op->dev); - int slot = p->dma; - - parport_pc_unregister_port(p); - - if (slot != PARPORT_DMA_NOFIFO) { - unsigned long d_base = op->resource[2].start; - unsigned long d_len; - - d_len = (op->resource[2].end - d_base) + 1UL; - - ebus_dma_irq_enable(&sparc_ebus_dmas[slot].info, 0); - ebus_dma_unregister(&sparc_ebus_dmas[slot].info); - of_iounmap(&op->resource[2], - sparc_ebus_dmas[slot].info.regs, - d_len); - clear_bit(slot, dma_slot_map); - } - - return 0; -} - -static const struct of_device_id ecpp_match[] = { - { - .name = "ecpp", - }, - { - .name = "parallel", - .compatible = "ecpp", - }, - { - .name = "parallel", - .compatible = "ns87317-ecpp", - }, - { - .name = "parallel", - .compatible = "pnpALI,1533,3", - }, - {}, -}; - -static struct platform_driver ecpp_driver = { - .driver = { - .name = "ecpp", - .of_match_table = ecpp_match, - }, - .probe = ecpp_probe, - .remove = ecpp_remove, -}; - -static int parport_pc_find_nonpci_ports(int autoirq, int autodma) -{ - return platform_driver_register(&ecpp_driver); -} - -#endif /* !(_ASM_SPARC64_PARPORT_H */ diff --git a/arch/sparc/include/asm/parport_64.h b/arch/sparc/include/asm/parport_64.h new file mode 100644 index 0000000000000000000000000000000000000000..0a7ffcfd59cda0ade67bd7c640b1f69edc758e30 --- /dev/null +++ b/arch/sparc/include/asm/parport_64.h @@ -0,0 +1,256 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* parport.h: sparc64 specific parport initialization and dma. + * + * Copyright (C) 1999 Eddie C. Dost (ecd@skynet.be) + */ + +#ifndef _ASM_SPARC64_PARPORT_H +#define _ASM_SPARC64_PARPORT_H 1 + +#include +#include + +#include +#include +#include + +#define PARPORT_PC_MAX_PORTS PARPORT_MAX + +/* + * While sparc64 doesn't have an ISA DMA API, we provide something that looks + * close enough to make parport_pc happy + */ +#define HAS_DMA + +#ifdef CONFIG_PARPORT_PC_FIFO +static DEFINE_SPINLOCK(dma_spin_lock); + +#define claim_dma_lock() \ +({ unsigned long flags; \ + spin_lock_irqsave(&dma_spin_lock, flags); \ + flags; \ +}) + +#define release_dma_lock(__flags) \ + spin_unlock_irqrestore(&dma_spin_lock, __flags); +#endif + +static struct sparc_ebus_info { + struct ebus_dma_info info; + unsigned int addr; + unsigned int count; + int lock; + + struct parport *port; +} sparc_ebus_dmas[PARPORT_PC_MAX_PORTS]; + +static DECLARE_BITMAP(dma_slot_map, PARPORT_PC_MAX_PORTS); + +static inline int request_dma(unsigned int dmanr, const char *device_id) +{ + if (dmanr >= PARPORT_PC_MAX_PORTS) + return -EINVAL; + if (xchg(&sparc_ebus_dmas[dmanr].lock, 1) != 0) + return -EBUSY; + return 0; +} + +static inline void free_dma(unsigned int dmanr) +{ + if (dmanr >= PARPORT_PC_MAX_PORTS) { + printk(KERN_WARNING "Trying to free DMA%d\n", dmanr); + return; + } + if (xchg(&sparc_ebus_dmas[dmanr].lock, 0) == 0) { + printk(KERN_WARNING "Trying to free free DMA%d\n", dmanr); + return; + } +} + +static inline void enable_dma(unsigned int dmanr) +{ + ebus_dma_enable(&sparc_ebus_dmas[dmanr].info, 1); + + if (ebus_dma_request(&sparc_ebus_dmas[dmanr].info, + sparc_ebus_dmas[dmanr].addr, + sparc_ebus_dmas[dmanr].count)) + BUG(); +} + +static inline void disable_dma(unsigned int dmanr) +{ + ebus_dma_enable(&sparc_ebus_dmas[dmanr].info, 0); +} + +static inline void clear_dma_ff(unsigned int dmanr) +{ + /* nothing */ +} + +static inline void set_dma_mode(unsigned int dmanr, char mode) +{ + ebus_dma_prepare(&sparc_ebus_dmas[dmanr].info, (mode != DMA_MODE_WRITE)); +} + +static inline void set_dma_addr(unsigned int dmanr, unsigned int addr) +{ + sparc_ebus_dmas[dmanr].addr = addr; +} + +static inline void set_dma_count(unsigned int dmanr, unsigned int count) +{ + sparc_ebus_dmas[dmanr].count = count; +} + +static inline unsigned int get_dma_residue(unsigned int dmanr) +{ + return ebus_dma_residue(&sparc_ebus_dmas[dmanr].info); +} + +static int ecpp_probe(struct platform_device *op) +{ + unsigned long base = op->resource[0].start; + unsigned long config = op->resource[1].start; + unsigned long d_base = op->resource[2].start; + unsigned long d_len; + struct device_node *parent; + struct parport *p; + int slot, err; + + parent = op->dev.of_node->parent; + if (of_node_name_eq(parent, "dma")) { + p = parport_pc_probe_port(base, base + 0x400, + op->archdata.irqs[0], PARPORT_DMA_NOFIFO, + op->dev.parent->parent, 0); + if (!p) + return -ENOMEM; + dev_set_drvdata(&op->dev, p); + return 0; + } + + for (slot = 0; slot < PARPORT_PC_MAX_PORTS; slot++) { + if (!test_and_set_bit(slot, dma_slot_map)) + break; + } + err = -ENODEV; + if (slot >= PARPORT_PC_MAX_PORTS) + goto out_err; + + spin_lock_init(&sparc_ebus_dmas[slot].info.lock); + + d_len = (op->resource[2].end - d_base) + 1UL; + sparc_ebus_dmas[slot].info.regs = + of_ioremap(&op->resource[2], 0, d_len, "ECPP DMA"); + + if (!sparc_ebus_dmas[slot].info.regs) + goto out_clear_map; + + sparc_ebus_dmas[slot].info.flags = 0; + sparc_ebus_dmas[slot].info.callback = NULL; + sparc_ebus_dmas[slot].info.client_cookie = NULL; + sparc_ebus_dmas[slot].info.irq = 0xdeadbeef; + strcpy(sparc_ebus_dmas[slot].info.name, "parport"); + if (ebus_dma_register(&sparc_ebus_dmas[slot].info)) + goto out_unmap_regs; + + ebus_dma_irq_enable(&sparc_ebus_dmas[slot].info, 1); + + /* Configure IRQ to Push Pull, Level Low */ + /* Enable ECP, set bit 2 of the CTR first */ + outb(0x04, base + 0x02); + ns87303_modify(config, PCR, + PCR_EPP_ENABLE | + PCR_IRQ_ODRAIN, + PCR_ECP_ENABLE | + PCR_ECP_CLK_ENA | + PCR_IRQ_POLAR); + + /* CTR bit 5 controls direction of port */ + ns87303_modify(config, PTR, + 0, PTR_LPT_REG_DIR); + + p = parport_pc_probe_port(base, base + 0x400, + op->archdata.irqs[0], + slot, + op->dev.parent, + 0); + err = -ENOMEM; + if (!p) + goto out_disable_irq; + + dev_set_drvdata(&op->dev, p); + + return 0; + +out_disable_irq: + ebus_dma_irq_enable(&sparc_ebus_dmas[slot].info, 0); + ebus_dma_unregister(&sparc_ebus_dmas[slot].info); + +out_unmap_regs: + of_iounmap(&op->resource[2], sparc_ebus_dmas[slot].info.regs, d_len); + +out_clear_map: + clear_bit(slot, dma_slot_map); + +out_err: + return err; +} + +static int ecpp_remove(struct platform_device *op) +{ + struct parport *p = dev_get_drvdata(&op->dev); + int slot = p->dma; + + parport_pc_unregister_port(p); + + if (slot != PARPORT_DMA_NOFIFO) { + unsigned long d_base = op->resource[2].start; + unsigned long d_len; + + d_len = (op->resource[2].end - d_base) + 1UL; + + ebus_dma_irq_enable(&sparc_ebus_dmas[slot].info, 0); + ebus_dma_unregister(&sparc_ebus_dmas[slot].info); + of_iounmap(&op->resource[2], + sparc_ebus_dmas[slot].info.regs, + d_len); + clear_bit(slot, dma_slot_map); + } + + return 0; +} + +static const struct of_device_id ecpp_match[] = { + { + .name = "ecpp", + }, + { + .name = "parallel", + .compatible = "ecpp", + }, + { + .name = "parallel", + .compatible = "ns87317-ecpp", + }, + { + .name = "parallel", + .compatible = "pnpALI,1533,3", + }, + {}, +}; + +static struct platform_driver ecpp_driver = { + .driver = { + .name = "ecpp", + .of_match_table = ecpp_match, + }, + .probe = ecpp_probe, + .remove = ecpp_remove, +}; + +static int parport_pc_find_nonpci_ports(int autoirq, int autodma) +{ + return platform_driver_register(&ecpp_driver); +} + +#endif /* !(_ASM_SPARC64_PARPORT_H */ diff --git a/arch/sparc/kernel/apc.c b/arch/sparc/kernel/apc.c index ecd05bc0a10454a440e0b362d0c413903363fbab..d44725d37e30f388bf8cf19d72baf720f94da084 100644 --- a/arch/sparc/kernel/apc.c +++ b/arch/sparc/kernel/apc.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/sparc/kernel/auxio_32.c b/arch/sparc/kernel/auxio_32.c index a32d588174f2f9eaaddc97442ef8f22e3c696c01..989860e890c4fea614f92688af7e59449a783fd3 100644 --- a/arch/sparc/kernel/auxio_32.c +++ b/arch/sparc/kernel/auxio_32.c @@ -8,7 +8,6 @@ #include #include #include -#include #include #include diff --git a/arch/sparc/kernel/auxio_64.c b/arch/sparc/kernel/auxio_64.c index 774a82b0c649f0bcf0d7bb15d66d7eaa805e41ed..2a2800d213256340cb729ecc2700aee3dd29fba5 100644 --- a/arch/sparc/kernel/auxio_64.c +++ b/arch/sparc/kernel/auxio_64.c @@ -10,7 +10,8 @@ #include #include #include -#include +#include +#include #include #include diff --git a/arch/sparc/kernel/central.c b/arch/sparc/kernel/central.c index 23f8838dd96e3ad3dd6be1ff0f7c2394f1244e6b..a1a6485c91831386334eaa8b5314ab61b9dbef4e 100644 --- a/arch/sparc/kernel/central.c +++ b/arch/sparc/kernel/central.c @@ -10,7 +10,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/sparc/kernel/chmc.c b/arch/sparc/kernel/chmc.c index 6ff43df740e08e9f4a8c69446a3fe4f9ab9607f1..d5fad5fb04c1d9687fd840e85da860373a3d3b95 100644 --- a/arch/sparc/kernel/chmc.c +++ b/arch/sparc/kernel/chmc.c @@ -15,7 +15,8 @@ #include #include #include -#include +#include +#include #include #include #include diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c index 4e4f3d3263e46ba409127cf6fe51b8e2bb1d8b6b..e5a327799e57484d1a522e7ebb9cdb5104cdd1e4 100644 --- a/arch/sparc/kernel/ioport.c +++ b/arch/sparc/kernel/ioport.c @@ -39,7 +39,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c index 39229940d725d0771d41fa31d9a61f40d78f3c81..4c61da491fee15ea890537f766d470041223cb23 100644 --- a/arch/sparc/kernel/leon_kernel.c +++ b/arch/sparc/kernel/leon_kernel.c @@ -8,9 +8,7 @@ #include #include #include -#include #include -#include #include #include diff --git a/arch/sparc/kernel/leon_pci.c b/arch/sparc/kernel/leon_pci.c index e5e5ff6b9a5c5a3d5aa144e797973d30c459479b..3a73bc466f95dc5cc118496a9f9908467a3b8c8d 100644 --- a/arch/sparc/kernel/leon_pci.c +++ b/arch/sparc/kernel/leon_pci.c @@ -7,7 +7,8 @@ * Code is partially derived from pcic.c */ -#include +#include +#include #include #include #include diff --git a/arch/sparc/kernel/leon_pci_grpci1.c b/arch/sparc/kernel/leon_pci_grpci1.c index e6935d0ac1ec9ffb463be7bff9e58b975774fd6a..b2b639bee068485dba8ef2ac5daee9ad086f3385 100644 --- a/arch/sparc/kernel/leon_pci_grpci1.c +++ b/arch/sparc/kernel/leon_pci_grpci1.c @@ -13,10 +13,11 @@ * Contributors: Daniel Hellstrom */ -#include #include #include +#include #include +#include #include #include @@ -696,7 +697,7 @@ err1: return err; } -static const struct of_device_id grpci1_of_match[] __initconst = { +static const struct of_device_id grpci1_of_match[] = { { .name = "GAISLER_PCIFBRG", }, diff --git a/arch/sparc/kernel/leon_pci_grpci2.c b/arch/sparc/kernel/leon_pci_grpci2.c index ca22f93d904548071d631671a6fafe7dce2a06e2..ac2acd62a24ece38d2dad4902b4fda4d39013556 100644 --- a/arch/sparc/kernel/leon_pci_grpci2.c +++ b/arch/sparc/kernel/leon_pci_grpci2.c @@ -6,12 +6,14 @@ * */ -#include #include #include #include #include #include +#include +#include + #include #include #include @@ -887,7 +889,7 @@ err1: return err; } -static const struct of_device_id grpci2_of_match[] __initconst = { +static const struct of_device_id grpci2_of_match[] = { { .name = "GAISLER_GRPCI2", }, diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index 060fff95a305c1135432f94a37216f68c76d6725..fbf25e926f67c4570b3bc798fbd44d981016b0e0 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -274,7 +274,7 @@ static int __init setup_nmi_watchdog(char *str) if (!strncmp(str, "panic", 5)) panic_on_timeout = 1; - return 0; + return 1; } __setup("nmi_watchdog=", setup_nmi_watchdog); diff --git a/arch/sparc/kernel/of_device_32.c b/arch/sparc/kernel/of_device_32.c index 4ebf51e6e78ec1a8d12f4cabbd3106b7cace359c..9ac6853b34c1b4a2d014e520c2e3e33ccf79a4c1 100644 --- a/arch/sparc/kernel/of_device_32.c +++ b/arch/sparc/kernel/of_device_32.c @@ -7,8 +7,8 @@ #include #include #include -#include #include +#include #include #include #include diff --git a/arch/sparc/kernel/of_device_64.c b/arch/sparc/kernel/of_device_64.c index 5a9f86b1d4e7e33cb7b60cca06b0c99e1f696dbf..a8ccd7260fe7f4ce1f9c12c87a08830349afd675 100644 --- a/arch/sparc/kernel/of_device_64.c +++ b/arch/sparc/kernel/of_device_64.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include #include -#include #include #include #include @@ -9,8 +8,9 @@ #include #include #include -#include +#include #include +#include #include #include "of_device_common.h" diff --git a/arch/sparc/kernel/of_device_common.c b/arch/sparc/kernel/of_device_common.c index e717a56efc5d3d6743b2f0a42dd1a87e9fa90092..a09724381bd40660813eeae0594522d36145bdfa 100644 --- a/arch/sparc/kernel/of_device_common.c +++ b/arch/sparc/kernel/of_device_common.c @@ -1,15 +1,15 @@ // SPDX-License-Identifier: GPL-2.0-only #include #include -#include #include #include #include #include +#include #include #include -#include #include +#include #include "of_device_common.h" diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index cb1ef25116e943436c83d68ae033dbb7d7161b25..5637b37ba911415185fc9e5b749858ca8e7f7f87 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -20,8 +20,9 @@ #include #include #include -#include +#include #include +#include #include #include diff --git a/arch/sparc/kernel/pci_common.c b/arch/sparc/kernel/pci_common.c index 4759ccd542fe6a7f7522dc811673c7703cdd30ca..5eeec9ad684570fc1a6464423cc52f53309d6ba2 100644 --- a/arch/sparc/kernel/pci_common.c +++ b/arch/sparc/kernel/pci_common.c @@ -8,7 +8,8 @@ #include #include #include -#include +#include +#include #include #include diff --git a/arch/sparc/kernel/pci_fire.c b/arch/sparc/kernel/pci_fire.c index 0ca08d455e805d7cc72bfc74377105e78d699a68..0b91bde80fdc5e9d70492bd03edf4c116a9ad834 100644 --- a/arch/sparc/kernel/pci_fire.c +++ b/arch/sparc/kernel/pci_fire.c @@ -10,7 +10,8 @@ #include #include #include -#include +#include +#include #include #include diff --git a/arch/sparc/kernel/pci_impl.h b/arch/sparc/kernel/pci_impl.h index 4e3d15189fa95f10a2e8e8ba4212820979938686..f31761f517575d7efa69d344cef61b0a816a4e02 100644 --- a/arch/sparc/kernel/pci_impl.h +++ b/arch/sparc/kernel/pci_impl.h @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/sparc/kernel/pci_msi.c b/arch/sparc/kernel/pci_msi.c index 9ed11985768e1318e8e7a67307882a111bc50944..fc7402948b7bc06e46e0eb85f799aa8bfa4efb75 100644 --- a/arch/sparc/kernel/pci_msi.c +++ b/arch/sparc/kernel/pci_msi.c @@ -5,6 +5,8 @@ */ #include #include +#include +#include #include #include diff --git a/arch/sparc/kernel/pci_psycho.c b/arch/sparc/kernel/pci_psycho.c index f413371da387193c7dc01a7ca90af62605fb886c..1efc98305ec76d00c221c84dac8b6bc41e63c36a 100644 --- a/arch/sparc/kernel/pci_psycho.c +++ b/arch/sparc/kernel/pci_psycho.c @@ -13,7 +13,9 @@ #include #include #include -#include +#include +#include +#include #include #include diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index 38448097180523b24c3f4b1582c6ee3497abac19..0ddef827e0f996ab0c34552800721daa5787b137 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -15,7 +15,8 @@ #include #include #include -#include +#include +#include #include #include diff --git a/arch/sparc/kernel/pmc.c b/arch/sparc/kernel/pmc.c index b5c1eb33b9518aab087fcb81c08a3da3e0e63873..69a0206e56f0122ed08ef919f8bbec3646a47afb 100644 --- a/arch/sparc/kernel/pmc.c +++ b/arch/sparc/kernel/pmc.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/sparc/kernel/power.c b/arch/sparc/kernel/power.c index d941875dd718653aa4cdbd5f8e705b38f48c3a04..2f6c909e1755d8c1636661ef2ed3065c1b5c6878 100644 --- a/arch/sparc/kernel/power.c +++ b/arch/sparc/kernel/power.c @@ -9,7 +9,8 @@ #include #include #include -#include +#include +#include #include #include diff --git a/arch/sparc/kernel/prom_irqtrans.c b/arch/sparc/kernel/prom_irqtrans.c index 28aff1c524b58fd81717ffa4b0bf9cc4a4a3bf5e..426bd08cb2ab1053111a4ef33ca24b092311285a 100644 --- a/arch/sparc/kernel/prom_irqtrans.c +++ b/arch/sparc/kernel/prom_irqtrans.c @@ -4,6 +4,7 @@ #include #include #include +#include #include #include diff --git a/arch/sparc/kernel/psycho_common.c b/arch/sparc/kernel/psycho_common.c index e90bcb6bad7fc76b24a241eb224aff738c2e0296..5ee74b4c0cf40e3e920ddcb0834b2ca100592bbe 100644 --- a/arch/sparc/kernel/psycho_common.c +++ b/arch/sparc/kernel/psycho_common.c @@ -6,6 +6,7 @@ #include #include #include +#include #include diff --git a/arch/sparc/kernel/sbus.c b/arch/sparc/kernel/sbus.c index 32141e1006c4a4907c5d6bbc4caba20aa30cb5db..0bababf6f2bcd8a5866b36a2c59ab77374e0c968 100644 --- a/arch/sparc/kernel/sbus.c +++ b/arch/sparc/kernel/sbus.c @@ -14,7 +14,8 @@ #include #include #include -#include +#include +#include #include #include diff --git a/arch/sparc/kernel/time_32.c b/arch/sparc/kernel/time_32.c index 8a08830e4a653fc7e6c46f8a431c67d730574940..79934beba03a6cc7ab914090cb56b77704e83001 100644 --- a/arch/sparc/kernel/time_32.c +++ b/arch/sparc/kernel/time_32.c @@ -33,7 +33,6 @@ #include #include #include -#include #include #include diff --git a/arch/sparc/mm/io-unit.c b/arch/sparc/mm/io-unit.c index bf3e6d2fe5d949549b8ab103482a58c0b84d7619..3afbbe5fba46be392935aa0312f951e431fdb3ac 100644 --- a/arch/sparc/mm/io-unit.c +++ b/arch/sparc/mm/io-unit.c @@ -13,7 +13,8 @@ #include #include #include -#include +#include +#include #include #include diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c index 9e3f6933ca13f4e3282d128a0581b3519b086802..14e178bfe33abce60f26feb9e947f43b88649f35 100644 --- a/arch/sparc/mm/iommu.c +++ b/arch/sparc/mm/iommu.c @@ -7,14 +7,15 @@ * Copyright (C) 1996 Eddie C. Dost (ecd@skynet.be) * Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz) */ - + #include #include #include #include #include #include -#include +#include +#include #include #include diff --git a/arch/sparc/vdso/vma.c b/arch/sparc/vdso/vma.c index ae9a86cb6f3d978245005c06777f12990b9fcad3..2b97df0850aa7990f959440283bb94b0b95e7d3d 100644 --- a/arch/sparc/vdso/vma.c +++ b/arch/sparc/vdso/vma.c @@ -449,9 +449,8 @@ static __init int vdso_setup(char *s) unsigned long val; err = kstrtoul(s, 10, &val); - if (err) - return err; - vdso_enabled = val; - return 0; + if (!err) + vdso_enabled = val; + return 1; } __setup("vdso=", vdso_setup); diff --git a/arch/um/Makefile b/arch/um/Makefile index 3dbd0e3b660eacb2b8641093433573009dc55a90..778c50f2739926ebfc7eeb20b4a13acd853212ae 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -118,7 +118,9 @@ archprepare: $(Q)$(MAKE) $(build)=$(HOST_DIR)/um include/generated/user_constants.h LINK-$(CONFIG_LD_SCRIPT_STATIC) += -static -LINK-$(CONFIG_LD_SCRIPT_DYN) += $(call cc-option, -no-pie) +ifdef CONFIG_LD_SCRIPT_DYN +LINK-$(call gcc-min-version, 60100)$(CONFIG_CC_IS_CLANG) += -no-pie +endif LINK-$(CONFIG_LD_SCRIPT_DYN_RPATH) += -Wl,-rpath,/lib CFLAGS_NO_HARDENING := $(call cc-option, -fno-PIC,) $(call cc-option, -fno-pic,) \ diff --git a/arch/um/include/asm/cpufeature.h b/arch/um/include/asm/cpufeature.h index 4b6d1b526bc1217e2e89d4670f9c4385e68dacc7..66fe06db872f05bb775f0089a4f134f77563efe4 100644 --- a/arch/um/include/asm/cpufeature.h +++ b/arch/um/include/asm/cpufeature.h @@ -75,7 +75,7 @@ extern void setup_clear_cpu_cap(unsigned int bit); */ static __always_inline bool _static_cpu_has(u16 bit) { - asm_volatile_goto("1: jmp 6f\n" + asm goto("1: jmp 6f\n" "2:\n" ".skip -(((5f-4f) - (2b-1b)) > 0) * " "((5f-4f) - (2b-1b)),0x90\n" diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 4c9bfc4be58d4e541bdbcdccdfdf1765f3d049b6..49cea5b81649d3e46fb571e977c5974da0abae4b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -61,6 +61,7 @@ config X86 select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI select ARCH_32BIT_OFF_T if X86_32 select ARCH_CLOCKSOURCE_INIT + select ARCH_CONFIGURES_CPU_MITIGATIONS select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE select ARCH_ENABLE_HUGEPAGE_MIGRATION if X86_64 && HUGETLB_PAGE && MIGRATION select ARCH_ENABLE_MEMORY_HOTPLUG if X86_64 @@ -1553,19 +1554,6 @@ config AMD_MEM_ENCRYPT This requires an AMD processor that supports Secure Memory Encryption (SME). -config AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT - bool "Activate AMD Secure Memory Encryption (SME) by default" - depends on AMD_MEM_ENCRYPT - help - Say yes to have system memory encrypted by default if running on - an AMD processor that supports Secure Memory Encryption (SME). - - If set to Y, then the encryption of system memory can be - deactivated with the mem_encrypt=off command line option. - - If set to N, then the encryption of system memory can be - activated with the mem_encrypt=on command line option. - # Common NUMA Features config NUMA bool "NUMA Memory Allocation and Scheduler Support" @@ -1982,6 +1970,23 @@ config EFI_STUB See Documentation/admin-guide/efi-stub.rst for more information. +config EFI_HANDOVER_PROTOCOL + bool "EFI handover protocol (DEPRECATED)" + depends on EFI_STUB + default y + help + Select this in order to include support for the deprecated EFI + handover protocol, which defines alternative entry points into the + EFI stub. This is a practice that has no basis in the UEFI + specification, and requires a priori knowledge on the part of the + bootloader about Linux/x86 specific ways of passing the command line + and initrd, and where in memory those assets may be loaded. + + If in doubt, say Y. Even though the corresponding support is not + present in upstream GRUB or other bootloaders, most distros build + GRUB with numerous downstream patches applied, and may rely on the + handover protocol as as result. + config EFI_MIXED bool "EFI mixed-mode support" depends on EFI_STUB && X86_64 @@ -2445,17 +2450,17 @@ config CC_HAS_SLS config CC_HAS_RETURN_THUNK def_bool $(cc-option,-mfunction-return=thunk-extern) -menuconfig SPECULATION_MITIGATIONS - bool "Mitigations for speculative execution vulnerabilities" +menuconfig CPU_MITIGATIONS + bool "Mitigations for CPU vulnerabilities" default y help - Say Y here to enable options which enable mitigations for - speculative execution hardware vulnerabilities. + Say Y here to enable options which enable mitigations for hardware + vulnerabilities (usually related to speculative execution). If you say N, all mitigations will be disabled. You really should know what you are doing to say so. -if SPECULATION_MITIGATIONS +if CPU_MITIGATIONS config PAGE_TABLE_ISOLATION bool "Remove the kernel mapping in user mode" @@ -2548,6 +2553,27 @@ config GDS_FORCE_MITIGATION If in doubt, say N. +config MITIGATION_RFDS + bool "RFDS Mitigation" + depends on CPU_SUP_INTEL + default y + help + Enable mitigation for Register File Data Sampling (RFDS) by default. + RFDS is a hardware vulnerability which affects Intel Atom CPUs. It + allows unprivileged speculative access to stale data previously + stored in floating point, vector and integer registers. + See also + +config MITIGATION_SPECTRE_BHI + bool "Mitigate Spectre-BHB (Branch History Injection)" + depends on CPU_SUP_INTEL + default y + help + Enable BHI mitigations. BHI attacks are a form of Spectre V2 attacks + where the branch history buffer is poisoned to speculatively steer + indirect branches. + See + endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 542377cd419d788e470e2a90d306ee3212cf9024..ce5ed2c2db0c9b2f20c77bee5052f7c497e14d24 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -375,7 +375,7 @@ config X86_CMOV config X86_MINIMUM_CPU_FAMILY int default "64" if X86_64 - default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8) + default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCORE2 || MK7 || MK8) default "5" if X86_32 && X86_CMPXCHG64 default "4" diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 9e38ffaadb5d972e640520e4985718b23b0a76ba..3c1b3520361c711806d03eef2d45a3028cf1727e 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -91,7 +91,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE SETUP_OBJS = $(addprefix $(obj)/,$(setup-y)) -sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|efi32_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p' +sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|efi.._stub_entry\|efi\(32\)\?_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|_e\?data\|z_.*\)$$/\#define ZO_\2 0x\1/p' quiet_cmd_zoffset = ZOFFSET $@ cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@ diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 15b7b403a4bd030c2d16dd02c9042a143874d993..6e61baff223f80d6304eaa3910657afbb340c8ad 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -74,12 +74,17 @@ LDFLAGS_vmlinux += -z noexecstack ifeq ($(CONFIG_LD_IS_BFD),y) LDFLAGS_vmlinux += $(call ld-option,--no-warn-rwx-segments) endif +ifeq ($(CONFIG_EFI_STUB),y) +# ensure that the static EFI stub library will be pulled in, even if it is +# never referenced explicitly from the startup code +LDFLAGS_vmlinux += -u efi_pe_entry +endif LDFLAGS_vmlinux += -T hostprogs := mkpiggy HOST_EXTRACFLAGS += -I$(srctree)/tools/include -sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p' +sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__start_rodata\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p' quiet_cmd_voffset = VOFFSET $@ cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@ @@ -100,7 +105,7 @@ vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o ifdef CONFIG_X86_64 vmlinux-objs-y += $(obj)/ident_map_64.o vmlinux-objs-y += $(obj)/idt_64.o $(obj)/idt_handlers_64.o - vmlinux-objs-y += $(obj)/mem_encrypt.o + vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/mem_encrypt.o vmlinux-objs-y += $(obj)/pgtable_64.o vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev.o endif @@ -108,11 +113,11 @@ endif vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o vmlinux-objs-$(CONFIG_INTEL_TDX_GUEST) += $(obj)/tdx.o $(obj)/tdcall.o -vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o -efi-obj-$(CONFIG_EFI_STUB) = $(objtree)/drivers/firmware/efi/libstub/lib.a +vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_mixed.o +vmlinux-objs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a -$(obj)/vmlinux: $(vmlinux-objs-y) $(efi-obj-y) FORCE +$(obj)/vmlinux: $(vmlinux-objs-y) FORCE $(call if_changed,ld) OBJCOPYFLAGS_vmlinux.bin := -R .comment -S diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c index 9caf89063e775eb054a857849eb8dd35a0ed9818..55c98fdd67d2b7f599ab333d5f1fa1c517c3e4eb 100644 --- a/arch/x86/boot/compressed/acpi.c +++ b/arch/x86/boot/compressed/acpi.c @@ -30,13 +30,13 @@ __efi_get_rsdp_addr(unsigned long cfg_tbl_pa, unsigned int cfg_tbl_len) * Search EFI system tables for RSDP. Preferred is ACPI_20_TABLE_GUID to * ACPI_TABLE_GUID because it has more features. */ - rsdp_addr = efi_find_vendor_table(boot_params, cfg_tbl_pa, cfg_tbl_len, + rsdp_addr = efi_find_vendor_table(boot_params_ptr, cfg_tbl_pa, cfg_tbl_len, ACPI_20_TABLE_GUID); if (rsdp_addr) return (acpi_physical_address)rsdp_addr; /* No ACPI_20_TABLE_GUID found, fallback to ACPI_TABLE_GUID. */ - rsdp_addr = efi_find_vendor_table(boot_params, cfg_tbl_pa, cfg_tbl_len, + rsdp_addr = efi_find_vendor_table(boot_params_ptr, cfg_tbl_pa, cfg_tbl_len, ACPI_TABLE_GUID); if (rsdp_addr) return (acpi_physical_address)rsdp_addr; @@ -56,15 +56,15 @@ static acpi_physical_address efi_get_rsdp_addr(void) enum efi_type et; int ret; - et = efi_get_type(boot_params); + et = efi_get_type(boot_params_ptr); if (et == EFI_TYPE_NONE) return 0; - systab_pa = efi_get_system_table(boot_params); + systab_pa = efi_get_system_table(boot_params_ptr); if (!systab_pa) error("EFI support advertised, but unable to locate system table."); - ret = efi_get_conf_table(boot_params, &cfg_tbl_pa, &cfg_tbl_len); + ret = efi_get_conf_table(boot_params_ptr, &cfg_tbl_pa, &cfg_tbl_len); if (ret || !cfg_tbl_pa) error("EFI config table not found."); @@ -156,7 +156,7 @@ acpi_physical_address get_rsdp_addr(void) { acpi_physical_address pa; - pa = boot_params->acpi_rsdp_addr; + pa = boot_params_ptr->acpi_rsdp_addr; if (!pa) pa = efi_get_rsdp_addr(); @@ -210,7 +210,7 @@ static unsigned long get_acpi_srat_table(void) rsdp = (struct acpi_table_rsdp *)get_cmdline_acpi_rsdp(); if (!rsdp) rsdp = (struct acpi_table_rsdp *)(long) - boot_params->acpi_rsdp_addr; + boot_params_ptr->acpi_rsdp_addr; if (!rsdp) return 0; diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c index f1add5d85da9d9881e44e2316a2f0018deb364f7..c1bb180973ea2a74eaf7b1788faeeba366643daa 100644 --- a/arch/x86/boot/compressed/cmdline.c +++ b/arch/x86/boot/compressed/cmdline.c @@ -14,9 +14,9 @@ static inline char rdfs8(addr_t addr) #include "../cmdline.c" unsigned long get_cmd_line_ptr(void) { - unsigned long cmd_line_ptr = boot_params->hdr.cmd_line_ptr; + unsigned long cmd_line_ptr = boot_params_ptr->hdr.cmd_line_ptr; - cmd_line_ptr |= (u64)boot_params->ext_cmd_line_ptr << 32; + cmd_line_ptr |= (u64)boot_params_ptr->ext_cmd_line_ptr << 32; return cmd_line_ptr; } diff --git a/arch/x86/boot/compressed/efi_mixed.S b/arch/x86/boot/compressed/efi_mixed.S new file mode 100644 index 0000000000000000000000000000000000000000..fb6d60dcd6ed1f06ee42a98bfcf3b613235c066b --- /dev/null +++ b/arch/x86/boot/compressed/efi_mixed.S @@ -0,0 +1,347 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2014, 2015 Intel Corporation; author Matt Fleming + * + * Early support for invoking 32-bit EFI services from a 64-bit kernel. + * + * Because this thunking occurs before ExitBootServices() we have to + * restore the firmware's 32-bit GDT and IDT before we make EFI service + * calls. + * + * On the plus side, we don't have to worry about mangling 64-bit + * addresses into 32-bits because we're executing with an identity + * mapped pagetable and haven't transitioned to 64-bit virtual addresses + * yet. + */ + +#include +#include +#include +#include +#include +#include +#include + + .code64 + .text +/* + * When booting in 64-bit mode on 32-bit EFI firmware, startup_64_mixed_mode() + * is the first thing that runs after switching to long mode. Depending on + * whether the EFI handover protocol or the compat entry point was used to + * enter the kernel, it will either branch to the common 64-bit EFI stub + * entrypoint efi_stub_entry() directly, or via the 64-bit EFI PE/COFF + * entrypoint efi_pe_entry(). In the former case, the bootloader must provide a + * struct bootparams pointer as the third argument, so the presence of such a + * pointer is used to disambiguate. + * + * +--------------+ + * +------------------+ +------------+ +------>| efi_pe_entry | + * | efi32_pe_entry |---->| | | +-----------+--+ + * +------------------+ | | +------+----------------+ | + * | startup_32 |---->| startup_64_mixed_mode | | + * +------------------+ | | +------+----------------+ | + * | efi32_stub_entry |---->| | | | + * +------------------+ +------------+ | | + * V | + * +------------+ +----------------+ | + * | startup_64 |<----| efi_stub_entry |<--------+ + * +------------+ +----------------+ + */ +SYM_FUNC_START(startup_64_mixed_mode) + lea efi32_boot_args(%rip), %rdx + mov 0(%rdx), %edi + mov 4(%rdx), %esi + + /* Switch to the firmware's stack */ + movl efi32_boot_sp(%rip), %esp + andl $~7, %esp + +#ifdef CONFIG_EFI_HANDOVER_PROTOCOL + mov 8(%rdx), %edx // saved bootparams pointer + test %edx, %edx + jnz efi_stub_entry +#endif + /* + * efi_pe_entry uses MS calling convention, which requires 32 bytes of + * shadow space on the stack even if all arguments are passed in + * registers. We also need an additional 8 bytes for the space that + * would be occupied by the return address, and this also results in + * the correct stack alignment for entry. + */ + sub $40, %rsp + mov %rdi, %rcx // MS calling convention + mov %rsi, %rdx + jmp efi_pe_entry +SYM_FUNC_END(startup_64_mixed_mode) + +SYM_FUNC_START(__efi64_thunk) + push %rbp + push %rbx + + movl %ds, %eax + push %rax + movl %es, %eax + push %rax + movl %ss, %eax + push %rax + + /* Copy args passed on stack */ + movq 0x30(%rsp), %rbp + movq 0x38(%rsp), %rbx + movq 0x40(%rsp), %rax + + /* + * Convert x86-64 ABI params to i386 ABI + */ + subq $64, %rsp + movl %esi, 0x0(%rsp) + movl %edx, 0x4(%rsp) + movl %ecx, 0x8(%rsp) + movl %r8d, 0xc(%rsp) + movl %r9d, 0x10(%rsp) + movl %ebp, 0x14(%rsp) + movl %ebx, 0x18(%rsp) + movl %eax, 0x1c(%rsp) + + leaq 0x20(%rsp), %rbx + sgdt (%rbx) + sidt 16(%rbx) + + leaq 1f(%rip), %rbp + + /* + * Switch to IDT and GDT with 32-bit segments. These are the firmware + * GDT and IDT that were installed when the kernel started executing. + * The pointers were saved by the efi32_entry() routine below. + * + * Pass the saved DS selector to the 32-bit code, and use far return to + * restore the saved CS selector. + */ + lidt efi32_boot_idt(%rip) + lgdt efi32_boot_gdt(%rip) + + movzwl efi32_boot_ds(%rip), %edx + movzwq efi32_boot_cs(%rip), %rax + pushq %rax + leaq efi_enter32(%rip), %rax + pushq %rax + lretq + +1: addq $64, %rsp + movq %rdi, %rax + + pop %rbx + movl %ebx, %ss + pop %rbx + movl %ebx, %es + pop %rbx + movl %ebx, %ds + /* Clear out 32-bit selector from FS and GS */ + xorl %ebx, %ebx + movl %ebx, %fs + movl %ebx, %gs + + /* + * Convert 32-bit status code into 64-bit. + */ + roll $1, %eax + rorq $1, %rax + + pop %rbx + pop %rbp + RET +SYM_FUNC_END(__efi64_thunk) + + .code32 +#ifdef CONFIG_EFI_HANDOVER_PROTOCOL +SYM_FUNC_START(efi32_stub_entry) + call 1f +1: popl %ecx + leal (efi32_boot_args - 1b)(%ecx), %ebx + + /* Clear BSS */ + xorl %eax, %eax + leal (_bss - 1b)(%ecx), %edi + leal (_ebss - 1b)(%ecx), %ecx + subl %edi, %ecx + shrl $2, %ecx + cld + rep stosl + + add $0x4, %esp /* Discard return address */ + popl %ecx + popl %edx + popl %esi + movl %esi, 8(%ebx) + jmp efi32_entry +SYM_FUNC_END(efi32_stub_entry) +#endif + +/* + * EFI service pointer must be in %edi. + * + * The stack should represent the 32-bit calling convention. + */ +SYM_FUNC_START_LOCAL(efi_enter32) + /* Load firmware selector into data and stack segment registers */ + movl %edx, %ds + movl %edx, %es + movl %edx, %fs + movl %edx, %gs + movl %edx, %ss + + /* Reload pgtables */ + movl %cr3, %eax + movl %eax, %cr3 + + /* Disable paging */ + movl %cr0, %eax + btrl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 + + /* Disable long mode via EFER */ + movl $MSR_EFER, %ecx + rdmsr + btrl $_EFER_LME, %eax + wrmsr + + call *%edi + + /* We must preserve return value */ + movl %eax, %edi + + /* + * Some firmware will return with interrupts enabled. Be sure to + * disable them before we switch GDTs and IDTs. + */ + cli + + lidtl 16(%ebx) + lgdtl (%ebx) + + movl %cr4, %eax + btsl $(X86_CR4_PAE_BIT), %eax + movl %eax, %cr4 + + movl %cr3, %eax + movl %eax, %cr3 + + movl $MSR_EFER, %ecx + rdmsr + btsl $_EFER_LME, %eax + wrmsr + + xorl %eax, %eax + lldt %ax + + pushl $__KERNEL_CS + pushl %ebp + + /* Enable paging */ + movl %cr0, %eax + btsl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 + lret +SYM_FUNC_END(efi_enter32) + +/* + * This is the common EFI stub entry point for mixed mode. + * + * Arguments: %ecx image handle + * %edx EFI system table pointer + * + * Since this is the point of no return for ordinary execution, no registers + * are considered live except for the function parameters. [Note that the EFI + * stub may still exit and return to the firmware using the Exit() EFI boot + * service.] + */ +SYM_FUNC_START_LOCAL(efi32_entry) + call 1f +1: pop %ebx + + /* Save firmware GDTR and code/data selectors */ + sgdtl (efi32_boot_gdt - 1b)(%ebx) + movw %cs, (efi32_boot_cs - 1b)(%ebx) + movw %ds, (efi32_boot_ds - 1b)(%ebx) + + /* Store firmware IDT descriptor */ + sidtl (efi32_boot_idt - 1b)(%ebx) + + /* Store firmware stack pointer */ + movl %esp, (efi32_boot_sp - 1b)(%ebx) + + /* Store boot arguments */ + leal (efi32_boot_args - 1b)(%ebx), %ebx + movl %ecx, 0(%ebx) + movl %edx, 4(%ebx) + movb $0x0, 12(%ebx) // efi_is64 + + /* + * Allocate some memory for a temporary struct boot_params, which only + * needs the minimal pieces that startup_32() relies on. + */ + subl $PARAM_SIZE, %esp + movl %esp, %esi + movl $PAGE_SIZE, BP_kernel_alignment(%esi) + movl $_end - 1b, BP_init_size(%esi) + subl $startup_32 - 1b, BP_init_size(%esi) + + /* Disable paging */ + movl %cr0, %eax + btrl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 + + jmp startup_32 +SYM_FUNC_END(efi32_entry) + +/* + * efi_status_t efi32_pe_entry(efi_handle_t image_handle, + * efi_system_table_32_t *sys_table) + */ +SYM_FUNC_START(efi32_pe_entry) + pushl %ebp + movl %esp, %ebp + pushl %ebx // save callee-save registers + pushl %edi + + call verify_cpu // check for long mode support + testl %eax, %eax + movl $0x80000003, %eax // EFI_UNSUPPORTED + jnz 2f + + movl 8(%ebp), %ecx // image_handle + movl 12(%ebp), %edx // sys_table + jmp efi32_entry // pass %ecx, %edx + // no other registers remain live + +2: popl %edi // restore callee-save registers + popl %ebx + leave + RET +SYM_FUNC_END(efi32_pe_entry) + +#ifdef CONFIG_EFI_HANDOVER_PROTOCOL + .org efi32_stub_entry + 0x200 + .code64 +SYM_FUNC_START_NOALIGN(efi64_stub_entry) + jmp efi_handover_entry +SYM_FUNC_END(efi64_stub_entry) +#endif + + .data + .balign 8 +SYM_DATA_START_LOCAL(efi32_boot_gdt) + .word 0 + .quad 0 +SYM_DATA_END(efi32_boot_gdt) + +SYM_DATA_START_LOCAL(efi32_boot_idt) + .word 0 + .quad 0 +SYM_DATA_END(efi32_boot_idt) + +SYM_DATA_LOCAL(efi32_boot_cs, .word 0) +SYM_DATA_LOCAL(efi32_boot_ds, .word 0) +SYM_DATA_LOCAL(efi32_boot_sp, .long 0) +SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0, 0) +SYM_DATA(efi_is64, .byte 1) diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S deleted file mode 100644 index 67e7edcdfea8fa44d036e50bad7921a11ff10b98..0000000000000000000000000000000000000000 --- a/arch/x86/boot/compressed/efi_thunk_64.S +++ /dev/null @@ -1,195 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2014, 2015 Intel Corporation; author Matt Fleming - * - * Early support for invoking 32-bit EFI services from a 64-bit kernel. - * - * Because this thunking occurs before ExitBootServices() we have to - * restore the firmware's 32-bit GDT and IDT before we make EFI service - * calls. - * - * On the plus side, we don't have to worry about mangling 64-bit - * addresses into 32-bits because we're executing with an identity - * mapped pagetable and haven't transitioned to 64-bit virtual addresses - * yet. - */ - -#include -#include -#include -#include -#include - - .code64 - .text -SYM_FUNC_START(__efi64_thunk) - push %rbp - push %rbx - - movl %ds, %eax - push %rax - movl %es, %eax - push %rax - movl %ss, %eax - push %rax - - /* Copy args passed on stack */ - movq 0x30(%rsp), %rbp - movq 0x38(%rsp), %rbx - movq 0x40(%rsp), %rax - - /* - * Convert x86-64 ABI params to i386 ABI - */ - subq $64, %rsp - movl %esi, 0x0(%rsp) - movl %edx, 0x4(%rsp) - movl %ecx, 0x8(%rsp) - movl %r8d, 0xc(%rsp) - movl %r9d, 0x10(%rsp) - movl %ebp, 0x14(%rsp) - movl %ebx, 0x18(%rsp) - movl %eax, 0x1c(%rsp) - - leaq 0x20(%rsp), %rbx - sgdt (%rbx) - - addq $16, %rbx - sidt (%rbx) - - leaq 1f(%rip), %rbp - - /* - * Switch to IDT and GDT with 32-bit segments. This is the firmware GDT - * and IDT that was installed when the kernel started executing. The - * pointers were saved at the EFI stub entry point in head_64.S. - * - * Pass the saved DS selector to the 32-bit code, and use far return to - * restore the saved CS selector. - */ - leaq efi32_boot_idt(%rip), %rax - lidt (%rax) - leaq efi32_boot_gdt(%rip), %rax - lgdt (%rax) - - movzwl efi32_boot_ds(%rip), %edx - movzwq efi32_boot_cs(%rip), %rax - pushq %rax - leaq efi_enter32(%rip), %rax - pushq %rax - lretq - -1: addq $64, %rsp - movq %rdi, %rax - - pop %rbx - movl %ebx, %ss - pop %rbx - movl %ebx, %es - pop %rbx - movl %ebx, %ds - /* Clear out 32-bit selector from FS and GS */ - xorl %ebx, %ebx - movl %ebx, %fs - movl %ebx, %gs - - /* - * Convert 32-bit status code into 64-bit. - */ - roll $1, %eax - rorq $1, %rax - - pop %rbx - pop %rbp - RET -SYM_FUNC_END(__efi64_thunk) - - .code32 -/* - * EFI service pointer must be in %edi. - * - * The stack should represent the 32-bit calling convention. - */ -SYM_FUNC_START_LOCAL(efi_enter32) - /* Load firmware selector into data and stack segment registers */ - movl %edx, %ds - movl %edx, %es - movl %edx, %fs - movl %edx, %gs - movl %edx, %ss - - /* Reload pgtables */ - movl %cr3, %eax - movl %eax, %cr3 - - /* Disable paging */ - movl %cr0, %eax - btrl $X86_CR0_PG_BIT, %eax - movl %eax, %cr0 - - /* Disable long mode via EFER */ - movl $MSR_EFER, %ecx - rdmsr - btrl $_EFER_LME, %eax - wrmsr - - call *%edi - - /* We must preserve return value */ - movl %eax, %edi - - /* - * Some firmware will return with interrupts enabled. Be sure to - * disable them before we switch GDTs and IDTs. - */ - cli - - lidtl (%ebx) - subl $16, %ebx - - lgdtl (%ebx) - - movl %cr4, %eax - btsl $(X86_CR4_PAE_BIT), %eax - movl %eax, %cr4 - - movl %cr3, %eax - movl %eax, %cr3 - - movl $MSR_EFER, %ecx - rdmsr - btsl $_EFER_LME, %eax - wrmsr - - xorl %eax, %eax - lldt %ax - - pushl $__KERNEL_CS - pushl %ebp - - /* Enable paging */ - movl %cr0, %eax - btsl $X86_CR0_PG_BIT, %eax - movl %eax, %cr0 - lret -SYM_FUNC_END(efi_enter32) - - .data - .balign 8 -SYM_DATA_START(efi32_boot_gdt) - .word 0 - .quad 0 -SYM_DATA_END(efi32_boot_gdt) - -SYM_DATA_START(efi32_boot_idt) - .word 0 - .quad 0 -SYM_DATA_END(efi32_boot_idt) - -SYM_DATA_START(efi32_boot_cs) - .word 0 -SYM_DATA_END(efi32_boot_cs) - -SYM_DATA_START(efi32_boot_ds) - .word 0 -SYM_DATA_END(efi32_boot_ds) diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 3b354eb9516df416e8e2a595044c016fabf6f98f..1cfe9802a42fe5704e0a74ce205a3d6bce3f9418 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -84,19 +84,6 @@ SYM_FUNC_START(startup_32) #ifdef CONFIG_RELOCATABLE leal startup_32@GOTOFF(%edx), %ebx - -#ifdef CONFIG_EFI_STUB -/* - * If we were loaded via the EFI LoadImage service, startup_32() will be at an - * offset to the start of the space allocated for the image. efi_pe_entry() will - * set up image_offset to tell us where the image actually starts, so that we - * can use the full available buffer. - * image_offset = startup_32 - image_base - * Otherwise image_offset will be zero and has no effect on the calculations. - */ - subl image_offset@GOTOFF(%edx), %ebx -#endif - movl BP_kernel_alignment(%esi), %eax decl %eax addl %eax, %ebx @@ -150,17 +137,6 @@ SYM_FUNC_START(startup_32) jmp *%eax SYM_FUNC_END(startup_32) -#ifdef CONFIG_EFI_STUB -SYM_FUNC_START(efi32_stub_entry) - add $0x4, %esp - movl 8(%esp), %esi /* save boot_params pointer */ - call efi_main - /* efi_main returns the possibly relocated address of startup_32 */ - jmp *%eax -SYM_FUNC_END(efi32_stub_entry) -SYM_FUNC_ALIAS(efi_stub_entry, efi32_stub_entry) -#endif - .text SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) @@ -179,15 +155,9 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) */ /* push arguments for extract_kernel: */ - pushl output_len@GOTOFF(%ebx) /* decompressed length, end of relocs */ pushl %ebp /* output address */ - pushl input_len@GOTOFF(%ebx) /* input_len */ - leal input_data@GOTOFF(%ebx), %eax - pushl %eax /* input_data */ - leal boot_heap@GOTOFF(%ebx), %eax - pushl %eax /* heap area */ pushl %esi /* real mode pointer */ - call extract_kernel /* returns kernel location in %eax */ + call extract_kernel /* returns kernel entry point in %eax */ addl $24, %esp /* @@ -208,17 +178,11 @@ SYM_DATA_START_LOCAL(gdt) .quad 0x00cf92000000ffff /* __KERNEL_DS */ SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end) -#ifdef CONFIG_EFI_STUB -SYM_DATA(image_offset, .long 0) -#endif - /* * Stack and heap for uncompression */ .bss .balign 4 -boot_heap: - .fill BOOT_HEAP_SIZE, 1, 0 boot_stack: .fill BOOT_STACK_SIZE, 1, 0 boot_stack_end: diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index b4bd6df29116f379003ba34d3fbfdb221f75a9ba..0d7aef10b19ad9c4179733ee49f8359d326212b4 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -118,7 +118,9 @@ SYM_FUNC_START(startup_32) 1: /* Setup Exception handling for SEV-ES */ +#ifdef CONFIG_AMD_MEM_ENCRYPT call startup32_load_idt +#endif /* Make sure cpu supports long mode. */ call verify_cpu @@ -136,19 +138,6 @@ SYM_FUNC_START(startup_32) #ifdef CONFIG_RELOCATABLE movl %ebp, %ebx - -#ifdef CONFIG_EFI_STUB -/* - * If we were loaded via the EFI LoadImage service, startup_32 will be at an - * offset to the start of the space allocated for the image. efi_pe_entry will - * set up image_offset to tell us where the image actually starts, so that we - * can use the full available buffer. - * image_offset = startup_32 - image_base - * Otherwise image_offset will be zero and has no effect on the calculations. - */ - subl rva(image_offset)(%ebp), %ebx -#endif - movl BP_kernel_alignment(%esi), %eax decl %eax addl %eax, %ebx @@ -178,12 +167,13 @@ SYM_FUNC_START(startup_32) */ /* * If SEV is active then set the encryption mask in the page tables. - * This will insure that when the kernel is copied and decompressed + * This will ensure that when the kernel is copied and decompressed * it will be done so encrypted. */ - call get_sev_encryption_bit xorl %edx, %edx #ifdef CONFIG_AMD_MEM_ENCRYPT + call get_sev_encryption_bit + xorl %edx, %edx testl %eax, %eax jz 1f subl $32, %eax /* Encryption bit is always above bit 31 */ @@ -249,6 +239,11 @@ SYM_FUNC_START(startup_32) movl $__BOOT_TSS, %eax ltr %ax +#ifdef CONFIG_AMD_MEM_ENCRYPT + /* Check if the C-bit position is correct when SEV is active */ + call startup32_check_sev_cbit +#endif + /* * Setup for the jump to 64bit mode * @@ -261,29 +256,11 @@ SYM_FUNC_START(startup_32) */ leal rva(startup_64)(%ebp), %eax #ifdef CONFIG_EFI_MIXED - movl rva(efi32_boot_args)(%ebp), %edi - testl %edi, %edi - jz 1f - leal rva(efi64_stub_entry)(%ebp), %eax - movl rva(efi32_boot_args+4)(%ebp), %esi - movl rva(efi32_boot_args+8)(%ebp), %edx // saved bootparams pointer - testl %edx, %edx - jnz 1f - /* - * efi_pe_entry uses MS calling convention, which requires 32 bytes of - * shadow space on the stack even if all arguments are passed in - * registers. We also need an additional 8 bytes for the space that - * would be occupied by the return address, and this also results in - * the correct stack alignment for entry. - */ - subl $40, %esp - leal rva(efi_pe_entry)(%ebp), %eax - movl %edi, %ecx // MS calling convention - movl %esi, %edx + cmpb $1, rva(efi_is64)(%ebp) + je 1f + leal rva(startup_64_mixed_mode)(%ebp), %eax 1: #endif - /* Check if the C-bit position is correct when SEV is active */ - call startup32_check_sev_cbit pushl $__KERNEL_CS pushl %eax @@ -296,41 +273,6 @@ SYM_FUNC_START(startup_32) lret SYM_FUNC_END(startup_32) -#ifdef CONFIG_EFI_MIXED - .org 0x190 -SYM_FUNC_START(efi32_stub_entry) - add $0x4, %esp /* Discard return address */ - popl %ecx - popl %edx - popl %esi - - call 1f -1: pop %ebp - subl $ rva(1b), %ebp - - movl %esi, rva(efi32_boot_args+8)(%ebp) -SYM_INNER_LABEL(efi32_pe_stub_entry, SYM_L_LOCAL) - movl %ecx, rva(efi32_boot_args)(%ebp) - movl %edx, rva(efi32_boot_args+4)(%ebp) - movb $0, rva(efi_is64)(%ebp) - - /* Save firmware GDTR and code/data selectors */ - sgdtl rva(efi32_boot_gdt)(%ebp) - movw %cs, rva(efi32_boot_cs)(%ebp) - movw %ds, rva(efi32_boot_ds)(%ebp) - - /* Store firmware IDT descriptor */ - sidtl rva(efi32_boot_idt)(%ebp) - - /* Disable paging */ - movl %cr0, %eax - btrl $X86_CR0_PG_BIT, %eax - movl %eax, %cr0 - - jmp startup_32 -SYM_FUNC_END(efi32_stub_entry) -#endif - .code64 .org 0x200 SYM_CODE_START(startup_64) @@ -372,20 +314,6 @@ SYM_CODE_START(startup_64) /* Start with the delta to where the kernel will run at. */ #ifdef CONFIG_RELOCATABLE leaq startup_32(%rip) /* - $startup_32 */, %rbp - -#ifdef CONFIG_EFI_STUB -/* - * If we were loaded via the EFI LoadImage service, startup_32 will be at an - * offset to the start of the space allocated for the image. efi_pe_entry will - * set up image_offset to tell us where the image actually starts, so that we - * can use the full available buffer. - * image_offset = startup_32 - image_base - * Otherwise image_offset will be zero and has no effect on the calculations. - */ - movl image_offset(%rip), %eax - subq %rax, %rbp -#endif - movl BP_kernel_alignment(%rsi), %eax decl %eax addq %rax, %rbp @@ -424,10 +352,6 @@ SYM_CODE_START(startup_64) * For the trampoline, we need the top page table to reside in lower * memory as we don't have a way to load 64-bit values into CR3 in * 32-bit mode. - * - * We go though the trampoline even if we don't have to: if we're - * already in a desired paging mode. This way the trampoline code gets - * tested on every boot. */ /* Make sure we have GDT with 32-bit code segment */ @@ -442,10 +366,14 @@ SYM_CODE_START(startup_64) lretq .Lon_kernel_cs: + /* + * RSI holds a pointer to a boot_params structure provided by the + * loader, and this needs to be preserved across C function calls. So + * move it into a callee saved register. + */ + movq %rsi, %r15 - pushq %rsi call load_stage1_idt - popq %rsi #ifdef CONFIG_AMD_MEM_ENCRYPT /* @@ -456,82 +384,24 @@ SYM_CODE_START(startup_64) * CPUID instructions being issued, so go ahead and do that now via * sev_enable(), which will also handle the rest of the SEV-related * detection/setup to ensure that has been done in advance of any dependent - * code. + * code. Pass the boot_params pointer as the first argument. */ - pushq %rsi - movq %rsi, %rdi /* real mode address */ + movq %r15, %rdi call sev_enable - popq %rsi #endif /* - * paging_prepare() sets up the trampoline and checks if we need to - * enable 5-level paging. - * - * paging_prepare() returns a two-quadword structure which lands - * into RDX:RAX: - * - Address of the trampoline is returned in RAX. - * - Non zero RDX means trampoline needs to enable 5-level - * paging. - * - * RSI holds real mode data and needs to be preserved across - * this function call. - */ - pushq %rsi - movq %rsi, %rdi /* real mode address */ - call paging_prepare - popq %rsi - - /* Save the trampoline address in RCX */ - movq %rax, %rcx - - /* Set up 32-bit addressable stack */ - leaq TRAMPOLINE_32BIT_STACK_END(%rcx), %rsp - - /* - * Preserve live 64-bit registers on the stack: this is necessary - * because the architecture does not guarantee that GPRs will retain - * their full 64-bit values across a 32-bit mode switch. - */ - pushq %rbp - pushq %rbx - pushq %rsi - - /* - * Push the 64-bit address of trampoline_return() onto the new stack. - * It will be used by the trampoline to return to the main code. Due to - * the 32-bit mode switch, it cannot be kept it in a register either. - */ - leaq trampoline_return(%rip), %rdi - pushq %rdi - - /* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */ - pushq $__KERNEL32_CS - leaq TRAMPOLINE_32BIT_CODE_OFFSET(%rax), %rax - pushq %rax - lretq -trampoline_return: - /* Restore live 64-bit registers */ - popq %rsi - popq %rbx - popq %rbp - - /* Restore the stack, the 32-bit trampoline uses its own stack */ - leaq rva(boot_stack_end)(%rbx), %rsp - - /* - * cleanup_trampoline() would restore trampoline memory. - * - * RDI is address of the page table to use instead of page table - * in trampoline memory (if required). + * configure_5level_paging() updates the number of paging levels using + * a trampoline in 32-bit addressable memory if the current number does + * not match the desired number. * - * RSI holds real mode data and needs to be preserved across - * this function call. + * Pass the boot_params pointer as the first argument. The second + * argument is the relocated address of the page table to use instead + * of the page table in trampoline memory (if required). */ - pushq %rsi - leaq rva(top_pgtable)(%rbx), %rdi - call cleanup_trampoline - popq %rsi + movq %r15, %rdi + leaq rva(top_pgtable)(%rbx), %rsi + call configure_5level_paging /* Zero EFLAGS */ pushq $0 @@ -541,7 +411,6 @@ trampoline_return: * Copy the compressed kernel to the end of our buffer * where decompression in place becomes safe. */ - pushq %rsi leaq (_bss-8)(%rip), %rsi leaq rva(_bss-8)(%rbx), %rdi movl $(_bss - startup_32), %ecx @@ -549,7 +418,6 @@ trampoline_return: std rep movsq cld - popq %rsi /* * The GDT may get overwritten either during the copy we just did or @@ -568,19 +436,6 @@ trampoline_return: jmp *%rax SYM_CODE_END(startup_64) -#ifdef CONFIG_EFI_STUB - .org 0x390 -SYM_FUNC_START(efi64_stub_entry) - and $~0xf, %rsp /* realign the stack */ - movq %rdx, %rbx /* save boot_params pointer */ - call efi_main - movq %rbx,%rsi - leaq rva(startup_64)(%rax), %rax - jmp *%rax -SYM_FUNC_END(efi64_stub_entry) -SYM_FUNC_ALIAS(efi_stub_entry, efi64_stub_entry) -#endif - .text SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) @@ -594,125 +449,122 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) shrq $3, %rcx rep stosq - pushq %rsi call load_stage2_idt /* Pass boot_params to initialize_identity_maps() */ - movq (%rsp), %rdi + movq %r15, %rdi call initialize_identity_maps - popq %rsi /* * Do the extraction, and jump to the new kernel.. */ - pushq %rsi /* Save the real mode argument */ - movq %rsi, %rdi /* real mode address */ - leaq boot_heap(%rip), %rsi /* malloc area for uncompression */ - leaq input_data(%rip), %rdx /* input_data */ - movl input_len(%rip), %ecx /* input_len */ - movq %rbp, %r8 /* output target address */ - movl output_len(%rip), %r9d /* decompressed length, end of relocs */ - call extract_kernel /* returns kernel location in %rax */ - popq %rsi + /* pass struct boot_params pointer and output target address */ + movq %r15, %rdi + movq %rbp, %rsi + call extract_kernel /* returns kernel entry point in %rax */ /* * Jump to the decompressed kernel. */ + movq %r15, %rsi jmp *%rax SYM_FUNC_END(.Lrelocated) - .code32 /* - * This is the 32-bit trampoline that will be copied over to low memory. + * This is the 32-bit trampoline that will be copied over to low memory. It + * will be called using the ordinary 64-bit calling convention from code + * running in 64-bit mode. * * Return address is at the top of the stack (might be above 4G). - * ECX contains the base address of the trampoline memory. - * Non zero RDX means trampoline needs to enable 5-level paging. + * The first argument (EDI) contains the address of the temporary PGD level + * page table in 32-bit addressable memory which will be programmed into + * register CR3. */ + .section ".rodata", "a", @progbits SYM_CODE_START(trampoline_32bit_src) - /* Set up data and stack segments */ - movl $__KERNEL_DS, %eax - movl %eax, %ds - movl %eax, %ss + /* + * Preserve callee save 64-bit registers on the stack: this is + * necessary because the architecture does not guarantee that GPRs will + * retain their full 64-bit values across a 32-bit mode switch. + */ + pushq %r15 + pushq %r14 + pushq %r13 + pushq %r12 + pushq %rbp + pushq %rbx + + /* Preserve top half of RSP in a legacy mode GPR to avoid truncation */ + movq %rsp, %rbx + shrq $32, %rbx + /* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */ + pushq $__KERNEL32_CS + leaq 0f(%rip), %rax + pushq %rax + lretq + + /* + * The 32-bit code below will do a far jump back to long mode and end + * up here after reconfiguring the number of paging levels. First, the + * stack pointer needs to be restored to its full 64-bit value before + * the callee save register contents can be popped from the stack. + */ +.Lret: + shlq $32, %rbx + orq %rbx, %rsp + + /* Restore the preserved 64-bit registers */ + popq %rbx + popq %rbp + popq %r12 + popq %r13 + popq %r14 + popq %r15 + retq + + .code32 +0: /* Disable paging */ movl %cr0, %eax btrl $X86_CR0_PG_BIT, %eax movl %eax, %cr0 - /* Check what paging mode we want to be in after the trampoline */ - testl %edx, %edx - jz 1f - - /* We want 5-level paging: don't touch CR3 if it already points to 5-level page tables */ - movl %cr4, %eax - testl $X86_CR4_LA57, %eax - jnz 3f - jmp 2f -1: - /* We want 4-level paging: don't touch CR3 if it already points to 4-level page tables */ - movl %cr4, %eax - testl $X86_CR4_LA57, %eax - jz 3f -2: /* Point CR3 to the trampoline's new top level page table */ - leal TRAMPOLINE_32BIT_PGTABLE_OFFSET(%ecx), %eax - movl %eax, %cr3 -3: + movl %edi, %cr3 + /* Set EFER.LME=1 as a precaution in case hypervsior pulls the rug */ - pushl %ecx - pushl %edx movl $MSR_EFER, %ecx rdmsr btsl $_EFER_LME, %eax /* Avoid writing EFER if no change was made (for TDX guest) */ jc 1f wrmsr -1: popl %edx - popl %ecx - -#ifdef CONFIG_X86_MCE - /* - * Preserve CR4.MCE if the kernel will enable #MC support. - * Clearing MCE may fault in some environments (that also force #MC - * support). Any machine check that occurs before #MC support is fully - * configured will crash the system regardless of the CR4.MCE value set - * here. - */ - movl %cr4, %eax - andl $X86_CR4_MCE, %eax -#else - movl $0, %eax -#endif - - /* Enable PAE and LA57 (if required) paging modes */ - orl $X86_CR4_PAE, %eax - testl %edx, %edx - jz 1f - orl $X86_CR4_LA57, %eax 1: + /* Toggle CR4.LA57 */ + movl %cr4, %eax + btcl $X86_CR4_LA57_BIT, %eax movl %eax, %cr4 - /* Calculate address of paging_enabled() once we are executing in the trampoline */ - leal .Lpaging_enabled - trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_OFFSET(%ecx), %eax - - /* Prepare the stack for far return to Long Mode */ - pushl $__KERNEL_CS - pushl %eax - /* Enable paging again. */ movl %cr0, %eax btsl $X86_CR0_PG_BIT, %eax movl %eax, %cr0 - lret + /* + * Return to the 64-bit calling code using LJMP rather than LRET, to + * avoid the need for a 32-bit addressable stack. The destination + * address will be adjusted after the template code is copied into a + * 32-bit addressable buffer. + */ +.Ljmp: ljmpl $__KERNEL_CS, $(.Lret - trampoline_32bit_src) SYM_CODE_END(trampoline_32bit_src) - .code64 -SYM_FUNC_START_LOCAL_NOALIGN(.Lpaging_enabled) - /* Return from the trampoline */ - retq -SYM_FUNC_END(.Lpaging_enabled) +/* + * This symbol is placed right after trampoline_32bit_src() so its address can + * be used to infer the size of the trampoline code. + */ +SYM_DATA(trampoline_ljmp_imm_offset, .word .Ljmp + 1 - trampoline_32bit_src) /* * The trampoline code has a size limit. @@ -721,7 +573,7 @@ SYM_FUNC_END(.Lpaging_enabled) */ .org trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_SIZE - .code32 + .text SYM_FUNC_START_LOCAL_NOALIGN(.Lno_longmode) /* This isn't an x86-64 CPU, so hang intentionally, we cannot continue */ 1: @@ -729,6 +581,7 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lno_longmode) jmp 1b SYM_FUNC_END(.Lno_longmode) + .globl verify_cpu #include "../../kernel/verify_cpu.S" .data @@ -760,249 +613,11 @@ SYM_DATA_START(boot_idt) .endr SYM_DATA_END_LABEL(boot_idt, SYM_L_GLOBAL, boot_idt_end) -#ifdef CONFIG_AMD_MEM_ENCRYPT -SYM_DATA_START(boot32_idt_desc) - .word boot32_idt_end - boot32_idt - 1 - .long 0 -SYM_DATA_END(boot32_idt_desc) - .balign 8 -SYM_DATA_START(boot32_idt) - .rept 32 - .quad 0 - .endr -SYM_DATA_END_LABEL(boot32_idt, SYM_L_GLOBAL, boot32_idt_end) -#endif - -#ifdef CONFIG_EFI_STUB -SYM_DATA(image_offset, .long 0) -#endif -#ifdef CONFIG_EFI_MIXED -SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0, 0) -SYM_DATA(efi_is64, .byte 1) - -#define ST32_boottime 60 // offsetof(efi_system_table_32_t, boottime) -#define BS32_handle_protocol 88 // offsetof(efi_boot_services_32_t, handle_protocol) -#define LI32_image_base 32 // offsetof(efi_loaded_image_32_t, image_base) - - __HEAD - .code32 -SYM_FUNC_START(efi32_pe_entry) -/* - * efi_status_t efi32_pe_entry(efi_handle_t image_handle, - * efi_system_table_32_t *sys_table) - */ - - pushl %ebp - movl %esp, %ebp - pushl %eax // dummy push to allocate loaded_image - - pushl %ebx // save callee-save registers - pushl %edi - - call verify_cpu // check for long mode support - testl %eax, %eax - movl $0x80000003, %eax // EFI_UNSUPPORTED - jnz 2f - - call 1f -1: pop %ebx - subl $ rva(1b), %ebx - - /* Get the loaded image protocol pointer from the image handle */ - leal -4(%ebp), %eax - pushl %eax // &loaded_image - leal rva(loaded_image_proto)(%ebx), %eax - pushl %eax // pass the GUID address - pushl 8(%ebp) // pass the image handle - - /* - * Note the alignment of the stack frame. - * sys_table - * handle <-- 16-byte aligned on entry by ABI - * return address - * frame pointer - * loaded_image <-- local variable - * saved %ebx <-- 16-byte aligned here - * saved %edi - * &loaded_image - * &loaded_image_proto - * handle <-- 16-byte aligned for call to handle_protocol - */ - - movl 12(%ebp), %eax // sys_table - movl ST32_boottime(%eax), %eax // sys_table->boottime - call *BS32_handle_protocol(%eax) // sys_table->boottime->handle_protocol - addl $12, %esp // restore argument space - testl %eax, %eax - jnz 2f - - movl 8(%ebp), %ecx // image_handle - movl 12(%ebp), %edx // sys_table - movl -4(%ebp), %esi // loaded_image - movl LI32_image_base(%esi), %esi // loaded_image->image_base - movl %ebx, %ebp // startup_32 for efi32_pe_stub_entry - /* - * We need to set the image_offset variable here since startup_32() will - * use it before we get to the 64-bit efi_pe_entry() in C code. - */ - subl %esi, %ebx - movl %ebx, rva(image_offset)(%ebp) // save image_offset - jmp efi32_pe_stub_entry - -2: popl %edi // restore callee-save registers - popl %ebx - leave - RET -SYM_FUNC_END(efi32_pe_entry) - - .section ".rodata" - /* EFI loaded image protocol GUID */ - .balign 4 -SYM_DATA_START_LOCAL(loaded_image_proto) - .long 0x5b1b31a1 - .word 0x9562, 0x11d2 - .byte 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b -SYM_DATA_END(loaded_image_proto) -#endif - -#ifdef CONFIG_AMD_MEM_ENCRYPT - __HEAD - .code32 -/* - * Write an IDT entry into boot32_idt - * - * Parameters: - * - * %eax: Handler address - * %edx: Vector number - * - * Physical offset is expected in %ebp - */ -SYM_FUNC_START(startup32_set_idt_entry) - push %ebx - push %ecx - - /* IDT entry address to %ebx */ - leal rva(boot32_idt)(%ebp), %ebx - shl $3, %edx - addl %edx, %ebx - - /* Build IDT entry, lower 4 bytes */ - movl %eax, %edx - andl $0x0000ffff, %edx # Target code segment offset [15:0] - movl $__KERNEL32_CS, %ecx # Target code segment selector - shl $16, %ecx - orl %ecx, %edx - - /* Store lower 4 bytes to IDT */ - movl %edx, (%ebx) - - /* Build IDT entry, upper 4 bytes */ - movl %eax, %edx - andl $0xffff0000, %edx # Target code segment offset [31:16] - orl $0x00008e00, %edx # Present, Type 32-bit Interrupt Gate - - /* Store upper 4 bytes to IDT */ - movl %edx, 4(%ebx) - - pop %ecx - pop %ebx - RET -SYM_FUNC_END(startup32_set_idt_entry) -#endif - -SYM_FUNC_START(startup32_load_idt) -#ifdef CONFIG_AMD_MEM_ENCRYPT - /* #VC handler */ - leal rva(startup32_vc_handler)(%ebp), %eax - movl $X86_TRAP_VC, %edx - call startup32_set_idt_entry - - /* Load IDT */ - leal rva(boot32_idt)(%ebp), %eax - movl %eax, rva(boot32_idt_desc+2)(%ebp) - lidt rva(boot32_idt_desc)(%ebp) -#endif - RET -SYM_FUNC_END(startup32_load_idt) - -/* - * Check for the correct C-bit position when the startup_32 boot-path is used. - * - * The check makes use of the fact that all memory is encrypted when paging is - * disabled. The function creates 64 bits of random data using the RDRAND - * instruction. RDRAND is mandatory for SEV guests, so always available. If the - * hypervisor violates that the kernel will crash right here. - * - * The 64 bits of random data are stored to a memory location and at the same - * time kept in the %eax and %ebx registers. Since encryption is always active - * when paging is off the random data will be stored encrypted in main memory. - * - * Then paging is enabled. When the C-bit position is correct all memory is - * still mapped encrypted and comparing the register values with memory will - * succeed. An incorrect C-bit position will map all memory unencrypted, so that - * the compare will use the encrypted random data and fail. - */ -SYM_FUNC_START(startup32_check_sev_cbit) -#ifdef CONFIG_AMD_MEM_ENCRYPT - pushl %eax - pushl %ebx - pushl %ecx - pushl %edx - - /* Check for non-zero sev_status */ - movl rva(sev_status)(%ebp), %eax - testl %eax, %eax - jz 4f - - /* - * Get two 32-bit random values - Don't bail out if RDRAND fails - * because it is better to prevent forward progress if no random value - * can be gathered. - */ -1: rdrand %eax - jnc 1b -2: rdrand %ebx - jnc 2b - - /* Store to memory and keep it in the registers */ - movl %eax, rva(sev_check_data)(%ebp) - movl %ebx, rva(sev_check_data+4)(%ebp) - - /* Enable paging to see if encryption is active */ - movl %cr0, %edx /* Backup %cr0 in %edx */ - movl $(X86_CR0_PG | X86_CR0_PE), %ecx /* Enable Paging and Protected mode */ - movl %ecx, %cr0 - - cmpl %eax, rva(sev_check_data)(%ebp) - jne 3f - cmpl %ebx, rva(sev_check_data+4)(%ebp) - jne 3f - - movl %edx, %cr0 /* Restore previous %cr0 */ - - jmp 4f - -3: /* Check failed - hlt the machine */ - hlt - jmp 3b - -4: - popl %edx - popl %ecx - popl %ebx - popl %eax -#endif - RET -SYM_FUNC_END(startup32_check_sev_cbit) - /* * Stack and heap for uncompression */ .bss .balign 4 -SYM_DATA_LOCAL(boot_heap, .fill BOOT_HEAP_SIZE, 1, 0) - SYM_DATA_START_LOCAL(boot_stack) .fill BOOT_STACK_SIZE, 1, 0 .balign 16 diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index d34222816c9f5b1f0cc6a32e722c58f40dace567..b8c42339bc355bfad1c09a7b31519e0d581287ac 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -167,8 +167,9 @@ void initialize_identity_maps(void *rmode) * or does not touch all the pages covering them. */ kernel_add_identity_map((unsigned long)_head, (unsigned long)_end); - boot_params = rmode; - kernel_add_identity_map((unsigned long)boot_params, (unsigned long)(boot_params + 1)); + boot_params_ptr = rmode; + kernel_add_identity_map((unsigned long)boot_params_ptr, + (unsigned long)(boot_params_ptr + 1)); cmdline = get_cmd_line_ptr(); kernel_add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE); @@ -176,7 +177,7 @@ void initialize_identity_maps(void *rmode) * Also map the setup_data entries passed via boot_params in case they * need to be accessed by uncompressed kernel via the identity mapping. */ - sd = (struct setup_data *)boot_params->hdr.setup_data; + sd = (struct setup_data *)boot_params_ptr->hdr.setup_data; while (sd) { unsigned long sd_addr = (unsigned long)sd; diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index e476bcbd9b422f6e2a980b59ac59d4e0cb30ce0d..9794d9174795d34927f7b92b00a967fa4243e8cd 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -63,7 +63,7 @@ static unsigned long get_boot_seed(void) unsigned long hash = 0; hash = rotate_xor(hash, build_str, sizeof(build_str)); - hash = rotate_xor(hash, boot_params, sizeof(*boot_params)); + hash = rotate_xor(hash, boot_params_ptr, sizeof(*boot_params_ptr)); return hash; } @@ -383,7 +383,7 @@ static void handle_mem_options(void) static void mem_avoid_init(unsigned long input, unsigned long input_size, unsigned long output) { - unsigned long init_size = boot_params->hdr.init_size; + unsigned long init_size = boot_params_ptr->hdr.init_size; u64 initrd_start, initrd_size; unsigned long cmd_line, cmd_line_size; @@ -395,10 +395,10 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, mem_avoid[MEM_AVOID_ZO_RANGE].size = (output + init_size) - input; /* Avoid initrd. */ - initrd_start = (u64)boot_params->ext_ramdisk_image << 32; - initrd_start |= boot_params->hdr.ramdisk_image; - initrd_size = (u64)boot_params->ext_ramdisk_size << 32; - initrd_size |= boot_params->hdr.ramdisk_size; + initrd_start = (u64)boot_params_ptr->ext_ramdisk_image << 32; + initrd_start |= boot_params_ptr->hdr.ramdisk_image; + initrd_size = (u64)boot_params_ptr->ext_ramdisk_size << 32; + initrd_size |= boot_params_ptr->hdr.ramdisk_size; mem_avoid[MEM_AVOID_INITRD].start = initrd_start; mem_avoid[MEM_AVOID_INITRD].size = initrd_size; /* No need to set mapping for initrd, it will be handled in VO. */ @@ -413,8 +413,8 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, } /* Avoid boot parameters. */ - mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params; - mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params); + mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params_ptr; + mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params_ptr); /* We don't need to set a mapping for setup_data. */ @@ -447,7 +447,7 @@ static bool mem_avoid_overlap(struct mem_vector *img, } /* Avoid all entries in the setup_data linked list. */ - ptr = (struct setup_data *)(unsigned long)boot_params->hdr.setup_data; + ptr = (struct setup_data *)(unsigned long)boot_params_ptr->hdr.setup_data; while (ptr) { struct mem_vector avoid; @@ -679,7 +679,7 @@ static bool process_mem_region(struct mem_vector *region, static bool process_efi_entries(unsigned long minimum, unsigned long image_size) { - struct efi_info *e = &boot_params->efi_info; + struct efi_info *e = &boot_params_ptr->efi_info; bool efi_mirror_found = false; struct mem_vector region; efi_memory_desc_t *md; @@ -761,8 +761,8 @@ static void process_e820_entries(unsigned long minimum, struct boot_e820_entry *entry; /* Verify potential e820 positions, appending to slots list. */ - for (i = 0; i < boot_params->e820_entries; i++) { - entry = &boot_params->e820_table[i]; + for (i = 0; i < boot_params_ptr->e820_entries; i++) { + entry = &boot_params_ptr->e820_table[i]; /* Skip non-RAM entries. */ if (entry->type != E820_TYPE_RAM) continue; @@ -836,7 +836,7 @@ void choose_random_location(unsigned long input, return; } - boot_params->hdr.loadflags |= KASLR_FLAG; + boot_params_ptr->hdr.loadflags |= KASLR_FLAG; if (IS_ENABLED(CONFIG_X86_32)) mem_limit = KERNEL_IMAGE_SIZE; diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S index a73e4d783cae20b6786969c1505ac3bca32bedd7..32f7cc8a862547e426f998e14b1e3125263a408d 100644 --- a/arch/x86/boot/compressed/mem_encrypt.S +++ b/arch/x86/boot/compressed/mem_encrypt.S @@ -12,16 +12,13 @@ #include #include #include +#include +#include .text .code32 SYM_FUNC_START(get_sev_encryption_bit) - xor %eax, %eax - -#ifdef CONFIG_AMD_MEM_ENCRYPT push %ebx - push %ecx - push %edx movl $0x80000000, %eax /* CPUID to check the highest leaf */ cpuid @@ -52,12 +49,7 @@ SYM_FUNC_START(get_sev_encryption_bit) xor %eax, %eax .Lsev_exit: - pop %edx - pop %ecx pop %ebx - -#endif /* CONFIG_AMD_MEM_ENCRYPT */ - RET SYM_FUNC_END(get_sev_encryption_bit) @@ -98,7 +90,7 @@ SYM_CODE_START_LOCAL(sev_es_req_cpuid) jmp 1b SYM_CODE_END(sev_es_req_cpuid) -SYM_CODE_START(startup32_vc_handler) +SYM_CODE_START_LOCAL(startup32_vc_handler) pushl %eax pushl %ebx pushl %ecx @@ -184,15 +176,149 @@ SYM_CODE_START(startup32_vc_handler) jmp .Lfail SYM_CODE_END(startup32_vc_handler) +/* + * Write an IDT entry into boot32_idt + * + * Parameters: + * + * %eax: Handler address + * %edx: Vector number + * %ecx: IDT address + */ +SYM_FUNC_START_LOCAL(startup32_set_idt_entry) + /* IDT entry address to %ecx */ + leal (%ecx, %edx, 8), %ecx + + /* Build IDT entry, lower 4 bytes */ + movl %eax, %edx + andl $0x0000ffff, %edx # Target code segment offset [15:0] + orl $(__KERNEL32_CS << 16), %edx # Target code segment selector + + /* Store lower 4 bytes to IDT */ + movl %edx, (%ecx) + + /* Build IDT entry, upper 4 bytes */ + movl %eax, %edx + andl $0xffff0000, %edx # Target code segment offset [31:16] + orl $0x00008e00, %edx # Present, Type 32-bit Interrupt Gate + + /* Store upper 4 bytes to IDT */ + movl %edx, 4(%ecx) + + RET +SYM_FUNC_END(startup32_set_idt_entry) + +SYM_FUNC_START(startup32_load_idt) + push %ebp + push %ebx + + call 1f +1: pop %ebp + + leal (boot32_idt - 1b)(%ebp), %ebx + + /* #VC handler */ + leal (startup32_vc_handler - 1b)(%ebp), %eax + movl $X86_TRAP_VC, %edx + movl %ebx, %ecx + call startup32_set_idt_entry + + /* Load IDT */ + leal (boot32_idt_desc - 1b)(%ebp), %ecx + movl %ebx, 2(%ecx) + lidt (%ecx) + + pop %ebx + pop %ebp + RET +SYM_FUNC_END(startup32_load_idt) + +/* + * Check for the correct C-bit position when the startup_32 boot-path is used. + * + * The check makes use of the fact that all memory is encrypted when paging is + * disabled. The function creates 64 bits of random data using the RDRAND + * instruction. RDRAND is mandatory for SEV guests, so always available. If the + * hypervisor violates that the kernel will crash right here. + * + * The 64 bits of random data are stored to a memory location and at the same + * time kept in the %eax and %ebx registers. Since encryption is always active + * when paging is off the random data will be stored encrypted in main memory. + * + * Then paging is enabled. When the C-bit position is correct all memory is + * still mapped encrypted and comparing the register values with memory will + * succeed. An incorrect C-bit position will map all memory unencrypted, so that + * the compare will use the encrypted random data and fail. + */ +SYM_FUNC_START(startup32_check_sev_cbit) + pushl %ebx + pushl %ebp + + call 0f +0: popl %ebp + + /* Check for non-zero sev_status */ + movl (sev_status - 0b)(%ebp), %eax + testl %eax, %eax + jz 4f + + /* + * Get two 32-bit random values - Don't bail out if RDRAND fails + * because it is better to prevent forward progress if no random value + * can be gathered. + */ +1: rdrand %eax + jnc 1b +2: rdrand %ebx + jnc 2b + + /* Store to memory and keep it in the registers */ + leal (sev_check_data - 0b)(%ebp), %ebp + movl %eax, 0(%ebp) + movl %ebx, 4(%ebp) + + /* Enable paging to see if encryption is active */ + movl %cr0, %edx /* Backup %cr0 in %edx */ + movl $(X86_CR0_PG | X86_CR0_PE), %ecx /* Enable Paging and Protected mode */ + movl %ecx, %cr0 + + cmpl %eax, 0(%ebp) + jne 3f + cmpl %ebx, 4(%ebp) + jne 3f + + movl %edx, %cr0 /* Restore previous %cr0 */ + + jmp 4f + +3: /* Check failed - hlt the machine */ + hlt + jmp 3b + +4: + popl %ebp + popl %ebx + RET +SYM_FUNC_END(startup32_check_sev_cbit) + .code64 #include "../../kernel/sev_verify_cbit.S" .data -#ifdef CONFIG_AMD_MEM_ENCRYPT .balign 8 SYM_DATA(sme_me_mask, .quad 0) SYM_DATA(sev_status, .quad 0) SYM_DATA(sev_check_data, .quad 0) -#endif + +SYM_DATA_START_LOCAL(boot32_idt) + .rept 32 + .quad 0 + .endr +SYM_DATA_END(boot32_idt) + +SYM_DATA_START_LOCAL(boot32_idt_desc) + .word . - boot32_idt - 1 + .long 0 +SYM_DATA_END(boot32_idt_desc) diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index cf690d8712f4eda895861a802e10f86ccc7d68a1..45435ff8836358f70d05e9823e68a8cb374172ff 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -46,7 +46,7 @@ void *memmove(void *dest, const void *src, size_t n); /* * This is set up by the setup-routine at boot-time */ -struct boot_params *boot_params; +struct boot_params *boot_params_ptr; struct port_io_ops pio_ops; @@ -132,8 +132,8 @@ void __putstr(const char *s) if (lines == 0 || cols == 0) return; - x = boot_params->screen_info.orig_x; - y = boot_params->screen_info.orig_y; + x = boot_params_ptr->screen_info.orig_x; + y = boot_params_ptr->screen_info.orig_y; while ((c = *s++) != '\0') { if (c == '\n') { @@ -154,8 +154,8 @@ void __putstr(const char *s) } } - boot_params->screen_info.orig_x = x; - boot_params->screen_info.orig_y = y; + boot_params_ptr->screen_info.orig_x = x; + boot_params_ptr->screen_info.orig_y = y; pos = (x + cols * y) * 2; /* Update cursor position */ outb(14, vidport); @@ -277,7 +277,7 @@ static inline void handle_relocations(void *output, unsigned long output_len, { } #endif -static void parse_elf(void *output) +static size_t parse_elf(void *output) { #ifdef CONFIG_X86_64 Elf64_Ehdr ehdr; @@ -293,10 +293,8 @@ static void parse_elf(void *output) if (ehdr.e_ident[EI_MAG0] != ELFMAG0 || ehdr.e_ident[EI_MAG1] != ELFMAG1 || ehdr.e_ident[EI_MAG2] != ELFMAG2 || - ehdr.e_ident[EI_MAG3] != ELFMAG3) { + ehdr.e_ident[EI_MAG3] != ELFMAG3) error("Kernel is not a valid ELF file"); - return; - } debug_putstr("Parsing ELF... "); @@ -328,6 +326,36 @@ static void parse_elf(void *output) } free(phdrs); + + return ehdr.e_entry - LOAD_PHYSICAL_ADDR; +} + +const unsigned long kernel_text_size = VO___start_rodata - VO__text; +const unsigned long kernel_total_size = VO__end - VO__text; + +static u8 boot_heap[BOOT_HEAP_SIZE] __aligned(4); + +extern unsigned char input_data[]; +extern unsigned int input_len, output_len; + +unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr, + void (*error)(char *x)) +{ + unsigned long entry; + + if (!free_mem_ptr) { + free_mem_ptr = (unsigned long)boot_heap; + free_mem_end_ptr = (unsigned long)boot_heap + sizeof(boot_heap); + } + + if (__decompress(input_data, input_len, NULL, NULL, outbuf, output_len, + NULL, error) < 0) + return ULONG_MAX; + + entry = parse_elf(outbuf); + handle_relocations(outbuf, output_len, virt_addr); + + return entry; } /* @@ -347,25 +375,22 @@ static void parse_elf(void *output) * |-------uncompressed kernel image---------| * */ -asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, - unsigned char *input_data, - unsigned long input_len, - unsigned char *output, - unsigned long output_len) +asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output) { - const unsigned long kernel_total_size = VO__end - VO__text; unsigned long virt_addr = LOAD_PHYSICAL_ADDR; + memptr heap = (memptr)boot_heap; unsigned long needed_size; + size_t entry_offset; /* Retain x86 boot parameters pointer passed from startup_32/64. */ - boot_params = rmode; + boot_params_ptr = rmode; /* Clear flags intended for solely in-kernel use. */ - boot_params->hdr.loadflags &= ~KASLR_FLAG; + boot_params_ptr->hdr.loadflags &= ~KASLR_FLAG; - sanitize_boot_params(boot_params); + sanitize_boot_params(boot_params_ptr); - if (boot_params->screen_info.orig_video_mode == 7) { + if (boot_params_ptr->screen_info.orig_video_mode == 7) { vidmem = (char *) 0xb0000; vidport = 0x3b4; } else { @@ -373,8 +398,8 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, vidport = 0x3d4; } - lines = boot_params->screen_info.orig_video_lines; - cols = boot_params->screen_info.orig_video_cols; + lines = boot_params_ptr->screen_info.orig_video_lines; + cols = boot_params_ptr->screen_info.orig_video_cols; init_default_io_ops(); @@ -393,7 +418,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, * so that early debugging output from the RSDP parsing code can be * collected. */ - boot_params->acpi_rsdp_addr = get_rsdp_addr(); + boot_params_ptr->acpi_rsdp_addr = get_rsdp_addr(); debug_putstr("early console in extract_kernel\n"); @@ -411,7 +436,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, * entries. This ensures the full mapped area is usable RAM * and doesn't include any reserved areas. */ - needed_size = max(output_len, kernel_total_size); + needed_size = max_t(unsigned long, output_len, kernel_total_size); #ifdef CONFIG_X86_64 needed_size = ALIGN(needed_size, MIN_KERNEL_ALIGN); #endif @@ -442,7 +467,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, #ifdef CONFIG_X86_64 if (heap > 0x3fffffffffffUL) error("Destination address too large"); - if (virt_addr + max(output_len, kernel_total_size) > KERNEL_IMAGE_SIZE) + if (virt_addr + needed_size > KERNEL_IMAGE_SIZE) error("Destination virtual address is beyond the kernel mapping area"); #else if (heap > ((-__PAGE_OFFSET-(128<<20)-1) & 0x7fffffff)) @@ -454,16 +479,17 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, #endif debug_putstr("\nDecompressing Linux... "); - __decompress(input_data, input_len, NULL, NULL, output, output_len, - NULL, error); - parse_elf(output); - handle_relocations(output, output_len, virt_addr); - debug_putstr("done.\nBooting the kernel.\n"); + + entry_offset = decompress_kernel(output, virt_addr, error); + + debug_putstr("done.\nBooting the kernel (entry_offset: 0x"); + debug_puthex(entry_offset); + debug_putstr(").\n"); /* Disable exception handling before booting the kernel */ cleanup_exception_handling(); - return output; + return output + entry_offset; } void fortify_panic(const char *name) diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index a49d9219c06e51edd2d6f70e82e4f63174f3c57c..254acd76efde25feade322c295a9cc7f8e57e58a 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -52,7 +52,6 @@ extern memptr free_mem_ptr; extern memptr free_mem_end_ptr; void *malloc(int size); void free(void *where); -extern struct boot_params *boot_params; void __putstr(const char *s); void __puthex(unsigned long value); #define error_putstr(__x) __putstr(__x) @@ -170,9 +169,7 @@ static inline int count_immovable_mem_regions(void) { return 0; } #endif /* ident_map_64.c */ -#ifdef CONFIG_X86_5LEVEL extern unsigned int __pgtable_l5_enabled, pgdir_shift, ptrs_per_p4d; -#endif extern void kernel_add_identity_map(unsigned long start, unsigned long end); /* Used by PAGE_KERN* macros: */ diff --git a/arch/x86/boot/compressed/pgtable.h b/arch/x86/boot/compressed/pgtable.h index cc9b2529a08634b4249ec65c0d33219f811d08a1..6d595abe06b34d63e5e090fa1c27b108fd799fd0 100644 --- a/arch/x86/boot/compressed/pgtable.h +++ b/arch/x86/boot/compressed/pgtable.h @@ -3,18 +3,16 @@ #define TRAMPOLINE_32BIT_SIZE (2 * PAGE_SIZE) -#define TRAMPOLINE_32BIT_PGTABLE_OFFSET 0 - #define TRAMPOLINE_32BIT_CODE_OFFSET PAGE_SIZE -#define TRAMPOLINE_32BIT_CODE_SIZE 0x80 - -#define TRAMPOLINE_32BIT_STACK_END TRAMPOLINE_32BIT_SIZE +#define TRAMPOLINE_32BIT_CODE_SIZE 0xA0 #ifndef __ASSEMBLER__ extern unsigned long *trampoline_32bit; -extern void trampoline_32bit_src(void *return_ptr); +extern void trampoline_32bit_src(void *trampoline, bool enable_5lvl); + +extern const u16 trampoline_ljmp_imm_offset; #endif /* __ASSEMBLER__ */ #endif /* BOOT_COMPRESSED_PAGETABLE_H */ diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index 2ac12ff4111bf8c0dddeafc38680daaf9c0834cc..51f957b24ba7a2babdd7c89d3b6cf0b070519691 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -16,11 +16,6 @@ unsigned int __section(".data") pgdir_shift = 39; unsigned int __section(".data") ptrs_per_p4d = 1; #endif -struct paging_config { - unsigned long trampoline_start; - unsigned long l5_required; -}; - /* Buffer to preserve trampoline memory */ static char trampoline_save[TRAMPOLINE_32BIT_SIZE]; @@ -29,11 +24,10 @@ static char trampoline_save[TRAMPOLINE_32BIT_SIZE]; * purposes. * * Avoid putting the pointer into .bss as it will be cleared between - * paging_prepare() and extract_kernel(). + * configure_5level_paging() and extract_kernel(). */ unsigned long *trampoline_32bit __section(".data"); -extern struct boot_params *boot_params; int cmdline_find_option_bool(const char *option); static unsigned long find_trampoline_placement(void) @@ -54,7 +48,7 @@ static unsigned long find_trampoline_placement(void) * * Only look for values in the legacy ROM for non-EFI system. */ - signature = (char *)&boot_params->efi_info.efi_loader_signature; + signature = (char *)&boot_params_ptr->efi_info.efi_loader_signature; if (strncmp(signature, EFI32_LOADER_SIGNATURE, 4) && strncmp(signature, EFI64_LOADER_SIGNATURE, 4)) { ebda_start = *(unsigned short *)0x40e << 4; @@ -70,10 +64,10 @@ static unsigned long find_trampoline_placement(void) bios_start = round_down(bios_start, PAGE_SIZE); /* Find the first usable memory region under bios_start. */ - for (i = boot_params->e820_entries - 1; i >= 0; i--) { + for (i = boot_params_ptr->e820_entries - 1; i >= 0; i--) { unsigned long new = bios_start; - entry = &boot_params->e820_table[i]; + entry = &boot_params_ptr->e820_table[i]; /* Skip all entries above bios_start. */ if (bios_start <= entry->addr) @@ -106,12 +100,13 @@ static unsigned long find_trampoline_placement(void) return bios_start - TRAMPOLINE_32BIT_SIZE; } -struct paging_config paging_prepare(void *rmode) +asmlinkage void configure_5level_paging(struct boot_params *bp, void *pgtable) { - struct paging_config paging_config = {}; + void (*toggle_la57)(void *cr3); + bool l5_required = false; /* Initialize boot_params. Required for cmdline_find_option_bool(). */ - boot_params = rmode; + boot_params_ptr = bp; /* * Check if LA57 is desired and supported. @@ -129,12 +124,22 @@ struct paging_config paging_prepare(void *rmode) !cmdline_find_option_bool("no5lvl") && native_cpuid_eax(0) >= 7 && (native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) { - paging_config.l5_required = 1; + l5_required = true; + + /* Initialize variables for 5-level paging */ + __pgtable_l5_enabled = 1; + pgdir_shift = 48; + ptrs_per_p4d = 512; } - paging_config.trampoline_start = find_trampoline_placement(); + /* + * The trampoline will not be used if the paging mode is already set to + * the desired one. + */ + if (l5_required == !!(native_read_cr4() & X86_CR4_LA57)) + return; - trampoline_32bit = (unsigned long *)paging_config.trampoline_start; + trampoline_32bit = (unsigned long *)find_trampoline_placement(); /* Preserve trampoline memory */ memcpy(trampoline_save, trampoline_32bit, TRAMPOLINE_32BIT_SIZE); @@ -143,32 +148,32 @@ struct paging_config paging_prepare(void *rmode) memset(trampoline_32bit, 0, TRAMPOLINE_32BIT_SIZE); /* Copy trampoline code in place */ - memcpy(trampoline_32bit + TRAMPOLINE_32BIT_CODE_OFFSET / sizeof(unsigned long), + toggle_la57 = memcpy(trampoline_32bit + + TRAMPOLINE_32BIT_CODE_OFFSET / sizeof(unsigned long), &trampoline_32bit_src, TRAMPOLINE_32BIT_CODE_SIZE); + /* + * Avoid the need for a stack in the 32-bit trampoline code, by using + * LJMP rather than LRET to return back to long mode. LJMP takes an + * immediate absolute address, which needs to be adjusted based on the + * placement of the trampoline. + */ + *(u32 *)((u8 *)toggle_la57 + trampoline_ljmp_imm_offset) += + (unsigned long)toggle_la57; + /* * The code below prepares page table in trampoline memory. * * The new page table will be used by trampoline code for switching * from 4- to 5-level paging or vice versa. - * - * If switching is not required, the page table is unused: trampoline - * code wouldn't touch CR3. - */ - - /* - * We are not going to use the page table in trampoline memory if we - * are already in the desired paging mode. */ - if (paging_config.l5_required == !!(native_read_cr4() & X86_CR4_LA57)) - goto out; - if (paging_config.l5_required) { + if (l5_required) { /* * For 4- to 5-level paging transition, set up current CR3 as * the first and the only entry in a new top-level page table. */ - trampoline_32bit[TRAMPOLINE_32BIT_PGTABLE_OFFSET] = __native_read_cr3() | _PAGE_TABLE_NOENC; + *trampoline_32bit = __native_read_cr3() | _PAGE_TABLE_NOENC; } else { unsigned long src; @@ -181,38 +186,17 @@ struct paging_config paging_prepare(void *rmode) * may be above 4G. */ src = *(unsigned long *)__native_read_cr3() & PAGE_MASK; - memcpy(trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET / sizeof(unsigned long), - (void *)src, PAGE_SIZE); + memcpy(trampoline_32bit, (void *)src, PAGE_SIZE); } -out: - return paging_config; -} - -void cleanup_trampoline(void *pgtable) -{ - void *trampoline_pgtable; - - trampoline_pgtable = trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET / sizeof(unsigned long); + toggle_la57(trampoline_32bit); /* - * Move the top level page table out of trampoline memory, - * if it's there. + * Move the top level page table out of trampoline memory. */ - if ((void *)__native_read_cr3() == trampoline_pgtable) { - memcpy(pgtable, trampoline_pgtable, PAGE_SIZE); - native_write_cr3((unsigned long)pgtable); - } + memcpy(pgtable, trampoline_32bit, PAGE_SIZE); + native_write_cr3((unsigned long)pgtable); /* Restore trampoline memory */ memcpy(trampoline_32bit, trampoline_save, TRAMPOLINE_32BIT_SIZE); - - /* Initialize variables for 5-level paging */ -#ifdef CONFIG_X86_5LEVEL - if (__read_cr4() & X86_CR4_LA57) { - __pgtable_l5_enabled = 1; - pgdir_shift = 48; - ptrs_per_p4d = 512; - } -#endif } diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index 9c91cc40f4565640429ce8af8519a3dbbc5b5301..3c5d5c97f8f73b5f4e958b37e0dc785aed79dedf 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -118,6 +118,9 @@ static bool fault_in_kernel_space(unsigned long address) #define __init #define __pa(x) ((unsigned long)(x)) +#undef __head +#define __head + #define __BOOT_COMPRESSED /* Basic instruction decoding support needed */ @@ -327,20 +330,25 @@ static void enforce_vmpl0(void) */ #define SNP_FEATURES_PRESENT (0) +u64 snp_get_unsupported_features(u64 status) +{ + if (!(status & MSR_AMD64_SEV_SNP_ENABLED)) + return 0; + + return status & SNP_FEATURES_IMPL_REQ & ~SNP_FEATURES_PRESENT; +} + void snp_check_features(void) { u64 unsupported; - if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) - return; - /* * Terminate the boot if hypervisor has enabled any feature lacking * guest side implementation. Pass on the unsupported features mask through * EXIT_INFO_2 of the GHCB protocol so that those features can be reported * as part of the guest boot failure. */ - unsupported = sev_status & SNP_FEATURES_IMPL_REQ & ~SNP_FEATURES_PRESENT; + unsupported = snp_get_unsupported_features(sev_status); if (unsupported) { if (ghcb_version < 2 || (!boot_ghcb && !early_setup_ghcb())) sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); @@ -350,35 +358,22 @@ void snp_check_features(void) } } -void sev_enable(struct boot_params *bp) +/* + * sev_check_cpu_support - Check for SEV support in the CPU capabilities + * + * Returns < 0 if SEV is not supported, otherwise the position of the + * encryption bit in the page table descriptors. + */ +static int sev_check_cpu_support(void) { unsigned int eax, ebx, ecx, edx; - struct msr m; - bool snp; - - /* - * bp->cc_blob_address should only be set by boot/compressed kernel. - * Initialize it to 0 to ensure that uninitialized values from - * buggy bootloaders aren't propagated. - */ - if (bp) - bp->cc_blob_address = 0; - - /* - * Do an initial SEV capability check before snp_init() which - * loads the CPUID page and the same checks afterwards are done - * without the hypervisor and are trustworthy. - * - * If the HV fakes SEV support, the guest will crash'n'burn - * which is good enough. - */ /* Check for the SME/SEV support leaf */ eax = 0x80000000; ecx = 0; native_cpuid(&eax, &ebx, &ecx, &edx); if (eax < 0x8000001f) - return; + return -ENODEV; /* * Check for the SME/SEV feature: @@ -393,6 +388,35 @@ void sev_enable(struct boot_params *bp) native_cpuid(&eax, &ebx, &ecx, &edx); /* Check whether SEV is supported */ if (!(eax & BIT(1))) + return -ENODEV; + + return ebx & 0x3f; +} + +void sev_enable(struct boot_params *bp) +{ + struct msr m; + int bitpos; + bool snp; + + /* + * bp->cc_blob_address should only be set by boot/compressed kernel. + * Initialize it to 0 to ensure that uninitialized values from + * buggy bootloaders aren't propagated. + */ + if (bp) + bp->cc_blob_address = 0; + + /* + * Do an initial SEV capability check before snp_init() which + * loads the CPUID page and the same checks afterwards are done + * without the hypervisor and are trustworthy. + * + * If the HV fakes SEV support, the guest will crash'n'burn + * which is good enough. + */ + + if (sev_check_cpu_support() < 0) return; /* @@ -403,26 +427,8 @@ void sev_enable(struct boot_params *bp) /* Now repeat the checks with the SNP CPUID table. */ - /* Recheck the SME/SEV support leaf */ - eax = 0x80000000; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - if (eax < 0x8000001f) - return; - - /* - * Recheck for the SME/SEV feature: - * CPUID Fn8000_001F[EAX] - * - Bit 0 - Secure Memory Encryption support - * - Bit 1 - Secure Encrypted Virtualization support - * CPUID Fn8000_001F[EBX] - * - Bits 5:0 - Pagetable bit position used to indicate encryption - */ - eax = 0x8000001f; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - /* Check whether SEV is supported */ - if (!(eax & BIT(1))) { + bitpos = sev_check_cpu_support(); + if (bitpos < 0) { if (snp) error("SEV-SNP support indicated by CC blob, but not CPUID."); return; @@ -454,7 +460,24 @@ void sev_enable(struct boot_params *bp) if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) error("SEV-SNP supported indicated by CC blob, but not SEV status MSR."); - sme_me_mask = BIT_ULL(ebx & 0x3f); + sme_me_mask = BIT_ULL(bitpos); +} + +/* + * sev_get_status - Retrieve the SEV status mask + * + * Returns 0 if the CPU is not SEV capable, otherwise the value of the + * AMD64_SEV MSR. + */ +u64 sev_get_status(void) +{ + struct msr m; + + if (sev_check_cpu_support() < 0) + return 0; + + boot_rdmsr(MSR_AMD64_SEV, &m); + return m.q; } /* Search for Confidential Computing blob in the EFI config table. */ @@ -545,7 +568,7 @@ void sev_prep_identity_maps(unsigned long top_level_pgt) * accessed after switchover. */ if (sev_snp_enabled()) { - unsigned long cc_info_pa = boot_params->cc_blob_address; + unsigned long cc_info_pa = boot_params_ptr->cc_blob_address; struct cc_blob_sev_info *cc_info; kernel_add_identity_map(cc_info_pa, cc_info_pa + sizeof(*cc_info)); diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index 112b2375d021bb190fb6491bf05a41f52c2ea4fe..bcf0e4e4c98e8e3862d3a19c1fc920b53dfab624 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -42,11 +42,13 @@ SECTIONS *(.rodata.*) _erodata = . ; } - .data : { + .data : ALIGN(0x1000) { _data = . ; *(.data) *(.data.*) - *(.bss.efistub) + + /* Add 4 bytes of extra space for a CRC-32 checksum */ + . = ALIGN(. + 4, 0x200); _edata = . ; } . = ALIGN(L1_CACHE_BYTES); diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index f912d777013052eaddfcb3d0bca1efc154be5bdd..7593339b529a233a0e7e62c100ede38f0850e84a 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -36,65 +36,19 @@ SYSSEG = 0x1000 /* historical load address >> 4 */ #define ROOT_RDONLY 1 #endif + .set salign, 0x1000 + .set falign, 0x200 + .code16 .section ".bstext", "ax" - - .global bootsect_start -bootsect_start: #ifdef CONFIG_EFI_STUB # "MZ", MS-DOS header .word MZ_MAGIC -#endif - - # Normalize the start address - ljmp $BOOTSEG, $start2 - -start2: - movw %cs, %ax - movw %ax, %ds - movw %ax, %es - movw %ax, %ss - xorw %sp, %sp - sti - cld - - movw $bugger_off_msg, %si - -msg_loop: - lodsb - andb %al, %al - jz bs_die - movb $0xe, %ah - movw $7, %bx - int $0x10 - jmp msg_loop - -bs_die: - # Allow the user to press a key, then reboot - xorw %ax, %ax - int $0x16 - int $0x19 - - # int 0x19 should never return. In case it does anyway, - # invoke the BIOS reset code... - ljmp $0xf000,$0xfff0 - -#ifdef CONFIG_EFI_STUB .org 0x3c # # Offset to the PE header. # .long pe_header -#endif /* CONFIG_EFI_STUB */ - - .section ".bsdata", "a" -bugger_off_msg: - .ascii "Use a boot loader.\r\n" - .ascii "\n" - .ascii "Remove disk and press any key to reboot...\r\n" - .byte 0 - -#ifdef CONFIG_EFI_STUB pe_header: .long PE_MAGIC @@ -123,30 +77,26 @@ optional_header: .byte 0x02 # MajorLinkerVersion .byte 0x14 # MinorLinkerVersion - # Filled in by build.c - .long 0 # SizeOfCode + .long ZO__data # SizeOfCode - .long 0 # SizeOfInitializedData + .long ZO__end - ZO__data # SizeOfInitializedData .long 0 # SizeOfUninitializedData - # Filled in by build.c - .long 0x0000 # AddressOfEntryPoint + .long setup_size + ZO_efi_pe_entry # AddressOfEntryPoint - .long 0x0200 # BaseOfCode + .long setup_size # BaseOfCode #ifdef CONFIG_X86_32 .long 0 # data #endif extra_header_fields: - # PE specification requires ImageBase to be 64k aligned - .set image_base, (LOAD_PHYSICAL_ADDR + 0xffff) & ~0xffff #ifdef CONFIG_X86_32 - .long image_base # ImageBase + .long 0 # ImageBase #else - .quad image_base # ImageBase + .quad 0 # ImageBase #endif - .long 0x20 # SectionAlignment - .long 0x20 # FileAlignment + .long salign # SectionAlignment + .long falign # FileAlignment .word 0 # MajorOperatingSystemVersion .word 0 # MinorOperatingSystemVersion .word LINUX_EFISTUB_MAJOR_VERSION # MajorImageVersion @@ -155,12 +105,9 @@ extra_header_fields: .word 0 # MinorSubsystemVersion .long 0 # Win32VersionValue - # - # The size of the bzImage is written in tools/build.c - # - .long 0 # SizeOfImage + .long setup_size + ZO__end # SizeOfImage - .long 0x200 # SizeOfHeaders + .long salign # SizeOfHeaders .long 0 # CheckSum .word IMAGE_SUBSYSTEM_EFI_APPLICATION # Subsystem (EFI application) #ifdef CONFIG_EFI_DXE_MEM_ATTRIBUTES @@ -191,87 +138,77 @@ extra_header_fields: # Section table section_table: - # - # The offset & size fields are filled in by build.c. - # .ascii ".setup" .byte 0 .byte 0 - .long 0 - .long 0x0 # startup_{32,64} - .long 0 # Size of initialized data - # on disk - .long 0x0 # startup_{32,64} - .long 0 # PointerToRelocations - .long 0 # PointerToLineNumbers - .word 0 # NumberOfRelocations - .word 0 # NumberOfLineNumbers - .long IMAGE_SCN_CNT_CODE | \ - IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_EXECUTE | \ - IMAGE_SCN_ALIGN_16BYTES # Characteristics + .long pecompat_fstart - salign # VirtualSize + .long salign # VirtualAddress + .long pecompat_fstart - salign # SizeOfRawData + .long salign # PointerToRawData - # - # The EFI application loader requires a relocation section - # because EFI applications must be relocatable. The .reloc - # offset & size fields are filled in by build.c. - # - .ascii ".reloc" - .byte 0 - .byte 0 - .long 0 - .long 0 - .long 0 # SizeOfRawData - .long 0 # PointerToRawData - .long 0 # PointerToRelocations - .long 0 # PointerToLineNumbers - .word 0 # NumberOfRelocations - .word 0 # NumberOfLineNumbers + .long 0, 0, 0 .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_DISCARDABLE | \ - IMAGE_SCN_ALIGN_1BYTES # Characteristics + IMAGE_SCN_MEM_DISCARDABLE # Characteristics #ifdef CONFIG_EFI_MIXED - # - # The offset & size fields are filled in by build.c. - # .asciz ".compat" - .long 0 - .long 0x0 - .long 0 # Size of initialized data - # on disk - .long 0x0 - .long 0 # PointerToRelocations - .long 0 # PointerToLineNumbers - .word 0 # NumberOfRelocations - .word 0 # NumberOfLineNumbers + + .long pecompat_fsize # VirtualSize + .long pecompat_fstart # VirtualAddress + .long pecompat_fsize # SizeOfRawData + .long pecompat_fstart # PointerToRawData + + .long 0, 0, 0 .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_DISCARDABLE | \ - IMAGE_SCN_ALIGN_1BYTES # Characteristics + IMAGE_SCN_MEM_DISCARDABLE # Characteristics + + /* + * Put the IA-32 machine type and the associated entry point address in + * the .compat section, so loaders can figure out which other execution + * modes this image supports. + */ + .pushsection ".pecompat", "a", @progbits + .balign salign + .globl pecompat_fstart +pecompat_fstart: + .byte 0x1 # Version + .byte 8 # Size + .word IMAGE_FILE_MACHINE_I386 # PE machine type + .long setup_size + ZO_efi32_pe_entry # Entrypoint + .byte 0x0 # Sentinel + .popsection +#else + .set pecompat_fstart, setup_size #endif - - # - # The offset & size fields are filled in by build.c. - # .ascii ".text" .byte 0 .byte 0 .byte 0 - .long 0 - .long 0x0 # startup_{32,64} - .long 0 # Size of initialized data + .long ZO__data + .long setup_size + .long ZO__data # Size of initialized data # on disk - .long 0x0 # startup_{32,64} + .long setup_size .long 0 # PointerToRelocations .long 0 # PointerToLineNumbers .word 0 # NumberOfRelocations .word 0 # NumberOfLineNumbers .long IMAGE_SCN_CNT_CODE | \ IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_EXECUTE | \ - IMAGE_SCN_ALIGN_16BYTES # Characteristics + IMAGE_SCN_MEM_EXECUTE # Characteristics + + .ascii ".data\0\0\0" + .long ZO__end - ZO__data # VirtualSize + .long setup_size + ZO__data # VirtualAddress + .long ZO__edata - ZO__data # SizeOfRawData + .long setup_size + ZO__data # PointerToRawData + + .long 0, 0, 0 + .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ + IMAGE_SCN_MEM_READ | \ + IMAGE_SCN_MEM_WRITE # Characteristics .set section_count, (. - section_table) / 40 #endif /* CONFIG_EFI_STUB */ @@ -285,12 +222,12 @@ sentinel: .byte 0xff, 0xff /* Used to detect broken loaders */ .globl hdr hdr: -setup_sects: .byte 0 /* Filled in by build.c */ + .byte setup_sects - 1 root_flags: .word ROOT_RDONLY -syssize: .long 0 /* Filled in by build.c */ +syssize: .long ZO__edata / 16 ram_size: .word 0 /* Obsolete */ vid_mode: .word SVGA_MODE -root_dev: .word 0 /* Filled in by build.c */ +root_dev: .word 0 /* Default to major/minor 0/0 */ boot_flag: .word 0xAA55 # offset 512, entry point @@ -406,7 +343,7 @@ xloadflags: # define XLF1 0 #endif -#ifdef CONFIG_EFI_STUB +#ifdef CONFIG_EFI_HANDOVER_PROTOCOL # ifdef CONFIG_EFI_MIXED # define XLF23 (XLF_EFI_HANDOVER_32|XLF_EFI_HANDOVER_64) # else @@ -578,9 +515,25 @@ pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr # define INIT_SIZE VO_INIT_SIZE #endif + .macro __handover_offset +#ifndef CONFIG_EFI_HANDOVER_PROTOCOL + .long 0 +#elif !defined(CONFIG_X86_64) + .long ZO_efi32_stub_entry +#else + /* Yes, this is really how we defined it :( */ + .long ZO_efi64_stub_entry - 0x200 +#ifdef CONFIG_EFI_MIXED + .if ZO_efi32_stub_entry != ZO_efi64_stub_entry - 0x200 + .error "32-bit and 64-bit EFI entry points do not match" + .endif +#endif +#endif + .endm + init_size: .long INIT_SIZE # kernel initialization size -handover_offset: .long 0 # Filled in by build.c -kernel_info_offset: .long 0 # Filled in by build.c +handover_offset: __handover_offset +kernel_info_offset: .long ZO_kernel_info # End of setup header ##################################################### diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld index 49546c247ae25e97e8e9fcd083263f6f08254878..3a2d1360abb016902495f5879632335d883b8c03 100644 --- a/arch/x86/boot/setup.ld +++ b/arch/x86/boot/setup.ld @@ -10,10 +10,11 @@ ENTRY(_start) SECTIONS { . = 0; - .bstext : { *(.bstext) } - .bsdata : { *(.bsdata) } + .bstext : { + *(.bstext) + . = 495; + } =0xffffffff - . = 495; .header : { *(.header) } .entrytext : { *(.entrytext) } .inittext : { *(.inittext) } @@ -23,6 +24,9 @@ SECTIONS .text : { *(.text .text.*) } .text32 : { *(.text32) } + .pecompat : { *(.pecompat) } + PROVIDE(pecompat_fsize = setup_size - pecompat_fstart); + . = ALIGN(16); .rodata : { *(.rodata*) } @@ -38,8 +42,10 @@ SECTIONS .signature : { setup_sig = .; LONG(0x5a5aaa55) - } + setup_size = ALIGN(ABSOLUTE(.), 4096); + setup_sects = ABSOLUTE(setup_size / 512); + } . = ALIGN(16); .bss : diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index a3725ad46c5a0b49d3a88f4a5735a79fe98a5736..10311d77c67f8fac343adff8756d97d2f896a4f4 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -40,10 +40,6 @@ typedef unsigned char u8; typedef unsigned short u16; typedef unsigned int u32; -#define DEFAULT_MAJOR_ROOT 0 -#define DEFAULT_MINOR_ROOT 0 -#define DEFAULT_ROOT_DEV (DEFAULT_MAJOR_ROOT << 8 | DEFAULT_MINOR_ROOT) - /* Minimal number of setup sectors */ #define SETUP_SECT_MIN 5 #define SETUP_SECT_MAX 64 @@ -51,22 +47,7 @@ typedef unsigned int u32; /* This must be large enough to hold the entire setup */ u8 buf[SETUP_SECT_MAX*512]; -#define PECOFF_RELOC_RESERVE 0x20 - -#ifdef CONFIG_EFI_MIXED -#define PECOFF_COMPAT_RESERVE 0x20 -#else -#define PECOFF_COMPAT_RESERVE 0x0 -#endif - -static unsigned long efi32_stub_entry; -static unsigned long efi64_stub_entry; -static unsigned long efi_pe_entry; -static unsigned long efi32_pe_entry; -static unsigned long kernel_info; -static unsigned long startup_64; -static unsigned long _ehead; -static unsigned long _end; +static unsigned long _edata; /*----------------------------------------------------------------------*/ @@ -152,178 +133,6 @@ static void usage(void) die("Usage: build setup system zoffset.h image"); } -#ifdef CONFIG_EFI_STUB - -static void update_pecoff_section_header_fields(char *section_name, u32 vma, u32 size, u32 datasz, u32 offset) -{ - unsigned int pe_header; - unsigned short num_sections; - u8 *section; - - pe_header = get_unaligned_le32(&buf[0x3c]); - num_sections = get_unaligned_le16(&buf[pe_header + 6]); - -#ifdef CONFIG_X86_32 - section = &buf[pe_header + 0xa8]; -#else - section = &buf[pe_header + 0xb8]; -#endif - - while (num_sections > 0) { - if (strncmp((char*)section, section_name, 8) == 0) { - /* section header size field */ - put_unaligned_le32(size, section + 0x8); - - /* section header vma field */ - put_unaligned_le32(vma, section + 0xc); - - /* section header 'size of initialised data' field */ - put_unaligned_le32(datasz, section + 0x10); - - /* section header 'file offset' field */ - put_unaligned_le32(offset, section + 0x14); - - break; - } - section += 0x28; - num_sections--; - } -} - -static void update_pecoff_section_header(char *section_name, u32 offset, u32 size) -{ - update_pecoff_section_header_fields(section_name, offset, size, size, offset); -} - -static void update_pecoff_setup_and_reloc(unsigned int size) -{ - u32 setup_offset = 0x200; - u32 reloc_offset = size - PECOFF_RELOC_RESERVE - PECOFF_COMPAT_RESERVE; -#ifdef CONFIG_EFI_MIXED - u32 compat_offset = reloc_offset + PECOFF_RELOC_RESERVE; -#endif - u32 setup_size = reloc_offset - setup_offset; - - update_pecoff_section_header(".setup", setup_offset, setup_size); - update_pecoff_section_header(".reloc", reloc_offset, PECOFF_RELOC_RESERVE); - - /* - * Modify .reloc section contents with a single entry. The - * relocation is applied to offset 10 of the relocation section. - */ - put_unaligned_le32(reloc_offset + 10, &buf[reloc_offset]); - put_unaligned_le32(10, &buf[reloc_offset + 4]); - -#ifdef CONFIG_EFI_MIXED - update_pecoff_section_header(".compat", compat_offset, PECOFF_COMPAT_RESERVE); - - /* - * Put the IA-32 machine type (0x14c) and the associated entry point - * address in the .compat section, so loaders can figure out which other - * execution modes this image supports. - */ - buf[compat_offset] = 0x1; - buf[compat_offset + 1] = 0x8; - put_unaligned_le16(0x14c, &buf[compat_offset + 2]); - put_unaligned_le32(efi32_pe_entry + size, &buf[compat_offset + 4]); -#endif -} - -static void update_pecoff_text(unsigned int text_start, unsigned int file_sz, - unsigned int init_sz) -{ - unsigned int pe_header; - unsigned int text_sz = file_sz - text_start; - unsigned int bss_sz = init_sz - file_sz; - - pe_header = get_unaligned_le32(&buf[0x3c]); - - /* - * The PE/COFF loader may load the image at an address which is - * misaligned with respect to the kernel_alignment field in the setup - * header. - * - * In order to avoid relocating the kernel to correct the misalignment, - * add slack to allow the buffer to be aligned within the declared size - * of the image. - */ - bss_sz += CONFIG_PHYSICAL_ALIGN; - init_sz += CONFIG_PHYSICAL_ALIGN; - - /* - * Size of code: Subtract the size of the first sector (512 bytes) - * which includes the header. - */ - put_unaligned_le32(file_sz - 512 + bss_sz, &buf[pe_header + 0x1c]); - - /* Size of image */ - put_unaligned_le32(init_sz, &buf[pe_header + 0x50]); - - /* - * Address of entry point for PE/COFF executable - */ - put_unaligned_le32(text_start + efi_pe_entry, &buf[pe_header + 0x28]); - - update_pecoff_section_header_fields(".text", text_start, text_sz + bss_sz, - text_sz, text_start); -} - -static int reserve_pecoff_reloc_section(int c) -{ - /* Reserve 0x20 bytes for .reloc section */ - memset(buf+c, 0, PECOFF_RELOC_RESERVE); - return PECOFF_RELOC_RESERVE; -} - -static void efi_stub_defaults(void) -{ - /* Defaults for old kernel */ -#ifdef CONFIG_X86_32 - efi_pe_entry = 0x10; -#else - efi_pe_entry = 0x210; - startup_64 = 0x200; -#endif -} - -static void efi_stub_entry_update(void) -{ - unsigned long addr = efi32_stub_entry; - -#ifdef CONFIG_X86_64 - /* Yes, this is really how we defined it :( */ - addr = efi64_stub_entry - 0x200; -#endif - -#ifdef CONFIG_EFI_MIXED - if (efi32_stub_entry != addr) - die("32-bit and 64-bit EFI entry points do not match\n"); -#endif - put_unaligned_le32(addr, &buf[0x264]); -} - -#else - -static inline void update_pecoff_setup_and_reloc(unsigned int size) {} -static inline void update_pecoff_text(unsigned int text_start, - unsigned int file_sz, - unsigned int init_sz) {} -static inline void efi_stub_defaults(void) {} -static inline void efi_stub_entry_update(void) {} - -static inline int reserve_pecoff_reloc_section(int c) -{ - return 0; -} -#endif /* CONFIG_EFI_STUB */ - -static int reserve_pecoff_compat_section(int c) -{ - /* Reserve 0x20 bytes for .compat section */ - memset(buf+c, 0, PECOFF_COMPAT_RESERVE); - return PECOFF_COMPAT_RESERVE; -} - /* * Parse zoffset.h and find the entry points. We could just #include zoffset.h * but that would mean tools/build would have to be rebuilt every time. It's @@ -352,14 +161,7 @@ static void parse_zoffset(char *fname) p = (char *)buf; while (p && *p) { - PARSE_ZOFS(p, efi32_stub_entry); - PARSE_ZOFS(p, efi64_stub_entry); - PARSE_ZOFS(p, efi_pe_entry); - PARSE_ZOFS(p, efi32_pe_entry); - PARSE_ZOFS(p, kernel_info); - PARSE_ZOFS(p, startup_64); - PARSE_ZOFS(p, _ehead); - PARSE_ZOFS(p, _end); + PARSE_ZOFS(p, _edata); p = strchr(p, '\n'); while (p && (*p == '\r' || *p == '\n')) @@ -369,17 +171,14 @@ static void parse_zoffset(char *fname) int main(int argc, char ** argv) { - unsigned int i, sz, setup_sectors, init_sz; + unsigned int i, sz, setup_sectors; int c; - u32 sys_size; struct stat sb; FILE *file, *dest; int fd; void *kernel; u32 crc = 0xffffffffUL; - efi_stub_defaults(); - if (argc != 5) usage(); parse_zoffset(argv[3]); @@ -401,72 +200,27 @@ int main(int argc, char ** argv) die("Boot block hasn't got boot flag (0xAA55)"); fclose(file); - c += reserve_pecoff_compat_section(c); - c += reserve_pecoff_reloc_section(c); - /* Pad unused space with zeros */ - setup_sectors = (c + 511) / 512; + setup_sectors = (c + 4095) / 4096; + setup_sectors *= 8; if (setup_sectors < SETUP_SECT_MIN) setup_sectors = SETUP_SECT_MIN; i = setup_sectors*512; memset(buf+c, 0, i-c); - update_pecoff_setup_and_reloc(i); - - /* Set the default root device */ - put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]); - /* Open and stat the kernel file */ fd = open(argv[2], O_RDONLY); if (fd < 0) die("Unable to open `%s': %m", argv[2]); if (fstat(fd, &sb)) die("Unable to stat `%s': %m", argv[2]); - sz = sb.st_size; + if (_edata != sb.st_size) + die("Unexpected file size `%s': %u != %u", argv[2], _edata, + sb.st_size); + sz = _edata - 4; kernel = mmap(NULL, sz, PROT_READ, MAP_SHARED, fd, 0); if (kernel == MAP_FAILED) die("Unable to mmap '%s': %m", argv[2]); - /* Number of 16-byte paragraphs, including space for a 4-byte CRC */ - sys_size = (sz + 15 + 4) / 16; -#ifdef CONFIG_EFI_STUB - /* - * COFF requires minimum 32-byte alignment of sections, and - * adding a signature is problematic without that alignment. - */ - sys_size = (sys_size + 1) & ~1; -#endif - - /* Patch the setup code with the appropriate size parameters */ - buf[0x1f1] = setup_sectors-1; - put_unaligned_le32(sys_size, &buf[0x1f4]); - - init_sz = get_unaligned_le32(&buf[0x260]); -#ifdef CONFIG_EFI_STUB - /* - * The decompression buffer will start at ImageBase. When relocating - * the compressed kernel to its end, we must ensure that the head - * section does not get overwritten. The head section occupies - * [i, i + _ehead), and the destination is [init_sz - _end, init_sz). - * - * At present these should never overlap, because 'i' is at most 32k - * because of SETUP_SECT_MAX, '_ehead' is less than 1k, and the - * calculation of INIT_SIZE in boot/header.S ensures that - * 'init_sz - _end' is at least 64k. - * - * For future-proofing, increase init_sz if necessary. - */ - - if (init_sz - _end < i + _ehead) { - init_sz = (i + _ehead + _end + 4095) & ~4095; - put_unaligned_le32(init_sz, &buf[0x260]); - } -#endif - update_pecoff_text(setup_sectors * 512, i + (sys_size * 16), init_sz); - - efi_stub_entry_update(); - - /* Update kernel_info offset. */ - put_unaligned_le32(kernel_info, &buf[0x268]); crc = partial_crc32(buf, i, crc); if (fwrite(buf, 1, i, dest) != i) @@ -477,13 +231,6 @@ int main(int argc, char ** argv) if (fwrite(kernel, 1, sz, dest) != sz) die("Writing kernel failed"); - /* Add padding leaving 4 bytes for the checksum */ - while (sz++ < (sys_size*16) - 4) { - crc = partial_crc32_one('\0', crc); - if (fwrite("\0", 1, 1, dest) != 1) - die("Writing padding failed"); - } - /* Write the CRC */ put_unaligned_le32(crc, buf); if (fwrite(buf, 1, 4, dest) != 4) diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c index 49b44f881484680376a7393dc0f101e4565a4009..801e943fd2b29d3ac5b480130a461eb9455f1ece 100644 --- a/arch/x86/coco/core.c +++ b/arch/x86/coco/core.c @@ -3,18 +3,22 @@ * Confidential Computing Platform Capability checks * * Copyright (C) 2021 Advanced Micro Devices, Inc. + * Copyright (C) 2024 Jason A. Donenfeld . All Rights Reserved. * * Author: Tom Lendacky */ #include #include +#include +#include +#include #include #include -static enum cc_vendor vendor __ro_after_init; -static u64 cc_mask __ro_after_init; +enum cc_vendor cc_vendor __ro_after_init = CC_VENDOR_NONE; +u64 cc_mask __ro_after_init; static bool intel_cc_platform_has(enum cc_attr attr) { @@ -83,7 +87,7 @@ static bool hyperv_cc_platform_has(enum cc_attr attr) bool cc_platform_has(enum cc_attr attr) { - switch (vendor) { + switch (cc_vendor) { case CC_VENDOR_AMD: return amd_cc_platform_has(attr); case CC_VENDOR_INTEL: @@ -105,7 +109,7 @@ u64 cc_mkenc(u64 val) * - for AMD, bit *set* means the page is encrypted * - for Intel *clear* means encrypted. */ - switch (vendor) { + switch (cc_vendor) { case CC_VENDOR_AMD: return val | cc_mask; case CC_VENDOR_INTEL: @@ -118,7 +122,7 @@ u64 cc_mkenc(u64 val) u64 cc_mkdec(u64 val) { /* See comment in cc_mkenc() */ - switch (vendor) { + switch (cc_vendor) { case CC_VENDOR_AMD: return val & ~cc_mask; case CC_VENDOR_INTEL: @@ -129,12 +133,39 @@ u64 cc_mkdec(u64 val) } EXPORT_SYMBOL_GPL(cc_mkdec); -__init void cc_set_vendor(enum cc_vendor v) +__init void cc_random_init(void) { - vendor = v; -} + /* + * The seed is 32 bytes (in units of longs), which is 256 bits, which + * is the security level that the RNG is targeting. + */ + unsigned long rng_seed[32 / sizeof(long)]; + size_t i, longs; -__init void cc_set_mask(u64 mask) -{ - cc_mask = mask; + if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) + return; + + /* + * Since the CoCo threat model includes the host, the only reliable + * source of entropy that can be neither observed nor manipulated is + * RDRAND. Usually, RDRAND failure is considered tolerable, but since + * CoCo guests have no other unobservable source of entropy, it's + * important to at least ensure the RNG gets some initial random seeds. + */ + for (i = 0; i < ARRAY_SIZE(rng_seed); i += longs) { + longs = arch_get_random_longs(&rng_seed[i], ARRAY_SIZE(rng_seed) - i); + + /* + * A zero return value means that the guest doesn't have RDRAND + * or the CPU is physically broken, and in both cases that + * means most crypto inside of the CoCo instance will be + * broken, defeating the purpose of CoCo in the first place. So + * just panic here because it's absolutely unsafe to continue + * executing. + */ + if (longs == 0) + panic("RDRAND is defective."); + } + add_device_randomness(rng_seed, sizeof(rng_seed)); + memzero_explicit(rng_seed, sizeof(rng_seed)); } diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index d0565a9e7d8c9483dbbed6dd6ed29ace7d1926e9..4692450aeb4d337c87aa5163af69c269d446edfc 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -793,7 +793,7 @@ void __init tdx_early_init(void) setup_force_cpu_cap(X86_FEATURE_TDX_GUEST); - cc_set_vendor(CC_VENDOR_INTEL); + cc_vendor = CC_VENDOR_INTEL; tdx_parse_tdinfo(&cc_mask); cc_set_mask(cc_mask); diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 9c0b26ae5106960d1e799e291a83c2661c39178f..e72dac092245a5040a76205079b77b4b94f0877c 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -48,7 +48,7 @@ static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr) if (likely(unr < NR_syscalls)) { unr = array_index_nospec(unr, NR_syscalls); - regs->ax = sys_call_table[unr](regs); + regs->ax = x64_sys_call(regs, unr); return true; } return false; @@ -65,7 +65,7 @@ static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr) if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) { xnr = array_index_nospec(xnr, X32_NR_syscalls); - regs->ax = x32_sys_call_table[xnr](regs); + regs->ax = x32_sys_call(regs, xnr); return true; } return false; @@ -114,7 +114,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr) if (likely(unr < IA32_NR_syscalls)) { unr = array_index_nospec(unr, IA32_NR_syscalls); - regs->ax = ia32_sys_call_table[unr](regs); + regs->ax = ia32_sys_call(regs, unr); } else if (nr != -1) { regs->ax = __ia32_sys_ni_syscall(regs); } @@ -141,7 +141,7 @@ static __always_inline bool int80_is_external(void) } /** - * int80_emulation - 32-bit legacy syscall entry + * do_int80_emulation - 32-bit legacy syscall C entry from asm * * This entry point can be used by 32-bit and 64-bit programs to perform * 32-bit system calls. Instances of INT $0x80 can be found inline in @@ -159,7 +159,7 @@ static __always_inline bool int80_is_external(void) * eax: system call number * ebx, ecx, edx, esi, edi, ebp: arg1 - arg 6 */ -DEFINE_IDTENTRY_RAW(int80_emulation) +__visible noinstr void do_int80_emulation(struct pt_regs *regs) { int nr; diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S index bfb7bcb362bcfca2f84947e0925766925687d77c..09e99d13fc0b307169c6d611a1fe71aa04db2a35 100644 --- a/arch/x86/entry/entry.S +++ b/arch/x86/entry/entry.S @@ -6,6 +6,9 @@ #include #include #include +#include +#include +#include .pushsection .noinstr.text, "ax" @@ -20,3 +23,23 @@ SYM_FUNC_END(entry_ibpb) EXPORT_SYMBOL_GPL(entry_ibpb); .popsection + +/* + * Define the VERW operand that is disguised as entry code so that + * it can be referenced with KPTI enabled. This ensure VERW can be + * used late in exit-to-user path after page tables are switched. + */ +.pushsection .entry.text, "ax" + +.align L1_CACHE_BYTES, 0xcc +SYM_CODE_START_NOALIGN(mds_verw_sel) + UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR + .word __KERNEL_DS +.align L1_CACHE_BYTES, 0xcc +SYM_CODE_END(mds_verw_sel); +/* For KVM */ +EXPORT_SYMBOL_GPL(mds_verw_sel); + +.popsection + diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index e309e7156038935ab92cd025616c5c765e3a5214..ee5def1060c86c237067393f6c4dc3ba092ae06b 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -912,6 +912,7 @@ SYM_FUNC_START(entry_SYSENTER_32) BUG_IF_WRONG_CR3 no_user_check=1 popfl popl %eax + CLEAR_CPU_BUFFERS /* * Return back to the vDSO, which will pop ecx and edx. @@ -981,6 +982,7 @@ restore_all_switch_stack: /* Restore user state */ RESTORE_REGS pop=4 # skip orig_eax/error_code + CLEAR_CPU_BUFFERS .Lirq_return: /* * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization @@ -1173,6 +1175,7 @@ SYM_CODE_START(asm_exc_nmi) /* Not on SYSENTER stack. */ call exc_nmi + CLEAR_CPU_BUFFERS jmp .Lnmi_return .Lnmi_from_sysenter_stack: diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 9953d966d12443115bc7ecb3d5c083c9b5c8847f..6624806e6904b70fe230773ef79a294b9cd423ce 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -116,6 +116,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) /* clobbers %rax, make sure it is after saving the syscall nr */ IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY call do_syscall_64 /* returns with IRQs disabled */ @@ -223,6 +224,7 @@ syscall_return_via_sysret: SYM_INNER_LABEL(entry_SYSRETQ_unsafe_stack, SYM_L_GLOBAL) ANNOTATE_NOENDBR swapgs + CLEAR_CPU_BUFFERS sysretq SYM_INNER_LABEL(entry_SYSRETQ_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR @@ -656,6 +658,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) /* Restore RDI. */ popq %rdi swapgs + CLEAR_CPU_BUFFERS jmp .Lnative_iret @@ -767,6 +770,8 @@ native_irq_return_ldt: */ popq %rax /* Restore user RAX */ + CLEAR_CPU_BUFFERS + /* * RSP now points to an ordinary IRET frame, except that the page * is read-only and RSP[31:16] are preloaded with the userspace @@ -1493,6 +1498,12 @@ nmi_restore: std movq $0, 5*8(%rsp) /* clear "NMI executing" */ + /* + * Skip CLEAR_CPU_BUFFERS here, since it only helps in rare cases like + * NMI in kernel after user state is restored. For an unprivileged user + * these conditions are hard to meet. + */ + /* * iretq reads the "iret" frame and exits the NMI stack in a * single instruction. We are returning to kernel mode, so this @@ -1511,6 +1522,7 @@ SYM_CODE_START(ignore_sysret) UNWIND_HINT_EMPTY ENDBR mov $-ENOSYS, %eax + CLEAR_CPU_BUFFERS sysretl SYM_CODE_END(ignore_sysret) #endif @@ -1528,3 +1540,63 @@ SYM_CODE_START(rewind_stack_and_make_dead) call make_task_dead SYM_CODE_END(rewind_stack_and_make_dead) .popsection + +/* + * This sequence executes branches in order to remove user branch information + * from the branch history tracker in the Branch Predictor, therefore removing + * user influence on subsequent BTB lookups. + * + * It should be used on parts prior to Alder Lake. Newer parts should use the + * BHI_DIS_S hardware control instead. If a pre-Alder Lake part is being + * virtualized on newer hardware the VMM should protect against BHI attacks by + * setting BHI_DIS_S for the guests. + * + * CALLs/RETs are necessary to prevent Loop Stream Detector(LSD) from engaging + * and not clearing the branch history. The call tree looks like: + * + * call 1 + * call 2 + * call 2 + * call 2 + * call 2 + * call 2 + * ret + * ret + * ret + * ret + * ret + * ret + * + * This means that the stack is non-constant and ORC can't unwind it with %rsp + * alone. Therefore we unconditionally set up the frame pointer, which allows + * ORC to unwind properly. + * + * The alignment is for performance and not for safety, and may be safely + * refactored in the future if needed. + */ +SYM_FUNC_START(clear_bhb_loop) + push %rbp + mov %rsp, %rbp + movl $5, %ecx + ANNOTATE_INTRA_FUNCTION_CALL + call 1f + jmp 5f + .align 64, 0xcc + ANNOTATE_INTRA_FUNCTION_CALL +1: call 2f + RET + .align 64, 0xcc +2: movl $5, %eax +3: jmp 4f + nop +4: sub $1, %eax + jnz 3b + sub $1, %ecx + jnz 1b + RET +5: lfence + pop %rbp + RET +SYM_FUNC_END(clear_bhb_loop) +EXPORT_SYMBOL_GPL(clear_bhb_loop) +STACK_FRAME_NON_STANDARD(clear_bhb_loop) diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index d6c08d8986b17b4b9d9b66ac9e48d1d5d798f4b7..b14b8cd85eb23d4167bca30a72bcee44768aa887 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -92,6 +92,7 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY /* * SYSENTER doesn't filter flags, so we need to clear NT and AC @@ -210,6 +211,7 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL) IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY movq %rsp, %rdi call do_fast_syscall_32 @@ -272,8 +274,23 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_unsafe_stack, SYM_L_GLOBAL) xorl %r9d, %r9d xorl %r10d, %r10d swapgs + CLEAR_CPU_BUFFERS sysretl SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR int3 SYM_CODE_END(entry_SYSCALL_compat) + +/* + * int 0x80 is used by 32 bit mode as a system call entry. Normally idt entries + * point to C routines, however since this is a system call interface the branch + * history needs to be scrubbed to protect against BHI attacks, and that + * scrubbing needs to take place in assembly code prior to entering any C + * routines. + */ +SYM_CODE_START(int80_emulation) + ANNOTATE_NOENDBR + UNWIND_HINT_FUNC + CLEAR_BRANCH_HISTORY + jmp do_int80_emulation +SYM_CODE_END(int80_emulation) diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c index 8cfc9bc73e7f8b21f748367256a78df3dc5e5b4a..c2235bae17ef665098342c323a24e4b388c169cb 100644 --- a/arch/x86/entry/syscall_32.c +++ b/arch/x86/entry/syscall_32.c @@ -18,8 +18,25 @@ #include #undef __SYSCALL +/* + * The sys_call_table[] is no longer used for system calls, but + * kernel/trace/trace_syscalls.c still wants to know the system + * call address. + */ +#ifdef CONFIG_X86_32 #define __SYSCALL(nr, sym) __ia32_##sym, - -__visible const sys_call_ptr_t ia32_sys_call_table[] = { +const sys_call_ptr_t sys_call_table[] = { #include }; +#undef __SYSCALL +#endif + +#define __SYSCALL(nr, sym) case nr: return __ia32_##sym(regs); + +long ia32_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include + default: return __ia32_sys_ni_syscall(regs); + } +}; diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index be120eec1fc9f95c69c23074bcd3fbc355b90d47..33b3f09e6f151e11faca1c9d13f0eb4917f3392b 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -11,8 +11,23 @@ #include #undef __SYSCALL +/* + * The sys_call_table[] is no longer used for system calls, but + * kernel/trace/trace_syscalls.c still wants to know the system + * call address. + */ #define __SYSCALL(nr, sym) __x64_##sym, - -asmlinkage const sys_call_ptr_t sys_call_table[] = { +const sys_call_ptr_t sys_call_table[] = { #include }; +#undef __SYSCALL + +#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs); + +long x64_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include + default: return __x64_sys_ni_syscall(regs); + } +}; diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c index bdd0e03a1265d23e474c5c45e1bd64e7b14b7b79..03de4a93213182c6fa5809b077a54ea51be411ea 100644 --- a/arch/x86/entry/syscall_x32.c +++ b/arch/x86/entry/syscall_x32.c @@ -11,8 +11,12 @@ #include #undef __SYSCALL -#define __SYSCALL(nr, sym) __x64_##sym, +#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs); -asmlinkage const sys_call_ptr_t x32_sys_call_table[] = { -#include +long x32_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include + default: return __x64_sys_ni_syscall(regs); + } }; diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 04f4b96dec6df74f71a6f8dce2bcd0cfb02ff08e..3ac069a4559b0401072599ac8c880e2ccf3f5d8a 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -604,7 +604,6 @@ static void amd_pmu_cpu_dead(int cpu) kfree(cpuhw->lbr_sel); cpuhw->lbr_sel = NULL; - amd_pmu_cpu_reset(cpu); if (!x86_pmu.amd_nb_constraints) return; @@ -905,8 +904,8 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) if (!status) goto done; - /* Read branch records before unfreezing */ - if (status & GLOBAL_STATUS_LBRS_FROZEN) { + /* Read branch records */ + if (x86_pmu.lbr_nr) { amd_pmu_lbr_read(); status &= ~GLOBAL_STATUS_LBRS_FROZEN; } diff --git a/arch/x86/events/amd/lbr.c b/arch/x86/events/amd/lbr.c index 38a75216c12cffc89a49e19f747e7a0adf272d9b..48f4095f500d4210971ef0647950ac52455be8f2 100644 --- a/arch/x86/events/amd/lbr.c +++ b/arch/x86/events/amd/lbr.c @@ -173,9 +173,11 @@ void amd_pmu_lbr_read(void) /* * Check if a branch has been logged; if valid = 0, spec = 0 - * then no branch was recorded + * then no branch was recorded; if reserved = 1 then an + * erroneous branch was recorded (see Erratum 1452) */ - if (!entry.to.split.valid && !entry.to.split.spec) + if ((!entry.to.split.valid && !entry.to.split.spec) || + entry.to.split.reserved) continue; perf_clear_branch_entry_bitfields(br + out); @@ -400,10 +402,12 @@ void amd_pmu_lbr_enable_all(void) wrmsrl(MSR_AMD64_LBR_SELECT, lbr_select); } - rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); - rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg); + if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) { + rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); + wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + } - wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg); wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg | DBG_EXTN_CFG_LBRV2EN); } @@ -416,10 +420,12 @@ void amd_pmu_lbr_disable_all(void) return; rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg); - rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); - wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg & ~DBG_EXTN_CFG_LBRV2EN); - wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + + if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) { + rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); + wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + } } __init int amd_pmu_lbr_init(void) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 30fb4931d387137d469a0c053014ae7b25c7ea64..1394312b732a3414aebd9559110a3ef908a35e79 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1644,6 +1644,7 @@ static void x86_pmu_del(struct perf_event *event, int flags) while (++i < cpuc->n_events) { cpuc->event_list[i-1] = cpuc->event_list[i]; cpuc->event_constraint[i-1] = cpuc->event_constraint[i]; + cpuc->assign[i-1] = cpuc->assign[i]; } cpuc->event_constraint[i-1] = NULL; --cpuc->n_events; diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 3216da7074bad80515872a72a69e75ff7add4d66..36ceecd40fd931e82afff14f6c2ddc109a9eb945 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -12,6 +12,7 @@ #include #include #include +#include #define ARCH_APICTIMER_STOPS_ON_C3 1 @@ -109,7 +110,7 @@ static inline void native_apic_mem_write(u32 reg, u32 v) static inline u32 native_apic_mem_read(u32 reg) { - return *((volatile u32 *)(APIC_BASE + reg)); + return readl((void __iomem *)(APIC_BASE + reg)); } extern void native_apic_wait_icr_idle(void); diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 8f80de627c60a8accabc0c6bcc1595045f0af53c..5cdccea455544f692569ecef2063659c11167b9b 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -12,6 +12,7 @@ #include #include #include +#include #ifndef CONFIG_X86_CMPXCHG64 extern void cmpxchg8b_emu(void); diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index fbcfec4dc4ccd74d983d84ebad2c6b4d188bde1a..ca8eed1d496ab4630fd65a98d491da491f23e35e 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -113,6 +113,20 @@ #endif +#ifndef __ASSEMBLY__ +#ifndef __pic__ +static __always_inline __pure void *rip_rel_ptr(void *p) +{ + asm("leaq %c1(%%rip), %0" : "=r"(p) : "i"(p)); + + return p; +} +#define RIP_REL_REF(var) (*(typeof(&(var)))rip_rel_ptr(&(var))) +#else +#define RIP_REL_REF(var) (var) +#endif +#endif + /* * Macros to generate condition code outputs from inline assembly, * The output operand must be type "bool". diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index 215d37f7dde8a993295160eaa6e8f012beb05783..a3e0be0470a400b9e31a008a019de2453f950a09 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -79,4 +79,15 @@ # define BOOT_STACK_SIZE 0x1000 #endif +#ifndef __ASSEMBLY__ +extern unsigned int output_len; +extern const unsigned long kernel_text_size; +extern const unsigned long kernel_total_size; + +unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr, + void (*error)(char *x)); + +extern struct boot_params *boot_params_ptr; +#endif + #endif /* _ASM_X86_BOOT_H */ diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h index 3d98c3a60d34f97fc6403a7248b9c06c03b63f8d..100a752c33bb3e64b16484264f930a884e3e892f 100644 --- a/arch/x86/include/asm/coco.h +++ b/arch/x86/include/asm/coco.h @@ -2,6 +2,7 @@ #ifndef _ASM_X86_COCO_H #define _ASM_X86_COCO_H +#include #include enum cc_vendor { @@ -11,13 +12,22 @@ enum cc_vendor { CC_VENDOR_INTEL, }; -void cc_set_vendor(enum cc_vendor v); -void cc_set_mask(u64 mask); +extern enum cc_vendor cc_vendor; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM +extern u64 cc_mask; + +static inline void cc_set_mask(u64 mask) +{ + RIP_REL_REF(cc_mask) = mask; +} + u64 cc_mkenc(u64 val); u64 cc_mkdec(u64 val); +void cc_random_init(void); #else +static const u64 cc_mask = 0; + static inline u64 cc_mkenc(u64 val) { return val; @@ -27,6 +37,7 @@ static inline u64 cc_mkdec(u64 val) { return val; } +static inline void cc_random_init(void) { } #endif #endif /* _ASM_X86_COCO_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index ce0c8f7d32186f32893bfdf4555246c856febc61..16051c6f3b13d4ccac08a7f489fcd2490817a6d8 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -33,6 +33,8 @@ enum cpuid_leafs CPUID_7_EDX, CPUID_8000_001F_EAX, CPUID_8000_0021_EAX, + CPUID_LNX_5, + NR_CPUID_WORDS, }; #define X86_CAP_FMT_NUM "%d:%d" @@ -96,8 +98,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 21, feature_bit) || \ REQUIRED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 21)) + BUILD_BUG_ON_ZERO(NCAPINTS != 22)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ @@ -121,8 +124,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 21, feature_bit) || \ DISABLED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 21)) + BUILD_BUG_ON_ZERO(NCAPINTS != 22)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ @@ -173,7 +177,7 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); */ static __always_inline bool _static_cpu_has(u16 bit) { - asm_volatile_goto( + asm goto( ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]") ".pushsection .altinstr_aux,\"ax\"\n" "6:\n" diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index b122708792c4d557fb6fc464c7d99f99647cbd45..7ded926724147e31001d2245454b77d09f8b6215 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 21 /* N 32-bit words worth of info */ +#define NCAPINTS 22 /* N 32-bit words worth of info */ #define NBUGINTS 2 /* N 32-bit bug flags */ /* @@ -304,7 +304,7 @@ #define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */ #define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */ #define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */ - +#define X86_FEATURE_CLEAR_CPU_BUF (11*32+18) /* "" Clear CPU buffers using VERW */ #define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ @@ -427,10 +427,23 @@ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ +#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* "" Automatic IBRS */ #define X86_FEATURE_SBPB (20*32+27) /* "" Selective Branch Prediction Barrier */ #define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */ #define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */ +/* + * Extended auxiliary flags: Linux defined - for features scattered in various + * CPUID levels like 0x80000022, etc and Linux defined features. + * + * Reuse free bits when adding new feature flags! + */ +#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */ +#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */ +#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */ +#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */ +#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */ + /* * BUG word(s) */ @@ -477,4 +490,6 @@ /* BUG word 2 */ #define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ #define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ +#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ +#define X86_BUG_BHI X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 000037078db439546294e0ca4cab42efc2122f84..380e963149cc7e30bfd0ca46931541f845a93697 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -112,6 +112,7 @@ #define DISABLED_MASK18 0 #define DISABLED_MASK19 0 #define DISABLED_MASK20 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define DISABLED_MASK21 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 233ae6986d6f2f2595479f0db3ea8874b46add1a..e601264b1a2430e88e6a552ac666e71316fa250f 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -88,6 +88,8 @@ static inline void efi_fpu_end(void) } #ifdef CONFIG_X86_32 +#define EFI_X86_KERNEL_ALLOC_LIMIT (SZ_512M - 1) + #define arch_efi_call_virt_setup() \ ({ \ efi_fpu_begin(); \ @@ -101,8 +103,7 @@ static inline void efi_fpu_end(void) }) #else /* !CONFIG_X86_32 */ - -#define EFI_LOADER_SIGNATURE "EL64" +#define EFI_X86_KERNEL_ALLOC_LIMIT EFI_ALLOC_LIMIT extern asmlinkage u64 __efi_call(void *fp, ...); @@ -214,6 +215,8 @@ efi_status_t efi_set_virtual_address_map(unsigned long memory_map_size, #ifdef CONFIG_EFI_MIXED +#define EFI_ALLOC_LIMIT (efi_is_64bit() ? ULONG_MAX : U32_MAX) + #define ARCH_HAS_EFISTUB_WRAPPERS static inline bool efi_is_64bit(void) @@ -325,6 +328,13 @@ static inline u32 efi64_convert_status(efi_status_t status) #define __efi64_argmap_set_memory_space_attributes(phys, size, flags) \ (__efi64_split(phys), __efi64_split(size), __efi64_split(flags)) +/* Memory Attribute Protocol */ +#define __efi64_argmap_set_memory_attributes(protocol, phys, size, flags) \ + ((protocol), __efi64_split(phys), __efi64_split(size), __efi64_split(flags)) + +#define __efi64_argmap_clear_memory_attributes(protocol, phys, size, flags) \ + ((protocol), __efi64_split(phys), __efi64_split(size), __efi64_split(flags)) + /* * The macros below handle the plumbing for the argument mapping. To add a * mapping for a specific EFI method, simply define a macro diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index 11203a9fe0a8772aa58c080725b1f22a9d7a68b4..ffe72790ceafdeeac8d722e27d06a9568312e7ec 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -91,7 +91,6 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, static __always_inline void arch_exit_to_user_mode(void) { - mds_user_clear_cpu_buffers(); amd_clear_divider(); } #define arch_exit_to_user_mode arch_exit_to_user_mode diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h index 5f1d3c421f686019847efd0533c049a608e401bf..cc9ccf61b6bd114df3ee9c5fdfa3134daee0f043 100644 --- a/arch/x86/include/asm/init.h +++ b/arch/x86/include/asm/init.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_INIT_H #define _ASM_X86_INIT_H +#define __head __section(".head.text") + struct x86_mapping_info { void *(*alloc_pgt_page)(void *); /* allocate buf for page table */ void *context; /* context for alloc_pgt_page */ diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index 071572e23d3a06783e3a1f63e11bb47e99af9daa..cbbef32517f0049a3df51842162032ff1946e901 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -24,7 +24,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:" + asm goto("1:" "jmp %l[l_yes] # objtool NOPs this \n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (2 | branch) : : l_yes); @@ -38,7 +38,7 @@ l_yes: static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { - asm_volatile_goto("1:" + asm goto("1:" ".byte " __stringify(BYTES_NOP5) "\n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (branch) : : l_yes); @@ -52,7 +52,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { - asm_volatile_goto("1:" + asm goto("1:" "jmp %l[l_yes]\n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (branch) : : l_yes); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index dfcdcafe3a2cd595331fe51aa84b95584fc7cb03..887a171488ea28532fa4b068a723c405a176e270 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -773,6 +773,7 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; u32 kvm_cpuid_base; + bool is_amd_compatible; u64 reserved_gpa_bits; int maxphyaddr; diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index c91326593e74179a53356d1e2f8c210d353aa4b0..853f423b1d138b5cfdbfbf7b188530904480d299 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -15,7 +15,8 @@ #include #include -#include +#include +struct boot_params; #ifdef CONFIG_X86_MEM_ENCRYPT void __init mem_encrypt_init(void); @@ -45,8 +46,8 @@ void __init sme_unmap_bootdata(char *real_mode_data); void __init sme_early_init(void); void __init sev_setup_arch(void); -void __init sme_encrypt_kernel(struct boot_params *bp); -void __init sme_enable(struct boot_params *bp); +void sme_encrypt_kernel(struct boot_params *bp); +void sme_enable(struct boot_params *bp); int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size); int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size); @@ -57,6 +58,11 @@ void __init mem_encrypt_free_decrypted_mem(void); void __init sev_es_init_vc_handling(void); +static inline u64 sme_get_me_mask(void) +{ + return RIP_REL_REF(sme_me_mask); +} + #define __bss_decrypted __section(".bss..decrypted") #else /* !CONFIG_AMD_MEM_ENCRYPT */ @@ -74,8 +80,8 @@ static inline void __init sme_unmap_bootdata(char *real_mode_data) { } static inline void __init sme_early_init(void) { } static inline void __init sev_setup_arch(void) { } -static inline void __init sme_encrypt_kernel(struct boot_params *bp) { } -static inline void __init sme_enable(struct boot_params *bp) { } +static inline void sme_encrypt_kernel(struct boot_params *bp) { } +static inline void sme_enable(struct boot_params *bp) { } static inline void sev_es_init_vc_handling(void) { } @@ -88,6 +94,8 @@ early_set_mem_enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool en static inline void mem_encrypt_free_decrypted_mem(void) { } +static inline u64 sme_get_me_mask(void) { return 0; } + #define __bss_decrypted #endif /* CONFIG_AMD_MEM_ENCRYPT */ @@ -105,11 +113,6 @@ void add_encrypt_protection_map(void); extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[]; -static inline u64 sme_get_me_mask(void) -{ - return sme_me_mask; -} - #endif /* __ASSEMBLY__ */ #endif /* __X86_MEM_ENCRYPT_H__ */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index ec955ab2ff034aba076ac56cf42a194974c51fa5..681e8401b8a351736b41bcfd14dfe0d70bdb01db 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -30,6 +30,7 @@ #define _EFER_SVME 12 /* Enable virtualization */ #define _EFER_LMSLE 13 /* Long Mode Segment Limit Enable */ #define _EFER_FFXSR 14 /* Enable Fast FXSAVE/FXRSTOR */ +#define _EFER_AUTOIBRS 21 /* Enable Automatic IBRS */ #define EFER_SCE (1<<_EFER_SCE) #define EFER_LME (1<<_EFER_LME) @@ -38,6 +39,7 @@ #define EFER_SVME (1<<_EFER_SVME) #define EFER_LMSLE (1<<_EFER_LMSLE) #define EFER_FFXSR (1<<_EFER_FFXSR) +#define EFER_AUTOIBRS (1<<_EFER_AUTOIBRS) /* Intel MSRs. Some also available on other CPUs */ @@ -53,10 +55,13 @@ #define SPEC_CTRL_SSBD BIT(SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ #define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */ #define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT) +#define SPEC_CTRL_BHI_DIS_S_SHIFT 10 /* Disable Branch History Injection behavior */ +#define SPEC_CTRL_BHI_DIS_S BIT(SPEC_CTRL_BHI_DIS_S_SHIFT) /* A mask for bits which the kernel toggles when controlling mitigations */ #define SPEC_CTRL_MITIGATIONS_MASK (SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \ - | SPEC_CTRL_RRSBA_DIS_S) + | SPEC_CTRL_RRSBA_DIS_S \ + | SPEC_CTRL_BHI_DIS_S) #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ @@ -155,6 +160,10 @@ * are restricted to targets in * kernel. */ +#define ARCH_CAP_BHI_NO BIT(20) /* + * CPU is not affected by Branch + * History Injection. + */ #define ARCH_CAP_PBRSB_NO BIT(24) /* * Not susceptible to Post-Barrier * Return Stack Buffer Predictions. @@ -168,6 +177,14 @@ * CPU is not vulnerable to Gather * Data Sampling (GDS). */ +#define ARCH_CAP_RFDS_NO BIT(27) /* + * Not susceptible to Register + * File Data Sampling. + */ +#define ARCH_CAP_RFDS_CLEAR BIT(28) /* + * VERW clears CPU Register + * File. + */ #define ARCH_CAP_XAPIC_DISABLE BIT(21) /* * IA32_XAPIC_DISABLE_STATUS MSR diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 2f123d4fb85b5bf86c9953dc8bc4c75e44009417..1e481d308e188bf06d363ff13a8de56d38b77ac7 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -167,11 +167,20 @@ .Lskip_rsb_\@: .endm +/* + * The CALL to srso_alias_untrain_ret() must be patched in directly at + * the spot where untraining must be done, ie., srso_alias_untrain_ret() + * must be the target of a CALL instruction instead of indirectly + * jumping to a wrapper which then calls it. Therefore, this macro is + * called outside of __UNTRAIN_RET below, for the time being, before the + * kernel can support nested alternatives with arbitrary nesting. + */ +.macro CALL_UNTRAIN_RET #ifdef CONFIG_CPU_UNRET_ENTRY -#define CALL_UNTRAIN_RET "call entry_untrain_ret" -#else -#define CALL_UNTRAIN_RET "" + ALTERNATIVE_2 "", "call entry_untrain_ret", X86_FEATURE_UNRET, \ + "call srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS #endif +.endm /* * Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the @@ -188,12 +197,37 @@ #if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \ defined(CONFIG_CPU_SRSO) ANNOTATE_UNRET_END - ALTERNATIVE_2 "", \ - CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \ - "call entry_ibpb", X86_FEATURE_ENTRY_IBPB + CALL_UNTRAIN_RET + ALTERNATIVE "", "call entry_ibpb", X86_FEATURE_ENTRY_IBPB #endif .endm +/* + * Macro to execute VERW instruction that mitigate transient data sampling + * attacks such as MDS. On affected systems a microcode update overloaded VERW + * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF. + * + * Note: Only the memory operand variant of VERW clears the CPU buffers. + */ +.macro CLEAR_CPU_BUFFERS + ALTERNATIVE "jmp .Lskip_verw_\@", "", X86_FEATURE_CLEAR_CPU_BUF + verw _ASM_RIP(mds_verw_sel) +.Lskip_verw_\@: +.endm + +#ifdef CONFIG_X86_64 +.macro CLEAR_BRANCH_HISTORY + ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP +.endm + +.macro CLEAR_BRANCH_HISTORY_VMEXIT + ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT +.endm +#else +#define CLEAR_BRANCH_HISTORY +#define CLEAR_BRANCH_HISTORY_VMEXIT +#endif + #else /* __ASSEMBLY__ */ #define ANNOTATE_RETPOLINE_SAFE \ @@ -222,6 +256,12 @@ extern void srso_alias_untrain_ret(void); extern void entry_untrain_ret(void); extern void entry_ibpb(void); +#ifdef CONFIG_X86_64 +extern void clear_bhb_loop(void); +#endif + +extern void (*x86_return_thunk)(void); + #ifdef CONFIG_RETPOLINE #define GEN(reg) \ @@ -366,13 +406,14 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); -DECLARE_STATIC_KEY_FALSE(mds_user_clear); DECLARE_STATIC_KEY_FALSE(mds_idle_clear); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear); +extern u16 mds_verw_sel; + #include /** @@ -398,17 +439,6 @@ static __always_inline void mds_clear_cpu_buffers(void) asm volatile("verw %[ds]" : : [ds] "m" (ds) : "cc"); } -/** - * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability - * - * Clear CPU buffers if the corresponding static key is enabled - */ -static __always_inline void mds_user_clear_cpu_buffers(void) -{ - if (static_branch_likely(&mds_user_clear)) - mds_clear_cpu_buffers(); -} - /** * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability * diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index a506a411474d4ad0213d1cdfb64fe6598ab1f9ca..86bd4311daf8a5046e5fa4cb71979535667a2e3d 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -11,20 +11,14 @@ #define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE-1)) -#define PMD_PAGE_SIZE (_AC(1, UL) << PMD_SHIFT) -#define PMD_PAGE_MASK (~(PMD_PAGE_SIZE-1)) - -#define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT) -#define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1)) - #define __VIRTUAL_MASK ((1UL << __VIRTUAL_MASK_SHIFT) - 1) -/* Cast *PAGE_MASK to a signed type so that it is sign-extended if +/* Cast P*D_MASK to a signed type so that it is sign-extended if virtual addresses are 32-bits but physical addresses are larger (ie, 32-bit PAE). */ #define PHYSICAL_PAGE_MASK (((signed long)PAGE_MASK) & __PHYSICAL_MASK) -#define PHYSICAL_PMD_PAGE_MASK (((signed long)PMD_PAGE_MASK) & __PHYSICAL_MASK) -#define PHYSICAL_PUD_PAGE_MASK (((signed long)PUD_PAGE_MASK) & __PHYSICAL_MASK) +#define PHYSICAL_PMD_PAGE_MASK (((signed long)PMD_MASK) & __PHYSICAL_MASK) +#define PHYSICAL_PUD_PAGE_MASK (((signed long)PUD_MASK) & __PHYSICAL_MASK) #define HPAGE_SHIFT PMD_SHIFT #define HPAGE_SIZE (_AC(1,UL) << HPAGE_SHIFT) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index f6116b66f289274aa45e813ccaadb710413298a0..f0b9b37c4609beb32b979c60419102d2fbb739ba 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -127,7 +127,7 @@ */ #define _COMMON_PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY |\ - _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_ENC | \ + _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_CC | \ _PAGE_UFFD_WP) #define _PAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PAT) #define _HPAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_PAT_LARGE) @@ -153,6 +153,7 @@ enum page_cache_mode { }; #endif +#define _PAGE_CC (_AT(pteval_t, cc_mask)) #define _PAGE_ENC (_AT(pteval_t, sme_me_mask)) #define _PAGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT) diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index 7ba1726b71c7b8bfc95888dc78508998bba263fe..e9187ddd3d1fdc61fff087b0ea3b8b9b0ff33ac3 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -99,6 +99,7 @@ #define REQUIRED_MASK18 0 #define REQUIRED_MASK19 0 #define REQUIRED_MASK20 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define REQUIRED_MASK21 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h index 7fa6112164172d3fff1a8b55dc6944f575d1b567..1919ccf493cd15438d10a234a361e189b28b234a 100644 --- a/arch/x86/include/asm/rmwcc.h +++ b/arch/x86/include/asm/rmwcc.h @@ -18,7 +18,7 @@ #define __GEN_RMWcc(fullop, _var, cc, clobbers, ...) \ ({ \ bool c = false; \ - asm_volatile_goto (fullop "; j" #cc " %l[cc_label]" \ + asm goto (fullop "; j" #cc " %l[cc_label]" \ : : [var] "m" (_var), ## __VA_ARGS__ \ : clobbers : cc_label); \ if (0) { \ diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 7ca5c9ec8b52e20ba1a2ec2774c5ef3e2de05d65..bcac2e53d50bba5e1319476739b504944e082558 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -157,6 +157,7 @@ static __always_inline void sev_es_nmi_complete(void) __sev_es_nmi_complete(); } extern int __init sev_es_efi_map_ghcbs(pgd_t *pgd); +extern void sev_enable(struct boot_params *bp); static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs) { @@ -191,23 +192,26 @@ static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) struct snp_guest_request_ioctl; void setup_ghcb(void); -void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, - unsigned long npages); -void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, - unsigned long npages); -void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op); +void early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, + unsigned long npages); +void early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, + unsigned long npages); void snp_set_memory_shared(unsigned long vaddr, unsigned long npages); void snp_set_memory_private(unsigned long vaddr, unsigned long npages); void snp_set_wakeup_secondary_cpu(void); bool snp_init(struct boot_params *bp); -void __init __noreturn snp_abort(void); +void __noreturn snp_abort(void); +void snp_dmi_setup(void); int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio); +u64 snp_get_unsupported_features(u64 status); +u64 sev_get_status(void); #else static inline void sev_es_ist_enter(struct pt_regs *regs) { } static inline void sev_es_ist_exit(void) { } static inline int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { return 0; } static inline void sev_es_nmi_complete(void) { } static inline int sev_es_efi_map_ghcbs(pgd_t *pgd) { return 0; } +static inline void sev_enable(struct boot_params *bp) { } static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) { return 0; } static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs) { return 0; } static inline void setup_ghcb(void) { } @@ -215,16 +219,19 @@ static inline void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned long npages) { } static inline void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, unsigned long npages) { } -static inline void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) { } static inline void snp_set_memory_shared(unsigned long vaddr, unsigned long npages) { } static inline void snp_set_memory_private(unsigned long vaddr, unsigned long npages) { } static inline void snp_set_wakeup_secondary_cpu(void) { } static inline bool snp_init(struct boot_params *bp) { return false; } static inline void snp_abort(void) { } +static inline void snp_dmi_setup(void) { } static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio) { return -ENOTTY; } + +static inline u64 snp_get_unsupported_features(u64 status) { return 0; } +static inline u64 sev_get_status(void) { return 0; } #endif #endif diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index a800abb1a99255b7ece0f95f2adc9953303da532..d8416b3bf832e420357a4a41a22052889d52852c 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -12,11 +12,6 @@ /* image of the saved processor state */ struct saved_context { - /* - * On x86_32, all segment registers except gs are saved at kernel - * entry in pt_regs. - */ - u16 gs; unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; struct saved_msrs saved_msrs; @@ -27,6 +22,11 @@ struct saved_context { unsigned long tr; unsigned long safety; unsigned long return_address; + /* + * On x86_32, all segment registers except gs are saved at kernel + * entry in pt_regs. + */ + u16 gs; bool misc_enable_saved; } __attribute__((packed)); diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 5b85987a5e97c3d350636b2a3d72ed86f6e589e3..2725a4502321bb7baf7feb48a4cebb2cbfa6b680 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -16,19 +16,17 @@ #include /* for TS_COMPAT */ #include +/* This is used purely for kernel/trace/trace_syscalls.c */ typedef long (*sys_call_ptr_t)(const struct pt_regs *); extern const sys_call_ptr_t sys_call_table[]; -#if defined(CONFIG_X86_32) -#define ia32_sys_call_table sys_call_table -#else /* * These may not exist, but still put the prototypes in so we * can use IS_ENABLED(). */ -extern const sys_call_ptr_t ia32_sys_call_table[]; -extern const sys_call_ptr_t x32_sys_call_table[]; -#endif +extern long ia32_sys_call(const struct pt_regs *, unsigned int nr); +extern long x32_sys_call(const struct pt_regs *, unsigned int nr); +extern long x64_sys_call(const struct pt_regs *, unsigned int nr); /* * Only the low 32 bits of orig_ax are meaningful, so we return int. @@ -129,6 +127,7 @@ static inline int syscall_get_arch(struct task_struct *task) void do_syscall_64(struct pt_regs *regs, int nr); void do_int80_syscall_32(struct pt_regs *regs); long do_fast_syscall_32(struct pt_regs *regs); +void do_int80_emulation(struct pt_regs *regs); #endif /* CONFIG_X86_32 */ diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 6ca0c661cb637ce82805e970d900583fc0460be1..c638535eedd556a4c989d924c64d75b155781e4a 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -155,7 +155,7 @@ extern int __get_user_bad(void); #ifdef CONFIG_X86_32 #define __put_user_goto_u64(x, addr, label) \ - asm_volatile_goto("\n" \ + asm goto("\n" \ "1: movl %%eax,0(%1)\n" \ "2: movl %%edx,4(%1)\n" \ _ASM_EXTABLE_UA(1b, %l2) \ @@ -317,7 +317,7 @@ do { \ } while (0) #define __get_user_asm(x, addr, itype, ltype, label) \ - asm_volatile_goto("\n" \ + asm_goto_output("\n" \ "1: mov"itype" %[umem],%[output]\n" \ _ASM_EXTABLE_UA(1b, %l2) \ : [output] ltype(x) \ @@ -397,7 +397,7 @@ do { \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ - asm_volatile_goto("\n" \ + asm_goto_output("\n" \ "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ _ASM_EXTABLE_UA(1b, %l[label]) \ : CC_OUT(z) (success), \ @@ -416,7 +416,7 @@ do { \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ - asm_volatile_goto("\n" \ + asm_goto_output("\n" \ "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ _ASM_EXTABLE_UA(1b, %l[label]) \ : CC_OUT(z) (success), \ @@ -499,7 +499,7 @@ struct __large_struct { unsigned long buf[100]; }; * aliasing issues. */ #define __put_user_goto(x, addr, itype, ltype, label) \ - asm_volatile_goto("\n" \ + asm goto("\n" \ "1: mov"itype" %0,%1\n" \ _ASM_EXTABLE_UA(1b, %l2) \ : : ltype(x), "m" (__m(addr)) \ diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h index 6c2e3ff3cb28f9e19440301fd8de8bc38b466852..724ce44809ed251fa78f37e9227c657eb11c0aba 100644 --- a/arch/x86/include/asm/virtext.h +++ b/arch/x86/include/asm/virtext.h @@ -43,9 +43,9 @@ static inline int cpu_has_vmx(void) */ static inline int cpu_vmxoff(void) { - asm_volatile_goto("1: vmxoff\n\t" - _ASM_EXTABLE(1b, %l[fault]) - ::: "cc", "memory" : fault); + asm goto("1: vmxoff\n\t" + _ASM_EXTABLE(1b, %l[fault]) + ::: "cc", "memory" : fault); cr4_clear_bits(X86_CR4_VMXE); return 0; @@ -129,9 +129,9 @@ static inline void cpu_svm_disable(void) * case, GIF must already be set, otherwise the NMI would have * been blocked, so just eat the fault. */ - asm_volatile_goto("1: stgi\n\t" - _ASM_EXTABLE(1b, %l[fault]) - ::: "memory" : fault); + asm goto("1: stgi\n\t" + _ASM_EXTABLE(1b, %l[fault]) + ::: "memory" : fault); fault: wrmsrl(MSR_EFER, efer & ~EFER_SVME); } diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index ab60a71a8dcb98e62bccf3c045066df8f42f30f4..472f0263dbc6129c30636f149b94d5828ac300c6 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -4,6 +4,7 @@ #include #include +#include #ifdef CONFIG_X86_VSYSCALL_EMULATION extern void map_vsyscall(void); @@ -24,4 +25,13 @@ static inline bool emulate_vsyscall(unsigned long error_code, } #endif +/* + * The (legacy) vsyscall page is the long page in the kernel portion + * of the address space that has user-accessible permissions. + */ +static inline bool is_vsyscall_vaddr(unsigned long vaddr) +{ + return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR); +} + #endif /* _ASM_X86_VSYSCALL_H */ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 034e62838b284b430e38ce845349c105dc4bcdbe..c3e910b1d5a252cb1859cbeb87bdd6387a3620ca 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -30,12 +30,13 @@ struct x86_init_mpparse { * @reserve_resources: reserve the standard resources for the * platform * @memory_setup: platform specific memory setup - * + * @dmi_setup: platform specific DMI setup */ struct x86_init_resources { void (*probe_roms)(void); void (*reserve_resources)(void); char *(*memory_setup)(void); + void (*dmi_setup)(void); }; /** diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c index 8d8752b44f11395298a40acce79de2027614248b..ff8f25faca3dd158ca50f91728332ba6b0b06454 100644 --- a/arch/x86/kernel/acpi/cppc.c +++ b/arch/x86/kernel/acpi/cppc.c @@ -20,7 +20,7 @@ bool cpc_supported_by_cpu(void) (boot_cpu_data.x86_model >= 0x20 && boot_cpu_data.x86_model <= 0x2f))) return true; else if (boot_cpu_data.x86 == 0x17 && - boot_cpu_data.x86_model >= 0x70 && boot_cpu_data.x86_model <= 0x7f) + boot_cpu_data.x86_model >= 0x30 && boot_cpu_data.x86_model <= 0x7f) return true; return boot_cpu_has(X86_FEATURE_CPPC); } diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 6b8c93989aa312805ad4e7fe631f785977c97db4..69f85e2746119665a9e8169ad10229b627008c64 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -536,6 +536,7 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) } #ifdef CONFIG_RETHUNK + /* * Rewrite the compiler generated return thunk tail-calls. * @@ -551,14 +552,18 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes) { int i = 0; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) - return -1; + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) { + if (x86_return_thunk == __x86_return_thunk) + return -1; - bytes[i++] = RET_INSN_OPCODE; + i = JMP32_INSN_SIZE; + __text_gen_insn(bytes, JMP32_INSN_OPCODE, addr, x86_return_thunk, i); + } else { + bytes[i++] = RET_INSN_OPCODE; + } for (; i < insn->length;) bytes[i++] = INT3_INSN_OPCODE; - return i; } diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index 19a0207e529fe33f6d340ae36a6f5fcbf60ea475..56a917df410d30b49ed3dedc709b32f8c34decfd 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -504,7 +504,7 @@ static __init unsigned long check_iommu_size(unsigned long aper, u64 aper_size) } a = aper + iommu_size; - iommu_size -= round_up(a, PMD_PAGE_SIZE) - a; + iommu_size -= round_up(a, PMD_SIZE) - a; if (iommu_size < 64*1024*1024) { pr_warn("PCI-DMA: Warning: Small IOMMU %luMB." diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 77055711005187c10c9b973f0df4ca27ac5b772d..e1672cc77c65f29723bd3a249ee069e6771d5837 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1760,11 +1760,11 @@ static int x2apic_state; static bool x2apic_hw_locked(void) { - u64 ia32_cap; + u64 x86_arch_cap_msr; u64 msr; - ia32_cap = x86_read_arch_cap_msr(); - if (ia32_cap & ARCH_CAP_XAPIC_DISABLE) { + x86_arch_cap_msr = x86_read_arch_cap_msr(); + if (x86_arch_cap_msr & ARCH_CAP_XAPIC_DISABLE) { rdmsrl(MSR_IA32_XAPIC_DISABLE_STATUS, msr); return (msr & LEGACY_XAPIC_DISABLED); } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index c1d09c8844d67b6e81c8ae26b5debbc4e4810fd9..425092806f8fe0abcc51a3e481880fff60a04f77 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -997,11 +997,11 @@ static bool cpu_has_zenbleed_microcode(void) u32 good_rev = 0; switch (boot_cpu_data.x86_model) { - case 0x30 ... 0x3f: good_rev = 0x0830107a; break; - case 0x60 ... 0x67: good_rev = 0x0860010b; break; - case 0x68 ... 0x6f: good_rev = 0x08608105; break; - case 0x70 ... 0x7f: good_rev = 0x08701032; break; - case 0xa0 ... 0xaf: good_rev = 0x08a00008; break; + case 0x30 ... 0x3f: good_rev = 0x0830107b; break; + case 0x60 ... 0x67: good_rev = 0x0860010c; break; + case 0x68 ... 0x6f: good_rev = 0x08608107; break; + case 0x70 ... 0x7f: good_rev = 0x08701033; break; + case 0xa0 ... 0xaf: good_rev = 0x08a00009; break; default: return false; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 13dffc43ded020ce9e24c02ea8c8fed0eb2bcd3b..3f38592ec77130fff75afb072672547eb2940695 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -60,6 +60,8 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_current); u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB; EXPORT_SYMBOL_GPL(x86_pred_cmd); +static u64 __ro_after_init x86_arch_cap_msr; + static DEFINE_MUTEX(spec_ctrl_mutex); void (*x86_return_thunk)(void) __ro_after_init = &__x86_return_thunk; @@ -110,9 +112,6 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); /* Control unconditional IBPB in switch_mm() */ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb); -/* Control MDS CPU buffer clear before returning to user space */ -DEFINE_STATIC_KEY_FALSE(mds_user_clear); -EXPORT_SYMBOL_GPL(mds_user_clear); /* Control MDS CPU buffer clear before idling (halt, mwait) */ DEFINE_STATIC_KEY_FALSE(mds_idle_clear); EXPORT_SYMBOL_GPL(mds_idle_clear); @@ -146,6 +145,8 @@ void __init cpu_select_mitigations(void) x86_spec_ctrl_base &= ~SPEC_CTRL_MITIGATIONS_MASK; } + x86_arch_cap_msr = x86_read_arch_cap_msr(); + /* Select the proper CPU mitigations before patching alternatives: */ spectre_v1_select_mitigation(); spectre_v2_select_mitigation(); @@ -251,7 +252,7 @@ static void __init mds_select_mitigation(void) if (!boot_cpu_has(X86_FEATURE_MD_CLEAR)) mds_mitigation = MDS_MITIGATION_VMWERV; - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) && (mds_nosmt || cpu_mitigations_auto_nosmt())) @@ -303,8 +304,6 @@ static const char * const taa_strings[] = { static void __init taa_select_mitigation(void) { - u64 ia32_cap; - if (!boot_cpu_has_bug(X86_BUG_TAA)) { taa_mitigation = TAA_MITIGATION_OFF; return; @@ -343,9 +342,8 @@ static void __init taa_select_mitigation(void) * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode * update is required. */ - ia32_cap = x86_read_arch_cap_msr(); - if ( (ia32_cap & ARCH_CAP_MDS_NO) && - !(ia32_cap & ARCH_CAP_TSX_CTRL_MSR)) + if ( (x86_arch_cap_msr & ARCH_CAP_MDS_NO) && + !(x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR)) taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; /* @@ -355,7 +353,7 @@ static void __init taa_select_mitigation(void) * For guests that can't determine whether the correct microcode is * present on host, enable the mitigation for UCODE_NEEDED as well. */ - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); if (taa_nosmt || cpu_mitigations_auto_nosmt()) cpu_smt_disable(false); @@ -403,8 +401,6 @@ static const char * const mmio_strings[] = { static void __init mmio_select_mitigation(void) { - u64 ia32_cap; - if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) || boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN) || cpu_mitigations_off()) { @@ -415,15 +411,20 @@ static void __init mmio_select_mitigation(void) if (mmio_mitigation == MMIO_MITIGATION_OFF) return; - ia32_cap = x86_read_arch_cap_msr(); - /* * Enable CPU buffer clear mitigation for host and VMM, if also affected * by MDS or TAA. Otherwise, enable mitigation for VMM only. */ if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM))) - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + + /* + * X86_FEATURE_CLEAR_CPU_BUF could be enabled by other VERW based + * mitigations, disable KVM-only mitigation in that case. + */ + if (boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF)) + static_branch_disable(&mmio_stale_data_clear); else static_branch_enable(&mmio_stale_data_clear); @@ -432,7 +433,7 @@ static void __init mmio_select_mitigation(void) * be propagated to uncore buffers, clearing the Fill buffers on idle * is required irrespective of SMT state. */ - if (!(ia32_cap & ARCH_CAP_FBSDP_NO)) + if (!(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) static_branch_enable(&mds_idle_clear); /* @@ -442,10 +443,10 @@ static void __init mmio_select_mitigation(void) * FB_CLEAR or by the presence of both MD_CLEAR and L1D_FLUSH on MDS * affected systems. */ - if ((ia32_cap & ARCH_CAP_FB_CLEAR) || + if ((x86_arch_cap_msr & ARCH_CAP_FB_CLEAR) || (boot_cpu_has(X86_FEATURE_MD_CLEAR) && boot_cpu_has(X86_FEATURE_FLUSH_L1D) && - !(ia32_cap & ARCH_CAP_MDS_NO))) + !(x86_arch_cap_msr & ARCH_CAP_MDS_NO))) mmio_mitigation = MMIO_MITIGATION_VERW; else mmio_mitigation = MMIO_MITIGATION_UCODE_NEEDED; @@ -475,6 +476,57 @@ static int __init mmio_stale_data_parse_cmdline(char *str) } early_param("mmio_stale_data", mmio_stale_data_parse_cmdline); +#undef pr_fmt +#define pr_fmt(fmt) "Register File Data Sampling: " fmt + +enum rfds_mitigations { + RFDS_MITIGATION_OFF, + RFDS_MITIGATION_VERW, + RFDS_MITIGATION_UCODE_NEEDED, +}; + +/* Default mitigation for Register File Data Sampling */ +static enum rfds_mitigations rfds_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_RFDS) ? RFDS_MITIGATION_VERW : RFDS_MITIGATION_OFF; + +static const char * const rfds_strings[] = { + [RFDS_MITIGATION_OFF] = "Vulnerable", + [RFDS_MITIGATION_VERW] = "Mitigation: Clear Register File", + [RFDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", +}; + +static void __init rfds_select_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_RFDS) || cpu_mitigations_off()) { + rfds_mitigation = RFDS_MITIGATION_OFF; + return; + } + if (rfds_mitigation == RFDS_MITIGATION_OFF) + return; + + if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR) + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + else + rfds_mitigation = RFDS_MITIGATION_UCODE_NEEDED; +} + +static __init int rfds_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!boot_cpu_has_bug(X86_BUG_RFDS)) + return 0; + + if (!strcmp(str, "off")) + rfds_mitigation = RFDS_MITIGATION_OFF; + else if (!strcmp(str, "on")) + rfds_mitigation = RFDS_MITIGATION_VERW; + + return 0; +} +early_param("reg_file_data_sampling", rfds_parse_cmdline); + #undef pr_fmt #define pr_fmt(fmt) "" fmt @@ -483,12 +535,12 @@ static void __init md_clear_update_mitigation(void) if (cpu_mitigations_off()) return; - if (!static_key_enabled(&mds_user_clear)) + if (!boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF)) goto out; /* - * mds_user_clear is now enabled. Update MDS, TAA and MMIO Stale Data - * mitigation, if necessary. + * X86_FEATURE_CLEAR_CPU_BUF is now enabled. Update MDS, TAA and MMIO + * Stale Data mitigation, if necessary. */ if (mds_mitigation == MDS_MITIGATION_OFF && boot_cpu_has_bug(X86_BUG_MDS)) { @@ -500,11 +552,19 @@ static void __init md_clear_update_mitigation(void) taa_mitigation = TAA_MITIGATION_VERW; taa_select_mitigation(); } - if (mmio_mitigation == MMIO_MITIGATION_OFF && - boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) { + /* + * MMIO_MITIGATION_OFF is not checked here so that mmio_stale_data_clear + * gets updated correctly as per X86_FEATURE_CLEAR_CPU_BUF state. + */ + if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) { mmio_mitigation = MMIO_MITIGATION_VERW; mmio_select_mitigation(); } + if (rfds_mitigation == RFDS_MITIGATION_OFF && + boot_cpu_has_bug(X86_BUG_RFDS)) { + rfds_mitigation = RFDS_MITIGATION_VERW; + rfds_select_mitigation(); + } out: if (boot_cpu_has_bug(X86_BUG_MDS)) pr_info("MDS: %s\n", mds_strings[mds_mitigation]); @@ -514,6 +574,8 @@ out: pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]); else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) pr_info("MMIO Stale Data: Unknown: No mitigations\n"); + if (boot_cpu_has_bug(X86_BUG_RFDS)) + pr_info("Register File Data Sampling: %s\n", rfds_strings[rfds_mitigation]); } static void __init md_clear_select_mitigation(void) @@ -521,11 +583,12 @@ static void __init md_clear_select_mitigation(void) mds_select_mitigation(); taa_select_mitigation(); mmio_select_mitigation(); + rfds_select_mitigation(); /* - * As MDS, TAA and MMIO Stale Data mitigations are inter-related, update - * and print their mitigation after MDS, TAA and MMIO Stale Data - * mitigation selection is done. + * As these mitigations are inter-related and rely on VERW instruction + * to clear the microarchitural buffers, update and print their status + * after mitigation selection is done for each of these vulnerabilities. */ md_clear_update_mitigation(); } @@ -592,8 +655,6 @@ void update_srbds_msr(void) static void __init srbds_select_mitigation(void) { - u64 ia32_cap; - if (!boot_cpu_has_bug(X86_BUG_SRBDS)) return; @@ -602,8 +663,7 @@ static void __init srbds_select_mitigation(void) * are only exposed to SRBDS when TSX is enabled or when CPU is affected * by Processor MMIO Stale Data vulnerability. */ - ia32_cap = x86_read_arch_cap_msr(); - if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) && + if ((x86_arch_cap_msr & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) && !boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) srbds_mitigation = SRBDS_MITIGATION_TSX_OFF; else if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) @@ -746,7 +806,7 @@ static void __init gds_select_mitigation(void) /* Will verify below that mitigation _can_ be disabled */ /* No microcode */ - if (!(x86_read_arch_cap_msr() & ARCH_CAP_GDS_CTRL)) { + if (!(x86_arch_cap_msr & ARCH_CAP_GDS_CTRL)) { if (gds_mitigation == GDS_MITIGATION_FORCE) { /* * This only needs to be done on the boot CPU so do it @@ -1288,19 +1348,21 @@ spectre_v2_user_select_mitigation(void) } /* - * If no STIBP, enhanced IBRS is enabled, or SMT impossible, STIBP + * If no STIBP, Intel enhanced IBRS is enabled, or SMT impossible, STIBP * is not required. * - * Enhanced IBRS also protects against cross-thread branch target + * Intel's Enhanced IBRS also protects against cross-thread branch target * injection in user-mode as the IBRS bit remains always set which * implicitly enables cross-thread protections. However, in legacy IBRS * mode, the IBRS bit is set only on kernel entry and cleared on return - * to userspace. This disables the implicit cross-thread protection, - * so allow for STIBP to be selected in that case. + * to userspace. AMD Automatic IBRS also does not protect userspace. + * These modes therefore disable the implicit cross-thread protection, + * so allow for STIBP to be selected in those cases. */ if (!boot_cpu_has(X86_FEATURE_STIBP) || !smt_possible || - spectre_v2_in_eibrs_mode(spectre_v2_enabled)) + (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && + !boot_cpu_has(X86_FEATURE_AUTOIBRS))) return; /* @@ -1330,9 +1392,9 @@ static const char * const spectre_v2_strings[] = { [SPECTRE_V2_NONE] = "Vulnerable", [SPECTRE_V2_RETPOLINE] = "Mitigation: Retpolines", [SPECTRE_V2_LFENCE] = "Mitigation: LFENCE", - [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced IBRS", - [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced IBRS + LFENCE", - [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced IBRS + Retpolines", + [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced / Automatic IBRS", + [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced / Automatic IBRS + LFENCE", + [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced / Automatic IBRS + Retpolines", [SPECTRE_V2_IBRS] = "Mitigation: IBRS", }; @@ -1401,7 +1463,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) cmd == SPECTRE_V2_CMD_EIBRS_LFENCE || cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) && !boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) { - pr_err("%s selected but CPU doesn't have eIBRS. Switching to AUTO select\n", + pr_err("%s selected but CPU doesn't have Enhanced or Automatic IBRS. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } @@ -1453,20 +1515,25 @@ static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void) return SPECTRE_V2_RETPOLINE; } +static bool __ro_after_init rrsba_disabled; + /* Disable in-kernel use of non-RSB RET predictors */ static void __init spec_ctrl_disable_kernel_rrsba(void) { - u64 ia32_cap; + if (rrsba_disabled) + return; - if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL)) + if (!(x86_arch_cap_msr & ARCH_CAP_RRSBA)) { + rrsba_disabled = true; return; + } - ia32_cap = x86_read_arch_cap_msr(); + if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL)) + return; - if (ia32_cap & ARCH_CAP_RRSBA) { - x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S; - update_spec_ctrl(x86_spec_ctrl_base); - } + x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S; + update_spec_ctrl(x86_spec_ctrl_base); + rrsba_disabled = true; } static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_mitigation mode) @@ -1516,6 +1583,74 @@ static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_ dump_stack(); } +/* + * Set BHI_DIS_S to prevent indirect branches in kernel to be influenced by + * branch history in userspace. Not needed if BHI_NO is set. + */ +static bool __init spec_ctrl_bhi_dis(void) +{ + if (!boot_cpu_has(X86_FEATURE_BHI_CTRL)) + return false; + + x86_spec_ctrl_base |= SPEC_CTRL_BHI_DIS_S; + update_spec_ctrl(x86_spec_ctrl_base); + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_HW); + + return true; +} + +enum bhi_mitigations { + BHI_MITIGATION_OFF, + BHI_MITIGATION_ON, +}; + +static enum bhi_mitigations bhi_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_SPECTRE_BHI) ? BHI_MITIGATION_ON : BHI_MITIGATION_OFF; + +static int __init spectre_bhi_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + bhi_mitigation = BHI_MITIGATION_OFF; + else if (!strcmp(str, "on")) + bhi_mitigation = BHI_MITIGATION_ON; + else + pr_err("Ignoring unknown spectre_bhi option (%s)", str); + + return 0; +} +early_param("spectre_bhi", spectre_bhi_parse_cmdline); + +static void __init bhi_select_mitigation(void) +{ + if (bhi_mitigation == BHI_MITIGATION_OFF) + return; + + /* Retpoline mitigates against BHI unless the CPU has RRSBA behavior */ + if (boot_cpu_has(X86_FEATURE_RETPOLINE) && + !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) { + spec_ctrl_disable_kernel_rrsba(); + if (rrsba_disabled) + return; + } + + if (spec_ctrl_bhi_dis()) + return; + + if (!IS_ENABLED(CONFIG_X86_64)) + return; + + /* Mitigate KVM by default */ + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT); + pr_info("Spectre BHI mitigation: SW BHB clearing on vm exit\n"); + + /* Mitigate syscalls when the mitigation is forced =on */ + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP); + pr_info("Spectre BHI mitigation: SW BHB clearing on syscall\n"); +} + static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -1586,8 +1721,12 @@ static void __init spectre_v2_select_mitigation(void) pr_err(SPECTRE_V2_EIBRS_EBPF_MSG); if (spectre_v2_in_ibrs_mode(mode)) { - x86_spec_ctrl_base |= SPEC_CTRL_IBRS; - update_spec_ctrl(x86_spec_ctrl_base); + if (boot_cpu_has(X86_FEATURE_AUTOIBRS)) { + msr_set_bit(MSR_EFER, _EFER_AUTOIBRS); + } else { + x86_spec_ctrl_base |= SPEC_CTRL_IBRS; + update_spec_ctrl(x86_spec_ctrl_base); + } } switch (mode) { @@ -1622,6 +1761,9 @@ static void __init spectre_v2_select_mitigation(void) mode == SPECTRE_V2_RETPOLINE) spec_ctrl_disable_kernel_rrsba(); + if (boot_cpu_has(X86_BUG_BHI)) + bhi_select_mitigation(); + spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); @@ -1671,8 +1813,8 @@ static void __init spectre_v2_select_mitigation(void) /* * Retpoline protects the kernel, but doesn't protect firmware. IBRS * and Enhanced IBRS protect firmware too, so enable IBRS around - * firmware calls only when IBRS / Enhanced IBRS aren't otherwise - * enabled. + * firmware calls only when IBRS / Enhanced / Automatic IBRS aren't + * otherwise enabled. * * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because * the user might select retpoline on the kernel command line and if @@ -1736,8 +1878,6 @@ static void update_indir_branch_cond(void) /* Update the static key controlling the MDS CPU buffer clear in idle */ static void update_mds_branch_idle(void) { - u64 ia32_cap = x86_read_arch_cap_msr(); - /* * Enable the idle clearing if SMT is active on CPUs which are * affected only by MSBDS and not any other MDS variant. @@ -1752,7 +1892,7 @@ static void update_mds_branch_idle(void) if (sched_smt_active()) { static_branch_enable(&mds_idle_clear); } else if (mmio_mitigation == MMIO_MITIGATION_OFF || - (ia32_cap & ARCH_CAP_FBSDP_NO)) { + (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) { static_branch_disable(&mds_idle_clear); } } @@ -2502,74 +2642,74 @@ static const char * const l1tf_vmx_states[] = { static ssize_t l1tf_show_state(char *buf) { if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) - return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); + return sysfs_emit(buf, "%s\n", L1TF_DEFAULT_MSG); if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_EPT_DISABLED || (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER && sched_smt_active())) { - return sprintf(buf, "%s; VMX: %s\n", L1TF_DEFAULT_MSG, - l1tf_vmx_states[l1tf_vmx_mitigation]); + return sysfs_emit(buf, "%s; VMX: %s\n", L1TF_DEFAULT_MSG, + l1tf_vmx_states[l1tf_vmx_mitigation]); } - return sprintf(buf, "%s; VMX: %s, SMT %s\n", L1TF_DEFAULT_MSG, - l1tf_vmx_states[l1tf_vmx_mitigation], - sched_smt_active() ? "vulnerable" : "disabled"); + return sysfs_emit(buf, "%s; VMX: %s, SMT %s\n", L1TF_DEFAULT_MSG, + l1tf_vmx_states[l1tf_vmx_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); } static ssize_t itlb_multihit_show_state(char *buf) { if (!boot_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || !boot_cpu_has(X86_FEATURE_VMX)) - return sprintf(buf, "KVM: Mitigation: VMX unsupported\n"); + return sysfs_emit(buf, "KVM: Mitigation: VMX unsupported\n"); else if (!(cr4_read_shadow() & X86_CR4_VMXE)) - return sprintf(buf, "KVM: Mitigation: VMX disabled\n"); + return sysfs_emit(buf, "KVM: Mitigation: VMX disabled\n"); else if (itlb_multihit_kvm_mitigation) - return sprintf(buf, "KVM: Mitigation: Split huge pages\n"); + return sysfs_emit(buf, "KVM: Mitigation: Split huge pages\n"); else - return sprintf(buf, "KVM: Vulnerable\n"); + return sysfs_emit(buf, "KVM: Vulnerable\n"); } #else static ssize_t l1tf_show_state(char *buf) { - return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); + return sysfs_emit(buf, "%s\n", L1TF_DEFAULT_MSG); } static ssize_t itlb_multihit_show_state(char *buf) { - return sprintf(buf, "Processor vulnerable\n"); + return sysfs_emit(buf, "Processor vulnerable\n"); } #endif static ssize_t mds_show_state(char *buf) { if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { - return sprintf(buf, "%s; SMT Host state unknown\n", - mds_strings[mds_mitigation]); + return sysfs_emit(buf, "%s; SMT Host state unknown\n", + mds_strings[mds_mitigation]); } if (boot_cpu_has(X86_BUG_MSBDS_ONLY)) { - return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], - (mds_mitigation == MDS_MITIGATION_OFF ? "vulnerable" : - sched_smt_active() ? "mitigated" : "disabled")); + return sysfs_emit(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], + (mds_mitigation == MDS_MITIGATION_OFF ? "vulnerable" : + sched_smt_active() ? "mitigated" : "disabled")); } - return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], - sched_smt_active() ? "vulnerable" : "disabled"); + return sysfs_emit(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); } static ssize_t tsx_async_abort_show_state(char *buf) { if ((taa_mitigation == TAA_MITIGATION_TSX_DISABLED) || (taa_mitigation == TAA_MITIGATION_OFF)) - return sprintf(buf, "%s\n", taa_strings[taa_mitigation]); + return sysfs_emit(buf, "%s\n", taa_strings[taa_mitigation]); if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { - return sprintf(buf, "%s; SMT Host state unknown\n", - taa_strings[taa_mitigation]); + return sysfs_emit(buf, "%s; SMT Host state unknown\n", + taa_strings[taa_mitigation]); } - return sprintf(buf, "%s; SMT %s\n", taa_strings[taa_mitigation], - sched_smt_active() ? "vulnerable" : "disabled"); + return sysfs_emit(buf, "%s; SMT %s\n", taa_strings[taa_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); } static ssize_t mmio_stale_data_show_state(char *buf) @@ -2589,22 +2729,28 @@ static ssize_t mmio_stale_data_show_state(char *buf) sched_smt_active() ? "vulnerable" : "disabled"); } +static ssize_t rfds_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]); +} + static char *stibp_state(void) { - if (spectre_v2_in_eibrs_mode(spectre_v2_enabled)) + if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && + !boot_cpu_has(X86_FEATURE_AUTOIBRS)) return ""; switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: - return ", STIBP: disabled"; + return "; STIBP: disabled"; case SPECTRE_V2_USER_STRICT: - return ", STIBP: forced"; + return "; STIBP: forced"; case SPECTRE_V2_USER_STRICT_PREFERRED: - return ", STIBP: always-on"; + return "; STIBP: always-on"; case SPECTRE_V2_USER_PRCTL: case SPECTRE_V2_USER_SECCOMP: if (static_key_enabled(&switch_to_cond_stibp)) - return ", STIBP: conditional"; + return "; STIBP: conditional"; } return ""; } @@ -2613,10 +2759,10 @@ static char *ibpb_state(void) { if (boot_cpu_has(X86_FEATURE_IBPB)) { if (static_key_enabled(&switch_mm_always_ibpb)) - return ", IBPB: always-on"; + return "; IBPB: always-on"; if (static_key_enabled(&switch_mm_cond_ibpb)) - return ", IBPB: conditional"; - return ", IBPB: disabled"; + return "; IBPB: conditional"; + return "; IBPB: disabled"; } return ""; } @@ -2626,58 +2772,77 @@ static char *pbrsb_eibrs_state(void) if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) { if (boot_cpu_has(X86_FEATURE_RSB_VMEXIT_LITE) || boot_cpu_has(X86_FEATURE_RSB_VMEXIT)) - return ", PBRSB-eIBRS: SW sequence"; + return "; PBRSB-eIBRS: SW sequence"; else - return ", PBRSB-eIBRS: Vulnerable"; + return "; PBRSB-eIBRS: Vulnerable"; } else { - return ", PBRSB-eIBRS: Not affected"; + return "; PBRSB-eIBRS: Not affected"; } } +static const char *spectre_bhi_state(void) +{ + if (!boot_cpu_has_bug(X86_BUG_BHI)) + return "; BHI: Not affected"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_HW)) + return "; BHI: BHI_DIS_S"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP)) + return "; BHI: SW loop, KVM: SW loop"; + else if (boot_cpu_has(X86_FEATURE_RETPOLINE) && + !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE) && + rrsba_disabled) + return "; BHI: Retpoline"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT)) + return "; BHI: Vulnerable, KVM: SW loop"; + + return "; BHI: Vulnerable"; +} + static ssize_t spectre_v2_show_state(char *buf) { if (spectre_v2_enabled == SPECTRE_V2_LFENCE) - return sprintf(buf, "Vulnerable: LFENCE\n"); + return sysfs_emit(buf, "Vulnerable: LFENCE\n"); if (spectre_v2_enabled == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled()) - return sprintf(buf, "Vulnerable: eIBRS with unprivileged eBPF\n"); + return sysfs_emit(buf, "Vulnerable: eIBRS with unprivileged eBPF\n"); if (sched_smt_active() && unprivileged_ebpf_enabled() && spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) - return sprintf(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); + return sysfs_emit(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); - return sprintf(buf, "%s%s%s%s%s%s%s\n", - spectre_v2_strings[spectre_v2_enabled], - ibpb_state(), - boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", - stibp_state(), - boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", - pbrsb_eibrs_state(), - spectre_v2_module_string()); + return sysfs_emit(buf, "%s%s%s%s%s%s%s%s\n", + spectre_v2_strings[spectre_v2_enabled], + ibpb_state(), + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? "; IBRS_FW" : "", + stibp_state(), + boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? "; RSB filling" : "", + pbrsb_eibrs_state(), + spectre_bhi_state(), + /* this should always be at the end */ + spectre_v2_module_string()); } static ssize_t srbds_show_state(char *buf) { - return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]); + return sysfs_emit(buf, "%s\n", srbds_strings[srbds_mitigation]); } static ssize_t retbleed_show_state(char *buf) { if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET || retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { - if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && - boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) - return sprintf(buf, "Vulnerable: untrained return thunk / IBPB on non-AMD based uarch\n"); + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) + return sysfs_emit(buf, "Vulnerable: untrained return thunk / IBPB on non-AMD based uarch\n"); - return sprintf(buf, "%s; SMT %s\n", - retbleed_strings[retbleed_mitigation], - !sched_smt_active() ? "disabled" : - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ? - "enabled with STIBP protection" : "vulnerable"); + return sysfs_emit(buf, "%s; SMT %s\n", retbleed_strings[retbleed_mitigation], + !sched_smt_active() ? "disabled" : + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ? + "enabled with STIBP protection" : "vulnerable"); } - return sprintf(buf, "%s\n", retbleed_strings[retbleed_mitigation]); + return sysfs_emit(buf, "%s\n", retbleed_strings[retbleed_mitigation]); } static ssize_t gds_show_state(char *buf) @@ -2699,26 +2864,26 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr char *buf, unsigned int bug) { if (!boot_cpu_has_bug(bug)) - return sprintf(buf, "Not affected\n"); + return sysfs_emit(buf, "Not affected\n"); switch (bug) { case X86_BUG_CPU_MELTDOWN: if (boot_cpu_has(X86_FEATURE_PTI)) - return sprintf(buf, "Mitigation: PTI\n"); + return sysfs_emit(buf, "Mitigation: PTI\n"); if (hypervisor_is_type(X86_HYPER_XEN_PV)) - return sprintf(buf, "Unknown (XEN PV detected, hypervisor mitigation required)\n"); + return sysfs_emit(buf, "Unknown (XEN PV detected, hypervisor mitigation required)\n"); break; case X86_BUG_SPECTRE_V1: - return sprintf(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]); + return sysfs_emit(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]); case X86_BUG_SPECTRE_V2: return spectre_v2_show_state(buf); case X86_BUG_SPEC_STORE_BYPASS: - return sprintf(buf, "%s\n", ssb_strings[ssb_mode]); + return sysfs_emit(buf, "%s\n", ssb_strings[ssb_mode]); case X86_BUG_L1TF: if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV)) @@ -2750,11 +2915,14 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_SRSO: return srso_show_state(buf); + case X86_BUG_RFDS: + return rfds_show_state(buf); + default: break; } - return sprintf(buf, "Vulnerable\n"); + return sysfs_emit(buf, "Vulnerable\n"); } ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) @@ -2824,4 +2992,9 @@ ssize_t cpu_show_spec_rstack_overflow(struct device *dev, struct device_attribut { return cpu_show_common(dev, attr, buf, X86_BUG_SRSO); } + +ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_RFDS); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 454cdf3418624effbf4ba1b1b7b918aec984c9ba..f2bc651c0dcd816e904ebbf087d3b14f87bcda83 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1144,6 +1144,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #define NO_SPECTRE_V2 BIT(8) #define NO_MMIO BIT(9) #define NO_EIBRS_PBRSB BIT(10) +#define NO_BHI BIT(11) #define VULNWL(vendor, family, model, whitelist) \ X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist) @@ -1206,18 +1207,18 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB), /* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI), + VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI), /* Zhaoxin Family 7 */ - VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), - VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), + VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI), + VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI), {} }; @@ -1248,6 +1249,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define SRSO BIT(5) /* CPU is affected by GDS */ #define GDS BIT(6) +/* CPU is affected by Register File Data Sampling */ +#define RFDS BIT(7) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1275,9 +1278,18 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(TIGERLAKE, X86_STEPPING_ANY, GDS), VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE_L, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE_P, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE_S, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE_N, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_D, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_PLUS, X86_STEPPING_ANY, RFDS), VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), @@ -1296,28 +1308,46 @@ static bool __init cpu_matches(const struct x86_cpu_id *table, unsigned long whi u64 x86_read_arch_cap_msr(void) { - u64 ia32_cap = 0; + u64 x86_arch_cap_msr = 0; if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, x86_arch_cap_msr); - return ia32_cap; + return x86_arch_cap_msr; } -static bool arch_cap_mmio_immune(u64 ia32_cap) +static bool arch_cap_mmio_immune(u64 x86_arch_cap_msr) { - return (ia32_cap & ARCH_CAP_FBSDP_NO && - ia32_cap & ARCH_CAP_PSDP_NO && - ia32_cap & ARCH_CAP_SBDR_SSDP_NO); + return (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO && + x86_arch_cap_msr & ARCH_CAP_PSDP_NO && + x86_arch_cap_msr & ARCH_CAP_SBDR_SSDP_NO); +} + +static bool __init vulnerable_to_rfds(u64 x86_arch_cap_msr) +{ + /* The "immunity" bit trumps everything else: */ + if (x86_arch_cap_msr & ARCH_CAP_RFDS_NO) + return false; + + /* + * VMMs set ARCH_CAP_RFDS_CLEAR for processors not in the blacklist to + * indicate that mitigation is needed because guest is running on a + * vulnerable hardware or may migrate to such hardware: + */ + if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR) + return true; + + /* Only consult the blacklist when there is no enumeration: */ + return cpu_matches(cpu_vuln_blacklist, RFDS); } static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { - u64 ia32_cap = x86_read_arch_cap_msr(); + u64 x86_arch_cap_msr = x86_read_arch_cap_msr(); /* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */ if (!cpu_matches(cpu_vuln_whitelist, NO_ITLB_MULTIHIT) && - !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO)) + !(x86_arch_cap_msr & ARCH_CAP_PSCHANGE_MC_NO)) setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT); if (cpu_matches(cpu_vuln_whitelist, NO_SPECULATION)) @@ -1329,15 +1359,23 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_SPECTRE_V2); if (!cpu_matches(cpu_vuln_whitelist, NO_SSB) && - !(ia32_cap & ARCH_CAP_SSB_NO) && + !(x86_arch_cap_msr & ARCH_CAP_SSB_NO) && !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); - if (ia32_cap & ARCH_CAP_IBRS_ALL) + /* + * AMD's AutoIBRS is equivalent to Intel's eIBRS - use the Intel feature + * flag and protect from vendor-specific bugs via the whitelist. + */ + if ((x86_arch_cap_msr & ARCH_CAP_IBRS_ALL) || cpu_has(c, X86_FEATURE_AUTOIBRS)) { setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); + if (!cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && + !(x86_arch_cap_msr & ARCH_CAP_PBRSB_NO)) + setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB); + } if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) && - !(ia32_cap & ARCH_CAP_MDS_NO)) { + !(x86_arch_cap_msr & ARCH_CAP_MDS_NO)) { setup_force_cpu_bug(X86_BUG_MDS); if (cpu_matches(cpu_vuln_whitelist, MSBDS_ONLY)) setup_force_cpu_bug(X86_BUG_MSBDS_ONLY); @@ -1356,9 +1394,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * TSX_CTRL check alone is not sufficient for cases when the microcode * update is not present or running as guest that don't get TSX_CTRL. */ - if (!(ia32_cap & ARCH_CAP_TAA_NO) && + if (!(x86_arch_cap_msr & ARCH_CAP_TAA_NO) && (cpu_has(c, X86_FEATURE_RTM) || - (ia32_cap & ARCH_CAP_TSX_CTRL_MSR))) + (x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR))) setup_force_cpu_bug(X86_BUG_TAA); /* @@ -1384,7 +1422,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * Set X86_BUG_MMIO_UNKNOWN for CPUs that are neither in the blacklist, * nor in the whitelist and also don't enumerate MSR ARCH_CAP MMIO bits. */ - if (!arch_cap_mmio_immune(ia32_cap)) { + if (!arch_cap_mmio_immune(x86_arch_cap_msr)) { if (cpu_matches(cpu_vuln_blacklist, MMIO)) setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA); else if (!cpu_matches(cpu_vuln_whitelist, NO_MMIO)) @@ -1392,15 +1430,10 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) } if (!cpu_has(c, X86_FEATURE_BTC_NO)) { - if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA)) + if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (x86_arch_cap_msr & ARCH_CAP_RSBA)) setup_force_cpu_bug(X86_BUG_RETBLEED); } - if (cpu_has(c, X86_FEATURE_IBRS_ENHANCED) && - !cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && - !(ia32_cap & ARCH_CAP_PBRSB_NO)) - setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB); - if (cpu_matches(cpu_vuln_blacklist, SMT_RSB)) setup_force_cpu_bug(X86_BUG_SMT_RSB); @@ -1410,7 +1443,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * disabling AVX2. The only way to do this in HW is to clear XCR0[2], * which means that AVX will be disabled. */ - if (cpu_matches(cpu_vuln_blacklist, GDS) && !(ia32_cap & ARCH_CAP_GDS_NO) && + if (cpu_matches(cpu_vuln_blacklist, GDS) && !(x86_arch_cap_msr & ARCH_CAP_GDS_NO) && boot_cpu_has(X86_FEATURE_AVX)) setup_force_cpu_bug(X86_BUG_GDS); @@ -1419,11 +1452,21 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_SRSO); } + if (vulnerable_to_rfds(x86_arch_cap_msr)) + setup_force_cpu_bug(X86_BUG_RFDS); + + /* When virtualized, eIBRS could be hidden, assume vulnerable */ + if (!(x86_arch_cap_msr & ARCH_CAP_BHI_NO) && + !cpu_matches(cpu_vuln_whitelist, NO_BHI) && + (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) || + boot_cpu_has(X86_FEATURE_HYPERVISOR))) + setup_force_cpu_bug(X86_BUG_BHI); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; /* Rogue Data Cache Load? No! */ - if (ia32_cap & ARCH_CAP_RDCL_NO) + if (x86_arch_cap_msr & ARCH_CAP_RDCL_NO) return; setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index c881bcafba7d702fce65f36c178c3f4a84aa98e9..9c19f40b1b2720a2818c57a9921ec01664e9d86f 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -44,7 +44,10 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_F16C, X86_FEATURE_XMM2, }, { X86_FEATURE_AES, X86_FEATURE_XMM2 }, { X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 }, + { X86_FEATURE_GFNI, X86_FEATURE_XMM2 }, { X86_FEATURE_FMA, X86_FEATURE_AVX }, + { X86_FEATURE_VAES, X86_FEATURE_AVX }, + { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX }, { X86_FEATURE_AVX2, X86_FEATURE_AVX, }, { X86_FEATURE_AVX512F, X86_FEATURE_AVX, }, { X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F }, @@ -56,9 +59,6 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL }, - { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL }, - { X86_FEATURE_VAES, X86_FEATURE_AVX512VL }, - { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F }, diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 42789965048339786387c0cb4691d62bedbc5b4d..32bd640170475128801bda38e1814109af666d9a 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -216,6 +216,90 @@ int intel_cpu_collect_info(struct ucode_cpu_info *uci) } EXPORT_SYMBOL_GPL(intel_cpu_collect_info); +#define MSR_IA32_TME_ACTIVATE 0x982 + +/* Helpers to access TME_ACTIVATE MSR */ +#define TME_ACTIVATE_LOCKED(x) (x & 0x1) +#define TME_ACTIVATE_ENABLED(x) (x & 0x2) + +#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ +#define TME_ACTIVATE_POLICY_AES_XTS_128 0 + +#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ + +#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ +#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 + +/* Values for mktme_status (SW only construct) */ +#define MKTME_ENABLED 0 +#define MKTME_DISABLED 1 +#define MKTME_UNINITIALIZED 2 +static int mktme_status = MKTME_UNINITIALIZED; + +static void detect_tme_early(struct cpuinfo_x86 *c) +{ + u64 tme_activate, tme_policy, tme_crypto_algs; + int keyid_bits = 0, nr_keyids = 0; + static u64 tme_activate_cpu0 = 0; + + rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); + + if (mktme_status != MKTME_UNINITIALIZED) { + if (tme_activate != tme_activate_cpu0) { + /* Broken BIOS? */ + pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); + pr_err_once("x86/tme: MKTME is not usable\n"); + mktme_status = MKTME_DISABLED; + + /* Proceed. We may need to exclude bits from x86_phys_bits. */ + } + } else { + tme_activate_cpu0 = tme_activate; + } + + if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { + pr_info_once("x86/tme: not enabled by BIOS\n"); + mktme_status = MKTME_DISABLED; + return; + } + + if (mktme_status != MKTME_UNINITIALIZED) + goto detect_keyid_bits; + + pr_info("x86/tme: enabled by BIOS\n"); + + tme_policy = TME_ACTIVATE_POLICY(tme_activate); + if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) + pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); + + tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); + if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { + pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", + tme_crypto_algs); + mktme_status = MKTME_DISABLED; + } +detect_keyid_bits: + keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); + nr_keyids = (1UL << keyid_bits) - 1; + if (nr_keyids) { + pr_info_once("x86/mktme: enabled by BIOS\n"); + pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); + } else { + pr_info_once("x86/mktme: disabled by BIOS\n"); + } + + if (mktme_status == MKTME_UNINITIALIZED) { + /* MKTME is usable */ + mktme_status = MKTME_ENABLED; + } + + /* + * KeyID bits effectively lower the number of physical address + * bits. Update cpuinfo_x86::x86_phys_bits accordingly. + */ + c->x86_phys_bits -= keyid_bits; +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -367,6 +451,13 @@ static void early_init_intel(struct cpuinfo_x86 *c) */ if (detect_extended_topology_early(c) < 0) detect_ht_early(c); + + /* + * Adjust the number of physical bits early because it affects the + * valid bits of the MTRR mask registers. + */ + if (cpu_has(c, X86_FEATURE_TME)) + detect_tme_early(c); } static void bsp_init_intel(struct cpuinfo_x86 *c) @@ -527,90 +618,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #endif } -#define MSR_IA32_TME_ACTIVATE 0x982 - -/* Helpers to access TME_ACTIVATE MSR */ -#define TME_ACTIVATE_LOCKED(x) (x & 0x1) -#define TME_ACTIVATE_ENABLED(x) (x & 0x2) - -#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ -#define TME_ACTIVATE_POLICY_AES_XTS_128 0 - -#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ - -#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ -#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 - -/* Values for mktme_status (SW only construct) */ -#define MKTME_ENABLED 0 -#define MKTME_DISABLED 1 -#define MKTME_UNINITIALIZED 2 -static int mktme_status = MKTME_UNINITIALIZED; - -static void detect_tme(struct cpuinfo_x86 *c) -{ - u64 tme_activate, tme_policy, tme_crypto_algs; - int keyid_bits = 0, nr_keyids = 0; - static u64 tme_activate_cpu0 = 0; - - rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); - - if (mktme_status != MKTME_UNINITIALIZED) { - if (tme_activate != tme_activate_cpu0) { - /* Broken BIOS? */ - pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); - pr_err_once("x86/tme: MKTME is not usable\n"); - mktme_status = MKTME_DISABLED; - - /* Proceed. We may need to exclude bits from x86_phys_bits. */ - } - } else { - tme_activate_cpu0 = tme_activate; - } - - if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { - pr_info_once("x86/tme: not enabled by BIOS\n"); - mktme_status = MKTME_DISABLED; - return; - } - - if (mktme_status != MKTME_UNINITIALIZED) - goto detect_keyid_bits; - - pr_info("x86/tme: enabled by BIOS\n"); - - tme_policy = TME_ACTIVATE_POLICY(tme_activate); - if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) - pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); - - tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); - if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { - pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", - tme_crypto_algs); - mktme_status = MKTME_DISABLED; - } -detect_keyid_bits: - keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); - nr_keyids = (1UL << keyid_bits) - 1; - if (nr_keyids) { - pr_info_once("x86/mktme: enabled by BIOS\n"); - pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); - } else { - pr_info_once("x86/mktme: disabled by BIOS\n"); - } - - if (mktme_status == MKTME_UNINITIALIZED) { - /* MKTME is usable */ - mktme_status = MKTME_ENABLED; - } - - /* - * KeyID bits effectively lower the number of physical address - * bits. Update cpuinfo_x86::x86_phys_bits accordingly. - */ - c->x86_phys_bits -= keyid_bits; -} - static void init_cpuid_fault(struct cpuinfo_x86 *c) { u64 msr; @@ -747,9 +754,6 @@ static void init_intel(struct cpuinfo_x86 *c) init_ia32_feat_ctl(c); - if (cpu_has(c, X86_FEATURE_TME)) - detect_tme(c); - init_intel_misc_features(c); split_lock_init(); diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index cad6ea1911e9bfcd3158d2ec14b3c9f830abc31b..359218bc1b34bd85af61586d2e1992e6f2b42dc7 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -2471,12 +2471,14 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr, return -EINVAL; b = &per_cpu(mce_banks_array, s->id)[bank]; - if (!b->init) return -ENODEV; b->ctl = new; + + mutex_lock(&mce_sysfs_mutex); mce_restart(); + mutex_unlock(&mce_sysfs_mutex); return size; } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 34d9e899e471e91533f8aaa7cdf4fe23ca86661b..9b039e9635e40c9d5e4a28f546944707418b23db 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -344,7 +344,7 @@ static void __init ms_hyperv_init_platform(void) /* Isolation VMs are unenlightened SEV-based VMs, thus this check: */ if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) { if (hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE) - cc_set_vendor(CC_VENDOR_HYPERV); + cc_vendor = CC_VENDOR_HYPERV; } } diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 0b5c6c76f6f7b500573b64d1ffc0bf29476b3d0d..4761d489a117ab07d252f15b61b840ed78035d9f 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -281,14 +281,10 @@ struct rftype { * struct mbm_state - status for each MBM counter in each domain * @prev_bw_bytes: Previous bytes value read for bandwidth calculation * @prev_bw: The most recent bandwidth in MBps - * @delta_bw: Difference between the current and previous bandwidth - * @delta_comp: Indicates whether to compute the delta_bw */ struct mbm_state { u64 prev_bw_bytes; u32 prev_bw; - u32 delta_bw; - bool delta_comp; }; /** diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 77538abeb72afe7b99736efbe552d8293bdd8b60..b9adb707750c696f811fc11c6c85c08c5eaa0627 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -428,9 +428,6 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr) cur_bw = bytes / SZ_1M; - if (m->delta_comp) - m->delta_bw = abs(cur_bw - m->prev_bw); - m->delta_comp = false; m->prev_bw = cur_bw; } @@ -508,11 +505,11 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) { u32 closid, rmid, cur_msr_val, new_msr_val; struct mbm_state *pmbm_data, *cmbm_data; - u32 cur_bw, delta_bw, user_bw; struct rdt_resource *r_mba; struct rdt_domain *dom_mba; struct list_head *head; struct rdtgroup *entry; + u32 cur_bw, user_bw; if (!is_mbm_local_enabled()) return; @@ -531,7 +528,6 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) cur_bw = pmbm_data->prev_bw; user_bw = dom_mba->mbps_val[closid]; - delta_bw = pmbm_data->delta_bw; /* MBA resource doesn't support CDP */ cur_msr_val = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE); @@ -543,49 +539,31 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) list_for_each_entry(entry, head, mon.crdtgrp_list) { cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid]; cur_bw += cmbm_data->prev_bw; - delta_bw += cmbm_data->delta_bw; } /* * Scale up/down the bandwidth linearly for the ctrl group. The * bandwidth step is the bandwidth granularity specified by the * hardware. - * - * The delta_bw is used when increasing the bandwidth so that we - * dont alternately increase and decrease the control values - * continuously. - * - * For ex: consider cur_bw = 90MBps, user_bw = 100MBps and if - * bandwidth step is 20MBps(> user_bw - cur_bw), we would keep - * switching between 90 and 110 continuously if we only check - * cur_bw < user_bw. + * Always increase throttling if current bandwidth is above the + * target set by user. + * But avoid thrashing up and down on every poll by checking + * whether a decrease in throttling is likely to push the group + * back over target. E.g. if currently throttling to 30% of bandwidth + * on a system with 10% granularity steps, check whether moving to + * 40% would go past the limit by multiplying current bandwidth by + * "(30 + 10) / 30". */ if (cur_msr_val > r_mba->membw.min_bw && user_bw < cur_bw) { new_msr_val = cur_msr_val - r_mba->membw.bw_gran; } else if (cur_msr_val < MAX_MBA_BW && - (user_bw > (cur_bw + delta_bw))) { + (user_bw > (cur_bw * (cur_msr_val + r_mba->membw.min_bw) / cur_msr_val))) { new_msr_val = cur_msr_val + r_mba->membw.bw_gran; } else { return; } resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val); - - /* - * Delta values are updated dynamically package wise for each - * rdtgrp every time the throttle MSR changes value. - * - * This is because (1)the increase in bandwidth is not perfectly - * linear and only "approximately" linear even when the hardware - * says it is linear.(2)Also since MBA is a core specific - * mechanism, the delta values vary based on number of cores used - * by the rdtgrp. - */ - pmbm_data->delta_comp = true; - list_for_each_entry(entry, head, mon.crdtgrp_list) { - cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid]; - cmbm_data->delta_comp = true; - } } static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index fc01f81f6e2a382b4daccdac85a9fe0e79d95fc2..28c357cf7c75ee04660416c13bdad14c4ce0fbc3 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -28,6 +28,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_INTEL_PPIN, CPUID_EBX, 0, 0x00000007, 1 }, { X86_FEATURE_RRSBA_CTRL, CPUID_EDX, 2, 0x00000007, 2 }, + { X86_FEATURE_BHI_CTRL, CPUID_EDX, 4, 0x00000007, 2 }, { X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 }, { X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 }, { X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 }, @@ -46,6 +47,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 }, { X86_FEATURE_PERFMON_V2, CPUID_EAX, 0, 0x80000022, 0 }, { X86_FEATURE_AMD_LBR_V2, CPUID_EAX, 1, 0x80000022, 0 }, + { X86_FEATURE_AMD_LBR_PMC_FREEZE, CPUID_EAX, 2, 0x80000022, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 9dac24680ff8ea1ffdb37aa1f957b7b8df7005c8..993734e96615a3bb1ae8c845739dbc722f8631c1 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1017,10 +1017,12 @@ void __init e820__reserve_setup_data(void) e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); /* - * SETUP_EFI and SETUP_IMA are supplied by kexec and do not need - * to be reserved. + * SETUP_EFI, SETUP_IMA and SETUP_RNG_SEED are supplied by + * kexec and do not need to be reserved. */ - if (data->type != SETUP_EFI && data->type != SETUP_IMA) + if (data->type != SETUP_EFI && + data->type != SETUP_IMA && + data->type != SETUP_RNG_SEED) e820__range_update_kexec(pa_data, sizeof(*data) + data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); diff --git a/arch/x86/kernel/eisa.c b/arch/x86/kernel/eisa.c index e963344b044902a78340be45c30e5634bfdb2566..53935b4d62e30560d806d2c70d8aee209ec9f9df 100644 --- a/arch/x86/kernel/eisa.c +++ b/arch/x86/kernel/eisa.c @@ -2,6 +2,7 @@ /* * EISA specific code */ +#include #include #include #include @@ -12,7 +13,7 @@ static __init int eisa_bus_probe(void) { void __iomem *p; - if (xen_pv_domain() && !xen_initial_domain()) + if ((xen_pv_domain() && !xen_initial_domain()) || cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) return 0; p = ioremap(0x0FFFD9, 4); diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 558076dbde5bfca582139f8de63bd9ffa1050d6f..247f2225aa9f36f0a0fef0a22ed921b4748a7de5 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -274,12 +274,13 @@ static int __restore_fpregs_from_user(void __user *buf, u64 ufeatures, * Attempt to restore the FPU registers directly from user memory. * Pagefaults are handled and any errors returned are fatal. */ -static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, - bool fx_only, unsigned int size) +static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only) { struct fpu *fpu = ¤t->thread.fpu; int ret; + /* Restore enabled features only. */ + xrestore &= fpu->fpstate->user_xfeatures; retry: fpregs_lock(); /* Ensure that XFD is up to date */ @@ -309,7 +310,7 @@ retry: if (ret != X86_TRAP_PF) return false; - if (!fault_in_readable(buf, size)) + if (!fault_in_readable(buf, fpu->fpstate->user_size)) goto retry; return false; } @@ -339,7 +340,6 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx, struct user_i387_ia32_struct env; bool success, fx_only = false; union fpregs_state *fpregs; - unsigned int state_size; u64 user_xfeatures = 0; if (use_xsave()) { @@ -349,17 +349,14 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx, return false; fx_only = !fx_sw_user.magic1; - state_size = fx_sw_user.xstate_size; user_xfeatures = fx_sw_user.xfeatures; } else { user_xfeatures = XFEATURE_MASK_FPSSE; - state_size = fpu->fpstate->user_size; } if (likely(!ia32_fxstate)) { /* Restore the FPU registers directly from user memory. */ - return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only, - state_size); + return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only); } /* diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index ebe698f8af73b5d15ef80bc27086042d61afecbd..2aa849705bb68484a052adc484b9370ddbef1f7b 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -177,10 +177,11 @@ void fpu__init_cpu_xstate(void) * Must happen after CR4 setup and before xsetbv() to allow KVM * lazy passthrough. Write independent of the dynamic state static * key as that does not work on the boot CPU. This also ensures - * that any stale state is wiped out from XFD. + * that any stale state is wiped out from XFD. Reset the per CPU + * xfd cache too. */ if (cpu_feature_enabled(X86_FEATURE_XFD)) - wrmsrl(MSR_IA32_XFD, init_fpstate.xfd); + xfd_set_state(init_fpstate.xfd); /* * XCR_XFEATURE_ENABLED_MASK (aka. XCR0) sets user features diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index 3518fb26d06b021144a4f8c1427ad8ee620cb78d..19ca623ffa2ac77204d9ffa47208d867a5dbb8da 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -148,20 +148,26 @@ static inline void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rs #endif #ifdef CONFIG_X86_64 +static inline void xfd_set_state(u64 xfd) +{ + wrmsrl(MSR_IA32_XFD, xfd); + __this_cpu_write(xfd_state, xfd); +} + static inline void xfd_update_state(struct fpstate *fpstate) { if (fpu_state_size_dynamic()) { u64 xfd = fpstate->xfd; - if (__this_cpu_read(xfd_state) != xfd) { - wrmsrl(MSR_IA32_XFD, xfd); - __this_cpu_write(xfd_state, xfd); - } + if (__this_cpu_read(xfd_state) != xfd) + xfd_set_state(xfd); } } extern int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu); #else +static inline void xfd_set_state(u64 xfd) { } + static inline void xfd_update_state(struct fpstate *fpstate) { } static inline int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu) { diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index e07234ec7e237a78d1d6b51d13de41992bc571ad..ec51ce713dea45deb89ef67ca85b50aceebd2370 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -361,7 +361,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) ip = trampoline + size; if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) - __text_gen_insn(ip, JMP32_INSN_OPCODE, ip, &__x86_return_thunk, JMP32_INSN_SIZE); + __text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE); else memcpy(ip, retq, sizeof(retq)); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 84adf12a76d3cd0862e07d437a028c5ae71bd1cc..4fae511b2e2b2495abec27adeca45f2e31626fc0 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -41,6 +41,7 @@ #include #include #include +#include /* * Manage page tables very early on. @@ -84,8 +85,6 @@ static struct desc_ptr startup_gdt_descr = { .address = 0, }; -#define __head __section(".head.text") - static void __head *fixup_pointer(void *ptr, unsigned long physaddr) { return ptr - (void *)_text + (void *)physaddr; @@ -203,7 +202,7 @@ unsigned long __head __startup_64(unsigned long physaddr, load_delta = physaddr - (unsigned long)(_text - __START_KERNEL_map); /* Is the address not 2M aligned? */ - if (load_delta & ~PMD_PAGE_MASK) + if (load_delta & ~PMD_MASK) for (;;); /* Include the SME encryption mask in the fixup value */ @@ -588,7 +587,7 @@ static void set_bringup_idt_handler(gate_desc *idt, int n, void *handler) } /* This runs while still in the direct mapping */ -static void startup_64_load_idt(unsigned long physbase) +static void __head startup_64_load_idt(unsigned long physbase) { struct desc_ptr *desc = fixup_pointer(&bringup_idt_descr, physbase); gate_desc *idt = fixup_pointer(bringup_idt_table, physbase); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 6120f25b0d5cc5cbe5c7c4b7a396b88c8d55c295..991f00c817e6c76dc5c97d0c6bda415086231878 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -301,7 +301,16 @@ static int can_probe(unsigned long paddr) kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset, bool *on_func_entry) { - if (is_endbr(*(u32 *)addr)) { + u32 insn; + + /* + * Since 'addr' is not guaranteed to be safe to access, use + * copy_from_kernel_nofault() to read the instruction: + */ + if (copy_from_kernel_nofault(&insn, (void *)addr, sizeof(u32))) + return NULL; + + if (is_endbr(insn)) { *on_func_entry = !offset || offset == 4; if (*on_func_entry) offset = 4; diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index cec0bfa3bc04fa21fbf741d5c6fca0464956bf1d..ed6cce6c395040158895d2eb2e1187a71dc58175 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -522,9 +522,6 @@ nmi_restart: write_cr2(this_cpu_read(nmi_cr2)); if (this_cpu_dec_return(nmi_state)) goto nmi_restart; - - if (user_mode(regs)) - mds_user_clear_cpu_buffers(); } #if defined(CONFIG_X86_64) && IS_ENABLED(CONFIG_KVM_INTEL) diff --git a/arch/x86/kernel/platform-quirks.c b/arch/x86/kernel/platform-quirks.c index b348a672f71d5ecd381822deab84585d35d1afc8..b525fe6d66571232d8029493348de8dbfb320dbe 100644 --- a/arch/x86/kernel/platform-quirks.c +++ b/arch/x86/kernel/platform-quirks.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include #include #include diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index 319fef37d9dce41f8109c768f58f627649dbac99..cc2c34ba7228ac52b5c8d14e1f57625337154881 100644 --- a/arch/x86/kernel/probe_roms.c +++ b/arch/x86/kernel/probe_roms.c @@ -203,16 +203,6 @@ void __init probe_roms(void) unsigned char c; int i; - /* - * The ROM memory range is not part of the e820 table and is therefore not - * pre-validated by BIOS. The kernel page table maps the ROM region as encrypted - * memory, and SNP requires encrypted memory to be validated before access. - * Do that here. - */ - snp_prep_memory(video_rom_resource.start, - ((system_rom_resource.end + 1) - video_rom_resource.start), - SNP_PAGE_STATE_PRIVATE); - /* video rom */ upper = adapter_rom_resources[0].start; for (start = video_rom_resource.start; start < upper; start += 2048) { diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 7f94dbbc397b7c1833054222b3ff075dd34d795c..a0d3059bee3de394bf0c672543d0051b68c6252b 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -137,7 +137,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode, log_lvl, d3, d6, d7); } - if (cpu_feature_enabled(X86_FEATURE_OSPKE)) + if (cr4 & X86_CR4_PKE) printk("%sPKRU: %08x\n", log_lvl, read_pkru()); } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 804a252382da7c1a2e94e92f77878a62247f5ec8..18a034613d94d62ba9f438bad9aadcbe828c2969 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -9,7 +9,6 @@ #include #include #include -#include #include #include #include @@ -34,6 +33,7 @@ #include #include #include +#include #include #include #include @@ -1032,7 +1032,7 @@ void __init setup_arch(char **cmdline_p) if (efi_enabled(EFI_BOOT)) efi_init(); - dmi_setup(); + x86_init.resources.dmi_setup(); /* * VMware detection requires dmi to be available, so this @@ -1133,6 +1133,7 @@ void __init setup_arch(char **cmdline_p) * memory size. */ sev_setup_arch(); + cc_random_init(); efi_fake_memmap(); efi_find_mirror(); diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index 71d8698702ce34f903e97663932ec24f3358fcee..3fe76bf17d95e9dc284bcacd6c55ad7a5c44b6e0 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -86,7 +86,8 @@ static bool __init sev_es_check_cpu_features(void) return true; } -static void __noreturn sev_es_terminate(unsigned int set, unsigned int reason) +static void __head __noreturn +sev_es_terminate(unsigned int set, unsigned int reason) { u64 val = GHCB_MSR_TERM_REQ; @@ -323,13 +324,7 @@ static int sev_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid */ static const struct snp_cpuid_table *snp_cpuid_get_table(void) { - void *ptr; - - asm ("lea cpuid_table_copy(%%rip), %0" - : "=r" (ptr) - : "p" (&cpuid_table_copy)); - - return ptr; + return &RIP_REL_REF(cpuid_table_copy); } /* @@ -388,7 +383,7 @@ static u32 snp_cpuid_calc_xsave_size(u64 xfeatures_en, bool compacted) return xsave_size; } -static bool +static bool __head snp_cpuid_get_validated_func(struct cpuid_leaf *leaf) { const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); @@ -525,7 +520,8 @@ static int snp_cpuid_postprocess(struct ghcb *ghcb, struct es_em_ctxt *ctxt, * Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value * should be treated as fatal by caller. */ -static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) +static int __head +snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) { const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); @@ -553,9 +549,9 @@ static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_le leaf->eax = leaf->ebx = leaf->ecx = leaf->edx = 0; /* Skip post-processing for out-of-range zero leafs. */ - if (!(leaf->fn <= cpuid_std_range_max || - (leaf->fn >= 0x40000000 && leaf->fn <= cpuid_hyp_range_max) || - (leaf->fn >= 0x80000000 && leaf->fn <= cpuid_ext_range_max))) + if (!(leaf->fn <= RIP_REL_REF(cpuid_std_range_max) || + (leaf->fn >= 0x40000000 && leaf->fn <= RIP_REL_REF(cpuid_hyp_range_max)) || + (leaf->fn >= 0x80000000 && leaf->fn <= RIP_REL_REF(cpuid_ext_range_max)))) return 0; } @@ -567,7 +563,7 @@ static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_le * page yet, so it only supports the MSR based communication with the * hypervisor and only the CPUID exit-code. */ -void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) +void __head do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) { unsigned int subfn = lower_bits(regs->cx, 32); unsigned int fn = lower_bits(regs->ax, 32); @@ -1013,7 +1009,8 @@ struct cc_setup_data { * Search for a Confidential Computing blob passed in as a setup_data entry * via the Linux Boot Protocol. */ -static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp) +static __head +struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp) { struct cc_setup_data *sd = NULL; struct setup_data *hdr; @@ -1040,7 +1037,7 @@ static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp) * mapping needs to be updated in sync with all the changes to virtual memory * layout and related mapping facilities throughout the boot process. */ -static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info) +static void __head setup_cpuid_table(const struct cc_blob_sev_info *cc_info) { const struct snp_cpuid_table *cpuid_table_fw, *cpuid_table; int i; @@ -1060,10 +1057,10 @@ static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info) const struct snp_cpuid_fn *fn = &cpuid_table->fn[i]; if (fn->eax_in == 0x0) - cpuid_std_range_max = fn->eax; + RIP_REL_REF(cpuid_std_range_max) = fn->eax; else if (fn->eax_in == 0x40000000) - cpuid_hyp_range_max = fn->eax; + RIP_REL_REF(cpuid_hyp_range_max) = fn->eax; else if (fn->eax_in == 0x80000000) - cpuid_ext_range_max = fn->eax; + RIP_REL_REF(cpuid_ext_range_max) = fn->eax; } } diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index c8dfb0fdde7f990b7e0d2573d370eb52dde79d32..f8a8249ae11779da123241c7c9ab0cd671edd4e1 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -23,8 +23,10 @@ #include #include #include +#include #include +#include #include #include #include @@ -689,7 +691,7 @@ static void pvalidate_pages(unsigned long vaddr, unsigned long npages, bool vali } } -static void __init early_set_pages_state(unsigned long paddr, unsigned long npages, enum psc_op op) +static void __head early_set_pages_state(unsigned long paddr, unsigned long npages, enum psc_op op) { unsigned long paddr_end; u64 val; @@ -727,7 +729,7 @@ e_term: sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); } -void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, +void __head early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned long npages) { /* @@ -736,7 +738,7 @@ void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long padd * This eliminates worries about jump tables or checking boot_cpu_data * in the cc_platform_has() function. */ - if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED)) return; /* @@ -758,7 +760,7 @@ void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr * This eliminates worries about jump tables or checking boot_cpu_data * in the cc_platform_has() function. */ - if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED)) return; /* Invalidate the memory pages before they are marked shared in the RMP table. */ @@ -768,21 +770,6 @@ void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr early_set_pages_state(paddr, npages, SNP_PAGE_STATE_SHARED); } -void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) -{ - unsigned long vaddr, npages; - - vaddr = (unsigned long)__va(paddr); - npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; - - if (op == SNP_PAGE_STATE_PRIVATE) - early_snp_set_memory_private(vaddr, paddr, npages); - else if (op == SNP_PAGE_STATE_SHARED) - early_snp_set_memory_shared(vaddr, paddr, npages); - else - WARN(1, "invalid memory op %d\n", op); -} - static int vmgexit_psc(struct snp_psc_desc *desc) { int cur_entry, end_entry, ret = 0; @@ -2099,7 +2086,7 @@ fail: * * Scan for the blob in that order. */ -static __init struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp) +static __head struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp) { struct cc_blob_sev_info *cc_info; @@ -2125,7 +2112,7 @@ found_cc_info: return cc_info; } -bool __init snp_init(struct boot_params *bp) +bool __head snp_init(struct boot_params *bp) { struct cc_blob_sev_info *cc_info; @@ -2147,11 +2134,22 @@ bool __init snp_init(struct boot_params *bp) return true; } -void __init __noreturn snp_abort(void) +void __head __noreturn snp_abort(void) { sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); } +/* + * SEV-SNP guests should only execute dmi_setup() if EFI_CONFIG_TABLES are + * enabled, as the alternative (fallback) logic for DMI probing in the legacy + * ROM region can cause a crash since this region is not pre-validated. + */ +void __init snp_dmi_setup(void) +{ + if (efi_enabled(EFI_CONFIG_TABLES)) + dmi_setup(); +} + static void dump_cpuid_table(void) { const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 3fbb49168827521e64532b5edf7d9438b65ce264..b32134b093ec801ca496b56c655daa3702fdfdcb 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -80,7 +80,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, case RET: if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) - code = text_gen_insn(JMP32_INSN_OPCODE, insn, &__x86_return_thunk); + code = text_gen_insn(JMP32_INSN_OPCODE, insn, x86_return_thunk); else code = &retinsn; break; diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 41e5b4cb898c3dd9791cf9f029fa3f05cc617f07..a4a921b9e66466c759e2c2e7211ff609e076bc4a 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -3,6 +3,7 @@ * * For licencing details see kernel-base/COPYING */ +#include #include #include #include @@ -66,6 +67,7 @@ struct x86_init_ops x86_init __initdata = { .probe_roms = probe_roms, .reserve_resources = reserve_standard_io_resources, .memory_setup = e820__memory_setup_default, + .dmi_setup = dmi_setup, }, .mpparse = { diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index c3ef1fc602bf981fa94430ef329992f711bc02ca..f02961cbbb75a8a0bbac07d50c12cc2d5269b65d 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -340,6 +340,7 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_update_pv_runtime(vcpu); + vcpu->arch.is_amd_compatible = guest_cpuid_is_amd_or_hygon(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); @@ -535,9 +536,9 @@ static __always_inline void __kvm_cpu_cap_mask(unsigned int leaf) } static __always_inline -void kvm_cpu_cap_init_scattered(enum kvm_only_cpuid_leafs leaf, u32 mask) +void kvm_cpu_cap_init_kvm_defined(enum kvm_only_cpuid_leafs leaf, u32 mask) { - /* Use kvm_cpu_cap_mask for non-scattered leafs. */ + /* Use kvm_cpu_cap_mask for leafs that aren't KVM-only. */ BUILD_BUG_ON(leaf < NCAPINTS); kvm_cpu_caps[leaf] = mask; @@ -547,7 +548,7 @@ void kvm_cpu_cap_init_scattered(enum kvm_only_cpuid_leafs leaf, u32 mask) static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask) { - /* Use kvm_cpu_cap_init_scattered for scattered leafs. */ + /* Use kvm_cpu_cap_init_kvm_defined for KVM-only leafs. */ BUILD_BUG_ON(leaf >= NCAPINTS); kvm_cpu_caps[leaf] &= mask; @@ -652,11 +653,16 @@ void kvm_set_cpu_caps(void) F(AVX_VNNI) | F(AVX512_BF16) ); + kvm_cpu_cap_init_kvm_defined(CPUID_7_2_EDX, + F(INTEL_PSFD) | F(IPRED_CTRL) | F(RRSBA_CTRL) | F(DDPD_U) | + F(BHI_CTRL) | F(MCDT_NO) + ); + kvm_cpu_cap_mask(CPUID_D_1_EAX, F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) | f_xfd ); - kvm_cpu_cap_init_scattered(CPUID_12_EAX, + kvm_cpu_cap_init_kvm_defined(CPUID_12_EAX, SF(SGX1) | SF(SGX2) ); @@ -902,13 +908,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) break; /* function 7 has additional index. */ case 7: - entry->eax = min(entry->eax, 1u); + max_idx = entry->eax = min(entry->eax, 2u); cpuid_entry_override(entry, CPUID_7_0_EBX); cpuid_entry_override(entry, CPUID_7_ECX); cpuid_entry_override(entry, CPUID_7_EDX); - /* KVM only supports 0x7.0 and 0x7.1, capped above via min(). */ - if (entry->eax == 1) { + /* KVM only supports up to 0x7.2, capped above via min(). */ + if (max_idx >= 1) { entry = do_host_cpuid(array, function, 1); if (!entry) goto out; @@ -918,6 +924,16 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->ecx = 0; entry->edx = 0; } + if (max_idx >= 2) { + entry = do_host_cpuid(array, function, 2); + if (!entry) + goto out; + + cpuid_entry_override(entry, CPUID_7_2_EDX); + entry->ecx = 0; + entry->ebx = 0; + entry->eax = 0; + } break; case 0xa: { /* Architectural Performance Monitoring */ union cpuid10_eax eax; diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index b1658c0de847cd38c0560c9bbb947a1a267c2c7e..18fd2e845989a77aab8d73290db22cb743f59e0b 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -125,6 +125,16 @@ static inline bool guest_cpuid_is_intel(struct kvm_vcpu *vcpu) return best && is_guest_vendor_intel(best->ebx, best->ecx, best->edx); } +static inline bool guest_cpuid_is_amd_compatible(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.is_amd_compatible; +} + +static inline bool guest_cpuid_is_intel_compatible(struct kvm_vcpu *vcpu) +{ + return !guest_cpuid_is_amd_compatible(vcpu); +} + static inline int guest_cpuid_family(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index edcf45e312b993ed37148cf90dab26539982fcce..c90fef0258c51375b61fa834735abb6e1fbb2924 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -40,6 +40,7 @@ #include "ioapic.h" #include "trace.h" #include "x86.h" +#include "xen.h" #include "cpuid.h" #include "hyperv.h" @@ -338,8 +339,10 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) } /* Check if there are APF page ready requests pending */ - if (enabled) + if (enabled) { kvm_make_request(KVM_REQ_APF_READY, apic->vcpu); + kvm_xen_sw_enable_lapic(apic->vcpu); + } } static inline void kvm_apic_set_xapic_id(struct kvm_lapic *apic, u8 id) @@ -2545,7 +2548,8 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) trig_mode = reg & APIC_LVT_LEVEL_TRIGGER; r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL); - if (r && lvt_type == APIC_LVTPC) + if (r && lvt_type == APIC_LVTPC && + guest_cpuid_is_intel_compatible(apic->vcpu)) kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED); return r; } diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index d30325e297a037956afc8a925da11bafff51df2d..13134954e24dfb5df413d0e7cbf4836839712298 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4649,7 +4649,7 @@ static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu, context->cpu_role.base.level, is_efer_nx(context), guest_can_use_gbpages(vcpu), is_cr4_pse(context), - guest_cpuid_is_amd_or_hygon(vcpu)); + guest_cpuid_is_amd_compatible(vcpu)); } static void diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index 7eeade35a425bfa53edd6a70bb0676446c8fa6dd..e43909d6504afb128db9c0c27fdfa5e920d4620e 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -7,23 +7,44 @@ #include /* - * Hardware-defined CPUID leafs that are scattered in the kernel, but need to - * be directly used by KVM. Note, these word values conflict with the kernel's - * "bug" caps, but KVM doesn't use those. + * Hardware-defined CPUID leafs that are either scattered by the kernel or are + * unknown to the kernel, but need to be directly used by KVM. Note, these + * word values conflict with the kernel's "bug" caps, but KVM doesn't use those. */ enum kvm_only_cpuid_leafs { CPUID_12_EAX = NCAPINTS, + CPUID_7_2_EDX, NR_KVM_CPU_CAPS, NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, }; +/* + * Define a KVM-only feature flag. + * + * For features that are scattered by cpufeatures.h, __feature_translate() also + * needs to be updated to translate the kernel-defined feature into the + * KVM-defined feature. + * + * For features that are 100% KVM-only, i.e. not defined by cpufeatures.h, + * forego the intermediate KVM_X86_FEATURE and directly define X86_FEATURE_* so + * that X86_FEATURE_* can be used in KVM. No __feature_translate() handling is + * needed in this case. + */ #define KVM_X86_FEATURE(w, f) ((w)*32 + (f)) /* Intel-defined SGX sub-features, CPUID level 0x12 (EAX). */ #define KVM_X86_FEATURE_SGX1 KVM_X86_FEATURE(CPUID_12_EAX, 0) #define KVM_X86_FEATURE_SGX2 KVM_X86_FEATURE(CPUID_12_EAX, 1) +/* Intel-defined sub-features, CPUID level 0x00000007:2 (EDX) */ +#define X86_FEATURE_INTEL_PSFD KVM_X86_FEATURE(CPUID_7_2_EDX, 0) +#define X86_FEATURE_IPRED_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 1) +#define KVM_X86_FEATURE_RRSBA_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 2) +#define X86_FEATURE_DDPD_U KVM_X86_FEATURE(CPUID_7_2_EDX, 3) +#define KVM_X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4) +#define X86_FEATURE_MCDT_NO KVM_X86_FEATURE(CPUID_7_2_EDX, 5) + struct cpuid_reg { u32 function; u32 index; @@ -49,6 +70,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_12_EAX] = {0x00000012, 0, CPUID_EAX}, [CPUID_8000_001F_EAX] = {0x8000001f, 0, CPUID_EAX}, [CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX}, + [CPUID_7_2_EDX] = { 7, 2, CPUID_EDX}, }; /* @@ -61,10 +83,12 @@ static const struct cpuid_reg reverse_cpuid[] = { */ static __always_inline void reverse_cpuid_check(unsigned int x86_leaf) { + BUILD_BUG_ON(NR_CPUID_WORDS != NCAPINTS); BUILD_BUG_ON(x86_leaf == CPUID_LNX_1); BUILD_BUG_ON(x86_leaf == CPUID_LNX_2); BUILD_BUG_ON(x86_leaf == CPUID_LNX_3); BUILD_BUG_ON(x86_leaf == CPUID_LNX_4); + BUILD_BUG_ON(x86_leaf == CPUID_LNX_5); BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid)); BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0); } @@ -75,12 +99,17 @@ static __always_inline void reverse_cpuid_check(unsigned int x86_leaf) */ static __always_inline u32 __feature_translate(int x86_feature) { - if (x86_feature == X86_FEATURE_SGX1) - return KVM_X86_FEATURE_SGX1; - else if (x86_feature == X86_FEATURE_SGX2) - return KVM_X86_FEATURE_SGX2; - - return x86_feature; +#define KVM_X86_TRANSLATE_FEATURE(f) \ + case X86_FEATURE_##f: return KVM_X86_FEATURE_##f + + switch (x86_feature) { + KVM_X86_TRANSLATE_FEATURE(SGX1); + KVM_X86_TRANSLATE_FEATURE(SGX2); + KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL); + KVM_X86_TRANSLATE_FEATURE(BHI_CTRL); + default: + return x86_feature; + } } static __always_inline u32 __feature_leaf(int x86_feature) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 3060fe4e9731aaa421970f0a271af65a73d286e4..d8e192ad59538e08ce6fa127a96e483c47fa8dac 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -76,9 +76,10 @@ struct enc_region { }; /* Called with the sev_bitmap_lock held, or on shutdown */ -static int sev_flush_asids(int min_asid, int max_asid) +static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid) { - int ret, asid, error = 0; + int ret, error = 0; + unsigned int asid; /* Check if there are any ASIDs to reclaim before performing a flush */ asid = find_next_bit(sev_reclaim_asid_bitmap, nr_asids, min_asid); @@ -108,7 +109,7 @@ static inline bool is_mirroring_enc_context(struct kvm *kvm) } /* Must be called with the sev_bitmap_lock held */ -static bool __sev_recycle_asids(int min_asid, int max_asid) +static bool __sev_recycle_asids(unsigned int min_asid, unsigned int max_asid) { if (sev_flush_asids(min_asid, max_asid)) return false; @@ -135,8 +136,20 @@ static void sev_misc_cg_uncharge(struct kvm_sev_info *sev) static int sev_asid_new(struct kvm_sev_info *sev) { - int asid, min_asid, max_asid, ret; + /* + * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid. + * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1. + * Note: min ASID can end up larger than the max if basic SEV support is + * effectively disabled by disallowing use of ASIDs for SEV guests. + */ + unsigned int min_asid = sev->es_active ? 1 : min_sev_asid; + unsigned int max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid; + unsigned int asid; bool retry = true; + int ret; + + if (min_asid > max_asid) + return -ENOTTY; WARN_ON(sev->misc_cg); sev->misc_cg = get_current_misc_cg(); @@ -149,12 +162,6 @@ static int sev_asid_new(struct kvm_sev_info *sev) mutex_lock(&sev_bitmap_lock); - /* - * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid. - * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1. - */ - min_asid = sev->es_active ? 1 : min_sev_asid; - max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid; again: asid = find_next_zero_bit(sev_asid_bitmap, max_asid + 1, min_asid); if (asid > max_asid) { @@ -179,7 +186,7 @@ e_uncharge: return ret; } -static int sev_get_asid(struct kvm *kvm) +static unsigned int sev_get_asid(struct kvm *kvm) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; @@ -276,8 +283,8 @@ e_no_asid: static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) { + unsigned int asid = sev_get_asid(kvm); struct sev_data_activate activate; - int asid = sev_get_asid(kvm); int ret; /* activate ASID on the given handle */ @@ -1958,20 +1965,22 @@ int sev_mem_enc_register_region(struct kvm *kvm, goto e_free; } - region->uaddr = range->addr; - region->size = range->size; - - list_add_tail(®ion->list, &sev->regions_list); - mutex_unlock(&kvm->lock); - /* * The guest may change the memory encryption attribute from C=0 -> C=1 * or vice versa for this memory range. Lets make sure caches are * flushed to ensure that guest data gets written into memory with - * correct C-bit. + * correct C-bit. Note, this must be done before dropping kvm->lock, + * as region and its array of pages can be freed by a different task + * once kvm->lock is released. */ sev_clflush_pages(region->pages, region->npages); + region->uaddr = range->addr; + region->size = range->size; + + list_add_tail(®ion->list, &sev->regions_list); + mutex_unlock(&kvm->lock); + return ret; e_free: @@ -2211,11 +2220,10 @@ void __init sev_hardware_setup(void) goto out; } - sev_asid_count = max_sev_asid - min_sev_asid + 1; - if (misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count)) - goto out; - - pr_info("SEV supported: %u ASIDs\n", sev_asid_count); + if (min_sev_asid <= max_sev_asid) { + sev_asid_count = max_sev_asid - min_sev_asid + 1; + WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count)); + } sev_supported = true; /* SEV-ES support requested? */ @@ -2240,13 +2248,21 @@ void __init sev_hardware_setup(void) goto out; sev_es_asid_count = min_sev_asid - 1; - if (misc_cg_set_capacity(MISC_CG_RES_SEV_ES, sev_es_asid_count)) - goto out; - - pr_info("SEV-ES supported: %u ASIDs\n", sev_es_asid_count); + WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV_ES, sev_es_asid_count)); sev_es_supported = true; out: + if (boot_cpu_has(X86_FEATURE_SEV)) + pr_info("SEV %s (ASIDs %u - %u)\n", + sev_supported ? min_sev_asid <= max_sev_asid ? "enabled" : + "unusable" : + "disabled", + min_sev_asid, max_sev_asid); + if (boot_cpu_has(X86_FEATURE_SEV_ES)) + pr_info("SEV-ES %s (ASIDs %u - %u)\n", + sev_es_supported ? "enabled" : "disabled", + min_sev_asid > 1 ? 1 : 0, min_sev_asid - 1); + sev_enabled = sev_supported; sev_es_enabled = sev_es_supported; #endif @@ -2285,7 +2301,7 @@ int sev_cpu_init(struct svm_cpu_data *sd) */ static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va) { - int asid = to_kvm_svm(vcpu->kvm)->sev_info.asid; + unsigned int asid = sev_get_asid(vcpu->kvm); /* * Note! The address must be a kernel address, as regular page walk @@ -2606,7 +2622,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm) void pre_sev_run(struct vcpu_svm *svm, int cpu) { struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); - int asid = sev_get_asid(svm->vcpu.kvm); + unsigned int asid = sev_get_asid(svm->vcpu.kvm); /* Assign the asid allocated with this SEV guest */ svm->asid = asid; diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h index 36c8af87a707ac0556fb1e50157e70c6305df798..4e725854c63a10c8645fa3b875a7a718020e96fe 100644 --- a/arch/x86/kvm/svm/svm_ops.h +++ b/arch/x86/kvm/svm/svm_ops.h @@ -8,7 +8,7 @@ #define svm_asm(insn, clobber...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) "\n\t" \ + asm goto("1: " __stringify(insn) "\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ ::: clobber : fault); \ return; \ @@ -18,7 +18,7 @@ fault: \ #define svm_asm1(insn, op1, clobber...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %0\n\t" \ + asm goto("1: " __stringify(insn) " %0\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ :: op1 : clobber : fault); \ return; \ @@ -28,7 +28,7 @@ fault: \ #define svm_asm2(insn, op1, op2, clobber...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %1, %0\n\t" \ + asm goto("1: " __stringify(insn) " %1, %0\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ :: op1, op2 : clobber : fault); \ return; \ diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index bc25589ad588676974770919234b67f9ce198c43..6c1dcf44c4fa3e51a4e1508692189ba3b28e19db 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -729,13 +729,13 @@ TRACE_EVENT(kvm_nested_intr_vmexit, * Tracepoint for nested #vmexit because of interrupt pending */ TRACE_EVENT(kvm_invlpga, - TP_PROTO(__u64 rip, int asid, u64 address), + TP_PROTO(__u64 rip, unsigned int asid, u64 address), TP_ARGS(rip, asid, address), TP_STRUCT__entry( - __field( __u64, rip ) - __field( int, asid ) - __field( __u64, address ) + __field( __u64, rip ) + __field( unsigned int, asid ) + __field( __u64, address ) ), TP_fast_assign( @@ -744,7 +744,7 @@ TRACE_EVENT(kvm_invlpga, __entry->address = address; ), - TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx", + TP_printk("rip: 0x%016llx asid: %u address: 0x%016llx", __entry->rip, __entry->asid, __entry->address) ); diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 9a75a0d5deae150ab6dd83c1b3e487a41fbaff65..220cdbe1e286ed2a3045d16fb67d79c0f7d6500e 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -38,7 +38,7 @@ static int fixed_pmc_events[] = {1, 0, 7}; static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) { struct kvm_pmc *pmc; - u8 old_fixed_ctr_ctrl = pmu->fixed_ctr_ctrl; + u64 old_fixed_ctr_ctrl = pmu->fixed_ctr_ctrl; int i; pmu->fixed_ctr_ctrl = data; diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h index edc3f16cc1896f29e4eef46da685d22b4c31c668..6a9bfdfbb6e59b2e613385cd2ad46cc651a0eb28 100644 --- a/arch/x86/kvm/vmx/run_flags.h +++ b/arch/x86/kvm/vmx/run_flags.h @@ -2,7 +2,10 @@ #ifndef __KVM_X86_VMX_RUN_FLAGS_H #define __KVM_X86_VMX_RUN_FLAGS_H -#define VMX_RUN_VMRESUME (1 << 0) -#define VMX_RUN_SAVE_SPEC_CTRL (1 << 1) +#define VMX_RUN_VMRESUME_SHIFT 0 +#define VMX_RUN_SAVE_SPEC_CTRL_SHIFT 1 + +#define VMX_RUN_VMRESUME BIT(VMX_RUN_VMRESUME_SHIFT) +#define VMX_RUN_SAVE_SPEC_CTRL BIT(VMX_RUN_SAVE_SPEC_CTRL_SHIFT) #endif /* __KVM_X86_VMX_RUN_FLAGS_H */ diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 0b5db4de4d09e568cc01b6005748f97104d02ec8..b4f8937226c21110f9b73e1724627dcaaddc5e19 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -106,7 +106,7 @@ SYM_FUNC_START(__vmx_vcpu_run) mov (%_ASM_SP), %_ASM_AX /* Check if vmlaunch or vmresume is needed */ - testb $VMX_RUN_VMRESUME, %bl + bt $VMX_RUN_VMRESUME_SHIFT, %bx /* Load guest registers. Don't clobber flags. */ mov VCPU_RCX(%_ASM_AX), %_ASM_CX @@ -128,8 +128,11 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX - /* Check EFLAGS.ZF from 'testb' above */ - jz .Lvmlaunch + /* Clobbers EFLAGS.ZF */ + CLEAR_CPU_BUFFERS + + /* Check EFLAGS.CF from the VMX_RUN_VMRESUME bit test above. */ + jnc .Lvmlaunch /* * After a successful VMRESUME/VMLAUNCH, control flow "magically" @@ -239,6 +242,8 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) call vmx_spec_ctrl_restore_host + CLEAR_BRANCH_HISTORY_VMEXIT + /* Put return value in AX */ mov %_ASM_BX, %_ASM_AX diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 98d732b9418f1089a0e5f7108d703ebdbf875345..10aff2c9a4e4cb631333428483cf7f213be73912 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -407,7 +407,8 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) { - vmx->disable_fb_clear = vmx_fb_clear_ctrl_available; + vmx->disable_fb_clear = !cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF) && + vmx_fb_clear_ctrl_available; /* * If guest will not execute VERW, there is no need to set FB_CLEAR_DIS @@ -2469,10 +2470,10 @@ static int kvm_cpu_vmxon(u64 vmxon_pointer) cr4_set_bits(X86_CR4_VMXE); - asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t" - _ASM_EXTABLE(1b, %l[fault]) - : : [vmxon_pointer] "m"(vmxon_pointer) - : : fault); + asm goto("1: vmxon %[vmxon_pointer]\n\t" + _ASM_EXTABLE(1b, %l[fault]) + : : [vmxon_pointer] "m"(vmxon_pointer) + : : fault); return 0; fault: @@ -7120,11 +7121,14 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, { guest_state_enter_irqoff(); - /* L1D Flush includes CPU buffer clear to mitigate MDS */ + /* + * L1D Flush includes CPU buffer clear to mitigate MDS, but VERW + * mitigation for MDS is done late in VMentry and is still + * executed in spite of L1D Flush. This is because an extra VERW + * should not matter much after the big hammer L1D Flush. + */ if (static_branch_unlikely(&vmx_l1d_should_flush)) vmx_l1d_flush(vcpu); - else if (static_branch_unlikely(&mds_user_clear)) - mds_clear_cpu_buffers(); else if (static_branch_unlikely(&mmio_stale_data_clear) && kvm_arch_has_assigned_device(vcpu->kvm)) mds_clear_cpu_buffers(); @@ -7738,8 +7742,28 @@ static u64 vmx_get_perf_capabilities(void) if (vmx_pebs_supported()) { perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK; - if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4) - perf_cap &= ~PERF_CAP_PEBS_BASELINE; + + /* + * Disallow adaptive PEBS as it is functionally broken, can be + * used by the guest to read *host* LBRs, and can be used to + * bypass userspace event filters. To correctly and safely + * support adaptive PEBS, KVM needs to: + * + * 1. Account for the ADAPTIVE flag when (re)programming fixed + * counters. + * + * 2. Gain support from perf (or take direct control of counter + * programming) to support events without adaptive PEBS + * enabled for the hardware counter. + * + * 3. Ensure LBR MSRs cannot hold host data on VM-Entry with + * adaptive PEBS enabled and MSR_PEBS_DATA_CFG.LBRS=1. + * + * 4. Document which PMU events are effectively exposed to the + * guest via adaptive PEBS, and make adaptive PEBS mutually + * exclusive with KVM_SET_PMU_EVENT_FILTER if necessary. + */ + perf_cap &= ~PERF_CAP_PEBS_BASELINE; } return perf_cap; diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index ec268df83ed67988f76a007ad65e9d77aa5d7a3f..5edab28dfb2efecd30a15e97e48cfe919f4afbf2 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -73,7 +73,7 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field) #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT - asm_volatile_goto("1: vmread %[field], %[output]\n\t" + asm_goto_output("1: vmread %[field], %[output]\n\t" "jna %l[do_fail]\n\t" _ASM_EXTABLE(1b, %l[do_exception]) @@ -166,7 +166,7 @@ static __always_inline unsigned long vmcs_readl(unsigned long field) #define vmx_asm1(insn, op1, error_args...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %0\n\t" \ + asm goto("1: " __stringify(insn) " %0\n\t" \ ".byte 0x2e\n\t" /* branch not taken hint */ \ "jna %l[error]\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ @@ -183,7 +183,7 @@ fault: \ #define vmx_asm2(insn, op1, op2, error_args...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %1, %0\n\t" \ + asm goto("1: " __stringify(insn) " %1, %0\n\t" \ ".byte 0x2e\n\t" /* branch not taken hint */ \ "jna %l[error]\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7144e516681364d39a647bf4402b70aa61be4648..a2ea636a230867b0b87bb516537390cc98655fc1 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1613,7 +1613,8 @@ static unsigned int num_msr_based_features; ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \ ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ - ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO) + ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \ + ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO) static u64 kvm_get_arch_capabilities(void) { @@ -1650,6 +1651,8 @@ static u64 kvm_get_arch_capabilities(void) data |= ARCH_CAP_SSB_NO; if (!boot_cpu_has_bug(X86_BUG_MDS)) data |= ARCH_CAP_MDS_NO; + if (!boot_cpu_has_bug(X86_BUG_RFDS)) + data |= ARCH_CAP_RFDS_NO; if (!boot_cpu_has(X86_FEATURE_RTM)) { /* @@ -3275,7 +3278,7 @@ static bool is_mci_status_msr(u32 msr) static bool can_set_mci_status(struct kvm_vcpu *vcpu) { /* McStatusWrEn enabled? */ - if (guest_cpuid_is_amd_or_hygon(vcpu)) + if (guest_cpuid_is_amd_compatible(vcpu)) return !!(vcpu->arch.msr_hwcr & BIT_ULL(18)); return false; @@ -7755,6 +7758,16 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, if (r < 0) return X86EMUL_UNHANDLEABLE; + + /* + * Mark the page dirty _before_ checking whether or not the CMPXCHG was + * successful, as the old value is written back on failure. Note, for + * live migration, this is unnecessarily conservative as CMPXCHG writes + * back the original value and the access is atomic, but KVM's ABI is + * that all writes are dirty logged, regardless of the value written. + */ + kvm_vcpu_mark_page_dirty(vcpu, gpa_to_gfn(gpa)); + if (r) return X86EMUL_CMPXCHG_FAILED; diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index a58a426e6b1c0c8d4fe1dab2e13ee130d5c8d95c..684a39df60d9e88c28e092564b49f1d5f102c841 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -314,7 +314,7 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) mark_page_dirty_in_slot(v->kvm, gpc->memslot, gpc->gpa >> PAGE_SHIFT); } -static void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *v) +void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *v) { struct kvm_lapic_irq irq = { }; int r; diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h index 532a535a9e99f43c4cfadc1fbbb1192630225bf8..500d9593a5a38e26dd13f74ded2f381615936207 100644 --- a/arch/x86/kvm/xen.h +++ b/arch/x86/kvm/xen.h @@ -16,6 +16,7 @@ extern struct static_key_false_deferred kvm_xen_enabled; int __kvm_xen_has_interrupt(struct kvm_vcpu *vcpu); void kvm_xen_inject_pending_events(struct kvm_vcpu *vcpu); +void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *vcpu); int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data); int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data); int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data); @@ -33,6 +34,19 @@ int kvm_xen_setup_evtchn(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue); +static inline void kvm_xen_sw_enable_lapic(struct kvm_vcpu *vcpu) +{ + /* + * The local APIC is being enabled. If the per-vCPU upcall vector is + * set and the vCPU's evtchn_upcall_pending flag is set, inject the + * interrupt. + */ + if (static_branch_unlikely(&kvm_xen_enabled.key) && + vcpu->arch.xen.vcpu_info_cache.active && + vcpu->arch.xen.upcall_vector && __kvm_xen_has_interrupt(vcpu)) + kvm_xen_inject_vcpu_vector(vcpu); +} + static inline bool kvm_xen_msr_enabled(struct kvm *kvm) { return static_branch_unlikely(&kvm_xen_enabled.key) && @@ -98,6 +112,10 @@ static inline void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) { } +static inline void kvm_xen_sw_enable_lapic(struct kvm_vcpu *vcpu) +{ +} + static inline bool kvm_xen_msr_enabled(struct kvm *kvm) { return false; diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 65c5c44f006bc2b7022567d1692b9cdc99b6b781..055955c9bfcb728924f4bfceed20b0735c31f205 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -110,6 +110,7 @@ SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) ret int3 SYM_FUNC_END(srso_alias_untrain_ret) +__EXPORT_THUNK(srso_alias_untrain_ret) #endif SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE) @@ -252,9 +253,7 @@ SYM_CODE_START(srso_return_thunk) SYM_CODE_END(srso_return_thunk) SYM_FUNC_START(entry_untrain_ret) - ALTERNATIVE_2 "jmp retbleed_untrain_ret", \ - "jmp srso_untrain_ret", X86_FEATURE_SRSO, \ - "jmp srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS + ALTERNATIVE "jmp retbleed_untrain_ret", "jmp srso_untrain_ret", X86_FEATURE_SRSO SYM_FUNC_END(entry_untrain_ret) __EXPORT_THUNK(entry_untrain_ret) @@ -262,6 +261,7 @@ SYM_CODE_START(__x86_return_thunk) UNWIND_HINT_FUNC ANNOTATE_NOENDBR ANNOTATE_UNRET_SAFE + ANNOTATE_NOENDBR ret int3 SYM_CODE_END(__x86_return_thunk) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 1dbbad73192a16679cf2055185936d2524e82e03..f20636510eb1ef84fee772924cacebae5639eef0 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -818,15 +818,6 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, show_opcodes(regs, loglvl); } -/* - * The (legacy) vsyscall page is the long page in the kernel portion - * of the address space that has user-accessible permissions. - */ -static bool is_vsyscall_vaddr(unsigned long vaddr) -{ - return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR); -} - static void __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, unsigned long address, u32 pkey, int si_code) diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c index 6993f026adec9d12a68cdbf3af3314336882f36f..42115ac079cfe617b76199a167c61e5b3c7de10f 100644 --- a/arch/x86/mm/maccess.c +++ b/arch/x86/mm/maccess.c @@ -3,6 +3,8 @@ #include #include +#include + #ifdef CONFIG_X86_64 bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { @@ -15,6 +17,14 @@ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) if (vaddr < TASK_SIZE_MAX + PAGE_SIZE) return false; + /* + * Reading from the vsyscall page may cause an unhandled fault in + * certain cases. Though it is at an address above TASK_SIZE_MAX, it is + * usually considered as a user space address. + */ + if (is_vsyscall_vaddr(vaddr)) + return false; + /* * Allow everything during early boot before 'x86_virt_bits' * is initialized. Needed for instruction decoding in early diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index 3e93af083e037db8b286f693938cc3a6181ec2fa..d4957eefef267e1fd041736a1517958a7b06f007 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -513,6 +513,24 @@ void __init sme_early_init(void) */ if (sev_status & MSR_AMD64_SEV_ENABLED) ia32_disable(); + + /* + * Override init functions that scan the ROM region in SEV-SNP guests, + * as this memory is not pre-validated and would thus cause a crash. + */ + if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) { + x86_init.mpparse.find_smp_config = x86_init_noop; + x86_init.pci.init_irq = x86_init_noop; + x86_init.resources.probe_roms = x86_init_noop; + + /* + * DMI setup behavior for SEV-SNP guests depends on + * efi_enabled(EFI_CONFIG_TABLES), which hasn't been + * parsed yet. snp_dmi_setup() will run after that + * parsing has happened. + */ + x86_init.resources.dmi_setup = snp_dmi_setup; + } } void __init mem_encrypt_free_decrypted_mem(void) diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S index 9de3d900bc927142b5ec1688551464c26aa60851..e25288ee33c2df72755451175269775e8e1481a8 100644 --- a/arch/x86/mm/mem_encrypt_boot.S +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -26,7 +26,7 @@ SYM_FUNC_START(sme_encrypt_execute) * RCX - virtual address of the encryption workarea, including: * - stack page (PAGE_SIZE) * - encryption routine page (PAGE_SIZE) - * - intermediate copy buffer (PMD_PAGE_SIZE) + * - intermediate copy buffer (PMD_SIZE) * R8 - physical address of the pagetables to use for encryption */ @@ -123,7 +123,7 @@ SYM_FUNC_START(__enc_copy) wbinvd /* Invalidate any cache entries */ /* Copy/encrypt up to 2MB at a time */ - movq $PMD_PAGE_SIZE, %r12 + movq $PMD_SIZE, %r12 1: cmpq %r12, %r9 jnb 2f diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index d94ebd8acdfdecdcdff836ca0351dde63f11ecb7..f1760988487497f901ad51a4894ab2b93ead85f0 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -41,6 +41,7 @@ #include #include +#include #include #include #include @@ -93,13 +94,12 @@ struct sme_populate_pgd_data { * section is 2MB aligned to allow for simple pagetable setup using only * PMD entries (see vmlinux.lds.S). */ -static char sme_workarea[2 * PMD_PAGE_SIZE] __section(".init.scratch"); +static char sme_workarea[2 * PMD_SIZE] __section(".init.scratch"); static char sme_cmdline_arg[] __initdata = "mem_encrypt"; static char sme_cmdline_on[] __initdata = "on"; -static char sme_cmdline_off[] __initdata = "off"; -static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd) +static void __head sme_clear_pgd(struct sme_populate_pgd_data *ppd) { unsigned long pgd_start, pgd_end, pgd_size; pgd_t *pgd_p; @@ -114,7 +114,7 @@ static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd) memset(pgd_p, 0, pgd_size); } -static pud_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) +static pud_t __head *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) { pgd_t *pgd; p4d_t *p4d; @@ -151,7 +151,7 @@ static pud_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) return pud; } -static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) +static void __head sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) { pud_t *pud; pmd_t *pmd; @@ -167,7 +167,7 @@ static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) set_pmd(pmd, __pmd(ppd->paddr | ppd->pmd_flags)); } -static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd) +static void __head sme_populate_pgd(struct sme_populate_pgd_data *ppd) { pud_t *pud; pmd_t *pmd; @@ -193,17 +193,17 @@ static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd) set_pte(pte, __pte(ppd->paddr | ppd->pte_flags)); } -static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) +static void __head __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) { while (ppd->vaddr < ppd->vaddr_end) { sme_populate_pgd_large(ppd); - ppd->vaddr += PMD_PAGE_SIZE; - ppd->paddr += PMD_PAGE_SIZE; + ppd->vaddr += PMD_SIZE; + ppd->paddr += PMD_SIZE; } } -static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd) +static void __head __sme_map_range_pte(struct sme_populate_pgd_data *ppd) { while (ppd->vaddr < ppd->vaddr_end) { sme_populate_pgd(ppd); @@ -213,7 +213,7 @@ static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd) } } -static void __init __sme_map_range(struct sme_populate_pgd_data *ppd, +static void __head __sme_map_range(struct sme_populate_pgd_data *ppd, pmdval_t pmd_flags, pteval_t pte_flags) { unsigned long vaddr_end; @@ -225,11 +225,11 @@ static void __init __sme_map_range(struct sme_populate_pgd_data *ppd, vaddr_end = ppd->vaddr_end; /* If start is not 2MB aligned, create PTE entries */ - ppd->vaddr_end = ALIGN(ppd->vaddr, PMD_PAGE_SIZE); + ppd->vaddr_end = ALIGN(ppd->vaddr, PMD_SIZE); __sme_map_range_pte(ppd); /* Create PMD entries */ - ppd->vaddr_end = vaddr_end & PMD_PAGE_MASK; + ppd->vaddr_end = vaddr_end & PMD_MASK; __sme_map_range_pmd(ppd); /* If end is not 2MB aligned, create PTE entries */ @@ -237,22 +237,22 @@ static void __init __sme_map_range(struct sme_populate_pgd_data *ppd, __sme_map_range_pte(ppd); } -static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd) +static void __head sme_map_range_encrypted(struct sme_populate_pgd_data *ppd) { __sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC); } -static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd) +static void __head sme_map_range_decrypted(struct sme_populate_pgd_data *ppd) { __sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC); } -static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd) +static void __head sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd) { __sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP); } -static unsigned long __init sme_pgtable_calc(unsigned long len) +static unsigned long __head sme_pgtable_calc(unsigned long len) { unsigned long entries = 0, tables = 0; @@ -289,7 +289,7 @@ static unsigned long __init sme_pgtable_calc(unsigned long len) return entries + tables; } -void __init sme_encrypt_kernel(struct boot_params *bp) +void __head sme_encrypt_kernel(struct boot_params *bp) { unsigned long workarea_start, workarea_end, workarea_len; unsigned long execute_start, execute_end, execute_len; @@ -305,7 +305,8 @@ void __init sme_encrypt_kernel(struct boot_params *bp) * instrumentation or checking boot_cpu_data in the cc_platform_has() * function. */ - if (!sme_get_me_mask() || sev_status & MSR_AMD64_SEV_ENABLED) + if (!sme_get_me_mask() || + RIP_REL_REF(sev_status) & MSR_AMD64_SEV_ENABLED) return; /* @@ -323,9 +324,8 @@ void __init sme_encrypt_kernel(struct boot_params *bp) * memory from being cached. */ - /* Physical addresses gives us the identity mapped virtual addresses */ - kernel_start = __pa_symbol(_text); - kernel_end = ALIGN(__pa_symbol(_end), PMD_PAGE_SIZE); + kernel_start = (unsigned long)RIP_REL_REF(_text); + kernel_end = ALIGN((unsigned long)RIP_REL_REF(_end), PMD_SIZE); kernel_len = kernel_end - kernel_start; initrd_start = 0; @@ -342,25 +342,17 @@ void __init sme_encrypt_kernel(struct boot_params *bp) } #endif - /* - * We're running identity mapped, so we must obtain the address to the - * SME encryption workarea using rip-relative addressing. - */ - asm ("lea sme_workarea(%%rip), %0" - : "=r" (workarea_start) - : "p" (sme_workarea)); - /* * Calculate required number of workarea bytes needed: * executable encryption area size: * stack page (PAGE_SIZE) * encryption routine page (PAGE_SIZE) - * intermediate copy buffer (PMD_PAGE_SIZE) + * intermediate copy buffer (PMD_SIZE) * pagetable structures for the encryption of the kernel * pagetable structures for workarea (in case not currently mapped) */ - execute_start = workarea_start; - execute_end = execute_start + (PAGE_SIZE * 2) + PMD_PAGE_SIZE; + execute_start = workarea_start = (unsigned long)RIP_REL_REF(sme_workarea); + execute_end = execute_start + (PAGE_SIZE * 2) + PMD_SIZE; execute_len = execute_end - execute_start; /* @@ -383,7 +375,7 @@ void __init sme_encrypt_kernel(struct boot_params *bp) * before it is mapped. */ workarea_len = execute_len + pgtable_area_len; - workarea_end = ALIGN(workarea_start + workarea_len, PMD_PAGE_SIZE); + workarea_end = ALIGN(workarea_start + workarea_len, PMD_SIZE); /* * Set the address to the start of where newly created pagetable @@ -502,12 +494,11 @@ void __init sme_encrypt_kernel(struct boot_params *bp) native_write_cr3(__native_read_cr3()); } -void __init sme_enable(struct boot_params *bp) +void __head sme_enable(struct boot_params *bp) { - const char *cmdline_ptr, *cmdline_arg, *cmdline_on, *cmdline_off; + const char *cmdline_ptr, *cmdline_arg, *cmdline_on; unsigned int eax, ebx, ecx, edx; unsigned long feature_mask; - bool active_by_default; unsigned long me_mask; char buffer[16]; bool snp; @@ -543,11 +534,11 @@ void __init sme_enable(struct boot_params *bp) me_mask = 1UL << (ebx & 0x3f); /* Check the SEV MSR whether SEV or SME is enabled */ - sev_status = __rdmsr(MSR_AMD64_SEV); - feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; + RIP_REL_REF(sev_status) = msr = __rdmsr(MSR_AMD64_SEV); + feature_mask = (msr & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; /* The SEV-SNP CC blob should never be present unless SEV-SNP is enabled. */ - if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + if (snp && !(msr & MSR_AMD64_SEV_SNP_ENABLED)) snp_abort(); /* Check if memory encryption is enabled */ @@ -573,7 +564,6 @@ void __init sme_enable(struct boot_params *bp) return; } else { /* SEV state cannot be controlled by a command line option */ - sme_me_mask = me_mask; goto out; } @@ -588,31 +578,17 @@ void __init sme_enable(struct boot_params *bp) asm ("lea sme_cmdline_on(%%rip), %0" : "=r" (cmdline_on) : "p" (sme_cmdline_on)); - asm ("lea sme_cmdline_off(%%rip), %0" - : "=r" (cmdline_off) - : "p" (sme_cmdline_off)); - - if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT)) - active_by_default = true; - else - active_by_default = false; cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr | ((u64)bp->ext_cmd_line_ptr << 32)); - if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0) + if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0 || + strncmp(buffer, cmdline_on, sizeof(buffer))) return; - if (!strncmp(buffer, cmdline_on, sizeof(buffer))) - sme_me_mask = me_mask; - else if (!strncmp(buffer, cmdline_off, sizeof(buffer))) - sme_me_mask = 0; - else - sme_me_mask = active_by_default ? me_mask : 0; out: - if (sme_me_mask) { - physical_mask &= ~sme_me_mask; - cc_set_vendor(CC_VENDOR_AMD); - cc_set_mask(sme_me_mask); - } + RIP_REL_REF(sme_me_mask) = me_mask; + physical_mask &= ~me_mask; + cc_vendor = CC_VENDOR_AMD; + cc_set_mask(me_mask); } diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index aa39d678fe81d8e26d81a4104cb5ab25788affa8..dae5c952735c78e542dfb71ab9456677725ecd2a 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -961,7 +961,7 @@ static int __init cmp_memblk(const void *a, const void *b) const struct numa_memblk *ma = *(const struct numa_memblk **)a; const struct numa_memblk *mb = *(const struct numa_memblk **)b; - return ma->start - mb->start; + return (ma->start > mb->start) - (ma->start < mb->start); } static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata; @@ -971,14 +971,12 @@ static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata; * @start: address to begin fill * @end: address to end fill * - * Find and extend numa_meminfo memblks to cover the @start-@end - * physical address range, such that the first memblk includes - * @start, the last memblk includes @end, and any gaps in between - * are filled. + * Find and extend numa_meminfo memblks to cover the physical + * address range @start-@end * * RETURNS: * 0 : Success - * NUMA_NO_MEMBLK : No memblk exists in @start-@end range + * NUMA_NO_MEMBLK : No memblks exist in address range @start-@end */ int __init numa_fill_memblks(u64 start, u64 end) @@ -990,17 +988,14 @@ int __init numa_fill_memblks(u64 start, u64 end) /* * Create a list of pointers to numa_meminfo memblks that - * overlap start, end. Exclude (start == bi->end) since - * end addresses in both a CFMWS range and a memblk range - * are exclusive. - * - * This list of pointers is used to make in-place changes - * that fill out the numa_meminfo memblks. + * overlap start, end. The list is used to make in-place + * changes that fill out the numa_meminfo memblks. */ for (int i = 0; i < mi->nr_blks; i++) { struct numa_memblk *bi = &mi->blk[i]; - if (start < bi->end && end >= bi->start) { + if (memblock_addrs_overlap(start, end - start, bi->start, + bi->end - bi->start)) { blk[count] = &mi->blk[i]; count++; } diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 66a209f7eb86da01b9c27537cb7a4183f657162b..d6fe9093ea919659690054b7d774c03b935e6479 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -997,6 +997,38 @@ static void free_pfn_range(u64 paddr, unsigned long size) memtype_free(paddr, paddr + size); } +static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr, + pgprot_t *pgprot) +{ + unsigned long prot; + + VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT)); + + /* + * We need the starting PFN and cachemode used for track_pfn_remap() + * that covered the whole VMA. For most mappings, we can obtain that + * information from the page tables. For COW mappings, we might now + * suddenly have anon folios mapped and follow_phys() will fail. + * + * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to + * detect the PFN. If we need the cachemode as well, we're out of luck + * for now and have to fail fork(). + */ + if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) { + if (pgprot) + *pgprot = __pgprot(prot); + return 0; + } + if (is_cow_mapping(vma->vm_flags)) { + if (pgprot) + return -EINVAL; + *paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT; + return 0; + } + WARN_ON_ONCE(1); + return -EINVAL; +} + /* * track_pfn_copy is called when vma that is covering the pfnmap gets * copied through copy_page_range(). @@ -1007,20 +1039,13 @@ static void free_pfn_range(u64 paddr, unsigned long size) int track_pfn_copy(struct vm_area_struct *vma) { resource_size_t paddr; - unsigned long prot; unsigned long vma_size = vma->vm_end - vma->vm_start; pgprot_t pgprot; if (vma->vm_flags & VM_PAT) { - /* - * reserve the whole chunk covered by vma. We need the - * starting address and protection from pte. - */ - if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { - WARN_ON_ONCE(1); + if (get_pat_info(vma, &paddr, &pgprot)) return -EINVAL; - } - pgprot = __pgprot(prot); + /* reserve the whole chunk covered by vma. */ return reserve_pfn_range(paddr, vma_size, &pgprot, 1); } @@ -1095,7 +1120,6 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size) { resource_size_t paddr; - unsigned long prot; if (vma && !(vma->vm_flags & VM_PAT)) return; @@ -1103,11 +1127,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, /* free the chunk starting from pfn or the whole chunk */ paddr = (resource_size_t)pfn << PAGE_SHIFT; if (!paddr && !size) { - if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { - WARN_ON_ONCE(1); + if (get_pat_info(vma, &paddr, NULL)) return; - } - size = vma->vm_end - vma->vm_start; } free_pfn_range(paddr, size); diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 5f0ce77a259d8d38f3c19376ba3b4b3eac7c10c2..68d4f328f1696233db6d7ec2b800c13f41ca1184 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -747,11 +747,11 @@ phys_addr_t slow_virt_to_phys(void *__virt_addr) switch (level) { case PG_LEVEL_1G: phys_addr = (phys_addr_t)pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; - offset = virt_addr & ~PUD_PAGE_MASK; + offset = virt_addr & ~PUD_MASK; break; case PG_LEVEL_2M: phys_addr = (phys_addr_t)pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; - offset = virt_addr & ~PMD_PAGE_MASK; + offset = virt_addr & ~PMD_MASK; break; default: phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; @@ -1041,7 +1041,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, case PG_LEVEL_1G: ref_prot = pud_pgprot(*(pud_t *)kpte); ref_pfn = pud_pfn(*(pud_t *)kpte); - pfninc = PMD_PAGE_SIZE >> PAGE_SHIFT; + pfninc = PMD_SIZE >> PAGE_SHIFT; lpaddr = address & PUD_MASK; lpinc = PMD_SIZE; /* diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index ffe3b3a087feaaa31bb0ca6b30dab8caf84857fe..78414c6d1b5ed1c245d13767907649b40f88b993 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -592,7 +592,7 @@ static void pti_set_kernel_image_nonglobal(void) * of the image. */ unsigned long start = PFN_ALIGN(_text); - unsigned long end = ALIGN((unsigned long)_end, PMD_PAGE_SIZE); + unsigned long end = ALIGN((unsigned long)_end, PMD_SIZE); /* * This clears _PAGE_GLOBAL from the entire kernel image. diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index b69aee6245e4a9ada2af976507a0f45053006f2f..7913440c0fd46d896a54c00c4d4057d9bba861dd 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -432,7 +432,7 @@ static void emit_return(u8 **pprog, u8 *ip) u8 *prog = *pprog; if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) { - emit_jump(&prog, &__x86_return_thunk, ip); + emit_jump(&prog, x86_return_thunk, ip); } else { EMIT1(0xC3); /* ret */ if (IS_ENABLED(CONFIG_SLS)) diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 2925074b9a588dec46961384bbd9668e013ce43b..9a5b101c4502333809ce4228d701e501c1c3327c 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -653,6 +653,14 @@ static void print_absolute_relocs(void) if (!(sec_applies->shdr.sh_flags & SHF_ALLOC)) { continue; } + /* + * Do not perform relocations in .notes section; any + * values there are meant for pre-boot consumption (e.g. + * startup_xen). + */ + if (sec_applies->shdr.sh_type == SHT_NOTE) { + continue; + } sh_symtab = sec_symtab->symtab; sym_strtab = sec_symtab->link->strtab; for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) { diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 4b0d6fff88de5a544e2ef91a8c3f7c5fa1339aa5..1fb9a1644d944b825a7eb5735b68f48b4c8df9ce 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -65,6 +65,8 @@ int xen_smp_intr_init(unsigned int cpu) char *resched_name, *callfunc_name, *debug_name; resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu); + if (!resched_name) + goto fail_mem; per_cpu(xen_resched_irq, cpu).name = resched_name; rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR, cpu, @@ -77,6 +79,8 @@ int xen_smp_intr_init(unsigned int cpu) per_cpu(xen_resched_irq, cpu).irq = rc; callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu); + if (!callfunc_name) + goto fail_mem; per_cpu(xen_callfunc_irq, cpu).name = callfunc_name; rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR, cpu, @@ -90,6 +94,9 @@ int xen_smp_intr_init(unsigned int cpu) if (!xen_fifo_events) { debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu); + if (!debug_name) + goto fail_mem; + per_cpu(xen_debug_irq, cpu).name = debug_name; rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt, @@ -101,6 +108,9 @@ int xen_smp_intr_init(unsigned int cpu) } callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu); + if (!callfunc_name) + goto fail_mem; + per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name; rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR, cpu, @@ -114,6 +124,8 @@ int xen_smp_intr_init(unsigned int cpu) return 0; + fail_mem: + rc = -ENOMEM; fail: xen_smp_intr_free(cpu); return rc; diff --git a/arch/xtensa/include/asm/jump_label.h b/arch/xtensa/include/asm/jump_label.h index c812bf85021c02db59d107fda752dba2872e3b60..46c8596259d2d921fc0395a9eaf8dd444032029c 100644 --- a/arch/xtensa/include/asm/jump_label.h +++ b/arch/xtensa/include/asm/jump_label.h @@ -13,7 +13,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" "_nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".word 1b, %l[l_yes], %c0\n\t" @@ -38,7 +38,7 @@ static __always_inline bool arch_static_branch_jump(struct static_key *key, * make it reachable and wrap both into a no-transform block * to avoid any assembler interference with this. */ - asm_volatile_goto("1:\n\t" + asm goto("1:\n\t" ".begin no-transform\n\t" "_j %l[l_yes]\n\t" "2:\n\t" diff --git a/block/bio.c b/block/bio.c index 74c2818c7ec99dcb7fda12060ef870c1180e81bb..3318e0022fdfd19584f12b5c2b18c14ce7d99c4f 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1112,19 +1112,16 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty) struct folio_iter fi; bio_for_each_folio_all(fi, bio) { - struct page *page; - size_t done = 0; + size_t nr_pages; if (mark_dirty) { folio_lock(fi.folio); folio_mark_dirty(fi.folio); folio_unlock(fi.folio); } - page = folio_page(fi.folio, fi.offset / PAGE_SIZE); - do { - folio_put(fi.folio); - done += PAGE_SIZE; - } while (done < fi.length); + nr_pages = (fi.offset + fi.length - 1) / PAGE_SIZE - + fi.offset / PAGE_SIZE + 1; + folio_put_refs(fi.folio, nr_pages); } } EXPORT_SYMBOL_GPL(__bio_release_pages); diff --git a/block/blk-core.c b/block/blk-core.c index 6eaf2b0ad7cca7d5b3eb1bc2dd5a42bb9c4e1ca7..aefdf07bdc2cfce870e23cf1ac6892f61dc7432d 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -864,7 +864,16 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags) */ blk_flush_plug(current->plug, false); - if (bio_queue_enter(bio)) + /* + * We need to be able to enter a frozen queue, similar to how + * timeouts also need to do that. If that is blocked, then we can + * have pending IO when a queue freeze is started, and then the + * wait for the freeze to finish will wait for polled requests to + * timeout as the poller is preventer from entering the queue and + * completing them. As long as we prevent new IO from being queued, + * that should be all that matters. + */ + if (!percpu_ref_tryget(&q->q_usage_counter)) return 0; if (queue_is_mq(q)) { ret = blk_mq_poll(q, cookie, iob, flags); diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 7dd6a33e1d6a8aaec70ee25a4cb07a536c82a62f..64b594d660b79f2fffa1d7da66d7c295c232aa5d 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1331,16 +1331,24 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct blkcg_gq *blkg = iocg_to_blkg(iocg); - u64 tdelta, delay, new_delay; + u64 tdelta, delay, new_delay, shift; s64 vover, vover_pct; u32 hwa; lockdep_assert_held(&iocg->waitq.lock); + /* + * If the delay is set by another CPU, we may be in the past. No need to + * change anything if so. This avoids decay calculation underflow. + */ + if (time_before64(now->now, iocg->delay_at)) + return false; + /* calculate the current delay in effect - 1/2 every second */ tdelta = now->now - iocg->delay_at; - if (iocg->delay) - delay = iocg->delay >> div64_u64(tdelta, USEC_PER_SEC); + shift = div64_u64(tdelta, USEC_PER_SEC); + if (iocg->delay && shift < BITS_PER_LONG) + delay = iocg->delay >> shift; else delay = 0; diff --git a/block/blk-map.c b/block/blk-map.c index 66da9e2b19abffd9d92d9961fa8cce8210a593d2..b337ae347bfa3ca0996b22b5de4d840f39615e10 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -203,12 +203,19 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data, /* * success */ - if ((iov_iter_rw(iter) == WRITE && - (!map_data || !map_data->null_mapped)) || - (map_data && map_data->from_user)) { + if (iov_iter_rw(iter) == WRITE && + (!map_data || !map_data->null_mapped)) { ret = bio_copy_from_iter(bio, iter); if (ret) goto cleanup; + } else if (map_data && map_data->from_user) { + struct iov_iter iter2 = *iter; + + /* This is the copy-in part of SG_DXFER_TO_FROM_DEV. */ + iter2.data_source = ITER_SOURCE; + ret = bio_copy_from_iter(bio, &iter2); + if (ret) + goto cleanup; } else { if (bmd->is_our_pages) zero_fill_bio(bio); diff --git a/block/blk-mq.c b/block/blk-mq.c index c07e5eebcbd8533c3aedfeb14d2d49571423132d..e1b12f3d54bd4d811574a4cf1b67d8f7cc2f5fda 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -675,6 +675,22 @@ out_queue_exit: } EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx); +static void blk_mq_finish_request(struct request *rq) +{ + struct request_queue *q = rq->q; + + if ((rq->rq_flags & RQF_ELVPRIV) && + q->elevator->type->ops.finish_request) { + q->elevator->type->ops.finish_request(rq); + /* + * For postflush request that may need to be + * completed twice, we should clear this flag + * to avoid double finish_request() on the rq. + */ + rq->rq_flags &= ~RQF_ELVPRIV; + } +} + static void __blk_mq_free_request(struct request *rq) { struct request_queue *q = rq->q; @@ -701,9 +717,7 @@ void blk_mq_free_request(struct request *rq) { struct request_queue *q = rq->q; - if ((rq->rq_flags & RQF_ELVPRIV) && - q->elevator->type->ops.finish_request) - q->elevator->type->ops.finish_request(rq); + blk_mq_finish_request(rq); if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq))) laptop_io_completion(q->disk->bdi); @@ -1020,6 +1034,8 @@ inline void __blk_mq_end_request(struct request *rq, blk_status_t error) if (blk_mq_need_time_stamp(rq)) __blk_mq_end_request_acct(rq, ktime_get_ns()); + blk_mq_finish_request(rq); + if (rq->end_io) { rq_qos_done(rq->q, rq); if (rq->end_io(rq, error) == RQ_END_IO_FREE) @@ -1074,6 +1090,8 @@ void blk_mq_end_request_batch(struct io_comp_batch *iob) if (iob->need_ts) __blk_mq_end_request_acct(rq, now); + blk_mq_finish_request(rq); + rq_qos_done(rq->q, rq); /* diff --git a/block/blk-settings.c b/block/blk-settings.c index bbca4ce77a2d35ce51f24d0781fbc5260cdaabc6..c702f408bbc0abee8d19e2d3547c404433507dcd 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -680,6 +680,10 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->zone_write_granularity = max(t->zone_write_granularity, b->zone_write_granularity); t->zoned = max(t->zoned, b->zoned); + if (!t->zoned) { + t->zone_write_granularity = 0; + t->max_zone_append_sectors = 0; + } return ret; } EXPORT_SYMBOL(blk_stack_limits); diff --git a/block/blk-stat.c b/block/blk-stat.c index da9407b7d4abffac24d622958d1ec2c7546f362b..41be89ecaf20e9a2cac10dc238e42ed186a735f4 100644 --- a/block/blk-stat.c +++ b/block/blk-stat.c @@ -28,7 +28,7 @@ void blk_rq_stat_init(struct blk_rq_stat *stat) /* src is a per-cpu stat, mean isn't initialized */ void blk_rq_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src) { - if (!src->nr_samples) + if (dst->nr_samples + src->nr_samples <= dst->nr_samples) return; dst->min = min(dst->min, src->min); diff --git a/block/ioctl.c b/block/ioctl.c index 47567ba1185a64c87286cba873180d6abce0c7fb..99b8e2e448729f08f84ce89a772e49a89f8c9c41 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -89,7 +89,7 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, unsigned long arg) { uint64_t range[2]; - uint64_t start, len; + uint64_t start, len, end; struct inode *inode = bdev->bd_inode; int err; @@ -110,7 +110,8 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, if (len & 511) return -EINVAL; - if (start + len > bdev_nr_bytes(bdev)) + if (check_add_overflow(start, len, &end) || + end > bdev_nr_bytes(bdev)) return -EINVAL; filemap_invalidate_lock(inode->i_mapping); diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 55e26065c2e27501f34c487b45ca879ad2a72cc6..f10c2a0d18d41170bd565e96d0aa1c2c10160f40 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -622,9 +622,8 @@ static void dd_depth_updated(struct blk_mq_hw_ctx *hctx) struct request_queue *q = hctx->queue; struct deadline_data *dd = q->elevator->elevator_data; struct blk_mq_tags *tags = hctx->sched_tags; - unsigned int shift = tags->bitmap_tags.sb.shift; - dd->async_depth = max(1U, 3 * (1U << shift) / 4); + dd->async_depth = max(1UL, 3 * q->nr_requests / 4); sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, dd->async_depth); } diff --git a/block/opal_proto.h b/block/opal_proto.h index 7152aa1f1a49e3bf177ce65f4e64990892deca57..7f306b08a0fe7c59c8bc2c48dd69f3a0e5b471fb 100644 --- a/block/opal_proto.h +++ b/block/opal_proto.h @@ -71,6 +71,7 @@ enum opal_response_token { #define SHORT_ATOM_BYTE 0xBF #define MEDIUM_ATOM_BYTE 0xDF #define LONG_ATOM_BYTE 0xE3 +#define EMPTY_ATOM_BYTE 0xFF #define OPAL_INVAL_PARAM 12 #define OPAL_MANUFACTURED_INACTIVE 0x08 diff --git a/block/sed-opal.c b/block/sed-opal.c index 9bdb833e5817dad4f0caa2ce0e86dfe772249152..25e4ce452c1d3812049170a3aeb18d7fb908bc8c 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -935,16 +935,20 @@ static int response_parse(const u8 *buf, size_t length, token_length = response_parse_medium(iter, pos); else if (pos[0] <= LONG_ATOM_BYTE) /* long atom */ token_length = response_parse_long(iter, pos); + else if (pos[0] == EMPTY_ATOM_BYTE) /* empty atom */ + token_length = 1; else /* TOKEN */ token_length = response_parse_token(iter, pos); if (token_length < 0) return token_length; + if (pos[0] != EMPTY_ATOM_BYTE) + num_entries++; + pos += token_length; total -= token_length; iter++; - num_entries++; } resp->num = num_entries; diff --git a/crypto/Kconfig b/crypto/Kconfig index d779667671b23f03c57b5e887627f06da775ef2f..edf193aff23e72faf6ec470eadb44100f3780c9a 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -1285,10 +1285,11 @@ config CRYPTO_JITTERENTROPY A non-physical non-deterministic ("true") RNG (e.g., an entropy source compliant with NIST SP800-90B) intended to provide a seed to a - deterministic RNG (e.g. per NIST SP800-90C). + deterministic RNG (e.g., per NIST SP800-90C). This RNG does not perform any cryptographic whitening of the generated + random numbers. - See https://www.chronox.de/jent.html + See https://www.chronox.de/jent/ config CRYPTO_KDF800108_CTR tristate diff --git a/crypto/algapi.c b/crypto/algapi.c index c73d1359b9d41dc5df5d794f53207580be6415da..5dc9ccdd5a510a5645398121ab5a475cfb2d0c92 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -290,7 +290,6 @@ static struct crypto_larval *__crypto_register_alg(struct crypto_alg *alg) } if (!strcmp(q->cra_driver_name, alg->cra_name) || - !strcmp(q->cra_driver_name, alg->cra_driver_name) || !strcmp(q->cra_name, alg->cra_driver_name)) goto err; } diff --git a/drivers/accessibility/speakup/main.c b/drivers/accessibility/speakup/main.c index 73db0cb44fc7b075ce84ddc70300b81ae5344ef9..45d906f17ea3d03e1599ffbe47d57b8373da26c0 100644 --- a/drivers/accessibility/speakup/main.c +++ b/drivers/accessibility/speakup/main.c @@ -573,7 +573,7 @@ static u_long get_word(struct vc_data *vc) } attr_ch = get_char(vc, (u_short *)tmp_pos, &spk_attr); buf[cnt++] = attr_ch; - while (tmpx < vc->vc_cols - 1) { + while (tmpx < vc->vc_cols - 1 && cnt < sizeof(buf) - 1) { tmp_pos += 2; tmpx++; ch = get_char(vc, (u_short *)tmp_pos, &temp); diff --git a/drivers/accessibility/speakup/synth.c b/drivers/accessibility/speakup/synth.c index eea2a2fa4f0159af7ece0add14d5b23100f6d49f..45f90610313382cac117da4cbe93d1d782a96054 100644 --- a/drivers/accessibility/speakup/synth.c +++ b/drivers/accessibility/speakup/synth.c @@ -208,8 +208,10 @@ void spk_do_flush(void) wake_up_process(speakup_task); } -void synth_write(const char *buf, size_t count) +void synth_write(const char *_buf, size_t count) { + const unsigned char *buf = (const unsigned char *) _buf; + while (count--) synth_buffer_add(*buf++); synth_start(); diff --git a/drivers/acpi/acpica/dbnames.c b/drivers/acpi/acpica/dbnames.c index b91155ea9c343cd82871b3dc0638a2143a0f11bf..c9131259f717b0cf37f939bb39f5dada23d12ddc 100644 --- a/drivers/acpi/acpica/dbnames.c +++ b/drivers/acpi/acpica/dbnames.c @@ -550,8 +550,12 @@ acpi_db_walk_for_fields(acpi_handle obj_handle, ACPI_FREE(buffer.pointer); buffer.length = ACPI_ALLOCATE_LOCAL_BUFFER; - acpi_evaluate_object(obj_handle, NULL, NULL, &buffer); - + status = acpi_evaluate_object(obj_handle, NULL, NULL, &buffer); + if (ACPI_FAILURE(status)) { + acpi_os_printf("Could Not evaluate object %p\n", + obj_handle); + return (AE_OK); + } /* * Since this is a field unit, surround the output in braces */ diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 093675b1a1ffbe04614e7b3a317ea835a14685ae..49339f37d940512a9a5917e84dae03eb6961d49d 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -163,6 +163,13 @@ show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, nominal_freq); show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, reference_perf); show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, wraparound_time); +/* Check for valid access_width, otherwise, fallback to using bit_width */ +#define GET_BIT_WIDTH(reg) ((reg)->access_width ? (8 << ((reg)->access_width - 1)) : (reg)->bit_width) + +/* Shift and apply the mask for CPC reads/writes */ +#define MASK_VAL(reg, val) (((val) >> (reg)->bit_offset) & \ + GENMASK(((reg)->bit_width) - 1, 0)) + static ssize_t show_feedback_ctrs(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -776,6 +783,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) } else if (gas_t->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { if (gas_t->address) { void __iomem *addr; + size_t access_width; if (!osc_cpc_flexible_adr_space_confirmed) { pr_debug("Flexible address space capability not supported\n"); @@ -783,7 +791,8 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) goto out_free; } - addr = ioremap(gas_t->address, gas_t->bit_width/8); + access_width = GET_BIT_WIDTH(gas_t) / 8; + addr = ioremap(gas_t->address, access_width); if (!addr) goto out_free; cpc_ptr->cpc_regs[i-2].sys_mem_vaddr = addr; @@ -979,6 +988,7 @@ int __weak cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val) static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) { void __iomem *vaddr = NULL; + int size; int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu); struct cpc_reg *reg = ®_res->cpc_entry.reg; @@ -988,14 +998,14 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) } *val = 0; + size = GET_BIT_WIDTH(reg); if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) { - u32 width = 8 << (reg->access_width - 1); u32 val_u32; acpi_status status; status = acpi_os_read_port((acpi_io_address)reg->address, - &val_u32, width); + &val_u32, size); if (ACPI_FAILURE(status)) { pr_debug("Error: Failed to read SystemIO port %llx\n", reg->address); @@ -1004,17 +1014,24 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) *val = val_u32; return 0; - } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) + } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) { + /* + * For registers in PCC space, the register size is determined + * by the bit width field; the access size is used to indicate + * the PCC subspace id. + */ + size = reg->bit_width; vaddr = GET_PCC_VADDR(reg->address, pcc_ss_id); + } else if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) vaddr = reg_res->sys_mem_vaddr; else if (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) return cpc_read_ffh(cpu, reg, val); else return acpi_os_read_memory((acpi_physical_address)reg->address, - val, reg->bit_width); + val, size); - switch (reg->bit_width) { + switch (size) { case 8: *val = readb_relaxed(vaddr); break; @@ -1028,27 +1045,37 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) *val = readq_relaxed(vaddr); break; default: - pr_debug("Error: Cannot read %u bit width from PCC for ss: %d\n", - reg->bit_width, pcc_ss_id); + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { + pr_debug("Error: Cannot read %u bit width from system memory: 0x%llx\n", + size, reg->address); + } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM) { + pr_debug("Error: Cannot read %u bit width from PCC for ss: %d\n", + size, pcc_ss_id); + } return -EFAULT; } + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) + *val = MASK_VAL(reg, *val); + return 0; } static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) { int ret_val = 0; + int size; void __iomem *vaddr = NULL; int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu); struct cpc_reg *reg = ®_res->cpc_entry.reg; + size = GET_BIT_WIDTH(reg); + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) { - u32 width = 8 << (reg->access_width - 1); acpi_status status; status = acpi_os_write_port((acpi_io_address)reg->address, - (u32)val, width); + (u32)val, size); if (ACPI_FAILURE(status)) { pr_debug("Error: Failed to write SystemIO port %llx\n", reg->address); @@ -1056,17 +1083,27 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) } return 0; - } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) + } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) { + /* + * For registers in PCC space, the register size is determined + * by the bit width field; the access size is used to indicate + * the PCC subspace id. + */ + size = reg->bit_width; vaddr = GET_PCC_VADDR(reg->address, pcc_ss_id); + } else if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) vaddr = reg_res->sys_mem_vaddr; else if (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) return cpc_write_ffh(cpu, reg, val); else return acpi_os_write_memory((acpi_physical_address)reg->address, - val, reg->bit_width); + val, size); + + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) + val = MASK_VAL(reg, val); - switch (reg->bit_width) { + switch (size) { case 8: writeb_relaxed(val, vaddr); break; @@ -1080,8 +1117,13 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) writeq_relaxed(val, vaddr); break; default: - pr_debug("Error: Cannot write %u bit width to PCC for ss: %d\n", - reg->bit_width, pcc_ss_id); + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { + pr_debug("Error: Cannot write %u bit width to system memory: 0x%llx\n", + size, reg->address); + } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM) { + pr_debug("Error: Cannot write %u bit width to PCC for ss: %d\n", + size, pcc_ss_id); + } ret_val = -EFAULT; break; } diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index fc5b5b2c9e8194e6de3ca51724bb847f15102e98..6f613eef2887947aea71b22c5f41d11987f75fcb 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -1431,6 +1431,8 @@ int acpi_processor_power_exit(struct acpi_processor *pr) acpi_processor_registered--; if (acpi_processor_registered == 0) cpuidle_unregister_driver(&acpi_idle_driver); + + kfree(dev); } pr->flags.power_setup_done = 0; diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 5ebeb0d7b6be09f47e09d77bb86f8c06d362ec81..1c5c1a269fbee466db616f4ea1b62f58f8af5917 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -543,6 +543,39 @@ static const struct dmi_system_id lg_laptop[] = { DMI_MATCH(DMI_BOARD_NAME, "17U70P"), }, }, + { + /* Infinity E15-5A165-BM */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GM5RG1E0009COM"), + }, + }, + { + /* Infinity E15-5A305-1M */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GM5RGEE0016COM"), + }, + }, + { + /* Lunnen Ground 15 / AMD Ryzen 5 5500U */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Lunnen"), + DMI_MATCH(DMI_BOARD_NAME, "LLL5DAW"), + }, + }, + { + /* Lunnen Ground 16 / AMD Ryzen 7 5800U */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Lunnen"), + DMI_MATCH(DMI_BOARD_NAME, "LL6FA"), + }, + }, + { + /* MAIBENBEN X577 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "MAIBENBEN"), + DMI_MATCH(DMI_BOARD_NAME, "X577"), + }, + }, { } }; diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 94154a849a3ead0e30cd1f45b93990aecea7e5c9..293cdf486fd81364d840d0492957d8a6bec5f8a2 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -315,18 +315,14 @@ static int acpi_scan_device_check(struct acpi_device *adev) * again). */ if (adev->handler) { - dev_warn(&adev->dev, "Already enumerated\n"); - return -EALREADY; + dev_dbg(&adev->dev, "Already enumerated\n"); + return 0; } error = acpi_bus_scan(adev->handle); if (error) { dev_warn(&adev->dev, "Namespace scan failure\n"); return error; } - if (!adev->handler) { - dev_warn(&adev->dev, "Enumeration failure\n"); - error = -ENODEV; - } } else { error = acpi_scan_device_not_present(adev); } diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 539c12fbd2f14dd3099d86028ee873546ee678bb..6026e20f022a28a0cd045d95e4f4f8be6f297c2e 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -385,18 +385,6 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "20GGA00L00"), }, }, - /* - * ASUS B1400CEAE hangs on resume from suspend (see - * https://bugzilla.kernel.org/show_bug.cgi?id=215742). - */ - { - .callback = init_default_s3, - .ident = "ASUS B1400CEAE", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "ASUS EXPERTBOOK B1400CEAE"), - }, - }, {}, }; diff --git a/drivers/android/binder.c b/drivers/android/binder.c index d933ef6cc65af71de49cfd4d560dd2e22847f12c..46111f8c12e61946ccf0d7a3d64c71f357dcbbb1 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -477,6 +477,16 @@ binder_enqueue_thread_work_ilocked(struct binder_thread *thread, { WARN_ON(!list_empty(&thread->waiting_thread_node)); binder_enqueue_work_ilocked(work, &thread->todo); + + /* (e)poll-based threads require an explicit wakeup signal when + * queuing their own work; they rely on these events to consume + * messages without I/O block. Without it, threads risk waiting + * indefinitely without handling the work. + */ + if (thread->looper & BINDER_LOOPER_STATE_POLL && + thread->pid == current->pid && !thread->process_todo) + wake_up_interruptible_sync(&thread->wait); + thread->process_todo = true; } @@ -1697,8 +1707,10 @@ static size_t binder_get_object(struct binder_proc *proc, size_t object_size = 0; read_size = min_t(size_t, sizeof(*object), buffer->data_size - offset); - if (offset > buffer->data_size || read_size < sizeof(*hdr)) + if (offset > buffer->data_size || read_size < sizeof(*hdr) || + !IS_ALIGNED(offset, sizeof(u32))) return 0; + if (u) { if (copy_from_user(object, u + offset, read_size)) return 0; @@ -5338,7 +5350,7 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) goto err; break; case BINDER_SET_MAX_THREADS: { - int max_threads; + u32 max_threads; if (copy_from_user(&max_threads, ubuf, sizeof(max_threads))) { diff --git a/drivers/android/binder_internal.h b/drivers/android/binder_internal.h index abe19d88c6ecc636fae4029e688b01b2dcea9bb9..c2c1bb3c1e60bae5064345f9b3e427ddf3081616 100644 --- a/drivers/android/binder_internal.h +++ b/drivers/android/binder_internal.h @@ -420,7 +420,7 @@ struct binder_proc { struct list_head todo; struct binder_stats stats; struct list_head delivered_death; - int max_threads; + u32 max_threads; int requested_threads; int requested_threads_started; int tmp_ref; diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 805645efb3ccfc7d0f9b15aca58c2de9f6b1c896..17119e8dc8c308506da4be5257e4013ad8f23fc1 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -49,6 +49,7 @@ enum { enum board_ids { /* board IDs by feature in alphabetical order */ board_ahci, + board_ahci_43bit_dma, board_ahci_ign_iferr, board_ahci_low_power, board_ahci_no_debounce_delay, @@ -129,6 +130,13 @@ static const struct ata_port_info ahci_port_info[] = { .udma_mask = ATA_UDMA6, .port_ops = &ahci_ops, }, + [board_ahci_43bit_dma] = { + AHCI_HFLAGS (AHCI_HFLAG_43BIT_ONLY), + .flags = AHCI_FLAG_COMMON, + .pio_mask = ATA_PIO4, + .udma_mask = ATA_UDMA6, + .port_ops = &ahci_ops, + }, [board_ahci_ign_iferr] = { AHCI_HFLAGS (AHCI_HFLAG_IGN_IRQ_IF_ERR), .flags = AHCI_FLAG_COMMON, @@ -597,14 +605,19 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(PROMISE, 0x3f20), board_ahci }, /* PDC42819 */ { PCI_VDEVICE(PROMISE, 0x3781), board_ahci }, /* FastTrak TX8660 ahci-mode */ - /* Asmedia */ - { PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci }, /* ASM1060 */ - { PCI_VDEVICE(ASMEDIA, 0x0602), board_ahci }, /* ASM1060 */ - { PCI_VDEVICE(ASMEDIA, 0x0611), board_ahci }, /* ASM1061 */ - { PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci }, /* ASM1062 */ - { PCI_VDEVICE(ASMEDIA, 0x0621), board_ahci }, /* ASM1061R */ - { PCI_VDEVICE(ASMEDIA, 0x0622), board_ahci }, /* ASM1062R */ - { PCI_VDEVICE(ASMEDIA, 0x0624), board_ahci }, /* ASM1062+JMB575 */ + /* ASMedia */ + { PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci_43bit_dma }, /* ASM1060 */ + { PCI_VDEVICE(ASMEDIA, 0x0602), board_ahci_43bit_dma }, /* ASM1060 */ + { PCI_VDEVICE(ASMEDIA, 0x0611), board_ahci_43bit_dma }, /* ASM1061 */ + { PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci_43bit_dma }, /* ASM1061/1062 */ + { PCI_VDEVICE(ASMEDIA, 0x0621), board_ahci_43bit_dma }, /* ASM1061R */ + { PCI_VDEVICE(ASMEDIA, 0x0622), board_ahci_43bit_dma }, /* ASM1062R */ + { PCI_VDEVICE(ASMEDIA, 0x0624), board_ahci_43bit_dma }, /* ASM1062+JMB575 */ + { PCI_VDEVICE(ASMEDIA, 0x1062), board_ahci }, /* ASM1062A */ + { PCI_VDEVICE(ASMEDIA, 0x1064), board_ahci }, /* ASM1064 */ + { PCI_VDEVICE(ASMEDIA, 0x1164), board_ahci }, /* ASM1164 */ + { PCI_VDEVICE(ASMEDIA, 0x1165), board_ahci }, /* ASM1165 */ + { PCI_VDEVICE(ASMEDIA, 0x1166), board_ahci }, /* ASM1166 */ /* * Samsung SSDs found on some macbooks. NCQ times out if MSI is @@ -944,11 +957,20 @@ static int ahci_pci_device_resume(struct device *dev) #endif /* CONFIG_PM */ -static int ahci_configure_dma_masks(struct pci_dev *pdev, int using_dac) +static int ahci_configure_dma_masks(struct pci_dev *pdev, + struct ahci_host_priv *hpriv) { - const int dma_bits = using_dac ? 64 : 32; + int dma_bits; int rc; + if (hpriv->cap & HOST_CAP_64) { + dma_bits = 64; + if (hpriv->flags & AHCI_HFLAG_43BIT_ONLY) + dma_bits = 43; + } else { + dma_bits = 32; + } + /* * If the device fixup already set the dma_mask to some non-standard * value, don't extend it here. This happens on STA2X11, for example. @@ -1921,7 +1943,7 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) ahci_gtf_filter_workaround(host); /* initialize adapter */ - rc = ahci_configure_dma_masks(pdev, hpriv->cap & HOST_CAP_64); + rc = ahci_configure_dma_masks(pdev, hpriv); if (rc) return rc; diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index ff8e6ae1c6362f2a26abde461910bd1a388f1655..f9c5906a8afa8c8633b9946cff84721909516d7c 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -247,6 +247,7 @@ enum { AHCI_HFLAG_SUSPEND_PHYS = BIT(26), /* handle PHYs during suspend/resume */ AHCI_HFLAG_NO_SXS = BIT(28), /* SXS not supported */ + AHCI_HFLAG_43BIT_ONLY = BIT(29), /* 43bit DMA addr limit */ /* ap->flags bits */ diff --git a/drivers/ata/ahci_ceva.c b/drivers/ata/ahci_ceva.c index cb24ecf36fafe040c97aa7c90eb02f76c87c249c..50e07ea60e45c86cbab620e6dd8132ed64955510 100644 --- a/drivers/ata/ahci_ceva.c +++ b/drivers/ata/ahci_ceva.c @@ -88,7 +88,6 @@ struct ceva_ahci_priv { u32 axicc; bool is_cci_enabled; int flags; - struct reset_control *rst; }; static unsigned int ceva_ahci_read_id(struct ata_device *dev, @@ -189,6 +188,60 @@ static struct scsi_host_template ahci_platform_sht = { AHCI_SHT(DRV_NAME), }; +static int ceva_ahci_platform_enable_resources(struct ahci_host_priv *hpriv) +{ + int rc, i; + + rc = ahci_platform_enable_regulators(hpriv); + if (rc) + return rc; + + rc = ahci_platform_enable_clks(hpriv); + if (rc) + goto disable_regulator; + + /* Assert the controller reset */ + rc = ahci_platform_assert_rsts(hpriv); + if (rc) + goto disable_clks; + + for (i = 0; i < hpriv->nports; i++) { + rc = phy_init(hpriv->phys[i]); + if (rc) + goto disable_rsts; + } + + /* De-assert the controller reset */ + ahci_platform_deassert_rsts(hpriv); + + for (i = 0; i < hpriv->nports; i++) { + rc = phy_power_on(hpriv->phys[i]); + if (rc) { + phy_exit(hpriv->phys[i]); + goto disable_phys; + } + } + + return 0; + +disable_rsts: + ahci_platform_deassert_rsts(hpriv); + +disable_phys: + while (--i >= 0) { + phy_power_off(hpriv->phys[i]); + phy_exit(hpriv->phys[i]); + } + +disable_clks: + ahci_platform_disable_clks(hpriv); + +disable_regulator: + ahci_platform_disable_regulators(hpriv); + + return rc; +} + static int ceva_ahci_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; @@ -203,47 +256,19 @@ static int ceva_ahci_probe(struct platform_device *pdev) return -ENOMEM; cevapriv->ahci_pdev = pdev; - - cevapriv->rst = devm_reset_control_get_optional_exclusive(&pdev->dev, - NULL); - if (IS_ERR(cevapriv->rst)) - dev_err_probe(&pdev->dev, PTR_ERR(cevapriv->rst), - "failed to get reset\n"); - hpriv = ahci_platform_get_resources(pdev, 0); if (IS_ERR(hpriv)) return PTR_ERR(hpriv); - if (!cevapriv->rst) { - rc = ahci_platform_enable_resources(hpriv); - if (rc) - return rc; - } else { - int i; + hpriv->rsts = devm_reset_control_get_optional_exclusive(&pdev->dev, + NULL); + if (IS_ERR(hpriv->rsts)) + return dev_err_probe(&pdev->dev, PTR_ERR(hpriv->rsts), + "failed to get reset\n"); - rc = ahci_platform_enable_clks(hpriv); - if (rc) - return rc; - /* Assert the controller reset */ - reset_control_assert(cevapriv->rst); - - for (i = 0; i < hpriv->nports; i++) { - rc = phy_init(hpriv->phys[i]); - if (rc) - return rc; - } - - /* De-assert the controller reset */ - reset_control_deassert(cevapriv->rst); - - for (i = 0; i < hpriv->nports; i++) { - rc = phy_power_on(hpriv->phys[i]); - if (rc) { - phy_exit(hpriv->phys[i]); - return rc; - } - } - } + rc = ceva_ahci_platform_enable_resources(hpriv); + if (rc) + return rc; if (of_property_read_bool(np, "ceva,broken-gen2")) cevapriv->flags = CEVA_FLAG_BROKEN_GEN2; @@ -252,52 +277,60 @@ static int ceva_ahci_probe(struct platform_device *pdev) if (of_property_read_u8_array(np, "ceva,p0-cominit-params", (u8 *)&cevapriv->pp2c[0], 4) < 0) { dev_warn(dev, "ceva,p0-cominit-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } if (of_property_read_u8_array(np, "ceva,p1-cominit-params", (u8 *)&cevapriv->pp2c[1], 4) < 0) { dev_warn(dev, "ceva,p1-cominit-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } /* Read OOB timing value for COMWAKE from device-tree*/ if (of_property_read_u8_array(np, "ceva,p0-comwake-params", (u8 *)&cevapriv->pp3c[0], 4) < 0) { dev_warn(dev, "ceva,p0-comwake-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } if (of_property_read_u8_array(np, "ceva,p1-comwake-params", (u8 *)&cevapriv->pp3c[1], 4) < 0) { dev_warn(dev, "ceva,p1-comwake-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } /* Read phy BURST timing value from device-tree */ if (of_property_read_u8_array(np, "ceva,p0-burst-params", (u8 *)&cevapriv->pp4c[0], 4) < 0) { dev_warn(dev, "ceva,p0-burst-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } if (of_property_read_u8_array(np, "ceva,p1-burst-params", (u8 *)&cevapriv->pp4c[1], 4) < 0) { dev_warn(dev, "ceva,p1-burst-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } /* Read phy RETRY interval timing value from device-tree */ if (of_property_read_u16_array(np, "ceva,p0-retry-params", (u16 *)&cevapriv->pp5c[0], 2) < 0) { dev_warn(dev, "ceva,p0-retry-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } if (of_property_read_u16_array(np, "ceva,p1-retry-params", (u16 *)&cevapriv->pp5c[1], 2) < 0) { dev_warn(dev, "ceva,p1-retry-params property not defined\n"); - return -EINVAL; + rc = -EINVAL; + goto disable_resources; } /* @@ -335,7 +368,7 @@ static int __maybe_unused ceva_ahci_resume(struct device *dev) struct ahci_host_priv *hpriv = host->private_data; int rc; - rc = ahci_platform_enable_resources(hpriv); + rc = ceva_ahci_platform_enable_resources(hpriv); if (rc) return rc; diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index fa2fc1953fc2677ab017fe1a827d3ad7ca7de49d..f14e56a5cff6b83bdd431d4e3aa2adc9524c9254 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2005,6 +2005,10 @@ void ata_dev_power_set_active(struct ata_device *dev) struct ata_taskfile tf; unsigned int err_mask; + /* If the device is already sleeping, do nothing. */ + if (dev->flags & ATA_DFLAG_SLEEPING) + return; + /* * Issue READ VERIFY SECTORS command for 1 sector at lba=0 only * if supported by the device. diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 1eaaf01418ea71922614e34b0d1d575286809996..b8034d194078dfe7ca661c4342313a7c69bdfd5b 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -711,8 +711,10 @@ void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap) ehc->saved_ncq_enabled |= 1 << devno; /* If we are resuming, wake up the device */ - if (ap->pflags & ATA_PFLAG_RESUMING) + if (ap->pflags & ATA_PFLAG_RESUMING) { + dev->flags |= ATA_DFLAG_RESUMING; ehc->i.dev_action[devno] |= ATA_EH_SET_ACTIVE; + } } } @@ -3089,6 +3091,7 @@ static int ata_eh_revalidate_and_attach(struct ata_link *link, return 0; err: + dev->flags &= ~ATA_DFLAG_RESUMING; *r_failed_dev = dev; return rc; } diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index a9da2f05e629729fa0b302f510242fd357712965..65fde5717928b56356f3b711ee80d5f423693abc 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -4652,6 +4652,7 @@ void ata_scsi_dev_rescan(struct work_struct *work) struct ata_link *link; struct ata_device *dev; unsigned long flags; + bool do_resume; int ret = 0; mutex_lock(&ap->scsi_scan_mutex); @@ -4666,25 +4667,34 @@ void ata_scsi_dev_rescan(struct work_struct *work) * bail out. */ if (ap->pflags & ATA_PFLAG_SUSPENDED) - goto unlock; + goto unlock_ap; if (!sdev) continue; if (scsi_device_get(sdev)) continue; + do_resume = dev->flags & ATA_DFLAG_RESUMING; + spin_unlock_irqrestore(ap->lock, flags); + if (do_resume) { + ret = scsi_resume_device(sdev); + if (ret == -EWOULDBLOCK) + goto unlock_scan; + dev->flags &= ~ATA_DFLAG_RESUMING; + } ret = scsi_rescan_device(sdev); scsi_device_put(sdev); spin_lock_irqsave(ap->lock, flags); if (ret) - goto unlock; + goto unlock_ap; } } -unlock: +unlock_ap: spin_unlock_irqrestore(ap->lock, flags); +unlock_scan: mutex_unlock(&ap->scsi_scan_mutex); /* Reschedule with a delay if scsi_rescan_device() returned an error */ diff --git a/drivers/ata/sata_gemini.c b/drivers/ata/sata_gemini.c index c96fcf9ee3c075e0019b48b088a5b1eeb99e5c18..01f050b1bc93b6a4b3dd1e2d8a61da9834f7cbdd 100644 --- a/drivers/ata/sata_gemini.c +++ b/drivers/ata/sata_gemini.c @@ -201,7 +201,10 @@ int gemini_sata_start_bridge(struct sata_gemini *sg, unsigned int bridge) pclk = sg->sata0_pclk; else pclk = sg->sata1_pclk; - clk_enable(pclk); + ret = clk_enable(pclk); + if (ret) + return ret; + msleep(10); /* Do not keep clocking a bridge that is not online */ diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index 17f9062b0eaa526b4b8dd89e6f62ec6cfca0eaf2..9cf540017a5e56aa23e763a799aea1d08e45cfd5 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -787,37 +787,6 @@ static const struct ata_port_info mv_port_info[] = { }, }; -static const struct pci_device_id mv_pci_tbl[] = { - { PCI_VDEVICE(MARVELL, 0x5040), chip_504x }, - { PCI_VDEVICE(MARVELL, 0x5041), chip_504x }, - { PCI_VDEVICE(MARVELL, 0x5080), chip_5080 }, - { PCI_VDEVICE(MARVELL, 0x5081), chip_508x }, - /* RocketRAID 1720/174x have different identifiers */ - { PCI_VDEVICE(TTI, 0x1720), chip_6042 }, - { PCI_VDEVICE(TTI, 0x1740), chip_6042 }, - { PCI_VDEVICE(TTI, 0x1742), chip_6042 }, - - { PCI_VDEVICE(MARVELL, 0x6040), chip_604x }, - { PCI_VDEVICE(MARVELL, 0x6041), chip_604x }, - { PCI_VDEVICE(MARVELL, 0x6042), chip_6042 }, - { PCI_VDEVICE(MARVELL, 0x6080), chip_608x }, - { PCI_VDEVICE(MARVELL, 0x6081), chip_608x }, - - { PCI_VDEVICE(ADAPTEC2, 0x0241), chip_604x }, - - /* Adaptec 1430SA */ - { PCI_VDEVICE(ADAPTEC2, 0x0243), chip_7042 }, - - /* Marvell 7042 support */ - { PCI_VDEVICE(MARVELL, 0x7042), chip_7042 }, - - /* Highpoint RocketRAID PCIe series */ - { PCI_VDEVICE(TTI, 0x2300), chip_7042 }, - { PCI_VDEVICE(TTI, 0x2310), chip_7042 }, - - { } /* terminate list */ -}; - static const struct mv_hw_ops mv5xxx_ops = { .phy_errata = mv5_phy_errata, .enable_leds = mv5_enable_leds, @@ -4301,6 +4270,36 @@ static int mv_pci_init_one(struct pci_dev *pdev, static int mv_pci_device_resume(struct pci_dev *pdev); #endif +static const struct pci_device_id mv_pci_tbl[] = { + { PCI_VDEVICE(MARVELL, 0x5040), chip_504x }, + { PCI_VDEVICE(MARVELL, 0x5041), chip_504x }, + { PCI_VDEVICE(MARVELL, 0x5080), chip_5080 }, + { PCI_VDEVICE(MARVELL, 0x5081), chip_508x }, + /* RocketRAID 1720/174x have different identifiers */ + { PCI_VDEVICE(TTI, 0x1720), chip_6042 }, + { PCI_VDEVICE(TTI, 0x1740), chip_6042 }, + { PCI_VDEVICE(TTI, 0x1742), chip_6042 }, + + { PCI_VDEVICE(MARVELL, 0x6040), chip_604x }, + { PCI_VDEVICE(MARVELL, 0x6041), chip_604x }, + { PCI_VDEVICE(MARVELL, 0x6042), chip_6042 }, + { PCI_VDEVICE(MARVELL, 0x6080), chip_608x }, + { PCI_VDEVICE(MARVELL, 0x6081), chip_608x }, + + { PCI_VDEVICE(ADAPTEC2, 0x0241), chip_604x }, + + /* Adaptec 1430SA */ + { PCI_VDEVICE(ADAPTEC2, 0x0243), chip_7042 }, + + /* Marvell 7042 support */ + { PCI_VDEVICE(MARVELL, 0x7042), chip_7042 }, + + /* Highpoint RocketRAID PCIe series */ + { PCI_VDEVICE(TTI, 0x2300), chip_7042 }, + { PCI_VDEVICE(TTI, 0x2310), chip_7042 }, + + { } /* terminate list */ +}; static struct pci_driver mv_pci_driver = { .name = DRV_NAME, @@ -4313,6 +4312,7 @@ static struct pci_driver mv_pci_driver = { #endif }; +MODULE_DEVICE_TABLE(pci, mv_pci_tbl); /** * mv_print_info - Dump key info to kernel log for perusal. @@ -4485,7 +4485,6 @@ static void __exit mv_exit(void) MODULE_AUTHOR("Brett Russ"); MODULE_DESCRIPTION("SCSI low-level driver for Marvell SATA controllers"); MODULE_LICENSE("GPL v2"); -MODULE_DEVICE_TABLE(pci, mv_pci_tbl); MODULE_VERSION(DRV_VERSION); MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c index 6ceec59cb2913c2228e2e629ab6435f647fe7e35..fa1966638c0605337e878968b03fd62de3fe0a9a 100644 --- a/drivers/ata/sata_sx4.c +++ b/drivers/ata/sata_sx4.c @@ -958,8 +958,7 @@ static void pdc20621_get_from_dimm(struct ata_host *host, void *psource, offset -= (idx * window_size); idx++; - dist = ((long) (window_size - (offset + size))) >= 0 ? size : - (long) (window_size - offset); + dist = min(size, window_size - offset); memcpy_fromio(psource, dimm_mmio + offset / 4, dist); psource += dist; @@ -1006,8 +1005,7 @@ static void pdc20621_put_to_dimm(struct ata_host *host, void *psource, readl(mmio + PDC_DIMM_WINDOW_CTLR); offset -= (idx * window_size); idx++; - dist = ((long)(s32)(window_size - (offset + size))) >= 0 ? size : - (long) (window_size - offset); + dist = min(size, window_size - offset); memcpy_toio(dimm_mmio + offset / 4, psource, dist); writel(0x01, mmio + PDC_GENERAL_CTLR); readl(mmio + PDC_GENERAL_CTLR); diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index 49cb4537344aa80ae6219c8596d39161e6e0c925..2daf50d4cd47adf2a5ae5b74e177564721f48438 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -2930,6 +2930,8 @@ open_card_ubr0(struct idt77252_dev *card) vc->scq = alloc_scq(card, vc->class); if (!vc->scq) { printk("%s: can't get SCQ.\n", card->name); + kfree(card->vcs[0]); + card->vcs[0] = NULL; return -ENOMEM; } diff --git a/drivers/base/core.c b/drivers/base/core.c index af90bfb0cc3d8445b034d6a2245da043e4158828..8d87808cdb8aad2b08c47ca8cf385f6f1c16af87 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -56,6 +56,7 @@ static bool fw_devlink_is_permissive(void); static void __fw_devlink_link_to_consumers(struct device *dev); static bool fw_devlink_drv_reg_done; static bool fw_devlink_best_effort; +static struct workqueue_struct *device_link_wq; /** * __fwnode_link_add - Create a link between two fwnode_handles. @@ -337,10 +338,12 @@ static bool device_is_ancestor(struct device *dev, struct device *target) return false; } +#define DL_MARKER_FLAGS (DL_FLAG_INFERRED | \ + DL_FLAG_CYCLE | \ + DL_FLAG_MANAGED) static inline bool device_link_flag_is_sync_state_only(u32 flags) { - return (flags & ~(DL_FLAG_INFERRED | DL_FLAG_CYCLE)) == - (DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED); + return (flags & ~DL_MARKER_FLAGS) == DL_FLAG_SYNC_STATE_ONLY; } /** @@ -583,12 +586,26 @@ static void devlink_dev_release(struct device *dev) /* * It may take a while to complete this work because of the SRCU * synchronization in device_link_release_fn() and if the consumer or - * supplier devices get deleted when it runs, so put it into the "long" - * workqueue. + * supplier devices get deleted when it runs, so put it into the + * dedicated workqueue. */ - queue_work(system_long_wq, &link->rm_work); + queue_work(device_link_wq, &link->rm_work); } +/** + * device_link_wait_removal - Wait for ongoing devlink removal jobs to terminate + */ +void device_link_wait_removal(void) +{ + /* + * devlink removal jobs are queued in the dedicated work queue. + * To be sure that all removal jobs are terminated, ensure that any + * scheduled work has run to completion. + */ + flush_workqueue(device_link_wq); +} +EXPORT_SYMBOL_GPL(device_link_wait_removal); + static struct class devlink_class = { .name = "devlink", .owner = THIS_MODULE, @@ -2054,9 +2071,14 @@ static int fw_devlink_create_devlink(struct device *con, /* * SYNC_STATE_ONLY device links don't block probing and supports cycles. - * So cycle detection isn't necessary and shouldn't be done. + * So, one might expect that cycle detection isn't necessary for them. + * However, if the device link was marked as SYNC_STATE_ONLY because + * it's part of a cycle, then we still need to do cycle detection. This + * is because the consumer and supplier might be part of multiple cycles + * and we need to detect all those cycles. */ - if (!(flags & DL_FLAG_SYNC_STATE_ONLY)) { + if (!device_link_flag_is_sync_state_only(flags) || + flags & DL_FLAG_CYCLE) { device_links_write_lock(); if (__fw_devlink_relax_cycles(con, sup_handle)) { __fwnode_link_cycle(link); @@ -4125,9 +4147,14 @@ int __init devices_init(void) sysfs_dev_char_kobj = kobject_create_and_add("char", dev_kobj); if (!sysfs_dev_char_kobj) goto char_kobj_err; + device_link_wq = alloc_workqueue("device_link_wq", 0, 0); + if (!device_link_wq) + goto wq_err; return 0; + wq_err: + kobject_put(sysfs_dev_char_kobj); char_kobj_err: kobject_put(sysfs_dev_block_kobj); block_kobj_err: diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index dab70a65377c877d6f5ee0ff62d21e53aff59c29..31da94afe4f3ddf51d86e99681ae24315cabe0ed 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -589,6 +589,12 @@ ssize_t __weak cpu_show_spec_rstack_overflow(struct device *dev, return sysfs_emit(buf, "Not affected\n"); } +ssize_t __weak cpu_show_reg_file_data_sampling(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "Not affected\n"); +} + static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); @@ -602,6 +608,7 @@ static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL); static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL); static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL); static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NULL); +static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -617,6 +624,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_retbleed.attr, &dev_attr_gather_data_sampling.attr, &dev_attr_spec_rstack_overflow.attr, + &dev_attr_reg_file_data_sampling.attr, NULL }; diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 56ceba469802425dec4a67a9fdbc8b8bb03d9fad..d238b47f74c348c209ddd0bb2f949ee57a0ca507 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -1052,7 +1052,7 @@ static int __init genpd_power_off_unused(void) return 0; } -late_initcall(genpd_power_off_unused); +late_initcall_sync(genpd_power_off_unused); #ifdef CONFIG_PM_SLEEP diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c index afd094dec5ca387505e517ba88847c06e3d53b5c..ca0c092ba47fb08ecbcef2c3c221230e1a86a043 100644 --- a/drivers/base/power/wakeirq.c +++ b/drivers/base/power/wakeirq.c @@ -362,8 +362,10 @@ void dev_pm_enable_wake_irq_complete(struct device *dev) return; if (wirq->status & WAKE_IRQ_DEDICATED_MANAGED && - wirq->status & WAKE_IRQ_DEDICATED_REVERSE) + wirq->status & WAKE_IRQ_DEDICATED_REVERSE) { enable_irq(wirq->irq); + wirq->status |= WAKE_IRQ_DEDICATED_ENABLED; + } } /** diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index 128722cf6c3cad69dede6a2b3f3748f0ed5e00b8..827802e418dd392286781af384b4a2ec92511938 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -333,6 +333,7 @@ aoeblk_gdalloc(void *vp) struct gendisk *gd; mempool_t *mp; struct blk_mq_tag_set *set; + sector_t ssize; ulong flags; int late = 0; int err; @@ -395,7 +396,7 @@ aoeblk_gdalloc(void *vp) gd->minors = AOE_PARTITIONS; gd->fops = &aoe_bdops; gd->private_data = d; - set_capacity(gd, d->ssize); + ssize = d->ssize; snprintf(gd->disk_name, sizeof gd->disk_name, "etherd/e%ld.%d", d->aoemajor, d->aoeminor); @@ -404,6 +405,8 @@ aoeblk_gdalloc(void *vp) spin_unlock_irqrestore(&d->lock, flags); + set_capacity(gd, ssize); + err = device_add_disk(NULL, gd, aoe_attr_groups); if (err) goto out_disk_cleanup; diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index d7317425be510d1c3d4bbac5a18fba2ea8e76c1d..cc9077b588d7e7af30401ab03c826a358b2a232c 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -419,13 +419,16 @@ aoecmd_cfg_pkts(ushort aoemajor, unsigned char aoeminor, struct sk_buff_head *qu rcu_read_lock(); for_each_netdev_rcu(&init_net, ifp) { dev_hold(ifp); - if (!is_aoe_netif(ifp)) - goto cont; + if (!is_aoe_netif(ifp)) { + dev_put(ifp); + continue; + } skb = new_skb(sizeof *h + sizeof *ch); if (skb == NULL) { printk(KERN_INFO "aoe: skb alloc failure\n"); - goto cont; + dev_put(ifp); + continue; } skb_put(skb, sizeof *h + sizeof *ch); skb->dev = ifp; @@ -440,9 +443,6 @@ aoecmd_cfg_pkts(ushort aoemajor, unsigned char aoeminor, struct sk_buff_head *qu h->major = cpu_to_be16(aoemajor); h->minor = aoeminor; h->cmd = AOECMD_CFG; - -cont: - dev_put(ifp); } rcu_read_unlock(); } diff --git a/drivers/block/aoe/aoenet.c b/drivers/block/aoe/aoenet.c index 63773a90581dd36818051a114e38b5b60af0a874..1e66c7a188a1217d7a7205230e2f9557f6ddcf31 100644 --- a/drivers/block/aoe/aoenet.c +++ b/drivers/block/aoe/aoenet.c @@ -64,6 +64,7 @@ tx(int id) __must_hold(&txlock) pr_warn("aoe: packet could not be sent on %s. %s\n", ifp ? ifp->name : "netif", "consider increasing tx_queue_len"); + dev_put(ifp); spin_lock_irq(&txlock); } return 0; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 9a53165de4cef6922041ae95d9b691ce0dd811d3..5c4be8dda253c3309edbda9684e07301a40c379b 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -2408,6 +2408,12 @@ static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info) } dev_list = nla_nest_start_noflag(reply, NBD_ATTR_DEVICE_LIST); + if (!dev_list) { + nlmsg_free(reply); + ret = -EMSGSIZE; + goto out; + } + if (index == -1) { ret = idr_for_each(&nbd_index_idr, &status_cb, reply); if (ret) { diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 3124837aa406fb7ece779ac7055873081edda8cc..505026f0025c7fcff5c528ab2a7aa0f7e27f9eaa 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -1206,14 +1206,15 @@ static int virtblk_freeze(struct virtio_device *vdev) { struct virtio_blk *vblk = vdev->priv; + /* Ensure no requests in virtqueues before deleting vqs. */ + blk_mq_freeze_queue(vblk->disk->queue); + /* Ensure we don't receive any more interrupts */ virtio_reset_device(vdev); /* Make sure no work handler is accessing the device. */ flush_work(&vblk->config_work); - blk_mq_quiesce_queue(vblk->disk->queue); - vdev->config->del_vqs(vdev); kfree(vblk->vqs); @@ -1231,7 +1232,7 @@ static int virtblk_restore(struct virtio_device *vdev) virtio_device_ready(vdev); - blk_mq_unquiesce_queue(vblk->disk->queue); + blk_mq_unfreeze_queue(vblk->disk->queue); return 0; } #endif diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index bbad1207cdfd8faba07aa4d3b3f8544ed6100322..7a9d2da3c8146d7f810192daf6117a4b755e9180 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -411,7 +411,7 @@ int btintel_read_version(struct hci_dev *hdev, struct intel_version *ver) return PTR_ERR(skb); } - if (skb->len != sizeof(*ver)) { + if (!skb || skb->len != sizeof(*ver)) { bt_dev_err(hdev, "Intel version event size mismatch"); kfree_skb(skb); return -EILSEQ; diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index 809762d64fc659ea90199f9bcf3fb446aee54153..b77e337778a44a8215bb7e14941f64b2b00e1197 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -288,4 +288,5 @@ MODULE_LICENSE("GPL"); MODULE_FIRMWARE(FIRMWARE_MT7622); MODULE_FIRMWARE(FIRMWARE_MT7663); MODULE_FIRMWARE(FIRMWARE_MT7668); +MODULE_FIRMWARE(FIRMWARE_MT7922); MODULE_FIRMWARE(FIRMWARE_MT7961); diff --git a/drivers/bluetooth/btmtk.h b/drivers/bluetooth/btmtk.h index 2a88ea8e475e816a16222ee5d5bfeeb2bc9544e6..ee0b1d27aa5c0e2fb327fe4eedec956456a149de 100644 --- a/drivers/bluetooth/btmtk.h +++ b/drivers/bluetooth/btmtk.h @@ -4,6 +4,7 @@ #define FIRMWARE_MT7622 "mediatek/mt7622pr2h.bin" #define FIRMWARE_MT7663 "mediatek/mt7663pr2h.bin" #define FIRMWARE_MT7668 "mediatek/mt7668pr2h.bin" +#define FIRMWARE_MT7922 "mediatek/BT_RAM_CODE_MT7922_1_1_hdr.bin" #define FIRMWARE_MT7961 "mediatek/BT_RAM_CODE_MT7961_1_2_hdr.bin" #define HCI_EV_WMT 0xe4 diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c index c9064d34d8308f29e725929d31238366d8d8f3aa..a0fadde993d704fe4c33cf2c1fb5234f5ec8908d 100644 --- a/drivers/bluetooth/btqca.c +++ b/drivers/bluetooth/btqca.c @@ -99,7 +99,8 @@ static int qca_read_fw_build_info(struct hci_dev *hdev) { struct sk_buff *skb; struct edl_event_hdr *edl; - char cmd, build_label[QCA_FW_BUILD_VER_LEN]; + char *build_label; + char cmd; int build_lbl_len, err = 0; bt_dev_dbg(hdev, "QCA read fw build info"); @@ -114,6 +115,11 @@ static int qca_read_fw_build_info(struct hci_dev *hdev) return err; } + if (skb->len < sizeof(*edl)) { + err = -EILSEQ; + goto out; + } + edl = (struct edl_event_hdr *)(skb->data); if (!edl) { bt_dev_err(hdev, "QCA read fw build info with no header"); @@ -129,14 +135,25 @@ static int qca_read_fw_build_info(struct hci_dev *hdev) goto out; } + if (skb->len < sizeof(*edl) + 1) { + err = -EILSEQ; + goto out; + } + build_lbl_len = edl->data[0]; - if (build_lbl_len <= QCA_FW_BUILD_VER_LEN - 1) { - memcpy(build_label, edl->data + 1, build_lbl_len); - *(build_label + build_lbl_len) = '\0'; + + if (skb->len < sizeof(*edl) + 1 + build_lbl_len) { + err = -EILSEQ; + goto out; } + build_label = kstrndup(&edl->data[1], build_lbl_len, GFP_KERNEL); + if (!build_label) + goto out; + hci_set_fw_info(hdev, "%s", build_label); + kfree(build_label); out: kfree_skb(skb); return err; @@ -152,7 +169,7 @@ static int qca_send_patch_config_cmd(struct hci_dev *hdev) bt_dev_dbg(hdev, "QCA Patch config"); skb = __hci_cmd_sync_ev(hdev, EDL_PATCH_CMD_OPCODE, sizeof(cmd), - cmd, HCI_EV_VENDOR, HCI_INIT_TIMEOUT); + cmd, 0, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { err = PTR_ERR(skb); bt_dev_err(hdev, "Sending QCA Patch config failed (%d)", err); @@ -205,6 +222,49 @@ static int qca_send_reset(struct hci_dev *hdev) return 0; } +static int qca_read_fw_board_id(struct hci_dev *hdev, u16 *bid) +{ + u8 cmd; + struct sk_buff *skb; + struct edl_event_hdr *edl; + int err = 0; + + cmd = EDL_GET_BID_REQ_CMD; + skb = __hci_cmd_sync_ev(hdev, EDL_PATCH_CMD_OPCODE, EDL_PATCH_CMD_LEN, + &cmd, 0, HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + err = PTR_ERR(skb); + bt_dev_err(hdev, "Reading QCA board ID failed (%d)", err); + return err; + } + + edl = skb_pull_data(skb, sizeof(*edl)); + if (!edl) { + bt_dev_err(hdev, "QCA read board ID with no header"); + err = -EILSEQ; + goto out; + } + + if (edl->cresp != EDL_CMD_REQ_RES_EVT || + edl->rtype != EDL_GET_BID_REQ_CMD) { + bt_dev_err(hdev, "QCA Wrong packet: %d %d", edl->cresp, edl->rtype); + err = -EIO; + goto out; + } + + if (skb->len < 3) { + err = -EILSEQ; + goto out; + } + + *bid = (edl->data[1] << 8) + edl->data[2]; + bt_dev_dbg(hdev, "%s: bid = %x", __func__, *bid); + +out: + kfree_skb(skb); + return err; +} + int qca_send_pre_shutdown_cmd(struct hci_dev *hdev) { struct sk_buff *skb; @@ -227,9 +287,10 @@ int qca_send_pre_shutdown_cmd(struct hci_dev *hdev) } EXPORT_SYMBOL_GPL(qca_send_pre_shutdown_cmd); -static void qca_tlv_check_data(struct hci_dev *hdev, +static int qca_tlv_check_data(struct hci_dev *hdev, struct qca_fw_config *config, - u8 *fw_data, enum qca_btsoc_type soc_type) + u8 *fw_data, size_t fw_size, + enum qca_btsoc_type soc_type) { const u8 *data; u32 type_len; @@ -239,12 +300,16 @@ static void qca_tlv_check_data(struct hci_dev *hdev, struct tlv_type_patch *tlv_patch; struct tlv_type_nvm *tlv_nvm; uint8_t nvm_baud_rate = config->user_baud_rate; + u8 type; config->dnld_mode = QCA_SKIP_EVT_NONE; config->dnld_type = QCA_SKIP_EVT_NONE; switch (config->type) { case ELF_TYPE_PATCH: + if (fw_size < 7) + return -EINVAL; + config->dnld_mode = QCA_SKIP_EVT_VSE_CC; config->dnld_type = QCA_SKIP_EVT_VSE_CC; @@ -253,6 +318,9 @@ static void qca_tlv_check_data(struct hci_dev *hdev, bt_dev_dbg(hdev, "File version : 0x%x", fw_data[6]); break; case TLV_TYPE_PATCH: + if (fw_size < sizeof(struct tlv_type_hdr) + sizeof(struct tlv_type_patch)) + return -EINVAL; + tlv = (struct tlv_type_hdr *)fw_data; type_len = le32_to_cpu(tlv->type_len); tlv_patch = (struct tlv_type_patch *)tlv->data; @@ -292,25 +360,56 @@ static void qca_tlv_check_data(struct hci_dev *hdev, break; case TLV_TYPE_NVM: + if (fw_size < sizeof(struct tlv_type_hdr)) + return -EINVAL; + tlv = (struct tlv_type_hdr *)fw_data; type_len = le32_to_cpu(tlv->type_len); - length = (type_len >> 8) & 0x00ffffff; + length = type_len >> 8; + type = type_len & 0xff; - BT_DBG("TLV Type\t\t : 0x%x", type_len & 0x000000ff); + /* Some NVM files have more than one set of tags, only parse + * the first set when it has type 2 for now. When there is + * more than one set there is an enclosing header of type 4. + */ + if (type == 4) { + if (fw_size < 2 * sizeof(struct tlv_type_hdr)) + return -EINVAL; + + tlv++; + + type_len = le32_to_cpu(tlv->type_len); + length = type_len >> 8; + type = type_len & 0xff; + } + + BT_DBG("TLV Type\t\t : 0x%x", type); BT_DBG("Length\t\t : %d bytes", length); + if (type != 2) + break; + + if (fw_size < length + (tlv->data - fw_data)) + return -EINVAL; + idx = 0; data = tlv->data; - while (idx < length) { + while (idx < length - sizeof(struct tlv_type_nvm)) { tlv_nvm = (struct tlv_type_nvm *)(data + idx); tag_id = le16_to_cpu(tlv_nvm->tag_id); tag_len = le16_to_cpu(tlv_nvm->tag_len); + if (length < idx + sizeof(struct tlv_type_nvm) + tag_len) + return -EINVAL; + /* Update NVM tags as needed */ switch (tag_id) { case EDL_TAG_ID_HCI: + if (tag_len < 3) + return -EINVAL; + /* HCI transport layer parameters * enabling software inband sleep * onto controller side. @@ -326,6 +425,9 @@ static void qca_tlv_check_data(struct hci_dev *hdev, break; case EDL_TAG_ID_DEEP_SLEEP: + if (tag_len < 1) + return -EINVAL; + /* Sleep enable mask * enabling deep sleep feature on controller. */ @@ -334,14 +436,16 @@ static void qca_tlv_check_data(struct hci_dev *hdev, break; } - idx += (sizeof(u16) + sizeof(u16) + 8 + tag_len); + idx += sizeof(struct tlv_type_nvm) + tag_len; } break; default: BT_ERR("Unknown TLV type %d", config->type); - break; + return -EINVAL; } + + return 0; } static int qca_tlv_send_segment(struct hci_dev *hdev, int seg_size, @@ -491,7 +595,9 @@ static int qca_download_firmware(struct hci_dev *hdev, memcpy(data, fw->data, size); release_firmware(fw); - qca_tlv_check_data(hdev, config, data, soc_type); + ret = qca_tlv_check_data(hdev, config, data, size, soc_type); + if (ret) + goto out; segment = data; remain = size; @@ -574,6 +680,23 @@ int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr) } EXPORT_SYMBOL_GPL(qca_set_bdaddr_rome); +static void qca_generate_hsp_nvm_name(char *fwname, size_t max_size, + struct qca_btsoc_version ver, u8 rom_ver, u16 bid) +{ + const char *variant; + + /* hsp gf chip */ + if ((le32_to_cpu(ver.soc_id) & QCA_HSP_GF_SOC_MASK) == QCA_HSP_GF_SOC_ID) + variant = "g"; + else + variant = ""; + + if (bid == 0x0) + snprintf(fwname, max_size, "qca/hpnv%02x%s.bin", rom_ver, variant); + else + snprintf(fwname, max_size, "qca/hpnv%02x%s.%x", rom_ver, variant, bid); +} + int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, enum qca_btsoc_type soc_type, struct qca_btsoc_version ver, const char *firmware_name) @@ -582,6 +705,7 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, int err; u8 rom_ver = 0; u32 soc_ver; + u16 boardid = 0; bt_dev_dbg(hdev, "QCA setup on UART"); @@ -594,27 +718,52 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, /* Firmware files to download are based on ROM version. * ROM version is derived from last two bytes of soc_ver. */ - rom_ver = ((soc_ver & 0x00000f00) >> 0x04) | (soc_ver & 0x0000000f); + if (soc_type == QCA_WCN3988) + rom_ver = ((soc_ver & 0x00000f00) >> 0x05) | (soc_ver & 0x0000000f); + else + rom_ver = ((soc_ver & 0x00000f00) >> 0x04) | (soc_ver & 0x0000000f); if (soc_type == QCA_WCN6750) qca_send_patch_config_cmd(hdev); /* Download rampatch file */ config.type = TLV_TYPE_PATCH; - if (qca_is_wcn399x(soc_type)) { + switch (soc_type) { + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: snprintf(config.fwname, sizeof(config.fwname), "qca/crbtfw%02x.tlv", rom_ver); - } else if (soc_type == QCA_QCA6390) { + break; + case QCA_WCN3988: + snprintf(config.fwname, sizeof(config.fwname), + "qca/apbtfw%02x.tlv", rom_ver); + break; + case QCA_QCA2066: + snprintf(config.fwname, sizeof(config.fwname), + "qca/hpbtfw%02x.tlv", rom_ver); + break; + case QCA_QCA6390: snprintf(config.fwname, sizeof(config.fwname), "qca/htbtfw%02x.tlv", rom_ver); - } else if (soc_type == QCA_WCN6750) { + break; + case QCA_WCN6750: /* Choose mbn file by default.If mbn file is not found * then choose tlv file */ config.type = ELF_TYPE_PATCH; snprintf(config.fwname, sizeof(config.fwname), "qca/msbtfw%02x.mbn", rom_ver); - } else { + break; + case QCA_WCN6855: + snprintf(config.fwname, sizeof(config.fwname), + "qca/hpbtfw%02x.tlv", rom_ver); + break; + case QCA_WCN7850: + snprintf(config.fwname, sizeof(config.fwname), + "qca/hmtbtfw%02x.tlv", rom_ver); + break; + default: snprintf(config.fwname, sizeof(config.fwname), "qca/rampatch_%08x.bin", soc_ver); } @@ -628,29 +777,57 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, /* Give the controller some time to get ready to receive the NVM */ msleep(10); + if (soc_type == QCA_QCA2066) + qca_read_fw_board_id(hdev, &boardid); + /* Download NVM configuration */ config.type = TLV_TYPE_NVM; - if (firmware_name) + if (firmware_name) { snprintf(config.fwname, sizeof(config.fwname), "qca/%s", firmware_name); - else if (qca_is_wcn399x(soc_type)) { - if (ver.soc_id == QCA_WCN3991_SOC_ID) { + } else { + switch (soc_type) { + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + if (le32_to_cpu(ver.soc_id) == QCA_WCN3991_SOC_ID) { + snprintf(config.fwname, sizeof(config.fwname), + "qca/crnv%02xu.bin", rom_ver); + } else { + snprintf(config.fwname, sizeof(config.fwname), + "qca/crnv%02x.bin", rom_ver); + } + break; + case QCA_WCN3988: snprintf(config.fwname, sizeof(config.fwname), - "qca/crnv%02xu.bin", rom_ver); - } else { + "qca/apnv%02x.bin", rom_ver); + break; + case QCA_QCA2066: + qca_generate_hsp_nvm_name(config.fwname, + sizeof(config.fwname), ver, rom_ver, boardid); + break; + case QCA_QCA6390: + snprintf(config.fwname, sizeof(config.fwname), + "qca/htnv%02x.bin", rom_ver); + break; + case QCA_WCN6750: + snprintf(config.fwname, sizeof(config.fwname), + "qca/msnv%02x.bin", rom_ver); + break; + case QCA_WCN6855: + snprintf(config.fwname, sizeof(config.fwname), + "qca/hpnv%02x.bin", rom_ver); + break; + case QCA_WCN7850: snprintf(config.fwname, sizeof(config.fwname), - "qca/crnv%02x.bin", rom_ver); + "qca/hmtnv%02x.bin", rom_ver); + break; + + default: + snprintf(config.fwname, sizeof(config.fwname), + "qca/nvm_%08x.bin", soc_ver); } } - else if (soc_type == QCA_QCA6390) - snprintf(config.fwname, sizeof(config.fwname), - "qca/htnv%02x.bin", rom_ver); - else if (soc_type == QCA_WCN6750) - snprintf(config.fwname, sizeof(config.fwname), - "qca/msnv%02x.bin", rom_ver); - else - snprintf(config.fwname, sizeof(config.fwname), - "qca/nvm_%08x.bin", soc_ver); err = qca_download_firmware(hdev, &config, soc_type, rom_ver); if (err < 0) { @@ -658,16 +835,26 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, return err; } - if (soc_type >= QCA_WCN3991) { + switch (soc_type) { + case QCA_WCN3991: + case QCA_QCA2066: + case QCA_QCA6390: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: err = qca_disable_soc_logging(hdev); if (err < 0) return err; + break; + default: + break; } /* WCN399x and WCN6750 supports the Microsoft vendor extension with 0xFD70 as the * VsMsftOpCode. */ switch (soc_type) { + case QCA_WCN3988: case QCA_WCN3990: case QCA_WCN3991: case QCA_WCN3998: @@ -685,11 +872,18 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, return err; } - if (soc_type == QCA_WCN3991 || soc_type == QCA_WCN6750) { + switch (soc_type) { + case QCA_WCN3991: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: /* get fw build info */ err = qca_read_fw_build_info(hdev); if (err < 0) return err; + break; + default: + break; } bt_dev_info(hdev, "QCA setup on UART is completed"); @@ -700,11 +894,15 @@ EXPORT_SYMBOL_GPL(qca_uart_setup); int qca_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr) { + bdaddr_t bdaddr_swapped; struct sk_buff *skb; int err; - skb = __hci_cmd_sync_ev(hdev, EDL_WRITE_BD_ADDR_OPCODE, 6, bdaddr, - HCI_EV_VENDOR, HCI_INIT_TIMEOUT); + baswap(&bdaddr_swapped, bdaddr); + + skb = __hci_cmd_sync_ev(hdev, EDL_WRITE_BD_ADDR_OPCODE, 6, + &bdaddr_swapped, HCI_EV_VENDOR, + HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { err = PTR_ERR(skb); bt_dev_err(hdev, "QCA Change address cmd failed (%d)", err); diff --git a/drivers/bluetooth/btqca.h b/drivers/bluetooth/btqca.h index 61e9a50e66ae1f7687d9f0968247b01b87d6d5d4..38e2fbc950248ec3f127e6d42e616ee23c14c861 100644 --- a/drivers/bluetooth/btqca.h +++ b/drivers/bluetooth/btqca.h @@ -12,6 +12,7 @@ #define EDL_PATCH_VER_REQ_CMD (0x19) #define EDL_PATCH_TLV_REQ_CMD (0x1E) #define EDL_GET_BUILD_INFO_CMD (0x20) +#define EDL_GET_BID_REQ_CMD (0x23) #define EDL_NVM_ACCESS_SET_REQ_CMD (0x01) #define EDL_PATCH_CONFIG_CMD (0x28) #define MAX_SIZE_PER_TLV_SEGMENT (243) @@ -46,8 +47,8 @@ #define get_soc_ver(soc_id, rom_ver) \ ((le32_to_cpu(soc_id) << 16) | (le16_to_cpu(rom_ver))) -#define QCA_FW_BUILD_VER_LEN 255 - +#define QCA_HSP_GF_SOC_ID 0x1200 +#define QCA_HSP_GF_SOC_MASK 0x0000ff00 enum qca_baudrate { QCA_BAUDRATE_115200 = 0, @@ -142,11 +143,15 @@ enum qca_btsoc_type { QCA_INVALID = -1, QCA_AR3002, QCA_ROME, + QCA_WCN3988, QCA_WCN3990, QCA_WCN3998, QCA_WCN3991, + QCA_QCA2066, QCA_QCA6390, QCA_WCN6750, + QCA_WCN6855, + QCA_WCN7850, }; #if IS_ENABLED(CONFIG_BT_QCA) @@ -159,16 +164,6 @@ int qca_read_soc_version(struct hci_dev *hdev, struct qca_btsoc_version *ver, enum qca_btsoc_type); int qca_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr); int qca_send_pre_shutdown_cmd(struct hci_dev *hdev); -static inline bool qca_is_wcn399x(enum qca_btsoc_type soc_type) -{ - return soc_type == QCA_WCN3990 || soc_type == QCA_WCN3991 || - soc_type == QCA_WCN3998; -} -static inline bool qca_is_wcn6750(enum qca_btsoc_type soc_type) -{ - return soc_type == QCA_WCN6750; -} - #else static inline int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr) @@ -196,16 +191,6 @@ static inline int qca_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr) return -EOPNOTSUPP; } -static inline bool qca_is_wcn399x(enum qca_btsoc_type soc_type) -{ - return false; -} - -static inline bool qca_is_wcn6750(enum qca_btsoc_type soc_type) -{ - return false; -} - static inline int qca_send_pre_shutdown_cmd(struct hci_dev *hdev) { return -EOPNOTSUPP; diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 954f7f3b5cc302ee972cf1eac0ff9c597816cb86..6a772b955d69dce473bc94c663cdf6f571318c8d 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -535,6 +535,8 @@ static const struct usb_device_id blacklist_table[] = { /* Realtek 8852BE Bluetooth devices */ { USB_DEVICE(0x0cb8, 0xc559), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x0bda, 0x4853), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x0bda, 0x887b), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x0bda, 0xb85b), .driver_info = BTUSB_REALTEK | diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 76ceb8a0183d14929708e901869344fb0c59b0ee..a0e2b5d992695624b1091fbba63f9c60b3175bef 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -225,6 +225,7 @@ struct qca_serdev { struct qca_power *bt_power; u32 init_speed; u32 oper_speed; + bool bdaddr_property_broken; const char *firmware_name; }; @@ -606,9 +607,18 @@ static int qca_open(struct hci_uart *hu) if (hu->serdev) { qcadev = serdev_device_get_drvdata(hu->serdev); - if (qca_is_wcn399x(qcadev->btsoc_type) || - qca_is_wcn6750(qcadev->btsoc_type)) + switch (qcadev->btsoc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + case QCA_WCN6750: hu->init_speed = qcadev->init_speed; + break; + + default: + break; + } if (qcadev->oper_speed) hu->oper_speed = qcadev->oper_speed; @@ -1314,11 +1324,20 @@ static int qca_set_baudrate(struct hci_dev *hdev, uint8_t baudrate) msecs_to_jiffies(CMD_TRANS_TIMEOUT_MS)); /* Give the controller time to process the request */ - if (qca_is_wcn399x(qca_soc_type(hu)) || - qca_is_wcn6750(qca_soc_type(hu))) + switch (qca_soc_type(hu)) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: usleep_range(1000, 10000); - else + break; + + default: msleep(300); + } return 0; } @@ -1391,12 +1410,20 @@ static unsigned int qca_get_speed(struct hci_uart *hu, static int qca_check_speeds(struct hci_uart *hu) { - if (qca_is_wcn399x(qca_soc_type(hu)) || - qca_is_wcn6750(qca_soc_type(hu))) { + switch (qca_soc_type(hu)) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: if (!qca_get_speed(hu, QCA_INIT_SPEED) && !qca_get_speed(hu, QCA_OPER_SPEED)) return -EINVAL; - } else { + break; + + default: if (!qca_get_speed(hu, QCA_INIT_SPEED) || !qca_get_speed(hu, QCA_OPER_SPEED)) return -EINVAL; @@ -1425,13 +1452,29 @@ static int qca_set_speed(struct hci_uart *hu, enum qca_speed_type speed_type) /* Disable flow control for wcn3990 to deassert RTS while * changing the baudrate of chip and host. */ - if (qca_is_wcn399x(soc_type) || - qca_is_wcn6750(soc_type)) + switch (soc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: hci_uart_set_flow_control(hu, true); + break; - if (soc_type == QCA_WCN3990) { + default: + break; + } + + switch (soc_type) { + case QCA_WCN3990: reinit_completion(&qca->drop_ev_comp); set_bit(QCA_DROP_VENDOR_EVENT, &qca->flags); + break; + + default: + break; } qca_baudrate = qca_get_baudrate_value(speed); @@ -1443,11 +1486,23 @@ static int qca_set_speed(struct hci_uart *hu, enum qca_speed_type speed_type) host_set_baudrate(hu, speed); error: - if (qca_is_wcn399x(soc_type) || - qca_is_wcn6750(soc_type)) + switch (soc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: hci_uart_set_flow_control(hu, false); + break; + + default: + break; + } - if (soc_type == QCA_WCN3990) { + switch (soc_type) { + case QCA_WCN3990: /* Wait for the controller to send the vendor event * for the baudrate change command. */ @@ -1459,6 +1514,10 @@ error: } clear_bit(QCA_DROP_VENDOR_EVENT, &qca->flags); + break; + + default: + break; } } @@ -1586,6 +1645,9 @@ static bool qca_wakeup(struct hci_dev *hdev) struct hci_uart *hu = hci_get_drvdata(hdev); bool wakeup; + if (!hu->serdev) + return true; + /* BT SoC attached through the serial bus is handled by the serdev driver. * So we need to use the device handle of the serdev driver to get the * status of device may wakeup. @@ -1620,12 +1682,20 @@ static int qca_regulator_init(struct hci_uart *hu) } } - if (qca_is_wcn399x(soc_type)) { + switch (soc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: /* Forcefully enable wcn399x to enter in to boot mode. */ host_set_baudrate(hu, 2400); ret = qca_send_power_pulse(hu, false); if (ret) return ret; + break; + + default: + break; } /* For wcn6750 need to enable gpio bt_en */ @@ -1642,10 +1712,18 @@ static int qca_regulator_init(struct hci_uart *hu) qca_set_speed(hu, QCA_INIT_SPEED); - if (qca_is_wcn399x(soc_type)) { + switch (soc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: ret = qca_send_power_pulse(hu, true); if (ret) return ret; + break; + + default: + break; } /* Now the device is in ready state to communicate with host. @@ -1679,10 +1757,18 @@ static int qca_power_on(struct hci_dev *hdev) if (!hu->serdev) return 0; - if (qca_is_wcn399x(soc_type) || - qca_is_wcn6750(soc_type)) { + switch (soc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: ret = qca_regulator_init(hu); - } else { + break; + + default: qcadev = serdev_device_get_drvdata(hu->serdev); if (qcadev->bt_en) { gpiod_set_value_cansleep(qcadev->bt_en, 1); @@ -1705,6 +1791,8 @@ static int qca_setup(struct hci_uart *hu) const char *firmware_name = qca_get_firmware_name(hu); int ret; struct qca_btsoc_version ver; + struct qca_serdev *qcadev; + const char *soc_name; ret = qca_check_speeds(hu); if (ret) @@ -1719,9 +1807,34 @@ static int qca_setup(struct hci_uart *hu) */ set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); - bt_dev_info(hdev, "setting up %s", - qca_is_wcn399x(soc_type) ? "wcn399x" : - (soc_type == QCA_WCN6750) ? "wcn6750" : "ROME/QCA6390"); + switch (soc_type) { + case QCA_QCA2066: + soc_name = "qca2066"; + break; + + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + soc_name = "wcn399x"; + break; + + case QCA_WCN6750: + soc_name = "wcn6750"; + break; + + case QCA_WCN6855: + soc_name = "wcn6855"; + break; + + case QCA_WCN7850: + soc_name = "wcn7850"; + break; + + default: + soc_name = "ROME/QCA6390"; + } + bt_dev_info(hdev, "setting up %s", soc_name); qca->memdump_state = QCA_MEMDUMP_IDLE; @@ -1732,15 +1845,28 @@ retry: clear_bit(QCA_SSR_TRIGGERED, &qca->flags); - if (qca_is_wcn399x(soc_type) || - qca_is_wcn6750(soc_type)) { + switch (soc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks); + + qcadev = serdev_device_get_drvdata(hu->serdev); + if (qcadev->bdaddr_property_broken) + set_bit(HCI_QUIRK_BDADDR_PROPERTY_BROKEN, &hdev->quirks); + hci_set_aosp_capable(hdev); ret = qca_read_soc_version(hdev, &ver, soc_type); if (ret) goto out; - } else { + break; + + default: qca_set_speed(hu, QCA_INIT_SPEED); } @@ -1754,8 +1880,17 @@ retry: qca_baudrate = qca_get_baudrate_value(speed); } - if (!(qca_is_wcn399x(soc_type) || - qca_is_wcn6750(soc_type))) { + switch (soc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: + break; + + default: /* Get QCA version information */ ret = qca_read_soc_version(hdev, &ver, soc_type); if (ret) @@ -1824,7 +1959,18 @@ static const struct hci_uart_proto qca_proto = { .dequeue = qca_dequeue, }; -static const struct qca_device_data qca_soc_data_wcn3990 = { +static const struct qca_device_data qca_soc_data_wcn3988 __maybe_unused = { + .soc_type = QCA_WCN3988, + .vregs = (struct qca_vreg []) { + { "vddio", 15000 }, + { "vddxo", 80000 }, + { "vddrf", 300000 }, + { "vddch0", 450000 }, + }, + .num_vregs = 4, +}; + +static const struct qca_device_data qca_soc_data_wcn3990 __maybe_unused = { .soc_type = QCA_WCN3990, .vregs = (struct qca_vreg []) { { "vddio", 15000 }, @@ -1835,7 +1981,7 @@ static const struct qca_device_data qca_soc_data_wcn3990 = { .num_vregs = 4, }; -static const struct qca_device_data qca_soc_data_wcn3991 = { +static const struct qca_device_data qca_soc_data_wcn3991 __maybe_unused = { .soc_type = QCA_WCN3991, .vregs = (struct qca_vreg []) { { "vddio", 15000 }, @@ -1847,7 +1993,7 @@ static const struct qca_device_data qca_soc_data_wcn3991 = { .capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES, }; -static const struct qca_device_data qca_soc_data_wcn3998 = { +static const struct qca_device_data qca_soc_data_wcn3998 __maybe_unused = { .soc_type = QCA_WCN3998, .vregs = (struct qca_vreg []) { { "vddio", 10000 }, @@ -1858,13 +2004,18 @@ static const struct qca_device_data qca_soc_data_wcn3998 = { .num_vregs = 4, }; -static const struct qca_device_data qca_soc_data_qca6390 = { +static const struct qca_device_data qca_soc_data_qca2066 __maybe_unused = { + .soc_type = QCA_QCA2066, + .num_vregs = 0, +}; + +static const struct qca_device_data qca_soc_data_qca6390 __maybe_unused = { .soc_type = QCA_QCA6390, .num_vregs = 0, .capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES, }; -static const struct qca_device_data qca_soc_data_wcn6750 = { +static const struct qca_device_data qca_soc_data_wcn6750 __maybe_unused = { .soc_type = QCA_WCN6750, .vregs = (struct qca_vreg []) { { "vddio", 5000 }, @@ -1881,6 +2032,34 @@ static const struct qca_device_data qca_soc_data_wcn6750 = { .capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES, }; +static const struct qca_device_data qca_soc_data_wcn6855 = { + .soc_type = QCA_WCN6855, + .vregs = (struct qca_vreg []) { + { "vddio", 5000 }, + { "vddbtcxmx", 126000 }, + { "vddrfacmn", 12500 }, + { "vddrfa0p8", 102000 }, + { "vddrfa1p7", 302000 }, + { "vddrfa1p2", 257000 }, + }, + .num_vregs = 6, + .capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES, +}; + +static const struct qca_device_data qca_soc_data_wcn7850 __maybe_unused = { + .soc_type = QCA_WCN7850, + .vregs = (struct qca_vreg []) { + { "vddio", 5000 }, + { "vddaon", 26000 }, + { "vdddig", 126000 }, + { "vddrfa0p8", 102000 }, + { "vddrfa1p2", 257000 }, + { "vddrfa1p9", 302000 }, + }, + .num_vregs = 6, + .capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES, +}; + static void qca_power_shutdown(struct hci_uart *hu) { struct qca_serdev *qcadev; @@ -1906,11 +2085,18 @@ static void qca_power_shutdown(struct hci_uart *hu) qcadev = serdev_device_get_drvdata(hu->serdev); - if (qca_is_wcn399x(soc_type)) { + switch (soc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: host_set_baudrate(hu, 2400); qca_send_power_pulse(hu, false); qca_regulator_disable(qcadev); - } else if (soc_type == QCA_WCN6750) { + break; + + case QCA_WCN6750: + case QCA_WCN6855: gpiod_set_value_cansleep(qcadev->bt_en, 0); msleep(100); qca_regulator_disable(qcadev); @@ -1918,7 +2104,9 @@ static void qca_power_shutdown(struct hci_uart *hu) sw_ctrl_state = gpiod_get_value_cansleep(qcadev->sw_ctrl); bt_dev_dbg(hu->hdev, "SW_CTRL is %d", sw_ctrl_state); } - } else if (qcadev->bt_en) { + break; + + default: gpiod_set_value_cansleep(qcadev->bt_en, 0); } @@ -2043,10 +2231,22 @@ static int qca_serdev_probe(struct serdev_device *serdev) if (!qcadev->oper_speed) BT_DBG("UART will pick default operating speed"); - if (data && - (qca_is_wcn399x(data->soc_type) || - qca_is_wcn6750(data->soc_type))) { + qcadev->bdaddr_property_broken = device_property_read_bool(&serdev->dev, + "qcom,local-bd-address-broken"); + + if (data) qcadev->btsoc_type = data->soc_type; + else + qcadev->btsoc_type = QCA_ROME; + + switch (qcadev->btsoc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: qcadev->bt_power = devm_kzalloc(&serdev->dev, sizeof(struct qca_power), GFP_KERNEL); @@ -2065,15 +2265,25 @@ static int qca_serdev_probe(struct serdev_device *serdev) qcadev->bt_en = devm_gpiod_get_optional(&serdev->dev, "enable", GPIOD_OUT_LOW); - if (IS_ERR_OR_NULL(qcadev->bt_en) && data->soc_type == QCA_WCN6750) { + if (IS_ERR(qcadev->bt_en) && + (data->soc_type == QCA_WCN6750 || + data->soc_type == QCA_WCN6855)) { dev_err(&serdev->dev, "failed to acquire BT_EN gpio\n"); - power_ctrl_enabled = false; + return PTR_ERR(qcadev->bt_en); } + if (!qcadev->bt_en) + power_ctrl_enabled = false; + qcadev->sw_ctrl = devm_gpiod_get_optional(&serdev->dev, "swctrl", GPIOD_IN); - if (IS_ERR_OR_NULL(qcadev->sw_ctrl) && data->soc_type == QCA_WCN6750) - dev_warn(&serdev->dev, "failed to acquire SW_CTRL gpio\n"); + if (IS_ERR(qcadev->sw_ctrl) && + (data->soc_type == QCA_WCN6750 || + data->soc_type == QCA_WCN6855 || + data->soc_type == QCA_WCN7850)) { + dev_err(&serdev->dev, "failed to acquire SW_CTRL gpio\n"); + return PTR_ERR(qcadev->sw_ctrl); + } qcadev->susclk = devm_clk_get_optional(&serdev->dev, NULL); if (IS_ERR(qcadev->susclk)) { @@ -2086,19 +2296,19 @@ static int qca_serdev_probe(struct serdev_device *serdev) BT_ERR("wcn3990 serdev registration failed"); return err; } - } else { - if (data) - qcadev->btsoc_type = data->soc_type; - else - qcadev->btsoc_type = QCA_ROME; + break; + default: qcadev->bt_en = devm_gpiod_get_optional(&serdev->dev, "enable", GPIOD_OUT_LOW); - if (IS_ERR_OR_NULL(qcadev->bt_en)) { - dev_warn(&serdev->dev, "failed to acquire enable gpio\n"); - power_ctrl_enabled = false; + if (IS_ERR(qcadev->bt_en)) { + dev_err(&serdev->dev, "failed to acquire enable gpio\n"); + return PTR_ERR(qcadev->bt_en); } + if (!qcadev->bt_en) + power_ctrl_enabled = false; + qcadev->susclk = devm_clk_get_optional(&serdev->dev, NULL); if (IS_ERR(qcadev->susclk)) { dev_warn(&serdev->dev, "failed to acquire clk\n"); @@ -2147,12 +2357,24 @@ static void qca_serdev_remove(struct serdev_device *serdev) struct qca_serdev *qcadev = serdev_device_get_drvdata(serdev); struct qca_power *power = qcadev->bt_power; - if ((qca_is_wcn399x(qcadev->btsoc_type) || - qca_is_wcn6750(qcadev->btsoc_type)) && - power->vregs_on) - qca_power_shutdown(&qcadev->serdev_hu); - else if (qcadev->susclk) - clk_disable_unprepare(qcadev->susclk); + switch (qcadev->btsoc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: + if (power->vregs_on) { + qca_power_shutdown(&qcadev->serdev_hu); + break; + } + fallthrough; + + default: + if (qcadev->susclk) + clk_disable_unprepare(qcadev->susclk); + } hci_uart_unregister_device(&qcadev->serdev_hu); } @@ -2326,13 +2548,17 @@ static SIMPLE_DEV_PM_OPS(qca_pm_ops, qca_suspend, qca_resume); #ifdef CONFIG_OF static const struct of_device_id qca_bluetooth_of_match[] = { + { .compatible = "qcom,qca2066-bt", .data = &qca_soc_data_qca2066}, { .compatible = "qcom,qca6174-bt" }, { .compatible = "qcom,qca6390-bt", .data = &qca_soc_data_qca6390}, { .compatible = "qcom,qca9377-bt" }, + { .compatible = "qcom,wcn3988-bt", .data = &qca_soc_data_wcn3988}, { .compatible = "qcom,wcn3990-bt", .data = &qca_soc_data_wcn3990}, { .compatible = "qcom,wcn3991-bt", .data = &qca_soc_data_wcn3991}, { .compatible = "qcom,wcn3998-bt", .data = &qca_soc_data_wcn3998}, { .compatible = "qcom,wcn6750-bt", .data = &qca_soc_data_wcn6750}, + { .compatible = "qcom,wcn6855-bt", .data = &qca_soc_data_wcn6855}, + { .compatible = "qcom,wcn7850-bt", .data = &qca_soc_data_wcn7850}, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, qca_bluetooth_of_match); @@ -2340,6 +2566,7 @@ MODULE_DEVICE_TABLE(of, qca_bluetooth_of_match); #ifdef CONFIG_ACPI static const struct acpi_device_id qca_bluetooth_acpi_match[] = { + { "QCOM2066", (kernel_ulong_t)&qca_soc_data_qca2066 }, { "QCOM6390", (kernel_ulong_t)&qca_soc_data_qca6390 }, { "DLA16390", (kernel_ulong_t)&qca_soc_data_qca6390 }, { "DLB16390", (kernel_ulong_t)&qca_soc_data_qca6390 }, diff --git a/drivers/bus/Kconfig b/drivers/bus/Kconfig index 7bfe998f3514ac6d8f3a5f2f0e8283c264bc7a5d..bdc76339055041164211c3ba88a65d38d48d4e18 100644 --- a/drivers/bus/Kconfig +++ b/drivers/bus/Kconfig @@ -186,11 +186,12 @@ config SUNXI_RSB config TEGRA_ACONNECT tristate "Tegra ACONNECT Bus Driver" - depends on ARCH_TEGRA_210_SOC + depends on ARCH_TEGRA depends on OF && PM help Driver for the Tegra ACONNECT bus which is used to interface with - the devices inside the Audio Processing Engine (APE) for Tegra210. + the devices inside the Audio Processing Engine (APE) for + Tegra210 and later. config TEGRA_GMI tristate "Tegra Generic Memory Interface bus driver" diff --git a/drivers/bus/mhi/host/init.c b/drivers/bus/mhi/host/init.c index 04fbccff65ac2e1410ae9df4bec84885ad5f3248..60c1df048fa20cb5732aac559bf5f25dd28373f5 100644 --- a/drivers/bus/mhi/host/init.c +++ b/drivers/bus/mhi/host/init.c @@ -62,6 +62,7 @@ static const char * const mhi_pm_state_str[] = { [MHI_PM_STATE_FW_DL_ERR] = "Firmware Download Error", [MHI_PM_STATE_SYS_ERR_DETECT] = "SYS ERROR Detect", [MHI_PM_STATE_SYS_ERR_PROCESS] = "SYS ERROR Process", + [MHI_PM_STATE_SYS_ERR_FAIL] = "SYS ERROR Failure", [MHI_PM_STATE_SHUTDOWN_PROCESS] = "SHUTDOWN Process", [MHI_PM_STATE_LD_ERR_FATAL_DETECT] = "Linkdown or Error Fatal Detect", }; diff --git a/drivers/bus/mhi/host/internal.h b/drivers/bus/mhi/host/internal.h index 01fd10a399b61b4399c218d6978b10b244e3903b..6abf09da4f618702999b8e12f2add2b045fc0a16 100644 --- a/drivers/bus/mhi/host/internal.h +++ b/drivers/bus/mhi/host/internal.h @@ -88,6 +88,7 @@ enum mhi_pm_state { MHI_PM_STATE_FW_DL_ERR, MHI_PM_STATE_SYS_ERR_DETECT, MHI_PM_STATE_SYS_ERR_PROCESS, + MHI_PM_STATE_SYS_ERR_FAIL, MHI_PM_STATE_SHUTDOWN_PROCESS, MHI_PM_STATE_LD_ERR_FATAL_DETECT, MHI_PM_STATE_MAX @@ -104,14 +105,16 @@ enum mhi_pm_state { #define MHI_PM_FW_DL_ERR BIT(7) #define MHI_PM_SYS_ERR_DETECT BIT(8) #define MHI_PM_SYS_ERR_PROCESS BIT(9) -#define MHI_PM_SHUTDOWN_PROCESS BIT(10) +#define MHI_PM_SYS_ERR_FAIL BIT(10) +#define MHI_PM_SHUTDOWN_PROCESS BIT(11) /* link not accessible */ -#define MHI_PM_LD_ERR_FATAL_DETECT BIT(11) +#define MHI_PM_LD_ERR_FATAL_DETECT BIT(12) #define MHI_REG_ACCESS_VALID(pm_state) ((pm_state & (MHI_PM_POR | MHI_PM_M0 | \ MHI_PM_M2 | MHI_PM_M3_ENTER | MHI_PM_M3_EXIT | \ MHI_PM_SYS_ERR_DETECT | MHI_PM_SYS_ERR_PROCESS | \ - MHI_PM_SHUTDOWN_PROCESS | MHI_PM_FW_DL_ERR))) + MHI_PM_SYS_ERR_FAIL | MHI_PM_SHUTDOWN_PROCESS | \ + MHI_PM_FW_DL_ERR))) #define MHI_PM_IN_ERROR_STATE(pm_state) (pm_state >= MHI_PM_FW_DL_ERR) #define MHI_PM_IN_FATAL_STATE(pm_state) (pm_state == MHI_PM_LD_ERR_FATAL_DETECT) #define MHI_DB_ACCESS_VALID(mhi_cntrl) (mhi_cntrl->pm_state & mhi_cntrl->db_access) diff --git a/drivers/bus/mhi/host/pm.c b/drivers/bus/mhi/host/pm.c index 8a4362d75fc4375635be266406a3a364b58df363..27f8a40f288cfd45b96d7889d24c7f39261047cc 100644 --- a/drivers/bus/mhi/host/pm.c +++ b/drivers/bus/mhi/host/pm.c @@ -36,7 +36,10 @@ * M0 <--> M0 * M0 -> FW_DL_ERR * M0 -> M3_ENTER -> M3 -> M3_EXIT --> M0 - * L1: SYS_ERR_DETECT -> SYS_ERR_PROCESS --> POR + * L1: SYS_ERR_DETECT -> SYS_ERR_PROCESS + * SYS_ERR_PROCESS -> SYS_ERR_FAIL + * SYS_ERR_FAIL -> SYS_ERR_DETECT + * SYS_ERR_PROCESS --> POR * L2: SHUTDOWN_PROCESS -> LD_ERR_FATAL_DETECT * SHUTDOWN_PROCESS -> DISABLE * L3: LD_ERR_FATAL_DETECT <--> LD_ERR_FATAL_DETECT @@ -93,7 +96,12 @@ static const struct mhi_pm_transitions dev_state_transitions[] = { }, { MHI_PM_SYS_ERR_PROCESS, - MHI_PM_POR | MHI_PM_SHUTDOWN_PROCESS | + MHI_PM_POR | MHI_PM_SYS_ERR_FAIL | MHI_PM_SHUTDOWN_PROCESS | + MHI_PM_LD_ERR_FATAL_DETECT + }, + { + MHI_PM_SYS_ERR_FAIL, + MHI_PM_SYS_ERR_DETECT | MHI_PM_SHUTDOWN_PROCESS | MHI_PM_LD_ERR_FATAL_DETECT }, /* L2 States */ @@ -624,7 +632,13 @@ static void mhi_pm_sys_error_transition(struct mhi_controller *mhi_cntrl) !in_reset, timeout); if (!ret || in_reset) { dev_err(dev, "Device failed to exit MHI Reset state\n"); - goto exit_sys_error_transition; + write_lock_irq(&mhi_cntrl->pm_lock); + cur_state = mhi_tryset_pm_state(mhi_cntrl, + MHI_PM_SYS_ERR_FAIL); + write_unlock_irq(&mhi_cntrl->pm_lock); + /* Shutdown may have occurred, otherwise cleanup now */ + if (cur_state != MHI_PM_SYS_ERR_FAIL) + goto exit_sys_error_transition; } /* diff --git a/drivers/bus/moxtet.c b/drivers/bus/moxtet.c index 5eb0fe73ddc45b2c092877cb002c605dbbf6e043..79fc96c8d8364340c97c42d26dba00eae788c766 100644 --- a/drivers/bus/moxtet.c +++ b/drivers/bus/moxtet.c @@ -830,6 +830,12 @@ static void moxtet_remove(struct spi_device *spi) mutex_destroy(&moxtet->lock); } +static const struct spi_device_id moxtet_spi_ids[] = { + { "moxtet" }, + { }, +}; +MODULE_DEVICE_TABLE(spi, moxtet_spi_ids); + static const struct of_device_id moxtet_dt_ids[] = { { .compatible = "cznic,moxtet" }, {}, @@ -841,6 +847,7 @@ static struct spi_driver moxtet_spi_driver = { .name = "moxtet", .of_match_table = moxtet_dt_ids, }, + .id_table = moxtet_spi_ids, .probe = moxtet_probe, .remove = moxtet_remove, }; diff --git a/drivers/char/random.c b/drivers/char/random.c index fbf227c5b52846e0092e30a893442a6ae66d1163..dc4857d3eec85c50e3717245ba0beab957aee9ad 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -683,7 +683,7 @@ static void extract_entropy(void *buf, size_t len) static void __cold _credit_init_bits(size_t bits) { - static struct execute_work set_ready; + static DECLARE_WORK(set_ready, crng_set_ready); unsigned int new, orig, add; unsigned long flags; @@ -699,8 +699,8 @@ static void __cold _credit_init_bits(size_t bits) if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) { crng_reseed(); /* Sets crng_init to CRNG_READY under base_crng.lock. */ - if (static_key_initialized) - execute_in_process_context(crng_set_ready, &set_ready); + if (static_key_initialized && system_unbound_wq) + queue_work(system_unbound_wq, &set_ready); wake_up_interruptible(&crng_init_wait); kill_fasync(&fasync, SIGIO, POLL_IN); pr_notice("crng init done\n"); @@ -878,8 +878,8 @@ void __init random_init(void) /* * If we were initialized by the cpu or bootloader before jump labels - * are initialized, then we should enable the static branch here, where - * it's guaranteed that jump labels have been initialized. + * or workqueues are initialized, then we should enable the static + * branch here, where it's guaranteed that these have been initialized. */ if (!static_branch_likely(&crng_is_ready) && crng_init >= CRNG_READY) crng_set_ready(NULL); diff --git a/drivers/char/tpm/tpm-dev-common.c b/drivers/char/tpm/tpm-dev-common.c index dc4c0a0a512903235d9c580789cf2c74453ad5c0..30b4c288c1bbc3ba4dfedd38abf9663ace12e819 100644 --- a/drivers/char/tpm/tpm-dev-common.c +++ b/drivers/char/tpm/tpm-dev-common.c @@ -155,7 +155,7 @@ ssize_t tpm_common_read(struct file *file, char __user *buf, out: if (!priv->response_length) { *off = 0; - del_singleshot_timer_sync(&priv->user_read_timer); + del_timer_sync(&priv->user_read_timer); flush_work(&priv->timeout_work); } mutex_unlock(&priv->buffer_mutex); @@ -262,7 +262,7 @@ __poll_t tpm_common_poll(struct file *file, poll_table *wait) void tpm_common_release(struct file *file, struct file_priv *priv) { flush_work(&priv->async_work); - del_singleshot_timer_sync(&priv->user_read_timer); + del_timer_sync(&priv->user_read_timer); flush_work(&priv->timeout_work); file->private_data = NULL; priv->response_length = 0; diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 33fedbd096f3337f5c8dc8c061e188e930d630ba..8ecbb8f4946552c7e22c8fb863e01a958ca7b1fe 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -37,6 +37,10 @@ static HLIST_HEAD(clk_root_list); static HLIST_HEAD(clk_orphan_list); static LIST_HEAD(clk_notifier_list); +/* List of registered clks that use runtime PM */ +static HLIST_HEAD(clk_rpm_list); +static DEFINE_MUTEX(clk_rpm_list_lock); + static const struct hlist_head *all_lists[] = { &clk_root_list, &clk_orphan_list, @@ -59,6 +63,7 @@ struct clk_core { struct clk_hw *hw; struct module *owner; struct device *dev; + struct hlist_node rpm_node; struct device_node *of_node; struct clk_core *parent; struct clk_parent_map *parents; @@ -122,6 +127,89 @@ static void clk_pm_runtime_put(struct clk_core *core) pm_runtime_put_sync(core->dev); } +/** + * clk_pm_runtime_get_all() - Runtime "get" all clk provider devices + * + * Call clk_pm_runtime_get() on all runtime PM enabled clks in the clk tree so + * that disabling unused clks avoids a deadlock where a device is runtime PM + * resuming/suspending and the runtime PM callback is trying to grab the + * prepare_lock for something like clk_prepare_enable() while + * clk_disable_unused_subtree() holds the prepare_lock and is trying to runtime + * PM resume/suspend the device as well. + * + * Context: Acquires the 'clk_rpm_list_lock' and returns with the lock held on + * success. Otherwise the lock is released on failure. + * + * Return: 0 on success, negative errno otherwise. + */ +static int clk_pm_runtime_get_all(void) +{ + int ret; + struct clk_core *core, *failed; + + /* + * Grab the list lock to prevent any new clks from being registered + * or unregistered until clk_pm_runtime_put_all(). + */ + mutex_lock(&clk_rpm_list_lock); + + /* + * Runtime PM "get" all the devices that are needed for the clks + * currently registered. Do this without holding the prepare_lock, to + * avoid the deadlock. + */ + hlist_for_each_entry(core, &clk_rpm_list, rpm_node) { + ret = clk_pm_runtime_get(core); + if (ret) { + failed = core; + pr_err("clk: Failed to runtime PM get '%s' for clk '%s'\n", + dev_name(failed->dev), failed->name); + goto err; + } + } + + return 0; + +err: + hlist_for_each_entry(core, &clk_rpm_list, rpm_node) { + if (core == failed) + break; + + clk_pm_runtime_put(core); + } + mutex_unlock(&clk_rpm_list_lock); + + return ret; +} + +/** + * clk_pm_runtime_put_all() - Runtime "put" all clk provider devices + * + * Put the runtime PM references taken in clk_pm_runtime_get_all() and release + * the 'clk_rpm_list_lock'. + */ +static void clk_pm_runtime_put_all(void) +{ + struct clk_core *core; + + hlist_for_each_entry(core, &clk_rpm_list, rpm_node) + clk_pm_runtime_put(core); + mutex_unlock(&clk_rpm_list_lock); +} + +static void clk_pm_runtime_init(struct clk_core *core) +{ + struct device *dev = core->dev; + + if (dev && pm_runtime_enabled(dev)) { + core->rpm_enabled = true; + + mutex_lock(&clk_rpm_list_lock); + hlist_add_head(&core->rpm_node, &clk_rpm_list); + mutex_unlock(&clk_rpm_list_lock); + } +} + /*** locking ***/ static void clk_prepare_lock(void) { @@ -407,6 +495,9 @@ static struct clk_core *clk_core_get(struct clk_core *core, u8 p_index) if (IS_ERR(hw)) return ERR_CAST(hw); + if (!hw) + return NULL; + return hw->core; } @@ -1307,9 +1398,6 @@ static void __init clk_unprepare_unused_subtree(struct clk_core *core) if (core->flags & CLK_IGNORE_UNUSED) return; - if (clk_pm_runtime_get(core)) - return; - if (clk_core_is_prepared(core)) { trace_clk_unprepare(core); if (core->ops->unprepare_unused) @@ -1318,8 +1406,6 @@ static void __init clk_unprepare_unused_subtree(struct clk_core *core) core->ops->unprepare(core->hw); trace_clk_unprepare_complete(core); } - - clk_pm_runtime_put(core); } static void __init clk_disable_unused_subtree(struct clk_core *core) @@ -1335,9 +1421,6 @@ static void __init clk_disable_unused_subtree(struct clk_core *core) if (core->flags & CLK_OPS_PARENT_ENABLE) clk_core_prepare_enable(core->parent); - if (clk_pm_runtime_get(core)) - goto unprepare_out; - flags = clk_enable_lock(); if (core->enable_count) @@ -1362,8 +1445,6 @@ static void __init clk_disable_unused_subtree(struct clk_core *core) unlock_out: clk_enable_unlock(flags); - clk_pm_runtime_put(core); -unprepare_out: if (core->flags & CLK_OPS_PARENT_ENABLE) clk_core_disable_unprepare(core->parent); } @@ -1379,12 +1460,22 @@ __setup("clk_ignore_unused", clk_ignore_unused_setup); static int __init clk_disable_unused(void) { struct clk_core *core; + int ret; if (clk_ignore_unused) { pr_warn("clk: Not disabling unused clocks\n"); return 0; } + pr_info("clk: Disabling unused clocks\n"); + + ret = clk_pm_runtime_get_all(); + if (ret) + return ret; + /* + * Grab the prepare lock to keep the clk topology stable while iterating + * over clks. + */ clk_prepare_lock(); hlist_for_each_entry(core, &clk_root_list, child_node) @@ -1401,6 +1492,8 @@ static int __init clk_disable_unused(void) clk_prepare_unlock(); + clk_pm_runtime_put_all(); + return 0; } late_initcall_sync(clk_disable_unused); @@ -3112,28 +3205,41 @@ static void clk_summary_show_one(struct seq_file *s, struct clk_core *c, int level) { int phase; + struct clk *clk_user; + int multi_node = 0; - seq_printf(s, "%*s%-*s %7d %8d %8d %11lu %10lu ", + seq_printf(s, "%*s%-*s %-7d %-8d %-8d %-11lu %-10lu ", level * 3 + 1, "", - 30 - level * 3, c->name, + 35 - level * 3, c->name, c->enable_count, c->prepare_count, c->protect_count, clk_core_get_rate_recalc(c), clk_core_get_accuracy_recalc(c)); phase = clk_core_get_phase(c); if (phase >= 0) - seq_printf(s, "%5d", phase); + seq_printf(s, "%-5d", phase); else seq_puts(s, "-----"); - seq_printf(s, " %6d", clk_core_get_scaled_duty_cycle(c, 100000)); + seq_printf(s, " %-6d", clk_core_get_scaled_duty_cycle(c, 100000)); if (c->ops->is_enabled) - seq_printf(s, " %9c\n", clk_core_is_enabled(c) ? 'Y' : 'N'); + seq_printf(s, " %5c ", clk_core_is_enabled(c) ? 'Y' : 'N'); else if (!c->ops->enable) - seq_printf(s, " %9c\n", 'Y'); + seq_printf(s, " %5c ", 'Y'); else - seq_printf(s, " %9c\n", '?'); + seq_printf(s, " %5c ", '?'); + + hlist_for_each_entry(clk_user, &c->clks, clks_node) { + seq_printf(s, "%*s%-*s %-25s\n", + level * 3 + 2 + 105 * multi_node, "", + 30, + clk_user->dev_id ? clk_user->dev_id : "deviceless", + clk_user->con_id ? clk_user->con_id : "no_connection_id"); + + multi_node = 1; + } + } static void clk_summary_show_subtree(struct seq_file *s, struct clk_core *c, @@ -3141,9 +3247,7 @@ static void clk_summary_show_subtree(struct seq_file *s, struct clk_core *c, { struct clk_core *child; - clk_pm_runtime_get(c); clk_summary_show_one(s, c, level); - clk_pm_runtime_put(c); hlist_for_each_entry(child, &c->children, child_node) clk_summary_show_subtree(s, child, level + 1); @@ -3152,11 +3256,16 @@ static void clk_summary_show_subtree(struct seq_file *s, struct clk_core *c, static int clk_summary_show(struct seq_file *s, void *data) { struct clk_core *c; - struct hlist_head **lists = (struct hlist_head **)s->private; + struct hlist_head **lists = s->private; + int ret; - seq_puts(s, " enable prepare protect duty hardware\n"); - seq_puts(s, " clock count count count rate accuracy phase cycle enable\n"); - seq_puts(s, "-------------------------------------------------------------------------------------------------------\n"); + seq_puts(s, " enable prepare protect duty hardware connection\n"); + seq_puts(s, " clock count count count rate accuracy phase cycle enable consumer id\n"); + seq_puts(s, "---------------------------------------------------------------------------------------------------------------------------------------------\n"); + + ret = clk_pm_runtime_get_all(); + if (ret) + return ret; clk_prepare_lock(); @@ -3165,6 +3274,7 @@ static int clk_summary_show(struct seq_file *s, void *data) clk_summary_show_subtree(s, c, 0); clk_prepare_unlock(); + clk_pm_runtime_put_all(); return 0; } @@ -3211,9 +3321,15 @@ static int clk_dump_show(struct seq_file *s, void *data) { struct clk_core *c; bool first_node = true; - struct hlist_head **lists = (struct hlist_head **)s->private; + struct hlist_head **lists = s->private; + int ret; + + ret = clk_pm_runtime_get_all(); + if (ret) + return ret; seq_putc(s, '{'); + clk_prepare_lock(); for (; *lists; lists++) { @@ -3226,6 +3342,7 @@ static int clk_dump_show(struct seq_file *s, void *data) } clk_prepare_unlock(); + clk_pm_runtime_put_all(); seq_puts(s, "}\n"); return 0; @@ -3833,8 +3950,6 @@ static int __clk_core_init(struct clk_core *core) } clk_core_reparent_orphans_nolock(); - - kref_init(&core->ref); out: clk_pm_runtime_put(core); unlock: @@ -4063,6 +4178,22 @@ static void clk_core_free_parent_map(struct clk_core *core) kfree(core->parents); } +/* Free memory allocated for a struct clk_core */ +static void __clk_release(struct kref *ref) +{ + struct clk_core *core = container_of(ref, struct clk_core, ref); + + if (core->rpm_enabled) { + mutex_lock(&clk_rpm_list_lock); + hlist_del(&core->rpm_node); + mutex_unlock(&clk_rpm_list_lock); + } + + clk_core_free_parent_map(core); + kfree_const(core->name); + kfree(core); +} + static struct clk * __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) { @@ -4083,6 +4214,8 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) goto fail_out; } + kref_init(&core->ref); + core->name = kstrdup_const(init->name, GFP_KERNEL); if (!core->name) { ret = -ENOMEM; @@ -4095,9 +4228,8 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) } core->ops = init->ops; - if (dev && pm_runtime_enabled(dev)) - core->rpm_enabled = true; core->dev = dev; + clk_pm_runtime_init(core); core->of_node = np; if (dev && dev->driver) core->owner = dev->driver->owner; @@ -4137,12 +4269,10 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) hw->clk = NULL; fail_create_clk: - clk_core_free_parent_map(core); fail_parents: fail_ops: - kfree_const(core->name); fail_name: - kfree(core); + kref_put(&core->ref, __clk_release); fail_out: return ERR_PTR(ret); } @@ -4222,18 +4352,6 @@ int of_clk_hw_register(struct device_node *node, struct clk_hw *hw) } EXPORT_SYMBOL_GPL(of_clk_hw_register); -/* Free memory allocated for a clock. */ -static void __clk_release(struct kref *ref) -{ - struct clk_core *core = container_of(ref, struct clk_core, ref); - - lockdep_assert_held(&prepare_lock); - - clk_core_free_parent_map(core); - kfree_const(core->name); - kfree(core); -} - /* * Empty clk_ops for unregistered clocks. These are used temporarily * after clk_unregister() was called on a clock and until last clock @@ -4317,7 +4435,8 @@ void clk_unregister(struct clk *clk) if (ops == &clk_nodrv_ops) { pr_err("%s: unregistered clock: %s\n", __func__, clk->core->name); - goto unlock; + clk_prepare_unlock(); + return; } /* * Assign empty clock ops for consumers that might still hold @@ -4351,11 +4470,10 @@ void clk_unregister(struct clk *clk) if (clk->core->protect_count) pr_warn("%s: unregistering protected clock: %s\n", __func__, clk->core->name); + clk_prepare_unlock(); kref_put(&clk->core->ref, __clk_release); free_clk(clk); -unlock: - clk_prepare_unlock(); } EXPORT_SYMBOL_GPL(clk_unregister); @@ -4514,13 +4632,11 @@ void __clk_put(struct clk *clk) if (clk->min_rate > 0 || clk->max_rate < ULONG_MAX) clk_set_rate_range_nolock(clk, 0, ULONG_MAX); - owner = clk->core->owner; - kref_put(&clk->core->ref, __clk_release); - clk_prepare_unlock(); + owner = clk->core->owner; + kref_put(&clk->core->ref, __clk_release); module_put(owner); - free_clk(clk); } diff --git a/drivers/clk/hisilicon/clk-hi3519.c b/drivers/clk/hisilicon/clk-hi3519.c index ad0c7f350cf0314845edff48b053accd0a187b3b..60d8a27a9082440364693ee286891af02b0665a2 100644 --- a/drivers/clk/hisilicon/clk-hi3519.c +++ b/drivers/clk/hisilicon/clk-hi3519.c @@ -130,7 +130,7 @@ static void hi3519_clk_unregister(struct platform_device *pdev) of_clk_del_provider(pdev->dev.of_node); hisi_clk_unregister_gate(hi3519_gate_clks, - ARRAY_SIZE(hi3519_mux_clks), + ARRAY_SIZE(hi3519_gate_clks), crg->clk_data); hisi_clk_unregister_mux(hi3519_mux_clks, ARRAY_SIZE(hi3519_mux_clks), diff --git a/drivers/clk/hisilicon/clk-hi3559a.c b/drivers/clk/hisilicon/clk-hi3559a.c index 9ea1a80acbe8b5be6475d2f729e5609c0a61d3a9..0272276550ff1cefc51e307eba9f90319b8a7ac0 100644 --- a/drivers/clk/hisilicon/clk-hi3559a.c +++ b/drivers/clk/hisilicon/clk-hi3559a.c @@ -491,7 +491,6 @@ static void hisi_clk_register_pll(struct hi3559av100_pll_clock *clks, clk = clk_register(NULL, &p_clk->hw); if (IS_ERR(clk)) { - devm_kfree(dev, p_clk); dev_err(dev, "%s: failed to register clock %s\n", __func__, clks[i].name); continue; diff --git a/drivers/clk/mediatek/clk-gate.c b/drivers/clk/mediatek/clk-gate.c index 0c867136e49d79a05ceb0391621c529d53ba1b11..67d9e741c5e736a61e2705a383ecaa07155d985e 100644 --- a/drivers/clk/mediatek/clk-gate.c +++ b/drivers/clk/mediatek/clk-gate.c @@ -152,12 +152,12 @@ const struct clk_ops mtk_clk_gate_ops_no_setclr_inv = { }; EXPORT_SYMBOL_GPL(mtk_clk_gate_ops_no_setclr_inv); -static struct clk_hw *mtk_clk_register_gate(const char *name, +static struct clk_hw *mtk_clk_register_gate(struct device *dev, const char *name, const char *parent_name, struct regmap *regmap, int set_ofs, int clr_ofs, int sta_ofs, u8 bit, const struct clk_ops *ops, - unsigned long flags, struct device *dev) + unsigned long flags) { struct mtk_clk_gate *cg; int ret; @@ -202,10 +202,9 @@ static void mtk_clk_unregister_gate(struct clk_hw *hw) kfree(cg); } -int mtk_clk_register_gates_with_dev(struct device_node *node, - const struct mtk_gate *clks, int num, - struct clk_hw_onecell_data *clk_data, - struct device *dev) +int mtk_clk_register_gates(struct device *dev, struct device_node *node, + const struct mtk_gate *clks, int num, + struct clk_hw_onecell_data *clk_data) { int i; struct clk_hw *hw; @@ -229,13 +228,13 @@ int mtk_clk_register_gates_with_dev(struct device_node *node, continue; } - hw = mtk_clk_register_gate(gate->name, gate->parent_name, + hw = mtk_clk_register_gate(dev, gate->name, gate->parent_name, regmap, gate->regs->set_ofs, gate->regs->clr_ofs, gate->regs->sta_ofs, gate->shift, gate->ops, - gate->flags, dev); + gate->flags); if (IS_ERR(hw)) { pr_err("Failed to register clk %s: %pe\n", gate->name, @@ -261,14 +260,6 @@ err: return PTR_ERR(hw); } -EXPORT_SYMBOL_GPL(mtk_clk_register_gates_with_dev); - -int mtk_clk_register_gates(struct device_node *node, - const struct mtk_gate *clks, int num, - struct clk_hw_onecell_data *clk_data) -{ - return mtk_clk_register_gates_with_dev(node, clks, num, clk_data, NULL); -} EXPORT_SYMBOL_GPL(mtk_clk_register_gates); void mtk_clk_unregister_gates(const struct mtk_gate *clks, int num, diff --git a/drivers/clk/mediatek/clk-gate.h b/drivers/clk/mediatek/clk-gate.h index d9897ef5352844badc0b8107693aa6751b292ef1..1a46b4c56fc5d0a1cb4f16fd7a3fae8a3314271a 100644 --- a/drivers/clk/mediatek/clk-gate.h +++ b/drivers/clk/mediatek/clk-gate.h @@ -50,15 +50,10 @@ struct mtk_gate { #define GATE_MTK(_id, _name, _parent, _regs, _shift, _ops) \ GATE_MTK_FLAGS(_id, _name, _parent, _regs, _shift, _ops, 0) -int mtk_clk_register_gates(struct device_node *node, +int mtk_clk_register_gates(struct device *dev, struct device_node *node, const struct mtk_gate *clks, int num, struct clk_hw_onecell_data *clk_data); -int mtk_clk_register_gates_with_dev(struct device_node *node, - const struct mtk_gate *clks, int num, - struct clk_hw_onecell_data *clk_data, - struct device *dev); - void mtk_clk_unregister_gates(const struct mtk_gate *clks, int num, struct clk_hw_onecell_data *clk_data); diff --git a/drivers/clk/mediatek/clk-mt2701-aud.c b/drivers/clk/mediatek/clk-mt2701-aud.c index 4287bd3f545ee0bbeec873120c3c8fc5d48cb85d..03ab212aa7f4e64e2d80306a9e7293720f2a7636 100644 --- a/drivers/clk/mediatek/clk-mt2701-aud.c +++ b/drivers/clk/mediatek/clk-mt2701-aud.c @@ -127,8 +127,8 @@ static int clk_mt2701_aud_probe(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_AUD_NR); - mtk_clk_register_gates(node, audio_clks, ARRAY_SIZE(audio_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, audio_clks, + ARRAY_SIZE(audio_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) { diff --git a/drivers/clk/mediatek/clk-mt2701-eth.c b/drivers/clk/mediatek/clk-mt2701-eth.c index 601358748750e03009db6d9b4ca97366fb104e65..924725d67c13ecb42bf483bc674c9a3a6727023e 100644 --- a/drivers/clk/mediatek/clk-mt2701-eth.c +++ b/drivers/clk/mediatek/clk-mt2701-eth.c @@ -51,8 +51,8 @@ static int clk_mt2701_eth_probe(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_ETHSYS_NR); - mtk_clk_register_gates(node, eth_clks, ARRAY_SIZE(eth_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, eth_clks, + ARRAY_SIZE(eth_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) diff --git a/drivers/clk/mediatek/clk-mt2701-g3d.c b/drivers/clk/mediatek/clk-mt2701-g3d.c index 8d1fc8e3336eb22e43f3c698f69917391d4986e7..501fb99bb41a25ddc86345cc5c3f5099578d11b0 100644 --- a/drivers/clk/mediatek/clk-mt2701-g3d.c +++ b/drivers/clk/mediatek/clk-mt2701-g3d.c @@ -45,7 +45,7 @@ static int clk_mt2701_g3dsys_init(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_G3DSYS_NR); - mtk_clk_register_gates(node, g3d_clks, ARRAY_SIZE(g3d_clks), + mtk_clk_register_gates(&pdev->dev, node, g3d_clks, ARRAY_SIZE(g3d_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); diff --git a/drivers/clk/mediatek/clk-mt2701-hif.c b/drivers/clk/mediatek/clk-mt2701-hif.c index edeeb033a2350a5e64ee41cd939866eab5c88aba..1ddefc21d6a0dfae3b583484d9f0a75b31939538 100644 --- a/drivers/clk/mediatek/clk-mt2701-hif.c +++ b/drivers/clk/mediatek/clk-mt2701-hif.c @@ -48,8 +48,8 @@ static int clk_mt2701_hif_probe(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_HIFSYS_NR); - mtk_clk_register_gates(node, hif_clks, ARRAY_SIZE(hif_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, hif_clks, + ARRAY_SIZE(hif_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) { diff --git a/drivers/clk/mediatek/clk-mt2701-mm.c b/drivers/clk/mediatek/clk-mt2701-mm.c index eb069f3bc9a2b07b54fd05c63b12981cb32efff0..f4885dffb324f2af7d6d7d17eb311ebe9307bdbc 100644 --- a/drivers/clk/mediatek/clk-mt2701-mm.c +++ b/drivers/clk/mediatek/clk-mt2701-mm.c @@ -76,8 +76,8 @@ static int clk_mt2701_mm_probe(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_MM_NR); - mtk_clk_register_gates(node, mm_clks, ARRAY_SIZE(mm_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, mm_clks, + ARRAY_SIZE(mm_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) diff --git a/drivers/clk/mediatek/clk-mt2701.c b/drivers/clk/mediatek/clk-mt2701.c index 00d2e81bdd43ec4f17361713ac479ecf6269af89..e80fe9c942eebcace8a541d0fc113bb87b50bf3f 100644 --- a/drivers/clk/mediatek/clk-mt2701.c +++ b/drivers/clk/mediatek/clk-mt2701.c @@ -679,14 +679,15 @@ static int mtk_topckgen_init(struct platform_device *pdev) mtk_clk_register_factors(top_fixed_divs, ARRAY_SIZE(top_fixed_divs), clk_data); - mtk_clk_register_composites(top_muxes, ARRAY_SIZE(top_muxes), - base, &mt2701_clk_lock, clk_data); + mtk_clk_register_composites(&pdev->dev, top_muxes, + ARRAY_SIZE(top_muxes), base, + &mt2701_clk_lock, clk_data); mtk_clk_register_dividers(top_adj_divs, ARRAY_SIZE(top_adj_divs), base, &mt2701_clk_lock, clk_data); - mtk_clk_register_gates(node, top_clks, ARRAY_SIZE(top_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, top_clks, + ARRAY_SIZE(top_clks), clk_data); return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); } @@ -789,8 +790,8 @@ static int mtk_infrasys_init(struct platform_device *pdev) } } - mtk_clk_register_gates(node, infra_clks, ARRAY_SIZE(infra_clks), - infra_clk_data); + mtk_clk_register_gates(&pdev->dev, node, infra_clks, + ARRAY_SIZE(infra_clks), infra_clk_data); mtk_clk_register_factors(infra_fixed_divs, ARRAY_SIZE(infra_fixed_divs), infra_clk_data); @@ -902,11 +903,12 @@ static int mtk_pericfg_init(struct platform_device *pdev) if (!clk_data) return -ENOMEM; - mtk_clk_register_gates(node, peri_clks, ARRAY_SIZE(peri_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, peri_clks, + ARRAY_SIZE(peri_clks), clk_data); - mtk_clk_register_composites(peri_muxs, ARRAY_SIZE(peri_muxs), base, - &mt2701_clk_lock, clk_data); + mtk_clk_register_composites(&pdev->dev, peri_muxs, + ARRAY_SIZE(peri_muxs), base, + &mt2701_clk_lock, clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) diff --git a/drivers/clk/mediatek/clk-mt2712-mm.c b/drivers/clk/mediatek/clk-mt2712-mm.c index ad6daa8f28a83c4e67f03b2ab41dba25201fc852..e5264f1ce60d0acb5869d2d5284165105f75c1f8 100644 --- a/drivers/clk/mediatek/clk-mt2712-mm.c +++ b/drivers/clk/mediatek/clk-mt2712-mm.c @@ -117,8 +117,8 @@ static int clk_mt2712_mm_probe(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_MM_NR_CLK); - mtk_clk_register_gates(node, mm_clks, ARRAY_SIZE(mm_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, mm_clks, + ARRAY_SIZE(mm_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); diff --git a/drivers/clk/mediatek/clk-mt2712.c b/drivers/clk/mediatek/clk-mt2712.c index d6c2cc183b1a10317152c01401d2160d16b7fe83..a0f0c9ed48d10d325ec6d857d1700b7fc59abffd 100644 --- a/drivers/clk/mediatek/clk-mt2712.c +++ b/drivers/clk/mediatek/clk-mt2712.c @@ -1320,12 +1320,13 @@ static int clk_mt2712_top_probe(struct platform_device *pdev) mtk_clk_register_factors(top_early_divs, ARRAY_SIZE(top_early_divs), top_clk_data); mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), top_clk_data); - mtk_clk_register_composites(top_muxes, ARRAY_SIZE(top_muxes), base, - &mt2712_clk_lock, top_clk_data); + mtk_clk_register_composites(&pdev->dev, top_muxes, + ARRAY_SIZE(top_muxes), base, + &mt2712_clk_lock, top_clk_data); mtk_clk_register_dividers(top_adj_divs, ARRAY_SIZE(top_adj_divs), base, &mt2712_clk_lock, top_clk_data); - mtk_clk_register_gates(node, top_clks, ARRAY_SIZE(top_clks), - top_clk_data); + mtk_clk_register_gates(&pdev->dev, node, top_clks, + ARRAY_SIZE(top_clks), top_clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, top_clk_data); @@ -1344,8 +1345,8 @@ static int clk_mt2712_infra_probe(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_INFRA_NR_CLK); - mtk_clk_register_gates(node, infra_clks, ARRAY_SIZE(infra_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, infra_clks, + ARRAY_SIZE(infra_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); @@ -1366,8 +1367,8 @@ static int clk_mt2712_peri_probe(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_PERI_NR_CLK); - mtk_clk_register_gates(node, peri_clks, ARRAY_SIZE(peri_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, peri_clks, + ARRAY_SIZE(peri_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); @@ -1395,8 +1396,11 @@ static int clk_mt2712_mcu_probe(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_MCU_NR_CLK); - mtk_clk_register_composites(mcu_muxes, ARRAY_SIZE(mcu_muxes), base, - &mt2712_clk_lock, clk_data); + r = mtk_clk_register_composites(&pdev->dev, mcu_muxes, + ARRAY_SIZE(mcu_muxes), base, + &mt2712_clk_lock, clk_data); + if (r) + dev_err(&pdev->dev, "Could not register composites: %d\n", r); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); diff --git a/drivers/clk/mediatek/clk-mt6765.c b/drivers/clk/mediatek/clk-mt6765.c index 2c6a52ff5564e2cff09000bd5ea7e698de9155c2..c4941523f5520f1bc0956e70c64101a04104d4eb 100644 --- a/drivers/clk/mediatek/clk-mt6765.c +++ b/drivers/clk/mediatek/clk-mt6765.c @@ -743,7 +743,7 @@ static int clk_mt6765_apmixed_probe(struct platform_device *pdev) mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); - mtk_clk_register_gates(node, apmixed_clks, + mtk_clk_register_gates(&pdev->dev, node, apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); @@ -782,10 +782,11 @@ static int clk_mt6765_top_probe(struct platform_device *pdev) clk_data); mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data); - mtk_clk_register_muxes(top_muxes, ARRAY_SIZE(top_muxes), node, + mtk_clk_register_muxes(&pdev->dev, top_muxes, + ARRAY_SIZE(top_muxes), node, &mt6765_clk_lock, clk_data); - mtk_clk_register_gates(node, top_clks, ARRAY_SIZE(top_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, top_clks, + ARRAY_SIZE(top_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); @@ -820,8 +821,8 @@ static int clk_mt6765_ifr_probe(struct platform_device *pdev) if (!clk_data) return -ENOMEM; - mtk_clk_register_gates(node, ifr_clks, ARRAY_SIZE(ifr_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, ifr_clks, + ARRAY_SIZE(ifr_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) diff --git a/drivers/clk/mediatek/clk-mt6779-mm.c b/drivers/clk/mediatek/clk-mt6779-mm.c index eda8cbee3d234203fedeb7438c7aa45601184d67..2cccf62d3b36f024288423d0f5a238aa3de3e7ba 100644 --- a/drivers/clk/mediatek/clk-mt6779-mm.c +++ b/drivers/clk/mediatek/clk-mt6779-mm.c @@ -93,8 +93,8 @@ static int clk_mt6779_mm_probe(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_MM_NR_CLK); - mtk_clk_register_gates(node, mm_clks, ARRAY_SIZE(mm_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, mm_clks, + ARRAY_SIZE(mm_clks), clk_data); return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); } diff --git a/drivers/clk/mediatek/clk-mt6779.c b/drivers/clk/mediatek/clk-mt6779.c index 39dadc9547088c4cc144ba60a01bb7db23f57bbb..7fe9d12b2dfddfd7887efef547b0f4fb1f4df52d 100644 --- a/drivers/clk/mediatek/clk-mt6779.c +++ b/drivers/clk/mediatek/clk-mt6779.c @@ -1223,7 +1223,7 @@ static int clk_mt6779_apmixed_probe(struct platform_device *pdev) mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); - mtk_clk_register_gates(node, apmixed_clks, + mtk_clk_register_gates(&pdev->dev, node, apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); @@ -1248,14 +1248,17 @@ static int clk_mt6779_top_probe(struct platform_device *pdev) mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data); - mtk_clk_register_muxes(top_muxes, ARRAY_SIZE(top_muxes), - node, &mt6779_clk_lock, clk_data); + mtk_clk_register_muxes(&pdev->dev, top_muxes, + ARRAY_SIZE(top_muxes), node, + &mt6779_clk_lock, clk_data); - mtk_clk_register_composites(top_aud_muxes, ARRAY_SIZE(top_aud_muxes), - base, &mt6779_clk_lock, clk_data); + mtk_clk_register_composites(&pdev->dev, top_aud_muxes, + ARRAY_SIZE(top_aud_muxes), base, + &mt6779_clk_lock, clk_data); - mtk_clk_register_composites(top_aud_divs, ARRAY_SIZE(top_aud_divs), - base, &mt6779_clk_lock, clk_data); + mtk_clk_register_composites(&pdev->dev, top_aud_divs, + ARRAY_SIZE(top_aud_divs), base, + &mt6779_clk_lock, clk_data); return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); } @@ -1267,8 +1270,8 @@ static int clk_mt6779_infra_probe(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_INFRA_NR_CLK); - mtk_clk_register_gates(node, infra_clks, ARRAY_SIZE(infra_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, infra_clks, + ARRAY_SIZE(infra_clks), clk_data); return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); } diff --git a/drivers/clk/mediatek/clk-mt6795-infracfg.c b/drivers/clk/mediatek/clk-mt6795-infracfg.c index df7eed6e071e3354f0aba9b757f07524335af5d0..8025d171d6923585837cf3e840b2df571eeb4f08 100644 --- a/drivers/clk/mediatek/clk-mt6795-infracfg.c +++ b/drivers/clk/mediatek/clk-mt6795-infracfg.c @@ -101,7 +101,8 @@ static int clk_mt6795_infracfg_probe(struct platform_device *pdev) if (ret) goto free_clk_data; - ret = mtk_clk_register_gates(node, infra_gates, ARRAY_SIZE(infra_gates), clk_data); + ret = mtk_clk_register_gates(&pdev->dev, node, infra_gates, + ARRAY_SIZE(infra_gates), clk_data); if (ret) goto free_clk_data; diff --git a/drivers/clk/mediatek/clk-mt6795-mm.c b/drivers/clk/mediatek/clk-mt6795-mm.c index fd73f202f2925e93b0342c4ba389718beccf1b0e..eebb6143ada221a470a066b93203344eba264f6a 100644 --- a/drivers/clk/mediatek/clk-mt6795-mm.c +++ b/drivers/clk/mediatek/clk-mt6795-mm.c @@ -87,7 +87,8 @@ static int clk_mt6795_mm_probe(struct platform_device *pdev) if (!clk_data) return -ENOMEM; - ret = mtk_clk_register_gates(node, mm_gates, ARRAY_SIZE(mm_gates), clk_data); + ret = mtk_clk_register_gates(&pdev->dev, node, mm_gates, + ARRAY_SIZE(mm_gates), clk_data); if (ret) goto free_clk_data; diff --git a/drivers/clk/mediatek/clk-mt6795-pericfg.c b/drivers/clk/mediatek/clk-mt6795-pericfg.c index cb28d35dad59b4e304905edb97245ffaca934dec..08aaa9b09c363e77db3443ba8d4b62f41a38aea5 100644 --- a/drivers/clk/mediatek/clk-mt6795-pericfg.c +++ b/drivers/clk/mediatek/clk-mt6795-pericfg.c @@ -109,11 +109,13 @@ static int clk_mt6795_pericfg_probe(struct platform_device *pdev) if (ret) goto free_clk_data; - ret = mtk_clk_register_gates(node, peri_gates, ARRAY_SIZE(peri_gates), clk_data); + ret = mtk_clk_register_gates(&pdev->dev, node, peri_gates, + ARRAY_SIZE(peri_gates), clk_data); if (ret) goto free_clk_data; - ret = mtk_clk_register_composites(peri_clks, ARRAY_SIZE(peri_clks), base, + ret = mtk_clk_register_composites(&pdev->dev, peri_clks, + ARRAY_SIZE(peri_clks), base, &mt6795_peri_clk_lock, clk_data); if (ret) goto unregister_gates; diff --git a/drivers/clk/mediatek/clk-mt6795-topckgen.c b/drivers/clk/mediatek/clk-mt6795-topckgen.c index 2948dd1aee8fa796178d472cd4cf03c13ba692ce..2ab8bf5d6d6d99b128c4f07edcc4383ab158a8c5 100644 --- a/drivers/clk/mediatek/clk-mt6795-topckgen.c +++ b/drivers/clk/mediatek/clk-mt6795-topckgen.c @@ -552,12 +552,14 @@ static int clk_mt6795_topckgen_probe(struct platform_device *pdev) if (ret) goto unregister_fixed_clks; - ret = mtk_clk_register_muxes(top_muxes, ARRAY_SIZE(top_muxes), node, + ret = mtk_clk_register_muxes(&pdev->dev, top_muxes, + ARRAY_SIZE(top_muxes), node, &mt6795_top_clk_lock, clk_data); if (ret) goto unregister_factors; - ret = mtk_clk_register_composites(top_aud_divs, ARRAY_SIZE(top_aud_divs), base, + ret = mtk_clk_register_composites(&pdev->dev, top_aud_divs, + ARRAY_SIZE(top_aud_divs), base, &mt6795_top_clk_lock, clk_data); if (ret) goto unregister_muxes; diff --git a/drivers/clk/mediatek/clk-mt6797-mm.c b/drivers/clk/mediatek/clk-mt6797-mm.c index 99a63f46642fa11b71e868fa3ef9b1dc53e3773d..d5e9fe445e308a12075566fcb564515b1e6ae7dd 100644 --- a/drivers/clk/mediatek/clk-mt6797-mm.c +++ b/drivers/clk/mediatek/clk-mt6797-mm.c @@ -89,8 +89,8 @@ static int clk_mt6797_mm_probe(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_MM_NR); - mtk_clk_register_gates(node, mm_clks, ARRAY_SIZE(mm_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, mm_clks, + ARRAY_SIZE(mm_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) diff --git a/drivers/clk/mediatek/clk-mt6797.c b/drivers/clk/mediatek/clk-mt6797.c index b362e99c8f53c198a685c849dff321eaf32ce700..0429a80f3cad7e7b51c3f736e710670e1a193cf9 100644 --- a/drivers/clk/mediatek/clk-mt6797.c +++ b/drivers/clk/mediatek/clk-mt6797.c @@ -398,7 +398,8 @@ static int mtk_topckgen_init(struct platform_device *pdev) mtk_clk_register_factors(top_fixed_divs, ARRAY_SIZE(top_fixed_divs), clk_data); - mtk_clk_register_composites(top_muxes, ARRAY_SIZE(top_muxes), base, + mtk_clk_register_composites(&pdev->dev, top_muxes, + ARRAY_SIZE(top_muxes), base, &mt6797_clk_lock, clk_data); return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); @@ -584,8 +585,8 @@ static int mtk_infrasys_init(struct platform_device *pdev) } } - mtk_clk_register_gates(node, infra_clks, ARRAY_SIZE(infra_clks), - infra_clk_data); + mtk_clk_register_gates(&pdev->dev, node, infra_clks, + ARRAY_SIZE(infra_clks), infra_clk_data); mtk_clk_register_factors(infra_fixed_divs, ARRAY_SIZE(infra_fixed_divs), infra_clk_data); diff --git a/drivers/clk/mediatek/clk-mt7622-aud.c b/drivers/clk/mediatek/clk-mt7622-aud.c index b17731fa114456625090d0d7fd42d4c8587ba620..e9070d0bea8d6ebbcfa3899a6e6d595332ebcc13 100644 --- a/drivers/clk/mediatek/clk-mt7622-aud.c +++ b/drivers/clk/mediatek/clk-mt7622-aud.c @@ -114,8 +114,8 @@ static int clk_mt7622_audiosys_init(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_AUDIO_NR_CLK); - mtk_clk_register_gates(node, audio_clks, ARRAY_SIZE(audio_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, audio_clks, + ARRAY_SIZE(audio_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) { diff --git a/drivers/clk/mediatek/clk-mt7622-eth.c b/drivers/clk/mediatek/clk-mt7622-eth.c index a60190e83418694cb4721b8428c910cf7b4a8538..ece0f7a7c5f62ea0f9fdf541fb86a0025ac3d628 100644 --- a/drivers/clk/mediatek/clk-mt7622-eth.c +++ b/drivers/clk/mediatek/clk-mt7622-eth.c @@ -69,8 +69,8 @@ static int clk_mt7622_ethsys_init(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_ETH_NR_CLK); - mtk_clk_register_gates(node, eth_clks, ARRAY_SIZE(eth_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, eth_clks, + ARRAY_SIZE(eth_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) @@ -91,8 +91,8 @@ static int clk_mt7622_sgmiisys_init(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_SGMII_NR_CLK); - mtk_clk_register_gates(node, sgmii_clks, ARRAY_SIZE(sgmii_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, sgmii_clks, + ARRAY_SIZE(sgmii_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) diff --git a/drivers/clk/mediatek/clk-mt7622-hif.c b/drivers/clk/mediatek/clk-mt7622-hif.c index 55baa6d06a205b0c2ad91573798b245b55dd3c4c..c57ac2273c4e2d87379b9f62344f6537cdda840e 100644 --- a/drivers/clk/mediatek/clk-mt7622-hif.c +++ b/drivers/clk/mediatek/clk-mt7622-hif.c @@ -80,8 +80,8 @@ static int clk_mt7622_ssusbsys_init(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_SSUSB_NR_CLK); - mtk_clk_register_gates(node, ssusb_clks, ARRAY_SIZE(ssusb_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, ssusb_clks, + ARRAY_SIZE(ssusb_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) @@ -102,8 +102,8 @@ static int clk_mt7622_pciesys_init(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_PCIE_NR_CLK); - mtk_clk_register_gates(node, pcie_clks, ARRAY_SIZE(pcie_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, pcie_clks, + ARRAY_SIZE(pcie_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) diff --git a/drivers/clk/mediatek/clk-mt7622.c b/drivers/clk/mediatek/clk-mt7622.c index eebbb87906930f458d7b53c319f820de7ad4c883..67a296646722ff1af10ad8b216b10e0871c391d3 100644 --- a/drivers/clk/mediatek/clk-mt7622.c +++ b/drivers/clk/mediatek/clk-mt7622.c @@ -615,14 +615,15 @@ static int mtk_topckgen_init(struct platform_device *pdev) mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data); - mtk_clk_register_composites(top_muxes, ARRAY_SIZE(top_muxes), - base, &mt7622_clk_lock, clk_data); + mtk_clk_register_composites(&pdev->dev, top_muxes, + ARRAY_SIZE(top_muxes), base, + &mt7622_clk_lock, clk_data); mtk_clk_register_dividers(top_adj_divs, ARRAY_SIZE(top_adj_divs), base, &mt7622_clk_lock, clk_data); - mtk_clk_register_gates(node, top_clks, ARRAY_SIZE(top_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, top_clks, + ARRAY_SIZE(top_clks), clk_data); return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); } @@ -635,8 +636,8 @@ static int mtk_infrasys_init(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_INFRA_NR_CLK); - mtk_clk_register_gates(node, infra_clks, ARRAY_SIZE(infra_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, infra_clks, + ARRAY_SIZE(infra_clks), clk_data); mtk_clk_register_cpumuxes(node, infra_muxes, ARRAY_SIZE(infra_muxes), clk_data); @@ -663,7 +664,7 @@ static int mtk_apmixedsys_init(struct platform_device *pdev) mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); - mtk_clk_register_gates(node, apmixed_clks, + mtk_clk_register_gates(&pdev->dev, node, apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); @@ -682,10 +683,11 @@ static int mtk_pericfg_init(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_PERI_NR_CLK); - mtk_clk_register_gates(node, peri_clks, ARRAY_SIZE(peri_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, peri_clks, + ARRAY_SIZE(peri_clks), clk_data); - mtk_clk_register_composites(peri_muxes, ARRAY_SIZE(peri_muxes), base, + mtk_clk_register_composites(&pdev->dev, peri_muxes, + ARRAY_SIZE(peri_muxes), base, &mt7622_clk_lock, clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); diff --git a/drivers/clk/mediatek/clk-mt7629-eth.c b/drivers/clk/mediatek/clk-mt7629-eth.c index e1d2635c72c107b4945583e0875811038fa22348..eab838af6d41346a6f8cfe403b8177a80378b326 100644 --- a/drivers/clk/mediatek/clk-mt7629-eth.c +++ b/drivers/clk/mediatek/clk-mt7629-eth.c @@ -82,7 +82,8 @@ static int clk_mt7629_ethsys_init(struct platform_device *pdev) if (!clk_data) return -ENOMEM; - mtk_clk_register_gates(node, eth_clks, CLK_ETH_NR_CLK, clk_data); + mtk_clk_register_gates(&pdev->dev, node, eth_clks, + CLK_ETH_NR_CLK, clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) @@ -106,8 +107,8 @@ static int clk_mt7629_sgmiisys_init(struct platform_device *pdev) if (!clk_data) return -ENOMEM; - mtk_clk_register_gates(node, sgmii_clks[id++], CLK_SGMII_NR_CLK, - clk_data); + mtk_clk_register_gates(&pdev->dev, node, sgmii_clks[id++], + CLK_SGMII_NR_CLK, clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) diff --git a/drivers/clk/mediatek/clk-mt7629-hif.c b/drivers/clk/mediatek/clk-mt7629-hif.c index 3628811a2f57f0cccc1bb24506ac335013328ae7..804900792e490461005f19f8541e4095fc6fa6be 100644 --- a/drivers/clk/mediatek/clk-mt7629-hif.c +++ b/drivers/clk/mediatek/clk-mt7629-hif.c @@ -75,8 +75,8 @@ static int clk_mt7629_ssusbsys_init(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_SSUSB_NR_CLK); - mtk_clk_register_gates(node, ssusb_clks, ARRAY_SIZE(ssusb_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, ssusb_clks, + ARRAY_SIZE(ssusb_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) @@ -97,8 +97,8 @@ static int clk_mt7629_pciesys_init(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_PCIE_NR_CLK); - mtk_clk_register_gates(node, pcie_clks, ARRAY_SIZE(pcie_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, pcie_clks, + ARRAY_SIZE(pcie_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) diff --git a/drivers/clk/mediatek/clk-mt7629.c b/drivers/clk/mediatek/clk-mt7629.c index 01ee45fcd7e3454d40389fe988d5ffcffe35f413..2019e272d1cd7852900305d5ee9619bb964e2538 100644 --- a/drivers/clk/mediatek/clk-mt7629.c +++ b/drivers/clk/mediatek/clk-mt7629.c @@ -566,8 +566,9 @@ static int mtk_topckgen_init(struct platform_device *pdev) mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data); - mtk_clk_register_composites(top_muxes, ARRAY_SIZE(top_muxes), - base, &mt7629_clk_lock, clk_data); + mtk_clk_register_composites(&pdev->dev, top_muxes, + ARRAY_SIZE(top_muxes), base, + &mt7629_clk_lock, clk_data); clk_prepare_enable(clk_data->hws[CLK_TOP_AXI_SEL]->clk); clk_prepare_enable(clk_data->hws[CLK_TOP_MEM_SEL]->clk); @@ -585,8 +586,8 @@ static int mtk_infrasys_init(struct platform_device *pdev) if (!clk_data) return -ENOMEM; - mtk_clk_register_gates(node, infra_clks, ARRAY_SIZE(infra_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, infra_clks, + ARRAY_SIZE(infra_clks), clk_data); mtk_clk_register_cpumuxes(node, infra_muxes, ARRAY_SIZE(infra_muxes), clk_data); @@ -610,10 +611,11 @@ static int mtk_pericfg_init(struct platform_device *pdev) if (!clk_data) return -ENOMEM; - mtk_clk_register_gates(node, peri_clks, ARRAY_SIZE(peri_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, peri_clks, + ARRAY_SIZE(peri_clks), clk_data); - mtk_clk_register_composites(peri_muxes, ARRAY_SIZE(peri_muxes), base, + mtk_clk_register_composites(&pdev->dev, peri_muxes, + ARRAY_SIZE(peri_muxes), base, &mt7629_clk_lock, clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); @@ -637,7 +639,7 @@ static int mtk_apmixedsys_init(struct platform_device *pdev) mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); - mtk_clk_register_gates(node, apmixed_clks, + mtk_clk_register_gates(&pdev->dev, node, apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); clk_prepare_enable(clk_data->hws[CLK_APMIXED_ARMPLL]->clk); diff --git a/drivers/clk/mediatek/clk-mt7986-eth.c b/drivers/clk/mediatek/clk-mt7986-eth.c index c21e1d672384aa72e9a5d4c228ebb9fe739513dc..e04bc6845ea6dc90e605dac01b631d44d63a1e2f 100644 --- a/drivers/clk/mediatek/clk-mt7986-eth.c +++ b/drivers/clk/mediatek/clk-mt7986-eth.c @@ -72,8 +72,8 @@ static void __init mtk_sgmiisys_0_init(struct device_node *node) clk_data = mtk_alloc_clk_data(ARRAY_SIZE(sgmii0_clks)); - mtk_clk_register_gates(node, sgmii0_clks, ARRAY_SIZE(sgmii0_clks), - clk_data); + mtk_clk_register_gates(NULL, node, sgmii0_clks, + ARRAY_SIZE(sgmii0_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) @@ -90,8 +90,8 @@ static void __init mtk_sgmiisys_1_init(struct device_node *node) clk_data = mtk_alloc_clk_data(ARRAY_SIZE(sgmii1_clks)); - mtk_clk_register_gates(node, sgmii1_clks, ARRAY_SIZE(sgmii1_clks), - clk_data); + mtk_clk_register_gates(NULL, node, sgmii1_clks, + ARRAY_SIZE(sgmii1_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); @@ -109,7 +109,7 @@ static void __init mtk_ethsys_init(struct device_node *node) clk_data = mtk_alloc_clk_data(ARRAY_SIZE(eth_clks)); - mtk_clk_register_gates(node, eth_clks, ARRAY_SIZE(eth_clks), clk_data); + mtk_clk_register_gates(NULL, node, eth_clks, ARRAY_SIZE(eth_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); diff --git a/drivers/clk/mediatek/clk-mt7986-infracfg.c b/drivers/clk/mediatek/clk-mt7986-infracfg.c index 74e68a7197301f24dddc07ae7b4a069de5617a93..0a4bf87ee160705d04d33be411d57df1c3bdfbce 100644 --- a/drivers/clk/mediatek/clk-mt7986-infracfg.c +++ b/drivers/clk/mediatek/clk-mt7986-infracfg.c @@ -178,10 +178,11 @@ static int clk_mt7986_infracfg_probe(struct platform_device *pdev) return -ENOMEM; mtk_clk_register_factors(infra_divs, ARRAY_SIZE(infra_divs), clk_data); - mtk_clk_register_muxes(infra_muxes, ARRAY_SIZE(infra_muxes), node, + mtk_clk_register_muxes(&pdev->dev, infra_muxes, + ARRAY_SIZE(infra_muxes), node, &mt7986_clk_lock, clk_data); - mtk_clk_register_gates(node, infra_clks, ARRAY_SIZE(infra_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, infra_clks, + ARRAY_SIZE(infra_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) { diff --git a/drivers/clk/mediatek/clk-mt7986-topckgen.c b/drivers/clk/mediatek/clk-mt7986-topckgen.c index de5121cf28774f718116015bbbb361071332e1a3..c9bf47e6098fdfca74e6560f1c279d3b8c72b565 100644 --- a/drivers/clk/mediatek/clk-mt7986-topckgen.c +++ b/drivers/clk/mediatek/clk-mt7986-topckgen.c @@ -303,7 +303,8 @@ static int clk_mt7986_topckgen_probe(struct platform_device *pdev) mtk_clk_register_fixed_clks(top_fixed_clks, ARRAY_SIZE(top_fixed_clks), clk_data); mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data); - mtk_clk_register_muxes(top_muxes, ARRAY_SIZE(top_muxes), node, + mtk_clk_register_muxes(&pdev->dev, top_muxes, + ARRAY_SIZE(top_muxes), node, &mt7986_clk_lock, clk_data); clk_prepare_enable(clk_data->hws[CLK_TOP_SYSAXI_SEL]->clk); diff --git a/drivers/clk/mediatek/clk-mt8135.c b/drivers/clk/mediatek/clk-mt8135.c index 3ea06d2ec2f11fc6da491b94ed8a2a8f01f978de..a39ad58e27418fc4a7f47f39db7a595487203dd5 100644 --- a/drivers/clk/mediatek/clk-mt8135.c +++ b/drivers/clk/mediatek/clk-mt8135.c @@ -536,8 +536,9 @@ static void __init mtk_topckgen_init(struct device_node *node) mtk_clk_register_factors(root_clk_alias, ARRAY_SIZE(root_clk_alias), clk_data); mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data); - mtk_clk_register_composites(top_muxes, ARRAY_SIZE(top_muxes), base, - &mt8135_clk_lock, clk_data); + mtk_clk_register_composites(NULL, top_muxes, + ARRAY_SIZE(top_muxes), base, + &mt8135_clk_lock, clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) @@ -553,8 +554,8 @@ static void __init mtk_infrasys_init(struct device_node *node) clk_data = mtk_alloc_clk_data(CLK_INFRA_NR_CLK); - mtk_clk_register_gates(node, infra_clks, ARRAY_SIZE(infra_clks), - clk_data); + mtk_clk_register_gates(NULL, node, infra_clks, + ARRAY_SIZE(infra_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) @@ -579,10 +580,11 @@ static void __init mtk_pericfg_init(struct device_node *node) clk_data = mtk_alloc_clk_data(CLK_PERI_NR_CLK); - mtk_clk_register_gates(node, peri_gates, ARRAY_SIZE(peri_gates), - clk_data); - mtk_clk_register_composites(peri_clks, ARRAY_SIZE(peri_clks), base, - &mt8135_clk_lock, clk_data); + mtk_clk_register_gates(NULL, node, peri_gates, + ARRAY_SIZE(peri_gates), clk_data); + mtk_clk_register_composites(NULL, peri_clks, + ARRAY_SIZE(peri_clks), base, + &mt8135_clk_lock, clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) diff --git a/drivers/clk/mediatek/clk-mt8167-aud.c b/drivers/clk/mediatek/clk-mt8167-aud.c index b5ac196cd9454f1a627dd2aac9009b400802e18e..47a7d89d5777c2af13409c42b6d75fdb80ae8a66 100644 --- a/drivers/clk/mediatek/clk-mt8167-aud.c +++ b/drivers/clk/mediatek/clk-mt8167-aud.c @@ -50,7 +50,7 @@ static void __init mtk_audsys_init(struct device_node *node) clk_data = mtk_alloc_clk_data(CLK_AUD_NR_CLK); - mtk_clk_register_gates(node, aud_clks, ARRAY_SIZE(aud_clks), clk_data); + mtk_clk_register_gates(NULL, node, aud_clks, ARRAY_SIZE(aud_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) diff --git a/drivers/clk/mediatek/clk-mt8167-img.c b/drivers/clk/mediatek/clk-mt8167-img.c index 4e7c0772b4f99a1ba58ad954d643da8a3e88a292..e196b3b894a16b48366d58e8b22447961cd4b4a7 100644 --- a/drivers/clk/mediatek/clk-mt8167-img.c +++ b/drivers/clk/mediatek/clk-mt8167-img.c @@ -42,7 +42,7 @@ static void __init mtk_imgsys_init(struct device_node *node) clk_data = mtk_alloc_clk_data(CLK_IMG_NR_CLK); - mtk_clk_register_gates(node, img_clks, ARRAY_SIZE(img_clks), clk_data); + mtk_clk_register_gates(NULL, node, img_clks, ARRAY_SIZE(img_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); diff --git a/drivers/clk/mediatek/clk-mt8167-mfgcfg.c b/drivers/clk/mediatek/clk-mt8167-mfgcfg.c index 192714498b2ec1dc4852629c5857c253929f8d14..602d25f4cb2e2b595d13f5ca2acdc1557753d3e5 100644 --- a/drivers/clk/mediatek/clk-mt8167-mfgcfg.c +++ b/drivers/clk/mediatek/clk-mt8167-mfgcfg.c @@ -40,7 +40,7 @@ static void __init mtk_mfgcfg_init(struct device_node *node) clk_data = mtk_alloc_clk_data(CLK_MFG_NR_CLK); - mtk_clk_register_gates(node, mfg_clks, ARRAY_SIZE(mfg_clks), clk_data); + mtk_clk_register_gates(NULL, node, mfg_clks, ARRAY_SIZE(mfg_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); diff --git a/drivers/clk/mediatek/clk-mt8167-mm.c b/drivers/clk/mediatek/clk-mt8167-mm.c index a94961b7b8cc63be48467e242691cd6fd6a8a2cb..abc70e1221bf94a5204a537014ccf00e75153ddf 100644 --- a/drivers/clk/mediatek/clk-mt8167-mm.c +++ b/drivers/clk/mediatek/clk-mt8167-mm.c @@ -98,8 +98,8 @@ static int clk_mt8167_mm_probe(struct platform_device *pdev) data = &mt8167_mmsys_driver_data; - ret = mtk_clk_register_gates(node, data->gates_clk, data->gates_num, - clk_data); + ret = mtk_clk_register_gates(&pdev->dev, node, data->gates_clk, + data->gates_num, clk_data); if (ret) return ret; diff --git a/drivers/clk/mediatek/clk-mt8167-vdec.c b/drivers/clk/mediatek/clk-mt8167-vdec.c index 38f0ba357d5994c1bfeaea0e74d49145208ef40d..92bc05d997985fb1b8768f5789f5b60fd6f5d1e3 100644 --- a/drivers/clk/mediatek/clk-mt8167-vdec.c +++ b/drivers/clk/mediatek/clk-mt8167-vdec.c @@ -49,7 +49,8 @@ static void __init mtk_vdecsys_init(struct device_node *node) clk_data = mtk_alloc_clk_data(CLK_VDEC_NR_CLK); - mtk_clk_register_gates(node, vdec_clks, ARRAY_SIZE(vdec_clks), clk_data); + mtk_clk_register_gates(NULL, node, vdec_clks, ARRAY_SIZE(vdec_clks), + clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); diff --git a/drivers/clk/mediatek/clk-mt8167.c b/drivers/clk/mediatek/clk-mt8167.c index f900ac4bf7b8d9f86eac5ddf7c397c4e20cade85..91669ebafaf9bc5b08fe221dba27f19066ab20ae 100644 --- a/drivers/clk/mediatek/clk-mt8167.c +++ b/drivers/clk/mediatek/clk-mt8167.c @@ -937,11 +937,12 @@ static void __init mtk_topckgen_init(struct device_node *node) mtk_clk_register_fixed_clks(fixed_clks, ARRAY_SIZE(fixed_clks), clk_data); - mtk_clk_register_gates(node, top_clks, ARRAY_SIZE(top_clks), clk_data); + mtk_clk_register_gates(NULL, node, top_clks, ARRAY_SIZE(top_clks), clk_data); mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data); - mtk_clk_register_composites(top_muxes, ARRAY_SIZE(top_muxes), base, - &mt8167_clk_lock, clk_data); + mtk_clk_register_composites(NULL, top_muxes, + ARRAY_SIZE(top_muxes), base, + &mt8167_clk_lock, clk_data); mtk_clk_register_dividers(top_adj_divs, ARRAY_SIZE(top_adj_divs), base, &mt8167_clk_lock, clk_data); @@ -966,8 +967,9 @@ static void __init mtk_infracfg_init(struct device_node *node) clk_data = mtk_alloc_clk_data(CLK_IFR_NR_CLK); - mtk_clk_register_composites(ifr_muxes, ARRAY_SIZE(ifr_muxes), base, - &mt8167_clk_lock, clk_data); + mtk_clk_register_composites(NULL, ifr_muxes, + ARRAY_SIZE(ifr_muxes), base, + &mt8167_clk_lock, clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) diff --git a/drivers/clk/mediatek/clk-mt8173-mm.c b/drivers/clk/mediatek/clk-mt8173-mm.c index 5826eabdc9c77e88120d80d83b9eae1a9f8bc548..444a3d58c8bf58877759fe3cd5e5787fa5b63875 100644 --- a/drivers/clk/mediatek/clk-mt8173-mm.c +++ b/drivers/clk/mediatek/clk-mt8173-mm.c @@ -112,8 +112,8 @@ static int clk_mt8173_mm_probe(struct platform_device *pdev) data = &mt8173_mmsys_driver_data; - ret = mtk_clk_register_gates(node, data->gates_clk, data->gates_num, - clk_data); + ret = mtk_clk_register_gates(&pdev->dev, node, data->gates_clk, + data->gates_num, clk_data); if (ret) return ret; diff --git a/drivers/clk/mediatek/clk-mt8173.c b/drivers/clk/mediatek/clk-mt8173.c index b8529ee7199dad75afe289b970478ef8ce475f93..d05c1109b4f875b85683d7950810f4b140bbfd71 100644 --- a/drivers/clk/mediatek/clk-mt8173.c +++ b/drivers/clk/mediatek/clk-mt8173.c @@ -869,8 +869,9 @@ static void __init mtk_topckgen_init(struct device_node *node) mtk_clk_register_fixed_clks(fixed_clks, ARRAY_SIZE(fixed_clks), clk_data); mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data); - mtk_clk_register_composites(top_muxes, ARRAY_SIZE(top_muxes), base, - &mt8173_clk_lock, clk_data); + mtk_clk_register_composites(NULL, top_muxes, + ARRAY_SIZE(top_muxes), base, + &mt8173_clk_lock, clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) @@ -888,8 +889,8 @@ static void __init mtk_infrasys_init(struct device_node *node) clk_data = mtk_alloc_clk_data(CLK_INFRA_NR_CLK); - mtk_clk_register_gates(node, infra_clks, ARRAY_SIZE(infra_clks), - clk_data); + mtk_clk_register_gates(NULL, node, infra_clks, + ARRAY_SIZE(infra_clks), clk_data); mtk_clk_register_factors(infra_divs, ARRAY_SIZE(infra_divs), clk_data); mtk_clk_register_cpumuxes(node, cpu_muxes, ARRAY_SIZE(cpu_muxes), @@ -918,10 +919,11 @@ static void __init mtk_pericfg_init(struct device_node *node) clk_data = mtk_alloc_clk_data(CLK_PERI_NR_CLK); - mtk_clk_register_gates(node, peri_gates, ARRAY_SIZE(peri_gates), - clk_data); - mtk_clk_register_composites(peri_clks, ARRAY_SIZE(peri_clks), base, - &mt8173_clk_lock, clk_data); + mtk_clk_register_gates(NULL, node, peri_gates, + ARRAY_SIZE(peri_gates), clk_data); + mtk_clk_register_composites(NULL, peri_clks, + ARRAY_SIZE(peri_clks), base, + &mt8173_clk_lock, clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) @@ -1062,8 +1064,8 @@ static void __init mtk_imgsys_init(struct device_node *node) clk_data = mtk_alloc_clk_data(CLK_IMG_NR_CLK); - mtk_clk_register_gates(node, img_clks, ARRAY_SIZE(img_clks), - clk_data); + mtk_clk_register_gates(NULL, node, img_clks, + ARRAY_SIZE(img_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); @@ -1080,8 +1082,8 @@ static void __init mtk_vdecsys_init(struct device_node *node) clk_data = mtk_alloc_clk_data(CLK_VDEC_NR_CLK); - mtk_clk_register_gates(node, vdec_clks, ARRAY_SIZE(vdec_clks), - clk_data); + mtk_clk_register_gates(NULL, node, vdec_clks, + ARRAY_SIZE(vdec_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) @@ -1097,8 +1099,8 @@ static void __init mtk_vencsys_init(struct device_node *node) clk_data = mtk_alloc_clk_data(CLK_VENC_NR_CLK); - mtk_clk_register_gates(node, venc_clks, ARRAY_SIZE(venc_clks), - clk_data); + mtk_clk_register_gates(NULL, node, venc_clks, + ARRAY_SIZE(venc_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) @@ -1114,8 +1116,8 @@ static void __init mtk_vencltsys_init(struct device_node *node) clk_data = mtk_alloc_clk_data(CLK_VENCLT_NR_CLK); - mtk_clk_register_gates(node, venclt_clks, ARRAY_SIZE(venclt_clks), - clk_data); + mtk_clk_register_gates(NULL, node, venclt_clks, + ARRAY_SIZE(venclt_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) diff --git a/drivers/clk/mediatek/clk-mt8183-audio.c b/drivers/clk/mediatek/clk-mt8183-audio.c index b2d7746eddbed9d8e4e8442579d4097362caff85..f358a6e7a340874d18c7224c3012011fcb1b2230 100644 --- a/drivers/clk/mediatek/clk-mt8183-audio.c +++ b/drivers/clk/mediatek/clk-mt8183-audio.c @@ -75,8 +75,8 @@ static int clk_mt8183_audio_probe(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_AUDIO_NR_CLK); - mtk_clk_register_gates(node, audio_clks, ARRAY_SIZE(audio_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, audio_clks, + ARRAY_SIZE(audio_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) diff --git a/drivers/clk/mediatek/clk-mt8183-mm.c b/drivers/clk/mediatek/clk-mt8183-mm.c index 11ecc6fb0065b5c2eacabc1aa413a2e3590ed984..3580315309132b821d3ede54098a9677ff0cdede 100644 --- a/drivers/clk/mediatek/clk-mt8183-mm.c +++ b/drivers/clk/mediatek/clk-mt8183-mm.c @@ -90,8 +90,8 @@ static int clk_mt8183_mm_probe(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_MM_NR_CLK); - mtk_clk_register_gates(node, mm_clks, ARRAY_SIZE(mm_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, mm_clks, + ARRAY_SIZE(mm_clks), clk_data); return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); } diff --git a/drivers/clk/mediatek/clk-mt8183.c b/drivers/clk/mediatek/clk-mt8183.c index 1860a35a723a59a8b666c117016d464dc3868b51..78620244144e8895c8d871e2b9fec9af634aa559 100644 --- a/drivers/clk/mediatek/clk-mt8183.c +++ b/drivers/clk/mediatek/clk-mt8183.c @@ -1172,8 +1172,8 @@ static int clk_mt8183_apmixed_probe(struct platform_device *pdev) mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); - mtk_clk_register_gates(node, apmixed_clks, ARRAY_SIZE(apmixed_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, apmixed_clks, + ARRAY_SIZE(apmixed_clks), clk_data); return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); } @@ -1238,17 +1238,20 @@ static int clk_mt8183_top_probe(struct platform_device *pdev) mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), top_clk_data); - mtk_clk_register_muxes(top_muxes, ARRAY_SIZE(top_muxes), - node, &mt8183_clk_lock, top_clk_data); + mtk_clk_register_muxes(&pdev->dev, top_muxes, + ARRAY_SIZE(top_muxes), node, + &mt8183_clk_lock, top_clk_data); - mtk_clk_register_composites(top_aud_muxes, ARRAY_SIZE(top_aud_muxes), - base, &mt8183_clk_lock, top_clk_data); + mtk_clk_register_composites(&pdev->dev, top_aud_muxes, + ARRAY_SIZE(top_aud_muxes), base, + &mt8183_clk_lock, top_clk_data); - mtk_clk_register_composites(top_aud_divs, ARRAY_SIZE(top_aud_divs), - base, &mt8183_clk_lock, top_clk_data); + mtk_clk_register_composites(&pdev->dev, top_aud_divs, + ARRAY_SIZE(top_aud_divs), base, + &mt8183_clk_lock, top_clk_data); - mtk_clk_register_gates(node, top_clks, ARRAY_SIZE(top_clks), - top_clk_data); + mtk_clk_register_gates(&pdev->dev, node, top_clks, + ARRAY_SIZE(top_clks), top_clk_data); ret = clk_mt8183_reg_mfg_mux_notifier(&pdev->dev, top_clk_data->hws[CLK_TOP_MUX_MFG]->clk); @@ -1267,8 +1270,8 @@ static int clk_mt8183_infra_probe(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_INFRA_NR_CLK); - mtk_clk_register_gates(node, infra_clks, ARRAY_SIZE(infra_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, infra_clks, + ARRAY_SIZE(infra_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) { @@ -1290,8 +1293,8 @@ static int clk_mt8183_peri_probe(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_PERI_NR_CLK); - mtk_clk_register_gates(node, peri_clks, ARRAY_SIZE(peri_clks), - clk_data); + mtk_clk_register_gates(&pdev->dev, node, peri_clks, + ARRAY_SIZE(peri_clks), clk_data); return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); } @@ -1308,8 +1311,9 @@ static int clk_mt8183_mcu_probe(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_MCU_NR_CLK); - mtk_clk_register_composites(mcu_muxes, ARRAY_SIZE(mcu_muxes), base, - &mt8183_clk_lock, clk_data); + mtk_clk_register_composites(&pdev->dev, mcu_muxes, + ARRAY_SIZE(mcu_muxes), base, + &mt8183_clk_lock, clk_data); return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); } diff --git a/drivers/clk/mediatek/clk-mt8186-mcu.c b/drivers/clk/mediatek/clk-mt8186-mcu.c index dfc305c1fc5d8ffd822573d889870abe02136f1e..e52a2d986c99c9f4fbd8f5006fb2d3d58c7ca2cc 100644 --- a/drivers/clk/mediatek/clk-mt8186-mcu.c +++ b/drivers/clk/mediatek/clk-mt8186-mcu.c @@ -65,7 +65,8 @@ static int clk_mt8186_mcu_probe(struct platform_device *pdev) goto free_mcu_data; } - r = mtk_clk_register_composites(mcu_muxes, ARRAY_SIZE(mcu_muxes), base, + r = mtk_clk_register_composites(&pdev->dev, mcu_muxes, + ARRAY_SIZE(mcu_muxes), base, NULL, clk_data); if (r) goto free_mcu_data; diff --git a/drivers/clk/mediatek/clk-mt8186-mm.c b/drivers/clk/mediatek/clk-mt8186-mm.c index 1d33be4079470e814334128ff9f5b661d425692d..0b72607777fa1657615d8703995f199dec41b185 100644 --- a/drivers/clk/mediatek/clk-mt8186-mm.c +++ b/drivers/clk/mediatek/clk-mt8186-mm.c @@ -69,7 +69,8 @@ static int clk_mt8186_mm_probe(struct platform_device *pdev) if (!clk_data) return -ENOMEM; - r = mtk_clk_register_gates(node, mm_clks, ARRAY_SIZE(mm_clks), clk_data); + r = mtk_clk_register_gates(&pdev->dev, node, mm_clks, + ARRAY_SIZE(mm_clks), clk_data); if (r) goto free_mm_data; diff --git a/drivers/clk/mediatek/clk-mt8186-topckgen.c b/drivers/clk/mediatek/clk-mt8186-topckgen.c index d7f2c4663c853a46bd8beb7a9394b7fc929e9c69..70b6e008a188b243e32d02675b48456c31d57cd0 100644 --- a/drivers/clk/mediatek/clk-mt8186-topckgen.c +++ b/drivers/clk/mediatek/clk-mt8186-topckgen.c @@ -715,17 +715,20 @@ static int clk_mt8186_topck_probe(struct platform_device *pdev) if (r) goto unregister_fixed_clks; - r = mtk_clk_register_muxes(top_mtk_muxes, ARRAY_SIZE(top_mtk_muxes), node, + r = mtk_clk_register_muxes(&pdev->dev, top_mtk_muxes, + ARRAY_SIZE(top_mtk_muxes), node, &mt8186_clk_lock, clk_data); if (r) goto unregister_factors; - r = mtk_clk_register_composites(top_muxes, ARRAY_SIZE(top_muxes), base, + r = mtk_clk_register_composites(&pdev->dev, top_muxes, + ARRAY_SIZE(top_muxes), base, &mt8186_clk_lock, clk_data); if (r) goto unregister_muxes; - r = mtk_clk_register_composites(top_adj_divs, ARRAY_SIZE(top_adj_divs), base, + r = mtk_clk_register_composites(&pdev->dev, top_adj_divs, + ARRAY_SIZE(top_adj_divs), base, &mt8186_clk_lock, clk_data); if (r) goto unregister_composite_muxes; diff --git a/drivers/clk/mediatek/clk-mt8192-aud.c b/drivers/clk/mediatek/clk-mt8192-aud.c index 8c989bffd8c726a8816366f38812df280e18331b..f524188fe4c2de5db9525d9cb2ac03ed9096fa06 100644 --- a/drivers/clk/mediatek/clk-mt8192-aud.c +++ b/drivers/clk/mediatek/clk-mt8192-aud.c @@ -87,7 +87,8 @@ static int clk_mt8192_aud_probe(struct platform_device *pdev) if (!clk_data) return -ENOMEM; - r = mtk_clk_register_gates(node, aud_clks, ARRAY_SIZE(aud_clks), clk_data); + r = mtk_clk_register_gates(&pdev->dev, node, aud_clks, + ARRAY_SIZE(aud_clks), clk_data); if (r) return r; diff --git a/drivers/clk/mediatek/clk-mt8192-mm.c b/drivers/clk/mediatek/clk-mt8192-mm.c index 1be3ff4d407db0e4035955f2326f6b46d82a09ae..e9eb4cf8349acff1ec4a5dfa1171c6c89efd09ad 100644 --- a/drivers/clk/mediatek/clk-mt8192-mm.c +++ b/drivers/clk/mediatek/clk-mt8192-mm.c @@ -91,7 +91,8 @@ static int clk_mt8192_mm_probe(struct platform_device *pdev) if (!clk_data) return -ENOMEM; - r = mtk_clk_register_gates(node, mm_clks, ARRAY_SIZE(mm_clks), clk_data); + r = mtk_clk_register_gates(&pdev->dev, node, mm_clks, + ARRAY_SIZE(mm_clks), clk_data); if (r) return r; diff --git a/drivers/clk/mediatek/clk-mt8192.c b/drivers/clk/mediatek/clk-mt8192.c index d0f2269310706544ac20916698074f017057391c..16feb86dcb1b8655c61c24c508da9d3c48e2620f 100644 --- a/drivers/clk/mediatek/clk-mt8192.c +++ b/drivers/clk/mediatek/clk-mt8192.c @@ -1100,27 +1100,68 @@ static int clk_mt8192_top_probe(struct platform_device *pdev) if (IS_ERR(base)) return PTR_ERR(base); - mtk_clk_register_fixed_clks(top_fixed_clks, ARRAY_SIZE(top_fixed_clks), top_clk_data); - mtk_clk_register_factors(top_early_divs, ARRAY_SIZE(top_early_divs), top_clk_data); - mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), top_clk_data); - mtk_clk_register_muxes(top_mtk_muxes, ARRAY_SIZE(top_mtk_muxes), node, &mt8192_clk_lock, - top_clk_data); - mtk_clk_register_composites(top_muxes, ARRAY_SIZE(top_muxes), base, &mt8192_clk_lock, - top_clk_data); - mtk_clk_register_composites(top_adj_divs, ARRAY_SIZE(top_adj_divs), base, &mt8192_clk_lock, - top_clk_data); - r = mtk_clk_register_gates(node, top_clks, ARRAY_SIZE(top_clks), top_clk_data); + r = mtk_clk_register_fixed_clks(top_fixed_clks, ARRAY_SIZE(top_fixed_clks), top_clk_data); if (r) return r; + r = mtk_clk_register_factors(top_early_divs, ARRAY_SIZE(top_early_divs), top_clk_data); + if (r) + goto unregister_fixed_clks; + + r = mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), top_clk_data); + if (r) + goto unregister_early_factors; + + r = mtk_clk_register_muxes(&pdev->dev, top_mtk_muxes, + ARRAY_SIZE(top_mtk_muxes), node, + &mt8192_clk_lock, top_clk_data); + if (r) + goto unregister_factors; + + r = mtk_clk_register_composites(&pdev->dev, top_muxes, + ARRAY_SIZE(top_muxes), base, + &mt8192_clk_lock, top_clk_data); + if (r) + goto unregister_muxes; + + r = mtk_clk_register_composites(&pdev->dev, top_adj_divs, + ARRAY_SIZE(top_adj_divs), base, + &mt8192_clk_lock, top_clk_data); + if (r) + goto unregister_top_composites; + + r = mtk_clk_register_gates(&pdev->dev, node, top_clks, + ARRAY_SIZE(top_clks), top_clk_data); + if (r) + goto unregister_adj_divs_composites; + r = clk_mt8192_reg_mfg_mux_notifier(&pdev->dev, top_clk_data->hws[CLK_TOP_MFG_PLL_SEL]->clk); if (r) - return r; + goto unregister_gates; - - return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, + r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, top_clk_data); + if (r) + goto unregister_gates; + + return 0; + +unregister_gates: + mtk_clk_unregister_gates(top_clks, ARRAY_SIZE(top_clks), top_clk_data); +unregister_adj_divs_composites: + mtk_clk_unregister_composites(top_adj_divs, ARRAY_SIZE(top_adj_divs), top_clk_data); +unregister_top_composites: + mtk_clk_unregister_composites(top_muxes, ARRAY_SIZE(top_muxes), top_clk_data); +unregister_muxes: + mtk_clk_unregister_muxes(top_mtk_muxes, ARRAY_SIZE(top_mtk_muxes), top_clk_data); +unregister_factors: + mtk_clk_unregister_factors(top_divs, ARRAY_SIZE(top_divs), top_clk_data); +unregister_early_factors: + mtk_clk_unregister_factors(top_early_divs, ARRAY_SIZE(top_early_divs), top_clk_data); +unregister_fixed_clks: + mtk_clk_unregister_fixed_clks(top_fixed_clks, ARRAY_SIZE(top_fixed_clks), top_clk_data); + return r; } static int clk_mt8192_infra_probe(struct platform_device *pdev) @@ -1133,20 +1174,23 @@ static int clk_mt8192_infra_probe(struct platform_device *pdev) if (!clk_data) return -ENOMEM; - r = mtk_clk_register_gates(node, infra_clks, ARRAY_SIZE(infra_clks), clk_data); + r = mtk_clk_register_gates(&pdev->dev, node, infra_clks, + ARRAY_SIZE(infra_clks), clk_data); if (r) goto free_clk_data; r = mtk_register_reset_controller_with_dev(&pdev->dev, &clk_rst_desc); if (r) - goto free_clk_data; + goto unregister_gates; r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) - goto free_clk_data; + goto unregister_gates; return r; +unregister_gates: + mtk_clk_unregister_gates(infra_clks, ARRAY_SIZE(infra_clks), clk_data); free_clk_data: mtk_free_clk_data(clk_data); return r; @@ -1162,16 +1206,19 @@ static int clk_mt8192_peri_probe(struct platform_device *pdev) if (!clk_data) return -ENOMEM; - r = mtk_clk_register_gates(node, peri_clks, ARRAY_SIZE(peri_clks), clk_data); + r = mtk_clk_register_gates(&pdev->dev, node, peri_clks, + ARRAY_SIZE(peri_clks), clk_data); if (r) goto free_clk_data; r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) - goto free_clk_data; + goto unregister_gates; return r; +unregister_gates: + mtk_clk_unregister_gates(peri_clks, ARRAY_SIZE(peri_clks), clk_data); free_clk_data: mtk_free_clk_data(clk_data); return r; @@ -1188,16 +1235,19 @@ static int clk_mt8192_apmixed_probe(struct platform_device *pdev) return -ENOMEM; mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); - r = mtk_clk_register_gates(node, apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); + r = mtk_clk_register_gates(&pdev->dev, node, apmixed_clks, + ARRAY_SIZE(apmixed_clks), clk_data); if (r) goto free_clk_data; r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) - goto free_clk_data; + goto unregister_gates; return r; +unregister_gates: + mtk_clk_unregister_gates(apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); free_clk_data: mtk_free_clk_data(clk_data); return r; diff --git a/drivers/clk/mediatek/clk-mt8195-apmixedsys.c b/drivers/clk/mediatek/clk-mt8195-apmixedsys.c index 0dfed6ec4d15516830526be86fc44e2a3894e9c5..1bc917f2667e485c4ce4b16092f9a9da83447bd3 100644 --- a/drivers/clk/mediatek/clk-mt8195-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8195-apmixedsys.c @@ -124,7 +124,8 @@ static int clk_mt8195_apmixed_probe(struct platform_device *pdev) if (r) goto free_apmixed_data; - r = mtk_clk_register_gates(node, apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); + r = mtk_clk_register_gates(&pdev->dev, node, apmixed_clks, + ARRAY_SIZE(apmixed_clks), clk_data); if (r) goto unregister_plls; diff --git a/drivers/clk/mediatek/clk-mt8195-topckgen.c b/drivers/clk/mediatek/clk-mt8195-topckgen.c index 1e016329c1d23e19e71aa013a525e7978f4fb757..3485ebb17ab830ea82f0b933b7a9418c8121d2e0 100644 --- a/drivers/clk/mediatek/clk-mt8195-topckgen.c +++ b/drivers/clk/mediatek/clk-mt8195-topckgen.c @@ -1262,7 +1262,8 @@ static int clk_mt8195_topck_probe(struct platform_device *pdev) if (r) goto unregister_fixed_clks; - r = mtk_clk_register_muxes(top_mtk_muxes, ARRAY_SIZE(top_mtk_muxes), node, + r = mtk_clk_register_muxes(&pdev->dev, top_mtk_muxes, + ARRAY_SIZE(top_mtk_muxes), node, &mt8195_clk_lock, top_clk_data); if (r) goto unregister_factors; @@ -1281,12 +1282,14 @@ static int clk_mt8195_topck_probe(struct platform_device *pdev) if (r) goto unregister_muxes; - r = mtk_clk_register_composites(top_adj_divs, ARRAY_SIZE(top_adj_divs), base, + r = mtk_clk_register_composites(&pdev->dev, top_adj_divs, + ARRAY_SIZE(top_adj_divs), base, &mt8195_clk_lock, top_clk_data); if (r) goto unregister_muxes; - r = mtk_clk_register_gates(node, top_clks, ARRAY_SIZE(top_clks), top_clk_data); + r = mtk_clk_register_gates(&pdev->dev, node, top_clks, + ARRAY_SIZE(top_clks), top_clk_data); if (r) goto unregister_composite_divs; diff --git a/drivers/clk/mediatek/clk-mt8195-vdo0.c b/drivers/clk/mediatek/clk-mt8195-vdo0.c index 07b46bfd504068ebce7c0c3a158e0f9997400a77..839b730688acbc6d086ee54c40a330f26ef97a28 100644 --- a/drivers/clk/mediatek/clk-mt8195-vdo0.c +++ b/drivers/clk/mediatek/clk-mt8195-vdo0.c @@ -104,7 +104,8 @@ static int clk_mt8195_vdo0_probe(struct platform_device *pdev) if (!clk_data) return -ENOMEM; - r = mtk_clk_register_gates(node, vdo0_clks, ARRAY_SIZE(vdo0_clks), clk_data); + r = mtk_clk_register_gates(&pdev->dev, node, vdo0_clks, + ARRAY_SIZE(vdo0_clks), clk_data); if (r) goto free_vdo0_data; diff --git a/drivers/clk/mediatek/clk-mt8195-vdo1.c b/drivers/clk/mediatek/clk-mt8195-vdo1.c index 835335b9d87bba06a19dcd8c5509fd7dd9535eea..7df695b2892588dfa94ff647823083fa67254a72 100644 --- a/drivers/clk/mediatek/clk-mt8195-vdo1.c +++ b/drivers/clk/mediatek/clk-mt8195-vdo1.c @@ -131,7 +131,8 @@ static int clk_mt8195_vdo1_probe(struct platform_device *pdev) if (!clk_data) return -ENOMEM; - r = mtk_clk_register_gates(node, vdo1_clks, ARRAY_SIZE(vdo1_clks), clk_data); + r = mtk_clk_register_gates(&pdev->dev, node, vdo1_clks, + ARRAY_SIZE(vdo1_clks), clk_data); if (r) goto free_vdo1_data; diff --git a/drivers/clk/mediatek/clk-mt8365-mm.c b/drivers/clk/mediatek/clk-mt8365-mm.c index 5c8bf18ab1f1d0872bebb35009fa8e380919c731..22c75a03a6452dc4c991dc34ba0b98d906524fbb 100644 --- a/drivers/clk/mediatek/clk-mt8365-mm.c +++ b/drivers/clk/mediatek/clk-mt8365-mm.c @@ -81,9 +81,8 @@ static int clk_mt8365_mm_probe(struct platform_device *pdev) clk_data = mtk_alloc_clk_data(CLK_MM_NR_CLK); - ret = mtk_clk_register_gates_with_dev(node, mm_clks, - ARRAY_SIZE(mm_clks), clk_data, - dev); + ret = mtk_clk_register_gates(dev, node, mm_clks, + ARRAY_SIZE(mm_clks), clk_data); if (ret) goto err_free_clk_data; diff --git a/drivers/clk/mediatek/clk-mt8365.c b/drivers/clk/mediatek/clk-mt8365.c index adfecb618f10255cb12483bf36047bf113392928..c9faa07ec0a6403bc3b365dc2c07705fefc68406 100644 --- a/drivers/clk/mediatek/clk-mt8365.c +++ b/drivers/clk/mediatek/clk-mt8365.c @@ -947,12 +947,13 @@ static int clk_mt8365_top_probe(struct platform_device *pdev) if (ret) goto unregister_fixed_clks; - ret = mtk_clk_register_muxes(top_muxes, ARRAY_SIZE(top_muxes), node, + ret = mtk_clk_register_muxes(&pdev->dev, top_muxes, + ARRAY_SIZE(top_muxes), node, &mt8365_clk_lock, clk_data); if (ret) goto unregister_factors; - ret = mtk_clk_register_composites(top_misc_mux_gates, + ret = mtk_clk_register_composites(&pdev->dev, top_misc_mux_gates, ARRAY_SIZE(top_misc_mux_gates), base, &mt8365_clk_lock, clk_data); if (ret) @@ -1019,8 +1020,8 @@ static int clk_mt8365_infra_probe(struct platform_device *pdev) if (!clk_data) return -ENOMEM; - ret = mtk_clk_register_gates(node, ifr_clks, ARRAY_SIZE(ifr_clks), - clk_data); + ret = mtk_clk_register_gates(&pdev->dev, node, ifr_clks, + ARRAY_SIZE(ifr_clks), clk_data); if (ret) goto free_clk_data; @@ -1080,8 +1081,9 @@ static int clk_mt8365_mcu_probe(struct platform_device *pdev) if (!clk_data) return -ENOMEM; - ret = mtk_clk_register_composites(mcu_muxes, ARRAY_SIZE(mcu_muxes), - base, &mt8365_clk_lock, clk_data); + ret = mtk_clk_register_composites(&pdev->dev, mcu_muxes, + ARRAY_SIZE(mcu_muxes), base, + &mt8365_clk_lock, clk_data); if (ret) goto free_clk_data; diff --git a/drivers/clk/mediatek/clk-mt8516-aud.c b/drivers/clk/mediatek/clk-mt8516-aud.c index a3dafc719799c6afddb74501f51b3b4c56111551..a6ae8003b9ff66c3e79e45b59220b8679a722d36 100644 --- a/drivers/clk/mediatek/clk-mt8516-aud.c +++ b/drivers/clk/mediatek/clk-mt8516-aud.c @@ -48,7 +48,7 @@ static void __init mtk_audsys_init(struct device_node *node) clk_data = mtk_alloc_clk_data(CLK_AUD_NR_CLK); - mtk_clk_register_gates(node, aud_clks, ARRAY_SIZE(aud_clks), clk_data); + mtk_clk_register_gates(NULL, node, aud_clks, ARRAY_SIZE(aud_clks), clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) diff --git a/drivers/clk/mediatek/clk-mt8516.c b/drivers/clk/mediatek/clk-mt8516.c index 056953d594c662c7cbe9e2767c0a3a815cf5f141..6983d3a48dc9a385c1983e0b64b9f56a41ad03a5 100644 --- a/drivers/clk/mediatek/clk-mt8516.c +++ b/drivers/clk/mediatek/clk-mt8516.c @@ -655,11 +655,12 @@ static void __init mtk_topckgen_init(struct device_node *node) mtk_clk_register_fixed_clks(fixed_clks, ARRAY_SIZE(fixed_clks), clk_data); - mtk_clk_register_gates(node, top_clks, ARRAY_SIZE(top_clks), clk_data); + mtk_clk_register_gates(NULL, node, top_clks, ARRAY_SIZE(top_clks), clk_data); mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data); - mtk_clk_register_composites(top_muxes, ARRAY_SIZE(top_muxes), base, - &mt8516_clk_lock, clk_data); + mtk_clk_register_composites(NULL, top_muxes, + ARRAY_SIZE(top_muxes), base, + &mt8516_clk_lock, clk_data); mtk_clk_register_dividers(top_adj_divs, ARRAY_SIZE(top_adj_divs), base, &mt8516_clk_lock, clk_data); @@ -684,8 +685,9 @@ static void __init mtk_infracfg_init(struct device_node *node) clk_data = mtk_alloc_clk_data(CLK_IFR_NR_CLK); - mtk_clk_register_composites(ifr_muxes, ARRAY_SIZE(ifr_muxes), base, - &mt8516_clk_lock, clk_data); + mtk_clk_register_composites(NULL, ifr_muxes, + ARRAY_SIZE(ifr_muxes), base, + &mt8516_clk_lock, clk_data); r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) diff --git a/drivers/clk/mediatek/clk-mtk.c b/drivers/clk/mediatek/clk-mtk.c index d31f01d0ba1c23c19c964aea19f7a49eaba14680..fa2c1b1c7dee4eee9015c2826aff3ef37a43bda4 100644 --- a/drivers/clk/mediatek/clk-mtk.c +++ b/drivers/clk/mediatek/clk-mtk.c @@ -11,12 +11,15 @@ #include #include #include +#include #include #include +#include #include #include "clk-mtk.h" #include "clk-gate.h" +#include "clk-mux.h" static void mtk_init_clk_data(struct clk_hw_onecell_data *clk_data, unsigned int clk_num) @@ -197,8 +200,8 @@ void mtk_clk_unregister_factors(const struct mtk_fixed_factor *clks, int num, } EXPORT_SYMBOL_GPL(mtk_clk_unregister_factors); -static struct clk_hw *mtk_clk_register_composite(const struct mtk_composite *mc, - void __iomem *base, spinlock_t *lock) +static struct clk_hw *mtk_clk_register_composite(struct device *dev, + const struct mtk_composite *mc, void __iomem *base, spinlock_t *lock) { struct clk_hw *hw; struct clk_mux *mux = NULL; @@ -264,7 +267,7 @@ static struct clk_hw *mtk_clk_register_composite(const struct mtk_composite *mc, div_ops = &clk_divider_ops; } - hw = clk_hw_register_composite(NULL, mc->name, parent_names, num_parents, + hw = clk_hw_register_composite(dev, mc->name, parent_names, num_parents, mux_hw, mux_ops, div_hw, div_ops, gate_hw, gate_ops, @@ -308,7 +311,8 @@ static void mtk_clk_unregister_composite(struct clk_hw *hw) kfree(mux); } -int mtk_clk_register_composites(const struct mtk_composite *mcs, int num, +int mtk_clk_register_composites(struct device *dev, + const struct mtk_composite *mcs, int num, void __iomem *base, spinlock_t *lock, struct clk_hw_onecell_data *clk_data) { @@ -327,7 +331,7 @@ int mtk_clk_register_composites(const struct mtk_composite *mcs, int num, continue; } - hw = mtk_clk_register_composite(mc, base, lock); + hw = mtk_clk_register_composite(dev, mc, base, lock); if (IS_ERR(hw)) { pr_err("Failed to register clk %s: %pe\n", mc->name, @@ -449,20 +453,81 @@ int mtk_clk_simple_probe(struct platform_device *pdev) const struct mtk_clk_desc *mcd; struct clk_hw_onecell_data *clk_data; struct device_node *node = pdev->dev.of_node; - int r; + void __iomem *base; + int num_clks, r; mcd = of_device_get_match_data(&pdev->dev); if (!mcd) return -EINVAL; - clk_data = mtk_alloc_clk_data(mcd->num_clks); + /* Composite clocks needs us to pass iomem pointer */ + if (mcd->composite_clks) { + if (!mcd->shared_io) + base = devm_platform_ioremap_resource(pdev, 0); + else + base = of_iomap(node, 0); + + if (IS_ERR_OR_NULL(base)) + return IS_ERR(base) ? PTR_ERR(base) : -ENOMEM; + } + + + devm_pm_runtime_enable(&pdev->dev); + /* + * Do a pm_runtime_resume_and_get() to workaround a possible + * deadlock between clk_register() and the genpd framework. + */ + r = pm_runtime_resume_and_get(&pdev->dev); + if (r) + return r; + + /* Calculate how many clk_hw_onecell_data entries to allocate */ + num_clks = mcd->num_clks + mcd->num_composite_clks; + num_clks += mcd->num_fixed_clks + mcd->num_factor_clks; + num_clks += mcd->num_mux_clks; + + clk_data = mtk_alloc_clk_data(num_clks); if (!clk_data) return -ENOMEM; - r = mtk_clk_register_gates_with_dev(node, mcd->clks, mcd->num_clks, - clk_data, &pdev->dev); - if (r) - goto free_data; + if (mcd->fixed_clks) { + r = mtk_clk_register_fixed_clks(mcd->fixed_clks, + mcd->num_fixed_clks, clk_data); + if (r) + goto free_data; + } + + if (mcd->factor_clks) { + r = mtk_clk_register_factors(mcd->factor_clks, + mcd->num_factor_clks, clk_data); + if (r) + goto unregister_fixed_clks; + } + + if (mcd->mux_clks) { + r = mtk_clk_register_muxes(&pdev->dev, mcd->mux_clks, + mcd->num_mux_clks, node, + mcd->clk_lock, clk_data); + if (r) + goto unregister_factors; + }; + + if (mcd->composite_clks) { + /* We don't check composite_lock because it's optional */ + r = mtk_clk_register_composites(&pdev->dev, + mcd->composite_clks, + mcd->num_composite_clks, + base, mcd->clk_lock, clk_data); + if (r) + goto unregister_muxes; + } + + if (mcd->clks) { + r = mtk_clk_register_gates(&pdev->dev, node, mcd->clks, + mcd->num_clks, clk_data); + if (r) + goto unregister_composites; + } r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) @@ -477,12 +542,35 @@ int mtk_clk_simple_probe(struct platform_device *pdev) goto unregister_clks; } + pm_runtime_put(&pdev->dev); + return r; unregister_clks: - mtk_clk_unregister_gates(mcd->clks, mcd->num_clks, clk_data); + if (mcd->clks) + mtk_clk_unregister_gates(mcd->clks, mcd->num_clks, clk_data); +unregister_composites: + if (mcd->composite_clks) + mtk_clk_unregister_composites(mcd->composite_clks, + mcd->num_composite_clks, clk_data); +unregister_muxes: + if (mcd->mux_clks) + mtk_clk_unregister_muxes(mcd->mux_clks, + mcd->num_mux_clks, clk_data); +unregister_factors: + if (mcd->factor_clks) + mtk_clk_unregister_factors(mcd->factor_clks, + mcd->num_factor_clks, clk_data); +unregister_fixed_clks: + if (mcd->fixed_clks) + mtk_clk_unregister_fixed_clks(mcd->fixed_clks, + mcd->num_fixed_clks, clk_data); free_data: mtk_free_clk_data(clk_data); + if (mcd->shared_io && base) + iounmap(base); + + pm_runtime_put(&pdev->dev); return r; } EXPORT_SYMBOL_GPL(mtk_clk_simple_probe); @@ -494,7 +582,20 @@ int mtk_clk_simple_remove(struct platform_device *pdev) struct device_node *node = pdev->dev.of_node; of_clk_del_provider(node); - mtk_clk_unregister_gates(mcd->clks, mcd->num_clks, clk_data); + if (mcd->clks) + mtk_clk_unregister_gates(mcd->clks, mcd->num_clks, clk_data); + if (mcd->composite_clks) + mtk_clk_unregister_composites(mcd->composite_clks, + mcd->num_composite_clks, clk_data); + if (mcd->mux_clks) + mtk_clk_unregister_muxes(mcd->mux_clks, + mcd->num_mux_clks, clk_data); + if (mcd->factor_clks) + mtk_clk_unregister_factors(mcd->factor_clks, + mcd->num_factor_clks, clk_data); + if (mcd->fixed_clks) + mtk_clk_unregister_fixed_clks(mcd->fixed_clks, + mcd->num_fixed_clks, clk_data); mtk_free_clk_data(clk_data); return 0; diff --git a/drivers/clk/mediatek/clk-mtk.h b/drivers/clk/mediatek/clk-mtk.h index 63ae7941aa92f10c03483f288ab352aed44637ee..880b3d6d8011906f7cdc9b2511bf7f8c7269027c 100644 --- a/drivers/clk/mediatek/clk-mtk.h +++ b/drivers/clk/mediatek/clk-mtk.h @@ -149,7 +149,8 @@ struct mtk_composite { .flags = 0, \ } -int mtk_clk_register_composites(const struct mtk_composite *mcs, int num, +int mtk_clk_register_composites(struct device *dev, + const struct mtk_composite *mcs, int num, void __iomem *base, spinlock_t *lock, struct clk_hw_onecell_data *clk_data); void mtk_clk_unregister_composites(const struct mtk_composite *mcs, int num, @@ -195,7 +196,17 @@ void mtk_clk_unregister_ref2usb_tx(struct clk_hw *hw); struct mtk_clk_desc { const struct mtk_gate *clks; size_t num_clks; + const struct mtk_composite *composite_clks; + size_t num_composite_clks; + const struct mtk_fixed_clk *fixed_clks; + size_t num_fixed_clks; + const struct mtk_fixed_factor *factor_clks; + size_t num_factor_clks; + const struct mtk_mux *mux_clks; + size_t num_mux_clks; const struct mtk_clk_rst_desc *rst_desc; + spinlock_t *clk_lock; + bool shared_io; }; int mtk_clk_simple_probe(struct platform_device *pdev); diff --git a/drivers/clk/mediatek/clk-mux.c b/drivers/clk/mediatek/clk-mux.c index ba1720b9e23101929a54b4c09955f0ec93d52342..c8593554239d6e9da6612161a9479291f2e2b884 100644 --- a/drivers/clk/mediatek/clk-mux.c +++ b/drivers/clk/mediatek/clk-mux.c @@ -154,9 +154,10 @@ const struct clk_ops mtk_mux_gate_clr_set_upd_ops = { }; EXPORT_SYMBOL_GPL(mtk_mux_gate_clr_set_upd_ops); -static struct clk_hw *mtk_clk_register_mux(const struct mtk_mux *mux, - struct regmap *regmap, - spinlock_t *lock) +static struct clk_hw *mtk_clk_register_mux(struct device *dev, + const struct mtk_mux *mux, + struct regmap *regmap, + spinlock_t *lock) { struct mtk_clk_mux *clk_mux; struct clk_init_data init = {}; @@ -177,7 +178,7 @@ static struct clk_hw *mtk_clk_register_mux(const struct mtk_mux *mux, clk_mux->lock = lock; clk_mux->hw.init = &init; - ret = clk_hw_register(NULL, &clk_mux->hw); + ret = clk_hw_register(dev, &clk_mux->hw); if (ret) { kfree(clk_mux); return ERR_PTR(ret); @@ -198,7 +199,8 @@ static void mtk_clk_unregister_mux(struct clk_hw *hw) kfree(mux); } -int mtk_clk_register_muxes(const struct mtk_mux *muxes, +int mtk_clk_register_muxes(struct device *dev, + const struct mtk_mux *muxes, int num, struct device_node *node, spinlock_t *lock, struct clk_hw_onecell_data *clk_data) @@ -222,7 +224,7 @@ int mtk_clk_register_muxes(const struct mtk_mux *muxes, continue; } - hw = mtk_clk_register_mux(mux, regmap, lock); + hw = mtk_clk_register_mux(dev, mux, regmap, lock); if (IS_ERR(hw)) { pr_err("Failed to register clk %s: %pe\n", mux->name, diff --git a/drivers/clk/mediatek/clk-mux.h b/drivers/clk/mediatek/clk-mux.h index 83ff420f4ebe6f49627018f6f616a820d6c7b7af..7ecb963b0ec6880e52466248e1832eb25d9eef41 100644 --- a/drivers/clk/mediatek/clk-mux.h +++ b/drivers/clk/mediatek/clk-mux.h @@ -83,7 +83,8 @@ extern const struct clk_ops mtk_mux_gate_clr_set_upd_ops; 0, _upd_ofs, _upd, CLK_SET_RATE_PARENT, \ mtk_mux_clr_set_upd_ops) -int mtk_clk_register_muxes(const struct mtk_mux *muxes, +int mtk_clk_register_muxes(struct device *dev, + const struct mtk_mux *muxes, int num, struct device_node *node, spinlock_t *lock, struct clk_hw_onecell_data *clk_data); diff --git a/drivers/clk/meson/axg.c b/drivers/clk/meson/axg.c index 2ad3801398dc114d660be253f1cb98dbf9f9f3be..7802dabb26f6d0fad078b05c6deaf7baec3a11b1 100644 --- a/drivers/clk/meson/axg.c +++ b/drivers/clk/meson/axg.c @@ -2144,7 +2144,9 @@ static struct clk_regmap *const axg_clk_regmaps[] = { &axg_vclk_input, &axg_vclk2_input, &axg_vclk_div, + &axg_vclk_div1, &axg_vclk2_div, + &axg_vclk2_div1, &axg_vclk_div2_en, &axg_vclk_div4_en, &axg_vclk_div6_en, diff --git a/drivers/clk/qcom/dispcc-sdm845.c b/drivers/clk/qcom/dispcc-sdm845.c index 735adfefc37983b0929b2133b6ff5235a53a68d4..e792e0b130d33320b1029f6f1e9895e08d350d18 100644 --- a/drivers/clk/qcom/dispcc-sdm845.c +++ b/drivers/clk/qcom/dispcc-sdm845.c @@ -759,6 +759,8 @@ static struct clk_branch disp_cc_mdss_vsync_clk = { static struct gdsc mdss_gdsc = { .gdscr = 0x3000, + .en_few_wait_val = 0x6, + .en_rest_wait_val = 0x5, .pd = { .name = "mdss_gdsc", }, diff --git a/drivers/clk/qcom/gcc-ipq6018.c b/drivers/clk/qcom/gcc-ipq6018.c index 4c5c7a8f41d0846fae7642e8033d32fe96a08bf1..b9844e41cf99d3ef67ee814f9e0be65fd24bd14b 100644 --- a/drivers/clk/qcom/gcc-ipq6018.c +++ b/drivers/clk/qcom/gcc-ipq6018.c @@ -1557,6 +1557,7 @@ static struct clk_regmap_div nss_ubi0_div_clk_src = { static const struct freq_tbl ftbl_pcie_aux_clk_src[] = { F(24000000, P_XO, 1, 0, 0), + { } }; static const struct clk_parent_data gcc_xo_gpll0_core_pi_sleep_clk[] = { @@ -1737,6 +1738,7 @@ static const struct freq_tbl ftbl_sdcc_ice_core_clk_src[] = { F(160000000, P_GPLL0, 5, 0, 0), F(216000000, P_GPLL6, 5, 0, 0), F(308570000, P_GPLL6, 3.5, 0, 0), + { } }; static const struct clk_parent_data gcc_xo_gpll0_gpll6_gpll0_div2[] = { diff --git a/drivers/clk/qcom/gcc-ipq8074.c b/drivers/clk/qcom/gcc-ipq8074.c index b2e83b38976e51daf481c4b4ac4a92b674f0f7c1..b52c923a2fbca770ddb0b65655e09f02d2271704 100644 --- a/drivers/clk/qcom/gcc-ipq8074.c +++ b/drivers/clk/qcom/gcc-ipq8074.c @@ -973,6 +973,7 @@ static struct clk_rcg2 pcie0_axi_clk_src = { static const struct freq_tbl ftbl_pcie_aux_clk_src[] = { F(19200000, P_XO, 1, 0, 0), + { } }; static struct clk_rcg2 pcie0_aux_clk_src = { @@ -1078,6 +1079,7 @@ static const struct freq_tbl ftbl_sdcc_ice_core_clk_src[] = { F(19200000, P_XO, 1, 0, 0), F(160000000, P_GPLL0, 5, 0, 0), F(308570000, P_GPLL6, 3.5, 0, 0), + { } }; static struct clk_rcg2 sdcc1_ice_core_clk_src = { diff --git a/drivers/clk/qcom/gcc-sdm845.c b/drivers/clk/qcom/gcc-sdm845.c index 6af08e0ca847569963c703ce03b3a0e6bd7bd74b..ef15e8f114027b046b78afb67666835f99e5e307 100644 --- a/drivers/clk/qcom/gcc-sdm845.c +++ b/drivers/clk/qcom/gcc-sdm845.c @@ -4038,3 +4038,4 @@ module_exit(gcc_sdm845_exit); MODULE_DESCRIPTION("QTI GCC SDM845 Driver"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("platform:gcc-sdm845"); +MODULE_SOFTDEP("pre: rpmhpd"); diff --git a/drivers/clk/qcom/mmcc-apq8084.c b/drivers/clk/qcom/mmcc-apq8084.c index e9f971359155879f9b108629c6c87c2171355bf9..5f373c10ec6ee3d682f019a6b97a110b39f0e56a 100644 --- a/drivers/clk/qcom/mmcc-apq8084.c +++ b/drivers/clk/qcom/mmcc-apq8084.c @@ -334,6 +334,7 @@ static struct freq_tbl ftbl_mmss_axi_clk[] = { F(333430000, P_MMPLL1, 3.5, 0, 0), F(400000000, P_MMPLL0, 2, 0, 0), F(466800000, P_MMPLL1, 2.5, 0, 0), + { } }; static struct clk_rcg2 mmss_axi_clk_src = { @@ -358,6 +359,7 @@ static struct freq_tbl ftbl_ocmemnoc_clk[] = { F(150000000, P_GPLL0, 4, 0, 0), F(228570000, P_MMPLL0, 3.5, 0, 0), F(320000000, P_MMPLL0, 2.5, 0, 0), + { } }; static struct clk_rcg2 ocmemnoc_clk_src = { diff --git a/drivers/clk/qcom/mmcc-msm8974.c b/drivers/clk/qcom/mmcc-msm8974.c index 17ed52046170af4a348f96d20465cdeca26a42eb..eb2b0e2200d232c037da509911bfba1065d738cc 100644 --- a/drivers/clk/qcom/mmcc-msm8974.c +++ b/drivers/clk/qcom/mmcc-msm8974.c @@ -279,6 +279,7 @@ static struct freq_tbl ftbl_mmss_axi_clk[] = { F(291750000, P_MMPLL1, 4, 0, 0), F(400000000, P_MMPLL0, 2, 0, 0), F(466800000, P_MMPLL1, 2.5, 0, 0), + { } }; static struct clk_rcg2 mmss_axi_clk_src = { @@ -303,6 +304,7 @@ static struct freq_tbl ftbl_ocmemnoc_clk[] = { F(150000000, P_GPLL0, 4, 0, 0), F(291750000, P_MMPLL1, 4, 0, 0), F(400000000, P_MMPLL0, 2, 0, 0), + { } }; static struct clk_rcg2 ocmemnoc_clk_src = { diff --git a/drivers/clk/qcom/reset.c b/drivers/clk/qcom/reset.c index e45e32804d2c75aa5e5a1bf11be76e3d422b140b..d96c96a9089f40b3a111067434d4d19632505a16 100644 --- a/drivers/clk/qcom/reset.c +++ b/drivers/clk/qcom/reset.c @@ -22,8 +22,8 @@ static int qcom_reset(struct reset_controller_dev *rcdev, unsigned long id) return 0; } -static int -qcom_reset_assert(struct reset_controller_dev *rcdev, unsigned long id) +static int qcom_reset_set_assert(struct reset_controller_dev *rcdev, + unsigned long id, bool assert) { struct qcom_reset_controller *rst; const struct qcom_reset_map *map; @@ -33,21 +33,22 @@ qcom_reset_assert(struct reset_controller_dev *rcdev, unsigned long id) map = &rst->reset_map[id]; mask = map->bitmask ? map->bitmask : BIT(map->bit); - return regmap_update_bits(rst->regmap, map->reg, mask, mask); + regmap_update_bits(rst->regmap, map->reg, mask, assert ? mask : 0); + + /* Read back the register to ensure write completion, ignore the value */ + regmap_read(rst->regmap, map->reg, &mask); + + return 0; } -static int -qcom_reset_deassert(struct reset_controller_dev *rcdev, unsigned long id) +static int qcom_reset_assert(struct reset_controller_dev *rcdev, unsigned long id) { - struct qcom_reset_controller *rst; - const struct qcom_reset_map *map; - u32 mask; - - rst = to_qcom_reset_controller(rcdev); - map = &rst->reset_map[id]; - mask = map->bitmask ? map->bitmask : BIT(map->bit); + return qcom_reset_set_assert(rcdev, id, true); +} - return regmap_update_bits(rst->regmap, map->reg, mask, 0); +static int qcom_reset_deassert(struct reset_controller_dev *rcdev, unsigned long id) +{ + return qcom_reset_set_assert(rcdev, id, false); } const struct reset_control_ops qcom_reset_ops = { diff --git a/drivers/clk/renesas/r8a779f0-cpg-mssr.c b/drivers/clk/renesas/r8a779f0-cpg-mssr.c index 27b668def357fa44d753650b8522c6d6621b0789..7a49b91c93710502d1ed2189e182940824f3fce8 100644 --- a/drivers/clk/renesas/r8a779f0-cpg-mssr.c +++ b/drivers/clk/renesas/r8a779f0-cpg-mssr.c @@ -159,7 +159,7 @@ static const struct mssr_mod_clk r8a779f0_mod_clks[] __initconst = { DEF_MOD("cmt1", 911, R8A779F0_CLK_R), DEF_MOD("cmt2", 912, R8A779F0_CLK_R), DEF_MOD("cmt3", 913, R8A779F0_CLK_R), - DEF_MOD("pfc0", 915, R8A779F0_CLK_CL16M), + DEF_MOD("pfc0", 915, R8A779F0_CLK_CPEX), DEF_MOD("tsc", 919, R8A779F0_CLK_CL16M), DEF_MOD("ufs", 1514, R8A779F0_CLK_S0D4_HSC), }; diff --git a/drivers/clk/renesas/r8a779g0-cpg-mssr.c b/drivers/clk/renesas/r8a779g0-cpg-mssr.c index d5b325e3c53983d4915db390ac3c8ac0017bffe9..e4c616921e5ea3591ec082ce4d730e3e718703db 100644 --- a/drivers/clk/renesas/r8a779g0-cpg-mssr.c +++ b/drivers/clk/renesas/r8a779g0-cpg-mssr.c @@ -22,7 +22,7 @@ enum clk_ids { /* Core Clock Outputs exported to DT */ - LAST_DT_CORE_CLK = R8A779G0_CLK_R, + LAST_DT_CORE_CLK = R8A779G0_CLK_CP, /* External Input Clocks */ CLK_EXTAL, @@ -139,6 +139,7 @@ static const struct cpg_core_clk r8a779g0_core_clks[] __initconst = { DEF_FIXED("svd2_vip", R8A779G0_CLK_SVD2_VIP, CLK_SV_VIP, 2, 1), DEF_FIXED("cbfusa", R8A779G0_CLK_CBFUSA, CLK_EXTAL, 2, 1), DEF_FIXED("cpex", R8A779G0_CLK_CPEX, CLK_EXTAL, 2, 1), + DEF_FIXED("cp", R8A779G0_CLK_CP, CLK_EXTAL, 2, 1), DEF_FIXED("viobus", R8A779G0_CLK_VIOBUS, CLK_VIO, 1, 1), DEF_FIXED("viobusd2", R8A779G0_CLK_VIOBUSD2, CLK_VIO, 2, 1), DEF_FIXED("vcbus", R8A779G0_CLK_VCBUS, CLK_VC, 1, 1), @@ -169,10 +170,17 @@ static const struct mssr_mod_clk r8a779g0_mod_clks[] __initconst = { DEF_MOD("i2c4", 522, R8A779G0_CLK_S0D6_PER), DEF_MOD("i2c5", 523, R8A779G0_CLK_S0D6_PER), DEF_MOD("wdt1:wdt0", 907, R8A779G0_CLK_R), - DEF_MOD("pfc0", 915, R8A779G0_CLK_CL16M), - DEF_MOD("pfc1", 916, R8A779G0_CLK_CL16M), - DEF_MOD("pfc2", 917, R8A779G0_CLK_CL16M), - DEF_MOD("pfc3", 918, R8A779G0_CLK_CL16M), + DEF_MOD("cmt0", 910, R8A779G0_CLK_R), + DEF_MOD("cmt1", 911, R8A779G0_CLK_R), + DEF_MOD("cmt2", 912, R8A779G0_CLK_R), + DEF_MOD("cmt3", 913, R8A779G0_CLK_R), + DEF_MOD("pfc0", 915, R8A779G0_CLK_CP), + DEF_MOD("pfc1", 916, R8A779G0_CLK_CP), + DEF_MOD("pfc2", 917, R8A779G0_CLK_CP), + DEF_MOD("pfc3", 918, R8A779G0_CLK_CP), + DEF_MOD("tsc", 919, R8A779G0_CLK_CL16M), + DEF_MOD("ssiu", 2926, R8A779G0_CLK_S0D6_PER), + DEF_MOD("ssi", 2927, R8A779G0_CLK_S0D6_PER), }; /* diff --git a/drivers/clk/samsung/clk-exynos850.c b/drivers/clk/samsung/clk-exynos850.c index 541761e96aeb677d2abebfd86ef079ead45b15d1..87e463ad427414fc16a0b64444f9882679ed22b9 100644 --- a/drivers/clk/samsung/clk-exynos850.c +++ b/drivers/clk/samsung/clk-exynos850.c @@ -572,7 +572,7 @@ static const struct samsung_div_clock apm_div_clks[] __initconst = { static const struct samsung_gate_clock apm_gate_clks[] __initconst = { GATE(CLK_GOUT_CLKCMU_CMGP_BUS, "gout_clkcmu_cmgp_bus", "dout_apm_bus", - CLK_CON_GAT_CLKCMU_CMGP_BUS, 21, 0, 0), + CLK_CON_GAT_CLKCMU_CMGP_BUS, 21, CLK_SET_RATE_PARENT, 0), GATE(CLK_GOUT_CLKCMU_CHUB_BUS, "gout_clkcmu_chub_bus", "mout_clkcmu_chub_bus", CLK_CON_GAT_GATE_CLKCMU_CHUB_BUS, 21, 0, 0), @@ -936,19 +936,19 @@ static const struct samsung_fixed_rate_clock cmgp_fixed_clks[] __initconst = { static const struct samsung_mux_clock cmgp_mux_clks[] __initconst = { MUX(CLK_MOUT_CMGP_ADC, "mout_cmgp_adc", mout_cmgp_adc_p, CLK_CON_MUX_CLK_CMGP_ADC, 0, 1), - MUX(CLK_MOUT_CMGP_USI0, "mout_cmgp_usi0", mout_cmgp_usi0_p, - CLK_CON_MUX_MUX_CLK_CMGP_USI_CMGP0, 0, 1), - MUX(CLK_MOUT_CMGP_USI1, "mout_cmgp_usi1", mout_cmgp_usi1_p, - CLK_CON_MUX_MUX_CLK_CMGP_USI_CMGP1, 0, 1), + MUX_F(CLK_MOUT_CMGP_USI0, "mout_cmgp_usi0", mout_cmgp_usi0_p, + CLK_CON_MUX_MUX_CLK_CMGP_USI_CMGP0, 0, 1, CLK_SET_RATE_PARENT, 0), + MUX_F(CLK_MOUT_CMGP_USI1, "mout_cmgp_usi1", mout_cmgp_usi1_p, + CLK_CON_MUX_MUX_CLK_CMGP_USI_CMGP1, 0, 1, CLK_SET_RATE_PARENT, 0), }; static const struct samsung_div_clock cmgp_div_clks[] __initconst = { DIV(CLK_DOUT_CMGP_ADC, "dout_cmgp_adc", "gout_clkcmu_cmgp_bus", CLK_CON_DIV_DIV_CLK_CMGP_ADC, 0, 4), - DIV(CLK_DOUT_CMGP_USI0, "dout_cmgp_usi0", "mout_cmgp_usi0", - CLK_CON_DIV_DIV_CLK_CMGP_USI_CMGP0, 0, 5), - DIV(CLK_DOUT_CMGP_USI1, "dout_cmgp_usi1", "mout_cmgp_usi1", - CLK_CON_DIV_DIV_CLK_CMGP_USI_CMGP1, 0, 5), + DIV_F(CLK_DOUT_CMGP_USI0, "dout_cmgp_usi0", "mout_cmgp_usi0", + CLK_CON_DIV_DIV_CLK_CMGP_USI_CMGP0, 0, 5, CLK_SET_RATE_PARENT, 0), + DIV_F(CLK_DOUT_CMGP_USI1, "dout_cmgp_usi1", "mout_cmgp_usi1", + CLK_CON_DIV_DIV_CLK_CMGP_USI_CMGP1, 0, 5, CLK_SET_RATE_PARENT, 0), }; static const struct samsung_gate_clock cmgp_gate_clks[] __initconst = { @@ -963,12 +963,12 @@ static const struct samsung_gate_clock cmgp_gate_clks[] __initconst = { "gout_clkcmu_cmgp_bus", CLK_CON_GAT_GOUT_CMGP_GPIO_PCLK, 21, CLK_IGNORE_UNUSED, 0), GATE(CLK_GOUT_CMGP_USI0_IPCLK, "gout_cmgp_usi0_ipclk", "dout_cmgp_usi0", - CLK_CON_GAT_GOUT_CMGP_USI_CMGP0_IPCLK, 21, 0, 0), + CLK_CON_GAT_GOUT_CMGP_USI_CMGP0_IPCLK, 21, CLK_SET_RATE_PARENT, 0), GATE(CLK_GOUT_CMGP_USI0_PCLK, "gout_cmgp_usi0_pclk", "gout_clkcmu_cmgp_bus", CLK_CON_GAT_GOUT_CMGP_USI_CMGP0_PCLK, 21, 0, 0), GATE(CLK_GOUT_CMGP_USI1_IPCLK, "gout_cmgp_usi1_ipclk", "dout_cmgp_usi1", - CLK_CON_GAT_GOUT_CMGP_USI_CMGP1_IPCLK, 21, 0, 0), + CLK_CON_GAT_GOUT_CMGP_USI_CMGP1_IPCLK, 21, CLK_SET_RATE_PARENT, 0), GATE(CLK_GOUT_CMGP_USI1_PCLK, "gout_cmgp_usi1_pclk", "gout_clkcmu_cmgp_bus", CLK_CON_GAT_GOUT_CMGP_USI_CMGP1_PCLK, 21, 0, 0), @@ -1409,8 +1409,9 @@ static const struct samsung_mux_clock peri_mux_clks[] __initconst = { mout_peri_uart_user_p, PLL_CON0_MUX_CLKCMU_PERI_UART_USER, 4, 1), MUX(CLK_MOUT_PERI_HSI2C_USER, "mout_peri_hsi2c_user", mout_peri_hsi2c_user_p, PLL_CON0_MUX_CLKCMU_PERI_HSI2C_USER, 4, 1), - MUX(CLK_MOUT_PERI_SPI_USER, "mout_peri_spi_user", mout_peri_spi_user_p, - PLL_CON0_MUX_CLKCMU_PERI_SPI_USER, 4, 1), + MUX_F(CLK_MOUT_PERI_SPI_USER, "mout_peri_spi_user", + mout_peri_spi_user_p, PLL_CON0_MUX_CLKCMU_PERI_SPI_USER, 4, 1, + CLK_SET_RATE_PARENT, 0), }; static const struct samsung_div_clock peri_div_clks[] __initconst = { @@ -1420,8 +1421,8 @@ static const struct samsung_div_clock peri_div_clks[] __initconst = { CLK_CON_DIV_DIV_CLK_PERI_HSI2C_1, 0, 5), DIV(CLK_DOUT_PERI_HSI2C2, "dout_peri_hsi2c2", "gout_peri_hsi2c2", CLK_CON_DIV_DIV_CLK_PERI_HSI2C_2, 0, 5), - DIV(CLK_DOUT_PERI_SPI0, "dout_peri_spi0", "mout_peri_spi_user", - CLK_CON_DIV_DIV_CLK_PERI_SPI_0, 0, 5), + DIV_F(CLK_DOUT_PERI_SPI0, "dout_peri_spi0", "mout_peri_spi_user", + CLK_CON_DIV_DIV_CLK_PERI_SPI_0, 0, 5, CLK_SET_RATE_PARENT, 0), }; static const struct samsung_gate_clock peri_gate_clks[] __initconst = { @@ -1463,7 +1464,7 @@ static const struct samsung_gate_clock peri_gate_clks[] __initconst = { "mout_peri_bus_user", CLK_CON_GAT_GOUT_PERI_PWM_MOTOR_PCLK, 21, 0, 0), GATE(CLK_GOUT_SPI0_IPCLK, "gout_spi0_ipclk", "dout_peri_spi0", - CLK_CON_GAT_GOUT_PERI_SPI_0_IPCLK, 21, 0, 0), + CLK_CON_GAT_GOUT_PERI_SPI_0_IPCLK, 21, CLK_SET_RATE_PARENT, 0), GATE(CLK_GOUT_SPI0_PCLK, "gout_spi0_pclk", "mout_peri_bus_user", CLK_CON_GAT_GOUT_PERI_SPI_0_PCLK, 21, 0, 0), GATE(CLK_GOUT_SYSREG_PERI_PCLK, "gout_sysreg_peri_pclk", diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-h6.c b/drivers/clk/sunxi-ng/ccu-sun50i-h6.c index 42568c6161814dc797079d1ee224bc7a2e6847a8..892df807275c8e57b1b53112faece02a47f22f6e 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-h6.c +++ b/drivers/clk/sunxi-ng/ccu-sun50i-h6.c @@ -1181,11 +1181,18 @@ static const u32 usb2_clk_regs[] = { SUN50I_H6_USB3_CLK_REG, }; +static struct ccu_mux_nb sun50i_h6_cpu_nb = { + .common = &cpux_clk.common, + .cm = &cpux_clk.mux, + .delay_us = 1, + .bypass_index = 0, /* index of 24 MHz oscillator */ +}; + static int sun50i_h6_ccu_probe(struct platform_device *pdev) { void __iomem *reg; + int i, ret; u32 val; - int i; reg = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(reg)) @@ -1252,7 +1259,15 @@ static int sun50i_h6_ccu_probe(struct platform_device *pdev) val |= BIT(24); writel(val, reg + SUN50I_H6_HDMI_CEC_CLK_REG); - return devm_sunxi_ccu_probe(&pdev->dev, reg, &sun50i_h6_ccu_desc); + ret = devm_sunxi_ccu_probe(&pdev->dev, reg, &sun50i_h6_ccu_desc); + if (ret) + return ret; + + /* Reparent CPU during PLL CPUX rate changes */ + ccu_mux_notifier_register(pll_cpux_clk.common.hw.clk, + &sun50i_h6_cpu_nb); + + return 0; } static const struct of_device_id sun50i_h6_ccu_ids[] = { diff --git a/drivers/clk/tegra/clk-tegra20.c b/drivers/clk/tegra/clk-tegra20.c index 422d782475532b3362cdd5f42664dd53298763b5..dcacc5064d339dc79a41784c3f162aaae56b8165 100644 --- a/drivers/clk/tegra/clk-tegra20.c +++ b/drivers/clk/tegra/clk-tegra20.c @@ -21,24 +21,24 @@ #define MISC_CLK_ENB 0x48 #define OSC_CTRL 0x50 -#define OSC_CTRL_OSC_FREQ_MASK (3<<30) -#define OSC_CTRL_OSC_FREQ_13MHZ (0<<30) -#define OSC_CTRL_OSC_FREQ_19_2MHZ (1<<30) -#define OSC_CTRL_OSC_FREQ_12MHZ (2<<30) -#define OSC_CTRL_OSC_FREQ_26MHZ (3<<30) -#define OSC_CTRL_MASK (0x3f2 | OSC_CTRL_OSC_FREQ_MASK) - -#define OSC_CTRL_PLL_REF_DIV_MASK (3<<28) -#define OSC_CTRL_PLL_REF_DIV_1 (0<<28) -#define OSC_CTRL_PLL_REF_DIV_2 (1<<28) -#define OSC_CTRL_PLL_REF_DIV_4 (2<<28) +#define OSC_CTRL_OSC_FREQ_MASK (3u<<30) +#define OSC_CTRL_OSC_FREQ_13MHZ (0u<<30) +#define OSC_CTRL_OSC_FREQ_19_2MHZ (1u<<30) +#define OSC_CTRL_OSC_FREQ_12MHZ (2u<<30) +#define OSC_CTRL_OSC_FREQ_26MHZ (3u<<30) +#define OSC_CTRL_MASK (0x3f2u | OSC_CTRL_OSC_FREQ_MASK) + +#define OSC_CTRL_PLL_REF_DIV_MASK (3u<<28) +#define OSC_CTRL_PLL_REF_DIV_1 (0u<<28) +#define OSC_CTRL_PLL_REF_DIV_2 (1u<<28) +#define OSC_CTRL_PLL_REF_DIV_4 (2u<<28) #define OSC_FREQ_DET 0x58 -#define OSC_FREQ_DET_TRIG (1<<31) +#define OSC_FREQ_DET_TRIG (1u<<31) #define OSC_FREQ_DET_STATUS 0x5c -#define OSC_FREQ_DET_BUSY (1<<31) -#define OSC_FREQ_DET_CNT_MASK 0xFFFF +#define OSC_FREQ_DET_BUSYu (1<<31) +#define OSC_FREQ_DET_CNT_MASK 0xFFFFu #define TEGRA20_CLK_PERIPH_BANKS 3 diff --git a/drivers/clk/zynq/clkc.c b/drivers/clk/zynq/clkc.c index 7bdeaff2bfd68b00a25e6cd9ef4f0623a8b2cc9a..c28d3dacf0fb22c6e2586caf2201564afb56cd7b 100644 --- a/drivers/clk/zynq/clkc.c +++ b/drivers/clk/zynq/clkc.c @@ -42,6 +42,7 @@ static void __iomem *zynq_clkc_base; #define SLCR_SWDT_CLK_SEL (zynq_clkc_base + 0x204) #define NUM_MIO_PINS 54 +#define CLK_NAME_LEN 16 #define DBG_CLK_CTRL_CLKACT_TRC BIT(0) #define DBG_CLK_CTRL_CPU_1XCLKACT BIT(1) @@ -215,7 +216,7 @@ static void __init zynq_clk_setup(struct device_node *np) int i; u32 tmp; int ret; - char *clk_name; + char clk_name[CLK_NAME_LEN]; unsigned int fclk_enable = 0; const char *clk_output_name[clk_max]; const char *cpu_parents[4]; @@ -426,12 +427,10 @@ static void __init zynq_clk_setup(struct device_node *np) "gem1_emio_mux", CLK_SET_RATE_PARENT, SLCR_GEM1_CLK_CTRL, 0, 0, &gem1clk_lock); - tmp = strlen("mio_clk_00x"); - clk_name = kmalloc(tmp, GFP_KERNEL); for (i = 0; i < NUM_MIO_PINS; i++) { int idx; - snprintf(clk_name, tmp, "mio_clk_%2.2d", i); + snprintf(clk_name, CLK_NAME_LEN, "mio_clk_%2.2d", i); idx = of_property_match_string(np, "clock-names", clk_name); if (idx >= 0) can_mio_mux_parents[i] = of_clk_get_parent_name(np, @@ -439,7 +438,6 @@ static void __init zynq_clk_setup(struct device_node *np) else can_mio_mux_parents[i] = dummy_nm; } - kfree(clk_name); clk_register_mux(NULL, "can_mux", periph_parents, 4, CLK_SET_RATE_NO_REPARENT, SLCR_CAN_CLK_CTRL, 4, 2, 0, &canclk_lock); diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c index 44a61dc6f93208c897f1379cbb1371191d29d7b4..e1c773bb55359c630a4d8623fe2076506509c71a 100644 --- a/drivers/clocksource/arm_global_timer.c +++ b/drivers/clocksource/arm_global_timer.c @@ -32,7 +32,7 @@ #define GT_CONTROL_IRQ_ENABLE BIT(2) /* banked */ #define GT_CONTROL_AUTO_INC BIT(3) /* banked */ #define GT_CONTROL_PRESCALER_SHIFT 8 -#define GT_CONTROL_PRESCALER_MAX 0xF +#define GT_CONTROL_PRESCALER_MAX 0xFF #define GT_CONTROL_PRESCALER_MASK (GT_CONTROL_PRESCALER_MAX << \ GT_CONTROL_PRESCALER_SHIFT) diff --git a/drivers/comedi/drivers/comedi_test.c b/drivers/comedi/drivers/comedi_test.c index 0b5c0af1cebf0502e276fd740279ffb36625b273..626d53bf9146ac9038499ea0f343cc2e9726aef0 100644 --- a/drivers/comedi/drivers/comedi_test.c +++ b/drivers/comedi/drivers/comedi_test.c @@ -85,6 +85,8 @@ struct waveform_private { struct comedi_device *dev; /* parent comedi device */ u64 ao_last_scan_time; /* time of previous AO scan in usec */ unsigned int ao_scan_period; /* AO scan period in usec */ + bool ai_timer_enable:1; /* should AI timer be running? */ + bool ao_timer_enable:1; /* should AO timer be running? */ unsigned short ao_loopbacks[N_CHANS]; }; @@ -234,8 +236,12 @@ static void waveform_ai_timer(struct timer_list *t) time_increment = devpriv->ai_convert_time - now; else time_increment = 1; - mod_timer(&devpriv->ai_timer, - jiffies + usecs_to_jiffies(time_increment)); + spin_lock(&dev->spinlock); + if (devpriv->ai_timer_enable) { + mod_timer(&devpriv->ai_timer, + jiffies + usecs_to_jiffies(time_increment)); + } + spin_unlock(&dev->spinlock); } overrun: @@ -391,9 +397,12 @@ static int waveform_ai_cmd(struct comedi_device *dev, * Seem to need an extra jiffy here, otherwise timer expires slightly * early! */ + spin_lock_bh(&dev->spinlock); + devpriv->ai_timer_enable = true; devpriv->ai_timer.expires = jiffies + usecs_to_jiffies(devpriv->ai_convert_period) + 1; add_timer(&devpriv->ai_timer); + spin_unlock_bh(&dev->spinlock); return 0; } @@ -402,6 +411,9 @@ static int waveform_ai_cancel(struct comedi_device *dev, { struct waveform_private *devpriv = dev->private; + spin_lock_bh(&dev->spinlock); + devpriv->ai_timer_enable = false; + spin_unlock_bh(&dev->spinlock); if (in_softirq()) { /* Assume we were called from the timer routine itself. */ del_timer(&devpriv->ai_timer); @@ -493,8 +505,12 @@ static void waveform_ao_timer(struct timer_list *t) unsigned int time_inc = devpriv->ao_last_scan_time + devpriv->ao_scan_period - now; - mod_timer(&devpriv->ao_timer, - jiffies + usecs_to_jiffies(time_inc)); + spin_lock(&dev->spinlock); + if (devpriv->ao_timer_enable) { + mod_timer(&devpriv->ao_timer, + jiffies + usecs_to_jiffies(time_inc)); + } + spin_unlock(&dev->spinlock); } underrun: @@ -515,9 +531,12 @@ static int waveform_ao_inttrig_start(struct comedi_device *dev, async->inttrig = NULL; devpriv->ao_last_scan_time = ktime_to_us(ktime_get()); + spin_lock_bh(&dev->spinlock); + devpriv->ao_timer_enable = true; devpriv->ao_timer.expires = jiffies + usecs_to_jiffies(devpriv->ao_scan_period); add_timer(&devpriv->ao_timer); + spin_unlock_bh(&dev->spinlock); return 1; } @@ -602,6 +621,9 @@ static int waveform_ao_cancel(struct comedi_device *dev, struct waveform_private *devpriv = dev->private; s->async->inttrig = NULL; + spin_lock_bh(&dev->spinlock); + devpriv->ao_timer_enable = false; + spin_unlock_bh(&dev->spinlock); if (in_softirq()) { /* Assume we were called from the timer routine itself. */ del_timer(&devpriv->ao_timer); diff --git a/drivers/comedi/drivers/vmk80xx.c b/drivers/comedi/drivers/vmk80xx.c index 4536ed43f65b2763ec4612a000eb4dae70875c17..84dce5184a77ae7903035c8905dbff30cea390ca 100644 --- a/drivers/comedi/drivers/vmk80xx.c +++ b/drivers/comedi/drivers/vmk80xx.c @@ -641,33 +641,22 @@ static int vmk80xx_find_usb_endpoints(struct comedi_device *dev) struct vmk80xx_private *devpriv = dev->private; struct usb_interface *intf = comedi_to_usb_interface(dev); struct usb_host_interface *iface_desc = intf->cur_altsetting; - struct usb_endpoint_descriptor *ep_desc; - int i; - - if (iface_desc->desc.bNumEndpoints != 2) - return -ENODEV; - - for (i = 0; i < iface_desc->desc.bNumEndpoints; i++) { - ep_desc = &iface_desc->endpoint[i].desc; - - if (usb_endpoint_is_int_in(ep_desc) || - usb_endpoint_is_bulk_in(ep_desc)) { - if (!devpriv->ep_rx) - devpriv->ep_rx = ep_desc; - continue; - } + struct usb_endpoint_descriptor *ep_rx_desc, *ep_tx_desc; + int ret; - if (usb_endpoint_is_int_out(ep_desc) || - usb_endpoint_is_bulk_out(ep_desc)) { - if (!devpriv->ep_tx) - devpriv->ep_tx = ep_desc; - continue; - } - } + if (devpriv->model == VMK8061_MODEL) + ret = usb_find_common_endpoints(iface_desc, &ep_rx_desc, + &ep_tx_desc, NULL, NULL); + else + ret = usb_find_common_endpoints(iface_desc, NULL, NULL, + &ep_rx_desc, &ep_tx_desc); - if (!devpriv->ep_rx || !devpriv->ep_tx) + if (ret) return -ENODEV; + devpriv->ep_rx = ep_rx_desc; + devpriv->ep_tx = ep_tx_desc; + if (!usb_endpoint_maxp(devpriv->ep_rx) || !usb_endpoint_maxp(devpriv->ep_tx)) return -EINVAL; diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index edc294ee5a5bca792cbf778bb018bb63639cc3b4..90dcf26f0973188a7691ace00f295482294ff307 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -320,7 +320,7 @@ static void amd_pstate_adjust_perf(unsigned int cpu, if (target_perf < capacity) des_perf = DIV_ROUND_UP(cap_perf * target_perf, capacity); - min_perf = READ_ONCE(cpudata->highest_perf); + min_perf = READ_ONCE(cpudata->lowest_perf); if (_min_perf < capacity) min_perf = DIV_ROUND_UP(cap_perf * _min_perf, capacity); diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c index b74289a95a17178b7e2177e1bf3ad0b12bb307b0..bea41ccabf1f0747775d4b2830956164620f51d0 100644 --- a/drivers/cpufreq/armada-37xx-cpufreq.c +++ b/drivers/cpufreq/armada-37xx-cpufreq.c @@ -14,10 +14,8 @@ #include #include #include +#include #include -#include -#include -#include #include #include #include diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c index f644c5e325fb2def542ce0e9000ec2ba1c040130..552db816ed22c5f2470b676d77c284e90aa8647a 100644 --- a/drivers/cpufreq/brcmstb-avs-cpufreq.c +++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c @@ -481,8 +481,11 @@ static bool brcm_avs_is_firmware_loaded(struct private_data *priv) static unsigned int brcm_avs_cpufreq_get(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - struct private_data *priv = policy->driver_data; + struct private_data *priv; + if (!policy) + return 0; + priv = policy->driver_data; cpufreq_cpu_put(policy); return brcm_avs_get_frequency(priv->base); diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index 4aec4b2a522594a44d817dc2a5ceb57c7cd3a432..8f8f1949d66f6d3986756dd660505b61995df194 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -208,7 +208,7 @@ static int dt_cpufreq_early_init(struct device *dev, int cpu) if (!priv) return -ENOMEM; - if (!alloc_cpumask_var(&priv->cpus, GFP_KERNEL)) + if (!zalloc_cpumask_var(&priv->cpus, GFP_KERNEL)) return -ENOMEM; cpumask_set_cpu(cpu, priv->cpus); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index c8912756fc06dde44591e861dcf6e2a3ce2b2b80..91efa23e0e8f3a5cd4e74b1f9075937098d5c5cc 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1525,7 +1525,8 @@ static int cpufreq_online(unsigned int cpu) if (cpufreq_driver->ready) cpufreq_driver->ready(policy); - if (cpufreq_thermal_control_enabled(cpufreq_driver)) + /* Register cpufreq cooling only for a new policy */ + if (new_policy && cpufreq_thermal_control_enabled(cpufreq_driver)) policy->cdev = of_cpufreq_cooling_register(policy); pr_debug("initialization complete\n"); @@ -1609,11 +1610,6 @@ static void __cpufreq_offline(unsigned int cpu, struct cpufreq_policy *policy) else policy->last_policy = policy->policy; - if (cpufreq_thermal_control_enabled(cpufreq_driver)) { - cpufreq_cooling_unregister(policy->cdev); - policy->cdev = NULL; - } - if (has_target()) cpufreq_exit_governor(policy); @@ -1674,6 +1670,15 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif) return; } + /* + * Unregister cpufreq cooling once all the CPUs of the policy are + * removed. + */ + if (cpufreq_thermal_control_enabled(cpufreq_driver)) { + cpufreq_cooling_unregister(policy->cdev); + policy->cdev = NULL; + } + /* We did light-weight exit earlier, do full tear down now */ if (cpufreq_driver->offline) cpufreq_driver->exit(policy); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index abdd26f7d04c91b8ea5cef369fbfac5f8b9863b3..5771f3fc6115d0e0dc5b235a6e424af2a483f0f7 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2952,6 +2952,9 @@ static void intel_cpufreq_adjust_perf(unsigned int cpunum, if (min_pstate < cpu->min_perf_ratio) min_pstate = cpu->min_perf_ratio; + if (min_pstate > cpu->max_perf_ratio) + min_pstate = cpu->max_perf_ratio; + max_pstate = min(cap_pstate, cpu->max_perf_ratio); if (max_pstate < min_pstate) max_pstate = min_pstate; diff --git a/drivers/cpufreq/mediatek-cpufreq-hw.c b/drivers/cpufreq/mediatek-cpufreq-hw.c index f0e0a35c7f21744e4e5ac042c9bd3f8fc11387d1..7f326bb5fd8dec595b0308f0e2fc77c76c83f12d 100644 --- a/drivers/cpufreq/mediatek-cpufreq-hw.c +++ b/drivers/cpufreq/mediatek-cpufreq-hw.c @@ -10,8 +10,10 @@ #include #include #include -#include +#include #include +#include +#include #include #define LUT_MAX_ENTRIES 32U @@ -295,7 +297,23 @@ static struct cpufreq_driver cpufreq_mtk_hw_driver = { static int mtk_cpufreq_hw_driver_probe(struct platform_device *pdev) { const void *data; - int ret; + int ret, cpu; + struct device *cpu_dev; + struct regulator *cpu_reg; + + /* Make sure that all CPU supplies are available before proceeding. */ + for_each_possible_cpu(cpu) { + cpu_dev = get_cpu_device(cpu); + if (!cpu_dev) + return dev_err_probe(&pdev->dev, -EPROBE_DEFER, + "Failed to get cpu%d device\n", cpu); + + cpu_reg = devm_regulator_get(cpu_dev, "cpu"); + if (IS_ERR(cpu_reg)) + return dev_err_probe(&pdev->dev, PTR_ERR(cpu_reg), + "CPU%d regulator get failed\n", cpu); + } + data = of_device_get_match_data(&pdev->dev); if (!data) diff --git a/drivers/cpufreq/ppc_cbe_cpufreq.c b/drivers/cpufreq/ppc_cbe_cpufreq.c index e3313ce63b38840a9f9df64efc0da08b6a906994..88afc49941b7165ba2949477d6179b06b54fcf38 100644 --- a/drivers/cpufreq/ppc_cbe_cpufreq.c +++ b/drivers/cpufreq/ppc_cbe_cpufreq.c @@ -9,7 +9,7 @@ #include #include -#include +#include #include #include diff --git a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c index 4fba3637b115c184611282d011cf23df6737df37..6f0c32592416ded9864ec397dac527de954fc1fc 100644 --- a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c +++ b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include diff --git a/drivers/cpufreq/qcom-cpufreq-nvmem.c b/drivers/cpufreq/qcom-cpufreq-nvmem.c index a577586b23be26b74115e57adf326bf1bf770a20..cb03bfb0435eaa8ba39014c81486e684fe1a03fc 100644 --- a/drivers/cpufreq/qcom-cpufreq-nvmem.c +++ b/drivers/cpufreq/qcom-cpufreq-nvmem.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c index fd2c16821d54c68e00fb94997580564f0ec417f3..ac719aca49b754b00f46453d70ce51326f5fc7df 100644 --- a/drivers/cpufreq/scpi-cpufreq.c +++ b/drivers/cpufreq/scpi-cpufreq.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/cpufreq/sti-cpufreq.c b/drivers/cpufreq/sti-cpufreq.c index 1a63aeea87112c2d856b16b13aa9a7ddaec1b762..9c542e723a157f7e86e22dbf84426214f30fab14 100644 --- a/drivers/cpufreq/sti-cpufreq.c +++ b/drivers/cpufreq/sti-cpufreq.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c index f64180dd2005b30416d20e7586fa65e9b9b8746a..61ef653bcf56f2acb9538db1ccde90679e40e975 100644 --- a/drivers/cpufreq/ti-cpufreq.c +++ b/drivers/cpufreq/ti-cpufreq.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/cpufreq/vexpress-spc-cpufreq.c b/drivers/cpufreq/vexpress-spc-cpufreq.c index d295f405c4bb08cb371741fb98c44a61e8f0b814..865e501648034baf2e0c5f350ca65be820d049d3 100644 --- a/drivers/cpufreq/vexpress-spc-cpufreq.c +++ b/drivers/cpufreq/vexpress-spc-cpufreq.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index f70aa17e2a8e0e9e9576252f8a33280c3d601115..c594e28adddf3deb08d6299eca46113d04fe6392 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -16,6 +16,7 @@ #include #include #include +#include #include "cpuidle.h" @@ -185,7 +186,7 @@ static void __cpuidle_driver_init(struct cpuidle_driver *drv) s->target_residency_ns = 0; if (s->exit_latency > 0) - s->exit_latency_ns = s->exit_latency * NSEC_PER_USEC; + s->exit_latency_ns = mul_u32_u32(s->exit_latency, NSEC_PER_USEC); else if (s->exit_latency_ns < 0) s->exit_latency_ns = 0; } diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index b8e02c3a19610c7828d7d9423c6f441e4a0ebe5a..bbfb0f288dc350352446b6b579e056d569c5d79e 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -515,10 +515,16 @@ EXPORT_SYMBOL_GPL(sev_platform_init); static int __sev_platform_shutdown_locked(int *error) { - struct sev_device *sev = psp_master->sev_data; + struct psp_device *psp = psp_master; + struct sev_device *sev; int ret; - if (!sev || sev->state == SEV_STATE_UNINIT) + if (!psp || !psp->sev_data) + return 0; + + sev = psp->sev_data; + + if (sev->state == SEV_STATE_UNINIT) return 0; ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, NULL, error); diff --git a/drivers/crypto/qat/qat_common/adf_aer.c b/drivers/crypto/qat/qat_common/adf_aer.c index fe9bb2f3536a978439aa55700f649db8b43f3805..4f36b5a9164a7f4d09b42e966352b064dd070a9c 100644 --- a/drivers/crypto/qat/qat_common/adf_aer.c +++ b/drivers/crypto/qat/qat_common/adf_aer.c @@ -95,18 +95,28 @@ static void adf_device_reset_worker(struct work_struct *work) if (adf_dev_init(accel_dev) || adf_dev_start(accel_dev)) { /* The device hanged and we can't restart it so stop here */ dev_err(&GET_DEV(accel_dev), "Restart device failed\n"); - kfree(reset_data); + if (reset_data->mode == ADF_DEV_RESET_ASYNC || + completion_done(&reset_data->compl)) + kfree(reset_data); WARN(1, "QAT: device restart failed. Device is unusable\n"); return; } adf_dev_restarted_notify(accel_dev); clear_bit(ADF_STATUS_RESTARTING, &accel_dev->status); - /* The dev is back alive. Notify the caller if in sync mode */ - if (reset_data->mode == ADF_DEV_RESET_SYNC) - complete(&reset_data->compl); - else + /* + * The dev is back alive. Notify the caller if in sync mode + * + * If device restart will take a more time than expected, + * the schedule_reset() function can timeout and exit. This can be + * detected by calling the completion_done() function. In this case + * the reset_data structure needs to be freed here. + */ + if (reset_data->mode == ADF_DEV_RESET_ASYNC || + completion_done(&reset_data->compl)) kfree(reset_data); + else + complete(&reset_data->compl); } static int adf_dev_aer_schedule_reset(struct adf_accel_dev *accel_dev, @@ -139,8 +149,9 @@ static int adf_dev_aer_schedule_reset(struct adf_accel_dev *accel_dev, dev_err(&GET_DEV(accel_dev), "Reset device timeout expired\n"); ret = -EFAULT; + } else { + kfree(reset_data); } - kfree(reset_data); return ret; } return 0; diff --git a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c index 168195672e2e10bed4a18d13991de26ef6536125..d2df97cfcb294dc7fb0880f42ffec61c46a59107 100644 --- a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c +++ b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c @@ -104,7 +104,8 @@ static void virtio_crypto_dataq_akcipher_callback(struct virtio_crypto_request * } static int virtio_crypto_alg_akcipher_init_session(struct virtio_crypto_akcipher_ctx *ctx, - struct virtio_crypto_ctrl_header *header, void *para, + struct virtio_crypto_ctrl_header *header, + struct virtio_crypto_akcipher_session_para *para, const uint8_t *key, unsigned int keylen) { struct scatterlist outhdr_sg, key_sg, inhdr_sg, *sgs[3]; @@ -128,7 +129,7 @@ static int virtio_crypto_alg_akcipher_init_session(struct virtio_crypto_akcipher ctrl = &vc_ctrl_req->ctrl; memcpy(&ctrl->header, header, sizeof(ctrl->header)); - memcpy(&ctrl->u, para, sizeof(ctrl->u)); + memcpy(&ctrl->u.akcipher_create_session.para, para, sizeof(*para)); input = &vc_ctrl_req->input; input->status = cpu_to_le32(VIRTIO_CRYPTO_ERR); diff --git a/drivers/crypto/xilinx/zynqmp-aes-gcm.c b/drivers/crypto/xilinx/zynqmp-aes-gcm.c index bf1f421e05f256879451bdc60a16198ba727f12e..74bd3eb63734ddb6e32288960316883e3c64c44e 100644 --- a/drivers/crypto/xilinx/zynqmp-aes-gcm.c +++ b/drivers/crypto/xilinx/zynqmp-aes-gcm.c @@ -231,7 +231,10 @@ static int zynqmp_handle_aes_req(struct crypto_engine *engine, err = zynqmp_aes_aead_cipher(areq); } + local_bh_disable(); crypto_finalize_aead_request(engine, areq, err); + local_bh_enable(); + return 0; } diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index 003a44132418aaa61737ba6d41e67f844273354c..5584af15300a89ccdbf50ef4eb8afc402892252b 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -376,9 +376,9 @@ static bool __cxl_hdm_decode_init(struct cxl_dev_state *cxlds, allowed++; } - if (!allowed) { - cxl_set_mem_enable(cxlds, 0); - info->mem_enabled = 0; + if (!allowed && info->mem_enabled) { + dev_err(dev, "Range register decodes outside platform defined CXL ranges.\n"); + return -ENXIO; } /* diff --git a/drivers/dma-buf/st-dma-fence-chain.c b/drivers/dma-buf/st-dma-fence-chain.c index 0a9b099d05187e44ab5cb17abdda3a9e593dba55..d90479d830fc3f4da3f287211e8ed42fd0b4f954 100644 --- a/drivers/dma-buf/st-dma-fence-chain.c +++ b/drivers/dma-buf/st-dma-fence-chain.c @@ -84,11 +84,11 @@ static int sanitycheck(void *arg) return -ENOMEM; chain = mock_chain(NULL, f, 1); - if (!chain) + if (chain) + dma_fence_enable_sw_signaling(chain); + else err = -ENOMEM; - dma_fence_enable_sw_signaling(chain); - dma_fence_signal(f); dma_fence_put(f); diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 75ca1b83e65b2bdd05bd535835159b74f18e6eb3..d4f50117ce1ce5bee580c7451469c6ce025b7acf 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -665,16 +665,16 @@ config TEGRA20_APB_DMA config TEGRA210_ADMA tristate "NVIDIA Tegra210 ADMA support" - depends on (ARCH_TEGRA_210_SOC || COMPILE_TEST) + depends on (ARCH_TEGRA || COMPILE_TEST) select DMA_ENGINE select DMA_VIRTUAL_CHANNELS help - Support for the NVIDIA Tegra210 ADMA controller driver. The - DMA controller has multiple DMA channels and is used to service - various audio clients in the Tegra210 audio processing engine - (APE). This DMA controller transfers data from memory to - peripheral and vice versa. It does not support memory to - memory data transfer. + Support for the NVIDIA Tegra210/Tegra186/Tegra194/Tegra234 ADMA + controller driver. The DMA controller has multiple DMA channels + and is used to service various audio clients in the Tegra210 + audio processing engine (APE). This DMA controller transfers + data from memory to peripheral and vice versa. It does not + support memory to memory data transfer. config TIMB_DMA tristate "Timberdale FPGA DMA support" diff --git a/drivers/dma/apple-admac.c b/drivers/dma/apple-admac.c index 4cf8da77bdd91329012579de26bb7aa01f7979f4..cac4532fe23a973c5074d9eefa527d90e77e0131 100644 --- a/drivers/dma/apple-admac.c +++ b/drivers/dma/apple-admac.c @@ -56,6 +56,8 @@ #define REG_BUS_WIDTH(ch) (0x8040 + (ch) * 0x200) +#define BUS_WIDTH_WORD_SIZE GENMASK(3, 0) +#define BUS_WIDTH_FRAME_SIZE GENMASK(7, 4) #define BUS_WIDTH_8BIT 0x00 #define BUS_WIDTH_16BIT 0x01 #define BUS_WIDTH_32BIT 0x02 @@ -739,7 +741,8 @@ static int admac_device_config(struct dma_chan *chan, struct admac_data *ad = adchan->host; bool is_tx = admac_chan_direction(adchan->no) == DMA_MEM_TO_DEV; int wordsize = 0; - u32 bus_width = 0; + u32 bus_width = readl_relaxed(ad->base + REG_BUS_WIDTH(adchan->no)) & + ~(BUS_WIDTH_WORD_SIZE | BUS_WIDTH_FRAME_SIZE); switch (is_tx ? config->dst_addr_width : config->src_addr_width) { case DMA_SLAVE_BUSWIDTH_1_BYTE: diff --git a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c index 8dd40d00a672a7ac5943ebf0bcbc22fafd058011..6b829d347417aef93df5ec70610171892a96f267 100644 --- a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c +++ b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c @@ -38,15 +38,17 @@ static int dpaa2_qdma_alloc_chan_resources(struct dma_chan *chan) if (!dpaa2_chan->fd_pool) goto err; - dpaa2_chan->fl_pool = dma_pool_create("fl_pool", dev, - sizeof(struct dpaa2_fl_entry), - sizeof(struct dpaa2_fl_entry), 0); + dpaa2_chan->fl_pool = + dma_pool_create("fl_pool", dev, + sizeof(struct dpaa2_fl_entry) * 3, + sizeof(struct dpaa2_fl_entry), 0); + if (!dpaa2_chan->fl_pool) goto err_fd; dpaa2_chan->sdd_pool = dma_pool_create("sdd_pool", dev, - sizeof(struct dpaa2_qdma_sd_d), + sizeof(struct dpaa2_qdma_sd_d) * 2, sizeof(struct dpaa2_qdma_sd_d), 0); if (!dpaa2_chan->sdd_pool) goto err_fl; diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c index 045ead46ec8fcb6fb410e219165c2a944a77f7f5..7082a5a6814a40653abef713b9b81929f9125bf6 100644 --- a/drivers/dma/fsl-qdma.c +++ b/drivers/dma/fsl-qdma.c @@ -109,6 +109,7 @@ #define FSL_QDMA_CMD_WTHROTL_OFFSET 20 #define FSL_QDMA_CMD_DSEN_OFFSET 19 #define FSL_QDMA_CMD_LWC_OFFSET 16 +#define FSL_QDMA_CMD_PF BIT(17) /* Field definition for Descriptor status */ #define QDMA_CCDF_STATUS_RTE BIT(5) @@ -384,7 +385,8 @@ static void fsl_qdma_comp_fill_memcpy(struct fsl_qdma_comp *fsl_comp, qdma_csgf_set_f(csgf_dest, len); /* Descriptor Buffer */ cmd = cpu_to_le32(FSL_QDMA_CMD_RWTTYPE << - FSL_QDMA_CMD_RWTTYPE_OFFSET); + FSL_QDMA_CMD_RWTTYPE_OFFSET) | + FSL_QDMA_CMD_PF; sdf->data = QDMA_SDDF_CMD(cmd); cmd = cpu_to_le32(FSL_QDMA_CMD_RWTTYPE << @@ -514,11 +516,11 @@ static struct fsl_qdma_queue queue_temp = queue_head + i + (j * queue_num); queue_temp->cq = - dma_alloc_coherent(&pdev->dev, - sizeof(struct fsl_qdma_format) * - queue_size[i], - &queue_temp->bus_addr, - GFP_KERNEL); + dmam_alloc_coherent(&pdev->dev, + sizeof(struct fsl_qdma_format) * + queue_size[i], + &queue_temp->bus_addr, + GFP_KERNEL); if (!queue_temp->cq) return NULL; queue_temp->block_base = fsl_qdma->block_base + @@ -563,11 +565,11 @@ static struct fsl_qdma_queue /* * Buffer for queue command */ - status_head->cq = dma_alloc_coherent(&pdev->dev, - sizeof(struct fsl_qdma_format) * - status_size, - &status_head->bus_addr, - GFP_KERNEL); + status_head->cq = dmam_alloc_coherent(&pdev->dev, + sizeof(struct fsl_qdma_format) * + status_size, + &status_head->bus_addr, + GFP_KERNEL); if (!status_head->cq) { devm_kfree(&pdev->dev, status_head); return NULL; @@ -805,7 +807,7 @@ fsl_qdma_irq_init(struct platform_device *pdev, int i; int cpu; int ret; - char irq_name[20]; + char irq_name[32]; fsl_qdma->error_irq = platform_get_irq_byname(pdev, "qdma-error"); @@ -1201,10 +1203,6 @@ static int fsl_qdma_probe(struct platform_device *pdev) if (!fsl_qdma->queue) return -ENOMEM; - ret = fsl_qdma_irq_init(pdev, fsl_qdma); - if (ret) - return ret; - fsl_qdma->irq_base = platform_get_irq_byname(pdev, "qdma-queue0"); if (fsl_qdma->irq_base < 0) return fsl_qdma->irq_base; @@ -1243,16 +1241,19 @@ static int fsl_qdma_probe(struct platform_device *pdev) platform_set_drvdata(pdev, fsl_qdma); - ret = dma_async_device_register(&fsl_qdma->dma_dev); + ret = fsl_qdma_reg_init(fsl_qdma); if (ret) { - dev_err(&pdev->dev, - "Can't register NXP Layerscape qDMA engine.\n"); + dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n"); return ret; } - ret = fsl_qdma_reg_init(fsl_qdma); + ret = fsl_qdma_irq_init(pdev, fsl_qdma); + if (ret) + return ret; + + ret = dma_async_device_register(&fsl_qdma->dma_dev); if (ret) { - dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n"); + dev_err(&pdev->dev, "Can't register NXP Layerscape qDMA engine.\n"); return ret; } @@ -1272,8 +1273,6 @@ static void fsl_qdma_cleanup_vchan(struct dma_device *dmadev) static int fsl_qdma_remove(struct platform_device *pdev) { - int i; - struct fsl_qdma_queue *status; struct device_node *np = pdev->dev.of_node; struct fsl_qdma_engine *fsl_qdma = platform_get_drvdata(pdev); @@ -1282,11 +1281,6 @@ static int fsl_qdma_remove(struct platform_device *pdev) of_dma_controller_free(np); dma_async_device_unregister(&fsl_qdma->dma_dev); - for (i = 0; i < fsl_qdma->block_number; i++) { - status = fsl_qdma->status[i]; - dma_free_coherent(&pdev->dev, sizeof(struct fsl_qdma_format) * - status->n_cq, status->cq, status->bus_addr); - } return 0; } diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c index f4c07ad3be15b427a43b7c9a60e4e5d43f9a9fa2..af8777a1ec2e36b83a12f59402118e6359b4c2b1 100644 --- a/drivers/dma/idma64.c +++ b/drivers/dma/idma64.c @@ -167,6 +167,10 @@ static irqreturn_t idma64_irq(int irq, void *dev) u32 status_err; unsigned short i; + /* Since IRQ may be shared, check if DMA controller is powered on */ + if (status == GENMASK(31, 0)) + return IRQ_NONE; + dev_vdbg(idma64->dma.dev, "%s: status=%#x\n", __func__, status); /* Check if we have any interrupt from the DMA controller */ diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index a9b96b18772f322ef4c74ba8acad04ae1f978c99..9f8adb7013ebae276883129e2e82835db35e4d45 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -198,6 +198,18 @@ static int idxd_cdev_mmap(struct file *filp, struct vm_area_struct *vma) int rc; dev_dbg(&pdev->dev, "%s called\n", __func__); + + /* + * Due to an erratum in some of the devices supported by the driver, + * direct user submission to the device can be unsafe. + * (See the INTEL-SA-01084 security advisory) + * + * For the devices that exhibit this behavior, require that the user + * has CAP_SYS_RAWIO capabilities. + */ + if (!idxd->user_submission_safe && !capable(CAP_SYS_RAWIO)) + return -EPERM; + rc = check_vma(wq, vma, __func__); if (rc < 0) return rc; @@ -212,6 +224,70 @@ static int idxd_cdev_mmap(struct file *filp, struct vm_area_struct *vma) vma->vm_page_prot); } +static int idxd_submit_user_descriptor(struct idxd_user_context *ctx, + struct dsa_hw_desc __user *udesc) +{ + struct idxd_wq *wq = ctx->wq; + struct idxd_dev *idxd_dev = &wq->idxd->idxd_dev; + const uint64_t comp_addr_align = is_dsa_dev(idxd_dev) ? 0x20 : 0x40; + void __iomem *portal = idxd_wq_portal_addr(wq); + struct dsa_hw_desc descriptor __aligned(64); + int rc; + + rc = copy_from_user(&descriptor, udesc, sizeof(descriptor)); + if (rc) + return -EFAULT; + + /* + * DSA devices are capable of indirect ("batch") command submission. + * On devices where direct user submissions are not safe, we cannot + * allow this since there is no good way for us to verify these + * indirect commands. + */ + if (is_dsa_dev(idxd_dev) && descriptor.opcode == DSA_OPCODE_BATCH && + !wq->idxd->user_submission_safe) + return -EINVAL; + /* + * As per the programming specification, the completion address must be + * aligned to 32 or 64 bytes. If this is violated the hardware + * engine can get very confused (security issue). + */ + if (!IS_ALIGNED(descriptor.completion_addr, comp_addr_align)) + return -EINVAL; + + if (wq_dedicated(wq)) + iosubmit_cmds512(portal, &descriptor, 1); + else { + descriptor.priv = 0; + descriptor.pasid = ctx->pasid; + rc = idxd_enqcmds(wq, portal, &descriptor); + if (rc < 0) + return rc; + } + + return 0; +} + +static ssize_t idxd_cdev_write(struct file *filp, const char __user *buf, size_t len, + loff_t *unused) +{ + struct dsa_hw_desc __user *udesc = (struct dsa_hw_desc __user *)buf; + struct idxd_user_context *ctx = filp->private_data; + ssize_t written = 0; + int i; + + for (i = 0; i < len/sizeof(struct dsa_hw_desc); i++) { + int rc = idxd_submit_user_descriptor(ctx, udesc + i); + + if (rc) + return written ? written : rc; + + written += sizeof(struct dsa_hw_desc); + } + + return written; +} + static __poll_t idxd_cdev_poll(struct file *filp, struct poll_table_struct *wait) { @@ -234,6 +310,7 @@ static const struct file_operations idxd_cdev_fops = { .open = idxd_cdev_open, .release = idxd_cdev_release, .mmap = idxd_cdev_mmap, + .write = idxd_cdev_write, .poll = idxd_cdev_poll, }; diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index 7ced8d283d98b28f071e5ce7f0f5f6c5f71d78c6..14c6ef987fede70891b17957c0d4069630bdd110 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -258,6 +258,7 @@ struct idxd_driver_data { struct device_type *dev_type; int compl_size; int align; + bool user_submission_safe; }; struct idxd_device { @@ -316,6 +317,8 @@ struct idxd_device { struct idxd_pmu *idxd_pmu; unsigned long *opcap_bmap; + + bool user_submission_safe; }; /* IDXD software descriptor */ diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index e0f49545d89ff1d9ec5c6e0ec1cc730100ec96e5..30193195c8133a158db39cccb9ce24ee73cc0a64 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -48,6 +48,7 @@ static struct idxd_driver_data idxd_driver_data[] = { .compl_size = sizeof(struct dsa_completion_record), .align = 32, .dev_type = &dsa_device_type, + .user_submission_safe = false, /* See INTEL-SA-01084 security advisory */ }, [IDXD_TYPE_IAX] = { .name_prefix = "iax", @@ -55,6 +56,7 @@ static struct idxd_driver_data idxd_driver_data[] = { .compl_size = sizeof(struct iax_completion_record), .align = 64, .dev_type = &iax_device_type, + .user_submission_safe = false, /* See INTEL-SA-01084 security advisory */ }, }; @@ -663,6 +665,8 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) dev_info(&pdev->dev, "Intel(R) Accelerator Device (v%x)\n", idxd->hw.version); + idxd->user_submission_safe = data->user_submission_safe; + return 0; err_dev_register: diff --git a/drivers/dma/idxd/perfmon.c b/drivers/dma/idxd/perfmon.c index d73004f47cf4b40f0cddf8a57907500884b69e29..612ef13b71603d5525d6aff5673d39af40629acc 100644 --- a/drivers/dma/idxd/perfmon.c +++ b/drivers/dma/idxd/perfmon.c @@ -529,14 +529,11 @@ static int perf_event_cpu_offline(unsigned int cpu, struct hlist_node *node) return 0; target = cpumask_any_but(cpu_online_mask, cpu); - /* migrate events if there is a valid target */ - if (target < nr_cpu_ids) + if (target < nr_cpu_ids) { cpumask_set_cpu(target, &perfmon_dsa_cpu_mask); - else - target = -1; - - perf_pmu_migrate_context(&idxd_pmu->pmu, cpu, target); + perf_pmu_migrate_context(&idxd_pmu->pmu, cpu, target); + } return 0; } diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index fe3b8d04f9db165d5df454a31e0a6b398f9451e4..fdfe7930f1834c73ad0b0fa888d2a80a80ffdc6a 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -4,9 +4,6 @@ #define _IDXD_REGISTERS_H_ /* PCI Config */ -#define PCI_DEVICE_ID_INTEL_DSA_SPR0 0x0b25 -#define PCI_DEVICE_ID_INTEL_IAX_SPR0 0x0cfe - #define DEVICE_VERSION_1 0x100 #define DEVICE_VERSION_2 0x200 diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 6e1e14b376e6583ff43aa25722eef66bdee2125d..c811757d0f97fa19fa8e5b95b807af0057fe8bc4 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -1162,12 +1162,35 @@ static ssize_t wq_enqcmds_retries_store(struct device *dev, struct device_attrib static struct device_attribute dev_attr_wq_enqcmds_retries = __ATTR(enqcmds_retries, 0644, wq_enqcmds_retries_show, wq_enqcmds_retries_store); +static ssize_t op_cap_show_common(struct device *dev, char *buf, unsigned long *opcap_bmap) +{ + ssize_t pos; + int i; + + pos = 0; + for (i = IDXD_MAX_OPCAP_BITS/64 - 1; i >= 0; i--) { + unsigned long val = opcap_bmap[i]; + + /* On systems where direct user submissions are not safe, we need to clear out + * the BATCH capability from the capability mask in sysfs since we cannot support + * that command on such systems. + */ + if (i == DSA_OPCODE_BATCH/64 && !confdev_to_idxd(dev)->user_submission_safe) + clear_bit(DSA_OPCODE_BATCH % 64, &val); + + pos += sysfs_emit_at(buf, pos, "%*pb", 64, &val); + pos += sysfs_emit_at(buf, pos, "%c", i == 0 ? '\n' : ','); + } + + return pos; +} + static ssize_t wq_op_config_show(struct device *dev, struct device_attribute *attr, char *buf) { struct idxd_wq *wq = confdev_to_wq(dev); - return sysfs_emit(buf, "%*pb\n", IDXD_MAX_OPCAP_BITS, wq->opcap_bmap); + return op_cap_show_common(dev, buf, wq->opcap_bmap); } static int idxd_verify_supported_opcap(struct idxd_device *idxd, unsigned long *opmask) @@ -1381,7 +1404,7 @@ static ssize_t op_cap_show(struct device *dev, { struct idxd_device *idxd = confdev_to_idxd(dev); - return sysfs_emit(buf, "%*pb\n", IDXD_MAX_OPCAP_BITS, idxd->opcap_bmap); + return op_cap_show_common(dev, buf, idxd->opcap_bmap); } static DEVICE_ATTR_RO(op_cap); diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c index e2070df6cad287bda75386961060339eb1b15d30..0b846c605d4bd1e66289b92146d7ae891e6ebf9d 100644 --- a/drivers/dma/ioat/dma.c +++ b/drivers/dma/ioat/dma.c @@ -584,11 +584,11 @@ desc_get_errstat(struct ioatdma_chan *ioat_chan, struct ioat_ring_ent *desc) } /** - * __cleanup - reclaim used descriptors + * __ioat_cleanup - reclaim used descriptors * @ioat_chan: channel (ring) to clean * @phys_complete: zeroed (or not) completion address (from status) */ -static void __cleanup(struct ioatdma_chan *ioat_chan, dma_addr_t phys_complete) +static void __ioat_cleanup(struct ioatdma_chan *ioat_chan, dma_addr_t phys_complete) { struct ioatdma_device *ioat_dma = ioat_chan->ioat_dma; struct ioat_ring_ent *desc; @@ -675,7 +675,7 @@ static void ioat_cleanup(struct ioatdma_chan *ioat_chan) spin_lock_bh(&ioat_chan->cleanup_lock); if (ioat_cleanup_preamble(ioat_chan, &phys_complete)) - __cleanup(ioat_chan, phys_complete); + __ioat_cleanup(ioat_chan, phys_complete); if (is_ioat_halted(*ioat_chan->completion)) { u32 chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET); @@ -712,7 +712,7 @@ static void ioat_restart_channel(struct ioatdma_chan *ioat_chan) ioat_quiesce(ioat_chan, 0); if (ioat_cleanup_preamble(ioat_chan, &phys_complete)) - __cleanup(ioat_chan, phys_complete); + __ioat_cleanup(ioat_chan, phys_complete); __ioat_restart_chan(ioat_chan); } @@ -786,7 +786,7 @@ static void ioat_eh(struct ioatdma_chan *ioat_chan) /* cleanup so tail points to descriptor that caused the error */ if (ioat_cleanup_preamble(ioat_chan, &phys_complete)) - __cleanup(ioat_chan, phys_complete); + __ioat_cleanup(ioat_chan, phys_complete); chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET); pci_read_config_dword(pdev, IOAT_PCI_CHANERR_INT_OFFSET, &chanerr_int); @@ -943,7 +943,7 @@ void ioat_timer_event(struct timer_list *t) /* timer restarted in ioat_cleanup_preamble * and IOAT_COMPLETION_ACK cleared */ - __cleanup(ioat_chan, phys_complete); + __ioat_cleanup(ioat_chan, phys_complete); goto unlock_out; } diff --git a/drivers/dma/owl-dma.c b/drivers/dma/owl-dma.c index b6e0ac8314e5cd278a0d3555805146a21bd206b3..0819f19c87cc553107be1023df2b3993e7bcf6c4 100644 --- a/drivers/dma/owl-dma.c +++ b/drivers/dma/owl-dma.c @@ -249,7 +249,7 @@ static void pchan_update(struct owl_dma_pchan *pchan, u32 reg, else regval &= ~val; - writel(val, pchan->base + reg); + writel(regval, pchan->base + reg); } static void pchan_writel(struct owl_dma_pchan *pchan, u32 reg, u32 data) @@ -273,7 +273,7 @@ static void dma_update(struct owl_dma *od, u32 reg, u32 val, bool state) else regval &= ~val; - writel(val, od->base + reg); + writel(regval, od->base + reg); } static void dma_writel(struct owl_dma *od, u32 reg, u32 data) diff --git a/drivers/dma/ptdma/ptdma-dmaengine.c b/drivers/dma/ptdma/ptdma-dmaengine.c index 1aa65e5de0f3ad9bc0fa0907ebda8e8c0fe6d0ab..f792407348077dd9fe481cfdec6577a701493487 100644 --- a/drivers/dma/ptdma/ptdma-dmaengine.c +++ b/drivers/dma/ptdma/ptdma-dmaengine.c @@ -385,8 +385,6 @@ int pt_dmaengine_register(struct pt_device *pt) chan->vc.desc_free = pt_do_cleanup; vchan_init(&chan->vc, dma_dev); - dma_set_mask_and_coherent(pt->dev, DMA_BIT_MASK(64)); - ret = dma_async_device_register(dma_dev); if (ret) goto err_reg; diff --git a/drivers/dma/sh/shdma.h b/drivers/dma/sh/shdma.h index 9c121a4b33ad829c77ae88c094fc80d942b9d709..f97d80343aea42fd399e93da3492e07a8fa86b35 100644 --- a/drivers/dma/sh/shdma.h +++ b/drivers/dma/sh/shdma.h @@ -25,7 +25,7 @@ struct sh_dmae_chan { const struct sh_dmae_slave_config *config; /* Slave DMA configuration */ int xmit_shift; /* log_2(bytes_per_xfer) */ void __iomem *base; - char dev_id[16]; /* unique name per DMAC of channel */ + char dev_id[32]; /* unique name per DMAC of channel */ int pm_error; dma_addr_t slave_addr; }; diff --git a/drivers/dma/tegra186-gpc-dma.c b/drivers/dma/tegra186-gpc-dma.c index 75af3488a3baf5667f2f8d41c790df1ba31b979c..e70b7c41dcab73005313b5ea71d7d7c559f77f1f 100644 --- a/drivers/dma/tegra186-gpc-dma.c +++ b/drivers/dma/tegra186-gpc-dma.c @@ -742,6 +742,9 @@ static int tegra_dma_get_residual(struct tegra_dma_channel *tdc) bytes_xfer = dma_desc->bytes_xfer + sg_req[dma_desc->sg_idx].len - (wcount * 4); + if (dma_desc->bytes_req == bytes_xfer) + return 0; + residual = dma_desc->bytes_req - (bytes_xfer % dma_desc->bytes_req); return residual; diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c index 7ec6e5d728b03fffefdcf3fc8dfdc1dbd0ba5db8..9212ac9f978f2a86214e6fc70fcf124c73ff00a8 100644 --- a/drivers/dma/ti/edma.c +++ b/drivers/dma/ti/edma.c @@ -2413,6 +2413,11 @@ static int edma_probe(struct platform_device *pdev) if (irq > 0) { irq_name = devm_kasprintf(dev, GFP_KERNEL, "%s_ccint", dev_name(dev)); + if (!irq_name) { + ret = -ENOMEM; + goto err_disable_pm; + } + ret = devm_request_irq(dev, irq, dma_irq_handler, 0, irq_name, ecc); if (ret) { @@ -2429,6 +2434,11 @@ static int edma_probe(struct platform_device *pdev) if (irq > 0) { irq_name = devm_kasprintf(dev, GFP_KERNEL, "%s_ccerrint", dev_name(dev)); + if (!irq_name) { + ret = -ENOMEM; + goto err_disable_pm; + } + ret = devm_request_irq(dev, irq, dma_ccerr_handler, 0, irq_name, ecc); if (ret) { diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index b86b809eb1f7e3be49d0722a2d7acf2d0f65f315..82e7acfda6ed0911da0ab3bc47d7188962063e67 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -3963,6 +3963,7 @@ static void udma_desc_pre_callback(struct virt_dma_chan *vc, { struct udma_chan *uc = to_udma_chan(&vc->chan); struct udma_desc *d; + u8 status; if (!vd) return; @@ -3972,12 +3973,12 @@ static void udma_desc_pre_callback(struct virt_dma_chan *vc, if (d->metadata_size) udma_fetch_epib(uc, d); - /* Provide residue information for the client */ if (result) { void *desc_vaddr = udma_curr_cppi5_desc_vaddr(d, d->desc_idx); if (cppi5_desc_get_type(desc_vaddr) == CPPI5_INFO0_DESC_TYPE_VAL_HOST) { + /* Provide residue information for the client */ result->residue = d->residue - cppi5_hdesc_get_pktlen(desc_vaddr); if (result->residue) @@ -3986,7 +3987,12 @@ static void udma_desc_pre_callback(struct virt_dma_chan *vc, result->result = DMA_TRANS_NOERROR; } else { result->residue = 0; - result->result = DMA_TRANS_NOERROR; + /* Propagate TR Response errors to the client */ + status = d->hwdesc[0].tr_resp_base->status; + if (status) + result->result = DMA_TRANS_ABORTED; + else + result->result = DMA_TRANS_NOERROR; } } } diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c index 84dc5240a8074ad3f184df62696ed8c902b58a9e..93938ed80fc83723b002ab0275895de0714dd7d5 100644 --- a/drivers/dma/xilinx/xilinx_dpdma.c +++ b/drivers/dma/xilinx/xilinx_dpdma.c @@ -214,7 +214,8 @@ struct xilinx_dpdma_tx_desc { * @running: true if the channel is running * @first_frame: flag for the first frame of stream * @video_group: flag if multi-channel operation is needed for video channels - * @lock: lock to access struct xilinx_dpdma_chan + * @lock: lock to access struct xilinx_dpdma_chan. Must be taken before + * @vchan.lock, if both are to be held. * @desc_pool: descriptor allocation pool * @err_task: error IRQ bottom half handler * @desc: References to descriptors being processed @@ -1097,12 +1098,14 @@ static void xilinx_dpdma_chan_vsync_irq(struct xilinx_dpdma_chan *chan) * Complete the active descriptor, if any, promote the pending * descriptor to active, and queue the next transfer, if any. */ + spin_lock(&chan->vchan.lock); if (chan->desc.active) vchan_cookie_complete(&chan->desc.active->vdesc); chan->desc.active = pending; chan->desc.pending = NULL; xilinx_dpdma_chan_queue_transfer(chan); + spin_unlock(&chan->vchan.lock); out: spin_unlock_irqrestore(&chan->lock, flags); @@ -1264,10 +1267,12 @@ static void xilinx_dpdma_issue_pending(struct dma_chan *dchan) struct xilinx_dpdma_chan *chan = to_xilinx_chan(dchan); unsigned long flags; - spin_lock_irqsave(&chan->vchan.lock, flags); + spin_lock_irqsave(&chan->lock, flags); + spin_lock(&chan->vchan.lock); if (vchan_issue_pending(&chan->vchan)) xilinx_dpdma_chan_queue_transfer(chan); - spin_unlock_irqrestore(&chan->vchan.lock, flags); + spin_unlock(&chan->vchan.lock); + spin_unlock_irqrestore(&chan->lock, flags); } static int xilinx_dpdma_config(struct dma_chan *dchan, @@ -1495,7 +1500,9 @@ static void xilinx_dpdma_chan_err_task(struct tasklet_struct *t) XILINX_DPDMA_EINTR_CHAN_ERR_MASK << chan->id); spin_lock_irqsave(&chan->lock, flags); + spin_lock(&chan->vchan.lock); xilinx_dpdma_chan_queue_transfer(chan); + spin_unlock(&chan->vchan.lock); spin_unlock_irqrestore(&chan->lock, flags); } diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c index 6ac5ff20a2fe22f1c3c5a7010ca0af87caf4c446..401a77e3b5fa8ed9e9b834c4a55cde98d2b2a8db 100644 --- a/drivers/firewire/core-card.c +++ b/drivers/firewire/core-card.c @@ -429,7 +429,23 @@ static void bm_work(struct work_struct *work) */ card->bm_generation = generation; - if (root_device == NULL) { + if (card->gap_count == 0) { + /* + * If self IDs have inconsistent gap counts, do a + * bus reset ASAP. The config rom read might never + * complete, so don't wait for it. However, still + * send a PHY configuration packet prior to the + * bus reset. The PHY configuration packet might + * fail, but 1394-2008 8.4.5.2 explicitly permits + * it in this case, so it should be safe to try. + */ + new_root_id = local_id; + /* + * We must always send a bus reset if the gap count + * is inconsistent, so bypass the 5-reset limit. + */ + card->bm_retries = 0; + } else if (root_device == NULL) { /* * Either link_on is false, or we failed to read the * config rom. In either case, pick another root. @@ -484,7 +500,19 @@ static void bm_work(struct work_struct *work) fw_notice(card, "phy config: new root=%x, gap_count=%d\n", new_root_id, gap_count); fw_send_phy_config(card, new_root_id, generation, gap_count); - reset_bus(card, true); + /* + * Where possible, use a short bus reset to minimize + * disruption to isochronous transfers. But in the event + * of a gap count inconsistency, use a long bus reset. + * + * As noted in 1394a 8.4.6.2, nodes on a mixed 1394/1394a bus + * may set different gap counts after a bus reset. On a mixed + * 1394/1394a bus, a short bus reset can get doubled. Some + * nodes may treat the double reset as one bus reset and others + * may treat it as two, causing a gap count inconsistency + * again. Using a long bus reset prevents this. + */ + reset_bus(card, card->gap_count != 0); /* Will allocate broadcast channel after the reset. */ goto out; } diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c index 74bab06283b71dcead93d439257b5d0880fbe7a7..1879ec27c02360fb1a974551d4e9666c67e97850 100644 --- a/drivers/firewire/core-device.c +++ b/drivers/firewire/core-device.c @@ -100,10 +100,9 @@ static int textual_leaf_to_string(const u32 *block, char *buf, size_t size) * @buf: where to put the string * @size: size of @buf, in bytes * - * The string is taken from a minimal ASCII text descriptor leaf after - * the immediate entry with @key. The string is zero-terminated. - * An overlong string is silently truncated such that it and the - * zero byte fit into @size. + * The string is taken from a minimal ASCII text descriptor leaf just after the entry with the + * @key. The string is zero-terminated. An overlong string is silently truncated such that it + * and the zero byte fit into @size. * * Returns strlen(buf) or a negative error code. */ diff --git a/drivers/firewire/nosy.c b/drivers/firewire/nosy.c index b0d671db178a85b6ab98de29f05b994db99a8697..ea31ac7ac1ca931a569af239dbaa2052448e8df5 100644 --- a/drivers/firewire/nosy.c +++ b/drivers/firewire/nosy.c @@ -148,10 +148,12 @@ packet_buffer_get(struct client *client, char __user *data, size_t user_length) if (atomic_read(&buffer->size) == 0) return -ENODEV; - /* FIXME: Check length <= user_length. */ + length = buffer->head->length; + + if (length > user_length) + return 0; end = buffer->data + buffer->capacity; - length = buffer->head->length; if (&buffer->head->data[length] < end) { if (copy_to_user(data, buffer->head->data, length)) diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 667ff40f393536e168bf454623b41cd48b53a443..7d94e1cbc0ed3fd8306b934bb4772b5a483c5a0c 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -2049,6 +2049,8 @@ static void bus_reset_work(struct work_struct *work) ohci->generation = generation; reg_write(ohci, OHCI1394_IntEventClear, OHCI1394_busReset); + if (param_debug & OHCI_PARAM_DEBUG_BUSRESETS) + reg_write(ohci, OHCI1394_IntMaskSet, OHCI1394_busReset); if (ohci->quirks & QUIRK_RESET_PACKET) ohci->request_generation = generation; @@ -2115,12 +2117,14 @@ static irqreturn_t irq_handler(int irq, void *data) return IRQ_NONE; /* - * busReset and postedWriteErr must not be cleared yet + * busReset and postedWriteErr events must not be cleared yet * (OHCI 1.1 clauses 7.2.3.2 and 13.2.8.1) */ reg_write(ohci, OHCI1394_IntEventClear, event & ~(OHCI1394_busReset | OHCI1394_postedWriteErr)); log_irqs(ohci, event); + if (event & OHCI1394_busReset) + reg_write(ohci, OHCI1394_IntMaskClear, OHCI1394_busReset); if (event & OHCI1394_selfIDComplete) queue_work(selfid_workqueue, &ohci->bus_reset_work); diff --git a/drivers/firmware/arm_scmi/smc.c b/drivers/firmware/arm_scmi/smc.c index ac0bd51ef16a2ed8433c552cfcc47fcd0ae806aa..42ea308a2c1d53bc2cc082c86b5306557245174b 100644 --- a/drivers/firmware/arm_scmi/smc.c +++ b/drivers/firmware/arm_scmi/smc.c @@ -171,6 +171,13 @@ static int smc_chan_free(int id, void *p, void *data) struct scmi_chan_info *cinfo = p; struct scmi_smc *scmi_info = cinfo->transport_info; + /* + * Different protocols might share the same chan info, so a previous + * smc_chan_free call might have already freed the structure. + */ + if (!scmi_info) + return 0; + /* Ignore any possible further reception on the IRQ path */ if (scmi_info->irq > 0) free_irq(scmi_info->irq, scmi_info); diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c index 7c48c380d722cb8d8e854be494391243afb180e9..1995f0a2e0fc04fa535a22c330388cad0cff68cc 100644 --- a/drivers/firmware/efi/arm-runtime.c +++ b/drivers/firmware/efi/arm-runtime.c @@ -107,7 +107,7 @@ static int __init arm_enable_runtime_services(void) efi_memory_desc_t *md; for_each_efi_memory_desc(md) { - int md_size = md->num_pages << EFI_PAGE_SHIFT; + u64 md_size = md->num_pages << EFI_PAGE_SHIFT; struct resource *res; if (!(md->attribute & EFI_MEMORY_SP)) diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c index 3e8d4b51a8140c16720eef8f08d311b024b1a830..97bafb5f7038924fb99eea6f5679b18b2d459e5a 100644 --- a/drivers/firmware/efi/capsule-loader.c +++ b/drivers/firmware/efi/capsule-loader.c @@ -292,7 +292,7 @@ static int efi_capsule_open(struct inode *inode, struct file *file) return -ENOMEM; } - cap_info->phys = kzalloc(sizeof(void *), GFP_KERNEL); + cap_info->phys = kzalloc(sizeof(phys_addr_t), GFP_KERNEL); if (!cap_info->phys) { kfree(cap_info->pages); kfree(cap_info); diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c index 2fd770b499a35301f2c0c04f09cd379fa11dcf30..ff9791ce2e15650d70d113bd492ef78c17a8e8c8 100644 --- a/drivers/firmware/efi/efi-init.c +++ b/drivers/firmware/efi/efi-init.c @@ -116,15 +116,6 @@ static __init int is_usable_memory(efi_memory_desc_t *md) case EFI_BOOT_SERVICES_DATA: case EFI_CONVENTIONAL_MEMORY: case EFI_PERSISTENT_MEMORY: - /* - * Special purpose memory is 'soft reserved', which means it - * is set aside initially, but can be hotplugged back in or - * be assigned to the dax driver after boot. - */ - if (efi_soft_reserve_enabled() && - (md->attribute & EFI_MEMORY_SP)) - return false; - /* * According to the spec, these regions are no longer reserved * after calling ExitBootServices(). However, we can only use @@ -169,6 +160,16 @@ static __init void reserve_regions(void) size = npages << PAGE_SHIFT; if (is_memory(md)) { + /* + * Special purpose memory is 'soft reserved', which + * means it is set aside initially. Don't add a memblock + * for it now so that it can be hotplugged back in or + * be assigned to the dax driver after boot. + */ + if (efi_soft_reserve_enabled() && + (md->attribute & EFI_MEMORY_SP)) + continue; + early_init_dt_add_memory_arch(paddr, size); if (!is_usable_memory(md)) diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index b7c0e8cc0764fa015e78c881098d16b59d68807f..28d4defc5d0cd23bd9059ad2ec22fc269c5b06f1 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -185,8 +185,29 @@ static const struct attribute_group efi_subsys_attr_group = { static struct efivars generic_efivars; static struct efivar_operations generic_ops; +static bool generic_ops_supported(void) +{ + unsigned long name_size; + efi_status_t status; + efi_char16_t name; + efi_guid_t guid; + + name_size = sizeof(name); + + if (!efi.get_next_variable) + return false; + status = efi.get_next_variable(&name_size, &name, &guid); + if (status == EFI_UNSUPPORTED) + return false; + + return true; +} + static int generic_ops_register(void) { + if (!generic_ops_supported()) + return 0; + generic_ops.get_variable = efi.get_variable; generic_ops.get_next_variable = efi.get_next_variable; generic_ops.query_variable_store = efi_query_variable_store; @@ -200,6 +221,9 @@ static int generic_ops_register(void) static void generic_ops_unregister(void) { + if (!generic_ops.get_variable) + return; + efivars_unregister(&generic_efivars); } diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index ef5045a53ce096535df7a7d12bad78f7f9464fcc..748781c25787179dac7da29d76ebed8aa89a96ef 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -25,7 +25,7 @@ cflags-$(CONFIG_ARM) := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \ -fno-builtin -fpic \ $(call cc-option,-mno-single-pic-base) cflags-$(CONFIG_RISCV) := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \ - -fpic + -fpic -mno-relax cflags-$(CONFIG_LOONGARCH) := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \ -fpie @@ -84,6 +84,7 @@ lib-$(CONFIG_EFI_GENERIC_STUB) += efi-stub.o string.o intrinsics.o systable.o lib-$(CONFIG_ARM) += arm32-stub.o lib-$(CONFIG_ARM64) += arm64-stub.o smbios.o lib-$(CONFIG_X86) += x86-stub.o +lib-$(CONFIG_X86_64) += x86-5lvl.o lib-$(CONFIG_RISCV) += riscv-stub.o lib-$(CONFIG_LOONGARCH) += loongarch-stub.o @@ -101,13 +102,6 @@ lib-y := $(patsubst %.o,%.stub.o,$(lib-y)) # https://bugs.llvm.org/show_bug.cgi?id=46480 STUBCOPY_FLAGS-y += --remove-section=.note.gnu.property -# -# For x86, bootloaders like systemd-boot or grub-efi do not zero-initialize the -# .bss section, so the .bss section of the EFI stub needs to be included in the -# .data section of the compressed kernel to ensure initialization. Rename the -# .bss section here so it's easy to pick out in the linker script. -# -STUBCOPY_FLAGS-$(CONFIG_X86) += --rename-section .bss=.bss.efistub,load,alloc STUBCOPY_RELOC-$(CONFIG_X86_32) := R_386_32 STUBCOPY_RELOC-$(CONFIG_X86_64) := R_X86_64_64 diff --git a/drivers/firmware/efi/libstub/alignedmem.c b/drivers/firmware/efi/libstub/alignedmem.c index 1de9878ddd3a2fbbeea8c00a7fce98f00beb862c..6b83c492c3b8260d52e16bb73a1d5abaa4cb943d 100644 --- a/drivers/firmware/efi/libstub/alignedmem.c +++ b/drivers/firmware/efi/libstub/alignedmem.c @@ -22,12 +22,15 @@ * Return: status code */ efi_status_t efi_allocate_pages_aligned(unsigned long size, unsigned long *addr, - unsigned long max, unsigned long align) + unsigned long max, unsigned long align, + int memory_type) { efi_physical_addr_t alloc_addr; efi_status_t status; int slack; + max = min(max, EFI_ALLOC_LIMIT); + if (align < EFI_ALLOC_ALIGN) align = EFI_ALLOC_ALIGN; @@ -36,7 +39,7 @@ efi_status_t efi_allocate_pages_aligned(unsigned long size, unsigned long *addr, slack = align / EFI_PAGE_SIZE - 1; status = efi_bs_call(allocate_pages, EFI_ALLOCATE_MAX_ADDRESS, - EFI_LOADER_DATA, size / EFI_PAGE_SIZE + slack, + memory_type, size / EFI_PAGE_SIZE + slack, &alloc_addr); if (status != EFI_SUCCESS) return status; diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c index e2f90566b291af4e48899ea73eaa304cf14edfdb..16f15e36f9a7d418d94f9ea8792b1892121e43b8 100644 --- a/drivers/firmware/efi/libstub/arm64-stub.c +++ b/drivers/firmware/efi/libstub/arm64-stub.c @@ -180,7 +180,8 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, * locate the kernel at a randomized offset in physical memory. */ status = efi_random_alloc(*reserve_size, min_kimg_align, - reserve_addr, phys_seed); + reserve_addr, phys_seed, + EFI_LOADER_CODE, 0, EFI_ALLOC_LIMIT); if (status != EFI_SUCCESS) efi_warn("efi_random_alloc() failed: 0x%lx\n", status); } else { @@ -190,10 +191,11 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, if (status != EFI_SUCCESS) { if (!check_image_region((u64)_text, kernel_memsize)) { efi_err("FIRMWARE BUG: Image BSS overlaps adjacent EFI memory region\n"); - } else if (IS_ALIGNED((u64)_text, min_kimg_align)) { + } else if (IS_ALIGNED((u64)_text, min_kimg_align) && + (u64)_end < EFI_ALLOC_LIMIT) { /* * Just execute from wherever we were loaded by the - * UEFI PE/COFF loader if the alignment is suitable. + * UEFI PE/COFF loader if the placement is suitable. */ *image_addr = (u64)_text; *reserve_size = 0; @@ -201,7 +203,8 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, } status = efi_allocate_pages_aligned(*reserve_size, reserve_addr, - ULONG_MAX, min_kimg_align); + ULONG_MAX, min_kimg_align, + EFI_LOADER_CODE); if (status != EFI_SUCCESS) { efi_err("Failed to relocate kernel\n"); diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index 3d9b2469a0dfd84902fb62595d8b2f7e4c493d25..97744822dd9512ce09b41919ece3b95bf40f5c5e 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -216,6 +216,8 @@ efi_status_t efi_parse_options(char const *cmdline) efi_loglevel = CONSOLE_LOGLEVEL_QUIET; } else if (!strcmp(param, "noinitrd")) { efi_noinitrd = true; + } else if (IS_ENABLED(CONFIG_X86_64) && !strcmp(param, "no5lvl")) { + efi_no5lvl = true; } else if (!strcmp(param, "efi") && val) { efi_nochunk = parse_option_str(val, "nochunk"); efi_novamap |= parse_option_str(val, "novamap"); diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index 970e86e3aab05652eea933be406ff6c8b91c61d5..6741f3d900c5ae247ff5ad3863b0353e41303ae0 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -29,6 +29,11 @@ #define EFI_ALLOC_ALIGN EFI_PAGE_SIZE #endif +#ifndef EFI_ALLOC_LIMIT +#define EFI_ALLOC_LIMIT ULONG_MAX +#endif + +extern bool efi_no5lvl; extern bool efi_nochunk; extern bool efi_nokaslr; extern int efi_loglevel; @@ -415,6 +420,26 @@ union efi_dxe_services_table { } mixed_mode; }; +typedef union efi_memory_attribute_protocol efi_memory_attribute_protocol_t; + +union efi_memory_attribute_protocol { + struct { + efi_status_t (__efiapi *get_memory_attributes)( + efi_memory_attribute_protocol_t *, efi_physical_addr_t, u64, u64 *); + + efi_status_t (__efiapi *set_memory_attributes)( + efi_memory_attribute_protocol_t *, efi_physical_addr_t, u64, u64); + + efi_status_t (__efiapi *clear_memory_attributes)( + efi_memory_attribute_protocol_t *, efi_physical_addr_t, u64, u64); + }; + struct { + u32 get_memory_attributes; + u32 set_memory_attributes; + u32 clear_memory_attributes; + } mixed_mode; +}; + typedef union efi_uga_draw_protocol efi_uga_draw_protocol_t; union efi_uga_draw_protocol { @@ -880,7 +905,9 @@ void efi_get_virtmap(efi_memory_desc_t *memory_map, unsigned long map_size, efi_status_t efi_get_random_bytes(unsigned long size, u8 *out); efi_status_t efi_random_alloc(unsigned long size, unsigned long align, - unsigned long *addr, unsigned long random_seed); + unsigned long *addr, unsigned long random_seed, + int memory_type, unsigned long alloc_min, + unsigned long alloc_max); efi_status_t efi_random_get_seed(void); @@ -907,7 +934,8 @@ efi_status_t efi_allocate_pages(unsigned long size, unsigned long *addr, unsigned long max); efi_status_t efi_allocate_pages_aligned(unsigned long size, unsigned long *addr, - unsigned long max, unsigned long align); + unsigned long max, unsigned long align, + int memory_type); efi_status_t efi_low_alloc_above(unsigned long size, unsigned long align, unsigned long *addr, unsigned long min); diff --git a/drivers/firmware/efi/libstub/mem.c b/drivers/firmware/efi/libstub/mem.c index 45841ef55a9f6ba284ec7f4bd34fc24a6b91451e..4f1fa302234d880f68c4f63e92d3326c3cd4dd29 100644 --- a/drivers/firmware/efi/libstub/mem.c +++ b/drivers/firmware/efi/libstub/mem.c @@ -89,9 +89,12 @@ efi_status_t efi_allocate_pages(unsigned long size, unsigned long *addr, efi_physical_addr_t alloc_addr; efi_status_t status; + max = min(max, EFI_ALLOC_LIMIT); + if (EFI_ALLOC_ALIGN > EFI_PAGE_SIZE) return efi_allocate_pages_aligned(size, addr, max, - EFI_ALLOC_ALIGN); + EFI_ALLOC_ALIGN, + EFI_LOADER_DATA); alloc_addr = ALIGN_DOWN(max + 1, EFI_ALLOC_ALIGN) - 1; status = efi_bs_call(allocate_pages, EFI_ALLOCATE_MAX_ADDRESS, diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c index 9fb5869896be7340c9bb7f4141c4cf93c9a4bbca..fff826f56728ccd85628dac969f85a3d1fd4ff93 100644 --- a/drivers/firmware/efi/libstub/randomalloc.c +++ b/drivers/firmware/efi/libstub/randomalloc.c @@ -16,7 +16,8 @@ */ static unsigned long get_entry_num_slots(efi_memory_desc_t *md, unsigned long size, - unsigned long align_shift) + unsigned long align_shift, + u64 alloc_min, u64 alloc_max) { unsigned long align = 1UL << align_shift; u64 first_slot, last_slot, region_end; @@ -29,11 +30,11 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md, return 0; region_end = min(md->phys_addr + md->num_pages * EFI_PAGE_SIZE - 1, - (u64)ULONG_MAX); + alloc_max); if (region_end < size) return 0; - first_slot = round_up(md->phys_addr, align); + first_slot = round_up(max(md->phys_addr, alloc_min), align); last_slot = round_down(region_end - size + 1, align); if (first_slot > last_slot) @@ -53,7 +54,10 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md, efi_status_t efi_random_alloc(unsigned long size, unsigned long align, unsigned long *addr, - unsigned long random_seed) + unsigned long random_seed, + int memory_type, + unsigned long alloc_min, + unsigned long alloc_max) { unsigned long total_slots = 0, target_slot; unsigned long total_mirrored_slots = 0; @@ -75,7 +79,8 @@ efi_status_t efi_random_alloc(unsigned long size, efi_memory_desc_t *md = (void *)map->map + map_offset; unsigned long slots; - slots = get_entry_num_slots(md, size, ilog2(align)); + slots = get_entry_num_slots(md, size, ilog2(align), alloc_min, + alloc_max); MD_NUM_SLOTS(md) = slots; total_slots += slots; if (md->attribute & EFI_MEMORY_MORE_RELIABLE) @@ -114,11 +119,11 @@ efi_status_t efi_random_alloc(unsigned long size, continue; } - target = round_up(md->phys_addr, align) + target_slot * align; + target = round_up(max_t(u64, md->phys_addr, alloc_min), align) + target_slot * align; pages = size / EFI_PAGE_SIZE; status = efi_bs_call(allocate_pages, EFI_ALLOCATE_ADDRESS, - EFI_LOADER_DATA, pages, &target); + memory_type, pages, &target); if (status == EFI_SUCCESS) *addr = target; break; diff --git a/drivers/firmware/efi/libstub/x86-5lvl.c b/drivers/firmware/efi/libstub/x86-5lvl.c new file mode 100644 index 0000000000000000000000000000000000000000..479dd445acdcff8d9bdc7021d17041fef715f6ac --- /dev/null +++ b/drivers/firmware/efi/libstub/x86-5lvl.c @@ -0,0 +1,95 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include + +#include +#include +#include + +#include "efistub.h" +#include "x86-stub.h" + +bool efi_no5lvl; + +static void (*la57_toggle)(void *cr3); + +static const struct desc_struct gdt[] = { + [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(0xc09b, 0, 0xfffff), + [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(0xa09b, 0, 0xfffff), +}; + +/* + * Enabling (or disabling) 5 level paging is tricky, because it can only be + * done from 32-bit mode with paging disabled. This means not only that the + * code itself must be running from 32-bit addressable physical memory, but + * also that the root page table must be 32-bit addressable, as programming + * a 64-bit value into CR3 when running in 32-bit mode is not supported. + */ +efi_status_t efi_setup_5level_paging(void) +{ + u8 tmpl_size = (u8 *)&trampoline_ljmp_imm_offset - (u8 *)&trampoline_32bit_src; + efi_status_t status; + u8 *la57_code; + + if (!efi_is_64bit()) + return EFI_SUCCESS; + + /* check for 5 level paging support */ + if (native_cpuid_eax(0) < 7 || + !(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) + return EFI_SUCCESS; + + /* allocate some 32-bit addressable memory for code and a page table */ + status = efi_allocate_pages(2 * PAGE_SIZE, (unsigned long *)&la57_code, + U32_MAX); + if (status != EFI_SUCCESS) + return status; + + la57_toggle = memcpy(la57_code, trampoline_32bit_src, tmpl_size); + memset(la57_code + tmpl_size, 0x90, PAGE_SIZE - tmpl_size); + + /* + * To avoid the need to allocate a 32-bit addressable stack, the + * trampoline uses a LJMP instruction to switch back to long mode. + * LJMP takes an absolute destination address, which needs to be + * fixed up at runtime. + */ + *(u32 *)&la57_code[trampoline_ljmp_imm_offset] += (unsigned long)la57_code; + + efi_adjust_memory_range_protection((unsigned long)la57_toggle, PAGE_SIZE); + + return EFI_SUCCESS; +} + +void efi_5level_switch(void) +{ + bool want_la57 = IS_ENABLED(CONFIG_X86_5LEVEL) && !efi_no5lvl; + bool have_la57 = native_read_cr4() & X86_CR4_LA57; + bool need_toggle = want_la57 ^ have_la57; + u64 *pgt = (void *)la57_toggle + PAGE_SIZE; + u64 *cr3 = (u64 *)__native_read_cr3(); + u64 *new_cr3; + + if (!la57_toggle || !need_toggle) + return; + + if (!have_la57) { + /* + * 5 level paging will be enabled, so a root level page needs + * to be allocated from the 32-bit addressable physical region, + * with its first entry referring to the existing hierarchy. + */ + new_cr3 = memset(pgt, 0, PAGE_SIZE); + new_cr3[0] = (u64)cr3 | _PAGE_TABLE_NOENC; + } else { + /* take the new root table pointer from the current entry #0 */ + new_cr3 = (u64 *)(cr3[0] & PAGE_MASK); + + /* copy the new root table if it is not 32-bit addressable */ + if ((u64)new_cr3 > U32_MAX) + new_cr3 = memcpy(pgt, new_cr3, PAGE_SIZE); + } + + native_load_gdt(&(struct desc_ptr){ sizeof(gdt) - 1, (u64)gdt }); + + la57_toggle(new_cr3); +} diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 4f0152b11a89062becff40c01b00f6c91c2ae834..55468debd55d01f0b340ae16f848c89c3c3202ed 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -15,16 +15,18 @@ #include #include #include +#include +#include #include "efistub.h" +#include "x86-stub.h" -/* Maximum physical address for 64-bit kernel with 4-level paging */ -#define MAXMEM_X86_64_4LEVEL (1ull << 46) +extern char _bss[], _ebss[]; const efi_system_table_t *efi_system_table; const efi_dxe_services_table_t *efi_dxe_table; -extern u32 image_offset; static efi_loaded_image_t *image = NULL; +static efi_memory_attribute_protocol_t *memattr; static efi_status_t preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) @@ -212,8 +214,8 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params) } } -static void -adjust_memory_range_protection(unsigned long start, unsigned long size) +efi_status_t efi_adjust_memory_range_protection(unsigned long start, + unsigned long size) { efi_status_t status; efi_gcd_memory_space_desc_t desc; @@ -221,12 +223,31 @@ adjust_memory_range_protection(unsigned long start, unsigned long size) unsigned long rounded_start, rounded_end; unsigned long unprotect_start, unprotect_size; - if (efi_dxe_table == NULL) - return; - rounded_start = rounddown(start, EFI_PAGE_SIZE); rounded_end = roundup(start + size, EFI_PAGE_SIZE); + if (memattr != NULL) { + status = efi_call_proto(memattr, set_memory_attributes, + rounded_start, + rounded_end - rounded_start, + EFI_MEMORY_RO); + if (status != EFI_SUCCESS) { + efi_warn("Failed to set EFI_MEMORY_RO attribute\n"); + return status; + } + + status = efi_call_proto(memattr, clear_memory_attributes, + rounded_start, + rounded_end - rounded_start, + EFI_MEMORY_XP); + if (status != EFI_SUCCESS) + efi_warn("Failed to clear EFI_MEMORY_XP attribute\n"); + return status; + } + + if (efi_dxe_table == NULL) + return EFI_SUCCESS; + /* * Don't modify memory region attributes, they are * already suitable, to lower the possibility to @@ -238,7 +259,7 @@ adjust_memory_range_protection(unsigned long start, unsigned long size) status = efi_dxe_call(get_memory_space_descriptor, start, &desc); if (status != EFI_SUCCESS) - return; + break; next = desc.base_address + desc.length; @@ -263,69 +284,26 @@ adjust_memory_range_protection(unsigned long start, unsigned long size) unprotect_start, unprotect_start + unprotect_size, status); + break; } } + return EFI_SUCCESS; } -/* - * Trampoline takes 2 pages and can be loaded in first megabyte of memory - * with its end placed between 128k and 640k where BIOS might start. - * (see arch/x86/boot/compressed/pgtable_64.c) - * - * We cannot find exact trampoline placement since memory map - * can be modified by UEFI, and it can alter the computed address. - */ - -#define TRAMPOLINE_PLACEMENT_BASE ((128 - 8)*1024) -#define TRAMPOLINE_PLACEMENT_SIZE (640*1024 - (128 - 8)*1024) - -void startup_32(struct boot_params *boot_params); - -static void -setup_memory_protection(unsigned long image_base, unsigned long image_size) +static efi_char16_t *efistub_fw_vendor(void) { - /* - * Allow execution of possible trampoline used - * for switching between 4- and 5-level page tables - * and relocated kernel image. - */ - - adjust_memory_range_protection(TRAMPOLINE_PLACEMENT_BASE, - TRAMPOLINE_PLACEMENT_SIZE); + unsigned long vendor = efi_table_attr(efi_system_table, fw_vendor); -#ifdef CONFIG_64BIT - if (image_base != (unsigned long)startup_32) - adjust_memory_range_protection(image_base, image_size); -#else - /* - * Clear protection flags on a whole range of possible - * addresses used for KASLR. We don't need to do that - * on x86_64, since KASLR/extraction is performed after - * dedicated identity page tables are built and we only - * need to remove possible protection on relocated image - * itself disregarding further relocations. - */ - adjust_memory_range_protection(LOAD_PHYSICAL_ADDR, - KERNEL_IMAGE_SIZE - LOAD_PHYSICAL_ADDR); -#endif + return (efi_char16_t *)vendor; } static const efi_char16_t apple[] = L"Apple"; -static void setup_quirks(struct boot_params *boot_params, - unsigned long image_base, - unsigned long image_size) +static void setup_quirks(struct boot_params *boot_params) { - efi_char16_t *fw_vendor = (efi_char16_t *)(unsigned long) - efi_table_attr(efi_system_table, fw_vendor); - - if (!memcmp(fw_vendor, apple, sizeof(apple))) { - if (IS_ENABLED(CONFIG_APPLE_PROPERTIES)) - retrieve_apple_device_properties(boot_params); - } - - if (IS_ENABLED(CONFIG_EFI_DXE_MEM_ATTRIBUTES)) - setup_memory_protection(image_base, image_size); + if (IS_ENABLED(CONFIG_APPLE_PROPERTIES) && + !memcmp(efistub_fw_vendor(), apple, sizeof(apple))) + retrieve_apple_device_properties(boot_params); } /* @@ -457,14 +435,16 @@ void __noreturn efi_stub_entry(efi_handle_t handle, efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg) { - struct boot_params *boot_params; - struct setup_header *hdr; - void *image_base; + static struct boot_params boot_params __page_aligned_bss; + struct setup_header *hdr = &boot_params.hdr; efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID; int options_size = 0; efi_status_t status; char *cmdline_ptr; + if (efi_is_native()) + memset(_bss, 0, _ebss - _bss); + efi_system_table = sys_table_arg; /* Check if we were booted by the EFI firmware */ @@ -477,58 +457,25 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, efi_exit(handle, status); } - image_base = efi_table_attr(image, image_base); - image_offset = (void *)startup_32 - image_base; - - status = efi_allocate_pages(sizeof(struct boot_params), - (unsigned long *)&boot_params, ULONG_MAX); - if (status != EFI_SUCCESS) { - efi_err("Failed to allocate lowmem for boot params\n"); - efi_exit(handle, status); - } - - memset(boot_params, 0x0, sizeof(struct boot_params)); - - hdr = &boot_params->hdr; - - /* Copy the setup header from the second sector to boot_params */ - memcpy(&hdr->jump, image_base + 512, - sizeof(struct setup_header) - offsetof(struct setup_header, jump)); - - /* - * Fill out some of the header fields ourselves because the - * EFI firmware loader doesn't load the first sector. - */ + /* Assign the setup_header fields that the kernel actually cares about */ hdr->root_flags = 1; hdr->vid_mode = 0xffff; - hdr->boot_flag = 0xAA55; hdr->type_of_loader = 0x21; + hdr->initrd_addr_max = INT_MAX; /* Convert unicode cmdline to ascii */ cmdline_ptr = efi_convert_cmdline(image, &options_size); if (!cmdline_ptr) goto fail; - efi_set_u64_split((unsigned long)cmdline_ptr, - &hdr->cmd_line_ptr, &boot_params->ext_cmd_line_ptr); - - hdr->ramdisk_image = 0; - hdr->ramdisk_size = 0; - - /* - * Disregard any setup data that was provided by the bootloader: - * setup_data could be pointing anywhere, and we have no way of - * authenticating or validating the payload. - */ - hdr->setup_data = 0; + efi_set_u64_split((unsigned long)cmdline_ptr, &hdr->cmd_line_ptr, + &boot_params.ext_cmd_line_ptr); - efi_stub_entry(handle, sys_table_arg, boot_params); + efi_stub_entry(handle, sys_table_arg, &boot_params); /* not reached */ fail: - efi_free(sizeof(struct boot_params), (unsigned long)boot_params); - efi_exit(handle, status); } @@ -760,85 +707,139 @@ static efi_status_t exit_boot(struct boot_params *boot_params, void *handle) return EFI_SUCCESS; } +static bool have_unsupported_snp_features(void) +{ + u64 unsupported; + + unsupported = snp_get_unsupported_features(sev_get_status()); + if (unsupported) { + efi_err("Unsupported SEV-SNP features detected: 0x%llx\n", + unsupported); + return true; + } + return false; +} + +static void efi_get_seed(void *seed, int size) +{ + efi_get_random_bytes(size, seed); + + /* + * This only updates seed[0] when running on 32-bit, but in that case, + * seed[1] is not used anyway, as there is no virtual KASLR on 32-bit. + */ + *(unsigned long *)seed ^= kaslr_get_random_long("EFI"); +} + +static void error(char *str) +{ + efi_warn("Decompression failed: %s\n", str); +} + +static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry) +{ + unsigned long virt_addr = LOAD_PHYSICAL_ADDR; + unsigned long addr, alloc_size, entry; + efi_status_t status; + u32 seed[2] = {}; + + /* determine the required size of the allocation */ + alloc_size = ALIGN(max_t(unsigned long, output_len, kernel_total_size), + MIN_KERNEL_ALIGN); + + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && !efi_nokaslr) { + u64 range = KERNEL_IMAGE_SIZE - LOAD_PHYSICAL_ADDR - kernel_total_size; + static const efi_char16_t ami[] = L"American Megatrends"; + + efi_get_seed(seed, sizeof(seed)); + + virt_addr += (range * seed[1]) >> 32; + virt_addr &= ~(CONFIG_PHYSICAL_ALIGN - 1); + + /* + * Older Dell systems with AMI UEFI firmware v2.0 may hang + * while decompressing the kernel if physical address + * randomization is enabled. + * + * https://bugzilla.kernel.org/show_bug.cgi?id=218173 + */ + if (efi_system_table->hdr.revision <= EFI_2_00_SYSTEM_TABLE_REVISION && + !memcmp(efistub_fw_vendor(), ami, sizeof(ami))) { + efi_debug("AMI firmware v2.0 or older detected - disabling physical KASLR\n"); + seed[0] = 0; + } + + boot_params_ptr->hdr.loadflags |= KASLR_FLAG; + } + + status = efi_random_alloc(alloc_size, CONFIG_PHYSICAL_ALIGN, &addr, + seed[0], EFI_LOADER_CODE, + LOAD_PHYSICAL_ADDR, + EFI_X86_KERNEL_ALLOC_LIMIT); + if (status != EFI_SUCCESS) + return status; + + entry = decompress_kernel((void *)addr, virt_addr, error); + if (entry == ULONG_MAX) { + efi_free(alloc_size, addr); + return EFI_LOAD_ERROR; + } + + *kernel_entry = addr + entry; + + return efi_adjust_memory_range_protection(addr, kernel_text_size); +} + +static void __noreturn enter_kernel(unsigned long kernel_addr, + struct boot_params *boot_params) +{ + /* enter decompressed kernel with boot_params pointer in RSI/ESI */ + asm("jmp *%0"::"r"(kernel_addr), "S"(boot_params)); + + unreachable(); +} + /* - * On success, we return the address of startup_32, which has potentially been - * relocated by efi_relocate_kernel. - * On failure, we exit to the firmware via efi_exit instead of returning. + * On success, this routine will jump to the relocated image directly and never + * return. On failure, it will exit to the firmware via efi_exit() instead of + * returning. */ -asmlinkage unsigned long efi_main(efi_handle_t handle, - efi_system_table_t *sys_table_arg, - struct boot_params *boot_params) +void __noreturn efi_stub_entry(efi_handle_t handle, + efi_system_table_t *sys_table_arg, + struct boot_params *boot_params) { - unsigned long bzimage_addr = (unsigned long)startup_32; - unsigned long buffer_start, buffer_end; + efi_guid_t guid = EFI_MEMORY_ATTRIBUTE_PROTOCOL_GUID; struct setup_header *hdr = &boot_params->hdr; const struct linux_efi_initrd *initrd = NULL; + unsigned long kernel_entry; efi_status_t status; + boot_params_ptr = boot_params; + efi_system_table = sys_table_arg; /* Check if we were booted by the EFI firmware */ if (efi_system_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) efi_exit(handle, EFI_INVALID_PARAMETER); - efi_dxe_table = get_efi_config_table(EFI_DXE_SERVICES_TABLE_GUID); - if (efi_dxe_table && - efi_dxe_table->hdr.signature != EFI_DXE_SERVICES_TABLE_SIGNATURE) { - efi_warn("Ignoring DXE services table: invalid signature\n"); - efi_dxe_table = NULL; + if (have_unsupported_snp_features()) + efi_exit(handle, EFI_UNSUPPORTED); + + if (IS_ENABLED(CONFIG_EFI_DXE_MEM_ATTRIBUTES)) { + efi_dxe_table = get_efi_config_table(EFI_DXE_SERVICES_TABLE_GUID); + if (efi_dxe_table && + efi_dxe_table->hdr.signature != EFI_DXE_SERVICES_TABLE_SIGNATURE) { + efi_warn("Ignoring DXE services table: invalid signature\n"); + efi_dxe_table = NULL; + } } - /* - * If the kernel isn't already loaded at a suitable address, - * relocate it. - * - * It must be loaded above LOAD_PHYSICAL_ADDR. - * - * The maximum address for 64-bit is 1 << 46 for 4-level paging. This - * is defined as the macro MAXMEM, but unfortunately that is not a - * compile-time constant if 5-level paging is configured, so we instead - * define our own macro for use here. - * - * For 32-bit, the maximum address is complicated to figure out, for - * now use KERNEL_IMAGE_SIZE, which will be 512MiB, the same as what - * KASLR uses. - * - * Also relocate it if image_offset is zero, i.e. the kernel wasn't - * loaded by LoadImage, but rather by a bootloader that called the - * handover entry. The reason we must always relocate in this case is - * to handle the case of systemd-boot booting a unified kernel image, - * which is a PE executable that contains the bzImage and an initrd as - * COFF sections. The initrd section is placed after the bzImage - * without ensuring that there are at least init_size bytes available - * for the bzImage, and thus the compressed kernel's startup code may - * overwrite the initrd unless it is moved out of the way. - */ + /* grab the memory attributes protocol if it exists */ + efi_bs_call(locate_protocol, &guid, NULL, (void **)&memattr); - buffer_start = ALIGN(bzimage_addr - image_offset, - hdr->kernel_alignment); - buffer_end = buffer_start + hdr->init_size; - - if ((buffer_start < LOAD_PHYSICAL_ADDR) || - (IS_ENABLED(CONFIG_X86_32) && buffer_end > KERNEL_IMAGE_SIZE) || - (IS_ENABLED(CONFIG_X86_64) && buffer_end > MAXMEM_X86_64_4LEVEL) || - (image_offset == 0)) { - extern char _bss[]; - - status = efi_relocate_kernel(&bzimage_addr, - (unsigned long)_bss - bzimage_addr, - hdr->init_size, - hdr->pref_address, - hdr->kernel_alignment, - LOAD_PHYSICAL_ADDR); - if (status != EFI_SUCCESS) { - efi_err("efi_relocate_kernel() failed!\n"); - goto fail; - } - /* - * Now that we've copied the kernel elsewhere, we no longer - * have a set up block before startup_32(), so reset image_offset - * to zero in case it was set earlier. - */ - image_offset = 0; + status = efi_setup_5level_paging(); + if (status != EFI_SUCCESS) { + efi_err("efi_setup_5level_paging() failed!\n"); + goto fail; } #ifdef CONFIG_CMDLINE_BOOL @@ -858,6 +859,12 @@ asmlinkage unsigned long efi_main(efi_handle_t handle, } } + status = efi_decompress_kernel(&kernel_entry); + if (status != EFI_SUCCESS) { + efi_err("Failed to decompress kernel\n"); + goto fail; + } + /* * At this point, an initrd may already have been loaded by the * bootloader and passed via bootparams. We permit an initrd loaded @@ -897,7 +904,7 @@ asmlinkage unsigned long efi_main(efi_handle_t handle, setup_efi_pci(boot_params); - setup_quirks(boot_params, bzimage_addr, buffer_end - buffer_start); + setup_quirks(boot_params); status = exit_boot(boot_params, handle); if (status != EFI_SUCCESS) { @@ -905,9 +912,36 @@ asmlinkage unsigned long efi_main(efi_handle_t handle, goto fail; } - return bzimage_addr; + /* + * Call the SEV init code while still running with the firmware's + * GDT/IDT, so #VC exceptions will be handled by EFI. + */ + sev_enable(boot_params); + + efi_5level_switch(); + + enter_kernel(kernel_entry, boot_params); fail: - efi_err("efi_main() failed!\n"); + efi_err("efi_stub_entry() failed!\n"); efi_exit(handle, status); } + +#ifdef CONFIG_EFI_HANDOVER_PROTOCOL +void efi_handover_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg, + struct boot_params *boot_params) +{ + memset(_bss, 0, _ebss - _bss); + efi_stub_entry(handle, sys_table_arg, boot_params); +} + +#ifndef CONFIG_EFI_MIXED +extern __alias(efi_handover_entry) +void efi32_stub_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg, + struct boot_params *boot_params); + +extern __alias(efi_handover_entry) +void efi64_stub_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg, + struct boot_params *boot_params); +#endif +#endif diff --git a/drivers/firmware/efi/libstub/x86-stub.h b/drivers/firmware/efi/libstub/x86-stub.h new file mode 100644 index 0000000000000000000000000000000000000000..1c20e99a6494423787ef1dd091739ed9cbc89a24 --- /dev/null +++ b/drivers/firmware/efi/libstub/x86-stub.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include + +extern void trampoline_32bit_src(void *, bool); +extern const u16 trampoline_ljmp_imm_offset; + +efi_status_t efi_adjust_memory_range_protection(unsigned long start, + unsigned long size); + +#ifdef CONFIG_X86_64 +efi_status_t efi_setup_5level_paging(void); +void efi_5level_switch(void); +#else +static inline efi_status_t efi_setup_5level_paging(void) { return EFI_SUCCESS; } +static inline void efi_5level_switch(void) {} +#endif diff --git a/drivers/firmware/efi/riscv-runtime.c b/drivers/firmware/efi/riscv-runtime.c index d0daacd2c903f18224c993c32afd4e56e2e6df8a..6b142aa35389eea1ac7311074dbcdf906dd9f20e 100644 --- a/drivers/firmware/efi/riscv-runtime.c +++ b/drivers/firmware/efi/riscv-runtime.c @@ -85,7 +85,7 @@ static int __init riscv_enable_runtime_services(void) efi_memory_desc_t *md; for_each_efi_memory_desc(md) { - int md_size = md->num_pages << EFI_PAGE_SHIFT; + u64 md_size = md->num_pages << EFI_PAGE_SHIFT; struct resource *res; if (!(md->attribute & EFI_MEMORY_SP)) diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index 0ba9f18312f5b822531fab61f277f77ccdce02cf..4ca256bcd69715bd9add11d4271f81919e649711 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -66,19 +66,28 @@ int efivars_register(struct efivars *efivars, const struct efivar_operations *ops, struct kobject *kobject) { + int rv; + if (down_interruptible(&efivars_lock)) return -EINTR; + if (__efivars) { + pr_warn("efivars already registered\n"); + rv = -EBUSY; + goto out; + } + efivars->ops = ops; efivars->kobject = kobject; __efivars = efivars; pr_info("Registered efivars operations\n"); - + rv = 0; +out: up(&efivars_lock); - return 0; + return rv; } EXPORT_SYMBOL_GPL(efivars_register); diff --git a/drivers/firmware/tegra/bpmp-debugfs.c b/drivers/firmware/tegra/bpmp-debugfs.c index 9d3874cdaaeefc567e1be8b31d3915a74ad709c9..34e4152477f3bd973ad1ff32286ff8d6c65b368f 100644 --- a/drivers/firmware/tegra/bpmp-debugfs.c +++ b/drivers/firmware/tegra/bpmp-debugfs.c @@ -81,7 +81,7 @@ static const char *get_filename(struct tegra_bpmp *bpmp, root_path_buf = kzalloc(root_path_buf_len, GFP_KERNEL); if (!root_path_buf) - goto out; + return NULL; root_path = dentry_path(bpmp->debugfs_mirror, root_path_buf, root_path_buf_len); diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 84e4d72c9b5d7903cc9e0c2894110be1dc4f7bc5..b2ccdf19885336cdfd7e3ade2b03c558a3e87660 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -693,7 +693,8 @@ config GPIO_UNIPHIER Say yes here to support UniPhier GPIOs. config GPIO_VF610 - def_bool y + bool "VF610 GPIO support" + default y if SOC_VF610 depends on ARCH_MXC select GPIOLIB_IRQCHIP help diff --git a/drivers/gpio/gpio-74x164.c b/drivers/gpio/gpio-74x164.c index e00c333105170f5a2a702593feab340ddc4a7d8e..753e7be039e4d9cd830190d75d8b62ca1219ec96 100644 --- a/drivers/gpio/gpio-74x164.c +++ b/drivers/gpio/gpio-74x164.c @@ -127,8 +127,6 @@ static int gen_74x164_probe(struct spi_device *spi) if (IS_ERR(chip->gpiod_oe)) return PTR_ERR(chip->gpiod_oe); - gpiod_set_value_cansleep(chip->gpiod_oe, 1); - spi_set_drvdata(spi, chip); chip->gpio_chip.label = spi->modalias; @@ -153,6 +151,8 @@ static int gen_74x164_probe(struct spi_device *spi) goto exit_destroy; } + gpiod_set_value_cansleep(chip->gpiod_oe, 1); + ret = gpiochip_add_data(&chip->gpio_chip, chip); if (!ret) return 0; diff --git a/drivers/gpio/gpio-crystalcove.c b/drivers/gpio/gpio-crystalcove.c index 1ee62cd58582b6496f0536fa7c45e2dc0305797f..25db014494a4de9bb8c44d0b2bd39d8786c3bb59 100644 --- a/drivers/gpio/gpio-crystalcove.c +++ b/drivers/gpio/gpio-crystalcove.c @@ -92,7 +92,7 @@ static inline int to_reg(int gpio, enum ctrl_register reg_type) case 0x5e: return GPIOPANELCTL; default: - return -EOPNOTSUPP; + return -ENOTSUPP; } } diff --git a/drivers/gpio/gpio-wcove.c b/drivers/gpio/gpio-wcove.c index c18b6b47384f1b8b9a3a26c3ac7c5f125e82d365..94ca9d03c0949453abf3ad82e013698a7a97ffda 100644 --- a/drivers/gpio/gpio-wcove.c +++ b/drivers/gpio/gpio-wcove.c @@ -104,7 +104,7 @@ static inline int to_reg(int gpio, enum ctrl_register type) unsigned int reg = type == CTRL_IN ? GPIO_IN_CTRL_BASE : GPIO_OUT_CTRL_BASE; if (gpio >= WCOVE_GPIO_NUM) - return -EOPNOTSUPP; + return -ENOTSUPP; return reg + gpio; } diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index e40c93f0960b41e606ffe55ade33e1bd10507f81..97e8335716b011d88ca09e802bea29f42c172977 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -12,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -20,11 +22,13 @@ #include #include #include +#include +#include #include #include #include #include -#include + #include #include "gpiolib.h" @@ -463,6 +467,7 @@ out_free_lh: /** * struct line - contains the state of a requested line + * @node: to store the object in supinfo_tree if supplemental * @desc: the GPIO descriptor for this line. * @req: the corresponding line request * @irq: the interrupt triggered in response to events on this GPIO @@ -475,6 +480,7 @@ out_free_lh: * @line_seqno: the seqno for the current edge event in the sequence of * events for this line. * @work: the worker that implements software debouncing + * @debounce_period_us: the debounce period in microseconds * @sw_debounced: flag indicating if the software debouncer is active * @level: the current debounced physical level of the line * @hdesc: the Hardware Timestamp Engine (HTE) descriptor @@ -483,6 +489,7 @@ out_free_lh: * @last_seqno: the last sequence number before debounce period expires */ struct line { + struct rb_node node; struct gpio_desc *desc; /* * -- edge detector specific fields -- @@ -516,6 +523,15 @@ struct line { * -- debouncer specific fields -- */ struct delayed_work work; + /* + * debounce_period_us is accessed by debounce_irq_handler() and + * process_hw_ts() which are disabled when modified by + * debounce_setup(), edge_detector_setup() or edge_detector_stop() + * or can live with a stale version when updated by + * edge_detector_update(). + * The modifying functions are themselves mutually exclusive. + */ + unsigned int debounce_period_us; /* * sw_debounce is accessed by linereq_set_config(), which is the * only setter, and linereq_get_values(), which can live with a @@ -548,6 +564,17 @@ struct line { #endif /* CONFIG_HTE */ }; +/* + * a rbtree of the struct lines containing supplemental info. + * Used to populate gpio_v2_line_info with cdev specific fields not contained + * in the struct gpio_desc. + * A line is determined to contain supplemental information by + * line_has_supinfo(). + */ +static struct rb_root supinfo_tree = RB_ROOT; +/* covers supinfo_tree */ +static DEFINE_SPINLOCK(supinfo_lock); + /** * struct linereq - contains the state of a userspace line request * @gdev: the GPIO device the line request pertains to @@ -560,7 +587,8 @@ struct line { * this line request. Note that this is not used when @num_lines is 1, as * the line_seqno is then the same and is cheaper to calculate. * @config_mutex: mutex for serializing ioctl() calls to ensure consistency - * of configuration, particularly multi-step accesses to desc flags. + * of configuration, particularly multi-step accesses to desc flags and + * changes to supinfo status. * @lines: the lines held by this line request, with @num_lines elements. */ struct linereq { @@ -575,6 +603,103 @@ struct linereq { struct line lines[]; }; +static void supinfo_insert(struct line *line) +{ + struct rb_node **new = &(supinfo_tree.rb_node), *parent = NULL; + struct line *entry; + + guard(spinlock)(&supinfo_lock); + + while (*new) { + entry = container_of(*new, struct line, node); + + parent = *new; + if (line->desc < entry->desc) { + new = &((*new)->rb_left); + } else if (line->desc > entry->desc) { + new = &((*new)->rb_right); + } else { + /* this should never happen */ + WARN(1, "duplicate line inserted"); + return; + } + } + + rb_link_node(&line->node, parent, new); + rb_insert_color(&line->node, &supinfo_tree); +} + +static void supinfo_erase(struct line *line) +{ + guard(spinlock)(&supinfo_lock); + + rb_erase(&line->node, &supinfo_tree); +} + +static struct line *supinfo_find(struct gpio_desc *desc) +{ + struct rb_node *node = supinfo_tree.rb_node; + struct line *line; + + while (node) { + line = container_of(node, struct line, node); + if (desc < line->desc) + node = node->rb_left; + else if (desc > line->desc) + node = node->rb_right; + else + return line; + } + return NULL; +} + +static void supinfo_to_lineinfo(struct gpio_desc *desc, + struct gpio_v2_line_info *info) +{ + struct gpio_v2_line_attribute *attr; + struct line *line; + + guard(spinlock)(&supinfo_lock); + + line = supinfo_find(desc); + if (!line) + return; + + attr = &info->attrs[info->num_attrs]; + attr->id = GPIO_V2_LINE_ATTR_ID_DEBOUNCE; + attr->debounce_period_us = READ_ONCE(line->debounce_period_us); + info->num_attrs++; +} + +static inline bool line_has_supinfo(struct line *line) +{ + return READ_ONCE(line->debounce_period_us); +} + +/* + * Checks line_has_supinfo() before and after the change to avoid unnecessary + * supinfo_tree access. + * Called indirectly by linereq_create() or linereq_set_config() so line + * is already protected from concurrent changes. + */ +static void line_set_debounce_period(struct line *line, + unsigned int debounce_period_us) +{ + bool was_suppl = line_has_supinfo(line); + + WRITE_ONCE(line->debounce_period_us, debounce_period_us); + + /* if supinfo status is unchanged then we're done */ + if (line_has_supinfo(line) == was_suppl) + return; + + /* supinfo status has changed, so update the tree */ + if (was_suppl) + supinfo_erase(line); + else + supinfo_insert(line); +} + #define GPIO_V2_LINE_BIAS_FLAGS \ (GPIO_V2_LINE_FLAG_BIAS_PULL_UP | \ GPIO_V2_LINE_FLAG_BIAS_PULL_DOWN | \ @@ -712,7 +837,7 @@ static enum hte_return process_hw_ts(struct hte_ts_data *ts, void *p) line->total_discard_seq++; line->last_seqno = ts->seq; mod_delayed_work(system_wq, &line->work, - usecs_to_jiffies(READ_ONCE(line->desc->debounce_period_us))); + usecs_to_jiffies(READ_ONCE(line->debounce_period_us))); } else { if (unlikely(ts->seq < line->line_seqno)) return HTE_CB_HANDLED; @@ -853,7 +978,7 @@ static irqreturn_t debounce_irq_handler(int irq, void *p) struct line *line = p; mod_delayed_work(system_wq, &line->work, - usecs_to_jiffies(READ_ONCE(line->desc->debounce_period_us))); + usecs_to_jiffies(READ_ONCE(line->debounce_period_us))); return IRQ_HANDLED; } @@ -935,7 +1060,7 @@ static int debounce_setup(struct line *line, unsigned int debounce_period_us) /* try hardware */ ret = gpiod_set_debounce(line->desc, debounce_period_us); if (!ret) { - WRITE_ONCE(line->desc->debounce_period_us, debounce_period_us); + line_set_debounce_period(line, debounce_period_us); return ret; } if (ret != -ENOTSUPP) @@ -1014,8 +1139,7 @@ static void edge_detector_stop(struct line *line) cancel_delayed_work_sync(&line->work); WRITE_ONCE(line->sw_debounced, 0); WRITE_ONCE(line->edflags, 0); - if (line->desc) - WRITE_ONCE(line->desc->debounce_period_us, 0); + line_set_debounce_period(line, 0); /* do not change line->level - see comment in debounced_value() */ } @@ -1040,7 +1164,7 @@ static int edge_detector_setup(struct line *line, ret = debounce_setup(line, debounce_period_us); if (ret) return ret; - WRITE_ONCE(line->desc->debounce_period_us, debounce_period_us); + line_set_debounce_period(line, debounce_period_us); } /* detection disabled or sw debouncer will provide edge detection */ @@ -1077,17 +1201,31 @@ static int edge_detector_update(struct line *line, struct gpio_v2_line_config *lc, unsigned int line_idx, u64 edflags) { + u64 eflags; + int ret; u64 active_edflags = READ_ONCE(line->edflags); unsigned int debounce_period_us = gpio_v2_line_config_debounce_period(lc, line_idx); if ((active_edflags == edflags) && - (READ_ONCE(line->desc->debounce_period_us) == debounce_period_us)) + (READ_ONCE(line->debounce_period_us) == debounce_period_us)) return 0; /* sw debounced and still will be...*/ if (debounce_period_us && READ_ONCE(line->sw_debounced)) { - WRITE_ONCE(line->desc->debounce_period_us, debounce_period_us); + line_set_debounce_period(line, debounce_period_us); + /* + * ensure event fifo is initialised if edge detection + * is now enabled. + */ + eflags = edflags & GPIO_V2_LINE_EDGE_FLAGS; + if (eflags && !kfifo_initialized(&line->req->events)) { + ret = kfifo_alloc(&line->req->events, + line->req->event_buffer_size, + GFP_KERNEL); + if (ret) + return ret; + } return 0; } @@ -1564,13 +1702,18 @@ static ssize_t linereq_read(struct file *file, char __user *buf, static void linereq_free(struct linereq *lr) { + struct line *line; unsigned int i; for (i = 0; i < lr->num_lines; i++) { - if (lr->lines[i].desc) { - edge_detector_stop(&lr->lines[i]); - gpiod_free(lr->lines[i].desc); - } + line = &lr->lines[i]; + if (!line->desc) + continue; + + edge_detector_stop(line); + if (line_has_supinfo(line)) + supinfo_erase(line); + gpiod_free(line->desc); } kfifo_free(&lr->events); kfree(lr->label); @@ -2237,8 +2380,6 @@ static void gpio_desc_to_lineinfo(struct gpio_desc *desc, struct gpio_chip *gc = desc->gdev->chip; bool ok_for_pinctrl; unsigned long flags; - u32 debounce_period_us; - unsigned int num_attrs = 0; memset(info, 0, sizeof(*info)); info->offset = gpio_chip_hwgpio(desc); @@ -2305,14 +2446,6 @@ static void gpio_desc_to_lineinfo(struct gpio_desc *desc, else if (test_bit(FLAG_EVENT_CLOCK_HTE, &desc->flags)) info->flags |= GPIO_V2_LINE_FLAG_EVENT_CLOCK_HTE; - debounce_period_us = READ_ONCE(desc->debounce_period_us); - if (debounce_period_us) { - info->attrs[num_attrs].id = GPIO_V2_LINE_ATTR_ID_DEBOUNCE; - info->attrs[num_attrs].debounce_period_us = debounce_period_us; - num_attrs++; - } - info->num_attrs = num_attrs; - spin_unlock_irqrestore(&gpio_lock, flags); } @@ -2418,6 +2551,7 @@ static int lineinfo_get(struct gpio_chardev_data *cdev, void __user *ip, return -EBUSY; } gpio_desc_to_lineinfo(desc, &lineinfo); + supinfo_to_lineinfo(desc, &lineinfo); if (copy_to_user(ip, &lineinfo, sizeof(lineinfo))) { if (watch) @@ -2521,6 +2655,7 @@ static int lineinfo_changed_notify(struct notifier_block *nb, chg.event_type = action; chg.timestamp_ns = ktime_get_ns(); gpio_desc_to_lineinfo(desc, &chg.info); + supinfo_to_lineinfo(desc, &chg.info); ret = kfifo_in_spinlocked(&cdev->events, &chg, 1, &cdev->wait.lock); if (ret) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index e3060424a6e8dfabd172b2d76a88a962c928423c..47c7fd26b9e890a50eb6bc663f1b886773e6b842 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -786,11 +786,11 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, ret = gpiochip_irqchip_init_valid_mask(gc); if (ret) - goto err_remove_acpi_chip; + goto err_free_hogs; ret = gpiochip_irqchip_init_hw(gc); if (ret) - goto err_remove_acpi_chip; + goto err_remove_irqchip_mask; ret = gpiochip_add_irqchip(gc, lock_key, request_key); if (ret) @@ -815,13 +815,13 @@ err_remove_irqchip: gpiochip_irqchip_remove(gc); err_remove_irqchip_mask: gpiochip_irqchip_free_valid_mask(gc); -err_remove_acpi_chip: +err_free_hogs: + gpiochip_free_hogs(gc); acpi_gpiochip_remove(gc); + gpiochip_remove_pin_ranges(gc); err_remove_of_chip: - gpiochip_free_hogs(gc); of_gpiochip_remove(gc); err_free_gpiochip_mask: - gpiochip_remove_pin_ranges(gc); gpiochip_free_valid_mask(gc); if (gdev->dev.release) { /* release() has been registered by gpiochip_setup_dev() */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index c46c6fbd235e88e5dbf53e8bbf5552a0c031df92..dd22d2559720cf02b45a1a2b095c3599f5409d32 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -999,6 +999,8 @@ struct amdgpu_device { bool in_s3; bool in_s4; bool in_s0ix; + /* indicate amdgpu suspension status */ + bool suspend_complete; enum pp_mp1_state mp1_state; struct amdgpu_doorbell_index doorbell_index; @@ -1340,6 +1342,7 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev, void amdgpu_driver_release_kms(struct drm_device *dev); int amdgpu_device_ip_suspend(struct amdgpu_device *adev); +int amdgpu_device_prepare(struct drm_device *dev); int amdgpu_device_suspend(struct drm_device *dev, bool fbcon); int amdgpu_device_resume(struct drm_device *dev, bool fbcon); u32 amdgpu_get_vblank_counter_kms(struct drm_crtc *crtc); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 260e6a3316db0b238112636f23ecf5df5882281d..7d5fbaaba72f70efb753eeecf9ce23f85d61f46a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1779,6 +1779,7 @@ err_node_allow: err_bo_create: amdgpu_amdkfd_unreserve_mem_limit(adev, aligned_size, flags); err_reserve_limit: + amdgpu_sync_free(&(*mem)->sync); mutex_destroy(&(*mem)->lock); if (gobj) drm_gem_object_put(gobj); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 4b91f95066ecac4a28b96caa8d9396339384185d..b11690a816e736fe8a82752a63e855a329741bc6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1639,6 +1639,7 @@ static void amdgpu_switcheroo_set_state(struct pci_dev *pdev, } else { pr_info("switched off\n"); dev->switch_power_state = DRM_SWITCH_POWER_CHANGING; + amdgpu_device_prepare(dev); amdgpu_device_suspend(dev, true); amdgpu_device_cache_pci_state(pdev); /* Shut down the device */ @@ -4167,6 +4168,43 @@ static int amdgpu_device_evict_resources(struct amdgpu_device *adev) /* * Suspend & resume. */ +/** + * amdgpu_device_prepare - prepare for device suspend + * + * @dev: drm dev pointer + * + * Prepare to put the hw in the suspend state (all asics). + * Returns 0 for success or an error on failure. + * Called at driver suspend. + */ +int amdgpu_device_prepare(struct drm_device *dev) +{ + struct amdgpu_device *adev = drm_to_adev(dev); + int i, r; + + if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) + return 0; + + /* Evict the majority of BOs before starting suspend sequence */ + r = amdgpu_device_evict_resources(adev); + if (r) + return r; + + flush_delayed_work(&adev->gfx.gfx_off_delay_work); + + for (i = 0; i < adev->num_ip_blocks; i++) { + if (!adev->ip_blocks[i].status.valid) + continue; + if (!adev->ip_blocks[i].version->funcs->prepare_suspend) + continue; + r = adev->ip_blocks[i].version->funcs->prepare_suspend((void *)adev); + if (r) + return r; + } + + return 0; +} + /** * amdgpu_device_suspend - initiate device suspend * @@ -4203,7 +4241,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true); cancel_delayed_work_sync(&adev->delayed_init_work); - flush_delayed_work(&adev->gfx.gfx_off_delay_work); amdgpu_ras_suspend(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index b9983ca99eb7d7bf8692b1165cc39d5a8e79434f..9a5416331f02efb2c1c302cb4765492558d59970 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2391,8 +2391,9 @@ static int amdgpu_pmops_prepare(struct device *dev) /* Return a positive number here so * DPM_FLAG_SMART_SUSPEND works properly */ - if (amdgpu_device_supports_boco(drm_dev)) - return pm_runtime_suspended(dev); + if (amdgpu_device_supports_boco(drm_dev) && + pm_runtime_suspended(dev)) + return 1; /* if we will not support s3 or s2i for the device * then skip suspend @@ -2401,7 +2402,7 @@ static int amdgpu_pmops_prepare(struct device *dev) !amdgpu_acpi_is_s3_active(adev)) return 1; - return 0; + return amdgpu_device_prepare(drm_dev); } static void amdgpu_pmops_complete(struct device *dev) @@ -2414,6 +2415,7 @@ static int amdgpu_pmops_suspend(struct device *dev) struct drm_device *drm_dev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(drm_dev); + adev->suspend_complete = false; if (amdgpu_acpi_is_s0ix_active(adev)) adev->in_s0ix = true; else if (amdgpu_acpi_is_s3_active(adev)) @@ -2428,6 +2430,7 @@ static int amdgpu_pmops_suspend_noirq(struct device *dev) struct drm_device *drm_dev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(drm_dev); + adev->suspend_complete = true; if (amdgpu_acpi_should_gpu_reset(adev)) return amdgpu_asic_reset(adev); @@ -2598,6 +2601,9 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev) if (amdgpu_device_supports_boco(drm_dev)) adev->mp1_state = PP_MP1_STATE_UNLOAD; + ret = amdgpu_device_prepare(drm_dev); + if (ret) + return ret; ret = amdgpu_device_suspend(drm_dev, false); if (ret) { adev->in_runpm = false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 23f0067f92e4e206f5ba7414ab1b1f871a5f009d..b803e785d3aff6424f55a505a5bf6fff78dca742 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -585,8 +585,15 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable) if (adev->gfx.gfx_off_req_count == 0 && !adev->gfx.gfx_off_state) { - schedule_delayed_work(&adev->gfx.gfx_off_delay_work, + /* If going to s2idle, no need to wait */ + if (adev->in_s0ix) { + if (!amdgpu_dpm_set_powergating_by_smu(adev, + AMD_IP_BLOCK_TYPE_GFX, true)) + adev->gfx.gfx_off_state = true; + } else { + schedule_delayed_work(&adev->gfx.gfx_off_delay_work, delay); + } } } else { if (adev->gfx.gfx_off_req_count == 0) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 3bf0e893c07dfb9b4a875a0944be3973f1202646..f34bc9bb7045a0e0f7d83a5cf1daa5403471d95c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -301,12 +301,15 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job) dma_fence_set_error(finished, -ECANCELED); if (finished->error < 0) { - DRM_INFO("Skip scheduling IBs!\n"); + dev_dbg(adev->dev, "Skip scheduling IBs in ring(%s)", + ring->name); } else { r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs, job, &fence); if (r) - DRM_ERROR("Error scheduling IBs (%d)\n", r); + dev_err(adev->dev, + "Error scheduling IBs (%d) in ring(%s)", r, + ring->name); } job->job_run_counter++; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index cde2fd2f7117155d89158d0de5b9dcaba4bc1a94..9a111988b7f156992c468c06a294bf68986fe57d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1222,14 +1222,18 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer, * amdgpu_bo_move_notify - notification about a memory move * @bo: pointer to a buffer object * @evict: if this move is evicting the buffer from the graphics address space + * @new_mem: new resource for backing the BO * * Marks the corresponding &amdgpu_bo buffer object as invalid, also performs * bookkeeping. * TTM driver callback which is called when ttm moves a buffer. */ -void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict) +void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, + bool evict, + struct ttm_resource *new_mem) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); + struct ttm_resource *old_mem = bo->resource; struct amdgpu_bo *abo; if (!amdgpu_bo_is_amdgpu_bo(bo)) @@ -1241,12 +1245,12 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict) amdgpu_bo_kunmap(abo); if (abo->tbo.base.dma_buf && !abo->tbo.base.import_attach && - bo->resource->mem_type != TTM_PL_SYSTEM) + old_mem && old_mem->mem_type != TTM_PL_SYSTEM) dma_buf_move_notify(abo->tbo.base.dma_buf); - /* remember the eviction */ - if (evict) - atomic64_inc(&adev->num_evictions); + /* move_notify is called before move happens */ + trace_amdgpu_bo_move(abo, new_mem ? new_mem->mem_type : -1, + old_mem ? old_mem->mem_type : -1); } void amdgpu_bo_get_memory(struct amdgpu_bo *bo, uint64_t *vram_mem, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index 2ada421e79e4f492b3ab713740aa46a2ad02cf65..6dcd7bab42fbb2c0a0c0e2448a203ce5ccbc4216 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -312,7 +312,9 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata, int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer, size_t buffer_size, uint32_t *metadata_size, uint64_t *flags); -void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict); +void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, + bool evict, + struct ttm_resource *new_mem); void amdgpu_bo_release_notify(struct ttm_buffer_object *bo); vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo); void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 9fe2eae88ec1704567bee9afd54b8bd3832058e2..ee83d282b49a84b42ad3841601a1fe3972e23e04 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -974,6 +974,9 @@ int amdgpu_ras_query_error_status(struct amdgpu_device *adev, if (!obj) return -EINVAL; + if (!info || info->head.block == AMDGPU_RAS_BLOCK_COUNT) + return -EINVAL; + if (info->head.block == AMDGPU_RAS_BLOCK__UMC) { amdgpu_ras_get_ecc_info(adev, &err_data); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 158b791883f03e7392d663693e7ba9512064a2b1..7afefaa3742763d032b3b54be8ca841ae768b13f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -483,14 +483,16 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, if (!old_mem || (old_mem->mem_type == TTM_PL_SYSTEM && bo->ttm == NULL)) { + amdgpu_bo_move_notify(bo, evict, new_mem); ttm_bo_move_null(bo, new_mem); - goto out; + return 0; } if (old_mem->mem_type == TTM_PL_SYSTEM && (new_mem->mem_type == TTM_PL_TT || new_mem->mem_type == AMDGPU_PL_PREEMPT)) { + amdgpu_bo_move_notify(bo, evict, new_mem); ttm_bo_move_null(bo, new_mem); - goto out; + return 0; } if ((old_mem->mem_type == TTM_PL_TT || old_mem->mem_type == AMDGPU_PL_PREEMPT) && @@ -500,9 +502,10 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, return r; amdgpu_ttm_backend_unbind(bo->bdev, bo->ttm); + amdgpu_bo_move_notify(bo, evict, new_mem); ttm_resource_free(bo, &bo->resource); ttm_bo_assign_mem(bo, new_mem); - goto out; + return 0; } if (old_mem->mem_type == AMDGPU_PL_GDS || @@ -512,8 +515,9 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, new_mem->mem_type == AMDGPU_PL_GWS || new_mem->mem_type == AMDGPU_PL_OA) { /* Nothing to save here */ + amdgpu_bo_move_notify(bo, evict, new_mem); ttm_bo_move_null(bo, new_mem); - goto out; + return 0; } if (bo->type == ttm_bo_type_device && @@ -525,22 +529,23 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, abo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; } - if (adev->mman.buffer_funcs_enabled) { - if (((old_mem->mem_type == TTM_PL_SYSTEM && - new_mem->mem_type == TTM_PL_VRAM) || - (old_mem->mem_type == TTM_PL_VRAM && - new_mem->mem_type == TTM_PL_SYSTEM))) { - hop->fpfn = 0; - hop->lpfn = 0; - hop->mem_type = TTM_PL_TT; - hop->flags = TTM_PL_FLAG_TEMPORARY; - return -EMULTIHOP; - } + if (adev->mman.buffer_funcs_enabled && + ((old_mem->mem_type == TTM_PL_SYSTEM && + new_mem->mem_type == TTM_PL_VRAM) || + (old_mem->mem_type == TTM_PL_VRAM && + new_mem->mem_type == TTM_PL_SYSTEM))) { + hop->fpfn = 0; + hop->lpfn = 0; + hop->mem_type = TTM_PL_TT; + hop->flags = TTM_PL_FLAG_TEMPORARY; + return -EMULTIHOP; + } + amdgpu_bo_move_notify(bo, evict, new_mem); + if (adev->mman.buffer_funcs_enabled) r = amdgpu_move_blit(bo, evict, new_mem, old_mem); - } else { + else r = -ENODEV; - } if (r) { /* Check that all memory is CPU accessible */ @@ -555,11 +560,10 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, return r; } - trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type); -out: - /* update statistics */ + /* update statistics after the move */ + if (evict) + atomic64_inc(&adev->num_evictions); atomic64_add(bo->base.size, &adev->num_bytes_moved); - amdgpu_bo_move_notify(bo, evict); return 0; } @@ -838,6 +842,7 @@ static void amdgpu_ttm_gart_bind(struct amdgpu_device *adev, amdgpu_gart_bind(adev, gtt->offset, ttm->num_pages, gtt->ttm.dma_address, flags); } + gtt->bound = true; } /* @@ -1504,7 +1509,7 @@ static int amdgpu_ttm_access_memory(struct ttm_buffer_object *bo, static void amdgpu_bo_delete_mem_notify(struct ttm_buffer_object *bo) { - amdgpu_bo_move_notify(bo, false); + amdgpu_bo_move_notify(bo, false, NULL); } static struct ttm_device_funcs amdgpu_bo_driver = { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 4c661e024e13d0e2dff4a681cbf4b2f0cc77cad8..49a47807c42d6dd7020603914691737717f8f116 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1400,6 +1400,37 @@ static void amdgpu_vm_bo_insert_map(struct amdgpu_device *adev, trace_amdgpu_vm_bo_map(bo_va, mapping); } +/* Validate operation parameters to prevent potential abuse */ +static int amdgpu_vm_verify_parameters(struct amdgpu_device *adev, + struct amdgpu_bo *bo, + uint64_t saddr, + uint64_t offset, + uint64_t size) +{ + uint64_t tmp, lpfn; + + if (saddr & AMDGPU_GPU_PAGE_MASK + || offset & AMDGPU_GPU_PAGE_MASK + || size & AMDGPU_GPU_PAGE_MASK) + return -EINVAL; + + if (check_add_overflow(saddr, size, &tmp) + || check_add_overflow(offset, size, &tmp) + || size == 0 /* which also leads to end < begin */) + return -EINVAL; + + /* make sure object fit at this offset */ + if (bo && offset + size > amdgpu_bo_size(bo)) + return -EINVAL; + + /* Ensure last pfn not exceed max_pfn */ + lpfn = (saddr + size - 1) >> AMDGPU_GPU_PAGE_SHIFT; + if (lpfn >= adev->vm_manager.max_pfn) + return -EINVAL; + + return 0; +} + /** * amdgpu_vm_bo_map - map bo inside a vm * @@ -1426,21 +1457,14 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, struct amdgpu_bo *bo = bo_va->base.bo; struct amdgpu_vm *vm = bo_va->base.vm; uint64_t eaddr; + int r; - /* validate the parameters */ - if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || size & ~PAGE_MASK) - return -EINVAL; - if (saddr + size <= saddr || offset + size <= offset) - return -EINVAL; - - /* make sure object fit at this offset */ - eaddr = saddr + size - 1; - if ((bo && offset + size > amdgpu_bo_size(bo)) || - (eaddr >= adev->vm_manager.max_pfn << AMDGPU_GPU_PAGE_SHIFT)) - return -EINVAL; + r = amdgpu_vm_verify_parameters(adev, bo, saddr, offset, size); + if (r) + return r; saddr /= AMDGPU_GPU_PAGE_SIZE; - eaddr /= AMDGPU_GPU_PAGE_SIZE; + eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE; tmp = amdgpu_vm_it_iter_first(&vm->va, saddr, eaddr); if (tmp) { @@ -1493,17 +1517,9 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev, uint64_t eaddr; int r; - /* validate the parameters */ - if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || size & ~PAGE_MASK) - return -EINVAL; - if (saddr + size <= saddr || offset + size <= offset) - return -EINVAL; - - /* make sure object fit at this offset */ - eaddr = saddr + size - 1; - if ((bo && offset + size > amdgpu_bo_size(bo)) || - (eaddr >= adev->vm_manager.max_pfn << AMDGPU_GPU_PAGE_SHIFT)) - return -EINVAL; + r = amdgpu_vm_verify_parameters(adev, bo, saddr, offset, size); + if (r) + return r; /* Allocate all the needed memory */ mapping = kmalloc(sizeof(*mapping), GFP_KERNEL); @@ -1517,7 +1533,7 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev, } saddr /= AMDGPU_GPU_PAGE_SIZE; - eaddr /= AMDGPU_GPU_PAGE_SIZE; + eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE; mapping->start = saddr; mapping->last = eaddr; @@ -1604,10 +1620,14 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev, struct amdgpu_bo_va_mapping *before, *after, *tmp, *next; LIST_HEAD(removed); uint64_t eaddr; + int r; + + r = amdgpu_vm_verify_parameters(adev, NULL, saddr, 0, size); + if (r) + return r; - eaddr = saddr + size - 1; saddr /= AMDGPU_GPU_PAGE_SIZE; - eaddr /= AMDGPU_GPU_PAGE_SIZE; + eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE; /* Allocate all the needed memory */ before = kzalloc(sizeof(*before), GFP_KERNEL); diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c index 1c5d9388ad0bb930a0aab5df6e7c6f6b5ebe1bda..cb6eb47aab65bea2a300132ce385d684575e654e 100644 --- a/drivers/gpu/drm/amd/amdgpu/atom.c +++ b/drivers/gpu/drm/amd/amdgpu/atom.c @@ -313,7 +313,7 @@ static uint32_t atom_get_src_int(atom_exec_context *ctx, uint8_t attr, DEBUG("IMM 0x%02X\n", val); return val; } - return 0; + break; case ATOM_ARG_PLL: idx = U8(*ptr); (*ptr)++; diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c index df385ffc97683e8ac2892753bb862aa36a30c852..6578ca1b90afabd8af1c5af0cc1d4527c5272905 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c @@ -204,6 +204,12 @@ static u32 cik_ih_get_wptr(struct amdgpu_device *adev, tmp = RREG32(mmIH_RB_CNTL); tmp |= IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK; WREG32(mmIH_RB_CNTL, tmp); + + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp &= ~IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK; + WREG32(mmIH_RB_CNTL, tmp); } return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c index b8c47e0cf37ad53bcb3f1afe161e6356b91789e3..c19681492efa748bf7b5d92864dbdc61c0351520 100644 --- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c @@ -216,6 +216,11 @@ static u32 cz_ih_get_wptr(struct amdgpu_device *adev, tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32(mmIH_RB_CNTL, tmp); + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32(mmIH_RB_CNTL, tmp); out: return (wptr & ih->ptr_mask); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 66a6f7a37ebcf2937ceae0893d80c0d34963f56d..5a5787bfbce7f746461374f12d5d00148bb5da79 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -1531,44 +1531,70 @@ static void gfx_v11_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, WREG32_SOC15(GC, 0, regGRBM_GFX_INDEX, data); } -static u32 gfx_v11_0_get_rb_active_bitmap(struct amdgpu_device *adev) +static u32 gfx_v11_0_get_sa_active_bitmap(struct amdgpu_device *adev) { - u32 data, mask; + u32 gc_disabled_sa_mask, gc_user_disabled_sa_mask, sa_mask; + + gc_disabled_sa_mask = RREG32_SOC15(GC, 0, regCC_GC_SA_UNIT_DISABLE); + gc_disabled_sa_mask = REG_GET_FIELD(gc_disabled_sa_mask, + CC_GC_SA_UNIT_DISABLE, + SA_DISABLE); + gc_user_disabled_sa_mask = RREG32_SOC15(GC, 0, regGC_USER_SA_UNIT_DISABLE); + gc_user_disabled_sa_mask = REG_GET_FIELD(gc_user_disabled_sa_mask, + GC_USER_SA_UNIT_DISABLE, + SA_DISABLE); + sa_mask = amdgpu_gfx_create_bitmask(adev->gfx.config.max_sh_per_se * + adev->gfx.config.max_shader_engines); - data = RREG32_SOC15(GC, 0, regCC_RB_BACKEND_DISABLE); - data |= RREG32_SOC15(GC, 0, regGC_USER_RB_BACKEND_DISABLE); + return sa_mask & (~(gc_disabled_sa_mask | gc_user_disabled_sa_mask)); +} - data &= CC_RB_BACKEND_DISABLE__BACKEND_DISABLE_MASK; - data >>= GC_USER_RB_BACKEND_DISABLE__BACKEND_DISABLE__SHIFT; +static u32 gfx_v11_0_get_rb_active_bitmap(struct amdgpu_device *adev) +{ + u32 gc_disabled_rb_mask, gc_user_disabled_rb_mask; + u32 rb_mask; - mask = amdgpu_gfx_create_bitmask(adev->gfx.config.max_backends_per_se / - adev->gfx.config.max_sh_per_se); + gc_disabled_rb_mask = RREG32_SOC15(GC, 0, regCC_RB_BACKEND_DISABLE); + gc_disabled_rb_mask = REG_GET_FIELD(gc_disabled_rb_mask, + CC_RB_BACKEND_DISABLE, + BACKEND_DISABLE); + gc_user_disabled_rb_mask = RREG32_SOC15(GC, 0, regGC_USER_RB_BACKEND_DISABLE); + gc_user_disabled_rb_mask = REG_GET_FIELD(gc_user_disabled_rb_mask, + GC_USER_RB_BACKEND_DISABLE, + BACKEND_DISABLE); + rb_mask = amdgpu_gfx_create_bitmask(adev->gfx.config.max_backends_per_se * + adev->gfx.config.max_shader_engines); - return (~data) & mask; + return rb_mask & (~(gc_disabled_rb_mask | gc_user_disabled_rb_mask)); } static void gfx_v11_0_setup_rb(struct amdgpu_device *adev) { - int i, j; - u32 data; - u32 active_rbs = 0; - u32 rb_bitmap_width_per_sh = adev->gfx.config.max_backends_per_se / - adev->gfx.config.max_sh_per_se; + u32 rb_bitmap_width_per_sa; + u32 max_sa; + u32 active_sa_bitmap; + u32 global_active_rb_bitmap; + u32 active_rb_bitmap = 0; + u32 i; - mutex_lock(&adev->grbm_idx_mutex); - for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { - for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { - gfx_v11_0_select_se_sh(adev, i, j, 0xffffffff); - data = gfx_v11_0_get_rb_active_bitmap(adev); - active_rbs |= data << ((i * adev->gfx.config.max_sh_per_se + j) * - rb_bitmap_width_per_sh); - } + /* query sa bitmap from SA_UNIT_DISABLE registers */ + active_sa_bitmap = gfx_v11_0_get_sa_active_bitmap(adev); + /* query rb bitmap from RB_BACKEND_DISABLE registers */ + global_active_rb_bitmap = gfx_v11_0_get_rb_active_bitmap(adev); + + /* generate active rb bitmap according to active sa bitmap */ + max_sa = adev->gfx.config.max_shader_engines * + adev->gfx.config.max_sh_per_se; + rb_bitmap_width_per_sa = adev->gfx.config.max_backends_per_se / + adev->gfx.config.max_sh_per_se; + for (i = 0; i < max_sa; i++) { + if (active_sa_bitmap & (1 << i)) + active_rb_bitmap |= (0x3 << (i * rb_bitmap_width_per_sa)); } - gfx_v11_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); - mutex_unlock(&adev->grbm_idx_mutex); - adev->gfx.config.backend_enable_mask = active_rbs; - adev->gfx.config.num_rbs = hweight32(active_rbs); + active_rb_bitmap &= global_active_rb_bitmap; + adev->gfx.config.backend_enable_mask = active_rb_bitmap; + adev->gfx.config.num_rbs = hweight32(active_rb_bitmap); } #define DEFAULT_SH_MEM_BASES (0x6000) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 84ca601f7d5f3aa8c7d9719948fbe6b1b492af29..195b2989235433623a11317acc1c7335e506a970 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -3064,6 +3064,14 @@ static int gfx_v9_0_cp_gfx_start(struct amdgpu_device *adev) gfx_v9_0_cp_gfx_enable(adev, true); + /* Now only limit the quirk on the APU gfx9 series and already + * confirmed that the APU gfx10/gfx11 needn't such update. + */ + if (adev->flags & AMD_IS_APU && + adev->in_s3 && !adev->suspend_complete) { + DRM_INFO(" Will skip the CSB packet resubmit\n"); + return 0; + } r = amdgpu_ring_alloc(ring, gfx_v9_0_get_csb_size(adev) + 4 + 3); if (r) { DRM_ERROR("amdgpu: cp failed to lock ring (%d).\n", r); diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c index aecad530b10a61289f9e2413612bbf58a33cec22..2c02ae69883d2bb86bec8e1d1fb521f8481d7ebb 100644 --- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c @@ -215,6 +215,11 @@ static u32 iceland_ih_get_wptr(struct amdgpu_device *adev, tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32(mmIH_RB_CNTL, tmp); + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32(mmIH_RB_CNTL, tmp); out: return (wptr & ih->ptr_mask); diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c index 7cd79a3844b243fb95267d198ef2dc42f7c10f7f..657e4ca6f9dd2f7489b497c933767e3508db5ac5 100644 --- a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c @@ -417,6 +417,12 @@ static u32 ih_v6_0_get_wptr(struct amdgpu_device *adev, tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl); tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); out: return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c index eec13cb5bf75828e45c88c7715b0afb157d7605d..84e8e8b008ef616ff31fb20be07dab2454486b62 100644 --- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c @@ -442,6 +442,12 @@ static u32 navi10_ih_get_wptr(struct amdgpu_device *adev, tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl); tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); out: return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index 856db876af141d23d020e9710df5c94d2bcef22c..c7af36370b0deda3ea13ec8fbc240a04c4173777 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -345,17 +345,21 @@ static void sdma_v5_2_ring_emit_hdp_flush(struct amdgpu_ring *ring) u32 ref_and_mask = 0; const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio.hdp_flush_reg; - ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 << ring->me; - - amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) | - SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(1) | - SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* == */ - amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_done_offset(adev)) << 2); - amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_req_offset(adev)) << 2); - amdgpu_ring_write(ring, ref_and_mask); /* reference */ - amdgpu_ring_write(ring, ref_and_mask); /* mask */ - amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) | - SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10)); /* retry count, poll interval */ + if (ring->me > 1) { + amdgpu_asic_flush_hdp(adev, ring); + } else { + ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 << ring->me; + + amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) | + SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(1) | + SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* == */ + amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_done_offset(adev)) << 2); + amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_req_offset(adev)) << 2); + amdgpu_ring_write(ring, ref_and_mask); /* reference */ + amdgpu_ring_write(ring, ref_and_mask); /* mask */ + amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) | + SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10)); /* retry count, poll interval */ + } } /** diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c b/drivers/gpu/drm/amd/amdgpu/si_ih.c index 9a24f17a57502edaa744451bd312dfcd8b3d678c..cada9f300a7f510a3f025c3ed17c87aedcbbaeb5 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c @@ -119,6 +119,12 @@ static u32 si_ih_get_wptr(struct amdgpu_device *adev, tmp = RREG32(IH_RB_CNTL); tmp |= IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK; WREG32(IH_RB_CNTL, tmp); + + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp &= ~IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK; + WREG32(IH_RB_CNTL, tmp); } return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 811dd3ea63620ec9b273c2be69bb921aa7115deb..c373a2a3248eb74cf62e2b1cda97cbc6be571928 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -584,11 +584,34 @@ soc15_asic_reset_method(struct amdgpu_device *adev) return AMD_RESET_METHOD_MODE1; } +static bool soc15_need_reset_on_resume(struct amdgpu_device *adev) +{ + u32 sol_reg; + + sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81); + + /* Will reset for the following suspend abort cases. + * 1) Only reset limit on APU side, dGPU hasn't checked yet. + * 2) S3 suspend abort and TOS already launched. + */ + if (adev->flags & AMD_IS_APU && adev->in_s3 && + !adev->suspend_complete && + sol_reg) + return true; + + return false; +} + static int soc15_asic_reset(struct amdgpu_device *adev) { /* original raven doesn't have full asic reset */ - if ((adev->apu_flags & AMD_APU_IS_RAVEN) || - (adev->apu_flags & AMD_APU_IS_RAVEN2)) + /* On the latest Raven, the GPU reset can be performed + * successfully. So now, temporarily enable it for the + * S3 suspend abort case. + */ + if (((adev->apu_flags & AMD_APU_IS_RAVEN) || + (adev->apu_flags & AMD_APU_IS_RAVEN2)) && + !soc15_need_reset_on_resume(adev)) return 0; switch (soc15_asic_reset_method(adev)) { @@ -1289,6 +1312,10 @@ static int soc15_common_resume(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + if (soc15_need_reset_on_resume(adev)) { + dev_info(adev->dev, "S3 suspend abort case, let's reset ASIC.\n"); + soc15_asic_reset(adev); + } return soc15_common_hw_init(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 56af7b5abac14c41b267d416646df51a720141b8..56cc59629d96b1509c86b15f03c81aee59b97ef9 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -460,10 +460,8 @@ static bool soc21_need_full_reset(struct amdgpu_device *adev) { switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(11, 0, 0): - return amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC); case IP_VERSION(11, 0, 2): case IP_VERSION(11, 0, 3): - return false; default: return true; } @@ -780,10 +778,35 @@ static int soc21_common_suspend(void *handle) return soc21_common_hw_fini(adev); } +static bool soc21_need_reset_on_resume(struct amdgpu_device *adev) +{ + u32 sol_reg1, sol_reg2; + + /* Will reset for the following suspend abort cases. + * 1) Only reset dGPU side. + * 2) S3 suspend got aborted and TOS is active. + */ + if (!(adev->flags & AMD_IS_APU) && adev->in_s3 && + !adev->suspend_complete) { + sol_reg1 = RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_81); + msleep(100); + sol_reg2 = RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_81); + + return (sol_reg1 != sol_reg2); + } + + return false; +} + static int soc21_common_resume(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + if (soc21_need_reset_on_resume(adev)) { + dev_info(adev->dev, "S3 suspend aborted, resetting..."); + soc21_asic_reset(adev); + } + return soc21_common_hw_init(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c index b08905d1c00f06c65913964cb0e6b8b0ba0e8261..07a5d95be07f5fff18858a4ce2d361457b22dda7 100644 --- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c @@ -219,6 +219,12 @@ static u32 tonga_ih_get_wptr(struct amdgpu_device *adev, tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32(mmIH_RB_CNTL, tmp); + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32(mmIH_RB_CNTL, tmp); + out: return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c index 1e83db0c5438d0c07b27bf1540ad6b4bdf2bc61e..74c94df42345512e78d0ff2c8620cd2d00ca5777 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c @@ -373,6 +373,12 @@ static u32 vega10_ih_get_wptr(struct amdgpu_device *adev, tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + out: return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c index 59dfca093155c6a1cf5bd58b8f62a31e2adf4738..f1ba76c35cd6eec109701fc60696e41ab1da61de 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c @@ -424,6 +424,12 @@ static u32 vega20_ih_get_wptr(struct amdgpu_device *adev, tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + out: return (wptr & ih->ptr_mask); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index e191d38f3da62c83eed7735cdc2a29bf90254805..b0f475d51ae7eec179c197d93feca4ad779dd5e9 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -765,8 +765,8 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp, * nodes, but not more than args->num_of_nodes as that is * the amount of memory allocated by user */ - pa = kzalloc((sizeof(struct kfd_process_device_apertures) * - args->num_of_nodes), GFP_KERNEL); + pa = kcalloc(args->num_of_nodes, sizeof(struct kfd_process_device_apertures), + GFP_KERNEL); if (!pa) return -ENOMEM; @@ -1106,7 +1106,7 @@ static int kfd_ioctl_alloc_memory_of_gpu(struct file *filep, goto err_unlock; } offset = dev->adev->rmmio_remap.bus_addr; - if (!offset) { + if (!offset || (PAGE_SIZE > 4096)) { err = -ENOMEM; goto err_unlock; } @@ -2215,7 +2215,7 @@ static int criu_restore_memory_of_gpu(struct kfd_process_device *pdd, return -EINVAL; } offset = pdd->dev->adev->rmmio_remap.bus_addr; - if (!offset) { + if (!offset || (PAGE_SIZE > 4096)) { pr_err("amdgpu_amdkfd_get_mmio_remap_phys_addr failed\n"); return -ENOMEM; } @@ -2886,6 +2886,9 @@ static int kfd_mmio_mmap(struct kfd_dev *dev, struct kfd_process *process, if (vma->vm_end - vma->vm_start != PAGE_SIZE) return -EINVAL; + if (PAGE_SIZE > 4096) + return -EINVAL; + address = dev->adev->rmmio_remap.bus_addr; vma->vm_flags |= VM_IO | VM_DONTCOPY | VM_DONTEXPAND | VM_NORESERVE | diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 0b87034d9dd512cbaacad61d6d7481d5afaabfcf..1b7b29426480479e98722524731daf90b7195b01 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1805,6 +1805,7 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm, pr_err("HIQ MQD's queue_doorbell_id0 is not 0, Queue preemption time out\n"); while (halt_if_hws_hang) schedule(); + kfd_hws_hang(dqm); return -ETIME; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index ec8a576ac5a9e1191a8bd68aa013cfda2add4d8b..3c7d267f2a07bb0ef43a4a416552753e3c40f5bb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -1349,7 +1349,7 @@ void kfd_flush_tlb(struct kfd_process_device *pdd, enum TLB_FLUSH_TYPE type); static inline bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev) { - return KFD_GC_VERSION(dev) > IP_VERSION(9, 4, 2) || + return KFD_GC_VERSION(dev) >= IP_VERSION(9, 4, 2) || (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1) && dev->sdma_fw_version >= 18) || KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 0); } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index f02e509d5facb2550ea99593cc574a5a747af764..ff460c9802eb2e27ed41479a4a287957391cf66d 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2255,6 +2255,7 @@ static int dm_sw_fini(void *handle) if (adev->dm.dmub_srv) { dmub_srv_destroy(adev->dm.dmub_srv); + kfree(adev->dm.dmub_srv); adev->dm.dmub_srv = NULL; } @@ -5937,6 +5938,7 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, bool scale = dm_state ? (dm_state->scaling != RMX_OFF) : false; int mode_refresh; int preferred_refresh = 0; + enum color_transfer_func tf = TRANSFER_FUNC_UNKNOWN; #if defined(CONFIG_DRM_AMD_DC_DCN) struct dsc_dec_dpcd_caps dsc_caps; #endif @@ -6001,7 +6003,9 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, if (recalculate_timing) { freesync_mode = get_highest_refresh_rate_mode(aconnector, false); drm_mode_copy(&saved_mode, &mode); + saved_mode.picture_aspect_ratio = mode.picture_aspect_ratio; drm_mode_copy(&mode, freesync_mode); + mode.picture_aspect_ratio = saved_mode.picture_aspect_ratio; } else { decide_crtc_timing_for_drm_display_mode( &mode, preferred_mode, scale); @@ -6068,7 +6072,9 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, if (stream->link->dpcd_caps.dprx_feature.bits.VSC_SDP_COLORIMETRY_SUPPORTED) stream->use_vsc_sdp_for_colorimetry = true; } - mod_build_vsc_infopacket(stream, &stream->vsc_infopacket, stream->output_color_space); + if (stream->out_transfer_func->tf == TRANSFER_FUNCTION_GAMMA22) + tf = TRANSFER_FUNC_GAMMA_22; + mod_build_vsc_infopacket(stream, &stream->vsc_infopacket, stream->output_color_space, tf); aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY; } @@ -10117,11 +10123,13 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, } #if defined(CONFIG_DRM_AMD_DC_DCN) - ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars); - if (ret) { - DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n"); - ret = -EINVAL; - goto fail; + if (dc_resource_is_dsc_encoding_supported(dc)) { + ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars); + if (ret) { + DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n"); + ret = -EINVAL; + goto fail; + } } ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context, vars); @@ -10495,14 +10503,23 @@ void amdgpu_dm_update_freesync_caps(struct drm_connector *connector, if (range->flags != 1) continue; - amdgpu_dm_connector->min_vfreq = range->min_vfreq; - amdgpu_dm_connector->max_vfreq = range->max_vfreq; - amdgpu_dm_connector->pixel_clock_mhz = - range->pixel_clock_mhz * 10; - connector->display_info.monitor_range.min_vfreq = range->min_vfreq; connector->display_info.monitor_range.max_vfreq = range->max_vfreq; + if (edid->revision >= 4) { + if (data->pad2 & DRM_EDID_RANGE_OFFSET_MIN_VFREQ) + connector->display_info.monitor_range.min_vfreq += 255; + if (data->pad2 & DRM_EDID_RANGE_OFFSET_MAX_VFREQ) + connector->display_info.monitor_range.max_vfreq += 255; + } + + amdgpu_dm_connector->min_vfreq = + connector->display_info.monitor_range.min_vfreq; + amdgpu_dm_connector->max_vfreq = + connector->display_info.monitor_range.max_vfreq; + amdgpu_dm_connector->pixel_clock_mhz = + range->pixel_clock_mhz * 10; + break; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index ee242d9d8b06011c2d8307a35d96d24c24d220bd..ff7dd17ad0763aca5e639dd577a80bc13cf1ebb4 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -1358,7 +1358,7 @@ static ssize_t dp_dsc_clock_en_read(struct file *f, char __user *buf, const uint32_t rd_buf_size = 10; struct pipe_ctx *pipe_ctx; ssize_t result = 0; - int i, r, str_len = 30; + int i, r, str_len = 10; rd_buf = kcalloc(rd_buf_size, sizeof(char), GFP_KERNEL); diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index 93e40e0a150876fbcc17f640c832dcc637a7041c..4d2590964a204acc70c86cf8a52939b799927f21 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -2962,6 +2962,7 @@ static enum bp_result construct_integrated_info( result = get_integrated_info_v2_1(bp, info); break; case 2: + case 3: result = get_integrated_info_v2_2(bp, info); break; default: diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c index 187f5b27fdc80dec1545a7c75d5622dd04d4e368..29d2003fb7129ac2aacc1e43169288ed6d2cd530 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c @@ -112,20 +112,25 @@ static int dcn316_get_active_display_cnt_wa( return display_count; } -static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable) +static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, + bool safe_to_lower, bool disable) { struct dc *dc = clk_mgr_base->ctx->dc; int i; for (i = 0; i < dc->res_pool->pipe_count; ++i) { - struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + struct pipe_ctx *pipe = safe_to_lower + ? &context->res_ctx.pipe_ctx[i] + : &dc->current_state->res_ctx.pipe_ctx[i]; if (pipe->top_pipe || pipe->prev_odm_pipe) continue; - if (pipe->stream && (pipe->stream->dpms_off || pipe->plane_state == NULL || - dc_is_virtual_signal(pipe->stream->signal))) { + if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal) || + !pipe->stream->link_enc)) { if (disable) { - pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); + if (pipe->stream_res.tg && pipe->stream_res.tg->funcs->immediate_disable_crtc) + pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); + reset_sync_context_for_pipe(dc, context, i); } else pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg); @@ -222,11 +227,11 @@ static void dcn316_update_clocks(struct clk_mgr *clk_mgr_base, } if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) { - dcn316_disable_otg_wa(clk_mgr_base, context, true); + dcn316_disable_otg_wa(clk_mgr_base, context, safe_to_lower, true); clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz; dcn316_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz); - dcn316_disable_otg_wa(clk_mgr_base, context, false); + dcn316_disable_otg_wa(clk_mgr_base, context, safe_to_lower, false); update_dispclk = true; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dpcd.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dpcd.c index af110bf9470fabff86d7433614c68073d48e7f41..aefca9756dbe863977c23ba0059c6bd3a50a0ecd 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dpcd.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dpcd.c @@ -202,7 +202,7 @@ enum dc_status core_link_read_dpcd( uint32_t extended_size; /* size of the remaining partitioned address space */ uint32_t size_left_to_read; - enum dc_status status; + enum dc_status status = DC_ERROR_UNEXPECTED; /* size of the next partition to be read from */ uint32_t partition_size; uint32_t data_index = 0; @@ -231,7 +231,7 @@ enum dc_status core_link_write_dpcd( { uint32_t partition_size; uint32_t data_index = 0; - enum dc_status status; + enum dc_status status = DC_ERROR_UNEXPECTED; while (size) { partition_size = dpcd_get_next_partition_size(address, size); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 66923f51037a3f2c481c5457362d595201353e22..e2f80cd0ca8cbd8ade8d6ac8a493c4e45a6e1dbb 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -3038,6 +3038,12 @@ static void set_avi_info_frame( hdmi_info.bits.C0_C1 = COLORIMETRY_EXTENDED; } + if (pixel_encoding && color_space == COLOR_SPACE_2020_YCBCR && + stream->out_transfer_func->tf == TRANSFER_FUNCTION_GAMMA22) { + hdmi_info.bits.EC0_EC2 = 0; + hdmi_info.bits.C0_C1 = COLORIMETRY_ITU709; + } + /* TODO: un-hardcode aspect ratio */ aspect = stream->timing.aspect_ratio; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 009b5861a3fecd57b4a157eced924d6c23556cc1..d6c5d48c878eca8b97f5d0995ed67c117b901975 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -1854,6 +1854,9 @@ bool dcn10_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx, { struct dpp *dpp = pipe_ctx->plane_res.dpp; + if (!stream) + return false; + if (dpp == NULL) return false; @@ -1876,8 +1879,8 @@ bool dcn10_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx, } else dpp->funcs->dpp_program_regamma_pwl(dpp, NULL, OPP_REGAMMA_BYPASS); - if (stream != NULL && stream->ctx != NULL && - stream->out_transfer_func != NULL) { + if (stream->ctx && + stream->out_transfer_func) { log_tf(stream->ctx, stream->out_transfer_func, dpp->regamma_params.hw_points_num); diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index 72bec33e371f3848baf2f955419c9491f0884399..0225b2c96041d72832292c303c87b65a77530e94 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -651,10 +651,20 @@ void dcn30_set_avmute(struct pipe_ctx *pipe_ctx, bool enable) if (pipe_ctx == NULL) return; - if (dc_is_hdmi_signal(pipe_ctx->stream->signal) && pipe_ctx->stream_res.stream_enc != NULL) + if (dc_is_hdmi_signal(pipe_ctx->stream->signal) && pipe_ctx->stream_res.stream_enc != NULL) { pipe_ctx->stream_res.stream_enc->funcs->set_avmute( pipe_ctx->stream_res.stream_enc, enable); + + /* Wait for two frame to make sure AV mute is sent out */ + if (enable) { + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + } + } } void dcn30_update_info_frame(struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c index f04595b750abcd0b108be9518b536f9b5b0e32db..5ec3f50a72acdb71f00f4d4a3e8dc2c44f3f0195 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c @@ -1014,7 +1014,7 @@ static struct stream_encoder *dcn301_stream_encoder_create(enum engine_id eng_id vpg = dcn301_vpg_create(ctx, vpg_inst); afmt = dcn301_afmt_create(ctx, afmt_inst); - if (!enc1 || !vpg || !afmt) { + if (!enc1 || !vpg || !afmt || eng_id >= ARRAY_SIZE(stream_enc_regs)) { kfree(enc1); kfree(vpg); kfree(afmt); diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c index 80dfaa4d4d81eefe8df967a10982402a60355bf1..eb3a4624f781bfe5777ac7fa92d73955afd2d89d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c @@ -393,6 +393,12 @@ void dcn31_hpo_dp_link_enc_set_throttled_vcp_size( x), 25)); + // If y rounds up to integer, carry it over to x. + if (y >> 25) { + x += 1; + y = 0; + } + switch (stream_encoder_inst) { case 0: REG_SET_2(DP_DPHY_SYM32_VC_RATE_CNTL0, 0, diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c index a974f86e718a80d60bbb65861c7687a03650c5d9..37c645a882dd8ca0a0319830d2657f8c0f6c29f3 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c @@ -216,9 +216,6 @@ static void optc32_setup_manual_trigger(struct timing_generator *optc) OTG_V_TOTAL_MAX_SEL, 1, OTG_FORCE_LOCK_ON_EVENT, 0, OTG_SET_V_TOTAL_MIN_MASK, (1 << 1)); /* TRIGA */ - - // Setup manual flow control for EOF via TRIG_A - optc->funcs->setup_manual_trigger(optc); } } diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index ca7d2400062137958de2a5d1669ad9b964e8eef8..6c7b286e1123de298a3777e96d589cbb522de968 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -51,8 +51,12 @@ endif endif ifneq ($(CONFIG_FRAME_WARN),0) +ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y) +frame_warn_flag := -Wframe-larger-than=3072 +else frame_warn_flag := -Wframe-larger-than=2048 endif +endif CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags) @@ -60,11 +64,11 @@ ifdef CONFIG_DRM_AMD_DC_DCN CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn10/dcn10_fpu.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/dcn20_fpu.o := $(dml_ccflags) -CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_ccflags) -CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_ccflags) -CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags) diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c index d52cbc0e9b6799047eeff793974e8b136332f59b..5f57bdd597c279aafba3ec08fba973cf61be46a5 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c +++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c @@ -924,7 +924,12 @@ static bool setup_dsc_config( if (!is_dsc_possible) goto done; - dsc_cfg->num_slices_v = pic_height/slice_height; + if (slice_height > 0) { + dsc_cfg->num_slices_v = pic_height / slice_height; + } else { + is_dsc_possible = false; + goto done; + } if (target_bandwidth_kbps > 0) { is_dsc_possible = decide_dsc_target_bpp_x16( diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c index ee67a35c2a8eddab3d27f4403054032aa93c187b..ff930a71e496a94399fe5c05f46cb187f3e1d440 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c @@ -513,6 +513,9 @@ enum mod_hdcp_status mod_hdcp_hdcp2_create_session(struct mod_hdcp *hdcp) hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf; memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory)); + if (!display) + return MOD_HDCP_STATUS_DISPLAY_NOT_FOUND; + hdcp_cmd->in_msg.hdcp2_create_session_v2.display_handle = display->index; if (hdcp->connection.link.adjust.hdcp2.force_type == MOD_HDCP_FORCE_TYPE_0) diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_info_packet.h b/drivers/gpu/drm/amd/display/modules/inc/mod_info_packet.h index 1d8b746b02f248334e966bddf7695304cbcc22ba..edf5845f6a1f77082ac3dc62b00265d2f49f89bb 100644 --- a/drivers/gpu/drm/amd/display/modules/inc/mod_info_packet.h +++ b/drivers/gpu/drm/amd/display/modules/inc/mod_info_packet.h @@ -35,7 +35,8 @@ struct mod_vrr_params; void mod_build_vsc_infopacket(const struct dc_stream_state *stream, struct dc_info_packet *info_packet, - enum dc_color_space cs); + enum dc_color_space cs, + enum color_transfer_func tf); void mod_build_hf_vsif_infopacket(const struct dc_stream_state *stream, struct dc_info_packet *info_packet); diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h b/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h index 4220fd8fdd60ca560cb9eb883afcb03c9c9de014..54cd86060f4d678cf79351160cef9c01c7c43b36 100644 --- a/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h +++ b/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h @@ -57,10 +57,10 @@ void mod_stats_update_event(struct mod_stats *mod_stats, unsigned int length); void mod_stats_update_flip(struct mod_stats *mod_stats, - unsigned long timestamp_in_ns); + unsigned long long timestamp_in_ns); void mod_stats_update_vupdate(struct mod_stats *mod_stats, - unsigned long timestamp_in_ns); + unsigned long long timestamp_in_ns); void mod_stats_update_freesync(struct mod_stats *mod_stats, unsigned int v_total_min, diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c index 27ceba9d6d6581e0def0225644413b1223ac525e..69691058ab89817c6d7edf50fc47c49cd9fcbcbd 100644 --- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c +++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c @@ -132,7 +132,8 @@ enum ColorimetryYCCDP { void mod_build_vsc_infopacket(const struct dc_stream_state *stream, struct dc_info_packet *info_packet, - enum dc_color_space cs) + enum dc_color_space cs, + enum color_transfer_func tf) { unsigned int vsc_packet_revision = vsc_packet_undefined; unsigned int i; @@ -382,6 +383,9 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream, colorimetryFormat = ColorimetryYCC_DP_AdobeYCC; else if (cs == COLOR_SPACE_2020_YCBCR) colorimetryFormat = ColorimetryYCC_DP_ITU2020YCbCr; + + if (cs == COLOR_SPACE_2020_YCBCR && tf == TRANSFER_FUNC_GAMMA_22) + colorimetryFormat = ColorimetryYCC_DP_ITU709; break; default: diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index f175e65b853a001ea1bcc66d8edfd5b726cbc952..34467427c9f97119965d4bb47cb94582f6210bd2 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -294,6 +294,7 @@ struct amd_ip_funcs { int (*hw_init)(void *handle); int (*hw_fini)(void *handle); void (*late_fini)(void *handle); + int (*prepare_suspend)(void *handle); int (*suspend)(void *handle); int (*resume)(void *handle); bool (*is_idle)(void *handle); diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 29f3d8431089e7f7658cd9c9d35c4fa338315cd0..cdb406690b7e7ea9cfedf0b302fce6f2a2ad4bdd 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -2344,6 +2344,7 @@ static ssize_t amdgpu_hwmon_set_pwm1_enable(struct device *dev, { struct amdgpu_device *adev = dev_get_drvdata(dev); int err, ret; + u32 pwm_mode; int value; if (amdgpu_in_reset(adev)) @@ -2355,13 +2356,22 @@ static ssize_t amdgpu_hwmon_set_pwm1_enable(struct device *dev, if (err) return err; + if (value == 0) + pwm_mode = AMD_FAN_CTRL_NONE; + else if (value == 1) + pwm_mode = AMD_FAN_CTRL_MANUAL; + else if (value == 2) + pwm_mode = AMD_FAN_CTRL_AUTO; + else + return -EINVAL; + ret = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (ret < 0) { pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); return ret; } - ret = amdgpu_dpm_set_fan_control_mode(adev, value); + ret = amdgpu_dpm_set_fan_control_mode(adev, pwm_mode); pm_runtime_mark_last_busy(adev_to_drm(adev)->dev); pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c index dc0a6fba7050fbd106049a6ed5c3b4ac54f9620d..ff1032de4f76d1e23b22cb264c7f2ce7f075488c 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c @@ -6925,6 +6925,23 @@ static int si_dpm_enable(struct amdgpu_device *adev) return 0; } +static int si_set_temperature_range(struct amdgpu_device *adev) +{ + int ret; + + ret = si_thermal_enable_alert(adev, false); + if (ret) + return ret; + ret = si_thermal_set_temperature_range(adev, R600_TEMP_RANGE_MIN, R600_TEMP_RANGE_MAX); + if (ret) + return ret; + ret = si_thermal_enable_alert(adev, true); + if (ret) + return ret; + + return ret; +} + static void si_dpm_disable(struct amdgpu_device *adev) { struct rv7xx_power_info *pi = rv770_get_pi(adev); @@ -7608,6 +7625,18 @@ static int si_dpm_process_interrupt(struct amdgpu_device *adev, static int si_dpm_late_init(void *handle) { + int ret; + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + + if (!adev->pm.dpm_enabled) + return 0; + + ret = si_set_temperature_range(adev); + if (ret) + return ret; +#if 0 //TODO ? + si_dpm_powergate_uvd(adev, true); +#endif return 0; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c index 6d9760eac16d8de73480ac9448390b3806a5f671..5de31961319a23761027a8ffb294231267114bca 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c @@ -222,8 +222,18 @@ static int smu_v13_0_4_system_features_control(struct smu_context *smu, bool en) struct amdgpu_device *adev = smu->adev; int ret = 0; - if (!en && !adev->in_s0ix) + if (!en && adev->in_s4) { + /* Adds a GFX reset as workaround just before sending the + * MP1_UNLOAD message to prevent GC/RLC/PMFW from entering + * an invalid state. + */ + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GfxDeviceDriverReset, + SMU_RESET_MODE_2, NULL); + if (ret) + return ret; + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_PrepareMp1ForUnload, NULL); + } return ret; } diff --git a/drivers/gpu/drm/ast/ast_dp.c b/drivers/gpu/drm/ast/ast_dp.c index 56483860306b4b2970aa9ab654444a122fb7f82f..a4a23b9623ad3747b2660c2ca701c6529297a65a 100644 --- a/drivers/gpu/drm/ast/ast_dp.c +++ b/drivers/gpu/drm/ast/ast_dp.c @@ -190,6 +190,7 @@ void ast_dp_set_on_off(struct drm_device *dev, bool on) { struct ast_private *ast = to_ast_private(dev); u8 video_on_off = on; + u32 i = 0; // Video On/Off ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xE3, (u8) ~AST_DP_VIDEO_ENABLE, on); @@ -202,6 +203,8 @@ void ast_dp_set_on_off(struct drm_device *dev, bool on) ASTDP_MIRROR_VIDEO_ENABLE) != video_on_off) { // wait 1 ms mdelay(1); + if (++i > 200) + break; } } } diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c index 7098f125b54a9a3004ea98345f7ec486cc8ae24a..fd32041f82263bebd5d264812a4b31a9d3f7e6f7 100644 --- a/drivers/gpu/drm/drm_buddy.c +++ b/drivers/gpu/drm/drm_buddy.c @@ -332,6 +332,7 @@ alloc_range_bias(struct drm_buddy *mm, u64 start, u64 end, unsigned int order) { + u64 req_size = mm->chunk_size << order; struct drm_buddy_block *block; struct drm_buddy_block *buddy; LIST_HEAD(dfs); @@ -367,6 +368,15 @@ alloc_range_bias(struct drm_buddy *mm, if (drm_buddy_block_is_allocated(block)) continue; + if (block_start < start || block_end > end) { + u64 adjusted_start = max(block_start, start); + u64 adjusted_end = min(block_end, end); + + if (round_down(adjusted_end + 1, req_size) <= + round_up(adjusted_start, req_size)) + continue; + } + if (contains(start, end, block_start, block_end) && order == drm_buddy_block_order(block)) { /* diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c index 7847020de0a494ed7186e541ad59c1f011e6b342..9a65806047b5ed60bd16ebb5129d5069840cf997 100644 --- a/drivers/gpu/drm/drm_client_modeset.c +++ b/drivers/gpu/drm/drm_client_modeset.c @@ -781,6 +781,7 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, unsigned int total_modes_count = 0; struct drm_client_offset *offsets; unsigned int connector_count = 0; + /* points to modes protected by mode_config.mutex */ struct drm_display_mode **modes; struct drm_crtc **crtcs; int i, ret = 0; @@ -849,7 +850,6 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, drm_client_pick_crtcs(client, connectors, connector_count, crtcs, modes, 0, width, height); } - mutex_unlock(&dev->mode_config.mutex); drm_client_modeset_release(client); @@ -879,6 +879,7 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, modeset->y = offset->y; } } + mutex_unlock(&dev->mode_config.mutex); mutex_unlock(&client->modeset_mutex); out: diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index 53e11ed63f0d8a15f255b7b17ab5e615c14dc7c6..f9d0bc419f32947df168fd0509d924e8d34fa2c2 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -2759,7 +2759,7 @@ int drm_mode_getconnector(struct drm_device *dev, void *data, dev->mode_config.max_width, dev->mode_config.max_height); else - drm_dbg_kms(dev, "User-space requested a forced probe on [CONNECTOR:%d:%s] but is not the DRM master, demoting to read-only probe", + drm_dbg_kms(dev, "User-space requested a forced probe on [CONNECTOR:%d:%s] but is not the DRM master, demoting to read-only probe\n", connector->base.id, connector->name); } diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c index bee5066e9227171775273c2eb5e9ef7d9786432c..ad55f179cfb2f1abb468e5a88b4ac966022ab22c 100644 --- a/drivers/gpu/drm/drm_panel.c +++ b/drivers/gpu/drm/drm_panel.c @@ -210,19 +210,24 @@ EXPORT_SYMBOL(drm_panel_disable); * The modes probed from the panel are automatically added to the connector * that the panel is attached to. * - * Return: The number of modes available from the panel on success or a - * negative error code on failure. + * Return: The number of modes available from the panel on success, or 0 on + * failure (no modes). */ int drm_panel_get_modes(struct drm_panel *panel, struct drm_connector *connector) { if (!panel) - return -EINVAL; + return 0; - if (panel->funcs && panel->funcs->get_modes) - return panel->funcs->get_modes(panel, connector); + if (panel->funcs && panel->funcs->get_modes) { + int num; - return -EOPNOTSUPP; + num = panel->funcs->get_modes(panel, connector); + if (num > 0) + return num; + } + + return 0; } EXPORT_SYMBOL(drm_panel_get_modes); diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index d5c15292ae93781335a8e8a441be94f9bb235f04..aa93129c3397e40c67027d2098d8e6dd1a875932 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -117,6 +117,12 @@ static const struct drm_dmi_panel_orientation_data lcd1080x1920_leftside_up = { .orientation = DRM_MODE_PANEL_ORIENTATION_LEFT_UP, }; +static const struct drm_dmi_panel_orientation_data lcd1080x1920_rightside_up = { + .width = 1080, + .height = 1920, + .orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP, +}; + static const struct drm_dmi_panel_orientation_data lcd1200x1920_rightside_up = { .width = 1200, .height = 1920, @@ -279,6 +285,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "G1618-03") }, .driver_data = (void *)&lcd720x1280_rightside_up, + }, { /* GPD Win Mini */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "GPD"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "G1617-01") + }, + .driver_data = (void *)&lcd1080x1920_rightside_up, }, { /* I.T.Works TW891 */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "To be filled by O.E.M."), @@ -336,6 +348,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "IdeaPad Duet 3 10IGL5"), }, .driver_data = (void *)&lcd1200x1920_rightside_up, + }, { /* Lenovo Legion Go 8APU1 */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Legion Go 8APU1"), + }, + .driver_data = (void *)&lcd1600x2560_leftside_up, }, { /* Lenovo Yoga Book X90F / X90L */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Intel Corporation"), diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index eb09e86044c6d4df1cade4dfe0d63099d9f9ab94..68a6d4b0ead75f8d2847311296850615c1ba812c 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -828,7 +828,7 @@ struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev, if (max_segment == 0) max_segment = UINT_MAX; err = sg_alloc_table_from_pages_segment(sg, pages, nr_pages, 0, - nr_pages << PAGE_SHIFT, + (unsigned long)nr_pages << PAGE_SHIFT, max_segment, GFP_KERNEL); if (err) { kfree(sg); diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c index 3b968ad187cf389ad88509a728a378a96db101d2..52dbaf74fe1640f9ac3df2cb244ed59cc117798f 100644 --- a/drivers/gpu/drm/drm_probe_helper.c +++ b/drivers/gpu/drm/drm_probe_helper.c @@ -362,6 +362,13 @@ static int drm_helper_probe_get_modes(struct drm_connector *connector) count = connector_funcs->get_modes(connector); + /* The .get_modes() callback should not return negative values. */ + if (count < 0) { + drm_err(connector->dev, ".get_modes() returned %pe\n", + ERR_PTR(count)); + count = 0; + } + /* * Fallback for when DDC probe failed in drm_get_edid() and thus skipped * override/firmware EDID. diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index da0145bc104a89a029801775120ebc628b2a8c83..8f2737075dc2fee5c4b2b084793ddd372bb5036c 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -980,7 +980,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, uint64_t *points; uint32_t signaled_count, i; - if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) + if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT | + DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE)) lockdep_assert_none_held_once(); points = kmalloc_array(count, sizeof(*points), GFP_KERNEL); @@ -1049,7 +1050,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, * fallthough and try a 0 timeout wait! */ - if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) { + if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT | + DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE)) { for (i = 0; i < count; ++i) drm_syncobj_fence_add_wait(syncobjs[i], &entries[i]); } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c index 1d2b4fb4bcf8b7b6153da65568b6ca04b34a4064..f29952a55c05d84f31ed7ea813c7588ad1cabf27 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c @@ -488,7 +488,7 @@ static const struct drm_driver etnaviv_drm_driver = { .desc = "etnaviv DRM", .date = "20151214", .major = 1, - .minor = 3, + .minor = 4, }; /* diff --git a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c index f2fc645c795695e6db29f242ba8460e9e30fa93a..212e7050c4ba67d02c46b4105679ccba0cb929ad 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c @@ -135,6 +135,9 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { bool etnaviv_fill_identity_from_hwdb(struct etnaviv_gpu *gpu) { struct etnaviv_chip_identity *ident = &gpu->identity; + const u32 product_id = ident->product_id; + const u32 customer_id = ident->customer_id; + const u32 eco_id = ident->eco_id; int i; for (i = 0; i < ARRAY_SIZE(etnaviv_chip_identities); i++) { @@ -148,6 +151,12 @@ bool etnaviv_fill_identity_from_hwdb(struct etnaviv_gpu *gpu) etnaviv_chip_identities[i].eco_id == ~0U)) { memcpy(ident, &etnaviv_chip_identities[i], sizeof(*ident)); + + /* Restore some id values as ~0U aka 'don't care' might been used. */ + ident->product_id = product_id; + ident->customer_id = customer_id; + ident->eco_id = eco_id; + return true; } } diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c index f5e1adfcaa514ee0a84b00b1c7357e7d43a64ecf..fb941a8c99f0f5d9fd4bbc405a307275cb2973fa 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c @@ -316,14 +316,14 @@ static int vidi_get_modes(struct drm_connector *connector) */ if (!ctx->raw_edid) { DRM_DEV_DEBUG_KMS(ctx->dev, "raw_edid is null.\n"); - return -EFAULT; + return 0; } edid_len = (1 + ctx->raw_edid->extensions) * EDID_LENGTH; edid = kmemdup(ctx->raw_edid, edid_len, GFP_KERNEL); if (!edid) { DRM_DEV_DEBUG_KMS(ctx->dev, "failed to allocate edid\n"); - return -ENOMEM; + return 0; } drm_connector_update_edid_property(connector, edid); diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index 1a7194a653ae5d124f33c2b8f4f1d0d8cb3bfe89..be2d9cbaaef2e9528472a0629ba23ae92630de67 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -887,11 +887,11 @@ static int hdmi_get_modes(struct drm_connector *connector) int ret; if (!hdata->ddc_adpt) - return -ENODEV; + return 0; edid = drm_get_edid(connector, hdata->ddc_adpt); if (!edid) - return -ENODEV; + return 0; hdata->dvi_mode = !connector->display_info.is_hdmi; DRM_DEV_DEBUG_KMS(hdata->dev, "%s : width[%d] x height[%d]\n", diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index a70b7061742a83335da61823479003c7cc95f175..efbb0cffd3bc95de5be7adf09476aa3208364322 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -1034,22 +1034,11 @@ parse_lfp_backlight(struct drm_i915_private *i915, panel->vbt.backlight.type = INTEL_BACKLIGHT_DISPLAY_DDI; if (i915->display.vbt.version >= 191) { - size_t exp_size; + const struct lfp_backlight_control_method *method; - if (i915->display.vbt.version >= 236) - exp_size = sizeof(struct bdb_lfp_backlight_data); - else if (i915->display.vbt.version >= 234) - exp_size = EXP_BDB_LFP_BL_DATA_SIZE_REV_234; - else - exp_size = EXP_BDB_LFP_BL_DATA_SIZE_REV_191; - - if (get_blocksize(backlight_data) >= exp_size) { - const struct lfp_backlight_control_method *method; - - method = &backlight_data->backlight_control[panel_type]; - panel->vbt.backlight.type = method->type; - panel->vbt.backlight.controller = method->controller; - } + method = &backlight_data->backlight_control[panel_type]; + panel->vbt.backlight.type = method->type; + panel->vbt.backlight.controller = method->controller; } panel->vbt.backlight.pwm_freq_hz = entry->pwm_freq_hz; @@ -3413,6 +3402,9 @@ static bool intel_bios_encoder_supports_dp_dual_mode(const struct intel_bios_enc { const struct child_device_config *child = &devdata->child; + if (!devdata) + return false; + if (!intel_bios_encoder_supports_dp(devdata) || !intel_bios_encoder_supports_hdmi(devdata)) return false; diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index 25dcdde5feb6939a4fbe09b5968d9e2c67bfa542..5147718f38d6a0033afe033d219bf6d2feb10ebe 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -2152,7 +2152,7 @@ intel_set_cdclk_pre_plane_update(struct intel_atomic_state *state) &new_cdclk_state->actual)) return; - if (pipe == INVALID_PIPE || + if (new_cdclk_state->disable_pipes || old_cdclk_state->actual.cdclk <= new_cdclk_state->actual.cdclk) { drm_WARN_ON(&dev_priv->drm, !new_cdclk_state->base.changed); @@ -2181,7 +2181,7 @@ intel_set_cdclk_post_plane_update(struct intel_atomic_state *state) &new_cdclk_state->actual)) return; - if (pipe != INVALID_PIPE && + if (!new_cdclk_state->disable_pipes && old_cdclk_state->actual.cdclk > new_cdclk_state->actual.cdclk) { drm_WARN_ON(&dev_priv->drm, !new_cdclk_state->base.changed); @@ -2634,6 +2634,7 @@ static struct intel_global_state *intel_cdclk_duplicate_state(struct intel_globa return NULL; cdclk_state->pipe = INVALID_PIPE; + cdclk_state->disable_pipes = false; return &cdclk_state->base; } @@ -2793,6 +2794,8 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state) if (ret) return ret; + new_cdclk_state->disable_pipes = true; + drm_dbg_kms(&dev_priv->drm, "Modeset required for cdclk change\n"); } diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.h b/drivers/gpu/drm/i915/display/intel_cdclk.h index c674879a84a58c765d1cfccc44b17e0f3eb2e240..c4b3e5938bb3feee032e64baabfea0894689cc34 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.h +++ b/drivers/gpu/drm/i915/display/intel_cdclk.h @@ -51,6 +51,9 @@ struct intel_cdclk_state { /* bitmask of active pipes */ u8 active_pipes; + + /* update cdclk with pipes disabled */ + bool disable_pipes; }; int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 706e2d956801daa35e61f368e8ed496debdd38b5..76277eb3eb252c7bf34d9c1a8ef656141ab0b1bb 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -3683,7 +3683,12 @@ static bool m_n_equal(const struct intel_link_m_n *m_n_1, static bool crtcs_port_sync_compatible(const struct intel_crtc_state *crtc_state1, const struct intel_crtc_state *crtc_state2) { + /* + * FIXME the modeset sequence is currently wrong and + * can't deal with bigjoiner + port sync at the same time. + */ return crtc_state1->hw.active && crtc_state2->hw.active && + !crtc_state1->bigjoiner_pipes && !crtc_state2->bigjoiner_pipes && crtc_state1->output_types == crtc_state2->output_types && crtc_state1->output_format == crtc_state2->output_format && crtc_state1->lane_count == crtc_state2->lane_count && diff --git a/drivers/gpu/drm/i915/display/intel_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_vbt_defs.h index a9f44abfc9fc283da886724d9d2447c4b8ad59f4..b50cd0dcabda90ab228578d25e6dbd2219380e28 100644 --- a/drivers/gpu/drm/i915/display/intel_vbt_defs.h +++ b/drivers/gpu/drm/i915/display/intel_vbt_defs.h @@ -897,11 +897,6 @@ struct lfp_brightness_level { u16 reserved; } __packed; -#define EXP_BDB_LFP_BL_DATA_SIZE_REV_191 \ - offsetof(struct bdb_lfp_backlight_data, brightness_level) -#define EXP_BDB_LFP_BL_DATA_SIZE_REV_234 \ - offsetof(struct bdb_lfp_backlight_data, brightness_precision_bits) - struct bdb_lfp_backlight_data { u8 entry_size; struct lfp_backlight_data_entry data[16]; diff --git a/drivers/gpu/drm/i915/display/intel_vrr.c b/drivers/gpu/drm/i915/display/intel_vrr.c index 5eac99021875ed88dc8b19fe16d8d062194fe5e2..6615e4153f37a753eaa22fe12b2b24505765b078 100644 --- a/drivers/gpu/drm/i915/display/intel_vrr.c +++ b/drivers/gpu/drm/i915/display/intel_vrr.c @@ -110,6 +110,13 @@ intel_vrr_compute_config(struct intel_crtc_state *crtc_state, if (!intel_vrr_is_capable(connector)) return; + /* + * FIXME all joined pipes share the same transcoder. + * Need to account for that during VRR toggle/push/etc. + */ + if (crtc_state->bigjoiner_pipes) + return; + if (adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE) return; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index ba14b18d65f380cc75fe2fa7a52b4eff84886e5c..2e7c52c2e47dda5190349b72233b4d187dd0f3d5 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -378,6 +378,9 @@ i915_gem_userptr_release(struct drm_i915_gem_object *obj) { GEM_WARN_ON(obj->userptr.page_ref); + if (!obj->userptr.notifier.mm) + return; + mmu_interval_notifier_remove(&obj->userptr.notifier); obj->userptr.notifier.mm = NULL; } diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c index b0a4a2dbe3ee9a1493d4047daf6298a7345f802d..feb0fc32a19ae495c3f115de6111cdae5504c7d3 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c @@ -253,9 +253,6 @@ static int __engine_park(struct intel_wakeref *wf) intel_engine_park_heartbeat(engine); intel_breadcrumbs_park(engine->breadcrumbs); - /* Must be reset upon idling, or we may miss the busy wakeup. */ - GEM_BUG_ON(engine->sched_engine->queue_priority_hint != INT_MIN); - if (engine->park) engine->park(engine); diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index f903ee1ce06e776140dd9be7d19759fae2da1786..eae138b9f2df38abd081d2ee9ea1e446536728a6 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -3270,6 +3270,9 @@ static void execlists_park(struct intel_engine_cs *engine) { cancel_timer(&engine->execlists.timer); cancel_timer(&engine->execlists.preempt); + + /* Reset upon idling, or we may delay the busy wakeup. */ + WRITE_ONCE(engine->sched_engine->queue_priority_hint, INT_MIN); } static void add_to_engine(struct i915_request *rq) diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index daac2050d77d0440bca30c83ca2d6399f65fc89c..6f531bb61f7e5cb4561fdefc26bdccdd0b2cfb6b 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -2844,8 +2844,7 @@ static int handle_mmio(struct intel_gvt_mmio_table_iter *iter, u32 offset, for (i = start; i < end; i += 4) { p = intel_gvt_find_mmio_info(gvt, i); if (p) { - WARN(1, "dup mmio definition offset %x\n", - info->offset); + WARN(1, "dup mmio definition offset %x\n", i); /* We return -EEXIST here to make GVT-g load fail. * So duplicated MMIO can be found as soon as diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index c8ad8f37e5cfe2b6f5f9b4371082e95634a59924..58a03da16a10fa19bed5c7812b7a2c2a93ba8c76 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -32,6 +32,7 @@ #include "gt/intel_engine.h" #include "gt/intel_engine_heartbeat.h" #include "gt/intel_gt.h" +#include "gt/intel_gt_pm.h" #include "gt/intel_gt_requests.h" #include "i915_drv.h" @@ -98,12 +99,34 @@ static inline struct i915_vma *active_to_vma(struct i915_active *ref) static int __i915_vma_active(struct i915_active *ref) { - return i915_vma_tryget(active_to_vma(ref)) ? 0 : -ENOENT; + struct i915_vma *vma = active_to_vma(ref); + + if (!i915_vma_tryget(vma)) + return -ENOENT; + + /* + * Exclude global GTT VMA from holding a GT wakeref + * while active, otherwise GPU never goes idle. + */ + if (!i915_vma_is_ggtt(vma)) + intel_gt_pm_get(vma->vm->gt); + + return 0; } static void __i915_vma_retire(struct i915_active *ref) { - i915_vma_put(active_to_vma(ref)); + struct i915_vma *vma = active_to_vma(ref); + + if (!i915_vma_is_ggtt(vma)) { + /* + * Since we can be called from atomic contexts, + * use an async variant of intel_gt_pm_put(). + */ + intel_gt_pm_put_async(vma->vm->gt); + } + + i915_vma_put(vma); } static struct i915_vma * @@ -1365,7 +1388,7 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, struct i915_vma_work *work = NULL; struct dma_fence *moving = NULL; struct i915_vma_resource *vma_res = NULL; - intel_wakeref_t wakeref = 0; + intel_wakeref_t wakeref; unsigned int bound; int err; @@ -1385,8 +1408,14 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, if (err) return err; - if (flags & PIN_GLOBAL) - wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm); + /* + * In case of a global GTT, we must hold a runtime-pm wakeref + * while global PTEs are updated. In other cases, we hold + * the rpm reference while the VMA is active. Since runtime + * resume may require allocations, which are forbidden inside + * vm->mutex, get the first rpm wakeref outside of the mutex. + */ + wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm); if (flags & vma->vm->bind_async_flags) { /* lock VM */ @@ -1522,8 +1551,7 @@ err_fence: if (work) dma_fence_work_commit_imm(&work->base); err_rpm: - if (wakeref) - intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref); + intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref); if (moving) dma_fence_put(moving); diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c index 06723b2e9b84785343939542f3cdf81a7249553e..64b6bc2de873ef4d479a56e288e71e889657ce89 100644 --- a/drivers/gpu/drm/imx/parallel-display.c +++ b/drivers/gpu/drm/imx/parallel-display.c @@ -72,14 +72,14 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector) int ret; if (!mode) - return -EINVAL; + return 0; ret = of_get_drm_display_mode(np, &imxpd->mode, &imxpd->bus_flags, OF_USE_NATIVE_MODE); if (ret) { drm_mode_destroy(connector->dev, mode); - return ret; + return 0; } drm_mode_copy(mode, &imxpd->mode); diff --git a/drivers/gpu/drm/lima/lima_gem.c b/drivers/gpu/drm/lima/lima_gem.c index 0f1ca0b0db495c771f8cbd6e079dcf3c36e7d135..d72c5bf4e5ac1019c34c05e69215a03567d23fea 100644 --- a/drivers/gpu/drm/lima/lima_gem.c +++ b/drivers/gpu/drm/lima/lima_gem.c @@ -75,29 +75,34 @@ int lima_heap_alloc(struct lima_bo *bo, struct lima_vm *vm) } else { bo->base.sgt = kmalloc(sizeof(*bo->base.sgt), GFP_KERNEL); if (!bo->base.sgt) { - sg_free_table(&sgt); - return -ENOMEM; + ret = -ENOMEM; + goto err_out0; } } ret = dma_map_sgtable(dev, &sgt, DMA_BIDIRECTIONAL, 0); - if (ret) { - sg_free_table(&sgt); - kfree(bo->base.sgt); - bo->base.sgt = NULL; - return ret; - } + if (ret) + goto err_out1; *bo->base.sgt = sgt; if (vm) { ret = lima_vm_map_bo(vm, bo, old_size >> PAGE_SHIFT); if (ret) - return ret; + goto err_out2; } bo->heap_size = new_size; return 0; + +err_out2: + dma_unmap_sgtable(dev, &sgt, DMA_BIDIRECTIONAL, 0); +err_out1: + kfree(bo->base.sgt); + bo->base.sgt = NULL; +err_out0: + sg_free_table(&sgt); + return ret; } int lima_gem_create_handle(struct drm_device *dev, struct drm_file *file, diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index 558000db4a1006674e7640d193668b4109b9aff8..beaaf44004cfd96f346f398d20d8d614e89619db 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -91,11 +91,13 @@ static void mtk_drm_crtc_finish_page_flip(struct mtk_drm_crtc *mtk_crtc) struct drm_crtc *crtc = &mtk_crtc->base; unsigned long flags; - spin_lock_irqsave(&crtc->dev->event_lock, flags); - drm_crtc_send_vblank_event(crtc, mtk_crtc->event); - drm_crtc_vblank_put(crtc); - mtk_crtc->event = NULL; - spin_unlock_irqrestore(&crtc->dev->event_lock, flags); + if (mtk_crtc->event) { + spin_lock_irqsave(&crtc->dev->event_lock, flags); + drm_crtc_send_vblank_event(crtc, mtk_crtc->event); + drm_crtc_vblank_put(crtc); + mtk_crtc->event = NULL; + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); + } } static void mtk_drm_finish_page_flip(struct mtk_drm_crtc *mtk_crtc) diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index 3e74c7c1b89faa3b91dbf3ab9115c8154f815b2d..d871b1dba083dfef8dc4194d3999f89da7d93616 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -70,8 +70,8 @@ #define DSI_PS_WC 0x3fff #define DSI_PS_SEL (3 << 16) #define PACKED_PS_16BIT_RGB565 (0 << 16) -#define LOOSELY_PS_18BIT_RGB666 (1 << 16) -#define PACKED_PS_18BIT_RGB666 (2 << 16) +#define PACKED_PS_18BIT_RGB666 (1 << 16) +#define LOOSELY_PS_24BIT_RGB666 (2 << 16) #define PACKED_PS_24BIT_RGB888 (3 << 16) #define DSI_VSA_NL 0x20 @@ -366,10 +366,10 @@ static void mtk_dsi_ps_control_vact(struct mtk_dsi *dsi) ps_bpp_mode |= PACKED_PS_24BIT_RGB888; break; case MIPI_DSI_FMT_RGB666: - ps_bpp_mode |= PACKED_PS_18BIT_RGB666; + ps_bpp_mode |= LOOSELY_PS_24BIT_RGB666; break; case MIPI_DSI_FMT_RGB666_PACKED: - ps_bpp_mode |= LOOSELY_PS_18BIT_RGB666; + ps_bpp_mode |= PACKED_PS_18BIT_RGB666; break; case MIPI_DSI_FMT_RGB565: ps_bpp_mode |= PACKED_PS_16BIT_RGB565; @@ -423,7 +423,7 @@ static void mtk_dsi_ps_control(struct mtk_dsi *dsi) dsi_tmp_buf_bpp = 3; break; case MIPI_DSI_FMT_RGB666: - tmp_reg = LOOSELY_PS_18BIT_RGB666; + tmp_reg = LOOSELY_PS_24BIT_RGB666; dsi_tmp_buf_bpp = 3; break; case MIPI_DSI_FMT_RGB666_PACKED: diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index 119544d88b586a9a31dc2a74808be30cd5797e9d..fbac39aa38cc45c648b0d0f7d797fa655f032d47 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -316,32 +316,34 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) goto exit_afbcd; if (has_components) { - ret = component_bind_all(drm->dev, drm); + ret = component_bind_all(dev, drm); if (ret) { dev_err(drm->dev, "Couldn't bind all components\n"); + /* Do not try to unbind */ + has_components = false; goto exit_afbcd; } } ret = meson_encoder_hdmi_init(priv); if (ret) - goto unbind_all; + goto exit_afbcd; ret = meson_plane_create(priv); if (ret) - goto unbind_all; + goto exit_afbcd; ret = meson_overlay_create(priv); if (ret) - goto unbind_all; + goto exit_afbcd; ret = meson_crtc_create(priv); if (ret) - goto unbind_all; + goto exit_afbcd; ret = request_irq(priv->vsync_irq, meson_irq, 0, drm->driver->name, drm); if (ret) - goto unbind_all; + goto exit_afbcd; drm_mode_config_reset(drm); @@ -359,15 +361,18 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) uninstall_irq: free_irq(priv->vsync_irq, drm); -unbind_all: - if (has_components) - component_unbind_all(drm->dev, drm); exit_afbcd: if (priv->afbcd.ops) priv->afbcd.ops->exit(priv); free_drm: drm_dev_put(drm); + meson_encoder_hdmi_remove(priv); + meson_encoder_cvbs_remove(priv); + + if (has_components) + component_unbind_all(dev, drm); + return ret; } diff --git a/drivers/gpu/drm/meson/meson_dw_hdmi.c b/drivers/gpu/drm/meson/meson_dw_hdmi.c index 5cd2b2ebbbd33e92d02792875e6e810de946d610..2c8e978eb9ab97a55f3a325e8abf12dcf710396f 100644 --- a/drivers/gpu/drm/meson/meson_dw_hdmi.c +++ b/drivers/gpu/drm/meson/meson_dw_hdmi.c @@ -105,6 +105,8 @@ #define HHI_HDMI_CLK_CNTL 0x1cc /* 0x73 */ #define HHI_HDMI_PHY_CNTL0 0x3a0 /* 0xe8 */ #define HHI_HDMI_PHY_CNTL1 0x3a4 /* 0xe9 */ +#define PHY_CNTL1_INIT 0x03900000 +#define PHY_INVERT BIT(17) #define HHI_HDMI_PHY_CNTL2 0x3a8 /* 0xea */ #define HHI_HDMI_PHY_CNTL3 0x3ac /* 0xeb */ #define HHI_HDMI_PHY_CNTL4 0x3b0 /* 0xec */ @@ -129,6 +131,8 @@ struct meson_dw_hdmi_data { unsigned int addr); void (*dwc_write)(struct meson_dw_hdmi *dw_hdmi, unsigned int addr, unsigned int data); + u32 cntl0_init; + u32 cntl1_init; }; struct meson_dw_hdmi { @@ -384,26 +388,6 @@ static int dw_hdmi_phy_init(struct dw_hdmi *hdmi, void *data, drm_mode_is_420_also(display, mode))) mode_is_420 = true; - /* Enable clocks */ - regmap_update_bits(priv->hhi, HHI_HDMI_CLK_CNTL, 0xffff, 0x100); - - /* Bring HDMITX MEM output of power down */ - regmap_update_bits(priv->hhi, HHI_MEM_PD_REG0, 0xff << 8, 0); - - /* Bring out of reset */ - dw_hdmi->data->top_write(dw_hdmi, HDMITX_TOP_SW_RESET, 0); - - /* Enable internal pixclk, tmds_clk, spdif_clk, i2s_clk, cecclk */ - dw_hdmi_top_write_bits(dw_hdmi, HDMITX_TOP_CLK_CNTL, - 0x3, 0x3); - - /* Enable cec_clk and hdcp22_tmdsclk_en */ - dw_hdmi_top_write_bits(dw_hdmi, HDMITX_TOP_CLK_CNTL, - 0x3 << 4, 0x3 << 4); - - /* Enable normal output to PHY */ - dw_hdmi->data->top_write(dw_hdmi, HDMITX_TOP_BIST_CNTL, BIT(12)); - /* TMDS pattern setup */ if (mode->clock > 340000 && !mode_is_420) { dw_hdmi->data->top_write(dw_hdmi, HDMITX_TOP_TMDS_CLK_PTTN_01, @@ -425,20 +409,6 @@ static int dw_hdmi_phy_init(struct dw_hdmi *hdmi, void *data, /* Setup PHY parameters */ meson_hdmi_phy_setup_mode(dw_hdmi, mode, mode_is_420); - /* Setup PHY */ - regmap_update_bits(priv->hhi, HHI_HDMI_PHY_CNTL1, - 0xffff << 16, 0x0390 << 16); - - /* BIT_INVERT */ - if (dw_hdmi_is_compatible(dw_hdmi, "amlogic,meson-gxl-dw-hdmi") || - dw_hdmi_is_compatible(dw_hdmi, "amlogic,meson-gxm-dw-hdmi") || - dw_hdmi_is_compatible(dw_hdmi, "amlogic,meson-g12a-dw-hdmi")) - regmap_update_bits(priv->hhi, HHI_HDMI_PHY_CNTL1, - BIT(17), 0); - else - regmap_update_bits(priv->hhi, HHI_HDMI_PHY_CNTL1, - BIT(17), BIT(17)); - /* Disable clock, fifo, fifo_wr */ regmap_update_bits(priv->hhi, HHI_HDMI_PHY_CNTL1, 0xf, 0); @@ -492,7 +462,9 @@ static void dw_hdmi_phy_disable(struct dw_hdmi *hdmi, DRM_DEBUG_DRIVER("\n"); - regmap_write(priv->hhi, HHI_HDMI_PHY_CNTL0, 0); + /* Fallback to init mode */ + regmap_write(priv->hhi, HHI_HDMI_PHY_CNTL1, dw_hdmi->data->cntl1_init); + regmap_write(priv->hhi, HHI_HDMI_PHY_CNTL0, dw_hdmi->data->cntl0_init); } static enum drm_connector_status dw_hdmi_read_hpd(struct dw_hdmi *hdmi, @@ -610,11 +582,22 @@ static const struct regmap_config meson_dw_hdmi_regmap_config = { .fast_io = true, }; -static const struct meson_dw_hdmi_data meson_dw_hdmi_gx_data = { +static const struct meson_dw_hdmi_data meson_dw_hdmi_gxbb_data = { .top_read = dw_hdmi_top_read, .top_write = dw_hdmi_top_write, .dwc_read = dw_hdmi_dwc_read, .dwc_write = dw_hdmi_dwc_write, + .cntl0_init = 0x0, + .cntl1_init = PHY_CNTL1_INIT | PHY_INVERT, +}; + +static const struct meson_dw_hdmi_data meson_dw_hdmi_gxl_data = { + .top_read = dw_hdmi_top_read, + .top_write = dw_hdmi_top_write, + .dwc_read = dw_hdmi_dwc_read, + .dwc_write = dw_hdmi_dwc_write, + .cntl0_init = 0x0, + .cntl1_init = PHY_CNTL1_INIT, }; static const struct meson_dw_hdmi_data meson_dw_hdmi_g12a_data = { @@ -622,6 +605,8 @@ static const struct meson_dw_hdmi_data meson_dw_hdmi_g12a_data = { .top_write = dw_hdmi_g12a_top_write, .dwc_read = dw_hdmi_g12a_dwc_read, .dwc_write = dw_hdmi_g12a_dwc_write, + .cntl0_init = 0x000b4242, /* Bandgap */ + .cntl1_init = PHY_CNTL1_INIT, }; static void meson_dw_hdmi_init(struct meson_dw_hdmi *meson_dw_hdmi) @@ -656,6 +641,13 @@ static void meson_dw_hdmi_init(struct meson_dw_hdmi *meson_dw_hdmi) meson_dw_hdmi->data->top_write(meson_dw_hdmi, HDMITX_TOP_CLK_CNTL, 0xff); + /* Enable normal output to PHY */ + meson_dw_hdmi->data->top_write(meson_dw_hdmi, HDMITX_TOP_BIST_CNTL, BIT(12)); + + /* Setup PHY */ + regmap_write(priv->hhi, HHI_HDMI_PHY_CNTL1, meson_dw_hdmi->data->cntl1_init); + regmap_write(priv->hhi, HHI_HDMI_PHY_CNTL0, meson_dw_hdmi->data->cntl0_init); + /* Enable HDMI-TX Interrupt */ meson_dw_hdmi->data->top_write(meson_dw_hdmi, HDMITX_TOP_INTR_STAT_CLR, HDMITX_TOP_INTR_CORE); @@ -883,11 +875,11 @@ static const struct dev_pm_ops meson_dw_hdmi_pm_ops = { static const struct of_device_id meson_dw_hdmi_of_table[] = { { .compatible = "amlogic,meson-gxbb-dw-hdmi", - .data = &meson_dw_hdmi_gx_data }, + .data = &meson_dw_hdmi_gxbb_data }, { .compatible = "amlogic,meson-gxl-dw-hdmi", - .data = &meson_dw_hdmi_gx_data }, + .data = &meson_dw_hdmi_gxl_data }, { .compatible = "amlogic,meson-gxm-dw-hdmi", - .data = &meson_dw_hdmi_gx_data }, + .data = &meson_dw_hdmi_gxl_data }, { .compatible = "amlogic,meson-g12a-dw-hdmi", .data = &meson_dw_hdmi_g12a_data }, { } diff --git a/drivers/gpu/drm/meson/meson_encoder_cvbs.c b/drivers/gpu/drm/meson/meson_encoder_cvbs.c index 3f73b211fa8e3e3bc4812180883c9685f8377f19..3407450435e2057dd3973441ba6e31485e69ee6d 100644 --- a/drivers/gpu/drm/meson/meson_encoder_cvbs.c +++ b/drivers/gpu/drm/meson/meson_encoder_cvbs.c @@ -294,6 +294,5 @@ void meson_encoder_cvbs_remove(struct meson_drm *priv) if (priv->encoders[MESON_ENC_CVBS]) { meson_encoder_cvbs = priv->encoders[MESON_ENC_CVBS]; drm_bridge_remove(&meson_encoder_cvbs->bridge); - drm_bridge_remove(meson_encoder_cvbs->next_bridge); } } diff --git a/drivers/gpu/drm/meson/meson_encoder_hdmi.c b/drivers/gpu/drm/meson/meson_encoder_hdmi.c index b14e6e507c61bf22ed2adb97eddc0660d0fe2b3c..03062e7a02b649de36be4fde4094bcd0a6f59088 100644 --- a/drivers/gpu/drm/meson/meson_encoder_hdmi.c +++ b/drivers/gpu/drm/meson/meson_encoder_hdmi.c @@ -472,6 +472,5 @@ void meson_encoder_hdmi_remove(struct meson_drm *priv) if (priv->encoders[MESON_ENC_HDMI]) { meson_encoder_hdmi = priv->encoders[MESON_ENC_HDMI]; drm_bridge_remove(&meson_encoder_hdmi->bridge); - drm_bridge_remove(meson_encoder_hdmi->next_bridge); } } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 38d38f923df64c662ee3ea6e0504c4ffd5e7ff35..3632f0768aa9ef32e8819c7e1e4bff05d3c81411 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -228,6 +228,13 @@ bool dpu_encoder_is_widebus_enabled(const struct drm_encoder *drm_enc) return dpu_enc->wide_bus_en; } +bool dpu_encoder_is_dsc_enabled(const struct drm_encoder *drm_enc) +{ + const struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc); + + return dpu_enc->dsc ? true : false; +} + int dpu_encoder_get_crc_values_cnt(const struct drm_encoder *drm_enc) { struct dpu_encoder_virt *dpu_enc; @@ -1864,7 +1871,9 @@ static void dpu_encoder_prep_dsc(struct dpu_encoder_virt *dpu_enc, dsc_common_mode = 0; pic_width = dsc->pic_width; - dsc_common_mode = DSC_MODE_MULTIPLEX | DSC_MODE_SPLIT_PANEL; + dsc_common_mode = DSC_MODE_SPLIT_PANEL; + if (dpu_encoder_use_dsc_merge(enc_master->parent)) + dsc_common_mode |= DSC_MODE_MULTIPLEX; if (enc_master->intf_mode == INTF_MODE_VIDEO) dsc_common_mode |= DSC_MODE_VIDEO; @@ -2053,7 +2062,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) } /* reset the merge 3D HW block */ - if (phys_enc->hw_pp->merge_3d) { + if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) { phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d, BLEND_3D_NONE); if (phys_enc->hw_ctl->ops.update_pending_flush_merge_3d) @@ -2069,7 +2078,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) if (phys_enc->hw_wb) intf_cfg.wb = phys_enc->hw_wb->idx; - if (phys_enc->hw_pp->merge_3d) + if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) intf_cfg.merge_3d = phys_enc->hw_pp->merge_3d->idx; if (ctl->ops.reset_intf_cfg) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h index 9e7236ef34e6d6041497223e3005156023516143..a71efa2b9e5086ec248f8a0dddbc16feed3d9fbd 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h @@ -175,6 +175,13 @@ int dpu_encoder_get_vsync_count(struct drm_encoder *drm_enc); bool dpu_encoder_is_widebus_enabled(const struct drm_encoder *drm_enc); +/** + * dpu_encoder_is_dsc_enabled - indicate whether dsc is enabled + * for the encoder. + * @drm_enc: Pointer to previously created drm encoder structure + */ +bool dpu_encoder_is_dsc_enabled(const struct drm_encoder *drm_enc); + /** * dpu_encoder_get_crc_values_cnt - get number of physical encoders contained * in virtual encoder that can collect CRC values diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c index 2c14646661b7746d1bca09be435eae217ece8c59..2baade1cd48768998e08d85d3c716665b2acd92c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c @@ -100,6 +100,7 @@ static void drm_mode_to_intf_timing_params( } timing->wide_bus_en = dpu_encoder_is_widebus_enabled(phys_enc->parent); + timing->compression_en = dpu_encoder_is_dsc_enabled(phys_enc->parent); /* * for DP, divide the horizonal parameters by 2 when @@ -256,12 +257,14 @@ static void dpu_encoder_phys_vid_setup_timing_engine( mode.htotal >>= 1; mode.hsync_start >>= 1; mode.hsync_end >>= 1; + mode.hskew >>= 1; DPU_DEBUG_VIDENC(phys_enc, - "split_role %d, halve horizontal %d %d %d %d\n", + "split_role %d, halve horizontal %d %d %d %d %d\n", phys_enc->split_role, mode.hdisplay, mode.htotal, - mode.hsync_start, mode.hsync_end); + mode.hsync_start, mode.hsync_end, + mode.hskew); } drm_mode_to_intf_timing_params(phys_enc, &mode, &timing_params); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c index 384558d2f96023590502e0d29f7d002b585f26cb..1debac4fcc3ebef3f41726732422279b330eac1c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c @@ -154,13 +154,8 @@ static void dpu_hw_intf_setup_timing_engine(struct dpu_hw_intf *ctx, hsync_ctl = (hsync_period << 16) | p->hsync_pulse_width; display_hctl = (hsync_end_x << 16) | hsync_start_x; - /* - * DATA_HCTL_EN controls data timing which can be different from - * video timing. It is recommended to enable it for all cases, except - * if compression is enabled in 1 pixel per clock mode - */ if (p->wide_bus_en) - intf_cfg2 |= INTF_CFG2_DATABUS_WIDEN | INTF_CFG2_DATA_HCTL_EN; + intf_cfg2 |= INTF_CFG2_DATABUS_WIDEN; data_width = p->width; @@ -230,6 +225,14 @@ static void dpu_hw_intf_setup_timing_engine(struct dpu_hw_intf *ctx, DPU_REG_WRITE(c, INTF_CONFIG, intf_cfg); DPU_REG_WRITE(c, INTF_PANEL_FORMAT, panel_format); if (ctx->cap->features & BIT(DPU_DATA_HCTL_EN)) { + /* + * DATA_HCTL_EN controls data timing which can be different from + * video timing. It is recommended to enable it for all cases, except + * if compression is enabled in 1 pixel per clock mode + */ + if (!(p->compression_en && !p->wide_bus_en)) + intf_cfg2 |= INTF_CFG2_DATA_HCTL_EN; + DPU_REG_WRITE(c, INTF_CONFIG2, intf_cfg2); DPU_REG_WRITE(c, INTF_DISPLAY_DATA_HCTL, display_data_hctl); DPU_REG_WRITE(c, INTF_ACTIVE_DATA_HCTL, active_data_hctl); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h index e75339b96a1d2554a48734d205777b51e0e7ca07..7f502c8bee1d46c7d79c1648f31b4836129abc7d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h @@ -33,6 +33,7 @@ struct intf_timing_params { u32 hsync_skew; bool wide_bus_en; + bool compression_en; }; struct intf_prog_fetch { diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index 103eef9f059a0bb9111731c7c847b64b0244b1d7..b20701893e5b33e6feb3abafa09e1b93903b6e2e 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -133,11 +133,6 @@ static void dp_ctrl_config_ctrl(struct dp_ctrl_private *ctrl) tbd = dp_link_get_test_bits_depth(ctrl->link, ctrl->panel->dp_mode.bpp); - if (tbd == DP_TEST_BIT_DEPTH_UNKNOWN) { - pr_debug("BIT_DEPTH not set. Configure default\n"); - tbd = DP_TEST_BIT_DEPTH_8; - } - config |= tbd << DP_CONFIGURATION_CTRL_BPC_SHIFT; /* Num of Lanes */ diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c index cb66d1126ea9607c0a8ac34bc41e70cf505fe82f..ceb382fa56d5b3c7f726bbc67d22f9c58753317a 100644 --- a/drivers/gpu/drm/msm/dp/dp_link.c +++ b/drivers/gpu/drm/msm/dp/dp_link.c @@ -7,6 +7,7 @@ #include +#include "dp_reg.h" #include "dp_link.h" #include "dp_panel.h" @@ -1075,7 +1076,7 @@ int dp_link_process_request(struct dp_link *dp_link) int dp_link_get_colorimetry_config(struct dp_link *dp_link) { - u32 cc; + u32 cc = DP_MISC0_COLORIMERY_CFG_LEGACY_RGB; struct dp_link_private *link; if (!dp_link) { @@ -1089,10 +1090,11 @@ int dp_link_get_colorimetry_config(struct dp_link *dp_link) * Unless a video pattern CTS test is ongoing, use RGB_VESA * Only RGB_VESA and RGB_CEA supported for now */ - if (dp_link_is_video_pattern_requested(link)) - cc = link->dp_link.test_video.test_dyn_range; - else - cc = DP_TEST_DYNAMIC_RANGE_VESA; + if (dp_link_is_video_pattern_requested(link)) { + if (link->dp_link.test_video.test_dyn_range & + DP_TEST_DYNAMIC_RANGE_CEA) + cc = DP_MISC0_COLORIMERY_CFG_CEA_RGB; + } return cc; } @@ -1172,6 +1174,9 @@ void dp_link_reset_phy_params_vx_px(struct dp_link *dp_link) u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp) { u32 tbd; + struct dp_link_private *link; + + link = container_of(dp_link, struct dp_link_private, dp_link); /* * Few simplistic rules and assumptions made here: @@ -1189,12 +1194,13 @@ u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp) tbd = DP_TEST_BIT_DEPTH_10; break; default: - tbd = DP_TEST_BIT_DEPTH_UNKNOWN; + drm_dbg_dp(link->drm_dev, "bpp=%d not supported, use bpc=8\n", + bpp); + tbd = DP_TEST_BIT_DEPTH_8; break; } - if (tbd != DP_TEST_BIT_DEPTH_UNKNOWN) - tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT); + tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT); return tbd; } diff --git a/drivers/gpu/drm/msm/dp/dp_reg.h b/drivers/gpu/drm/msm/dp/dp_reg.h index 268602803d9a328a8b759eb9d829bc8d29fccf39..176a503ece9c04d7d0fe2519376e2514a22609d4 100644 --- a/drivers/gpu/drm/msm/dp/dp_reg.h +++ b/drivers/gpu/drm/msm/dp/dp_reg.h @@ -129,6 +129,9 @@ #define DP_MISC0_COLORIMETRY_CFG_SHIFT (0x00000001) #define DP_MISC0_TEST_BITS_DEPTH_SHIFT (0x00000005) +#define DP_MISC0_COLORIMERY_CFG_LEGACY_RGB (0) +#define DP_MISC0_COLORIMERY_CFG_CEA_RGB (0x04) + #define REG_DP_VALID_BOUNDARY (0x00000030) #define REG_DP_VALID_BOUNDARY_2 (0x00000034) diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index d12ba47b37c4fa95553735b69abd2f6df8cdfec3..0de3612135e965bda95b7cfecdf849d8d910a051 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -21,6 +21,8 @@ struct msm_iommu_pagetable { struct msm_mmu base; struct msm_mmu *parent; struct io_pgtable_ops *pgtbl_ops; + const struct iommu_flush_ops *tlb; + struct device *iommu_dev; unsigned long pgsize_bitmap; /* Bitmap of page sizes in use */ phys_addr_t ttbr; u32 asid; @@ -194,11 +196,33 @@ static const struct msm_mmu_funcs pagetable_funcs = { static void msm_iommu_tlb_flush_all(void *cookie) { + struct msm_iommu_pagetable *pagetable = cookie; + struct adreno_smmu_priv *adreno_smmu; + + if (!pm_runtime_get_if_in_use(pagetable->iommu_dev)) + return; + + adreno_smmu = dev_get_drvdata(pagetable->parent->dev); + + pagetable->tlb->tlb_flush_all((void *)adreno_smmu->cookie); + + pm_runtime_put_autosuspend(pagetable->iommu_dev); } static void msm_iommu_tlb_flush_walk(unsigned long iova, size_t size, size_t granule, void *cookie) { + struct msm_iommu_pagetable *pagetable = cookie; + struct adreno_smmu_priv *adreno_smmu; + + if (!pm_runtime_get_if_in_use(pagetable->iommu_dev)) + return; + + adreno_smmu = dev_get_drvdata(pagetable->parent->dev); + + pagetable->tlb->tlb_flush_walk(iova, size, granule, (void *)adreno_smmu->cookie); + + pm_runtime_put_autosuspend(pagetable->iommu_dev); } static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather, @@ -206,7 +230,7 @@ static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather, { } -static const struct iommu_flush_ops null_tlb_ops = { +static const struct iommu_flush_ops tlb_ops = { .tlb_flush_all = msm_iommu_tlb_flush_all, .tlb_flush_walk = msm_iommu_tlb_flush_walk, .tlb_add_page = msm_iommu_tlb_add_page, @@ -254,10 +278,10 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) /* The incoming cfg will have the TTBR1 quirk enabled */ ttbr0_cfg.quirks &= ~IO_PGTABLE_QUIRK_ARM_TTBR1; - ttbr0_cfg.tlb = &null_tlb_ops; + ttbr0_cfg.tlb = &tlb_ops; pagetable->pgtbl_ops = alloc_io_pgtable_ops(ARM_64_LPAE_S1, - &ttbr0_cfg, iommu->domain); + &ttbr0_cfg, pagetable); if (!pagetable->pgtbl_ops) { kfree(pagetable); @@ -282,6 +306,8 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) /* Needed later for TLB flush */ pagetable->parent = parent; + pagetable->tlb = ttbr1_cfg->tlb; + pagetable->iommu_dev = ttbr1_cfg->iommu_dev; pagetable->pgsize_bitmap = ttbr0_cfg.pgsize_bitmap; pagetable->ttbr = ttbr0_cfg.arm_lpae_s1_cfg.ttbr; diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c index 189903b65edc997d0250d9b39920f7654c105a0b..48cf593383b34108cf12c3ebc2fb0b12764d426a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bios.c +++ b/drivers/gpu/drm/nouveau/nouveau_bios.c @@ -23,6 +23,7 @@ */ #include "nouveau_drv.h" +#include "nouveau_bios.h" #include "nouveau_reg.h" #include "dispnv04/hw.h" #include "nouveau_encoder.h" @@ -1675,7 +1676,7 @@ apply_dcb_encoder_quirks(struct drm_device *dev, int idx, u32 *conn, u32 *conf) */ if (nv_match_device(dev, 0x0201, 0x1462, 0x8851)) { if (*conn == 0xf2005014 && *conf == 0xffffffff) { - fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 1, 1, 1); + fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 1, 1, DCB_OUTPUT_B); return false; } } @@ -1761,26 +1762,26 @@ fabricate_dcb_encoder_table(struct drm_device *dev, struct nvbios *bios) #ifdef __powerpc__ /* Apple iMac G4 NV17 */ if (of_machine_is_compatible("PowerMac4,5")) { - fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 0, all_heads, 1); - fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, 1, all_heads, 2); + fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 0, all_heads, DCB_OUTPUT_B); + fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, 1, all_heads, DCB_OUTPUT_C); return; } #endif /* Make up some sane defaults */ fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, - bios->legacy.i2c_indices.crt, 1, 1); + bios->legacy.i2c_indices.crt, 1, DCB_OUTPUT_B); if (nv04_tv_identify(dev, bios->legacy.i2c_indices.tv) >= 0) fabricate_dcb_output(dcb, DCB_OUTPUT_TV, bios->legacy.i2c_indices.tv, - all_heads, 0); + all_heads, DCB_OUTPUT_A); else if (bios->tmds.output0_script_ptr || bios->tmds.output1_script_ptr) fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, bios->legacy.i2c_indices.panel, - all_heads, 1); + all_heads, DCB_OUTPUT_B); } static int diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 126b3c6e12f997c8db70bacd9d19e66766deafa9..f2dca41e46c5fb52cf3892ec9df9a37091f755da 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -1194,6 +1194,8 @@ out: drm_vma_node_unmap(&nvbo->bo.base.vma_node, bdev->dev_mapping); nouveau_ttm_io_mem_free_locked(drm, nvbo->bo.resource); + nvbo->bo.resource->bus.offset = 0; + nvbo->bo.resource->bus.addr = NULL; goto retry; } diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 20fe53815b20f9d5aca35ffe5727debb83e92ff3..6ca4a46a82ee9cdfeea460844e704476e848ba8e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -379,9 +379,9 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk) dma_addr_t *dma_addrs; struct nouveau_fence *fence; - src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL); - dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL); - dma_addrs = kcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL); + src_pfns = kvcalloc(npages, sizeof(*src_pfns), GFP_KERNEL | __GFP_NOFAIL); + dst_pfns = kvcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL | __GFP_NOFAIL); + dma_addrs = kvcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL | __GFP_NOFAIL); migrate_device_range(src_pfns, chunk->pagemap.range.start >> PAGE_SHIFT, npages); @@ -407,11 +407,11 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk) migrate_device_pages(src_pfns, dst_pfns, npages); nouveau_dmem_fence_done(&fence); migrate_device_finalize(src_pfns, dst_pfns, npages); - kfree(src_pfns); - kfree(dst_pfns); + kvfree(src_pfns); + kvfree(dst_pfns); for (i = 0; i < npages; i++) dma_unmap_page(chunk->drm->dev->dev, dma_addrs[i], PAGE_SIZE, DMA_BIDIRECTIONAL); - kfree(dma_addrs); + kvfree(dma_addrs); } void diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c index 53185746fb3d14ec6077002be1cacc4e0841cdc0..17e1e23a780e0a7bc97ec6aef6dd11d93239ac3b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dp.c +++ b/drivers/gpu/drm/nouveau/nouveau_dp.c @@ -109,12 +109,15 @@ nouveau_dp_detect(struct nouveau_connector *nv_connector, u8 *dpcd = nv_encoder->dp.dpcd; int ret = NOUVEAU_DP_NONE, hpd; - /* If we've already read the DPCD on an eDP device, we don't need to - * reread it as it won't change + /* eDP ports don't support hotplugging - so there's no point in probing eDP ports unless we + * haven't probed them once before. */ - if (connector->connector_type == DRM_MODE_CONNECTOR_eDP && - dpcd[DP_DPCD_REV] != 0) - return NOUVEAU_DP_SST; + if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) { + if (connector->status == connector_status_connected) + return NOUVEAU_DP_SST; + else if (connector->status == connector_status_disconnected) + return NOUVEAU_DP_NONE; + } mutex_lock(&nv_encoder->dp.hpd_irq_lock); if (mstm) { diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 31a5b81ee9fc469e4458b57c3133c29c303aa5db..be6674fb1af711d61fc8399256375c7d45246bde 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -997,7 +997,7 @@ nouveau_svm_fault_buffer_ctor(struct nouveau_svm *svm, s32 oclass, int id) if (ret) return ret; - buffer->fault = kvcalloc(sizeof(*buffer->fault), buffer->entries, GFP_KERNEL); + buffer->fault = kvcalloc(buffer->entries, sizeof(*buffer->fault), GFP_KERNEL); if (!buffer->fault) return -ENOMEM; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c index 19188683c8fca90a7656b53ab15a8ee58d8575e0..8c2bf1c16f2a9568a8d434838d0c7691d9d70ff7 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c @@ -154,11 +154,17 @@ shadow_fw_init(struct nvkm_bios *bios, const char *name) return (void *)fw; } +static void +shadow_fw_release(void *fw) +{ + release_firmware(fw); +} + static const struct nvbios_source shadow_fw = { .name = "firmware", .init = shadow_fw_init, - .fini = (void(*)(void *))release_firmware, + .fini = shadow_fw_release, .read = shadow_fw_read, .rw = false, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c index 4bf486b57101367708bba2b6fe4bdd1d985f1d19..cb05f7f48a98bb53fc3e03b57166466c675acd7c 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c @@ -66,11 +66,16 @@ of_init(struct nvkm_bios *bios, const char *name) return ERR_PTR(-EINVAL); } +static void of_fini(void *p) +{ + kfree(p); +} + const struct nvbios_source nvbios_of = { .name = "OpenFirmware", .init = of_init, - .fini = (void(*)(void *))kfree, + .fini = of_fini, .read = of_read, .size = of_size, .rw = false, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c index c51bac76174c1c0223f9c15034bc377e33b7c28a..9fe5b6a36ab98f0f27606d112bc2a54531b26c4f 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c @@ -221,8 +221,11 @@ nv50_instobj_acquire(struct nvkm_memory *memory) void __iomem *map = NULL; /* Already mapped? */ - if (refcount_inc_not_zero(&iobj->maps)) + if (refcount_inc_not_zero(&iobj->maps)) { + /* read barrier match the wmb on refcount set */ + smp_rmb(); return iobj->map; + } /* Take the lock, and re-check that another thread hasn't * already mapped the object in the meantime. @@ -249,6 +252,8 @@ nv50_instobj_acquire(struct nvkm_memory *memory) iobj->base.memory.ptrs = &nv50_instobj_fast; else iobj->base.memory.ptrs = &nv50_instobj_slow; + /* barrier to ensure the ptrs are written before refcount is set */ + smp_wmb(); refcount_set(&iobj->maps, 1); } diff --git a/drivers/gpu/drm/panel/panel-edp.c b/drivers/gpu/drm/panel/panel-edp.c index 42584d8a9aeb66a1cd6cfac51868ed38b8df7294..bfcddd4aa93227be193922740dbc9d0f84fb6ef6 100644 --- a/drivers/gpu/drm/panel/panel-edp.c +++ b/drivers/gpu/drm/panel/panel-edp.c @@ -413,8 +413,7 @@ static int panel_edp_unprepare(struct drm_panel *panel) if (!p->prepared) return 0; - pm_runtime_mark_last_busy(panel->dev); - ret = pm_runtime_put_autosuspend(panel->dev); + ret = pm_runtime_put_sync_suspend(panel->dev); if (ret < 0) return ret; p->prepared = false; diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c index 39dc40cf681f015abaea9158348c2c839b990605..285e76818d84d9eac6c071305d3b9b6a6db23b98 100644 --- a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c +++ b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c @@ -420,7 +420,7 @@ static int ili9341_dpi_prepare(struct drm_panel *panel) ili9341_dpi_init(ili); - return ret; + return 0; } static int ili9341_dpi_enable(struct drm_panel *panel) @@ -717,18 +717,18 @@ static int ili9341_probe(struct spi_device *spi) reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); if (IS_ERR(reset)) - dev_err(dev, "Failed to get gpio 'reset'\n"); + return dev_err_probe(dev, PTR_ERR(reset), "Failed to get gpio 'reset'\n"); dc = devm_gpiod_get_optional(dev, "dc", GPIOD_OUT_LOW); if (IS_ERR(dc)) - dev_err(dev, "Failed to get gpio 'dc'\n"); + return dev_err_probe(dev, PTR_ERR(dc), "Failed to get gpio 'dc'\n"); if (!strcmp(id->name, "sf-tc240t-9370-t")) return ili9341_dpi_probe(spi, dc, reset); else if (!strcmp(id->name, "yx240qv29")) return ili9341_dbi_probe(spi, dc, reset); - return -1; + return -ENODEV; } static void ili9341_remove(struct spi_device *spi) diff --git a/drivers/gpu/drm/panel/panel-visionox-rm69299.c b/drivers/gpu/drm/panel/panel-visionox-rm69299.c index ec228c269146f0c5177de3a16ccbe04010ed8339..b380bbb0e0d0a9d04ec0a740a8ff48dd4783a3b7 100644 --- a/drivers/gpu/drm/panel/panel-visionox-rm69299.c +++ b/drivers/gpu/drm/panel/panel-visionox-rm69299.c @@ -261,8 +261,6 @@ static void visionox_rm69299_remove(struct mipi_dsi_device *dsi) struct visionox_rm69299 *ctx = mipi_dsi_get_drvdata(dsi); mipi_dsi_detach(ctx->dsi); - mipi_dsi_device_unregister(ctx->dsi); - drm_panel_remove(&ctx->panel); } diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c index 55d2430485168ae0bca5719620d2ab48ebf9ba66..40b6314459926a883b6dfec1563472fac3dcb14e 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gpu.c +++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c @@ -379,19 +379,19 @@ void panfrost_gpu_power_off(struct panfrost_device *pfdev) gpu_write(pfdev, SHADER_PWROFF_LO, pfdev->features.shader_present); ret = readl_relaxed_poll_timeout(pfdev->iomem + SHADER_PWRTRANS_LO, - val, !val, 1, 1000); + val, !val, 1, 2000); if (ret) dev_err(pfdev->dev, "shader power transition timeout"); gpu_write(pfdev, TILER_PWROFF_LO, pfdev->features.tiler_present); ret = readl_relaxed_poll_timeout(pfdev->iomem + TILER_PWRTRANS_LO, - val, !val, 1, 1000); + val, !val, 1, 2000); if (ret) dev_err(pfdev->dev, "tiler power transition timeout"); gpu_write(pfdev, L2_PWROFF_LO, pfdev->features.l2_present); ret = readl_poll_timeout(pfdev->iomem + L2_PWRTRANS_LO, - val, !val, 0, 1000); + val, !val, 0, 2000); if (ret) dev_err(pfdev->dev, "l2 power transition timeout"); } diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c index 927e5f42e97d018240b5204c9d0dd7339391292a..3e48cbb522a1ca6008ed52dce4df7ff248f8a777 100644 --- a/drivers/gpu/drm/radeon/ni.c +++ b/drivers/gpu/drm/radeon/ni.c @@ -813,7 +813,7 @@ int ni_init_microcode(struct radeon_device *rdev) err = 0; } else if (rdev->smc_fw->size != smc_req_size) { pr_err("ni_mc: Bogus length %zu in firmware \"%s\"\n", - rdev->mc_fw->size, fw_name); + rdev->smc_fw->size, fw_name); err = -EINVAL; } } diff --git a/drivers/gpu/drm/rockchip/inno_hdmi.c b/drivers/gpu/drm/rockchip/inno_hdmi.c index f51774866f412f7cbfb488fa76c37c787e458071..8f230f4c01bc3ac1dc46449ed41b8468588fd67e 100644 --- a/drivers/gpu/drm/rockchip/inno_hdmi.c +++ b/drivers/gpu/drm/rockchip/inno_hdmi.c @@ -411,7 +411,7 @@ static int inno_hdmi_config_video_timing(struct inno_hdmi *hdmi, hdmi_writeb(hdmi, HDMI_VIDEO_EXT_HBLANK_L, value & 0xFF); hdmi_writeb(hdmi, HDMI_VIDEO_EXT_HBLANK_H, (value >> 8) & 0xFF); - value = mode->hsync_start - mode->hdisplay; + value = mode->htotal - mode->hsync_start; hdmi_writeb(hdmi, HDMI_VIDEO_EXT_HDELAY_L, value & 0xFF); hdmi_writeb(hdmi, HDMI_VIDEO_EXT_HDELAY_H, (value >> 8) & 0xFF); @@ -426,7 +426,7 @@ static int inno_hdmi_config_video_timing(struct inno_hdmi *hdmi, value = mode->vtotal - mode->vdisplay; hdmi_writeb(hdmi, HDMI_VIDEO_EXT_VBLANK, value & 0xFF); - value = mode->vsync_start - mode->vdisplay; + value = mode->vtotal - mode->vsync_start; hdmi_writeb(hdmi, HDMI_VIDEO_EXT_VDELAY, value & 0xFF); value = mode->vsync_end - mode->vsync_start; diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.c b/drivers/gpu/drm/rockchip/rockchip_lvds.c index 68f6ebb33460bc7992eb31831073ea66901bf943..eb4a108c5bd2ab927af02f6d3e41d9296f258d2f 100644 --- a/drivers/gpu/drm/rockchip/rockchip_lvds.c +++ b/drivers/gpu/drm/rockchip/rockchip_lvds.c @@ -577,8 +577,7 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master, ret = -EINVAL; goto err_put_port; } else if (ret) { - DRM_DEV_ERROR(dev, "failed to find panel and bridge node\n"); - ret = -EPROBE_DEFER; + dev_err_probe(dev, ret, "failed to find panel and bridge node\n"); goto err_put_port; } if (lvds->panel) diff --git a/drivers/gpu/drm/tegra/dpaux.c b/drivers/gpu/drm/tegra/dpaux.c index d773ef48541889fef3933393ac811cf384d20b28..b563988fb684855e7d28331b8c4bfcf67aa4e4c4 100644 --- a/drivers/gpu/drm/tegra/dpaux.c +++ b/drivers/gpu/drm/tegra/dpaux.c @@ -524,7 +524,7 @@ static int tegra_dpaux_probe(struct platform_device *pdev) if (err < 0) { dev_err(dpaux->dev, "failed to request IRQ#%u: %d\n", dpaux->irq, err); - return err; + goto err_pm_disable; } disable_irq(dpaux->irq); @@ -544,7 +544,7 @@ static int tegra_dpaux_probe(struct platform_device *pdev) */ err = tegra_dpaux_pad_config(dpaux, DPAUX_PADCTL_FUNC_I2C); if (err < 0) - return err; + goto err_pm_disable; #ifdef CONFIG_GENERIC_PINCONF dpaux->desc.name = dev_name(&pdev->dev); @@ -557,7 +557,8 @@ static int tegra_dpaux_probe(struct platform_device *pdev) dpaux->pinctrl = devm_pinctrl_register(&pdev->dev, &dpaux->desc, dpaux); if (IS_ERR(dpaux->pinctrl)) { dev_err(&pdev->dev, "failed to register pincontrol\n"); - return PTR_ERR(dpaux->pinctrl); + err = PTR_ERR(dpaux->pinctrl); + goto err_pm_disable; } #endif /* enable and clear all interrupts */ @@ -573,10 +574,15 @@ static int tegra_dpaux_probe(struct platform_device *pdev) err = devm_of_dp_aux_populate_ep_devices(&dpaux->aux); if (err < 0) { dev_err(dpaux->dev, "failed to populate AUX bus: %d\n", err); - return err; + goto err_pm_disable; } return 0; + +err_pm_disable: + pm_runtime_put_sync(&pdev->dev); + pm_runtime_disable(&pdev->dev); + return err; } static int tegra_dpaux_remove(struct platform_device *pdev) diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 5fc55b9777cbf4f54686bd02cae16d8958b8de22..6806779f8eccefec41e0d12ec6ef468eae6b2b1b 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -1252,9 +1252,26 @@ static int host1x_drm_probe(struct host1x_device *dev) drm_mode_config_reset(drm); - err = drm_aperture_remove_framebuffers(&tegra_drm_driver); - if (err < 0) - goto hub; + /* + * Only take over from a potential firmware framebuffer if any CRTCs + * have been registered. This must not be a fatal error because there + * are other accelerators that are exposed via this driver. + * + * Another case where this happens is on Tegra234 where the display + * hardware is no longer part of the host1x complex, so this driver + * will not expose any modesetting features. + */ + if (drm->mode_config.num_crtc > 0) { + err = drm_aperture_remove_framebuffers(&tegra_drm_driver); + if (err < 0) + goto hub; + } else { + /* + * Indicate to userspace that this doesn't expose any display + * capabilities. + */ + drm->driver_features &= ~(DRIVER_MODESET | DRIVER_ATOMIC); + } err = tegra_drm_fb_init(drm); if (err < 0) diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c index de1333dc0d8670aa30dc9867d5c13a41691ea4a3..7bb26655cb3ccf40ddc964dc418af7553d7b4d2e 100644 --- a/drivers/gpu/drm/tegra/dsi.c +++ b/drivers/gpu/drm/tegra/dsi.c @@ -1534,9 +1534,11 @@ static int tegra_dsi_ganged_probe(struct tegra_dsi *dsi) np = of_parse_phandle(dsi->dev->of_node, "nvidia,ganged-mode", 0); if (np) { struct platform_device *gangster = of_find_device_by_node(np); + of_node_put(np); + if (!gangster) + return -EPROBE_DEFER; dsi->slave = platform_get_drvdata(gangster); - of_node_put(np); if (!dsi->slave) { put_device(&gangster->dev); @@ -1584,48 +1586,58 @@ static int tegra_dsi_probe(struct platform_device *pdev) if (!pdev->dev.pm_domain) { dsi->rst = devm_reset_control_get(&pdev->dev, "dsi"); - if (IS_ERR(dsi->rst)) - return PTR_ERR(dsi->rst); + if (IS_ERR(dsi->rst)) { + err = PTR_ERR(dsi->rst); + goto remove; + } } dsi->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(dsi->clk)) { - dev_err(&pdev->dev, "cannot get DSI clock\n"); - return PTR_ERR(dsi->clk); + err = dev_err_probe(&pdev->dev, PTR_ERR(dsi->clk), + "cannot get DSI clock\n"); + goto remove; } dsi->clk_lp = devm_clk_get(&pdev->dev, "lp"); if (IS_ERR(dsi->clk_lp)) { - dev_err(&pdev->dev, "cannot get low-power clock\n"); - return PTR_ERR(dsi->clk_lp); + err = dev_err_probe(&pdev->dev, PTR_ERR(dsi->clk_lp), + "cannot get low-power clock\n"); + goto remove; } dsi->clk_parent = devm_clk_get(&pdev->dev, "parent"); if (IS_ERR(dsi->clk_parent)) { - dev_err(&pdev->dev, "cannot get parent clock\n"); - return PTR_ERR(dsi->clk_parent); + err = dev_err_probe(&pdev->dev, PTR_ERR(dsi->clk_parent), + "cannot get parent clock\n"); + goto remove; } dsi->vdd = devm_regulator_get(&pdev->dev, "avdd-dsi-csi"); if (IS_ERR(dsi->vdd)) { - dev_err(&pdev->dev, "cannot get VDD supply\n"); - return PTR_ERR(dsi->vdd); + err = dev_err_probe(&pdev->dev, PTR_ERR(dsi->vdd), + "cannot get VDD supply\n"); + goto remove; } err = tegra_dsi_setup_clocks(dsi); if (err < 0) { dev_err(&pdev->dev, "cannot setup clocks\n"); - return err; + goto remove; } regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); dsi->regs = devm_ioremap_resource(&pdev->dev, regs); - if (IS_ERR(dsi->regs)) - return PTR_ERR(dsi->regs); + if (IS_ERR(dsi->regs)) { + err = PTR_ERR(dsi->regs); + goto remove; + } dsi->mipi = tegra_mipi_request(&pdev->dev, pdev->dev.of_node); - if (IS_ERR(dsi->mipi)) - return PTR_ERR(dsi->mipi); + if (IS_ERR(dsi->mipi)) { + err = PTR_ERR(dsi->mipi); + goto remove; + } dsi->host.ops = &tegra_dsi_host_ops; dsi->host.dev = &pdev->dev; @@ -1653,9 +1665,12 @@ static int tegra_dsi_probe(struct platform_device *pdev) return 0; unregister: + pm_runtime_disable(&pdev->dev); mipi_dsi_host_unregister(&dsi->host); mipi_free: tegra_mipi_free(dsi->mipi); +remove: + tegra_output_remove(&dsi->output); return err; } diff --git a/drivers/gpu/drm/tegra/fb.c b/drivers/gpu/drm/tegra/fb.c index 9291209154a7a947e6d7d2bbfb4057e6e592b4d4..a688ecf08451e985e4d86cee2d9aecddaf32e428 100644 --- a/drivers/gpu/drm/tegra/fb.c +++ b/drivers/gpu/drm/tegra/fb.c @@ -166,6 +166,7 @@ struct drm_framebuffer *tegra_fb_create(struct drm_device *drm, if (gem->size < size) { err = -EINVAL; + drm_gem_object_put(gem); goto unreference; } diff --git a/drivers/gpu/drm/tegra/hdmi.c b/drivers/gpu/drm/tegra/hdmi.c index bf240767dad9f376ff56e96b85e59eb7018a648d..c66764c0bd25093954778e637d54a6f9ef5efb77 100644 --- a/drivers/gpu/drm/tegra/hdmi.c +++ b/drivers/gpu/drm/tegra/hdmi.c @@ -1776,7 +1776,6 @@ static irqreturn_t tegra_hdmi_irq(int irq, void *data) static int tegra_hdmi_probe(struct platform_device *pdev) { struct tegra_hdmi *hdmi; - struct resource *regs; int err; hdmi = devm_kzalloc(&pdev->dev, sizeof(*hdmi), GFP_KERNEL); @@ -1838,14 +1837,15 @@ static int tegra_hdmi_probe(struct platform_device *pdev) if (err < 0) return err; - regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); - hdmi->regs = devm_ioremap_resource(&pdev->dev, regs); - if (IS_ERR(hdmi->regs)) - return PTR_ERR(hdmi->regs); + hdmi->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(hdmi->regs)) { + err = PTR_ERR(hdmi->regs); + goto remove; + } err = platform_get_irq(pdev, 0); if (err < 0) - return err; + goto remove; hdmi->irq = err; @@ -1854,18 +1854,18 @@ static int tegra_hdmi_probe(struct platform_device *pdev) if (err < 0) { dev_err(&pdev->dev, "failed to request IRQ#%u: %d\n", hdmi->irq, err); - return err; + goto remove; } platform_set_drvdata(pdev, hdmi); err = devm_pm_runtime_enable(&pdev->dev); if (err) - return err; + goto remove; err = devm_tegra_core_dev_init_opp_table_common(&pdev->dev); if (err) - return err; + goto remove; INIT_LIST_HEAD(&hdmi->client.list); hdmi->client.ops = &hdmi_client_ops; @@ -1875,10 +1875,14 @@ static int tegra_hdmi_probe(struct platform_device *pdev) if (err < 0) { dev_err(&pdev->dev, "failed to register host1x client: %d\n", err); - return err; + goto remove; } return 0; + +remove: + tegra_output_remove(&hdmi->output); + return err; } static int tegra_hdmi_remove(struct platform_device *pdev) diff --git a/drivers/gpu/drm/tegra/output.c b/drivers/gpu/drm/tegra/output.c index 47d26b5d99456bdd0a3d1facc99f2d90949075a8..7ccd010a821b7c3633a7d2841d044238d71f2106 100644 --- a/drivers/gpu/drm/tegra/output.c +++ b/drivers/gpu/drm/tegra/output.c @@ -139,8 +139,10 @@ int tegra_output_probe(struct tegra_output *output) GPIOD_IN, "HDMI hotplug detect"); if (IS_ERR(output->hpd_gpio)) { - if (PTR_ERR(output->hpd_gpio) != -ENOENT) - return PTR_ERR(output->hpd_gpio); + if (PTR_ERR(output->hpd_gpio) != -ENOENT) { + err = PTR_ERR(output->hpd_gpio); + goto put_i2c; + } output->hpd_gpio = NULL; } @@ -149,7 +151,7 @@ int tegra_output_probe(struct tegra_output *output) err = gpiod_to_irq(output->hpd_gpio); if (err < 0) { dev_err(output->dev, "gpiod_to_irq(): %d\n", err); - return err; + goto put_i2c; } output->hpd_irq = err; @@ -162,7 +164,7 @@ int tegra_output_probe(struct tegra_output *output) if (err < 0) { dev_err(output->dev, "failed to request IRQ#%u: %d\n", output->hpd_irq, err); - return err; + goto put_i2c; } output->connector.polled = DRM_CONNECTOR_POLL_HPD; @@ -176,6 +178,12 @@ int tegra_output_probe(struct tegra_output *output) } return 0; + +put_i2c: + if (output->ddc) + i2c_put_adapter(output->ddc); + + return err; } void tegra_output_remove(struct tegra_output *output) diff --git a/drivers/gpu/drm/tegra/rgb.c b/drivers/gpu/drm/tegra/rgb.c index ff8fce36d2aa14e09a27c3fd662a8a407410c788..86e55e5d12b39c9a5612ad17ef31c3dba51d55b3 100644 --- a/drivers/gpu/drm/tegra/rgb.c +++ b/drivers/gpu/drm/tegra/rgb.c @@ -214,26 +214,28 @@ int tegra_dc_rgb_probe(struct tegra_dc *dc) rgb->clk = devm_clk_get(dc->dev, NULL); if (IS_ERR(rgb->clk)) { dev_err(dc->dev, "failed to get clock\n"); - return PTR_ERR(rgb->clk); + err = PTR_ERR(rgb->clk); + goto remove; } rgb->clk_parent = devm_clk_get(dc->dev, "parent"); if (IS_ERR(rgb->clk_parent)) { dev_err(dc->dev, "failed to get parent clock\n"); - return PTR_ERR(rgb->clk_parent); + err = PTR_ERR(rgb->clk_parent); + goto remove; } err = clk_set_parent(rgb->clk, rgb->clk_parent); if (err < 0) { dev_err(dc->dev, "failed to set parent clock: %d\n", err); - return err; + goto remove; } rgb->pll_d_out0 = clk_get_sys(NULL, "pll_d_out0"); if (IS_ERR(rgb->pll_d_out0)) { err = PTR_ERR(rgb->pll_d_out0); dev_err(dc->dev, "failed to get pll_d_out0: %d\n", err); - return err; + goto remove; } if (dc->soc->has_pll_d2_out0) { @@ -241,13 +243,19 @@ int tegra_dc_rgb_probe(struct tegra_dc *dc) if (IS_ERR(rgb->pll_d2_out0)) { err = PTR_ERR(rgb->pll_d2_out0); dev_err(dc->dev, "failed to get pll_d2_out0: %d\n", err); - return err; + goto put_pll; } } dc->rgb = &rgb->output; return 0; + +put_pll: + clk_put(rgb->pll_d_out0); +remove: + tegra_output_remove(&rgb->output); + return err; } int tegra_dc_rgb_remove(struct tegra_dc *dc) diff --git a/drivers/gpu/drm/tidss/tidss_crtc.c b/drivers/gpu/drm/tidss/tidss_crtc.c index cb66a425dd200492ce5d400ba8b884c87f6e2afc..896a77853ebc5784c46568f059f5d68badfbfde6 100644 --- a/drivers/gpu/drm/tidss/tidss_crtc.c +++ b/drivers/gpu/drm/tidss/tidss_crtc.c @@ -270,6 +270,16 @@ static void tidss_crtc_atomic_disable(struct drm_crtc *crtc, reinit_completion(&tcrtc->framedone_completion); + /* + * If a layer is left enabled when the videoport is disabled, and the + * vid pipeline that was used for the layer is taken into use on + * another videoport, the DSS will report sync lost issues. Disable all + * the layers here as a work-around. + */ + for (u32 layer = 0; layer < tidss->feat->num_planes; layer++) + dispc_ovr_enable_layer(tidss->dispc, tcrtc->hw_videoport, layer, + false); + dispc_vp_disable(tidss->dispc, tcrtc->hw_videoport); if (!wait_for_completion_timeout(&tcrtc->framedone_completion, diff --git a/drivers/gpu/drm/tidss/tidss_plane.c b/drivers/gpu/drm/tidss/tidss_plane.c index 42d50ec5526d72830fe328ba9a3a0c5145fcf514..435b3b66ae63204fd27fc720ac960d5972cc7f80 100644 --- a/drivers/gpu/drm/tidss/tidss_plane.c +++ b/drivers/gpu/drm/tidss/tidss_plane.c @@ -211,7 +211,7 @@ struct tidss_plane *tidss_plane_create(struct tidss_device *tidss, drm_plane_helper_add(&tplane->plane, &tidss_plane_helper_funcs); - drm_plane_create_zpos_property(&tplane->plane, hw_plane_id, 0, + drm_plane_create_zpos_property(&tplane->plane, tidss->num_planes, 0, num_planes - 1); ret = drm_plane_create_color_properties(&tplane->plane, diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index 86affe987a1cbcd28291fbfeb2c9b3f55a61325b..393b97b4a991fcf3f61b1a185324dd8ac82822f9 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -383,7 +383,7 @@ static void ttm_pool_free_range(struct ttm_pool *pool, struct ttm_tt *tt, enum ttm_caching caching, pgoff_t start_page, pgoff_t end_page) { - struct page **pages = tt->pages; + struct page **pages = &tt->pages[start_page]; unsigned int order; pgoff_t i, nr; diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 780eb5d9980b279428610a8b37b1597fe0f129d6..f5fe3cc193c5e745d53c3e88fd95f0c4c5b72c7e 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -527,7 +527,7 @@ static int vc4_hdmi_connector_get_modes(struct drm_connector *connector) edid = drm_get_edid(connector, vc4_hdmi->ddc); cec_s_phys_addr_from_edid(vc4_hdmi->cec_adap, edid); if (!edid) - return -ENODEV; + return 0; drm_connector_update_edid_property(connector, edid); ret = drm_add_edid_modes(connector, edid); diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c index 0035affc3e590f1f10dc2e6574acaeeaed311dad..9b2d235168bb62c4f1657997f184071be400b473 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.c +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c @@ -93,6 +93,7 @@ static int virtio_gpu_probe(struct virtio_device *vdev) goto err_free; } + dma_set_max_seg_size(dev->dev, dma_max_mapping_size(dev->dev) ?: UINT_MAX); ret = virtio_gpu_init(vdev, dev); if (ret) goto err_free; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index b909a3ce9af3ca92621e7d3d9994ac24ac7cb717..53f63ad656a41e96896cb010bdfc25e8fb6aadc3 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -663,11 +663,12 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv) [vmw_dma_map_populate] = "Caching DMA mappings.", [vmw_dma_map_bind] = "Giving up DMA mappings early."}; - /* TTM currently doesn't fully support SEV encryption. */ - if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) - return -EINVAL; - - if (vmw_force_coherent) + /* + * When running with SEV we always want dma mappings, because + * otherwise ttm tt pool pages will bounce through swiotlb running + * out of available space. + */ + if (vmw_force_coherent || cc_platform_has(CC_ATTR_MEM_ENCRYPT)) dev_priv->map_mode = vmw_dma_alloc_coherent; else if (vmw_restrict_iommu) dev_priv->map_mode = vmw_dma_map_bind; @@ -1429,12 +1430,15 @@ static void vmw_debugfs_resource_managers_init(struct vmw_private *vmw) root, "system_ttm"); ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, TTM_PL_VRAM), root, "vram_ttm"); - ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_GMR), - root, "gmr_ttm"); - ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_MOB), - root, "mob_ttm"); - ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_SYSTEM), - root, "system_mob_ttm"); + if (vmw->has_gmr) + ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_GMR), + root, "gmr_ttm"); + if (vmw->has_mob) { + ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_MOB), + root, "mob_ttm"); + ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_SYSTEM), + root, "system_mob_ttm"); + } } static int vmwgfx_pm_notifier(struct notifier_block *nb, unsigned long val, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index bc7f02e4ecebbb4045315608de43cd369306a319..2f7ac91149fc001720306dba625ae73e4f6d1cca 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -447,7 +447,7 @@ static int vmw_resource_context_res_add(struct vmw_private *dev_priv, vmw_res_type(ctx) == vmw_res_dx_context) { for (i = 0; i < cotable_max; ++i) { res = vmw_context_cotable(ctx, i); - if (IS_ERR(res)) + if (IS_ERR_OR_NULL(res)) continue; ret = vmw_execbuf_res_val_add(sw_context, res, @@ -1259,6 +1259,8 @@ static int vmw_cmd_dx_define_query(struct vmw_private *dev_priv, return -EINVAL; cotable_res = vmw_context_cotable(ctx_node->ctx, SVGA_COTABLE_DXQUERY); + if (IS_ERR_OR_NULL(cotable_res)) + return cotable_res ? PTR_ERR(cotable_res) : -EINVAL; ret = vmw_cotable_notify(cotable_res, cmd->body.queryId); return ret; @@ -2477,6 +2479,8 @@ static int vmw_cmd_dx_view_define(struct vmw_private *dev_priv, return ret; res = vmw_context_cotable(ctx_node->ctx, vmw_view_cotables[view_type]); + if (IS_ERR_OR_NULL(res)) + return res ? PTR_ERR(res) : -EINVAL; ret = vmw_cotable_notify(res, cmd->defined_id); if (unlikely(ret != 0)) return ret; @@ -2562,8 +2566,8 @@ static int vmw_cmd_dx_so_define(struct vmw_private *dev_priv, so_type = vmw_so_cmd_to_type(header->id); res = vmw_context_cotable(ctx_node->ctx, vmw_so_cotables[so_type]); - if (IS_ERR(res)) - return PTR_ERR(res); + if (IS_ERR_OR_NULL(res)) + return res ? PTR_ERR(res) : -EINVAL; cmd = container_of(header, typeof(*cmd), header); ret = vmw_cotable_notify(res, cmd->defined_id); @@ -2682,6 +2686,8 @@ static int vmw_cmd_dx_define_shader(struct vmw_private *dev_priv, return -EINVAL; res = vmw_context_cotable(ctx_node->ctx, SVGA_COTABLE_DXSHADER); + if (IS_ERR_OR_NULL(res)) + return res ? PTR_ERR(res) : -EINVAL; ret = vmw_cotable_notify(res, cmd->body.shaderId); if (ret) return ret; @@ -3003,6 +3009,8 @@ static int vmw_cmd_dx_define_streamoutput(struct vmw_private *dev_priv, } res = vmw_context_cotable(ctx_node->ctx, SVGA_COTABLE_STREAMOUTPUT); + if (IS_ERR_OR_NULL(res)) + return res ? PTR_ERR(res) : -EINVAL; ret = vmw_cotable_notify(res, cmd->body.soid); if (ret) return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c index 66cc35dc223e709089e5d2b4051658bc1a335d9d..95344735d00e6fef328d986e4d830b94b7ad560b 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c @@ -991,7 +991,7 @@ static int vmw_event_fence_action_create(struct drm_file *file_priv, } event->event.base.type = DRM_VMW_EVENT_FENCE_SIGNALED; - event->event.base.length = sizeof(*event); + event->event.base.length = sizeof(event->event); event->event.user_data = user_data; ret = drm_event_reserve_init(dev, file_priv, &event->base, &event->event.base); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c index 60e3cc537f36574e871b7febe0f164db8890338f..b9e5c8cd31001a72d0f7b7386cb6b4bc9062b345 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c @@ -65,8 +65,11 @@ static int vmw_gmrid_man_get_node(struct ttm_resource_manager *man, ttm_resource_init(bo, place, *res); id = ida_alloc_max(&gman->gmr_ida, gman->max_gmr_ids - 1, GFP_KERNEL); - if (id < 0) + if (id < 0) { + ttm_resource_fini(man, *res); + kfree(*res); return id; + } spin_lock(&gman->lock); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index aa571b75cd07f6ad6f9ded6418fbd1e02e41a609..b1aed051b41abdb78264ac2a3670afdf46870de4 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -793,6 +793,7 @@ int vmw_du_cursor_plane_atomic_check(struct drm_plane *plane, int vmw_du_crtc_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *state) { + struct vmw_private *vmw = vmw_priv(crtc->dev); struct drm_crtc_state *new_state = drm_atomic_get_new_crtc_state(state, crtc); struct vmw_display_unit *du = vmw_crtc_to_du(new_state->crtc); @@ -800,9 +801,13 @@ int vmw_du_crtc_atomic_check(struct drm_crtc *crtc, bool has_primary = new_state->plane_mask & drm_plane_mask(crtc->primary); - /* We always want to have an active plane with an active CRTC */ - if (has_primary != new_state->enable) - return -EINVAL; + /* + * This is fine in general, but broken userspace might expect + * some actual rendering so give a clue as why it's blank. + */ + if (new_state->enable && !has_primary) + drm_dbg_driver(&vmw->drm, + "CRTC without a primary plane will be blank.\n"); if (new_state->connector_mask != connector_mask && diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h index b02d2793659f9253222ad7a9496dd51ece7fc9c3..b116600b343a846d5606a4f601a48efde2f17944 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h @@ -246,10 +246,10 @@ struct vmw_framebuffer_bo { static const uint32_t __maybe_unused vmw_primary_plane_formats[] = { - DRM_FORMAT_XRGB1555, - DRM_FORMAT_RGB565, DRM_FORMAT_XRGB8888, DRM_FORMAT_ARGB8888, + DRM_FORMAT_RGB565, + DRM_FORMAT_XRGB1555, }; static const uint32_t __maybe_unused vmw_cursor_plane_formats[] = { diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c index bdee16a0bb8e217a8f063ea5cfa3eccb5c9a3c70..ba622fb5e48225fb7fc4f8b1b417d89cf346384c 100644 --- a/drivers/gpu/host1x/bus.c +++ b/drivers/gpu/host1x/bus.c @@ -368,11 +368,6 @@ static int host1x_device_uevent(struct device *dev, return 0; } -static int host1x_dma_configure(struct device *dev) -{ - return of_dma_configure(dev, dev->of_node, true); -} - static const struct dev_pm_ops host1x_device_pm_ops = { .suspend = pm_generic_suspend, .resume = pm_generic_resume, @@ -386,7 +381,6 @@ struct bus_type host1x_bus_type = { .name = "host1x", .match = host1x_device_match, .uevent = host1x_device_uevent, - .dma_configure = host1x_dma_configure, .pm = &host1x_device_pm_ops, }; @@ -475,8 +469,6 @@ static int host1x_device_add(struct host1x *host1x, device->dev.bus = &host1x_bus_type; device->dev.parent = host1x->dev; - of_dma_configure(&device->dev, host1x->dev->of_node, true); - device->dev.dma_parms = &device->dma_parms; dma_set_max_seg_size(&device->dev, UINT_MAX); diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c index c936d6a51c0cd6750d8f46c9a831d9655d9e3335..9c963ad27f9d18e9c32af331f86551e841f19a27 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c @@ -34,6 +34,8 @@ static int sensor_mask_override = -1; module_param_named(sensor_mask, sensor_mask_override, int, 0444); MODULE_PARM_DESC(sensor_mask, "override the detected sensors mask"); +static bool intr_disable = true; + static int amd_sfh_wait_response_v2(struct amd_mp2_dev *mp2, u8 sid, u32 sensor_sts) { union cmd_response cmd_resp; @@ -54,7 +56,7 @@ static void amd_start_sensor_v2(struct amd_mp2_dev *privdata, struct amd_mp2_sen cmd_base.ul = 0; cmd_base.cmd_v2.cmd_id = ENABLE_SENSOR; - cmd_base.cmd_v2.intr_disable = 1; + cmd_base.cmd_v2.intr_disable = intr_disable; cmd_base.cmd_v2.period = info.period; cmd_base.cmd_v2.sensor_id = info.sensor_idx; cmd_base.cmd_v2.length = 16; @@ -72,7 +74,7 @@ static void amd_stop_sensor_v2(struct amd_mp2_dev *privdata, u16 sensor_idx) cmd_base.ul = 0; cmd_base.cmd_v2.cmd_id = DISABLE_SENSOR; - cmd_base.cmd_v2.intr_disable = 1; + cmd_base.cmd_v2.intr_disable = intr_disable; cmd_base.cmd_v2.period = 0; cmd_base.cmd_v2.sensor_id = sensor_idx; cmd_base.cmd_v2.length = 16; @@ -86,7 +88,7 @@ static void amd_stop_all_sensor_v2(struct amd_mp2_dev *privdata) union sfh_cmd_base cmd_base; cmd_base.cmd_v2.cmd_id = STOP_ALL_SENSORS; - cmd_base.cmd_v2.intr_disable = 1; + cmd_base.cmd_v2.intr_disable = intr_disable; cmd_base.cmd_v2.period = 0; cmd_base.cmd_v2.sensor_id = 0; @@ -288,6 +290,26 @@ int amd_sfh_irq_init(struct amd_mp2_dev *privdata) return 0; } +static int mp2_disable_intr(const struct dmi_system_id *id) +{ + intr_disable = false; + return 0; +} + +static const struct dmi_system_id dmi_sfh_table[] = { + { + /* + * https://bugzilla.kernel.org/show_bug.cgi?id=218104 + */ + .callback = mp2_disable_intr, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook x360 435 G7"), + }, + }, + {} +}; + static const struct dmi_system_id dmi_nodevs[] = { { /* @@ -311,6 +333,8 @@ static int amd_mp2_pci_probe(struct pci_dev *pdev, const struct pci_device_id *i if (dmi_first_match(dmi_nodevs)) return -ENODEV; + dmi_check_system(dmi_sfh_table); + privdata = devm_kzalloc(&pdev->dev, sizeof(*privdata), GFP_KERNEL); if (!privdata) return -ENOMEM; diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h index dfb7cabd82efec722b842955c4ab2368018700b6..2b125cd9742cbbed00a9da24e13b1c74723ab3e4 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h +++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h @@ -89,10 +89,10 @@ enum mem_use_type { struct hpd_status { union { struct { - u32 human_presence_report : 4; - u32 human_presence_actual : 4; - u32 probablity : 8; u32 object_distance : 16; + u32 probablity : 8; + u32 human_presence_actual : 4; + u32 human_presence_report : 4; } shpd; u32 val; }; diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 3f4e23bb69839163188d81467fe1d703f1e80ed0..3bb776f3fe8c187cd75b6a96b2bd5b19de096fec 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -720,10 +720,10 @@ #define USB_DEVICE_ID_KYE_GPEN_560 0x5003 #define USB_DEVICE_ID_KYE_EASYPEN_I405X 0x5010 #define USB_DEVICE_ID_KYE_MOUSEPEN_I608X 0x5011 -#define USB_DEVICE_ID_KYE_MOUSEPEN_I608X_V2 0x501a #define USB_DEVICE_ID_KYE_EASYPEN_M610X 0x5013 #define USB_DEVICE_ID_KYE_PENSKETCH_M912 0x5015 #define USB_DEVICE_ID_KYE_EASYPEN_M406XE 0x5019 +#define USB_DEVICE_ID_KYE_MOUSEPEN_I608X_V2 0x501A #define USB_VENDOR_ID_LABTEC 0x1020 #define USB_DEVICE_ID_LABTEC_WIRELESS_KEYBOARD 0x0006 diff --git a/drivers/hid/hid-kye.c b/drivers/hid/hid-kye.c index da903138eee4901c9e94a1f4061bc960365f78ef..dc57e9d4a3e20ccf65ae05fcd8eb60ff41d6b0cb 100644 --- a/drivers/hid/hid-kye.c +++ b/drivers/hid/hid-kye.c @@ -602,6 +602,18 @@ static __u8 *kye_report_fixup(struct hid_device *hdev, __u8 *rdesc, rdesc[74] = 0x08; } break; + case USB_DEVICE_ID_GENIUS_GILA_GAMING_MOUSE: + rdesc = kye_consumer_control_fixup(hdev, rdesc, rsize, 104, + "Genius Gila Gaming Mouse"); + break; + case USB_DEVICE_ID_GENIUS_MANTICORE: + rdesc = kye_consumer_control_fixup(hdev, rdesc, rsize, 104, + "Genius Manticore Keyboard"); + break; + case USB_DEVICE_ID_GENIUS_GX_IMPERATOR: + rdesc = kye_consumer_control_fixup(hdev, rdesc, rsize, 83, + "Genius Gx Imperator Keyboard"); + break; case USB_DEVICE_ID_KYE_EASYPEN_I405X: if (*rsize == EASYPEN_I405X_RDESC_ORIG_SIZE) { rdesc = easypen_i405x_rdesc_fixed; @@ -638,18 +650,6 @@ static __u8 *kye_report_fixup(struct hid_device *hdev, __u8 *rdesc, *rsize = sizeof(pensketch_m912_rdesc_fixed); } break; - case USB_DEVICE_ID_GENIUS_GILA_GAMING_MOUSE: - rdesc = kye_consumer_control_fixup(hdev, rdesc, rsize, 104, - "Genius Gila Gaming Mouse"); - break; - case USB_DEVICE_ID_GENIUS_GX_IMPERATOR: - rdesc = kye_consumer_control_fixup(hdev, rdesc, rsize, 83, - "Genius Gx Imperator Keyboard"); - break; - case USB_DEVICE_ID_GENIUS_MANTICORE: - rdesc = kye_consumer_control_fixup(hdev, rdesc, rsize, 104, - "Genius Manticore Keyboard"); - break; } return rdesc; } @@ -717,26 +717,26 @@ static int kye_probe(struct hid_device *hdev, const struct hid_device_id *id) } switch (id->product) { + case USB_DEVICE_ID_GENIUS_MANTICORE: + /* + * The manticore keyboard needs to have all the interfaces + * opened at least once to be fully functional. + */ + if (hid_hw_open(hdev)) + hid_hw_close(hdev); + break; case USB_DEVICE_ID_KYE_EASYPEN_I405X: case USB_DEVICE_ID_KYE_MOUSEPEN_I608X: - case USB_DEVICE_ID_KYE_MOUSEPEN_I608X_V2: case USB_DEVICE_ID_KYE_EASYPEN_M610X: - case USB_DEVICE_ID_KYE_EASYPEN_M406XE: case USB_DEVICE_ID_KYE_PENSKETCH_M912: + case USB_DEVICE_ID_KYE_EASYPEN_M406XE: + case USB_DEVICE_ID_KYE_MOUSEPEN_I608X_V2: ret = kye_tablet_enable(hdev); if (ret) { hid_err(hdev, "tablet enabling failed\n"); goto enabling_err; } break; - case USB_DEVICE_ID_GENIUS_MANTICORE: - /* - * The manticore keyboard needs to have all the interfaces - * opened at least once to be fully functional. - */ - if (hid_hw_open(hdev)) - hid_hw_close(hdev); - break; } return 0; @@ -749,23 +749,23 @@ err: static const struct hid_device_id kye_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_ERGO_525V) }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, - USB_DEVICE_ID_KYE_EASYPEN_I405X) }, + USB_DEVICE_ID_GENIUS_GILA_GAMING_MOUSE) }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, - USB_DEVICE_ID_KYE_MOUSEPEN_I608X) }, + USB_DEVICE_ID_GENIUS_MANTICORE) }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, - USB_DEVICE_ID_KYE_MOUSEPEN_I608X_V2) }, + USB_DEVICE_ID_GENIUS_GX_IMPERATOR) }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, - USB_DEVICE_ID_KYE_EASYPEN_M610X) }, + USB_DEVICE_ID_KYE_EASYPEN_I405X) }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, - USB_DEVICE_ID_KYE_EASYPEN_M406XE) }, + USB_DEVICE_ID_KYE_MOUSEPEN_I608X) }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, - USB_DEVICE_ID_GENIUS_GILA_GAMING_MOUSE) }, + USB_DEVICE_ID_KYE_EASYPEN_M610X) }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, - USB_DEVICE_ID_GENIUS_GX_IMPERATOR) }, + USB_DEVICE_ID_KYE_PENSKETCH_M912) }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, - USB_DEVICE_ID_GENIUS_MANTICORE) }, + USB_DEVICE_ID_KYE_EASYPEN_M406XE) }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, - USB_DEVICE_ID_KYE_PENSKETCH_M912) }, + USB_DEVICE_ID_KYE_MOUSEPEN_I608X_V2) }, { } }; MODULE_DEVICE_TABLE(hid, kye_devices); diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c index 149a3c74346b4f28b0f97fba19b99427e85cd89a..f86c1ea83a0378c565ff1be4707933c8a5c2f4d2 100644 --- a/drivers/hid/hid-lenovo.c +++ b/drivers/hid/hid-lenovo.c @@ -54,10 +54,10 @@ struct lenovo_drvdata { /* 0: Up * 1: Down (undecided) * 2: Scrolling - * 3: Patched firmware, disable workaround */ u8 middlebutton_state; bool fn_lock; + bool middleclick_workaround_cptkbd; }; #define map_key_clear(c) hid_map_usage_clear(hi, usage, bit, max, EV_KEY, (c)) @@ -621,6 +621,36 @@ static ssize_t attr_sensitivity_store_cptkbd(struct device *dev, return count; } +static ssize_t attr_middleclick_workaround_show_cptkbd(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hid_device *hdev = to_hid_device(dev); + struct lenovo_drvdata *cptkbd_data = hid_get_drvdata(hdev); + + return snprintf(buf, PAGE_SIZE, "%u\n", + cptkbd_data->middleclick_workaround_cptkbd); +} + +static ssize_t attr_middleclick_workaround_store_cptkbd(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t count) +{ + struct hid_device *hdev = to_hid_device(dev); + struct lenovo_drvdata *cptkbd_data = hid_get_drvdata(hdev); + int value; + + if (kstrtoint(buf, 10, &value)) + return -EINVAL; + if (value < 0 || value > 1) + return -EINVAL; + + cptkbd_data->middleclick_workaround_cptkbd = !!value; + + return count; +} + static struct device_attribute dev_attr_fn_lock = __ATTR(fn_lock, S_IWUSR | S_IRUGO, @@ -632,10 +662,16 @@ static struct device_attribute dev_attr_sensitivity_cptkbd = attr_sensitivity_show_cptkbd, attr_sensitivity_store_cptkbd); +static struct device_attribute dev_attr_middleclick_workaround_cptkbd = + __ATTR(middleclick_workaround, S_IWUSR | S_IRUGO, + attr_middleclick_workaround_show_cptkbd, + attr_middleclick_workaround_store_cptkbd); + static struct attribute *lenovo_attributes_cptkbd[] = { &dev_attr_fn_lock.attr, &dev_attr_sensitivity_cptkbd.attr, + &dev_attr_middleclick_workaround_cptkbd.attr, NULL }; @@ -686,23 +722,7 @@ static int lenovo_event_cptkbd(struct hid_device *hdev, { struct lenovo_drvdata *cptkbd_data = hid_get_drvdata(hdev); - if (cptkbd_data->middlebutton_state != 3) { - /* REL_X and REL_Y events during middle button pressed - * are only possible on patched, bug-free firmware - * so set middlebutton_state to 3 - * to never apply workaround anymore - */ - if (hdev->product == USB_DEVICE_ID_LENOVO_CUSBKBD && - cptkbd_data->middlebutton_state == 1 && - usage->type == EV_REL && - (usage->code == REL_X || usage->code == REL_Y)) { - cptkbd_data->middlebutton_state = 3; - /* send middle button press which was hold before */ - input_event(field->hidinput->input, - EV_KEY, BTN_MIDDLE, 1); - input_sync(field->hidinput->input); - } - + if (cptkbd_data->middleclick_workaround_cptkbd) { /* "wheel" scroll events */ if (usage->type == EV_REL && (usage->code == REL_WHEEL || usage->code == REL_HWHEEL)) { @@ -1166,6 +1186,7 @@ static int lenovo_probe_cptkbd(struct hid_device *hdev) cptkbd_data->middlebutton_state = 0; cptkbd_data->fn_lock = true; cptkbd_data->sensitivity = 0x05; + cptkbd_data->middleclick_workaround_cptkbd = true; lenovo_features_set_cptkbd(hdev); ret = sysfs_create_group(&hdev->dev.kobj, &lenovo_attr_group_cptkbd); diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index 08768e5accedc626a4ddc50a79d80b6dec68f908..57697605b2e2470b9ac9b6b5e4424345b4a48638 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -965,9 +965,7 @@ static void logi_hidpp_dev_conn_notif_equad(struct hid_device *hdev, } break; case REPORT_TYPE_MOUSE: - workitem->reports_supported |= STD_MOUSE | HIDPP; - if (djrcv_dev->type == recvr_type_mouse_only) - workitem->reports_supported |= MULTIMEDIA; + workitem->reports_supported |= STD_MOUSE | HIDPP | MULTIMEDIA; break; } } diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 5ec1f174127a3205b830cd9295fed67af03dd873..3816fd06bc953cfa129727be8e32cfe5e521e954 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -2153,6 +2153,10 @@ static const struct hid_device_id mt_devices[] = { HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, USB_VENDOR_ID_SYNAPTICS, 0xcd7e) }, + { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT, + HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, + USB_VENDOR_ID_SYNAPTICS, 0xcddc) }, + { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT, HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, USB_VENDOR_ID_SYNAPTICS, 0xce08) }, diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index f1bdada24fe3b25ae1a46dcf0797b686e1757402..a7d0b9c4129da5a23ba8c992606a0e1c60b13a71 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -108,12 +108,12 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_1f4a), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_IDEACOM, USB_DEVICE_ID_IDEACOM_IDC6680), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_INNOMEDIA, USB_DEVICE_ID_INNEX_GENESIS_ATARI), HID_QUIRK_MULTI_INPUT }, - { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X), HID_QUIRK_MULTI_INPUT }, + { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_PIXART_USB_OPTICAL_MOUSE_ID2), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X), HID_QUIRK_MULTI_INPUT }, - { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_V2), HID_QUIRK_MULTI_INPUT }, + { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_PENSKETCH_M912), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M406XE), HID_QUIRK_MULTI_INPUT }, - { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_PIXART_USB_OPTICAL_MOUSE_ID2), HID_QUIRK_ALWAYS_POLL }, + { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_V2), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_OPTICAL_USB_MOUSE_600E), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019), HID_QUIRK_ALWAYS_POLL }, diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 969f8eb086f0205f73617022a4905749f63388ea..0b05bb1e4410e1eab6876c03b19afa9e034b3170 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -61,7 +61,6 @@ /* flags */ #define I2C_HID_STARTED 0 #define I2C_HID_RESET_PENDING 1 -#define I2C_HID_READ_PENDING 2 #define I2C_HID_PWR_ON 0x00 #define I2C_HID_PWR_SLEEP 0x01 @@ -193,15 +192,10 @@ static int i2c_hid_xfer(struct i2c_hid *ihid, msgs[n].len = recv_len; msgs[n].buf = recv_buf; n++; - - set_bit(I2C_HID_READ_PENDING, &ihid->flags); } ret = i2c_transfer(client->adapter, msgs, n); - if (recv_len) - clear_bit(I2C_HID_READ_PENDING, &ihid->flags); - if (ret != n) return ret < 0 ? ret : -EIO; @@ -569,9 +563,6 @@ static irqreturn_t i2c_hid_irq(int irq, void *dev_id) { struct i2c_hid *ihid = dev_id; - if (test_bit(I2C_HID_READ_PENDING, &ihid->flags)) - return IRQ_HANDLED; - i2c_hid_get_input(ihid); return IRQ_HANDLED; diff --git a/drivers/hid/i2c-hid/i2c-hid-of.c b/drivers/hid/i2c-hid/i2c-hid-of.c index 97a27a803f58d2ab6c68f255c83fd989b2b2701b..6feb812fce37591f0b1f2a9b9a58f93f67b6e827 100644 --- a/drivers/hid/i2c-hid/i2c-hid-of.c +++ b/drivers/hid/i2c-hid/i2c-hid-of.c @@ -80,6 +80,7 @@ static int i2c_hid_of_probe(struct i2c_client *client, if (!ihid_of) return -ENOMEM; + ihid_of->client = client; ihid_of->ops.power_up = i2c_hid_of_power_up; ihid_of->ops.power_down = i2c_hid_of_power_down; diff --git a/drivers/hid/intel-ish-hid/ipc/ipc.c b/drivers/hid/intel-ish-hid/ipc/ipc.c index a49c6affd7c4c48cdd09e3bdcca95139d0c066b8..dd5fc60874ba1d4f507e99fb5f28d87c16fdca9b 100644 --- a/drivers/hid/intel-ish-hid/ipc/ipc.c +++ b/drivers/hid/intel-ish-hid/ipc/ipc.c @@ -948,6 +948,7 @@ struct ishtp_device *ish_dev_init(struct pci_dev *pdev) if (!dev) return NULL; + dev->devc = &pdev->dev; ishtp_device_init(dev); init_waitqueue_head(&dev->wait_hw_ready); @@ -983,7 +984,6 @@ struct ishtp_device *ish_dev_init(struct pci_dev *pdev) } dev->ops = &ish_hw_ops; - dev->devc = &pdev->dev; dev->mtu = IPC_PAYLOAD_SIZE - sizeof(struct ishtp_msg_hdr); return dev; } diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index af163e8dfec07c8fe0ea3fbdbfcdf51ac30b9d89..12d4c28741d7e502cace1da1351b13403281f0d3 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -2080,7 +2080,7 @@ static int wacom_allocate_inputs(struct wacom *wacom) return 0; } -static int wacom_register_inputs(struct wacom *wacom) +static int wacom_setup_inputs(struct wacom *wacom) { struct input_dev *pen_input_dev, *touch_input_dev, *pad_input_dev; struct wacom_wac *wacom_wac = &(wacom->wacom_wac); @@ -2099,10 +2099,6 @@ static int wacom_register_inputs(struct wacom *wacom) input_free_device(pen_input_dev); wacom_wac->pen_input = NULL; pen_input_dev = NULL; - } else { - error = input_register_device(pen_input_dev); - if (error) - goto fail; } error = wacom_setup_touch_input_capabilities(touch_input_dev, wacom_wac); @@ -2111,10 +2107,6 @@ static int wacom_register_inputs(struct wacom *wacom) input_free_device(touch_input_dev); wacom_wac->touch_input = NULL; touch_input_dev = NULL; - } else { - error = input_register_device(touch_input_dev); - if (error) - goto fail; } error = wacom_setup_pad_input_capabilities(pad_input_dev, wacom_wac); @@ -2123,7 +2115,34 @@ static int wacom_register_inputs(struct wacom *wacom) input_free_device(pad_input_dev); wacom_wac->pad_input = NULL; pad_input_dev = NULL; - } else { + } + + return 0; +} + +static int wacom_register_inputs(struct wacom *wacom) +{ + struct input_dev *pen_input_dev, *touch_input_dev, *pad_input_dev; + struct wacom_wac *wacom_wac = &(wacom->wacom_wac); + int error = 0; + + pen_input_dev = wacom_wac->pen_input; + touch_input_dev = wacom_wac->touch_input; + pad_input_dev = wacom_wac->pad_input; + + if (pen_input_dev) { + error = input_register_device(pen_input_dev); + if (error) + goto fail; + } + + if (touch_input_dev) { + error = input_register_device(touch_input_dev); + if (error) + goto fail; + } + + if (pad_input_dev) { error = input_register_device(pad_input_dev); if (error) goto fail; @@ -2379,6 +2398,20 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless) goto fail; } + error = wacom_setup_inputs(wacom); + if (error) + goto fail; + + if (features->type == HID_GENERIC) + connect_mask |= HID_CONNECT_DRIVER; + + /* Regular HID work starts now */ + error = hid_hw_start(hdev, connect_mask); + if (error) { + hid_err(hdev, "hw start failed\n"); + goto fail; + } + error = wacom_register_inputs(wacom); if (error) goto fail; @@ -2393,16 +2426,6 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless) goto fail; } - if (features->type == HID_GENERIC) - connect_mask |= HID_CONNECT_DRIVER; - - /* Regular HID work starts now */ - error = hid_hw_start(hdev, connect_mask); - if (error) { - hid_err(hdev, "hw start failed\n"); - goto fail; - } - if (!wireless) { /* Note that if query fails it is not a hard failure */ wacom_query_tablet_data(wacom); diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 165ed872fa4e773c4591b5889ff0c0559a2cf7bc..53235b276bb248cab1b1f89e0059d962012e9a97 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -2571,7 +2571,14 @@ static void wacom_wac_pen_report(struct hid_device *hdev, wacom_wac->hid_data.tipswitch); input_report_key(input, wacom_wac->tool[0], sense); if (wacom_wac->serial[0]) { - input_event(input, EV_MSC, MSC_SERIAL, wacom_wac->serial[0]); + /* + * xf86-input-wacom does not accept a serial number + * of '0'. Report the low 32 bits if possible, but + * if they are zero, report the upper ones instead. + */ + __u32 serial_lo = wacom_wac->serial[0] & 0xFFFFFFFFu; + __u32 serial_hi = wacom_wac->serial[0] >> 32; + input_event(input, EV_MSC, MSC_SERIAL, (int)(serial_lo ? serial_lo : serial_hi)); input_report_abs(input, ABS_MISC, sense ? id : 0); } diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 56f7e06c673e4236ba8d1e01957723a800af63a0..47e1bd8de9fcf050b055e7f8905b08c5397d4f69 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -153,7 +153,9 @@ void vmbus_free_ring(struct vmbus_channel *channel) hv_ringbuffer_cleanup(&channel->inbound); if (channel->ringbuffer_page) { - __free_pages(channel->ringbuffer_page, + /* In a CoCo VM leak the memory if it didn't get re-encrypted */ + if (!channel->ringbuffer_gpadlhandle.decrypted) + __free_pages(channel->ringbuffer_page, get_order(channel->ringbuffer_pagecount << PAGE_SHIFT)); channel->ringbuffer_page = NULL; @@ -472,9 +474,18 @@ static int __vmbus_establish_gpadl(struct vmbus_channel *channel, (atomic_inc_return(&vmbus_connection.next_gpadl_handle) - 1); ret = create_gpadl_header(type, kbuffer, size, send_offset, &msginfo); - if (ret) + if (ret) { + gpadl->decrypted = false; return ret; + } + /* + * Set the "decrypted" flag to true for the set_memory_decrypted() + * success case. In the failure case, the encryption state of the + * memory is unknown. Leave "decrypted" as true to ensure the + * memory will be leaked instead of going back on the free list. + */ + gpadl->decrypted = true; ret = set_memory_decrypted((unsigned long)kbuffer, PFN_UP(size)); if (ret) { @@ -563,9 +574,15 @@ cleanup: kfree(msginfo); - if (ret) - set_memory_encrypted((unsigned long)kbuffer, - PFN_UP(size)); + if (ret) { + /* + * If set_memory_encrypted() fails, the decrypted flag is + * left as true so the memory is leaked instead of being + * put back on the free list. + */ + if (!set_memory_encrypted((unsigned long)kbuffer, PFN_UP(size))) + gpadl->decrypted = false; + } return ret; } @@ -886,6 +903,8 @@ post_msg_err: if (ret) pr_warn("Fail to set mem host visibility in GPADL teardown %d.\n", ret); + gpadl->decrypted = ret; + return ret; } EXPORT_SYMBOL_GPL(vmbus_teardown_gpadl); diff --git a/drivers/hwmon/amc6821.c b/drivers/hwmon/amc6821.c index 3bfd12ff4b3ca67aa2cc2883524a9b93b8f26f7d..6868db4ac84f38cf86bdef23e9ba5f0cee8d319b 100644 --- a/drivers/hwmon/amc6821.c +++ b/drivers/hwmon/amc6821.c @@ -934,10 +934,21 @@ static const struct i2c_device_id amc6821_id[] = { MODULE_DEVICE_TABLE(i2c, amc6821_id); +static const struct of_device_id __maybe_unused amc6821_of_match[] = { + { + .compatible = "ti,amc6821", + .data = (void *)amc6821, + }, + { } +}; + +MODULE_DEVICE_TABLE(of, amc6821_of_match); + static struct i2c_driver amc6821_driver = { .class = I2C_CLASS_HWMON, .driver = { .name = "amc6821", + .of_match_table = of_match_ptr(amc6821_of_match), }, .probe_new = amc6821_probe, .id_table = amc6821_id, diff --git a/drivers/hwmon/aspeed-pwm-tacho.c b/drivers/hwmon/aspeed-pwm-tacho.c index d11f674e3dc37e7d601a1dbf87fb73f7eb47cd0e..51f321bcd778ae45dda3720c13a9deff699d9812 100644 --- a/drivers/hwmon/aspeed-pwm-tacho.c +++ b/drivers/hwmon/aspeed-pwm-tacho.c @@ -194,6 +194,8 @@ struct aspeed_pwm_tacho_data { u8 fan_tach_ch_source[16]; struct aspeed_cooling_device *cdev[8]; const struct attribute_group *groups[3]; + /* protects access to shared ASPEED_PTCR_RESULT */ + struct mutex tach_lock; }; enum type { TYPEM, TYPEN, TYPEO }; @@ -528,6 +530,8 @@ static int aspeed_get_fan_tach_ch_rpm(struct aspeed_pwm_tacho_data *priv, u8 fan_tach_ch_source, type, mode, both; int ret; + mutex_lock(&priv->tach_lock); + regmap_write(priv->regmap, ASPEED_PTCR_TRIGGER, 0); regmap_write(priv->regmap, ASPEED_PTCR_TRIGGER, 0x1 << fan_tach_ch); @@ -545,6 +549,8 @@ static int aspeed_get_fan_tach_ch_rpm(struct aspeed_pwm_tacho_data *priv, ASPEED_RPM_STATUS_SLEEP_USEC, usec); + mutex_unlock(&priv->tach_lock); + /* return -ETIMEDOUT if we didn't get an answer. */ if (ret) return ret; @@ -904,6 +910,7 @@ static int aspeed_pwm_tacho_probe(struct platform_device *pdev) priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; + mutex_init(&priv->tach_lock); priv->regmap = devm_regmap_init(dev, NULL, (__force void *)regs, &aspeed_pwm_tacho_regmap_config); if (IS_ERR(priv->regmap)) diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index 09aab5859fa75c6e16e5899ba7e290d971d67266..c0aa6bfa66b244b339c7f0c0ba5572fe88f61daf 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -40,7 +40,7 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius"); #define PKG_SYSFS_ATTR_NO 1 /* Sysfs attribute for package temp */ #define BASE_SYSFS_ATTR_NO 2 /* Sysfs Base attr no for coretemp */ -#define NUM_REAL_CORES 128 /* Number of Real cores per cpu */ +#define NUM_REAL_CORES 512 /* Number of Real cores per cpu */ #define CORETEMP_NAME_LENGTH 28 /* String Length of attrs */ #define MAX_CORE_ATTRS 4 /* Maximum no of basic attrs */ #define TOTAL_ATTRS (MAX_CORE_ATTRS + 1) @@ -380,7 +380,7 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev) } static int create_core_attrs(struct temp_data *tdata, struct device *dev, - int attr_no) + int index) { int i; static ssize_t (*const rd_ptr[TOTAL_ATTRS]) (struct device *dev, @@ -392,13 +392,20 @@ static int create_core_attrs(struct temp_data *tdata, struct device *dev, }; for (i = 0; i < tdata->attr_size; i++) { + /* + * We map the attr number to core id of the CPU + * The attr number is always core id + 2 + * The Pkgtemp will always show up as temp1_*, if available + */ + int attr_no = tdata->is_pkg_data ? 1 : tdata->cpu_core_id + 2; + snprintf(tdata->attr_name[i], CORETEMP_NAME_LENGTH, "temp%d_%s", attr_no, suffixes[i]); sysfs_attr_init(&tdata->sd_attrs[i].dev_attr.attr); tdata->sd_attrs[i].dev_attr.attr.name = tdata->attr_name[i]; tdata->sd_attrs[i].dev_attr.attr.mode = 0444; tdata->sd_attrs[i].dev_attr.show = rd_ptr[i]; - tdata->sd_attrs[i].index = attr_no; + tdata->sd_attrs[i].index = index; tdata->attrs[i] = &tdata->sd_attrs[i].dev_attr.attr; } tdata->attr_group.attrs = tdata->attrs; @@ -456,27 +463,22 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu, struct platform_data *pdata = platform_get_drvdata(pdev); struct cpuinfo_x86 *c = &cpu_data(cpu); u32 eax, edx; - int err, index, attr_no; + int err, index; /* - * Find attr number for sysfs: - * We map the attr number to core id of the CPU - * The attr number is always core id + 2 - * The Pkgtemp will always show up as temp1_*, if available + * Get the index of tdata in pdata->core_data[] + * tdata for package: pdata->core_data[1] + * tdata for core: pdata->core_data[2] .. pdata->core_data[NUM_REAL_CORES + 1] */ if (pkg_flag) { - attr_no = PKG_SYSFS_ATTR_NO; + index = PKG_SYSFS_ATTR_NO; } else { - index = ida_alloc(&pdata->ida, GFP_KERNEL); + index = ida_alloc_max(&pdata->ida, NUM_REAL_CORES - 1, GFP_KERNEL); if (index < 0) return index; - pdata->cpu_map[index] = topology_core_id(cpu); - attr_no = index + BASE_SYSFS_ATTR_NO; - } - if (attr_no > MAX_CORE_DATA - 1) { - err = -ERANGE; - goto ida_free; + pdata->cpu_map[index] = topology_core_id(cpu); + index += BASE_SYSFS_ATTR_NO; } tdata = init_temp_data(cpu, pkg_flag); @@ -508,20 +510,20 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu, } } - pdata->core_data[attr_no] = tdata; + pdata->core_data[index] = tdata; /* Create sysfs interfaces */ - err = create_core_attrs(tdata, pdata->hwmon_dev, attr_no); + err = create_core_attrs(tdata, pdata->hwmon_dev, index); if (err) goto exit_free; return 0; exit_free: - pdata->core_data[attr_no] = NULL; + pdata->core_data[index] = NULL; kfree(tdata); ida_free: if (!pkg_flag) - ida_free(&pdata->ida, index); + ida_free(&pdata->ida, index - BASE_SYSFS_ATTR_NO); return err; } diff --git a/drivers/hwmon/corsair-cpro.c b/drivers/hwmon/corsair-cpro.c index fa6aa4fc8b5213dacccd954bb137219bf5644854..486fb6a8c3566469135c05d8f593a05acfd45d88 100644 --- a/drivers/hwmon/corsair-cpro.c +++ b/drivers/hwmon/corsair-cpro.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #define USB_VENDOR_ID_CORSAIR 0x1b1c @@ -77,8 +78,11 @@ struct ccp_device { struct hid_device *hdev; struct device *hwmon_dev; + /* For reinitializing the completion below */ + spinlock_t wait_input_report_lock; struct completion wait_input_report; struct mutex mutex; /* whenever buffer is used, lock before send_usb_cmd */ + u8 *cmd_buffer; u8 *buffer; int target[6]; DECLARE_BITMAP(temp_cnct, NUM_TEMP_SENSORS); @@ -111,15 +115,23 @@ static int send_usb_cmd(struct ccp_device *ccp, u8 command, u8 byte1, u8 byte2, unsigned long t; int ret; - memset(ccp->buffer, 0x00, OUT_BUFFER_SIZE); - ccp->buffer[0] = command; - ccp->buffer[1] = byte1; - ccp->buffer[2] = byte2; - ccp->buffer[3] = byte3; - + memset(ccp->cmd_buffer, 0x00, OUT_BUFFER_SIZE); + ccp->cmd_buffer[0] = command; + ccp->cmd_buffer[1] = byte1; + ccp->cmd_buffer[2] = byte2; + ccp->cmd_buffer[3] = byte3; + + /* + * Disable raw event parsing for a moment to safely reinitialize the + * completion. Reinit is done because hidraw could have triggered + * the raw event parsing and marked the ccp->wait_input_report + * completion as done. + */ + spin_lock_bh(&ccp->wait_input_report_lock); reinit_completion(&ccp->wait_input_report); + spin_unlock_bh(&ccp->wait_input_report_lock); - ret = hid_hw_output_report(ccp->hdev, ccp->buffer, OUT_BUFFER_SIZE); + ret = hid_hw_output_report(ccp->hdev, ccp->cmd_buffer, OUT_BUFFER_SIZE); if (ret < 0) return ret; @@ -135,11 +147,12 @@ static int ccp_raw_event(struct hid_device *hdev, struct hid_report *report, u8 struct ccp_device *ccp = hid_get_drvdata(hdev); /* only copy buffer when requested */ - if (completion_done(&ccp->wait_input_report)) - return 0; - - memcpy(ccp->buffer, data, min(IN_BUFFER_SIZE, size)); - complete(&ccp->wait_input_report); + spin_lock(&ccp->wait_input_report_lock); + if (!completion_done(&ccp->wait_input_report)) { + memcpy(ccp->buffer, data, min(IN_BUFFER_SIZE, size)); + complete_all(&ccp->wait_input_report); + } + spin_unlock(&ccp->wait_input_report_lock); return 0; } @@ -492,7 +505,11 @@ static int ccp_probe(struct hid_device *hdev, const struct hid_device_id *id) if (!ccp) return -ENOMEM; - ccp->buffer = devm_kmalloc(&hdev->dev, OUT_BUFFER_SIZE, GFP_KERNEL); + ccp->cmd_buffer = devm_kmalloc(&hdev->dev, OUT_BUFFER_SIZE, GFP_KERNEL); + if (!ccp->cmd_buffer) + return -ENOMEM; + + ccp->buffer = devm_kmalloc(&hdev->dev, IN_BUFFER_SIZE, GFP_KERNEL); if (!ccp->buffer) return -ENOMEM; @@ -510,7 +527,9 @@ static int ccp_probe(struct hid_device *hdev, const struct hid_device_id *id) ccp->hdev = hdev; hid_set_drvdata(hdev, ccp); + mutex_init(&ccp->mutex); + spin_lock_init(&ccp->wait_input_report_lock); init_completion(&ccp->wait_input_report); hid_device_io_start(hdev); diff --git a/drivers/hwmon/pmbus/ucd9000.c b/drivers/hwmon/pmbus/ucd9000.c index 3daaf22378322f6c2d0074bcad0f96220e227003..d6dfa268f31b84cdd260deb72f39ab673b762622 100644 --- a/drivers/hwmon/pmbus/ucd9000.c +++ b/drivers/hwmon/pmbus/ucd9000.c @@ -80,11 +80,11 @@ struct ucd9000_debugfs_entry { * It has been observed that the UCD90320 randomly fails register access when * doing another access right on the back of a register write. To mitigate this * make sure that there is a minimum delay between a write access and the - * following access. The 250us is based on experimental data. At a delay of - * 200us the issue seems to go away. Add a bit of extra margin to allow for + * following access. The 500 is based on experimental data. At a delay of + * 350us the issue seems to go away. Add a bit of extra margin to allow for * system to system differences. */ -#define UCD90320_WAIT_DELAY_US 250 +#define UCD90320_WAIT_DELAY_US 500 static inline void ucd90320_wait(const struct ucd9000_data *data) { diff --git a/drivers/hwtracing/ptt/hisi_ptt.c b/drivers/hwtracing/ptt/hisi_ptt.c index 8d8fa8e8afe04a02dd4718fc886cfa2dfa41d87b..20a9cddb3723a77631fb36e7974f07d161939cce 100644 --- a/drivers/hwtracing/ptt/hisi_ptt.c +++ b/drivers/hwtracing/ptt/hisi_ptt.c @@ -654,6 +654,9 @@ static int hisi_ptt_pmu_event_init(struct perf_event *event) int ret; u32 val; + if (event->attr.type != hisi_ptt->hisi_ptt_pmu.type) + return -ENOENT; + if (event->cpu < 0) { dev_dbg(event->pmu->dev, "Per-task mode not supported\n"); return -EOPNOTSUPP; @@ -662,9 +665,6 @@ static int hisi_ptt_pmu_event_init(struct perf_event *event) if (event->attach_state & PERF_ATTACH_TASK) return -EOPNOTSUPP; - if (event->attr.type != hisi_ptt->hisi_ptt_pmu.type) - return -ENOENT; - ret = hisi_ptt_trace_valid_filter(hisi_ptt, event->attr.config); if (ret < 0) return ret; diff --git a/drivers/i2c/busses/Makefile b/drivers/i2c/busses/Makefile index 68cb64774afc9597eade1de3bc46e5a67919d8d3..84f99018876b659c2b1343b7e37f9afd8fd0d516 100644 --- a/drivers/i2c/busses/Makefile +++ b/drivers/i2c/busses/Makefile @@ -91,10 +91,8 @@ obj-$(CONFIG_I2C_NPCM) += i2c-npcm7xx.o obj-$(CONFIG_I2C_OCORES) += i2c-ocores.o obj-$(CONFIG_I2C_OMAP) += i2c-omap.o obj-$(CONFIG_I2C_OWL) += i2c-owl.o -i2c-pasemi-objs := i2c-pasemi-core.o i2c-pasemi-pci.o -obj-$(CONFIG_I2C_PASEMI) += i2c-pasemi.o -i2c-apple-objs := i2c-pasemi-core.o i2c-pasemi-platform.o -obj-$(CONFIG_I2C_APPLE) += i2c-apple.o +obj-$(CONFIG_I2C_PASEMI) += i2c-pasemi-core.o i2c-pasemi-pci.o +obj-$(CONFIG_I2C_APPLE) += i2c-pasemi-core.o i2c-pasemi-platform.o obj-$(CONFIG_I2C_PCA_PLATFORM) += i2c-pca-platform.o obj-$(CONFIG_I2C_PNX) += i2c-pnx.o obj-$(CONFIG_I2C_PXA) += i2c-pxa.o diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 3159ffbb77a20df33f5b3cd928fd4aae249d6578..1c970842624ba309e20886ba013efb77557800ea 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -500,11 +500,10 @@ static int i801_block_transaction_by_block(struct i801_priv *priv, /* Set block buffer mode */ outb_p(inb_p(SMBAUXCTL(priv)) | SMBAUXCTL_E32B, SMBAUXCTL(priv)); - inb_p(SMBHSTCNT(priv)); /* reset the data buffer index */ - if (read_write == I2C_SMBUS_WRITE) { len = data->block[0]; outb_p(len, SMBHSTDAT0(priv)); + inb_p(SMBHSTCNT(priv)); /* reset the data buffer index */ for (i = 0; i < len; i++) outb_p(data->block[i+1], SMBBLKDAT(priv)); } @@ -520,6 +519,7 @@ static int i801_block_transaction_by_block(struct i801_priv *priv, return -EPROTO; data->block[0] = len; + inb_p(SMBHSTCNT(priv)); /* reset the data buffer index */ for (i = 0; i < len; i++) data->block[i + 1] = inb_p(SMBBLKDAT(priv)); } @@ -1422,7 +1422,6 @@ static void i801_add_mux(struct i801_priv *priv) lookup->table[i] = GPIO_LOOKUP(mux_config->gpio_chip, mux_config->gpios[i], "mux", 0); gpiod_add_lookup_table(lookup); - priv->lookup = lookup; /* * Register the mux device, we use PLATFORM_DEVID_NONE here @@ -1436,7 +1435,10 @@ static void i801_add_mux(struct i801_priv *priv) sizeof(struct i2c_mux_gpio_platform_data)); if (IS_ERR(priv->mux_pdev)) { gpiod_remove_lookup_table(lookup); + devm_kfree(dev, lookup); dev_err(dev, "Failed to register i2c-mux-gpio device\n"); + } else { + priv->lookup = lookup; } } diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index fc70920c4ddabab247eae7de1434d48e3d83d593..0c203c614197c64bef3d79740b8336c8512b79d4 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -804,6 +804,11 @@ static irqreturn_t i2c_imx_slave_handle(struct imx_i2c_struct *i2c_imx, ctl &= ~I2CR_MTX; imx_i2c_write_reg(ctl, i2c_imx, IMX_I2C_I2CR); imx_i2c_read_reg(i2c_imx, IMX_I2C_I2DR); + + /* flag the last byte as processed */ + i2c_imx_slave_event(i2c_imx, + I2C_SLAVE_READ_PROCESSED, &value); + i2c_imx_slave_finish_op(i2c_imx); return IRQ_HANDLED; } diff --git a/drivers/i2c/busses/i2c-pasemi-core.c b/drivers/i2c/busses/i2c-pasemi-core.c index 9028ffb58cc079697f6acaed7714cba5cf0bbf27..f297e41352e7aee77822359deb1ea538a9a8bf2b 100644 --- a/drivers/i2c/busses/i2c-pasemi-core.c +++ b/drivers/i2c/busses/i2c-pasemi-core.c @@ -356,3 +356,8 @@ int pasemi_i2c_common_probe(struct pasemi_smbus *smbus) return 0; } +EXPORT_SYMBOL_GPL(pasemi_i2c_common_probe); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Olof Johansson "); +MODULE_DESCRIPTION("PA Semi PWRficient SMBus driver"); diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 8fce98bb77ff974a23bebfc51e9189e7d11d592e..75b9c3f26bba6285c6b8b7fa3a1c00cd9ac46cc2 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -605,20 +605,20 @@ static int geni_i2c_gpi_xfer(struct geni_i2c_dev *gi2c, struct i2c_msg msgs[], i peripheral.addr = msgs[i].addr; + ret = geni_i2c_gpi(gi2c, &msgs[i], &config, + &tx_addr, &tx_buf, I2C_WRITE, gi2c->tx_c); + if (ret) + goto err; + if (msgs[i].flags & I2C_M_RD) { ret = geni_i2c_gpi(gi2c, &msgs[i], &config, &rx_addr, &rx_buf, I2C_READ, gi2c->rx_c); if (ret) goto err; - } - - ret = geni_i2c_gpi(gi2c, &msgs[i], &config, - &tx_addr, &tx_buf, I2C_WRITE, gi2c->tx_c); - if (ret) - goto err; - if (msgs[i].flags & I2C_M_RD) dma_async_issue_pending(gi2c->rx_c); + } + dma_async_issue_pending(gi2c->tx_c); timeout = wait_for_completion_timeout(&gi2c->done, XFER_TIMEOUT); diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 5e3976ba52650087869eb9761c72bbf4c9c4676d..1ebc953799149d5a2fc2009bcf029ec23ae1772a 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -2075,13 +2075,18 @@ static int i2c_check_for_quirks(struct i2c_adapter *adap, struct i2c_msg *msgs, * Returns negative errno, else the number of messages executed. * * Adapter lock must be held when calling this function. No debug logging - * takes place. adap->algo->master_xfer existence isn't checked. + * takes place. */ int __i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) { unsigned long orig_jiffies; int ret, try; + if (!adap->algo->master_xfer) { + dev_dbg(&adap->dev, "I2C level transfers not supported\n"); + return -EOPNOTSUPP; + } + if (WARN_ON(!msgs || num < 1)) return -EINVAL; @@ -2148,11 +2153,6 @@ int i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) { int ret; - if (!adap->algo->master_xfer) { - dev_dbg(&adap->dev, "I2C level transfers not supported\n"); - return -EOPNOTSUPP; - } - /* REVISIT the fault reporting model here is weak: * * - When we get an error after receiving N bytes from a slave, diff --git a/drivers/iio/accel/Kconfig b/drivers/iio/accel/Kconfig index ffac66db7ac92901d74aeec22d43f303c268d8d7..1f34747a68bfe78a7623c903f8dbd4d3201e755e 100644 --- a/drivers/iio/accel/Kconfig +++ b/drivers/iio/accel/Kconfig @@ -219,10 +219,12 @@ config BMA400 config BMA400_I2C tristate + select REGMAP_I2C depends on BMA400 config BMA400_SPI tristate + select REGMAP_SPI depends on BMA400 config BMC150_ACCEL diff --git a/drivers/iio/accel/adxl367.c b/drivers/iio/accel/adxl367.c index 7c7d780407937a2a7cb1897685b30db7b4f72d25..f1a41b92543af890bab047e5eb3cb1430b39e73b 100644 --- a/drivers/iio/accel/adxl367.c +++ b/drivers/iio/accel/adxl367.c @@ -1444,9 +1444,11 @@ static int adxl367_verify_devid(struct adxl367_state *st) unsigned int val; int ret; - ret = regmap_read_poll_timeout(st->regmap, ADXL367_REG_DEVID, val, - val == ADXL367_DEVID_AD, 1000, 10000); + ret = regmap_read(st->regmap, ADXL367_REG_DEVID, &val); if (ret) + return dev_err_probe(st->dev, ret, "Failed to read dev id\n"); + + if (val != ADXL367_DEVID_AD) return dev_err_probe(st->dev, -ENODEV, "Invalid dev id 0x%02X, expected 0x%02X\n", val, ADXL367_DEVID_AD); @@ -1543,6 +1545,8 @@ int adxl367_probe(struct device *dev, const struct adxl367_ops *ops, if (ret) return ret; + fsleep(15000); + ret = adxl367_verify_devid(st); if (ret) return ret; diff --git a/drivers/iio/accel/adxl367_i2c.c b/drivers/iio/accel/adxl367_i2c.c index 3606efa25835eac4d0daf2f61d518ba140975716..5c040915276d112b14ddb8c237211141caaab1aa 100644 --- a/drivers/iio/accel/adxl367_i2c.c +++ b/drivers/iio/accel/adxl367_i2c.c @@ -11,7 +11,7 @@ #include "adxl367.h" -#define ADXL367_I2C_FIFO_DATA 0x42 +#define ADXL367_I2C_FIFO_DATA 0x18 struct adxl367_i2c_state { struct regmap *regmap; diff --git a/drivers/iio/accel/mxc4005.c b/drivers/iio/accel/mxc4005.c index df600d2917c0ad56250922ef4bc431989bf28796..ffae30e5eb5bee0114919e7f740c14e471a0f4d9 100644 --- a/drivers/iio/accel/mxc4005.c +++ b/drivers/iio/accel/mxc4005.c @@ -27,9 +27,13 @@ #define MXC4005_REG_ZOUT_UPPER 0x07 #define MXC4005_REG_ZOUT_LOWER 0x08 +#define MXC4005_REG_INT_MASK0 0x0A + #define MXC4005_REG_INT_MASK1 0x0B #define MXC4005_REG_INT_MASK1_BIT_DRDYE 0x01 +#define MXC4005_REG_INT_CLR0 0x00 + #define MXC4005_REG_INT_CLR1 0x01 #define MXC4005_REG_INT_CLR1_BIT_DRDYC 0x01 @@ -113,7 +117,9 @@ static bool mxc4005_is_readable_reg(struct device *dev, unsigned int reg) static bool mxc4005_is_writeable_reg(struct device *dev, unsigned int reg) { switch (reg) { + case MXC4005_REG_INT_CLR0: case MXC4005_REG_INT_CLR1: + case MXC4005_REG_INT_MASK0: case MXC4005_REG_INT_MASK1: case MXC4005_REG_CONTROL: return true; @@ -330,17 +336,13 @@ static int mxc4005_set_trigger_state(struct iio_trigger *trig, { struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig); struct mxc4005_data *data = iio_priv(indio_dev); + unsigned int val; int ret; mutex_lock(&data->mutex); - if (state) { - ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK1, - MXC4005_REG_INT_MASK1_BIT_DRDYE); - } else { - ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK1, - ~MXC4005_REG_INT_MASK1_BIT_DRDYE); - } + val = state ? MXC4005_REG_INT_MASK1_BIT_DRDYE : 0; + ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK1, val); if (ret < 0) { mutex_unlock(&data->mutex); dev_err(data->dev, "failed to update reg_int_mask1"); @@ -382,6 +384,14 @@ static int mxc4005_chip_init(struct mxc4005_data *data) dev_dbg(data->dev, "MXC4005 chip id %02x\n", reg); + ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK0, 0); + if (ret < 0) + return dev_err_probe(data->dev, ret, "writing INT_MASK0\n"); + + ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK1, 0); + if (ret < 0) + return dev_err_probe(data->dev, ret, "writing INT_MASK1\n"); + return 0; } diff --git a/drivers/iio/imu/adis16475.c b/drivers/iio/imu/adis16475.c index 2d939773445d79db77442df7b9f3d26466b37846..e2931ea8af1f4ce0461feb59a3a2a4e818df8c09 100644 --- a/drivers/iio/imu/adis16475.c +++ b/drivers/iio/imu/adis16475.c @@ -1126,6 +1126,7 @@ static int adis16475_config_sync_mode(struct adis16475 *st) struct device *dev = &st->adis.spi->dev; const struct adis16475_sync *sync; u32 sync_mode; + u16 val; /* default to internal clk */ st->clk_freq = st->info->int_clk * 1000; @@ -1187,8 +1188,9 @@ static int adis16475_config_sync_mode(struct adis16475 *st) * I'm keeping this for simplicity and avoiding extra variables * in chip_info. */ + val = ADIS16475_SYNC_MODE(sync->sync_mode); ret = __adis_update_bits(&st->adis, ADIS16475_REG_MSG_CTRL, - ADIS16475_SYNC_MODE_MASK, sync->sync_mode); + ADIS16475_SYNC_MODE_MASK, val); if (ret) return ret; diff --git a/drivers/iio/imu/bno055/Kconfig b/drivers/iio/imu/bno055/Kconfig index 83e53acfbe88011f4306f19438b6f31d4cad5b22..c7f5866a177d90edef7c30bfe54ada71cc17870c 100644 --- a/drivers/iio/imu/bno055/Kconfig +++ b/drivers/iio/imu/bno055/Kconfig @@ -8,6 +8,7 @@ config BOSCH_BNO055 config BOSCH_BNO055_SERIAL tristate "Bosch BNO055 attached via UART" depends on SERIAL_DEV_BUS + select REGMAP select BOSCH_BNO055 help Enable this to support Bosch BNO055 IMUs attached via UART. diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index c9614982cb671ac68008053f622149b6865ea369..a2f8278f00856a88cd4b51bb538e16c6d34a24b4 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -1601,10 +1601,13 @@ static int iio_device_register_sysfs(struct iio_dev *indio_dev) ret = iio_device_register_sysfs_group(indio_dev, &iio_dev_opaque->chan_attr_group); if (ret) - goto error_clear_attrs; + goto error_free_chan_attrs; return 0; +error_free_chan_attrs: + kfree(iio_dev_opaque->chan_attr_group.attrs); + iio_dev_opaque->chan_attr_group.attrs = NULL; error_clear_attrs: iio_free_chan_devattr_list(&iio_dev_opaque->channel_attr_list); diff --git a/drivers/iio/light/hid-sensor-als.c b/drivers/iio/light/hid-sensor-als.c index 5a1a625d8d16de9fe439b70038af175e0a8df345..85097b769c209a6e6c872f31d5e1f97134c6e8f2 100644 --- a/drivers/iio/light/hid-sensor-als.c +++ b/drivers/iio/light/hid-sensor-als.c @@ -228,6 +228,7 @@ static int als_capture_sample(struct hid_sensor_hub_device *hsdev, case HID_USAGE_SENSOR_TIME_TIMESTAMP: als_state->timestamp = hid_sensor_convert_timestamp(&als_state->common_attributes, *(s64 *)raw_data); + ret = 0; break; default: break; diff --git a/drivers/iio/magnetometer/rm3100-core.c b/drivers/iio/magnetometer/rm3100-core.c index 69938204456f8bb0c1c4777d93ee7d0b8f2421dd..42b70cd42b39359ddd542e273163cab829128ab4 100644 --- a/drivers/iio/magnetometer/rm3100-core.c +++ b/drivers/iio/magnetometer/rm3100-core.c @@ -530,6 +530,7 @@ int rm3100_common_probe(struct device *dev, struct regmap *regmap, int irq) struct rm3100_data *data; unsigned int tmp; int ret; + int samp_rate_index; indio_dev = devm_iio_device_alloc(dev, sizeof(*data)); if (!indio_dev) @@ -586,9 +587,14 @@ int rm3100_common_probe(struct device *dev, struct regmap *regmap, int irq) ret = regmap_read(regmap, RM3100_REG_TMRC, &tmp); if (ret < 0) return ret; + + samp_rate_index = tmp - RM3100_TMRC_OFFSET; + if (samp_rate_index < 0 || samp_rate_index >= RM3100_SAMP_NUM) { + dev_err(dev, "The value read from RM3100_REG_TMRC is invalid!\n"); + return -EINVAL; + } /* Initializing max wait time, which is double conversion time. */ - data->conversion_time = rm3100_samp_rates[tmp - RM3100_TMRC_OFFSET][2] - * 2; + data->conversion_time = rm3100_samp_rates[samp_rate_index][2] * 2; /* Cycle count values may not be what we want. */ if ((tmp - RM3100_TMRC_OFFSET) == 0) diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index b7f9023442890c32558d46a21715988f972548f2..950fe205995b76f60a07072197246c1adb65806d 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -34,6 +34,7 @@ MODULE_AUTHOR("Sean Hefty"); MODULE_DESCRIPTION("InfiniBand CM"); MODULE_LICENSE("Dual BSD/GPL"); +#define CM_DESTROY_ID_WAIT_TIMEOUT 10000 /* msecs */ static const char * const ibcm_rej_reason_strs[] = { [IB_CM_REJ_NO_QP] = "no QP", [IB_CM_REJ_NO_EEC] = "no EEC", @@ -1025,13 +1026,26 @@ static void cm_reset_to_idle(struct cm_id_private *cm_id_priv) } } +static noinline void cm_destroy_id_wait_timeout(struct ib_cm_id *cm_id, + enum ib_cm_state old_state) +{ + struct cm_id_private *cm_id_priv; + + cm_id_priv = container_of(cm_id, struct cm_id_private, id); + pr_err("%s: cm_id=%p timed out. state %d -> %d, refcnt=%d\n", __func__, + cm_id, old_state, cm_id->state, refcount_read(&cm_id_priv->refcount)); +} + static void cm_destroy_id(struct ib_cm_id *cm_id, int err) { struct cm_id_private *cm_id_priv; + enum ib_cm_state old_state; struct cm_work *work; + int ret; cm_id_priv = container_of(cm_id, struct cm_id_private, id); spin_lock_irq(&cm_id_priv->lock); + old_state = cm_id->state; retest: switch (cm_id->state) { case IB_CM_LISTEN: @@ -1135,7 +1149,14 @@ retest: xa_erase(&cm.local_id_table, cm_local_id(cm_id->local_id)); cm_deref_id(cm_id_priv); - wait_for_completion(&cm_id_priv->comp); + do { + ret = wait_for_completion_timeout(&cm_id_priv->comp, + msecs_to_jiffies( + CM_DESTROY_ID_WAIT_TIMEOUT)); + if (!ret) /* timeout happened */ + cm_destroy_id_wait_timeout(cm_id, old_state); + } while (!ret); + while ((work = cm_dequeue_work(cm_id_priv)) != NULL) cm_free_work(work); diff --git a/drivers/infiniband/core/cm_trace.h b/drivers/infiniband/core/cm_trace.h index e9d282679ef15542e05f32a7867c018edcd38a65..944d9071245d26bc4ef4fae0fdd242e14e095770 100644 --- a/drivers/infiniband/core/cm_trace.h +++ b/drivers/infiniband/core/cm_trace.h @@ -16,7 +16,7 @@ #include #include -#include +#include /* * enum ib_cm_state, from include/rdma/ib_cm.h diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 0773ca7ace247cdc280e25333a21e43a45fc07da..067d7f42871ff2eb91e38cda9e0202de53b0ebe8 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -3547,121 +3547,6 @@ err: return ret; } -static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, - const struct sockaddr *dst_addr) -{ - struct sockaddr_storage zero_sock = {}; - - if (src_addr && src_addr->sa_family) - return rdma_bind_addr(id, src_addr); - - /* - * When the src_addr is not specified, automatically supply an any addr - */ - zero_sock.ss_family = dst_addr->sa_family; - if (IS_ENABLED(CONFIG_IPV6) && dst_addr->sa_family == AF_INET6) { - struct sockaddr_in6 *src_addr6 = - (struct sockaddr_in6 *)&zero_sock; - struct sockaddr_in6 *dst_addr6 = - (struct sockaddr_in6 *)dst_addr; - - src_addr6->sin6_scope_id = dst_addr6->sin6_scope_id; - if (ipv6_addr_type(&dst_addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL) - id->route.addr.dev_addr.bound_dev_if = - dst_addr6->sin6_scope_id; - } else if (dst_addr->sa_family == AF_IB) { - ((struct sockaddr_ib *)&zero_sock)->sib_pkey = - ((struct sockaddr_ib *)dst_addr)->sib_pkey; - } - return rdma_bind_addr(id, (struct sockaddr *)&zero_sock); -} - -/* - * If required, resolve the source address for bind and leave the id_priv in - * state RDMA_CM_ADDR_BOUND. This oddly uses the state to determine the prior - * calls made by ULP, a previously bound ID will not be re-bound and src_addr is - * ignored. - */ -static int resolve_prepare_src(struct rdma_id_private *id_priv, - struct sockaddr *src_addr, - const struct sockaddr *dst_addr) -{ - int ret; - - memcpy(cma_dst_addr(id_priv), dst_addr, rdma_addr_size(dst_addr)); - if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY)) { - /* For a well behaved ULP state will be RDMA_CM_IDLE */ - ret = cma_bind_addr(&id_priv->id, src_addr, dst_addr); - if (ret) - goto err_dst; - if (WARN_ON(!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, - RDMA_CM_ADDR_QUERY))) { - ret = -EINVAL; - goto err_dst; - } - } - - if (cma_family(id_priv) != dst_addr->sa_family) { - ret = -EINVAL; - goto err_state; - } - return 0; - -err_state: - cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND); -err_dst: - memset(cma_dst_addr(id_priv), 0, rdma_addr_size(dst_addr)); - return ret; -} - -int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, - const struct sockaddr *dst_addr, unsigned long timeout_ms) -{ - struct rdma_id_private *id_priv = - container_of(id, struct rdma_id_private, id); - int ret; - - ret = resolve_prepare_src(id_priv, src_addr, dst_addr); - if (ret) - return ret; - - if (cma_any_addr(dst_addr)) { - ret = cma_resolve_loopback(id_priv); - } else { - if (dst_addr->sa_family == AF_IB) { - ret = cma_resolve_ib_addr(id_priv); - } else { - /* - * The FSM can return back to RDMA_CM_ADDR_BOUND after - * rdma_resolve_ip() is called, eg through the error - * path in addr_handler(). If this happens the existing - * request must be canceled before issuing a new one. - * Since canceling a request is a bit slow and this - * oddball path is rare, keep track once a request has - * been issued. The track turns out to be a permanent - * state since this is the only cancel as it is - * immediately before rdma_resolve_ip(). - */ - if (id_priv->used_resolve_ip) - rdma_addr_cancel(&id->route.addr.dev_addr); - else - id_priv->used_resolve_ip = 1; - ret = rdma_resolve_ip(cma_src_addr(id_priv), dst_addr, - &id->route.addr.dev_addr, - timeout_ms, addr_handler, - false, id_priv); - } - } - if (ret) - goto err; - - return 0; -err: - cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND); - return ret; -} -EXPORT_SYMBOL(rdma_resolve_addr); - int rdma_set_reuseaddr(struct rdma_cm_id *id, int reuse) { struct rdma_id_private *id_priv; @@ -4064,27 +3949,26 @@ err: } EXPORT_SYMBOL(rdma_listen); -int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) +static int rdma_bind_addr_dst(struct rdma_id_private *id_priv, + struct sockaddr *addr, const struct sockaddr *daddr) { - struct rdma_id_private *id_priv; + struct sockaddr *id_daddr; int ret; - struct sockaddr *daddr; if (addr->sa_family != AF_INET && addr->sa_family != AF_INET6 && addr->sa_family != AF_IB) return -EAFNOSUPPORT; - id_priv = container_of(id, struct rdma_id_private, id); if (!cma_comp_exch(id_priv, RDMA_CM_IDLE, RDMA_CM_ADDR_BOUND)) return -EINVAL; - ret = cma_check_linklocal(&id->route.addr.dev_addr, addr); + ret = cma_check_linklocal(&id_priv->id.route.addr.dev_addr, addr); if (ret) goto err1; memcpy(cma_src_addr(id_priv), addr, rdma_addr_size(addr)); if (!cma_any_addr(addr)) { - ret = cma_translate_addr(addr, &id->route.addr.dev_addr); + ret = cma_translate_addr(addr, &id_priv->id.route.addr.dev_addr); if (ret) goto err1; @@ -4104,8 +3988,10 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) } #endif } - daddr = cma_dst_addr(id_priv); - daddr->sa_family = addr->sa_family; + id_daddr = cma_dst_addr(id_priv); + if (daddr != id_daddr) + memcpy(id_daddr, daddr, rdma_addr_size(addr)); + id_daddr->sa_family = addr->sa_family; ret = cma_get_port(id_priv); if (ret) @@ -4121,6 +4007,129 @@ err1: cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_IDLE); return ret; } + +static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, + const struct sockaddr *dst_addr) +{ + struct rdma_id_private *id_priv = + container_of(id, struct rdma_id_private, id); + struct sockaddr_storage zero_sock = {}; + + if (src_addr && src_addr->sa_family) + return rdma_bind_addr_dst(id_priv, src_addr, dst_addr); + + /* + * When the src_addr is not specified, automatically supply an any addr + */ + zero_sock.ss_family = dst_addr->sa_family; + if (IS_ENABLED(CONFIG_IPV6) && dst_addr->sa_family == AF_INET6) { + struct sockaddr_in6 *src_addr6 = + (struct sockaddr_in6 *)&zero_sock; + struct sockaddr_in6 *dst_addr6 = + (struct sockaddr_in6 *)dst_addr; + + src_addr6->sin6_scope_id = dst_addr6->sin6_scope_id; + if (ipv6_addr_type(&dst_addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL) + id->route.addr.dev_addr.bound_dev_if = + dst_addr6->sin6_scope_id; + } else if (dst_addr->sa_family == AF_IB) { + ((struct sockaddr_ib *)&zero_sock)->sib_pkey = + ((struct sockaddr_ib *)dst_addr)->sib_pkey; + } + return rdma_bind_addr_dst(id_priv, (struct sockaddr *)&zero_sock, dst_addr); +} + +/* + * If required, resolve the source address for bind and leave the id_priv in + * state RDMA_CM_ADDR_BOUND. This oddly uses the state to determine the prior + * calls made by ULP, a previously bound ID will not be re-bound and src_addr is + * ignored. + */ +static int resolve_prepare_src(struct rdma_id_private *id_priv, + struct sockaddr *src_addr, + const struct sockaddr *dst_addr) +{ + int ret; + + if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY)) { + /* For a well behaved ULP state will be RDMA_CM_IDLE */ + ret = cma_bind_addr(&id_priv->id, src_addr, dst_addr); + if (ret) + return ret; + if (WARN_ON(!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, + RDMA_CM_ADDR_QUERY))) + return -EINVAL; + + } else { + memcpy(cma_dst_addr(id_priv), dst_addr, rdma_addr_size(dst_addr)); + } + + if (cma_family(id_priv) != dst_addr->sa_family) { + ret = -EINVAL; + goto err_state; + } + return 0; + +err_state: + cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND); + return ret; +} + +int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, + const struct sockaddr *dst_addr, unsigned long timeout_ms) +{ + struct rdma_id_private *id_priv = + container_of(id, struct rdma_id_private, id); + int ret; + + ret = resolve_prepare_src(id_priv, src_addr, dst_addr); + if (ret) + return ret; + + if (cma_any_addr(dst_addr)) { + ret = cma_resolve_loopback(id_priv); + } else { + if (dst_addr->sa_family == AF_IB) { + ret = cma_resolve_ib_addr(id_priv); + } else { + /* + * The FSM can return back to RDMA_CM_ADDR_BOUND after + * rdma_resolve_ip() is called, eg through the error + * path in addr_handler(). If this happens the existing + * request must be canceled before issuing a new one. + * Since canceling a request is a bit slow and this + * oddball path is rare, keep track once a request has + * been issued. The track turns out to be a permanent + * state since this is the only cancel as it is + * immediately before rdma_resolve_ip(). + */ + if (id_priv->used_resolve_ip) + rdma_addr_cancel(&id->route.addr.dev_addr); + else + id_priv->used_resolve_ip = 1; + ret = rdma_resolve_ip(cma_src_addr(id_priv), dst_addr, + &id->route.addr.dev_addr, + timeout_ms, addr_handler, + false, id_priv); + } + } + if (ret) + goto err; + + return 0; +err: + cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND); + return ret; +} +EXPORT_SYMBOL(rdma_resolve_addr); + +int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) +{ + struct rdma_id_private *id_priv = + container_of(id, struct rdma_id_private, id); + + return rdma_bind_addr_dst(id_priv, addr, cma_dst_addr(id_priv)); +} EXPORT_SYMBOL(rdma_bind_addr); static int cma_format_hdr(void *hdr, struct rdma_id_private *id_priv) diff --git a/drivers/infiniband/core/cma_trace.h b/drivers/infiniband/core/cma_trace.h index e45264267bcc99f6929662bf3793ef52b055406d..47f3c6e4be8932affcd57d2e7e83fb0a97ec1e1c 100644 --- a/drivers/infiniband/core/cma_trace.h +++ b/drivers/infiniband/core/cma_trace.h @@ -15,7 +15,7 @@ #define _TRACE_RDMA_CMA_H #include -#include +#include DECLARE_EVENT_CLASS(cma_fsm_class, diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 3a9b9a28d858fc1460f5f89a2cc1b9175e58786d..453188db39d83c74aa83c94b73d5ecf860895f43 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -1730,7 +1730,7 @@ static int assign_client_id(struct ib_client *client) { int ret; - down_write(&clients_rwsem); + lockdep_assert_held(&clients_rwsem); /* * The add/remove callbacks must be called in FIFO/LIFO order. To * achieve this we assign client_ids so they are sorted in @@ -1739,14 +1739,11 @@ static int assign_client_id(struct ib_client *client) client->client_id = highest_client_id; ret = xa_insert(&clients, client->client_id, client, GFP_KERNEL); if (ret) - goto out; + return ret; highest_client_id++; xa_set_mark(&clients, client->client_id, CLIENT_REGISTERED); - -out: - up_write(&clients_rwsem); - return ret; + return 0; } static void remove_client_id(struct ib_client *client) @@ -1776,25 +1773,35 @@ int ib_register_client(struct ib_client *client) { struct ib_device *device; unsigned long index; + bool need_unreg = false; int ret; refcount_set(&client->uses, 1); init_completion(&client->uses_zero); + + /* + * The devices_rwsem is held in write mode to ensure that a racing + * ib_register_device() sees a consisent view of clients and devices. + */ + down_write(&devices_rwsem); + down_write(&clients_rwsem); ret = assign_client_id(client); if (ret) - return ret; + goto out; - down_read(&devices_rwsem); + need_unreg = true; xa_for_each_marked (&devices, index, device, DEVICE_REGISTERED) { ret = add_client_context(device, client); - if (ret) { - up_read(&devices_rwsem); - ib_unregister_client(client); - return ret; - } + if (ret) + goto out; } - up_read(&devices_rwsem); - return 0; + ret = 0; +out: + up_write(&clients_rwsem); + up_write(&devices_rwsem); + if (need_unreg && ret) + ib_unregister_client(client); + return ret; } EXPORT_SYMBOL(ib_register_client); diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c index d96c78e436f98c3b0f205e3967376df15ba65bd5..5c284dfbe69232193ba746fd13021eb721d71ab7 100644 --- a/drivers/infiniband/core/user_mad.c +++ b/drivers/infiniband/core/user_mad.c @@ -131,6 +131,11 @@ struct ib_umad_packet { struct ib_user_mad mad; }; +struct ib_rmpp_mad_hdr { + struct ib_mad_hdr mad_hdr; + struct ib_rmpp_hdr rmpp_hdr; +} __packed; + #define CREATE_TRACE_POINTS #include @@ -494,11 +499,11 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf, size_t count, loff_t *pos) { struct ib_umad_file *file = filp->private_data; + struct ib_rmpp_mad_hdr *rmpp_mad_hdr; struct ib_umad_packet *packet; struct ib_mad_agent *agent; struct rdma_ah_attr ah_attr; struct ib_ah *ah; - struct ib_rmpp_mad *rmpp_mad; __be64 *tid; int ret, data_len, hdr_len, copy_offset, rmpp_active; u8 base_version; @@ -506,7 +511,7 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf, if (count < hdr_size(file) + IB_MGMT_RMPP_HDR) return -EINVAL; - packet = kzalloc(sizeof *packet + IB_MGMT_RMPP_HDR, GFP_KERNEL); + packet = kzalloc(sizeof(*packet) + IB_MGMT_RMPP_HDR, GFP_KERNEL); if (!packet) return -ENOMEM; @@ -560,13 +565,13 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf, goto err_up; } - rmpp_mad = (struct ib_rmpp_mad *) packet->mad.data; - hdr_len = ib_get_mad_data_offset(rmpp_mad->mad_hdr.mgmt_class); + rmpp_mad_hdr = (struct ib_rmpp_mad_hdr *)packet->mad.data; + hdr_len = ib_get_mad_data_offset(rmpp_mad_hdr->mad_hdr.mgmt_class); - if (ib_is_mad_class_rmpp(rmpp_mad->mad_hdr.mgmt_class) + if (ib_is_mad_class_rmpp(rmpp_mad_hdr->mad_hdr.mgmt_class) && ib_mad_kernel_rmpp_agent(agent)) { copy_offset = IB_MGMT_RMPP_HDR; - rmpp_active = ib_get_rmpp_flags(&rmpp_mad->rmpp_hdr) & + rmpp_active = ib_get_rmpp_flags(&rmpp_mad_hdr->rmpp_hdr) & IB_MGMT_RMPP_FLAG_ACTIVE; } else { copy_offset = IB_MGMT_MAD_HDR; @@ -615,12 +620,12 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf, tid = &((struct ib_mad_hdr *) packet->msg->mad)->tid; *tid = cpu_to_be64(((u64) agent->hi_tid) << 32 | (be64_to_cpup(tid) & 0xffffffff)); - rmpp_mad->mad_hdr.tid = *tid; + rmpp_mad_hdr->mad_hdr.tid = *tid; } if (!ib_mad_kernel_rmpp_agent(agent) - && ib_is_mad_class_rmpp(rmpp_mad->mad_hdr.mgmt_class) - && (ib_get_rmpp_flags(&rmpp_mad->rmpp_hdr) & IB_MGMT_RMPP_FLAG_ACTIVE)) { + && ib_is_mad_class_rmpp(rmpp_mad_hdr->mad_hdr.mgmt_class) + && (ib_get_rmpp_flags(&rmpp_mad_hdr->rmpp_hdr) & IB_MGMT_RMPP_FLAG_ACTIVE)) { spin_lock_irq(&file->send_lock); list_add_tail(&packet->list, &file->send_list); spin_unlock_irq(&file->send_lock); diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 4ed8814efde6fbac18e4b5aec2dc5840051c752b..6ed0568747eaa858d9549de054a0b5b66634acac 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -1710,7 +1710,7 @@ int bnxt_re_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr, switch (srq_attr_mask) { case IB_SRQ_MAX_WR: /* SRQ resize is not supported */ - break; + return -EINVAL; case IB_SRQ_LIMIT: /* Change the SRQ threshold */ if (srq_attr->srq_limit > srq->qplib_srq.max_wqe) @@ -1725,13 +1725,12 @@ int bnxt_re_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr, /* On success, update the shadow */ srq->srq_limit = srq_attr->srq_limit; /* No need to Build and send response back to udata */ - break; + return 0; default: ibdev_err(&rdev->ibdev, "Unsupported srq_attr_mask 0x%x", srq_attr_mask); return -EINVAL; } - return 0; } int bnxt_re_query_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr) diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index 51ae58c02b15c76d2919e2059dcbcdb02ead7fd3..802b0e5801a7dbbffdc124943e1ca44239010bb2 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -2089,7 +2089,7 @@ int init_credit_return(struct hfi1_devdata *dd) "Unable to allocate credit return DMA range for NUMA %d\n", i); ret = -ENOMEM; - goto done; + goto free_cr_base; } } set_dev_node(&dd->pcidev->dev, dd->node); @@ -2097,6 +2097,10 @@ int init_credit_return(struct hfi1_devdata *dd) ret = 0; done: return ret; + +free_cr_base: + free_credit_return(dd); + goto done; } void free_credit_return(struct hfi1_devdata *dd) diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 26c62162759bab6e4d3c14809f389296a345865b..969c5c3ab859e754216322e0e5d002a277da8a0d 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -3158,7 +3158,7 @@ int _pad_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx) { int rval = 0; - if ((unlikely(tx->num_desc + 1 == tx->desc_limit))) { + if ((unlikely(tx->num_desc == tx->desc_limit))) { rval = _extend_sdma_tx_descs(dd, tx); if (rval) { __sdma_txclean(dd, tx); diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index 1112afa0af5526b2e25141d49079e01234c19fbc..8748b65c87ea77b0b913fdc6beb678bd7b3173de 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -595,6 +595,13 @@ struct hns_roce_work { u32 queue_num; }; +enum hns_roce_cong_type { + CONG_TYPE_DCQCN, + CONG_TYPE_LDCP, + CONG_TYPE_HC3, + CONG_TYPE_DIP, +}; + struct hns_roce_qp { struct ib_qp ibqp; struct hns_roce_wq rq; @@ -639,6 +646,7 @@ struct hns_roce_qp { struct list_head sq_node; /* all send qps are on a list */ struct hns_user_mmap_entry *dwqe_mmap_entry; u32 config; + enum hns_roce_cong_type cong_type; }; struct hns_roce_ib_iboe { @@ -710,13 +718,6 @@ struct hns_roce_eq_table { struct hns_roce_eq *eq; }; -enum cong_type { - CONG_TYPE_DCQCN, - CONG_TYPE_LDCP, - CONG_TYPE_HC3, - CONG_TYPE_DIP, -}; - struct hns_roce_caps { u64 fw_ver; u8 num_ports; @@ -847,7 +848,7 @@ struct hns_roce_caps { u16 default_aeq_period; u16 default_aeq_arm_st; u16 default_ceq_arm_st; - enum cong_type cong_type; + enum hns_roce_cong_type cong_type; }; enum hns_roce_device_state { diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 58fbb1d3b7f41f73dc8b57cf6bf0a03c7add17f6..d06b19e69a151ba6822bdab3f107ff7b4af27b25 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -4886,12 +4886,15 @@ static int check_cong_type(struct ib_qp *ibqp, struct hns_roce_congestion_algorithm *cong_alg) { struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device); + struct hns_roce_qp *hr_qp = to_hr_qp(ibqp); - if (ibqp->qp_type == IB_QPT_UD) - hr_dev->caps.cong_type = CONG_TYPE_DCQCN; + if (ibqp->qp_type == IB_QPT_UD || ibqp->qp_type == IB_QPT_GSI) + hr_qp->cong_type = CONG_TYPE_DCQCN; + else + hr_qp->cong_type = hr_dev->caps.cong_type; /* different congestion types match different configurations */ - switch (hr_dev->caps.cong_type) { + switch (hr_qp->cong_type) { case CONG_TYPE_DCQCN: cong_alg->alg_sel = CONG_DCQCN; cong_alg->alg_sub_sel = UNSUPPORT_CONG_LEVEL; @@ -4919,8 +4922,8 @@ static int check_cong_type(struct ib_qp *ibqp, default: ibdev_warn(&hr_dev->ib_dev, "invalid type(%u) for congestion selection.\n", - hr_dev->caps.cong_type); - hr_dev->caps.cong_type = CONG_TYPE_DCQCN; + hr_qp->cong_type); + hr_qp->cong_type = CONG_TYPE_DCQCN; cong_alg->alg_sel = CONG_DCQCN; cong_alg->alg_sub_sel = UNSUPPORT_CONG_LEVEL; cong_alg->dip_vld = DIP_INVALID; @@ -4939,6 +4942,7 @@ static int fill_cong_field(struct ib_qp *ibqp, const struct ib_qp_attr *attr, struct hns_roce_congestion_algorithm cong_field; struct ib_device *ibdev = ibqp->device; struct hns_roce_dev *hr_dev = to_hr_dev(ibdev); + struct hns_roce_qp *hr_qp = to_hr_qp(ibqp); u32 dip_idx = 0; int ret; @@ -4951,7 +4955,7 @@ static int fill_cong_field(struct ib_qp *ibqp, const struct ib_qp_attr *attr, return ret; hr_reg_write(context, QPC_CONG_ALGO_TMPL_ID, hr_dev->cong_algo_tmpl_id + - hr_dev->caps.cong_type * HNS_ROCE_CONG_SIZE); + hr_qp->cong_type * HNS_ROCE_CONG_SIZE); hr_reg_clear(qpc_mask, QPC_CONG_ALGO_TMPL_ID); hr_reg_write(&context->ext, QPCEX_CONG_ALG_SEL, cong_field.alg_sel); hr_reg_clear(&qpc_mask->ext, QPCEX_CONG_ALG_SEL); diff --git a/drivers/infiniband/hw/irdma/defs.h b/drivers/infiniband/hw/irdma/defs.h index ad54260cb58c9d566ac657ce0c919a54066f534d..ebe98fa2b1cd2a52b71d7a29d841bad6c62041a6 100644 --- a/drivers/infiniband/hw/irdma/defs.h +++ b/drivers/infiniband/hw/irdma/defs.h @@ -345,6 +345,7 @@ enum irdma_cqp_op_type { #define IRDMA_AE_LLP_TOO_MANY_KEEPALIVE_RETRIES 0x050b #define IRDMA_AE_LLP_DOUBT_REACHABILITY 0x050c #define IRDMA_AE_LLP_CONNECTION_ESTABLISHED 0x050e +#define IRDMA_AE_LLP_TOO_MANY_RNRS 0x050f #define IRDMA_AE_RESOURCE_EXHAUSTION 0x0520 #define IRDMA_AE_RESET_SENT 0x0601 #define IRDMA_AE_TERMINATE_SENT 0x0602 diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c index 311a1138e838d4ec1e846d2179326ab4087ee9e4..918a2d783141f54aa88718f16d9896b0da9c1658 100644 --- a/drivers/infiniband/hw/irdma/hw.c +++ b/drivers/infiniband/hw/irdma/hw.c @@ -379,6 +379,7 @@ static void irdma_process_aeq(struct irdma_pci_f *rf) case IRDMA_AE_LLP_TOO_MANY_RETRIES: case IRDMA_AE_LCE_QP_CATASTROPHIC: case IRDMA_AE_LCE_FUNCTION_CATASTROPHIC: + case IRDMA_AE_LLP_TOO_MANY_RNRS: case IRDMA_AE_LCE_CQ_CATASTROPHIC: case IRDMA_AE_UDA_XMIT_DGRAM_TOO_LONG: default: @@ -562,6 +563,13 @@ static void irdma_destroy_irq(struct irdma_pci_f *rf, dev->irq_ops->irdma_dis_irq(dev, msix_vec->idx); irq_update_affinity_hint(msix_vec->irq, NULL); free_irq(msix_vec->irq, dev_id); + if (rf == dev_id) { + tasklet_kill(&rf->dpc_tasklet); + } else { + struct irdma_ceq *iwceq = (struct irdma_ceq *)dev_id; + + tasklet_kill(&iwceq->dpc_tasklet); + } } /** diff --git a/drivers/infiniband/hw/irdma/uk.c b/drivers/infiniband/hw/irdma/uk.c index 280d633d4ec4f1917d9b416f0ba0111e16da47e5..d691cdef5e9a39c4b5eb88faa8479ed33935c888 100644 --- a/drivers/infiniband/hw/irdma/uk.c +++ b/drivers/infiniband/hw/irdma/uk.c @@ -1414,6 +1414,78 @@ static void irdma_setup_connection_wqes(struct irdma_qp_uk *qp, IRDMA_RING_MOVE_HEAD_BY_COUNT_NOCHECK(qp->initial_ring, move_cnt); } +/** + * irdma_uk_calc_shift_wq - calculate WQE shift for both SQ and RQ + * @ukinfo: qp initialization info + * @sq_shift: Returns shift of SQ + * @rq_shift: Returns shift of RQ + */ +void irdma_uk_calc_shift_wq(struct irdma_qp_uk_init_info *ukinfo, u8 *sq_shift, + u8 *rq_shift) +{ + bool imm_support = ukinfo->uk_attrs->hw_rev >= IRDMA_GEN_2; + + irdma_get_wqe_shift(ukinfo->uk_attrs, + imm_support ? ukinfo->max_sq_frag_cnt + 1 : + ukinfo->max_sq_frag_cnt, + ukinfo->max_inline_data, sq_shift); + + irdma_get_wqe_shift(ukinfo->uk_attrs, ukinfo->max_rq_frag_cnt, 0, + rq_shift); + + if (ukinfo->uk_attrs->hw_rev == IRDMA_GEN_1) { + if (ukinfo->abi_ver > 4) + *rq_shift = IRDMA_MAX_RQ_WQE_SHIFT_GEN1; + } +} + +/** + * irdma_uk_calc_depth_shift_sq - calculate depth and shift for SQ size. + * @ukinfo: qp initialization info + * @sq_depth: Returns depth of SQ + * @sq_shift: Returns shift of SQ + */ +int irdma_uk_calc_depth_shift_sq(struct irdma_qp_uk_init_info *ukinfo, + u32 *sq_depth, u8 *sq_shift) +{ + bool imm_support = ukinfo->uk_attrs->hw_rev >= IRDMA_GEN_2; + int status; + + irdma_get_wqe_shift(ukinfo->uk_attrs, + imm_support ? ukinfo->max_sq_frag_cnt + 1 : + ukinfo->max_sq_frag_cnt, + ukinfo->max_inline_data, sq_shift); + status = irdma_get_sqdepth(ukinfo->uk_attrs, ukinfo->sq_size, + *sq_shift, sq_depth); + + return status; +} + +/** + * irdma_uk_calc_depth_shift_rq - calculate depth and shift for RQ size. + * @ukinfo: qp initialization info + * @rq_depth: Returns depth of RQ + * @rq_shift: Returns shift of RQ + */ +int irdma_uk_calc_depth_shift_rq(struct irdma_qp_uk_init_info *ukinfo, + u32 *rq_depth, u8 *rq_shift) +{ + int status; + + irdma_get_wqe_shift(ukinfo->uk_attrs, ukinfo->max_rq_frag_cnt, 0, + rq_shift); + + if (ukinfo->uk_attrs->hw_rev == IRDMA_GEN_1) { + if (ukinfo->abi_ver > 4) + *rq_shift = IRDMA_MAX_RQ_WQE_SHIFT_GEN1; + } + + status = irdma_get_rqdepth(ukinfo->uk_attrs, ukinfo->rq_size, + *rq_shift, rq_depth); + + return status; +} + /** * irdma_uk_qp_init - initialize shared qp * @qp: hw qp (user and kernel) @@ -1428,23 +1500,12 @@ int irdma_uk_qp_init(struct irdma_qp_uk *qp, struct irdma_qp_uk_init_info *info) { int ret_code = 0; u32 sq_ring_size; - u8 sqshift, rqshift; qp->uk_attrs = info->uk_attrs; if (info->max_sq_frag_cnt > qp->uk_attrs->max_hw_wq_frags || info->max_rq_frag_cnt > qp->uk_attrs->max_hw_wq_frags) return -EINVAL; - irdma_get_wqe_shift(qp->uk_attrs, info->max_rq_frag_cnt, 0, &rqshift); - if (qp->uk_attrs->hw_rev == IRDMA_GEN_1) { - irdma_get_wqe_shift(qp->uk_attrs, info->max_sq_frag_cnt, - info->max_inline_data, &sqshift); - if (info->abi_ver > 4) - rqshift = IRDMA_MAX_RQ_WQE_SHIFT_GEN1; - } else { - irdma_get_wqe_shift(qp->uk_attrs, info->max_sq_frag_cnt + 1, - info->max_inline_data, &sqshift); - } qp->qp_caps = info->qp_caps; qp->sq_base = info->sq; qp->rq_base = info->rq; @@ -1458,7 +1519,7 @@ int irdma_uk_qp_init(struct irdma_qp_uk *qp, struct irdma_qp_uk_init_info *info) qp->sq_size = info->sq_size; qp->push_mode = false; qp->max_sq_frag_cnt = info->max_sq_frag_cnt; - sq_ring_size = qp->sq_size << sqshift; + sq_ring_size = qp->sq_size << info->sq_shift; IRDMA_RING_INIT(qp->sq_ring, sq_ring_size); IRDMA_RING_INIT(qp->initial_ring, sq_ring_size); if (info->first_sq_wq) { @@ -1473,9 +1534,9 @@ int irdma_uk_qp_init(struct irdma_qp_uk *qp, struct irdma_qp_uk_init_info *info) qp->rq_size = info->rq_size; qp->max_rq_frag_cnt = info->max_rq_frag_cnt; qp->max_inline_data = info->max_inline_data; - qp->rq_wqe_size = rqshift; + qp->rq_wqe_size = info->rq_shift; IRDMA_RING_INIT(qp->rq_ring, qp->rq_size); - qp->rq_wqe_size_multiplier = 1 << rqshift; + qp->rq_wqe_size_multiplier = 1 << info->rq_shift; if (qp->uk_attrs->hw_rev == IRDMA_GEN_1) qp->wqe_ops = iw_wqe_uk_ops_gen_1; else diff --git a/drivers/infiniband/hw/irdma/user.h b/drivers/infiniband/hw/irdma/user.h index d0cdf609f5e06aa71c24a5471b63b8f8aab2ba36..1e0e1a71dbadad5cc77fcfc8e1e413675d5e16e3 100644 --- a/drivers/infiniband/hw/irdma/user.h +++ b/drivers/infiniband/hw/irdma/user.h @@ -295,6 +295,12 @@ void irdma_uk_cq_init(struct irdma_cq_uk *cq, struct irdma_cq_uk_init_info *info); int irdma_uk_qp_init(struct irdma_qp_uk *qp, struct irdma_qp_uk_init_info *info); +void irdma_uk_calc_shift_wq(struct irdma_qp_uk_init_info *ukinfo, u8 *sq_shift, + u8 *rq_shift); +int irdma_uk_calc_depth_shift_sq(struct irdma_qp_uk_init_info *ukinfo, + u32 *sq_depth, u8 *sq_shift); +int irdma_uk_calc_depth_shift_rq(struct irdma_qp_uk_init_info *ukinfo, + u32 *rq_depth, u8 *rq_shift); struct irdma_sq_uk_wr_trk_info { u64 wrid; u32 wr_len; @@ -374,8 +380,12 @@ struct irdma_qp_uk_init_info { u32 max_sq_frag_cnt; u32 max_rq_frag_cnt; u32 max_inline_data; + u32 sq_depth; + u32 rq_depth; u8 first_sq_wq; u8 type; + u8 sq_shift; + u8 rq_shift; int abi_ver; bool legacy_mode; }; diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 447e1bcc82a323036dc6d2dcd3ba8cc5a39f8f33..76c5f461faca0997fe9ef2f15807fe2fe671e637 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -277,7 +277,7 @@ static int irdma_alloc_ucontext(struct ib_ucontext *uctx, struct irdma_alloc_ucontext_req req = {}; struct irdma_alloc_ucontext_resp uresp = {}; struct irdma_ucontext *ucontext = to_ucontext(uctx); - struct irdma_uk_attrs *uk_attrs; + struct irdma_uk_attrs *uk_attrs = &iwdev->rf->sc_dev.hw_attrs.uk_attrs; if (udata->inlen < IRDMA_ALLOC_UCTX_MIN_REQ_LEN || udata->outlen < IRDMA_ALLOC_UCTX_MIN_RESP_LEN) @@ -292,7 +292,9 @@ static int irdma_alloc_ucontext(struct ib_ucontext *uctx, ucontext->iwdev = iwdev; ucontext->abi_ver = req.userspace_ver; - uk_attrs = &iwdev->rf->sc_dev.hw_attrs.uk_attrs; + if (req.comp_mask & IRDMA_ALLOC_UCTX_USE_RAW_ATTR) + ucontext->use_raw_attrs = true; + /* GEN_1 legacy support with libi40iw */ if (udata->outlen == IRDMA_ALLOC_UCTX_MIN_RESP_LEN) { if (uk_attrs->hw_rev != IRDMA_GEN_1) @@ -327,6 +329,7 @@ static int irdma_alloc_ucontext(struct ib_ucontext *uctx, uresp.max_hw_cq_size = uk_attrs->max_hw_cq_size; uresp.min_hw_cq_size = uk_attrs->min_hw_cq_size; uresp.hw_rev = uk_attrs->hw_rev; + uresp.comp_mask |= IRDMA_ALLOC_UCTX_USE_RAW_ATTR; if (ib_copy_to_udata(udata, &uresp, min(sizeof(uresp), udata->outlen))) { rdma_user_mmap_entry_remove(ucontext->db_mmap_entry); @@ -566,6 +569,86 @@ static void irdma_setup_virt_qp(struct irdma_device *iwdev, } } +/** + * irdma_setup_umode_qp - setup sq and rq size in user mode qp + * @iwdev: iwarp device + * @iwqp: qp ptr (user or kernel) + * @info: initialize info to return + * @init_attr: Initial QP create attributes + */ +static int irdma_setup_umode_qp(struct ib_udata *udata, + struct irdma_device *iwdev, + struct irdma_qp *iwqp, + struct irdma_qp_init_info *info, + struct ib_qp_init_attr *init_attr) +{ + struct irdma_ucontext *ucontext = rdma_udata_to_drv_context(udata, + struct irdma_ucontext, ibucontext); + struct irdma_qp_uk_init_info *ukinfo = &info->qp_uk_init_info; + struct irdma_create_qp_req req; + unsigned long flags; + int ret; + + ret = ib_copy_from_udata(&req, udata, + min(sizeof(req), udata->inlen)); + if (ret) { + ibdev_dbg(&iwdev->ibdev, "VERBS: ib_copy_from_data fail\n"); + return ret; + } + + iwqp->ctx_info.qp_compl_ctx = req.user_compl_ctx; + iwqp->user_mode = 1; + if (req.user_wqe_bufs) { + info->qp_uk_init_info.legacy_mode = ucontext->legacy_mode; + spin_lock_irqsave(&ucontext->qp_reg_mem_list_lock, flags); + iwqp->iwpbl = irdma_get_pbl((unsigned long)req.user_wqe_bufs, + &ucontext->qp_reg_mem_list); + spin_unlock_irqrestore(&ucontext->qp_reg_mem_list_lock, flags); + + if (!iwqp->iwpbl) { + ret = -ENODATA; + ibdev_dbg(&iwdev->ibdev, "VERBS: no pbl info\n"); + return ret; + } + } + + if (!ucontext->use_raw_attrs) { + /** + * Maintain backward compat with older ABI which passes sq and + * rq depth in quanta in cap.max_send_wr and cap.max_recv_wr. + * There is no way to compute the correct value of + * iwqp->max_send_wr/max_recv_wr in the kernel. + */ + iwqp->max_send_wr = init_attr->cap.max_send_wr; + iwqp->max_recv_wr = init_attr->cap.max_recv_wr; + ukinfo->sq_size = init_attr->cap.max_send_wr; + ukinfo->rq_size = init_attr->cap.max_recv_wr; + irdma_uk_calc_shift_wq(ukinfo, &ukinfo->sq_shift, + &ukinfo->rq_shift); + } else { + ret = irdma_uk_calc_depth_shift_sq(ukinfo, &ukinfo->sq_depth, + &ukinfo->sq_shift); + if (ret) + return ret; + + ret = irdma_uk_calc_depth_shift_rq(ukinfo, &ukinfo->rq_depth, + &ukinfo->rq_shift); + if (ret) + return ret; + + iwqp->max_send_wr = + (ukinfo->sq_depth - IRDMA_SQ_RSVD) >> ukinfo->sq_shift; + iwqp->max_recv_wr = + (ukinfo->rq_depth - IRDMA_RQ_RSVD) >> ukinfo->rq_shift; + ukinfo->sq_size = ukinfo->sq_depth >> ukinfo->sq_shift; + ukinfo->rq_size = ukinfo->rq_depth >> ukinfo->rq_shift; + } + + irdma_setup_virt_qp(iwdev, iwqp, info); + + return 0; +} + /** * irdma_setup_kmode_qp - setup initialization for kernel mode qp * @iwdev: iwarp device @@ -579,40 +662,28 @@ static int irdma_setup_kmode_qp(struct irdma_device *iwdev, struct ib_qp_init_attr *init_attr) { struct irdma_dma_mem *mem = &iwqp->kqp.dma_mem; - u32 sqdepth, rqdepth; - u8 sqshift, rqshift; u32 size; int status; struct irdma_qp_uk_init_info *ukinfo = &info->qp_uk_init_info; - struct irdma_uk_attrs *uk_attrs = &iwdev->rf->sc_dev.hw_attrs.uk_attrs; - irdma_get_wqe_shift(uk_attrs, - uk_attrs->hw_rev >= IRDMA_GEN_2 ? ukinfo->max_sq_frag_cnt + 1 : - ukinfo->max_sq_frag_cnt, - ukinfo->max_inline_data, &sqshift); - status = irdma_get_sqdepth(uk_attrs, ukinfo->sq_size, sqshift, - &sqdepth); + status = irdma_uk_calc_depth_shift_sq(ukinfo, &ukinfo->sq_depth, + &ukinfo->sq_shift); if (status) return status; - if (uk_attrs->hw_rev == IRDMA_GEN_1) - rqshift = IRDMA_MAX_RQ_WQE_SHIFT_GEN1; - else - irdma_get_wqe_shift(uk_attrs, ukinfo->max_rq_frag_cnt, 0, - &rqshift); - - status = irdma_get_rqdepth(uk_attrs, ukinfo->rq_size, rqshift, - &rqdepth); + status = irdma_uk_calc_depth_shift_rq(ukinfo, &ukinfo->rq_depth, + &ukinfo->rq_shift); if (status) return status; iwqp->kqp.sq_wrid_mem = - kcalloc(sqdepth, sizeof(*iwqp->kqp.sq_wrid_mem), GFP_KERNEL); + kcalloc(ukinfo->sq_depth, sizeof(*iwqp->kqp.sq_wrid_mem), GFP_KERNEL); if (!iwqp->kqp.sq_wrid_mem) return -ENOMEM; iwqp->kqp.rq_wrid_mem = - kcalloc(rqdepth, sizeof(*iwqp->kqp.rq_wrid_mem), GFP_KERNEL); + kcalloc(ukinfo->rq_depth, sizeof(*iwqp->kqp.rq_wrid_mem), GFP_KERNEL); + if (!iwqp->kqp.rq_wrid_mem) { kfree(iwqp->kqp.sq_wrid_mem); iwqp->kqp.sq_wrid_mem = NULL; @@ -622,7 +693,7 @@ static int irdma_setup_kmode_qp(struct irdma_device *iwdev, ukinfo->sq_wrtrk_array = iwqp->kqp.sq_wrid_mem; ukinfo->rq_wrid_array = iwqp->kqp.rq_wrid_mem; - size = (sqdepth + rqdepth) * IRDMA_QP_WQE_MIN_SIZE; + size = (ukinfo->sq_depth + ukinfo->rq_depth) * IRDMA_QP_WQE_MIN_SIZE; size += (IRDMA_SHADOW_AREA_SIZE << 3); mem->size = ALIGN(size, 256); @@ -638,16 +709,18 @@ static int irdma_setup_kmode_qp(struct irdma_device *iwdev, ukinfo->sq = mem->va; info->sq_pa = mem->pa; - ukinfo->rq = &ukinfo->sq[sqdepth]; - info->rq_pa = info->sq_pa + (sqdepth * IRDMA_QP_WQE_MIN_SIZE); - ukinfo->shadow_area = ukinfo->rq[rqdepth].elem; - info->shadow_area_pa = info->rq_pa + (rqdepth * IRDMA_QP_WQE_MIN_SIZE); - ukinfo->sq_size = sqdepth >> sqshift; - ukinfo->rq_size = rqdepth >> rqshift; - ukinfo->qp_id = iwqp->ibqp.qp_num; - - init_attr->cap.max_send_wr = (sqdepth - IRDMA_SQ_RSVD) >> sqshift; - init_attr->cap.max_recv_wr = (rqdepth - IRDMA_RQ_RSVD) >> rqshift; + ukinfo->rq = &ukinfo->sq[ukinfo->sq_depth]; + info->rq_pa = info->sq_pa + (ukinfo->sq_depth * IRDMA_QP_WQE_MIN_SIZE); + ukinfo->shadow_area = ukinfo->rq[ukinfo->rq_depth].elem; + info->shadow_area_pa = + info->rq_pa + (ukinfo->rq_depth * IRDMA_QP_WQE_MIN_SIZE); + ukinfo->sq_size = ukinfo->sq_depth >> ukinfo->sq_shift; + ukinfo->rq_size = ukinfo->rq_depth >> ukinfo->rq_shift; + + iwqp->max_send_wr = (ukinfo->sq_depth - IRDMA_SQ_RSVD) >> ukinfo->sq_shift; + iwqp->max_recv_wr = (ukinfo->rq_depth - IRDMA_RQ_RSVD) >> ukinfo->rq_shift; + init_attr->cap.max_send_wr = iwqp->max_send_wr; + init_attr->cap.max_recv_wr = iwqp->max_recv_wr; return 0; } @@ -762,7 +835,9 @@ static int irdma_validate_qp_attrs(struct ib_qp_init_attr *init_attr, if (init_attr->cap.max_inline_data > uk_attrs->max_hw_inline || init_attr->cap.max_send_sge > uk_attrs->max_hw_wq_frags || - init_attr->cap.max_recv_sge > uk_attrs->max_hw_wq_frags) + init_attr->cap.max_recv_sge > uk_attrs->max_hw_wq_frags || + init_attr->cap.max_send_wr > uk_attrs->max_hw_wq_quanta || + init_attr->cap.max_recv_wr > uk_attrs->max_hw_rq_quanta) return -EINVAL; if (rdma_protocol_roce(&iwdev->ibdev, 1)) { @@ -803,18 +878,14 @@ static int irdma_create_qp(struct ib_qp *ibqp, struct irdma_device *iwdev = to_iwdev(ibpd->device); struct irdma_pci_f *rf = iwdev->rf; struct irdma_qp *iwqp = to_iwqp(ibqp); - struct irdma_create_qp_req req = {}; struct irdma_create_qp_resp uresp = {}; u32 qp_num = 0; int err_code; - int sq_size; - int rq_size; struct irdma_sc_qp *qp; struct irdma_sc_dev *dev = &rf->sc_dev; struct irdma_uk_attrs *uk_attrs = &dev->hw_attrs.uk_attrs; struct irdma_qp_init_info init_info = {}; struct irdma_qp_host_ctx_info *ctx_info; - unsigned long flags; err_code = irdma_validate_qp_attrs(init_attr, iwdev); if (err_code) @@ -824,13 +895,10 @@ static int irdma_create_qp(struct ib_qp *ibqp, udata->outlen < IRDMA_CREATE_QP_MIN_RESP_LEN)) return -EINVAL; - sq_size = init_attr->cap.max_send_wr; - rq_size = init_attr->cap.max_recv_wr; - init_info.vsi = &iwdev->vsi; init_info.qp_uk_init_info.uk_attrs = uk_attrs; - init_info.qp_uk_init_info.sq_size = sq_size; - init_info.qp_uk_init_info.rq_size = rq_size; + init_info.qp_uk_init_info.sq_size = init_attr->cap.max_send_wr; + init_info.qp_uk_init_info.rq_size = init_attr->cap.max_recv_wr; init_info.qp_uk_init_info.max_sq_frag_cnt = init_attr->cap.max_send_sge; init_info.qp_uk_init_info.max_rq_frag_cnt = init_attr->cap.max_recv_sge; init_info.qp_uk_init_info.max_inline_data = init_attr->cap.max_inline_data; @@ -872,7 +940,7 @@ static int irdma_create_qp(struct ib_qp *ibqp, iwqp->host_ctx.size = IRDMA_QP_CTX_SIZE; init_info.pd = &iwpd->sc_pd; - init_info.qp_uk_init_info.qp_id = iwqp->ibqp.qp_num; + init_info.qp_uk_init_info.qp_id = qp_num; if (!rdma_protocol_roce(&iwdev->ibdev, 1)) init_info.qp_uk_init_info.first_sq_wq = 1; iwqp->ctx_info.qp_compl_ctx = (uintptr_t)qp; @@ -880,36 +948,9 @@ static int irdma_create_qp(struct ib_qp *ibqp, init_waitqueue_head(&iwqp->mod_qp_waitq); if (udata) { - err_code = ib_copy_from_udata(&req, udata, - min(sizeof(req), udata->inlen)); - if (err_code) { - ibdev_dbg(&iwdev->ibdev, - "VERBS: ib_copy_from_data fail\n"); - goto error; - } - - iwqp->ctx_info.qp_compl_ctx = req.user_compl_ctx; - iwqp->user_mode = 1; - if (req.user_wqe_bufs) { - struct irdma_ucontext *ucontext = - rdma_udata_to_drv_context(udata, - struct irdma_ucontext, - ibucontext); - - init_info.qp_uk_init_info.legacy_mode = ucontext->legacy_mode; - spin_lock_irqsave(&ucontext->qp_reg_mem_list_lock, flags); - iwqp->iwpbl = irdma_get_pbl((unsigned long)req.user_wqe_bufs, - &ucontext->qp_reg_mem_list); - spin_unlock_irqrestore(&ucontext->qp_reg_mem_list_lock, flags); - - if (!iwqp->iwpbl) { - err_code = -ENODATA; - ibdev_dbg(&iwdev->ibdev, "VERBS: no pbl info\n"); - goto error; - } - } init_info.qp_uk_init_info.abi_ver = iwpd->sc_pd.abi_ver; - irdma_setup_virt_qp(iwdev, iwqp, &init_info); + err_code = irdma_setup_umode_qp(udata, iwdev, iwqp, &init_info, + init_attr); } else { INIT_DELAYED_WORK(&iwqp->dwork_flush, irdma_flush_worker); init_info.qp_uk_init_info.abi_ver = IRDMA_ABI_VER; @@ -964,8 +1005,6 @@ static int irdma_create_qp(struct ib_qp *ibqp, spin_lock_init(&iwqp->sc_qp.pfpdu.lock); iwqp->sig_all = (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR) ? 1 : 0; rf->qp_table[qp_num] = iwqp; - iwqp->max_send_wr = sq_size; - iwqp->max_recv_wr = rq_size; if (rdma_protocol_roce(&iwdev->ibdev, 1)) { if (dev->ws_add(&iwdev->vsi, 0)) { @@ -986,8 +1025,8 @@ static int irdma_create_qp(struct ib_qp *ibqp, if (rdma_protocol_iwarp(&iwdev->ibdev, 1)) uresp.lsmm = 1; } - uresp.actual_sq_size = sq_size; - uresp.actual_rq_size = rq_size; + uresp.actual_sq_size = init_info.qp_uk_init_info.sq_size; + uresp.actual_rq_size = init_info.qp_uk_init_info.rq_size; uresp.qp_id = qp_num; uresp.qp_caps = qp->qp_uk.qp_caps; @@ -2119,9 +2158,8 @@ static int irdma_create_cq(struct ib_cq *ibcq, info.cq_base_pa = iwcq->kmem.pa; } - if (dev->hw_attrs.uk_attrs.hw_rev >= IRDMA_GEN_2) - info.shadow_read_threshold = min(info.cq_uk_init_info.cq_size / 2, - (u32)IRDMA_MAX_CQ_READ_THRESH); + info.shadow_read_threshold = min(info.cq_uk_init_info.cq_size / 2, + (u32)IRDMA_MAX_CQ_READ_THRESH); if (irdma_sc_cq_init(cq, &info)) { ibdev_dbg(&iwdev->ibdev, "VERBS: init cq fail\n"); @@ -2825,7 +2863,7 @@ static struct ib_mr *irdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 len, iwmr->ibmr.pd = pd; iwmr->ibmr.device = pd->device; iwmr->ibmr.iova = virt; - iwmr->page_size = PAGE_SIZE; + iwmr->page_size = SZ_4K; if (req.reg_type == IRDMA_MEMREG_TYPE_MEM) { iwmr->page_size = ib_umem_find_best_pgsz(region, @@ -2845,6 +2883,13 @@ static struct ib_mr *irdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 len, switch (req.reg_type) { case IRDMA_MEMREG_TYPE_QP: + /* iWarp: Catch page not starting on OS page boundary */ + if (!rdma_protocol_roce(&iwdev->ibdev, 1) && + ib_umem_offset(iwmr->region)) { + err = -EINVAL; + goto error; + } + total = req.sq_pages + req.rq_pages + shadow_pgcnt; if (total > iwmr->page_cnt) { err = -EINVAL; diff --git a/drivers/infiniband/hw/irdma/verbs.h b/drivers/infiniband/hw/irdma/verbs.h index 9f9e273bbff3e144722e7095c88a5973999411e8..0bc0d0faa086853b075fdc6763ebe9e04eabbf65 100644 --- a/drivers/infiniband/hw/irdma/verbs.h +++ b/drivers/infiniband/hw/irdma/verbs.h @@ -18,7 +18,8 @@ struct irdma_ucontext { struct list_head qp_reg_mem_list; spinlock_t qp_reg_mem_list_lock; /* protect QP memory list */ int abi_ver; - bool legacy_mode; + u8 legacy_mode : 1; + u8 use_raw_attrs : 1; }; struct irdma_pd { diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index f8e2baed27a5cecc445d0300c33ee1a7096ce1a4..7013ce20549bdc680fd657e4025496e5bebfc0b3 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -2951,7 +2951,7 @@ DECLARE_UVERBS_NAMED_METHOD( MLX5_IB_METHOD_DEVX_OBJ_MODIFY, UVERBS_ATTR_IDR(MLX5_IB_ATTR_DEVX_OBJ_MODIFY_HANDLE, UVERBS_IDR_ANY_OBJECT, - UVERBS_ACCESS_WRITE, + UVERBS_ACCESS_READ, UA_MANDATORY), UVERBS_ATTR_PTR_IN( MLX5_IB_ATTR_DEVX_OBJ_MODIFY_CMD_IN, diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c index 9c8a7b206dcf470473fd6eab945a271d58b35c6d..e61efed320f114e83822e896302c9ab5c54a452f 100644 --- a/drivers/infiniband/hw/mlx5/mad.c +++ b/drivers/infiniband/hw/mlx5/mad.c @@ -188,7 +188,8 @@ static int process_pma_cmd(struct mlx5_ib_dev *dev, u32 port_num, mdev = dev->mdev; mdev_port_num = 1; } - if (MLX5_CAP_GEN(dev->mdev, num_ports) == 1) { + if (MLX5_CAP_GEN(dev->mdev, num_ports) == 1 && + !mlx5_core_mp_enabled(mdev)) { /* set local port to one for Function-Per-Port HCA. */ mdev = dev->mdev; mdev_port_num = 1; diff --git a/drivers/infiniband/hw/mlx5/wr.c b/drivers/infiniband/hw/mlx5/wr.c index 855f3f4fefaddf970d769d483db8f4e8923d503b..737db67a9ce1d56b30641cdf9683dace124bd8bb 100644 --- a/drivers/infiniband/hw/mlx5/wr.c +++ b/drivers/infiniband/hw/mlx5/wr.c @@ -78,7 +78,7 @@ static void set_eth_seg(const struct ib_send_wr *wr, struct mlx5_ib_qp *qp, */ copysz = min_t(u64, *cur_edge - (void *)eseg->inline_hdr.start, left); - memcpy(eseg->inline_hdr.start, pdata, copysz); + memcpy(eseg->inline_hdr.data, pdata, copysz); stride = ALIGN(sizeof(struct mlx5_wqe_eth_seg) - sizeof(eseg->inline_hdr.start) + copysz, 16); *size += stride / 16; diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index d745ce9dc88aa89381c6ee2d1d98de3460ee2933..61755b5f3e20d9421385a594e2ae0eee94004f83 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -1879,8 +1879,17 @@ static int qedr_create_user_qp(struct qedr_dev *dev, /* RQ - read access only (0) */ rc = qedr_init_user_queue(udata, dev, &qp->urq, ureq.rq_addr, ureq.rq_len, true, 0, alloc_and_init); - if (rc) + if (rc) { + ib_umem_release(qp->usq.umem); + qp->usq.umem = NULL; + if (rdma_protocol_roce(&dev->ibdev, 1)) { + qedr_free_pbl(dev, &qp->usq.pbl_info, + qp->usq.pbl_tbl); + } else { + kfree(qp->usq.pbl_tbl); + } return rc; + } } memset(&in_params, 0, sizeof(in_params)); diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c index a973905afd13207e9f2beaa2dc260772dc8a2a74..182a89bb24ef4c563eb85b6797316505347b5d3e 100644 --- a/drivers/infiniband/hw/qib/qib_fs.c +++ b/drivers/infiniband/hw/qib/qib_fs.c @@ -440,6 +440,7 @@ static int remove_device_files(struct super_block *sb, return PTR_ERR(dir); } simple_recursive_removal(dir, NULL); + dput(dir); return 0; } diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c index 51daac5c4feb75b847bb06f8a32818ebd941ac73..be3ddfbf3cae35c5ccc24e2c436794faeb53305e 100644 --- a/drivers/infiniband/sw/rxe/rxe.c +++ b/drivers/infiniband/sw/rxe/rxe.c @@ -33,6 +33,8 @@ void rxe_dealloc(struct ib_device *ib_dev) if (rxe->tfm) crypto_free_shash(rxe->tfm); + + mutex_destroy(&rxe->usdev_lock); } /* initialize rxe device parameters */ diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt-sysfs.c b/drivers/infiniband/ulp/rtrs/rtrs-clt-sysfs.c index d3c436ead69461a9965afd7590f3551dba2c624d..4aa80c9388f058b745fca05b86f532d6a2b3339a 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt-sysfs.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt-sysfs.c @@ -133,7 +133,7 @@ static ssize_t mpath_policy_store(struct device *dev, /* distinguish "mi" and "min-latency" with length */ len = strnlen(buf, NAME_MAX); - if (buf[len - 1] == '\n') + if (len && buf[len - 1] == '\n') len--; if (!strncasecmp(buf, "round-robin", 11) || diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 25e799dba999e4a19ef9dc98f78ef307a078dbb7..fd6c260d5857d091bc70609b52751bbbf7b7dcb0 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -79,12 +79,16 @@ module_param(srpt_srq_size, int, 0444); MODULE_PARM_DESC(srpt_srq_size, "Shared receive queue (SRQ) size."); +static int srpt_set_u64_x(const char *buffer, const struct kernel_param *kp) +{ + return kstrtou64(buffer, 16, (u64 *)kp->arg); +} static int srpt_get_u64_x(char *buffer, const struct kernel_param *kp) { return sprintf(buffer, "0x%016llx\n", *(u64 *)kp->arg); } -module_param_call(srpt_service_guid, NULL, srpt_get_u64_x, &srpt_service_guid, - 0444); +module_param_call(srpt_service_guid, srpt_set_u64_x, srpt_get_u64_x, + &srpt_service_guid, 0444); MODULE_PARM_DESC(srpt_service_guid, "Using this value for ioc_guid, id_ext, and cm_listen_id instead of using the node_guid of the first HCA."); @@ -210,10 +214,12 @@ static const char *get_ch_state_name(enum rdma_ch_state s) /** * srpt_qp_event - QP event callback function * @event: Description of the event that occurred. - * @ch: SRPT RDMA channel. + * @ptr: SRPT RDMA channel. */ -static void srpt_qp_event(struct ib_event *event, struct srpt_rdma_ch *ch) +static void srpt_qp_event(struct ib_event *event, void *ptr) { + struct srpt_rdma_ch *ch = ptr; + pr_debug("QP event %d on ch=%p sess_name=%s-%d state=%s\n", event->event, ch, ch->sess_name, ch->qp->qp_num, get_ch_state_name(ch->state)); @@ -1807,8 +1813,7 @@ retry: ch->cq_size = ch->rq_size + sq_size; qp_init->qp_context = (void *)ch; - qp_init->event_handler - = (void(*)(struct ib_event *, void*))srpt_qp_event; + qp_init->event_handler = srpt_qp_event; qp_init->send_cq = ch->cq; qp_init->recv_cq = ch->cq; qp_init->sq_sig_type = IB_SIGNAL_REQ_WR; @@ -3204,7 +3209,6 @@ static int srpt_add_one(struct ib_device *device) INIT_IB_EVENT_HANDLER(&sdev->event_handler, sdev->device, srpt_event_handler); - ib_register_event_handler(&sdev->event_handler); for (i = 1; i <= sdev->device->phys_port_cnt; i++) { sport = &sdev->port[i - 1]; @@ -3227,6 +3231,7 @@ static int srpt_add_one(struct ib_device *device) } } + ib_register_event_handler(&sdev->event_handler); spin_lock(&srpt_dev_lock); list_add_tail(&sdev->list, &srpt_dev_list); spin_unlock(&srpt_dev_lock); @@ -3237,7 +3242,6 @@ static int srpt_add_one(struct ib_device *device) err_port: srpt_unregister_mad_agent(sdev, i); - ib_unregister_event_handler(&sdev->event_handler); err_cm: if (sdev->cm_id) ib_destroy_cm_id(sdev->cm_id); diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index e8011d70d079936a3f32f9e181eef19288c556cd..13c36f51b93533cc45207b2616453d9721356d65 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -294,6 +294,7 @@ static const struct xpad_device { { 0x1689, 0xfd00, "Razer Onza Tournament Edition", 0, XTYPE_XBOX360 }, { 0x1689, 0xfd01, "Razer Onza Classic Edition", 0, XTYPE_XBOX360 }, { 0x1689, 0xfe00, "Razer Sabertooth", 0, XTYPE_XBOX360 }, + { 0x17ef, 0x6182, "Lenovo Legion Controller for Windows", 0, XTYPE_XBOX360 }, { 0x1949, 0x041a, "Amazon Game Controller", 0, XTYPE_XBOX360 }, { 0x1bad, 0x0002, "Harmonix Rock Band Guitar", 0, XTYPE_XBOX360 }, { 0x1bad, 0x0003, "Harmonix Rock Band Drumkit", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 }, @@ -489,6 +490,7 @@ static const struct usb_device_id xpad_table[] = { XPAD_XBOX360_VENDOR(0x15e4), /* Numark X-Box 360 controllers */ XPAD_XBOX360_VENDOR(0x162e), /* Joytech X-Box 360 controllers */ XPAD_XBOX360_VENDOR(0x1689), /* Razer Onza */ + XPAD_XBOX360_VENDOR(0x17ef), /* Lenovo */ XPAD_XBOX360_VENDOR(0x1949), /* Amazon controllers */ XPAD_XBOX360_VENDOR(0x1bad), /* Harminix Rock Band Guitar and Drums */ XPAD_XBOX360_VENDOR(0x20d6), /* PowerA Controllers */ @@ -562,6 +564,9 @@ struct xboxone_init_packet { #define GIP_MOTOR_LT BIT(3) #define GIP_MOTOR_ALL (GIP_MOTOR_R | GIP_MOTOR_L | GIP_MOTOR_RT | GIP_MOTOR_LT) +#define GIP_WIRED_INTF_DATA 0 +#define GIP_WIRED_INTF_AUDIO 1 + /* * This packet is required for all Xbox One pads with 2015 * or later firmware installed (or present from the factory). @@ -2006,7 +2011,7 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id } if (xpad->xtype == XTYPE_XBOXONE && - intf->cur_altsetting->desc.bInterfaceNumber != 0) { + intf->cur_altsetting->desc.bInterfaceNumber != GIP_WIRED_INTF_DATA) { /* * The Xbox One controller lists three interfaces all with the * same interface class, subclass and protocol. Differentiate by diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c index c4d8caadec59ef2fede700cf47afa550ab8dd8b9..661d6c8b059bf565212dcfcc8ba7eea8b4cbe2c3 100644 --- a/drivers/input/keyboard/atkbd.c +++ b/drivers/input/keyboard/atkbd.c @@ -792,7 +792,6 @@ static int atkbd_probe(struct atkbd *atkbd) { struct ps2dev *ps2dev = &atkbd->ps2dev; unsigned char param[2]; - bool skip_getid; /* * Some systems, where the bit-twiddling when testing the io-lines of the @@ -806,6 +805,11 @@ static int atkbd_probe(struct atkbd *atkbd) "keyboard reset failed on %s\n", ps2dev->serio->phys); + if (atkbd_skip_getid(atkbd)) { + atkbd->id = 0xab83; + return 0; + } + /* * Then we check the keyboard ID. We should get 0xab83 under normal conditions. * Some keyboards report different values, but the first byte is always 0xab or @@ -814,18 +818,17 @@ static int atkbd_probe(struct atkbd *atkbd) */ param[0] = param[1] = 0xa5; /* initialize with invalid values */ - skip_getid = atkbd_skip_getid(atkbd); - if (skip_getid || ps2_command(ps2dev, param, ATKBD_CMD_GETID)) { + if (ps2_command(ps2dev, param, ATKBD_CMD_GETID)) { /* - * If the get ID command was skipped or failed, we check if we can at least set + * If the get ID command failed, we check if we can at least set * the LEDs on the keyboard. This should work on every keyboard out there. * It also turns the LEDs off, which we want anyway. */ param[0] = 0; if (ps2_command(ps2dev, param, ATKBD_CMD_SETLEDS)) return -1; - atkbd->id = skip_getid ? 0xab83 : 0xabba; + atkbd->id = 0xabba; return 0; } diff --git a/drivers/input/keyboard/gpio_keys_polled.c b/drivers/input/keyboard/gpio_keys_polled.c index c3937d2fc7446e8b68e517cb4e5491809407fb06..a0f9978c68f552827a446d3e45ea34208767c0e7 100644 --- a/drivers/input/keyboard/gpio_keys_polled.c +++ b/drivers/input/keyboard/gpio_keys_polled.c @@ -319,12 +319,10 @@ static int gpio_keys_polled_probe(struct platform_device *pdev) error = devm_gpio_request_one(dev, button->gpio, flags, button->desc ? : DRV_NAME); - if (error) { - dev_err(dev, - "unable to claim gpio %u, err=%d\n", - button->gpio, error); - return error; - } + if (error) + return dev_err_probe(dev, error, + "unable to claim gpio %u\n", + button->gpio); bdata->gpiod = gpio_to_desc(button->gpio); if (!bdata->gpiod) { diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c index 258d5fe3d395c4670088aa0d736cac69c7d24550..aa32371f04af6c8838efa1e9cb3ab1e8a3100dc6 100644 --- a/drivers/input/rmi4/rmi_driver.c +++ b/drivers/input/rmi4/rmi_driver.c @@ -1196,7 +1196,11 @@ static int rmi_driver_probe(struct device *dev) } rmi_driver_set_input_params(rmi_dev, data->input); data->input->phys = devm_kasprintf(dev, GFP_KERNEL, - "%s/input0", dev_name(dev)); + "%s/input0", dev_name(dev)); + if (!data->input->phys) { + retval = -ENOMEM; + goto err; + } } retval = rmi_init_functions(data); diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h index b585b1dab870e0725daa62d7b52d2c9ca406798a..dfc6c581873b7d45da63d88a216295a24fa2c13b 100644 --- a/drivers/input/serio/i8042-acpipnpio.h +++ b/drivers/input/serio/i8042-acpipnpio.h @@ -634,6 +634,14 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { }, .driver_data = (void *)(SERIO_QUIRK_NOAUX) }, + { + /* Fujitsu Lifebook U728 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U728"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOAUX) + }, { /* Gigabyte M912 */ .matches = { @@ -1208,6 +1216,12 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "NS5x_7xPU"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOAUX) + }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "NJ50_70CU"), diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index 0c5fd9789edf411ebefcde2acbfda679848f7463..255ce125cdfd295da3b2482ebab81e5715dee120 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -937,7 +937,8 @@ static int goodix_add_acpi_gpio_mappings(struct goodix_ts_data *ts) } } - if (ts->gpio_count == 2 && ts->gpio_int_idx == 0) { + /* Some devices with gpio_int_idx 0 list a third unused GPIO */ + if ((ts->gpio_count == 2 || ts->gpio_count == 3) && ts->gpio_int_idx == 0) { ts->irq_pin_access_method = IRQ_PIN_ACCESS_ACPI_GPIO; gpio_mapping = acpi_goodix_int_first_gpios; } else if (ts->gpio_count == 2 && ts->gpio_int_idx == 1) { diff --git a/drivers/input/touchscreen/imagis.c b/drivers/input/touchscreen/imagis.c index e2697e6c6d2a0f75c466e05d28b48ffc2d2a10fd..2636e1c9435d82693c7dff291e96e71f6098cb80 100644 --- a/drivers/input/touchscreen/imagis.c +++ b/drivers/input/touchscreen/imagis.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only +#include #include #include #include @@ -23,12 +24,9 @@ #define IST3038C_I2C_RETRY_COUNT 3 #define IST3038C_MAX_FINGER_NUM 10 #define IST3038C_X_MASK GENMASK(23, 12) -#define IST3038C_X_SHIFT 12 #define IST3038C_Y_MASK GENMASK(11, 0) #define IST3038C_AREA_MASK GENMASK(27, 24) -#define IST3038C_AREA_SHIFT 24 #define IST3038C_FINGER_COUNT_MASK GENMASK(15, 12) -#define IST3038C_FINGER_COUNT_SHIFT 12 #define IST3038C_FINGER_STATUS_MASK GENMASK(9, 0) struct imagis_ts { @@ -92,8 +90,7 @@ static irqreturn_t imagis_interrupt(int irq, void *dev_id) goto out; } - finger_count = (intr_message & IST3038C_FINGER_COUNT_MASK) >> - IST3038C_FINGER_COUNT_SHIFT; + finger_count = FIELD_GET(IST3038C_FINGER_COUNT_MASK, intr_message); if (finger_count > IST3038C_MAX_FINGER_NUM) { dev_err(&ts->client->dev, "finger count %d is more than maximum supported\n", @@ -101,7 +98,7 @@ static irqreturn_t imagis_interrupt(int irq, void *dev_id) goto out; } - finger_pressed = intr_message & IST3038C_FINGER_STATUS_MASK; + finger_pressed = FIELD_GET(IST3038C_FINGER_STATUS_MASK, intr_message); for (i = 0; i < finger_count; i++) { error = imagis_i2c_read_reg(ts, @@ -118,12 +115,11 @@ static irqreturn_t imagis_interrupt(int irq, void *dev_id) input_mt_report_slot_state(ts->input_dev, MT_TOOL_FINGER, finger_pressed & BIT(i)); touchscreen_report_pos(ts->input_dev, &ts->prop, - (finger_status & IST3038C_X_MASK) >> - IST3038C_X_SHIFT, - finger_status & IST3038C_Y_MASK, 1); + FIELD_GET(IST3038C_X_MASK, finger_status), + FIELD_GET(IST3038C_Y_MASK, finger_status), + true); input_report_abs(ts->input_dev, ABS_MT_TOUCH_MAJOR, - (finger_status & IST3038C_AREA_MASK) >> - IST3038C_AREA_SHIFT); + FIELD_GET(IST3038C_AREA_MASK, finger_status)); } input_mt_sync_frame(ts->input_dev); @@ -210,7 +206,7 @@ static int imagis_init_input_dev(struct imagis_ts *ts) input_set_capability(input_dev, EV_ABS, ABS_MT_POSITION_X); input_set_capability(input_dev, EV_ABS, ABS_MT_POSITION_Y); - input_set_abs_params(input_dev, ABS_MT_TOUCH_MAJOR, 0, 255, 0, 0); + input_set_abs_params(input_dev, ABS_MT_TOUCH_MAJOR, 0, 16, 0, 0); touchscreen_parse_properties(input_dev, true, &ts->prop); if (!ts->prop.max_x || !ts->prop.max_y) { diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 1d9494f64a21574db4b174a955fc26819f12b2fd..4526ff2e1bd5fdbb4cd9235e92767d7905c079ae 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -29,7 +29,6 @@ static LIST_HEAD(icc_providers); static int providers_count; static bool synced_state; static DEFINE_MUTEX(icc_lock); -static DEFINE_MUTEX(icc_bw_lock); static struct dentry *icc_debugfs_dir; static void icc_summary_show_one(struct seq_file *s, struct icc_node *n) @@ -636,7 +635,7 @@ int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw) if (WARN_ON(IS_ERR(path) || !path->num_nodes)) return -EINVAL; - mutex_lock(&icc_bw_lock); + mutex_lock(&icc_lock); old_avg = path->reqs[0].avg_bw; old_peak = path->reqs[0].peak_bw; @@ -668,7 +667,7 @@ int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw) apply_constraints(path); } - mutex_unlock(&icc_bw_lock); + mutex_unlock(&icc_lock); trace_icc_set_bw_end(path, ret); @@ -971,7 +970,6 @@ void icc_node_add(struct icc_node *node, struct icc_provider *provider) return; mutex_lock(&icc_lock); - mutex_lock(&icc_bw_lock); node->provider = provider; list_add_tail(&node->node_list, &provider->nodes); @@ -997,7 +995,6 @@ void icc_node_add(struct icc_node *node, struct icc_provider *provider) node->avg_bw = 0; node->peak_bw = 0; - mutex_unlock(&icc_bw_lock); mutex_unlock(&icc_lock); } EXPORT_SYMBOL_GPL(icc_node_add); @@ -1137,7 +1134,6 @@ void icc_sync_state(struct device *dev) return; mutex_lock(&icc_lock); - mutex_lock(&icc_bw_lock); synced_state = true; list_for_each_entry(p, &icc_providers, provider_list) { dev_dbg(p->dev, "interconnect provider is in synced state\n"); @@ -1150,21 +1146,13 @@ void icc_sync_state(struct device *dev) } } } - mutex_unlock(&icc_bw_lock); mutex_unlock(&icc_lock); } EXPORT_SYMBOL_GPL(icc_sync_state); static int __init icc_init(void) { - struct device_node *root; - - /* Teach lockdep about lock ordering wrt. shrinker: */ - fs_reclaim_acquire(GFP_KERNEL); - might_lock(&icc_bw_lock); - fs_reclaim_release(GFP_KERNEL); - - root = of_find_node_by_path("/"); + struct device_node *root = of_find_node_by_path("/"); providers_count = of_count_icc_providers(root); of_node_put(root); diff --git a/drivers/interconnect/qcom/sc8180x.c b/drivers/interconnect/qcom/sc8180x.c index 83461e31774ec9e7b6bfdfcd46b8d7ca5484c5f5..d9ee193fb18bdc24bfa976a4d127fe2d67f854ee 100644 --- a/drivers/interconnect/qcom/sc8180x.c +++ b/drivers/interconnect/qcom/sc8180x.c @@ -1387,6 +1387,7 @@ static struct qcom_icc_bcm bcm_mm0 = { static struct qcom_icc_bcm bcm_co0 = { .name = "CO0", + .keepalive = true, .num_nodes = 1, .nodes = { &slv_qns_cdsp_mem_noc } }; diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 28267b6f2d090d0d0031cc0c31c5c94bb649b3ed..15767545d22bc0b4d50c0c6139486135c15c208d 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -192,7 +192,7 @@ source "drivers/iommu/intel/Kconfig" config IRQ_REMAP bool "Support for Interrupt Remapping" depends on X86_64 && X86_IO_APIC && PCI_MSI && ACPI - select DMAR_TABLE + select DMAR_TABLE if INTEL_IOMMU help Supports Interrupt remapping for IO-APIC and MSI devices. To use x2apic mode in the CPU's which support x2APIC enhancements or diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index f6e64c985802185a1292338c2cc3a26bf153ed91..cc94ac6662339353be8ef929967870275083bdb8 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -2047,6 +2047,9 @@ static int __init iommu_init_pci(struct amd_iommu *iommu) /* Prevent binding other PCI device drivers to IOMMU devices */ iommu->dev->match_driver = false; + /* ACPI _PRT won't have an IRQ for IOMMU */ + iommu->dev->irq_managed = 1; + pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET, &iommu->cap); diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 8966f7d5aab61667e65af0f73e7b79b083e3fa04..82f100e591b5a2c578685ea903ba18780c669505 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -152,6 +152,18 @@ static void queue_inc_cons(struct arm_smmu_ll_queue *q) q->cons = Q_OVF(q->cons) | Q_WRP(q, cons) | Q_IDX(q, cons); } +static void queue_sync_cons_ovf(struct arm_smmu_queue *q) +{ + struct arm_smmu_ll_queue *llq = &q->llq; + + if (likely(Q_OVF(llq->prod) == Q_OVF(llq->cons))) + return; + + llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) | + Q_IDX(llq, llq->cons); + queue_sync_cons_out(q); +} + static int queue_sync_prod_in(struct arm_smmu_queue *q) { u32 prod; @@ -1583,8 +1595,7 @@ static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev) } while (!queue_empty(llq)); /* Sync our overflow flag, as we believe we're up to speed */ - llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) | - Q_IDX(llq, llq->cons); + queue_sync_cons_ovf(q); return IRQ_HANDLED; } @@ -1642,9 +1653,7 @@ static irqreturn_t arm_smmu_priq_thread(int irq, void *dev) } while (!queue_empty(llq)); /* Sync our overflow flag, as we believe we're up to speed */ - llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) | - Q_IDX(llq, llq->cons); - queue_sync_cons_out(q); + queue_sync_cons_ovf(q); return IRQ_HANDLED; } diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c index d80065c8105af982699f0d002861009402b85382..f15dcb9e4175c1c680a9a5423d17afc0048ffee1 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c @@ -267,12 +267,26 @@ static int qcom_smmu_init_context(struct arm_smmu_domain *smmu_domain, static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu) { - unsigned int last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1); struct qcom_smmu *qsmmu = to_qcom_smmu(smmu); + unsigned int last_s2cr; u32 reg; u32 smr; int i; + /* + * Some platforms support more than the Arm SMMU architected maximum of + * 128 stream matching groups. For unknown reasons, the additional + * groups don't exhibit the same behavior as the architected registers, + * so limit the groups to 128 until the behavior is fixed for the other + * groups. + */ + if (smmu->num_mapping_groups > 128) { + dev_notice(smmu->dev, "\tLimiting the stream matching groups to 128\n"); + smmu->num_mapping_groups = 128; + } + + last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1); + /* * With some firmware versions writes to S2CR of type FAULT are * ignored, and writing BYPASS will end up written as FAULT in the diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index aa6d62cc567ae2167a307c4b70a7264b82678cc7..3fa66dba0a326df9824c74a49775b3f415e842a7 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -1547,6 +1547,14 @@ static size_t iommu_dma_opt_mapping_size(void) return iova_rcache_range(); } +static size_t iommu_dma_max_mapping_size(struct device *dev) +{ + if (dev_is_untrusted(dev)) + return swiotlb_max_mapping_size(dev); + + return SIZE_MAX; +} + static const struct dma_map_ops iommu_dma_ops = { .flags = DMA_F_PCI_P2PDMA_SUPPORTED, .alloc = iommu_dma_alloc, @@ -1569,6 +1577,7 @@ static const struct dma_map_ops iommu_dma_ops = { .unmap_resource = iommu_dma_unmap_resource, .get_merge_boundary = iommu_dma_get_merge_boundary, .opt_mapping_size = iommu_dma_opt_mapping_size, + .max_mapping_size = iommu_dma_max_mapping_size, }; /* diff --git a/drivers/iommu/intel/Kconfig b/drivers/iommu/intel/Kconfig index b7dff5092fd21c06bd73e293548d3af95c7072f6..12e1e90fdae138647eab7c004e080fc34fa5da5b 100644 --- a/drivers/iommu/intel/Kconfig +++ b/drivers/iommu/intel/Kconfig @@ -96,4 +96,15 @@ config INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON passing intel_iommu=sm_on to the kernel. If not sure, please use the default value. +config INTEL_IOMMU_PERF_EVENTS + def_bool y + bool "Intel IOMMU performance events" + depends on INTEL_IOMMU && PERF_EVENTS + help + Selecting this option will enable the performance monitoring + infrastructure in the Intel IOMMU. It collects information about + key events occurring during operation of the remapping hardware, + to aid performance tuning and debug. These are available on modern + processors which support Intel VT-d 4.0 and later. + endif # INTEL_IOMMU diff --git a/drivers/iommu/intel/Makefile b/drivers/iommu/intel/Makefile index fa0dae16441cb50e712973063df5c6bde935ccf9..29d26a4371327c839f4cd23d1452fcba26806638 100644 --- a/drivers/iommu/intel/Makefile +++ b/drivers/iommu/intel/Makefile @@ -5,4 +5,7 @@ obj-$(CONFIG_DMAR_TABLE) += trace.o cap_audit.o obj-$(CONFIG_DMAR_PERF) += perf.o obj-$(CONFIG_INTEL_IOMMU_DEBUGFS) += debugfs.o obj-$(CONFIG_INTEL_IOMMU_SVM) += svm.o +ifdef CONFIG_INTEL_IOMMU obj-$(CONFIG_IRQ_REMAP) += irq_remapping.o +endif +obj-$(CONFIG_INTEL_IOMMU_PERF_EVENTS) += perfmon.o diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 418af1db0192d9d2020acfa591937d48713e7958..4759f79ad7b949659c129952cd38b20ae6ceab4f 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -34,6 +34,7 @@ #include "../irq_remapping.h" #include "perf.h" #include "trace.h" +#include "perfmon.h" typedef int (*dmar_res_handler_t)(struct acpi_dmar_header *, void *); struct dmar_res_callback { @@ -1104,6 +1105,9 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) if (sts & DMA_GSTS_QIES) iommu->gcmd |= DMA_GCMD_QIE; + if (alloc_iommu_pmu(iommu)) + pr_debug("Cannot alloc PMU for iommu (seq_id = %d)\n", iommu->seq_id); + raw_spin_lock_init(&iommu->register_lock); /* @@ -1131,6 +1135,7 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) err_sysfs: iommu_device_sysfs_remove(&iommu->iommu); err_unmap: + free_iommu_pmu(iommu); unmap_iommu(iommu); error_free_seq_id: ida_free(&dmar_seq_ids, iommu->seq_id); @@ -1146,6 +1151,8 @@ static void free_iommu(struct intel_iommu *iommu) iommu_device_sysfs_remove(&iommu->iommu); } + free_iommu_pmu(iommu); + if (iommu->irq) { if (iommu->pr_irq) { free_irq(iommu->pr_irq, iommu); diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index c99cb715bd9a282ba761794905cf1de863ae412f..c1348bedab3b3a998a775d3c469077b2e6401746 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -125,6 +125,11 @@ #define DMAR_MTRR_PHYSMASK8_REG 0x208 #define DMAR_MTRR_PHYSBASE9_REG 0x210 #define DMAR_MTRR_PHYSMASK9_REG 0x218 +#define DMAR_PERFCAP_REG 0x300 +#define DMAR_PERFCFGOFF_REG 0x310 +#define DMAR_PERFOVFOFF_REG 0x318 +#define DMAR_PERFCNTROFF_REG 0x31c +#define DMAR_PERFEVNTCAP_REG 0x380 #define DMAR_VCCAP_REG 0xe30 /* Virtual command capability register */ #define DMAR_VCMD_REG 0xe00 /* Virtual command register */ #define DMAR_VCRSP_REG 0xe10 /* Virtual command response register */ @@ -148,6 +153,7 @@ */ #define cap_esrtps(c) (((c) >> 63) & 1) #define cap_esirtps(c) (((c) >> 62) & 1) +#define cap_ecmds(c) (((c) >> 61) & 1) #define cap_fl5lp_support(c) (((c) >> 60) & 1) #define cap_pi_support(c) (((c) >> 59) & 1) #define cap_fl1gp_support(c) (((c) >> 56) & 1) @@ -179,7 +185,8 @@ * Extended Capability Register */ -#define ecap_rps(e) (((e) >> 49) & 0x1) +#define ecap_pms(e) (((e) >> 51) & 0x1) +#define ecap_rps(e) (((e) >> 49) & 0x1) #define ecap_smpwc(e) (((e) >> 48) & 0x1) #define ecap_flts(e) (((e) >> 47) & 0x1) #define ecap_slts(e) (((e) >> 46) & 0x1) @@ -210,6 +217,22 @@ #define ecap_max_handle_mask(e) (((e) >> 20) & 0xf) #define ecap_sc_support(e) (((e) >> 7) & 0x1) /* Snooping Control */ +/* + * Decoding Perf Capability Register + */ +#define pcap_num_cntr(p) ((p) & 0xffff) +#define pcap_cntr_width(p) (((p) >> 16) & 0x7f) +#define pcap_num_event_group(p) (((p) >> 24) & 0x1f) +#define pcap_filters_mask(p) (((p) >> 32) & 0x1f) +#define pcap_interrupt(p) (((p) >> 50) & 0x1) +/* The counter stride is calculated as 2 ^ (x+10) bytes */ +#define pcap_cntr_stride(p) (1ULL << ((((p) >> 52) & 0x7) + 10)) + +/* + * Decoding Perf Event Capability Register + */ +#define pecap_es(p) ((p) & 0xfffffff) + /* Virtual command interface capability */ #define vccap_pasid(v) (((v) & DMA_VCS_PAS)) /* PASID allocation */ @@ -561,6 +584,22 @@ struct dmar_domain { iommu core */ }; +struct iommu_pmu { + struct intel_iommu *iommu; + u32 num_cntr; /* Number of counters */ + u32 num_eg; /* Number of event group */ + u32 cntr_width; /* Counter width */ + u32 cntr_stride; /* Counter Stride */ + u32 filter; /* Bitmask of filter support */ + void __iomem *base; /* the PerfMon base address */ + void __iomem *cfg_reg; /* counter configuration base address */ + void __iomem *cntr_reg; /* counter 0 address*/ + void __iomem *overflow; /* overflow status register */ + + u64 *evcap; /* Indicates all supported events */ + u32 **cntr_evcap; /* Supported events of each counter. */ +}; + struct intel_iommu { void __iomem *reg; /* Pointer to hardware regs, virtual addr */ u64 reg_phys; /* physical address of hw register set */ @@ -608,6 +647,8 @@ struct intel_iommu { struct dmar_drhd_unit *drhd; void *perf_statistic; + + struct iommu_pmu *pmu; }; /* PCI domain-device relationship */ diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index 3f03039e5cce516c627b773175fe2665a5014d58..32432d82d7744f242a43d4b6dfe696120cc319a6 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -435,6 +435,9 @@ devtlb_invalidation_with_pasid(struct intel_iommu *iommu, if (!info || !info->ats_enabled) return; + if (pci_dev_is_disconnected(to_pci_dev(dev))) + return; + sid = info->bus << 8 | info->devfn; qdep = info->ats_qdep; pfsid = info->pfsid; diff --git a/drivers/iommu/intel/perfmon.c b/drivers/iommu/intel/perfmon.c new file mode 100644 index 0000000000000000000000000000000000000000..db5791a5445512a2f6cd7a884c7b1560f9342be6 --- /dev/null +++ b/drivers/iommu/intel/perfmon.c @@ -0,0 +1,172 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Support Intel IOMMU PerfMon + * Copyright(c) 2023 Intel Corporation. + */ +#define pr_fmt(fmt) "DMAR: " fmt +#define dev_fmt(fmt) pr_fmt(fmt) + +#include +#include "iommu.h" +#include "perfmon.h" + +static inline void __iomem * +get_perf_reg_address(struct intel_iommu *iommu, u32 offset) +{ + u32 off = dmar_readl(iommu->reg + offset); + + return iommu->reg + off; +} + +int alloc_iommu_pmu(struct intel_iommu *iommu) +{ + struct iommu_pmu *iommu_pmu; + int i, j, ret; + u64 perfcap; + u32 cap; + + if (!ecap_pms(iommu->ecap)) + return 0; + + /* The IOMMU PMU requires the ECMD support as well */ + if (!cap_ecmds(iommu->cap)) + return -ENODEV; + + perfcap = dmar_readq(iommu->reg + DMAR_PERFCAP_REG); + /* The performance monitoring is not supported. */ + if (!perfcap) + return -ENODEV; + + /* Sanity check for the number of the counters and event groups */ + if (!pcap_num_cntr(perfcap) || !pcap_num_event_group(perfcap)) + return -ENODEV; + + /* The interrupt on overflow is required */ + if (!pcap_interrupt(perfcap)) + return -ENODEV; + + iommu_pmu = kzalloc(sizeof(*iommu_pmu), GFP_KERNEL); + if (!iommu_pmu) + return -ENOMEM; + + iommu_pmu->num_cntr = pcap_num_cntr(perfcap); + iommu_pmu->cntr_width = pcap_cntr_width(perfcap); + iommu_pmu->filter = pcap_filters_mask(perfcap); + iommu_pmu->cntr_stride = pcap_cntr_stride(perfcap); + iommu_pmu->num_eg = pcap_num_event_group(perfcap); + + iommu_pmu->evcap = kcalloc(iommu_pmu->num_eg, sizeof(u64), GFP_KERNEL); + if (!iommu_pmu->evcap) { + ret = -ENOMEM; + goto free_pmu; + } + + /* Parse event group capabilities */ + for (i = 0; i < iommu_pmu->num_eg; i++) { + u64 pcap; + + pcap = dmar_readq(iommu->reg + DMAR_PERFEVNTCAP_REG + + i * IOMMU_PMU_CAP_REGS_STEP); + iommu_pmu->evcap[i] = pecap_es(pcap); + } + + iommu_pmu->cntr_evcap = kcalloc(iommu_pmu->num_cntr, sizeof(u32 *), GFP_KERNEL); + if (!iommu_pmu->cntr_evcap) { + ret = -ENOMEM; + goto free_pmu_evcap; + } + for (i = 0; i < iommu_pmu->num_cntr; i++) { + iommu_pmu->cntr_evcap[i] = kcalloc(iommu_pmu->num_eg, sizeof(u32), GFP_KERNEL); + if (!iommu_pmu->cntr_evcap[i]) { + ret = -ENOMEM; + goto free_pmu_cntr_evcap; + } + /* + * Set to the global capabilities, will adjust according + * to per-counter capabilities later. + */ + for (j = 0; j < iommu_pmu->num_eg; j++) + iommu_pmu->cntr_evcap[i][j] = (u32)iommu_pmu->evcap[j]; + } + + iommu_pmu->cfg_reg = get_perf_reg_address(iommu, DMAR_PERFCFGOFF_REG); + iommu_pmu->cntr_reg = get_perf_reg_address(iommu, DMAR_PERFCNTROFF_REG); + iommu_pmu->overflow = get_perf_reg_address(iommu, DMAR_PERFOVFOFF_REG); + + /* + * Check per-counter capabilities. All counters should have the + * same capabilities on Interrupt on Overflow Support and Counter + * Width. + */ + for (i = 0; i < iommu_pmu->num_cntr; i++) { + cap = dmar_readl(iommu_pmu->cfg_reg + + i * IOMMU_PMU_CFG_OFFSET + + IOMMU_PMU_CFG_CNTRCAP_OFFSET); + if (!iommu_cntrcap_pcc(cap)) + continue; + + /* + * It's possible that some counters have a different + * capability because of e.g., HW bug. Check the corner + * case here and simply drop those counters. + */ + if ((iommu_cntrcap_cw(cap) != iommu_pmu->cntr_width) || + !iommu_cntrcap_ios(cap)) { + iommu_pmu->num_cntr = i; + pr_warn("PMU counter capability inconsistent, counter number reduced to %d\n", + iommu_pmu->num_cntr); + } + + /* Clear the pre-defined events group */ + for (j = 0; j < iommu_pmu->num_eg; j++) + iommu_pmu->cntr_evcap[i][j] = 0; + + /* Override with per-counter event capabilities */ + for (j = 0; j < iommu_cntrcap_egcnt(cap); j++) { + cap = dmar_readl(iommu_pmu->cfg_reg + i * IOMMU_PMU_CFG_OFFSET + + IOMMU_PMU_CFG_CNTREVCAP_OFFSET + + (j * IOMMU_PMU_OFF_REGS_STEP)); + iommu_pmu->cntr_evcap[i][iommu_event_group(cap)] = iommu_event_select(cap); + /* + * Some events may only be supported by a specific counter. + * Track them in the evcap as well. + */ + iommu_pmu->evcap[iommu_event_group(cap)] |= iommu_event_select(cap); + } + } + + iommu_pmu->iommu = iommu; + iommu->pmu = iommu_pmu; + + return 0; + +free_pmu_cntr_evcap: + for (i = 0; i < iommu_pmu->num_cntr; i++) + kfree(iommu_pmu->cntr_evcap[i]); + kfree(iommu_pmu->cntr_evcap); +free_pmu_evcap: + kfree(iommu_pmu->evcap); +free_pmu: + kfree(iommu_pmu); + + return ret; +} + +void free_iommu_pmu(struct intel_iommu *iommu) +{ + struct iommu_pmu *iommu_pmu = iommu->pmu; + + if (!iommu_pmu) + return; + + if (iommu_pmu->evcap) { + int i; + + for (i = 0; i < iommu_pmu->num_cntr; i++) + kfree(iommu_pmu->cntr_evcap[i]); + kfree(iommu_pmu->cntr_evcap); + } + kfree(iommu_pmu->evcap); + kfree(iommu_pmu); + iommu->pmu = NULL; +} diff --git a/drivers/iommu/intel/perfmon.h b/drivers/iommu/intel/perfmon.h new file mode 100644 index 0000000000000000000000000000000000000000..4b0d9c1fea6fffc444160a0f7f9c215f8074da81 --- /dev/null +++ b/drivers/iommu/intel/perfmon.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * PERFCFGOFF_REG, PERFFRZOFF_REG + * PERFOVFOFF_REG, PERFCNTROFF_REG + */ +#define IOMMU_PMU_NUM_OFF_REGS 4 +#define IOMMU_PMU_OFF_REGS_STEP 4 + +#define IOMMU_PMU_CFG_OFFSET 0x100 +#define IOMMU_PMU_CFG_CNTRCAP_OFFSET 0x80 +#define IOMMU_PMU_CFG_CNTREVCAP_OFFSET 0x84 +#define IOMMU_PMU_CFG_SIZE 0x8 +#define IOMMU_PMU_CFG_FILTERS_OFFSET 0x4 + +#define IOMMU_PMU_CAP_REGS_STEP 8 + +#define iommu_cntrcap_pcc(p) ((p) & 0x1) +#define iommu_cntrcap_cw(p) (((p) >> 8) & 0xff) +#define iommu_cntrcap_ios(p) (((p) >> 16) & 0x1) +#define iommu_cntrcap_egcnt(p) (((p) >> 28) & 0xf) + +#define iommu_event_select(p) ((p) & 0xfffffff) +#define iommu_event_group(p) (((p) >> 28) & 0xf) + +#ifdef CONFIG_INTEL_IOMMU_PERF_EVENTS +int alloc_iommu_pmu(struct intel_iommu *iommu); +void free_iommu_pmu(struct intel_iommu *iommu); +#else +static inline int +alloc_iommu_pmu(struct intel_iommu *iommu) +{ + return 0; +} + +static inline void +free_iommu_pmu(struct intel_iommu *iommu) +{ +} +#endif /* CONFIG_INTEL_IOMMU_PERF_EVENTS */ diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 03b25358946c4fa00d101f69a8178effc61d7664..cb862ab96873e47177ae3c49104246d08133d3d2 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -71,7 +71,7 @@ int intel_svm_enable_prq(struct intel_iommu *iommu) struct page *pages; int irq, ret; - pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, PRQ_ORDER); + pages = alloc_pages_node(iommu->node, GFP_KERNEL | __GFP_ZERO, PRQ_ORDER); if (!pages) { pr_warn("IOMMU: %s: Failed to allocate page request queue\n", iommu->name); diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 8b38972394776c4ed9b5c15f10dad14417942770..83736824f17d1ac97f2781706686ae8032fbd2bc 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1741,6 +1741,9 @@ static void probe_alloc_default_domain(struct bus_type *bus, { struct __group_domain_type gtype; + if (group->default_domain) + return; + memset(>ype, 0, sizeof(gtype)); /* Ask for default domain requirements of all devices in the group */ diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c index 83314b9d8f38bfcf63652ddb63e5c4c05d4c7f93..ee59647c20501ec29792a19b381b0d133313cac8 100644 --- a/drivers/iommu/irq_remapping.c +++ b/drivers/iommu/irq_remapping.c @@ -99,7 +99,8 @@ int __init irq_remapping_prepare(void) if (disable_irq_remap) return -ENOSYS; - if (intel_irq_remap_ops.prepare() == 0) + if (IS_ENABLED(CONFIG_INTEL_IOMMU) && + intel_irq_remap_ops.prepare() == 0) remap_ops = &intel_irq_remap_ops; else if (IS_ENABLED(CONFIG_AMD_IOMMU) && amd_iommu_irq_ops.prepare() == 0) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 0ba2a63a9538af2b916a0ac9ca5397ca69575745..576163f88a4a5efed80a46284f6511d5715a3237 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -1570,6 +1570,7 @@ static const struct of_device_id mtk_iommu_of_ids[] = { { .compatible = "mediatek,mt8195-iommu-vpp", .data = &mt8195_data_vpp}, {} }; +MODULE_DEVICE_TABLE(of, mtk_iommu_of_ids); static struct platform_driver mtk_iommu_driver = { .probe = mtk_iommu_probe, diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index a978220eb620e44388e322d1b6f0874b51c3e3aa..5dd06bcb507f6bf618f444c5069c64ca6b11bf8d 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -602,6 +602,7 @@ static const struct of_device_id mtk_iommu_v1_of_ids[] = { { .compatible = "mediatek,mt2701-m4u", }, {} }; +MODULE_DEVICE_TABLE(of, mtk_iommu_v1_of_ids); static const struct component_master_ops mtk_iommu_v1_com_ops = { .bind = mtk_iommu_v1_bind, diff --git a/drivers/iommu/sprd-iommu.c b/drivers/iommu/sprd-iommu.c index 8261066de07d70296d5e4a57fd6f835e461f8871..e4358393fe3783477a07c7771d16a5ecec44248f 100644 --- a/drivers/iommu/sprd-iommu.c +++ b/drivers/iommu/sprd-iommu.c @@ -152,13 +152,6 @@ static struct iommu_domain *sprd_iommu_domain_alloc(unsigned int domain_type) return &dom->domain; } -static void sprd_iommu_domain_free(struct iommu_domain *domain) -{ - struct sprd_iommu_domain *dom = to_sprd_domain(domain); - - kfree(dom); -} - static void sprd_iommu_first_vpn(struct sprd_iommu_domain *dom) { struct sprd_iommu_device *sdev = dom->sdev; @@ -231,6 +224,28 @@ static void sprd_iommu_hw_en(struct sprd_iommu_device *sdev, bool en) sprd_iommu_update_bits(sdev, reg_cfg, mask, 0, val); } +static void sprd_iommu_cleanup(struct sprd_iommu_domain *dom) +{ + size_t pgt_size; + + /* Nothing need to do if the domain hasn't been attached */ + if (!dom->sdev) + return; + + pgt_size = sprd_iommu_pgt_size(&dom->domain); + dma_free_coherent(dom->sdev->dev, pgt_size, dom->pgt_va, dom->pgt_pa); + dom->sdev = NULL; + sprd_iommu_hw_en(dom->sdev, false); +} + +static void sprd_iommu_domain_free(struct iommu_domain *domain) +{ + struct sprd_iommu_domain *dom = to_sprd_domain(domain); + + sprd_iommu_cleanup(dom); + kfree(dom); +} + static int sprd_iommu_attach_device(struct iommu_domain *domain, struct device *dev) { diff --git a/drivers/irqchip/irq-brcmstb-l2.c b/drivers/irqchip/irq-brcmstb-l2.c index 0e979e6b081e498d51fe4d8679b3fc826475edcf..b53fdbb7ac11f3d0b55773e2bac8b1af2685cd03 100644 --- a/drivers/irqchip/irq-brcmstb-l2.c +++ b/drivers/irqchip/irq-brcmstb-l2.c @@ -2,7 +2,7 @@ /* * Generic Broadcom Set Top Box Level 2 Interrupt controller driver * - * Copyright (C) 2014-2017 Broadcom + * Copyright (C) 2014-2024 Broadcom */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -123,6 +123,9 @@ static void brcmstb_l2_intc_irq_handle(struct irq_desc *desc) generic_handle_domain_irq(b->domain, irq); } while (status); out: + /* Don't ack parent before all device writes are done */ + wmb(); + chained_irq_exit(chip, desc); } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 8956881503d9acb62c709b9315455d27aa549e3f..f9ab5cfc9b94769b51eabbc0930650ba301d39b2 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3161,6 +3161,7 @@ static void its_cpu_init_lpis(void) val |= GICR_CTLR_ENABLE_LPIS; writel_relaxed(val, rbase + GICR_CTLR); +out: if (gic_rdists->has_vlpis && !gic_rdists->has_rvpeid) { void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); @@ -3196,7 +3197,6 @@ static void its_cpu_init_lpis(void) /* Make sure the GIC has seen the above */ dsb(sy); -out: gic_data_rdist()->flags |= RD_LOCAL_LPI_ENABLED; pr_info("GICv3: CPU%d: using %s LPI pending table @%pa\n", smp_processor_id(), @@ -3805,8 +3805,9 @@ static int its_vpe_set_affinity(struct irq_data *d, bool force) { struct its_vpe *vpe = irq_data_get_irq_chip_data(d); - int from, cpu = cpumask_first(mask_val); + struct cpumask common, *table_mask; unsigned long flags; + int from, cpu; /* * Changing affinity is mega expensive, so let's be as lazy as @@ -3822,19 +3823,22 @@ static int its_vpe_set_affinity(struct irq_data *d, * taken on any vLPI handling path that evaluates vpe->col_idx. */ from = vpe_to_cpuid_lock(vpe, &flags); - if (from == cpu) - goto out; - - vpe->col_idx = cpu; + table_mask = gic_data_rdist_cpu(from)->vpe_table_mask; /* - * GICv4.1 allows us to skip VMOVP if moving to a cpu whose RD - * is sharing its VPE table with the current one. + * If we are offered another CPU in the same GICv4.1 ITS + * affinity, pick this one. Otherwise, any CPU will do. */ - if (gic_data_rdist_cpu(cpu)->vpe_table_mask && - cpumask_test_cpu(from, gic_data_rdist_cpu(cpu)->vpe_table_mask)) + if (table_mask && cpumask_and(&common, mask_val, table_mask)) + cpu = cpumask_test_cpu(from, &common) ? from : cpumask_first(&common); + else + cpu = cpumask_first(mask_val); + + if (from == cpu) goto out; + vpe->col_idx = cpu; + its_send_vmovp(vpe); its_vpe_db_proxy_move(vpe, from, cpu); @@ -4531,13 +4535,8 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq set_bit(i, bitmap); } - if (err) { - if (i > 0) - its_vpe_irq_domain_free(domain, virq, i); - - its_lpi_free(bitmap, base, nr_ids); - its_free_prop_table(vprop_page); - } + if (err) + its_vpe_irq_domain_free(domain, virq, i); return err; } diff --git a/drivers/irqchip/irq-loongson-eiointc.c b/drivers/irqchip/irq-loongson-eiointc.c index 3d99b8bdd8ef19c304584500872a5194e3124b2a..de115ee6e9ec796bef96ef35a4eab95244739c23 100644 --- a/drivers/irqchip/irq-loongson-eiointc.c +++ b/drivers/irqchip/irq-loongson-eiointc.c @@ -242,7 +242,7 @@ static int eiointc_domain_alloc(struct irq_domain *domain, unsigned int virq, int ret; unsigned int i, type; unsigned long hwirq = 0; - struct eiointc *priv = domain->host_data; + struct eiointc_priv *priv = domain->host_data; ret = irq_domain_translate_onecell(domain, arg, &hwirq, &type); if (ret) diff --git a/drivers/irqchip/irq-renesas-rzg2l.c b/drivers/irqchip/irq-renesas-rzg2l.c index 10c3e85c90c231ed7c32afd9ca2cdbe14773fc66..be71459c7465ab56d945e0b656c9381baddb6648 100644 --- a/drivers/irqchip/irq-renesas-rzg2l.c +++ b/drivers/irqchip/irq-renesas-rzg2l.c @@ -28,8 +28,7 @@ #define ISCR 0x10 #define IITSR 0x14 #define TSCR 0x20 -#define TITSR0 0x24 -#define TITSR1 0x28 +#define TITSR(n) (0x24 + (n) * 4) #define TITSR0_MAX_INT 16 #define TITSEL_WIDTH 0x2 #define TSSR(n) (0x30 + ((n) * 4)) @@ -67,28 +66,43 @@ static struct rzg2l_irqc_priv *irq_data_to_priv(struct irq_data *data) return data->domain->host_data; } -static void rzg2l_irq_eoi(struct irq_data *d) +static void rzg2l_clear_irq_int(struct rzg2l_irqc_priv *priv, unsigned int hwirq) { - unsigned int hw_irq = irqd_to_hwirq(d) - IRQC_IRQ_START; - struct rzg2l_irqc_priv *priv = irq_data_to_priv(d); + unsigned int hw_irq = hwirq - IRQC_IRQ_START; u32 bit = BIT(hw_irq); - u32 reg; + u32 iitsr, iscr; - reg = readl_relaxed(priv->base + ISCR); - if (reg & bit) - writel_relaxed(reg & ~bit, priv->base + ISCR); + iscr = readl_relaxed(priv->base + ISCR); + iitsr = readl_relaxed(priv->base + IITSR); + + /* + * ISCR can only be cleared if the type is falling-edge, rising-edge or + * falling/rising-edge. + */ + if ((iscr & bit) && (iitsr & IITSR_IITSEL_MASK(hw_irq))) { + writel_relaxed(iscr & ~bit, priv->base + ISCR); + /* + * Enforce that the posted write is flushed to prevent that the + * just handled interrupt is raised again. + */ + readl_relaxed(priv->base + ISCR); + } } -static void rzg2l_tint_eoi(struct irq_data *d) +static void rzg2l_clear_tint_int(struct rzg2l_irqc_priv *priv, unsigned int hwirq) { - unsigned int hw_irq = irqd_to_hwirq(d) - IRQC_TINT_START; - struct rzg2l_irqc_priv *priv = irq_data_to_priv(d); - u32 bit = BIT(hw_irq); + u32 bit = BIT(hwirq - IRQC_TINT_START); u32 reg; reg = readl_relaxed(priv->base + TSCR); - if (reg & bit) + if (reg & bit) { writel_relaxed(reg & ~bit, priv->base + TSCR); + /* + * Enforce that the posted write is flushed to prevent that the + * just handled interrupt is raised again. + */ + readl_relaxed(priv->base + TSCR); + } } static void rzg2l_irqc_eoi(struct irq_data *d) @@ -98,9 +112,9 @@ static void rzg2l_irqc_eoi(struct irq_data *d) raw_spin_lock(&priv->lock); if (hw_irq >= IRQC_IRQ_START && hw_irq <= IRQC_IRQ_COUNT) - rzg2l_irq_eoi(d); + rzg2l_clear_irq_int(priv, hw_irq); else if (hw_irq >= IRQC_TINT_START && hw_irq < IRQC_NUM_IRQ) - rzg2l_tint_eoi(d); + rzg2l_clear_tint_int(priv, hw_irq); raw_spin_unlock(&priv->lock); irq_chip_eoi_parent(d); } @@ -148,8 +162,10 @@ static void rzg2l_irqc_irq_enable(struct irq_data *d) static int rzg2l_irq_set_type(struct irq_data *d, unsigned int type) { - unsigned int hw_irq = irqd_to_hwirq(d) - IRQC_IRQ_START; struct rzg2l_irqc_priv *priv = irq_data_to_priv(d); + unsigned int hwirq = irqd_to_hwirq(d); + u32 iitseln = hwirq - IRQC_IRQ_START; + bool clear_irq_int = false; u16 sense, tmp; switch (type & IRQ_TYPE_SENSE_MASK) { @@ -159,14 +175,17 @@ static int rzg2l_irq_set_type(struct irq_data *d, unsigned int type) case IRQ_TYPE_EDGE_FALLING: sense = IITSR_IITSEL_EDGE_FALLING; + clear_irq_int = true; break; case IRQ_TYPE_EDGE_RISING: sense = IITSR_IITSEL_EDGE_RISING; + clear_irq_int = true; break; case IRQ_TYPE_EDGE_BOTH: sense = IITSR_IITSEL_EDGE_BOTH; + clear_irq_int = true; break; default: @@ -175,22 +194,40 @@ static int rzg2l_irq_set_type(struct irq_data *d, unsigned int type) raw_spin_lock(&priv->lock); tmp = readl_relaxed(priv->base + IITSR); - tmp &= ~IITSR_IITSEL_MASK(hw_irq); - tmp |= IITSR_IITSEL(hw_irq, sense); + tmp &= ~IITSR_IITSEL_MASK(iitseln); + tmp |= IITSR_IITSEL(iitseln, sense); + if (clear_irq_int) + rzg2l_clear_irq_int(priv, hwirq); writel_relaxed(tmp, priv->base + IITSR); raw_spin_unlock(&priv->lock); return 0; } +static u32 rzg2l_disable_tint_and_set_tint_source(struct irq_data *d, struct rzg2l_irqc_priv *priv, + u32 reg, u32 tssr_offset, u8 tssr_index) +{ + u32 tint = (u32)(uintptr_t)irq_data_get_irq_chip_data(d); + u32 tien = reg & (TIEN << TSSEL_SHIFT(tssr_offset)); + + /* Clear the relevant byte in reg */ + reg &= ~(TSSEL_MASK << TSSEL_SHIFT(tssr_offset)); + /* Set TINT and leave TIEN clear */ + reg |= tint << TSSEL_SHIFT(tssr_offset); + writel_relaxed(reg, priv->base + TSSR(tssr_index)); + + return reg | tien; +} + static int rzg2l_tint_set_edge(struct irq_data *d, unsigned int type) { struct rzg2l_irqc_priv *priv = irq_data_to_priv(d); unsigned int hwirq = irqd_to_hwirq(d); u32 titseln = hwirq - IRQC_TINT_START; - u32 offset; - u8 sense; - u32 reg; + u32 tssr_offset = TSSR_OFFSET(titseln); + u8 tssr_index = TSSR_INDEX(titseln); + u8 index, sense; + u32 reg, tssr; switch (type & IRQ_TYPE_SENSE_MASK) { case IRQ_TYPE_EDGE_RISING: @@ -205,17 +242,21 @@ static int rzg2l_tint_set_edge(struct irq_data *d, unsigned int type) return -EINVAL; } - offset = TITSR0; + index = 0; if (titseln >= TITSR0_MAX_INT) { titseln -= TITSR0_MAX_INT; - offset = TITSR1; + index = 1; } raw_spin_lock(&priv->lock); - reg = readl_relaxed(priv->base + offset); + tssr = readl_relaxed(priv->base + TSSR(tssr_index)); + tssr = rzg2l_disable_tint_and_set_tint_source(d, priv, tssr, tssr_offset, tssr_index); + reg = readl_relaxed(priv->base + TITSR(index)); reg &= ~(IRQ_MASK << (titseln * TITSEL_WIDTH)); reg |= sense << (titseln * TITSEL_WIDTH); - writel_relaxed(reg, priv->base + offset); + writel_relaxed(reg, priv->base + TITSR(index)); + rzg2l_clear_tint_int(priv, hwirq); + writel_relaxed(tssr, priv->base + TSSR(tssr_index)); raw_spin_unlock(&priv->lock); return 0; diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c index 2f4784860df5df38315c923a9fec220655f855b4..be5e19a86ac3b273425e7c88bb3f2f34513dc72c 100644 --- a/drivers/irqchip/irq-sifive-plic.c +++ b/drivers/irqchip/irq-sifive-plic.c @@ -144,7 +144,13 @@ static void plic_irq_eoi(struct irq_data *d) { struct plic_handler *handler = this_cpu_ptr(&plic_handlers); - writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM); + if (unlikely(irqd_irq_disabled(d))) { + plic_toggle(handler, d->hwirq, 1); + writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM); + plic_toggle(handler, d->hwirq, 0); + } else { + writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM); + } } #ifdef CONFIG_SMP diff --git a/drivers/leds/flash/leds-sgm3140.c b/drivers/leds/flash/leds-sgm3140.c index d3a30ad94ac463e4f472e675c1918f0d67d8d399..dd5d327c52a106fa9e29b5525ba9eecdb300920e 100644 --- a/drivers/leds/flash/leds-sgm3140.c +++ b/drivers/leds/flash/leds-sgm3140.c @@ -114,8 +114,11 @@ static int sgm3140_brightness_set(struct led_classdev *led_cdev, "failed to enable regulator: %d\n", ret); return ret; } + gpiod_set_value_cansleep(priv->flash_gpio, 0); gpiod_set_value_cansleep(priv->enable_gpio, 1); } else { + del_timer_sync(&priv->powerdown_timer); + gpiod_set_value_cansleep(priv->flash_gpio, 0); gpiod_set_value_cansleep(priv->enable_gpio, 0); ret = regulator_disable(priv->vin_regulator); if (ret) { diff --git a/drivers/leds/leds-aw2013.c b/drivers/leds/leds-aw2013.c index 0b52fc9097c6e1abcb3459ffb7405bd83c419c3c..3c05958578a1c08a9f947ac51126613b43a72310 100644 --- a/drivers/leds/leds-aw2013.c +++ b/drivers/leds/leds-aw2013.c @@ -397,6 +397,7 @@ error_reg: regulator_disable(chip->vcc_regulator); error: + mutex_unlock(&chip->mutex); mutex_destroy(&chip->mutex); return ret; } diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 100a6a236d92ad8baf5838ddc426fd9b263c4fd2..ec662f97ba82881437eac5d6ca4509a633347518 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -614,7 +614,7 @@ static void use_dmio(struct dm_buffer *b, enum req_op op, sector_t sector, io_req.mem.ptr.vma = (char *)b->data + offset; } - r = dm_io(&io_req, 1, ®ion, NULL); + r = dm_io(&io_req, 1, ®ion, NULL, IOPRIO_DEFAULT); if (unlikely(r)) b->end_io(b, errno_to_blk_status(r)); } @@ -1375,7 +1375,7 @@ int dm_bufio_issue_flush(struct dm_bufio_client *c) BUG_ON(dm_bufio_in_request()); - return dm_io(&io_req, 1, &io_reg, NULL); + return dm_io(&io_req, 1, &io_reg, NULL, IOPRIO_DEFAULT); } EXPORT_SYMBOL_GPL(dm_bufio_issue_flush); @@ -1398,7 +1398,7 @@ int dm_bufio_issue_discard(struct dm_bufio_client *c, sector_t block, sector_t c BUG_ON(dm_bufio_in_request()); - return dm_io(&io_req, 1, &io_reg, NULL); + return dm_io(&io_req, 1, &io_reg, NULL, IOPRIO_DEFAULT); } EXPORT_SYMBOL_GPL(dm_bufio_issue_discard); diff --git a/drivers/md/dm-cache-policy.h b/drivers/md/dm-cache-policy.h index 6ba3e9c91af531775bb0f2159a8651fb60bf3441..8bc21d54884e9777eefca6918464988bf5d64388 100644 --- a/drivers/md/dm-cache-policy.h +++ b/drivers/md/dm-cache-policy.h @@ -75,7 +75,7 @@ struct dm_cache_policy { * background work. */ int (*get_background_work)(struct dm_cache_policy *p, bool idle, - struct policy_work **result); + struct policy_work **result); /* * You must pass in the same work pointer that you were given, not diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 71dcd8fd4050a647f00f8cfda521ce54017dd5e6..6314210d36971bb20456565f0ba43d469fb42f28 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -21,6 +21,8 @@ #include "dm-ima.h" #define DM_RESERVED_MAX_IOS 1024 +#define DM_MAX_TARGETS 1048576 +#define DM_MAX_TARGET_PARAMS 1024 struct dm_io; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index ff515437d81e75d850d72ce754e3148f75ed66c9..25e51dc6e55985705c258a334ba9dee087c797d4 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -52,15 +52,17 @@ struct convert_context { struct completion restart; struct bio *bio_in; - struct bio *bio_out; struct bvec_iter iter_in; + struct bio *bio_out; struct bvec_iter iter_out; - u64 cc_sector; atomic_t cc_pending; + u64 cc_sector; union { struct skcipher_request *req; struct aead_request *req_aead; } r; + bool aead_recheck; + bool aead_failed; }; @@ -72,10 +74,8 @@ struct dm_crypt_io { struct bio *base_bio; u8 *integrity_metadata; bool integrity_metadata_from_pool:1; - bool in_tasklet:1; struct work_struct work; - struct tasklet_struct tasklet; struct convert_context ctx; @@ -83,6 +83,8 @@ struct dm_crypt_io { blk_status_t error; sector_t sector; + struct bvec_iter saved_bi_iter; + struct rb_node rb_node; } CRYPTO_MINALIGN_ATTR; @@ -1367,10 +1369,13 @@ static int crypt_convert_block_aead(struct crypt_config *cc, if (r == -EBADMSG) { sector_t s = le64_to_cpu(*sector); - DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu", - ctx->bio_in->bi_bdev, s); - dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead", - ctx->bio_in, s, 0); + ctx->aead_failed = true; + if (ctx->aead_recheck) { + DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu", + ctx->bio_in->bi_bdev, s); + dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead", + ctx->bio_in, s, 0); + } } if (!r && cc->iv_gen_ops && cc->iv_gen_ops->post) @@ -1726,10 +1731,11 @@ static void crypt_io_init(struct dm_crypt_io *io, struct crypt_config *cc, io->base_bio = bio; io->sector = sector; io->error = 0; + io->ctx.aead_recheck = false; + io->ctx.aead_failed = false; io->ctx.r.req = NULL; io->integrity_metadata = NULL; io->integrity_metadata_from_pool = false; - io->in_tasklet = false; atomic_set(&io->io_pending, 0); } @@ -1738,11 +1744,7 @@ static void crypt_inc_pending(struct dm_crypt_io *io) atomic_inc(&io->io_pending); } -static void kcryptd_io_bio_endio(struct work_struct *work) -{ - struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work); - bio_endio(io->base_bio); -} +static void kcryptd_queue_read(struct dm_crypt_io *io); /* * One of the bios was finished. Check for completion of @@ -1757,6 +1759,15 @@ static void crypt_dec_pending(struct dm_crypt_io *io) if (!atomic_dec_and_test(&io->io_pending)) return; + if (likely(!io->ctx.aead_recheck) && unlikely(io->ctx.aead_failed) && + cc->on_disk_tag_size && bio_data_dir(base_bio) == READ) { + io->ctx.aead_recheck = true; + io->ctx.aead_failed = false; + io->error = 0; + kcryptd_queue_read(io); + return; + } + if (io->ctx.r.req) crypt_free_req(cc, io->ctx.r.req, base_bio); @@ -1767,20 +1778,6 @@ static void crypt_dec_pending(struct dm_crypt_io *io) base_bio->bi_status = error; - /* - * If we are running this function from our tasklet, - * we can't call bio_endio() here, because it will call - * clone_endio() from dm.c, which in turn will - * free the current struct dm_crypt_io structure with - * our tasklet. In this case we need to delay bio_endio() - * execution to after the tasklet is done and dequeued. - */ - if (io->in_tasklet) { - INIT_WORK(&io->work, kcryptd_io_bio_endio); - queue_work(cc->io_queue, &io->work); - return; - } - bio_endio(base_bio); } @@ -1806,15 +1803,19 @@ static void crypt_endio(struct bio *clone) struct dm_crypt_io *io = clone->bi_private; struct crypt_config *cc = io->cc; unsigned int rw = bio_data_dir(clone); - blk_status_t error; + blk_status_t error = clone->bi_status; + + if (io->ctx.aead_recheck && !error) { + kcryptd_queue_crypt(io); + return; + } /* * free the processed pages */ - if (rw == WRITE) + if (rw == WRITE || io->ctx.aead_recheck) crypt_free_buffer_pages(cc, clone); - error = clone->bi_status; bio_put(clone); if (rw == READ && !error) { @@ -1835,6 +1836,22 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp) struct crypt_config *cc = io->cc; struct bio *clone; + if (io->ctx.aead_recheck) { + if (!(gfp & __GFP_DIRECT_RECLAIM)) + return 1; + crypt_inc_pending(io); + clone = crypt_alloc_buffer(io, io->base_bio->bi_iter.bi_size); + if (unlikely(!clone)) { + crypt_dec_pending(io); + return 1; + } + clone->bi_iter.bi_sector = cc->start + io->sector; + crypt_convert_init(cc, &io->ctx, clone, clone, io->sector); + io->saved_bi_iter = clone->bi_iter; + dm_submit_bio_remap(io->base_bio, clone); + return 0; + } + /* * We need the original biovec array in order to decrypt the whole bio * data *afterwards* -- thanks to immutable biovecs we don't need to @@ -2061,6 +2078,12 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) io->ctx.bio_out = clone; io->ctx.iter_out = clone->bi_iter; + if (crypt_integrity_aead(cc)) { + bio_copy_data(clone, io->base_bio); + io->ctx.bio_in = clone; + io->ctx.iter_in = clone->bi_iter; + } + sector += bio_sectors(clone); crypt_inc_pending(io); @@ -2097,6 +2120,14 @@ dec: static void kcryptd_crypt_read_done(struct dm_crypt_io *io) { + if (io->ctx.aead_recheck) { + if (!io->error) { + io->ctx.bio_in->bi_iter = io->saved_bi_iter; + bio_copy_data(io->base_bio, io->ctx.bio_in); + } + crypt_free_buffer_pages(io->cc, io->ctx.bio_in); + bio_put(io->ctx.bio_in); + } crypt_dec_pending(io); } @@ -2126,11 +2157,17 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io) crypt_inc_pending(io); - crypt_convert_init(cc, &io->ctx, io->base_bio, io->base_bio, - io->sector); + if (io->ctx.aead_recheck) { + io->ctx.cc_sector = io->sector + cc->iv_offset; + r = crypt_convert(cc, &io->ctx, + test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true); + } else { + crypt_convert_init(cc, &io->ctx, io->base_bio, io->base_bio, + io->sector); - r = crypt_convert(cc, &io->ctx, - test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true); + r = crypt_convert(cc, &io->ctx, + test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true); + } /* * Crypto API backlogged the request, because its queue was full * and we're in softirq context, so continue from a workqueue @@ -2173,10 +2210,13 @@ static void kcryptd_async_done(struct crypto_async_request *async_req, if (error == -EBADMSG) { sector_t s = le64_to_cpu(*org_sector_of_dmreq(cc, dmreq)); - DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu", - ctx->bio_in->bi_bdev, s); - dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead", - ctx->bio_in, s, 0); + ctx->aead_failed = true; + if (ctx->aead_recheck) { + DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu", + ctx->bio_in->bi_bdev, s); + dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead", + ctx->bio_in, s, 0); + } io->error = BLK_STS_PROTECTION; } else if (error < 0) io->error = BLK_STS_IOERR; @@ -2213,11 +2253,6 @@ static void kcryptd_crypt(struct work_struct *work) kcryptd_crypt_write_convert(io); } -static void kcryptd_crypt_tasklet(unsigned long work) -{ - kcryptd_crypt((struct work_struct *)work); -} - static void kcryptd_queue_crypt(struct dm_crypt_io *io) { struct crypt_config *cc = io->cc; @@ -2229,15 +2264,10 @@ static void kcryptd_queue_crypt(struct dm_crypt_io *io) * irqs_disabled(): the kernel may run some IO completion from the idle thread, but * it is being executed with irqs disabled. */ - if (in_hardirq() || irqs_disabled()) { - io->in_tasklet = true; - tasklet_init(&io->tasklet, kcryptd_crypt_tasklet, (unsigned long)&io->work); - tasklet_schedule(&io->tasklet); + if (!(in_hardirq() || irqs_disabled())) { + kcryptd_crypt(&io->work); return; } - - kcryptd_crypt(&io->work); - return; } INIT_WORK(&io->work, kcryptd_crypt); @@ -2505,7 +2535,7 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string type = &key_type_encrypted; set_key = set_key_encrypted; } else if (IS_ENABLED(CONFIG_TRUSTED_KEYS) && - !strncmp(key_string, "trusted:", key_desc - key_string + 1)) { + !strncmp(key_string, "trusted:", key_desc - key_string + 1)) { type = &key_type_trusted; set_key = set_key_trusted; } else { @@ -3112,7 +3142,7 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar sval = strchr(opt_string + strlen("integrity:"), ':') + 1; if (!strcasecmp(sval, "aead")) { set_bit(CRYPT_MODE_INTEGRITY_AEAD, &cc->cipher_flags); - } else if (strcasecmp(sval, "none")) { + } else if (strcasecmp(sval, "none")) { ti->error = "Unknown integrity profile"; return -EINVAL; } diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 77fcff82c82ac78d011e007c0fdd2ba5734f4894..696365f8f3b5fe943ec2b8721c4ba291a50d32f3 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -279,6 +279,8 @@ struct dm_integrity_c { atomic64_t number_of_mismatches; + mempool_t recheck_pool; + struct notifier_block reboot_notifier; }; @@ -577,7 +579,7 @@ static int sync_rw_sb(struct dm_integrity_c *ic, blk_opf_t opf) } } - r = dm_io(&io_req, 1, &io_loc, NULL); + r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT); if (unlikely(r)) return r; @@ -1087,7 +1089,7 @@ static void rw_journal_sectors(struct dm_integrity_c *ic, blk_opf_t opf, io_loc.sector = ic->start + SB_SECTORS + sector; io_loc.count = n_sectors; - r = dm_io(&io_req, 1, &io_loc, NULL); + r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT); if (unlikely(r)) { dm_integrity_io_error(ic, (opf & REQ_OP_MASK) == REQ_OP_READ ? "reading journal" : "writing journal", r); @@ -1203,7 +1205,7 @@ static void copy_from_journal(struct dm_integrity_c *ic, unsigned int section, u io_loc.sector = target; io_loc.count = n_sectors; - r = dm_io(&io_req, 1, &io_loc, NULL); + r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT); if (unlikely(r)) { WARN_ONCE(1, "asynchronous dm_io failed: %d", r); fn(-1UL, data); @@ -1530,7 +1532,7 @@ static void dm_integrity_flush_buffers(struct dm_integrity_c *ic, bool flush_dat fr.io_reg.count = 0, fr.ic = ic; init_completion(&fr.comp); - r = dm_io(&fr.io_req, 1, &fr.io_reg, NULL); + r = dm_io(&fr.io_req, 1, &fr.io_reg, NULL, IOPRIO_DEFAULT); BUG_ON(r); } @@ -1699,6 +1701,85 @@ failed: get_random_bytes(result, ic->tag_size); } +static noinline void integrity_recheck(struct dm_integrity_io *dio, char *checksum) +{ + struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io)); + struct dm_integrity_c *ic = dio->ic; + struct bvec_iter iter; + struct bio_vec bv; + sector_t sector, logical_sector, area, offset; + struct page *page; + + get_area_and_offset(ic, dio->range.logical_sector, &area, &offset); + dio->metadata_block = get_metadata_sector_and_offset(ic, area, offset, + &dio->metadata_offset); + sector = get_data_sector(ic, area, offset); + logical_sector = dio->range.logical_sector; + + page = mempool_alloc(&ic->recheck_pool, GFP_NOIO); + + __bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) { + unsigned pos = 0; + + do { + sector_t alignment; + char *mem; + char *buffer = page_to_virt(page); + int r; + struct dm_io_request io_req; + struct dm_io_region io_loc; + io_req.bi_opf = REQ_OP_READ; + io_req.mem.type = DM_IO_KMEM; + io_req.mem.ptr.addr = buffer; + io_req.notify.fn = NULL; + io_req.client = ic->io; + io_loc.bdev = ic->dev->bdev; + io_loc.sector = sector; + io_loc.count = ic->sectors_per_block; + + /* Align the bio to logical block size */ + alignment = dio->range.logical_sector | bio_sectors(bio) | (PAGE_SIZE >> SECTOR_SHIFT); + alignment &= -alignment; + io_loc.sector = round_down(io_loc.sector, alignment); + io_loc.count += sector - io_loc.sector; + buffer += (sector - io_loc.sector) << SECTOR_SHIFT; + io_loc.count = round_up(io_loc.count, alignment); + + r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT); + if (unlikely(r)) { + dio->bi_status = errno_to_blk_status(r); + goto free_ret; + } + + integrity_sector_checksum(ic, logical_sector, buffer, checksum); + r = dm_integrity_rw_tag(ic, checksum, &dio->metadata_block, + &dio->metadata_offset, ic->tag_size, TAG_CMP); + if (r) { + if (r > 0) { + DMERR_LIMIT("%pg: Checksum failed at sector 0x%llx", + bio->bi_bdev, logical_sector); + atomic64_inc(&ic->number_of_mismatches); + dm_audit_log_bio(DM_MSG_PREFIX, "integrity-checksum", + bio, logical_sector, 0); + r = -EILSEQ; + } + dio->bi_status = errno_to_blk_status(r); + goto free_ret; + } + + mem = bvec_kmap_local(&bv); + memcpy(mem + pos, buffer, ic->sectors_per_block << SECTOR_SHIFT); + kunmap_local(mem); + + pos += ic->sectors_per_block << SECTOR_SHIFT; + sector += ic->sectors_per_block; + logical_sector += ic->sectors_per_block; + } while (pos < bv.bv_len); + } +free_ret: + mempool_free(page, &ic->recheck_pool); +} + static void integrity_metadata(struct work_struct *w) { struct dm_integrity_io *dio = container_of(w, struct dm_integrity_io, work); @@ -1783,19 +1864,12 @@ again: r = dm_integrity_rw_tag(ic, checksums, &dio->metadata_block, &dio->metadata_offset, checksums_ptr - checksums, dio->op == REQ_OP_READ ? TAG_CMP : TAG_WRITE); if (unlikely(r)) { - if (r > 0) { - sector_t s; - - s = sector - ((r + ic->tag_size - 1) / ic->tag_size); - DMERR_LIMIT("%pg: Checksum failed at sector 0x%llx", - bio->bi_bdev, s); - r = -EILSEQ; - atomic64_inc(&ic->number_of_mismatches); - dm_audit_log_bio(DM_MSG_PREFIX, "integrity-checksum", - bio, s, 0); - } if (likely(checksums != checksums_onstack)) kfree(checksums); + if (r > 0) { + integrity_recheck(dio, checksums_onstack); + goto skip_io; + } goto error; } @@ -2301,7 +2375,6 @@ offload_to_thread: else skip_check: dec_in_flight(dio); - } else { INIT_WORK(&dio->work, integrity_metadata); queue_work(ic->metadata_wq, &dio->work); @@ -2709,7 +2782,7 @@ next_chunk: io_loc.sector = get_data_sector(ic, area, offset); io_loc.count = n_sectors; - r = dm_io(&io_req, 1, &io_loc, NULL); + r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT); if (unlikely(r)) { dm_integrity_io_error(ic, "reading data", r); goto err; @@ -4085,7 +4158,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv } else if (sscanf(opt_string, "block_size:%u%c", &val, &dummy) == 1) { if (val < 1 << SECTOR_SHIFT || val > MAX_SECTORS_PER_BLOCK << SECTOR_SHIFT || - (val & (val -1))) { + (val & (val - 1))) { r = -EINVAL; ti->error = "Invalid block_size argument"; goto bad; @@ -4094,7 +4167,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv } else if (sscanf(opt_string, "sectors_per_bit:%llu%c", &llval, &dummy) == 1) { log2_sectors_per_bitmap_bit = !llval ? 0 : __ilog2_u64(llval); } else if (sscanf(opt_string, "bitmap_flush_interval:%u%c", &val, &dummy) == 1) { - if (val >= (uint64_t)UINT_MAX * 1000 / HZ) { + if ((uint64_t)val >= (uint64_t)UINT_MAX * 1000 / HZ) { r = -EINVAL; ti->error = "Invalid bitmap_flush_interval argument"; goto bad; @@ -4208,6 +4281,12 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv goto bad; } + r = mempool_init_page_pool(&ic->recheck_pool, 1, 0); + if (r) { + ti->error = "Cannot allocate mempool"; + goto bad; + } + ic->metadata_wq = alloc_workqueue("dm-integrity-metadata", WQ_MEM_RECLAIM, METADATA_WORKQUEUE_MAX_ACTIVE); if (!ic->metadata_wq) { @@ -4405,7 +4484,7 @@ try_smaller_buffer: if (ic->internal_hash) { size_t recalc_tags_size; ic->recalc_wq = alloc_workqueue("dm-integrity-recalc", WQ_MEM_RECLAIM, 1); - if (!ic->recalc_wq ) { + if (!ic->recalc_wq) { ti->error = "Cannot allocate workqueue"; r = -ENOMEM; goto bad; @@ -4572,6 +4651,7 @@ static void dm_integrity_dtr(struct dm_target *ti) kvfree(ic->bbs); if (ic->bufio) dm_bufio_client_destroy(ic->bufio); + mempool_exit(&ic->recheck_pool); mempool_exit(&ic->journal_io_mempool); if (ic->io) dm_io_client_destroy(ic->io); diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index e488b05e35fa39767ef8c06db79d0ad9c847f992..ec97658387c39d80dd71c4eef562007544d2fdbb 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -295,7 +295,7 @@ static void km_dp_init(struct dpages *dp, void *data) *---------------------------------------------------------------*/ static void do_region(const blk_opf_t opf, unsigned int region, struct dm_io_region *where, struct dpages *dp, - struct io *io) + struct io *io, unsigned short ioprio) { struct bio *bio; struct page *page; @@ -344,6 +344,7 @@ static void do_region(const blk_opf_t opf, unsigned int region, &io->client->bios); bio->bi_iter.bi_sector = where->sector + (where->count - remaining); bio->bi_end_io = endio; + bio->bi_ioprio = ioprio; store_io_and_region_in_bio(bio, io, region); if (op == REQ_OP_DISCARD || op == REQ_OP_WRITE_ZEROES) { @@ -371,7 +372,7 @@ static void do_region(const blk_opf_t opf, unsigned int region, static void dispatch_io(blk_opf_t opf, unsigned int num_regions, struct dm_io_region *where, struct dpages *dp, - struct io *io, int sync) + struct io *io, int sync, unsigned short ioprio) { int i; struct dpages old_pages = *dp; @@ -388,7 +389,7 @@ static void dispatch_io(blk_opf_t opf, unsigned int num_regions, for (i = 0; i < num_regions; i++) { *dp = old_pages; if (where[i].count || (opf & REQ_PREFLUSH)) - do_region(opf, i, where + i, dp, io); + do_region(opf, i, where + i, dp, io, ioprio); } /* @@ -413,7 +414,7 @@ static void sync_io_complete(unsigned long error, void *context) static int sync_io(struct dm_io_client *client, unsigned int num_regions, struct dm_io_region *where, blk_opf_t opf, struct dpages *dp, - unsigned long *error_bits) + unsigned long *error_bits, unsigned short ioprio) { struct io *io; struct sync_io sio; @@ -435,7 +436,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions, io->vma_invalidate_address = dp->vma_invalidate_address; io->vma_invalidate_size = dp->vma_invalidate_size; - dispatch_io(opf, num_regions, where, dp, io, 1); + dispatch_io(opf, num_regions, where, dp, io, 1, ioprio); wait_for_completion_io(&sio.wait); @@ -447,7 +448,8 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions, static int async_io(struct dm_io_client *client, unsigned int num_regions, struct dm_io_region *where, blk_opf_t opf, - struct dpages *dp, io_notify_fn fn, void *context) + struct dpages *dp, io_notify_fn fn, void *context, + unsigned short ioprio) { struct io *io; @@ -467,7 +469,7 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions, io->vma_invalidate_address = dp->vma_invalidate_address; io->vma_invalidate_size = dp->vma_invalidate_size; - dispatch_io(opf, num_regions, where, dp, io, 0); + dispatch_io(opf, num_regions, where, dp, io, 0, ioprio); return 0; } @@ -509,7 +511,8 @@ static int dp_init(struct dm_io_request *io_req, struct dpages *dp, } int dm_io(struct dm_io_request *io_req, unsigned int num_regions, - struct dm_io_region *where, unsigned long *sync_error_bits) + struct dm_io_region *where, unsigned long *sync_error_bits, + unsigned short ioprio) { int r; struct dpages dp; @@ -520,11 +523,11 @@ int dm_io(struct dm_io_request *io_req, unsigned int num_regions, if (!io_req->notify.fn) return sync_io(io_req->client, num_regions, where, - io_req->bi_opf, &dp, sync_error_bits); + io_req->bi_opf, &dp, sync_error_bits, ioprio); return async_io(io_req->client, num_regions, where, io_req->bi_opf, &dp, io_req->notify.fn, - io_req->notify.context); + io_req->notify.context, ioprio); } EXPORT_SYMBOL(dm_io); diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 206e6ce554dc723136f64eac111eab7506f8e76a..4376754816abe29ddb591903212d40d79ce52415 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1877,7 +1877,8 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern minimum_data_size - sizeof(param_kernel->version))) return -EFAULT; - if (param_kernel->data_size < minimum_data_size) { + if (unlikely(param_kernel->data_size < minimum_data_size) || + unlikely(param_kernel->data_size > DM_MAX_TARGETS * DM_MAX_TARGET_PARAMS)) { DMERR("Invalid data size in the ioctl structure: %u", param_kernel->data_size); return -EINVAL; diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index 0ef78e56aa88c6caf8e28db68125690a0557f9a7..fda51bd140ed3d44369911953689eba44e668248 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -572,9 +572,9 @@ static int run_io_job(struct kcopyd_job *job) io_job_start(job->kc->throttle); if (job->op == REQ_OP_READ) - r = dm_io(&io_req, 1, &job->source, NULL); + r = dm_io(&io_req, 1, &job->source, NULL, IOPRIO_DEFAULT); else - r = dm_io(&io_req, job->num_dests, job->dests, NULL); + r = dm_io(&io_req, job->num_dests, job->dests, NULL, IOPRIO_DEFAULT); return r; } diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c index 05141eea18d3cfe53a6fe986de3ba5f043f82709..da77878cb2c029570ec37583faeec55455477618 100644 --- a/drivers/md/dm-log.c +++ b/drivers/md/dm-log.c @@ -295,7 +295,7 @@ static int rw_header(struct log_c *lc, enum req_op op) { lc->io_req.bi_opf = op; - return dm_io(&lc->io_req, 1, &lc->header_location, NULL); + return dm_io(&lc->io_req, 1, &lc->header_location, NULL, IOPRIO_DEFAULT); } static int flush_header(struct log_c *lc) @@ -308,7 +308,7 @@ static int flush_header(struct log_c *lc) lc->io_req.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; - return dm_io(&lc->io_req, 1, &null_location, NULL); + return dm_io(&lc->io_req, 1, &null_location, NULL, IOPRIO_DEFAULT); } static int read_header(struct log_c *log) @@ -756,8 +756,8 @@ static void core_set_region_sync(struct dm_dirty_log *log, region_t region, log_clear_bit(lc, lc->recovering_bits, region); if (in_sync) { log_set_bit(lc, lc->sync_bits, region); - lc->sync_count++; - } else if (log_test_bit(lc->sync_bits, region)) { + lc->sync_count++; + } else if (log_test_bit(lc->sync_bits, region)) { lc->sync_count--; log_clear_bit(lc, lc->sync_bits, region); } @@ -765,9 +765,9 @@ static void core_set_region_sync(struct dm_dirty_log *log, region_t region, static region_t core_get_sync_count(struct dm_dirty_log *log) { - struct log_c *lc = (struct log_c *) log->context; + struct log_c *lc = (struct log_c *) log->context; - return lc->sync_count; + return lc->sync_count; } #define DMEMIT_SYNC \ diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 4b7528dc2fd08d3d69ce4f21a1111f696d75d92f..99b4738e867a811ad9de0873bfc0610e857ad673 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -362,8 +362,8 @@ static struct { const int mode; const char *param; } _raid456_journal_mode[] = { - { R5C_JOURNAL_MODE_WRITE_THROUGH , "writethrough" }, - { R5C_JOURNAL_MODE_WRITE_BACK , "writeback" } + { R5C_JOURNAL_MODE_WRITE_THROUGH, "writethrough" }, + { R5C_JOURNAL_MODE_WRITE_BACK, "writeback" } }; /* Return MD raid4/5/6 journal mode for dm @journal_mode one */ @@ -1114,7 +1114,7 @@ too_many: * [stripe_cache ] Stripe cache size for higher RAIDs * [region_size ] Defines granularity of bitmap * [journal_dev ] raid4/5/6 journaling deviice - * (i.e. write hole closing log) + * (i.e. write hole closing log) * * RAID10-only options: * [raid10_copies <# copies>] Number of copies. (Default: 2) @@ -3325,14 +3325,14 @@ static int raid_map(struct dm_target *ti, struct bio *bio) struct mddev *mddev = &rs->md; /* - * If we're reshaping to add disk(s)), ti->len and + * If we're reshaping to add disk(s), ti->len and * mddev->array_sectors will differ during the process * (ti->len > mddev->array_sectors), so we have to requeue * bios with addresses > mddev->array_sectors here or * there will occur accesses past EOD of the component * data images thus erroring the raid set. */ - if (unlikely(bio_end_sector(bio) > mddev->array_sectors)) + if (unlikely(bio_has_data(bio) && bio_end_sector(bio) > mddev->array_sectors)) return DM_MAPIO_REQUEUE; md_handle_request(mddev, bio); @@ -3999,7 +3999,7 @@ static int raid_preresume(struct dm_target *ti) } /* Resize bitmap to adjust to changed region size (aka MD bitmap chunksize) or grown device size */ - if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) && mddev->bitmap && + if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) && mddev->bitmap && (test_bit(RT_FLAG_RS_GROW, &rs->runtime_flags) || (rs->requested_bitmap_chunk_sectors && mddev->bitmap_info.chunksize != to_bytes(rs->requested_bitmap_chunk_sectors)))) { @@ -4046,7 +4046,9 @@ static void raid_resume(struct dm_target *ti) * Take this opportunity to check whether any failed * devices are reachable again. */ + mddev_lock_nointr(mddev); attempt_restore_of_faulty_devices(rs); + mddev_unlock(mddev); } if (test_and_clear_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) { diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index c38e63706d91128559d597fcadaaf05b167f1593..1004199ae77ac8c1fa7ad7431cd4aeb8b87b2ccc 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -273,7 +273,7 @@ static int mirror_flush(struct dm_target *ti) } error_bits = -1; - dm_io(&io_req, ms->nr_mirrors, io, &error_bits); + dm_io(&io_req, ms->nr_mirrors, io, &error_bits, IOPRIO_DEFAULT); if (unlikely(error_bits != 0)) { for (i = 0; i < ms->nr_mirrors; i++) if (test_bit(i, &error_bits)) @@ -543,7 +543,7 @@ static void read_async_bio(struct mirror *m, struct bio *bio) map_region(&io, m, bio); bio_set_m(bio, m); - BUG_ON(dm_io(&io_req, 1, &io, NULL)); + BUG_ON(dm_io(&io_req, 1, &io, NULL, IOPRIO_DEFAULT)); } static inline int region_in_sync(struct mirror_set *ms, region_t region, @@ -670,7 +670,7 @@ static void do_write(struct mirror_set *ms, struct bio *bio) */ bio_set_m(bio, get_default_mirror(ms)); - BUG_ON(dm_io(&io_req, ms->nr_mirrors, io, NULL)); + BUG_ON(dm_io(&io_req, ms->nr_mirrors, io, NULL, IOPRIO_DEFAULT)); } static void do_writes(struct mirror_set *ms, struct bio_list *writes) @@ -902,7 +902,7 @@ static struct mirror_set *alloc_context(unsigned int nr_mirrors, if (IS_ERR(ms->io_client)) { ti->error = "Error creating dm_io client"; kfree(ms); - return NULL; + return NULL; } ms->rh = dm_region_hash_create(ms, dispatch_bios, wakeup_mirrord, diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 80b95746a43e066237de3be8a34b1e25f05b9842..eee1cd3aa3fcf2fe302bf1e2fc9815df345f63f3 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -220,7 +220,7 @@ static void do_metadata(struct work_struct *work) { struct mdata_req *req = container_of(work, struct mdata_req, work); - req->result = dm_io(req->io_req, 1, req->where, NULL); + req->result = dm_io(req->io_req, 1, req->where, NULL, IOPRIO_DEFAULT); } /* @@ -244,7 +244,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, blk_opf_t opf, struct mdata_req req; if (!metadata) - return dm_io(&io_req, 1, &where, NULL); + return dm_io(&io_req, 1, &where, NULL, IOPRIO_DEFAULT); req.where = &where; req.io_req = &io_req; diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index b748901a4fb55e720e8cb413bb32045658ce3bb4..1c601508ce0b465072d7de0d670e01bb3641a239 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -679,8 +679,10 @@ static void dm_exception_table_exit(struct dm_exception_table *et, for (i = 0; i < size; i++) { slot = et->table + i; - hlist_bl_for_each_entry_safe(ex, pos, n, slot, hash_list) + hlist_bl_for_each_entry_safe(ex, pos, n, slot, hash_list) { kmem_cache_free(mem, ex); + cond_resched(); + } } kvfree(et->table); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index dac6a5f25f2be4cb4e031a6a8c1ddca0894c7c89..aabb2435070b8e6cf279a5e959867f3ed42f601a 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -72,7 +72,7 @@ static sector_t high(struct dm_table *t, unsigned int l, unsigned int n) n = get_child(n, CHILDREN_PER_NODE - 1); if (n >= t->counts[l]) - return (sector_t) - 1; + return (sector_t) -1; return get_node(t, l, n)[KEYS_PER_NODE - 1]; } @@ -128,7 +128,12 @@ static int alloc_targets(struct dm_table *t, unsigned int num) int dm_table_create(struct dm_table **result, fmode_t mode, unsigned int num_targets, struct mapped_device *md) { - struct dm_table *t = kzalloc(sizeof(*t), GFP_KERNEL); + struct dm_table *t; + + if (num_targets > DM_MAX_TARGETS) + return -EOVERFLOW; + + t = kzalloc(sizeof(*t), GFP_KERNEL); if (!t) return -ENOMEM; @@ -143,7 +148,7 @@ int dm_table_create(struct dm_table **result, fmode_t mode, if (!num_targets) { kfree(t); - return -ENOMEM; + return -EOVERFLOW; } if (alloc_targets(t, num_targets)) { @@ -1528,7 +1533,7 @@ static bool dm_table_any_dev_attr(struct dm_table *t, if (ti->type->iterate_devices && ti->type->iterate_devices(ti, func, data)) return true; - } + } return false; } diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 601f9e4e6234f06b0201feb229916df3d177ae4e..f24d89af7c5f0e572324f75cda7a26a4fa8a13be 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -1179,9 +1179,9 @@ static void process_prepared_discard_passdown_pt1(struct dm_thin_new_mapping *m) discard_parent = bio_alloc(NULL, 1, 0, GFP_NOIO); discard_parent->bi_end_io = passdown_endio; discard_parent->bi_private = m; - if (m->maybe_shared) - passdown_double_checking_shared_status(m, discard_parent); - else { + if (m->maybe_shared) + passdown_double_checking_shared_status(m, discard_parent); + else { struct discard_op op; begin_discard(&op, tc, discard_parent); diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 24df610a2c438972227e8a6181372ee7b59a260c..6a707b41dc865f62cafa56228d915accacecb764 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -474,6 +474,63 @@ int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io, return 0; } +static int verity_recheck_copy(struct dm_verity *v, struct dm_verity_io *io, + u8 *data, size_t len) +{ + memcpy(data, io->recheck_buffer, len); + io->recheck_buffer += len; + + return 0; +} + +static noinline int verity_recheck(struct dm_verity *v, struct dm_verity_io *io, + struct bvec_iter start, sector_t cur_block) +{ + struct page *page; + void *buffer; + int r; + struct dm_io_request io_req; + struct dm_io_region io_loc; + + page = mempool_alloc(&v->recheck_pool, GFP_NOIO); + buffer = page_to_virt(page); + + io_req.bi_opf = REQ_OP_READ; + io_req.mem.type = DM_IO_KMEM; + io_req.mem.ptr.addr = buffer; + io_req.notify.fn = NULL; + io_req.client = v->io; + io_loc.bdev = v->data_dev->bdev; + io_loc.sector = cur_block << (v->data_dev_block_bits - SECTOR_SHIFT); + io_loc.count = 1 << (v->data_dev_block_bits - SECTOR_SHIFT); + r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT); + if (unlikely(r)) + goto free_ret; + + r = verity_hash(v, verity_io_hash_req(v, io), buffer, + 1 << v->data_dev_block_bits, + verity_io_real_digest(v, io), true); + if (unlikely(r)) + goto free_ret; + + if (memcmp(verity_io_real_digest(v, io), + verity_io_want_digest(v, io), v->digest_size)) { + r = -EIO; + goto free_ret; + } + + io->recheck_buffer = buffer; + r = verity_for_bv_block(v, io, &start, verity_recheck_copy); + if (unlikely(r)) + goto free_ret; + + r = 0; +free_ret: + mempool_free(page, &v->recheck_pool); + + return r; +} + static int verity_bv_zero(struct dm_verity *v, struct dm_verity_io *io, u8 *data, size_t len) { @@ -500,9 +557,7 @@ static int verity_verify_io(struct dm_verity_io *io) { bool is_zero; struct dm_verity *v = io->v; -#if defined(CONFIG_DM_VERITY_FEC) struct bvec_iter start; -#endif struct bvec_iter iter_copy; struct bvec_iter *iter; struct crypto_wait wait; @@ -553,10 +608,7 @@ static int verity_verify_io(struct dm_verity_io *io) if (unlikely(r < 0)) return r; -#if defined(CONFIG_DM_VERITY_FEC) - if (verity_fec_is_enabled(v)) - start = *iter; -#endif + start = *iter; r = verity_for_io_block(v, io, iter, &wait); if (unlikely(r < 0)) return r; @@ -578,6 +630,10 @@ static int verity_verify_io(struct dm_verity_io *io) * tasklet since it may sleep, so fallback to work-queue. */ return -EAGAIN; + } else if (verity_recheck(v, io, start, cur_block) == 0) { + if (v->validated_blocks) + set_bit(cur_block, v->validated_blocks); + continue; #if defined(CONFIG_DM_VERITY_FEC) } else if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_DATA, cur_block, NULL, &start) == 0) { @@ -634,23 +690,6 @@ static void verity_work(struct work_struct *w) verity_finish_io(io, errno_to_blk_status(verity_verify_io(io))); } -static void verity_tasklet(unsigned long data) -{ - struct dm_verity_io *io = (struct dm_verity_io *)data; - int err; - - io->in_tasklet = true; - err = verity_verify_io(io); - if (err == -EAGAIN || err == -ENOMEM) { - /* fallback to retrying with work-queue */ - INIT_WORK(&io->work, verity_work); - queue_work(io->v->verify_wq, &io->work); - return; - } - - verity_finish_io(io, errno_to_blk_status(err)); -} - static void verity_end_io(struct bio *bio) { struct dm_verity_io *io = bio->bi_private; @@ -663,13 +702,8 @@ static void verity_end_io(struct bio *bio) return; } - if (static_branch_unlikely(&use_tasklet_enabled) && io->v->use_tasklet) { - tasklet_init(&io->tasklet, verity_tasklet, (unsigned long)io); - tasklet_schedule(&io->tasklet); - } else { - INIT_WORK(&io->work, verity_work); - queue_work(io->v->verify_wq, &io->work); - } + INIT_WORK(&io->work, verity_work); + queue_work(io->v->verify_wq, &io->work); } /* @@ -950,6 +984,10 @@ static void verity_dtr(struct dm_target *ti) if (v->verify_wq) destroy_workqueue(v->verify_wq); + mempool_exit(&v->recheck_pool); + if (v->io) + dm_io_client_destroy(v->io); + if (v->bufio) dm_bufio_client_destroy(v->bufio); @@ -1386,6 +1424,20 @@ static int verity_ctr(struct dm_target *ti, unsigned int argc, char **argv) } v->hash_blocks = hash_position; + r = mempool_init_page_pool(&v->recheck_pool, 1, 0); + if (unlikely(r)) { + ti->error = "Cannot allocate mempool"; + goto bad; + } + + v->io = dm_io_client_create(); + if (IS_ERR(v->io)) { + r = PTR_ERR(v->io); + v->io = NULL; + ti->error = "Cannot allocate dm io"; + goto bad; + } + v->bufio = dm_bufio_client_create(v->hash_dev->bdev, 1 << v->hash_dev_block_bits, 1, sizeof(struct buffer_aux), dm_bufio_alloc_callback, NULL, diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h index f9d522c870e61665d87271f66c690138db42108f..db93a91169d5e6de31d344a6f37589bbc0bdb654 100644 --- a/drivers/md/dm-verity.h +++ b/drivers/md/dm-verity.h @@ -11,6 +11,7 @@ #ifndef DM_VERITY_H #define DM_VERITY_H +#include #include #include #include @@ -68,6 +69,9 @@ struct dm_verity { unsigned long *validated_blocks; /* bitset blocks validated */ char *signature_key_desc; /* signature keyring reference */ + + struct dm_io_client *io; + mempool_t recheck_pool; }; struct dm_verity_io { @@ -76,14 +80,15 @@ struct dm_verity_io { /* original value of bio->bi_end_io */ bio_end_io_t *orig_bi_end_io; + struct bvec_iter iter; + sector_t block; unsigned int n_blocks; bool in_tasklet; - struct bvec_iter iter; - struct work_struct work; - struct tasklet_struct tasklet; + + char *recheck_buffer; /* * Three variably-size fields follow this struct: diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index c6ff43a8f0b25b7618d3e212cecf4c0a601a04a6..20fc84b24fc75f36782616d248fa7661113b8584 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -531,7 +531,7 @@ static void ssd_commit_flushed(struct dm_writecache *wc, bool wait_for_ios) req.notify.context = &endio; /* writing via async dm-io (implied by notify.fn above) won't return an error */ - (void) dm_io(&req, 1, ®ion, NULL); + (void) dm_io(&req, 1, ®ion, NULL, IOPRIO_DEFAULT); i = j; } @@ -568,7 +568,7 @@ static void ssd_commit_superblock(struct dm_writecache *wc) req.notify.fn = NULL; req.notify.context = NULL; - r = dm_io(&req, 1, ®ion, NULL); + r = dm_io(&req, 1, ®ion, NULL, IOPRIO_DEFAULT); if (unlikely(r)) writecache_error(wc, r, "error writing superblock"); } @@ -596,7 +596,7 @@ static void writecache_disk_flush(struct dm_writecache *wc, struct dm_dev *dev) req.client = wc->dm_io; req.notify.fn = NULL; - r = dm_io(&req, 1, ®ion, NULL); + r = dm_io(&req, 1, ®ion, NULL, IOPRIO_DEFAULT); if (unlikely(r)) writecache_error(wc, r, "error flushing metadata: %d", r); } @@ -984,7 +984,7 @@ static int writecache_read_metadata(struct dm_writecache *wc, sector_t n_sectors req.client = wc->dm_io; req.notify.fn = NULL; - return dm_io(&req, 1, ®ion, NULL); + return dm_io(&req, 1, ®ion, NULL, IOPRIO_DEFAULT); } static void writecache_resume(struct dm_target *ti) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 0ec85d159bcde2be9e640b7aca6aa4c7af8d79fd..29270f6f272f6aa2140850245feecdc4daecbd88 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2897,6 +2897,9 @@ static void __dm_internal_suspend(struct mapped_device *md, unsigned int suspend static void __dm_internal_resume(struct mapped_device *md) { + int r; + struct dm_table *map; + BUG_ON(!md->internal_suspend_count); if (--md->internal_suspend_count) @@ -2905,12 +2908,23 @@ static void __dm_internal_resume(struct mapped_device *md) if (dm_suspended_md(md)) goto done; /* resume from nested suspend */ - /* - * NOTE: existing callers don't need to call dm_table_resume_targets - * (which may fail -- so best to avoid it for now by passing NULL map) - */ - (void) __dm_resume(md, NULL); - + map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock)); + r = __dm_resume(md, map); + if (r) { + /* + * If a preresume method of some target failed, we are in a + * tricky situation. We can't return an error to the caller. We + * can't fake success because then the "resume" and + * "postsuspend" methods would not be paired correctly, and it + * would break various targets, for example it would cause list + * corruption in the "origin" target. + * + * So, we fake normal suspend here, to make sure that the + * "resume" and "postsuspend" methods will be paired correctly. + */ + DMERR("Preresume method failed: %d", r); + set_bit(DMF_SUSPENDED, &md->flags); + } done: clear_bit(DMF_SUSPENDED_INTERNALLY, &md->flags); smp_mb__after_atomic(); diff --git a/drivers/md/md.c b/drivers/md/md.c index 3ccf1920682cb9c4e1aa8e40a64bc57f47faaf2d..506c998c0ca5956449bca5c46a098088cefaf10c 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -564,8 +564,12 @@ static void submit_flushes(struct work_struct *ws) rcu_read_lock(); } rcu_read_unlock(); - if (atomic_dec_and_test(&mddev->flush_pending)) + if (atomic_dec_and_test(&mddev->flush_pending)) { + /* The pair is percpu_ref_get() from md_flush_request() */ + percpu_ref_put(&mddev->active_io); + queue_work(md_wq, &mddev->flush_work); + } } static void md_submit_flush_data(struct work_struct *ws) @@ -963,9 +967,10 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev, return; bio = bio_alloc_bioset(rdev->meta_bdev ? rdev->meta_bdev : rdev->bdev, - 1, - REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH | REQ_FUA, - GFP_NOIO, &mddev->sync_set); + 1, + REQ_OP_WRITE | REQ_SYNC | REQ_IDLE | REQ_META + | REQ_PREFLUSH | REQ_FUA, + GFP_NOIO, &mddev->sync_set); atomic_inc(&rdev->nr_pending); @@ -2503,6 +2508,7 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev) fail: pr_warn("md: failed to register dev-%s for %s\n", b, mdname(mddev)); + mddev_destroy_serial_pool(mddev, rdev, false); return err; } @@ -4898,11 +4904,21 @@ action_store(struct mddev *mddev, const char *page, size_t len) return -EINVAL; err = mddev_lock(mddev); if (!err) { - if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { err = -EBUSY; - else { + } else if (mddev->reshape_position == MaxSector || + mddev->pers->check_reshape == NULL || + mddev->pers->check_reshape(mddev)) { clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); err = mddev->pers->start_reshape(mddev); + } else { + /* + * If reshape is still in progress, and + * md_check_recovery() can continue to reshape, + * don't restart reshape because data can be + * corrupted for raid456. + */ + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); } mddev_unlock(mddev); } @@ -6228,7 +6244,15 @@ static void md_clean(struct mddev *mddev) mddev->persistent = 0; mddev->level = LEVEL_NONE; mddev->clevel[0] = 0; - mddev->flags = 0; + /* + * Don't clear MD_CLOSING, or mddev can be opened again. + * 'hold_active != 0' means mddev is still in the creation + * process and will be used later. + */ + if (mddev->hold_active) + mddev->flags = 0; + else + mddev->flags &= BIT_ULL_MASK(MD_CLOSING); mddev->sb_flags = 0; mddev->ro = MD_RDWR; mddev->metadata_type[0] = 0; @@ -7556,7 +7580,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, int err = 0; void __user *argp = (void __user *)arg; struct mddev *mddev = NULL; - bool did_set_md_closing = false; if (!md_ioctl_valid(cmd)) return -ENOTTY; @@ -7643,7 +7666,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, err = -EBUSY; goto out; } - did_set_md_closing = true; mutex_unlock(&mddev->open_mutex); sync_blockdev(bdev); } @@ -7806,7 +7828,7 @@ unlock: mddev->hold_active = 0; mddev_unlock(mddev); out: - if(did_set_md_closing) + if (cmd == STOP_ARRAY_RO || (err && cmd == STOP_ARRAY)) clear_bit(MD_CLOSING, &mddev->flags); return err; } diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index 1cc783d7030d84d3a94812c29d885dd357e337a8..18d949d63543bea80f986d8eb86ce304a9243413 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -726,7 +726,7 @@ static int shadow_child(struct dm_btree_info *info, struct dm_btree_value_type * * nodes, so saves metadata space. */ static int split_two_into_three(struct shadow_spine *s, unsigned int parent_index, - struct dm_btree_value_type *vt, uint64_t key) + struct dm_btree_value_type *vt, uint64_t key) { int r; unsigned int middle_index; @@ -781,7 +781,7 @@ static int split_two_into_three(struct shadow_spine *s, unsigned int parent_inde if (shadow_current(s) != right) unlock_block(s->info, right); - return r; + return r; } @@ -1216,7 +1216,7 @@ int btree_get_overwrite_leaf(struct dm_btree_info *info, dm_block_t root, static bool need_insert(struct btree_node *node, uint64_t *keys, unsigned int level, unsigned int index) { - return ((index >= le32_to_cpu(node->header.nr_entries)) || + return ((index >= le32_to_cpu(node->header.nr_entries)) || (le64_to_cpu(node->keys[index]) != keys[level])); } diff --git a/drivers/md/persistent-data/dm-space-map-common.c b/drivers/md/persistent-data/dm-space-map-common.c index af800efed9f3ce99668bbb45448fcb664500d2e7..4833a3998c1d979b0496db53985827f755837ed7 100644 --- a/drivers/md/persistent-data/dm-space-map-common.c +++ b/drivers/md/persistent-data/dm-space-map-common.c @@ -390,7 +390,7 @@ int sm_ll_find_free_block(struct ll_disk *ll, dm_block_t begin, } int sm_ll_find_common_free_block(struct ll_disk *old_ll, struct ll_disk *new_ll, - dm_block_t begin, dm_block_t end, dm_block_t *b) + dm_block_t begin, dm_block_t end, dm_block_t *b) { int r; uint32_t count; diff --git a/drivers/md/persistent-data/dm-space-map-common.h b/drivers/md/persistent-data/dm-space-map-common.h index 706ceb85d68006d0e6d968d2841b5844d051d29f..63d9a72e3265c23af2ec3da61c6d447133d999c3 100644 --- a/drivers/md/persistent-data/dm-space-map-common.h +++ b/drivers/md/persistent-data/dm-space-map-common.h @@ -120,7 +120,7 @@ int sm_ll_lookup(struct ll_disk *ll, dm_block_t b, uint32_t *result); int sm_ll_find_free_block(struct ll_disk *ll, dm_block_t begin, dm_block_t end, dm_block_t *result); int sm_ll_find_common_free_block(struct ll_disk *old_ll, struct ll_disk *new_ll, - dm_block_t begin, dm_block_t end, dm_block_t *result); + dm_block_t begin, dm_block_t end, dm_block_t *result); /* * The next three functions return (via nr_allocations) the net number of diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 7b318e7e8d459c8ac60d8fac4b6e7be6992bae88..009f7ffe4e10c7f325b97502ce79a1fcc806ec6a 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -920,6 +920,7 @@ static void flush_pending_writes(struct r10conf *conf) raid1_submit_write(bio); bio = next; + cond_resched(); } blk_finish_plug(&plug); } else @@ -1130,6 +1131,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) raid1_submit_write(bio); bio = next; + cond_resched(); } kfree(plug); } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index e4564ca1f2434935bd73155bb7756f2d5eecccbd..8cf2317857e0ac6925c6fa7de03b0a206abcdbe5 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2420,7 +2420,7 @@ static int grow_one_stripe(struct r5conf *conf, gfp_t gfp) atomic_inc(&conf->active_stripes); raid5_release_stripe(sh); - conf->max_nr_stripes++; + WRITE_ONCE(conf->max_nr_stripes, conf->max_nr_stripes + 1); return 1; } @@ -2717,7 +2717,7 @@ static int drop_one_stripe(struct r5conf *conf) shrink_buffers(sh); free_stripe(conf->slab_cache, sh); atomic_dec(&conf->active_stripes); - conf->max_nr_stripes--; + WRITE_ONCE(conf->max_nr_stripes, conf->max_nr_stripes - 1); return 1; } @@ -6891,7 +6891,7 @@ raid5_set_cache_size(struct mddev *mddev, int size) if (size <= 16 || size > 32768) return -EINVAL; - conf->min_nr_stripes = size; + WRITE_ONCE(conf->min_nr_stripes, size); mutex_lock(&conf->cache_size_mutex); while (size < conf->max_nr_stripes && drop_one_stripe(conf)) @@ -6903,7 +6903,7 @@ raid5_set_cache_size(struct mddev *mddev, int size) mutex_lock(&conf->cache_size_mutex); while (size > conf->max_nr_stripes) if (!grow_one_stripe(conf, GFP_KERNEL)) { - conf->min_nr_stripes = conf->max_nr_stripes; + WRITE_ONCE(conf->min_nr_stripes, conf->max_nr_stripes); result = -ENOMEM; break; } @@ -7468,11 +7468,13 @@ static unsigned long raid5_cache_count(struct shrinker *shrink, struct shrink_control *sc) { struct r5conf *conf = container_of(shrink, struct r5conf, shrinker); + int max_stripes = READ_ONCE(conf->max_nr_stripes); + int min_stripes = READ_ONCE(conf->min_nr_stripes); - if (conf->max_nr_stripes < conf->min_nr_stripes) + if (max_stripes < min_stripes) /* unlikely, but not impossible */ return 0; - return conf->max_nr_stripes - conf->min_nr_stripes; + return max_stripes - min_stripes; } static struct r5conf *setup_conf(struct mddev *mddev) diff --git a/drivers/media/cec/core/cec-adap.c b/drivers/media/cec/core/cec-adap.c index 4bc2a705029e614e4b61865a4f1be2e4849b38f2..c761ac35e120dc419da911fb9352450ab6e2e92d 100644 --- a/drivers/media/cec/core/cec-adap.c +++ b/drivers/media/cec/core/cec-adap.c @@ -1121,20 +1121,6 @@ void cec_received_msg_ts(struct cec_adapter *adap, if (valid_la && min_len) { /* These messages have special length requirements */ switch (cmd) { - case CEC_MSG_TIMER_STATUS: - if (msg->msg[2] & 0x10) { - switch (msg->msg[2] & 0xf) { - case CEC_OP_PROG_INFO_NOT_ENOUGH_SPACE: - case CEC_OP_PROG_INFO_MIGHT_NOT_BE_ENOUGH_SPACE: - if (msg->len < 5) - valid_la = false; - break; - } - } else if ((msg->msg[2] & 0xf) == CEC_OP_PROG_ERROR_DUPLICATE) { - if (msg->len < 5) - valid_la = false; - } - break; case CEC_MSG_RECORD_ON: switch (msg->msg[2]) { case CEC_OP_RECORD_SRC_OWN: diff --git a/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c b/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c index 303d02b1d71c9e67d34a8710a54f98c5d2576e9f..fe30f5b0050dd9866002d7b6bd43a27a7a011b90 100644 --- a/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c +++ b/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c @@ -113,6 +113,7 @@ int tpg_alloc(struct tpg_data *tpg, unsigned max_w) { unsigned pat; unsigned plane; + int ret = 0; tpg->max_line_width = max_w; for (pat = 0; pat < TPG_MAX_PAT_LINES; pat++) { @@ -121,14 +122,18 @@ int tpg_alloc(struct tpg_data *tpg, unsigned max_w) tpg->lines[pat][plane] = vzalloc(array3_size(max_w, 2, pixelsz)); - if (!tpg->lines[pat][plane]) - return -ENOMEM; + if (!tpg->lines[pat][plane]) { + ret = -ENOMEM; + goto free_lines; + } if (plane == 0) continue; tpg->downsampled_lines[pat][plane] = vzalloc(array3_size(max_w, 2, pixelsz)); - if (!tpg->downsampled_lines[pat][plane]) - return -ENOMEM; + if (!tpg->downsampled_lines[pat][plane]) { + ret = -ENOMEM; + goto free_lines; + } } } for (plane = 0; plane < TPG_MAX_PLANES; plane++) { @@ -136,18 +141,45 @@ int tpg_alloc(struct tpg_data *tpg, unsigned max_w) tpg->contrast_line[plane] = vzalloc(array_size(pixelsz, max_w)); - if (!tpg->contrast_line[plane]) - return -ENOMEM; + if (!tpg->contrast_line[plane]) { + ret = -ENOMEM; + goto free_contrast_line; + } tpg->black_line[plane] = vzalloc(array_size(pixelsz, max_w)); - if (!tpg->black_line[plane]) - return -ENOMEM; + if (!tpg->black_line[plane]) { + ret = -ENOMEM; + goto free_contrast_line; + } tpg->random_line[plane] = vzalloc(array3_size(max_w, 2, pixelsz)); - if (!tpg->random_line[plane]) - return -ENOMEM; + if (!tpg->random_line[plane]) { + ret = -ENOMEM; + goto free_contrast_line; + } } return 0; + +free_contrast_line: + for (plane = 0; plane < TPG_MAX_PLANES; plane++) { + vfree(tpg->contrast_line[plane]); + vfree(tpg->black_line[plane]); + vfree(tpg->random_line[plane]); + tpg->contrast_line[plane] = NULL; + tpg->black_line[plane] = NULL; + tpg->random_line[plane] = NULL; + } +free_lines: + for (pat = 0; pat < TPG_MAX_PAT_LINES; pat++) + for (plane = 0; plane < TPG_MAX_PLANES; plane++) { + vfree(tpg->lines[pat][plane]); + tpg->lines[pat][plane] = NULL; + if (plane == 0) + continue; + vfree(tpg->downsampled_lines[pat][plane]); + tpg->downsampled_lines[pat][plane] = NULL; + } + return ret; } EXPORT_SYMBOL_GPL(tpg_alloc); diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c index d352e028491aa380db224604332912a1f1e36907..aefee2277254d0c5d85f2771931fc8ec8d0226f3 100644 --- a/drivers/media/dvb-core/dvbdev.c +++ b/drivers/media/dvb-core/dvbdev.c @@ -494,6 +494,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, dvbdevfops = kmemdup(template->fops, sizeof(*dvbdevfops), GFP_KERNEL); if (!dvbdevfops) { kfree(dvbdev); + *pdvbdev = NULL; mutex_unlock(&dvbdev_register_lock); return -ENOMEM; } @@ -502,6 +503,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, if (!new_node) { kfree(dvbdevfops); kfree(dvbdev); + *pdvbdev = NULL; mutex_unlock(&dvbdev_register_lock); return -ENOMEM; } @@ -535,6 +537,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, } list_del (&dvbdev->list_head); kfree(dvbdev); + *pdvbdev = NULL; up_write(&minor_rwsem); mutex_unlock(&dvbdev_register_lock); return -EINVAL; @@ -557,6 +560,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, dvb_media_device_free(dvbdev); list_del (&dvbdev->list_head); kfree(dvbdev); + *pdvbdev = NULL; mutex_unlock(&dvbdev_register_lock); return ret; } @@ -575,6 +579,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, dvb_media_device_free(dvbdev); list_del (&dvbdev->list_head); kfree(dvbdev); + *pdvbdev = NULL; mutex_unlock(&dvbdev_register_lock); return PTR_ERR(clsdev); } diff --git a/drivers/media/dvb-frontends/stv0367.c b/drivers/media/dvb-frontends/stv0367.c index 04556b77c16c9b51ddfcb628d42e48ba4a73efaa..0977564a4a1a4066e6fb14f01f183b64099dbe93 100644 --- a/drivers/media/dvb-frontends/stv0367.c +++ b/drivers/media/dvb-frontends/stv0367.c @@ -118,50 +118,32 @@ static const s32 stv0367cab_RF_LookUp2[RF_LOOKUP_TABLE2_SIZE][RF_LOOKUP_TABLE2_S } }; -static -int stv0367_writeregs(struct stv0367_state *state, u16 reg, u8 *data, int len) +static noinline_for_stack +int stv0367_writereg(struct stv0367_state *state, u16 reg, u8 data) { - u8 buf[MAX_XFER_SIZE]; + u8 buf[3] = { MSB(reg), LSB(reg), data }; struct i2c_msg msg = { .addr = state->config->demod_address, .flags = 0, .buf = buf, - .len = len + 2 + .len = 3, }; int ret; - if (2 + len > sizeof(buf)) { - printk(KERN_WARNING - "%s: i2c wr reg=%04x: len=%d is too big!\n", - KBUILD_MODNAME, reg, len); - return -EINVAL; - } - - - buf[0] = MSB(reg); - buf[1] = LSB(reg); - memcpy(buf + 2, data, len); - if (i2cdebug) printk(KERN_DEBUG "%s: [%02x] %02x: %02x\n", __func__, - state->config->demod_address, reg, buf[2]); + state->config->demod_address, reg, data); ret = i2c_transfer(state->i2c, &msg, 1); if (ret != 1) printk(KERN_ERR "%s: i2c write error! ([%02x] %02x: %02x)\n", - __func__, state->config->demod_address, reg, buf[2]); + __func__, state->config->demod_address, reg, data); return (ret != 1) ? -EREMOTEIO : 0; } -static int stv0367_writereg(struct stv0367_state *state, u16 reg, u8 data) -{ - u8 tmp = data; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */ - - return stv0367_writeregs(state, reg, &tmp, 1); -} - -static u8 stv0367_readreg(struct stv0367_state *state, u16 reg) +static noinline_for_stack +u8 stv0367_readreg(struct stv0367_state *state, u16 reg) { u8 b0[] = { 0, 0 }; u8 b1[] = { 0 }; diff --git a/drivers/media/i2c/tc358743.c b/drivers/media/i2c/tc358743.c index cc699daf244c3e64725378d2f307450f89380c29..fe50f1d4304a8c3a127a5e8e149eb8b73fea5195 100644 --- a/drivers/media/i2c/tc358743.c +++ b/drivers/media/i2c/tc358743.c @@ -2123,9 +2123,6 @@ static int tc358743_probe(struct i2c_client *client) state->mbus_fmt_code = MEDIA_BUS_FMT_RGB888_1X24; sd->dev = &client->dev; - err = v4l2_async_register_subdev(sd); - if (err < 0) - goto err_hdl; mutex_init(&state->confctl_mutex); @@ -2183,6 +2180,10 @@ static int tc358743_probe(struct i2c_client *client) if (err) goto err_work_queues; + err = v4l2_async_register_subdev(sd); + if (err < 0) + goto err_work_queues; + v4l2_info(sd, "%s found @ 0x%x (%s)\n", client->name, client->addr << 1, client->adapter->name); diff --git a/drivers/media/mc/mc-entity.c b/drivers/media/mc/mc-entity.c index f268cf66053e17aaa865152dfba6ace3e2165517..8919df09e3e8d6b07bd91f25c88d34830bfcfaa9 100644 --- a/drivers/media/mc/mc-entity.c +++ b/drivers/media/mc/mc-entity.c @@ -509,14 +509,15 @@ static int media_pipeline_walk_push(struct media_pipeline_walk *walk, /* * Move the top entry link cursor to the next link. If all links of the entry - * have been visited, pop the entry itself. + * have been visited, pop the entry itself. Return true if the entry has been + * popped. */ -static void media_pipeline_walk_pop(struct media_pipeline_walk *walk) +static bool media_pipeline_walk_pop(struct media_pipeline_walk *walk) { struct media_pipeline_walk_entry *entry; if (WARN_ON(walk->stack.top < 0)) - return; + return false; entry = media_pipeline_walk_top(walk); @@ -526,7 +527,7 @@ static void media_pipeline_walk_pop(struct media_pipeline_walk *walk) walk->stack.top); walk->stack.top--; - return; + return true; } entry->links = entry->links->next; @@ -534,6 +535,8 @@ static void media_pipeline_walk_pop(struct media_pipeline_walk *walk) dev_dbg(walk->mdev->dev, "media pipeline: moved entry %u to next link\n", walk->stack.top); + + return false; } /* Free all memory allocated while walking the pipeline. */ @@ -579,30 +582,24 @@ static int media_pipeline_explore_next_link(struct media_pipeline *pipe, struct media_pipeline_walk *walk) { struct media_pipeline_walk_entry *entry = media_pipeline_walk_top(walk); - struct media_pad *pad; + struct media_pad *origin; struct media_link *link; struct media_pad *local; struct media_pad *remote; + bool last_link; int ret; - pad = entry->pad; + origin = entry->pad; link = list_entry(entry->links, typeof(*link), list); - media_pipeline_walk_pop(walk); + last_link = media_pipeline_walk_pop(walk); dev_dbg(walk->mdev->dev, "media pipeline: exploring link '%s':%u -> '%s':%u\n", link->source->entity->name, link->source->index, link->sink->entity->name, link->sink->index); - /* Skip links that are not enabled. */ - if (!(link->flags & MEDIA_LNK_FL_ENABLED)) { - dev_dbg(walk->mdev->dev, - "media pipeline: skipping link (disabled)\n"); - return 0; - } - /* Get the local pad and remote pad. */ - if (link->source->entity == pad->entity) { + if (link->source->entity == origin->entity) { local = link->source; remote = link->sink; } else { @@ -614,25 +611,64 @@ static int media_pipeline_explore_next_link(struct media_pipeline *pipe, * Skip links that originate from a different pad than the incoming pad * that is not connected internally in the entity to the incoming pad. */ - if (pad != local && - !media_entity_has_pad_interdep(pad->entity, pad->index, local->index)) { + if (origin != local && + !media_entity_has_pad_interdep(origin->entity, origin->index, + local->index)) { dev_dbg(walk->mdev->dev, "media pipeline: skipping link (no route)\n"); - return 0; + goto done; } /* - * Add the local and remote pads of the link to the pipeline and push - * them to the stack, if they're not already present. + * Add the local pad of the link to the pipeline and push it to the + * stack, if not already present. */ ret = media_pipeline_add_pad(pipe, walk, local); if (ret) return ret; + /* Similarly, add the remote pad, but only if the link is enabled. */ + if (!(link->flags & MEDIA_LNK_FL_ENABLED)) { + dev_dbg(walk->mdev->dev, + "media pipeline: skipping link (disabled)\n"); + goto done; + } + ret = media_pipeline_add_pad(pipe, walk, remote); if (ret) return ret; +done: + /* + * If we're done iterating over links, iterate over pads of the entity. + * This is necessary to discover pads that are not connected with any + * link. Those are dead ends from a pipeline exploration point of view, + * but are still part of the pipeline and need to be added to enable + * proper validation. + */ + if (!last_link) + return 0; + + dev_dbg(walk->mdev->dev, + "media pipeline: adding unconnected pads of '%s'\n", + local->entity->name); + + media_entity_for_each_pad(origin->entity, local) { + /* + * Skip the origin pad (already handled), pad that have links + * (already discovered through iterating over links) and pads + * not internally connected. + */ + if (origin == local || !local->num_links || + !media_entity_has_pad_interdep(origin->entity, origin->index, + local->index)) + continue; + + ret = media_pipeline_add_pad(pipe, walk, local); + if (ret) + return ret; + } + return 0; } @@ -744,7 +780,6 @@ __must_check int __media_pipeline_start(struct media_pad *pad, struct media_pad *pad = ppad->pad; struct media_entity *entity = pad->entity; bool has_enabled_link = false; - bool has_link = false; struct media_link *link; dev_dbg(mdev->dev, "Validating pad '%s':%u\n", pad->entity->name, @@ -774,7 +809,6 @@ __must_check int __media_pipeline_start(struct media_pad *pad, /* Record if the pad has links and enabled links. */ if (link->flags & MEDIA_LNK_FL_ENABLED) has_enabled_link = true; - has_link = true; /* * Validate the link if it's enabled and has the @@ -812,7 +846,7 @@ __must_check int __media_pipeline_start(struct media_pad *pad, * 3. If the pad has the MEDIA_PAD_FL_MUST_CONNECT flag set, * ensure that it has either no link or an enabled link. */ - if ((pad->flags & MEDIA_PAD_FL_MUST_CONNECT) && has_link && + if ((pad->flags & MEDIA_PAD_FL_MUST_CONNECT) && !has_enabled_link) { dev_dbg(mdev->dev, "Pad '%s':%u must be connected by an enabled link\n", @@ -957,6 +991,9 @@ static void __media_entity_remove_link(struct media_entity *entity, /* Remove the reverse links for a data link. */ if ((link->flags & MEDIA_LNK_FL_LINK_TYPE) == MEDIA_LNK_FL_DATA_LINK) { + link->source->num_links--; + link->sink->num_links--; + if (link->source->entity == entity) remote = link->sink->entity; else @@ -1017,6 +1054,11 @@ media_create_pad_link(struct media_entity *source, u16 source_pad, struct media_link *link; struct media_link *backlink; + if (flags & MEDIA_LNK_FL_LINK_TYPE) + return -EINVAL; + + flags |= MEDIA_LNK_FL_DATA_LINK; + if (WARN_ON(!source || !sink) || WARN_ON(source_pad >= source->num_pads) || WARN_ON(sink_pad >= sink->num_pads)) @@ -1032,7 +1074,7 @@ media_create_pad_link(struct media_entity *source, u16 source_pad, link->source = &source->pads[source_pad]; link->sink = &sink->pads[sink_pad]; - link->flags = flags & ~MEDIA_LNK_FL_INTERFACE_LINK; + link->flags = flags; /* Initialize graph object embedded at the new link */ media_gobj_create(source->graph_obj.mdev, MEDIA_GRAPH_LINK, @@ -1063,6 +1105,9 @@ media_create_pad_link(struct media_entity *source, u16 source_pad, sink->num_links++; source->num_links++; + link->source->num_links++; + link->sink->num_links++; + return 0; } EXPORT_SYMBOL_GPL(media_create_pad_link); diff --git a/drivers/media/pci/sta2x11/sta2x11_vip.c b/drivers/media/pci/sta2x11/sta2x11_vip.c index 8535e49a4c4f9ba852db4889e7984132083ae285..1f7ab56de4a0036d82170a1c95458599b490410f 100644 --- a/drivers/media/pci/sta2x11/sta2x11_vip.c +++ b/drivers/media/pci/sta2x11/sta2x11_vip.c @@ -756,7 +756,7 @@ static const struct video_device video_dev_template = { /** * vip_irq - interrupt routine * @irq: Number of interrupt ( not used, correct number is assumed ) - * @vip: local data structure containing all information + * @data: local data structure containing all information * * check for both frame interrupts set ( top and bottom ). * check FIFO overflow, but limit number of log messages after open. @@ -766,8 +766,9 @@ static const struct video_device video_dev_template = { * * IRQ_HANDLED, interrupt done. */ -static irqreturn_t vip_irq(int irq, struct sta2x11_vip *vip) +static irqreturn_t vip_irq(int irq, void *data) { + struct sta2x11_vip *vip = data; unsigned int status; status = reg_read(vip, DVP_ITS); @@ -1049,9 +1050,7 @@ static int sta2x11_vip_init_one(struct pci_dev *pdev, spin_lock_init(&vip->slock); - ret = request_irq(pdev->irq, - (irq_handler_t) vip_irq, - IRQF_SHARED, KBUILD_MODNAME, vip); + ret = request_irq(pdev->irq, vip_irq, IRQF_SHARED, KBUILD_MODNAME, vip); if (ret) { dev_err(&pdev->dev, "request_irq failed\n"); ret = -ENODEV; diff --git a/drivers/media/platform/mediatek/mdp/mtk_mdp_vpu.c b/drivers/media/platform/mediatek/mdp/mtk_mdp_vpu.c index b065ccd0691404e73a4fdb1ec4952d5ef1e20d3a..378a1cba0144fa771eddbb021f22569c133c3221 100644 --- a/drivers/media/platform/mediatek/mdp/mtk_mdp_vpu.c +++ b/drivers/media/platform/mediatek/mdp/mtk_mdp_vpu.c @@ -26,7 +26,7 @@ static void mtk_mdp_vpu_handle_init_ack(const struct mdp_ipi_comm_ack *msg) vpu->inst_addr = msg->vpu_inst_addr; } -static void mtk_mdp_vpu_ipi_handler(const void *data, unsigned int len, +static void mtk_mdp_vpu_ipi_handler(void *data, unsigned int len, void *priv) { const struct mdp_ipi_comm_ack *msg = data; diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_fw_vpu.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_fw_vpu.c index cfc7ebed8fb7ab7a828ff1357b5cc5fa04afbe2a..1ec29f1b163a13a68cd4f3ed11be3d24b2218662 100644 --- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_fw_vpu.c +++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_fw_vpu.c @@ -29,15 +29,7 @@ static int mtk_vcodec_vpu_set_ipi_register(struct mtk_vcodec_fw *fw, int id, mtk_vcodec_ipi_handler handler, const char *name, void *priv) { - /* - * The handler we receive takes a void * as its first argument. We - * cannot change this because it needs to be passed down to the rproc - * subsystem when SCP is used. VPU takes a const argument, which is - * more constrained, so the conversion below is safe. - */ - ipi_handler_t handler_const = (ipi_handler_t)handler; - - return vpu_ipi_register(fw->pdev, id, handler_const, name, priv); + return vpu_ipi_register(fw->pdev, id, handler, name, priv); } static int mtk_vcodec_vpu_ipi_send(struct mtk_vcodec_fw *fw, int id, void *buf, diff --git a/drivers/media/platform/mediatek/vpu/mtk_vpu.c b/drivers/media/platform/mediatek/vpu/mtk_vpu.c index 6beab9e86a22a435310ae6a4dcfe6caef3a5b8ba..44adf5cfc9bb23f2c14d6c52f5bf561bab1a5c53 100644 --- a/drivers/media/platform/mediatek/vpu/mtk_vpu.c +++ b/drivers/media/platform/mediatek/vpu/mtk_vpu.c @@ -635,7 +635,7 @@ OUT_LOAD_FW: } EXPORT_SYMBOL_GPL(vpu_load_firmware); -static void vpu_init_ipi_handler(const void *data, unsigned int len, void *priv) +static void vpu_init_ipi_handler(void *data, unsigned int len, void *priv) { struct mtk_vpu *vpu = priv; const struct vpu_run *run = data; diff --git a/drivers/media/platform/mediatek/vpu/mtk_vpu.h b/drivers/media/platform/mediatek/vpu/mtk_vpu.h index a56053ff135af7b8e74c4463c7687b4a3a98f113..da05f3e74081084dd965284ecfe7e38af2fef99c 100644 --- a/drivers/media/platform/mediatek/vpu/mtk_vpu.h +++ b/drivers/media/platform/mediatek/vpu/mtk_vpu.h @@ -17,7 +17,7 @@ * VPU interfaces with other blocks by share memory and interrupt. */ -typedef void (*ipi_handler_t) (const void *data, +typedef void (*ipi_handler_t) (void *data, unsigned int len, void *priv); diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c index d4540684ea9af64e36df3df419a859df6c43b78b..0bcb9db5ad19012754323cccea4f3a6684a3aca5 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c @@ -701,6 +701,9 @@ irqreturn_t rkisp1_capture_isr(int irq, void *ctx) unsigned int i; u32 status; + if (!rkisp1->irqs_enabled) + return IRQ_NONE; + status = rkisp1_read(rkisp1, RKISP1_CIF_MI_MIS); if (!status) return IRQ_NONE; diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-common.h b/drivers/media/platform/rockchip/rkisp1/rkisp1-common.h index f9ec1c613894790484f4f5461567afe87a3482d1..5776292f914a4b1fcaee92dac1680b23e4fb48c3 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-common.h +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-common.h @@ -467,6 +467,7 @@ struct rkisp1_debug { * @debug: debug params to be exposed on debugfs * @info: version-specific ISP information * @irqs: IRQ line numbers + * @irqs_enabled: the hardware is enabled and can cause interrupts */ struct rkisp1_device { void __iomem *base_addr; @@ -488,6 +489,7 @@ struct rkisp1_device { struct rkisp1_debug debug; const struct rkisp1_info *info; int irqs[RKISP1_NUM_IRQS]; + bool irqs_enabled; }; /* diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c index e862f515cc6d3534e3357eacc7829a414cb12947..95b6e41c48ec25a84cbdb9ccf9ba40162b85112b 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c @@ -211,6 +211,9 @@ irqreturn_t rkisp1_csi_isr(int irq, void *ctx) struct rkisp1_device *rkisp1 = dev_get_drvdata(dev); u32 val, status; + if (!rkisp1->irqs_enabled) + return IRQ_NONE; + status = rkisp1_read(rkisp1, RKISP1_CIF_MIPI_MIS); if (!status) return IRQ_NONE; diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c index aeb6bb63667ebb3ac28a77fa709f89f834566069..7a3b69ba51b9759ccb2e7528cdd5ee33ff75b078 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c @@ -305,6 +305,24 @@ static int __maybe_unused rkisp1_runtime_suspend(struct device *dev) { struct rkisp1_device *rkisp1 = dev_get_drvdata(dev); + rkisp1->irqs_enabled = false; + /* Make sure the IRQ handler will see the above */ + mb(); + + /* + * Wait until any running IRQ handler has returned. The IRQ handler + * may get called even after this (as it's a shared interrupt line) + * but the 'irqs_enabled' flag will make the handler return immediately. + */ + for (unsigned int il = 0; il < ARRAY_SIZE(rkisp1->irqs); ++il) { + if (rkisp1->irqs[il] == -1) + continue; + + /* Skip if the irq line is the same as previous */ + if (il == 0 || rkisp1->irqs[il - 1] != rkisp1->irqs[il]) + synchronize_irq(rkisp1->irqs[il]); + } + clk_bulk_disable_unprepare(rkisp1->clk_size, rkisp1->clks); return pinctrl_pm_select_sleep_state(dev); } @@ -321,6 +339,10 @@ static int __maybe_unused rkisp1_runtime_resume(struct device *dev) if (ret) return ret; + rkisp1->irqs_enabled = true; + /* Make sure the IRQ handler will see the above */ + mb(); + return 0; } @@ -559,7 +581,7 @@ static int rkisp1_probe(struct platform_device *pdev) rkisp1->irqs[il] = irq; } - ret = devm_request_irq(dev, irq, info->isrs[i].isr, 0, + ret = devm_request_irq(dev, irq, info->isrs[i].isr, IRQF_SHARED, dev_driver_string(dev), dev); if (ret) { dev_err(dev, "request irq failed: %d\n", ret); diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c index 00dca284c122206df9bd603b6305f022c0d74a71..2af5c1a48070bbf2fe2c08287a9461584c489f6b 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c @@ -1023,6 +1023,9 @@ irqreturn_t rkisp1_isp_isr(int irq, void *ctx) struct rkisp1_device *rkisp1 = dev_get_drvdata(dev); u32 status, isp_err; + if (!rkisp1->irqs_enabled) + return IRQ_NONE; + status = rkisp1_read(rkisp1, RKISP1_CIF_ISP_MIS); if (!status) return IRQ_NONE; diff --git a/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c b/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c index aa65d70b6270a70ced67d3a880e43ec65a17d71b..7a2f558c981db65b6f4ce6c35a84847d6d345b01 100644 --- a/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c +++ b/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c @@ -66,6 +66,7 @@ static void deinterlace_device_run(void *priv) struct vb2_v4l2_buffer *src, *dst; unsigned int hstep, vstep; dma_addr_t addr; + int i; src = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx); dst = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx); @@ -160,6 +161,26 @@ static void deinterlace_device_run(void *priv) deinterlace_write(dev, DEINTERLACE_CH1_HORZ_FACT, hstep); deinterlace_write(dev, DEINTERLACE_CH1_VERT_FACT, vstep); + /* neutral filter coefficients */ + deinterlace_set_bits(dev, DEINTERLACE_FRM_CTRL, + DEINTERLACE_FRM_CTRL_COEF_ACCESS); + readl_poll_timeout(dev->base + DEINTERLACE_STATUS, val, + val & DEINTERLACE_STATUS_COEF_STATUS, 2, 40); + + for (i = 0; i < 32; i++) { + deinterlace_write(dev, DEINTERLACE_CH0_HORZ_COEF0 + i * 4, + DEINTERLACE_IDENTITY_COEF); + deinterlace_write(dev, DEINTERLACE_CH0_VERT_COEF + i * 4, + DEINTERLACE_IDENTITY_COEF); + deinterlace_write(dev, DEINTERLACE_CH1_HORZ_COEF0 + i * 4, + DEINTERLACE_IDENTITY_COEF); + deinterlace_write(dev, DEINTERLACE_CH1_VERT_COEF + i * 4, + DEINTERLACE_IDENTITY_COEF); + } + + deinterlace_clr_set_bits(dev, DEINTERLACE_FRM_CTRL, + DEINTERLACE_FRM_CTRL_COEF_ACCESS, 0); + deinterlace_clr_set_bits(dev, DEINTERLACE_FIELD_CTRL, DEINTERLACE_FIELD_CTRL_FIELD_CNT_MSK, DEINTERLACE_FIELD_CTRL_FIELD_CNT(ctx->field)); @@ -248,7 +269,6 @@ static irqreturn_t deinterlace_irq(int irq, void *data) static void deinterlace_init(struct deinterlace_dev *dev) { u32 val; - int i; deinterlace_write(dev, DEINTERLACE_BYPASS, DEINTERLACE_BYPASS_CSC); @@ -284,27 +304,7 @@ static void deinterlace_init(struct deinterlace_dev *dev) deinterlace_clr_set_bits(dev, DEINTERLACE_CHROMA_DIFF, DEINTERLACE_CHROMA_DIFF_TH_MSK, - DEINTERLACE_CHROMA_DIFF_TH(5)); - - /* neutral filter coefficients */ - deinterlace_set_bits(dev, DEINTERLACE_FRM_CTRL, - DEINTERLACE_FRM_CTRL_COEF_ACCESS); - readl_poll_timeout(dev->base + DEINTERLACE_STATUS, val, - val & DEINTERLACE_STATUS_COEF_STATUS, 2, 40); - - for (i = 0; i < 32; i++) { - deinterlace_write(dev, DEINTERLACE_CH0_HORZ_COEF0 + i * 4, - DEINTERLACE_IDENTITY_COEF); - deinterlace_write(dev, DEINTERLACE_CH0_VERT_COEF + i * 4, - DEINTERLACE_IDENTITY_COEF); - deinterlace_write(dev, DEINTERLACE_CH1_HORZ_COEF0 + i * 4, - DEINTERLACE_IDENTITY_COEF); - deinterlace_write(dev, DEINTERLACE_CH1_VERT_COEF + i * 4, - DEINTERLACE_IDENTITY_COEF); - } - - deinterlace_clr_set_bits(dev, DEINTERLACE_FRM_CTRL, - DEINTERLACE_FRM_CTRL_COEF_ACCESS, 0); + DEINTERLACE_CHROMA_DIFF_TH(31)); } static inline struct deinterlace_ctx *deinterlace_file2ctx(struct file *file) @@ -931,11 +931,18 @@ static int deinterlace_runtime_resume(struct device *device) return ret; } + ret = reset_control_deassert(dev->rstc); + if (ret) { + dev_err(dev->dev, "Failed to apply reset\n"); + + goto err_exclusive_rate; + } + ret = clk_prepare_enable(dev->bus_clk); if (ret) { dev_err(dev->dev, "Failed to enable bus clock\n"); - goto err_exclusive_rate; + goto err_rst; } ret = clk_prepare_enable(dev->mod_clk); @@ -952,23 +959,16 @@ static int deinterlace_runtime_resume(struct device *device) goto err_mod_clk; } - ret = reset_control_deassert(dev->rstc); - if (ret) { - dev_err(dev->dev, "Failed to apply reset\n"); - - goto err_ram_clk; - } - deinterlace_init(dev); return 0; -err_ram_clk: - clk_disable_unprepare(dev->ram_clk); err_mod_clk: clk_disable_unprepare(dev->mod_clk); err_bus_clk: clk_disable_unprepare(dev->bus_clk); +err_rst: + reset_control_assert(dev->rstc); err_exclusive_rate: clk_rate_exclusive_put(dev->mod_clk); @@ -979,11 +979,12 @@ static int deinterlace_runtime_suspend(struct device *device) { struct deinterlace_dev *dev = dev_get_drvdata(device); - reset_control_assert(dev->rstc); - clk_disable_unprepare(dev->ram_clk); clk_disable_unprepare(dev->mod_clk); clk_disable_unprepare(dev->bus_clk); + + reset_control_assert(dev->rstc); + clk_rate_exclusive_put(dev->mod_clk); return 0; diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index fe17c7f98e8101afdae3d608ab12a2ef7f971d0e..52d82cbe7685f5b5adadf4448a171fcb146612b8 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -253,7 +253,7 @@ int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) if (attr->attach_flags) return -EINVAL; - rcdev = rc_dev_get_from_fd(attr->target_fd); + rcdev = rc_dev_get_from_fd(attr->target_fd, true); if (IS_ERR(rcdev)) return PTR_ERR(rcdev); @@ -278,7 +278,7 @@ int lirc_prog_detach(const union bpf_attr *attr) if (IS_ERR(prog)) return PTR_ERR(prog); - rcdev = rc_dev_get_from_fd(attr->target_fd); + rcdev = rc_dev_get_from_fd(attr->target_fd, true); if (IS_ERR(rcdev)) { bpf_prog_put(prog); return PTR_ERR(rcdev); @@ -303,7 +303,7 @@ int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) if (attr->query.query_flags) return -EINVAL; - rcdev = rc_dev_get_from_fd(attr->query.target_fd); + rcdev = rc_dev_get_from_fd(attr->query.target_fd, false); if (IS_ERR(rcdev)) return PTR_ERR(rcdev); diff --git a/drivers/media/rc/ir_toy.c b/drivers/media/rc/ir_toy.c index 1968067092594979942f030af29bf4b484b5fd09..69e630d85262f65f413ee8c9d092ea85cee01c91 100644 --- a/drivers/media/rc/ir_toy.c +++ b/drivers/media/rc/ir_toy.c @@ -332,6 +332,7 @@ static int irtoy_tx(struct rc_dev *rc, uint *txbuf, uint count) sizeof(COMMAND_SMODE_EXIT), STATE_COMMAND_NO_RESP); if (err) { dev_err(irtoy->dev, "exit sample mode: %d\n", err); + kfree(buf); return err; } @@ -339,6 +340,7 @@ static int irtoy_tx(struct rc_dev *rc, uint *txbuf, uint count) sizeof(COMMAND_SMODE_ENTER), STATE_COMMAND); if (err) { dev_err(irtoy->dev, "enter sample mode: %d\n", err); + kfree(buf); return err; } diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c index 184e0b35744f3a580e7d6e8a9a19aab0991e41aa..adb8c794a2d7bbabfef16c538c43d189d85d3da1 100644 --- a/drivers/media/rc/lirc_dev.c +++ b/drivers/media/rc/lirc_dev.c @@ -814,7 +814,7 @@ void __exit lirc_dev_exit(void) unregister_chrdev_region(lirc_base_dev, RC_DEV_MAX); } -struct rc_dev *rc_dev_get_from_fd(int fd) +struct rc_dev *rc_dev_get_from_fd(int fd, bool write) { struct fd f = fdget(fd); struct lirc_fh *fh; @@ -828,6 +828,9 @@ struct rc_dev *rc_dev_get_from_fd(int fd) return ERR_PTR(-EINVAL); } + if (write && !(f.file->f_mode & FMODE_WRITE)) + return ERR_PTR(-EPERM); + fh = f.file->private_data; dev = fh->rc; diff --git a/drivers/media/rc/rc-core-priv.h b/drivers/media/rc/rc-core-priv.h index ef1e95e1af7fcccda49324e375b940cc92c627f2..7df949fc65e2b68bf88c12643410330fc1ad4635 100644 --- a/drivers/media/rc/rc-core-priv.h +++ b/drivers/media/rc/rc-core-priv.h @@ -325,7 +325,7 @@ void lirc_raw_event(struct rc_dev *dev, struct ir_raw_event ev); void lirc_scancode_event(struct rc_dev *dev, struct lirc_scancode *lsc); int lirc_register(struct rc_dev *dev); void lirc_unregister(struct rc_dev *dev); -struct rc_dev *rc_dev_get_from_fd(int fd); +struct rc_dev *rc_dev_get_from_fd(int fd, bool write); #else static inline int lirc_dev_init(void) { return 0; } static inline void lirc_dev_exit(void) {} diff --git a/drivers/media/tuners/xc4000.c b/drivers/media/tuners/xc4000.c index 57ded9ff3f04350df4c7705487c0110d0437d195..29bc63021c5aae978b7937b31b9eb81fc03a4fde 100644 --- a/drivers/media/tuners/xc4000.c +++ b/drivers/media/tuners/xc4000.c @@ -1515,10 +1515,10 @@ static int xc4000_get_frequency(struct dvb_frontend *fe, u32 *freq) { struct xc4000_priv *priv = fe->tuner_priv; + mutex_lock(&priv->lock); *freq = priv->freq_hz + priv->freq_offset; if (debug) { - mutex_lock(&priv->lock); if ((priv->cur_fw.type & (BASE | FM | DTV6 | DTV7 | DTV78 | DTV8)) == BASE) { u16 snr = 0; @@ -1529,8 +1529,8 @@ static int xc4000_get_frequency(struct dvb_frontend *fe, u32 *freq) return 0; } } - mutex_unlock(&priv->lock); } + mutex_unlock(&priv->lock); dprintk(1, "%s()\n", __func__); diff --git a/drivers/media/usb/em28xx/em28xx-cards.c b/drivers/media/usb/em28xx/em28xx-cards.c index 4d037c92af7c58a29fc39b3ab7d2ce593f1503cd..bae76023cf71d33cc7a85cdc4402c6d3a26f0d4b 100644 --- a/drivers/media/usb/em28xx/em28xx-cards.c +++ b/drivers/media/usb/em28xx/em28xx-cards.c @@ -4094,6 +4094,10 @@ static int em28xx_usb_probe(struct usb_interface *intf, * topology will likely change after the load of the em28xx subdrivers. */ #ifdef CONFIG_MEDIA_CONTROLLER + /* + * No need to check the return value, the device will still be + * usable without media controller API. + */ retval = media_device_register(dev->media_dev); #endif diff --git a/drivers/media/usb/go7007/go7007-driver.c b/drivers/media/usb/go7007/go7007-driver.c index 0c24e2984304874631c09dde658c3946463627ab..eb03f98b2ef1136079f9d1607f466e22cf0c9242 100644 --- a/drivers/media/usb/go7007/go7007-driver.c +++ b/drivers/media/usb/go7007/go7007-driver.c @@ -80,7 +80,7 @@ static int go7007_load_encoder(struct go7007 *go) const struct firmware *fw_entry; char fw_name[] = "go7007/go7007fw.bin"; void *bounce; - int fw_len, rv = 0; + int fw_len; u16 intr_val, intr_data; if (go->boot_fw == NULL) { @@ -109,9 +109,11 @@ static int go7007_load_encoder(struct go7007 *go) go7007_read_interrupt(go, &intr_val, &intr_data) < 0 || (intr_val & ~0x1) != 0x5a5a) { v4l2_err(go, "error transferring firmware\n"); - rv = -1; + kfree(go->boot_fw); + go->boot_fw = NULL; + return -1; } - return rv; + return 0; } MODULE_FIRMWARE("go7007/go7007fw.bin"); diff --git a/drivers/media/usb/go7007/go7007-usb.c b/drivers/media/usb/go7007/go7007-usb.c index eeb85981e02b67fcdb30307185e1a305c9a54d5e..762c13e49bfa5c76cf218dd942feb7217d4b9603 100644 --- a/drivers/media/usb/go7007/go7007-usb.c +++ b/drivers/media/usb/go7007/go7007-usb.c @@ -1201,7 +1201,9 @@ static int go7007_usb_probe(struct usb_interface *intf, u16 channel; /* read channel number from GPIO[1:0] */ - go7007_read_addr(go, 0x3c81, &channel); + if (go7007_read_addr(go, 0x3c81, &channel)) + goto allocfail; + channel &= 0x3; go->board_id = GO7007_BOARDID_ADLINK_MPG24; usb->board = board = &board_adlink_mpg24; diff --git a/drivers/media/usb/pvrusb2/pvrusb2-context.c b/drivers/media/usb/pvrusb2/pvrusb2-context.c index 1764674de98bc062faf5861681690aa19586e1ed..73c95ba2328a41b14a340847dbd864ae72040196 100644 --- a/drivers/media/usb/pvrusb2/pvrusb2-context.c +++ b/drivers/media/usb/pvrusb2/pvrusb2-context.c @@ -90,8 +90,10 @@ static void pvr2_context_destroy(struct pvr2_context *mp) } -static void pvr2_context_notify(struct pvr2_context *mp) +static void pvr2_context_notify(void *ptr) { + struct pvr2_context *mp = ptr; + pvr2_context_set_notify(mp,!0); } @@ -106,9 +108,7 @@ static void pvr2_context_check(struct pvr2_context *mp) pvr2_trace(PVR2_TRACE_CTXT, "pvr2_context %p (initialize)", mp); /* Finish hardware initialization */ - if (pvr2_hdw_initialize(mp->hdw, - (void (*)(void *))pvr2_context_notify, - mp)) { + if (pvr2_hdw_initialize(mp->hdw, pvr2_context_notify, mp)) { mp->video_stream.stream = pvr2_hdw_get_video_stream(mp->hdw); /* Trigger interface initialization. By doing this @@ -267,9 +267,9 @@ static void pvr2_context_exit(struct pvr2_context *mp) void pvr2_context_disconnect(struct pvr2_context *mp) { pvr2_hdw_disconnect(mp->hdw); - mp->disconnect_flag = !0; if (!pvr2_context_shutok()) pvr2_context_notify(mp); + mp->disconnect_flag = !0; } diff --git a/drivers/media/usb/pvrusb2/pvrusb2-dvb.c b/drivers/media/usb/pvrusb2/pvrusb2-dvb.c index 26811efe0fb58b32dbfe05c63cb1380e3704aa5c..9a9bae21c61475e9a5a8a98e68a8fb842188d6bc 100644 --- a/drivers/media/usb/pvrusb2/pvrusb2-dvb.c +++ b/drivers/media/usb/pvrusb2/pvrusb2-dvb.c @@ -88,8 +88,10 @@ static int pvr2_dvb_feed_thread(void *data) return stat; } -static void pvr2_dvb_notify(struct pvr2_dvb_adapter *adap) +static void pvr2_dvb_notify(void *ptr) { + struct pvr2_dvb_adapter *adap = ptr; + wake_up(&adap->buffer_wait_data); } @@ -149,7 +151,7 @@ static int pvr2_dvb_stream_do_start(struct pvr2_dvb_adapter *adap) } pvr2_stream_set_callback(pvr->video_stream.stream, - (pvr2_stream_callback) pvr2_dvb_notify, adap); + pvr2_dvb_notify, adap); ret = pvr2_stream_set_buffer_count(stream, PVR2_DVB_BUFFER_COUNT); if (ret < 0) return ret; diff --git a/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c b/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c index c04ab7258d645266c05bf9adc117566e9a1d962e..d608b793fa847b72c19ea78b4250283b9bf05f4b 100644 --- a/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c +++ b/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c @@ -1033,8 +1033,10 @@ static int pvr2_v4l2_open(struct file *file) } -static void pvr2_v4l2_notify(struct pvr2_v4l2_fh *fhp) +static void pvr2_v4l2_notify(void *ptr) { + struct pvr2_v4l2_fh *fhp = ptr; + wake_up(&fhp->wait_data); } @@ -1067,7 +1069,7 @@ static int pvr2_v4l2_iosetup(struct pvr2_v4l2_fh *fh) hdw = fh->channel.mc_head->hdw; sp = fh->pdi->stream->stream; - pvr2_stream_set_callback(sp,(pvr2_stream_callback)pvr2_v4l2_notify,fh); + pvr2_stream_set_callback(sp, pvr2_v4l2_notify, fh); pvr2_hdw_set_stream_type(hdw,fh->pdi->config); if ((ret = pvr2_hdw_set_streaming(hdw,!0)) < 0) return ret; return pvr2_ioread_set_enabled(fh->rhp,!0); @@ -1198,11 +1200,6 @@ static void pvr2_v4l2_dev_init(struct pvr2_v4l2_dev *dip, dip->minor_type = pvr2_v4l_type_video; nr_ptr = video_nr; caps |= V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_AUDIO; - if (!dip->stream) { - pr_err(KBUILD_MODNAME - ": Failed to set up pvrusb2 v4l video dev due to missing stream instance\n"); - return; - } break; case VFL_TYPE_VBI: dip->config = pvr2_config_vbi; diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c index 8fb6d3354f547d392b6547295c7da55ece8ba72c..a7aafd969dab993b25a381a4d538fdd319d161bd 100644 --- a/drivers/media/v4l2-core/v4l2-mem2mem.c +++ b/drivers/media/v4l2-core/v4l2-mem2mem.c @@ -1083,11 +1083,17 @@ static int v4l2_m2m_register_entity(struct media_device *mdev, entity->function = function; ret = media_entity_pads_init(entity, num_pads, pads); - if (ret) + if (ret) { + kfree(entity->name); + entity->name = NULL; return ret; + } ret = media_device_register_entity(mdev, entity); - if (ret) + if (ret) { + kfree(entity->name); + entity->name = NULL; return ret; + } return 0; } diff --git a/drivers/mfd/altera-sysmgr.c b/drivers/mfd/altera-sysmgr.c index 5d3715a28b28e2fd3067f34ab2e69999350b4b19..dbe1009943718349a4867de375b4520bee404316 100644 --- a/drivers/mfd/altera-sysmgr.c +++ b/drivers/mfd/altera-sysmgr.c @@ -110,7 +110,9 @@ struct regmap *altr_sysmgr_regmap_lookup_by_phandle(struct device_node *np, dev = driver_find_device_by_of_node(&altr_sysmgr_driver.driver, (void *)sysmgr_np); - of_node_put(sysmgr_np); + if (property) + of_node_put(sysmgr_np); + if (!dev) return ERR_PTR(-EPROBE_DEFER); diff --git a/drivers/mfd/stpmic1.c b/drivers/mfd/stpmic1.c index eb3da558c3fbdeeb52555ab31f5d016bb0222b93..ee0469d5d4354c890b2926551879971f31e7902c 100644 --- a/drivers/mfd/stpmic1.c +++ b/drivers/mfd/stpmic1.c @@ -108,8 +108,9 @@ static const struct regmap_irq stpmic1_irqs[] = { static const struct regmap_irq_chip stpmic1_regmap_irq_chip = { .name = "pmic_irq", .status_base = INT_PENDING_R1, - .mask_base = INT_CLEAR_MASK_R1, - .unmask_base = INT_SET_MASK_R1, + .mask_base = INT_SET_MASK_R1, + .unmask_base = INT_CLEAR_MASK_R1, + .mask_unmask_non_inverted = true, .ack_base = INT_CLEAR_R1, .num_regs = STPMIC1_PMIC_NUM_IRQ_REGS, .irqs = stpmic1_irqs, diff --git a/drivers/mfd/syscon.c b/drivers/mfd/syscon.c index 6196724ef39bb7fe42bab6b3d3de807ec4507de8..ecfe151220919e9a542295a28e48bc141395882d 100644 --- a/drivers/mfd/syscon.c +++ b/drivers/mfd/syscon.c @@ -223,7 +223,9 @@ struct regmap *syscon_regmap_lookup_by_phandle(struct device_node *np, return ERR_PTR(-ENODEV); regmap = syscon_node_to_regmap(syscon_np); - of_node_put(syscon_np); + + if (property) + of_node_put(syscon_np); return regmap; } diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index 938c4f41b98c7a2eaacb88ab5fc287c99df07f56..e664c1c852503dee6a6401660d9eedc4c3c38fac 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -581,6 +581,31 @@ static unsigned int at24_get_offset_adj(u8 flags, unsigned int byte_len) } } +static void at24_probe_temp_sensor(struct i2c_client *client) +{ + struct at24_data *at24 = i2c_get_clientdata(client); + struct i2c_board_info info = { .type = "jc42" }; + int ret; + u8 val; + + /* + * Byte 2 has value 11 for DDR3, earlier versions don't + * support the thermal sensor present flag + */ + ret = at24_read(at24, 2, &val, 1); + if (ret || val != 11) + return; + + /* Byte 32, bit 7 is set if temp sensor is present */ + ret = at24_read(at24, 32, &val, 1); + if (ret || !(val & BIT(7))) + return; + + info.addr = 0x18 | (client->addr & 7); + + i2c_new_client_device(client->adapter, &info); +} + static int at24_probe(struct i2c_client *client) { struct regmap_config regmap_config = { }; @@ -756,14 +781,6 @@ static int at24_probe(struct i2c_client *client) } pm_runtime_enable(dev); - at24->nvmem = devm_nvmem_register(dev, &nvmem_config); - if (IS_ERR(at24->nvmem)) { - pm_runtime_disable(dev); - if (!pm_runtime_status_suspended(dev)) - regulator_disable(at24->vcc_reg); - return PTR_ERR(at24->nvmem); - } - /* * Perform a one-byte test read to verify that the chip is functional, * unless powering on the device is to be avoided during probe (i.e. @@ -779,6 +796,19 @@ static int at24_probe(struct i2c_client *client) } } + at24->nvmem = devm_nvmem_register(dev, &nvmem_config); + if (IS_ERR(at24->nvmem)) { + pm_runtime_disable(dev); + if (!pm_runtime_status_suspended(dev)) + regulator_disable(at24->vcc_reg); + return dev_err_probe(dev, PTR_ERR(at24->nvmem), + "failed to register nvmem\n"); + } + + /* If this a SPD EEPROM, probe for DDR3 thermal sensor */ + if (cdata == &at24_data_spd) + at24_probe_temp_sensor(client); + pm_runtime_idle(dev); if (writable) diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index cc57cc820432876157940d016eaf24249e304886..69cc24962706c512f12379df54e9f5001c402628 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -1990,7 +1990,7 @@ static int fastrpc_cb_remove(struct platform_device *pdev) int i; spin_lock_irqsave(&cctx->lock, flags); - for (i = 1; i < FASTRPC_MAX_SESSIONS; i++) { + for (i = 0; i < FASTRPC_MAX_SESSIONS; i++) { if (cctx->session[i].sid == sess->sid) { cctx->session[i].valid = false; cctx->sesscount--; diff --git a/drivers/misc/lis3lv02d/lis3lv02d_i2c.c b/drivers/misc/lis3lv02d/lis3lv02d_i2c.c index fdec2c30eb165b73d17e63418e04f7dbf26152b2..63c717053e36bdd5cab4e2babd3572d1af952723 100644 --- a/drivers/misc/lis3lv02d/lis3lv02d_i2c.c +++ b/drivers/misc/lis3lv02d/lis3lv02d_i2c.c @@ -199,8 +199,14 @@ static int lis3lv02d_i2c_suspend(struct device *dev) struct i2c_client *client = to_i2c_client(dev); struct lis3lv02d *lis3 = i2c_get_clientdata(client); - if (!lis3->pdata || !lis3->pdata->wakeup_flags) + /* Turn on for wakeup if turned off by runtime suspend */ + if (lis3->pdata && lis3->pdata->wakeup_flags) { + if (pm_runtime_suspended(dev)) + lis3lv02d_poweron(lis3); + /* For non wakeup turn off if not already turned off by runtime suspend */ + } else if (!pm_runtime_suspended(dev)) lis3lv02d_poweroff(lis3); + return 0; } @@ -209,13 +215,12 @@ static int lis3lv02d_i2c_resume(struct device *dev) struct i2c_client *client = to_i2c_client(dev); struct lis3lv02d *lis3 = i2c_get_clientdata(client); - /* - * pm_runtime documentation says that devices should always - * be powered on at resume. Pm_runtime turns them off after system - * wide resume is complete. - */ - if (!lis3->pdata || !lis3->pdata->wakeup_flags || - pm_runtime_suspended(dev)) + /* Turn back off if turned on for wakeup and runtime suspended*/ + if (lis3->pdata && lis3->pdata->wakeup_flags) { + if (pm_runtime_suspended(dev)) + lis3lv02d_poweroff(lis3); + /* For non wakeup turn back on if not runtime suspended */ + } else if (!pm_runtime_suspended(dev)) lis3lv02d_poweron(lis3); return 0; diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index bdc65d50b945fc3c8f65f576880ce006f917559f..d3c03d4edbeff3631020cffdb4e6e7012f87d74d 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -112,6 +112,10 @@ #define MEI_DEV_ID_RPL_S 0x7A68 /* Raptor Lake Point S */ #define MEI_DEV_ID_MTL_M 0x7E70 /* Meteor Lake Point M */ +#define MEI_DEV_ID_ARL_S 0x7F68 /* Arrow Lake Point S */ +#define MEI_DEV_ID_ARL_H 0x7770 /* Arrow Lake Point H */ + +#define MEI_DEV_ID_LNL_M 0xA870 /* Lunar Lake Point M */ /* * MEI HW Section diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 5bf0d50d55a00b47391f34ac52dee239fd8145bd..a4bdc412845826f6339d4cda63d9f0da78d0ad88 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -116,9 +116,13 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_ADP_P, MEI_ME_PCH15_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_ADP_N, MEI_ME_PCH15_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_RPL_S, MEI_ME_PCH15_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_RPL_S, MEI_ME_PCH15_SPS_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_MTL_M, MEI_ME_PCH15_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ARL_S, MEI_ME_PCH15_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ARL_H, MEI_ME_PCH15_CFG)}, + + {MEI_PCI_DEVICE(MEI_DEV_ID_LNL_M, MEI_ME_PCH15_CFG)}, /* required last entry */ {0, } diff --git a/drivers/misc/open-dice.c b/drivers/misc/open-dice.c index c61be3404c6f283e8e3408edc3d35dd064e5d859..504b836a7abf8a1cf07a00de76f1041dbefd7995 100644 --- a/drivers/misc/open-dice.c +++ b/drivers/misc/open-dice.c @@ -142,7 +142,6 @@ static int __init open_dice_probe(struct platform_device *pdev) return -ENOMEM; *drvdata = (struct open_dice_drvdata){ - .lock = __MUTEX_INITIALIZER(drvdata->lock), .rmem = rmem, .misc = (struct miscdevice){ .parent = dev, @@ -152,6 +151,7 @@ static int __init open_dice_probe(struct platform_device *pdev) .mode = 0600, }, }; + mutex_init(&drvdata->lock); /* Index overflow check not needed, misc_register() will fail. */ snprintf(drvdata->name, sizeof(drvdata->name), DRIVER_NAME"%u", dev_idx++); diff --git a/drivers/misc/vmw_vmci/vmci_datagram.c b/drivers/misc/vmw_vmci/vmci_datagram.c index f50d22882476f943fbf7ac2c7d15c82379dd126e..a0ad1f3a69f7e9018a746b96e30586e4580e423f 100644 --- a/drivers/misc/vmw_vmci/vmci_datagram.c +++ b/drivers/misc/vmw_vmci/vmci_datagram.c @@ -234,7 +234,8 @@ static int dg_dispatch_as_host(u32 context_id, struct vmci_datagram *dg) dg_info->in_dg_host_queue = true; dg_info->entry = dst_entry; - memcpy(&dg_info->msg, dg, dg_size); + dg_info->msg = *dg; + memcpy(&dg_info->msg_payload, dg + 1, dg->payload_size); INIT_WORK(&dg_info->work, dg_delayed_dispatch); schedule_work(&dg_info->work); @@ -377,7 +378,8 @@ int vmci_datagram_invoke_guest_handler(struct vmci_datagram *dg) dg_info->in_dg_host_queue = false; dg_info->entry = dst_entry; - memcpy(&dg_info->msg, dg, VMCI_DG_SIZE(dg)); + dg_info->msg = *dg; + memcpy(&dg_info->msg_payload, dg + 1, dg->payload_size); INIT_WORK(&dg_info->work, dg_delayed_dispatch); schedule_work(&dg_info->work); diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 68c12d19870cecde5a639d62d06b9d3733474281..703873692f597805831f78206fd4e690d211dd0e 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -422,7 +422,7 @@ static struct mmc_blk_ioc_data *mmc_blk_ioctl_copy_from_user( struct mmc_blk_ioc_data *idata; int err; - idata = kmalloc(sizeof(*idata), GFP_KERNEL); + idata = kzalloc(sizeof(*idata), GFP_KERNEL); if (!idata) { err = -ENOMEM; goto out; @@ -497,7 +497,7 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, if (idata->flags & MMC_BLK_IOC_DROP) return 0; - if (idata->flags & MMC_BLK_IOC_SBC) + if (idata->flags & MMC_BLK_IOC_SBC && i > 0) prev_idata = idatas[i - 1]; /* @@ -896,10 +896,11 @@ static const struct block_device_operations mmc_bdops = { static int mmc_blk_part_switch_pre(struct mmc_card *card, unsigned int part_type) { - const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_RPMB; + const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_MASK; + const unsigned int rpmb = EXT_CSD_PART_CONFIG_ACC_RPMB; int ret = 0; - if ((part_type & mask) == mask) { + if ((part_type & mask) == rpmb) { if (card->ext_csd.cmdq_en) { ret = mmc_cmdq_disable(card); if (ret) @@ -914,10 +915,11 @@ static int mmc_blk_part_switch_pre(struct mmc_card *card, static int mmc_blk_part_switch_post(struct mmc_card *card, unsigned int part_type) { - const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_RPMB; + const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_MASK; + const unsigned int rpmb = EXT_CSD_PART_CONFIG_ACC_RPMB; int ret = 0; - if ((part_type & mask) == mask) { + if ((part_type & mask) == rpmb) { mmc_retune_unpause(card->host); if (card->reenable_cmdq && !card->ext_csd.cmdq_en) ret = mmc_cmdq_enable(card); diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index a46ce0868fe1f92bbb4edcde0fb81ab2077f5336..7e39017e440fb2275ed95e6b9aaff197884122d3 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1007,10 +1007,12 @@ static int mmc_select_bus_width(struct mmc_card *card) static unsigned ext_csd_bits[] = { EXT_CSD_BUS_WIDTH_8, EXT_CSD_BUS_WIDTH_4, + EXT_CSD_BUS_WIDTH_1, }; static unsigned bus_widths[] = { MMC_BUS_WIDTH_8, MMC_BUS_WIDTH_4, + MMC_BUS_WIDTH_1, }; struct mmc_host *host = card->host; unsigned idx, bus_width = 0; @@ -1817,8 +1819,13 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr, if (err) goto free_card; - - } else if (!mmc_card_hs400es(card)) { + } else if (mmc_card_hs400es(card)) { + if (host->ops->execute_hs400_tuning) { + err = host->ops->execute_hs400_tuning(host, card); + if (err) + goto free_card; + } + } else { /* Select the desired bus width optionally */ err = mmc_select_bus_width(card); if (err > 0 && mmc_card_hs(card)) { diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c index dd2a4b6ab6adb825b5e4f80232cb3707e1ae4103..e3c69c6b85a6c2e8514fbaf4ba4baf372b805aba 100644 --- a/drivers/mmc/core/slot-gpio.c +++ b/drivers/mmc/core/slot-gpio.c @@ -62,11 +62,15 @@ int mmc_gpio_alloc(struct mmc_host *host) int mmc_gpio_get_ro(struct mmc_host *host) { struct mmc_gpio *ctx = host->slot.handler_priv; + int cansleep; if (!ctx || !ctx->ro_gpio) return -ENOSYS; - return gpiod_get_value_cansleep(ctx->ro_gpio); + cansleep = gpiod_cansleep(ctx->ro_gpio); + return cansleep ? + gpiod_get_value_cansleep(ctx->ro_gpio) : + gpiod_get_value(ctx->ro_gpio); } EXPORT_SYMBOL(mmc_gpio_get_ro); diff --git a/drivers/mmc/host/mmci_stm32_sdmmc.c b/drivers/mmc/host/mmci_stm32_sdmmc.c index 60bca78a72b19f7ccea58c09e87c10c909eac0a6..0511583ffa76490cfe85a52febab556b577a3ddf 100644 --- a/drivers/mmc/host/mmci_stm32_sdmmc.c +++ b/drivers/mmc/host/mmci_stm32_sdmmc.c @@ -200,6 +200,8 @@ static int sdmmc_idma_start(struct mmci_host *host, unsigned int *datactrl) struct scatterlist *sg; int i; + host->dma_in_progress = true; + if (!host->variant->dma_lli || data->sg_len == 1 || idma->use_bounce_buffer) { u32 dma_addr; @@ -238,9 +240,30 @@ static int sdmmc_idma_start(struct mmci_host *host, unsigned int *datactrl) return 0; } +static void sdmmc_idma_error(struct mmci_host *host) +{ + struct mmc_data *data = host->data; + struct sdmmc_idma *idma = host->dma_priv; + + if (!dma_inprogress(host)) + return; + + writel_relaxed(0, host->base + MMCI_STM32_IDMACTRLR); + host->dma_in_progress = false; + data->host_cookie = 0; + + if (!idma->use_bounce_buffer) + dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len, + mmc_get_dma_dir(data)); +} + static void sdmmc_idma_finalize(struct mmci_host *host, struct mmc_data *data) { + if (!dma_inprogress(host)) + return; + writel_relaxed(0, host->base + MMCI_STM32_IDMACTRLR); + host->dma_in_progress = false; if (!data->host_cookie) sdmmc_idma_unprep_data(host, data, 0); @@ -567,6 +590,7 @@ static struct mmci_host_ops sdmmc_variant_ops = { .dma_setup = sdmmc_idma_setup, .dma_start = sdmmc_idma_start, .dma_finalize = sdmmc_idma_finalize, + .dma_error = sdmmc_idma_error, .set_clkreg = mmci_sdmmc_set_clkreg, .set_pwrreg = mmci_sdmmc_set_pwrreg, .busy_complete = sdmmc_busy_complete, diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index a5ab2af3e52011ff297c1211cf677f2ff4d02e0d..e37fb25577c0f09cc7bc6fe6e2c7c162dc3513d7 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -2831,6 +2831,11 @@ static __maybe_unused int sdhci_msm_runtime_suspend(struct device *dev) struct sdhci_host *host = dev_get_drvdata(dev); struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host); + unsigned long flags; + + spin_lock_irqsave(&host->lock, flags); + host->runtime_suspended = true; + spin_unlock_irqrestore(&host->lock, flags); /* Drop the performance vote */ dev_pm_opp_set_rate(dev, 0); @@ -2845,6 +2850,7 @@ static __maybe_unused int sdhci_msm_runtime_resume(struct device *dev) struct sdhci_host *host = dev_get_drvdata(dev); struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host); + unsigned long flags; int ret; ret = clk_bulk_prepare_enable(ARRAY_SIZE(msm_host->bulk_clks), @@ -2863,7 +2869,15 @@ static __maybe_unused int sdhci_msm_runtime_resume(struct device *dev) dev_pm_opp_set_rate(dev, msm_host->clk_rate); - return sdhci_msm_ice_resume(msm_host); + ret = sdhci_msm_ice_resume(msm_host); + if (ret) + return ret; + + spin_lock_irqsave(&host->lock, flags); + host->runtime_suspended = false; + spin_unlock_irqrestore(&host->lock, flags); + + return ret; } static const struct dev_pm_ops sdhci_msm_pm_ops = { diff --git a/drivers/mmc/host/sdhci-omap.c b/drivers/mmc/host/sdhci-omap.c index 033be559a730946882a6f954d64b89f7508b8e80..bfb7c8b96341c254fbe51a9b3e31381b2fced232 100644 --- a/drivers/mmc/host/sdhci-omap.c +++ b/drivers/mmc/host/sdhci-omap.c @@ -1442,6 +1442,9 @@ static int __maybe_unused sdhci_omap_runtime_suspend(struct device *dev) struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct sdhci_omap_host *omap_host = sdhci_pltfm_priv(pltfm_host); + if (host->tuning_mode != SDHCI_TUNING_MODE_3) + mmc_retune_needed(host->mmc); + if (omap_host->con != -EINVAL) sdhci_runtime_suspend_host(host); diff --git a/drivers/mmc/host/sdhci-pci-o2micro.c b/drivers/mmc/host/sdhci-pci-o2micro.c index bca1d095b7597dae6df0b2dbb5afbdd667b66d12..24bb0e9809e762abd79ee50e06ea4f6e784e794e 100644 --- a/drivers/mmc/host/sdhci-pci-o2micro.c +++ b/drivers/mmc/host/sdhci-pci-o2micro.c @@ -602,6 +602,35 @@ static void sdhci_pci_o2_set_clock(struct sdhci_host *host, unsigned int clock) sdhci_o2_enable_clk(host, clk); } +static void sdhci_pci_o2_set_power(struct sdhci_host *host, unsigned char mode, unsigned short vdd) +{ + struct sdhci_pci_chip *chip; + struct sdhci_pci_slot *slot = sdhci_priv(host); + u32 scratch_32 = 0; + u8 scratch_8 = 0; + + chip = slot->chip; + + if (mode == MMC_POWER_OFF) { + /* UnLock WP */ + pci_read_config_byte(chip->pdev, O2_SD_LOCK_WP, &scratch_8); + scratch_8 &= 0x7f; + pci_write_config_byte(chip->pdev, O2_SD_LOCK_WP, scratch_8); + + /* Set PCR 0x354[16] to switch Clock Source back to OPE Clock */ + pci_read_config_dword(chip->pdev, O2_SD_OUTPUT_CLK_SOURCE_SWITCH, &scratch_32); + scratch_32 &= ~(O2_SD_SEL_DLL); + pci_write_config_dword(chip->pdev, O2_SD_OUTPUT_CLK_SOURCE_SWITCH, scratch_32); + + /* Lock WP */ + pci_read_config_byte(chip->pdev, O2_SD_LOCK_WP, &scratch_8); + scratch_8 |= 0x80; + pci_write_config_byte(chip->pdev, O2_SD_LOCK_WP, scratch_8); + } + + sdhci_set_power(host, mode, vdd); +} + static int sdhci_pci_o2_probe_slot(struct sdhci_pci_slot *slot) { struct sdhci_pci_chip *chip; @@ -911,6 +940,7 @@ static const struct sdhci_ops sdhci_pci_o2_ops = { .set_bus_width = sdhci_set_bus_width, .reset = sdhci_reset, .set_uhs_signaling = sdhci_set_uhs_signaling, + .set_power = sdhci_pci_o2_set_power, }; const struct sdhci_pci_fixes sdhci_o2 = { diff --git a/drivers/mmc/host/sdhci-xenon-phy.c b/drivers/mmc/host/sdhci-xenon-phy.c index 8cf3a375de659a6d98b7dcfc2f4e2be09f7c4a5d..cc9d28b75eb911733d847a1d0c19cf24d9a3f755 100644 --- a/drivers/mmc/host/sdhci-xenon-phy.c +++ b/drivers/mmc/host/sdhci-xenon-phy.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include "sdhci-pltfm.h" @@ -109,6 +110,8 @@ #define XENON_EMMC_PHY_LOGIC_TIMING_ADJUST (XENON_EMMC_PHY_REG_BASE + 0x18) #define XENON_LOGIC_TIMING_VALUE 0x00AA8977 +#define XENON_MAX_PHY_TIMEOUT_LOOPS 100 + /* * List offset of PHY registers and some special register values * in eMMC PHY 5.0 or eMMC PHY 5.1 @@ -216,6 +219,19 @@ static int xenon_alloc_emmc_phy(struct sdhci_host *host) return 0; } +static int xenon_check_stability_internal_clk(struct sdhci_host *host) +{ + u32 reg; + int err; + + err = read_poll_timeout(sdhci_readw, reg, reg & SDHCI_CLOCK_INT_STABLE, + 1100, 20000, false, host, SDHCI_CLOCK_CONTROL); + if (err) + dev_err(mmc_dev(host->mmc), "phy_init: Internal clock never stabilized.\n"); + + return err; +} + /* * eMMC 5.0/5.1 PHY init/re-init. * eMMC PHY init should be executed after: @@ -232,6 +248,11 @@ static int xenon_emmc_phy_init(struct sdhci_host *host) struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host); struct xenon_emmc_phy_regs *phy_regs = priv->emmc_phy_regs; + int ret = xenon_check_stability_internal_clk(host); + + if (ret) + return ret; + reg = sdhci_readl(host, phy_regs->timing_adj); reg |= XENON_PHY_INITIALIZAION; sdhci_writel(host, reg, phy_regs->timing_adj); @@ -259,18 +280,27 @@ static int xenon_emmc_phy_init(struct sdhci_host *host) /* get the wait time */ wait /= clock; wait++; - /* wait for host eMMC PHY init completes */ - udelay(wait); - reg = sdhci_readl(host, phy_regs->timing_adj); - reg &= XENON_PHY_INITIALIZAION; - if (reg) { + /* + * AC5X spec says bit must be polled until zero. + * We see cases in which timeout can take longer + * than the standard calculation on AC5X, which is + * expected following the spec comment above. + * According to the spec, we must wait as long as + * it takes for that bit to toggle on AC5X. + * Cap that with 100 delay loops so we won't get + * stuck here forever: + */ + + ret = read_poll_timeout(sdhci_readl, reg, + !(reg & XENON_PHY_INITIALIZAION), + wait, XENON_MAX_PHY_TIMEOUT_LOOPS * wait, + false, host, phy_regs->timing_adj); + if (ret) dev_err(mmc_dev(host->mmc), "eMMC PHY init cannot complete after %d us\n", - wait); - return -ETIMEDOUT; - } + wait * XENON_MAX_PHY_TIMEOUT_LOOPS); - return 0; + return ret; } #define ARMADA_3700_SOC_PAD_1_8V 0x1 diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c index 437048bb802736b196389f4d57976c9efe9941e3..5024cae411d3a2bfcf0dc9449da0fe996b900553 100644 --- a/drivers/mmc/host/tmio_mmc_core.c +++ b/drivers/mmc/host/tmio_mmc_core.c @@ -259,6 +259,8 @@ static void tmio_mmc_reset_work(struct work_struct *work) else mrq->cmd->error = -ETIMEDOUT; + /* No new calls yet, but disallow concurrent tmio_mmc_done_work() */ + host->mrq = ERR_PTR(-EBUSY); host->cmd = NULL; host->data = NULL; diff --git a/drivers/mmc/host/wmt-sdmmc.c b/drivers/mmc/host/wmt-sdmmc.c index 9aa3027ca25e495a2499cbdc38b4e658b509fb16..f2abebb2d85740a66ec78a301da61be12a473a7b 100644 --- a/drivers/mmc/host/wmt-sdmmc.c +++ b/drivers/mmc/host/wmt-sdmmc.c @@ -886,7 +886,6 @@ static int wmt_mci_remove(struct platform_device *pdev) { struct mmc_host *mmc; struct wmt_mci_priv *priv; - struct resource *res; u32 reg_tmp; mmc = platform_get_drvdata(pdev); @@ -914,9 +913,6 @@ static int wmt_mci_remove(struct platform_device *pdev) clk_disable_unprepare(priv->clk_sdmmc); clk_put(priv->clk_sdmmc); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - release_mem_region(res->start, resource_size(res)); - mmc_free_host(mmc); dev_info(&pdev->dev, "WMT MCI device removed\n"); diff --git a/drivers/mtd/maps/physmap-core.c b/drivers/mtd/maps/physmap-core.c index 19dad5a23f94454a9cb30172efbcc020e4e5737c..8cdb3512107d317825a929f96c94598b20fc46fc 100644 --- a/drivers/mtd/maps/physmap-core.c +++ b/drivers/mtd/maps/physmap-core.c @@ -524,7 +524,7 @@ static int physmap_flash_probe(struct platform_device *dev) if (!info->maps[i].phys) info->maps[i].phys = res->start; - info->win_order = get_bitmask_order(resource_size(res)) - 1; + info->win_order = fls64(resource_size(res)) - 1; info->maps[i].size = BIT(info->win_order + (info->gpios ? info->gpios->ndescs : 0)); diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c index 5d2ddb037a9a249668208510ecd7d63be69d61b2..2068025d56396ae1def5c25bd5072879210e9832 100644 --- a/drivers/mtd/nand/raw/diskonchip.c +++ b/drivers/mtd/nand/raw/diskonchip.c @@ -53,7 +53,7 @@ static unsigned long doc_locations[] __initdata = { 0xe8000, 0xea000, 0xec000, 0xee000, #endif #endif - 0xffffffff }; +}; static struct mtd_info *doclist = NULL; @@ -1552,7 +1552,7 @@ static int __init init_nanddoc(void) if (ret < 0) return ret; } else { - for (i = 0; (doc_locations[i] != 0xffffffff); i++) { + for (i = 0; i < ARRAY_SIZE(doc_locations); i++) { doc_probe(doc_locations[i]); } } diff --git a/drivers/mtd/nand/raw/lpc32xx_mlc.c b/drivers/mtd/nand/raw/lpc32xx_mlc.c index 452ecaf7775ac85693d02dcb4fa24682c8b0c62f..1cfe3dd0bad4d1e954c18125e6819e5e863ea2a3 100644 --- a/drivers/mtd/nand/raw/lpc32xx_mlc.c +++ b/drivers/mtd/nand/raw/lpc32xx_mlc.c @@ -303,8 +303,9 @@ static int lpc32xx_nand_device_ready(struct nand_chip *nand_chip) return 0; } -static irqreturn_t lpc3xxx_nand_irq(int irq, struct lpc32xx_nand_host *host) +static irqreturn_t lpc3xxx_nand_irq(int irq, void *data) { + struct lpc32xx_nand_host *host = data; uint8_t sr; /* Clear interrupt flag by reading status */ @@ -779,7 +780,7 @@ static int lpc32xx_nand_probe(struct platform_device *pdev) goto release_dma_chan; } - if (request_irq(host->irq, (irq_handler_t)&lpc3xxx_nand_irq, + if (request_irq(host->irq, &lpc3xxx_nand_irq, IRQF_TRIGGER_HIGH, DRV_NAME, host)) { dev_err(&pdev->dev, "Error requesting NAND IRQ\n"); res = -ENXIO; diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c index 0aeac8ccbd0eee5c250f52d29f5a0f272fac3050..05925fb6946022411b5d31478f533b99ea2f8570 100644 --- a/drivers/mtd/nand/raw/meson_nand.c +++ b/drivers/mtd/nand/raw/meson_nand.c @@ -63,7 +63,7 @@ #define CMDRWGEN(cmd_dir, ran, bch, short_mode, page_size, pages) \ ( \ (cmd_dir) | \ - ((ran) << 19) | \ + (ran) | \ ((bch) << 14) | \ ((short_mode) << 13) | \ (((page_size) & 0x7f) << 6) | \ diff --git a/drivers/mtd/nand/spi/gigadevice.c b/drivers/mtd/nand/spi/gigadevice.c index 6b043e24855fb1b557d44a01ceb5b163d115b78d..9116ee7f023ed7407f7facea83db62c937e895c5 100644 --- a/drivers/mtd/nand/spi/gigadevice.c +++ b/drivers/mtd/nand/spi/gigadevice.c @@ -186,7 +186,7 @@ static int gd5fxgq4uexxg_ecc_get_status(struct spinand_device *spinand, { u8 status2; struct spi_mem_op op = SPINAND_GET_FEATURE_OP(GD5FXGQXXEXXG_REG_STATUS2, - &status2); + spinand->scratchbuf); int ret; switch (status & STATUS_ECC_MASK) { @@ -207,6 +207,7 @@ static int gd5fxgq4uexxg_ecc_get_status(struct spinand_device *spinand, * report the maximum of 4 in this case */ /* bits sorted this way (3...0): ECCS1,ECCS0,ECCSE1,ECCSE0 */ + status2 = *(spinand->scratchbuf); return ((status & STATUS_ECC_MASK) >> 2) | ((status2 & STATUS_ECC_MASK) >> 4); @@ -228,7 +229,7 @@ static int gd5fxgq5xexxg_ecc_get_status(struct spinand_device *spinand, { u8 status2; struct spi_mem_op op = SPINAND_GET_FEATURE_OP(GD5FXGQXXEXXG_REG_STATUS2, - &status2); + spinand->scratchbuf); int ret; switch (status & STATUS_ECC_MASK) { @@ -248,6 +249,7 @@ static int gd5fxgq5xexxg_ecc_get_status(struct spinand_device *spinand, * 1 ... 4 bits are flipped (and corrected) */ /* bits sorted this way (1...0): ECCSE1, ECCSE0 */ + status2 = *(spinand->scratchbuf); return ((status2 & STATUS_ECC_MASK) >> 4) + 1; case STATUS_ECC_UNCOR_ERROR: diff --git a/drivers/mtd/parsers/ofpart_core.c b/drivers/mtd/parsers/ofpart_core.c index 192190c42fc84d3f8c8ba72465fa3c44bf5243e7..e7b8e9d0a910339a72bd243c7d74f3c41b2f6713 100644 --- a/drivers/mtd/parsers/ofpart_core.c +++ b/drivers/mtd/parsers/ofpart_core.c @@ -122,6 +122,25 @@ static int parse_fixed_partitions(struct mtd_info *master, a_cells = of_n_addr_cells(pp); s_cells = of_n_size_cells(pp); + if (!dedicated && s_cells == 0) { + /* + * This is a ugly workaround to not create + * regression on devices that are still creating + * partitions as direct children of the nand controller. + * This can happen in case the nand controller node has + * #size-cells equal to 0 and the firmware (e.g. + * U-Boot) just add the partitions there assuming + * 32-bit addressing. + * + * If you get this warning your firmware and/or DTS + * should be really fixed. + * + * This is working only for devices smaller than 4GiB. + */ + pr_warn("%s: ofpart partition %pOF (%pOF) #size-cells is wrongly set to <0>, assuming <1> for parsing partitions.\n", + master->name, pp, mtd_node); + s_cells = 1; + } if (len / 4 != a_cells + s_cells) { pr_debug("%s: ofpart partition %pOF (%pOF) error parsing reg property.\n", master->name, pp, diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c index ca2d9efe62c3c75063b41ecacb6cbbd6f107146d..1060e19205d2af103ebcd91c7fdac5a3ddd800ee 100644 --- a/drivers/mtd/ubi/fastmap.c +++ b/drivers/mtd/ubi/fastmap.c @@ -85,9 +85,10 @@ size_t ubi_calc_fm_size(struct ubi_device *ubi) sizeof(struct ubi_fm_scan_pool) + sizeof(struct ubi_fm_scan_pool) + (ubi->peb_count * sizeof(struct ubi_fm_ec)) + - (sizeof(struct ubi_fm_eba) + - (ubi->peb_count * sizeof(__be32))) + - sizeof(struct ubi_fm_volhdr) * UBI_MAX_VOLUMES; + ((sizeof(struct ubi_fm_eba) + + sizeof(struct ubi_fm_volhdr)) * + (UBI_MAX_VOLUMES + UBI_INT_VOL_COUNT)) + + (ubi->peb_count * sizeof(__be32)); return roundup(size, ubi->leb_size); } diff --git a/drivers/mtd/ubi/vtbl.c b/drivers/mtd/ubi/vtbl.c index f700f0e4f2ec4d7c700a2428fd83e54129992c24..6e5489e233dd2afadc99e150ac9476ec622c38d3 100644 --- a/drivers/mtd/ubi/vtbl.c +++ b/drivers/mtd/ubi/vtbl.c @@ -791,6 +791,12 @@ int ubi_read_volume_table(struct ubi_device *ubi, struct ubi_attach_info *ai) * The number of supported volumes is limited by the eraseblock size * and by the UBI_MAX_VOLUMES constant. */ + + if (ubi->leb_size < UBI_VTBL_RECORD_SIZE) { + ubi_err(ubi, "LEB size too small for a volume record"); + return -EINVAL; + } + ubi->vtbl_slots = ubi->leb_size / UBI_VTBL_RECORD_SIZE; if (ubi->vtbl_slots > UBI_MAX_VOLUMES) ubi->vtbl_slots = UBI_MAX_VOLUMES; diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index 8efa22d9f214d2f8b05b6726f22de26633687dd9..053d375eae4f53e7d4b0cc7d987a9e3c02f4d2f9 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -311,7 +311,7 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], /* Neither of TDC parameters nor TDC flags are * provided: do calculation */ - can_calc_tdco(&priv->tdc, priv->tdc_const, &priv->data_bittiming, + can_calc_tdco(&priv->tdc, priv->tdc_const, &dbt, &priv->ctrlmode, priv->ctrlmode_supported); } /* else: both CAN_CTRLMODE_TDC_{AUTO,MANUAL} are explicitly * turned off. TDC is disabled: do nothing diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index c63e082dc57dc7258af4a586a7909271a2e8ab26..934600eccbaf2359736902ec4adc416fb63a9dd2 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -49,9 +49,9 @@ static int ksz8_ind_write8(struct ksz_device *dev, u8 table, u16 addr, u8 data) mutex_lock(&dev->alu_mutex); ctrl_addr = IND_ACC_TABLE(table) | addr; - ret = ksz_write8(dev, regs[REG_IND_BYTE], data); + ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr); if (!ret) - ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr); + ret = ksz_write8(dev, regs[REG_IND_BYTE], data); mutex_unlock(&dev->alu_mutex); diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index b988c8a40d536731fddad0291a76fa8676401189..1aba0cf38630ffc4af3354156f8d899058a94d33 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -419,6 +419,20 @@ static void mt7530_pll_setup(struct mt7530_priv *priv) core_set(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN); } +/* If port 6 is available as a CPU port, always prefer that as the default, + * otherwise don't care. + */ +static struct dsa_port * +mt753x_preferred_default_local_cpu_port(struct dsa_switch *ds) +{ + struct dsa_port *cpu_dp = dsa_to_port(ds, 6); + + if (dsa_port_is_cpu(cpu_dp)) + return cpu_dp; + + return NULL; +} + /* Setup port 6 interface mode and TRGMII TX circuit */ static int mt7530_pad_clk_setup(struct dsa_switch *ds, phy_interface_t interface) @@ -998,20 +1012,217 @@ unlock_exit: mutex_unlock(&priv->reg_mutex); } +/* In Clause 5 of IEEE Std 802-2014, two sublayers of the data link layer (DLL) + * of the Open Systems Interconnection basic reference model (OSI/RM) are + * described; the medium access control (MAC) and logical link control (LLC) + * sublayers. The MAC sublayer is the one facing the physical layer. + * + * In 8.2 of IEEE Std 802.1Q-2022, the Bridge architecture is described. A + * Bridge component comprises a MAC Relay Entity for interconnecting the Ports + * of the Bridge, at least two Ports, and higher layer entities with at least a + * Spanning Tree Protocol Entity included. + * + * Each Bridge Port also functions as an end station and shall provide the MAC + * Service to an LLC Entity. Each instance of the MAC Service is provided to a + * distinct LLC Entity that supports protocol identification, multiplexing, and + * demultiplexing, for protocol data unit (PDU) transmission and reception by + * one or more higher layer entities. + * + * It is described in 8.13.9 of IEEE Std 802.1Q-2022 that in a Bridge, the LLC + * Entity associated with each Bridge Port is modeled as being directly + * connected to the attached Local Area Network (LAN). + * + * On the switch with CPU port architecture, CPU port functions as Management + * Port, and the Management Port functionality is provided by software which + * functions as an end station. Software is connected to an IEEE 802 LAN that is + * wholly contained within the system that incorporates the Bridge. Software + * provides access to the LLC Entity associated with each Bridge Port by the + * value of the source port field on the special tag on the frame received by + * software. + * + * We call frames that carry control information to determine the active + * topology and current extent of each Virtual Local Area Network (VLAN), i.e., + * spanning tree or Shortest Path Bridging (SPB) and Multiple VLAN Registration + * Protocol Data Units (MVRPDUs), and frames from other link constrained + * protocols, such as Extensible Authentication Protocol over LAN (EAPOL) and + * Link Layer Discovery Protocol (LLDP), link-local frames. They are not + * forwarded by a Bridge. Permanently configured entries in the filtering + * database (FDB) ensure that such frames are discarded by the Forwarding + * Process. In 8.6.3 of IEEE Std 802.1Q-2022, this is described in detail: + * + * Each of the reserved MAC addresses specified in Table 8-1 + * (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]) shall be + * permanently configured in the FDB in C-VLAN components and ERs. + * + * Each of the reserved MAC addresses specified in Table 8-2 + * (01-80-C2-00-00-[01,02,03,04,05,06,07,08,09,0A,0E]) shall be permanently + * configured in the FDB in S-VLAN components. + * + * Each of the reserved MAC addresses specified in Table 8-3 + * (01-80-C2-00-00-[01,02,04,0E]) shall be permanently configured in the FDB in + * TPMR components. + * + * The FDB entries for reserved MAC addresses shall specify filtering for all + * Bridge Ports and all VIDs. Management shall not provide the capability to + * modify or remove entries for reserved MAC addresses. + * + * The addresses in Table 8-1, Table 8-2, and Table 8-3 determine the scope of + * propagation of PDUs within a Bridged Network, as follows: + * + * The Nearest Bridge group address (01-80-C2-00-00-0E) is an address that no + * conformant Two-Port MAC Relay (TPMR) component, Service VLAN (S-VLAN) + * component, Customer VLAN (C-VLAN) component, or MAC Bridge can forward. + * PDUs transmitted using this destination address, or any other addresses + * that appear in Table 8-1, Table 8-2, and Table 8-3 + * (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]), can + * therefore travel no further than those stations that can be reached via a + * single individual LAN from the originating station. + * + * The Nearest non-TPMR Bridge group address (01-80-C2-00-00-03), is an + * address that no conformant S-VLAN component, C-VLAN component, or MAC + * Bridge can forward; however, this address is relayed by a TPMR component. + * PDUs using this destination address, or any of the other addresses that + * appear in both Table 8-1 and Table 8-2 but not in Table 8-3 + * (01-80-C2-00-00-[00,03,05,06,07,08,09,0A,0B,0C,0D,0F]), will be relayed by + * any TPMRs but will propagate no further than the nearest S-VLAN component, + * C-VLAN component, or MAC Bridge. + * + * The Nearest Customer Bridge group address (01-80-C2-00-00-00) is an address + * that no conformant C-VLAN component, MAC Bridge can forward; however, it is + * relayed by TPMR components and S-VLAN components. PDUs using this + * destination address, or any of the other addresses that appear in Table 8-1 + * but not in either Table 8-2 or Table 8-3 (01-80-C2-00-00-[00,0B,0C,0D,0F]), + * will be relayed by TPMR components and S-VLAN components but will propagate + * no further than the nearest C-VLAN component or MAC Bridge. + * + * Because the LLC Entity associated with each Bridge Port is provided via CPU + * port, we must not filter these frames but forward them to CPU port. + * + * In a Bridge, the transmission Port is majorly decided by ingress and egress + * rules, FDB, and spanning tree Port State functions of the Forwarding Process. + * For link-local frames, only CPU port should be designated as destination port + * in the FDB, and the other functions of the Forwarding Process must not + * interfere with the decision of the transmission Port. We call this process + * trapping frames to CPU port. + * + * Therefore, on the switch with CPU port architecture, link-local frames must + * be trapped to CPU port, and certain link-local frames received by a Port of a + * Bridge comprising a TPMR component or an S-VLAN component must be excluded + * from it. + * + * A Bridge of the switch with CPU port architecture cannot comprise a Two-Port + * MAC Relay (TPMR) component as a TPMR component supports only a subset of the + * functionality of a MAC Bridge. A Bridge comprising two Ports (Management Port + * doesn't count) of this architecture will either function as a standard MAC + * Bridge or a standard VLAN Bridge. + * + * Therefore, a Bridge of this architecture can only comprise S-VLAN components, + * C-VLAN components, or MAC Bridge components. Since there's no TPMR component, + * we don't need to relay PDUs using the destination addresses specified on the + * Nearest non-TPMR section, and the proportion of the Nearest Customer Bridge + * section where they must be relayed by TPMR components. + * + * One option to trap link-local frames to CPU port is to add static FDB entries + * with CPU port designated as destination port. However, because that + * Independent VLAN Learning (IVL) is being used on every VID, each entry only + * applies to a single VLAN Identifier (VID). For a Bridge comprising a MAC + * Bridge component or a C-VLAN component, there would have to be 16 times 4096 + * entries. This switch intellectual property can only hold a maximum of 2048 + * entries. Using this option, there also isn't a mechanism to prevent + * link-local frames from being discarded when the spanning tree Port State of + * the reception Port is discarding. + * + * The remaining option is to utilise the BPC, RGAC1, RGAC2, RGAC3, and RGAC4 + * registers. Whilst this applies to every VID, it doesn't contain all of the + * reserved MAC addresses without affecting the remaining Standard Group MAC + * Addresses. The REV_UN frame tag utilised using the RGAC4 register covers the + * remaining 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F] destination + * addresses. It also includes the 01-80-C2-00-00-22 to 01-80-C2-00-00-FF + * destination addresses which may be relayed by MAC Bridges or VLAN Bridges. + * The latter option provides better but not complete conformance. + * + * This switch intellectual property also does not provide a mechanism to trap + * link-local frames with specific destination addresses to CPU port by Bridge, + * to conform to the filtering rules for the distinct Bridge components. + * + * Therefore, regardless of the type of the Bridge component, link-local frames + * with these destination addresses will be trapped to CPU port: + * + * 01-80-C2-00-00-[00,01,02,03,0E] + * + * In a Bridge comprising a MAC Bridge component or a C-VLAN component: + * + * Link-local frames with these destination addresses won't be trapped to CPU + * port which won't conform to IEEE Std 802.1Q-2022: + * + * 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F] + * + * In a Bridge comprising an S-VLAN component: + * + * Link-local frames with these destination addresses will be trapped to CPU + * port which won't conform to IEEE Std 802.1Q-2022: + * + * 01-80-C2-00-00-00 + * + * Link-local frames with these destination addresses won't be trapped to CPU + * port which won't conform to IEEE Std 802.1Q-2022: + * + * 01-80-C2-00-00-[04,05,06,07,08,09,0A] + * + * To trap link-local frames to CPU port as conformant as this switch + * intellectual property can allow, link-local frames are made to be regarded as + * Bridge Protocol Data Units (BPDUs). This is because this switch intellectual + * property only lets the frames regarded as BPDUs bypass the spanning tree Port + * State function of the Forwarding Process. + * + * The only remaining interference is the ingress rules. When the reception Port + * has no PVID assigned on software, VLAN-untagged frames won't be allowed in. + * There doesn't seem to be a mechanism on the switch intellectual property to + * have link-local frames bypass this function of the Forwarding Process. + */ static void mt753x_trap_frames(struct mt7530_priv *priv) { - /* Trap BPDUs to the CPU port(s) */ - mt7530_rmw(priv, MT753X_BPC, MT753X_BPDU_PORT_FW_MASK, - MT753X_BPDU_CPU_ONLY); - - /* Trap 802.1X PAE frames to the CPU port(s) */ - mt7530_rmw(priv, MT753X_BPC, MT753X_PAE_PORT_FW_MASK, - MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY)); - - /* Trap LLDP frames with :0E MAC DA to the CPU port(s) */ - mt7530_rmw(priv, MT753X_RGAC2, MT753X_R0E_PORT_FW_MASK, - MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY)); + /* Trap 802.1X PAE frames and BPDUs to the CPU port(s) and egress them + * VLAN-untagged. + */ + mt7530_rmw(priv, MT753X_BPC, + MT753X_PAE_BPDU_FR | MT753X_PAE_EG_TAG_MASK | + MT753X_PAE_PORT_FW_MASK | MT753X_BPDU_EG_TAG_MASK | + MT753X_BPDU_PORT_FW_MASK, + MT753X_PAE_BPDU_FR | + MT753X_PAE_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY) | + MT753X_BPDU_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_BPDU_CPU_ONLY); + + /* Trap frames with :01 and :02 MAC DAs to the CPU port(s) and egress + * them VLAN-untagged. + */ + mt7530_rmw(priv, MT753X_RGAC1, + MT753X_R02_BPDU_FR | MT753X_R02_EG_TAG_MASK | + MT753X_R02_PORT_FW_MASK | MT753X_R01_BPDU_FR | + MT753X_R01_EG_TAG_MASK | MT753X_R01_PORT_FW_MASK, + MT753X_R02_BPDU_FR | + MT753X_R02_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_R02_PORT_FW(MT753X_BPDU_CPU_ONLY) | + MT753X_R01_BPDU_FR | + MT753X_R01_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_BPDU_CPU_ONLY); + + /* Trap frames with :03 and :0E MAC DAs to the CPU port(s) and egress + * them VLAN-untagged. + */ + mt7530_rmw(priv, MT753X_RGAC2, + MT753X_R0E_BPDU_FR | MT753X_R0E_EG_TAG_MASK | + MT753X_R0E_PORT_FW_MASK | MT753X_R03_BPDU_FR | + MT753X_R03_EG_TAG_MASK | MT753X_R03_PORT_FW_MASK, + MT753X_R0E_BPDU_FR | + MT753X_R0E_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY) | + MT753X_R03_BPDU_FR | + MT753X_R03_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_BPDU_CPU_ONLY); } static int @@ -1039,6 +1250,13 @@ mt753x_cpu_port_enable(struct dsa_switch *ds, int port) if (priv->id == ID_MT7530 || priv->id == ID_MT7621) mt7530_rmw(priv, MT7530_MFC, CPU_MASK, CPU_EN | CPU_PORT(port)); + /* Add the CPU port to the CPU port bitmap for MT7531. Trapped frames + * will be forwarded to the CPU port that is affine to the inbound user + * port. + */ + if (priv->id == ID_MT7531) + mt7530_set(priv, MT7531_CFC, MT7531_CPU_PMAP(BIT(port))); + /* CPU port gets connected to all user ports of * the switch. */ @@ -2187,11 +2405,11 @@ mt7530_setup(struct dsa_switch *ds) */ if (priv->mcm) { reset_control_assert(priv->rstc); - usleep_range(1000, 1100); + usleep_range(5000, 5100); reset_control_deassert(priv->rstc); } else { gpiod_set_value_cansleep(priv->reset, 0); - usleep_range(1000, 1100); + usleep_range(5000, 5100); gpiod_set_value_cansleep(priv->reset, 1); } @@ -2216,8 +2434,6 @@ mt7530_setup(struct dsa_switch *ds) SYS_CTRL_PHY_RST | SYS_CTRL_SW_RST | SYS_CTRL_REG_RST); - mt7530_pll_setup(priv); - /* Lower Tx driving for TRGMII path */ for (i = 0; i < NUM_TRGMII_CTRL; i++) mt7530_write(priv, MT7530_TRGMII_TD_ODT(i), @@ -2235,6 +2451,9 @@ mt7530_setup(struct dsa_switch *ds) priv->p6_interface = PHY_INTERFACE_MODE_NA; + if ((val & HWTRAP_XTAL_MASK) == HWTRAP_XTAL_40MHZ) + mt7530_pll_setup(priv); + mt753x_trap_frames(priv); /* Enable and reset MIB counters */ @@ -2264,6 +2483,9 @@ mt7530_setup(struct dsa_switch *ds) PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT)); } + /* Allow mirroring frames received on the local port (monitor port). */ + mt7530_set(priv, MT753X_AGC, LOCAL_EN); + /* Setup VLAN ID 0 for VLAN-unaware bridges */ ret = mt7530_setup_vlan0(priv); if (ret) @@ -2334,16 +2556,8 @@ static int mt7531_setup_common(struct dsa_switch *ds) { struct mt7530_priv *priv = ds->priv; - struct dsa_port *cpu_dp; int ret, i; - /* BPDU to CPU port */ - dsa_switch_for_each_cpu_port(cpu_dp, ds) { - mt7530_rmw(priv, MT7531_CFC, MT7531_CPU_PMAP_MASK, - BIT(cpu_dp->index)); - break; - } - mt753x_trap_frames(priv); /* Enable and reset MIB counters */ @@ -2380,6 +2594,9 @@ mt7531_setup_common(struct dsa_switch *ds) PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT)); } + /* Allow mirroring frames received on the local port (monitor port). */ + mt7530_set(priv, MT753X_AGC, LOCAL_EN); + /* Flush the FDB table */ ret = mt7530_fdb_cmd(priv, MT7530_FDB_FLUSH, NULL); if (ret < 0) @@ -2401,11 +2618,11 @@ mt7531_setup(struct dsa_switch *ds) */ if (priv->mcm) { reset_control_assert(priv->rstc); - usleep_range(1000, 1100); + usleep_range(5000, 5100); reset_control_deassert(priv->rstc); } else { gpiod_set_value_cansleep(priv->reset, 0); - usleep_range(1000, 1100); + usleep_range(5000, 5100); gpiod_set_value_cansleep(priv->reset, 1); } @@ -2458,18 +2675,25 @@ mt7531_setup(struct dsa_switch *ds) priv->p5_interface = PHY_INTERFACE_MODE_NA; priv->p6_interface = PHY_INTERFACE_MODE_NA; - /* Enable PHY core PLL, since phy_device has not yet been created - * provided for phy_[read,write]_mmd_indirect is called, we provide - * our own mt7531_ind_mmd_phy_[read,write] to complete this - * function. + /* Enable Energy-Efficient Ethernet (EEE) and PHY core PLL, since + * phy_device has not yet been created provided for + * phy_[read,write]_mmd_indirect is called, we provide our own + * mt7531_ind_mmd_phy_[read,write] to complete this function. */ val = mt7531_ind_c45_phy_read(priv, MT753X_CTRL_PHY_ADDR, MDIO_MMD_VEND2, CORE_PLL_GROUP4); - val |= MT7531_PHY_PLL_BYPASS_MODE; + val |= MT7531_RG_SYSPLL_DMY2 | MT7531_PHY_PLL_BYPASS_MODE; val &= ~MT7531_PHY_PLL_OFF; mt7531_ind_c45_phy_write(priv, MT753X_CTRL_PHY_ADDR, MDIO_MMD_VEND2, CORE_PLL_GROUP4, val); + /* Disable EEE advertisement on the switch PHYs. */ + for (i = MT753X_CTRL_PHY_ADDR; + i < MT753X_CTRL_PHY_ADDR + MT7530_NUM_PHYS; i++) { + mt7531_ind_c45_phy_write(priv, i, MDIO_MMD_AN, MDIO_AN_EEE_ADV, + 0); + } + mt7531_setup_common(ds); /* Setup VLAN ID 0 for VLAN-unaware bridges */ @@ -3203,6 +3427,7 @@ static int mt753x_set_mac_eee(struct dsa_switch *ds, int port, static const struct dsa_switch_ops mt7530_switch_ops = { .get_tag_protocol = mtk_get_tag_protocol, .setup = mt753x_setup, + .preferred_default_local_cpu_port = mt753x_preferred_default_local_cpu_port, .get_strings = mt7530_get_strings, .get_ethtool_stats = mt7530_get_ethtool_stats, .get_sset_count = mt7530_get_sset_count, diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index 6202b0f8c3f349fb894e43214575967760197bd7..6441e8d7f05d9bf12f6715a3a560b7eb6ce977fe 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -31,6 +31,10 @@ enum mt753x_id { #define SYSC_REG_RSTCTRL 0x34 #define RESET_MCM BIT(2) +/* Register for ARL global control */ +#define MT753X_AGC 0xc +#define LOCAL_EN BIT(7) + /* Registers to mac forward control for unknown frames */ #define MT7530_MFC 0x10 #define BC_FFP(x) (((x) & 0xff) << 24) @@ -53,6 +57,7 @@ enum mt753x_id { #define MT7531_MIRROR_PORT_GET(x) (((x) >> 16) & MIRROR_MASK) #define MT7531_MIRROR_PORT_SET(x) (((x) & MIRROR_MASK) << 16) #define MT7531_CPU_PMAP_MASK GENMASK(7, 0) +#define MT7531_CPU_PMAP(x) FIELD_PREP(MT7531_CPU_PMAP_MASK, x) #define MT753X_MIRROR_REG(id) (((id) == ID_MT7531) ? \ MT7531_CFC : MT7530_MFC) @@ -63,14 +68,38 @@ enum mt753x_id { /* Registers for BPDU and PAE frame control*/ #define MT753X_BPC 0x24 -#define MT753X_BPDU_PORT_FW_MASK GENMASK(2, 0) +#define MT753X_PAE_BPDU_FR BIT(25) +#define MT753X_PAE_EG_TAG_MASK GENMASK(24, 22) +#define MT753X_PAE_EG_TAG(x) FIELD_PREP(MT753X_PAE_EG_TAG_MASK, x) #define MT753X_PAE_PORT_FW_MASK GENMASK(18, 16) #define MT753X_PAE_PORT_FW(x) FIELD_PREP(MT753X_PAE_PORT_FW_MASK, x) +#define MT753X_BPDU_EG_TAG_MASK GENMASK(8, 6) +#define MT753X_BPDU_EG_TAG(x) FIELD_PREP(MT753X_BPDU_EG_TAG_MASK, x) +#define MT753X_BPDU_PORT_FW_MASK GENMASK(2, 0) + +/* Register for :01 and :02 MAC DA frame control */ +#define MT753X_RGAC1 0x28 +#define MT753X_R02_BPDU_FR BIT(25) +#define MT753X_R02_EG_TAG_MASK GENMASK(24, 22) +#define MT753X_R02_EG_TAG(x) FIELD_PREP(MT753X_R02_EG_TAG_MASK, x) +#define MT753X_R02_PORT_FW_MASK GENMASK(18, 16) +#define MT753X_R02_PORT_FW(x) FIELD_PREP(MT753X_R02_PORT_FW_MASK, x) +#define MT753X_R01_BPDU_FR BIT(9) +#define MT753X_R01_EG_TAG_MASK GENMASK(8, 6) +#define MT753X_R01_EG_TAG(x) FIELD_PREP(MT753X_R01_EG_TAG_MASK, x) +#define MT753X_R01_PORT_FW_MASK GENMASK(2, 0) /* Register for :03 and :0E MAC DA frame control */ #define MT753X_RGAC2 0x2c +#define MT753X_R0E_BPDU_FR BIT(25) +#define MT753X_R0E_EG_TAG_MASK GENMASK(24, 22) +#define MT753X_R0E_EG_TAG(x) FIELD_PREP(MT753X_R0E_EG_TAG_MASK, x) #define MT753X_R0E_PORT_FW_MASK GENMASK(18, 16) #define MT753X_R0E_PORT_FW(x) FIELD_PREP(MT753X_R0E_PORT_FW_MASK, x) +#define MT753X_R03_BPDU_FR BIT(9) +#define MT753X_R03_EG_TAG_MASK GENMASK(8, 6) +#define MT753X_R03_EG_TAG(x) FIELD_PREP(MT753X_R03_EG_TAG_MASK, x) +#define MT753X_R03_PORT_FW_MASK GENMASK(2, 0) enum mt753x_bpdu_port_fw { MT753X_BPDU_FOLLOW_MFC, @@ -251,6 +280,7 @@ enum mt7530_port_mode { enum mt7530_vlan_port_eg_tag { MT7530_VLAN_EG_DISABLED = 0, MT7530_VLAN_EG_CONSISTENT = 1, + MT7530_VLAN_EG_UNTAGGED = 4, }; enum mt7530_vlan_port_attr { @@ -643,6 +673,7 @@ enum mt7531_clk_skew { #define RG_SYSPLL_DDSFBK_EN BIT(12) #define RG_SYSPLL_BIAS_EN BIT(11) #define RG_SYSPLL_BIAS_LPF_EN BIT(10) +#define MT7531_RG_SYSPLL_DMY2 BIT(6) #define MT7531_PHY_PLL_OFF BIT(5) #define MT7531_PHY_PLL_BYPASS_MODE BIT(4) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index ba906dfab055cf7dd897b5db0e79f08768d4079b..517c50d11fbceea301d5874aab79383bd6a53eeb 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -5677,7 +5677,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .prod_num = MV88E6XXX_PORT_SWITCH_ID_PROD_6141, .family = MV88E6XXX_FAMILY_6341, .name = "Marvell 88E6141", - .num_databases = 4096, + .num_databases = 256, .num_macs = 2048, .num_ports = 6, .num_internal_phys = 5, @@ -6134,7 +6134,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .prod_num = MV88E6XXX_PORT_SWITCH_ID_PROD_6341, .family = MV88E6XXX_FAMILY_6341, .name = "Marvell 88E6341", - .num_databases = 4096, + .num_databases = 256, .num_macs = 2048, .num_internal_phys = 5, .num_ports = 6, diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index 1917da784191988ea5c0cbc995ec946f647a4b29..5a274b99f2992131505443f461a42f7f59a3bd07 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -84,7 +84,6 @@ source "drivers/net/ethernet/huawei/Kconfig" source "drivers/net/ethernet/i825xx/Kconfig" source "drivers/net/ethernet/ibm/Kconfig" source "drivers/net/ethernet/intel/Kconfig" -source "drivers/net/ethernet/wangxun/Kconfig" source "drivers/net/ethernet/xscale/Kconfig" config JME @@ -189,6 +188,7 @@ source "drivers/net/ethernet/toshiba/Kconfig" source "drivers/net/ethernet/tundra/Kconfig" source "drivers/net/ethernet/vertexcom/Kconfig" source "drivers/net/ethernet/via/Kconfig" +source "drivers/net/ethernet/wangxun/Kconfig" source "drivers/net/ethernet/wiznet/Kconfig" source "drivers/net/ethernet/xilinx/Kconfig" source "drivers/net/ethernet/xircom/Kconfig" diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 633b321d7fdd97c9090ee6d7f6452d952dbc1fd8..4db689372980e6ed59aa720e076d50a7dd9de863 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -362,7 +362,7 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev, ENA_COM_BOUNCE_BUFFER_CNTRL_CNT; io_sq->bounce_buf_ctrl.next_to_use = 0; - size = io_sq->bounce_buf_ctrl.buffer_size * + size = (size_t)io_sq->bounce_buf_ctrl.buffer_size * io_sq->bounce_buf_ctrl.buffers_num; dev_node = dev_to_node(ena_dev->dmadev); diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 044b8afde69a03ea3e56d72a2c41b474d60d9c48..5e37b18ac3adfbff0701ddf14a70e442403cebc3 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -1203,8 +1203,11 @@ static void ena_unmap_tx_buff(struct ena_ring *tx_ring, static void ena_free_tx_bufs(struct ena_ring *tx_ring) { bool print_once = true; + bool is_xdp_ring; u32 i; + is_xdp_ring = ENA_IS_XDP_INDEX(tx_ring->adapter, tx_ring->qid); + for (i = 0; i < tx_ring->ring_size; i++) { struct ena_tx_buffer *tx_info = &tx_ring->tx_buffer_info[i]; @@ -1224,10 +1227,15 @@ static void ena_free_tx_bufs(struct ena_ring *tx_ring) ena_unmap_tx_buff(tx_ring, tx_info); - dev_kfree_skb_any(tx_info->skb); + if (is_xdp_ring) + xdp_return_frame(tx_info->xdpf); + else + dev_kfree_skb_any(tx_info->skb); } - netdev_tx_reset_queue(netdev_get_tx_queue(tx_ring->netdev, - tx_ring->qid)); + + if (!is_xdp_ring) + netdev_tx_reset_queue(netdev_get_tx_queue(tx_ring->netdev, + tx_ring->qid)); } static void ena_free_all_tx_bufs(struct ena_adapter *adapter) @@ -3174,22 +3182,6 @@ error_drop_packet: return NETDEV_TX_OK; } -static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev) -{ - u16 qid; - /* we suspect that this is good for in--kernel network services that - * want to loop incoming skb rx to tx in normal user generated traffic, - * most probably we will not get to this - */ - if (skb_rx_queue_recorded(skb)) - qid = skb_get_rx_queue(skb); - else - qid = netdev_pick_tx(dev, skb, NULL); - - return qid; -} - static void ena_config_host_info(struct ena_com_dev *ena_dev, struct pci_dev *pdev) { struct device *dev = &pdev->dev; @@ -3359,7 +3351,6 @@ static const struct net_device_ops ena_netdev_ops = { .ndo_open = ena_open, .ndo_stop = ena_close, .ndo_start_xmit = ena_start_xmit, - .ndo_select_queue = ena_select_queue, .ndo_get_stats64 = ena_get_stats64, .ndo_tx_timeout = ena_tx_timeout, .ndo_change_mtu = ena_change_mtu, @@ -3814,10 +3805,11 @@ static void check_for_missing_completions(struct ena_adapter *adapter) { struct ena_ring *tx_ring; struct ena_ring *rx_ring; - int i, budget, rc; + int qid, budget, rc; int io_queue_count; io_queue_count = adapter->xdp_num_queues + adapter->num_io_queues; + /* Make sure the driver doesn't turn the device in other process */ smp_rmb(); @@ -3830,27 +3822,29 @@ static void check_for_missing_completions(struct ena_adapter *adapter) if (adapter->missing_tx_completion_to == ENA_HW_HINTS_NO_TIMEOUT) return; - budget = ENA_MONITORED_TX_QUEUES; + budget = min_t(u32, io_queue_count, ENA_MONITORED_TX_QUEUES); - for (i = adapter->last_monitored_tx_qid; i < io_queue_count; i++) { - tx_ring = &adapter->tx_ring[i]; - rx_ring = &adapter->rx_ring[i]; + qid = adapter->last_monitored_tx_qid; + + while (budget) { + qid = (qid + 1) % io_queue_count; + + tx_ring = &adapter->tx_ring[qid]; + rx_ring = &adapter->rx_ring[qid]; rc = check_missing_comp_in_tx_queue(adapter, tx_ring); if (unlikely(rc)) return; - rc = !ENA_IS_XDP_INDEX(adapter, i) ? + rc = !ENA_IS_XDP_INDEX(adapter, qid) ? check_for_rx_interrupt_queue(adapter, rx_ring) : 0; if (unlikely(rc)) return; budget--; - if (!budget) - break; } - adapter->last_monitored_tx_qid = i % io_queue_count; + adapter->last_monitored_tx_qid = qid; } /* trigger napi schedule after 2 consecutive detections */ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c index abd4832e4ed21f3c2a22aed047a0331675162907..5acb3e16b5677b7826e488942ff6efb2c3cdf400 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c @@ -993,7 +993,7 @@ int aq_ptp_ring_alloc(struct aq_nic_s *aq_nic) return 0; err_exit_hwts_rx: - aq_ring_free(&aq_ptp->hwts_rx); + aq_ring_hwts_rx_free(&aq_ptp->hwts_rx); err_exit_ptp_rx: aq_ring_free(&aq_ptp->ptp_rx); err_exit_ptp_tx: @@ -1011,7 +1011,7 @@ void aq_ptp_ring_free(struct aq_nic_s *aq_nic) aq_ring_free(&aq_ptp->ptp_tx); aq_ring_free(&aq_ptp->ptp_rx); - aq_ring_free(&aq_ptp->hwts_rx); + aq_ring_hwts_rx_free(&aq_ptp->hwts_rx); aq_ptp_skb_ring_release(&aq_ptp->skb_ring); } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 9c314fe14ab62072e8d87544072097085f40a4e7..0eaaba3a18ee06225eb12c6082f94dfb782951d5 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -919,6 +919,19 @@ void aq_ring_free(struct aq_ring_s *self) } } +void aq_ring_hwts_rx_free(struct aq_ring_s *self) +{ + if (!self) + return; + + if (self->dx_ring) { + dma_free_coherent(aq_nic_get_dev(self->aq_nic), + self->size * self->dx_size + AQ_CFG_RXDS_DEF, + self->dx_ring, self->dx_ring_pa); + self->dx_ring = NULL; + } +} + unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data) { unsigned int count; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h index 52847310740a21097dfc35a395e96dfe5de46321..d627ace850ff54201b760a079416e4d690e73184 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h @@ -210,6 +210,7 @@ int aq_ring_rx_fill(struct aq_ring_s *self); int aq_ring_hwts_rx_alloc(struct aq_ring_s *self, struct aq_nic_s *aq_nic, unsigned int idx, unsigned int size, unsigned int dx_size); +void aq_ring_hwts_rx_free(struct aq_ring_s *self); void aq_ring_hwts_rx_clean(struct aq_ring_s *self, struct aq_nic_s *aq_nic); unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data); diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index 7f876721596c1a6067301a635ad08eb055b8a65d..5b6209f5a801726fb9fe1adc4af7474b17146f6d 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -2033,12 +2033,14 @@ static int b44_set_pauseparam(struct net_device *dev, bp->flags |= B44_FLAG_TX_PAUSE; else bp->flags &= ~B44_FLAG_TX_PAUSE; - if (bp->flags & B44_FLAG_PAUSE_AUTO) { - b44_halt(bp); - b44_init_rings(bp); - b44_init_hw(bp, B44_FULL_RESET); - } else { - __b44_set_flow_ctrl(bp, bp->flags); + if (netif_running(dev)) { + if (bp->flags & B44_FLAG_PAUSE_AUTO) { + b44_halt(bp); + b44_init_rings(bp); + b44_init_hw(bp, B44_FULL_RESET); + } else { + __b44_set_flow_ctrl(bp, bp->flags); + } } spin_unlock_irq(&bp->lock); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 4950fde82d175a70c6572346a4c5b3e8342a7169..b04c5b51eb598cc5ef6985b2502c7bc88e159bb1 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -147,10 +147,11 @@ void bnx2x_fill_fw_str(struct bnx2x *bp, char *buf, size_t buf_len) phy_fw_ver[0] = '\0'; bnx2x_get_ext_phy_fw_version(&bp->link_params, - phy_fw_ver, PHY_FW_VER_LEN); - strscpy(buf, bp->fw_ver, buf_len); - snprintf(buf + strlen(bp->fw_ver), 32 - strlen(bp->fw_ver), - "bc %d.%d.%d%s%s", + phy_fw_ver, sizeof(phy_fw_ver)); + /* This may become truncated. */ + scnprintf(buf, buf_len, + "%sbc %d.%d.%d%s%s", + bp->fw_ver, (bp->common.bc_ver & 0xff0000) >> 16, (bp->common.bc_ver & 0xff00) >> 8, (bp->common.bc_ver & 0xff), diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index d8b1824c334d3b0d7b515b8f5dd11aa34190a909..0bc1367fd64924b2338cf6c1483f8b80119ee421 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -1002,9 +1002,6 @@ static inline void bnx2x_set_fw_mac_addr(__le16 *fw_hi, __le16 *fw_mid, static inline void bnx2x_free_rx_mem_pool(struct bnx2x *bp, struct bnx2x_alloc_pool *pool) { - if (!pool->page) - return; - put_page(pool->page); pool->page = NULL; @@ -1015,6 +1012,9 @@ static inline void bnx2x_free_rx_sge_range(struct bnx2x *bp, { int i; + if (!fp->page_pool.page) + return; + if (fp->mode == TPA_MODE_DISABLED) return; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index bda3ccc28eca67c9e24ace5c6f094cb4b828a2b1..f920976c36f0c6dfbe35b214c1dfde54161ffabb 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -1132,7 +1132,7 @@ static void bnx2x_get_drvinfo(struct net_device *dev, } memset(version, 0, sizeof(version)); - bnx2x_fill_fw_str(bp, version, ETHTOOL_FWVERS_LEN); + bnx2x_fill_fw_str(bp, version, sizeof(version)); strlcat(info->fw_version, version, sizeof(info->fw_version)); strscpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info)); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index 02808513ffe45b7b09c4fee82e6e79f4849544c8..ea310057fe3aff71a091e1d5627b5f6e3f3b49b0 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -6163,8 +6163,8 @@ static void bnx2x_link_int_ack(struct link_params *params, static int bnx2x_null_format_ver(u32 spirom_ver, u8 *str, u16 *len) { - str[0] = '\0'; - (*len)--; + if (*len) + str[0] = '\0'; return 0; } @@ -6173,7 +6173,7 @@ static int bnx2x_format_ver(u32 num, u8 *str, u16 *len) u16 ret; if (*len < 10) { - /* Need more than 10chars for this format */ + /* Need more than 10 chars for this format */ bnx2x_null_format_ver(num, str, len); return -EINVAL; } @@ -6188,8 +6188,8 @@ static int bnx2x_3_seq_format_ver(u32 num, u8 *str, u16 *len) { u16 ret; - if (*len < 10) { - /* Need more than 10chars for this format */ + if (*len < 9) { + /* Need more than 9 chars for this format */ bnx2x_null_format_ver(num, str, len); return -EINVAL; } @@ -6208,7 +6208,7 @@ int bnx2x_get_ext_phy_fw_version(struct link_params *params, u8 *version, int status = 0; u8 *ver_p = version; u16 remain_len = len; - if (version == NULL || params == NULL) + if (version == NULL || params == NULL || len == 0) return -EINVAL; bp = params->bp; @@ -11546,7 +11546,7 @@ static int bnx2x_7101_format_ver(u32 spirom_ver, u8 *str, u16 *len) str[2] = (spirom_ver & 0xFF0000) >> 16; str[3] = (spirom_ver & 0xFF000000) >> 24; str[4] = '\0'; - *len -= 5; + *len -= 4; return 0; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index f810b5dc25f01e3cad3cbd4a7461971182efb7ea..77ea19bcdc6fe2672c3741dcddf15eefe56a97e3 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1697,7 +1697,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, skb = bnxt_copy_skb(bnapi, data_ptr, len, mapping); if (!skb) { bnxt_abort_tpa(cpr, idx, agg_bufs); - cpr->sw_stats.rx.rx_oom_discards += 1; + cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1; return NULL; } } else { @@ -1707,7 +1707,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, new_data = __bnxt_alloc_rx_frag(bp, &new_mapping, GFP_ATOMIC); if (!new_data) { bnxt_abort_tpa(cpr, idx, agg_bufs); - cpr->sw_stats.rx.rx_oom_discards += 1; + cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1; return NULL; } @@ -1723,7 +1723,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, if (!skb) { skb_free_frag(data); bnxt_abort_tpa(cpr, idx, agg_bufs); - cpr->sw_stats.rx.rx_oom_discards += 1; + cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1; return NULL; } skb_reserve(skb, bp->rx_offset); @@ -1734,7 +1734,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, skb = bnxt_rx_agg_pages_skb(bp, cpr, skb, idx, agg_bufs, true); if (!skb) { /* Page reuse already handled by bnxt_rx_pages(). */ - cpr->sw_stats.rx.rx_oom_discards += 1; + cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1; return NULL; } } @@ -1950,11 +1950,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, u32 frag_len = bnxt_rx_agg_pages_xdp(bp, cpr, &xdp, cp_cons, agg_bufs, false); - if (!frag_len) { - cpr->sw_stats.rx.rx_oom_discards += 1; - rc = -ENOMEM; - goto next_rx; - } + if (!frag_len) + goto oom_next_rx; } xdp_active = true; } @@ -1977,9 +1974,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, else bnxt_xdp_buff_frags_free(rxr, &xdp); } - cpr->sw_stats.rx.rx_oom_discards += 1; - rc = -ENOMEM; - goto next_rx; + goto oom_next_rx; } } else { u32 payload; @@ -1990,29 +1985,21 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, payload = 0; skb = bp->rx_skb_func(bp, rxr, cons, data, data_ptr, dma_addr, payload | len); - if (!skb) { - cpr->sw_stats.rx.rx_oom_discards += 1; - rc = -ENOMEM; - goto next_rx; - } + if (!skb) + goto oom_next_rx; } if (agg_bufs) { if (!xdp_active) { skb = bnxt_rx_agg_pages_skb(bp, cpr, skb, cp_cons, agg_bufs, false); - if (!skb) { - cpr->sw_stats.rx.rx_oom_discards += 1; - rc = -ENOMEM; - goto next_rx; - } + if (!skb) + goto oom_next_rx; } else { skb = bnxt_xdp_build_skb(bp, skb, agg_bufs, rxr->page_pool, &xdp, rxcmp1); if (!skb) { /* we should be able to free the old skb here */ bnxt_xdp_buff_frags_free(rxr, &xdp); - cpr->sw_stats.rx.rx_oom_discards += 1; - rc = -ENOMEM; - goto next_rx; + goto oom_next_rx; } } } @@ -2090,6 +2077,11 @@ next_rx_no_prod_no_len: *raw_cons = tmp_raw_cons; return rc; + +oom_next_rx: + cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1; + rc = -ENOMEM; + goto next_rx; } /* In netpoll mode, if we are using a combined completion ring, we need to @@ -2135,7 +2127,7 @@ static int bnxt_force_rx_discard(struct bnxt *bp, } rc = bnxt_rx_pkt(bp, cpr, raw_cons, event); if (rc && rc != -EBUSY) - cpr->sw_stats.rx.rx_netpoll_discards += 1; + cpr->bnapi->cp_ring.sw_stats.rx.rx_netpoll_discards += 1; return rc; } @@ -10564,6 +10556,8 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) /* VF-reps may need to be re-opened after the PF is re-opened */ if (BNXT_PF(bp)) bnxt_vf_reps_open(bp); + if (bp->ptp_cfg) + atomic_set(&bp->ptp_cfg->tx_avail, BNXT_MAX_TX_TS); bnxt_ptp_init_rtc(bp, true); bnxt_ptp_cfg_tstamp_filters(bp); return 0; @@ -11810,6 +11804,16 @@ static void bnxt_rx_ring_reset(struct bnxt *bp) bnxt_rtnl_unlock_sp(bp); } +static void bnxt_fw_fatal_close(struct bnxt *bp) +{ + bnxt_tx_disable(bp); + bnxt_disable_napi(bp); + bnxt_disable_int_sync(bp); + bnxt_free_irq(bp); + bnxt_clear_int_mode(bp); + pci_disable_device(bp->pdev); +} + static void bnxt_fw_reset_close(struct bnxt *bp) { bnxt_ulp_stop(bp); @@ -11823,12 +11827,7 @@ static void bnxt_fw_reset_close(struct bnxt *bp) pci_read_config_word(bp->pdev, PCI_SUBSYSTEM_ID, &val); if (val == 0xffff) bp->fw_reset_min_dsecs = 0; - bnxt_tx_disable(bp); - bnxt_disable_napi(bp); - bnxt_disable_int_sync(bp); - bnxt_free_irq(bp); - bnxt_clear_int_mode(bp); - pci_disable_device(bp->pdev); + bnxt_fw_fatal_close(bp); } __bnxt_close_nic(bp, true, false); bnxt_vf_reps_free(bp); @@ -13976,6 +13975,7 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev, { struct net_device *netdev = pci_get_drvdata(pdev); struct bnxt *bp = netdev_priv(netdev); + bool abort = false; netdev_info(netdev, "PCI I/O error detected\n"); @@ -13984,16 +13984,27 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev, bnxt_ulp_stop(bp); - if (state == pci_channel_io_perm_failure) { + if (test_and_set_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) { + netdev_err(bp->dev, "Firmware reset already in progress\n"); + abort = true; + } + + if (abort || state == pci_channel_io_perm_failure) { rtnl_unlock(); return PCI_ERS_RESULT_DISCONNECT; } - if (state == pci_channel_io_frozen) + /* Link is not reliable anymore if state is pci_channel_io_frozen + * so we disable bus master to prevent any potential bad DMAs before + * freeing kernel memory. + */ + if (state == pci_channel_io_frozen) { set_bit(BNXT_STATE_PCI_CHANNEL_IO_FROZEN, &bp->state); + bnxt_fw_fatal_close(bp); + } if (netif_running(netdev)) - bnxt_close(netdev); + __bnxt_close_nic(bp, true, true); if (pci_is_enabled(pdev)) pci_disable_device(pdev); @@ -14079,6 +14090,7 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) } reset_exit: + clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); bnxt_clear_reservations(bp, true); rtnl_unlock(); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 79c40c846398900ed872cdee023551cfc0701793..0a8bea6c47555fbdb91bbd4786bc06b564063d0b 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -2,7 +2,7 @@ /* * Broadcom GENET (Gigabit Ethernet) controller driver * - * Copyright (c) 2014-2020 Broadcom + * Copyright (c) 2014-2024 Broadcom */ #define pr_fmt(fmt) "bcmgenet: " fmt @@ -2474,14 +2474,18 @@ static void umac_enable_set(struct bcmgenet_priv *priv, u32 mask, bool enable) { u32 reg; + spin_lock_bh(&priv->reg_lock); reg = bcmgenet_umac_readl(priv, UMAC_CMD); - if (reg & CMD_SW_RESET) + if (reg & CMD_SW_RESET) { + spin_unlock_bh(&priv->reg_lock); return; + } if (enable) reg |= mask; else reg &= ~mask; bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock_bh(&priv->reg_lock); /* UniMAC stops on a packet boundary, wait for a full-size packet * to be processed @@ -2502,8 +2506,10 @@ static void reset_umac(struct bcmgenet_priv *priv) } /* issue soft reset and disable MAC while updating its registers */ + spin_lock_bh(&priv->reg_lock); bcmgenet_umac_writel(priv, CMD_SW_RESET, UMAC_CMD); udelay(2); + spin_unlock_bh(&priv->reg_lock); } static void bcmgenet_intr_disable(struct bcmgenet_priv *priv) @@ -3309,7 +3315,7 @@ static void bcmgenet_get_hw_addr(struct bcmgenet_priv *priv, } /* Returns a reusable dma control register value */ -static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv) +static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv, bool flush_rx) { unsigned int i; u32 reg; @@ -3334,6 +3340,14 @@ static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv) udelay(10); bcmgenet_umac_writel(priv, 0, UMAC_TX_FLUSH); + if (flush_rx) { + reg = bcmgenet_rbuf_ctrl_get(priv); + bcmgenet_rbuf_ctrl_set(priv, reg | BIT(0)); + udelay(10); + bcmgenet_rbuf_ctrl_set(priv, reg); + udelay(10); + } + return dma_ctrl; } @@ -3355,7 +3369,9 @@ static void bcmgenet_netif_start(struct net_device *dev) struct bcmgenet_priv *priv = netdev_priv(dev); /* Start the network engine */ + netif_addr_lock_bh(dev); bcmgenet_set_rx_mode(dev); + netif_addr_unlock_bh(dev); bcmgenet_enable_rx_napi(priv); umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, true); @@ -3397,8 +3413,8 @@ static int bcmgenet_open(struct net_device *dev) bcmgenet_set_hw_addr(priv, dev->dev_addr); - /* Disable RX/TX DMA and flush TX queues */ - dma_ctrl = bcmgenet_dma_disable(priv); + /* Disable RX/TX DMA and flush TX and RX queues */ + dma_ctrl = bcmgenet_dma_disable(priv, true); /* Reinitialize TDMA and RDMA and SW housekeeping */ ret = bcmgenet_init_dma(priv); @@ -3627,16 +3643,19 @@ static void bcmgenet_set_rx_mode(struct net_device *dev) * 3. The number of filters needed exceeds the number filters * supported by the hardware. */ + spin_lock(&priv->reg_lock); reg = bcmgenet_umac_readl(priv, UMAC_CMD); if ((dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) || (nfilter > MAX_MDF_FILTER)) { reg |= CMD_PROMISC; bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock(&priv->reg_lock); bcmgenet_umac_writel(priv, 0, UMAC_MDF_CTRL); return; } else { reg &= ~CMD_PROMISC; bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock(&priv->reg_lock); } /* update MDF filter */ @@ -4038,6 +4057,7 @@ static int bcmgenet_probe(struct platform_device *pdev) goto err; } + spin_lock_init(&priv->reg_lock); spin_lock_init(&priv->lock); /* Set default pause parameters */ @@ -4283,7 +4303,7 @@ static int bcmgenet_resume(struct device *d) bcmgenet_hfb_create_rxnfc_filter(priv, rule); /* Disable RX/TX DMA and flush TX queues */ - dma_ctrl = bcmgenet_dma_disable(priv); + dma_ctrl = bcmgenet_dma_disable(priv, false); /* Reinitialize TDMA and RDMA and SW housekeeping */ ret = bcmgenet_init_dma(priv); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index 4a73c157239851216220ba1cc34441c459ad9e02..44e42d7d26894c379cf07278198485f0f7793ef1 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2014-2020 Broadcom + * Copyright (c) 2014-2024 Broadcom */ #ifndef __BCMGENET_H__ @@ -573,6 +573,8 @@ struct bcmgenet_rxnfc_rule { /* device context */ struct bcmgenet_priv { void __iomem *base; + /* reg_lock: lock to serialize access to shared registers */ + spinlock_t reg_lock; enum bcmgenet_version version; struct net_device *dev; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c index f55d9d9c01a857d48e5d0a9c632dbaa87319a918..56781e72149785915b86ebb12ff9add34cf927b2 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c @@ -2,7 +2,7 @@ /* * Broadcom GENET (Gigabit Ethernet) Wake-on-LAN support * - * Copyright (c) 2014-2020 Broadcom + * Copyright (c) 2014-2024 Broadcom */ #define pr_fmt(fmt) "bcmgenet_wol: " fmt @@ -133,6 +133,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, } /* Can't suspend with WoL if MAC is still in reset */ + spin_lock_bh(&priv->reg_lock); reg = bcmgenet_umac_readl(priv, UMAC_CMD); if (reg & CMD_SW_RESET) reg &= ~CMD_SW_RESET; @@ -140,6 +141,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, /* disable RX */ reg &= ~CMD_RX_EN; bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock_bh(&priv->reg_lock); mdelay(10); if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) { @@ -185,6 +187,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, } /* Enable CRC forward */ + spin_lock_bh(&priv->reg_lock); reg = bcmgenet_umac_readl(priv, UMAC_CMD); priv->crc_fwd_en = 1; reg |= CMD_CRC_FWD; @@ -192,6 +195,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, /* Receiver must be enabled for WOL MP detection */ reg |= CMD_RX_EN; bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock_bh(&priv->reg_lock); reg = UMAC_IRQ_MPD_R; if (hfb_enable) @@ -238,7 +242,9 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv, } /* Disable CRC Forward */ + spin_lock_bh(&priv->reg_lock); reg = bcmgenet_umac_readl(priv, UMAC_CMD); reg &= ~CMD_CRC_FWD; bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock_bh(&priv->reg_lock); } diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 827fea61a018861d2334700b45ca30fbd9f208d5..0a06735105ef5443b4a41ced4ae4c57b3dcdfb75 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -2,7 +2,7 @@ /* * Broadcom GENET MDIO routines * - * Copyright (c) 2014-2017 Broadcom + * Copyright (c) 2014-2024 Broadcom */ #include @@ -72,10 +72,10 @@ static void bcmgenet_mac_config(struct net_device *dev) * Receive clock is provided by the PHY. */ reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL); - reg &= ~OOB_DISABLE; reg |= RGMII_LINK; bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); + spin_lock_bh(&priv->reg_lock); reg = bcmgenet_umac_readl(priv, UMAC_CMD); reg &= ~((CMD_SPEED_MASK << CMD_SPEED_SHIFT) | CMD_HD_EN | @@ -88,6 +88,7 @@ static void bcmgenet_mac_config(struct net_device *dev) reg |= CMD_TX_EN | CMD_RX_EN; } bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock_bh(&priv->reg_lock); priv->eee.eee_active = phy_init_eee(phydev, 0) >= 0; bcmgenet_eee_enable_set(dev, @@ -100,10 +101,18 @@ static void bcmgenet_mac_config(struct net_device *dev) */ void bcmgenet_mii_setup(struct net_device *dev) { + struct bcmgenet_priv *priv = netdev_priv(dev); struct phy_device *phydev = dev->phydev; + u32 reg; - if (phydev->link) + if (phydev->link) { bcmgenet_mac_config(dev); + } else { + reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL); + reg &= ~RGMII_LINK; + bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); + } + phy_print_status(phydev); } @@ -264,18 +273,22 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) (priv->phy_interface != PHY_INTERFACE_MODE_MOCA); /* This is an external PHY (xMII), so we need to enable the RGMII - * block for the interface to work + * block for the interface to work, unconditionally clear the + * Out-of-band disable since we do not need it. */ + mutex_lock(&phydev->lock); + reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL); + reg &= ~OOB_DISABLE; if (priv->ext_phy) { - reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL); reg &= ~ID_MODE_DIS; reg |= id_mode_dis; if (GENET_IS_V1(priv) || GENET_IS_V2(priv) || GENET_IS_V3(priv)) reg |= RGMII_MODE_EN_V123; else reg |= RGMII_MODE_EN; - bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); } + bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); + mutex_unlock(&phydev->lock); if (init) dev_info(kdev, "configuring instance for %s\n", phy_name); diff --git a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c index 04ad0f2b9677e1405a85e160935acc5ae757acc2..777f0d7e48192060f69a562df35a9b1d3ad2e6d9 100644 --- a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c +++ b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c @@ -312,7 +312,7 @@ bnad_debugfs_write_regrd(struct file *file, const char __user *buf, void *kern_buf; /* Copy the user space buf */ - kern_buf = memdup_user(buf, nbytes); + kern_buf = memdup_user_nul(buf, nbytes); if (IS_ERR(kern_buf)) return PTR_ERR(kern_buf); @@ -372,7 +372,7 @@ bnad_debugfs_write_regwr(struct file *file, const char __user *buf, void *kern_buf; /* Copy the user space buf */ - kern_buf = memdup_user(buf, nbytes); + kern_buf = memdup_user_nul(buf, nbytes); if (IS_ERR(kern_buf)) return PTR_ERR(kern_buf); diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 46809e2d94ee08bf619398791daf034beb4f8405..4809d9eae6ca57c9e25dffbcfb5f88b6105cccc4 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -2684,12 +2684,12 @@ int cxgb4_selftest_lb_pkt(struct net_device *netdev) lb->loopback = 1; q = &adap->sge.ethtxq[pi->first_qset]; - __netif_tx_lock(q->txq, smp_processor_id()); + __netif_tx_lock_bh(q->txq); reclaim_completed_tx(adap, &q->q, -1, true); credits = txq_avail(&q->q) - ndesc; if (unlikely(credits < 0)) { - __netif_tx_unlock(q->txq); + __netif_tx_unlock_bh(q->txq); return -ENOMEM; } @@ -2724,7 +2724,7 @@ int cxgb4_selftest_lb_pkt(struct net_device *netdev) init_completion(&lb->completion); txq_advance(&q->q, ndesc); cxgb4_ring_tx_db(adap, &q->q, ndesc); - __netif_tx_unlock(q->txq); + __netif_tx_unlock_bh(q->txq); /* wait for the pkt to return */ ret = wait_for_completion_timeout(&lb->completion, 10 * HZ); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 97d12c7eea77200f0e3367083718ee6890604461..ebff14b0837d9c7de56fa653d082c6ed4044af9a 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2236,8 +2236,6 @@ static int fec_enet_mii_probe(struct net_device *ndev) fep->link = 0; fep->full_duplex = 0; - phy_dev->mac_managed_pm = 1; - phy_attached_info(phy_dev); return 0; @@ -2249,10 +2247,12 @@ static int fec_enet_mii_init(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); bool suppress_preamble = false; + struct phy_device *phydev; struct device_node *node; int err = -ENXIO; u32 mii_speed, holdtime; u32 bus_freq; + int addr; /* * The i.MX28 dual fec interfaces are not equal. @@ -2362,6 +2362,13 @@ static int fec_enet_mii_init(struct platform_device *pdev) goto err_out_free_mdiobus; of_node_put(node); + /* find all the PHY devices on the bus and set mac_managed_pm to true */ + for (addr = 0; addr < PHY_MAX_ADDR; addr++) { + phydev = mdiobus_get_phy(fep->mii_bus, addr); + if (phydev) + phydev->mac_managed_pm = true; + } + mii_cnt++; /* save fec0 mii_bus */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index c693bb701ba3e2a267633d026a384a66fe6d8279..60b8d61af07f9048c8a1e35fc0262921cd0dffdc 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -873,7 +873,7 @@ struct hnae3_handle { struct hnae3_roce_private_info rinfo; }; - u32 numa_node_mask; /* for multi-chip support */ + nodemask_t numa_node_mask; /* for multi-chip support */ enum hnae3_port_base_vlan_state port_base_vlan_state; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c index f3c9395d8351cb31108973e1867332e00026c6ac..618f66d9586b390a4d4ec45aafa4178ec06e5a91 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c @@ -85,7 +85,7 @@ int hclge_comm_tqps_update_stats(struct hnae3_handle *handle, hclge_comm_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_TX_STATS, true); - desc.data[0] = cpu_to_le32(tqp->index & 0x1ff); + desc.data[0] = cpu_to_le32(tqp->index); ret = hclge_comm_cmd_send(hw, &desc, 1); if (ret) { dev_err(&hw->cmq.csq.pdev->dev, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c b/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c index 3b6dbf158b98db7d9ec97bfa22b34e4e61f0d260..f72dc0cee30e553dba0fac192308107e858da404 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c @@ -76,7 +76,7 @@ static int hns3_dcbnl_ieee_delapp(struct net_device *ndev, struct dcb_app *app) if (hns3_nic_resetting(ndev)) return -EBUSY; - if (h->kinfo.dcb_ops->ieee_setapp) + if (h->kinfo.dcb_ops->ieee_delapp) return h->kinfo.dcb_ops->ieee_delapp(h, app); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index e22835ae8a9412a6ce52734981b21de533a34df9..9fce976a08f011be837b48846f2f2424a6cfdb21 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -78,6 +78,9 @@ static const struct hns3_stats hns3_rxq_stats[] = { #define HNS3_NIC_LB_TEST_NO_MEM_ERR 1 #define HNS3_NIC_LB_TEST_TX_CNT_ERR 2 #define HNS3_NIC_LB_TEST_RX_CNT_ERR 3 +#define HNS3_NIC_LB_TEST_UNEXECUTED 4 + +static int hns3_get_sset_count(struct net_device *netdev, int stringset); static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en) { @@ -419,18 +422,26 @@ static void hns3_do_external_lb(struct net_device *ndev, static void hns3_self_test(struct net_device *ndev, struct ethtool_test *eth_test, u64 *data) { + int cnt = hns3_get_sset_count(ndev, ETH_SS_TEST); struct hns3_nic_priv *priv = netdev_priv(ndev); struct hnae3_handle *h = priv->ae_handle; int st_param[HNAE3_LOOP_NONE][2]; bool if_running = netif_running(ndev); + int i; + + /* initialize the loopback test result, avoid marking an unexcuted + * loopback test as PASS. + */ + for (i = 0; i < cnt; i++) + data[i] = HNS3_NIC_LB_TEST_UNEXECUTED; if (hns3_nic_resetting(ndev)) { netdev_err(ndev, "dev resetting!"); - return; + goto failure; } if (!(eth_test->flags & ETH_TEST_FL_OFFLINE)) - return; + goto failure; if (netif_msg_ifdown(h)) netdev_info(ndev, "self test start\n"); @@ -452,6 +463,10 @@ static void hns3_self_test(struct net_device *ndev, if (netif_msg_ifdown(h)) netdev_info(ndev, "self test end\n"); + return; + +failure: + eth_test->flags |= ETH_TEST_FL_FAILED; } static void hns3_update_limit_promisc_mode(struct net_device *netdev, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 48b0cb5ec5d29f8106d0a7c981e950ccd0bebb9c..a2655adc764cd871c7765b0b8ebd7f9dd6ff5290 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -1624,6 +1624,9 @@ static int hclge_configure(struct hclge_dev *hdev) cfg.default_speed, ret); return ret; } + hdev->hw.mac.req_speed = hdev->hw.mac.speed; + hdev->hw.mac.req_autoneg = AUTONEG_ENABLE; + hdev->hw.mac.req_duplex = DUPLEX_FULL; hclge_parse_link_mode(hdev, cfg.speed_ability); @@ -1853,7 +1856,8 @@ static int hclge_vport_setup(struct hclge_vport *vport, u16 num_tqps) nic->pdev = hdev->pdev; nic->ae_algo = &ae_algo; - nic->numa_node_mask = hdev->numa_node_mask; + bitmap_copy(nic->numa_node_mask.bits, hdev->numa_node_mask.bits, + MAX_NUMNODES); nic->kinfo.io_base = hdev->hw.hw.io_base; ret = hclge_knic_setup(vport, num_tqps, @@ -2545,7 +2549,8 @@ static int hclge_init_roce_base_info(struct hclge_vport *vport) roce->pdev = nic->pdev; roce->ae_algo = nic->ae_algo; - roce->numa_node_mask = nic->numa_node_mask; + bitmap_copy(roce->numa_node_mask.bits, nic->numa_node_mask.bits, + MAX_NUMNODES); return 0; } @@ -2990,7 +2995,10 @@ static int hclge_mac_init(struct hclge_dev *hdev) int ret; hdev->support_sfp_query = true; - hdev->hw.mac.duplex = HCLGE_MAC_FULL; + + if (!test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) + hdev->hw.mac.duplex = HCLGE_MAC_FULL; + ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.speed, hdev->hw.mac.duplex, hdev->hw.mac.lane_num); if (ret) @@ -3426,9 +3434,9 @@ hclge_set_phy_link_ksettings(struct hnae3_handle *handle, return ret; } - hdev->hw.mac.autoneg = cmd->base.autoneg; - hdev->hw.mac.speed = cmd->base.speed; - hdev->hw.mac.duplex = cmd->base.duplex; + hdev->hw.mac.req_autoneg = cmd->base.autoneg; + hdev->hw.mac.req_speed = cmd->base.speed; + hdev->hw.mac.req_duplex = cmd->base.duplex; linkmode_copy(hdev->hw.mac.advertising, cmd->link_modes.advertising); return 0; @@ -3461,9 +3469,9 @@ static int hclge_tp_port_init(struct hclge_dev *hdev) if (!hnae3_dev_phy_imp_supported(hdev)) return 0; - cmd.base.autoneg = hdev->hw.mac.autoneg; - cmd.base.speed = hdev->hw.mac.speed; - cmd.base.duplex = hdev->hw.mac.duplex; + cmd.base.autoneg = hdev->hw.mac.req_autoneg; + cmd.base.speed = hdev->hw.mac.req_speed; + cmd.base.duplex = hdev->hw.mac.req_duplex; linkmode_copy(cmd.link_modes.advertising, hdev->hw.mac.advertising); return hclge_set_phy_link_ksettings(&hdev->vport->nic, &cmd); @@ -8043,8 +8051,7 @@ static void hclge_set_timer_task(struct hnae3_handle *handle, bool enable) /* Set the DOWN flag here to disable link updating */ set_bit(HCLGE_STATE_DOWN, &hdev->state); - /* flush memory to make sure DOWN is seen by service task */ - smp_mb__before_atomic(); + smp_mb__after_atomic(); /* flush memory to make sure DOWN is seen by service task */ hclge_flush_link_update(hdev); } } @@ -9997,6 +10004,7 @@ static int hclge_set_vlan_protocol_type(struct hclge_dev *hdev) static int hclge_init_vlan_filter(struct hclge_dev *hdev) { struct hclge_vport *vport; + bool enable = true; int ret; int i; @@ -10016,8 +10024,12 @@ static int hclge_init_vlan_filter(struct hclge_dev *hdev) vport->cur_vlan_fltr_en = true; } + if (test_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, hdev->ae_dev->caps) && + !test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, hdev->ae_dev->caps)) + enable = false; + return hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT, - HCLGE_FILTER_FE_INGRESS, true, 0); + HCLGE_FILTER_FE_INGRESS, enable, 0); } static int hclge_init_vlan_type(struct hclge_dev *hdev) @@ -11597,14 +11609,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) if (ret) goto out; - ret = hclge_devlink_init(hdev); - if (ret) - goto err_pci_uninit; - /* Firmware command queue initialize */ ret = hclge_comm_cmd_queue_init(hdev->pdev, &hdev->hw.hw); if (ret) - goto err_devlink_uninit; + goto err_pci_uninit; /* Firmware command initialize */ ret = hclge_comm_cmd_init(hdev->ae_dev, &hdev->hw.hw, &hdev->fw_version, @@ -11732,7 +11740,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) ret = hclge_update_port_info(hdev); if (ret) - goto err_mdiobus_unreg; + goto err_ptp_uninit; INIT_KFIFO(hdev->mac_tnl_log); @@ -11767,6 +11775,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) /* Enable MISC vector(vector0) */ hclge_enable_vector(&hdev->misc_vector, true); + ret = hclge_devlink_init(hdev); + if (ret) + goto err_ptp_uninit; + hclge_state_init(hdev); hdev->last_reset_time = jiffies; @@ -11774,9 +11786,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) HCLGE_DRIVER_NAME); hclge_task_schedule(hdev, round_jiffies_relative(HZ)); - return 0; +err_ptp_uninit: + hclge_ptp_uninit(hdev); err_mdiobus_unreg: if (hdev->hw.mac.phydev) mdiobus_unregister(hdev->hw.mac.mdio_bus); @@ -11786,8 +11799,6 @@ err_msi_uninit: pci_free_irq_vectors(pdev); err_cmd_uninit: hclge_comm_cmd_uninit(hdev->ae_dev, &hdev->hw.hw); -err_devlink_uninit: - hclge_devlink_uninit(hdev); err_pci_uninit: pcim_iounmap(pdev, hdev->hw.hw.io_base); pci_clear_master(pdev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index f6fef790e16c1bbc1c6cccd2bd190148372d93ac..fd79bb81b6e071d76777dc59e0b5367757948905 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -256,11 +256,14 @@ struct hclge_mac { u8 media_type; /* port media type, e.g. fibre/copper/backplane */ u8 mac_addr[ETH_ALEN]; u8 autoneg; + u8 req_autoneg; u8 duplex; + u8 req_duplex; u8 support_autoneg; u8 speed_type; /* 0: sfp speed, 1: active speed */ u8 lane_num; u32 speed; + u32 req_speed; u32 max_speed; u32 speed_ability; /* speed ability supported by current media */ u32 module_type; /* sub media type, e.g. kr/cr/sr/lr */ @@ -872,7 +875,7 @@ struct hclge_dev { u16 fdir_pf_filter_count; /* Num of guaranteed filters for this PF */ u16 num_alloc_vport; /* Num vports this driver supports */ - u32 numa_node_mask; + nodemask_t numa_node_mask; u16 rx_buf_len; u16 num_tx_desc; /* desc num of per tx queue */ u16 num_rx_desc; /* desc num of per rx queue */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 04ff9bf121853ab7a0f876c55b49d1e6d9199035..877feee53804f10229fe8f14675a1f45f84b5f09 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -1077,12 +1077,13 @@ static void hclge_mbx_request_handling(struct hclge_mbx_ops_param *param) hdev = param->vport->back; cmd_func = hclge_mbx_ops_list[param->req->msg.code]; - if (cmd_func) - ret = cmd_func(param); - else + if (!cmd_func) { dev_err(&hdev->pdev->dev, "un-supported mailbox message, code = %u\n", param->req->msg.code); + return; + } + ret = cmd_func(param); /* PF driver should not reply IMP */ if (hnae3_get_bit(param->req->mbx_need_resp, HCLGE_MBX_NEED_RESP_B) && diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c index a40b1583f114944570fab972ec32333d5c23db98..0f06f95b09bc28b486178b6b3f54d7ed5b3c1733 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c @@ -120,7 +120,7 @@ void hclge_ptp_get_rx_hwts(struct hnae3_handle *handle, struct sk_buff *skb, u64 ns = nsec; u32 sec_h; - if (!test_bit(HCLGE_PTP_FLAG_RX_EN, &hdev->ptp->flags)) + if (!hdev->ptp || !test_bit(HCLGE_PTP_FLAG_RX_EN, &hdev->ptp->flags)) return; /* Since the BD does not have enough space for the higher 16 bits of diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h index 8510b88d49820acf3ef81c34ee263d6eaebd2591..f3cd5a376eca90493395687fc40f9da27715a674 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h @@ -24,7 +24,7 @@ TRACE_EVENT(hclge_pf_mbx_get, __field(u8, code) __field(u8, subcode) __string(pciname, pci_name(hdev->pdev)) - __string(devname, &hdev->vport[0].nic.kinfo.netdev->name) + __string(devname, hdev->vport[0].nic.kinfo.netdev->name) __array(u32, mbx_data, PF_GET_MBX_LEN) ), @@ -33,7 +33,7 @@ TRACE_EVENT(hclge_pf_mbx_get, __entry->code = req->msg.code; __entry->subcode = req->msg.subcode; __assign_str(pciname, pci_name(hdev->pdev)); - __assign_str(devname, &hdev->vport[0].nic.kinfo.netdev->name); + __assign_str(devname, hdev->vport[0].nic.kinfo.netdev->name); memcpy(__entry->mbx_data, req, sizeof(struct hclge_mbx_vf_to_pf_cmd)); ), @@ -56,7 +56,7 @@ TRACE_EVENT(hclge_pf_mbx_send, __field(u8, vfid) __field(u16, code) __string(pciname, pci_name(hdev->pdev)) - __string(devname, &hdev->vport[0].nic.kinfo.netdev->name) + __string(devname, hdev->vport[0].nic.kinfo.netdev->name) __array(u32, mbx_data, PF_SEND_MBX_LEN) ), @@ -64,7 +64,7 @@ TRACE_EVENT(hclge_pf_mbx_send, __entry->vfid = req->dest_vfid; __entry->code = le16_to_cpu(req->msg.code); __assign_str(pciname, pci_name(hdev->pdev)); - __assign_str(devname, &hdev->vport[0].nic.kinfo.netdev->name); + __assign_str(devname, hdev->vport[0].nic.kinfo.netdev->name); memcpy(__entry->mbx_data, req, sizeof(struct hclge_mbx_pf_to_vf_cmd)); ), diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 5a978ea101a902c5005bf35da9c0abd04a89657d..1f5a27fb309aacc206f0aad26293bc8ed6ca274b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -464,7 +464,8 @@ static int hclgevf_set_handle_info(struct hclgevf_dev *hdev) nic->ae_algo = &ae_algovf; nic->pdev = hdev->pdev; - nic->numa_node_mask = hdev->numa_node_mask; + bitmap_copy(nic->numa_node_mask.bits, hdev->numa_node_mask.bits, + MAX_NUMNODES); nic->flags |= HNAE3_SUPPORT_VF; nic->kinfo.io_base = hdev->hw.hw.io_base; @@ -2136,8 +2137,8 @@ static int hclgevf_init_roce_base_info(struct hclgevf_dev *hdev) roce->pdev = nic->pdev; roce->ae_algo = nic->ae_algo; - roce->numa_node_mask = nic->numa_node_mask; - + bitmap_copy(roce->numa_node_mask.bits, nic->numa_node_mask.bits, + MAX_NUMNODES); return 0; } @@ -2235,8 +2236,7 @@ static void hclgevf_set_timer_task(struct hnae3_handle *handle, bool enable) } else { set_bit(HCLGEVF_STATE_DOWN, &hdev->state); - /* flush memory to make sure DOWN is seen by service task */ - smp_mb__before_atomic(); + smp_mb__after_atomic(); /* flush memory to make sure DOWN is seen by service task */ hclgevf_flush_link_update(hdev); } } @@ -2902,10 +2902,6 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) if (ret) return ret; - ret = hclgevf_devlink_init(hdev); - if (ret) - goto err_devlink_init; - ret = hclge_comm_cmd_queue_init(hdev->pdev, &hdev->hw.hw); if (ret) goto err_cmd_queue_init; @@ -2998,6 +2994,10 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) hclgevf_init_rxd_adv_layout(hdev); + ret = hclgevf_devlink_init(hdev); + if (ret) + goto err_config; + set_bit(HCLGEVF_STATE_SERVICE_INITED, &hdev->state); hdev->last_reset_time = jiffies; @@ -3017,8 +3017,6 @@ err_misc_irq_init: err_cmd_init: hclge_comm_cmd_uninit(hdev->ae_dev, &hdev->hw.hw); err_cmd_queue_init: - hclgevf_devlink_uninit(hdev); -err_devlink_init: hclgevf_pci_uninit(hdev); clear_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state); return ret; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index d65ace07b4569f04b6a36a6209960da1286d7f53..976414d00e67a3bd743a2e605afd55846b14a226 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -236,7 +236,7 @@ struct hclgevf_dev { u16 rss_size_max; /* HW defined max RSS task queue */ u16 num_alloc_vport; /* num vports this driver supports */ - u32 numa_node_mask; + nodemask_t numa_node_mask; u16 rx_buf_len; u16 num_tx_desc; /* desc num of per tx queue */ u16 num_rx_desc; /* desc num of per rx queue */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h index 5d4895bb57a17d9a01b29545af427ae760c0d578..b259e95dd53c263819af84e280d1aa2133165c59 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h @@ -23,7 +23,7 @@ TRACE_EVENT(hclge_vf_mbx_get, __field(u8, vfid) __field(u16, code) __string(pciname, pci_name(hdev->pdev)) - __string(devname, &hdev->nic.kinfo.netdev->name) + __string(devname, hdev->nic.kinfo.netdev->name) __array(u32, mbx_data, VF_GET_MBX_LEN) ), @@ -31,7 +31,7 @@ TRACE_EVENT(hclge_vf_mbx_get, __entry->vfid = req->dest_vfid; __entry->code = le16_to_cpu(req->msg.code); __assign_str(pciname, pci_name(hdev->pdev)); - __assign_str(devname, &hdev->nic.kinfo.netdev->name); + __assign_str(devname, hdev->nic.kinfo.netdev->name); memcpy(__entry->mbx_data, req, sizeof(struct hclge_mbx_pf_to_vf_cmd)); ), @@ -55,7 +55,7 @@ TRACE_EVENT(hclge_vf_mbx_send, __field(u8, code) __field(u8, subcode) __string(pciname, pci_name(hdev->pdev)) - __string(devname, &hdev->nic.kinfo.netdev->name) + __string(devname, hdev->nic.kinfo.netdev->name) __array(u32, mbx_data, VF_SEND_MBX_LEN) ), @@ -64,7 +64,7 @@ TRACE_EVENT(hclge_vf_mbx_send, __entry->code = req->msg.code; __entry->subcode = req->msg.subcode; __assign_str(pciname, pci_name(hdev->pdev)); - __assign_str(devname, &hdev->nic.kinfo.netdev->name); + __assign_str(devname, hdev->nic.kinfo.netdev->name); memcpy(__entry->mbx_data, req, sizeof(struct hclge_mbx_vf_to_pf_cmd)); ), diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 7d4cc4eafd59e7e6ecf0cb46ad78d283b3217f10..5293fc00938cf511262f5a8f0fe7dbbc3ee02e13 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -108,7 +108,7 @@ #define I40E_MAX_BW_INACTIVE_ACCUM 4 /* accumulate 4 credits max */ /* driver state flags */ -enum i40e_state_t { +enum i40e_state { __I40E_TESTING, __I40E_CONFIG_BUSY, __I40E_CONFIG_DONE, @@ -156,7 +156,7 @@ enum i40e_state_t { BIT_ULL(__I40E_PF_RESET_AND_REBUILD_REQUESTED) /* VSI state flags */ -enum i40e_vsi_state_t { +enum i40e_vsi_state { __I40E_VSI_DOWN, __I40E_VSI_NEEDS_RESTART, __I40E_VSI_SYNCING_FILTERS, @@ -992,6 +992,8 @@ struct i40e_q_vector { struct rcu_head rcu; /* to avoid race with update stats on free */ char name[I40E_INT_NAME_STR_LEN]; bool arm_wb_state; + bool in_busy_poll; + int irq_num; /* IRQ assigned to this q_vector */ } ____cacheline_internodealigned_in_smp; /* lan device */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 63d43ef86f9b946c6e01bf87b153d1ee0129ff14..9efd4b962dce2332d32694843b7c7d370fa7fd1c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1249,8 +1249,11 @@ int i40e_count_filters(struct i40e_vsi *vsi) int bkt; int cnt = 0; - hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) - ++cnt; + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { + if (f->state == I40E_FILTER_NEW || + f->state == I40E_FILTER_ACTIVE) + ++cnt; + } return cnt; } @@ -3888,6 +3891,12 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi) q_vector->tx.target_itr >> 1); q_vector->tx.current_itr = q_vector->tx.target_itr; + /* Set ITR for software interrupts triggered after exiting + * busy-loop polling. + */ + wr32(hw, I40E_PFINT_ITRN(I40E_SW_ITR, vector - 1), + I40E_ITR_20K); + wr32(hw, I40E_PFINT_RATEN(vector - 1), i40e_intrl_usec_to_reg(vsi->int_rate_limit)); @@ -4142,6 +4151,7 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename) } /* register for affinity change notifications */ + q_vector->irq_num = irq_num; 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); @@ -5333,7 +5343,7 @@ static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf) { int v, ret = 0; - for (v = 0; v < pf->hw.func_caps.num_vsis; v++) { + for (v = 0; v < pf->num_alloc_vsi; v++) { if (pf->vsi[v]) { ret = i40e_vsi_wait_queues_disabled(pf->vsi[v]); if (ret) @@ -13569,9 +13579,9 @@ int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair) return err; i40e_queue_pair_disable_irq(vsi, queue_pair); + i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */); err = i40e_queue_pair_toggle_rings(vsi, queue_pair, false /* off */); i40e_clean_rx_ring(vsi->rx_rings[queue_pair]); - i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */); i40e_queue_pair_clean_rings(vsi, queue_pair); i40e_queue_pair_reset_stats(vsi, queue_pair); @@ -16163,8 +16173,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) val = (rd32(&pf->hw, I40E_PRTGL_SAH) & I40E_PRTGL_SAH_MFS_MASK) >> I40E_PRTGL_SAH_MFS_SHIFT; if (val < MAX_FRAME_SIZE_DEFAULT) - dev_warn(&pdev->dev, "MFS for port %x has been set below the default: %x\n", - pf->hw.port, val); + dev_warn(&pdev->dev, "MFS for port %x (%d) has been set below the default (%d)\n", + pf->hw.port, val, MAX_FRAME_SIZE_DEFAULT); /* Add a filter to drop all Flow control frames from any VSI from being * transmitted. By doing so we stop a malicious VF from sending out @@ -16706,7 +16716,7 @@ static int __init i40e_init_module(void) * since we need to be able to guarantee forward progress even under * memory pressure. */ - i40e_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, i40e_driver_name); + i40e_wq = alloc_workqueue("%s", 0, 0, i40e_driver_name); if (!i40e_wq) { pr_err("%s: Failed to create workqueue\n", i40e_driver_name); return -ENOMEM; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index 97a9efe7b713e7d2bf26e80279ecc10b8d5a665d..5f2555848a69e6cc0faf8235c7f38c8328419c35 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -34,7 +34,7 @@ enum i40e_ptp_pin { GPIO_4 }; -enum i40e_can_set_pins_t { +enum i40e_can_set_pins { CANT_DO_PINS = -1, CAN_SET_PINS, CAN_DO_PINS @@ -192,7 +192,7 @@ static bool i40e_is_ptp_pin_dev(struct i40e_hw *hw) * return CAN_DO_PINS if pins can be manipulated within a NIC or * return CANT_DO_PINS otherwise. **/ -static enum i40e_can_set_pins_t i40e_can_set_pins(struct i40e_pf *pf) +static enum i40e_can_set_pins i40e_can_set_pins(struct i40e_pf *pf) { if (!i40e_is_ptp_pin_dev(&pf->hw)) { dev_warn(&pf->pdev->dev, @@ -1081,7 +1081,7 @@ static void i40e_ptp_set_pins_hw(struct i40e_pf *pf) static int i40e_ptp_set_pins(struct i40e_pf *pf, struct i40e_ptp_pins_settings *pins) { - enum i40e_can_set_pins_t pin_caps = i40e_can_set_pins(pf); + enum i40e_can_set_pins pin_caps = i40e_can_set_pins(pf); int i = 0; if (pin_caps == CANT_DO_PINS) diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h index 7339003aa17cd346d404c6cd4548d1f5f5f8bbcc..694cb3e45c1ecf06ff918d0b9ee67e105489945f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_register.h +++ b/drivers/net/ethernet/intel/i40e/i40e_register.h @@ -328,8 +328,11 @@ #define I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT 3 #define I40E_PFINT_DYN_CTLN_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) #define I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT 5 +#define I40E_PFINT_DYN_CTLN_INTERVAL_MASK I40E_MASK(0xFFF, I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT) #define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT 24 #define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT) +#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT 25 +#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT) #define I40E_PFINT_ICR0 0x00038780 /* Reset: CORER */ #define I40E_PFINT_ICR0_INTEVENT_SHIFT 0 #define I40E_PFINT_ICR0_INTEVENT_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_INTEVENT_SHIFT) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 94cf82668efaaece562d91d3d23baa60364fb2b0..3d83fccf742b14e248c0a8b70921d7296dfb657c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2571,7 +2571,22 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) return failure ? budget : (int)total_rx_packets; } -static inline u32 i40e_buildreg_itr(const int type, u16 itr) +/** + * i40e_buildreg_itr - build a value for writing to I40E_PFINT_DYN_CTLN register + * @itr_idx: interrupt throttling index + * @interval: interrupt throttling interval value in usecs + * @force_swint: force software interrupt + * + * The function builds a value for I40E_PFINT_DYN_CTLN register that + * is used to update interrupt throttling interval for specified ITR index + * and optionally enforces a software interrupt. If the @itr_idx is equal + * to I40E_ITR_NONE then no interval change is applied and only @force_swint + * parameter is taken into account. If the interval change and enforced + * software interrupt are not requested then the built value just enables + * appropriate vector interrupt. + **/ +static u32 i40e_buildreg_itr(enum i40e_dyn_idx itr_idx, u16 interval, + bool force_swint) { u32 val; @@ -2585,23 +2600,33 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr) * an event in the PBA anyway so we need to rely on the automask * to hold pending events for us until the interrupt is re-enabled * - * The itr value is reported in microseconds, and the register - * value is recorded in 2 microsecond units. For this reason we - * only need to shift by the interval shift - 1 instead of the - * full value. + * We have to shift the given value as it is reported in microseconds + * and the register value is recorded in 2 microsecond units. */ - itr &= I40E_ITR_MASK; + interval >>= 1; + /* 1. Enable vector interrupt + * 2. Update the interval for the specified ITR index + * (I40E_ITR_NONE in the register is used to indicate that + * no interval update is requested) + */ val = I40E_PFINT_DYN_CTLN_INTENA_MASK | - (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) | - (itr << (I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT - 1)); + FIELD_PREP(I40E_PFINT_DYN_CTLN_ITR_INDX_MASK, itr_idx) | + FIELD_PREP(I40E_PFINT_DYN_CTLN_INTERVAL_MASK, interval); + + /* 3. Enforce software interrupt trigger if requested + * (These software interrupts rate is limited by ITR2 that is + * set to 20K interrupts per second) + */ + if (force_swint) + val |= I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK | + I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK | + FIELD_PREP(I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK, + I40E_SW_ITR); return val; } -/* a small macro to shorten up some long lines */ -#define INTREG I40E_PFINT_DYN_CTLN - /* The act of updating the ITR will cause it to immediately trigger. In order * to prevent this from throwing off adaptive update statistics we defer the * update so that it can only happen so often. So after either Tx or Rx are @@ -2620,8 +2645,10 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr) static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) { + enum i40e_dyn_idx itr_idx = I40E_ITR_NONE; struct i40e_hw *hw = &vsi->back->hw; - u32 intval; + u16 interval = 0; + u32 itr_val; /* If we don't have MSIX, then we only need to re-enable icr0 */ if (!(vsi->back->flags & I40E_FLAG_MSIX_ENABLED)) { @@ -2643,8 +2670,8 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, */ if (q_vector->rx.target_itr < q_vector->rx.current_itr) { /* Rx ITR needs to be reduced, this is highest priority */ - intval = i40e_buildreg_itr(I40E_RX_ITR, - q_vector->rx.target_itr); + itr_idx = I40E_RX_ITR; + interval = q_vector->rx.target_itr; q_vector->rx.current_itr = q_vector->rx.target_itr; q_vector->itr_countdown = ITR_COUNTDOWN_START; } else if ((q_vector->tx.target_itr < q_vector->tx.current_itr) || @@ -2653,25 +2680,36 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, /* Tx ITR needs to be reduced, this is second priority * Tx ITR needs to be increased more than Rx, fourth priority */ - intval = i40e_buildreg_itr(I40E_TX_ITR, - q_vector->tx.target_itr); + itr_idx = I40E_TX_ITR; + interval = q_vector->tx.target_itr; q_vector->tx.current_itr = q_vector->tx.target_itr; q_vector->itr_countdown = ITR_COUNTDOWN_START; } else if (q_vector->rx.current_itr != q_vector->rx.target_itr) { /* Rx ITR needs to be increased, third priority */ - intval = i40e_buildreg_itr(I40E_RX_ITR, - q_vector->rx.target_itr); + itr_idx = I40E_RX_ITR; + interval = q_vector->rx.target_itr; q_vector->rx.current_itr = q_vector->rx.target_itr; q_vector->itr_countdown = ITR_COUNTDOWN_START; } else { /* No ITR update, lowest priority */ - intval = i40e_buildreg_itr(I40E_ITR_NONE, 0); if (q_vector->itr_countdown) q_vector->itr_countdown--; } - if (!test_bit(__I40E_VSI_DOWN, vsi->state)) - wr32(hw, INTREG(q_vector->reg_idx), intval); + /* Do not update interrupt control register if VSI is down */ + if (test_bit(__I40E_VSI_DOWN, vsi->state)) + return; + + /* Update ITR interval if necessary and enforce software interrupt + * if we are exiting busy poll. + */ + if (q_vector->in_busy_poll) { + itr_val = i40e_buildreg_itr(itr_idx, interval, true); + q_vector->in_busy_poll = false; + } else { + itr_val = i40e_buildreg_itr(itr_idx, interval, false); + } + wr32(hw, I40E_PFINT_DYN_CTLN(q_vector->reg_idx), itr_val); } /** @@ -2778,6 +2816,8 @@ tx_only: */ if (likely(napi_complete_done(napi, work_done))) i40e_update_enable_itr(vsi, q_vector); + else + q_vector->in_busy_poll = true; return min(work_done, budget - 1); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 768290dc6f48b983d3e5d7e630016a10211e9a52..6e567d343e0316459369a165ab3cc09b12b5b050 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -57,7 +57,7 @@ static inline u16 i40e_intrl_usec_to_reg(int intrl) * mentioning ITR_INDX, ITR_NONE cannot be used as an index 'n' into any * register but instead is a special value meaning "don't update" ITR0/1/2. */ -enum i40e_dyn_idx_t { +enum i40e_dyn_idx { I40E_IDX_ITR0 = 0, I40E_IDX_ITR1 = 1, I40E_IDX_ITR2 = 2, @@ -67,6 +67,7 @@ enum i40e_dyn_idx_t { /* these are indexes into ITRN registers */ #define I40E_RX_ITR I40E_IDX_ITR0 #define I40E_TX_ITR I40E_IDX_ITR1 +#define I40E_SW_ITR I40E_IDX_ITR2 /* Supported RSS offloads */ #define I40E_DEFAULT_RSS_HENA ( \ @@ -304,7 +305,7 @@ struct i40e_rx_queue_stats { u64 page_busy_count; }; -enum i40e_ring_state_t { +enum i40e_ring_state { __I40E_TX_FDIR_INIT_DONE, __I40E_TX_XPS_INIT_DONE, __I40E_RING_STATE_NBITS /* must be last */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 3d3db58090ed177350a30a25e8061be3fe2f55e4..a5f0c95cba8b5e8808be8e21f7402a0e3940fb07 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1626,8 +1626,8 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) { struct i40e_hw *hw = &pf->hw; struct i40e_vf *vf; - int i, v; u32 reg; + int i; /* If we don't have any VFs, then there is nothing to reset */ if (!pf->num_alloc_vfs) @@ -1638,11 +1638,10 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) return false; /* Begin reset on all VFs at once */ - for (v = 0; v < pf->num_alloc_vfs; v++) { - vf = &pf->vf[v]; + for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) { /* If VF is being reset no need to trigger reset again */ if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) - i40e_trigger_vf_reset(&pf->vf[v], flr); + i40e_trigger_vf_reset(vf, flr); } /* HW requires some time to make sure it can flush the FIFO for a VF @@ -1651,14 +1650,13 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) * the VFs using a simple iterator that increments once that VF has * finished resetting. */ - for (i = 0, v = 0; i < 10 && v < pf->num_alloc_vfs; i++) { + for (i = 0, vf = &pf->vf[0]; i < 10 && vf < &pf->vf[pf->num_alloc_vfs]; ++i) { usleep_range(10000, 20000); /* Check each VF in sequence, beginning with the VF to fail * the previous check. */ - while (v < pf->num_alloc_vfs) { - vf = &pf->vf[v]; + while (vf < &pf->vf[pf->num_alloc_vfs]) { if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) { reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id)); if (!(reg & I40E_VPGEN_VFRSTAT_VFRD_MASK)) @@ -1668,7 +1666,7 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) /* If the current VF has finished resetting, move on * to the next VF in sequence. */ - v++; + ++vf; } } @@ -1678,39 +1676,39 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) /* Display a warning if at least one VF didn't manage to reset in * time, but continue on with the operation. */ - if (v < pf->num_alloc_vfs) + if (vf < &pf->vf[pf->num_alloc_vfs]) dev_err(&pf->pdev->dev, "VF reset check timeout on VF %d\n", - pf->vf[v].vf_id); + vf->vf_id); usleep_range(10000, 20000); /* Begin disabling all the rings associated with VFs, but do not wait * between each VF. */ - for (v = 0; v < pf->num_alloc_vfs; v++) { + for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) { /* On initial reset, we don't have any queues to disable */ - if (pf->vf[v].lan_vsi_idx == 0) + if (vf->lan_vsi_idx == 0) continue; /* If VF is reset in another thread just continue */ if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) continue; - i40e_vsi_stop_rings_no_wait(pf->vsi[pf->vf[v].lan_vsi_idx]); + i40e_vsi_stop_rings_no_wait(pf->vsi[vf->lan_vsi_idx]); } /* Now that we've notified HW to disable all of the VF rings, wait * until they finish. */ - for (v = 0; v < pf->num_alloc_vfs; v++) { + for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) { /* On initial reset, we don't have any queues to disable */ - if (pf->vf[v].lan_vsi_idx == 0) + if (vf->lan_vsi_idx == 0) continue; /* If VF is reset in another thread just continue */ if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) continue; - i40e_vsi_wait_queues_disabled(pf->vsi[pf->vf[v].lan_vsi_idx]); + i40e_vsi_wait_queues_disabled(pf->vsi[vf->lan_vsi_idx]); } /* Hw may need up to 50ms to finish disabling the RX queues. We @@ -1719,12 +1717,12 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) mdelay(50); /* Finish the reset on each VF */ - for (v = 0; v < pf->num_alloc_vfs; v++) { + for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) { /* If VF is reset in another thread just continue */ if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) continue; - i40e_cleanup_reset_vf(&pf->vf[v]); + i40e_cleanup_reset_vf(vf); } i40e_flush(hw); @@ -2846,6 +2844,24 @@ error_param: (u8 *)&stats, sizeof(stats)); } +/** + * i40e_can_vf_change_mac + * @vf: pointer to the VF info + * + * Return true if the VF is allowed to change its MAC filters, false otherwise + */ +static bool i40e_can_vf_change_mac(struct i40e_vf *vf) +{ + /* If the VF MAC address has been set administratively (via the + * ndo_set_vf_mac command), then deny permission to the VF to + * add/delete unicast MAC addresses, unless the VF is trusted + */ + if (vf->pf_set_mac && !vf->trusted) + return false; + + return true; +} + #define I40E_MAX_MACVLAN_PER_HW 3072 #define I40E_MAX_MACVLAN_PER_PF(num_ports) (I40E_MAX_MACVLAN_PER_HW / \ (num_ports)) @@ -2905,8 +2921,8 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf, * The VF may request to set the MAC address filter already * assigned to it so do not return an error in that case. */ - if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps) && - !is_multicast_ether_addr(addr) && vf->pf_set_mac && + if (!i40e_can_vf_change_mac(vf) && + !is_multicast_ether_addr(addr) && !ether_addr_equal(addr, vf->default_lan_addr.addr)) { dev_err(&pf->pdev->dev, "VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n"); @@ -3049,19 +3065,30 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) ret = I40E_ERR_INVALID_MAC_ADDR; goto error_param; } - if (ether_addr_equal(al->list[i].addr, vf->default_lan_addr.addr)) - was_unimac_deleted = true; } vsi = pf->vsi[vf->lan_vsi_idx]; spin_lock_bh(&vsi->mac_filter_hash_lock); /* delete addresses from the list */ - for (i = 0; i < al->num_elements; i++) + for (i = 0; i < al->num_elements; i++) { + const u8 *addr = al->list[i].addr; + + /* Allow to delete VF primary MAC only if it was not set + * administratively by PF or if VF is trusted. + */ + if (ether_addr_equal(addr, vf->default_lan_addr.addr)) { + if (i40e_can_vf_change_mac(vf)) + was_unimac_deleted = true; + else + continue; + } + if (i40e_del_mac_filter(vsi, al->list[i].addr)) { ret = I40E_ERR_INVALID_MAC_ADDR; spin_unlock_bh(&vsi->mac_filter_hash_lock); goto error_param; } + } spin_unlock_bh(&vsi->mac_filter_hash_lock); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index b9c4b311cd6251c1617bc45a8b5bf7f861542d41..53b9fe35d803510e69aca0b6c281e41bfa5c7036 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3631,6 +3631,34 @@ static void iavf_del_all_cloud_filters(struct iavf_adapter *adapter) spin_unlock_bh(&adapter->cloud_filter_list_lock); } +/** + * iavf_is_tc_config_same - Compare the mqprio TC config with the + * TC config already configured on this adapter. + * @adapter: board private structure + * @mqprio_qopt: TC config received from kernel. + * + * This function compares the TC config received from the kernel + * with the config already configured on the adapter. + * + * Return: True if configuration is same, false otherwise. + **/ +static bool iavf_is_tc_config_same(struct iavf_adapter *adapter, + struct tc_mqprio_qopt *mqprio_qopt) +{ + struct virtchnl_channel_info *ch = &adapter->ch_config.ch_info[0]; + int i; + + if (adapter->num_tc != mqprio_qopt->num_tc) + return false; + + for (i = 0; i < adapter->num_tc; i++) { + if (ch[i].count != mqprio_qopt->count[i] || + ch[i].offset != mqprio_qopt->offset[i]) + return false; + } + return true; +} + /** * __iavf_setup_tc - configure multiple traffic classes * @netdev: network interface device structure @@ -3688,7 +3716,7 @@ static int __iavf_setup_tc(struct net_device *netdev, void *type_data) if (ret) return ret; /* Return if same TC config is requested */ - if (adapter->num_tc == num_tc) + if (iavf_is_tc_config_same(adapter, &mqprio_qopt->qopt)) return 0; adapter->num_tc = num_tc; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index ab46cfca4028d703f16643ce03aa693f357ade58..3117f65253b37edf3452a1785c3eabb6ca99b564 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -7681,6 +7681,8 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, pf_sw = pf->first_sw; /* find the attribute in the netlink message */ br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (!br_spec) + return -EINVAL; nla_for_each_nested(attr, br_spec, rem) { __u16 mode; diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index 652ef09eeb3050f1bfa670184cc617950a3b3448..ec6628aacc13b49fb786842103b1894b0d35730d 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -663,7 +663,7 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) int ret; int i; - if (!flags || (flags & ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT)) { + if (flags & ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT) { NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported encap field(s)"); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 6c03ebf81ffdaacdf628273936c0e59486d485a8..42d8e5e771b7e05d6ad3b0ae28c600b1672e0f90 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -440,7 +440,6 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vf->driver_caps = *(u32 *)msg; else vf->driver_caps = VIRTCHNL_VF_OFFLOAD_L2 | - VIRTCHNL_VF_OFFLOAD_RSS_REG | VIRTCHNL_VF_OFFLOAD_VLAN; vfres->vf_cap_flags = VIRTCHNL_VF_OFFLOAD_L2; @@ -453,14 +452,8 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vfres->vf_cap_flags |= ice_vc_get_vlan_caps(hw, vf, vsi, vf->driver_caps); - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) { + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PF; - } else { - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_AQ) - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_AQ; - else - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_REG; - } if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_FDIR_PF) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_FDIR_PF; @@ -500,7 +493,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vfres->rss_lut_size = ICE_VSIQF_HLUT_ARRAY_SIZE; vfres->max_mtu = ice_vc_get_max_frame_size(vf); - vfres->vsi_res[0].vsi_id = vf->lan_vsi_num; + vfres->vsi_res[0].vsi_id = ICE_VF_VSI_ID; vfres->vsi_res[0].vsi_type = VIRTCHNL_VSI_SRIOV; vfres->vsi_res[0].num_queue_pairs = vsi->num_txq; ether_addr_copy(vfres->vsi_res[0].default_mac_addr, @@ -546,27 +539,20 @@ static void ice_vc_reset_vf_msg(struct ice_vf *vf) */ bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id) { - struct ice_pf *pf = vf->pf; - struct ice_vsi *vsi; - - vsi = ice_find_vsi(pf, vsi_id); - - return (vsi && (vsi->vf == vf)); + return vsi_id == ICE_VF_VSI_ID; } /** * ice_vc_isvalid_q_id - * @vf: pointer to the VF info - * @vsi_id: VSI ID + * @vsi: VSI to check queue ID against * @qid: VSI relative queue ID * * check for the valid queue ID */ -static bool ice_vc_isvalid_q_id(struct ice_vf *vf, u16 vsi_id, u8 qid) +static bool ice_vc_isvalid_q_id(struct ice_vsi *vsi, u8 qid) { - struct ice_vsi *vsi = ice_find_vsi(vf->pf, vsi_id); /* allocated Tx and Rx queues should be always equal for VF VSI */ - return (vsi && (qid < vsi->alloc_txq)); + return qid < vsi->alloc_txq; } /** @@ -1266,7 +1252,7 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) */ q_map = vqs->rx_queues; for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -1288,7 +1274,7 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) q_map = vqs->tx_queues; for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -1393,7 +1379,7 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) q_map = vqs->tx_queues; for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -1419,7 +1405,7 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) bitmap_zero(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF); } else if (q_map) { for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -1475,7 +1461,7 @@ ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi, u16 vector_id, for_each_set_bit(vsi_q_id_idx, &qmap, ICE_MAX_RSS_QS_PER_VF) { vsi_q_id = vsi_q_id_idx; - if (!ice_vc_isvalid_q_id(vf, vsi->vsi_num, vsi_q_id)) + if (!ice_vc_isvalid_q_id(vsi, vsi_q_id)) return VIRTCHNL_STATUS_ERR_PARAM; q_vector->num_ring_rx++; @@ -1489,7 +1475,7 @@ ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi, u16 vector_id, for_each_set_bit(vsi_q_id_idx, &qmap, ICE_MAX_RSS_QS_PER_VF) { vsi_q_id = vsi_q_id_idx; - if (!ice_vc_isvalid_q_id(vf, vsi->vsi_num, vsi_q_id)) + if (!ice_vc_isvalid_q_id(vsi, vsi_q_id)) return VIRTCHNL_STATUS_ERR_PARAM; q_vector->num_ring_tx++; @@ -1623,7 +1609,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) qpi->txq.headwb_enabled || !ice_vc_isvalid_ring_len(qpi->txq.ring_len) || !ice_vc_isvalid_ring_len(qpi->rxq.ring_len) || - !ice_vc_isvalid_q_id(vf, qci->vsi_id, qpi->txq.queue_id)) { + !ice_vc_isvalid_q_id(vsi, qpi->txq.queue_id)) { goto error_param; } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.h b/drivers/net/ethernet/intel/ice/ice_virtchnl.h index b5a3fd8adbb4e4123bc213fbc8ce398525d04881..6073d3b2d2d65c28fa705d4ef09af56704fe867d 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.h @@ -18,6 +18,15 @@ */ #define ICE_MAX_MACADDR_PER_VF 18 +/* VFs only get a single VSI. For ice hardware, the VF does not need to know + * its VSI index. However, the virtchnl interface requires a VSI number, + * mainly due to legacy hardware. + * + * Since the VF doesn't need this information, report a static value to the VF + * instead of leaking any information about the PF or hardware setup. + */ +#define ICE_VF_VSI_ID 1 + struct ice_virtchnl_ops { int (*get_ver_msg)(struct ice_vf *vf, u8 *msg); int (*get_vf_res_msg)(struct ice_vf *vf, u8 *msg); diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c index 5a82216e7d034eb7020c104daeccc873ca50b446..63e83e8b97e55b16aa7c1ec0ede0b14cb56e6259 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c @@ -13,8 +13,6 @@ * - opcodes needed by VF when caps are activated * * Caps that don't use new opcodes (no opcodes should be allowed): - * - VIRTCHNL_VF_OFFLOAD_RSS_AQ - * - VIRTCHNL_VF_OFFLOAD_RSS_REG * - VIRTCHNL_VF_OFFLOAD_WB_ON_ITR * - VIRTCHNL_VF_OFFLOAD_CRC * - VIRTCHNL_VF_OFFLOAD_RX_POLLING diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c index 7f726040797231e94184072ed80880a964ef6b87..fb8e8569330979bdcbafd6ab6a2f451ea859e547 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -107,9 +107,6 @@ ice_vc_fdir_param_check(struct ice_vf *vf, u16 vsi_id) if (!(vf->driver_caps & VIRTCHNL_VF_OFFLOAD_FDIR_PF)) return -EINVAL; - if (vsi_id != vf->lan_vsi_num) - return -EINVAL; - if (!ice_vc_isvalid_vsi_id(vf, vsi_id)) return -EINVAL; diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 41ee081eb8875f75a1c7d27c0cf96f5807e39992..48cf24709fe32fc28c5c0b8e6b1a1418ffce3984 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -171,6 +171,10 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) return -EBUSY; usleep_range(1000, 2000); } + + ice_qvec_dis_irq(vsi, rx_ring, q_vector); + ice_qvec_toggle_napi(vsi, q_vector, false); + netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); ice_fill_txq_meta(vsi, tx_ring, &txq_meta); @@ -187,13 +191,10 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) if (err) return err; } - ice_qvec_dis_irq(vsi, rx_ring, q_vector); - err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true); if (err) return err; - ice_qvec_toggle_napi(vsi, q_vector, false); ice_qp_clean_rings(vsi, q_idx); ice_qp_reset_stats(vsi, q_idx); @@ -256,11 +257,11 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) if (err) goto free_buf; - clear_bit(ICE_CFG_BUSY, vsi->state); ice_qvec_toggle_napi(vsi, q_vector, true); ice_qvec_ena_irq(vsi, q_vector); netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); + clear_bit(ICE_CFG_BUSY, vsi->state); free_buf: kfree(qg_buf); return err; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 45ce4ed16146e7598b074fc5510cd8a870a76942..81d9a5338be5e136203b42de2480ca4945ba3986 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -6926,44 +6926,31 @@ static void igb_extts(struct igb_adapter *adapter, int tsintr_tt) static void igb_tsync_interrupt(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; - u32 ack = 0, tsicr = rd32(E1000_TSICR); + u32 tsicr = rd32(E1000_TSICR); struct ptp_clock_event event; if (tsicr & TSINTR_SYS_WRAP) { event.type = PTP_CLOCK_PPS; if (adapter->ptp_caps.pps) ptp_clock_event(adapter->ptp_clock, &event); - ack |= TSINTR_SYS_WRAP; } if (tsicr & E1000_TSICR_TXTS) { /* retrieve hardware timestamp */ schedule_work(&adapter->ptp_tx_work); - ack |= E1000_TSICR_TXTS; } - if (tsicr & TSINTR_TT0) { + if (tsicr & TSINTR_TT0) igb_perout(adapter, 0); - ack |= TSINTR_TT0; - } - if (tsicr & TSINTR_TT1) { + if (tsicr & TSINTR_TT1) igb_perout(adapter, 1); - ack |= TSINTR_TT1; - } - if (tsicr & TSINTR_AUTT0) { + if (tsicr & TSINTR_AUTT0) igb_extts(adapter, 0); - ack |= TSINTR_AUTT0; - } - if (tsicr & TSINTR_AUTT1) { + if (tsicr & TSINTR_AUTT1) igb_extts(adapter, 1); - ack |= TSINTR_AUTT1; - } - - /* acknowledge the interrupts */ - wr32(E1000_TSICR, ack); } static irqreturn_t igb_msix_other(int irq, void *data) diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 07171e574e7d7d10d933ac299bafa4c8307b3c13..36e62197fba0bdc7fba1904b4f4afed0134deeb4 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -976,7 +976,7 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter) igb_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval); /* adjust timestamp for the TX latency based on link speed */ - if (adapter->hw.mac.type == e1000_i210) { + if (hw->mac.type == e1000_i210 || hw->mac.type == e1000_i211) { switch (adapter->link_speed) { case SPEED_10: adjust = IGB_I210_TX_LATENCY_10; @@ -1022,6 +1022,7 @@ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, ktime_t *timestamp) { struct igb_adapter *adapter = q_vector->adapter; + struct e1000_hw *hw = &adapter->hw; struct skb_shared_hwtstamps ts; __le64 *regval = (__le64 *)va; int adjust = 0; @@ -1041,7 +1042,7 @@ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, igb_ptp_systim_to_hwtstamp(adapter, &ts, le64_to_cpu(regval[1])); /* adjust timestamp for the RX latency based on link speed */ - if (adapter->hw.mac.type == e1000_i210) { + if (hw->mac.type == e1000_i210 || hw->mac.type == e1000_i211) { switch (adapter->link_speed) { case SPEED_10: adjust = IGB_I210_RX_LATENCY_10; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 4b6f882b380dc6a304244e8d7ef603da068be387..e052f49cc08d7b704a6f09474f06247f2e4d525f 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6330,7 +6330,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, int cpu = smp_processor_id(); struct netdev_queue *nq; struct igc_ring *ring; - int i, drops; + int i, nxmit; if (unlikely(!netif_carrier_ok(dev))) return -ENETDOWN; @@ -6346,16 +6346,15 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, /* Avoid transmit queue timeout since we share it with the slow path */ txq_trans_cond_update(nq); - drops = 0; + nxmit = 0; for (i = 0; i < num_frames; i++) { int err; struct xdp_frame *xdpf = frames[i]; err = igc_xdp_init_tx_descriptor(ring, xdpf); - if (err) { - xdp_return_frame_rx_napi(xdpf); - drops++; - } + if (err) + break; + nxmit++; } if (flags & XDP_XMIT_FLUSH) @@ -6363,7 +6362,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, __netif_tx_unlock(nq); - return num_frames - drops; + return nxmit; } static void igc_trigger_rxtxq_interrupt(struct igc_adapter *adapter, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c index 774de63dd93a605e7d3e82eefca8be57fd21b724..15fc2acffb8716701f27d84e4d800951585c32ee 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -908,7 +908,13 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) goto err_out; } - xs = kzalloc(sizeof(*xs), GFP_KERNEL); + algo = xfrm_aead_get_byname(aes_gcm_name, IXGBE_IPSEC_AUTH_BITS, 1); + if (unlikely(!algo)) { + err = -ENOENT; + goto err_out; + } + + xs = kzalloc(sizeof(*xs), GFP_ATOMIC); if (unlikely(!xs)) { err = -ENOMEM; goto err_out; @@ -924,14 +930,8 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) memcpy(&xs->id.daddr.a4, sam->addr, sizeof(xs->id.daddr.a4)); xs->xso.dev = adapter->netdev; - algo = xfrm_aead_get_byname(aes_gcm_name, IXGBE_IPSEC_AUTH_BITS, 1); - if (unlikely(!algo)) { - err = -ENOENT; - goto err_xs; - } - aead_len = sizeof(*xs->aead) + IXGBE_IPSEC_KEY_BITS / 8; - xs->aead = kzalloc(aead_len, GFP_KERNEL); + xs->aead = kzalloc(aead_len, GFP_ATOMIC); if (unlikely(!xs->aead)) { err = -ENOMEM; goto err_xs; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 6dc554e810a170c03247cf6f1e5f4c2edac46f32..086cc25730338341bcd66d4484b320012d392e7c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2947,8 +2947,8 @@ static void ixgbe_check_lsc(struct ixgbe_adapter *adapter) static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter, u64 qmask) { - u32 mask; struct ixgbe_hw *hw = &adapter->hw; + u32 mask; switch (hw->mac.type) { case ixgbe_mac_82598EB: @@ -10543,6 +10543,44 @@ static void ixgbe_reset_rxr_stats(struct ixgbe_ring *rx_ring) memset(&rx_ring->rx_stats, 0, sizeof(rx_ring->rx_stats)); } +/** + * ixgbe_irq_disable_single - Disable single IRQ vector + * @adapter: adapter structure + * @ring: ring index + **/ +static void ixgbe_irq_disable_single(struct ixgbe_adapter *adapter, u32 ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + u64 qmask = BIT_ULL(ring); + u32 mask; + + switch (adapter->hw.mac.type) { + case ixgbe_mac_82598EB: + mask = qmask & IXGBE_EIMC_RTX_QUEUE; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, mask); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + mask = (qmask & 0xFFFFFFFF); + if (mask) + IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask); + mask = (qmask >> 32); + if (mask) + IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(1), mask); + break; + default: + break; + } + IXGBE_WRITE_FLUSH(&adapter->hw); + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) + synchronize_irq(adapter->msix_entries[ring].vector); + else + synchronize_irq(adapter->pdev->irq); +} + /** * ixgbe_txrx_ring_disable - Disable Rx/Tx/XDP Tx rings * @adapter: adapter structure @@ -10559,6 +10597,11 @@ void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring) tx_ring = adapter->tx_ring[ring]; xdp_ring = adapter->xdp_ring[ring]; + ixgbe_irq_disable_single(adapter, ring); + + /* Rx/Tx/XDP Tx share the same napi context. */ + napi_disable(&rx_ring->q_vector->napi); + ixgbe_disable_txr(adapter, tx_ring); if (xdp_ring) ixgbe_disable_txr(adapter, xdp_ring); @@ -10567,9 +10610,6 @@ void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring) if (xdp_ring) synchronize_rcu(); - /* Rx/Tx/XDP Tx share the same napi context. */ - napi_disable(&rx_ring->q_vector->napi); - ixgbe_clean_tx_ring(tx_ring); if (xdp_ring) ixgbe_clean_tx_ring(xdp_ring); @@ -10597,9 +10637,6 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring) tx_ring = adapter->tx_ring[ring]; xdp_ring = adapter->xdp_ring[ring]; - /* Rx/Tx/XDP Tx share the same napi context. */ - napi_enable(&rx_ring->q_vector->napi); - ixgbe_configure_tx_ring(adapter, tx_ring); if (xdp_ring) ixgbe_configure_tx_ring(adapter, xdp_ring); @@ -10608,6 +10645,11 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring) clear_bit(__IXGBE_TX_DISABLED, &tx_ring->state); if (xdp_ring) clear_bit(__IXGBE_TX_DISABLED, &xdp_ring->state); + + /* Rx/Tx/XDP Tx share the same napi context. */ + napi_enable(&rx_ring->q_vector->napi); + ixgbe_irq_enable_queues(adapter, BIT_ULL(ring)); + IXGBE_WRITE_FLUSH(&adapter->hw); } /** diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index 90be87dc105d3f00363d24c37ed0ef2a4f113855..254cad45a555fd2d93ae571554684e426367ab8e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -814,6 +814,11 @@ static int cgx_lmac_enadis_pause_frm(void *cgxd, int lmac_id, if (!is_lmac_valid(cgx, lmac_id)) return -ENODEV; + cfg = cgx_read(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL); + cfg &= ~CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK; + cfg |= rx_pause ? CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK : 0x0; + cgx_write(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL, cfg); + cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL); cfg &= ~CGX_SMUX_RX_FRM_CTL_CTL_BCK; cfg |= rx_pause ? CGX_SMUX_RX_FRM_CTL_CTL_BCK : 0x0; @@ -1346,7 +1351,7 @@ static irqreturn_t cgx_fwi_event_handler(int irq, void *data) /* Release thread waiting for completion */ lmac->cmd_pend = false; - wake_up_interruptible(&lmac->wq_cmd_cmplt); + wake_up(&lmac->wq_cmd_cmplt); break; case CGX_EVT_ASYNC: if (cgx_event_is_linkevent(event)) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c index 9690ac01f02c8db9b9ed2e524b05aa124b077c7a..7d741e3ba8c514515ae9e51d0e1f465e99c2044e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c @@ -214,11 +214,12 @@ int otx2_mbox_busy_poll_for_rsp(struct otx2_mbox *mbox, int devid) } EXPORT_SYMBOL(otx2_mbox_busy_poll_for_rsp); -void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid) +static void otx2_mbox_msg_send_data(struct otx2_mbox *mbox, int devid, u64 data) { struct otx2_mbox_dev *mdev = &mbox->dev[devid]; struct mbox_hdr *tx_hdr, *rx_hdr; void *hw_mbase = mdev->hwbase; + u64 intr_val; tx_hdr = hw_mbase + mbox->tx_start; rx_hdr = hw_mbase + mbox->rx_start; @@ -254,14 +255,52 @@ void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid) spin_unlock(&mdev->mbox_lock); + /* Check if interrupt pending */ + intr_val = readq((void __iomem *)mbox->reg_base + + (mbox->trigger | (devid << mbox->tr_shift))); + + intr_val |= data; /* The interrupt should be fired after num_msgs is written * to the shared memory */ - writeq(1, (void __iomem *)mbox->reg_base + + writeq(intr_val, (void __iomem *)mbox->reg_base + (mbox->trigger | (devid << mbox->tr_shift))); } + +void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid) +{ + otx2_mbox_msg_send_data(mbox, devid, MBOX_DOWN_MSG); +} EXPORT_SYMBOL(otx2_mbox_msg_send); +void otx2_mbox_msg_send_up(struct otx2_mbox *mbox, int devid) +{ + otx2_mbox_msg_send_data(mbox, devid, MBOX_UP_MSG); +} +EXPORT_SYMBOL(otx2_mbox_msg_send_up); + +bool otx2_mbox_wait_for_zero(struct otx2_mbox *mbox, int devid) +{ + u64 data; + + data = readq((void __iomem *)mbox->reg_base + + (mbox->trigger | (devid << mbox->tr_shift))); + + /* If data is non-zero wait for ~1ms and return to caller + * whether data has changed to zero or not after the wait. + */ + if (!data) + return true; + + usleep_range(950, 1000); + + data = readq((void __iomem *)mbox->reg_base + + (mbox->trigger | (devid << mbox->tr_shift))); + + return data == 0; +} +EXPORT_SYMBOL(otx2_mbox_wait_for_zero); + struct mbox_msghdr *otx2_mbox_alloc_msg_rsp(struct otx2_mbox *mbox, int devid, int size, int size_rsp) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 03ebabd61635383f1723e046da0a476f29c732ea..be70269e91684fb3aac31abe80a87343bde0c0c3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -16,6 +16,9 @@ #define MBOX_SIZE SZ_64K +#define MBOX_DOWN_MSG 1 +#define MBOX_UP_MSG 2 + /* AF/PF: PF initiated, PF/VF VF initiated */ #define MBOX_DOWN_RX_START 0 #define MBOX_DOWN_RX_SIZE (46 * SZ_1K) @@ -101,6 +104,7 @@ int otx2_mbox_regions_init(struct otx2_mbox *mbox, void __force **hwbase, struct pci_dev *pdev, void __force *reg_base, int direction, int ndevs, unsigned long *bmap); void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid); +void otx2_mbox_msg_send_up(struct otx2_mbox *mbox, int devid); int otx2_mbox_wait_for_rsp(struct otx2_mbox *mbox, int devid); int otx2_mbox_busy_poll_for_rsp(struct otx2_mbox *mbox, int devid); struct mbox_msghdr *otx2_mbox_alloc_msg_rsp(struct otx2_mbox *mbox, int devid, @@ -118,6 +122,8 @@ static inline struct mbox_msghdr *otx2_mbox_alloc_msg(struct otx2_mbox *mbox, return otx2_mbox_alloc_msg_rsp(mbox, devid, size, 0); } +bool otx2_mbox_wait_for_zero(struct otx2_mbox *mbox, int devid); + /* Mailbox message types */ #define MBOX_MSG_MASK 0xFFFF #define MBOX_MSG_INVALID 0xFFFE @@ -196,6 +202,9 @@ M(CPT_STATS, 0xA05, cpt_sts, cpt_sts_req, cpt_sts_rsp) \ M(CPT_RXC_TIME_CFG, 0xA06, cpt_rxc_time_cfg, cpt_rxc_time_cfg_req, \ msg_rsp) \ M(CPT_CTX_CACHE_SYNC, 0xA07, cpt_ctx_cache_sync, msg_req, msg_rsp) \ +M(CPT_LF_RESET, 0xA08, cpt_lf_reset, cpt_lf_rst_req, msg_rsp) \ +M(CPT_FLT_ENG_INFO, 0xA09, cpt_flt_eng_info, cpt_flt_eng_info_req, \ + cpt_flt_eng_info_rsp) \ /* SDP mbox IDs (range 0x1000 - 0x11FF) */ \ M(SET_SDP_CHAN_INFO, 0x1000, set_sdp_chan_info, sdp_chan_info_msg, msg_rsp) \ M(GET_SDP_CHAN_INFO, 0x1001, get_sdp_chan_info, msg_req, sdp_get_chan_info_msg) \ @@ -1702,6 +1711,28 @@ struct cpt_inst_lmtst_req { u64 rsvd; }; +/* Mailbox message format to request for CPT LF reset */ +struct cpt_lf_rst_req { + struct mbox_msghdr hdr; + u32 slot; + u32 rsvd; +}; + +/* Mailbox message format to request for CPT faulted engines */ +struct cpt_flt_eng_info_req { + struct mbox_msghdr hdr; + int blkaddr; + bool reset; + u32 rsvd; +}; + +struct cpt_flt_eng_info_rsp { + struct mbox_msghdr hdr; + u64 flt_eng_map[CPT_10K_AF_INT_VEC_RVU]; + u64 rcvrd_eng_map[CPT_10K_AF_INT_VEC_RVU]; + u64 rsvd; +}; + struct sdp_node_info { /* Node to which this PF belons to */ u8 node_id; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c index dfd23580e3b8e1fc88e3597e3eaf04832ad18dc7..d39d86e694ccf7530237a904315a294726cf55f8 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c @@ -121,13 +121,17 @@ int mcs_add_intr_wq_entry(struct mcs *mcs, struct mcs_intr_event *event) static int mcs_notify_pfvf(struct mcs_intr_event *event, struct rvu *rvu) { struct mcs_intr_info *req; - int err, pf; + int pf; pf = rvu_get_pf(event->pcifunc); + mutex_lock(&rvu->mbox_lock); + req = otx2_mbox_alloc_msg_mcs_intr_notify(rvu, pf); - if (!req) + if (!req) { + mutex_unlock(&rvu->mbox_lock); return -ENOMEM; + } req->mcs_id = event->mcs_id; req->intr_mask = event->intr_mask; @@ -135,10 +139,11 @@ static int mcs_notify_pfvf(struct mcs_intr_event *event, struct rvu *rvu) req->hdr.pcifunc = event->pcifunc; req->lmac_id = event->lmac_id; - otx2_mbox_msg_send(&rvu->afpf_wq_info.mbox_up, pf); - err = otx2_mbox_wait_for_rsp(&rvu->afpf_wq_info.mbox_up, pf); - if (err) - dev_warn(rvu->dev, "MCS notification to pf %d failed\n", pf); + otx2_mbox_wait_for_zero(&rvu->afpf_wq_info.mbox_up, pf); + + otx2_mbox_msg_send_up(&rvu->afpf_wq_info.mbox_up, pf); + + mutex_unlock(&rvu->mbox_lock); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index d88d86bf07b03dc964b4e91a6a15a7b56c99b377..a7034b47ed6c959f9e354a6838c39df1ad0fa5ef 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -1164,8 +1164,16 @@ cpt: goto nix_err; } + err = rvu_cpt_init(rvu); + if (err) { + dev_err(rvu->dev, "%s: Failed to initialize cpt\n", __func__); + goto mcs_err; + } + return 0; +mcs_err: + rvu_mcs_exit(rvu); nix_err: rvu_nix_freemem(rvu); npa_err: @@ -2106,7 +2114,7 @@ bad_message: } } -static void __rvu_mbox_handler(struct rvu_work *mwork, int type) +static void __rvu_mbox_handler(struct rvu_work *mwork, int type, bool poll) { struct rvu *rvu = mwork->rvu; int offset, err, id, devid; @@ -2173,6 +2181,9 @@ static void __rvu_mbox_handler(struct rvu_work *mwork, int type) } mw->mbox_wrk[devid].num_msgs = 0; + if (poll) + otx2_mbox_wait_for_zero(mbox, devid); + /* Send mbox responses to VF/PF */ otx2_mbox_msg_send(mbox, devid); } @@ -2180,15 +2191,18 @@ static void __rvu_mbox_handler(struct rvu_work *mwork, int type) static inline void rvu_afpf_mbox_handler(struct work_struct *work) { struct rvu_work *mwork = container_of(work, struct rvu_work, work); + struct rvu *rvu = mwork->rvu; - __rvu_mbox_handler(mwork, TYPE_AFPF); + mutex_lock(&rvu->mbox_lock); + __rvu_mbox_handler(mwork, TYPE_AFPF, true); + mutex_unlock(&rvu->mbox_lock); } static inline void rvu_afvf_mbox_handler(struct work_struct *work) { struct rvu_work *mwork = container_of(work, struct rvu_work, work); - __rvu_mbox_handler(mwork, TYPE_AFVF); + __rvu_mbox_handler(mwork, TYPE_AFVF, false); } static void __rvu_mbox_up_handler(struct rvu_work *mwork, int type) @@ -2363,6 +2377,8 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw, } } + mutex_init(&rvu->mbox_lock); + mbox_regions = kcalloc(num, sizeof(void *), GFP_KERNEL); if (!mbox_regions) { err = -ENOMEM; @@ -2512,10 +2528,9 @@ static void rvu_queue_work(struct mbox_wq_info *mw, int first, } } -static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq) +static irqreturn_t rvu_mbox_pf_intr_handler(int irq, void *rvu_irq) { struct rvu *rvu = (struct rvu *)rvu_irq; - int vfs = rvu->vfs; u64 intr; intr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT); @@ -2529,6 +2544,18 @@ static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq) rvu_queue_work(&rvu->afpf_wq_info, 0, rvu->hw->total_pfs, intr); + return IRQ_HANDLED; +} + +static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq) +{ + struct rvu *rvu = (struct rvu *)rvu_irq; + int vfs = rvu->vfs; + u64 intr; + + /* Sync with mbox memory region */ + rmb(); + /* Handle VF interrupts */ if (vfs > 64) { intr = rvupf_read64(rvu, RVU_PF_VFPF_MBOX_INTX(1)); @@ -2865,7 +2892,7 @@ static int rvu_register_interrupts(struct rvu *rvu) /* Register mailbox interrupt handler */ sprintf(&rvu->irq_name[RVU_AF_INT_VEC_MBOX * NAME_SIZE], "RVUAF Mbox"); ret = request_irq(pci_irq_vector(rvu->pdev, RVU_AF_INT_VEC_MBOX), - rvu_mbox_intr_handler, 0, + rvu_mbox_pf_intr_handler, 0, &rvu->irq_name[RVU_AF_INT_VEC_MBOX * NAME_SIZE], rvu); if (ret) { dev_err(rvu->dev, @@ -3039,9 +3066,8 @@ static int rvu_flr_init(struct rvu *rvu) cfg | BIT_ULL(22)); } - rvu->flr_wq = alloc_workqueue("rvu_afpf_flr", - WQ_UNBOUND | WQ_HIGHPRI | WQ_MEM_RECLAIM, - 1); + rvu->flr_wq = alloc_ordered_workqueue("rvu_afpf_flr", + WQ_HIGHPRI | WQ_MEM_RECLAIM); if (!rvu->flr_wq) return -ENOMEM; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 0b76dfa979d4e4c761c5ad913e82fffa68fe065b..a3ae21398ca74e050ceccf0055acb3d871a1e813 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -109,6 +109,8 @@ struct rvu_block { u64 lfreset_reg; unsigned char name[NAME_SIZE]; struct rvu *rvu; + u64 cpt_flt_eng_map[3]; + u64 cpt_rcvrd_eng_map[3]; }; struct nix_mcast { @@ -506,6 +508,7 @@ struct rvu { struct ptp *ptp; int mcs_blk_cnt; + int cpt_pf_num; #ifdef CONFIG_DEBUG_FS struct rvu_debugfs rvu_dbg; @@ -520,6 +523,10 @@ struct rvu { struct list_head mcs_intrq_head; /* mcs interrupt queue lock */ spinlock_t mcs_intrq_lock; + /* CPT interrupt lock */ + spinlock_t cpt_intr_lock; + + struct mutex mbox_lock; /* Serialize mbox up and down msgs */ }; static inline void rvu_write64(struct rvu *rvu, u64 block, u64 offset, u64 val) @@ -872,6 +879,7 @@ void rvu_cpt_unregister_interrupts(struct rvu *rvu); int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf, int slot); int rvu_cpt_ctx_flush(struct rvu *rvu, u16 pcifunc); +int rvu_cpt_init(struct rvu *rvu); #define NDC_AF_BANK_MASK GENMASK_ULL(7, 0) #define NDC_AF_BANK_LINE_MASK GENMASK_ULL(31, 16) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index bcb4385d0621cda3a0e9ba6845e51cfe35069c9f..cc6d6c94f4002e068112126df064a920e82ee0c3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -160,6 +160,8 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu) continue; lmac_bmap = cgx_get_lmac_bmap(rvu_cgx_pdata(cgx, rvu)); for_each_set_bit(iter, &lmac_bmap, rvu->hw->lmac_per_cgx) { + if (iter >= MAX_LMAC_COUNT) + continue; lmac = cgx_get_lmacid(rvu_cgx_pdata(cgx, rvu), iter); rvu->pf2cgxlmac_map[pf] = cgxlmac_id_to_bmap(cgx, lmac); @@ -232,7 +234,7 @@ static void cgx_notify_pfs(struct cgx_link_event *event, struct rvu *rvu) struct cgx_link_user_info *linfo; struct cgx_link_info_msg *msg; unsigned long pfmap; - int err, pfid; + int pfid; linfo = &event->link_uinfo; pfmap = cgxlmac_to_pfmap(rvu, event->cgx_id, event->lmac_id); @@ -250,16 +252,22 @@ static void cgx_notify_pfs(struct cgx_link_event *event, struct rvu *rvu) continue; } + mutex_lock(&rvu->mbox_lock); + /* Send mbox message to PF */ msg = otx2_mbox_alloc_msg_cgx_link_event(rvu, pfid); - if (!msg) + if (!msg) { + mutex_unlock(&rvu->mbox_lock); continue; + } + msg->link_info = *linfo; - otx2_mbox_msg_send(&rvu->afpf_wq_info.mbox_up, pfid); - err = otx2_mbox_wait_for_rsp(&rvu->afpf_wq_info.mbox_up, pfid); - if (err) - dev_warn(rvu->dev, "notification to pf %d failed\n", - pfid); + + otx2_mbox_wait_for_zero(&rvu->afpf_wq_info.mbox_up, pfid); + + otx2_mbox_msg_send_up(&rvu->afpf_wq_info.mbox_up, pfid); + + mutex_unlock(&rvu->mbox_lock); } while (pfmap); } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c index 38bbae5d9ae05282e8448715a1ff42df2dbeccb3..6fb02b93c17185499f80b7b91e7593e51360e247 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c @@ -37,34 +37,68 @@ (_rsp)->free_sts_##etype = free_sts; \ }) -static irqreturn_t rvu_cpt_af_flt_intr_handler(int irq, void *ptr) +static irqreturn_t cpt_af_flt_intr_handler(int vec, void *ptr) { struct rvu_block *block = ptr; struct rvu *rvu = block->rvu; int blkaddr = block->addr; - u64 reg0, reg1, reg2; - - reg0 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(0)); - reg1 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(1)); - if (!is_rvu_otx2(rvu)) { - reg2 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(2)); - dev_err_ratelimited(rvu->dev, - "Received CPTAF FLT irq : 0x%llx, 0x%llx, 0x%llx", - reg0, reg1, reg2); - } else { - dev_err_ratelimited(rvu->dev, - "Received CPTAF FLT irq : 0x%llx, 0x%llx", - reg0, reg1); + u64 reg, val; + int i, eng; + u8 grp; + + reg = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(vec)); + dev_err_ratelimited(rvu->dev, "Received CPTAF FLT%d irq : 0x%llx", vec, reg); + + i = -1; + while ((i = find_next_bit((unsigned long *)®, 64, i + 1)) < 64) { + switch (vec) { + case 0: + eng = i; + break; + case 1: + eng = i + 64; + break; + case 2: + eng = i + 128; + break; + } + grp = rvu_read64(rvu, blkaddr, CPT_AF_EXEX_CTL2(eng)) & 0xFF; + /* Disable and enable the engine which triggers fault */ + rvu_write64(rvu, blkaddr, CPT_AF_EXEX_CTL2(eng), 0x0); + val = rvu_read64(rvu, blkaddr, CPT_AF_EXEX_CTL(eng)); + rvu_write64(rvu, blkaddr, CPT_AF_EXEX_CTL(eng), val & ~1ULL); + + rvu_write64(rvu, blkaddr, CPT_AF_EXEX_CTL2(eng), grp); + rvu_write64(rvu, blkaddr, CPT_AF_EXEX_CTL(eng), val | 1ULL); + + spin_lock(&rvu->cpt_intr_lock); + block->cpt_flt_eng_map[vec] |= BIT_ULL(i); + val = rvu_read64(rvu, blkaddr, CPT_AF_EXEX_STS(eng)); + val = val & 0x3; + if (val == 0x1 || val == 0x2) + block->cpt_rcvrd_eng_map[vec] |= BIT_ULL(i); + spin_unlock(&rvu->cpt_intr_lock); } - - rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(0), reg0); - rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(1), reg1); - if (!is_rvu_otx2(rvu)) - rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(2), reg2); + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(vec), reg); return IRQ_HANDLED; } +static irqreturn_t rvu_cpt_af_flt0_intr_handler(int irq, void *ptr) +{ + return cpt_af_flt_intr_handler(CPT_AF_INT_VEC_FLT0, ptr); +} + +static irqreturn_t rvu_cpt_af_flt1_intr_handler(int irq, void *ptr) +{ + return cpt_af_flt_intr_handler(CPT_AF_INT_VEC_FLT1, ptr); +} + +static irqreturn_t rvu_cpt_af_flt2_intr_handler(int irq, void *ptr) +{ + return cpt_af_flt_intr_handler(CPT_10K_AF_INT_VEC_FLT2, ptr); +} + static irqreturn_t rvu_cpt_af_rvu_intr_handler(int irq, void *ptr) { struct rvu_block *block = ptr; @@ -119,8 +153,10 @@ static void cpt_10k_unregister_interrupts(struct rvu_block *block, int off) int i; /* Disable all CPT AF interrupts */ - for (i = 0; i < CPT_10K_AF_INT_VEC_RVU; i++) - rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(i), 0x1); + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(0), ~0ULL); + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(1), ~0ULL); + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(2), 0xFFFF); + rvu_write64(rvu, blkaddr, CPT_AF_RVU_INT_ENA_W1C, 0x1); rvu_write64(rvu, blkaddr, CPT_AF_RAS_INT_ENA_W1C, 0x1); @@ -151,7 +187,7 @@ static void cpt_unregister_interrupts(struct rvu *rvu, int blkaddr) /* Disable all CPT AF interrupts */ for (i = 0; i < CPT_AF_INT_VEC_RVU; i++) - rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(i), 0x1); + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(i), ~0ULL); rvu_write64(rvu, blkaddr, CPT_AF_RVU_INT_ENA_W1C, 0x1); rvu_write64(rvu, blkaddr, CPT_AF_RAS_INT_ENA_W1C, 0x1); @@ -172,16 +208,31 @@ static int cpt_10k_register_interrupts(struct rvu_block *block, int off) { struct rvu *rvu = block->rvu; int blkaddr = block->addr; + irq_handler_t flt_fn; int i, ret; for (i = CPT_10K_AF_INT_VEC_FLT0; i < CPT_10K_AF_INT_VEC_RVU; i++) { sprintf(&rvu->irq_name[(off + i) * NAME_SIZE], "CPTAF FLT%d", i); + + switch (i) { + case CPT_10K_AF_INT_VEC_FLT0: + flt_fn = rvu_cpt_af_flt0_intr_handler; + break; + case CPT_10K_AF_INT_VEC_FLT1: + flt_fn = rvu_cpt_af_flt1_intr_handler; + break; + case CPT_10K_AF_INT_VEC_FLT2: + flt_fn = rvu_cpt_af_flt2_intr_handler; + break; + } ret = rvu_cpt_do_register_interrupt(block, off + i, - rvu_cpt_af_flt_intr_handler, - &rvu->irq_name[(off + i) * NAME_SIZE]); + flt_fn, &rvu->irq_name[(off + i) * NAME_SIZE]); if (ret) goto err; - rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), 0x1); + if (i == CPT_10K_AF_INT_VEC_FLT2) + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), 0xFFFF); + else + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), ~0ULL); } ret = rvu_cpt_do_register_interrupt(block, off + CPT_10K_AF_INT_VEC_RVU, @@ -208,8 +259,8 @@ static int cpt_register_interrupts(struct rvu *rvu, int blkaddr) { struct rvu_hwinfo *hw = rvu->hw; struct rvu_block *block; + irq_handler_t flt_fn; int i, offs, ret = 0; - char irq_name[16]; if (!is_block_implemented(rvu->hw, blkaddr)) return 0; @@ -226,13 +277,20 @@ static int cpt_register_interrupts(struct rvu *rvu, int blkaddr) return cpt_10k_register_interrupts(block, offs); for (i = CPT_AF_INT_VEC_FLT0; i < CPT_AF_INT_VEC_RVU; i++) { - snprintf(irq_name, sizeof(irq_name), "CPTAF FLT%d", i); + sprintf(&rvu->irq_name[(offs + i) * NAME_SIZE], "CPTAF FLT%d", i); + switch (i) { + case CPT_AF_INT_VEC_FLT0: + flt_fn = rvu_cpt_af_flt0_intr_handler; + break; + case CPT_AF_INT_VEC_FLT1: + flt_fn = rvu_cpt_af_flt1_intr_handler; + break; + } ret = rvu_cpt_do_register_interrupt(block, offs + i, - rvu_cpt_af_flt_intr_handler, - irq_name); + flt_fn, &rvu->irq_name[(offs + i) * NAME_SIZE]); if (ret) goto err; - rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), 0x1); + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), ~0ULL); } ret = rvu_cpt_do_register_interrupt(block, offs + CPT_AF_INT_VEC_RVU, @@ -290,7 +348,7 @@ static int get_cpt_pf_num(struct rvu *rvu) static bool is_cpt_pf(struct rvu *rvu, u16 pcifunc) { - int cpt_pf_num = get_cpt_pf_num(rvu); + int cpt_pf_num = rvu->cpt_pf_num; if (rvu_get_pf(pcifunc) != cpt_pf_num) return false; @@ -302,7 +360,7 @@ static bool is_cpt_pf(struct rvu *rvu, u16 pcifunc) static bool is_cpt_vf(struct rvu *rvu, u16 pcifunc) { - int cpt_pf_num = get_cpt_pf_num(rvu); + int cpt_pf_num = rvu->cpt_pf_num; if (rvu_get_pf(pcifunc) != cpt_pf_num) return false; @@ -801,6 +859,64 @@ int rvu_mbox_handler_cpt_ctx_cache_sync(struct rvu *rvu, struct msg_req *req, return rvu_cpt_ctx_flush(rvu, req->hdr.pcifunc); } +int rvu_mbox_handler_cpt_lf_reset(struct rvu *rvu, struct cpt_lf_rst_req *req, + struct msg_rsp *rsp) +{ + u16 pcifunc = req->hdr.pcifunc; + struct rvu_block *block; + int cptlf, blkaddr, ret; + u16 actual_slot; + u64 ctl, ctl2; + + blkaddr = rvu_get_blkaddr_from_slot(rvu, BLKTYPE_CPT, pcifunc, + req->slot, &actual_slot); + if (blkaddr < 0) + return CPT_AF_ERR_LF_INVALID; + + block = &rvu->hw->block[blkaddr]; + + cptlf = rvu_get_lf(rvu, block, pcifunc, actual_slot); + if (cptlf < 0) + return CPT_AF_ERR_LF_INVALID; + ctl = rvu_read64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf)); + ctl2 = rvu_read64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf)); + + ret = rvu_lf_reset(rvu, block, cptlf); + if (ret) + dev_err(rvu->dev, "Failed to reset blkaddr %d LF%d\n", + block->addr, cptlf); + + rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf), ctl); + rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf), ctl2); + + return 0; +} + +int rvu_mbox_handler_cpt_flt_eng_info(struct rvu *rvu, struct cpt_flt_eng_info_req *req, + struct cpt_flt_eng_info_rsp *rsp) +{ + struct rvu_block *block; + unsigned long flags; + int blkaddr, vec; + + blkaddr = validate_and_get_cpt_blkaddr(req->blkaddr); + if (blkaddr < 0) + return blkaddr; + + block = &rvu->hw->block[blkaddr]; + for (vec = 0; vec < CPT_10K_AF_INT_VEC_RVU; vec++) { + spin_lock_irqsave(&rvu->cpt_intr_lock, flags); + rsp->flt_eng_map[vec] = block->cpt_flt_eng_map[vec]; + rsp->rcvrd_eng_map[vec] = block->cpt_rcvrd_eng_map[vec]; + if (req->reset) { + block->cpt_flt_eng_map[vec] = 0x0; + block->cpt_rcvrd_eng_map[vec] = 0x0; + } + spin_unlock_irqrestore(&rvu->cpt_intr_lock, flags); + } + return 0; +} + static void cpt_rxc_teardown(struct rvu *rvu, int blkaddr) { struct cpt_rxc_time_cfg_req req; @@ -940,7 +1056,7 @@ int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf, int s static int cpt_inline_inb_lf_cmd_send(struct rvu *rvu, int blkaddr, int nix_blkaddr) { - int cpt_pf_num = get_cpt_pf_num(rvu); + int cpt_pf_num = rvu->cpt_pf_num; struct cpt_inst_lmtst_req *req; dma_addr_t res_daddr; int timeout = 3000; @@ -1084,3 +1200,12 @@ unlock: return 0; } + +int rvu_cpt_init(struct rvu *rvu) +{ + /* Retrieve CPT PF number */ + rvu->cpt_pf_num = get_cpt_pf_num(rvu); + spin_lock_init(&rvu->cpt_intr_lock); + + return 0; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index cc5d342e026c7ab2cfe2056ca3bff30466b874a5..a3c1d82032f55a3d590575be1b520226e8de5560 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -999,12 +999,10 @@ static ssize_t rvu_dbg_qsize_write(struct file *filp, u16 pcifunc; int ret, lf; - cmd_buf = memdup_user(buffer, count + 1); + cmd_buf = memdup_user_nul(buffer, count); if (IS_ERR(cmd_buf)) return -ENOMEM; - cmd_buf[count] = '\0'; - cmd_buf_tmp = strchr(cmd_buf, '\n'); if (cmd_buf_tmp) { *cmd_buf_tmp = '\0'; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index bb99302eab67ae87a391ca4b2f2a32516b468a57..67080d5053e078ce49ee57241018be0ca17621fd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -4237,18 +4237,18 @@ static int rvu_nix_block_init(struct rvu *rvu, struct nix_hw *nix_hw) */ rvu_write64(rvu, blkaddr, NIX_AF_CFG, rvu_read64(rvu, blkaddr, NIX_AF_CFG) | 0x40ULL); + } - /* Set chan/link to backpressure TL3 instead of TL2 */ - rvu_write64(rvu, blkaddr, NIX_AF_PSE_CHANNEL_LEVEL, 0x01); + /* Set chan/link to backpressure TL3 instead of TL2 */ + rvu_write64(rvu, blkaddr, NIX_AF_PSE_CHANNEL_LEVEL, 0x01); - /* Disable SQ manager's sticky mode operation (set TM6 = 0) - * This sticky mode is known to cause SQ stalls when multiple - * SQs are mapped to same SMQ and transmitting pkts at a time. - */ - cfg = rvu_read64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS); - cfg &= ~BIT_ULL(15); - rvu_write64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS, cfg); - } + /* Disable SQ manager's sticky mode operation (set TM6 = 0) + * This sticky mode is known to cause SQ stalls when multiple + * SQs are mapped to same SMQ and transmitting pkts at a time. + */ + cfg = rvu_read64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS); + cfg &= ~BIT_ULL(15); + rvu_write64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS, cfg); ltdefs = rvu->kpu.lt_def; /* Calibrate X2P bus to check if CGX/LBK links are fine */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 3784347b6fd883023ca5962ee6a51768c8beab4b..91a4ea529d0775ea482a19721d9bef54aae99e7f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -437,6 +437,10 @@ static void npc_fixup_vf_rule(struct rvu *rvu, struct npc_mcam *mcam, return; } + /* AF modifies given action iff PF/VF has requested for it */ + if ((entry->action & 0xFULL) != NIX_RX_ACTION_DEFAULT) + return; + /* copy VF default entry action to the VF mcam entry */ rx_action = npc_get_default_entry_action(rvu, mcam, blkaddr, target_func); @@ -1665,7 +1669,7 @@ static int npc_fwdb_detect_load_prfl_img(struct rvu *rvu, uint64_t prfl_sz, struct npc_coalesced_kpu_prfl *img_data = NULL; int i = 0, rc = -EINVAL; void __iomem *kpu_prfl_addr; - u16 offset; + u32 offset; img_data = (struct npc_coalesced_kpu_prfl __force *)rvu->kpu_prfl_addr; if (le64_to_cpu(img_data->signature) == KPU_SIGN && diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 0f896f606c3e66da39728bab6bf179c2f543a3dc..c00d6d67db51875d1878e498f16c37f16ad61285 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -930,8 +930,11 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura) if (pfvf->ptp && qidx < pfvf->hw.tx_queues) { err = qmem_alloc(pfvf->dev, &sq->timestamps, qset->sqe_cnt, sizeof(*sq->timestamps)); - if (err) + if (err) { + kfree(sq->sg); + sq->sg = NULL; return err; + } } sq->head = 0; @@ -947,7 +950,14 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura) sq->stats.bytes = 0; sq->stats.pkts = 0; - return pfvf->hw_ops->sq_aq_init(pfvf, qidx, sqb_aura); + err = pfvf->hw_ops->sq_aq_init(pfvf, qidx, sqb_aura); + if (err) { + kfree(sq->sg); + sq->sg = NULL; + return err; + } + + return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 44950c2542bb7f983e537ec8f5459d722e9c83fa..c15d1864a63719da7207b711d282868d62939ff4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -785,7 +785,7 @@ static inline int otx2_sync_mbox_up_msg(struct mbox *mbox, int devid) if (!otx2_mbox_nonempty(&mbox->mbox_up, devid)) return 0; - otx2_mbox_msg_send(&mbox->mbox_up, devid); + otx2_mbox_msg_send_up(&mbox->mbox_up, devid); err = otx2_mbox_wait_for_rsp(&mbox->mbox_up, devid); if (err) return err; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index a2d8ac6204054dd8ec16c7c453ccad4515b8d7d0..6b7fb324e756e584189190c5ee30a899f03a97ae 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -272,8 +272,7 @@ static int otx2_pf_flr_init(struct otx2_nic *pf, int num_vfs) { int vf; - pf->flr_wq = alloc_workqueue("otx2_pf_flr_wq", - WQ_UNBOUND | WQ_HIGHPRI, 1); + pf->flr_wq = alloc_ordered_workqueue("otx2_pf_flr_wq", WQ_HIGHPRI); if (!pf->flr_wq) return -ENOMEM; @@ -292,8 +291,8 @@ static int otx2_pf_flr_init(struct otx2_nic *pf, int num_vfs) return 0; } -static void otx2_queue_work(struct mbox *mw, struct workqueue_struct *mbox_wq, - int first, int mdevs, u64 intr, int type) +static void otx2_queue_vf_work(struct mbox *mw, struct workqueue_struct *mbox_wq, + int first, int mdevs, u64 intr) { struct otx2_mbox_dev *mdev; struct otx2_mbox *mbox; @@ -307,40 +306,26 @@ static void otx2_queue_work(struct mbox *mw, struct workqueue_struct *mbox_wq, mbox = &mw->mbox; mdev = &mbox->dev[i]; - if (type == TYPE_PFAF) - otx2_sync_mbox_bbuf(mbox, i); hdr = mdev->mbase + mbox->rx_start; /* The hdr->num_msgs is set to zero immediately in the interrupt - * handler to ensure that it holds a correct value next time - * when the interrupt handler is called. - * pf->mbox.num_msgs holds the data for use in pfaf_mbox_handler - * pf>mbox.up_num_msgs holds the data for use in - * pfaf_mbox_up_handler. + * handler to ensure that it holds a correct value next time + * when the interrupt handler is called. pf->mw[i].num_msgs + * holds the data for use in otx2_pfvf_mbox_handler and + * pf->mw[i].up_num_msgs holds the data for use in + * otx2_pfvf_mbox_up_handler. */ if (hdr->num_msgs) { mw[i].num_msgs = hdr->num_msgs; hdr->num_msgs = 0; - if (type == TYPE_PFAF) - memset(mbox->hwbase + mbox->rx_start, 0, - ALIGN(sizeof(struct mbox_hdr), - sizeof(u64))); - queue_work(mbox_wq, &mw[i].mbox_wrk); } mbox = &mw->mbox_up; mdev = &mbox->dev[i]; - if (type == TYPE_PFAF) - otx2_sync_mbox_bbuf(mbox, i); hdr = mdev->mbase + mbox->rx_start; if (hdr->num_msgs) { mw[i].up_num_msgs = hdr->num_msgs; hdr->num_msgs = 0; - if (type == TYPE_PFAF) - memset(mbox->hwbase + mbox->rx_start, 0, - ALIGN(sizeof(struct mbox_hdr), - sizeof(u64))); - queue_work(mbox_wq, &mw[i].mbox_up_wrk); } } @@ -356,8 +341,10 @@ static void otx2_forward_msg_pfvf(struct otx2_mbox_dev *mdev, /* Msgs are already copied, trigger VF's mbox irq */ smp_wmb(); + otx2_mbox_wait_for_zero(pfvf_mbox, devid); + offset = pfvf_mbox->trigger | (devid << pfvf_mbox->tr_shift); - writeq(1, (void __iomem *)pfvf_mbox->reg_base + offset); + writeq(MBOX_DOWN_MSG, (void __iomem *)pfvf_mbox->reg_base + offset); /* Restore VF's mbox bounce buffer region address */ src_mdev->mbase = bbuf_base; @@ -547,7 +534,7 @@ static void otx2_pfvf_mbox_up_handler(struct work_struct *work) end: offset = mbox->rx_start + msg->next_msgoff; if (mdev->msgs_acked == (vf_mbox->up_num_msgs - 1)) - __otx2_mbox_reset(mbox, 0); + __otx2_mbox_reset(mbox, vf_idx); mdev->msgs_acked++; } } @@ -564,8 +551,7 @@ static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq) if (vfs > 64) { intr = otx2_read64(pf, RVU_PF_VFPF_MBOX_INTX(1)); otx2_write64(pf, RVU_PF_VFPF_MBOX_INTX(1), intr); - otx2_queue_work(mbox, pf->mbox_pfvf_wq, 64, vfs, intr, - TYPE_PFVF); + otx2_queue_vf_work(mbox, pf->mbox_pfvf_wq, 64, vfs, intr); if (intr) trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr); vfs = 64; @@ -574,7 +560,7 @@ static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq) intr = otx2_read64(pf, RVU_PF_VFPF_MBOX_INTX(0)); otx2_write64(pf, RVU_PF_VFPF_MBOX_INTX(0), intr); - otx2_queue_work(mbox, pf->mbox_pfvf_wq, 0, vfs, intr, TYPE_PFVF); + otx2_queue_vf_work(mbox, pf->mbox_pfvf_wq, 0, vfs, intr); if (intr) trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr); @@ -599,7 +585,7 @@ static int otx2_pfvf_mbox_init(struct otx2_nic *pf, int numvfs) pf->mbox_pfvf_wq = alloc_workqueue("otx2_pfvf_mailbox", WQ_UNBOUND | WQ_HIGHPRI | - WQ_MEM_RECLAIM, 1); + WQ_MEM_RECLAIM, 0); if (!pf->mbox_pfvf_wq) return -ENOMEM; @@ -822,20 +808,22 @@ static void otx2_pfaf_mbox_handler(struct work_struct *work) struct mbox *af_mbox; struct otx2_nic *pf; int offset, id; + u16 num_msgs; af_mbox = container_of(work, struct mbox, mbox_wrk); mbox = &af_mbox->mbox; mdev = &mbox->dev[0]; rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + num_msgs = rsp_hdr->num_msgs; offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN); pf = af_mbox->pfvf; - for (id = 0; id < af_mbox->num_msgs; id++) { + for (id = 0; id < num_msgs; id++) { msg = (struct mbox_msghdr *)(mdev->mbase + offset); otx2_process_pfaf_mbox_msg(pf, msg); offset = mbox->rx_start + msg->next_msgoff; - if (mdev->msgs_acked == (af_mbox->num_msgs - 1)) + if (mdev->msgs_acked == (num_msgs - 1)) __otx2_mbox_reset(mbox, 0); mdev->msgs_acked++; } @@ -946,12 +934,14 @@ static void otx2_pfaf_mbox_up_handler(struct work_struct *work) int offset, id, devid = 0; struct mbox_hdr *rsp_hdr; struct mbox_msghdr *msg; + u16 num_msgs; rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + num_msgs = rsp_hdr->num_msgs; offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN); - for (id = 0; id < af_mbox->up_num_msgs; id++) { + for (id = 0; id < num_msgs; id++) { msg = (struct mbox_msghdr *)(mdev->mbase + offset); devid = msg->pcifunc & RVU_PFVF_FUNC_MASK; @@ -960,10 +950,11 @@ static void otx2_pfaf_mbox_up_handler(struct work_struct *work) otx2_process_mbox_msg_up(pf, msg); offset = mbox->rx_start + msg->next_msgoff; } - if (devid) { + /* Forward to VF iff VFs are really present */ + if (devid && pci_num_vf(pf->pdev)) { otx2_forward_vf_mbox_msgs(pf, &pf->mbox.mbox_up, MBOX_DIR_PFVF_UP, devid - 1, - af_mbox->up_num_msgs); + num_msgs); return; } @@ -973,16 +964,49 @@ static void otx2_pfaf_mbox_up_handler(struct work_struct *work) static irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq) { struct otx2_nic *pf = (struct otx2_nic *)pf_irq; - struct mbox *mbox; + struct mbox *mw = &pf->mbox; + struct otx2_mbox_dev *mdev; + struct otx2_mbox *mbox; + struct mbox_hdr *hdr; + u64 mbox_data; /* Clear the IRQ */ otx2_write64(pf, RVU_PF_INT, BIT_ULL(0)); - mbox = &pf->mbox; - trace_otx2_msg_interrupt(mbox->mbox.pdev, "AF to PF", BIT_ULL(0)); + mbox_data = otx2_read64(pf, RVU_PF_PFAF_MBOX0); + + if (mbox_data & MBOX_UP_MSG) { + mbox_data &= ~MBOX_UP_MSG; + otx2_write64(pf, RVU_PF_PFAF_MBOX0, mbox_data); + + mbox = &mw->mbox_up; + mdev = &mbox->dev[0]; + otx2_sync_mbox_bbuf(mbox, 0); + + hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + if (hdr->num_msgs) + queue_work(pf->mbox_wq, &mw->mbox_up_wrk); + + trace_otx2_msg_interrupt(pf->pdev, "UP message from AF to PF", + BIT_ULL(0)); + } + + if (mbox_data & MBOX_DOWN_MSG) { + mbox_data &= ~MBOX_DOWN_MSG; + otx2_write64(pf, RVU_PF_PFAF_MBOX0, mbox_data); + + mbox = &mw->mbox; + mdev = &mbox->dev[0]; + otx2_sync_mbox_bbuf(mbox, 0); + + hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + if (hdr->num_msgs) + queue_work(pf->mbox_wq, &mw->mbox_wrk); - otx2_queue_work(mbox, pf->mbox_wq, 0, 1, 1, TYPE_PFAF); + trace_otx2_msg_interrupt(pf->pdev, "DOWN reply from AF to PF", + BIT_ULL(0)); + } return IRQ_HANDLED; } @@ -1063,9 +1087,8 @@ static int otx2_pfaf_mbox_init(struct otx2_nic *pf) int err; mbox->pfvf = pf; - pf->mbox_wq = alloc_workqueue("otx2_pfaf_mailbox", - WQ_UNBOUND | WQ_HIGHPRI | - WQ_MEM_RECLAIM, 1); + pf->mbox_wq = alloc_ordered_workqueue("otx2_pfaf_mailbox", + WQ_HIGHPRI | WQ_MEM_RECLAIM); if (!pf->mbox_wq) return -ENOMEM; @@ -1891,7 +1914,7 @@ int otx2_open(struct net_device *netdev) * mcam entries are enabled to receive the packets. Hence disable the * packet I/O. */ - if (err == EIO) + if (err == -EIO) goto err_disable_rxtx; else if (err) goto err_tx_stop_queues; @@ -3030,6 +3053,7 @@ static void otx2_vf_link_event_task(struct work_struct *work) struct otx2_vf_config *config; struct cgx_link_info_msg *req; struct mbox_msghdr *msghdr; + struct delayed_work *dwork; struct otx2_nic *pf; int vf_idx; @@ -3038,10 +3062,24 @@ static void otx2_vf_link_event_task(struct work_struct *work) vf_idx = config - config->pf->vf_configs; pf = config->pf; + if (config->intf_down) + return; + + mutex_lock(&pf->mbox.lock); + + dwork = &config->link_event_work; + + if (!otx2_mbox_wait_for_zero(&pf->mbox_pfvf[0].mbox_up, vf_idx)) { + schedule_delayed_work(dwork, msecs_to_jiffies(100)); + mutex_unlock(&pf->mbox.lock); + return; + } + msghdr = otx2_mbox_alloc_msg_rsp(&pf->mbox_pfvf[0].mbox_up, vf_idx, sizeof(*req), sizeof(struct msg_rsp)); if (!msghdr) { dev_err(pf->dev, "Failed to create VF%d link event\n", vf_idx); + mutex_unlock(&pf->mbox.lock); return; } @@ -3050,7 +3088,11 @@ static void otx2_vf_link_event_task(struct work_struct *work) req->hdr.sig = OTX2_MBOX_REQ_SIG; memcpy(&req->link_info, &pf->linfo, sizeof(req->link_info)); + otx2_mbox_wait_for_zero(&pf->mbox_pfvf[0].mbox_up, vf_idx); + otx2_sync_mbox_up_msg(&pf->mbox_pfvf[0], vf_idx); + + mutex_unlock(&pf->mbox.lock); } static int otx2_sriov_enable(struct pci_dev *pdev, int numvfs) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 404855bccb4b628b62c7bec887feb3eaf156936c..dcb8190de24073575d60f4fae60c5cc92f7ddfc6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -89,16 +89,20 @@ static void otx2vf_vfaf_mbox_handler(struct work_struct *work) struct otx2_mbox *mbox; struct mbox *af_mbox; int offset, id; + u16 num_msgs; af_mbox = container_of(work, struct mbox, mbox_wrk); mbox = &af_mbox->mbox; mdev = &mbox->dev[0]; rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); - if (af_mbox->num_msgs == 0) + num_msgs = rsp_hdr->num_msgs; + + if (num_msgs == 0) return; + offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN); - for (id = 0; id < af_mbox->num_msgs; id++) { + for (id = 0; id < num_msgs; id++) { msg = (struct mbox_msghdr *)(mdev->mbase + offset); otx2vf_process_vfaf_mbox_msg(af_mbox->pfvf, msg); offset = mbox->rx_start + msg->next_msgoff; @@ -151,6 +155,7 @@ static void otx2vf_vfaf_mbox_up_handler(struct work_struct *work) struct mbox *vf_mbox; struct otx2_nic *vf; int offset, id; + u16 num_msgs; vf_mbox = container_of(work, struct mbox, mbox_up_wrk); vf = vf_mbox->pfvf; @@ -158,12 +163,14 @@ static void otx2vf_vfaf_mbox_up_handler(struct work_struct *work) mdev = &mbox->dev[0]; rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); - if (vf_mbox->up_num_msgs == 0) + num_msgs = rsp_hdr->num_msgs; + + if (num_msgs == 0) return; offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN); - for (id = 0; id < vf_mbox->up_num_msgs; id++) { + for (id = 0; id < num_msgs; id++) { msg = (struct mbox_msghdr *)(mdev->mbase + offset); otx2vf_process_mbox_msg_up(vf, msg); offset = mbox->rx_start + msg->next_msgoff; @@ -178,40 +185,48 @@ static irqreturn_t otx2vf_vfaf_mbox_intr_handler(int irq, void *vf_irq) struct otx2_mbox_dev *mdev; struct otx2_mbox *mbox; struct mbox_hdr *hdr; + u64 mbox_data; /* Clear the IRQ */ otx2_write64(vf, RVU_VF_INT, BIT_ULL(0)); + mbox_data = otx2_read64(vf, RVU_VF_VFPF_MBOX0); + /* Read latest mbox data */ smp_rmb(); - /* Check for PF => VF response messages */ - mbox = &vf->mbox.mbox; - mdev = &mbox->dev[0]; - otx2_sync_mbox_bbuf(mbox, 0); + if (mbox_data & MBOX_DOWN_MSG) { + mbox_data &= ~MBOX_DOWN_MSG; + otx2_write64(vf, RVU_VF_VFPF_MBOX0, mbox_data); - trace_otx2_msg_interrupt(mbox->pdev, "PF to VF", BIT_ULL(0)); + /* Check for PF => VF response messages */ + mbox = &vf->mbox.mbox; + mdev = &mbox->dev[0]; + otx2_sync_mbox_bbuf(mbox, 0); - hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); - if (hdr->num_msgs) { - vf->mbox.num_msgs = hdr->num_msgs; - hdr->num_msgs = 0; - memset(mbox->hwbase + mbox->rx_start, 0, - ALIGN(sizeof(struct mbox_hdr), sizeof(u64))); - queue_work(vf->mbox_wq, &vf->mbox.mbox_wrk); + hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + if (hdr->num_msgs) + queue_work(vf->mbox_wq, &vf->mbox.mbox_wrk); + + trace_otx2_msg_interrupt(mbox->pdev, "DOWN reply from PF to VF", + BIT_ULL(0)); } - /* Check for PF => VF notification messages */ - mbox = &vf->mbox.mbox_up; - mdev = &mbox->dev[0]; - otx2_sync_mbox_bbuf(mbox, 0); - hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); - if (hdr->num_msgs) { - vf->mbox.up_num_msgs = hdr->num_msgs; - hdr->num_msgs = 0; - memset(mbox->hwbase + mbox->rx_start, 0, - ALIGN(sizeof(struct mbox_hdr), sizeof(u64))); - queue_work(vf->mbox_wq, &vf->mbox.mbox_up_wrk); + if (mbox_data & MBOX_UP_MSG) { + mbox_data &= ~MBOX_UP_MSG; + otx2_write64(vf, RVU_VF_VFPF_MBOX0, mbox_data); + + /* Check for PF => VF notification messages */ + mbox = &vf->mbox.mbox_up; + mdev = &mbox->dev[0]; + otx2_sync_mbox_bbuf(mbox, 0); + + hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + if (hdr->num_msgs) + queue_work(vf->mbox_wq, &vf->mbox.mbox_up_wrk); + + trace_otx2_msg_interrupt(mbox->pdev, "UP message from PF to VF", + BIT_ULL(0)); } return IRQ_HANDLED; @@ -293,9 +308,8 @@ static int otx2vf_vfaf_mbox_init(struct otx2_nic *vf) int err; mbox->pfvf = vf; - vf->mbox_wq = alloc_workqueue("otx2_vfaf_mailbox", - WQ_UNBOUND | WQ_HIGHPRI | - WQ_MEM_RECLAIM, 1); + vf->mbox_wq = alloc_ordered_workqueue("otx2_vfaf_mailbox", + WQ_HIGHPRI | WQ_MEM_RECLAIM); if (!vf->mbox_wq) return -ENOMEM; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 17e6ac4445afc338d7129b7d9441c4adba42ca02..fecf3dd22dfaa34ce19b9564434f1cfd2be9c2ea 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -561,8 +561,7 @@ static int mtk_mac_finish(struct phylink_config *config, unsigned int mode, mcr_cur = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id)); mcr_new = mcr_cur; mcr_new |= MAC_MCR_IPG_CFG | MAC_MCR_FORCE_MODE | - MAC_MCR_BACKOFF_EN | MAC_MCR_BACKPR_EN | MAC_MCR_FORCE_LINK | - MAC_MCR_RX_FIFO_CLR_DIS; + MAC_MCR_BACKOFF_EN | MAC_MCR_BACKPR_EN | MAC_MCR_RX_FIFO_CLR_DIS; /* Only update control register when needed! */ if (mcr_new != mcr_cur) @@ -610,7 +609,7 @@ static void mtk_mac_link_down(struct phylink_config *config, unsigned int mode, phylink_config); u32 mcr = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id)); - mcr &= ~(MAC_MCR_TX_EN | MAC_MCR_RX_EN); + mcr &= ~(MAC_MCR_TX_EN | MAC_MCR_RX_EN | MAC_MCR_FORCE_LINK); mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id)); } @@ -649,7 +648,7 @@ static void mtk_mac_link_up(struct phylink_config *config, if (rx_pause) mcr |= MAC_MCR_FORCE_RX_FC; - mcr |= MAC_MCR_TX_EN | MAC_MCR_RX_EN; + mcr |= MAC_MCR_TX_EN | MAC_MCR_RX_EN | MAC_MCR_FORCE_LINK; mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id)); } diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c index d6eed204574a9a50a012b8fc3b5ec33d92d50cd4..c64211e22ae707869862f7d91a7e1c2792ba7ac1 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe.c @@ -811,7 +811,7 @@ void mtk_ppe_start(struct mtk_ppe *ppe) MTK_PPE_KEEPALIVE_DISABLE) | FIELD_PREP(MTK_PPE_TB_CFG_HASH_MODE, 1) | FIELD_PREP(MTK_PPE_TB_CFG_SCAN_MODE, - MTK_PPE_SCAN_MODE_KEEPALIVE_AGE) | + MTK_PPE_SCAN_MODE_CHECK_AGE) | FIELD_PREP(MTK_PPE_TB_CFG_ENTRY_NUM, MTK_PPE_ENTRIES_SHIFT); if (MTK_HAS_CAPS(ppe->eth->soc->caps, MTK_NETSYS_V2)) @@ -895,17 +895,21 @@ int mtk_ppe_stop(struct mtk_ppe *ppe) mtk_ppe_cache_enable(ppe, false); - /* disable offload engine */ - ppe_clear(ppe, MTK_PPE_GLO_CFG, MTK_PPE_GLO_CFG_EN); - ppe_w32(ppe, MTK_PPE_FLOW_CFG, 0); - /* disable aging */ val = MTK_PPE_TB_CFG_AGE_NON_L4 | MTK_PPE_TB_CFG_AGE_UNBIND | MTK_PPE_TB_CFG_AGE_TCP | MTK_PPE_TB_CFG_AGE_UDP | - MTK_PPE_TB_CFG_AGE_TCP_FIN; + MTK_PPE_TB_CFG_AGE_TCP_FIN | + MTK_PPE_TB_CFG_SCAN_MODE; ppe_clear(ppe, MTK_PPE_TB_CFG, val); - return mtk_ppe_wait_busy(ppe); + if (mtk_ppe_wait_busy(ppe)) + return -ETIMEDOUT; + + /* disable offload engine */ + ppe_clear(ppe, MTK_PPE_GLO_CFG, MTK_PPE_GLO_CFG_EN); + ppe_w32(ppe, MTK_PPE_FLOW_CFG, 0); + + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c index 2842195ee548adf5a464c2a1fd7429114360cb4e..1e887d640cffc52a9555edbd4813e576980220f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c @@ -82,24 +82,25 @@ int mlx5e_open_qos_sq(struct mlx5e_priv *priv, struct mlx5e_channels *chs, txq_ix = mlx5e_qid_from_qos(chs, node_qid); - WARN_ON(node_qid > priv->htb_max_qos_sqs); - if (node_qid == priv->htb_max_qos_sqs) { - struct mlx5e_sq_stats *stats, **stats_list = NULL; - - if (priv->htb_max_qos_sqs == 0) { - stats_list = kvcalloc(mlx5e_qos_max_leaf_nodes(priv->mdev), - sizeof(*stats_list), - GFP_KERNEL); - if (!stats_list) - return -ENOMEM; - } + WARN_ON(node_qid >= mlx5e_htb_cur_leaf_nodes(priv->htb)); + if (!priv->htb_qos_sq_stats) { + struct mlx5e_sq_stats **stats_list; + + stats_list = kvcalloc(mlx5e_qos_max_leaf_nodes(priv->mdev), + sizeof(*stats_list), GFP_KERNEL); + if (!stats_list) + return -ENOMEM; + + WRITE_ONCE(priv->htb_qos_sq_stats, stats_list); + } + + if (!priv->htb_qos_sq_stats[node_qid]) { + struct mlx5e_sq_stats *stats; + stats = kzalloc(sizeof(*stats), GFP_KERNEL); - if (!stats) { - kvfree(stats_list); + if (!stats) return -ENOMEM; - } - if (stats_list) - WRITE_ONCE(priv->htb_qos_sq_stats, stats_list); + WRITE_ONCE(priv->htb_qos_sq_stats[node_qid], stats); /* Order htb_max_qos_sqs increment after writing the array pointer. * Pairs with smp_load_acquire in en_stats.c. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c b/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c index f675b1926340f9ca4218aa47febac7c5139ab0e9..f66bbc8464645efabc08ebf923fada5e1f79c5fe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c @@ -57,6 +57,7 @@ int mlx5e_selq_init(struct mlx5e_selq *selq, struct mutex *state_lock) void mlx5e_selq_cleanup(struct mlx5e_selq *selq) { + mutex_lock(selq->state_lock); WARN_ON_ONCE(selq->is_prepared); kvfree(selq->standby); @@ -67,6 +68,7 @@ void mlx5e_selq_cleanup(struct mlx5e_selq *selq) kvfree(selq->standby); selq->standby = NULL; + mutex_unlock(selq->state_lock); } void mlx5e_selq_prepare_params(struct mlx5e_selq *selq, struct mlx5e_params *params) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index a7832a0180ee6b215f368ac7dc51c536594e1455..48cf691842b54c9b44ca923d6cf6857f3a8a3edb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -1703,6 +1703,7 @@ static const struct macsec_ops macsec_offload_ops = { .mdo_add_secy = mlx5e_macsec_add_secy, .mdo_upd_secy = mlx5e_macsec_upd_secy, .mdo_del_secy = mlx5e_macsec_del_secy, + .rx_uses_md_dst = true, }; bool mlx5e_macsec_handle_tx_skb(struct mlx5e_macsec *macsec, struct sk_buff *skb) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index 58eacba6de8cd6e2b214b2e72072a168ae497b67..ad51edf55318501fdd91e0a2edcc066b87cf2de7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -45,6 +45,10 @@ struct arfs_table { struct hlist_head rules_hash[ARFS_HASH_SIZE]; }; +enum { + MLX5E_ARFS_STATE_ENABLED, +}; + enum arfs_type { ARFS_IPV4_TCP, ARFS_IPV6_TCP, @@ -60,6 +64,7 @@ struct mlx5e_arfs_tables { struct list_head rules; int last_filter_id; struct workqueue_struct *wq; + unsigned long state; }; struct arfs_tuple { @@ -170,6 +175,8 @@ int mlx5e_arfs_enable(struct mlx5e_flow_steering *fs) return err; } } + set_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state); + return 0; } @@ -454,6 +461,8 @@ static void arfs_del_rules(struct mlx5e_flow_steering *fs) int i; int j; + clear_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state); + spin_lock_bh(&arfs->arfs_lock); mlx5e_for_each_arfs_rule(rule, htmp, arfs->arfs_tables, i, j) { hlist_del_init(&rule->hlist); @@ -621,17 +630,8 @@ static void arfs_handle_work(struct work_struct *work) struct mlx5_flow_handle *rule; arfs = mlx5e_fs_get_arfs(priv->fs); - mutex_lock(&priv->state_lock); - if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { - spin_lock_bh(&arfs->arfs_lock); - hlist_del(&arfs_rule->hlist); - spin_unlock_bh(&arfs->arfs_lock); - - mutex_unlock(&priv->state_lock); - kfree(arfs_rule); - goto out; - } - mutex_unlock(&priv->state_lock); + if (!test_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state)) + return; if (!arfs_rule->rule) { rule = arfs_add_rule(priv, arfs_rule); @@ -744,6 +744,11 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, return -EPROTONOSUPPORT; spin_lock_bh(&arfs->arfs_lock); + if (!test_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state)) { + spin_unlock_bh(&arfs->arfs_lock); + return -EPERM; + } + arfs_rule = arfs_find_rule(arfs_t, &fk); if (arfs_rule) { if (arfs_rule->rxq == rxq_index) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 9910a0480f5899d08266c41e060ded3067ca497c..e7d396434da3648e5f4bb34ebe3a7e5ff5b2d676 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5578,9 +5578,7 @@ void mlx5e_priv_cleanup(struct mlx5e_priv *priv) kfree(priv->tx_rates); kfree(priv->txq2sq); destroy_workqueue(priv->wq); - mutex_lock(&priv->state_lock); mlx5e_selq_cleanup(&priv->selq); - mutex_unlock(&priv->state_lock); free_cpumask_var(priv->scratchpad.cpumask); for (i = 0; i < priv->htb_max_qos_sqs; i++) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index e6674118bc42851fa42dabd3f9cf02ec7629f932..164e10b5f9b7f7adb46a98896c88de093195e57f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1752,8 +1752,9 @@ static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg, } trace_mlx5_fs_set_fte(fte, false); + /* Link newly added rules into the tree. */ for (i = 0; i < handle->num_rules; i++) { - if (refcount_read(&handle->rule[i]->node.refcount) == 1) { + if (!handle->rule[i]->node.parent) { tree_add_node(&handle->rule[i]->node, &fte->node); trace_mlx5_fs_add_rule(handle->rule[i]); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index ad32b80e8501855a19bcb21d5f10687d14b9ba21..01c0e1ee918d82a61af93ac00a68428274cbc736 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -679,8 +679,10 @@ static int mlx5_deactivate_lag(struct mlx5_lag *ldev) return err; } - if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags)) + if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags)) { mlx5_lag_port_sel_destroy(ldev); + ldev->buckets = 1; + } if (mlx5_lag_has_drop_rule(ldev)) mlx5_lag_drop_rule_cleanup(ldev); diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c index 83c4659390fd59125dfcd3385760875262dacfa4..d6b4d163bbbfd368ec2eace666bd26995a94df0c 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include "mlxbf_gige.h" @@ -139,13 +140,10 @@ static int mlxbf_gige_open(struct net_device *netdev) control |= MLXBF_GIGE_CONTROL_PORT_EN; writeq(control, priv->base + MLXBF_GIGE_CONTROL); - err = mlxbf_gige_request_irqs(priv); - if (err) - return err; mlxbf_gige_cache_stats(priv); err = mlxbf_gige_clean_port(priv); if (err) - goto free_irqs; + return err; /* Clear driver's valid_polarity to match hardware, * since the above call to clean_port() resets the @@ -157,7 +155,7 @@ static int mlxbf_gige_open(struct net_device *netdev) err = mlxbf_gige_tx_init(priv); if (err) - goto free_irqs; + goto phy_deinit; err = mlxbf_gige_rx_init(priv); if (err) goto tx_deinit; @@ -166,6 +164,10 @@ static int mlxbf_gige_open(struct net_device *netdev) napi_enable(&priv->napi); netif_start_queue(netdev); + err = mlxbf_gige_request_irqs(priv); + if (err) + goto napi_deinit; + /* Set bits in INT_EN that we care about */ int_en = MLXBF_GIGE_INT_EN_HW_ACCESS_ERROR | MLXBF_GIGE_INT_EN_TX_CHECKSUM_INPUTS | @@ -182,11 +184,17 @@ static int mlxbf_gige_open(struct net_device *netdev) return 0; +napi_deinit: + netif_stop_queue(netdev); + napi_disable(&priv->napi); + netif_napi_del(&priv->napi); + mlxbf_gige_rx_deinit(priv); + tx_deinit: mlxbf_gige_tx_deinit(priv); -free_irqs: - mlxbf_gige_free_irqs(priv); +phy_deinit: + phy_stop(phydev); return err; } @@ -410,8 +418,13 @@ static void mlxbf_gige_shutdown(struct platform_device *pdev) { struct mlxbf_gige *priv = platform_get_drvdata(pdev); - writeq(0, priv->base + MLXBF_GIGE_INT_EN); - mlxbf_gige_clean_port(priv); + rtnl_lock(); + netif_device_detach(priv->netdev); + + if (netif_running(priv->netdev)) + dev_close(priv->netdev); + + rtnl_unlock(); } static const struct acpi_device_id __maybe_unused mlxbf_gige_acpi_match[] = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index e2a985ec2c765a36269d20ca60c3b186fa87c30d..f36a416ffcfe90cfb08d767f24a1bbd057e75f88 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -792,7 +792,7 @@ free_skb: static const struct mlxsw_listener mlxsw_emad_rx_listener = MLXSW_RXL(mlxsw_emad_rx_listener_func, ETHEMAD, TRAP_TO_CPU, false, - EMAD, DISCARD); + EMAD, FORWARD); static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 3b9ba8fa247ab090b8add681789fa64c5a213a37..685bcf8cbfa9a23ce7b240ec9e94ecb0f78c3341 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -52,8 +52,10 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, max_regions = max_tcam_regions; tcam->used_regions = bitmap_zalloc(max_regions, GFP_KERNEL); - if (!tcam->used_regions) - return -ENOMEM; + if (!tcam->used_regions) { + err = -ENOMEM; + goto err_alloc_used_regions; + } tcam->max_regions = max_regions; max_groups = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_GROUPS); @@ -65,6 +67,8 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, tcam->max_groups = max_groups; tcam->max_group_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_GROUP_SIZE); + tcam->max_group_size = min_t(unsigned int, tcam->max_group_size, + MLXSW_REG_PAGT_ACL_MAX_NUM); err = ops->init(mlxsw_sp, tcam->priv, tcam); if (err) @@ -76,6 +80,8 @@ err_tcam_init: bitmap_free(tcam->used_groups); err_alloc_used_groups: bitmap_free(tcam->used_regions); +err_alloc_used_regions: + mutex_destroy(&tcam->lock); return err; } @@ -84,10 +90,10 @@ void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, { const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - mutex_destroy(&tcam->lock); ops->fini(mlxsw_sp, tcam->priv); bitmap_free(tcam->used_groups); bitmap_free(tcam->used_regions); + mutex_destroy(&tcam->lock); } int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp, @@ -774,7 +780,9 @@ static void mlxsw_sp_acl_tcam_vregion_rehash_work(struct work_struct *work) rehash.dw.work); int credits = MLXSW_SP_ACL_TCAM_VREGION_REHASH_CREDITS; + mutex_lock(&vregion->lock); mlxsw_sp_acl_tcam_vregion_rehash(vregion->mlxsw_sp, vregion, &credits); + mutex_unlock(&vregion->lock); if (credits < 0) /* Rehash gone out of credits so it was interrupted. * Schedule the work as soon as possible to continue. @@ -784,6 +792,17 @@ static void mlxsw_sp_acl_tcam_vregion_rehash_work(struct work_struct *work) mlxsw_sp_acl_tcam_vregion_rehash_work_schedule(vregion); } +static void +mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(struct mlxsw_sp_acl_tcam_rehash_ctx *ctx) +{ + /* The entry markers are relative to the current chunk and therefore + * needs to be reset together with the chunk marker. + */ + ctx->current_vchunk = NULL; + ctx->start_ventry = NULL; + ctx->stop_ventry = NULL; +} + static void mlxsw_sp_acl_tcam_rehash_ctx_vchunk_changed(struct mlxsw_sp_acl_tcam_vchunk *vchunk) { @@ -806,7 +825,7 @@ mlxsw_sp_acl_tcam_rehash_ctx_vregion_changed(struct mlxsw_sp_acl_tcam_vregion *v * the current chunk pointer to make sure all chunks * are properly migrated. */ - vregion->rehash.ctx.current_vchunk = NULL; + mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(&vregion->rehash.ctx); } static struct mlxsw_sp_acl_tcam_vregion * @@ -879,10 +898,14 @@ mlxsw_sp_acl_tcam_vregion_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam *tcam = vregion->tcam; if (vgroup->vregion_rehash_enabled && ops->region_rehash_hints_get) { + struct mlxsw_sp_acl_tcam_rehash_ctx *ctx = &vregion->rehash.ctx; + mutex_lock(&tcam->lock); list_del(&vregion->tlist); mutex_unlock(&tcam->lock); - cancel_delayed_work_sync(&vregion->rehash.dw); + if (cancel_delayed_work_sync(&vregion->rehash.dw) && + ctx->hints_priv) + ops->region_rehash_hints_put(ctx->hints_priv); } mlxsw_sp_acl_tcam_vgroup_vregion_detach(mlxsw_sp, vregion); if (vregion->region2) @@ -1248,8 +1271,14 @@ mlxsw_sp_acl_tcam_ventry_activity_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam_ventry *ventry, bool *activity) { - return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, - ventry->entry, activity); + struct mlxsw_sp_acl_tcam_vregion *vregion = ventry->vchunk->vregion; + int err; + + mutex_lock(&vregion->lock); + err = mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, ventry->entry, + activity); + mutex_unlock(&vregion->lock); + return err; } static int @@ -1283,6 +1312,8 @@ mlxsw_sp_acl_tcam_vchunk_migrate_start(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_acl_tcam_chunk *new_chunk; + WARN_ON(vchunk->chunk2); + new_chunk = mlxsw_sp_acl_tcam_chunk_create(mlxsw_sp, vchunk, region); if (IS_ERR(new_chunk)) return PTR_ERR(new_chunk); @@ -1301,7 +1332,7 @@ mlxsw_sp_acl_tcam_vchunk_migrate_end(struct mlxsw_sp *mlxsw_sp, { mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, vchunk->chunk2); vchunk->chunk2 = NULL; - ctx->current_vchunk = NULL; + mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(ctx); } static int @@ -1324,6 +1355,9 @@ mlxsw_sp_acl_tcam_vchunk_migrate_one(struct mlxsw_sp *mlxsw_sp, return 0; } + if (list_empty(&vchunk->ventry_list)) + goto out; + /* If the migration got interrupted, we have the ventry to start from * stored in context. */ @@ -1333,6 +1367,8 @@ mlxsw_sp_acl_tcam_vchunk_migrate_one(struct mlxsw_sp *mlxsw_sp, ventry = list_first_entry(&vchunk->ventry_list, typeof(*ventry), list); + WARN_ON(ventry->vchunk != vchunk); + list_for_each_entry_from(ventry, &vchunk->ventry_list, list) { /* During rollback, once we reach the ventry that failed * to migrate, we are done. @@ -1373,6 +1409,7 @@ mlxsw_sp_acl_tcam_vchunk_migrate_one(struct mlxsw_sp *mlxsw_sp, } } +out: mlxsw_sp_acl_tcam_vchunk_migrate_end(mlxsw_sp, vchunk, ctx); return 0; } @@ -1386,6 +1423,9 @@ mlxsw_sp_acl_tcam_vchunk_migrate_all(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam_vchunk *vchunk; int err; + if (list_empty(&vregion->vchunk_list)) + return 0; + /* If the migration got interrupted, we have the vchunk * we are working on stored in context. */ @@ -1414,16 +1454,17 @@ mlxsw_sp_acl_tcam_vregion_migrate(struct mlxsw_sp *mlxsw_sp, int err, err2; trace_mlxsw_sp_acl_tcam_vregion_migrate(mlxsw_sp, vregion); - mutex_lock(&vregion->lock); err = mlxsw_sp_acl_tcam_vchunk_migrate_all(mlxsw_sp, vregion, ctx, credits); if (err) { + if (ctx->this_is_rollback) + return err; /* In case migration was not successful, we need to swap * so the original region pointer is assigned again * to vregion->region. */ swap(vregion->region, vregion->region2); - ctx->current_vchunk = NULL; + mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(ctx); ctx->this_is_rollback = true; err2 = mlxsw_sp_acl_tcam_vchunk_migrate_all(mlxsw_sp, vregion, ctx, credits); @@ -1434,7 +1475,6 @@ mlxsw_sp_acl_tcam_vregion_migrate(struct mlxsw_sp *mlxsw_sp, /* Let the rollback to be continued later on. */ } } - mutex_unlock(&vregion->lock); trace_mlxsw_sp_acl_tcam_vregion_migrate_end(mlxsw_sp, vregion); return err; } @@ -1483,6 +1523,7 @@ mlxsw_sp_acl_tcam_vregion_rehash_start(struct mlxsw_sp *mlxsw_sp, ctx->hints_priv = hints_priv; ctx->this_is_rollback = false; + mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(ctx); return 0; @@ -1535,7 +1576,8 @@ mlxsw_sp_acl_tcam_vregion_rehash(struct mlxsw_sp *mlxsw_sp, err = mlxsw_sp_acl_tcam_vregion_migrate(mlxsw_sp, vregion, ctx, credits); if (err) { - dev_err(mlxsw_sp->bus_info->dev, "Failed to migrate vregion\n"); + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to migrate vregion\n"); + return; } if (*credits >= 0) diff --git a/drivers/net/ethernet/micrel/ks8851.h b/drivers/net/ethernet/micrel/ks8851.h index e5ec0a363aff84d44470b8cf2374ef36a98c6b06..31f75b4a67fd79eb1c7c08096a5a11a163a96b73 100644 --- a/drivers/net/ethernet/micrel/ks8851.h +++ b/drivers/net/ethernet/micrel/ks8851.h @@ -368,7 +368,6 @@ union ks8851_tx_hdr { * @rdfifo: FIFO read callback * @wrfifo: FIFO write callback * @start_xmit: start_xmit() implementation callback - * @rx_skb: rx_skb() implementation callback * @flush_tx_work: flush_tx_work() implementation callback * * The @statelock is used to protect information in the structure which may @@ -423,8 +422,6 @@ struct ks8851_net { struct sk_buff *txp, bool irq); netdev_tx_t (*start_xmit)(struct sk_buff *skb, struct net_device *dev); - void (*rx_skb)(struct ks8851_net *ks, - struct sk_buff *skb); void (*flush_tx_work)(struct ks8851_net *ks); }; diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c index 0bf13b38b8f5b907b464649422331421337d8411..6453c92f0fa7ccbfad4e184a81b07c8f4ca94f1a 100644 --- a/drivers/net/ethernet/micrel/ks8851_common.c +++ b/drivers/net/ethernet/micrel/ks8851_common.c @@ -231,25 +231,16 @@ static void ks8851_dbg_dumpkkt(struct ks8851_net *ks, u8 *rxpkt) rxpkt[12], rxpkt[13], rxpkt[14], rxpkt[15]); } -/** - * ks8851_rx_skb - receive skbuff - * @ks: The device state. - * @skb: The skbuff - */ -static void ks8851_rx_skb(struct ks8851_net *ks, struct sk_buff *skb) -{ - ks->rx_skb(ks, skb); -} - /** * ks8851_rx_pkts - receive packets from the host * @ks: The device information. + * @rxq: Queue of packets received in this function. * * This is called from the IRQ work queue when the system detects that there * are packets in the receive queue. Find out how many packets there are and * read them from the FIFO. */ -static void ks8851_rx_pkts(struct ks8851_net *ks) +static void ks8851_rx_pkts(struct ks8851_net *ks, struct sk_buff_head *rxq) { struct sk_buff *skb; unsigned rxfc; @@ -309,7 +300,7 @@ static void ks8851_rx_pkts(struct ks8851_net *ks) ks8851_dbg_dumpkkt(ks, rxpkt); skb->protocol = eth_type_trans(skb, ks->netdev); - ks8851_rx_skb(ks, skb); + __skb_queue_tail(rxq, skb); ks->netdev->stats.rx_packets++; ks->netdev->stats.rx_bytes += rxlen; @@ -336,31 +327,25 @@ static void ks8851_rx_pkts(struct ks8851_net *ks) static irqreturn_t ks8851_irq(int irq, void *_ks) { struct ks8851_net *ks = _ks; - unsigned handled = 0; + struct sk_buff_head rxq; unsigned long flags; unsigned int status; + struct sk_buff *skb; ks8851_lock(ks, &flags); status = ks8851_rdreg16(ks, KS_ISR); + ks8851_wrreg16(ks, KS_ISR, status); netif_dbg(ks, intr, ks->netdev, "%s: status 0x%04x\n", __func__, status); - if (status & IRQ_LCI) - handled |= IRQ_LCI; - if (status & IRQ_LDI) { u16 pmecr = ks8851_rdreg16(ks, KS_PMECR); pmecr &= ~PMECR_WKEVT_MASK; ks8851_wrreg16(ks, KS_PMECR, pmecr | PMECR_WKEVT_LINK); - - handled |= IRQ_LDI; } - if (status & IRQ_RXPSI) - handled |= IRQ_RXPSI; - if (status & IRQ_TXI) { unsigned short tx_space = ks8851_rdreg16(ks, KS_TXMIR); @@ -372,27 +357,20 @@ static irqreturn_t ks8851_irq(int irq, void *_ks) if (netif_queue_stopped(ks->netdev)) netif_wake_queue(ks->netdev); spin_unlock(&ks->statelock); - - handled |= IRQ_TXI; } - if (status & IRQ_RXI) - handled |= IRQ_RXI; - if (status & IRQ_SPIBEI) { netdev_err(ks->netdev, "%s: spi bus error\n", __func__); - handled |= IRQ_SPIBEI; } - ks8851_wrreg16(ks, KS_ISR, handled); - if (status & IRQ_RXI) { /* the datasheet says to disable the rx interrupt during * packet read-out, however we're masking the interrupt * from the device so do not bother masking just the RX * from the device. */ - ks8851_rx_pkts(ks); + __skb_queue_head_init(&rxq); + ks8851_rx_pkts(ks, &rxq); } /* if something stopped the rx process, probably due to wanting @@ -416,6 +394,10 @@ static irqreturn_t ks8851_irq(int irq, void *_ks) if (status & IRQ_LCI) mii_check_link(&ks->mii); + if (status & IRQ_RXI) + while ((skb = __skb_dequeue(&rxq))) + netif_rx(skb); + return IRQ_HANDLED; } diff --git a/drivers/net/ethernet/micrel/ks8851_par.c b/drivers/net/ethernet/micrel/ks8851_par.c index 7f49042484bdcebd05def5bfd8be8956cb3d13df..96fb0ffcedb90232e83b882778d5b652fda83149 100644 --- a/drivers/net/ethernet/micrel/ks8851_par.c +++ b/drivers/net/ethernet/micrel/ks8851_par.c @@ -210,16 +210,6 @@ static void ks8851_wrfifo_par(struct ks8851_net *ks, struct sk_buff *txp, iowrite16_rep(ksp->hw_addr, txp->data, len / 2); } -/** - * ks8851_rx_skb_par - receive skbuff - * @ks: The device state. - * @skb: The skbuff - */ -static void ks8851_rx_skb_par(struct ks8851_net *ks, struct sk_buff *skb) -{ - netif_rx(skb); -} - static unsigned int ks8851_rdreg16_par_txqcr(struct ks8851_net *ks) { return ks8851_rdreg16_par(ks, KS_TXQCR); @@ -298,7 +288,6 @@ static int ks8851_probe_par(struct platform_device *pdev) ks->rdfifo = ks8851_rdfifo_par; ks->wrfifo = ks8851_wrfifo_par; ks->start_xmit = ks8851_start_xmit_par; - ks->rx_skb = ks8851_rx_skb_par; #define STD_IRQ (IRQ_LCI | /* Link Change */ \ IRQ_RXI | /* RX done */ \ diff --git a/drivers/net/ethernet/micrel/ks8851_spi.c b/drivers/net/ethernet/micrel/ks8851_spi.c index 88e26c120b48368bb63e422c692124ef03411ad1..4dcbff789b19dad12c221937c710ab2547588807 100644 --- a/drivers/net/ethernet/micrel/ks8851_spi.c +++ b/drivers/net/ethernet/micrel/ks8851_spi.c @@ -298,16 +298,6 @@ static unsigned int calc_txlen(unsigned int len) return ALIGN(len + 4, 4); } -/** - * ks8851_rx_skb_spi - receive skbuff - * @ks: The device state - * @skb: The skbuff - */ -static void ks8851_rx_skb_spi(struct ks8851_net *ks, struct sk_buff *skb) -{ - netif_rx(skb); -} - /** * ks8851_tx_work - process tx packet(s) * @work: The work strucutre what was scheduled. @@ -435,7 +425,6 @@ static int ks8851_probe_spi(struct spi_device *spi) ks->rdfifo = ks8851_rdfifo_spi; ks->wrfifo = ks8851_wrfifo_spi; ks->start_xmit = ks8851_start_xmit_spi; - ks->rx_skb = ks8851_rx_skb_spi; ks->flush_tx_work = ks8851_flush_tx_work_spi; #define STD_IRQ (IRQ_LCI | /* Link Change */ \ diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index e804613faa1fc16ebbf9f1a9a140d74c894f7268..d5123e8c4a9f48719a9350c2f33f709161ffca8b 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -25,6 +25,8 @@ #define PCS_POWER_STATE_DOWN 0x6 #define PCS_POWER_STATE_UP 0x4 +#define RFE_RD_FIFO_TH_3_DWORDS 0x3 + static void pci11x1x_strap_get_status(struct lan743x_adapter *adapter) { u32 chip_rev; @@ -3217,6 +3219,21 @@ static void lan743x_full_cleanup(struct lan743x_adapter *adapter) lan743x_pci_cleanup(adapter); } +static void pci11x1x_set_rfe_rd_fifo_threshold(struct lan743x_adapter *adapter) +{ + u16 rev = adapter->csr.id_rev & ID_REV_CHIP_REV_MASK_; + + if (rev == ID_REV_CHIP_REV_PCI11X1X_B0_) { + u32 misc_ctl; + + misc_ctl = lan743x_csr_read(adapter, MISC_CTL_0); + misc_ctl &= ~MISC_CTL_0_RFE_READ_FIFO_MASK_; + misc_ctl |= FIELD_PREP(MISC_CTL_0_RFE_READ_FIFO_MASK_, + RFE_RD_FIFO_TH_3_DWORDS); + lan743x_csr_write(adapter, MISC_CTL_0, misc_ctl); + } +} + static int lan743x_hardware_init(struct lan743x_adapter *adapter, struct pci_dev *pdev) { @@ -3232,6 +3249,7 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter, pci11x1x_strap_get_status(adapter); spin_lock_init(&adapter->eth_syslock_spinlock); mutex_init(&adapter->sgmii_rw_lock); + pci11x1x_set_rfe_rd_fifo_threshold(adapter); } else { adapter->max_tx_channels = LAN743X_MAX_TX_CHANNELS; adapter->used_tx_channels = LAN743X_USED_TX_CHANNELS; diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h index 67877d3b6dd9842308401063e20ffc00aeea4df7..d304be17b9d82573ea2c3427d2e476f65b8b4cfc 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.h +++ b/drivers/net/ethernet/microchip/lan743x_main.h @@ -26,6 +26,7 @@ #define ID_REV_CHIP_REV_MASK_ (0x0000FFFF) #define ID_REV_CHIP_REV_A0_ (0x00000000) #define ID_REV_CHIP_REV_B0_ (0x00000010) +#define ID_REV_CHIP_REV_PCI11X1X_B0_ (0x000000B0) #define FPGA_REV (0x04) #define FPGA_REV_GET_MINOR_(fpga_rev) (((fpga_rev) >> 8) & 0x000000FF) @@ -311,6 +312,9 @@ #define SGMII_CTL_LINK_STATUS_SOURCE_ BIT(8) #define SGMII_CTL_SGMII_POWER_DN_ BIT(1) +#define MISC_CTL_0 (0x920) +#define MISC_CTL_0_RFE_READ_FIFO_MASK_ GENMASK(6, 4) + /* Vendor Specific SGMII MMD details */ #define SR_VSMMD_PCS_ID1 0x0004 #define SR_VSMMD_PCS_ID2 0x0005 diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c b/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c index 41fa2523d91d3bf57479dd7d66c1903786aa98b2..5f2cd9a8cf8fb39cef3d6be0806f3a6f9b7cdac7 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c @@ -37,19 +37,24 @@ static void lan966x_lag_set_aggr_pgids(struct lan966x *lan966x) /* Now, set PGIDs for each active LAG */ for (lag = 0; lag < lan966x->num_phys_ports; ++lag) { - struct net_device *bond = lan966x->ports[lag]->bond; + struct lan966x_port *port = lan966x->ports[lag]; int num_active_ports = 0; + struct net_device *bond; unsigned long bond_mask; u8 aggr_idx[16]; - if (!bond || (visited & BIT(lag))) + if (!port || !port->bond || (visited & BIT(lag))) continue; + bond = port->bond; bond_mask = lan966x_lag_get_mask(lan966x, bond); for_each_set_bit(p, &bond_mask, lan966x->num_phys_ports) { struct lan966x_port *port = lan966x->ports[p]; + if (!port) + continue; + lan_wr(ANA_PGID_PGID_SET(bond_mask), lan966x, ANA_PGID(p)); if (port->lag_tx_active) diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c b/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c index 4af285918ea2a45cae16ca01ec1ab8fd3f5370c9..75868b3f548ec40549c02ad1ac2a3c5c388eade4 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c @@ -347,10 +347,10 @@ int sparx5_del_mact_entry(struct sparx5 *sparx5, list) { if ((vid == 0 || mact_entry->vid == vid) && ether_addr_equal(addr, mact_entry->mac)) { + sparx5_mact_forget(sparx5, addr, mact_entry->vid); + list_del(&mact_entry->list); devm_kfree(sparx5->dev, mact_entry); - - sparx5_mact_forget(sparx5, addr, mact_entry->vid); } } mutex_unlock(&sparx5->mact_lock); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c index 3423c95cc84ae35b56865bc1062afdf9dca64f48..7031f41287e0948a0451696167238061c77cd49c 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -744,6 +744,7 @@ static int mchp_sparx5_probe(struct platform_device *pdev) platform_set_drvdata(pdev, sparx5); sparx5->pdev = pdev; sparx5->dev = &pdev->dev; + spin_lock_init(&sparx5->tx_lock); /* Do switch core reset if available */ reset = devm_reset_control_get_optional_shared(&pdev->dev, "switch"); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h index 7a83222caa737bcb1cc13f6a32cb0522659241d0..cb3173d2b0e8d0eb7973312997ef8d6652a8a84d 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h @@ -278,6 +278,7 @@ struct sparx5 { int xtr_irq; /* Frame DMA */ int fdma_irq; + spinlock_t tx_lock; /* lock for frame transmission */ struct sparx5_rx rx; struct sparx5_tx tx; /* PTP */ diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c index 6db6ac6a3bbc26db972e2f611ddd7c72fac29c16..ac7e1cffbcecf0ccc4f89e394730d90ec2ada2f8 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c @@ -244,10 +244,12 @@ netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev) } skb_tx_timestamp(skb); + spin_lock(&sparx5->tx_lock); if (sparx5->fdma_irq > 0) ret = sparx5_fdma_xmit(sparx5, ifh, skb); else ret = sparx5_inject(sparx5, ifh, skb, dev); + spin_unlock(&sparx5->tx_lock); if (ret == -EBUSY) goto busy; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c index 32709d21ab2f9753a5b50a3229677745ad167107..212bf6f4ed72d4869c76ac82a23d3281b7f786cb 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c @@ -730,7 +730,7 @@ static int sparx5_port_pcs_low_set(struct sparx5 *sparx5, bool sgmii = false, inband_aneg = false; int err; - if (port->conf.inband) { + if (conf->inband) { if (conf->portmode == PHY_INTERFACE_MODE_SGMII || conf->portmode == PHY_INTERFACE_MODE_QSGMII) inband_aneg = true; /* Cisco-SGMII in-band-aneg */ @@ -947,7 +947,7 @@ int sparx5_port_pcs_set(struct sparx5 *sparx5, if (err) return -EINVAL; - if (port->conf.inband) { + if (conf->inband) { /* Enable/disable 1G counters in ASM */ spx5_rmw(ASM_PORT_CFG_CSC_STAT_DIS_SET(high_speed_dev), ASM_PORT_CFG_CSC_STAT_DIS, diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c index f7492be452aed47ddde07142c65cd974d4b148ee..497766ecdd91da13961e5cd399e619df9f03f9b9 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c +++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c @@ -1243,7 +1243,7 @@ static int nfp_ct_do_tc_merge(struct nfp_fl_ct_zone_entry *zt, /* Checks that the chain_index of the filter matches the * chain_index of the GOTO action. */ - if (post_ct_entry->chain_index != pre_ct_entry->chain_index) + if (post_ct_entry->chain_index != pre_ct_entry->goto_chain_index) return -EINVAL; err = nfp_ct_merge_check(pre_ct_entry, post_ct_entry); @@ -1379,10 +1379,30 @@ static void nfp_nft_ct_translate_mangle_action(struct flow_action_entry *mangle_ mangle_action->mangle.mask = (__force u32)cpu_to_be32(mangle_action->mangle.mask); return; + /* Both struct tcphdr and struct udphdr start with + * __be16 source; + * __be16 dest; + * so we can use the same code for both. + */ case FLOW_ACT_MANGLE_HDR_TYPE_TCP: case FLOW_ACT_MANGLE_HDR_TYPE_UDP: - mangle_action->mangle.val = (__force u16)cpu_to_be16(mangle_action->mangle.val); - mangle_action->mangle.mask = (__force u16)cpu_to_be16(mangle_action->mangle.mask); + if (mangle_action->mangle.offset == offsetof(struct tcphdr, source)) { + mangle_action->mangle.val = + (__force u32)cpu_to_be32(mangle_action->mangle.val << 16); + /* The mask of mangle action is inverse mask, + * so clear the dest tp port with 0xFFFF to + * instead of rotate-left operation. + */ + mangle_action->mangle.mask = + (__force u32)cpu_to_be32(mangle_action->mangle.mask << 16 | 0xFFFF); + } + if (mangle_action->mangle.offset == offsetof(struct tcphdr, dest)) { + mangle_action->mangle.offset = 0; + mangle_action->mangle.val = + (__force u32)cpu_to_be32(mangle_action->mangle.val); + mangle_action->mangle.mask = + (__force u32)cpu_to_be32(mangle_action->mangle.mask); + } return; default: @@ -1756,7 +1776,8 @@ int nfp_fl_ct_handle_pre_ct(struct nfp_flower_priv *priv, if (IS_ERR(ct_entry)) return PTR_ERR(ct_entry); ct_entry->type = CT_TYPE_PRE_CT; - ct_entry->chain_index = ct_goto->chain_index; + ct_entry->chain_index = flow->common.chain_index; + ct_entry->goto_chain_index = ct_goto->chain_index; list_add(&ct_entry->list_node, &zt->pre_ct_list); zt->pre_ct_count++; @@ -1776,9 +1797,30 @@ int nfp_fl_ct_handle_post_ct(struct nfp_flower_priv *priv, { struct flow_rule *rule = flow_cls_offload_flow_rule(flow); struct nfp_fl_ct_flow_entry *ct_entry; + struct flow_action_entry *ct_goto; struct nfp_fl_ct_zone_entry *zt; + struct flow_action_entry *act; bool wildcarded = false; struct flow_match_ct ct; + int i; + + flow_action_for_each(i, act, &rule->action) { + switch (act->id) { + case FLOW_ACTION_REDIRECT: + case FLOW_ACTION_REDIRECT_INGRESS: + case FLOW_ACTION_MIRRED: + case FLOW_ACTION_MIRRED_INGRESS: + if (act->dev->rtnl_link_ops && + !strcmp(act->dev->rtnl_link_ops->kind, "openvswitch")) { + NL_SET_ERR_MSG_MOD(extack, + "unsupported offload: out port is openvswitch internal port"); + return -EOPNOTSUPP; + } + break; + default: + break; + } + } flow_rule_match_ct(rule, &ct); if (!ct.mask->ct_zone) { @@ -1803,6 +1845,8 @@ int nfp_fl_ct_handle_post_ct(struct nfp_flower_priv *priv, ct_entry->type = CT_TYPE_POST_CT; ct_entry->chain_index = flow->common.chain_index; + ct_goto = get_flow_act(flow->rule, FLOW_ACTION_GOTO); + ct_entry->goto_chain_index = ct_goto ? ct_goto->chain_index : 0; list_add(&ct_entry->list_node, &zt->post_ct_list); zt->post_ct_count++; diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.h b/drivers/net/ethernet/netronome/nfp/flower/conntrack.h index 762c0b36e269b973b812ab03db34f91da7960f9e..9440ab776eceadb6906df3d7becbb2c94563eb52 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/conntrack.h +++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.h @@ -112,6 +112,7 @@ enum nfp_nfp_layer_name { * @cookie: Flow cookie, same as original TC flow, used as key * @list_node: Used by the list * @chain_index: Chain index of the original flow + * @goto_chain_index: goto chain index of the flow * @netdev: netdev structure. * @type: Type of pre-entry from enum ct_entry_type * @zt: Reference to the zone table this belongs to @@ -125,6 +126,7 @@ struct nfp_fl_ct_flow_entry { unsigned long cookie; struct list_head list_node; u32 chain_index; + u32 goto_chain_index; enum ct_entry_type type; struct net_device *netdev; struct nfp_fl_ct_zone_entry *zt; diff --git a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c index e92860e20a24a841526a0847af6cc4816cbcd875..c6a2c302a8c8b7811327c1f07e96e80f9807a12f 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c @@ -308,6 +308,11 @@ static void nfp_fl_lag_do_work(struct work_struct *work) acti_netdevs = kmalloc_array(entry->slave_cnt, sizeof(*acti_netdevs), GFP_KERNEL); + if (!acti_netdevs) { + schedule_delayed_work(&lag->work, + NFP_FL_LAG_DELAY); + continue; + } /* Include sanity check in the loop. It may be that a bond has * changed between processing the last notification and the diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 52f67157bd0f70be1ebd8a76ae9e20798a5aba83..a3c52c91a575de19c7259bb68b383928d01760a3 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -980,7 +980,7 @@ nfp_tunnel_add_shared_mac(struct nfp_app *app, struct net_device *netdev, u16 nfp_mac_idx = 0; entry = nfp_tunnel_lookup_offloaded_macs(app, netdev->dev_addr); - if (entry && nfp_tunnel_is_mac_idx_global(entry->index)) { + if (entry && (nfp_tunnel_is_mac_idx_global(entry->index) || netif_is_lag_port(netdev))) { if (entry->bridge_count || !nfp_flower_is_supported_bridge(netdev)) { nfp_tunnel_offloaded_macs_inc_ref_and_link(entry, diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c index 33b4c28563162eeab3938da414b32cfd480c13d7..3f10c5365c80ebb2fe079b779fee644a46ed33da 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c @@ -537,11 +537,13 @@ static int enable_bars(struct nfp6000_pcie *nfp, u16 interface) const u32 barcfg_msix_general = NFP_PCIE_BAR_PCIE2CPP_MapType( NFP_PCIE_BAR_PCIE2CPP_MapType_GENERAL) | - NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT; + NFP_PCIE_BAR_PCIE2CPP_LengthSelect( + NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT); const u32 barcfg_msix_xpb = NFP_PCIE_BAR_PCIE2CPP_MapType( NFP_PCIE_BAR_PCIE2CPP_MapType_BULK) | - NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT | + NFP_PCIE_BAR_PCIE2CPP_LengthSelect( + NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT) | NFP_PCIE_BAR_PCIE2CPP_Target_BaseAddress( NFP_CPP_TARGET_ISLAND_XPB); const u32 barcfg_explicit[4] = { diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index fcc3faecb0600b5402200b351622a9a90afec199..d33cf8ee7c3362e52eb3bc14b5db2f7ca47c9a92 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -3216,9 +3216,12 @@ static int ionic_lif_adminq_init(struct ionic_lif *lif) napi_enable(&qcq->napi); - if (qcq->flags & IONIC_QCQ_F_INTR) + if (qcq->flags & IONIC_QCQ_F_INTR) { + irq_set_affinity_hint(qcq->intr.vector, + &qcq->intr.affinity_mask); ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, IONIC_INTR_MASK_CLEAR); + } qcq->flags |= IONIC_QCQ_F_INITED; diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index 3010833ddde33d6278172915d322dd56130701dc..8871099b99d8ab9b876670232b32fd09ad6c5198 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -1868,8 +1868,8 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto, struct flow_cls_offload *f) { struct qede_arfs_fltr_node *n; - int min_hlen, rc = -EINVAL; struct qede_arfs_tuple t; + int min_hlen, rc; __qede_lock(edev); @@ -1879,7 +1879,8 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto, } /* parse flower attribute and prepare filter */ - if (qede_parse_flow_attr(edev, proto, f->rule, &t)) + rc = qede_parse_flow_attr(edev, proto, f->rule, &t); + if (rc) goto unlock; /* Validate profile mode and number of filters */ @@ -1888,11 +1889,13 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto, DP_NOTICE(edev, "Filter configuration invalidated, filter mode=0x%x, configured mode=0x%x, filter count=0x%x\n", t.mode, edev->arfs->mode, edev->arfs->filter_count); + rc = -EINVAL; goto unlock; } /* parse tc actions and get the vf_id */ - if (qede_parse_actions(edev, &f->rule->action, f->common.extack)) + rc = qede_parse_actions(edev, &f->rule->action, f->common.extack); + if (rc) goto unlock; if (qede_flow_find_fltr(edev, &t)) { @@ -1998,10 +2001,9 @@ static int qede_flow_spec_to_rule(struct qede_dev *edev, if (IS_ERR(flow)) return PTR_ERR(flow); - if (qede_parse_flow_attr(edev, proto, flow->rule, t)) { - err = -EINVAL; + err = qede_parse_flow_attr(edev, proto, flow->rule, t); + if (err) goto err_out; - } /* Make sure location is valid and filter isn't already set */ err = qede_flow_spec_validate(edev, &flow->rule->action, t, diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 06663c11ca96d7c61e9d10b175877385801c58e7..6e3417712e402bd2adb80e84596a3769d9fea073 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -615,6 +615,9 @@ struct rtl8169_private { struct work_struct work; } wk; + spinlock_t config25_lock; + spinlock_t mac_ocp_lock; + unsigned supports_gmii:1; unsigned aspm_manageable:1; unsigned dash_enabled:1; @@ -678,6 +681,28 @@ static void rtl_pci_commit(struct rtl8169_private *tp) RTL_R8(tp, ChipCmd); } +static void rtl_mod_config2(struct rtl8169_private *tp, u8 clear, u8 set) +{ + unsigned long flags; + u8 val; + + spin_lock_irqsave(&tp->config25_lock, flags); + val = RTL_R8(tp, Config2); + RTL_W8(tp, Config2, (val & ~clear) | set); + spin_unlock_irqrestore(&tp->config25_lock, flags); +} + +static void rtl_mod_config5(struct rtl8169_private *tp, u8 clear, u8 set) +{ + unsigned long flags; + u8 val; + + spin_lock_irqsave(&tp->config25_lock, flags); + val = RTL_R8(tp, Config5); + RTL_W8(tp, Config5, (val & ~clear) | set); + spin_unlock_irqrestore(&tp->config25_lock, flags); +} + static bool rtl_is_8125(struct rtl8169_private *tp) { return tp->mac_version >= RTL_GIGA_MAC_VER_61; @@ -850,7 +875,7 @@ static int r8168_phy_ocp_read(struct rtl8169_private *tp, u32 reg) (RTL_R32(tp, GPHY_OCP) & 0xffff) : -ETIMEDOUT; } -static void r8168_mac_ocp_write(struct rtl8169_private *tp, u32 reg, u32 data) +static void __r8168_mac_ocp_write(struct rtl8169_private *tp, u32 reg, u32 data) { if (rtl_ocp_reg_failure(reg)) return; @@ -858,7 +883,16 @@ static void r8168_mac_ocp_write(struct rtl8169_private *tp, u32 reg, u32 data) RTL_W32(tp, OCPDR, OCPAR_FLAG | (reg << 15) | data); } -static u16 r8168_mac_ocp_read(struct rtl8169_private *tp, u32 reg) +static void r8168_mac_ocp_write(struct rtl8169_private *tp, u32 reg, u32 data) +{ + unsigned long flags; + + spin_lock_irqsave(&tp->mac_ocp_lock, flags); + __r8168_mac_ocp_write(tp, reg, data); + spin_unlock_irqrestore(&tp->mac_ocp_lock, flags); +} + +static u16 __r8168_mac_ocp_read(struct rtl8169_private *tp, u32 reg) { if (rtl_ocp_reg_failure(reg)) return 0; @@ -868,12 +902,28 @@ static u16 r8168_mac_ocp_read(struct rtl8169_private *tp, u32 reg) return RTL_R32(tp, OCPDR); } +static u16 r8168_mac_ocp_read(struct rtl8169_private *tp, u32 reg) +{ + unsigned long flags; + u16 val; + + spin_lock_irqsave(&tp->mac_ocp_lock, flags); + val = __r8168_mac_ocp_read(tp, reg); + spin_unlock_irqrestore(&tp->mac_ocp_lock, flags); + + return val; +} + static void r8168_mac_ocp_modify(struct rtl8169_private *tp, u32 reg, u16 mask, u16 set) { - u16 data = r8168_mac_ocp_read(tp, reg); + unsigned long flags; + u16 data; - r8168_mac_ocp_write(tp, reg, (data & ~mask) | set); + spin_lock_irqsave(&tp->mac_ocp_lock, flags); + data = __r8168_mac_ocp_read(tp, reg); + __r8168_mac_ocp_write(tp, reg, (data & ~mask) | set); + spin_unlock_irqrestore(&tp->mac_ocp_lock, flags); } /* Work around a hw issue with RTL8168g PHY, the quirk disables @@ -1135,17 +1185,40 @@ static void rtl8168ep_stop_cmac(struct rtl8169_private *tp) RTL_W8(tp, IBCR0, RTL_R8(tp, IBCR0) & ~0x01); } +static void rtl_dash_loop_wait(struct rtl8169_private *tp, + const struct rtl_cond *c, + unsigned long usecs, int n, bool high) +{ + if (!tp->dash_enabled) + return; + rtl_loop_wait(tp, c, usecs, n, high); +} + +static void rtl_dash_loop_wait_high(struct rtl8169_private *tp, + const struct rtl_cond *c, + unsigned long d, int n) +{ + rtl_dash_loop_wait(tp, c, d, n, true); +} + +static void rtl_dash_loop_wait_low(struct rtl8169_private *tp, + const struct rtl_cond *c, + unsigned long d, int n) +{ + rtl_dash_loop_wait(tp, c, d, n, false); +} + static void rtl8168dp_driver_start(struct rtl8169_private *tp) { r8168dp_oob_notify(tp, OOB_CMD_DRIVER_START); - rtl_loop_wait_high(tp, &rtl_dp_ocp_read_cond, 10000, 10); + rtl_dash_loop_wait_high(tp, &rtl_dp_ocp_read_cond, 10000, 10); } static void rtl8168ep_driver_start(struct rtl8169_private *tp) { r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_START); r8168ep_ocp_write(tp, 0x01, 0x30, r8168ep_ocp_read(tp, 0x30) | 0x01); - rtl_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 30); + rtl_dash_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 30); } static void rtl8168_driver_start(struct rtl8169_private *tp) @@ -1159,7 +1232,7 @@ static void rtl8168_driver_start(struct rtl8169_private *tp) static void rtl8168dp_driver_stop(struct rtl8169_private *tp) { r8168dp_oob_notify(tp, OOB_CMD_DRIVER_STOP); - rtl_loop_wait_low(tp, &rtl_dp_ocp_read_cond, 10000, 10); + rtl_dash_loop_wait_low(tp, &rtl_dp_ocp_read_cond, 10000, 10); } static void rtl8168ep_driver_stop(struct rtl8169_private *tp) @@ -1167,7 +1240,7 @@ static void rtl8168ep_driver_stop(struct rtl8169_private *tp) rtl8168ep_stop_cmac(tp); r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_STOP); r8168ep_ocp_write(tp, 0x01, 0x30, r8168ep_ocp_read(tp, 0x30) | 0x01); - rtl_loop_wait_low(tp, &rtl_ep_ocp_read_cond, 10000, 10); + rtl_dash_loop_wait_low(tp, &rtl_ep_ocp_read_cond, 10000, 10); } static void rtl8168_driver_stop(struct rtl8169_private *tp) @@ -1351,6 +1424,7 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) { WAKE_MAGIC, Config3, MagicPacket } }; unsigned int i, tmp = ARRAY_SIZE(cfg); + unsigned long flags; u8 options; rtl_unlock_config_regs(tp); @@ -1369,12 +1443,14 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) r8168_mac_ocp_modify(tp, 0xc0b6, BIT(0), 0); } + spin_lock_irqsave(&tp->config25_lock, flags); for (i = 0; i < tmp; i++) { options = RTL_R8(tp, cfg[i].reg) & ~cfg[i].mask; if (wolopts & cfg[i].opt) options |= cfg[i].mask; RTL_W8(tp, cfg[i].reg, options); } + spin_unlock_irqrestore(&tp->config25_lock, flags); switch (tp->mac_version) { case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_06: @@ -1386,10 +1462,10 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) case RTL_GIGA_MAC_VER_34: case RTL_GIGA_MAC_VER_37: case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_63: - options = RTL_R8(tp, Config2) & ~PME_SIGNAL; if (wolopts) - options |= PME_SIGNAL; - RTL_W8(tp, Config2, options); + rtl_mod_config2(tp, 0, PME_SIGNAL); + else + rtl_mod_config2(tp, PME_SIGNAL, 0); break; default: break; @@ -2696,10 +2772,13 @@ static void rtl_disable_exit_l1(struct rtl8169_private *tp) static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable) { + if (tp->mac_version < RTL_GIGA_MAC_VER_32) + return; + /* Don't enable ASPM in the chip if OS can't control ASPM */ if (enable && tp->aspm_manageable) { - RTL_W8(tp, Config5, RTL_R8(tp, Config5) | ASPM_en); - RTL_W8(tp, Config2, RTL_R8(tp, Config2) | ClkReqEn); + rtl_mod_config5(tp, 0, ASPM_en); + rtl_mod_config2(tp, 0, ClkReqEn); switch (tp->mac_version) { case RTL_GIGA_MAC_VER_46 ... RTL_GIGA_MAC_VER_48: @@ -2722,11 +2801,9 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable) break; } - RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); - RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); + rtl_mod_config2(tp, ClkReqEn, 0); + rtl_mod_config5(tp, ASPM_en, 0); } - - udelay(10); } static void rtl_set_fifo_size(struct rtl8169_private *tp, u16 rx_stat, @@ -2884,7 +2961,7 @@ static void rtl_hw_start_8168e_1(struct rtl8169_private *tp) RTL_W32(tp, MISC, RTL_R32(tp, MISC) | TXPLA_RST); RTL_W32(tp, MISC, RTL_R32(tp, MISC) & ~TXPLA_RST); - RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~Spi_en); + rtl_mod_config5(tp, Spi_en, 0); } static void rtl_hw_start_8168e_2(struct rtl8169_private *tp) @@ -2917,7 +2994,7 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp) RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN); RTL_W32(tp, MISC, RTL_R32(tp, MISC) | PWM_EN); - RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~Spi_en); + rtl_mod_config5(tp, Spi_en, 0); rtl_hw_aspm_clkreq_enable(tp, true); } @@ -2940,7 +3017,7 @@ static void rtl_hw_start_8168f(struct rtl8169_private *tp) RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB); RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN); RTL_W32(tp, MISC, RTL_R32(tp, MISC) | PWM_EN); - RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~Spi_en); + rtl_mod_config5(tp, Spi_en, 0); rtl8168_config_eee_mac(tp); } @@ -5032,6 +5109,15 @@ static int r8169_mdio_register(struct rtl8169_private *tp) struct mii_bus *new_bus; int ret; + /* On some boards with this chip version the BIOS is buggy and misses + * to reset the PHY page selector. This results in the PHY ID read + * accessing registers on a different page, returning a more or + * less random value. Fix this by resetting the page selector first. + */ + if (tp->mac_version == RTL_GIGA_MAC_VER_25 || + tp->mac_version == RTL_GIGA_MAC_VER_26) + r8169_mdio_write(tp, 0x1f, 0); + new_bus = devm_mdiobus_alloc(&pdev->dev); if (!new_bus) return -ENOMEM; @@ -5062,7 +5148,7 @@ static int r8169_mdio_register(struct rtl8169_private *tp) return -EUNATCH; } - tp->phydev->mac_managed_pm = 1; + tp->phydev->mac_managed_pm = true; phy_support_asym_pause(tp->phydev); @@ -5200,6 +5286,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->eee_adv = -1; tp->ocp_base = OCP_STD_PHY_BASE; + spin_lock_init(&tp->config25_lock); + spin_lock_init(&tp->mac_ocp_lock); + dev->tstats = devm_netdev_alloc_pcpu_stats(&pdev->dev, struct pcpu_sw_netstats); if (!dev->tstats) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index e7b70006261f78c8d0ebcd04939dfea212970b07..756ac4a07f60bf5fe64de6cdd7b0fef9ccc39422 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1290,25 +1290,16 @@ static int ravb_poll(struct napi_struct *napi, int budget) struct net_device *ndev = napi->dev; struct ravb_private *priv = netdev_priv(ndev); const struct ravb_hw_info *info = priv->info; - bool gptp = info->gptp || info->ccc_gac; - struct ravb_rx_desc *desc; unsigned long flags; int q = napi - priv->napi; int mask = BIT(q); int quota = budget; - unsigned int entry; + bool unmask; - if (!gptp) { - entry = priv->cur_rx[q] % priv->num_rx_ring[q]; - desc = &priv->gbeth_rx_ring[entry]; - } /* Processing RX Descriptor Ring */ /* Clear RX interrupt */ ravb_write(ndev, ~(mask | RIS0_RESERVED), RIS0); - if (gptp || desc->die_dt != DT_FEMPTY) { - if (ravb_rx(ndev, "a, q)) - goto out; - } + unmask = !ravb_rx(ndev, "a, q); /* Processing TX Descriptor Ring */ spin_lock_irqsave(&priv->lock, flags); @@ -1318,6 +1309,18 @@ static int ravb_poll(struct napi_struct *napi, int budget) netif_wake_subqueue(ndev, q); spin_unlock_irqrestore(&priv->lock, flags); + /* Receive error message handling */ + priv->rx_over_errors = priv->stats[RAVB_BE].rx_over_errors; + if (info->nc_queues) + priv->rx_over_errors += priv->stats[RAVB_NC].rx_over_errors; + if (priv->rx_over_errors != ndev->stats.rx_over_errors) + ndev->stats.rx_over_errors = priv->rx_over_errors; + if (priv->rx_fifo_errors != ndev->stats.rx_fifo_errors) + ndev->stats.rx_fifo_errors = priv->rx_fifo_errors; + + if (!unmask) + goto out; + napi_complete(napi); /* Re-enable RX/TX interrupts */ @@ -1331,14 +1334,6 @@ static int ravb_poll(struct napi_struct *napi, int budget) } spin_unlock_irqrestore(&priv->lock, flags); - /* Receive error message handling */ - priv->rx_over_errors = priv->stats[RAVB_BE].rx_over_errors; - if (info->nc_queues) - priv->rx_over_errors += priv->stats[RAVB_NC].rx_over_errors; - if (priv->rx_over_errors != ndev->stats.rx_over_errors) - ndev->stats.rx_over_errors = priv->rx_over_errors; - if (priv->rx_fifo_errors != ndev->stats.rx_fifo_errors) - ndev->stats.rx_fifo_errors = priv->rx_fifo_errors; out: return budget - quota; } diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 54bb072aeb2d3c39950b96aca0203dc0b367cf95..c11d626856247b3d9cf6af201d6a9f5e757c699e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -209,6 +209,7 @@ struct stmmac_safety_stats { unsigned long mac_errors[32]; unsigned long mtl_errors[32]; unsigned long dma_errors[32]; + unsigned long dma_dpp_errors[32]; }; /* Number of fields in Safety Stats */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 84276eb681d707ea786127af0680727a99369bed..39112d5cb5b800fe46e01a38529b16fe22f7b3b2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -87,19 +87,41 @@ static void dwmac4_rx_queue_priority(struct mac_device_info *hw, u32 prio, u32 queue) { void __iomem *ioaddr = hw->pcsr; - u32 base_register; - u32 value; + u32 clear_mask = 0; + u32 ctrl2, ctrl3; + int i; - base_register = (queue < 4) ? GMAC_RXQ_CTRL2 : GMAC_RXQ_CTRL3; - if (queue >= 4) - queue -= 4; + ctrl2 = readl(ioaddr + GMAC_RXQ_CTRL2); + ctrl3 = readl(ioaddr + GMAC_RXQ_CTRL3); - value = readl(ioaddr + base_register); + /* The software must ensure that the same priority + * is not mapped to multiple Rx queues + */ + for (i = 0; i < 4; i++) + clear_mask |= ((prio << GMAC_RXQCTRL_PSRQX_SHIFT(i)) & + GMAC_RXQCTRL_PSRQX_MASK(i)); - value &= ~GMAC_RXQCTRL_PSRQX_MASK(queue); - value |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) & + ctrl2 &= ~clear_mask; + ctrl3 &= ~clear_mask; + + /* First assign new priorities to a queue, then + * clear them from others queues + */ + if (queue < 4) { + ctrl2 |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) & GMAC_RXQCTRL_PSRQX_MASK(queue); - writel(value, ioaddr + base_register); + + writel(ctrl2, ioaddr + GMAC_RXQ_CTRL2); + writel(ctrl3, ioaddr + GMAC_RXQ_CTRL3); + } else { + queue -= 4; + + ctrl3 |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) & + GMAC_RXQCTRL_PSRQX_MASK(queue); + + writel(ctrl3, ioaddr + GMAC_RXQ_CTRL3); + writel(ctrl2, ioaddr + GMAC_RXQ_CTRL2); + } } static void dwmac4_tx_queue_priority(struct mac_device_info *hw, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index 880a75bf2eb1f03bd85e66a8eafd17b5b2e018c9..8748c37e9dac921c18390ae13f87c2de1fbf93ab 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -282,6 +282,8 @@ #define XGMAC_RXCEIE BIT(4) #define XGMAC_TXCEIE BIT(0) #define XGMAC_MTL_ECC_INT_STATUS 0x000010cc +#define XGMAC_MTL_DPP_CONTROL 0x000010e0 +#define XGMAC_DPP_DISABLE BIT(0) #define XGMAC_MTL_TXQ_OPMODE(x) (0x00001100 + (0x80 * (x))) #define XGMAC_TQS GENMASK(25, 16) #define XGMAC_TQS_SHIFT 16 @@ -364,6 +366,7 @@ #define XGMAC_DCEIE BIT(1) #define XGMAC_TCEIE BIT(0) #define XGMAC_DMA_ECC_INT_STATUS 0x0000306c +#define XGMAC_DMA_DPP_INT_STATUS 0x00003074 #define XGMAC_DMA_CH_CONTROL(x) (0x00003100 + (0x80 * (x))) #define XGMAC_SPH BIT(24) #define XGMAC_PBLx8 BIT(16) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index c2181c277291bd2f3072302203e607a5d6b639cb..dd73f38ec08d809aad19269ee8f39693ffd7c07e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -97,17 +97,41 @@ static void dwxgmac2_rx_queue_prio(struct mac_device_info *hw, u32 prio, u32 queue) { void __iomem *ioaddr = hw->pcsr; - u32 value, reg; + u32 clear_mask = 0; + u32 ctrl2, ctrl3; + int i; - reg = (queue < 4) ? XGMAC_RXQ_CTRL2 : XGMAC_RXQ_CTRL3; - if (queue >= 4) + ctrl2 = readl(ioaddr + XGMAC_RXQ_CTRL2); + ctrl3 = readl(ioaddr + XGMAC_RXQ_CTRL3); + + /* The software must ensure that the same priority + * is not mapped to multiple Rx queues + */ + for (i = 0; i < 4; i++) + clear_mask |= ((prio << XGMAC_PSRQ_SHIFT(i)) & + XGMAC_PSRQ(i)); + + ctrl2 &= ~clear_mask; + ctrl3 &= ~clear_mask; + + /* First assign new priorities to a queue, then + * clear them from others queues + */ + if (queue < 4) { + ctrl2 |= (prio << XGMAC_PSRQ_SHIFT(queue)) & + XGMAC_PSRQ(queue); + + writel(ctrl2, ioaddr + XGMAC_RXQ_CTRL2); + writel(ctrl3, ioaddr + XGMAC_RXQ_CTRL3); + } else { queue -= 4; - value = readl(ioaddr + reg); - value &= ~XGMAC_PSRQ(queue); - value |= (prio << XGMAC_PSRQ_SHIFT(queue)) & XGMAC_PSRQ(queue); + ctrl3 |= (prio << XGMAC_PSRQ_SHIFT(queue)) & + XGMAC_PSRQ(queue); - writel(value, ioaddr + reg); + writel(ctrl3, ioaddr + XGMAC_RXQ_CTRL3); + writel(ctrl2, ioaddr + XGMAC_RXQ_CTRL2); + } } static void dwxgmac2_tx_queue_prio(struct mac_device_info *hw, u32 prio, @@ -789,6 +813,44 @@ static const struct dwxgmac3_error_desc dwxgmac3_dma_errors[32]= { { false, "UNKNOWN", "Unknown Error" }, /* 31 */ }; +#define DPP_RX_ERR "Read Rx Descriptor Parity checker Error" +#define DPP_TX_ERR "Read Tx Descriptor Parity checker Error" + +static const struct dwxgmac3_error_desc dwxgmac3_dma_dpp_errors[32] = { + { true, "TDPES0", DPP_TX_ERR }, + { true, "TDPES1", DPP_TX_ERR }, + { true, "TDPES2", DPP_TX_ERR }, + { true, "TDPES3", DPP_TX_ERR }, + { true, "TDPES4", DPP_TX_ERR }, + { true, "TDPES5", DPP_TX_ERR }, + { true, "TDPES6", DPP_TX_ERR }, + { true, "TDPES7", DPP_TX_ERR }, + { true, "TDPES8", DPP_TX_ERR }, + { true, "TDPES9", DPP_TX_ERR }, + { true, "TDPES10", DPP_TX_ERR }, + { true, "TDPES11", DPP_TX_ERR }, + { true, "TDPES12", DPP_TX_ERR }, + { true, "TDPES13", DPP_TX_ERR }, + { true, "TDPES14", DPP_TX_ERR }, + { true, "TDPES15", DPP_TX_ERR }, + { true, "RDPES0", DPP_RX_ERR }, + { true, "RDPES1", DPP_RX_ERR }, + { true, "RDPES2", DPP_RX_ERR }, + { true, "RDPES3", DPP_RX_ERR }, + { true, "RDPES4", DPP_RX_ERR }, + { true, "RDPES5", DPP_RX_ERR }, + { true, "RDPES6", DPP_RX_ERR }, + { true, "RDPES7", DPP_RX_ERR }, + { true, "RDPES8", DPP_RX_ERR }, + { true, "RDPES9", DPP_RX_ERR }, + { true, "RDPES10", DPP_RX_ERR }, + { true, "RDPES11", DPP_RX_ERR }, + { true, "RDPES12", DPP_RX_ERR }, + { true, "RDPES13", DPP_RX_ERR }, + { true, "RDPES14", DPP_RX_ERR }, + { true, "RDPES15", DPP_RX_ERR }, +}; + static void dwxgmac3_handle_dma_err(struct net_device *ndev, void __iomem *ioaddr, bool correctable, struct stmmac_safety_stats *stats) @@ -800,6 +862,13 @@ static void dwxgmac3_handle_dma_err(struct net_device *ndev, dwxgmac3_log_error(ndev, value, correctable, "DMA", dwxgmac3_dma_errors, STAT_OFF(dma_errors), stats); + + value = readl(ioaddr + XGMAC_DMA_DPP_INT_STATUS); + writel(value, ioaddr + XGMAC_DMA_DPP_INT_STATUS); + + dwxgmac3_log_error(ndev, value, false, "DMA_DPP", + dwxgmac3_dma_dpp_errors, + STAT_OFF(dma_dpp_errors), stats); } static int @@ -838,6 +907,12 @@ dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp, value |= XGMAC_TMOUTEN; /* FSM Timeout Feature */ writel(value, ioaddr + XGMAC_MAC_FSM_CONTROL); + /* 5. Enable Data Path Parity Protection */ + value = readl(ioaddr + XGMAC_MTL_DPP_CONTROL); + /* already enabled by default, explicit enable it again */ + value &= ~XGMAC_DPP_DISABLE; + writel(value, ioaddr + XGMAC_MTL_DPP_CONTROL); + return 0; } @@ -871,7 +946,11 @@ static int dwxgmac3_safety_feat_irq_status(struct net_device *ndev, ret |= !corr; } - err = dma & (XGMAC_DEUIS | XGMAC_DECIS); + /* DMA_DPP_Interrupt_Status is indicated by MCSIS bit in + * DMA_Safety_Interrupt_Status, so we handle DMA Data Path + * Parity Errors here + */ + err = dma & (XGMAC_DEUIS | XGMAC_DECIS | XGMAC_MCSIS); corr = dma & XGMAC_DECIS; if (err) { dwxgmac3_handle_dma_err(ndev, ioaddr, corr, stats); @@ -887,6 +966,7 @@ static const struct dwxgmac3_error { { dwxgmac3_mac_errors }, { dwxgmac3_mtl_errors }, { dwxgmac3_dma_errors }, + { dwxgmac3_dma_dpp_errors }, }; static int dwxgmac3_safety_feat_dump(struct stmmac_safety_stats *stats, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index e988a60c8561b5bb3bc972fa9e1363ec4a212690..e2d51014ab4bc8235b0002a492c4788fabbb8dd4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3826,6 +3826,9 @@ static int __stmmac_open(struct net_device *dev, priv->rx_copybreak = STMMAC_RX_COPYBREAK; buf_sz = dma_conf->dma_buf_sz; + for (int i = 0; i < MTL_MAX_TX_QUEUES; i++) + if (priv->dma_conf.tx_queue[i].tbs & STMMAC_TBS_EN) + dma_conf->tx_queue[i].tbs = priv->dma_conf.tx_queue[i].tbs; memcpy(&priv->dma_conf, dma_conf, sizeof(*dma_conf)); stmmac_reset_queues_param(priv); @@ -3897,8 +3900,10 @@ static void stmmac_fpe_stop_wq(struct stmmac_priv *priv) { set_bit(__FPE_REMOVING, &priv->fpe_task_state); - if (priv->fpe_wq) + if (priv->fpe_wq) { destroy_workqueue(priv->fpe_wq); + priv->fpe_wq = NULL; + } netdev_info(priv->dev, "FPE workqueue stop"); } @@ -5820,11 +5825,6 @@ static irqreturn_t stmmac_mac_interrupt(int irq, void *dev_id) struct net_device *dev = (struct net_device *)dev_id; struct stmmac_priv *priv = netdev_priv(dev); - if (unlikely(!dev)) { - netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__); - return IRQ_NONE; - } - /* Check if adapter is up */ if (test_bit(STMMAC_DOWN, &priv->state)) return IRQ_HANDLED; @@ -5840,11 +5840,6 @@ static irqreturn_t stmmac_safety_interrupt(int irq, void *dev_id) struct net_device *dev = (struct net_device *)dev_id; struct stmmac_priv *priv = netdev_priv(dev); - if (unlikely(!dev)) { - netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__); - return IRQ_NONE; - } - /* Check if adapter is up */ if (test_bit(STMMAC_DOWN, &priv->state)) return IRQ_HANDLED; @@ -5866,11 +5861,6 @@ static irqreturn_t stmmac_msi_intr_tx(int irq, void *data) dma_conf = container_of(tx_q, struct stmmac_dma_conf, tx_queue[chan]); priv = container_of(dma_conf, struct stmmac_priv, dma_conf); - if (unlikely(!data)) { - netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__); - return IRQ_NONE; - } - /* Check if adapter is up */ if (test_bit(STMMAC_DOWN, &priv->state)) return IRQ_HANDLED; @@ -5897,11 +5887,6 @@ static irqreturn_t stmmac_msi_intr_rx(int irq, void *data) dma_conf = container_of(rx_q, struct stmmac_dma_conf, rx_queue[chan]); priv = container_of(dma_conf, struct stmmac_priv, dma_conf); - if (unlikely(!data)) { - netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__); - return IRQ_NONE; - } - /* Check if adapter is up */ if (test_bit(STMMAC_DOWN, &priv->state)) return IRQ_HANDLED; diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 76fabeae512dbe42f2e4d31c8eee88738cbbfb72..33df06a2de13ad2c1f88561e83916628a5833868 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -2549,6 +2549,8 @@ static void am65_cpsw_unregister_devlink(struct am65_cpsw_common *common) static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) { + struct am65_cpsw_rx_chn *rx_chan = &common->rx_chns; + struct am65_cpsw_tx_chn *tx_chan = common->tx_chns; struct device *dev = common->dev; struct devlink_port *dl_port; struct am65_cpsw_port *port; @@ -2567,6 +2569,22 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) return ret; } + /* The DMA Channels are not guaranteed to be in a clean state. + * Reset and disable them to ensure that they are back to the + * clean state and ready to be used. + */ + for (i = 0; i < common->tx_ch_num; i++) { + k3_udma_glue_reset_tx_chn(tx_chan[i].tx_chn, &tx_chan[i], + am65_cpsw_nuss_tx_cleanup); + k3_udma_glue_disable_tx_chn(tx_chan[i].tx_chn); + } + + for (i = 0; i < AM65_CPSW_MAX_RX_FLOWS; i++) + k3_udma_glue_reset_rx_chn(rx_chan->rx_chn, i, rx_chan, + am65_cpsw_nuss_rx_cleanup, !!i); + + k3_udma_glue_disable_rx_chn(rx_chan->rx_chn); + ret = am65_cpsw_nuss_register_devlink(common); if (ret) return ret; diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c index 9948ac14e68db3764ad50fb9ff798d631b923b33..c1bdf045e98157bf879409176c0e9bb4f73c94a3 100644 --- a/drivers/net/ethernet/ti/am65-cpts.c +++ b/drivers/net/ethernet/ti/am65-cpts.c @@ -649,6 +649,11 @@ static bool am65_cpts_match_tx_ts(struct am65_cpts *cpts, struct am65_cpts_skb_cb_data *skb_cb = (struct am65_cpts_skb_cb_data *)skb->cb; + if ((ptp_classify_raw(skb) & PTP_CLASS_V1) && + ((mtype_seqid & AM65_CPTS_EVENT_1_SEQUENCE_ID_MASK) == + (skb_cb->skb_mtype_seqid & AM65_CPTS_EVENT_1_SEQUENCE_ID_MASK))) + mtype_seqid = skb_cb->skb_mtype_seqid; + if (mtype_seqid == skb_cb->skb_mtype_seqid) { u64 ns = event->timestamp; diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 13c9c2d6b79bbada479af66db547a71464ecb325..d95771ca4e5a362c7fe140e662f7a52b5c2bf715 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -631,6 +631,8 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv) } } + phy->mac_managed_pm = true; + slave->phy = phy; phy_attached_info(slave->phy); diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 83596ec0c7cb9b0527ebff58f43928b36dbcc01f..6e70aa1cc7bf12db7e48b5105ee78096bc631c99 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -772,6 +772,9 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv) slave->slave_num); return; } + + phy->mac_managed_pm = true; + slave->phy = phy; phy_attached_info(slave->phy); diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index 6bf5e341c3c1179cc617289cad7483ba7ffba2dc..08c45756b2181c98d3a739d16bd91915de680030 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -1445,7 +1445,7 @@ static int temac_probe(struct platform_device *pdev) } /* map device registers */ - lp->regs = devm_platform_ioremap_resource_byname(pdev, 0); + lp->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(lp->regs)) { dev_err(&pdev->dev, "could not map TEMAC registers\n"); return -ENOMEM; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index f393e454f45ca1cda064f112cb2ba1742569d4e7..488ca1c85496281b3460eb80f8b1b3b79ee12899 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -221,7 +221,7 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, struct genevehdr *gnvh = geneve_hdr(skb); struct metadata_dst *tun_dst = NULL; unsigned int len; - int err = 0; + int nh, err = 0; void *oiph; if (ip_tunnel_collect_metadata() || gs->collect_md) { @@ -272,9 +272,23 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, skb->pkt_type = PACKET_HOST; } - oiph = skb_network_header(skb); + /* Save offset of outer header relative to skb->head, + * because we are going to reset the network header to the inner header + * and might change skb->head. + */ + nh = skb_network_header(skb) - skb->head; + skb_reset_network_header(skb); + if (!pskb_inet_may_pull(skb)) { + DEV_STATS_INC(geneve->dev, rx_length_errors); + DEV_STATS_INC(geneve->dev, rx_errors); + goto drop; + } + + /* Get the outer header. */ + oiph = skb->head + nh; + if (geneve_get_sk_family(gs) == AF_INET) err = IP_ECN_decapsulate(oiph, skb); #if IS_ENABLED(CONFIG_IPV6) @@ -916,7 +930,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, __be16 sport; int err; - if (!pskb_inet_may_pull(skb)) + if (!skb_vlan_inet_prepare(skb)) return -EINVAL; sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); @@ -1014,7 +1028,7 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, __be16 sport; int err; - if (!pskb_inet_may_pull(skb)) + if (!skb_vlan_inet_prepare(skb)) return -EINVAL; sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index bace989591f75490cd813bfbbb7838699767fc0a..05b5914d83582bb9a64324c5b92da64e0428dde8 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1110,11 +1110,12 @@ out_hashtable: static void gtp_dellink(struct net_device *dev, struct list_head *head) { struct gtp_dev *gtp = netdev_priv(dev); + struct hlist_node *next; struct pdp_ctx *pctx; int i; for (i = 0; i < gtp->hash_size; i++) - hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) + hlist_for_each_entry_safe(pctx, next, >p->tid_hash[i], hlist_tid) pdp_context_delete(pctx); list_del_rcu(>p->list); @@ -1902,26 +1903,26 @@ static int __init gtp_init(void) get_random_bytes(>p_h_initval, sizeof(gtp_h_initval)); - err = rtnl_link_register(>p_link_ops); + err = register_pernet_subsys(>p_net_ops); if (err < 0) goto error_out; - err = genl_register_family(>p_genl_family); + err = rtnl_link_register(>p_link_ops); if (err < 0) - goto unreg_rtnl_link; + goto unreg_pernet_subsys; - err = register_pernet_subsys(>p_net_ops); + err = genl_register_family(>p_genl_family); if (err < 0) - goto unreg_genl_family; + goto unreg_rtnl_link; pr_info("GTP module loaded (pdp ctx size %zd bytes)\n", sizeof(struct pdp_ctx)); return 0; -unreg_genl_family: - genl_unregister_family(>p_genl_family); unreg_rtnl_link: rtnl_link_unregister(>p_link_ops); +unreg_pernet_subsys: + unregister_pernet_subsys(>p_net_ops); error_out: pr_err("error loading GTP module loaded\n"); return err; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index da737d959e81c034a97c6fa99ffcb565d6aeb67e..3a834d4e1c8427c1c5fb895b7f9cab767185bfa4 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -740,7 +740,10 @@ void netvsc_device_remove(struct hv_device *device) /* Disable NAPI and disassociate its context from the device. */ for (i = 0; i < net_device->num_chn; i++) { /* See also vmbus_reset_channel_cb(). */ - napi_disable(&net_device->chan_table[i].napi); + /* only disable enabled NAPI channel */ + if (i < ndev->real_num_rx_queues) + napi_disable(&net_device->chan_table[i].napi); + netif_napi_del(&net_device->chan_table[i].napi); } diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index c1aac6ceb29e6dcd2c24e51432e11314840eab33..1b74055399840130a1f4bee6a5b5973e71585bdf 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -42,6 +42,10 @@ #define LINKCHANGE_INT (2 * HZ) #define VF_TAKEOVER_INT (HZ / 10) +/* Macros to define the context of vf registration */ +#define VF_REG_IN_PROBE 1 +#define VF_REG_IN_NOTIFIER 2 + static unsigned int ring_size __ro_after_init = 128; module_param(ring_size, uint, 0444); MODULE_PARM_DESC(ring_size, "Ring buffer size (# of 4K pages)"); @@ -2181,7 +2185,7 @@ static rx_handler_result_t netvsc_vf_handle_frame(struct sk_buff **pskb) } static int netvsc_vf_join(struct net_device *vf_netdev, - struct net_device *ndev) + struct net_device *ndev, int context) { struct net_device_context *ndev_ctx = netdev_priv(ndev); int ret; @@ -2204,7 +2208,11 @@ static int netvsc_vf_join(struct net_device *vf_netdev, goto upper_link_failed; } - schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT); + /* If this registration is called from probe context vf_takeover + * is taken care of later in probe itself. + */ + if (context == VF_REG_IN_NOTIFIER) + schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT); call_netdevice_notifiers(NETDEV_JOIN, vf_netdev); @@ -2342,7 +2350,7 @@ static int netvsc_prepare_bonding(struct net_device *vf_netdev) return NOTIFY_DONE; } -static int netvsc_register_vf(struct net_device *vf_netdev) +static int netvsc_register_vf(struct net_device *vf_netdev, int context) { struct net_device_context *net_device_ctx; struct netvsc_device *netvsc_dev; @@ -2382,7 +2390,7 @@ static int netvsc_register_vf(struct net_device *vf_netdev) netdev_info(ndev, "VF registering: %s\n", vf_netdev->name); - if (netvsc_vf_join(vf_netdev, ndev) != 0) + if (netvsc_vf_join(vf_netdev, ndev, context) != 0) return NOTIFY_DONE; dev_hold(vf_netdev); @@ -2480,10 +2488,31 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev) return NOTIFY_OK; } +static int check_dev_is_matching_vf(struct net_device *event_ndev) +{ + /* Skip NetVSC interfaces */ + if (event_ndev->netdev_ops == &device_ops) + return -ENODEV; + + /* Avoid non-Ethernet type devices */ + if (event_ndev->type != ARPHRD_ETHER) + return -ENODEV; + + /* Avoid Vlan dev with same MAC registering as VF */ + if (is_vlan_dev(event_ndev)) + return -ENODEV; + + /* Avoid Bonding master dev with same MAC registering as VF */ + if (netif_is_bond_master(event_ndev)) + return -ENODEV; + + return 0; +} + static int netvsc_probe(struct hv_device *dev, const struct hv_vmbus_device_id *dev_id) { - struct net_device *net = NULL; + struct net_device *net = NULL, *vf_netdev; struct net_device_context *net_device_ctx; struct netvsc_device_info *device_info = NULL; struct netvsc_device *nvdev; @@ -2592,6 +2621,30 @@ static int netvsc_probe(struct hv_device *dev, } list_add(&net_device_ctx->list, &netvsc_dev_list); + + /* When the hv_netvsc driver is unloaded and reloaded, the + * NET_DEVICE_REGISTER for the vf device is replayed before probe + * is complete. This is because register_netdevice_notifier() gets + * registered before vmbus_driver_register() so that callback func + * is set before probe and we don't miss events like NETDEV_POST_INIT + * So, in this section we try to register the matching vf device that + * is present as a netdevice, knowing that its register call is not + * processed in the netvsc_netdev_notifier(as probing is progress and + * get_netvsc_byslot fails). + */ + for_each_netdev(dev_net(net), vf_netdev) { + ret = check_dev_is_matching_vf(vf_netdev); + if (ret != 0) + continue; + + if (net != get_netvsc_byslot(vf_netdev)) + continue; + + netvsc_prepare_bonding(vf_netdev); + netvsc_register_vf(vf_netdev, VF_REG_IN_PROBE); + __netvsc_vf_setup(net, vf_netdev); + break; + } rtnl_unlock(); netvsc_devinfo_put(device_info); @@ -2748,28 +2801,17 @@ static int netvsc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); + int ret = 0; - /* Skip our own events */ - if (event_dev->netdev_ops == &device_ops) - return NOTIFY_DONE; - - /* Avoid non-Ethernet type devices */ - if (event_dev->type != ARPHRD_ETHER) - return NOTIFY_DONE; - - /* Avoid Vlan dev with same MAC registering as VF */ - if (is_vlan_dev(event_dev)) - return NOTIFY_DONE; - - /* Avoid Bonding master dev with same MAC registering as VF */ - if (netif_is_bond_master(event_dev)) + ret = check_dev_is_matching_vf(event_dev); + if (ret != 0) return NOTIFY_DONE; switch (event) { case NETDEV_POST_INIT: return netvsc_prepare_bonding(event_dev); case NETDEV_REGISTER: - return netvsc_register_vf(event_dev); + return netvsc_register_vf(event_dev, VF_REG_IN_NOTIFIER); case NETDEV_UNREGISTER: return netvsc_unregister_vf(event_dev); case NETDEV_UP: diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 209ee9f35275465f310ed25c855cf092895ff43e..8a8fd74110e2c095340485b7fcf260f715893da2 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1007,10 +1007,12 @@ static enum rx_handler_result handle_not_macsec(struct sk_buff *skb) struct metadata_dst *md_dst; struct macsec_rxh_data *rxd; struct macsec_dev *macsec; + bool is_macsec_md_dst; rcu_read_lock(); rxd = macsec_data_rcu(skb->dev); md_dst = skb_metadata_dst(skb); + is_macsec_md_dst = md_dst && md_dst->type == METADATA_MACSEC; list_for_each_entry_rcu(macsec, &rxd->secys, secys) { struct sk_buff *nskb; @@ -1021,10 +1023,42 @@ static enum rx_handler_result handle_not_macsec(struct sk_buff *skb) * the SecTAG, so we have to deduce which port to deliver to. */ if (macsec_is_offloaded(macsec) && netif_running(ndev)) { - if (md_dst && md_dst->type == METADATA_MACSEC && - (!find_rx_sc(&macsec->secy, md_dst->u.macsec_info.sci))) + const struct macsec_ops *ops; + + ops = macsec_get_ops(macsec, NULL); + + if (ops->rx_uses_md_dst && !is_macsec_md_dst) continue; + if (is_macsec_md_dst) { + struct macsec_rx_sc *rx_sc; + + /* All drivers that implement MACsec offload + * support using skb metadata destinations must + * indicate that they do so. + */ + DEBUG_NET_WARN_ON_ONCE(!ops->rx_uses_md_dst); + rx_sc = find_rx_sc(&macsec->secy, + md_dst->u.macsec_info.sci); + if (!rx_sc) + continue; + /* device indicated macsec offload occurred */ + skb->dev = ndev; + skb->pkt_type = PACKET_HOST; + eth_skb_pkt_type(skb, ndev); + ret = RX_HANDLER_ANOTHER; + goto out; + } + + /* This datapath is insecure because it is unable to + * enforce isolation of broadcast/multicast traffic and + * unicast traffic with promiscuous mode on the macsec + * netdev. Since the core stack has no mechanism to + * check that the hardware did indeed receive MACsec + * traffic, it is possible that the response handling + * done by the MACsec port was to a plaintext packet. + * This violates the MACsec protocol standard. + */ if (ether_addr_equal_64bits(hdr->h_dest, ndev->dev_addr)) { /* exact match, divert skb to this port */ @@ -1040,11 +1074,7 @@ static enum rx_handler_result handle_not_macsec(struct sk_buff *skb) break; nskb->dev = ndev; - if (ether_addr_equal_64bits(hdr->h_dest, - ndev->broadcast)) - nskb->pkt_type = PACKET_BROADCAST; - else - nskb->pkt_type = PACKET_MULTICAST; + eth_skb_pkt_type(nskb, ndev); __netif_rx(nskb); } diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index c3fbdd6b68bafb597eb6bf3d33ab4037ad950202..f3fa4bd121169ebdefcf05a070b0244dc0438556 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -835,14 +835,14 @@ static void nsim_dev_trap_report_work(struct work_struct *work) trap_report_dw.work); nsim_dev = nsim_trap_data->nsim_dev; - /* For each running port and enabled packet trap, generate a UDP - * packet with a random 5-tuple and report it. - */ if (!devl_trylock(priv_to_devlink(nsim_dev))) { - schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, 0); + schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, 1); return; } + /* For each running port and enabled packet trap, generate a UDP + * packet with a random 5-tuple and report it. + */ list_for_each_entry(nsim_dev_port, &nsim_dev->port_list, list) { if (!netif_running(nsim_dev_port->ns->netdev)) continue; diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 3f882bce37f42289d99746d87d0f71d0c1391337..d126273daab4f39ca2b2fb9f598606d1f22cc554 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -262,7 +262,7 @@ static int xpcs_soft_reset(struct dw_xpcs *xpcs, dev = MDIO_MMD_VEND2; break; default: - return -1; + return -EINVAL; } ret = xpcs_write(xpcs, dev, MDIO_CTRL1, MDIO_CTRL1_RESET); @@ -904,7 +904,7 @@ int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, return ret; break; default: - return -1; + return -EINVAL; } if (compat->pma_config) { diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index 267e6fd3d44480f650ce1f11ba412236e25a1617..57411ee1d837449546368b5750f4acf9e8d2f731 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -380,7 +380,7 @@ static int dp83822_config_init(struct phy_device *phydev) { struct dp83822_private *dp83822 = phydev->priv; struct device *dev = &phydev->mdio.dev; - int rgmii_delay; + int rgmii_delay = 0; s32 rx_int_delay; s32 tx_int_delay; int err = 0; @@ -390,30 +390,33 @@ static int dp83822_config_init(struct phy_device *phydev) rx_int_delay = phy_get_internal_delay(phydev, dev, NULL, 0, true); - if (rx_int_delay <= 0) - rgmii_delay = 0; - else - rgmii_delay = DP83822_RX_CLK_SHIFT; + /* Set DP83822_RX_CLK_SHIFT to enable rx clk internal delay */ + if (rx_int_delay > 0) + rgmii_delay |= DP83822_RX_CLK_SHIFT; tx_int_delay = phy_get_internal_delay(phydev, dev, NULL, 0, false); + + /* Set DP83822_TX_CLK_SHIFT to disable tx clk internal delay */ if (tx_int_delay <= 0) - rgmii_delay &= ~DP83822_TX_CLK_SHIFT; - else rgmii_delay |= DP83822_TX_CLK_SHIFT; - if (rgmii_delay) { - err = phy_set_bits_mmd(phydev, DP83822_DEVADDR, - MII_DP83822_RCSR, rgmii_delay); - if (err) - return err; - } + err = phy_modify_mmd(phydev, DP83822_DEVADDR, MII_DP83822_RCSR, + DP83822_RX_CLK_SHIFT | DP83822_TX_CLK_SHIFT, rgmii_delay); + if (err) + return err; + + err = phy_set_bits_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_RCSR, DP83822_RGMII_MODE_EN); - phy_set_bits_mmd(phydev, DP83822_DEVADDR, - MII_DP83822_RCSR, DP83822_RGMII_MODE_EN); + if (err) + return err; } else { - phy_clear_bits_mmd(phydev, DP83822_DEVADDR, - MII_DP83822_RCSR, DP83822_RGMII_MODE_EN); + err = phy_clear_bits_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_RCSR, DP83822_RGMII_MODE_EN); + + if (err) + return err; } if (dp83822->fx_enabled) { diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 9481f172830f551834e174747e6e7791ce9f7f2a..2cbb1d1830bbd2ac2764f7b23607264226f3e67b 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -2188,6 +2188,7 @@ static int lan8814_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr) struct hwtstamp_config config; int txcfg = 0, rxcfg = 0; int pkt_ts_enable; + int tx_mod; if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; @@ -2237,9 +2238,14 @@ static int lan8814_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr) lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_RX_TIMESTAMP_EN, pkt_ts_enable); lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_TX_TIMESTAMP_EN, pkt_ts_enable); - if (ptp_priv->hwts_tx_type == HWTSTAMP_TX_ONESTEP_SYNC) + tx_mod = lanphy_read_page_reg(ptp_priv->phydev, 5, PTP_TX_MOD); + if (ptp_priv->hwts_tx_type == HWTSTAMP_TX_ONESTEP_SYNC) { lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_TX_MOD, - PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_); + tx_mod | PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_); + } else if (ptp_priv->hwts_tx_type == HWTSTAMP_TX_ON) { + lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_TX_MOD, + tx_mod & ~PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_); + } if (config.rx_filter != HWTSTAMP_FILTER_NONE) lan8814_config_ts_intr(ptp_priv->phydev, true); @@ -2297,7 +2303,7 @@ static void lan8814_txtstamp(struct mii_timestamper *mii_ts, } } -static void lan8814_get_sig_rx(struct sk_buff *skb, u16 *sig) +static bool lan8814_get_sig_rx(struct sk_buff *skb, u16 *sig) { struct ptp_header *ptp_header; u32 type; @@ -2307,7 +2313,11 @@ static void lan8814_get_sig_rx(struct sk_buff *skb, u16 *sig) ptp_header = ptp_parse_header(skb, type); skb_pull_inline(skb, ETH_HLEN); + if (!ptp_header) + return false; + *sig = (__force u16)(ntohs(ptp_header->sequence_id)); + return true; } static bool lan8814_match_rx_ts(struct kszphy_ptp_priv *ptp_priv, @@ -2319,7 +2329,8 @@ static bool lan8814_match_rx_ts(struct kszphy_ptp_priv *ptp_priv, bool ret = false; u16 skb_sig; - lan8814_get_sig_rx(skb, &skb_sig); + if (!lan8814_get_sig_rx(skb, &skb_sig)) + return ret; /* Iterate over all RX timestamps and match it with the received skbs */ spin_lock_irqsave(&ptp_priv->rx_ts_lock, flags); @@ -2599,7 +2610,7 @@ static int lan8814_ptpci_adjfine(struct ptp_clock_info *ptpci, long scaled_ppm) return 0; } -static void lan8814_get_sig_tx(struct sk_buff *skb, u16 *sig) +static bool lan8814_get_sig_tx(struct sk_buff *skb, u16 *sig) { struct ptp_header *ptp_header; u32 type; @@ -2607,7 +2618,11 @@ static void lan8814_get_sig_tx(struct sk_buff *skb, u16 *sig) type = ptp_classify_raw(skb); ptp_header = ptp_parse_header(skb, type); + if (!ptp_header) + return false; + *sig = (__force u16)(ntohs(ptp_header->sequence_id)); + return true; } static void lan8814_dequeue_tx_skb(struct kszphy_ptp_priv *ptp_priv) @@ -2625,7 +2640,8 @@ static void lan8814_dequeue_tx_skb(struct kszphy_ptp_priv *ptp_priv) spin_lock_irqsave(&ptp_priv->tx_queue.lock, flags); skb_queue_walk_safe(&ptp_priv->tx_queue, skb, skb_tmp) { - lan8814_get_sig_tx(skb, &skb_sig); + if (!lan8814_get_sig_tx(skb, &skb_sig)) + continue; if (memcmp(&skb_sig, &seq_id, sizeof(seq_id))) continue; @@ -2669,7 +2685,8 @@ static bool lan8814_match_skb(struct kszphy_ptp_priv *ptp_priv, spin_lock_irqsave(&ptp_priv->rx_queue.lock, flags); skb_queue_walk_safe(&ptp_priv->rx_queue, skb, skb_tmp) { - lan8814_get_sig_rx(skb, &skb_sig); + if (!lan8814_get_sig_rx(skb, &skb_sig)) + continue; if (memcmp(&skb_sig, &rx_ts->seq_id, sizeof(rx_ts->seq_id))) continue; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 944f76e6fc8ebff5f13b72a905817854035ee2d0..f25b0d338ca8dbc8ee1a1de0a23be7388cd0f346 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -2640,8 +2640,8 @@ EXPORT_SYMBOL(genphy_resume); int genphy_loopback(struct phy_device *phydev, bool enable) { if (enable) { - u16 val, ctl = BMCR_LOOPBACK; - int ret; + u16 ctl = BMCR_LOOPBACK; + int ret, val; ctl |= mii_bmcr_encode_fixed(phydev->speed, phydev->duplex); @@ -2893,7 +2893,7 @@ s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev, if (delay < 0) return delay; - if (delay && size == 0) + if (size == 0) return delay; if (delay < delay_values[0] || delay > delay_values[size - 1]) { diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 3d99fd6664d7a3a95877333b937a85bb283f9aab..70e52d27064eccce37ecfa6ba79a59174b72d84a 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -414,9 +414,11 @@ static int rtl8211f_config_init(struct phy_device *phydev) ERR_PTR(ret)); return ret; } + + return genphy_soft_reset(phydev); } - return genphy_soft_reset(phydev); + return 0; } static int rtl821x_resume(struct phy_device *phydev) diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c index 15a179631903f31e0db40facbac02779776ff318..abc65c4d7a303b1af6efedfc1ece091312d79481 100644 --- a/drivers/net/ppp/ppp_async.c +++ b/drivers/net/ppp/ppp_async.c @@ -469,6 +469,10 @@ ppp_async_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg) case PPPIOCSMRU: if (get_user(val, p)) break; + if (val > U16_MAX) { + err = -EINVAL; + break; + } if (val < PPP_MRU) val = PPP_MRU; ap->mru = val; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 367255bb44cdc6d4bd28ab417bf7e6bf9444aef0..4af1ba5d074c05abe37694fd22bf85b9c7654284 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -653,6 +653,7 @@ static void __tun_detach(struct tun_file *tfile, bool clean) tun->tfiles[tun->numqueues - 1]); ntfile = rtnl_dereference(tun->tfiles[index]); ntfile->queue_index = index; + ntfile->xdp_rxq.queue_index = index; rcu_assign_pointer(tun->tfiles[tun->numqueues - 1], NULL); @@ -2120,14 +2121,16 @@ static ssize_t tun_put_user(struct tun_struct *tun, tun_is_little_endian(tun), true, vlan_hlen)) { struct skb_shared_info *sinfo = skb_shinfo(skb); - pr_err("unexpected GSO type: " - "0x%x, gso_size %d, hdr_len %d\n", - sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size), - tun16_to_cpu(tun, gso.hdr_len)); - print_hex_dump(KERN_ERR, "tun: ", - DUMP_PREFIX_NONE, - 16, 1, skb->head, - min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true); + + if (net_ratelimit()) { + netdev_err(tun->dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n", + sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size), + tun16_to_cpu(tun, gso.hdr_len)); + print_hex_dump(KERN_ERR, "tun: ", + DUMP_PREFIX_NONE, + 16, 1, skb->head, + min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true); + } WARN_ON_ONCE(1); return -EINVAL; } diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 6eacbf17f1c0c5feb3f80d927d131fb9d37c0d3c..34cd568b27f192bae08f32205e7e112bb6f57f32 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -714,7 +714,7 @@ static int ax88772_init_phy(struct usbnet *dev) } phy_suspend(priv->phydev); - priv->phydev->mac_managed_pm = 1; + priv->phydev->mac_managed_pm = true; phy_attached_info(priv->phydev); @@ -734,7 +734,7 @@ static int ax88772_init_phy(struct usbnet *dev) return -ENODEV; } - priv->phydev_int->mac_managed_pm = 1; + priv->phydev_int->mac_managed_pm = true; phy_suspend(priv->phydev_int); return 0; diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index d837c18874161d41cdf2b388bd8a96aaaff2eba1..6d31061818e939bfd5401827540507acb8e18fb0 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -174,6 +174,7 @@ struct ax88179_data { u32 wol_supported; u32 wolopts; u8 disconnecting; + u8 initialized; }; struct ax88179_int_data { @@ -1273,6 +1274,8 @@ static void ax88179_get_mac_addr(struct usbnet *dev) if (is_valid_ether_addr(mac)) { eth_hw_addr_set(dev->net, mac); + if (!is_local_ether_addr(mac)) + dev->net->addr_assign_type = NET_ADDR_PERM; } else { netdev_info(dev->net, "invalid MAC address, using random\n"); eth_hw_addr_random(dev->net); @@ -1315,6 +1318,8 @@ static int ax88179_bind(struct usbnet *dev, struct usb_interface *intf) netif_set_tso_max_size(dev->net, 16384); + ax88179_reset(dev); + return 0; } @@ -1452,21 +1457,16 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb) /* Skip IP alignment pseudo header */ skb_pull(skb, 2); - skb->truesize = SKB_TRUESIZE(pkt_len_plus_padd); ax88179_rx_checksum(skb, pkt_hdr); return 1; } - ax_skb = skb_clone(skb, GFP_ATOMIC); + ax_skb = netdev_alloc_skb_ip_align(dev->net, pkt_len); if (!ax_skb) return 0; - skb_trim(ax_skb, pkt_len); - - /* Skip IP alignment pseudo header */ - skb_pull(ax_skb, 2); + skb_put(ax_skb, pkt_len); + memcpy(ax_skb->data, skb->data + 2, pkt_len); - skb->truesize = pkt_len_plus_padd + - SKB_DATA_ALIGN(sizeof(struct sk_buff)); ax88179_rx_checksum(ax_skb, pkt_hdr); usbnet_skb_return(dev, ax_skb); @@ -1674,6 +1674,18 @@ static int ax88179_reset(struct usbnet *dev) return 0; } +static int ax88179_net_reset(struct usbnet *dev) +{ + struct ax88179_data *ax179_data = dev->driver_priv; + + if (ax179_data->initialized) + ax88179_reset(dev); + else + ax179_data->initialized = 1; + + return 0; +} + static int ax88179_stop(struct usbnet *dev) { u16 tmp16; @@ -1693,7 +1705,7 @@ static const struct driver_info ax88179_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1706,7 +1718,7 @@ static const struct driver_info ax88178a_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1719,7 +1731,7 @@ static const struct driver_info cypress_GX3_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1732,7 +1744,7 @@ static const struct driver_info dlink_dub1312_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1745,7 +1757,7 @@ static const struct driver_info sitecom_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1758,7 +1770,7 @@ static const struct driver_info samsung_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1771,7 +1783,7 @@ static const struct driver_info lenovo_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1784,7 +1796,7 @@ static const struct driver_info belkin_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1797,7 +1809,7 @@ static const struct driver_info toshiba_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1810,7 +1822,7 @@ static const struct driver_info mct_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1823,7 +1835,7 @@ static const struct driver_info at_umc2000_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1836,7 +1848,7 @@ static const struct driver_info at_umc200_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1849,7 +1861,7 @@ static const struct driver_info at_umc2000sp_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c index 99ec1d4a972db8c1232ce8ee8eb8d97385a9b5f0..8b6d6a1b3c2eca086e77915e26428c1110127f4d 100644 --- a/drivers/net/usb/dm9601.c +++ b/drivers/net/usb/dm9601.c @@ -232,7 +232,7 @@ static int dm9601_mdio_read(struct net_device *netdev, int phy_id, int loc) err = dm_read_shared_word(dev, 1, loc, &res); if (err < 0) { netdev_err(dev->net, "MDIO read error: %d\n", err); - return err; + return 0; } netdev_dbg(dev->net, diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 033e0e6be78cce1463201836421227dae3671b53..6e841636004e10bbcff2f9ad9bfa468580d9e189 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1518,7 +1518,9 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) lan78xx_rx_urb_submit_all(dev); + local_bh_disable(); napi_schedule(&dev->napi); + local_bh_enable(); } return 0; @@ -3078,7 +3080,8 @@ static int lan78xx_reset(struct lan78xx_net *dev) if (dev->chipid == ID_REV_CHIP_ID_7801_) buf &= ~MAC_CR_GMII_EN_; - if (dev->chipid == ID_REV_CHIP_ID_7800_) { + if (dev->chipid == ID_REV_CHIP_ID_7800_ || + dev->chipid == ID_REV_CHIP_ID_7850_) { ret = lan78xx_read_raw_eeprom(dev, 0, 1, &sig); if (!ret && sig != EEPROM_INDICATOR) { /* Implies there is no external eeprom. Set mac speed */ @@ -3180,7 +3183,8 @@ static int lan78xx_open(struct net_device *net) done: mutex_unlock(&dev->dev_mutex); - usb_autopm_put_interface(dev->intf); + if (ret < 0) + usb_autopm_put_interface(dev->intf); return ret; } diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 2d82481d34e6b90d97f6ee1b184e3bd4f1da80ec..45a542659a8142a79abcf8225034bba8a4e85f15 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1429,6 +1429,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x0489, 0xe0b5, 0)}, /* Foxconn T77W968 LTE with eSIM support*/ {QMI_FIXED_INTF(0x2692, 0x9025, 4)}, /* Cellient MPL200 (rebranded Qualcomm 05c6:9025) */ {QMI_QUIRK_SET_DTR(0x1546, 0x1342, 4)}, /* u-blox LARA-L6 */ + {QMI_QUIRK_SET_DTR(0x33f8, 0x0104, 4)}, /* Rolling RW101 RMNET */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 340a877eaf69a216032100929cfe0e1a96e73234..44aefcb23930b42a6358fba1b5867b9bba8d55e1 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -2141,6 +2141,11 @@ static const struct usb_device_id products[] = { USB_DEVICE(0x0424, 0x9E08), .driver_info = (unsigned long) &smsc95xx_info, }, + { + /* SYSTEC USB-SPEmodule1 10BASE-T1L Ethernet Device */ + USB_DEVICE(0x0878, 0x1400), + .driver_info = (unsigned long)&smsc95xx_info, + }, { /* Microchip's EVB-LAN8670-USB 10BASE-T1S Ethernet Device */ USB_DEVICE(0x184F, 0x0051), diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c index f5e19f3ef6cdd250726730f5ec90f6ed706b1903..4de51448218355350c48aa502459fe9317b93d9a 100644 --- a/drivers/net/usb/sr9800.c +++ b/drivers/net/usb/sr9800.c @@ -737,7 +737,9 @@ static int sr9800_bind(struct usbnet *dev, struct usb_interface *intf) data->eeprom_len = SR9800_EEPROM_LEN; - usbnet_get_endpoints(dev, intf); + ret = usbnet_get_endpoints(dev, intf); + if (ret) + goto out; /* LED Setting Rule : * AABB:CCDD diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 36c5a41f84e446f7aeb7652d7e40e009013c0366..8dcd3b6e143b9befeba90ebd5c2605e37152d86a 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1135,14 +1135,6 @@ static int veth_enable_xdp(struct net_device *dev) veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, true); return err; } - - if (!veth_gro_requested(dev)) { - /* user-space did not require GRO, but adding XDP - * is supposed to get GRO working - */ - dev->features |= NETIF_F_GRO; - netdev_features_change(dev); - } } } @@ -1162,18 +1154,9 @@ static void veth_disable_xdp(struct net_device *dev) for (i = 0; i < dev->real_num_rx_queues; i++) rcu_assign_pointer(priv->rq[i].xdp_prog, NULL); - if (!netif_running(dev) || !veth_gro_requested(dev)) { + if (!netif_running(dev) || !veth_gro_requested(dev)) veth_napi_del(dev); - /* if user-space did not require GRO, since adding XDP - * enabled it, clear it now - */ - if (!veth_gro_requested(dev) && netif_running(dev)) { - dev->features &= ~NETIF_F_GRO; - netdev_features_change(dev); - } - } - veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, false); } @@ -1376,7 +1359,8 @@ static int veth_alloc_queues(struct net_device *dev) struct veth_priv *priv = netdev_priv(dev); int i; - priv->rq = kcalloc(dev->num_rx_queues, sizeof(*priv->rq), GFP_KERNEL_ACCOUNT); + priv->rq = kvcalloc(dev->num_rx_queues, sizeof(*priv->rq), + GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!priv->rq) return -ENOMEM; @@ -1392,7 +1376,7 @@ static void veth_free_queues(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); - kfree(priv->rq); + kvfree(priv->rq); } static int veth_dev_init(struct net_device *dev) @@ -1460,8 +1444,6 @@ static netdev_features_t veth_fix_features(struct net_device *dev, if (peer_priv->_xdp_prog) features &= ~NETIF_F_GSO_SOFTWARE; } - if (priv->_xdp_prog) - features |= NETIF_F_GRO; return features; } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 45f1a871b7da81765d9d1958e868e6f57f949bd5..32cddb633793d79f2af3ae6e44fe9e65589333d3 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2948,19 +2948,35 @@ static int virtnet_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, u8 *hfu static int virtnet_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key, const u8 hfunc) { struct virtnet_info *vi = netdev_priv(dev); + bool update = false; int i; if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) return -EOPNOTSUPP; if (indir) { + if (!vi->has_rss) + return -EOPNOTSUPP; + for (i = 0; i < vi->rss_indir_table_size; ++i) vi->ctrl->rss.indirection_table[i] = indir[i]; + update = true; } - if (key) + + if (key) { + /* If either _F_HASH_REPORT or _F_RSS are negotiated, the + * device provides hash calculation capabilities, that is, + * hash_key is configured. + */ + if (!vi->has_rss && !vi->has_rss_hash_report) + return -EOPNOTSUPP; + memcpy(vi->ctrl->rss.key, key, vi->rss_key_size); + update = true; + } - virtnet_commit_rss_command(vi); + if (update) + virtnet_commit_rss_command(vi); return 0; } @@ -3852,13 +3868,15 @@ static int virtnet_probe(struct virtio_device *vdev) if (virtio_has_feature(vdev, VIRTIO_NET_F_HASH_REPORT)) vi->has_rss_hash_report = true; - if (virtio_has_feature(vdev, VIRTIO_NET_F_RSS)) + if (virtio_has_feature(vdev, VIRTIO_NET_F_RSS)) { vi->has_rss = true; - if (vi->has_rss || vi->has_rss_hash_report) { vi->rss_indir_table_size = virtio_cread16(vdev, offsetof(struct virtio_net_config, rss_max_indirection_table_length)); + } + + if (vi->has_rss || vi->has_rss_hash_report) { vi->rss_key_size = virtio_cread8(vdev, offsetof(struct virtio_net_config, rss_max_key_size)); diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 619dd71c9d75eab33ab4482bc4a898433d438cd8..01ce289f4abf055ebbc1c49404d3714e6816a149 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -1662,6 +1662,10 @@ static bool vxlan_set_mac(struct vxlan_dev *vxlan, if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr)) return false; + /* Ignore packets from invalid src-address */ + if (!is_valid_ether_addr(eth_hdr(skb)->h_source)) + return false; + /* Get address from the outer IP header */ if (vxlan_get_sk_family(vs) == AF_INET) { saddr.sin.sin_addr.s_addr = ip_hdr(skb)->saddr; @@ -1717,6 +1721,7 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) bool raw_proto = false; void *oiph; __be32 vni = 0; + int nh; /* Need UDP and VXLAN header to be present */ if (!pskb_may_pull(skb, VXLAN_HLEN)) @@ -1805,9 +1810,25 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) skb->pkt_type = PACKET_HOST; } - oiph = skb_network_header(skb); + /* Save offset of outer header relative to skb->head, + * because we are going to reset the network header to the inner header + * and might change skb->head. + */ + nh = skb_network_header(skb) - skb->head; + skb_reset_network_header(skb); + if (!pskb_inet_may_pull(skb)) { + DEV_STATS_INC(vxlan->dev, rx_length_errors); + DEV_STATS_INC(vxlan->dev, rx_errors); + vxlan_vnifilter_count(vxlan, vni, vninode, + VXLAN_VNI_STATS_RX_ERRORS, 0); + goto drop; + } + + /* Get the outer header. */ + oiph = skb->head + nh; + if (!vxlan_ecn_decapsulate(vs, oiph, skb)) { ++vxlan->dev->stats.rx_frame_errors; ++vxlan->dev->stats.rx_errors; diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c index 6d1bd9f52d02a07498ce5217348de1ee8f4bc03d..81b716e6612e24f794298fa55529474ebd6cf607 100644 --- a/drivers/net/wireguard/netlink.c +++ b/drivers/net/wireguard/netlink.c @@ -164,8 +164,8 @@ get_peer(struct wg_peer *peer, struct sk_buff *skb, struct dump_ctx *ctx) if (!allowedips_node) goto no_allowedips; if (!ctx->allowedips_seq) - ctx->allowedips_seq = peer->device->peer_allowedips.seq; - else if (ctx->allowedips_seq != peer->device->peer_allowedips.seq) + ctx->allowedips_seq = ctx->wg->peer_allowedips.seq; + else if (ctx->allowedips_seq != ctx->wg->peer_allowedips.seq) goto no_allowedips; allowedips_nest = nla_nest_start(skb, WGPEER_A_ALLOWEDIPS); @@ -255,17 +255,17 @@ static int wg_get_device_dump(struct sk_buff *skb, struct netlink_callback *cb) if (!peers_nest) goto out; ret = 0; - /* If the last cursor was removed via list_del_init in peer_remove, then + lockdep_assert_held(&wg->device_update_lock); + /* If the last cursor was removed in peer_remove or peer_remove_all, then * we just treat this the same as there being no more peers left. The * reason is that seq_nr should indicate to userspace that this isn't a * coherent dump anyway, so they'll try again. */ if (list_empty(&wg->peer_list) || - (ctx->next_peer && list_empty(&ctx->next_peer->peer_list))) { + (ctx->next_peer && ctx->next_peer->is_dead)) { nla_nest_cancel(skb, peers_nest); goto out; } - lockdep_assert_held(&wg->device_update_lock); peer = list_prepare_entry(ctx->next_peer, &wg->peer_list, peer_list); list_for_each_entry_continue(peer, &wg->peer_list, peer_list) { if (get_peer(peer, skb, ctx)) { diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index a176653c88616b1bc871fe52fcea778b5e189f69..db01ec03bda0057671990d68ce3ac3e948c9bfa5 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -251,7 +251,7 @@ static bool decrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair) if (unlikely(!READ_ONCE(keypair->receiving.is_valid) || wg_birthdate_has_expired(keypair->receiving.birthdate, REJECT_AFTER_TIME) || - keypair->receiving_counter.counter >= REJECT_AFTER_MESSAGES)) { + READ_ONCE(keypair->receiving_counter.counter) >= REJECT_AFTER_MESSAGES)) { WRITE_ONCE(keypair->receiving.is_valid, false); return false; } @@ -318,7 +318,7 @@ static bool counter_validate(struct noise_replay_counter *counter, u64 their_cou for (i = 1; i <= top; ++i) counter->backtrack[(i + index_current) & ((COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1)] = 0; - counter->counter = their_counter; + WRITE_ONCE(counter->counter, their_counter); } index &= (COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1; @@ -463,7 +463,7 @@ int wg_packet_rx_poll(struct napi_struct *napi, int budget) net_dbg_ratelimited("%s: Packet has invalid nonce %llu (max %llu)\n", peer->device->dev->name, PACKET_CB(skb)->nonce, - keypair->receiving_counter.counter); + READ_ONCE(keypair->receiving_counter.counter)); goto next; } diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c index 876410a47d1d2088b4e83b913cc6a338e926c81c..4d5009604eee7fb00be2b3d9c735d87485fec789 100644 --- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c +++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c @@ -844,6 +844,10 @@ ath10k_wmi_tlv_op_pull_mgmt_tx_compl_ev(struct ath10k *ar, struct sk_buff *skb, } ev = tb[WMI_TLV_TAG_STRUCT_MGMT_TX_COMPL_EVENT]; + if (!ev) { + kfree(tb); + return -EPROTO; + } arg->desc_id = ev->desc_id; arg->status = ev->status; diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index 21c6b36dc6ebbbfd0d1b0979608d1e5c3376b23e..51fc77e93de5c41722ac199a1f439dd56841fe08 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -2112,6 +2112,8 @@ static void ath11k_peer_assoc_h_he(struct ath11k *ar, mcs_160_map = le16_to_cpu(he_cap->he_mcs_nss_supp.rx_mcs_160); mcs_80_map = le16_to_cpu(he_cap->he_mcs_nss_supp.rx_mcs_80); + /* Initialize rx_mcs_160 to 9 which is an invalid value */ + rx_mcs_160 = 9; if (support_160) { for (i = 7; i >= 0; i--) { u8 mcs_160 = (mcs_160_map >> (2 * i)) & 3; @@ -2123,6 +2125,8 @@ static void ath11k_peer_assoc_h_he(struct ath11k *ar, } } + /* Initialize rx_mcs_80 to 9 which is an invalid value */ + rx_mcs_80 = 9; for (i = 7; i >= 0; i--) { u8 mcs_80 = (mcs_80_map >> (2 * i)) & 3; diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c index a62ee05c54097253d3514ffbc1c2c7e95e1141d7..4bea36cc7108500a16ea93f7fe3dc56c4e38d167 100644 --- a/drivers/net/wireless/ath/ath11k/mhi.c +++ b/drivers/net/wireless/ath/ath11k/mhi.c @@ -105,7 +105,7 @@ static struct mhi_controller_config ath11k_mhi_config_qca6390 = { .max_channels = 128, .timeout_ms = 2000, .use_bounce_buf = false, - .buf_len = 0, + .buf_len = 8192, .num_channels = ARRAY_SIZE(ath11k_mhi_channels_qca6390), .ch_cfg = ath11k_mhi_channels_qca6390, .num_events = ARRAY_SIZE(ath11k_mhi_events_qca6390), diff --git a/drivers/net/wireless/ath/ath9k/antenna.c b/drivers/net/wireless/ath/ath9k/antenna.c index 988222cea9dfe760073e0312de65206343b65e50..acc84e6711b0e10dfcab53b02e0afaa5b077c1ff 100644 --- a/drivers/net/wireless/ath/ath9k/antenna.c +++ b/drivers/net/wireless/ath/ath9k/antenna.c @@ -643,7 +643,7 @@ static void ath_ant_try_scan(struct ath_ant_comb *antcomb, conf->main_lna_conf = ATH_ANT_DIV_COMB_LNA1; conf->alt_lna_conf = ATH_ANT_DIV_COMB_LNA1_PLUS_LNA2; } else if (antcomb->rssi_sub > - antcomb->rssi_lna1) { + antcomb->rssi_lna2) { /* set to A-B */ conf->main_lna_conf = ATH_ANT_DIV_COMB_LNA1; conf->alt_lna_conf = ATH_ANT_DIV_COMB_LNA1_MINUS_LNA2; diff --git a/drivers/net/wireless/ath/ath9k/htc.h b/drivers/net/wireless/ath/ath9k/htc.h index 237f4ec2cffd7b0c53f8d1b253fe81072cf1ceab..6c33e898b30006820f3b7993715a3eac0d9486a0 100644 --- a/drivers/net/wireless/ath/ath9k/htc.h +++ b/drivers/net/wireless/ath/ath9k/htc.h @@ -306,7 +306,6 @@ struct ath9k_htc_tx { DECLARE_BITMAP(tx_slot, MAX_TX_BUF_NUM); struct timer_list cleanup_timer; spinlock_t tx_lock; - bool initialized; }; struct ath9k_htc_tx_ctl { @@ -515,6 +514,7 @@ struct ath9k_htc_priv { unsigned long ps_usecount; bool ps_enabled; bool ps_idle; + bool initialized; #ifdef CONFIG_MAC80211_LEDS enum led_brightness brightness; diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c index 96a3185a96d75070bf71b07905a085210ac21f1e..b014185373f34058aa174d7916a62f944ad923a4 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c @@ -966,6 +966,10 @@ int ath9k_htc_probe_device(struct htc_target *htc_handle, struct device *dev, htc_handle->drv_priv = priv; + /* Allow ath9k_wmi_event_tasklet() to operate. */ + smp_wmb(); + priv->initialized = true; + return 0; err_init: diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c index d6a3f001dacb981885191df2e0a2638b558b2b1c..2fdd27885f54372e6689636ba0f3179f572c5c9a 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c @@ -815,10 +815,6 @@ int ath9k_tx_init(struct ath9k_htc_priv *priv) skb_queue_head_init(&priv->tx.data_vo_queue); skb_queue_head_init(&priv->tx.tx_failed); - /* Allow ath9k_wmi_event_tasklet(WMI_TXSTATUS_EVENTID) to operate. */ - smp_wmb(); - priv->tx.initialized = true; - return 0; } diff --git a/drivers/net/wireless/ath/ath9k/wmi.c b/drivers/net/wireless/ath/ath9k/wmi.c index 1476b42b52a9156f40aac8cf262f71a2aa6c4beb..805ad31edba2ba3aeaad619467ab93733bd84e4e 100644 --- a/drivers/net/wireless/ath/ath9k/wmi.c +++ b/drivers/net/wireless/ath/ath9k/wmi.c @@ -155,6 +155,12 @@ void ath9k_wmi_event_tasklet(struct tasklet_struct *t) } spin_unlock_irqrestore(&wmi->wmi_lock, flags); + /* Check if ath9k_htc_probe_device() completed. */ + if (!data_race(priv->initialized)) { + kfree_skb(skb); + continue; + } + hdr = (struct wmi_cmd_hdr *) skb->data; cmd_id = be16_to_cpu(hdr->command_id); wmi_event = skb_pull(skb, sizeof(struct wmi_cmd_hdr)); @@ -169,10 +175,6 @@ void ath9k_wmi_event_tasklet(struct tasklet_struct *t) &wmi->drv_priv->fatal_work); break; case WMI_TXSTATUS_EVENTID: - /* Check if ath9k_tx_init() completed. */ - if (!data_race(priv->tx.initialized)) - break; - spin_lock_bh(&priv->tx.tx_lock); if (priv->tx.flags & ATH9K_HTC_OP_TX_DRAIN) { spin_unlock_bh(&priv->tx.tx_lock); diff --git a/drivers/net/wireless/broadcom/b43/b43.h b/drivers/net/wireless/broadcom/b43/b43.h index 67b4bac048e585bd336196b8004fa6555d6abd0c..c0d8fc0b22fb2898ef29bbbc948bd399ee547dac 100644 --- a/drivers/net/wireless/broadcom/b43/b43.h +++ b/drivers/net/wireless/broadcom/b43/b43.h @@ -1082,6 +1082,22 @@ static inline bool b43_using_pio_transfers(struct b43_wldev *dev) return dev->__using_pio_transfers; } +static inline void b43_wake_queue(struct b43_wldev *dev, int queue_prio) +{ + if (dev->qos_enabled) + ieee80211_wake_queue(dev->wl->hw, queue_prio); + else + ieee80211_wake_queue(dev->wl->hw, 0); +} + +static inline void b43_stop_queue(struct b43_wldev *dev, int queue_prio) +{ + if (dev->qos_enabled) + ieee80211_stop_queue(dev->wl->hw, queue_prio); + else + ieee80211_stop_queue(dev->wl->hw, 0); +} + /* Message printing */ __printf(2, 3) void b43info(struct b43_wl *wl, const char *fmt, ...); __printf(2, 3) void b43err(struct b43_wl *wl, const char *fmt, ...); diff --git a/drivers/net/wireless/broadcom/b43/dma.c b/drivers/net/wireless/broadcom/b43/dma.c index 9a7c62bd5e431651aa347e194a1a2c51e393e0ec..cfaf2f9d67b2277a5a27a3e449923ec6f50f0e3c 100644 --- a/drivers/net/wireless/broadcom/b43/dma.c +++ b/drivers/net/wireless/broadcom/b43/dma.c @@ -1399,7 +1399,7 @@ int b43_dma_tx(struct b43_wldev *dev, struct sk_buff *skb) should_inject_overflow(ring)) { /* This TX ring is full. */ unsigned int skb_mapping = skb_get_queue_mapping(skb); - ieee80211_stop_queue(dev->wl->hw, skb_mapping); + b43_stop_queue(dev, skb_mapping); dev->wl->tx_queue_stopped[skb_mapping] = true; ring->stopped = true; if (b43_debug(dev, B43_DBG_DMAVERBOSE)) { @@ -1570,7 +1570,7 @@ void b43_dma_handle_txstatus(struct b43_wldev *dev, } else { /* If the driver queue is running wake the corresponding * mac80211 queue. */ - ieee80211_wake_queue(dev->wl->hw, ring->queue_prio); + b43_wake_queue(dev, ring->queue_prio); if (b43_debug(dev, B43_DBG_DMAVERBOSE)) { b43dbg(dev->wl, "Woke up TX ring %d\n", ring->index); } diff --git a/drivers/net/wireless/broadcom/b43/main.c b/drivers/net/wireless/broadcom/b43/main.c index b2539a916fd040c7fbe4c877caf33483864261a8..bdfa68cc7ee2a68922f15fc842a618f59b26c7b0 100644 --- a/drivers/net/wireless/broadcom/b43/main.c +++ b/drivers/net/wireless/broadcom/b43/main.c @@ -2587,7 +2587,8 @@ static void b43_request_firmware(struct work_struct *work) start_ieee80211: wl->hw->queues = B43_QOS_QUEUE_NUM; - if (!modparam_qos || dev->fw.opensource) + if (!modparam_qos || dev->fw.opensource || + dev->dev->chip_id == BCMA_CHIP_ID_BCM4331) wl->hw->queues = 1; err = ieee80211_register_hw(wl->hw); @@ -3603,7 +3604,7 @@ static void b43_tx_work(struct work_struct *work) err = b43_dma_tx(dev, skb); if (err == -ENOSPC) { wl->tx_queue_stopped[queue_num] = true; - ieee80211_stop_queue(wl->hw, queue_num); + b43_stop_queue(dev, queue_num); skb_queue_head(&wl->tx_queue[queue_num], skb); break; } @@ -3627,6 +3628,7 @@ static void b43_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb) { struct b43_wl *wl = hw_to_b43_wl(hw); + u16 skb_queue_mapping; if (unlikely(skb->len < 2 + 2 + 6)) { /* Too short, this can't be a valid frame. */ @@ -3635,12 +3637,12 @@ static void b43_op_tx(struct ieee80211_hw *hw, } B43_WARN_ON(skb_shinfo(skb)->nr_frags); - skb_queue_tail(&wl->tx_queue[skb->queue_mapping], skb); - if (!wl->tx_queue_stopped[skb->queue_mapping]) { + skb_queue_mapping = skb_get_queue_mapping(skb); + skb_queue_tail(&wl->tx_queue[skb_queue_mapping], skb); + if (!wl->tx_queue_stopped[skb_queue_mapping]) ieee80211_queue_work(wl->hw, &wl->tx_work); - } else { - ieee80211_stop_queue(wl->hw, skb->queue_mapping); - } + else + b43_stop_queue(wl->current_dev, skb_queue_mapping); } static void b43_qos_params_upload(struct b43_wldev *dev, diff --git a/drivers/net/wireless/broadcom/b43/pio.c b/drivers/net/wireless/broadcom/b43/pio.c index 8c28a9250cd19a45da54a1e6c7ec0d9315698ab7..cc19b589fa70deded190b5e30959c4f63bd9c680 100644 --- a/drivers/net/wireless/broadcom/b43/pio.c +++ b/drivers/net/wireless/broadcom/b43/pio.c @@ -525,7 +525,7 @@ int b43_pio_tx(struct b43_wldev *dev, struct sk_buff *skb) if (total_len > (q->buffer_size - q->buffer_used)) { /* Not enough memory on the queue. */ err = -EBUSY; - ieee80211_stop_queue(dev->wl->hw, skb_get_queue_mapping(skb)); + b43_stop_queue(dev, skb_get_queue_mapping(skb)); q->stopped = true; goto out; } @@ -552,7 +552,7 @@ int b43_pio_tx(struct b43_wldev *dev, struct sk_buff *skb) if (((q->buffer_size - q->buffer_used) < roundup(2 + 2 + 6, 4)) || (q->free_packet_slots == 0)) { /* The queue is full. */ - ieee80211_stop_queue(dev->wl->hw, skb_get_queue_mapping(skb)); + b43_stop_queue(dev, skb_get_queue_mapping(skb)); q->stopped = true; } @@ -587,7 +587,7 @@ void b43_pio_handle_txstatus(struct b43_wldev *dev, list_add(&pack->list, &q->packets_list); if (q->stopped) { - ieee80211_wake_queue(dev->wl->hw, q->queue_prio); + b43_wake_queue(dev, q->queue_prio); q->stopped = false; } } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index e0f97cf6d273c47c93e39fac6465e5923fee8051..3d25aea61960c66cc642b1c5ee4319d1ccf46d32 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -792,8 +792,7 @@ s32 brcmf_notify_escan_complete(struct brcmf_cfg80211_info *cfg, scan_request = cfg->scan_request; cfg->scan_request = NULL; - if (timer_pending(&cfg->escan_timeout)) - del_timer_sync(&cfg->escan_timeout); + timer_delete_sync(&cfg->escan_timeout); if (fw_abort) { /* Do a scan abort to stop the driver's scan engine */ @@ -7821,6 +7820,7 @@ void brcmf_cfg80211_detach(struct brcmf_cfg80211_info *cfg) brcmf_btcoex_detach(cfg); wiphy_unregister(cfg->wiphy); wl_deinit_priv(cfg); + cancel_work_sync(&cfg->escan_timeout_work); brcmf_free_wiphy(cfg->wiphy); kfree(cfg); } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/dmi.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/dmi.c index 86ff174936a9a0e0ae1874be113eef0b2de77e14..c3a602197662b77693f5b10d0a6e327b0362f991 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/dmi.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/dmi.c @@ -82,6 +82,15 @@ static const struct dmi_system_id dmi_platform_data[] = { }, .driver_data = (void *)&acepc_t8_data, }, + { + /* ACEPC W5 Pro Cherry Trail Z8350 HDMI stick, same wifi as the T8 */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "T3 MRD"), + DMI_MATCH(DMI_CHASSIS_TYPE, "3"), + DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."), + }, + .driver_data = (void *)&acepc_t8_data, + }, { /* Chuwi Hi8 Pro with D2D3_Hi8Pro.233 BIOS */ .matches = { diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c index ccc621b8ed9f2b21f107d37f605d710f90c7d92b..4a1fe982a948e44ee4de9a25b7f180467f39e60c 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c @@ -383,8 +383,9 @@ struct shared_phy *wlc_phy_shared_attach(struct shared_phy_params *shp) return sh; } -static void wlc_phy_timercb_phycal(struct brcms_phy *pi) +static void wlc_phy_timercb_phycal(void *ptr) { + struct brcms_phy *pi = ptr; uint delay = 5; if (PHY_PERICAL_MPHASE_PENDING(pi)) { diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.c index a0de5db0cd64675fb02e2f435cc814715976261d..b7238179153653f35e6480314ba12980fcb88f69 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.c @@ -57,12 +57,11 @@ void wlc_phy_shim_detach(struct phy_shim_info *physhim) } struct wlapi_timer *wlapi_init_timer(struct phy_shim_info *physhim, - void (*fn)(struct brcms_phy *pi), + void (*fn)(void *pi), void *arg, const char *name) { return (struct wlapi_timer *) - brcms_init_timer(physhim->wl, (void (*)(void *))fn, - arg, name); + brcms_init_timer(physhim->wl, fn, arg, name); } void wlapi_free_timer(struct wlapi_timer *t) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.h b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.h index dd8774717adee148134cb85229f422c72fa143e2..27d0934e600ed37ff93e9e9eec7a6e9b087e58c4 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.h @@ -131,7 +131,7 @@ void wlc_phy_shim_detach(struct phy_shim_info *physhim); /* PHY to WL utility functions */ struct wlapi_timer *wlapi_init_timer(struct phy_shim_info *physhim, - void (*fn)(struct brcms_phy *pi), + void (*fn)(void *pi), void *arg, const char *name); void wlapi_free_timer(struct wlapi_timer *t); void wlapi_add_timer(struct wlapi_timer *t, uint ms, int periodic); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c index 585e8cd2d332d94882ac529eefb27cba4b3bfcba..235963e1d7a9a2d342dceb531e4a29d0627ad16e 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c @@ -576,7 +576,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 2) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -592,7 +592,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 1) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -608,7 +608,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 0) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -665,7 +665,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 2) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -681,7 +681,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 1) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -697,7 +697,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt) &tbl_rev); if (!IS_ERR(wifi_pkg)) { if (tbl_rev != 0) { - ret = PTR_ERR(wifi_pkg); + ret = -EINVAL; goto out_free; } @@ -725,7 +725,7 @@ read_table: * from index 1, so the maximum value allowed here is * ACPI_SAR_PROFILES_NUM - 1. */ - if (n_profiles <= 0 || n_profiles >= ACPI_SAR_PROFILE_NUM) { + if (n_profiles >= ACPI_SAR_PROFILE_NUM) { ret = -EINVAL; goto out_free; } @@ -1044,6 +1044,9 @@ int iwl_acpi_get_ppag_table(struct iwl_fw_runtime *fwrt) goto read_table; } + ret = PTR_ERR(wifi_pkg); + goto out_free; + read_table: fwrt->ppag_ver = tbl_rev; flags = &wifi_pkg->package.elements[1]; diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c index 3ef0b776b7727c348b94622920af23eb5fb0d71d..3b0ed1cdfa11ed47d26b99edef32208a970da2cd 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c @@ -2903,8 +2903,6 @@ static void iwl_fw_dbg_collect_sync(struct iwl_fw_runtime *fwrt, u8 wk_idx) struct iwl_fw_dbg_params params = {0}; struct iwl_fwrt_dump_data *dump_data = &fwrt->dump.wks[wk_idx].dump_data; - u32 policy; - u32 time_point; if (!test_bit(wk_idx, &fwrt->dump.active_wks)) return; @@ -2935,13 +2933,16 @@ static void iwl_fw_dbg_collect_sync(struct iwl_fw_runtime *fwrt, u8 wk_idx) iwl_fw_dbg_stop_restart_recording(fwrt, ¶ms, false); - policy = le32_to_cpu(dump_data->trig->apply_policy); - time_point = le32_to_cpu(dump_data->trig->time_point); + if (iwl_trans_dbg_ini_valid(fwrt->trans)) { + u32 policy = le32_to_cpu(dump_data->trig->apply_policy); + u32 time_point = le32_to_cpu(dump_data->trig->time_point); - if (policy & IWL_FW_INI_APPLY_POLICY_DUMP_COMPLETE_CMD) { - IWL_DEBUG_FW_INFO(fwrt, "WRT: sending dump complete\n"); - iwl_send_dbg_dump_complete_cmd(fwrt, time_point, 0); + if (policy & IWL_FW_INI_APPLY_POLICY_DUMP_COMPLETE_CMD) { + IWL_DEBUG_FW_INFO(fwrt, "WRT: sending dump complete\n"); + iwl_send_dbg_dump_complete_cmd(fwrt, time_point, 0); + } } + if (fwrt->trans->dbg.last_tp_resetfw == IWL_FW_INI_RESET_FW_MODE_STOP_FW_ONLY) iwl_force_nmi(fwrt->trans); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c index 5979d904bbbd255c387458b1ec978f76be77747e..677c9e0b46f10a1ed9de609e9a38f6559d257a56 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c @@ -103,6 +103,12 @@ static int iwl_dbg_tlv_alloc_debug_info(struct iwl_trans *trans, if (le32_to_cpu(tlv->length) != sizeof(*debug_info)) return -EINVAL; + /* we use this as a string, ensure input was NUL terminated */ + if (strnlen(debug_info->debug_cfg_name, + sizeof(debug_info->debug_cfg_name)) == + sizeof(debug_info->debug_cfg_name)) + return -EINVAL; + IWL_DEBUG_FW(trans, "WRT: Loading debug cfg: %s\n", debug_info->debug_cfg_name); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index 2748459d1227931d2a07240b0da6848dac0cc4ec..88f4f429d875c8a9af90a3bc17f5da36d63733b1 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -461,12 +461,10 @@ static int iwl_mvm_wowlan_config_rsc_tsc(struct iwl_mvm *mvm, struct wowlan_key_rsc_v5_data data = {}; int i; - data.rsc = kmalloc(sizeof(*data.rsc), GFP_KERNEL); + data.rsc = kzalloc(sizeof(*data.rsc), GFP_KERNEL); if (!data.rsc) return -ENOMEM; - memset(data.rsc, 0xff, sizeof(*data.rsc)); - for (i = 0; i < ARRAY_SIZE(data.rsc->mcast_key_id_map); i++) data.rsc->mcast_key_id_map[i] = IWL_MCAST_KEY_MAP_INVALID; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c index 8c5b97fb194147ae70cae8bd598f0e275c183384..5b0b4bb2bb68496443cad5ba6d04e0f2efe871f3 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c @@ -48,6 +48,8 @@ int iwl_mvm_ftm_add_pasn_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, if (!pasn) return -ENOBUFS; + iwl_mvm_ftm_remove_pasn_sta(mvm, addr); + pasn->cipher = iwl_mvm_cipher_to_location_cipher(cipher); switch (pasn->cipher) { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c index bb77bc9aa8218af83b21fa8b353d118b12c3685b..fb2408c0551d2bed655c04cbdf023f727c08654c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c @@ -122,14 +122,18 @@ struct iwl_rfi_freq_table_resp_cmd *iwl_rfi_get_freq_table(struct iwl_mvm *mvm) if (ret) return ERR_PTR(ret); - if (WARN_ON_ONCE(iwl_rx_packet_payload_len(cmd.resp_pkt) != resp_size)) + if (WARN_ON_ONCE(iwl_rx_packet_payload_len(cmd.resp_pkt) != + resp_size)) { + iwl_free_resp(&cmd); return ERR_PTR(-EIO); + } resp = kmemdup(cmd.resp_pkt->data, resp_size, GFP_KERNEL); + iwl_free_resp(&cmd); + if (!resp) return ERR_PTR(-ENOMEM); - iwl_free_resp(&cmd); return resp; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index f268a31ce26d96b4910e6f66e9b58bb40471ce70..105f283b777d223bd6fc3f70e73ae136c8eda6fc 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -299,6 +299,7 @@ static int iwl_mvm_rx_mgmt_prot(struct ieee80211_sta *sta, u32 status, struct ieee80211_rx_status *stats) { + struct wireless_dev *wdev; struct iwl_mvm_sta *mvmsta; struct iwl_mvm_vif *mvmvif; u8 keyid; @@ -320,9 +321,15 @@ static int iwl_mvm_rx_mgmt_prot(struct ieee80211_sta *sta, if (!ieee80211_is_beacon(hdr->frame_control)) return 0; + if (!sta) + return -1; + + mvmsta = iwl_mvm_sta_from_mac80211(sta); + mvmvif = iwl_mvm_vif_from_mac80211(mvmsta->vif); + /* key mismatch - will also report !MIC_OK but we shouldn't count it */ if (!(status & IWL_RX_MPDU_STATUS_KEY_VALID)) - return -1; + goto report; /* good cases */ if (likely(status & IWL_RX_MPDU_STATUS_MIC_OK && @@ -331,13 +338,6 @@ static int iwl_mvm_rx_mgmt_prot(struct ieee80211_sta *sta, return 0; } - if (!sta) - return -1; - - mvmsta = iwl_mvm_sta_from_mac80211(sta); - - mvmvif = iwl_mvm_vif_from_mac80211(mvmsta->vif); - /* * both keys will have the same cipher and MIC length, use * whichever one is available @@ -346,11 +346,11 @@ static int iwl_mvm_rx_mgmt_prot(struct ieee80211_sta *sta, if (!key) { key = rcu_dereference(mvmvif->bcn_prot.keys[1]); if (!key) - return -1; + goto report; } if (len < key->icv_len + IEEE80211_GMAC_PN_LEN + 2) - return -1; + goto report; /* get the real key ID */ keyid = frame[len - key->icv_len - IEEE80211_GMAC_PN_LEN - 2]; @@ -364,7 +364,7 @@ static int iwl_mvm_rx_mgmt_prot(struct ieee80211_sta *sta, return -1; key = rcu_dereference(mvmvif->bcn_prot.keys[keyid - 6]); if (!key) - return -1; + goto report; } /* Report status to mac80211 */ @@ -372,6 +372,10 @@ static int iwl_mvm_rx_mgmt_prot(struct ieee80211_sta *sta, ieee80211_key_mic_failure(key); else if (status & IWL_RX_MPDU_STATUS_REPLAY_ERROR) ieee80211_key_replay(key); +report: + wdev = ieee80211_vif_to_wdev(mvmsta->vif); + if (wdev->netdev) + cfg80211_rx_unprot_mlme_mgmt(wdev->netdev, (void *)hdr, len); return -1; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c index acd8803dbcdd6866aec87b6aecc4d6426a5c1665..b20d64dbba1ad830707b8250a4bb95bff1ab527b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -2650,7 +2650,8 @@ static int iwl_mvm_build_scan_cmd(struct iwl_mvm *mvm, if (ver_handler->version != scan_ver) continue; - return ver_handler->handler(mvm, vif, params, type, uid); + err = ver_handler->handler(mvm, vif, params, type, uid); + return err ? : uid; } err = iwl_mvm_scan_umac(mvm, vif, params, type, uid); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 4d4db5f6836be386f752cfa9ab0a1e12de80a9f5..7f30e6add99334eac6ad2f765a760d5ad30ea73f 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -505,6 +505,7 @@ static const struct pci_device_id iwl_hw_card_ids[] = { /* Bz devices */ {IWL_PCI_DEVICE(0x2727, PCI_ANY_ID, iwl_bz_trans_cfg)}, + {IWL_PCI_DEVICE(0x272D, PCI_ANY_ID, iwl_bz_trans_cfg)}, {IWL_PCI_DEVICE(0x272b, PCI_ANY_ID, iwl_bz_trans_cfg)}, {IWL_PCI_DEVICE(0xA840, PCI_ANY_ID, iwl_bz_trans_cfg)}, {IWL_PCI_DEVICE(0x7740, PCI_ANY_ID, iwl_bz_trans_cfg)}, diff --git a/drivers/net/wireless/marvell/libertas/cmd.c b/drivers/net/wireless/marvell/libertas/cmd.c index 104d2b6dc9af6ec2add89b5c32e08c835033ebc6..5a525da434c28192784fae0101acd1b46100858c 100644 --- a/drivers/net/wireless/marvell/libertas/cmd.c +++ b/drivers/net/wireless/marvell/libertas/cmd.c @@ -1132,7 +1132,7 @@ int lbs_allocate_cmd_buffer(struct lbs_private *priv) if (!cmdarray[i].cmdbuf) { lbs_deb_host("ALLOC_CMD_BUF: ptempvirtualaddr is NULL\n"); ret = -1; - goto done; + goto free_cmd_array; } } @@ -1140,8 +1140,17 @@ int lbs_allocate_cmd_buffer(struct lbs_private *priv) init_waitqueue_head(&cmdarray[i].cmdwait_q); lbs_cleanup_and_insert_cmd(priv, &cmdarray[i]); } - ret = 0; + return 0; +free_cmd_array: + for (i = 0; i < LBS_NUM_CMD_BUFFERS; i++) { + if (cmdarray[i].cmdbuf) { + kfree(cmdarray[i].cmdbuf); + cmdarray[i].cmdbuf = NULL; + } + } + kfree(priv->cmd_array); + priv->cmd_array = NULL; done: return ret; } diff --git a/drivers/net/wireless/marvell/mwifiex/Kconfig b/drivers/net/wireless/marvell/mwifiex/Kconfig index 2b4ff2b78a7e132554d526ca663f6c75f9038900..b182f7155d66faddf4c95d8459fa251bab07cab2 100644 --- a/drivers/net/wireless/marvell/mwifiex/Kconfig +++ b/drivers/net/wireless/marvell/mwifiex/Kconfig @@ -10,13 +10,14 @@ config MWIFIEX mwifiex. config MWIFIEX_SDIO - tristate "Marvell WiFi-Ex Driver for SD8786/SD8787/SD8797/SD8887/SD8897/SD8977/SD8987/SD8997" + tristate "Marvell WiFi-Ex Driver for SD8786/SD8787/SD8797/SD8887/SD8897/SD8977/SD8978/SD8987/SD8997" depends on MWIFIEX && MMC select FW_LOADER select WANT_DEV_COREDUMP help This adds support for wireless adapters based on Marvell - 8786/8787/8797/8887/8897/8977/8987/8997 chipsets with SDIO interface. + 8786/8787/8797/8887/8897/8977/8978/8987/8997 chipsets with + SDIO interface. SD8978 is also known as NXP IW416. If you choose to build it as a module, it will be called mwifiex_sdio. diff --git a/drivers/net/wireless/marvell/mwifiex/debugfs.c b/drivers/net/wireless/marvell/mwifiex/debugfs.c index 63f232c72337461a48114362f0916f7daa75517f..55ca5b287fe7ff3b6a0c908d5b36b58c352bf0a9 100644 --- a/drivers/net/wireless/marvell/mwifiex/debugfs.c +++ b/drivers/net/wireless/marvell/mwifiex/debugfs.c @@ -964,9 +964,6 @@ mwifiex_dev_debugfs_init(struct mwifiex_private *priv) priv->dfs_dev_dir = debugfs_create_dir(priv->netdev->name, mwifiex_dfs_dir); - if (!priv->dfs_dev_dir) - return; - MWIFIEX_DFS_ADD_FILE(info); MWIFIEX_DFS_ADD_FILE(debug); MWIFIEX_DFS_ADD_FILE(getlog); diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c index ea1c1c2412e72d4fc60a03a61a096606e3280f20..2c9b70e9a7263e8a40f55e5040e805e94d9640dd 100644 --- a/drivers/net/wireless/marvell/mwifiex/sdio.c +++ b/drivers/net/wireless/marvell/mwifiex/sdio.c @@ -263,7 +263,7 @@ static const struct mwifiex_sdio_card_reg mwifiex_reg_sd8887 = { 0x68, 0x69, 0x6a}, }; -static const struct mwifiex_sdio_card_reg mwifiex_reg_sd8987 = { +static const struct mwifiex_sdio_card_reg mwifiex_reg_sd89xx = { .start_rd_port = 0, .start_wr_port = 0, .base_0_reg = 0xF8, @@ -331,6 +331,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8786 = { .can_dump_fw = false, .can_auto_tdls = false, .can_ext_scan = false, + .fw_ready_extra_delay = false, }; static const struct mwifiex_sdio_device mwifiex_sdio_sd8787 = { @@ -346,6 +347,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8787 = { .can_dump_fw = false, .can_auto_tdls = false, .can_ext_scan = true, + .fw_ready_extra_delay = false, }; static const struct mwifiex_sdio_device mwifiex_sdio_sd8797 = { @@ -361,6 +363,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8797 = { .can_dump_fw = false, .can_auto_tdls = false, .can_ext_scan = true, + .fw_ready_extra_delay = false, }; static const struct mwifiex_sdio_device mwifiex_sdio_sd8897 = { @@ -376,6 +379,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8897 = { .can_dump_fw = true, .can_auto_tdls = false, .can_ext_scan = true, + .fw_ready_extra_delay = false, }; static const struct mwifiex_sdio_device mwifiex_sdio_sd8977 = { @@ -392,6 +396,24 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8977 = { .fw_dump_enh = true, .can_auto_tdls = false, .can_ext_scan = true, + .fw_ready_extra_delay = false, +}; + +static const struct mwifiex_sdio_device mwifiex_sdio_sd8978 = { + .firmware_sdiouart = SD8978_SDIOUART_FW_NAME, + .reg = &mwifiex_reg_sd89xx, + .max_ports = 32, + .mp_agg_pkt_limit = 16, + .tx_buf_size = MWIFIEX_TX_DATA_BUF_SIZE_4K, + .mp_tx_agg_buf_size = MWIFIEX_MP_AGGR_BUF_SIZE_MAX, + .mp_rx_agg_buf_size = MWIFIEX_MP_AGGR_BUF_SIZE_MAX, + .supports_sdio_new_mode = true, + .has_control_mask = false, + .can_dump_fw = true, + .fw_dump_enh = true, + .can_auto_tdls = false, + .can_ext_scan = true, + .fw_ready_extra_delay = true, }; static const struct mwifiex_sdio_device mwifiex_sdio_sd8997 = { @@ -409,6 +431,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8997 = { .fw_dump_enh = true, .can_auto_tdls = false, .can_ext_scan = true, + .fw_ready_extra_delay = false, }; static const struct mwifiex_sdio_device mwifiex_sdio_sd8887 = { @@ -424,11 +447,12 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8887 = { .can_dump_fw = false, .can_auto_tdls = true, .can_ext_scan = true, + .fw_ready_extra_delay = false, }; static const struct mwifiex_sdio_device mwifiex_sdio_sd8987 = { .firmware = SD8987_DEFAULT_FW_NAME, - .reg = &mwifiex_reg_sd8987, + .reg = &mwifiex_reg_sd89xx, .max_ports = 32, .mp_agg_pkt_limit = 16, .tx_buf_size = MWIFIEX_TX_DATA_BUF_SIZE_2K, @@ -440,6 +464,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8987 = { .fw_dump_enh = true, .can_auto_tdls = true, .can_ext_scan = true, + .fw_ready_extra_delay = false, }; static const struct mwifiex_sdio_device mwifiex_sdio_sd8801 = { @@ -455,6 +480,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8801 = { .can_dump_fw = false, .can_auto_tdls = false, .can_ext_scan = true, + .fw_ready_extra_delay = false, }; static struct memory_type_mapping generic_mem_type_map[] = { @@ -482,7 +508,9 @@ static struct memory_type_mapping mem_type_mapping_tbl[] = { static const struct of_device_id mwifiex_sdio_of_match_table[] __maybe_unused = { { .compatible = "marvell,sd8787" }, { .compatible = "marvell,sd8897" }, + { .compatible = "marvell,sd8978" }, { .compatible = "marvell,sd8997" }, + { .compatible = "nxp,iw416" }, { } }; @@ -545,6 +573,7 @@ mwifiex_sdio_probe(struct sdio_func *func, const struct sdio_device_id *id) card->fw_dump_enh = data->fw_dump_enh; card->can_auto_tdls = data->can_auto_tdls; card->can_ext_scan = data->can_ext_scan; + card->fw_ready_extra_delay = data->fw_ready_extra_delay; INIT_WORK(&card->work, mwifiex_sdio_work); } @@ -748,8 +777,9 @@ mwifiex_sdio_read_fw_status(struct mwifiex_adapter *adapter, u16 *dat) static int mwifiex_check_fw_status(struct mwifiex_adapter *adapter, u32 poll_num) { + struct sdio_mmc_card *card = adapter->card; int ret = 0; - u16 firmware_stat; + u16 firmware_stat = 0; u32 tries; for (tries = 0; tries < poll_num; tries++) { @@ -765,6 +795,13 @@ static int mwifiex_check_fw_status(struct mwifiex_adapter *adapter, ret = -1; } + if (card->fw_ready_extra_delay && + firmware_stat == FIRMWARE_READY_SDIO) + /* firmware might pretend to be ready, when it's not. + * Wait a little bit more as a workaround. + */ + msleep(100); + return ret; } @@ -920,6 +957,8 @@ static const struct sdio_device_id mwifiex_ids[] = { .driver_data = (unsigned long)&mwifiex_sdio_sd8801}, {SDIO_DEVICE(SDIO_VENDOR_ID_MARVELL, SDIO_DEVICE_ID_MARVELL_8977_WLAN), .driver_data = (unsigned long)&mwifiex_sdio_sd8977}, + {SDIO_DEVICE(SDIO_VENDOR_ID_MARVELL, SDIO_DEVICE_ID_MARVELL_8978_WLAN), + .driver_data = (unsigned long)&mwifiex_sdio_sd8978}, {SDIO_DEVICE(SDIO_VENDOR_ID_MARVELL, SDIO_DEVICE_ID_MARVELL_8987_WLAN), .driver_data = (unsigned long)&mwifiex_sdio_sd8987}, {SDIO_DEVICE(SDIO_VENDOR_ID_MARVELL, SDIO_DEVICE_ID_MARVELL_8997_WLAN), @@ -3164,6 +3203,7 @@ MODULE_FIRMWARE(SD8797_DEFAULT_FW_NAME); MODULE_FIRMWARE(SD8897_DEFAULT_FW_NAME); MODULE_FIRMWARE(SD8887_DEFAULT_FW_NAME); MODULE_FIRMWARE(SD8977_DEFAULT_FW_NAME); +MODULE_FIRMWARE(SD8978_SDIOUART_FW_NAME); MODULE_FIRMWARE(SD8987_DEFAULT_FW_NAME); MODULE_FIRMWARE(SD8997_DEFAULT_FW_NAME); MODULE_FIRMWARE(SD8997_SDIOUART_FW_NAME); diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.h b/drivers/net/wireless/marvell/mwifiex/sdio.h index 3a24bb48b29962884b55bc847d317729e3ec3989..a5112cb35cdcda60956b23b6647401b21bf96e63 100644 --- a/drivers/net/wireless/marvell/mwifiex/sdio.h +++ b/drivers/net/wireless/marvell/mwifiex/sdio.h @@ -25,6 +25,7 @@ #define SD8887_DEFAULT_FW_NAME "mrvl/sd8887_uapsta.bin" #define SD8801_DEFAULT_FW_NAME "mrvl/sd8801_uapsta.bin" #define SD8977_DEFAULT_FW_NAME "mrvl/sdsd8977_combo_v2.bin" +#define SD8978_SDIOUART_FW_NAME "mrvl/sdiouartiw416_combo_v0.bin" #define SD8987_DEFAULT_FW_NAME "mrvl/sd8987_uapsta.bin" #define SD8997_DEFAULT_FW_NAME "mrvl/sdsd8997_combo_v4.bin" #define SD8997_SDIOUART_FW_NAME "mrvl/sdiouart8997_combo_v4.bin" @@ -257,6 +258,7 @@ struct sdio_mmc_card { bool fw_dump_enh; bool can_auto_tdls; bool can_ext_scan; + bool fw_ready_extra_delay; struct mwifiex_sdio_mpa_tx mpa_tx; struct mwifiex_sdio_mpa_rx mpa_rx; @@ -280,6 +282,7 @@ struct mwifiex_sdio_device { bool fw_dump_enh; bool can_auto_tdls; bool can_ext_scan; + bool fw_ready_extra_delay; }; /* diff --git a/drivers/net/wireless/microchip/wilc1000/cfg80211.c b/drivers/net/wireless/microchip/wilc1000/cfg80211.c index b545d93c6e374e6cf1b8f1837735440475870aac..6f3245a43aef179c9c97f26475d17fdf83411771 100644 --- a/drivers/net/wireless/microchip/wilc1000/cfg80211.c +++ b/drivers/net/wireless/microchip/wilc1000/cfg80211.c @@ -1615,7 +1615,6 @@ static int del_virtual_intf(struct wiphy *wiphy, struct wireless_dev *wdev) cfg80211_unregister_netdevice(vif->ndev); vif->monitor_flag = 0; - wilc_set_operation_mode(vif, 0, 0, 0); mutex_lock(&wl->vif_mutex); list_del_rcu(&vif->list); wl->vif_num--; @@ -1810,15 +1809,24 @@ int wilc_cfg80211_init(struct wilc **wilc, struct device *dev, int io_type, INIT_LIST_HEAD(&wl->rxq_head.list); INIT_LIST_HEAD(&wl->vif_list); + wl->hif_workqueue = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, + wiphy_name(wl->wiphy)); + if (!wl->hif_workqueue) { + ret = -ENOMEM; + goto free_cfg; + } vif = wilc_netdev_ifc_init(wl, "wlan%d", WILC_STATION_MODE, NL80211_IFTYPE_STATION, false); if (IS_ERR(vif)) { ret = PTR_ERR(vif); - goto free_cfg; + goto free_hq; } return 0; +free_hq: + destroy_workqueue(wl->hif_workqueue); + free_cfg: wilc_wlan_cfg_deinit(wl); diff --git a/drivers/net/wireless/microchip/wilc1000/hif.c b/drivers/net/wireless/microchip/wilc1000/hif.c index a1b75feec6edf5eeb54d0a223e0fe4b41b2b84cd..5eb02902e875ada60e502800d138ad9e95f1768f 100644 --- a/drivers/net/wireless/microchip/wilc1000/hif.c +++ b/drivers/net/wireless/microchip/wilc1000/hif.c @@ -374,38 +374,49 @@ out: void *wilc_parse_join_bss_param(struct cfg80211_bss *bss, struct cfg80211_crypto_settings *crypto) { - struct wilc_join_bss_param *param; - struct ieee80211_p2p_noa_attr noa_attr; - u8 rates_len = 0; - const u8 *tim_elm, *ssid_elm, *rates_ie, *supp_rates_ie; + const u8 *ies_data, *tim_elm, *ssid_elm, *rates_ie, *supp_rates_ie; const u8 *ht_ie, *wpa_ie, *wmm_ie, *rsn_ie; + struct ieee80211_p2p_noa_attr noa_attr; + const struct cfg80211_bss_ies *ies; + struct wilc_join_bss_param *param; + u8 rates_len = 0, ies_len; int ret; - const struct cfg80211_bss_ies *ies = rcu_dereference(bss->ies); param = kzalloc(sizeof(*param), GFP_KERNEL); if (!param) return NULL; + rcu_read_lock(); + ies = rcu_dereference(bss->ies); + ies_data = kmemdup(ies->data, ies->len, GFP_ATOMIC); + if (!ies_data) { + rcu_read_unlock(); + kfree(param); + return NULL; + } + ies_len = ies->len; + rcu_read_unlock(); + param->beacon_period = cpu_to_le16(bss->beacon_interval); param->cap_info = cpu_to_le16(bss->capability); param->bss_type = WILC_FW_BSS_TYPE_INFRA; param->ch = ieee80211_frequency_to_channel(bss->channel->center_freq); ether_addr_copy(param->bssid, bss->bssid); - ssid_elm = cfg80211_find_ie(WLAN_EID_SSID, ies->data, ies->len); + ssid_elm = cfg80211_find_ie(WLAN_EID_SSID, ies_data, ies_len); if (ssid_elm) { if (ssid_elm[1] <= IEEE80211_MAX_SSID_LEN) memcpy(param->ssid, ssid_elm + 2, ssid_elm[1]); } - tim_elm = cfg80211_find_ie(WLAN_EID_TIM, ies->data, ies->len); + tim_elm = cfg80211_find_ie(WLAN_EID_TIM, ies_data, ies_len); if (tim_elm && tim_elm[1] >= 2) param->dtim_period = tim_elm[3]; memset(param->p_suites, 0xFF, 3); memset(param->akm_suites, 0xFF, 3); - rates_ie = cfg80211_find_ie(WLAN_EID_SUPP_RATES, ies->data, ies->len); + rates_ie = cfg80211_find_ie(WLAN_EID_SUPP_RATES, ies_data, ies_len); if (rates_ie) { rates_len = rates_ie[1]; if (rates_len > WILC_MAX_RATES_SUPPORTED) @@ -416,7 +427,7 @@ void *wilc_parse_join_bss_param(struct cfg80211_bss *bss, if (rates_len < WILC_MAX_RATES_SUPPORTED) { supp_rates_ie = cfg80211_find_ie(WLAN_EID_EXT_SUPP_RATES, - ies->data, ies->len); + ies_data, ies_len); if (supp_rates_ie) { u8 ext_rates = supp_rates_ie[1]; @@ -431,11 +442,11 @@ void *wilc_parse_join_bss_param(struct cfg80211_bss *bss, } } - ht_ie = cfg80211_find_ie(WLAN_EID_HT_CAPABILITY, ies->data, ies->len); + ht_ie = cfg80211_find_ie(WLAN_EID_HT_CAPABILITY, ies_data, ies_len); if (ht_ie) param->ht_capable = true; - ret = cfg80211_get_p2p_attr(ies->data, ies->len, + ret = cfg80211_get_p2p_attr(ies_data, ies_len, IEEE80211_P2P_ATTR_ABSENCE_NOTICE, (u8 *)&noa_attr, sizeof(noa_attr)); if (ret > 0) { @@ -459,7 +470,7 @@ void *wilc_parse_join_bss_param(struct cfg80211_bss *bss, } wmm_ie = cfg80211_find_vendor_ie(WLAN_OUI_MICROSOFT, WLAN_OUI_TYPE_MICROSOFT_WMM, - ies->data, ies->len); + ies_data, ies_len); if (wmm_ie) { struct ieee80211_wmm_param_ie *ie; @@ -474,13 +485,13 @@ void *wilc_parse_join_bss_param(struct cfg80211_bss *bss, wpa_ie = cfg80211_find_vendor_ie(WLAN_OUI_MICROSOFT, WLAN_OUI_TYPE_MICROSOFT_WPA, - ies->data, ies->len); + ies_data, ies_len); if (wpa_ie) { param->mode_802_11i = 1; param->rsn_found = true; } - rsn_ie = cfg80211_find_ie(WLAN_EID_RSN, ies->data, ies->len); + rsn_ie = cfg80211_find_ie(WLAN_EID_RSN, ies_data, ies_len); if (rsn_ie) { int rsn_ie_len = sizeof(struct element) + rsn_ie[1]; int offset = 8; @@ -514,6 +525,7 @@ void *wilc_parse_join_bss_param(struct cfg80211_bss *bss, param->akm_suites[i] = crypto->akm_suites[i] & 0xFF; } + kfree(ies_data); return (void *)param; } diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.c b/drivers/net/wireless/microchip/wilc1000/netdev.c index e9f59de31b0b9559c7f8a43619a71b755b9e44b3..b714da48eaa17250f60ea9c7de1320728eb61f1c 100644 --- a/drivers/net/wireless/microchip/wilc1000/netdev.c +++ b/drivers/net/wireless/microchip/wilc1000/netdev.c @@ -878,8 +878,7 @@ static const struct net_device_ops wilc_netdev_ops = { void wilc_netdev_cleanup(struct wilc *wilc) { - struct wilc_vif *vif; - int srcu_idx, ifc_cnt = 0; + struct wilc_vif *vif, *vif_tmp; if (!wilc) return; @@ -889,32 +888,19 @@ void wilc_netdev_cleanup(struct wilc *wilc) wilc->firmware = NULL; } - srcu_idx = srcu_read_lock(&wilc->srcu); - list_for_each_entry_rcu(vif, &wilc->vif_list, list) { + list_for_each_entry_safe(vif, vif_tmp, &wilc->vif_list, list) { + mutex_lock(&wilc->vif_mutex); + list_del_rcu(&vif->list); + wilc->vif_num--; + mutex_unlock(&wilc->vif_mutex); + synchronize_srcu(&wilc->srcu); if (vif->ndev) unregister_netdev(vif->ndev); } - srcu_read_unlock(&wilc->srcu, srcu_idx); wilc_wfi_deinit_mon_interface(wilc, false); destroy_workqueue(wilc->hif_workqueue); - while (ifc_cnt < WILC_NUM_CONCURRENT_IFC) { - mutex_lock(&wilc->vif_mutex); - if (wilc->vif_num <= 0) { - mutex_unlock(&wilc->vif_mutex); - break; - } - vif = wilc_get_wl_to_vif(wilc); - if (!IS_ERR(vif)) - list_del_rcu(&vif->list); - - wilc->vif_num--; - mutex_unlock(&wilc->vif_mutex); - synchronize_srcu(&wilc->srcu); - ifc_cnt++; - } - wilc_wlan_cfg_deinit(wilc); wlan_deinit_locks(wilc); wiphy_unregister(wilc->wiphy); @@ -977,13 +963,6 @@ struct wilc_vif *wilc_netdev_ifc_init(struct wilc *wl, const char *name, goto error; } - wl->hif_workqueue = alloc_ordered_workqueue("%s-wq", WQ_MEM_RECLAIM, - ndev->name); - if (!wl->hif_workqueue) { - ret = -ENOMEM; - goto unregister_netdev; - } - ndev->needs_free_netdev = true; vif->iftype = vif_type; vif->idx = wilc_get_available_idx(wl); @@ -996,12 +975,11 @@ struct wilc_vif *wilc_netdev_ifc_init(struct wilc *wl, const char *name, return vif; -unregister_netdev: +error: if (rtnl_locked) cfg80211_unregister_netdevice(ndev); else unregister_netdev(ndev); - error: free_netdev(ndev); return ERR_PTR(ret); } diff --git a/drivers/net/wireless/microchip/wilc1000/spi.c b/drivers/net/wireless/microchip/wilc1000/spi.c index b0fc5e68feeca5db355918acca1959d613f1f948..5877e2c1fa0fc935483ab09dbf579f4dfd8bddcf 100644 --- a/drivers/net/wireless/microchip/wilc1000/spi.c +++ b/drivers/net/wireless/microchip/wilc1000/spi.c @@ -191,11 +191,11 @@ static void wilc_wlan_power(struct wilc *wilc, bool on) /* assert ENABLE: */ gpiod_set_value(gpios->enable, 1); mdelay(5); - /* assert RESET: */ - gpiod_set_value(gpios->reset, 1); - } else { /* deassert RESET: */ gpiod_set_value(gpios->reset, 0); + } else { + /* assert RESET: */ + gpiod_set_value(gpios->reset, 1); /* deassert ENABLE: */ gpiod_set_value(gpios->enable, 0); } diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index 6dd5ec1e4d8c39be3570c2f4ca9344b7dae265bc..ccac47dd781d6237a4cc873876c201dc17ddc7ce 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -6542,6 +6542,7 @@ static void rtl8xxxu_stop(struct ieee80211_hw *hw) if (priv->usb_interrupts) rtl8xxxu_write32(priv, REG_USB_HIMR, 0); + cancel_work_sync(&priv->c2hcmd_work); cancel_delayed_work_sync(&priv->ra_watchdog); rtl8xxxu_free_rx_resources(priv); diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c index 4c8164db4a9e4859b4a5a842687e9a35b1e91f1d..81f3112923f1c2c70358649277795a8338d7027f 100644 --- a/drivers/net/wireless/realtek/rtw88/main.c +++ b/drivers/net/wireless/realtek/rtw88/main.c @@ -1989,8 +1989,6 @@ static int rtw_chip_board_info_setup(struct rtw_dev *rtwdev) rtw_phy_setup_phy_cond(rtwdev, 0); rtw_phy_init_tx_power(rtwdev); - if (rfe_def->agc_btg_tbl) - rtw_load_table(rtwdev, rfe_def->agc_btg_tbl); rtw_load_table(rtwdev, rfe_def->phy_pg_tbl); rtw_load_table(rtwdev, rfe_def->txpwr_lmt_tbl); rtw_phy_tx_power_by_rate_config(hal); diff --git a/drivers/net/wireless/realtek/rtw88/phy.c b/drivers/net/wireless/realtek/rtw88/phy.c index bd7d05e0808483d301f7e3cf7b81c1743b8ddf0d..fde7b532bc07e92a0e8cc50cb448a6e736d998df 100644 --- a/drivers/net/wireless/realtek/rtw88/phy.c +++ b/drivers/net/wireless/realtek/rtw88/phy.c @@ -1761,12 +1761,15 @@ static void rtw_load_rfk_table(struct rtw_dev *rtwdev) void rtw_phy_load_tables(struct rtw_dev *rtwdev) { + const struct rtw_rfe_def *rfe_def = rtw_get_rfe_def(rtwdev); const struct rtw_chip_info *chip = rtwdev->chip; u8 rf_path; rtw_load_table(rtwdev, chip->mac_tbl); rtw_load_table(rtwdev, chip->bb_tbl); rtw_load_table(rtwdev, chip->agc_tbl); + if (rfe_def->agc_btg_tbl) + rtw_load_table(rtwdev, rfe_def->agc_btg_tbl); rtw_load_rfk_table(rtwdev); for (rf_path = 0; rf_path < rtwdev->hal.rf_path_num; rf_path++) { diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821c.c b/drivers/net/wireless/realtek/rtw88/rtw8821c.c index 609a2b86330d8cb60be247a85f5fcc8e6f0c5320..50e3e46f7d8aaa5b887be73ba9b5cc1584eff4a2 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8821c.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8821c.c @@ -674,9 +674,9 @@ static void rtw8821c_false_alarm_statistics(struct rtw_dev *rtwdev) dm_info->cck_fa_cnt = cck_fa_cnt; dm_info->ofdm_fa_cnt = ofdm_fa_cnt; + dm_info->total_fa_cnt = ofdm_fa_cnt; if (cck_enable) dm_info->total_fa_cnt += cck_fa_cnt; - dm_info->total_fa_cnt = ofdm_fa_cnt; crc32_cnt = rtw_read32(rtwdev, REG_CRC_CCK); dm_info->cck_ok_cnt = FIELD_GET(GENMASK(15, 0), crc32_cnt); diff --git a/drivers/net/wireless/realtek/rtw89/pci.h b/drivers/net/wireless/realtek/rtw89/pci.h index 179740607778a54a63c1c1cc3e9762e8a8e912cc..d982c5dc0889f76fc0a05364c49046de6743e042 100644 --- a/drivers/net/wireless/realtek/rtw89/pci.h +++ b/drivers/net/wireless/realtek/rtw89/pci.h @@ -546,7 +546,7 @@ #define RTW89_PCI_TXWD_NUM_MAX 512 #define RTW89_PCI_TXWD_PAGE_SIZE 128 #define RTW89_PCI_ADDRINFO_MAX 4 -#define RTW89_PCI_RX_BUF_SIZE 11460 +#define RTW89_PCI_RX_BUF_SIZE (11454 + 40) /* +40 for rtw89_rxdesc_long_v2 */ #define RTW89_PCI_POLL_BDRAM_RST_CNT 100 #define RTW89_PCI_MULTITAG 8 diff --git a/drivers/net/wireless/silabs/wfx/sta.c b/drivers/net/wireless/silabs/wfx/sta.c index 073e870b264159b7fd610ff74052168d87ddace6..871667650dbefef889102c6e731e2b5baae411bd 100644 --- a/drivers/net/wireless/silabs/wfx/sta.c +++ b/drivers/net/wireless/silabs/wfx/sta.c @@ -362,6 +362,7 @@ static int wfx_set_mfp_ap(struct wfx_vif *wvif) const int pairwise_cipher_suite_count_offset = 8 / sizeof(u16); const int pairwise_cipher_suite_size = 4 / sizeof(u16); const int akm_suite_size = 4 / sizeof(u16); + int ret = -EINVAL; const u16 *ptr; if (unlikely(!skb)) @@ -370,22 +371,26 @@ static int wfx_set_mfp_ap(struct wfx_vif *wvif) ptr = (u16 *)cfg80211_find_ie(WLAN_EID_RSN, skb->data + ieoffset, skb->len - ieoffset); if (unlikely(!ptr)) - return -EINVAL; + goto free_skb; ptr += pairwise_cipher_suite_count_offset; if (WARN_ON(ptr > (u16 *)skb_tail_pointer(skb))) - return -EINVAL; + goto free_skb; ptr += 1 + pairwise_cipher_suite_size * *ptr; if (WARN_ON(ptr > (u16 *)skb_tail_pointer(skb))) - return -EINVAL; + goto free_skb; ptr += 1 + akm_suite_size * *ptr; if (WARN_ON(ptr > (u16 *)skb_tail_pointer(skb))) - return -EINVAL; + goto free_skb; wfx_hif_set_mfp(wvif, *ptr & BIT(7), *ptr & BIT(6)); - return 0; + ret = 0; + +free_skb: + dev_kfree_skb(skb); + return ret; } int wfx_start_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif, diff --git a/drivers/net/wwan/t7xx/t7xx_cldma.c b/drivers/net/wwan/t7xx/t7xx_cldma.c index 9f43f256db1d063c45c17dda3d78037be4183f9c..f0a4783baf1f328ed50e629591244f3a4ccb77eb 100644 --- a/drivers/net/wwan/t7xx/t7xx_cldma.c +++ b/drivers/net/wwan/t7xx/t7xx_cldma.c @@ -106,7 +106,7 @@ bool t7xx_cldma_tx_addr_is_set(struct t7xx_cldma_hw *hw_info, unsigned int qno) { u32 offset = REG_CLDMA_UL_START_ADDRL_0 + qno * ADDR_SIZE; - return ioread64(hw_info->ap_pdn_base + offset); + return ioread64_lo_hi(hw_info->ap_pdn_base + offset); } void t7xx_cldma_hw_set_start_addr(struct t7xx_cldma_hw *hw_info, unsigned int qno, u64 address, @@ -117,7 +117,7 @@ void t7xx_cldma_hw_set_start_addr(struct t7xx_cldma_hw *hw_info, unsigned int qn reg = tx_rx == MTK_RX ? hw_info->ap_ao_base + REG_CLDMA_DL_START_ADDRL_0 : hw_info->ap_pdn_base + REG_CLDMA_UL_START_ADDRL_0; - iowrite64(address, reg + offset); + iowrite64_lo_hi(address, reg + offset); } void t7xx_cldma_hw_resume_queue(struct t7xx_cldma_hw *hw_info, unsigned int qno, diff --git a/drivers/net/wwan/t7xx/t7xx_hif_cldma.c b/drivers/net/wwan/t7xx/t7xx_hif_cldma.c index 6ff30cb8eb16ff269135dddf1eb95d9db6c219d3..5d6032ceb9e512eb2f852ff7b7728479c3aed722 100644 --- a/drivers/net/wwan/t7xx/t7xx_hif_cldma.c +++ b/drivers/net/wwan/t7xx/t7xx_hif_cldma.c @@ -139,8 +139,9 @@ static int t7xx_cldma_gpd_rx_from_q(struct cldma_queue *queue, int budget, bool return -ENODEV; } - gpd_addr = ioread64(hw_info->ap_pdn_base + REG_CLDMA_DL_CURRENT_ADDRL_0 + - queue->index * sizeof(u64)); + gpd_addr = ioread64_lo_hi(hw_info->ap_pdn_base + + REG_CLDMA_DL_CURRENT_ADDRL_0 + + queue->index * sizeof(u64)); if (req->gpd_addr == gpd_addr || hwo_polling_count++ >= 100) return 0; @@ -318,8 +319,8 @@ static void t7xx_cldma_txq_empty_hndl(struct cldma_queue *queue) struct t7xx_cldma_hw *hw_info = &md_ctrl->hw_info; /* Check current processing TGPD, 64-bit address is in a table by Q index */ - ul_curr_addr = ioread64(hw_info->ap_pdn_base + REG_CLDMA_UL_CURRENT_ADDRL_0 + - queue->index * sizeof(u64)); + ul_curr_addr = ioread64_lo_hi(hw_info->ap_pdn_base + REG_CLDMA_UL_CURRENT_ADDRL_0 + + queue->index * sizeof(u64)); if (req->gpd_addr != ul_curr_addr) { spin_unlock_irqrestore(&md_ctrl->cldma_lock, flags); dev_err(md_ctrl->dev, "CLDMA%d queue %d is not empty\n", diff --git a/drivers/net/wwan/t7xx/t7xx_pcie_mac.c b/drivers/net/wwan/t7xx/t7xx_pcie_mac.c index 76da4c15e3de17c11d0373a26066450b34ee9666..f071ec7ff23d50842b280fae1535863ecfd0740d 100644 --- a/drivers/net/wwan/t7xx/t7xx_pcie_mac.c +++ b/drivers/net/wwan/t7xx/t7xx_pcie_mac.c @@ -75,7 +75,7 @@ static void t7xx_pcie_mac_atr_tables_dis(void __iomem *pbase, enum t7xx_atr_src_ for (i = 0; i < ATR_TABLE_NUM_PER_ATR; i++) { offset = ATR_PORT_OFFSET * port + ATR_TABLE_OFFSET * i; reg = pbase + ATR_PCIE_WIN0_T0_ATR_PARAM_SRC_ADDR + offset; - iowrite64(0, reg); + iowrite64_lo_hi(0, reg); } } @@ -112,17 +112,17 @@ static int t7xx_pcie_mac_atr_cfg(struct t7xx_pci_dev *t7xx_dev, struct t7xx_atr_ reg = pbase + ATR_PCIE_WIN0_T0_TRSL_ADDR + offset; value = cfg->trsl_addr & ATR_PCIE_WIN0_ADDR_ALGMT; - iowrite64(value, reg); + iowrite64_lo_hi(value, reg); reg = pbase + ATR_PCIE_WIN0_T0_TRSL_PARAM + offset; iowrite32(cfg->trsl_id, reg); reg = pbase + ATR_PCIE_WIN0_T0_ATR_PARAM_SRC_ADDR + offset; value = (cfg->src_addr & ATR_PCIE_WIN0_ADDR_ALGMT) | (atr_size << 1) | BIT(0); - iowrite64(value, reg); + iowrite64_lo_hi(value, reg); /* Ensure ATR is set */ - ioread64(reg); + ioread64_lo_hi(reg); return 0; } diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 27160409857485e879c915acdfef9474aaef1b61..0d51c900c55384cadf129ef93742e2cdbc141a13 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -104,13 +104,12 @@ bool provides_xdp_headroom = true; module_param(provides_xdp_headroom, bool, 0644); static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, - u8 status); + s8 status); static void make_tx_response(struct xenvif_queue *queue, - struct xen_netif_tx_request *txp, + const struct xen_netif_tx_request *txp, unsigned int extra_count, - s8 st); -static void push_tx_responses(struct xenvif_queue *queue); + s8 status); static void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx); @@ -208,13 +207,9 @@ static void xenvif_tx_err(struct xenvif_queue *queue, unsigned int extra_count, RING_IDX end) { RING_IDX cons = queue->tx.req_cons; - unsigned long flags; do { - spin_lock_irqsave(&queue->response_lock, flags); make_tx_response(queue, txp, extra_count, XEN_NETIF_RSP_ERROR); - push_tx_responses(queue); - spin_unlock_irqrestore(&queue->response_lock, flags); if (cons == end) break; RING_COPY_REQUEST(&queue->tx, cons++, txp); @@ -465,12 +460,7 @@ static void xenvif_get_requests(struct xenvif_queue *queue, for (shinfo->nr_frags = 0; nr_slots > 0 && shinfo->nr_frags < MAX_SKB_FRAGS; nr_slots--) { if (unlikely(!txp->size)) { - unsigned long flags; - - spin_lock_irqsave(&queue->response_lock, flags); make_tx_response(queue, txp, 0, XEN_NETIF_RSP_OKAY); - push_tx_responses(queue); - spin_unlock_irqrestore(&queue->response_lock, flags); ++txp; continue; } @@ -496,14 +486,8 @@ static void xenvif_get_requests(struct xenvif_queue *queue, for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; ++txp) { if (unlikely(!txp->size)) { - unsigned long flags; - - spin_lock_irqsave(&queue->response_lock, flags); make_tx_response(queue, txp, 0, XEN_NETIF_RSP_OKAY); - push_tx_responses(queue); - spin_unlock_irqrestore(&queue->response_lock, - flags); continue; } @@ -997,7 +981,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, (ret == 0) ? XEN_NETIF_RSP_OKAY : XEN_NETIF_RSP_ERROR); - push_tx_responses(queue); continue; } @@ -1009,7 +992,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, make_tx_response(queue, &txreq, extra_count, XEN_NETIF_RSP_OKAY); - push_tx_responses(queue); continue; } @@ -1444,8 +1426,35 @@ int xenvif_tx_action(struct xenvif_queue *queue, int budget) return work_done; } +static void _make_tx_response(struct xenvif_queue *queue, + const struct xen_netif_tx_request *txp, + unsigned int extra_count, + s8 status) +{ + RING_IDX i = queue->tx.rsp_prod_pvt; + struct xen_netif_tx_response *resp; + + resp = RING_GET_RESPONSE(&queue->tx, i); + resp->id = txp->id; + resp->status = status; + + while (extra_count-- != 0) + RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL; + + queue->tx.rsp_prod_pvt = ++i; +} + +static void push_tx_responses(struct xenvif_queue *queue) +{ + int notify; + + RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify); + if (notify) + notify_remote_via_irq(queue->tx_irq); +} + static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, - u8 status) + s8 status) { struct pending_tx_info *pending_tx_info; pending_ring_idx_t index; @@ -1455,8 +1464,8 @@ static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, spin_lock_irqsave(&queue->response_lock, flags); - make_tx_response(queue, &pending_tx_info->req, - pending_tx_info->extra_count, status); + _make_tx_response(queue, &pending_tx_info->req, + pending_tx_info->extra_count, status); /* Release the pending index before pusing the Tx response so * its available before a new Tx request is pushed by the @@ -1470,32 +1479,19 @@ static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, spin_unlock_irqrestore(&queue->response_lock, flags); } - static void make_tx_response(struct xenvif_queue *queue, - struct xen_netif_tx_request *txp, + const struct xen_netif_tx_request *txp, unsigned int extra_count, - s8 st) + s8 status) { - RING_IDX i = queue->tx.rsp_prod_pvt; - struct xen_netif_tx_response *resp; - - resp = RING_GET_RESPONSE(&queue->tx, i); - resp->id = txp->id; - resp->status = st; - - while (extra_count-- != 0) - RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL; + unsigned long flags; - queue->tx.rsp_prod_pvt = ++i; -} + spin_lock_irqsave(&queue->response_lock, flags); -static void push_tx_responses(struct xenvif_queue *queue) -{ - int notify; + _make_tx_response(queue, txp, extra_count, status); + push_tx_responses(queue); - RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify); - if (notify) - notify_remote_via_irq(queue->tx_irq); + spin_unlock_irqrestore(&queue->response_lock, flags); } static void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx) diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index dc404e05970cd22b4e81c72c7b15114c00b18309..95b5ab4b964e25dca12a57ad8b35ea4cb8e7d71e 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -285,6 +285,7 @@ static struct sk_buff *xennet_alloc_one_rx_buffer(struct netfront_queue *queue) return NULL; } skb_add_rx_frag(skb, 0, page, 0, 0, PAGE_SIZE); + skb_mark_for_recycle(skb); /* Align ip header to a 16 bytes boundary */ skb_reserve(skb, NET_IP_ALIGN); diff --git a/drivers/nfc/trf7970a.c b/drivers/nfc/trf7970a.c index 21d68664fe0824bb8499c8fcb91b27ab9b224188..7968baa626d16f281dcc2c03aef4e5923fb846ca 100644 --- a/drivers/nfc/trf7970a.c +++ b/drivers/nfc/trf7970a.c @@ -424,7 +424,8 @@ struct trf7970a { enum trf7970a_state state; struct device *dev; struct spi_device *spi; - struct regulator *regulator; + struct regulator *vin_regulator; + struct regulator *vddio_regulator; struct nfc_digital_dev *ddev; u32 quirks; bool is_initiator; @@ -1883,7 +1884,7 @@ static int trf7970a_power_up(struct trf7970a *trf) if (trf->state != TRF7970A_ST_PWR_OFF) return 0; - ret = regulator_enable(trf->regulator); + ret = regulator_enable(trf->vin_regulator); if (ret) { dev_err(trf->dev, "%s - Can't enable VIN: %d\n", __func__, ret); return ret; @@ -1926,7 +1927,7 @@ static int trf7970a_power_down(struct trf7970a *trf) if (trf->en2_gpiod && !(trf->quirks & TRF7970A_QUIRK_EN2_MUST_STAY_LOW)) gpiod_set_value_cansleep(trf->en2_gpiod, 0); - ret = regulator_disable(trf->regulator); + ret = regulator_disable(trf->vin_regulator); if (ret) dev_err(trf->dev, "%s - Can't disable VIN: %d\n", __func__, ret); @@ -2065,37 +2066,37 @@ static int trf7970a_probe(struct spi_device *spi) mutex_init(&trf->lock); INIT_DELAYED_WORK(&trf->timeout_work, trf7970a_timeout_work_handler); - trf->regulator = devm_regulator_get(&spi->dev, "vin"); - if (IS_ERR(trf->regulator)) { - ret = PTR_ERR(trf->regulator); + trf->vin_regulator = devm_regulator_get(&spi->dev, "vin"); + if (IS_ERR(trf->vin_regulator)) { + ret = PTR_ERR(trf->vin_regulator); dev_err(trf->dev, "Can't get VIN regulator: %d\n", ret); goto err_destroy_lock; } - ret = regulator_enable(trf->regulator); + ret = regulator_enable(trf->vin_regulator); if (ret) { dev_err(trf->dev, "Can't enable VIN: %d\n", ret); goto err_destroy_lock; } - uvolts = regulator_get_voltage(trf->regulator); + uvolts = regulator_get_voltage(trf->vin_regulator); if (uvolts > 4000000) trf->chip_status_ctrl = TRF7970A_CHIP_STATUS_VRS5_3; - trf->regulator = devm_regulator_get(&spi->dev, "vdd-io"); - if (IS_ERR(trf->regulator)) { - ret = PTR_ERR(trf->regulator); + trf->vddio_regulator = devm_regulator_get(&spi->dev, "vdd-io"); + if (IS_ERR(trf->vddio_regulator)) { + ret = PTR_ERR(trf->vddio_regulator); dev_err(trf->dev, "Can't get VDD_IO regulator: %d\n", ret); - goto err_destroy_lock; + goto err_disable_vin_regulator; } - ret = regulator_enable(trf->regulator); + ret = regulator_enable(trf->vddio_regulator); if (ret) { dev_err(trf->dev, "Can't enable VDD_IO: %d\n", ret); - goto err_destroy_lock; + goto err_disable_vin_regulator; } - if (regulator_get_voltage(trf->regulator) == 1800000) { + if (regulator_get_voltage(trf->vddio_regulator) == 1800000) { trf->io_ctrl = TRF7970A_REG_IO_CTRL_IO_LOW; dev_dbg(trf->dev, "trf7970a config vdd_io to 1.8V\n"); } @@ -2108,7 +2109,7 @@ static int trf7970a_probe(struct spi_device *spi) if (!trf->ddev) { dev_err(trf->dev, "Can't allocate NFC digital device\n"); ret = -ENOMEM; - goto err_disable_regulator; + goto err_disable_vddio_regulator; } nfc_digital_set_parent_dev(trf->ddev, trf->dev); @@ -2137,8 +2138,10 @@ err_shutdown: trf7970a_shutdown(trf); err_free_ddev: nfc_digital_free_device(trf->ddev); -err_disable_regulator: - regulator_disable(trf->regulator); +err_disable_vddio_regulator: + regulator_disable(trf->vddio_regulator); +err_disable_vin_regulator: + regulator_disable(trf->vin_regulator); err_destroy_lock: mutex_destroy(&trf->lock); return ret; @@ -2157,7 +2160,8 @@ static void trf7970a_remove(struct spi_device *spi) nfc_digital_unregister_device(trf->ddev); nfc_digital_free_device(trf->ddev); - regulator_disable(trf->regulator); + regulator_disable(trf->vddio_regulator); + regulator_disable(trf->vin_regulator); mutex_destroy(&trf->lock); } diff --git a/drivers/ntb/core.c b/drivers/ntb/core.c index 27dd93deff6e561bea171f4695dbd8b975df6c0c..d702bee7808266e3ee04fd49a2c157a3413bc9b2 100644 --- a/drivers/ntb/core.c +++ b/drivers/ntb/core.c @@ -100,6 +100,8 @@ EXPORT_SYMBOL(ntb_unregister_client); int ntb_register_device(struct ntb_dev *ntb) { + int ret; + if (!ntb) return -EINVAL; if (!ntb->pdev) @@ -120,7 +122,11 @@ int ntb_register_device(struct ntb_dev *ntb) ntb->ctx_ops = NULL; spin_lock_init(&ntb->ctx_lock); - return device_register(&ntb->dev); + ret = device_register(&ntb->dev); + if (ret) + put_device(&ntb->dev); + + return ret; } EXPORT_SYMBOL(ntb_register_device); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 0c088db944706663c43f69db92cc8776cb14ec6d..75b4dd8a55b033ac22a41162f68efb43cf6c88e5 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1151,7 +1151,7 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, return effects; } -void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects, +void nvme_passthru_end(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u32 effects, struct nvme_command *cmd, int status) { if (effects & NVME_CMD_EFFECTS_CSE_MASK) { @@ -1167,6 +1167,8 @@ void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects, nvme_queue_scan(ctrl); flush_work(&ctrl->scan_work); } + if (ns) + return; switch (cmd->common.opcode) { case nvme_admin_set_features: @@ -4282,7 +4284,7 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) "Found shared namespace %d, but multipathing not supported.\n", info->nsid); dev_warn_once(ctrl->device, - "Support for shared namespaces without CONFIG_NVME_MULTIPATH is deprecated and will be removed in Linux 6.0\n."); + "Support for shared namespaces without CONFIG_NVME_MULTIPATH is deprecated and will be removed in Linux 6.0.\n"); } } @@ -4971,7 +4973,8 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, set->ops = ops; set->queue_depth = NVME_AQ_MQ_TAG_DEPTH; if (ctrl->ops->flags & NVME_F_FABRICS) - set->reserved_tags = NVMF_RESERVED_TAGS; + /* Reserved for fabric connect and keep alive */ + set->reserved_tags = 2; set->numa_node = ctrl->numa_node; set->flags = BLK_MQ_F_NO_SCHED; if (ctrl->ops->flags & NVME_F_BLOCKING) @@ -5029,7 +5032,15 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, memset(set, 0, sizeof(*set)); set->ops = ops; set->queue_depth = ctrl->sqsize + 1; - set->reserved_tags = NVMF_RESERVED_TAGS; + /* + * Some Apple controllers requires tags to be unique across admin and + * the (only) I/O queue, so reserve the first 32 tags of the I/O queue. + */ + if (ctrl->quirks & NVME_QUIRK_SHARED_TAGS) + set->reserved_tags = NVME_AQ_DEPTH; + else if (ctrl->ops->flags & NVME_F_FABRICS) + /* Reserved for fabric connect */ + set->reserved_tags = 1; set->numa_node = ctrl->numa_node; set->flags = BLK_MQ_F_SHOULD_MERGE; if (ctrl->ops->flags & NVME_F_BLOCKING) diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index dcac3df8a5f760427cff2750ac7c0de501fca409..60c238caf7a97e763c283d61d65c53b87cc0f8b7 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -18,13 +18,6 @@ /* default is -1: the fail fast mechanism is disabled */ #define NVMF_DEF_FAIL_FAST_TMO -1 -/* - * Reserved one command for internal usage. This command is used for sending - * the connect command, as well as for the keep alive command on the admin - * queue once live. - */ -#define NVMF_RESERVED_TAGS 1 - /* * Define a host as seen by the target. We allocate one at boot, but also * allow the override it when creating controllers. This is both to provide diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 177a365b8ec558ce06cc97016c72f3786d13d69c..3dbf926fd99fd5541ef108f891bca1509aec61ba 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -221,11 +221,6 @@ static LIST_HEAD(nvme_fc_lport_list); static DEFINE_IDA(nvme_fc_local_port_cnt); static DEFINE_IDA(nvme_fc_ctrl_cnt); -static struct workqueue_struct *nvme_fc_wq; - -static bool nvme_fc_waiting_to_unload; -static DECLARE_COMPLETION(nvme_fc_unload_proceed); - /* * These items are short-term. They will eventually be moved into * a generic FC class. See comments in module init. @@ -255,8 +250,6 @@ nvme_fc_free_lport(struct kref *ref) /* remove from transport list */ spin_lock_irqsave(&nvme_fc_lock, flags); list_del(&lport->port_list); - if (nvme_fc_waiting_to_unload && list_empty(&nvme_fc_lport_list)) - complete(&nvme_fc_unload_proceed); spin_unlock_irqrestore(&nvme_fc_lock, flags); ida_free(&nvme_fc_local_port_cnt, lport->localport.port_num); @@ -3869,10 +3862,6 @@ static int __init nvme_fc_init_module(void) { int ret; - nvme_fc_wq = alloc_workqueue("nvme_fc_wq", WQ_MEM_RECLAIM, 0); - if (!nvme_fc_wq) - return -ENOMEM; - /* * NOTE: * It is expected that in the future the kernel will combine @@ -3890,7 +3879,7 @@ static int __init nvme_fc_init_module(void) ret = class_register(&fc_class); if (ret) { pr_err("couldn't register class fc\n"); - goto out_destroy_wq; + return ret; } /* @@ -3914,8 +3903,6 @@ out_destroy_device: device_destroy(&fc_class, MKDEV(0, 0)); out_destroy_class: class_unregister(&fc_class); -out_destroy_wq: - destroy_workqueue(nvme_fc_wq); return ret; } @@ -3935,45 +3922,23 @@ nvme_fc_delete_controllers(struct nvme_fc_rport *rport) spin_unlock(&rport->lock); } -static void -nvme_fc_cleanup_for_unload(void) +static void __exit nvme_fc_exit_module(void) { struct nvme_fc_lport *lport; struct nvme_fc_rport *rport; - - list_for_each_entry(lport, &nvme_fc_lport_list, port_list) { - list_for_each_entry(rport, &lport->endp_list, endp_list) { - nvme_fc_delete_controllers(rport); - } - } -} - -static void __exit nvme_fc_exit_module(void) -{ unsigned long flags; - bool need_cleanup = false; spin_lock_irqsave(&nvme_fc_lock, flags); - nvme_fc_waiting_to_unload = true; - if (!list_empty(&nvme_fc_lport_list)) { - need_cleanup = true; - nvme_fc_cleanup_for_unload(); - } + list_for_each_entry(lport, &nvme_fc_lport_list, port_list) + list_for_each_entry(rport, &lport->endp_list, endp_list) + nvme_fc_delete_controllers(rport); spin_unlock_irqrestore(&nvme_fc_lock, flags); - if (need_cleanup) { - pr_info("%s: waiting for ctlr deletes\n", __func__); - wait_for_completion(&nvme_fc_unload_proceed); - pr_info("%s: ctrl deletes complete\n", __func__); - } + flush_workqueue(nvme_delete_wq); nvmf_unregister_transport(&nvme_fc_transport); - ida_destroy(&nvme_fc_local_port_cnt); - ida_destroy(&nvme_fc_ctrl_cnt); - device_destroy(&fc_class, MKDEV(0, 0)); class_unregister(&fc_class); - destroy_workqueue(nvme_fc_wq); } module_init(nvme_fc_init_module); diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 91e6d03475798edb7e53867c30285a2e100306a5..b3e322e4ade38c386cadd21b220f91c8c0df7fa7 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -147,6 +147,7 @@ static int nvme_submit_user_cmd(struct request_queue *q, unsigned bufflen, void __user *meta_buffer, unsigned meta_len, u32 meta_seed, u64 *result, unsigned timeout, bool vec) { + struct nvme_ns *ns = q->queuedata; struct nvme_ctrl *ctrl; struct request *req; void *meta = NULL; @@ -181,7 +182,7 @@ static int nvme_submit_user_cmd(struct request_queue *q, blk_mq_free_request(req); if (effects) - nvme_passthru_end(ctrl, effects, cmd, ret); + nvme_passthru_end(ctrl, ns, effects, cmd, ret); return ret; } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index a892d679e33890c3a8f7199b5ea2920c3ecb6326..8e28d2de45c0e76f75ad3a5c79a460f90e4028e6 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -1063,7 +1063,7 @@ static inline void nvme_auth_free(struct nvme_ctrl *ctrl) {}; u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode); int nvme_execute_passthru_rq(struct request *rq, u32 *effects); -void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects, +void nvme_passthru_end(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u32 effects, struct nvme_command *cmd, int status); struct nvme_ctrl *nvme_ctrl_from_file(struct file *file); struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 3d01290994d89601ac6ddfa379e302852f549895..5ff09f2cacab71ee12cd311cd0fd004a5a675ec7 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3471,6 +3471,9 @@ static const struct pci_device_id nvme_id_table[] = { NVME_QUIRK_BOGUS_NID, }, { PCI_VDEVICE(REDHAT, 0x0010), /* Qemu emulated controller */ .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x126f, 0x2262), /* Silicon Motion generic */ + .driver_data = NVME_QUIRK_NO_DEEPEST_PS | + NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x126f, 0x2263), /* Silicon Motion unidentified */ .driver_data = NVME_QUIRK_NO_NS_DESC_LIST | NVME_QUIRK_BOGUS_NID, }, diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 1ab6601fdd5cf97cad666437591b166059cebd3e..8a02ed63b15666b2da69e9b6f2667d3b2d4f9946 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -111,6 +111,8 @@ struct nvmet_fc_tgtport { struct nvmet_fc_port_entry *pe; struct kref ref; u32 max_sg_cnt; + + struct work_struct put_work; }; struct nvmet_fc_port_entry { @@ -165,7 +167,7 @@ struct nvmet_fc_tgt_assoc { struct nvmet_fc_hostport *hostport; struct nvmet_fc_ls_iod *rcv_disconn; struct list_head a_list; - struct nvmet_fc_tgt_queue __rcu *queues[NVMET_NR_QUEUES + 1]; + struct nvmet_fc_tgt_queue *queues[NVMET_NR_QUEUES + 1]; struct kref ref; struct work_struct del_work; struct rcu_head rcu; @@ -248,6 +250,13 @@ static int nvmet_fc_tgt_a_get(struct nvmet_fc_tgt_assoc *assoc); static void nvmet_fc_tgt_q_put(struct nvmet_fc_tgt_queue *queue); static int nvmet_fc_tgt_q_get(struct nvmet_fc_tgt_queue *queue); static void nvmet_fc_tgtport_put(struct nvmet_fc_tgtport *tgtport); +static void nvmet_fc_put_tgtport_work(struct work_struct *work) +{ + struct nvmet_fc_tgtport *tgtport = + container_of(work, struct nvmet_fc_tgtport, put_work); + + nvmet_fc_tgtport_put(tgtport); +} static int nvmet_fc_tgtport_get(struct nvmet_fc_tgtport *tgtport); static void nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport, struct nvmet_fc_fcp_iod *fod); @@ -359,7 +368,7 @@ __nvmet_fc_finish_ls_req(struct nvmet_fc_ls_req_op *lsop) if (!lsop->req_queued) { spin_unlock_irqrestore(&tgtport->lock, flags); - return; + goto out_putwork; } list_del(&lsop->lsreq_list); @@ -372,7 +381,8 @@ __nvmet_fc_finish_ls_req(struct nvmet_fc_ls_req_op *lsop) (lsreq->rqstlen + lsreq->rsplen), DMA_BIDIRECTIONAL); - nvmet_fc_tgtport_put(tgtport); +out_putwork: + queue_work(nvmet_wq, &tgtport->put_work); } static int @@ -801,14 +811,11 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc, if (!queue) return NULL; - if (!nvmet_fc_tgt_a_get(assoc)) - goto out_free_queue; - queue->work_q = alloc_workqueue("ntfc%d.%d.%d", 0, 0, assoc->tgtport->fc_target_port.port_num, assoc->a_id, qid); if (!queue->work_q) - goto out_a_put; + goto out_free_queue; queue->qid = qid; queue->sqsize = sqsize; @@ -830,15 +837,13 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc, goto out_fail_iodlist; WARN_ON(assoc->queues[qid]); - rcu_assign_pointer(assoc->queues[qid], queue); + assoc->queues[qid] = queue; return queue; out_fail_iodlist: nvmet_fc_destroy_fcp_iodlist(assoc->tgtport, queue); destroy_workqueue(queue->work_q); -out_a_put: - nvmet_fc_tgt_a_put(assoc); out_free_queue: kfree(queue); return NULL; @@ -851,12 +856,8 @@ nvmet_fc_tgt_queue_free(struct kref *ref) struct nvmet_fc_tgt_queue *queue = container_of(ref, struct nvmet_fc_tgt_queue, ref); - rcu_assign_pointer(queue->assoc->queues[queue->qid], NULL); - nvmet_fc_destroy_fcp_iodlist(queue->assoc->tgtport, queue); - nvmet_fc_tgt_a_put(queue->assoc); - destroy_workqueue(queue->work_q); kfree_rcu(queue, rcu); @@ -968,7 +969,7 @@ nvmet_fc_find_target_queue(struct nvmet_fc_tgtport *tgtport, rcu_read_lock(); list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) { if (association_id == assoc->association_id) { - queue = rcu_dereference(assoc->queues[qid]); + queue = assoc->queues[qid]; if (queue && (!atomic_read(&queue->connected) || !nvmet_fc_tgt_q_get(queue))) @@ -1077,8 +1078,6 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle) /* new allocation not needed */ kfree(newhost); newhost = match; - /* no new allocation - release reference */ - nvmet_fc_tgtport_put(tgtport); } else { newhost->tgtport = tgtport; newhost->hosthandle = hosthandle; @@ -1093,13 +1092,28 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle) } static void -nvmet_fc_delete_assoc(struct work_struct *work) +nvmet_fc_delete_assoc(struct nvmet_fc_tgt_assoc *assoc) +{ + nvmet_fc_delete_target_assoc(assoc); + nvmet_fc_tgt_a_put(assoc); +} + +static void +nvmet_fc_delete_assoc_work(struct work_struct *work) { struct nvmet_fc_tgt_assoc *assoc = container_of(work, struct nvmet_fc_tgt_assoc, del_work); + struct nvmet_fc_tgtport *tgtport = assoc->tgtport; - nvmet_fc_delete_target_assoc(assoc); - nvmet_fc_tgt_a_put(assoc); + nvmet_fc_delete_assoc(assoc); + nvmet_fc_tgtport_put(tgtport); +} + +static void +nvmet_fc_schedule_delete_assoc(struct nvmet_fc_tgt_assoc *assoc) +{ + nvmet_fc_tgtport_get(assoc->tgtport); + queue_work(nvmet_wq, &assoc->del_work); } static struct nvmet_fc_tgt_assoc * @@ -1111,6 +1125,9 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle) int idx; bool needrandom = true; + if (!tgtport->pe) + return NULL; + assoc = kzalloc(sizeof(*assoc), GFP_KERNEL); if (!assoc) return NULL; @@ -1130,7 +1147,7 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle) assoc->a_id = idx; INIT_LIST_HEAD(&assoc->a_list); kref_init(&assoc->ref); - INIT_WORK(&assoc->del_work, nvmet_fc_delete_assoc); + INIT_WORK(&assoc->del_work, nvmet_fc_delete_assoc_work); atomic_set(&assoc->terminating, 0); while (needrandom) { @@ -1171,13 +1188,18 @@ nvmet_fc_target_assoc_free(struct kref *ref) struct nvmet_fc_tgtport *tgtport = assoc->tgtport; struct nvmet_fc_ls_iod *oldls; unsigned long flags; + int i; + + for (i = NVMET_NR_QUEUES; i >= 0; i--) { + if (assoc->queues[i]) + nvmet_fc_delete_target_queue(assoc->queues[i]); + } /* Send Disconnect now that all i/o has completed */ nvmet_fc_xmt_disconnect_assoc(assoc); nvmet_fc_free_hostport(assoc->hostport); spin_lock_irqsave(&tgtport->lock, flags); - list_del_rcu(&assoc->a_list); oldls = assoc->rcv_disconn; spin_unlock_irqrestore(&tgtport->lock, flags); /* if pending Rcv Disconnect Association LS, send rsp now */ @@ -1207,7 +1229,7 @@ static void nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc) { struct nvmet_fc_tgtport *tgtport = assoc->tgtport; - struct nvmet_fc_tgt_queue *queue; + unsigned long flags; int i, terminating; terminating = atomic_xchg(&assoc->terminating, 1); @@ -1216,29 +1238,21 @@ nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc) if (terminating) return; + spin_lock_irqsave(&tgtport->lock, flags); + list_del_rcu(&assoc->a_list); + spin_unlock_irqrestore(&tgtport->lock, flags); - for (i = NVMET_NR_QUEUES; i >= 0; i--) { - rcu_read_lock(); - queue = rcu_dereference(assoc->queues[i]); - if (!queue) { - rcu_read_unlock(); - continue; - } + synchronize_rcu(); - if (!nvmet_fc_tgt_q_get(queue)) { - rcu_read_unlock(); - continue; - } - rcu_read_unlock(); - nvmet_fc_delete_target_queue(queue); - nvmet_fc_tgt_q_put(queue); + /* ensure all in-flight I/Os have been processed */ + for (i = NVMET_NR_QUEUES; i >= 0; i--) { + if (assoc->queues[i]) + flush_workqueue(assoc->queues[i]->work_q); } dev_info(tgtport->dev, "{%d:%d} Association deleted\n", tgtport->fc_target_port.port_num, assoc->a_id); - - nvmet_fc_tgt_a_put(assoc); } static struct nvmet_fc_tgt_assoc * @@ -1414,6 +1428,7 @@ nvmet_fc_register_targetport(struct nvmet_fc_port_info *pinfo, kref_init(&newrec->ref); ida_init(&newrec->assoc_cnt); newrec->max_sg_cnt = template->max_sgl_segments; + INIT_WORK(&newrec->put_work, nvmet_fc_put_tgtport_work); ret = nvmet_fc_alloc_ls_iodlist(newrec); if (ret) { @@ -1491,9 +1506,8 @@ __nvmet_fc_free_assocs(struct nvmet_fc_tgtport *tgtport) list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) { if (!nvmet_fc_tgt_a_get(assoc)) continue; - if (!queue_work(nvmet_wq, &assoc->del_work)) - /* already deleting - release local reference */ - nvmet_fc_tgt_a_put(assoc); + nvmet_fc_schedule_delete_assoc(assoc); + nvmet_fc_tgt_a_put(assoc); } rcu_read_unlock(); } @@ -1546,9 +1560,8 @@ nvmet_fc_invalidate_host(struct nvmet_fc_target_port *target_port, continue; assoc->hostport->invalid = 1; noassoc = false; - if (!queue_work(nvmet_wq, &assoc->del_work)) - /* already deleting - release local reference */ - nvmet_fc_tgt_a_put(assoc); + nvmet_fc_schedule_delete_assoc(assoc); + nvmet_fc_tgt_a_put(assoc); } spin_unlock_irqrestore(&tgtport->lock, flags); @@ -1580,7 +1593,7 @@ nvmet_fc_delete_ctrl(struct nvmet_ctrl *ctrl) rcu_read_lock(); list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) { - queue = rcu_dereference(assoc->queues[0]); + queue = assoc->queues[0]; if (queue && queue->nvme_sq.ctrl == ctrl) { if (nvmet_fc_tgt_a_get(assoc)) found_ctrl = true; @@ -1592,9 +1605,8 @@ nvmet_fc_delete_ctrl(struct nvmet_ctrl *ctrl) nvmet_fc_tgtport_put(tgtport); if (found_ctrl) { - if (!queue_work(nvmet_wq, &assoc->del_work)) - /* already deleting - release local reference */ - nvmet_fc_tgt_a_put(assoc); + nvmet_fc_schedule_delete_assoc(assoc); + nvmet_fc_tgt_a_put(assoc); return; } @@ -1624,6 +1636,8 @@ nvmet_fc_unregister_targetport(struct nvmet_fc_target_port *target_port) /* terminate any outstanding associations */ __nvmet_fc_free_assocs(tgtport); + flush_workqueue(nvmet_wq); + /* * should terminate LS's as well. However, LS's will be generated * at the tail end of association termination, so they likely don't @@ -1869,9 +1883,6 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, sizeof(struct fcnvme_ls_disconnect_assoc_acc)), FCNVME_LS_DISCONNECT_ASSOC); - /* release get taken in nvmet_fc_find_target_assoc */ - nvmet_fc_tgt_a_put(assoc); - /* * The rules for LS response says the response cannot * go back until ABTS's have been sent for all outstanding @@ -1886,8 +1897,6 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, assoc->rcv_disconn = iod; spin_unlock_irqrestore(&tgtport->lock, flags); - nvmet_fc_delete_target_assoc(assoc); - if (oldls) { dev_info(tgtport->dev, "{%d:%d} Multiple Disconnect Association LS's " @@ -1903,6 +1912,9 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, nvmet_fc_xmt_ls_rsp(tgtport, oldls); } + nvmet_fc_schedule_delete_assoc(assoc); + nvmet_fc_tgt_a_put(assoc); + return false; } @@ -2539,8 +2551,9 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport, fod->req.cmd = &fod->cmdiubuf.sqe; fod->req.cqe = &fod->rspiubuf.cqe; - if (tgtport->pe) - fod->req.port = tgtport->pe->port; + if (!tgtport->pe) + goto transport_error; + fod->req.port = tgtport->pe->port; /* clear any response payload */ memset(&fod->rspiubuf, 0, sizeof(fod->rspiubuf)); @@ -2901,6 +2914,9 @@ nvmet_fc_remove_port(struct nvmet_port *port) nvmet_fc_portentry_unbind(pe); + /* terminate any outstanding associations */ + __nvmet_fc_free_assocs(pe->tgtport); + kfree(pe); } @@ -2932,6 +2948,9 @@ static int __init nvmet_fc_init_module(void) static void __exit nvmet_fc_exit_module(void) { + /* ensure any shutdown operation, e.g. delete ctrls have finished */ + flush_workqueue(nvmet_wq); + /* sanity check - all lports should be removed */ if (!list_empty(&nvmet_fc_target_list)) pr_warn("%s: targetport list not empty\n", __func__); diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index c780af36c1d4a5ac90ed20150d31d65e5a8f0f41..f5b8442b653db79f3ec45311e88fe1cfc6409339 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -358,7 +358,7 @@ fcloop_h2t_ls_req(struct nvme_fc_local_port *localport, if (!rport->targetport) { tls_req->status = -ECONNREFUSED; spin_lock(&rport->lock); - list_add_tail(&rport->ls_list, &tls_req->ls_list); + list_add_tail(&tls_req->ls_list, &rport->ls_list); spin_unlock(&rport->lock); queue_work(nvmet_wq, &rport->ls_work); return ret; @@ -391,7 +391,7 @@ fcloop_h2t_xmt_ls_rsp(struct nvmet_fc_target_port *targetport, if (remoteport) { rport = remoteport->private; spin_lock(&rport->lock); - list_add_tail(&rport->ls_list, &tls_req->ls_list); + list_add_tail(&tls_req->ls_list, &rport->ls_list); spin_unlock(&rport->lock); queue_work(nvmet_wq, &rport->ls_work); } @@ -446,7 +446,7 @@ fcloop_t2h_ls_req(struct nvmet_fc_target_port *targetport, void *hosthandle, if (!tport->remoteport) { tls_req->status = -ECONNREFUSED; spin_lock(&tport->lock); - list_add_tail(&tport->ls_list, &tls_req->ls_list); + list_add_tail(&tls_req->ls_list, &tport->ls_list); spin_unlock(&tport->lock); queue_work(nvmet_wq, &tport->ls_work); return ret; diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index adc0958755d66f738f41fc588e2c359f0949bf69..a0a292d49588cbbb023d01bbbbceb2fb4e2f5b5e 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -216,6 +216,7 @@ static void nvmet_passthru_execute_cmd_work(struct work_struct *w) struct nvmet_req *req = container_of(w, struct nvmet_req, p.work); struct request *rq = req->p.rq; struct nvme_ctrl *ctrl = nvme_req(rq)->ctrl; + struct nvme_ns *ns = rq->q->queuedata; u32 effects; int status; @@ -242,7 +243,7 @@ static void nvmet_passthru_execute_cmd_work(struct work_struct *w) blk_mq_free_request(rq); if (effects) - nvme_passthru_end(ctrl, effects, req->cmd, status); + nvme_passthru_end(ctrl, ns, effects, req->cmd, status); } static enum rq_end_io_ret nvmet_passthru_req_done(struct request *rq, diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index ce42afe8f64efa7f533497fe82c016266709b459..3480768274699796d3d7d904000914167aa4a6c2 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -1884,6 +1884,7 @@ static void __exit nvmet_tcp_exit(void) flush_workqueue(nvmet_wq); destroy_workqueue(nvmet_tcp_wq); + ida_destroy(&nvmet_tcp_queue_ida); } module_init(nvmet_tcp_init); diff --git a/drivers/nvmem/meson-efuse.c b/drivers/nvmem/meson-efuse.c index d6b533497ce1a5334acd6c647e1d87c15cc579af..ba2714bef8d0e32826b07e4b17599709267ffaf5 100644 --- a/drivers/nvmem/meson-efuse.c +++ b/drivers/nvmem/meson-efuse.c @@ -47,7 +47,6 @@ static int meson_efuse_probe(struct platform_device *pdev) struct nvmem_config *econfig; struct clk *clk; unsigned int size; - int ret; sm_np = of_parse_phandle(pdev->dev.of_node, "secure-monitor", 0); if (!sm_np) { @@ -60,27 +59,9 @@ static int meson_efuse_probe(struct platform_device *pdev) if (!fw) return -EPROBE_DEFER; - clk = devm_clk_get(dev, NULL); - if (IS_ERR(clk)) { - ret = PTR_ERR(clk); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to get efuse gate"); - return ret; - } - - ret = clk_prepare_enable(clk); - if (ret) { - dev_err(dev, "failed to enable gate"); - return ret; - } - - ret = devm_add_action_or_reset(dev, - (void(*)(void *))clk_disable_unprepare, - clk); - if (ret) { - dev_err(dev, "failed to add disable callback"); - return ret; - } + clk = devm_clk_get_enabled(dev, NULL); + if (IS_ERR(clk)) + return dev_err_probe(dev, PTR_ERR(clk), "failed to get efuse gate"); if (meson_sm_call(fw, SM_EFUSE_USER_MAX, &size, 0, 0, 0, 0, 0) < 0) { dev_err(dev, "failed to get max user"); diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c index 9bb9fe0fad07ced1cffa8739d1c7d5243117fb89..e2a9651014c6e16f0c519d605818ad1932247d61 100644 --- a/drivers/of/dynamic.c +++ b/drivers/of/dynamic.c @@ -9,6 +9,7 @@ #define pr_fmt(fmt) "OF: " fmt +#include #include #include #include @@ -679,6 +680,17 @@ void of_changeset_destroy(struct of_changeset *ocs) { struct of_changeset_entry *ce, *cen; + /* + * When a device is deleted, the device links to/from it are also queued + * for deletion. Until these device links are freed, the devices + * themselves aren't freed. If the device being deleted is due to an + * overlay change, this device might be holding a reference to a device + * node that will be freed. So, wait until all already pending device + * links are deleted before freeing a device node. This ensures we don't + * free any device node that has a non-zero reference count. + */ + device_link_wait_removal(); + list_for_each_entry_safe_reverse(ce, cen, &ocs->entries, node) __of_changeset_entry_destroy(ce); } diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c index cab8623d30b56d1da10ee43eed0749aeafad0205..2377a583b9b77b7b4c11583f94bf606da395c880 100644 --- a/drivers/of/overlay.c +++ b/drivers/of/overlay.c @@ -45,8 +45,8 @@ struct target { /** * struct fragment - info about fragment nodes in overlay expanded device tree - * @target: target of the overlay operation * @overlay: pointer to the __overlay__ node + * @target: target of the overlay operation */ struct fragment { struct device_node *overlay; diff --git a/drivers/of/property.c b/drivers/of/property.c index b636777e6f7c8b95b9018d34949d04f78021e0eb..da5d7121977049ddbee9d05ac1d0fc8834989127 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -762,7 +762,9 @@ struct device_node *of_graph_get_port_parent(struct device_node *node) /* Walk 3 levels up only if there is 'ports' node. */ for (depth = 3; depth && node; depth--) { node = of_get_next_parent(node); - if (depth == 2 && !of_node_name_eq(node, "ports")) + if (depth == 2 && !of_node_name_eq(node, "ports") && + !of_node_name_eq(node, "in-ports") && + !of_node_name_eq(node, "out-ports")) break; } return node; @@ -1243,7 +1245,7 @@ DEFINE_SIMPLE_PROP(clocks, "clocks", "#clock-cells") DEFINE_SIMPLE_PROP(interconnects, "interconnects", "#interconnect-cells") DEFINE_SIMPLE_PROP(iommus, "iommus", "#iommu-cells") DEFINE_SIMPLE_PROP(mboxes, "mboxes", "#mbox-cells") -DEFINE_SIMPLE_PROP(io_channels, "io-channel", "#io-channel-cells") +DEFINE_SIMPLE_PROP(io_channels, "io-channels", "#io-channel-cells") DEFINE_SIMPLE_PROP(interrupt_parent, "interrupt-parent", NULL) DEFINE_SIMPLE_PROP(dmas, "dmas", "#dma-cells") DEFINE_SIMPLE_PROP(power_domains, "power-domains", "#power-domain-cells") @@ -1261,7 +1263,6 @@ DEFINE_SIMPLE_PROP(pinctrl5, "pinctrl-5", NULL) DEFINE_SIMPLE_PROP(pinctrl6, "pinctrl-6", NULL) DEFINE_SIMPLE_PROP(pinctrl7, "pinctrl-7", NULL) DEFINE_SIMPLE_PROP(pinctrl8, "pinctrl-8", NULL) -DEFINE_SIMPLE_PROP(remote_endpoint, "remote-endpoint", NULL) DEFINE_SIMPLE_PROP(pwms, "pwms", "#pwm-cells") DEFINE_SIMPLE_PROP(resets, "resets", "#reset-cells") DEFINE_SIMPLE_PROP(leds, "leds", NULL) @@ -1326,6 +1327,17 @@ static struct device_node *parse_interrupts(struct device_node *np, return of_irq_parse_one(np, index, &sup_args) ? NULL : sup_args.np; } +static struct device_node *parse_remote_endpoint(struct device_node *np, + const char *prop_name, + int index) +{ + /* Return NULL for index > 0 to signify end of remote-endpoints. */ + if (index > 0 || strcmp(prop_name, "remote-endpoint")) + return NULL; + + return of_graph_get_remote_port_parent(np); +} + static const struct supplier_bindings of_supplier_bindings[] = { { .parse_prop = parse_clocks, }, { .parse_prop = parse_interconnects, }, diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index e541a8960f1de0767c77d9ce83d2e9b231d4a49e..ce1386074e66b0ed9a4a514f2a5e80ab1bbb8972 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -49,6 +49,12 @@ static struct unittest_results { failed; \ }) +#ifdef CONFIG_OF_KOBJ +#define OF_KREF_READ(NODE) kref_read(&(NODE)->kobj.kref) +#else +#define OF_KREF_READ(NODE) 1 +#endif + /* * Expected message may have a message level other than KERN_INFO. * Print the expected message only if the current loglevel will allow @@ -562,7 +568,7 @@ static void __init of_unittest_parse_phandle_with_args_map(void) pr_err("missing testcase data\n"); return; } - prefs[i] = kref_read(&p[i]->kobj.kref); + prefs[i] = OF_KREF_READ(p[i]); } rc = of_count_phandle_with_args(np, "phandle-list", "#phandle-cells"); @@ -685,9 +691,9 @@ static void __init of_unittest_parse_phandle_with_args_map(void) unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); for (i = 0; i < ARRAY_SIZE(p); ++i) { - unittest(prefs[i] == kref_read(&p[i]->kobj.kref), + unittest(prefs[i] == OF_KREF_READ(p[i]), "provider%d: expected:%d got:%d\n", - i, prefs[i], kref_read(&p[i]->kobj.kref)); + i, prefs[i], OF_KREF_READ(p[i])); of_node_put(p[i]); } } diff --git a/drivers/opp/debugfs.c b/drivers/opp/debugfs.c index 2c7fb683441effcc7ceedc50296c8a53c8b59f14..de81bbf4be100d42e3451eb3ffd08e11918f2972 100644 --- a/drivers/opp/debugfs.c +++ b/drivers/opp/debugfs.c @@ -37,10 +37,12 @@ static ssize_t bw_name_read(struct file *fp, char __user *userbuf, size_t count, loff_t *ppos) { struct icc_path *path = fp->private_data; + const char *name = icc_get_name(path); char buf[64]; - int i; + int i = 0; - i = scnprintf(buf, sizeof(buf), "%.62s\n", icc_get_name(path)); + if (name) + i = scnprintf(buf, sizeof(buf), "%.62s\n", name); return simple_read_from_buffer(userbuf, count, ppos, buf, i); } diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index feafa378bf8ea1cd547dba104edc1365a46afd3b..aa2fba1c0f5671b4d3bf8d12e8570a4f4513a6ce 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -379,21 +379,8 @@ void pci_bus_add_devices(const struct pci_bus *bus) } EXPORT_SYMBOL(pci_bus_add_devices); -/** pci_walk_bus - walk devices on/under bus, calling callback. - * @top bus whose devices should be walked - * @cb callback to be called for each device found - * @userdata arbitrary pointer to be passed to callback. - * - * Walk the given bus, including any bridged devices - * on buses under this bus. Call the provided callback - * on each device found. - * - * We check the return of @cb each time. If it returns anything - * other than 0, we break out. - * - */ -void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), - void *userdata) +static void __pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), + void *userdata, bool locked) { struct pci_dev *dev; struct pci_bus *bus; @@ -401,7 +388,8 @@ void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), int retval; bus = top; - down_read(&pci_bus_sem); + if (!locked) + down_read(&pci_bus_sem); next = top->devices.next; for (;;) { if (next == &bus->devices) { @@ -424,10 +412,37 @@ void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), if (retval) break; } - up_read(&pci_bus_sem); + if (!locked) + up_read(&pci_bus_sem); +} + +/** + * pci_walk_bus - walk devices on/under bus, calling callback. + * @top: bus whose devices should be walked + * @cb: callback to be called for each device found + * @userdata: arbitrary pointer to be passed to callback + * + * Walk the given bus, including any bridged devices + * on buses under this bus. Call the provided callback + * on each device found. + * + * We check the return of @cb each time. If it returns anything + * other than 0, we break out. + */ +void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata) +{ + __pci_walk_bus(top, cb, userdata, false); } EXPORT_SYMBOL_GPL(pci_walk_bus); +void pci_walk_bus_locked(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata) +{ + lockdep_assert_held(&pci_bus_sem); + + __pci_walk_bus(top, cb, userdata, true); +} +EXPORT_SYMBOL_GPL(pci_walk_bus_locked); + struct pci_bus *pci_bus_get(struct pci_bus *bus) { if (bus) diff --git a/drivers/pci/controller/dwc/pci-layerscape-ep.c b/drivers/pci/controller/dwc/pci-layerscape-ep.c index ad99707b3b994f26da992e6ecb736518f2ae6553..dd7d74fecc48e1085d08466fe1b6ae825a61482b 100644 --- a/drivers/pci/controller/dwc/pci-layerscape-ep.c +++ b/drivers/pci/controller/dwc/pci-layerscape-ep.c @@ -18,6 +18,20 @@ #include "pcie-designware.h" +#define PEX_PF0_CONFIG 0xC0014 +#define PEX_PF0_CFG_READY BIT(0) + +/* PEX PFa PCIE PME and message interrupt registers*/ +#define PEX_PF0_PME_MES_DR 0xC0020 +#define PEX_PF0_PME_MES_DR_LUD BIT(7) +#define PEX_PF0_PME_MES_DR_LDD BIT(9) +#define PEX_PF0_PME_MES_DR_HRD BIT(10) + +#define PEX_PF0_PME_MES_IER 0xC0028 +#define PEX_PF0_PME_MES_IER_LUDIE BIT(7) +#define PEX_PF0_PME_MES_IER_LDDIE BIT(9) +#define PEX_PF0_PME_MES_IER_HRDIE BIT(10) + #define to_ls_pcie_ep(x) dev_get_drvdata((x)->dev) struct ls_pcie_ep_drvdata { @@ -30,8 +44,99 @@ struct ls_pcie_ep { struct dw_pcie *pci; struct pci_epc_features *ls_epc; const struct ls_pcie_ep_drvdata *drvdata; + int irq; + u32 lnkcap; + bool big_endian; }; +static u32 ls_lut_readl(struct ls_pcie_ep *pcie, u32 offset) +{ + struct dw_pcie *pci = pcie->pci; + + if (pcie->big_endian) + return ioread32be(pci->dbi_base + offset); + else + return ioread32(pci->dbi_base + offset); +} + +static void ls_lut_writel(struct ls_pcie_ep *pcie, u32 offset, u32 value) +{ + struct dw_pcie *pci = pcie->pci; + + if (pcie->big_endian) + iowrite32be(value, pci->dbi_base + offset); + else + iowrite32(value, pci->dbi_base + offset); +} + +static irqreturn_t ls_pcie_ep_event_handler(int irq, void *dev_id) +{ + struct ls_pcie_ep *pcie = dev_id; + struct dw_pcie *pci = pcie->pci; + u32 val, cfg; + u8 offset; + + val = ls_lut_readl(pcie, PEX_PF0_PME_MES_DR); + ls_lut_writel(pcie, PEX_PF0_PME_MES_DR, val); + + if (!val) + return IRQ_NONE; + + if (val & PEX_PF0_PME_MES_DR_LUD) { + + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + + /* + * The values of the Maximum Link Width and Supported Link + * Speed from the Link Capabilities Register will be lost + * during link down or hot reset. Restore initial value + * that configured by the Reset Configuration Word (RCW). + */ + dw_pcie_dbi_ro_wr_en(pci); + dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCAP, pcie->lnkcap); + dw_pcie_dbi_ro_wr_dis(pci); + + cfg = ls_lut_readl(pcie, PEX_PF0_CONFIG); + cfg |= PEX_PF0_CFG_READY; + ls_lut_writel(pcie, PEX_PF0_CONFIG, cfg); + dw_pcie_ep_linkup(&pci->ep); + + dev_dbg(pci->dev, "Link up\n"); + } else if (val & PEX_PF0_PME_MES_DR_LDD) { + dev_dbg(pci->dev, "Link down\n"); + } else if (val & PEX_PF0_PME_MES_DR_HRD) { + dev_dbg(pci->dev, "Hot reset\n"); + } + + return IRQ_HANDLED; +} + +static int ls_pcie_ep_interrupt_init(struct ls_pcie_ep *pcie, + struct platform_device *pdev) +{ + u32 val; + int ret; + + pcie->irq = platform_get_irq_byname(pdev, "pme"); + if (pcie->irq < 0) + return pcie->irq; + + ret = devm_request_irq(&pdev->dev, pcie->irq, ls_pcie_ep_event_handler, + IRQF_SHARED, pdev->name, pcie); + if (ret) { + dev_err(&pdev->dev, "Can't register PCIe IRQ\n"); + return ret; + } + + /* Enable interrupts */ + val = ls_lut_readl(pcie, PEX_PF0_PME_MES_IER); + val |= PEX_PF0_PME_MES_IER_LDDIE | PEX_PF0_PME_MES_IER_HRDIE | + PEX_PF0_PME_MES_IER_LUDIE; + ls_lut_writel(pcie, PEX_PF0_PME_MES_IER, val); + + return 0; +} + static const struct pci_epc_features* ls_pcie_ep_get_features(struct dw_pcie_ep *ep) { @@ -124,6 +229,8 @@ static int __init ls_pcie_ep_probe(struct platform_device *pdev) struct ls_pcie_ep *pcie; struct pci_epc_features *ls_epc; struct resource *dbi_base; + u8 offset; + int ret; pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); if (!pcie) @@ -143,6 +250,7 @@ static int __init ls_pcie_ep_probe(struct platform_device *pdev) pci->ops = pcie->drvdata->dw_pcie_ops; ls_epc->bar_fixed_64bit = (1 << BAR_2) | (1 << BAR_4); + ls_epc->linkup_notifier = true; pcie->pci = pci; pcie->ls_epc = ls_epc; @@ -154,9 +262,18 @@ static int __init ls_pcie_ep_probe(struct platform_device *pdev) pci->ep.ops = &ls_pcie_ep_ops; + pcie->big_endian = of_property_read_bool(dev->of_node, "big-endian"); + platform_set_drvdata(pdev, pcie); - return dw_pcie_ep_init(&pci->ep); + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + pcie->lnkcap = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP); + + ret = dw_pcie_ep_init(&pci->ep); + if (ret) + return ret; + + return ls_pcie_ep_interrupt_init(pcie, pdev); } static struct platform_driver ls_pcie_ep_driver = { diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index 59c164b5c64aa8289b5545c070f3020fa30a3e7e..506d6d061d4cd64c463c178c7786f9703b86a510 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -6,6 +6,7 @@ * Author: Kishon Vijay Abraham I */ +#include #include #include @@ -600,7 +601,7 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, } aligned_offset = msg_addr & (epc->mem->window.page_size - 1); - msg_addr &= ~aligned_offset; + msg_addr = ALIGN_DOWN(msg_addr, epc->mem->window.page_size); ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr, epc->mem->window.page_size); if (ret) @@ -668,8 +669,13 @@ int dw_pcie_ep_init_complete(struct dw_pcie_ep *ep) nbars = (reg & PCI_REBAR_CTRL_NBAR_MASK) >> PCI_REBAR_CTRL_NBAR_SHIFT; + /* + * PCIe r6.0, sec 7.8.6.2 require us to support at least one + * size in the range from 1 MB to 512 GB. Advertise support + * for 1 MB BAR size only. + */ for (i = 0; i < nbars; i++, offset += PCI_REBAR_CTRL) - dw_pcie_writel_dbi(pci, offset + PCI_REBAR_CAP, 0x0); + dw_pcie_writel_dbi(pci, offset + PCI_REBAR_CAP, BIT(4)); } dw_pcie_setup(pci); diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index 0ccd92faf078ad5cc54038e4d85d77db42e0d403..0bad23ec53ee86be51a2c13618f70e8abf30522d 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -50,6 +50,7 @@ #define PARF_SLV_ADDR_SPACE_SIZE 0x358 #define PARF_DEVICE_TYPE 0x1000 #define PARF_BDF_TO_SID_TABLE_N 0x2000 +#define PARF_BDF_TO_SID_CFG 0x2c00 /* ELBI registers */ #define ELBI_SYS_CTRL 0x04 @@ -102,6 +103,9 @@ /* PARF_DEVICE_TYPE register fields */ #define DEVICE_TYPE_RC 0x4 +/* PARF_BDF_TO_SID_CFG fields */ +#define BDF_TO_SID_BYPASS BIT(0) + /* ELBI_SYS_CTRL register fields */ #define ELBI_SYS_CTRL_LT_ENABLE BIT(0) @@ -1312,6 +1316,82 @@ static void qcom_pcie_deinit_2_7_0(struct qcom_pcie *pcie) regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies); } +static int qcom_pcie_config_sid_1_9_0(struct qcom_pcie *pcie) +{ + /* iommu map structure */ + struct { + u32 bdf; + u32 phandle; + u32 smmu_sid; + u32 smmu_sid_len; + } *map; + void __iomem *bdf_to_sid_base = pcie->parf + PARF_BDF_TO_SID_TABLE_N; + struct device *dev = pcie->pci->dev; + u8 qcom_pcie_crc8_table[CRC8_TABLE_SIZE]; + int i, nr_map, size = 0; + u32 smmu_sid_base; + u32 val; + + of_get_property(dev->of_node, "iommu-map", &size); + if (!size) + return 0; + + /* Enable BDF to SID translation by disabling bypass mode (default) */ + val = readl(pcie->parf + PARF_BDF_TO_SID_CFG); + val &= ~BDF_TO_SID_BYPASS; + writel(val, pcie->parf + PARF_BDF_TO_SID_CFG); + + map = kzalloc(size, GFP_KERNEL); + if (!map) + return -ENOMEM; + + of_property_read_u32_array(dev->of_node, "iommu-map", (u32 *)map, + size / sizeof(u32)); + + nr_map = size / (sizeof(*map)); + + crc8_populate_msb(qcom_pcie_crc8_table, QCOM_PCIE_CRC8_POLYNOMIAL); + + /* Registers need to be zero out first */ + memset_io(bdf_to_sid_base, 0, CRC8_TABLE_SIZE * sizeof(u32)); + + /* Extract the SMMU SID base from the first entry of iommu-map */ + smmu_sid_base = map[0].smmu_sid; + + /* Look for an available entry to hold the mapping */ + for (i = 0; i < nr_map; i++) { + __be16 bdf_be = cpu_to_be16(map[i].bdf); + u32 val; + u8 hash; + + hash = crc8(qcom_pcie_crc8_table, (u8 *)&bdf_be, sizeof(bdf_be), 0); + + val = readl(bdf_to_sid_base + hash * sizeof(u32)); + + /* If the register is already populated, look for next available entry */ + while (val) { + u8 current_hash = hash++; + u8 next_mask = 0xff; + + /* If NEXT field is NULL then update it with next hash */ + if (!(val & next_mask)) { + val |= (u32)hash; + writel(val, bdf_to_sid_base + current_hash * sizeof(u32)); + } + + val = readl(bdf_to_sid_base + hash * sizeof(u32)); + } + + /* BDF [31:16] | SID [15:8] | NEXT [7:0] */ + val = map[i].bdf << 16 | (map[i].smmu_sid - smmu_sid_base) << 8 | 0; + writel(val, bdf_to_sid_base + hash * sizeof(u32)); + } + + kfree(map); + + return 0; +} + static int qcom_pcie_get_resources_2_9_0(struct qcom_pcie *pcie) { struct qcom_pcie_resources_2_9_0 *res = &pcie->res.v2_9_0; @@ -1429,77 +1509,6 @@ static int qcom_pcie_link_up(struct dw_pcie *pci) return !!(val & PCI_EXP_LNKSTA_DLLLA); } -static int qcom_pcie_config_sid_sm8250(struct qcom_pcie *pcie) -{ - /* iommu map structure */ - struct { - u32 bdf; - u32 phandle; - u32 smmu_sid; - u32 smmu_sid_len; - } *map; - void __iomem *bdf_to_sid_base = pcie->parf + PARF_BDF_TO_SID_TABLE_N; - struct device *dev = pcie->pci->dev; - u8 qcom_pcie_crc8_table[CRC8_TABLE_SIZE]; - int i, nr_map, size = 0; - u32 smmu_sid_base; - - of_get_property(dev->of_node, "iommu-map", &size); - if (!size) - return 0; - - map = kzalloc(size, GFP_KERNEL); - if (!map) - return -ENOMEM; - - of_property_read_u32_array(dev->of_node, - "iommu-map", (u32 *)map, size / sizeof(u32)); - - nr_map = size / (sizeof(*map)); - - crc8_populate_msb(qcom_pcie_crc8_table, QCOM_PCIE_CRC8_POLYNOMIAL); - - /* Registers need to be zero out first */ - memset_io(bdf_to_sid_base, 0, CRC8_TABLE_SIZE * sizeof(u32)); - - /* Extract the SMMU SID base from the first entry of iommu-map */ - smmu_sid_base = map[0].smmu_sid; - - /* Look for an available entry to hold the mapping */ - for (i = 0; i < nr_map; i++) { - __be16 bdf_be = cpu_to_be16(map[i].bdf); - u32 val; - u8 hash; - - hash = crc8(qcom_pcie_crc8_table, (u8 *)&bdf_be, sizeof(bdf_be), - 0); - - val = readl(bdf_to_sid_base + hash * sizeof(u32)); - - /* If the register is already populated, look for next available entry */ - while (val) { - u8 current_hash = hash++; - u8 next_mask = 0xff; - - /* If NEXT field is NULL then update it with next hash */ - if (!(val & next_mask)) { - val |= (u32)hash; - writel(val, bdf_to_sid_base + current_hash * sizeof(u32)); - } - - val = readl(bdf_to_sid_base + hash * sizeof(u32)); - } - - /* BDF [31:16] | SID [15:8] | NEXT [7:0] */ - val = map[i].bdf << 16 | (map[i].smmu_sid - smmu_sid_base) << 8 | 0; - writel(val, bdf_to_sid_base + hash * sizeof(u32)); - } - - kfree(map); - - return 0; -} - static int qcom_pcie_host_init(struct dw_pcie_rp *pp) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); @@ -1616,7 +1625,7 @@ static const struct qcom_pcie_ops ops_1_9_0 = { .init = qcom_pcie_init_2_7_0, .deinit = qcom_pcie_deinit_2_7_0, .ltssm_enable = qcom_pcie_2_3_2_ltssm_enable, - .config_sid = qcom_pcie_config_sid_sm8250, + .config_sid = qcom_pcie_config_sid_1_9_0, }; /* Qcom IP rev.: 2.9.0 Synopsys IP rev.: 5.00a */ diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 9693bab59bf7ce4915e30a329c93edef10d61b1b..b36cbc9136ae1c49d392d61b4237988a1c2a87d1 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -49,6 +49,7 @@ #include #include #include +#include #include /* @@ -465,7 +466,7 @@ struct pci_eject_response { u32 status; } __packed; -static int pci_ring_size = (4 * PAGE_SIZE); +static int pci_ring_size = VMBUS_RING_SIZE(SZ_16K); /* * Driver specific state. diff --git a/drivers/pci/endpoint/functions/pci-epf-vntb.c b/drivers/pci/endpoint/functions/pci-epf-vntb.c index 8c6931210ac4d7c42ab86fb4b4aa308e6905e788..b4c1a4f6029d431769e04881242dd715dffd35ca 100644 --- a/drivers/pci/endpoint/functions/pci-epf-vntb.c +++ b/drivers/pci/endpoint/functions/pci-epf-vntb.c @@ -1281,14 +1281,11 @@ static int pci_vntb_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = ntb_register_device(&ndev->ntb); if (ret) { dev_err(dev, "Failed to register NTB device\n"); - goto err_register_dev; + return ret; } dev_dbg(dev, "PCI Virtual NTB driver loaded\n"); return 0; - -err_register_dev: - return -EINVAL; } static struct pci_device_id pci_vntb_table[] = { diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index e9cf318e6670f7cab5bfa93892295bf0b6d9f4e5..34877a1f43a15abd2ea0e14ebc32dd3549e6ab11 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -60,7 +60,7 @@ static irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc) return (irq_hw_number_t)desc->msi_index | pci_dev_id(dev) << 11 | - (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 27; + ((irq_hw_number_t)(pci_domain_nr(dev->bus) & 0xFFFFFFFF)) << 27; } static inline bool pci_msi_desc_is_multi_msi(struct msi_desc *desc) diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index f47a3b10bf504027f54fa724653ca8376e3434cb..8dda3b205dfd0262be3039b6bc7783009406d192 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -473,6 +473,13 @@ static void pci_device_remove(struct device *dev) if (drv->remove) { pm_runtime_get_sync(dev); + /* + * If the driver provides a .runtime_idle() callback and it has + * started to run already, it may continue to run in parallel + * with the code below, so wait until all of the runtime PM + * activity has completed. + */ + pm_runtime_barrier(dev); drv->remove(pci_dev); pm_runtime_put_noidle(dev); } diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 5368a37154cf972d0f954837e39ac7dc2313f36d..67956bfebf87955045f505488ddbbdb06e404f51 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1258,6 +1258,7 @@ end: /** * pci_set_full_power_state - Put a PCI device into D0 and update its state * @dev: PCI device to power up + * @locked: whether pci_bus_sem is held * * Call pci_power_up() to put @dev into D0, read from its PCI_PM_CTRL register * to confirm the state change, restore its BARs if they might be lost and @@ -1267,7 +1268,7 @@ end: * to D0, it is more efficient to use pci_power_up() directly instead of this * function. */ -static int pci_set_full_power_state(struct pci_dev *dev) +static int pci_set_full_power_state(struct pci_dev *dev, bool locked) { u16 pmcsr; int ret; @@ -1303,7 +1304,7 @@ static int pci_set_full_power_state(struct pci_dev *dev) } if (dev->bus->self) - pcie_aspm_pm_state_change(dev->bus->self); + pcie_aspm_pm_state_change(dev->bus->self, locked); return 0; } @@ -1332,10 +1333,22 @@ void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state) pci_walk_bus(bus, __pci_dev_set_current_state, &state); } +static void __pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state, bool locked) +{ + if (!bus) + return; + + if (locked) + pci_walk_bus_locked(bus, __pci_dev_set_current_state, &state); + else + pci_walk_bus(bus, __pci_dev_set_current_state, &state); +} + /** * pci_set_low_power_state - Put a PCI device into a low-power state. * @dev: PCI device to handle. * @state: PCI power state (D1, D2, D3hot) to put the device into. + * @locked: whether pci_bus_sem is held * * Use the device's PCI_PM_CTRL register to put it into a low-power state. * @@ -1346,7 +1359,7 @@ void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state) * 0 if device already is in the requested state. * 0 if device's power state has been successfully changed. */ -static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state) +static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state, bool locked) { u16 pmcsr; @@ -1400,29 +1413,12 @@ static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state) pci_power_name(state)); if (dev->bus->self) - pcie_aspm_pm_state_change(dev->bus->self); + pcie_aspm_pm_state_change(dev->bus->self, locked); return 0; } -/** - * pci_set_power_state - Set the power state of a PCI device - * @dev: PCI device to handle. - * @state: PCI power state (D0, D1, D2, D3hot) to put the device into. - * - * Transition a device to a new power state, using the platform firmware and/or - * the device's PCI PM registers. - * - * RETURN VALUE: - * -EINVAL if the requested state is invalid. - * -EIO if device does not support PCI PM or its PM capabilities register has a - * wrong version, or device doesn't support the requested state. - * 0 if the transition is to D1 or D2 but D1 and D2 are not supported. - * 0 if device already is in the requested state. - * 0 if the transition is to D3 but D3 is not supported. - * 0 if device's power state has been successfully changed. - */ -int pci_set_power_state(struct pci_dev *dev, pci_power_t state) +static int __pci_set_power_state(struct pci_dev *dev, pci_power_t state, bool locked) { int error; @@ -1446,7 +1442,7 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state) return 0; if (state == PCI_D0) - return pci_set_full_power_state(dev); + return pci_set_full_power_state(dev, locked); /* * This device is quirked not to be put into D3, so don't put it in @@ -1460,16 +1456,16 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state) * To put the device in D3cold, put it into D3hot in the native * way, then put it into D3cold using platform ops. */ - error = pci_set_low_power_state(dev, PCI_D3hot); + error = pci_set_low_power_state(dev, PCI_D3hot, locked); if (pci_platform_power_transition(dev, PCI_D3cold)) return error; /* Powering off a bridge may power off the whole hierarchy */ if (dev->current_state == PCI_D3cold) - pci_bus_set_current_state(dev->subordinate, PCI_D3cold); + __pci_bus_set_current_state(dev->subordinate, PCI_D3cold, locked); } else { - error = pci_set_low_power_state(dev, state); + error = pci_set_low_power_state(dev, state, locked); if (pci_platform_power_transition(dev, state)) return error; @@ -1477,8 +1473,38 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state) return 0; } + +/** + * pci_set_power_state - Set the power state of a PCI device + * @dev: PCI device to handle. + * @state: PCI power state (D0, D1, D2, D3hot) to put the device into. + * + * Transition a device to a new power state, using the platform firmware and/or + * the device's PCI PM registers. + * + * RETURN VALUE: + * -EINVAL if the requested state is invalid. + * -EIO if device does not support PCI PM or its PM capabilities register has a + * wrong version, or device doesn't support the requested state. + * 0 if the transition is to D1 or D2 but D1 and D2 are not supported. + * 0 if device already is in the requested state. + * 0 if the transition is to D3 but D3 is not supported. + * 0 if device's power state has been successfully changed. + */ +int pci_set_power_state(struct pci_dev *dev, pci_power_t state) +{ + return __pci_set_power_state(dev, state, false); +} EXPORT_SYMBOL(pci_set_power_state); +int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state) +{ + lockdep_assert_held(&pci_bus_sem); + + return __pci_set_power_state(dev, state, true); +} +EXPORT_SYMBOL(pci_set_power_state_locked); + #define PCI_EXP_SAVE_REGS 7 static struct pci_cap_saved_state *_pci_find_saved_cap(struct pci_dev *pci_dev, diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index e1d02b7c60294885b75fe8a60428b3b8150923fb..88576a22fecb13028c40a4638de1176d65eb0241 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -357,11 +357,6 @@ static inline int pci_dev_set_disconnected(struct pci_dev *dev, void *unused) return 0; } -static inline bool pci_dev_is_disconnected(const struct pci_dev *dev) -{ - return dev->error_state == pci_channel_io_perm_failure; -} - /* pci_dev priv_flags */ #define PCI_DEV_ADDED 0 #define PCI_DPC_RECOVERED 1 @@ -561,12 +556,12 @@ bool pcie_wait_for_link(struct pci_dev *pdev, bool active); #ifdef CONFIG_PCIEASPM void pcie_aspm_init_link_state(struct pci_dev *pdev); void pcie_aspm_exit_link_state(struct pci_dev *pdev); -void pcie_aspm_pm_state_change(struct pci_dev *pdev); +void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked); void pcie_aspm_powersave_config_link(struct pci_dev *pdev); #else static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { } static inline void pcie_aspm_exit_link_state(struct pci_dev *pdev) { } -static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev) { } +static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked) { } static inline void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { } #endif diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 25736d408e88e54b3117115eb5d84539f8fea002..cf4acea6610d5146c4950e31238084b20bae1863 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -743,10 +743,10 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state) * in pcie_config_aspm_link(). */ if (enable_req & (ASPM_STATE_L1_1 | ASPM_STATE_L1_2)) { - pcie_capability_clear_and_set_word(child, PCI_EXP_LNKCTL, - PCI_EXP_LNKCTL_ASPM_L1, 0); - pcie_capability_clear_and_set_word(parent, PCI_EXP_LNKCTL, - PCI_EXP_LNKCTL_ASPM_L1, 0); + pcie_capability_clear_word(child, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_ASPM_L1); + pcie_capability_clear_word(parent, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_ASPM_L1); } val = 0; @@ -1055,8 +1055,11 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev) up_read(&pci_bus_sem); } -/* @pdev: the root port or switch downstream port */ -void pcie_aspm_pm_state_change(struct pci_dev *pdev) +/* + * @pdev: the root port or switch downstream port + * @locked: whether pci_bus_sem is held + */ +void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked) { struct pcie_link_state *link = pdev->link_state; @@ -1066,12 +1069,14 @@ void pcie_aspm_pm_state_change(struct pci_dev *pdev) * Devices changed PM state, we should recheck if latency * meets all functions' requirement */ - down_read(&pci_bus_sem); + if (!locked) + down_read(&pci_bus_sem); mutex_lock(&aspm_lock); pcie_update_aspm_capable(link->root); pcie_config_aspm_path(link); mutex_unlock(&aspm_lock); - up_read(&pci_bus_sem); + if (!locked) + up_read(&pci_bus_sem); } void pcie_aspm_powersave_config_link(struct pci_dev *pdev) diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c index a5d7c69b764e05654b1dba1bfdd5b46fb9033715..acdbf9e770a8ae565e32640790524034376ed143 100644 --- a/drivers/pci/pcie/dpc.c +++ b/drivers/pci/pcie/dpc.c @@ -9,6 +9,7 @@ #define dev_fmt(fmt) "DPC: " fmt #include +#include #include #include #include @@ -203,7 +204,7 @@ static void dpc_process_rp_pio_error(struct pci_dev *pdev) /* Get First Error Pointer */ pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &dpc_status); - first_error = (dpc_status & 0x1f00) >> 8; + first_error = FIELD_GET(PCI_EXP_DPC_RP_PIO_FEP, dpc_status); for (i = 0; i < ARRAY_SIZE(rp_pio_error_string); i++) { if ((status & ~mask) & (1 << i)) @@ -231,7 +232,7 @@ static void dpc_process_rp_pio_error(struct pci_dev *pdev) for (i = 0; i < pdev->dpc_rp_log_size - 5; i++) { pci_read_config_dword(pdev, - cap + PCI_EXP_DPC_RP_PIO_TLPPREFIX_LOG, &prefix); + cap + PCI_EXP_DPC_RP_PIO_TLPPREFIX_LOG + i * 4, &prefix); pci_err(pdev, "TLP Prefix Header: dw%d, %#010x\n", i, prefix); } clear_status: @@ -339,7 +340,7 @@ void pci_dpc_init(struct pci_dev *pdev) /* Quirks may set dpc_rp_log_size if device or firmware is buggy */ if (!pdev->dpc_rp_log_size) { pdev->dpc_rp_log_size = - (cap & PCI_EXP_DPC_RP_PIO_LOG_SIZE) >> 8; + FIELD_GET(PCI_EXP_DPC_RP_PIO_LOG_SIZE, cap); if (pdev->dpc_rp_log_size < 4 || pdev->dpc_rp_log_size > 9) { pci_err(pdev, "RP PIO log size %u is invalid\n", pdev->dpc_rp_log_size); diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c index 59c90d04a609afbc6f2c485604e8038fbaecddc2..705893b5f7b09babb7ff2b003dd49d74f408f0fe 100644 --- a/drivers/pci/pcie/err.c +++ b/drivers/pci/pcie/err.c @@ -13,6 +13,7 @@ #define dev_fmt(fmt) "AER: " fmt #include +#include #include #include #include @@ -85,6 +86,18 @@ static int report_error_detected(struct pci_dev *dev, return 0; } +static int pci_pm_runtime_get_sync(struct pci_dev *pdev, void *data) +{ + pm_runtime_get_sync(&pdev->dev); + return 0; +} + +static int pci_pm_runtime_put(struct pci_dev *pdev, void *data) +{ + pm_runtime_put(&pdev->dev); + return 0; +} + static int report_frozen_detected(struct pci_dev *dev, void *data) { return report_error_detected(dev, pci_channel_io_frozen, data); @@ -207,6 +220,8 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev, else bridge = pci_upstream_bridge(dev); + pci_walk_bridge(bridge, pci_pm_runtime_get_sync, NULL); + pci_dbg(bridge, "broadcast error_detected message\n"); if (state == pci_channel_io_frozen) { pci_walk_bridge(bridge, report_frozen_detected, &status); @@ -251,10 +266,15 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev, pcie_clear_device_status(dev); pci_aer_clear_nonfatal_status(dev); } + + pci_walk_bridge(bridge, pci_pm_runtime_put, NULL); + pci_info(bridge, "device recovery successful\n"); return status; failed: + pci_walk_bridge(bridge, pci_pm_runtime_put, NULL); + pci_uevent_ers(bridge, PCI_ERS_RESULT_DISCONNECT); /* TODO: Should kernel panic here? */ diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 51d634fbdfb8e42b861c9bd49a2f8fc41e3dff5b..56dce858a69349bf7e8eadb6a944c2ba7143dbd2 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -2425,9 +2425,9 @@ static void quirk_enable_clear_retrain_link(struct pci_dev *dev) dev->clear_retrain_link = 1; pci_info(dev, "Enable PCIe Retrain Link quirk\n"); } -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_PERICOM, 0xe110, quirk_enable_clear_retrain_link); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_PERICOM, 0xe111, quirk_enable_clear_retrain_link); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_PERICOM, 0xe130, quirk_enable_clear_retrain_link); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_PERICOM, 0xe110, quirk_enable_clear_retrain_link); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_PERICOM, 0xe111, quirk_enable_clear_retrain_link); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_PERICOM, 0xe130, quirk_enable_clear_retrain_link); static void fixup_rev1_53c810(struct pci_dev *dev) { @@ -4011,10 +4011,11 @@ static int nvme_disable_and_flr(struct pci_dev *dev, bool probe) } /* - * Intel DC P3700 NVMe controller will timeout waiting for ready status - * to change after NVMe enable if the driver starts interacting with the - * device too soon after FLR. A 250ms delay after FLR has heuristically - * proven to produce reliably working results for device assignment cases. + * Some NVMe controllers such as Intel DC P3700 and Solidigm P44 Pro will + * timeout waiting for ready status to change after NVMe enable if the driver + * starts interacting with the device too soon after FLR. A 250ms delay after + * FLR has heuristically proven to produce reliably working results for device + * assignment cases. */ static int delay_250ms_after_flr(struct pci_dev *dev, bool probe) { @@ -4101,6 +4102,7 @@ static const struct pci_dev_reset_methods pci_dev_reset_methods[] = { { PCI_VENDOR_ID_SAMSUNG, 0xa804, nvme_disable_and_flr }, { PCI_VENDOR_ID_INTEL, 0x0953, delay_250ms_after_flr }, { PCI_VENDOR_ID_INTEL, 0x0a54, delay_250ms_after_flr }, + { PCI_VENDOR_ID_SOLIDIGM, 0xf1ac, delay_250ms_after_flr }, { PCI_VENDOR_ID_CHELSIO, PCI_ANY_ID, reset_chelsio_generic_dev }, { PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_HINIC_VF, @@ -4474,9 +4476,9 @@ static void quirk_disable_root_port_attributes(struct pci_dev *pdev) pci_info(root_port, "Disabling No Snoop/Relaxed Ordering Attributes to avoid PCIe Completion erratum in %s\n", dev_name(&pdev->dev)); - pcie_capability_clear_and_set_word(root_port, PCI_EXP_DEVCTL, - PCI_EXP_DEVCTL_RELAX_EN | - PCI_EXP_DEVCTL_NOSNOOP_EN, 0); + pcie_capability_clear_word(root_port, PCI_EXP_DEVCTL, + PCI_EXP_DEVCTL_RELAX_EN | + PCI_EXP_DEVCTL_NOSNOOP_EN); } /* @@ -5403,6 +5405,14 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x7901, quirk_no_flr); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1502, quirk_no_flr); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1503, quirk_no_flr); +/* FLR may cause the SolidRun SNET DPU (rev 0x1) to hang */ +static void quirk_no_flr_snet(struct pci_dev *dev) +{ + if (dev->revision == 0x1) + quirk_no_flr(dev); +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SOLIDRUN, 0x1000, quirk_no_flr_snet); + static void quirk_no_ext_tags(struct pci_dev *pdev) { struct pci_host_bridge *bridge = pci_find_host_bridge(pdev->bus); @@ -5415,6 +5425,7 @@ static void quirk_no_ext_tags(struct pci_dev *pdev) pci_walk_bus(bridge->bus, pci_configure_extended_tags, NULL); } +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_3WARE, 0x1004, quirk_no_ext_tags); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0132, quirk_no_ext_tags); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0140, quirk_no_ext_tags); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0141, quirk_no_ext_tags); @@ -5807,6 +5818,42 @@ SWITCHTEC_QUIRK(0x4428); /* PSXA 28XG4 */ SWITCHTEC_QUIRK(0x4552); /* PAXA 52XG4 */ SWITCHTEC_QUIRK(0x4536); /* PAXA 36XG4 */ SWITCHTEC_QUIRK(0x4528); /* PAXA 28XG4 */ +SWITCHTEC_QUIRK(0x5000); /* PFX 100XG5 */ +SWITCHTEC_QUIRK(0x5084); /* PFX 84XG5 */ +SWITCHTEC_QUIRK(0x5068); /* PFX 68XG5 */ +SWITCHTEC_QUIRK(0x5052); /* PFX 52XG5 */ +SWITCHTEC_QUIRK(0x5036); /* PFX 36XG5 */ +SWITCHTEC_QUIRK(0x5028); /* PFX 28XG5 */ +SWITCHTEC_QUIRK(0x5100); /* PSX 100XG5 */ +SWITCHTEC_QUIRK(0x5184); /* PSX 84XG5 */ +SWITCHTEC_QUIRK(0x5168); /* PSX 68XG5 */ +SWITCHTEC_QUIRK(0x5152); /* PSX 52XG5 */ +SWITCHTEC_QUIRK(0x5136); /* PSX 36XG5 */ +SWITCHTEC_QUIRK(0x5128); /* PSX 28XG5 */ +SWITCHTEC_QUIRK(0x5200); /* PAX 100XG5 */ +SWITCHTEC_QUIRK(0x5284); /* PAX 84XG5 */ +SWITCHTEC_QUIRK(0x5268); /* PAX 68XG5 */ +SWITCHTEC_QUIRK(0x5252); /* PAX 52XG5 */ +SWITCHTEC_QUIRK(0x5236); /* PAX 36XG5 */ +SWITCHTEC_QUIRK(0x5228); /* PAX 28XG5 */ +SWITCHTEC_QUIRK(0x5300); /* PFXA 100XG5 */ +SWITCHTEC_QUIRK(0x5384); /* PFXA 84XG5 */ +SWITCHTEC_QUIRK(0x5368); /* PFXA 68XG5 */ +SWITCHTEC_QUIRK(0x5352); /* PFXA 52XG5 */ +SWITCHTEC_QUIRK(0x5336); /* PFXA 36XG5 */ +SWITCHTEC_QUIRK(0x5328); /* PFXA 28XG5 */ +SWITCHTEC_QUIRK(0x5400); /* PSXA 100XG5 */ +SWITCHTEC_QUIRK(0x5484); /* PSXA 84XG5 */ +SWITCHTEC_QUIRK(0x5468); /* PSXA 68XG5 */ +SWITCHTEC_QUIRK(0x5452); /* PSXA 52XG5 */ +SWITCHTEC_QUIRK(0x5436); /* PSXA 36XG5 */ +SWITCHTEC_QUIRK(0x5428); /* PSXA 28XG5 */ +SWITCHTEC_QUIRK(0x5500); /* PAXA 100XG5 */ +SWITCHTEC_QUIRK(0x5584); /* PAXA 84XG5 */ +SWITCHTEC_QUIRK(0x5568); /* PAXA 68XG5 */ +SWITCHTEC_QUIRK(0x5552); /* PAXA 52XG5 */ +SWITCHTEC_QUIRK(0x5536); /* PAXA 36XG5 */ +SWITCHTEC_QUIRK(0x5528); /* PAXA 28XG5 */ /* * The PLX NTB uses devfn proxy IDs to move TLPs between NT endpoints. @@ -6056,7 +6103,7 @@ static void dpc_log_size(struct pci_dev *dev) if (!(val & PCI_EXP_DPC_CAP_RP_EXT)) return; - if (!((val & PCI_EXP_DPC_RP_PIO_LOG_SIZE) >> 8)) { + if (FIELD_GET(PCI_EXP_DPC_RP_PIO_LOG_SIZE, val) == 0) { pci_info(dev, "Overriding RP PIO Log Size to 4\n"); dev->dpc_rp_log_size = 4; } @@ -6077,6 +6124,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a2b, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a2d, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a2f, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a31, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0xa73f, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0xa76e, dpc_log_size); #endif /* diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 3f3320d0a4f8f15ede6381f0f736070aa63956ff..332af6938d7fd9aaee6bd5e568b793ac66e08cad 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -372,7 +372,7 @@ static ssize_t field ## _show(struct device *dev, \ if (stdev->gen == SWITCHTEC_GEN3) \ return io_string_show(buf, &si->gen3.field, \ sizeof(si->gen3.field)); \ - else if (stdev->gen == SWITCHTEC_GEN4) \ + else if (stdev->gen >= SWITCHTEC_GEN4) \ return io_string_show(buf, &si->gen4.field, \ sizeof(si->gen4.field)); \ else \ @@ -663,7 +663,7 @@ static int ioctl_flash_info(struct switchtec_dev *stdev, if (stdev->gen == SWITCHTEC_GEN3) { info.flash_length = ioread32(&fi->gen3.flash_length); info.num_partitions = SWITCHTEC_NUM_PARTITIONS_GEN3; - } else if (stdev->gen == SWITCHTEC_GEN4) { + } else if (stdev->gen >= SWITCHTEC_GEN4) { info.flash_length = ioread32(&fi->gen4.flash_length); info.num_partitions = SWITCHTEC_NUM_PARTITIONS_GEN4; } else { @@ -870,7 +870,7 @@ static int ioctl_flash_part_info(struct switchtec_dev *stdev, ret = flash_part_info_gen3(stdev, &info); if (ret) return ret; - } else if (stdev->gen == SWITCHTEC_GEN4) { + } else if (stdev->gen >= SWITCHTEC_GEN4) { ret = flash_part_info_gen4(stdev, &info); if (ret) return ret; @@ -1606,7 +1606,7 @@ static int switchtec_init_pci(struct switchtec_dev *stdev, if (stdev->gen == SWITCHTEC_GEN3) part_id = &stdev->mmio_sys_info->gen3.partition_id; - else if (stdev->gen == SWITCHTEC_GEN4) + else if (stdev->gen >= SWITCHTEC_GEN4) part_id = &stdev->mmio_sys_info->gen4.partition_id; else return -EOPNOTSUPP; @@ -1674,7 +1674,7 @@ static int switchtec_pci_probe(struct pci_dev *pdev, rc = switchtec_init_isr(stdev); if (rc) { dev_err(&stdev->dev, "failed to init isr.\n"); - goto err_put; + goto err_exit_pci; } iowrite32(SWITCHTEC_EVENT_CLEAR | @@ -1695,6 +1695,8 @@ static int switchtec_pci_probe(struct pci_dev *pdev, err_devadd: stdev_kill(stdev); +err_exit_pci: + switchtec_exit_pci(stdev); err_put: ida_free(&switchtec_minor_ida, MINOR(stdev->dev.devt)); put_device(&stdev->dev); @@ -1738,63 +1740,99 @@ static void switchtec_pci_remove(struct pci_dev *pdev) } static const struct pci_device_id switchtec_pci_tbl[] = { - SWITCHTEC_PCI_DEVICE(0x8531, SWITCHTEC_GEN3), //PFX 24xG3 - SWITCHTEC_PCI_DEVICE(0x8532, SWITCHTEC_GEN3), //PFX 32xG3 - SWITCHTEC_PCI_DEVICE(0x8533, SWITCHTEC_GEN3), //PFX 48xG3 - SWITCHTEC_PCI_DEVICE(0x8534, SWITCHTEC_GEN3), //PFX 64xG3 - SWITCHTEC_PCI_DEVICE(0x8535, SWITCHTEC_GEN3), //PFX 80xG3 - SWITCHTEC_PCI_DEVICE(0x8536, SWITCHTEC_GEN3), //PFX 96xG3 - SWITCHTEC_PCI_DEVICE(0x8541, SWITCHTEC_GEN3), //PSX 24xG3 - SWITCHTEC_PCI_DEVICE(0x8542, SWITCHTEC_GEN3), //PSX 32xG3 - SWITCHTEC_PCI_DEVICE(0x8543, SWITCHTEC_GEN3), //PSX 48xG3 - SWITCHTEC_PCI_DEVICE(0x8544, SWITCHTEC_GEN3), //PSX 64xG3 - SWITCHTEC_PCI_DEVICE(0x8545, SWITCHTEC_GEN3), //PSX 80xG3 - SWITCHTEC_PCI_DEVICE(0x8546, SWITCHTEC_GEN3), //PSX 96xG3 - SWITCHTEC_PCI_DEVICE(0x8551, SWITCHTEC_GEN3), //PAX 24XG3 - SWITCHTEC_PCI_DEVICE(0x8552, SWITCHTEC_GEN3), //PAX 32XG3 - SWITCHTEC_PCI_DEVICE(0x8553, SWITCHTEC_GEN3), //PAX 48XG3 - SWITCHTEC_PCI_DEVICE(0x8554, SWITCHTEC_GEN3), //PAX 64XG3 - SWITCHTEC_PCI_DEVICE(0x8555, SWITCHTEC_GEN3), //PAX 80XG3 - SWITCHTEC_PCI_DEVICE(0x8556, SWITCHTEC_GEN3), //PAX 96XG3 - SWITCHTEC_PCI_DEVICE(0x8561, SWITCHTEC_GEN3), //PFXL 24XG3 - SWITCHTEC_PCI_DEVICE(0x8562, SWITCHTEC_GEN3), //PFXL 32XG3 - SWITCHTEC_PCI_DEVICE(0x8563, SWITCHTEC_GEN3), //PFXL 48XG3 - SWITCHTEC_PCI_DEVICE(0x8564, SWITCHTEC_GEN3), //PFXL 64XG3 - SWITCHTEC_PCI_DEVICE(0x8565, SWITCHTEC_GEN3), //PFXL 80XG3 - SWITCHTEC_PCI_DEVICE(0x8566, SWITCHTEC_GEN3), //PFXL 96XG3 - SWITCHTEC_PCI_DEVICE(0x8571, SWITCHTEC_GEN3), //PFXI 24XG3 - SWITCHTEC_PCI_DEVICE(0x8572, SWITCHTEC_GEN3), //PFXI 32XG3 - SWITCHTEC_PCI_DEVICE(0x8573, SWITCHTEC_GEN3), //PFXI 48XG3 - SWITCHTEC_PCI_DEVICE(0x8574, SWITCHTEC_GEN3), //PFXI 64XG3 - SWITCHTEC_PCI_DEVICE(0x8575, SWITCHTEC_GEN3), //PFXI 80XG3 - SWITCHTEC_PCI_DEVICE(0x8576, SWITCHTEC_GEN3), //PFXI 96XG3 - SWITCHTEC_PCI_DEVICE(0x4000, SWITCHTEC_GEN4), //PFX 100XG4 - SWITCHTEC_PCI_DEVICE(0x4084, SWITCHTEC_GEN4), //PFX 84XG4 - SWITCHTEC_PCI_DEVICE(0x4068, SWITCHTEC_GEN4), //PFX 68XG4 - SWITCHTEC_PCI_DEVICE(0x4052, SWITCHTEC_GEN4), //PFX 52XG4 - SWITCHTEC_PCI_DEVICE(0x4036, SWITCHTEC_GEN4), //PFX 36XG4 - SWITCHTEC_PCI_DEVICE(0x4028, SWITCHTEC_GEN4), //PFX 28XG4 - SWITCHTEC_PCI_DEVICE(0x4100, SWITCHTEC_GEN4), //PSX 100XG4 - SWITCHTEC_PCI_DEVICE(0x4184, SWITCHTEC_GEN4), //PSX 84XG4 - SWITCHTEC_PCI_DEVICE(0x4168, SWITCHTEC_GEN4), //PSX 68XG4 - SWITCHTEC_PCI_DEVICE(0x4152, SWITCHTEC_GEN4), //PSX 52XG4 - SWITCHTEC_PCI_DEVICE(0x4136, SWITCHTEC_GEN4), //PSX 36XG4 - SWITCHTEC_PCI_DEVICE(0x4128, SWITCHTEC_GEN4), //PSX 28XG4 - SWITCHTEC_PCI_DEVICE(0x4200, SWITCHTEC_GEN4), //PAX 100XG4 - SWITCHTEC_PCI_DEVICE(0x4284, SWITCHTEC_GEN4), //PAX 84XG4 - SWITCHTEC_PCI_DEVICE(0x4268, SWITCHTEC_GEN4), //PAX 68XG4 - SWITCHTEC_PCI_DEVICE(0x4252, SWITCHTEC_GEN4), //PAX 52XG4 - SWITCHTEC_PCI_DEVICE(0x4236, SWITCHTEC_GEN4), //PAX 36XG4 - SWITCHTEC_PCI_DEVICE(0x4228, SWITCHTEC_GEN4), //PAX 28XG4 - SWITCHTEC_PCI_DEVICE(0x4352, SWITCHTEC_GEN4), //PFXA 52XG4 - SWITCHTEC_PCI_DEVICE(0x4336, SWITCHTEC_GEN4), //PFXA 36XG4 - SWITCHTEC_PCI_DEVICE(0x4328, SWITCHTEC_GEN4), //PFXA 28XG4 - SWITCHTEC_PCI_DEVICE(0x4452, SWITCHTEC_GEN4), //PSXA 52XG4 - SWITCHTEC_PCI_DEVICE(0x4436, SWITCHTEC_GEN4), //PSXA 36XG4 - SWITCHTEC_PCI_DEVICE(0x4428, SWITCHTEC_GEN4), //PSXA 28XG4 - SWITCHTEC_PCI_DEVICE(0x4552, SWITCHTEC_GEN4), //PAXA 52XG4 - SWITCHTEC_PCI_DEVICE(0x4536, SWITCHTEC_GEN4), //PAXA 36XG4 - SWITCHTEC_PCI_DEVICE(0x4528, SWITCHTEC_GEN4), //PAXA 28XG4 + SWITCHTEC_PCI_DEVICE(0x8531, SWITCHTEC_GEN3), /* PFX 24xG3 */ + SWITCHTEC_PCI_DEVICE(0x8532, SWITCHTEC_GEN3), /* PFX 32xG3 */ + SWITCHTEC_PCI_DEVICE(0x8533, SWITCHTEC_GEN3), /* PFX 48xG3 */ + SWITCHTEC_PCI_DEVICE(0x8534, SWITCHTEC_GEN3), /* PFX 64xG3 */ + SWITCHTEC_PCI_DEVICE(0x8535, SWITCHTEC_GEN3), /* PFX 80xG3 */ + SWITCHTEC_PCI_DEVICE(0x8536, SWITCHTEC_GEN3), /* PFX 96xG3 */ + SWITCHTEC_PCI_DEVICE(0x8541, SWITCHTEC_GEN3), /* PSX 24xG3 */ + SWITCHTEC_PCI_DEVICE(0x8542, SWITCHTEC_GEN3), /* PSX 32xG3 */ + SWITCHTEC_PCI_DEVICE(0x8543, SWITCHTEC_GEN3), /* PSX 48xG3 */ + SWITCHTEC_PCI_DEVICE(0x8544, SWITCHTEC_GEN3), /* PSX 64xG3 */ + SWITCHTEC_PCI_DEVICE(0x8545, SWITCHTEC_GEN3), /* PSX 80xG3 */ + SWITCHTEC_PCI_DEVICE(0x8546, SWITCHTEC_GEN3), /* PSX 96xG3 */ + SWITCHTEC_PCI_DEVICE(0x8551, SWITCHTEC_GEN3), /* PAX 24XG3 */ + SWITCHTEC_PCI_DEVICE(0x8552, SWITCHTEC_GEN3), /* PAX 32XG3 */ + SWITCHTEC_PCI_DEVICE(0x8553, SWITCHTEC_GEN3), /* PAX 48XG3 */ + SWITCHTEC_PCI_DEVICE(0x8554, SWITCHTEC_GEN3), /* PAX 64XG3 */ + SWITCHTEC_PCI_DEVICE(0x8555, SWITCHTEC_GEN3), /* PAX 80XG3 */ + SWITCHTEC_PCI_DEVICE(0x8556, SWITCHTEC_GEN3), /* PAX 96XG3 */ + SWITCHTEC_PCI_DEVICE(0x8561, SWITCHTEC_GEN3), /* PFXL 24XG3 */ + SWITCHTEC_PCI_DEVICE(0x8562, SWITCHTEC_GEN3), /* PFXL 32XG3 */ + SWITCHTEC_PCI_DEVICE(0x8563, SWITCHTEC_GEN3), /* PFXL 48XG3 */ + SWITCHTEC_PCI_DEVICE(0x8564, SWITCHTEC_GEN3), /* PFXL 64XG3 */ + SWITCHTEC_PCI_DEVICE(0x8565, SWITCHTEC_GEN3), /* PFXL 80XG3 */ + SWITCHTEC_PCI_DEVICE(0x8566, SWITCHTEC_GEN3), /* PFXL 96XG3 */ + SWITCHTEC_PCI_DEVICE(0x8571, SWITCHTEC_GEN3), /* PFXI 24XG3 */ + SWITCHTEC_PCI_DEVICE(0x8572, SWITCHTEC_GEN3), /* PFXI 32XG3 */ + SWITCHTEC_PCI_DEVICE(0x8573, SWITCHTEC_GEN3), /* PFXI 48XG3 */ + SWITCHTEC_PCI_DEVICE(0x8574, SWITCHTEC_GEN3), /* PFXI 64XG3 */ + SWITCHTEC_PCI_DEVICE(0x8575, SWITCHTEC_GEN3), /* PFXI 80XG3 */ + SWITCHTEC_PCI_DEVICE(0x8576, SWITCHTEC_GEN3), /* PFXI 96XG3 */ + SWITCHTEC_PCI_DEVICE(0x4000, SWITCHTEC_GEN4), /* PFX 100XG4 */ + SWITCHTEC_PCI_DEVICE(0x4084, SWITCHTEC_GEN4), /* PFX 84XG4 */ + SWITCHTEC_PCI_DEVICE(0x4068, SWITCHTEC_GEN4), /* PFX 68XG4 */ + SWITCHTEC_PCI_DEVICE(0x4052, SWITCHTEC_GEN4), /* PFX 52XG4 */ + SWITCHTEC_PCI_DEVICE(0x4036, SWITCHTEC_GEN4), /* PFX 36XG4 */ + SWITCHTEC_PCI_DEVICE(0x4028, SWITCHTEC_GEN4), /* PFX 28XG4 */ + SWITCHTEC_PCI_DEVICE(0x4100, SWITCHTEC_GEN4), /* PSX 100XG4 */ + SWITCHTEC_PCI_DEVICE(0x4184, SWITCHTEC_GEN4), /* PSX 84XG4 */ + SWITCHTEC_PCI_DEVICE(0x4168, SWITCHTEC_GEN4), /* PSX 68XG4 */ + SWITCHTEC_PCI_DEVICE(0x4152, SWITCHTEC_GEN4), /* PSX 52XG4 */ + SWITCHTEC_PCI_DEVICE(0x4136, SWITCHTEC_GEN4), /* PSX 36XG4 */ + SWITCHTEC_PCI_DEVICE(0x4128, SWITCHTEC_GEN4), /* PSX 28XG4 */ + SWITCHTEC_PCI_DEVICE(0x4200, SWITCHTEC_GEN4), /* PAX 100XG4 */ + SWITCHTEC_PCI_DEVICE(0x4284, SWITCHTEC_GEN4), /* PAX 84XG4 */ + SWITCHTEC_PCI_DEVICE(0x4268, SWITCHTEC_GEN4), /* PAX 68XG4 */ + SWITCHTEC_PCI_DEVICE(0x4252, SWITCHTEC_GEN4), /* PAX 52XG4 */ + SWITCHTEC_PCI_DEVICE(0x4236, SWITCHTEC_GEN4), /* PAX 36XG4 */ + SWITCHTEC_PCI_DEVICE(0x4228, SWITCHTEC_GEN4), /* PAX 28XG4 */ + SWITCHTEC_PCI_DEVICE(0x4352, SWITCHTEC_GEN4), /* PFXA 52XG4 */ + SWITCHTEC_PCI_DEVICE(0x4336, SWITCHTEC_GEN4), /* PFXA 36XG4 */ + SWITCHTEC_PCI_DEVICE(0x4328, SWITCHTEC_GEN4), /* PFXA 28XG4 */ + SWITCHTEC_PCI_DEVICE(0x4452, SWITCHTEC_GEN4), /* PSXA 52XG4 */ + SWITCHTEC_PCI_DEVICE(0x4436, SWITCHTEC_GEN4), /* PSXA 36XG4 */ + SWITCHTEC_PCI_DEVICE(0x4428, SWITCHTEC_GEN4), /* PSXA 28XG4 */ + SWITCHTEC_PCI_DEVICE(0x4552, SWITCHTEC_GEN4), /* PAXA 52XG4 */ + SWITCHTEC_PCI_DEVICE(0x4536, SWITCHTEC_GEN4), /* PAXA 36XG4 */ + SWITCHTEC_PCI_DEVICE(0x4528, SWITCHTEC_GEN4), /* PAXA 28XG4 */ + SWITCHTEC_PCI_DEVICE(0x5000, SWITCHTEC_GEN5), /* PFX 100XG5 */ + SWITCHTEC_PCI_DEVICE(0x5084, SWITCHTEC_GEN5), /* PFX 84XG5 */ + SWITCHTEC_PCI_DEVICE(0x5068, SWITCHTEC_GEN5), /* PFX 68XG5 */ + SWITCHTEC_PCI_DEVICE(0x5052, SWITCHTEC_GEN5), /* PFX 52XG5 */ + SWITCHTEC_PCI_DEVICE(0x5036, SWITCHTEC_GEN5), /* PFX 36XG5 */ + SWITCHTEC_PCI_DEVICE(0x5028, SWITCHTEC_GEN5), /* PFX 28XG5 */ + SWITCHTEC_PCI_DEVICE(0x5100, SWITCHTEC_GEN5), /* PSX 100XG5 */ + SWITCHTEC_PCI_DEVICE(0x5184, SWITCHTEC_GEN5), /* PSX 84XG5 */ + SWITCHTEC_PCI_DEVICE(0x5168, SWITCHTEC_GEN5), /* PSX 68XG5 */ + SWITCHTEC_PCI_DEVICE(0x5152, SWITCHTEC_GEN5), /* PSX 52XG5 */ + SWITCHTEC_PCI_DEVICE(0x5136, SWITCHTEC_GEN5), /* PSX 36XG5 */ + SWITCHTEC_PCI_DEVICE(0x5128, SWITCHTEC_GEN5), /* PSX 28XG5 */ + SWITCHTEC_PCI_DEVICE(0x5200, SWITCHTEC_GEN5), /* PAX 100XG5 */ + SWITCHTEC_PCI_DEVICE(0x5284, SWITCHTEC_GEN5), /* PAX 84XG5 */ + SWITCHTEC_PCI_DEVICE(0x5268, SWITCHTEC_GEN5), /* PAX 68XG5 */ + SWITCHTEC_PCI_DEVICE(0x5252, SWITCHTEC_GEN5), /* PAX 52XG5 */ + SWITCHTEC_PCI_DEVICE(0x5236, SWITCHTEC_GEN5), /* PAX 36XG5 */ + SWITCHTEC_PCI_DEVICE(0x5228, SWITCHTEC_GEN5), /* PAX 28XG5 */ + SWITCHTEC_PCI_DEVICE(0x5300, SWITCHTEC_GEN5), /* PFXA 100XG5 */ + SWITCHTEC_PCI_DEVICE(0x5384, SWITCHTEC_GEN5), /* PFXA 84XG5 */ + SWITCHTEC_PCI_DEVICE(0x5368, SWITCHTEC_GEN5), /* PFXA 68XG5 */ + SWITCHTEC_PCI_DEVICE(0x5352, SWITCHTEC_GEN5), /* PFXA 52XG5 */ + SWITCHTEC_PCI_DEVICE(0x5336, SWITCHTEC_GEN5), /* PFXA 36XG5 */ + SWITCHTEC_PCI_DEVICE(0x5328, SWITCHTEC_GEN5), /* PFXA 28XG5 */ + SWITCHTEC_PCI_DEVICE(0x5400, SWITCHTEC_GEN5), /* PSXA 100XG5 */ + SWITCHTEC_PCI_DEVICE(0x5484, SWITCHTEC_GEN5), /* PSXA 84XG5 */ + SWITCHTEC_PCI_DEVICE(0x5468, SWITCHTEC_GEN5), /* PSXA 68XG5 */ + SWITCHTEC_PCI_DEVICE(0x5452, SWITCHTEC_GEN5), /* PSXA 52XG5 */ + SWITCHTEC_PCI_DEVICE(0x5436, SWITCHTEC_GEN5), /* PSXA 36XG5 */ + SWITCHTEC_PCI_DEVICE(0x5428, SWITCHTEC_GEN5), /* PSXA 28XG5 */ + SWITCHTEC_PCI_DEVICE(0x5500, SWITCHTEC_GEN5), /* PAXA 100XG5 */ + SWITCHTEC_PCI_DEVICE(0x5584, SWITCHTEC_GEN5), /* PAXA 84XG5 */ + SWITCHTEC_PCI_DEVICE(0x5568, SWITCHTEC_GEN5), /* PAXA 68XG5 */ + SWITCHTEC_PCI_DEVICE(0x5552, SWITCHTEC_GEN5), /* PAXA 52XG5 */ + SWITCHTEC_PCI_DEVICE(0x5536, SWITCHTEC_GEN5), /* PAXA 36XG5 */ + SWITCHTEC_PCI_DEVICE(0x5528, SWITCHTEC_GEN5), /* PAXA 28XG5 */ {0} }; MODULE_DEVICE_TABLE(pci, switchtec_pci_tbl); diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c index 47e7c3206939f68ae57f0819f869dcbfc72b6b10..899e4ed49905c487ed17ea0e008e29d542765cbb 100644 --- a/drivers/perf/arm-cmn.c +++ b/drivers/perf/arm-cmn.c @@ -2178,6 +2178,17 @@ static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset) dev_dbg(cmn->dev, "ignoring external node %llx\n", reg); continue; } + /* + * AmpereOneX erratum AC04_MESH_1 makes some XPs report a bogus + * child count larger than the number of valid child pointers. + * A child offset of 0 can only occur on CMN-600; otherwise it + * would imply the root node being its own grandchild, which + * we can safely dismiss in general. + */ + if (reg == 0 && cmn->part != PART_CMN600) { + dev_dbg(cmn->dev, "bogus child pointer?\n"); + continue; + } arm_cmn_init_node_info(cmn, reg & CMN_CHILD_NODE_ADDR, dn); diff --git a/drivers/perf/riscv_pmu.c b/drivers/perf/riscv_pmu.c index 56897d4d4fd3efa339f2e001985112bd752108a5..2d5cf135e8a1d6eac535a0e7b599cd90cc557b85 100644 --- a/drivers/perf/riscv_pmu.c +++ b/drivers/perf/riscv_pmu.c @@ -246,6 +246,10 @@ static int riscv_pmu_event_init(struct perf_event *event) u64 event_config = 0; uint64_t cmask; + /* driver does not support branch stack sampling */ + if (has_branch_stack(event)) + return -EOPNOTSUPP; + hwc->flags = 0; mapped_event = rvpmu->event_map(event, &event_config); if (mapped_event < 0) { diff --git a/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c b/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c index e625b32889bfceaef9846db42e594e971cccb54d..0928a526e2ab3692eaeb1e4abaa45e23eee4cf5b 100644 --- a/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c +++ b/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c @@ -706,7 +706,7 @@ static int mixel_dphy_probe(struct platform_device *pdev) return ret; } - priv->id = of_alias_get_id(np, "mipi_dphy"); + priv->id = of_alias_get_id(np, "mipi-dphy"); if (priv->id < 0) { dev_err(dev, "Failed to get phy node alias id: %d\n", priv->id); diff --git a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c index c93286483b4259178a5d46ef0d73f708af564825..211ce84d980f92a14937d04ca0b95b6b3e4f8213 100644 --- a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c +++ b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -47,6 +48,15 @@ #define IMX8MM_GPR_PCIE_SSC_EN BIT(16) #define IMX8MM_GPR_PCIE_AUX_EN_OVERRIDE BIT(9) +enum imx8_pcie_phy_type { + IMX8MM, +}; + +struct imx8_pcie_phy_drvdata { + const char *gpr; + enum imx8_pcie_phy_type variant; +}; + struct imx8_pcie_phy { void __iomem *base; struct clk *clk; @@ -57,6 +67,7 @@ struct imx8_pcie_phy { u32 tx_deemph_gen1; u32 tx_deemph_gen2; bool clkreq_unused; + const struct imx8_pcie_phy_drvdata *drvdata; }; static int imx8_pcie_phy_power_on(struct phy *phy) @@ -68,31 +79,17 @@ static int imx8_pcie_phy_power_on(struct phy *phy) reset_control_assert(imx8_phy->reset); pad_mode = imx8_phy->refclk_pad_mode; - /* Set AUX_EN_OVERRIDE 1'b0, when the CLKREQ# isn't hooked */ - regmap_update_bits(imx8_phy->iomuxc_gpr, IOMUXC_GPR14, - IMX8MM_GPR_PCIE_AUX_EN_OVERRIDE, - imx8_phy->clkreq_unused ? - 0 : IMX8MM_GPR_PCIE_AUX_EN_OVERRIDE); - regmap_update_bits(imx8_phy->iomuxc_gpr, IOMUXC_GPR14, - IMX8MM_GPR_PCIE_AUX_EN, - IMX8MM_GPR_PCIE_AUX_EN); - regmap_update_bits(imx8_phy->iomuxc_gpr, IOMUXC_GPR14, - IMX8MM_GPR_PCIE_POWER_OFF, 0); - regmap_update_bits(imx8_phy->iomuxc_gpr, IOMUXC_GPR14, - IMX8MM_GPR_PCIE_SSC_EN, 0); - - regmap_update_bits(imx8_phy->iomuxc_gpr, IOMUXC_GPR14, - IMX8MM_GPR_PCIE_REF_CLK_SEL, - pad_mode == IMX8_PCIE_REFCLK_PAD_INPUT ? - IMX8MM_GPR_PCIE_REF_CLK_EXT : - IMX8MM_GPR_PCIE_REF_CLK_PLL); - usleep_range(100, 200); - - /* Do the PHY common block reset */ - regmap_update_bits(imx8_phy->iomuxc_gpr, IOMUXC_GPR14, - IMX8MM_GPR_PCIE_CMN_RST, - IMX8MM_GPR_PCIE_CMN_RST); - usleep_range(200, 500); + switch (imx8_phy->drvdata->variant) { + case IMX8MM: + /* Tune PHY de-emphasis setting to pass PCIe compliance. */ + if (imx8_phy->tx_deemph_gen1) + writel(imx8_phy->tx_deemph_gen1, + imx8_phy->base + PCIE_PHY_TRSV_REG5); + if (imx8_phy->tx_deemph_gen2) + writel(imx8_phy->tx_deemph_gen2, + imx8_phy->base + PCIE_PHY_TRSV_REG6); + break; + } if (pad_mode == IMX8_PCIE_REFCLK_PAD_INPUT || pad_mode == IMX8_PCIE_REFCLK_PAD_UNUSED) { @@ -111,8 +108,10 @@ static int imx8_pcie_phy_power_on(struct phy *phy) /* Source clock from SoC internal PLL */ writel(ANA_PLL_CLK_OUT_TO_EXT_IO_SEL, imx8_phy->base + IMX8MM_PCIE_PHY_CMN_REG062); - writel(AUX_PLL_REFCLK_SEL_SYS_PLL, - imx8_phy->base + IMX8MM_PCIE_PHY_CMN_REG063); + if (imx8_phy->drvdata->variant != IMX8MM) { + writel(AUX_PLL_REFCLK_SEL_SYS_PLL, + imx8_phy->base + IMX8MM_PCIE_PHY_CMN_REG063); + } val = ANA_AUX_RX_TX_SEL_TX | ANA_AUX_TX_TERM; writel(val | ANA_AUX_RX_TERM_GND_EN, imx8_phy->base + IMX8MM_PCIE_PHY_CMN_REG064); @@ -120,15 +119,37 @@ static int imx8_pcie_phy_power_on(struct phy *phy) imx8_phy->base + IMX8MM_PCIE_PHY_CMN_REG065); } - /* Tune PHY de-emphasis setting to pass PCIe compliance. */ - if (imx8_phy->tx_deemph_gen1) - writel(imx8_phy->tx_deemph_gen1, - imx8_phy->base + PCIE_PHY_TRSV_REG5); - if (imx8_phy->tx_deemph_gen2) - writel(imx8_phy->tx_deemph_gen2, - imx8_phy->base + PCIE_PHY_TRSV_REG6); + /* Set AUX_EN_OVERRIDE 1'b0, when the CLKREQ# isn't hooked */ + regmap_update_bits(imx8_phy->iomuxc_gpr, IOMUXC_GPR14, + IMX8MM_GPR_PCIE_AUX_EN_OVERRIDE, + imx8_phy->clkreq_unused ? + 0 : IMX8MM_GPR_PCIE_AUX_EN_OVERRIDE); + regmap_update_bits(imx8_phy->iomuxc_gpr, IOMUXC_GPR14, + IMX8MM_GPR_PCIE_AUX_EN, + IMX8MM_GPR_PCIE_AUX_EN); + regmap_update_bits(imx8_phy->iomuxc_gpr, IOMUXC_GPR14, + IMX8MM_GPR_PCIE_POWER_OFF, 0); + regmap_update_bits(imx8_phy->iomuxc_gpr, IOMUXC_GPR14, + IMX8MM_GPR_PCIE_SSC_EN, 0); - reset_control_deassert(imx8_phy->reset); + regmap_update_bits(imx8_phy->iomuxc_gpr, IOMUXC_GPR14, + IMX8MM_GPR_PCIE_REF_CLK_SEL, + pad_mode == IMX8_PCIE_REFCLK_PAD_INPUT ? + IMX8MM_GPR_PCIE_REF_CLK_EXT : + IMX8MM_GPR_PCIE_REF_CLK_PLL); + usleep_range(100, 200); + + /* Do the PHY common block reset */ + regmap_update_bits(imx8_phy->iomuxc_gpr, IOMUXC_GPR14, + IMX8MM_GPR_PCIE_CMN_RST, + IMX8MM_GPR_PCIE_CMN_RST); + + switch (imx8_phy->drvdata->variant) { + case IMX8MM: + reset_control_deassert(imx8_phy->reset); + usleep_range(200, 500); + break; + } /* Polling to check the phy is ready or not. */ ret = readl_poll_timeout(imx8_phy->base + IMX8MM_PCIE_PHY_CMN_REG75, @@ -160,6 +181,17 @@ static const struct phy_ops imx8_pcie_phy_ops = { .owner = THIS_MODULE, }; +static const struct imx8_pcie_phy_drvdata imx8mm_drvdata = { + .gpr = "fsl,imx8mm-iomuxc-gpr", + .variant = IMX8MM, +}; + +static const struct of_device_id imx8_pcie_phy_of_match[] = { + {.compatible = "fsl,imx8mm-pcie-phy", .data = &imx8mm_drvdata, }, + { }, +}; +MODULE_DEVICE_TABLE(of, imx8_pcie_phy_of_match); + static int imx8_pcie_phy_probe(struct platform_device *pdev) { struct phy_provider *phy_provider; @@ -172,6 +204,8 @@ static int imx8_pcie_phy_probe(struct platform_device *pdev) if (!imx8_phy) return -ENOMEM; + imx8_phy->drvdata = of_device_get_match_data(dev); + /* get PHY refclk pad mode */ of_property_read_u32(np, "fsl,refclk-pad-mode", &imx8_phy->refclk_pad_mode); @@ -197,7 +231,7 @@ static int imx8_pcie_phy_probe(struct platform_device *pdev) /* Grab GPR config register range */ imx8_phy->iomuxc_gpr = - syscon_regmap_lookup_by_compatible("fsl,imx6q-iomuxc-gpr"); + syscon_regmap_lookup_by_compatible(imx8_phy->drvdata->gpr); if (IS_ERR(imx8_phy->iomuxc_gpr)) { dev_err(dev, "unable to find iomuxc registers\n"); return PTR_ERR(imx8_phy->iomuxc_gpr); @@ -225,12 +259,6 @@ static int imx8_pcie_phy_probe(struct platform_device *pdev) return PTR_ERR_OR_ZERO(phy_provider); } -static const struct of_device_id imx8_pcie_phy_of_match[] = { - {.compatible = "fsl,imx8mm-pcie-phy",}, - { }, -}; -MODULE_DEVICE_TABLE(of, imx8_pcie_phy_of_match); - static struct platform_driver imx8_pcie_phy_driver = { .probe = imx8_pcie_phy_probe, .driver = { diff --git a/drivers/phy/marvell/phy-mvebu-a3700-comphy.c b/drivers/phy/marvell/phy-mvebu-a3700-comphy.c index d641b345afa35cf8392fb335c8214749a4efbf07..251e1aedd4a6ef19412af819dbeec2976f4efb17 100644 --- a/drivers/phy/marvell/phy-mvebu-a3700-comphy.c +++ b/drivers/phy/marvell/phy-mvebu-a3700-comphy.c @@ -602,7 +602,7 @@ static void comphy_gbe_phy_init(struct mvebu_a3700_comphy_lane *lane, u16 val; fix_idx = 0; - for (addr = 0; addr < 512; addr++) { + for (addr = 0; addr < ARRAY_SIZE(gbe_phy_init); addr++) { /* * All PHY register values are defined in full for 3.125Gbps * SERDES speed. The values required for 1.25 Gbps are almost @@ -610,11 +610,12 @@ static void comphy_gbe_phy_init(struct mvebu_a3700_comphy_lane *lane, * comparison to 3.125 Gbps values. These register values are * stored in "gbe_phy_init_fix" array. */ - if (!is_1gbps && gbe_phy_init_fix[fix_idx].addr == addr) { + if (!is_1gbps && + fix_idx < ARRAY_SIZE(gbe_phy_init_fix) && + gbe_phy_init_fix[fix_idx].addr == addr) { /* Use new value */ val = gbe_phy_init_fix[fix_idx].value; - if (fix_idx < ARRAY_SIZE(gbe_phy_init_fix)) - fix_idx++; + fix_idx++; } else { val = gbe_phy_init[addr]; } diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c index 9de617ca9daa26ab119357d0e9291ee6f5776345..7e61c6b278a74274580332b54c748521203a516f 100644 --- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c +++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c @@ -675,8 +675,6 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev) channel->irq = platform_get_irq_optional(pdev, 0); channel->dr_mode = rcar_gen3_get_dr_mode(dev->of_node); if (channel->dr_mode != USB_DR_MODE_UNKNOWN) { - int ret; - channel->is_otg_channel = true; channel->uses_otg_pins = !of_property_read_bool(dev->of_node, "renesas,no-otg-pins"); @@ -740,8 +738,6 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev) ret = PTR_ERR(provider); goto error; } else if (channel->is_otg_channel) { - int ret; - ret = device_create_file(dev, &dev_attr_role); if (ret < 0) goto error; diff --git a/drivers/phy/rockchip/phy-rockchip-snps-pcie3.c b/drivers/phy/rockchip/phy-rockchip-snps-pcie3.c index 1d355b32ba5599394c090c8939592f49c0408a82..c6aa6bc69e90011e79099ff7ac3b1eaed43eaf1c 100644 --- a/drivers/phy/rockchip/phy-rockchip-snps-pcie3.c +++ b/drivers/phy/rockchip/phy-rockchip-snps-pcie3.c @@ -39,6 +39,8 @@ #define RK3588_BIFURCATION_LANE_0_1 BIT(0) #define RK3588_BIFURCATION_LANE_2_3 BIT(1) #define RK3588_LANE_AGGREGATION BIT(2) +#define RK3588_PCIE1LN_SEL_EN (GENMASK(1, 0) << 16) +#define RK3588_PCIE30_PHY_MODE_EN (GENMASK(2, 0) << 16) struct rockchip_p3phy_ops; @@ -131,7 +133,7 @@ static const struct rockchip_p3phy_ops rk3568_ops = { static int rockchip_p3phy_rk3588_init(struct rockchip_p3phy_priv *priv) { u32 reg = 0; - u8 mode = 0; + u8 mode = RK3588_LANE_AGGREGATION; /* default */ int ret; /* Deassert PCIe PMA output clamp mode */ @@ -139,31 +141,24 @@ static int rockchip_p3phy_rk3588_init(struct rockchip_p3phy_priv *priv) /* Set bifurcation if needed */ for (int i = 0; i < priv->num_lanes; i++) { - if (!priv->lanes[i]) - mode |= (BIT(i) << 3); - if (priv->lanes[i] > 1) - mode |= (BIT(i) >> 1); - } - - if (!mode) - reg = RK3588_LANE_AGGREGATION; - else { - if (mode & (BIT(0) | BIT(1))) - reg |= RK3588_BIFURCATION_LANE_0_1; - - if (mode & (BIT(2) | BIT(3))) - reg |= RK3588_BIFURCATION_LANE_2_3; + mode &= ~RK3588_LANE_AGGREGATION; + if (priv->lanes[i] == 3) + mode |= RK3588_BIFURCATION_LANE_0_1; + if (priv->lanes[i] == 4) + mode |= RK3588_BIFURCATION_LANE_2_3; } - regmap_write(priv->phy_grf, RK3588_PCIE3PHY_GRF_CMN_CON0, (0x7<<16) | reg); + reg = mode; + regmap_write(priv->phy_grf, RK3588_PCIE3PHY_GRF_CMN_CON0, + RK3588_PCIE30_PHY_MODE_EN | reg); /* Set pcie1ln_sel in PHP_GRF_PCIESEL_CON */ if (!IS_ERR(priv->pipe_grf)) { - reg = (mode & (BIT(6) | BIT(7))) >> 6; + reg = mode & (RK3588_BIFURCATION_LANE_0_1 | RK3588_BIFURCATION_LANE_2_3); if (reg) regmap_write(priv->pipe_grf, PHP_GRF_PCIESEL_CON, - (reg << 16) | reg); + RK3588_PCIE1LN_SEL_EN | reg); } reset_control_deassert(priv->p30phy); diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index 4d5b4071d47d5514289f99fb9146581f1ca675d3..dc22b1dd2c8badf51d39df3264a6235676ad035d 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -1518,6 +1518,19 @@ int tegra_xusb_padctl_get_usb3_companion(struct tegra_xusb_padctl *padctl, } EXPORT_SYMBOL_GPL(tegra_xusb_padctl_get_usb3_companion); +int tegra_xusb_padctl_get_port_number(struct phy *phy) +{ + struct tegra_xusb_lane *lane; + + if (!phy) + return -ENODEV; + + lane = phy_get_drvdata(phy); + + return lane->index; +} +EXPORT_SYMBOL_GPL(tegra_xusb_padctl_get_port_number); + MODULE_AUTHOR("Thierry Reding "); MODULE_DESCRIPTION("Tegra XUSB Pad Controller driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/phy/ti/phy-omap-usb2.c b/drivers/phy/ti/phy-omap-usb2.c index 31a775877f6e3040df1b53b4b43f1e2571b009f8..63c45809943ff2855a5cf9608d29b1107bc1b405 100644 --- a/drivers/phy/ti/phy-omap-usb2.c +++ b/drivers/phy/ti/phy-omap-usb2.c @@ -116,7 +116,7 @@ static int omap_usb_set_vbus(struct usb_otg *otg, bool enabled) { struct omap_usb *phy = phy_to_omapusb(otg->usb_phy); - if (!phy->comparator) + if (!phy->comparator || !phy->comparator->set_vbus) return -ENODEV; return phy->comparator->set_vbus(phy->comparator, enabled); @@ -126,7 +126,7 @@ static int omap_usb_start_srp(struct usb_otg *otg) { struct omap_usb *phy = phy_to_omapusb(otg->usb_phy); - if (!phy->comparator) + if (!phy->comparator || !phy->comparator->start_srp) return -ENODEV; return phy->comparator->start_srp(phy->comparator); diff --git a/drivers/phy/ti/phy-tusb1210.c b/drivers/phy/ti/phy-tusb1210.c index 669c13d6e402fa422d5ee67c5770835a0dd953ee..bdd44ec3e809827cad7519eb9e7fa702b60f84a0 100644 --- a/drivers/phy/ti/phy-tusb1210.c +++ b/drivers/phy/ti/phy-tusb1210.c @@ -64,7 +64,6 @@ struct tusb1210 { struct delayed_work chg_det_work; struct notifier_block psy_nb; struct power_supply *psy; - struct power_supply *charger; #endif }; @@ -230,19 +229,24 @@ static const char * const tusb1210_chargers[] = { static bool tusb1210_get_online(struct tusb1210 *tusb) { + struct power_supply *charger = NULL; union power_supply_propval val; - int i; + bool online = false; + int i, ret; - for (i = 0; i < ARRAY_SIZE(tusb1210_chargers) && !tusb->charger; i++) - tusb->charger = power_supply_get_by_name(tusb1210_chargers[i]); + for (i = 0; i < ARRAY_SIZE(tusb1210_chargers) && !charger; i++) + charger = power_supply_get_by_name(tusb1210_chargers[i]); - if (!tusb->charger) + if (!charger) return false; - if (power_supply_get_property(tusb->charger, POWER_SUPPLY_PROP_ONLINE, &val)) - return false; + ret = power_supply_get_property(charger, POWER_SUPPLY_PROP_ONLINE, &val); + if (ret == 0) + online = val.intval; + + power_supply_put(charger); - return val.intval; + return online; } static void tusb1210_chg_det_work(struct work_struct *work) @@ -466,9 +470,6 @@ static void tusb1210_remove_charger_detect(struct tusb1210 *tusb) cancel_delayed_work_sync(&tusb->chg_det_work); power_supply_unregister(tusb->psy); } - - if (tusb->charger) - power_supply_put(tusb->charger); } #else static void tusb1210_probe_charger_detect(struct tusb1210 *tusb) { } diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c index 80838dc54b3abb1eccbb15a3e749f7f94a526a12..7938741136a2c2a833e20e8a767f6b6ba301643f 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c @@ -43,7 +43,7 @@ #define SCU614 0x614 /* Disable GPIO Internal Pull-Down #1 */ #define SCU618 0x618 /* Disable GPIO Internal Pull-Down #2 */ #define SCU61C 0x61c /* Disable GPIO Internal Pull-Down #3 */ -#define SCU620 0x620 /* Disable GPIO Internal Pull-Down #4 */ +#define SCU630 0x630 /* Disable GPIO Internal Pull-Down #4 */ #define SCU634 0x634 /* Disable GPIO Internal Pull-Down #5 */ #define SCU638 0x638 /* Disable GPIO Internal Pull-Down #6 */ #define SCU690 0x690 /* Multi-function Pin Control #24 */ @@ -2494,38 +2494,38 @@ static struct aspeed_pin_config aspeed_g6_configs[] = { ASPEED_PULL_DOWN_PINCONF(D14, SCU61C, 0), /* GPIOS7 */ - ASPEED_PULL_DOWN_PINCONF(T24, SCU620, 23), + ASPEED_PULL_DOWN_PINCONF(T24, SCU630, 23), /* GPIOS6 */ - ASPEED_PULL_DOWN_PINCONF(P23, SCU620, 22), + ASPEED_PULL_DOWN_PINCONF(P23, SCU630, 22), /* GPIOS5 */ - ASPEED_PULL_DOWN_PINCONF(P24, SCU620, 21), + ASPEED_PULL_DOWN_PINCONF(P24, SCU630, 21), /* GPIOS4 */ - ASPEED_PULL_DOWN_PINCONF(R26, SCU620, 20), + ASPEED_PULL_DOWN_PINCONF(R26, SCU630, 20), /* GPIOS3*/ - ASPEED_PULL_DOWN_PINCONF(R24, SCU620, 19), + ASPEED_PULL_DOWN_PINCONF(R24, SCU630, 19), /* GPIOS2 */ - ASPEED_PULL_DOWN_PINCONF(T26, SCU620, 18), + ASPEED_PULL_DOWN_PINCONF(T26, SCU630, 18), /* GPIOS1 */ - ASPEED_PULL_DOWN_PINCONF(T25, SCU620, 17), + ASPEED_PULL_DOWN_PINCONF(T25, SCU630, 17), /* GPIOS0 */ - ASPEED_PULL_DOWN_PINCONF(R23, SCU620, 16), + ASPEED_PULL_DOWN_PINCONF(R23, SCU630, 16), /* GPIOR7 */ - ASPEED_PULL_DOWN_PINCONF(U26, SCU620, 15), + ASPEED_PULL_DOWN_PINCONF(U26, SCU630, 15), /* GPIOR6 */ - ASPEED_PULL_DOWN_PINCONF(W26, SCU620, 14), + ASPEED_PULL_DOWN_PINCONF(W26, SCU630, 14), /* GPIOR5 */ - ASPEED_PULL_DOWN_PINCONF(T23, SCU620, 13), + ASPEED_PULL_DOWN_PINCONF(T23, SCU630, 13), /* GPIOR4 */ - ASPEED_PULL_DOWN_PINCONF(U25, SCU620, 12), + ASPEED_PULL_DOWN_PINCONF(U25, SCU630, 12), /* GPIOR3*/ - ASPEED_PULL_DOWN_PINCONF(V26, SCU620, 11), + ASPEED_PULL_DOWN_PINCONF(V26, SCU630, 11), /* GPIOR2 */ - ASPEED_PULL_DOWN_PINCONF(V24, SCU620, 10), + ASPEED_PULL_DOWN_PINCONF(V24, SCU630, 10), /* GPIOR1 */ - ASPEED_PULL_DOWN_PINCONF(U24, SCU620, 9), + ASPEED_PULL_DOWN_PINCONF(U24, SCU630, 9), /* GPIOR0 */ - ASPEED_PULL_DOWN_PINCONF(V25, SCU620, 8), + ASPEED_PULL_DOWN_PINCONF(V25, SCU630, 8), /* GPIOX7 */ ASPEED_PULL_DOWN_PINCONF(AB10, SCU634, 31), diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c index f1962866bb8148b99225fe7464e67ce88a00b0a4..223482584f54f7b21a2b88b437bfd8e42b14a5e1 100644 --- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -205,6 +205,7 @@ static int pinctrl_register_one_pin(struct pinctrl_dev *pctldev, const struct pinctrl_pin_desc *pin) { struct pin_desc *pindesc; + int error; pindesc = pin_desc_get(pctldev, pin->number); if (pindesc) { @@ -226,18 +227,25 @@ static int pinctrl_register_one_pin(struct pinctrl_dev *pctldev, } else { pindesc->name = kasprintf(GFP_KERNEL, "PIN%u", pin->number); if (!pindesc->name) { - kfree(pindesc); - return -ENOMEM; + error = -ENOMEM; + goto failed; } pindesc->dynamic_name = true; } pindesc->drv_data = pin->drv_data; - radix_tree_insert(&pctldev->pin_desc_tree, pin->number, pindesc); + error = radix_tree_insert(&pctldev->pin_desc_tree, pin->number, pindesc); + if (error) + goto failed; + pr_debug("registered pin %d (%s) on %s\n", pin->number, pindesc->name, pctldev->desc->name); return 0; + +failed: + kfree(pindesc); + return error; } static int pinctrl_register_pins(struct pinctrl_dev *pctldev, @@ -2098,13 +2106,7 @@ int pinctrl_enable(struct pinctrl_dev *pctldev) error = pinctrl_claim_hogs(pctldev); if (error) { - dev_err(pctldev->dev, "could not claim hogs: %i\n", - error); - pinctrl_free_pindescs(pctldev, pctldev->desc->pins, - pctldev->desc->npins); - mutex_destroy(&pctldev->mutex); - kfree(pctldev); - + dev_err(pctldev->dev, "could not claim hogs: %i\n", error); return error; } diff --git a/drivers/pinctrl/devicetree.c b/drivers/pinctrl/devicetree.c index 6e0a40962f384ad05688550993c3cfa6d9980a70..5ee746cb81f591ef49ec0fca77048e11db4d20d1 100644 --- a/drivers/pinctrl/devicetree.c +++ b/drivers/pinctrl/devicetree.c @@ -220,14 +220,16 @@ int pinctrl_dt_to_map(struct pinctrl *p, struct pinctrl_dev *pctldev) for (state = 0; ; state++) { /* Retrieve the pinctrl-* property */ propname = kasprintf(GFP_KERNEL, "pinctrl-%d", state); - if (!propname) - return -ENOMEM; + if (!propname) { + ret = -ENOMEM; + goto err; + } prop = of_find_property(np, propname, &size); kfree(propname); if (!prop) { if (state == 0) { - of_node_put(np); - return -ENODEV; + ret = -ENODEV; + goto err; } break; } diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c index 67db79f3805100753c52bbe82d8c7cf018e08500..a0b7b16cb4de3af607fca5c9d4f41ac8a2ee19ff 100644 --- a/drivers/pinctrl/intel/pinctrl-baytrail.c +++ b/drivers/pinctrl/intel/pinctrl-baytrail.c @@ -276,33 +276,33 @@ static const unsigned int byt_score_plt_clk5_pins[] = { 101 }; static const unsigned int byt_score_smbus_pins[] = { 51, 52, 53 }; static const struct intel_pingroup byt_score_groups[] = { - PIN_GROUP("uart1_grp", byt_score_uart1_pins, 1), - PIN_GROUP("uart2_grp", byt_score_uart2_pins, 1), - PIN_GROUP("pwm0_grp", byt_score_pwm0_pins, 1), - PIN_GROUP("pwm1_grp", byt_score_pwm1_pins, 1), - PIN_GROUP("ssp2_grp", byt_score_ssp2_pins, 1), - PIN_GROUP("sio_spi_grp", byt_score_sio_spi_pins, 1), - PIN_GROUP("i2c5_grp", byt_score_i2c5_pins, 1), - PIN_GROUP("i2c6_grp", byt_score_i2c6_pins, 1), - PIN_GROUP("i2c4_grp", byt_score_i2c4_pins, 1), - PIN_GROUP("i2c3_grp", byt_score_i2c3_pins, 1), - PIN_GROUP("i2c2_grp", byt_score_i2c2_pins, 1), - PIN_GROUP("i2c1_grp", byt_score_i2c1_pins, 1), - PIN_GROUP("i2c0_grp", byt_score_i2c0_pins, 1), - PIN_GROUP("ssp0_grp", byt_score_ssp0_pins, 1), - PIN_GROUP("ssp1_grp", byt_score_ssp1_pins, 1), - PIN_GROUP("sdcard_grp", byt_score_sdcard_pins, byt_score_sdcard_mux_values), - PIN_GROUP("sdio_grp", byt_score_sdio_pins, 1), - PIN_GROUP("emmc_grp", byt_score_emmc_pins, 1), - PIN_GROUP("lpc_grp", byt_score_ilb_lpc_pins, 1), - PIN_GROUP("sata_grp", byt_score_sata_pins, 1), - PIN_GROUP("plt_clk0_grp", byt_score_plt_clk0_pins, 1), - PIN_GROUP("plt_clk1_grp", byt_score_plt_clk1_pins, 1), - PIN_GROUP("plt_clk2_grp", byt_score_plt_clk2_pins, 1), - PIN_GROUP("plt_clk3_grp", byt_score_plt_clk3_pins, 1), - PIN_GROUP("plt_clk4_grp", byt_score_plt_clk4_pins, 1), - PIN_GROUP("plt_clk5_grp", byt_score_plt_clk5_pins, 1), - PIN_GROUP("smbus_grp", byt_score_smbus_pins, 1), + PIN_GROUP_GPIO("uart1_grp", byt_score_uart1_pins, 1), + PIN_GROUP_GPIO("uart2_grp", byt_score_uart2_pins, 1), + PIN_GROUP_GPIO("pwm0_grp", byt_score_pwm0_pins, 1), + PIN_GROUP_GPIO("pwm1_grp", byt_score_pwm1_pins, 1), + PIN_GROUP_GPIO("ssp2_grp", byt_score_ssp2_pins, 1), + PIN_GROUP_GPIO("sio_spi_grp", byt_score_sio_spi_pins, 1), + PIN_GROUP_GPIO("i2c5_grp", byt_score_i2c5_pins, 1), + PIN_GROUP_GPIO("i2c6_grp", byt_score_i2c6_pins, 1), + PIN_GROUP_GPIO("i2c4_grp", byt_score_i2c4_pins, 1), + PIN_GROUP_GPIO("i2c3_grp", byt_score_i2c3_pins, 1), + PIN_GROUP_GPIO("i2c2_grp", byt_score_i2c2_pins, 1), + PIN_GROUP_GPIO("i2c1_grp", byt_score_i2c1_pins, 1), + PIN_GROUP_GPIO("i2c0_grp", byt_score_i2c0_pins, 1), + PIN_GROUP_GPIO("ssp0_grp", byt_score_ssp0_pins, 1), + PIN_GROUP_GPIO("ssp1_grp", byt_score_ssp1_pins, 1), + PIN_GROUP_GPIO("sdcard_grp", byt_score_sdcard_pins, byt_score_sdcard_mux_values), + PIN_GROUP_GPIO("sdio_grp", byt_score_sdio_pins, 1), + PIN_GROUP_GPIO("emmc_grp", byt_score_emmc_pins, 1), + PIN_GROUP_GPIO("lpc_grp", byt_score_ilb_lpc_pins, 1), + PIN_GROUP_GPIO("sata_grp", byt_score_sata_pins, 1), + PIN_GROUP_GPIO("plt_clk0_grp", byt_score_plt_clk0_pins, 1), + PIN_GROUP_GPIO("plt_clk1_grp", byt_score_plt_clk1_pins, 1), + PIN_GROUP_GPIO("plt_clk2_grp", byt_score_plt_clk2_pins, 1), + PIN_GROUP_GPIO("plt_clk3_grp", byt_score_plt_clk3_pins, 1), + PIN_GROUP_GPIO("plt_clk4_grp", byt_score_plt_clk4_pins, 1), + PIN_GROUP_GPIO("plt_clk5_grp", byt_score_plt_clk5_pins, 1), + PIN_GROUP_GPIO("smbus_grp", byt_score_smbus_pins, 1), }; static const char * const byt_score_uart_groups[] = { @@ -330,12 +330,14 @@ static const char * const byt_score_plt_clk_groups[] = { }; static const char * const byt_score_smbus_groups[] = { "smbus_grp" }; static const char * const byt_score_gpio_groups[] = { - "uart1_grp", "uart2_grp", "pwm0_grp", "pwm1_grp", "ssp0_grp", - "ssp1_grp", "ssp2_grp", "sio_spi_grp", "i2c0_grp", "i2c1_grp", - "i2c2_grp", "i2c3_grp", "i2c4_grp", "i2c5_grp", "i2c6_grp", - "sdcard_grp", "sdio_grp", "emmc_grp", "lpc_grp", "sata_grp", - "plt_clk0_grp", "plt_clk1_grp", "plt_clk2_grp", "plt_clk3_grp", - "plt_clk4_grp", "plt_clk5_grp", "smbus_grp", + "uart1_grp_gpio", "uart2_grp_gpio", "pwm0_grp_gpio", + "pwm1_grp_gpio", "ssp0_grp_gpio", "ssp1_grp_gpio", "ssp2_grp_gpio", + "sio_spi_grp_gpio", "i2c0_grp_gpio", "i2c1_grp_gpio", "i2c2_grp_gpio", + "i2c3_grp_gpio", "i2c4_grp_gpio", "i2c5_grp_gpio", "i2c6_grp_gpio", + "sdcard_grp_gpio", "sdio_grp_gpio", "emmc_grp_gpio", "lpc_grp_gpio", + "sata_grp_gpio", "plt_clk0_grp_gpio", "plt_clk1_grp_gpio", + "plt_clk2_grp_gpio", "plt_clk3_grp_gpio", "plt_clk4_grp_gpio", + "plt_clk5_grp_gpio", "smbus_grp_gpio", }; static const struct intel_function byt_score_functions[] = { @@ -454,8 +456,8 @@ static const struct intel_pingroup byt_sus_groups[] = { PIN_GROUP("usb_oc_grp_gpio", byt_sus_usb_over_current_pins, byt_sus_usb_over_current_gpio_mode_values), PIN_GROUP("usb_ulpi_grp_gpio", byt_sus_usb_ulpi_pins, byt_sus_usb_ulpi_gpio_mode_values), PIN_GROUP("pcu_spi_grp_gpio", byt_sus_pcu_spi_pins, byt_sus_pcu_spi_gpio_mode_values), - PIN_GROUP("pmu_clk1_grp", byt_sus_pmu_clk1_pins, 1), - PIN_GROUP("pmu_clk2_grp", byt_sus_pmu_clk2_pins, 1), + PIN_GROUP_GPIO("pmu_clk1_grp", byt_sus_pmu_clk1_pins, 1), + PIN_GROUP_GPIO("pmu_clk2_grp", byt_sus_pmu_clk2_pins, 1), }; static const char * const byt_sus_usb_groups[] = { @@ -467,7 +469,7 @@ static const char * const byt_sus_pmu_clk_groups[] = { }; static const char * const byt_sus_gpio_groups[] = { "usb_oc_grp_gpio", "usb_ulpi_grp_gpio", "pcu_spi_grp_gpio", - "pmu_clk1_grp", "pmu_clk2_grp", + "pmu_clk1_grp_gpio", "pmu_clk2_grp_gpio", }; static const struct intel_function byt_sus_functions[] = { diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index 954a4122674029d9c5e19fb58c8fb6838490925c..8542053d4d6d0744431146e7c71464853688aaa0 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -362,7 +362,7 @@ static const char *intel_get_function_name(struct pinctrl_dev *pctldev, { struct intel_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev); - return pctrl->soc->functions[function].name; + return pctrl->soc->functions[function].func.name; } static int intel_get_function_groups(struct pinctrl_dev *pctldev, @@ -372,8 +372,8 @@ static int intel_get_function_groups(struct pinctrl_dev *pctldev, { struct intel_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev); - *groups = pctrl->soc->functions[function].groups; - *ngroups = pctrl->soc->functions[function].ngroups; + *groups = pctrl->soc->functions[function].func.groups; + *ngroups = pctrl->soc->functions[function].func.ngroups; return 0; } diff --git a/drivers/pinctrl/intel/pinctrl-intel.h b/drivers/pinctrl/intel/pinctrl-intel.h index 65628423bf6399bfb851acb61bffdfedd69df00f..0d45063435ebccd81362c955921be0144e1e0f8a 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.h +++ b/drivers/pinctrl/intel/pinctrl-intel.h @@ -36,11 +36,13 @@ struct intel_pingroup { /** * struct intel_function - Description about a function + * @func: Generic data of the pin function (name and groups of pins) * @name: Name of the function * @groups: An array of groups for this function * @ngroups: Number of groups in @groups */ struct intel_function { + struct pinfunction func; const char *name; const char * const *groups; size_t ngroups; @@ -158,11 +160,16 @@ struct intel_community { .modes = __builtin_choose_expr(__builtin_constant_p((m)), NULL, (m)), \ } -#define FUNCTION(n, g) \ - { \ - .name = (n), \ - .groups = (g), \ - .ngroups = ARRAY_SIZE((g)), \ +#define PIN_GROUP_GPIO(n, p, m) \ + PIN_GROUP(n, p, m), \ + PIN_GROUP(n "_gpio", p, 0) + +#define FUNCTION(n, g) \ + { \ + .func = PINCTRL_PINFUNCTION((n), (g), ARRAY_SIZE(g)), \ + .name = (n), \ + .groups = (g), \ + .ngroups = ARRAY_SIZE((g)), \ } /** diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8186.c b/drivers/pinctrl/mediatek/pinctrl-mt8186.c index a02f7c3269707ee9adf3b0dc75706f97289892b6..09edcf47effec521b8843ea44900532f5cb0a2b8 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mt8186.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt8186.c @@ -1198,7 +1198,6 @@ static const struct mtk_pin_reg_calc mt8186_reg_cals[PINCTRL_PIN_REG_MAX] = { [PINCTRL_PIN_REG_DIR] = MTK_RANGE(mt8186_pin_dir_range), [PINCTRL_PIN_REG_DI] = MTK_RANGE(mt8186_pin_di_range), [PINCTRL_PIN_REG_DO] = MTK_RANGE(mt8186_pin_do_range), - [PINCTRL_PIN_REG_SR] = MTK_RANGE(mt8186_pin_dir_range), [PINCTRL_PIN_REG_SMT] = MTK_RANGE(mt8186_pin_smt_range), [PINCTRL_PIN_REG_IES] = MTK_RANGE(mt8186_pin_ies_range), [PINCTRL_PIN_REG_PU] = MTK_RANGE(mt8186_pin_pu_range), diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8192.c b/drivers/pinctrl/mediatek/pinctrl-mt8192.c index 9695f4ec6aba9c72b649141d5d966aff4e379de3..f120268c00f56380055e2a0e2ea4f5d3e7e34234 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mt8192.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt8192.c @@ -1379,7 +1379,6 @@ static const struct mtk_pin_reg_calc mt8192_reg_cals[PINCTRL_PIN_REG_MAX] = { [PINCTRL_PIN_REG_DIR] = MTK_RANGE(mt8192_pin_dir_range), [PINCTRL_PIN_REG_DI] = MTK_RANGE(mt8192_pin_di_range), [PINCTRL_PIN_REG_DO] = MTK_RANGE(mt8192_pin_do_range), - [PINCTRL_PIN_REG_SR] = MTK_RANGE(mt8192_pin_dir_range), [PINCTRL_PIN_REG_SMT] = MTK_RANGE(mt8192_pin_smt_range), [PINCTRL_PIN_REG_IES] = MTK_RANGE(mt8192_pin_ies_range), [PINCTRL_PIN_REG_PU] = MTK_RANGE(mt8192_pin_pu_range), diff --git a/drivers/pinctrl/mediatek/pinctrl-paris.c b/drivers/pinctrl/mediatek/pinctrl-paris.c index ad873bd051b68576e2afc42ef29c01c164df00d6..ee72c6894a5d7e0684cda881812f8d950dc34043 100644 --- a/drivers/pinctrl/mediatek/pinctrl-paris.c +++ b/drivers/pinctrl/mediatek/pinctrl-paris.c @@ -160,20 +160,21 @@ static int mtk_pinconf_get(struct pinctrl_dev *pctldev, err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_SR, &ret); break; case PIN_CONFIG_INPUT_ENABLE: - case PIN_CONFIG_OUTPUT_ENABLE: + err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_IES, &ret); + if (!ret) + err = -EINVAL; + break; + case PIN_CONFIG_OUTPUT: err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_DIR, &ret); if (err) break; - /* CONFIG Current direction return value - * ------------- ----------------- ---------------------- - * OUTPUT_ENABLE output 1 (= HW value) - * input 0 (= HW value) - * INPUT_ENABLE output 0 (= reverse HW value) - * input 1 (= reverse HW value) - */ - if (param == PIN_CONFIG_INPUT_ENABLE) - ret = !ret; + if (!ret) { + err = -EINVAL; + break; + } + + err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_DO, &ret); break; case PIN_CONFIG_INPUT_SCHMITT_ENABLE: err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_DIR, &ret); @@ -188,6 +189,8 @@ static int mtk_pinconf_get(struct pinctrl_dev *pctldev, } err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_SMT, &ret); + if (!ret) + err = -EINVAL; break; case PIN_CONFIG_DRIVE_STRENGTH: if (!hw->soc->drive_get) @@ -276,26 +279,9 @@ static int mtk_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, break; err = hw->soc->bias_set_combo(hw, desc, 0, arg); break; - case PIN_CONFIG_OUTPUT_ENABLE: - err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_SMT, - MTK_DISABLE); - /* Keep set direction to consider the case that a GPIO pin - * does not have SMT control - */ - if (err != -ENOTSUPP) - break; - - err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_DIR, - MTK_OUTPUT); - break; case PIN_CONFIG_INPUT_ENABLE: /* regard all non-zero value as enable */ err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_IES, !!arg); - if (err) - break; - - err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_DIR, - MTK_INPUT); break; case PIN_CONFIG_SLEW_RATE: /* regard all non-zero value as enable */ diff --git a/drivers/pinctrl/meson/pinctrl-meson-a1.c b/drivers/pinctrl/meson/pinctrl-meson-a1.c index 79f5d753d7e1a53df0da9bb0446bf8fdfbd3042c..50a87d9618a8e8e078424db33c7e13a7c7ed1dc6 100644 --- a/drivers/pinctrl/meson/pinctrl-meson-a1.c +++ b/drivers/pinctrl/meson/pinctrl-meson-a1.c @@ -250,7 +250,7 @@ static const unsigned int pdm_dclk_x_pins[] = { GPIOX_10 }; static const unsigned int pdm_din2_a_pins[] = { GPIOA_6 }; static const unsigned int pdm_din1_a_pins[] = { GPIOA_7 }; static const unsigned int pdm_din0_a_pins[] = { GPIOA_8 }; -static const unsigned int pdm_dclk_pins[] = { GPIOA_9 }; +static const unsigned int pdm_dclk_a_pins[] = { GPIOA_9 }; /* gen_clk */ static const unsigned int gen_clk_x_pins[] = { GPIOX_7 }; @@ -591,7 +591,7 @@ static struct meson_pmx_group meson_a1_periphs_groups[] = { GROUP(pdm_din2_a, 3), GROUP(pdm_din1_a, 3), GROUP(pdm_din0_a, 3), - GROUP(pdm_dclk, 3), + GROUP(pdm_dclk_a, 3), GROUP(pwm_c_a, 3), GROUP(pwm_b_a, 3), @@ -755,7 +755,7 @@ static const char * const spi_a_groups[] = { static const char * const pdm_groups[] = { "pdm_din0_x", "pdm_din1_x", "pdm_din2_x", "pdm_dclk_x", "pdm_din2_a", - "pdm_din1_a", "pdm_din0_a", "pdm_dclk", + "pdm_din1_a", "pdm_din0_a", "pdm_dclk_a", }; static const char * const gen_clk_groups[] = { diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.c b/drivers/pinctrl/nomadik/pinctrl-nomadik.c index f7d02513d8cc103f98cdc5752dd0abb17df93020..e79037dc85796691e704d4e222d4f1a634392e54 100644 --- a/drivers/pinctrl/nomadik/pinctrl-nomadik.c +++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.c @@ -1571,8 +1571,10 @@ static int nmk_pmx_set(struct pinctrl_dev *pctldev, unsigned function, * Then mask the pins that need to be sleeping now when we're * switching to the ALT C function. */ - for (i = 0; i < g->grp.npins; i++) - slpm[g->grp.pins[i] / NMK_GPIO_PER_CHIP] &= ~BIT(g->grp.pins[i]); + for (i = 0; i < g->grp.npins; i++) { + unsigned int bit = g->grp.pins[i] % NMK_GPIO_PER_CHIP; + slpm[g->grp.pins[i] / NMK_GPIO_PER_CHIP] &= ~BIT(bit); + } nmk_gpio_glitch_slpm_init(slpm); } diff --git a/drivers/pinctrl/renesas/core.c b/drivers/pinctrl/renesas/core.c index c91102d3f1d1559020a0a31ba4c192b610f8f6eb..1c7f8caf7f7cdd8080887ed25c67bd3c70a4a561 100644 --- a/drivers/pinctrl/renesas/core.c +++ b/drivers/pinctrl/renesas/core.c @@ -921,9 +921,11 @@ static void __init sh_pfc_check_cfg_reg(const char *drvname, sh_pfc_err("reg 0x%x: var_field_width declares %u instead of %u bits\n", cfg_reg->reg, rw, cfg_reg->reg_width); - if (n != cfg_reg->nr_enum_ids) + if (n != cfg_reg->nr_enum_ids) { sh_pfc_err("reg 0x%x: enum_ids[] has %u instead of %u values\n", cfg_reg->reg, cfg_reg->nr_enum_ids, n); + n = cfg_reg->nr_enum_ids; + } check_enum_ids: sh_pfc_check_reg_enums(drvname, cfg_reg->reg, cfg_reg->enum_ids, n); diff --git a/drivers/pinctrl/renesas/pfc-r8a779g0.c b/drivers/pinctrl/renesas/pfc-r8a779g0.c index 43a63a21a6fb5076df9cbe488ac6e67f0bdd1117..acf7664ea835bf3b6d6bf374551257fd96148246 100644 --- a/drivers/pinctrl/renesas/pfc-r8a779g0.c +++ b/drivers/pinctrl/renesas/pfc-r8a779g0.c @@ -2360,6 +2360,30 @@ static const unsigned int scif_clk_mux[] = { SCIF_CLK_MARK, }; +static const unsigned int scif_clk2_pins[] = { + /* SCIF_CLK2 */ + RCAR_GP_PIN(8, 11), +}; +static const unsigned int scif_clk2_mux[] = { + SCIF_CLK2_MARK, +}; + +/* - SSI ------------------------------------------------- */ +static const unsigned int ssi_data_pins[] = { + /* SSI_SD */ + RCAR_GP_PIN(1, 20), +}; +static const unsigned int ssi_data_mux[] = { + SSI_SD_MARK, +}; +static const unsigned int ssi_ctrl_pins[] = { + /* SSI_SCK, SSI_WS */ + RCAR_GP_PIN(1, 18), RCAR_GP_PIN(1, 19), +}; +static const unsigned int ssi_ctrl_mux[] = { + SSI_SCK_MARK, SSI_WS_MARK, +}; + /* - TPU ------------------------------------------------------------------- */ static const unsigned int tpu_to0_pins[] = { /* TPU0TO0 */ @@ -2651,6 +2675,10 @@ static const struct sh_pfc_pin_group pinmux_groups[] = { SH_PFC_PIN_GROUP(scif4_clk), SH_PFC_PIN_GROUP(scif4_ctrl), SH_PFC_PIN_GROUP(scif_clk), + SH_PFC_PIN_GROUP(scif_clk2), + + SH_PFC_PIN_GROUP(ssi_data), + SH_PFC_PIN_GROUP(ssi_ctrl), SH_PFC_PIN_GROUP(tpu_to0), /* suffix might be updated */ SH_PFC_PIN_GROUP(tpu_to0_a), /* suffix might be updated */ @@ -2964,6 +2992,15 @@ static const char * const scif_clk_groups[] = { "scif_clk", }; +static const char * const scif_clk2_groups[] = { + "scif_clk2", +}; + +static const char * const ssi_groups[] = { + "ssi_data", + "ssi_ctrl", +}; + static const char * const tpu_groups[] = { /* suffix might be updated */ "tpu_to0", @@ -3044,6 +3081,9 @@ static const struct sh_pfc_function pinmux_functions[] = { SH_PFC_FUNCTION(scif3), SH_PFC_FUNCTION(scif4), SH_PFC_FUNCTION(scif_clk), + SH_PFC_FUNCTION(scif_clk2), + + SH_PFC_FUNCTION(ssi), SH_PFC_FUNCTION(tpu), diff --git a/drivers/platform/x86/intel/vbtn.c b/drivers/platform/x86/intel/vbtn.c index 8e2b07ed2ce94a2d03e3b7ea7929e6fcfce5594c..224139006a433044a43c33642e91b7165672e2b4 100644 --- a/drivers/platform/x86/intel/vbtn.c +++ b/drivers/platform/x86/intel/vbtn.c @@ -136,8 +136,6 @@ static int intel_vbtn_input_setup(struct platform_device *device) priv->switches_dev->id.bustype = BUS_HOST; if (priv->has_switches) { - detect_tablet_mode(&device->dev); - ret = input_register_device(priv->switches_dev); if (ret) return ret; @@ -200,9 +198,6 @@ static void notify_handler(acpi_handle handle, u32 event, void *context) autorelease = val && (!ke_rel || ke_rel->type == KE_IGNORE); sparse_keymap_report_event(input_dev, event, val, autorelease); - - /* Some devices need this to report further events */ - acpi_evaluate_object(handle, "VBDL", NULL, NULL); } /* @@ -319,6 +314,9 @@ static int intel_vbtn_probe(struct platform_device *device) if (ACPI_FAILURE(status)) dev_err(&device->dev, "Error VBDL failed with ACPI status %d\n", status); } + // Check switches after buttons since VBDL may have side effects. + if (has_switches) + detect_tablet_mode(&device->dev); device_init_wakeup(&device->dev, true); /* diff --git a/drivers/platform/x86/p2sb.c b/drivers/platform/x86/p2sb.c index 17cc4b45e0239b68ea8ea19112ae2d77c6009007..a64f56ddd4a44927f7b6a0ef6e002399bd0f802c 100644 --- a/drivers/platform/x86/p2sb.c +++ b/drivers/platform/x86/p2sb.c @@ -20,9 +20,11 @@ #define P2SBC_HIDE BIT(8) #define P2SB_DEVFN_DEFAULT PCI_DEVFN(31, 1) +#define P2SB_DEVFN_GOLDMONT PCI_DEVFN(13, 0) +#define SPI_DEVFN_GOLDMONT PCI_DEVFN(13, 2) static const struct x86_cpu_id p2sb_cpu_ids[] = { - X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, PCI_DEVFN(13, 0)), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, P2SB_DEVFN_GOLDMONT), {} }; @@ -98,21 +100,12 @@ static void p2sb_scan_and_cache_devfn(struct pci_bus *bus, unsigned int devfn) static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn) { - unsigned int slot, fn; - - if (PCI_FUNC(devfn) == 0) { - /* - * When function number of the P2SB device is zero, scan it and - * other function numbers, and if devices are available, cache - * their BAR0s. - */ - slot = PCI_SLOT(devfn); - for (fn = 0; fn < NR_P2SB_RES_CACHE; fn++) - p2sb_scan_and_cache_devfn(bus, PCI_DEVFN(slot, fn)); - } else { - /* Scan the P2SB device and cache its BAR0 */ - p2sb_scan_and_cache_devfn(bus, devfn); - } + /* Scan the P2SB device and cache its BAR0 */ + p2sb_scan_and_cache_devfn(bus, devfn); + + /* On Goldmont p2sb_bar() also gets called for the SPI controller */ + if (devfn == P2SB_DEVFN_GOLDMONT) + p2sb_scan_and_cache_devfn(bus, SPI_DEVFN_GOLDMONT); if (!p2sb_valid_resource(&p2sb_resources[PCI_FUNC(devfn)].res)) return -ENOENT; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 6edd2e294750e6884ab8680300acf48f50b59a2d..c2fb19af10705ad45ec178de8f89531e7addbda0 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -10511,6 +10511,7 @@ static int convert_dytc_to_profile(int funcmode, int dytcmode, return 0; default: /* Unknown function */ + pr_debug("unknown function 0x%x\n", funcmode); return -EOPNOTSUPP; } return 0; @@ -10696,8 +10697,8 @@ static void dytc_profile_refresh(void) return; perfmode = (output >> DYTC_GET_MODE_BIT) & 0xF; - convert_dytc_to_profile(funcmode, perfmode, &profile); - if (profile != dytc_current_profile) { + err = convert_dytc_to_profile(funcmode, perfmode, &profile); + if (!err && profile != dytc_current_profile) { dytc_current_profile = profile; platform_profile_notify(); } diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 9a92d515abb9bcf4215322267e3fe643f8d8a907..399b97b54dd0fa684e11e960ce81acac0e6abc8c 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -50,7 +50,7 @@ static const struct property_entry chuwi_hi8_air_props[] = { }; static const struct ts_dmi_data chuwi_hi8_air_data = { - .acpi_name = "MSSL1680:00", + .acpi_name = "MSSL1680", .properties = chuwi_hi8_air_props, }; @@ -913,6 +913,32 @@ static const struct ts_dmi_data teclast_tbook11_data = { .properties = teclast_tbook11_props, }; +static const struct property_entry teclast_x16_plus_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 8), + PROPERTY_ENTRY_U32("touchscreen-min-y", 14), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1916), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1264), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl3692-teclast-x16-plus.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + PROPERTY_ENTRY_BOOL("silead,home-button"), + { } +}; + +static const struct ts_dmi_data teclast_x16_plus_data = { + .embedded_fw = { + .name = "silead/gsl3692-teclast-x16-plus.fw", + .prefix = { 0xf0, 0x00, 0x00, 0x00, 0x02, 0x00, 0x00, 0x00 }, + .length = 43560, + .sha256 = { 0x9d, 0xb0, 0x3d, 0xf1, 0x00, 0x3c, 0xb5, 0x25, + 0x62, 0x8a, 0xa0, 0x93, 0x4b, 0xe0, 0x4e, 0x75, + 0xd1, 0x27, 0xb1, 0x65, 0x3c, 0xba, 0xa5, 0x0f, + 0xcd, 0xb4, 0xbe, 0x00, 0xbb, 0xf6, 0x43, 0x29 }, + }, + .acpi_name = "MSSL1680:00", + .properties = teclast_x16_plus_props, +}; + static const struct property_entry teclast_x3_plus_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1980), PROPERTY_ENTRY_U32("touchscreen-size-y", 1500), @@ -1151,6 +1177,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = { DMI_MATCH(DMI_BIOS_VERSION, "CHUWI.D86JLBNR"), }, }, + { + /* Chuwi Vi8 dual-boot (CWI506) */ + .driver_data = (void *)&chuwi_vi8_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Insyde"), + DMI_MATCH(DMI_PRODUCT_NAME, "i86"), + DMI_MATCH(DMI_BIOS_VERSION, "CHUWI2.D86JHBNR02"), + }, + }, { /* Chuwi Vi8 Plus (CWI519) */ .driver_data = (void *)&chuwi_vi8_plus_data, @@ -1567,6 +1602,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_SKU, "E5A6_A1"), }, }, + { + /* Teclast X16 Plus */ + .driver_data = (void *)&teclast_x16_plus_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TECLAST"), + DMI_MATCH(DMI_PRODUCT_NAME, "Default string"), + DMI_MATCH(DMI_PRODUCT_SKU, "D3A5_A1"), + }, + }, { /* Teclast X3 Plus */ .driver_data = (void *)&teclast_x3_plus_data, @@ -1741,7 +1785,7 @@ static void ts_dmi_add_props(struct i2c_client *client) int error; if (has_acpi_companion(dev) && - !strncmp(ts_data->acpi_name, client->name, I2C_NAME_SIZE)) { + strstarts(client->name, ts_data->acpi_name)) { error = device_create_managed_software_node(dev, ts_data->properties, NULL); if (error) dev_err(dev, "failed to add properties: %d\n", error); diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c index 0713a52a25107c96f964b5772f8a0f8973d3a0b0..17b37354e32c0263a65cff95d99f704133a04ce4 100644 --- a/drivers/power/supply/bq27xxx_battery_i2c.c +++ b/drivers/power/supply/bq27xxx_battery_i2c.c @@ -209,7 +209,9 @@ static void bq27xxx_battery_i2c_remove(struct i2c_client *client) { struct bq27xxx_device_info *di = i2c_get_clientdata(client); - free_irq(client->irq, di); + if (client->irq) + free_irq(client->irq, di); + bq27xxx_battery_teardown(di); mutex_lock(&battery_mutex); diff --git a/drivers/power/supply/mt6360_charger.c b/drivers/power/supply/mt6360_charger.c index f1248faf5905815aa2736eb1aedf94aa5a78a6ed..383bf19819dfbf513a278330bf1d2c1ccb1ec677 100644 --- a/drivers/power/supply/mt6360_charger.c +++ b/drivers/power/supply/mt6360_charger.c @@ -591,7 +591,7 @@ static const struct regulator_ops mt6360_chg_otg_ops = { }; static const struct regulator_desc mt6360_otg_rdesc = { - .of_match = "usb-otg-vbus", + .of_match = "usb-otg-vbus-regulator", .name = "usb-otg-vbus", .ops = &mt6360_chg_otg_ops, .owner = THIS_MODULE, diff --git a/drivers/power/supply/rt9455_charger.c b/drivers/power/supply/rt9455_charger.c index 72962286d70459eee3c4f3e35ceda5e823c45796..c5597967a06999d4c5715137d9c657d19c20f86d 100644 --- a/drivers/power/supply/rt9455_charger.c +++ b/drivers/power/supply/rt9455_charger.c @@ -193,6 +193,7 @@ static const int rt9455_voreg_values[] = { 4450000, 4450000, 4450000, 4450000, 4450000, 4450000, 4450000, 4450000 }; +#if IS_ENABLED(CONFIG_USB_PHY) /* * When the charger is in boost mode, REG02[7:2] represent boost output * voltage. @@ -208,6 +209,7 @@ static const int rt9455_boost_voltage_values[] = { 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, }; +#endif /* REG07[3:0] (VMREG) in uV */ static const int rt9455_vmreg_values[] = { diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c index 9193c3b8edebe9bf0cebc9a0d9d7084518a91c2d..ae7ee611978ba1ad44b44e92b92a254673658969 100644 --- a/drivers/powercap/dtpm_cpu.c +++ b/drivers/powercap/dtpm_cpu.c @@ -219,7 +219,7 @@ static int __dtpm_cpu_setup(int cpu, struct dtpm *parent) ret = freq_qos_add_request(&policy->constraints, &dtpm_cpu->qos_req, FREQ_QOS_MAX, pd->table[pd->nr_perf_states - 1].frequency); - if (ret) + if (ret < 0) goto out_dtpm_unregister; cpufreq_cpu_put(policy); diff --git a/drivers/pwm/pwm-atmel-hlcdc.c b/drivers/pwm/pwm-atmel-hlcdc.c index a43b2babc809384002fef48196f3ad73def05924..3e9c94a8d7f72fd6612ad633db2ca5fa185e90b2 100644 --- a/drivers/pwm/pwm-atmel-hlcdc.c +++ b/drivers/pwm/pwm-atmel-hlcdc.c @@ -38,11 +38,11 @@ static inline struct atmel_hlcdc_pwm *to_atmel_hlcdc_pwm(struct pwm_chip *chip) return container_of(chip, struct atmel_hlcdc_pwm, chip); } -static int atmel_hlcdc_pwm_apply(struct pwm_chip *c, struct pwm_device *pwm, +static int atmel_hlcdc_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, const struct pwm_state *state) { - struct atmel_hlcdc_pwm *chip = to_atmel_hlcdc_pwm(c); - struct atmel_hlcdc *hlcdc = chip->hlcdc; + struct atmel_hlcdc_pwm *atmel = to_atmel_hlcdc_pwm(chip); + struct atmel_hlcdc *hlcdc = atmel->hlcdc; unsigned int status; int ret; @@ -54,7 +54,7 @@ static int atmel_hlcdc_pwm_apply(struct pwm_chip *c, struct pwm_device *pwm, u32 pwmcfg; int pres; - if (!chip->errata || !chip->errata->slow_clk_erratum) { + if (!atmel->errata || !atmel->errata->slow_clk_erratum) { clk_freq = clk_get_rate(new_clk); if (!clk_freq) return -EINVAL; @@ -64,7 +64,7 @@ static int atmel_hlcdc_pwm_apply(struct pwm_chip *c, struct pwm_device *pwm, } /* Errata: cannot use slow clk on some IP revisions */ - if ((chip->errata && chip->errata->slow_clk_erratum) || + if ((atmel->errata && atmel->errata->slow_clk_erratum) || clk_period_ns > state->period) { new_clk = hlcdc->sys_clk; clk_freq = clk_get_rate(new_clk); @@ -77,8 +77,8 @@ static int atmel_hlcdc_pwm_apply(struct pwm_chip *c, struct pwm_device *pwm, for (pres = 0; pres <= ATMEL_HLCDC_PWMPS_MAX; pres++) { /* Errata: cannot divide by 1 on some IP revisions */ - if (!pres && chip->errata && - chip->errata->div1_clk_erratum) + if (!pres && atmel->errata && + atmel->errata->div1_clk_erratum) continue; if ((clk_period_ns << pres) >= state->period) @@ -90,7 +90,7 @@ static int atmel_hlcdc_pwm_apply(struct pwm_chip *c, struct pwm_device *pwm, pwmcfg = ATMEL_HLCDC_PWMPS(pres); - if (new_clk != chip->cur_clk) { + if (new_clk != atmel->cur_clk) { u32 gencfg = 0; int ret; @@ -98,8 +98,8 @@ static int atmel_hlcdc_pwm_apply(struct pwm_chip *c, struct pwm_device *pwm, if (ret) return ret; - clk_disable_unprepare(chip->cur_clk); - chip->cur_clk = new_clk; + clk_disable_unprepare(atmel->cur_clk); + atmel->cur_clk = new_clk; if (new_clk == hlcdc->sys_clk) gencfg = ATMEL_HLCDC_CLKPWMSEL; @@ -160,8 +160,8 @@ static int atmel_hlcdc_pwm_apply(struct pwm_chip *c, struct pwm_device *pwm, if (ret) return ret; - clk_disable_unprepare(chip->cur_clk); - chip->cur_clk = NULL; + clk_disable_unprepare(atmel->cur_clk); + atmel->cur_clk = NULL; } return 0; @@ -183,31 +183,32 @@ static const struct atmel_hlcdc_pwm_errata atmel_hlcdc_pwm_sama5d3_errata = { #ifdef CONFIG_PM_SLEEP static int atmel_hlcdc_pwm_suspend(struct device *dev) { - struct atmel_hlcdc_pwm *chip = dev_get_drvdata(dev); + struct atmel_hlcdc_pwm *atmel = dev_get_drvdata(dev); /* Keep the periph clock enabled if the PWM is still running. */ - if (pwm_is_enabled(&chip->chip.pwms[0])) - clk_disable_unprepare(chip->hlcdc->periph_clk); + if (!pwm_is_enabled(&atmel->chip.pwms[0])) + clk_disable_unprepare(atmel->hlcdc->periph_clk); return 0; } static int atmel_hlcdc_pwm_resume(struct device *dev) { - struct atmel_hlcdc_pwm *chip = dev_get_drvdata(dev); + struct atmel_hlcdc_pwm *atmel = dev_get_drvdata(dev); struct pwm_state state; int ret; - pwm_get_state(&chip->chip.pwms[0], &state); + pwm_get_state(&atmel->chip.pwms[0], &state); /* Re-enable the periph clock it was stopped during suspend. */ if (!state.enabled) { - ret = clk_prepare_enable(chip->hlcdc->periph_clk); + ret = clk_prepare_enable(atmel->hlcdc->periph_clk); if (ret) return ret; } - return atmel_hlcdc_pwm_apply(&chip->chip, &chip->chip.pwms[0], &state); + return atmel_hlcdc_pwm_apply(&atmel->chip, &atmel->chip.pwms[0], + &state); } #endif @@ -244,14 +245,14 @@ static int atmel_hlcdc_pwm_probe(struct platform_device *pdev) { const struct of_device_id *match; struct device *dev = &pdev->dev; - struct atmel_hlcdc_pwm *chip; + struct atmel_hlcdc_pwm *atmel; struct atmel_hlcdc *hlcdc; int ret; hlcdc = dev_get_drvdata(dev->parent); - chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL); - if (!chip) + atmel = devm_kzalloc(dev, sizeof(*atmel), GFP_KERNEL); + if (!atmel) return -ENOMEM; ret = clk_prepare_enable(hlcdc->periph_clk); @@ -260,33 +261,31 @@ static int atmel_hlcdc_pwm_probe(struct platform_device *pdev) match = of_match_node(atmel_hlcdc_dt_ids, dev->parent->of_node); if (match) - chip->errata = match->data; + atmel->errata = match->data; - chip->hlcdc = hlcdc; - chip->chip.ops = &atmel_hlcdc_pwm_ops; - chip->chip.dev = dev; - chip->chip.npwm = 1; + atmel->hlcdc = hlcdc; + atmel->chip.ops = &atmel_hlcdc_pwm_ops; + atmel->chip.dev = dev; + atmel->chip.npwm = 1; - ret = pwmchip_add(&chip->chip); + ret = pwmchip_add(&atmel->chip); if (ret) { clk_disable_unprepare(hlcdc->periph_clk); return ret; } - platform_set_drvdata(pdev, chip); + platform_set_drvdata(pdev, atmel); return 0; } -static int atmel_hlcdc_pwm_remove(struct platform_device *pdev) +static void atmel_hlcdc_pwm_remove(struct platform_device *pdev) { - struct atmel_hlcdc_pwm *chip = platform_get_drvdata(pdev); + struct atmel_hlcdc_pwm *atmel = platform_get_drvdata(pdev); - pwmchip_remove(&chip->chip); + pwmchip_remove(&atmel->chip); - clk_disable_unprepare(chip->hlcdc->periph_clk); - - return 0; + clk_disable_unprepare(atmel->hlcdc->periph_clk); } static const struct of_device_id atmel_hlcdc_pwm_dt_ids[] = { @@ -301,7 +300,7 @@ static struct platform_driver atmel_hlcdc_pwm_driver = { .pm = &atmel_hlcdc_pwm_pm_ops, }, .probe = atmel_hlcdc_pwm_probe, - .remove = atmel_hlcdc_pwm_remove, + .remove_new = atmel_hlcdc_pwm_remove, }; module_platform_driver(atmel_hlcdc_pwm_driver); diff --git a/drivers/pwm/pwm-img.c b/drivers/pwm/pwm-img.c index 0fccf061ab958852b03f209dd133b5db735b022a..8ce6c453adf071124692928032968ffc845bd327 100644 --- a/drivers/pwm/pwm-img.c +++ b/drivers/pwm/pwm-img.c @@ -289,9 +289,9 @@ static int img_pwm_probe(struct platform_device *pdev) return PTR_ERR(imgchip->sys_clk); } - imgchip->pwm_clk = devm_clk_get(&pdev->dev, "imgchip"); + imgchip->pwm_clk = devm_clk_get(&pdev->dev, "pwm"); if (IS_ERR(imgchip->pwm_clk)) { - dev_err(&pdev->dev, "failed to get imgchip clock\n"); + dev_err(&pdev->dev, "failed to get pwm clock\n"); return PTR_ERR(imgchip->pwm_clk); } diff --git a/drivers/pwm/pwm-sti.c b/drivers/pwm/pwm-sti.c index 652fdb8dc7bfa868ca584ae76a499747ec75bc9c..0a7920cbd494997011ea8269ea04e8e19e829af4 100644 --- a/drivers/pwm/pwm-sti.c +++ b/drivers/pwm/pwm-sti.c @@ -395,8 +395,17 @@ out: static int sti_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, const struct pwm_state *state) { + struct sti_pwm_chip *pc = to_sti_pwmchip(chip); + struct sti_pwm_compat_data *cdata = pc->cdata; + struct device *dev = pc->dev; int err; + if (pwm->hwpwm >= cdata->pwm_num_devs) { + dev_err(dev, "device %u is not valid for pwm mode\n", + pwm->hwpwm); + return -EINVAL; + } + if (state->polarity != PWM_POLARITY_NORMAL) return -EINVAL; @@ -647,7 +656,7 @@ static int sti_pwm_probe(struct platform_device *pdev) pc->chip.dev = dev; pc->chip.ops = &sti_pwm_ops; - pc->chip.npwm = pc->cdata->pwm_num_devs; + pc->chip.npwm = max(cdata->pwm_num_devs, cdata->cpt_num_devs); for (i = 0; i < cdata->cpt_num_devs; i++) { struct sti_cpt_ddata *ddata = &cdata->ddata[i]; diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index c8702011b7613a435fa92580f8875dac3f4dd302..ff11f37e28c719786446214c0ecc79da01ed3051 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1916,19 +1916,24 @@ static struct regulator *create_regulator(struct regulator_dev *rdev, } } - if (err != -EEXIST) + if (err != -EEXIST) { regulator->debugfs = debugfs_create_dir(supply_name, rdev->debugfs); - if (IS_ERR(regulator->debugfs)) - rdev_dbg(rdev, "Failed to create debugfs directory\n"); + if (IS_ERR(regulator->debugfs)) { + rdev_dbg(rdev, "Failed to create debugfs directory\n"); + regulator->debugfs = NULL; + } + } - debugfs_create_u32("uA_load", 0444, regulator->debugfs, - ®ulator->uA_load); - debugfs_create_u32("min_uV", 0444, regulator->debugfs, - ®ulator->voltage[PM_SUSPEND_ON].min_uV); - debugfs_create_u32("max_uV", 0444, regulator->debugfs, - ®ulator->voltage[PM_SUSPEND_ON].max_uV); - debugfs_create_file("constraint_flags", 0444, regulator->debugfs, - regulator, &constraint_flags_fops); + if (regulator->debugfs) { + debugfs_create_u32("uA_load", 0444, regulator->debugfs, + ®ulator->uA_load); + debugfs_create_u32("min_uV", 0444, regulator->debugfs, + ®ulator->voltage[PM_SUSPEND_ON].min_uV); + debugfs_create_u32("max_uV", 0444, regulator->debugfs, + ®ulator->voltage[PM_SUSPEND_ON].max_uV); + debugfs_create_file("constraint_flags", 0444, regulator->debugfs, + regulator, &constraint_flags_fops); + } /* * Check now if the regulator is an always on regulator - if diff --git a/drivers/regulator/mt6360-regulator.c b/drivers/regulator/mt6360-regulator.c index 4d34be94d166359341a581ba60a1a1693dbf4940..fc464a4450dc5683f9afdb50638c766ddb385875 100644 --- a/drivers/regulator/mt6360-regulator.c +++ b/drivers/regulator/mt6360-regulator.c @@ -319,15 +319,15 @@ static unsigned int mt6360_regulator_of_map_mode(unsigned int hw_mode) } } -#define MT6360_REGULATOR_DESC(_name, _sname, ereg, emask, vreg, vmask, \ - mreg, mmask, streg, stmask, vranges, \ - vcnts, offon_delay, irq_tbls) \ +#define MT6360_REGULATOR_DESC(match, _name, _sname, ereg, emask, vreg, \ + vmask, mreg, mmask, streg, stmask, \ + vranges, vcnts, offon_delay, irq_tbls) \ { \ .desc = { \ .name = #_name, \ .supply_name = #_sname, \ .id = MT6360_REGULATOR_##_name, \ - .of_match = of_match_ptr(#_name), \ + .of_match = of_match_ptr(match), \ .regulators_node = of_match_ptr("regulator"), \ .of_map_mode = mt6360_regulator_of_map_mode, \ .owner = THIS_MODULE, \ @@ -351,21 +351,29 @@ static unsigned int mt6360_regulator_of_map_mode(unsigned int hw_mode) } static const struct mt6360_regulator_desc mt6360_regulator_descs[] = { - MT6360_REGULATOR_DESC(BUCK1, BUCK1_VIN, 0x117, 0x40, 0x110, 0xff, 0x117, 0x30, 0x117, 0x04, + MT6360_REGULATOR_DESC("buck1", BUCK1, BUCK1_VIN, + 0x117, 0x40, 0x110, 0xff, 0x117, 0x30, 0x117, 0x04, buck_vout_ranges, 256, 0, buck1_irq_tbls), - MT6360_REGULATOR_DESC(BUCK2, BUCK2_VIN, 0x127, 0x40, 0x120, 0xff, 0x127, 0x30, 0x127, 0x04, + MT6360_REGULATOR_DESC("buck2", BUCK2, BUCK2_VIN, + 0x127, 0x40, 0x120, 0xff, 0x127, 0x30, 0x127, 0x04, buck_vout_ranges, 256, 0, buck2_irq_tbls), - MT6360_REGULATOR_DESC(LDO6, LDO_VIN3, 0x137, 0x40, 0x13B, 0xff, 0x137, 0x30, 0x137, 0x04, + MT6360_REGULATOR_DESC("ldo6", LDO6, LDO_VIN3, + 0x137, 0x40, 0x13B, 0xff, 0x137, 0x30, 0x137, 0x04, ldo_vout_ranges1, 256, 0, ldo6_irq_tbls), - MT6360_REGULATOR_DESC(LDO7, LDO_VIN3, 0x131, 0x40, 0x135, 0xff, 0x131, 0x30, 0x131, 0x04, + MT6360_REGULATOR_DESC("ldo7", LDO7, LDO_VIN3, + 0x131, 0x40, 0x135, 0xff, 0x131, 0x30, 0x131, 0x04, ldo_vout_ranges1, 256, 0, ldo7_irq_tbls), - MT6360_REGULATOR_DESC(LDO1, LDO_VIN1, 0x217, 0x40, 0x21B, 0xff, 0x217, 0x30, 0x217, 0x04, + MT6360_REGULATOR_DESC("ldo1", LDO1, LDO_VIN1, + 0x217, 0x40, 0x21B, 0xff, 0x217, 0x30, 0x217, 0x04, ldo_vout_ranges2, 256, 0, ldo1_irq_tbls), - MT6360_REGULATOR_DESC(LDO2, LDO_VIN1, 0x211, 0x40, 0x215, 0xff, 0x211, 0x30, 0x211, 0x04, + MT6360_REGULATOR_DESC("ldo2", LDO2, LDO_VIN1, + 0x211, 0x40, 0x215, 0xff, 0x211, 0x30, 0x211, 0x04, ldo_vout_ranges2, 256, 0, ldo2_irq_tbls), - MT6360_REGULATOR_DESC(LDO3, LDO_VIN1, 0x205, 0x40, 0x209, 0xff, 0x205, 0x30, 0x205, 0x04, + MT6360_REGULATOR_DESC("ldo3", LDO3, LDO_VIN1, + 0x205, 0x40, 0x209, 0xff, 0x205, 0x30, 0x205, 0x04, ldo_vout_ranges2, 256, 100, ldo3_irq_tbls), - MT6360_REGULATOR_DESC(LDO5, LDO_VIN2, 0x20B, 0x40, 0x20F, 0x7f, 0x20B, 0x30, 0x20B, 0x04, + MT6360_REGULATOR_DESC("ldo5", LDO5, LDO_VIN2, + 0x20B, 0x40, 0x20F, 0x7f, 0x20B, 0x30, 0x20B, 0x04, ldo_vout_ranges3, 128, 100, ldo5_irq_tbls), }; diff --git a/drivers/regulator/pwm-regulator.c b/drivers/regulator/pwm-regulator.c index b9eeaff1c661507ca3cbc40c4da7c5c91e5125a8..925e486f73a6d8d69d197d482ca66efee6dac6ca 100644 --- a/drivers/regulator/pwm-regulator.c +++ b/drivers/regulator/pwm-regulator.c @@ -158,6 +158,9 @@ static int pwm_regulator_get_voltage(struct regulator_dev *rdev) pwm_get_state(drvdata->pwm, &pstate); voltage = pwm_get_relative_duty_cycle(&pstate, duty_unit); + if (voltage < min(max_uV_duty, min_uV_duty) || + voltage > max(max_uV_duty, min_uV_duty)) + return -ENOTRECOVERABLE; /* * The dutycycle for min_uV might be greater than the one for max_uV. diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig index 1660197866531d79dc31d7cef0b011ae1c4343d9..d93113b6ffaa10081fe0852c765ffd860cd298bd 100644 --- a/drivers/remoteproc/Kconfig +++ b/drivers/remoteproc/Kconfig @@ -313,7 +313,7 @@ config ST_SLIM_REMOTEPROC config STM32_RPROC tristate "STM32 remoteproc support" - depends on ARCH_STM32 + depends on ARCH_STM32 || COMPILE_TEST depends on REMOTEPROC select MAILBOX help diff --git a/drivers/remoteproc/mtk_scp.c b/drivers/remoteproc/mtk_scp.c index d421a2ccaa1ea78e005a0012a157bb4db0644d76..ffec5299b5c1d0ea9ab4f50fe62247a5bebfbb2f 100644 --- a/drivers/remoteproc/mtk_scp.c +++ b/drivers/remoteproc/mtk_scp.c @@ -126,7 +126,7 @@ static int scp_elf_read_ipi_buf_addr(struct mtk_scp *scp, static int scp_ipi_init(struct mtk_scp *scp, const struct firmware *fw) { int ret; - size_t offset; + size_t buf_sz, offset; /* read the ipi buf addr from FW itself first */ ret = scp_elf_read_ipi_buf_addr(scp, fw, &offset); @@ -138,6 +138,14 @@ static int scp_ipi_init(struct mtk_scp *scp, const struct firmware *fw) } dev_info(scp->dev, "IPI buf addr %#010zx\n", offset); + /* Make sure IPI buffer fits in the L2TCM range assigned to this core */ + buf_sz = sizeof(*scp->recv_buf) + sizeof(*scp->send_buf); + + if (scp->sram_size < buf_sz + offset) { + dev_err(scp->dev, "IPI buffer does not fit in SRAM.\n"); + return -EOVERFLOW; + } + scp->recv_buf = (struct mtk_share_obj __iomem *) (scp->sram_base + offset); scp->send_buf = (struct mtk_share_obj __iomem *) diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c index 0e95525c1158156cf76b1cb71f78e582ddc74eeb..ab5e4f02ab2257d20287dc15e9127931ce1992aa 100644 --- a/drivers/remoteproc/remoteproc_virtio.c +++ b/drivers/remoteproc/remoteproc_virtio.c @@ -351,6 +351,9 @@ static void rproc_virtio_dev_release(struct device *dev) kfree(vdev); + of_reserved_mem_device_release(&rvdev->pdev->dev); + dma_release_coherent_memory(&rvdev->pdev->dev); + put_device(&rvdev->pdev->dev); } @@ -584,9 +587,6 @@ static int rproc_virtio_remove(struct platform_device *pdev) rproc_remove_subdev(rproc, &rvdev->subdev); rproc_remove_rvdev(rvdev); - of_reserved_mem_device_release(&pdev->dev); - dma_release_coherent_memory(&pdev->dev); - put_device(&rproc->dev); return 0; diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c index 8746cbb1f168d11d3ad6929903559b26139bc73a..74da0393172c5a7822f404e8a4eec4d42e74af88 100644 --- a/drivers/remoteproc/stm32_rproc.c +++ b/drivers/remoteproc/stm32_rproc.c @@ -118,10 +118,10 @@ static int stm32_rproc_mem_alloc(struct rproc *rproc, struct device *dev = rproc->dev.parent; void *va; - dev_dbg(dev, "map memory: %pa+%x\n", &mem->dma, mem->len); - va = ioremap_wc(mem->dma, mem->len); + dev_dbg(dev, "map memory: %pad+%zx\n", &mem->dma, mem->len); + va = (__force void *)ioremap_wc(mem->dma, mem->len); if (IS_ERR_OR_NULL(va)) { - dev_err(dev, "Unable to map memory region: %pa+%x\n", + dev_err(dev, "Unable to map memory region: %pad+0x%zx\n", &mem->dma, mem->len); return -ENOMEM; } @@ -136,7 +136,7 @@ static int stm32_rproc_mem_release(struct rproc *rproc, struct rproc_mem_entry *mem) { dev_dbg(rproc->dev.parent, "unmap memory: %pa\n", &mem->dma); - iounmap(mem->va); + iounmap((__force __iomem void *)mem->va); return 0; } @@ -627,7 +627,7 @@ stm32_rproc_get_loaded_rsc_table(struct rproc *rproc, size_t *table_sz) ddata->rsc_va = devm_ioremap_wc(dev, rsc_pa, RSC_TBL_SIZE); if (IS_ERR_OR_NULL(ddata->rsc_va)) { - dev_err(dev, "Unable to map memory region: %pa+%zx\n", + dev_err(dev, "Unable to map memory region: %pa+%x\n", &rsc_pa, RSC_TBL_SIZE); ddata->rsc_va = NULL; return ERR_PTR(-ENOMEM); @@ -641,7 +641,7 @@ done: * entire area by overwriting it with the initial values stored in rproc->clean_table. */ *table_sz = RSC_TBL_SIZE; - return (struct resource_table *)ddata->rsc_va; + return (__force struct resource_table *)ddata->rsc_va; } static const struct rproc_ops st_rproc_ops = { @@ -889,7 +889,7 @@ static int stm32_rproc_remove(struct platform_device *pdev) return 0; } -static int __maybe_unused stm32_rproc_suspend(struct device *dev) +static int stm32_rproc_suspend(struct device *dev) { struct rproc *rproc = dev_get_drvdata(dev); struct stm32_rproc *ddata = rproc->priv; @@ -900,7 +900,7 @@ static int __maybe_unused stm32_rproc_suspend(struct device *dev) return 0; } -static int __maybe_unused stm32_rproc_resume(struct device *dev) +static int stm32_rproc_resume(struct device *dev) { struct rproc *rproc = dev_get_drvdata(dev); struct stm32_rproc *ddata = rproc->priv; @@ -911,16 +911,16 @@ static int __maybe_unused stm32_rproc_resume(struct device *dev) return 0; } -static SIMPLE_DEV_PM_OPS(stm32_rproc_pm_ops, - stm32_rproc_suspend, stm32_rproc_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(stm32_rproc_pm_ops, + stm32_rproc_suspend, stm32_rproc_resume); static struct platform_driver stm32_rproc_driver = { .probe = stm32_rproc_probe, .remove = stm32_rproc_remove, .driver = { .name = "stm32-rproc", - .pm = &stm32_rproc_pm_ops, - .of_match_table = of_match_ptr(stm32_rproc_match), + .pm = pm_ptr(&stm32_rproc_pm_ops), + .of_match_table = stm32_rproc_match, }, }; module_platform_driver(stm32_rproc_driver); diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index 50d3af36c3da4ef2a4b73c7f941a3a68015ff6f6..f975b1c1e5de10f7b3ca49b9b212f429cdb2ea7d 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -1854,7 +1854,8 @@ config RTC_DRV_MT2712 config RTC_DRV_MT6397 tristate "MediaTek PMIC based RTC" - depends on MFD_MT6397 || (COMPILE_TEST && IRQ_DOMAIN) + depends on MFD_MT6397 || COMPILE_TEST + select IRQ_DOMAIN help This selects the MediaTek(R) RTC driver. RTC is part of MediaTek MT6397 PMIC. You should enable MT6397 PMIC MFD before select diff --git a/drivers/rtc/lib_test.c b/drivers/rtc/lib_test.c index d5caf36c56cdcfdfdc22537de70cd5ab44b1644c..225c859d6da550a8cb44c3d2446f3d433c9716e3 100644 --- a/drivers/rtc/lib_test.c +++ b/drivers/rtc/lib_test.c @@ -54,7 +54,7 @@ static void rtc_time64_to_tm_test_date_range(struct kunit *test) days = div_s64(secs, 86400); - #define FAIL_MSG "%d/%02d/%02d (%2d) : %ld", \ + #define FAIL_MSG "%d/%02d/%02d (%2d) : %lld", \ year, month, mday, yday, days KUNIT_ASSERT_EQ_MSG(test, year - 1900, result.tm_year, FAIL_MSG); diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index f207de4a87a0fb2591bcf4f80837eb73ffbc6872..341d65acd715d677bd97a097712cb9944885fef2 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -8,9 +8,6 @@ * Copyright IBM Corp. 1999, 2009 */ -#define KMSG_COMPONENT "dasd" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt - #include #include #include @@ -73,7 +70,8 @@ static void dasd_profile_init(struct dasd_profile *, struct dentry *); static void dasd_profile_exit(struct dasd_profile *); static void dasd_hosts_init(struct dentry *, struct dasd_device *); static void dasd_hosts_exit(struct dasd_device *); - +static int dasd_handle_autoquiesce(struct dasd_device *, struct dasd_ccw_req *, + unsigned int); /* * SECTION: Operations on the device structure. */ @@ -2327,7 +2325,7 @@ static int _dasd_sleep_on(struct dasd_ccw_req *maincqr, int interruptible) /* Non-temporary stop condition will trigger fail fast */ if (device->stopped & ~DASD_STOPPED_PENDING && test_bit(DASD_CQR_FLAGS_FAILFAST, &cqr->flags) && - (!dasd_eer_enabled(device))) { + !dasd_eer_enabled(device) && device->aq_mask == 0) { cqr->status = DASD_CQR_FAILED; cqr->intrc = -ENOLINK; continue; @@ -2803,20 +2801,18 @@ restart: dasd_log_sense(cqr, &cqr->irb); } - /* First of all call extended error reporting. */ - if (dasd_eer_enabled(base) && - cqr->status == DASD_CQR_FAILED) { - dasd_eer_write(base, cqr, DASD_EER_FATALERROR); - - /* restart request */ + /* + * First call extended error reporting and check for autoquiesce + */ + spin_lock_irqsave(get_ccwdev_lock(base->cdev), flags); + if (cqr->status == DASD_CQR_FAILED && + dasd_handle_autoquiesce(base, cqr, DASD_EER_FATALERROR)) { cqr->status = DASD_CQR_FILLED; cqr->retries = 255; - spin_lock_irqsave(get_ccwdev_lock(base->cdev), flags); - dasd_device_set_stop_bits(base, DASD_STOPPED_QUIESCE); - spin_unlock_irqrestore(get_ccwdev_lock(base->cdev), - flags); + spin_unlock_irqrestore(get_ccwdev_lock(base->cdev), flags); goto restart; } + spin_unlock_irqrestore(get_ccwdev_lock(base->cdev), flags); /* Process finished ERP request. */ if (cqr->refers) { @@ -2858,7 +2854,7 @@ static void __dasd_block_start_head(struct dasd_block *block) /* Non-temporary stop condition will trigger fail fast */ if (block->base->stopped & ~DASD_STOPPED_PENDING && test_bit(DASD_CQR_FLAGS_FAILFAST, &cqr->flags) && - (!dasd_eer_enabled(block->base))) { + !dasd_eer_enabled(block->base) && block->base->aq_mask == 0) { cqr->status = DASD_CQR_FAILED; cqr->intrc = -ENOLINK; dasd_schedule_block_bh(block); @@ -3391,8 +3387,7 @@ static void dasd_generic_auto_online(void *data, async_cookie_t cookie) ret = ccw_device_set_online(cdev); if (ret) - pr_warn("%s: Setting the DASD online failed with rc=%d\n", - dev_name(&cdev->dev), ret); + dev_warn(&cdev->dev, "Setting the DASD online failed with rc=%d\n", ret); } /* @@ -3479,8 +3474,11 @@ int dasd_generic_set_online(struct ccw_device *cdev, { struct dasd_discipline *discipline; struct dasd_device *device; + struct device *dev; int rc; + dev = &cdev->dev; + /* first online clears initial online feature flag */ dasd_set_feature(cdev, DASD_FEATURE_INITIAL_ONLINE, 0); device = dasd_create_device(cdev); @@ -3493,11 +3491,10 @@ int dasd_generic_set_online(struct ccw_device *cdev, /* Try to load the required module. */ rc = request_module(DASD_DIAG_MOD); if (rc) { - pr_warn("%s Setting the DASD online failed " - "because the required module %s " - "could not be loaded (rc=%d)\n", - dev_name(&cdev->dev), DASD_DIAG_MOD, - rc); + dev_warn(dev, "Setting the DASD online failed " + "because the required module %s " + "could not be loaded (rc=%d)\n", + DASD_DIAG_MOD, rc); dasd_delete_device(device); return -ENODEV; } @@ -3505,8 +3502,7 @@ int dasd_generic_set_online(struct ccw_device *cdev, /* Module init could have failed, so check again here after * request_module(). */ if (!dasd_diag_discipline_pointer) { - pr_warn("%s Setting the DASD online failed because of missing DIAG discipline\n", - dev_name(&cdev->dev)); + dev_warn(dev, "Setting the DASD online failed because of missing DIAG discipline\n"); dasd_delete_device(device); return -ENODEV; } @@ -3516,37 +3512,33 @@ int dasd_generic_set_online(struct ccw_device *cdev, dasd_delete_device(device); return -EINVAL; } + device->base_discipline = base_discipline; if (!try_module_get(discipline->owner)) { - module_put(base_discipline->owner); dasd_delete_device(device); return -EINVAL; } - device->base_discipline = base_discipline; device->discipline = discipline; /* check_device will allocate block device if necessary */ rc = discipline->check_device(device); if (rc) { - pr_warn("%s Setting the DASD online with discipline %s failed with rc=%i\n", - dev_name(&cdev->dev), discipline->name, rc); - module_put(discipline->owner); - module_put(base_discipline->owner); + dev_warn(dev, "Setting the DASD online with discipline %s failed with rc=%i\n", + discipline->name, rc); dasd_delete_device(device); return rc; } dasd_set_target_state(device, DASD_STATE_ONLINE); if (device->state <= DASD_STATE_KNOWN) { - pr_warn("%s Setting the DASD online failed because of a missing discipline\n", - dev_name(&cdev->dev)); + dev_warn(dev, "Setting the DASD online failed because of a missing discipline\n"); rc = -ENODEV; dasd_set_target_state(device, DASD_STATE_NEW); if (device->block) dasd_free_block(device->block); dasd_delete_device(device); - } else - pr_debug("dasd_generic device %s found\n", - dev_name(&cdev->dev)); + } else { + dev_dbg(dev, "dasd_generic device found\n"); + } wait_event(dasd_init_waitq, _wait_for_device(device)); @@ -3557,10 +3549,13 @@ EXPORT_SYMBOL_GPL(dasd_generic_set_online); int dasd_generic_set_offline(struct ccw_device *cdev) { + int max_count, open_count, rc; struct dasd_device *device; struct dasd_block *block; - int max_count, open_count, rc; unsigned long flags; + struct device *dev; + + dev = &cdev->dev; rc = 0; spin_lock_irqsave(get_ccwdev_lock(cdev), flags); @@ -3581,11 +3576,10 @@ int dasd_generic_set_offline(struct ccw_device *cdev) open_count = atomic_read(&device->block->open_count); if (open_count > max_count) { if (open_count > 0) - pr_warn("%s: The DASD cannot be set offline with open count %i\n", - dev_name(&cdev->dev), open_count); + dev_warn(dev, "The DASD cannot be set offline with open count %i\n", + open_count); else - pr_warn("%s: The DASD cannot be set offline while it is in use\n", - dev_name(&cdev->dev)); + dev_warn(dev, "The DASD cannot be set offline while it is in use\n"); rc = -EBUSY; goto out_err; } @@ -3682,8 +3676,8 @@ int dasd_generic_last_path_gone(struct dasd_device *device) dev_warn(&device->cdev->dev, "No operational channel path is left " "for the device\n"); DBF_DEV_EVENT(DBF_WARNING, device, "%s", "last path gone"); - /* First of all call extended error reporting. */ - dasd_eer_write(device, NULL, DASD_EER_NOPATH); + /* First call extended error reporting and check for autoquiesce. */ + dasd_handle_autoquiesce(device, NULL, DASD_EER_NOPATH); if (device->state < DASD_STATE_BASIC) return 0; @@ -3815,7 +3809,8 @@ void dasd_generic_path_event(struct ccw_device *cdev, int *path_event) "No verified channel paths remain for the device\n"); DBF_DEV_EVENT(DBF_WARNING, device, "%s", "last verified path gone"); - dasd_eer_write(device, NULL, DASD_EER_NOPATH); + /* First call extended error reporting and check for autoquiesce. */ + dasd_handle_autoquiesce(device, NULL, DASD_EER_NOPATH); dasd_device_set_stop_bits(device, DASD_STOPPED_DC_WAIT); } @@ -3837,7 +3832,8 @@ EXPORT_SYMBOL_GPL(dasd_generic_verify_path); void dasd_generic_space_exhaust(struct dasd_device *device, struct dasd_ccw_req *cqr) { - dasd_eer_write(device, NULL, DASD_EER_NOSPC); + /* First call extended error reporting and check for autoquiesce. */ + dasd_handle_autoquiesce(device, NULL, DASD_EER_NOSPC); if (device->state < DASD_STATE_BASIC) return; @@ -3931,6 +3927,31 @@ void dasd_schedule_requeue(struct dasd_device *device) } EXPORT_SYMBOL(dasd_schedule_requeue); +static int dasd_handle_autoquiesce(struct dasd_device *device, + struct dasd_ccw_req *cqr, + unsigned int reason) +{ + /* in any case write eer message with reason */ + if (dasd_eer_enabled(device)) + dasd_eer_write(device, cqr, reason); + + if (!test_bit(reason, &device->aq_mask)) + return 0; + + /* notify eer about autoquiesce */ + if (dasd_eer_enabled(device)) + dasd_eer_write(device, NULL, DASD_EER_AUTOQUIESCE); + + dev_info(&device->cdev->dev, + "The DASD has been put in the quiesce state\n"); + dasd_device_set_stop_bits(device, DASD_STOPPED_QUIESCE); + + if (device->features & DASD_FEATURE_REQUEUEQUIESCE) + dasd_schedule_requeue(device); + + return 1; +} + static struct dasd_ccw_req *dasd_generic_build_rdc(struct dasd_device *device, int rdc_buffer_size, int magic) diff --git a/drivers/s390/block/dasd_eer.c b/drivers/s390/block/dasd_eer.c index d4d31cd11d2615e78cf52484e53d3b0a110c4590..d16c699b9ac6d9f20f10a2f8940ca2c131652824 100644 --- a/drivers/s390/block/dasd_eer.c +++ b/drivers/s390/block/dasd_eer.c @@ -387,6 +387,7 @@ void dasd_eer_write(struct dasd_device *device, struct dasd_ccw_req *cqr, break; case DASD_EER_NOPATH: case DASD_EER_NOSPC: + case DASD_EER_AUTOQUIESCE: dasd_eer_write_standard_trigger(device, NULL, id); break; case DASD_EER_STATECHANGE: diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index f50932518f83aa26e54dcc51ae4eb3ee142493c1..00bcd177264ac6cca4f66e4b86cd65da12989897 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -464,6 +464,7 @@ extern struct dasd_discipline *dasd_diag_discipline_pointer; #define DASD_EER_STATECHANGE 3 #define DASD_EER_PPRCSUSPEND 4 #define DASD_EER_NOSPC 5 +#define DASD_EER_AUTOQUIESCE 31 /* DASD path handling */ @@ -641,6 +642,7 @@ struct dasd_device { struct dasd_format_entry format_entry; struct kset *paths_info; struct dasd_copy_relation *copy; + unsigned long aq_mask; }; struct dasd_block { diff --git a/drivers/s390/cio/cio_inject.c b/drivers/s390/cio/cio_inject.c index 8613fa937237bde02368523577a485b62b07c5dc..a2e771ebae8ebd55e1cb841f76b44a69ebb2bea7 100644 --- a/drivers/s390/cio/cio_inject.c +++ b/drivers/s390/cio/cio_inject.c @@ -95,7 +95,7 @@ static ssize_t crw_inject_write(struct file *file, const char __user *buf, return -EINVAL; } - buffer = vmemdup_user(buf, lbuf); + buffer = memdup_user_nul(buf, lbuf); if (IS_ERR(buffer)) return -ENOMEM; diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index 02813b63f90fda68411cd1e941131d342213e3d2..5666b9cc5d296461dbe77fe308b4423b2d3f1c26 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -360,10 +360,8 @@ int ccw_device_set_online(struct ccw_device *cdev) spin_lock_irq(cdev->ccwlock); ret = ccw_device_online(cdev); - spin_unlock_irq(cdev->ccwlock); - if (ret == 0) - wait_event(cdev->private->wait_q, dev_fsm_final_state(cdev)); - else { + if (ret) { + spin_unlock_irq(cdev->ccwlock); CIO_MSG_EVENT(0, "ccw_device_online returned %d, " "device 0.%x.%04x\n", ret, cdev->private->dev_id.ssid, @@ -372,7 +370,12 @@ int ccw_device_set_online(struct ccw_device *cdev) put_device(&cdev->dev); return ret; } - spin_lock_irq(cdev->ccwlock); + /* Wait until a final state is reached */ + while (!dev_fsm_final_state(cdev)) { + spin_unlock_irq(cdev->ccwlock); + wait_event(cdev->private->wait_q, dev_fsm_final_state(cdev)); + spin_lock_irq(cdev->ccwlock); + } /* Check if online processing was successful */ if ((cdev->private->state != DEV_STATE_ONLINE) && (cdev->private->state != DEV_STATE_W4SENSE)) { diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c index c533d1dadc6bbb0f3f388ac62b01049ac99a72c5..a5dba3829769c7954ed2d3ba38800bc768fb0019 100644 --- a/drivers/s390/cio/device_ops.c +++ b/drivers/s390/cio/device_ops.c @@ -202,7 +202,8 @@ int ccw_device_start_timeout_key(struct ccw_device *cdev, struct ccw1 *cpa, return -EINVAL; if (cdev->private->state == DEV_STATE_NOT_OPER) return -ENODEV; - if (cdev->private->state == DEV_STATE_VERIFY) { + if (cdev->private->state == DEV_STATE_VERIFY || + cdev->private->flags.doverify) { /* Remember to fake irb when finished. */ if (!cdev->private->flags.fake_irb) { cdev->private->flags.fake_irb = FAKE_CMD_IRB; @@ -214,8 +215,7 @@ int ccw_device_start_timeout_key(struct ccw_device *cdev, struct ccw1 *cpa, } if (cdev->private->state != DEV_STATE_ONLINE || ((sch->schib.scsw.cmd.stctl & SCSW_STCTL_PRIM_STATUS) && - !(sch->schib.scsw.cmd.stctl & SCSW_STCTL_SEC_STATUS)) || - cdev->private->flags.doverify) + !(sch->schib.scsw.cmd.stctl & SCSW_STCTL_SEC_STATUS))) return -EBUSY; ret = cio_set_options (sch, flags); if (ret) diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index 9cde55730b65a733b5d1cb9977c83750392e6312..ebcb535809882f464a5eed2015e4dc14940b7beb 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -722,8 +722,8 @@ static void qdio_handle_activate_check(struct qdio_irq *irq_ptr, lgr_info_log(); } -static void qdio_establish_handle_irq(struct qdio_irq *irq_ptr, int cstat, - int dstat) +static int qdio_establish_handle_irq(struct qdio_irq *irq_ptr, int cstat, + int dstat, int dcc) { DBF_DEV_EVENT(DBF_INFO, irq_ptr, "qest irq"); @@ -731,15 +731,18 @@ static void qdio_establish_handle_irq(struct qdio_irq *irq_ptr, int cstat, goto error; if (dstat & ~(DEV_STAT_DEV_END | DEV_STAT_CHN_END)) goto error; + if (dcc == 1) + return -EAGAIN; if (!(dstat & DEV_STAT_DEV_END)) goto error; qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ESTABLISHED); - return; + return 0; error: DBF_ERROR("%4x EQ:error", irq_ptr->schid.sch_no); DBF_ERROR("ds: %2x cs:%2x", dstat, cstat); qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ERR); + return -EIO; } /* qdio interrupt handler */ @@ -748,7 +751,7 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm, { struct qdio_irq *irq_ptr = cdev->private->qdio_data; struct subchannel_id schid; - int cstat, dstat; + int cstat, dstat, rc, dcc; if (!intparm || !irq_ptr) { ccw_device_get_schid(cdev, &schid); @@ -768,10 +771,12 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm, qdio_irq_check_sense(irq_ptr, irb); cstat = irb->scsw.cmd.cstat; dstat = irb->scsw.cmd.dstat; + dcc = scsw_cmd_is_valid_cc(&irb->scsw) ? irb->scsw.cmd.cc : 0; + rc = 0; switch (irq_ptr->state) { case QDIO_IRQ_STATE_INACTIVE: - qdio_establish_handle_irq(irq_ptr, cstat, dstat); + rc = qdio_establish_handle_irq(irq_ptr, cstat, dstat, dcc); break; case QDIO_IRQ_STATE_CLEANUP: qdio_set_state(irq_ptr, QDIO_IRQ_STATE_INACTIVE); @@ -785,12 +790,25 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm, if (cstat || dstat) qdio_handle_activate_check(irq_ptr, intparm, cstat, dstat); + else if (dcc == 1) + rc = -EAGAIN; break; case QDIO_IRQ_STATE_STOPPED: break; default: WARN_ON_ONCE(1); } + + if (rc == -EAGAIN) { + DBF_DEV_EVENT(DBF_INFO, irq_ptr, "qint retry"); + rc = ccw_device_start(cdev, irq_ptr->ccw, intparm, 0, 0); + if (!rc) + return; + DBF_ERROR("%4x RETRY ERR", irq_ptr->schid.sch_no); + DBF_ERROR("rc:%4x", rc); + qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ERR); + } + wake_up(&cdev->private->wait_q); } diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 28e34d155334be24e1716d3628dd385a2021d293..6f44963d34bbfa9c4754b920270e4ee26d3210e9 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -617,6 +617,7 @@ static inline struct zcrypt_queue *zcrypt_pick_queue(struct zcrypt_card *zc, { if (!zq || !try_module_get(zq->queue->ap_dev.device.driver->owner)) return NULL; + zcrypt_card_get(zc); zcrypt_queue_get(zq); get_device(&zq->queue->ap_dev.device); atomic_add(weight, &zc->load); @@ -636,6 +637,7 @@ static inline void zcrypt_drop_queue(struct zcrypt_card *zc, atomic_sub(weight, &zq->load); put_device(&zq->queue->ap_dev.device); zcrypt_queue_put(zq); + zcrypt_card_put(zc); module_put(mod); } diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index ae4b6d24bc902ecdcda391462c3edf0b93a5ceff..f99d1d325f3ea7612770cc0120ddcd0673793b3a 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -364,30 +364,33 @@ out: return rc; } +static void qeth_free_cq(struct qeth_card *card) +{ + if (card->qdio.c_q) { + qeth_free_qdio_queue(card->qdio.c_q); + card->qdio.c_q = NULL; + } +} + static int qeth_alloc_cq(struct qeth_card *card) { if (card->options.cq == QETH_CQ_ENABLED) { QETH_CARD_TEXT(card, 2, "cqon"); - card->qdio.c_q = qeth_alloc_qdio_queue(); if (!card->qdio.c_q) { - dev_err(&card->gdev->dev, "Failed to create completion queue\n"); - return -ENOMEM; + card->qdio.c_q = qeth_alloc_qdio_queue(); + if (!card->qdio.c_q) { + dev_err(&card->gdev->dev, + "Failed to create completion queue\n"); + return -ENOMEM; + } } } else { QETH_CARD_TEXT(card, 2, "nocq"); - card->qdio.c_q = NULL; + qeth_free_cq(card); } return 0; } -static void qeth_free_cq(struct qeth_card *card) -{ - if (card->qdio.c_q) { - qeth_free_qdio_queue(card->qdio.c_q); - card->qdio.c_q = NULL; - } -} - static enum iucv_tx_notify qeth_compute_cq_notification(int sbalf15, int delayed) { @@ -1179,6 +1182,20 @@ static int qeth_check_irb_error(struct qeth_card *card, struct ccw_device *cdev, } } +/** + * qeth_irq() - qeth interrupt handler + * @cdev: ccw device + * @intparm: expect pointer to iob + * @irb: Interruption Response Block + * + * In the good path: + * corresponding qeth channel is locked with last used iob as active_cmd. + * But this function is also called for error interrupts. + * + * Caller ensures that: + * Interrupts are disabled; ccw device lock is held; + * + */ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, struct irb *irb) { @@ -1220,11 +1237,10 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, iob = (struct qeth_cmd_buffer *) (addr_t)intparm; } - qeth_unlock_channel(card, channel); - rc = qeth_check_irb_error(card, cdev, irb); if (rc) { /* IO was terminated, free its resources. */ + qeth_unlock_channel(card, channel); if (iob) qeth_cancel_cmd(iob, rc); return; @@ -1268,6 +1284,7 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, rc = qeth_get_problem(card, cdev, irb); if (rc) { card->read_or_write_problem = 1; + qeth_unlock_channel(card, channel); if (iob) qeth_cancel_cmd(iob, rc); qeth_clear_ipacmd_list(card); @@ -1276,6 +1293,26 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, } } + if (scsw_cmd_is_valid_cc(&irb->scsw) && irb->scsw.cmd.cc == 1 && iob) { + /* channel command hasn't started: retry. + * active_cmd is still set to last iob + */ + QETH_CARD_TEXT(card, 2, "irqcc1"); + rc = ccw_device_start_timeout(cdev, __ccw_from_cmd(iob), + (addr_t)iob, 0, 0, iob->timeout); + if (rc) { + QETH_DBF_MESSAGE(2, + "ccw retry on %x failed, rc = %i\n", + CARD_DEVID(card), rc); + QETH_CARD_TEXT_(card, 2, " err%d", rc); + qeth_unlock_channel(card, channel); + qeth_cancel_cmd(iob, rc); + } + return; + } + + qeth_unlock_channel(card, channel); + if (iob) { /* sanity check: */ if (irb->scsw.cmd.count > iob->length) { @@ -2594,6 +2631,10 @@ static int qeth_alloc_qdio_queues(struct qeth_card *card) QETH_CARD_TEXT(card, 2, "allcqdbf"); + /* completion */ + if (qeth_alloc_cq(card)) + goto out_err; + if (atomic_cmpxchg(&card->qdio.state, QETH_QDIO_UNINITIALIZED, QETH_QDIO_ALLOCATED) != QETH_QDIO_UNINITIALIZED) return 0; @@ -2629,10 +2670,6 @@ static int qeth_alloc_qdio_queues(struct qeth_card *card) queue->priority = QETH_QIB_PQUE_PRIO_DEFAULT; } - /* completion */ - if (qeth_alloc_cq(card)) - goto out_freeoutq; - return 0; out_freeoutq: @@ -2643,6 +2680,8 @@ out_freeoutq: qeth_free_buffer_pool(card); out_buffer_pool: atomic_set(&card->qdio.state, QETH_QDIO_UNINITIALIZED); + qeth_free_cq(card); +out_err: return -ENOMEM; } @@ -2650,11 +2689,12 @@ static void qeth_free_qdio_queues(struct qeth_card *card) { int i, j; + qeth_free_cq(card); + if (atomic_xchg(&card->qdio.state, QETH_QDIO_UNINITIALIZED) == QETH_QDIO_UNINITIALIZED) return; - qeth_free_cq(card); for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j) { if (card->qdio.in_q->bufs[j].rx_skb) { consume_skb(card->qdio.in_q->bufs[j].rx_skb); @@ -3706,24 +3746,11 @@ static void qeth_qdio_poll(struct ccw_device *cdev, unsigned long card_ptr) int qeth_configure_cq(struct qeth_card *card, enum qeth_cq cq) { - int rc; - - if (card->options.cq == QETH_CQ_NOTAVAILABLE) { - rc = -1; - goto out; - } else { - if (card->options.cq == cq) { - rc = 0; - goto out; - } - - qeth_free_qdio_queues(card); - card->options.cq = cq; - rc = 0; - } -out: - return rc; + if (card->options.cq == QETH_CQ_NOTAVAILABLE) + return -1; + card->options.cq = cq; + return 0; } EXPORT_SYMBOL_GPL(qeth_configure_cq); diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index c0f30cefec102b75a6519cf99918b000fd9e1402..a4160113918561aaea8edb544930e08f7f8ac269 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -254,9 +254,10 @@ static void qeth_l3_clear_ip_htable(struct qeth_card *card, int recover) if (!recover) { hash_del(&addr->hnode); kfree(addr); - continue; + } else { + /* prepare for recovery */ + addr->disp_flag = QETH_DISP_ADDR_ADD; } - addr->disp_flag = QETH_DISP_ADDR_ADD; } mutex_unlock(&card->ip_lock); @@ -277,9 +278,11 @@ static void qeth_l3_recover_ip(struct qeth_card *card) if (addr->disp_flag == QETH_DISP_ADDR_ADD) { rc = qeth_l3_register_addr_entry(card, addr); - if (!rc) { + if (!rc || rc == -EADDRINUSE || rc == -ENETDOWN) { + /* keep it in the records */ addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING; } else { + /* bad address */ hash_del(&addr->hnode); kfree(addr); } diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 03e71e3d5e5b34fd580dcad9e824f5745eaa2969..3b990cf2c1954fca0b40736a382202c57f8fae64 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -1285,7 +1285,7 @@ source "drivers/scsi/arm/Kconfig" config JAZZ_ESP bool "MIPS JAZZ FAS216 SCSI support" - depends on MACH_JAZZ && SCSI + depends on MACH_JAZZ && SCSI=y select SCSI_SPI_ATTRS help This is the driver for the onboard SCSI host adapter of MIPS Magnum diff --git a/drivers/scsi/bfa/bfa.h b/drivers/scsi/bfa/bfa.h index 7bd2ba1ad4d1184feac315d6e2909e861a58f46b..f30fe324e6ecc1428a691b1d61dda3c80b22ed8c 100644 --- a/drivers/scsi/bfa/bfa.h +++ b/drivers/scsi/bfa/bfa.h @@ -20,7 +20,6 @@ struct bfa_s; typedef void (*bfa_isr_func_t) (struct bfa_s *bfa, struct bfi_msg_s *m); -typedef void (*bfa_cb_cbfn_status_t) (void *cbarg, bfa_status_t status); /* * Interrupt message handlers @@ -437,4 +436,12 @@ struct bfa_cb_pending_q_s { (__qe)->data = (__data); \ } while (0) +#define bfa_pending_q_init_status(__qe, __cbfn, __cbarg, __data) do { \ + bfa_q_qe_init(&((__qe)->hcb_qe.qe)); \ + (__qe)->hcb_qe.cbfn_status = (__cbfn); \ + (__qe)->hcb_qe.cbarg = (__cbarg); \ + (__qe)->hcb_qe.pre_rmv = BFA_TRUE; \ + (__qe)->data = (__data); \ +} while (0) + #endif /* __BFA_H__ */ diff --git a/drivers/scsi/bfa/bfa_core.c b/drivers/scsi/bfa/bfa_core.c index 6846ca8f7313c379b03983f4c532f631bc0b2a40..3438d0b8ba0624020a4c33e29656c0a55ef06070 100644 --- a/drivers/scsi/bfa/bfa_core.c +++ b/drivers/scsi/bfa/bfa_core.c @@ -1907,15 +1907,13 @@ bfa_comp_process(struct bfa_s *bfa, struct list_head *comp_q) struct list_head *qe; struct list_head *qen; struct bfa_cb_qe_s *hcb_qe; - bfa_cb_cbfn_status_t cbfn; list_for_each_safe(qe, qen, comp_q) { hcb_qe = (struct bfa_cb_qe_s *) qe; if (hcb_qe->pre_rmv) { /* qe is invalid after return, dequeue before cbfn() */ list_del(qe); - cbfn = (bfa_cb_cbfn_status_t)(hcb_qe->cbfn); - cbfn(hcb_qe->cbarg, hcb_qe->fw_status); + hcb_qe->cbfn_status(hcb_qe->cbarg, hcb_qe->fw_status); } else hcb_qe->cbfn(hcb_qe->cbarg, BFA_TRUE); } diff --git a/drivers/scsi/bfa/bfa_ioc.h b/drivers/scsi/bfa/bfa_ioc.h index 933a1c3890ff50bd5ee9da57d5e4137116b401d2..5e568d6d7b261032ec0ad028e541daa9c5ffc97b 100644 --- a/drivers/scsi/bfa/bfa_ioc.h +++ b/drivers/scsi/bfa/bfa_ioc.h @@ -361,14 +361,18 @@ struct bfa_reqq_wait_s { void *cbarg; }; -typedef void (*bfa_cb_cbfn_t) (void *cbarg, bfa_boolean_t complete); +typedef void (*bfa_cb_cbfn_t) (void *cbarg, bfa_boolean_t complete); +typedef void (*bfa_cb_cbfn_status_t) (void *cbarg, bfa_status_t status); /* * Generic BFA callback element. */ struct bfa_cb_qe_s { struct list_head qe; - bfa_cb_cbfn_t cbfn; + union { + bfa_cb_cbfn_status_t cbfn_status; + bfa_cb_cbfn_t cbfn; + }; bfa_boolean_t once; bfa_boolean_t pre_rmv; /* set for stack based qe(s) */ bfa_status_t fw_status; /* to access fw status in comp proc */ diff --git a/drivers/scsi/bfa/bfad_bsg.c b/drivers/scsi/bfa/bfad_bsg.c index be8dfbe13e904e057e5f007550b47b557251cb7b..524e4e6979c9f265de626a17091f00bb9a71bc44 100644 --- a/drivers/scsi/bfa/bfad_bsg.c +++ b/drivers/scsi/bfa/bfad_bsg.c @@ -2135,8 +2135,7 @@ bfad_iocmd_fcport_get_stats(struct bfad_s *bfad, void *cmd) struct bfa_cb_pending_q_s cb_qe; init_completion(&fcomp.comp); - bfa_pending_q_init(&cb_qe, (bfa_cb_cbfn_t)bfad_hcb_comp, - &fcomp, &iocmd->stats); + bfa_pending_q_init_status(&cb_qe, bfad_hcb_comp, &fcomp, &iocmd->stats); spin_lock_irqsave(&bfad->bfad_lock, flags); iocmd->status = bfa_fcport_get_stats(&bfad->bfa, &cb_qe); spin_unlock_irqrestore(&bfad->bfad_lock, flags); @@ -2159,7 +2158,7 @@ bfad_iocmd_fcport_reset_stats(struct bfad_s *bfad, void *cmd) struct bfa_cb_pending_q_s cb_qe; init_completion(&fcomp.comp); - bfa_pending_q_init(&cb_qe, (bfa_cb_cbfn_t)bfad_hcb_comp, &fcomp, NULL); + bfa_pending_q_init_status(&cb_qe, bfad_hcb_comp, &fcomp, NULL); spin_lock_irqsave(&bfad->bfad_lock, flags); iocmd->status = bfa_fcport_clear_stats(&bfad->bfa, &cb_qe); @@ -2443,8 +2442,7 @@ bfad_iocmd_qos_get_stats(struct bfad_s *bfad, void *cmd) struct bfa_fcport_s *fcport = BFA_FCPORT_MOD(&bfad->bfa); init_completion(&fcomp.comp); - bfa_pending_q_init(&cb_qe, (bfa_cb_cbfn_t)bfad_hcb_comp, - &fcomp, &iocmd->stats); + bfa_pending_q_init_status(&cb_qe, bfad_hcb_comp, &fcomp, &iocmd->stats); spin_lock_irqsave(&bfad->bfad_lock, flags); WARN_ON(!bfa_ioc_get_fcmode(&bfad->bfa.ioc)); @@ -2474,8 +2472,7 @@ bfad_iocmd_qos_reset_stats(struct bfad_s *bfad, void *cmd) struct bfa_fcport_s *fcport = BFA_FCPORT_MOD(&bfad->bfa); init_completion(&fcomp.comp); - bfa_pending_q_init(&cb_qe, (bfa_cb_cbfn_t)bfad_hcb_comp, - &fcomp, NULL); + bfa_pending_q_init_status(&cb_qe, bfad_hcb_comp, &fcomp, NULL); spin_lock_irqsave(&bfad->bfad_lock, flags); WARN_ON(!bfa_ioc_get_fcmode(&bfad->bfa.ioc)); diff --git a/drivers/scsi/bnx2fc/bnx2fc_tgt.c b/drivers/scsi/bnx2fc/bnx2fc_tgt.c index 2c246e80c1c4d614fafb7183ecd8c5515bc9dd13..d91659811eb3c569e437d61a92a5fb3746d2902e 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_tgt.c +++ b/drivers/scsi/bnx2fc/bnx2fc_tgt.c @@ -833,7 +833,6 @@ static void bnx2fc_free_session_resc(struct bnx2fc_hba *hba, BNX2FC_TGT_DBG(tgt, "Freeing up session resources\n"); - spin_lock_bh(&tgt->cq_lock); ctx_base_ptr = tgt->ctx_base; tgt->ctx_base = NULL; @@ -889,7 +888,6 @@ static void bnx2fc_free_session_resc(struct bnx2fc_hba *hba, tgt->sq, tgt->sq_dma); tgt->sq = NULL; } - spin_unlock_bh(&tgt->cq_lock); if (ctx_base_ptr) iounmap(ctx_base_ptr); diff --git a/drivers/scsi/csiostor/csio_defs.h b/drivers/scsi/csiostor/csio_defs.h index c38017b4af9826871bec6205f26ee73b115b20d2..e50e93e7fe5a1c3c79225d92f660333a22344db6 100644 --- a/drivers/scsi/csiostor/csio_defs.h +++ b/drivers/scsi/csiostor/csio_defs.h @@ -73,7 +73,21 @@ csio_list_deleted(struct list_head *list) #define csio_list_prev(elem) (((struct list_head *)(elem))->prev) /* State machine */ -typedef void (*csio_sm_state_t)(void *, uint32_t); +struct csio_lnode; + +/* State machine evets */ +enum csio_ln_ev { + CSIO_LNE_NONE = (uint32_t)0, + CSIO_LNE_LINKUP, + CSIO_LNE_FAB_INIT_DONE, + CSIO_LNE_LINK_DOWN, + CSIO_LNE_DOWN_LINK, + CSIO_LNE_LOGO, + CSIO_LNE_CLOSE, + CSIO_LNE_MAX_EVENT, +}; + +typedef void (*csio_sm_state_t)(struct csio_lnode *ln, enum csio_ln_ev evt); struct csio_sm { struct list_head sm_list; @@ -83,7 +97,7 @@ struct csio_sm { static inline void csio_set_state(void *smp, void *state) { - ((struct csio_sm *)smp)->sm_state = (csio_sm_state_t)state; + ((struct csio_sm *)smp)->sm_state = state; } static inline void diff --git a/drivers/scsi/csiostor/csio_lnode.c b/drivers/scsi/csiostor/csio_lnode.c index d5ac9389702327fdf6d6767324ec7f8bdaa642cb..5b3ffefae476d011999a9ac66913381080b34920 100644 --- a/drivers/scsi/csiostor/csio_lnode.c +++ b/drivers/scsi/csiostor/csio_lnode.c @@ -1095,7 +1095,7 @@ csio_handle_link_down(struct csio_hw *hw, uint8_t portid, uint32_t fcfi, int csio_is_lnode_ready(struct csio_lnode *ln) { - return (csio_get_state(ln) == ((csio_sm_state_t)csio_lns_ready)); + return (csio_get_state(ln) == csio_lns_ready); } /*****************************************************************************/ @@ -1366,15 +1366,15 @@ csio_free_fcfinfo(struct kref *kref) void csio_lnode_state_to_str(struct csio_lnode *ln, int8_t *str) { - if (csio_get_state(ln) == ((csio_sm_state_t)csio_lns_uninit)) { + if (csio_get_state(ln) == csio_lns_uninit) { strcpy(str, "UNINIT"); return; } - if (csio_get_state(ln) == ((csio_sm_state_t)csio_lns_ready)) { + if (csio_get_state(ln) == csio_lns_ready) { strcpy(str, "READY"); return; } - if (csio_get_state(ln) == ((csio_sm_state_t)csio_lns_offline)) { + if (csio_get_state(ln) == csio_lns_offline) { strcpy(str, "OFFLINE"); return; } diff --git a/drivers/scsi/csiostor/csio_lnode.h b/drivers/scsi/csiostor/csio_lnode.h index 372a67d122d38fc161743c105db229c534d26a89..607698a0f06315935a169633a5f2e50038d37f48 100644 --- a/drivers/scsi/csiostor/csio_lnode.h +++ b/drivers/scsi/csiostor/csio_lnode.h @@ -53,19 +53,6 @@ extern int csio_fcoe_rnodes; extern int csio_fdmi_enable; -/* State machine evets */ -enum csio_ln_ev { - CSIO_LNE_NONE = (uint32_t)0, - CSIO_LNE_LINKUP, - CSIO_LNE_FAB_INIT_DONE, - CSIO_LNE_LINK_DOWN, - CSIO_LNE_DOWN_LINK, - CSIO_LNE_LOGO, - CSIO_LNE_CLOSE, - CSIO_LNE_MAX_EVENT, -}; - - struct csio_fcf_info { struct list_head list; uint8_t priority; diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c index 8a4124e7d2043630adbacad4db576386163bceda..ddc048069af25aeac8680512e4bae041bfef9c2b 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -319,17 +319,16 @@ static void fcoe_ctlr_announce(struct fcoe_ctlr *fip) { struct fcoe_fcf *sel; struct fcoe_fcf *fcf; - unsigned long flags; mutex_lock(&fip->ctlr_mutex); - spin_lock_irqsave(&fip->ctlr_lock, flags); + spin_lock_bh(&fip->ctlr_lock); kfree_skb(fip->flogi_req); fip->flogi_req = NULL; list_for_each_entry(fcf, &fip->fcfs, list) fcf->flogi_sent = 0; - spin_unlock_irqrestore(&fip->ctlr_lock, flags); + spin_unlock_bh(&fip->ctlr_lock); sel = fip->sel_fcf; if (sel && ether_addr_equal(sel->fcf_mac, fip->dest_addr)) @@ -700,7 +699,6 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport, { struct fc_frame *fp; struct fc_frame_header *fh; - unsigned long flags; u16 old_xid; u8 op; u8 mac[ETH_ALEN]; @@ -734,11 +732,11 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport, op = FIP_DT_FLOGI; if (fip->mode == FIP_MODE_VN2VN) break; - spin_lock_irqsave(&fip->ctlr_lock, flags); + spin_lock_bh(&fip->ctlr_lock); kfree_skb(fip->flogi_req); fip->flogi_req = skb; fip->flogi_req_send = 1; - spin_unlock_irqrestore(&fip->ctlr_lock, flags); + spin_unlock_bh(&fip->ctlr_lock); schedule_work(&fip->timer_work); return -EINPROGRESS; case ELS_FDISC: @@ -1707,11 +1705,10 @@ static int fcoe_ctlr_flogi_send_locked(struct fcoe_ctlr *fip) static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip) { struct fcoe_fcf *fcf; - unsigned long flags; int error; mutex_lock(&fip->ctlr_mutex); - spin_lock_irqsave(&fip->ctlr_lock, flags); + spin_lock_bh(&fip->ctlr_lock); LIBFCOE_FIP_DBG(fip, "re-sending FLOGI - reselect\n"); fcf = fcoe_ctlr_select(fip); if (!fcf || fcf->flogi_sent) { @@ -1722,7 +1719,7 @@ static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip) fcoe_ctlr_solicit(fip, NULL); error = fcoe_ctlr_flogi_send_locked(fip); } - spin_unlock_irqrestore(&fip->ctlr_lock, flags); + spin_unlock_bh(&fip->ctlr_lock); mutex_unlock(&fip->ctlr_mutex); return error; } @@ -1739,9 +1736,8 @@ static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip) static void fcoe_ctlr_flogi_send(struct fcoe_ctlr *fip) { struct fcoe_fcf *fcf; - unsigned long flags; - spin_lock_irqsave(&fip->ctlr_lock, flags); + spin_lock_bh(&fip->ctlr_lock); fcf = fip->sel_fcf; if (!fcf || !fip->flogi_req_send) goto unlock; @@ -1768,7 +1764,7 @@ static void fcoe_ctlr_flogi_send(struct fcoe_ctlr *fip) } else /* XXX */ LIBFCOE_FIP_DBG(fip, "No FCF selected - defer send\n"); unlock: - spin_unlock_irqrestore(&fip->ctlr_lock, flags); + spin_unlock_bh(&fip->ctlr_lock); } /** diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index 450a8578157cbbbedbe0f962b69bf60bf4b59bb1..2116f5ee36e20ab2fa5a36ca469eb339eb12fdf3 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -1715,7 +1715,7 @@ static int hisi_sas_debug_I_T_nexus_reset(struct domain_device *device) if (dev_is_sata(device)) { struct ata_link *link = &device->sata_dev.ap->link; - rc = ata_wait_after_reset(link, HISI_SAS_WAIT_PHYUP_TIMEOUT, + rc = ata_wait_after_reset(link, jiffies + HISI_SAS_WAIT_PHYUP_TIMEOUT, smp_ata_check_ready_type); } else { msleep(2000); diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 8b825364baade15024ae5a9fb92cfa7a5a28a486..c785493b105c0729d95ebdd50560013a918b687f 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -353,12 +353,13 @@ static void scsi_host_dev_release(struct device *dev) if (shost->shost_state == SHOST_CREATED) { /* - * Free the shost_dev device name here if scsi_host_alloc() - * and scsi_host_put() have been called but neither + * Free the shost_dev device name and remove the proc host dir + * here if scsi_host_{alloc,put}() have been called but neither * scsi_host_add() nor scsi_host_remove() has been called. * This avoids that the memory allocated for the shost_dev - * name is leaked. + * name as well as the proc dir structure are leaked. */ + scsi_proc_hostdir_rm(shost->hostt); kfree(dev_name(&shost->shost_dev)); } diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c index 63a23251fb1d87d7958d544f753067205e1b901f..4b5ceba68e46e22d3141c086db715deb6ad29e3d 100644 --- a/drivers/scsi/libsas/sas_expander.c +++ b/drivers/scsi/libsas/sas_expander.c @@ -1651,6 +1651,16 @@ out_err: /* ---------- Domain revalidation ---------- */ +static void sas_get_sas_addr_and_dev_type(struct smp_disc_resp *disc_resp, + u8 *sas_addr, + enum sas_device_type *type) +{ + memcpy(sas_addr, disc_resp->disc.attached_sas_addr, SAS_ADDR_SIZE); + *type = to_dev_type(&disc_resp->disc); + if (*type == SAS_PHY_UNUSED) + memset(sas_addr, 0, SAS_ADDR_SIZE); +} + static int sas_get_phy_discover(struct domain_device *dev, int phy_id, struct smp_disc_resp *disc_resp) { @@ -1704,13 +1714,8 @@ int sas_get_phy_attached_dev(struct domain_device *dev, int phy_id, return -ENOMEM; res = sas_get_phy_discover(dev, phy_id, disc_resp); - if (res == 0) { - memcpy(sas_addr, disc_resp->disc.attached_sas_addr, - SAS_ADDR_SIZE); - *type = to_dev_type(&disc_resp->disc); - if (*type == 0) - memset(sas_addr, 0, SAS_ADDR_SIZE); - } + if (res == 0) + sas_get_sas_addr_and_dev_type(disc_resp, sas_addr, type); kfree(disc_resp); return res; } @@ -1972,6 +1977,7 @@ static int sas_rediscover_dev(struct domain_device *dev, int phy_id, struct expander_device *ex = &dev->ex_dev; struct ex_phy *phy = &ex->ex_phy[phy_id]; enum sas_device_type type = SAS_PHY_UNUSED; + struct smp_disc_resp *disc_resp; u8 sas_addr[SAS_ADDR_SIZE]; char msg[80] = ""; int res; @@ -1983,33 +1989,41 @@ static int sas_rediscover_dev(struct domain_device *dev, int phy_id, SAS_ADDR(dev->sas_addr), phy_id, msg); memset(sas_addr, 0, SAS_ADDR_SIZE); - res = sas_get_phy_attached_dev(dev, phy_id, sas_addr, &type); + disc_resp = alloc_smp_resp(DISCOVER_RESP_SIZE); + if (!disc_resp) + return -ENOMEM; + + res = sas_get_phy_discover(dev, phy_id, disc_resp); switch (res) { case SMP_RESP_NO_PHY: phy->phy_state = PHY_NOT_PRESENT; sas_unregister_devs_sas_addr(dev, phy_id, last); - return res; + goto out_free_resp; case SMP_RESP_PHY_VACANT: phy->phy_state = PHY_VACANT; sas_unregister_devs_sas_addr(dev, phy_id, last); - return res; + goto out_free_resp; case SMP_RESP_FUNC_ACC: break; case -ECOMM: break; default: - return res; + goto out_free_resp; } + if (res == 0) + sas_get_sas_addr_and_dev_type(disc_resp, sas_addr, &type); + if ((SAS_ADDR(sas_addr) == 0) || (res == -ECOMM)) { phy->phy_state = PHY_EMPTY; sas_unregister_devs_sas_addr(dev, phy_id, last); /* - * Even though the PHY is empty, for convenience we discover - * the PHY to update the PHY info, like negotiated linkrate. + * Even though the PHY is empty, for convenience we update + * the PHY info, like negotiated linkrate. */ - sas_ex_phy_discover(dev, phy_id); - return res; + if (res == 0) + sas_set_ex_phy(dev, phy_id, disc_resp); + goto out_free_resp; } else if (SAS_ADDR(sas_addr) == SAS_ADDR(phy->attached_sas_addr) && dev_type_flutter(type, phy->attached_dev_type)) { struct domain_device *ata_dev = sas_ex_to_ata(dev, phy_id); @@ -2021,7 +2035,7 @@ static int sas_rediscover_dev(struct domain_device *dev, int phy_id, action = ", needs recovery"; pr_debug("ex %016llx phy%02d broadcast flutter%s\n", SAS_ADDR(dev->sas_addr), phy_id, action); - return res; + goto out_free_resp; } /* we always have to delete the old device when we went here */ @@ -2030,7 +2044,10 @@ static int sas_rediscover_dev(struct domain_device *dev, int phy_id, SAS_ADDR(phy->attached_sas_addr)); sas_unregister_devs_sas_addr(dev, phy_id, last); - return sas_discover_new(dev, phy_id); + res = sas_discover_new(dev, phy_id); +out_free_resp: + kfree(disc_resp); + return res; } /** diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index dc5ac3cc70f6d151db8733f4c0ca09e459e5dd85..6f08fbe103cb951802efab5af1d73e89ff6a6134 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -1355,7 +1355,6 @@ struct lpfc_hba { struct timer_list fabric_block_timer; unsigned long bit_flags; atomic_t num_rsrc_err; - atomic_t num_cmd_success; unsigned long last_rsrc_error_time; unsigned long last_ramp_down_time; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c index b54fafb486e0697668070d10e4f2d45d6582ccda..2373dad016033ec9918d8378ab39f4f8be41446e 100644 --- a/drivers/scsi/lpfc/lpfc_bsg.c +++ b/drivers/scsi/lpfc/lpfc_bsg.c @@ -3169,10 +3169,10 @@ lpfc_bsg_diag_loopback_run(struct bsg_job *job) } cmdwqe = &cmdiocbq->wqe; - memset(cmdwqe, 0, sizeof(union lpfc_wqe)); + memset(cmdwqe, 0, sizeof(*cmdwqe)); if (phba->sli_rev < LPFC_SLI_REV4) { rspwqe = &rspiocbq->wqe; - memset(rspwqe, 0, sizeof(union lpfc_wqe)); + memset(rspwqe, 0, sizeof(*rspwqe)); } INIT_LIST_HEAD(&head); diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index 6b5ce9869e6b4b5333b738330474a5ff2b377ab2..05764008f6e70f4a3b029c6113eff64e30f3f3e8 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -4384,23 +4384,23 @@ lpfc_els_retry_delay(struct timer_list *t) unsigned long flags; struct lpfc_work_evt *evtp = &ndlp->els_retry_evt; + /* Hold a node reference for outstanding queued work */ + if (!lpfc_nlp_get(ndlp)) + return; + spin_lock_irqsave(&phba->hbalock, flags); if (!list_empty(&evtp->evt_listp)) { spin_unlock_irqrestore(&phba->hbalock, flags); + lpfc_nlp_put(ndlp); return; } - /* We need to hold the node by incrementing the reference - * count until the queued work is done - */ - evtp->evt_arg1 = lpfc_nlp_get(ndlp); - if (evtp->evt_arg1) { - evtp->evt = LPFC_EVT_ELS_RETRY; - list_add_tail(&evtp->evt_listp, &phba->work_list); - lpfc_worker_wake_up(phba); - } + evtp->evt_arg1 = ndlp; + evtp->evt = LPFC_EVT_ELS_RETRY; + list_add_tail(&evtp->evt_listp, &phba->work_list); spin_unlock_irqrestore(&phba->hbalock, flags); - return; + + lpfc_worker_wake_up(phba); } /** diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 549fa7d6c0f6fd636c869ddaa595dd2e4e6c2334..aaa98a006fdcbf908cd2a3eea82f5921f63d1a18 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -241,7 +241,9 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) if (evtp->evt_arg1) { evtp->evt = LPFC_EVT_DEV_LOSS; list_add_tail(&evtp->evt_listp, &phba->work_list); + spin_unlock_irqrestore(&phba->hbalock, iflags); lpfc_worker_wake_up(phba); + return; } spin_unlock_irqrestore(&phba->hbalock, iflags); } else { @@ -259,10 +261,7 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) lpfc_disc_state_machine(vport, ndlp, NULL, NLP_EVT_DEVICE_RM); } - } - - return; } /** diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c index b86ff9fcdf0c6a909197cf1e2d6824ccdb28007b..f21396a0ba9d02d7fbf4f369cef5b0621179b3a0 100644 --- a/drivers/scsi/lpfc/lpfc_nportdisc.c +++ b/drivers/scsi/lpfc/lpfc_nportdisc.c @@ -748,8 +748,10 @@ lpfc_rcv_padisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, /* Save the ELS cmd */ elsiocb->drvrTimeout = cmd; - lpfc_sli4_resume_rpi(ndlp, - lpfc_mbx_cmpl_resume_rpi, elsiocb); + if (lpfc_sli4_resume_rpi(ndlp, + lpfc_mbx_cmpl_resume_rpi, + elsiocb)) + kfree(elsiocb); goto out; } } diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index 152245f7cacc7adb1f60f57e16210f8004360f68..7e9e0d969256af621b2c6a82cef4b1077bff56da 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -2621,9 +2621,9 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) /* No concern about the role change on the nvme remoteport. * The transport will update it. */ - spin_lock_irq(&vport->phba->hbalock); + spin_lock_irq(&ndlp->lock); ndlp->fc4_xpt_flags |= NVME_XPT_UNREG_WAIT; - spin_unlock_irq(&vport->phba->hbalock); + spin_unlock_irq(&ndlp->lock); /* Don't let the host nvme transport keep sending keep-alives * on this remoteport. Vport is unloading, no recovery. The diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c index f7cfac0da9b6e0779fc93fc364b7eef5b538816a..1c64da3b2e9f009d62070c9d1c429d01c115b6ee 100644 --- a/drivers/scsi/lpfc/lpfc_nvmet.c +++ b/drivers/scsi/lpfc/lpfc_nvmet.c @@ -1586,7 +1586,7 @@ lpfc_nvmet_setup_io_context(struct lpfc_hba *phba) wqe = &nvmewqe->wqe; /* Initialize WQE */ - memset(wqe, 0, sizeof(union lpfc_wqe)); + memset(wqe, 0, sizeof(*wqe)); ctx_buf->iocbq->cmd_dmabuf = NULL; spin_lock(&phba->sli4_hba.sgl_list_lock); diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 7aac9fc719675956d564d89d0fc71d3041822c7e..2a81a42de5c14efae49943ffbd8fdee91e7dfd88 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -167,11 +167,10 @@ lpfc_ramp_down_queue_handler(struct lpfc_hba *phba) struct Scsi_Host *shost; struct scsi_device *sdev; unsigned long new_queue_depth; - unsigned long num_rsrc_err, num_cmd_success; + unsigned long num_rsrc_err; int i; num_rsrc_err = atomic_read(&phba->num_rsrc_err); - num_cmd_success = atomic_read(&phba->num_cmd_success); /* * The error and success command counters are global per @@ -186,20 +185,16 @@ lpfc_ramp_down_queue_handler(struct lpfc_hba *phba) for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) { shost = lpfc_shost_from_vport(vports[i]); shost_for_each_device(sdev, shost) { - new_queue_depth = - sdev->queue_depth * num_rsrc_err / - (num_rsrc_err + num_cmd_success); - if (!new_queue_depth) - new_queue_depth = sdev->queue_depth - 1; + if (num_rsrc_err >= sdev->queue_depth) + new_queue_depth = 1; else new_queue_depth = sdev->queue_depth - - new_queue_depth; + num_rsrc_err; scsi_change_queue_depth(sdev, new_queue_depth); } } lpfc_destroy_vport_work_array(phba, vports); atomic_set(&phba->num_rsrc_err, 0); - atomic_set(&phba->num_cmd_success, 0); } /** @@ -1919,7 +1914,7 @@ out: * * Returns the number of SGEs added to the SGL. **/ -static int +static uint32_t lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc, struct sli4_sge *sgl, int datasegcnt, struct lpfc_io_buf *lpfc_cmd) @@ -1927,8 +1922,8 @@ lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc, struct scatterlist *sgde = NULL; /* s/g data entry */ struct sli4_sge_diseed *diseed = NULL; dma_addr_t physaddr; - int i = 0, num_sge = 0, status; - uint32_t reftag; + int i = 0, status; + uint32_t reftag, num_sge = 0; uint8_t txop, rxop; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS uint32_t rc; @@ -2100,7 +2095,7 @@ out: * * Returns the number of SGEs added to the SGL. **/ -static int +static uint32_t lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc, struct sli4_sge *sgl, int datacnt, int protcnt, struct lpfc_io_buf *lpfc_cmd) @@ -2124,8 +2119,8 @@ lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc, uint32_t rc; #endif uint32_t checking = 1; - uint32_t dma_offset = 0; - int num_sge = 0, j = 2; + uint32_t dma_offset = 0, num_sge = 0; + int j = 2; struct sli4_hybrid_sgl *sgl_xtra = NULL; sgpe = scsi_prot_sglist(sc); diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 427a6ac803e508c2b780221a633491a89962e3b7..47b8102a7063a4aab285baf1c93979e73f9a9144 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -1217,9 +1217,9 @@ lpfc_set_rrq_active(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp, empty = list_empty(&phba->active_rrq_list); list_add_tail(&rrq->list, &phba->active_rrq_list); phba->hba_flag |= HBA_RRQ_ACTIVE; + spin_unlock_irqrestore(&phba->hbalock, iflags); if (empty) lpfc_worker_wake_up(phba); - spin_unlock_irqrestore(&phba->hbalock, iflags); return 0; out: spin_unlock_irqrestore(&phba->hbalock, iflags); @@ -11361,18 +11361,18 @@ lpfc_sli_post_recovery_event(struct lpfc_hba *phba, unsigned long iflags; struct lpfc_work_evt *evtp = &ndlp->recovery_evt; + /* Hold a node reference for outstanding queued work */ + if (!lpfc_nlp_get(ndlp)) + return; + spin_lock_irqsave(&phba->hbalock, iflags); if (!list_empty(&evtp->evt_listp)) { spin_unlock_irqrestore(&phba->hbalock, iflags); + lpfc_nlp_put(ndlp); return; } - /* Incrementing the reference count until the queued work is done. */ - evtp->evt_arg1 = lpfc_nlp_get(ndlp); - if (!evtp->evt_arg1) { - spin_unlock_irqrestore(&phba->hbalock, iflags); - return; - } + evtp->evt_arg1 = ndlp; evtp->evt = LPFC_EVT_RECOVER_PORT; list_add_tail(&evtp->evt_listp, &phba->work_list); spin_unlock_irqrestore(&phba->hbalock, iflags); diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c index 4d171f5c213f7350a2cbf8e9957dbeda17ac6ded..6b4259894584f380fc0f6997c6bfe8b5e2079a02 100644 --- a/drivers/scsi/lpfc/lpfc_vport.c +++ b/drivers/scsi/lpfc/lpfc_vport.c @@ -693,10 +693,6 @@ lpfc_vport_delete(struct fc_vport *fc_vport) lpfc_free_sysfs_attr(vport); lpfc_debugfs_terminate(vport); - /* Remove FC host to break driver binding. */ - fc_remove_host(shost); - scsi_remove_host(shost); - /* Send the DA_ID and Fabric LOGO to cleanup Nameserver entries. */ ndlp = lpfc_findnode_did(vport, Fabric_DID); if (!ndlp) @@ -740,6 +736,10 @@ lpfc_vport_delete(struct fc_vport *fc_vport) skip_logo: + /* Remove FC host to break driver binding. */ + fc_remove_host(shost); + scsi_remove_host(shost); + lpfc_cleanup(vport); /* Remove scsi host now. The nodes are cleaned up. */ diff --git a/drivers/scsi/mpi3mr/mpi3mr_app.c b/drivers/scsi/mpi3mr/mpi3mr_app.c index 8c662d08706f1c078d94f717baeb9ebeee148f23..42600e5c457a11801b081c785117a347e531b50b 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_app.c +++ b/drivers/scsi/mpi3mr/mpi3mr_app.c @@ -1344,7 +1344,7 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job, unsigned int *reply if ((mpirep_offset != 0xFF) && drv_bufs[mpirep_offset].bsg_buf_len) { drv_buf_iter = &drv_bufs[mpirep_offset]; - drv_buf_iter->kern_buf_len = (sizeof(*bsg_reply_buf) - 1 + + drv_buf_iter->kern_buf_len = (sizeof(*bsg_reply_buf) + mrioc->reply_sz); bsg_reply_buf = kzalloc(drv_buf_iter->kern_buf_len, GFP_KERNEL); diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 809be43f440dc960f18b24cb3f9e805c455c7733..8e6ac08e553bb407a8396e8d45da79eb4868ad19 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -7398,7 +7398,9 @@ _base_wait_for_iocstate(struct MPT3SAS_ADAPTER *ioc, int timeout) return -EFAULT; } - issue_diag_reset: + return 0; + +issue_diag_reset: rc = _base_diag_reset(ioc); return rc; } diff --git a/drivers/scsi/myrb.c b/drivers/scsi/myrb.c index e885c1dbf61f962aa7706434f6970b37b2fbb9c1..e2f1b186efd007151199391660b44b99a6e21337 100644 --- a/drivers/scsi/myrb.c +++ b/drivers/scsi/myrb.c @@ -1775,9 +1775,9 @@ static ssize_t raid_state_show(struct device *dev, name = myrb_devstate_name(ldev_info->state); if (name) - ret = snprintf(buf, 32, "%s\n", name); + ret = snprintf(buf, 64, "%s\n", name); else - ret = snprintf(buf, 32, "Invalid (%02X)\n", + ret = snprintf(buf, 64, "Invalid (%02X)\n", ldev_info->state); } else { struct myrb_pdev_state *pdev_info = sdev->hostdata; @@ -1796,9 +1796,9 @@ static ssize_t raid_state_show(struct device *dev, else name = myrb_devstate_name(pdev_info->state); if (name) - ret = snprintf(buf, 32, "%s\n", name); + ret = snprintf(buf, 64, "%s\n", name); else - ret = snprintf(buf, 32, "Invalid (%02X)\n", + ret = snprintf(buf, 64, "Invalid (%02X)\n", pdev_info->state); } return ret; @@ -1886,11 +1886,11 @@ static ssize_t raid_level_show(struct device *dev, name = myrb_raidlevel_name(ldev_info->raid_level); if (!name) - return snprintf(buf, 32, "Invalid (%02X)\n", + return snprintf(buf, 64, "Invalid (%02X)\n", ldev_info->state); - return snprintf(buf, 32, "%s\n", name); + return snprintf(buf, 64, "%s\n", name); } - return snprintf(buf, 32, "Physical Drive\n"); + return snprintf(buf, 64, "Physical Drive\n"); } static DEVICE_ATTR_RO(raid_level); @@ -1903,15 +1903,15 @@ static ssize_t rebuild_show(struct device *dev, unsigned char status; if (sdev->channel < myrb_logical_channel(sdev->host)) - return snprintf(buf, 32, "physical device - not rebuilding\n"); + return snprintf(buf, 64, "physical device - not rebuilding\n"); status = myrb_get_rbld_progress(cb, &rbld_buf); if (rbld_buf.ldev_num != sdev->id || status != MYRB_STATUS_SUCCESS) - return snprintf(buf, 32, "not rebuilding\n"); + return snprintf(buf, 64, "not rebuilding\n"); - return snprintf(buf, 32, "rebuilding block %u of %u\n", + return snprintf(buf, 64, "rebuilding block %u of %u\n", rbld_buf.ldev_size - rbld_buf.blocks_left, rbld_buf.ldev_size); } diff --git a/drivers/scsi/myrs.c b/drivers/scsi/myrs.c index 7eb8c39da366316877bbb3820eff7488dbec24d1..95e7c00cb7e54e5fbd3b982a3b15309b65baeb58 100644 --- a/drivers/scsi/myrs.c +++ b/drivers/scsi/myrs.c @@ -947,9 +947,9 @@ static ssize_t raid_state_show(struct device *dev, name = myrs_devstate_name(ldev_info->dev_state); if (name) - ret = snprintf(buf, 32, "%s\n", name); + ret = snprintf(buf, 64, "%s\n", name); else - ret = snprintf(buf, 32, "Invalid (%02X)\n", + ret = snprintf(buf, 64, "Invalid (%02X)\n", ldev_info->dev_state); } else { struct myrs_pdev_info *pdev_info; @@ -958,9 +958,9 @@ static ssize_t raid_state_show(struct device *dev, pdev_info = sdev->hostdata; name = myrs_devstate_name(pdev_info->dev_state); if (name) - ret = snprintf(buf, 32, "%s\n", name); + ret = snprintf(buf, 64, "%s\n", name); else - ret = snprintf(buf, 32, "Invalid (%02X)\n", + ret = snprintf(buf, 64, "Invalid (%02X)\n", pdev_info->dev_state); } return ret; @@ -1066,13 +1066,13 @@ static ssize_t raid_level_show(struct device *dev, ldev_info = sdev->hostdata; name = myrs_raid_level_name(ldev_info->raid_level); if (!name) - return snprintf(buf, 32, "Invalid (%02X)\n", + return snprintf(buf, 64, "Invalid (%02X)\n", ldev_info->dev_state); } else name = myrs_raid_level_name(MYRS_RAID_PHYSICAL); - return snprintf(buf, 32, "%s\n", name); + return snprintf(buf, 64, "%s\n", name); } static DEVICE_ATTR_RO(raid_level); @@ -1086,7 +1086,7 @@ static ssize_t rebuild_show(struct device *dev, unsigned char status; if (sdev->channel < cs->ctlr_info->physchan_present) - return snprintf(buf, 32, "physical device - not rebuilding\n"); + return snprintf(buf, 64, "physical device - not rebuilding\n"); ldev_info = sdev->hostdata; ldev_num = ldev_info->ldev_num; @@ -1098,11 +1098,11 @@ static ssize_t rebuild_show(struct device *dev, return -EIO; } if (ldev_info->rbld_active) { - return snprintf(buf, 32, "rebuilding block %zu of %zu\n", + return snprintf(buf, 64, "rebuilding block %zu of %zu\n", (size_t)ldev_info->rbld_lba, (size_t)ldev_info->cfg_devsize); } else - return snprintf(buf, 32, "not rebuilding\n"); + return snprintf(buf, 64, "not rebuilding\n"); } static ssize_t rebuild_store(struct device *dev, @@ -1190,7 +1190,7 @@ static ssize_t consistency_check_show(struct device *dev, unsigned short ldev_num; if (sdev->channel < cs->ctlr_info->physchan_present) - return snprintf(buf, 32, "physical device - not checking\n"); + return snprintf(buf, 64, "physical device - not checking\n"); ldev_info = sdev->hostdata; if (!ldev_info) @@ -1198,11 +1198,11 @@ static ssize_t consistency_check_show(struct device *dev, ldev_num = ldev_info->ldev_num; myrs_get_ldev_info(cs, ldev_num, ldev_info); if (ldev_info->cc_active) - return snprintf(buf, 32, "checking block %zu of %zu\n", + return snprintf(buf, 64, "checking block %zu of %zu\n", (size_t)ldev_info->cc_lba, (size_t)ldev_info->cfg_devsize); else - return snprintf(buf, 32, "not checking\n"); + return snprintf(buf, 64, "not checking\n"); } static ssize_t consistency_check_store(struct device *dev, diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 07fbaa452d8a125756d515ee05190147b7044203..0d414c1aa84e7d1029add253600396168eeb22d9 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -2741,7 +2741,13 @@ qla2x00_dev_loss_tmo_callbk(struct fc_rport *rport) return; if (unlikely(pci_channel_offline(fcport->vha->hw->pdev))) { - qla2x00_abort_all_cmds(fcport->vha, DID_NO_CONNECT << 16); + /* Will wait for wind down of adapter */ + ql_dbg(ql_dbg_aer, fcport->vha, 0x900c, + "%s pci offline detected (id %06x)\n", __func__, + fcport->d_id.b24); + qla_pci_set_eeh_busy(fcport->vha); + qla2x00_eh_wait_for_pending_commands(fcport->vha, fcport->d_id.b24, + 0, WAIT_TARGET); return; } } @@ -2763,7 +2769,11 @@ qla2x00_terminate_rport_io(struct fc_rport *rport) vha = fcport->vha; if (unlikely(pci_channel_offline(fcport->vha->hw->pdev))) { - qla2x00_abort_all_cmds(fcport->vha, DID_NO_CONNECT << 16); + /* Will wait for wind down of adapter */ + ql_dbg(ql_dbg_aer, fcport->vha, 0x900b, + "%s pci offline detected (id %06x)\n", __func__, + fcport->d_id.b24); + qla_pci_set_eeh_busy(vha); qla2x00_eh_wait_for_pending_commands(fcport->vha, fcport->d_id.b24, 0, WAIT_TARGET); return; diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 1713588f671f3d9828961a63b9ff1a9c8e83e511..31c451daeeb8286e271060635f7e5224ff14de2f 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -83,7 +83,7 @@ typedef union { #include "qla_nvme.h" #define QLA2XXX_DRIVER_NAME "qla2xxx" #define QLA2XXX_APIDEV "ql2xapidev" -#define QLA2XXX_MANUFACTURER "Marvell Semiconductor, Inc." +#define QLA2XXX_MANUFACTURER "Marvell" /* * We have MAILBOX_REGISTER_COUNT sized arrays in a few places, diff --git a/drivers/scsi/qla2xxx/qla_edif.c b/drivers/scsi/qla2xxx/qla_edif.c index 7aee4d093969a0094d03d08bef86471186eaa4b0..969008071decdf8c43b09886c964362cc43a7c55 100644 --- a/drivers/scsi/qla2xxx/qla_edif.c +++ b/drivers/scsi/qla2xxx/qla_edif.c @@ -1058,7 +1058,7 @@ qla_edif_app_getstats(scsi_qla_host_t *vha, struct bsg_job *bsg_job) list_for_each_entry_safe(fcport, tf, &vha->vp_fcports, list) { if (fcport->edif.enable) { - if (pcnt > app_req.num_ports) + if (pcnt >= app_req.num_ports) break; app_reply->elem[pcnt].rekey_count = diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h index 2e4537f9e5b50ef52725120d5e78ffa5075380a4..73cd869caf6093c719cd0e38e434dae39703117a 100644 --- a/drivers/scsi/qla2xxx/qla_gbl.h +++ b/drivers/scsi/qla2xxx/qla_gbl.h @@ -44,7 +44,7 @@ extern int qla2x00_fabric_login(scsi_qla_host_t *, fc_port_t *, uint16_t *); extern int qla2x00_local_device_login(scsi_qla_host_t *, fc_port_t *); extern int qla24xx_els_dcmd_iocb(scsi_qla_host_t *, int, port_id_t); -extern int qla24xx_els_dcmd2_iocb(scsi_qla_host_t *, int, fc_port_t *, bool); +extern int qla24xx_els_dcmd2_iocb(scsi_qla_host_t *, int, fc_port_t *); extern void qla2x00_els_dcmd2_free(scsi_qla_host_t *vha, struct els_plogi *els_plogi); diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 884ed77259f857513469524f05fdf159e2e42a5d..c64e44964d84080a5c9f92b848afa79b0dcbf640 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -1187,8 +1187,12 @@ int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport) return rval; done_free_sp: - /* ref: INIT */ - kref_put(&sp->cmd_kref, qla2x00_sp_release); + /* + * use qla24xx_async_gnl_sp_done to purge all pending gnl request. + * kref_put is call behind the scene. + */ + sp->u.iocb_cmd.u.mbx.in_mb[0] = MBS_COMMAND_ERROR; + qla24xx_async_gnl_sp_done(sp, QLA_COMMAND_ERROR); fcport->flags &= ~(FCF_ASYNC_SENT); done: fcport->flags &= ~(FCF_ASYNC_ACTIVE); @@ -2666,6 +2670,40 @@ exit: return rval; } +static void qla_enable_fce_trace(scsi_qla_host_t *vha) +{ + int rval; + struct qla_hw_data *ha = vha->hw; + + if (ha->fce) { + ha->flags.fce_enabled = 1; + memset(ha->fce, 0, fce_calc_size(ha->fce_bufs)); + rval = qla2x00_enable_fce_trace(vha, + ha->fce_dma, ha->fce_bufs, ha->fce_mb, &ha->fce_bufs); + + if (rval) { + ql_log(ql_log_warn, vha, 0x8033, + "Unable to reinitialize FCE (%d).\n", rval); + ha->flags.fce_enabled = 0; + } + } +} + +static void qla_enable_eft_trace(scsi_qla_host_t *vha) +{ + int rval; + struct qla_hw_data *ha = vha->hw; + + if (ha->eft) { + memset(ha->eft, 0, EFT_SIZE); + rval = qla2x00_enable_eft_trace(vha, ha->eft_dma, EFT_NUM_BUFFERS); + + if (rval) { + ql_log(ql_log_warn, vha, 0x8034, + "Unable to reinitialize EFT (%d).\n", rval); + } + } +} /* * qla2x00_initialize_adapter * Initialize board. @@ -3669,9 +3707,8 @@ qla24xx_chip_diag(scsi_qla_host_t *vha) } static void -qla2x00_init_fce_trace(scsi_qla_host_t *vha) +qla2x00_alloc_fce_trace(scsi_qla_host_t *vha) { - int rval; dma_addr_t tc_dma; void *tc; struct qla_hw_data *ha = vha->hw; @@ -3700,27 +3737,17 @@ qla2x00_init_fce_trace(scsi_qla_host_t *vha) return; } - rval = qla2x00_enable_fce_trace(vha, tc_dma, FCE_NUM_BUFFERS, - ha->fce_mb, &ha->fce_bufs); - if (rval) { - ql_log(ql_log_warn, vha, 0x00bf, - "Unable to initialize FCE (%d).\n", rval); - dma_free_coherent(&ha->pdev->dev, FCE_SIZE, tc, tc_dma); - return; - } - ql_dbg(ql_dbg_init, vha, 0x00c0, "Allocated (%d KB) for FCE...\n", FCE_SIZE / 1024); - ha->flags.fce_enabled = 1; ha->fce_dma = tc_dma; ha->fce = tc; + ha->fce_bufs = FCE_NUM_BUFFERS; } static void -qla2x00_init_eft_trace(scsi_qla_host_t *vha) +qla2x00_alloc_eft_trace(scsi_qla_host_t *vha) { - int rval; dma_addr_t tc_dma; void *tc; struct qla_hw_data *ha = vha->hw; @@ -3745,14 +3772,6 @@ qla2x00_init_eft_trace(scsi_qla_host_t *vha) return; } - rval = qla2x00_enable_eft_trace(vha, tc_dma, EFT_NUM_BUFFERS); - if (rval) { - ql_log(ql_log_warn, vha, 0x00c2, - "Unable to initialize EFT (%d).\n", rval); - dma_free_coherent(&ha->pdev->dev, EFT_SIZE, tc, tc_dma); - return; - } - ql_dbg(ql_dbg_init, vha, 0x00c3, "Allocated (%d KB) EFT ...\n", EFT_SIZE / 1024); @@ -3760,13 +3779,6 @@ qla2x00_init_eft_trace(scsi_qla_host_t *vha) ha->eft = tc; } -static void -qla2x00_alloc_offload_mem(scsi_qla_host_t *vha) -{ - qla2x00_init_fce_trace(vha); - qla2x00_init_eft_trace(vha); -} - void qla2x00_alloc_fw_dump(scsi_qla_host_t *vha) { @@ -3821,10 +3833,10 @@ qla2x00_alloc_fw_dump(scsi_qla_host_t *vha) if (ha->tgt.atio_ring) mq_size += ha->tgt.atio_q_length * sizeof(request_t); - qla2x00_init_fce_trace(vha); + qla2x00_alloc_fce_trace(vha); if (ha->fce) fce_size = sizeof(struct qla2xxx_fce_chain) + FCE_SIZE; - qla2x00_init_eft_trace(vha); + qla2x00_alloc_eft_trace(vha); if (ha->eft) eft_size = EFT_SIZE; } @@ -4254,7 +4266,6 @@ qla2x00_setup_chip(scsi_qla_host_t *vha) struct qla_hw_data *ha = vha->hw; struct device_reg_2xxx __iomem *reg = &ha->iobase->isp; unsigned long flags; - uint16_t fw_major_version; int done_once = 0; if (IS_P3P_TYPE(ha)) { @@ -4321,7 +4332,6 @@ execute_fw_with_lr: goto failed; enable_82xx_npiv: - fw_major_version = ha->fw_major_version; if (IS_P3P_TYPE(ha)) qla82xx_check_md_needed(vha); else @@ -4350,12 +4360,11 @@ enable_82xx_npiv: if (rval != QLA_SUCCESS) goto failed; - if (!fw_major_version && !(IS_P3P_TYPE(ha))) - qla2x00_alloc_offload_mem(vha); - if (ql2xallocfwdump && !(IS_P3P_TYPE(ha))) qla2x00_alloc_fw_dump(vha); + qla_enable_fce_trace(vha); + qla_enable_eft_trace(vha); } else { goto failed; } @@ -7540,12 +7549,12 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha) int qla2x00_abort_isp(scsi_qla_host_t *vha) { - int rval; uint8_t status = 0; struct qla_hw_data *ha = vha->hw; struct scsi_qla_host *vp, *tvp; struct req_que *req = ha->req_q_map[0]; unsigned long flags; + fc_port_t *fcport; if (vha->flags.online) { qla2x00_abort_isp_cleanup(vha); @@ -7614,6 +7623,15 @@ qla2x00_abort_isp(scsi_qla_host_t *vha) "ISP Abort - ISP reg disconnect post nvmram config, exiting.\n"); return status; } + + /* User may have updated [fcp|nvme] prefer in flash */ + list_for_each_entry(fcport, &vha->vp_fcports, list) { + if (NVME_PRIORITY(ha, fcport)) + fcport->do_prli_nvme = 1; + else + fcport->do_prli_nvme = 0; + } + if (!qla2x00_restart_isp(vha)) { clear_bit(RESET_MARKER_NEEDED, &vha->dpc_flags); @@ -7634,31 +7652,7 @@ qla2x00_abort_isp(scsi_qla_host_t *vha) if (IS_QLA81XX(ha) || IS_QLA8031(ha)) qla2x00_get_fw_version(vha); - if (ha->fce) { - ha->flags.fce_enabled = 1; - memset(ha->fce, 0, - fce_calc_size(ha->fce_bufs)); - rval = qla2x00_enable_fce_trace(vha, - ha->fce_dma, ha->fce_bufs, ha->fce_mb, - &ha->fce_bufs); - if (rval) { - ql_log(ql_log_warn, vha, 0x8033, - "Unable to reinitialize FCE " - "(%d).\n", rval); - ha->flags.fce_enabled = 0; - } - } - if (ha->eft) { - memset(ha->eft, 0, EFT_SIZE); - rval = qla2x00_enable_eft_trace(vha, - ha->eft_dma, EFT_NUM_BUFFERS); - if (rval) { - ql_log(ql_log_warn, vha, 0x8034, - "Unable to reinitialize EFT " - "(%d).\n", rval); - } - } } else { /* failed the ISP abort */ vha->flags.online = 1; if (test_bit(ISP_ABORT_RETRY, &vha->dpc_flags)) { @@ -7708,6 +7702,14 @@ qla2x00_abort_isp(scsi_qla_host_t *vha) atomic_inc(&vp->vref_count); spin_unlock_irqrestore(&ha->vport_slock, flags); + /* User may have updated [fcp|nvme] prefer in flash */ + list_for_each_entry(fcport, &vp->vp_fcports, list) { + if (NVME_PRIORITY(ha, fcport)) + fcport->do_prli_nvme = 1; + else + fcport->do_prli_nvme = 0; + } + qla2x00_vp_abort_isp(vp); spin_lock_irqsave(&ha->vport_slock, flags); diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index 9e524d52dc86229cf1fc42a2210e9053ba3d3783..7bccd525ee19b91c9bc448661c6d54176ac14c9b 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -2588,6 +2588,33 @@ void qla2x00_sp_release(struct kref *kref) { struct srb *sp = container_of(kref, struct srb, cmd_kref); + struct scsi_qla_host *vha = sp->vha; + + switch (sp->type) { + case SRB_CT_PTHRU_CMD: + /* GPSC & GFPNID use fcport->ct_desc.ct_sns for both req & rsp */ + if (sp->u.iocb_cmd.u.ctarg.req && + (!sp->fcport || + sp->u.iocb_cmd.u.ctarg.req != sp->fcport->ct_desc.ct_sns)) { + dma_free_coherent(&vha->hw->pdev->dev, + sp->u.iocb_cmd.u.ctarg.req_allocated_size, + sp->u.iocb_cmd.u.ctarg.req, + sp->u.iocb_cmd.u.ctarg.req_dma); + sp->u.iocb_cmd.u.ctarg.req = NULL; + } + if (sp->u.iocb_cmd.u.ctarg.rsp && + (!sp->fcport || + sp->u.iocb_cmd.u.ctarg.rsp != sp->fcport->ct_desc.ct_sns)) { + dma_free_coherent(&vha->hw->pdev->dev, + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size, + sp->u.iocb_cmd.u.ctarg.rsp, + sp->u.iocb_cmd.u.ctarg.rsp_dma); + sp->u.iocb_cmd.u.ctarg.rsp = NULL; + } + break; + default: + break; + } sp->free(sp); } @@ -2611,7 +2638,8 @@ static void qla2x00_els_dcmd_sp_free(srb_t *sp) { struct srb_iocb *elsio = &sp->u.iocb_cmd; - kfree(sp->fcport); + if (sp->fcport) + qla2x00_free_fcport(sp->fcport); if (elsio->u.els_logo.els_logo_pyld) dma_free_coherent(&sp->vha->hw->pdev->dev, DMA_POOL_SIZE, @@ -2693,7 +2721,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode, */ sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL); if (!sp) { - kfree(fcport); + qla2x00_free_fcport(fcport); ql_log(ql_log_info, vha, 0x70e6, "SRB allocation failed\n"); return -ENOMEM; @@ -2724,6 +2752,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode, if (!elsio->u.els_logo.els_logo_pyld) { /* ref: INIT */ kref_put(&sp->cmd_kref, qla2x00_sp_release); + qla2x00_free_fcport(fcport); return QLA_FUNCTION_FAILED; } @@ -2748,6 +2777,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode, if (rval != QLA_SUCCESS) { /* ref: INIT */ kref_put(&sp->cmd_kref, qla2x00_sp_release); + qla2x00_free_fcport(fcport); return QLA_FUNCTION_FAILED; } @@ -3013,7 +3043,7 @@ static void qla2x00_els_dcmd2_sp_done(srb_t *sp, int res) int qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, - fc_port_t *fcport, bool wait) + fc_port_t *fcport) { srb_t *sp; struct srb_iocb *elsio = NULL; @@ -3028,8 +3058,7 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, if (!sp) { ql_log(ql_log_info, vha, 0x70e6, "SRB allocation failed\n"); - fcport->flags &= ~FCF_ASYNC_ACTIVE; - return -ENOMEM; + goto done; } fcport->flags |= FCF_ASYNC_SENT; @@ -3038,9 +3067,6 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, ql_dbg(ql_dbg_io, vha, 0x3073, "%s Enter: PLOGI portid=%06x\n", __func__, fcport->d_id.b24); - if (wait) - sp->flags = SRB_WAKEUP_ON_COMP; - sp->type = SRB_ELS_DCMD; sp->name = "ELS_DCMD"; sp->fcport = fcport; @@ -3056,7 +3082,7 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, if (!elsio->u.els_plogi.els_plogi_pyld) { rval = QLA_FUNCTION_FAILED; - goto out; + goto done_free_sp; } resp_ptr = elsio->u.els_plogi.els_resp_pyld = @@ -3065,7 +3091,7 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, if (!elsio->u.els_plogi.els_resp_pyld) { rval = QLA_FUNCTION_FAILED; - goto out; + goto done_free_sp; } ql_dbg(ql_dbg_io, vha, 0x3073, "PLOGI %p %p\n", ptr, resp_ptr); @@ -3080,7 +3106,6 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, if (els_opcode == ELS_DCMD_PLOGI && DBELL_ACTIVE(vha)) { struct fc_els_flogi *p = ptr; - p->fl_csp.sp_features |= cpu_to_be16(FC_SP_FT_SEC); } @@ -3089,10 +3114,11 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, (uint8_t *)elsio->u.els_plogi.els_plogi_pyld, sizeof(*elsio->u.els_plogi.els_plogi_pyld)); - init_completion(&elsio->u.els_plogi.comp); rval = qla2x00_start_sp(sp); if (rval != QLA_SUCCESS) { - rval = QLA_FUNCTION_FAILED; + fcport->flags |= FCF_LOGIN_NEEDED; + set_bit(RELOGIN_NEEDED, &vha->dpc_flags); + goto done_free_sp; } else { ql_dbg(ql_dbg_disc, vha, 0x3074, "%s PLOGI sent, hdl=%x, loopid=%x, to port_id %06x from port_id %06x\n", @@ -3100,21 +3126,15 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, fcport->d_id.b24, vha->d_id.b24); } - if (wait) { - wait_for_completion(&elsio->u.els_plogi.comp); - - if (elsio->u.els_plogi.comp_status != CS_COMPLETE) - rval = QLA_FUNCTION_FAILED; - } else { - goto done; - } + return rval; -out: - fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); +done_free_sp: qla2x00_els_dcmd2_free(vha, &elsio->u.els_plogi); /* ref: INIT */ kref_put(&sp->cmd_kref, qla2x00_sp_release); done: + fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); + qla2x00_set_fcport_disc_state(fcport, DSC_DELETED); return rval; } @@ -3916,7 +3936,7 @@ qla2x00_start_sp(srb_t *sp) return -EAGAIN; } - pkt = __qla2x00_alloc_iocbs(sp->qpair, sp); + pkt = qla2x00_alloc_iocbs_ready(sp->qpair, sp); if (!pkt) { rval = -EAGAIN; ql_log(ql_log_warn, vha, 0x700c, diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index f794f4363a38cff2a9a613964b47c92a0b93d37e..1fd9485985f2e547b1b06098d028cdddf793d092 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -194,7 +194,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp) if (ha->flags.purge_mbox || chip_reset != ha->chip_reset || ha->flags.eeh_busy) { ql_log(ql_log_warn, vha, 0xd035, - "Error detected: purge[%d] eeh[%d] cmd=0x%x, Exiting.\n", + "Purge mbox: purge[%d] eeh[%d] cmd=0x%x, Exiting.\n", ha->flags.purge_mbox, ha->flags.eeh_busy, mcp->mb[0]); rval = QLA_ABORTED; goto premature_exit; diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 25ca0544b96399acf3b77576b5ab88aa46a7dcba..25d0c2bfdd742c2549d441814a4319556099f728 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -5562,7 +5562,7 @@ qla2x00_do_work(struct scsi_qla_host *vha) break; case QLA_EVT_ELS_PLOGI: qla24xx_els_dcmd2_iocb(vha, ELS_DCMD_PLOGI, - e->u.fcport.fcport, false); + e->u.fcport.fcport); break; case QLA_EVT_SA_REPLACE: rc = qla24xx_issue_sa_replace_iocb(vha, e); diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 5a5beb41786ed5999cec4fbcaaab3c29b2bf8359..043cfa10c7167486ecf995629494316360819753 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1079,6 +1079,16 @@ void qlt_free_session_done(struct work_struct *work) "%s: sess %p logout completed\n", __func__, sess); } + /* check for any straggling io left behind */ + if (!(sess->flags & FCF_FCP2_DEVICE) && + qla2x00_eh_wait_for_pending_commands(sess->vha, sess->d_id.b24, 0, WAIT_TARGET)) { + ql_log(ql_log_warn, vha, 0x3027, + "IO not return. Resetting.\n"); + set_bit(ISP_ABORT_NEEDED, &vha->dpc_flags); + qla2xxx_wake_dpc(vha); + qla2x00_wait_for_chip_reset(vha); + } + if (sess->logo_ack_needed) { sess->logo_ack_needed = 0; qla24xx_async_notify_ack(vha, sess, diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 3cda5d26b66ca52a220aae21d8d4530e31292801..e70ab8db30142def437904122237100b4f420b9f 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -328,21 +328,39 @@ static int scsi_vpd_inquiry(struct scsi_device *sdev, unsigned char *buffer, return result + 4; } +enum scsi_vpd_parameters { + SCSI_VPD_HEADER_SIZE = 4, + SCSI_VPD_LIST_SIZE = 36, +}; + static int scsi_get_vpd_size(struct scsi_device *sdev, u8 page) { - unsigned char vpd_header[SCSI_VPD_HEADER_SIZE] __aligned(4); + unsigned char vpd[SCSI_VPD_LIST_SIZE] __aligned(4); int result; if (sdev->no_vpd_size) return SCSI_DEFAULT_VPD_LEN; + /* + * Fetch the supported pages VPD and validate that the requested page + * number is present. + */ + if (page != 0) { + result = scsi_vpd_inquiry(sdev, vpd, 0, sizeof(vpd)); + if (result < SCSI_VPD_HEADER_SIZE) + return 0; + + result -= SCSI_VPD_HEADER_SIZE; + if (!memchr(&vpd[SCSI_VPD_HEADER_SIZE], page, result)) + return 0; + } /* * Fetch the VPD page header to find out how big the page * is. This is done to prevent problems on legacy devices * which can not handle allocation lengths as large as * potentially requested by the caller. */ - result = scsi_vpd_inquiry(sdev, vpd_header, page, sizeof(vpd_header)); + result = scsi_vpd_inquiry(sdev, vpd, page, SCSI_VPD_HEADER_SIZE); if (result < 0) return 0; diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 66290961c47c231a6e3c44716aaf8935f5ff3c48..cfa6f0edff17ce67bdb4c4f02e7ed499af9a3d42 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -277,11 +277,12 @@ static void scsi_eh_inc_host_failed(struct rcu_head *head) { struct scsi_cmnd *scmd = container_of(head, typeof(*scmd), rcu); struct Scsi_Host *shost = scmd->device->host; + unsigned int busy = scsi_host_busy(shost); unsigned long flags; spin_lock_irqsave(shost->host_lock, flags); shost->host_failed++; - scsi_eh_wakeup(shost, scsi_host_busy(shost)); + scsi_eh_wakeup(shost, busy); spin_unlock_irqrestore(shost->host_lock, flags); } diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 0e7e9f1e5a0297c1e8cc3716403d1e9499cea3da..5c5954b78585e243ef1f61a989145fbac501bca4 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -280,9 +280,11 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost, struct scsi_cmnd *cmd) rcu_read_lock(); __clear_bit(SCMD_STATE_INFLIGHT, &cmd->state); if (unlikely(scsi_host_in_recovery(shost))) { + unsigned int busy = scsi_host_busy(shost); + spin_lock_irqsave(shost->host_lock, flags); if (shost->host_failed || shost->host_eh_scheduled) - scsi_eh_wakeup(shost, scsi_host_busy(shost)); + scsi_eh_wakeup(shost, busy); spin_unlock_irqrestore(shost->host_lock, flags); } rcu_read_unlock(); diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index bab00b65bc9d1f4901fea9000bec160f0136fb33..852d509b19b2b7b0860a0a5273c7b8bad03ccbe0 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -1611,6 +1611,40 @@ int scsi_add_device(struct Scsi_Host *host, uint channel, } EXPORT_SYMBOL(scsi_add_device); +int scsi_resume_device(struct scsi_device *sdev) +{ + struct device *dev = &sdev->sdev_gendev; + int ret = 0; + + device_lock(dev); + + /* + * Bail out if the device or its queue are not running. Otherwise, + * the rescan may block waiting for commands to be executed, with us + * holding the device lock. This can result in a potential deadlock + * in the power management core code when system resume is on-going. + */ + if (sdev->sdev_state != SDEV_RUNNING || + blk_queue_pm_only(sdev->request_queue)) { + ret = -EWOULDBLOCK; + goto unlock; + } + + if (dev->driver && try_module_get(dev->driver->owner)) { + struct scsi_driver *drv = to_scsi_driver(dev->driver); + + if (drv->resume) + ret = drv->resume(dev); + module_put(dev->driver->owner); + } + +unlock: + device_unlock(dev); + + return ret; +} +EXPORT_SYMBOL(scsi_resume_device); + int scsi_rescan_device(struct scsi_device *sdev) { struct device *dev = &sdev->sdev_gendev; diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 31b5273f43a71ecc2a25ee1de79a0d53f06b6177..3ec9b324fdcf9b462a5f0ed3d245e93eb6e63842 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -110,6 +110,7 @@ static int sd_suspend_system(struct device *); static int sd_suspend_runtime(struct device *); static int sd_resume_system(struct device *); static int sd_resume_runtime(struct device *); +static int sd_resume(struct device *); static void sd_rescan(struct device *); static blk_status_t sd_init_command(struct scsi_cmnd *SCpnt); static void sd_uninit_command(struct scsi_cmnd *SCpnt); @@ -691,6 +692,7 @@ static struct scsi_driver sd_template = { .pm = &sd_pm_ops, }, .rescan = sd_rescan, + .resume = sd_resume, .init_command = sd_init_command, .uninit_command = sd_uninit_command, .done = sd_done, @@ -3284,6 +3286,24 @@ static bool sd_validate_opt_xfer_size(struct scsi_disk *sdkp, return true; } +static void sd_read_block_zero(struct scsi_disk *sdkp) +{ + unsigned int buf_len = sdkp->device->sector_size; + char *buffer, cmd[10] = { }; + + buffer = kmalloc(buf_len, GFP_KERNEL); + if (!buffer) + return; + + cmd[0] = READ_10; + put_unaligned_be32(0, &cmd[2]); /* Logical block address 0 */ + put_unaligned_be16(1, &cmd[7]); /* Transfer 1 logical block */ + + scsi_execute_req(sdkp->device, cmd, DMA_FROM_DEVICE, buffer, buf_len, + NULL, SD_TIMEOUT, sdkp->max_retries, NULL); + kfree(buffer); +} + /** * sd_revalidate_disk - called the first time a new disk is seen, * performs disk spin up, read_capacity, etc. @@ -3323,7 +3343,13 @@ static int sd_revalidate_disk(struct gendisk *disk) */ if (sdkp->media_present) { sd_read_capacity(sdkp, buffer); - + /* + * Some USB/UAS devices return generic values for mode pages + * until the media has been accessed. Trigger a READ operation + * to force the device to populate mode pages. + */ + if (sdp->read_before_ms) + sd_read_block_zero(sdkp); /* * set the default to rotational. All non-rotational devices * support the block characteristics VPD page, which will @@ -3610,7 +3636,7 @@ static int sd_probe(struct device *dev) error = device_add_disk(dev, gd, NULL); if (error) { - put_device(&sdkp->disk_dev); + device_unregister(&sdkp->disk_dev); put_disk(gd); goto out; } @@ -3806,7 +3832,22 @@ static int sd_suspend_runtime(struct device *dev) return sd_suspend_common(dev, true); } -static int sd_resume(struct device *dev, bool runtime) +static int sd_resume(struct device *dev) +{ + struct scsi_disk *sdkp = dev_get_drvdata(dev); + + if (sdkp->device->no_start_on_resume) + sd_printk(KERN_NOTICE, sdkp, "Starting disk\n"); + + if (opal_unlock_from_suspend(sdkp->opal_dev)) { + sd_printk(KERN_NOTICE, sdkp, "OPAL unlock failed\n"); + return -EIO; + } + + return 0; +} + +static int sd_resume_common(struct device *dev, bool runtime) { struct scsi_disk *sdkp = dev_get_drvdata(dev); int ret = 0; @@ -3825,7 +3866,7 @@ static int sd_resume(struct device *dev, bool runtime) } if (!ret) { - opal_unlock_from_suspend(sdkp->opal_dev); + sd_resume(dev); sdkp->suspended = false; } @@ -3844,7 +3885,7 @@ static int sd_resume_system(struct device *dev) return 0; } - return sd_resume(dev, false); + return sd_resume_common(dev, false); } static int sd_resume_runtime(struct device *dev) @@ -3868,7 +3909,7 @@ static int sd_resume_runtime(struct device *dev) "Failed to clear sense data\n"); } - return sd_resume(dev, true); + return sd_resume_common(dev, true); } /** diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c index 47d487729635c41783d773628a9cc036f3ac3d6b..e44f6bb25a8eabe3c75b82870a94d1c6721c2f0d 100644 --- a/drivers/scsi/smartpqi/smartpqi_init.c +++ b/drivers/scsi/smartpqi/smartpqi_init.c @@ -6449,8 +6449,11 @@ static void pqi_map_queues(struct Scsi_Host *shost) { struct pqi_ctrl_info *ctrl_info = shost_to_hba(shost); - blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT], + if (!ctrl_info->disable_managed_interrupts) + return blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT], ctrl_info->pci_dev, 0); + else + return blk_mq_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT]); } static inline bool pqi_is_tape_changer_device(struct pqi_scsi_dev *device) diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index c2d981d5a2dd54b6ebfcc25497ce701347a5af82..4fad9d85bd6f9f447cfa6f8f2bd0092f910d77a4 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -326,6 +326,7 @@ enum storvsc_request_type { */ static int storvsc_ringbuffer_size = (128 * 1024); +static int aligned_ringbuffer_size; static u32 max_outstanding_req_per_channel; static int storvsc_change_queue_depth(struct scsi_device *sdev, int queue_depth); @@ -683,8 +684,8 @@ static void handle_sc_creation(struct vmbus_channel *new_sc) new_sc->next_request_id_callback = storvsc_next_request_id; ret = vmbus_open(new_sc, - storvsc_ringbuffer_size, - storvsc_ringbuffer_size, + aligned_ringbuffer_size, + aligned_ringbuffer_size, (void *)&props, sizeof(struct vmstorage_channel_properties), storvsc_on_channel_callback, new_sc); @@ -1964,7 +1965,7 @@ static int storvsc_probe(struct hv_device *device, dma_set_min_align_mask(&device->device, HV_HYP_PAGE_SIZE - 1); stor_device->port_number = host->host_no; - ret = storvsc_connect_to_vsp(device, storvsc_ringbuffer_size, is_fc); + ret = storvsc_connect_to_vsp(device, aligned_ringbuffer_size, is_fc); if (ret) goto err_out1; @@ -2157,7 +2158,7 @@ static int storvsc_resume(struct hv_device *hv_dev) { int ret; - ret = storvsc_connect_to_vsp(hv_dev, storvsc_ringbuffer_size, + ret = storvsc_connect_to_vsp(hv_dev, aligned_ringbuffer_size, hv_dev_is_fc(hv_dev)); return ret; } @@ -2191,8 +2192,9 @@ static int __init storvsc_drv_init(void) * the ring buffer indices) by the max request size (which is * vmbus_channel_packet_multipage_buffer + struct vstor_packet + u64) */ + aligned_ringbuffer_size = VMBUS_RING_SIZE(storvsc_ringbuffer_size); max_outstanding_req_per_channel = - ((storvsc_ringbuffer_size - PAGE_SIZE) / + ((aligned_ringbuffer_size - PAGE_SIZE) / ALIGN(MAX_MULTIPAGE_BUFFER_PACKET + sizeof(struct vstor_packet) + sizeof(u64), sizeof(u64))); diff --git a/drivers/slimbus/core.c b/drivers/slimbus/core.c index 219483b79c09ced217d01e86f384cad51b8b4c20..37fd655994ef31b0e88ce1516bedcf5dd5c65040 100644 --- a/drivers/slimbus/core.c +++ b/drivers/slimbus/core.c @@ -436,8 +436,8 @@ static int slim_device_alloc_laddr(struct slim_device *sbdev, if (ret < 0) goto err; } else if (report_present) { - ret = ida_simple_get(&ctrl->laddr_ida, - 0, SLIM_LA_MANAGER - 1, GFP_KERNEL); + ret = ida_alloc_max(&ctrl->laddr_ida, + SLIM_LA_MANAGER - 1, GFP_KERNEL); if (ret < 0) goto err; diff --git a/drivers/slimbus/qcom-ngd-ctrl.c b/drivers/slimbus/qcom-ngd-ctrl.c index 76c5e446d2433c4bcee6666af5ca78db89b55c62..da8555f3b6ca537d4372851d78d3fc37887caa68 100644 --- a/drivers/slimbus/qcom-ngd-ctrl.c +++ b/drivers/slimbus/qcom-ngd-ctrl.c @@ -1376,7 +1376,11 @@ static void qcom_slim_ngd_up_worker(struct work_struct *work) ctrl = container_of(work, struct qcom_slim_ngd_ctrl, ngd_up_work); /* Make sure qmi service is up before continuing */ - wait_for_completion_interruptible(&ctrl->qmi_up); + if (!wait_for_completion_interruptible_timeout(&ctrl->qmi_up, + msecs_to_jiffies(MSEC_PER_SEC))) { + dev_err(ctrl->dev, "QMI wait timeout\n"); + return; + } mutex_lock(&ctrl->ssr_lock); qcom_slim_ngd_enable(ctrl, true); diff --git a/drivers/soc/fsl/dpio/dpio-service.c b/drivers/soc/fsl/dpio/dpio-service.c index 1d2b27e3ea63f800c97b76c936940520fc96fa0b..b811446e0fa55febb51e6338c53ec62f183e9955 100644 --- a/drivers/soc/fsl/dpio/dpio-service.c +++ b/drivers/soc/fsl/dpio/dpio-service.c @@ -523,7 +523,7 @@ int dpaa2_io_service_enqueue_multiple_desc_fq(struct dpaa2_io *d, struct qbman_eq_desc *ed; int i, ret; - ed = kcalloc(sizeof(struct qbman_eq_desc), 32, GFP_KERNEL); + ed = kcalloc(32, sizeof(struct qbman_eq_desc), GFP_KERNEL); if (!ed) return -ENOMEM; diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c index 739e4eee6b75ca666abe04004184fc451a09ad21..7e9074519ad22d7d6b26a9148f5f65b4e2e79b4f 100644 --- a/drivers/soc/fsl/qbman/qman.c +++ b/drivers/soc/fsl/qbman/qman.c @@ -991,7 +991,7 @@ struct qman_portal { /* linked-list of CSCN handlers. */ struct list_head cgr_cbs; /* list lock */ - spinlock_t cgr_lock; + raw_spinlock_t cgr_lock; struct work_struct congestion_work; struct work_struct mr_work; char irqname[MAX_IRQNAME]; @@ -1281,7 +1281,7 @@ static int qman_create_portal(struct qman_portal *portal, /* if the given mask is NULL, assume all CGRs can be seen */ qman_cgrs_fill(&portal->cgrs[0]); INIT_LIST_HEAD(&portal->cgr_cbs); - spin_lock_init(&portal->cgr_lock); + raw_spin_lock_init(&portal->cgr_lock); INIT_WORK(&portal->congestion_work, qm_congestion_task); INIT_WORK(&portal->mr_work, qm_mr_process_task); portal->bits = 0; @@ -1456,11 +1456,14 @@ static void qm_congestion_task(struct work_struct *work) union qm_mc_result *mcr; struct qman_cgr *cgr; - spin_lock(&p->cgr_lock); + /* + * FIXME: QM_MCR_TIMEOUT is 10ms, which is too long for a raw spinlock! + */ + raw_spin_lock_irq(&p->cgr_lock); qm_mc_start(&p->p); qm_mc_commit(&p->p, QM_MCC_VERB_QUERYCONGESTION); if (!qm_mc_result_timeout(&p->p, &mcr)) { - spin_unlock(&p->cgr_lock); + raw_spin_unlock_irq(&p->cgr_lock); dev_crit(p->config->dev, "QUERYCONGESTION timeout\n"); qman_p_irqsource_add(p, QM_PIRQ_CSCI); return; @@ -1476,7 +1479,7 @@ static void qm_congestion_task(struct work_struct *work) list_for_each_entry(cgr, &p->cgr_cbs, node) if (cgr->cb && qman_cgrs_get(&c, cgr->cgrid)) cgr->cb(p, cgr, qman_cgrs_get(&rr, cgr->cgrid)); - spin_unlock(&p->cgr_lock); + raw_spin_unlock_irq(&p->cgr_lock); qman_p_irqsource_add(p, QM_PIRQ_CSCI); } @@ -2440,7 +2443,7 @@ int qman_create_cgr(struct qman_cgr *cgr, u32 flags, preempt_enable(); cgr->chan = p->config->channel; - spin_lock(&p->cgr_lock); + raw_spin_lock_irq(&p->cgr_lock); if (opts) { struct qm_mcc_initcgr local_opts = *opts; @@ -2477,7 +2480,7 @@ int qman_create_cgr(struct qman_cgr *cgr, u32 flags, qman_cgrs_get(&p->cgrs[1], cgr->cgrid)) cgr->cb(p, cgr, 1); out: - spin_unlock(&p->cgr_lock); + raw_spin_unlock_irq(&p->cgr_lock); put_affine_portal(); return ret; } @@ -2512,7 +2515,7 @@ int qman_delete_cgr(struct qman_cgr *cgr) return -EINVAL; memset(&local_opts, 0, sizeof(struct qm_mcc_initcgr)); - spin_lock_irqsave(&p->cgr_lock, irqflags); + raw_spin_lock_irqsave(&p->cgr_lock, irqflags); list_del(&cgr->node); /* * If there are no other CGR objects for this CGRID in the list, @@ -2537,7 +2540,7 @@ int qman_delete_cgr(struct qman_cgr *cgr) /* add back to the list */ list_add(&cgr->node, &p->cgr_cbs); release_lock: - spin_unlock_irqrestore(&p->cgr_lock, irqflags); + raw_spin_unlock_irqrestore(&p->cgr_lock, irqflags); put_affine_portal(); return ret; } @@ -2577,9 +2580,9 @@ static int qman_update_cgr(struct qman_cgr *cgr, struct qm_mcc_initcgr *opts) if (!p) return -EINVAL; - spin_lock_irqsave(&p->cgr_lock, irqflags); + raw_spin_lock_irqsave(&p->cgr_lock, irqflags); ret = qm_modify_cgr(cgr, 0, opts); - spin_unlock_irqrestore(&p->cgr_lock, irqflags); + raw_spin_unlock_irqrestore(&p->cgr_lock, irqflags); put_affine_portal(); return ret; } diff --git a/drivers/soc/mediatek/mtk-pm-domains.c b/drivers/soc/mediatek/mtk-pm-domains.c index 474b272f9b02d6cf305f59bf238762d9db93827d..832adb570b501226a2e9d93bf79b0b228f46399a 100644 --- a/drivers/soc/mediatek/mtk-pm-domains.c +++ b/drivers/soc/mediatek/mtk-pm-domains.c @@ -499,6 +499,11 @@ static int scpsys_add_subdomain(struct scpsys *scpsys, struct device_node *paren goto err_put_node; } + /* recursive call to add all subdomains */ + ret = scpsys_add_subdomain(scpsys, child); + if (ret) + goto err_put_node; + ret = pm_genpd_add_subdomain(parent_pd, child_pd); if (ret) { dev_err(scpsys->dev, "failed to add %s subdomain to parent %s\n", @@ -508,11 +513,6 @@ static int scpsys_add_subdomain(struct scpsys *scpsys, struct device_node *paren dev_dbg(scpsys->dev, "%s add subdomain: %s\n", parent_pd->name, child_pd->name); } - - /* recursive call to add all subdomains */ - ret = scpsys_add_subdomain(scpsys, child); - if (ret) - goto err_put_node; } return 0; @@ -526,9 +526,6 @@ static void scpsys_remove_one_domain(struct scpsys_domain *pd) { int ret; - if (scpsys_domain_is_on(pd)) - scpsys_power_off(&pd->genpd); - /* * We're in the error cleanup already, so we only complain, * but won't emit another error on top of the original one. @@ -538,6 +535,8 @@ static void scpsys_remove_one_domain(struct scpsys_domain *pd) dev_err(pd->scpsys->dev, "failed to remove domain '%s' : %d - state may be inconsistent\n", pd->genpd.name, ret); + if (scpsys_domain_is_on(pd)) + scpsys_power_off(&pd->genpd); clk_bulk_put(pd->num_clks, pd->clks); clk_bulk_put(pd->num_subsys_clks, pd->subsys_clks); diff --git a/drivers/soc/microchip/Kconfig b/drivers/soc/microchip/Kconfig index eb656b33156ba405c7d452dc29540462f1636c20..f19e74d342aa25c943dc61a0595d9d41a70428d2 100644 --- a/drivers/soc/microchip/Kconfig +++ b/drivers/soc/microchip/Kconfig @@ -1,5 +1,5 @@ config POLARFIRE_SOC_SYS_CTRL - tristate "POLARFIRE_SOC_SYS_CTRL" + tristate "Microchip PolarFire SoC (MPFS) system controller support" depends on POLARFIRE_SOC_MAILBOX help This driver adds support for the PolarFire SoC (MPFS) system controller. diff --git a/drivers/soc/qcom/rpmhpd.c b/drivers/soc/qcom/rpmhpd.c index 092f6ab09acf3c5d6ab11a60c3522c9eba6c15a5..6efe36aeb48e9fd7c54a98073567466da47f9a34 100644 --- a/drivers/soc/qcom/rpmhpd.c +++ b/drivers/soc/qcom/rpmhpd.c @@ -195,7 +195,6 @@ static struct rpmhpd *sa8540p_rpmhpds[] = { [SC8280XP_CX] = &cx, [SC8280XP_CX_AO] = &cx_ao, [SC8280XP_EBI] = &ebi, - [SC8280XP_GFX] = &gfx, [SC8280XP_LCX] = &lcx, [SC8280XP_LMX] = &lmx, [SC8280XP_MMCX] = &mmcx, @@ -492,12 +491,15 @@ static int rpmhpd_aggregate_corner(struct rpmhpd *pd, unsigned int corner) unsigned int active_corner, sleep_corner; unsigned int this_active_corner = 0, this_sleep_corner = 0; unsigned int peer_active_corner = 0, peer_sleep_corner = 0; + unsigned int peer_enabled_corner; to_active_sleep(pd, corner, &this_active_corner, &this_sleep_corner); - if (peer && peer->enabled) - to_active_sleep(peer, peer->corner, &peer_active_corner, + if (peer && peer->enabled) { + peer_enabled_corner = max(peer->corner, peer->enable_corner); + to_active_sleep(peer, peer_enabled_corner, &peer_active_corner, &peer_sleep_corner); + } active_corner = max(this_active_corner, peer_active_corner); diff --git a/drivers/soc/renesas/r8a77980-sysc.c b/drivers/soc/renesas/r8a77980-sysc.c index 39ca84a67daadd21202e1ba80f13ec6cbc671a7a..621e411fc9991a4050cd6da699695912f18a46b0 100644 --- a/drivers/soc/renesas/r8a77980-sysc.c +++ b/drivers/soc/renesas/r8a77980-sysc.c @@ -25,7 +25,8 @@ static const struct rcar_sysc_area r8a77980_areas[] __initconst = { PD_CPU_NOCR }, { "ca53-cpu3", 0x200, 3, R8A77980_PD_CA53_CPU3, R8A77980_PD_CA53_SCU, PD_CPU_NOCR }, - { "cr7", 0x240, 0, R8A77980_PD_CR7, R8A77980_PD_ALWAYS_ON }, + { "cr7", 0x240, 0, R8A77980_PD_CR7, R8A77980_PD_ALWAYS_ON, + PD_CPU_NOCR }, { "a3ir", 0x180, 0, R8A77980_PD_A3IR, R8A77980_PD_ALWAYS_ON }, { "a2ir0", 0x400, 0, R8A77980_PD_A2IR0, R8A77980_PD_A3IR }, { "a2ir1", 0x400, 1, R8A77980_PD_A2IR1, R8A77980_PD_A3IR }, diff --git a/drivers/soundwire/dmi-quirks.c b/drivers/soundwire/dmi-quirks.c index 9ebdd0cd0b1cf598b35902541c0997c5934578d3..91ab97a456fa9fe898bcb1f9f496bb0d8152356c 100644 --- a/drivers/soundwire/dmi-quirks.c +++ b/drivers/soundwire/dmi-quirks.c @@ -130,6 +130,14 @@ static const struct dmi_system_id adr_remap_quirk_table[] = { }, .driver_data = (void *)intel_rooks_county, }, + { + /* quirk used for NUC15 LAPRC710 skew */ + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Intel Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "LAPRC710"), + }, + .driver_data = (void *)intel_rooks_county, + }, { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), diff --git a/drivers/spi/spi-axi-spi-engine.c b/drivers/spi/spi-axi-spi-engine.c index 80c3e38f5c1b52483866d161fdbc3d37c7792717..a5f0a61b266f1f04c9060f4fb49ae45469fa584b 100644 --- a/drivers/spi/spi-axi-spi-engine.c +++ b/drivers/spi/spi-axi-spi-engine.c @@ -6,6 +6,8 @@ */ #include +#include +#include #include #include #include @@ -13,12 +15,6 @@ #include #include -#define SPI_ENGINE_VERSION_MAJOR(x) ((x >> 16) & 0xff) -#define SPI_ENGINE_VERSION_MINOR(x) ((x >> 8) & 0xff) -#define SPI_ENGINE_VERSION_PATCH(x) (x & 0xff) - -#define SPI_ENGINE_REG_VERSION 0x00 - #define SPI_ENGINE_REG_RESET 0x40 #define SPI_ENGINE_REG_INT_ENABLE 0x80 @@ -78,28 +74,42 @@ struct spi_engine_program { uint16_t instructions[]; }; -struct spi_engine { - struct clk *clk; - struct clk *ref_clk; - - spinlock_t lock; - - void __iomem *base; - - struct spi_message *msg; +/** + * struct spi_engine_message_state - SPI engine per-message state + */ +struct spi_engine_message_state { + /** Instructions for executing this message. */ struct spi_engine_program *p; + /** Number of elements in cmd_buf array. */ unsigned cmd_length; + /** Array of commands not yet written to CMD FIFO. */ const uint16_t *cmd_buf; - + /** Next xfer with tx_buf not yet fully written to TX FIFO. */ struct spi_transfer *tx_xfer; + /** Size of tx_buf in bytes. */ unsigned int tx_length; + /** Bytes not yet written to TX FIFO. */ const uint8_t *tx_buf; - + /** Next xfer with rx_buf not yet fully written to RX FIFO. */ struct spi_transfer *rx_xfer; + /** Size of tx_buf in bytes. */ unsigned int rx_length; + /** Bytes not yet written to the RX FIFO. */ uint8_t *rx_buf; + /** ID to correlate SYNC interrupts with this message. */ + u8 sync_id; +}; + +struct spi_engine { + struct clk *clk; + struct clk *ref_clk; + + spinlock_t lock; - unsigned int sync_id; + void __iomem *base; + + struct spi_message *msg; + struct ida sync_ida; unsigned int completed_id; unsigned int int_enable; @@ -258,106 +268,111 @@ static void spi_engine_xfer_next(struct spi_engine *spi_engine, static void spi_engine_tx_next(struct spi_engine *spi_engine) { - struct spi_transfer *xfer = spi_engine->tx_xfer; + struct spi_engine_message_state *st = spi_engine->msg->state; + struct spi_transfer *xfer = st->tx_xfer; do { spi_engine_xfer_next(spi_engine, &xfer); } while (xfer && !xfer->tx_buf); - spi_engine->tx_xfer = xfer; + st->tx_xfer = xfer; if (xfer) { - spi_engine->tx_length = xfer->len; - spi_engine->tx_buf = xfer->tx_buf; + st->tx_length = xfer->len; + st->tx_buf = xfer->tx_buf; } else { - spi_engine->tx_buf = NULL; + st->tx_buf = NULL; } } static void spi_engine_rx_next(struct spi_engine *spi_engine) { - struct spi_transfer *xfer = spi_engine->rx_xfer; + struct spi_engine_message_state *st = spi_engine->msg->state; + struct spi_transfer *xfer = st->rx_xfer; do { spi_engine_xfer_next(spi_engine, &xfer); } while (xfer && !xfer->rx_buf); - spi_engine->rx_xfer = xfer; + st->rx_xfer = xfer; if (xfer) { - spi_engine->rx_length = xfer->len; - spi_engine->rx_buf = xfer->rx_buf; + st->rx_length = xfer->len; + st->rx_buf = xfer->rx_buf; } else { - spi_engine->rx_buf = NULL; + st->rx_buf = NULL; } } static bool spi_engine_write_cmd_fifo(struct spi_engine *spi_engine) { void __iomem *addr = spi_engine->base + SPI_ENGINE_REG_CMD_FIFO; + struct spi_engine_message_state *st = spi_engine->msg->state; unsigned int n, m, i; const uint16_t *buf; n = readl_relaxed(spi_engine->base + SPI_ENGINE_REG_CMD_FIFO_ROOM); - while (n && spi_engine->cmd_length) { - m = min(n, spi_engine->cmd_length); - buf = spi_engine->cmd_buf; + while (n && st->cmd_length) { + m = min(n, st->cmd_length); + buf = st->cmd_buf; for (i = 0; i < m; i++) writel_relaxed(buf[i], addr); - spi_engine->cmd_buf += m; - spi_engine->cmd_length -= m; + st->cmd_buf += m; + st->cmd_length -= m; n -= m; } - return spi_engine->cmd_length != 0; + return st->cmd_length != 0; } static bool spi_engine_write_tx_fifo(struct spi_engine *spi_engine) { void __iomem *addr = spi_engine->base + SPI_ENGINE_REG_SDO_DATA_FIFO; + struct spi_engine_message_state *st = spi_engine->msg->state; unsigned int n, m, i; const uint8_t *buf; n = readl_relaxed(spi_engine->base + SPI_ENGINE_REG_SDO_FIFO_ROOM); - while (n && spi_engine->tx_length) { - m = min(n, spi_engine->tx_length); - buf = spi_engine->tx_buf; + while (n && st->tx_length) { + m = min(n, st->tx_length); + buf = st->tx_buf; for (i = 0; i < m; i++) writel_relaxed(buf[i], addr); - spi_engine->tx_buf += m; - spi_engine->tx_length -= m; + st->tx_buf += m; + st->tx_length -= m; n -= m; - if (spi_engine->tx_length == 0) + if (st->tx_length == 0) spi_engine_tx_next(spi_engine); } - return spi_engine->tx_length != 0; + return st->tx_length != 0; } static bool spi_engine_read_rx_fifo(struct spi_engine *spi_engine) { void __iomem *addr = spi_engine->base + SPI_ENGINE_REG_SDI_DATA_FIFO; + struct spi_engine_message_state *st = spi_engine->msg->state; unsigned int n, m, i; uint8_t *buf; n = readl_relaxed(spi_engine->base + SPI_ENGINE_REG_SDI_FIFO_LEVEL); - while (n && spi_engine->rx_length) { - m = min(n, spi_engine->rx_length); - buf = spi_engine->rx_buf; + while (n && st->rx_length) { + m = min(n, st->rx_length); + buf = st->rx_buf; for (i = 0; i < m; i++) buf[i] = readl_relaxed(addr); - spi_engine->rx_buf += m; - spi_engine->rx_length -= m; + st->rx_buf += m; + st->rx_length -= m; n -= m; - if (spi_engine->rx_length == 0) + if (st->rx_length == 0) spi_engine_rx_next(spi_engine); } - return spi_engine->rx_length != 0; + return st->rx_length != 0; } static irqreturn_t spi_engine_irq(int irq, void *devid) { - struct spi_master *master = devid; - struct spi_engine *spi_engine = spi_master_get_devdata(master); + struct spi_controller *host = devid; + struct spi_engine *spi_engine = spi_controller_get_devdata(host); unsigned int disable_int = 0; unsigned int pending; @@ -387,16 +402,20 @@ static irqreturn_t spi_engine_irq(int irq, void *devid) disable_int |= SPI_ENGINE_INT_SDI_ALMOST_FULL; } - if (pending & SPI_ENGINE_INT_SYNC) { - if (spi_engine->msg && - spi_engine->completed_id == spi_engine->sync_id) { + if (pending & SPI_ENGINE_INT_SYNC && spi_engine->msg) { + struct spi_engine_message_state *st = spi_engine->msg->state; + + if (spi_engine->completed_id == st->sync_id) { struct spi_message *msg = spi_engine->msg; + struct spi_engine_message_state *st = msg->state; - kfree(spi_engine->p); + ida_free(&spi_engine->sync_ida, st->sync_id); + kfree(st->p); + kfree(st); msg->status = 0; msg->actual_length = msg->frame_length; spi_engine->msg = NULL; - spi_finalize_current_message(master); + spi_finalize_current_message(host); disable_int |= SPI_ENGINE_INT_SYNC; } } @@ -412,34 +431,51 @@ static irqreturn_t spi_engine_irq(int irq, void *devid) return IRQ_HANDLED; } -static int spi_engine_transfer_one_message(struct spi_master *master, +static int spi_engine_transfer_one_message(struct spi_controller *host, struct spi_message *msg) { struct spi_engine_program p_dry, *p; - struct spi_engine *spi_engine = spi_master_get_devdata(master); + struct spi_engine *spi_engine = spi_controller_get_devdata(host); + struct spi_engine_message_state *st; unsigned int int_enable = 0; unsigned long flags; size_t size; + int ret; + + st = kzalloc(sizeof(*st), GFP_KERNEL); + if (!st) + return -ENOMEM; p_dry.length = 0; spi_engine_compile_message(spi_engine, msg, true, &p_dry); size = sizeof(*p->instructions) * (p_dry.length + 1); p = kzalloc(sizeof(*p) + size, GFP_KERNEL); - if (!p) + if (!p) { + kfree(st); return -ENOMEM; + } + + ret = ida_alloc_range(&spi_engine->sync_ida, 0, U8_MAX, GFP_KERNEL); + if (ret < 0) { + kfree(p); + kfree(st); + return ret; + } + + st->sync_id = ret; + spi_engine_compile_message(spi_engine, msg, false, p); spin_lock_irqsave(&spi_engine->lock, flags); - spi_engine->sync_id = (spi_engine->sync_id + 1) & 0xff; - spi_engine_program_add_cmd(p, false, - SPI_ENGINE_CMD_SYNC(spi_engine->sync_id)); + spi_engine_program_add_cmd(p, false, SPI_ENGINE_CMD_SYNC(st->sync_id)); + msg->state = st; spi_engine->msg = msg; - spi_engine->p = p; + st->p = p; - spi_engine->cmd_buf = p->instructions; - spi_engine->cmd_length = p->length; + st->cmd_buf = p->instructions; + st->cmd_length = p->length; if (spi_engine_write_cmd_fifo(spi_engine)) int_enable |= SPI_ENGINE_INT_CMD_ALMOST_EMPTY; @@ -448,7 +484,7 @@ static int spi_engine_transfer_one_message(struct spi_master *master, int_enable |= SPI_ENGINE_INT_SDO_ALMOST_EMPTY; spi_engine_rx_next(spi_engine); - if (spi_engine->rx_length != 0) + if (st->rx_length != 0) int_enable |= SPI_ENGINE_INT_SDI_ALMOST_FULL; int_enable |= SPI_ENGINE_INT_SYNC; @@ -464,7 +500,7 @@ static int spi_engine_transfer_one_message(struct spi_master *master, static int spi_engine_probe(struct platform_device *pdev) { struct spi_engine *spi_engine; - struct spi_master *master; + struct spi_controller *host; unsigned int version; int irq; int ret; @@ -473,107 +509,76 @@ static int spi_engine_probe(struct platform_device *pdev) if (irq <= 0) return -ENXIO; - spi_engine = devm_kzalloc(&pdev->dev, sizeof(*spi_engine), GFP_KERNEL); - if (!spi_engine) - return -ENOMEM; - - master = spi_alloc_master(&pdev->dev, 0); - if (!master) + host = devm_spi_alloc_host(&pdev->dev, sizeof(*spi_engine)); + if (!host) return -ENOMEM; - spi_master_set_devdata(master, spi_engine); + spi_engine = spi_controller_get_devdata(host); spin_lock_init(&spi_engine->lock); + ida_init(&spi_engine->sync_ida); - spi_engine->clk = devm_clk_get(&pdev->dev, "s_axi_aclk"); - if (IS_ERR(spi_engine->clk)) { - ret = PTR_ERR(spi_engine->clk); - goto err_put_master; - } - - spi_engine->ref_clk = devm_clk_get(&pdev->dev, "spi_clk"); - if (IS_ERR(spi_engine->ref_clk)) { - ret = PTR_ERR(spi_engine->ref_clk); - goto err_put_master; - } + spi_engine->clk = devm_clk_get_enabled(&pdev->dev, "s_axi_aclk"); + if (IS_ERR(spi_engine->clk)) + return PTR_ERR(spi_engine->clk); - ret = clk_prepare_enable(spi_engine->clk); - if (ret) - goto err_put_master; - - ret = clk_prepare_enable(spi_engine->ref_clk); - if (ret) - goto err_clk_disable; + spi_engine->ref_clk = devm_clk_get_enabled(&pdev->dev, "spi_clk"); + if (IS_ERR(spi_engine->ref_clk)) + return PTR_ERR(spi_engine->ref_clk); spi_engine->base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(spi_engine->base)) { - ret = PTR_ERR(spi_engine->base); - goto err_ref_clk_disable; - } - - version = readl(spi_engine->base + SPI_ENGINE_REG_VERSION); - if (SPI_ENGINE_VERSION_MAJOR(version) != 1) { - dev_err(&pdev->dev, "Unsupported peripheral version %u.%u.%c\n", - SPI_ENGINE_VERSION_MAJOR(version), - SPI_ENGINE_VERSION_MINOR(version), - SPI_ENGINE_VERSION_PATCH(version)); - ret = -ENODEV; - goto err_ref_clk_disable; + if (IS_ERR(spi_engine->base)) + return PTR_ERR(spi_engine->base); + + version = readl(spi_engine->base + ADI_AXI_REG_VERSION); + if (ADI_AXI_PCORE_VER_MAJOR(version) != 1) { + dev_err(&pdev->dev, "Unsupported peripheral version %u.%u.%u\n", + ADI_AXI_PCORE_VER_MAJOR(version), + ADI_AXI_PCORE_VER_MINOR(version), + ADI_AXI_PCORE_VER_PATCH(version)); + return -ENODEV; } writel_relaxed(0x00, spi_engine->base + SPI_ENGINE_REG_RESET); writel_relaxed(0xff, spi_engine->base + SPI_ENGINE_REG_INT_PENDING); writel_relaxed(0x00, spi_engine->base + SPI_ENGINE_REG_INT_ENABLE); - ret = request_irq(irq, spi_engine_irq, 0, pdev->name, master); + ret = request_irq(irq, spi_engine_irq, 0, pdev->name, host); if (ret) - goto err_ref_clk_disable; + return ret; - master->dev.of_node = pdev->dev.of_node; - master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_3WIRE; - master->bits_per_word_mask = SPI_BPW_MASK(8); - master->max_speed_hz = clk_get_rate(spi_engine->ref_clk) / 2; - master->transfer_one_message = spi_engine_transfer_one_message; - master->num_chipselect = 8; + host->dev.of_node = pdev->dev.of_node; + host->mode_bits = SPI_CPOL | SPI_CPHA | SPI_3WIRE; + host->bits_per_word_mask = SPI_BPW_MASK(8); + host->max_speed_hz = clk_get_rate(spi_engine->ref_clk) / 2; + host->transfer_one_message = spi_engine_transfer_one_message; + host->num_chipselect = 8; - ret = spi_register_master(master); + ret = spi_register_controller(host); if (ret) goto err_free_irq; - platform_set_drvdata(pdev, master); + platform_set_drvdata(pdev, host); return 0; err_free_irq: - free_irq(irq, master); -err_ref_clk_disable: - clk_disable_unprepare(spi_engine->ref_clk); -err_clk_disable: - clk_disable_unprepare(spi_engine->clk); -err_put_master: - spi_master_put(master); + free_irq(irq, host); return ret; } -static int spi_engine_remove(struct platform_device *pdev) +static void spi_engine_remove(struct platform_device *pdev) { - struct spi_master *master = spi_master_get(platform_get_drvdata(pdev)); - struct spi_engine *spi_engine = spi_master_get_devdata(master); + struct spi_controller *host = platform_get_drvdata(pdev); + struct spi_engine *spi_engine = spi_controller_get_devdata(host); int irq = platform_get_irq(pdev, 0); - spi_unregister_master(master); - - free_irq(irq, master); + spi_unregister_controller(host); - spi_master_put(master); + free_irq(irq, host); writel_relaxed(0xff, spi_engine->base + SPI_ENGINE_REG_INT_PENDING); writel_relaxed(0x00, spi_engine->base + SPI_ENGINE_REG_INT_ENABLE); writel_relaxed(0x01, spi_engine->base + SPI_ENGINE_REG_RESET); - - clk_disable_unprepare(spi_engine->ref_clk); - clk_disable_unprepare(spi_engine->clk); - - return 0; } static const struct of_device_id spi_engine_match_table[] = { @@ -584,7 +589,7 @@ MODULE_DEVICE_TABLE(of, spi_engine_match_table); static struct platform_driver spi_engine_driver = { .probe = spi_engine_probe, - .remove = spi_engine_remove, + .remove_new = spi_engine_remove, .driver = { .name = "spi-engine", .of_match_table = spi_engine_match_table, diff --git a/drivers/spi/spi-hisi-kunpeng.c b/drivers/spi/spi-hisi-kunpeng.c index 525cc0143a3050ec7a592aea4ea1eb75097277ad..54730e93fba45a4286623389704cb9c0e9aba988 100644 --- a/drivers/spi/spi-hisi-kunpeng.c +++ b/drivers/spi/spi-hisi-kunpeng.c @@ -151,8 +151,6 @@ static const struct debugfs_reg32 hisi_spi_regs[] = { HISI_SPI_DBGFS_REG("ENR", HISI_SPI_ENR), HISI_SPI_DBGFS_REG("FIFOC", HISI_SPI_FIFOC), HISI_SPI_DBGFS_REG("IMR", HISI_SPI_IMR), - HISI_SPI_DBGFS_REG("DIN", HISI_SPI_DIN), - HISI_SPI_DBGFS_REG("DOUT", HISI_SPI_DOUT), HISI_SPI_DBGFS_REG("SR", HISI_SPI_SR), HISI_SPI_DBGFS_REG("RISR", HISI_SPI_RISR), HISI_SPI_DBGFS_REG("ISR", HISI_SPI_ISR), diff --git a/drivers/spi/spi-hisi-sfc-v3xx.c b/drivers/spi/spi-hisi-sfc-v3xx.c index d3a23b1c2a4c546ff702f477a36e32989932bdd0..61bf00dfe9c33ee7b4e98a5c7850096a45de326a 100644 --- a/drivers/spi/spi-hisi-sfc-v3xx.c +++ b/drivers/spi/spi-hisi-sfc-v3xx.c @@ -377,6 +377,11 @@ static const struct spi_controller_mem_ops hisi_sfc_v3xx_mem_ops = { static irqreturn_t hisi_sfc_v3xx_isr(int irq, void *data) { struct hisi_sfc_v3xx_host *host = data; + u32 reg; + + reg = readl(host->regbase + HISI_SFC_V3XX_INT_STAT); + if (!reg) + return IRQ_NONE; hisi_sfc_v3xx_disable_int(host); diff --git a/drivers/spi/spi-microchip-core-qspi.c b/drivers/spi/spi-microchip-core-qspi.c index 19a6a46829f6d963ee671701e9b5a299fc6cdc6e..620c5d19031e2d1c16543803c63bd3ec03a79ee7 100644 --- a/drivers/spi/spi-microchip-core-qspi.c +++ b/drivers/spi/spi-microchip-core-qspi.c @@ -283,6 +283,7 @@ static int mchp_coreqspi_setup_clock(struct mchp_coreqspi *qspi, struct spi_devi } control = readl_relaxed(qspi->regs + REG_CONTROL); + control &= ~CONTROL_CLKRATE_MASK; control |= baud_rate_val << CONTROL_CLKRATE_SHIFT; writel_relaxed(control, qspi->regs + REG_CONTROL); control = readl_relaxed(qspi->regs + REG_CONTROL); diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index 6e95efb50acbc08f6574efbdc4855ee5bd19fc6e..f9ec8742917a6c497ad0de18b1ffa136269cd81a 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -787,17 +787,19 @@ static irqreturn_t mtk_spi_interrupt(int irq, void *dev_id) mdata->xfer_len = min(MTK_SPI_MAX_FIFO_SIZE, len); mtk_spi_setup_packet(master); - cnt = mdata->xfer_len / 4; - iowrite32_rep(mdata->base + SPI_TX_DATA_REG, - trans->tx_buf + mdata->num_xfered, cnt); + if (trans->tx_buf) { + cnt = mdata->xfer_len / 4; + iowrite32_rep(mdata->base + SPI_TX_DATA_REG, + trans->tx_buf + mdata->num_xfered, cnt); - remainder = mdata->xfer_len % 4; - if (remainder > 0) { - reg_val = 0; - memcpy(®_val, - trans->tx_buf + (cnt * 4) + mdata->num_xfered, - remainder); - writel(reg_val, mdata->base + SPI_TX_DATA_REG); + remainder = mdata->xfer_len % 4; + if (remainder > 0) { + reg_val = 0; + memcpy(®_val, + trans->tx_buf + (cnt * 4) + mdata->num_xfered, + remainder); + writel(reg_val, mdata->base + SPI_TX_DATA_REG); + } } mtk_spi_enable_transfer(master); diff --git a/drivers/spi/spi-ppc4xx.c b/drivers/spi/spi-ppc4xx.c index d65f047b6c823d2e3d5de5b7a8a352853744e983..1179a1115137fd2ce0e04120c178fb06f2d8aaea 100644 --- a/drivers/spi/spi-ppc4xx.c +++ b/drivers/spi/spi-ppc4xx.c @@ -166,10 +166,8 @@ static int spi_ppc4xx_setupxfer(struct spi_device *spi, struct spi_transfer *t) int scr; u8 cdm = 0; u32 speed; - u8 bits_per_word; /* Start with the generic configuration for this device. */ - bits_per_word = spi->bits_per_word; speed = spi->max_speed_hz; /* @@ -177,9 +175,6 @@ static int spi_ppc4xx_setupxfer(struct spi_device *spi, struct spi_transfer *t) * the transfer to overwrite the generic configuration with zeros. */ if (t) { - if (t->bits_per_word) - bits_per_word = t->bits_per_word; - if (t->speed_hz) speed = min(t->speed_hz, spi->max_speed_hz); } diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c index 51ceaa4857249c267ad6c64b496b3113934c7e6c..ec3a4939ee984d615d4c98fb269bae0d7dda311c 100644 --- a/drivers/spi/spi-sh-msiof.c +++ b/drivers/spi/spi-sh-msiof.c @@ -137,14 +137,14 @@ struct sh_msiof_spi_priv { /* SIFCTR */ #define SIFCTR_TFWM_MASK GENMASK(31, 29) /* Transmit FIFO Watermark */ -#define SIFCTR_TFWM_64 (0 << 29) /* Transfer Request when 64 empty stages */ -#define SIFCTR_TFWM_32 (1 << 29) /* Transfer Request when 32 empty stages */ -#define SIFCTR_TFWM_24 (2 << 29) /* Transfer Request when 24 empty stages */ -#define SIFCTR_TFWM_16 (3 << 29) /* Transfer Request when 16 empty stages */ -#define SIFCTR_TFWM_12 (4 << 29) /* Transfer Request when 12 empty stages */ -#define SIFCTR_TFWM_8 (5 << 29) /* Transfer Request when 8 empty stages */ -#define SIFCTR_TFWM_4 (6 << 29) /* Transfer Request when 4 empty stages */ -#define SIFCTR_TFWM_1 (7 << 29) /* Transfer Request when 1 empty stage */ +#define SIFCTR_TFWM_64 (0UL << 29) /* Transfer Request when 64 empty stages */ +#define SIFCTR_TFWM_32 (1UL << 29) /* Transfer Request when 32 empty stages */ +#define SIFCTR_TFWM_24 (2UL << 29) /* Transfer Request when 24 empty stages */ +#define SIFCTR_TFWM_16 (3UL << 29) /* Transfer Request when 16 empty stages */ +#define SIFCTR_TFWM_12 (4UL << 29) /* Transfer Request when 12 empty stages */ +#define SIFCTR_TFWM_8 (5UL << 29) /* Transfer Request when 8 empty stages */ +#define SIFCTR_TFWM_4 (6UL << 29) /* Transfer Request when 4 empty stages */ +#define SIFCTR_TFWM_1 (7UL << 29) /* Transfer Request when 1 empty stage */ #define SIFCTR_TFUA_MASK GENMASK(26, 20) /* Transmit FIFO Usable Area */ #define SIFCTR_TFUA_SHIFT 20 #define SIFCTR_TFUA(i) ((i) << SIFCTR_TFUA_SHIFT) diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index d5b1d1091170a8d3e2bf124a4f50db384bebc6c1..12447d5247d8063a6b63d6678db349b5d2dab41d 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -2774,6 +2774,17 @@ int spi_slave_abort(struct spi_device *spi) } EXPORT_SYMBOL_GPL(spi_slave_abort); +int spi_target_abort(struct spi_device *spi) +{ + struct spi_controller *ctlr = spi->controller; + + if (spi_controller_is_target(ctlr) && ctlr->target_abort) + return ctlr->target_abort(ctlr); + + return -ENOTSUPP; +} +EXPORT_SYMBOL_GPL(spi_target_abort); + static ssize_t slave_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -4215,6 +4226,7 @@ static int __spi_sync(struct spi_device *spi, struct spi_message *message) wait_for_completion(&done); status = message->status; } + message->complete = NULL; message->context = NULL; return status; diff --git a/drivers/staging/greybus/light.c b/drivers/staging/greybus/light.c index 87d36948c610675bc09f01542930eb5f98f7acd4..c6bd86a5335ab52d6331262c20a28b7f94b9e9d1 100644 --- a/drivers/staging/greybus/light.c +++ b/drivers/staging/greybus/light.c @@ -100,15 +100,15 @@ static struct led_classdev *get_channel_cdev(struct gb_channel *channel) static struct gb_channel *get_channel_from_mode(struct gb_light *light, u32 mode) { - struct gb_channel *channel = NULL; + struct gb_channel *channel; int i; for (i = 0; i < light->channels_count; i++) { channel = &light->channels[i]; - if (channel && channel->mode == mode) - break; + if (channel->mode == mode) + return channel; } - return channel; + return NULL; } static int __gb_lights_flash_intensity_set(struct gb_channel *channel, diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c index f177b20f0f2d983f4244228112d3051f60e9a60e..ceba632138940fdf8aa0f9dd3f9357d6b95bc50a 100644 --- a/drivers/staging/iio/impedance-analyzer/ad5933.c +++ b/drivers/staging/iio/impedance-analyzer/ad5933.c @@ -608,7 +608,7 @@ static void ad5933_work(struct work_struct *work) struct ad5933_state, work.work); struct iio_dev *indio_dev = i2c_get_clientdata(st->client); __be16 buf[2]; - int val[2]; + u16 val[2]; unsigned char status; int ret; diff --git a/drivers/staging/media/deprecated/saa7146/ttpci/budget-av.c b/drivers/staging/media/deprecated/saa7146/ttpci/budget-av.c index 0c61a2dec2211afa19ac1765196b37aefc9860af..81fc4835679f3f492d13000d917a669ef532c579 100644 --- a/drivers/staging/media/deprecated/saa7146/ttpci/budget-av.c +++ b/drivers/staging/media/deprecated/saa7146/ttpci/budget-av.c @@ -1462,7 +1462,8 @@ static int budget_av_attach(struct saa7146_dev *dev, struct saa7146_pci_extensio budget_av->has_saa7113 = 1; err = saa7146_vv_init(dev, &vv_data); if (err != 0) { - /* fixme: proper cleanup here */ + ttpci_budget_deinit(&budget_av->budget); + kfree(budget_av); ERR("cannot init vv subsystem\n"); return err; } @@ -1471,9 +1472,10 @@ static int budget_av_attach(struct saa7146_dev *dev, struct saa7146_pci_extensio vv_data.vid_ops.vidioc_s_input = vidioc_s_input; if ((err = saa7146_register_device(&budget_av->vd, dev, "knc1", VFL_TYPE_VIDEO))) { - /* fixme: proper cleanup here */ - ERR("cannot register capture v4l2 device\n"); saa7146_vv_release(dev); + ttpci_budget_deinit(&budget_av->budget); + kfree(budget_av); + ERR("cannot register capture v4l2 device\n"); return err; } diff --git a/drivers/staging/media/imx/imx-media-csc-scaler.c b/drivers/staging/media/imx/imx-media-csc-scaler.c index 1fd39a2fca98ae70ca74ea3768aeb5d7c95a51da..95cca281e8a378c6244bd25d5b81c392712361aa 100644 --- a/drivers/staging/media/imx/imx-media-csc-scaler.c +++ b/drivers/staging/media/imx/imx-media-csc-scaler.c @@ -803,6 +803,7 @@ static int ipu_csc_scaler_release(struct file *file) dev_dbg(priv->dev, "Releasing instance %p\n", ctx); + v4l2_ctrl_handler_free(&ctx->ctrl_hdlr); v4l2_m2m_ctx_release(ctx->fh.m2m_ctx); v4l2_fh_del(&ctx->fh); v4l2_fh_exit(&ctx->fh); diff --git a/drivers/staging/media/ipu3/ipu3-v4l2.c b/drivers/staging/media/ipu3/ipu3-v4l2.c index e530767e80a5d1cfca3854038dc755f2d388c667..55cc44a401bc43b07812cacaae7d7a33f2b4fd8b 100644 --- a/drivers/staging/media/ipu3/ipu3-v4l2.c +++ b/drivers/staging/media/ipu3/ipu3-v4l2.c @@ -1069,6 +1069,11 @@ static int imgu_v4l2_subdev_register(struct imgu_device *imgu, struct imgu_media_pipe *imgu_pipe = &imgu->imgu_pipe[pipe]; /* Initialize subdev media entity */ + imgu_sd->subdev.entity.ops = &imgu_media_ops; + for (i = 0; i < IMGU_NODE_NUM; i++) { + imgu_sd->subdev_pads[i].flags = imgu_pipe->nodes[i].output ? + MEDIA_PAD_FL_SINK : MEDIA_PAD_FL_SOURCE; + } r = media_entity_pads_init(&imgu_sd->subdev.entity, IMGU_NODE_NUM, imgu_sd->subdev_pads); if (r) { @@ -1076,11 +1081,6 @@ static int imgu_v4l2_subdev_register(struct imgu_device *imgu, "failed initialize subdev media entity (%d)\n", r); return r; } - imgu_sd->subdev.entity.ops = &imgu_media_ops; - for (i = 0; i < IMGU_NODE_NUM; i++) { - imgu_sd->subdev_pads[i].flags = imgu_pipe->nodes[i].output ? - MEDIA_PAD_FL_SINK : MEDIA_PAD_FL_SOURCE; - } /* Initialize subdev */ v4l2_subdev_init(&imgu_sd->subdev, &imgu_subdev_ops); @@ -1177,15 +1177,15 @@ static int imgu_v4l2_node_setup(struct imgu_device *imgu, unsigned int pipe, } /* Initialize media entities */ + node->vdev_pad.flags = node->output ? + MEDIA_PAD_FL_SOURCE : MEDIA_PAD_FL_SINK; + vdev->entity.ops = NULL; r = media_entity_pads_init(&vdev->entity, 1, &node->vdev_pad); if (r) { dev_err(dev, "failed initialize media entity (%d)\n", r); mutex_destroy(&node->lock); return r; } - node->vdev_pad.flags = node->output ? - MEDIA_PAD_FL_SOURCE : MEDIA_PAD_FL_SINK; - vdev->entity.ops = NULL; /* Initialize vbq */ vbq->type = node->vdev_fmt.type; diff --git a/drivers/staging/media/sunxi/cedrus/cedrus.h b/drivers/staging/media/sunxi/cedrus/cedrus.h index 93a2196006f7378cc293ea152b5dac5e26aaaa46..cb99610f3e1281e593d330d8155f6da62111badb 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus.h +++ b/drivers/staging/media/sunxi/cedrus/cedrus.h @@ -109,6 +109,11 @@ struct cedrus_buffer { unsigned int position; enum cedrus_h264_pic_type pic_type; } h264; + struct { + void *mv_col_buf; + dma_addr_t mv_col_buf_dma; + ssize_t mv_col_buf_size; + } h265; } codec; }; @@ -142,10 +147,6 @@ struct cedrus_ctx { ssize_t intra_pred_buf_size; } h264; struct { - void *mv_col_buf; - dma_addr_t mv_col_buf_addr; - ssize_t mv_col_buf_size; - ssize_t mv_col_buf_unit_size; void *neighbor_info_buf; dma_addr_t neighbor_info_buf_addr; void *entry_points_buf; diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_h265.c b/drivers/staging/media/sunxi/cedrus/cedrus_h265.c index 625f77a8c5bde59ea79284188203a9ac5f3e7a27..9f13c942a806b63e37e0cb493804f40c303a7ee7 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus_h265.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus_h265.c @@ -90,12 +90,13 @@ static void cedrus_h265_sram_write_data(struct cedrus_dev *dev, void *data, } static inline dma_addr_t -cedrus_h265_frame_info_mv_col_buf_addr(struct cedrus_ctx *ctx, - unsigned int index, unsigned int field) +cedrus_h265_frame_info_mv_col_buf_addr(struct vb2_buffer *buf, + unsigned int field) { - return ctx->codec.h265.mv_col_buf_addr + index * - ctx->codec.h265.mv_col_buf_unit_size + - field * ctx->codec.h265.mv_col_buf_unit_size / 2; + struct cedrus_buffer *cedrus_buf = vb2_to_cedrus_buffer(buf); + + return cedrus_buf->codec.h265.mv_col_buf_dma + + field * cedrus_buf->codec.h265.mv_col_buf_size / 2; } static void cedrus_h265_frame_info_write_single(struct cedrus_ctx *ctx, @@ -108,9 +109,8 @@ static void cedrus_h265_frame_info_write_single(struct cedrus_ctx *ctx, dma_addr_t dst_luma_addr = cedrus_dst_buf_addr(ctx, buf, 0); dma_addr_t dst_chroma_addr = cedrus_dst_buf_addr(ctx, buf, 1); dma_addr_t mv_col_buf_addr[2] = { - cedrus_h265_frame_info_mv_col_buf_addr(ctx, buf->index, 0), - cedrus_h265_frame_info_mv_col_buf_addr(ctx, buf->index, - field_pic ? 1 : 0) + cedrus_h265_frame_info_mv_col_buf_addr(buf, 0), + cedrus_h265_frame_info_mv_col_buf_addr(buf, field_pic ? 1 : 0) }; u32 offset = VE_DEC_H265_SRAM_OFFSET_FRAME_INFO + VE_DEC_H265_SRAM_OFFSET_FRAME_INFO_UNIT * index; @@ -412,12 +412,13 @@ static int cedrus_h265_setup(struct cedrus_ctx *ctx, struct cedrus_run *run) unsigned int width_in_ctb_luma, ctb_size_luma; unsigned int log2_max_luma_coding_block_size; unsigned int ctb_addr_x, ctb_addr_y; + struct cedrus_buffer *cedrus_buf; dma_addr_t src_buf_addr; - dma_addr_t src_buf_end_addr; u32 chroma_log2_weight_denom; u32 num_entry_point_offsets; u32 output_pic_list_index; u32 pic_order_cnt[2]; + size_t slice_bytes; u8 padding; int count; u32 reg; @@ -428,6 +429,8 @@ static int cedrus_h265_setup(struct cedrus_ctx *ctx, struct cedrus_run *run) decode_params = run->h265.decode_params; pred_weight_table = &slice_params->pred_weight_table; num_entry_point_offsets = slice_params->num_entry_point_offsets; + cedrus_buf = vb2_to_cedrus_buffer(&run->dst->vb2_buf); + slice_bytes = vb2_get_plane_payload(&run->src->vb2_buf, 0); /* * If entry points offsets are present, we should get them @@ -445,31 +448,25 @@ static int cedrus_h265_setup(struct cedrus_ctx *ctx, struct cedrus_run *run) DIV_ROUND_UP(sps->pic_width_in_luma_samples, ctb_size_luma); /* MV column buffer size and allocation. */ - if (!ctx->codec.h265.mv_col_buf_size) { - unsigned int num_buffers = - run->dst->vb2_buf.vb2_queue->num_buffers; - + if (!cedrus_buf->codec.h265.mv_col_buf_size) { /* * Each CTB requires a MV col buffer with a specific unit size. * Since the address is given with missing lsb bits, 1 KiB is * added to each buffer to ensure proper alignment. */ - ctx->codec.h265.mv_col_buf_unit_size = + cedrus_buf->codec.h265.mv_col_buf_size = DIV_ROUND_UP(ctx->src_fmt.width, ctb_size_luma) * DIV_ROUND_UP(ctx->src_fmt.height, ctb_size_luma) * CEDRUS_H265_MV_COL_BUF_UNIT_CTB_SIZE + SZ_1K; - ctx->codec.h265.mv_col_buf_size = num_buffers * - ctx->codec.h265.mv_col_buf_unit_size; - /* Buffer is never accessed by CPU, so we can skip kernel mapping. */ - ctx->codec.h265.mv_col_buf = + cedrus_buf->codec.h265.mv_col_buf = dma_alloc_attrs(dev->dev, - ctx->codec.h265.mv_col_buf_size, - &ctx->codec.h265.mv_col_buf_addr, + cedrus_buf->codec.h265.mv_col_buf_size, + &cedrus_buf->codec.h265.mv_col_buf_dma, GFP_KERNEL, DMA_ATTR_NO_KERNEL_MAPPING); - if (!ctx->codec.h265.mv_col_buf) { - ctx->codec.h265.mv_col_buf_size = 0; + if (!cedrus_buf->codec.h265.mv_col_buf) { + cedrus_buf->codec.h265.mv_col_buf_size = 0; return -ENOMEM; } } @@ -481,7 +478,7 @@ static int cedrus_h265_setup(struct cedrus_ctx *ctx, struct cedrus_run *run) cedrus_write(dev, VE_DEC_H265_BITS_OFFSET, 0); - reg = slice_params->bit_size; + reg = slice_bytes * 8; cedrus_write(dev, VE_DEC_H265_BITS_LEN, reg); /* Source beginning and end addresses. */ @@ -495,10 +492,7 @@ static int cedrus_h265_setup(struct cedrus_ctx *ctx, struct cedrus_run *run) cedrus_write(dev, VE_DEC_H265_BITS_ADDR, reg); - src_buf_end_addr = src_buf_addr + - DIV_ROUND_UP(slice_params->bit_size, 8); - - reg = VE_DEC_H265_BITS_END_ADDR_BASE(src_buf_end_addr); + reg = VE_DEC_H265_BITS_END_ADDR_BASE(src_buf_addr + slice_bytes); cedrus_write(dev, VE_DEC_H265_BITS_END_ADDR, reg); /* Coding tree block address */ @@ -816,9 +810,6 @@ static int cedrus_h265_start(struct cedrus_ctx *ctx) { struct cedrus_dev *dev = ctx->dev; - /* The buffer size is calculated at setup time. */ - ctx->codec.h265.mv_col_buf_size = 0; - /* Buffer is never accessed by CPU, so we can skip kernel mapping. */ ctx->codec.h265.neighbor_info_buf = dma_alloc_attrs(dev->dev, CEDRUS_H265_NEIGHBOR_INFO_BUF_SIZE, @@ -845,14 +836,24 @@ static int cedrus_h265_start(struct cedrus_ctx *ctx) static void cedrus_h265_stop(struct cedrus_ctx *ctx) { struct cedrus_dev *dev = ctx->dev; + struct cedrus_buffer *buf; + struct vb2_queue *vq; + unsigned int i; - if (ctx->codec.h265.mv_col_buf_size > 0) { - dma_free_attrs(dev->dev, ctx->codec.h265.mv_col_buf_size, - ctx->codec.h265.mv_col_buf, - ctx->codec.h265.mv_col_buf_addr, - DMA_ATTR_NO_KERNEL_MAPPING); + vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); + + for (i = 0; i < vq->num_buffers; i++) { + buf = vb2_to_cedrus_buffer(vb2_get_buffer(vq, i)); - ctx->codec.h265.mv_col_buf_size = 0; + if (buf->codec.h265.mv_col_buf_size > 0) { + dma_free_attrs(dev->dev, + buf->codec.h265.mv_col_buf_size, + buf->codec.h265.mv_col_buf, + buf->codec.h265.mv_col_buf_dma, + DMA_ATTR_NO_KERNEL_MAPPING); + + buf->codec.h265.mv_col_buf_size = 0; + } } dma_free_attrs(dev->dev, CEDRUS_H265_NEIGHBOR_INFO_BUF_SIZE, diff --git a/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c b/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c index f112394b65d1d3c380a0361c607482ff9c90926a..95a6c1a03f50b9ead665bf5e461659c639c90f64 100644 --- a/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c +++ b/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c @@ -1076,8 +1076,9 @@ static int create_component(struct vchiq_mmal_instance *instance, /* build component create message */ m.h.type = MMAL_MSG_TYPE_COMPONENT_CREATE; m.u.component_create.client_component = component->client_component; - strncpy(m.u.component_create.name, name, - sizeof(m.u.component_create.name)); + strscpy_pad(m.u.component_create.name, name, + sizeof(m.u.component_create.name)); + m.u.component_create.pid = 0; ret = send_synchronous_mmal_msg(instance, &m, sizeof(m.u.component_create), diff --git a/drivers/staging/wlan-ng/hfa384x_usb.c b/drivers/staging/wlan-ng/hfa384x_usb.c index 02fdef7a16c872dab6fb3694550d7b3f5adab549..c7cd54171d99439a7f52803c0f74c56d3fcb73e0 100644 --- a/drivers/staging/wlan-ng/hfa384x_usb.c +++ b/drivers/staging/wlan-ng/hfa384x_usb.c @@ -1116,8 +1116,8 @@ cleanup: if (ctlx == get_active_ctlx(hw)) { spin_unlock_irqrestore(&hw->ctlxq.lock, flags); - del_singleshot_timer_sync(&hw->reqtimer); - del_singleshot_timer_sync(&hw->resptimer); + del_timer_sync(&hw->reqtimer); + del_timer_sync(&hw->resptimer); hw->req_timer_done = 1; hw->resp_timer_done = 1; usb_kill_urb(&hw->ctlx_urb); diff --git a/drivers/staging/wlan-ng/prism2usb.c b/drivers/staging/wlan-ng/prism2usb.c index e13da7fadffff4153c42070c996147cb91080fc5..c13f1699e5a2ffa71b67bb14acaced81ea1738cc 100644 --- a/drivers/staging/wlan-ng/prism2usb.c +++ b/drivers/staging/wlan-ng/prism2usb.c @@ -170,9 +170,9 @@ static void prism2sta_disconnect_usb(struct usb_interface *interface) */ prism2sta_ifstate(wlandev, P80211ENUM_ifstate_disable); - del_singleshot_timer_sync(&hw->throttle); - del_singleshot_timer_sync(&hw->reqtimer); - del_singleshot_timer_sync(&hw->resptimer); + del_timer_sync(&hw->throttle); + del_timer_sync(&hw->reqtimer); + del_timer_sync(&hw->resptimer); /* Unlink all the URBs. This "removes the wheels" * from the entire CTLX handling mechanism. diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index 416514c5c7acd5acf92914d7d9348d988e0ebb0c..1a26dd0d5666245426b33c86bd52d9e7858cc2c6 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -3587,6 +3587,8 @@ static int __init target_core_init_configfs(void) { struct configfs_subsystem *subsys = &target_core_fabrics; struct t10_alua_lu_gp *lu_gp; + struct cred *kern_cred; + const struct cred *old_cred; int ret; pr_debug("TARGET_CORE[0]: Loading Generic Kernel Storage" @@ -3663,11 +3665,21 @@ static int __init target_core_init_configfs(void) if (ret < 0) goto out; + /* We use the kernel credentials to access the target directory */ + kern_cred = prepare_kernel_cred(&init_task); + if (!kern_cred) { + ret = -ENOMEM; + goto out; + } + old_cred = override_creds(kern_cred); target_init_dbroot(); + revert_creds(old_cred); + put_cred(kern_cred); return 0; out: + target_xcopy_release_pt(); configfs_unregister_subsystem(subsys); core_dev_release_virtual_lun0(); rd_module_exit(); diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 301fe376a120695f2449c3af85f9e4fdb5594d37..13558cbd9b82e637883a9d8a67391e1fdcc89d37 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -147,7 +147,6 @@ int transport_lookup_tmr_lun(struct se_cmd *se_cmd) struct se_session *se_sess = se_cmd->se_sess; struct se_node_acl *nacl = se_sess->se_node_acl; struct se_tmr_req *se_tmr = se_cmd->se_tmr_req; - unsigned long flags; rcu_read_lock(); deve = target_nacl_find_deve(nacl, se_cmd->orig_fe_lun); @@ -178,10 +177,6 @@ out_unlock: se_cmd->se_dev = rcu_dereference_raw(se_lun->lun_se_dev); se_tmr->tmr_dev = rcu_dereference_raw(se_lun->lun_se_dev); - spin_lock_irqsave(&se_tmr->tmr_dev->se_tmr_lock, flags); - list_add_tail(&se_tmr->tmr_list, &se_tmr->tmr_dev->dev_tmr_list); - spin_unlock_irqrestore(&se_tmr->tmr_dev->se_tmr_lock, flags); - return 0; } EXPORT_SYMBOL(transport_lookup_tmr_lun); diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 69a4c9581e80e50394c29bfb12ed24afc301f748..7aec34c090661f7a424ffaef558d8f929bbaac1b 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -910,12 +910,15 @@ new_bio: return 0; fail: - if (bio) - bio_put(bio); + if (bio) { + bio_uninit(bio); + kfree(bio); + } while (req->bio) { bio = req->bio; req->bio = bio->bi_next; - bio_put(bio); + bio_uninit(bio); + kfree(bio); } req->biotail = NULL; return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 0686882bcbda351fbf5c46b6a66cdf4cfe35e9e0..fb93d74c5d0b2a5e47a0ccaefc42fc80c0321ebd 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -3627,6 +3627,10 @@ int transport_generic_handle_tmr( unsigned long flags; bool aborted = false; + spin_lock_irqsave(&cmd->se_dev->se_tmr_lock, flags); + list_add_tail(&cmd->se_tmr_req->tmr_list, &cmd->se_dev->dev_tmr_list); + spin_unlock_irqrestore(&cmd->se_dev->se_tmr_lock, flags); + spin_lock_irqsave(&cmd->t_state_lock, flags); if (cmd->transport_state & CMD_T_ABORTED) { aborted = true; diff --git a/drivers/tee/optee/device.c b/drivers/tee/optee/device.c index 4b10921276942ed13a43e531b723e746b76dd6fa..1892e49a8e6a68b5c0f8e719042b34b4d2856b42 100644 --- a/drivers/tee/optee/device.c +++ b/drivers/tee/optee/device.c @@ -90,13 +90,14 @@ static int optee_register_device(const uuid_t *device_uuid, u32 func) if (rc) { pr_err("device registration failed, err: %d\n", rc); put_device(&optee_device->dev); + return rc; } if (func == PTA_CMD_GET_DEVICES_SUPP) device_create_file(&optee_device->dev, &dev_attr_need_supplicant); - return rc; + return 0; } static int __optee_enumerate_devices(u32 func) diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c index 24b474925cd68e5e82fe6377e5c22b0bd0dc1317..0b424bc8cadfd8540d40a56131362feb5d4a4881 100644 --- a/drivers/thermal/devfreq_cooling.c +++ b/drivers/thermal/devfreq_cooling.c @@ -201,7 +201,7 @@ static int devfreq_cooling_get_requested_power(struct thermal_cooling_device *cd res = dfc->power_ops->get_real_power(df, power, freq, voltage); if (!res) { - state = dfc->capped_state; + state = dfc->max_state - dfc->capped_state; /* Convert EM power into milli-Watts first */ dfc->res_util = dfc->em_pd->table[state].power; diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c index 4104743dbc17ebf277d2a384d688bca2bf8f653e..202dce0d2e3096bc71a4ccf6ccc134ca3074b449 100644 --- a/drivers/thermal/thermal_of.c +++ b/drivers/thermal/thermal_of.c @@ -337,14 +337,18 @@ static int thermal_of_monitor_init(struct device_node *np, int *delay, int *pdel int ret; ret = of_property_read_u32(np, "polling-delay-passive", pdelay); - if (ret < 0) { - pr_err("%pOFn: missing polling-delay-passive property\n", np); + if (ret == -EINVAL) { + *pdelay = 0; + } else if (ret < 0) { + pr_err("%pOFn: Couldn't get polling-delay-passive: %d\n", np, ret); return ret; } ret = of_property_read_u32(np, "polling-delay", delay); - if (ret < 0) { - pr_err("%pOFn: missing polling-delay property\n", np); + if (ret == -EINVAL) { + *delay = 0; + } else if (ret < 0) { + pr_err("%pOFn: Couldn't get polling-delay: %d\n", np, ret); return ret; } diff --git a/drivers/thunderbolt/quirks.c b/drivers/thunderbolt/quirks.c index 4ab3803e10c8396b3cd2f6ce5e61f6ce3e1905da..e81de9c30eac9acc8f9a41941cbeacb82bbebd66 100644 --- a/drivers/thunderbolt/quirks.c +++ b/drivers/thunderbolt/quirks.c @@ -10,6 +10,7 @@ static void quirk_force_power_link(struct tb_switch *sw) { sw->quirks |= QUIRK_FORCE_POWER_LINK_CONTROLLER; + tb_sw_dbg(sw, "forcing power to link controller\n"); } static void quirk_dp_credit_allocation(struct tb_switch *sw) @@ -42,6 +43,12 @@ static void quirk_usb3_maximum_bandwidth(struct tb_switch *sw) } } +static void quirk_block_rpm_in_redrive(struct tb_switch *sw) +{ + sw->quirks |= QUIRK_KEEP_POWER_IN_DP_REDRIVE; + tb_sw_dbg(sw, "preventing runtime PM in DP redrive mode\n"); +} + struct tb_quirk { u16 hw_vendor_id; u16 hw_device_id; @@ -85,6 +92,14 @@ static const struct tb_quirk tb_quirks[] = { quirk_usb3_maximum_bandwidth }, { 0x8087, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HUB_40G_BRIDGE, 0x0000, 0x0000, quirk_usb3_maximum_bandwidth }, + /* + * Block Runtime PM in DP redrive mode for Intel Barlow Ridge host + * controllers. + */ + { 0x8087, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_80G_NHI, 0x0000, 0x0000, + quirk_block_rpm_in_redrive }, + { 0x8087, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_40G_NHI, 0x0000, 0x0000, + quirk_block_rpm_in_redrive }, /* * CLx is not supported on AMD USB4 Yellow Carp and Pink Sardine platforms. */ @@ -116,6 +131,7 @@ void tb_check_quirks(struct tb_switch *sw) if (q->device && q->device != sw->device) continue; + tb_sw_dbg(sw, "running %ps\n", q->hook); q->hook(sw); } } diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 55698a0978f03a03573cf2d7eefafd56d74a3a59..d3058ede5306439cffba226e8d2aeab4432fcb5c 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -2880,22 +2880,29 @@ void tb_switch_unconfigure_link(struct tb_switch *sw) { struct tb_port *up, *down; - if (sw->is_unplugged) - return; if (!tb_route(sw) || tb_switch_is_icm(sw)) return; + /* + * Unconfigure downstream port so that wake-on-connect can be + * configured after router unplug. No need to unconfigure upstream port + * since its router is unplugged. + */ up = tb_upstream_port(sw); - if (tb_switch_is_usb4(up->sw)) - usb4_port_unconfigure(up); - else - tb_lc_unconfigure_port(up); - down = up->remote; if (tb_switch_is_usb4(down->sw)) usb4_port_unconfigure(down); else tb_lc_unconfigure_port(down); + + if (sw->is_unplugged) + return; + + up = tb_upstream_port(sw); + if (tb_switch_is_usb4(up->sw)) + usb4_port_unconfigure(up); + else + tb_lc_unconfigure_port(up); } static void tb_switch_credits_init(struct tb_switch *sw) @@ -3135,7 +3142,26 @@ static int tb_switch_set_wake(struct tb_switch *sw, unsigned int flags) return tb_lc_set_wake(sw, flags); } -int tb_switch_resume(struct tb_switch *sw) +static void tb_switch_check_wakes(struct tb_switch *sw) +{ + if (device_may_wakeup(&sw->dev)) { + if (tb_switch_is_usb4(sw)) + usb4_switch_check_wakes(sw); + } +} + +/** + * tb_switch_resume() - Resume a switch after sleep + * @sw: Switch to resume + * @runtime: Is this resume from runtime suspend or system sleep + * + * Resumes and re-enumerates router (and all its children), if still plugged + * after suspend. Don't enumerate device router whose UID was changed during + * suspend. If this is resume from system sleep, notifies PM core about the + * wakes occurred during suspend. Disables all wakes, except USB4 wake of + * upstream port for USB4 routers that shall be always enabled. + */ +int tb_switch_resume(struct tb_switch *sw, bool runtime) { struct tb_port *port; int err; @@ -3184,6 +3210,9 @@ int tb_switch_resume(struct tb_switch *sw) if (err) return err; + if (!runtime) + tb_switch_check_wakes(sw); + /* Disable wakes */ tb_switch_set_wake(sw, 0); @@ -3213,7 +3242,8 @@ int tb_switch_resume(struct tb_switch *sw) */ if (tb_port_unlock(port)) tb_port_warn(port, "failed to unlock port\n"); - if (port->remote && tb_switch_resume(port->remote->sw)) { + if (port->remote && + tb_switch_resume(port->remote->sw, runtime)) { tb_port_warn(port, "lost during suspend, disconnecting\n"); tb_sw_set_unplugged(port->remote->sw); diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index e1eb092ad1d67fb16630cec8086129476e27cd9a..c5e4fa478e643ff7b3e5b68beab3069a3f07116a 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -1050,6 +1050,49 @@ err_rpm_put: pm_runtime_put_autosuspend(&in->sw->dev); } +static void tb_enter_redrive(struct tb_port *port) +{ + struct tb_switch *sw = port->sw; + + if (!(sw->quirks & QUIRK_KEEP_POWER_IN_DP_REDRIVE)) + return; + + /* + * If we get hot-unplug for the DP IN port of the host router + * and the DP resource is not available anymore it means there + * is a monitor connected directly to the Type-C port and we are + * in "redrive" mode. For this to work we cannot enter RTD3 so + * we bump up the runtime PM reference count here. + */ + if (!tb_port_is_dpin(port)) + return; + if (tb_route(sw)) + return; + if (!tb_switch_query_dp_resource(sw, port)) { + port->redrive = true; + pm_runtime_get(&sw->dev); + tb_port_dbg(port, "enter redrive mode, keeping powered\n"); + } +} + +static void tb_exit_redrive(struct tb_port *port) +{ + struct tb_switch *sw = port->sw; + + if (!(sw->quirks & QUIRK_KEEP_POWER_IN_DP_REDRIVE)) + return; + + if (!tb_port_is_dpin(port)) + return; + if (tb_route(sw)) + return; + if (port->redrive && tb_switch_query_dp_resource(sw, port)) { + port->redrive = false; + pm_runtime_put(&sw->dev); + tb_port_dbg(port, "exit redrive mode\n"); + } +} + static void tb_dp_resource_unavailable(struct tb *tb, struct tb_port *port) { struct tb_port *in, *out; @@ -1066,7 +1109,10 @@ static void tb_dp_resource_unavailable(struct tb *tb, struct tb_port *port) } tunnel = tb_find_tunnel(tb, TB_TUNNEL_DP, in, out); - tb_deactivate_and_free_tunnel(tunnel); + if (tunnel) + tb_deactivate_and_free_tunnel(tunnel); + else + tb_enter_redrive(port); list_del_init(&port->list); /* @@ -1092,6 +1138,7 @@ static void tb_dp_resource_available(struct tb *tb, struct tb_port *port) tb_port_dbg(port, "DP %s resource available\n", tb_port_is_dpin(port) ? "IN" : "OUT"); list_add_tail(&port->list, &tcm->dp_resources); + tb_exit_redrive(port); /* Look for suitable DP IN <-> DP OUT pairs now */ tb_tunnel_dp(tb); @@ -1581,7 +1628,7 @@ static int tb_resume_noirq(struct tb *tb) /* remove any pci devices the firmware might have setup */ tb_switch_reset(tb->root_switch); - tb_switch_resume(tb->root_switch); + tb_switch_resume(tb->root_switch, false); tb_free_invalid_tunnels(tb); tb_free_unplugged_children(tb->root_switch); tb_restore_children(tb->root_switch); @@ -1707,7 +1754,7 @@ static int tb_runtime_resume(struct tb *tb) struct tb_tunnel *tunnel, *n; mutex_lock(&tb->lock); - tb_switch_resume(tb->root_switch); + tb_switch_resume(tb->root_switch, true); tb_free_invalid_tunnels(tb); tb_restore_children(tb->root_switch); list_for_each_entry_safe(tunnel, n, &tcm->tunnel_list, list) diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index f79cae48a8eab76b91051e22d9ed9b10c56d9804..acf5b86208455a9c5db05ef9864e5507ae18c5ce 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -27,6 +27,8 @@ #define QUIRK_FORCE_POWER_LINK_CONTROLLER BIT(0) /* Disable CLx if not supported */ #define QUIRK_NO_CLX BIT(1) +/* Need to keep power on while USB4 port is in redrive mode */ +#define QUIRK_KEEP_POWER_IN_DP_REDRIVE BIT(2) /** * struct tb_nvm - Structure holding NVM information @@ -254,6 +256,7 @@ struct tb_switch { * DMA paths through this port. * @max_bw: Maximum possible bandwidth through this adapter if set to * non-zero. + * @redrive: For DP IN, if true the adapter is in redrive mode. * * In USB4 terminology this structure represents an adapter (protocol or * lane adapter). @@ -280,6 +283,7 @@ struct tb_port { unsigned int ctl_credits; unsigned int dma_credits; unsigned int max_bw; + bool redrive; }; /** @@ -783,7 +787,7 @@ int tb_switch_configure(struct tb_switch *sw); int tb_switch_add(struct tb_switch *sw); void tb_switch_remove(struct tb_switch *sw); void tb_switch_suspend(struct tb_switch *sw, bool runtime); -int tb_switch_resume(struct tb_switch *sw); +int tb_switch_resume(struct tb_switch *sw, bool runtime); int tb_switch_reset(struct tb_switch *sw); int tb_switch_wait_for_bit(struct tb_switch *sw, u32 offset, u32 bit, u32 value, int timeout_msec); @@ -1178,6 +1182,7 @@ static inline struct tb_retimer *tb_to_retimer(struct device *dev) return NULL; } +void usb4_switch_check_wakes(struct tb_switch *sw); int usb4_switch_setup(struct tb_switch *sw); int usb4_switch_read_uid(struct tb_switch *sw, u64 *uid); int usb4_switch_drom_read(struct tb_switch *sw, unsigned int address, void *buf, diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 3c821f5e448148b93e2a1c2bc5043db0025d1789..b0394ba6d111d277a7869bafb6428b6fd2517c44 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -153,15 +153,18 @@ static inline int usb4_switch_op_data(struct tb_switch *sw, u16 opcode, tx_dwords, rx_data, rx_dwords); } -static void usb4_switch_check_wakes(struct tb_switch *sw) +/** + * usb4_switch_check_wakes() - Check for wakes and notify PM core about them + * @sw: Router whose wakes to check + * + * Checks wakes occurred during suspend and notify the PM core about them. + */ +void usb4_switch_check_wakes(struct tb_switch *sw) { struct tb_port *port; bool wakeup = false; u32 val; - if (!device_may_wakeup(&sw->dev)) - return; - if (tb_route(sw)) { if (tb_sw_read(sw, &val, TB_CFG_SWITCH, ROUTER_CS_6, 1)) return; @@ -226,8 +229,6 @@ int usb4_switch_setup(struct tb_switch *sw) u32 val = 0; int ret; - usb4_switch_check_wakes(sw); - if (!tb_route(sw)) return 0; diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 6b6abce6b69f4fcd044cdfc62f5832780755ca17..d2daf0a72e347f907c8aaadc04be9059792922a6 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -2969,6 +2969,9 @@ static int gsmld_open(struct tty_struct *tty) { struct gsm_mux *gsm; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (tty->ops->write == NULL) return -EINVAL; diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index dca1abe363248dbf7977a84d36a20b161f67bdc8..55451ff846520e9362954c03fe5476b3b4a8065f 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -714,6 +714,7 @@ static void exar_pci_remove(struct pci_dev *pcidev) for (i = 0; i < priv->nr; i++) serial8250_unregister_port(priv->line[i]); + /* Ensure that every init quirk is properly torn down */ if (priv->board->exit) priv->board->exit(pcidev); } @@ -728,10 +729,6 @@ static int __maybe_unused exar_suspend(struct device *dev) if (priv->line[i] >= 0) serial8250_suspend_port(priv->line[i]); - /* Ensure that every init quirk is properly torn down */ - if (priv->board->exit) - priv->board->exit(pcidev); - return 0; } diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 8862c860961cb227ab5e757ae14e13e175fa7da8..60ad390a6faaa4c1216dcbae2b8503ac4ce5558e 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1377,9 +1377,6 @@ static void autoconfig_irq(struct uart_8250_port *up) inb_p(ICP); } - if (uart_console(port)) - console_lock(); - /* forget possible initially masked and pending IRQ */ probe_irq_off(probe_irq_on()); save_mcr = serial8250_in_MCR(up); @@ -1410,9 +1407,6 @@ static void autoconfig_irq(struct uart_8250_port *up) if (port->flags & UPF_FOURPORT) outb_p(save_ICP, ICP); - if (uart_console(port)) - console_unlock(); - port->irq = (irq > 0) ? irq : 0; } diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 17d7d1e4a3bca4e222ee86865783bdef3ac6669b..fc628a596048d19d7ab8b0e4e1d10edbc729d5cb 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -1359,11 +1359,41 @@ static void pl011_start_tx_pio(struct uart_amba_port *uap) } } +static void pl011_rs485_tx_start(struct uart_amba_port *uap) +{ + struct uart_port *port = &uap->port; + u32 cr; + + /* Enable transmitter */ + cr = pl011_read(uap, REG_CR); + cr |= UART011_CR_TXE; + + /* Disable receiver if half-duplex */ + if (!(port->rs485.flags & SER_RS485_RX_DURING_TX)) + cr &= ~UART011_CR_RXE; + + if (port->rs485.flags & SER_RS485_RTS_ON_SEND) + cr &= ~UART011_CR_RTS; + else + cr |= UART011_CR_RTS; + + pl011_write(cr, uap, REG_CR); + + if (port->rs485.delay_rts_before_send) + mdelay(port->rs485.delay_rts_before_send); + + uap->rs485_tx_started = true; +} + static void pl011_start_tx(struct uart_port *port) { struct uart_amba_port *uap = container_of(port, struct uart_amba_port, port); + if ((uap->port.rs485.flags & SER_RS485_ENABLED) && + !uap->rs485_tx_started) + pl011_rs485_tx_start(uap); + if (!pl011_dma_tx_start(uap)) pl011_start_tx_pio(uap); } @@ -1446,42 +1476,12 @@ static bool pl011_tx_char(struct uart_amba_port *uap, unsigned char c, return true; } -static void pl011_rs485_tx_start(struct uart_amba_port *uap) -{ - struct uart_port *port = &uap->port; - u32 cr; - - /* Enable transmitter */ - cr = pl011_read(uap, REG_CR); - cr |= UART011_CR_TXE; - - /* Disable receiver if half-duplex */ - if (!(port->rs485.flags & SER_RS485_RX_DURING_TX)) - cr &= ~UART011_CR_RXE; - - if (port->rs485.flags & SER_RS485_RTS_ON_SEND) - cr &= ~UART011_CR_RTS; - else - cr |= UART011_CR_RTS; - - pl011_write(cr, uap, REG_CR); - - if (port->rs485.delay_rts_before_send) - mdelay(port->rs485.delay_rts_before_send); - - uap->rs485_tx_started = true; -} - /* Returns true if tx interrupts have to be (kept) enabled */ static bool pl011_tx_chars(struct uart_amba_port *uap, bool from_irq) { struct circ_buf *xmit = &uap->port.state->xmit; int count = uap->fifosize >> 1; - if ((uap->port.rs485.flags & SER_RS485_ENABLED) && - !uap->rs485_tx_started) - pl011_rs485_tx_start(uap); - if (uap->port.x_char) { if (!pl011_tx_char(uap, uap->port.x_char, from_irq)) return true; diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index c5a9b89c4d3139550b1c8bae901573b4fd4392ff..f94c782638686de4b09ade16db1e083d84c18834 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -2213,9 +2213,12 @@ lpuart32_set_termios(struct uart_port *port, struct ktermios *termios, lpuart32_write(&sport->port, bd, UARTBAUD); lpuart32_serial_setbrg(sport, baud); - lpuart32_write(&sport->port, modem, UARTMODIR); - lpuart32_write(&sport->port, ctrl, UARTCTRL); + /* disable CTS before enabling UARTCTRL_TE to avoid pending idle preamble */ + lpuart32_write(&sport->port, modem & ~UARTMODIR_TXCTSE, UARTMODIR); /* restore control register */ + lpuart32_write(&sport->port, ctrl, UARTCTRL); + /* re-enable the CTS if needed */ + lpuart32_write(&sport->port, modem, UARTMODIR); if ((ctrl & (UARTCTRL_PE | UARTCTRL_M)) == UARTCTRL_PE) sport->is_cs7 = true; diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index f8962a3d44216271c4b13f0072425144def88acd..573bf7e9b79788c9b0f9b12d617428954ecc96c7 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -496,8 +496,7 @@ static void imx_uart_stop_tx(struct uart_port *port) } } -/* called with port.lock taken and irqs off */ -static void imx_uart_stop_rx(struct uart_port *port) +static void imx_uart_stop_rx_with_loopback_ctrl(struct uart_port *port, bool loopback) { struct imx_port *sport = (struct imx_port *)port; u32 ucr1, ucr2, ucr4, uts; @@ -519,7 +518,7 @@ static void imx_uart_stop_rx(struct uart_port *port) /* See SER_RS485_ENABLED/UTS_LOOP comment in imx_uart_probe() */ if (port->rs485.flags & SER_RS485_ENABLED && port->rs485.flags & SER_RS485_RTS_ON_SEND && - sport->have_rtscts && !sport->have_rtsgpio) { + sport->have_rtscts && !sport->have_rtsgpio && loopback) { uts = imx_uart_readl(sport, imx_uart_uts_reg(sport)); uts |= UTS_LOOP; imx_uart_writel(sport, uts, imx_uart_uts_reg(sport)); @@ -531,6 +530,16 @@ static void imx_uart_stop_rx(struct uart_port *port) imx_uart_writel(sport, ucr2, UCR2); } +/* called with port.lock taken and irqs off */ +static void imx_uart_stop_rx(struct uart_port *port) +{ + /* + * Stop RX and enable loopback in order to make sure RS485 bus + * is not blocked. Se comment in imx_uart_probe(). + */ + imx_uart_stop_rx_with_loopback_ctrl(port, true); +} + /* called with port.lock taken and irqs off */ static void imx_uart_enable_ms(struct uart_port *port) { @@ -719,8 +728,13 @@ static void imx_uart_start_tx(struct uart_port *port) imx_uart_rts_inactive(sport, &ucr2); imx_uart_writel(sport, ucr2, UCR2); + /* + * Since we are about to transmit we can not stop RX + * with loopback enabled because that will make our + * transmitted data being just looped to RX. + */ if (!(port->rs485.flags & SER_RS485_RX_DURING_TX)) - imx_uart_stop_rx(port); + imx_uart_stop_rx_with_loopback_ctrl(port, false); sport->tx_state = WAIT_AFTER_RTS; diff --git a/drivers/tty/serial/kgdboc.c b/drivers/tty/serial/kgdboc.c index 7aa37be3216a57e23a88e4e9a336d031a5a0a261..86433e3c3409a60193d46bab0ee1eba286cae219 100644 --- a/drivers/tty/serial/kgdboc.c +++ b/drivers/tty/serial/kgdboc.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -48,6 +49,25 @@ static struct kgdb_io kgdboc_earlycon_io_ops; static int (*earlycon_orig_exit)(struct console *con); #endif /* IS_BUILTIN(CONFIG_KGDB_SERIAL_CONSOLE) */ +/* + * When we leave the debug trap handler we need to reset the keyboard status + * (since the original keyboard state gets partially clobbered by kdb use of + * the keyboard). + * + * The path to deliver the reset is somewhat circuitous. + * + * To deliver the reset we register an input handler, reset the keyboard and + * then deregister the input handler. However, to get this done right, we do + * have to carefully manage the calling context because we can only register + * input handlers from task context. + * + * In particular we need to trigger the action from the debug trap handler with + * all its NMI and/or NMI-like oddities. To solve this the kgdboc trap exit code + * (the "post_exception" callback) uses irq_work_queue(), which is NMI-safe, to + * schedule a callback from a hardirq context. From there we have to defer the + * work again, this time using schedule_work(), to get a callback using the + * system workqueue, which runs in task context. + */ #ifdef CONFIG_KDB_KEYBOARD static int kgdboc_reset_connect(struct input_handler *handler, struct input_dev *dev, @@ -99,10 +119,17 @@ static void kgdboc_restore_input_helper(struct work_struct *dummy) static DECLARE_WORK(kgdboc_restore_input_work, kgdboc_restore_input_helper); +static void kgdboc_queue_restore_input_helper(struct irq_work *unused) +{ + schedule_work(&kgdboc_restore_input_work); +} + +static DEFINE_IRQ_WORK(kgdboc_restore_input_irq_work, kgdboc_queue_restore_input_helper); + static void kgdboc_restore_input(void) { if (likely(system_state == SYSTEM_RUNNING)) - schedule_work(&kgdboc_restore_input_work); + irq_work_queue(&kgdboc_restore_input_irq_work); } static int kgdboc_register_kbd(char **cptr) @@ -133,6 +160,7 @@ static void kgdboc_unregister_kbd(void) i--; } } + irq_work_sync(&kgdboc_restore_input_irq_work); flush_work(&kgdboc_restore_input_work); } #else /* ! CONFIG_KDB_KEYBOARD */ diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c index 338cb19dec23c9da6ff81ab4e7f4ae317c5594b7..d409ef388721251dca6dfd9c3ce87a8a1c7b5e98 100644 --- a/drivers/tty/serial/max310x.c +++ b/drivers/tty/serial/max310x.c @@ -237,6 +237,14 @@ #define MAX310x_REV_MASK (0xf8) #define MAX310X_WRITE_BIT 0x80 +/* Port startup definitions */ +#define MAX310X_PORT_STARTUP_WAIT_RETRIES 20 /* Number of retries */ +#define MAX310X_PORT_STARTUP_WAIT_DELAY_MS 10 /* Delay between retries */ + +/* Crystal-related definitions */ +#define MAX310X_XTAL_WAIT_RETRIES 20 /* Number of retries */ +#define MAX310X_XTAL_WAIT_DELAY_MS 10 /* Delay between retries */ + /* MAX3107 specific */ #define MAX3107_REV_ID (0xa0) @@ -583,7 +591,7 @@ static int max310x_update_best_err(unsigned long f, long *besterr) return 1; } -static u32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s, +static s32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s, unsigned long freq, bool xtal) { unsigned int div, clksrc, pllcfg = 0; @@ -641,12 +649,20 @@ static u32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s, /* Wait for crystal */ if (xtal) { - unsigned int val; - msleep(10); - regmap_read(s->regmap, MAX310X_STS_IRQSTS_REG, &val); - if (!(val & MAX310X_STS_CLKREADY_BIT)) { - dev_warn(dev, "clock is not stable yet\n"); - } + bool stable = false; + unsigned int try = 0, val = 0; + + do { + msleep(MAX310X_XTAL_WAIT_DELAY_MS); + regmap_read(s->regmap, MAX310X_STS_IRQSTS_REG, &val); + + if (val & MAX310X_STS_CLKREADY_BIT) + stable = true; + } while (!stable && (++try < MAX310X_XTAL_WAIT_RETRIES)); + + if (!stable) + return dev_err_probe(dev, -EAGAIN, + "clock is not stable\n"); } return bestfreq; @@ -1274,7 +1290,7 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty { int i, ret, fmin, fmax, freq; struct max310x_port *s; - u32 uartclk = 0; + s32 uartclk = 0; bool xtal; for (i = 0; i < devtype->nr; i++) @@ -1337,6 +1353,9 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty goto out_clk; for (i = 0; i < devtype->nr; i++) { + bool started = false; + unsigned int try = 0, val = 0; + /* Reset port */ regmap_write(regmaps[i], MAX310X_MODE2_REG, MAX310X_MODE2_RST_BIT); @@ -1345,13 +1364,27 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty /* Wait for port startup */ do { - regmap_read(regmaps[i], MAX310X_BRGDIVLSB_REG, &ret); - } while (ret != 0x01); + msleep(MAX310X_PORT_STARTUP_WAIT_DELAY_MS); + regmap_read(regmaps[i], MAX310X_BRGDIVLSB_REG, &val); + + if (val == 0x01) + started = true; + } while (!started && (++try < MAX310X_PORT_STARTUP_WAIT_RETRIES)); + + if (!started) { + ret = dev_err_probe(dev, -EAGAIN, "port reset failed\n"); + goto out_uart; + } regmap_write(regmaps[i], MAX310X_MODE1_REG, devtype->mode1); } uartclk = max310x_set_ref_clk(dev, s, freq, xtal); + if (uartclk < 0) { + ret = uartclk; + goto out_uart; + } + dev_dbg(dev, "Reference clock set to %i Hz\n", uartclk); for (i = 0; i < devtype->nr; i++) { @@ -1426,7 +1459,7 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty if (!ret) return 0; - dev_err(dev, "Unable to reguest IRQ %i\n", irq); + dev_err(dev, "Unable to request IRQ %i\n", irq); out_uart: for (i = 0; i < devtype->nr; i++) { @@ -1600,13 +1633,16 @@ static unsigned short max310x_i2c_slave_addr(unsigned short addr, static int max310x_i2c_probe(struct i2c_client *client) { - const struct max310x_devtype *devtype = - device_get_match_data(&client->dev); + const struct max310x_devtype *devtype; struct i2c_client *port_client; struct regmap *regmaps[4]; unsigned int i; u8 port_addr; + devtype = device_get_match_data(&client->dev); + if (!devtype) + return dev_err_probe(&client->dev, -ENODEV, "Failed to match device\n"); + if (client->addr < devtype->slave_addr.min || client->addr > devtype->slave_addr.max) return dev_err_probe(&client->dev, -EINVAL, diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c index d21a4f3ef2fe614de096df2ac694ee102a1878fc..8b31017e7e56312b538c4c68009945ba501c112e 100644 --- a/drivers/tty/serial/mxs-auart.c +++ b/drivers/tty/serial/mxs-auart.c @@ -1094,11 +1094,13 @@ static void mxs_auart_set_ldisc(struct uart_port *port, static irqreturn_t mxs_auart_irq_handle(int irq, void *context) { - u32 istat; + u32 istat, stat; struct mxs_auart_port *s = context; u32 mctrl_temp = s->mctrl_prev; - u32 stat = mxs_read(s, REG_STAT); + uart_port_lock(&s->port); + + stat = mxs_read(s, REG_STAT); istat = mxs_read(s, REG_INTR); /* ack irq */ @@ -1134,6 +1136,8 @@ static irqreturn_t mxs_auart_irq_handle(int irq, void *context) istat &= ~AUART_INTR_TXIS; } + uart_port_unlock(&s->port); + return IRQ_HANDLED; } diff --git a/drivers/tty/serial/pmac_zilog.c b/drivers/tty/serial/pmac_zilog.c index fe2e4ec423f7948e5fd005c97b0d94e62a580b3e..daf15d23bb42ec3853af7efb242c3f960fc66d65 100644 --- a/drivers/tty/serial/pmac_zilog.c +++ b/drivers/tty/serial/pmac_zilog.c @@ -210,7 +210,6 @@ static bool pmz_receive_chars(struct uart_pmac_port *uap) { struct tty_port *port; unsigned char ch, r1, drop, flag; - int loops = 0; /* Sanity check, make sure the old bug is no longer happening */ if (uap->port.state == NULL) { @@ -291,24 +290,11 @@ static bool pmz_receive_chars(struct uart_pmac_port *uap) if (r1 & Rx_OVR) tty_insert_flip_char(port, 0, TTY_OVERRUN); next_char: - /* We can get stuck in an infinite loop getting char 0 when the - * line is in a wrong HW state, we break that here. - * When that happens, I disable the receive side of the driver. - * Note that what I've been experiencing is a real irq loop where - * I'm getting flooded regardless of the actual port speed. - * Something strange is going on with the HW - */ - if ((++loops) > 1000) - goto flood; ch = read_zsreg(uap, R0); if (!(ch & Rx_CH_AV)) break; } - return true; - flood: - pmz_interrupt_control(uap, 0); - pmz_error("pmz: rx irq flood !\n"); return true; } diff --git a/drivers/tty/serial/samsung_tty.c b/drivers/tty/serial/samsung_tty.c index aa2c51b84116fa313a23e1f480d4ae82081de860..589daed19e625aff6c42c8c4f6f5605fde5bc73e 100644 --- a/drivers/tty/serial/samsung_tty.c +++ b/drivers/tty/serial/samsung_tty.c @@ -996,11 +996,10 @@ static unsigned int s3c24xx_serial_tx_empty(struct uart_port *port) if ((ufstat & info->tx_fifomask) != 0 || (ufstat & info->tx_fifofull)) return 0; - - return 1; + return TIOCSER_TEMT; } - return s3c24xx_serial_txempty_nofifo(port); + return s3c24xx_serial_txempty_nofifo(port) ? TIOCSER_TEMT : 0; } /* no modem control lines */ diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index f0ed30d0a697cce15d3473d1a05abd63a63318de..fe3f1d655dfe24f7c3b8c74608d0c32e60ab9820 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -2561,7 +2561,12 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, port->type = PORT_UNKNOWN; flags |= UART_CONFIG_TYPE; } + /* Synchronize with possible boot console. */ + if (uart_console(port)) + console_lock(); port->ops->config_port(port, flags); + if (uart_console(port)) + console_unlock(); } if (port->type != PORT_UNKNOWN) { @@ -2569,6 +2574,10 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, uart_report_port(drv, port); + /* Synchronize with possible boot console. */ + if (uart_console(port)) + console_lock(); + /* Power up port for set_mctrl() */ uart_change_pm(state, UART_PM_STATE_ON); @@ -2585,6 +2594,9 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, uart_rs485_config(port); + if (uart_console(port)) + console_unlock(); + /* * If this driver supports console, and it hasn't been * successfully registered yet, try to re-register it. diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c index 2a9c4058824a8d9fea476f53ef241127278a13e9..7d11511c8c12afc33b135fc2123a388167edc2b0 100644 --- a/drivers/tty/serial/stm32-usart.c +++ b/drivers/tty/serial/stm32-usart.c @@ -755,6 +755,7 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) const struct stm32_usart_offsets *ofs = &stm32_port->info->ofs; u32 sr; unsigned int size; + irqreturn_t ret = IRQ_NONE; sr = readl_relaxed(port->membase + ofs->isr); @@ -763,11 +764,14 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) (sr & USART_SR_TC)) { stm32_usart_tc_interrupt_disable(port); stm32_usart_rs485_rts_disable(port); + ret = IRQ_HANDLED; } - if ((sr & USART_SR_RTOF) && ofs->icr != UNDEF_REG) + if ((sr & USART_SR_RTOF) && ofs->icr != UNDEF_REG) { writel_relaxed(USART_ICR_RTOCF, port->membase + ofs->icr); + ret = IRQ_HANDLED; + } if ((sr & USART_SR_WUF) && ofs->icr != UNDEF_REG) { /* Clear wake up flag and disable wake up interrupt */ @@ -776,6 +780,7 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) stm32_usart_clr_bits(port, ofs->cr3, USART_CR3_WUFIE); if (irqd_is_wakeup_set(irq_get_irq_data(port->irq))) pm_wakeup_event(tport->tty->dev, 0); + ret = IRQ_HANDLED; } /* @@ -790,6 +795,7 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) uart_unlock_and_check_sysrq(port); if (size) tty_flip_buffer_push(tport); + ret = IRQ_HANDLED; } } @@ -797,6 +803,7 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) spin_lock(&port->lock); stm32_usart_transmit_chars(port); spin_unlock(&port->lock); + ret = IRQ_HANDLED; } /* Receiver timeout irq for DMA RX */ @@ -806,9 +813,10 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) uart_unlock_and_check_sysrq(port); if (size) tty_flip_buffer_push(tport); + ret = IRQ_HANDLED; } - return IRQ_HANDLED; + return ret; } static void stm32_usart_set_mctrl(struct uart_port *port, unsigned int mctrl) @@ -1013,6 +1021,7 @@ static int stm32_usart_startup(struct uart_port *port) val |= USART_CR2_SWAP; writel_relaxed(val, port->membase + ofs->cr2); } + stm32_port->throttled = false; /* RX FIFO Flush */ if (ofs->rqr != UNDEF_REG) diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 981d2bfcf9a5ba2fb89f364d6e112fcfc0966e73..48a9ed7c93c97f8f929ce88846ee853b686b078c 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -398,7 +398,7 @@ static void vc_uniscr_delete(struct vc_data *vc, unsigned int nr) char32_t *ln = uniscr->lines[vc->state.y]; unsigned int x = vc->state.x, cols = vc->vc_cols; - memcpy(&ln[x], &ln[x + nr], (cols - x - nr) * sizeof(*ln)); + memmove(&ln[x], &ln[x + nr], (cols - x - nr) * sizeof(*ln)); memset32(&ln[cols - nr], ' ', nr); } } @@ -2515,7 +2515,7 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c) } return; case EScsiignore: - if (c >= 20 && c <= 0x3f) + if (c >= 0x20 && c <= 0x3f) return; vc->vc_state = ESnormal; return; diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 9fd4e9ed93b8b94ef9d0dc85440edcee3b056be1..948449a13247ce81fe42f4414f9d15b7ddfefeed 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -6159,7 +6159,6 @@ static void ufshcd_err_handling_prepare(struct ufs_hba *hba) ufshcd_hold(hba, false); if (!ufshcd_is_clkgating_allowed(hba)) ufshcd_setup_clocks(hba, true); - ufshcd_release(hba); pm_op = hba->is_sys_suspended ? UFS_SYSTEM_PM : UFS_RUNTIME_PM; ufshcd_vops_resume(hba, pm_op); } else { @@ -9045,7 +9044,10 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) /* UFS device & link must be active before we enter in this function */ if (!ufshcd_is_ufs_dev_active(hba) || !ufshcd_is_link_active(hba)) { - ret = -EINVAL; + /* Wait err handler finish or trigger err recovery */ + if (!ufshcd_eh_in_progress(hba)) + ufshcd_force_error_recovery(hba); + ret = -EBUSY; goto enable_scaling; } diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c index c08a6cfd119f2d4030840eea2ee1e02d1360c191..e5789dfcaff612e3afb328f20990381f8048ca68 100644 --- a/drivers/uio/uio_hv_generic.c +++ b/drivers/uio/uio_hv_generic.c @@ -181,12 +181,14 @@ hv_uio_cleanup(struct hv_device *dev, struct hv_uio_private_data *pdata) { if (pdata->send_gpadl.gpadl_handle) { vmbus_teardown_gpadl(dev->channel, &pdata->send_gpadl); - vfree(pdata->send_buf); + if (!pdata->send_gpadl.decrypted) + vfree(pdata->send_buf); } if (pdata->recv_gpadl.gpadl_handle) { vmbus_teardown_gpadl(dev->channel, &pdata->recv_gpadl); - vfree(pdata->recv_buf); + if (!pdata->recv_gpadl.decrypted) + vfree(pdata->recv_buf); } } @@ -295,7 +297,8 @@ hv_uio_probe(struct hv_device *dev, ret = vmbus_establish_gpadl(channel, pdata->recv_buf, RECV_BUFFER_SIZE, &pdata->recv_gpadl); if (ret) { - vfree(pdata->recv_buf); + if (!pdata->recv_gpadl.decrypted) + vfree(pdata->recv_buf); goto fail_close; } @@ -317,7 +320,8 @@ hv_uio_probe(struct hv_device *dev, ret = vmbus_establish_gpadl(channel, pdata->send_buf, SEND_BUFFER_SIZE, &pdata->send_gpadl); if (ret) { - vfree(pdata->send_buf); + if (!pdata->send_gpadl.decrypted) + vfree(pdata->send_buf); goto fail_close; } diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c index ccdd525bd7c800456a9edc8983b7589f979eba41..2b8f98f0707e7890af22510c6eb1e1ed528615ad 100644 --- a/drivers/usb/cdns3/cdns3-gadget.c +++ b/drivers/usb/cdns3/cdns3-gadget.c @@ -826,7 +826,11 @@ void cdns3_gadget_giveback(struct cdns3_endpoint *priv_ep, return; } - if (request->complete) { + /* + * zlp request is appended by driver, needn't call usb_gadget_giveback_request() to notify + * gadget composite driver. + */ + if (request->complete && request->buf != priv_dev->zlp_buf) { spin_unlock(&priv_dev->lock); usb_gadget_giveback_request(&priv_ep->endpoint, request); @@ -2537,11 +2541,11 @@ static int cdns3_gadget_ep_disable(struct usb_ep *ep) while (!list_empty(&priv_ep->wa2_descmiss_req_list)) { priv_req = cdns3_next_priv_request(&priv_ep->wa2_descmiss_req_list); + list_del_init(&priv_req->list); kfree(priv_req->request.buf); cdns3_gadget_ep_free_request(&priv_ep->endpoint, &priv_req->request); - list_del_init(&priv_req->list); --priv_ep->wa2_counter; } diff --git a/drivers/usb/cdns3/core.c b/drivers/usb/cdns3/core.c index 7b20d2d5c262e0b33b3fc72966f5e89d29f5b4b1..7242591b346bcb7546054a5328e6eaac6214ce8f 100644 --- a/drivers/usb/cdns3/core.c +++ b/drivers/usb/cdns3/core.c @@ -394,7 +394,6 @@ pm_put: return ret; } - /** * cdns_wakeup_irq - interrupt handler for wakeup events * @irq: irq number for cdns3/cdnsp core device diff --git a/drivers/usb/cdns3/drd.c b/drivers/usb/cdns3/drd.c index d00ff98dffabfa9cc1fdcde47212b9a0af843b7e..33ba30f79b3371b4e1994c46a57982403103f719 100644 --- a/drivers/usb/cdns3/drd.c +++ b/drivers/usb/cdns3/drd.c @@ -156,7 +156,8 @@ bool cdns_is_device(struct cdns *cdns) */ static void cdns_otg_disable_irq(struct cdns *cdns) { - writel(0, &cdns->otg_irq_regs->ien); + if (cdns->version) + writel(0, &cdns->otg_irq_regs->ien); } /** @@ -418,15 +419,20 @@ int cdns_drd_init(struct cdns *cdns) cdns->otg_regs = (void __iomem *)&cdns->otg_v1_regs->cmd; - if (readl(&cdns->otg_cdnsp_regs->did) == OTG_CDNSP_DID) { + state = readl(&cdns->otg_cdnsp_regs->did); + + if (OTG_CDNSP_CHECK_DID(state)) { cdns->otg_irq_regs = (struct cdns_otg_irq_regs __iomem *) &cdns->otg_cdnsp_regs->ien; cdns->version = CDNSP_CONTROLLER_V2; - } else { + } else if (OTG_CDNS3_CHECK_DID(state)) { cdns->otg_irq_regs = (struct cdns_otg_irq_regs __iomem *) &cdns->otg_v1_regs->ien; writel(1, &cdns->otg_v1_regs->simulate); cdns->version = CDNS3_CONTROLLER_V1; + } else { + dev_err(cdns->dev, "not supporte DID=0x%08x\n", state); + return -EINVAL; } dev_dbg(cdns->dev, "DRD version v1 (ID: %08x, rev: %08x)\n", @@ -479,7 +485,6 @@ int cdns_drd_exit(struct cdns *cdns) return 0; } - /* Indicate the cdns3 core was power lost before */ bool cdns_power_is_lost(struct cdns *cdns) { diff --git a/drivers/usb/cdns3/drd.h b/drivers/usb/cdns3/drd.h index cbdf94f73ed917bb14baf23a9087b10aca2f7015..d72370c321d3929fc477854585d9e46be6848fef 100644 --- a/drivers/usb/cdns3/drd.h +++ b/drivers/usb/cdns3/drd.h @@ -79,7 +79,11 @@ struct cdnsp_otg_regs { __le32 susp_timing_ctrl; }; -#define OTG_CDNSP_DID 0x0004034E +/* CDNSP driver supports 0x000403xx Cadence USB controller family. */ +#define OTG_CDNSP_CHECK_DID(did) (((did) & GENMASK(31, 8)) == 0x00040300) + +/* CDNS3 driver supports 0x000402xx Cadence USB controller family. */ +#define OTG_CDNS3_CHECK_DID(did) (((did) & GENMASK(31, 8)) == 0x00040200) /* * Common registers interface for both CDNS3 and CDNSP version of DRD. diff --git a/drivers/usb/cdns3/host.c b/drivers/usb/cdns3/host.c index 6164fc4c96a49b60b73f772bdc92b8acf383269c..ceca4d839dfd42b87167f4de3019ab63776fa6c2 100644 --- a/drivers/usb/cdns3/host.c +++ b/drivers/usb/cdns3/host.c @@ -18,6 +18,11 @@ #include "../host/xhci.h" #include "../host/xhci-plat.h" +/* + * The XECP_PORT_CAP_REG and XECP_AUX_CTRL_REG1 exist only + * in Cadence USB3 dual-role controller, so it can't be used + * with Cadence CDNSP dual-role controller. + */ #define XECP_PORT_CAP_REG 0x8000 #define XECP_AUX_CTRL_REG1 0x8120 @@ -57,6 +62,8 @@ static const struct xhci_plat_priv xhci_plat_cdns3_xhci = { .resume_quirk = xhci_cdns3_resume_quirk, }; +static const struct xhci_plat_priv xhci_plat_cdnsp_xhci; + static int __cdns_host_init(struct cdns *cdns) { struct platform_device *xhci; @@ -81,8 +88,13 @@ static int __cdns_host_init(struct cdns *cdns) goto err1; } - cdns->xhci_plat_data = kmemdup(&xhci_plat_cdns3_xhci, - sizeof(struct xhci_plat_priv), GFP_KERNEL); + if (cdns->version < CDNSP_CONTROLLER_V2) + cdns->xhci_plat_data = kmemdup(&xhci_plat_cdns3_xhci, + sizeof(struct xhci_plat_priv), GFP_KERNEL); + else + cdns->xhci_plat_data = kmemdup(&xhci_plat_cdnsp_xhci, + sizeof(struct xhci_plat_priv), GFP_KERNEL); + if (!cdns->xhci_plat_data) { ret = -ENOMEM; goto err1; diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c index 38703781ee2d1a72a46dfe45ca65d1b56d9e6417..1283c427cdf88927130701dddaba6bf62f4e0b81 100644 --- a/drivers/usb/common/ulpi.c +++ b/drivers/usb/common/ulpi.c @@ -301,7 +301,7 @@ static int ulpi_register(struct device *dev, struct ulpi *ulpi) return ret; } - root = debugfs_create_dir(dev_name(dev), ulpi_root); + root = debugfs_create_dir(dev_name(&ulpi->dev), ulpi_root); debugfs_create_file("regs", 0444, root, ulpi, &ulpi_regs_fops); dev_dbg(&ulpi->dev, "registered ULPI PHY: vendor %04x, product %04x\n", diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 8c6f3f8d4f21c8cb1de955651cfe81cc527b50f4..9ae55ff4d29ef01c4c4179ddfb8f0001e810f04b 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -60,6 +60,12 @@ #define USB_PING_RESPONSE_TIME 400 /* ns */ #define USB_REDUCE_FRAME_INTR_BINTERVAL 9 +/* + * The SET_ADDRESS request timeout will be 500 ms when + * USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT quirk flag is set. + */ +#define USB_SHORT_SET_ADDRESS_REQ_TIMEOUT 500 /* ms */ + /* Protect struct usb_device->state and ->children members * Note: Both are also protected by ->dev.sem, except that ->state can * change to USB_STATE_NOTATTACHED even when the semaphore isn't held. */ @@ -123,7 +129,6 @@ EXPORT_SYMBOL_GPL(ehci_cf_port_reset_rwsem); #define HUB_DEBOUNCE_STEP 25 #define HUB_DEBOUNCE_STABLE 100 -static void hub_release(struct kref *kref); static int usb_reset_and_verify_device(struct usb_device *udev); static int hub_port_disable(struct usb_hub *hub, int port1, int set_state); static bool hub_port_warm_reset_required(struct usb_hub *hub, int port1, @@ -685,14 +690,14 @@ static void kick_hub_wq(struct usb_hub *hub) */ intf = to_usb_interface(hub->intfdev); usb_autopm_get_interface_no_resume(intf); - kref_get(&hub->kref); + hub_get(hub); if (queue_work(hub_wq, &hub->events)) return; /* the work has already been scheduled */ usb_autopm_put_interface_async(intf); - kref_put(&hub->kref, hub_release); + hub_put(hub); } void usb_kick_hub_wq(struct usb_device *hdev) @@ -1060,7 +1065,7 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) goto init2; goto init3; } - kref_get(&hub->kref); + hub_get(hub); /* The superspeed hub except for root hub has to use Hub Depth * value as an offset into the route string to locate the bits @@ -1308,7 +1313,7 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) device_unlock(&hdev->dev); } - kref_put(&hub->kref, hub_release); + hub_put(hub); } /* Implement the continuations for the delays above */ @@ -1724,6 +1729,16 @@ static void hub_release(struct kref *kref) kfree(hub); } +void hub_get(struct usb_hub *hub) +{ + kref_get(&hub->kref); +} + +void hub_put(struct usb_hub *hub) +{ + kref_put(&hub->kref, hub_release); +} + static unsigned highspeed_hubs; static void hub_disconnect(struct usb_interface *intf) @@ -1772,7 +1787,7 @@ static void hub_disconnect(struct usb_interface *intf) onboard_hub_destroy_pdevs(&hub->onboard_hub_devs); - kref_put(&hub->kref, hub_release); + hub_put(hub); } static bool hub_descriptor_is_sane(struct usb_host_interface *desc) @@ -2389,17 +2404,25 @@ static int usb_enumerate_device_otg(struct usb_device *udev) } } else if (desc->bLength == sizeof (struct usb_otg_descriptor)) { - /* Set a_alt_hnp_support for legacy otg device */ - err = usb_control_msg(udev, - usb_sndctrlpipe(udev, 0), - USB_REQ_SET_FEATURE, 0, - USB_DEVICE_A_ALT_HNP_SUPPORT, - 0, NULL, 0, - USB_CTRL_SET_TIMEOUT); - if (err < 0) - dev_err(&udev->dev, - "set a_alt_hnp_support failed: %d\n", - err); + /* + * We are operating on a legacy OTP device + * These should be told that they are operating + * on the wrong port if we have another port that does + * support HNP + */ + if (bus->otg_port != 0) { + /* Set a_alt_hnp_support for legacy otg device */ + err = usb_control_msg(udev, + usb_sndctrlpipe(udev, 0), + USB_REQ_SET_FEATURE, 0, + USB_DEVICE_A_ALT_HNP_SUPPORT, + 0, NULL, 0, + USB_CTRL_SET_TIMEOUT); + if (err < 0) + dev_err(&udev->dev, + "set a_alt_hnp_support failed: %d\n", + err); + } } } #endif @@ -4631,7 +4654,12 @@ EXPORT_SYMBOL_GPL(usb_ep0_reinit); static int hub_set_address(struct usb_device *udev, int devnum) { int retval; + unsigned int timeout_ms = USB_CTRL_SET_TIMEOUT; struct usb_hcd *hcd = bus_to_hcd(udev->bus); + struct usb_hub *hub = usb_hub_to_struct_hub(udev->parent); + + if (hub->hdev->quirks & USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT) + timeout_ms = USB_SHORT_SET_ADDRESS_REQ_TIMEOUT; /* * The host controller will choose the device address, @@ -4644,11 +4672,11 @@ static int hub_set_address(struct usb_device *udev, int devnum) if (udev->state != USB_STATE_DEFAULT) return -EINVAL; if (hcd->driver->address_device) - retval = hcd->driver->address_device(hcd, udev); + retval = hcd->driver->address_device(hcd, udev, timeout_ms); else retval = usb_control_msg(udev, usb_sndaddr0pipe(), USB_REQ_SET_ADDRESS, 0, devnum, 0, - NULL, 0, USB_CTRL_SET_TIMEOUT); + NULL, 0, timeout_ms); if (retval == 0) { update_devnum(udev, devnum); /* Device now using proper address. */ @@ -5041,9 +5069,10 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, } if (usb_endpoint_maxp(&udev->ep0.desc) == i) { ; /* Initial ep0 maxpacket guess is right */ - } else if ((udev->speed == USB_SPEED_FULL || + } else if (((udev->speed == USB_SPEED_FULL || udev->speed == USB_SPEED_HIGH) && - (i == 8 || i == 16 || i == 32 || i == 64)) { + (i == 8 || i == 16 || i == 32 || i == 64)) || + (udev->speed >= USB_SPEED_SUPER && i > 0)) { /* Initial guess is wrong; use the descriptor's value */ if (udev->speed == USB_SPEED_FULL) dev_dbg(&udev->dev, "ep0 maxpacket = %d\n", i); @@ -5866,7 +5895,7 @@ out_hdev_lock: /* Balance the stuff in kick_hub_wq() and allow autosuspend */ usb_autopm_put_interface(intf); - kref_put(&hub->kref, hub_release); + hub_put(hub); kcov_remote_stop(); } diff --git a/drivers/usb/core/hub.h b/drivers/usb/core/hub.h index bc66205ca52c33958e8123f8267d081d85d974d6..1085c72335d5c20ae6322743845357b424ed2f0c 100644 --- a/drivers/usb/core/hub.h +++ b/drivers/usb/core/hub.h @@ -118,6 +118,8 @@ extern void usb_hub_remove_port_device(struct usb_hub *hub, extern int usb_hub_set_port_power(struct usb_device *hdev, struct usb_hub *hub, int port1, bool set); extern struct usb_hub *usb_hub_to_struct_hub(struct usb_device *hdev); +extern void hub_get(struct usb_hub *hub); +extern void hub_put(struct usb_hub *hub); extern int hub_port_debounce(struct usb_hub *hub, int port1, bool must_be_connected); extern int usb_clear_port_feature(struct usb_device *hdev, diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c index 38c1a4f4fdeae5025633727774a15eace5b4492f..0007031fad0de15f563ffd1676035d9b463a35b6 100644 --- a/drivers/usb/core/port.c +++ b/drivers/usb/core/port.c @@ -23,16 +23,29 @@ static ssize_t disable_show(struct device *dev, struct usb_port *port_dev = to_usb_port(dev); struct usb_device *hdev = to_usb_device(dev->parent->parent); struct usb_hub *hub = usb_hub_to_struct_hub(hdev); - struct usb_interface *intf = to_usb_interface(hub->intfdev); + struct usb_interface *intf = to_usb_interface(dev->parent); int port1 = port_dev->portnum; u16 portstatus, unused; bool disabled; int rc; + struct kernfs_node *kn; + if (!hub) + return -ENODEV; + hub_get(hub); rc = usb_autopm_get_interface(intf); if (rc < 0) - return rc; + goto out_hub_get; + /* + * Prevent deadlock if another process is concurrently + * trying to unregister hdev. + */ + kn = sysfs_break_active_protection(&dev->kobj, &attr->attr); + if (!kn) { + rc = -ENODEV; + goto out_autopm; + } usb_lock_device(hdev); if (hub->disconnected) { rc = -ENODEV; @@ -42,9 +55,13 @@ static ssize_t disable_show(struct device *dev, usb_hub_port_status(hub, port1, &portstatus, &unused); disabled = !usb_port_is_power_on(hub, portstatus); -out_hdev_lock: + out_hdev_lock: usb_unlock_device(hdev); + sysfs_unbreak_active_protection(kn); + out_autopm: usb_autopm_put_interface(intf); + out_hub_get: + hub_put(hub); if (rc) return rc; @@ -58,19 +75,32 @@ static ssize_t disable_store(struct device *dev, struct device_attribute *attr, struct usb_port *port_dev = to_usb_port(dev); struct usb_device *hdev = to_usb_device(dev->parent->parent); struct usb_hub *hub = usb_hub_to_struct_hub(hdev); - struct usb_interface *intf = to_usb_interface(hub->intfdev); + struct usb_interface *intf = to_usb_interface(dev->parent); int port1 = port_dev->portnum; bool disabled; int rc; + struct kernfs_node *kn; + if (!hub) + return -ENODEV; rc = strtobool(buf, &disabled); if (rc) return rc; + hub_get(hub); rc = usb_autopm_get_interface(intf); if (rc < 0) - return rc; + goto out_hub_get; + /* + * Prevent deadlock if another process is concurrently + * trying to unregister hdev. + */ + kn = sysfs_break_active_protection(&dev->kobj, &attr->attr); + if (!kn) { + rc = -ENODEV; + goto out_autopm; + } usb_lock_device(hdev); if (hub->disconnected) { rc = -ENODEV; @@ -91,9 +121,13 @@ static ssize_t disable_store(struct device *dev, struct device_attribute *attr, if (!rc) rc = count; -out_hdev_lock: + out_hdev_lock: usb_unlock_device(hdev); + sysfs_unbreak_active_protection(kn); + out_autopm: usb_autopm_put_interface(intf); + out_hub_get: + hub_put(hub); return rc; } @@ -379,8 +413,10 @@ static void usb_port_shutdown(struct device *dev) { struct usb_port *port_dev = to_usb_port(dev); - if (port_dev->child) + if (port_dev->child) { usb_disable_usb2_hardware_lpm(port_dev->child); + usb_unlocked_disable_lpm(port_dev->child); + } } static const struct dev_pm_ops usb_port_pm_ops = { @@ -534,7 +570,7 @@ static int match_location(struct usb_device *peer_hdev, void *p) struct usb_hub *peer_hub = usb_hub_to_struct_hub(peer_hdev); struct usb_device *hdev = to_usb_device(port_dev->dev.parent->parent); - if (!peer_hub) + if (!peer_hub || port_dev->connect_type == USB_PORT_NOT_USED) return 0; hcd = bus_to_hcd(hdev->bus); @@ -545,7 +581,8 @@ static int match_location(struct usb_device *peer_hdev, void *p) for (port1 = 1; port1 <= peer_hdev->maxchild; port1++) { peer = peer_hub->ports[port1 - 1]; - if (peer && peer->location == port_dev->location) { + if (peer && peer->connect_type != USB_PORT_NOT_USED && + peer->location == port_dev->location) { link_peers_report(port_dev, peer); return 1; /* done */ } diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 15e9bd180a1d253f3b3cd2eebb3de68bcae9fb5e..b4783574b8e6603b7c521accdbc4cc52518d61ec 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -138,6 +138,9 @@ static int quirks_param_set(const char *value, const struct kernel_param *kp) case 'o': flags |= USB_QUIRK_HUB_SLOW_RESET; break; + case 'p': + flags |= USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT; + break; /* Ignore unrecognized flag characters */ } } @@ -527,6 +530,10 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x2386, 0x350e), .driver_info = USB_QUIRK_NO_LPM }, + /* APTIV AUTOMOTIVE HUB */ + { USB_DEVICE(0x2c48, 0x0132), .driver_info = + USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT }, + /* DJI CineSSD */ { USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM }, diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c index ccf6cd972269340b50df0ed1b4401badba0096f9..5f1e07341f36368bf2107fc98249fd75fcc05680 100644 --- a/drivers/usb/core/sysfs.c +++ b/drivers/usb/core/sysfs.c @@ -1170,14 +1170,24 @@ static ssize_t interface_authorized_store(struct device *dev, { struct usb_interface *intf = to_usb_interface(dev); bool val; + struct kernfs_node *kn; if (strtobool(buf, &val) != 0) return -EINVAL; - if (val) + if (val) { usb_authorize_interface(intf); - else - usb_deauthorize_interface(intf); + } else { + /* + * Prevent deadlock if another process is concurrently + * trying to unregister intf. + */ + kn = sysfs_break_active_protection(&dev->kobj, &attr->attr); + if (kn) { + usb_deauthorize_interface(intf); + sysfs_unbreak_active_protection(kn); + } + } return count; } diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h index 40cf2880d7e595354a25fafd056f6758f19d5ecc..b106c0e0b77bae1c22a2919b47047ffe5887f6f7 100644 --- a/drivers/usb/dwc2/core.h +++ b/drivers/usb/dwc2/core.h @@ -729,8 +729,14 @@ struct dwc2_dregs_backup { * struct dwc2_hregs_backup - Holds host registers state before * entering partial power down * @hcfg: Backup of HCFG register + * @hflbaddr: Backup of HFLBADDR register * @haintmsk: Backup of HAINTMSK register + * @hcchar: Backup of HCCHAR register + * @hcsplt: Backup of HCSPLT register * @hcintmsk: Backup of HCINTMSK register + * @hctsiz: Backup of HCTSIZ register + * @hdma: Backup of HCDMA register + * @hcdmab: Backup of HCDMAB register * @hprt0: Backup of HPTR0 register * @hfir: Backup of HFIR register * @hptxfsiz: Backup of HPTXFSIZ register @@ -738,8 +744,14 @@ struct dwc2_dregs_backup { */ struct dwc2_hregs_backup { u32 hcfg; + u32 hflbaddr; u32 haintmsk; + u32 hcchar[MAX_EPS_CHANNELS]; + u32 hcsplt[MAX_EPS_CHANNELS]; u32 hcintmsk[MAX_EPS_CHANNELS]; + u32 hctsiz[MAX_EPS_CHANNELS]; + u32 hcidma[MAX_EPS_CHANNELS]; + u32 hcidmab[MAX_EPS_CHANNELS]; u32 hprt0; u32 hfir; u32 hptxfsiz; @@ -1084,6 +1096,7 @@ struct dwc2_hsotg { bool needs_byte_swap; /* DWC OTG HW Release versions */ +#define DWC2_CORE_REV_4_30a 0x4f54430a #define DWC2_CORE_REV_2_71a 0x4f54271a #define DWC2_CORE_REV_2_72a 0x4f54272a #define DWC2_CORE_REV_2_80a 0x4f54280a @@ -1321,6 +1334,7 @@ int dwc2_backup_global_registers(struct dwc2_hsotg *hsotg); int dwc2_restore_global_registers(struct dwc2_hsotg *hsotg); void dwc2_enable_acg(struct dwc2_hsotg *hsotg); +void dwc2_wakeup_from_lpm_l1(struct dwc2_hsotg *hsotg, bool remotewakeup); /* This function should be called on every hardware interrupt. */ irqreturn_t dwc2_handle_common_intr(int irq, void *dev); diff --git a/drivers/usb/dwc2/core_intr.c b/drivers/usb/dwc2/core_intr.c index 158ede7538548e4d6daba4fc08d543f434b3ec6d..26d752a4c3ca956c7f7bd7c5dbb4a38f6670b03d 100644 --- a/drivers/usb/dwc2/core_intr.c +++ b/drivers/usb/dwc2/core_intr.c @@ -297,7 +297,8 @@ static void dwc2_handle_session_req_intr(struct dwc2_hsotg *hsotg) /* Exit gadget mode clock gating. */ if (hsotg->params.power_down == - DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended) + DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended && + !hsotg->params.no_clock_gating) dwc2_gadget_exit_clock_gating(hsotg, 0); } @@ -322,10 +323,11 @@ static void dwc2_handle_session_req_intr(struct dwc2_hsotg *hsotg) * @hsotg: Programming view of DWC_otg controller * */ -static void dwc2_wakeup_from_lpm_l1(struct dwc2_hsotg *hsotg) +void dwc2_wakeup_from_lpm_l1(struct dwc2_hsotg *hsotg, bool remotewakeup) { u32 glpmcfg; - u32 i = 0; + u32 pcgctl; + u32 dctl; if (hsotg->lx_state != DWC2_L1) { dev_err(hsotg->dev, "Core isn't in DWC2_L1 state\n"); @@ -334,37 +336,57 @@ static void dwc2_wakeup_from_lpm_l1(struct dwc2_hsotg *hsotg) glpmcfg = dwc2_readl(hsotg, GLPMCFG); if (dwc2_is_device_mode(hsotg)) { - dev_dbg(hsotg->dev, "Exit from L1 state\n"); + dev_dbg(hsotg->dev, "Exit from L1 state, remotewakeup=%d\n", remotewakeup); glpmcfg &= ~GLPMCFG_ENBLSLPM; - glpmcfg &= ~GLPMCFG_HIRD_THRES_EN; + glpmcfg &= ~GLPMCFG_HIRD_THRES_MASK; dwc2_writel(hsotg, glpmcfg, GLPMCFG); - do { - glpmcfg = dwc2_readl(hsotg, GLPMCFG); + pcgctl = dwc2_readl(hsotg, PCGCTL); + pcgctl &= ~PCGCTL_ENBL_SLEEP_GATING; + dwc2_writel(hsotg, pcgctl, PCGCTL); - if (!(glpmcfg & (GLPMCFG_COREL1RES_MASK | - GLPMCFG_L1RESUMEOK | GLPMCFG_SLPSTS))) - break; + glpmcfg = dwc2_readl(hsotg, GLPMCFG); + if (glpmcfg & GLPMCFG_ENBESL) { + glpmcfg |= GLPMCFG_RSTRSLPSTS; + dwc2_writel(hsotg, glpmcfg, GLPMCFG); + } + + if (remotewakeup) { + if (dwc2_hsotg_wait_bit_set(hsotg, GLPMCFG, GLPMCFG_L1RESUMEOK, 1000)) { + dev_warn(hsotg->dev, "%s: timeout GLPMCFG_L1RESUMEOK\n", __func__); + goto fail; + return; + } + + dctl = dwc2_readl(hsotg, DCTL); + dctl |= DCTL_RMTWKUPSIG; + dwc2_writel(hsotg, dctl, DCTL); - udelay(1); - } while (++i < 200); + if (dwc2_hsotg_wait_bit_set(hsotg, GINTSTS, GINTSTS_WKUPINT, 1000)) { + dev_warn(hsotg->dev, "%s: timeout GINTSTS_WKUPINT\n", __func__); + goto fail; + return; + } + } - if (i == 200) { - dev_err(hsotg->dev, "Failed to exit L1 sleep state in 200us.\n"); + glpmcfg = dwc2_readl(hsotg, GLPMCFG); + if (glpmcfg & GLPMCFG_COREL1RES_MASK || glpmcfg & GLPMCFG_SLPSTS || + glpmcfg & GLPMCFG_L1RESUMEOK) { + goto fail; return; } - dwc2_gadget_init_lpm(hsotg); + + /* Inform gadget to exit from L1 */ + call_gadget(hsotg, resume); + /* Change to L0 state */ + hsotg->lx_state = DWC2_L0; + hsotg->bus_suspended = false; +fail: dwc2_gadget_init_lpm(hsotg); } else { /* TODO */ dev_err(hsotg->dev, "Host side LPM is not supported.\n"); return; } - - /* Change to L0 state */ - hsotg->lx_state = DWC2_L0; - - /* Inform gadget to exit from L1 */ - call_gadget(hsotg, resume); } /* @@ -385,7 +407,7 @@ static void dwc2_handle_wakeup_detected_intr(struct dwc2_hsotg *hsotg) dev_dbg(hsotg->dev, "%s lxstate = %d\n", __func__, hsotg->lx_state); if (hsotg->lx_state == DWC2_L1) { - dwc2_wakeup_from_lpm_l1(hsotg); + dwc2_wakeup_from_lpm_l1(hsotg, false); return; } @@ -408,7 +430,8 @@ static void dwc2_handle_wakeup_detected_intr(struct dwc2_hsotg *hsotg) /* Exit gadget mode clock gating. */ if (hsotg->params.power_down == - DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended) + DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended && + !hsotg->params.no_clock_gating) dwc2_gadget_exit_clock_gating(hsotg, 0); } else { /* Change to L0 state */ @@ -425,7 +448,8 @@ static void dwc2_handle_wakeup_detected_intr(struct dwc2_hsotg *hsotg) } if (hsotg->params.power_down == - DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended) + DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended && + !hsotg->params.no_clock_gating) dwc2_host_exit_clock_gating(hsotg, 1); /* diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index 8b15742d9e8aa03301c41a7192207b33dd1a7293..cb29f9fae2f230634366d55e27f5759c4e9a99ab 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -1416,6 +1416,10 @@ static int dwc2_hsotg_ep_queue(struct usb_ep *ep, struct usb_request *req, ep->name, req, req->length, req->buf, req->no_interrupt, req->zero, req->short_not_ok); + if (hs->lx_state == DWC2_L1) { + dwc2_wakeup_from_lpm_l1(hs, true); + } + /* Prevent new request submission when controller is suspended */ if (hs->lx_state != DWC2_L0) { dev_dbg(hs->dev, "%s: submit request only in active state\n", @@ -3728,6 +3732,12 @@ irq_retry: if (hsotg->in_ppd && hsotg->lx_state == DWC2_L2) dwc2_exit_partial_power_down(hsotg, 0, true); + /* Exit gadget mode clock gating. */ + if (hsotg->params.power_down == + DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended && + !hsotg->params.no_clock_gating) + dwc2_gadget_exit_clock_gating(hsotg, 0); + hsotg->lx_state = DWC2_L0; } diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c index 35c7a4df8e71754f88d36f2f551d2e1e9eecef56..dd5b1c5691e11efa8e9300a289a32839e9212300 100644 --- a/drivers/usb/dwc2/hcd.c +++ b/drivers/usb/dwc2/hcd.c @@ -2701,8 +2701,11 @@ enum dwc2_transaction_type dwc2_hcd_select_transactions( hsotg->available_host_channels--; } qh = list_entry(qh_ptr, struct dwc2_qh, qh_list_entry); - if (dwc2_assign_and_init_hc(hsotg, qh)) + if (dwc2_assign_and_init_hc(hsotg, qh)) { + if (hsotg->params.uframe_sched) + hsotg->available_host_channels++; break; + } /* * Move the QH from the periodic ready schedule to the @@ -2735,8 +2738,11 @@ enum dwc2_transaction_type dwc2_hcd_select_transactions( hsotg->available_host_channels--; } - if (dwc2_assign_and_init_hc(hsotg, qh)) + if (dwc2_assign_and_init_hc(hsotg, qh)) { + if (hsotg->params.uframe_sched) + hsotg->available_host_channels++; break; + } /* * Move the QH from the non-periodic inactive schedule to the @@ -4143,6 +4149,8 @@ void dwc2_host_complete(struct dwc2_hsotg *hsotg, struct dwc2_qtd *qtd, urb->actual_length); if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) { + if (!hsotg->params.dma_desc_enable) + urb->start_frame = qtd->qh->start_active_frame; urb->error_count = dwc2_hcd_urb_get_error_count(qtd->urb); for (i = 0; i < urb->number_of_packets; ++i) { urb->iso_frame_desc[i].actual_length = @@ -4649,7 +4657,7 @@ static int _dwc2_hcd_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, } if (hsotg->params.power_down == DWC2_POWER_DOWN_PARAM_NONE && - hsotg->bus_suspended) { + hsotg->bus_suspended && !hsotg->params.no_clock_gating) { if (dwc2_is_device_mode(hsotg)) dwc2_gadget_exit_clock_gating(hsotg, 0); else @@ -5406,9 +5414,16 @@ int dwc2_backup_host_registers(struct dwc2_hsotg *hsotg) /* Backup Host regs */ hr = &hsotg->hr_backup; hr->hcfg = dwc2_readl(hsotg, HCFG); + hr->hflbaddr = dwc2_readl(hsotg, HFLBADDR); hr->haintmsk = dwc2_readl(hsotg, HAINTMSK); - for (i = 0; i < hsotg->params.host_channels; ++i) + for (i = 0; i < hsotg->params.host_channels; ++i) { + hr->hcchar[i] = dwc2_readl(hsotg, HCCHAR(i)); + hr->hcsplt[i] = dwc2_readl(hsotg, HCSPLT(i)); hr->hcintmsk[i] = dwc2_readl(hsotg, HCINTMSK(i)); + hr->hctsiz[i] = dwc2_readl(hsotg, HCTSIZ(i)); + hr->hcidma[i] = dwc2_readl(hsotg, HCDMA(i)); + hr->hcidmab[i] = dwc2_readl(hsotg, HCDMAB(i)); + } hr->hprt0 = dwc2_read_hprt0(hsotg); hr->hfir = dwc2_readl(hsotg, HFIR); @@ -5442,10 +5457,17 @@ int dwc2_restore_host_registers(struct dwc2_hsotg *hsotg) hr->valid = false; dwc2_writel(hsotg, hr->hcfg, HCFG); + dwc2_writel(hsotg, hr->hflbaddr, HFLBADDR); dwc2_writel(hsotg, hr->haintmsk, HAINTMSK); - for (i = 0; i < hsotg->params.host_channels; ++i) + for (i = 0; i < hsotg->params.host_channels; ++i) { + dwc2_writel(hsotg, hr->hcchar[i], HCCHAR(i)); + dwc2_writel(hsotg, hr->hcsplt[i], HCSPLT(i)); dwc2_writel(hsotg, hr->hcintmsk[i], HCINTMSK(i)); + dwc2_writel(hsotg, hr->hctsiz[i], HCTSIZ(i)); + dwc2_writel(hsotg, hr->hcidma[i], HCDMA(i)); + dwc2_writel(hsotg, hr->hcidmab[i], HCDMAB(i)); + } dwc2_writel(hsotg, hr->hprt0, HPRT0); dwc2_writel(hsotg, hr->hfir, HFIR); @@ -5610,10 +5632,12 @@ int dwc2_host_exit_hibernation(struct dwc2_hsotg *hsotg, int rem_wakeup, dwc2_writel(hsotg, hr->hcfg, HCFG); /* De-assert Wakeup Logic */ - gpwrdn = dwc2_readl(hsotg, GPWRDN); - gpwrdn &= ~GPWRDN_PMUACTV; - dwc2_writel(hsotg, gpwrdn, GPWRDN); - udelay(10); + if (!(rem_wakeup && hsotg->hw_params.snpsid >= DWC2_CORE_REV_4_30a)) { + gpwrdn = dwc2_readl(hsotg, GPWRDN); + gpwrdn &= ~GPWRDN_PMUACTV; + dwc2_writel(hsotg, gpwrdn, GPWRDN); + udelay(10); + } hprt0 = hr->hprt0; hprt0 |= HPRT0_PWR; @@ -5638,6 +5662,13 @@ int dwc2_host_exit_hibernation(struct dwc2_hsotg *hsotg, int rem_wakeup, hprt0 |= HPRT0_RES; dwc2_writel(hsotg, hprt0, HPRT0); + /* De-assert Wakeup Logic */ + if ((rem_wakeup && hsotg->hw_params.snpsid >= DWC2_CORE_REV_4_30a)) { + gpwrdn = dwc2_readl(hsotg, GPWRDN); + gpwrdn &= ~GPWRDN_PMUACTV; + dwc2_writel(hsotg, gpwrdn, GPWRDN); + udelay(10); + } /* Wait for Resume time and then program HPRT again */ mdelay(100); hprt0 &= ~HPRT0_RES; diff --git a/drivers/usb/dwc2/hcd_ddma.c b/drivers/usb/dwc2/hcd_ddma.c index 6b4d825e97a2d91bbafd04ada5fdce4a1ab52c0c..994a78ad084b1c485673ca3c88819d4e752ef2ee 100644 --- a/drivers/usb/dwc2/hcd_ddma.c +++ b/drivers/usb/dwc2/hcd_ddma.c @@ -559,7 +559,7 @@ static void dwc2_init_isoc_dma_desc(struct dwc2_hsotg *hsotg, idx = qh->td_last; inc = qh->host_interval; hsotg->frame_number = dwc2_hcd_get_frame_number(hsotg); - cur_idx = dwc2_frame_list_idx(hsotg->frame_number); + cur_idx = idx; next_idx = dwc2_desclist_idx_inc(qh->td_last, inc, qh->dev_speed); /* @@ -866,20 +866,27 @@ static int dwc2_cmpl_host_isoc_dma_desc(struct dwc2_hsotg *hsotg, { struct dwc2_dma_desc *dma_desc; struct dwc2_hcd_iso_packet_desc *frame_desc; + u16 frame_desc_idx; + struct urb *usb_urb; u16 remain = 0; int rc = 0; if (!qtd->urb) return -EINVAL; + usb_urb = qtd->urb->priv; + dma_sync_single_for_cpu(hsotg->dev, qh->desc_list_dma + (idx * sizeof(struct dwc2_dma_desc)), sizeof(struct dwc2_dma_desc), DMA_FROM_DEVICE); dma_desc = &qh->desc_list[idx]; + frame_desc_idx = (idx - qtd->isoc_td_first) & (usb_urb->number_of_packets - 1); - frame_desc = &qtd->urb->iso_descs[qtd->isoc_frame_index_last]; + frame_desc = &qtd->urb->iso_descs[frame_desc_idx]; + if (idx == qtd->isoc_td_first) + usb_urb->start_frame = dwc2_hcd_get_frame_number(hsotg); dma_desc->buf = (u32)(qtd->urb->dma + frame_desc->offset); if (chan->ep_is_in) remain = (dma_desc->status & HOST_DMA_ISOC_NBYTES_MASK) >> @@ -900,7 +907,7 @@ static int dwc2_cmpl_host_isoc_dma_desc(struct dwc2_hsotg *hsotg, frame_desc->status = 0; } - if (++qtd->isoc_frame_index == qtd->urb->packet_count) { + if (++qtd->isoc_frame_index == usb_urb->number_of_packets) { /* * urb->status is not used for isoc transfers here. The * individual frame_desc status are used instead. @@ -1005,11 +1012,11 @@ static void dwc2_complete_isoc_xfer_ddma(struct dwc2_hsotg *hsotg, return; idx = dwc2_desclist_idx_inc(idx, qh->host_interval, chan->speed); - if (!rc) + if (rc == 0) continue; - if (rc == DWC2_CMPL_DONE) - break; + if (rc == DWC2_CMPL_DONE || rc == DWC2_CMPL_STOP) + goto stop_scan; /* rc == DWC2_CMPL_STOP */ diff --git a/drivers/usb/dwc2/hw.h b/drivers/usb/dwc2/hw.h index 13abdd5f6752999cc20603fa404b02c3d84bac20..12f8c7f86dc980fc8fb754a7c6d82eab9f88bc7a 100644 --- a/drivers/usb/dwc2/hw.h +++ b/drivers/usb/dwc2/hw.h @@ -698,7 +698,7 @@ #define TXSTS_QTOP_TOKEN_MASK (0x3 << 25) #define TXSTS_QTOP_TOKEN_SHIFT 25 #define TXSTS_QTOP_TERMINATE BIT(24) -#define TXSTS_QSPCAVAIL_MASK (0xff << 16) +#define TXSTS_QSPCAVAIL_MASK (0x7f << 16) #define TXSTS_QSPCAVAIL_SHIFT 16 #define TXSTS_FSPCAVAIL_MASK (0xffff << 0) #define TXSTS_FSPCAVAIL_SHIFT 0 diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index 58f53faab340f13e7a9fc80a3ce9be6304fd9ba3..2e4c6884f36a418c2930dfbcbd0e9a0a2cdad511 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -298,7 +298,7 @@ static int dwc2_driver_remove(struct platform_device *dev) /* Exit clock gating when driver is removed. */ if (hsotg->params.power_down == DWC2_POWER_DOWN_PARAM_NONE && - hsotg->bus_suspended) { + hsotg->bus_suspended && !hsotg->params.no_clock_gating) { if (dwc2_is_device_mode(hsotg)) dwc2_gadget_exit_clock_gating(hsotg, 0); else diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 81a97ad5cbf48250e176aa4b8bf002dca82b050f..bc898dc1a86c3a30564314c2e27dfcd61b4c0052 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -104,6 +104,27 @@ static int dwc3_get_dr_mode(struct dwc3 *dwc) return 0; } +void dwc3_enable_susphy(struct dwc3 *dwc, bool enable) +{ + u32 reg; + + reg = dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0)); + if (enable && !dwc->dis_u3_susphy_quirk) + reg |= DWC3_GUSB3PIPECTL_SUSPHY; + else + reg &= ~DWC3_GUSB3PIPECTL_SUSPHY; + + dwc3_writel(dwc->regs, DWC3_GUSB3PIPECTL(0), reg); + + reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); + if (enable && !dwc->dis_u2_susphy_quirk) + reg |= DWC3_GUSB2PHYCFG_SUSPHY; + else + reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; + + dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg); +} + void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode) { u32 reg; @@ -669,11 +690,8 @@ static int dwc3_core_ulpi_init(struct dwc3 *dwc) */ static int dwc3_phy_setup(struct dwc3 *dwc) { - unsigned int hw_mode; u32 reg; - hw_mode = DWC3_GHWPARAMS0_MODE(dwc->hwparams.hwparams0); - reg = dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0)); /* @@ -683,21 +701,16 @@ static int dwc3_phy_setup(struct dwc3 *dwc) reg &= ~DWC3_GUSB3PIPECTL_UX_EXIT_PX; /* - * Above 1.94a, it is recommended to set DWC3_GUSB3PIPECTL_SUSPHY - * to '0' during coreConsultant configuration. So default value - * will be '0' when the core is reset. Application needs to set it - * to '1' after the core initialization is completed. - */ - if (!DWC3_VER_IS_WITHIN(DWC3, ANY, 194A)) - reg |= DWC3_GUSB3PIPECTL_SUSPHY; - - /* - * For DRD controllers, GUSB3PIPECTL.SUSPENDENABLE must be cleared after - * power-on reset, and it can be set after core initialization, which is - * after device soft-reset during initialization. + * Above DWC_usb3.0 1.94a, it is recommended to set + * DWC3_GUSB3PIPECTL_SUSPHY to '0' during coreConsultant configuration. + * So default value will be '0' when the core is reset. Application + * needs to set it to '1' after the core initialization is completed. + * + * Similarly for DRD controllers, GUSB3PIPECTL.SUSPENDENABLE must be + * cleared after power-on reset, and it can be set after core + * initialization. */ - if (hw_mode == DWC3_GHWPARAMS0_MODE_DRD) - reg &= ~DWC3_GUSB3PIPECTL_SUSPHY; + reg &= ~DWC3_GUSB3PIPECTL_SUSPHY; if (dwc->u2ss_inp3_quirk) reg |= DWC3_GUSB3PIPECTL_U2SSINP3OK; @@ -723,9 +736,6 @@ static int dwc3_phy_setup(struct dwc3 *dwc) if (dwc->tx_de_emphasis_quirk) reg |= DWC3_GUSB3PIPECTL_TX_DEEPH(dwc->tx_de_emphasis); - if (dwc->dis_u3_susphy_quirk) - reg &= ~DWC3_GUSB3PIPECTL_SUSPHY; - if (dwc->dis_del_phy_power_chg_quirk) reg &= ~DWC3_GUSB3PIPECTL_DEPOCHANGE; @@ -773,24 +783,15 @@ static int dwc3_phy_setup(struct dwc3 *dwc) } /* - * Above 1.94a, it is recommended to set DWC3_GUSB2PHYCFG_SUSPHY to - * '0' during coreConsultant configuration. So default value will - * be '0' when the core is reset. Application needs to set it to - * '1' after the core initialization is completed. - */ - if (!DWC3_VER_IS_WITHIN(DWC3, ANY, 194A)) - reg |= DWC3_GUSB2PHYCFG_SUSPHY; - - /* - * For DRD controllers, GUSB2PHYCFG.SUSPHY must be cleared after - * power-on reset, and it can be set after core initialization, which is - * after device soft-reset during initialization. + * Above DWC_usb3.0 1.94a, it is recommended to set + * DWC3_GUSB2PHYCFG_SUSPHY to '0' during coreConsultant configuration. + * So default value will be '0' when the core is reset. Application + * needs to set it to '1' after the core initialization is completed. + * + * Similarly for DRD controllers, GUSB2PHYCFG.SUSPHY must be cleared + * after power-on reset, and it can be set after core initialization. */ - if (hw_mode == DWC3_GHWPARAMS0_MODE_DRD) - reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; - - if (dwc->dis_u2_susphy_quirk) - reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; + reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; if (dwc->dis_enblslpm_quirk) reg &= ~DWC3_GUSB2PHYCFG_ENBLSLPM; @@ -1256,21 +1257,6 @@ static int dwc3_core_init(struct dwc3 *dwc) if (ret) goto err1; - if (hw_mode == DWC3_GHWPARAMS0_MODE_DRD && - !DWC3_VER_IS_WITHIN(DWC3, ANY, 194A)) { - if (!dwc->dis_u3_susphy_quirk) { - reg = dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0)); - reg |= DWC3_GUSB3PIPECTL_SUSPHY; - dwc3_writel(dwc->regs, DWC3_GUSB3PIPECTL(0), reg); - } - - if (!dwc->dis_u2_susphy_quirk) { - reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); - reg |= DWC3_GUSB2PHYCFG_SUSPHY; - dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg); - } - } - dwc3_core_setup_global_control(dwc); dwc3_core_num_eps(dwc); diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 8cf71e305d715793e51fb7aaa6cb4436c68e5b1f..11212eca3765f44b32e75f097e14bf05510db36a 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -1563,6 +1563,7 @@ int dwc3_event_buffers_setup(struct dwc3 *dwc); void dwc3_event_buffers_cleanup(struct dwc3 *dwc); int dwc3_core_soft_reset(struct dwc3 *dwc); +void dwc3_enable_susphy(struct dwc3 *dwc, bool enable); #if IS_ENABLED(CONFIG_USB_DWC3_HOST) || IS_ENABLED(CONFIG_USB_DWC3_DUAL_ROLE) int dwc3_host_init(struct dwc3 *dwc); diff --git a/drivers/usb/dwc3/dwc3-am62.c b/drivers/usb/dwc3/dwc3-am62.c index 173cf3579c55d8098f89f1c5a1615cdc5eb98611..ad8a2eadb472b6391966d495460e2f4a0f241673 100644 --- a/drivers/usb/dwc3/dwc3-am62.c +++ b/drivers/usb/dwc3/dwc3-am62.c @@ -89,7 +89,7 @@ #define DWC3_AM62_AUTOSUSPEND_DELAY 100 -struct dwc3_data { +struct dwc3_am62 { struct device *dev; void __iomem *usbss; struct clk *usb2_refclk; @@ -115,19 +115,19 @@ static const int dwc3_ti_rate_table[] = { /* in KHZ */ 52000, }; -static inline u32 dwc3_ti_readl(struct dwc3_data *data, u32 offset) +static inline u32 dwc3_ti_readl(struct dwc3_am62 *am62, u32 offset) { - return readl((data->usbss) + offset); + return readl((am62->usbss) + offset); } -static inline void dwc3_ti_writel(struct dwc3_data *data, u32 offset, u32 value) +static inline void dwc3_ti_writel(struct dwc3_am62 *am62, u32 offset, u32 value) { - writel(value, (data->usbss) + offset); + writel(value, (am62->usbss) + offset); } -static int phy_syscon_pll_refclk(struct dwc3_data *data) +static int phy_syscon_pll_refclk(struct dwc3_am62 *am62) { - struct device *dev = data->dev; + struct device *dev = am62->dev; struct device_node *node = dev->of_node; struct of_phandle_args args; struct regmap *syscon; @@ -139,16 +139,16 @@ static int phy_syscon_pll_refclk(struct dwc3_data *data) return PTR_ERR(syscon); } - data->syscon = syscon; + am62->syscon = syscon; ret = of_parse_phandle_with_fixed_args(node, "ti,syscon-phy-pll-refclk", 1, 0, &args); if (ret) return ret; - data->offset = args.args[0]; + am62->offset = args.args[0]; - ret = regmap_update_bits(data->syscon, data->offset, PHY_PLL_REFCLK_MASK, data->rate_code); + ret = regmap_update_bits(am62->syscon, am62->offset, PHY_PLL_REFCLK_MASK, am62->rate_code); if (ret) { dev_err(dev, "failed to set phy pll reference clock rate\n"); return ret; @@ -161,32 +161,32 @@ static int dwc3_ti_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct device_node *node = pdev->dev.of_node; - struct dwc3_data *data; + struct dwc3_am62 *am62; int i, ret; unsigned long rate; u32 reg; - data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); - if (!data) + am62 = devm_kzalloc(dev, sizeof(*am62), GFP_KERNEL); + if (!am62) return -ENOMEM; - data->dev = dev; - platform_set_drvdata(pdev, data); + am62->dev = dev; + platform_set_drvdata(pdev, am62); - data->usbss = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(data->usbss)) { + am62->usbss = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(am62->usbss)) { dev_err(dev, "can't map IOMEM resource\n"); - return PTR_ERR(data->usbss); + return PTR_ERR(am62->usbss); } - data->usb2_refclk = devm_clk_get(dev, "ref"); - if (IS_ERR(data->usb2_refclk)) { + am62->usb2_refclk = devm_clk_get(dev, "ref"); + if (IS_ERR(am62->usb2_refclk)) { dev_err(dev, "can't get usb2_refclk\n"); - return PTR_ERR(data->usb2_refclk); + return PTR_ERR(am62->usb2_refclk); } /* Calculate the rate code */ - rate = clk_get_rate(data->usb2_refclk); + rate = clk_get_rate(am62->usb2_refclk); rate /= 1000; // To KHz for (i = 0; i < ARRAY_SIZE(dwc3_ti_rate_table); i++) { if (dwc3_ti_rate_table[i] == rate) @@ -198,20 +198,20 @@ static int dwc3_ti_probe(struct platform_device *pdev) return -EINVAL; } - data->rate_code = i; + am62->rate_code = i; /* Read the syscon property and set the rate code */ - ret = phy_syscon_pll_refclk(data); + ret = phy_syscon_pll_refclk(am62); if (ret) return ret; /* VBUS divider select */ - data->vbus_divider = device_property_read_bool(dev, "ti,vbus-divider"); - reg = dwc3_ti_readl(data, USBSS_PHY_CONFIG); - if (data->vbus_divider) + am62->vbus_divider = device_property_read_bool(dev, "ti,vbus-divider"); + reg = dwc3_ti_readl(am62, USBSS_PHY_CONFIG); + if (am62->vbus_divider) reg |= 1 << USBSS_PHY_VBUS_SEL_SHIFT; - dwc3_ti_writel(data, USBSS_PHY_CONFIG, reg); + dwc3_ti_writel(am62, USBSS_PHY_CONFIG, reg); pm_runtime_set_active(dev); pm_runtime_enable(dev); @@ -219,7 +219,7 @@ static int dwc3_ti_probe(struct platform_device *pdev) * Don't ignore its dependencies with its children */ pm_suspend_ignore_children(dev, false); - clk_prepare_enable(data->usb2_refclk); + clk_prepare_enable(am62->usb2_refclk); pm_runtime_get_noresume(dev); ret = of_platform_populate(node, NULL, NULL, dev); @@ -229,9 +229,9 @@ static int dwc3_ti_probe(struct platform_device *pdev) } /* Set mode valid bit to indicate role is valid */ - reg = dwc3_ti_readl(data, USBSS_MODE_CONTROL); + reg = dwc3_ti_readl(am62, USBSS_MODE_CONTROL); reg |= USBSS_MODE_VALID; - dwc3_ti_writel(data, USBSS_MODE_CONTROL, reg); + dwc3_ti_writel(am62, USBSS_MODE_CONTROL, reg); /* Setting up autosuspend */ pm_runtime_set_autosuspend_delay(dev, DWC3_AM62_AUTOSUSPEND_DELAY); @@ -241,35 +241,27 @@ static int dwc3_ti_probe(struct platform_device *pdev) return 0; err_pm_disable: - clk_disable_unprepare(data->usb2_refclk); + clk_disable_unprepare(am62->usb2_refclk); pm_runtime_disable(dev); pm_runtime_set_suspended(dev); return ret; } -static int dwc3_ti_remove_core(struct device *dev, void *c) -{ - struct platform_device *pdev = to_platform_device(dev); - - platform_device_unregister(pdev); - return 0; -} - static int dwc3_ti_remove(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct dwc3_data *data = platform_get_drvdata(pdev); + struct dwc3_am62 *am62 = platform_get_drvdata(pdev); u32 reg; - device_for_each_child(dev, NULL, dwc3_ti_remove_core); + pm_runtime_get_sync(dev); + of_platform_depopulate(dev); /* Clear mode valid bit */ - reg = dwc3_ti_readl(data, USBSS_MODE_CONTROL); + reg = dwc3_ti_readl(am62, USBSS_MODE_CONTROL); reg &= ~USBSS_MODE_VALID; - dwc3_ti_writel(data, USBSS_MODE_CONTROL, reg); + dwc3_ti_writel(am62, USBSS_MODE_CONTROL, reg); pm_runtime_put_sync(dev); - clk_disable_unprepare(data->usb2_refclk); pm_runtime_disable(dev); pm_runtime_set_suspended(dev); @@ -280,18 +272,18 @@ static int dwc3_ti_remove(struct platform_device *pdev) #ifdef CONFIG_PM static int dwc3_ti_suspend_common(struct device *dev) { - struct dwc3_data *data = dev_get_drvdata(dev); + struct dwc3_am62 *am62 = dev_get_drvdata(dev); - clk_disable_unprepare(data->usb2_refclk); + clk_disable_unprepare(am62->usb2_refclk); return 0; } static int dwc3_ti_resume_common(struct device *dev) { - struct dwc3_data *data = dev_get_drvdata(dev); + struct dwc3_am62 *am62 = dev_get_drvdata(dev); - clk_prepare_enable(data->usb2_refclk); + clk_prepare_enable(am62->usb2_refclk); return 0; } diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index c4703f6b208940e5a5e83369ddf70d5a09ddceaf..c72c6f8ec2c88bd6d845de10daee224e782ccbe7 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1708,7 +1708,6 @@ static int __dwc3_gadget_get_frame(struct dwc3 *dwc) */ static int __dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool interrupt) { - struct dwc3 *dwc = dep->dwc; struct dwc3_gadget_ep_cmd_params params; u32 cmd; int ret; @@ -1733,8 +1732,7 @@ static int __dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool int dep->resource_index = 0; if (!interrupt) { - if (!DWC3_IP_IS(DWC3) || DWC3_VER_IS_PRIOR(DWC3, 310A)) - mdelay(1); + mdelay(1); dep->flags &= ~DWC3_EP_TRANSFER_STARTED; } else if (!ret) { dep->flags |= DWC3_EP_END_TRANSFER_PENDING; @@ -2548,6 +2546,11 @@ static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc) int ret; spin_lock_irqsave(&dwc->lock, flags); + if (!dwc->pullups_connected) { + spin_unlock_irqrestore(&dwc->lock, flags); + return 0; + } + dwc->connected = false; /* @@ -2826,6 +2829,7 @@ static int __dwc3_gadget_start(struct dwc3 *dwc) dwc3_ep0_out_start(dwc); dwc3_gadget_enable_irq(dwc); + dwc3_enable_susphy(dwc, true); return 0; @@ -4568,6 +4572,7 @@ void dwc3_gadget_exit(struct dwc3 *dwc) if (!dwc->gadget) return; + dwc3_enable_susphy(dwc, false); usb_del_gadget(dwc->gadget); dwc3_gadget_free_endpoints(dwc); usb_put_gadget(dwc->gadget); @@ -4583,15 +4588,13 @@ int dwc3_gadget_suspend(struct dwc3 *dwc) unsigned long flags; int ret; - if (!dwc->gadget_driver) - return 0; - ret = dwc3_gadget_soft_disconnect(dwc); if (ret) goto err; spin_lock_irqsave(&dwc->lock, flags); - dwc3_disconnect_gadget(dwc); + if (dwc->gadget_driver) + dwc3_disconnect_gadget(dwc); spin_unlock_irqrestore(&dwc->lock, flags); return 0; diff --git a/drivers/usb/dwc3/host.c b/drivers/usb/dwc3/host.c index 683434660b40eafece3d11a0aa1a130f25dbfe49..4656c52486aec80f9628bd0f58d6b35822caf226 100644 --- a/drivers/usb/dwc3/host.c +++ b/drivers/usb/dwc3/host.c @@ -10,9 +10,30 @@ #include #include #include +#include +#include +#include "../host/xhci-plat.h" #include "core.h" +static void dwc3_xhci_plat_start(struct usb_hcd *hcd) +{ + struct platform_device *pdev; + struct dwc3 *dwc; + + if (!usb_hcd_is_primary_hcd(hcd)) + return; + + pdev = to_platform_device(hcd->self.controller); + dwc = dev_get_drvdata(pdev->dev.parent); + + dwc3_enable_susphy(dwc, true); +} + +static const struct xhci_plat_priv dwc3_xhci_plat_quirk = { + .plat_start = dwc3_xhci_plat_start, +}; + static void dwc3_host_fill_xhci_irq_res(struct dwc3 *dwc, int irq, char *name) { @@ -66,7 +87,7 @@ out: int dwc3_host_init(struct dwc3 *dwc) { - struct property_entry props[4]; + struct property_entry props[5]; struct platform_device *xhci; struct platform_device *pdev = to_platform_device(dwc->dev); int ret, irq; @@ -101,6 +122,8 @@ int dwc3_host_init(struct dwc3 *dwc) memset(props, 0, sizeof(struct property_entry) * ARRAY_SIZE(props)); + props[prop_idx++] = PROPERTY_ENTRY_BOOL("xhci-sg-trb-cache-size-quirk"); + if (dwc->usb3_lpm_capable) props[prop_idx++] = PROPERTY_ENTRY_BOOL("usb3-lpm-capable"); @@ -127,6 +150,11 @@ int dwc3_host_init(struct dwc3 *dwc) } } + ret = platform_device_add_data(xhci, &dwc3_xhci_plat_quirk, + sizeof(struct xhci_plat_priv)); + if (ret) + goto err; + ret = platform_device_add(xhci); if (ret) { dev_err(dwc->dev, "failed to register xHCI device\n"); @@ -141,6 +169,7 @@ err: void dwc3_host_exit(struct dwc3 *dwc) { + dwc3_enable_susphy(dwc, false); platform_device_unregister(dwc->xhci); dwc->xhci = NULL; } diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index cb0a4e2cdbb737eba8a34b9428dfb66962e96abe..f10e43a948fd8cec8d0f5ab2ce29a8277e069290 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -511,6 +511,19 @@ static u8 encode_bMaxPower(enum usb_device_speed speed, return min(val, 900U) / 8; } +void check_remote_wakeup_config(struct usb_gadget *g, + struct usb_configuration *c) +{ + if (USB_CONFIG_ATT_WAKEUP & c->bmAttributes) { + /* Reset the rw bit if gadget is not capable of it */ + if (!g->wakeup_capable && g->ops->set_remote_wakeup) { + WARN(c->cdev, "Clearing wakeup bit for config c.%d\n", + c->bConfigurationValue); + c->bmAttributes &= ~USB_CONFIG_ATT_WAKEUP; + } + } +} + static int config_buf(struct usb_configuration *config, enum usb_device_speed speed, void *buf, u8 type) { @@ -959,6 +972,11 @@ static int set_config(struct usb_composite_dev *cdev, power = min(power, 500U); else power = min(power, 900U); + + if (USB_CONFIG_ATT_WAKEUP & c->bmAttributes) + usb_gadget_set_remote_wakeup(gadget, 1); + else + usb_gadget_set_remote_wakeup(gadget, 0); done: if (power <= USB_SELF_POWER_VBUS_MAX_DRAW) usb_gadget_set_selfpowered(gadget); @@ -1975,7 +1993,7 @@ unknown: buf[5] = 0x01; switch (ctrl->bRequestType & USB_RECIP_MASK) { case USB_RECIP_DEVICE: - if (w_index != 0x4 || (w_value >> 8)) + if (w_index != 0x4 || (w_value & 0xff)) break; buf[6] = w_index; /* Number of ext compat interfaces */ @@ -1991,9 +2009,9 @@ unknown: } break; case USB_RECIP_INTERFACE: - if (w_index != 0x5 || (w_value >> 8)) + if (w_index != 0x5 || (w_value & 0xff)) break; - interface = w_value & 0xFF; + interface = w_value >> 8; if (interface >= MAX_CONFIG_INTERFACES || !os_desc_cfg->interface[interface]) break; diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 4dcf29577f8f11e532992a378def6d70f5ad417f..b94aec6227c51d2f60574baec828f2a70001b5f5 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -1376,6 +1376,9 @@ static int configfs_composite_bind(struct usb_gadget *gadget, if (gadget_is_otg(gadget)) c->descriptors = otg_desc; + /* Properly configure the bmAttributes wakeup bit */ + check_remote_wakeup_config(gadget, c); + cfg = container_of(c, struct config_usb_cfg, c); if (!list_empty(&cfg->string_list)) { i = 0; diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 3e59055aa5040bc456a4202f68e0ddb92a01e7f0..b2da74bb107afee10c2a64929647fa5b6fe7e0b0 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3414,7 +3414,7 @@ static int ffs_func_setup(struct usb_function *f, __ffs_event_add(ffs, FUNCTIONFS_SETUP); spin_unlock_irqrestore(&ffs->ev.waitq.lock, flags); - return creq->wLength == 0 ? USB_GADGET_DELAYED_STATUS : 0; + return ffs->ev.setup.wLength == 0 ? USB_GADGET_DELAYED_STATUS : 0; } static bool ffs_func_req_match(struct usb_function *f, diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index 7b9a4cf9b100c6caf64f33ebb9ee58668746ed12..d35f30a9cae2cbd8bc8c000bae2088b35f68f44b 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -544,21 +544,37 @@ static int start_transfer(struct fsg_dev *fsg, struct usb_ep *ep, static bool start_in_transfer(struct fsg_common *common, struct fsg_buffhd *bh) { + int rc; + if (!fsg_is_set(common)) return false; bh->state = BUF_STATE_SENDING; - if (start_transfer(common->fsg, common->fsg->bulk_in, bh->inreq)) + rc = start_transfer(common->fsg, common->fsg->bulk_in, bh->inreq); + if (rc) { bh->state = BUF_STATE_EMPTY; + if (rc == -ESHUTDOWN) { + common->running = 0; + return false; + } + } return true; } static bool start_out_transfer(struct fsg_common *common, struct fsg_buffhd *bh) { + int rc; + if (!fsg_is_set(common)) return false; bh->state = BUF_STATE_RECEIVING; - if (start_transfer(common->fsg, common->fsg->bulk_out, bh->outreq)) + rc = start_transfer(common->fsg, common->fsg->bulk_out, bh->outreq); + if (rc) { bh->state = BUF_STATE_FULL; + if (rc == -ESHUTDOWN) { + common->running = 0; + return false; + } + } return true; } diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index bbb6ff6b11aa122f48a030bdb8101de87ad23c2c..b267ed9dc6d99be4d38846f84594a15f982792a2 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -884,7 +884,7 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt) if (alt > 1) goto fail; - if (ncm->port.in_ep->enabled) { + if (ncm->netdev) { DBG(cdev, "reset ncm\n"); ncm->netdev = NULL; gether_disconnect(&ncm->port); @@ -1340,7 +1340,15 @@ parse_ntb: "Parsed NTB with %d frames\n", dgram_counter); to_process -= block_len; - if (to_process != 0) { + + /* + * Windows NCM driver avoids USB ZLPs by adding a 1-byte + * zero pad as needed. + */ + if (to_process == 1 && + (*(unsigned char *)(ntb_ptr + block_len) == 0x00)) { + to_process--; + } else if ((to_process > 0) && (block_len != 0)) { ntb_ptr = (unsigned char *)(ntb_ptr + block_len); goto parse_ntb; } @@ -1361,7 +1369,7 @@ static void ncm_disable(struct usb_function *f) DBG(cdev, "ncm deactivated\n"); - if (ncm->port.in_ep->enabled) { + if (ncm->netdev) { ncm->netdev = NULL; gether_disconnect(&ncm->port); } diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c index e81865978299ccea3fdd652b0160c892cf99f617..be48d5ab17c7b5860d575214636cb24f82ef9fe8 100644 --- a/drivers/usb/gadget/function/uvc_video.c +++ b/drivers/usb/gadget/function/uvc_video.c @@ -35,6 +35,9 @@ uvc_video_encode_header(struct uvc_video *video, struct uvc_buffer *buf, data[1] = UVC_STREAM_EOH | video->fid; + if (video->queue.flags & UVC_QUEUE_DROP_INCOMPLETE) + data[1] |= UVC_STREAM_ERR; + if (video->queue.buf_used == 0 && ts.tv_sec) { /* dwClockFrequency is 48 MHz */ u32 pts = ((u64)ts.tv_sec * USEC_PER_SEC + ts.tv_nsec / NSEC_PER_USEC) * 48; diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index c40f2ecbe1b8c0a160a954d23847529c90d95eb7..82a10774a7ebc52fc2ed81072735680e89b99e13 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -292,7 +292,9 @@ int usb_ep_queue(struct usb_ep *ep, { int ret = 0; - if (WARN_ON_ONCE(!ep->enabled && ep->address)) { + if (!ep->enabled && ep->address) { + pr_debug("USB gadget: queue request to disabled ep 0x%x (%s)\n", + ep->address, ep->name); ret = -ESHUTDOWN; goto out; } @@ -525,6 +527,33 @@ out: } EXPORT_SYMBOL_GPL(usb_gadget_wakeup); +/** + * usb_gadget_set_remote_wakeup - configures the device remote wakeup feature. + * @gadget:the device being configured for remote wakeup + * @set:value to be configured. + * + * set to one to enable remote wakeup feature and zero to disable it. + * + * returns zero on success, else negative errno. + */ +int usb_gadget_set_remote_wakeup(struct usb_gadget *gadget, int set) +{ + int ret = 0; + + if (!gadget->ops->set_remote_wakeup) { + ret = -EOPNOTSUPP; + goto out; + } + + ret = gadget->ops->set_remote_wakeup(gadget, set); + +out: + trace_usb_gadget_set_remote_wakeup(gadget, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_gadget_set_remote_wakeup); + /** * usb_gadget_set_selfpowered - sets the device selfpowered feature. * @gadget:the device being declared as self-powered diff --git a/drivers/usb/gadget/udc/net2272.c b/drivers/usb/gadget/udc/net2272.c index 538c1b9a2883546fa15ac03cf0ab241b33c22f74..c42d5aa99e81a97db7a48d80fec12b98be3c5b5b 100644 --- a/drivers/usb/gadget/udc/net2272.c +++ b/drivers/usb/gadget/udc/net2272.c @@ -2650,7 +2650,7 @@ net2272_plat_probe(struct platform_device *pdev) goto err_req; } - ret = net2272_probe_fin(dev, IRQF_TRIGGER_LOW); + ret = net2272_probe_fin(dev, irqflags); if (ret) goto err_io; diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c index a8cadc45c65aa0836909a4b8a5f100c6da0db02d..fd7a9535973ed1a13c104c3dd346df970b02c073 100644 --- a/drivers/usb/gadget/udc/tegra-xudc.c +++ b/drivers/usb/gadget/udc/tegra-xudc.c @@ -3486,8 +3486,8 @@ static void tegra_xudc_device_params_init(struct tegra_xudc *xudc) static int tegra_xudc_phy_get(struct tegra_xudc *xudc) { - int err = 0, usb3; - unsigned int i; + int err = 0, usb3_companion_port; + unsigned int i, j; xudc->utmi_phy = devm_kcalloc(xudc->dev, xudc->soc->num_phys, sizeof(*xudc->utmi_phy), GFP_KERNEL); @@ -3515,7 +3515,7 @@ static int tegra_xudc_phy_get(struct tegra_xudc *xudc) if (IS_ERR(xudc->utmi_phy[i])) { err = PTR_ERR(xudc->utmi_phy[i]); dev_err_probe(xudc->dev, err, - "failed to get usb2-%d PHY\n", i); + "failed to get PHY for phy-name usb2-%d\n", i); goto clean_up; } else if (xudc->utmi_phy[i]) { /* Get usb-phy, if utmi phy is available */ @@ -3534,19 +3534,30 @@ static int tegra_xudc_phy_get(struct tegra_xudc *xudc) } /* Get USB3 phy */ - usb3 = tegra_xusb_padctl_get_usb3_companion(xudc->padctl, i); - if (usb3 < 0) + usb3_companion_port = tegra_xusb_padctl_get_usb3_companion(xudc->padctl, i); + if (usb3_companion_port < 0) continue; - snprintf(phy_name, sizeof(phy_name), "usb3-%d", usb3); - xudc->usb3_phy[i] = devm_phy_optional_get(xudc->dev, phy_name); - if (IS_ERR(xudc->usb3_phy[i])) { - err = PTR_ERR(xudc->usb3_phy[i]); - dev_err_probe(xudc->dev, err, - "failed to get usb3-%d PHY\n", usb3); - goto clean_up; - } else if (xudc->usb3_phy[i]) - dev_dbg(xudc->dev, "usb3-%d PHY registered", usb3); + for (j = 0; j < xudc->soc->num_phys; j++) { + snprintf(phy_name, sizeof(phy_name), "usb3-%d", j); + xudc->usb3_phy[i] = devm_phy_optional_get(xudc->dev, phy_name); + if (IS_ERR(xudc->usb3_phy[i])) { + err = PTR_ERR(xudc->usb3_phy[i]); + dev_err_probe(xudc->dev, err, + "failed to get PHY for phy-name usb3-%d\n", j); + goto clean_up; + } else if (xudc->usb3_phy[i]) { + int usb2_port = + tegra_xusb_padctl_get_port_number(xudc->utmi_phy[i]); + int usb3_port = + tegra_xusb_padctl_get_port_number(xudc->usb3_phy[i]); + if (usb3_port == usb3_companion_port) { + dev_dbg(xudc->dev, "USB2 port %d is paired with USB3 port %d for device mode port %d\n", + usb2_port, usb3_port, i); + break; + } + } + } } return err; diff --git a/drivers/usb/gadget/udc/trace.h b/drivers/usb/gadget/udc/trace.h index abdbcb1bacb0bb01625e47e5ddc91b758b06f57b..a5ed26fbc2dad698c896e817fb8266bbaa6d29a9 100644 --- a/drivers/usb/gadget/udc/trace.h +++ b/drivers/usb/gadget/udc/trace.h @@ -91,6 +91,11 @@ DEFINE_EVENT(udc_log_gadget, usb_gadget_wakeup, TP_ARGS(g, ret) ); +DEFINE_EVENT(udc_log_gadget, usb_gadget_set_remote_wakeup, + TP_PROTO(struct usb_gadget *g, int ret), + TP_ARGS(g, ret) +); + DEFINE_EVENT(udc_log_gadget, usb_gadget_set_selfpowered, TP_PROTO(struct usb_gadget *g, int ret), TP_ARGS(g, ret) diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c index 0457dd9f6c19ab7985524ead90bc81294531e4d5..ab175e181e55cfa4403f69b8d9fb82ad39cbb42a 100644 --- a/drivers/usb/host/ohci-hcd.c +++ b/drivers/usb/host/ohci-hcd.c @@ -888,6 +888,7 @@ static irqreturn_t ohci_irq (struct usb_hcd *hcd) /* Check for an all 1's result which is a typical consequence * of dead, unclocked, or unplugged (CardBus...) devices */ +again: if (ints == ~(u32)0) { ohci->rh_state = OHCI_RH_HALTED; ohci_dbg (ohci, "device removed!\n"); @@ -982,6 +983,13 @@ static irqreturn_t ohci_irq (struct usb_hcd *hcd) } spin_unlock(&ohci->lock); + /* repeat until all enabled interrupts are handled */ + if (ohci->rh_state != OHCI_RH_HALTED) { + ints = ohci_readl(ohci, ®s->intrstatus); + if (ints && (ints & ohci_readl(ohci, ®s->intrenable))) + goto again; + } + return IRQ_HANDLED; } diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index ef08d68b9714924513a3e5b47d467f4793e18f73..2665832f9addff97c4ec520cb7f7bb66de82dac0 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -207,8 +207,7 @@ EXPORT_SYMBOL_GPL(sb800_prefetch); static void usb_amd_find_chipset_info(void) { unsigned long flags; - struct amd_chipset_info info; - info.need_pll_quirk = false; + struct amd_chipset_info info = { }; spin_lock_irqsave(&amd_lock, flags); @@ -218,7 +217,6 @@ static void usb_amd_find_chipset_info(void) spin_unlock_irqrestore(&amd_lock, flags); return; } - memset(&info, 0, sizeof(info)); spin_unlock_irqrestore(&amd_lock, flags); if (!amd_chipset_sb_type_init(&info)) { diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c index b8b90eec91078ef2aeea61f08386363a05d8d0ed..48478eb712119bcc324d5fb146159cb9b9bb5bb1 100644 --- a/drivers/usb/host/sl811-hcd.c +++ b/drivers/usb/host/sl811-hcd.c @@ -585,6 +585,7 @@ done(struct sl811 *sl811, struct sl811h_ep *ep, u8 bank) finish_request(sl811, ep, urb, urbstat); } +#ifdef QUIRK2 static inline u8 checkdone(struct sl811 *sl811) { u8 ctl; @@ -616,6 +617,7 @@ static inline u8 checkdone(struct sl811 *sl811) #endif return irqstat; } +#endif static irqreturn_t sl811h_irq(struct usb_hcd *hcd) { diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 49510181da571210dc95db387fe966c13690d3d3..667d573b32c9d952d9f0cce52acef2aeb131f065 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1796,6 +1796,8 @@ struct xhci_command *xhci_alloc_command(struct xhci_hcd *xhci, } command->status = 0; + /* set default timeout to 5000 ms */ + command->timeout_ms = XHCI_CMD_DEFAULT_TIMEOUT; INIT_LIST_HEAD(&command->cmd_list); return command; } diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index c9438dc56f5fcb01d5645055bb83770fa5cbe833..b387d39bfb81da4ac0a359791869982ee25fcdec 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -301,6 +301,9 @@ static int xhci_plat_probe(struct platform_device *pdev) if (device_property_read_bool(tmpdev, "quirk-broken-port-ped")) xhci->quirks |= XHCI_BROKEN_PORT_PED; + if (device_property_read_bool(tmpdev, "xhci-sg-trb-cache-size-quirk")) + xhci->quirks |= XHCI_SG_TRB_CACHE_SIZE_QUIRK; + device_property_read_u32(tmpdev, "imod-interval-ns", &xhci->imod_interval); } diff --git a/drivers/usb/host/xhci-plat.h b/drivers/usb/host/xhci-plat.h index 1fb149d1fbcea319d712ccc9af6857e54c9cc6f8..f3abce238207ec38f56a78db4f96ca8462af37cb 100644 --- a/drivers/usb/host/xhci-plat.h +++ b/drivers/usb/host/xhci-plat.h @@ -8,7 +8,9 @@ #ifndef _XHCI_PLAT_H #define _XHCI_PLAT_H -#include "xhci.h" /* for hcd_to_xhci() */ +struct device; +struct platform_device; +struct usb_hcd; struct xhci_plat_priv { const char *firmware_name; diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 5a1148e4327c9f87d9142bc36a8d939e92dd0f56..b95697cd711a49253b2aff8ab17ee7ff92e23892 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -341,9 +341,10 @@ void xhci_ring_cmd_db(struct xhci_hcd *xhci) readl(&xhci->dba->doorbell[0]); } -static bool xhci_mod_cmd_timer(struct xhci_hcd *xhci, unsigned long delay) +static bool xhci_mod_cmd_timer(struct xhci_hcd *xhci) { - return mod_delayed_work(system_wq, &xhci->cmd_timer, delay); + return mod_delayed_work(system_wq, &xhci->cmd_timer, + msecs_to_jiffies(xhci->current_cmd->timeout_ms)); } static struct xhci_command *xhci_next_queued_cmd(struct xhci_hcd *xhci) @@ -387,7 +388,7 @@ static void xhci_handle_stopped_cmd_ring(struct xhci_hcd *xhci, if ((xhci->cmd_ring->dequeue != xhci->cmd_ring->enqueue) && !(xhci->xhc_state & XHCI_STATE_DYING)) { xhci->current_cmd = cur_cmd; - xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT); + xhci_mod_cmd_timer(xhci); xhci_ring_cmd_db(xhci); } } @@ -1795,7 +1796,7 @@ static void handle_cmd_completion(struct xhci_hcd *xhci, if (!list_is_singular(&xhci->cmd_list)) { xhci->current_cmd = list_first_entry(&cmd->cmd_list, struct xhci_command, cmd_list); - xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT); + xhci_mod_cmd_timer(xhci); } else if (xhci->current_cmd == cmd) { xhci->current_cmd = NULL; } @@ -2396,6 +2397,9 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, /* handle completion code */ switch (trb_comp_code) { case COMP_SUCCESS: + /* Don't overwrite status if TD had an error, see xHCI 4.9.1 */ + if (td->error_mid_td) + break; if (remaining) { frame->status = short_framestatus; if (xhci->quirks & XHCI_TRUST_TX_LENGTH) @@ -2411,9 +2415,13 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, case COMP_BANDWIDTH_OVERRUN_ERROR: frame->status = -ECOMM; break; - case COMP_ISOCH_BUFFER_OVERRUN: case COMP_BABBLE_DETECTED_ERROR: + sum_trbs_for_length = true; + fallthrough; + case COMP_ISOCH_BUFFER_OVERRUN: frame->status = -EOVERFLOW; + if (ep_trb != td->last_trb) + td->error_mid_td = true; break; case COMP_INCOMPATIBLE_DEVICE_ERROR: case COMP_STALL_ERROR: @@ -2421,8 +2429,9 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, break; case COMP_USB_TRANSACTION_ERROR: frame->status = -EPROTO; + sum_trbs_for_length = true; if (ep_trb != td->last_trb) - return 0; + td->error_mid_td = true; break; case COMP_STOPPED: sum_trbs_for_length = true; @@ -2442,6 +2451,9 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, break; } + if (td->urb_length_set) + goto finish_td; + if (sum_trbs_for_length) frame->actual_length = sum_trb_lengths(xhci, ep->ring, ep_trb) + ep_trb_len - remaining; @@ -2450,6 +2462,14 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, td->urb->actual_length += frame->actual_length; +finish_td: + /* Don't give back TD yet if we encountered an error mid TD */ + if (td->error_mid_td && ep_trb != td->last_trb) { + xhci_dbg(xhci, "Error mid isoc TD, wait for final completion event\n"); + td->urb_length_set = true; + return 0; + } + return finish_td(xhci, ep, ep_ring, td, trb_comp_code); } @@ -2834,17 +2854,51 @@ static int handle_tx_event(struct xhci_hcd *xhci, } if (!ep_seg) { - if (!ep->skip || - !usb_endpoint_xfer_isoc(&td->urb->ep->desc)) { - /* Some host controllers give a spurious - * successful event after a short transfer. - * Ignore it. - */ - if ((xhci->quirks & XHCI_SPURIOUS_SUCCESS) && - ep_ring->last_td_was_short) { - ep_ring->last_td_was_short = false; - goto cleanup; + + if (ep->skip && usb_endpoint_xfer_isoc(&td->urb->ep->desc)) { + skip_isoc_td(xhci, td, ep, status); + goto cleanup; + } + + /* + * Some hosts give a spurious success event after a short + * transfer. Ignore it. + */ + if ((xhci->quirks & XHCI_SPURIOUS_SUCCESS) && + ep_ring->last_td_was_short) { + ep_ring->last_td_was_short = false; + goto cleanup; + } + + /* + * xhci 4.10.2 states isoc endpoints should continue + * processing the next TD if there was an error mid TD. + * So host like NEC don't generate an event for the last + * isoc TRB even if the IOC flag is set. + * xhci 4.9.1 states that if there are errors in mult-TRB + * TDs xHC should generate an error for that TRB, and if xHC + * proceeds to the next TD it should genete an event for + * any TRB with IOC flag on the way. Other host follow this. + * So this event might be for the next TD. + */ + if (td->error_mid_td && + !list_is_last(&td->td_list, &ep_ring->td_list)) { + struct xhci_td *td_next = list_next_entry(td, td_list); + + ep_seg = trb_in_td(xhci, td_next->start_seg, td_next->first_trb, + td_next->last_trb, ep_trb_dma, false); + if (ep_seg) { + /* give back previous TD, start handling new */ + xhci_dbg(xhci, "Missing TD completion event after mid TD error\n"); + ep_ring->dequeue = td->last_trb; + ep_ring->deq_seg = td->last_trb_seg; + inc_deq(xhci, ep_ring); + xhci_td_cleanup(xhci, td, ep_ring, td->status); + td = td_next; } + } + + if (!ep_seg) { /* HC is busted, give up! */ xhci_err(xhci, "ERROR Transfer event TRB DMA ptr not " @@ -2856,9 +2910,6 @@ static int handle_tx_event(struct xhci_hcd *xhci, ep_trb_dma, true); return -ESHUTDOWN; } - - skip_isoc_td(xhci, td, ep, status); - goto cleanup; } if (trb_comp_code == COMP_SHORT_PACKET) ep_ring->last_td_was_short = true; @@ -4381,7 +4432,7 @@ static int queue_command(struct xhci_hcd *xhci, struct xhci_command *cmd, /* if there are no other commands queued we start the timeout timer */ if (list_empty(&xhci->cmd_list)) { xhci->current_cmd = cmd; - xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT); + xhci_mod_cmd_timer(xhci); } list_add_tail(&cmd->cmd_list, &xhci->cmd_list); diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index d46ab02c788554a7479545283d3c9b9b6b3d350b..0bed4ec120270edb68fb0515f00ebe8e39ae2b37 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -1334,6 +1334,8 @@ static int xhci_map_temp_buffer(struct usb_hcd *hcd, struct urb *urb) temp = kzalloc_node(buf_len, GFP_ATOMIC, dev_to_node(hcd->self.sysdev)); + if (!temp) + return -ENOMEM; if (usb_urb_dir_out(urb)) sg_pcopy_to_buffer(urb->sg, urb->num_sgs, @@ -4271,12 +4273,18 @@ disable_slot: return 0; } -/* - * Issue an Address Device command and optionally send a corresponding - * SetAddress request to the device. +/** + * xhci_setup_device - issues an Address Device command to assign a unique + * USB bus address. + * @hcd: USB host controller data structure. + * @udev: USB dev structure representing the connected device. + * @setup: Enum specifying setup mode: address only or with context. + * @timeout_ms: Max wait time (ms) for the command operation to complete. + * + * Return: 0 if successful; otherwise, negative error code. */ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev, - enum xhci_setup_dev setup) + enum xhci_setup_dev setup, unsigned int timeout_ms) { const char *act = setup == SETUP_CONTEXT_ONLY ? "context" : "address"; unsigned long flags; @@ -4333,6 +4341,7 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev, } command->in_ctx = virt_dev->in_ctx; + command->timeout_ms = timeout_ms; slot_ctx = xhci_get_slot_ctx(xhci, virt_dev->in_ctx); ctrl_ctx = xhci_get_input_control_ctx(virt_dev->in_ctx); @@ -4459,14 +4468,16 @@ out: return ret; } -static int xhci_address_device(struct usb_hcd *hcd, struct usb_device *udev) +static int xhci_address_device(struct usb_hcd *hcd, struct usb_device *udev, + unsigned int timeout_ms) { - return xhci_setup_device(hcd, udev, SETUP_CONTEXT_ADDRESS); + return xhci_setup_device(hcd, udev, SETUP_CONTEXT_ADDRESS, timeout_ms); } static int xhci_enable_device(struct usb_hcd *hcd, struct usb_device *udev) { - return xhci_setup_device(hcd, udev, SETUP_CONTEXT_ONLY); + return xhci_setup_device(hcd, udev, SETUP_CONTEXT_ONLY, + XHCI_CMD_DEFAULT_TIMEOUT); } /* diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 1d45643f7edd950a1f12ee110b7d86c007847058..a908246582498a0fce195016c19317c5d6cb5a78 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -815,6 +815,8 @@ struct xhci_command { struct completion *completion; union xhci_trb *command_trb; struct list_head cmd_list; + /* xHCI command response timeout in milliseconds */ + unsigned int timeout_ms; }; /* drop context bitmasks */ @@ -1570,11 +1572,15 @@ struct xhci_td { struct xhci_segment *bounce_seg; /* actual_length of the URB has already been set */ bool urb_length_set; + bool error_mid_td; unsigned int num_trbs; }; -/* xHCI command default timeout value */ -#define XHCI_CMD_DEFAULT_TIMEOUT (5 * HZ) +/* + * xHCI command default timeout value in milliseconds. + * USB 3.2 spec, section 9.2.6.1 + */ +#define XHCI_CMD_DEFAULT_TIMEOUT 5000 /* command descriptor */ struct xhci_cd { diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c index 32e6d19f7011a3cdc69d3679297c33eadf7ba52e..a327f8bc570439a1953019ea31a53b10b2d4a232 100644 --- a/drivers/usb/roles/class.c +++ b/drivers/usb/roles/class.c @@ -19,7 +19,9 @@ static struct class *role_class; struct usb_role_switch { struct device dev; struct mutex lock; /* device lock*/ + struct module *module; /* the module this device depends on */ enum usb_role role; + bool registered; /* From descriptor */ struct device *usb2_port; @@ -46,6 +48,9 @@ int usb_role_switch_set_role(struct usb_role_switch *sw, enum usb_role role) if (IS_ERR_OR_NULL(sw)) return 0; + if (!sw->registered) + return -EOPNOTSUPP; + mutex_lock(&sw->lock); ret = sw->set(sw, role); @@ -71,7 +76,7 @@ enum usb_role usb_role_switch_get_role(struct usb_role_switch *sw) { enum usb_role role; - if (IS_ERR_OR_NULL(sw)) + if (IS_ERR_OR_NULL(sw) || !sw->registered) return USB_ROLE_NONE; mutex_lock(&sw->lock); @@ -133,7 +138,7 @@ struct usb_role_switch *usb_role_switch_get(struct device *dev) usb_role_switch_match); if (!IS_ERR_OR_NULL(sw)) - WARN_ON(!try_module_get(sw->dev.parent->driver->owner)); + WARN_ON(!try_module_get(sw->module)); return sw; } @@ -155,7 +160,7 @@ struct usb_role_switch *fwnode_usb_role_switch_get(struct fwnode_handle *fwnode) sw = fwnode_connection_find_match(fwnode, "usb-role-switch", NULL, usb_role_switch_match); if (!IS_ERR_OR_NULL(sw)) - WARN_ON(!try_module_get(sw->dev.parent->driver->owner)); + WARN_ON(!try_module_get(sw->module)); return sw; } @@ -170,7 +175,7 @@ EXPORT_SYMBOL_GPL(fwnode_usb_role_switch_get); void usb_role_switch_put(struct usb_role_switch *sw) { if (!IS_ERR_OR_NULL(sw)) { - module_put(sw->dev.parent->driver->owner); + module_put(sw->module); put_device(&sw->dev); } } @@ -187,15 +192,18 @@ struct usb_role_switch * usb_role_switch_find_by_fwnode(const struct fwnode_handle *fwnode) { struct device *dev; + struct usb_role_switch *sw = NULL; if (!fwnode) return NULL; dev = class_find_device_by_fwnode(role_class, fwnode); - if (dev) - WARN_ON(!try_module_get(dev->parent->driver->owner)); + if (dev) { + sw = to_role_switch(dev); + WARN_ON(!try_module_get(sw->module)); + } - return dev ? to_role_switch(dev) : NULL; + return sw; } EXPORT_SYMBOL_GPL(usb_role_switch_find_by_fwnode); @@ -337,6 +345,7 @@ usb_role_switch_register(struct device *parent, sw->set = desc->set; sw->get = desc->get; + sw->module = parent->driver->owner; sw->dev.parent = parent; sw->dev.fwnode = desc->fwnode; sw->dev.class = role_class; @@ -351,6 +360,8 @@ usb_role_switch_register(struct device *parent, return ERR_PTR(ret); } + sw->registered = true; + /* TODO: Symlinks for the host port and the device controller. */ return sw; @@ -365,8 +376,10 @@ EXPORT_SYMBOL_GPL(usb_role_switch_register); */ void usb_role_switch_unregister(struct usb_role_switch *sw) { - if (!IS_ERR_OR_NULL(sw)) + if (!IS_ERR_OR_NULL(sw)) { + sw->registered = false; device_unregister(&sw->dev); + } } EXPORT_SYMBOL_GPL(usb_role_switch_unregister); diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index f1d7a5a863aa4dc8d1b7a9b892baf2250c6f67af..aa30288c8a8e0720fa9f78cea2eb9f5362fcf29e 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -56,6 +56,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x0471, 0x066A) }, /* AKTAKOM ACE-1001 cable */ { USB_DEVICE(0x0489, 0xE000) }, /* Pirelli Broadband S.p.A, DP-L10 SIP/GSM Mobile */ { USB_DEVICE(0x0489, 0xE003) }, /* Pirelli Broadband S.p.A, DP-L10 SIP/GSM Mobile */ + { USB_DEVICE(0x04BF, 0x1301) }, /* TDK Corporation NC0110013M - Network Controller */ + { USB_DEVICE(0x04BF, 0x1303) }, /* TDK Corporation MM0110113M - i3 Micro Module */ { USB_DEVICE(0x0745, 0x1000) }, /* CipherLab USB CCD Barcode Scanner 1000 */ { USB_DEVICE(0x0846, 0x1100) }, /* NetGear Managed Switch M4100 series, M5300 series, M7100 series */ { USB_DEVICE(0x08e6, 0x5501) }, /* Gemalto Prox-PU/CU contactless smartcard reader */ @@ -144,8 +146,10 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x85EA) }, /* AC-Services IBUS-IF */ { USB_DEVICE(0x10C4, 0x85EB) }, /* AC-Services CIS-IBUS */ { USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */ + { USB_DEVICE(0x10C4, 0x863C) }, /* MGP Instruments PDS100 */ { USB_DEVICE(0x10C4, 0x8664) }, /* AC-Services CAN-IF */ { USB_DEVICE(0x10C4, 0x8665) }, /* AC-Services OBD-IF */ + { USB_DEVICE(0x10C4, 0x87ED) }, /* IMST USB-Stick for Smart Meter */ { USB_DEVICE(0x10C4, 0x8856) }, /* CEL EM357 ZigBee USB Stick - LR */ { USB_DEVICE(0x10C4, 0x8857) }, /* CEL EM357 ZigBee USB Stick */ { USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */ @@ -176,6 +180,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0xF004) }, /* Elan Digital Systems USBcount50 */ { USB_DEVICE(0x10C5, 0xEA61) }, /* Silicon Labs MobiData GPRS USB Modem */ { USB_DEVICE(0x10CE, 0xEA6A) }, /* Silicon Labs MobiData GPRS USB Modem 100EU */ + { USB_DEVICE(0x11CA, 0x0212) }, /* Verifone USB to Printer (UART, CP2102) */ { USB_DEVICE(0x12B8, 0xEC60) }, /* Link G4 ECU */ { USB_DEVICE(0x12B8, 0xEC62) }, /* Link G4+ ECU */ { USB_DEVICE(0x13AD, 0x9999) }, /* Baltech card reader */ diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index fe2173e37b061bf9d5d53e4e3a3be2d095a8bf90..248cbc9c48fd1fac698568ad62f9792f9dfb2128 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -1077,6 +1077,8 @@ static const struct usb_device_id id_table_combined[] = { .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { USB_DEVICE(FTDI_VID, FTDI_FALCONIA_JTAG_UNBUF_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + /* GMC devices */ + { USB_DEVICE(GMC_VID, GMC_Z216C_PID) }, { } /* Terminating entry */ }; diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 21a2b5a25fc09732800830401546626d91074ffa..5ee60ba2a73cdbeaa117a2f81ad46c20c837d8c7 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -1606,3 +1606,9 @@ #define UBLOX_VID 0x1546 #define UBLOX_C099F9P_ZED_PID 0x0502 #define UBLOX_C099F9P_ODIN_PID 0x0503 + +/* + * GMC devices + */ +#define GMC_VID 0x1cd7 +#define GMC_Z216C_PID 0x0217 /* GMC Z216C Adapter IR-USB */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 4adef925987096700198c05097ff655b3198654a..b5ee8518fcc78eb6549eb6bca44e4301eabf4844 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -255,6 +255,10 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_EM061K_LMS 0x0124 #define QUECTEL_PRODUCT_EC25 0x0125 #define QUECTEL_PRODUCT_EM060K_128 0x0128 +#define QUECTEL_PRODUCT_EM060K_129 0x0129 +#define QUECTEL_PRODUCT_EM060K_12a 0x012a +#define QUECTEL_PRODUCT_EM060K_12b 0x012b +#define QUECTEL_PRODUCT_EM060K_12c 0x012c #define QUECTEL_PRODUCT_EG91 0x0191 #define QUECTEL_PRODUCT_EG95 0x0195 #define QUECTEL_PRODUCT_BG96 0x0296 @@ -613,6 +617,11 @@ static void option_instat_callback(struct urb *urb); /* Luat Air72*U series based on UNISOC UIS8910 uses UNISOC's vendor ID */ #define LUAT_PRODUCT_AIR720U 0x4e00 +/* MeiG Smart Technology products */ +#define MEIGSMART_VENDOR_ID 0x2dee +/* MeiG Smart SLM320 based on UNISOC UIS8910 */ +#define MEIGSMART_PRODUCT_SLM320 0x4d41 + /* Device flags */ /* Highest interface number which can be used with NCTRL() and RSVD() */ @@ -1213,6 +1222,18 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_128, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_128, 0xff, 0x00, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_128, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_129, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_129, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_129, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12a, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12a, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12a, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12b, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12b, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12b, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12c, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12c, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12c, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0x00, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0xff, 0x40) }, @@ -1355,6 +1376,12 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1083, 0xff), /* Telit FE990 (ECM) */ .driver_info = NCTRL(0) | RSVD(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a0, 0xff), /* Telit FN20C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a4, 0xff), /* Telit FN20C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a9, 0xff), /* Telit FN20C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), @@ -2047,6 +2074,10 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(LONGCHEER_VENDOR_ID, 0x9803, 0xff), .driver_info = RSVD(4) }, + { USB_DEVICE(LONGCHEER_VENDOR_ID, 0x9b05), /* Longsung U8300 */ + .driver_info = RSVD(4) | RSVD(5) }, + { USB_DEVICE(LONGCHEER_VENDOR_ID, 0x9b3c), /* Longsung U9300 */ + .driver_info = RSVD(0) | RSVD(4) }, { USB_DEVICE(LONGCHEER_VENDOR_ID, ZOOM_PRODUCT_4597) }, { USB_DEVICE(LONGCHEER_VENDOR_ID, IBALL_3_5G_CONNECT) }, { USB_DEVICE(HAIER_VENDOR_ID, HAIER_PRODUCT_CE100) }, @@ -2267,20 +2298,36 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0xff, 0x30) }, /* Fibocom FG150 Diag */ { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0, 0) }, /* Fibocom FG150 AT */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0111, 0xff) }, /* Fibocom FM160 (MBIM mode) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0115, 0xff), /* Fibocom FM135 (laptop MBIM) */ + .driver_info = RSVD(5) }, { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) }, /* Fibocom NL668-AM/NL652-EU (laptop MBIM) */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a2, 0xff) }, /* Fibocom FM101-GL (laptop MBIM) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a3, 0xff) }, /* Fibocom FM101-GL (laptop MBIM) */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a4, 0xff), /* Fibocom FM101-GL (laptop MBIM) */ .driver_info = RSVD(4) }, + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a04, 0xff) }, /* Fibocom FM650-CN (ECM mode) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a05, 0xff) }, /* Fibocom FM650-CN (NCM mode) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a06, 0xff) }, /* Fibocom FM650-CN (RNDIS mode) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a07, 0xff) }, /* Fibocom FM650-CN (MBIM mode) */ { USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) }, /* LongSung M5710 */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) }, /* GosunCn GM500 RNDIS */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) }, /* GosunCn GM500 MBIM */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1406, 0xff) }, /* GosunCn GM500 ECM/NCM */ + { USB_DEVICE(0x33f8, 0x0104), /* Rolling RW101-GL (laptop RMNET) */ + .driver_info = RSVD(4) | RSVD(5) }, + { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x01a2, 0xff) }, /* Rolling RW101-GL (laptop MBIM) */ + { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x01a3, 0xff) }, /* Rolling RW101-GL (laptop MBIM) */ + { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x01a4, 0xff), /* Rolling RW101-GL (laptop MBIM) */ + .driver_info = RSVD(4) }, + { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x0115, 0xff), /* Rolling RW135-GL (laptop MBIM) */ + .driver_info = RSVD(5) }, { USB_DEVICE_AND_INTERFACE_INFO(OPPO_VENDOR_ID, OPPO_PRODUCT_R11, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SLM320, 0xff, 0, 0) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index b1e844bf31f81f7984a976bf4ca5dcd8f01b3a97..703a9c56355731c158801f89996937f7ea760d35 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -184,6 +184,8 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x413c, 0x81d0)}, /* Dell Wireless 5819 */ {DEVICE_SWI(0x413c, 0x81d1)}, /* Dell Wireless 5818 */ {DEVICE_SWI(0x413c, 0x81d2)}, /* Dell Wireless 5818 */ + {DEVICE_SWI(0x413c, 0x8217)}, /* Dell Wireless DW5826e */ + {DEVICE_SWI(0x413c, 0x8218)}, /* Dell Wireless DW5826e QDL */ /* Huawei devices */ {DEVICE_HWI(0x03f0, 0x581d)}, /* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */ diff --git a/drivers/usb/storage/isd200.c b/drivers/usb/storage/isd200.c index 4e0eef1440b7fd7407cf2158adad796b516aeda5..300aeef160e75c9d84fbd4b69b3c3ad35a774f5b 100644 --- a/drivers/usb/storage/isd200.c +++ b/drivers/usb/storage/isd200.c @@ -1105,7 +1105,7 @@ static void isd200_dump_driveid(struct us_data *us, u16 *id) static int isd200_get_inquiry_data( struct us_data *us ) { struct isd200_info *info = (struct isd200_info *)us->extra; - int retStatus = ISD200_GOOD; + int retStatus; u16 *id = info->id; usb_stor_dbg(us, "Entering isd200_get_inquiry_data\n"); @@ -1137,6 +1137,13 @@ static int isd200_get_inquiry_data( struct us_data *us ) isd200_fix_driveid(id); isd200_dump_driveid(us, id); + /* Prevent division by 0 in isd200_scsi_to_ata() */ + if (id[ATA_ID_HEADS] == 0 || id[ATA_ID_SECTORS] == 0) { + usb_stor_dbg(us, " Invalid ATA Identify data\n"); + retStatus = ISD200_ERROR; + goto Done; + } + memset(&info->InquiryData, 0, sizeof(info->InquiryData)); /* Standard IDE interface only supports disks */ @@ -1202,6 +1209,7 @@ static int isd200_get_inquiry_data( struct us_data *us ) } } + Done: usb_stor_dbg(us, "Leaving isd200_get_inquiry_data %08X\n", retStatus); return(retStatus); @@ -1481,22 +1489,27 @@ static int isd200_init_info(struct us_data *us) static int isd200_Initialization(struct us_data *us) { + int rc = 0; + usb_stor_dbg(us, "ISD200 Initialization...\n"); /* Initialize ISD200 info struct */ - if (isd200_init_info(us) == ISD200_ERROR) { + if (isd200_init_info(us) < 0) { usb_stor_dbg(us, "ERROR Initializing ISD200 Info struct\n"); + rc = -ENOMEM; } else { /* Get device specific data */ - if (isd200_get_inquiry_data(us) != ISD200_GOOD) + if (isd200_get_inquiry_data(us) != ISD200_GOOD) { usb_stor_dbg(us, "ISD200 Initialization Failure\n"); - else + rc = -EINVAL; + } else { usb_stor_dbg(us, "ISD200 Initialization complete\n"); + } } - return 0; + return rc; } diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index c54e9805da536a0ec139ad789017b79131c88561..12cf9940e5b6759167f9ae7450df8af92a85c63a 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -179,6 +179,13 @@ static int slave_configure(struct scsi_device *sdev) */ sdev->use_192_bytes_for_3f = 1; + /* + * Some devices report generic values until the media has been + * accessed. Force a READ(10) prior to querying device + * characteristics. + */ + sdev->read_before_ms = 1; + /* * Some devices don't like MODE SENSE with page=0x3f, * which is the command used for checking if a device diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index de3836412bf32ecc97b12971ae3b7303fbb01fd3..af619efe8eabf3fc7ab7b2ae2ae078d866173dfc 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -533,7 +533,7 @@ static struct urb *uas_alloc_cmd_urb(struct uas_dev_info *devinfo, gfp_t gfp, * daft to me. */ -static struct urb *uas_submit_sense_urb(struct scsi_cmnd *cmnd, gfp_t gfp) +static int uas_submit_sense_urb(struct scsi_cmnd *cmnd, gfp_t gfp) { struct uas_dev_info *devinfo = cmnd->device->hostdata; struct urb *urb; @@ -541,30 +541,28 @@ static struct urb *uas_submit_sense_urb(struct scsi_cmnd *cmnd, gfp_t gfp) urb = uas_alloc_sense_urb(devinfo, gfp, cmnd); if (!urb) - return NULL; + return -ENOMEM; usb_anchor_urb(urb, &devinfo->sense_urbs); err = usb_submit_urb(urb, gfp); if (err) { usb_unanchor_urb(urb); uas_log_cmd_state(cmnd, "sense submit err", err); usb_free_urb(urb); - return NULL; } - return urb; + return err; } static int uas_submit_urbs(struct scsi_cmnd *cmnd, struct uas_dev_info *devinfo) { struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); - struct urb *urb; int err; lockdep_assert_held(&devinfo->lock); if (cmdinfo->state & SUBMIT_STATUS_URB) { - urb = uas_submit_sense_urb(cmnd, GFP_ATOMIC); - if (!urb) - return SCSI_MLQUEUE_DEVICE_BUSY; + err = uas_submit_sense_urb(cmnd, GFP_ATOMIC); + if (err) + return err; cmdinfo->state &= ~SUBMIT_STATUS_URB; } @@ -572,7 +570,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd, cmdinfo->data_in_urb = uas_alloc_data_urb(devinfo, GFP_ATOMIC, cmnd, DMA_FROM_DEVICE); if (!cmdinfo->data_in_urb) - return SCSI_MLQUEUE_DEVICE_BUSY; + return -ENOMEM; cmdinfo->state &= ~ALLOC_DATA_IN_URB; } @@ -582,7 +580,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd, if (err) { usb_unanchor_urb(cmdinfo->data_in_urb); uas_log_cmd_state(cmnd, "data in submit err", err); - return SCSI_MLQUEUE_DEVICE_BUSY; + return err; } cmdinfo->state &= ~SUBMIT_DATA_IN_URB; cmdinfo->state |= DATA_IN_URB_INFLIGHT; @@ -592,7 +590,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd, cmdinfo->data_out_urb = uas_alloc_data_urb(devinfo, GFP_ATOMIC, cmnd, DMA_TO_DEVICE); if (!cmdinfo->data_out_urb) - return SCSI_MLQUEUE_DEVICE_BUSY; + return -ENOMEM; cmdinfo->state &= ~ALLOC_DATA_OUT_URB; } @@ -602,7 +600,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd, if (err) { usb_unanchor_urb(cmdinfo->data_out_urb); uas_log_cmd_state(cmnd, "data out submit err", err); - return SCSI_MLQUEUE_DEVICE_BUSY; + return err; } cmdinfo->state &= ~SUBMIT_DATA_OUT_URB; cmdinfo->state |= DATA_OUT_URB_INFLIGHT; @@ -611,7 +609,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd, if (cmdinfo->state & ALLOC_CMD_URB) { cmdinfo->cmd_urb = uas_alloc_cmd_urb(devinfo, GFP_ATOMIC, cmnd); if (!cmdinfo->cmd_urb) - return SCSI_MLQUEUE_DEVICE_BUSY; + return -ENOMEM; cmdinfo->state &= ~ALLOC_CMD_URB; } @@ -621,7 +619,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd, if (err) { usb_unanchor_urb(cmdinfo->cmd_urb); uas_log_cmd_state(cmnd, "cmd submit err", err); - return SCSI_MLQUEUE_DEVICE_BUSY; + return err; } cmdinfo->cmd_urb = NULL; cmdinfo->state &= ~SUBMIT_CMD_URB; @@ -698,7 +696,7 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd) * of queueing, no matter how fatal the error */ if (err == -ENODEV) { - set_host_byte(cmnd, DID_ERROR); + set_host_byte(cmnd, DID_NO_CONNECT); scsi_done(cmnd); goto zombie; } @@ -878,6 +876,13 @@ static int uas_slave_configure(struct scsi_device *sdev) if (devinfo->flags & US_FL_CAPACITY_HEURISTICS) sdev->guess_capacity = 1; + /* + * Some devices report generic values until the media has been + * accessed. Force a READ(10) prior to querying device + * characteristics. + */ + sdev->read_before_ms = 1; + /* * Some devices don't like MODE SENSE with page=0x3f, * which is the command used for checking if a device diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index 3da404d5178d34032915809bd1f5b3756f266f8c..ce83f558fe44741d22323d1141b9cd7910e49ca2 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -1245,6 +1245,7 @@ static ssize_t select_usb_power_delivery_store(struct device *dev, { struct typec_port *port = to_typec_port(dev); struct usb_power_delivery *pd; + int ret; if (!port->ops || !port->ops->pd_set) return -EOPNOTSUPP; @@ -1253,7 +1254,11 @@ static ssize_t select_usb_power_delivery_store(struct device *dev, if (!pd) return -EINVAL; - return port->ops->pd_set(port, pd); + ret = port->ops->pd_set(port, pd); + if (ret) + return ret; + + return size; } static ssize_t select_usb_power_delivery_show(struct device *dev, diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index 816945913ed0d3b0d1ba3f4ae9ad335d84e9facf..f649769912e53b8442cdc190e3209011b0f48bb6 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -875,6 +875,7 @@ MODULE_DEVICE_TABLE(i2c, tcpci_id); #ifdef CONFIG_OF static const struct of_device_id tcpci_of_match[] = { { .compatible = "nxp,ptn5110", }, + { .compatible = "tcpci", }, {}, }; MODULE_DEVICE_TABLE(of, tcpci_of_match); diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index bf615dc8085e93d838a76d8527227744b9d4297e..bbcc0e0aa070a88c2ecef395efae1326199e3670 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -1479,7 +1479,8 @@ static void svdm_consume_identity(struct tcpm_port *port, const u32 *p, int cnt) port->partner_ident.cert_stat = p[VDO_INDEX_CSTAT]; port->partner_ident.product = product; - typec_partner_set_identity(port->partner); + if (port->partner) + typec_partner_set_identity(port->partner); tcpm_log(port, "Identity: %04x:%04x.%04x", PD_IDH_VID(vdo), @@ -1567,6 +1568,9 @@ static void tcpm_register_partner_altmodes(struct tcpm_port *port) struct typec_altmode *altmode; int i; + if (!port->partner) + return; + for (i = 0; i < modep->altmodes; i++) { altmode = typec_partner_register_altmode(port->partner, &modep->altmode_desc[i]); @@ -2416,7 +2420,7 @@ static int tcpm_register_sink_caps(struct tcpm_port *port) { struct usb_power_delivery_desc desc = { port->negotiated_rev }; struct usb_power_delivery_capabilities_desc caps = { }; - struct usb_power_delivery_capabilities *cap; + struct usb_power_delivery_capabilities *cap = port->partner_source_caps; if (!port->partner_pd) port->partner_pd = usb_power_delivery_register(NULL, &desc); @@ -2426,6 +2430,9 @@ static int tcpm_register_sink_caps(struct tcpm_port *port) memcpy(caps.pdo, port->sink_caps, sizeof(u32) * port->nr_sink_caps); caps.role = TYPEC_SINK; + if (cap) + usb_power_delivery_unregister_capabilities(cap); + cap = usb_power_delivery_register_capabilities(port->partner_pd, &caps); if (IS_ERR(cap)) return PTR_ERR(cap); @@ -3635,7 +3642,10 @@ static int tcpm_init_vconn(struct tcpm_port *port) static void tcpm_typec_connect(struct tcpm_port *port) { + struct typec_partner *partner; + if (!port->connected) { + port->connected = true; /* Make sure we don't report stale identity information */ memset(&port->partner_ident, 0, sizeof(port->partner_ident)); port->partner_desc.usb_pd = port->pd_capable; @@ -3645,9 +3655,13 @@ static void tcpm_typec_connect(struct tcpm_port *port) port->partner_desc.accessory = TYPEC_ACCESSORY_AUDIO; else port->partner_desc.accessory = TYPEC_ACCESSORY_NONE; - port->partner = typec_register_partner(port->typec_port, - &port->partner_desc); - port->connected = true; + partner = typec_register_partner(port->typec_port, &port->partner_desc); + if (IS_ERR(partner)) { + dev_err(port->dev, "Failed to register partner (%ld)\n", PTR_ERR(partner)); + return; + } + + port->partner = partner; typec_partner_set_usb_power_delivery(port->partner, port->partner_pd); } } @@ -3717,9 +3731,11 @@ out_disable_mux: static void tcpm_typec_disconnect(struct tcpm_port *port) { if (port->connected) { - typec_partner_set_usb_power_delivery(port->partner, NULL); - typec_unregister_partner(port->partner); - port->partner = NULL; + if (port->partner) { + typec_partner_set_usb_power_delivery(port->partner, NULL); + typec_unregister_partner(port->partner); + port->partner = NULL; + } port->connected = false; } } @@ -3935,6 +3951,9 @@ static enum typec_cc_status tcpm_pwr_opmode_to_rp(enum typec_pwr_opmode opmode) static void tcpm_set_initial_svdm_version(struct tcpm_port *port) { + if (!port->partner) + return; + switch (port->negotiated_rev) { case PD_REV30: break; diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c index 195c9c16f817f8beccaa9f8a3dea71bdf60f73f6..e804db927d5cfa1d8b382aeda309c5246ebebfc7 100644 --- a/drivers/usb/typec/tipd/core.c +++ b/drivers/usb/typec/tipd/core.c @@ -24,6 +24,7 @@ #define TPS_REG_MODE 0x03 #define TPS_REG_CMD1 0x08 #define TPS_REG_DATA1 0x09 +#define TPS_REG_VERSION 0x0F #define TPS_REG_INT_EVENT1 0x14 #define TPS_REG_INT_EVENT2 0x15 #define TPS_REG_INT_MASK1 0x16 @@ -518,49 +519,67 @@ err_unlock: static irqreturn_t tps6598x_interrupt(int irq, void *data) { + int intev_len = TPS_65981_2_6_INTEVENT_LEN; struct tps6598x *tps = data; - u64 event1 = 0; - u64 event2 = 0; + u64 event1[2] = { }; + u64 event2[2] = { }; + u32 version; u32 status; int ret; mutex_lock(&tps->lock); - ret = tps6598x_read64(tps, TPS_REG_INT_EVENT1, &event1); - ret |= tps6598x_read64(tps, TPS_REG_INT_EVENT2, &event2); + ret = tps6598x_read32(tps, TPS_REG_VERSION, &version); + if (ret) + dev_warn(tps->dev, "%s: failed to read version (%d)\n", + __func__, ret); + + if (TPS_VERSION_HW_VERSION(version) == TPS_VERSION_HW_65987_8_DH || + TPS_VERSION_HW_VERSION(version) == TPS_VERSION_HW_65987_8_DK) + intev_len = TPS_65987_8_INTEVENT_LEN; + + ret = tps6598x_block_read(tps, TPS_REG_INT_EVENT1, event1, intev_len); + + ret = tps6598x_block_read(tps, TPS_REG_INT_EVENT1, event1, intev_len); if (ret) { - dev_err(tps->dev, "%s: failed to read events\n", __func__); + dev_err(tps->dev, "%s: failed to read event1\n", __func__); goto err_unlock; } - trace_tps6598x_irq(event1, event2); + ret = tps6598x_block_read(tps, TPS_REG_INT_EVENT2, event2, intev_len); + if (ret) { + dev_err(tps->dev, "%s: failed to read event2\n", __func__); + goto err_unlock; + } + trace_tps6598x_irq(event1[0], event2[0]); - if (!(event1 | event2)) + if (!(event1[0] | event1[1] | event2[0] | event2[1])) goto err_unlock; if (!tps6598x_read_status(tps, &status)) goto err_clear_ints; - if ((event1 | event2) & TPS_REG_INT_POWER_STATUS_UPDATE) + if ((event1[0] | event2[0]) & TPS_REG_INT_POWER_STATUS_UPDATE) if (!tps6598x_read_power_status(tps)) goto err_clear_ints; - if ((event1 | event2) & TPS_REG_INT_DATA_STATUS_UPDATE) + if ((event1[0] | event2[0]) & TPS_REG_INT_DATA_STATUS_UPDATE) if (!tps6598x_read_data_status(tps)) goto err_clear_ints; /* Handle plug insert or removal */ - if ((event1 | event2) & TPS_REG_INT_PLUG_EVENT) + if ((event1[0] | event2[0]) & TPS_REG_INT_PLUG_EVENT) tps6598x_handle_plug_event(tps, status); err_clear_ints: - tps6598x_write64(tps, TPS_REG_INT_CLEAR1, event1); - tps6598x_write64(tps, TPS_REG_INT_CLEAR2, event2); + tps6598x_block_write(tps, TPS_REG_INT_CLEAR1, event1, intev_len); + tps6598x_block_write(tps, TPS_REG_INT_CLEAR2, event2, intev_len); err_unlock: mutex_unlock(&tps->lock); - if (event1 | event2) + if (event1[0] | event1[1] | event2[0] | event2[1]) return IRQ_HANDLED; + return IRQ_NONE; } diff --git a/drivers/usb/typec/tipd/tps6598x.h b/drivers/usb/typec/tipd/tps6598x.h index 527857549d699ea6cbd426beab91c71961729b96..1fc3cc8ad199a908ffd8ce1c3d711f6f76b37fb0 100644 --- a/drivers/usb/typec/tipd/tps6598x.h +++ b/drivers/usb/typec/tipd/tps6598x.h @@ -199,4 +199,15 @@ #define TPS_DATA_STATUS_DP_SPEC_PIN_ASSIGNMENT_A BIT(2) #define TPS_DATA_STATUS_DP_SPEC_PIN_ASSIGNMENT_B (BIT(2) | BIT(1)) +/* Version Register */ +#define TPS_VERSION_HW_VERSION_MASK GENMASK(31, 24) +#define TPS_VERSION_HW_VERSION(x) TPS_FIELD_GET(TPS_VERSION_HW_VERSION_MASK, (x)) +#define TPS_VERSION_HW_65981_2_6 0x00 +#define TPS_VERSION_HW_65987_8_DH 0xF7 +#define TPS_VERSION_HW_65987_8_DK 0xF9 + +/* Int Event Register length */ +#define TPS_65981_2_6_INTEVENT_LEN 8 +#define TPS_65987_8_INTEVENT_LEN 11 + #endif /* __TPS6598X_H__ */ diff --git a/drivers/usb/typec/ucsi/displayport.c b/drivers/usb/typec/ucsi/displayport.c index 73cd5bf350472fcb88756a4faa94c0757edab1fe..2431febc461516a9002cc9749a349310eac10f98 100644 --- a/drivers/usb/typec/ucsi/displayport.c +++ b/drivers/usb/typec/ucsi/displayport.c @@ -275,8 +275,6 @@ static void ucsi_displayport_work(struct work_struct *work) struct ucsi_dp *dp = container_of(work, struct ucsi_dp, work); int ret; - mutex_lock(&dp->con->lock); - ret = typec_altmode_vdm(dp->alt, dp->header, dp->vdo_data, dp->vdo_size); if (ret) @@ -285,8 +283,6 @@ static void ucsi_displayport_work(struct work_struct *work) dp->vdo_data = NULL; dp->vdo_size = 0; dp->header = 0; - - mutex_unlock(&dp->con->lock); } void ucsi_displayport_remove_partner(struct typec_altmode *alt) diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index dc2dea3768fb6d508146b87d6263b2ad3f593e10..a163218fdc74955ea77b051665ce0029d4ba6c53 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -138,8 +138,12 @@ static int ucsi_exec_command(struct ucsi *ucsi, u64 cmd) if (!(cci & UCSI_CCI_COMMAND_COMPLETE)) return -EIO; - if (cci & UCSI_CCI_NOT_SUPPORTED) + if (cci & UCSI_CCI_NOT_SUPPORTED) { + if (ucsi_acknowledge_command(ucsi) < 0) + dev_err(ucsi->dev, + "ACK of unsupported command failed\n"); return -EOPNOTSUPP; + } if (cci & UCSI_CCI_ERROR) { if (cmd == UCSI_GET_ERROR_STATUS) @@ -829,9 +833,11 @@ static void ucsi_handle_connector_change(struct work_struct *work) if (con->status.change & UCSI_CONSTAT_CAM_CHANGE) ucsi_partner_task(con, ucsi_check_altmodes, 1, 0); + mutex_lock(&ucsi->ppm_lock); clear_bit(EVENT_PENDING, &con->ucsi->flags); - ret = ucsi_acknowledge_connector_change(ucsi); + mutex_unlock(&ucsi->ppm_lock); + if (ret) dev_err(ucsi->dev, "%s: ACK failed (%d)", __func__, ret); @@ -849,7 +855,7 @@ void ucsi_connector_change(struct ucsi *ucsi, u8 num) struct ucsi_connector *con = &ucsi->connector[num - 1]; if (!(ucsi->ntfy & UCSI_ENABLE_NTFY_CONNECTOR_CHANGE)) { - dev_dbg(ucsi->dev, "Bogus connector change event\n"); + dev_dbg(ucsi->dev, "Early connector change event\n"); return; } @@ -872,13 +878,47 @@ static int ucsi_reset_connector(struct ucsi_connector *con, bool hard) static int ucsi_reset_ppm(struct ucsi *ucsi) { - u64 command = UCSI_PPM_RESET; + u64 command; unsigned long tmo; u32 cci; int ret; mutex_lock(&ucsi->ppm_lock); + ret = ucsi->ops->read(ucsi, UCSI_CCI, &cci, sizeof(cci)); + if (ret < 0) + goto out; + + /* + * If UCSI_CCI_RESET_COMPLETE is already set we must clear + * the flag before we start another reset. Send a + * UCSI_SET_NOTIFICATION_ENABLE command to achieve this. + * Ignore a timeout and try the reset anyway if this fails. + */ + if (cci & UCSI_CCI_RESET_COMPLETE) { + command = UCSI_SET_NOTIFICATION_ENABLE; + ret = ucsi->ops->async_write(ucsi, UCSI_CONTROL, &command, + sizeof(command)); + if (ret < 0) + goto out; + + tmo = jiffies + msecs_to_jiffies(UCSI_TIMEOUT_MS); + do { + ret = ucsi->ops->read(ucsi, UCSI_CCI, + &cci, sizeof(cci)); + if (ret < 0) + goto out; + if (cci & UCSI_CCI_COMMAND_COMPLETE) + break; + if (time_is_before_jiffies(tmo)) + break; + msleep(20); + } while (1); + + WARN_ON(cci & UCSI_CCI_RESET_COMPLETE); + } + + command = UCSI_PPM_RESET; ret = ucsi->ops->async_write(ucsi, UCSI_CONTROL, &command, sizeof(command)); if (ret < 0) @@ -1208,6 +1248,7 @@ static int ucsi_init(struct ucsi *ucsi) { struct ucsi_connector *con, *connector; u64 command, ntfy; + u32 cci; int ret; int i; @@ -1260,6 +1301,15 @@ static int ucsi_init(struct ucsi *ucsi) ucsi->connector = connector; ucsi->ntfy = ntfy; + + mutex_lock(&ucsi->ppm_lock); + ret = ucsi->ops->read(ucsi, UCSI_CCI, &cci, sizeof(cci)); + mutex_unlock(&ucsi->ppm_lock); + if (ret) + return ret; + if (UCSI_CCI_CONNECTOR(cci)) + ucsi_connector_change(ucsi, UCSI_CCI_CONNECTOR(cci)); + return 0; err_unregister: diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h index 60ce9fb6e7450f5c29168393e31ef78fe23c875e..dbb10cb310d4c1c5b6b34749d1ee8ab93ebcb7bc 100644 --- a/drivers/usb/typec/ucsi/ucsi.h +++ b/drivers/usb/typec/ucsi/ucsi.h @@ -220,12 +220,12 @@ struct ucsi_cable_property { #define UCSI_CABLE_PROP_FLAG_VBUS_IN_CABLE BIT(0) #define UCSI_CABLE_PROP_FLAG_ACTIVE_CABLE BIT(1) #define UCSI_CABLE_PROP_FLAG_DIRECTIONALITY BIT(2) -#define UCSI_CABLE_PROP_FLAG_PLUG_TYPE(_f_) ((_f_) & GENMASK(3, 0)) +#define UCSI_CABLE_PROP_FLAG_PLUG_TYPE(_f_) (((_f_) & GENMASK(4, 3)) >> 3) #define UCSI_CABLE_PROPERTY_PLUG_TYPE_A 0 #define UCSI_CABLE_PROPERTY_PLUG_TYPE_B 1 #define UCSI_CABLE_PROPERTY_PLUG_TYPE_C 2 #define UCSI_CABLE_PROPERTY_PLUG_OTHER 3 -#define UCSI_CABLE_PROP_MODE_SUPPORT BIT(5) +#define UCSI_CABLE_PROP_FLAG_MODE_SUPPORT BIT(5) u8 latency; } __packed; diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c index 217355f1f9b94a7de899b9b2e9d9cd2f30b1ac56..b4d86d47c5db476af7b938aed4ced76908ae3b2b 100644 --- a/drivers/usb/typec/ucsi/ucsi_acpi.c +++ b/drivers/usb/typec/ucsi/ucsi_acpi.c @@ -23,6 +23,9 @@ struct ucsi_acpi { void *base; struct completion complete; unsigned long flags; +#define UCSI_ACPI_SUPPRESS_EVENT 0 +#define UCSI_ACPI_COMMAND_PENDING 1 +#define UCSI_ACPI_ACK_PENDING 2 guid_t guid; u64 cmd; }; @@ -73,9 +76,13 @@ static int ucsi_acpi_sync_write(struct ucsi *ucsi, unsigned int offset, const void *val, size_t val_len) { struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi); + bool ack = UCSI_COMMAND(*(u64 *)val) == UCSI_ACK_CC_CI; int ret; - set_bit(COMMAND_PENDING, &ua->flags); + if (ack) + set_bit(UCSI_ACPI_ACK_PENDING, &ua->flags); + else + set_bit(UCSI_ACPI_COMMAND_PENDING, &ua->flags); ret = ucsi_acpi_async_write(ucsi, offset, val, val_len); if (ret) @@ -85,7 +92,10 @@ static int ucsi_acpi_sync_write(struct ucsi *ucsi, unsigned int offset, ret = -ETIMEDOUT; out_clear_bit: - clear_bit(COMMAND_PENDING, &ua->flags); + if (ack) + clear_bit(UCSI_ACPI_ACK_PENDING, &ua->flags); + else + clear_bit(UCSI_ACPI_COMMAND_PENDING, &ua->flags); return ret; } @@ -119,12 +129,62 @@ static const struct ucsi_operations ucsi_zenbook_ops = { .async_write = ucsi_acpi_async_write }; -static const struct dmi_system_id zenbook_dmi_id[] = { +/* + * Some Dell laptops don't like ACK commands with the + * UCSI_ACK_CONNECTOR_CHANGE but not the UCSI_ACK_COMMAND_COMPLETE + * bit set. To work around this send a dummy command and bundle the + * UCSI_ACK_CONNECTOR_CHANGE with the UCSI_ACK_COMMAND_COMPLETE + * for the dummy command. + */ +static int +ucsi_dell_sync_write(struct ucsi *ucsi, unsigned int offset, + const void *val, size_t val_len) +{ + struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi); + u64 cmd = *(u64 *)val; + u64 dummycmd = UCSI_GET_CAPABILITY; + int ret; + + if (cmd == (UCSI_ACK_CC_CI | UCSI_ACK_CONNECTOR_CHANGE)) { + cmd |= UCSI_ACK_COMMAND_COMPLETE; + + /* + * The UCSI core thinks it is sending a connector change ack + * and will accept new connector change events. We don't want + * this to happen for the dummy command as its response will + * still report the very event that the core is trying to clear. + */ + set_bit(UCSI_ACPI_SUPPRESS_EVENT, &ua->flags); + ret = ucsi_acpi_sync_write(ucsi, UCSI_CONTROL, &dummycmd, + sizeof(dummycmd)); + clear_bit(UCSI_ACPI_SUPPRESS_EVENT, &ua->flags); + + if (ret < 0) + return ret; + } + + return ucsi_acpi_sync_write(ucsi, UCSI_CONTROL, &cmd, sizeof(cmd)); +} + +static const struct ucsi_operations ucsi_dell_ops = { + .read = ucsi_acpi_read, + .sync_write = ucsi_dell_sync_write, + .async_write = ucsi_acpi_async_write +}; + +static const struct dmi_system_id ucsi_acpi_quirks[] = { { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX325UA_UM325UA"), }, + .driver_data = (void *)&ucsi_zenbook_ops, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + }, + .driver_data = (void *)&ucsi_dell_ops, }, { } }; @@ -139,11 +199,14 @@ static void ucsi_acpi_notify(acpi_handle handle, u32 event, void *data) if (ret) return; - if (UCSI_CCI_CONNECTOR(cci)) + if (UCSI_CCI_CONNECTOR(cci) && + !test_bit(UCSI_ACPI_SUPPRESS_EVENT, &ua->flags)) ucsi_connector_change(ua->ucsi, UCSI_CCI_CONNECTOR(cci)); - if (test_bit(COMMAND_PENDING, &ua->flags) && - cci & (UCSI_CCI_ACK_COMPLETE | UCSI_CCI_COMMAND_COMPLETE)) + if (cci & UCSI_CCI_ACK_COMPLETE && test_bit(ACK_PENDING, &ua->flags)) + complete(&ua->complete); + if (cci & UCSI_CCI_COMMAND_COMPLETE && + test_bit(UCSI_ACPI_COMMAND_PENDING, &ua->flags)) complete(&ua->complete); } @@ -151,6 +214,7 @@ static int ucsi_acpi_probe(struct platform_device *pdev) { struct acpi_device *adev = ACPI_COMPANION(&pdev->dev); const struct ucsi_operations *ops = &ucsi_acpi_ops; + const struct dmi_system_id *id; struct ucsi_acpi *ua; struct resource *res; acpi_status status; @@ -180,8 +244,9 @@ static int ucsi_acpi_probe(struct platform_device *pdev) init_completion(&ua->complete); ua->dev = &pdev->dev; - if (dmi_check_system(zenbook_dmi_id)) - ops = &ucsi_zenbook_ops; + id = dmi_first_match(ucsi_acpi_quirks); + if (id) + ops = id->driver_data; ua->ucsi = ucsi_create(&pdev->dev, ops); if (IS_ERR(ua->ucsi)) diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 2b7e796c48897e74f606d3a6af15ba13663b45c3..74d295312466fbb37737eca8503f7a8926c5eeff 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -185,8 +185,6 @@ static void teardown_driver(struct mlx5_vdpa_net *ndev); static bool mlx5_vdpa_debug; -#define MLX5_CVQ_MAX_ENT 16 - #define MLX5_LOG_VIO_FLAG(_feature) \ do { \ if (features & BIT_ULL(_feature)) \ @@ -1980,9 +1978,16 @@ static void mlx5_vdpa_set_vq_num(struct vdpa_device *vdev, u16 idx, u32 num) struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); struct mlx5_vdpa_virtqueue *mvq; - if (!is_index_valid(mvdev, idx) || is_ctrl_vq_idx(mvdev, idx)) + if (!is_index_valid(mvdev, idx)) return; + if (is_ctrl_vq_idx(mvdev, idx)) { + struct mlx5_control_vq *cvq = &mvdev->cvq; + + cvq->vring.vring.num = num; + return; + } + mvq = &ndev->vqs[idx]; mvq->num_ent = num; } @@ -2512,7 +2517,7 @@ static int setup_cvq_vring(struct mlx5_vdpa_dev *mvdev) u16 idx = cvq->vring.last_avail_idx; err = vringh_init_iotlb(&cvq->vring, mvdev->actual_features, - MLX5_CVQ_MAX_ENT, false, + cvq->vring.vring.num, false, (struct vring_desc *)(uintptr_t)cvq->desc_addr, (struct vring_avail *)(uintptr_t)cvq->driver_addr, (struct vring_used *)(uintptr_t)cvq->device_addr); diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index 61bde476cf9c8e4ee440e2c954fd1dd5859bab7d..e7fc25bfdd2375f507e5ebbb9e9ed21b31a16b44 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -120,7 +120,7 @@ static void vdpasim_do_reset(struct vdpasim *vdpasim) for (i = 0; i < vdpasim->dev_attr.nas; i++) vhost_iotlb_reset(&vdpasim->iommu[i]); - vdpasim->running = true; + vdpasim->running = false; spin_unlock(&vdpasim->iommu_lock); vdpasim->features = 0; @@ -513,6 +513,7 @@ static void vdpasim_set_status(struct vdpa_device *vdpa, u8 status) spin_lock(&vdpasim->lock); vdpasim->status = status; + vdpasim->running = (status & VIRTIO_CONFIG_S_DRIVER_OK) != 0; spin_unlock(&vdpasim->lock); } diff --git a/drivers/vfio/container.c b/drivers/vfio/container.c index d74164abbf401d42cbcf42b6f5f7282dd7769de7..ab9d8e3481f759bdb878fecec5e577cbcb2a78cf 100644 --- a/drivers/vfio/container.c +++ b/drivers/vfio/container.c @@ -366,7 +366,7 @@ static int vfio_fops_open(struct inode *inode, struct file *filep) { struct vfio_container *container; - container = kzalloc(sizeof(*container), GFP_KERNEL); + container = kzalloc(sizeof(*container), GFP_KERNEL_ACCOUNT); if (!container) return -ENOMEM; diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c index 7b428eac3d3e5bb84df8f2269100ef5df79ebb50..b125b6edf634e59ad10a72163041160f805a36ee 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c @@ -142,13 +142,14 @@ static int vfio_fsl_mc_set_irq_trigger(struct vfio_fsl_mc_device *vdev, irq = &vdev->mc_irqs[index]; if (flags & VFIO_IRQ_SET_DATA_NONE) { - vfio_fsl_mc_irq_handler(hwirq, irq); + if (irq->trigger) + eventfd_signal(irq->trigger, 1); } else if (flags & VFIO_IRQ_SET_DATA_BOOL) { u8 trigger = *(u8 *)data; - if (trigger) - vfio_fsl_mc_irq_handler(hwirq, irq); + if (trigger && irq->trigger) + eventfd_signal(irq->trigger, 1); } return 0; diff --git a/drivers/vfio/iova_bitmap.c b/drivers/vfio/iova_bitmap.c index 0f19d502f351b27dd178121ee84acd12f2338dcd..dfab5b742191a0bc5f9315d30be0598aa2230e0c 100644 --- a/drivers/vfio/iova_bitmap.c +++ b/drivers/vfio/iova_bitmap.c @@ -99,7 +99,7 @@ struct iova_bitmap { struct iova_bitmap_map mapped; /* userspace address of the bitmap */ - u64 __user *bitmap; + u8 __user *bitmap; /* u64 index that @mapped points to */ unsigned long mapped_base_index; @@ -161,7 +161,7 @@ static int iova_bitmap_get(struct iova_bitmap *bitmap) { struct iova_bitmap_map *mapped = &bitmap->mapped; unsigned long npages; - u64 __user *addr; + u8 __user *addr; long ret; /* @@ -174,18 +174,19 @@ static int iova_bitmap_get(struct iova_bitmap *bitmap) bitmap->mapped_base_index) * sizeof(*bitmap->bitmap), PAGE_SIZE); - /* - * We always cap at max number of 'struct page' a base page can fit. - * This is, for example, on x86 means 2M of bitmap data max. - */ - npages = min(npages, PAGE_SIZE / sizeof(struct page *)); - /* * Bitmap address to be pinned is calculated via pointer arithmetic * with bitmap u64 word index. */ addr = bitmap->bitmap + bitmap->mapped_base_index; + /* + * We always cap at max number of 'struct page' a base page can fit. + * This is, for example, on x86 means 2M of bitmap data max. + */ + npages = min(npages + !!offset_in_page(addr), + PAGE_SIZE / sizeof(struct page *)); + ret = pin_user_pages_fast((unsigned long)addr, npages, FOLL_WRITE, mapped->pages); if (ret <= 0) @@ -246,7 +247,7 @@ struct iova_bitmap *iova_bitmap_alloc(unsigned long iova, size_t length, mapped = &bitmap->mapped; mapped->pgshift = __ffs(page_size); - bitmap->bitmap = data; + bitmap->bitmap = (u8 __user *)data; bitmap->mapped_total_index = iova_bitmap_offset_to_index(bitmap, length - 1) + 1; bitmap->iova = iova; @@ -301,7 +302,7 @@ static unsigned long iova_bitmap_mapped_remaining(struct iova_bitmap *bitmap) remaining = bitmap->mapped_total_index - bitmap->mapped_base_index; remaining = min_t(unsigned long, remaining, - bytes / sizeof(*bitmap->bitmap)); + DIV_ROUND_UP(bytes, sizeof(*bitmap->bitmap))); return remaining; } @@ -405,6 +406,7 @@ void iova_bitmap_set(struct iova_bitmap *bitmap, mapped->pgshift) + mapped->pgoff * BITS_PER_BYTE; unsigned long last_bit = (((iova + length - 1) - mapped->iova) >> mapped->pgshift) + mapped->pgoff * BITS_PER_BYTE; + unsigned long last_page_idx = mapped->npages - 1; do { unsigned int page_idx = cur_bit / BITS_PER_PAGE; @@ -413,6 +415,9 @@ void iova_bitmap_set(struct iova_bitmap *bitmap, last_bit - cur_bit + 1); void *kaddr; + if (unlikely(page_idx > last_page_idx)) + break; + kaddr = kmap_local_page(mapped->pages[page_idx]); bitmap_set(kaddr, offset, nbits); kunmap_local(kaddr); diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 1d4919edfbde488918327ca894529c291310f7cf..a3ed9ab477486dbeff02bc562f11c461c91322d2 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -71,6 +71,8 @@ static bool vfio_pci_dev_in_denylist(struct pci_dev *pdev) case PCI_DEVICE_ID_INTEL_QAT_C62X_VF: case PCI_DEVICE_ID_INTEL_QAT_DH895XCC: case PCI_DEVICE_ID_INTEL_QAT_DH895XCC_VF: + case PCI_DEVICE_ID_INTEL_DSA_SPR0: + case PCI_DEVICE_ID_INTEL_IAX_SPR0: return true; default: return false; diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index 4a350421c5f62a7a215b690d6b16d7a9dca7c83a..523e0144c86fab80bb619164bdfc0d9c38f15a21 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -1244,7 +1244,7 @@ static int vfio_msi_cap_len(struct vfio_pci_core_device *vdev, u8 pos) if (vdev->msi_perm) return len; - vdev->msi_perm = kmalloc(sizeof(struct perm_bits), GFP_KERNEL); + vdev->msi_perm = kmalloc(sizeof(struct perm_bits), GFP_KERNEL_ACCOUNT); if (!vdev->msi_perm) return -ENOMEM; @@ -1731,11 +1731,11 @@ int vfio_config_init(struct vfio_pci_core_device *vdev) * no requirements on the length of a capability, so the gap between * capabilities needs byte granularity. */ - map = kmalloc(pdev->cfg_size, GFP_KERNEL); + map = kmalloc(pdev->cfg_size, GFP_KERNEL_ACCOUNT); if (!map) return -ENOMEM; - vconfig = kmalloc(pdev->cfg_size, GFP_KERNEL); + vconfig = kmalloc(pdev->cfg_size, GFP_KERNEL_ACCOUNT); if (!vconfig) { kfree(map); return -ENOMEM; diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index e030c2120183ef5c6bd4019ad50e5e6ac4f40a6c..f357fd157e1ed7cc65ad6f75a9ebfe2804f75743 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -141,7 +141,8 @@ static void vfio_pci_probe_mmaps(struct vfio_pci_core_device *vdev) * of the exclusive page in case that hot-add * device's bar is assigned into it. */ - dummy_res = kzalloc(sizeof(*dummy_res), GFP_KERNEL); + dummy_res = + kzalloc(sizeof(*dummy_res), GFP_KERNEL_ACCOUNT); if (dummy_res == NULL) goto no_mmap; @@ -856,7 +857,7 @@ int vfio_pci_core_register_dev_region(struct vfio_pci_core_device *vdev, region = krealloc(vdev->region, (vdev->num_regions + 1) * sizeof(*region), - GFP_KERNEL); + GFP_KERNEL_ACCOUNT); if (!region) return -ENOMEM; @@ -1637,7 +1638,7 @@ static int __vfio_pci_add_vma(struct vfio_pci_core_device *vdev, { struct vfio_pci_mmap_vma *mmap_vma; - mmap_vma = kmalloc(sizeof(*mmap_vma), GFP_KERNEL); + mmap_vma = kmalloc(sizeof(*mmap_vma), GFP_KERNEL_ACCOUNT); if (!mmap_vma) return -ENOMEM; diff --git a/drivers/vfio/pci/vfio_pci_igd.c b/drivers/vfio/pci/vfio_pci_igd.c index 5e6ca592695485c883e9a3402c21445dbd60bbdf..dd70e2431bd74271ae932a6509a60857af6c7da5 100644 --- a/drivers/vfio/pci/vfio_pci_igd.c +++ b/drivers/vfio/pci/vfio_pci_igd.c @@ -180,7 +180,7 @@ static int vfio_pci_igd_opregion_init(struct vfio_pci_core_device *vdev) if (!addr || !(~addr)) return -ENODEV; - opregionvbt = kzalloc(sizeof(*opregionvbt), GFP_KERNEL); + opregionvbt = kzalloc(sizeof(*opregionvbt), GFP_KERNEL_ACCOUNT); if (!opregionvbt) return -ENOMEM; diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 40c3d7cf163f69ce0a860e36d583db4b0ea1015b..03246a59b5536ca9c1f34b1f72c2d241dd0e2419 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -55,17 +55,24 @@ static void vfio_send_intx_eventfd(void *opaque, void *unused) { struct vfio_pci_core_device *vdev = opaque; - if (likely(is_intx(vdev) && !vdev->virq_disabled)) - eventfd_signal(vdev->ctx[0].trigger, 1); + if (likely(is_intx(vdev) && !vdev->virq_disabled)) { + struct eventfd_ctx *trigger; + + trigger = READ_ONCE(vdev->ctx[0].trigger); + if (likely(trigger)) + eventfd_signal(trigger, 1); + } } /* Returns true if the INTx vfio_pci_irq_ctx.masked value is changed. */ -bool vfio_pci_intx_mask(struct vfio_pci_core_device *vdev) +static bool __vfio_pci_intx_mask(struct vfio_pci_core_device *vdev) { struct pci_dev *pdev = vdev->pdev; unsigned long flags; bool masked_changed = false; + lockdep_assert_held(&vdev->igate); + spin_lock_irqsave(&vdev->irqlock, flags); /* @@ -95,6 +102,17 @@ bool vfio_pci_intx_mask(struct vfio_pci_core_device *vdev) return masked_changed; } +bool vfio_pci_intx_mask(struct vfio_pci_core_device *vdev) +{ + bool mask_changed; + + mutex_lock(&vdev->igate); + mask_changed = __vfio_pci_intx_mask(vdev); + mutex_unlock(&vdev->igate); + + return mask_changed; +} + /* * If this is triggered by an eventfd, we can't call eventfd_signal * or else we'll deadlock on the eventfd wait queue. Return >0 when @@ -137,12 +155,21 @@ static int vfio_pci_intx_unmask_handler(void *opaque, void *unused) return ret; } -void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev) +static void __vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev) { + lockdep_assert_held(&vdev->igate); + if (vfio_pci_intx_unmask_handler(vdev, NULL) > 0) vfio_send_intx_eventfd(vdev, NULL); } +void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev) +{ + mutex_lock(&vdev->igate); + __vfio_pci_intx_unmask(vdev); + mutex_unlock(&vdev->igate); +} + static irqreturn_t vfio_intx_handler(int irq, void *dev_id) { struct vfio_pci_core_device *vdev = dev_id; @@ -169,95 +196,104 @@ static irqreturn_t vfio_intx_handler(int irq, void *dev_id) return ret; } -static int vfio_intx_enable(struct vfio_pci_core_device *vdev) +static int vfio_intx_enable(struct vfio_pci_core_device *vdev, + struct eventfd_ctx *trigger) { + struct pci_dev *pdev = vdev->pdev; + unsigned long irqflags; + char *name; + int ret; + if (!is_irq_none(vdev)) return -EINVAL; - if (!vdev->pdev->irq) + if (!pdev->irq) return -ENODEV; - vdev->ctx = kzalloc(sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL); + name = kasprintf(GFP_KERNEL_ACCOUNT, "vfio-intx(%s)", pci_name(pdev)); + if (!name) + return -ENOMEM; + + vdev->ctx = kzalloc(sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL_ACCOUNT); if (!vdev->ctx) return -ENOMEM; vdev->num_ctx = 1; + vdev->ctx[0].name = name; + vdev->ctx[0].trigger = trigger; + /* - * If the virtual interrupt is masked, restore it. Devices - * supporting DisINTx can be masked at the hardware level - * here, non-PCI-2.3 devices will have to wait until the - * interrupt is enabled. + * Fill the initial masked state based on virq_disabled. After + * enable, changing the DisINTx bit in vconfig directly changes INTx + * masking. igate prevents races during setup, once running masked + * is protected via irqlock. + * + * Devices supporting DisINTx also reflect the current mask state in + * the physical DisINTx bit, which is not affected during IRQ setup. + * + * Devices without DisINTx support require an exclusive interrupt. + * IRQ masking is performed at the IRQ chip. Again, igate protects + * against races during setup and IRQ handlers and irqfds are not + * yet active, therefore masked is stable and can be used to + * conditionally auto-enable the IRQ. + * + * irq_type must be stable while the IRQ handler is registered, + * therefore it must be set before request_irq(). */ vdev->ctx[0].masked = vdev->virq_disabled; - if (vdev->pci_2_3) - pci_intx(vdev->pdev, !vdev->ctx[0].masked); + if (vdev->pci_2_3) { + pci_intx(pdev, !vdev->ctx[0].masked); + irqflags = IRQF_SHARED; + } else { + irqflags = vdev->ctx[0].masked ? IRQF_NO_AUTOEN : 0; + } vdev->irq_type = VFIO_PCI_INTX_IRQ_INDEX; + ret = request_irq(pdev->irq, vfio_intx_handler, + irqflags, vdev->ctx[0].name, vdev); + if (ret) { + vdev->irq_type = VFIO_PCI_NUM_IRQS; + kfree(name); + vdev->num_ctx = 0; + kfree(vdev->ctx); + return ret; + } + return 0; } -static int vfio_intx_set_signal(struct vfio_pci_core_device *vdev, int fd) +static int vfio_intx_set_signal(struct vfio_pci_core_device *vdev, + struct eventfd_ctx *trigger) { struct pci_dev *pdev = vdev->pdev; - unsigned long irqflags = IRQF_SHARED; - struct eventfd_ctx *trigger; - unsigned long flags; - int ret; + struct eventfd_ctx *old; - if (vdev->ctx[0].trigger) { - free_irq(pdev->irq, vdev); - kfree(vdev->ctx[0].name); - eventfd_ctx_put(vdev->ctx[0].trigger); - vdev->ctx[0].trigger = NULL; - } - - if (fd < 0) /* Disable only */ - return 0; - - vdev->ctx[0].name = kasprintf(GFP_KERNEL, "vfio-intx(%s)", - pci_name(pdev)); - if (!vdev->ctx[0].name) - return -ENOMEM; + old = vdev->ctx[0].trigger; - trigger = eventfd_ctx_fdget(fd); - if (IS_ERR(trigger)) { - kfree(vdev->ctx[0].name); - return PTR_ERR(trigger); - } + WRITE_ONCE(vdev->ctx[0].trigger, trigger); - vdev->ctx[0].trigger = trigger; - - if (!vdev->pci_2_3) - irqflags = 0; - - ret = request_irq(pdev->irq, vfio_intx_handler, - irqflags, vdev->ctx[0].name, vdev); - if (ret) { - vdev->ctx[0].trigger = NULL; - kfree(vdev->ctx[0].name); - eventfd_ctx_put(trigger); - return ret; + /* Releasing an old ctx requires synchronizing in-flight users */ + if (old) { + synchronize_irq(pdev->irq); + vfio_virqfd_flush_thread(&vdev->ctx[0].unmask); + eventfd_ctx_put(old); } - /* - * INTx disable will stick across the new irq setup, - * disable_irq won't. - */ - spin_lock_irqsave(&vdev->irqlock, flags); - if (!vdev->pci_2_3 && vdev->ctx[0].masked) - disable_irq_nosync(pdev->irq); - spin_unlock_irqrestore(&vdev->irqlock, flags); - return 0; } static void vfio_intx_disable(struct vfio_pci_core_device *vdev) { + struct pci_dev *pdev = vdev->pdev; + vfio_virqfd_disable(&vdev->ctx[0].unmask); vfio_virqfd_disable(&vdev->ctx[0].mask); - vfio_intx_set_signal(vdev, -1); + free_irq(pdev->irq, vdev); + if (vdev->ctx[0].trigger) + eventfd_ctx_put(vdev->ctx[0].trigger); + kfree(vdev->ctx[0].name); vdev->irq_type = VFIO_PCI_NUM_IRQS; vdev->num_ctx = 0; kfree(vdev->ctx); @@ -284,7 +320,8 @@ static int vfio_msi_enable(struct vfio_pci_core_device *vdev, int nvec, bool msi if (!is_irq_none(vdev)) return -EINVAL; - vdev->ctx = kcalloc(nvec, sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL); + vdev->ctx = kcalloc(nvec, sizeof(struct vfio_pci_irq_ctx), + GFP_KERNEL_ACCOUNT); if (!vdev->ctx) return -ENOMEM; @@ -316,14 +353,14 @@ static int vfio_msi_enable(struct vfio_pci_core_device *vdev, int nvec, bool msi } static int vfio_msi_set_vector_signal(struct vfio_pci_core_device *vdev, - int vector, int fd, bool msix) + unsigned int vector, int fd, bool msix) { struct pci_dev *pdev = vdev->pdev; struct eventfd_ctx *trigger; int irq, ret; u16 cmd; - if (vector < 0 || vector >= vdev->num_ctx) + if (vector >= vdev->num_ctx) return -EINVAL; irq = pci_irq_vector(pdev, vector); @@ -343,7 +380,8 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_core_device *vdev, if (fd < 0) return 0; - vdev->ctx[vector].name = kasprintf(GFP_KERNEL, "vfio-msi%s[%d](%s)", + vdev->ctx[vector].name = kasprintf(GFP_KERNEL_ACCOUNT, + "vfio-msi%s[%d](%s)", msix ? "x" : "", vector, pci_name(pdev)); if (!vdev->ctx[vector].name) @@ -397,7 +435,8 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_core_device *vdev, static int vfio_msi_set_block(struct vfio_pci_core_device *vdev, unsigned start, unsigned count, int32_t *fds, bool msix) { - int i, j, ret = 0; + unsigned int i, j; + int ret = 0; if (start >= vdev->num_ctx || start + count > vdev->num_ctx) return -EINVAL; @@ -408,8 +447,8 @@ static int vfio_msi_set_block(struct vfio_pci_core_device *vdev, unsigned start, } if (ret) { - for (--j; j >= (int)start; j--) - vfio_msi_set_vector_signal(vdev, j, -1, msix); + for (i = start; i < j; i++) + vfio_msi_set_vector_signal(vdev, i, -1, msix); } return ret; @@ -418,16 +457,15 @@ static int vfio_msi_set_block(struct vfio_pci_core_device *vdev, unsigned start, static void vfio_msi_disable(struct vfio_pci_core_device *vdev, bool msix) { struct pci_dev *pdev = vdev->pdev; - int i; + unsigned int i; u16 cmd; for (i = 0; i < vdev->num_ctx; i++) { vfio_virqfd_disable(&vdev->ctx[i].unmask); vfio_virqfd_disable(&vdev->ctx[i].mask); + vfio_msi_set_vector_signal(vdev, i, -1, msix); } - vfio_msi_set_block(vdev, 0, vdev->num_ctx, NULL, msix); - cmd = vfio_pci_memory_lock_and_enable(vdev); pci_free_irq_vectors(pdev); vfio_pci_memory_unlock_and_restore(vdev, cmd); @@ -455,11 +493,11 @@ static int vfio_pci_set_intx_unmask(struct vfio_pci_core_device *vdev, return -EINVAL; if (flags & VFIO_IRQ_SET_DATA_NONE) { - vfio_pci_intx_unmask(vdev); + __vfio_pci_intx_unmask(vdev); } else if (flags & VFIO_IRQ_SET_DATA_BOOL) { uint8_t unmask = *(uint8_t *)data; if (unmask) - vfio_pci_intx_unmask(vdev); + __vfio_pci_intx_unmask(vdev); } else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { int32_t fd = *(int32_t *)data; if (fd >= 0) @@ -482,11 +520,11 @@ static int vfio_pci_set_intx_mask(struct vfio_pci_core_device *vdev, return -EINVAL; if (flags & VFIO_IRQ_SET_DATA_NONE) { - vfio_pci_intx_mask(vdev); + __vfio_pci_intx_mask(vdev); } else if (flags & VFIO_IRQ_SET_DATA_BOOL) { uint8_t mask = *(uint8_t *)data; if (mask) - vfio_pci_intx_mask(vdev); + __vfio_pci_intx_mask(vdev); } else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { return -ENOTTY; /* XXX implement me */ } @@ -507,19 +545,23 @@ static int vfio_pci_set_intx_trigger(struct vfio_pci_core_device *vdev, return -EINVAL; if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { + struct eventfd_ctx *trigger = NULL; int32_t fd = *(int32_t *)data; int ret; - if (is_intx(vdev)) - return vfio_intx_set_signal(vdev, fd); + if (fd >= 0) { + trigger = eventfd_ctx_fdget(fd); + if (IS_ERR(trigger)) + return PTR_ERR(trigger); + } - ret = vfio_intx_enable(vdev); - if (ret) - return ret; + if (is_intx(vdev)) + ret = vfio_intx_set_signal(vdev, trigger); + else + ret = vfio_intx_enable(vdev, trigger); - ret = vfio_intx_set_signal(vdev, fd); - if (ret) - vfio_intx_disable(vdev); + if (ret && trigger) + eventfd_ctx_put(trigger); return ret; } @@ -541,7 +583,7 @@ static int vfio_pci_set_msi_trigger(struct vfio_pci_core_device *vdev, unsigned index, unsigned start, unsigned count, uint32_t flags, void *data) { - int i; + unsigned int i; bool msix = (index == VFIO_PCI_MSIX_IRQ_INDEX) ? true : false; if (irq_is(vdev, index) && !count && (flags & VFIO_IRQ_SET_DATA_NONE)) { diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c index e352a033b4aef770e434a42ebbeece0fbf6eb7a3..e27de61ac9fe75f5818dc8d7386270c592c05a07 100644 --- a/drivers/vfio/pci/vfio_pci_rdwr.c +++ b/drivers/vfio/pci/vfio_pci_rdwr.c @@ -470,7 +470,7 @@ int vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset, goto out_unlock; } - ioeventfd = kzalloc(sizeof(*ioeventfd), GFP_KERNEL); + ioeventfd = kzalloc(sizeof(*ioeventfd), GFP_KERNEL_ACCOUNT); if (!ioeventfd) { ret = -ENOMEM; goto out_unlock; diff --git a/drivers/vfio/platform/vfio_platform_irq.c b/drivers/vfio/platform/vfio_platform_irq.c index c5b09ec0a3c981499c81befff6a18871c8f18e05..7f4341a8d718582f6fa1acd48d31c936d73618b9 100644 --- a/drivers/vfio/platform/vfio_platform_irq.c +++ b/drivers/vfio/platform/vfio_platform_irq.c @@ -136,6 +136,16 @@ static int vfio_platform_set_irq_unmask(struct vfio_platform_device *vdev, return 0; } +/* + * The trigger eventfd is guaranteed valid in the interrupt path + * and protected by the igate mutex when triggered via ioctl. + */ +static void vfio_send_eventfd(struct vfio_platform_irq *irq_ctx) +{ + if (likely(irq_ctx->trigger)) + eventfd_signal(irq_ctx->trigger, 1); +} + static irqreturn_t vfio_automasked_irq_handler(int irq, void *dev_id) { struct vfio_platform_irq *irq_ctx = dev_id; @@ -155,7 +165,7 @@ static irqreturn_t vfio_automasked_irq_handler(int irq, void *dev_id) spin_unlock_irqrestore(&irq_ctx->lock, flags); if (ret == IRQ_HANDLED) - eventfd_signal(irq_ctx->trigger, 1); + vfio_send_eventfd(irq_ctx); return ret; } @@ -164,22 +174,19 @@ static irqreturn_t vfio_irq_handler(int irq, void *dev_id) { struct vfio_platform_irq *irq_ctx = dev_id; - eventfd_signal(irq_ctx->trigger, 1); + vfio_send_eventfd(irq_ctx); return IRQ_HANDLED; } static int vfio_set_trigger(struct vfio_platform_device *vdev, int index, - int fd, irq_handler_t handler) + int fd) { struct vfio_platform_irq *irq = &vdev->irqs[index]; struct eventfd_ctx *trigger; - int ret; if (irq->trigger) { - irq_clear_status_flags(irq->hwirq, IRQ_NOAUTOEN); - free_irq(irq->hwirq, irq); - kfree(irq->name); + disable_irq(irq->hwirq); eventfd_ctx_put(irq->trigger); irq->trigger = NULL; } @@ -187,30 +194,20 @@ static int vfio_set_trigger(struct vfio_platform_device *vdev, int index, if (fd < 0) /* Disable only */ return 0; - irq->name = kasprintf(GFP_KERNEL, "vfio-irq[%d](%s)", - irq->hwirq, vdev->name); - if (!irq->name) - return -ENOMEM; - trigger = eventfd_ctx_fdget(fd); - if (IS_ERR(trigger)) { - kfree(irq->name); + if (IS_ERR(trigger)) return PTR_ERR(trigger); - } irq->trigger = trigger; - irq_set_status_flags(irq->hwirq, IRQ_NOAUTOEN); - ret = request_irq(irq->hwirq, handler, 0, irq->name, irq); - if (ret) { - kfree(irq->name); - eventfd_ctx_put(trigger); - irq->trigger = NULL; - return ret; - } - - if (!irq->masked) - enable_irq(irq->hwirq); + /* + * irq->masked effectively provides nested disables within the overall + * enable relative to trigger. Specifically request_irq() is called + * with NO_AUTOEN, therefore the IRQ is initially disabled. The user + * may only further disable the IRQ with a MASK operations because + * irq->masked is initially false. + */ + enable_irq(irq->hwirq); return 0; } @@ -229,7 +226,7 @@ static int vfio_platform_set_irq_trigger(struct vfio_platform_device *vdev, handler = vfio_irq_handler; if (!count && (flags & VFIO_IRQ_SET_DATA_NONE)) - return vfio_set_trigger(vdev, index, -1, handler); + return vfio_set_trigger(vdev, index, -1); if (start != 0 || count != 1) return -EINVAL; @@ -237,7 +234,7 @@ static int vfio_platform_set_irq_trigger(struct vfio_platform_device *vdev, if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { int32_t fd = *(int32_t *)data; - return vfio_set_trigger(vdev, index, fd, handler); + return vfio_set_trigger(vdev, index, fd); } if (flags & VFIO_IRQ_SET_DATA_NONE) { @@ -261,6 +258,14 @@ int vfio_platform_set_irqs_ioctl(struct vfio_platform_device *vdev, unsigned start, unsigned count, uint32_t flags, void *data) = NULL; + /* + * For compatibility, errors from request_irq() are local to the + * SET_IRQS path and reflected in the name pointer. This allows, + * for example, polling mode fallback for an exclusive IRQ failure. + */ + if (IS_ERR(vdev->irqs[index].name)) + return PTR_ERR(vdev->irqs[index].name); + switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) { case VFIO_IRQ_SET_ACTION_MASK: func = vfio_platform_set_irq_mask; @@ -281,7 +286,7 @@ int vfio_platform_set_irqs_ioctl(struct vfio_platform_device *vdev, int vfio_platform_irq_init(struct vfio_platform_device *vdev) { - int cnt = 0, i; + int cnt = 0, i, ret = 0; while (vdev->get_irq(vdev, cnt) >= 0) cnt++; @@ -292,37 +297,70 @@ int vfio_platform_irq_init(struct vfio_platform_device *vdev) for (i = 0; i < cnt; i++) { int hwirq = vdev->get_irq(vdev, i); + irq_handler_t handler = vfio_irq_handler; - if (hwirq < 0) + if (hwirq < 0) { + ret = -EINVAL; goto err; + } spin_lock_init(&vdev->irqs[i].lock); vdev->irqs[i].flags = VFIO_IRQ_INFO_EVENTFD; - if (irq_get_trigger_type(hwirq) & IRQ_TYPE_LEVEL_MASK) + if (irq_get_trigger_type(hwirq) & IRQ_TYPE_LEVEL_MASK) { vdev->irqs[i].flags |= VFIO_IRQ_INFO_MASKABLE | VFIO_IRQ_INFO_AUTOMASKED; + handler = vfio_automasked_irq_handler; + } vdev->irqs[i].count = 1; vdev->irqs[i].hwirq = hwirq; vdev->irqs[i].masked = false; + vdev->irqs[i].name = kasprintf(GFP_KERNEL, + "vfio-irq[%d](%s)", hwirq, + vdev->name); + if (!vdev->irqs[i].name) { + ret = -ENOMEM; + goto err; + } + + ret = request_irq(hwirq, handler, IRQF_NO_AUTOEN, + vdev->irqs[i].name, &vdev->irqs[i]); + if (ret) { + kfree(vdev->irqs[i].name); + vdev->irqs[i].name = ERR_PTR(ret); + } } vdev->num_irqs = cnt; return 0; err: + for (--i; i >= 0; i--) { + if (!IS_ERR(vdev->irqs[i].name)) { + free_irq(vdev->irqs[i].hwirq, &vdev->irqs[i]); + kfree(vdev->irqs[i].name); + } + } kfree(vdev->irqs); - return -EINVAL; + return ret; } void vfio_platform_irq_cleanup(struct vfio_platform_device *vdev) { int i; - for (i = 0; i < vdev->num_irqs; i++) - vfio_set_trigger(vdev, i, -1, NULL); + for (i = 0; i < vdev->num_irqs; i++) { + vfio_virqfd_disable(&vdev->irqs[i].mask); + vfio_virqfd_disable(&vdev->irqs[i].unmask); + if (!IS_ERR(vdev->irqs[i].name)) { + free_irq(vdev->irqs[i].hwirq, &vdev->irqs[i]); + if (vdev->irqs[i].trigger) + eventfd_ctx_put(vdev->irqs[i].trigger); + kfree(vdev->irqs[i].name); + } + } vdev->num_irqs = 0; kfree(vdev->irqs); diff --git a/drivers/vfio/virqfd.c b/drivers/vfio/virqfd.c index 414e98d82b02e561d5423910d0cb572b7c4ea7d3..e06b32ddedcedcf149d307df864e3b7477a307e9 100644 --- a/drivers/vfio/virqfd.c +++ b/drivers/vfio/virqfd.c @@ -104,6 +104,13 @@ static void virqfd_inject(struct work_struct *work) virqfd->thread(virqfd->opaque, virqfd->data); } +static void virqfd_flush_inject(struct work_struct *work) +{ + struct virqfd *virqfd = container_of(work, struct virqfd, flush_inject); + + flush_work(&virqfd->inject); +} + int vfio_virqfd_enable(void *opaque, int (*handler)(void *, void *), void (*thread)(void *, void *), @@ -115,7 +122,7 @@ int vfio_virqfd_enable(void *opaque, int ret = 0; __poll_t events; - virqfd = kzalloc(sizeof(*virqfd), GFP_KERNEL); + virqfd = kzalloc(sizeof(*virqfd), GFP_KERNEL_ACCOUNT); if (!virqfd) return -ENOMEM; @@ -127,6 +134,7 @@ int vfio_virqfd_enable(void *opaque, INIT_WORK(&virqfd->shutdown, virqfd_shutdown); INIT_WORK(&virqfd->inject, virqfd_inject); + INIT_WORK(&virqfd->flush_inject, virqfd_flush_inject); irqfd = fdget(fd); if (!irqfd.file) { @@ -217,6 +225,19 @@ void vfio_virqfd_disable(struct virqfd **pvirqfd) } EXPORT_SYMBOL_GPL(vfio_virqfd_disable); +void vfio_virqfd_flush_thread(struct virqfd **pvirqfd) +{ + unsigned long flags; + + spin_lock_irqsave(&virqfd_lock, flags); + if (*pvirqfd && (*pvirqfd)->thread) + queue_work(vfio_irqfd_cleanup_wq, &(*pvirqfd)->flush_inject); + spin_unlock_irqrestore(&virqfd_lock, flags); + + flush_workqueue(vfio_irqfd_cleanup_wq); +} +EXPORT_SYMBOL_GPL(vfio_virqfd_flush_thread); + module_init(vfio_virqfd_init); module_exit(vfio_virqfd_exit); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 2eea08029881283334b65a46dd5dcf55451b98c3..1b00ed5ef1cfabab08296e721960fcdca65ff181 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -2523,9 +2523,19 @@ bool vhost_vq_avail_empty(struct vhost_dev *dev, struct vhost_virtqueue *vq) r = vhost_get_avail_idx(vq, &avail_idx); if (unlikely(r)) return false; + vq->avail_idx = vhost16_to_cpu(vq, avail_idx); + if (vq->avail_idx != vq->last_avail_idx) { + /* Since we have updated avail_idx, the following + * call to vhost_get_vq_desc() will read available + * ring entries. Make sure that read happens after + * the avail_idx read. + */ + smp_rmb(); + return false; + } - return vq->avail_idx == vq->last_avail_idx; + return true; } EXPORT_SYMBOL_GPL(vhost_vq_avail_empty); @@ -2562,9 +2572,19 @@ bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq) &vq->avail->idx, r); return false; } + vq->avail_idx = vhost16_to_cpu(vq, avail_idx); + if (vq->avail_idx != vq->last_avail_idx) { + /* Since we have updated avail_idx, the following + * call to vhost_get_vq_desc() will read available + * ring entries. Make sure that read happens after + * the avail_idx read. + */ + smp_rmb(); + return true; + } - return vq->avail_idx != vq->last_avail_idx; + return false; } EXPORT_SYMBOL_GPL(vhost_enable_notify); @@ -2588,12 +2608,11 @@ EXPORT_SYMBOL_GPL(vhost_disable_notify); /* Create a new message. */ struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type) { - struct vhost_msg_node *node = kmalloc(sizeof *node, GFP_KERNEL); + /* Make sure all padding within the structure is initialized. */ + struct vhost_msg_node *node = kzalloc(sizeof(*node), GFP_KERNEL); if (!node) return NULL; - /* Make sure all padding within the structure is initialized. */ - memset(&node->msg, 0, sizeof node->msg); node->vq = vq; node->msg.type = type; return node; diff --git a/drivers/video/backlight/da9052_bl.c b/drivers/video/backlight/da9052_bl.c index 882359dd288c06743a50fbd49c30fbe73666d093..aa00379392a0f74b224118db8679b7c255d6b8fd 100644 --- a/drivers/video/backlight/da9052_bl.c +++ b/drivers/video/backlight/da9052_bl.c @@ -117,6 +117,7 @@ static int da9052_backlight_probe(struct platform_device *pdev) wleds->led_reg = platform_get_device_id(pdev)->driver_data; wleds->state = DA9052_WLEDS_OFF; + memset(&props, 0, sizeof(struct backlight_properties)); props.type = BACKLIGHT_RAW; props.max_brightness = DA9052_MAX_BRIGHTNESS; diff --git a/drivers/video/backlight/lm3630a_bl.c b/drivers/video/backlight/lm3630a_bl.c index 475f35635bf671e81f181419ed62a0384ba1d89e..0d43f6326750fc0584555d4056eb59a20d7d4c4e 100644 --- a/drivers/video/backlight/lm3630a_bl.c +++ b/drivers/video/backlight/lm3630a_bl.c @@ -231,7 +231,7 @@ static int lm3630a_bank_a_get_brightness(struct backlight_device *bl) if (rval < 0) goto out_i2c_err; brightness |= rval; - goto out; + return brightness; } /* disable sleep */ @@ -242,11 +242,8 @@ static int lm3630a_bank_a_get_brightness(struct backlight_device *bl) rval = lm3630a_read(pchip, REG_BRT_A); if (rval < 0) goto out_i2c_err; - brightness = rval; + return rval; -out: - bl->props.brightness = brightness; - return bl->props.brightness; out_i2c_err: dev_err(pchip->dev, "i2c failed to access register\n"); return 0; @@ -306,7 +303,7 @@ static int lm3630a_bank_b_get_brightness(struct backlight_device *bl) if (rval < 0) goto out_i2c_err; brightness |= rval; - goto out; + return brightness; } /* disable sleep */ @@ -317,11 +314,8 @@ static int lm3630a_bank_b_get_brightness(struct backlight_device *bl) rval = lm3630a_read(pchip, REG_BRT_B); if (rval < 0) goto out_i2c_err; - brightness = rval; + return rval; -out: - bl->props.brightness = brightness; - return bl->props.brightness; out_i2c_err: dev_err(pchip->dev, "i2c failed to access register\n"); return 0; @@ -339,6 +333,7 @@ static int lm3630a_backlight_register(struct lm3630a_chip *pchip) struct backlight_properties props; const char *label; + memset(&props, 0, sizeof(struct backlight_properties)); props.type = BACKLIGHT_RAW; if (pdata->leda_ctrl != LM3630A_LEDA_DISABLE) { props.brightness = pdata->leda_init_brt; diff --git a/drivers/video/backlight/lm3639_bl.c b/drivers/video/backlight/lm3639_bl.c index 6580911671a3e774310b2a84d596037693f5092d..4c9726a7fa720b5696a839204298f8f70761a6c4 100644 --- a/drivers/video/backlight/lm3639_bl.c +++ b/drivers/video/backlight/lm3639_bl.c @@ -339,6 +339,7 @@ static int lm3639_probe(struct i2c_client *client, } /* backlight */ + memset(&props, 0, sizeof(struct backlight_properties)); props.type = BACKLIGHT_RAW; props.brightness = pdata->init_brt_led; props.max_brightness = pdata->max_brt_led; diff --git a/drivers/video/backlight/lp8788_bl.c b/drivers/video/backlight/lp8788_bl.c index ba42f3fe0c739421d99cab50dca78c8185b5db6f..d9b95dbd40d3098f5a66eae223a7b5422f077bef 100644 --- a/drivers/video/backlight/lp8788_bl.c +++ b/drivers/video/backlight/lp8788_bl.c @@ -191,6 +191,7 @@ static int lp8788_backlight_register(struct lp8788_bl *bl) int init_brt; char *name; + memset(&props, 0, sizeof(struct backlight_properties)); props.type = BACKLIGHT_PLATFORM; props.max_brightness = MAX_BRIGHTNESS; diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c index 7c02b954f7d35bc2ffb03e10e04a7ecebf6f96e4..2e8b46dd1bdf8605427b661e95752f42e2d0acc6 100644 --- a/drivers/video/fbdev/core/fb_defio.c +++ b/drivers/video/fbdev/core/fb_defio.c @@ -200,7 +200,7 @@ err_mutex_unlock: */ static vm_fault_t fb_deferred_io_page_mkwrite(struct fb_info *info, struct vm_fault *vmf) { - unsigned long offset = vmf->address - vmf->vma->vm_start; + unsigned long offset = vmf->pgoff << PAGE_SHIFT; struct page *page = vmf->page; file_update_time(vmf->vma->vm_file); diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index fa205be94a4b81d8cf569e3d0412030b39a8c213..14498a0d13e0b717101584a4691d22876c0b7162 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2397,11 +2397,9 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount, struct fbcon_ops *ops = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; int resize, ret, old_userfont, old_width, old_height, old_charcount; - char *old_data = NULL; + u8 *old_data = vc->vc_font.data; resize = (w != vc->vc_font.width) || (h != vc->vc_font.height); - if (p->userfont) - old_data = vc->vc_font.data; vc->vc_font.data = (void *)(p->fontdata = data); old_userfont = p->userfont; if ((p->userfont = userfont)) @@ -2435,13 +2433,13 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount, update_screen(vc); } - if (old_data && (--REFCOUNT(old_data) == 0)) + if (old_userfont && (--REFCOUNT(old_data) == 0)) kfree(old_data - FONT_EXTRA_WORDS * sizeof(int)); return 0; err_out: p->fontdata = old_data; - vc->vc_font.data = (void *)old_data; + vc->vc_font.data = old_data; if (userfont) { p->userfont = old_userfont; diff --git a/drivers/video/fbdev/core/fbmon.c b/drivers/video/fbdev/core/fbmon.c index b0e690f41025a23e2b9798f7675f5991f3797ad1..9ca99da3a56a0a684c880650b09f4e0ffc45471a 100644 --- a/drivers/video/fbdev/core/fbmon.c +++ b/drivers/video/fbdev/core/fbmon.c @@ -1311,7 +1311,7 @@ int fb_get_mode(int flags, u32 val, struct fb_var_screeninfo *var, struct fb_inf int fb_videomode_from_videomode(const struct videomode *vm, struct fb_videomode *fbmode) { - unsigned int htotal, vtotal; + unsigned int htotal, vtotal, total; fbmode->xres = vm->hactive; fbmode->left_margin = vm->hback_porch; @@ -1344,8 +1344,9 @@ int fb_videomode_from_videomode(const struct videomode *vm, vtotal = vm->vactive + vm->vfront_porch + vm->vback_porch + vm->vsync_len; /* prevent division by zero */ - if (htotal && vtotal) { - fbmode->refresh = vm->pixelclock / (htotal * vtotal); + total = htotal * vtotal; + if (total) { + fbmode->refresh = vm->pixelclock / total; /* a mode must have htotal and vtotal != 0 or it is invalid */ } else { fbmode->refresh = 0; diff --git a/drivers/video/fbdev/savage/savagefb_driver.c b/drivers/video/fbdev/savage/savagefb_driver.c index b7818b652698f079ba2500fd963bb9c89efbd7ab..a7b63c475f95474b0c646edfd0ea900171d6f186 100644 --- a/drivers/video/fbdev/savage/savagefb_driver.c +++ b/drivers/video/fbdev/savage/savagefb_driver.c @@ -869,6 +869,9 @@ static int savagefb_check_var(struct fb_var_screeninfo *var, DBG("savagefb_check_var"); + if (!var->pixclock) + return -EINVAL; + var->transp.offset = 0; var->transp.length = 0; switch (var->bits_per_pixel) { diff --git a/drivers/video/fbdev/sis/sis_main.c b/drivers/video/fbdev/sis/sis_main.c index 1c197c3f95381e531d45209419f72aa172e172c8..fe8996461b9ef31cfc2965e02b2510ca40fb6a10 100644 --- a/drivers/video/fbdev/sis/sis_main.c +++ b/drivers/video/fbdev/sis/sis_main.c @@ -1475,6 +1475,8 @@ sisfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) vtotal = var->upper_margin + var->lower_margin + var->vsync_len; + if (!var->pixclock) + return -EINVAL; pixclock = var->pixclock; if((var->vmode & FB_VMODE_MASK) == FB_VMODE_NONINTERLACED) { diff --git a/drivers/video/fbdev/via/accel.c b/drivers/video/fbdev/via/accel.c index 0a1bc7a4d7853cebb85b46a90a11a4c25257717c..1e04026f0809185a91486043abca094d19d43c45 100644 --- a/drivers/video/fbdev/via/accel.c +++ b/drivers/video/fbdev/via/accel.c @@ -115,7 +115,7 @@ static int hw_bitblt_1(void __iomem *engine, u8 op, u32 width, u32 height, if (op != VIA_BITBLT_FILL) { tmp = src_mem ? 0 : src_addr; - if (dst_addr & 0xE0000007) { + if (tmp & 0xE0000007) { printk(KERN_WARNING "hw_bitblt_1: Unsupported source " "address %X\n", tmp); return -EINVAL; @@ -260,7 +260,7 @@ static int hw_bitblt_2(void __iomem *engine, u8 op, u32 width, u32 height, writel(tmp, engine + 0x18); tmp = src_mem ? 0 : src_addr; - if (dst_addr & 0xE0000007) { + if (tmp & 0xE0000007) { printk(KERN_WARNING "hw_bitblt_2: Unsupported source " "address %X\n", tmp); return -EINVAL; diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 828ced060742358069ae33e46dd62899d5400760..1ef094427f299984aa0b232d4a767dd37f6f598d 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -489,13 +489,19 @@ EXPORT_SYMBOL_GPL(unregister_virtio_device); int virtio_device_freeze(struct virtio_device *dev) { struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); + int ret; virtio_config_disable(dev); dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED; - if (drv && drv->freeze) - return drv->freeze(dev); + if (drv && drv->freeze) { + ret = drv->freeze(dev); + if (ret) { + virtio_config_enable(dev); + return ret; + } + } return 0; } diff --git a/drivers/watchdog/stm32_iwdg.c b/drivers/watchdog/stm32_iwdg.c index 570a71509d2a9b0070494de4419b3b6df862a51a..78d51deab87aa1b0eb1144045d99c826e9e0c4d6 100644 --- a/drivers/watchdog/stm32_iwdg.c +++ b/drivers/watchdog/stm32_iwdg.c @@ -21,6 +21,8 @@ #include #include +#define DEFAULT_TIMEOUT 10 + /* IWDG registers */ #define IWDG_KR 0x00 /* Key register */ #define IWDG_PR 0x04 /* Prescaler Register */ @@ -249,6 +251,7 @@ static int stm32_iwdg_probe(struct platform_device *pdev) wdd->parent = dev; wdd->info = &stm32_iwdg_info; wdd->ops = &stm32_iwdg_ops; + wdd->timeout = DEFAULT_TIMEOUT; wdd->min_timeout = DIV_ROUND_UP((RLR_MIN + 1) * PR_MIN, wdt->rate); wdd->max_hw_heartbeat_ms = ((RLR_MAX + 1) * wdt->data->max_prescaler * 1000) / wdt->rate; diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 00f8e349921d47fa26b381aefbeb83a8440b3ce6..96b96516c9806c5bd1b7eb7b1290a38cd90c5492 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -937,8 +937,8 @@ static void shutdown_pirq(struct irq_data *data) return; do_mask(info, EVT_MASK_REASON_EXPLICIT); - xen_evtchn_close(evtchn); xen_irq_info_cleanup(info); + xen_evtchn_close(evtchn); } static void enable_pirq(struct irq_data *data) @@ -982,8 +982,6 @@ static void __unbind_from_irq(unsigned int irq) unsigned int cpu = cpu_from_irq(irq); struct xenbus_device *dev; - xen_evtchn_close(evtchn); - switch (type_from_irq(irq)) { case IRQT_VIRQ: per_cpu(virq_to_irq, cpu)[virq_from_irq(irq)] = -1; @@ -1001,6 +999,7 @@ static void __unbind_from_irq(unsigned int irq) } xen_irq_info_cleanup(info); + xen_evtchn_close(evtchn); } xen_free_irq(irq); diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index aec43ba83799255caa41d69d7671234f26be1003..87222067fe5def3c0a58c1bd1fb7c974d6282cd9 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -667,6 +667,7 @@ const struct file_operations v9fs_file_operations = { .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync, + .setlease = simple_nosetlease, }; const struct file_operations v9fs_file_operations_dotl = { @@ -708,4 +709,5 @@ const struct file_operations v9fs_mmap_file_operations_dotl = { .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync_dotl, + .setlease = simple_nosetlease, }; diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 5e2657c1dbbe6492d517962cae37cbd21eb3c5ef..8f287009545c97aa57fd005caf153cde63e30f02 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -85,7 +85,7 @@ static int p9mode2perm(struct v9fs_session_info *v9ses, int res; int mode = stat->mode; - res = mode & S_IALLUGO; + res = mode & 0777; /* S_IRWXUGO */ if (v9fs_proto_dotu(v9ses)) { if ((mode & P9_DMSETUID) == P9_DMSETUID) res |= S_ISUID; @@ -181,6 +181,9 @@ int v9fs_uflags2omode(int uflags, int extended) break; } + if (uflags & O_TRUNC) + ret |= P9_OTRUNC; + if (extended) { if (uflags & O_EXCL) ret |= P9_OEXCL; diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index 2d9ee073d12c3ab5c62062e790e2e821d5eeab7f..7c35347f1d9be2424c42f45adda509b49ae65a2f 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -342,6 +342,7 @@ static const struct super_operations v9fs_super_ops = { .alloc_inode = v9fs_alloc_inode, .free_inode = v9fs_free_inode, .statfs = simple_statfs, + .drop_inode = v9fs_drop_inode, .evict_inode = v9fs_evict_inode, .show_options = v9fs_show_options, .umount_begin = v9fs_umount_begin, diff --git a/fs/afs/dir.c b/fs/afs/dir.c index cf811b77ee671fd47c1124202746a1e320fe02eb..07dc4ec73520c7504a8d074c42beae7f6acd6528 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -473,14 +473,6 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, continue; } - /* Don't expose silly rename entries to userspace. */ - if (nlen > 6 && - dire->u.name[0] == '.' && - ctx->actor != afs_lookup_filldir && - ctx->actor != afs_lookup_one_filldir && - memcmp(dire->u.name, ".__afs", 6) == 0) - continue; - /* found the next entry */ if (!dir_emit(ctx, dire->u.name, nlen, ntohl(dire->u.vnode), diff --git a/fs/afs/volume.c b/fs/afs/volume.c index 1c9144e3e83acbf8dff1aefa5026b0a1c85ddcbd..a146d70efa65019604885dc9d581d4519afff7b3 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -341,7 +341,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key) { struct afs_server_list *new, *old, *discard; struct afs_vldb_entry *vldb; - char idbuf[16]; + char idbuf[24]; int ret, idsz; _enter(""); @@ -349,7 +349,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key) /* We look up an ID by passing it as a decimal string in the * operation's name parameter. */ - idsz = sprintf(idbuf, "%llu", volume->vid); + idsz = snprintf(idbuf, sizeof(idbuf), "%llu", volume->vid); vldb = afs_vl_lookup_vldb(volume->cell, key, idbuf, idsz); if (IS_ERR(vldb)) { diff --git a/fs/aio.c b/fs/aio.c index e85ba0b77f596ebded92d6db246410b6b67f49a8..3e3bf6fdc5ab6e82be83b082cfcc6e70b435b591 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -591,13 +591,24 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events) void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) { - struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, rw); - struct kioctx *ctx = req->ki_ctx; + struct aio_kiocb *req; + struct kioctx *ctx; unsigned long flags; + /* + * kiocb didn't come from aio or is neither a read nor a write, hence + * ignore it. + */ + if (!(iocb->ki_flags & IOCB_AIO_RW)) + return; + + req = container_of(iocb, struct aio_kiocb, rw); + if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; + ctx = req->ki_ctx; + spin_lock_irqsave(&ctx->ctx_lock, flags); list_add_tail(&req->ki_list, &ctx->active_reqs); req->ki_cancel = cancel; @@ -1476,7 +1487,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) req->ki_complete = aio_complete_rw; req->private = NULL; req->ki_pos = iocb->aio_offset; - req->ki_flags = req->ki_filp->f_iocb_flags; + req->ki_flags = req->ki_filp->f_iocb_flags | IOCB_AIO_RW; if (iocb->aio_flags & IOCB_FLAG_RESFD) req->ki_flags |= IOCB_EVENTFD; if (iocb->aio_flags & IOCB_FLAG_IOPRIO) { diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 18cf801ab59081904b773063a9d593a75eed466e..23d0372e88821a75d375995e7d235d4657ddb9a4 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -2475,20 +2475,14 @@ struct btrfs_data_container *init_data_container(u32 total_bytes) size_t alloc_bytes; alloc_bytes = max_t(size_t, total_bytes, sizeof(*data)); - data = kvmalloc(alloc_bytes, GFP_KERNEL); + data = kvzalloc(alloc_bytes, GFP_KERNEL); if (!data) return ERR_PTR(-ENOMEM); - if (total_bytes >= sizeof(*data)) { + if (total_bytes >= sizeof(*data)) data->bytes_left = total_bytes - sizeof(*data); - data->bytes_missing = 0; - } else { + else data->bytes_missing = sizeof(*data) - total_bytes; - data->bytes_left = 0; - } - - data->elem_cnt = 0; - data->elem_missed = 0; return data; } diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 08017b180a10d7e4f344483e21613fbd726f5491..5993b627be58049193ebb32704270c21f01c5dc1 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1318,6 +1318,7 @@ out: */ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) { + LIST_HEAD(retry_list); struct btrfs_block_group *block_group; struct btrfs_space_info *space_info; struct btrfs_trans_handle *trans; @@ -1339,6 +1340,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) spin_lock(&fs_info->unused_bgs_lock); while (!list_empty(&fs_info->unused_bgs)) { + u64 used; int trimming; block_group = list_first_entry(&fs_info->unused_bgs, @@ -1374,9 +1376,9 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) goto next; } + spin_lock(&space_info->lock); spin_lock(&block_group->lock); - if (block_group->reserved || block_group->pinned || - block_group->used || block_group->ro || + if (btrfs_is_block_group_used(block_group) || block_group->ro || list_is_singular(&block_group->list)) { /* * We want to bail if we made new allocations or have @@ -1386,10 +1388,50 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) */ trace_btrfs_skip_unused_block_group(block_group); spin_unlock(&block_group->lock); + spin_unlock(&space_info->lock); + up_write(&space_info->groups_sem); + goto next; + } + + /* + * The block group may be unused but there may be space reserved + * accounting with the existence of that block group, that is, + * space_info->bytes_may_use was incremented by a task but no + * space was yet allocated from the block group by the task. + * That space may or may not be allocated, as we are generally + * pessimistic about space reservation for metadata as well as + * for data when using compression (as we reserve space based on + * the worst case, when data can't be compressed, and before + * actually attempting compression, before starting writeback). + * + * So check if the total space of the space_info minus the size + * of this block group is less than the used space of the + * space_info - if that's the case, then it means we have tasks + * that might be relying on the block group in order to allocate + * extents, and add back the block group to the unused list when + * we finish, so that we retry later in case no tasks ended up + * needing to allocate extents from the block group. + */ + used = btrfs_space_info_used(space_info, true); + if (space_info->total_bytes - block_group->length < used && + block_group->zone_unusable < block_group->length) { + /* + * Add a reference for the list, compensate for the ref + * drop under the "next" label for the + * fs_info->unused_bgs list. + */ + btrfs_get_block_group(block_group); + list_add_tail(&block_group->bg_list, &retry_list); + + trace_btrfs_skip_unused_block_group(block_group); + spin_unlock(&block_group->lock); + spin_unlock(&space_info->lock); up_write(&space_info->groups_sem); goto next; } + spin_unlock(&block_group->lock); + spin_unlock(&space_info->lock); /* We don't want to force the issue, only flip if it's ok. */ ret = inc_block_group_ro(block_group, 0); @@ -1513,12 +1555,16 @@ next: btrfs_put_block_group(block_group); spin_lock(&fs_info->unused_bgs_lock); } + list_splice_tail(&retry_list, &fs_info->unused_bgs); spin_unlock(&fs_info->unused_bgs_lock); mutex_unlock(&fs_info->reclaim_bgs_lock); return; flip_async: btrfs_end_transaction(trans); + spin_lock(&fs_info->unused_bgs_lock); + list_splice_tail(&retry_list, &fs_info->unused_bgs); + spin_unlock(&fs_info->unused_bgs_lock); mutex_unlock(&fs_info->reclaim_bgs_lock); btrfs_put_block_group(block_group); btrfs_discard_punt_unused_bgs_list(fs_info); diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 47a2dcbfee255f5f074eef9db627721a9bd68d9b..bace40a00637970c71aedc6f8a427d9081b578a5 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -241,6 +241,13 @@ static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group) return (block_group->start + block_group->length); } +static inline bool btrfs_is_block_group_used(const struct btrfs_block_group *bg) +{ + lockdep_assert_held(&bg->lock); + + return (bg->used > 0 || bg->reserved > 0 || bg->pinned > 0); +} + static inline bool btrfs_is_block_group_data_only( struct btrfs_block_group *block_group) { diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c index 507b44d18572db551fafd968d6e5a3ee7473cbcb..4cbf386166209c99221fd2402ad8d4fd7bc55664 100644 --- a/fs/btrfs/block-rsv.c +++ b/fs/btrfs/block-rsv.c @@ -512,7 +512,7 @@ struct btrfs_block_rsv *btrfs_use_block_rsv(struct btrfs_trans_handle *trans, block_rsv = get_block_rsv(trans, root); - if (unlikely(block_rsv->size == 0)) + if (unlikely(btrfs_block_rsv_size(block_rsv) == 0)) goto try_reserve; again: ret = btrfs_block_rsv_use_bytes(block_rsv, blocksize); diff --git a/fs/btrfs/block-rsv.h b/fs/btrfs/block-rsv.h index 578c3497a455c54f6f3e0ab125d29a584b8fb9f4..df87c4949d06573aab005997f492f594994dab28 100644 --- a/fs/btrfs/block-rsv.h +++ b/fs/btrfs/block-rsv.h @@ -101,4 +101,36 @@ static inline bool btrfs_block_rsv_full(const struct btrfs_block_rsv *rsv) return data_race(rsv->full); } +/* + * Get the reserved mount of a block reserve in a context where getting a stale + * value is acceptable, instead of accessing it directly and trigger data race + * warning from KCSAN. + */ +static inline u64 btrfs_block_rsv_reserved(struct btrfs_block_rsv *rsv) +{ + u64 ret; + + spin_lock(&rsv->lock); + ret = rsv->reserved; + spin_unlock(&rsv->lock); + + return ret; +} + +/* + * Get the size of a block reserve in a context where getting a stale value is + * acceptable, instead of accessing it directly and trigger data race warning + * from KCSAN. + */ +static inline u64 btrfs_block_rsv_size(struct btrfs_block_rsv *rsv) +{ + u64 ret; + + spin_lock(&rsv->lock); + ret = rsv->size; + spin_unlock(&rsv->lock); + + return ret; +} + #endif /* BTRFS_BLOCK_RSV_H */ diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index f2bc5563c0f920458606e6da8a6c9dd92d15b5bd..63b7fa7067434efd28bd006892ea4438d78326ed 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -243,7 +243,6 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *block_rsv = &inode->block_rsv; u64 reserve_size = 0; u64 qgroup_rsv_size = 0; - u64 csum_leaves; unsigned outstanding_extents; lockdep_assert_held(&inode->lock); @@ -258,10 +257,12 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info, outstanding_extents); reserve_size += btrfs_calc_metadata_size(fs_info, 1); } - csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, - inode->csum_bytes); - reserve_size += btrfs_calc_insert_metadata_size(fs_info, - csum_leaves); + if (!(inode->flags & BTRFS_INODE_NODATASUM)) { + u64 csum_leaves; + + csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, inode->csum_bytes); + reserve_size += btrfs_calc_insert_metadata_size(fs_info, csum_leaves); + } /* * For qgroup rsv, the calculation is very simple: * account one nodesize for each outstanding extent @@ -276,14 +277,20 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info, spin_unlock(&block_rsv->lock); } -static void calc_inode_reservations(struct btrfs_fs_info *fs_info, +static void calc_inode_reservations(struct btrfs_inode *inode, u64 num_bytes, u64 disk_num_bytes, u64 *meta_reserve, u64 *qgroup_reserve) { + struct btrfs_fs_info *fs_info = inode->root->fs_info; u64 nr_extents = count_max_extents(fs_info, num_bytes); - u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes); + u64 csum_leaves; u64 inode_update = btrfs_calc_metadata_size(fs_info, 1); + if (inode->flags & BTRFS_INODE_NODATASUM) + csum_leaves = 0; + else + csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes); + *meta_reserve = btrfs_calc_insert_metadata_size(fs_info, nr_extents + csum_leaves); @@ -335,7 +342,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes, * everything out and try again, which is bad. This way we just * over-reserve slightly, and clean up the mess when we are done. */ - calc_inode_reservations(fs_info, num_bytes, disk_num_bytes, + calc_inode_reservations(inode, num_bytes, disk_num_bytes, &meta_reserve, &qgroup_reserve); ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true, noflush); @@ -356,7 +363,8 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes, spin_lock(&inode->lock); nr_extents = count_max_extents(fs_info, num_bytes); btrfs_mod_outstanding_extents(inode, nr_extents); - inode->csum_bytes += disk_num_bytes; + if (!(inode->flags & BTRFS_INODE_NODATASUM)) + inode->csum_bytes += disk_num_bytes; btrfs_calculate_inode_block_rsv_size(fs_info, inode); spin_unlock(&inode->lock); @@ -390,7 +398,8 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes, num_bytes = ALIGN(num_bytes, fs_info->sectorsize); spin_lock(&inode->lock); - inode->csum_bytes -= num_bytes; + if (!(inode->flags & BTRFS_INODE_NODATASUM)) + inode->csum_bytes -= num_bytes; btrfs_calculate_inode_block_rsv_size(fs_info, inode); spin_unlock(&inode->lock); diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index c6426080cf0adaab494c758a5b76355dcec0da18..1494ce990d298f0b58a9dffac684ad1c2e2d7de2 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1115,6 +1115,9 @@ __btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans, if (ret) return ret; + ret = btrfs_record_root_in_trans(trans, node->root); + if (ret) + return ret; ret = btrfs_update_delayed_inode(trans, node->root, path, node); return ret; } diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 61e58066b5fd2bbd6216e84b58896216d042135f..9c856a73d5333c8e3ea2944429557e57e289b638 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -740,6 +740,23 @@ leave: return ret; } +static int btrfs_check_replace_dev_names(struct btrfs_ioctl_dev_replace_args *args) +{ + if (args->start.srcdevid == 0) { + if (memchr(args->start.srcdev_name, 0, + sizeof(args->start.srcdev_name)) == NULL) + return -ENAMETOOLONG; + } else { + args->start.srcdev_name[0] = 0; + } + + if (memchr(args->start.tgtdev_name, 0, + sizeof(args->start.tgtdev_name)) == NULL) + return -ENAMETOOLONG; + + return 0; +} + int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_dev_replace_args *args) { @@ -752,10 +769,9 @@ int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info, default: return -EINVAL; } - - if ((args->start.srcdevid == 0 && args->start.srcdev_name[0] == '\0') || - args->start.tgtdev_name[0] == '\0') - return -EINVAL; + ret = btrfs_check_replace_dev_names(args); + if (ret < 0) + return ret; ret = btrfs_dev_replace_start(fs_info, args->start.tgtdev_name, args->start.srcdevid, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 40152458e7b74c472adb881336c97f539d416fa5..5756edb37c61ed3a33fae2d952add1ae15925305 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1643,12 +1643,12 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) * * @objectid: root id * @anon_dev: preallocated anonymous block device number for new roots, - * pass 0 for new allocation. + * pass NULL for a new allocation. * @check_ref: whether to check root item references, If true, return -ENOENT * for orphan roots */ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, - u64 objectid, dev_t anon_dev, + u64 objectid, dev_t *anon_dev, bool check_ref) { struct btrfs_root *root; @@ -1662,8 +1662,17 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, again: root = btrfs_lookup_fs_root(fs_info, objectid); if (root) { - /* Shouldn't get preallocated anon_dev for cached roots */ - ASSERT(!anon_dev); + /* + * Some other caller may have read out the newly inserted + * subvolume already (for things like backref walk etc). Not + * that common but still possible. In that case, we just need + * to free the anon_dev. + */ + if (unlikely(anon_dev && *anon_dev)) { + free_anon_bdev(*anon_dev); + *anon_dev = 0; + } + if (check_ref && btrfs_root_refs(&root->root_item) == 0) { btrfs_put_root(root); return ERR_PTR(-ENOENT); @@ -1683,7 +1692,7 @@ again: goto fail; } - ret = btrfs_init_fs_root(root, anon_dev); + ret = btrfs_init_fs_root(root, anon_dev ? *anon_dev : 0); if (ret) goto fail; @@ -1719,7 +1728,7 @@ fail: * root's anon_dev to 0 to avoid a double free, once by btrfs_put_root() * and once again by our caller. */ - if (anon_dev) + if (anon_dev && *anon_dev) root->anon_dev = 0; btrfs_put_root(root); return ERR_PTR(ret); @@ -1735,7 +1744,7 @@ fail: struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, u64 objectid, bool check_ref) { - return btrfs_get_root_ref(fs_info, objectid, 0, check_ref); + return btrfs_get_root_ref(fs_info, objectid, NULL, check_ref); } /* @@ -1743,11 +1752,11 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, * the anonymous block device id * * @objectid: tree objectid - * @anon_dev: if zero, allocate a new anonymous block device or use the - * parameter value + * @anon_dev: if NULL, allocate a new anonymous block device or use the + * parameter value if not NULL */ struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, - u64 objectid, dev_t anon_dev) + u64 objectid, dev_t *anon_dev) { return btrfs_get_root_ref(fs_info, objectid, anon_dev, true); } diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 7322af63c0cc7db0b7553006f13056efce407971..24bddca86e9c9e153a6c07a08ccbfa7c45139c02 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -65,7 +65,7 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info); struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, u64 objectid, bool check_ref); struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, - u64 objectid, dev_t anon_dev); + u64 objectid, dev_t *anon_dev); struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info, struct btrfs_path *path, u64 objectid); diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index fab7eb76e53b2a3e9b3f2508f4b7aa2ef9077c2f..58b0f04d7123f34537e97525a5cb5d33a7936843 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -161,8 +161,15 @@ struct dentry *btrfs_get_parent(struct dentry *child) ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto fail; + if (ret == 0) { + /* + * Key with offset of -1 found, there would have to exist an + * inode with such number or a root with such id. + */ + ret = -EUCLEAN; + goto fail; + } - BUG_ON(ret == 0); /* Key with offset of -1 found */ if (path->slots[0] == 0) { ret = -ENOENT; goto fail; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 539bc9bdcb93fc597ff3309e25391b80276632b7..5f923c9b773e046f2802d2e770e06546993c4790 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1324,19 +1324,14 @@ int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array) unsigned int last = allocated; allocated = alloc_pages_bulk_array(GFP_NOFS, nr_pages, page_array); - - if (allocated == nr_pages) - return 0; - - /* - * During this iteration, no page could be allocated, even - * though alloc_pages_bulk_array() falls back to alloc_page() - * if it could not bulk-allocate. So we must be out of memory. - */ - if (allocated == last) + if (unlikely(allocated == last)) { + /* No progress, fail and do cleanup. */ + for (int i = 0; i < allocated; i++) { + __free_page(page_array[i]); + page_array[i] = NULL; + } return -ENOMEM; - - memalloc_retry_wait(GFP_NOFS); + } } return 0; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 82f92b5652a77a476add500b0940d47d75de0709..10ded9c2be03bcbb699b51486738c74ace9fb210 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2472,7 +2472,7 @@ void btrfs_clear_delalloc_extent(struct inode *vfs_inode, */ if (bits & EXTENT_CLEAR_META_RESV && root != fs_info->tree_root) - btrfs_delalloc_release_metadata(inode, len, false); + btrfs_delalloc_release_metadata(inode, len, true); /* For sanity tests. */ if (btrfs_is_testing(fs_info)) @@ -3364,8 +3364,23 @@ out: unwritten_start += logical_len; clear_extent_uptodate(io_tree, unwritten_start, end, NULL); - /* Drop extent maps for the part of the extent we didn't write. */ - btrfs_drop_extent_map_range(inode, unwritten_start, end, false); + /* + * Drop extent maps for the part of the extent we didn't write. + * + * We have an exception here for the free_space_inode, this is + * because when we do btrfs_get_extent() on the free space inode + * we will search the commit root. If this is a new block group + * we won't find anything, and we will trip over the assert in + * writepage where we do ASSERT(em->block_start != + * EXTENT_MAP_HOLE). + * + * Theoretically we could also skip this for any NOCOW extent as + * we don't mess with the extent map tree in the NOCOW case, but + * for now simply skip this if we are the free space inode. + */ + if (!btrfs_is_free_space_inode(inode)) + btrfs_drop_extent_map_range(inode, unwritten_start, + end, false); /* * If the ordered extent had an IOERR or something else went @@ -10774,6 +10789,13 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from, if (encoded->encryption != BTRFS_ENCODED_IO_ENCRYPTION_NONE) return -EINVAL; + /* + * Compressed extents should always have checksums, so error out if we + * have a NOCOW file or inode was created while mounted with NODATASUM. + */ + if (inode->flags & BTRFS_INODE_NODATASUM) + return -EINVAL; + orig_count = iov_iter_count(from); /* The extent size must be sane. */ diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 8516c70b5edc1a079eee2659187a218764787fa1..64b37afb7c87ff040a8cd79baf67de56ea983355 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -708,7 +708,7 @@ static noinline int create_subvol(struct user_namespace *mnt_userns, free_extent_buffer(leaf); leaf = NULL; - new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev); + new_root = btrfs_get_new_fs_root(fs_info, objectid, &anon_dev); if (IS_ERR(new_root)) { ret = PTR_ERR(new_root); btrfs_abort_transaction(trans, ret); @@ -4695,6 +4695,11 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg) goto out; } + if (sa->create && is_fstree(sa->qgroupid)) { + ret = -EINVAL; + goto out; + } + trans = btrfs_join_transaction(root); if (IS_ERR(trans)) { ret = PTR_ERR(trans); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 96ec9ccc2ef612a4510c48dee546e4c36b351a2d..80ca7b435b0d11784a94b804d4c27b6d6fdb2666 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1635,6 +1635,15 @@ out: return ret; } +static bool qgroup_has_usage(struct btrfs_qgroup *qgroup) +{ + return (qgroup->rfer > 0 || qgroup->rfer_cmpr > 0 || + qgroup->excl > 0 || qgroup->excl_cmpr > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA] > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC] > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS] > 0); +} + int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) { struct btrfs_fs_info *fs_info = trans->fs_info; @@ -1654,6 +1663,11 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) goto out; } + if (is_fstree(qgroupid) && qgroup_has_usage(qgroup)) { + ret = -EBUSY; + goto out; + } + /* Check if there are no children of this qgroup */ if (!list_empty(&qgroup->members)) { ret = -EBUSY; @@ -2786,11 +2800,6 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans) goto cleanup; } - /* Free the reserved data space */ - btrfs_qgroup_free_refroot(fs_info, - record->data_rsv_refroot, - record->data_rsv, - BTRFS_QGROUP_RSV_DATA); /* * Use BTRFS_SEQ_LAST as time_seq to do special search, * which doesn't lock tree or delayed_refs and search @@ -2812,6 +2821,11 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans) record->old_roots = NULL; new_roots = NULL; } + /* Free the reserved data space */ + btrfs_qgroup_free_refroot(fs_info, + record->data_rsv_refroot, + record->data_rsv, + BTRFS_QGROUP_RSV_DATA); cleanup: ulist_free(record->old_roots); ulist_free(new_roots); @@ -4140,6 +4154,8 @@ void btrfs_qgroup_convert_reserved_meta(struct btrfs_root *root, int num_bytes) BTRFS_QGROUP_RSV_META_PREALLOC); trace_qgroup_meta_convert(root, num_bytes); qgroup_convert_meta(fs_info, root->root_key.objectid, num_bytes); + if (!sb_rdonly(fs_info->sb)) + add_root_meta_rsv(root, num_bytes, BTRFS_QGROUP_RSV_META_PERTRANS); } /* diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 1672d4846baaf63f977dd3d50289e82668d88925..12a2b1e3f1e356789c782e34520193757c780622 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -4177,7 +4177,17 @@ static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx, gen = fs_info->last_trans_committed; for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) { - bytenr = btrfs_sb_offset(i); + ret = btrfs_sb_log_location(scrub_dev, i, 0, &bytenr); + if (ret == -ENOENT) + break; + + if (ret) { + spin_lock(&sctx->stat_lock); + sctx->stat.super_errors++; + spin_unlock(&sctx->stat_lock); + continue; + } + if (bytenr + BTRFS_SUPER_INFO_SIZE > scrub_dev->commit_total_bytes) break; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 4a4d65b5e24f7450021818630b55d3e3be681a28..ec3db315f5618dd5abfd1ef4c5d59a25419cef12 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1015,7 +1015,15 @@ static int iterate_inode_ref(struct btrfs_root *root, struct btrfs_path *path, ret = PTR_ERR(start); goto out; } - BUG_ON(start < p->buf); + if (unlikely(start < p->buf)) { + btrfs_err(root->fs_info, + "send: path ref buffer underflow for key (%llu %u %llu)", + found_key->objectid, + found_key->type, + found_key->offset); + ret = -EINVAL; + goto out; + } } p->start = start; } else { @@ -6462,11 +6470,20 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end) if (ret) goto out; } - if (sctx->cur_inode_last_extent < - sctx->cur_inode_size) { - ret = send_hole(sctx, sctx->cur_inode_size); - if (ret) + if (sctx->cur_inode_last_extent < sctx->cur_inode_size) { + ret = range_is_hole_in_parent(sctx, + sctx->cur_inode_last_extent, + sctx->cur_inode_size); + if (ret < 0) { goto out; + } else if (ret == 0) { + ret = send_hole(sctx, sctx->cur_inode_size); + if (ret < 0) + goto out; + } else { + /* Range is already a hole, skip. */ + ret = 0; + } } } if (need_truncate) { @@ -7852,7 +7869,7 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg) } if (arg->flags & ~BTRFS_SEND_FLAG_MASK) { - ret = -EINVAL; + ret = -EOPNOTSUPP; goto out; } @@ -7938,8 +7955,8 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg) sctx->rbtree_new_refs = RB_ROOT; sctx->rbtree_deleted_refs = RB_ROOT; - sctx->clone_roots = kvcalloc(sizeof(*sctx->clone_roots), - arg->clone_sources_count + 1, + sctx->clone_roots = kvcalloc(arg->clone_sources_count + 1, + sizeof(*sctx->clone_roots), GFP_KERNEL); if (!sctx->clone_roots) { ret = -ENOMEM; diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 2635fb4bffa06179696da2814ec3ac481fe6be57..8b75f436a9a3c86ae92017c8703c387da970d663 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -847,7 +847,7 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info) { - u64 global_rsv_size = fs_info->global_block_rsv.reserved; + const u64 global_rsv_size = btrfs_block_rsv_reserved(&fs_info->global_block_rsv); u64 ordered, delalloc; u64 total = writable_total_bytes(fs_info, space_info); u64 thresh; @@ -948,8 +948,8 @@ static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info, ordered = percpu_counter_read_positive(&fs_info->ordered_bytes) >> 1; delalloc = percpu_counter_read_positive(&fs_info->delalloc_bytes); if (ordered >= delalloc) - used += fs_info->delayed_refs_rsv.reserved + - fs_info->delayed_block_rsv.reserved; + used += btrfs_block_rsv_reserved(&fs_info->delayed_refs_rsv) + + btrfs_block_rsv_reserved(&fs_info->delayed_block_rsv); else used += space_info->bytes_may_use - global_rsv_size; @@ -1164,7 +1164,7 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work) enum btrfs_flush_state flush; u64 delalloc_size = 0; u64 to_reclaim, block_rsv_size; - u64 global_rsv_size = global_rsv->reserved; + const u64 global_rsv_size = btrfs_block_rsv_reserved(global_rsv); loops++; @@ -1176,9 +1176,9 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work) * assume it's tied up in delalloc reservations. */ block_rsv_size = global_rsv_size + - delayed_block_rsv->reserved + - delayed_refs_rsv->reserved + - trans_rsv->reserved; + btrfs_block_rsv_reserved(delayed_block_rsv) + + btrfs_block_rsv_reserved(delayed_refs_rsv) + + btrfs_block_rsv_reserved(trans_rsv); if (block_rsv_size < space_info->bytes_may_use) delalloc_size = space_info->bytes_may_use - block_rsv_size; @@ -1198,16 +1198,16 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work) to_reclaim = delalloc_size; flush = FLUSH_DELALLOC; } else if (space_info->bytes_pinned > - (delayed_block_rsv->reserved + - delayed_refs_rsv->reserved)) { + (btrfs_block_rsv_reserved(delayed_block_rsv) + + btrfs_block_rsv_reserved(delayed_refs_rsv))) { to_reclaim = space_info->bytes_pinned; flush = COMMIT_TRANS; - } else if (delayed_block_rsv->reserved > - delayed_refs_rsv->reserved) { - to_reclaim = delayed_block_rsv->reserved; + } else if (btrfs_block_rsv_reserved(delayed_block_rsv) > + btrfs_block_rsv_reserved(delayed_refs_rsv)) { + to_reclaim = btrfs_block_rsv_reserved(delayed_block_rsv); flush = FLUSH_DELAYED_ITEMS_NR; } else { - to_reclaim = delayed_refs_rsv->reserved; + to_reclaim = btrfs_block_rsv_reserved(delayed_refs_rsv); flush = FLUSH_DELAYED_REFS_NR; } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 60db4c3b82fa1b4de938e162785a33135a3ff9a0..a7853a3a5719088e4cd2005cd2d44069aea91075 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -700,14 +700,6 @@ again: h->reloc_reserved = reloc_reserved; } - /* - * Now that we have found a transaction to be a part of, convert the - * qgroup reservation from prealloc to pertrans. A different transaction - * can't race in and free our pertrans out from under us. - */ - if (qgroup_reserved) - btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved); - got_it: if (!current->journal_info) current->journal_info = h; @@ -741,8 +733,15 @@ got_it: * not just freed. */ btrfs_end_transaction(h); - return ERR_PTR(ret); + goto reserve_fail; } + /* + * Now that we have found a transaction to be a part of, convert the + * qgroup reservation from prealloc to pertrans. A different transaction + * can't race in and free our pertrans out from under us. + */ + if (qgroup_reserved) + btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved); return h; @@ -1441,6 +1440,7 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) radix_tree_tag_clear(&fs_info->fs_roots_radix, (unsigned long)root->root_key.objectid, BTRFS_ROOT_TRANS_TAG); + btrfs_qgroup_free_meta_all_pertrans(root); spin_unlock(&fs_info->fs_roots_radix_lock); btrfs_free_log(trans, root); @@ -1465,7 +1465,6 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) if (ret2) return ret2; spin_lock(&fs_info->fs_roots_radix_lock); - btrfs_qgroup_free_meta_all_pertrans(root); } } spin_unlock(&fs_info->fs_roots_radix_lock); @@ -1809,7 +1808,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, } key.offset = (u64)-1; - pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev); + pending->snap = btrfs_get_new_fs_root(fs_info, objectid, &pending->anon_dev); if (IS_ERR(pending->snap)) { ret = PTR_ERR(pending->snap); pending->snap = NULL; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 6fc2d99270c180a4d0768cbe469ec97969f31ae3..8c7e74499ed1782de0255e20db67c849e31905f7 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1233,25 +1233,32 @@ static int open_fs_devices(struct btrfs_fs_devices *fs_devices, struct btrfs_device *device; struct btrfs_device *latest_dev = NULL; struct btrfs_device *tmp_device; + int ret = 0; flags |= FMODE_EXCL; list_for_each_entry_safe(device, tmp_device, &fs_devices->devices, dev_list) { - int ret; + int ret2; - ret = btrfs_open_one_device(fs_devices, device, flags, holder); - if (ret == 0 && + ret2 = btrfs_open_one_device(fs_devices, device, flags, holder); + if (ret2 == 0 && (!latest_dev || device->generation > latest_dev->generation)) { latest_dev = device; - } else if (ret == -ENODATA) { + } else if (ret2 == -ENODATA) { fs_devices->num_devices--; list_del(&device->dev_list); btrfs_free_device(device); } + if (ret == 0 && ret2 != 0) + ret = ret2; } - if (fs_devices->open_devices == 0) + + if (fs_devices->open_devices == 0) { + if (ret) + return ret; return -EINVAL; + } fs_devices->opened = 1; fs_devices->latest_dev = latest_dev; @@ -1444,7 +1451,7 @@ static bool contains_pending_extent(struct btrfs_device *device, u64 *start, if (in_range(physical_start, *start, len) || in_range(*start, physical_start, - physical_end - physical_start)) { + physical_end + 1 - physical_start)) { *start = physical_end + 1; return true; } @@ -3381,7 +3388,18 @@ again: mutex_unlock(&fs_info->reclaim_bgs_lock); goto error; } - BUG_ON(ret == 0); /* Corruption */ + if (ret == 0) { + /* + * On the first search we would find chunk tree with + * offset -1, which is not possible. On subsequent + * loops this would find an existing item on an invalid + * offset (one less than the previous one, wrong + * alignment and size). + */ + ret = -EUCLEAN; + mutex_unlock(&fs_info->reclaim_bgs_lock); + goto error; + } ret = btrfs_previous_item(chunk_root, path, key.objectid, key.type); diff --git a/fs/cachefiles/cache.c b/fs/cachefiles/cache.c index 7077f72e6f4747c2a1f1bd6c898221d4bdaab380..f449f7340aad0811ae2cea3134731e1a2111f5ff 100644 --- a/fs/cachefiles/cache.c +++ b/fs/cachefiles/cache.c @@ -168,6 +168,8 @@ error_unsupported: dput(root); error_open_root: cachefiles_end_secure(cache, saved_cred); + put_cred(cache->cache_cred); + cache->cache_cred = NULL; error_getsec: fscache_relinquish_cache(cache_cookie); cache->cache = NULL; diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index aa4efcabb5e37b155407e724d22572c34fde1d3f..5f4df9588620ffc55eb94cc03d3e58faa3ca7fe3 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -805,6 +805,7 @@ static void cachefiles_daemon_unbind(struct cachefiles_cache *cache) cachefiles_put_directory(cache->graveyard); cachefiles_put_directory(cache->store); mntput(cache->mnt); + put_cred(cache->cache_cred); kfree(cache->rootdirname); kfree(cache->secctx); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 111938a6307e66bdc5d4f38d535483ac9d3704c4..57603782e7e2a698c7da9728a93b9cd97805a648 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1391,7 +1391,7 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap, if (flushing & CEPH_CAP_XATTR_EXCL) { arg->old_xattr_buf = __ceph_build_xattrs_blob(ci); arg->xattr_version = ci->i_xattrs.version; - arg->xattr_buf = ci->i_xattrs.blob; + arg->xattr_buf = ceph_buffer_get(ci->i_xattrs.blob); } else { arg->xattr_buf = NULL; arg->old_xattr_buf = NULL; @@ -1457,6 +1457,7 @@ static void __send_cap(struct cap_msg_args *arg, struct ceph_inode_info *ci) encode_cap_msg(msg, arg); ceph_con_send(&arg->session->s_con, msg); ceph_buffer_put(arg->old_xattr_buf); + ceph_buffer_put(arg->xattr_buf); if (arg->wake) wake_up_all(&ci->i_cap_wq); } diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 3fbabc98e1f702a90ea75ce6d4f7c5f9fb7b4a16..4a089d70ebd0761444b5578512c3f51587e315c5 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -379,10 +379,11 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2) ceph_decode_skip_8(p, end, bad_ext); /* required_client_features */ ceph_decode_skip_set(p, end, 64, bad_ext); + /* bal_rank_mask */ + ceph_decode_skip_string(p, end, bad_ext); + } + if (mdsmap_ev >= 18) { ceph_decode_64_safe(p, end, m->m_max_xattr_size, bad_ext); - } else { - /* This forces the usage of the (sync) SETXATTR Op */ - m->m_max_xattr_size = 0; } bad_ext: dout("mdsmap_decode m_enabled: %d, m_damaged: %d, m_num_laggy: %d\n", diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 72f34f96d015594cd98f99b1533782b2a0762328..2c797eb519da97049410545d33f7a64889ec25a3 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -174,7 +174,7 @@ static LIST_HEAD(dlm_node_addrs); static DEFINE_SPINLOCK(dlm_node_addrs_spin); static struct listen_connection listen_con; -static struct sockaddr_storage *dlm_local_addr[DLM_MAX_ADDR_COUNT]; +static struct sockaddr_storage dlm_local_addr[DLM_MAX_ADDR_COUNT]; static int dlm_local_count; int dlm_allow_conn; @@ -398,7 +398,7 @@ static int nodeid_to_addr(int nodeid, struct sockaddr_storage *sas_out, if (!sa_out) return 0; - if (dlm_local_addr[0]->ss_family == AF_INET) { + if (dlm_local_addr[0].ss_family == AF_INET) { struct sockaddr_in *in4 = (struct sockaddr_in *) &sas; struct sockaddr_in *ret4 = (struct sockaddr_in *) sa_out; ret4->sin_addr.s_addr = in4->sin_addr.s_addr; @@ -727,7 +727,7 @@ static void add_sock(struct socket *sock, struct connection *con) static void make_sockaddr(struct sockaddr_storage *saddr, uint16_t port, int *addr_len) { - saddr->ss_family = dlm_local_addr[0]->ss_family; + saddr->ss_family = dlm_local_addr[0].ss_family; if (saddr->ss_family == AF_INET) { struct sockaddr_in *in4_addr = (struct sockaddr_in *)saddr; in4_addr->sin_port = cpu_to_be16(port); @@ -1167,7 +1167,7 @@ static int sctp_bind_addrs(struct socket *sock, uint16_t port) int i, addr_len, result = 0; for (i = 0; i < dlm_local_count; i++) { - memcpy(&localaddr, dlm_local_addr[i], sizeof(localaddr)); + memcpy(&localaddr, &dlm_local_addr[i], sizeof(localaddr)); make_sockaddr(&localaddr, port, &addr_len); if (!i) @@ -1187,7 +1187,7 @@ static int sctp_bind_addrs(struct socket *sock, uint16_t port) /* Get local addresses */ static void init_local(void) { - struct sockaddr_storage sas, *addr; + struct sockaddr_storage sas; int i; dlm_local_count = 0; @@ -1195,21 +1195,10 @@ static void init_local(void) if (dlm_our_addr(&sas, i)) break; - addr = kmemdup(&sas, sizeof(*addr), GFP_NOFS); - if (!addr) - break; - dlm_local_addr[dlm_local_count++] = addr; + memcpy(&dlm_local_addr[dlm_local_count++], &sas, sizeof(sas)); } } -static void deinit_local(void) -{ - int i; - - for (i = 0; i < dlm_local_count; i++) - kfree(dlm_local_addr[i]); -} - static struct writequeue_entry *new_writequeue_entry(struct connection *con) { struct writequeue_entry *entry; @@ -1575,7 +1564,7 @@ static void dlm_connect(struct connection *con) } /* Create a socket to communicate with */ - result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family, + result = sock_create_kern(&init_net, dlm_local_addr[0].ss_family, SOCK_STREAM, dlm_proto_ops->proto, &sock); if (result < 0) goto socket_err; @@ -1786,7 +1775,6 @@ void dlm_lowcomms_stop(void) foreach_conn(free_conn); srcu_read_unlock(&connections_srcu, idx); work_stop(); - deinit_local(); dlm_proto_ops = NULL; } @@ -1803,7 +1791,7 @@ static int dlm_listen_for_all(void) if (result < 0) return result; - result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family, + result = sock_create_kern(&init_net, dlm_local_addr[0].ss_family, SOCK_STREAM, dlm_proto_ops->proto, &sock); if (result < 0) { log_print("Can't create comms socket: %d", result); @@ -1842,7 +1830,7 @@ static int dlm_tcp_bind(struct socket *sock) /* Bind to our cluster-known address connecting to avoid * routing problems. */ - memcpy(&src_addr, dlm_local_addr[0], sizeof(src_addr)); + memcpy(&src_addr, &dlm_local_addr[0], sizeof(src_addr)); make_sockaddr(&src_addr, 0, &addr_len); result = kernel_bind(sock, (struct sockaddr *)&src_addr, @@ -1899,9 +1887,9 @@ static int dlm_tcp_listen_bind(struct socket *sock) int addr_len; /* Bind to our port */ - make_sockaddr(dlm_local_addr[0], dlm_config.ci_tcp_port, &addr_len); + make_sockaddr(&dlm_local_addr[0], dlm_config.ci_tcp_port, &addr_len); return kernel_bind(sock, (struct sockaddr *)&dlm_local_addr[0], - addr_len); + addr_len); } static const struct dlm_proto_ops dlm_tcp_ops = { @@ -1992,7 +1980,7 @@ int dlm_lowcomms_start(void) error = work_start(); if (error) - goto fail_local; + goto fail; dlm_allow_conn = 1; @@ -2022,8 +2010,6 @@ fail_listen: fail_proto_ops: dlm_allow_conn = 0; work_stop(); -fail_local: - deinit_local(); fail: return error; } diff --git a/fs/efivarfs/vars.c b/fs/efivarfs/vars.c index 9e4f47808bd5ad6a3d0cc390623330089968af3a..13bc6069895571e75827da9d825760b1f0a50528 100644 --- a/fs/efivarfs/vars.c +++ b/fs/efivarfs/vars.c @@ -372,7 +372,7 @@ static void dup_variable_bug(efi_char16_t *str16, efi_guid_t *vendor_guid, int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), void *data, bool duplicates, struct list_head *head) { - unsigned long variable_name_size = 1024; + unsigned long variable_name_size = 512; efi_char16_t *variable_name; efi_status_t status; efi_guid_t vendor_guid; @@ -389,12 +389,13 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), goto free; /* - * Per EFI spec, the maximum storage allocated for both - * the variable name and variable data is 1024 bytes. + * A small set of old UEFI implementations reject sizes + * above a certain threshold, the lowest seen in the wild + * is 512. */ do { - variable_name_size = 1024; + variable_name_size = 512; status = efivar_get_next_variable(&variable_name_size, variable_name, @@ -431,9 +432,13 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), break; case EFI_NOT_FOUND: break; + case EFI_BUFFER_TOO_SMALL: + pr_warn("efivars: Variable name size exceeds maximum (%lu > 512)\n", + variable_name_size); + status = EFI_NOT_FOUND; + break; default: - printk(KERN_WARNING "efivars: get_next_variable: status=%lx\n", - status); + pr_warn("efivars: get_next_variable: status=%lx\n", status); status = EFI_NOT_FOUND; break; } diff --git a/fs/erofs/compress.h b/fs/erofs/compress.h index 26fa170090b8fb8c04c4463bbee4242c0e3d3c88..c4a3187bdb8fce69aff0a8fc38fb25fb12ee2167 100644 --- a/fs/erofs/compress.h +++ b/fs/erofs/compress.h @@ -21,6 +21,8 @@ struct z_erofs_decompress_req { }; struct z_erofs_decompressor { + int (*config)(struct super_block *sb, struct erofs_super_block *dsb, + void *data, int size); int (*decompress)(struct z_erofs_decompress_req *rq, struct page **pagepool); char *name; @@ -93,6 +95,8 @@ int z_erofs_decompress(struct z_erofs_decompress_req *rq, struct page **pagepool); /* prototypes for specific algorithms */ +int z_erofs_load_lzma_config(struct super_block *sb, + struct erofs_super_block *dsb, void *data, int size); int z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq, struct page **pagepool); #endif diff --git a/fs/erofs/data.c b/fs/erofs/data.c index b32801d716f8982a0b7df96ca77c6cc9f0c809ee..9d20e5d23ae0bd8a495fb30d0333b62f6f55398b 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -440,4 +440,5 @@ const struct file_operations erofs_file_fops = { .read_iter = erofs_file_read_iter, .mmap = erofs_file_mmap, .splice_read = generic_file_splice_read, + .get_unmapped_area = thp_get_unmapped_area, }; diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index 0cfad74374ca9cce0a1a71bce3f6a6525110363f..1eefa4411e066374021fb7cd53e6a7f04ee3dde5 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -24,11 +24,11 @@ struct z_erofs_lz4_decompress_ctx { unsigned int oend; }; -int z_erofs_load_lz4_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lz4_cfgs *lz4, int size) +static int z_erofs_load_lz4_config(struct super_block *sb, + struct erofs_super_block *dsb, void *data, int size) { struct erofs_sb_info *sbi = EROFS_SB(sb); + struct z_erofs_lz4_cfgs *lz4 = data; u16 distance; if (lz4) { @@ -374,17 +374,71 @@ static struct z_erofs_decompressor decompressors[] = { .name = "interlaced" }, [Z_EROFS_COMPRESSION_LZ4] = { + .config = z_erofs_load_lz4_config, .decompress = z_erofs_lz4_decompress, .name = "lz4" }, #ifdef CONFIG_EROFS_FS_ZIP_LZMA [Z_EROFS_COMPRESSION_LZMA] = { + .config = z_erofs_load_lzma_config, .decompress = z_erofs_lzma_decompress, .name = "lzma" }, #endif }; +int z_erofs_parse_cfgs(struct super_block *sb, struct erofs_super_block *dsb) +{ + struct erofs_sb_info *sbi = EROFS_SB(sb); + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; + unsigned int algs, alg; + erofs_off_t offset; + int size, ret = 0; + + if (!erofs_sb_has_compr_cfgs(sbi)) { + sbi->available_compr_algs = 1 << Z_EROFS_COMPRESSION_LZ4; + return z_erofs_load_lz4_config(sb, dsb, NULL, 0); + } + + sbi->available_compr_algs = le16_to_cpu(dsb->u1.available_compr_algs); + if (sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS) { + erofs_err(sb, "unidentified algorithms %x, please upgrade kernel", + sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS); + return -EOPNOTSUPP; + } + + offset = EROFS_SUPER_OFFSET + sbi->sb_size; + alg = 0; + for (algs = sbi->available_compr_algs; algs; algs >>= 1, ++alg) { + void *data; + + if (!(algs & 1)) + continue; + + data = erofs_read_metadata(sb, &buf, &offset, &size); + if (IS_ERR(data)) { + ret = PTR_ERR(data); + break; + } + + if (alg >= ARRAY_SIZE(decompressors) || + !decompressors[alg].config) { + erofs_err(sb, "algorithm %d isn't enabled on this kernel", + alg); + ret = -EOPNOTSUPP; + } else { + ret = decompressors[alg].config(sb, + dsb, data, size); + } + + kfree(data); + if (ret) + break; + } + erofs_put_metabuf(&buf); + return ret; +} + int z_erofs_decompress(struct z_erofs_decompress_req *rq, struct page **pagepool) { diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c index 49addc345aebea0c868e9aab7767073b0e496278..970464c4b6769f906f18bb4f6b71c6dd2cdaa1fa 100644 --- a/fs/erofs/decompressor_lzma.c +++ b/fs/erofs/decompressor_lzma.c @@ -72,10 +72,10 @@ int z_erofs_lzma_init(void) } int z_erofs_load_lzma_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lzma_cfgs *lzma, int size) + struct erofs_super_block *dsb, void *data, int size) { static DEFINE_MUTEX(lzma_resize_mutex); + struct z_erofs_lzma_cfgs *lzma = data; unsigned int dict_size, i; struct z_erofs_lzma *strm, *head = NULL; int err; diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index d8d09fc3ed655c363d81c5b05e7f805139531e4f..79a7a5815ea63642eecb2d83d32ef1d435a42332 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -471,6 +471,8 @@ struct erofs_map_dev { /* data.c */ extern const struct file_operations erofs_file_fops; +void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, + erofs_off_t *offset, int *lengthp); void erofs_unmap_metabuf(struct erofs_buf *buf); void erofs_put_metabuf(struct erofs_buf *buf); void *erofs_bread(struct erofs_buf *buf, struct inode *inode, @@ -565,9 +567,7 @@ void z_erofs_exit_zip_subsystem(void); int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi, struct erofs_workgroup *egrp); int erofs_try_to_free_cached_page(struct page *page); -int z_erofs_load_lz4_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lz4_cfgs *lz4, int len); +int z_erofs_parse_cfgs(struct super_block *sb, struct erofs_super_block *dsb); #else static inline void erofs_shrinker_register(struct super_block *sb) {} static inline void erofs_shrinker_unregister(struct super_block *sb) {} @@ -575,36 +575,14 @@ static inline int erofs_init_shrinker(void) { return 0; } static inline void erofs_exit_shrinker(void) {} static inline int z_erofs_init_zip_subsystem(void) { return 0; } static inline void z_erofs_exit_zip_subsystem(void) {} -static inline int z_erofs_load_lz4_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lz4_cfgs *lz4, int len) -{ - if (lz4 || dsb->u1.lz4_max_distance) { - erofs_err(sb, "lz4 algorithm isn't enabled"); - return -EINVAL; - } - return 0; -} #endif /* !CONFIG_EROFS_FS_ZIP */ #ifdef CONFIG_EROFS_FS_ZIP_LZMA int z_erofs_lzma_init(void); void z_erofs_lzma_exit(void); -int z_erofs_load_lzma_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lzma_cfgs *lzma, int size); #else static inline int z_erofs_lzma_init(void) { return 0; } static inline int z_erofs_lzma_exit(void) { return 0; } -static inline int z_erofs_load_lzma_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lzma_cfgs *lzma, int size) { - if (lzma) { - erofs_err(sb, "lzma algorithm isn't enabled"); - return -EINVAL; - } - return 0; -} #endif /* !CONFIG_EROFS_FS_ZIP */ /* flags for erofs_fscache_register_cookie() */ diff --git a/fs/erofs/namei.c b/fs/erofs/namei.c index 0dc34721080c7f5b312f92d4e1cc3dde6ecb98cc..e8ccaa761bd635e27f7e142bbd154a6c71cdee9e 100644 --- a/fs/erofs/namei.c +++ b/fs/erofs/namei.c @@ -137,24 +137,24 @@ static void *find_target_block_classic(struct erofs_buf *target, /* string comparison without already matched prefix */ diff = erofs_dirnamecmp(name, &dname, &matched); - if (!diff) { - *_ndirents = 0; - goto out; - } else if (diff > 0) { - head = mid + 1; - startprfx = matched; - - if (!IS_ERR(candidate)) - erofs_put_metabuf(target); - *target = buf; - candidate = de; - *_ndirents = ndirents; - } else { + if (diff < 0) { erofs_put_metabuf(&buf); - back = mid - 1; endprfx = matched; + continue; + } + + if (!IS_ERR(candidate)) + erofs_put_metabuf(target); + *target = buf; + if (!diff) { + *_ndirents = 0; + return de; } + head = mid + 1; + startprfx = matched; + candidate = de; + *_ndirents = ndirents; continue; } out: /* free if the candidate is valid */ diff --git a/fs/erofs/super.c b/fs/erofs/super.c index bd8bf8fc2f5dfe46cb5b411f86579bae9ff55ff9..f2647126cb2fbc40bc81af726d1eb4b4356e6ca5 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -126,8 +126,8 @@ static bool check_layout_compatibility(struct super_block *sb, #ifdef CONFIG_EROFS_FS_ZIP /* read variable-sized metadata, offset will be aligned by 4-byte */ -static void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, - erofs_off_t *offset, int *lengthp) +void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, + erofs_off_t *offset, int *lengthp) { u8 *buffer, *ptr; int len, i, cnt; @@ -159,64 +159,15 @@ static void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, } return buffer; } - -static int erofs_load_compr_cfgs(struct super_block *sb, - struct erofs_super_block *dsb) -{ - struct erofs_sb_info *sbi = EROFS_SB(sb); - struct erofs_buf buf = __EROFS_BUF_INITIALIZER; - unsigned int algs, alg; - erofs_off_t offset; - int size, ret = 0; - - sbi->available_compr_algs = le16_to_cpu(dsb->u1.available_compr_algs); - if (sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS) { - erofs_err(sb, "try to load compressed fs with unsupported algorithms %x", - sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS); - return -EINVAL; - } - - offset = EROFS_SUPER_OFFSET + sbi->sb_size; - alg = 0; - for (algs = sbi->available_compr_algs; algs; algs >>= 1, ++alg) { - void *data; - - if (!(algs & 1)) - continue; - - data = erofs_read_metadata(sb, &buf, &offset, &size); - if (IS_ERR(data)) { - ret = PTR_ERR(data); - break; - } - - switch (alg) { - case Z_EROFS_COMPRESSION_LZ4: - ret = z_erofs_load_lz4_config(sb, dsb, data, size); - break; - case Z_EROFS_COMPRESSION_LZMA: - ret = z_erofs_load_lzma_config(sb, dsb, data, size); - break; - default: - DBG_BUGON(1); - ret = -EFAULT; - } - kfree(data); - if (ret) - break; - } - erofs_put_metabuf(&buf); - return ret; -} #else -static int erofs_load_compr_cfgs(struct super_block *sb, - struct erofs_super_block *dsb) +static int z_erofs_parse_cfgs(struct super_block *sb, + struct erofs_super_block *dsb) { - if (dsb->u1.available_compr_algs) { - erofs_err(sb, "try to load compressed fs when compression is disabled"); - return -EINVAL; - } - return 0; + if (!dsb->u1.available_compr_algs) + return 0; + + erofs_err(sb, "compression disabled, unable to mount compressed EROFS"); + return -EOPNOTSUPP; } #endif @@ -398,10 +349,7 @@ static int erofs_read_superblock(struct super_block *sb) } /* parse on-disk compression configurations */ - if (erofs_sb_has_compr_cfgs(sbi)) - ret = erofs_load_compr_cfgs(sb, dsb); - else - ret = z_erofs_load_lz4_config(sb, dsb, NULL, 0); + ret = z_erofs_parse_cfgs(sb, dsb); if (ret < 0) goto out; diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 0337b70b2dac40622a84bc18553cc75b62bd9c50..abcded1acd1949414d1d73d595e792eacda8fcc3 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -610,7 +610,7 @@ static int z_erofs_do_map_blocks(struct inode *inode, .map = map, }; int err = 0; - unsigned int lclusterbits, endoff; + unsigned int lclusterbits, endoff, afmt; unsigned long initial_lcn; unsigned long long ofs, end; @@ -700,17 +700,20 @@ static int z_erofs_do_map_blocks(struct inode *inode, err = -EFSCORRUPTED; goto unmap_out; } - if (vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER) - map->m_algorithmformat = - Z_EROFS_COMPRESSION_INTERLACED; - else - map->m_algorithmformat = - Z_EROFS_COMPRESSION_SHIFTED; - } else if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2) { - map->m_algorithmformat = vi->z_algorithmtype[1]; + afmt = vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER ? + Z_EROFS_COMPRESSION_INTERLACED : + Z_EROFS_COMPRESSION_SHIFTED; } else { - map->m_algorithmformat = vi->z_algorithmtype[0]; + afmt = m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2 ? + vi->z_algorithmtype[1] : vi->z_algorithmtype[0]; + if (!(EROFS_I_SB(inode)->available_compr_algs & (1 << afmt))) { + erofs_err(inode->i_sb, "inconsistent algorithmtype %u for nid %llu", + afmt, vi->nid); + err = -EFSCORRUPTED; + goto unmap_out; + } } + map->m_algorithmformat = afmt; if ((flags & EROFS_GET_BLOCKS_FIEMAP) || ((flags & EROFS_GET_BLOCKS_READMORE) && diff --git a/fs/exec.c b/fs/exec.c index 39f7751c90fc31011ede1415353457566895987b..b01434d6a512de16e480b70145f83e81730406f6 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -896,6 +896,7 @@ int transfer_args_to_stack(struct linux_binprm *bprm, goto out; } + bprm->exec += *sp_location - MAX_ARG_PAGES * PAGE_SIZE; *sp_location = sp; out: diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index c648a493faf23865780924ece6dceda506d75152..3204bd33e4e8a45f4fef150e651834d5e15cf607 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -18,7 +18,7 @@ #include #include -#define dprintk(fmt, args...) do{}while(0) +#define dprintk(fmt, args...) pr_debug(fmt, ##args) static int get_name(const struct path *path, char *name, struct dentry *child); @@ -132,8 +132,8 @@ static struct dentry *reconnect_one(struct vfsmount *mnt, inode_unlock(dentry->d_inode); if (IS_ERR(parent)) { - dprintk("%s: get_parent of %ld failed, err %d\n", - __func__, dentry->d_inode->i_ino, PTR_ERR(parent)); + dprintk("get_parent of %lu failed, err %ld\n", + dentry->d_inode->i_ino, PTR_ERR(parent)); return parent; } @@ -147,7 +147,7 @@ static struct dentry *reconnect_one(struct vfsmount *mnt, dprintk("%s: found name: %s\n", __func__, nbuf); tmp = lookup_one_unlocked(mnt_user_ns(mnt), nbuf, parent, strlen(nbuf)); if (IS_ERR(tmp)) { - dprintk("%s: lookup failed: %d\n", __func__, PTR_ERR(tmp)); + dprintk("lookup failed: %ld\n", PTR_ERR(tmp)); err = PTR_ERR(tmp); goto out_err; } diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index aa5aadd70bbc2aa0e4bd6afdccdd5b24ad9b70d2..67af684e44e6ea76d31a85e6f1e55e7646533bbd 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2229,7 +2229,7 @@ static int ext4_fill_es_cache_info(struct inode *inode, /* - * ext4_ext_determine_hole - determine hole around given block + * ext4_ext_find_hole - find hole around given block according to the given path * @inode: inode we lookup in * @path: path in extent tree to @lblk * @lblk: pointer to logical block around which we want to determine hole @@ -2241,9 +2241,9 @@ static int ext4_fill_es_cache_info(struct inode *inode, * The function returns the length of a hole starting at @lblk. We update @lblk * to the beginning of the hole if we managed to find it. */ -static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode, - struct ext4_ext_path *path, - ext4_lblk_t *lblk) +static ext4_lblk_t ext4_ext_find_hole(struct inode *inode, + struct ext4_ext_path *path, + ext4_lblk_t *lblk) { int depth = ext_depth(inode); struct ext4_extent *ex; @@ -2270,30 +2270,6 @@ static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode, return len; } -/* - * ext4_ext_put_gap_in_cache: - * calculate boundaries of the gap that the requested block fits into - * and cache this gap - */ -static void -ext4_ext_put_gap_in_cache(struct inode *inode, ext4_lblk_t hole_start, - ext4_lblk_t hole_len) -{ - struct extent_status es; - - ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start, - hole_start + hole_len - 1, &es); - if (es.es_len) { - /* There's delayed extent containing lblock? */ - if (es.es_lblk <= hole_start) - return; - hole_len = min(es.es_lblk - hole_start, hole_len); - } - ext_debug(inode, " -> %u:%u\n", hole_start, hole_len); - ext4_es_insert_extent(inode, hole_start, hole_len, ~0, - EXTENT_STATUS_HOLE); -} - /* * ext4_ext_rm_idx: * removes index from the index block. @@ -4064,6 +4040,69 @@ static int get_implied_cluster_alloc(struct super_block *sb, return 0; } +/* + * Determine hole length around the given logical block, first try to + * locate and expand the hole from the given @path, and then adjust it + * if it's partially or completely converted to delayed extents, insert + * it into the extent cache tree if it's indeed a hole, finally return + * the length of the determined extent. + */ +static ext4_lblk_t ext4_ext_determine_insert_hole(struct inode *inode, + struct ext4_ext_path *path, + ext4_lblk_t lblk) +{ + ext4_lblk_t hole_start, len; + struct extent_status es; + + hole_start = lblk; + len = ext4_ext_find_hole(inode, path, &hole_start); +again: + ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start, + hole_start + len - 1, &es); + if (!es.es_len) + goto insert_hole; + + /* + * There's a delalloc extent in the hole, handle it if the delalloc + * extent is in front of, behind and straddle the queried range. + */ + if (lblk >= es.es_lblk + es.es_len) { + /* + * The delalloc extent is in front of the queried range, + * find again from the queried start block. + */ + len -= lblk - hole_start; + hole_start = lblk; + goto again; + } else if (in_range(lblk, es.es_lblk, es.es_len)) { + /* + * The delalloc extent containing lblk, it must have been + * added after ext4_map_blocks() checked the extent status + * tree, adjust the length to the delalloc extent's after + * lblk. + */ + len = es.es_lblk + es.es_len - lblk; + return len; + } else { + /* + * The delalloc extent is partially or completely behind + * the queried range, update hole length until the + * beginning of the delalloc extent. + */ + len = min(es.es_lblk - hole_start, len); + } + +insert_hole: + /* Put just found gap into cache to speed up subsequent requests */ + ext_debug(inode, " -> %u:%u\n", hole_start, len); + ext4_es_insert_extent(inode, hole_start, len, ~0, EXTENT_STATUS_HOLE); + + /* Update hole_len to reflect hole size after lblk */ + if (hole_start != lblk) + len -= lblk - hole_start; + + return len; +} /* * Block allocation/map/preallocation routine for extents based files @@ -4181,22 +4220,12 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, * we couldn't try to create block if create flag is zero */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { - ext4_lblk_t hole_start, hole_len; + ext4_lblk_t len; - hole_start = map->m_lblk; - hole_len = ext4_ext_determine_hole(inode, path, &hole_start); - /* - * put just found gap into cache to speed up - * subsequent requests - */ - ext4_ext_put_gap_in_cache(inode, hole_start, hole_len); + len = ext4_ext_determine_insert_hole(inode, path, map->m_lblk); - /* Update hole_len to reflect hole size after map->m_lblk */ - if (hole_start != map->m_lblk) - hole_len -= map->m_lblk - hole_start; map->m_pblk = 0; - map->m_len = min_t(unsigned int, map->m_len, hole_len); - + map->m_len = min_t(unsigned int, map->m_len, len); goto out; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index c1515daf1def1bccc33388c0859b8ecc9113c227..a843f964332c28adffe04d5916e9b981b82b81b1 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -831,7 +831,7 @@ mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp) struct ext4_sb_info *sbi = EXT4_SB(sb); int new_order; - if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_free == 0) + if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_fragments == 0) return; new_order = mb_avg_fragment_size_order(sb, @@ -1118,6 +1118,24 @@ void ext4_mb_generate_buddy(struct super_block *sb, atomic64_add(period, &sbi->s_mb_generation_time); } +static void mb_regenerate_buddy(struct ext4_buddy *e4b) +{ + int count; + int order = 1; + void *buddy; + + while ((buddy = mb_find_buddy(e4b, order++, &count))) + mb_set_bits(buddy, 0, count); + + e4b->bd_info->bb_fragments = 0; + memset(e4b->bd_info->bb_counters, 0, + sizeof(*e4b->bd_info->bb_counters) * + (e4b->bd_sb->s_blocksize_bits + 2)); + + ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy, + e4b->bd_bitmap, e4b->bd_group, e4b->bd_info); +} + /* The buddy information is attached the buddy cache inode * for convenience. The information regarding each group * is loaded via ext4_mb_load_buddy. The information involve @@ -1767,11 +1785,6 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, mb_check_buddy(e4b); mb_free_blocks_double(inode, e4b, first, count); - this_cpu_inc(discard_pa_seq); - e4b->bd_info->bb_free += count; - if (first < e4b->bd_info->bb_first_free) - e4b->bd_info->bb_first_free = first; - /* access memory sequentially: check left neighbour, * clear range and then check right neighbour */ @@ -1785,21 +1798,31 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t blocknr; + /* + * Fastcommit replay can free already freed blocks which + * corrupts allocation info. Regenerate it. + */ + if (sbi->s_mount_state & EXT4_FC_REPLAY) { + mb_regenerate_buddy(e4b); + goto check; + } + blocknr = ext4_group_first_block_no(sb, e4b->bd_group); blocknr += EXT4_C2B(sbi, block); - if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { - ext4_grp_locked_error(sb, e4b->bd_group, - inode ? inode->i_ino : 0, - blocknr, - "freeing already freed block (bit %u); block bitmap corrupt.", - block); - ext4_mark_group_bitmap_corrupted( - sb, e4b->bd_group, + ext4_grp_locked_error(sb, e4b->bd_group, + inode ? inode->i_ino : 0, blocknr, + "freeing already freed block (bit %u); block bitmap corrupt.", + block); + ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); - } - goto done; + return; } + this_cpu_inc(discard_pa_seq); + e4b->bd_info->bb_free += count; + if (first < e4b->bd_info->bb_first_free) + e4b->bd_info->bb_first_free = first; + /* let's maintain fragments counter */ if (left_is_free && right_is_free) e4b->bd_info->bb_fragments--; @@ -1824,9 +1847,9 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, if (first <= last) mb_buddy_mark_free(e4b, first >> 1, last >> 1); -done: mb_set_largest_free_order(sb, e4b->bd_info); mb_update_avg_fragment_size(sb, e4b->bd_info); +check: mb_check_buddy(e4b); } @@ -2153,6 +2176,9 @@ int ext4_mb_try_best_found(struct ext4_allocation_context *ac, return err; ext4_lock_group(ac->ac_sb, group); + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) + goto out; + max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex); if (max > 0) { @@ -2160,6 +2186,7 @@ int ext4_mb_try_best_found(struct ext4_allocation_context *ac, ext4_mb_use_best_found(ac, e4b); } +out: ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); @@ -2188,12 +2215,10 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, if (err) return err; - if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) { - ext4_mb_unload_buddy(e4b); - return 0; - } - ext4_lock_group(ac->ac_sb, group); + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) + goto out; + max = mb_find_extent(e4b, ac->ac_g_ex.fe_start, ac->ac_g_ex.fe_len, &ex); ex.fe_logical = 0xDEADFA11; /* debug value */ @@ -2226,6 +2251,7 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } +out: ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); @@ -2879,7 +2905,10 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) for (i = 0; i <= 13; i++) seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ? sg.info.bb_counters[i] : 0); - seq_puts(seq, " ]\n"); + seq_puts(seq, " ]"); + if (EXT4_MB_GRP_BBITMAP_CORRUPT(&sg.info)) + seq_puts(seq, " Block bitmap corrupted!"); + seq_puts(seq, "\n"); return 0; } @@ -4658,10 +4687,16 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) .fe_len = ac->ac_g_ex.fe_len, }; loff_t orig_goal_end = extent_logical_end(sbi, &ex); + loff_t o_ex_end = extent_logical_end(sbi, &ac->ac_o_ex); - /* we can't allocate as much as normalizer wants. - * so, found space must get proper lstart - * to cover original request */ + /* + * We can't allocate as much as normalizer wants, so we try + * to get proper lstart to cover the original request, except + * when the goal doesn't cover the original request as below: + * + * orig_ex:2045/2055(10), isize:8417280 -> normalized:0/2048 + * best_ex:0/200(200) -> adjusted: 1848/2048(200) + */ BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical); BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len); @@ -4673,7 +4708,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) * 1. Check if best ex can be kept at end of goal and still * cover original start * 2. Else, check if best ex can be kept at start of goal and - * still cover original start + * still cover original end * 3. Else, keep the best ex at start of original request. */ ex.fe_len = ac->ac_b_ex.fe_len; @@ -4683,7 +4718,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) goto adjust_bex; ex.fe_logical = ac->ac_g_ex.fe_logical; - if (ac->ac_o_ex.fe_logical < extent_logical_end(sbi, &ex)) + if (o_ex_end <= extent_logical_end(sbi, &ex)) goto adjust_bex; ex.fe_logical = ac->ac_o_ex.fe_logical; @@ -4691,7 +4726,6 @@ adjust_bex: ac->ac_b_ex.fe_logical = ex.fe_logical; BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical); - BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len); BUG_ON(extent_logical_end(sbi, &ex) > orig_goal_end); } diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index dedc9d445f24337476b5a47cb67addec0d44851d..8e3ff150bc36b19f57190a6e62128b3cd3d23dd3 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -621,6 +621,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, goto out; o_end = o_start + len; + *moved_len = 0; while (o_start < o_end) { struct ext4_extent *ex; ext4_lblk_t cur_blk, next_blk; @@ -675,7 +676,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, */ ext4_double_up_write_data_sem(orig_inode, donor_inode); /* Swap original branches with new branches */ - move_extent_per_page(o_filp, donor_inode, + *moved_len += move_extent_per_page(o_filp, donor_inode, orig_page_index, donor_page_index, offset_in_page, cur_len, unwritten, &ret); @@ -685,9 +686,6 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, o_start += cur_len; d_start += cur_len; } - *moved_len = o_start - orig_blk; - if (*moved_len > len) - *moved_len = len; out: if (*moved_len) { diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index f2ed15af703a80b5eaa732764a7c7ff940493648..38ce42396758d94bb4114a2b69123dc118b69728 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1606,7 +1606,8 @@ exit_journal: int gdb_num = group / EXT4_DESC_PER_BLOCK(sb); int gdb_num_end = ((group + flex_gd->count - 1) / EXT4_DESC_PER_BLOCK(sb)); - int meta_bg = ext4_has_feature_meta_bg(sb); + int meta_bg = ext4_has_feature_meta_bg(sb) && + gdb_num >= le32_to_cpu(es->s_first_meta_bg); sector_t padding_blocks = meta_bg ? 0 : sbi->s_sbh->b_blocknr - ext4_group_first_block_no(sb, 0); sector_t old_gdb = 0; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 601e097e17207180e536d3b19fb1d3d3cf3718c2..274542d869d0c7cc3c9ce3f09f1509e068ee14ce 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -6751,6 +6751,10 @@ static int ext4_write_dquot(struct dquot *dquot) if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_commit(dquot); + if (ret < 0) + ext4_error_err(dquot->dq_sb, -ret, + "Failed to commit dquot type %d", + dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; @@ -6767,6 +6771,10 @@ static int ext4_acquire_dquot(struct dquot *dquot) if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_acquire(dquot); + if (ret < 0) + ext4_error_err(dquot->dq_sb, -ret, + "Failed to acquire dquot type %d", + dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; @@ -6786,6 +6794,10 @@ static int ext4_release_dquot(struct dquot *dquot) return PTR_ERR(handle); } ret = dquot_release(dquot); + if (ret < 0) + ext4_error_err(dquot->dq_sb, -ret, + "Failed to release dquot type %d", + dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index eb4d69f53337f453d69d5d60392c52bea20737d9..3ec203bbd5593c811f519f230618ebf16a45bf3e 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -70,7 +70,7 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index, .old_blkaddr = index, .new_blkaddr = index, .encrypted_page = NULL, - .is_por = !is_meta, + .is_por = !is_meta ? 1 : 0, }; int err; @@ -234,8 +234,8 @@ int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, .op = REQ_OP_READ, .op_flags = sync ? (REQ_META | REQ_PRIO) : REQ_RAHEAD, .encrypted_page = NULL, - .in_list = false, - .is_por = (type == META_POR), + .in_list = 0, + .is_por = (type == META_POR) ? 1 : 0, }; struct blk_plug plug; int err; diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 3d9f6495a4db4171f1c60db55033d9a4b35d72ed..df6dfd7de6d0d588905d557667da416d333e2036 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -55,6 +55,7 @@ struct f2fs_compress_ops { int (*init_decompress_ctx)(struct decompress_io_ctx *dic); void (*destroy_decompress_ctx)(struct decompress_io_ctx *dic); int (*decompress_pages)(struct decompress_io_ctx *dic); + bool (*is_level_valid)(int level); }; static unsigned int offset_in_cluster(struct compress_ctx *cc, pgoff_t index) @@ -322,11 +323,21 @@ static int lz4_decompress_pages(struct decompress_io_ctx *dic) return 0; } +static bool lz4_is_level_valid(int lvl) +{ +#ifdef CONFIG_F2FS_FS_LZ4HC + return !lvl || (lvl >= LZ4HC_MIN_CLEVEL && lvl <= LZ4HC_MAX_CLEVEL); +#else + return lvl == 0; +#endif +} + static const struct f2fs_compress_ops f2fs_lz4_ops = { .init_compress_ctx = lz4_init_compress_ctx, .destroy_compress_ctx = lz4_destroy_compress_ctx, .compress_pages = lz4_compress_pages, .decompress_pages = lz4_decompress_pages, + .is_level_valid = lz4_is_level_valid, }; #endif @@ -490,6 +501,11 @@ static int zstd_decompress_pages(struct decompress_io_ctx *dic) return 0; } +static bool zstd_is_level_valid(int lvl) +{ + return lvl >= zstd_min_clevel() && lvl <= zstd_max_clevel(); +} + static const struct f2fs_compress_ops f2fs_zstd_ops = { .init_compress_ctx = zstd_init_compress_ctx, .destroy_compress_ctx = zstd_destroy_compress_ctx, @@ -497,6 +513,7 @@ static const struct f2fs_compress_ops f2fs_zstd_ops = { .init_decompress_ctx = zstd_init_decompress_ctx, .destroy_decompress_ctx = zstd_destroy_decompress_ctx, .decompress_pages = zstd_decompress_pages, + .is_level_valid = zstd_is_level_valid, }; #endif @@ -555,6 +572,16 @@ bool f2fs_is_compress_backend_ready(struct inode *inode) return f2fs_cops[F2FS_I(inode)->i_compress_algorithm]; } +bool f2fs_is_compress_level_valid(int alg, int lvl) +{ + const struct f2fs_compress_ops *cops = f2fs_cops[alg]; + + if (cops->is_level_valid) + return cops->is_level_valid(lvl); + + return lvl == 0; +} + static mempool_t *compress_page_pool; static int num_compress_pages = 512; module_param(num_compress_pages, uint, 0444); @@ -1222,10 +1249,11 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc, .page = NULL, .encrypted_page = NULL, .compressed_page = NULL, - .submitted = false, + .submitted = 0, .io_type = io_type, .io_wbc = wbc, - .encrypted = fscrypt_inode_uses_fs_layer_crypto(cc->inode), + .encrypted = fscrypt_inode_uses_fs_layer_crypto(cc->inode) ? + 1 : 0, }; struct dnode_of_data dn; struct node_info ni; @@ -1360,8 +1388,6 @@ unlock_continue: add_compr_block_stat(inode, cc->valid_nr_cpages); set_inode_flag(cc->inode, FI_APPEND_WRITE); - if (cc->cluster_idx == 0) - set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); f2fs_put_dnode(&dn); if (quota_inode) @@ -1409,6 +1435,8 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page) struct f2fs_sb_info *sbi = bio->bi_private; struct compress_io_ctx *cic = (struct compress_io_ctx *)page_private(page); + enum count_type type = WB_DATA_TYPE(page, + f2fs_is_compressed_page(page)); int i; if (unlikely(bio->bi_status)) @@ -1416,7 +1444,7 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page) f2fs_compress_free_page(page); - dec_page_count(sbi, F2FS_WB_DATA); + dec_page_count(sbi, type); if (atomic_dec_return(&cic->pending_pages)) return; @@ -1432,12 +1460,14 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page) } static int f2fs_write_raw_pages(struct compress_ctx *cc, - int *submitted, + int *submitted_p, struct writeback_control *wbc, enum iostat_type io_type) { struct address_space *mapping = cc->inode->i_mapping; - int _submitted, compr_blocks, ret, i; + struct f2fs_sb_info *sbi = F2FS_M_SB(mapping); + int submitted, compr_blocks, i; + int ret = 0; compr_blocks = f2fs_compressed_blocks(cc); @@ -1452,6 +1482,10 @@ static int f2fs_write_raw_pages(struct compress_ctx *cc, if (compr_blocks < 0) return compr_blocks; + /* overwrite compressed cluster w/ normal cluster */ + if (compr_blocks > 0) + f2fs_lock_op(sbi); + for (i = 0; i < cc->cluster_size; i++) { if (!cc->rpages[i]) continue; @@ -1476,7 +1510,7 @@ continue_unlock: if (!clear_page_dirty_for_io(cc->rpages[i])) goto continue_unlock; - ret = f2fs_write_single_data_page(cc->rpages[i], &_submitted, + ret = f2fs_write_single_data_page(cc->rpages[i], &submitted, NULL, NULL, wbc, io_type, compr_blocks, false); if (ret) { @@ -1484,26 +1518,29 @@ continue_unlock: unlock_page(cc->rpages[i]); ret = 0; } else if (ret == -EAGAIN) { + ret = 0; /* * for quota file, just redirty left pages to * avoid deadlock caused by cluster update race * from foreground operation. */ if (IS_NOQUOTA(cc->inode)) - return 0; - ret = 0; + goto out; f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT); goto retry_write; } - return ret; + goto out; } - *submitted += _submitted; + *submitted_p += submitted; } - f2fs_balance_fs(F2FS_M_SB(mapping), true); +out: + if (compr_blocks > 0) + f2fs_unlock_op(sbi); - return 0; + f2fs_balance_fs(sbi, true); + return ret; } int f2fs_write_multi_pages(struct compress_ctx *cc, @@ -1806,16 +1843,18 @@ void f2fs_put_page_dic(struct page *page, bool in_task) * check whether cluster blocks are contiguous, and add extent cache entry * only if cluster blocks are logically and physically contiguous. */ -unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn) +unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn, + unsigned int ofs_in_node) { - bool compressed = f2fs_data_blkaddr(dn) == COMPRESS_ADDR; + bool compressed = data_blkaddr(dn->inode, dn->node_page, + ofs_in_node) == COMPRESS_ADDR; int i = compressed ? 1 : 0; block_t first_blkaddr = data_blkaddr(dn->inode, dn->node_page, - dn->ofs_in_node + i); + ofs_in_node + i); for (i += 1; i < F2FS_I(dn->inode)->i_cluster_size; i++) { block_t blkaddr = data_blkaddr(dn->inode, dn->node_page, - dn->ofs_in_node + i); + ofs_in_node + i); if (!__is_valid_data_blkaddr(blkaddr)) break; diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 8b561af379743a232cab343415b0c0989f10c286..b83b8ac29f430868af60d3e910dc4fc3312c85ea 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -50,7 +50,7 @@ void f2fs_destroy_bioset(void) bioset_exit(&f2fs_bioset); } -static bool __is_cp_guaranteed(struct page *page) +bool f2fs_is_cp_guaranteed(struct page *page) { struct address_space *mapping = page->mapping; struct inode *inode; @@ -67,8 +67,6 @@ static bool __is_cp_guaranteed(struct page *page) S_ISDIR(inode->i_mode)) return true; - if (f2fs_is_compressed_page(page)) - return false; if ((S_ISREG(inode->i_mode) && IS_NOQUOTA(inode)) || page_private_gcing(page)) return true; @@ -327,7 +325,7 @@ static void f2fs_write_end_io(struct bio *bio) bio_for_each_segment_all(bvec, bio, iter_all) { struct page *page = bvec->bv_page; - enum count_type type = WB_DATA_TYPE(page); + enum count_type type = WB_DATA_TYPE(page, false); if (page_private_dummy(page)) { clear_page_private_dummy(page); @@ -733,7 +731,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE); inc_page_count(fio->sbi, is_read_io(fio->op) ? - __read_io_type(page) : WB_DATA_TYPE(fio->page)); + __read_io_type(page) : WB_DATA_TYPE(fio->page, false)); __submit_bio(fio->sbi, bio, fio->type); return 0; @@ -941,7 +939,7 @@ alloc_new: if (fio->io_wbc) wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE); - inc_page_count(fio->sbi, WB_DATA_TYPE(page)); + inc_page_count(fio->sbi, WB_DATA_TYPE(page, false)); *fio->last_block = fio->new_blkaddr; *fio->bio = bio; @@ -955,6 +953,7 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio) enum page_type btype = PAGE_TYPE_OF_BIO(fio->type); struct f2fs_bio_info *io = sbi->write_io[btype] + fio->temp; struct page *bio_page; + enum count_type type; f2fs_bug_on(sbi, is_read_io(fio->op)); @@ -982,9 +981,10 @@ next: bio_page = fio->page; /* set submitted = true as a return value */ - fio->submitted = true; + fio->submitted = 1; - inc_page_count(sbi, WB_DATA_TYPE(bio_page)); + type = WB_DATA_TYPE(bio_page, fio->compressed_page); + inc_page_count(sbi, type); if (io->bio && (!io_is_mergeable(sbi, io->bio, io, fio, io->last_block_in_bio, @@ -997,8 +997,9 @@ alloc_new: if (F2FS_IO_ALIGNED(sbi) && (fio->type == DATA || fio->type == NODE) && fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) { - dec_page_count(sbi, WB_DATA_TYPE(bio_page)); - fio->retry = true; + dec_page_count(sbi, WB_DATA_TYPE(bio_page, + fio->compressed_page)); + fio->retry = 1; goto skip; } io->bio = __bio_alloc(fio, BIO_MAX_VECS); @@ -1102,18 +1103,12 @@ static int f2fs_submit_page_read(struct inode *inode, struct page *page, return 0; } -static void __set_data_blkaddr(struct dnode_of_data *dn) +static void __set_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr) { - struct f2fs_node *rn = F2FS_NODE(dn->node_page); - __le32 *addr_array; - int base = 0; - - if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode)) - base = get_extra_isize(dn->inode); + __le32 *addr = get_dnode_addr(dn->inode, dn->node_page); - /* Get physical address of data block */ - addr_array = blkaddr_in_node(rn); - addr_array[base + dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr); + dn->data_blkaddr = blkaddr; + addr[dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr); } /* @@ -1122,18 +1117,17 @@ static void __set_data_blkaddr(struct dnode_of_data *dn) * ->node_page * update block addresses in the node page */ -void f2fs_set_data_blkaddr(struct dnode_of_data *dn) +void f2fs_set_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr) { f2fs_wait_on_page_writeback(dn->node_page, NODE, true, true); - __set_data_blkaddr(dn); + __set_data_blkaddr(dn, blkaddr); if (set_page_dirty(dn->node_page)) dn->node_changed = true; } void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr) { - dn->data_blkaddr = blkaddr; - f2fs_set_data_blkaddr(dn); + f2fs_set_data_blkaddr(dn, blkaddr); f2fs_update_read_extent_cache(dn); } @@ -1148,7 +1142,8 @@ int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC))) return -EPERM; - if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count)))) + err = inc_valid_block_count(sbi, dn->inode, &count, true); + if (unlikely(err)) return err; trace_f2fs_reserve_new_blocks(dn->inode, dn->nid, @@ -1160,8 +1155,7 @@ int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) block_t blkaddr = f2fs_data_blkaddr(dn); if (blkaddr == NULL_ADDR) { - dn->data_blkaddr = NEW_ADDR; - __set_data_blkaddr(dn); + __set_data_blkaddr(dn, NEW_ADDR); count--; } } @@ -1419,13 +1413,12 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type) return err; dn->data_blkaddr = f2fs_data_blkaddr(dn); - if (dn->data_blkaddr != NULL_ADDR) - goto alloc; - - if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count)))) - return err; + if (dn->data_blkaddr == NULL_ADDR) { + err = inc_valid_block_count(sbi, dn->inode, &count, true); + if (unlikely(err)) + return err; + } -alloc: set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version); old_blkaddr = dn->data_blkaddr; f2fs_allocate_data_block(sbi, NULL, old_blkaddr, &dn->data_blkaddr, @@ -2739,8 +2732,6 @@ got_it: f2fs_outplace_write_data(&dn, fio); trace_f2fs_do_write_data_page(page, OPU); set_inode_flag(inode, FI_APPEND_WRITE); - if (page->index == 0) - set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); out_writepage: f2fs_put_dnode(&dn); out: @@ -2776,10 +2767,10 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, .old_blkaddr = NULL_ADDR, .page = page, .encrypted_page = NULL, - .submitted = false, + .submitted = 0, .compr_blocks = compr_blocks, - .need_lock = LOCK_RETRY, - .post_read = f2fs_post_read_required(inode), + .need_lock = compr_blocks ? LOCK_DONE : LOCK_RETRY, + .post_read = f2fs_post_read_required(inode) ? 1 : 0, .io_type = io_type, .io_wbc = wbc, .bio = bio, @@ -2819,9 +2810,6 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, zero_user_segment(page, offset, PAGE_SIZE); write: - if (f2fs_is_drop_cache(inode)) - goto out; - /* Dentry/quota blocks are controlled by checkpoint */ if (S_ISDIR(inode->i_mode) || quota_inode) { /* @@ -2858,6 +2846,7 @@ write: if (err == -EAGAIN) { err = f2fs_do_write_data_page(&fio); if (err == -EAGAIN) { + f2fs_bug_on(sbi, compr_blocks); fio.need_lock = LOCK_REQ; err = f2fs_do_write_data_page(&fio); } @@ -2902,7 +2891,7 @@ out: } if (submitted) - *submitted = fio.submitted ? 1 : 0; + *submitted = fio.submitted; return 0; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 5c76ba764b71f0932e27199de2295688c498f25d..b54d681c6457dd17117cef04cb7ae4f4408af338 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -74,6 +74,11 @@ struct f2fs_fault_info { extern const char *f2fs_fault_name[FAULT_MAX]; #define IS_FAULT_SET(fi, type) ((fi)->inject_type & BIT(type)) + +/* maximum retry count for injected failure */ +#define DEFAULT_FAILURE_RETRY_COUNT 8 +#else +#define DEFAULT_FAILURE_RETRY_COUNT 1 #endif /* @@ -764,8 +769,6 @@ enum { FI_UPDATE_WRITE, /* inode has in-place-update data */ FI_NEED_IPU, /* used for ipu per file */ FI_ATOMIC_FILE, /* indicate atomic file */ - FI_FIRST_BLOCK_WRITTEN, /* indicate #0 data block was written */ - FI_DROP_CACHE, /* drop dirty page cache */ FI_DATA_EXIST, /* indicate data exists */ FI_INLINE_DOTS, /* indicate inline dot dentries */ FI_SKIP_WRITES, /* should skip data page writeback */ @@ -1067,7 +1070,8 @@ struct f2fs_sm_info { * f2fs monitors the number of several block types such as on-writeback, * dirty dentry blocks, dirty node blocks, and dirty meta blocks. */ -#define WB_DATA_TYPE(p) (__is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA) +#define WB_DATA_TYPE(p, f) \ + (f || f2fs_is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA) enum count_type { F2FS_DIRTY_DENTS, F2FS_DIRTY_DATA, @@ -1183,19 +1187,19 @@ struct f2fs_io_info { struct page *encrypted_page; /* encrypted page */ struct page *compressed_page; /* compressed page */ struct list_head list; /* serialize IOs */ - bool submitted; /* indicate IO submission */ - int need_lock; /* indicate we need to lock cp_rwsem */ - bool in_list; /* indicate fio is in io_list */ - bool is_por; /* indicate IO is from recovery or not */ - bool retry; /* need to reallocate block address */ - int compr_blocks; /* # of compressed block addresses */ - bool encrypted; /* indicate file is encrypted */ - bool post_read; /* require post read */ + unsigned int compr_blocks; /* # of compressed block addresses */ + unsigned int need_lock:8; /* indicate we need to lock cp_rwsem */ + unsigned int version:8; /* version of the node */ + unsigned int submitted:1; /* indicate IO submission */ + unsigned int in_list:1; /* indicate fio is in io_list */ + unsigned int is_por:1; /* indicate IO is from recovery or not */ + unsigned int retry:1; /* need to reallocate block address */ + unsigned int encrypted:1; /* indicate file is encrypted */ + unsigned int post_read:1; /* require post read */ enum iostat_type io_type; /* io type */ struct writeback_control *io_wbc; /* writeback control */ struct bio **bio; /* bio for ipu */ sector_t *last_block; /* last block number in bio */ - unsigned char version; /* version of the node */ }; struct bio_entry { @@ -2287,7 +2291,7 @@ static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi, static inline void f2fs_i_blocks_write(struct inode *, block_t, bool, bool); static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, - struct inode *inode, blkcnt_t *count) + struct inode *inode, blkcnt_t *count, bool partial) { blkcnt_t diff = 0, release = 0; block_t avail_user_block_count; @@ -2328,6 +2332,11 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, avail_user_block_count = 0; } if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) { + if (!partial) { + spin_unlock(&sbi->stat_lock); + goto enospc; + } + diff = sbi->total_valid_block_count - avail_user_block_count; if (diff > *count) diff = *count; @@ -2991,6 +3000,7 @@ static inline void __mark_inode_dirty_flag(struct inode *inode, case FI_INLINE_DOTS: case FI_PIN_FILE: case FI_COMPRESS_RELEASED: + case FI_ATOMIC_COMMITTED: f2fs_mark_inode_dirty_sync(inode, true); } } @@ -3247,22 +3257,13 @@ static inline bool f2fs_is_cow_file(struct inode *inode) return is_inode_flag_set(inode, FI_COW_FILE); } -static inline bool f2fs_is_first_block_written(struct inode *inode) -{ - return is_inode_flag_set(inode, FI_FIRST_BLOCK_WRITTEN); -} - -static inline bool f2fs_is_drop_cache(struct inode *inode) -{ - return is_inode_flag_set(inode, FI_DROP_CACHE); -} - +static inline __le32 *get_dnode_addr(struct inode *inode, + struct page *node_page); static inline void *inline_data_addr(struct inode *inode, struct page *page) { - struct f2fs_inode *ri = F2FS_INODE(page); - int extra_size = get_extra_isize(inode); + __le32 *addr = get_dnode_addr(inode, page); - return (void *)&(ri->i_addr[extra_size + DEF_INLINE_RESERVED_SIZE]); + return (void *)(addr + DEF_INLINE_RESERVED_SIZE); } static inline int f2fs_has_inline_dentry(struct inode *inode) @@ -3397,6 +3398,17 @@ static inline int get_inline_xattr_addrs(struct inode *inode) return F2FS_I(inode)->i_inline_xattr_size; } +static inline __le32 *get_dnode_addr(struct inode *inode, + struct page *node_page) +{ + int base = 0; + + if (IS_INODE(node_page) && f2fs_has_extra_attr(inode)) + base = get_extra_isize(inode); + + return blkaddr_in_node(F2FS_NODE(node_page)) + base; +} + #define f2fs_get_inode_mode(i) \ ((is_inode_flag_set(i, FI_ACL_MODE)) ? \ (F2FS_I(i)->i_acl_mode) : ((i)->i_mode)) @@ -3761,6 +3773,7 @@ void f2fs_init_ckpt_req_control(struct f2fs_sb_info *sbi); */ int __init f2fs_init_bioset(void); void f2fs_destroy_bioset(void); +bool f2fs_is_cp_guaranteed(struct page *page); int f2fs_init_bio_entry_cache(void); void f2fs_destroy_bio_entry_cache(void); void f2fs_submit_bio(struct f2fs_sb_info *sbi, @@ -3779,7 +3792,7 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio); struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi, block_t blk_addr, sector_t *sector); int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr); -void f2fs_set_data_blkaddr(struct dnode_of_data *dn); +void f2fs_set_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr); void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr); int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count); int f2fs_reserve_new_block(struct dnode_of_data *dn); @@ -4219,6 +4232,7 @@ bool f2fs_compress_write_end(struct inode *inode, void *fsdata, int f2fs_truncate_partial_cluster(struct inode *inode, u64 from, bool lock); void f2fs_compress_write_end_io(struct bio *bio, struct page *page); bool f2fs_is_compress_backend_ready(struct inode *inode); +bool f2fs_is_compress_level_valid(int alg, int lvl); int f2fs_init_compress_mempool(void); void f2fs_destroy_compress_mempool(void); void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task); @@ -4245,7 +4259,8 @@ struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc); void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed, bool in_task); void f2fs_put_page_dic(struct page *page, bool in_task); -unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn); +unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn, + unsigned int ofs_in_node); int f2fs_init_compress_ctx(struct compress_ctx *cc); void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse); void f2fs_init_compress_info(struct f2fs_sb_info *sbi); @@ -4283,6 +4298,7 @@ static inline bool f2fs_is_compress_backend_ready(struct inode *inode) /* not support compression */ return false; } +static inline bool f2fs_is_compress_level_valid(int alg, int lvl) { return false; } static inline struct page *f2fs_compress_control_page(struct page *page) { WARN_ON_ONCE(1); @@ -4301,7 +4317,8 @@ static inline void f2fs_put_page_dic(struct page *page, bool in_task) { WARN_ON_ONCE(1); } -static inline unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn) { return 0; } +static inline unsigned int f2fs_cluster_blocks_are_contiguous( + struct dnode_of_data *dn, unsigned int ofs_in_node) { return 0; } static inline bool f2fs_sanity_check_cluster(struct dnode_of_data *dn) { return false; } static inline int f2fs_init_compress_inode(struct f2fs_sb_info *sbi) { return 0; } static inline void f2fs_destroy_compress_inode(struct f2fs_sb_info *sbi) { } @@ -4358,15 +4375,24 @@ static inline bool f2fs_disable_compressed_file(struct inode *inode) { struct f2fs_inode_info *fi = F2FS_I(inode); - if (!f2fs_compressed_file(inode)) + f2fs_down_write(&F2FS_I(inode)->i_sem); + + if (!f2fs_compressed_file(inode)) { + f2fs_up_write(&F2FS_I(inode)->i_sem); return true; - if (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode)) + } + if (f2fs_is_mmap_file(inode) || + (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode))) { + f2fs_up_write(&F2FS_I(inode)->i_sem); return false; + } fi->i_flags &= ~F2FS_COMPR_FL; stat_dec_compr_inode(inode); clear_inode_flag(inode, FI_COMPRESSED_FILE); f2fs_mark_inode_dirty_sync(inode, true); + + f2fs_up_write(&F2FS_I(inode)->i_sem); return true; } diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 46e4960a9dcf749f166500d7add0e5f9dd0bcdb6..2fbc8d89c600bcb76b6520ffb558c30cacac5f3f 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -560,20 +560,14 @@ static int f2fs_file_open(struct inode *inode, struct file *filp) void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); - struct f2fs_node *raw_node; int nr_free = 0, ofs = dn->ofs_in_node, len = count; __le32 *addr; - int base = 0; bool compressed_cluster = false; int cluster_index = 0, valid_blocks = 0; int cluster_size = F2FS_I(dn->inode)->i_cluster_size; bool released = !atomic_read(&F2FS_I(dn->inode)->i_compr_blocks); - if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode)) - base = get_extra_isize(dn->inode); - - raw_node = F2FS_NODE(dn->node_page); - addr = blkaddr_in_node(raw_node) + base + ofs; + addr = get_dnode_addr(dn->inode, dn->node_page) + ofs; /* Assumption: truncateion starts with cluster */ for (; count > 0; count--, addr++, dn->ofs_in_node++, cluster_index++) { @@ -591,8 +585,7 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) if (blkaddr == NULL_ADDR) continue; - dn->data_blkaddr = NULL_ADDR; - f2fs_set_data_blkaddr(dn); + f2fs_set_data_blkaddr(dn, NULL_ADDR); if (__is_valid_data_blkaddr(blkaddr)) { if (!f2fs_is_valid_blkaddr(sbi, blkaddr, @@ -602,9 +595,6 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) valid_blocks++; } - if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page)) - clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN); - f2fs_invalidate_blocks(sbi, blkaddr); if (!released || blkaddr != COMPRESS_ADDR) @@ -1497,8 +1487,7 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start, } f2fs_invalidate_blocks(sbi, dn->data_blkaddr); - dn->data_blkaddr = NEW_ADDR; - f2fs_set_data_blkaddr(dn); + f2fs_set_data_blkaddr(dn, NEW_ADDR); } f2fs_update_read_extent_cache_range(dn, start, 0, index - start); @@ -3449,8 +3438,7 @@ static int release_compress_blocks(struct dnode_of_data *dn, pgoff_t count) if (blkaddr != NEW_ADDR) continue; - dn->data_blkaddr = NULL_ADDR; - f2fs_set_data_blkaddr(dn); + f2fs_set_data_blkaddr(dn, NULL_ADDR); } f2fs_i_compr_blocks_update(dn->inode, compr_blocks, false); @@ -3474,7 +3462,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) int ret; int writecount; - if (!f2fs_sb_has_compression(F2FS_I_SB(inode))) + if (!f2fs_sb_has_compression(sbi)) return -EOPNOTSUPP; if (!f2fs_compressed_file(inode)) @@ -3487,7 +3475,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) if (ret) return ret; - f2fs_balance_fs(F2FS_I_SB(inode), true); + f2fs_balance_fs(sbi, true); inode_lock(inode); @@ -3573,10 +3561,10 @@ out: return ret; } -static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count) +static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count, + unsigned int *reserved_blocks) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); - unsigned int reserved_blocks = 0; int cluster_size = F2FS_I(dn->inode)->i_cluster_size; block_t blkaddr; int i; @@ -3599,41 +3587,53 @@ static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count) blkcnt_t reserved; int ret; - for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) { - blkaddr = f2fs_data_blkaddr(dn); + for (i = 0; i < cluster_size; i++) { + blkaddr = data_blkaddr(dn->inode, dn->node_page, + dn->ofs_in_node + i); if (i == 0) { - if (blkaddr == COMPRESS_ADDR) - continue; - dn->ofs_in_node += cluster_size; - goto next; + if (blkaddr != COMPRESS_ADDR) { + dn->ofs_in_node += cluster_size; + goto next; + } + continue; } - if (__is_valid_data_blkaddr(blkaddr)) { + /* + * compressed cluster was not released due to it + * fails in release_compress_blocks(), so NEW_ADDR + * is a possible case. + */ + if (blkaddr == NEW_ADDR || + __is_valid_data_blkaddr(blkaddr)) { compr_blocks++; continue; } - - dn->data_blkaddr = NEW_ADDR; - f2fs_set_data_blkaddr(dn); } reserved = cluster_size - compr_blocks; - ret = inc_valid_block_count(sbi, dn->inode, &reserved); - if (ret) + + /* for the case all blocks in cluster were reserved */ + if (reserved == 1) + goto next; + + ret = inc_valid_block_count(sbi, dn->inode, &reserved, false); + if (unlikely(ret)) return ret; - if (reserved != cluster_size - compr_blocks) - return -ENOSPC; + for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) { + if (f2fs_data_blkaddr(dn) == NULL_ADDR) + f2fs_set_data_blkaddr(dn, NEW_ADDR); + } f2fs_i_compr_blocks_update(dn->inode, compr_blocks, true); - reserved_blocks += reserved; + *reserved_blocks += reserved; next: count -= cluster_size; } - return reserved_blocks; + return 0; } static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) @@ -3644,7 +3644,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) unsigned int reserved_blocks = 0; int ret; - if (!f2fs_sb_has_compression(F2FS_I_SB(inode))) + if (!f2fs_sb_has_compression(sbi)) return -EOPNOTSUPP; if (!f2fs_compressed_file(inode)) @@ -3657,10 +3657,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) if (ret) return ret; - if (atomic_read(&F2FS_I(inode)->i_compr_blocks)) - goto out; - - f2fs_balance_fs(F2FS_I_SB(inode), true); + f2fs_balance_fs(sbi, true); inode_lock(inode); @@ -3669,6 +3666,9 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) goto unlock_inode; } + if (atomic_read(&F2FS_I(inode)->i_compr_blocks)) + goto unlock_inode; + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); filemap_invalidate_lock(inode->i_mapping); @@ -3694,7 +3694,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) count = min(end_offset - dn.ofs_in_node, last_idx - page_idx); count = round_up(count, F2FS_I(inode)->i_cluster_size); - ret = reserve_compress_blocks(&dn, count); + ret = reserve_compress_blocks(&dn, count, &reserved_blocks); f2fs_put_dnode(&dn); @@ -3702,23 +3702,21 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) break; page_idx += count; - reserved_blocks += ret; } filemap_invalidate_unlock(inode->i_mapping); f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); - if (ret >= 0) { + if (!ret) { clear_inode_flag(inode, FI_COMPRESS_RELEASED); inode->i_ctime = current_time(inode); f2fs_mark_inode_dirty_sync(inode, true); } unlock_inode: inode_unlock(inode); -out: mnt_drop_write_file(filp); - if (ret >= 0) { + if (!ret) { ret = put_user(reserved_blocks, (u64 __user *)arg); } else if (reserved_blocks && atomic_read(&F2FS_I(inode)->i_compr_blocks)) { @@ -3967,16 +3965,20 @@ static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg) sizeof(option))) return -EFAULT; - if (!f2fs_compressed_file(inode) || - option.log_cluster_size < MIN_COMPRESS_LOG_SIZE || - option.log_cluster_size > MAX_COMPRESS_LOG_SIZE || - option.algorithm >= COMPRESS_MAX) + if (option.log_cluster_size < MIN_COMPRESS_LOG_SIZE || + option.log_cluster_size > MAX_COMPRESS_LOG_SIZE || + option.algorithm >= COMPRESS_MAX) return -EINVAL; file_start_write(filp); inode_lock(inode); f2fs_down_write(&F2FS_I(inode)->i_sem); + if (!f2fs_compressed_file(inode)) { + ret = -EINVAL; + goto out; + } + if (f2fs_is_mmap_file(inode) || get_dirty_pages(inode)) { ret = -EBUSY; goto out; @@ -4066,7 +4068,7 @@ static int f2fs_ioc_decompress_file(struct file *filp, unsigned long arg) if (!f2fs_compressed_file(inode)) return -EINVAL; - f2fs_balance_fs(F2FS_I_SB(inode), true); + f2fs_balance_fs(sbi, true); file_start_write(filp); inode_lock(inode); @@ -4138,7 +4140,7 @@ static int f2fs_ioc_compress_file(struct file *filp, unsigned long arg) if (!f2fs_compressed_file(inode)) return -EINVAL; - f2fs_balance_fs(F2FS_I_SB(inode), true); + f2fs_balance_fs(sbi, true); file_start_write(filp); inode_lock(inode); diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index ec7212f7a9b73b9a13fe22eff75cfcfae7af6134..d4662ccb94c8f7a5e27522a91f387768b122f795 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1187,8 +1187,8 @@ static int ra_data_block(struct inode *inode, pgoff_t index) .op = REQ_OP_READ, .op_flags = 0, .encrypted_page = NULL, - .in_list = false, - .retry = false, + .in_list = 0, + .retry = 0, }; int err; @@ -1276,8 +1276,8 @@ static int move_data_block(struct inode *inode, block_t bidx, .op = REQ_OP_READ, .op_flags = 0, .encrypted_page = NULL, - .in_list = false, - .retry = false, + .in_list = 0, + .retry = 0, }; struct dnode_of_data dn; struct f2fs_summary sum; @@ -1410,8 +1410,6 @@ static int move_data_block(struct inode *inode, block_t bidx, f2fs_update_data_blkaddr(&dn, newaddr); set_inode_flag(inode, FI_APPEND_WRITE); - if (page->index == 0) - set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); put_page_out: f2fs_put_page(fio.encrypted_page, 1); recover_block: diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 0010579f1736832286417626fb0926ffb36c248d..869bb6ec107cc69e00d98fe55b1ed7f9e0ef09cc 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -59,49 +59,31 @@ void f2fs_set_inode_flags(struct inode *inode) S_ENCRYPTED|S_VERITY|S_CASEFOLD); } -static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri) +static void __get_inode_rdev(struct inode *inode, struct page *node_page) { - int extra_size = get_extra_isize(inode); + __le32 *addr = get_dnode_addr(inode, node_page); if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { - if (ri->i_addr[extra_size]) - inode->i_rdev = old_decode_dev( - le32_to_cpu(ri->i_addr[extra_size])); + if (addr[0]) + inode->i_rdev = old_decode_dev(le32_to_cpu(addr[0])); else - inode->i_rdev = new_decode_dev( - le32_to_cpu(ri->i_addr[extra_size + 1])); + inode->i_rdev = new_decode_dev(le32_to_cpu(addr[1])); } } -static int __written_first_block(struct f2fs_sb_info *sbi, - struct f2fs_inode *ri) +static void __set_inode_rdev(struct inode *inode, struct page *node_page) { - block_t addr = le32_to_cpu(ri->i_addr[offset_in_addr(ri)]); - - if (!__is_valid_data_blkaddr(addr)) - return 1; - if (!f2fs_is_valid_blkaddr(sbi, addr, DATA_GENERIC_ENHANCE)) { - f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR); - return -EFSCORRUPTED; - } - return 0; -} - -static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri) -{ - int extra_size = get_extra_isize(inode); + __le32 *addr = get_dnode_addr(inode, node_page); if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) { if (old_valid_dev(inode->i_rdev)) { - ri->i_addr[extra_size] = - cpu_to_le32(old_encode_dev(inode->i_rdev)); - ri->i_addr[extra_size + 1] = 0; + addr[0] = cpu_to_le32(old_encode_dev(inode->i_rdev)); + addr[1] = 0; } else { - ri->i_addr[extra_size] = 0; - ri->i_addr[extra_size + 1] = - cpu_to_le32(new_encode_dev(inode->i_rdev)); - ri->i_addr[extra_size + 2] = 0; + addr[0] = 0; + addr[1] = cpu_to_le32(new_encode_dev(inode->i_rdev)); + addr[2] = 0; } } } @@ -336,7 +318,6 @@ static int do_read_inode(struct inode *inode) struct page *node_page; struct f2fs_inode *ri; projid_t i_projid; - int err; /* Check if ino is within scope */ if (f2fs_check_nid_range(sbi, inode->i_ino)) @@ -415,17 +396,7 @@ static int do_read_inode(struct inode *inode) } /* get rdev by using inline_info */ - __get_inode_rdev(inode, ri); - - if (S_ISREG(inode->i_mode)) { - err = __written_first_block(sbi, ri); - if (err < 0) { - f2fs_put_page(node_page, 1); - return err; - } - if (!err) - set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); - } + __get_inode_rdev(inode, node_page); if (!f2fs_need_inode_block_update(sbi, inode->i_ino)) fi->last_disk_size = inode->i_size; @@ -697,7 +668,7 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page) } } - __set_inode_rdev(inode, ri); + __set_inode_rdev(inode, node_page); /* deleted inode */ if (inode->i_nlink == 0) diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index c6d0e070963263bd17ad1bcffe50fdab1360de87..fcf22a50ff5db0e337c1a2c53b41c567a7cb3043 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -850,21 +850,29 @@ int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) if (is_inode_flag_set(dn->inode, FI_COMPRESSED_FILE) && f2fs_sb_has_readonly(sbi)) { - unsigned int c_len = f2fs_cluster_blocks_are_contiguous(dn); + unsigned int cluster_size = F2FS_I(dn->inode)->i_cluster_size; + unsigned int ofs_in_node = dn->ofs_in_node; + pgoff_t fofs = index; + unsigned int c_len; block_t blkaddr; + /* should align fofs and ofs_in_node to cluster_size */ + if (fofs % cluster_size) { + fofs = round_down(fofs, cluster_size); + ofs_in_node = round_down(ofs_in_node, cluster_size); + } + + c_len = f2fs_cluster_blocks_are_contiguous(dn, ofs_in_node); if (!c_len) goto out; - blkaddr = f2fs_data_blkaddr(dn); + blkaddr = data_blkaddr(dn->inode, dn->node_page, ofs_in_node); if (blkaddr == COMPRESS_ADDR) blkaddr = data_blkaddr(dn->inode, dn->node_page, - dn->ofs_in_node + 1); + ofs_in_node + 1); f2fs_update_read_extent_tree_range_compressed(dn->inode, - index, blkaddr, - F2FS_I(dn->inode)->i_cluster_size, - c_len); + fofs, blkaddr, cluster_size, c_len); } out: return 0; @@ -1587,7 +1595,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, .op_flags = wbc_to_write_flags(wbc), .page = page, .encrypted_page = NULL, - .submitted = false, + .submitted = 0, .io_type = io_type, .io_wbc = wbc, }; diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 53a6487f91e44952fa2f9a44ade0db384ab4860a..f5efc37a2b5136671c987276d05e7ef7e22b57ac 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -582,6 +582,19 @@ truncate_out: return 0; } +static int f2fs_reserve_new_block_retry(struct dnode_of_data *dn) +{ + int i, err = 0; + + for (i = DEFAULT_FAILURE_RETRY_COUNT; i > 0; i--) { + err = f2fs_reserve_new_block(dn); + if (!err) + break; + } + + return err; +} + static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, struct page *page) { @@ -683,14 +696,8 @@ retry_dn: */ if (dest == NEW_ADDR) { f2fs_truncate_data_blocks_range(&dn, 1); - do { - err = f2fs_reserve_new_block(&dn); - if (err == -ENOSPC) { - f2fs_bug_on(sbi, 1); - break; - } - } while (err && - IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)); + + err = f2fs_reserve_new_block_retry(&dn); if (err) goto err; continue; @@ -698,16 +705,8 @@ retry_dn: /* dest is valid block, try to recover from src to dest */ if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) { - if (src == NULL_ADDR) { - do { - err = f2fs_reserve_new_block(&dn); - if (err == -ENOSPC) { - f2fs_bug_on(sbi, 1); - break; - } - } while (err && - IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)); + err = f2fs_reserve_new_block_retry(&dn); if (err) goto err; } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index c1be4a7f3a0f073926b797414708a1d997f3a34d..c71fe7be3ea105d2855f3bc1cec47e2b8dd7dde0 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -192,6 +192,9 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean) if (!f2fs_is_atomic_file(inode)) return; + if (clean) + truncate_inode_pages_final(inode->i_mapping); + release_atomic_write_cnt(inode); clear_inode_flag(inode, FI_ATOMIC_COMMITTED); clear_inode_flag(inode, FI_ATOMIC_FILE); @@ -200,7 +203,6 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean) F2FS_I(inode)->atomic_write_task = NULL; if (clean) { - truncate_inode_pages_final(inode->i_mapping); f2fs_i_size_write(inode, fi->original_i_size); fi->original_i_size = 0; } @@ -247,7 +249,7 @@ retry: } else { blkcnt_t count = 1; - err = inc_valid_block_count(sbi, inode, &count); + err = inc_valid_block_count(sbi, inode, &count, true); if (err) { f2fs_put_dnode(&dn); return err; @@ -3310,10 +3312,10 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, struct f2fs_bio_info *io; if (F2FS_IO_ALIGNED(sbi)) - fio->retry = false; + fio->retry = 0; INIT_LIST_HEAD(&fio->list); - fio->in_list = true; + fio->in_list = 1; io = sbi->write_io[fio->type] + fio->temp; spin_lock(&io->io_lock); list_add_tail(&fio->list, &io->io_list); @@ -3394,7 +3396,7 @@ void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page, .new_blkaddr = page->index, .page = page, .encrypted_page = NULL, - .in_list = false, + .in_list = 0, }; if (unlikely(page->index >= MAIN_BLKADDR(sbi))) diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index f3951e8ad39484195ca1d713d765df99f1b87465..aa9ad85e0901d0190096a71e629ab9f9e8168570 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -586,23 +586,22 @@ static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi, unsigned int node_blocks, unsigned int dent_blocks) { - unsigned int segno, left_blocks; + unsigned segno, left_blocks; int i; - /* check current node segment */ + /* check current node sections in the worst case. */ for (i = CURSEG_HOT_NODE; i <= CURSEG_COLD_NODE; i++) { segno = CURSEG_I(sbi, i)->segno; - left_blocks = f2fs_usable_blks_in_seg(sbi, segno) - - get_seg_entry(sbi, segno)->ckpt_valid_blocks; - + left_blocks = CAP_BLKS_PER_SEC(sbi) - + get_ckpt_valid_blocks(sbi, segno, true); if (node_blocks > left_blocks) return false; } - /* check current data segment */ + /* check current data section for dentry blocks. */ segno = CURSEG_I(sbi, CURSEG_HOT_DATA)->segno; - left_blocks = f2fs_usable_blks_in_seg(sbi, segno) - - get_seg_entry(sbi, segno)->ckpt_valid_blocks; + left_blocks = CAP_BLKS_PER_SEC(sbi) - + get_ckpt_valid_blocks(sbi, segno, true); if (dent_blocks > left_blocks) return false; return true; @@ -651,7 +650,7 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, if (free_secs > upper_secs) return false; - else if (free_secs <= lower_secs) + if (free_secs <= lower_secs) return true; return !curseg_space; } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 3805162dcef2b503fcc417450508aecc94443a11..c529ce5d986cc8118f561b84086b3fdd38f9e214 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -628,7 +628,7 @@ static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str) if (kstrtouint(str + 1, 10, &level)) return -EINVAL; - if (level < LZ4HC_MIN_CLEVEL || level > LZ4HC_MAX_CLEVEL) { + if (!f2fs_is_compress_level_valid(COMPRESS_LZ4, level)) { f2fs_info(sbi, "invalid lz4hc compress level: %d", level); return -EINVAL; } @@ -649,7 +649,7 @@ static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str) #ifdef CONFIG_F2FS_FS_ZSTD static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str) { - unsigned int level; + int level; int len = 4; if (strlen(str) == len) { @@ -663,10 +663,16 @@ static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str) f2fs_info(sbi, "wrong format, e.g. :"); return -EINVAL; } - if (kstrtouint(str + 1, 10, &level)) + if (kstrtoint(str + 1, 10, &level)) return -EINVAL; - if (level < zstd_min_clevel() || level > zstd_max_clevel()) { + /* f2fs does not support negative compress level now */ + if (level < 0) { + f2fs_info(sbi, "do not support negative compress level: %d", level); + return -ERANGE; + } + + if (!f2fs_is_compress_level_valid(COMPRESS_ZSTD, level)) { f2fs_info(sbi, "invalid zstd compress level: %d", level); return -EINVAL; } diff --git a/fs/fat/nfs.c b/fs/fat/nfs.c index af191371c3529beb3e84fb30484632b255de629a..bab63eeaf9cbc7cdb4f4cc5ebcb11ac1909824f3 100644 --- a/fs/fat/nfs.c +++ b/fs/fat/nfs.c @@ -130,6 +130,12 @@ fat_encode_fh_nostale(struct inode *inode, __u32 *fh, int *lenp, fid->parent_i_gen = parent->i_generation; type = FILEID_FAT_WITH_PARENT; *lenp = FAT_FID_SIZE_WITH_PARENT; + } else { + /* + * We need to initialize this field because the fh is actually + * 12 bytes long + */ + fid->parent_i_pos_hi = 0; } return type; diff --git a/fs/fcntl.c b/fs/fcntl.c index 146c9ab0cd4b7c81e6f661205e79ae562da11cee..0964e5dbf0cac5c2a84fc82211a5cd208a97a234 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -267,7 +267,7 @@ static int f_getowner_uids(struct file *filp, unsigned long arg) } #endif -static bool rw_hint_valid(enum rw_hint hint) +static bool rw_hint_valid(u64 hint) { switch (hint) { case RWH_WRITE_LIFE_NOT_SET: @@ -287,19 +287,17 @@ static long fcntl_rw_hint(struct file *file, unsigned int cmd, { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; - enum rw_hint hint; - u64 h; + u64 hint; switch (cmd) { case F_GET_RW_HINT: - h = inode->i_write_hint; - if (copy_to_user(argp, &h, sizeof(*argp))) + hint = inode->i_write_hint; + if (copy_to_user(argp, &hint, sizeof(*argp))) return -EFAULT; return 0; case F_SET_RW_HINT: - if (copy_from_user(&h, argp, sizeof(h))) + if (copy_from_user(&hint, argp, sizeof(hint))) return -EFAULT; - hint = (enum rw_hint) h; if (!rw_hint_valid(hint)) return -EINVAL; diff --git a/fs/fhandle.c b/fs/fhandle.c index f2bc27d1975e14bd45da242fe25b083b32b2e015..a8c25557c8c124644c69eedc6e7867fe82d85075 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -37,7 +37,7 @@ static long do_sys_name_to_handle(const struct path *path, if (f_handle.handle_bytes > MAX_HANDLE_SZ) return -EINVAL; - handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes, + handle = kzalloc(sizeof(struct file_handle) + f_handle.handle_bytes, GFP_KERNEL); if (!handle) return -ENOMEM; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 5e408e7ec4c6b7154a370a4e0680fa6c47e74618..936a24b646cef0352b58e1af8c811d34d7f68200 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -399,6 +399,10 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name goto out_put_forget; if (fuse_invalid_attr(&outarg->attr)) goto out_put_forget; + if (outarg->nodeid == FUSE_ROOT_ID && outarg->generation != 0) { + pr_warn_once("root generation should be zero\n"); + outarg->generation = 0; + } *inode = fuse_iget(sb, outarg->nodeid, outarg->generation, &outarg->attr, entry_attr_timeout(outarg), diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index a9681fecbd91f60c84b65c7069876c516ff2f167..253b9b78d6f13f5e5ab25d1c60a157ac0092d9b4 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -923,7 +923,6 @@ static inline bool fuse_stale_inode(const struct inode *inode, int generation, static inline void fuse_make_bad(struct inode *inode) { - remove_inode_hash(inode); set_bit(FUSE_I_BAD, &get_fuse_inode(inode)->state); } diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index f81000d968875289750032d541dcee65383ab93a..367e3b276092fd2cad89fac554168b7ce880e1be 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -445,8 +445,11 @@ retry: } else if (fuse_stale_inode(inode, generation, attr)) { /* nodeid was reused, any I/O on the old inode should fail */ fuse_make_bad(inode); - iput(inode); - goto retry; + if (inode != d_inode(sb->s_root)) { + remove_inode_hash(inode); + iput(inode); + goto retry; + } } fi = get_fuse_inode(inode); spin_lock(&fi->lock); diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index e7537fd305dd293635580a4cad5897d93f6839d7..9ad11e5bf14c3dfefe4735449d32335df8df8af6 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1702,7 +1702,8 @@ static int punch_hole(struct gfs2_inode *ip, u64 offset, u64 length) struct buffer_head *dibh, *bh; struct gfs2_holder rd_gh; unsigned int bsize_shift = sdp->sd_sb.sb_bsize_shift; - u64 lblock = (offset + (1 << bsize_shift) - 1) >> bsize_shift; + unsigned int bsize = 1 << bsize_shift; + u64 lblock = (offset + bsize - 1) >> bsize_shift; __u16 start_list[GFS2_MAX_META_HEIGHT]; __u16 __end_list[GFS2_MAX_META_HEIGHT], *end_list = NULL; unsigned int start_aligned, end_aligned; @@ -1713,7 +1714,7 @@ static int punch_hole(struct gfs2_inode *ip, u64 offset, u64 length) u64 prev_bnr = 0; __be64 *start, *end; - if (offset >= maxsize) { + if (offset + bsize - 1 >= maxsize) { /* * The starting point lies beyond the allocated meta-data; * there are no blocks do deallocate. diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 8eea709e36599e26aea3f3ebc1b0de8548623f94..330729445d8ab6169812882cdd13b1d8a5487982 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -123,6 +123,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) loff_t len, vma_len; int ret; struct hstate *h = hstate_file(file); + vm_flags_t vm_flags; /* * vma address alignment (but not the pgoff alignment) has @@ -164,10 +165,20 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) file_accessed(file); ret = -ENOMEM; + + vm_flags = vma->vm_flags; + /* + * for SHM_HUGETLB, the pages are reserved in the shmget() call so skip + * reserving here. Note: only for SHM hugetlbfs file, the inode + * flag S_PRIVATE is set. + */ + if (inode->i_flags & S_PRIVATE) + vm_flags |= VM_NORESERVE; + if (!hugetlb_reserve_pages(inode, vma->vm_pgoff >> huge_page_order(h), len >> huge_page_shift(h), vma, - vma->vm_flags)) + vm_flags)) goto out; ret = 0; @@ -1097,10 +1108,10 @@ static int hugetlbfs_migrate_folio(struct address_space *mapping, if (rc != MIGRATEPAGE_SUCCESS) return rc; - if (hugetlb_page_subpool(&src->page)) { - hugetlb_set_page_subpool(&dst->page, - hugetlb_page_subpool(&src->page)); - hugetlb_set_page_subpool(&src->page, NULL); + if (hugetlb_folio_subpool(src)) { + hugetlb_set_folio_subpool(dst, + hugetlb_folio_subpool(src)); + hugetlb_set_folio_subpool(src, NULL); } if (mode != MIGRATE_SYNC_NO_COPY) @@ -1350,6 +1361,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par { struct hugetlbfs_fs_context *ctx = fc->fs_private; struct fs_parse_result result; + struct hstate *h; char *rest; unsigned long ps; int opt; @@ -1394,11 +1406,12 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par case Opt_pagesize: ps = memparse(param->string, &rest); - ctx->hstate = size_to_hstate(ps); - if (!ctx->hstate) { + h = size_to_hstate(ps); + if (!h) { pr_err("Unsupported page size %lu MB\n", ps / SZ_1M); return -EINVAL; } + ctx->hstate = h; return 0; case Opt_min_size: diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index a0a4d8de82cad21715d12b6c17e8085cfd3157b3..dac1a5c110c0e05176754ef7e8975f61d1320645 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -579,7 +579,7 @@ static int iomap_write_begin_inline(const struct iomap_iter *iter, return iomap_read_inline_data(iter, folio); } -static int iomap_write_begin(const struct iomap_iter *iter, loff_t pos, +static int iomap_write_begin(struct iomap_iter *iter, loff_t pos, size_t len, struct folio **foliop) { const struct iomap_page_ops *page_ops = iter->iomap.page_ops; @@ -613,6 +613,27 @@ static int iomap_write_begin(const struct iomap_iter *iter, loff_t pos, status = (iter->flags & IOMAP_NOWAIT) ? -EAGAIN : -ENOMEM; goto out_no_page; } + + /* + * Now we have a locked folio, before we do anything with it we need to + * check that the iomap we have cached is not stale. The inode extent + * mapping can change due to concurrent IO in flight (e.g. + * IOMAP_UNWRITTEN state can change and memory reclaim could have + * reclaimed a previously partially written page at this index after IO + * completion before this write reaches this file offset) and hence we + * could do the wrong thing here (zero a page range incorrectly or fail + * to zero) and corrupt data. + */ + if (page_ops && page_ops->iomap_valid) { + bool iomap_valid = page_ops->iomap_valid(iter->inode, + &iter->iomap); + if (!iomap_valid) { + iter->iomap.flags |= IOMAP_F_STALE; + status = 0; + goto out_unlock; + } + } + if (pos + len > folio_pos(folio) + folio_size(folio)) len = folio_pos(folio) + folio_size(folio) - pos; @@ -768,6 +789,8 @@ again: status = iomap_write_begin(iter, pos, bytes, &folio); if (unlikely(status)) break; + if (iter->iomap.flags & IOMAP_F_STALE) + break; page = folio_file_page(folio, pos >> PAGE_SHIFT); if (mapping_writably_mapped(mapping)) @@ -827,6 +850,231 @@ iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i, } EXPORT_SYMBOL_GPL(iomap_file_buffered_write); +/* + * Scan the data range passed to us for dirty page cache folios. If we find a + * dirty folio, punch out the preceeding range and update the offset from which + * the next punch will start from. + * + * We can punch out storage reservations under clean pages because they either + * contain data that has been written back - in which case the delalloc punch + * over that range is a no-op - or they have been read faults in which case they + * contain zeroes and we can remove the delalloc backing range and any new + * writes to those pages will do the normal hole filling operation... + * + * This makes the logic simple: we only need to keep the delalloc extents only + * over the dirty ranges of the page cache. + * + * This function uses [start_byte, end_byte) intervals (i.e. open ended) to + * simplify range iterations. + */ +static int iomap_write_delalloc_scan(struct inode *inode, + loff_t *punch_start_byte, loff_t start_byte, loff_t end_byte, + int (*punch)(struct inode *inode, loff_t offset, loff_t length)) +{ + while (start_byte < end_byte) { + struct folio *folio; + + /* grab locked page */ + folio = filemap_lock_folio(inode->i_mapping, + start_byte >> PAGE_SHIFT); + if (!folio) { + start_byte = ALIGN_DOWN(start_byte, PAGE_SIZE) + + PAGE_SIZE; + continue; + } + + /* if dirty, punch up to offset */ + if (folio_test_dirty(folio)) { + if (start_byte > *punch_start_byte) { + int error; + + error = punch(inode, *punch_start_byte, + start_byte - *punch_start_byte); + if (error) { + folio_unlock(folio); + folio_put(folio); + return error; + } + } + + /* + * Make sure the next punch start is correctly bound to + * the end of this data range, not the end of the folio. + */ + *punch_start_byte = min_t(loff_t, end_byte, + folio_next_index(folio) << PAGE_SHIFT); + } + + /* move offset to start of next folio in range */ + start_byte = folio_next_index(folio) << PAGE_SHIFT; + folio_unlock(folio); + folio_put(folio); + } + return 0; +} + +/* + * Punch out all the delalloc blocks in the range given except for those that + * have dirty data still pending in the page cache - those are going to be + * written and so must still retain the delalloc backing for writeback. + * + * As we are scanning the page cache for data, we don't need to reimplement the + * wheel - mapping_seek_hole_data() does exactly what we need to identify the + * start and end of data ranges correctly even for sub-folio block sizes. This + * byte range based iteration is especially convenient because it means we + * don't have to care about variable size folios, nor where the start or end of + * the data range lies within a folio, if they lie within the same folio or even + * if there are multiple discontiguous data ranges within the folio. + * + * It should be noted that mapping_seek_hole_data() is not aware of EOF, and so + * can return data ranges that exist in the cache beyond EOF. e.g. a page fault + * spanning EOF will initialise the post-EOF data to zeroes and mark it up to + * date. A write page fault can then mark it dirty. If we then fail a write() + * beyond EOF into that up to date cached range, we allocate a delalloc block + * beyond EOF and then have to punch it out. Because the range is up to date, + * mapping_seek_hole_data() will return it, and we will skip the punch because + * the folio is dirty. THis is incorrect - we always need to punch out delalloc + * beyond EOF in this case as writeback will never write back and covert that + * delalloc block beyond EOF. Hence we limit the cached data scan range to EOF, + * resulting in always punching out the range from the EOF to the end of the + * range the iomap spans. + * + * Intervals are of the form [start_byte, end_byte) (i.e. open ended) because it + * matches the intervals returned by mapping_seek_hole_data(). i.e. SEEK_DATA + * returns the start of a data range (start_byte), and SEEK_HOLE(start_byte) + * returns the end of the data range (data_end). Using closed intervals would + * require sprinkling this code with magic "+ 1" and "- 1" arithmetic and expose + * the code to subtle off-by-one bugs.... + */ +static int iomap_write_delalloc_release(struct inode *inode, + loff_t start_byte, loff_t end_byte, + int (*punch)(struct inode *inode, loff_t pos, loff_t length)) +{ + loff_t punch_start_byte = start_byte; + loff_t scan_end_byte = min(i_size_read(inode), end_byte); + int error = 0; + + /* + * Lock the mapping to avoid races with page faults re-instantiating + * folios and dirtying them via ->page_mkwrite whilst we walk the + * cache and perform delalloc extent removal. Failing to do this can + * leave dirty pages with no space reservation in the cache. + */ + filemap_invalidate_lock(inode->i_mapping); + while (start_byte < scan_end_byte) { + loff_t data_end; + + start_byte = mapping_seek_hole_data(inode->i_mapping, + start_byte, scan_end_byte, SEEK_DATA); + /* + * If there is no more data to scan, all that is left is to + * punch out the remaining range. + */ + if (start_byte == -ENXIO || start_byte == scan_end_byte) + break; + if (start_byte < 0) { + error = start_byte; + goto out_unlock; + } + WARN_ON_ONCE(start_byte < punch_start_byte); + WARN_ON_ONCE(start_byte > scan_end_byte); + + /* + * We find the end of this contiguous cached data range by + * seeking from start_byte to the beginning of the next hole. + */ + data_end = mapping_seek_hole_data(inode->i_mapping, start_byte, + scan_end_byte, SEEK_HOLE); + if (data_end < 0) { + error = data_end; + goto out_unlock; + } + WARN_ON_ONCE(data_end <= start_byte); + WARN_ON_ONCE(data_end > scan_end_byte); + + error = iomap_write_delalloc_scan(inode, &punch_start_byte, + start_byte, data_end, punch); + if (error) + goto out_unlock; + + /* The next data search starts at the end of this one. */ + start_byte = data_end; + } + + if (punch_start_byte < end_byte) + error = punch(inode, punch_start_byte, + end_byte - punch_start_byte); +out_unlock: + filemap_invalidate_unlock(inode->i_mapping); + return error; +} + +/* + * When a short write occurs, the filesystem may need to remove reserved space + * that was allocated in ->iomap_begin from it's ->iomap_end method. For + * filesystems that use delayed allocation, we need to punch out delalloc + * extents from the range that are not dirty in the page cache. As the write can + * race with page faults, there can be dirty pages over the delalloc extent + * outside the range of a short write but still within the delalloc extent + * allocated for this iomap. + * + * This function uses [start_byte, end_byte) intervals (i.e. open ended) to + * simplify range iterations. + * + * The punch() callback *must* only punch delalloc extents in the range passed + * to it. It must skip over all other types of extents in the range and leave + * them completely unchanged. It must do this punch atomically with respect to + * other extent modifications. + * + * The punch() callback may be called with a folio locked to prevent writeback + * extent allocation racing at the edge of the range we are currently punching. + * The locked folio may or may not cover the range being punched, so it is not + * safe for the punch() callback to lock folios itself. + * + * Lock order is: + * + * inode->i_rwsem (shared or exclusive) + * inode->i_mapping->invalidate_lock (exclusive) + * folio_lock() + * ->punch + * internal filesystem allocation lock + */ +int iomap_file_buffered_write_punch_delalloc(struct inode *inode, + struct iomap *iomap, loff_t pos, loff_t length, + ssize_t written, + int (*punch)(struct inode *inode, loff_t pos, loff_t length)) +{ + loff_t start_byte; + loff_t end_byte; + int blocksize = i_blocksize(inode); + + if (iomap->type != IOMAP_DELALLOC) + return 0; + + /* If we didn't reserve the blocks, we're not allowed to punch them. */ + if (!(iomap->flags & IOMAP_F_NEW)) + return 0; + + /* + * start_byte refers to the first unused block after a short write. If + * nothing was written, round offset down to point at the first block in + * the range. + */ + if (unlikely(!written)) + start_byte = round_down(pos, blocksize); + else + start_byte = round_up(pos + written, blocksize); + end_byte = round_up(pos + length, blocksize); + + /* Nothing to do if we've written the entire delalloc extent */ + if (start_byte >= end_byte) + return 0; + + return iomap_write_delalloc_release(inode, start_byte, end_byte, + punch); +} +EXPORT_SYMBOL_GPL(iomap_file_buffered_write_punch_delalloc); + static loff_t iomap_unshare_iter(struct iomap_iter *iter) { struct iomap *iomap = &iter->iomap; @@ -851,6 +1099,8 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter) status = iomap_write_begin(iter, pos, bytes, &folio); if (unlikely(status)) return status; + if (iter->iomap.flags & IOMAP_F_STALE) + break; status = iomap_write_end(iter, pos, bytes, bytes, folio); if (WARN_ON_ONCE(status == 0)) @@ -906,6 +1156,8 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) status = iomap_write_begin(iter, pos, bytes, &folio); if (status) return status; + if (iter->iomap.flags & IOMAP_F_STALE) + break; offset = offset_in_folio(folio, pos); if (bytes > folio_size(folio) - offset) diff --git a/fs/iomap/iter.c b/fs/iomap/iter.c index a1c7592d2aded78ecbe9f0077ce6b0d0356287d0..79a0614eaab777e71767a9148ca105e571b509e8 100644 --- a/fs/iomap/iter.c +++ b/fs/iomap/iter.c @@ -7,12 +7,28 @@ #include #include "trace.h" +/* + * Advance to the next range we need to map. + * + * If the iomap is marked IOMAP_F_STALE, it means the existing map was not fully + * processed - it was aborted because the extent the iomap spanned may have been + * changed during the operation. In this case, the iteration behaviour is to + * remap the unprocessed range of the iter, and that means we may need to remap + * even when we've made no progress (i.e. iter->processed = 0). Hence the + * "finished iterating" case needs to distinguish between + * (processed = 0) meaning we are done and (processed = 0 && stale) meaning we + * need to remap the entire remaining range. + */ static inline int iomap_iter_advance(struct iomap_iter *iter) { + bool stale = iter->iomap.flags & IOMAP_F_STALE; + /* handle the previous iteration (if any) */ if (iter->iomap.length) { - if (iter->processed <= 0) + if (iter->processed < 0) return iter->processed; + if (!iter->processed && !stale) + return 0; if (WARN_ON_ONCE(iter->processed > iomap_length(iter))) return -EIO; iter->pos += iter->processed; @@ -33,6 +49,7 @@ static inline void iomap_iter_done(struct iomap_iter *iter) WARN_ON_ONCE(iter->iomap.offset > iter->pos); WARN_ON_ONCE(iter->iomap.length == 0); WARN_ON_ONCE(iter->iomap.offset + iter->iomap.length <= iter->pos); + WARN_ON_ONCE(iter->iomap.flags & IOMAP_F_STALE); trace_iomap_iter_dstmap(iter->inode, &iter->iomap); if (iter->srcmap.type != IOMAP_HOLE) diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index df9d70588b600b382e8075bc3898f0d488fc086a..8a6c7fdc1d5fc11907c27feceb64963c4b839da2 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -908,8 +908,22 @@ root_found: * we then decide whether to use the Joliet descriptor. */ inode = isofs_iget(s, sbi->s_firstdatazone, 0); - if (IS_ERR(inode)) - goto out_no_root; + + /* + * Fix for broken CDs with a corrupt root inode but a correct Joliet + * root directory. + */ + if (IS_ERR(inode)) { + if (joliet_level && sbi->s_firstdatazone != first_data_zone) { + printk(KERN_NOTICE + "ISOFS: root inode is unusable. " + "Disabling Rock Ridge and switching to Joliet."); + sbi->s_rock = 0; + inode = NULL; + } else { + goto out_no_root; + } + } /* * Fix for broken CDs with Rock Ridge and empty ISO root directory but diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 284b019cb6529b999c9a2dbdd21f06f7c0325c38..b72023a6b4c16d9fbdb4d9c0021d93e732bbc99b 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -52,6 +52,7 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp, *filp = file; /* Set up the missing parts of the file_lock structure */ + lock->fl.fl_flags = FL_POSIX; lock->fl.fl_file = file->f_file[mode]; lock->fl.fl_pid = current->tgid; lock->fl.fl_start = (loff_t)lock->lock_start; diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index 9c1aa75441e1ccf94a46b78133ed5e230cdd3fb4..4e30f3c50970127ea0a5197ed03b310f2409e3eb 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -659,11 +659,13 @@ nlmsvc_unlock(struct net *net, struct nlm_file *file, struct nlm_lock *lock) nlmsvc_cancel_blocked(net, file, lock); lock->fl.fl_type = F_UNLCK; - if (file->f_file[O_RDONLY]) - error = vfs_lock_file(file->f_file[O_RDONLY], F_SETLK, + lock->fl.fl_file = file->f_file[O_RDONLY]; + if (lock->fl.fl_file) + error = vfs_lock_file(lock->fl.fl_file, F_SETLK, &lock->fl, NULL); - if (file->f_file[O_WRONLY]) - error = vfs_lock_file(file->f_file[O_WRONLY], F_SETLK, + lock->fl.fl_file = file->f_file[O_WRONLY]; + if (lock->fl.fl_file) + error |= vfs_lock_file(lock->fl.fl_file, F_SETLK, &lock->fl, NULL); return (error < 0)? nlm_lck_denied_nolocks : nlm_granted; @@ -697,9 +699,10 @@ nlmsvc_cancel_blocked(struct net *net, struct nlm_file *file, struct nlm_lock *l block = nlmsvc_lookup_block(file, lock); mutex_unlock(&file->f_mutex); if (block != NULL) { - mode = lock_to_openmode(&lock->fl); - vfs_cancel_lock(block->b_file->f_file[mode], - &block->b_call->a_args.lock.fl); + struct file_lock *fl = &block->b_call->a_args.lock.fl; + + mode = lock_to_openmode(fl); + vfs_cancel_lock(block->b_file->f_file[mode], fl); status = nlmsvc_unlink_block(block); nlmsvc_release_block(block); } diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index e35c05e2780618bcf62504b79f41f8f12a4f292b..32784f508c8106313a4b1e7728b56e22bcd857b7 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -77,6 +77,7 @@ nlmsvc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp, /* Set up the missing parts of the file_lock structure */ mode = lock_to_openmode(&lock->fl); + lock->fl.fl_flags = FL_POSIX; lock->fl.fl_file = file->f_file[mode]; lock->fl.fl_pid = current->tgid; lock->fl.fl_lmops = &nlmsvc_lock_operations; diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index 3515f17eaf3fb5bc1deda4c4e7352546f135c80b..e3b6229e7ae5cdd807198a47bbb8e8546a6ff3ba 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -210,7 +210,7 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file, { struct inode *inode = nlmsvc_file_inode(file); struct file_lock *fl; - struct file_lock_context *flctx = inode->i_flctx; + struct file_lock_context *flctx = locks_inode_context(inode); struct nlm_host *lockhost; if (!flctx || list_empty_careful(&flctx->flc_posix)) @@ -265,7 +265,7 @@ nlm_file_inuse(struct nlm_file *file) { struct inode *inode = nlmsvc_file_inode(file); struct file_lock *fl; - struct file_lock_context *flctx = inode->i_flctx; + struct file_lock_context *flctx = locks_inode_context(inode); if (file->f_count || !list_empty(&file->f_blocks) || file->f_shares) return 1; diff --git a/fs/locks.c b/fs/locks.c index 1047ab2b15e960acdeedd7abe693f3a12c2c5569..7d0918b8fe5d611f4d34f694b4f08be9304d68f3 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -175,7 +175,7 @@ locks_get_lock_context(struct inode *inode, int type) struct file_lock_context *ctx; /* paired with cmpxchg() below */ - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (likely(ctx) || type == F_UNLCK) goto out; @@ -194,7 +194,7 @@ locks_get_lock_context(struct inode *inode, int type) */ if (cmpxchg(&inode->i_flctx, NULL, ctx)) { kmem_cache_free(flctx_cache, ctx); - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); } out: trace_locks_get_lock_context(inode, type, ctx); @@ -247,7 +247,7 @@ locks_check_ctx_file_list(struct file *filp, struct list_head *list, void locks_free_lock_context(struct inode *inode) { - struct file_lock_context *ctx = inode->i_flctx; + struct file_lock_context *ctx = locks_inode_context(inode); if (unlikely(ctx)) { locks_check_ctx_lists(inode); @@ -891,7 +891,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl) void *owner; void (*func)(void); - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx || list_empty_careful(&ctx->flc_posix)) { fl->fl_type = F_UNLCK; return; @@ -1483,7 +1483,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) new_fl->fl_flags = type; /* typically we will check that ctx is non-NULL before calling */ - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx) { WARN_ON_ONCE(1); goto free_lock; @@ -1588,7 +1588,7 @@ void lease_get_mtime(struct inode *inode, struct timespec64 *time) struct file_lock_context *ctx; struct file_lock *fl; - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (ctx && !list_empty_careful(&ctx->flc_lease)) { spin_lock(&ctx->flc_lock); fl = list_first_entry_or_null(&ctx->flc_lease, @@ -1634,7 +1634,7 @@ int fcntl_getlease(struct file *filp) int type = F_UNLCK; LIST_HEAD(dispose); - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (ctx && !list_empty_careful(&ctx->flc_lease)) { percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); @@ -1823,7 +1823,7 @@ static int generic_delete_lease(struct file *filp, void *owner) struct file_lock_context *ctx; LIST_HEAD(dispose); - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx) { trace_generic_delete_lease(inode, NULL); return error; @@ -2562,7 +2562,7 @@ void locks_remove_posix(struct file *filp, fl_owner_t owner) * posix_lock_file(). Another process could be setting a lock on this * file at the same time, but we wouldn't remove that lock anyway. */ - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx || list_empty(&ctx->flc_posix)) return; @@ -2635,7 +2635,7 @@ void locks_remove_file(struct file *filp) { struct file_lock_context *ctx; - ctx = smp_load_acquire(&locks_inode(filp)->i_flctx); + ctx = locks_inode_context(locks_inode(filp)); if (!ctx) return; @@ -2682,7 +2682,7 @@ bool vfs_inode_has_locks(struct inode *inode) struct file_lock_context *ctx; bool ret; - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx) return false; @@ -2863,7 +2863,7 @@ void show_fd_locks(struct seq_file *f, struct file_lock_context *ctx; int id = 0; - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx) return; diff --git a/fs/namespace.c b/fs/namespace.c index 29a8d90dd1072d6a1e5f838f7e95664d54daf3ab..1533550f73567350c7a9dbdc6b0aa8d46d9068c5 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4172,10 +4172,15 @@ static int do_mount_setattr(struct path *path, struct mount_kattr *kattr) /* * If this is an attached mount make sure it's located in the callers * mount namespace. If it's not don't let the caller interact with it. - * If this is a detached mount make sure it has an anonymous mount - * namespace attached to it, i.e. we've created it via OPEN_TREE_CLONE. + * + * If this mount doesn't have a parent it's most often simply a + * detached mount with an anonymous mount namespace. IOW, something + * that's simply not attached yet. But there are apparently also users + * that do change mount properties on the rootfs itself. That obviously + * neither has a parent nor is it a detached mount so we cannot + * unconditionally check for detached mounts. */ - if (!(mnt_has_parent(mnt) ? check_mnt(mnt) : is_anon_ns(mnt->mnt_ns))) + if ((mnt_has_parent(mnt) || !is_anon_ns(mnt->mnt_ns)) && !check_mnt(mnt)) goto out; /* diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 456af7d230cf180ec0b7d22dc1d498726ce70a7a..46a0a2d6962e1c81b8dbb6663748befb5bb93f3a 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -80,9 +80,6 @@ nfs4_callback_svc(void *vrqstp) set_freezable(); while (!kthread_freezable_should_stop(NULL)) { - - if (signal_pending(current)) - flush_signals(current); /* * Listen for a request on the socket */ @@ -112,11 +109,7 @@ nfs41_callback_svc(void *vrqstp) set_freezable(); while (!kthread_freezable_should_stop(NULL)) { - - if (signal_pending(current)) - flush_signals(current); - - prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE); + prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_IDLE); spin_lock_bh(&serv->sv_cb_lock); if (!list_empty(&serv->sv_cb_list)) { req = list_first_entry(&serv->sv_cb_list, diff --git a/fs/nfs/client.c b/fs/nfs/client.c index f50e025ae40640f14e3d79771c576f6ea1a8246f..755256875052f8e3a2d0acd8bd7d7d6155eb0cb4 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -73,7 +73,6 @@ const struct rpc_program nfs_program = { .number = NFS_PROGRAM, .nrvers = ARRAY_SIZE(nfs_version), .version = nfs_version, - .stats = &nfs_rpcstat, .pipe_dir_name = NFS_PIPE_DIRNAME, }; @@ -496,6 +495,7 @@ int nfs_create_rpc_client(struct nfs_client *clp, const struct nfs_client_initdata *cl_init, rpc_authflavor_t flavor) { + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); struct rpc_clnt *clnt = NULL; struct rpc_create_args args = { .net = clp->cl_net, @@ -507,6 +507,7 @@ int nfs_create_rpc_client(struct nfs_client *clp, .servername = clp->cl_hostname, .nodename = cl_init->nodename, .program = &nfs_program, + .stats = &nn->rpcstats, .version = clp->rpc_ops->version, .authflavor = flavor, .cred = cl_init->cred, @@ -1142,6 +1143,8 @@ void nfs_clients_init(struct net *net) #endif spin_lock_init(&nn->nfs_client_lock); nn->boot_time = ktime_get_real(); + memset(&nn->rpcstats, 0, sizeof(nn->rpcstats)); + nn->rpcstats.program = &nfs_program; nfs_netns_sysfs_setup(nn, net); } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 8fdb65e1b14a3e391e70d0653562f846a26580d5..b555efca01d204adc66380831279162100d58141 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -647,10 +647,17 @@ static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq) LIST_HEAD(mds_list); nfs_init_cinfo_from_dreq(&cinfo, dreq); + nfs_commit_begin(cinfo.mds); nfs_scan_commit(dreq->inode, &mds_list, &cinfo); res = nfs_generic_commit_list(dreq->inode, &mds_list, 0, &cinfo); - if (res < 0) /* res == -ENOMEM */ - nfs_direct_write_reschedule(dreq); + if (res < 0) { /* res == -ENOMEM */ + spin_lock(&dreq->lock); + if (dreq->flags == 0) + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + spin_unlock(&dreq->lock); + } + if (nfs_commit_end(cinfo.mds)) + nfs_direct_write_complete(dreq); } static void nfs_direct_write_clear_reqs(struct nfs_direct_req *dreq) diff --git a/fs/nfs/export.c b/fs/nfs/export.c index 01596f2d0a1ed6127afd006d93b1abedd4cf0f7f..9fe9586a51b713351e464bdff21de66dc67d15e6 100644 --- a/fs/nfs/export.c +++ b/fs/nfs/export.c @@ -156,7 +156,10 @@ const struct export_operations nfs_export_ops = { .fh_to_dentry = nfs_fh_to_dentry, .get_parent = nfs_get_parent, .fetch_iversion = nfs_fetch_iversion, - .flags = EXPORT_OP_NOWCC|EXPORT_OP_NOSUBTREECHK| - EXPORT_OP_CLOSE_BEFORE_UNLINK|EXPORT_OP_REMOTE_FS| - EXPORT_OP_NOATOMIC_ATTR, + .flags = EXPORT_OP_NOWCC | + EXPORT_OP_NOSUBTREECHK | + EXPORT_OP_CLOSE_BEFORE_UNLINK | + EXPORT_OP_REMOTE_FS | + EXPORT_OP_NOATOMIC_ATTR | + EXPORT_OP_FLUSH_ON_CLOSE, }; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 81bbafab18a99751238719912a9b7981fd9a2c01..4376881be7918f0da9ab801f3820102a03672f32 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -2016,7 +2016,7 @@ static void ff_layout_cancel_io(struct pnfs_layout_segment *lseg) for (idx = 0; idx < flseg->mirror_array_cnt; idx++) { mirror = flseg->mirror_array[idx]; mirror_ds = mirror->mirror_ds; - if (!mirror_ds) + if (IS_ERR_OR_NULL(mirror_ds)) continue; ds = mirror->mirror_ds->ds; if (!ds) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index e0c1fb98f907a69697df8024dea5568ea4a61b5d..cf8c3771e4bfb7cddbb026164ad6f82109e45efd 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -2333,12 +2333,21 @@ EXPORT_SYMBOL_GPL(nfs_net_id); static int nfs_net_init(struct net *net) { + struct nfs_net *nn = net_generic(net, nfs_net_id); + nfs_clients_init(net); + + if (!rpc_proc_register(net, &nn->rpcstats)) { + nfs_clients_exit(net); + return -ENOMEM; + } + return nfs_fs_proc_net_init(net); } static void nfs_net_exit(struct net *net) { + rpc_proc_unregister(net, "nfs"); nfs_fs_proc_net_exit(net); nfs_clients_exit(net); } @@ -2393,15 +2402,12 @@ static int __init init_nfs_fs(void) if (err) goto out1; - rpc_proc_register(&init_net, &nfs_rpcstat); - err = register_nfs_fs(); if (err) goto out0; return 0; out0: - rpc_proc_unregister(&init_net, "nfs"); nfs_destroy_directcache(); out1: nfs_destroy_writepagecache(); @@ -2431,7 +2437,6 @@ static void __exit exit_nfs_fs(void) nfs_destroy_inodecache(); nfs_destroy_nfspagecache(); unregister_pernet_subsys(&nfs_net_ops); - rpc_proc_unregister(&init_net, "nfs"); unregister_nfs_fs(); nfs_fs_proc_exit(); nfsiod_stop(); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 35a8ae46b6c3460d651a5837398d4b795272278c..b3b801e7c4bc578b73015fe28ba4f06700c8235a 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -443,8 +443,6 @@ int nfs_try_get_tree(struct fs_context *); int nfs_get_tree_common(struct fs_context *); void nfs_kill_super(struct super_block *); -extern struct rpc_stat nfs_rpcstat; - extern int __init register_nfs_fs(void); extern void __exit unregister_nfs_fs(void); extern bool nfs_sb_active(struct super_block *sb); diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h index c8374f74dce1142289ed717c5281b4600a2a44e5..a68b21603ea9a867ba513e2a667b08fbc6d80dd8 100644 --- a/fs/nfs/netns.h +++ b/fs/nfs/netns.h @@ -9,6 +9,7 @@ #include #include #include +#include struct bl_dev_msg { int32_t status; @@ -34,6 +35,7 @@ struct nfs_net { struct nfs_netns_client *nfs_client; spinlock_t nfs_client_lock; ktime_t boot_time; + struct rpc_stat rpcstats; #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_nfsfs; #endif diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h index b59876b01a1e3c15206b7d12528e3e42312d3a42..0282d93c8bccb386d744017e9d2741abcb9a5f13 100644 --- a/fs/nfs/nfs42.h +++ b/fs/nfs/nfs42.h @@ -55,11 +55,14 @@ int nfs42_proc_removexattr(struct inode *inode, const char *name); * They would be 7 bytes long in the eventual buffer ("user.x\0"), and * 8 bytes long XDR-encoded. * - * Include the trailing eof word as well. + * Include the trailing eof word as well and make the result a multiple + * of 4 bytes. */ static inline u32 nfs42_listxattr_xdrsize(u32 buflen) { - return ((buflen / (XATTR_USER_PREFIX_LEN + 2)) * 8) + 4; + u32 size = 8 * buflen / (XATTR_USER_PREFIX_LEN + 2) + 4; + + return (size + 3) & ~3; } #endif /* CONFIG_NFS_V4_2 */ #endif /* __LINUX_FS_NFS_NFS4_2_H */ diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ec3f0103e1a7f4f41d8297964a21c2ae0eed783a..7cc74f7451d679a02821486564adfe1ea8d7a7c1 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -10592,29 +10592,33 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = { static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size) { ssize_t error, error2, error3; + size_t left = size; - error = generic_listxattr(dentry, list, size); + error = generic_listxattr(dentry, list, left); if (error < 0) return error; if (list) { list += error; - size -= error; + left -= error; } - error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, size); + error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, left); if (error2 < 0) return error2; if (list) { list += error2; - size -= error2; + left -= error2; } - error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, size); + error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, left); if (error3 < 0) return error3; - return error + error2 + error3; + error += error2 + error3; + if (size && error > size) + return -ERANGE; + return error; } static void nfs4_enable_swap(struct inode *inode) diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index 3fa77ad7258f2ffeda3fca7c12db1620b4840335..c8a57cfde64b43d05996adf3ad13e356cbe12f81 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -9,10 +9,10 @@ #define _TRACE_NFS4_H #include -#include +#include -#include -#include +#include +#include #define show_nfs_fattr_flags(valid) \ __print_flags((unsigned long)valid, "|", \ diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c index 620329b7e6aeb18eac2a5512e20592ef344ad506..0b1c1d2e076c1083fcb5e5169904986f5475e9d9 100644 --- a/fs/nfs/nfsroot.c +++ b/fs/nfs/nfsroot.c @@ -175,10 +175,10 @@ static int __init root_nfs_cat(char *dest, const char *src, size_t len = strlen(dest); if (len && dest[len - 1] != ',') - if (strlcat(dest, ",", destlen) > destlen) + if (strlcat(dest, ",", destlen) >= destlen) return -1; - if (strlcat(dest, src, destlen) > destlen) + if (strlcat(dest, src, destlen) >= destlen) return -1; return 0; } diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 8c6cc58679ff85f1d4730da3297443328c7eb4c5..642f6921852fa8c7895f60d1a6363811fdc16580 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -11,9 +11,9 @@ #include #include -#include -#include -#include +#include +#include +#include #define nfs_show_cache_validity(v) \ __print_flags(v, "|", \ diff --git a/fs/nfs/write.c b/fs/nfs/write.c index f41d24b54fd1f8b19a3e34e8cfad1bdb7b5ff206..8e21caae4cae244fb1c67c11cd6cafe8925bb2fb 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -667,8 +667,10 @@ static int nfs_writepage_locked(struct page *page, int err; if (wbc->sync_mode == WB_SYNC_NONE && - NFS_SERVER(inode)->write_congested) + NFS_SERVER(inode)->write_congested) { + redirty_page_for_writepage(wbc, page); return AOP_WRITEPAGE_ACTIVATE; + } nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); nfs_pageio_init_write(&pgio, inode, 0, @@ -1654,7 +1656,7 @@ static int wait_on_commit(struct nfs_mds_commit_info *cinfo) !atomic_read(&cinfo->rpcs_out)); } -static void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) +void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) { atomic_inc(&cinfo->rpcs_out); } diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index f6a2fd3015e75a20f627885ba36277c83f9a13ac..7c441f2bd4440c17bd1e5c59d172ff4595c8cb31 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -8,6 +8,7 @@ config NFSD select SUNRPC select EXPORTFS select NFS_ACL_SUPPORT if NFSD_V2_ACL + select NFS_ACL_SUPPORT if NFSD_V3_ACL depends on MULTIUSER help Choose Y here if you want to allow other computers to access @@ -26,19 +27,29 @@ config NFSD Below you can choose which versions of the NFS protocol are available to clients mounting the NFS server on this system. - Support for NFS version 2 (RFC 1094) is always available when + Support for NFS version 3 (RFC 1813) is always available when CONFIG_NFSD is selected. If unsure, say N. -config NFSD_V2_ACL - bool +config NFSD_V2 + bool "NFS server support for NFS version 2 (DEPRECATED)" depends on NFSD + default n + help + NFSv2 (RFC 1094) was the first publicly-released version of NFS. + Unless you are hosting ancient (1990's era) NFS clients, you don't + need this. + + If unsure, say N. + +config NFSD_V2_ACL + bool "NFS server support for the NFSv2 ACL protocol extension" + depends on NFSD_V2 config NFSD_V3_ACL bool "NFS server support for the NFSv3 ACL protocol extension" depends on NFSD - select NFSD_V2_ACL help Solaris NFS servers support an auxiliary NFSv3 ACL protocol that never became an official part of the NFS version 3 protocol. diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile index 805c06d5f1b4ba2daa57571b3c860eca47b22496..6fffc8f03f740857f2ae5cd59a3296f4b77ba56c 100644 --- a/fs/nfsd/Makefile +++ b/fs/nfsd/Makefile @@ -10,9 +10,10 @@ obj-$(CONFIG_NFSD) += nfsd.o # this one should be compiled first, as the tracing macros can easily blow up nfsd-y += trace.o -nfsd-y += nfssvc.o nfsctl.o nfsproc.o nfsfh.o vfs.o \ - export.o auth.o lockd.o nfscache.o nfsxdr.o \ +nfsd-y += nfssvc.o nfsctl.o nfsfh.o vfs.o \ + export.o auth.o lockd.o nfscache.o \ stats.o filecache.o nfs3proc.o nfs3xdr.o +nfsd-$(CONFIG_NFSD_V2) += nfsproc.o nfsxdr.o nfsd-$(CONFIG_NFSD_V2_ACL) += nfs2acl.o nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o nfsd-$(CONFIG_NFSD_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \ diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index e7e6e78d965db7bbf97c52906ab70b3559bda9df..01d7fd108cf3df6bd1abdd050c4a75c14b34fd3d 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -12,6 +12,7 @@ #include "blocklayoutxdr.h" #include "pnfs.h" #include "filecache.h" +#include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PNFS diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c index 2455dc8be18a86a74463e911f2137bae3a316a0d..1ed2f691ebb908670387c05da0968249a89041af 100644 --- a/fs/nfsd/blocklayoutxdr.c +++ b/fs/nfsd/blocklayoutxdr.c @@ -9,6 +9,7 @@ #include "nfsd.h" #include "blocklayoutxdr.h" +#include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PNFS diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h index ee0e3aba4a6e51df4c4e21cc9946665b1564b336..d03f7f6a8642d354f03d33306b2344996f57375f 100644 --- a/fs/nfsd/export.h +++ b/fs/nfsd/export.h @@ -115,7 +115,6 @@ struct svc_export * rqst_find_fsidzero_export(struct svc_rqst *); int exp_rootfh(struct net *, struct auth_domain *, char *path, struct knfsd_fh *, int maxsize); __be32 exp_pseudoroot(struct svc_rqst *, struct svc_fh *); -__be32 nfserrno(int errno); static inline void exp_put(struct svc_export *exp) { diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 5cb8cce153a574e6e83f2889eb1ade709c33d1da..ee9c923192e08a60a8e038a0621d86f4db442c0d 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -1,7 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * Open file cache. + * The NFSD open file cache. * * (c) 2015 - Jeff Layton + * + * An nfsd_file object is a per-file collection of open state that binds + * together: + * - a struct file * + * - a user credential + * - a network namespace + * - a read-ahead context + * - monitoring for writeback errors + * + * nfsd_file objects are reference-counted. Consumers acquire a new + * object via the nfsd_file_acquire API. They manage their interest in + * the acquired object, and hence the object's reference count, via + * nfsd_file_get and nfsd_file_put. There are two varieties of nfsd_file + * object: + * + * * non-garbage-collected: When a consumer wants to precisely control + * the lifetime of a file's open state, it acquires a non-garbage- + * collected nfsd_file. The final nfsd_file_put releases the open + * state immediately. + * + * * garbage-collected: When a consumer does not control the lifetime + * of open state, it acquires a garbage-collected nfsd_file. The + * final nfsd_file_put allows the open state to linger for a period + * during which it may be re-used. */ #include @@ -49,70 +74,9 @@ static struct list_lru nfsd_file_lru; static unsigned long nfsd_file_flags; static struct fsnotify_group *nfsd_file_fsnotify_group; static struct delayed_work nfsd_filecache_laundrette; -static struct rhashtable nfsd_file_rhash_tbl +static struct rhltable nfsd_file_rhltable ____cacheline_aligned_in_smp; -enum nfsd_file_lookup_type { - NFSD_FILE_KEY_INODE, - NFSD_FILE_KEY_FULL, -}; - -struct nfsd_file_lookup_key { - struct inode *inode; - struct net *net; - const struct cred *cred; - unsigned char need; - bool gc; - enum nfsd_file_lookup_type type; -}; - -/* - * The returned hash value is based solely on the address of an in-code - * inode, a pointer to a slab-allocated object. The entropy in such a - * pointer is concentrated in its middle bits. - */ -static u32 nfsd_file_inode_hash(const struct inode *inode, u32 seed) -{ - unsigned long ptr = (unsigned long)inode; - u32 k; - - k = ptr >> L1_CACHE_SHIFT; - k &= 0x00ffffff; - return jhash2(&k, 1, seed); -} - -/** - * nfsd_file_key_hashfn - Compute the hash value of a lookup key - * @data: key on which to compute the hash value - * @len: rhash table's key_len parameter (unused) - * @seed: rhash table's random seed of the day - * - * Return value: - * Computed 32-bit hash value - */ -static u32 nfsd_file_key_hashfn(const void *data, u32 len, u32 seed) -{ - const struct nfsd_file_lookup_key *key = data; - - return nfsd_file_inode_hash(key->inode, seed); -} - -/** - * nfsd_file_obj_hashfn - Compute the hash value of an nfsd_file - * @data: object on which to compute the hash value - * @len: rhash table's key_len parameter (unused) - * @seed: rhash table's random seed of the day - * - * Return value: - * Computed 32-bit hash value - */ -static u32 nfsd_file_obj_hashfn(const void *data, u32 len, u32 seed) -{ - const struct nfsd_file *nf = data; - - return nfsd_file_inode_hash(nf->nf_inode, seed); -} - static bool nfsd_match_cred(const struct cred *c1, const struct cred *c2) { @@ -133,65 +97,25 @@ nfsd_match_cred(const struct cred *c1, const struct cred *c2) return true; } -/** - * nfsd_file_obj_cmpfn - Match a cache item against search criteria - * @arg: search criteria - * @ptr: cache item to check - * - * Return values: - * %0 - Item matches search criteria - * %1 - Item does not match search criteria - */ -static int nfsd_file_obj_cmpfn(struct rhashtable_compare_arg *arg, - const void *ptr) -{ - const struct nfsd_file_lookup_key *key = arg->key; - const struct nfsd_file *nf = ptr; - - switch (key->type) { - case NFSD_FILE_KEY_INODE: - if (nf->nf_inode != key->inode) - return 1; - break; - case NFSD_FILE_KEY_FULL: - if (nf->nf_inode != key->inode) - return 1; - if (nf->nf_may != key->need) - return 1; - if (nf->nf_net != key->net) - return 1; - if (!nfsd_match_cred(nf->nf_cred, key->cred)) - return 1; - if (!!test_bit(NFSD_FILE_GC, &nf->nf_flags) != key->gc) - return 1; - if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) - return 1; - break; - } - return 0; -} - static const struct rhashtable_params nfsd_file_rhash_params = { .key_len = sizeof_field(struct nfsd_file, nf_inode), .key_offset = offsetof(struct nfsd_file, nf_inode), - .head_offset = offsetof(struct nfsd_file, nf_rhash), - .hashfn = nfsd_file_key_hashfn, - .obj_hashfn = nfsd_file_obj_hashfn, - .obj_cmpfn = nfsd_file_obj_cmpfn, - /* Reduce resizing churn on light workloads */ - .min_size = 512, /* buckets */ + .head_offset = offsetof(struct nfsd_file, nf_rlist), + + /* + * Start with a single page hash table to reduce resizing churn + * on light workloads. + */ + .min_size = 256, .automatic_shrinking = true, }; static void nfsd_file_schedule_laundrette(void) { - if ((atomic_read(&nfsd_file_rhash_tbl.nelems) == 0) || - test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 0) - return; - - queue_delayed_work(system_wq, &nfsd_filecache_laundrette, - NFSD_LAUNDRETTE_DELAY); + if (test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags)) + queue_delayed_work(system_wq, &nfsd_filecache_laundrette, + NFSD_LAUNDRETTE_DELAY); } static void @@ -285,27 +209,27 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf, struct inode *inode) } static struct nfsd_file * -nfsd_file_alloc(struct nfsd_file_lookup_key *key, unsigned int may) +nfsd_file_alloc(struct net *net, struct inode *inode, unsigned char need, + bool want_gc) { struct nfsd_file *nf; nf = kmem_cache_alloc(nfsd_file_slab, GFP_KERNEL); - if (nf) { - INIT_LIST_HEAD(&nf->nf_lru); - nf->nf_birthtime = ktime_get(); - nf->nf_file = NULL; - nf->nf_cred = get_current_cred(); - nf->nf_net = key->net; - nf->nf_flags = 0; - __set_bit(NFSD_FILE_HASHED, &nf->nf_flags); - __set_bit(NFSD_FILE_PENDING, &nf->nf_flags); - if (key->gc) - __set_bit(NFSD_FILE_GC, &nf->nf_flags); - nf->nf_inode = key->inode; - refcount_set(&nf->nf_ref, 1); - nf->nf_may = key->need; - nf->nf_mark = NULL; - } + if (unlikely(!nf)) + return NULL; + + INIT_LIST_HEAD(&nf->nf_lru); + nf->nf_birthtime = ktime_get(); + nf->nf_file = NULL; + nf->nf_cred = get_current_cred(); + nf->nf_net = net; + nf->nf_flags = want_gc ? + BIT(NFSD_FILE_HASHED) | BIT(NFSD_FILE_PENDING) | BIT(NFSD_FILE_GC) : + BIT(NFSD_FILE_HASHED) | BIT(NFSD_FILE_PENDING); + nf->nf_inode = inode; + refcount_set(&nf->nf_ref, 1); + nf->nf_may = need; + nf->nf_mark = NULL; return nf; } @@ -330,8 +254,8 @@ static void nfsd_file_hash_remove(struct nfsd_file *nf) { trace_nfsd_file_unhash(nf); - rhashtable_remove_fast(&nfsd_file_rhash_tbl, &nf->nf_rhash, - nfsd_file_rhash_params); + rhltable_remove(&nfsd_file_rhltable, &nf->nf_rlist, + nfsd_file_rhash_params); } static bool @@ -358,10 +282,8 @@ nfsd_file_free(struct nfsd_file *nf) if (nf->nf_mark) nfsd_file_mark_put(nf->nf_mark); if (nf->nf_file) { - get_file(nf->nf_file); - filp_close(nf->nf_file, NULL); nfsd_file_check_write_error(nf); - fput(nf->nf_file); + filp_close(nf->nf_file, NULL); } /* @@ -380,13 +302,23 @@ nfsd_file_check_writeback(struct nfsd_file *nf) struct file *file = nf->nf_file; struct address_space *mapping; - if (!file || !(file->f_mode & FMODE_WRITE)) + /* File not open for write? */ + if (!(file->f_mode & FMODE_WRITE)) return false; + + /* + * Some filesystems (e.g. NFS) flush all dirty data on close. + * On others, there is no need to wait for writeback. + */ + if (!(file_inode(file)->i_sb->s_export_op->flags & EXPORT_OP_FLUSH_ON_CLOSE)) + return false; + mapping = file->f_mapping; return mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) || mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK); } + static bool nfsd_file_lru_add(struct nfsd_file *nf) { set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags); @@ -409,7 +341,7 @@ static bool nfsd_file_lru_remove(struct nfsd_file *nf) struct nfsd_file * nfsd_file_get(struct nfsd_file *nf) { - if (likely(refcount_inc_not_zero(&nf->nf_ref))) + if (nf && refcount_inc_not_zero(&nf->nf_ref)) return nf; return NULL; } @@ -470,49 +402,26 @@ nfsd_file_dispose_list(struct list_head *dispose) } } -static void -nfsd_file_list_remove_disposal(struct list_head *dst, - struct nfsd_fcache_disposal *l) -{ - spin_lock(&l->lock); - list_splice_init(&l->freeme, dst); - spin_unlock(&l->lock); -} - -static void -nfsd_file_list_add_disposal(struct list_head *files, struct net *net) -{ - struct nfsd_net *nn = net_generic(net, nfsd_net_id); - struct nfsd_fcache_disposal *l = nn->fcache_disposal; - - spin_lock(&l->lock); - list_splice_tail_init(files, &l->freeme); - spin_unlock(&l->lock); - queue_work(nfsd_filecache_wq, &l->work); -} - -static void -nfsd_file_list_add_pernet(struct list_head *dst, struct list_head *src, - struct net *net) -{ - struct nfsd_file *nf, *tmp; - - list_for_each_entry_safe(nf, tmp, src, nf_lru) { - if (nf->nf_net == net) - list_move_tail(&nf->nf_lru, dst); - } -} - +/** + * nfsd_file_dispose_list_delayed - move list of dead files to net's freeme list + * @dispose: list of nfsd_files to be disposed + * + * Transfers each file to the "freeme" list for its nfsd_net, to eventually + * be disposed of by the per-net garbage collector. + */ static void nfsd_file_dispose_list_delayed(struct list_head *dispose) { - LIST_HEAD(list); - struct nfsd_file *nf; - while(!list_empty(dispose)) { - nf = list_first_entry(dispose, struct nfsd_file, nf_lru); - nfsd_file_list_add_pernet(&list, dispose, nf->nf_net); - nfsd_file_list_add_disposal(&list, nf->nf_net); + struct nfsd_file *nf = list_first_entry(dispose, + struct nfsd_file, nf_lru); + struct nfsd_net *nn = net_generic(nf->nf_net, nfsd_net_id); + struct nfsd_fcache_disposal *l = nn->fcache_disposal; + + spin_lock(&l->lock); + list_move_tail(&nf->nf_lru, &l->freeme); + spin_unlock(&l->lock); + queue_work(nfsd_filecache_wq, &l->work); } } @@ -589,7 +498,8 @@ static void nfsd_file_gc_worker(struct work_struct *work) { nfsd_file_gc(); - nfsd_file_schedule_laundrette(); + if (list_lru_count(&nfsd_file_lru)) + nfsd_file_schedule_laundrette(); } static unsigned long @@ -655,8 +565,8 @@ nfsd_file_cond_queue(struct nfsd_file *nf, struct list_head *dispose) * @inode: inode on which to close out nfsd_files * @dispose: list on which to gather nfsd_files to close out * - * An nfsd_file represents a struct file being held open on behalf of nfsd. An - * open file however can block other activity (such as leases), or cause + * An nfsd_file represents a struct file being held open on behalf of nfsd. + * An open file however can block other activity (such as leases), or cause * undesirable behavior (e.g. spurious silly-renames when reexporting NFS). * * This function is intended to find open nfsd_files when this sort of @@ -669,20 +579,17 @@ nfsd_file_cond_queue(struct nfsd_file *nf, struct list_head *dispose) static void nfsd_file_queue_for_close(struct inode *inode, struct list_head *dispose) { - struct nfsd_file_lookup_key key = { - .type = NFSD_FILE_KEY_INODE, - .inode = inode, - }; + struct rhlist_head *tmp, *list; struct nfsd_file *nf; rcu_read_lock(); - do { - nf = rhashtable_lookup(&nfsd_file_rhash_tbl, &key, - nfsd_file_rhash_params); - if (!nf) - break; + list = rhltable_lookup(&nfsd_file_rhltable, &inode, + nfsd_file_rhash_params); + rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist) { + if (!test_bit(NFSD_FILE_GC, &nf->nf_flags)) + continue; nfsd_file_cond_queue(nf, dispose); - } while (1); + } rcu_read_unlock(); } @@ -735,8 +642,8 @@ nfsd_file_close_inode_sync(struct inode *inode) * nfsd_file_delayed_close - close unused nfsd_files * @work: dummy * - * Walk the LRU list and destroy any entries that have not been used since - * the last scan. + * Scrape the freeme list for this nfsd_net, and then dispose of them + * all. */ static void nfsd_file_delayed_close(struct work_struct *work) @@ -745,7 +652,10 @@ nfsd_file_delayed_close(struct work_struct *work) struct nfsd_fcache_disposal *l = container_of(work, struct nfsd_fcache_disposal, work); - nfsd_file_list_remove_disposal(&head, l); + spin_lock(&l->lock); + list_splice_init(&l->freeme, &head); + spin_unlock(&l->lock); + nfsd_file_dispose_list(&head); } @@ -806,7 +716,7 @@ nfsd_file_cache_init(void) if (test_and_set_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 1) return 0; - ret = rhashtable_init(&nfsd_file_rhash_tbl, &nfsd_file_rhash_params); + ret = rhltable_init(&nfsd_file_rhltable, &nfsd_file_rhash_params); if (ret) return ret; @@ -874,7 +784,7 @@ out_err: nfsd_file_mark_slab = NULL; destroy_workqueue(nfsd_filecache_wq); nfsd_filecache_wq = NULL; - rhashtable_destroy(&nfsd_file_rhash_tbl); + rhltable_destroy(&nfsd_file_rhltable); goto out; } @@ -883,7 +793,8 @@ out_err: * @net: net-namespace to shut down the cache (may be NULL) * * Walk the nfsd_file cache and close out any that match @net. If @net is NULL, - * then close out everything. Called when an nfsd instance is being shut down. + * then close out everything. Called when an nfsd instance is being shut down, + * and when the exports table is flushed. */ static void __nfsd_file_cache_purge(struct net *net) @@ -892,7 +803,7 @@ __nfsd_file_cache_purge(struct net *net) struct nfsd_file *nf; LIST_HEAD(dispose); - rhashtable_walk_enter(&nfsd_file_rhash_tbl, &iter); + rhltable_walk_enter(&nfsd_file_rhltable, &iter); do { rhashtable_walk_start(&iter); @@ -998,7 +909,7 @@ nfsd_file_cache_shutdown(void) nfsd_file_mark_slab = NULL; destroy_workqueue(nfsd_filecache_wq); nfsd_filecache_wq = NULL; - rhashtable_destroy(&nfsd_file_rhash_tbl); + rhltable_destroy(&nfsd_file_rhltable); for_each_possible_cpu(i) { per_cpu(nfsd_file_cache_hits, i) = 0; @@ -1009,6 +920,35 @@ nfsd_file_cache_shutdown(void) } } +static struct nfsd_file * +nfsd_file_lookup_locked(const struct net *net, const struct cred *cred, + struct inode *inode, unsigned char need, + bool want_gc) +{ + struct rhlist_head *tmp, *list; + struct nfsd_file *nf; + + list = rhltable_lookup(&nfsd_file_rhltable, &inode, + nfsd_file_rhash_params); + rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist) { + if (nf->nf_may != need) + continue; + if (nf->nf_net != net) + continue; + if (!nfsd_match_cred(nf->nf_cred, cred)) + continue; + if (test_bit(NFSD_FILE_GC, &nf->nf_flags) != want_gc) + continue; + if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) + continue; + + if (!nfsd_file_get(nf)) + continue; + return nf; + } + return NULL; +} + /** * nfsd_file_is_cached - are there any cached open files for this inode? * @inode: inode to check @@ -1023,15 +963,20 @@ nfsd_file_cache_shutdown(void) bool nfsd_file_is_cached(struct inode *inode) { - struct nfsd_file_lookup_key key = { - .type = NFSD_FILE_KEY_INODE, - .inode = inode, - }; + struct rhlist_head *tmp, *list; + struct nfsd_file *nf; bool ret = false; - if (rhashtable_lookup_fast(&nfsd_file_rhash_tbl, &key, - nfsd_file_rhash_params) != NULL) - ret = true; + rcu_read_lock(); + list = rhltable_lookup(&nfsd_file_rhltable, &inode, + nfsd_file_rhash_params); + rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist) + if (test_bit(NFSD_FILE_GC, &nf->nf_flags)) { + ret = true; + break; + } + rcu_read_unlock(); + trace_nfsd_file_is_cached(inode, (int)ret); return ret; } @@ -1041,14 +986,12 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct file *file, struct nfsd_file **pnf, bool want_gc) { - struct nfsd_file_lookup_key key = { - .type = NFSD_FILE_KEY_FULL, - .need = may_flags & NFSD_FILE_MAY_MASK, - .net = SVC_NET(rqstp), - .gc = want_gc, - }; + unsigned char need = may_flags & NFSD_FILE_MAY_MASK; + struct net *net = SVC_NET(rqstp); + struct nfsd_file *new, *nf; + const struct cred *cred; bool open_retry = true; - struct nfsd_file *nf; + struct inode *inode; __be32 status; int ret; @@ -1056,81 +999,88 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, may_flags|NFSD_MAY_OWNER_OVERRIDE); if (status != nfs_ok) return status; - key.inode = d_inode(fhp->fh_dentry); - key.cred = get_current_cred(); + inode = d_inode(fhp->fh_dentry); + cred = get_current_cred(); retry: rcu_read_lock(); - nf = rhashtable_lookup(&nfsd_file_rhash_tbl, &key, - nfsd_file_rhash_params); - if (nf) - nf = nfsd_file_get(nf); + nf = nfsd_file_lookup_locked(net, cred, inode, need, want_gc); rcu_read_unlock(); if (nf) { + /* + * If the nf is on the LRU then it holds an extra reference + * that must be put if it's removed. It had better not be + * the last one however, since we should hold another. + */ if (nfsd_file_lru_remove(nf)) WARN_ON_ONCE(refcount_dec_and_test(&nf->nf_ref)); goto wait_for_construction; } - nf = nfsd_file_alloc(&key, may_flags); - if (!nf) { + new = nfsd_file_alloc(net, inode, need, want_gc); + if (!new) { status = nfserr_jukebox; - goto out_status; + goto out; } - ret = rhashtable_lookup_insert_key(&nfsd_file_rhash_tbl, - &key, &nf->nf_rhash, - nfsd_file_rhash_params); + rcu_read_lock(); + spin_lock(&inode->i_lock); + nf = nfsd_file_lookup_locked(net, cred, inode, need, want_gc); + if (unlikely(nf)) { + spin_unlock(&inode->i_lock); + rcu_read_unlock(); + nfsd_file_slab_free(&new->nf_rcu); + goto wait_for_construction; + } + nf = new; + ret = rhltable_insert(&nfsd_file_rhltable, &nf->nf_rlist, + nfsd_file_rhash_params); + spin_unlock(&inode->i_lock); + rcu_read_unlock(); if (likely(ret == 0)) goto open_file; - nfsd_file_slab_free(&nf->nf_rcu); - nf = NULL; if (ret == -EEXIST) goto retry; - trace_nfsd_file_insert_err(rqstp, key.inode, may_flags, ret); + trace_nfsd_file_insert_err(rqstp, inode, may_flags, ret); status = nfserr_jukebox; - goto out_status; + goto construction_err; wait_for_construction: wait_on_bit(&nf->nf_flags, NFSD_FILE_PENDING, TASK_UNINTERRUPTIBLE); /* Did construction of this file fail? */ if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { - trace_nfsd_file_cons_err(rqstp, key.inode, may_flags, nf); + trace_nfsd_file_cons_err(rqstp, inode, may_flags, nf); if (!open_retry) { status = nfserr_jukebox; - goto out; + goto construction_err; } open_retry = false; - if (refcount_dec_and_test(&nf->nf_ref)) - nfsd_file_free(nf); goto retry; } - this_cpu_inc(nfsd_file_cache_hits); status = nfserrno(nfsd_open_break_lease(file_inode(nf->nf_file), may_flags)); + if (status != nfs_ok) { + nfsd_file_put(nf); + nf = NULL; + } + out: if (status == nfs_ok) { this_cpu_inc(nfsd_file_acquisitions); nfsd_file_check_write_error(nf); *pnf = nf; - } else { - if (refcount_dec_and_test(&nf->nf_ref)) - nfsd_file_free(nf); - nf = NULL; } - -out_status: - put_cred(key.cred); - trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status); + put_cred(cred); + trace_nfsd_file_acquire(rqstp, inode, may_flags, nf, status); return status; open_file: trace_nfsd_file_alloc(nf); - nf->nf_mark = nfsd_file_mark_find_or_create(nf, key.inode); + nf->nf_mark = nfsd_file_mark_find_or_create(nf, inode); if (nf->nf_mark) { if (file) { get_file(file); @@ -1148,13 +1098,16 @@ open_file: * If construction failed, or we raced with a call to unlink() * then unhash. */ - if (status == nfs_ok && key.inode->i_nlink == 0) - status = nfserr_jukebox; - if (status != nfs_ok) + if (status != nfs_ok || inode->i_nlink == 0) nfsd_file_unhash(nf); - clear_bit_unlock(NFSD_FILE_PENDING, &nf->nf_flags); - smp_mb__after_atomic(); - wake_up_bit(&nf->nf_flags, NFSD_FILE_PENDING); + clear_and_wake_up_bit(NFSD_FILE_PENDING, &nf->nf_flags); + if (status == nfs_ok) + goto out; + +construction_err: + if (refcount_dec_and_test(&nf->nf_ref)) + nfsd_file_free(nf); + nf = NULL; goto out; } @@ -1170,8 +1123,11 @@ open_file: * seconds after the final nfsd_file_put() in case the caller * wants to re-use it. * - * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in - * network byte order is returned. + * Return values: + * %nfs_ok - @pnf points to an nfsd_file with its reference + * count boosted. + * + * On error, an nfsstat value in network byte order is returned. */ __be32 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp, @@ -1191,8 +1147,11 @@ nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp, * but not garbage-collected. The object is unhashed after the * final nfsd_file_put(). * - * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in - * network byte order is returned. + * Return values: + * %nfs_ok - @pnf points to an nfsd_file with its reference + * count boosted. + * + * On error, an nfsstat value in network byte order is returned. */ __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, @@ -1213,8 +1172,11 @@ nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, * and @file is non-NULL, use it to instantiate a new nfsd_file instead of * opening a new one. * - * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in - * network byte order is returned. + * Return values: + * %nfs_ok - @pnf points to an nfsd_file with its reference + * count boosted. + * + * On error, an nfsstat value in network byte order is returned. */ __be32 nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp, @@ -1245,7 +1207,7 @@ int nfsd_file_cache_stats_show(struct seq_file *m, void *v) lru = list_lru_count(&nfsd_file_lru); rcu_read_lock(); - ht = &nfsd_file_rhash_tbl; + ht = &nfsd_file_rhltable.ht; count = atomic_read(&ht->nelems); tbl = rht_dereference_rcu(ht->tbl, ht); buckets = tbl->size; @@ -1261,7 +1223,7 @@ int nfsd_file_cache_stats_show(struct seq_file *m, void *v) evictions += per_cpu(nfsd_file_evictions, i); } - seq_printf(m, "total entries: %u\n", count); + seq_printf(m, "total inodes: %u\n", count); seq_printf(m, "hash buckets: %u\n", buckets); seq_printf(m, "lru entries: %lu\n", lru); seq_printf(m, "cache hits: %lu\n", hits); diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h index 41516a4263ea519c8af05e85d82f8ca87a248e4f..e54165a3224f0be68e88c8ee33e037fcaca691e0 100644 --- a/fs/nfsd/filecache.h +++ b/fs/nfsd/filecache.h @@ -29,9 +29,8 @@ struct nfsd_file_mark { * never be dereferenced, only used for comparison. */ struct nfsd_file { - struct rhash_head nf_rhash; - struct list_head nf_lru; - struct rcu_head nf_rcu; + struct rhlist_head nf_rlist; + void *nf_inode; struct file *nf_file; const struct cred *nf_cred; struct net *nf_net; @@ -40,10 +39,12 @@ struct nfsd_file { #define NFSD_FILE_REFERENCED (2) #define NFSD_FILE_GC (3) unsigned long nf_flags; - struct inode *nf_inode; /* don't deref */ refcount_t nf_ref; unsigned char nf_may; + struct nfsd_file_mark *nf_mark; + struct list_head nf_lru; + struct rcu_head nf_rcu; ktime_t nf_birthtime; }; diff --git a/fs/nfsd/flexfilelayout.c b/fs/nfsd/flexfilelayout.c index 070f90ed09b61336394a2d903bfedcdaa77de341..3ca5304440ff0a61b026fb42adc28b7a0b5b8f9e 100644 --- a/fs/nfsd/flexfilelayout.c +++ b/fs/nfsd/flexfilelayout.c @@ -15,6 +15,7 @@ #include "flexfilelayoutxdr.h" #include "pnfs.h" +#include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PNFS diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 8c854ba3285bbcddfe62010dc6b93018fdc3927c..51a4b7885cae2a2a5f5cab4932ebcd6306d10348 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -195,7 +195,7 @@ struct nfsd_net { atomic_t nfsd_courtesy_clients; struct shrinker nfsd_client_shrinker; - struct delayed_work nfsd_shrinker_work; + struct work_struct nfsd_shrinker_work; }; /* Simple check to find out if a given net was properly initialized */ diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 39989c14c8a1e5646c2286611408e517b71e9243..4eae2c5af2edf4de95c5e63a18a4634e1ca87872 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -76,6 +76,17 @@ static __be32 *xdr_encode_empty_array(__be32 *p) * 1 Protocol" */ +static void encode_uint32(struct xdr_stream *xdr, u32 n) +{ + WARN_ON_ONCE(xdr_stream_encode_u32(xdr, n) < 0); +} + +static void encode_bitmap4(struct xdr_stream *xdr, const __u32 *bitmap, + size_t len) +{ + WARN_ON_ONCE(xdr_stream_encode_uint32_array(xdr, bitmap, len) < 0); +} + /* * nfs_cb_opnum4 * @@ -328,6 +339,24 @@ static void encode_cb_recall4args(struct xdr_stream *xdr, hdr->nops++; } +/* + * CB_RECALLANY4args + * + * struct CB_RECALLANY4args { + * uint32_t craa_objects_to_keep; + * bitmap4 craa_type_mask; + * }; + */ +static void +encode_cb_recallany4args(struct xdr_stream *xdr, + struct nfs4_cb_compound_hdr *hdr, struct nfsd4_cb_recall_any *ra) +{ + encode_nfs_cb_opnum4(xdr, OP_CB_RECALL_ANY); + encode_uint32(xdr, ra->ra_keep); + encode_bitmap4(xdr, ra->ra_bmval, ARRAY_SIZE(ra->ra_bmval)); + hdr->nops++; +} + /* * CB_SEQUENCE4args * @@ -482,6 +511,26 @@ static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr, encode_cb_nops(&hdr); } +/* + * 20.6. Operation 8: CB_RECALL_ANY - Keep Any N Recallable Objects + */ +static void +nfs4_xdr_enc_cb_recall_any(struct rpc_rqst *req, + struct xdr_stream *xdr, const void *data) +{ + const struct nfsd4_callback *cb = data; + struct nfsd4_cb_recall_any *ra; + struct nfs4_cb_compound_hdr hdr = { + .ident = cb->cb_clp->cl_cb_ident, + .minorversion = cb->cb_clp->cl_minorversion, + }; + + ra = container_of(cb, struct nfsd4_cb_recall_any, ra_cb); + encode_cb_compound4args(xdr, &hdr); + encode_cb_sequence4args(xdr, cb, &hdr); + encode_cb_recallany4args(xdr, &hdr, ra); + encode_cb_nops(&hdr); +} /* * NFSv4.0 and NFSv4.1 XDR decode functions @@ -520,6 +569,28 @@ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, return decode_cb_op_status(xdr, OP_CB_RECALL, &cb->cb_status); } +/* + * 20.6. Operation 8: CB_RECALL_ANY - Keep Any N Recallable Objects + */ +static int +nfs4_xdr_dec_cb_recall_any(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *data) +{ + struct nfsd4_callback *cb = data; + struct nfs4_cb_compound_hdr hdr; + int status; + + status = decode_cb_compound4res(xdr, &hdr); + if (unlikely(status)) + return status; + status = decode_cb_sequence4res(xdr, cb); + if (unlikely(status || cb->cb_seq_status)) + return status; + status = decode_cb_op_status(xdr, OP_CB_RECALL_ANY, &cb->cb_status); + return status; +} + #ifdef CONFIG_NFSD_PNFS /* * CB_LAYOUTRECALL4args @@ -783,6 +854,7 @@ static const struct rpc_procinfo nfs4_cb_procedures[] = { #endif PROC(CB_NOTIFY_LOCK, COMPOUND, cb_notify_lock, cb_notify_lock), PROC(CB_OFFLOAD, COMPOUND, cb_offload, cb_offload), + PROC(CB_RECALL_ANY, COMPOUND, cb_recall_any, cb_recall_any), }; static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)]; diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index e70a1a2999b7b4f2943478259c144f14beb0b1b0..5e9809aff37ebcd3792024b70fced4df745be274 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -41,6 +41,7 @@ #include "idmap.h" #include "nfsd.h" #include "netns.h" +#include "vfs.h" /* * Turn off idmapping when using AUTH_SYS. diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index a9105e95b59c5424eddbdf123186f434e439451a..b6d768bd5ccca463379f7d5f41166dc5723eaf7f 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -943,12 +943,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &read->rd_stateid, RD_STATE, &read->rd_nf, NULL); - if (status) { - dprintk("NFSD: nfsd4_read: couldn't process stateid!\n"); - goto out; - } - status = nfs_ok; -out: + read->rd_rqstp = rqstp; read->rd_fhp = &cstate->current_fh; return status; @@ -1117,10 +1112,8 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &setattr->sa_stateid, WR_STATE, NULL, NULL); - if (status) { - dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n"); + if (status) return status; - } } err = fh_want_write(&cstate->current_fh); if (err) @@ -1170,10 +1163,8 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, write->wr_offset, cnt); status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, stateid, WR_STATE, &nf, NULL); - if (status) { - dprintk("NFSD: nfsd4_write: couldn't process stateid!\n"); + if (status) return status; - } write->wr_how_written = write->wr_stable_how; @@ -1204,17 +1195,13 @@ nfsd4_verify_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh, src_stateid, RD_STATE, src, NULL); - if (status) { - dprintk("NFSD: %s: couldn't process src stateid!\n", __func__); + if (status) goto out; - } status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, dst_stateid, WR_STATE, dst, NULL); - if (status) { - dprintk("NFSD: %s: couldn't process dst stateid!\n", __func__); + if (status) goto out_put_src; - } /* fix up for NFS-specific error code */ if (!S_ISREG(file_inode((*src)->nf_file)->i_mode) || @@ -1326,12 +1313,11 @@ try_again: /* found a match */ if (ni->nsui_busy) { /* wait - and try again */ - prepare_to_wait(&nn->nfsd_ssc_waitq, &wait, - TASK_INTERRUPTIBLE); + prepare_to_wait(&nn->nfsd_ssc_waitq, &wait, TASK_IDLE); spin_unlock(&nn->nfsd_ssc_lock); /* allow 20secs for mount/unmount for now - revisit */ - if (signal_pending(current) || + if (kthread_should_stop() || (schedule_timeout(20*HZ) == 0)) { finish_wait(&nn->nfsd_ssc_waitq, &wait); kfree(work); @@ -1935,10 +1921,8 @@ nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &fallocate->falloc_stateid, WR_STATE, &nf, NULL); - if (status != nfs_ok) { - dprintk("NFSD: nfsd4_fallocate: couldn't process stateid!\n"); + if (status != nfs_ok) return status; - } status = nfsd4_vfs_fallocate(rqstp, &cstate->current_fh, nf->nf_file, fallocate->falloc_offset, @@ -1994,10 +1978,8 @@ nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &seek->seek_stateid, RD_STATE, &nf, NULL); - if (status) { - dprintk("NFSD: nfsd4_seek: couldn't process stateid!\n"); + if (status) return status; - } switch (seek->seek_whence) { case NFS4_CONTENT_DATA: diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index faecdbfa01a29c1ab88d1543724455396e93c341..8d15959004ad2579ff9238fe7432daf141c4f457 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -44,7 +44,9 @@ #include #include #include +#include #include + #include "xdr4.h" #include "xdr4cb.h" #include "vfs.h" @@ -84,6 +86,7 @@ static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) static void nfs4_free_ol_stateid(struct nfs4_stid *stid); void nfsd4_end_grace(struct nfsd_net *nn); static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps); +static void nfsd4_file_hash_remove(struct nfs4_file *fi); /* Locking: */ @@ -588,11 +591,8 @@ static void nfsd4_free_file_rcu(struct rcu_head *rcu) void put_nfs4_file(struct nfs4_file *fi) { - might_lock(&state_lock); - - if (refcount_dec_and_lock(&fi->fi_ref, &state_lock)) { - hlist_del_rcu(&fi->fi_hash); - spin_unlock(&state_lock); + if (refcount_dec_and_test(&fi->fi_ref)) { + nfsd4_file_hash_remove(fi); WARN_ON_ONCE(!list_empty(&fi->fi_clnt_odstate)); WARN_ON_ONCE(!list_empty(&fi->fi_delegations)); call_rcu(&fi->fi_rcu, nfsd4_free_file_rcu); @@ -602,9 +602,7 @@ put_nfs4_file(struct nfs4_file *fi) static struct nfsd_file * __nfs4_get_fd(struct nfs4_file *f, int oflag) { - if (f->fi_fds[oflag]) - return nfsd_file_get(f->fi_fds[oflag]); - return NULL; + return nfsd_file_get(f->fi_fds[oflag]); } static struct nfsd_file * @@ -717,19 +715,20 @@ static unsigned int ownerstr_hashval(struct xdr_netobj *ownername) return ret & OWNER_HASH_MASK; } -/* hash table for nfs4_file */ -#define FILE_HASH_BITS 8 -#define FILE_HASH_SIZE (1 << FILE_HASH_BITS) +static struct rhltable nfs4_file_rhltable ____cacheline_aligned_in_smp; -static unsigned int file_hashval(struct svc_fh *fh) -{ - struct inode *inode = d_inode(fh->fh_dentry); +static const struct rhashtable_params nfs4_file_rhash_params = { + .key_len = sizeof_field(struct nfs4_file, fi_inode), + .key_offset = offsetof(struct nfs4_file, fi_inode), + .head_offset = offsetof(struct nfs4_file, fi_rlist), - /* XXX: why not (here & in file cache) use inode? */ - return (unsigned int)hash_long(inode->i_ino, FILE_HASH_BITS); -} - -static struct hlist_head file_hashtbl[FILE_HASH_SIZE]; + /* + * Start with a single page hash table to reduce resizing churn + * on light workloads. + */ + .min_size = 256, + .automatic_shrinking = true, +}; /* * Check if courtesy clients have conflicting access and resolve it if possible @@ -1367,6 +1366,8 @@ static void revoke_delegation(struct nfs4_delegation *dp) WARN_ON(!list_empty(&dp->dl_recall_lru)); + trace_nfsd_stid_revoke(&dp->dl_stid); + if (clp->cl_minorversion) { spin_lock(&clp->cl_lock); dp->dl_stid.sc_type = NFS4_REVOKED_DELEG_STID; @@ -1831,13 +1832,12 @@ static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fattrs, int numslots = fattrs->maxreqs; int slotsize = slot_bytes(fattrs); struct nfsd4_session *new; - int mem, i; + int i; - BUILD_BUG_ON(NFSD_MAX_SLOTS_PER_SESSION * sizeof(struct nfsd4_slot *) - + sizeof(struct nfsd4_session) > PAGE_SIZE); - mem = numslots * sizeof(struct nfsd4_slot *); + BUILD_BUG_ON(struct_size(new, se_slots, NFSD_MAX_SLOTS_PER_SESSION) + > PAGE_SIZE); - new = kzalloc(sizeof(*new) + mem, GFP_KERNEL); + new = kzalloc(struct_size(new, se_slots, numslots), GFP_KERNEL); if (!new) return NULL; /* allocate each struct nfsd4_slot and data cache in one piece */ @@ -2143,6 +2143,7 @@ static void __free_client(struct kref *k) kfree(clp->cl_nii_domain.data); kfree(clp->cl_nii_name.data); idr_destroy(&clp->cl_stateids); + kfree(clp->cl_ra); kmem_cache_free(client_slab, clp); } @@ -2870,6 +2871,34 @@ static const struct tree_descr client_files[] = { [3] = {""}, }; +static int +nfsd4_cb_recall_any_done(struct nfsd4_callback *cb, + struct rpc_task *task) +{ + trace_nfsd_cb_recall_any_done(cb, task); + switch (task->tk_status) { + case -NFS4ERR_DELAY: + rpc_delay(task, 2 * HZ); + return 0; + default: + return 1; + } +} + +static void +nfsd4_cb_recall_any_release(struct nfsd4_callback *cb) +{ + struct nfs4_client *clp = cb->cb_clp; + + clear_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); + drop_client(clp); +} + +static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = { + .done = nfsd4_cb_recall_any_done, + .release = nfsd4_cb_recall_any_release, +}; + static struct nfs4_client *create_client(struct xdr_netobj name, struct svc_rqst *rqstp, nfs4_verifier *verf) { @@ -2907,6 +2936,14 @@ static struct nfs4_client *create_client(struct xdr_netobj name, free_client(clp); return NULL; } + clp->cl_ra = kzalloc(sizeof(*clp->cl_ra), GFP_KERNEL); + if (!clp->cl_ra) { + free_client(clp); + return NULL; + } + clp->cl_ra_time = 0; + nfsd4_init_cb(&clp->cl_ra->ra_cb, clp, &nfsd4_cb_recall_any_ops, + NFSPROC4_CLNT_CB_RECALL_ANY); return clp; } @@ -4276,11 +4313,9 @@ static struct nfs4_file *nfsd4_alloc_file(void) } /* OPEN Share state helper functions */ -static void nfsd4_init_file(struct svc_fh *fh, unsigned int hashval, - struct nfs4_file *fp) -{ - lockdep_assert_held(&state_lock); +static void nfsd4_file_init(const struct svc_fh *fh, struct nfs4_file *fp) +{ refcount_set(&fp->fi_ref, 1); spin_lock_init(&fp->fi_lock); INIT_LIST_HEAD(&fp->fi_stateids); @@ -4298,7 +4333,6 @@ static void nfsd4_init_file(struct svc_fh *fh, unsigned int hashval, INIT_LIST_HEAD(&fp->fi_lo_states); atomic_set(&fp->fi_lo_recalls, 0); #endif - hlist_add_head_rcu(&fp->fi_hash, &file_hashtbl[hashval]); } void @@ -4363,25 +4397,27 @@ out: } static unsigned long -nfsd_courtesy_client_count(struct shrinker *shrink, struct shrink_control *sc) +nfsd4_state_shrinker_count(struct shrinker *shrink, struct shrink_control *sc) { - int cnt; + int count; struct nfsd_net *nn = container_of(shrink, struct nfsd_net, nfsd_client_shrinker); - cnt = atomic_read(&nn->nfsd_courtesy_clients); - if (cnt > 0) - mod_delayed_work(laundry_wq, &nn->nfsd_shrinker_work, 0); - return (unsigned long)cnt; + count = atomic_read(&nn->nfsd_courtesy_clients); + if (!count) + count = atomic_long_read(&num_delegations); + if (count) + queue_work(laundry_wq, &nn->nfsd_shrinker_work); + return (unsigned long)count; } static unsigned long -nfsd_courtesy_client_scan(struct shrinker *shrink, struct shrink_control *sc) +nfsd4_state_shrinker_scan(struct shrinker *shrink, struct shrink_control *sc) { return SHRINK_STOP; } -int +void nfsd4_init_leases_net(struct nfsd_net *nn) { struct sysinfo si; @@ -4403,16 +4439,6 @@ nfsd4_init_leases_net(struct nfsd_net *nn) nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB); atomic_set(&nn->nfsd_courtesy_clients, 0); - nn->nfsd_client_shrinker.scan_objects = nfsd_courtesy_client_scan; - nn->nfsd_client_shrinker.count_objects = nfsd_courtesy_client_count; - nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS; - return register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client"); -} - -void -nfsd4_leases_net_shutdown(struct nfsd_net *nn) -{ - unregister_shrinker(&nn->nfsd_client_shrinker); } static void init_nfs4_replay(struct nfs4_replay *rp) @@ -4683,71 +4709,80 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net) nfs4_put_stid(&last->st_stid); } -/* search file_hashtbl[] for file */ -static struct nfs4_file * -find_file_locked(struct svc_fh *fh, unsigned int hashval) +static noinline_for_stack struct nfs4_file * +nfsd4_file_hash_lookup(const struct svc_fh *fhp) { - struct nfs4_file *fp; + struct inode *inode = d_inode(fhp->fh_dentry); + struct rhlist_head *tmp, *list; + struct nfs4_file *fi; - hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash, - lockdep_is_held(&state_lock)) { - if (fh_match(&fp->fi_fhandle, &fh->fh_handle)) { - if (refcount_inc_not_zero(&fp->fi_ref)) - return fp; + rcu_read_lock(); + list = rhltable_lookup(&nfs4_file_rhltable, &inode, + nfs4_file_rhash_params); + rhl_for_each_entry_rcu(fi, tmp, list, fi_rlist) { + if (fh_match(&fi->fi_fhandle, &fhp->fh_handle)) { + if (refcount_inc_not_zero(&fi->fi_ref)) { + rcu_read_unlock(); + return fi; + } } } + rcu_read_unlock(); return NULL; } -static struct nfs4_file *insert_file(struct nfs4_file *new, struct svc_fh *fh, - unsigned int hashval) +/* + * On hash insertion, identify entries with the same inode but + * distinct filehandles. They will all be on the list returned + * by rhltable_lookup(). + * + * inode->i_lock prevents racing insertions from adding an entry + * for the same inode/fhp pair twice. + */ +static noinline_for_stack struct nfs4_file * +nfsd4_file_hash_insert(struct nfs4_file *new, const struct svc_fh *fhp) { - struct nfs4_file *fp; + struct inode *inode = d_inode(fhp->fh_dentry); + struct rhlist_head *tmp, *list; struct nfs4_file *ret = NULL; bool alias_found = false; + struct nfs4_file *fi; + int err; - spin_lock(&state_lock); - hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash, - lockdep_is_held(&state_lock)) { - if (fh_match(&fp->fi_fhandle, &fh->fh_handle)) { - if (refcount_inc_not_zero(&fp->fi_ref)) - ret = fp; - } else if (d_inode(fh->fh_dentry) == fp->fi_inode) - fp->fi_aliased = alias_found = true; - } - if (likely(ret == NULL)) { - nfsd4_init_file(fh, hashval, new); - new->fi_aliased = alias_found; - ret = new; + rcu_read_lock(); + spin_lock(&inode->i_lock); + + list = rhltable_lookup(&nfs4_file_rhltable, &inode, + nfs4_file_rhash_params); + rhl_for_each_entry_rcu(fi, tmp, list, fi_rlist) { + if (fh_match(&fi->fi_fhandle, &fhp->fh_handle)) { + if (refcount_inc_not_zero(&fi->fi_ref)) + ret = fi; + } else + fi->fi_aliased = alias_found = true; } - spin_unlock(&state_lock); - return ret; -} + if (ret) + goto out_unlock; -static struct nfs4_file * find_file(struct svc_fh *fh) -{ - struct nfs4_file *fp; - unsigned int hashval = file_hashval(fh); + nfsd4_file_init(fhp, new); + err = rhltable_insert(&nfs4_file_rhltable, &new->fi_rlist, + nfs4_file_rhash_params); + if (err) + goto out_unlock; - rcu_read_lock(); - fp = find_file_locked(fh, hashval); + new->fi_aliased = alias_found; + ret = new; + +out_unlock: + spin_unlock(&inode->i_lock); rcu_read_unlock(); - return fp; + return ret; } -static struct nfs4_file * -find_or_add_file(struct nfs4_file *new, struct svc_fh *fh) +static noinline_for_stack void nfsd4_file_hash_remove(struct nfs4_file *fi) { - struct nfs4_file *fp; - unsigned int hashval = file_hashval(fh); - - rcu_read_lock(); - fp = find_file_locked(fh, hashval); - rcu_read_unlock(); - if (fp) - return fp; - - return insert_file(new, fh, hashval); + rhltable_remove(&nfs4_file_rhltable, &fi->fi_rlist, + nfs4_file_rhash_params); } /* @@ -4760,9 +4795,10 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type) struct nfs4_file *fp; __be32 ret = nfs_ok; - fp = find_file(current_fh); + fp = nfsd4_file_hash_lookup(current_fh); if (!fp) return ret; + /* Check for conflicting share reservations */ spin_lock(&fp->fi_lock); if (fp->fi_share_deny & deny_type) @@ -4774,7 +4810,7 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type) static bool nfsd4_deleg_present(const struct inode *inode) { - struct file_lock_context *ctx = smp_load_acquire(&inode->i_flctx); + struct file_lock_context *ctx = locks_inode_context(inode); return ctx && !list_empty_careful(&ctx->flc_lease); } @@ -4908,10 +4944,8 @@ nfsd_break_deleg_cb(struct file_lock *fl) */ fl->fl_break_time = 0; - spin_lock(&fp->fi_lock); fp->fi_had_conflict = true; nfsd_break_one_deleg(dp); - spin_unlock(&fp->fi_lock); return false; } @@ -5499,12 +5533,13 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, if (status) goto out_unlock; + status = -EAGAIN; + if (fp->fi_had_conflict) + goto out_unlock; + spin_lock(&state_lock); spin_lock(&fp->fi_lock); - if (fp->fi_had_conflict) - status = -EAGAIN; - else - status = hash_delegation_locked(dp, fp); + status = hash_delegation_locked(dp, fp); spin_unlock(&fp->fi_lock); spin_unlock(&state_lock); @@ -5656,7 +5691,9 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf * and check for delegations in the process of being recalled. * If not found, create the nfs4_file struct */ - fp = find_or_add_file(open->op_file, current_fh); + fp = nfsd4_file_hash_insert(open->op_file, current_fh); + if (unlikely(!fp)) + return nfserr_jukebox; if (fp != open->op_file) { status = nfs4_check_deleg(cl, open, &dp); if (status) @@ -5933,7 +5970,7 @@ nfs4_lockowner_has_blockers(struct nfs4_lockowner *lo) list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) { nf = stp->st_stid.sc_file; - ctx = nf->fi_inode->i_flctx; + ctx = locks_inode_context(nf->fi_inode); if (!ctx) continue; if (locks_owner_has_blockers(ctx, lo)) @@ -6161,17 +6198,63 @@ laundromat_main(struct work_struct *laundry) } static void -courtesy_client_reaper(struct work_struct *reaper) +courtesy_client_reaper(struct nfsd_net *nn) { struct list_head reaplist; - struct delayed_work *dwork = to_delayed_work(reaper); - struct nfsd_net *nn = container_of(dwork, struct nfsd_net, - nfsd_shrinker_work); nfs4_get_courtesy_client_reaplist(nn, &reaplist); nfs4_process_client_reaplist(&reaplist); } +static void +deleg_reaper(struct nfsd_net *nn) +{ + struct list_head *pos, *next; + struct nfs4_client *clp; + struct list_head cblist; + + INIT_LIST_HEAD(&cblist); + spin_lock(&nn->client_lock); + list_for_each_safe(pos, next, &nn->client_lru) { + clp = list_entry(pos, struct nfs4_client, cl_lru); + if (clp->cl_state != NFSD4_ACTIVE || + list_empty(&clp->cl_delegations) || + atomic_read(&clp->cl_delegs_in_recall) || + test_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags) || + (ktime_get_boottime_seconds() - + clp->cl_ra_time < 5)) { + continue; + } + list_add(&clp->cl_ra_cblist, &cblist); + + /* release in nfsd4_cb_recall_any_release */ + kref_get(&clp->cl_nfsdfs.cl_ref); + set_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); + clp->cl_ra_time = ktime_get_boottime_seconds(); + } + spin_unlock(&nn->client_lock); + + while (!list_empty(&cblist)) { + clp = list_first_entry(&cblist, struct nfs4_client, + cl_ra_cblist); + list_del_init(&clp->cl_ra_cblist); + clp->cl_ra->ra_keep = 0; + clp->cl_ra->ra_bmval[0] = BIT(RCA4_TYPE_MASK_RDATA_DLG); + trace_nfsd_cb_recall_any(clp->cl_ra); + nfsd4_run_cb(&clp->cl_ra->ra_cb); + } +} + +static void +nfsd4_state_shrinker_worker(struct work_struct *work) +{ + struct nfsd_net *nn = container_of(work, struct nfsd_net, + nfsd_shrinker_work); + + courtesy_client_reaper(nn); + deleg_reaper(nn); +} + static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp) { if (!fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle)) @@ -6936,6 +7019,7 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto put_stateid; + trace_nfsd_deleg_return(stateid); wake_up_var(d_inode(cstate->current_fh.fh_dentry)); destroy_delegation(dp); put_stateid: @@ -7736,18 +7820,20 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) { struct file_lock *fl; int status = false; - struct nfsd_file *nf = find_any_file(fp); + struct nfsd_file *nf; struct inode *inode; struct file_lock_context *flctx; + spin_lock(&fp->fi_lock); + nf = find_any_file_locked(fp); if (!nf) { /* Any valid lock stateid should have some sort of access */ WARN_ON_ONCE(1); - return status; + goto out; } inode = locks_inode(nf->nf_file); - flctx = inode->i_flctx; + flctx = locks_inode_context(inode); if (flctx && !list_empty_careful(&flctx->flc_posix)) { spin_lock(&flctx->flc_lock); @@ -7759,7 +7845,8 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) } spin_unlock(&flctx->flc_lock); } - nfsd_file_put(nf); +out: + spin_unlock(&fp->fi_lock); return status; } @@ -7769,10 +7856,8 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) * @cstate: NFSv4 COMPOUND state * @u: RELEASE_LOCKOWNER arguments * - * The lockowner's so_count is bumped when a lock record is added - * or when copying a conflicting lock. The latter case is brief, - * but can lead to fleeting false positives when looking for - * locks-in-use. + * Check if theree are any locks still held and if not - free the lockowner + * and any lock state that is owned. * * Return values: * %nfs_ok: lockowner released or not found @@ -7808,10 +7893,13 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, spin_unlock(&clp->cl_lock); return nfs_ok; } - if (atomic_read(&lo->lo_owner.so_count) != 2) { - spin_unlock(&clp->cl_lock); - nfs4_put_stateowner(&lo->lo_owner); - return nfserr_locks_held; + + list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) { + if (check_for_locks(stp->st_stid.sc_file, lo)) { + spin_unlock(&clp->cl_lock); + nfs4_put_stateowner(&lo->lo_owner); + return nfserr_locks_held; + } } unhash_lockowner_locked(lo); while (!list_empty(&lo->lo_owner.so_stateids)) { @@ -7992,11 +8080,20 @@ static int nfs4_state_create_net(struct net *net) INIT_LIST_HEAD(&nn->blocked_locks_lru); INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main); - INIT_DELAYED_WORK(&nn->nfsd_shrinker_work, courtesy_client_reaper); + INIT_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker); get_net(net); + nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan; + nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count; + nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS; + + if (register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client")) + goto err_shrinker; return 0; +err_shrinker: + put_net(net); + kfree(nn->sessionid_hashtbl); err_sessionid: kfree(nn->unconf_id_hashtbl); err_unconf_id: @@ -8068,10 +8165,16 @@ nfs4_state_start(void) { int ret; - ret = nfsd4_create_callback_queue(); + ret = rhltable_init(&nfs4_file_rhltable, &nfs4_file_rhash_params); if (ret) return ret; + ret = nfsd4_create_callback_queue(); + if (ret) { + rhltable_destroy(&nfs4_file_rhltable); + return ret; + } + set_max_delegations(); return 0; } @@ -8083,6 +8186,8 @@ nfs4_state_shutdown_net(struct net *net) struct list_head *pos, *next, reaplist; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + unregister_shrinker(&nn->nfsd_client_shrinker); + cancel_work(&nn->nfsd_shrinker_work); cancel_delayed_work_sync(&nn->laundromat_work); locks_end_grace(&nn->nfsd4_manager); @@ -8111,6 +8216,7 @@ void nfs4_state_shutdown(void) { nfsd4_destroy_callback_queue(); + rhltable_destroy(&nfs4_file_rhltable); } static void diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 89a579be042e540bb466c06f3e7b9202522925e4..4ed9fef14adc2848b0683ff823e8737ef21bcf14 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -770,16 +770,18 @@ nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_cb_sec *cbs) static __be32 nfsd4_decode_access(struct nfsd4_compoundargs *argp, - struct nfsd4_access *access) + union nfsd4_op_u *u) { + struct nfsd4_access *access = &u->access; if (xdr_stream_decode_u32(argp->xdr, &access->ac_req_access) < 0) return nfserr_bad_xdr; return nfs_ok; } static __be32 -nfsd4_decode_close(struct nfsd4_compoundargs *argp, struct nfsd4_close *close) +nfsd4_decode_close(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_close *close = &u->close; if (xdr_stream_decode_u32(argp->xdr, &close->cl_seqid) < 0) return nfserr_bad_xdr; return nfsd4_decode_stateid4(argp, &close->cl_stateid); @@ -787,8 +789,9 @@ nfsd4_decode_close(struct nfsd4_compoundargs *argp, struct nfsd4_close *close) static __be32 -nfsd4_decode_commit(struct nfsd4_compoundargs *argp, struct nfsd4_commit *commit) +nfsd4_decode_commit(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_commit *commit = &u->commit; if (xdr_stream_decode_u64(argp->xdr, &commit->co_offset) < 0) return nfserr_bad_xdr; if (xdr_stream_decode_u32(argp->xdr, &commit->co_count) < 0) @@ -798,8 +801,9 @@ nfsd4_decode_commit(struct nfsd4_compoundargs *argp, struct nfsd4_commit *commit } static __be32 -nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create) +nfsd4_decode_create(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_create *create = &u->create; __be32 *p, status; memset(create, 0, sizeof(*create)); @@ -844,22 +848,25 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create } static inline __be32 -nfsd4_decode_delegreturn(struct nfsd4_compoundargs *argp, struct nfsd4_delegreturn *dr) +nfsd4_decode_delegreturn(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_delegreturn *dr = &u->delegreturn; return nfsd4_decode_stateid4(argp, &dr->dr_stateid); } static inline __be32 -nfsd4_decode_getattr(struct nfsd4_compoundargs *argp, struct nfsd4_getattr *getattr) +nfsd4_decode_getattr(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_getattr *getattr = &u->getattr; memset(getattr, 0, sizeof(*getattr)); return nfsd4_decode_bitmap4(argp, getattr->ga_bmval, ARRAY_SIZE(getattr->ga_bmval)); } static __be32 -nfsd4_decode_link(struct nfsd4_compoundargs *argp, struct nfsd4_link *link) +nfsd4_decode_link(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_link *link = &u->link; memset(link, 0, sizeof(*link)); return nfsd4_decode_component4(argp, &link->li_name, &link->li_namelen); } @@ -907,8 +914,9 @@ nfsd4_decode_locker4(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) } static __be32 -nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) +nfsd4_decode_lock(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_lock *lock = &u->lock; memset(lock, 0, sizeof(*lock)); if (xdr_stream_decode_u32(argp->xdr, &lock->lk_type) < 0) return nfserr_bad_xdr; @@ -924,8 +932,9 @@ nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) } static __be32 -nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, struct nfsd4_lockt *lockt) +nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_lockt *lockt = &u->lockt; memset(lockt, 0, sizeof(*lockt)); if (xdr_stream_decode_u32(argp->xdr, &lockt->lt_type) < 0) return nfserr_bad_xdr; @@ -940,8 +949,9 @@ nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, struct nfsd4_lockt *lockt) } static __be32 -nfsd4_decode_locku(struct nfsd4_compoundargs *argp, struct nfsd4_locku *locku) +nfsd4_decode_locku(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_locku *locku = &u->locku; __be32 status; if (xdr_stream_decode_u32(argp->xdr, &locku->lu_type) < 0) @@ -962,8 +972,9 @@ nfsd4_decode_locku(struct nfsd4_compoundargs *argp, struct nfsd4_locku *locku) } static __be32 -nfsd4_decode_lookup(struct nfsd4_compoundargs *argp, struct nfsd4_lookup *lookup) +nfsd4_decode_lookup(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_lookup *lookup = &u->lookup; return nfsd4_decode_component4(argp, &lookup->lo_name, &lookup->lo_len); } @@ -1143,8 +1154,9 @@ nfsd4_decode_open_claim4(struct nfsd4_compoundargs *argp, } static __be32 -nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) +nfsd4_decode_open(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_open *open = &u->open; __be32 status; u32 dummy; @@ -1171,8 +1183,10 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) } static __be32 -nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_open_confirm *open_conf) +nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_open_confirm *open_conf = &u->open_confirm; __be32 status; if (argp->minorversion >= 1) @@ -1190,8 +1204,10 @@ nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_open_con } static __be32 -nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, struct nfsd4_open_downgrade *open_down) +nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_open_downgrade *open_down = &u->open_downgrade; __be32 status; memset(open_down, 0, sizeof(*open_down)); @@ -1209,8 +1225,9 @@ nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, struct nfsd4_open_d } static __be32 -nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, struct nfsd4_putfh *putfh) +nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_putfh *putfh = &u->putfh; __be32 *p; if (xdr_stream_decode_u32(argp->xdr, &putfh->pf_fhlen) < 0) @@ -1229,7 +1246,7 @@ nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, struct nfsd4_putfh *putfh) } static __be32 -nfsd4_decode_putpubfh(struct nfsd4_compoundargs *argp, void *p) +nfsd4_decode_putpubfh(struct nfsd4_compoundargs *argp, union nfsd4_op_u *p) { if (argp->minorversion == 0) return nfs_ok; @@ -1237,8 +1254,9 @@ nfsd4_decode_putpubfh(struct nfsd4_compoundargs *argp, void *p) } static __be32 -nfsd4_decode_read(struct nfsd4_compoundargs *argp, struct nfsd4_read *read) +nfsd4_decode_read(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_read *read = &u->read; __be32 status; memset(read, 0, sizeof(*read)); @@ -1254,8 +1272,9 @@ nfsd4_decode_read(struct nfsd4_compoundargs *argp, struct nfsd4_read *read) } static __be32 -nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, struct nfsd4_readdir *readdir) +nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_readdir *readdir = &u->readdir; __be32 status; memset(readdir, 0, sizeof(*readdir)); @@ -1276,15 +1295,17 @@ nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, struct nfsd4_readdir *read } static __be32 -nfsd4_decode_remove(struct nfsd4_compoundargs *argp, struct nfsd4_remove *remove) +nfsd4_decode_remove(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_remove *remove = &u->remove; memset(&remove->rm_cinfo, 0, sizeof(remove->rm_cinfo)); return nfsd4_decode_component4(argp, &remove->rm_name, &remove->rm_namelen); } static __be32 -nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename) +nfsd4_decode_rename(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_rename *rename = &u->rename; __be32 status; memset(rename, 0, sizeof(*rename)); @@ -1295,22 +1316,25 @@ nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename } static __be32 -nfsd4_decode_renew(struct nfsd4_compoundargs *argp, clientid_t *clientid) +nfsd4_decode_renew(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + clientid_t *clientid = &u->renew; return nfsd4_decode_clientid4(argp, clientid); } static __be32 nfsd4_decode_secinfo(struct nfsd4_compoundargs *argp, - struct nfsd4_secinfo *secinfo) + union nfsd4_op_u *u) { + struct nfsd4_secinfo *secinfo = &u->secinfo; secinfo->si_exp = NULL; return nfsd4_decode_component4(argp, &secinfo->si_name, &secinfo->si_namelen); } static __be32 -nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *setattr) +nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_setattr *setattr = &u->setattr; __be32 status; memset(setattr, 0, sizeof(*setattr)); @@ -1324,8 +1348,9 @@ nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *seta } static __be32 -nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclientid *setclientid) +nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_setclientid *setclientid = &u->setclientid; __be32 *p, status; memset(setclientid, 0, sizeof(*setclientid)); @@ -1367,8 +1392,10 @@ nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclient } static __be32 -nfsd4_decode_setclientid_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_setclientid_confirm *scd_c) +nfsd4_decode_setclientid_confirm(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_setclientid_confirm *scd_c = &u->setclientid_confirm; __be32 status; if (argp->minorversion >= 1) @@ -1382,8 +1409,9 @@ nfsd4_decode_setclientid_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_s /* Also used for NVERIFY */ static __be32 -nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify) +nfsd4_decode_verify(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_verify *verify = &u->verify; __be32 *p, status; memset(verify, 0, sizeof(*verify)); @@ -1409,8 +1437,9 @@ nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify } static __be32 -nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) +nfsd4_decode_write(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_write *write = &u->write; __be32 status; status = nfsd4_decode_stateid4(argp, &write->wr_stateid); @@ -1434,8 +1463,10 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) } static __be32 -nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_release_lockowner *rlockowner) +nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_release_lockowner *rlockowner = &u->release_lockowner; __be32 status; if (argp->minorversion >= 1) @@ -1452,16 +1483,20 @@ nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_rel return nfs_ok; } -static __be32 nfsd4_decode_backchannel_ctl(struct nfsd4_compoundargs *argp, struct nfsd4_backchannel_ctl *bc) +static __be32 nfsd4_decode_backchannel_ctl(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_backchannel_ctl *bc = &u->backchannel_ctl; memset(bc, 0, sizeof(*bc)); if (xdr_stream_decode_u32(argp->xdr, &bc->bc_cb_program) < 0) return nfserr_bad_xdr; return nfsd4_decode_cb_sec(argp, &bc->bc_cb_sec); } -static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp, struct nfsd4_bind_conn_to_session *bcts) +static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_bind_conn_to_session *bcts = &u->bind_conn_to_session; u32 use_conn_in_rdma_mode; __be32 status; @@ -1603,8 +1638,9 @@ nfsd4_decode_nfs_impl_id4(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp, - struct nfsd4_exchange_id *exid) + union nfsd4_op_u *u) { + struct nfsd4_exchange_id *exid = &u->exchange_id; __be32 status; memset(exid, 0, sizeof(*exid)); @@ -1656,8 +1692,9 @@ nfsd4_decode_channel_attrs4(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_create_session(struct nfsd4_compoundargs *argp, - struct nfsd4_create_session *sess) + union nfsd4_op_u *u) { + struct nfsd4_create_session *sess = &u->create_session; __be32 status; memset(sess, 0, sizeof(*sess)); @@ -1681,23 +1718,26 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_destroy_session(struct nfsd4_compoundargs *argp, - struct nfsd4_destroy_session *destroy_session) + union nfsd4_op_u *u) { + struct nfsd4_destroy_session *destroy_session = &u->destroy_session; return nfsd4_decode_sessionid4(argp, &destroy_session->sessionid); } static __be32 nfsd4_decode_free_stateid(struct nfsd4_compoundargs *argp, - struct nfsd4_free_stateid *free_stateid) + union nfsd4_op_u *u) { + struct nfsd4_free_stateid *free_stateid = &u->free_stateid; return nfsd4_decode_stateid4(argp, &free_stateid->fr_stateid); } #ifdef CONFIG_NFSD_PNFS static __be32 nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp, - struct nfsd4_getdeviceinfo *gdev) + union nfsd4_op_u *u) { + struct nfsd4_getdeviceinfo *gdev = &u->getdeviceinfo; __be32 status; memset(gdev, 0, sizeof(*gdev)); @@ -1717,8 +1757,9 @@ nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp, - struct nfsd4_layoutcommit *lcp) + union nfsd4_op_u *u) { + struct nfsd4_layoutcommit *lcp = &u->layoutcommit; __be32 *p, status; memset(lcp, 0, sizeof(*lcp)); @@ -1753,8 +1794,9 @@ nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_layoutget(struct nfsd4_compoundargs *argp, - struct nfsd4_layoutget *lgp) + union nfsd4_op_u *u) { + struct nfsd4_layoutget *lgp = &u->layoutget; __be32 status; memset(lgp, 0, sizeof(*lgp)); @@ -1781,8 +1823,9 @@ nfsd4_decode_layoutget(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_layoutreturn(struct nfsd4_compoundargs *argp, - struct nfsd4_layoutreturn *lrp) + union nfsd4_op_u *u) { + struct nfsd4_layoutreturn *lrp = &u->layoutreturn; memset(lrp, 0, sizeof(*lrp)); if (xdr_stream_decode_bool(argp->xdr, &lrp->lr_reclaim) < 0) return nfserr_bad_xdr; @@ -1795,8 +1838,9 @@ nfsd4_decode_layoutreturn(struct nfsd4_compoundargs *argp, #endif /* CONFIG_NFSD_PNFS */ static __be32 nfsd4_decode_secinfo_no_name(struct nfsd4_compoundargs *argp, - struct nfsd4_secinfo_no_name *sin) + union nfsd4_op_u *u) { + struct nfsd4_secinfo_no_name *sin = &u->secinfo_no_name; if (xdr_stream_decode_u32(argp->xdr, &sin->sin_style) < 0) return nfserr_bad_xdr; @@ -1806,8 +1850,9 @@ static __be32 nfsd4_decode_secinfo_no_name(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_sequence(struct nfsd4_compoundargs *argp, - struct nfsd4_sequence *seq) + union nfsd4_op_u *u) { + struct nfsd4_sequence *seq = &u->sequence; __be32 *p, status; status = nfsd4_decode_sessionid4(argp, &seq->sessionid); @@ -1826,8 +1871,10 @@ nfsd4_decode_sequence(struct nfsd4_compoundargs *argp, } static __be32 -nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, struct nfsd4_test_stateid *test_stateid) +nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_test_stateid *test_stateid = &u->test_stateid; struct nfsd4_test_stateid_id *stateid; __be32 status; u32 i; @@ -1852,14 +1899,16 @@ nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, struct nfsd4_test_sta } static __be32 nfsd4_decode_destroy_clientid(struct nfsd4_compoundargs *argp, - struct nfsd4_destroy_clientid *dc) + union nfsd4_op_u *u) { + struct nfsd4_destroy_clientid *dc = &u->destroy_clientid; return nfsd4_decode_clientid4(argp, &dc->clientid); } static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, - struct nfsd4_reclaim_complete *rc) + union nfsd4_op_u *u) { + struct nfsd4_reclaim_complete *rc = &u->reclaim_complete; if (xdr_stream_decode_bool(argp->xdr, &rc->rca_one_fs) < 0) return nfserr_bad_xdr; return nfs_ok; @@ -1867,8 +1916,9 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_fallocate(struct nfsd4_compoundargs *argp, - struct nfsd4_fallocate *fallocate) + union nfsd4_op_u *u) { + struct nfsd4_fallocate *fallocate = &u->allocate; __be32 status; status = nfsd4_decode_stateid4(argp, &fallocate->falloc_stateid); @@ -1924,8 +1974,9 @@ static __be32 nfsd4_decode_nl4_server(struct nfsd4_compoundargs *argp, } static __be32 -nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy) +nfsd4_decode_copy(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_copy *copy = &u->copy; u32 consecutive, i, count, sync; struct nl4_server *ns_dummy; __be32 status; @@ -1982,8 +2033,9 @@ nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy) static __be32 nfsd4_decode_copy_notify(struct nfsd4_compoundargs *argp, - struct nfsd4_copy_notify *cn) + union nfsd4_op_u *u) { + struct nfsd4_copy_notify *cn = &u->copy_notify; __be32 status; memset(cn, 0, sizeof(*cn)); @@ -2002,16 +2054,18 @@ nfsd4_decode_copy_notify(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_offload_status(struct nfsd4_compoundargs *argp, - struct nfsd4_offload_status *os) + union nfsd4_op_u *u) { + struct nfsd4_offload_status *os = &u->offload_status; os->count = 0; os->status = 0; return nfsd4_decode_stateid4(argp, &os->stateid); } static __be32 -nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek) +nfsd4_decode_seek(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_seek *seek = &u->seek; __be32 status; status = nfsd4_decode_stateid4(argp, &seek->seek_stateid); @@ -2028,8 +2082,9 @@ nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek) } static __be32 -nfsd4_decode_clone(struct nfsd4_compoundargs *argp, struct nfsd4_clone *clone) +nfsd4_decode_clone(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_clone *clone = &u->clone; __be32 status; status = nfsd4_decode_stateid4(argp, &clone->cl_src_stateid); @@ -2154,8 +2209,9 @@ nfsd4_decode_xattr_name(struct nfsd4_compoundargs *argp, char **namep) */ static __be32 nfsd4_decode_getxattr(struct nfsd4_compoundargs *argp, - struct nfsd4_getxattr *getxattr) + union nfsd4_op_u *u) { + struct nfsd4_getxattr *getxattr = &u->getxattr; __be32 status; u32 maxcount; @@ -2173,8 +2229,9 @@ nfsd4_decode_getxattr(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_setxattr(struct nfsd4_compoundargs *argp, - struct nfsd4_setxattr *setxattr) + union nfsd4_op_u *u) { + struct nfsd4_setxattr *setxattr = &u->setxattr; u32 flags, maxcount, size; __be32 status; @@ -2214,8 +2271,9 @@ nfsd4_decode_setxattr(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_listxattrs(struct nfsd4_compoundargs *argp, - struct nfsd4_listxattrs *listxattrs) + union nfsd4_op_u *u) { + struct nfsd4_listxattrs *listxattrs = &u->listxattrs; u32 maxcount; memset(listxattrs, 0, sizeof(*listxattrs)); @@ -2245,113 +2303,114 @@ nfsd4_decode_listxattrs(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_removexattr(struct nfsd4_compoundargs *argp, - struct nfsd4_removexattr *removexattr) + union nfsd4_op_u *u) { + struct nfsd4_removexattr *removexattr = &u->removexattr; memset(removexattr, 0, sizeof(*removexattr)); return nfsd4_decode_xattr_name(argp, &removexattr->rmxa_name); } static __be32 -nfsd4_decode_noop(struct nfsd4_compoundargs *argp, void *p) +nfsd4_decode_noop(struct nfsd4_compoundargs *argp, union nfsd4_op_u *p) { return nfs_ok; } static __be32 -nfsd4_decode_notsupp(struct nfsd4_compoundargs *argp, void *p) +nfsd4_decode_notsupp(struct nfsd4_compoundargs *argp, union nfsd4_op_u *p) { return nfserr_notsupp; } -typedef __be32(*nfsd4_dec)(struct nfsd4_compoundargs *argp, void *); +typedef __be32(*nfsd4_dec)(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u); static const nfsd4_dec nfsd4_dec_ops[] = { - [OP_ACCESS] = (nfsd4_dec)nfsd4_decode_access, - [OP_CLOSE] = (nfsd4_dec)nfsd4_decode_close, - [OP_COMMIT] = (nfsd4_dec)nfsd4_decode_commit, - [OP_CREATE] = (nfsd4_dec)nfsd4_decode_create, - [OP_DELEGPURGE] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_DELEGRETURN] = (nfsd4_dec)nfsd4_decode_delegreturn, - [OP_GETATTR] = (nfsd4_dec)nfsd4_decode_getattr, - [OP_GETFH] = (nfsd4_dec)nfsd4_decode_noop, - [OP_LINK] = (nfsd4_dec)nfsd4_decode_link, - [OP_LOCK] = (nfsd4_dec)nfsd4_decode_lock, - [OP_LOCKT] = (nfsd4_dec)nfsd4_decode_lockt, - [OP_LOCKU] = (nfsd4_dec)nfsd4_decode_locku, - [OP_LOOKUP] = (nfsd4_dec)nfsd4_decode_lookup, - [OP_LOOKUPP] = (nfsd4_dec)nfsd4_decode_noop, - [OP_NVERIFY] = (nfsd4_dec)nfsd4_decode_verify, - [OP_OPEN] = (nfsd4_dec)nfsd4_decode_open, - [OP_OPENATTR] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_OPEN_CONFIRM] = (nfsd4_dec)nfsd4_decode_open_confirm, - [OP_OPEN_DOWNGRADE] = (nfsd4_dec)nfsd4_decode_open_downgrade, - [OP_PUTFH] = (nfsd4_dec)nfsd4_decode_putfh, - [OP_PUTPUBFH] = (nfsd4_dec)nfsd4_decode_putpubfh, - [OP_PUTROOTFH] = (nfsd4_dec)nfsd4_decode_noop, - [OP_READ] = (nfsd4_dec)nfsd4_decode_read, - [OP_READDIR] = (nfsd4_dec)nfsd4_decode_readdir, - [OP_READLINK] = (nfsd4_dec)nfsd4_decode_noop, - [OP_REMOVE] = (nfsd4_dec)nfsd4_decode_remove, - [OP_RENAME] = (nfsd4_dec)nfsd4_decode_rename, - [OP_RENEW] = (nfsd4_dec)nfsd4_decode_renew, - [OP_RESTOREFH] = (nfsd4_dec)nfsd4_decode_noop, - [OP_SAVEFH] = (nfsd4_dec)nfsd4_decode_noop, - [OP_SECINFO] = (nfsd4_dec)nfsd4_decode_secinfo, - [OP_SETATTR] = (nfsd4_dec)nfsd4_decode_setattr, - [OP_SETCLIENTID] = (nfsd4_dec)nfsd4_decode_setclientid, - [OP_SETCLIENTID_CONFIRM] = (nfsd4_dec)nfsd4_decode_setclientid_confirm, - [OP_VERIFY] = (nfsd4_dec)nfsd4_decode_verify, - [OP_WRITE] = (nfsd4_dec)nfsd4_decode_write, - [OP_RELEASE_LOCKOWNER] = (nfsd4_dec)nfsd4_decode_release_lockowner, + [OP_ACCESS] = nfsd4_decode_access, + [OP_CLOSE] = nfsd4_decode_close, + [OP_COMMIT] = nfsd4_decode_commit, + [OP_CREATE] = nfsd4_decode_create, + [OP_DELEGPURGE] = nfsd4_decode_notsupp, + [OP_DELEGRETURN] = nfsd4_decode_delegreturn, + [OP_GETATTR] = nfsd4_decode_getattr, + [OP_GETFH] = nfsd4_decode_noop, + [OP_LINK] = nfsd4_decode_link, + [OP_LOCK] = nfsd4_decode_lock, + [OP_LOCKT] = nfsd4_decode_lockt, + [OP_LOCKU] = nfsd4_decode_locku, + [OP_LOOKUP] = nfsd4_decode_lookup, + [OP_LOOKUPP] = nfsd4_decode_noop, + [OP_NVERIFY] = nfsd4_decode_verify, + [OP_OPEN] = nfsd4_decode_open, + [OP_OPENATTR] = nfsd4_decode_notsupp, + [OP_OPEN_CONFIRM] = nfsd4_decode_open_confirm, + [OP_OPEN_DOWNGRADE] = nfsd4_decode_open_downgrade, + [OP_PUTFH] = nfsd4_decode_putfh, + [OP_PUTPUBFH] = nfsd4_decode_putpubfh, + [OP_PUTROOTFH] = nfsd4_decode_noop, + [OP_READ] = nfsd4_decode_read, + [OP_READDIR] = nfsd4_decode_readdir, + [OP_READLINK] = nfsd4_decode_noop, + [OP_REMOVE] = nfsd4_decode_remove, + [OP_RENAME] = nfsd4_decode_rename, + [OP_RENEW] = nfsd4_decode_renew, + [OP_RESTOREFH] = nfsd4_decode_noop, + [OP_SAVEFH] = nfsd4_decode_noop, + [OP_SECINFO] = nfsd4_decode_secinfo, + [OP_SETATTR] = nfsd4_decode_setattr, + [OP_SETCLIENTID] = nfsd4_decode_setclientid, + [OP_SETCLIENTID_CONFIRM] = nfsd4_decode_setclientid_confirm, + [OP_VERIFY] = nfsd4_decode_verify, + [OP_WRITE] = nfsd4_decode_write, + [OP_RELEASE_LOCKOWNER] = nfsd4_decode_release_lockowner, /* new operations for NFSv4.1 */ - [OP_BACKCHANNEL_CTL] = (nfsd4_dec)nfsd4_decode_backchannel_ctl, - [OP_BIND_CONN_TO_SESSION]= (nfsd4_dec)nfsd4_decode_bind_conn_to_session, - [OP_EXCHANGE_ID] = (nfsd4_dec)nfsd4_decode_exchange_id, - [OP_CREATE_SESSION] = (nfsd4_dec)nfsd4_decode_create_session, - [OP_DESTROY_SESSION] = (nfsd4_dec)nfsd4_decode_destroy_session, - [OP_FREE_STATEID] = (nfsd4_dec)nfsd4_decode_free_stateid, - [OP_GET_DIR_DELEGATION] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_BACKCHANNEL_CTL] = nfsd4_decode_backchannel_ctl, + [OP_BIND_CONN_TO_SESSION] = nfsd4_decode_bind_conn_to_session, + [OP_EXCHANGE_ID] = nfsd4_decode_exchange_id, + [OP_CREATE_SESSION] = nfsd4_decode_create_session, + [OP_DESTROY_SESSION] = nfsd4_decode_destroy_session, + [OP_FREE_STATEID] = nfsd4_decode_free_stateid, + [OP_GET_DIR_DELEGATION] = nfsd4_decode_notsupp, #ifdef CONFIG_NFSD_PNFS - [OP_GETDEVICEINFO] = (nfsd4_dec)nfsd4_decode_getdeviceinfo, - [OP_GETDEVICELIST] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTCOMMIT] = (nfsd4_dec)nfsd4_decode_layoutcommit, - [OP_LAYOUTGET] = (nfsd4_dec)nfsd4_decode_layoutget, - [OP_LAYOUTRETURN] = (nfsd4_dec)nfsd4_decode_layoutreturn, + [OP_GETDEVICEINFO] = nfsd4_decode_getdeviceinfo, + [OP_GETDEVICELIST] = nfsd4_decode_notsupp, + [OP_LAYOUTCOMMIT] = nfsd4_decode_layoutcommit, + [OP_LAYOUTGET] = nfsd4_decode_layoutget, + [OP_LAYOUTRETURN] = nfsd4_decode_layoutreturn, #else - [OP_GETDEVICEINFO] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_GETDEVICELIST] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTCOMMIT] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTGET] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTRETURN] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_GETDEVICEINFO] = nfsd4_decode_notsupp, + [OP_GETDEVICELIST] = nfsd4_decode_notsupp, + [OP_LAYOUTCOMMIT] = nfsd4_decode_notsupp, + [OP_LAYOUTGET] = nfsd4_decode_notsupp, + [OP_LAYOUTRETURN] = nfsd4_decode_notsupp, #endif - [OP_SECINFO_NO_NAME] = (nfsd4_dec)nfsd4_decode_secinfo_no_name, - [OP_SEQUENCE] = (nfsd4_dec)nfsd4_decode_sequence, - [OP_SET_SSV] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_TEST_STATEID] = (nfsd4_dec)nfsd4_decode_test_stateid, - [OP_WANT_DELEGATION] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_DESTROY_CLIENTID] = (nfsd4_dec)nfsd4_decode_destroy_clientid, - [OP_RECLAIM_COMPLETE] = (nfsd4_dec)nfsd4_decode_reclaim_complete, + [OP_SECINFO_NO_NAME] = nfsd4_decode_secinfo_no_name, + [OP_SEQUENCE] = nfsd4_decode_sequence, + [OP_SET_SSV] = nfsd4_decode_notsupp, + [OP_TEST_STATEID] = nfsd4_decode_test_stateid, + [OP_WANT_DELEGATION] = nfsd4_decode_notsupp, + [OP_DESTROY_CLIENTID] = nfsd4_decode_destroy_clientid, + [OP_RECLAIM_COMPLETE] = nfsd4_decode_reclaim_complete, /* new operations for NFSv4.2 */ - [OP_ALLOCATE] = (nfsd4_dec)nfsd4_decode_fallocate, - [OP_COPY] = (nfsd4_dec)nfsd4_decode_copy, - [OP_COPY_NOTIFY] = (nfsd4_dec)nfsd4_decode_copy_notify, - [OP_DEALLOCATE] = (nfsd4_dec)nfsd4_decode_fallocate, - [OP_IO_ADVISE] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTERROR] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTSTATS] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_OFFLOAD_CANCEL] = (nfsd4_dec)nfsd4_decode_offload_status, - [OP_OFFLOAD_STATUS] = (nfsd4_dec)nfsd4_decode_offload_status, - [OP_READ_PLUS] = (nfsd4_dec)nfsd4_decode_read, - [OP_SEEK] = (nfsd4_dec)nfsd4_decode_seek, - [OP_WRITE_SAME] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_CLONE] = (nfsd4_dec)nfsd4_decode_clone, + [OP_ALLOCATE] = nfsd4_decode_fallocate, + [OP_COPY] = nfsd4_decode_copy, + [OP_COPY_NOTIFY] = nfsd4_decode_copy_notify, + [OP_DEALLOCATE] = nfsd4_decode_fallocate, + [OP_IO_ADVISE] = nfsd4_decode_notsupp, + [OP_LAYOUTERROR] = nfsd4_decode_notsupp, + [OP_LAYOUTSTATS] = nfsd4_decode_notsupp, + [OP_OFFLOAD_CANCEL] = nfsd4_decode_offload_status, + [OP_OFFLOAD_STATUS] = nfsd4_decode_offload_status, + [OP_READ_PLUS] = nfsd4_decode_read, + [OP_SEEK] = nfsd4_decode_seek, + [OP_WRITE_SAME] = nfsd4_decode_notsupp, + [OP_CLONE] = nfsd4_decode_clone, /* RFC 8276 extended atributes operations */ - [OP_GETXATTR] = (nfsd4_dec)nfsd4_decode_getxattr, - [OP_SETXATTR] = (nfsd4_dec)nfsd4_decode_setxattr, - [OP_LISTXATTRS] = (nfsd4_dec)nfsd4_decode_listxattrs, - [OP_REMOVEXATTR] = (nfsd4_dec)nfsd4_decode_removexattr, + [OP_GETXATTR] = nfsd4_decode_getxattr, + [OP_SETXATTR] = nfsd4_decode_setxattr, + [OP_LISTXATTRS] = nfsd4_decode_listxattrs, + [OP_REMOVEXATTR] = nfsd4_decode_removexattr, }; static inline bool @@ -2482,6 +2541,20 @@ static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode, return p; } +static __be32 nfsd4_encode_nfstime4(struct xdr_stream *xdr, + struct timespec64 *tv) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, XDR_UNIT * 3); + if (!p) + return nfserr_resource; + + p = xdr_encode_hyper(p, (s64)tv->tv_sec); + *p = cpu_to_be32(tv->tv_nsec); + return nfs_ok; +} + /* * ctime (in NFSv4, time_metadata) is not writeable, and the client * doesn't really care what resolution could theoretically be stored by @@ -3287,11 +3360,14 @@ out_acl: p = xdr_encode_hyper(p, dummy64); } if (bmval1 & FATTR4_WORD1_TIME_ACCESS) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (s64)stat.atime.tv_sec); - *p++ = cpu_to_be32(stat.atime.tv_nsec); + status = nfsd4_encode_nfstime4(xdr, &stat.atime); + if (status) + goto out; + } + if (bmval1 & FATTR4_WORD1_TIME_CREATE) { + status = nfsd4_encode_nfstime4(xdr, &stat.btime); + if (status) + goto out; } if (bmval1 & FATTR4_WORD1_TIME_DELTA) { p = xdr_reserve_space(xdr, 12); @@ -3300,25 +3376,14 @@ out_acl: p = encode_time_delta(p, d_inode(dentry)); } if (bmval1 & FATTR4_WORD1_TIME_METADATA) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (s64)stat.ctime.tv_sec); - *p++ = cpu_to_be32(stat.ctime.tv_nsec); + status = nfsd4_encode_nfstime4(xdr, &stat.ctime); + if (status) + goto out; } if (bmval1 & FATTR4_WORD1_TIME_MODIFY) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (s64)stat.mtime.tv_sec); - *p++ = cpu_to_be32(stat.mtime.tv_nsec); - } - if (bmval1 & FATTR4_WORD1_TIME_CREATE) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (s64)stat.btime.tv_sec); - *p++ = cpu_to_be32(stat.btime.tv_nsec); + status = nfsd4_encode_nfstime4(xdr, &stat.mtime); + if (status) + goto out; } if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) { u64 ino = stat.ino; @@ -3643,8 +3708,10 @@ nfsd4_encode_stateid(struct xdr_stream *xdr, stateid_t *sid) } static __be32 -nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_access *access) +nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_access *access = &u->access; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -3656,8 +3723,10 @@ nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ return 0; } -static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_bind_conn_to_session *bcts) +static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_bind_conn_to_session *bcts = &u->bind_conn_to_session; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -3673,8 +3742,10 @@ static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, } static __be32 -nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_close *close) +nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_close *close = &u->close; struct xdr_stream *xdr = resp->xdr; return nfsd4_encode_stateid(xdr, &close->cl_stateid); @@ -3682,8 +3753,10 @@ nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_c static __be32 -nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_commit *commit) +nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_commit *commit = &u->commit; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -3696,8 +3769,10 @@ nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ } static __be32 -nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_create *create) +nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_create *create = &u->create; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -3710,8 +3785,10 @@ nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ } static __be32 -nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_getattr *getattr) +nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_getattr *getattr = &u->getattr; struct svc_fh *fhp = getattr->ga_fhp; struct xdr_stream *xdr = resp->xdr; @@ -3720,8 +3797,10 @@ nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 } static __be32 -nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh **fhpp) +nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct svc_fh **fhpp = &u->getfh; struct xdr_stream *xdr = resp->xdr; struct svc_fh *fhp = *fhpp; unsigned int len; @@ -3775,8 +3854,10 @@ again: } static __be32 -nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lock *lock) +nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_lock *lock = &u->lock; struct xdr_stream *xdr = resp->xdr; if (!nfserr) @@ -3788,8 +3869,10 @@ nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lo } static __be32 -nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lockt *lockt) +nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_lockt *lockt = &u->lockt; struct xdr_stream *xdr = resp->xdr; if (nfserr == nfserr_denied) @@ -3798,8 +3881,10 @@ nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l } static __be32 -nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_locku *locku) +nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_locku *locku = &u->locku; struct xdr_stream *xdr = resp->xdr; return nfsd4_encode_stateid(xdr, &locku->lu_stateid); @@ -3807,8 +3892,10 @@ nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l static __be32 -nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_link *link) +nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_link *link = &u->link; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -3821,8 +3908,10 @@ nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_li static __be32 -nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open *open) +nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_open *open = &u->open; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -3915,16 +4004,20 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op } static __be32 -nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_confirm *oc) +nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_open_confirm *oc = &u->open_confirm; struct xdr_stream *xdr = resp->xdr; return nfsd4_encode_stateid(xdr, &oc->oc_resp_stateid); } static __be32 -nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_downgrade *od) +nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_open_downgrade *od = &u->open_downgrade; struct xdr_stream *xdr = resp->xdr; return nfsd4_encode_stateid(xdr, &od->od_stateid); @@ -4023,8 +4116,9 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, static __be32 nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_read *read) + union nfsd4_op_u *u) { + struct nfsd4_read *read = &u->read; bool splice_ok = test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags); unsigned long maxcount; struct xdr_stream *xdr = resp->xdr; @@ -4065,8 +4159,10 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, } static __be32 -nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readlink *readlink) +nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_readlink *readlink = &u->readlink; __be32 *p, *maxcount_p, zero = xdr_zero; struct xdr_stream *xdr = resp->xdr; int length_offset = xdr->buf->len; @@ -4110,8 +4206,10 @@ out_err: } static __be32 -nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readdir *readdir) +nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_readdir *readdir = &u->readdir; int maxcount; int bytes_left; loff_t offset; @@ -4201,8 +4299,10 @@ err_no_verf: } static __be32 -nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_remove *remove) +nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_remove *remove = &u->remove; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4214,8 +4314,10 @@ nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ } static __be32 -nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_rename *rename) +nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_rename *rename = &u->rename; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4297,8 +4399,9 @@ nfsd4_do_encode_secinfo(struct xdr_stream *xdr, struct svc_export *exp) static __be32 nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_secinfo *secinfo) + union nfsd4_op_u *u) { + struct nfsd4_secinfo *secinfo = &u->secinfo; struct xdr_stream *xdr = resp->xdr; return nfsd4_do_encode_secinfo(xdr, secinfo->si_exp); @@ -4306,8 +4409,9 @@ nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_secinfo_no_name *secinfo) + union nfsd4_op_u *u) { + struct nfsd4_secinfo_no_name *secinfo = &u->secinfo_no_name; struct xdr_stream *xdr = resp->xdr; return nfsd4_do_encode_secinfo(xdr, secinfo->sin_exp); @@ -4318,8 +4422,10 @@ nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr, * regardless of the error status. */ static __be32 -nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setattr *setattr) +nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_setattr *setattr = &u->setattr; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4342,8 +4448,10 @@ nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 } static __be32 -nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setclientid *scd) +nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_setclientid *scd = &u->setclientid; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4366,8 +4474,10 @@ nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct n } static __be32 -nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_write *write) +nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_write *write = &u->write; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4383,8 +4493,9 @@ nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_w static __be32 nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_exchange_id *exid) + union nfsd4_op_u *u) { + struct nfsd4_exchange_id *exid = &u->exchange_id; struct xdr_stream *xdr = resp->xdr; __be32 *p; char *major_id; @@ -4461,8 +4572,9 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_create_session(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_create_session *sess) + union nfsd4_op_u *u) { + struct nfsd4_create_session *sess = &u->create_session; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4514,8 +4626,9 @@ nfsd4_encode_create_session(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_sequence *seq) + union nfsd4_op_u *u) { + struct nfsd4_sequence *seq = &u->sequence; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4537,8 +4650,9 @@ nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_test_stateid *test_stateid) + union nfsd4_op_u *u) { + struct nfsd4_test_stateid *test_stateid = &u->test_stateid; struct xdr_stream *xdr = resp->xdr; struct nfsd4_test_stateid_id *stateid, *next; __be32 *p; @@ -4558,8 +4672,9 @@ nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr, #ifdef CONFIG_NFSD_PNFS static __be32 nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_getdeviceinfo *gdev) + union nfsd4_op_u *u) { + struct nfsd4_getdeviceinfo *gdev = &u->getdeviceinfo; struct xdr_stream *xdr = resp->xdr; const struct nfsd4_layout_ops *ops; u32 starting_len = xdr->buf->len, needed_len; @@ -4611,8 +4726,9 @@ toosmall: static __be32 nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_layoutget *lgp) + union nfsd4_op_u *u) { + struct nfsd4_layoutget *lgp = &u->layoutget; struct xdr_stream *xdr = resp->xdr; const struct nfsd4_layout_ops *ops; __be32 *p; @@ -4638,8 +4754,9 @@ nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_layoutcommit(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_layoutcommit *lcp) + union nfsd4_op_u *u) { + struct nfsd4_layoutcommit *lcp = &u->layoutcommit; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4659,8 +4776,9 @@ nfsd4_encode_layoutcommit(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_layoutreturn(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_layoutreturn *lrp) + union nfsd4_op_u *u) { + struct nfsd4_layoutreturn *lrp = &u->layoutreturn; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4745,8 +4863,9 @@ nfsd42_encode_nl4_server(struct nfsd4_compoundres *resp, struct nl4_server *ns) static __be32 nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_copy *copy) + union nfsd4_op_u *u) { + struct nfsd4_copy *copy = &u->copy; __be32 *p; nfserr = nfsd42_encode_write_res(resp, ©->cp_res, @@ -4762,8 +4881,9 @@ nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_offload_status(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_offload_status *os) + union nfsd4_op_u *u) { + struct nfsd4_offload_status *os = &u->offload_status; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4777,156 +4897,83 @@ nfsd4_encode_offload_status(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp, - struct nfsd4_read *read, - unsigned long *maxcount, u32 *eof, - loff_t *pos) + struct nfsd4_read *read) { - struct xdr_stream *xdr = resp->xdr; + bool splice_ok = test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags); struct file *file = read->rd_nf->nf_file; - int starting_len = xdr->buf->len; - loff_t hole_pos; - __be32 nfserr; - __be32 *p, tmp; - __be64 tmp64; - - hole_pos = pos ? *pos : vfs_llseek(file, read->rd_offset, SEEK_HOLE); - if (hole_pos > read->rd_offset) - *maxcount = min_t(unsigned long, *maxcount, hole_pos - read->rd_offset); - *maxcount = min_t(unsigned long, *maxcount, (xdr->buf->buflen - xdr->buf->len)); + struct xdr_stream *xdr = resp->xdr; + unsigned long maxcount; + __be32 nfserr, *p; /* Content type, offset, byte count */ p = xdr_reserve_space(xdr, 4 + 8 + 4); if (!p) - return nfserr_resource; + return nfserr_io; + if (resp->xdr->buf->page_len && splice_ok) { + WARN_ON_ONCE(splice_ok); + return nfserr_serverfault; + } - read->rd_vlen = xdr_reserve_space_vec(xdr, resp->rqstp->rq_vec, *maxcount); - if (read->rd_vlen < 0) - return nfserr_resource; + maxcount = min_t(unsigned long, read->rd_length, + (xdr->buf->buflen - xdr->buf->len)); - nfserr = nfsd_readv(resp->rqstp, read->rd_fhp, file, read->rd_offset, - resp->rqstp->rq_vec, read->rd_vlen, maxcount, eof); + if (file->f_op->splice_read && splice_ok) + nfserr = nfsd4_encode_splice_read(resp, read, file, maxcount); + else + nfserr = nfsd4_encode_readv(resp, read, file, maxcount); if (nfserr) return nfserr; - xdr_truncate_encode(xdr, starting_len + 16 + xdr_align_size(*maxcount)); - - tmp = htonl(NFS4_CONTENT_DATA); - write_bytes_to_xdr_buf(xdr->buf, starting_len, &tmp, 4); - tmp64 = cpu_to_be64(read->rd_offset); - write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp64, 8); - tmp = htonl(*maxcount); - write_bytes_to_xdr_buf(xdr->buf, starting_len + 12, &tmp, 4); - - tmp = xdr_zero; - write_bytes_to_xdr_buf(xdr->buf, starting_len + 16 + *maxcount, &tmp, - xdr_pad_size(*maxcount)); - return nfs_ok; -} -static __be32 -nfsd4_encode_read_plus_hole(struct nfsd4_compoundres *resp, - struct nfsd4_read *read, - unsigned long *maxcount, u32 *eof) -{ - struct file *file = read->rd_nf->nf_file; - loff_t data_pos = vfs_llseek(file, read->rd_offset, SEEK_DATA); - loff_t f_size = i_size_read(file_inode(file)); - unsigned long count; - __be32 *p; - - if (data_pos == -ENXIO) - data_pos = f_size; - else if (data_pos <= read->rd_offset || (data_pos < f_size && data_pos % PAGE_SIZE)) - return nfsd4_encode_read_plus_data(resp, read, maxcount, eof, &f_size); - count = data_pos - read->rd_offset; - - /* Content type, offset, byte count */ - p = xdr_reserve_space(resp->xdr, 4 + 8 + 8); - if (!p) - return nfserr_resource; - - *p++ = htonl(NFS4_CONTENT_HOLE); + *p++ = cpu_to_be32(NFS4_CONTENT_DATA); p = xdr_encode_hyper(p, read->rd_offset); - p = xdr_encode_hyper(p, count); + *p = cpu_to_be32(read->rd_length); - *eof = (read->rd_offset + count) >= f_size; - *maxcount = min_t(unsigned long, count, *maxcount); return nfs_ok; } static __be32 nfsd4_encode_read_plus(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_read *read) + union nfsd4_op_u *u) { - unsigned long maxcount, count; + struct nfsd4_read *read = &u->read; + struct file *file = read->rd_nf->nf_file; struct xdr_stream *xdr = resp->xdr; - struct file *file; int starting_len = xdr->buf->len; - int last_segment = xdr->buf->len; - int segments = 0; - __be32 *p, tmp; - bool is_data; - loff_t pos; - u32 eof; + u32 segments = 0; + __be32 *p; if (nfserr) return nfserr; - file = read->rd_nf->nf_file; /* eof flag, segment count */ p = xdr_reserve_space(xdr, 4 + 4); if (!p) - return nfserr_resource; + return nfserr_io; xdr_commit_encode(xdr); - maxcount = min_t(unsigned long, read->rd_length, - (xdr->buf->buflen - xdr->buf->len)); - count = maxcount; - - eof = read->rd_offset >= i_size_read(file_inode(file)); - if (eof) + read->rd_eof = read->rd_offset >= i_size_read(file_inode(file)); + if (read->rd_eof) goto out; - pos = vfs_llseek(file, read->rd_offset, SEEK_HOLE); - is_data = pos > read->rd_offset; - - while (count > 0 && !eof) { - maxcount = count; - if (is_data) - nfserr = nfsd4_encode_read_plus_data(resp, read, &maxcount, &eof, - segments == 0 ? &pos : NULL); - else - nfserr = nfsd4_encode_read_plus_hole(resp, read, &maxcount, &eof); - if (nfserr) - goto out; - count -= maxcount; - read->rd_offset += maxcount; - is_data = !is_data; - last_segment = xdr->buf->len; - segments++; - } - -out: - if (nfserr && segments == 0) + nfserr = nfsd4_encode_read_plus_data(resp, read); + if (nfserr) { xdr_truncate_encode(xdr, starting_len); - else { - if (nfserr) { - xdr_truncate_encode(xdr, last_segment); - nfserr = nfs_ok; - eof = 0; - } - tmp = htonl(eof); - write_bytes_to_xdr_buf(xdr->buf, starting_len, &tmp, 4); - tmp = htonl(segments); - write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4); + return nfserr; } + segments++; + +out: + p = xdr_encode_bool(p, read->rd_eof); + *p = cpu_to_be32(segments); return nfserr; } static __be32 nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_copy_notify *cn) + union nfsd4_op_u *u) { + struct nfsd4_copy_notify *cn = &u->copy_notify; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4960,8 +5007,9 @@ nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_seek *seek) + union nfsd4_op_u *u) { + struct nfsd4_seek *seek = &u->seek; __be32 *p; p = xdr_reserve_space(resp->xdr, 4 + 8); @@ -4972,7 +5020,8 @@ nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr, } static __be32 -nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, void *p) +nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *p) { return nfserr; } @@ -5023,8 +5072,9 @@ nfsd4_vbuf_to_stream(struct xdr_stream *xdr, char *buf, u32 buflen) static __be32 nfsd4_encode_getxattr(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_getxattr *getxattr) + union nfsd4_op_u *u) { + struct nfsd4_getxattr *getxattr = &u->getxattr; struct xdr_stream *xdr = resp->xdr; __be32 *p, err; @@ -5047,8 +5097,9 @@ nfsd4_encode_getxattr(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_setxattr(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_setxattr *setxattr) + union nfsd4_op_u *u) { + struct nfsd4_setxattr *setxattr = &u->setxattr; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -5088,8 +5139,9 @@ nfsd4_listxattr_validate_cookie(struct nfsd4_listxattrs *listxattrs, static __be32 nfsd4_encode_listxattrs(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_listxattrs *listxattrs) + union nfsd4_op_u *u) { + struct nfsd4_listxattrs *listxattrs = &u->listxattrs; struct xdr_stream *xdr = resp->xdr; u32 cookie_offset, count_offset, eof; u32 left, xdrleft, slen, count; @@ -5199,8 +5251,9 @@ out: static __be32 nfsd4_encode_removexattr(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_removexattr *removexattr) + union nfsd4_op_u *u) { + struct nfsd4_removexattr *removexattr = &u->removexattr; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -5212,7 +5265,7 @@ nfsd4_encode_removexattr(struct nfsd4_compoundres *resp, __be32 nfserr, return 0; } -typedef __be32(* nfsd4_enc)(struct nfsd4_compoundres *, __be32, void *); +typedef __be32(*nfsd4_enc)(struct nfsd4_compoundres *, __be32, union nfsd4_op_u *u); /* * Note: nfsd4_enc_ops vector is shared for v4.0 and v4.1 @@ -5220,93 +5273,93 @@ typedef __be32(* nfsd4_enc)(struct nfsd4_compoundres *, __be32, void *); * done in the decoding phase. */ static const nfsd4_enc nfsd4_enc_ops[] = { - [OP_ACCESS] = (nfsd4_enc)nfsd4_encode_access, - [OP_CLOSE] = (nfsd4_enc)nfsd4_encode_close, - [OP_COMMIT] = (nfsd4_enc)nfsd4_encode_commit, - [OP_CREATE] = (nfsd4_enc)nfsd4_encode_create, - [OP_DELEGPURGE] = (nfsd4_enc)nfsd4_encode_noop, - [OP_DELEGRETURN] = (nfsd4_enc)nfsd4_encode_noop, - [OP_GETATTR] = (nfsd4_enc)nfsd4_encode_getattr, - [OP_GETFH] = (nfsd4_enc)nfsd4_encode_getfh, - [OP_LINK] = (nfsd4_enc)nfsd4_encode_link, - [OP_LOCK] = (nfsd4_enc)nfsd4_encode_lock, - [OP_LOCKT] = (nfsd4_enc)nfsd4_encode_lockt, - [OP_LOCKU] = (nfsd4_enc)nfsd4_encode_locku, - [OP_LOOKUP] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LOOKUPP] = (nfsd4_enc)nfsd4_encode_noop, - [OP_NVERIFY] = (nfsd4_enc)nfsd4_encode_noop, - [OP_OPEN] = (nfsd4_enc)nfsd4_encode_open, - [OP_OPENATTR] = (nfsd4_enc)nfsd4_encode_noop, - [OP_OPEN_CONFIRM] = (nfsd4_enc)nfsd4_encode_open_confirm, - [OP_OPEN_DOWNGRADE] = (nfsd4_enc)nfsd4_encode_open_downgrade, - [OP_PUTFH] = (nfsd4_enc)nfsd4_encode_noop, - [OP_PUTPUBFH] = (nfsd4_enc)nfsd4_encode_noop, - [OP_PUTROOTFH] = (nfsd4_enc)nfsd4_encode_noop, - [OP_READ] = (nfsd4_enc)nfsd4_encode_read, - [OP_READDIR] = (nfsd4_enc)nfsd4_encode_readdir, - [OP_READLINK] = (nfsd4_enc)nfsd4_encode_readlink, - [OP_REMOVE] = (nfsd4_enc)nfsd4_encode_remove, - [OP_RENAME] = (nfsd4_enc)nfsd4_encode_rename, - [OP_RENEW] = (nfsd4_enc)nfsd4_encode_noop, - [OP_RESTOREFH] = (nfsd4_enc)nfsd4_encode_noop, - [OP_SAVEFH] = (nfsd4_enc)nfsd4_encode_noop, - [OP_SECINFO] = (nfsd4_enc)nfsd4_encode_secinfo, - [OP_SETATTR] = (nfsd4_enc)nfsd4_encode_setattr, - [OP_SETCLIENTID] = (nfsd4_enc)nfsd4_encode_setclientid, - [OP_SETCLIENTID_CONFIRM] = (nfsd4_enc)nfsd4_encode_noop, - [OP_VERIFY] = (nfsd4_enc)nfsd4_encode_noop, - [OP_WRITE] = (nfsd4_enc)nfsd4_encode_write, - [OP_RELEASE_LOCKOWNER] = (nfsd4_enc)nfsd4_encode_noop, + [OP_ACCESS] = nfsd4_encode_access, + [OP_CLOSE] = nfsd4_encode_close, + [OP_COMMIT] = nfsd4_encode_commit, + [OP_CREATE] = nfsd4_encode_create, + [OP_DELEGPURGE] = nfsd4_encode_noop, + [OP_DELEGRETURN] = nfsd4_encode_noop, + [OP_GETATTR] = nfsd4_encode_getattr, + [OP_GETFH] = nfsd4_encode_getfh, + [OP_LINK] = nfsd4_encode_link, + [OP_LOCK] = nfsd4_encode_lock, + [OP_LOCKT] = nfsd4_encode_lockt, + [OP_LOCKU] = nfsd4_encode_locku, + [OP_LOOKUP] = nfsd4_encode_noop, + [OP_LOOKUPP] = nfsd4_encode_noop, + [OP_NVERIFY] = nfsd4_encode_noop, + [OP_OPEN] = nfsd4_encode_open, + [OP_OPENATTR] = nfsd4_encode_noop, + [OP_OPEN_CONFIRM] = nfsd4_encode_open_confirm, + [OP_OPEN_DOWNGRADE] = nfsd4_encode_open_downgrade, + [OP_PUTFH] = nfsd4_encode_noop, + [OP_PUTPUBFH] = nfsd4_encode_noop, + [OP_PUTROOTFH] = nfsd4_encode_noop, + [OP_READ] = nfsd4_encode_read, + [OP_READDIR] = nfsd4_encode_readdir, + [OP_READLINK] = nfsd4_encode_readlink, + [OP_REMOVE] = nfsd4_encode_remove, + [OP_RENAME] = nfsd4_encode_rename, + [OP_RENEW] = nfsd4_encode_noop, + [OP_RESTOREFH] = nfsd4_encode_noop, + [OP_SAVEFH] = nfsd4_encode_noop, + [OP_SECINFO] = nfsd4_encode_secinfo, + [OP_SETATTR] = nfsd4_encode_setattr, + [OP_SETCLIENTID] = nfsd4_encode_setclientid, + [OP_SETCLIENTID_CONFIRM] = nfsd4_encode_noop, + [OP_VERIFY] = nfsd4_encode_noop, + [OP_WRITE] = nfsd4_encode_write, + [OP_RELEASE_LOCKOWNER] = nfsd4_encode_noop, /* NFSv4.1 operations */ - [OP_BACKCHANNEL_CTL] = (nfsd4_enc)nfsd4_encode_noop, - [OP_BIND_CONN_TO_SESSION] = (nfsd4_enc)nfsd4_encode_bind_conn_to_session, - [OP_EXCHANGE_ID] = (nfsd4_enc)nfsd4_encode_exchange_id, - [OP_CREATE_SESSION] = (nfsd4_enc)nfsd4_encode_create_session, - [OP_DESTROY_SESSION] = (nfsd4_enc)nfsd4_encode_noop, - [OP_FREE_STATEID] = (nfsd4_enc)nfsd4_encode_noop, - [OP_GET_DIR_DELEGATION] = (nfsd4_enc)nfsd4_encode_noop, + [OP_BACKCHANNEL_CTL] = nfsd4_encode_noop, + [OP_BIND_CONN_TO_SESSION] = nfsd4_encode_bind_conn_to_session, + [OP_EXCHANGE_ID] = nfsd4_encode_exchange_id, + [OP_CREATE_SESSION] = nfsd4_encode_create_session, + [OP_DESTROY_SESSION] = nfsd4_encode_noop, + [OP_FREE_STATEID] = nfsd4_encode_noop, + [OP_GET_DIR_DELEGATION] = nfsd4_encode_noop, #ifdef CONFIG_NFSD_PNFS - [OP_GETDEVICEINFO] = (nfsd4_enc)nfsd4_encode_getdeviceinfo, - [OP_GETDEVICELIST] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTCOMMIT] = (nfsd4_enc)nfsd4_encode_layoutcommit, - [OP_LAYOUTGET] = (nfsd4_enc)nfsd4_encode_layoutget, - [OP_LAYOUTRETURN] = (nfsd4_enc)nfsd4_encode_layoutreturn, + [OP_GETDEVICEINFO] = nfsd4_encode_getdeviceinfo, + [OP_GETDEVICELIST] = nfsd4_encode_noop, + [OP_LAYOUTCOMMIT] = nfsd4_encode_layoutcommit, + [OP_LAYOUTGET] = nfsd4_encode_layoutget, + [OP_LAYOUTRETURN] = nfsd4_encode_layoutreturn, #else - [OP_GETDEVICEINFO] = (nfsd4_enc)nfsd4_encode_noop, - [OP_GETDEVICELIST] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTCOMMIT] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTGET] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTRETURN] = (nfsd4_enc)nfsd4_encode_noop, + [OP_GETDEVICEINFO] = nfsd4_encode_noop, + [OP_GETDEVICELIST] = nfsd4_encode_noop, + [OP_LAYOUTCOMMIT] = nfsd4_encode_noop, + [OP_LAYOUTGET] = nfsd4_encode_noop, + [OP_LAYOUTRETURN] = nfsd4_encode_noop, #endif - [OP_SECINFO_NO_NAME] = (nfsd4_enc)nfsd4_encode_secinfo_no_name, - [OP_SEQUENCE] = (nfsd4_enc)nfsd4_encode_sequence, - [OP_SET_SSV] = (nfsd4_enc)nfsd4_encode_noop, - [OP_TEST_STATEID] = (nfsd4_enc)nfsd4_encode_test_stateid, - [OP_WANT_DELEGATION] = (nfsd4_enc)nfsd4_encode_noop, - [OP_DESTROY_CLIENTID] = (nfsd4_enc)nfsd4_encode_noop, - [OP_RECLAIM_COMPLETE] = (nfsd4_enc)nfsd4_encode_noop, + [OP_SECINFO_NO_NAME] = nfsd4_encode_secinfo_no_name, + [OP_SEQUENCE] = nfsd4_encode_sequence, + [OP_SET_SSV] = nfsd4_encode_noop, + [OP_TEST_STATEID] = nfsd4_encode_test_stateid, + [OP_WANT_DELEGATION] = nfsd4_encode_noop, + [OP_DESTROY_CLIENTID] = nfsd4_encode_noop, + [OP_RECLAIM_COMPLETE] = nfsd4_encode_noop, /* NFSv4.2 operations */ - [OP_ALLOCATE] = (nfsd4_enc)nfsd4_encode_noop, - [OP_COPY] = (nfsd4_enc)nfsd4_encode_copy, - [OP_COPY_NOTIFY] = (nfsd4_enc)nfsd4_encode_copy_notify, - [OP_DEALLOCATE] = (nfsd4_enc)nfsd4_encode_noop, - [OP_IO_ADVISE] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTERROR] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTSTATS] = (nfsd4_enc)nfsd4_encode_noop, - [OP_OFFLOAD_CANCEL] = (nfsd4_enc)nfsd4_encode_noop, - [OP_OFFLOAD_STATUS] = (nfsd4_enc)nfsd4_encode_offload_status, - [OP_READ_PLUS] = (nfsd4_enc)nfsd4_encode_read_plus, - [OP_SEEK] = (nfsd4_enc)nfsd4_encode_seek, - [OP_WRITE_SAME] = (nfsd4_enc)nfsd4_encode_noop, - [OP_CLONE] = (nfsd4_enc)nfsd4_encode_noop, + [OP_ALLOCATE] = nfsd4_encode_noop, + [OP_COPY] = nfsd4_encode_copy, + [OP_COPY_NOTIFY] = nfsd4_encode_copy_notify, + [OP_DEALLOCATE] = nfsd4_encode_noop, + [OP_IO_ADVISE] = nfsd4_encode_noop, + [OP_LAYOUTERROR] = nfsd4_encode_noop, + [OP_LAYOUTSTATS] = nfsd4_encode_noop, + [OP_OFFLOAD_CANCEL] = nfsd4_encode_noop, + [OP_OFFLOAD_STATUS] = nfsd4_encode_offload_status, + [OP_READ_PLUS] = nfsd4_encode_read_plus, + [OP_SEEK] = nfsd4_encode_seek, + [OP_WRITE_SAME] = nfsd4_encode_noop, + [OP_CLONE] = nfsd4_encode_noop, /* RFC 8276 extended atributes operations */ - [OP_GETXATTR] = (nfsd4_enc)nfsd4_encode_getxattr, - [OP_SETXATTR] = (nfsd4_enc)nfsd4_encode_setxattr, - [OP_LISTXATTRS] = (nfsd4_enc)nfsd4_encode_listxattrs, - [OP_REMOVEXATTR] = (nfsd4_enc)nfsd4_encode_removexattr, + [OP_GETXATTR] = nfsd4_encode_getxattr, + [OP_SETXATTR] = nfsd4_encode_setxattr, + [OP_LISTXATTRS] = nfsd4_encode_listxattrs, + [OP_REMOVEXATTR] = nfsd4_encode_removexattr, }; /* diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 573de0d49e1729c1dedef3dffd881490b2d9da27..76a60e7a750978406bcab7b6da8e9201e1f9518e 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -581,7 +581,9 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) cmd = sign == '-' ? NFSD_CLEAR : NFSD_SET; switch(num) { +#ifdef CONFIG_NFSD_V2 case 2: +#endif case 3: nfsd_vers(nn, num, cmd); break; @@ -601,7 +603,9 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) } break; default: - return -EINVAL; + /* Ignore requests to disable non-existent versions */ + if (cmd == NFSD_SET) + return -EINVAL; } vers += len + 1; } while ((len = qword_get(&mesg, vers, size)) > 0); @@ -1448,9 +1452,7 @@ static __net_init int nfsd_init_net(struct net *net) goto out_idmap_error; nn->nfsd_versions = NULL; nn->nfsd4_minorversions = NULL; - retval = nfsd4_init_leases_net(nn); - if (retval) - goto out_drc_error; + nfsd4_init_leases_net(nn); retval = nfsd_reply_cache_init(nn); if (retval) goto out_cache_error; @@ -1460,8 +1462,6 @@ static __net_init int nfsd_init_net(struct net *net) return 0; out_cache_error: - nfsd4_leases_net_shutdown(nn); -out_drc_error: nfsd_idmap_shutdown(net); out_idmap_error: nfsd_export_shutdown(net); @@ -1477,7 +1477,6 @@ static __net_exit void nfsd_exit_net(struct net *net) nfsd_idmap_shutdown(net); nfsd_export_shutdown(net); nfsd_netns_free_versions(net_generic(net, nfsd_net_id)); - nfsd4_leases_net_shutdown(nn); } static struct pernet_operations nfsd_net_ops = { diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 09726c5b9a317bbafe823c1c716e963d7a19f238..fa0144a742678fd46119dc6c871dba69cd383257 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -64,8 +64,7 @@ struct readdir_cd { extern struct svc_program nfsd_program; -extern const struct svc_version nfsd_version2, nfsd_version3, - nfsd_version4; +extern const struct svc_version nfsd_version2, nfsd_version3, nfsd_version4; extern struct mutex nfsd_mutex; extern spinlock_t nfsd_drc_lock; extern unsigned long nfsd_drc_max_mem; @@ -505,8 +504,7 @@ extern void unregister_cld_notifier(void); extern void nfsd4_ssc_init_umount_work(struct nfsd_net *nn); #endif -extern int nfsd4_init_leases_net(struct nfsd_net *nn); -extern void nfsd4_leases_net_shutdown(struct nfsd_net *nn); +extern void nfsd4_init_leases_net(struct nfsd_net *nn); #else /* CONFIG_NFSD_V4 */ static inline int nfsd4_is_junction(struct dentry *dentry) @@ -514,8 +512,7 @@ static inline int nfsd4_is_junction(struct dentry *dentry) return 0; } -static inline int nfsd4_init_leases_net(struct nfsd_net *nn) { return 0; }; -static inline void nfsd4_leases_net_shutdown(struct nfsd_net *nn) {}; +static inline void nfsd4_init_leases_net(struct nfsd_net *nn) { }; #define register_cld_notifier() 0 #define unregister_cld_notifier() do { } while(0) diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index c3ae6414fc5cfd6ac953ca007ad244c6383ff436..513e028b0bbee95b18d6b110bf3f2d3d84e371b7 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -220,7 +220,7 @@ __be32 fh_update(struct svc_fh *); void fh_put(struct svc_fh *); static __inline__ struct svc_fh * -fh_copy(struct svc_fh *dst, struct svc_fh *src) +fh_copy(struct svc_fh *dst, const struct svc_fh *src) { WARN_ON(src->fh_dentry); @@ -229,7 +229,7 @@ fh_copy(struct svc_fh *dst, struct svc_fh *src) } static inline void -fh_copy_shallow(struct knfsd_fh *dst, struct knfsd_fh *src) +fh_copy_shallow(struct knfsd_fh *dst, const struct knfsd_fh *src) { dst->fh_size = src->fh_size; memcpy(&dst->fh_raw, &src->fh_raw, src->fh_size); @@ -243,7 +243,8 @@ fh_init(struct svc_fh *fhp, int maxsize) return fhp; } -static inline bool fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) +static inline bool fh_match(const struct knfsd_fh *fh1, + const struct knfsd_fh *fh2) { if (fh1->fh_size != fh2->fh_size) return false; @@ -252,7 +253,8 @@ static inline bool fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) return true; } -static inline bool fh_fsid_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) +static inline bool fh_fsid_match(const struct knfsd_fh *fh1, + const struct knfsd_fh *fh2) { if (fh1->fh_fsid_type != fh2->fh_fsid_type) return false; diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 82b3ddeacc338a4ffcf85c3440c2f2990e40d002..9744443c396522af6bf9ae34eca57c60a133cc8f 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -211,7 +211,7 @@ nfsd_proc_read(struct svc_rqst *rqstp) if (resp->status == nfs_ok) resp->status = fh_getattr(&resp->fh, &resp->stat); else if (resp->status == nfserr_jukebox) - return rpc_drop_reply; + set_bit(RQ_DROPME, &rqstp->rq_flags); return rpc_success; } @@ -246,7 +246,7 @@ nfsd_proc_write(struct svc_rqst *rqstp) if (resp->status == nfs_ok) resp->status = fh_getattr(&resp->fh, &resp->stat); else if (resp->status == nfserr_jukebox) - return rpc_drop_reply; + set_bit(RQ_DROPME, &rqstp->rq_flags); return rpc_success; } @@ -848,65 +848,3 @@ const struct svc_version nfsd_version2 = { .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS2_SVC_XDRSIZE, }; - -/* - * Map errnos to NFS errnos. - */ -__be32 -nfserrno (int errno) -{ - static struct { - __be32 nfserr; - int syserr; - } nfs_errtbl[] = { - { nfs_ok, 0 }, - { nfserr_perm, -EPERM }, - { nfserr_noent, -ENOENT }, - { nfserr_io, -EIO }, - { nfserr_nxio, -ENXIO }, - { nfserr_fbig, -E2BIG }, - { nfserr_stale, -EBADF }, - { nfserr_acces, -EACCES }, - { nfserr_exist, -EEXIST }, - { nfserr_xdev, -EXDEV }, - { nfserr_mlink, -EMLINK }, - { nfserr_nodev, -ENODEV }, - { nfserr_notdir, -ENOTDIR }, - { nfserr_isdir, -EISDIR }, - { nfserr_inval, -EINVAL }, - { nfserr_fbig, -EFBIG }, - { nfserr_nospc, -ENOSPC }, - { nfserr_rofs, -EROFS }, - { nfserr_mlink, -EMLINK }, - { nfserr_nametoolong, -ENAMETOOLONG }, - { nfserr_notempty, -ENOTEMPTY }, -#ifdef EDQUOT - { nfserr_dquot, -EDQUOT }, -#endif - { nfserr_stale, -ESTALE }, - { nfserr_jukebox, -ETIMEDOUT }, - { nfserr_jukebox, -ERESTARTSYS }, - { nfserr_jukebox, -EAGAIN }, - { nfserr_jukebox, -EWOULDBLOCK }, - { nfserr_jukebox, -ENOMEM }, - { nfserr_io, -ETXTBSY }, - { nfserr_notsupp, -EOPNOTSUPP }, - { nfserr_toosmall, -ETOOSMALL }, - { nfserr_serverfault, -ESERVERFAULT }, - { nfserr_serverfault, -ENFILE }, - { nfserr_io, -EREMOTEIO }, - { nfserr_stale, -EOPENSTALE }, - { nfserr_io, -EUCLEAN }, - { nfserr_perm, -ENOKEY }, - { nfserr_no_grace, -ENOGRACE}, - }; - int i; - - for (i = 0; i < ARRAY_SIZE(nfs_errtbl); i++) { - if (nfs_errtbl[i].syserr == errno) - return nfs_errtbl[i].nfserr; - } - WARN_ONCE(1, "nfsd: non-standard errno: %d\n", errno); - return nfserr_io; -} - diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index c7695ebd28dc3c5b7934d988dc02a318fe599785..a8190caf77f1721df3193c7cf2f754151fe1f957 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -91,8 +91,12 @@ unsigned long nfsd_drc_mem_used; #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static struct svc_stat nfsd_acl_svcstats; static const struct svc_version *nfsd_acl_version[] = { +# if defined(CONFIG_NFSD_V2_ACL) [2] = &nfsd_acl_version2, +# endif +# if defined(CONFIG_NFSD_V3_ACL) [3] = &nfsd_acl_version3, +# endif }; #define NFSD_ACL_MINVERS 2 @@ -116,7 +120,9 @@ static struct svc_stat nfsd_acl_svcstats = { #endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */ static const struct svc_version *nfsd_version[] = { +#if defined(CONFIG_NFSD_V2) [2] = &nfsd_version2, +#endif [3] = &nfsd_version3, #if defined(CONFIG_NFSD_V4) [4] = &nfsd_version4, @@ -946,15 +952,6 @@ nfsd(void *vrqstp) current->fs->umask = 0; - /* - * thread is spawned with all signals set to SIG_IGN, re-enable - * the ones that will bring down the thread - */ - allow_signal(SIGKILL); - allow_signal(SIGHUP); - allow_signal(SIGINT); - allow_signal(SIGQUIT); - atomic_inc(&nfsdstats.th_cnt); set_freezable(); @@ -979,9 +976,6 @@ nfsd(void *vrqstp) validate_process_creds(); } - /* Clear signals before calling svc_exit_thread() */ - flush_signals(current); - atomic_dec(&nfsdstats.th_cnt); out: @@ -1065,7 +1059,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) nfs_reply = xdr_inline_decode(&rqstp->rq_res_stream, 0); *statp = proc->pc_func(rqstp); - if (*statp == rpc_drop_reply || test_bit(RQ_DROPME, &rqstp->rq_flags)) + if (test_bit(RQ_DROPME, &rqstp->rq_flags)) goto out_update_drop; if (!proc->pc_encode(rqstp, &rqstp->rq_res_stream)) diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index e2daef3cc0034b5f785958801fb57cb8268e5566..e94634d3059127f2ca9f385ced1bd694b98ad501 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -368,6 +368,7 @@ struct nfs4_client { #define NFSD4_CLIENT_UPCALL_LOCK (5) /* upcall serialization */ #define NFSD4_CLIENT_CB_FLAG_MASK (1 << NFSD4_CLIENT_CB_UPDATE | \ 1 << NFSD4_CLIENT_CB_KILL) +#define NFSD4_CLIENT_CB_RECALL_ANY (6) unsigned long cl_flags; const struct cred *cl_cb_cred; struct rpc_clnt *cl_cb_client; @@ -411,6 +412,10 @@ struct nfs4_client { unsigned int cl_state; atomic_t cl_delegs_in_recall; + + struct nfsd4_cb_recall_any *cl_ra; + time64_t cl_ra_time; + struct list_head cl_ra_cblist; }; /* struct nfs4_client_reset @@ -536,16 +541,13 @@ struct nfs4_clnt_odstate { * inode can have multiple filehandles associated with it, so there is * (potentially) a many to one relationship between this struct and struct * inode. - * - * These are hashed by filehandle in the file_hashtbl, which is protected by - * the global state_lock spinlock. */ struct nfs4_file { refcount_t fi_ref; struct inode * fi_inode; bool fi_aliased; spinlock_t fi_lock; - struct hlist_node fi_hash; /* hash on fi_fhandle */ + struct rhlist_head fi_rlist; struct list_head fi_stateids; union { struct list_head fi_delegations; @@ -639,6 +641,7 @@ enum nfsd4_cb_op { NFSPROC4_CLNT_CB_OFFLOAD, NFSPROC4_CLNT_CB_SEQUENCE, NFSPROC4_CLNT_CB_NOTIFY_LOCK, + NFSPROC4_CLNT_CB_RECALL_ANY, }; /* Returns true iff a is later than b: */ diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 132335011ccaeaac94f68bb4899ab64318b3cddc..84f26f281fe9f243a45ab3c55e440f3f5fa23b75 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -9,9 +9,12 @@ #define _NFSD_TRACE_H #include +#include +#include #include "export.h" #include "nfsfh.h" +#include "xdr4.h" #define NFSD_TRACE_PROC_RES_FIELDS \ __field(unsigned int, netns_ino) \ @@ -604,6 +607,7 @@ DEFINE_STATEID_EVENT(layout_recall_release); DEFINE_STATEID_EVENT(open); DEFINE_STATEID_EVENT(deleg_read); +DEFINE_STATEID_EVENT(deleg_return); DEFINE_STATEID_EVENT(deleg_recall); DECLARE_EVENT_CLASS(nfsd_stateseqid_class, @@ -636,6 +640,61 @@ DEFINE_EVENT(nfsd_stateseqid_class, nfsd_##name, \ DEFINE_STATESEQID_EVENT(preprocess); DEFINE_STATESEQID_EVENT(open_confirm); +TRACE_DEFINE_ENUM(NFS4_OPEN_STID); +TRACE_DEFINE_ENUM(NFS4_LOCK_STID); +TRACE_DEFINE_ENUM(NFS4_DELEG_STID); +TRACE_DEFINE_ENUM(NFS4_CLOSED_STID); +TRACE_DEFINE_ENUM(NFS4_REVOKED_DELEG_STID); +TRACE_DEFINE_ENUM(NFS4_CLOSED_DELEG_STID); +TRACE_DEFINE_ENUM(NFS4_LAYOUT_STID); + +#define show_stid_type(x) \ + __print_flags(x, "|", \ + { NFS4_OPEN_STID, "OPEN" }, \ + { NFS4_LOCK_STID, "LOCK" }, \ + { NFS4_DELEG_STID, "DELEG" }, \ + { NFS4_CLOSED_STID, "CLOSED" }, \ + { NFS4_REVOKED_DELEG_STID, "REVOKED" }, \ + { NFS4_CLOSED_DELEG_STID, "CLOSED_DELEG" }, \ + { NFS4_LAYOUT_STID, "LAYOUT" }) + +DECLARE_EVENT_CLASS(nfsd_stid_class, + TP_PROTO( + const struct nfs4_stid *stid + ), + TP_ARGS(stid), + TP_STRUCT__entry( + __field(unsigned long, sc_type) + __field(int, sc_count) + __field(u32, cl_boot) + __field(u32, cl_id) + __field(u32, si_id) + __field(u32, si_generation) + ), + TP_fast_assign( + const stateid_t *stp = &stid->sc_stateid; + + __entry->sc_type = stid->sc_type; + __entry->sc_count = refcount_read(&stid->sc_count); + __entry->cl_boot = stp->si_opaque.so_clid.cl_boot; + __entry->cl_id = stp->si_opaque.so_clid.cl_id; + __entry->si_id = stp->si_opaque.so_id; + __entry->si_generation = stp->si_generation; + ), + TP_printk("client %08x:%08x stateid %08x:%08x ref=%d type=%s", + __entry->cl_boot, __entry->cl_id, + __entry->si_id, __entry->si_generation, + __entry->sc_count, show_stid_type(__entry->sc_type) + ) +); + +#define DEFINE_STID_EVENT(name) \ +DEFINE_EVENT(nfsd_stid_class, nfsd_stid_##name, \ + TP_PROTO(const struct nfs4_stid *stid), \ + TP_ARGS(stid)) + +DEFINE_STID_EVENT(revoke); + DECLARE_EVENT_CLASS(nfsd_clientid_class, TP_PROTO(const clientid_t *clid), TP_ARGS(clid), @@ -783,7 +842,7 @@ DECLARE_EVENT_CLASS(nfsd_clid_class, __array(unsigned char, addr, sizeof(struct sockaddr_in6)) __field(unsigned long, flavor) __array(unsigned char, verifier, NFS4_VERIFIER_SIZE) - __string_len(name, name, clp->cl_name.len) + __string_len(name, clp->cl_name.data, clp->cl_name.len) ), TP_fast_assign( __entry->cl_boot = clp->cl_clientid.cl_boot; @@ -1436,6 +1495,32 @@ TRACE_EVENT(nfsd_cb_offload, __entry->fh_hash, __entry->count, __entry->status) ); +TRACE_EVENT(nfsd_cb_recall_any, + TP_PROTO( + const struct nfsd4_cb_recall_any *ra + ), + TP_ARGS(ra), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + __field(u32, keep) + __field(unsigned long, bmval0) + __sockaddr(addr, ra->ra_cb.cb_clp->cl_cb_conn.cb_addrlen) + ), + TP_fast_assign( + __entry->cl_boot = ra->ra_cb.cb_clp->cl_clientid.cl_boot; + __entry->cl_id = ra->ra_cb.cb_clp->cl_clientid.cl_id; + __entry->keep = ra->ra_keep; + __entry->bmval0 = ra->ra_bmval[0]; + __assign_sockaddr(addr, &ra->ra_cb.cb_clp->cl_addr, + ra->ra_cb.cb_clp->cl_cb_conn.cb_addrlen); + ), + TP_printk("addr=%pISpc client %08x:%08x keep=%u bmval0=%s", + __get_sockaddr(addr), __entry->cl_boot, __entry->cl_id, + __entry->keep, show_rca_mask(__entry->bmval0) + ) +); + DECLARE_EVENT_CLASS(nfsd_cb_done_class, TP_PROTO( const stateid_t *stp, @@ -1475,6 +1560,27 @@ DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_notify_lock_done); DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_layout_done); DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_offload_done); +TRACE_EVENT(nfsd_cb_recall_any_done, + TP_PROTO( + const struct nfsd4_callback *cb, + const struct rpc_task *task + ), + TP_ARGS(cb, task), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + __field(int, status) + ), + TP_fast_assign( + __entry->status = task->tk_status; + __entry->cl_boot = cb->cb_clp->cl_clientid.cl_boot; + __entry->cl_id = cb->cb_clp->cl_clientid.cl_id; + ), + TP_printk("client %08x:%08x status=%d", + __entry->cl_boot, __entry->cl_id, __entry->status + ) +); + #endif /* _NFSD_TRACE_H */ #undef TRACE_INCLUDE_PATH diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index eccc6ce55a63a8f483b1163d4dec18dec13711b1..5d6a61d47a90591f41c9694f292c35c9654d6baa 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -49,6 +49,69 @@ #define NFSDDBG_FACILITY NFSDDBG_FILEOP +/** + * nfserrno - Map Linux errnos to NFS errnos + * @errno: POSIX(-ish) error code to be mapped + * + * Returns the appropriate (net-endian) nfserr_* (or nfs_ok if errno is 0). If + * it's an error we don't expect, log it once and return nfserr_io. + */ +__be32 +nfserrno (int errno) +{ + static struct { + __be32 nfserr; + int syserr; + } nfs_errtbl[] = { + { nfs_ok, 0 }, + { nfserr_perm, -EPERM }, + { nfserr_noent, -ENOENT }, + { nfserr_io, -EIO }, + { nfserr_nxio, -ENXIO }, + { nfserr_fbig, -E2BIG }, + { nfserr_stale, -EBADF }, + { nfserr_acces, -EACCES }, + { nfserr_exist, -EEXIST }, + { nfserr_xdev, -EXDEV }, + { nfserr_mlink, -EMLINK }, + { nfserr_nodev, -ENODEV }, + { nfserr_notdir, -ENOTDIR }, + { nfserr_isdir, -EISDIR }, + { nfserr_inval, -EINVAL }, + { nfserr_fbig, -EFBIG }, + { nfserr_nospc, -ENOSPC }, + { nfserr_rofs, -EROFS }, + { nfserr_mlink, -EMLINK }, + { nfserr_nametoolong, -ENAMETOOLONG }, + { nfserr_notempty, -ENOTEMPTY }, + { nfserr_dquot, -EDQUOT }, + { nfserr_stale, -ESTALE }, + { nfserr_jukebox, -ETIMEDOUT }, + { nfserr_jukebox, -ERESTARTSYS }, + { nfserr_jukebox, -EAGAIN }, + { nfserr_jukebox, -EWOULDBLOCK }, + { nfserr_jukebox, -ENOMEM }, + { nfserr_io, -ETXTBSY }, + { nfserr_notsupp, -EOPNOTSUPP }, + { nfserr_toosmall, -ETOOSMALL }, + { nfserr_serverfault, -ESERVERFAULT }, + { nfserr_serverfault, -ENFILE }, + { nfserr_io, -EREMOTEIO }, + { nfserr_stale, -EOPENSTALE }, + { nfserr_io, -EUCLEAN }, + { nfserr_perm, -ENOKEY }, + { nfserr_no_grace, -ENOGRACE}, + }; + int i; + + for (i = 0; i < ARRAY_SIZE(nfs_errtbl); i++) { + if (nfs_errtbl[i].syserr == errno) + return nfs_errtbl[i].nfserr; + } + WARN_ONCE(1, "nfsd: non-standard errno: %d\n", errno); + return nfserr_io; +} + /* * Called from nfsd_lookup and encode_dirent. Check if we have crossed * a mount point. @@ -1317,7 +1380,6 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, iap->ia_mode &= ~current_umask(); err = 0; - host_err = 0; switch (type) { case S_IFREG: host_err = vfs_create(&init_user_ns, dirp, dchild, iap->ia_mode, true); diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index 9744b041105b50b888a327322e228434b25f098a..dbdfef7ae85bbacfb65c0dc46dbc9a5c74ffd9f0 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -60,6 +60,7 @@ static inline void nfsd_attrs_free(struct nfsd_attrs *attrs) posix_acl_release(attrs->na_dpacl); } +__be32 nfserrno (int errno); int nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, struct svc_export **expp); __be32 nfsd_lookup(struct svc_rqst *, struct svc_fh *, diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 36c3340c1d54a4e8db30f4e26ae4acae2097efe8..510978e602da628c19d1c4736a41ba59139547a4 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -896,5 +896,10 @@ struct nfsd4_operation { union nfsd4_op_u *); }; +struct nfsd4_cb_recall_any { + struct nfsd4_callback ra_cb; + u32 ra_keep; + u32 ra_bmval[1]; +}; #endif diff --git a/fs/nfsd/xdr4cb.h b/fs/nfsd/xdr4cb.h index 547cf07cf4e08c3fbfd4da2a2cb48859e403fdf9..0d39af1b00a0f32bcbfb9540164671fb8056a210 100644 --- a/fs/nfsd/xdr4cb.h +++ b/fs/nfsd/xdr4cb.h @@ -48,3 +48,9 @@ #define NFS4_dec_cb_offload_sz (cb_compound_dec_hdr_sz + \ cb_sequence_dec_sz + \ op_dec_sz) +#define NFS4_enc_cb_recall_any_sz (cb_compound_enc_hdr_sz + \ + cb_sequence_enc_sz + \ + 1 + 1 + 1) +#define NFS4_dec_cb_recall_any_sz (cb_compound_dec_hdr_sz + \ + cb_sequence_dec_sz + \ + op_dec_sz) diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 40ce92a332fe7a6553eeb78acf0414a32defac78..146640f0607a3c6c2d9ff471b9b904a7e1183d15 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -724,7 +724,7 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, dat = nilfs_bmap_get_dat(btree); ret = nilfs_dat_translate(dat, ptr, &blocknr); if (ret < 0) - goto out; + goto dat_error; ptr = blocknr; } cnt = 1; @@ -743,7 +743,7 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, if (dat) { ret = nilfs_dat_translate(dat, ptr2, &blocknr); if (ret < 0) - goto out; + goto dat_error; ptr2 = blocknr; } if (ptr2 != ptr + cnt || ++cnt == maxblocks) @@ -781,6 +781,11 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, out: nilfs_btree_free_path(path); return ret; + + dat_error: + if (ret == -ENOENT) + ret = -EINVAL; /* Notify bmap layer of metadata corruption */ + goto out; } static void nilfs_btree_promote_key(struct nilfs_bmap *btree, diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index 9930fa901039fcf16fe1cc4c8476499960c74869..1e7f653c1df7e0344a6d9ef3e9b446291fe7f13f 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -40,8 +40,21 @@ static inline struct nilfs_dat_info *NILFS_DAT_I(struct inode *dat) static int nilfs_dat_prepare_entry(struct inode *dat, struct nilfs_palloc_req *req, int create) { - return nilfs_palloc_get_entry_block(dat, req->pr_entry_nr, - create, &req->pr_entry_bh); + int ret; + + ret = nilfs_palloc_get_entry_block(dat, req->pr_entry_nr, + create, &req->pr_entry_bh); + if (unlikely(ret == -ENOENT)) { + nilfs_err(dat->i_sb, + "DAT doesn't have a block to manage vblocknr = %llu", + (unsigned long long)req->pr_entry_nr); + /* + * Return internal code -EINVAL to notify bmap layer of + * metadata corruption. + */ + ret = -EINVAL; + } + return ret; } static void nilfs_dat_commit_entry(struct inode *dat, @@ -123,11 +136,7 @@ static void nilfs_dat_commit_free(struct inode *dat, int nilfs_dat_prepare_start(struct inode *dat, struct nilfs_palloc_req *req) { - int ret; - - ret = nilfs_dat_prepare_entry(dat, req, 0); - WARN_ON(ret == -ENOENT); - return ret; + return nilfs_dat_prepare_entry(dat, req, 0); } void nilfs_dat_commit_start(struct inode *dat, struct nilfs_palloc_req *req, @@ -154,10 +163,8 @@ int nilfs_dat_prepare_end(struct inode *dat, struct nilfs_palloc_req *req) int ret; ret = nilfs_dat_prepare_entry(dat, req, 0); - if (ret < 0) { - WARN_ON(ret == -ENOENT); + if (ret < 0) return ret; - } kaddr = kmap_atomic(req->pr_entry_bh->b_page); entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr, diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index decd6471300b0f698e0e368e7ef181e05bae0adc..760405da852f6cec7423f69e19752d372f6571c7 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -243,7 +243,7 @@ nilfs_filetype_table[NILFS_FT_MAX] = { #define S_SHIFT 12 static unsigned char -nilfs_type_by_mode[S_IFMT >> S_SHIFT] = { +nilfs_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = { [S_IFREG >> S_SHIFT] = NILFS_FT_REG_FILE, [S_IFDIR >> S_SHIFT] = NILFS_FT_DIR, [S_IFCHR >> S_SHIFT] = NILFS_FT_CHRDEV, diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c index a35f2795b2422ffefc8a22b1892a557b146b2fc6..8f802f7b0840b3e0e457a8c994a9818b966fed66 100644 --- a/fs/nilfs2/direct.c +++ b/fs/nilfs2/direct.c @@ -66,7 +66,7 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, dat = nilfs_bmap_get_dat(direct); ret = nilfs_dat_translate(dat, ptr, &blocknr); if (ret < 0) - return ret; + goto dat_error; ptr = blocknr; } @@ -79,7 +79,7 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, if (dat) { ret = nilfs_dat_translate(dat, ptr2, &blocknr); if (ret < 0) - return ret; + goto dat_error; ptr2 = blocknr; } if (ptr2 != ptr + cnt) @@ -87,6 +87,11 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, } *ptrp = ptr; return cnt; + + dat_error: + if (ret == -ENOENT) + ret = -EINVAL; /* Notify bmap layer of metadata corruption */ + return ret; } static __u64 diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index a265d391ffe92dabd4da8a3d563706f7e267048b..822e8d95d31ef85a04c99d4bd5d8dc074c15a7fc 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -105,7 +105,13 @@ static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf) nilfs_transaction_commit(inode->i_sb); mapped: - wait_for_stable_page(page); + /* + * Since checksumming including data blocks is performed to determine + * the validity of the log to be written and used for recovery, it is + * necessary to wait for writeback to finish here, regardless of the + * stable write requirement of the backing device. + */ + wait_on_page_writeback(page); out: sb_end_pagefault(inode->i_sb); return block_page_mkwrite_return(ret); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index f625872321cca2639cb534bdb598d5242e05326d..8eb4288d46fe031f5b5c432634c9a869a263cd41 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -112,7 +112,7 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff, "%s (ino=%lu): a race condition while inserting a data block at offset=%llu", __func__, inode->i_ino, (unsigned long long)blkoff); - err = 0; + err = -EAGAIN; } nilfs_transaction_abort(inode->i_sb); goto out; diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index 0955b657938ff2ce993d92e7d8f81322ce71c2e1..a9b8d77c8c1d55b551582b826dafdcdcd047d13a 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -472,9 +472,10 @@ static int nilfs_prepare_segment_for_recovery(struct the_nilfs *nilfs, static int nilfs_recovery_copy_block(struct the_nilfs *nilfs, struct nilfs_recovery_block *rb, - struct page *page) + loff_t pos, struct page *page) { struct buffer_head *bh_org; + size_t from = pos & ~PAGE_MASK; void *kaddr; bh_org = __bread(nilfs->ns_bdev, rb->blocknr, nilfs->ns_blocksize); @@ -482,7 +483,7 @@ static int nilfs_recovery_copy_block(struct the_nilfs *nilfs, return -EIO; kaddr = kmap_atomic(page); - memcpy(kaddr + bh_offset(bh_org), bh_org->b_data, bh_org->b_size); + memcpy(kaddr + from, bh_org->b_data, bh_org->b_size); kunmap_atomic(kaddr); brelse(bh_org); return 0; @@ -521,7 +522,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, goto failed_inode; } - err = nilfs_recovery_copy_block(nilfs, rb, page); + err = nilfs_recovery_copy_block(nilfs, rb, pos, page); if (unlikely(err)) goto failed_page; diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index a4a147a983e0acdec3cbf4e2a3876f11da8c8d65..0a84613960dbf629c42ab5529d5e371327b58df9 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1702,7 +1702,6 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) { - set_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { if (bh->b_page != bd_page) { lock_page(bd_page); @@ -1713,6 +1712,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) } break; } + set_buffer_async_write(bh); if (bh->b_page != fs_page) { nilfs_begin_page_io(fs_page); fs_page = bh->b_page; @@ -1798,7 +1798,6 @@ static void nilfs_abort_logs(struct list_head *logs, int err) list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) { - clear_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { clear_buffer_uptodate(bh); if (bh->b_page != bd_page) { @@ -1807,6 +1806,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) } break; } + clear_buffer_async_write(bh); if (bh->b_page != fs_page) { nilfs_end_page_io(fs_page, err); fs_page = bh->b_page; @@ -1894,8 +1894,9 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci) BIT(BH_Delay) | BIT(BH_NILFS_Volatile) | BIT(BH_NILFS_Redirected)); - set_mask_bits(&bh->b_state, clear_bits, set_bits); if (bh == segbuf->sb_super_root) { + set_buffer_uptodate(bh); + clear_buffer_dirty(bh); if (bh->b_page != bd_page) { end_page_writeback(bd_page); bd_page = bh->b_page; @@ -1903,6 +1904,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci) update_sr = true; break; } + set_mask_bits(&bh->b_state, clear_bits, set_bits); if (bh->b_page != fs_page) { nilfs_end_page_io(fs_page, 0); fs_page = bh->b_page; diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c index 2215179c925b3f225f17bf4a49b392cd53ca9228..2618bf5a37892815a6e808090aefa250b7a0ae89 100644 --- a/fs/ntfs3/attrib.c +++ b/fs/ntfs3/attrib.c @@ -1658,8 +1658,10 @@ repack: le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); - if (!attr_b) - return -ENOENT; + if (!attr_b) { + err = -ENOENT; + goto out; + } attr = attr_b; le = le_b; @@ -1740,13 +1742,15 @@ ins_ext: ok: run_truncate_around(run, vcn); out: - if (new_valid > data_size) - new_valid = data_size; + if (attr_b) { + if (new_valid > data_size) + new_valid = data_size; - valid_size = le64_to_cpu(attr_b->nres.valid_size); - if (new_valid != valid_size) { - attr_b->nres.valid_size = cpu_to_le64(valid_size); - mi_b->dirty = true; + valid_size = le64_to_cpu(attr_b->nres.valid_size); + if (new_valid != valid_size) { + attr_b->nres.valid_size = cpu_to_le64(valid_size); + mi_b->dirty = true; + } } return err; diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c index 0c6a68e71e7d4779a5ceefa79b5b9bbf1761b1ce..723e49ec83ce77b3ff4811b0cdf4e7fcf5084a8e 100644 --- a/fs/ntfs3/attrlist.c +++ b/fs/ntfs3/attrlist.c @@ -127,12 +127,13 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni, { size_t off; u16 sz; + const unsigned le_min_size = le_size(0); if (!le) { le = ni->attr_list.le; } else { sz = le16_to_cpu(le->size); - if (sz < sizeof(struct ATTR_LIST_ENTRY)) { + if (sz < le_min_size) { /* Impossible 'cause we should not return such le. */ return NULL; } @@ -141,7 +142,7 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni, /* Check boundary. */ off = PtrOffset(ni->attr_list.le, le); - if (off + sizeof(struct ATTR_LIST_ENTRY) > ni->attr_list.size) { + if (off + le_min_size > ni->attr_list.size) { /* The regular end of list. */ return NULL; } @@ -149,8 +150,7 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni, sz = le16_to_cpu(le->size); /* Check le for errors. */ - if (sz < sizeof(struct ATTR_LIST_ENTRY) || - off + sz > ni->attr_list.size || + if (sz < le_min_size || off + sz > ni->attr_list.size || sz < le->name_off + le->name_len * sizeof(short)) { return NULL; } diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c index d4d9f4ffb6d9a26651d3f154816105eb39e07ed7..72cdfa8727d3c34a7a81515e1cbf84b80b7f4d34 100644 --- a/fs/ntfs3/dir.c +++ b/fs/ntfs3/dir.c @@ -309,11 +309,31 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni, return 0; } - /* NTFS: symlinks are "dir + reparse" or "file + reparse" */ - if (fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT) - dt_type = DT_LNK; - else - dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG; + /* + * NTFS: symlinks are "dir + reparse" or "file + reparse" + * Unfortunately reparse attribute is used for many purposes (several dozens). + * It is not possible here to know is this name symlink or not. + * To get exactly the type of name we should to open inode (read mft). + * getattr for opened file (fstat) correctly returns symlink. + */ + dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG; + + /* + * It is not reliable to detect the type of name using duplicated information + * stored in parent directory. + * The only correct way to get the type of name - read MFT record and find ATTR_STD. + * The code below is not good idea. + * It does additional locks/reads just to get the type of name. + * Should we use additional mount option to enable branch below? + */ + if ((fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT) && + ino != ni->mi.rno) { + struct inode *inode = ntfs_iget5(sbi->sb, &e->ref, NULL); + if (!IS_ERR_OR_NULL(inode)) { + dt_type = fs_umode_to_dtype(inode->i_mode); + iput(inode); + } + } return !dir_emit(ctx, (s8 *)name, name_len, ino, dt_type); } @@ -495,11 +515,9 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, struct INDEX_HDR *hdr; const struct ATTR_FILE_NAME *fname; u32 e_size, off, end; - u64 vbo = 0; size_t drs = 0, fles = 0, bit = 0; - loff_t i_size = ni->vfs_inode.i_size; struct indx_node *node = NULL; - u8 index_bits = ni->dir.index_bits; + size_t max_indx = ni->vfs_inode.i_size >> ni->dir.index_bits; if (is_empty) *is_empty = true; @@ -543,7 +561,7 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, fles += 1; } - if (vbo >= i_size) + if (bit >= max_indx) goto out; err = indx_used_bit(&ni->dir, ni, &bit); @@ -553,8 +571,7 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, if (bit == MINUS_ONE_T) goto out; - vbo = (u64)bit << index_bits; - if (vbo >= i_size) + if (bit >= max_indx) goto out; err = indx_read(&ni->dir, ni, bit << ni->dir.idx2vbn_bits, @@ -564,7 +581,6 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, hdr = &node->index->ihdr; bit += 1; - vbo = (u64)bit << ni->dir.idx2vbn_bits; } out: diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index f31c0389a2e7dc437121ac7e097362faa24ee993..14efe46df91eff605bff42d63425a3e1f3d9a47a 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -1110,6 +1110,8 @@ out: iocb->ki_pos += written; if (iocb->ki_pos > ni->i_valid) ni->i_valid = iocb->ki_pos; + if (iocb->ki_pos > i_size) + i_size_write(inode, iocb->ki_pos); return written; } diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index bb7e33c24073743f0696fea17a308fbe19367ebf..d2602609002417b6b826a0fac7e72105ad26c9a9 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -102,7 +102,7 @@ void ni_clear(struct ntfs_inode *ni) { struct rb_node *node; - if (!ni->vfs_inode.i_nlink && is_rec_inuse(ni->mi.mrec)) + if (!ni->vfs_inode.i_nlink && ni->mi.mrec && is_rec_inuse(ni->mi.mrec)) ni_delete_all(ni); al_destroy(ni); @@ -3255,6 +3255,9 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint) return 0; } + if (!ni->mi.mrec) + goto out; + if (is_rec_inuse(ni->mi.mrec) && !(sbi->flags & NTFS_FLAGS_LOG_REPLAYING) && inode->i_nlink) { bool modified = false; diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index 710cb5aa5a65b0cce8817d12273c0c1f30668b15..d53ef128fa7335a285fcfed91d85a32b2d1baade 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -465,7 +465,7 @@ static inline bool is_rst_area_valid(const struct RESTART_HDR *rhdr) { const struct RESTART_AREA *ra; u16 cl, fl, ul; - u32 off, l_size, file_dat_bits, file_size_round; + u32 off, l_size, seq_bits; u16 ro = le16_to_cpu(rhdr->ra_off); u32 sys_page = le32_to_cpu(rhdr->sys_page_size); @@ -511,13 +511,15 @@ static inline bool is_rst_area_valid(const struct RESTART_HDR *rhdr) /* Make sure the sequence number bits match the log file size. */ l_size = le64_to_cpu(ra->l_size); - file_dat_bits = sizeof(u64) * 8 - le32_to_cpu(ra->seq_num_bits); - file_size_round = 1u << (file_dat_bits + 3); - if (file_size_round != l_size && - (file_size_round < l_size || (file_size_round / 2) > l_size)) { - return false; + seq_bits = sizeof(u64) * 8 + 3; + while (l_size) { + l_size >>= 1; + seq_bits -= 1; } + if (seq_bits != ra->seq_num_bits) + return false; + /* The log page data offset and record header length must be quad-aligned. */ if (!IS_ALIGNED(le16_to_cpu(ra->data_off), 8) || !IS_ALIGNED(le16_to_cpu(ra->rec_hdr_len), 8)) diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 873b1434a9989aa54c1f7657460b05a8c6456e95..4c2d079b3d49babacb7b801333ed35479119f325 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -976,6 +976,30 @@ static inline __le32 security_hash(const void *sd, size_t bytes) return cpu_to_le32(hash); } +/* + * simple wrapper for sb_bread_unmovable. + */ +struct buffer_head *ntfs_bread(struct super_block *sb, sector_t block) +{ + struct ntfs_sb_info *sbi = sb->s_fs_info; + struct buffer_head *bh; + + if (unlikely(block >= sbi->volume.blocks)) { + /* prevent generic message "attempt to access beyond end of device" */ + ntfs_err(sb, "try to read out of volume at offset 0x%llx", + (u64)block << sb->s_blocksize_bits); + return NULL; + } + + bh = sb_bread_unmovable(sb, block); + if (bh) + return bh; + + ntfs_err(sb, "failed to read volume at offset 0x%llx", + (u64)block << sb->s_blocksize_bits); + return NULL; +} + int ntfs_sb_read(struct super_block *sb, u64 lbo, size_t bytes, void *buffer) { struct block_device *bdev = sb->s_bdev; @@ -1650,6 +1674,7 @@ struct ntfs_inode *ntfs_new_inode(struct ntfs_sb_info *sbi, CLST rno, bool dir) out: if (err) { + make_bad_inode(inode); iput(inode); ni = ERR_PTR(err); } @@ -1842,10 +1867,12 @@ int ntfs_security_init(struct ntfs_sb_info *sbi) goto out; } - root_sdh = resident_data_ex(attr, sizeof(struct INDEX_ROOT)); - if (root_sdh->type != ATTR_ZERO || + if(!(root_sdh = resident_data_ex(attr, sizeof(struct INDEX_ROOT))) || + root_sdh->type != ATTR_ZERO || root_sdh->rule != NTFS_COLLATION_TYPE_SECURITY_HASH || - offsetof(struct INDEX_ROOT, ihdr) + root_sdh->ihdr.used > attr->res.data_size) { + offsetof(struct INDEX_ROOT, ihdr) + + le32_to_cpu(root_sdh->ihdr.used) > + le32_to_cpu(attr->res.data_size)) { err = -EINVAL; goto out; } @@ -1861,10 +1888,12 @@ int ntfs_security_init(struct ntfs_sb_info *sbi) goto out; } - root_sii = resident_data_ex(attr, sizeof(struct INDEX_ROOT)); - if (root_sii->type != ATTR_ZERO || + if(!(root_sii = resident_data_ex(attr, sizeof(struct INDEX_ROOT))) || + root_sii->type != ATTR_ZERO || root_sii->rule != NTFS_COLLATION_TYPE_UINT || - offsetof(struct INDEX_ROOT, ihdr) + root_sii->ihdr.used > attr->res.data_size) { + offsetof(struct INDEX_ROOT, ihdr) + + le32_to_cpu(root_sii->ihdr.used) > + le32_to_cpu(attr->res.data_size)) { err = -EINVAL; goto out; } diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index b89a33f5761ef2e96c1069d1cd7db978785083b7..eee01db6e0cc52405f8c2070999825a7bda8163c 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -998,6 +998,7 @@ struct INDEX_ROOT *indx_get_root(struct ntfs_index *indx, struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le = NULL; struct ATTRIB *a; const struct INDEX_NAMES *in = &s_index_names[indx->type]; + struct INDEX_ROOT *root = NULL; a = ni_find_attr(ni, NULL, &le, ATTR_ROOT, in->name, in->name_len, NULL, mi); @@ -1007,7 +1008,15 @@ struct INDEX_ROOT *indx_get_root(struct ntfs_index *indx, struct ntfs_inode *ni, if (attr) *attr = a; - return resident_data_ex(a, sizeof(struct INDEX_ROOT)); + root = resident_data_ex(a, sizeof(struct INDEX_ROOT)); + + /* length check */ + if (root && offsetof(struct INDEX_ROOT, ihdr) + le32_to_cpu(root->ihdr.used) > + le32_to_cpu(a->res.data_size)) { + return NULL; + } + + return root; } static int indx_write(struct ntfs_index *indx, struct ntfs_inode *ni, @@ -1097,7 +1106,8 @@ ok: } /* check for index header length */ - if (offsetof(struct INDEX_BUFFER, ihdr) + ib->ihdr.used > bytes) { + if (offsetof(struct INDEX_BUFFER, ihdr) + le32_to_cpu(ib->ihdr.used) > + bytes) { err = -EINVAL; goto out; } diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index dc937089a464a0c98a0a3c3847d00d782649c844..42dd9fdaf41517ecf43a481e71b23dd7659dd626 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -402,7 +402,6 @@ end_enum: goto out; if (!is_match && name) { - /* Reuse rec as buffer for ascii name. */ err = -ENOENT; goto out; } @@ -417,6 +416,7 @@ end_enum: if (names != le16_to_cpu(rec->hard_links)) { /* Correct minor error on the fly. Do not mark inode as dirty. */ + ntfs_inode_warn(inode, "Correct links count -> %u.", names); rec->hard_links = cpu_to_le16(names); ni->mi.dirty = true; } diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h index 0f38d558169a1fb727d3e2a3fe31720941a24309..ba26a465b3091b2d6aef15f41deed6647a52b099 100644 --- a/fs/ntfs3/ntfs.h +++ b/fs/ntfs3/ntfs.h @@ -517,12 +517,10 @@ struct ATTR_LIST_ENTRY { __le64 vcn; // 0x08: Starting VCN of this attribute. struct MFT_REF ref; // 0x10: MFT record number with attribute. __le16 id; // 0x18: struct ATTRIB ID. - __le16 name[3]; // 0x1A: Just to align. To get real name can use bNameOffset. + __le16 name[]; // 0x1A: Just to align. To get real name can use name_off. }; // sizeof(0x20) -static_assert(sizeof(struct ATTR_LIST_ENTRY) == 0x20); - static inline u32 le_size(u8 name_len) { return ALIGN(offsetof(struct ATTR_LIST_ENTRY, name) + diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 8c9abaf139e67b0e5f31603b3dfdecd010a6fbeb..0f9bec29f2b702fd260dea5664dae8f0446f9f9d 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -467,7 +467,7 @@ bool al_delete_le(struct ntfs_inode *ni, enum ATTR_TYPE type, CLST vcn, int al_update(struct ntfs_inode *ni, int sync); static inline size_t al_aligned(size_t size) { - return (size + 1023) & ~(size_t)1023; + return size_add(size, 1023) & ~(size_t)1023; } /* Globals from bitfunc.c */ @@ -580,6 +580,7 @@ bool check_index_header(const struct INDEX_HDR *hdr, size_t bytes); int log_replay(struct ntfs_inode *ni, bool *initialized); /* Globals from fsntfs.c */ +struct buffer_head *ntfs_bread(struct super_block *sb, sector_t block); bool ntfs_fix_pre_write(struct NTFS_RECORD_HEADER *rhdr, size_t bytes); int ntfs_fix_post_read(struct NTFS_RECORD_HEADER *rhdr, size_t bytes, bool simple); @@ -1012,19 +1013,6 @@ static inline u64 bytes_to_block(const struct super_block *sb, u64 size) return (size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; } -static inline struct buffer_head *ntfs_bread(struct super_block *sb, - sector_t block) -{ - struct buffer_head *bh = sb_bread(sb, block); - - if (bh) - return bh; - - ntfs_err(sb, "failed to read volume at offset 0x%llx", - (u64)block << sb->s_blocksize_bits); - return NULL; -} - static inline struct ntfs_inode *ntfs_i(struct inode *inode) { return container_of(inode, struct ntfs_inode, vfs_inode); diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index ba336c7280b852ecfa8b072dbe7ca00c5761f83a..a8d4ed7bca025b72603d00feda05a15823f1ba8e 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -226,11 +226,6 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) return NULL; } - if (off + asize < off) { - /* overflow check */ - return NULL; - } - attr = Add2Ptr(attr, asize); off += asize; } @@ -253,8 +248,8 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) if ((t32 & 0xf) || (t32 > 0x100)) return NULL; - /* Check boundary. */ - if (off + asize > used) + /* Check overflow and boundary. */ + if (off + asize < off || off + asize > used) return NULL; /* Check size of attribute. */ @@ -491,8 +486,20 @@ bool mi_remove_attr(struct ntfs_inode *ni, struct mft_inode *mi, return false; if (ni && is_attr_indexed(attr)) { - le16_add_cpu(&ni->mi.mrec->hard_links, -1); - ni->mi.dirty = true; + u16 links = le16_to_cpu(ni->mi.mrec->hard_links); + struct ATTR_FILE_NAME *fname = + attr->type != ATTR_NAME ? + NULL : + resident_data_ex(attr, + SIZEOF_ATTRIBUTE_FILENAME); + if (fname && fname->type == FILE_NAME_DOS) { + /* Do not decrease links count deleting DOS name. */ + } else if (!links) { + /* minor error. Not critical. */ + } else { + ni->mi.mrec->hard_links = cpu_to_le16(links - 1); + ni->mi.dirty = true; + } } used -= asize; diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index df15e00c2a3a033565bf3cbffc20898174892487..d98cf7b382bcc2ab39860bb040905ef3b5aec2f7 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -217,6 +217,9 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer, if (!ea->name_len) break; + if (ea->name_len > ea_size) + break; + if (buffer) { /* Check if we can use field ea->name */ if (off + ea_size > size) diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c index 5254256a224d7a0a78f9673a42dc7df386370a4a..4ca8ed410c3cfeda80f5c1496a9885553ceec615 100644 --- a/fs/orangefs/super.c +++ b/fs/orangefs/super.c @@ -527,7 +527,7 @@ struct dentry *orangefs_mount(struct file_system_type *fst, sb->s_fs_info = kzalloc(sizeof(struct orangefs_sb_info_s), GFP_KERNEL); if (!ORANGEFS_SB(sb)) { d = ERR_PTR(-ENOMEM); - goto free_sb_and_op; + goto free_op; } ret = orangefs_fill_sb(sb, diff --git a/fs/pipe.c b/fs/pipe.c index 9873a6030df566d46837441c19b7efef41ca7df9..aa8e6ffe1cb58a1d4e25c6aabf0af5720819398a 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -424,6 +424,18 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) bool was_empty = false; bool wake_next_writer = false; + /* + * Reject writing to watch queue pipes before the point where we lock + * the pipe. + * Otherwise, lockdep would be unhappy if the caller already has another + * pipe locked. + * If we had to support locking a normal pipe and a notification pipe at + * the same time, we could set up lockdep annotations for that, but + * since we don't actually need that, it's simpler to just bail here. + */ + if (pipe_has_watch_queue(pipe)) + return -EXDEV; + /* Null write succeeds. */ if (unlikely(total_len == 0)) return 0; @@ -436,11 +448,6 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) goto out; } - if (pipe_has_watch_queue(pipe)) { - ret = -EXDEV; - goto out; - } - /* * If it wasn't empty we try to merge new data into * the last buffer. diff --git a/fs/proc/array.c b/fs/proc/array.c index 49283b8103c7ea28809bc1ea4026272a0eebff59..d210b2f8b7ed585616dff5e4e17bcc59da58ad41 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -467,13 +467,13 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, int permitted; struct mm_struct *mm; unsigned long long start_time; - unsigned long cmin_flt = 0, cmaj_flt = 0; - unsigned long min_flt = 0, maj_flt = 0; - u64 cutime, cstime, utime, stime; - u64 cgtime, gtime; + unsigned long cmin_flt, cmaj_flt, min_flt, maj_flt; + u64 cutime, cstime, cgtime, utime, stime, gtime; unsigned long rsslim = 0; unsigned long flags; int exit_code = task->exit_code; + struct signal_struct *sig = task->signal; + unsigned int seq = 1; state = *get_task_state(task); vsize = eip = esp = 0; @@ -501,12 +501,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, sigemptyset(&sigign); sigemptyset(&sigcatch); - cutime = cstime = utime = stime = 0; - cgtime = gtime = 0; if (lock_task_sighand(task, &flags)) { - struct signal_struct *sig = task->signal; - if (sig->tty) { struct pid *pgrp = tty_get_pgrp(sig->tty); tty_pgrp = pid_nr_ns(pgrp, ns); @@ -517,27 +513,9 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, num_threads = get_nr_threads(task); collect_sigign_sigcatch(task, &sigign, &sigcatch); - cmin_flt = sig->cmin_flt; - cmaj_flt = sig->cmaj_flt; - cutime = sig->cutime; - cstime = sig->cstime; - cgtime = sig->cgtime; rsslim = READ_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur); - /* add up live thread stats at the group level */ if (whole) { - struct task_struct *t = task; - do { - min_flt += t->min_flt; - maj_flt += t->maj_flt; - gtime += task_gtime(t); - } while_each_thread(task, t); - - min_flt += sig->min_flt; - maj_flt += sig->maj_flt; - thread_group_cputime_adjusted(task, &utime, &stime); - gtime += sig->gtime; - if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED)) exit_code = sig->group_exit_code; } @@ -551,10 +529,41 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, if (permitted && (!whole || num_threads < 2)) wchan = !task_is_running(task); - if (!whole) { + + do { + seq++; /* 2 on the 1st/lockless path, otherwise odd */ + flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq); + + cmin_flt = sig->cmin_flt; + cmaj_flt = sig->cmaj_flt; + cutime = sig->cutime; + cstime = sig->cstime; + cgtime = sig->cgtime; + + if (whole) { + struct task_struct *t; + + min_flt = sig->min_flt; + maj_flt = sig->maj_flt; + gtime = sig->gtime; + + rcu_read_lock(); + __for_each_thread(sig, t) { + min_flt += t->min_flt; + maj_flt += t->maj_flt; + gtime += task_gtime(t); + } + rcu_read_unlock(); + } + } while (need_seqretry(&sig->stats_lock, seq)); + done_seqretry_irqrestore(&sig->stats_lock, seq, flags); + + if (whole) { + thread_group_cputime_adjusted(task, &utime, &stime); + } else { + task_cputime_adjusted(task, &utime, &stime); min_flt = task->min_flt; maj_flt = task->maj_flt; - task_cputime_adjusted(task, &utime, &stime); gtime = task_gtime(task); } diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index ffbadb8b3032d04938411fea3aa90299de8c2946..ea3f104371d628b46fedd7188aa61e4614fd7803 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -182,25 +182,21 @@ static int pstore_unlink(struct inode *dir, struct dentry *dentry) { struct pstore_private *p = d_inode(dentry)->i_private; struct pstore_record *record = p->record; - int rc = 0; if (!record->psi->erase) return -EPERM; /* Make sure we can't race while removing this file. */ - mutex_lock(&records_list_lock); - if (!list_empty(&p->list)) - list_del_init(&p->list); - else - rc = -ENOENT; - p->dentry = NULL; - mutex_unlock(&records_list_lock); - if (rc) - return rc; - - mutex_lock(&record->psi->read_mutex); - record->psi->erase(record); - mutex_unlock(&record->psi->read_mutex); + scoped_guard(mutex, &records_list_lock) { + if (!list_empty(&p->list)) + list_del_init(&p->list); + else + return -ENOENT; + p->dentry = NULL; + } + + scoped_guard(mutex, &record->psi->read_mutex) + record->psi->erase(record); return simple_unlink(dir, dentry); } @@ -292,19 +288,16 @@ static struct dentry *psinfo_lock_root(void) { struct dentry *root; - mutex_lock(&pstore_sb_lock); + guard(mutex)(&pstore_sb_lock); /* * Having no backend is fine -- no records appear. * Not being mounted is fine -- nothing to do. */ - if (!psinfo || !pstore_sb) { - mutex_unlock(&pstore_sb_lock); + if (!psinfo || !pstore_sb) return NULL; - } root = pstore_sb->s_root; inode_lock(d_inode(root)); - mutex_unlock(&pstore_sb_lock); return root; } @@ -313,29 +306,25 @@ int pstore_put_backend_records(struct pstore_info *psi) { struct pstore_private *pos, *tmp; struct dentry *root; - int rc = 0; root = psinfo_lock_root(); if (!root) return 0; - mutex_lock(&records_list_lock); - list_for_each_entry_safe(pos, tmp, &records_list, list) { - if (pos->record->psi == psi) { - list_del_init(&pos->list); - rc = simple_unlink(d_inode(root), pos->dentry); - if (WARN_ON(rc)) - break; - d_drop(pos->dentry); - dput(pos->dentry); - pos->dentry = NULL; + scoped_guard(mutex, &records_list_lock) { + list_for_each_entry_safe(pos, tmp, &records_list, list) { + if (pos->record->psi == psi) { + list_del_init(&pos->list); + d_invalidate(pos->dentry); + simple_unlink(d_inode(root), pos->dentry); + pos->dentry = NULL; + } } } - mutex_unlock(&records_list_lock); inode_unlock(d_inode(root)); - return rc; + return 0; } /* @@ -355,20 +344,20 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record) if (WARN_ON(!inode_is_locked(d_inode(root)))) return -EINVAL; - rc = -EEXIST; + guard(mutex)(&records_list_lock); + /* Skip records that are already present in the filesystem. */ - mutex_lock(&records_list_lock); list_for_each_entry(pos, &records_list, list) { if (pos->record->type == record->type && pos->record->id == record->id && pos->record->psi == record->psi) - goto fail; + return -EEXIST; } rc = -ENOMEM; inode = pstore_get_inode(root->d_sb); if (!inode) - goto fail; + return -ENOMEM; inode->i_mode = S_IFREG | 0444; inode->i_fop = &pstore_file_operations; scnprintf(name, sizeof(name), "%s-%s-%llu%s", @@ -395,7 +384,6 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record) d_add(dentry, inode); list_add(&private->list, &records_list); - mutex_unlock(&records_list_lock); return 0; @@ -403,8 +391,6 @@ fail_private: free_pstore_private(private); fail_inode: iput(inode); -fail: - mutex_unlock(&records_list_lock); return rc; } @@ -450,9 +436,8 @@ static int pstore_fill_super(struct super_block *sb, void *data, int silent) if (!sb->s_root) return -ENOMEM; - mutex_lock(&pstore_sb_lock); - pstore_sb = sb; - mutex_unlock(&pstore_sb_lock); + scoped_guard(mutex, &pstore_sb_lock) + pstore_sb = sb; pstore_get_records(0); @@ -467,17 +452,14 @@ static struct dentry *pstore_mount(struct file_system_type *fs_type, static void pstore_kill_sb(struct super_block *sb) { - mutex_lock(&pstore_sb_lock); + guard(mutex)(&pstore_sb_lock); WARN_ON(pstore_sb && pstore_sb != sb); kill_litter_super(sb); pstore_sb = NULL; - mutex_lock(&records_list_lock); + guard(mutex)(&records_list_lock); INIT_LIST_HEAD(&records_list); - mutex_unlock(&records_list_lock); - - mutex_unlock(&pstore_sb_lock); } static struct file_system_type pstore_fs_type = { diff --git a/fs/pstore/zone.c b/fs/pstore/zone.c index 2770746bb7aa16243a4b7d6d675897c5000ae93a..abca117725c8160dea67d6c8a6d811466e5538f0 100644 --- a/fs/pstore/zone.c +++ b/fs/pstore/zone.c @@ -973,6 +973,8 @@ static ssize_t psz_kmsg_read(struct pstore_zone *zone, char *buf = kasprintf(GFP_KERNEL, "%s: Total %d times\n", kmsg_dump_reason_str(record->reason), record->count); + if (!buf) + return -ENOMEM; hlen = strlen(buf); record->buf = krealloc(buf, hlen + size, GFP_KERNEL); if (!record->buf) { diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index b0cf3869d3bf55cba993aa9bb7e633c8418dfa5a..b67557647d61fea8d15899eca2ad90fd9a6d0e00 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -399,15 +399,17 @@ int dquot_mark_dquot_dirty(struct dquot *dquot) EXPORT_SYMBOL(dquot_mark_dquot_dirty); /* Dirtify all the dquots - this can block when journalling */ -static inline int mark_all_dquot_dirty(struct dquot * const *dquot) +static inline int mark_all_dquot_dirty(struct dquot __rcu * const *dquots) { int ret, err, cnt; + struct dquot *dquot; ret = err = 0; for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (dquot[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (dquot) /* Even in case of error we have to continue */ - ret = mark_dquot_dirty(dquot[cnt]); + ret = mark_dquot_dirty(dquot); if (!err) err = ret; } @@ -1004,14 +1006,15 @@ out: } EXPORT_SYMBOL(dqget); -static inline struct dquot **i_dquot(struct inode *inode) +static inline struct dquot __rcu **i_dquot(struct inode *inode) { - return inode->i_sb->s_op->get_dquots(inode); + /* Force __rcu for now until filesystems are fixed */ + return (struct dquot __rcu **)inode->i_sb->s_op->get_dquots(inode); } static int dqinit_needed(struct inode *inode, int type) { - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; int cnt; if (IS_NOQUOTA(inode)) @@ -1084,59 +1087,7 @@ out: return err; } -/* - * Remove references to dquots from inode and add dquot to list for freeing - * if we have the last reference to dquot - */ -static void remove_inode_dquot_ref(struct inode *inode, int type, - struct list_head *tofree_head) -{ - struct dquot **dquots = i_dquot(inode); - struct dquot *dquot = dquots[type]; - - if (!dquot) - return; - - dquots[type] = NULL; - if (list_empty(&dquot->dq_free)) { - /* - * The inode still has reference to dquot so it can't be in the - * free list - */ - spin_lock(&dq_list_lock); - list_add(&dquot->dq_free, tofree_head); - spin_unlock(&dq_list_lock); - } else { - /* - * Dquot is already in a list to put so we won't drop the last - * reference here. - */ - dqput(dquot); - } -} - -/* - * Free list of dquots - * Dquots are removed from inodes and no new references can be got so we are - * the only ones holding reference - */ -static void put_dquot_list(struct list_head *tofree_head) -{ - struct list_head *act_head; - struct dquot *dquot; - - act_head = tofree_head->next; - while (act_head != tofree_head) { - dquot = list_entry(act_head, struct dquot, dq_free); - act_head = act_head->next; - /* Remove dquot from the list so we won't have problems... */ - list_del_init(&dquot->dq_free); - dqput(dquot); - } -} - -static void remove_dquot_ref(struct super_block *sb, int type, - struct list_head *tofree_head) +static void remove_dquot_ref(struct super_block *sb, int type) { struct inode *inode; #ifdef CONFIG_QUOTA_DEBUG @@ -1153,11 +1104,18 @@ static void remove_dquot_ref(struct super_block *sb, int type, */ spin_lock(&dq_data_lock); if (!IS_NOQUOTA(inode)) { + struct dquot __rcu **dquots = i_dquot(inode); + struct dquot *dquot = srcu_dereference_check( + dquots[type], &dquot_srcu, + lockdep_is_held(&dq_data_lock)); + #ifdef CONFIG_QUOTA_DEBUG if (unlikely(inode_get_rsv_space(inode) > 0)) reserved = 1; #endif - remove_inode_dquot_ref(inode, type, tofree_head); + rcu_assign_pointer(dquots[type], NULL); + if (dquot) + dqput(dquot); } spin_unlock(&dq_data_lock); } @@ -1174,13 +1132,8 @@ static void remove_dquot_ref(struct super_block *sb, int type, /* Gather all references from inodes and drop them */ static void drop_dquot_ref(struct super_block *sb, int type) { - LIST_HEAD(tofree_head); - - if (sb->dq_op) { - remove_dquot_ref(sb, type, &tofree_head); - synchronize_srcu(&dquot_srcu); - put_dquot_list(&tofree_head); - } + if (sb->dq_op) + remove_dquot_ref(sb, type); } static inline @@ -1513,7 +1466,8 @@ static int inode_quota_active(const struct inode *inode) static int __dquot_initialize(struct inode *inode, int type) { int cnt, init_needed = 0; - struct dquot **dquots, *got[MAXQUOTAS] = {}; + struct dquot __rcu **dquots; + struct dquot *got[MAXQUOTAS] = {}; struct super_block *sb = inode->i_sb; qsize_t rsv; int ret = 0; @@ -1588,7 +1542,7 @@ static int __dquot_initialize(struct inode *inode, int type) if (!got[cnt]) continue; if (!dquots[cnt]) { - dquots[cnt] = got[cnt]; + rcu_assign_pointer(dquots[cnt], got[cnt]); got[cnt] = NULL; /* * Make quota reservation system happy if someone @@ -1596,12 +1550,16 @@ static int __dquot_initialize(struct inode *inode, int type) */ rsv = inode_get_rsv_space(inode); if (unlikely(rsv)) { + struct dquot *dquot = srcu_dereference_check( + dquots[cnt], &dquot_srcu, + lockdep_is_held(&dq_data_lock)); + spin_lock(&inode->i_lock); /* Get reservation again under proper lock */ rsv = __inode_get_rsv_space(inode); - spin_lock(&dquots[cnt]->dq_dqb_lock); - dquots[cnt]->dq_dqb.dqb_rsvspace += rsv; - spin_unlock(&dquots[cnt]->dq_dqb_lock); + spin_lock(&dquot->dq_dqb_lock); + dquot->dq_dqb.dqb_rsvspace += rsv; + spin_unlock(&dquot->dq_dqb_lock); spin_unlock(&inode->i_lock); } } @@ -1623,7 +1581,7 @@ EXPORT_SYMBOL(dquot_initialize); bool dquot_initialize_needed(struct inode *inode) { - struct dquot **dquots; + struct dquot __rcu **dquots; int i; if (!inode_quota_active(inode)) @@ -1648,13 +1606,14 @@ EXPORT_SYMBOL(dquot_initialize_needed); static void __dquot_drop(struct inode *inode) { int cnt; - struct dquot **dquots = i_dquot(inode); + struct dquot __rcu **dquots = i_dquot(inode); struct dquot *put[MAXQUOTAS]; spin_lock(&dq_data_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - put[cnt] = dquots[cnt]; - dquots[cnt] = NULL; + put[cnt] = srcu_dereference_check(dquots[cnt], &dquot_srcu, + lockdep_is_held(&dq_data_lock)); + rcu_assign_pointer(dquots[cnt], NULL); } spin_unlock(&dq_data_lock); dqput_all(put); @@ -1662,7 +1621,7 @@ static void __dquot_drop(struct inode *inode) void dquot_drop(struct inode *inode) { - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; int cnt; if (IS_NOQUOTA(inode)) @@ -1735,7 +1694,8 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) int cnt, ret = 0, index; struct dquot_warn warn[MAXQUOTAS]; int reserve = flags & DQUOT_SPACE_RESERVE; - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; if (!inode_quota_active(inode)) { if (reserve) { @@ -1755,27 +1715,26 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; if (reserve) { - ret = dquot_add_space(dquots[cnt], 0, number, flags, - &warn[cnt]); + ret = dquot_add_space(dquot, 0, number, flags, &warn[cnt]); } else { - ret = dquot_add_space(dquots[cnt], number, 0, flags, - &warn[cnt]); + ret = dquot_add_space(dquot, number, 0, flags, &warn[cnt]); } if (ret) { /* Back out changes we already did */ for (cnt--; cnt >= 0; cnt--) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - spin_lock(&dquots[cnt]->dq_dqb_lock); + spin_lock(&dquot->dq_dqb_lock); if (reserve) - dquot_free_reserved_space(dquots[cnt], - number); + dquot_free_reserved_space(dquot, number); else - dquot_decr_space(dquots[cnt], number); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + dquot_decr_space(dquot, number); + spin_unlock(&dquot->dq_dqb_lock); } spin_unlock(&inode->i_lock); goto out_flush_warn; @@ -1805,7 +1764,8 @@ int dquot_alloc_inode(struct inode *inode) { int cnt, ret = 0, index; struct dquot_warn warn[MAXQUOTAS]; - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; + struct dquot *dquot; if (!inode_quota_active(inode)) return 0; @@ -1816,17 +1776,19 @@ int dquot_alloc_inode(struct inode *inode) index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - ret = dquot_add_inodes(dquots[cnt], 1, &warn[cnt]); + ret = dquot_add_inodes(dquot, 1, &warn[cnt]); if (ret) { for (cnt--; cnt >= 0; cnt--) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; /* Back out changes we already did */ - spin_lock(&dquots[cnt]->dq_dqb_lock); - dquot_decr_inodes(dquots[cnt], 1); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + spin_lock(&dquot->dq_dqb_lock); + dquot_decr_inodes(dquot, 1); + spin_unlock(&dquot->dq_dqb_lock); } goto warn_put_all; } @@ -1847,7 +1809,8 @@ EXPORT_SYMBOL(dquot_alloc_inode); */ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) { - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; int cnt, index; if (!inode_quota_active(inode)) { @@ -1863,9 +1826,8 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) spin_lock(&inode->i_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (dquots[cnt]) { - struct dquot *dquot = dquots[cnt]; - + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (dquot) { spin_lock(&dquot->dq_dqb_lock); if (WARN_ON_ONCE(dquot->dq_dqb.dqb_rsvspace < number)) number = dquot->dq_dqb.dqb_rsvspace; @@ -1889,7 +1851,8 @@ EXPORT_SYMBOL(dquot_claim_space_nodirty); */ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) { - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; int cnt, index; if (!inode_quota_active(inode)) { @@ -1905,9 +1868,8 @@ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) spin_lock(&inode->i_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (dquots[cnt]) { - struct dquot *dquot = dquots[cnt]; - + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (dquot) { spin_lock(&dquot->dq_dqb_lock); if (WARN_ON_ONCE(dquot->dq_dqb.dqb_curspace < number)) number = dquot->dq_dqb.dqb_curspace; @@ -1933,7 +1895,8 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) { unsigned int cnt; struct dquot_warn warn[MAXQUOTAS]; - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; int reserve = flags & DQUOT_SPACE_RESERVE, index; if (!inode_quota_active(inode)) { @@ -1954,17 +1917,18 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) int wtype; warn[cnt].w_type = QUOTA_NL_NOWARN; - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - spin_lock(&dquots[cnt]->dq_dqb_lock); - wtype = info_bdq_free(dquots[cnt], number); + spin_lock(&dquot->dq_dqb_lock); + wtype = info_bdq_free(dquot, number); if (wtype != QUOTA_NL_NOWARN) - prepare_warning(&warn[cnt], dquots[cnt], wtype); + prepare_warning(&warn[cnt], dquot, wtype); if (reserve) - dquot_free_reserved_space(dquots[cnt], number); + dquot_free_reserved_space(dquot, number); else - dquot_decr_space(dquots[cnt], number); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + dquot_decr_space(dquot, number); + spin_unlock(&dquot->dq_dqb_lock); } if (reserve) *inode_reserved_space(inode) -= number; @@ -1988,7 +1952,8 @@ void dquot_free_inode(struct inode *inode) { unsigned int cnt; struct dquot_warn warn[MAXQUOTAS]; - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; + struct dquot *dquot; int index; if (!inode_quota_active(inode)) @@ -1999,16 +1964,16 @@ void dquot_free_inode(struct inode *inode) spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { int wtype; - warn[cnt].w_type = QUOTA_NL_NOWARN; - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - spin_lock(&dquots[cnt]->dq_dqb_lock); - wtype = info_idq_free(dquots[cnt], 1); + spin_lock(&dquot->dq_dqb_lock); + wtype = info_idq_free(dquot, 1); if (wtype != QUOTA_NL_NOWARN) - prepare_warning(&warn[cnt], dquots[cnt], wtype); - dquot_decr_inodes(dquots[cnt], 1); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + prepare_warning(&warn[cnt], dquot, wtype); + dquot_decr_inodes(dquot, 1); + spin_unlock(&dquot->dq_dqb_lock); } spin_unlock(&inode->i_lock); mark_all_dquot_dirty(dquots); @@ -2034,8 +1999,9 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) qsize_t cur_space; qsize_t rsv_space = 0; qsize_t inode_usage = 1; + struct dquot __rcu **dquots; struct dquot *transfer_from[MAXQUOTAS] = {}; - int cnt, ret = 0; + int cnt, index, ret = 0; char is_valid[MAXQUOTAS] = {}; struct dquot_warn warn_to[MAXQUOTAS]; struct dquot_warn warn_from_inodes[MAXQUOTAS]; @@ -2066,6 +2032,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) } cur_space = __inode_get_bytes(inode); rsv_space = __inode_get_rsv_space(inode); + dquots = i_dquot(inode); /* * Build the transfer_from list, check limits, and update usage in * the target structures. @@ -2080,7 +2047,8 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) if (!sb_has_quota_active(inode->i_sb, cnt)) continue; is_valid[cnt] = 1; - transfer_from[cnt] = i_dquot(inode)[cnt]; + transfer_from[cnt] = srcu_dereference_check(dquots[cnt], + &dquot_srcu, lockdep_is_held(&dq_data_lock)); ret = dquot_add_inodes(transfer_to[cnt], inode_usage, &warn_to[cnt]); if (ret) @@ -2119,13 +2087,21 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) rsv_space); spin_unlock(&transfer_from[cnt]->dq_dqb_lock); } - i_dquot(inode)[cnt] = transfer_to[cnt]; + rcu_assign_pointer(dquots[cnt], transfer_to[cnt]); } spin_unlock(&inode->i_lock); spin_unlock(&dq_data_lock); - mark_all_dquot_dirty(transfer_from); - mark_all_dquot_dirty(transfer_to); + /* + * These arrays are local and we hold dquot references so we don't need + * the srcu protection but still take dquot_srcu to avoid warning in + * mark_all_dquot_dirty(). + */ + index = srcu_read_lock(&dquot_srcu); + mark_all_dquot_dirty((struct dquot __rcu **)transfer_from); + mark_all_dquot_dirty((struct dquot __rcu **)transfer_to); + srcu_read_unlock(&dquot_srcu, index); + flush_warnings(warn_to); flush_warnings(warn_from_inodes); flush_warnings(warn_from_space); diff --git a/fs/select.c b/fs/select.c index 0ee55af1a55c29b14b118907b98e0329b8792376..d4d881d439dcdf82086de22ffcc71278b2314798 100644 --- a/fs/select.c +++ b/fs/select.c @@ -476,7 +476,7 @@ static inline void wait_key_set(poll_table *wait, unsigned long in, wait->_key |= POLLOUT_SET; } -static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) +static noinline_for_stack int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) { ktime_t expire, *to = NULL; struct poll_wqueues table; diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index 5a132c1e6f6c4def3b4d80f3d10cfd8e00ce4511..2ca1881919c7b30ee423b2ae74f7386413c1ccc1 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -149,7 +149,7 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, return -EOPNOTSUPP; ses = tcon->ses; - server = ses->server; + server = cifs_pick_channel(ses); cfids = tcon->cfids; if (!server->ops->new_lease_key) @@ -218,7 +218,8 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, .tcon = tcon, .path = path, .create_options = cifs_create_options(cifs_sb, CREATE_NOT_FILE), - .desired_access = FILE_READ_DATA | FILE_READ_ATTRIBUTES, + .desired_access = FILE_READ_DATA | FILE_READ_ATTRIBUTES | + FILE_READ_EA, .disposition = FILE_OPEN, .fid = pfid, }; @@ -268,10 +269,12 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, if (o_rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) goto oshr_free; - smb2_parse_contexts(server, o_rsp, + rc = smb2_parse_contexts(server, rsp_iov, &oparms.fid->epoch, - oparms.fid->lease_key, &oplock, - NULL, NULL); + oparms.fid->lease_key, + &oplock, NULL, NULL); + if (rc) + goto oshr_free; if (!(oplock & SMB2_LEASE_READ_CACHING_HE)) goto oshr_free; qi_rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; @@ -367,6 +370,7 @@ smb2_close_cached_fid(struct kref *ref) { struct cached_fid *cfid = container_of(ref, struct cached_fid, refcount); + int rc; spin_lock(&cfid->cfids->cfid_list_lock); if (cfid->on_list) { @@ -380,9 +384,10 @@ smb2_close_cached_fid(struct kref *ref) cfid->dentry = NULL; if (cfid->is_open) { - SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, + rc = SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, cfid->fid.volatile_fid); - atomic_dec(&cfid->tcon->num_remote_opens); + if (rc) /* should we retry on -EBUSY or -EAGAIN? */ + cifs_dbg(VFS, "close cached dir rc %d\n", rc); } free_cached_dir(cfid); diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c index 5df8d93233376c46172f108d50aba6eb8974e4bb..a2afdf9c5f80bf4ac94091ec98baf29a07f8e745 100644 --- a/fs/smb/client/cifs_debug.c +++ b/fs/smb/client/cifs_debug.c @@ -186,6 +186,8 @@ static int cifs_debug_files_proc_show(struct seq_file *m, void *v) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); list_for_each_entry(cfile, &tcon->openFileList, tlist) { @@ -566,6 +568,8 @@ static ssize_t cifs_stats_proc_write(struct file *file, } #endif /* CONFIG_CIFS_STATS2 */ list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { atomic_set(&tcon->num_smbs_sent, 0); spin_lock(&tcon->stat_lock); @@ -644,6 +648,8 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v) } #endif /* STATS2 */ list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { i++; seq_printf(m, "\n%d) %s", i, tcon->tree_name); diff --git a/fs/smb/client/cifs_spnego.h b/fs/smb/client/cifs_spnego.h index 7f102ffeb675014985a16108596d6ee61b4517be..e4d751b0c812777ea4afc5c3afb6af5cca1baf8a 100644 --- a/fs/smb/client/cifs_spnego.h +++ b/fs/smb/client/cifs_spnego.h @@ -24,7 +24,7 @@ struct cifs_spnego_msg { uint32_t flags; uint32_t sesskey_len; uint32_t secblob_len; - uint8_t data[1]; + uint8_t data[]; }; #ifdef __KERNEL__ diff --git a/fs/smb/client/cifsencrypt.c b/fs/smb/client/cifsencrypt.c index d0ac2648c0d61c5e87b8fc2a0ee5cff03bc4a62d..d3d4cf6321fd53ce5b71b3ba847823c04dafecba 100644 --- a/fs/smb/client/cifsencrypt.c +++ b/fs/smb/client/cifsencrypt.c @@ -444,7 +444,7 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash, len = cifs_strtoUTF16(user, ses->user_name, len, nls_cp); UniStrupr(user); } else { - memset(user, '\0', 2); + *(u16 *)user = 0; } rc = crypto_shash_update(ses->server->secmech.hmacmd5, diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 7286a56aebfa9d59b16dc6de0333e4f92756f56d..f0a3336ffb6c8468c37474eea25a9986403d4cd9 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -154,6 +154,7 @@ struct workqueue_struct *decrypt_wq; struct workqueue_struct *fileinfo_put_wq; struct workqueue_struct *cifsoplockd_wq; struct workqueue_struct *deferredclose_wq; +struct workqueue_struct *serverclose_wq; __u32 cifs_lock_secret; /* @@ -386,6 +387,7 @@ cifs_alloc_inode(struct super_block *sb) * server, can not assume caching of file data or metadata. */ cifs_set_oplock_level(cifs_inode, 0); + cifs_inode->lease_granted = false; cifs_inode->flags = 0; spin_lock_init(&cifs_inode->writers_lock); cifs_inode->writers = 0; @@ -1866,6 +1868,13 @@ init_cifs(void) goto out_destroy_cifsoplockd_wq; } + serverclose_wq = alloc_workqueue("serverclose", + WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); + if (!serverclose_wq) { + rc = -ENOMEM; + goto out_destroy_serverclose_wq; + } + rc = cifs_init_inodecache(); if (rc) goto out_destroy_deferredclose_wq; @@ -1940,6 +1949,8 @@ out_destroy_decrypt_wq: destroy_workqueue(decrypt_wq); out_destroy_cifsiod_wq: destroy_workqueue(cifsiod_wq); +out_destroy_serverclose_wq: + destroy_workqueue(serverclose_wq); out_clean_proc: cifs_proc_clean(); return rc; @@ -1969,6 +1980,7 @@ exit_cifs(void) destroy_workqueue(cifsoplockd_wq); destroy_workqueue(decrypt_wq); destroy_workqueue(fileinfo_put_wq); + destroy_workqueue(serverclose_wq); destroy_workqueue(cifsiod_wq); cifs_proc_clean(); } diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 7f1aea4c11b9c9055596a92f71ab92cac0e05f0d..e5a72f9c793ef82a238ef9834b4d70297f4a8647 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -86,7 +86,7 @@ #define SMB_INTERFACE_POLL_INTERVAL 600 /* maximum number of PDUs in one compound */ -#define MAX_COMPOUND 5 +#define MAX_COMPOUND 7 /* * Default number of credits to keep available for SMB3. @@ -389,10 +389,10 @@ struct smb_version_operations { /* set fid protocol-specific info */ void (*set_fid)(struct cifsFileInfo *, struct cifs_fid *, __u32); /* close a file */ - void (*close)(const unsigned int, struct cifs_tcon *, + int (*close)(const unsigned int, struct cifs_tcon *, struct cifs_fid *); /* close a file, returning file attributes and timestamps */ - void (*close_getattr)(const unsigned int xid, struct cifs_tcon *tcon, + int (*close_getattr)(const unsigned int xid, struct cifs_tcon *tcon, struct cifsFileInfo *pfile_info); /* send a flush request to the server */ int (*flush)(const unsigned int, struct cifs_tcon *, struct cifs_fid *); @@ -1359,6 +1359,7 @@ struct cifsFileInfo { bool invalidHandle:1; /* file closed via session abend */ bool swapfile:1; bool oplock_break_cancelled:1; + bool offload:1; /* offload final part of _put to a wq */ unsigned int oplock_epoch; /* epoch from the lease break */ __u32 oplock_level; /* oplock/lease level from the lease break */ int count; @@ -1367,6 +1368,7 @@ struct cifsFileInfo { struct cifs_search_info srch_inf; struct work_struct oplock_break; /* work for oplock breaks */ struct work_struct put; /* work for the final part of _put */ + struct work_struct serverclose; /* work for serverclose */ struct delayed_work deferred; bool deferred_close_scheduled; /* Flag to indicate close is scheduled */ char *symlink_target; @@ -2005,6 +2007,7 @@ extern struct workqueue_struct *decrypt_wq; extern struct workqueue_struct *fileinfo_put_wq; extern struct workqueue_struct *cifsoplockd_wq; extern struct workqueue_struct *deferredclose_wq; +extern struct workqueue_struct *serverclose_wq; extern __u32 cifs_lock_secret; extern mempool_t *cifs_mid_poolp; @@ -2175,4 +2178,14 @@ static inline struct scatterlist *cifs_sg_set_buf(struct scatterlist *sg, return sg; } +static inline bool cifs_ses_exiting(struct cifs_ses *ses) +{ + bool ret; + + spin_lock(&ses->ses_lock); + ret = ses->ses_status == SES_EXITING; + spin_unlock(&ses->ses_lock); + return ret; +} + #endif /* _CIFS_GLOB_H */ diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h index 97bb1838555b444dc891a4b755d9ef188a8a97b7..9cb4577063344387c1333ab527eab5962b9a4240 100644 --- a/fs/smb/client/cifspdu.h +++ b/fs/smb/client/cifspdu.h @@ -562,7 +562,7 @@ typedef union smb_com_session_setup_andx { __u32 Reserved; __le32 Capabilities; /* see below */ __le16 ByteCount; - unsigned char SecurityBlob[1]; /* followed by */ + unsigned char SecurityBlob[]; /* followed by */ /* STRING NativeOS */ /* STRING NativeLanMan */ } __attribute__((packed)) req; /* NTLM request format (with @@ -582,7 +582,7 @@ typedef union smb_com_session_setup_andx { __u32 Reserved; /* see below */ __le32 Capabilities; __le16 ByteCount; - unsigned char CaseInsensitivePassword[1]; /* followed by: */ + unsigned char CaseInsensitivePassword[]; /* followed by: */ /* unsigned char * CaseSensitivePassword; */ /* STRING AccountName */ /* STRING PrimaryDomain */ @@ -599,7 +599,7 @@ typedef union smb_com_session_setup_andx { __le16 Action; /* see below */ __le16 SecurityBlobLength; __u16 ByteCount; - unsigned char SecurityBlob[1]; /* followed by */ + unsigned char SecurityBlob[]; /* followed by */ /* unsigned char * NativeOS; */ /* unsigned char * NativeLanMan; */ /* unsigned char * PrimaryDomain; */ @@ -618,7 +618,7 @@ typedef union smb_com_session_setup_andx { __le16 PasswordLength; __u32 Reserved; /* encrypt key len and offset */ __le16 ByteCount; - unsigned char AccountPassword[1]; /* followed by */ + unsigned char AccountPassword[]; /* followed by */ /* STRING AccountName */ /* STRING PrimaryDomain */ /* STRING NativeOS */ @@ -632,7 +632,7 @@ typedef union smb_com_session_setup_andx { __le16 AndXOffset; __le16 Action; /* see below */ __u16 ByteCount; - unsigned char NativeOS[1]; /* followed by */ + unsigned char NativeOS[]; /* followed by */ /* unsigned char * NativeLanMan; */ /* unsigned char * PrimaryDomain; */ } __attribute__((packed)) old_resp; /* pre-NTLM (LANMAN2.1) response */ @@ -693,7 +693,7 @@ typedef struct smb_com_tconx_req { __le16 Flags; /* see below */ __le16 PasswordLength; __le16 ByteCount; - unsigned char Password[1]; /* followed by */ + unsigned char Password[]; /* followed by */ /* STRING Path *//* \\server\share name */ /* STRING Service */ } __attribute__((packed)) TCONX_REQ; @@ -705,7 +705,7 @@ typedef struct smb_com_tconx_rsp { __le16 AndXOffset; __le16 OptionalSupport; /* see below */ __u16 ByteCount; - unsigned char Service[1]; /* always ASCII, not Unicode */ + unsigned char Service[]; /* always ASCII, not Unicode */ /* STRING NativeFileSystem */ } __attribute__((packed)) TCONX_RSP; @@ -718,7 +718,7 @@ typedef struct smb_com_tconx_rsp_ext { __le32 MaximalShareAccessRights; __le32 GuestMaximalShareAccessRights; __u16 ByteCount; - unsigned char Service[1]; /* always ASCII, not Unicode */ + unsigned char Service[]; /* always ASCII, not Unicode */ /* STRING NativeFileSystem */ } __attribute__((packed)) TCONX_RSP_EXT; @@ -755,14 +755,14 @@ typedef struct smb_com_echo_req { struct smb_hdr hdr; __le16 EchoCount; __le16 ByteCount; - char Data[1]; + char Data[]; } __attribute__((packed)) ECHO_REQ; typedef struct smb_com_echo_rsp { struct smb_hdr hdr; __le16 SequenceNumber; __le16 ByteCount; - char Data[1]; + char Data[]; } __attribute__((packed)) ECHO_RSP; typedef struct smb_com_logoff_andx_req { @@ -862,7 +862,7 @@ typedef struct smb_com_open_req { /* also handles create */ __le32 ImpersonationLevel; __u8 SecurityFlags; __le16 ByteCount; - char fileName[1]; + char fileName[]; } __attribute__((packed)) OPEN_REQ; /* open response: oplock levels */ @@ -882,7 +882,7 @@ typedef struct smb_com_open_rsp { __u8 OplockLevel; __u16 Fid; __le32 CreateAction; - struct_group(common_attributes, + struct_group_attr(common_attributes, __packed, __le64 CreationTime; __le64 LastAccessTime; __le64 LastWriteTime; @@ -939,7 +939,7 @@ typedef struct smb_com_openx_req { __le32 Timeout; __le32 Reserved; __le16 ByteCount; /* file name follows */ - char fileName[1]; + char fileName[]; } __attribute__((packed)) OPENX_REQ; typedef struct smb_com_openx_rsp { @@ -1087,7 +1087,7 @@ typedef struct smb_com_lock_req { __le16 NumberOfUnlocks; __le16 NumberOfLocks; __le16 ByteCount; - LOCKING_ANDX_RANGE Locks[1]; + LOCKING_ANDX_RANGE Locks[]; } __attribute__((packed)) LOCK_REQ; /* lock type */ @@ -1116,7 +1116,7 @@ typedef struct smb_com_rename_req { __le16 SearchAttributes; /* target file attributes */ __le16 ByteCount; __u8 BufferFormat; /* 4 = ASCII or Unicode */ - unsigned char OldFileName[1]; + unsigned char OldFileName[]; /* followed by __u8 BufferFormat2 */ /* followed by NewFileName */ } __attribute__((packed)) RENAME_REQ; @@ -1136,7 +1136,7 @@ typedef struct smb_com_copy_req { __le16 Flags; __le16 ByteCount; __u8 BufferFormat; /* 4 = ASCII or Unicode */ - unsigned char OldFileName[1]; + unsigned char OldFileName[]; /* followed by __u8 BufferFormat2 */ /* followed by NewFileName string */ } __attribute__((packed)) COPY_REQ; @@ -1146,7 +1146,7 @@ typedef struct smb_com_copy_rsp { __le16 CopyCount; /* number of files copied */ __u16 ByteCount; /* may be zero */ __u8 BufferFormat; /* 0x04 - only present if errored file follows */ - unsigned char ErrorFileName[1]; /* only present if error in copy */ + unsigned char ErrorFileName[]; /* only present if error in copy */ } __attribute__((packed)) COPY_RSP; #define CREATE_HARD_LINK 0x103 @@ -1160,7 +1160,7 @@ typedef struct smb_com_nt_rename_req { /* A5 - also used for create hardlink */ __le32 ClusterCount; __le16 ByteCount; __u8 BufferFormat; /* 4 = ASCII or Unicode */ - unsigned char OldFileName[1]; + unsigned char OldFileName[]; /* followed by __u8 BufferFormat2 */ /* followed by NewFileName */ } __attribute__((packed)) NT_RENAME_REQ; @@ -1175,7 +1175,7 @@ typedef struct smb_com_delete_file_req { __le16 SearchAttributes; __le16 ByteCount; __u8 BufferFormat; /* 4 = ASCII */ - unsigned char fileName[1]; + unsigned char fileName[]; } __attribute__((packed)) DELETE_FILE_REQ; typedef struct smb_com_delete_file_rsp { @@ -1187,7 +1187,7 @@ typedef struct smb_com_delete_directory_req { struct smb_hdr hdr; /* wct = 0 */ __le16 ByteCount; __u8 BufferFormat; /* 4 = ASCII */ - unsigned char DirName[1]; + unsigned char DirName[]; } __attribute__((packed)) DELETE_DIRECTORY_REQ; typedef struct smb_com_delete_directory_rsp { @@ -1199,7 +1199,7 @@ typedef struct smb_com_create_directory_req { struct smb_hdr hdr; /* wct = 0 */ __le16 ByteCount; __u8 BufferFormat; /* 4 = ASCII */ - unsigned char DirName[1]; + unsigned char DirName[]; } __attribute__((packed)) CREATE_DIRECTORY_REQ; typedef struct smb_com_create_directory_rsp { @@ -1211,7 +1211,7 @@ typedef struct smb_com_query_information_req { struct smb_hdr hdr; /* wct = 0 */ __le16 ByteCount; /* 1 + namelen + 1 */ __u8 BufferFormat; /* 4 = ASCII */ - unsigned char FileName[1]; + unsigned char FileName[]; } __attribute__((packed)) QUERY_INFORMATION_REQ; typedef struct smb_com_query_information_rsp { @@ -1231,7 +1231,7 @@ typedef struct smb_com_setattr_req { __le16 reserved[5]; /* must be zero */ __u16 ByteCount; __u8 BufferFormat; /* 4 = ASCII */ - unsigned char fileName[1]; + unsigned char fileName[]; } __attribute__((packed)) SETATTR_REQ; typedef struct smb_com_setattr_rsp { @@ -1313,7 +1313,7 @@ typedef struct smb_com_transaction_ioctl_req { __u8 IsRootFlag; /* 1 = apply command to root of share (must be DFS) */ __le16 ByteCount; __u8 Pad[3]; - __u8 Data[1]; + __u8 Data[]; } __attribute__((packed)) TRANSACT_IOCTL_REQ; typedef struct smb_com_transaction_compr_ioctl_req { @@ -1431,8 +1431,8 @@ typedef struct smb_com_transaction_change_notify_req { __u8 WatchTree; /* 1 = Monitor subdirectories */ __u8 Reserved2; __le16 ByteCount; -/* __u8 Pad[3];*/ -/* __u8 Data[1];*/ +/* __u8 Pad[3];*/ +/* __u8 Data[];*/ } __attribute__((packed)) TRANSACT_CHANGE_NOTIFY_REQ; /* BB eventually change to use generic ntransact rsp struct @@ -1521,7 +1521,7 @@ struct cifs_quota_data { __u64 space_used; __u64 soft_limit; __u64 hard_limit; - char sid[1]; /* variable size? */ + char sid[]; /* variable size? */ } __attribute__((packed)); /* quota sub commands */ @@ -1673,7 +1673,7 @@ typedef struct smb_com_transaction2_qpi_req { __u8 Pad; __le16 InformationLevel; __u32 Reserved4; - char FileName[1]; + char FileName[]; } __attribute__((packed)) TRANSACTION2_QPI_REQ; typedef struct smb_com_transaction2_qpi_rsp { @@ -1706,7 +1706,7 @@ typedef struct smb_com_transaction2_spi_req { __u16 Pad1; __le16 InformationLevel; __u32 Reserved4; - char FileName[1]; + char FileName[]; } __attribute__((packed)) TRANSACTION2_SPI_REQ; typedef struct smb_com_transaction2_spi_rsp { @@ -1813,7 +1813,7 @@ typedef struct smb_com_transaction2_ffirst_req { __le16 SearchFlags; __le16 InformationLevel; __le32 SearchStorageType; - char FileName[1]; + char FileName[]; } __attribute__((packed)) TRANSACTION2_FFIRST_REQ; typedef struct smb_com_transaction2_ffirst_rsp { @@ -2024,7 +2024,7 @@ typedef struct smb_com_transaction2_get_dfs_refer_req { perhaps?) followed by one byte pad - doesn't seem to matter though */ __le16 MaxReferralLevel; - char RequestFileName[1]; + char RequestFileName[]; } __attribute__((packed)) TRANSACTION2_GET_DFS_REFER_REQ; #define DFS_VERSION cpu_to_le16(0x0003) @@ -2053,7 +2053,7 @@ struct get_dfs_referral_rsp { __le16 PathConsumed; __le16 NumberOfReferrals; __le32 DFSFlags; - REFERRAL3 referrals[1]; /* array of level 3 dfs_referral structures */ + REFERRAL3 referrals[]; /* array of level 3 dfs_referral structures */ /* followed by the strings pointed to by the referral structures */ } __packed; @@ -2270,7 +2270,7 @@ typedef struct { /* QueryFileInfo/QueryPathinfo (also for SetPath/SetFile) data buffer formats */ /******************************************************************************/ typedef struct { /* data block encoding of response to level 263 QPathInfo */ - struct_group(common_attributes, + struct_group_attr(common_attributes, __packed, __le64 CreationTime; __le64 LastAccessTime; __le64 LastWriteTime; @@ -2292,7 +2292,10 @@ typedef struct { /* data block encoding of response to level 263 QPathInfo */ __le32 Mode; __le32 AlignmentRequirement; __le32 FileNameLength; - char FileName[1]; + union { + char __pad; + DECLARE_FLEX_ARRAY(char, FileName); + }; } __attribute__((packed)) FILE_ALL_INFO; /* level 0x107 QPathInfo */ typedef struct { @@ -2330,7 +2333,7 @@ typedef struct { } __attribute__((packed)) FILE_UNIX_BASIC_INFO; /* level 0x200 QPathInfo */ typedef struct { - char LinkDest[1]; + DECLARE_FLEX_ARRAY(char, LinkDest); } __attribute__((packed)) FILE_UNIX_LINK_INFO; /* level 0x201 QPathInfo */ /* The following three structures are needed only for @@ -2380,7 +2383,7 @@ struct file_end_of_file_info { } __attribute__((packed)); /* size info, level 0x104 for set, 0x106 for query */ struct file_alt_name_info { - __u8 alt_name[1]; + DECLARE_FLEX_ARRAY(__u8, alt_name); } __attribute__((packed)); /* level 0x0108 */ struct file_stream_info { @@ -2490,7 +2493,10 @@ typedef struct { __le32 NextEntryOffset; __u32 ResumeKey; /* as with FileIndex - no need to convert */ FILE_UNIX_BASIC_INFO basic; - char FileName[1]; + union { + char __pad; + DECLARE_FLEX_ARRAY(char, FileName); + }; } __attribute__((packed)) FILE_UNIX_INFO; /* level 0x202 */ typedef struct { @@ -2504,7 +2510,7 @@ typedef struct { __le64 AllocationSize; __le32 ExtFileAttributes; __le32 FileNameLength; - char FileName[1]; + char FileName[]; } __attribute__((packed)) FILE_DIRECTORY_INFO; /* level 0x101 FF resp data */ typedef struct { @@ -2519,7 +2525,7 @@ typedef struct { __le32 ExtFileAttributes; __le32 FileNameLength; __le32 EaSize; /* length of the xattrs */ - char FileName[1]; + char FileName[]; } __attribute__((packed)) FILE_FULL_DIRECTORY_INFO; /* level 0x102 rsp data */ typedef struct { @@ -2536,7 +2542,7 @@ typedef struct { __le32 EaSize; /* EA size */ __le32 Reserved; __le64 UniqueId; /* inode num - le since Samba puts ino in low 32 bit*/ - char FileName[1]; + char FileName[]; } __attribute__((packed)) SEARCH_ID_FULL_DIR_INFO; /* level 0x105 FF rsp data */ typedef struct { @@ -2554,7 +2560,7 @@ typedef struct { __u8 ShortNameLength; __u8 Reserved; __u8 ShortName[24]; - char FileName[1]; + char FileName[]; } __attribute__((packed)) FILE_BOTH_DIRECTORY_INFO; /* level 0x104 FFrsp data */ typedef struct { @@ -2569,7 +2575,7 @@ typedef struct { __le32 AllocationSize; __le16 Attributes; /* verify not u32 */ __u8 FileNameLength; - char FileName[1]; + char FileName[]; } __attribute__((packed)) FIND_FILE_STANDARD_INFO; /* level 0x1 FF resp data */ @@ -2579,16 +2585,6 @@ struct win_dev { __le64 minor; } __attribute__((packed)); -struct gea { - unsigned char name_len; - char name[1]; -} __attribute__((packed)); - -struct gealist { - unsigned long list_len; - struct gea list[1]; -} __attribute__((packed)); - struct fea { unsigned char EA_flags; __u8 name_len; diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 49fdc6dfdcf8d16e73a0e887edeaeb83fbf996e8..8c2a784200ec226baa47aa9195777489e8ce8262 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -216,6 +216,8 @@ cifs_signal_cifsd_for_reconnect(struct TCP_Server_Info *server, spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; spin_lock(&ses->chan_lock); for (i = 0; i < ses->chan_count; i++) { spin_lock(&ses->chans[i].server->srv_lock); diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c index e382b794acbed69eacadf101799a6a37982d0449..863c7bc3db86f842e220ddca6c7ff3cce1c21492 100644 --- a/fs/smb/client/dir.c +++ b/fs/smb/client/dir.c @@ -180,6 +180,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int disposition; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; + int rdwr_for_fscache = 0; *oplock = 0; if (tcon->ses->server->oplocks) @@ -191,6 +192,10 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned return PTR_ERR(full_path); } + /* If we're caching, we need to be able to fill in around partial writes. */ + if (cifs_fscache_enabled(inode) && (oflags & O_ACCMODE) == O_WRONLY) + rdwr_for_fscache = 1; + #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (tcon->unix_ext && cap_unix(tcon->ses) && !tcon->broken_posix_open && (CIFS_UNIX_POSIX_PATH_OPS_CAP & @@ -267,6 +272,8 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned desired_access |= GENERIC_READ; /* is this too little? */ if (OPEN_FMODE(oflags) & FMODE_WRITE) desired_access |= GENERIC_WRITE; + if (rdwr_for_fscache == 1) + desired_access |= GENERIC_READ; disposition = FILE_OVERWRITE_IF; if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) @@ -295,6 +302,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned if (!tcon->unix_ext && (mode & S_IWUGO) == 0) create_options |= CREATE_OPTION_READONLY; +retry_open: oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, @@ -308,8 +316,15 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned rc = server->ops->open(xid, &oparms, oplock, buf); if (rc) { cifs_dbg(FYI, "cifs_create returned 0x%x\n", rc); + if (rc == -EACCES && rdwr_for_fscache == 1) { + desired_access &= ~GENERIC_READ; + rdwr_for_fscache = 2; + goto retry_open; + } goto out; } + if (rdwr_for_fscache == 2) + cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE); #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY /* diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 0f3405e0f2e4853692af26c1f27950c61660ca4b..d23dfc83de507eb7076f4da291a0fbc2960981b4 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -77,12 +77,12 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon) */ } -static inline int cifs_convert_flags(unsigned int flags) +static inline int cifs_convert_flags(unsigned int flags, int rdwr_for_fscache) { if ((flags & O_ACCMODE) == O_RDONLY) return GENERIC_READ; else if ((flags & O_ACCMODE) == O_WRONLY) - return GENERIC_WRITE; + return rdwr_for_fscache == 1 ? (GENERIC_READ | GENERIC_WRITE) : GENERIC_WRITE; else if ((flags & O_ACCMODE) == O_RDWR) { /* GENERIC_ALL is too much permission to request can cause unnecessary access denied on create */ @@ -219,11 +219,16 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_ int create_options = CREATE_NOT_DIR; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; + int rdwr_for_fscache = 0; if (!server->ops->open) return -ENOSYS; - desired_access = cifs_convert_flags(f_flags); + /* If we're caching, we need to be able to fill in around partial writes. */ + if (cifs_fscache_enabled(inode) && (f_flags & O_ACCMODE) == O_WRONLY) + rdwr_for_fscache = 1; + + desired_access = cifs_convert_flags(f_flags, rdwr_for_fscache); /********************************************************************* * open flag mapping table: @@ -260,6 +265,7 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_ if (f_flags & O_DIRECT) create_options |= CREATE_NO_BUFFER; +retry_open: oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, @@ -271,8 +277,16 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_ }; rc = server->ops->open(xid, &oparms, oplock, buf); - if (rc) + if (rc) { + if (rc == -EACCES && rdwr_for_fscache == 1) { + desired_access = cifs_convert_flags(f_flags, 0); + rdwr_for_fscache = 2; + goto retry_open; + } return rc; + } + if (rdwr_for_fscache == 2) + cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE); /* TODO: Add support for calling posix query info but with passing in fid */ if (tcon->unix_ext) @@ -316,6 +330,7 @@ cifs_down_write(struct rw_semaphore *sem) } static void cifsFileInfo_put_work(struct work_struct *work); +void serverclose_work(struct work_struct *work); struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, struct tcon_link *tlink, __u32 oplock, @@ -362,6 +377,7 @@ struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, cfile->tlink = cifs_get_tlink(tlink); INIT_WORK(&cfile->oplock_break, cifs_oplock_break); INIT_WORK(&cfile->put, cifsFileInfo_put_work); + INIT_WORK(&cfile->serverclose, serverclose_work); INIT_DELAYED_WORK(&cfile->deferred, smb2_deferred_work_close); mutex_init(&cfile->fh_mutex); spin_lock_init(&cfile->file_info_lock); @@ -453,6 +469,40 @@ static void cifsFileInfo_put_work(struct work_struct *work) cifsFileInfo_put_final(cifs_file); } +void serverclose_work(struct work_struct *work) +{ + struct cifsFileInfo *cifs_file = container_of(work, + struct cifsFileInfo, serverclose); + + struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink); + + struct TCP_Server_Info *server = tcon->ses->server; + int rc = 0; + int retries = 0; + int MAX_RETRIES = 4; + + do { + if (server->ops->close_getattr) + rc = server->ops->close_getattr(0, tcon, cifs_file); + else if (server->ops->close) + rc = server->ops->close(0, tcon, &cifs_file->fid); + + if (rc == -EBUSY || rc == -EAGAIN) { + retries++; + msleep(250); + } + } while ((rc == -EBUSY || rc == -EAGAIN) && (retries < MAX_RETRIES) + ); + + if (retries == MAX_RETRIES) + pr_warn("Serverclose failed %d times, giving up\n", MAX_RETRIES); + + if (cifs_file->offload) + queue_work(fileinfo_put_wq, &cifs_file->put); + else + cifsFileInfo_put_final(cifs_file); +} + /** * cifsFileInfo_put - release a reference of file priv data * @@ -493,10 +543,13 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, struct cifs_fid fid = {}; struct cifs_pending_open open; bool oplock_break_cancelled; + bool serverclose_offloaded = false; spin_lock(&tcon->open_file_lock); spin_lock(&cifsi->open_file_lock); spin_lock(&cifs_file->file_info_lock); + + cifs_file->offload = offload; if (--cifs_file->count > 0) { spin_unlock(&cifs_file->file_info_lock); spin_unlock(&cifsi->open_file_lock); @@ -538,13 +591,20 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, if (!tcon->need_reconnect && !cifs_file->invalidHandle) { struct TCP_Server_Info *server = tcon->ses->server; unsigned int xid; + int rc = 0; xid = get_xid(); if (server->ops->close_getattr) - server->ops->close_getattr(xid, tcon, cifs_file); + rc = server->ops->close_getattr(xid, tcon, cifs_file); else if (server->ops->close) - server->ops->close(xid, tcon, &cifs_file->fid); + rc = server->ops->close(xid, tcon, &cifs_file->fid); _free_xid(xid); + + if (rc == -EBUSY || rc == -EAGAIN) { + // Server close failed, hence offloading it as an async op + queue_work(serverclose_wq, &cifs_file->serverclose); + serverclose_offloaded = true; + } } if (oplock_break_cancelled) @@ -552,10 +612,15 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, cifs_del_pending_open(&open); - if (offload) - queue_work(fileinfo_put_wq, &cifs_file->put); - else - cifsFileInfo_put_final(cifs_file); + // if serverclose has been offloaded to wq (on failure), it will + // handle offloading put as well. If serverclose not offloaded, + // we need to handle offloading put here. + if (!serverclose_offloaded) { + if (offload) + queue_work(fileinfo_put_wq, &cifs_file->put); + else + cifsFileInfo_put_final(cifs_file); + } } int cifs_open(struct inode *inode, struct file *file) @@ -705,11 +770,11 @@ int cifs_open(struct inode *inode, struct file *file) use_cache: fscache_use_cookie(cifs_inode_cookie(file_inode(file)), file->f_mode & FMODE_WRITE); - if (file->f_flags & O_DIRECT && - (!((file->f_flags & O_ACCMODE) != O_RDONLY) || - file->f_flags & O_APPEND)) - cifs_invalidate_cache(file_inode(file), - FSCACHE_INVAL_DIO_WRITE); + if (!(file->f_flags & O_DIRECT)) + goto out; + if ((file->f_flags & (O_ACCMODE | O_APPEND)) == O_RDONLY) + goto out; + cifs_invalidate_cache(file_inode(file), FSCACHE_INVAL_DIO_WRITE); out: free_dentry_path(page); @@ -774,6 +839,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) int disposition = FILE_OPEN; int create_options = CREATE_NOT_DIR; struct cifs_open_parms oparms; + int rdwr_for_fscache = 0; xid = get_xid(); mutex_lock(&cfile->fh_mutex); @@ -837,7 +903,11 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) } #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ - desired_access = cifs_convert_flags(cfile->f_flags); + /* If we're caching, we need to be able to fill in around partial writes. */ + if (cifs_fscache_enabled(inode) && (cfile->f_flags & O_ACCMODE) == O_WRONLY) + rdwr_for_fscache = 1; + + desired_access = cifs_convert_flags(cfile->f_flags, rdwr_for_fscache); /* O_SYNC also has bit for O_DSYNC so following check picks up either */ if (cfile->f_flags & O_SYNC) @@ -849,6 +919,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) if (server->ops->get_lease_key) server->ops->get_lease_key(inode, &cfile->fid); +retry_open: oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, @@ -874,6 +945,11 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) /* indicate that we need to relock the file */ oparms.reconnect = true; } + if (rc == -EACCES && rdwr_for_fscache == 1) { + desired_access = cifs_convert_flags(cfile->f_flags, 0); + rdwr_for_fscache = 2; + goto retry_open; + } if (rc) { mutex_unlock(&cfile->fh_mutex); @@ -882,6 +958,9 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) goto reopen_error_exit; } + if (rdwr_for_fscache == 2) + cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE); + #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY reopen_success: #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index f4818599c00a26c270021d46ce1048f7dc2db05e..ca39d01077cdf5c67362327bba34729e3c3a8da4 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -209,7 +209,7 @@ cifs_parse_security_flavors(struct fs_context *fc, char *value, struct smb3_fs_c switch (match_token(value, cifs_secflavor_tokens, args)) { case Opt_sec_krb5p: - cifs_errorf(fc, "sec=krb5p is not supported!\n"); + cifs_errorf(fc, "sec=krb5p is not supported. Use sec=krb5,seal instead\n"); return 1; case Opt_sec_krb5i: ctx->sign = true; @@ -676,6 +676,16 @@ static int smb3_fs_context_validate(struct fs_context *fc) /* set the port that we got earlier */ cifs_set_port((struct sockaddr *)&ctx->dstaddr, ctx->port); + if (ctx->uid_specified && !ctx->forceuid_specified) { + ctx->override_uid = 1; + pr_notice("enabling forceuid mount option implicitly because uid= option is specified\n"); + } + + if (ctx->gid_specified && !ctx->forcegid_specified) { + ctx->override_gid = 1; + pr_notice("enabling forcegid mount option implicitly because gid= option is specified\n"); + } + if (ctx->override_uid && !ctx->uid_specified) { ctx->override_uid = 0; pr_notice("ignoring forceuid mount option specified with no uid= option\n"); @@ -923,12 +933,14 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, ctx->override_uid = 0; else ctx->override_uid = 1; + ctx->forceuid_specified = true; break; case Opt_forcegid: if (result.negated) ctx->override_gid = 0; else ctx->override_gid = 1; + ctx->forcegid_specified = true; break; case Opt_perm: if (result.negated) diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h index 26093f54d3e657bad772b66c61962b89c5196734..319a91b7f67005da59577341865fcc2a3b1ee8b8 100644 --- a/fs/smb/client/fs_context.h +++ b/fs/smb/client/fs_context.h @@ -154,6 +154,8 @@ enum cifs_param { }; struct smb3_fs_context { + bool forceuid_specified; + bool forcegid_specified; bool uid_specified; bool cruid_specified; bool gid_specified; diff --git a/fs/smb/client/fscache.c b/fs/smb/client/fscache.c index f64bad513ba6d7ece76302fa89e75735268dab61..6df4ab2a6e5dc4844a3c217be1c123ff019d90f1 100644 --- a/fs/smb/client/fscache.c +++ b/fs/smb/client/fscache.c @@ -12,6 +12,16 @@ #include "cifs_fs_sb.h" #include "cifsproto.h" +/* + * Key for fscache inode. [!] Contents must match comparisons in cifs_find_inode(). + */ +struct cifs_fscache_inode_key { + + __le64 uniqueid; /* server inode number */ + __le64 createtime; /* creation time on server */ + u8 type; /* S_IFMT file type */ +} __packed; + static void cifs_fscache_fill_volume_coherency( struct cifs_tcon *tcon, struct cifs_fscache_volume_coherency_data *cd) @@ -97,15 +107,19 @@ void cifs_fscache_release_super_cookie(struct cifs_tcon *tcon) void cifs_fscache_get_inode_cookie(struct inode *inode) { struct cifs_fscache_inode_coherency_data cd; + struct cifs_fscache_inode_key key; struct cifsInodeInfo *cifsi = CIFS_I(inode); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); + key.uniqueid = cpu_to_le64(cifsi->uniqueid); + key.createtime = cpu_to_le64(cifsi->createtime); + key.type = (inode->i_mode & S_IFMT) >> 12; cifs_fscache_fill_coherency(&cifsi->netfs.inode, &cd); cifsi->netfs.cache = fscache_acquire_cookie(tcon->fscache, 0, - &cifsi->uniqueid, sizeof(cifsi->uniqueid), + &key, sizeof(key), &cd, sizeof(cd), i_size_read(&cifsi->netfs.inode)); if (cifsi->netfs.cache) diff --git a/fs/smb/client/fscache.h b/fs/smb/client/fscache.h index 67b601041f0a3701a5bdcf5e8f227071dc7478c9..c691b98b442a6d878c9ff5bfa9859b55f9220990 100644 --- a/fs/smb/client/fscache.h +++ b/fs/smb/client/fscache.h @@ -108,6 +108,11 @@ static inline void cifs_readpage_to_fscache(struct inode *inode, __cifs_readpage_to_fscache(inode, page); } +static inline bool cifs_fscache_enabled(struct inode *inode) +{ + return fscache_cookie_enabled(cifs_inode_cookie(inode)); +} + #else /* CONFIG_CIFS_FSCACHE */ static inline void cifs_fscache_fill_coherency(struct inode *inode, @@ -123,6 +128,7 @@ static inline void cifs_fscache_release_inode_cookie(struct inode *inode) {} static inline void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool update) {} static inline struct fscache_cookie *cifs_inode_cookie(struct inode *inode) { return NULL; } static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags) {} +static inline bool cifs_fscache_enabled(struct inode *inode) { return false; } static inline int cifs_fscache_query_occupancy(struct inode *inode, pgoff_t first, unsigned int nr_pages, diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 5343898bac8a679d151689d7b45286d3ac53136c..634f28f0d331eae53f9fc5328d5cafa0fc824c52 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -1274,6 +1274,8 @@ cifs_find_inode(struct inode *inode, void *opaque) { struct cifs_fattr *fattr = opaque; + /* [!] The compared values must be the same in struct cifs_fscache_inode_key. */ + /* don't match inode with different uniqueid */ if (CIFS_I(inode)->uniqueid != fattr->cf_uniqueid) return 0; diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index 41290c12d0bcc0bd293912bbd8f01d893e58c369..3826f71766086e067f3037e39ae2c078253f6b6e 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -476,6 +476,8 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->tid != buf->Tid) continue; diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index 2d75ba5aaa8adfedc432230e1102bd1561db7d4f..9a1f1913fb592ef52e13cef1e1cf40cbca9106bb 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -304,14 +304,16 @@ cifs_dir_info_to_fattr(struct cifs_fattr *fattr, FILE_DIRECTORY_INFO *info, } static void cifs_fulldir_info_to_fattr(struct cifs_fattr *fattr, - SEARCH_ID_FULL_DIR_INFO *info, + const void *info, struct cifs_sb_info *cifs_sb) { + const FILE_FULL_DIRECTORY_INFO *di = info; + __dir_info_to_fattr(fattr, info); - /* See MS-FSCC 2.4.19 FileIdFullDirectoryInformation */ + /* See MS-FSCC 2.4.14, 2.4.19 */ if (fattr->cf_cifsattrs & ATTR_REPARSE) - fattr->cf_cifstag = le32_to_cpu(info->EaSize); + fattr->cf_cifstag = le32_to_cpu(di->EaSize); cifs_fill_common_info(fattr, cifs_sb); } @@ -425,7 +427,7 @@ ffirst_retry: } else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) { cifsFile->srch_inf.info_level = SMB_FIND_FILE_ID_FULL_DIR_INFO; } else /* not srvinos - BB fixme add check for backlevel? */ { - cifsFile->srch_inf.info_level = SMB_FIND_FILE_DIRECTORY_INFO; + cifsFile->srch_inf.info_level = SMB_FIND_FILE_FULL_DIRECTORY_INFO; } search_flags = CIFS_SEARCH_CLOSE_AT_END | CIFS_SEARCH_RETURN_RESUME; @@ -495,7 +497,7 @@ static char *nxt_dir_entry(char *old_entry, char *end_of_smb, int level) FIND_FILE_STANDARD_INFO *pfData; pfData = (FIND_FILE_STANDARD_INFO *)pDirInfo; - new_entry = old_entry + sizeof(FIND_FILE_STANDARD_INFO) + + new_entry = old_entry + sizeof(FIND_FILE_STANDARD_INFO) + 1 + pfData->FileNameLength; } else { u32 next_offset = le32_to_cpu(pDirInfo->NextEntryOffset); @@ -513,9 +515,9 @@ static char *nxt_dir_entry(char *old_entry, char *end_of_smb, int level) new_entry, end_of_smb, old_entry); return NULL; } else if (((level == SMB_FIND_FILE_INFO_STANDARD) && - (new_entry + sizeof(FIND_FILE_STANDARD_INFO) > end_of_smb)) + (new_entry + sizeof(FIND_FILE_STANDARD_INFO) + 1 > end_of_smb)) || ((level != SMB_FIND_FILE_INFO_STANDARD) && - (new_entry + sizeof(FILE_DIRECTORY_INFO) > end_of_smb))) { + (new_entry + sizeof(FILE_DIRECTORY_INFO) + 1 > end_of_smb))) { cifs_dbg(VFS, "search entry %p extends after end of SMB %p\n", new_entry, end_of_smb); return NULL; @@ -1019,10 +1021,9 @@ static int cifs_filldir(char *find_entry, struct file *file, (FIND_FILE_STANDARD_INFO *)find_entry, cifs_sb); break; + case SMB_FIND_FILE_FULL_DIRECTORY_INFO: case SMB_FIND_FILE_ID_FULL_DIR_INFO: - cifs_fulldir_info_to_fattr(&fattr, - (SEARCH_ID_FULL_DIR_INFO *)find_entry, - cifs_sb); + cifs_fulldir_info_to_fattr(&fattr, find_entry, cifs_sb); break; default: cifs_dir_info_to_fattr(&fattr, diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index 634035bcb9347ffd264dbdfdb60e45748f726fd3..b8e14bcd2c68d7b0a0617ecd82ff7d5230fe0e29 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -248,6 +248,8 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses) &iface->sockaddr, rc); kref_put(&iface->refcount, release_iface); + /* failure to add chan should increase weight */ + iface->weight_fulfilled++; continue; } diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index 7d1b3fc014d94ac9dd1c9364c99e7e4a4b363359..d4045925f857740625f51f407ed680487397d5da 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -750,11 +750,11 @@ cifs_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock) cinode->can_cache_brlcks = CIFS_CACHE_WRITE(cinode); } -static void +static int cifs_close_file(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *fid) { - CIFSSMBClose(xid, tcon, fid->netfid); + return CIFSSMBClose(xid, tcon, fid->netfid); } static int diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index 15fa022e79993d2e998fe643a6e8ef3ec4db5518..8c149cb531d3f0745f6de646c15dd2fa1120aa2c 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -622,6 +622,8 @@ smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); cifs_stats_inc( @@ -697,6 +699,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 5a157000bdfe6312e6150e375d21f2cdcdf5f453..2291081653a85ef7385d3b4556701af10d5f6ecb 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -613,7 +613,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, goto out; } - while (bytes_left >= sizeof(*p)) { + while (bytes_left >= (ssize_t)sizeof(*p)) { memset(&tmp_iface, 0, sizeof(tmp_iface)); tmp_iface.speed = le64_to_cpu(p->LinkSpeed); tmp_iface.rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE) ? 1 : 0; @@ -1392,14 +1392,14 @@ smb2_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock) memcpy(cfile->fid.create_guid, fid->create_guid, 16); } -static void +static int smb2_close_file(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *fid) { - SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid); + return SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid); } -static void +static int smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon, struct cifsFileInfo *cfile) { @@ -1410,7 +1410,7 @@ smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon, rc = __SMB2_close(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, &file_inf); if (rc) - return; + return rc; inode = d_inode(cfile->dentry); @@ -1436,6 +1436,7 @@ smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon, /* End of file and Attributes should not have to be updated on close */ spin_unlock(&inode->i_lock); + return rc; } static int @@ -2436,6 +2437,8 @@ smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->tid == le32_to_cpu(shdr->Id.SyncId.TreeId)) { spin_lock(&tcon->tc_lock); diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index e65f998ea4cfc78c46b3a0021045e199ffee60c6..e15bf116c75583d402346a2b600d00b88761c660 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -2145,17 +2145,18 @@ parse_posix_ctxt(struct create_context *cc, struct smb2_file_all_info *info, posix->nlink, posix->mode, posix->reparse_tag); } -void -smb2_parse_contexts(struct TCP_Server_Info *server, - struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key, __u8 *oplock, - struct smb2_file_all_info *buf, - struct create_posix_rsp *posix) +int smb2_parse_contexts(struct TCP_Server_Info *server, + struct kvec *rsp_iov, + unsigned int *epoch, + char *lease_key, __u8 *oplock, + struct smb2_file_all_info *buf, + struct create_posix_rsp *posix) { - char *data_offset; + struct smb2_create_rsp *rsp = rsp_iov->iov_base; struct create_context *cc; - unsigned int next; - unsigned int remaining; + size_t rem, off, len; + size_t doff, dlen; + size_t noff, nlen; char *name; static const char smb3_create_tag_posix[] = { 0x93, 0xAD, 0x25, 0x50, 0x9C, @@ -2164,45 +2165,63 @@ smb2_parse_contexts(struct TCP_Server_Info *server, }; *oplock = 0; - data_offset = (char *)rsp + le32_to_cpu(rsp->CreateContextsOffset); - remaining = le32_to_cpu(rsp->CreateContextsLength); - cc = (struct create_context *)data_offset; + + off = le32_to_cpu(rsp->CreateContextsOffset); + rem = le32_to_cpu(rsp->CreateContextsLength); + if (check_add_overflow(off, rem, &len) || len > rsp_iov->iov_len) + return -EINVAL; + cc = (struct create_context *)((u8 *)rsp + off); /* Initialize inode number to 0 in case no valid data in qfid context */ if (buf) buf->IndexNumber = 0; - while (remaining >= sizeof(struct create_context)) { - name = le16_to_cpu(cc->NameOffset) + (char *)cc; - if (le16_to_cpu(cc->NameLength) == 4 && - strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4) == 0) - *oplock = server->ops->parse_lease_buf(cc, epoch, - lease_key); - else if (buf && (le16_to_cpu(cc->NameLength) == 4) && - strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4) == 0) - parse_query_id_ctxt(cc, buf); - else if ((le16_to_cpu(cc->NameLength) == 16)) { - if (posix && - memcmp(name, smb3_create_tag_posix, 16) == 0) + while (rem >= sizeof(*cc)) { + doff = le16_to_cpu(cc->DataOffset); + dlen = le32_to_cpu(cc->DataLength); + if (check_add_overflow(doff, dlen, &len) || len > rem) + return -EINVAL; + + noff = le16_to_cpu(cc->NameOffset); + nlen = le16_to_cpu(cc->NameLength); + if (noff + nlen > doff) + return -EINVAL; + + name = (char *)cc + noff; + switch (nlen) { + case 4: + if (!strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4)) { + *oplock = server->ops->parse_lease_buf(cc, epoch, + lease_key); + } else if (buf && + !strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4)) { + parse_query_id_ctxt(cc, buf); + } + break; + case 16: + if (posix && !memcmp(name, smb3_create_tag_posix, 16)) parse_posix_ctxt(cc, buf, posix); + break; + default: + cifs_dbg(FYI, "%s: unhandled context (nlen=%zu dlen=%zu)\n", + __func__, nlen, dlen); + if (IS_ENABLED(CONFIG_CIFS_DEBUG2)) + cifs_dump_mem("context data: ", cc, dlen); + break; } - /* else { - cifs_dbg(FYI, "Context not matched with len %d\n", - le16_to_cpu(cc->NameLength)); - cifs_dump_mem("Cctxt name: ", name, 4); - } */ - - next = le32_to_cpu(cc->Next); - if (!next) + + off = le32_to_cpu(cc->Next); + if (!off) break; - remaining -= next; - cc = (struct create_context *)((char *)cc + next); + if (check_sub_overflow(rem, off, &rem)) + return -EINVAL; + cc = (struct create_context *)((u8 *)cc + off); } if (rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) *oplock = rsp->OplockLevel; - return; + return 0; } static int @@ -3082,8 +3101,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, } - smb2_parse_contexts(server, rsp, &oparms->fid->epoch, - oparms->fid->lease_key, oplock, buf, posix); + rc = smb2_parse_contexts(server, &rsp_iov, &oparms->fid->epoch, + oparms->fid->lease_key, oplock, buf, posix); creat_exit: SMB2_open_free(&rqst); free_rsp_buf(resp_buftype, rsp); @@ -3433,9 +3452,9 @@ __SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, memcpy(&pbuf->network_open_info, &rsp->network_open_info, sizeof(pbuf->network_open_info)); + atomic_dec(&tcon->num_remote_opens); } - atomic_dec(&tcon->num_remote_opens); close_exit: SMB2_close_free(&rqst); free_rsp_buf(resp_buftype, rsp); @@ -4991,6 +5010,9 @@ int SMB2_query_directory_init(const unsigned int xid, case SMB_FIND_FILE_POSIX_INFO: req->FileInformationClass = SMB_FIND_FILE_POSIX_INFO; break; + case SMB_FIND_FILE_FULL_DIRECTORY_INFO: + req->FileInformationClass = FILE_FULL_DIRECTORY_INFORMATION; + break; default: cifs_tcon_dbg(VFS, "info level %u isn't supported\n", info_level); @@ -5051,15 +5073,18 @@ smb2_parse_query_directory(struct cifs_tcon *tcon, switch (srch_inf->info_level) { case SMB_FIND_FILE_DIRECTORY_INFO: - info_buf_size = sizeof(FILE_DIRECTORY_INFO) - 1; + info_buf_size = sizeof(FILE_DIRECTORY_INFO); break; case SMB_FIND_FILE_ID_FULL_DIR_INFO: - info_buf_size = sizeof(SEARCH_ID_FULL_DIR_INFO) - 1; + info_buf_size = sizeof(SEARCH_ID_FULL_DIR_INFO); break; case SMB_FIND_FILE_POSIX_INFO: /* note that posix payload are variable size */ info_buf_size = sizeof(struct smb2_posix_info); break; + case SMB_FIND_FILE_FULL_DIRECTORY_INFO: + info_buf_size = sizeof(FILE_FULL_DIRECTORY_INFO); + break; default: cifs_tcon_dbg(VFS, "info level %u isn't supported\n", srch_inf->info_level); diff --git a/fs/smb/client/smb2pdu.h b/fs/smb/client/smb2pdu.h index 8d011fedecd03eb1e0d320a23974075182bed7cc..2823526b66f7e9f9268d5f5415a4dd35ee7d8154 100644 --- a/fs/smb/client/smb2pdu.h +++ b/fs/smb/client/smb2pdu.h @@ -339,7 +339,7 @@ struct smb2_file_reparse_point_info { } __packed; struct smb2_file_network_open_info { - struct_group(network_open_info, + struct_group_attr(network_open_info, __packed, __le64 CreationTime; __le64 LastAccessTime; __le64 LastWriteTime; @@ -373,7 +373,7 @@ struct smb2_file_id_extd_directory_info { __le32 EaSize; /* EA size */ __le32 ReparsePointTag; /* valid if FILE_ATTR_REPARSE_POINT set in FileAttributes */ __le64 UniqueId; /* inode num - le since Samba puts ino in low 32 bit */ - char FileName[1]; + char FileName[]; } __packed; /* level 60 */ extern char smb2_padding[7]; diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h index be21b5d26f67efa9f4f3130d9f94efb542b4629f..b325fde010adc102e89ff07b86e4c24281e30d79 100644 --- a/fs/smb/client/smb2proto.h +++ b/fs/smb/client/smb2proto.h @@ -249,11 +249,13 @@ extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *); extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *, enum securityEnum); -extern void smb2_parse_contexts(struct TCP_Server_Info *server, - struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key, - __u8 *oplock, struct smb2_file_all_info *buf, - struct create_posix_rsp *posix); +int smb2_parse_contexts(struct TCP_Server_Info *server, + struct kvec *rsp_iov, + unsigned int *epoch, + char *lease_key, __u8 *oplock, + struct smb2_file_all_info *buf, + struct create_posix_rsp *posix); + extern int smb3_encryption_required(const struct cifs_tcon *tcon); extern int smb2_validate_iov(unsigned int offset, unsigned int buffer_length, struct kvec *iov, unsigned int min_buf_size); diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index 8a1dd8407a3a752132b7b9de2676601d5cdeed97..3fdafb9297f13471a59b833015e7aba1303ac524 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -427,10 +427,17 @@ unmask: server->conn_id, server->hostname); } smbd_done: - if (rc < 0 && rc != -EINTR) + /* + * there's hardly any use for the layers above to know the + * actual error code here. All they should do at this point is + * to retry the connection and hope it goes away. + */ + if (rc < 0 && rc != -EINTR && rc != -EAGAIN) { cifs_server_dbg(VFS, "Error %d sending data on socket to server\n", rc); - else if (rc > 0) + rc = -ECONNABORTED; + cifs_signal_cifsd_for_reconnect(server, false); + } else if (rc > 0) rc = 0; out: cifs_in_send_dec(server); @@ -449,8 +456,8 @@ smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, if (!(flags & CIFS_TRANSFORM_REQ)) return __smb_send_rqst(server, num_rqst, rqst); - if (num_rqst > MAX_COMPOUND - 1) - return -ENOMEM; + if (WARN_ON_ONCE(num_rqst > MAX_COMPOUND - 1)) + return -EIO; if (!server->ops->init_transform_rq) { cifs_server_dbg(VFS, "Encryption requested but transform callback is missing\n"); @@ -924,12 +931,15 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server) list_del_init(&mid->qhead); mid->mid_flags |= MID_DELETED; } + spin_unlock(&server->mid_lock); cifs_server_dbg(VFS, "%s: invalid mid state mid=%llu state=%d\n", __func__, mid->mid, mid->mid_state); rc = -EIO; + goto sync_mid_done; } spin_unlock(&server->mid_lock); +sync_mid_done: release_mid(mid); return rc; } @@ -1035,18 +1045,45 @@ cifs_cancelled_callback(struct mid_q_entry *mid) struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses) { uint index = 0; + unsigned int min_in_flight = UINT_MAX, max_in_flight = 0; + struct TCP_Server_Info *server = NULL; + int i; if (!ses) return NULL; - /* round robin */ - index = (uint)atomic_inc_return(&ses->chan_seq); - spin_lock(&ses->chan_lock); - index %= ses->chan_count; + for (i = 0; i < ses->chan_count; i++) { + server = ses->chans[i].server; + if (!server) + continue; + + /* + * strictly speaking, we should pick up req_lock to read + * server->in_flight. But it shouldn't matter much here if we + * race while reading this data. The worst that can happen is + * that we could use a channel that's not least loaded. Avoiding + * taking the lock could help reduce wait time, which is + * important for this function + */ + if (server->in_flight < min_in_flight) { + min_in_flight = server->in_flight; + index = i; + } + if (server->in_flight > max_in_flight) + max_in_flight = server->in_flight; + } + + /* if all channels are equally loaded, fall back to round-robin */ + if (min_in_flight == max_in_flight) { + index = (uint)atomic_inc_return(&ses->chan_seq); + index %= ses->chan_count; + } + + server = ses->chans[index].server; spin_unlock(&ses->chan_lock); - return ses->chans[index].server; + return server; } int diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index a3936ff53d9d04727968e582063771b31666eb20..25383b11d01b9acb2f817046908d869fd43bbae9 100644 --- a/fs/smb/common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h @@ -699,7 +699,7 @@ struct smb2_close_rsp { __le16 StructureSize; /* 60 */ __le16 Flags; __le32 Reserved; - struct_group(network_open_info, + struct_group_attr(network_open_info, __packed, __le64 CreationTime; __le64 LastAccessTime; __le64 LastWriteTime; diff --git a/fs/smb/server/ksmbd_netlink.h b/fs/smb/server/ksmbd_netlink.h index 0ebf91ffa2361c0940aba0fc301d1a65bf1612e5..4464a62228cf335855fd733aebd7e47ea5266f4d 100644 --- a/fs/smb/server/ksmbd_netlink.h +++ b/fs/smb/server/ksmbd_netlink.h @@ -166,7 +166,8 @@ struct ksmbd_share_config_response { __u16 force_uid; __u16 force_gid; __s8 share_name[KSMBD_REQ_MAX_SHARE_NAME]; - __u32 reserved[112]; /* Reserved room */ + __u32 reserved[111]; /* Reserved room */ + __u32 payload_sz; __u32 veto_list_sz; __s8 ____payload[]; }; diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c index 328a412259dc1b935eb2ce3eee2977d39155157b..a2f0a2edceb8ae49852dde1b40cf7594df6084d9 100644 --- a/fs/smb/server/mgmt/share_config.c +++ b/fs/smb/server/mgmt/share_config.c @@ -158,7 +158,12 @@ static struct ksmbd_share_config *share_config_request(struct unicode_map *um, share->name = kstrdup(name, GFP_KERNEL); if (!test_share_config_flag(share, KSMBD_SHARE_FLAG_PIPE)) { - share->path = kstrdup(ksmbd_share_config_path(resp), + int path_len = PATH_MAX; + + if (resp->payload_sz) + path_len = resp->payload_sz - resp->veto_list_sz; + + share->path = kstrndup(ksmbd_share_config_path(resp), path_len, GFP_KERNEL); if (share->path) share->path_sz = strlen(share->path); diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 1253e9bde34c88ca0a261dc65b09f3fd7a6e3957..1b98796499d783f562a56464f9c2e2f8628c7789 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -612,13 +612,23 @@ static int oplock_break_pending(struct oplock_info *opinfo, int req_op_level) if (opinfo->op_state == OPLOCK_CLOSING) return -ENOENT; - else if (!opinfo->is_lease && opinfo->level <= req_op_level) - return 1; + else if (opinfo->level <= req_op_level) { + if (opinfo->is_lease && + opinfo->o_lease->state != + (SMB2_LEASE_HANDLE_CACHING_LE | + SMB2_LEASE_READ_CACHING_LE)) + return 1; + } } - if (!opinfo->is_lease && opinfo->level <= req_op_level) { - wake_up_oplock_break(opinfo); - return 1; + if (opinfo->level <= req_op_level) { + if (opinfo->is_lease && + opinfo->o_lease->state != + (SMB2_LEASE_HANDLE_CACHING_LE | + SMB2_LEASE_READ_CACHING_LE)) { + wake_up_oplock_break(opinfo); + return 1; + } } return 0; } @@ -886,7 +896,6 @@ static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level) struct lease *lease = brk_opinfo->o_lease; atomic_inc(&brk_opinfo->breaking_cnt); - err = oplock_break_pending(brk_opinfo, req_op_level); if (err) return err < 0 ? err : 0; @@ -1199,7 +1208,9 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, /* Only v2 leases handle the directory */ if (S_ISDIR(file_inode(fp->filp)->i_mode)) { - if (!lctx || lctx->version != 2) + if (!lctx || lctx->version != 2 || + (lctx->flags != SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE && + !lctx->epoch)) return 0; } @@ -1461,8 +1472,9 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) buf->lcontext.LeaseFlags = lease->flags; buf->lcontext.Epoch = cpu_to_le16(lease->epoch); buf->lcontext.LeaseState = lease->state; - memcpy(buf->lcontext.ParentLeaseKey, lease->parent_lease_key, - SMB2_LEASE_KEY_SIZE); + if (lease->flags == SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE) + memcpy(buf->lcontext.ParentLeaseKey, lease->parent_lease_key, + SMB2_LEASE_KEY_SIZE); buf->ccontext.DataOffset = cpu_to_le16(offsetof (struct create_lease_v2, lcontext)); buf->ccontext.DataLength = cpu_to_le32(sizeof(struct lease_context_v2)); @@ -1527,8 +1539,9 @@ struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir) lreq->flags = lc->lcontext.LeaseFlags; lreq->epoch = lc->lcontext.Epoch; lreq->duration = lc->lcontext.LeaseDuration; - memcpy(lreq->parent_lease_key, lc->lcontext.ParentLeaseKey, - SMB2_LEASE_KEY_SIZE); + if (lreq->flags == SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE) + memcpy(lreq->parent_lease_key, lc->lcontext.ParentLeaseKey, + SMB2_LEASE_KEY_SIZE); lreq->version = 2; } else { struct create_lease *lc = (struct create_lease *)cc; diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 11b201e6ee44bed7fb598667b06ce2b96ee4f37f..63b01f7d97031f60a1c7842ccd5159bf918d7e80 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -167,20 +167,17 @@ static void __handle_ksmbd_work(struct ksmbd_work *work, int rc; bool is_chained = false; - if (conn->ops->allocate_rsp_buf(work)) - return; - if (conn->ops->is_transform_hdr && conn->ops->is_transform_hdr(work->request_buf)) { rc = conn->ops->decrypt_req(work); - if (rc < 0) { - conn->ops->set_rsp_status(work, STATUS_DATA_ERROR); - goto send; - } - + if (rc < 0) + return; work->encrypted = true; } + if (conn->ops->allocate_rsp_buf(work)) + return; + rc = conn->ops->init_rsp_hdr(work); if (rc) { /* either uid or tid is not correct */ diff --git a/fs/smb/server/smb2ops.c b/fs/smb/server/smb2ops.c index 27a9dce3e03abe4673ac7241aa828943d22754d8..8600f32c981a1ac8ac53e3ea9152617a89f4c7e5 100644 --- a/fs/smb/server/smb2ops.c +++ b/fs/smb/server/smb2ops.c @@ -228,6 +228,11 @@ void init_smb3_0_server(struct ksmbd_conn *conn) conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION) conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; + if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION || + (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) && + conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION)) + conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; + if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL; } @@ -275,11 +280,6 @@ int init_smb3_11_server(struct ksmbd_conn *conn) conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_DIRECTORY_LEASING; - if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION || - (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) && - conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION)) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; - if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 4cfa45c2727ea0bc0ea397d1f863fcc4618811c4..34d88425434ab467cd17dbcd1436d76ac7459b6f 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -534,6 +534,10 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work) if (cmd == SMB2_QUERY_INFO_HE) { struct smb2_query_info_req *req; + if (get_rfc1002_len(work->request_buf) < + offsetof(struct smb2_query_info_req, OutputBufferLength)) + return -EINVAL; + req = smb2_get_msg(work->request_buf); if ((req->InfoType == SMB2_O_INFO_FILE && (req->FileInfoClass == FILE_FULL_EA_INFORMATION || @@ -5579,8 +5583,9 @@ static int smb2_rename(struct ksmbd_work *work, if (!file_info->ReplaceIfExists) flags = RENAME_NOREPLACE; - smb_break_all_levII_oplock(work, fp, 0); rc = ksmbd_vfs_rename(work, &fp->filp->f_path, new_name, flags); + if (!rc) + smb_break_all_levII_oplock(work, fp, 0); out: kfree(new_name); return rc; @@ -5757,15 +5762,21 @@ static int set_file_allocation_info(struct ksmbd_work *work, loff_t alloc_blks; struct inode *inode; + struct kstat stat; int rc; if (!(fp->daccess & FILE_WRITE_DATA_LE)) return -EACCES; + rc = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (rc) + return rc; + alloc_blks = (le64_to_cpu(file_alloc_info->AllocationSize) + 511) >> 9; inode = file_inode(fp->filp); - if (alloc_blks > inode->i_blocks) { + if (alloc_blks > stat.blocks) { smb_break_all_levII_oplock(work, fp, 1); rc = vfs_fallocate(fp->filp, FALLOC_FL_KEEP_SIZE, 0, alloc_blks * 512); @@ -5773,7 +5784,7 @@ static int set_file_allocation_info(struct ksmbd_work *work, pr_err("vfs_fallocate is failed : %d\n", rc); return rc; } - } else if (alloc_blks < inode->i_blocks) { + } else if (alloc_blks < stat.blocks) { loff_t size; /* @@ -6171,8 +6182,10 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work) err = ksmbd_iov_pin_rsp_read(work, (void *)rsp, offsetof(struct smb2_read_rsp, Buffer), aux_payload_buf, nbytes); - if (err) + if (err) { + kvfree(aux_payload_buf); goto out; + } kvfree(rpc_resp); } else { err = ksmbd_iov_pin_rsp(work, (void *)rsp, @@ -6382,8 +6395,10 @@ int smb2_read(struct ksmbd_work *work) err = ksmbd_iov_pin_rsp_read(work, (void *)rsp, offsetof(struct smb2_read_rsp, Buffer), aux_payload_buf, nbytes); - if (err) + if (err) { + kvfree(aux_payload_buf); goto out; + } ksmbd_fd_put(work, fp); return 0; diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index f29bb03f0dc47bfcb0fe3fc5c5acff16d5a314a8..8752ac82c557bf92985bd4d87a3e37f4cd4a60dc 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -65,6 +65,7 @@ struct ipc_msg_table_entry { struct hlist_node ipc_table_hlist; void *response; + unsigned int msg_sz; }; static struct delayed_work ipc_timer_work; @@ -275,6 +276,7 @@ static int handle_response(int type, void *payload, size_t sz) } memcpy(entry->response, payload, sz); + entry->msg_sz = sz; wake_up_interruptible(&entry->wait); ret = 0; break; @@ -453,6 +455,34 @@ out: return ret; } +static int ipc_validate_msg(struct ipc_msg_table_entry *entry) +{ + unsigned int msg_sz = entry->msg_sz; + + if (entry->type == KSMBD_EVENT_RPC_REQUEST) { + struct ksmbd_rpc_command *resp = entry->response; + + msg_sz = sizeof(struct ksmbd_rpc_command) + resp->payload_sz; + } else if (entry->type == KSMBD_EVENT_SPNEGO_AUTHEN_REQUEST) { + struct ksmbd_spnego_authen_response *resp = entry->response; + + msg_sz = sizeof(struct ksmbd_spnego_authen_response) + + resp->session_key_len + resp->spnego_blob_len; + } else if (entry->type == KSMBD_EVENT_SHARE_CONFIG_REQUEST) { + struct ksmbd_share_config_response *resp = entry->response; + + if (resp->payload_sz) { + if (resp->payload_sz < resp->veto_list_sz) + return -EINVAL; + + msg_sz = sizeof(struct ksmbd_share_config_response) + + resp->payload_sz; + } + } + + return entry->msg_sz != msg_sz ? -EINVAL : 0; +} + static void *ipc_msg_send_request(struct ksmbd_ipc_msg *msg, unsigned int handle) { struct ipc_msg_table_entry entry; @@ -477,6 +507,13 @@ static void *ipc_msg_send_request(struct ksmbd_ipc_msg *msg, unsigned int handle ret = wait_event_interruptible_timeout(entry.wait, entry.response != NULL, IPC_WAIT_TIMEOUT); + if (entry.response) { + ret = ipc_validate_msg(&entry); + if (ret) { + kvfree(entry.response); + entry.response = NULL; + } + } out: down_write(&ipc_msg_table_lock); hash_del(&entry.ipc_table_hlist); diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index 9d4222154dcc0c92201a0d7a6e4dac77e0eea37b..0012919309f11fee335b09253dd9fb456984e512 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -446,6 +446,10 @@ static int create_socket(struct interface *iface) sin6.sin6_family = PF_INET6; sin6.sin6_addr = in6addr_any; sin6.sin6_port = htons(server_conf.tcp_port); + + lock_sock(ksmbd_socket->sk); + ksmbd_socket->sk->sk_ipv6only = false; + release_sock(ksmbd_socket->sk); } ksmbd_tcp_nodelay(ksmbd_socket); diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index fe2c80ea2e47e23d8fc9bf75ce37619855568432..a4c99ec38faca61decd79ac91eb54eb7a22f2698 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -746,10 +746,15 @@ retry: goto out4; } + /* + * explicitly handle file overwrite case, for compatibility with + * filesystems that may not support rename flags (e.g: fuse) + */ if ((flags & RENAME_NOREPLACE) && d_is_positive(new_dentry)) { err = -EEXIST; goto out4; } + flags &= ~(RENAME_NOREPLACE); if (old_child == trap) { err = -EINVAL; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index a12ac0356c69cd409a856b5a551ce1768cf7ad16..f21e73d107249df4fbf0a687e9a35d2e5d3bc513 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -450,6 +450,8 @@ struct kernfs_node *sysfs_break_active_protection(struct kobject *kobj, kn = kernfs_find_and_get(kobj->sd, attr->name); if (kn) kernfs_break_active_protection(kn); + else + kobject_put(kobj); return kn; } EXPORT_SYMBOL_GPL(sysfs_break_active_protection); diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index 9925cfe57159572c2d376313b0ea6863ddbe83ad..17c7d76770a0ab0e712255d6e52a761f09bda253 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -82,9 +82,6 @@ static inline sysv_zone_t *block_end(struct buffer_head *bh) return (sysv_zone_t*)((char*)bh->b_data + bh->b_size); } -/* - * Requires read_lock(&pointers_lock) or write_lock(&pointers_lock) - */ static Indirect *get_branch(struct inode *inode, int depth, int offsets[], @@ -104,15 +101,18 @@ static Indirect *get_branch(struct inode *inode, bh = sb_bread(sb, block); if (!bh) goto failure; + read_lock(&pointers_lock); if (!verify_chain(chain, p)) goto changed; add_chain(++p, bh, (sysv_zone_t*)bh->b_data + *++offsets); + read_unlock(&pointers_lock); if (!p->key) goto no_block; } return NULL; changed: + read_unlock(&pointers_lock); brelse(bh); *err = -EAGAIN; goto no_block; @@ -218,9 +218,7 @@ static int get_block(struct inode *inode, sector_t iblock, struct buffer_head *b goto out; reread: - read_lock(&pointers_lock); partial = get_branch(inode, depth, offsets, chain, &err); - read_unlock(&pointers_lock); /* Simplest case - block found, no allocation needed */ if (!partial) { @@ -290,9 +288,9 @@ static Indirect *find_shared(struct inode *inode, *top = 0; for (k = depth; k > 1 && !offsets[k-1]; k--) ; + partial = get_branch(inode, k, offsets, chain, &err); write_lock(&pointers_lock); - partial = get_branch(inode, k, offsets, chain, &err); if (!partial) partial = chain + k-1; /* diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 10c1779af9c519067e54cabe311f3b67843231f0..f7b1f9ece1364c90dca226040573e2bcad9325ff 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -261,9 +261,6 @@ static int write_begin_slow(struct address_space *mapping, return err; } } - - SetPageUptodate(page); - ClearPageError(page); } if (PagePrivate(page)) @@ -462,9 +459,6 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, return err; } } - - SetPageUptodate(page); - ClearPageError(page); } err = allocate_budget(c, page, ui, appending); @@ -474,10 +468,8 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, * If we skipped reading the page because we were going to * write all of it, then it is not up to date. */ - if (skipped_read) { + if (skipped_read) ClearPageChecked(page); - ClearPageUptodate(page); - } /* * Budgeting failed which means it would have to force * write-back but didn't, because we set the @fast flag in the @@ -568,6 +560,9 @@ static int ubifs_write_end(struct file *file, struct address_space *mapping, goto out; } + if (len == PAGE_SIZE) + SetPageUptodate(page); + if (!PagePrivate(page)) { attach_page_private(page, (void *)1); atomic_long_inc(&c->dirty_pg_cnt); diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c index d2f6df69f6110c02ec114a2938d855aca8df1487..74952e58cca06fc99870fa329614e01218e8f13f 100644 --- a/fs/vboxsf/super.c +++ b/fs/vboxsf/super.c @@ -151,7 +151,7 @@ static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc) if (!sbi->nls) { vbg_err("vboxsf: Count not load '%s' nls\n", nls_name); err = -EINVAL; - goto fail_free; + goto fail_destroy_idr; } } @@ -224,6 +224,7 @@ fail_free: ida_simple_remove(&vboxsf_bdi_ida, sbi->bdi_id); if (sbi->nls) unload_nls(sbi->nls); +fail_destroy_idr: idr_destroy(&sbi->ino_idr); kfree(sbi); return err; diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 49d0d4ea63fcdb11f9b1267f2c30e0585e765e70..0d56a8d862e801623fcbd43f4e4055bbfbc91ff3 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -4058,7 +4058,7 @@ xfs_bmap_alloc_userdata( * the busy list. */ bma->datatype = XFS_ALLOC_NOBUSY; - if (whichfork == XFS_DATA_FORK) { + if (whichfork == XFS_DATA_FORK || whichfork == XFS_COW_FORK) { bma->datatype |= XFS_ALLOC_USERDATA; if (bma->offset == 0) bma->datatype |= XFS_ALLOC_INITIAL_USER_DATA; @@ -4551,7 +4551,8 @@ xfs_bmapi_convert_delalloc( * the extent. Just return the real extent at this offset. */ if (!isnullstartblock(bma.got.br_startblock)) { - xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags); + xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags, + xfs_iomap_inode_sequence(ip, flags)); *seq = READ_ONCE(ifp->if_seq); goto out_trans_cancel; } @@ -4599,7 +4600,8 @@ xfs_bmapi_convert_delalloc( XFS_STATS_INC(mp, xs_xstrat_quick); ASSERT(!isnullstartblock(bma.got.br_startblock)); - xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags); + xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags, + xfs_iomap_inode_sequence(ip, flags)); *seq = READ_ONCE(ifp->if_seq); if (whichfork == XFS_COW_FORK) diff --git a/fs/xfs/libxfs/xfs_errortag.h b/fs/xfs/libxfs/xfs_errortag.h index 5362908164b0b1262f31fd83c4dc0c2538363d60..580ccbd5aadc2cf18f29d69b692ce32f71e6c9cf 100644 --- a/fs/xfs/libxfs/xfs_errortag.h +++ b/fs/xfs/libxfs/xfs_errortag.h @@ -40,13 +40,12 @@ #define XFS_ERRTAG_REFCOUNT_FINISH_ONE 25 #define XFS_ERRTAG_BMAP_FINISH_ONE 26 #define XFS_ERRTAG_AG_RESV_CRITICAL 27 + /* - * DEBUG mode instrumentation to test and/or trigger delayed allocation - * block killing in the event of failed writes. When enabled, all - * buffered writes are silenty dropped and handled as if they failed. - * All delalloc blocks in the range of the write (including pre-existing - * delalloc blocks!) are tossed as part of the write failure error - * handling sequence. + * Drop-writes support removed because write error handling cannot trash + * pre-existing delalloc extents in any useful way anymore. We retain the + * definition so that we can reject it as an invalid value in + * xfs_errortag_valid(). */ #define XFS_ERRTAG_DROP_WRITES 28 #define XFS_ERRTAG_LOG_BAD_CRC 29 @@ -95,7 +94,6 @@ #define XFS_RANDOM_REFCOUNT_FINISH_ONE 1 #define XFS_RANDOM_BMAP_FINISH_ONE 1 #define XFS_RANDOM_AG_RESV_CRITICAL 4 -#define XFS_RANDOM_DROP_WRITES 1 #define XFS_RANDOM_LOG_BAD_CRC 1 #define XFS_RANDOM_LOG_ITEM_PIN 1 #define XFS_RANDOM_BUF_LRU_REF 2 diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 3f34bafe18dd1d86225693c1c35d8e2b10026725..6f7ed9288fe402e04118277d38293b16d7ba4243 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -815,11 +815,136 @@ out_error: /* Is this extent valid? */ static inline bool xfs_refc_valid( - struct xfs_refcount_irec *rc) + const struct xfs_refcount_irec *rc) { return rc->rc_startblock != NULLAGBLOCK; } +static inline xfs_nlink_t +xfs_refc_merge_refcount( + const struct xfs_refcount_irec *irec, + enum xfs_refc_adjust_op adjust) +{ + /* Once a record hits MAXREFCOUNT, it is pinned there forever */ + if (irec->rc_refcount == MAXREFCOUNT) + return MAXREFCOUNT; + return irec->rc_refcount + adjust; +} + +static inline bool +xfs_refc_want_merge_center( + const struct xfs_refcount_irec *left, + const struct xfs_refcount_irec *cleft, + const struct xfs_refcount_irec *cright, + const struct xfs_refcount_irec *right, + bool cleft_is_cright, + enum xfs_refc_adjust_op adjust, + unsigned long long *ulenp) +{ + unsigned long long ulen = left->rc_blockcount; + xfs_nlink_t new_refcount; + + /* + * To merge with a center record, both shoulder records must be + * adjacent to the record we want to adjust. This is only true if + * find_left and find_right made all four records valid. + */ + if (!xfs_refc_valid(left) || !xfs_refc_valid(right) || + !xfs_refc_valid(cleft) || !xfs_refc_valid(cright)) + return false; + + /* There must only be one record for the entire range. */ + if (!cleft_is_cright) + return false; + + /* The shoulder record refcounts must match the new refcount. */ + new_refcount = xfs_refc_merge_refcount(cleft, adjust); + if (left->rc_refcount != new_refcount) + return false; + if (right->rc_refcount != new_refcount) + return false; + + /* + * The new record cannot exceed the max length. ulen is a ULL as the + * individual record block counts can be up to (u32 - 1) in length + * hence we need to catch u32 addition overflows here. + */ + ulen += cleft->rc_blockcount + right->rc_blockcount; + if (ulen >= MAXREFCEXTLEN) + return false; + + *ulenp = ulen; + return true; +} + +static inline bool +xfs_refc_want_merge_left( + const struct xfs_refcount_irec *left, + const struct xfs_refcount_irec *cleft, + enum xfs_refc_adjust_op adjust) +{ + unsigned long long ulen = left->rc_blockcount; + xfs_nlink_t new_refcount; + + /* + * For a left merge, the left shoulder record must be adjacent to the + * start of the range. If this is true, find_left made left and cleft + * contain valid contents. + */ + if (!xfs_refc_valid(left) || !xfs_refc_valid(cleft)) + return false; + + /* Left shoulder record refcount must match the new refcount. */ + new_refcount = xfs_refc_merge_refcount(cleft, adjust); + if (left->rc_refcount != new_refcount) + return false; + + /* + * The new record cannot exceed the max length. ulen is a ULL as the + * individual record block counts can be up to (u32 - 1) in length + * hence we need to catch u32 addition overflows here. + */ + ulen += cleft->rc_blockcount; + if (ulen >= MAXREFCEXTLEN) + return false; + + return true; +} + +static inline bool +xfs_refc_want_merge_right( + const struct xfs_refcount_irec *cright, + const struct xfs_refcount_irec *right, + enum xfs_refc_adjust_op adjust) +{ + unsigned long long ulen = right->rc_blockcount; + xfs_nlink_t new_refcount; + + /* + * For a right merge, the right shoulder record must be adjacent to the + * end of the range. If this is true, find_right made cright and right + * contain valid contents. + */ + if (!xfs_refc_valid(right) || !xfs_refc_valid(cright)) + return false; + + /* Right shoulder record refcount must match the new refcount. */ + new_refcount = xfs_refc_merge_refcount(cright, adjust); + if (right->rc_refcount != new_refcount) + return false; + + /* + * The new record cannot exceed the max length. ulen is a ULL as the + * individual record block counts can be up to (u32 - 1) in length + * hence we need to catch u32 addition overflows here. + */ + ulen += cright->rc_blockcount; + if (ulen >= MAXREFCEXTLEN) + return false; + + return true; +} + /* * Try to merge with any extents on the boundaries of the adjustment range. */ @@ -861,23 +986,15 @@ xfs_refcount_merge_extents( (cleft.rc_blockcount == cright.rc_blockcount); /* Try to merge left, cleft, and right. cleft must == cright. */ - ulen = (unsigned long long)left.rc_blockcount + cleft.rc_blockcount + - right.rc_blockcount; - if (xfs_refc_valid(&left) && xfs_refc_valid(&right) && - xfs_refc_valid(&cleft) && xfs_refc_valid(&cright) && cequal && - left.rc_refcount == cleft.rc_refcount + adjust && - right.rc_refcount == cleft.rc_refcount + adjust && - ulen < MAXREFCEXTLEN) { + if (xfs_refc_want_merge_center(&left, &cleft, &cright, &right, cequal, + adjust, &ulen)) { *shape_changed = true; return xfs_refcount_merge_center_extents(cur, &left, &cleft, &right, ulen, aglen); } /* Try to merge left and cleft. */ - ulen = (unsigned long long)left.rc_blockcount + cleft.rc_blockcount; - if (xfs_refc_valid(&left) && xfs_refc_valid(&cleft) && - left.rc_refcount == cleft.rc_refcount + adjust && - ulen < MAXREFCEXTLEN) { + if (xfs_refc_want_merge_left(&left, &cleft, adjust)) { *shape_changed = true; error = xfs_refcount_merge_left_extent(cur, &left, &cleft, agbno, aglen); @@ -893,10 +1010,7 @@ xfs_refcount_merge_extents( } /* Try to merge cright and right. */ - ulen = (unsigned long long)right.rc_blockcount + cright.rc_blockcount; - if (xfs_refc_valid(&right) && xfs_refc_valid(&cright) && - right.rc_refcount == cright.rc_refcount + adjust && - ulen < MAXREFCEXTLEN) { + if (xfs_refc_want_merge_right(&cright, &right, adjust)) { *shape_changed = true; return xfs_refcount_merge_right_extent(cur, &right, &cright, aglen); diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index b6a584e044be076f337a5552af8ff9785d35f00c..bf2cca78304eb9c5b5a73e1bc1e647a1be6787b9 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -266,7 +266,8 @@ xfs_validate_sb_write( return -EFSCORRUPTED; } - if (xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) { + if (!xfs_is_readonly(mp) && + xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) { xfs_alert(mp, "Corruption detected in superblock read-only compatible features (0x%x)!", (sbp->sb_features_ro_compat & @@ -973,7 +974,9 @@ xfs_log_sb( */ if (xfs_has_lazysbcount(mp)) { mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount); - mp->m_sb.sb_ifree = percpu_counter_sum(&mp->m_ifree); + mp->m_sb.sb_ifree = min_t(uint64_t, + percpu_counter_sum(&mp->m_ifree), + mp->m_sb.sb_icount); mp->m_sb.sb_fdblocks = percpu_counter_sum(&mp->m_fdblocks); } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 5d1a995b15f8331bb55f748fe2e42e2e9ebb652c..21c241e96d48309df4136d25f250a0067a250793 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -114,9 +114,8 @@ xfs_end_ioend( if (unlikely(error)) { if (ioend->io_flags & IOMAP_F_SHARED) { xfs_reflink_cancel_cow_range(ip, offset, size, true); - xfs_bmap_punch_delalloc_range(ip, - XFS_B_TO_FSBT(mp, offset), - XFS_B_TO_FSB(mp, size)); + xfs_bmap_punch_delalloc_range(ip, offset, + offset + size); } goto done; } @@ -373,7 +372,7 @@ retry: isnullstartblock(imap.br_startblock)) goto allocate_blocks; - xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0, 0); + xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0, 0, XFS_WPC(wpc)->data_seq); trace_xfs_map_blocks_found(ip, offset, count, whichfork, &imap); return 0; allocate_blocks: @@ -440,27 +439,25 @@ xfs_prepare_ioend( } /* - * If the page has delalloc blocks on it, we need to punch them out before we - * invalidate the page. If we don't, we leave a stale delalloc mapping on the - * inode that can trip up a later direct I/O read operation on the same region. + * If the folio has delalloc blocks on it, the caller is asking us to punch them + * out. If we don't, we can leave a stale delalloc mapping covered by a clean + * page that needs to be dirtied again before the delalloc mapping can be + * converted. This stale delalloc mapping can trip up a later direct I/O read + * operation on the same region. * - * We prevent this by truncating away the delalloc regions on the page. Because + * We prevent this by truncating away the delalloc regions on the folio. Because * they are delalloc, we can do this without needing a transaction. Indeed - if * we get ENOSPC errors, we have to be able to do this truncation without a - * transaction as there is no space left for block reservation (typically why we - * see a ENOSPC in writeback). + * transaction as there is no space left for block reservation (typically why + * we see a ENOSPC in writeback). */ static void xfs_discard_folio( struct folio *folio, loff_t pos) { - struct inode *inode = folio->mapping->host; - struct xfs_inode *ip = XFS_I(inode); + struct xfs_inode *ip = XFS_I(folio->mapping->host); struct xfs_mount *mp = ip->i_mount; - size_t offset = offset_in_folio(folio, pos); - xfs_fileoff_t start_fsb = XFS_B_TO_FSBT(mp, pos); - xfs_fileoff_t pageoff_fsb = XFS_B_TO_FSBT(mp, offset); int error; if (xfs_is_shutdown(mp)) @@ -470,8 +467,14 @@ xfs_discard_folio( "page discard on page "PTR_FMT", inode 0x%llx, pos %llu.", folio, ip->i_ino, pos); - error = xfs_bmap_punch_delalloc_range(ip, start_fsb, - i_blocks_per_folio(inode, folio) - pageoff_fsb); + /* + * The end of the punch range is always the offset of the the first + * byte of the next folio. Hence the end offset is only dependent on the + * folio itself and not the start offset that is passed in. + */ + error = xfs_bmap_punch_delalloc_range(ip, pos, + folio_pos(folio) + folio_size(folio)); + if (error && !xfs_is_shutdown(mp)) xfs_alert(mp, "page discard unable to remove delalloc mapping."); } diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 04d0c2bff67c4cfad424136a5777441d03309a48..867645b74d889ddc96f768f7e74d15690840c1e1 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -590,11 +590,13 @@ out_unlock_iolock: int xfs_bmap_punch_delalloc_range( struct xfs_inode *ip, - xfs_fileoff_t start_fsb, - xfs_fileoff_t length) + xfs_off_t start_byte, + xfs_off_t end_byte) { + struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp = &ip->i_df; - xfs_fileoff_t end_fsb = start_fsb + length; + xfs_fileoff_t start_fsb = XFS_B_TO_FSBT(mp, start_byte); + xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, end_byte); struct xfs_bmbt_irec got, del; struct xfs_iext_cursor icur; int error = 0; @@ -607,7 +609,7 @@ xfs_bmap_punch_delalloc_range( while (got.br_startoff + got.br_blockcount > start_fsb) { del = got; - xfs_trim_extent(&del, start_fsb, length); + xfs_trim_extent(&del, start_fsb, end_fsb - start_fsb); /* * A delete can push the cursor forward. Step back to the diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h index 24b37d211f1dcd8318a5aab00a7962b88e0a2f32..6888078f5c31e009b8a0f1b91938d3a1381423ce 100644 --- a/fs/xfs/xfs_bmap_util.h +++ b/fs/xfs/xfs_bmap_util.h @@ -31,7 +31,7 @@ xfs_bmap_rtalloc(struct xfs_bmalloca *ap) #endif /* CONFIG_XFS_RT */ int xfs_bmap_punch_delalloc_range(struct xfs_inode *ip, - xfs_fileoff_t start_fsb, xfs_fileoff_t length); + xfs_off_t start_byte, xfs_off_t end_byte); struct kgetbmap { __s64 bmv_offset; /* file offset of segment in blocks */ diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index dde346450952afe8175990126de089b214cef881..54c774af6e1c625abf96d5177fa11814952da1fb 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1945,6 +1945,7 @@ xfs_free_buftarg( list_lru_destroy(&btp->bt_lru); blkdev_issue_flush(btp->bt_bdev); + invalidate_bdev(btp->bt_bdev); fs_put_dax(btp->bt_daxdev, btp->bt_mount); kmem_free(btp); diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 522d450a94b18616183ebc2a0c8a35b56111341d..df7322ed73fa927b86f8f4de8b1583c7b5f1ef72 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -1018,6 +1018,8 @@ xfs_buf_item_relse( trace_xfs_buf_item_relse(bp, _RET_IP_); ASSERT(!test_bit(XFS_LI_IN_AIL, &bip->bli_item.li_flags)); + if (atomic_read(&bip->bli_refcount)) + return; bp->b_log_item = NULL; xfs_buf_rele(bp); xfs_buf_item_free(bip); diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index c6b2aabd6f1879716301e5129e607c54cc764ea6..dea3c0649d2f7f4ca504efeaa60d9887284e7845 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -46,7 +46,7 @@ static unsigned int xfs_errortag_random_default[] = { XFS_RANDOM_REFCOUNT_FINISH_ONE, XFS_RANDOM_BMAP_FINISH_ONE, XFS_RANDOM_AG_RESV_CRITICAL, - XFS_RANDOM_DROP_WRITES, + 0, /* XFS_RANDOM_DROP_WRITES has been removed */ XFS_RANDOM_LOG_BAD_CRC, XFS_RANDOM_LOG_ITEM_PIN, XFS_RANDOM_BUF_LRU_REF, @@ -162,7 +162,6 @@ XFS_ERRORTAG_ATTR_RW(refcount_continue_update, XFS_ERRTAG_REFCOUNT_CONTINUE_UPDA XFS_ERRORTAG_ATTR_RW(refcount_finish_one, XFS_ERRTAG_REFCOUNT_FINISH_ONE); XFS_ERRORTAG_ATTR_RW(bmap_finish_one, XFS_ERRTAG_BMAP_FINISH_ONE); XFS_ERRORTAG_ATTR_RW(ag_resv_critical, XFS_ERRTAG_AG_RESV_CRITICAL); -XFS_ERRORTAG_ATTR_RW(drop_writes, XFS_ERRTAG_DROP_WRITES); XFS_ERRORTAG_ATTR_RW(log_bad_crc, XFS_ERRTAG_LOG_BAD_CRC); XFS_ERRORTAG_ATTR_RW(log_item_pin, XFS_ERRTAG_LOG_ITEM_PIN); XFS_ERRORTAG_ATTR_RW(buf_lru_ref, XFS_ERRTAG_BUF_LRU_REF); @@ -206,7 +205,6 @@ static struct attribute *xfs_errortag_attrs[] = { XFS_ERRORTAG_ATTR_LIST(refcount_finish_one), XFS_ERRORTAG_ATTR_LIST(bmap_finish_one), XFS_ERRORTAG_ATTR_LIST(ag_resv_critical), - XFS_ERRORTAG_ATTR_LIST(drop_writes), XFS_ERRORTAG_ATTR_LIST(log_bad_crc), XFS_ERRORTAG_ATTR_LIST(log_item_pin), XFS_ERRORTAG_ATTR_LIST(buf_lru_ref), @@ -256,6 +254,19 @@ xfs_errortag_del( kmem_free(mp->m_errortag); } +static bool +xfs_errortag_valid( + unsigned int error_tag) +{ + if (error_tag >= XFS_ERRTAG_MAX) + return false; + + /* Error out removed injection types */ + if (error_tag == XFS_ERRTAG_DROP_WRITES) + return false; + return true; +} + bool xfs_errortag_test( struct xfs_mount *mp, @@ -277,7 +288,9 @@ xfs_errortag_test( if (!mp->m_errortag) return false; - ASSERT(error_tag < XFS_ERRTAG_MAX); + if (!xfs_errortag_valid(error_tag)) + return false; + randfactor = mp->m_errortag[error_tag]; if (!randfactor || prandom_u32_max(randfactor)) return false; @@ -293,7 +306,7 @@ xfs_errortag_get( struct xfs_mount *mp, unsigned int error_tag) { - if (error_tag >= XFS_ERRTAG_MAX) + if (!xfs_errortag_valid(error_tag)) return -EINVAL; return mp->m_errortag[error_tag]; @@ -305,7 +318,7 @@ xfs_errortag_set( unsigned int error_tag, unsigned int tag_value) { - if (error_tag >= XFS_ERRTAG_MAX) + if (!xfs_errortag_valid(error_tag)) return -EINVAL; mp->m_errortag[error_tag] = tag_value; @@ -319,7 +332,7 @@ xfs_errortag_add( { BUILD_BUG_ON(ARRAY_SIZE(xfs_errortag_random_default) != XFS_ERRTAG_MAX); - if (error_tag >= XFS_ERRTAG_MAX) + if (!xfs_errortag_valid(error_tag)) return -EINVAL; return xfs_errortag_set(mp, error_tag, diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index e462d39c840e62911242e1e157756b81d8737c9d..595a5bcf46b9496a6d1aee087282f103015c861c 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1325,7 +1325,7 @@ __xfs_filemap_fault( if (write_fault) { xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); ret = iomap_page_mkwrite(vmf, - &xfs_buffered_write_iomap_ops); + &xfs_page_mkwrite_iomap_ops); xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); } else { ret = filemap_fault(vmf); diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 13851c0d640bc8268361940ac5a7eac7b83e42e0..332da0d7b85cfa1490c05887b66f183698ac8dcf 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -129,6 +129,10 @@ xfs_growfs_data_private( if (delta < 0 && nagcount < 2) return -EINVAL; + /* No work to do */ + if (delta == 0) + return 0; + oagcount = mp->m_sb.sb_agcount; /* allocate the new per-ag structures */ if (nagcount > oagcount) { diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index d884cba1d7072280bb5da1df3662d69968180ca1..dd5a664c294f56265db6ddbd5b56aedf847e36b6 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -342,6 +342,9 @@ xfs_iget_recycle( trace_xfs_iget_recycle(ip); + if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) + return -EAGAIN; + /* * We need to make it look like the inode is being reclaimed to prevent * the actual reclaim workers from stomping over us while we recycle @@ -355,6 +358,7 @@ xfs_iget_recycle( ASSERT(!rwsem_is_locked(&inode->i_rwsem)); error = xfs_reinit_inode(mp, inode); + xfs_iunlock(ip, XFS_ILOCK_EXCL); if (error) { /* * Re-initializing the inode failed, and we are in deep @@ -523,6 +527,8 @@ xfs_iget_cache_hit( if (ip->i_flags & XFS_IRECLAIMABLE) { /* Drops i_flags_lock and RCU read lock. */ error = xfs_iget_recycle(pag, ip); + if (error == -EAGAIN) + goto out_skip; if (error) return error; } else { diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index aa303be11576ffb04b31a29a187529b38d533f04..54b707787f9070895bcd12f400ecdbf398965403 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1652,8 +1652,11 @@ xfs_inode_needs_inactive( if (VFS_I(ip)->i_mode == 0) return false; - /* If this is a read-only mount, don't do this (would generate I/O) */ - if (xfs_is_readonly(mp)) + /* + * If this is a read-only mount, don't do this (would generate I/O) + * unless we're in log recovery and cleaning the iunlinked list. + */ + if (xfs_is_readonly(mp) && !xlog_recovery_needed(mp->m_log)) return false; /* If the log isn't running, push inodes straight to reclaim. */ @@ -1713,8 +1716,11 @@ xfs_inactive( mp = ip->i_mount; ASSERT(!xfs_iflags_test(ip, XFS_IRECOVERY)); - /* If this is a read-only mount, don't do this (would generate I/O) */ - if (xfs_is_readonly(mp)) + /* + * If this is a read-only mount, don't do this (would generate I/O) + * unless we're in log recovery and cleaning the iunlinked list. + */ + if (xfs_is_readonly(mp) && !xlog_recovery_needed(mp->m_log)) goto out; /* Metadata inodes require explicit resource cleanup. */ @@ -2479,7 +2485,7 @@ xfs_remove( error = xfs_dir_replace(tp, ip, &xfs_name_dotdot, tp->t_mountp->m_sb.sb_rootino, 0); if (error) - return error; + goto out_trans_cancel; } } else { /* diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 1f783e97962968eebc5d1270aa27aecdf1752a3e..85fbb3b71d1c67b74a8647ef3d43bfe669515535 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -754,7 +754,7 @@ xfs_bulkstat_fmt( static int xfs_bulk_ireq_setup( struct xfs_mount *mp, - struct xfs_bulk_ireq *hdr, + const struct xfs_bulk_ireq *hdr, struct xfs_ibulk *breq, void __user *ubuffer) { @@ -780,7 +780,7 @@ xfs_bulk_ireq_setup( switch (hdr->ino) { case XFS_BULK_IREQ_SPECIAL_ROOT: - hdr->ino = mp->m_sb.sb_rootino; + breq->startino = mp->m_sb.sb_rootino; break; default: return -EINVAL; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 07da03976ec125c3d2cca979d2ff736e43252306..ab5512c0bcf7a91db02f62401d7184161cb52e53 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -48,13 +48,45 @@ xfs_alert_fsblock_zero( return -EFSCORRUPTED; } +u64 +xfs_iomap_inode_sequence( + struct xfs_inode *ip, + u16 iomap_flags) +{ + u64 cookie = 0; + + if (iomap_flags & IOMAP_F_XATTR) + return READ_ONCE(ip->i_af.if_seq); + if ((iomap_flags & IOMAP_F_SHARED) && ip->i_cowfp) + cookie = (u64)READ_ONCE(ip->i_cowfp->if_seq) << 32; + return cookie | READ_ONCE(ip->i_df.if_seq); +} + +/* + * Check that the iomap passed to us is still valid for the given offset and + * length. + */ +static bool +xfs_iomap_valid( + struct inode *inode, + const struct iomap *iomap) +{ + return iomap->validity_cookie == + xfs_iomap_inode_sequence(XFS_I(inode), iomap->flags); +} + +const struct iomap_page_ops xfs_iomap_page_ops = { + .iomap_valid = xfs_iomap_valid, +}; + int xfs_bmbt_to_iomap( struct xfs_inode *ip, struct iomap *iomap, struct xfs_bmbt_irec *imap, unsigned int mapping_flags, - u16 iomap_flags) + u16 iomap_flags, + u64 sequence_cookie) { struct xfs_mount *mp = ip->i_mount; struct xfs_buftarg *target = xfs_inode_buftarg(ip); @@ -91,6 +123,9 @@ xfs_bmbt_to_iomap( if (xfs_ipincount(ip) && (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP)) iomap->flags |= IOMAP_F_DIRTY; + + iomap->validity_cookie = sequence_cookie; + iomap->page_ops = &xfs_iomap_page_ops; return 0; } @@ -195,7 +230,8 @@ xfs_iomap_write_direct( xfs_fileoff_t offset_fsb, xfs_fileoff_t count_fsb, unsigned int flags, - struct xfs_bmbt_irec *imap) + struct xfs_bmbt_irec *imap, + u64 *seq) { struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; @@ -285,6 +321,7 @@ xfs_iomap_write_direct( error = xfs_alert_fsblock_zero(ip, imap); out_unlock: + *seq = xfs_iomap_inode_sequence(ip, 0); xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; @@ -743,6 +780,7 @@ xfs_direct_write_iomap_begin( bool shared = false; u16 iomap_flags = 0; unsigned int lockmode = XFS_ILOCK_SHARED; + u64 seq; ASSERT(flags & (IOMAP_WRITE | IOMAP_ZERO)); @@ -811,9 +849,10 @@ xfs_direct_write_iomap_begin( goto out_unlock; } + seq = xfs_iomap_inode_sequence(ip, iomap_flags); xfs_iunlock(ip, lockmode); trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap); - return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, iomap_flags); + return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, iomap_flags, seq); allocate_blocks: error = -EAGAIN; @@ -839,24 +878,26 @@ allocate_blocks: xfs_iunlock(ip, lockmode); error = xfs_iomap_write_direct(ip, offset_fsb, end_fsb - offset_fsb, - flags, &imap); + flags, &imap, &seq); if (error) return error; trace_xfs_iomap_alloc(ip, offset, length, XFS_DATA_FORK, &imap); return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, - iomap_flags | IOMAP_F_NEW); + iomap_flags | IOMAP_F_NEW, seq); out_found_cow: - xfs_iunlock(ip, lockmode); length = XFS_FSB_TO_B(mp, cmap.br_startoff + cmap.br_blockcount); trace_xfs_iomap_found(ip, offset, length - offset, XFS_COW_FORK, &cmap); if (imap.br_startblock != HOLESTARTBLOCK) { - error = xfs_bmbt_to_iomap(ip, srcmap, &imap, flags, 0); + seq = xfs_iomap_inode_sequence(ip, 0); + error = xfs_bmbt_to_iomap(ip, srcmap, &imap, flags, 0, seq); if (error) - return error; + goto out_unlock; } - return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, IOMAP_F_SHARED); + seq = xfs_iomap_inode_sequence(ip, IOMAP_F_SHARED); + xfs_iunlock(ip, lockmode); + return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, IOMAP_F_SHARED, seq); out_unlock: if (lockmode) @@ -915,6 +956,7 @@ xfs_buffered_write_iomap_begin( int allocfork = XFS_DATA_FORK; int error = 0; unsigned int lockmode = XFS_ILOCK_EXCL; + u64 seq; if (xfs_is_shutdown(mp)) return -EIO; @@ -926,6 +968,10 @@ xfs_buffered_write_iomap_begin( ASSERT(!XFS_IS_REALTIME_INODE(ip)); + error = xfs_qm_dqattach(ip); + if (error) + return error; + error = xfs_ilock_for_iomap(ip, flags, &lockmode); if (error) return error; @@ -1029,10 +1075,6 @@ xfs_buffered_write_iomap_begin( allocfork = XFS_COW_FORK; } - error = xfs_qm_dqattach_locked(ip, false); - if (error) - goto out_unlock; - if (eof && offset + count > XFS_ISIZE(ip)) { /* * Determine the initial size of the preallocation. @@ -1094,32 +1136,47 @@ retry: * Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch * them out if the write happens to fail. */ + seq = xfs_iomap_inode_sequence(ip, IOMAP_F_NEW); xfs_iunlock(ip, XFS_ILOCK_EXCL); trace_xfs_iomap_alloc(ip, offset, count, allocfork, &imap); - return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, IOMAP_F_NEW); + return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, IOMAP_F_NEW, seq); found_imap: + seq = xfs_iomap_inode_sequence(ip, 0); xfs_iunlock(ip, XFS_ILOCK_EXCL); - return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0); + return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0, seq); found_cow: - xfs_iunlock(ip, XFS_ILOCK_EXCL); + seq = xfs_iomap_inode_sequence(ip, 0); if (imap.br_startoff <= offset_fsb) { - error = xfs_bmbt_to_iomap(ip, srcmap, &imap, flags, 0); + error = xfs_bmbt_to_iomap(ip, srcmap, &imap, flags, 0, seq); if (error) - return error; + goto out_unlock; + seq = xfs_iomap_inode_sequence(ip, IOMAP_F_SHARED); + xfs_iunlock(ip, XFS_ILOCK_EXCL); return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, - IOMAP_F_SHARED); + IOMAP_F_SHARED, seq); } xfs_trim_extent(&cmap, offset_fsb, imap.br_startoff - offset_fsb); - return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, 0); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, 0, seq); out_unlock: xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; } +static int +xfs_buffered_write_delalloc_punch( + struct inode *inode, + loff_t offset, + loff_t length) +{ + return xfs_bmap_punch_delalloc_range(XFS_I(inode), offset, + offset + length); +} + static int xfs_buffered_write_iomap_end( struct inode *inode, @@ -1129,56 +1186,17 @@ xfs_buffered_write_iomap_end( unsigned flags, struct iomap *iomap) { - struct xfs_inode *ip = XFS_I(inode); - struct xfs_mount *mp = ip->i_mount; - xfs_fileoff_t start_fsb; - xfs_fileoff_t end_fsb; - int error = 0; - - if (iomap->type != IOMAP_DELALLOC) - return 0; - - /* - * Behave as if the write failed if drop writes is enabled. Set the NEW - * flag to force delalloc cleanup. - */ - if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_DROP_WRITES)) { - iomap->flags |= IOMAP_F_NEW; - written = 0; - } - /* - * start_fsb refers to the first unused block after a short write. If - * nothing was written, round offset down to point at the first block in - * the range. - */ - if (unlikely(!written)) - start_fsb = XFS_B_TO_FSBT(mp, offset); - else - start_fsb = XFS_B_TO_FSB(mp, offset + written); - end_fsb = XFS_B_TO_FSB(mp, offset + length); + struct xfs_mount *mp = XFS_M(inode->i_sb); + int error; - /* - * Trim delalloc blocks if they were allocated by this write and we - * didn't manage to write the whole range. - * - * We don't need to care about racing delalloc as we hold i_mutex - * across the reserve/allocate/unreserve calls. If there are delalloc - * blocks in the range, they are ours. - */ - if ((iomap->flags & IOMAP_F_NEW) && start_fsb < end_fsb) { - truncate_pagecache_range(VFS_I(ip), XFS_FSB_TO_B(mp, start_fsb), - XFS_FSB_TO_B(mp, end_fsb) - 1); - - error = xfs_bmap_punch_delalloc_range(ip, start_fsb, - end_fsb - start_fsb); - if (error && !xfs_is_shutdown(mp)) { - xfs_alert(mp, "%s: unable to clean up ino %lld", - __func__, ip->i_ino); - return error; - } + error = iomap_file_buffered_write_punch_delalloc(inode, iomap, offset, + length, written, &xfs_buffered_write_delalloc_punch); + if (error && !xfs_is_shutdown(mp)) { + xfs_alert(mp, "%s: unable to clean up ino 0x%llx", + __func__, XFS_I(inode)->i_ino); + return error; } - return 0; } @@ -1187,6 +1205,15 @@ const struct iomap_ops xfs_buffered_write_iomap_ops = { .iomap_end = xfs_buffered_write_iomap_end, }; +/* + * iomap_page_mkwrite() will never fail in a way that requires delalloc extents + * that it allocated to be revoked. Hence we do not need an .iomap_end method + * for this operation. + */ +const struct iomap_ops xfs_page_mkwrite_iomap_ops = { + .iomap_begin = xfs_buffered_write_iomap_begin, +}; + static int xfs_read_iomap_begin( struct inode *inode, @@ -1204,6 +1231,7 @@ xfs_read_iomap_begin( int nimaps = 1, error = 0; bool shared = false; unsigned int lockmode = XFS_ILOCK_SHARED; + u64 seq; ASSERT(!(flags & (IOMAP_WRITE | IOMAP_ZERO))); @@ -1217,13 +1245,14 @@ xfs_read_iomap_begin( &nimaps, 0); if (!error && (flags & IOMAP_REPORT)) error = xfs_reflink_trim_around_shared(ip, &imap, &shared); + seq = xfs_iomap_inode_sequence(ip, shared ? IOMAP_F_SHARED : 0); xfs_iunlock(ip, lockmode); if (error) return error; trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap); return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, - shared ? IOMAP_F_SHARED : 0); + shared ? IOMAP_F_SHARED : 0, seq); } const struct iomap_ops xfs_read_iomap_ops = { @@ -1248,6 +1277,7 @@ xfs_seek_iomap_begin( struct xfs_bmbt_irec imap, cmap; int error = 0; unsigned lockmode; + u64 seq; if (xfs_is_shutdown(mp)) return -EIO; @@ -1282,8 +1312,9 @@ xfs_seek_iomap_begin( if (data_fsb < cow_fsb + cmap.br_blockcount) end_fsb = min(end_fsb, data_fsb); xfs_trim_extent(&cmap, offset_fsb, end_fsb); + seq = xfs_iomap_inode_sequence(ip, IOMAP_F_SHARED); error = xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, - IOMAP_F_SHARED); + IOMAP_F_SHARED, seq); /* * This is a COW extent, so we must probe the page cache * because there could be dirty page cache being backed @@ -1304,8 +1335,9 @@ xfs_seek_iomap_begin( imap.br_startblock = HOLESTARTBLOCK; imap.br_state = XFS_EXT_NORM; done: + seq = xfs_iomap_inode_sequence(ip, 0); xfs_trim_extent(&imap, offset_fsb, end_fsb); - error = xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0); + error = xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0, seq); out_unlock: xfs_iunlock(ip, lockmode); return error; @@ -1331,6 +1363,7 @@ xfs_xattr_iomap_begin( struct xfs_bmbt_irec imap; int nimaps = 1, error = 0; unsigned lockmode; + int seq; if (xfs_is_shutdown(mp)) return -EIO; @@ -1347,12 +1380,14 @@ xfs_xattr_iomap_begin( error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap, &nimaps, XFS_BMAPI_ATTRFORK); out_unlock: + + seq = xfs_iomap_inode_sequence(ip, IOMAP_F_XATTR); xfs_iunlock(ip, lockmode); if (error) return error; ASSERT(nimaps); - return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0); + return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, IOMAP_F_XATTR, seq); } const struct iomap_ops xfs_xattr_iomap_ops = { diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index c782e8c0479c0afc6ff27028ea36fc9d20350f2b..4da13440bae9bd7e67f5044b8bfc3544d57e8be9 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -13,14 +13,15 @@ struct xfs_bmbt_irec; int xfs_iomap_write_direct(struct xfs_inode *ip, xfs_fileoff_t offset_fsb, xfs_fileoff_t count_fsb, unsigned int flags, - struct xfs_bmbt_irec *imap); + struct xfs_bmbt_irec *imap, u64 *sequence); int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool); xfs_fileoff_t xfs_iomap_eof_align_last_fsb(struct xfs_inode *ip, xfs_fileoff_t end_fsb); +u64 xfs_iomap_inode_sequence(struct xfs_inode *ip, u16 iomap_flags); int xfs_bmbt_to_iomap(struct xfs_inode *ip, struct iomap *iomap, struct xfs_bmbt_irec *imap, unsigned int mapping_flags, - u16 iomap_flags); + u16 iomap_flags, u64 sequence_cookie); int xfs_zero_range(struct xfs_inode *ip, loff_t pos, loff_t len, bool *did_zero); @@ -47,6 +48,7 @@ xfs_aligned_fsb_count( } extern const struct iomap_ops xfs_buffered_write_iomap_ops; +extern const struct iomap_ops xfs_page_mkwrite_iomap_ops; extern const struct iomap_ops xfs_direct_write_iomap_ops; extern const struct iomap_ops xfs_read_iomap_ops; extern const struct iomap_ops xfs_seek_iomap_ops; diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index f02a0dd522b3df1316df282e168c6d429792e5d2..d9aa5eab02c3f5c8764d92ac64c39537f94bb181 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -730,15 +730,7 @@ xfs_log_mount( * just worked. */ if (!xfs_has_norecovery(mp)) { - /* - * log recovery ignores readonly state and so we need to clear - * mount-based read only state so it can write to disk. - */ - bool readonly = test_and_clear_bit(XFS_OPSTATE_READONLY, - &mp->m_opstate); error = xlog_recover(log); - if (readonly) - set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate); if (error) { xfs_warn(mp, "log mount/recovery failed: error %d", error); @@ -787,7 +779,6 @@ xfs_log_mount_finish( struct xfs_mount *mp) { struct xlog *log = mp->m_log; - bool readonly; int error = 0; if (xfs_has_norecovery(mp)) { @@ -795,12 +786,6 @@ xfs_log_mount_finish( return 0; } - /* - * log recovery ignores readonly state and so we need to clear - * mount-based read only state so it can write to disk. - */ - readonly = test_and_clear_bit(XFS_OPSTATE_READONLY, &mp->m_opstate); - /* * During the second phase of log recovery, we need iget and * iput to behave like they do for an active filesystem. @@ -850,8 +835,6 @@ xfs_log_mount_finish( xfs_buftarg_drain(mp->m_ddev_targp); clear_bit(XLOG_RECOVERY_NEEDED, &log->l_opstate); - if (readonly) - set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate); /* Make sure the log is dead if we're returning failure. */ ASSERT(!error || xlog_is_shutdown(log)); @@ -886,6 +869,23 @@ xlog_force_iclog( return xlog_state_release_iclog(iclog->ic_log, iclog, NULL); } +/* + * Cycle all the iclogbuf locks to make sure all log IO completion + * is done before we tear down these buffers. + */ +static void +xlog_wait_iclog_completion(struct xlog *log) +{ + int i; + struct xlog_in_core *iclog = log->l_iclog; + + for (i = 0; i < log->l_iclog_bufs; i++) { + down(&iclog->ic_sema); + up(&iclog->ic_sema); + iclog = iclog->ic_next; + } +} + /* * Wait for the iclog and all prior iclogs to be written disk as required by the * log force state machine. Waiting on ic_force_wait ensures iclog completions @@ -1111,6 +1111,14 @@ xfs_log_unmount( { xfs_log_clean(mp); + /* + * If shutdown has come from iclog IO context, the log + * cleaning will have been skipped and so we need to wait + * for the iclog to complete shutdown processing before we + * tear anything down. + */ + xlog_wait_iclog_completion(mp->m_log); + xfs_buftarg_drain(mp->m_ddev_targp); xfs_trans_ail_destroy(mp); @@ -2113,17 +2121,6 @@ xlog_dealloc_log( xlog_in_core_t *iclog, *next_iclog; int i; - /* - * Cycle all the iclogbuf locks to make sure all log IO completion - * is done before we tear down these buffers. - */ - iclog = log->l_iclog; - for (i = 0; i < log->l_iclog_bufs; i++) { - down(&iclog->ic_sema); - up(&iclog->ic_sema); - iclog = iclog->ic_next; - } - /* * Destroy the CIL after waiting for iclog IO completion because an * iclog EIO error will try to shut down the log, which accesses the diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index e8bb3c2e847e1ad14769ccf2f285df0cb56929db..fb87ffb48f7fe7da20b84269a31a220e9b1e0247 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -538,6 +538,20 @@ xfs_check_summary_counts( return 0; } +static void +xfs_unmount_check( + struct xfs_mount *mp) +{ + if (xfs_is_shutdown(mp)) + return; + + if (percpu_counter_sum(&mp->m_ifree) > + percpu_counter_sum(&mp->m_icount)) { + xfs_alert(mp, "ifree/icount mismatch at unmount"); + xfs_fs_mark_sick(mp, XFS_SICK_FS_COUNTERS); + } +} + /* * Flush and reclaim dirty inodes in preparation for unmount. Inodes and * internal inode structures can be sitting in the CIL and AIL at this point, @@ -1077,6 +1091,7 @@ xfs_unmountfs( if (error) xfs_warn(mp, "Unable to free reserved block pool. " "Freespace may not be correct on next mount."); + xfs_unmount_check(mp); xfs_log_unmount(mp); xfs_da_unmount(mp); diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index 37a24f0f7cd4015964045aa20799b1b514d7660a..38d23f0e703a8eaeb259e42a0814604003dd586d 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -125,6 +125,7 @@ xfs_fs_map_blocks( int nimaps = 1; uint lock_flags; int error = 0; + u64 seq; if (xfs_is_shutdown(mp)) return -EIO; @@ -176,6 +177,7 @@ xfs_fs_map_blocks( lock_flags = xfs_ilock_data_map_shared(ip); error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap, &nimaps, bmapi_flags); + seq = xfs_iomap_inode_sequence(ip, 0); ASSERT(!nimaps || imap.br_startblock != DELAYSTARTBLOCK); @@ -189,7 +191,7 @@ xfs_fs_map_blocks( xfs_iunlock(ip, lock_flags); error = xfs_iomap_write_direct(ip, offset_fsb, - end_fsb - offset_fsb, 0, &imap); + end_fsb - offset_fsb, 0, &imap, &seq); if (error) goto out_unlock; @@ -209,7 +211,7 @@ xfs_fs_map_blocks( } xfs_iunlock(ip, XFS_IOLOCK_EXCL); - error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0, 0); + error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0, 0, seq); *device_generation = mp->m_generation; return error; out_unlock: diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c index 63cd50840419c5d1d8d17263068083eab1a9dac3..8d5f4a5a74e65bbbc67f2a2dfd5c32010cd74dab 100644 --- a/fs/zonefs/file.c +++ b/fs/zonefs/file.c @@ -349,7 +349,12 @@ static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size, struct zonefs_inode_info *zi = ZONEFS_I(inode); if (error) { - zonefs_io_error(inode, true); + /* + * For Sync IOs, error recovery is called from + * zonefs_file_dio_write(). + */ + if (!is_sync_kiocb(iocb)) + zonefs_io_error(inode, true); return error; } @@ -577,6 +582,14 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) ret = -EINVAL; goto inode_unlock; } + /* + * Advance the zone write pointer offset. This assumes that the + * IO will succeed, which is OK to do because we do not allow + * partial writes (IOMAP_DIO_PARTIAL is not set) and if the IO + * fails, the error path will correct the write pointer offset. + */ + z->z_wpoffset += count; + zonefs_inode_account_active(inode); mutex_unlock(&zi->i_truncate_mutex); append = sync; } @@ -596,20 +609,19 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) ret = -EBUSY; } - if (zonefs_zone_is_seq(z) && - (ret > 0 || ret == -EIOCBQUEUED)) { - if (ret > 0) - count = ret; - - /* - * Update the zone write pointer offset assuming the write - * operation succeeded. If it did not, the error recovery path - * will correct it. Also do active seq file accounting. - */ - mutex_lock(&zi->i_truncate_mutex); - z->z_wpoffset += count; - zonefs_inode_account_active(inode); - mutex_unlock(&zi->i_truncate_mutex); + /* + * For a failed IO or partial completion, trigger error recovery + * to update the zone write pointer offset to a correct value. + * For asynchronous IOs, zonefs_file_write_dio_end_io() may already + * have executed error recovery if the IO already completed when we + * reach here. However, we cannot know that and execute error recovery + * again (that will not change anything). + */ + if (zonefs_zone_is_seq(z)) { + if (ret > 0 && ret != count) + ret = -EIO; + if (ret < 0 && ret != -EIOCBQUEUED) + zonefs_io_error(inode, true); } inode_unlock: diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 270ded209dde5bc3be4418f78b631eefeda18d31..f6b701261078cd2c570b530fd6048e0737ab435a 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -245,16 +245,18 @@ static void zonefs_inode_update_mode(struct inode *inode) z->z_flags &= ~ZONEFS_ZONE_INIT_MODE; } -struct zonefs_ioerr_data { - struct inode *inode; - bool write; -}; - static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, void *data) { - struct zonefs_ioerr_data *err = data; - struct inode *inode = err->inode; + struct blk_zone *z = data; + + *z = *zone; + return 0; +} + +static void zonefs_handle_io_error(struct inode *inode, struct blk_zone *zone, + bool write) +{ struct zonefs_zone *z = zonefs_inode_zone(inode); struct super_block *sb = inode->i_sb; struct zonefs_sb_info *sbi = ZONEFS_SB(sb); @@ -269,8 +271,8 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, data_size = zonefs_check_zone_condition(sb, z, zone); isize = i_size_read(inode); if (!(z->z_flags & (ZONEFS_ZONE_READONLY | ZONEFS_ZONE_OFFLINE)) && - !err->write && isize == data_size) - return 0; + !write && isize == data_size) + return; /* * At this point, we detected either a bad zone or an inconsistency @@ -291,7 +293,7 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, * In all cases, warn about inode size inconsistency and handle the * IO error according to the zone condition and to the mount options. */ - if (zonefs_zone_is_seq(z) && isize != data_size) + if (isize != data_size) zonefs_warn(sb, "inode %lu: invalid size %lld (should be %lld)\n", inode->i_ino, isize, data_size); @@ -351,8 +353,6 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, zonefs_i_size_write(inode, data_size); z->z_wpoffset = data_size; zonefs_inode_account_active(inode); - - return 0; } /* @@ -366,23 +366,25 @@ void __zonefs_io_error(struct inode *inode, bool write) { struct zonefs_zone *z = zonefs_inode_zone(inode); struct super_block *sb = inode->i_sb; - struct zonefs_sb_info *sbi = ZONEFS_SB(sb); unsigned int noio_flag; - unsigned int nr_zones = 1; - struct zonefs_ioerr_data err = { - .inode = inode, - .write = write, - }; + struct blk_zone zone; int ret; /* - * The only files that have more than one zone are conventional zone - * files with aggregated conventional zones, for which the inode zone - * size is always larger than the device zone size. + * Conventional zone have no write pointer and cannot become read-only + * or offline. So simply fake a report for a single or aggregated zone + * and let zonefs_handle_io_error() correct the zone inode information + * according to the mount options. */ - if (z->z_size > bdev_zone_sectors(sb->s_bdev)) - nr_zones = z->z_size >> - (sbi->s_zone_sectors_shift + SECTOR_SHIFT); + if (!zonefs_zone_is_seq(z)) { + zone.start = z->z_sector; + zone.len = z->z_size >> SECTOR_SHIFT; + zone.wp = zone.start + zone.len; + zone.type = BLK_ZONE_TYPE_CONVENTIONAL; + zone.cond = BLK_ZONE_COND_NOT_WP; + zone.capacity = zone.len; + goto handle_io_error; + } /* * Memory allocations in blkdev_report_zones() can trigger a memory @@ -393,12 +395,20 @@ void __zonefs_io_error(struct inode *inode, bool write) * the GFP_NOIO context avoids both problems. */ noio_flag = memalloc_noio_save(); - ret = blkdev_report_zones(sb->s_bdev, z->z_sector, nr_zones, - zonefs_io_error_cb, &err); - if (ret != nr_zones) + ret = blkdev_report_zones(sb->s_bdev, z->z_sector, 1, + zonefs_io_error_cb, &zone); + memalloc_noio_restore(noio_flag); + + if (ret != 1) { zonefs_err(sb, "Get inode %lu zone information failed %d\n", inode->i_ino, ret); - memalloc_noio_restore(noio_flag); + zonefs_warn(sb, "remounting filesystem read-only\n"); + sb->s_flags |= SB_RDONLY; + return; + } + +handle_io_error: + zonefs_handle_io_error(inode, &zone, write); } static struct kmem_cache *zonefs_inode_cachep; diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 7ad6f51b3d914e081876bf230c940a68a9a70fee..1d1f480a5e9e4d939cf32a77a75f75fbc2cd9aac 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -351,7 +351,6 @@ *(.ref.data) \ *(.data..shared_aligned) /* percpu related */ \ MEM_KEEP(init.data*) \ - MEM_KEEP(exit.data*) \ *(.data.unlikely) \ __start_once = .; \ *(.data.once) \ @@ -546,7 +545,6 @@ __init_rodata : AT(ADDR(__init_rodata) - LOAD_OFFSET) { \ *(.ref.rodata) \ MEM_KEEP(init.rodata) \ - MEM_KEEP(exit.rodata) \ } \ \ /* Built-in module parameters. */ \ @@ -601,7 +599,6 @@ *(.ref.text) \ *(.text.asan.* .text.tsan.*) \ MEM_KEEP(init.text*) \ - MEM_KEEP(exit.text*) \ /* sched.text is aling to function alignment to secure we have same @@ -751,13 +748,10 @@ *(.exit.data .exit.data.*) \ *(.fini_array .fini_array.*) \ *(.dtors .dtors.*) \ - MEM_DISCARD(exit.data*) \ - MEM_DISCARD(exit.rodata*) #define EXIT_TEXT \ *(.exit.text) \ *(.text.exit) \ - MEM_DISCARD(exit.text) #define EXIT_CALL \ *(.exitcall.exit) diff --git a/include/drm/drm_fixed.h b/include/drm/drm_fixed.h index 03cb890690e83cde0b3129de0451a8260d8ecb5d..a476a406e59977d2f4af0485be32398c62a5dccb 100644 --- a/include/drm/drm_fixed.h +++ b/include/drm/drm_fixed.h @@ -70,7 +70,6 @@ static inline u32 dfixed_div(fixed20_12 A, fixed20_12 B) } #define DRM_FIXED_POINT 32 -#define DRM_FIXED_POINT_HALF 16 #define DRM_FIXED_ONE (1ULL << DRM_FIXED_POINT) #define DRM_FIXED_DECIMAL_MASK (DRM_FIXED_ONE - 1) #define DRM_FIXED_DIGITS_MASK (~DRM_FIXED_DECIMAL_MASK) @@ -89,12 +88,12 @@ static inline int drm_fixp2int(s64 a) static inline int drm_fixp2int_round(s64 a) { - return drm_fixp2int(a + (1 << (DRM_FIXED_POINT_HALF - 1))); + return drm_fixp2int(a + DRM_FIXED_ONE / 2); } static inline int drm_fixp2int_ceil(s64 a) { - if (a > 0) + if (a >= 0) return drm_fixp2int(a + DRM_FIXED_ALMOST_ONE); else return drm_fixp2int(a - DRM_FIXED_ALMOST_ONE); diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h index fafa70ac1337f1bfdd28843c2b7f9a092e130bd5..6f19cf5c210e5d1029dd5c8af49e13dd934b1153 100644 --- a/include/drm/drm_modeset_helper_vtables.h +++ b/include/drm/drm_modeset_helper_vtables.h @@ -896,7 +896,8 @@ struct drm_connector_helper_funcs { * * RETURNS: * - * The number of modes added by calling drm_mode_probed_add(). + * The number of modes added by calling drm_mode_probed_add(). Return 0 + * on failures (no modes) instead of negative error codes. */ int (*get_modes)(struct drm_connector *connector); diff --git a/include/dt-bindings/clock/r8a779g0-cpg-mssr.h b/include/dt-bindings/clock/r8a779g0-cpg-mssr.h index 754c54a6eb06a46dafeeb030df71dc6b96c16866..7850cdc62e2854939627552c8c34be6ff8625563 100644 --- a/include/dt-bindings/clock/r8a779g0-cpg-mssr.h +++ b/include/dt-bindings/clock/r8a779g0-cpg-mssr.h @@ -86,5 +86,6 @@ #define R8A779G0_CLK_CPEX 74 #define R8A779G0_CLK_CBFUSA 75 #define R8A779G0_CLK_R 76 +#define R8A779G0_CLK_CP 77 #endif /* __DT_BINDINGS_CLOCK_R8A779G0_CPG_MSSR_H__ */ diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index 96b192139a23a57a1cbac7fcb9f037dcb4df45ba..6196b71c5eb58d8fe29752477b94693a8c2ca718 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -85,7 +85,7 @@ void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu); */ #define kvm_pmu_update_vcpu_events(vcpu) \ do { \ - if (!has_vhe() && kvm_vcpu_has_pmu(vcpu)) \ + if (!has_vhe() && kvm_arm_support_pmu_v3()) \ vcpu->arch.pmu.events = *kvm_get_pmu_events(); \ } while (0) diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index ca73940e26df83ddd65301b39b77c350b0f4c3c2..4195444ec45d153f8dfb9afdce1735aed95f809b 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -287,7 +287,12 @@ int __init xbc_init(const char *buf, size_t size, const char **emsg, int *epos); int __init xbc_get_info(int *node_size, size_t *data_size); /* XBC cleanup data structures */ -void __init xbc_exit(void); +void __init _xbc_exit(bool early); + +static inline void xbc_exit(void) +{ + _xbc_exit(false); +} /* XBC embedded bootconfig data in kernel */ #ifdef CONFIG_BOOT_CONFIG_EMBED diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c04a61ffac8ae90fd90affde2d16090c53f663a6..1ca1902af23e95731ab61c00117761f1ff2a9cea 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2739,10 +2739,18 @@ struct btf_id_set; bool btf_id_set_contains(const struct btf_id_set *set, u32 id); #define MAX_BPRINTF_VARARGS 12 +#define MAX_BPRINTF_BUF 1024 + +struct bpf_bprintf_data { + u32 *bin_args; + char *buf; + bool get_bin_args; + bool get_buf; +}; int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, - u32 **bin_buf, u32 num_args); -void bpf_bprintf_cleanup(void); + u32 num_args, struct bpf_bprintf_data *data); +void bpf_bprintf_cleanup(struct bpf_bprintf_data *data); /* the implementation of the opaque uapi struct bpf_dynptr */ struct bpf_dynptr_kern { diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 9e3dac51eb26b603ef45444309c3cb72e06cc125..d4dbaae8b5218abbc3ece85133ddd573d40d71a0 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -59,7 +59,7 @@ struct bvec_iter { unsigned int bi_bvec_done; /* number of bytes completed in current bvec */ -} __packed; +} __packed __aligned(4); struct bvec_iter_all { struct bio_vec bv; diff --git a/include/linux/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h index 4c3e0648dc2775b0b7bfb38e4e7695e445d6bfd4..fcc95bff72a571696b5890048c198ff07af39709 100644 --- a/include/linux/ceph/mdsmap.h +++ b/include/linux/ceph/mdsmap.h @@ -25,7 +25,11 @@ struct ceph_mdsmap { u32 m_session_timeout; /* seconds */ u32 m_session_autoclose; /* seconds */ u64 m_max_file_size; - u64 m_max_xattr_size; /* maximum size for xattrs blob */ + /* + * maximum size for xattrs blob. + * Zeroed by default to force the usage of the (sync) SETXATTR Op. + */ + u64 m_max_xattr_size; u32 m_max_mds; /* expected up:active mds number */ u32 m_num_active_mds; /* actual up:active mds number */ u32 possible_max_rank; /* possible max rank index */ diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h new file mode 100644 index 0000000000000000000000000000000000000000..53f1a7a932b08c223fe1d1ca5d36cc1f9131287a --- /dev/null +++ b/include/linux/cleanup.h @@ -0,0 +1,171 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_GUARDS_H +#define __LINUX_GUARDS_H + +#include + +/* + * DEFINE_FREE(name, type, free): + * simple helper macro that defines the required wrapper for a __free() + * based cleanup function. @free is an expression using '_T' to access + * the variable. + * + * __free(name): + * variable attribute to add a scoped based cleanup to the variable. + * + * no_free_ptr(var): + * like a non-atomic xchg(var, NULL), such that the cleanup function will + * be inhibited -- provided it sanely deals with a NULL value. + * + * return_ptr(p): + * returns p while inhibiting the __free(). + * + * Ex. + * + * DEFINE_FREE(kfree, void *, if (_T) kfree(_T)) + * + * struct obj *p __free(kfree) = kmalloc(...); + * if (!p) + * return NULL; + * + * if (!init_obj(p)) + * return NULL; + * + * return_ptr(p); + */ + +#define DEFINE_FREE(_name, _type, _free) \ + static inline void __free_##_name(void *p) { _type _T = *(_type *)p; _free; } + +#define __free(_name) __cleanup(__free_##_name) + +#define no_free_ptr(p) \ + ({ __auto_type __ptr = (p); (p) = NULL; __ptr; }) + +#define return_ptr(p) return no_free_ptr(p) + + +/* + * DEFINE_CLASS(name, type, exit, init, init_args...): + * helper to define the destructor and constructor for a type. + * @exit is an expression using '_T' -- similar to FREE above. + * @init is an expression in @init_args resulting in @type + * + * EXTEND_CLASS(name, ext, init, init_args...): + * extends class @name to @name@ext with the new constructor + * + * CLASS(name, var)(args...): + * declare the variable @var as an instance of the named class + * + * Ex. + * + * DEFINE_CLASS(fdget, struct fd, fdput(_T), fdget(fd), int fd) + * + * CLASS(fdget, f)(fd); + * if (!f.file) + * return -EBADF; + * + * // use 'f' without concern + */ + +#define DEFINE_CLASS(_name, _type, _exit, _init, _init_args...) \ +typedef _type class_##_name##_t; \ +static inline void class_##_name##_destructor(_type *p) \ +{ _type _T = *p; _exit; } \ +static inline _type class_##_name##_constructor(_init_args) \ +{ _type t = _init; return t; } + +#define EXTEND_CLASS(_name, ext, _init, _init_args...) \ +typedef class_##_name##_t class_##_name##ext##_t; \ +static inline void class_##_name##ext##_destructor(class_##_name##_t *p)\ +{ class_##_name##_destructor(p); } \ +static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \ +{ class_##_name##_t t = _init; return t; } + +#define CLASS(_name, var) \ + class_##_name##_t var __cleanup(class_##_name##_destructor) = \ + class_##_name##_constructor + + +/* + * DEFINE_GUARD(name, type, lock, unlock): + * trivial wrapper around DEFINE_CLASS() above specifically + * for locks. + * + * guard(name): + * an anonymous instance of the (guard) class + * + * scoped_guard (name, args...) { }: + * similar to CLASS(name, scope)(args), except the variable (with the + * explicit name 'scope') is declard in a for-loop such that its scope is + * bound to the next (compound) statement. + * + */ + +#define DEFINE_GUARD(_name, _type, _lock, _unlock) \ + DEFINE_CLASS(_name, _type, _unlock, ({ _lock; _T; }), _type _T) + +#define guard(_name) \ + CLASS(_name, __UNIQUE_ID(guard)) + +#define scoped_guard(_name, args...) \ + for (CLASS(_name, scope)(args), \ + *done = NULL; !done; done = (void *)1) + +/* + * Additional helper macros for generating lock guards with types, either for + * locks that don't have a native type (eg. RCU, preempt) or those that need a + * 'fat' pointer (eg. spin_lock_irqsave). + * + * DEFINE_LOCK_GUARD_0(name, lock, unlock, ...) + * DEFINE_LOCK_GUARD_1(name, type, lock, unlock, ...) + * + * will result in the following type: + * + * typedef struct { + * type *lock; // 'type := void' for the _0 variant + * __VA_ARGS__; + * } class_##name##_t; + * + * As above, both _lock and _unlock are statements, except this time '_T' will + * be a pointer to the above struct. + */ + +#define __DEFINE_UNLOCK_GUARD(_name, _type, _unlock, ...) \ +typedef struct { \ + _type *lock; \ + __VA_ARGS__; \ +} class_##_name##_t; \ + \ +static inline void class_##_name##_destructor(class_##_name##_t *_T) \ +{ \ + if (_T->lock) { _unlock; } \ +} + + +#define __DEFINE_LOCK_GUARD_1(_name, _type, _lock) \ +static inline class_##_name##_t class_##_name##_constructor(_type *l) \ +{ \ + class_##_name##_t _t = { .lock = l }, *_T = &_t; \ + _lock; \ + return _t; \ +} + +#define __DEFINE_LOCK_GUARD_0(_name, _lock) \ +static inline class_##_name##_t class_##_name##_constructor(void) \ +{ \ + class_##_name##_t _t = { .lock = (void*)1 }, \ + *_T __maybe_unused = &_t; \ + _lock; \ + return _t; \ +} + +#define DEFINE_LOCK_GUARD_1(_name, _type, _lock, _unlock, ...) \ +__DEFINE_UNLOCK_GUARD(_name, _type, _unlock, __VA_ARGS__) \ +__DEFINE_LOCK_GUARD_1(_name, _type, _lock) + +#define DEFINE_LOCK_GUARD_0(_name, _lock, _unlock, ...) \ +__DEFINE_UNLOCK_GUARD(_name, void, _unlock, __VA_ARGS__) \ +__DEFINE_LOCK_GUARD_0(_name, _lock) + +#endif /* __LINUX_GUARDS_H */ diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 6cfd6902bd5b92ec1a353a2aaa14da27f3932a43..9b673fefcef8a60b9911492060244bb929e25f12 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -5,6 +5,15 @@ /* Compiler specific definitions for Clang compiler */ +/* + * Clang prior to 17 is being silly and considers many __cleanup() variables + * as unused (because they are, their sole purpose is to go out of scope). + * + * https://reviews.llvm.org/D152180 + */ +#undef __cleanup +#define __cleanup(func) __maybe_unused __attribute__((__cleanup__(func))) + /* same as gcc, this was present in clang-2.6 so we can assume it works * with any version that can compile the kernel */ diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index f55a37efdb9748cda549a1b292db66972275bc26..149a520515e1deb0814ff418a3d117871bae7ffc 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -66,6 +66,26 @@ __builtin_unreachable(); \ } while (0) +/* + * GCC 'asm goto' with outputs miscompiles certain code sequences: + * + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921 + * + * Work around it via the same compiler barrier quirk that we used + * to use for the old 'asm goto' workaround. + * + * Also, always mark such 'asm goto' statements as volatile: all + * asm goto statements are supposed to be volatile as per the + * documentation, but some versions of gcc didn't actually do + * that for asms with outputs: + * + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619 + */ +#ifdef CONFIG_GCC_ASM_GOTO_OUTPUT_WORKAROUND +#define asm_goto_output(x...) \ + do { asm volatile goto(x); asm (""); } while (0) +#endif + #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 898b3458b24a00dbab43d2deaf89f567ef7939ec..ae4c9579ca5f01edc5f8cb3ab4dbc6924ca09ab8 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -75,6 +75,12 @@ # define __assume_aligned(a, ...) #endif +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-cleanup-variable-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#cleanup + */ +#define __cleanup(func) __attribute__((__cleanup__(func))) + /* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-cold-function-attribute * gcc: https://gcc.gnu.org/onlinedocs/gcc/Label-Attributes.html#index-cold-label-attribute diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index eb0466236661f51cb11d9c06416fc11eca35a950..8f50c589ad5f4b5e4215eb9e5a7ce4e0eb4608bc 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -226,6 +226,17 @@ struct ftrace_likely_data { # define __no_kcsan #endif +#ifdef __SANITIZE_MEMORY__ +/* + * Similarly to KASAN and KCSAN, KMSAN loses function attributes of inlined + * functions, therefore disabling KMSAN checks also requires disabling inlining. + * + * __no_sanitize_or_inline effectively prevents KMSAN from reporting errors + * within the function and marks all its outputs as initialized. + */ +# define __no_sanitize_or_inline __no_kmsan_checks notrace __maybe_unused +#endif + #ifndef __no_sanitize_or_inline #define __no_sanitize_or_inline __always_inline #endif @@ -284,8 +295,15 @@ struct ftrace_likely_data { # define __realloc_size(x, ...) #endif -#ifndef asm_volatile_goto -#define asm_volatile_goto(x...) asm goto(x) +/* + * Some versions of gcc do not mark 'asm goto' volatile: + * + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103979 + * + * We do it here by hand, because it doesn't hurt. + */ +#ifndef asm_goto_output +#define asm_goto_output(x...) asm volatile goto(x) #endif #ifdef CONFIG_CC_HAS_ASM_INLINE diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 008bfa68cfabc75ad301289a5a0bae7d6798de9f..4b06b1f1e267affcb146cb00f3ab6a3d1bbbb019 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -74,6 +74,8 @@ extern ssize_t cpu_show_spec_rstack_overflow(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_reg_file_data_sampling(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index d5595d57f4e53680a7e8b2a6e1bf6435a7c14501..9d208648c84d50d9ba3c2b7bda54b824a59f5783 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -1023,6 +1023,18 @@ static inline int cpufreq_table_find_index_c(struct cpufreq_policy *policy, efficiencies); } +static inline bool cpufreq_is_in_limits(struct cpufreq_policy *policy, int idx) +{ + unsigned int freq; + + if (idx < 0) + return false; + + freq = policy->freq_table[idx].frequency; + + return freq == clamp_val(freq, policy->min, policy->max); +} + static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) @@ -1056,7 +1068,8 @@ retry: return 0; } - if (idx < 0 && efficiencies) { + /* Limit frequency index to honor policy->min/max */ + if (!cpufreq_is_in_limits(policy, idx) && efficiencies) { efficiencies = false; goto retry; } diff --git a/include/linux/decompress/mm.h b/include/linux/decompress/mm.h index 9192986b1a7313234f467732cbb4a2bd6eb59252..ac862422df158bef7fe7ad287066668ea5b6c425 100644 --- a/include/linux/decompress/mm.h +++ b/include/linux/decompress/mm.h @@ -48,7 +48,7 @@ MALLOC_VISIBLE void *malloc(int size) if (!malloc_ptr) malloc_ptr = free_mem_ptr; - malloc_ptr = (malloc_ptr + 3) & ~3; /* Align */ + malloc_ptr = (malloc_ptr + 7) & ~7; /* Align */ p = (void *)malloc_ptr; malloc_ptr += size; diff --git a/include/linux/device.h b/include/linux/device.h index 7cf24330d681443bd2316137d1d30c5832ccc94a..f88b498ee9da4adda892a0f9f5b351c235455a89 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -30,6 +30,7 @@ #include #include #include +#include #include struct device; @@ -898,6 +899,9 @@ void device_unregister(struct device *dev); void device_initialize(struct device *dev); int __must_check device_add(struct device *dev); void device_del(struct device *dev); + +DEFINE_FREE(device_del, struct device *, if (_T) device_del(_T)) + int device_for_each_child(struct device *dev, void *data, int (*fn)(struct device *dev, void *data)); int device_for_each_child_reverse(struct device *dev, void *data, @@ -1071,6 +1075,9 @@ extern int (*platform_notify_remove)(struct device *dev); */ struct device *get_device(struct device *dev); void put_device(struct device *dev); + +DEFINE_FREE(put_device, struct device *, if (_T) put_device(_T)) + bool kill_device(struct device *dev); #ifdef CONFIG_DEVTMPFS @@ -1092,6 +1099,7 @@ void device_link_del(struct device_link *link); void device_link_remove(void *consumer, struct device *supplier); void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); +void device_link_wait_removal(void); extern __printf(3, 4) int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); diff --git a/include/linux/dm-io.h b/include/linux/dm-io.h index 92e7abfe04f9299fe2459696ddce861498f5baa9..70b3737052dd241f4241c357c5c09666e988fcb9 100644 --- a/include/linux/dm-io.h +++ b/include/linux/dm-io.h @@ -79,7 +79,8 @@ void dm_io_client_destroy(struct dm_io_client *client); * error occurred doing io to the corresponding region. */ int dm_io(struct dm_io_request *io_req, unsigned int num_regions, - struct dm_io_region *region, unsigned int long *sync_error_bits); + struct dm_io_region *region, unsigned int long *sync_error_bits, + unsigned short ioprio); #endif /* __KERNEL__ */ #endif /* _LINUX_DM_IO_H */ diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index c923f4e60f2401451909a195956edd35a4efb489..3576c6e89fea46487499119291fab999c987d074 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -954,7 +954,8 @@ static inline int dmaengine_slave_config(struct dma_chan *chan, static inline bool is_slave_direction(enum dma_transfer_direction direction) { - return (direction == DMA_MEM_TO_DEV) || (direction == DMA_DEV_TO_MEM); + return (direction == DMA_MEM_TO_DEV) || (direction == DMA_DEV_TO_MEM) || + (direction == DMA_DEV_TO_DEV); } static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_single( diff --git a/include/linux/efi.h b/include/linux/efi.h index 4e1bfee9675d2f91f22605f4d8b46c8bae8272ab..de6d6558a4d3068dfd54a119a98bdd42596c08a9 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -390,6 +390,7 @@ void efi_native_runtime_setup(void); #define EFI_RT_PROPERTIES_TABLE_GUID EFI_GUID(0xeb66918a, 0x7eef, 0x402a, 0x84, 0x2e, 0x93, 0x1d, 0x21, 0xc3, 0x8a, 0xe9) #define EFI_DXE_SERVICES_TABLE_GUID EFI_GUID(0x05ad34ba, 0x6f02, 0x4214, 0x95, 0x2e, 0x4d, 0xa0, 0x39, 0x8e, 0x2b, 0xb9) #define EFI_SMBIOS_PROTOCOL_GUID EFI_GUID(0x03583ff6, 0xcb36, 0x4940, 0x94, 0x7e, 0xb9, 0xb3, 0x9f, 0x4a, 0xfa, 0xf7) +#define EFI_MEMORY_ATTRIBUTE_PROTOCOL_GUID EFI_GUID(0xf4560cf6, 0x40ec, 0x4b4a, 0xa1, 0x92, 0xbf, 0x1d, 0x57, 0xd0, 0xb1, 0x89) #define EFI_IMAGE_SECURITY_DATABASE_GUID EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596, 0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f) #define EFI_SHIM_LOCK_GUID EFI_GUID(0x605dab50, 0xe046, 0x4300, 0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23) diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index a541f0c4f146c85724b73d2fb38b042bdc9d2154..d7eef2158667d919d7ecd4d5c47d73cd480fa90f 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -593,6 +593,31 @@ static inline void eth_hw_addr_gen(struct net_device *dev, const u8 *base_addr, eth_hw_addr_set(dev, addr); } +/** + * eth_skb_pkt_type - Assign packet type if destination address does not match + * @skb: Assigned a packet type if address does not match @dev address + * @dev: Network device used to compare packet address against + * + * If the destination MAC address of the packet does not match the network + * device address, assign an appropriate packet type. + */ +static inline void eth_skb_pkt_type(struct sk_buff *skb, + const struct net_device *dev) +{ + const struct ethhdr *eth = eth_hdr(skb); + + if (unlikely(!ether_addr_equal_64bits(eth->h_dest, dev->dev_addr))) { + if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) { + if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) + skb->pkt_type = PACKET_BROADCAST; + else + skb->pkt_type = PACKET_MULTICAST; + } else { + skb->pkt_type = PACKET_OTHERHOST; + } + } +} + /** * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame * @skb: Buffer to pad diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index fe848901fcc3acb04a732b82df95c86fbad93ddc..218fc5c54e901c727ac55da4b46668616e47e373 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -221,6 +221,7 @@ struct export_operations { #define EXPORT_OP_NOATOMIC_ATTR (0x10) /* Filesystem cannot supply atomic attribute updates */ +#define EXPORT_OP_FLUSH_ON_CLOSE (0x20) /* fs flushes file data on close */ unsigned long flags; }; diff --git a/include/linux/file.h b/include/linux/file.h index 39704eae83e27fdc8b099de6718f5f1392f4904c..6e9099d2934368d2aa41ffc30f4e438f8d42531d 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -10,6 +10,7 @@ #include #include #include +#include struct file; @@ -80,6 +81,8 @@ static inline void fdput_pos(struct fd f) fdput(f); } +DEFINE_CLASS(fd, struct fd, fdput(_T), fdget(fd), int fd) + extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); extern void set_close_on_exec(unsigned int fd, int flag); @@ -88,6 +91,9 @@ extern int __get_unused_fd_flags(unsigned flags, unsigned long nofile); extern int get_unused_fd_flags(unsigned flags); extern void put_unused_fd(unsigned int fd); +DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T), + get_unused_fd_flags(flags), unsigned flags) + extern void fd_install(unsigned int fd, struct file *file); extern int __receive_fd(struct file *file, int __user *ufd, diff --git a/include/linux/filter.h b/include/linux/filter.h index efc42a6e3aed0f6605827c5b879e1207fa616608..face590b24e17616eaa3aa22064c5e34bb2dccc2 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -495,24 +495,27 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) __BPF_MAP(n, __BPF_DECL_ARGS, __BPF_N, u64, __ur_1, u64, __ur_2, \ u64, __ur_3, u64, __ur_4, u64, __ur_5) -#define BPF_CALL_x(x, name, ...) \ +#define BPF_CALL_x(x, attr, name, ...) \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ typedef u64 (*btf_##name)(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ - u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ - u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ + attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ + attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ { \ return ((btf_##name)____##name)(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ } \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)) -#define BPF_CALL_0(name, ...) BPF_CALL_x(0, name, __VA_ARGS__) -#define BPF_CALL_1(name, ...) BPF_CALL_x(1, name, __VA_ARGS__) -#define BPF_CALL_2(name, ...) BPF_CALL_x(2, name, __VA_ARGS__) -#define BPF_CALL_3(name, ...) BPF_CALL_x(3, name, __VA_ARGS__) -#define BPF_CALL_4(name, ...) BPF_CALL_x(4, name, __VA_ARGS__) -#define BPF_CALL_5(name, ...) BPF_CALL_x(5, name, __VA_ARGS__) +#define __NOATTR +#define BPF_CALL_0(name, ...) BPF_CALL_x(0, __NOATTR, name, __VA_ARGS__) +#define BPF_CALL_1(name, ...) BPF_CALL_x(1, __NOATTR, name, __VA_ARGS__) +#define BPF_CALL_2(name, ...) BPF_CALL_x(2, __NOATTR, name, __VA_ARGS__) +#define BPF_CALL_3(name, ...) BPF_CALL_x(3, __NOATTR, name, __VA_ARGS__) +#define BPF_CALL_4(name, ...) BPF_CALL_x(4, __NOATTR, name, __VA_ARGS__) +#define BPF_CALL_5(name, ...) BPF_CALL_x(5, __NOATTR, name, __VA_ARGS__) + +#define NOTRACE_BPF_CALL_1(name, ...) BPF_CALL_x(1, notrace, name, __VA_ARGS__) #define bpf_ctx_range(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 diff --git a/include/linux/fs.h b/include/linux/fs.h index 4a1911dcf834b8fc548d1c733101caf38e7cab1a..092d8fa10153feab03024ac4b12ab918fa9c94da 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -337,6 +337,8 @@ enum rw_hint { #define IOCB_NOIO (1 << 20) /* can use bio alloc cache */ #define IOCB_ALLOC_CACHE (1 << 21) +/* kiocb is a read or write operation submitted by fs/aio.c. */ +#define IOCB_AIO_RW (1 << 23) struct kiocb { struct file *ki_filp; @@ -1187,6 +1189,13 @@ extern void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files); extern bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner); + +static inline struct file_lock_context * +locks_inode_context(const struct inode *inode) +{ + return smp_load_acquire(&inode->i_flctx); +} + #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) @@ -1332,6 +1341,13 @@ static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, { return false; } + +static inline struct file_lock_context * +locks_inode_context(const struct inode *inode) +{ + return NULL; +} + #endif /* !CONFIG_FILE_LOCKING */ static inline struct inode *file_inode(const struct file *f) diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 65a78773dccad281ed8a6e4b5fe881868fb5ff08..e2ccb47c42643d3af7108a79113c15d5ffa1cb36 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -341,6 +341,15 @@ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask); extern void pm_restrict_gfp_mask(void); extern void pm_restore_gfp_mask(void); +/* + * Check if the gfp flags allow compaction - GFP_NOIO is a really + * tricky context because the migration might require IO. + */ +static inline bool gfp_compaction_allowed(gfp_t gfp_mask) +{ + return IS_ENABLED(CONFIG_COMPACTION) && (gfp_mask & __GFP_IO); +} + extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma); #ifdef CONFIG_PM_SLEEP diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index d88c46ca82e17c343455a5fe064b63e861025dae..6811ab702e8dc621a364c2f63da6058513780249 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -2,6 +2,8 @@ #ifndef __LINUX_GFP_TYPES_H #define __LINUX_GFP_TYPES_H +#include + /* The typedef is in types.h but we want the documentation here */ #if 0 /** diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index f2044d5a652b5c6eed1652f2a7f1c23050d854a6..254d4a898179c0ad9c3a4b41a07b8e2ed9b1741b 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -197,6 +197,7 @@ enum hrtimer_base_type { * @max_hang_time: Maximum time spent in hrtimer_interrupt * @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are * expired + * @online: CPU is online from an hrtimers point of view * @timer_waiters: A hrtimer_cancel() invocation waits for the timer * callback to finish. * @expires_next: absolute time of the next event, is required for remote @@ -219,7 +220,8 @@ struct hrtimer_cpu_base { unsigned int hres_active : 1, in_hrtirq : 1, hang_detected : 1, - softirq_activated : 1; + softirq_activated : 1, + online : 1; #ifdef CONFIG_HIGH_RES_TIMERS unsigned int nr_events; unsigned short nr_retries; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 1c6f35ba1604f890029e30a18e1800af4697fd4d..37eeef9841c4ef7c53dfd725865c68c287f34be6 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -625,26 +625,50 @@ enum hugetlb_page_flags { */ #ifdef CONFIG_HUGETLB_PAGE #define TESTHPAGEFLAG(uname, flname) \ +static __always_inline \ +bool folio_test_hugetlb_##flname(struct folio *folio) \ + { void *private = &folio->private; \ + return test_bit(HPG_##flname, private); \ + } \ static inline int HPage##uname(struct page *page) \ { return test_bit(HPG_##flname, &(page->private)); } #define SETHPAGEFLAG(uname, flname) \ +static __always_inline \ +void folio_set_hugetlb_##flname(struct folio *folio) \ + { void *private = &folio->private; \ + set_bit(HPG_##flname, private); \ + } \ static inline void SetHPage##uname(struct page *page) \ { set_bit(HPG_##flname, &(page->private)); } #define CLEARHPAGEFLAG(uname, flname) \ +static __always_inline \ +void folio_clear_hugetlb_##flname(struct folio *folio) \ + { void *private = &folio->private; \ + clear_bit(HPG_##flname, private); \ + } \ static inline void ClearHPage##uname(struct page *page) \ { clear_bit(HPG_##flname, &(page->private)); } #else #define TESTHPAGEFLAG(uname, flname) \ +static inline bool \ +folio_test_hugetlb_##flname(struct folio *folio) \ + { return 0; } \ static inline int HPage##uname(struct page *page) \ { return 0; } #define SETHPAGEFLAG(uname, flname) \ +static inline void \ +folio_set_hugetlb_##flname(struct folio *folio) \ + { } \ static inline void SetHPage##uname(struct page *page) \ { } #define CLEARHPAGEFLAG(uname, flname) \ +static inline void \ +folio_clear_hugetlb_##flname(struct folio *folio) \ + { } \ static inline void ClearHPage##uname(struct page *page) \ { } #endif @@ -730,18 +754,29 @@ extern unsigned int default_hstate_idx; #define default_hstate (hstates[default_hstate_idx]) +static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio) +{ + return (void *)folio_get_private_1(folio); +} + /* * hugetlb page subpool pointer located in hpage[1].private */ static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage) { - return (void *)page_private(hpage + SUBPAGE_INDEX_SUBPOOL); + return hugetlb_folio_subpool(page_folio(hpage)); +} + +static inline void hugetlb_set_folio_subpool(struct folio *folio, + struct hugepage_subpool *subpool) +{ + folio_set_private_1(folio, (unsigned long)subpool); } static inline void hugetlb_set_page_subpool(struct page *hpage, struct hugepage_subpool *subpool) { - set_page_private(hpage + SUBPAGE_INDEX_SUBPOOL, (unsigned long)subpool); + hugetlb_set_folio_subpool(page_folio(hpage), subpool); } static inline struct hstate *hstate_file(struct file *f) @@ -828,10 +863,15 @@ static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, } #endif +static inline struct hstate *folio_hstate(struct folio *folio) +{ + VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio); + return size_to_hstate(folio_size(folio)); +} + static inline struct hstate *page_hstate(struct page *page) { - VM_BUG_ON_PAGE(!PageHuge(page), page); - return size_to_hstate(page_size(page)); + return folio_hstate(page_folio(page)); } static inline unsigned hstate_index_to_shift(unsigned index) @@ -1042,6 +1082,11 @@ static inline struct hstate *hstate_vma(struct vm_area_struct *vma) return NULL; } +static inline struct hstate *folio_hstate(struct folio *folio) +{ + return NULL; +} + static inline struct hstate *page_hstate(struct page *page) { return NULL; diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index 630cd255d0cfd443c7d2a25f7db79e7790b0ba31..241bf4fe701aec56204b364d2a917888a378bab0 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -67,54 +67,61 @@ struct hugetlb_cgroup { }; static inline struct hugetlb_cgroup * -__hugetlb_cgroup_from_page(struct page *page, bool rsvd) +__hugetlb_cgroup_from_folio(struct folio *folio, bool rsvd) { - VM_BUG_ON_PAGE(!PageHuge(page), page); + struct page *tail; - if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER) + VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio); + if (folio_order(folio) < HUGETLB_CGROUP_MIN_ORDER) return NULL; - if (rsvd) - return (void *)page_private(page + SUBPAGE_INDEX_CGROUP_RSVD); - else - return (void *)page_private(page + SUBPAGE_INDEX_CGROUP); + + if (rsvd) { + tail = folio_page(folio, SUBPAGE_INDEX_CGROUP_RSVD); + return (void *)page_private(tail); + } + + else { + tail = folio_page(folio, SUBPAGE_INDEX_CGROUP); + return (void *)page_private(tail); + } } -static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page) +static inline struct hugetlb_cgroup *hugetlb_cgroup_from_folio(struct folio *folio) { - return __hugetlb_cgroup_from_page(page, false); + return __hugetlb_cgroup_from_folio(folio, false); } static inline struct hugetlb_cgroup * -hugetlb_cgroup_from_page_rsvd(struct page *page) +hugetlb_cgroup_from_folio_rsvd(struct folio *folio) { - return __hugetlb_cgroup_from_page(page, true); + return __hugetlb_cgroup_from_folio(folio, true); } -static inline void __set_hugetlb_cgroup(struct page *page, +static inline void __set_hugetlb_cgroup(struct folio *folio, struct hugetlb_cgroup *h_cg, bool rsvd) { - VM_BUG_ON_PAGE(!PageHuge(page), page); + VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio); - if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER) + if (folio_order(folio) < HUGETLB_CGROUP_MIN_ORDER) return; if (rsvd) - set_page_private(page + SUBPAGE_INDEX_CGROUP_RSVD, + set_page_private(folio_page(folio, SUBPAGE_INDEX_CGROUP_RSVD), (unsigned long)h_cg); else - set_page_private(page + SUBPAGE_INDEX_CGROUP, + set_page_private(folio_page(folio, SUBPAGE_INDEX_CGROUP), (unsigned long)h_cg); } static inline void set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg) { - __set_hugetlb_cgroup(page, h_cg, false); + __set_hugetlb_cgroup(page_folio(page), h_cg, false); } static inline void set_hugetlb_cgroup_rsvd(struct page *page, struct hugetlb_cgroup *h_cg) { - __set_hugetlb_cgroup(page, h_cg, true); + __set_hugetlb_cgroup(page_folio(page), h_cg, true); } static inline bool hugetlb_cgroup_disabled(void) @@ -151,10 +158,10 @@ extern void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, extern void hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct page *page); -extern void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, - struct page *page); -extern void hugetlb_cgroup_uncharge_page_rsvd(int idx, unsigned long nr_pages, - struct page *page); +extern void hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages, + struct folio *folio); +extern void hugetlb_cgroup_uncharge_folio_rsvd(int idx, unsigned long nr_pages, + struct folio *folio); extern void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg); @@ -181,19 +188,13 @@ static inline void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, { } -static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page) +static inline struct hugetlb_cgroup *hugetlb_cgroup_from_folio(struct folio *folio) { return NULL; } static inline struct hugetlb_cgroup * -hugetlb_cgroup_from_page_resv(struct page *page) -{ - return NULL; -} - -static inline struct hugetlb_cgroup * -hugetlb_cgroup_from_page_rsvd(struct page *page) +hugetlb_cgroup_from_folio_rsvd(struct folio *folio) { return NULL; } @@ -253,14 +254,14 @@ hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages, { } -static inline void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, - struct page *page) +static inline void hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages, + struct folio *folio) { } -static inline void hugetlb_cgroup_uncharge_page_rsvd(int idx, +static inline void hugetlb_cgroup_uncharge_folio_rsvd(int idx, unsigned long nr_pages, - struct page *page) + struct folio *folio) { } static inline void hugetlb_cgroup_uncharge_cgroup(int idx, diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 646f1da9f27e0a948a426c85a9a6b25a715a5985..811d59cf891ba9a9ea3f24a415dabde41b58077b 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -164,8 +164,28 @@ struct hv_ring_buffer { u8 buffer[]; } __packed; + +/* + * If the requested ring buffer size is at least 8 times the size of the + * header, steal space from the ring buffer for the header. Otherwise, add + * space for the header so that is doesn't take too much of the ring buffer + * space. + * + * The factor of 8 is somewhat arbitrary. The goal is to prevent adding a + * relatively small header (4 Kbytes on x86) to a large-ish power-of-2 ring + * buffer size (such as 128 Kbytes) and so end up making a nearly twice as + * large allocation that will be almost half wasted. As a contrasting example, + * on ARM64 with 64 Kbyte page size, we don't want to take 64 Kbytes for the + * header from a 128 Kbyte allocation, leaving only 64 Kbytes for the ring. + * In this latter case, we must add 64 Kbytes for the header and not worry + * about what's wasted. + */ +#define VMBUS_HEADER_ADJ(payload_sz) \ + ((payload_sz) >= 8 * sizeof(struct hv_ring_buffer) ? \ + 0 : sizeof(struct hv_ring_buffer)) + /* Calculate the proper size of a ringbuffer, it must be page-aligned */ -#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(sizeof(struct hv_ring_buffer) + \ +#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(VMBUS_HEADER_ADJ(payload_sz) + \ (payload_sz)) struct hv_ring_buffer_info { @@ -812,6 +832,7 @@ struct vmbus_gpadl { u32 gpadl_handle; u32 size; void *buffer; + bool decrypted; }; struct vmbus_channel { diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index 7852f6c9a714c6fb7dc84321c4b416717b6d4666..719cf9cc6e1ac4db6abbd1171b1590716dc50dc9 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -8,6 +8,8 @@ #ifndef __AD_SIGMA_DELTA_H__ #define __AD_SIGMA_DELTA_H__ +#include + enum ad_sigma_delta_mode { AD_SD_MODE_CONTINUOUS = 0, AD_SD_MODE_SINGLE = 1, @@ -99,7 +101,7 @@ struct ad_sigma_delta { * 'rx_buf' is up to 32 bits per sample + 64 bit timestamp, * rounded to 16 bytes to take into account padding. */ - uint8_t tx_buf[4] ____cacheline_aligned; + uint8_t tx_buf[4] __aligned(IIO_DMA_MINALIGN); uint8_t rx_buf[16] __aligned(8); }; diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index db4a1b260348ced7bea58aff794b75288bfe045e..c34e648f07e28298f9d6577aface5b595cc5a122 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -261,9 +261,9 @@ struct st_sensor_data { bool hw_irq_trigger; s64 hw_timestamp; - char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] ____cacheline_aligned; - struct mutex odr_lock; + + char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] __aligned(IIO_DMA_MINALIGN); }; #ifdef CONFIG_IIO_BUFFER diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index bcbefb7574751f39b43cea767ca10af3bcc0a78b..af083aa0c43175dc8b57eaad908a415f81196b85 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -11,6 +11,7 @@ #include #include +#include #include #define ADIS_WRITE_REG(reg) ((0x80 | (reg))) @@ -131,7 +132,7 @@ struct adis { unsigned long irq_flag; void *buffer; - u8 tx[10] ____cacheline_aligned; + u8 tx[10] __aligned(IIO_DMA_MINALIGN); u8 rx[4]; }; diff --git a/include/linux/init.h b/include/linux/init.h index 077d7f93b402f4e36ad2ed9079f163c0ac7c6d45..c96aea3229ca195dd74968fd6fc2beddd6315889 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -87,9 +87,6 @@ __latent_entropy #define __meminitdata __section(".meminit.data") #define __meminitconst __section(".meminit.rodata") -#define __memexit __section(".memexit.text") __exitused __cold notrace -#define __memexitdata __section(".memexit.data") -#define __memexitconst __section(".memexit.rodata") /* For assembly routines */ #define __HEAD .section ".head.text","ax" diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index a1484cdb3158ed7be7a5c5b6a50ba37191bd4bfd..a8f3058448eaa1253fc0354baa834c360be0bcd6 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -42,11 +42,11 @@ void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2, unsigned issue_flags); void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, void (*task_work_cb)(struct io_uring_cmd *, unsigned)); -struct sock *io_uring_get_socket(struct file *file); void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); void io_uring_unreg_ringfd(void); const char *io_uring_get_opcode(u8 opcode); +bool io_is_uring_fops(struct file *file); static inline void io_uring_files_cancel(void) { @@ -71,6 +71,10 @@ static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, { return -EOPNOTSUPP; } +static inline bool io_is_uring_fops(struct file *file) +{ + return false; +} static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t ret2, unsigned issue_flags) { @@ -79,10 +83,6 @@ static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, void (*task_work_cb)(struct io_uring_cmd *, unsigned)) { } -static inline struct sock *io_uring_get_socket(struct file *file) -{ - return NULL; -} static inline void io_uring_task_cancel(void) { } diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index f5b687a787a34de90fcdb0219c26ba20adb0a31e..37aeea266ebb32e9f37cf6f0b5c65216c0b042c8 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -330,9 +330,6 @@ struct io_ring_ctx { struct list_head io_buffers_pages; - #if defined(CONFIG_UNIX) - struct socket *ring_sock; - #endif /* hashed buffered write serialization */ struct io_wq_hash *hash_map; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 238a03087e17e333543710d74d22f912bfa41a7f..0983dfc9a203c39572d33320210d15f3f21cf138 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -49,26 +49,35 @@ struct vm_fault; * * IOMAP_F_BUFFER_HEAD indicates that the file system requires the use of * buffer heads for this mapping. + * + * IOMAP_F_XATTR indicates that the iomap is for an extended attribute extent + * rather than a file data extent. */ -#define IOMAP_F_NEW 0x01 -#define IOMAP_F_DIRTY 0x02 -#define IOMAP_F_SHARED 0x04 -#define IOMAP_F_MERGED 0x08 -#define IOMAP_F_BUFFER_HEAD 0x10 -#define IOMAP_F_ZONE_APPEND 0x20 +#define IOMAP_F_NEW (1U << 0) +#define IOMAP_F_DIRTY (1U << 1) +#define IOMAP_F_SHARED (1U << 2) +#define IOMAP_F_MERGED (1U << 3) +#define IOMAP_F_BUFFER_HEAD (1U << 4) +#define IOMAP_F_ZONE_APPEND (1U << 5) +#define IOMAP_F_XATTR (1U << 6) /* * Flags set by the core iomap code during operations: * * IOMAP_F_SIZE_CHANGED indicates to the iomap_end method that the file size * has changed as the result of this write operation. + * + * IOMAP_F_STALE indicates that the iomap is not valid any longer and the file + * range it covers needs to be remapped by the high level before the operation + * can proceed. */ -#define IOMAP_F_SIZE_CHANGED 0x100 +#define IOMAP_F_SIZE_CHANGED (1U << 8) +#define IOMAP_F_STALE (1U << 9) /* * Flags from 0x1000 up are for file system specific usage: */ -#define IOMAP_F_PRIVATE 0x1000 +#define IOMAP_F_PRIVATE (1U << 12) /* @@ -89,6 +98,7 @@ struct iomap { void *inline_data; void *private; /* filesystem private */ const struct iomap_page_ops *page_ops; + u64 validity_cookie; /* used with .iomap_valid() */ }; static inline sector_t iomap_sector(const struct iomap *iomap, loff_t pos) @@ -128,6 +138,23 @@ struct iomap_page_ops { int (*page_prepare)(struct inode *inode, loff_t pos, unsigned len); void (*page_done)(struct inode *inode, loff_t pos, unsigned copied, struct page *page); + + /* + * Check that the cached iomap still maps correctly to the filesystem's + * internal extent map. FS internal extent maps can change while iomap + * is iterating a cached iomap, so this hook allows iomap to detect that + * the iomap needs to be refreshed during a long running write + * operation. + * + * The filesystem can store internal state (e.g. a sequence number) in + * iomap->validity_cookie when the iomap is first mapped to be able to + * detect changes between mapping time and whenever .iomap_valid() is + * called. + * + * This is called with the folio over the specified file position held + * locked by the iomap code. + */ + bool (*iomap_valid)(struct inode *inode, const struct iomap *iomap); }; /* @@ -226,6 +253,10 @@ static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i) ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops); +int iomap_file_buffered_write_punch_delalloc(struct inode *inode, + struct iomap *iomap, loff_t pos, loff_t length, ssize_t written, + int (*punch)(struct inode *inode, loff_t pos, loff_t length)); + int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops); void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count); diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 5ec0fa71399e47e526265fe2c11ef52ad6088e80..2e09c269bf9d8e5237ac8fd86f8c5d65d944dc43 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -13,6 +13,7 @@ #define _LINUX_TRACE_IRQFLAGS_H #include +#include #include #include @@ -125,7 +126,7 @@ do { \ # define lockdep_softirq_enter() do { } while (0) # define lockdep_softirq_exit() do { } while (0) # define lockdep_hrtimer_enter(__hrtimer) false -# define lockdep_hrtimer_exit(__context) do { } while (0) +# define lockdep_hrtimer_exit(__context) do { (void)(__context); } while (0) # define lockdep_posixtimer_enter() do { } while (0) # define lockdep_posixtimer_exit() do { } while (0) # define lockdep_irq_work_enter(__work) do { } while (0) @@ -267,4 +268,10 @@ extern void warn_bogus_irq_restore(void); #define irqs_disabled_flags(flags) raw_irqs_disabled_flags(flags) +DEFINE_LOCK_GUARD_0(irq, local_irq_disable(), local_irq_enable()) +DEFINE_LOCK_GUARD_0(irqsave, + local_irq_save(_T->flags), + local_irq_restore(_T->flags), + unsigned long flags) + #endif diff --git a/include/linux/libata.h b/include/linux/libata.h index 45910aebc3778dfd0518f851f74fde29f63a79f2..6645259be1438d385386141f41691c210a0d094c 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -102,6 +102,7 @@ enum { ATA_DFLAG_NCQ_SEND_RECV = (1 << 19), /* device supports NCQ SEND and RECV */ ATA_DFLAG_NCQ_PRIO = (1 << 20), /* device supports NCQ priority */ ATA_DFLAG_NCQ_PRIO_ENABLED = (1 << 21), /* Priority cmds sent to dev */ + ATA_DFLAG_RESUMING = (1 << 22), /* Device is resuming */ ATA_DFLAG_INIT_MASK = (1 << 24) - 1, ATA_DFLAG_DETACH = (1 << 24), diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 50ad19662a322b8df1cc80d11161d7b4e6e7e506..6790f08066b7243c5c1010eeccf635b642337967 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -118,6 +118,8 @@ int memblock_reserve(phys_addr_t base, phys_addr_t size); int memblock_physmem_add(phys_addr_t base, phys_addr_t size); #endif void memblock_trim_memory(phys_addr_t align); +unsigned long memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, + phys_addr_t base2, phys_addr_t size2); bool memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size); int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size); diff --git a/include/linux/minmax.h b/include/linux/minmax.h index 5433c08fcc685856798e833202c74b44330ce479..1aea34b8f19bf951defedd114cc4f0405daaed48 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -51,6 +51,23 @@ */ #define max(x, y) __careful_cmp(x, y, >) +/** + * umin - return minimum of two non-negative values + * Signed types are zero extended to match a larger unsigned type. + * @x: first value + * @y: second value + */ +#define umin(x, y) \ + __careful_cmp((x) + 0u + 0ul + 0ull, (y) + 0u + 0ul + 0ull, <) + +/** + * umax - return maximum of two non-negative values + * @x: first value + * @y: second value + */ +#define umax(x, y) \ + __careful_cmp((x) + 0u + 0ul + 0ull, (y) + 0u + 0ul + 0ull, >) + /** * min3 - return minimum of three values * @x: first value diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 4657d5c54abefcc58a480c28b34420ad702d31e3..ca0eee571ad7b77b3949e30103cc6d777434fee2 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -269,7 +269,10 @@ struct mlx5_wqe_eth_seg { union { struct { __be16 sz; - u8 start[2]; + union { + u8 start[2]; + DECLARE_FLEX_ARRAY(u8, data); + }; } inline_hdr; struct { __be16 type; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 247aedb18d5c389cf0fb9f539e8b8cc8fbfa607b..a9c1d611029d147812b97daeb1cf4126a9509887 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -144,6 +144,7 @@ struct page { atomic_t compound_pincount; #ifdef CONFIG_64BIT unsigned int compound_nr; /* 1 << compound_order */ + unsigned long _private_1; #endif }; struct { /* Second tail page of compound page */ @@ -264,6 +265,7 @@ struct page { * @_total_mapcount: Do not use directly, call folio_entire_mapcount(). * @_pincount: Do not use directly, call folio_maybe_dma_pinned(). * @_folio_nr_pages: Do not use directly, call folio_nr_pages(). + * @_private_1: Do not use directly, call folio_get_private_1(). * * A folio is a physically, virtually and logically contiguous set * of bytes. It is a power-of-two in size, and it is aligned to that @@ -311,6 +313,7 @@ struct folio { #ifdef CONFIG_64BIT unsigned int _folio_nr_pages; #endif + unsigned long _private_1; }; #define FOLIO_MATCH(pg, fl) \ @@ -338,6 +341,7 @@ FOLIO_MATCH(compound_mapcount, _total_mapcount); FOLIO_MATCH(compound_pincount, _pincount); #ifdef CONFIG_64BIT FOLIO_MATCH(compound_nr, _folio_nr_pages); +FOLIO_MATCH(_private_1, _private_1); #endif #undef FOLIO_MATCH @@ -383,6 +387,16 @@ static inline void *folio_get_private(struct folio *folio) return folio->private; } +static inline void folio_set_private_1(struct folio *folio, unsigned long private) +{ + folio->_private_1 = private; +} + +static inline unsigned long folio_get_private_1(struct folio *folio) +{ + return folio->_private_1; +} + struct page_frag_cache { void * va; #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 74f9d9a6d33076dc6c000b32b123355c745896ab..0e4ef9c5127ad23a6894e8c4a84afe53bc586c25 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -102,6 +102,7 @@ #define SDIO_DEVICE_ID_MARVELL_8977_BT 0x9146 #define SDIO_DEVICE_ID_MARVELL_8987_WLAN 0x9149 #define SDIO_DEVICE_ID_MARVELL_8987_BT 0x914a +#define SDIO_DEVICE_ID_MARVELL_8978_WLAN 0x9159 #define SDIO_VENDOR_ID_MEDIATEK 0x037a #define SDIO_DEVICE_ID_MEDIATEK_MT7663 0x7663 diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 1322652a9d0d98a91a96d52779fb26fc17ebdeac..7dc186ec52a2931a8b876ee07b0797bc4b143d83 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -95,6 +95,14 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod); +#ifdef CONFIG_MODULES +void flush_module_init_free_work(void); +#else +static inline void flush_module_init_free_work(void) +{ +} +#endif + /* Any cleanup needed when module leaves. */ void module_arch_cleanup(struct module *mod); diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 8f226d460f51c84c8970fe0223ee8c2a284e21ea..a33aa9eb9fc3b0154b97096e4a5bcdea2a91fef0 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -19,6 +19,7 @@ #include #include #include +#include #ifdef CONFIG_DEBUG_LOCK_ALLOC # define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ @@ -219,4 +220,7 @@ extern void mutex_unlock(struct mutex *lock); extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); +DEFINE_GUARD(mutex, struct mutex *, mutex_lock(_T), mutex_unlock(_T)) +DEFINE_FREE(mutex, struct mutex *, if (_T) mutex_unlock(_T)) + #endif /* __LINUX_MUTEX_H */ diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index bef8db9d6c0859e3b96fca75fcac7c84b65e91e3..e5f4b6f8d1c097dc5c38dc225b4e8ab79273a4c7 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -437,11 +437,13 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) #include void nf_ct_attach(struct sk_buff *, const struct sk_buff *); +void nf_ct_set_closing(struct nf_conntrack *nfct); struct nf_conntrack_tuple; bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb); #else static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} +static inline void nf_ct_set_closing(struct nf_conntrack *nfct) {} struct nf_conntrack_tuple; static inline bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb) @@ -459,6 +461,8 @@ struct nf_ct_hook { bool (*get_tuple_skb)(struct nf_conntrack_tuple *, const struct sk_buff *); void (*attach)(struct sk_buff *nskb, const struct sk_buff *skb); + void (*set_closing)(struct nf_conntrack *nfct); + int (*confirm)(struct sk_buff *skb); }; extern const struct nf_ct_hook __rcu *nf_ct_hook; diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 72f5ebc5c97a9f17ca4cf8dcdd87891b42462107..0b217d4ae2a48edd9ebaec4a51472f6263dc0c0f 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -186,6 +186,8 @@ struct ip_set_type_variant { /* Return true if "b" set is the same as "a" * according to the create set parameters */ bool (*same_set)(const struct ip_set *a, const struct ip_set *b); + /* Cancel ongoing garbage collectors before destroying the set*/ + void (*cancel_gc)(struct ip_set *set); /* Region-locking is used */ bool region_lock; }; @@ -242,6 +244,8 @@ extern void ip_set_type_unregister(struct ip_set_type *set_type); /* A generic IP set */ struct ip_set { + /* For call_cru in destroy */ + struct rcu_head rcu; /* The name of the set */ char name[IPSET_MAXNAMELEN]; /* Lock protecting the set data */ diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 8d04b6a5964c4a67e5832286a7a638732cc5494d..730003c4f4af4c1147481534c7b4ce3e889f339e 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -732,4 +732,17 @@ enum nfs4_setxattr_options { SETXATTR4_CREATE = 1, SETXATTR4_REPLACE = 2, }; + +enum { + RCA4_TYPE_MASK_RDATA_DLG = 0, + RCA4_TYPE_MASK_WDATA_DLG = 1, + RCA4_TYPE_MASK_DIR_DLG = 2, + RCA4_TYPE_MASK_FILE_LAYOUT = 3, + RCA4_TYPE_MASK_BLK_LAYOUT = 4, + RCA4_TYPE_MASK_OBJ_LAYOUT_MIN = 8, + RCA4_TYPE_MASK_OBJ_LAYOUT_MAX = 9, + RCA4_TYPE_MASK_OTHER_LAYOUT_MIN = 12, + RCA4_TYPE_MASK_OTHER_LAYOUT_MAX = 15, +}; + #endif diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 7931fa47256129e26422531be56b65ec4fb39c50..ac7d799d9d3871c01c1a8aff1722c29a978b86df 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -582,6 +582,7 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(void); extern void nfs_commit_free(struct nfs_commit_data *data); +void nfs_commit_begin(struct nfs_mds_commit_info *cinfo); bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); static inline bool nfs_have_writebacks(const struct inode *inode) diff --git a/include/linux/pci.h b/include/linux/pci.h index eccaf1abea79dc28c8f26b1e1df25921fc17012f..4da7411da9baf5dcaa79d3ebc15d8adba171c88e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1383,6 +1383,7 @@ int pci_load_and_free_saved_state(struct pci_dev *dev, struct pci_saved_state **state); int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state); int pci_set_power_state(struct pci_dev *dev, pci_power_t state); +int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state); pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state); bool pci_pme_capable(struct pci_dev *dev, pci_power_t state); void pci_pme_active(struct pci_dev *dev, bool enable); @@ -1553,6 +1554,8 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata); +void pci_walk_bus_locked(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), + void *userdata); int pci_cfg_space_size(struct pci_dev *dev); unsigned char pci_bus_max_busnr(struct pci_bus *bus); void pci_setup_bridge(struct pci_bus *bus); @@ -1884,6 +1887,8 @@ static inline int pci_save_state(struct pci_dev *dev) { return 0; } static inline void pci_restore_state(struct pci_dev *dev) { } static inline int pci_set_power_state(struct pci_dev *dev, pci_power_t state) { return 0; } +static inline int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state) +{ return 0; } static inline int pci_wake_from_d3(struct pci_dev *dev, bool enable) { return 0; } static inline pci_power_t pci_choose_state(struct pci_dev *dev, @@ -2355,6 +2360,11 @@ static inline struct pci_dev *pcie_find_root_port(struct pci_dev *dev) return NULL; } +static inline bool pci_dev_is_disconnected(const struct pci_dev *dev) +{ + return dev->error_state == pci_channel_io_perm_failure; +} + void pci_request_acs(void); bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags); bool pci_acs_path_enabled(struct pci_dev *start, diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 73cc1e7dd15adb57b4a0e4518fed9e460e2b6105..2c1371320c29552f8cfb3585a61b39b17025e32c 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -158,6 +158,8 @@ #define PCI_VENDOR_ID_LOONGSON 0x0014 +#define PCI_VENDOR_ID_SOLIDIGM 0x025e + #define PCI_VENDOR_ID_TTTECH 0x0357 #define PCI_DEVICE_ID_TTTECH_MC322 0x000a @@ -2662,7 +2664,9 @@ #define PCI_DEVICE_ID_INTEL_QUARK_X1000_ILB 0x095e #define PCI_DEVICE_ID_INTEL_I960 0x0960 #define PCI_DEVICE_ID_INTEL_I960RM 0x0962 +#define PCI_DEVICE_ID_INTEL_DSA_SPR0 0x0b25 #define PCI_DEVICE_ID_INTEL_CENTERTON_ILB 0x0c60 +#define PCI_DEVICE_ID_INTEL_IAX_SPR0 0x0cfe #define PCI_DEVICE_ID_INTEL_8257X_SOL 0x1062 #define PCI_DEVICE_ID_INTEL_82573E_SOL 0x1085 #define PCI_DEVICE_ID_INTEL_82573L_SOL 0x108f diff --git a/include/linux/percpu.h b/include/linux/percpu.h index f1ec5ad1351cc1cb2a408848c8e4ad32035ff7bf..ba00a49369caec7c2753bd1b9105a732b06ab3d9 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -8,6 +8,7 @@ #include #include #include +#include #include @@ -128,6 +129,9 @@ extern void __init setup_per_cpu_areas(void); extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp) __alloc_size(1); extern void __percpu *__alloc_percpu(size_t size, size_t align) __alloc_size(1); extern void free_percpu(void __percpu *__pdata); + +DEFINE_FREE(free_percpu, void __percpu *, free_percpu(_T)) + extern phys_addr_t per_cpu_ptr_to_phys(void *addr); #define alloc_percpu_gfp(type, gfp) \ diff --git a/include/linux/phy/tegra/xusb.h b/include/linux/phy/tegra/xusb.h index 70998e6dd6fdc9ea5665d8e01615709b042d6b69..6ca51e0080ec092eeadfda3d55f1ef551f1f7262 100644 --- a/include/linux/phy/tegra/xusb.h +++ b/include/linux/phy/tegra/xusb.h @@ -26,6 +26,7 @@ void tegra_phy_xusb_utmi_pad_power_down(struct phy *phy); int tegra_phy_xusb_utmi_port_reset(struct phy *phy); int tegra_xusb_padctl_get_usb3_companion(struct tegra_xusb_padctl *padctl, unsigned int port); +int tegra_xusb_padctl_get_port_number(struct phy *phy); int tegra_xusb_padctl_enable_phy_sleepwalk(struct tegra_xusb_padctl *padctl, struct phy *phy, enum usb_device_speed speed); int tegra_xusb_padctl_disable_phy_sleepwalk(struct tegra_xusb_padctl *padctl, struct phy *phy); diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h index 487117ccb1bc26713a11147bf6d623df6145825a..fb25085d092244a175dccb5365e4d78d137caf79 100644 --- a/include/linux/pinctrl/pinctrl.h +++ b/include/linux/pinctrl/pinctrl.h @@ -206,6 +206,26 @@ extern int pinctrl_get_group_pins(struct pinctrl_dev *pctldev, const char *pin_group, const unsigned **pins, unsigned *num_pins); +/** + * struct pinfunction - Description about a function + * @name: Name of the function + * @groups: An array of groups for this function + * @ngroups: Number of groups in @groups + */ +struct pinfunction { + const char *name; + const char * const *groups; + size_t ngroups; +}; + +/* Convenience macro to define a single named pinfunction */ +#define PINCTRL_PINFUNCTION(_name, _groups, _ngroups) \ +(struct pinfunction) { \ + .name = (_name), \ + .groups = (_groups), \ + .ngroups = (_ngroups), \ + } + #if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_PINCTRL) extern struct pinctrl_dev *of_pinctrl_get(struct device_node *np); #else diff --git a/include/linux/poll.h b/include/linux/poll.h index a9e0e1c2d1f2ff89d99a9377a1de7d0dc78483cd..d1ea4f3714a8485677e89a4c6c07a657e53a15ca 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -14,11 +14,7 @@ /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating additional memory. */ -#ifdef __clang__ -#define MAX_STACK_ALLOC 768 -#else #define MAX_STACK_ALLOC 832 -#endif #define FRONTEND_STACK_ALLOC 256 #define SELECT_STACK_ALLOC FRONTEND_STACK_ALLOC #define POLL_STACK_ALLOC FRONTEND_STACK_ALLOC diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 8cfcc5d454512f8c160c6ab09b2ad1000bf84bb1..9aa6358a1a16b4b2670034165da2c184d48ff476 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -8,6 +8,7 @@ */ #include +#include #include /* @@ -474,4 +475,8 @@ static __always_inline void preempt_enable_nested(void) preempt_enable(); } +DEFINE_LOCK_GUARD_0(preempt, preempt_disable(), preempt_enable()) +DEFINE_LOCK_GUARD_0(preempt_notrace, preempt_disable_notrace(), preempt_enable_notrace()) +DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable()) + #endif /* __LINUX_PREEMPT_H */ diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h index 5d868505a94e43fe4f6124915e90dc814c269278..6d92b68efbf6c3afe86b9f6c22a8759ce51e7a28 100644 --- a/include/linux/randomize_kstack.h +++ b/include/linux/randomize_kstack.h @@ -80,7 +80,7 @@ DECLARE_PER_CPU(u32, kstack_offset); if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \ &randomize_kstack_offset)) { \ u32 offset = raw_cpu_read(kstack_offset); \ - offset ^= (rand); \ + offset = ror32(offset, 5) ^ (rand); \ raw_cpu_write(kstack_offset, offset); \ } \ } while (0) diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 46bd9a331fd5d377cc72787619bc00a747303bbc..6858cae98da9e8b7bdcc1df97b63cdb250181027 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -204,9 +205,9 @@ void rcu_tasks_trace_qs_blkd(struct task_struct *t); do { \ int ___rttq_nesting = READ_ONCE((t)->trc_reader_nesting); \ \ - if (likely(!READ_ONCE((t)->trc_reader_special.b.need_qs)) && \ + if (unlikely(READ_ONCE((t)->trc_reader_special.b.need_qs) == TRC_NEED_QS) && \ likely(!___rttq_nesting)) { \ - rcu_trc_cmpxchg_need_qs((t), 0, TRC_NEED_QS_CHECKED); \ + rcu_trc_cmpxchg_need_qs((t), TRC_NEED_QS, TRC_NEED_QS_CHECKED); \ } else if (___rttq_nesting && ___rttq_nesting != INT_MIN && \ !READ_ONCE((t)->trc_reader_special.b.blocked)) { \ rcu_tasks_trace_qs_blkd(t); \ @@ -267,6 +268,37 @@ do { \ cond_resched(); \ } while (0) +/** + * rcu_softirq_qs_periodic - Report RCU and RCU-Tasks quiescent states + * @old_ts: jiffies at start of processing. + * + * This helper is for long-running softirq handlers, such as NAPI threads in + * networking. The caller should initialize the variable passed in as @old_ts + * at the beginning of the softirq handler. When invoked frequently, this macro + * will invoke rcu_softirq_qs() every 100 milliseconds thereafter, which will + * provide both RCU and RCU-Tasks quiescent states. Note that this macro + * modifies its old_ts argument. + * + * Because regions of code that have disabled softirq act as RCU read-side + * critical sections, this macro should be invoked with softirq (and + * preemption) enabled. + * + * The macro is not needed when CONFIG_PREEMPT_RT is defined. RT kernels would + * have more chance to invoke schedule() calls and provide necessary quiescent + * states. As a contrast, calling cond_resched() only won't achieve the same + * effect because cond_resched() does not provide RCU-Tasks quiescent states. + */ +#define rcu_softirq_qs_periodic(old_ts) \ +do { \ + if (!IS_ENABLED(CONFIG_PREEMPT_RT) && \ + time_after(jiffies, (old_ts) + HZ / 10)) { \ + preempt_disable(); \ + rcu_softirq_qs(); \ + preempt_enable(); \ + (old_ts) = jiffies; \ + } \ +} while (0) + /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. @@ -1077,4 +1109,6 @@ rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) extern int rcu_expedited; extern int rcu_normal; +DEFINE_LOCK_GUARD_0(rcu, rcu_read_lock(), rcu_read_unlock()) + #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index ee3b4a0146119809e17476e7a30c62b7763125ea..a9ca87a8f4e616a0d0234155e69ea2c93cc86361 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -361,13 +361,13 @@ devm_regulator_get_exclusive(struct device *dev, const char *id) static inline int devm_regulator_get_enable(struct device *dev, const char *id) { - return -ENODEV; + return 0; } static inline int devm_regulator_get_enable_optional(struct device *dev, const char *id) { - return -ENODEV; + return 0; } static inline struct regulator *__must_check diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 3c7d295746f67e050d6b9296204ec56d7892ff72..3e7bfc0f65aee25a4e24dc362701f16b3289ff5a 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -98,6 +98,7 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k __ring_buffer_alloc((size), (flags), &__key); \ }) +typedef bool (*ring_buffer_cond_fn)(void *data); int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full); __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table, int full); diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index efa5c324369a2d752b4147f4e33642527a61df6b..1dd530ce8b45b9a7aa3934272b229360d2eee3ef 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -15,6 +15,7 @@ #include #include #include +#include #ifdef CONFIG_DEBUG_LOCK_ALLOC # define __RWSEM_DEP_MAP_INIT(lockname) \ @@ -201,6 +202,13 @@ extern void up_read(struct rw_semaphore *sem); */ extern void up_write(struct rw_semaphore *sem); +DEFINE_GUARD(rwsem_read, struct rw_semaphore *, down_read(_T), up_read(_T)) +DEFINE_GUARD(rwsem_write, struct rw_semaphore *, down_write(_T), up_write(_T)) + +DEFINE_FREE(up_read, struct rw_semaphore *, if (_T) up_read(_T)) +DEFINE_FREE(up_write, struct rw_semaphore *, if (_T) up_write(_T)) + + /* * downgrade write lock to read lock */ diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 7291fb6399d2a01447067891ac1450215f684adc..aaa25ed1a8fe05a45a96ba83e0547834542d249f 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -145,6 +145,8 @@ static inline void put_task_struct(struct task_struct *t) __put_task_struct(t); } +DEFINE_FREE(put_task, struct task_struct *, if (_T) put_task_struct(_T)) + static inline void put_task_struct_many(struct task_struct *t, int nr) { if (refcount_sub_and_test(nr, &t->usage)) diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h index 988528b5da438fa2e96f4166446361ee58958e02..48ffe325184c029899f74a4786903706214a3586 100644 --- a/include/linux/secretmem.h +++ b/include/linux/secretmem.h @@ -14,10 +14,10 @@ static inline bool page_is_secretmem(struct page *page) * Using page_mapping() is quite slow because of the actual call * instruction and repeated compound_head(page) inside the * page_mapping() function. - * We know that secretmem pages are not compound and LRU so we can + * We know that secretmem pages are not compound, so we can * save a couple of cycles here. */ - if (PageCompound(page) || !PageLRU(page)) + if (PageCompound(page)) return false; mapping = (struct address_space *) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c30d419ebf545746d58c1fad31a422e39ee224b6..cecd3b6bebb8bbc65891242f787e2877ad8713ae 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -745,8 +745,6 @@ typedef unsigned char *sk_buff_data_t; * @list: queue head * @ll_node: anchor in an llist (eg socket defer_list) * @sk: Socket we are owned by - * @ip_defrag_offset: (aka @sk) alternate use of @sk, used in - * fragmentation management * @dev: Device we arrived on/are leaving by * @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL * @cb: Control buffer. Free for use by every layer. Put private vars here @@ -870,10 +868,7 @@ struct sk_buff { struct llist_node ll_node; }; - union { - struct sock *sk; - int ip_defrag_offset; - }; + struct sock *sk; union { ktime_t tstamp; @@ -2608,6 +2603,8 @@ static inline void skb_put_u8(struct sk_buff *skb, u8 val) void *skb_push(struct sk_buff *skb, unsigned int len); static inline void *__skb_push(struct sk_buff *skb, unsigned int len) { + DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); + skb->data -= len; skb->len += len; return skb->data; @@ -2616,6 +2613,8 @@ static inline void *__skb_push(struct sk_buff *skb, unsigned int len) void *skb_pull(struct sk_buff *skb, unsigned int len); static inline void *__skb_pull(struct sk_buff *skb, unsigned int len) { + DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); + skb->len -= len; if (unlikely(skb->len < skb->data_len)) { #if defined(CONFIG_DEBUG_NET) @@ -2639,6 +2638,8 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta); static inline bool pskb_may_pull(struct sk_buff *skb, unsigned int len) { + DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); + if (likely(len <= skb_headlen(skb))) return true; if (unlikely(len > skb->len)) @@ -2801,6 +2802,11 @@ static inline void skb_set_inner_network_header(struct sk_buff *skb, skb->inner_network_header += offset; } +static inline bool skb_inner_network_header_was_set(const struct sk_buff *skb) +{ + return skb->inner_network_header > 0; +} + static inline unsigned char *skb_inner_mac_header(const struct sk_buff *skb) { return skb->head + skb->inner_mac_header; @@ -2921,6 +2927,21 @@ static inline void skb_mac_header_rebuild(struct sk_buff *skb) } } +/* Move the full mac header up to current network_header. + * Leaves skb->data pointing at offset skb->mac_len into the mac_header. + * Must be provided the complete mac header length. + */ +static inline void skb_mac_header_rebuild_full(struct sk_buff *skb, u32 full_mac_len) +{ + if (skb_mac_header_was_set(skb)) { + const unsigned char *old_mac = skb_mac_header(skb); + + skb_set_mac_header(skb, -full_mac_len); + memmove(skb_mac_header(skb), old_mac, full_mac_len); + __skb_push(skb, full_mac_len - skb->mac_len); + } +} + static inline int skb_checksum_start_offset(const struct sk_buff *skb) { return skb->csum_start - skb_headroom(skb); diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index bd4418377bacff9a0ad024942fc415fd02bbe6dc..062fe440f5d0952c03112990bde615366e8ea139 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -456,10 +456,12 @@ static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock) { + read_lock_bh(&sk->sk_callback_lock); if (psock->saved_data_ready) psock->saved_data_ready(sk); else sk->sk_data_ready(sk); + read_unlock_bh(&sk->sk_callback_lock); } static inline void psock_set_prog(struct bpf_prog **pprog, diff --git a/include/linux/slab.h b/include/linux/slab.h index 45efc6c553b826101da7855a4573dfe66c845ae4..b8e77ffc38929218a6bbffa4fd777897e1874f03 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -17,6 +17,7 @@ #include #include #include +#include /* @@ -197,6 +198,8 @@ void kfree(const void *objp); void kfree_sensitive(const void *objp); size_t __ksize(const void *objp); +DEFINE_FREE(kfree, void *, if (!IS_ERR_OR_NULL(_T)) kfree(_T)) + /** * ksize - Report actual allocation size of associated object * diff --git a/include/linux/socket.h b/include/linux/socket.h index b3c58042bd254551b369220e7e22df14ebcedbe1..d79efd026880986cb94f0b146efa17c47d8ab29b 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -33,7 +33,10 @@ typedef __kernel_sa_family_t sa_family_t; struct sockaddr { sa_family_t sa_family; /* address family, AF_xxx */ - char sa_data[14]; /* 14 bytes of protocol address */ + union { + char sa_data_min[14]; /* Minimum 14 bytes of protocol address */ + DECLARE_FLEX_ARRAY(char, sa_data); + }; }; struct linger { diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 8e9054d9f6df0c27787521e229523029b3e1f7da..0ce659d6fcb75202b5e30d74088674d589b2d4b7 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -376,6 +376,7 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @max_speed_hz: Highest supported transfer speed * @flags: other constraints relevant to this driver * @slave: indicates that this is an SPI slave controller + * @target: indicates that this is an SPI target controller * @devm_allocated: whether the allocation of this struct is devres-managed * @max_transfer_size: function that returns the max transfer size for * a &spi_device; may be %NULL, so the default %SIZE_MAX will be used. @@ -460,6 +461,7 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @mem_caps: controller capabilities for the handling of memory operations. * @unprepare_message: undo any work done by prepare_message(). * @slave_abort: abort the ongoing transfer request on an SPI slave controller + * @target_abort: abort the ongoing transfer request on an SPI target controller * @cs_gpiods: Array of GPIO descs to use as chip select lines; one per CS * number. Any individual value may be NULL for CS lines that * are not GPIOs (driven by the SPI controller itself). @@ -556,8 +558,12 @@ struct spi_controller { /* Flag indicating if the allocation of this struct is devres-managed */ bool devm_allocated; - /* Flag indicating this is an SPI slave controller */ - bool slave; + union { + /* Flag indicating this is an SPI slave controller */ + bool slave; + /* Flag indicating this is an SPI target controller */ + bool target; + }; /* * on some hardware transfer / message size may be constrained @@ -670,7 +676,10 @@ struct spi_controller { struct spi_message *message); int (*unprepare_message)(struct spi_controller *ctlr, struct spi_message *message); - int (*slave_abort)(struct spi_controller *ctlr); + union { + int (*slave_abort)(struct spi_controller *ctlr); + int (*target_abort)(struct spi_controller *ctlr); + }; /* * These hooks are for drivers that use a generic implementation @@ -748,6 +757,11 @@ static inline bool spi_controller_is_slave(struct spi_controller *ctlr) return IS_ENABLED(CONFIG_SPI_SLAVE) && ctlr->slave; } +static inline bool spi_controller_is_target(struct spi_controller *ctlr) +{ + return IS_ENABLED(CONFIG_SPI_SLAVE) && ctlr->target; +} + /* PM calls that need to be issued by the driver */ extern int spi_controller_suspend(struct spi_controller *ctlr); extern int spi_controller_resume(struct spi_controller *ctlr); @@ -784,6 +798,21 @@ static inline struct spi_controller *spi_alloc_slave(struct device *host, return __spi_alloc_controller(host, size, true); } +static inline struct spi_controller *spi_alloc_host(struct device *dev, + unsigned int size) +{ + return __spi_alloc_controller(dev, size, false); +} + +static inline struct spi_controller *spi_alloc_target(struct device *dev, + unsigned int size) +{ + if (!IS_ENABLED(CONFIG_SPI_SLAVE)) + return NULL; + + return __spi_alloc_controller(dev, size, true); +} + struct spi_controller *__devm_spi_alloc_controller(struct device *dev, unsigned int size, bool slave); @@ -803,6 +832,21 @@ static inline struct spi_controller *devm_spi_alloc_slave(struct device *dev, return __devm_spi_alloc_controller(dev, size, true); } +static inline struct spi_controller *devm_spi_alloc_host(struct device *dev, + unsigned int size) +{ + return __devm_spi_alloc_controller(dev, size, false); +} + +static inline struct spi_controller *devm_spi_alloc_target(struct device *dev, + unsigned int size) +{ + if (!IS_ENABLED(CONFIG_SPI_SLAVE)) + return NULL; + + return __devm_spi_alloc_controller(dev, size, true); +} + extern int spi_register_controller(struct spi_controller *ctlr); extern int devm_spi_register_controller(struct device *dev, struct spi_controller *ctlr); @@ -1162,6 +1206,7 @@ static inline void spi_message_free(struct spi_message *m) extern int spi_setup(struct spi_device *spi); extern int spi_async(struct spi_device *spi, struct spi_message *message); extern int spi_slave_abort(struct spi_device *spi); +extern int spi_target_abort(struct spi_device *spi); static inline size_t spi_max_message_size(struct spi_device *spi) diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 1341f7d62da44663d48630991e7455e364430b63..83377540c369a72d799dec8a20e993feb6cacfba 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -61,6 +61,7 @@ #include #include #include +#include #include #include @@ -493,5 +494,35 @@ int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask, void free_bucket_spinlocks(spinlock_t *locks); +DEFINE_LOCK_GUARD_1(raw_spinlock, raw_spinlock_t, + raw_spin_lock(_T->lock), + raw_spin_unlock(_T->lock)) + +DEFINE_LOCK_GUARD_1(raw_spinlock_nested, raw_spinlock_t, + raw_spin_lock_nested(_T->lock, SINGLE_DEPTH_NESTING), + raw_spin_unlock(_T->lock)) + +DEFINE_LOCK_GUARD_1(raw_spinlock_irq, raw_spinlock_t, + raw_spin_lock_irq(_T->lock), + raw_spin_unlock_irq(_T->lock)) + +DEFINE_LOCK_GUARD_1(raw_spinlock_irqsave, raw_spinlock_t, + raw_spin_lock_irqsave(_T->lock, _T->flags), + raw_spin_unlock_irqrestore(_T->lock, _T->flags), + unsigned long flags) + +DEFINE_LOCK_GUARD_1(spinlock, spinlock_t, + spin_lock(_T->lock), + spin_unlock(_T->lock)) + +DEFINE_LOCK_GUARD_1(spinlock_irq, spinlock_t, + spin_lock_irq(_T->lock), + spin_unlock_irq(_T->lock)) + +DEFINE_LOCK_GUARD_1(spinlock_irqsave, spinlock_t, + spin_lock_irqsave(_T->lock, _T->flags), + spin_unlock_irqrestore(_T->lock, _T->flags), + unsigned long flags) + #undef __LINUX_INSIDE_SPINLOCK_H #endif /* __LINUX_SPINLOCK_H */ diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 01226e4d960a023472248475ae78b532e8ac39f3..f9e1fa7ff86fcdebd939bef999917c8d20a69158 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -212,4 +212,9 @@ static inline void smp_mb__after_srcu_read_unlock(void) /* __srcu_read_unlock has smp_mb() internally so nothing to do here. */ } +DEFINE_LOCK_GUARD_1(srcu, struct srcu_struct, + _T->idx = srcu_read_lock(_T->lock), + srcu_read_unlock(_T->lock, _T->idx), + int idx) + #endif diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index c794b0ce4e782410515e604903a2ad92dc2b2258..809c23120d5488e3dd51ab6d95cd7f2f6e25fce3 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -131,6 +131,7 @@ struct rpc_create_args { const char *servername; const char *nodename; const struct rpc_program *program; + struct rpc_stat *stats; u32 prognumber; /* overrides program->number */ u32 version; rpc_authflavor_t authflavor; diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 8ada7dc802d3050790cc4ed3e2c38dbf3bc8efe3..8f9bee0e21c3bc329a19f4dc2fbda2bee844c810 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -186,7 +186,7 @@ struct rpc_wait_queue { unsigned char maxpriority; /* maximum priority (0 if queue is not a priority queue) */ unsigned char priority; /* current priority */ unsigned char nr; /* # tasks remaining for cookie */ - unsigned short qlen; /* total # tasks waiting in queue */ + unsigned int qlen; /* total # tasks waiting in queue */ struct rpc_timer timer_list; #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS) const char * name; diff --git a/include/linux/swap.h b/include/linux/swap.h index a18cf4b7c724c05a1a499ea2ac2723ec641cb5b2..add47f43e568eee5b88a8c4fa51b1b79ee66e6a0 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -571,6 +571,11 @@ static inline int swap_duplicate(swp_entry_t swp) return 0; } +static inline int swapcache_prepare(swp_entry_t swp) +{ + return 0; +} + static inline void swap_free(swp_entry_t swp) { } diff --git a/include/linux/swapops.h b/include/linux/swapops.h index b07b277d6a166e8d0ec2dd72eff7f193a2c956c6..1f59f9edcc24127a9edec19d93ac01da4ff9268c 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -409,6 +409,55 @@ static inline bool is_migration_entry_dirty(swp_entry_t entry) } #endif /* CONFIG_MIGRATION */ +#ifdef CONFIG_MEMORY_FAILURE + +extern atomic_long_t num_poisoned_pages __read_mostly; + +/* + * Support for hardware poisoned pages + */ +static inline swp_entry_t make_hwpoison_entry(struct page *page) +{ + BUG_ON(!PageLocked(page)); + return swp_entry(SWP_HWPOISON, page_to_pfn(page)); +} + +static inline int is_hwpoison_entry(swp_entry_t entry) +{ + return swp_type(entry) == SWP_HWPOISON; +} + +static inline void num_poisoned_pages_inc(void) +{ + atomic_long_inc(&num_poisoned_pages); +} + +static inline void num_poisoned_pages_sub(long i) +{ + atomic_long_sub(i, &num_poisoned_pages); +} + +#else /* CONFIG_MEMORY_FAILURE */ + +static inline swp_entry_t make_hwpoison_entry(struct page *page) +{ + return swp_entry(0, 0); +} + +static inline int is_hwpoison_entry(swp_entry_t swp) +{ + return 0; +} + +static inline void num_poisoned_pages_inc(void) +{ +} + +static inline void num_poisoned_pages_sub(long i) +{ +} +#endif /* CONFIG_MEMORY_FAILURE */ + typedef unsigned long pte_marker; #define PTE_MARKER_UFFD_WP BIT(0) @@ -503,8 +552,9 @@ static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) /* * A pfn swap entry is a special type of swap entry that always has a pfn stored - * in the swap offset. They are used to represent unaddressable device memory - * and to restrict access to a page undergoing migration. + * in the swap offset. They can either be used to represent unaddressable device + * memory, to restrict access to a page undergoing migration or to represent a + * pfn which has been hwpoisoned and unmapped. */ static inline bool is_pfn_swap_entry(swp_entry_t entry) { @@ -512,7 +562,7 @@ static inline bool is_pfn_swap_entry(swp_entry_t entry) BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS); return is_migration_entry(entry) || is_device_private_entry(entry) || - is_device_exclusive_entry(entry); + is_device_exclusive_entry(entry) || is_hwpoison_entry(entry); } struct page_vma_mapped_walk; @@ -581,55 +631,6 @@ static inline int is_pmd_migration_entry(pmd_t pmd) } #endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ -#ifdef CONFIG_MEMORY_FAILURE - -extern atomic_long_t num_poisoned_pages __read_mostly; - -/* - * Support for hardware poisoned pages - */ -static inline swp_entry_t make_hwpoison_entry(struct page *page) -{ - BUG_ON(!PageLocked(page)); - return swp_entry(SWP_HWPOISON, page_to_pfn(page)); -} - -static inline int is_hwpoison_entry(swp_entry_t entry) -{ - return swp_type(entry) == SWP_HWPOISON; -} - -static inline void num_poisoned_pages_inc(void) -{ - atomic_long_inc(&num_poisoned_pages); -} - -static inline void num_poisoned_pages_sub(long i) -{ - atomic_long_sub(i, &num_poisoned_pages); -} - -#else /* CONFIG_MEMORY_FAILURE */ - -static inline swp_entry_t make_hwpoison_entry(struct page *page) -{ - return swp_entry(0, 0); -} - -static inline int is_hwpoison_entry(swp_entry_t swp) -{ - return 0; -} - -static inline void num_poisoned_pages_inc(void) -{ -} - -static inline void num_poisoned_pages_sub(long i) -{ -} -#endif /* CONFIG_MEMORY_FAILURE */ - static inline int non_swap_entry(swp_entry_t entry) { return swp_type(entry) >= MAX_SWAPFILES; diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index 48fabe36509ee787756e094201d307ab4d33be83..8d8fac1626bd92588496ce15404fb1a957894be5 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -41,6 +41,7 @@ enum { enum switchtec_gen { SWITCHTEC_GEN3, SWITCHTEC_GEN4, + SWITCHTEC_GEN5, }; struct mrpc_regs { diff --git a/include/linux/timer.h b/include/linux/timer.h index 648f00105f588dac3e713aab419c21ac8e056e99..e338e173ce8bc52a9ae1ed5ed6017c9b39ddace3 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -169,7 +169,6 @@ static inline int timer_pending(const struct timer_list * timer) } extern void add_timer_on(struct timer_list *timer, int cpu); -extern int del_timer(struct timer_list * timer); extern int mod_timer(struct timer_list *timer, unsigned long expires); extern int mod_timer_pending(struct timer_list *timer, unsigned long expires); extern int timer_reduce(struct timer_list *timer, unsigned long expires); @@ -183,14 +182,34 @@ extern int timer_reduce(struct timer_list *timer, unsigned long expires); extern void add_timer(struct timer_list *timer); extern int try_to_del_timer_sync(struct timer_list *timer); +extern int timer_delete_sync(struct timer_list *timer); +extern int timer_delete(struct timer_list *timer); -#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) - extern int del_timer_sync(struct timer_list *timer); -#else -# define del_timer_sync(t) del_timer(t) -#endif +/** + * del_timer_sync - Delete a pending timer and wait for a running callback + * @timer: The timer to be deleted + * + * See timer_delete_sync() for detailed explanation. + * + * Do not use in new code. Use timer_delete_sync() instead. + */ +static inline int del_timer_sync(struct timer_list *timer) +{ + return timer_delete_sync(timer); +} -#define del_singleshot_timer_sync(t) del_timer_sync(t) +/** + * del_timer - Delete a pending timer + * @timer: The timer to be deleted + * + * See timer_delete() for detailed explanation. + * + * Do not use in new code. Use timer_delete() instead. + */ +static inline int del_timer(struct timer_list *timer) +{ + return timer_delete(timer); +} extern void init_timers(void); struct hrtimer; diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index 46040d66334a84f5c493417a200789a00dccb9e1..79c3bbaa7e13eca7740ad2ffbfce651abc5cc323 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -135,10 +135,11 @@ static inline void u64_stats_inc(u64_stats_t *p) p->v++; } -static inline void u64_stats_init(struct u64_stats_sync *syncp) -{ - seqcount_init(&syncp->seq); -} +#define u64_stats_init(syncp) \ + do { \ + struct u64_stats_sync *__s = (syncp); \ + seqcount_init(&__s->seq); \ + } while (0) static inline void __u64_stats_update_begin(struct u64_stats_sync *syncp) { diff --git a/include/linux/udp.h b/include/linux/udp.h index efd9ab6df379702316d73b94ae4bff14294eb75c..79a4eae6f1f8f316f0f9c0c6ff1bc68602ca5724 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -140,6 +140,24 @@ static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk, } } +DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key); +#if IS_ENABLED(CONFIG_IPV6) +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +#endif + +static inline bool udp_encap_needed(void) +{ + if (static_branch_unlikely(&udp_encap_needed_key)) + return true; + +#if IS_ENABLED(CONFIG_IPV6) + if (static_branch_unlikely(&udpv6_encap_needed_key)) + return true; +#endif + + return false; +} + static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) { if (!skb_is_gso(skb)) @@ -153,6 +171,16 @@ static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) !udp_test_bit(ACCEPT_FRAGLIST, sk)) return true; + /* GSO packets lacking the SKB_GSO_UDP_TUNNEL/_CSUM bits might still + * land in a tunnel as the socket check in udp_gro_receive cannot be + * foolproof. + */ + if (udp_encap_needed() && + READ_ONCE(udp_sk(sk)->encap_rcv) && + !(skb_shinfo(skb)->gso_type & + (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM))) + return true; + return false; } diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 43ac3fa760dbe5d0c2485bdc4e326fb28289f2c4..9783b9107d76ba3932c2eb91edc6bc031744c508 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -412,6 +412,8 @@ extern int composite_dev_prepare(struct usb_composite_driver *composite, extern int composite_os_desc_req_prepare(struct usb_composite_dev *cdev, struct usb_ep *ep0); void composite_dev_cleanup(struct usb_composite_dev *cdev); +void check_remote_wakeup_config(struct usb_gadget *g, + struct usb_configuration *c); static inline struct usb_composite_driver *to_cdriver( struct usb_gadget_driver *gdrv) diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index dc3092cea99e9b99a6eb8d6aba6102629f6f9344..5bec668b41dcd505d34e498c08b648416306fdba 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -309,6 +309,7 @@ struct usb_udc; struct usb_gadget_ops { int (*get_frame)(struct usb_gadget *); int (*wakeup)(struct usb_gadget *); + int (*set_remote_wakeup)(struct usb_gadget *, int set); int (*set_selfpowered) (struct usb_gadget *, int is_selfpowered); int (*vbus_session) (struct usb_gadget *, int is_active); int (*vbus_draw) (struct usb_gadget *, unsigned mA); @@ -383,6 +384,8 @@ struct usb_gadget_ops { * @connected: True if gadget is connected. * @lpm_capable: If the gadget max_speed is FULL or HIGH, this flag * indicates that it supports LPM as per the LPM ECN & errata. + * @wakeup_capable: True if gadget is capable of sending remote wakeup. + * @wakeup_armed: True if gadget is armed by the host for remote wakeup. * @irq: the interrupt number for device controller. * @id_number: a unique ID number for ensuring that gadget names are distinct * @@ -444,6 +447,8 @@ struct usb_gadget { unsigned deactivated:1; unsigned connected:1; unsigned lpm_capable:1; + unsigned wakeup_capable:1; + unsigned wakeup_armed:1; int irq; int id_number; }; @@ -600,6 +605,7 @@ static inline int gadget_is_otg(struct usb_gadget *g) #if IS_ENABLED(CONFIG_USB_GADGET) int usb_gadget_frame_number(struct usb_gadget *gadget); int usb_gadget_wakeup(struct usb_gadget *gadget); +int usb_gadget_set_remote_wakeup(struct usb_gadget *gadget, int set); int usb_gadget_set_selfpowered(struct usb_gadget *gadget); int usb_gadget_clear_selfpowered(struct usb_gadget *gadget); int usb_gadget_vbus_connect(struct usb_gadget *gadget); @@ -615,6 +621,8 @@ static inline int usb_gadget_frame_number(struct usb_gadget *gadget) { return 0; } static inline int usb_gadget_wakeup(struct usb_gadget *gadget) { return 0; } +static inline int usb_gadget_set_remote_wakeup(struct usb_gadget *gadget, int set) +{ return 0; } static inline int usb_gadget_set_selfpowered(struct usb_gadget *gadget) { return 0; } static inline int usb_gadget_clear_selfpowered(struct usb_gadget *gadget) diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 5a89928ea95349cdd9a82d687069862cc296ffc7..cd667acf62672d0e5474d0033844ccf71d3c197d 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -371,8 +371,9 @@ struct hc_driver { * or bandwidth constraints. */ void (*reset_bandwidth)(struct usb_hcd *, struct usb_device *); - /* Returns the hardware-chosen device address */ - int (*address_device)(struct usb_hcd *, struct usb_device *udev); + /* Set the hardware-chosen device address */ + int (*address_device)(struct usb_hcd *, struct usb_device *udev, + unsigned int timeout_ms); /* prepares the hardware to send commands to the device */ int (*enable_device)(struct usb_hcd *, struct usb_device *udev); /* Notifies the HCD after a hub descriptor is fetched. diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index eeb7c2157c72fba0e54f926cec863bb9e50ff9f5..59409c1fc3dee7b20112867615f9a7a92b65fa17 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -72,4 +72,7 @@ /* device has endpoints that should be ignored */ #define USB_QUIRK_ENDPOINT_IGNORE BIT(15) +/* short SET_ADDRESS request timeout */ +#define USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT BIT(16) + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/linux/vfio.h b/include/linux/vfio.h index fdd393f70b19816e503b366b9b87337e4f8cb978..5e7bf143cb2230df8485f26addbc21d5f0c201f5 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -268,6 +268,7 @@ struct virqfd { wait_queue_entry_t wait; poll_table pt; struct work_struct shutdown; + struct work_struct flush_inject; struct virqfd **pvirqfd; }; @@ -275,5 +276,6 @@ int vfio_virqfd_enable(void *opaque, int (*handler)(void *, void *), void (*thread)(void *, void *), void *data, struct virqfd **pvirqfd, int fd); void vfio_virqfd_disable(struct virqfd **pvirqfd); +void vfio_virqfd_flush_thread(struct virqfd **pvirqfd); #endif /* VFIO_H */ diff --git a/include/media/media-entity.h b/include/media/media-entity.h index 28c9de8a1f3484aa13b66d862e6a792cb5336995..03bb0963942bd9badadeb4a8fc47de5f8732890e 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -205,6 +205,7 @@ enum media_pad_signal_type { * @graph_obj: Embedded structure containing the media object common data * @entity: Entity this pad belongs to * @index: Pad index in the entity pads array, numbered from 0 to n + * @num_links: Number of links connected to this pad * @sig_type: Type of the signal inside a media pad * @flags: Pad flags, as defined in * :ref:`include/uapi/linux/media.h ` @@ -216,6 +217,7 @@ struct media_pad { struct media_gobj graph_obj; /* must be first field in struct */ struct media_entity *entity; u16 index; + u16 num_links; enum media_pad_signal_type sig_type; unsigned long flags; diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 86eb2aba1479c0b0b65a4cfa481d17ba60b7e820..5bcc63eade035700beaefd8b5b52290c0646d514 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -437,6 +437,10 @@ static inline void in6_ifa_hold(struct inet6_ifaddr *ifp) refcount_inc(&ifp->refcnt); } +static inline bool in6_ifa_hold_safe(struct inet6_ifaddr *ifp) +{ + return refcount_inc_not_zero(&ifp->refcnt); +} /* * compute link-local solicited-node multicast address diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 0920b669b9b31ea2133071aaec5278e95e8cbfd7..e7d71a516bd4df17e827c940963537b190ad4ced 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -54,7 +54,7 @@ struct unix_sock { struct mutex iolock, bindlock; struct sock *peer; struct list_head link; - atomic_long_t inflight; + unsigned long inflight; spinlock_t lock; unsigned long gc_flags; #define UNIX_GC_CANDIDATE 0 @@ -79,6 +79,9 @@ enum unix_socket_lock_class { U_LOCK_NORMAL, U_LOCK_SECOND, /* for double locking, see unix_state_double_lock(). */ U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */ + U_LOCK_GC_LISTENER, /* used for listening socket while determining gc + * candidates to close a small race window. + */ }; static inline void unix_state_lock_nested(struct sock *sk, diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index bcc5a4cd2c17b79b6f43507e22263103fb2da96b..5aaf7d7f3c6fa2b8c370b181f2e92c9f6d2e6459 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -565,6 +565,15 @@ static inline struct sk_buff *bt_skb_sendmmsg(struct sock *sk, return skb; } +static inline int bt_copy_from_sockptr(void *dst, size_t dst_size, + sockptr_t src, size_t src_size) +{ + if (dst_size > src_size) + return -EINVAL; + + return copy_from_sockptr(dst, src, dst_size); +} + int bt_to_errno(u16 code); __u8 bt_status(int err); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index a674221d151db7f96bf41e1aa002d1845168688d..09bc4bf805c624a9cbd54d034847fd70407dcdc2 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -175,6 +175,15 @@ enum { */ HCI_QUIRK_USE_BDADDR_PROPERTY, + /* When this quirk is set, the Bluetooth Device Address provided by + * the 'local-bd-address' fwnode property is incorrectly specified in + * big-endian order. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + */ + HCI_QUIRK_BDADDR_PROPERTY_BROKEN, + /* When this quirk is set, the duplicate filtering during * scanning is based on Bluetooth devices addresses. To allow * RSSI based updates, restart scanning if needed. @@ -416,7 +425,6 @@ enum { #define HCI_NCMD_TIMEOUT msecs_to_jiffies(4000) /* 4 seconds */ #define HCI_ACL_TX_TIMEOUT msecs_to_jiffies(45000) /* 45 seconds */ #define HCI_AUTO_OFF_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */ -#define HCI_POWER_OFF_TIMEOUT msecs_to_jiffies(5000) /* 5 seconds */ #define HCI_LE_CONN_TIMEOUT msecs_to_jiffies(20000) /* 20 seconds */ #define HCI_LE_AUTOCONN_TIMEOUT msecs_to_jiffies(4000) /* 4 seconds */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 09c978f3d95dca19821c221f0752ec1170e8b87d..c50a41f1782a416ad81d6ddbb0ec836dd7c6d67c 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -81,7 +81,7 @@ struct discovery_state { u8 last_adv_addr_type; s8 last_adv_rssi; u32 last_adv_flags; - u8 last_adv_data[HCI_MAX_AD_LENGTH]; + u8 last_adv_data[HCI_MAX_EXT_AD_LENGTH]; u8 last_adv_data_len; bool report_invalid_rssi; bool result_filtering; @@ -293,7 +293,7 @@ struct adv_pattern { __u8 ad_type; __u8 offset; __u8 length; - __u8 value[HCI_MAX_AD_LENGTH]; + __u8 value[HCI_MAX_EXT_AD_LENGTH]; }; struct adv_rssi_thresholds { @@ -549,6 +549,7 @@ struct hci_dev { __u32 req_status; __u32 req_result; struct sk_buff *req_skb; + struct sk_buff *req_rsp; void *smp_data; void *smp_bredr_data; @@ -726,7 +727,7 @@ struct hci_conn { __u16 le_conn_interval; __u16 le_conn_latency; __u16 le_supv_timeout; - __u8 le_adv_data[HCI_MAX_AD_LENGTH]; + __u8 le_adv_data[HCI_MAX_EXT_AD_LENGTH]; __u8 le_adv_data_len; __u8 le_per_adv_data[HCI_MAX_PER_AD_LENGTH]; __u8 le_per_adv_data_len; @@ -739,6 +740,7 @@ struct hci_conn { unsigned long flags; enum conn_reasons conn_reason; + __u8 abort_reason; __u32 clock; __u16 clock_accuracy; @@ -758,7 +760,6 @@ struct hci_conn { struct delayed_work auto_accept_work; struct delayed_work idle_work; struct delayed_work le_conn_timeout; - struct work_struct le_scan_cleanup; struct device dev; struct dentry *debugfs; @@ -1709,6 +1710,10 @@ void hci_conn_del_sysfs(struct hci_conn *conn); /* Extended advertising support */ #define ext_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_EXT_ADV)) +/* Maximum advertising length */ +#define max_adv_len(dev) \ + (ext_adv_capable(dev) ? HCI_MAX_EXT_AD_LENGTH : HCI_MAX_AD_LENGTH) + /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E page 1789: * * C24: Mandatory if the LE Controller supports Connection State and either diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h index 17f5a4c32f36ee1bfeff1b0bf5950e132bf218bb..59d15b1a978ab93f65469d31ad8ae76ff1133285 100644 --- a/include/net/bluetooth/hci_sync.h +++ b/include/net/bluetooth/hci_sync.h @@ -39,8 +39,10 @@ int __hci_cmd_sync_status_sk(struct hci_dev *hdev, u16 opcode, u32 plen, void hci_cmd_sync_init(struct hci_dev *hdev); void hci_cmd_sync_clear(struct hci_dev *hdev); void hci_cmd_sync_cancel(struct hci_dev *hdev, int err); -void __hci_cmd_sync_cancel(struct hci_dev *hdev, int err); +void hci_cmd_sync_cancel_sync(struct hci_dev *hdev, int err); +int hci_cmd_sync_submit(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy); int hci_cmd_sync_queue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy); diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index d8d8719315fd8400d5fb1dcff5c091c8c65a379c..5f7f28c9edcb6a7e26cd8cbcebaae856c9674035 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -267,6 +267,7 @@ struct ieee802154_llsec_key { struct ieee802154_llsec_key_entry { struct list_head list; + struct rcu_head rcu; struct ieee802154_llsec_key_id id; struct ieee802154_llsec_key *key; diff --git a/include/net/dsa.h b/include/net/dsa.h index ee369670e20e418bd5170b192257acb96ebf2f55..f96b61d9768e0bb596bbec0572481e5b5b741ae3 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -968,6 +968,14 @@ struct dsa_switch_ops { struct phy_device *phy); void (*port_disable)(struct dsa_switch *ds, int port); + /* + * Compatibility between device trees defining multiple CPU ports and + * drivers which are not OK to use by default the numerically smallest + * CPU port of a switch for its local ports. This can return NULL, + * meaning "don't know/don't care". + */ + struct dsa_port *(*preferred_default_local_cpu_port)(struct dsa_switch *ds); + /* * Port's MAC EEE settings */ diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 080968d6e6c53523562793d3d7230477c25fcd16..8132f330306dbee61ce608818d5c4ad49ffd6369 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -172,6 +172,7 @@ void inet_csk_init_xmit_timers(struct sock *sk, void (*delack_handler)(struct timer_list *), void (*keepalive_handler)(struct timer_list *)); void inet_csk_clear_xmit_timers(struct sock *sk); +void inet_csk_clear_xmit_timers_sync(struct sock *sk); static inline void inet_csk_schedule_ack(struct sock *sk) { diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index bca80522f95c889dae3daed670d30087b74c118a..f9906b73e7ff462143a8c48f5813fcb87361c761 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -351,6 +351,39 @@ static inline bool pskb_inet_may_pull(struct sk_buff *skb) return pskb_network_may_pull(skb, nhlen); } +/* Variant of pskb_inet_may_pull(). + */ +static inline bool skb_vlan_inet_prepare(struct sk_buff *skb) +{ + int nhlen = 0, maclen = ETH_HLEN; + __be16 type = skb->protocol; + + /* Essentially this is skb_protocol(skb, true) + * And we get MAC len. + */ + if (eth_type_vlan(type)) + type = __vlan_get_protocol(skb, type, &maclen); + + switch (type) { +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + nhlen = sizeof(struct ipv6hdr); + break; +#endif + case htons(ETH_P_IP): + nhlen = sizeof(struct iphdr); + break; + } + /* For ETH_P_IPV6/ETH_P_IP we make sure to pull + * a base network header in skb->head. + */ + if (!pskb_may_pull(skb, maclen + nhlen)) + return false; + + skb_set_network_header(skb, maclen); + return true; +} + static inline int ip_encap_hlen(struct ip_tunnel_encap *e) { const struct ip_tunnel_encap_ops *ops; diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index c48186bf47372761493e9502da90dadcc0c26b01..21da31e1dff5d3754aa479150a1dba569d07c8f6 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -85,6 +85,11 @@ struct ipv6_bpf_stub { sockptr_t optval, unsigned int optlen); int (*ipv6_getsockopt)(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen); + int (*ipv6_dev_get_saddr)(struct net *net, + const struct net_device *dst_dev, + const struct in6_addr *daddr, + unsigned int prefs, + struct in6_addr *saddr); }; extern const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly; diff --git a/include/net/macsec.h b/include/net/macsec.h index 65c93959c2dc57e5744f0b34b609ad6f7b3c5093..dd578d193f9aa3f517ebeaa5632bd009ff454518 100644 --- a/include/net/macsec.h +++ b/include/net/macsec.h @@ -302,6 +302,7 @@ struct macsec_ops { int (*mdo_get_tx_sa_stats)(struct macsec_context *ctx); int (*mdo_get_rx_sc_stats)(struct macsec_context *ctx); int (*mdo_get_rx_sa_stats)(struct macsec_context *ctx); + bool rx_uses_md_dst; }; void macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa); diff --git a/include/net/mctp.h b/include/net/mctp.h index 82800d521c3de186bf04a0e6f7eb4b29735a074e..7ed84054f4623eb6eb26aca41ee8219ea4d2eef0 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -249,6 +249,7 @@ struct mctp_route { struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet, mctp_eid_t daddr); +/* always takes ownership of skb */ int mctp_local_output(struct sock *sk, struct mctp_route *rt, struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag); diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 6a2019aaa46448be88b4994e5d41a07ce194a25f..3dbf947285be297ab4fbefc582edaccba88c33db 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -125,6 +125,12 @@ struct nf_conn { union nf_conntrack_proto proto; }; +static inline struct nf_conn * +nf_ct_to_nf_conn(const struct nf_conntrack *nfct) +{ + return container_of(nfct, struct nf_conn, ct_general); +} + static inline struct nf_conn * nf_ct_tuplehash_to_ctrack(const struct nf_conntrack_tuple_hash *hash) { @@ -175,6 +181,8 @@ nf_ct_get(const struct sk_buff *skb, enum ip_conntrack_info *ctinfo) void nf_ct_destroy(struct nf_conntrack *nfct); +void nf_conntrack_tcp_set_closing(struct nf_conn *ct); + /* decrement reference count on a conntrack */ static inline void nf_ct_put(struct nf_conn *ct) { diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index dde4dd9c4012c20fc94b4a3d2a595ac0a3dc69ab..df7775afb92b93401b0d8343ec69efde959d27bf 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -274,8 +274,8 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, flow_table->type->put(flow_table); } -int flow_offload_route_init(struct flow_offload *flow, - const struct nf_flow_route *route); +void flow_offload_route_init(struct flow_offload *flow, + struct nf_flow_route *route); int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow); void flow_offload_refresh(struct nf_flowtable *flow_table, @@ -335,7 +335,7 @@ int nf_flow_rule_route_ipv6(struct net *net, struct flow_offload *flow, int nf_flow_table_offload_init(void); void nf_flow_table_offload_exit(void); -static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb) +static inline __be16 __nf_flow_pppoe_proto(const struct sk_buff *skb) { __be16 proto; @@ -351,6 +351,16 @@ static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb) return 0; } +static inline bool nf_flow_pppoe_proto(struct sk_buff *skb, __be16 *inner_proto) +{ + if (!pskb_may_pull(skb, PPPOE_SES_HLEN)) + return false; + + *inner_proto = __nf_flow_pppoe_proto(skb); + + return true; +} + #define NF_FLOW_TABLE_STAT_INC(net, count) __this_cpu_inc((net)->ft.stat->count) #define NF_FLOW_TABLE_STAT_DEC(net, count) __this_cpu_dec((net)->ft.stat->count) #define NF_FLOW_TABLE_STAT_INC_ATOMIC(net, count) \ diff --git a/include/net/sock.h b/include/net/sock.h index 579732d47dfc43391673b648b7065953364c6573..77298c74822a6e5a696718c8ac837f783eecf195 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1483,33 +1483,36 @@ sk_memory_allocated(const struct sock *sk) /* 1 MB per cpu, in page units */ #define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT)) +extern int sysctl_mem_pcpu_rsv; + +static inline void proto_memory_pcpu_drain(struct proto *proto) +{ + int val = this_cpu_xchg(*proto->per_cpu_fw_alloc, 0); + + if (val) + atomic_long_add(val, proto->memory_allocated); +} static inline void -sk_memory_allocated_add(struct sock *sk, int amt) +sk_memory_allocated_add(const struct sock *sk, int val) { - int local_reserve; + struct proto *proto = sk->sk_prot; - preempt_disable(); - local_reserve = __this_cpu_add_return(*sk->sk_prot->per_cpu_fw_alloc, amt); - if (local_reserve >= SK_MEMORY_PCPU_RESERVE) { - __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); - atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); - } - preempt_enable(); + val = this_cpu_add_return(*proto->per_cpu_fw_alloc, val); + + if (unlikely(val >= READ_ONCE(sysctl_mem_pcpu_rsv))) + proto_memory_pcpu_drain(proto); } static inline void -sk_memory_allocated_sub(struct sock *sk, int amt) +sk_memory_allocated_sub(const struct sock *sk, int val) { - int local_reserve; + struct proto *proto = sk->sk_prot; - preempt_disable(); - local_reserve = __this_cpu_sub_return(*sk->sk_prot->per_cpu_fw_alloc, amt); - if (local_reserve <= -SK_MEMORY_PCPU_RESERVE) { - __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); - atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); - } - preempt_enable(); + val = this_cpu_sub_return(*proto->per_cpu_fw_alloc, val); + + if (unlikely(val <= -READ_ONCE(sysctl_mem_pcpu_rsv))) + proto_memory_pcpu_drain(proto); } #define SK_ALLOC_PERCPU_COUNTER_BATCH 16 @@ -1833,6 +1836,13 @@ static inline void sock_owned_by_me(const struct sock *sk) #endif } +static inline void sock_not_owned_by_me(const struct sock *sk) +{ +#ifdef CONFIG_LOCKDEP + WARN_ON_ONCE(lockdep_sock_is_held(sk) && debug_locks); +#endif +} + static inline bool sock_owned_by_user(const struct sock *sk) { sock_owned_by_me(sk); diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 7dcdc97c0bc3308b5fcfab399368d6b5a44e6510..a3d8f013adcd571450e9e719ea66f3f4aed3bae7 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -303,6 +303,9 @@ void switchdev_deferred_process(void); int switchdev_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, struct netlink_ext_ack *extack); +bool switchdev_port_obj_act_is_deferred(struct net_device *dev, + enum switchdev_notifier_type nt, + const struct switchdev_obj *obj); int switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj, struct netlink_ext_ack *extack); diff --git a/include/net/tcp.h b/include/net/tcp.h index 4c838f7290dd97ab0ea810732f7841437148ab8b..8ea1fba84eff96a3566a658f61fce68f39a050d4 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2290,7 +2290,7 @@ struct tcp_ulp_ops { /* cleanup ulp */ void (*release)(struct sock *sk); /* diagnostic */ - int (*get_info)(const struct sock *sk, struct sk_buff *skb); + int (*get_info)(struct sock *sk, struct sk_buff *skb); size_t (*get_info_size)(const struct sock *sk); /* clone ulp */ void (*clone)(const struct request_sock *req, struct sock *newsk, diff --git a/include/net/tls.h b/include/net/tls.h index c36bf4c50027e5528eb7fbe0d8b16997dc5c862a..899c863aba02cea4515046dca5be25ca0e438107 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -108,9 +108,6 @@ struct tls_sw_context_tx { struct tls_rec *open_rec; struct list_head tx_list; atomic_t encrypt_pending; - /* protect crypto_wait with encrypt_pending */ - spinlock_t encrypt_compl_lock; - int async_notify; u8 async_capable:1; #define BIT_TX_SCHEDULED 0 @@ -147,8 +144,6 @@ struct tls_sw_context_rx { struct tls_strparser strp; atomic_t decrypt_pending; - /* protect crypto_wait with decrypt_pending*/ - spinlock_t decrypt_compl_lock; struct sk_buff_head async_hold; struct wait_queue_head wq; }; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 9ec6f2e92ad3a758d8ab7e305486544c81b29aac..5b9c2c535702c630dfef4b7ea7de151d1bbe2feb 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1032,6 +1032,9 @@ struct xfrm_offload { #define CRYPTO_INVALID_PACKET_SYNTAX 64 #define CRYPTO_INVALID_PROTOCOL 128 + /* Used to keep whole l2 header for transport mode GRO */ + __u32 orig_mac_len; + __u8 proto; __u8 inner_ipproto; }; diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index fdc31fdb612dabb6db310f5b7a29a98c5daaa712..1504d3137cc6926ea94bb8b38214ee7cbd5a7e28 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -100,10 +100,6 @@ struct scsi_vpd { unsigned char data[]; }; -enum scsi_vpd_parameters { - SCSI_VPD_HEADER_SIZE = 4, -}; - struct scsi_device { struct Scsi_Host *host; struct request_queue *request_queue; @@ -208,6 +204,7 @@ struct scsi_device { unsigned use_10_for_rw:1; /* first try 10-byte read / write */ unsigned use_10_for_ms:1; /* first try 10-byte mode sense/select */ unsigned set_dbd_for_ms:1; /* Set "DBD" field in mode sense */ + unsigned read_before_ms:1; /* perform a READ before MODE SENSE */ unsigned no_report_opcodes:1; /* no REPORT SUPPORTED OPERATION CODES */ unsigned no_write_same:1; /* no WRITE SAME command */ unsigned use_16_for_rw:1; /* Use read/write(16) over read/write(10) */ diff --git a/include/scsi/scsi_driver.h b/include/scsi/scsi_driver.h index 4ce1988b2ba01c6a92a09f998346ea4c0ea29b19..f40915d2eceef44b46bb209270a878906255c998 100644 --- a/include/scsi/scsi_driver.h +++ b/include/scsi/scsi_driver.h @@ -12,6 +12,7 @@ struct request; struct scsi_driver { struct device_driver gendrv; + int (*resume)(struct device *); void (*rescan)(struct device *); blk_status_t (*init_command)(struct scsi_cmnd *); void (*uninit_command)(struct scsi_cmnd *); diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 71def41b1ad785aea43dd88bd4230d7c3cc1b4a0..149b63e3534ad6d76f24a0c16d9bcba320fe0424 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -752,6 +752,7 @@ extern int __must_check scsi_add_host_with_dma(struct Scsi_Host *, struct device *, struct device *); extern void scsi_scan_host(struct Scsi_Host *); +extern int scsi_resume_device(struct scsi_device *sdev); extern int scsi_rescan_device(struct scsi_device *sdev); extern void scsi_remove_host(struct Scsi_Host *); extern struct Scsi_Host *scsi_host_get(struct Scsi_Host *); diff --git a/include/trace/events/qdisc.h b/include/trace/events/qdisc.h index a3995925cb057021dc779344d19f7e3724f6df3c..1f4258308b967a9ca8e17bbf61ba4ef07b6d786b 100644 --- a/include/trace/events/qdisc.h +++ b/include/trace/events/qdisc.h @@ -81,14 +81,14 @@ TRACE_EVENT(qdisc_reset, TP_ARGS(q), TP_STRUCT__entry( - __string( dev, qdisc_dev(q) ) - __string( kind, q->ops->id ) - __field( u32, parent ) - __field( u32, handle ) + __string( dev, qdisc_dev(q)->name ) + __string( kind, q->ops->id ) + __field( u32, parent ) + __field( u32, handle ) ), TP_fast_assign( - __assign_str(dev, qdisc_dev(q)); + __assign_str(dev, qdisc_dev(q)->name); __assign_str(kind, q->ops->id); __entry->parent = q->parent; __entry->handle = q->handle; @@ -106,14 +106,14 @@ TRACE_EVENT(qdisc_destroy, TP_ARGS(q), TP_STRUCT__entry( - __string( dev, qdisc_dev(q) ) - __string( kind, q->ops->id ) - __field( u32, parent ) - __field( u32, handle ) + __string( dev, qdisc_dev(q)->name ) + __string( kind, q->ops->id ) + __field( u32, parent ) + __field( u32, handle ) ), TP_fast_assign( - __assign_str(dev, qdisc_dev(q)); + __assign_str(dev, qdisc_dev(q)->name); __assign_str(kind, q->ops->id); __entry->parent = q->parent; __entry->handle = q->handle; diff --git a/include/trace/events/rpcgss.h b/include/trace/events/rpcgss.h index c9048f3e471bb99f309696085227f7a6b9455a91..894d9fc8bd94a06199c50d7d07d12b9e3c6a2d9a 100644 --- a/include/trace/events/rpcgss.h +++ b/include/trace/events/rpcgss.h @@ -13,7 +13,7 @@ #include -#include +#include /** ** GSS-API related trace events @@ -587,7 +587,7 @@ TRACE_EVENT(rpcgss_context, __field(unsigned int, timeout) __field(u32, window_size) __field(int, len) - __string(acceptor, data) + __string_len(acceptor, data, len) ), TP_fast_assign( @@ -596,7 +596,7 @@ TRACE_EVENT(rpcgss_context, __entry->timeout = timeout; __entry->window_size = window_size; __entry->len = len; - strncpy(__get_str(acceptor), data, len); + __assign_str(acceptor, data); ), TP_printk("win_size=%u expiry=%lu now=%lu timeout=%u acceptor=%.*s", diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index fcd3b3f1020a6fd95f6f30ae16e7ac805ed11655..8f461e04e5f099bfbeb6bea89d33a1d4f93cc28b 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -15,8 +15,8 @@ #include #include -#include -#include +#include +#include /** ** Event classes diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index f48f2ab9d238b5998f163a48653e07d58f4f2bf9..ffe2679a13ced7e7c596bd345180006f0c722987 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -14,7 +14,7 @@ #include #include -#include +#include TRACE_DEFINE_ENUM(SOCK_STREAM); TRACE_DEFINE_ENUM(SOCK_DGRAM); diff --git a/include/trace/events/fs.h b/include/trace/misc/fs.h similarity index 100% rename from include/trace/events/fs.h rename to include/trace/misc/fs.h diff --git a/include/trace/events/nfs.h b/include/trace/misc/nfs.h similarity index 96% rename from include/trace/events/nfs.h rename to include/trace/misc/nfs.h index 09ffdbb04134d6838db389ef427c70034768348c..0d9d48dca38a8949047a72d472700ffcd2bebc20 100644 --- a/include/trace/events/nfs.h +++ b/include/trace/misc/nfs.h @@ -360,6 +360,18 @@ TRACE_DEFINE_ENUM(IOMODE_ANY); { IOMODE_RW, "RW" }, \ { IOMODE_ANY, "ANY" }) +#define show_rca_mask(x) \ + __print_flags(x, "|", \ + { BIT(RCA4_TYPE_MASK_RDATA_DLG), "RDATA_DLG" }, \ + { BIT(RCA4_TYPE_MASK_WDATA_DLG), "WDATA_DLG" }, \ + { BIT(RCA4_TYPE_MASK_DIR_DLG), "DIR_DLG" }, \ + { BIT(RCA4_TYPE_MASK_FILE_LAYOUT), "FILE_LAYOUT" }, \ + { BIT(RCA4_TYPE_MASK_BLK_LAYOUT), "BLK_LAYOUT" }, \ + { BIT(RCA4_TYPE_MASK_OBJ_LAYOUT_MIN), "OBJ_LAYOUT_MIN" }, \ + { BIT(RCA4_TYPE_MASK_OBJ_LAYOUT_MAX), "OBJ_LAYOUT_MAX" }, \ + { BIT(RCA4_TYPE_MASK_OTHER_LAYOUT_MIN), "OTHER_LAYOUT_MIN" }, \ + { BIT(RCA4_TYPE_MASK_OTHER_LAYOUT_MAX), "OTHER_LAYOUT_MAX" }) + #define show_nfs4_seq4_status(x) \ __print_flags(x, "|", \ { SEQ4_STATUS_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ diff --git a/include/trace/events/rdma.h b/include/trace/misc/rdma.h similarity index 100% rename from include/trace/events/rdma.h rename to include/trace/misc/rdma.h diff --git a/include/trace/events/sunrpc_base.h b/include/trace/misc/sunrpc.h similarity index 100% rename from include/trace/events/sunrpc_base.h rename to include/trace/misc/sunrpc.h diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 201dc77ebbd77eb59d0d060c713bc485a4e70507..d5d2183730b9f3863326e07f0b8350aac29dda6e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3109,6 +3109,10 @@ union bpf_attr { * **BPF_FIB_LOOKUP_DIRECT** * Do a direct table lookup vs full lookup using FIB * rules. + * **BPF_FIB_LOOKUP_TBID** + * Used with BPF_FIB_LOOKUP_DIRECT. + * Use the routing table ID present in *params*->tbid + * for the fib lookup. * **BPF_FIB_LOOKUP_OUTPUT** * Perform lookup from an egress perspective (default is * ingress). @@ -3117,6 +3121,11 @@ union bpf_attr { * and *params*->smac will not be set as output. A common * use case is to call **bpf_redirect_neigh**\ () after * doing **bpf_fib_lookup**\ (). + * **BPF_FIB_LOOKUP_SRC** + * Derive and set source IP addr in *params*->ipv{4,6}_src + * for the nexthop. If the src addr cannot be derived, + * **BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this + * case, *params*->dmac and *params*->smac are not set either. * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -6687,6 +6696,8 @@ enum { BPF_FIB_LOOKUP_DIRECT = (1U << 0), BPF_FIB_LOOKUP_OUTPUT = (1U << 1), BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), + BPF_FIB_LOOKUP_TBID = (1U << 3), + BPF_FIB_LOOKUP_SRC = (1U << 4), }; enum { @@ -6699,6 +6710,7 @@ enum { BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */ BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */ BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */ + BPF_FIB_LKUP_RET_NO_SRC_ADDR, /* failed to derive IP src addr */ }; struct bpf_fib_lookup { @@ -6733,6 +6745,9 @@ struct bpf_fib_lookup { __u32 rt_metric; }; + /* input: source address to consider for lookup + * output: source address result from lookup + */ union { __be32 ipv4_src; __u32 ipv6_src[4]; /* in6_addr; network order */ @@ -6747,9 +6762,19 @@ struct bpf_fib_lookup { __u32 ipv6_dst[4]; /* in6_addr; network order */ }; - /* output */ - __be16 h_vlan_proto; - __be16 h_vlan_TCI; + union { + struct { + /* output */ + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + }; + /* input: when accompanied with the + * 'BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID` flags, a + * specific routing table to use for the fib lookup. + */ + __u32 tbid; + }; + __u8 smac[6]; /* ETH_ALEN */ __u8 dmac[6]; /* ETH_ALEN */ }; diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index c4c53a9ab9595b2a5b95e5b22cafa5bd2cd6fd3c..ff8d21f9e95b7798eaf3e00635050e1631d6697a 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -145,7 +145,7 @@ struct in6_flowlabel_req { #define IPV6_TLV_PADN 1 #define IPV6_TLV_ROUTERALERT 5 #define IPV6_TLV_CALIPSO 7 /* RFC 5570 */ -#define IPV6_TLV_IOAM 49 /* TEMPORARY IANA allocation for IOAM */ +#define IPV6_TLV_IOAM 49 /* RFC 9486 */ #define IPV6_TLV_JUMBO 194 #define IPV6_TLV_HAO 201 /* home address option */ diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 7ad931a329706c7253914b9a04fa5902c3d8b194..1ce8a91349e9f7a710807ac18c919dfb287b84c3 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -602,6 +602,7 @@ #define KEY_ALS_TOGGLE 0x230 /* Ambient light sensor */ #define KEY_ROTATE_LOCK_TOGGLE 0x231 /* Display rotation lock */ +#define KEY_REFRESH_RATE_TOGGLE 0x232 /* Display refresh rate toggle */ #define KEY_BUTTONCONFIG 0x240 /* AL Button Configuration */ #define KEY_TASKMANAGER 0x241 /* AL Task/Project Manager */ diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index af8f4c304d2721db7ef71c4232078ed036d34b17..707af820f1a978383a8a488a1b73265906a46b40 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -266,9 +266,11 @@ enum nft_rule_attributes { /** * enum nft_rule_compat_flags - nf_tables rule compat flags * + * @NFT_RULE_COMPAT_F_UNUSED: unused * @NFT_RULE_COMPAT_F_INV: invert the check result */ enum nft_rule_compat_flags { + NFT_RULE_COMPAT_F_UNUSED = (1 << 0), NFT_RULE_COMPAT_F_INV = (1 << 1), NFT_RULE_COMPAT_F_MASK = NFT_RULE_COMPAT_F_INV, }; diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 57b8e2ffb1dd37fc99a356588d34f782e053bafe..3325155036c80f7e23ca2f0bc550aede1b5c5b45 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -1043,6 +1043,7 @@ #define PCI_EXP_DPC_STATUS_INTERRUPT 0x0008 /* Interrupt Status */ #define PCI_EXP_DPC_RP_BUSY 0x0010 /* Root Port Busy */ #define PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT 0x0060 /* Trig Reason Extension */ +#define PCI_EXP_DPC_RP_PIO_FEP 0x1f00 /* RP PIO First Err Ptr */ #define PCI_EXP_DPC_SOURCE_ID 0x0A /* DPC Source Identifier */ diff --git a/include/uapi/rdma/irdma-abi.h b/include/uapi/rdma/irdma-abi.h index a7085e092d34873f8745724058a82436d83ab6fc..3a0cde4dcf331f23d1749f6d52823558c1c5ce35 100644 --- a/include/uapi/rdma/irdma-abi.h +++ b/include/uapi/rdma/irdma-abi.h @@ -22,10 +22,15 @@ enum irdma_memreg_type { IRDMA_MEMREG_TYPE_CQ = 2, }; +enum { + IRDMA_ALLOC_UCTX_USE_RAW_ATTR = 1 << 0, +}; + struct irdma_alloc_ucontext_req { __u32 rsvd32; __u8 userspace_ver; __u8 rsvd8[3]; + __aligned_u64 comp_mask; }; struct irdma_alloc_ucontext_resp { @@ -46,6 +51,7 @@ struct irdma_alloc_ucontext_resp { __u16 max_hw_sq_chunk; __u8 hw_rev; __u8 rsvd2; + __aligned_u64 comp_mask; }; struct irdma_alloc_pd_resp { diff --git a/include/uapi/scsi/scsi_bsg_mpi3mr.h b/include/uapi/scsi/scsi_bsg_mpi3mr.h index fdc3517f9e1993ad891350e60662b939a6853d00..c48c5d08c0fa08b11c7ee4bd4eadad0bbdec6155 100644 --- a/include/uapi/scsi/scsi_bsg_mpi3mr.h +++ b/include/uapi/scsi/scsi_bsg_mpi3mr.h @@ -382,7 +382,7 @@ struct mpi3mr_bsg_in_reply_buf { __u8 mpi_reply_type; __u8 rsvd1; __u16 rsvd2; - __u8 reply_buf[1]; + __u8 reply_buf[]; }; /** diff --git a/init/Kconfig b/init/Kconfig index 148704640252e145f1c6316cce1a7e43298eb002..537f01eba2e6fccf116c089eb2c79cf9ad29c90a 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -89,6 +89,15 @@ config CC_HAS_ASM_GOTO_TIED_OUTPUT # Detect buggy gcc and clang, fixed in gcc-11 clang-14. def_bool $(success,echo 'int foo(int *x) { asm goto (".long (%l[bar]) - .": "+m"(*x) ::: bar); return *x; bar: return 0; }' | $CC -x c - -c -o /dev/null) +config GCC_ASM_GOTO_OUTPUT_WORKAROUND + bool + depends on CC_IS_GCC && CC_HAS_ASM_GOTO_OUTPUT + # Fixed in GCC 14, 13.3, 12.4 and 11.5 + # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921 + default y if GCC_VERSION < 110500 + default y if GCC_VERSION >= 120000 && GCC_VERSION < 120400 + default y if GCC_VERSION >= 130000 && GCC_VERSION < 130300 + config TOOLS_SUPPORT_RELR def_bool $(success,env "CC=$(CC)" "LD=$(LD)" "NM=$(NM)" "OBJCOPY=$(OBJCOPY)" $(srctree)/scripts/tools-support-relr.sh) @@ -893,14 +902,14 @@ config CC_IMPLICIT_FALLTHROUGH default "-Wimplicit-fallthrough=5" if CC_IS_GCC && $(cc-option,-Wimplicit-fallthrough=5) default "-Wimplicit-fallthrough" if CC_IS_CLANG && $(cc-option,-Wunreachable-code-fallthrough) -# Currently, disable gcc-11+ array-bounds globally. +# Currently, disable gcc-10+ array-bounds globally. # It's still broken in gcc-13, so no upper bound yet. -config GCC11_NO_ARRAY_BOUNDS +config GCC10_NO_ARRAY_BOUNDS def_bool y config CC_NO_ARRAY_BOUNDS bool - default y if CC_IS_GCC && GCC_VERSION >= 110000 && GCC11_NO_ARRAY_BOUNDS + default y if CC_IS_GCC && GCC_VERSION >= 100000 && GCC10_NO_ARRAY_BOUNDS # # For architectures that know their GCC __int128 support is sound @@ -1911,11 +1920,11 @@ config RUST bool "Rust support" depends on HAVE_RUST depends on RUST_IS_AVAILABLE + depends on !CFI_CLANG depends on !MODVERSIONS depends on !GCC_PLUGINS depends on !RANDSTRUCT depends on !DEBUG_INFO_BTF || PAHOLE_HAS_LANG_EXCLUDE - select CONSTRUCTORS help Enables Rust support in the kernel. diff --git a/init/initramfs.c b/init/initramfs.c index 2f5bfb7d765216c631759c1c37bf14ac90001982..7b915170789da8a6c760c4ff1c07208dd1a60483 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -680,7 +680,7 @@ static void __init populate_initrd_image(char *err) printk(KERN_INFO "rootfs image is not initramfs (%s); looks like an initrd\n", err); - file = filp_open("/initrd.image", O_WRONLY | O_CREAT, 0700); + file = filp_open("/initrd.image", O_WRONLY|O_CREAT|O_LARGEFILE, 0700); if (IS_ERR(file)) return; diff --git a/init/main.c b/init/main.c index 87a52bdb41d67177b4a691f01b397d69a5b06413..2c339793511b56bd260530e35b9488b218cd68b9 100644 --- a/init/main.c +++ b/init/main.c @@ -89,6 +89,7 @@ #include #include #include +#include #include #include #include @@ -632,6 +633,8 @@ static void __init setup_command_line(char *command_line) if (!saved_command_line) panic("%s: Failed to allocate %zu bytes\n", __func__, len + ilen); + len = xlen + strlen(command_line) + 1; + static_command_line = memblock_alloc(len, SMP_CACHE_BYTES); if (!static_command_line) panic("%s: Failed to allocate %zu bytes\n", __func__, len); @@ -1473,11 +1476,11 @@ static void mark_readonly(void) if (rodata_enabled) { /* * load_module() results in W+X mappings, which are cleaned - * up with call_rcu(). Let's make sure that queued work is + * up with init_free_wq. Let's make sure that queued work is * flushed so that we don't hit false positives looking for * insecure pages which are W+X. */ - rcu_barrier(); + flush_module_init_free_work(); mark_rodata_ro(); rodata_test(); } else diff --git a/io_uring/filetable.c b/io_uring/filetable.c index b80614e7d605112507363644c510d6312b65259d..4660cb89ea9f5235289e0bcc249422f50d75e294 100644 --- a/io_uring/filetable.c +++ b/io_uring/filetable.c @@ -95,12 +95,10 @@ static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file, needs_switch = true; } - ret = io_scm_file_account(ctx, file); - if (!ret) { - *io_get_tag_slot(ctx->file_data, slot_index) = 0; - io_fixed_file_set(file_slot, file); - io_file_bitmap_set(&ctx->file_table, slot_index); - } + *io_get_tag_slot(ctx->file_data, slot_index) = 0; + io_fixed_file_set(file_slot, file); + io_file_bitmap_set(&ctx->file_table, slot_index); + return 0; err: if (needs_switch) io_rsrc_node_switch(ctx, ctx->file_data); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 35894955b454983c498bfe32b7063fb626cb16a9..958c3b619020563111bfec634b6f592920d02d2d 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -60,7 +60,6 @@ #include #include #include -#include #include #include #include @@ -153,19 +152,6 @@ static void __io_submit_flush_completions(struct io_ring_ctx *ctx); static struct kmem_cache *req_cachep; -struct sock *io_uring_get_socket(struct file *file) -{ -#if defined(CONFIG_UNIX) - if (io_is_uring_fops(file)) { - struct io_ring_ctx *ctx = file->private_data; - - return ctx->ring_sock->sk; - } -#endif - return NULL; -} -EXPORT_SYMBOL(io_uring_get_socket); - static inline void io_submit_flush_completions(struct io_ring_ctx *ctx) { if (!wq_list_empty(&ctx->submit_state.compl_reqs)) @@ -1992,6 +1978,13 @@ static void io_init_req_drain(struct io_kiocb *req) } } +static __cold int io_init_fail_req(struct io_kiocb *req, int err) +{ + /* ensure per-opcode data is cleared if we fail before prep */ + memset(&req->cmd.data, 0, sizeof(req->cmd.data)); + return err; +} + static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, const struct io_uring_sqe *sqe) __must_hold(&ctx->uring_lock) @@ -2012,29 +2005,29 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, if (unlikely(opcode >= IORING_OP_LAST)) { req->opcode = 0; - return -EINVAL; + return io_init_fail_req(req, -EINVAL); } def = &io_op_defs[opcode]; if (unlikely(sqe_flags & ~SQE_COMMON_FLAGS)) { /* enforce forwards compatibility on users */ if (sqe_flags & ~SQE_VALID_FLAGS) - return -EINVAL; + return io_init_fail_req(req, -EINVAL); if (sqe_flags & IOSQE_BUFFER_SELECT) { if (!def->buffer_select) - return -EOPNOTSUPP; + return io_init_fail_req(req, -EOPNOTSUPP); req->buf_index = READ_ONCE(sqe->buf_group); } if (sqe_flags & IOSQE_CQE_SKIP_SUCCESS) ctx->drain_disabled = true; if (sqe_flags & IOSQE_IO_DRAIN) { if (ctx->drain_disabled) - return -EOPNOTSUPP; + return io_init_fail_req(req, -EOPNOTSUPP); io_init_req_drain(req); } } if (unlikely(ctx->restricted || ctx->drain_active || ctx->drain_next)) { if (ctx->restricted && !io_check_restriction(ctx, req, sqe_flags)) - return -EACCES; + return io_init_fail_req(req, -EACCES); /* knock it to the slow queue path, will be drained there */ if (ctx->drain_active) req->flags |= REQ_F_FORCE_ASYNC; @@ -2047,9 +2040,9 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, } if (!def->ioprio && sqe->ioprio) - return -EINVAL; + return io_init_fail_req(req, -EINVAL); if (!def->iopoll && (ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; + return io_init_fail_req(req, -EINVAL); if (def->needs_file) { struct io_submit_state *state = &ctx->submit_state; @@ -2073,12 +2066,12 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, req->creds = xa_load(&ctx->personalities, personality); if (!req->creds) - return -EINVAL; + return io_init_fail_req(req, -EINVAL); get_cred(req->creds); ret = security_uring_override_creds(req->creds); if (ret) { put_cred(req->creds); - return ret; + return io_init_fail_req(req, ret); } req->flags |= REQ_F_CREDS; } @@ -2433,6 +2426,14 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return 0; } while (ret > 0); + if (uts) { + struct timespec64 ts; + + if (get_timespec64(&ts, uts)) + return -EFAULT; + timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); + } + if (sig) { #ifdef CONFIG_COMPAT if (in_compat_syscall()) @@ -2446,14 +2447,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return ret; } - if (uts) { - struct timespec64 ts; - - if (get_timespec64(&ts, uts)) - return -EFAULT; - timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); - } - init_waitqueue_func_entry(&iowq.wq, io_wake_function); iowq.wq.private = current; INIT_LIST_HEAD(&iowq.wq.entry); @@ -2641,12 +2634,6 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list)); WARN_ON_ONCE(!llist_empty(&ctx->rsrc_put_llist)); -#if defined(CONFIG_UNIX) - if (ctx->ring_sock) { - ctx->ring_sock->file = NULL; /* so that iput() is called */ - sock_release(ctx->ring_sock); - } -#endif WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list)); if (ctx->mm_account) { @@ -3451,32 +3438,12 @@ static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file) /* * Allocate an anonymous fd, this is what constitutes the application * visible backing of an io_uring instance. The application mmaps this - * fd to gain access to the SQ/CQ ring details. If UNIX sockets are enabled, - * we have to tie this fd to a socket for file garbage collection purposes. + * fd to gain access to the SQ/CQ ring details. */ static struct file *io_uring_get_file(struct io_ring_ctx *ctx) { - struct file *file; -#if defined(CONFIG_UNIX) - int ret; - - ret = sock_create_kern(&init_net, PF_UNIX, SOCK_RAW, IPPROTO_IP, - &ctx->ring_sock); - if (ret) - return ERR_PTR(ret); -#endif - - file = anon_inode_getfile_secure("[io_uring]", &io_uring_fops, ctx, + return anon_inode_getfile_secure("[io_uring]", &io_uring_fops, ctx, O_RDWR | O_CLOEXEC, NULL); -#if defined(CONFIG_UNIX) - if (IS_ERR(file)) { - sock_release(ctx->ring_sock); - ctx->ring_sock = NULL; - } else { - ctx->ring_sock->file = file; - } -#endif - return file; } static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 019600570ee49eecd8d56eb880cde3811c1b1b30..59e6f755f12c686bea18687a33662b8f313ccb49 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -52,7 +52,6 @@ static inline bool io_req_ffs_set(struct io_kiocb *req) } void __io_req_task_work_add(struct io_kiocb *req, bool allow_local); -bool io_is_uring_fops(struct file *file); bool io_alloc_async_data(struct io_kiocb *req); void io_req_task_queue(struct io_kiocb *req); void io_queue_iowq(struct io_kiocb *req, bool *dont_use); diff --git a/io_uring/net.c b/io_uring/net.c index 67f09a40bcb211a4d48184f63aba7d07e6d15f36..48404bd330017d32347140252d96c7bf9dce7f3c 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -183,16 +183,115 @@ static int io_setup_async_msg(struct io_kiocb *req, return -EAGAIN; } +#ifdef CONFIG_COMPAT +static int io_compat_msg_copy_hdr(struct io_kiocb *req, + struct io_async_msghdr *iomsg, + struct compat_msghdr *msg, int ddir) +{ + struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); + struct compat_iovec __user *uiov; + int ret; + + if (copy_from_user(msg, sr->umsg_compat, sizeof(*msg))) + return -EFAULT; + + uiov = compat_ptr(msg->msg_iov); + if (req->flags & REQ_F_BUFFER_SELECT) { + compat_ssize_t clen; + + iomsg->free_iov = NULL; + if (msg->msg_iovlen == 0) { + sr->len = 0; + } else if (msg->msg_iovlen > 1) { + return -EINVAL; + } else { + if (!access_ok(uiov, sizeof(*uiov))) + return -EFAULT; + if (__get_user(clen, &uiov->iov_len)) + return -EFAULT; + if (clen < 0) + return -EINVAL; + sr->len = clen; + } + + return 0; + } + + iomsg->free_iov = iomsg->fast_iov; + ret = __import_iovec(ddir, (struct iovec __user *)uiov, msg->msg_iovlen, + UIO_FASTIOV, &iomsg->free_iov, + &iomsg->msg.msg_iter, true); + if (unlikely(ret < 0)) + return ret; + + return 0; +} +#endif + +static int io_msg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg, + struct user_msghdr *msg, int ddir) +{ + struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); + int ret; + + if (copy_from_user(msg, sr->umsg, sizeof(*sr->umsg))) + return -EFAULT; + + if (req->flags & REQ_F_BUFFER_SELECT) { + if (msg->msg_iovlen == 0) { + sr->len = iomsg->fast_iov[0].iov_len = 0; + iomsg->fast_iov[0].iov_base = NULL; + iomsg->free_iov = NULL; + } else if (msg->msg_iovlen > 1) { + return -EINVAL; + } else { + if (copy_from_user(iomsg->fast_iov, msg->msg_iov, + sizeof(*msg->msg_iov))) + return -EFAULT; + sr->len = iomsg->fast_iov[0].iov_len; + iomsg->free_iov = NULL; + } + + return 0; + } + + iomsg->free_iov = iomsg->fast_iov; + ret = __import_iovec(ddir, msg->msg_iov, msg->msg_iovlen, UIO_FASTIOV, + &iomsg->free_iov, &iomsg->msg.msg_iter, false); + if (unlikely(ret < 0)) + return ret; + + return 0; +} + static int io_sendmsg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg) { struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); + struct user_msghdr msg; int ret; iomsg->msg.msg_name = &iomsg->addr; - iomsg->free_iov = iomsg->fast_iov; - ret = sendmsg_copy_msghdr(&iomsg->msg, sr->umsg, sr->msg_flags, - &iomsg->free_iov); + iomsg->msg.msg_iter.nr_segs = 0; + +#ifdef CONFIG_COMPAT + if (unlikely(req->ctx->compat)) { + struct compat_msghdr cmsg; + + ret = io_compat_msg_copy_hdr(req, iomsg, &cmsg, ITER_SOURCE); + if (unlikely(ret)) + return ret; + + return __get_compat_msghdr(&iomsg->msg, &cmsg, NULL); + } +#endif + + ret = io_msg_copy_hdr(req, iomsg, &msg, ITER_SOURCE); + if (unlikely(ret)) + return ret; + + ret = __copy_msghdr(&iomsg->msg, &msg, NULL); + /* save msg_control as sys_sendmsg() overwrites it */ sr->msg_control = iomsg->msg.msg_control_user; return ret; @@ -415,142 +514,77 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags) return IOU_OK; } -static bool io_recvmsg_multishot_overflow(struct io_async_msghdr *iomsg) +static int io_recvmsg_mshot_prep(struct io_kiocb *req, + struct io_async_msghdr *iomsg, + int namelen, size_t controllen) { - int hdr; - - if (iomsg->namelen < 0) - return true; - if (check_add_overflow((int)sizeof(struct io_uring_recvmsg_out), - iomsg->namelen, &hdr)) - return true; - if (check_add_overflow(hdr, (int)iomsg->controllen, &hdr)) - return true; + if ((req->flags & (REQ_F_APOLL_MULTISHOT|REQ_F_BUFFER_SELECT)) == + (REQ_F_APOLL_MULTISHOT|REQ_F_BUFFER_SELECT)) { + int hdr; + + if (unlikely(namelen < 0)) + return -EOVERFLOW; + if (check_add_overflow(sizeof(struct io_uring_recvmsg_out), + namelen, &hdr)) + return -EOVERFLOW; + if (check_add_overflow(hdr, controllen, &hdr)) + return -EOVERFLOW; + + iomsg->namelen = namelen; + iomsg->controllen = controllen; + return 0; + } - return false; + return 0; } -static int __io_recvmsg_copy_hdr(struct io_kiocb *req, - struct io_async_msghdr *iomsg) +static int io_recvmsg_copy_hdr(struct io_kiocb *req, + struct io_async_msghdr *iomsg) { - struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); struct user_msghdr msg; int ret; - if (copy_from_user(&msg, sr->umsg, sizeof(*sr->umsg))) - return -EFAULT; - - ret = __copy_msghdr(&iomsg->msg, &msg, &iomsg->uaddr); - if (ret) - return ret; - - if (req->flags & REQ_F_BUFFER_SELECT) { - if (msg.msg_iovlen == 0) { - sr->len = iomsg->fast_iov[0].iov_len = 0; - iomsg->fast_iov[0].iov_base = NULL; - iomsg->free_iov = NULL; - } else if (msg.msg_iovlen > 1) { - return -EINVAL; - } else { - if (copy_from_user(iomsg->fast_iov, msg.msg_iov, sizeof(*msg.msg_iov))) - return -EFAULT; - sr->len = iomsg->fast_iov[0].iov_len; - iomsg->free_iov = NULL; - } - - if (req->flags & REQ_F_APOLL_MULTISHOT) { - iomsg->namelen = msg.msg_namelen; - iomsg->controllen = msg.msg_controllen; - if (io_recvmsg_multishot_overflow(iomsg)) - return -EOVERFLOW; - } - } else { - iomsg->free_iov = iomsg->fast_iov; - ret = __import_iovec(ITER_DEST, msg.msg_iov, msg.msg_iovlen, UIO_FASTIOV, - &iomsg->free_iov, &iomsg->msg.msg_iter, - false); - if (ret > 0) - ret = 0; - } - - return ret; -} + iomsg->msg.msg_name = &iomsg->addr; + iomsg->msg.msg_iter.nr_segs = 0; #ifdef CONFIG_COMPAT -static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req, - struct io_async_msghdr *iomsg) -{ - struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); - struct compat_msghdr msg; - struct compat_iovec __user *uiov; - int ret; - - if (copy_from_user(&msg, sr->umsg_compat, sizeof(msg))) - return -EFAULT; - - ret = __get_compat_msghdr(&iomsg->msg, &msg, &iomsg->uaddr); - if (ret) - return ret; - - uiov = compat_ptr(msg.msg_iov); - if (req->flags & REQ_F_BUFFER_SELECT) { - compat_ssize_t clen; + if (unlikely(req->ctx->compat)) { + struct compat_msghdr cmsg; - iomsg->free_iov = NULL; - if (msg.msg_iovlen == 0) { - sr->len = 0; - } else if (msg.msg_iovlen > 1) { - return -EINVAL; - } else { - if (!access_ok(uiov, sizeof(*uiov))) - return -EFAULT; - if (__get_user(clen, &uiov->iov_len)) - return -EFAULT; - if (clen < 0) - return -EINVAL; - sr->len = clen; - } + ret = io_compat_msg_copy_hdr(req, iomsg, &cmsg, ITER_DEST); + if (unlikely(ret)) + return ret; - if (req->flags & REQ_F_APOLL_MULTISHOT) { - iomsg->namelen = msg.msg_namelen; - iomsg->controllen = msg.msg_controllen; - if (io_recvmsg_multishot_overflow(iomsg)) - return -EOVERFLOW; - } - } else { - iomsg->free_iov = iomsg->fast_iov; - ret = __import_iovec(ITER_DEST, (struct iovec __user *)uiov, msg.msg_iovlen, - UIO_FASTIOV, &iomsg->free_iov, - &iomsg->msg.msg_iter, true); - if (ret < 0) + ret = __get_compat_msghdr(&iomsg->msg, &cmsg, &iomsg->uaddr); + if (unlikely(ret)) return ret; - } - return 0; -} + return io_recvmsg_mshot_prep(req, iomsg, cmsg.msg_namelen, + cmsg.msg_controllen); + } #endif -static int io_recvmsg_copy_hdr(struct io_kiocb *req, - struct io_async_msghdr *iomsg) -{ - iomsg->msg.msg_name = &iomsg->addr; - iomsg->msg.msg_iter.nr_segs = 0; + ret = io_msg_copy_hdr(req, iomsg, &msg, ITER_DEST); + if (unlikely(ret)) + return ret; -#ifdef CONFIG_COMPAT - if (req->ctx->compat) - return __io_compat_recvmsg_copy_hdr(req, iomsg); -#endif + ret = __copy_msghdr(&iomsg->msg, &msg, &iomsg->uaddr); + if (unlikely(ret)) + return ret; - return __io_recvmsg_copy_hdr(req, iomsg); + return io_recvmsg_mshot_prep(req, iomsg, msg.msg_namelen, + msg.msg_controllen); } int io_recvmsg_prep_async(struct io_kiocb *req) { + struct io_async_msghdr *iomsg; int ret; if (!io_msg_alloc_async_prep(req)) return -ENOMEM; - ret = io_recvmsg_copy_hdr(req, req->async_data); + iomsg = req->async_data; + ret = io_recvmsg_copy_hdr(req, iomsg); if (!ret) req->flags |= REQ_F_NEED_CLEANUP; return ret; @@ -842,7 +876,8 @@ retry_multishot: kfree(kmsg->free_iov); io_netmsg_recycle(req, issue_flags); req->flags &= ~REQ_F_NEED_CLEANUP; - } + } else if (ret == -EAGAIN) + return io_setup_async_msg(req, kmsg, issue_flags); return ret; } @@ -875,6 +910,7 @@ retry_multishot: if (!buf) return -ENOBUFS; sr->buf = buf; + sr->len = len; } ret = import_single_range(ITER_DEST, sr->buf, len, &iov, &msg.msg_iter); @@ -1193,6 +1229,7 @@ int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags) if (req_has_async_data(req)) { kmsg = req->async_data; + kmsg->msg.msg_control_user = sr->msg_control; } else { ret = io_sendmsg_copy_hdr(req, &iomsg); if (ret) @@ -1325,7 +1362,7 @@ retry: * has already been done */ if (issue_flags & IO_URING_F_MULTISHOT) - ret = IOU_ISSUE_SKIP_COMPLETE; + return IOU_ISSUE_SKIP_COMPLETE; return ret; } if (ret == -ERESTARTSYS) @@ -1349,7 +1386,8 @@ retry: if (io_post_aux_cqe(ctx, req->cqe.user_data, ret, IORING_CQE_F_MORE, false)) goto retry; - return -ECANCELED; + io_req_set_res(req, ret, 0); + return IOU_STOP_MULTISHOT; } int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index 7ada0339b3870522831f2891af9a6a1ac79e5a8f..ac658cfa89c63c61dadb7d29b8a66f6be91b7937 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -494,11 +494,6 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, err = -EBADF; break; } - err = io_scm_file_account(ctx, file); - if (err) { - fput(file); - break; - } *io_get_tag_slot(data, i) = tag; io_fixed_file_set(file_slot, file); io_file_bitmap_set(&ctx->file_table, i); @@ -762,22 +757,12 @@ void __io_sqe_files_unregister(struct io_ring_ctx *ctx) for (i = 0; i < ctx->nr_user_files; i++) { struct file *file = io_file_from_index(&ctx->file_table, i); - /* skip scm accounted files, they'll be freed by ->ring_sock */ - if (!file || io_file_need_scm(file)) + if (!file) continue; io_file_bitmap_clear(&ctx->file_table, i); fput(file); } -#if defined(CONFIG_UNIX) - if (ctx->ring_sock) { - struct sock *sock = ctx->ring_sock->sk; - struct sk_buff *skb; - - while ((skb = skb_dequeue(&sock->sk_receive_queue)) != NULL) - kfree_skb(skb); - } -#endif io_free_file_tables(&ctx->file_table); io_file_table_set_alloc_range(ctx, 0, 0); io_rsrc_data_free(ctx->file_data); @@ -805,134 +790,11 @@ int io_sqe_files_unregister(struct io_ring_ctx *ctx) return ret; } -/* - * Ensure the UNIX gc is aware of our file set, so we are certain that - * the io_uring can be safely unregistered on process exit, even if we have - * loops in the file referencing. We account only files that can hold other - * files because otherwise they can't form a loop and so are not interesting - * for GC. - */ -int __io_scm_file_account(struct io_ring_ctx *ctx, struct file *file) -{ -#if defined(CONFIG_UNIX) - struct sock *sk = ctx->ring_sock->sk; - struct sk_buff_head *head = &sk->sk_receive_queue; - struct scm_fp_list *fpl; - struct sk_buff *skb; - - if (likely(!io_file_need_scm(file))) - return 0; - - /* - * See if we can merge this file into an existing skb SCM_RIGHTS - * file set. If there's no room, fall back to allocating a new skb - * and filling it in. - */ - spin_lock_irq(&head->lock); - skb = skb_peek(head); - if (skb && UNIXCB(skb).fp->count < SCM_MAX_FD) - __skb_unlink(skb, head); - else - skb = NULL; - spin_unlock_irq(&head->lock); - - if (!skb) { - fpl = kzalloc(sizeof(*fpl), GFP_KERNEL); - if (!fpl) - return -ENOMEM; - - skb = alloc_skb(0, GFP_KERNEL); - if (!skb) { - kfree(fpl); - return -ENOMEM; - } - - fpl->user = get_uid(current_user()); - fpl->max = SCM_MAX_FD; - fpl->count = 0; - - UNIXCB(skb).fp = fpl; - skb->sk = sk; - skb->scm_io_uring = 1; - skb->destructor = unix_destruct_scm; - refcount_add(skb->truesize, &sk->sk_wmem_alloc); - } - - fpl = UNIXCB(skb).fp; - fpl->fp[fpl->count++] = get_file(file); - unix_inflight(fpl->user, file); - skb_queue_head(head, skb); - fput(file); -#endif - return 0; -} - static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) { struct file *file = prsrc->file; -#if defined(CONFIG_UNIX) - struct sock *sock = ctx->ring_sock->sk; - struct sk_buff_head list, *head = &sock->sk_receive_queue; - struct sk_buff *skb; - int i; - - if (!io_file_need_scm(file)) { - fput(file); - return; - } - - __skb_queue_head_init(&list); - - /* - * Find the skb that holds this file in its SCM_RIGHTS. When found, - * remove this entry and rearrange the file array. - */ - skb = skb_dequeue(head); - while (skb) { - struct scm_fp_list *fp; - fp = UNIXCB(skb).fp; - for (i = 0; i < fp->count; i++) { - int left; - - if (fp->fp[i] != file) - continue; - - unix_notinflight(fp->user, fp->fp[i]); - left = fp->count - 1 - i; - if (left) { - memmove(&fp->fp[i], &fp->fp[i + 1], - left * sizeof(struct file *)); - } - fp->count--; - if (!fp->count) { - kfree_skb(skb); - skb = NULL; - } else { - __skb_queue_tail(&list, skb); - } - fput(file); - file = NULL; - break; - } - - if (!file) - break; - - __skb_queue_tail(&list, skb); - - skb = skb_dequeue(head); - } - - if (skb_peek(&list)) { - spin_lock_irq(&head->lock); - while ((skb = __skb_dequeue(&list)) != NULL) - __skb_queue_tail(head, skb); - spin_unlock_irq(&head->lock); - } -#else fput(file); -#endif } int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, @@ -986,21 +848,12 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, goto fail; /* - * Don't allow io_uring instances to be registered. If UNIX - * isn't enabled, then this causes a reference cycle and this - * instance can never get freed. If UNIX is enabled we'll - * handle it just fine, but there's still no point in allowing - * a ring fd as it doesn't support regular read/write anyway. + * Don't allow io_uring instances to be registered. */ if (io_is_uring_fops(file)) { fput(file); goto fail; } - ret = io_scm_file_account(ctx, file); - if (ret) { - fput(file); - goto fail; - } file_slot = io_fixed_file_slot(&ctx->file_table, i); io_fixed_file_set(file_slot, file); io_file_bitmap_set(&ctx->file_table, i); diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index acaf8dad054014069ecd3df60fb8f2d6c7764cf2..85f145607c620943dfcdd94e6793438c2e5d0989 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -77,21 +77,6 @@ int io_sqe_files_unregister(struct io_ring_ctx *ctx); int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args, u64 __user *tags); -int __io_scm_file_account(struct io_ring_ctx *ctx, struct file *file); - -static inline bool io_file_need_scm(struct file *filp) -{ - return false; -} - -static inline int io_scm_file_account(struct io_ring_ctx *ctx, - struct file *file) -{ - if (likely(!io_file_need_scm(file))) - return 0; - return __io_scm_file_account(ctx, file); -} - int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args); int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg, diff --git a/kernel/bounds.c b/kernel/bounds.c index b529182e8b04fc5e53f106b5b7d0fdeea6c877aa..29b2cd00df2ccf2b991b9b78f4514b76c87ee354 100644 --- a/kernel/bounds.c +++ b/kernel/bounds.c @@ -19,7 +19,7 @@ int main(void) DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS); DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES); #ifdef CONFIG_SMP - DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS)); + DEFINE(NR_CPUS_BITS, order_base_2(CONFIG_NR_CPUS)); #endif DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t)); #ifdef CONFIG_LRU_GEN diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c index 48ee750849f25772ebe7f5cc325be53c509b33b0..78e810f49c4450b7dac3781e1ed5e05ff20f3fae 100644 --- a/kernel/bpf/bloom_filter.c +++ b/kernel/bpf/bloom_filter.c @@ -88,6 +88,18 @@ static int bloom_map_get_next_key(struct bpf_map *map, void *key, void *next_key return -EOPNOTSUPP; } +/* Called from syscall */ +static int bloom_map_alloc_check(union bpf_attr *attr) +{ + if (attr->value_size > KMALLOC_MAX_SIZE) + /* if value_size is bigger, the user space won't be able to + * access the elements. + */ + return -E2BIG; + + return 0; +} + static struct bpf_map *bloom_map_alloc(union bpf_attr *attr) { u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits; @@ -196,6 +208,7 @@ static int bloom_map_check_btf(const struct bpf_map *map, BTF_ID_LIST_SINGLE(bpf_bloom_map_btf_ids, struct, bpf_bloom_filter) const struct bpf_map_ops bloom_filter_map_ops = { .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = bloom_map_alloc_check, .map_alloc = bloom_map_alloc, .map_free = bloom_map_free, .map_get_next_key = bloom_map_get_next_key, diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 76bf1de2611524cc67a4bfc02b1988e70c111c60..44abf88e1bb0d95147e54f178d0d0ad4ef11827f 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -857,7 +857,12 @@ static LIST_HEAD(pack_list); * CONFIG_MMU=n. Use PAGE_SIZE in these cases. */ #ifdef PMD_SIZE -#define BPF_PROG_PACK_SIZE (PMD_SIZE * num_possible_nodes()) +/* PMD_SIZE is really big for some archs. It doesn't make sense to + * reserve too much memory in one allocation. Hardcode BPF_PROG_PACK_SIZE to + * 2MiB * num_possible_nodes(). On most architectures PMD_SIZE will be + * greater than or equal to 2MB. + */ +#define BPF_PROG_PACK_SIZE (SZ_2M * num_possible_nodes()) #else #define BPF_PROG_PACK_SIZE PAGE_SIZE #endif diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 08a8e81027289b9c044213eb54905d5e56fc2491..806a7c1b364b6ac67a97ec10c7d2d0a4b4ef8530 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -222,7 +222,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, void **frames, int n, struct xdp_cpumap_stats *stats) { - struct xdp_rxq_info rxq; + struct xdp_rxq_info rxq = {}; struct xdp_buff xdp; int i, nframes = 0; @@ -306,6 +306,7 @@ static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames, static int cpu_map_kthread_run(void *data) { struct bpf_cpu_map_entry *rcpu = data; + unsigned long last_qs = jiffies; complete(&rcpu->kthread_running); set_current_state(TASK_INTERRUPTIBLE); @@ -331,10 +332,12 @@ static int cpu_map_kthread_run(void *data) if (__ptr_ring_empty(rcpu->queue)) { schedule(); sched = 1; + last_qs = jiffies; } else { __set_current_state(TASK_RUNNING); } } else { + rcu_softirq_qs_periodic(last_qs); sched = cond_resched(); } diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index f9a87dcc5535bbfcdc31b2e96843b108b54873d4..e051cbb07dac02c49d96309dd39988538d778eb3 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -131,13 +131,14 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) bpf_map_init_from_attr(&dtab->map, attr); if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { - dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); - - if (!dtab->n_buckets) /* Overflow check */ + /* hash table size must be power of 2; roundup_pow_of_two() can + * overflow into UB on 32-bit arches, so check that first + */ + if (dtab->map.max_entries > 1UL << 31) return -EINVAL; - } - if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); + dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets, dtab->map.numa_node); if (!dtab->dev_index_head) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 88c71de0a0a95318d553752b6a76101e6e0666ba..0c74cc9012d5c65b0510c2d6bdbd68cfddc527fc 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -495,7 +495,13 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) num_possible_cpus()); } - /* hash table size must be power of 2 */ + /* hash table size must be power of 2; roundup_pow_of_two() can overflow + * into UB on 32-bit arches, so check that first + */ + err = -E2BIG; + if (htab->map.max_entries > 1UL << 31) + goto free_htab; + htab->n_buckets = roundup_pow_of_two(htab->map.max_entries); htab->elem_size = sizeof(struct htab_elem) + @@ -505,10 +511,8 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) else htab->elem_size += round_up(htab->map.value_size, 8); - err = -E2BIG; - /* prevent zero size kmalloc and check for u32 overflow */ - if (htab->n_buckets == 0 || - htab->n_buckets > U32_MAX / sizeof(struct bucket)) + /* check for u32 overflow */ + if (htab->n_buckets > U32_MAX / sizeof(struct bucket)) goto free_htab; err = -ENOMEM; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 34135fbd6097e790d7047095fc2d1b22c869a336..758510b46d87bb76d9c6e981cb7367f9e5cbe43e 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -328,7 +328,7 @@ static inline void __bpf_spin_lock_irqsave(struct bpf_spin_lock *lock) __this_cpu_write(irqsave_flags, flags); } -notrace BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) +NOTRACE_BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) { __bpf_spin_lock_irqsave(lock); return 0; @@ -350,7 +350,7 @@ static inline void __bpf_spin_unlock_irqrestore(struct bpf_spin_lock *lock) local_irq_restore(flags); } -notrace BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) +NOTRACE_BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) { __bpf_spin_unlock_irqrestore(lock); return 0; @@ -753,19 +753,20 @@ static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype, /* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary * arguments representation. */ -#define MAX_BPRINTF_BUF_LEN 512 +#define MAX_BPRINTF_BIN_ARGS 512 /* Support executing three nested bprintf helper calls on a given CPU */ #define MAX_BPRINTF_NEST_LEVEL 3 struct bpf_bprintf_buffers { - char tmp_bufs[MAX_BPRINTF_NEST_LEVEL][MAX_BPRINTF_BUF_LEN]; + char bin_args[MAX_BPRINTF_BIN_ARGS]; + char buf[MAX_BPRINTF_BUF]; }; -static DEFINE_PER_CPU(struct bpf_bprintf_buffers, bpf_bprintf_bufs); + +static DEFINE_PER_CPU(struct bpf_bprintf_buffers[MAX_BPRINTF_NEST_LEVEL], bpf_bprintf_bufs); static DEFINE_PER_CPU(int, bpf_bprintf_nest_level); -static int try_get_fmt_tmp_buf(char **tmp_buf) +static int try_get_buffers(struct bpf_bprintf_buffers **bufs) { - struct bpf_bprintf_buffers *bufs; int nest_level; preempt_disable(); @@ -775,18 +776,19 @@ static int try_get_fmt_tmp_buf(char **tmp_buf) preempt_enable(); return -EBUSY; } - bufs = this_cpu_ptr(&bpf_bprintf_bufs); - *tmp_buf = bufs->tmp_bufs[nest_level - 1]; + *bufs = this_cpu_ptr(&bpf_bprintf_bufs[nest_level - 1]); return 0; } -void bpf_bprintf_cleanup(void) +void bpf_bprintf_cleanup(struct bpf_bprintf_data *data) { - if (this_cpu_read(bpf_bprintf_nest_level)) { - this_cpu_dec(bpf_bprintf_nest_level); - preempt_enable(); - } + if (!data->bin_args && !data->buf) + return; + if (WARN_ON_ONCE(this_cpu_read(bpf_bprintf_nest_level) == 0)) + return; + this_cpu_dec(bpf_bprintf_nest_level); + preempt_enable(); } /* @@ -795,18 +797,20 @@ void bpf_bprintf_cleanup(void) * Returns a negative value if fmt is an invalid format string or 0 otherwise. * * This can be used in two ways: - * - Format string verification only: when bin_args is NULL + * - Format string verification only: when data->get_bin_args is false * - Arguments preparation: in addition to the above verification, it writes in - * bin_args a binary representation of arguments usable by bstr_printf where - * pointers from BPF have been sanitized. + * data->bin_args a binary representation of arguments usable by bstr_printf + * where pointers from BPF have been sanitized. * * In argument preparation mode, if 0 is returned, safe temporary buffers are * allocated and bpf_bprintf_cleanup should be called to free them after use. */ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, - u32 **bin_args, u32 num_args) + u32 num_args, struct bpf_bprintf_data *data) { + bool get_buffers = (data->get_bin_args && num_args) || data->get_buf; char *unsafe_ptr = NULL, *tmp_buf = NULL, *tmp_buf_end, *fmt_end; + struct bpf_bprintf_buffers *buffers = NULL; size_t sizeof_cur_arg, sizeof_cur_ip; int err, i, num_spec = 0; u64 cur_arg; @@ -817,14 +821,19 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, return -EINVAL; fmt_size = fmt_end - fmt; - if (bin_args) { - if (num_args && try_get_fmt_tmp_buf(&tmp_buf)) - return -EBUSY; + if (get_buffers && try_get_buffers(&buffers)) + return -EBUSY; - tmp_buf_end = tmp_buf + MAX_BPRINTF_BUF_LEN; - *bin_args = (u32 *)tmp_buf; + if (data->get_bin_args) { + if (num_args) + tmp_buf = buffers->bin_args; + tmp_buf_end = tmp_buf + MAX_BPRINTF_BIN_ARGS; + data->bin_args = (u32 *)tmp_buf; } + if (data->get_buf) + data->buf = buffers->buf; + for (i = 0; i < fmt_size; i++) { if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) { err = -EINVAL; @@ -1018,31 +1027,33 @@ nocopy_fmt: err = 0; out: if (err) - bpf_bprintf_cleanup(); + bpf_bprintf_cleanup(data); return err; } BPF_CALL_5(bpf_snprintf, char *, str, u32, str_size, char *, fmt, - const void *, data, u32, data_len) + const void *, args, u32, data_len) { + struct bpf_bprintf_data data = { + .get_bin_args = true, + }; int err, num_args; - u32 *bin_args; if (data_len % 8 || data_len > MAX_BPRINTF_VARARGS * 8 || - (data_len && !data)) + (data_len && !args)) return -EINVAL; num_args = data_len / 8; /* ARG_PTR_TO_CONST_STR guarantees that fmt is zero-terminated so we * can safely give an unbounded size. */ - err = bpf_bprintf_prepare(fmt, UINT_MAX, data, &bin_args, num_args); + err = bpf_bprintf_prepare(fmt, UINT_MAX, args, num_args, &data); if (err < 0) return err; - err = bstr_printf(str, str_size, fmt, bin_args); + err = bstr_printf(str, str_size, fmt, data.bin_args); - bpf_bprintf_cleanup(); + bpf_bprintf_cleanup(&data); return err + 1; } @@ -1080,6 +1091,7 @@ struct bpf_hrtimer { struct bpf_prog *prog; void __rcu *callback_fn; void *value; + struct rcu_head rcu; }; /* the actual struct hidden inside uapi struct bpf_timer */ @@ -1301,6 +1313,7 @@ BPF_CALL_1(bpf_timer_cancel, struct bpf_timer_kern *, timer) if (in_nmi()) return -EOPNOTSUPP; + rcu_read_lock(); __bpf_spin_lock_irqsave(&timer->lock); t = timer->timer; if (!t) { @@ -1322,6 +1335,7 @@ out: * if it was running. */ ret = ret ?: hrtimer_cancel(&t->timer); + rcu_read_unlock(); return ret; } @@ -1376,7 +1390,7 @@ out: */ if (this_cpu_read(hrtimer_running) != t) hrtimer_cancel(&t->timer); - kfree(t); + kfree_rcu(t, rcu); } BPF_CALL_2(bpf_kptr_xchg, void *, map_value, void *, ptr) diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index f86db3cf721238861e69e029403ce476017d7e86..f0fd936cef31938e97c57fd4198ec50a9de184e8 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -94,11 +94,14 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) } else if (value_size / 8 > sysctl_perf_event_max_stack) return ERR_PTR(-EINVAL); - /* hash table size must be power of 2 */ - n_buckets = roundup_pow_of_two(attr->max_entries); - if (!n_buckets) + /* hash table size must be power of 2; roundup_pow_of_two() can overflow + * into UB on 32-bit arches, so check that first + */ + if (attr->max_entries > 1UL << 31) return ERR_PTR(-E2BIG); + n_buckets = roundup_pow_of_two(attr->max_entries); + cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap); smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr)); if (!smap) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 23b6d57b5eef238647d7333cbe31ff0b3808168a..18b3f429abe1794d3214a6d8c2658229af683e08 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4965,6 +4965,11 @@ static int check_stack_access_within_bounds( err = check_stack_slot_within_bounds(min_off, state, type); if (!err && max_off > 0) err = -EINVAL; /* out of stack access into non-negative offsets */ + if (!err && access_size < 0) + /* access_size should not be negative (or overflow an int); others checks + * along the way should have prevented such an access. + */ + err = -EFAULT; /* invalid negative access size; integer overflow? */ if (err) { if (tnum_is_const(reg->var_off)) { @@ -7448,6 +7453,7 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env, struct bpf_reg_state *fmt_reg = ®s[BPF_REG_3]; struct bpf_reg_state *data_len_reg = ®s[BPF_REG_5]; struct bpf_map *fmt_map = fmt_reg->map_ptr; + struct bpf_bprintf_data data = {}; int err, fmt_map_off, num_args; u64 fmt_addr; char *fmt; @@ -7472,7 +7478,7 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env, /* We are also guaranteed that fmt+fmt_map_off is NULL terminated, we * can focus on validating the format specifiers. */ - err = bpf_bprintf_prepare(fmt, UINT_MAX, NULL, NULL, num_args); + err = bpf_bprintf_prepare(fmt, UINT_MAX, NULL, num_args, &data); if (err < 0) verbose(env, "Invalid format string\n"); @@ -13171,8 +13177,7 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) f = fdget(fd); map = __bpf_map_get(f); if (IS_ERR(map)) { - verbose(env, "fd %d is not pointing to valid bpf_map\n", - insn[0].imm); + verbose(env, "fd %d is not pointing to valid bpf_map\n", fd); return PTR_ERR(map); } diff --git a/kernel/cpu.c b/kernel/cpu.c index e6f0101941ed8772205c5657a22257d370313f6b..e0e09b700b43032fa47b0a09c21464c0ba45afd5 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2788,7 +2788,8 @@ enum cpu_mitigations { }; static enum cpu_mitigations cpu_mitigations __ro_after_init = - CPU_MITIGATIONS_AUTO; + IS_ENABLED(CONFIG_CPU_MITIGATIONS) ? CPU_MITIGATIONS_AUTO : + CPU_MITIGATIONS_OFF; static int __init mitigations_parse_cmdline(char *arg) { diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 63859a101ed8319a77d03a0ea378e980d69fdd17..d4215739efc71ae2477c4c0d43e8c946e974b812 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -296,7 +296,7 @@ void *dma_direct_alloc(struct device *dev, size_t size, } else { ret = page_address(page); if (dma_set_decrypted(dev, ret, size)) - goto out_free_pages; + goto out_leak_pages; } memset(ret, 0, size); @@ -317,6 +317,8 @@ out_encrypt_pages: out_free_pages: __dma_direct_free_pages(dev, page, size); return NULL; +out_leak_pages: + return NULL; } void dma_direct_free(struct device *dev, size_t size, @@ -379,12 +381,11 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size, ret = page_address(page); if (dma_set_decrypted(dev, ret, size)) - goto out_free_pages; + goto out_leak_pages; memset(ret, 0, size); *dma_handle = phys_to_dma_direct(dev, page_to_phys(page)); return page; -out_free_pages: - __dma_direct_free_pages(dev, page, size); +out_leak_pages: return NULL; } diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index ad6333c3fe1ffeffa74bd5c03b420130c266f6af..db89ac94e7db4f6507f4d6451679ae7d8f22d266 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -654,8 +654,7 @@ static int swiotlb_do_find_slots(struct device *dev, int area_index, dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(dev, mem->start) & boundary_mask; unsigned long max_slots = get_max_slots(boundary_mask); - unsigned int iotlb_align_mask = - dma_get_min_align_mask(dev) & ~(IO_TLB_SIZE - 1); + unsigned int iotlb_align_mask = dma_get_min_align_mask(dev); unsigned int nslots = nr_slots(alloc_size), stride; unsigned int index, wrap, count = 0, i; unsigned int offset = swiotlb_align_offset(dev, orig_addr); @@ -666,6 +665,14 @@ static int swiotlb_do_find_slots(struct device *dev, int area_index, BUG_ON(!nslots); BUG_ON(area_index >= mem->nareas); + /* + * Ensure that the allocation is at least slot-aligned and update + * 'iotlb_align_mask' to ignore bits that will be preserved when + * offsetting into the allocation. + */ + alloc_align_mask |= (IO_TLB_SIZE - 1); + iotlb_align_mask &= ~alloc_align_mask; + /* * For mappings with an alignment requirement don't bother looping to * unaligned slots once we found an aligned one. For allocations of diff --git a/kernel/entry/common.c b/kernel/entry/common.c index be61332c66b54a02b37d7a1847001b23a82d910e..ccf2b1e1b40be535913589bf9b3519fc5f568e67 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -77,8 +77,14 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall, /* Either of the above might have changed the syscall number */ syscall = syscall_get_nr(current, regs); - if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) + if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) { trace_sys_enter(regs, syscall); + /* + * Probes or BPF hooks in the tracepoint may have changed the + * system call number as well. + */ + syscall = syscall_get_nr(current, regs); + } syscall_enter_audit(regs, syscall); diff --git a/kernel/fork.c b/kernel/fork.c index 85617928041cf65054ba18dd186b373c76b40827..7e9a5919299b459eacbd88c42f1fbd3e0fe03ba5 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -662,6 +662,15 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, } else if (anon_vma_fork(tmp, mpnt)) goto fail_nomem_anon_vma_fork; tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT); + /* + * Copy/update hugetlb private vma information. + */ + if (is_vm_hugetlb_page(tmp)) + hugetlb_dup_vma_private(tmp); + + if (tmp->vm_ops && tmp->vm_ops->open) + tmp->vm_ops->open(tmp); + file = tmp->vm_file; if (file) { struct address_space *mapping = file->f_mapping; @@ -678,12 +687,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, i_mmap_unlock_write(mapping); } - /* - * Copy/update hugetlb private vma information. - */ - if (is_vm_hugetlb_page(tmp)) - hugetlb_dup_vma_private(tmp); - /* Link the vma into the MT */ mas.index = tmp->vm_start; mas.last = tmp->vm_end - 1; @@ -695,9 +698,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, if (!(tmp->vm_flags & VM_WIPEONFORK)) retval = copy_page_range(tmp, mpnt); - if (tmp->vm_ops && tmp->vm_ops->open) - tmp->vm_ops->open(tmp); - if (retval) goto loop_out; } diff --git a/kernel/kprobes.c b/kernel/kprobes.c index dbfddfa86c14e080d767b279d6085a8cb85d0a43..5b5ee060a2db54423f7880fc27f432487ca07c9a 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1567,10 +1567,17 @@ static int check_kprobe_address_safe(struct kprobe *p, jump_label_lock(); preempt_disable(); - /* Ensure it is not in reserved area nor out of text */ - if (!(core_kernel_text((unsigned long) p->addr) || - is_module_text_address((unsigned long) p->addr)) || - in_gate_area_no_mm((unsigned long) p->addr) || + /* Ensure the address is in a text area, and find a module if exists. */ + *probed_mod = NULL; + if (!core_kernel_text((unsigned long) p->addr)) { + *probed_mod = __module_text_address((unsigned long) p->addr); + if (!(*probed_mod)) { + ret = -EINVAL; + goto out; + } + } + /* Ensure it is not in reserved area. */ + if (in_gate_area_no_mm((unsigned long) p->addr) || within_kprobe_blacklist((unsigned long) p->addr) || jump_label_text_reserved(p->addr, p->addr) || static_call_text_reserved(p->addr, p->addr) || @@ -1580,8 +1587,7 @@ static int check_kprobe_address_safe(struct kprobe *p, goto out; } - /* Check if 'p' is probing a module. */ - *probed_mod = __module_text_address((unsigned long) p->addr); + /* Get module refcount and reject __init functions for loaded modules. */ if (*probed_mod) { /* * We must hold a refcount of the probed module while updating diff --git a/kernel/module/main.c b/kernel/module/main.c index 7a376e26de85b23fa83aa651ecb2bc417f50a44b..554aba47ab689d854dd19cbdeebf2053f4788977 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2434,6 +2434,11 @@ static void do_free_init(struct work_struct *w) } } +void flush_module_init_free_work(void) +{ + flush_work(&init_free_wq); +} + #undef MODULE_PARAM_PREFIX #define MODULE_PARAM_PREFIX "module." /* Default value for module->async_probe_requested */ @@ -2524,8 +2529,8 @@ static noinline int do_init_module(struct module *mod) * Note that module_alloc() on most architectures creates W+X page * mappings which won't be cleaned up until do_free_init() runs. Any * code such as mark_rodata_ro() which depends on those mappings to - * be cleaned up needs to sync with the queued work - ie - * rcu_barrier() + * be cleaned up needs to sync with the queued work by invoking + * flush_module_init_free_work(). */ if (llist_add(&freeinit->node, &init_free_list)) schedule_work(&init_free_wq); diff --git a/kernel/panic.c b/kernel/panic.c index 63e94f3bd8dcda37c2edc27547131d13c786799a..e6c2bf04a32c04f070cbb0e2cae8ba79c758043e 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -441,6 +441,14 @@ void panic(const char *fmt, ...) /* Do not scroll important messages printed above */ suppress_printk = 1; + + /* + * The final messages may not have been printed if in a context that + * defers printing (such as NMI) and irq_work is not available. + * Explicitly flush the kernel log buffer one last time. + */ + console_flush_on_panic(CONSOLE_FLUSH_PENDING); + local_irq_enable(); for (i = 0; ; i += PANIC_TIMER_STEP) { touch_softlockup_watchdog(); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index fa3bf161d13f79a6d28dc891d3b5708871e4a969..3aae526cc4aacaf582321d64dd4c8bdbecb18b08 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -106,6 +106,12 @@ static void s2idle_enter(void) swait_event_exclusive(s2idle_wait_head, s2idle_state == S2IDLE_STATE_WAKE); + /* + * Kick all CPUs to ensure that they resume their timers and restore + * consistent system state. + */ + wake_up_all_idle_cpus(); + cpus_read_unlock(); raw_spin_lock_irq(&s2idle_lock); @@ -192,6 +198,7 @@ static int __init mem_sleep_default_setup(char *str) if (mem_sleep_labels[state] && !strcmp(str, mem_sleep_labels[state])) { mem_sleep_default = state; + mem_sleep_current = state; break; } diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index cc53fb77f77cc2a22c4ac5f06320319cb1707e2f..0ae06d5046bb08fb0deac33a3683bbb2cae3d86d 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1797,10 +1797,23 @@ static bool console_waiter; */ static void console_lock_spinning_enable(void) { + /* + * Do not use spinning in panic(). The panic CPU wants to keep the lock. + * Non-panic CPUs abandon the flush anyway. + * + * Just keep the lockdep annotation. The panic-CPU should avoid + * taking console_owner_lock because it might cause a deadlock. + * This looks like the easiest way how to prevent false lockdep + * reports without handling races a lockless way. + */ + if (panic_in_progress()) + goto lockdep; + raw_spin_lock(&console_owner_lock); console_owner = current; raw_spin_unlock(&console_owner_lock); +lockdep: /* The waiter may spin on us after setting console_owner */ spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); } @@ -1824,6 +1837,22 @@ static int console_lock_spinning_disable_and_check(void) { int waiter; + /* + * Ignore spinning waiters during panic() because they might get stopped + * or blocked at any time, + * + * It is safe because nobody is allowed to start spinning during panic + * in the first place. If there has been a waiter then non panic CPUs + * might stay spinning. They would get stopped anyway. The panic context + * will never start spinning and an interrupted spin on panic CPU will + * never continue. + */ + if (panic_in_progress()) { + /* Keep lockdep happy. */ + spin_release(&console_owner_dep_map, _THIS_IP_); + return 0; + } + raw_spin_lock(&console_owner_lock); waiter = READ_ONCE(console_waiter); console_owner = NULL; @@ -1918,6 +1947,12 @@ static int console_trylock_spinning(void) */ mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_); + /* + * Update @console_may_schedule for trylock because the previous + * owner may have been schedulable. + */ + console_may_schedule = 0; + return 1; } @@ -3016,6 +3051,21 @@ static int __init keep_bootcon_setup(char *str) early_param("keep_bootcon", keep_bootcon_setup); +static int console_call_setup(struct console *newcon, char *options) +{ + int err; + + if (!newcon->setup) + return 0; + + /* Synchronize with possible boot console. */ + console_lock(); + err = newcon->setup(newcon, options); + console_unlock(); + + return err; +} + /* * This is called by register_console() to try to match * the newly registered console with any of the ones selected @@ -3051,8 +3101,8 @@ static int try_enable_preferred_console(struct console *newcon, if (_braille_register_console(newcon, c)) return 0; - if (newcon->setup && - (err = newcon->setup(newcon, c->options)) != 0) + err = console_call_setup(newcon, c->options); + if (err) return err; } newcon->flags |= CON_ENABLED; @@ -3078,7 +3128,7 @@ static void try_enable_default_console(struct console *newcon) if (newcon->index < 0) newcon->index = 0; - if (newcon->setup && newcon->setup(newcon, NULL) != 0) + if (console_call_setup(newcon, NULL) != 0) return; newcon->flags |= CON_ENABLED; diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 9d7464a90f85d65b574c22d4a28dc069bddfe0af..61f9503a5fe9c260f4f3bcde7b990de6d6ea27ba 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -4465,13 +4465,16 @@ static void __init rcu_start_exp_gp_kworkers(void) rcu_exp_gp_kworker = kthread_create_worker(0, gp_kworker_name); if (IS_ERR_OR_NULL(rcu_exp_gp_kworker)) { pr_err("Failed to create %s!\n", gp_kworker_name); + rcu_exp_gp_kworker = NULL; return; } rcu_exp_par_gp_kworker = kthread_create_worker(0, par_gp_kworker_name); if (IS_ERR_OR_NULL(rcu_exp_par_gp_kworker)) { pr_err("Failed to create %s!\n", par_gp_kworker_name); + rcu_exp_par_gp_kworker = NULL; kthread_destroy_worker(rcu_exp_gp_kworker); + rcu_exp_gp_kworker = NULL; return; } diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 6d2cbed96b46228c552150dd2098a671a1e9f6c3..75e8d9652f7bbc2aa97b792b966bcf5684615795 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -427,7 +427,12 @@ static void sync_rcu_exp_select_node_cpus(struct kthread_work *wp) __sync_rcu_exp_select_node_cpus(rewp); } -static inline bool rcu_gp_par_worker_started(void) +static inline bool rcu_exp_worker_started(void) +{ + return !!READ_ONCE(rcu_exp_gp_kworker); +} + +static inline bool rcu_exp_par_worker_started(void) { return !!READ_ONCE(rcu_exp_par_gp_kworker); } @@ -477,7 +482,12 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp) __sync_rcu_exp_select_node_cpus(rewp); } -static inline bool rcu_gp_par_worker_started(void) +static inline bool rcu_exp_worker_started(void) +{ + return !!READ_ONCE(rcu_gp_wq); +} + +static inline bool rcu_exp_par_worker_started(void) { return !!READ_ONCE(rcu_par_gp_wq); } @@ -540,7 +550,7 @@ static void sync_rcu_exp_select_cpus(void) rnp->exp_need_flush = false; if (!READ_ONCE(rnp->expmask)) continue; /* Avoid early boot non-existent wq. */ - if (!rcu_gp_par_worker_started() || + if (!rcu_exp_par_worker_started() || rcu_scheduler_active != RCU_SCHEDULER_RUNNING || rcu_is_last_leaf_node(rnp)) { /* No worker started yet or last leaf, do direct call. */ @@ -910,7 +920,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) */ void synchronize_rcu_expedited(void) { - bool boottime = (rcu_scheduler_active == RCU_SCHEDULER_INIT); + bool use_worker; unsigned long flags; struct rcu_exp_work rew; struct rcu_node *rnp; @@ -921,6 +931,9 @@ void synchronize_rcu_expedited(void) lock_is_held(&rcu_sched_lock_map), "Illegal synchronize_rcu_expedited() in RCU read-side critical section"); + use_worker = (rcu_scheduler_active != RCU_SCHEDULER_INIT) && + rcu_exp_worker_started(); + /* Is the state is such that the call is a grace period? */ if (rcu_blocking_is_gp()) { // Note well that this code runs with !PREEMPT && !SMP. @@ -950,7 +963,7 @@ void synchronize_rcu_expedited(void) return; /* Someone else did our work for us. */ /* Ensure that load happens before action based on it. */ - if (unlikely(boottime)) { + if (unlikely(!use_worker)) { /* Direct call during scheduler init and early_initcalls(). */ rcu_exp_sel_wait_wake(s); } else { @@ -968,7 +981,7 @@ void synchronize_rcu_expedited(void) /* Let the next expedited grace period start. */ mutex_unlock(&rcu_state.exp_mutex); - if (likely(!boottime)) + if (likely(use_worker)) synchronize_rcu_expedited_destroy_work(&rew); } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 2558ab9033bee2ba6b8bb3687b00d341c4407dbd..91c101ecfef9f9912d8e7164477bf19dbc708901 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6656,7 +6656,7 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu if (!available_idle_cpu(cpu)) { idle = false; if (*idle_cpu == -1) { - if (sched_idle_cpu(cpu) && cpumask_test_cpu(cpu, p->cpus_ptr)) { + if (sched_idle_cpu(cpu) && cpumask_test_cpu(cpu, cpus)) { *idle_cpu = cpu; break; } @@ -6664,7 +6664,7 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu } break; } - if (*idle_cpu == -1 && cpumask_test_cpu(cpu, p->cpus_ptr)) + if (*idle_cpu == -1 && cpumask_test_cpu(cpu, cpus)) *idle_cpu = cpu; } @@ -6678,13 +6678,19 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu /* * Scan the local SMT mask for idle CPUs. */ -static int select_idle_smt(struct task_struct *p, int target) +static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target) { int cpu; for_each_cpu_and(cpu, cpu_smt_mask(target), p->cpus_ptr) { if (cpu == target) continue; + /* + * Check if the CPU is in the LLC scheduling domain of @target. + * Due to isolcpus, there is no guarantee that all the siblings are in the domain. + */ + if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) + continue; if (available_idle_cpu(cpu) || sched_idle_cpu(cpu)) return cpu; } @@ -6708,7 +6714,7 @@ static inline int select_idle_core(struct task_struct *p, int core, struct cpuma return __select_idle_cpu(core, p); } -static inline int select_idle_smt(struct task_struct *p, int target) +static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target) { return -1; } @@ -6970,7 +6976,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) has_idle_core = test_idle_cores(target); if (!has_idle_core && cpus_share_cache(prev, target)) { - i = select_idle_smt(p, prev); + i = select_idle_smt(p, sd, prev); if ((unsigned int)i < nr_cpumask_bits) return i; } diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 0c5be7ebb1dcae2c15c1ff5aff2d99c4717de836..08b16d20c85bbf5580a47d587bc35a489760b365 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -161,6 +161,9 @@ | MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK \ | MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK) +static DEFINE_MUTEX(membarrier_ipi_mutex); +#define SERIALIZE_IPI() guard(mutex)(&membarrier_ipi_mutex) + static void ipi_mb(void *info) { smp_mb(); /* IPIs should be serializing but paranoid. */ @@ -258,6 +261,7 @@ static int membarrier_global_expedited(void) if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) return -ENOMEM; + SERIALIZE_IPI(); cpus_read_lock(); rcu_read_lock(); for_each_online_cpu(cpu) { @@ -346,6 +350,7 @@ static int membarrier_private_expedited(int flags, int cpu_id) if (cpu_id < 0 && !zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) return -ENOMEM; + SERIALIZE_IPI(); cpus_read_lock(); if (cpu_id >= 0) { @@ -459,6 +464,7 @@ static int sync_runqueues_membarrier_state(struct mm_struct *mm) * between threads which are users of @mm has its membarrier state * updated. */ + SERIALIZE_IPI(); cpus_read_lock(); rcu_read_lock(); for_each_online_cpu(cpu) { diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 76bafa8d331a76060721d43903a03dc4184c4c6f..3a2335bc1d58b27b34b1df2356aaa0365916c723 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -37,6 +37,8 @@ static struct ctl_table sched_rt_sysctls[] = { .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = sched_rt_handler, + .extra1 = SYSCTL_ONE, + .extra2 = SYSCTL_INT_MAX, }, { .procname = "sched_rt_runtime_us", @@ -44,6 +46,8 @@ static struct ctl_table sched_rt_sysctls[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = sched_rt_handler, + .extra1 = SYSCTL_NEG_ONE, + .extra2 = SYSCTL_INT_MAX, }, { .procname = "sched_rr_timeslice_ms", @@ -2970,9 +2974,6 @@ static int sched_rt_global_constraints(void) #ifdef CONFIG_SYSCTL static int sched_rt_global_validate(void) { - if (sysctl_sched_rt_period <= 0) - return -EINVAL; - if ((sysctl_sched_rt_runtime != RUNTIME_INF) && ((sysctl_sched_rt_runtime > sysctl_sched_rt_period) || ((u64)sysctl_sched_rt_runtime * @@ -3003,7 +3004,7 @@ static int sched_rt_handler(struct ctl_table *table, int write, void *buffer, old_period = sysctl_sched_rt_period; old_runtime = sysctl_sched_rt_runtime; - ret = proc_dointvec(table, write, buffer, lenp, ppos); + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!ret && write) { ret = sched_rt_global_validate(); @@ -3047,6 +3048,9 @@ static int sched_rr_handler(struct ctl_table *table, int write, void *buffer, sched_rr_timeslice = sysctl_sched_rr_timeslice <= 0 ? RR_TIMESLICE : msecs_to_jiffies(sysctl_sched_rr_timeslice); + + if (sysctl_sched_rr_timeslice <= 0) + sysctl_sched_rr_timeslice = jiffies_to_msecs(RR_TIMESLICE); } mutex_unlock(&mutex); diff --git a/kernel/sys.c b/kernel/sys.c index c85e1abf7b7c79cfc5ee617b0d3f8e2f4ac7f238..d06eda1387b690ee6d85a1348048e9464cb6f98d 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1778,74 +1778,87 @@ void getrusage(struct task_struct *p, int who, struct rusage *r) struct task_struct *t; unsigned long flags; u64 tgutime, tgstime, utime, stime; - unsigned long maxrss = 0; + unsigned long maxrss; + struct mm_struct *mm; + struct signal_struct *sig = p->signal; + unsigned int seq = 0; - memset((char *)r, 0, sizeof (*r)); +retry: + memset(r, 0, sizeof(*r)); utime = stime = 0; + maxrss = 0; if (who == RUSAGE_THREAD) { task_cputime_adjusted(current, &utime, &stime); accumulate_thread_rusage(p, r); - maxrss = p->signal->maxrss; - goto out; + maxrss = sig->maxrss; + goto out_thread; } - if (!lock_task_sighand(p, &flags)) - return; + flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq); switch (who) { case RUSAGE_BOTH: case RUSAGE_CHILDREN: - utime = p->signal->cutime; - stime = p->signal->cstime; - r->ru_nvcsw = p->signal->cnvcsw; - r->ru_nivcsw = p->signal->cnivcsw; - r->ru_minflt = p->signal->cmin_flt; - r->ru_majflt = p->signal->cmaj_flt; - r->ru_inblock = p->signal->cinblock; - r->ru_oublock = p->signal->coublock; - maxrss = p->signal->cmaxrss; + utime = sig->cutime; + stime = sig->cstime; + r->ru_nvcsw = sig->cnvcsw; + r->ru_nivcsw = sig->cnivcsw; + r->ru_minflt = sig->cmin_flt; + r->ru_majflt = sig->cmaj_flt; + r->ru_inblock = sig->cinblock; + r->ru_oublock = sig->coublock; + maxrss = sig->cmaxrss; if (who == RUSAGE_CHILDREN) break; fallthrough; case RUSAGE_SELF: - thread_group_cputime_adjusted(p, &tgutime, &tgstime); - utime += tgutime; - stime += tgstime; - r->ru_nvcsw += p->signal->nvcsw; - r->ru_nivcsw += p->signal->nivcsw; - r->ru_minflt += p->signal->min_flt; - r->ru_majflt += p->signal->maj_flt; - r->ru_inblock += p->signal->inblock; - r->ru_oublock += p->signal->oublock; - if (maxrss < p->signal->maxrss) - maxrss = p->signal->maxrss; - t = p; - do { + r->ru_nvcsw += sig->nvcsw; + r->ru_nivcsw += sig->nivcsw; + r->ru_minflt += sig->min_flt; + r->ru_majflt += sig->maj_flt; + r->ru_inblock += sig->inblock; + r->ru_oublock += sig->oublock; + if (maxrss < sig->maxrss) + maxrss = sig->maxrss; + + rcu_read_lock(); + __for_each_thread(sig, t) accumulate_thread_rusage(t, r); - } while_each_thread(p, t); + rcu_read_unlock(); + break; default: BUG(); } - unlock_task_sighand(p, &flags); -out: - r->ru_utime = ns_to_kernel_old_timeval(utime); - r->ru_stime = ns_to_kernel_old_timeval(stime); + if (need_seqretry(&sig->stats_lock, seq)) { + seq = 1; + goto retry; + } + done_seqretry_irqrestore(&sig->stats_lock, seq, flags); - if (who != RUSAGE_CHILDREN) { - struct mm_struct *mm = get_task_mm(p); + if (who == RUSAGE_CHILDREN) + goto out_children; - if (mm) { - setmax_mm_hiwater_rss(&maxrss, mm); - mmput(mm); - } + thread_group_cputime_adjusted(p, &tgutime, &tgstime); + utime += tgutime; + stime += tgstime; + +out_thread: + mm = get_task_mm(p); + if (mm) { + setmax_mm_hiwater_rss(&maxrss, mm); + mmput(mm); } + +out_children: r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */ + r->ru_utime = ns_to_kernel_old_timeval(utime); + r->ru_stime = ns_to_kernel_old_timeval(stime); } SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru) diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 1c90e710d537f1ede70f09ce0216c8d229d3839e..cc6db3bce1b2f1966dc3a63ccefe91fa39c33650 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -126,6 +126,7 @@ static DECLARE_WORK(watchdog_work, clocksource_watchdog_work); static DEFINE_SPINLOCK(watchdog_lock); static int watchdog_running; static atomic_t watchdog_reset_pending; +static int64_t watchdog_max_interval; static inline void clocksource_watchdog_lock(unsigned long *flags) { @@ -144,6 +145,7 @@ static void __clocksource_change_rating(struct clocksource *cs, int rating); * Interval: 0.5sec. */ #define WATCHDOG_INTERVAL (HZ >> 1) +#define WATCHDOG_INTERVAL_MAX_NS ((2 * WATCHDOG_INTERVAL) * (NSEC_PER_SEC / HZ)) static void clocksource_watchdog_work(struct work_struct *work) { @@ -396,8 +398,8 @@ static inline void clocksource_reset_watchdog(void) static void clocksource_watchdog(struct timer_list *unused) { u64 csnow, wdnow, cslast, wdlast, delta; + int64_t wd_nsec, cs_nsec, interval; int next_cpu, reset_pending; - int64_t wd_nsec, cs_nsec; struct clocksource *cs; enum wd_read_status read_ret; unsigned long extra_wait = 0; @@ -467,6 +469,27 @@ static void clocksource_watchdog(struct timer_list *unused) if (atomic_read(&watchdog_reset_pending)) continue; + /* + * The processing of timer softirqs can get delayed (usually + * on account of ksoftirqd not getting to run in a timely + * manner), which causes the watchdog interval to stretch. + * Skew detection may fail for longer watchdog intervals + * on account of fixed margins being used. + * Some clocksources, e.g. acpi_pm, cannot tolerate + * watchdog intervals longer than a few seconds. + */ + interval = max(cs_nsec, wd_nsec); + if (unlikely(interval > WATCHDOG_INTERVAL_MAX_NS)) { + if (system_state > SYSTEM_SCHEDULING && + interval > 2 * watchdog_max_interval) { + watchdog_max_interval = interval; + pr_warn("Long readout interval, skipping watchdog check: cs_nsec: %lld wd_nsec: %lld\n", + cs_nsec, wd_nsec); + } + watchdog_timer.expires = jiffies; + continue; + } + /* Check the deviation from the watchdog clocksource. */ md = cs->uncertainty_margin + watchdog->uncertainty_margin; if (abs(cs_nsec - wd_nsec) > md) { diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 5561dabc9b225cb8dcaedf824e8ff9e4b3199ca2..9bb88836c42e60c973e321bc84ecbcd60df6642e 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1082,6 +1082,7 @@ static int enqueue_hrtimer(struct hrtimer *timer, enum hrtimer_mode mode) { debug_activate(timer, mode); + WARN_ON_ONCE(!base->cpu_base->online); base->cpu_base->active_bases |= 1 << base->index; @@ -2180,6 +2181,7 @@ int hrtimers_prepare_cpu(unsigned int cpu) cpu_base->softirq_next_timer = NULL; cpu_base->expires_next = KTIME_MAX; cpu_base->softirq_expires_next = KTIME_MAX; + cpu_base->online = 1; hrtimer_cpu_base_init_expiry_lock(cpu_base); return 0; } @@ -2247,6 +2249,7 @@ int hrtimers_cpu_dying(unsigned int dying_cpu) smp_call_function_single(ncpu, retrigger_next_event, NULL, 0); raw_spin_unlock(&new_base->lock); + old_base->online = 0; raw_spin_unlock(&old_base->lock); return 0; @@ -2263,7 +2266,7 @@ void __init hrtimers_init(void) /** * schedule_hrtimeout_range_clock - sleep until timeout * @expires: timeout value (ktime_t) - * @delta: slack in expires timeout (ktime_t) + * @delta: slack in expires timeout (ktime_t) for SCHED_OTHER tasks * @mode: timer mode * @clock_id: timer clock to be used */ @@ -2290,6 +2293,13 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, return -EINTR; } + /* + * Override any slack passed by the user if under + * rt contraints. + */ + if (rt_task(current)) + delta = 0; + hrtimer_init_sleeper_on_stack(&t, clock_id, mode); hrtimer_set_expires_range_ns(&t.timer, *expires, delta); hrtimer_sleeper_start_expires(&t, mode); @@ -2309,7 +2319,7 @@ EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock); /** * schedule_hrtimeout_range - sleep until timeout * @expires: timeout value (ktime_t) - * @delta: slack in expires timeout (ktime_t) + * @delta: slack in expires timeout (ktime_t) for SCHED_OTHER tasks * @mode: timer mode * * Make the current task sleep until the given expiry time has @@ -2317,7 +2327,8 @@ EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock); * the current task state has been set (see set_current_state()). * * The @delta argument gives the kernel the freedom to schedule the - * actual wakeup to a time that is both power and performance friendly. + * actual wakeup to a time that is both power and performance friendly + * for regular (non RT/DL) tasks. * The kernel give the normal best effort behavior for "@expires+@delta", * but may decide to fire the timer earlier, but no earlier than @expires. * diff --git a/kernel/time/time_test.c b/kernel/time/time_test.c index 831e8e779acef50cdcb5ced72b039fdd621ad0d4..f7c3de01197c91dfec56a2e7bf6420639f18d756 100644 --- a/kernel/time/time_test.c +++ b/kernel/time/time_test.c @@ -73,7 +73,7 @@ static void time64_to_tm_test_date_range(struct kunit *test) days = div_s64(secs, 86400); - #define FAIL_MSG "%05ld/%02d/%02d (%2d) : %ld", \ + #define FAIL_MSG "%05ld/%02d/%02d (%2d) : %lld", \ year, month, mdday, yday, days KUNIT_ASSERT_EQ_MSG(test, year - 1900, result.tm_year, FAIL_MSG); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 221c8c404973ab66320224c43d50a03afec406a8..b158cbef4d8dcfb73f5f368498a5e933a18cb983 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1180,13 +1180,15 @@ static int adjust_historical_crosststamp(struct system_time_snapshot *history, } /* - * cycle_between - true if test occurs chronologically between before and after + * timestamp_in_interval - true if ts is chronologically in [start, end] + * + * True if ts occurs chronologically at or after start, and before or at end. */ -static bool cycle_between(u64 before, u64 test, u64 after) +static bool timestamp_in_interval(u64 start, u64 end, u64 ts) { - if (test > before && test < after) + if (ts >= start && ts <= end) return true; - if (test < before && before > after) + if (start > end && (ts >= start || ts <= end)) return true; return false; } @@ -1246,7 +1248,7 @@ int get_device_system_crosststamp(int (*get_time_fn) */ now = tk_clock_read(&tk->tkr_mono); interval_start = tk->tkr_mono.cycle_last; - if (!cycle_between(interval_start, cycles, now)) { + if (!timestamp_in_interval(interval_start, now, cycles)) { clock_was_set_seq = tk->clock_was_set_seq; cs_was_changed_seq = tk->cs_was_changed_seq; cycles = interval_start; @@ -1259,10 +1261,8 @@ int get_device_system_crosststamp(int (*get_time_fn) tk_core.timekeeper.offs_real); base_raw = tk->tkr_raw.base; - nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, - system_counterval.cycles); - nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, - system_counterval.cycles); + nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles); + nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, cycles); } while (read_seqcount_retry(&tk_core.seq, seq)); xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real); @@ -1277,13 +1277,13 @@ int get_device_system_crosststamp(int (*get_time_fn) bool discontinuity; /* - * Check that the counter value occurs after the provided + * Check that the counter value is not before the provided * history reference and that the history doesn't cross a * clocksource change */ if (!history_begin || - !cycle_between(history_begin->cycles, - system_counterval.cycles, cycles) || + !timestamp_in_interval(history_begin->cycles, + cycles, system_counterval.cycles) || history_begin->cs_was_changed_seq != cs_was_changed_seq) return -EINVAL; partial_history_cycles = cycles - system_counterval.cycles; diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 717fcb9fb14aa8306234b57aa4e45c466a3a720c..e09852be4e638483e7beb3feede80d3b8949f2c1 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1083,7 +1083,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option /* * We are trying to schedule the timer on the new base. * However we can't change timer's base while it is running, - * otherwise del_timer_sync() can't detect that the timer's + * otherwise timer_delete_sync() can't detect that the timer's * handler yet has not finished. This also guarantees that the * timer is serialized wrt itself. */ @@ -1121,14 +1121,16 @@ out_unlock: } /** - * mod_timer_pending - modify a pending timer's timeout - * @timer: the pending timer to be modified - * @expires: new timeout in jiffies + * mod_timer_pending - Modify a pending timer's timeout + * @timer: The pending timer to be modified + * @expires: New absolute timeout in jiffies * - * mod_timer_pending() is the same for pending timers as mod_timer(), - * but will not re-activate and modify already deleted timers. + * mod_timer_pending() is the same for pending timers as mod_timer(), but + * will not activate inactive timers. * - * It is useful for unserialized use of timers. + * Return: + * * %0 - The timer was inactive and not modified + * * %1 - The timer was active and requeued to expire at @expires */ int mod_timer_pending(struct timer_list *timer, unsigned long expires) { @@ -1137,24 +1139,27 @@ int mod_timer_pending(struct timer_list *timer, unsigned long expires) EXPORT_SYMBOL(mod_timer_pending); /** - * mod_timer - modify a timer's timeout - * @timer: the timer to be modified - * @expires: new timeout in jiffies - * - * mod_timer() is a more efficient way to update the expire field of an - * active timer (if the timer is inactive it will be activated) + * mod_timer - Modify a timer's timeout + * @timer: The timer to be modified + * @expires: New absolute timeout in jiffies * * mod_timer(timer, expires) is equivalent to: * * del_timer(timer); timer->expires = expires; add_timer(timer); * + * mod_timer() is more efficient than the above open coded sequence. In + * case that the timer is inactive, the del_timer() part is a NOP. The + * timer is in any case activated with the new expiry time @expires. + * * Note that if there are multiple unserialized concurrent users of the * same timer, then mod_timer() is the only safe way to modify the timeout, * since add_timer() cannot modify an already running timer. * - * The function returns whether it has modified a pending timer or not. - * (ie. mod_timer() of an inactive timer returns 0, mod_timer() of an - * active timer returns 1.) + * Return: + * * %0 - The timer was inactive and started + * * %1 - The timer was active and requeued to expire at @expires or + * the timer was active and not modified because @expires did + * not change the effective expiry time */ int mod_timer(struct timer_list *timer, unsigned long expires) { @@ -1165,11 +1170,18 @@ EXPORT_SYMBOL(mod_timer); /** * timer_reduce - Modify a timer's timeout if it would reduce the timeout * @timer: The timer to be modified - * @expires: New timeout in jiffies + * @expires: New absolute timeout in jiffies * * timer_reduce() is very similar to mod_timer(), except that it will only - * modify a running timer if that would reduce the expiration time (it will - * start a timer that isn't running). + * modify an enqueued timer if that would reduce the expiration time. If + * @timer is not enqueued it starts the timer. + * + * Return: + * * %0 - The timer was inactive and started + * * %1 - The timer was active and requeued to expire at @expires or + * the timer was active and not modified because @expires + * did not change the effective expiry time such that the + * timer would expire earlier than already scheduled */ int timer_reduce(struct timer_list *timer, unsigned long expires) { @@ -1178,18 +1190,21 @@ int timer_reduce(struct timer_list *timer, unsigned long expires) EXPORT_SYMBOL(timer_reduce); /** - * add_timer - start a timer - * @timer: the timer to be added + * add_timer - Start a timer + * @timer: The timer to be started * - * The kernel will do a ->function(@timer) callback from the - * timer interrupt at the ->expires point in the future. The - * current time is 'jiffies'. + * Start @timer to expire at @timer->expires in the future. @timer->expires + * is the absolute expiry time measured in 'jiffies'. When the timer expires + * timer->function(timer) will be invoked from soft interrupt context. * - * The timer's ->expires, ->function fields must be set prior calling this - * function. + * The @timer->expires and @timer->function fields must be set prior + * to calling this function. * - * Timers with an ->expires field in the past will be executed in the next - * timer tick. + * If @timer->expires is already in the past @timer will be queued to + * expire at the next timer tick. + * + * This can only operate on an inactive timer. Attempts to invoke this on + * an active timer are rejected with a warning. */ void add_timer(struct timer_list *timer) { @@ -1199,11 +1214,13 @@ void add_timer(struct timer_list *timer) EXPORT_SYMBOL(add_timer); /** - * add_timer_on - start a timer on a particular CPU - * @timer: the timer to be added - * @cpu: the CPU to start it on + * add_timer_on - Start a timer on a particular CPU + * @timer: The timer to be started + * @cpu: The CPU to start it on + * + * Same as add_timer() except that it starts the timer on the given CPU. * - * This is not very scalable on SMP. Double adds are not possible. + * See add_timer() for further details. */ void add_timer_on(struct timer_list *timer, int cpu) { @@ -1238,17 +1255,20 @@ void add_timer_on(struct timer_list *timer, int cpu) EXPORT_SYMBOL_GPL(add_timer_on); /** - * del_timer - deactivate a timer. - * @timer: the timer to be deactivated - * - * del_timer() deactivates a timer - this works on both active and inactive - * timers. - * - * The function returns whether it has deactivated a pending timer or not. - * (ie. del_timer() of an inactive timer returns 0, del_timer() of an - * active timer returns 1.) + * timer_delete - Deactivate a timer + * @timer: The timer to be deactivated + * + * The function only deactivates a pending timer, but contrary to + * timer_delete_sync() it does not take into account whether the timer's + * callback function is concurrently executed on a different CPU or not. + * It neither prevents rearming of the timer. If @timer can be rearmed + * concurrently then the return value of this function is meaningless. + * + * Return: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated */ -int del_timer(struct timer_list *timer) +int timer_delete(struct timer_list *timer) { struct timer_base *base; unsigned long flags; @@ -1264,14 +1284,23 @@ int del_timer(struct timer_list *timer) return ret; } -EXPORT_SYMBOL(del_timer); +EXPORT_SYMBOL(timer_delete); /** * try_to_del_timer_sync - Try to deactivate a timer - * @timer: timer to delete + * @timer: Timer to deactivate + * + * This function tries to deactivate a timer. On success the timer is not + * queued and the timer callback function is not running on any CPU. + * + * This function does not guarantee that the timer cannot be rearmed right + * after dropping the base lock. That needs to be prevented by the calling + * code if necessary. * - * This function tries to deactivate a timer. Upon successful (ret >= 0) - * exit the timer is not queued and the handler is not running on any CPU. + * Return: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated + * * %-1 - The timer callback function is running on a different CPU */ int try_to_del_timer_sync(struct timer_list *timer) { @@ -1365,25 +1394,20 @@ static inline void timer_sync_wait_running(struct timer_base *base) { } static inline void del_timer_wait_running(struct timer_list *timer) { } #endif -#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) /** - * del_timer_sync - deactivate a timer and wait for the handler to finish. - * @timer: the timer to be deactivated - * - * This function only differs from del_timer() on SMP: besides deactivating - * the timer it also makes sure the handler has finished executing on other - * CPUs. + * timer_delete_sync - Deactivate a timer and wait for the handler to finish. + * @timer: The timer to be deactivated * * Synchronization rules: Callers must prevent restarting of the timer, * otherwise this function is meaningless. It must not be called from * interrupt contexts unless the timer is an irqsafe one. The caller must - * not hold locks which would prevent completion of the timer's - * handler. The timer's handler must not call add_timer_on(). Upon exit the - * timer is not queued and the handler is not running on any CPU. + * not hold locks which would prevent completion of the timer's callback + * function. The timer's handler must not call add_timer_on(). Upon exit + * the timer is not queued and the handler is not running on any CPU. * - * Note: For !irqsafe timers, you must not hold locks that are held in - * interrupt context while calling this function. Even if the lock has - * nothing to do with the timer in question. Here's why:: + * For !irqsafe timers, the caller must not hold locks that are held in + * interrupt context. Even if the lock has nothing to do with the timer in + * question. Here's why:: * * CPU0 CPU1 * ---- ---- @@ -1393,16 +1417,23 @@ static inline void del_timer_wait_running(struct timer_list *timer) { } * spin_lock_irq(somelock); * * spin_lock(somelock); - * del_timer_sync(mytimer); + * timer_delete_sync(mytimer); * while (base->running_timer == mytimer); * - * Now del_timer_sync() will never return and never release somelock. - * The interrupt on the other CPU is waiting to grab somelock but - * it has interrupted the softirq that CPU0 is waiting to finish. + * Now timer_delete_sync() will never return and never release somelock. + * The interrupt on the other CPU is waiting to grab somelock but it has + * interrupted the softirq that CPU0 is waiting to finish. + * + * This function cannot guarantee that the timer is not rearmed again by + * some concurrent or preempting code, right after it dropped the base + * lock. If there is the possibility of a concurrent rearm then the return + * value of the function is meaningless. * - * The function returns whether it has deactivated a pending timer or not. + * Return: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated */ -int del_timer_sync(struct timer_list *timer) +int timer_delete_sync(struct timer_list *timer) { int ret; @@ -1442,8 +1473,7 @@ int del_timer_sync(struct timer_list *timer) return ret; } -EXPORT_SYMBOL(del_timer_sync); -#endif +EXPORT_SYMBOL(timer_delete_sync); static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list *), @@ -1465,8 +1495,8 @@ static void call_timer_fn(struct timer_list *timer, #endif /* * Couple the lock chain with the lock chain at - * del_timer_sync() by acquiring the lock_map around the fn() - * call here and in del_timer_sync(). + * timer_delete_sync() by acquiring the lock_map around the fn() + * call here and in timer_delete_sync(). */ lock_map_acquire(&lockdep_map); @@ -1933,7 +1963,7 @@ signed long __sched schedule_timeout(signed long timeout) timer_setup_on_stack(&timer.timer, process_timeout, 0); __mod_timer(&timer.timer, expire, MOD_TIMER_NOTPENDING); schedule(); - del_singleshot_timer_sync(&timer.timer); + del_timer_sync(&timer.timer); /* Remove the timer from the object tracker */ destroy_timer_on_stack(&timer.timer); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index f4a494a457c525b093d3bfdb74ef74b6bb5c3880..3fdde232eaa92d8b2c945332b21f1a3e8349e757 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -368,8 +368,6 @@ static const struct bpf_func_proto *bpf_get_probe_write_proto(void) return &bpf_probe_write_user_proto; } -static DEFINE_RAW_SPINLOCK(trace_printk_lock); - #define MAX_TRACE_PRINTK_VARARGS 3 #define BPF_TRACE_PRINTK_SIZE 1024 @@ -377,23 +375,22 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, u64, arg2, u64, arg3) { u64 args[MAX_TRACE_PRINTK_VARARGS] = { arg1, arg2, arg3 }; - u32 *bin_args; - static char buf[BPF_TRACE_PRINTK_SIZE]; - unsigned long flags; + struct bpf_bprintf_data data = { + .get_bin_args = true, + .get_buf = true, + }; int ret; - ret = bpf_bprintf_prepare(fmt, fmt_size, args, &bin_args, - MAX_TRACE_PRINTK_VARARGS); + ret = bpf_bprintf_prepare(fmt, fmt_size, args, + MAX_TRACE_PRINTK_VARARGS, &data); if (ret < 0) return ret; - raw_spin_lock_irqsave(&trace_printk_lock, flags); - ret = bstr_printf(buf, sizeof(buf), fmt, bin_args); + ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt, data.bin_args); - trace_bpf_trace_printk(buf); - raw_spin_unlock_irqrestore(&trace_printk_lock, flags); + trace_bpf_trace_printk(data.buf); - bpf_bprintf_cleanup(); + bpf_bprintf_cleanup(&data); return ret; } @@ -426,30 +423,29 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) return &bpf_trace_printk_proto; } -BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, data, +BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, args, u32, data_len) { - static char buf[BPF_TRACE_PRINTK_SIZE]; - unsigned long flags; + struct bpf_bprintf_data data = { + .get_bin_args = true, + .get_buf = true, + }; int ret, num_args; - u32 *bin_args; if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || - (data_len && !data)) + (data_len && !args)) return -EINVAL; num_args = data_len / 8; - ret = bpf_bprintf_prepare(fmt, fmt_size, data, &bin_args, num_args); + ret = bpf_bprintf_prepare(fmt, fmt_size, args, num_args, &data); if (ret < 0) return ret; - raw_spin_lock_irqsave(&trace_printk_lock, flags); - ret = bstr_printf(buf, sizeof(buf), fmt, bin_args); + ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt, data.bin_args); - trace_bpf_trace_printk(buf); - raw_spin_unlock_irqrestore(&trace_printk_lock, flags); + trace_bpf_trace_printk(data.buf); - bpf_bprintf_cleanup(); + bpf_bprintf_cleanup(&data); return ret; } @@ -471,23 +467,25 @@ const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void) } BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size, - const void *, data, u32, data_len) + const void *, args, u32, data_len) { + struct bpf_bprintf_data data = { + .get_bin_args = true, + }; int err, num_args; - u32 *bin_args; if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || - (data_len && !data)) + (data_len && !args)) return -EINVAL; num_args = data_len / 8; - err = bpf_bprintf_prepare(fmt, fmt_size, data, &bin_args, num_args); + err = bpf_bprintf_prepare(fmt, fmt_size, args, num_args, &data); if (err < 0) return err; - seq_bprintf(m, fmt, bin_args); + seq_bprintf(m, fmt, data.bin_args); - bpf_bprintf_cleanup(); + bpf_bprintf_cleanup(&data); return seq_has_overflowed(m) ? -EOVERFLOW : 0; } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 1285e7fb597ee5e53bc6efa09eceff421788a93e..337162e0c3d53e00a1fbab5ff0151a90f44cd304 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -414,7 +414,6 @@ struct rb_irq_work { struct irq_work work; wait_queue_head_t waiters; wait_queue_head_t full_waiters; - long wait_index; bool waiters_pending; bool full_waiters_pending; bool wakeup_full; @@ -908,8 +907,19 @@ static void rb_wake_up_waiters(struct irq_work *work) wake_up_all(&rbwork->waiters); if (rbwork->full_waiters_pending || rbwork->wakeup_full) { + /* Only cpu_buffer sets the above flags */ + struct ring_buffer_per_cpu *cpu_buffer = + container_of(rbwork, struct ring_buffer_per_cpu, irq_work); + + /* Called from interrupt context */ + raw_spin_lock(&cpu_buffer->reader_lock); rbwork->wakeup_full = false; rbwork->full_waiters_pending = false; + + /* Waking up all waiters, they will reset the shortest full */ + cpu_buffer->shortest_full = 0; + raw_spin_unlock(&cpu_buffer->reader_lock); + wake_up_all(&rbwork->full_waiters); } } @@ -949,14 +959,95 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu) rbwork = &cpu_buffer->irq_work; } - rbwork->wait_index++; - /* make sure the waiters see the new index */ - smp_wmb(); - /* This can be called in any context */ irq_work_queue(&rbwork->work); } +static bool rb_watermark_hit(struct trace_buffer *buffer, int cpu, int full) +{ + struct ring_buffer_per_cpu *cpu_buffer; + bool ret = false; + + /* Reads of all CPUs always waits for any data */ + if (cpu == RING_BUFFER_ALL_CPUS) + return !ring_buffer_empty(buffer); + + cpu_buffer = buffer->buffers[cpu]; + + if (!ring_buffer_empty_cpu(buffer, cpu)) { + unsigned long flags; + bool pagebusy; + + if (!full) + return true; + + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page; + ret = !pagebusy && full_hit(buffer, cpu, full); + + if (!ret && (!cpu_buffer->shortest_full || + cpu_buffer->shortest_full > full)) { + cpu_buffer->shortest_full = full; + } + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + } + return ret; +} + +static inline bool +rb_wait_cond(struct rb_irq_work *rbwork, struct trace_buffer *buffer, + int cpu, int full, ring_buffer_cond_fn cond, void *data) +{ + if (rb_watermark_hit(buffer, cpu, full)) + return true; + + if (cond(data)) + return true; + + /* + * The events can happen in critical sections where + * checking a work queue can cause deadlocks. + * After adding a task to the queue, this flag is set + * only to notify events to try to wake up the queue + * using irq_work. + * + * We don't clear it even if the buffer is no longer + * empty. The flag only causes the next event to run + * irq_work to do the work queue wake up. The worse + * that can happen if we race with !trace_empty() is that + * an event will cause an irq_work to try to wake up + * an empty queue. + * + * There's no reason to protect this flag either, as + * the work queue and irq_work logic will do the necessary + * synchronization for the wake ups. The only thing + * that is necessary is that the wake up happens after + * a task has been queued. It's OK for spurious wake ups. + */ + if (full) + rbwork->full_waiters_pending = true; + else + rbwork->waiters_pending = true; + + return false; +} + +/* + * The default wait condition for ring_buffer_wait() is to just to exit the + * wait loop the first time it is woken up. + */ +static bool rb_wait_once(void *data) +{ + long *once = data; + + /* wait_event() actually calls this twice before scheduling*/ + if (*once > 1) + return true; + + (*once)++; + return false; +} + /** * ring_buffer_wait - wait for input to the ring buffer * @buffer: buffer to wait on @@ -970,101 +1061,39 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu) int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) { struct ring_buffer_per_cpu *cpu_buffer; - DEFINE_WAIT(wait); - struct rb_irq_work *work; - long wait_index; + struct wait_queue_head *waitq; + ring_buffer_cond_fn cond; + struct rb_irq_work *rbwork; + void *data; + long once = 0; int ret = 0; + cond = rb_wait_once; + data = &once; + /* * Depending on what the caller is waiting for, either any * data in any cpu buffer, or a specific buffer, put the * caller on the appropriate wait queue. */ if (cpu == RING_BUFFER_ALL_CPUS) { - work = &buffer->irq_work; + rbwork = &buffer->irq_work; /* Full only makes sense on per cpu reads */ full = 0; } else { if (!cpumask_test_cpu(cpu, buffer->cpumask)) return -ENODEV; cpu_buffer = buffer->buffers[cpu]; - work = &cpu_buffer->irq_work; - } - - wait_index = READ_ONCE(work->wait_index); - - while (true) { - if (full) - prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE); - else - prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE); - - /* - * The events can happen in critical sections where - * checking a work queue can cause deadlocks. - * After adding a task to the queue, this flag is set - * only to notify events to try to wake up the queue - * using irq_work. - * - * We don't clear it even if the buffer is no longer - * empty. The flag only causes the next event to run - * irq_work to do the work queue wake up. The worse - * that can happen if we race with !trace_empty() is that - * an event will cause an irq_work to try to wake up - * an empty queue. - * - * There's no reason to protect this flag either, as - * the work queue and irq_work logic will do the necessary - * synchronization for the wake ups. The only thing - * that is necessary is that the wake up happens after - * a task has been queued. It's OK for spurious wake ups. - */ - if (full) - work->full_waiters_pending = true; - else - work->waiters_pending = true; - - if (signal_pending(current)) { - ret = -EINTR; - break; - } - - if (cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) - break; - - if (cpu != RING_BUFFER_ALL_CPUS && - !ring_buffer_empty_cpu(buffer, cpu)) { - unsigned long flags; - bool pagebusy; - bool done; - - if (!full) - break; - - raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); - pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page; - done = !pagebusy && full_hit(buffer, cpu, full); - - if (!cpu_buffer->shortest_full || - cpu_buffer->shortest_full > full) - cpu_buffer->shortest_full = full; - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); - if (done) - break; - } - - schedule(); - - /* Make sure to see the new wait index */ - smp_rmb(); - if (wait_index != work->wait_index) - break; + rbwork = &cpu_buffer->irq_work; } if (full) - finish_wait(&work->full_waiters, &wait); + waitq = &rbwork->full_waiters; else - finish_wait(&work->waiters, &wait); + waitq = &rbwork->waiters; + + ret = wait_event_interruptible((*waitq), + rb_wait_cond(rbwork, buffer, cpu, full, cond, data)); return ret; } @@ -1088,30 +1117,51 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table, int full) { struct ring_buffer_per_cpu *cpu_buffer; - struct rb_irq_work *work; + struct rb_irq_work *rbwork; if (cpu == RING_BUFFER_ALL_CPUS) { - work = &buffer->irq_work; + rbwork = &buffer->irq_work; full = 0; } else { if (!cpumask_test_cpu(cpu, buffer->cpumask)) - return -EINVAL; + return EPOLLERR; cpu_buffer = buffer->buffers[cpu]; - work = &cpu_buffer->irq_work; + rbwork = &cpu_buffer->irq_work; } if (full) { - poll_wait(filp, &work->full_waiters, poll_table); - work->full_waiters_pending = true; + unsigned long flags; + + poll_wait(filp, &rbwork->full_waiters, poll_table); + + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); if (!cpu_buffer->shortest_full || cpu_buffer->shortest_full > full) cpu_buffer->shortest_full = full; - } else { - poll_wait(filp, &work->waiters, poll_table); - work->waiters_pending = true; + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + if (full_hit(buffer, cpu, full)) + return EPOLLIN | EPOLLRDNORM; + /* + * Only allow full_waiters_pending update to be seen after + * the shortest_full is set. If the writer sees the + * full_waiters_pending flag set, it will compare the + * amount in the ring buffer to shortest_full. If the amount + * in the ring buffer is greater than the shortest_full + * percent, it will call the irq_work handler to wake up + * this list. The irq_handler will reset shortest_full + * back to zero. That's done under the reader_lock, but + * the below smp_mb() makes sure that the update to + * full_waiters_pending doesn't leak up into the above. + */ + smp_mb(); + rbwork->full_waiters_pending = true; + return 0; } + poll_wait(filp, &rbwork->waiters, poll_table); + rbwork->waiters_pending = true; + /* * There's a tight race between setting the waiters_pending and * checking if the ring buffer is empty. Once the waiters_pending bit @@ -1127,9 +1177,6 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, */ smp_mb(); - if (full) - return full_hit(buffer, cpu, full) ? EPOLLIN | EPOLLRDNORM : 0; - if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) return EPOLLIN | EPOLLRDNORM; @@ -1496,7 +1543,6 @@ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer, old_write = local_add_return(RB_WRITE_INTCNT, &next_page->write); old_entries = local_add_return(RB_WRITE_INTCNT, &next_page->entries); - local_inc(&cpu_buffer->pages_touched); /* * Just make sure we have seen our old_write and synchronize * with any interrupts that come in. @@ -1533,8 +1579,9 @@ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer, */ local_set(&next_page->page->commit, 0); - /* Again, either we update tail_page or an interrupt does */ - (void)cmpxchg(&cpu_buffer->tail_page, tail_page, next_page); + /* Either we update tail_page or an interrupt does */ + if (try_cmpxchg(&cpu_buffer->tail_page, &tail_page, next_page)) + local_inc(&cpu_buffer->pages_touched); } } @@ -4384,7 +4431,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter) cpu_buffer = iter->cpu_buffer; reader = cpu_buffer->reader_page; head_page = cpu_buffer->head_page; - commit_page = cpu_buffer->commit_page; + commit_page = READ_ONCE(cpu_buffer->commit_page); commit_ts = commit_page->page->time_stamp; /* diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 2b3c4cd8382b30c943f5bc5c824a1a77a303fd86..f2b00ea38111ae264ae3e7338fbf92a8cda4cf37 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include #include @@ -2249,7 +2250,7 @@ struct saved_cmdlines_buffer { unsigned *map_cmdline_to_pid; unsigned cmdline_num; int cmdline_idx; - char *saved_cmdlines; + char saved_cmdlines[]; }; static struct saved_cmdlines_buffer *savedcmd; @@ -2263,47 +2264,60 @@ static inline void set_cmdline(int idx, const char *cmdline) strncpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN); } -static int allocate_cmdlines_buffer(unsigned int val, - struct saved_cmdlines_buffer *s) +static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s) { + int order = get_order(sizeof(*s) + s->cmdline_num * TASK_COMM_LEN); + + kfree(s->map_cmdline_to_pid); + kmemleak_free(s); + free_pages((unsigned long)s, order); +} + +static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val) +{ + struct saved_cmdlines_buffer *s; + struct page *page; + int orig_size, size; + int order; + + /* Figure out how much is needed to hold the given number of cmdlines */ + orig_size = sizeof(*s) + val * TASK_COMM_LEN; + order = get_order(orig_size); + size = 1 << (order + PAGE_SHIFT); + page = alloc_pages(GFP_KERNEL, order); + if (!page) + return NULL; + + s = page_address(page); + kmemleak_alloc(s, size, 1, GFP_KERNEL); + memset(s, 0, sizeof(*s)); + + /* Round up to actual allocation */ + val = (size - sizeof(*s)) / TASK_COMM_LEN; + s->cmdline_num = val; + s->map_cmdline_to_pid = kmalloc_array(val, sizeof(*s->map_cmdline_to_pid), GFP_KERNEL); - if (!s->map_cmdline_to_pid) - return -ENOMEM; - - s->saved_cmdlines = kmalloc_array(TASK_COMM_LEN, val, GFP_KERNEL); - if (!s->saved_cmdlines) { - kfree(s->map_cmdline_to_pid); - return -ENOMEM; + if (!s->map_cmdline_to_pid) { + free_saved_cmdlines_buffer(s); + return NULL; } s->cmdline_idx = 0; - s->cmdline_num = val; memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP, sizeof(s->map_pid_to_cmdline)); memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP, val * sizeof(*s->map_cmdline_to_pid)); - return 0; + return s; } static int trace_create_savedcmd(void) { - int ret; - - savedcmd = kmalloc(sizeof(*savedcmd), GFP_KERNEL); - if (!savedcmd) - return -ENOMEM; + savedcmd = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT); - ret = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT, savedcmd); - if (ret < 0) { - kfree(savedcmd); - savedcmd = NULL; - return -ENOMEM; - } - - return 0; + return savedcmd ? 0 : -ENOMEM; } int is_tracing_stopped(void) @@ -5972,26 +5986,14 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf, return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } -static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s) -{ - kfree(s->saved_cmdlines); - kfree(s->map_cmdline_to_pid); - kfree(s); -} - static int tracing_resize_saved_cmdlines(unsigned int val) { struct saved_cmdlines_buffer *s, *savedcmd_temp; - s = kmalloc(sizeof(*s), GFP_KERNEL); + s = allocate_cmdlines_buffer(val); if (!s) return -ENOMEM; - if (allocate_cmdlines_buffer(val, s) < 0) { - kfree(s); - return -ENOMEM; - } - preempt_disable(); arch_spin_lock(&trace_cmdline_lock); savedcmd_temp = savedcmd; @@ -8276,6 +8278,20 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, return size; } +static int tracing_buffers_flush(struct file *file, fl_owner_t id) +{ + struct ftrace_buffer_info *info = file->private_data; + struct trace_iterator *iter = &info->iter; + + iter->wait_index++; + /* Make sure the waiters see the new wait_index */ + smp_wmb(); + + ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); + + return 0; +} + static int tracing_buffers_release(struct inode *inode, struct file *file) { struct ftrace_buffer_info *info = file->private_data; @@ -8287,12 +8303,6 @@ static int tracing_buffers_release(struct inode *inode, struct file *file) __trace_array_put(iter->tr); - iter->wait_index++; - /* Make sure the waiters see the new wait_index */ - smp_wmb(); - - ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); - if (info->spare) ring_buffer_free_read_page(iter->array_buffer->buffer, info->spare_cpu, info->spare); @@ -8506,6 +8516,7 @@ static const struct file_operations tracing_buffers_fops = { .read = tracing_buffers_read, .poll = tracing_buffers_poll, .release = tracing_buffers_release, + .flush = tracing_buffers_flush, .splice_read = tracing_buffers_splice_read, .unlocked_ioctl = tracing_buffers_ioctl, .llseek = no_llseek, diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index a6d2f99f847d37914d426692788038bfe4f7ddeb..24859d964505059860ef40d12b3d0c70cadfaccc 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1669,6 +1669,7 @@ static int trace_format_open(struct inode *inode, struct file *file) return 0; } +#ifdef CONFIG_PERF_EVENTS static ssize_t event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { @@ -1683,6 +1684,7 @@ event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) return simple_read_from_buffer(ubuf, cnt, ppos, buf, len); } +#endif static ssize_t event_filter_read(struct file *filp, char __user *ubuf, size_t cnt, @@ -2127,10 +2129,12 @@ static const struct file_operations ftrace_event_format_fops = { .release = seq_release, }; +#ifdef CONFIG_PERF_EVENTS static const struct file_operations ftrace_event_id_fops = { .read = event_id_read, .llseek = default_llseek, }; +#endif static const struct file_operations ftrace_event_filter_fops = { .open = tracing_open_file_tr, diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 918730d749325147c3772c2f858cb18e805b1291..f941ce01ee351e911e88ef392eec2df0edea7d07 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -1455,8 +1455,10 @@ register_snapshot_trigger(char *glob, struct event_trigger_data *data, struct trace_event_file *file) { - if (tracing_alloc_snapshot_instance(file->tr) != 0) - return 0; + int ret = tracing_alloc_snapshot_instance(file->tr); + + if (ret < 0) + return ret; return register_trigger(glob, data, file); } diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 95541b99aa8eaa3ede090a3c501f9efc5b4c08cc..b2dff19358938ba01178ba9156acd007ad51f7bd 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -343,7 +343,7 @@ config DEBUG_INFO_SPLIT Incompatible with older versions of ccache. config DEBUG_INFO_BTF - bool "Generate BTF typeinfo" + bool "Generate BTF type information" depends on !DEBUG_INFO_SPLIT && !DEBUG_INFO_REDUCED depends on !GCC_PLUGIN_RANDSTRUCT || COMPILE_TEST depends on BPF_SYSCALL @@ -374,7 +374,8 @@ config PAHOLE_HAS_LANG_EXCLUDE using DEBUG_INFO_BTF_MODULES. config DEBUG_INFO_BTF_MODULES - def_bool y + bool "Generate BTF type information for kernel modules" + default y depends on DEBUG_INFO_BTF && MODULES && PAHOLE_HAS_SPLIT_BTF help Generate compact split BTF type information for kernel modules. diff --git a/lib/bootconfig.c b/lib/bootconfig.c index c59d26068a6401990343e26c03002fcc4022ef98..8841554432d5b4770c19a948eb849af71386271f 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -61,9 +61,12 @@ static inline void * __init xbc_alloc_mem(size_t size) return memblock_alloc(size, SMP_CACHE_BYTES); } -static inline void __init xbc_free_mem(void *addr, size_t size) +static inline void __init xbc_free_mem(void *addr, size_t size, bool early) { - memblock_free(addr, size); + if (early) + memblock_free(addr, size); + else if (addr) + memblock_free_late(__pa(addr), size); } #else /* !__KERNEL__ */ @@ -73,7 +76,7 @@ static inline void *xbc_alloc_mem(size_t size) return malloc(size); } -static inline void xbc_free_mem(void *addr, size_t size) +static inline void xbc_free_mem(void *addr, size_t size, bool early) { free(addr); } @@ -904,13 +907,13 @@ static int __init xbc_parse_tree(void) * If you need to reuse xbc_init() with new boot config, you can * use this. */ -void __init xbc_exit(void) +void __init _xbc_exit(bool early) { - xbc_free_mem(xbc_data, xbc_data_size); + xbc_free_mem(xbc_data, xbc_data_size, early); xbc_data = NULL; xbc_data_size = 0; xbc_node_num = 0; - xbc_free_mem(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX); + xbc_free_mem(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX, early); xbc_nodes = NULL; brace_index = 0; } @@ -963,7 +966,7 @@ int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos) if (!xbc_nodes) { if (emsg) *emsg = "Failed to allocate bootconfig nodes"; - xbc_exit(); + _xbc_exit(true); return -ENOMEM; } memset(xbc_nodes, 0, sizeof(struct xbc_node) * XBC_NODE_MAX); @@ -977,7 +980,7 @@ int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos) *epos = xbc_err_pos; if (emsg) *emsg = xbc_err_msg; - xbc_exit(); + _xbc_exit(true); } else ret = xbc_node_num; diff --git a/lib/cmdline_kunit.c b/lib/cmdline_kunit.c index d4572dbc914539a56c8b2a6da5ab101a9e11d80d..705b82736be0890de9417ca62233479eb3999cd9 100644 --- a/lib/cmdline_kunit.c +++ b/lib/cmdline_kunit.c @@ -124,7 +124,7 @@ static void cmdline_do_one_range_test(struct kunit *test, const char *in, n, e[0], r[0]); p = memchr_inv(&r[1], 0, sizeof(r) - sizeof(r[0])); - KUNIT_EXPECT_PTR_EQ_MSG(test, p, NULL, "in test %u at %u out of bound", n, p - r); + KUNIT_EXPECT_PTR_EQ_MSG(test, p, NULL, "in test %u at %td out of bound", n, p - r); } static void cmdline_test_range(struct kunit *test) diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index 009f2ead09c1e0009479f999b36953dee4a02249..939678ea930e050710d1b46e9c3939c9b168aa0a 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -301,7 +301,11 @@ static int ddebug_tokenize(char *buf, char *words[], int maxwords) } else { for (end = buf; *end && !isspace(*end); end++) ; - BUG_ON(end == buf); + if (end == buf) { + pr_err("parse err after word:%d=%s\n", nwords, + nwords ? words[nwords - 1] : ""); + return -EINVAL; + } } /* `buf' is start of word, `end' is one past its end */ diff --git a/lib/memcpy_kunit.c b/lib/memcpy_kunit.c index 2b5cc70ac53fcfb794d37cf69fc5ead928b2873f..dbedd99aa6163e36f9515ab1980afdb3d6d942c9 100644 --- a/lib/memcpy_kunit.c +++ b/lib/memcpy_kunit.c @@ -32,7 +32,7 @@ struct some_bytes { BUILD_BUG_ON(sizeof(instance.data) != 32); \ for (size_t i = 0; i < sizeof(instance.data); i++) { \ KUNIT_ASSERT_EQ_MSG(test, instance.data[i], v, \ - "line %d: '%s' not initialized to 0x%02x @ %d (saw 0x%02x)\n", \ + "line %d: '%s' not initialized to 0x%02x @ %zu (saw 0x%02x)\n", \ __LINE__, #instance, v, i, instance.data[i]); \ } \ } while (0) @@ -41,7 +41,7 @@ struct some_bytes { BUILD_BUG_ON(sizeof(one) != sizeof(two)); \ for (size_t i = 0; i < sizeof(one); i++) { \ KUNIT_EXPECT_EQ_MSG(test, one.data[i], two.data[i], \ - "line %d: %s.data[%d] (0x%02x) != %s.data[%d] (0x%02x)\n", \ + "line %d: %s.data[%zu] (0x%02x) != %s.data[%zu] (0x%02x)\n", \ __LINE__, #one, i, one.data[i], #two, i, two.data[i]); \ } \ kunit_info(test, "ok: " TEST_OP "() " name "\n"); \ diff --git a/lib/mpi/ec.c b/lib/mpi/ec.c index 40f5908e57a4f084c836b776f5ebf209c11f5a85..e16dca1e23d520a2f5199fe076acfba8ce7943a0 100644 --- a/lib/mpi/ec.c +++ b/lib/mpi/ec.c @@ -584,6 +584,9 @@ void mpi_ec_init(struct mpi_ec_ctx *ctx, enum gcry_mpi_ec_models model, ctx->a = mpi_copy(a); ctx->b = mpi_copy(b); + ctx->d = NULL; + ctx->t.two_inv_p = NULL; + ctx->t.p_barrett = use_barrett > 0 ? mpi_barrett_init(ctx->p, 0) : NULL; mpi_ec_get_reset(ctx); diff --git a/lib/nlattr.c b/lib/nlattr.c index dffd60e4065fdcffc725314591b66e9c4576e265..86344df0ccf7b644c2c0086bc7dddac82dffd49c 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -30,6 +30,8 @@ static const u8 nla_attr_len[NLA_TYPE_MAX+1] = { [NLA_S16] = sizeof(s16), [NLA_S32] = sizeof(s32), [NLA_S64] = sizeof(s64), + [NLA_BE16] = sizeof(__be16), + [NLA_BE32] = sizeof(__be32), }; static const u8 nla_attr_minlen[NLA_TYPE_MAX+1] = { @@ -43,6 +45,8 @@ static const u8 nla_attr_minlen[NLA_TYPE_MAX+1] = { [NLA_S16] = sizeof(s16), [NLA_S32] = sizeof(s32), [NLA_S64] = sizeof(s64), + [NLA_BE16] = sizeof(__be16), + [NLA_BE32] = sizeof(__be32), }; /* diff --git a/lib/pci_iomap.c b/lib/pci_iomap.c index ce39ce9f3526ea2eee7891b62302369b076e8974..2829ddb0e316b4d300bdae37d0c82e4f2882bd35 100644 --- a/lib/pci_iomap.c +++ b/lib/pci_iomap.c @@ -170,8 +170,8 @@ void pci_iounmap(struct pci_dev *dev, void __iomem *p) if (addr >= start && addr < start + IO_SPACE_LIMIT) return; - iounmap(p); #endif + iounmap(p); } EXPORT_SYMBOL(pci_iounmap); diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 79e894cf84064ab3b84f8a0a38cc8cb278347e57..77eb944b7a6bdb82100c4651537a22848dc29853 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -466,10 +466,10 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries, /* * Zero out zone modifiers, as we don't have specific zone * requirements. Keep the flags related to allocation in atomic - * contexts and I/O. + * contexts, I/O, nolockdep. */ alloc_flags &= ~GFP_ZONEMASK; - alloc_flags &= (GFP_ATOMIC | GFP_KERNEL); + alloc_flags &= (GFP_ATOMIC | GFP_KERNEL | __GFP_NOLOCKDEP); alloc_flags |= __GFP_NOWARN; page = alloc_pages(alloc_flags, STACK_ALLOC_ORDER); if (page) diff --git a/lib/test_blackhole_dev.c b/lib/test_blackhole_dev.c index 4c40580a99a364b861f8f180e295300f461a7f12..f247089d63c0852dab192b17e58a637f39644277 100644 --- a/lib/test_blackhole_dev.c +++ b/lib/test_blackhole_dev.c @@ -29,7 +29,6 @@ static int __init test_blackholedev_init(void) { struct ipv6hdr *ip6h; struct sk_buff *skb; - struct ethhdr *ethh; struct udphdr *uh; int data_len; int ret; @@ -61,7 +60,7 @@ static int __init test_blackholedev_init(void) ip6h->saddr = in6addr_loopback; ip6h->daddr = in6addr_loopback; /* Ether */ - ethh = (struct ethhdr *)skb_push(skb, sizeof(struct ethhdr)); + skb_push(skb, sizeof(struct ethhdr)); skb_set_mac_header(skb, 0); skb->protocol = htons(ETH_P_IPV6); diff --git a/mm/compaction.c b/mm/compaction.c index 8238e83385a7916cfa4ff3398daadc641aa691ec..23af5f3b2ccafe1f80d15ed980374cf902e03ac4 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -2570,16 +2570,11 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, const struct alloc_context *ac, enum compact_priority prio, struct page **capture) { - int may_perform_io = (__force int)(gfp_mask & __GFP_IO); struct zoneref *z; struct zone *zone; enum compact_result rc = COMPACT_SKIPPED; - /* - * Check if the GFP flags allow compaction - GFP_NOIO is really - * tricky context because the migration might require IO - */ - if (!may_perform_io) + if (!gfp_compaction_allowed(gfp_mask)) return COMPACT_SKIPPED; trace_mm_compaction_try_to_compact_pages(order, gfp_mask, prio); diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c index 63bdad20dbaf86de5af3087da77df552dd310f97..98a678129b06717073d3cbdf5a4521bc289e9254 100644 --- a/mm/damon/lru_sort.c +++ b/mm/damon/lru_sort.c @@ -185,9 +185,21 @@ static struct damos *damon_lru_sort_new_cold_scheme(unsigned int cold_thres) return damon_lru_sort_new_scheme(&pattern, DAMOS_LRU_DEPRIO); } +static void damon_lru_sort_copy_quota_status(struct damos_quota *dst, + struct damos_quota *src) +{ + dst->total_charged_sz = src->total_charged_sz; + dst->total_charged_ns = src->total_charged_ns; + dst->charged_sz = src->charged_sz; + dst->charged_from = src->charged_from; + dst->charge_target_from = src->charge_target_from; + dst->charge_addr_from = src->charge_addr_from; +} + static int damon_lru_sort_apply_parameters(void) { - struct damos *scheme; + struct damos *scheme, *hot_scheme, *cold_scheme; + struct damos *old_hot_scheme = NULL, *old_cold_scheme = NULL; unsigned int hot_thres, cold_thres; int err = 0; @@ -195,18 +207,35 @@ static int damon_lru_sort_apply_parameters(void) if (err) return err; + damon_for_each_scheme(scheme, ctx) { + if (!old_hot_scheme) { + old_hot_scheme = scheme; + continue; + } + old_cold_scheme = scheme; + } + hot_thres = damon_max_nr_accesses(&damon_lru_sort_mon_attrs) * hot_thres_access_freq / 1000; - scheme = damon_lru_sort_new_hot_scheme(hot_thres); - if (!scheme) + hot_scheme = damon_lru_sort_new_hot_scheme(hot_thres); + if (!hot_scheme) return -ENOMEM; - damon_set_schemes(ctx, &scheme, 1); + if (old_hot_scheme) + damon_lru_sort_copy_quota_status(&hot_scheme->quota, + &old_hot_scheme->quota); cold_thres = cold_min_age / damon_lru_sort_mon_attrs.aggr_interval; - scheme = damon_lru_sort_new_cold_scheme(cold_thres); - if (!scheme) + cold_scheme = damon_lru_sort_new_cold_scheme(cold_thres); + if (!cold_scheme) { + damon_destroy_scheme(hot_scheme); return -ENOMEM; - damon_add_scheme(ctx, scheme); + } + if (old_cold_scheme) + damon_lru_sort_copy_quota_status(&cold_scheme->quota, + &old_cold_scheme->quota); + + damon_set_schemes(ctx, &hot_scheme, 1); + damon_add_scheme(ctx, cold_scheme); return damon_set_region_biggest_system_ram_default(target, &monitor_region_start, diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c index 162c9b1ca00fd0de35264bc9f215a797a981a44a..cc337e94acfda8e936fde8edfca864e4794ef84e 100644 --- a/mm/damon/reclaim.c +++ b/mm/damon/reclaim.c @@ -141,9 +141,20 @@ static struct damos *damon_reclaim_new_scheme(void) &damon_reclaim_wmarks); } +static void damon_reclaim_copy_quota_status(struct damos_quota *dst, + struct damos_quota *src) +{ + dst->total_charged_sz = src->total_charged_sz; + dst->total_charged_ns = src->total_charged_ns; + dst->charged_sz = src->charged_sz; + dst->charged_from = src->charged_from; + dst->charge_target_from = src->charge_target_from; + dst->charge_addr_from = src->charge_addr_from; +} + static int damon_reclaim_apply_parameters(void) { - struct damos *scheme; + struct damos *scheme, *old_scheme; int err = 0; err = damon_set_attrs(ctx, &damon_reclaim_mon_attrs); @@ -154,6 +165,11 @@ static int damon_reclaim_apply_parameters(void) scheme = damon_reclaim_new_scheme(); if (!scheme) return -ENOMEM; + if (!list_empty(&ctx->schemes)) { + damon_for_each_scheme(old_scheme, ctx) + damon_reclaim_copy_quota_status(&scheme->quota, + &old_scheme->quota); + } damon_set_schemes(ctx, &scheme, 1); return damon_set_region_biggest_system_ram_default(target, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 59577946735b1f906e90106174e6a5fb7e853713..9736e762184bdf34cf94c9aa9d3abd984ff07adc 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include @@ -607,6 +608,9 @@ static unsigned long __thp_get_unmapped_area(struct file *filp, loff_t off_align = round_up(off, size); unsigned long len_pad, ret; + if (IS_ENABLED(CONFIG_32BIT) || in_compat_syscall()) + return 0; + if (off_end <= off_align || (off_end - off_align) < size) return 0; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 37288a7f0fa6570e4ea35fb03da13037c0ce3413..4361dcf70139f7fc8d3521f672c87ec46ab27f07 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1661,9 +1661,10 @@ static void __remove_hugetlb_page(struct hstate *h, struct page *page, bool demote) { int nid = page_to_nid(page); + struct folio *folio = page_folio(page); - VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page); - VM_BUG_ON_PAGE(hugetlb_cgroup_from_page_rsvd(page), page); + VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio(folio), folio); + VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio_rsvd(folio), folio); lockdep_assert_held(&hugetlb_lock); if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) @@ -1761,7 +1762,6 @@ static void __update_and_free_page(struct hstate *h, struct page *page) { int i; struct page *subpage; - bool clear_dtor = HPageVmemmapOptimized(page); if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; @@ -1796,7 +1796,7 @@ static void __update_and_free_page(struct hstate *h, struct page *page) * If vmemmap pages were allocated above, then we need to clear the * hugetlb destructor under the hugetlb lock. */ - if (clear_dtor) { + if (PageHuge(page)) { spin_lock_irq(&hugetlb_lock); __clear_hugetlb_destructor(h, page); spin_unlock_irq(&hugetlb_lock); @@ -1917,21 +1917,22 @@ void free_huge_page(struct page *page) * Can't pass hstate in here because it is called from the * compound page destructor. */ - struct hstate *h = page_hstate(page); - int nid = page_to_nid(page); - struct hugepage_subpool *spool = hugetlb_page_subpool(page); + struct folio *folio = page_folio(page); + struct hstate *h = folio_hstate(folio); + int nid = folio_nid(folio); + struct hugepage_subpool *spool = hugetlb_folio_subpool(folio); bool restore_reserve; unsigned long flags; - VM_BUG_ON_PAGE(page_count(page), page); - VM_BUG_ON_PAGE(page_mapcount(page), page); + VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); + VM_BUG_ON_FOLIO(folio_mapcount(folio), folio); - hugetlb_set_page_subpool(page, NULL); - if (PageAnon(page)) - __ClearPageAnonExclusive(page); - page->mapping = NULL; - restore_reserve = HPageRestoreReserve(page); - ClearHPageRestoreReserve(page); + hugetlb_set_folio_subpool(folio, NULL); + if (folio_test_anon(folio)) + __ClearPageAnonExclusive(&folio->page); + folio->mapping = NULL; + restore_reserve = folio_test_hugetlb_restore_reserve(folio); + folio_clear_hugetlb_restore_reserve(folio); /* * If HPageRestoreReserve was set on page, page allocation consumed a @@ -1953,15 +1954,15 @@ void free_huge_page(struct page *page) } spin_lock_irqsave(&hugetlb_lock, flags); - ClearHPageMigratable(page); - hugetlb_cgroup_uncharge_page(hstate_index(h), - pages_per_huge_page(h), page); - hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h), - pages_per_huge_page(h), page); + folio_clear_hugetlb_migratable(folio); + hugetlb_cgroup_uncharge_folio(hstate_index(h), + pages_per_huge_page(h), folio); + hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), + pages_per_huge_page(h), folio); if (restore_reserve) h->resv_huge_pages++; - if (HPageTemporary(page)) { + if (folio_test_hugetlb_temporary(folio)) { remove_hugetlb_page(h, page, false); spin_unlock_irqrestore(&hugetlb_lock, flags); update_and_free_page(h, page, true); @@ -3080,6 +3081,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct page *page; + struct folio *folio; long map_chg, map_commit; long gbl_chg; int ret, idx; @@ -3143,6 +3145,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, * a reservation exists for the allocation. */ page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, gbl_chg); + if (!page) { spin_unlock_irq(&hugetlb_lock); page = alloc_buddy_huge_page_with_mpol(h, vma, addr); @@ -3157,6 +3160,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, set_page_refcounted(page); /* Fall through */ } + folio = page_folio(page); hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page); /* If allocation is not consuming a reservation, also store the * hugetlb_cgroup pointer on the page. @@ -3185,9 +3189,12 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, rsv_adjust = hugepage_subpool_put_pages(spool, 1); hugetlb_acct_memory(h, -rsv_adjust); - if (deferred_reserve) - hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h), - pages_per_huge_page(h), page); + if (deferred_reserve) { + spin_lock_irq(&hugetlb_lock); + hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), + pages_per_huge_page(h), folio); + spin_unlock_irq(&hugetlb_lock); + } } return page; diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index f61d132df52b34e304553ee899052c07a3929ac3..32f4408eda240d4c7a4a8ba6fb830cb5e37937a3 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -191,8 +191,9 @@ static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg, struct page_counter *counter; struct hugetlb_cgroup *page_hcg; struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(h_cg); + struct folio *folio = page_folio(page); - page_hcg = hugetlb_cgroup_from_page(page); + page_hcg = hugetlb_cgroup_from_folio(folio); /* * We can have pages in active list without any cgroup * ie, hugepage with less than 3 pages. We can safely @@ -314,7 +315,7 @@ static void __hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, if (hugetlb_cgroup_disabled() || !h_cg) return; - __set_hugetlb_cgroup(page, h_cg, rsvd); + __set_hugetlb_cgroup(page_folio(page), h_cg, rsvd); if (!rsvd) { unsigned long usage = h_cg->nodeinfo[page_to_nid(page)]->usage[idx]; @@ -345,18 +346,18 @@ void hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages, /* * Should be called with hugetlb_lock held */ -static void __hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, - struct page *page, bool rsvd) +static void __hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages, + struct folio *folio, bool rsvd) { struct hugetlb_cgroup *h_cg; if (hugetlb_cgroup_disabled()) return; lockdep_assert_held(&hugetlb_lock); - h_cg = __hugetlb_cgroup_from_page(page, rsvd); + h_cg = __hugetlb_cgroup_from_folio(folio, rsvd); if (unlikely(!h_cg)) return; - __set_hugetlb_cgroup(page, NULL, rsvd); + __set_hugetlb_cgroup(folio, NULL, rsvd); page_counter_uncharge(__hugetlb_cgroup_counter_from_cgroup(h_cg, idx, rsvd), @@ -366,27 +367,27 @@ static void __hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, css_put(&h_cg->css); else { unsigned long usage = - h_cg->nodeinfo[page_to_nid(page)]->usage[idx]; + h_cg->nodeinfo[folio_nid(folio)]->usage[idx]; /* * This write is not atomic due to fetching usage and writing * to it, but that's fine because we call this with * hugetlb_lock held anyway. */ - WRITE_ONCE(h_cg->nodeinfo[page_to_nid(page)]->usage[idx], + WRITE_ONCE(h_cg->nodeinfo[folio_nid(folio)]->usage[idx], usage - nr_pages); } } -void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, - struct page *page) +void hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages, + struct folio *folio) { - __hugetlb_cgroup_uncharge_page(idx, nr_pages, page, false); + __hugetlb_cgroup_uncharge_folio(idx, nr_pages, folio, false); } -void hugetlb_cgroup_uncharge_page_rsvd(int idx, unsigned long nr_pages, - struct page *page) +void hugetlb_cgroup_uncharge_folio_rsvd(int idx, unsigned long nr_pages, + struct folio *folio) { - __hugetlb_cgroup_uncharge_page(idx, nr_pages, page, true); + __hugetlb_cgroup_uncharge_folio(idx, nr_pages, folio, true); } static void __hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, @@ -888,13 +889,14 @@ void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage) struct hugetlb_cgroup *h_cg; struct hugetlb_cgroup *h_cg_rsvd; struct hstate *h = page_hstate(oldhpage); + struct folio *old_folio = page_folio(oldhpage); if (hugetlb_cgroup_disabled()) return; spin_lock_irq(&hugetlb_lock); - h_cg = hugetlb_cgroup_from_page(oldhpage); - h_cg_rsvd = hugetlb_cgroup_from_page_rsvd(oldhpage); + h_cg = hugetlb_cgroup_from_folio(old_folio); + h_cg_rsvd = hugetlb_cgroup_from_folio_rsvd(old_folio); set_hugetlb_cgroup(oldhpage, NULL); set_hugetlb_cgroup_rsvd(oldhpage, NULL); diff --git a/mm/kasan/kasan_test.c b/mm/kasan/kasan_test.c index 0d59098f087613d11ef37cdd02c50894eb67e9e1..cef683a2e0d2e6512ccfc9cbf7a8fbf6d5583138 100644 --- a/mm/kasan/kasan_test.c +++ b/mm/kasan/kasan_test.c @@ -415,7 +415,8 @@ static void kmalloc_oob_16(struct kunit *test) /* This test is specifically crafted for the generic mode. */ KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC); - ptr1 = kmalloc(sizeof(*ptr1) - 3, GFP_KERNEL); + /* RELOC_HIDE to prevent gcc from warning about short alloc */ + ptr1 = RELOC_HIDE(kmalloc(sizeof(*ptr1) - 3, GFP_KERNEL), 0); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr1); ptr2 = kmalloc(sizeof(*ptr2), GFP_KERNEL); diff --git a/mm/memblock.c b/mm/memblock.c index 511d4783dcf1d86374c14d528cfec69c51247749..516efec80851a49c29c166f23c55a69727ca9fef 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -175,8 +175,9 @@ static inline phys_addr_t memblock_cap_size(phys_addr_t base, phys_addr_t *size) /* * Address comparison utilities */ -static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, - phys_addr_t base2, phys_addr_t size2) +unsigned long __init_memblock +memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, phys_addr_t base2, + phys_addr_t size2) { return ((base1 < (base2 + size2)) && (base2 < (base1 + size1))); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9da98e3e71cfed84f1de91b1d7892d8879344928..4570d3e315cf15f7e2fe95515c78c102c9e43071 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -7517,9 +7517,13 @@ bool mem_cgroup_swap_full(struct folio *folio) static int __init setup_swap_account(char *s) { - pr_warn_once("The swapaccount= commandline option is deprecated. " - "Please report your usecase to linux-mm@kvack.org if you " - "depend on this functionality.\n"); + bool res; + + if (!kstrtobool(s, &res) && !res) + pr_warn_once("The swapaccount=0 commandline option is deprecated " + "in favor of configuring swap control via cgroupfs. " + "Please report your usecase to linux-mm@kvack.org if you " + "depend on this functionality.\n"); return 1; } __setup("swapaccount=", setup_swap_account); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 5b846ed5dcbe91aff726b461971fe7741a998aca..be58ce99925951f393917b1a2299de5656af70c5 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -84,11 +84,23 @@ static int __page_handle_poison(struct page *page) { int ret; - zone_pcp_disable(page_zone(page)); + /* + * zone_pcp_disable() can't be used here. It will + * hold pcp_batch_high_lock and dissolve_free_huge_page() might hold + * cpu_hotplug_lock via static_key_slow_dec() when hugetlb vmemmap + * optimization is enabled. This will break current lock dependency + * chain and leads to deadlock. + * Disabling pcp before dissolving the page was a deterministic + * approach because we made sure that those pages cannot end up in any + * PCP list. Draining PCP lists expels those pages to the buddy system, + * but nothing guarantees that those pages do not get back to a PCP + * queue if we need to refill those. + */ ret = dissolve_free_huge_page(page); - if (!ret) + if (!ret) { + drain_all_pages(page_zone(page)); ret = take_page_off_buddy(page); - zone_pcp_enable(page_zone(page)); + } return ret; } diff --git a/mm/memory.c b/mm/memory.c index fc8b264ec0caca1f6a6f9d8489e40e6f12af8584..301c74c44438554c2d059046b1e5da1c0087f92d 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3761,6 +3761,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) struct page *page; struct swap_info_struct *si = NULL; rmap_t rmap_flags = RMAP_NONE; + bool need_clear_cache = false; bool exclusive = false; swp_entry_t entry; pte_t pte; @@ -3822,6 +3823,20 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (!folio) { if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && __swap_count(entry) == 1) { + /* + * Prevent parallel swapin from proceeding with + * the cache flag. Otherwise, another thread may + * finish swapin first, free the entry, and swapout + * reusing the same entry. It's undetectable as + * pte_same() returns true due to entry reuse. + */ + if (swapcache_prepare(entry)) { + /* Relax a bit to prevent rapid repeated page faults */ + schedule_timeout_uninterruptible(1); + goto out; + } + need_clear_cache = true; + /* skip swapcache */ folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vmf->address, false); @@ -4073,6 +4088,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); out: + /* Clear the swap cache pin for direct swapin after PTL unlock */ + if (need_clear_cache) + swapcache_clear(si, entry); if (si) put_swap_device(si); return ret; @@ -4086,6 +4104,8 @@ out_release: folio_unlock(swapcache); folio_put(swapcache); } + if (need_clear_cache) + swapcache_clear(si, entry); if (si) put_swap_device(si); return ret; @@ -5573,6 +5593,10 @@ int follow_phys(struct vm_area_struct *vma, goto out; pte = *ptep; + /* Never return PFNs of anon folios in COW mappings. */ + if (vm_normal_folio(vma, address, pte)) + goto unlock; + if ((flags & FOLL_WRITE) && !pte_write(pte)) goto unlock; diff --git a/mm/memtest.c b/mm/memtest.c index f53ace709ccd82d207bae22679887c1da1e3b694..d407373f225b41c0d3422f3cd7be91e210556115 100644 --- a/mm/memtest.c +++ b/mm/memtest.c @@ -46,10 +46,10 @@ static void __init memtest(u64 pattern, phys_addr_t start_phys, phys_addr_t size last_bad = 0; for (p = start; p < end; p++) - *p = pattern; + WRITE_ONCE(*p, pattern); for (p = start; p < end; p++, start_phys_aligned += incr) { - if (*p == pattern) + if (READ_ONCE(*p) == pattern) continue; if (start_phys_aligned == last_bad + incr) { last_bad += incr; diff --git a/mm/migrate.c b/mm/migrate.c index c93dd6a31c31a4f21cee7751f5d1bea53d396feb..0252aa4ff572e6c52a42fc593df91d06e84dd49a 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -423,8 +423,12 @@ int folio_migrate_mapping(struct address_space *mapping, if (folio_test_swapbacked(folio)) { __folio_set_swapbacked(newfolio); if (folio_test_swapcache(folio)) { + int i; + folio_set_swapcache(newfolio); - newfolio->private = folio_get_private(folio); + for (i = 0; i < nr; i++) + set_page_private(folio_page(newfolio, i), + page_private(folio_page(folio, i))); } entries = nr; } else { @@ -1628,7 +1632,7 @@ struct page *alloc_migration_target(struct page *page, unsigned long private) nid = folio_nid(folio); if (folio_test_hugetlb(folio)) { - struct hstate *h = page_hstate(&folio->page); + struct hstate *h = folio_hstate(folio); gfp_mask = htlb_modify_alloc_mask(h, gfp_mask); return alloc_huge_page_nodemask(h, nid, mtc->nmask, gfp_mask); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index de5f69921b9465886692743648b43da2ee8a1332..d3e9d12860b9f49356fd679a0d0a9744456956e3 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1526,7 +1526,7 @@ static inline void wb_dirty_limits(struct dirty_throttle_control *dtc) */ dtc->wb_thresh = __wb_calc_thresh(dtc); dtc->wb_bg_thresh = dtc->thresh ? - div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; + div64_u64(dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 681077943c75b078c8956982a325d4b09569223a..8c3c6192fb1504d8eaeb7dce6cae0feeedd34d21 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5034,6 +5034,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, struct alloc_context *ac) { bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM; + bool can_compact = gfp_compaction_allowed(gfp_mask); const bool costly_order = order > PAGE_ALLOC_COSTLY_ORDER; struct page *page = NULL; unsigned int alloc_flags; @@ -5112,7 +5113,7 @@ restart: * Don't try this for allocations that are allowed to ignore * watermarks, as the ALLOC_NO_WATERMARKS attempt didn't yet happen. */ - if (can_direct_reclaim && + if (can_direct_reclaim && can_compact && (costly_order || (order > 0 && ac->migratetype != MIGRATE_MOVABLE)) && !gfp_pfmemalloc_allowed(gfp_mask)) { @@ -5210,9 +5211,10 @@ retry: /* * Do not retry costly high order allocations unless they are - * __GFP_RETRY_MAYFAIL + * __GFP_RETRY_MAYFAIL and we can compact */ - if (costly_order && !(gfp_mask & __GFP_RETRY_MAYFAIL)) + if (costly_order && (!can_compact || + !(gfp_mask & __GFP_RETRY_MAYFAIL))) goto nopage; if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags, @@ -5225,7 +5227,7 @@ retry: * implementation of the compaction depends on the sufficient amount * of free memory (see __compaction_suitable) */ - if (did_some_progress > 0 && + if (did_some_progress > 0 && can_compact && should_compact_retry(ac, order, alloc_flags, compact_result, &compact_priority, &compaction_retries)) diff --git a/mm/readahead.c b/mm/readahead.c index ba43428043a35b72d219eab82aaee3fa50025ac6..794d8ddc069720fe98fa40418b2d01b89d084a88 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -483,7 +483,7 @@ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index, if (!folio) return -ENOMEM; - mark = round_up(mark, 1UL << order); + mark = round_down(mark, 1UL << order); if (index == mark) folio_set_readahead(folio); err = filemap_add_folio(ractl->mapping, folio, index, gfp); @@ -504,6 +504,7 @@ void page_cache_ra_order(struct readahead_control *ractl, pgoff_t index = readahead_index(ractl); pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT; pgoff_t mark = index + ra->size - ra->async_size; + unsigned int nofs; int err = 0; gfp_t gfp = readahead_gfp_mask(mapping); @@ -520,6 +521,8 @@ void page_cache_ra_order(struct readahead_control *ractl, new_order--; } + /* See comment in page_cache_ra_unbounded() */ + nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); while (index <= limit) { unsigned int order = new_order; @@ -548,6 +551,7 @@ void page_cache_ra_order(struct readahead_control *ractl, read_pages(ractl); filemap_invalidate_unlock_shared(mapping); + memalloc_nofs_restore(nofs); /* * If there were already pages in the page cache, then we may have @@ -591,7 +595,7 @@ static void ondemand_readahead(struct readahead_control *ractl, * It's the expected callback index, assume sequential access. * Ramp up sizes, and push forward the readahead window. */ - expected = round_up(ra->start + ra->size - ra->async_size, + expected = round_down(ra->start + ra->size - ra->async_size, 1UL << order); if (index == expected || index == (ra->start + ra->size)) { ra->start += ra->size; diff --git a/mm/swap.h b/mm/swap.h index cc08c459c6190cd33a9e634b270873d4afa210a6..5eff40ef769349a03f7f892a8ffe65af5e4ecfa8 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -39,6 +39,7 @@ void __delete_from_swap_cache(struct folio *folio, void delete_from_swap_cache(struct folio *folio); void clear_shadow_from_swap_cache(int type, unsigned long begin, unsigned long end); +void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry); struct folio *swap_cache_get_folio(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr); struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index); @@ -98,6 +99,10 @@ static inline int swap_writepage(struct page *p, struct writeback_control *wbc) return 0; } +static inline void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) +{ +} + static inline struct folio *swap_cache_get_folio(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr) { diff --git a/mm/swapfile.c b/mm/swapfile.c index 71db6d8a1ea30a3d30e00888436be31e969a1c80..0d6182db44a6af7a509116b672f2fe2c0052fce1 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1222,6 +1222,18 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, } /* + * When we get a swap entry, if there aren't some other ways to + * prevent swapoff, such as the folio in swap cache is locked, page + * table lock is held, etc., the swap entry may become invalid because + * of swapoff. Then, we need to enclose all swap related functions + * with get_swap_device() and put_swap_device(), unless the swap + * functions call get/put_swap_device() by themselves. + * + * Note that when only holding the PTL, swapoff might succeed immediately + * after freeing a swap entry. Therefore, immediately after + * __swap_entry_free(), the swap info might become stale and should not + * be touched without a prior get_swap_device(). + * * Check whether swap entry is valid in the swap device. If so, * return pointer to swap_info_struct, and keep the swap entry valid * via preventing the swap device from being swapoff, until @@ -1230,9 +1242,8 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, * Notice that swapoff or swapoff+swapon can still happen before the * percpu_ref_tryget_live() in get_swap_device() or after the * percpu_ref_put() in put_swap_device() if there isn't any other way - * to prevent swapoff, such as page lock, page table lock, etc. The - * caller must be prepared for that. For example, the following - * situation is possible. + * to prevent swapoff. The caller must be prepared for that. For + * example, the following situation is possible. * * CPU1 CPU2 * do_swap_page() @@ -1624,13 +1635,19 @@ int free_swap_and_cache(swp_entry_t entry) if (non_swap_entry(entry)) return 1; - p = _swap_info_get(entry); + p = get_swap_device(entry); if (p) { + if (WARN_ON(data_race(!p->swap_map[swp_offset(entry)]))) { + put_swap_device(p); + return 0; + } + count = __swap_entry_free(p, entry); if (count == SWAP_HAS_CACHE && !swap_page_trans_huge_swapped(p, entry)) __try_to_reclaim_swap(p, swp_offset(entry), TTRS_UNMAPPED | TTRS_FULL); + put_swap_device(p); } return p != NULL; } @@ -3373,6 +3390,19 @@ int swapcache_prepare(swp_entry_t entry) return __swap_duplicate(entry, SWAP_HAS_CACHE); } +void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) +{ + struct swap_cluster_info *ci; + unsigned long offset = swp_offset(entry); + unsigned char usage; + + ci = lock_cluster_or_swap_info(si, offset); + usage = __swap_entry_free_locked(si, offset, SWAP_HAS_CACHE); + unlock_cluster_or_swap_info(si, ci); + if (!usage) + free_swap_slot(entry); +} + struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return swap_type_to_swap_info(swp_type(entry)); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 650ab6cfd5f49a36ff478149b9a14586fa6740cf..992a0a16846f7959b83f47bf221bd27718f03a3f 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -327,6 +327,7 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, enum mcopy_atomic_mode mode, bool wp_copy) { @@ -445,6 +446,15 @@ retry: goto out; } mmap_read_lock(dst_mm); + /* + * If memory mappings are changing because of non-cooperative + * operation (e.g. mremap) running in parallel, bail out and + * request the user to retry later + */ + if (mmap_changing && atomic_read(mmap_changing)) { + err = -EAGAIN; + break; + } dst_vma = NULL; goto retry; @@ -480,6 +490,7 @@ extern ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, enum mcopy_atomic_mode mode, bool wp_copy); #endif /* CONFIG_HUGETLB_PAGE */ @@ -601,8 +612,8 @@ retry: */ if (is_vm_hugetlb_page(dst_vma)) return __mcopy_atomic_hugetlb(dst_mm, dst_vma, dst_start, - src_start, len, mcopy_mode, - wp_copy); + src_start, len, mmap_changing, + mcopy_mode, wp_copy); if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock; diff --git a/mm/vmscan.c b/mm/vmscan.c index 9f3cfb7caa48d0cb4e704394a008e2b91c1e2b78..a3b1d8e5dbb3da75c1bbc64e7be7a30e60d3d36c 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -6024,7 +6024,7 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) /* Use reclaim/compaction for costly allocs or under memory pressure */ static bool in_reclaim_compaction(struct scan_control *sc) { - if (IS_ENABLED(CONFIG_COMPACTION) && sc->order && + if (gfp_compaction_allowed(sc->gfp_mask) && sc->order && (sc->order > PAGE_ALLOC_COSTLY_ORDER || sc->priority < DEF_PRIORITY - 2)) return true; @@ -6266,6 +6266,9 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) unsigned long watermark; enum compact_result suitable; + if (!gfp_compaction_allowed(sc->gfp_mask)) + return false; + suitable = compaction_suitable(zone, sc->order, 0, sc->reclaim_idx); if (suitable == COMPACT_SUCCESS) /* Allocation should succeed already. Don't reclaim. */ diff --git a/mm/zswap.c b/mm/zswap.c index ba0e211bb5c4ced7f81876512207078c3ebc07e4..17b44028d25c5a29651688405eee9959c352531f 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1029,6 +1029,8 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) if (zswap_rb_search(&tree->rbroot, entry->offset) != entry) { spin_unlock(&tree->lock); delete_from_swap_cache(page_folio(page)); + unlock_page(page); + put_page(page); ret = -ENOMEM; goto fail; } diff --git a/net/9p/client.c b/net/9p/client.c index 84b93b04d0f06ad32022249fe31d36ddf414c692..1d9a8a1f3f107f9fc6c40391ae8a00eb18ca0b8f 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -1581,7 +1581,7 @@ p9_client_read_once(struct p9_fid *fid, u64 offset, struct iov_iter *to, received = rsize; } - p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count); + p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", received); if (non_zc) { int n = copy_to_iter(dataptr, received, to); @@ -1607,9 +1607,6 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err) int total = 0; *err = 0; - p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %zd\n", - fid->fid, offset, iov_iter_count(from)); - while (iov_iter_count(from)) { int count = iov_iter_count(from); int rsize = fid->iounit; @@ -1621,6 +1618,9 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err) if (count < rsize) rsize = count; + p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %d (/%d)\n", + fid->fid, offset, rsize, count); + /* Don't bother zerocopy for small IO (< 1024) */ if (clnt->trans_mod->zc_request && rsize > 1024) { req = p9_client_zc_rpc(clnt, P9_TWRITE, NULL, from, 0, @@ -1648,7 +1648,7 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err) written = rsize; } - p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", count); + p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", written); p9_req_put(clnt, req); iov_iter_revert(from, count - written - iov_iter_count(from)); diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 6b4c25a9237746265158900ab92d7f411b77ab79..0bffac238b615787d1b334dc399ecdaa7d868644 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -103,7 +103,7 @@ again: s->ax25_dev = NULL; if (sk->sk_socket) { netdev_put(ax25_dev->dev, - &ax25_dev->dev_tracker); + &s->dev_tracker); ax25_dev_put(ax25_dev); } ax25_cb_del(s); diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 5d8cee74772fe2abf46e644c4a3be341234151b8..4fc66cd95dc47103f784b06eddab84bfb9966710 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -3948,7 +3948,7 @@ void batadv_tt_local_resize_to_mtu(struct net_device *soft_iface) spin_lock_bh(&bat_priv->tt.commit_lock); - while (true) { + while (timeout) { table_size = batadv_tt_local_table_transmit_size(bat_priv); if (packet_size_max >= table_size) break; diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index f1b7510359e4b0277d209db0d3584a5d7e1a5881..3f9ff02baafe395e8952d0aaac6ce23b7ed0480e 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -264,14 +264,11 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (flags & MSG_OOB) return -EOPNOTSUPP; - lock_sock(sk); - skb = skb_recv_datagram(sk, flags, &err); if (!skb) { if (sk->sk_shutdown & RCV_SHUTDOWN) err = 0; - release_sock(sk); return err; } @@ -297,8 +294,6 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, skb_free_datagram(sk, skb); - release_sock(sk); - if (flags & MSG_TRUNC) copied = skblen; @@ -521,10 +516,11 @@ int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) if (sk->sk_state == BT_LISTEN) return -EINVAL; - lock_sock(sk); + spin_lock(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); amount = skb ? skb->len : 0; - release_sock(sk); + spin_unlock(&sk->sk_receive_queue.lock); + err = put_user(amount, (int __user *)arg); break; diff --git a/net/bluetooth/eir.c b/net/bluetooth/eir.c index 8a85f6cdfbc16ac9397b782dffe3dbea2ecaef1b..1bc51e2b05a3474b12b25e7f396d3475cd6944dd 100644 --- a/net/bluetooth/eir.c +++ b/net/bluetooth/eir.c @@ -13,48 +13,33 @@ #define PNP_INFO_SVCLASS_ID 0x1200 -static u8 eir_append_name(u8 *eir, u16 eir_len, u8 type, u8 *data, u8 data_len) -{ - u8 name[HCI_MAX_SHORT_NAME_LENGTH + 1]; - - /* If data is already NULL terminated just pass it directly */ - if (data[data_len - 1] == '\0') - return eir_append_data(eir, eir_len, type, data, data_len); - - memcpy(name, data, HCI_MAX_SHORT_NAME_LENGTH); - name[HCI_MAX_SHORT_NAME_LENGTH] = '\0'; - - return eir_append_data(eir, eir_len, type, name, sizeof(name)); -} - u8 eir_append_local_name(struct hci_dev *hdev, u8 *ptr, u8 ad_len) { size_t short_len; size_t complete_len; - /* no space left for name (+ NULL + type + len) */ - if ((HCI_MAX_AD_LENGTH - ad_len) < HCI_MAX_SHORT_NAME_LENGTH + 3) + /* no space left for name (+ type + len) */ + if ((max_adv_len(hdev) - ad_len) < HCI_MAX_SHORT_NAME_LENGTH + 2) return ad_len; /* use complete name if present and fits */ complete_len = strnlen(hdev->dev_name, sizeof(hdev->dev_name)); if (complete_len && complete_len <= HCI_MAX_SHORT_NAME_LENGTH) - return eir_append_name(ptr, ad_len, EIR_NAME_COMPLETE, - hdev->dev_name, complete_len + 1); + return eir_append_data(ptr, ad_len, EIR_NAME_COMPLETE, + hdev->dev_name, complete_len); /* use short name if present */ short_len = strnlen(hdev->short_name, sizeof(hdev->short_name)); if (short_len) - return eir_append_name(ptr, ad_len, EIR_NAME_SHORT, + return eir_append_data(ptr, ad_len, EIR_NAME_SHORT, hdev->short_name, - short_len == HCI_MAX_SHORT_NAME_LENGTH ? - short_len : short_len + 1); + short_len); /* use shortened full name if present, we already know that name * is longer then HCI_MAX_SHORT_NAME_LENGTH */ if (complete_len) - return eir_append_name(ptr, ad_len, EIR_NAME_SHORT, + return eir_append_data(ptr, ad_len, EIR_NAME_SHORT, hdev->dev_name, HCI_MAX_SHORT_NAME_LENGTH); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 12d36875358b94e1a2807203d3d4eae602f3ea18..bac5a369d2bef95a1d89c5c5d9f14b9e82d4abec 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -175,57 +175,6 @@ static void hci_conn_cleanup(struct hci_conn *conn) hci_dev_put(hdev); } -static void le_scan_cleanup(struct work_struct *work) -{ - struct hci_conn *conn = container_of(work, struct hci_conn, - le_scan_cleanup); - struct hci_dev *hdev = conn->hdev; - struct hci_conn *c = NULL; - - BT_DBG("%s hcon %p", hdev->name, conn); - - hci_dev_lock(hdev); - - /* Check that the hci_conn is still around */ - rcu_read_lock(); - list_for_each_entry_rcu(c, &hdev->conn_hash.list, list) { - if (c == conn) - break; - } - rcu_read_unlock(); - - if (c == conn) { - hci_connect_le_scan_cleanup(conn, 0x00); - hci_conn_cleanup(conn); - } - - hci_dev_unlock(hdev); - hci_dev_put(hdev); - hci_conn_put(conn); -} - -static void hci_connect_le_scan_remove(struct hci_conn *conn) -{ - BT_DBG("%s hcon %p", conn->hdev->name, conn); - - /* We can't call hci_conn_del/hci_conn_cleanup here since that - * could deadlock with another hci_conn_del() call that's holding - * hci_dev_lock and doing cancel_delayed_work_sync(&conn->disc_work). - * Instead, grab temporary extra references to the hci_dev and - * hci_conn and perform the necessary cleanup in a separate work - * callback. - */ - - hci_dev_hold(conn->hdev); - hci_conn_get(conn); - - /* Even though we hold a reference to the hdev, many other - * things might get cleaned up meanwhile, including the hdev's - * own workqueue, so we can't use that for scheduling. - */ - schedule_work(&conn->le_scan_cleanup); -} - static void hci_acl_create_connection(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; @@ -672,13 +621,6 @@ static void hci_conn_timeout(struct work_struct *work) if (refcnt > 0) return; - /* LE connections in scanning state need special handling */ - if (conn->state == BT_CONNECT && conn->type == LE_LINK && - test_bit(HCI_CONN_SCANNING, &conn->flags)) { - hci_connect_le_scan_remove(conn); - return; - } - hci_abort_conn(conn, hci_proto_disconn_ind(conn)); } @@ -1050,7 +992,6 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, INIT_DELAYED_WORK(&conn->auto_accept_work, hci_conn_auto_accept); INIT_DELAYED_WORK(&conn->idle_work, hci_conn_idle); INIT_DELAYED_WORK(&conn->le_conn_timeout, le_conn_timeout); - INIT_WORK(&conn->le_scan_cleanup, le_scan_cleanup); atomic_set(&conn->refcnt, 0); @@ -2837,81 +2778,46 @@ u32 hci_conn_get_phy(struct hci_conn *conn) return phys; } -int hci_abort_conn(struct hci_conn *conn, u8 reason) +static int abort_conn_sync(struct hci_dev *hdev, void *data) { - int r = 0; + struct hci_conn *conn; + u16 handle = PTR_ERR(data); - if (test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) + conn = hci_conn_hash_lookup_handle(hdev, handle); + if (!conn) return 0; - switch (conn->state) { - case BT_CONNECTED: - case BT_CONFIG: - if (conn->type == AMP_LINK) { - struct hci_cp_disconn_phy_link cp; + return hci_abort_conn_sync(hdev, conn, conn->abort_reason); +} - cp.phy_handle = HCI_PHY_HANDLE(conn->handle); - cp.reason = reason; - r = hci_send_cmd(conn->hdev, HCI_OP_DISCONN_PHY_LINK, - sizeof(cp), &cp); - } else { - struct hci_cp_disconnect dc; +int hci_abort_conn(struct hci_conn *conn, u8 reason) +{ + struct hci_dev *hdev = conn->hdev; - dc.handle = cpu_to_le16(conn->handle); - dc.reason = reason; - r = hci_send_cmd(conn->hdev, HCI_OP_DISCONNECT, - sizeof(dc), &dc); - } + /* If abort_reason has already been set it means the connection is + * already being aborted so don't attempt to overwrite it. + */ + if (conn->abort_reason) + return 0; - conn->state = BT_DISCONN; + bt_dev_dbg(hdev, "handle 0x%2.2x reason 0x%2.2x", conn->handle, reason); - break; - case BT_CONNECT: - if (conn->type == LE_LINK) { - if (test_bit(HCI_CONN_SCANNING, &conn->flags)) - break; - r = hci_send_cmd(conn->hdev, - HCI_OP_LE_CREATE_CONN_CANCEL, 0, NULL); - } else if (conn->type == ACL_LINK) { - if (conn->hdev->hci_ver < BLUETOOTH_VER_1_2) - break; - r = hci_send_cmd(conn->hdev, - HCI_OP_CREATE_CONN_CANCEL, - 6, &conn->dst); - } - break; - case BT_CONNECT2: - if (conn->type == ACL_LINK) { - struct hci_cp_reject_conn_req rej; - - bacpy(&rej.bdaddr, &conn->dst); - rej.reason = reason; - - r = hci_send_cmd(conn->hdev, - HCI_OP_REJECT_CONN_REQ, - sizeof(rej), &rej); - } else if (conn->type == SCO_LINK || conn->type == ESCO_LINK) { - struct hci_cp_reject_sync_conn_req rej; - - bacpy(&rej.bdaddr, &conn->dst); - - /* SCO rejection has its own limited set of - * allowed error values (0x0D-0x0F) which isn't - * compatible with most values passed to this - * function. To be safe hard-code one of the - * values that's suitable for SCO. - */ - rej.reason = HCI_ERROR_REJ_LIMITED_RESOURCES; + conn->abort_reason = reason; - r = hci_send_cmd(conn->hdev, - HCI_OP_REJECT_SYNC_CONN_REQ, - sizeof(rej), &rej); + /* If the connection is pending check the command opcode since that + * might be blocking on hci_cmd_sync_work while waiting its respective + * event so we need to hci_cmd_sync_cancel to cancel it. + */ + if (conn->state == BT_CONNECT && hdev->req_status == HCI_REQ_PEND) { + switch (hci_skb_event(hdev->sent_cmd)) { + case HCI_EV_LE_CONN_COMPLETE: + case HCI_EV_LE_ENHANCED_CONN_COMPLETE: + case HCI_EVT_LE_CIS_ESTABLISHED: + hci_cmd_sync_cancel(hdev, ECANCELED); + break; } - break; - default: - conn->state = BT_CLOSED; - break; } - return r; + return hci_cmd_sync_queue(hdev, abort_conn_sync, ERR_PTR(conn->handle), + NULL); } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 6a1db678d032f083fadb19b32f9a36c046e07a66..d6be3cb86598eb1717550e9e41219050673f38c5 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -908,7 +908,7 @@ int hci_get_dev_info(void __user *arg) else flags = hdev->flags; - strcpy(di.name, hdev->name); + strscpy(di.name, hdev->name, sizeof(di.name)); di.bdaddr = hdev->bdaddr; di.type = (hdev->bus & 0x0f) | ((hdev->dev_type & 0x03) << 4); di.flags = flags; @@ -1049,6 +1049,7 @@ static void hci_error_reset(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, error_reset); + hci_dev_hold(hdev); BT_DBG("%s", hdev->name); if (hdev->hw_error) @@ -1056,10 +1057,10 @@ static void hci_error_reset(struct work_struct *work) else bt_dev_err(hdev, "hardware error 0x%2.2x", hdev->hw_error_code); - if (hci_dev_do_close(hdev)) - return; + if (!hci_dev_do_close(hdev)) + hci_dev_do_open(hdev); - hci_dev_do_open(hdev); + hci_dev_put(hdev); } void hci_uuids_clear(struct hci_dev *hdev) @@ -1490,11 +1491,12 @@ static void hci_cmd_timeout(struct work_struct *work) struct hci_dev *hdev = container_of(work, struct hci_dev, cmd_timer.work); - if (hdev->sent_cmd) { - struct hci_command_hdr *sent = (void *) hdev->sent_cmd->data; - u16 opcode = __le16_to_cpu(sent->opcode); + if (hdev->req_skb) { + u16 opcode = hci_skb_opcode(hdev->req_skb); bt_dev_err(hdev, "command 0x%4.4x tx timeout", opcode); + + hci_cmd_sync_cancel_sync(hdev, ETIMEDOUT); } else { bt_dev_err(hdev, "command tx timeout"); } @@ -2731,8 +2733,6 @@ void hci_unregister_dev(struct hci_dev *hdev) hci_unregister_suspend_notifier(hdev); - msft_unregister(hdev); - hci_dev_do_close(hdev); if (!test_bit(HCI_INIT, &hdev->flags) && @@ -2786,10 +2786,12 @@ void hci_release_dev(struct hci_dev *hdev) hci_discovery_filter_clear(hdev); hci_blocked_keys_clear(hdev); hci_codec_list_clear(&hdev->local_codecs); + msft_release(hdev); hci_dev_unlock(hdev); ida_simple_remove(&hci_index_ida, hdev->id); kfree_skb(hdev->sent_cmd); + kfree_skb(hdev->req_skb); kfree_skb(hdev->recv_event); kfree(hdev); } @@ -2821,6 +2823,23 @@ int hci_unregister_suspend_notifier(struct hci_dev *hdev) return ret; } +/* Cancel ongoing command synchronously: + * + * - Cancel command timer + * - Reset command counter + * - Cancel command request + */ +static void hci_cancel_cmd_sync(struct hci_dev *hdev, int err) +{ + bt_dev_dbg(hdev, "err 0x%2.2x", err); + + cancel_delayed_work_sync(&hdev->cmd_timer); + cancel_delayed_work_sync(&hdev->ncmd_timer); + atomic_set(&hdev->cmd_cnt, 1); + + hci_cmd_sync_cancel_sync(hdev, err); +} + /* Suspend HCI device */ int hci_suspend_dev(struct hci_dev *hdev) { @@ -2837,6 +2856,9 @@ int hci_suspend_dev(struct hci_dev *hdev) if (mgmt_powering_down(hdev)) return 0; + /* Cancel potentially blocking sync operation before suspend */ + hci_cancel_cmd_sync(hdev, EHOSTDOWN); + hci_req_sync_lock(hdev); ret = hci_suspend_sync(hdev); hci_req_sync_unlock(hdev); @@ -3099,21 +3121,33 @@ int __hci_cmd_send(struct hci_dev *hdev, u16 opcode, u32 plen, EXPORT_SYMBOL(__hci_cmd_send); /* Get data from the previously sent command */ -void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode) +static void *hci_cmd_data(struct sk_buff *skb, __u16 opcode) { struct hci_command_hdr *hdr; - if (!hdev->sent_cmd) + if (!skb || skb->len < HCI_COMMAND_HDR_SIZE) return NULL; - hdr = (void *) hdev->sent_cmd->data; + hdr = (void *)skb->data; if (hdr->opcode != cpu_to_le16(opcode)) return NULL; - BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode); + return skb->data + HCI_COMMAND_HDR_SIZE; +} + +/* Get data from the previously sent command */ +void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode) +{ + void *data; + + /* Check if opcode matches last sent command */ + data = hci_cmd_data(hdev->sent_cmd, opcode); + if (!data) + /* Check if opcode matches last request */ + data = hci_cmd_data(hdev->req_skb, opcode); - return hdev->sent_cmd->data + HCI_COMMAND_HDR_SIZE; + return data; } /* Get data from last received event */ @@ -4009,17 +4043,19 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status, if (!status && !hci_req_is_complete(hdev)) return; + skb = hdev->req_skb; + /* If this was the last command in a request the complete - * callback would be found in hdev->sent_cmd instead of the + * callback would be found in hdev->req_skb instead of the * command queue (hdev->cmd_q). */ - if (bt_cb(hdev->sent_cmd)->hci.req_flags & HCI_REQ_SKB) { - *req_complete_skb = bt_cb(hdev->sent_cmd)->hci.req_complete_skb; + if (skb && bt_cb(skb)->hci.req_flags & HCI_REQ_SKB) { + *req_complete_skb = bt_cb(skb)->hci.req_complete_skb; return; } - if (bt_cb(hdev->sent_cmd)->hci.req_complete) { - *req_complete = bt_cb(hdev->sent_cmd)->hci.req_complete; + if (skb && bt_cb(skb)->hci.req_complete) { + *req_complete = bt_cb(skb)->hci.req_complete; return; } @@ -4115,6 +4151,36 @@ static void hci_rx_work(struct work_struct *work) } } +static void hci_send_cmd_sync(struct hci_dev *hdev, struct sk_buff *skb) +{ + int err; + + bt_dev_dbg(hdev, "skb %p", skb); + + kfree_skb(hdev->sent_cmd); + + hdev->sent_cmd = skb_clone(skb, GFP_KERNEL); + if (!hdev->sent_cmd) { + skb_queue_head(&hdev->cmd_q, skb); + queue_work(hdev->workqueue, &hdev->cmd_work); + return; + } + + err = hci_send_frame(hdev, skb); + if (err < 0) { + hci_cmd_sync_cancel_sync(hdev, -err); + return; + } + + if (hci_req_status_pend(hdev) && + !hci_dev_test_and_set_flag(hdev, HCI_CMD_PENDING)) { + kfree_skb(hdev->req_skb); + hdev->req_skb = skb_clone(hdev->sent_cmd, GFP_KERNEL); + } + + atomic_dec(&hdev->cmd_cnt); +} + static void hci_cmd_work(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, cmd_work); @@ -4129,30 +4195,15 @@ static void hci_cmd_work(struct work_struct *work) if (!skb) return; - kfree_skb(hdev->sent_cmd); - - hdev->sent_cmd = skb_clone(skb, GFP_KERNEL); - if (hdev->sent_cmd) { - int res; - if (hci_req_status_pend(hdev)) - hci_dev_set_flag(hdev, HCI_CMD_PENDING); - atomic_dec(&hdev->cmd_cnt); - - res = hci_send_frame(hdev, skb); - if (res < 0) - __hci_cmd_sync_cancel(hdev, -res); - - rcu_read_lock(); - if (test_bit(HCI_RESET, &hdev->flags) || - hci_dev_test_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE)) - cancel_delayed_work(&hdev->cmd_timer); - else - queue_delayed_work(hdev->workqueue, &hdev->cmd_timer, - HCI_CMD_TIMEOUT); - rcu_read_unlock(); - } else { - skb_queue_head(&hdev->cmd_q, skb); - queue_work(hdev->workqueue, &hdev->cmd_work); - } + hci_send_cmd_sync(hdev, skb); + + rcu_read_lock(); + if (test_bit(HCI_RESET, &hdev->flags) || + hci_dev_test_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE)) + cancel_delayed_work(&hdev->cmd_timer); + else + queue_delayed_work(hdev->workqueue, &hdev->cmd_timer, + HCI_CMD_TIMEOUT); + rcu_read_unlock(); } } diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index 6124b3425f351901d2c4f1d4db35e5e759d13776..c9400a7d93d7bf8e911a56a141889e417f0da824 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -217,10 +217,12 @@ static int conn_info_min_age_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val > hdev->conn_info_max_age) + hci_dev_lock(hdev); + if (val == 0 || val > hdev->conn_info_max_age) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->conn_info_min_age = val; hci_dev_unlock(hdev); @@ -245,10 +247,12 @@ static int conn_info_max_age_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val < hdev->conn_info_min_age) + hci_dev_lock(hdev); + if (val == 0 || val < hdev->conn_info_min_age) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->conn_info_max_age = val; hci_dev_unlock(hdev); @@ -566,10 +570,12 @@ static int sniff_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val % 2 || val > hdev->sniff_max_interval) + hci_dev_lock(hdev); + if (val == 0 || val % 2 || val > hdev->sniff_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->sniff_min_interval = val; hci_dev_unlock(hdev); @@ -594,10 +600,12 @@ static int sniff_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val % 2 || val < hdev->sniff_min_interval) + hci_dev_lock(hdev); + if (val == 0 || val % 2 || val < hdev->sniff_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->sniff_max_interval = val; hci_dev_unlock(hdev); @@ -849,10 +857,12 @@ static int conn_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval) + hci_dev_lock(hdev); + if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_conn_min_interval = val; hci_dev_unlock(hdev); @@ -877,10 +887,12 @@ static int conn_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval) + hci_dev_lock(hdev); + if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_conn_max_interval = val; hci_dev_unlock(hdev); @@ -989,10 +1001,12 @@ static int adv_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval) + hci_dev_lock(hdev); + if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_adv_min_interval = val; hci_dev_unlock(hdev); @@ -1017,10 +1031,12 @@ static int adv_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval) + hci_dev_lock(hdev); + if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_adv_max_interval = val; hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 56ecc5f97b9161ee5a3541464ba26fedae190e9b..bc14223f66937a0714eda8964fb4ec4642aa32d8 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1761,7 +1761,7 @@ static void store_pending_adv_report(struct hci_dev *hdev, bdaddr_t *bdaddr, { struct discovery_state *d = &hdev->discovery; - if (len > HCI_MAX_AD_LENGTH) + if (len > max_adv_len(hdev)) return; bacpy(&d->last_adv_addr, bdaddr); @@ -3234,6 +3234,31 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, if (test_bit(HCI_ENCRYPT, &hdev->flags)) set_bit(HCI_CONN_ENCRYPT, &conn->flags); + /* "Link key request" completed ahead of "connect request" completes */ + if (ev->encr_mode == 1 && !test_bit(HCI_CONN_ENCRYPT, &conn->flags) && + ev->link_type == ACL_LINK) { + struct link_key *key; + struct hci_cp_read_enc_key_size cp; + + key = hci_find_link_key(hdev, &ev->bdaddr); + if (key) { + set_bit(HCI_CONN_ENCRYPT, &conn->flags); + + if (!(hdev->commands[20] & 0x10)) { + conn->enc_key_size = HCI_LINK_KEY_SIZE; + } else { + cp.handle = cpu_to_le16(conn->handle); + if (hci_send_cmd(hdev, HCI_OP_READ_ENC_KEY_SIZE, + sizeof(cp), &cp)) { + bt_dev_err(hdev, "sending read key size failed"); + conn->enc_key_size = HCI_LINK_KEY_SIZE; + } + } + + hci_encrypt_cfm(conn, ev->status); + } + } + /* Get remote features */ if (conn->type == ACL_LINK) { struct hci_cp_read_remote_features cp; @@ -3567,8 +3592,6 @@ static void hci_remote_name_evt(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); - hci_conn_check_pending(hdev); - hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); @@ -4331,7 +4354,7 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, void *data, * (since for this kind of commands there will not be a command * complete event). */ - if (ev->status || (hdev->sent_cmd && !hci_skb_event(hdev->sent_cmd))) { + if (ev->status || (hdev->req_skb && !hci_skb_event(hdev->req_skb))) { hci_req_cmd_complete(hdev, *opcode, ev->status, req_complete, req_complete_skb); if (hci_dev_test_flag(hdev, HCI_CMD_PENDING)) { @@ -5282,9 +5305,12 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, void *data, hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); - if (!conn || !hci_conn_ssp_enabled(conn)) + if (!conn || !hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) goto unlock; + /* Assume remote supports SSP since it has triggered this event */ + set_bit(HCI_CONN_SSP_ENABLED, &conn->flags); + hci_conn_hold(conn); if (!hci_dev_test_flag(hdev, HCI_MGMT)) @@ -6239,8 +6265,9 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, return; } - if (!ext_adv && len > HCI_MAX_AD_LENGTH) { - bt_dev_err_ratelimited(hdev, "legacy adv larger than 31 bytes"); + if (len > max_adv_len(hdev)) { + bt_dev_err_ratelimited(hdev, + "adv larger than maximum supported"); return; } @@ -6305,7 +6332,8 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, */ conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, bdaddr_resolved, type); - if (!ext_adv && conn && type == LE_ADV_IND && len <= HCI_MAX_AD_LENGTH) { + if (!ext_adv && conn && type == LE_ADV_IND && + len <= max_adv_len(hdev)) { /* Store report for later inclusion by * mgmt_device_connected */ @@ -6446,7 +6474,7 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, void *data, info->length + 1)) break; - if (info->length <= HCI_MAX_AD_LENGTH) { + if (info->length <= max_adv_len(hdev)) { rssi = info->data[info->length]; process_adv_report(hdev, info->type, &info->bdaddr, info->bdaddr_type, NULL, 0, rssi, @@ -6716,6 +6744,10 @@ static void hci_le_remote_conn_param_req_evt(struct hci_dev *hdev, void *data, return send_conn_param_neg_reply(hdev, handle, HCI_ERROR_UNKNOWN_CONN_ID); + if (max > hcon->le_conn_max_interval) + return send_conn_param_neg_reply(hdev, handle, + HCI_ERROR_INVALID_LL_PARAMS); + if (hci_check_conn_params(min, max, latency, timeout)) return send_conn_param_neg_reply(hdev, handle, HCI_ERROR_INVALID_LL_PARAMS); @@ -7142,10 +7174,10 @@ static void hci_le_meta_evt(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "subevent 0x%2.2x", ev->subevent); /* Only match event if command OGF is for LE */ - if (hdev->sent_cmd && - hci_opcode_ogf(hci_skb_opcode(hdev->sent_cmd)) == 0x08 && - hci_skb_event(hdev->sent_cmd) == ev->subevent) { - *opcode = hci_skb_opcode(hdev->sent_cmd); + if (hdev->req_skb && + hci_opcode_ogf(hci_skb_opcode(hdev->req_skb)) == 0x08 && + hci_skb_event(hdev->req_skb) == ev->subevent) { + *opcode = hci_skb_opcode(hdev->req_skb); hci_req_cmd_complete(hdev, *opcode, 0x00, req_complete, req_complete_skb); } @@ -7245,10 +7277,10 @@ static void hci_store_wake_reason(struct hci_dev *hdev, u8 event, * keep track of the bdaddr of the connection event that woke us up. */ if (event == HCI_EV_CONN_REQUEST) { - bacpy(&hdev->wake_addr, &conn_complete->bdaddr); + bacpy(&hdev->wake_addr, &conn_request->bdaddr); hdev->wake_addr_type = BDADDR_BREDR; } else if (event == HCI_EV_CONN_COMPLETE) { - bacpy(&hdev->wake_addr, &conn_request->bdaddr); + bacpy(&hdev->wake_addr, &conn_complete->bdaddr); hdev->wake_addr_type = BDADDR_BREDR; } else if (event == HCI_EV_LE_META) { struct hci_ev_le_meta *le_ev = (void *)skb->data; @@ -7532,10 +7564,10 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) } /* Only match event if command OGF is not for LE */ - if (hdev->sent_cmd && - hci_opcode_ogf(hci_skb_opcode(hdev->sent_cmd)) != 0x08 && - hci_skb_event(hdev->sent_cmd) == event) { - hci_req_cmd_complete(hdev, hci_skb_opcode(hdev->sent_cmd), + if (hdev->req_skb && + hci_opcode_ogf(hci_skb_opcode(hdev->req_skb)) != 0x08 && + hci_skb_event(hdev->req_skb) == event) { + hci_req_cmd_complete(hdev, hci_skb_opcode(hdev->req_skb), status, &req_complete, &req_complete_skb); req_evt = event; } diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index f7e006a363829e9002e299c6d063275267fb3583..cf69e973b724f7323185feabeadb69242160b8ff 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -105,8 +105,10 @@ void hci_req_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode, if (hdev->req_status == HCI_REQ_PEND) { hdev->req_result = result; hdev->req_status = HCI_REQ_DONE; - if (skb) + if (skb) { + kfree_skb(hdev->req_skb); hdev->req_skb = skb_get(skb); + } wake_up_interruptible(&hdev->req_wait_q); } } @@ -916,7 +918,7 @@ void hci_request_setup(struct hci_dev *hdev) void hci_request_cancel_all(struct hci_dev *hdev) { - __hci_cmd_sync_cancel(hdev, ENODEV); + hci_cmd_sync_cancel_sync(hdev, ENODEV); cancel_interleave_scan(hdev); } diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index aa8ee52ff20e740461830a349b133b9d463d8219..03ed77a301f88038a19e9f39c2507a9b95d2e3a8 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -31,6 +31,10 @@ static void hci_cmd_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode, hdev->req_result = result; hdev->req_status = HCI_REQ_DONE; + /* Free the request command so it is not used as response */ + kfree_skb(hdev->req_skb); + hdev->req_skb = NULL; + if (skb) { struct sock *sk = hci_skb_sk(skb); @@ -38,7 +42,7 @@ static void hci_cmd_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode, if (sk) sock_put(sk); - hdev->req_skb = skb_get(skb); + hdev->req_rsp = skb_get(skb); } wake_up_interruptible(&hdev->req_wait_q); @@ -186,8 +190,8 @@ struct sk_buff *__hci_cmd_sync_sk(struct hci_dev *hdev, u16 opcode, u32 plen, hdev->req_status = 0; hdev->req_result = 0; - skb = hdev->req_skb; - hdev->req_skb = NULL; + skb = hdev->req_rsp; + hdev->req_rsp = NULL; bt_dev_dbg(hdev, "end: err %d", err); @@ -651,7 +655,7 @@ void hci_cmd_sync_clear(struct hci_dev *hdev) mutex_unlock(&hdev->cmd_sync_work_lock); } -void __hci_cmd_sync_cancel(struct hci_dev *hdev, int err) +void hci_cmd_sync_cancel(struct hci_dev *hdev, int err) { bt_dev_dbg(hdev, "err 0x%2.2x", err); @@ -659,29 +663,38 @@ void __hci_cmd_sync_cancel(struct hci_dev *hdev, int err) hdev->req_result = err; hdev->req_status = HCI_REQ_CANCELED; - cancel_delayed_work_sync(&hdev->cmd_timer); - cancel_delayed_work_sync(&hdev->ncmd_timer); - atomic_set(&hdev->cmd_cnt, 1); - - wake_up_interruptible(&hdev->req_wait_q); + queue_work(hdev->workqueue, &hdev->cmd_sync_cancel_work); } } +EXPORT_SYMBOL(hci_cmd_sync_cancel); -void hci_cmd_sync_cancel(struct hci_dev *hdev, int err) +/* Cancel ongoing command request synchronously: + * + * - Set result and mark status to HCI_REQ_CANCELED + * - Wakeup command sync thread + */ +void hci_cmd_sync_cancel_sync(struct hci_dev *hdev, int err) { bt_dev_dbg(hdev, "err 0x%2.2x", err); if (hdev->req_status == HCI_REQ_PEND) { - hdev->req_result = err; + /* req_result is __u32 so error must be positive to be properly + * propagated. + */ + hdev->req_result = err < 0 ? -err : err; hdev->req_status = HCI_REQ_CANCELED; - queue_work(hdev->workqueue, &hdev->cmd_sync_cancel_work); + wake_up_interruptible(&hdev->req_wait_q); } } -EXPORT_SYMBOL(hci_cmd_sync_cancel); +EXPORT_SYMBOL(hci_cmd_sync_cancel_sync); -int hci_cmd_sync_queue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, - void *data, hci_cmd_sync_work_destroy_t destroy) +/* Submit HCI command to be run in as cmd_sync_work: + * + * - hdev must _not_ be unregistered + */ +int hci_cmd_sync_submit(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) { struct hci_cmd_sync_work_entry *entry; int err = 0; @@ -711,6 +724,23 @@ unlock: mutex_unlock(&hdev->unregister_lock); return err; } +EXPORT_SYMBOL(hci_cmd_sync_submit); + +/* Queue HCI command: + * + * - hdev must be running + */ +int hci_cmd_sync_queue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + /* Only queue command if hdev is running which means it had been opened + * and is either on init phase or is already up. + */ + if (!test_bit(HCI_RUNNING, &hdev->flags)) + return -ENETDOWN; + + return hci_cmd_sync_submit(hdev, func, data, destroy); +} EXPORT_SYMBOL(hci_cmd_sync_queue); int hci_update_eir_sync(struct hci_dev *hdev) @@ -2251,8 +2281,11 @@ static int hci_le_add_accept_list_sync(struct hci_dev *hdev, /* During suspend, only wakeable devices can be in acceptlist */ if (hdev->suspended && - !(params->flags & HCI_CONN_FLAG_REMOTE_WAKEUP)) + !(params->flags & HCI_CONN_FLAG_REMOTE_WAKEUP)) { + hci_le_del_accept_list_sync(hdev, ¶ms->addr, + params->addr_type); return 0; + } /* Select filter policy to accept all advertising */ if (*num_entries >= hdev->le_accept_list_size) @@ -3260,7 +3293,10 @@ static void hci_dev_get_bd_addr_from_property(struct hci_dev *hdev) if (ret < 0 || !bacmp(&ba, BDADDR_ANY)) return; - bacpy(&hdev->public_addr, &ba); + if (test_bit(HCI_QUIRK_BDADDR_PROPERTY_BROKEN, &hdev->quirks)) + baswap(&hdev->public_addr, &ba); + else + bacpy(&hdev->public_addr, &ba); } struct hci_init_stage { @@ -4856,6 +4892,11 @@ int hci_dev_open_sync(struct hci_dev *hdev) hdev->sent_cmd = NULL; } + if (hdev->req_skb) { + kfree_skb(hdev->req_skb); + hdev->req_skb = NULL; + } + clear_bit(HCI_RUNNING, &hdev->flags); hci_sock_dev_event(hdev, HCI_DEV_CLOSE); @@ -5017,6 +5058,12 @@ int hci_dev_close_sync(struct hci_dev *hdev) hdev->sent_cmd = NULL; } + /* Drop last request */ + if (hdev->req_skb) { + kfree_skb(hdev->req_skb); + hdev->req_skb = NULL; + } + clear_bit(HCI_RUNNING, &hdev->flags); hci_sock_dev_event(hdev, HCI_DEV_CLOSE); @@ -5209,22 +5256,27 @@ static int hci_disconnect_sync(struct hci_dev *hdev, struct hci_conn *conn, } static int hci_le_connect_cancel_sync(struct hci_dev *hdev, - struct hci_conn *conn) + struct hci_conn *conn, u8 reason) { + /* Return reason if scanning since the connection shall probably be + * cleanup directly. + */ if (test_bit(HCI_CONN_SCANNING, &conn->flags)) - return 0; + return reason; - if (test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) + if (conn->role == HCI_ROLE_SLAVE || + test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) return 0; return __hci_cmd_sync_status(hdev, HCI_OP_LE_CREATE_CONN_CANCEL, 0, NULL, HCI_CMD_TIMEOUT); } -static int hci_connect_cancel_sync(struct hci_dev *hdev, struct hci_conn *conn) +static int hci_connect_cancel_sync(struct hci_dev *hdev, struct hci_conn *conn, + u8 reason) { if (conn->type == LE_LINK) - return hci_le_connect_cancel_sync(hdev, conn); + return hci_le_connect_cancel_sync(hdev, conn, reason); if (hdev->hci_ver < BLUETOOTH_VER_1_2) return 0; @@ -5277,9 +5329,11 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) case BT_CONFIG: return hci_disconnect_sync(hdev, conn, reason); case BT_CONNECT: - err = hci_connect_cancel_sync(hdev, conn); + err = hci_connect_cancel_sync(hdev, conn, reason); /* Cleanup hci_conn object if it cannot be cancelled as it - * likelly means the controller and host stack are out of sync. + * likelly means the controller and host stack are out of sync + * or in case of LE it was still scanning so it can be cleanup + * safely. */ if (err) { hci_dev_lock(hdev); @@ -5485,7 +5539,7 @@ static int hci_inquiry_sync(struct hci_dev *hdev, u8 length) bt_dev_dbg(hdev, ""); - if (hci_dev_test_flag(hdev, HCI_INQUIRY)) + if (test_bit(HCI_INQUIRY, &hdev->flags)) return 0; hci_dev_lock(hdev); @@ -6194,7 +6248,7 @@ int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn) done: if (err == -ETIMEDOUT) - hci_le_connect_cancel_sync(hdev, conn); + hci_le_connect_cancel_sync(hdev, conn, 0x00); /* Re-enable advertising after the connection attempt is finished. */ hci_resume_advertising_sync(hdev); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 81f5974e5eb5aa2729b36e3208aa0e059317b892..c34011113d4c51d74f2cc5255effa3c5220bb80c 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -435,6 +435,9 @@ static void l2cap_chan_timeout(struct work_struct *work) BT_DBG("chan %p state %s", chan, state_to_string(chan->state)); + if (!conn) + return; + mutex_lock(&conn->chan_lock); /* __set_chan_timer() calls l2cap_chan_hold(chan) while scheduling * this work. No need to call l2cap_chan_hold(chan) here again. @@ -5614,7 +5617,13 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, memset(&rsp, 0, sizeof(rsp)); - err = hci_check_conn_params(min, max, latency, to_multiplier); + if (max > hcon->le_conn_max_interval) { + BT_DBG("requested connection interval exceeds current bounds."); + err = -EINVAL; + } else { + err = hci_check_conn_params(min, max, latency, to_multiplier); + } + if (err) rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_REJECTED); else diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 947ca580bb9a2f6b6ea21e456ea4bb6b1b8fe2c6..e3c7029ec8a612ecd7138303c2a1dd6ea08942de 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -457,7 +457,8 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, struct l2cap_chan *chan = l2cap_pi(sk)->chan; struct l2cap_options opts; struct l2cap_conninfo cinfo; - int len, err = 0; + int err = 0; + size_t len; u32 opt; BT_DBG("sk %p", sk); @@ -504,7 +505,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, BT_DBG("mode 0x%2.2x", chan->mode); - len = min_t(unsigned int, len, sizeof(opts)); + len = min(len, sizeof(opts)); if (copy_to_user(optval, (char *) &opts, len)) err = -EFAULT; @@ -554,7 +555,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, cinfo.hci_handle = chan->conn->hcon->handle; memcpy(cinfo.dev_class, chan->conn->hcon->dev_class, 3); - len = min_t(unsigned int, len, sizeof(cinfo)); + len = min(len, sizeof(cinfo)); if (copy_to_user(optval, (char *) &cinfo, len)) err = -EFAULT; @@ -745,7 +746,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, struct sock *sk = sock->sk; struct l2cap_chan *chan = l2cap_pi(sk)->chan; struct l2cap_options opts; - int len, err = 0; + int err = 0; u32 opt; BT_DBG("sk %p", sk); @@ -772,11 +773,9 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, opts.max_tx = chan->max_tx; opts.txwin_size = chan->tx_win; - len = min_t(unsigned int, sizeof(opts), optlen); - if (copy_from_sockptr(&opts, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opts, sizeof(opts), optval, optlen); + if (err) break; - } if (opts.txwin_size > L2CAP_DEFAULT_EXT_WINDOW) { err = -EINVAL; @@ -819,10 +818,9 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, break; case L2CAP_LM: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt & L2CAP_LM_FIPS) { err = -EINVAL; @@ -903,7 +901,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, struct bt_security sec; struct bt_power pwr; struct l2cap_conn *conn; - int len, err = 0; + int err = 0; u32 opt; u16 mtu; u8 mode; @@ -929,11 +927,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, sec.level = BT_SECURITY_LOW; - len = min_t(unsigned int, sizeof(sec), optlen); - if (copy_from_sockptr(&sec, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&sec, sizeof(sec), optval, optlen); + if (err) break; - } if (sec.level < BT_SECURITY_LOW || sec.level > BT_SECURITY_FIPS) { @@ -978,10 +974,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) { set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); @@ -993,10 +988,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_FLUSHABLE: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt > BT_FLUSHABLE_ON) { err = -EINVAL; @@ -1028,11 +1022,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, pwr.force_active = BT_POWER_FORCE_ACTIVE_ON; - len = min_t(unsigned int, sizeof(pwr), optlen); - if (copy_from_sockptr(&pwr, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&pwr, sizeof(pwr), optval, optlen); + if (err) break; - } if (pwr.force_active) set_bit(FLAG_FORCE_ACTIVE, &chan->flags); @@ -1041,10 +1033,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_CHANNEL_POLICY: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt > BT_CHANNEL_POLICY_AMP_PREFERRED) { err = -EINVAL; @@ -1089,10 +1080,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&mtu, optval, sizeof(u16))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&mtu, sizeof(mtu), optval, optlen); + if (err) break; - } if (chan->mode == L2CAP_MODE_EXT_FLOWCTL && sk->sk_state == BT_CONNECTED) @@ -1120,10 +1110,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&mode, optval, sizeof(u8))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&mode, sizeof(mode), optval, optlen); + if (err) break; - } BT_DBG("mode %u", mode); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 6d631a2e60166054fb8238b8a20d3f0a49bd1d38..76dac5a90aef0c9f31531d87738a42789857c156 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -1039,6 +1039,8 @@ static void rpa_expired(struct work_struct *work) hci_cmd_sync_queue(hdev, rpa_expired_sync, NULL, NULL); } +static int set_discoverable_sync(struct hci_dev *hdev, void *data); + static void discov_off(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, @@ -1057,7 +1059,7 @@ static void discov_off(struct work_struct *work) hci_dev_clear_flag(hdev, HCI_DISCOVERABLE); hdev->discov_timeout = 0; - hci_update_discoverable(hdev); + hci_cmd_sync_queue(hdev, set_discoverable_sync, NULL, NULL); mgmt_new_settings(hdev); @@ -1399,8 +1401,16 @@ static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data, goto failed; } - err = hci_cmd_sync_queue(hdev, set_powered_sync, cmd, - mgmt_set_powered_complete); + /* Cancel potentially blocking sync operation before power off */ + if (cp->val == 0x00) { + hci_cmd_sync_cancel_sync(hdev, -EHOSTDOWN); + err = hci_cmd_sync_queue(hdev, set_powered_sync, cmd, + mgmt_set_powered_complete); + } else { + /* Use hci_cmd_sync_submit since hdev might not be running */ + err = hci_cmd_sync_submit(hdev, set_powered_sync, cmd, + mgmt_set_powered_complete); + } if (err < 0) mgmt_pending_remove(cmd); @@ -2670,7 +2680,11 @@ static int add_uuid(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) goto failed; } - err = hci_cmd_sync_queue(hdev, add_uuid_sync, cmd, mgmt_class_complete); + /* MGMT_OP_ADD_UUID don't require adapter the UP/Running so use + * hci_cmd_sync_submit instead of hci_cmd_sync_queue. + */ + err = hci_cmd_sync_submit(hdev, add_uuid_sync, cmd, + mgmt_class_complete); if (err < 0) { mgmt_pending_free(cmd); goto failed; @@ -2764,8 +2778,11 @@ update_class: goto unlock; } - err = hci_cmd_sync_queue(hdev, remove_uuid_sync, cmd, - mgmt_class_complete); + /* MGMT_OP_REMOVE_UUID don't require adapter the UP/Running so use + * hci_cmd_sync_submit instead of hci_cmd_sync_queue. + */ + err = hci_cmd_sync_submit(hdev, remove_uuid_sync, cmd, + mgmt_class_complete); if (err < 0) mgmt_pending_free(cmd); @@ -2831,8 +2848,11 @@ static int set_dev_class(struct sock *sk, struct hci_dev *hdev, void *data, goto unlock; } - err = hci_cmd_sync_queue(hdev, set_class_sync, cmd, - mgmt_class_complete); + /* MGMT_OP_SET_DEV_CLASS don't require adapter the UP/Running so use + * hci_cmd_sync_submit instead of hci_cmd_sync_queue. + */ + err = hci_cmd_sync_submit(hdev, set_class_sync, cmd, + mgmt_class_complete); if (err < 0) mgmt_pending_free(cmd); @@ -3573,18 +3593,6 @@ unlock: return err; } -static int abort_conn_sync(struct hci_dev *hdev, void *data) -{ - struct hci_conn *conn; - u16 handle = PTR_ERR(data); - - conn = hci_conn_hash_lookup_handle(hdev, handle); - if (!conn) - return 0; - - return hci_abort_conn_sync(hdev, conn, HCI_ERROR_REMOTE_USER_TERM); -} - static int cancel_pair_device(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { @@ -3635,8 +3643,7 @@ static int cancel_pair_device(struct sock *sk, struct hci_dev *hdev, void *data, le_addr_type(addr->type)); if (conn->conn_reason == CONN_REASON_PAIR_DEVICE) - hci_cmd_sync_queue(hdev, abort_conn_sync, ERR_PTR(conn->handle), - NULL); + hci_abort_conn(conn, HCI_ERROR_REMOTE_USER_TERM); unlock: hci_dev_unlock(hdev); @@ -5381,9 +5388,9 @@ static u8 parse_adv_monitor_pattern(struct adv_monitor *m, u8 pattern_count, for (i = 0; i < pattern_count; i++) { offset = patterns[i].offset; length = patterns[i].length; - if (offset >= HCI_MAX_AD_LENGTH || - length > HCI_MAX_AD_LENGTH || - (offset + length) > HCI_MAX_AD_LENGTH) + if (offset >= HCI_MAX_EXT_AD_LENGTH || + length > HCI_MAX_EXT_AD_LENGTH || + (offset + length) > HCI_MAX_EXT_AD_LENGTH) return MGMT_STATUS_INVALID_PARAMS; p = kmalloc(sizeof(*p), GFP_KERNEL); @@ -5533,8 +5540,8 @@ static int remove_adv_monitor(struct sock *sk, struct hci_dev *hdev, goto unlock; } - err = hci_cmd_sync_queue(hdev, mgmt_remove_adv_monitor_sync, cmd, - mgmt_remove_adv_monitor_complete); + err = hci_cmd_sync_submit(hdev, mgmt_remove_adv_monitor_sync, cmd, + mgmt_remove_adv_monitor_complete); if (err) { mgmt_pending_remove(cmd); @@ -8439,8 +8446,8 @@ static int read_adv_features(struct sock *sk, struct hci_dev *hdev, supported_flags = get_supported_adv_flags(hdev); rp->supported_flags = cpu_to_le32(supported_flags); - rp->max_adv_data_len = HCI_MAX_AD_LENGTH; - rp->max_scan_rsp_len = HCI_MAX_AD_LENGTH; + rp->max_adv_data_len = max_adv_len(hdev); + rp->max_scan_rsp_len = max_adv_len(hdev); rp->max_instances = hdev->le_num_of_adv_sets; rp->num_instances = hdev->adv_instance_cnt; @@ -8468,7 +8475,7 @@ static int read_adv_features(struct sock *sk, struct hci_dev *hdev, static u8 calculate_name_len(struct hci_dev *hdev) { - u8 buf[HCI_MAX_SHORT_NAME_LENGTH + 3]; + u8 buf[HCI_MAX_SHORT_NAME_LENGTH + 2]; /* len + type + name */ return eir_append_local_name(hdev, buf, 0); } @@ -8476,7 +8483,7 @@ static u8 calculate_name_len(struct hci_dev *hdev) static u8 tlv_data_max_len(struct hci_dev *hdev, u32 adv_flags, bool is_adv_data) { - u8 max_len = HCI_MAX_AD_LENGTH; + u8 max_len = max_adv_len(hdev); if (is_adv_data) { if (adv_flags & (MGMT_ADV_FLAG_DISCOV | @@ -9764,14 +9771,6 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, struct mgmt_ev_device_disconnected ev; struct sock *sk = NULL; - /* The connection is still in hci_conn_hash so test for 1 - * instead of 0 to know if this is the last one. - */ - if (mgmt_powering_down(hdev) && hci_conn_count(hdev) == 1) { - cancel_delayed_work(&hdev->power_off); - queue_work(hdev->req_workqueue, &hdev->power_off.work); - } - if (!mgmt_connected) return; @@ -9828,14 +9827,6 @@ void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, { struct mgmt_ev_connect_failed ev; - /* The connection is still in hci_conn_hash so test for 1 - * instead of 0 to know if this is the last one. - */ - if (mgmt_powering_down(hdev) && hci_conn_count(hdev) == 1) { - cancel_delayed_work(&hdev->power_off); - queue_work(hdev->req_workqueue, &hdev->power_off.work); - } - bacpy(&ev.addr.bdaddr, bdaddr); ev.addr.type = link_to_bdaddr(link_type, addr_type); ev.status = mgmt_status(status); diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index bee6a4c656be4db573b11a813727f71429c9a9f1..076cf8bce4d9e3d63f5edc93ccf8ffc175c87e87 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -584,7 +584,7 @@ void msft_register(struct hci_dev *hdev) hdev->msft_data = msft; } -void msft_unregister(struct hci_dev *hdev) +void msft_release(struct hci_dev *hdev) { struct msft_data *msft = hdev->msft_data; diff --git a/net/bluetooth/msft.h b/net/bluetooth/msft.h index 2a63205b377b70a79044b983d49f140fd3eb5578..fe538e9c91c0194db03c0dd32e664a4cd20d5d98 100644 --- a/net/bluetooth/msft.h +++ b/net/bluetooth/msft.h @@ -14,7 +14,7 @@ bool msft_monitor_supported(struct hci_dev *hdev); void msft_register(struct hci_dev *hdev); -void msft_unregister(struct hci_dev *hdev); +void msft_release(struct hci_dev *hdev); void msft_do_open(struct hci_dev *hdev); void msft_do_close(struct hci_dev *hdev); void msft_vendor_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb); @@ -35,7 +35,7 @@ static inline bool msft_monitor_supported(struct hci_dev *hdev) } static inline void msft_register(struct hci_dev *hdev) {} -static inline void msft_unregister(struct hci_dev *hdev) {} +static inline void msft_release(struct hci_dev *hdev) {} static inline void msft_do_open(struct hci_dev *hdev) {} static inline void msft_do_close(struct hci_dev *hdev) {} static inline void msft_vendor_evt(struct hci_dev *hdev, void *data, diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 8d6fce9005bddf1bd4e7a53ea02b3a4663bf7ebd..4f54c7df3a94f8e55b9cb6efd81e2c8cf3f98aca 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -1937,7 +1937,7 @@ static struct rfcomm_session *rfcomm_process_rx(struct rfcomm_session *s) /* Get data directly from socket receive queue without copying it. */ while ((skb = skb_dequeue(&sk->sk_receive_queue))) { skb_orphan(skb); - if (!skb_linearize(skb)) { + if (!skb_linearize(skb) && sk->sk_state != BT_CLOSED) { s = rfcomm_recv_frame(s, skb); if (!s) break; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 6d4168cfeb5631782ce17613901b34cc10b2d04f..301cf802d32c406c9a745f5459cc9042301e1d73 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -84,6 +84,10 @@ static void sco_sock_timeout(struct work_struct *work) struct sock *sk; sco_conn_lock(conn); + if (!conn->hcon) { + sco_conn_unlock(conn); + return; + } sk = conn->sk; if (sk) sock_hold(sk); @@ -831,7 +835,7 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; - int len, err = 0; + int err = 0; struct bt_voice voice; u32 opt; struct bt_codecs *codecs; @@ -850,10 +854,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); @@ -870,11 +873,10 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, voice.setting = sco_pi(sk)->setting; - len = min_t(unsigned int, sizeof(voice), optlen); - if (copy_from_sockptr(&voice, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&voice, sizeof(voice), optval, + optlen); + if (err) break; - } /* Explicitly check for these values */ if (voice.setting != BT_VOICE_TRANSPARENT && @@ -897,10 +899,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_PKT_STATUS: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) sco_pi(sk)->cmsg_mask |= SCO_CMSG_PKT_STATUS; @@ -941,9 +942,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(buffer, optval, optlen)) { + err = bt_copy_from_sockptr(buffer, optlen, optval, optlen); + if (err) { hci_dev_put(hdev); - err = -EFAULT; break; } @@ -974,7 +975,8 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, struct sock *sk = sock->sk; struct sco_options opts; struct sco_conninfo cinfo; - int len, err = 0; + int err = 0; + size_t len; BT_DBG("sk %p", sk); @@ -996,7 +998,7 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, BT_DBG("mtu %u", opts.mtu); - len = min_t(unsigned int, len, sizeof(opts)); + len = min(len, sizeof(opts)); if (copy_to_user(optval, (char *)&opts, len)) err = -EFAULT; @@ -1014,7 +1016,7 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, cinfo.hci_handle = sco_pi(sk)->conn->hcon->handle; memcpy(cinfo.dev_class, sco_pi(sk)->conn->hcon->dev_class, 3); - len = min_t(unsigned int, len, sizeof(cinfo)); + len = min(len, sizeof(cinfo)); if (copy_to_user(optval, (char *)&cinfo, len)) err = -EFAULT; diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 4e3394a7d7d453b4c8588206d917c4620438db7c..9661698e86e40b188ab9f5ef1938ae73fd77a42c 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -253,6 +253,7 @@ static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb, { struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev; const unsigned char *src = eth_hdr(skb)->h_source; + struct sk_buff *nskb; if (!should_deliver(p, skb)) return; @@ -261,12 +262,16 @@ static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb, if (skb->dev == p->dev && ether_addr_equal(src, addr)) return; - skb = skb_copy(skb, GFP_ATOMIC); - if (!skb) { + __skb_push(skb, ETH_HLEN); + nskb = pskb_copy(skb, GFP_ATOMIC); + __skb_pull(skb, ETH_HLEN); + if (!nskb) { DEV_STATS_INC(dev, tx_dropped); return; } + skb = nskb; + __skb_pull(skb, ETH_HLEN); if (!is_broadcast_ether_addr(addr)) memcpy(eth_hdr(skb)->h_dest, addr, ETH_ALEN); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 6bb272894c960d81b69adeb586de68c4fc5e6954..b94a1783902eae12e39f3658d3077160b55efcb3 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -30,7 +30,7 @@ br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb) return netif_receive_skb(skb); } -static int br_pass_frame_up(struct sk_buff *skb) +static int br_pass_frame_up(struct sk_buff *skb, bool promisc) { struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev; struct net_bridge *br = netdev_priv(brdev); @@ -65,6 +65,8 @@ static int br_pass_frame_up(struct sk_buff *skb) br_multicast_count(br, NULL, skb, br_multicast_igmp_type(skb), BR_MCAST_DIR_TX); + BR_INPUT_SKB_CB(skb)->promisc = promisc; + return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, dev_net(indev), NULL, skb, indev, NULL, br_netif_receive_skb); @@ -82,6 +84,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb struct net_bridge_mcast *brmctx; struct net_bridge_vlan *vlan; struct net_bridge *br; + bool promisc; u16 vid = 0; u8 state; @@ -120,7 +123,9 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if (p->flags & BR_LEARNING) br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, 0); - local_rcv = !!(br->dev->flags & IFF_PROMISC); + promisc = !!(br->dev->flags & IFF_PROMISC); + local_rcv = promisc; + if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) { /* by definition the broadcast is also a multicast address */ if (is_broadcast_ether_addr(eth_hdr(skb)->h_dest)) { @@ -183,7 +188,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb unsigned long now = jiffies; if (test_bit(BR_FDB_LOCAL, &dst->flags)) - return br_pass_frame_up(skb); + return br_pass_frame_up(skb, false); if (now != dst->used) dst->used = now; @@ -196,7 +201,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb } if (local_rcv) - return br_pass_frame_up(skb); + return br_pass_frame_up(skb, promisc); out: return 0; @@ -368,6 +373,8 @@ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb) goto forward; } + BR_INPUT_SKB_CB(skb)->promisc = false; + /* The else clause should be hit when nf_hook(): * - returns < 0 (drop/error) * - returns = 0 (stolen/nf_queue) diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 202ad43e35d6b222d108087ea475cea4718127b5..9ac70c27da8355101b4a8a3e5f99bac03eaac5c7 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -43,6 +43,10 @@ #include #endif +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include +#endif + static unsigned int brnf_net_id __read_mostly; struct brnf_net { @@ -553,6 +557,96 @@ static unsigned int br_nf_pre_routing(void *priv, return NF_STOLEN; } +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +/* conntracks' nf_confirm logic cannot handle cloned skbs referencing + * the same nf_conn entry, which will happen for multicast (broadcast) + * Frames on bridges. + * + * Example: + * macvlan0 + * br0 + * ethX ethY + * + * ethX (or Y) receives multicast or broadcast packet containing + * an IP packet, not yet in conntrack table. + * + * 1. skb passes through bridge and fake-ip (br_netfilter)Prerouting. + * -> skb->_nfct now references a unconfirmed entry + * 2. skb is broad/mcast packet. bridge now passes clones out on each bridge + * interface. + * 3. skb gets passed up the stack. + * 4. In macvlan case, macvlan driver retains clone(s) of the mcast skb + * and schedules a work queue to send them out on the lower devices. + * + * The clone skb->_nfct is not a copy, it is the same entry as the + * original skb. The macvlan rx handler then returns RX_HANDLER_PASS. + * 5. Normal conntrack hooks (in NF_INET_LOCAL_IN) confirm the orig skb. + * + * The Macvlan broadcast worker and normal confirm path will race. + * + * This race will not happen if step 2 already confirmed a clone. In that + * case later steps perform skb_clone() with skb->_nfct already confirmed (in + * hash table). This works fine. + * + * But such confirmation won't happen when eb/ip/nftables rules dropped the + * packets before they reached the nf_confirm step in postrouting. + * + * Work around this problem by explicit confirmation of the entry at + * LOCAL_IN time, before upper layer has a chance to clone the unconfirmed + * entry. + * + */ +static unsigned int br_nf_local_in(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + bool promisc = BR_INPUT_SKB_CB(skb)->promisc; + struct nf_conntrack *nfct = skb_nfct(skb); + const struct nf_ct_hook *ct_hook; + struct nf_conn *ct; + int ret; + + if (promisc) { + nf_reset_ct(skb); + return NF_ACCEPT; + } + + if (!nfct || skb->pkt_type == PACKET_HOST) + return NF_ACCEPT; + + ct = container_of(nfct, struct nf_conn, ct_general); + if (likely(nf_ct_is_confirmed(ct))) + return NF_ACCEPT; + + WARN_ON_ONCE(skb_shared(skb)); + WARN_ON_ONCE(refcount_read(&nfct->use) != 1); + + /* We can't call nf_confirm here, it would create a dependency + * on nf_conntrack module. + */ + ct_hook = rcu_dereference(nf_ct_hook); + if (!ct_hook) { + skb->_nfct = 0ul; + nf_conntrack_put(nfct); + return NF_ACCEPT; + } + + nf_bridge_pull_encap_header(skb); + ret = ct_hook->confirm(skb); + switch (ret & NF_VERDICT_MASK) { + case NF_STOLEN: + return NF_STOLEN; + default: + nf_bridge_push_encap_header(skb); + break; + } + + ct = container_of(nfct, struct nf_conn, ct_general); + WARN_ON_ONCE(!nf_ct_is_confirmed(ct)); + + return ret; +} +#endif /* PF_BRIDGE/FORWARD *************************************************/ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) @@ -962,6 +1056,14 @@ static const struct nf_hook_ops br_nf_ops[] = { .hooknum = NF_BR_PRE_ROUTING, .priority = NF_BR_PRI_BRNF, }, +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + { + .hook = br_nf_local_in, + .pf = NFPROTO_BRIDGE, + .hooknum = NF_BR_LOCAL_IN, + .priority = NF_BR_PRI_LAST, + }, +#endif { .hook = br_nf_forward_ip, .pf = NFPROTO_BRIDGE, diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index d087fd4c784ac798d854e82604b55b76dfadbb5f..e9e5c77ef0f4a5f5879f2e6e9631e72155854380 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -439,7 +439,8 @@ static int br_fill_ifinfo(struct sk_buff *skb, u32 filter_mask, const struct net_device *dev, bool getlink) { - u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; + u8 operstate = netif_running(dev) ? READ_ONCE(dev->operstate) : + IF_OPER_DOWN; struct nlattr *af = NULL; struct net_bridge *br; struct ifinfomsg *hdr; @@ -650,7 +651,7 @@ void br_ifinfo_notify(int event, const struct net_bridge *br, { u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED; - return br_info_notify(event, br, port, filter); + br_info_notify(event, br, port, filter); } /* diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 51d010f64e06601f350b04b94dadf8dbc61efb59..940de95167689b668f58fd7d19f424b87ea7b534 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -559,6 +559,7 @@ struct br_input_skb_cb { #endif u8 proxyarp_replied:1; u8 src_port_isolated:1; + u8 promisc:1; #ifdef CONFIG_BRIDGE_VLAN_FILTERING u8 vlan_filtered:1; #endif diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 4b3982c368b35bbf6a57cca01d7f00ad43929d5b..b61ef2dff7a4bf7db7f19d0d6f00c8e08e05dfc0 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -593,21 +593,40 @@ br_switchdev_mdb_replay_one(struct notifier_block *nb, struct net_device *dev, } static int br_switchdev_mdb_queue_one(struct list_head *mdb_list, + struct net_device *dev, + unsigned long action, enum switchdev_obj_id id, const struct net_bridge_mdb_entry *mp, struct net_device *orig_dev) { - struct switchdev_obj_port_mdb *mdb; + struct switchdev_obj_port_mdb mdb = { + .obj = { + .id = id, + .orig_dev = orig_dev, + }, + }; + struct switchdev_obj_port_mdb *pmdb; - mdb = kzalloc(sizeof(*mdb), GFP_ATOMIC); - if (!mdb) - return -ENOMEM; + br_switchdev_mdb_populate(&mdb, mp); + + if (action == SWITCHDEV_PORT_OBJ_ADD && + switchdev_port_obj_act_is_deferred(dev, action, &mdb.obj)) { + /* This event is already in the deferred queue of + * events, so this replay must be elided, lest the + * driver receives duplicate events for it. This can + * only happen when replaying additions, since + * modifications are always immediately visible in + * br->mdb_list, whereas actual event delivery may be + * delayed. + */ + return 0; + } - mdb->obj.id = id; - mdb->obj.orig_dev = orig_dev; - br_switchdev_mdb_populate(mdb, mp); - list_add_tail(&mdb->obj.list, mdb_list); + pmdb = kmemdup(&mdb, sizeof(mdb), GFP_ATOMIC); + if (!pmdb) + return -ENOMEM; + list_add_tail(&pmdb->obj.list, mdb_list); return 0; } @@ -675,51 +694,50 @@ br_switchdev_mdb_replay(struct net_device *br_dev, struct net_device *dev, if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) return 0; - /* We cannot walk over br->mdb_list protected just by the rtnl_mutex, - * because the write-side protection is br->multicast_lock. But we - * need to emulate the [ blocking ] calling context of a regular - * switchdev event, so since both br->multicast_lock and RCU read side - * critical sections are atomic, we have no choice but to pick the RCU - * read side lock, queue up all our events, leave the critical section - * and notify switchdev from blocking context. + if (adding) + action = SWITCHDEV_PORT_OBJ_ADD; + else + action = SWITCHDEV_PORT_OBJ_DEL; + + /* br_switchdev_mdb_queue_one() will take care to not queue a + * replay of an event that is already pending in the switchdev + * deferred queue. In order to safely determine that, there + * must be no new deferred MDB notifications enqueued for the + * duration of the MDB scan. Therefore, grab the write-side + * lock to avoid racing with any concurrent IGMP/MLD snooping. */ - rcu_read_lock(); + spin_lock_bh(&br->multicast_lock); - hlist_for_each_entry_rcu(mp, &br->mdb_list, mdb_node) { + hlist_for_each_entry(mp, &br->mdb_list, mdb_node) { struct net_bridge_port_group __rcu * const *pp; const struct net_bridge_port_group *p; if (mp->host_joined) { - err = br_switchdev_mdb_queue_one(&mdb_list, + err = br_switchdev_mdb_queue_one(&mdb_list, dev, action, SWITCHDEV_OBJ_ID_HOST_MDB, mp, br_dev); if (err) { - rcu_read_unlock(); + spin_unlock_bh(&br->multicast_lock); goto out_free_mdb; } } - for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL; + for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (p->key.port->dev != dev) continue; - err = br_switchdev_mdb_queue_one(&mdb_list, + err = br_switchdev_mdb_queue_one(&mdb_list, dev, action, SWITCHDEV_OBJ_ID_PORT_MDB, mp, dev); if (err) { - rcu_read_unlock(); + spin_unlock_bh(&br->multicast_lock); goto out_free_mdb; } } } - rcu_read_unlock(); - - if (adding) - action = SWITCHDEV_PORT_OBJ_ADD; - else - action = SWITCHDEV_PORT_OBJ_DEL; + spin_unlock_bh(&br->multicast_lock); list_for_each_entry(obj, &mdb_list, list) { err = br_switchdev_mdb_replay_one(nb, dev, @@ -780,6 +798,16 @@ static void nbp_switchdev_unsync_objs(struct net_bridge_port *p, br_switchdev_mdb_replay(br_dev, dev, ctx, false, blocking_nb, NULL); br_switchdev_vlan_replay(br_dev, ctx, false, blocking_nb, NULL); + + /* Make sure that the device leaving this bridge has seen all + * relevant events before it is disassociated. In the normal + * case, when the device is directly attached to the bridge, + * this is covered by del_nbp(). If the association was indirect + * however, e.g. via a team or bond, and the device is leaving + * that intermediate device, then the bridge port remains in + * place. + */ + switchdev_deferred_process(); } /* Let the bridge know that this port is offloaded, so that it can assign a diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index aa23479b20b2aef3da7e67d58ed4af4d9d9c616c..ed62c1026fe93e59f7cbf24609d67626f3ba66e4 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1111,6 +1111,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) struct ebt_table_info *newinfo; struct ebt_replace tmp; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1423,6 +1425,8 @@ static int update_counters(struct net *net, sockptr_t arg, unsigned int len) { struct ebt_replace hlp; + if (len < sizeof(hlp)) + return -EINVAL; if (copy_from_sockptr(&hlp, arg, sizeof(hlp))) return -EFAULT; @@ -2352,6 +2356,8 @@ static int compat_update_counters(struct net *net, sockptr_t arg, { struct compat_ebt_replace hlp; + if (len < sizeof(hlp)) + return -EINVAL; if (copy_from_sockptr(&hlp, arg, sizeof(hlp))) return -EFAULT; diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 06d94b2c6b5de28d1a88c9f0ccd97556cfeff8cc..e60c38670f220bb7824110b26e1c7bd3a2be9c25 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -291,6 +291,36 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb, return nf_conntrack_in(skb, &bridge_state); } +static unsigned int nf_ct_bridge_in(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + bool promisc = BR_INPUT_SKB_CB(skb)->promisc; + struct nf_conntrack *nfct = skb_nfct(skb); + struct nf_conn *ct; + + if (promisc) { + nf_reset_ct(skb); + return NF_ACCEPT; + } + + if (!nfct || skb->pkt_type == PACKET_HOST) + return NF_ACCEPT; + + /* nf_conntrack_confirm() cannot handle concurrent clones, + * this happens for broad/multicast frames with e.g. macvlan on top + * of the bridge device. + */ + ct = container_of(nfct, struct nf_conn, ct_general); + if (nf_ct_is_confirmed(ct) || nf_ct_is_template(ct)) + return NF_ACCEPT; + + /* let inet prerouting call conntrack again */ + skb->_nfct = 0; + nf_ct_put(ct); + + return NF_ACCEPT; +} + static void nf_ct_bridge_frag_save(struct sk_buff *skb, struct nf_bridge_frag_data *data) { @@ -415,6 +445,12 @@ static struct nf_hook_ops nf_ct_bridge_hook_ops[] __read_mostly = { .hooknum = NF_BR_PRE_ROUTING, .priority = NF_IP_PRI_CONNTRACK, }, + { + .hook = nf_ct_bridge_in, + .pf = NFPROTO_BRIDGE, + .hooknum = NF_BR_LOCAL_IN, + .priority = NF_IP_PRI_CONNTRACK_CONFIRM, + }, { .hook = nf_ct_bridge_post, .pf = NFPROTO_BRIDGE, diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h index 16af1a7f80f60e18b5526c973f66e98821786a78..31a93cae5111b50d54e10a061a9e235e81a1da1c 100644 --- a/net/can/j1939/j1939-priv.h +++ b/net/can/j1939/j1939-priv.h @@ -86,7 +86,7 @@ struct j1939_priv { unsigned int tp_max_packet_size; /* lock for j1939_socks list */ - spinlock_t j1939_socks_lock; + rwlock_t j1939_socks_lock; struct list_head j1939_socks; struct kref rx_kref; @@ -301,6 +301,7 @@ struct j1939_sock { int ifindex; struct j1939_addr addr; + spinlock_t filters_lock; struct j1939_filter *filters; int nfilters; pgn_t pgn_rx_filter; diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index ecff1c947d683b2f3e4eeff144f39a8f5ff5de1a..a6fb89fa62785121f9edc42308b052142fda5fdd 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -274,7 +274,7 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) return ERR_PTR(-ENOMEM); j1939_tp_init(priv); - spin_lock_init(&priv->j1939_socks_lock); + rwlock_init(&priv->j1939_socks_lock); INIT_LIST_HEAD(&priv->j1939_socks); mutex_lock(&j1939_netdev_lock); diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index b0be23559243c85a39a355a56c9da3f83b3eec87..58909b36561a625e7372889d04381c382475eb18 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -80,16 +80,16 @@ static void j1939_jsk_add(struct j1939_priv *priv, struct j1939_sock *jsk) jsk->state |= J1939_SOCK_BOUND; j1939_priv_get(priv); - spin_lock_bh(&priv->j1939_socks_lock); + write_lock_bh(&priv->j1939_socks_lock); list_add_tail(&jsk->list, &priv->j1939_socks); - spin_unlock_bh(&priv->j1939_socks_lock); + write_unlock_bh(&priv->j1939_socks_lock); } static void j1939_jsk_del(struct j1939_priv *priv, struct j1939_sock *jsk) { - spin_lock_bh(&priv->j1939_socks_lock); + write_lock_bh(&priv->j1939_socks_lock); list_del_init(&jsk->list); - spin_unlock_bh(&priv->j1939_socks_lock); + write_unlock_bh(&priv->j1939_socks_lock); j1939_priv_put(priv); jsk->state &= ~J1939_SOCK_BOUND; @@ -262,12 +262,17 @@ static bool j1939_sk_match_dst(struct j1939_sock *jsk, static bool j1939_sk_match_filter(struct j1939_sock *jsk, const struct j1939_sk_buff_cb *skcb) { - const struct j1939_filter *f = jsk->filters; - int nfilter = jsk->nfilters; + const struct j1939_filter *f; + int nfilter; + + spin_lock_bh(&jsk->filters_lock); + + f = jsk->filters; + nfilter = jsk->nfilters; if (!nfilter) /* receive all when no filters are assigned */ - return true; + goto filter_match_found; for (; nfilter; ++f, --nfilter) { if ((skcb->addr.pgn & f->pgn_mask) != f->pgn) @@ -276,9 +281,15 @@ static bool j1939_sk_match_filter(struct j1939_sock *jsk, continue; if ((skcb->addr.src_name & f->name_mask) != f->name) continue; - return true; + goto filter_match_found; } + + spin_unlock_bh(&jsk->filters_lock); return false; + +filter_match_found: + spin_unlock_bh(&jsk->filters_lock); + return true; } static bool j1939_sk_recv_match_one(struct j1939_sock *jsk, @@ -329,13 +340,13 @@ bool j1939_sk_recv_match(struct j1939_priv *priv, struct j1939_sk_buff_cb *skcb) struct j1939_sock *jsk; bool match = false; - spin_lock_bh(&priv->j1939_socks_lock); + read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { match = j1939_sk_recv_match_one(jsk, skcb); if (match) break; } - spin_unlock_bh(&priv->j1939_socks_lock); + read_unlock_bh(&priv->j1939_socks_lock); return match; } @@ -344,11 +355,11 @@ void j1939_sk_recv(struct j1939_priv *priv, struct sk_buff *skb) { struct j1939_sock *jsk; - spin_lock_bh(&priv->j1939_socks_lock); + read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { j1939_sk_recv_one(jsk, skb); } - spin_unlock_bh(&priv->j1939_socks_lock); + read_unlock_bh(&priv->j1939_socks_lock); } static void j1939_sk_sock_destruct(struct sock *sk) @@ -401,6 +412,7 @@ static int j1939_sk_init(struct sock *sk) atomic_set(&jsk->skb_pending, 0); spin_lock_init(&jsk->sk_session_queue_lock); INIT_LIST_HEAD(&jsk->sk_session_queue); + spin_lock_init(&jsk->filters_lock); /* j1939_sk_sock_destruct() depends on SOCK_RCU_FREE flag */ sock_set_flag(sk, SOCK_RCU_FREE); @@ -703,9 +715,11 @@ static int j1939_sk_setsockopt(struct socket *sock, int level, int optname, } lock_sock(&jsk->sk); + spin_lock_bh(&jsk->filters_lock); ofilters = jsk->filters; jsk->filters = filters; jsk->nfilters = count; + spin_unlock_bh(&jsk->filters_lock); release_sock(&jsk->sk); kfree(ofilters); return 0; @@ -1080,12 +1094,12 @@ void j1939_sk_errqueue(struct j1939_session *session, } /* spread RX notifications to all sockets subscribed to this session */ - spin_lock_bh(&priv->j1939_socks_lock); + read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { if (j1939_sk_recv_match_one(jsk, &session->skcb)) __j1939_sk_errqueue(session, &jsk->sk, type); } - spin_unlock_bh(&priv->j1939_socks_lock); + read_unlock_bh(&priv->j1939_socks_lock); }; void j1939_sk_send_loop_abort(struct sock *sk, int err) @@ -1273,7 +1287,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv) struct j1939_sock *jsk; int error_code = ENETDOWN; - spin_lock_bh(&priv->j1939_socks_lock); + read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { jsk->sk.sk_err = error_code; if (!sock_flag(&jsk->sk, SOCK_DEAD)) @@ -1281,7 +1295,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv) j1939_sk_queue_drop_all(priv, jsk, error_code); } - spin_unlock_bh(&priv->j1939_socks_lock); + read_unlock_bh(&priv->j1939_socks_lock); } static int j1939_sk_no_ioctlcmd(struct socket *sock, unsigned int cmd, diff --git a/net/core/dev.c b/net/core/dev.c index 1ba3662faf0aae6d40d0e57d70d211d4fa58cde2..65284eeec7de50a8e6033e5bb5d5649f995deb80 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2271,7 +2271,7 @@ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) rcu_read_lock(); again: list_for_each_entry_rcu(ptype, ptype_list, list) { - if (ptype->ignore_outgoing) + if (READ_ONCE(ptype->ignore_outgoing)) continue; /* Never send packets back to the socket @@ -6645,6 +6645,8 @@ static int napi_threaded_poll(void *data) void *have; while (!napi_thread_wait(napi)) { + unsigned long last_qs = jiffies; + for (;;) { bool repoll = false; @@ -6659,6 +6661,7 @@ static int napi_threaded_poll(void *data) if (!repoll) break; + rcu_softirq_qs_periodic(last_qs); cond_resched(); } } @@ -8861,7 +8864,7 @@ EXPORT_SYMBOL(dev_set_mac_address_user); int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name) { - size_t size = sizeof(sa->sa_data); + size_t size = sizeof(sa->sa_data_min); struct net_device *dev; int ret = 0; diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 7674bb9f3076c706ca65a5b455c3f892da058f3c..5cdbfbf9a7dcf7e260a56d836fdc6e2afbc44e35 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -342,7 +342,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, if (ifr->ifr_hwaddr.sa_family != dev->type) return -EINVAL; memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, - min(sizeof(ifr->ifr_hwaddr.sa_data), + min(sizeof(ifr->ifr_hwaddr.sa_data_min), (size_t)dev->addr_len)); call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return 0; diff --git a/net/core/filter.c b/net/core/filter.c index 3a6110ea4009f8df728df503598c04f5bd615d36..1d8b271ef8cc240775ba4313a7cf03bc142b4822 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4244,10 +4244,12 @@ static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; + u32 flags = ri->flags; struct bpf_map *map; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ + ri->flags = 0; ri->map_type = BPF_MAP_TYPE_UNSPEC; if (unlikely(!xdpf)) { @@ -4259,11 +4261,20 @@ static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: - map = READ_ONCE(ri->map); - if (unlikely(map)) { + if (unlikely(flags & BPF_F_BROADCAST)) { + map = READ_ONCE(ri->map); + + /* The map pointer is cleared when the map is being torn + * down by bpf_clear_redirect_map() + */ + if (unlikely(!map)) { + err = -ENOENT; + break; + } + WRITE_ONCE(ri->map, NULL); err = dev_map_enqueue_multi(xdpf, dev, map, - ri->flags & BPF_F_EXCLUDE_INGRESS); + flags & BPF_F_EXCLUDE_INGRESS); } else { err = dev_map_enqueue(fwd, xdpf, dev); } @@ -4334,9 +4345,9 @@ EXPORT_SYMBOL_GPL(xdp_do_redirect_frame); static int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog, - void *fwd, - enum bpf_map_type map_type, u32 map_id) + struct bpf_prog *xdp_prog, void *fwd, + enum bpf_map_type map_type, u32 map_id, + u32 flags) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); struct bpf_map *map; @@ -4346,11 +4357,20 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: - map = READ_ONCE(ri->map); - if (unlikely(map)) { + if (unlikely(flags & BPF_F_BROADCAST)) { + map = READ_ONCE(ri->map); + + /* The map pointer is cleared when the map is being torn + * down by bpf_clear_redirect_map() + */ + if (unlikely(!map)) { + err = -ENOENT; + break; + } + WRITE_ONCE(ri->map, NULL); err = dev_map_redirect_multi(dev, skb, xdp_prog, map, - ri->flags & BPF_F_EXCLUDE_INGRESS); + flags & BPF_F_EXCLUDE_INGRESS); } else { err = dev_map_generic_redirect(fwd, skb, xdp_prog); } @@ -4387,9 +4407,11 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; + u32 flags = ri->flags; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ + ri->flags = 0; ri->map_type = BPF_MAP_TYPE_UNSPEC; if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) { @@ -4409,7 +4431,7 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, return 0; } - return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, map_type, map_id); + return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, map_type, map_id, flags); err: _trace_xdp_redirect_err(dev, xdp_prog, ri->tgt_index, err); return err; @@ -5752,6 +5774,12 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; struct fib_table *tb; + if (flags & BPF_FIB_LOOKUP_TBID) { + tbid = params->tbid; + /* zero out for vlan output */ + params->tbid = 0; + } + tb = fib_get_table(net, tbid); if (unlikely(!tb)) return BPF_FIB_LKUP_RET_NOT_FWDED; @@ -5803,6 +5831,9 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, params->rt_metric = res.fi->fib_priority; params->ifindex = dev->ifindex; + if (flags & BPF_FIB_LOOKUP_SRC) + params->ipv4_src = fib_result_prefsrc(net, &res); + /* xdp and cls_bpf programs are run in RCU-bh so * rcu_read_lock_bh is not needed here */ @@ -5885,6 +5916,12 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; struct fib6_table *tb; + if (flags & BPF_FIB_LOOKUP_TBID) { + tbid = params->tbid; + /* zero out for vlan output */ + params->tbid = 0; + } + tb = ipv6_stub->fib6_get_table(net, tbid); if (unlikely(!tb)) return BPF_FIB_LKUP_RET_NOT_FWDED; @@ -5939,6 +5976,18 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, params->rt_metric = res.f6i->fib6_metric; params->ifindex = dev->ifindex; + if (flags & BPF_FIB_LOOKUP_SRC) { + if (res.f6i->fib6_prefsrc.plen) { + *src = res.f6i->fib6_prefsrc.addr; + } else { + err = ipv6_bpf_stub->ipv6_dev_get_saddr(net, dev, + &fl6.daddr, 0, + src); + if (err) + return BPF_FIB_LKUP_RET_NO_SRC_ADDR; + } + } + if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH) goto set_fwd_params; @@ -5957,7 +6006,8 @@ set_fwd_params: #endif #define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \ - BPF_FIB_LOOKUP_SKIP_NEIGH) + BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID | \ + BPF_FIB_LOOKUP_SRC) BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx, struct bpf_fib_lookup *, params, int, plen, u32, flags) diff --git a/net/core/gro.c b/net/core/gro.c index 352f966cb1dac0607d96c111d1553fb46c5d3c65..47118e97ecfdd58d9623b4abdf334bf6b6924192 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -252,8 +252,9 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) } merge: - /* sk owenrship - if any - completely transferred to the aggregated packet */ + /* sk ownership - if any - completely transferred to the aggregated packet */ skb->destructor = NULL; + skb->sk = NULL; delta_truesize = skb->truesize; if (offset > headlen) { unsigned int eat = offset - headlen; diff --git a/net/core/link_watch.c b/net/core/link_watch.c index aa6cb1f90966f5643aca27bf50cc75c86921580a..13513efcfbfe8a39bc9fd981e3e2b8d7d5497c37 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -53,7 +53,7 @@ static void rfc2863_policy(struct net_device *dev) { unsigned char operstate = default_operstate(dev); - if (operstate == dev->operstate) + if (operstate == READ_ONCE(dev->operstate)) return; write_lock(&dev_base_lock); @@ -73,7 +73,7 @@ static void rfc2863_policy(struct net_device *dev) break; } - dev->operstate = operstate; + WRITE_ONCE(dev->operstate, operstate); write_unlock(&dev_base_lock); } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 8409d41405dfe4a4448f3b7f070bdf9f856d74b8..fdf3308b033506ab4559d084c52ca3da2cfd0386 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -306,11 +306,9 @@ static ssize_t operstate_show(struct device *dev, const struct net_device *netdev = to_net_dev(dev); unsigned char operstate; - read_lock(&dev_base_lock); - operstate = netdev->operstate; + operstate = READ_ONCE(netdev->operstate); if (!netif_running(netdev)) operstate = IF_OPER_DOWN; - read_unlock(&dev_base_lock); if (operstate >= ARRAY_SIZE(operstates)) return -EINVAL; /* should not happen */ diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 4c1707d0eb9b06b28277411cb45b7c111ff45860..c33930a1716293df3678340fffebe3e25fe6391a 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -68,12 +68,15 @@ DEFINE_COOKIE(net_cookie); static struct net_generic *net_alloc_generic(void) { + unsigned int gen_ptrs = READ_ONCE(max_gen_ptrs); + unsigned int generic_size; struct net_generic *ng; - unsigned int generic_size = offsetof(struct net_generic, ptr[max_gen_ptrs]); + + generic_size = offsetof(struct net_generic, ptr[gen_ptrs]); ng = kzalloc(generic_size, GFP_KERNEL); if (ng) - ng->s.len = max_gen_ptrs; + ng->s.len = gen_ptrs; return ng; } @@ -1217,7 +1220,11 @@ static int register_pernet_operations(struct list_head *list, if (error < 0) return error; *ops->id = error; - max_gen_ptrs = max(max_gen_ptrs, *ops->id + 1); + /* This does not require READ_ONCE as writers already hold + * pernet_ops_rwsem. But WRITE_ONCE is needed to protect + * net_alloc_generic. + */ + WRITE_ONCE(max_gen_ptrs, max(max_gen_ptrs, *ops->id + 1)); } error = __register_pernet_operations(list, ops); if (error) { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 7cf1e42d7f93b8e6bd261999e533ecd2aa51f54d..1163226c025c1f908ea763239a8bef4a1556660d 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -876,9 +876,9 @@ static void set_operstate(struct net_device *dev, unsigned char transition) break; } - if (dev->operstate != operstate) { + if (READ_ONCE(dev->operstate) != operstate) { write_lock(&dev_base_lock); - dev->operstate = operstate; + WRITE_ONCE(dev->operstate, operstate); write_unlock(&dev_base_lock); netdev_state_change(dev); } @@ -2443,7 +2443,7 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) nla_for_each_nested(attr, tb[IFLA_VF_VLAN_LIST], rem) { if (nla_type(attr) != IFLA_VF_VLAN_INFO || - nla_len(attr) < NLA_HDRLEN) { + nla_len(attr) < sizeof(struct ifla_vf_vlan_info)) { return -EINVAL; } if (len >= MAX_VLAN_LIST_LEN) @@ -5026,10 +5026,9 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); struct ifinfomsg *ifm; struct net_device *dev; - struct nlattr *br_spec, *attr = NULL; + struct nlattr *br_spec, *attr, *br_flags_attr = NULL; int rem, err = -EOPNOTSUPP; u16 flags = 0; - bool have_flags = false; if (nlmsg_len(nlh) < sizeof(*ifm)) return -EINVAL; @@ -5047,11 +5046,11 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (br_spec) { nla_for_each_nested(attr, br_spec, rem) { - if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !have_flags) { + if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !br_flags_attr) { if (nla_len(attr) < sizeof(flags)) return -EINVAL; - have_flags = true; + br_flags_attr = attr; flags = nla_get_u16(attr); } @@ -5095,8 +5094,8 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, } } - if (have_flags) - memcpy(nla_data(attr), &flags, sizeof(flags)); + if (br_flags_attr) + memcpy(nla_data(br_flags_attr), &flags, sizeof(flags)); out: return err; } diff --git a/net/core/scm.c b/net/core/scm.c index e762a4b8a1d220e05afd4de364cc421fda776b5d..a877c4ef4c256f742d10e00b75be8a7cc6336d50 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -105,7 +105,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) if (fd < 0 || !(file = fget_raw(fd))) return -EBADF; /* don't allow io_uring files */ - if (io_uring_get_socket(file)) { + if (io_is_uring_fops(file)) { fput(file); return -EINVAL; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 8a819d0a7bfb0e96253fbd1f511e88c958920c44..4d46788cd493a3e4bf688df8346596431a0d1165 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1720,11 +1720,17 @@ static inline int skb_alloc_rx_flag(const struct sk_buff *skb) struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) { - int headerlen = skb_headroom(skb); - unsigned int size = skb_end_offset(skb) + skb->data_len; - struct sk_buff *n = __alloc_skb(size, gfp_mask, - skb_alloc_rx_flag(skb), NUMA_NO_NODE); + struct sk_buff *n; + unsigned int size; + int headerlen; + + if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) + return NULL; + headerlen = skb_headroom(skb); + size = skb_end_offset(skb) + skb->data_len; + n = __alloc_skb(size, gfp_mask, + skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) return NULL; @@ -2037,12 +2043,17 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, /* * Allocate the copy buffer */ - struct sk_buff *n = __alloc_skb(newheadroom + skb->len + newtailroom, - gfp_mask, skb_alloc_rx_flag(skb), - NUMA_NO_NODE); - int oldheadroom = skb_headroom(skb); int head_copy_len, head_copy_off; + struct sk_buff *n; + int oldheadroom; + + if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) + return NULL; + oldheadroom = skb_headroom(skb); + n = __alloc_skb(newheadroom + skb->len + newtailroom, + gfp_mask, skb_alloc_rx_flag(skb), + NUMA_NO_NODE); if (!n) return NULL; @@ -4213,8 +4224,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, /* GSO partial only requires that we trim off any excess that * doesn't fit into an MSS sized block, so take care of that * now. + * Cap len to not accidentally hit GSO_BY_FRAGS. */ - partial_segs = len / mss; + partial_segs = min(len, GSO_BY_FRAGS - 1U) / mss; if (partial_segs > 1) mss *= partial_segs; else @@ -6499,6 +6511,14 @@ static struct skb_ext *skb_ext_maybe_cow(struct skb_ext *old, for (i = 0; i < sp->len; i++) xfrm_state_hold(sp->xvec[i]); } +#endif +#ifdef CONFIG_MCTP_FLOWS + if (old_active & (1 << SKB_EXT_MCTP)) { + struct mctp_flow *flow = skb_ext_get_ptr(old, SKB_EXT_MCTP); + + if (flow->key) + refcount_inc(&flow->key->refs); + } #endif __skb_ext_put(old); return new; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 3818035ea00219bd9917a67b38c6e2ff1cf82d61..8b0459a6b629f2cd83bb99b6f6385b11b64421b6 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1218,7 +1218,7 @@ static void sk_psock_verdict_data_ready(struct sock *sk) rcu_read_lock(); psock = sk_psock(sk); if (psock) - psock->saved_data_ready(sk); + sk_psock_data_ready(sk, psock); rcu_read_unlock(); } } diff --git a/net/core/sock.c b/net/core/sock.c index c8803b95ea0da3f8cc615e9e35601bad3229f884..48199e6e8f16191ca15a4561a66c832fce8d25f6 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -279,6 +279,7 @@ __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; EXPORT_SYMBOL(sysctl_rmem_max); __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; +int sysctl_mem_pcpu_rsv __read_mostly = SK_MEMORY_PCPU_RESERVE; /* Maximal space eaten by iovec or ancillary data plus some space */ int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); @@ -481,7 +482,7 @@ int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) unsigned long flags; struct sk_buff_head *list = &sk->sk_receive_queue; - if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) { + if (atomic_read(&sk->sk_rmem_alloc) >= READ_ONCE(sk->sk_rcvbuf)) { atomic_inc(&sk->sk_drops); trace_sock_rcvqueue_full(sk, skb); return -ENOMEM; @@ -551,7 +552,7 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, skb->dev = NULL; - if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) { + if (sk_rcvqueues_full(sk, READ_ONCE(sk->sk_rcvbuf))) { atomic_inc(&sk->sk_drops); goto discard_and_relse; } diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index f7cf74cdd3db1f7f0783db88fc28fd876fbac4b6..e6ea6764d10abe9d78c9b3a7df40fbc33b59c7a0 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -190,7 +190,7 @@ int sock_diag_register(const struct sock_diag_handler *hndl) if (sock_diag_handlers[hndl->family]) err = -EBUSY; else - sock_diag_handlers[hndl->family] = hndl; + WRITE_ONCE(sock_diag_handlers[hndl->family], hndl); mutex_unlock(&sock_diag_table_mutex); return err; @@ -206,7 +206,7 @@ void sock_diag_unregister(const struct sock_diag_handler *hnld) mutex_lock(&sock_diag_table_mutex); BUG_ON(sock_diag_handlers[family] != hnld); - sock_diag_handlers[family] = NULL; + WRITE_ONCE(sock_diag_handlers[family], NULL); mutex_unlock(&sock_diag_table_mutex); } EXPORT_SYMBOL_GPL(sock_diag_unregister); @@ -224,7 +224,7 @@ static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh) return -EINVAL; req->sdiag_family = array_index_nospec(req->sdiag_family, AF_MAX); - if (sock_diag_handlers[req->sdiag_family] == NULL) + if (READ_ONCE(sock_diag_handlers[req->sdiag_family]) == NULL) sock_load_diag_module(req->sdiag_family, 0); mutex_lock(&sock_diag_table_mutex); @@ -283,12 +283,12 @@ static int sock_diag_bind(struct net *net, int group) switch (group) { case SKNLGRP_INET_TCP_DESTROY: case SKNLGRP_INET_UDP_DESTROY: - if (!sock_diag_handlers[AF_INET]) + if (!READ_ONCE(sock_diag_handlers[AF_INET])) sock_load_diag_module(AF_INET, 0); break; case SKNLGRP_INET6_TCP_DESTROY: case SKNLGRP_INET6_UDP_DESTROY: - if (!sock_diag_handlers[AF_INET6]) + if (!READ_ONCE(sock_diag_handlers[AF_INET6])) sock_load_diag_module(AF_INET6, 0); break; } diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 91140bc0541f3cd9783c16be4801aaa70dc538db..aa7ff6a46429138e78e6af7846748cb773ca3696 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -413,6 +413,9 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock *sk; int err = 0; + if (irqs_disabled()) + return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ + raw_spin_lock_bh(&stab->lock); sk = *psk; if (!sk_test || sk_test == sk) @@ -926,6 +929,9 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key) struct bpf_shtab_elem *elem; int ret = -ENOENT; + if (irqs_disabled()) + return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ + hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 5b1ce656baa1d4701a1b62724edc437d847d8f5f..d281d5343ff4aa8ac99be08250c3a0270ae92b6b 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -29,6 +29,7 @@ static int int_3600 = 3600; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; static int max_skb_frags = MAX_SKB_FRAGS; +static int min_mem_pcpu_rsv = SK_MEMORY_PCPU_RESERVE; static int net_msg_warn; /* Unused, but still a sysctl */ @@ -348,6 +349,14 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec_minmax, .extra1 = &min_rcvbuf, }, + { + .procname = "mem_pcpu_rsv", + .data = &sysctl_mem_pcpu_rsv, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &min_mem_pcpu_rsv, + }, { .procname = "dev_weight", .data = &weight_p, diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 5417f7b1187cbf41498043798635e47614a437bb..98f86487917554be14a0a8feaea04e8bb1369d19 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -425,6 +425,24 @@ static int dsa_tree_setup_default_cpu(struct dsa_switch_tree *dst) return 0; } +static struct dsa_port * +dsa_switch_preferred_default_local_cpu_port(struct dsa_switch *ds) +{ + struct dsa_port *cpu_dp; + + if (!ds->ops->preferred_default_local_cpu_port) + return NULL; + + cpu_dp = ds->ops->preferred_default_local_cpu_port(ds); + if (!cpu_dp) + return NULL; + + if (WARN_ON(!dsa_port_is_cpu(cpu_dp) || cpu_dp->ds != ds)) + return NULL; + + return cpu_dp; +} + /* Perform initial assignment of CPU ports to user ports and DSA links in the * fabric, giving preference to CPU ports local to each switch. Default to * using the first CPU port in the switch tree if the port does not have a CPU @@ -432,12 +450,16 @@ static int dsa_tree_setup_default_cpu(struct dsa_switch_tree *dst) */ static int dsa_tree_setup_cpu_ports(struct dsa_switch_tree *dst) { - struct dsa_port *cpu_dp, *dp; + struct dsa_port *preferred_cpu_dp, *cpu_dp, *dp; list_for_each_entry(cpu_dp, &dst->ports, list) { if (!dsa_port_is_cpu(cpu_dp)) continue; + preferred_cpu_dp = dsa_switch_preferred_default_local_cpu_port(cpu_dp->ds); + if (preferred_cpu_dp && preferred_cpu_dp != cpu_dp) + continue; + /* Prefer a local CPU port */ dsa_switch_for_each_port(dp, cpu_dp->ds) { /* Prefer the first local CPU port found */ diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index e02daa74e8334508d17611b323699d5c9fc2ae59..5ba7b460cbf7689abfa6c0aa0f0967e159f73001 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -164,17 +164,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) eth = (struct ethhdr *)skb->data; skb_pull_inline(skb, ETH_HLEN); - if (unlikely(!ether_addr_equal_64bits(eth->h_dest, - dev->dev_addr))) { - if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) { - if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) - skb->pkt_type = PACKET_BROADCAST; - else - skb->pkt_type = PACKET_MULTICAST; - } else { - skb->pkt_type = PACKET_OTHERHOST; - } - } + eth_skb_pkt_type(skb, dev); /* * Some variants of DSA tagging don't have an ethertype field diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index b1e86a7265b32c9e54ed30556588cc7a7f0b2af4..ad75724b69adf712c7b57816cbffc301f3c1e91f 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -31,8 +31,8 @@ static bool is_slave_up(struct net_device *dev) static void __hsr_set_operstate(struct net_device *dev, int transition) { write_lock(&dev_base_lock); - if (dev->operstate != transition) { - dev->operstate = transition; + if (READ_ONCE(dev->operstate) != transition) { + WRITE_ONCE(dev->operstate, transition); write_unlock(&dev_base_lock); netdev_state_change(dev); } else { @@ -71,39 +71,36 @@ static bool hsr_check_carrier(struct hsr_port *master) return false; } -static void hsr_check_announce(struct net_device *hsr_dev, - unsigned char old_operstate) +static void hsr_check_announce(struct net_device *hsr_dev) { struct hsr_priv *hsr; hsr = netdev_priv(hsr_dev); - - if (hsr_dev->operstate == IF_OPER_UP && old_operstate != IF_OPER_UP) { - /* Went up */ - hsr->announce_count = 0; - mod_timer(&hsr->announce_timer, - jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL)); + if (netif_running(hsr_dev) && netif_oper_up(hsr_dev)) { + /* Enable announce timer and start sending supervisory frames */ + if (!timer_pending(&hsr->announce_timer)) { + hsr->announce_count = 0; + mod_timer(&hsr->announce_timer, jiffies + + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL)); + } + } else { + /* Deactivate the announce timer */ + timer_delete(&hsr->announce_timer); } - - if (hsr_dev->operstate != IF_OPER_UP && old_operstate == IF_OPER_UP) - /* Went down */ - del_timer(&hsr->announce_timer); } void hsr_check_carrier_and_operstate(struct hsr_priv *hsr) { struct hsr_port *master; - unsigned char old_operstate; bool has_carrier; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); /* netif_stacked_transfer_operstate() cannot be used here since * it doesn't set IF_OPER_LOWERLAYERDOWN (?) */ - old_operstate = master->dev->operstate; has_carrier = hsr_check_carrier(master); hsr_set_operstate(master, has_carrier); - hsr_check_announce(master->dev, old_operstate); + hsr_check_announce(master->dev); } int hsr_get_max_mtu(struct hsr_priv *hsr) @@ -291,7 +288,7 @@ static void send_hsr_supervision_frame(struct hsr_port *master, skb = hsr_init_skb(master); if (!skb) { - WARN_ONCE(1, "HSR: Could not send supervision frame\n"); + netdev_warn_once(master->dev, "HSR: Could not send supervision frame\n"); return; } @@ -338,7 +335,7 @@ static void send_prp_supervision_frame(struct hsr_port *master, skb = hsr_init_skb(master); if (!skb) { - WARN_ONCE(1, "PRP: Could not send supervision frame\n"); + netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n"); return; } diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 80cdc6f6b34c97601961179c4839dc68c0a6d2e1..0323ab5023c6905dbc965cedc6099db6fddb612e 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -83,7 +83,7 @@ static bool is_supervision_frame(struct hsr_priv *hsr, struct sk_buff *skb) return false; /* Get next tlv */ - total_length += sizeof(struct hsr_sup_tlv) + hsr_sup_tag->tlv.HSR_TLV_length; + total_length += hsr_sup_tag->tlv.HSR_TLV_length; if (!pskb_may_pull(skb, total_length)) return false; skb_pull(skb, total_length); diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 0b0199878095266787acc0cac040ebbdab2a95ba..e44a039e36afe876d6448b7919fb53adf3e3fc2d 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -235,6 +235,10 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db, */ if (ethhdr->h_proto == htons(ETH_P_PRP) || ethhdr->h_proto == htons(ETH_P_HSR)) { + /* Check if skb contains hsr_ethhdr */ + if (skb->mac_len < sizeof(struct hsr_ethhdr)) + return NULL; + /* Use the existing sequence_nr from the tag as starting point * for filtering duplicate frames. */ diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index b099c315015096f3637f4770ee9a6553baac2637..257b50124cee5e4d8b4f69b4c1d1287f13270d7f 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -148,14 +148,21 @@ static struct notifier_block hsr_nb = { static int __init hsr_init(void) { - int res; + int err; BUILD_BUG_ON(sizeof(struct hsr_tag) != HSR_HLEN); - register_netdevice_notifier(&hsr_nb); - res = hsr_netlink_init(); + err = register_netdevice_notifier(&hsr_nb); + if (err) + return err; + + err = hsr_netlink_init(); + if (err) { + unregister_netdevice_notifier(&hsr_nb); + return err; + } - return res; + return 0; } static void __exit hsr_exit(void) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 2f646335d2183f3bd7176a61148ab8d2441311aa..9408dc3bb42d3652ca60cc59d6c5d215921ec862 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1637,10 +1637,12 @@ EXPORT_SYMBOL(inet_current_timestamp); int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { - if (sk->sk_family == AF_INET) + unsigned int family = READ_ONCE(sk->sk_family); + + if (family == AF_INET) return ip_recv_error(sk, msg, len, addr_len); #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) + if (family == AF_INET6) return pingv6_ops.ipv6_recv_error(sk, msg, len, addr_len); #endif return -EINVAL; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 9456f5bb35e5d9e97d6c05be21561b435e2b704a..ccff96820a703e070f95315c5c207b0b70fa9b1b 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1125,7 +1125,8 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev) if (neigh) { if (!(READ_ONCE(neigh->nud_state) & NUD_NOARP)) { read_lock_bh(&neigh->lock); - memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len); + memcpy(r->arp_ha.sa_data, neigh->ha, + min(dev->addr_len, (unsigned char)sizeof(r->arp_ha.sa_data_min))); r->arp_flags = arp_state_to_flags(neigh); read_unlock_bh(&neigh->lock); r->arp_ha.sa_family = dev->type; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 35d6e74be8406ad471abf74019478eec6bf6b61a..bb0d1252cad864ff67b945c8f9b7bc23af53eac2 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1804,6 +1804,21 @@ done: return err; } +/* Combine dev_addr_genid and dev_base_seq to detect changes. + */ +static u32 inet_base_seq(const struct net *net) +{ + u32 res = atomic_read(&net->ipv4.dev_addr_genid) + + net->dev_base_seq; + + /* Must not return 0 (see nl_dump_check_consistent()). + * Chose a value far away from 0. + */ + if (!res) + res = 0x80000000; + return res; +} + static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; @@ -1855,8 +1870,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) idx = 0; head = &tgt_net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&tgt_net->ipv4.dev_addr_genid) ^ - tgt_net->dev_base_seq; + cb->seq = inet_base_seq(tgt_net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@ -2257,8 +2271,7 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb, idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^ - net->dev_base_seq; + cb->seq = inet_base_seq(net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 2b09ef70752f92ed5ca36460ed3ca424921881f0..31051b327e53c870eb91755662653a9c7ffc0b32 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -92,6 +92,7 @@ #include #include #include +#include /* * Build xmit assembly blocks @@ -1029,6 +1030,8 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr) struct icmp_ext_hdr *ext_hdr, _ext_hdr; struct icmp_ext_echo_iio *iio, _iio; struct net *net = dev_net(skb->dev); + struct inet6_dev *in6_dev; + struct in_device *in_dev; struct net_device *dev; char buff[IFNAMSIZ]; u16 ident_len; @@ -1112,10 +1115,15 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr) /* Fill bits in reply message */ if (dev->flags & IFF_UP) status |= ICMP_EXT_ECHOREPLY_ACTIVE; - if (__in_dev_get_rcu(dev) && __in_dev_get_rcu(dev)->ifa_list) + + in_dev = __in_dev_get_rcu(dev); + if (in_dev && rcu_access_pointer(in_dev->ifa_list)) status |= ICMP_EXT_ECHOREPLY_IPV4; - if (!list_empty(&rcu_dereference(dev->ip6_ptr)->addr_list)) + + in6_dev = __in6_dev_get(dev); + if (in6_dev && !list_empty(&in6_dev->addr_list)) status |= ICMP_EXT_ECHOREPLY_IPV6; + dev_put(dev); icmphdr->un.echo.sequence |= htons(status); return true; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 79fa19a36bbd1388978d5241cfca3595a8e461e5..8407098a59391c66d6aa1aafd556340a12233d10 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -289,6 +289,7 @@ static bool inet_bhash2_addr_any_conflict(const struct sock *sk, int port, int l struct sock_reuseport *reuseport_cb; struct inet_bind_hashbucket *head2; struct inet_bind2_bucket *tb2; + bool conflict = false; bool reuseport_cb_ok; rcu_read_lock(); @@ -301,18 +302,20 @@ static bool inet_bhash2_addr_any_conflict(const struct sock *sk, int port, int l spin_lock(&head2->lock); - inet_bind_bucket_for_each(tb2, &head2->chain) - if (inet_bind2_bucket_match_addr_any(tb2, net, port, l3mdev, sk)) - break; + inet_bind_bucket_for_each(tb2, &head2->chain) { + if (!inet_bind2_bucket_match_addr_any(tb2, net, port, l3mdev, sk)) + continue; - if (tb2 && inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, - reuseport_ok)) { - spin_unlock(&head2->lock); - return true; + if (!inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, reuseport_ok)) + continue; + + conflict = true; + break; } spin_unlock(&head2->lock); - return false; + + return conflict; } /* @@ -771,6 +774,20 @@ void inet_csk_clear_xmit_timers(struct sock *sk) } EXPORT_SYMBOL(inet_csk_clear_xmit_timers); +void inet_csk_clear_xmit_timers_sync(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + /* ongoing timer handlers need to acquire socket lock. */ + sock_not_owned_by_me(sk); + + icsk->icsk_pending = icsk->icsk_ack.pending = 0; + + sk_stop_timer_sync(sk, &icsk->icsk_retransmit_timer); + sk_stop_timer_sync(sk, &icsk->icsk_delack_timer); + sk_stop_timer_sync(sk, &sk->sk_timer); +} + void inet_csk_delete_keepalive_timer(struct sock *sk) { sk_stop_timer(sk, &sk->sk_timer); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index f7426926a10413b42ec3b99d97f59445b6d1becc..8f690a6e61baabf50b101d2eea2a20cc23585892 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -57,7 +57,7 @@ static const struct inet_diag_handler *inet_diag_lock_handler(int proto) return ERR_PTR(-ENOENT); } - if (!inet_diag_table[proto]) + if (!READ_ONCE(inet_diag_table[proto])) sock_load_diag_module(AF_INET, proto); mutex_lock(&inet_diag_table_mutex); @@ -1419,7 +1419,7 @@ int inet_diag_register(const struct inet_diag_handler *h) mutex_lock(&inet_diag_table_mutex); err = -EEXIST; if (!inet_diag_table[type]) { - inet_diag_table[type] = h; + WRITE_ONCE(inet_diag_table[type], h); err = 0; } mutex_unlock(&inet_diag_table_mutex); @@ -1436,7 +1436,7 @@ void inet_diag_unregister(const struct inet_diag_handler *h) return; mutex_lock(&inet_diag_table_mutex); - inet_diag_table[type] = NULL; + WRITE_ONCE(inet_diag_table[type], NULL); mutex_unlock(&inet_diag_table_mutex); } EXPORT_SYMBOL_GPL(inet_diag_unregister); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index c9f9ac5013a717ddbc403c7317aaa228b09f6a0c..834cdc57755f7f0cee83b495981427be904308cb 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -24,6 +24,8 @@ #include #include +#include "../core/sock_destructor.h" + /* Use skb->cb to track consecutive/adjacent fragments coming at * the end of the queue. Nodes in the rb-tree queue will * contain "runs" of one or more adjacent fragments. @@ -39,6 +41,7 @@ struct ipfrag_skb_cb { }; struct sk_buff *next_frag; int frag_run_len; + int ip_defrag_offset; }; #define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) @@ -390,12 +393,12 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, */ if (!last) fragrun_create(q, skb); /* First fragment. */ - else if (last->ip_defrag_offset + last->len < end) { + else if (FRAG_CB(last)->ip_defrag_offset + last->len < end) { /* This is the common case: skb goes to the end. */ /* Detect and discard overlaps. */ - if (offset < last->ip_defrag_offset + last->len) + if (offset < FRAG_CB(last)->ip_defrag_offset + last->len) return IPFRAG_OVERLAP; - if (offset == last->ip_defrag_offset + last->len) + if (offset == FRAG_CB(last)->ip_defrag_offset + last->len) fragrun_append_to_last(q, skb); else fragrun_create(q, skb); @@ -412,13 +415,13 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, parent = *rbn; curr = rb_to_skb(parent); - curr_run_end = curr->ip_defrag_offset + + curr_run_end = FRAG_CB(curr)->ip_defrag_offset + FRAG_CB(curr)->frag_run_len; - if (end <= curr->ip_defrag_offset) + if (end <= FRAG_CB(curr)->ip_defrag_offset) rbn = &parent->rb_left; else if (offset >= curr_run_end) rbn = &parent->rb_right; - else if (offset >= curr->ip_defrag_offset && + else if (offset >= FRAG_CB(curr)->ip_defrag_offset && end <= curr_run_end) return IPFRAG_DUP; else @@ -432,7 +435,7 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, rb_insert_color(&skb->rbnode, &q->rb_fragments); } - skb->ip_defrag_offset = offset; + FRAG_CB(skb)->ip_defrag_offset = offset; return IPFRAG_OK; } @@ -442,13 +445,28 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, struct sk_buff *parent) { struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments); - struct sk_buff **nextp; + void (*destructor)(struct sk_buff *); + unsigned int orig_truesize = 0; + struct sk_buff **nextp = NULL; + struct sock *sk = skb->sk; int delta; + if (sk && is_skb_wmem(skb)) { + /* TX: skb->sk might have been passed as argument to + * dst->output and must remain valid until tx completes. + * + * Move sk to reassembled skb and fix up wmem accounting. + */ + orig_truesize = skb->truesize; + destructor = skb->destructor; + } + if (head != skb) { fp = skb_clone(skb, GFP_ATOMIC); - if (!fp) - return NULL; + if (!fp) { + head = skb; + goto out_restore_sk; + } FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; if (RB_EMPTY_NODE(&skb->rbnode)) FRAG_CB(parent)->next_frag = fp; @@ -457,6 +475,12 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, &q->rb_fragments); if (q->fragments_tail == skb) q->fragments_tail = fp; + + if (orig_truesize) { + /* prevent skb_morph from releasing sk */ + skb->sk = NULL; + skb->destructor = NULL; + } skb_morph(skb, head); FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; rb_replace_node(&head->rbnode, &skb->rbnode, @@ -464,13 +488,13 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, consume_skb(head); head = skb; } - WARN_ON(head->ip_defrag_offset != 0); + WARN_ON(FRAG_CB(head)->ip_defrag_offset != 0); delta = -head->truesize; /* Head of list must not be cloned. */ if (skb_unclone(head, GFP_ATOMIC)) - return NULL; + goto out_restore_sk; delta += head->truesize; if (delta) @@ -486,7 +510,7 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, clone = alloc_skb(0, GFP_ATOMIC); if (!clone) - return NULL; + goto out_restore_sk; skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; skb_frag_list_init(head); for (i = 0; i < skb_shinfo(head)->nr_frags; i++) @@ -503,6 +527,21 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, nextp = &skb_shinfo(head)->frag_list; } +out_restore_sk: + if (orig_truesize) { + int ts_delta = head->truesize - orig_truesize; + + /* if this reassembled skb is fragmented later, + * fraglist skbs will get skb->sk assigned from head->sk, + * and each frag skb will be released via sock_wfree. + * + * Update sk_wmem_alloc. + */ + head->sk = sk; + head->destructor = destructor; + refcount_add(ts_delta, &sk->sk_wmem_alloc); + } + return nextp; } EXPORT_SYMBOL(inet_frag_reasm_prepare); @@ -510,6 +549,8 @@ EXPORT_SYMBOL(inet_frag_reasm_prepare); void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, void *reasm_data, bool try_coalesce) { + struct sock *sk = is_skb_wmem(head) ? head->sk : NULL; + const unsigned int head_truesize = head->truesize; struct sk_buff **nextp = reasm_data; struct rb_node *rbn; struct sk_buff *fp; @@ -573,6 +614,9 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, head->prev = NULL; head->tstamp = q->stamp; head->mono_delivery_time = q->mono_delivery_time; + + if (sk) + refcount_add(sum_truesize - head_truesize, &sk->sk_wmem_alloc); } EXPORT_SYMBOL(inet_frag_reasm_finish); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index f2ed2aed08ab3de4885ca11f706dbc21db858686..0ad25e6783ac7cd09bb45debf815f0aff3b2ca5f 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -1111,10 +1111,33 @@ ok: return 0; error: + if (sk_hashed(sk)) { + spinlock_t *lock = inet_ehash_lockp(hinfo, sk->sk_hash); + + sock_prot_inuse_add(net, sk->sk_prot, -1); + + spin_lock(lock); + __sk_nulls_del_node_init_rcu(sk); + spin_unlock(lock); + + sk->sk_hash = 0; + inet_sk(sk)->inet_sport = 0; + inet_sk(sk)->inet_num = 0; + + if (tw) + inet_twsk_bind_unhash(tw, hinfo); + } + spin_unlock(&head2->lock); if (tb_created) inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb); - spin_unlock_bh(&head->lock); + spin_unlock(&head->lock); + + if (tw) + inet_twsk_deschedule_put(tw); + + local_bh_enable(); + return -ENOMEM; } diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 1d77d992e6e77f7d96bd061be6dbb802c2566b3f..340a8f0c298003e28217ffb85ce5e32741d823af 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -281,12 +281,12 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) } EXPORT_SYMBOL_GPL(__inet_twsk_schedule); +/* Remove all non full sockets (TIME_WAIT and NEW_SYN_RECV) for dead netns */ void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family) { - struct inet_timewait_sock *tw; - struct sock *sk; struct hlist_nulls_node *node; unsigned int slot; + struct sock *sk; for (slot = 0; slot <= hashinfo->ehash_mask; slot++) { struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; @@ -295,38 +295,35 @@ restart_rcu: rcu_read_lock(); restart: sk_nulls_for_each_rcu(sk, node, &head->chain) { - if (sk->sk_state != TCP_TIME_WAIT) { - /* A kernel listener socket might not hold refcnt for net, - * so reqsk_timer_handler() could be fired after net is - * freed. Userspace listener and reqsk never exist here. - */ - if (unlikely(sk->sk_state == TCP_NEW_SYN_RECV && - hashinfo->pernet)) { - struct request_sock *req = inet_reqsk(sk); - - inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req); - } + int state = inet_sk_state_load(sk); + if ((1 << state) & ~(TCPF_TIME_WAIT | + TCPF_NEW_SYN_RECV)) continue; - } - tw = inet_twsk(sk); - if ((tw->tw_family != family) || - refcount_read(&twsk_net(tw)->ns.count)) + if (sk->sk_family != family || + refcount_read(&sock_net(sk)->ns.count)) continue; - if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt))) + if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) continue; - if (unlikely((tw->tw_family != family) || - refcount_read(&twsk_net(tw)->ns.count))) { - inet_twsk_put(tw); + if (unlikely(sk->sk_family != family || + refcount_read(&sock_net(sk)->ns.count))) { + sock_gen_put(sk); goto restart; } rcu_read_unlock(); local_bh_disable(); - inet_twsk_deschedule_put(tw); + if (state == TCP_TIME_WAIT) { + inet_twsk_deschedule_put(inet_twsk(sk)); + } else { + struct request_sock *req = inet_reqsk(sk); + + inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, + req); + } local_bh_enable(); goto restart_rcu; } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index fb153569889ecc8541640674880ff03e8c7bf24f..6c309c1ec3b0face6cd25b6f71d77131c225f8e7 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -378,6 +378,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) } skb_dst_drop(skb); + skb_orphan(skb); return -EINPROGRESS; insert_error: @@ -480,7 +481,6 @@ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user) struct ipq *qp; __IP_INC_STATS(net, IPSTATS_MIB_REASMREQDS); - skb_orphan(skb); /* Lookup (or create) queue header */ qp = ip_find(net, ip_hdr(skb), user, vif); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index d67d026d7f97502625e42d32474041be95874b18..0267fa05374aa3444ec0bdb641e4c1280e512c67 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -280,8 +280,13 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, tpi->flags | TUNNEL_NO_KEY, iph->saddr, iph->daddr, 0); } else { + if (unlikely(!pskb_may_pull(skb, + gre_hdr_len + sizeof(*ershdr)))) + return PACKET_REJECT; + ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); ver = ershdr->ver; + iph = ip_hdr(skb); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags | TUNNEL_KEY, iph->saddr, iph->daddr, tpi->key); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 24961b304dad093e3e04a3f9a598aa90f13c8000..3445e576b05bc2096c1ba2e4490c8ba1584aa791 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -364,7 +364,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, bool log_ecn_error) { const struct iphdr *iph = ip_hdr(skb); - int err; + int nh, err; #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { @@ -390,8 +390,21 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, tunnel->i_seqno = ntohl(tpi->seq) + 1; } + /* Save offset of outer header relative to skb->head, + * because we are going to reset the network header to the inner header + * and might change skb->head. + */ + nh = skb_network_header(skb) - skb->head; + skb_set_network_header(skb, (tunnel->dev->type == ARPHRD_ETHER) ? ETH_HLEN : 0); + if (!pskb_inet_may_pull(skb)) { + DEV_STATS_INC(tunnel->dev, rx_length_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); + goto drop; + } + iph = (struct iphdr *)(skb->head + nh); + err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) @@ -540,6 +553,20 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, return 0; } +static void ip_tunnel_adj_headroom(struct net_device *dev, unsigned int headroom) +{ + /* we must cap headroom to some upperlimit, else pskb_expand_head + * will overflow header offsets in skb_headers_offset_update(). + */ + static const unsigned int max_allowed = 512; + + if (headroom > max_allowed) + headroom = max_allowed; + + if (headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, headroom); +} + void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto, int tunnel_hlen) { @@ -614,13 +641,13 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; - if (headroom > READ_ONCE(dev->needed_headroom)) - WRITE_ONCE(dev->needed_headroom, headroom); - - if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { + if (skb_cow_head(skb, headroom)) { ip_rt_put(rt); goto tx_dropped; } + + ip_tunnel_adj_headroom(dev, headroom); + iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); return; @@ -800,16 +827,16 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len + ip_encap_hlen(&tunnel->encap); - if (max_headroom > READ_ONCE(dev->needed_headroom)) - WRITE_ONCE(dev->needed_headroom, max_headroom); - if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { + if (skb_cow_head(skb, max_headroom)) { ip_rt_put(rt); dev->stats.tx_dropped++; kfree_skb(skb); return; } + ip_tunnel_adj_headroom(dev, max_headroom); + iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); return; diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 586b1b3e35b805d46158531ae8e7b49122abbaa7..80ccd6661aa32f2b60a720a18deec26e9e2cc18d 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -332,7 +332,7 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu) }; skb_reset_network_header(skb); - csum = csum_partial(icmp6h, len, 0); + csum = skb_checksum(skb, skb_transport_offset(skb), len, 0); icmp6h->icmp6_cksum = csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr, len, IPPROTO_ICMPV6, csum); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index d5421c38c2aae41a7a6609c25eb000f647689c6c..3ed9ed2bffd295e3fe8b7300da7f5990d7848a4c 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1581,9 +1581,11 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval, if (copy_from_sockptr(&olr, optlen, sizeof(int))) return -EFAULT; - olr = min_t(unsigned int, olr, sizeof(int)); if (olr < 0) return -EINVAL; + + olr = min_t(unsigned int, olr, sizeof(int)); + if (copy_to_sockptr(optlen, &olr, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &val, olr)) diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 2407066b0fec1121d71561ecbad6f4f87ecdebbc..14365b20f1c5c09964dd7024060116737f22cb63 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -956,6 +956,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct arpt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -964,6 +966,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; @@ -1254,6 +1258,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct arpt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1262,6 +1268,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index da5998011ab9bb520da36a243fd692da50f2461f..a6208efcfccfceff57bd04cb4c6b8bd18a95b13a 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1110,6 +1110,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ipt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1118,6 +1120,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; @@ -1494,6 +1498,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ipt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1502,6 +1508,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 4073762996e221650a2c250100d63edc04280c0a..fc761915c5f6fbb637647daa5386c28729d62b74 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -279,6 +279,7 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, goto free_nskb; nf_ct_attach(nskb, oldskb); + nf_ct_set_closing(skb_nfct(oldskb)); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) /* If we use ip_local_out for bridged traffic, the MAC source on diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 7c63b91edbf7a362120792710a4961c600631921..ee0efd0efec400b24212319d25f2a08b24b58935 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -348,6 +348,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, goto error; skb_reserve(skb, hlen); + skb->protocol = htons(ETH_P_IP); skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 474f391fab35d3de490bc54d3be76d44d71134a1..6c0f1e347b855ae7de564f2ca0f0c5bf04184c27 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -926,13 +926,11 @@ void ip_rt_send_redirect(struct sk_buff *skb) icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; ++peer->n_redirects; -#ifdef CONFIG_IP_ROUTE_VERBOSE - if (log_martians && + if (IS_ENABLED(CONFIG_IP_ROUTE_VERBOSE) && log_martians && peer->n_redirects == ip_rt_redirect_number) net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", &ip_hdr(skb)->saddr, inet_iif(skb), &ip_hdr(skb)->daddr, &gw); -#endif } out_put_peer: inet_putpeer(peer); @@ -2170,6 +2168,9 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, int err = -EINVAL; u32 tag = 0; + if (!in_dev) + return -EINVAL; + if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 86e7695d91adff2780a4e99994d1a25bbc83a332..3447a09ee83a2f5960d305bc7b4ba511c62193e5 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2831,7 +2831,7 @@ void tcp_shutdown(struct sock *sk, int how) /* If we've already sent a FIN, or it's a closed state, skip this. */ if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_SYN_SENT | - TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) { + TCPF_CLOSE_WAIT)) { /* Clear out any half completed packets. FIN if needed. */ if (tcp_close_state(sk)) tcp_send_fin(sk); @@ -2940,7 +2940,7 @@ void __tcp_close(struct sock *sk, long timeout) * machine. State transitions: * * TCP_ESTABLISHED -> TCP_FIN_WAIT1 - * TCP_SYN_RECV -> TCP_FIN_WAIT1 (forget it, it's impossible) + * TCP_SYN_RECV -> TCP_FIN_WAIT1 (it is difficult) * TCP_CLOSE_WAIT -> TCP_LAST_ACK * * are legal only when FIN has been sent (i.e. in window), @@ -3052,6 +3052,8 @@ void tcp_close(struct sock *sk, long timeout) lock_sock(sk); __tcp_close(sk, timeout); release_sock(sk); + if (!sk->sk_net_refcnt) + inet_csk_clear_xmit_timers_sync(sk); sock_put(sk); } EXPORT_SYMBOL(tcp_close); @@ -4102,11 +4104,11 @@ int do_tcp_getsockopt(struct sock *sk, int level, if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); - if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + switch (optname) { case TCP_MAXSEG: val = tp->mss_cache; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 34460c9b37ae27d34b91feb11a3dba674e98c701..4c9da94553365bb717699341a5e311f789caff4f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6597,6 +6597,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_initialize_rcv_mss(sk); tcp_fast_path_on(tp); + if (sk->sk_shutdown & SEND_SHUTDOWN) + tcp_shutdown(sk, SEND_SHUTDOWN); break; case TCP_FIN_WAIT1: { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index be2c807eed15d8e5b0a7a223a465f191ca7cd637..5dcb969cb5e9cc7a79944e687b7f3ebe958dff4b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -153,6 +153,12 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) if (tcptw->tw_ts_recent_stamp && (!twp || (reuse && time_after32(ktime_get_seconds(), tcptw->tw_ts_recent_stamp)))) { + /* inet_twsk_hashdance() sets sk_refcnt after putting twsk + * and releasing the bucket lock. + */ + if (unlikely(!refcount_inc_not_zero(&sktw->sk_refcnt))) + return 0; + /* In case of repair and re-using TIME-WAIT sockets we still * want to be sure that it is safe as above but honor the * sequence numbers and time stamps set as part of the repair @@ -173,7 +179,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) tp->rx_opt.ts_recent = tcptw->tw_ts_recent; tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; } - sock_hold(sktw); + return 1; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 42844d20da0200f6105456c3aea8aa4a062a8a96..b3bfa1a09df6831c3fe7883b9259edec4f71abdb 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -357,10 +357,6 @@ void tcp_twsk_purge(struct list_head *net_exit_list, int family) /* Even if tw_refcount == 1, we must clean up kernel reqsk */ inet_twsk_purge(net->ipv4.tcp_death_row.hashinfo, family); } else if (!purged_once) { - /* The last refcount is decremented in tcp_sk_exit_batch() */ - if (refcount_read(&net->ipv4.tcp_death_row.tw_refcount) == 1) - continue; - inet_twsk_purge(&tcp_hashinfo, family); purged_once = true; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 67087da45a1f73a95e49f4e2283e19c02feef4f1..15f814c1e16934708002ad33a9329008a0492408 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3480,7 +3480,9 @@ void tcp_send_fin(struct sock *sk) return; } } else { - skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation); + skb = alloc_skb_fclone(MAX_TCP_HEADER, + sk_gfp_mask(sk, GFP_ATOMIC | + __GFP_NOWARN)); if (unlikely(!skb)) return; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 87d759bab00123bd582cba5d57f61b1378031bde..39fae7581d350028d468929dc6566c6dc06c13cd 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -603,6 +603,13 @@ static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk, } DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key); +EXPORT_SYMBOL(udp_encap_needed_key); + +#if IS_ENABLED(CONFIG_IPV6) +DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +EXPORT_SYMBOL(udpv6_encap_needed_key); +#endif + void udp_encap_enable(void) { static_branch_inc(&udp_encap_needed_key); @@ -1134,16 +1141,17 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = udp_cmsg_send(sk, msg, &ipc.gso_size); - if (err > 0) + if (err > 0) { err = ip_cmsg_send(sk, msg, &ipc, sk->sk_family == AF_INET6); + connected = 0; + } if (unlikely(err < 0)) { kfree(ipc.opt); return err; } if (ipc.opt) free = 1; - connected = 0; } if (!ipc.opt) { struct ip_options_rcu *inet_opt; @@ -2790,11 +2798,11 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); - if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + switch (optname) { case UDP_CORK: val = udp_test_bit(CORK, sk); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 8096576fd9bde6558a9ea18c6cb8138bcc10be16..794ea24292f62cac6d72dc0bb1a47a52d88fd299 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -441,8 +441,9 @@ static int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) NAPI_GRO_CB(p)->count++; p->data_len += skb->len; - /* sk owenrship - if any - completely transferred to the aggregated packet */ + /* sk ownership - if any - completely transferred to the aggregated packet */ skb->destructor = NULL; + skb->sk = NULL; p->truesize += skb->truesize; p->len += skb->len; @@ -462,6 +463,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, struct sk_buff *p; unsigned int ulen; int ret = 0; + int flush; /* requires non zero csum, for symmetry with GSO */ if (!uh->check) { @@ -495,13 +497,22 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, return p; } + flush = NAPI_GRO_CB(p)->flush; + + if (NAPI_GRO_CB(p)->flush_id != 1 || + NAPI_GRO_CB(p)->count != 1 || + !NAPI_GRO_CB(p)->is_atomic) + flush |= NAPI_GRO_CB(p)->flush_id; + else + NAPI_GRO_CB(p)->is_atomic = false; + /* Terminate the flow on len mismatch or if it grow "too much". * Under small packet flood GRO count could elsewhere grow a lot * leading to excessive truesize values. * On len mismatch merge the first packet shorter than gso_size, * otherwise complete the GRO packet. */ - if (ulen > ntohs(uh2->len)) { + if (ulen > ntohs(uh2->len) || flush) { pp = p; } else { if (NAPI_GRO_CB(skb)->is_flist) { @@ -543,11 +554,19 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, unsigned int off = skb_gro_offset(skb); int flush = 1; - /* we can do L4 aggregation only if the packet can't land in a tunnel - * otherwise we could corrupt the inner stream + /* We can do L4 aggregation only if the packet can't land in a tunnel + * otherwise we could corrupt the inner stream. Detecting such packets + * cannot be foolproof and the aggregation might still happen in some + * cases. Such packets should be caught in udp_unexpected_gso later. */ NAPI_GRO_CB(skb)->is_flist = 0; if (!sk || !udp_sk(sk)->gro_receive) { + /* If the packet was locally encapsulated in a UDP tunnel that + * wasn't detected above, do not GRO. + */ + if (skb->encapsulation) + goto out; + if (skb->dev->features & NETIF_F_GRO_FRAGLIST) NAPI_GRO_CB(skb)->is_flist = sk ? !udp_test_bit(GRO_ENABLED, sk) : 1; @@ -707,13 +726,7 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; - if (skb->ip_summed == CHECKSUM_UNNECESSARY) { - if (skb->csum_level < SKB_MAX_CSUM_LEVEL) - skb->csum_level++; - } else { - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb->csum_level = 0; - } + __skb_incr_checksum_unnecessary(skb); return 0; } diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 183f6dc3724293f60c05aac630347405344c5010..f6e90ba50b639de89ef2853382269cbefc769720 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -61,7 +61,11 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async) ip_send_check(iph); if (xo && (xo->flags & XFRM_GRO)) { - skb_mac_header_rebuild(skb); + /* The full l2 header needs to be preserved so that re-injecting the packet at l2 + * works correctly in the presence of vlan tags. + */ + skb_mac_header_rebuild_full(skb, xo->orig_mac_len); + skb_reset_network_header(skb); skb_reset_transport_header(skb); return 0; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index b8dc20fe7a4e2b0490114ec08dd538ba0a6405d9..22e246ff910ee326bcdfb3a46d02341620fe2bab 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -706,6 +706,22 @@ errout: return err; } +/* Combine dev_addr_genid and dev_base_seq to detect changes. + */ +static u32 inet6_base_seq(const struct net *net) +{ + u32 res = atomic_read(&net->ipv6.dev_addr_genid) + + net->dev_base_seq; + + /* Must not return 0 (see nl_dump_check_consistent()). + * Chose a value far away from 0. + */ + if (!res) + res = 0x80000000; + return res; +} + + static int inet6_netconf_dump_devconf(struct sk_buff *skb, struct netlink_callback *cb) { @@ -739,8 +755,7 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb, idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&net->ipv6.dev_addr_genid) ^ - net->dev_base_seq; + cb->seq = inet6_base_seq(net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@ -2035,9 +2050,10 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add if (ipv6_addr_equal(&ifp->addr, addr)) { if (!dev || ifp->idev->dev == dev || !(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) { - result = ifp; - in6_ifa_hold(ifp); - break; + if (in6_ifa_hold_safe(ifp)) { + result = ifp; + break; + } } } } @@ -4117,7 +4133,7 @@ static void addrconf_dad_work(struct work_struct *w) if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) && ipv6_addr_equal(&ifp->addr, &addr)) { /* DAD failed for link-local based on MAC */ - idev->cnf.disable_ipv6 = 1; + WRITE_ONCE(idev->cnf.disable_ipv6, 1); pr_info("%s: IPv6 being disabled!\n", ifp->idev->dev->name); @@ -5326,7 +5342,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, } rcu_read_lock(); - cb->seq = atomic_read(&tgt_net->ipv6.dev_addr_genid) ^ tgt_net->dev_base_seq; + cb->seq = inet6_base_seq(tgt_net); for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &tgt_net->dev_index_head[h]; @@ -5458,9 +5474,10 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, } addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer); - if (!addr) - return -EINVAL; - + if (!addr) { + err = -EINVAL; + goto errout; + } ifm = nlmsg_data(nlh); if (ifm->ifa_index) dev = dev_get_by_index(tgt_net, ifm->ifa_index); @@ -5962,7 +5979,7 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, (dev->ifindex != dev_get_iflink(dev) && nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))) || nla_put_u8(skb, IFLA_OPERSTATE, - netif_running(dev) ? dev->operstate : IF_OPER_DOWN)) + netif_running(dev) ? READ_ONCE(dev->operstate) : IF_OPER_DOWN)) goto nla_put_failure; protoinfo = nla_nest_start_noflag(skb, IFLA_PROTINFO); if (!protoinfo) @@ -6272,7 +6289,8 @@ static void addrconf_disable_change(struct net *net, __s32 newf) idev = __in6_dev_get(dev); if (idev) { int changed = (!idev->cnf.disable_ipv6) ^ (!newf); - idev->cnf.disable_ipv6 = newf; + + WRITE_ONCE(idev->cnf.disable_ipv6, newf); if (changed) dev_disable_change(idev); } @@ -6289,7 +6307,7 @@ static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf) net = (struct net *)table->extra2; old = *p; - *p = newf; + WRITE_ONCE(*p, newf); if (p == &net->ipv6.devconf_dflt->disable_ipv6) { rtnl_unlock(); @@ -6297,7 +6315,7 @@ static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf) } if (p == &net->ipv6.devconf_all->disable_ipv6) { - net->ipv6.devconf_dflt->disable_ipv6 = newf; + WRITE_ONCE(net->ipv6.devconf_dflt->disable_ipv6, newf); addrconf_disable_change(net, newf); } else if ((!newf) ^ (!old)) dev_disable_change((struct inet6_dev *)table->extra1); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 0b42eb8c55aaf88ebab55df0563d77949a98e887..62247621cea52ce4d55aafdbf4e4ec01c09d8e67 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1077,6 +1077,7 @@ static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = { .udp6_lib_lookup = __udp6_lib_lookup, .ipv6_setsockopt = do_ipv6_setsockopt, .ipv6_getsockopt = do_ipv6_getsockopt, + .ipv6_dev_get_saddr = ipv6_dev_get_saddr, }; static int __init inet6_init(void) diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 5fa0e37305d9dc4201fe8595a1a4134b901e8e84..1cfdd9d950123e6739d1accadea1c95ea24d0f31 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -180,6 +180,8 @@ static bool ip6_parse_tlv(bool hopbyhop, case IPV6_TLV_IOAM: if (!ipv6_hop_ioam(skb, off)) return false; + + nh = skb_network_header(skb); break; case IPV6_TLV_JUMBO: if (!ipv6_hop_jumbo(skb, off)) @@ -974,6 +976,14 @@ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) if (!skb_valid_dst(skb)) ip6_route_input(skb); + /* About to mangle packet header */ + if (skb_ensure_writable(skb, optoff + 2 + hdr->opt_len)) + goto drop; + + /* Trace pointer may have changed */ + trace = (struct ioam6_trace_hdr *)(skb_network_header(skb) + + optoff + sizeof(*hdr)); + ioam6_fill_trace_data(skb, ns, trace, true); break; default: diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 7c20038330104e9c1dd9f93f38667cff9a0fadc0..6eeab21512ba98721fbd54da2b3dfabdd7553862 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -233,8 +233,12 @@ static int __fib6_rule_action(struct fib_rule *rule, struct flowi *flp, rt = pol_lookup_func(lookup, net, table, flp6, arg->lookup_data, flags); if (rt != net->ipv6.ip6_null_entry) { + struct inet6_dev *idev = ip6_dst_idev(&rt->dst); + + if (!idev) + goto again; err = fib6_rule_saddr(net, rule, flags, flp6, - ip6_dst_idev(&rt->dst)->dev); + idev->dev); if (err == -EAGAIN) goto again; @@ -449,6 +453,11 @@ static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule) + nla_total_size(16); /* src */ } +static void fib6_rule_flush_cache(struct fib_rules_ops *ops) +{ + rt_genid_bump_ipv6(ops->fro_net); +} + static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { .family = AF_INET6, .rule_size = sizeof(struct fib6_rule), @@ -461,6 +470,7 @@ static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { .compare = fib6_rule_compare, .fill = fib6_rule_fill, .nlmsg_payload = fib6_rule_nlmsg_payload, + .flush_cache = fib6_rule_flush_cache, .nlgroup = RTNLGRP_IPV6_RULE, .owner = THIS_MODULE, .fro_net = &init_net, diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 1840735e9cb07db6704b251b1454f5c5ce9c9b33..8213626434b91de4dab74c54f38048cff2391d73 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -646,19 +646,19 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) if (!w) { /* New dump: * - * 1. hook callback destructor. - */ - cb->args[3] = (long)cb->done; - cb->done = fib6_dump_done; - - /* - * 2. allocate and initialize walker. + * 1. allocate and initialize walker. */ w = kzalloc(sizeof(*w), GFP_ATOMIC); if (!w) return -ENOMEM; w->func = fib6_dump_node; cb->args[2] = (long)w; + + /* 2. hook callback destructor. + */ + cb->args[3] = (long)cb->done; + cb->done = fib6_dump_done; + } arg.skb = skb; @@ -1376,7 +1376,10 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { struct fib6_table *table = rt->fib6_table; - struct fib6_node *fn, *pn = NULL; + struct fib6_node *fn; +#ifdef CONFIG_IPV6_SUBTREES + struct fib6_node *pn = NULL; +#endif int err = -ENOMEM; int allow_create = 1; int replace_required = 0; @@ -1400,9 +1403,9 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, goto out; } +#ifdef CONFIG_IPV6_SUBTREES pn = fn; -#ifdef CONFIG_IPV6_SUBTREES if (rt->fib6_src.plen) { struct fib6_node *sn; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index d3fba7d8dec4ebb59d35d2188985306c8f9b7488..b3e2d658af8090f3e5cb68a7b62f653806d3a897 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -528,6 +528,9 @@ static int ip6erspan_rcv(struct sk_buff *skb, struct ip6_tnl *tunnel; u8 ver; + if (unlikely(!pskb_may_pull(skb, sizeof(*ershdr)))) + return PACKET_REJECT; + ipv6h = ipv6_hdr(skb); ershdr = (struct erspan_base_hdr *)skb->data; ver = ershdr->ver; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index b8378814532cead0275e8b7a656f78450993f619..1ba97933c74fbd12e21f273f0aeda2313bd608b7 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -168,9 +168,9 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev, SKB_DR_SET(reason, NOT_SPECIFIED); if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL || - !idev || unlikely(idev->cnf.disable_ipv6)) { + !idev || unlikely(READ_ONCE(idev->cnf.disable_ipv6))) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); - if (idev && unlikely(idev->cnf.disable_ipv6)) + if (idev && unlikely(READ_ONCE(idev->cnf.disable_ipv6))) SKB_DR_SET(reason, IPV6DISABLED); goto drop; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index e9ae084d038d1401e881de3d13cd1424a691da83..fb26401950e7eff40ede30b1356f2c22ee5d76b5 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -224,7 +224,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; - if (unlikely(idev->cnf.disable_ipv6)) { + if (unlikely(!idev || READ_ONCE(idev->cnf.disable_ipv6))) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb_reason(skb, SKB_DROP_REASON_IPV6DISABLED); return 0; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 566f3b7b957e94c0b64300f115629c3c12189121..a777695389403ca298db51de41cc1382d835485e 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2722,7 +2722,6 @@ void ipv6_mc_down(struct inet6_dev *idev) /* Should stop work after group drop. or we will * start work again in mld_ifc_event() */ - synchronize_net(); mld_query_stop_work(idev); mld_report_stop_work(idev); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 0ce0ed17c758375c5b3fec81fde1148ce16d61bb..b844e519da1b4eafceeda3e7f62207c8c12ad374 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1127,6 +1127,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ip6t_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1135,6 +1137,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; @@ -1503,6 +1507,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ip6t_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1511,6 +1517,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 38db0064d6613a8472ec2835afdbf80071c1fcc2..87a394179092c47203baad231e6f1c70d64ff5a0 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -293,6 +293,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, } skb_dst_drop(skb); + skb_orphan(skb); return -EINPROGRESS; insert_error: @@ -468,7 +469,6 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) hdr = ipv6_hdr(skb); fhdr = (struct frag_hdr *)skb_transport_header(skb); - skb_orphan(skb); fq = fq_find(net, fhdr->identification, user, hdr, skb->dev ? skb->dev->ifindex : 0); if (fq == NULL) { diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index 433d98bbe33f7be01416ae73de7f2bb5a3c25ce3..71d692728230e0eed11e1bc472daebe14e8114fe 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -344,6 +344,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, nf_reject_ip6_tcphdr_put(nskb, oldskb, otcph, otcplen); nf_ct_attach(nskb, oldskb); + nf_ct_set_closing(skb_nfct(oldskb)); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) /* If we use ip6_local_out for bridged traffic, the MAC source on diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7f65dc750feb8ca63cecc6e73afc44b1caca6543..887599d351b8df67aa3b80691261d4ee0f9b40f4 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5335,19 +5335,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, err_nh = NULL; list_for_each_entry(nh, &rt6_nh_list, next) { err = __ip6_ins_rt(nh->fib6_info, info, extack); - fib6_info_release(nh->fib6_info); - - if (!err) { - /* save reference to last route successfully inserted */ - rt_last = nh->fib6_info; - - /* save reference to first route for notification */ - if (!rt_notif) - rt_notif = nh->fib6_info; - } - /* nh->fib6_info is used or freed at this point, reset to NULL*/ - nh->fib6_info = NULL; if (err) { if (replace && nhn) NL_SET_ERR_MSG_MOD(extack, @@ -5355,6 +5343,12 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, err_nh = nh; goto add_errout; } + /* save reference to last route successfully inserted */ + rt_last = nh->fib6_info; + + /* save reference to first route for notification */ + if (!rt_notif) + rt_notif = nh->fib6_info; /* Because each route is added like a single route we remove * these flags after the first nexthop: if there is a collision, @@ -5415,8 +5409,7 @@ add_errout: cleanup: list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) { - if (nh->fib6_info) - fib6_info_release(nh->fib6_info); + fib6_info_release(nh->fib6_info); list_del(&nh->next); kfree(nh); } diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 29346a6eec9ffed46b00153c4a6cb0295a327ceb..35508abd76f43d771ed7e66f29bc143af4a81977 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -512,22 +512,24 @@ int __init seg6_init(void) { int err; - err = genl_register_family(&seg6_genl_family); + err = register_pernet_subsys(&ip6_segments_ops); if (err) goto out; - err = register_pernet_subsys(&ip6_segments_ops); + err = genl_register_family(&seg6_genl_family); if (err) - goto out_unregister_genl; + goto out_unregister_pernet; #ifdef CONFIG_IPV6_SEG6_LWTUNNEL err = seg6_iptunnel_init(); if (err) - goto out_unregister_pernet; + goto out_unregister_genl; err = seg6_local_init(); - if (err) - goto out_unregister_pernet; + if (err) { + seg6_iptunnel_exit(); + goto out_unregister_genl; + } #endif #ifdef CONFIG_IPV6_SEG6_HMAC @@ -548,11 +550,11 @@ out_unregister_iptun: #endif #endif #ifdef CONFIG_IPV6_SEG6_LWTUNNEL -out_unregister_pernet: - unregister_pernet_subsys(&ip6_segments_ops); -#endif out_unregister_genl: genl_unregister_family(&seg6_genl_family); +#endif +out_unregister_pernet: + unregister_pernet_subsys(&ip6_segments_ops); goto out; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index c2c02dea6c386e05eb0f3584327935f74a32df17..504ea27d08fb09e6e48b62af7da6ffdc1e6392ac 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -476,7 +476,7 @@ csum_copy_err: goto try_again; } -DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void) { static_branch_inc(&udpv6_encap_needed_key); @@ -1493,9 +1493,11 @@ do_udp_sendmsg: ipc6.opt = opt; err = udp_cmsg_send(sk, msg, &ipc6.gso_size); - if (err > 0) + if (err > 0) { err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, fl6, &ipc6); + connected = false; + } if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -1507,7 +1509,6 @@ do_udp_sendmsg: } if (!(opt->opt_nflen|opt->opt_flen)) opt = NULL; - connected = false; } if (!opt) { opt = txopt_get(np); diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 7720d04ed396d0e190561e4d608cf5a7857050d8..b98c4c8d8e274671f1484fd07b6610ac8755a779 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -169,13 +169,7 @@ INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff) skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; - if (skb->ip_summed == CHECKSUM_UNNECESSARY) { - if (skb->csum_level < SKB_MAX_CSUM_LEVEL) - skb->csum_level++; - } else { - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb->csum_level = 0; - } + __skb_incr_checksum_unnecessary(skb); return 0; } diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 4156387248e40e15b0dd10ccfa89cee5dd7e7534..8432b50d9ce4ca4027fcb969cd8769e94d86e05f 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -56,7 +56,11 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async) skb_postpush_rcsum(skb, skb_network_header(skb), nhlen); if (xo && (xo->flags & XFRM_GRO)) { - skb_mac_header_rebuild(skb); + /* The full l2 header needs to be preserved so that re-injecting the packet at l2 + * works correctly in the presence of vlan tags. + */ + skb_mac_header_rebuild_full(skb, xo->orig_mac_len); + skb_reset_network_header(skb); skb_reset_transport_header(skb); return 0; } diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index fc3fddeb6f36d4066c91d4eae889deccb07799fc..f66b5f74cd83a6f93ae31fbe6ba00b92865d3d24 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -156,7 +156,7 @@ static char iucv_error_pathid[16] = "INVALID PATHID"; static LIST_HEAD(iucv_handler_list); /* - * iucv_path_table: an array of iucv_path structures. + * iucv_path_table: array of pointers to iucv_path structures. */ static struct iucv_path **iucv_path_table; static unsigned long iucv_max_pathid; @@ -544,7 +544,7 @@ static int iucv_enable(void) cpus_read_lock(); rc = -ENOMEM; - alloc_size = iucv_max_pathid * sizeof(struct iucv_path); + alloc_size = iucv_max_pathid * sizeof(*iucv_path_table); iucv_path_table = kzalloc(alloc_size, GFP_KERNEL); if (!iucv_path_table) goto out; diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 65845c59c065564590217d6cd7a7718171c8067c..7d37bf4334d261d786c6c2c1e015268034b781f2 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1274,10 +1274,11 @@ static int kcm_getsockopt(struct socket *sock, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + switch (optname) { case KCM_RECV_DISABLE: val = kcm->rx_disabled; diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index f2ae03c404736d826fd7dc327b1567eac1c8651a..1f41d2f3b8c4e06cc9c061fe96f881ed1c798cbd 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -136,6 +136,9 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, /* checksums verified by L2TP */ skb->ip_summed = CHECKSUM_NONE; + /* drop outer flow-hash */ + skb_clear_hash(skb); + skb_dst_drop(skb); nf_reset_ct(skb); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 314ec3a51e8de4b286111a52ed91997e21486a4f..bb92dc8b82f3932b29a3c851a51f26a6cef95732 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -630,7 +630,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) back_from_confirm: lock_sock(sk); - ulen = len + skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0; + ulen = len + (skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0); err = ip6_append_data(sk, ip_generic_getfrag, msg, ulen, transhdrlen, &ipc6, &fl6, (struct rt6_info *)dst, diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index f011af6601c9cdcdd200aec3de47542f7b96a3b0..6146e4e67bbb5438ebe9eb0046b1e5dbfce6f7ca 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1356,11 +1356,11 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); - if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + err = -ENOTCONN; if (!sk->sk_user_data) goto end; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index a2c4866080bd7289a9a3b00b41acb8a6e22bd764..1e57027da2913a90f08b9bd9a1db7f4158eb51e9 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1775,6 +1775,8 @@ static int sta_link_apply_parameters(struct ieee80211_local *local, sband->band); } + ieee80211_sta_set_rx_nss(link_sta); + return ret; } @@ -2073,15 +2075,14 @@ static int ieee80211_change_station(struct wiphy *wiphy, } if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN && - sta->sdata->u.vlan.sta) { - ieee80211_clear_fast_rx(sta); + sta->sdata->u.vlan.sta) RCU_INIT_POINTER(sta->sdata->u.vlan.sta, NULL); - } if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) ieee80211_vif_dec_num_mcast(sta->sdata); sta->sdata = vlansdata; + ieee80211_check_fast_rx(sta); ieee80211_check_fast_xmit(sta); if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) { diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index d5dd2d9e89b489745ca3a195ab65db0dc354a055..3e14d5c9aa1b4b71872263d8108472fbba78d7f6 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -120,7 +120,7 @@ struct ieee80211_bss { }; /** - * enum ieee80211_corrupt_data_flags - BSS data corruption flags + * enum ieee80211_bss_corrupt_data_flags - BSS data corruption flags * @IEEE80211_BSS_CORRUPT_BEACON: last beacon frame received was corrupted * @IEEE80211_BSS_CORRUPT_PROBE_RESP: last probe response received was corrupted * @@ -133,7 +133,7 @@ enum ieee80211_bss_corrupt_data_flags { }; /** - * enum ieee80211_valid_data_flags - BSS valid data flags + * enum ieee80211_bss_valid_data_flags - BSS valid data flags * @IEEE80211_BSS_VALID_WMM: WMM/UAPSD data was gathered from non-corrupt IE * @IEEE80211_BSS_VALID_RATES: Supported rates were gathered from non-corrupt IE * @IEEE80211_BSS_VALID_ERP: ERP flag was gathered from non-corrupt IE diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index c07645c999f9a2b21e332cfd640ae9c1e551f1e3..f25dc6931a5b1f1bf2237e5e8aff96a2eb00dc89 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -7221,8 +7221,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, rcu_read_lock(); beacon_ies = rcu_dereference(req->bss->beacon_ies); - - if (beacon_ies) { + if (!beacon_ies) { /* * Wait up to one beacon interval ... * should this be more if we miss one? @@ -7295,6 +7294,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true, req->reason_code, false); + drv_mgd_complete_tx(sdata->local, sdata, &info); return 0; } diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index d5ea5f5bcf3a069e1d4dc5dd2638275e58aae51f..9d33fd2377c88af8ec38b6e398d103449f3b03b8 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -119,7 +119,8 @@ void rate_control_rate_update(struct ieee80211_local *local, rcu_read_unlock(); } - drv_sta_rc_update(local, sta->sdata, &sta->sta, changed); + if (sta->uploaded) + drv_sta_rc_update(local, sta->sdata, &sta->sta, changed); } int ieee80211_rate_control_register(const struct rate_control_ops *ops) diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index f3d6c3e4c970e59e2b9e2a4c32245c11e1cf3726..bd56015b29258d2baeece999c94814b7ea1b0a37 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -891,6 +891,8 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) if (ieee80211_vif_is_mesh(&sdata->vif)) mesh_accept_plinks_update(sdata); + ieee80211_check_fast_xmit(sta); + return 0; out_remove: if (sta->sta.valid_links) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 2db103a56a28f4df728be08249083eef4cba68db..3d62e8b718740ae14a1eb1153725a4a631f2ce37 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc * Copyright 2007 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2018-2022 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation * * Transmit and frame generation functions. */ @@ -3044,7 +3044,7 @@ void ieee80211_check_fast_xmit(struct sta_info *sta) sdata->vif.type == NL80211_IFTYPE_STATION) goto out; - if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED)) + if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED) || !sta->uploaded) goto out; if (test_sta_flag(sta, WLAN_STA_PS_STA) || @@ -3838,6 +3838,7 @@ begin: goto begin; skb = __skb_dequeue(&tx.skbs); + info = IEEE80211_SKB_CB(skb); if (!skb_queue_empty(&tx.skbs)) { spin_lock_bh(&fq->lock); @@ -3882,7 +3883,7 @@ begin: } encap_out: - IEEE80211_SKB_CB(skb)->control.vif = vif; + info->control.vif = vif; if (tx.sta && wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) { diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c index 55550ead2ced8cbd1273bb4c0a02a0928080565f..a4cc9d077c59ce98c67d9d92e37159221a39246e 100644 --- a/net/mac802154/llsec.c +++ b/net/mac802154/llsec.c @@ -265,19 +265,27 @@ fail: return -ENOMEM; } +static void mac802154_llsec_key_del_rcu(struct rcu_head *rcu) +{ + struct ieee802154_llsec_key_entry *pos; + struct mac802154_llsec_key *mkey; + + pos = container_of(rcu, struct ieee802154_llsec_key_entry, rcu); + mkey = container_of(pos->key, struct mac802154_llsec_key, key); + + llsec_key_put(mkey); + kfree_sensitive(pos); +} + int mac802154_llsec_key_del(struct mac802154_llsec *sec, const struct ieee802154_llsec_key_id *key) { struct ieee802154_llsec_key_entry *pos; list_for_each_entry(pos, &sec->table.keys, list) { - struct mac802154_llsec_key *mkey; - - mkey = container_of(pos->key, struct mac802154_llsec_key, key); - if (llsec_key_id_equal(&pos->id, key)) { list_del_rcu(&pos->list); - llsec_key_put(mkey); + call_rcu(&pos->rcu, mac802154_llsec_key_del_rcu); return 0; } } diff --git a/net/mctp/route.c b/net/mctp/route.c index 68be8f2b622dd144b2ecb3a11ff59a1f018b0c86..05ab4fddc82e95b980715a16ee70adebcca32c54 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -663,7 +663,7 @@ struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, spin_unlock_irqrestore(&mns->keys_lock, flags); if (!tagbits) { - kfree(key); + mctp_key_unref(key); return ERR_PTR(-EBUSY); } @@ -843,6 +843,9 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, /* copy message payload */ skb_copy_bits(skb, pos, skb_transport_header(skb2), size); + /* we need to copy the extensions, for MCTP flow data */ + skb_ext_copy(skb2, skb); + /* do route */ rc = rt->output(rt, skb2); if (rc) @@ -888,7 +891,7 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, dev = dev_get_by_index_rcu(sock_net(sk), cb->ifindex); if (!dev) { rcu_read_unlock(); - return rc; + goto out_free; } rt->dev = __mctp_dev_get(dev); rcu_read_unlock(); @@ -903,7 +906,8 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, rt->mtu = 0; } else { - return -EINVAL; + rc = -EINVAL; + goto out_free; } spin_lock_irqsave(&rt->dev->addrs_lock, flags); @@ -966,12 +970,17 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, rc = mctp_do_fragment_route(rt, skb, mtu, tag); } + /* route output functions consume the skb, even on error */ + skb = NULL; + out_release: if (!ext_rt) mctp_route_release(rt); mctp_dev_put(tmp_rt.dev); +out_free: + kfree_skb(skb); return rc; } diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c index 1482259de9b5d7a5e791f0deb34cedcb1f26bf21..40334d4d89dea21df083b7b625d9586097e15a86 100644 --- a/net/mpls/mpls_gso.c +++ b/net/mpls/mpls_gso.c @@ -26,6 +26,9 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb, __be16 mpls_protocol; unsigned int mpls_hlen; + if (!skb_inner_network_header_was_set(skb)) + goto out; + skb_reset_network_header(skb); mpls_hlen = skb_inner_network_header(skb) - skb_network_header(skb); if (unlikely(!mpls_hlen || mpls_hlen % MPLS_HLEN)) diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index a536586742f28c1ddd54c79e62eb56fea267a8fa..7017dd60659dc7133318c1c82e3f429bea3a5d57 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -13,17 +13,22 @@ #include #include "protocol.h" -static int subflow_get_info(const struct sock *sk, struct sk_buff *skb) +static int subflow_get_info(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *sf; struct nlattr *start; u32 flags = 0; + bool slow; int err; + if (inet_sk_state_load(sk) == TCP_LISTEN) + return 0; + start = nla_nest_start_noflag(skb, INET_ULP_INFO_MPTCP); if (!start) return -EMSGSIZE; + slow = lock_sock_fast(sk); rcu_read_lock(); sf = rcu_dereference(inet_csk(sk)->icsk_ulp_data); if (!sf) { @@ -63,17 +68,19 @@ static int subflow_get_info(const struct sock *sk, struct sk_buff *skb) sf->map_data_len) || nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_FLAGS, flags) || nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_REM, sf->remote_id) || - nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, sf->local_id)) { + nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, subflow_get_local_id(sf))) { err = -EMSGSIZE; goto nla_failure; } rcu_read_unlock(); + unlock_sock_fast(sk, slow); nla_nest_end(skb, start); return 0; nla_failure: rcu_read_unlock(); + unlock_sock_fast(sk, slow); nla_nest_cancel(skb, start); return err; } diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 980050f6b456fbecbae4b3f16cbc353bca47d64e..3328870b0c1f882c2e3ebf6c9146e892c041c64e 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -407,23 +407,12 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk) } } -static bool lookup_address_in_vec(const struct mptcp_addr_info *addrs, unsigned int nr, - const struct mptcp_addr_info *addr) -{ - int i; - - for (i = 0; i < nr; i++) { - if (addrs[i].id == addr->id) - return true; - } - - return false; -} - /* Fill all the remote addresses into the array addrs[], * and return the array size. */ -static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullmesh, +static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, + struct mptcp_addr_info *local, + bool fullmesh, struct mptcp_addr_info *addrs) { bool deny_id0 = READ_ONCE(msk->pm.remote_deny_join_id0); @@ -446,15 +435,28 @@ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullm msk->pm.subflows++; addrs[i++] = remote; } else { + DECLARE_BITMAP(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1); + + /* Forbid creation of new subflows matching existing + * ones, possibly already created by incoming ADD_ADDR + */ + bitmap_zero(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1); + mptcp_for_each_subflow(msk, subflow) + if (READ_ONCE(subflow->local_id) == local->id) + __set_bit(subflow->remote_id, unavail_id); + mptcp_for_each_subflow(msk, subflow) { ssk = mptcp_subflow_tcp_sock(subflow); remote_address((struct sock_common *)ssk, &addrs[i]); - addrs[i].id = subflow->remote_id; + addrs[i].id = READ_ONCE(subflow->remote_id); if (deny_id0 && !addrs[i].id) continue; - if (!lookup_address_in_vec(addrs, i, &addrs[i]) && - msk->pm.subflows < subflows_max) { + if (msk->pm.subflows < subflows_max) { + /* forbid creating multiple address towards + * this id + */ + __set_bit(addrs[i].id, unavail_id); msk->pm.subflows++; i++; } @@ -603,7 +605,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH); msk->pm.local_addr_used++; - nr = fill_remote_addresses_vec(msk, fullmesh, addrs); + nr = fill_remote_addresses_vec(msk, &local->addr, fullmesh, addrs); if (nr) __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); spin_unlock_bh(&msk->pm.lock); @@ -798,18 +800,18 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, mptcp_for_each_subflow_safe(msk, subflow, tmp) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + u8 remote_id = READ_ONCE(subflow->remote_id); int how = RCV_SHUTDOWN | SEND_SHUTDOWN; - u8 id = subflow->local_id; + u8 id = subflow_get_local_id(subflow); - if (rm_type == MPTCP_MIB_RMADDR && subflow->remote_id != rm_id) + if (rm_type == MPTCP_MIB_RMADDR && remote_id != rm_id) continue; if (rm_type == MPTCP_MIB_RMSUBFLOW && !mptcp_local_id_match(msk, id, rm_id)) continue; pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u", rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", - i, rm_id, subflow->local_id, subflow->remote_id, - msk->mpc_endpoint_id); + i, rm_id, id, remote_id, msk->mpc_endpoint_id); spin_unlock_bh(&msk->pm.lock); mptcp_subflow_shutdown(sk, ssk, how); @@ -900,7 +902,8 @@ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry) } static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, - struct mptcp_pm_addr_entry *entry) + struct mptcp_pm_addr_entry *entry, + bool needs_id) { struct mptcp_pm_addr_entry *cur, *del_entry = NULL; unsigned int addr_max; @@ -942,7 +945,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, } } - if (!entry->addr.id) { + if (!entry->addr.id && needs_id) { find_next: entry->addr.id = find_next_zero_bit(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1, @@ -953,7 +956,7 @@ find_next: } } - if (!entry->addr.id) + if (!entry->addr.id && needs_id) goto out; __set_bit(entry->addr.id, pernet->id_bitmap); @@ -1095,7 +1098,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) entry->ifindex = 0; entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT; entry->lsk = NULL; - ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); + ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true); if (ret < 0) kfree(entry); @@ -1311,6 +1314,18 @@ next: return 0; } +static bool mptcp_pm_has_addr_attr_id(const struct nlattr *attr, + struct genl_info *info) +{ + struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1]; + + if (!nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr, + mptcp_pm_addr_policy, info->extack) && + tb[MPTCP_PM_ADDR_ATTR_ID]) + return true; + return false; +} + static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; @@ -1352,7 +1367,8 @@ static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) goto out_free; } } - ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); + ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, + !mptcp_pm_has_addr_attr_id(attr, info)); if (ret < 0) { GENL_SET_ERR_MSG(info, "too many addresses or duplicate one"); goto out_free; @@ -2014,7 +2030,7 @@ static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk) if (WARN_ON_ONCE(!sf)) return -EINVAL; - if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, sf->local_id)) + if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, subflow_get_local_id(sf))) return -EMSGSIZE; if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, sf->remote_id)) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 38cbdc66d8bff3f14cdcd9310741bfa8000c8c62..414ed70e7ba2ed574234c56ea18e138e6d3861c5 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -25,8 +25,9 @@ void mptcp_free_local_addr_list(struct mptcp_sock *msk) } } -int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, - struct mptcp_pm_addr_entry *entry) +static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, + struct mptcp_pm_addr_entry *entry, + bool needs_id) { DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); struct mptcp_pm_addr_entry *match = NULL; @@ -41,7 +42,7 @@ int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, spin_lock_bh(&msk->pm.lock); list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) { addr_match = mptcp_addresses_equal(&e->addr, &entry->addr, true); - if (addr_match && entry->addr.id == 0) + if (addr_match && entry->addr.id == 0 && needs_id) entry->addr.id = e->addr.id; id_match = (e->addr.id == entry->addr.id); if (addr_match && id_match) { @@ -64,7 +65,7 @@ int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, } *e = *entry; - if (!e->addr.id) + if (!e->addr.id && needs_id) e->addr.id = find_next_zero_bit(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1, 1); @@ -132,10 +133,21 @@ int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc) { - struct mptcp_pm_addr_entry new_entry; + struct mptcp_pm_addr_entry *entry = NULL, *e, new_entry; __be16 msk_sport = ((struct inet_sock *) inet_sk((struct sock *)msk))->inet_sport; + spin_lock_bh(&msk->pm.lock); + list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) { + if (mptcp_addresses_equal(&e->addr, skc, false)) { + entry = e; + break; + } + } + spin_unlock_bh(&msk->pm.lock); + if (entry) + return entry->addr.id; + memset(&new_entry, 0, sizeof(struct mptcp_pm_addr_entry)); new_entry.addr = *skc; new_entry.addr.id = 0; @@ -144,7 +156,7 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, if (new_entry.addr.port == msk_sport) new_entry.addr.port = 0; - return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry); + return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true); } int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) @@ -186,7 +198,7 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) goto announce_err; } - err = mptcp_userspace_pm_append_new_local_addr(msk, &addr_val); + err = mptcp_userspace_pm_append_new_local_addr(msk, &addr_val, false); if (err < 0) { GENL_SET_ERR_MSG(info, "did not match address and id"); goto announce_err; @@ -210,6 +222,40 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) return err; } +static int mptcp_userspace_pm_remove_id_zero_address(struct mptcp_sock *msk, + struct genl_info *info) +{ + struct mptcp_rm_list list = { .nr = 0 }; + struct mptcp_subflow_context *subflow; + struct sock *sk = (struct sock *)msk; + bool has_id_0 = false; + int err = -EINVAL; + + lock_sock(sk); + mptcp_for_each_subflow(msk, subflow) { + if (READ_ONCE(subflow->local_id) == 0) { + has_id_0 = true; + break; + } + } + if (!has_id_0) { + GENL_SET_ERR_MSG(info, "address with id 0 not found"); + goto remove_err; + } + + list.ids[list.nr++] = 0; + + spin_lock_bh(&msk->pm.lock); + mptcp_pm_remove_addr(msk, &list); + spin_unlock_bh(&msk->pm.lock); + + err = 0; + +remove_err: + release_sock(sk); + return err; +} + int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) { struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; @@ -241,6 +287,11 @@ int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) goto remove_err; } + if (id_val == 0) { + err = mptcp_userspace_pm_remove_id_zero_address(msk, info); + goto remove_err; + } + lock_sock((struct sock *)msk); list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { @@ -324,7 +375,7 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info) } local.addr = addr_l; - err = mptcp_userspace_pm_append_new_local_addr(msk, &local); + err = mptcp_userspace_pm_append_new_local_addr(msk, &local, false); if (err < 0) { GENL_SET_ERR_MSG(info, "did not match address and id"); goto create_err; @@ -438,6 +489,16 @@ int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info) goto destroy_err; } +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + if (addr_l.family == AF_INET && ipv6_addr_v4mapped(&addr_r.addr6)) { + ipv6_addr_set_v4mapped(addr_l.addr.s_addr, &addr_l.addr6); + addr_l.family = AF_INET6; + } + if (addr_r.family == AF_INET && ipv6_addr_v4mapped(&addr_l.addr6)) { + ipv6_addr_set_v4mapped(addr_r.addr.s_addr, &addr_r.addr6); + addr_r.family = AF_INET6; + } +#endif if (addr_l.family != addr_r.family) { GENL_SET_ERR_MSG(info, "address families do not match"); err = -EINVAL; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 76539d1004ebb52295ee86e7c2dac4e7175c0a73..b6815610a6fa175301613e548f5146c0dc631d41 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -119,7 +119,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) subflow->request_mptcp = 1; /* This is the first subflow, always with id 0 */ - subflow->local_id_valid = 1; + WRITE_ONCE(subflow->local_id, 0); mptcp_sock_graft(msk->first, sk->sk_socket); return 0; @@ -1319,6 +1319,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, mpext = skb_ext_find(skb, SKB_EXT_MPTCP); if (!mptcp_skb_can_collapse_to(data_seq, skb, mpext)) { TCP_SKB_CB(skb)->eor = 1; + tcp_mark_push(tcp_sk(ssk), skb); goto alloc_skb; } @@ -1582,8 +1583,11 @@ static void mptcp_update_post_push(struct mptcp_sock *msk, void mptcp_check_and_set_pending(struct sock *sk) { - if (mptcp_send_head(sk)) - mptcp_sk(sk)->push_pending |= BIT(MPTCP_PUSH_PENDING); + if (mptcp_send_head(sk)) { + mptcp_data_lock(sk); + mptcp_sk(sk)->cb_flags |= BIT(MPTCP_PUSH_PENDING); + mptcp_data_unlock(sk); + } } void __mptcp_push_pending(struct sock *sk, unsigned int flags) @@ -2336,9 +2340,6 @@ bool __mptcp_retransmit_pending_data(struct sock *sk) if (__mptcp_check_fallback(mptcp_sk(sk))) return false; - if (tcp_rtx_and_write_queues_empty(sk)) - return false; - /* the closing socket has some data untransmitted and/or unacked: * some data in the mptcp rtx queue has not really xmitted yet. * keep it simple and re-inject the whole mptcp level rtx queue @@ -2422,7 +2423,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, goto out_release; } - dispose_it = !msk->subflow || ssk != msk->subflow->sk; + dispose_it = msk->free_first || ssk != msk->first; if (dispose_it) list_del(&subflow->node); @@ -2440,7 +2441,8 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk); if (!dispose_it) { __mptcp_subflow_disconnect(ssk, subflow, flags); - msk->subflow->state = SS_UNCONNECTED; + if (msk->subflow && ssk == msk->subflow->sk) + msk->subflow->state = SS_UNCONNECTED; release_sock(ssk); goto out; @@ -3144,7 +3146,6 @@ static int mptcp_disconnect(struct sock *sk, int flags) msk->last_snd = NULL; WRITE_ONCE(msk->flags, 0); msk->cb_flags = 0; - msk->push_pending = 0; msk->recovery = false; msk->can_ack = false; msk->fully_established = false; @@ -3168,8 +3169,50 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk) return (struct ipv6_pinfo *)(((u8 *)sk) + offset); } + +static void mptcp_copy_ip6_options(struct sock *newsk, const struct sock *sk) +{ + const struct ipv6_pinfo *np = inet6_sk(sk); + struct ipv6_txoptions *opt; + struct ipv6_pinfo *newnp; + + newnp = inet6_sk(newsk); + + rcu_read_lock(); + opt = rcu_dereference(np->opt); + if (opt) { + opt = ipv6_dup_options(newsk, opt); + if (!opt) + net_warn_ratelimited("%s: Failed to copy ip6 options\n", __func__); + } + RCU_INIT_POINTER(newnp->opt, opt); + rcu_read_unlock(); +} #endif +static void mptcp_copy_ip_options(struct sock *newsk, const struct sock *sk) +{ + struct ip_options_rcu *inet_opt, *newopt = NULL; + const struct inet_sock *inet = inet_sk(sk); + struct inet_sock *newinet; + + newinet = inet_sk(newsk); + + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + if (inet_opt) { + newopt = sock_kmalloc(newsk, sizeof(*inet_opt) + + inet_opt->opt.optlen, GFP_ATOMIC); + if (newopt) + memcpy(newopt, inet_opt, sizeof(*inet_opt) + + inet_opt->opt.optlen); + else + net_warn_ratelimited("%s: Failed to copy ip options\n", __func__); + } + RCU_INIT_POINTER(newinet->inet_opt, newopt); + rcu_read_unlock(); +} + struct sock *mptcp_sk_clone_init(const struct sock *sk, const struct mptcp_options_received *mp_opt, struct sock *ssk, @@ -3190,6 +3233,13 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, __mptcp_init_sock(nsk); +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + if (nsk->sk_family == AF_INET6) + mptcp_copy_ip6_options(nsk, sk); + else +#endif + mptcp_copy_ip_options(nsk, sk); + msk = mptcp_sk(nsk); msk->local_key = subflow_req->local_key; msk->token = subflow_req->token; @@ -3202,7 +3252,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, msk->write_seq = subflow_req->idsn + 1; msk->snd_nxt = msk->write_seq; msk->snd_una = msk->write_seq; - msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd; + msk->wnd_end = msk->snd_nxt + tcp_sk(ssk)->snd_wnd; msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq; if (mp_opt->suboptions & OPTIONS_MPTCP_MPC) { @@ -3299,9 +3349,6 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, newsk = new_mptcp_sock; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK); - } else { - MPTCP_INC_STATS(sock_net(sk), - MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK); } out: @@ -3341,10 +3388,10 @@ static void mptcp_destroy(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - /* clears msk->subflow, allowing the following to close - * even the initial subflow - */ mptcp_dispose_initial_subflow(msk); + + /* allow the following to close even the initial subflow */ + msk->free_first = 1; mptcp_destroy_common(msk, 0); sk_sockets_allocated_dec(sk); } @@ -3388,8 +3435,7 @@ static void mptcp_release_cb(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(sk); for (;;) { - unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED) | - msk->push_pending; + unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED); struct list_head join_list; if (!flags) @@ -3405,7 +3451,6 @@ static void mptcp_release_cb(struct sock *sk) * datapath acquires the msk socket spinlock while helding * the subflow socket lock */ - msk->push_pending = 0; msk->cb_flags &= ~flags; spin_unlock_bh(&sk->sk_lock.slock); @@ -3709,6 +3754,9 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) MPTCP_INC_STATS(sock_net(ssock->sk), MPTCP_MIB_TOKENFALLBACKINIT); mptcp_subflow_early_fallback(msk, subflow); } + + WRITE_ONCE(msk->write_seq, subflow->idsn); + WRITE_ONCE(msk->snd_nxt, subflow->idsn); if (likely(!__mptcp_check_fallback(msk))) MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVE); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 4ec8e0a81b5a437f3d57967d20b6607727683196..2bc37773e7803396bf3f25675f0e0340c3eeca76 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -272,7 +272,6 @@ struct mptcp_sock { int rmem_released; unsigned long flags; unsigned long cb_flags; - unsigned long push_pending; bool recovery; /* closing subflow write queue reinjected */ bool can_ack; bool fully_established; @@ -287,7 +286,8 @@ struct mptcp_sock { cork:1, nodelay:1, fastopening:1, - in_accept_queue:1; + in_accept_queue:1, + free_first:1; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; @@ -475,7 +475,6 @@ struct mptcp_subflow_context { can_ack : 1, /* only after processing the remote a key */ disposable : 1, /* ctx can be free at ulp release time */ stale : 1, /* unable to snd/rcv data, do not use for xmit */ - local_id_valid : 1, /* local_id is correctly initialized */ valid_csum_seen : 1; /* at least one csum validated */ enum mptcp_data_avail data_avail; u32 remote_nonce; @@ -483,7 +482,7 @@ struct mptcp_subflow_context { u32 local_nonce; u32 remote_token; u8 hmac[MPTCPOPT_HMAC_LEN]; - u8 local_id; + s16 local_id; /* if negative not initialized yet */ u8 remote_id; u8 reset_seen:1; u8 reset_transient:1; @@ -529,6 +528,7 @@ mptcp_subflow_ctx_reset(struct mptcp_subflow_context *subflow) { memset(&subflow->reset, 0, sizeof(subflow->reset)); subflow->request_mptcp = 1; + WRITE_ONCE(subflow->local_id, -1); } static inline u64 @@ -834,8 +834,6 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list); void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, struct list_head *rm_list); -int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, - struct mptcp_pm_addr_entry *entry); void mptcp_free_local_addr_list(struct mptcp_sock *msk); int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info); int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info); @@ -911,6 +909,15 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); +static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflow) +{ + int local_id = READ_ONCE(subflow->local_id); + + if (local_id < 0) + return 0; + return local_id; +} + void __init mptcp_pm_nl_init(void); void mptcp_pm_nl_work(struct mptcp_sock *msk); void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 45d20e20cfc00b142c520fda8bb3946b209d92bd..f1d422396b28b687d063430d00ecdb9be806a7a7 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -446,7 +446,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->backup = mp_opt.backup; subflow->thmac = mp_opt.thmac; subflow->remote_nonce = mp_opt.nonce; - subflow->remote_id = mp_opt.join_id; + WRITE_ONCE(subflow->remote_id, mp_opt.join_id); pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d", subflow, subflow->thmac, subflow->remote_nonce, subflow->backup); @@ -489,8 +489,8 @@ do_reset: static void subflow_set_local_id(struct mptcp_subflow_context *subflow, int local_id) { - subflow->local_id = local_id; - subflow->local_id_valid = 1; + WARN_ON_ONCE(local_id < 0 || local_id > 255); + WRITE_ONCE(subflow->local_id, local_id); } static int subflow_chk_local_id(struct sock *sk) @@ -499,7 +499,7 @@ static int subflow_chk_local_id(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(subflow->conn); int err; - if (likely(subflow->local_id_valid)) + if (likely(subflow->local_id >= 0)) return 0; err = mptcp_pm_get_local_id(msk, (struct sock_common *)sk); @@ -816,6 +816,8 @@ dispose_child: return child; fallback: + if (fallback) + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK); mptcp_subflow_drop_ctx(child); return child; } @@ -1477,7 +1479,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk, remote_token, local_id, remote_id); subflow->remote_token = remote_token; - subflow->remote_id = remote_id; + WRITE_ONCE(subflow->remote_id, remote_id); subflow->request_join = 1; subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP); mptcp_info2sockaddr(remote, &addr, ssk->sk_family); @@ -1630,6 +1632,7 @@ static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk, pr_debug("subflow=%p", ctx); ctx->tcp_sock = sk; + WRITE_ONCE(ctx->local_id, -1); return ctx; } @@ -1867,13 +1870,13 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->idsn = subflow_req->idsn; /* this is the first subflow, id is always 0 */ - new_ctx->local_id_valid = 1; + subflow_set_local_id(new_ctx, 0); } else if (subflow_req->mp_join) { new_ctx->ssn_offset = subflow_req->ssn_offset; new_ctx->mp_join = 1; new_ctx->fully_established = 1; new_ctx->backup = subflow_req->backup; - new_ctx->remote_id = subflow_req->remote_id; + WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id); new_ctx->token = subflow_req->token; new_ctx->thmac = subflow_req->thmac; diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 55a7f72d547cd94ea2a59b4d9b0706aa425b115c..edf92074221e2b31b4789d254d69473ac8de7503 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -707,6 +707,22 @@ void nf_conntrack_destroy(struct nf_conntrack *nfct) } EXPORT_SYMBOL(nf_conntrack_destroy); +void nf_ct_set_closing(struct nf_conntrack *nfct) +{ + const struct nf_ct_hook *ct_hook; + + if (!nfct) + return; + + rcu_read_lock(); + ct_hook = rcu_dereference(nf_ct_hook); + if (ct_hook) + ct_hook->set_closing(nfct); + + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(nf_ct_set_closing); + bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb) { diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index 26ab0e9612d82579b6e89c99704c5bbe063c0e1b..9523104a90da473e77afb93309c2eed7c5cf14e9 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -28,6 +28,7 @@ #define mtype_del IPSET_TOKEN(MTYPE, _del) #define mtype_list IPSET_TOKEN(MTYPE, _list) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) +#define mtype_cancel_gc IPSET_TOKEN(MTYPE, _cancel_gc) #define mtype MTYPE #define get_ext(set, map, id) ((map)->extensions + ((set)->dsize * (id))) @@ -57,9 +58,6 @@ mtype_destroy(struct ip_set *set) { struct mtype *map = set->data; - if (SET_WITH_TIMEOUT(set)) - del_timer_sync(&map->gc); - if (set->dsize && set->extensions & IPSET_EXT_DESTROY) mtype_ext_cleanup(set); ip_set_free(map->members); @@ -288,6 +286,15 @@ mtype_gc(struct timer_list *t) add_timer(&map->gc); } +static void +mtype_cancel_gc(struct ip_set *set) +{ + struct mtype *map = set->data; + + if (SET_WITH_TIMEOUT(set)) + del_timer_sync(&map->gc); +} + static const struct ip_set_type_variant mtype = { .kadt = mtype_kadt, .uadt = mtype_uadt, @@ -301,6 +308,7 @@ static const struct ip_set_type_variant mtype = { .head = mtype_head, .list = mtype_list, .same_set = mtype_same_set, + .cancel_gc = mtype_cancel_gc, }; #endif /* __IP_SET_BITMAP_IP_GEN_H */ diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index d47dfdcb899b05a0630909e5ecd3c647ce8e4222..f645da82d826e2d2113c527a6fc52deb8aa427ee 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1156,6 +1156,7 @@ static int ip_set_create(struct sk_buff *skb, const struct nfnl_info *info, return ret; cleanup: + set->variant->cancel_gc(set); set->variant->destroy(set); put_out: module_put(set->type->me); @@ -1184,6 +1185,14 @@ ip_set_destroy_set(struct ip_set *set) kfree(set); } +static void +ip_set_destroy_set_rcu(struct rcu_head *head) +{ + struct ip_set *set = container_of(head, struct ip_set, rcu); + + ip_set_destroy_set(set); +} + static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const attr[]) { @@ -1195,8 +1204,6 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, if (unlikely(protocol_min_failed(attr))) return -IPSET_ERR_PROTOCOL; - /* Must wait for flush to be really finished in list:set */ - rcu_barrier(); /* Commands are serialized and references are * protected by the ip_set_ref_lock. @@ -1208,8 +1215,10 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, * counter, so if it's already zero, we can proceed * without holding the lock. */ - read_lock_bh(&ip_set_ref_lock); if (!attr[IPSET_ATTR_SETNAME]) { + /* Must wait for flush to be really finished in list:set */ + rcu_barrier(); + read_lock_bh(&ip_set_ref_lock); for (i = 0; i < inst->ip_set_max; i++) { s = ip_set(inst, i); if (s && (s->ref || s->ref_netlink)) { @@ -1223,6 +1232,8 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, s = ip_set(inst, i); if (s) { ip_set(inst, i) = NULL; + /* Must cancel garbage collectors */ + s->variant->cancel_gc(s); ip_set_destroy_set(s); } } @@ -1230,6 +1241,9 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, inst->is_destroyed = false; } else { u32 flags = flag_exist(info->nlh); + u16 features = 0; + + read_lock_bh(&ip_set_ref_lock); s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]), &i); if (!s) { @@ -1240,10 +1254,16 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, ret = -IPSET_ERR_BUSY; goto out; } + features = s->type->features; ip_set(inst, i) = NULL; read_unlock_bh(&ip_set_ref_lock); - - ip_set_destroy_set(s); + if (features & IPSET_TYPE_NAME) { + /* Must wait for flush to be really finished */ + rcu_barrier(); + } + /* Must cancel garbage collectors */ + s->variant->cancel_gc(s); + call_rcu(&s->rcu, ip_set_destroy_set_rcu); } return 0; out: @@ -1396,9 +1416,6 @@ static int ip_set_swap(struct sk_buff *skb, const struct nfnl_info *info, ip_set(inst, to_id) = from; write_unlock_bh(&ip_set_ref_lock); - /* Make sure all readers of the old set pointers are completed. */ - synchronize_rcu(); - return 0; } @@ -2364,6 +2381,7 @@ ip_set_net_exit(struct net *net) set = ip_set(inst, i); if (set) { ip_set(inst, i) = NULL; + set->variant->cancel_gc(set); ip_set_destroy_set(set); } } @@ -2411,8 +2429,11 @@ ip_set_fini(void) { nf_unregister_sockopt(&so_set); nfnetlink_subsys_unregister(&ip_set_netlink_subsys); - unregister_pernet_subsys(&ip_set_net_ops); + + /* Wait for call_rcu() in destroy */ + rcu_barrier(); + pr_debug("these are the famous last words\n"); } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 7499192af58666151b51f86a0d03fe6509b97806..ef04e556aadb41f292866978c9792c71d7ccd6f6 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -210,6 +210,7 @@ htable_size(u8 hbits) #undef mtype_gc_do #undef mtype_gc #undef mtype_gc_init +#undef mtype_cancel_gc #undef mtype_variant #undef mtype_data_match @@ -254,6 +255,7 @@ htable_size(u8 hbits) #define mtype_gc_do IPSET_TOKEN(MTYPE, _gc_do) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) #define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init) +#define mtype_cancel_gc IPSET_TOKEN(MTYPE, _cancel_gc) #define mtype_variant IPSET_TOKEN(MTYPE, _variant) #define mtype_data_match IPSET_TOKEN(MTYPE, _data_match) @@ -417,7 +419,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) u32 i; for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference(hbucket(t, i)); + n = (__force struct hbucket *)hbucket(t, i); if (!n) continue; if (set->extensions & IPSET_EXT_DESTROY && ext_destroy) @@ -437,10 +439,7 @@ mtype_destroy(struct ip_set *set) struct htype *h = set->data; struct list_head *l, *lt; - if (SET_WITH_TIMEOUT(set)) - cancel_delayed_work_sync(&h->gc.dwork); - - mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true); + mtype_ahash_destroy(set, (__force struct htable *)h->table, true); list_for_each_safe(l, lt, &h->ad) { list_del(l); kfree(l); @@ -586,6 +585,15 @@ mtype_gc_init(struct htable_gc *gc) queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ); } +static void +mtype_cancel_gc(struct ip_set *set) +{ + struct htype *h = set->data; + + if (SET_WITH_TIMEOUT(set)) + cancel_delayed_work_sync(&h->gc.dwork); +} + static int mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags); @@ -1416,6 +1424,7 @@ static const struct ip_set_type_variant mtype_variant = { .uref = mtype_uref, .resize = mtype_resize, .same_set = mtype_same_set, + .cancel_gc = mtype_cancel_gc, .region_lock = true, }; diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 5a67f79665742c3a2907baa7acab75cdec6ea32f..6bc7019982b0580489bb44336bd1ff265221b192 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -426,9 +426,6 @@ list_set_destroy(struct ip_set *set) struct list_set *map = set->data; struct set_elem *e, *n; - if (SET_WITH_TIMEOUT(set)) - del_timer_sync(&map->gc); - list_for_each_entry_safe(e, n, &map->members, list) { list_del(&e->list); ip_set_put_byindex(map->net, e->id); @@ -545,6 +542,15 @@ list_set_same_set(const struct ip_set *a, const struct ip_set *b) a->extensions == b->extensions; } +static void +list_set_cancel_gc(struct ip_set *set) +{ + struct list_set *map = set->data; + + if (SET_WITH_TIMEOUT(set)) + del_timer_sync(&map->gc); +} + static const struct ip_set_type_variant set_variant = { .kadt = list_set_kadt, .uadt = list_set_uadt, @@ -558,6 +564,7 @@ static const struct ip_set_type_variant set_variant = { .head = list_set_head, .list = list_set_list, .same_set = list_set_same_set, + .cancel_gc = list_set_cancel_gc, }; static void diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index a0921adc31a9ffe7db09d18e7ae54213a79a8fd7..1e689c71412716e04f417cdb62d9fb56b730a1ab 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -126,7 +126,8 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, if (sctph->source != cp->vport || payload_csum || skb->ip_summed == CHECKSUM_PARTIAL) { sctph->source = cp->vport; - sctp_nat_csum(skb, sctph, sctphoff); + if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb)) + sctp_nat_csum(skb, sctph, sctphoff); } else { skb->ip_summed = CHECKSUM_UNNECESSARY; } @@ -174,7 +175,8 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, (skb->ip_summed == CHECKSUM_PARTIAL && !(skb_dst(skb)->dev->features & NETIF_F_SCTP_CRC))) { sctph->dest = cp->dport; - sctp_nat_csum(skb, sctph, sctphoff); + if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb)) + sctp_nat_csum(skb, sctph, sctphoff); } else if (skb->ip_summed != CHECKSUM_PARTIAL) { skb->ip_summed = CHECKSUM_UNNECESSARY; } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 7960262966094c5ba94f0b0b4470d109e5e80ec2..024f93fc8c0bb2b6fd6ee40ec48acc56a0ec8559 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2772,11 +2772,24 @@ err_cachep: return ret; } +static void nf_conntrack_set_closing(struct nf_conntrack *nfct) +{ + struct nf_conn *ct = nf_ct_to_nf_conn(nfct); + + switch (nf_ct_protonum(ct)) { + case IPPROTO_TCP: + nf_conntrack_tcp_set_closing(ct); + break; + } +} + static const struct nf_ct_hook nf_conntrack_hook = { .update = nf_conntrack_update, .destroy = nf_ct_destroy, .get_tuple_skb = nf_conntrack_get_tuple_skb, .attach = nf_conntrack_attach, + .set_closing = nf_conntrack_set_closing, + .confirm = __nf_conntrack_confirm, }; void nf_conntrack_init_end(void) diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c index e697a824b0018e1f1e26e3d547c1e80c6ca49e39..540d97715bd23d6f53f29fc7df39f09cd6b2f5c0 100644 --- a/net/netfilter/nf_conntrack_h323_asn1.c +++ b/net/netfilter/nf_conntrack_h323_asn1.c @@ -533,6 +533,8 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, /* Get fields bitmap */ if (nf_h323_error_boundary(bs, 0, f->sz)) return H323_ERROR_BOUND; + if (f->sz > 32) + return H323_ERROR_RANGE; bmp = get_bitmap(bs, f->sz); if (base) *(unsigned int *)base = bmp; @@ -589,6 +591,8 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, bmp2_len = get_bits(bs, 7) + 1; if (nf_h323_error_boundary(bs, 0, bmp2_len)) return H323_ERROR_BOUND; + if (bmp2_len > 32) + return H323_ERROR_RANGE; bmp2 = get_bitmap(bs, bmp2_len); bmp |= bmp2 >> f->sz; if (base) diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index c94a9971d790c1ff1f0308001ec20e98e905f62c..7ffd698497f2ad76ff0b66cc3706641a07559909 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -299,7 +299,7 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb, pr_debug("Setting vtag %x for secondary conntrack\n", sh->vtag); ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = sh->vtag; - } else { + } else if (sch->type == SCTP_CID_SHUTDOWN_ACK) { /* If it is a shutdown ack OOTB packet, we expect a return shutdown complete, otherwise an ABORT Sec 8.4 (5) and (8) */ pr_debug("Setting vtag %x for new conn OOTB\n", diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index e0092bf273fd0551c86b4c87fc082d0b60174e25..9480e638e5d15d4ce3c2a5f87f9425b4b8603ccc 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -913,6 +913,41 @@ static bool tcp_can_early_drop(const struct nf_conn *ct) return false; } +void nf_conntrack_tcp_set_closing(struct nf_conn *ct) +{ + enum tcp_conntrack old_state; + const unsigned int *timeouts; + u32 timeout; + + if (!nf_ct_is_confirmed(ct)) + return; + + spin_lock_bh(&ct->lock); + old_state = ct->proto.tcp.state; + ct->proto.tcp.state = TCP_CONNTRACK_CLOSE; + + if (old_state == TCP_CONNTRACK_CLOSE || + test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status)) { + spin_unlock_bh(&ct->lock); + return; + } + + timeouts = nf_ct_timeout_lookup(ct); + if (!timeouts) { + const struct nf_tcp_net *tn; + + tn = nf_tcp_pernet(nf_ct_net(ct)); + timeouts = tn->timeouts; + } + + timeout = timeouts[TCP_CONNTRACK_CLOSE]; + WRITE_ONCE(ct->timeout, timeout + nfct_time_stamp); + + spin_unlock_bh(&ct->lock); + + nf_conntrack_event_cache(IPCT_PROTOINFO, ct); +} + static void nf_ct_tcp_state_reset(struct ip_ct_tcp_state *state) { state->td_end = 0; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index c1d99cb370b441b5512f3bab050664e6dee4a629..99195cf6b265757e749fd606acc10d2c41ec085c 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -87,12 +87,22 @@ static u32 flow_offload_dst_cookie(struct flow_offload_tuple *flow_tuple) return 0; } +static struct dst_entry *nft_route_dst_fetch(struct nf_flow_route *route, + enum flow_offload_tuple_dir dir) +{ + struct dst_entry *dst = route->tuple[dir].dst; + + route->tuple[dir].dst = NULL; + + return dst; +} + static int flow_offload_fill_route(struct flow_offload *flow, - const struct nf_flow_route *route, + struct nf_flow_route *route, enum flow_offload_tuple_dir dir) { struct flow_offload_tuple *flow_tuple = &flow->tuplehash[dir].tuple; - struct dst_entry *dst = route->tuple[dir].dst; + struct dst_entry *dst = nft_route_dst_fetch(route, dir); int i, j = 0; switch (flow_tuple->l3proto) { @@ -122,12 +132,10 @@ static int flow_offload_fill_route(struct flow_offload *flow, ETH_ALEN); flow_tuple->out.ifidx = route->tuple[dir].out.ifindex; flow_tuple->out.hw_ifidx = route->tuple[dir].out.hw_ifindex; + dst_release(dst); break; case FLOW_OFFLOAD_XMIT_XFRM: case FLOW_OFFLOAD_XMIT_NEIGH: - if (!dst_hold_safe(route->tuple[dir].dst)) - return -1; - flow_tuple->dst_cache = dst; flow_tuple->dst_cookie = flow_offload_dst_cookie(flow_tuple); break; @@ -148,27 +156,12 @@ static void nft_flow_dst_release(struct flow_offload *flow, dst_release(flow->tuplehash[dir].tuple.dst_cache); } -int flow_offload_route_init(struct flow_offload *flow, - const struct nf_flow_route *route) +void flow_offload_route_init(struct flow_offload *flow, + struct nf_flow_route *route) { - int err; - - err = flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL); - if (err < 0) - return err; - - err = flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY); - if (err < 0) - goto err_route_reply; - + flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL); + flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY); flow->type = NF_FLOW_OFFLOAD_ROUTE; - - return 0; - -err_route_reply: - nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_ORIGINAL); - - return err; } EXPORT_SYMBOL_GPL(flow_offload_route_init); diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 9505f9d188ff257a8ca35f30ee111c2f19805a5a..6eef15648b7b0853fb249288bf4545dca3a2cf85 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -21,7 +21,8 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb, proto = veth->h_vlan_encapsulated_proto; break; case htons(ETH_P_PPP_SES): - proto = nf_flow_pppoe_proto(skb); + if (!nf_flow_pppoe_proto(skb, &proto)) + return NF_ACCEPT; break; default: proto = skb->protocol; diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 6feaac9ab05c8667f87a30ffe8902b81e59a78c1..22bc0e3d8a0b5953373f6d42d44790bacfa96563 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -156,7 +156,7 @@ static void nf_flow_tuple_encap(struct sk_buff *skb, tuple->encap[i].proto = skb->protocol; break; case htons(ETH_P_PPP_SES): - phdr = (struct pppoe_hdr *)skb_mac_header(skb); + phdr = (struct pppoe_hdr *)skb_network_header(skb); tuple->encap[i].id = ntohs(phdr->sid); tuple->encap[i].proto = skb->protocol; break; @@ -267,10 +267,11 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, return NF_STOLEN; } -static bool nf_flow_skb_encap_protocol(const struct sk_buff *skb, __be16 proto, +static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto, u32 *offset) { struct vlan_ethhdr *veth; + __be16 inner_proto; switch (skb->protocol) { case htons(ETH_P_8021Q): @@ -281,7 +282,8 @@ static bool nf_flow_skb_encap_protocol(const struct sk_buff *skb, __be16 proto, } break; case htons(ETH_P_PPP_SES): - if (nf_flow_pppoe_proto(skb) == proto) { + if (nf_flow_pppoe_proto(skb, &inner_proto) && + inner_proto == proto) { *offset += PPPOE_SES_HLEN; return true; } @@ -310,7 +312,7 @@ static void nf_flow_encap_pop(struct sk_buff *skb, skb_reset_network_header(skb); break; case htons(ETH_P_PPP_SES): - skb->protocol = nf_flow_pppoe_proto(skb); + skb->protocol = __nf_flow_pppoe_proto(skb); skb_pull(skb, PPPOE_SES_HLEN); skb_reset_network_header(skb); break; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 49acb89ba9c566075ed29f617779870b75eede8f..1c4b7a8ec2cc61cc08fa9ebe068fc30edd88a995 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -686,15 +686,16 @@ static int nft_delobj(struct nft_ctx *ctx, struct nft_object *obj) return err; } -static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, - struct nft_flowtable *flowtable) +static struct nft_trans * +nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, + struct nft_flowtable *flowtable) { struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_flowtable)); if (trans == NULL) - return -ENOMEM; + return ERR_PTR(-ENOMEM); if (msg_type == NFT_MSG_NEWFLOWTABLE) nft_activate_next(ctx->net, flowtable); @@ -703,22 +704,22 @@ static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, nft_trans_flowtable(trans) = flowtable; nft_trans_commit_list_add_tail(ctx->net, trans); - return 0; + return trans; } static int nft_delflowtable(struct nft_ctx *ctx, struct nft_flowtable *flowtable) { - int err; + struct nft_trans *trans; - err = nft_trans_flowtable_add(ctx, NFT_MSG_DELFLOWTABLE, flowtable); - if (err < 0) - return err; + trans = nft_trans_flowtable_add(ctx, NFT_MSG_DELFLOWTABLE, flowtable); + if (IS_ERR(trans)) + return PTR_ERR(trans); nft_deactivate_next(ctx->net, flowtable); nft_use_dec(&ctx->table->use); - return err; + return 0; } static void __nft_reg_track_clobber(struct nft_regs_track *track, u8 dreg) @@ -1191,6 +1192,24 @@ static void nf_tables_table_disable(struct net *net, struct nft_table *table) #define __NFT_TABLE_F_UPDATE (__NFT_TABLE_F_WAS_DORMANT | \ __NFT_TABLE_F_WAS_AWAKEN) +static bool nft_table_pending_update(const struct nft_ctx *ctx) +{ + struct nftables_pernet *nft_net = nft_pernet(ctx->net); + struct nft_trans *trans; + + if (ctx->table->flags & __NFT_TABLE_F_UPDATE) + return true; + + list_for_each_entry(trans, &nft_net->commit_list, list) { + if (trans->ctx.table == ctx->table && + trans->msg_type == NFT_MSG_DELCHAIN && + nft_is_base_chain(trans->ctx.chain)) + return true; + } + + return false; +} + static int nf_tables_updtable(struct nft_ctx *ctx) { struct nft_trans *trans; @@ -1204,7 +1223,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx) if (flags & ~NFT_TABLE_F_MASK) return -EOPNOTSUPP; - if (flags == ctx->table->flags) + if (flags == (ctx->table->flags & NFT_TABLE_F_MASK)) return 0; if ((nft_table_has_owner(ctx->table) && @@ -1214,7 +1233,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx) return -EOPNOTSUPP; /* No dormant off/on/off/on games in single transaction */ - if (ctx->table->flags & __NFT_TABLE_F_UPDATE) + if (nft_table_pending_update(ctx)) return -EINVAL; trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, @@ -1245,6 +1264,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx) return 0; err_register_hooks: + ctx->table->flags |= NFT_TABLE_F_DORMANT; nft_trans_destroy(trans); return ret; } @@ -2057,7 +2077,7 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net, struct nft_hook *hook; int err; - hook = kmalloc(sizeof(struct nft_hook), GFP_KERNEL_ACCOUNT); + hook = kzalloc(sizeof(struct nft_hook), GFP_KERNEL_ACCOUNT); if (!hook) { err = -ENOMEM; goto err_hook_alloc; @@ -2370,6 +2390,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, struct nft_stats __percpu *stats = NULL; struct nft_chain_hook hook; + if (table->flags & __NFT_TABLE_F_UPDATE) + return -EINVAL; + if (flags & NFT_CHAIN_BINDING) return -EOPNOTSUPP; @@ -2458,19 +2481,15 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, RCU_INIT_POINTER(chain->blob_gen_0, blob); RCU_INIT_POINTER(chain->blob_gen_1, blob); - err = nf_tables_register_hook(net, table, chain); - if (err < 0) - goto err_destroy_chain; - if (!nft_use_inc(&table->use)) { err = -EMFILE; - goto err_use; + goto err_destroy_chain; } trans = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN); if (IS_ERR(trans)) { err = PTR_ERR(trans); - goto err_unregister_hook; + goto err_trans; } nft_trans_chain_policy(trans) = NFT_CHAIN_POLICY_UNSET; @@ -2478,17 +2497,22 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, nft_trans_chain_policy(trans) = policy; err = nft_chain_add(table, chain); - if (err < 0) { - nft_trans_destroy(trans); - goto err_unregister_hook; - } + if (err < 0) + goto err_chain_add; + + /* This must be LAST to ensure no packets are walking over this chain. */ + err = nf_tables_register_hook(net, table, chain); + if (err < 0) + goto err_register_hook; return 0; -err_unregister_hook: +err_register_hook: + nft_chain_del(chain); +err_chain_add: + nft_trans_destroy(trans); +err_trans: nft_use_dec_restore(&table->use); -err_use: - nf_tables_unregister_hook(net, table, chain); err_destroy_chain: nf_tables_chain_destroy(ctx); @@ -2867,7 +2891,7 @@ static const struct nft_expr_type *__nft_expr_type_get(u8 family, { const struct nft_expr_type *type, *candidate = NULL; - list_for_each_entry(type, &nf_tables_expressions, list) { + list_for_each_entry_rcu(type, &nf_tables_expressions, list) { if (!nla_strcmp(nla, type->name)) { if (!type->family && !candidate) candidate = type; @@ -2899,9 +2923,13 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net, if (nla == NULL) return ERR_PTR(-EINVAL); + rcu_read_lock(); type = __nft_expr_type_get(family, nla); - if (type != NULL && try_module_get(type->owner)) + if (type != NULL && try_module_get(type->owner)) { + rcu_read_unlock(); return type; + } + rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES @@ -4708,6 +4736,12 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if ((flags & (NFT_SET_EVAL | NFT_SET_OBJECT)) == (NFT_SET_EVAL | NFT_SET_OBJECT)) return -EOPNOTSUPP; + if ((flags & (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT | NFT_SET_EVAL)) == + (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT)) + return -EOPNOTSUPP; + if ((flags & (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) == + (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) + return -EOPNOTSUPP; } desc.dtype = 0; @@ -4749,6 +4783,9 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; + if (flags & NFT_SET_ANONYMOUS) + return -EOPNOTSUPP; + err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &desc.timeout); if (err) return err; @@ -4757,6 +4794,10 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (nla[NFTA_SET_GC_INTERVAL] != NULL) { if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; + + if (flags & NFT_SET_ANONYMOUS) + return -EOPNOTSUPP; + desc.gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL])); } @@ -5122,6 +5163,7 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) { list_del_rcu(&set->list); + set->dead = 1; if (event) nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_KERNEL); @@ -7133,7 +7175,7 @@ static const struct nft_object_type *__nft_obj_type_get(u32 objtype, u8 family) { const struct nft_object_type *type; - list_for_each_entry(type, &nf_tables_objects, list) { + list_for_each_entry_rcu(type, &nf_tables_objects, list) { if (type->family != NFPROTO_UNSPEC && type->family != family) continue; @@ -7149,9 +7191,13 @@ nft_obj_type_get(struct net *net, u32 objtype, u8 family) { const struct nft_object_type *type; + rcu_read_lock(); type = __nft_obj_type_get(objtype, family); - if (type != NULL && try_module_get(type->owner)) + if (type != NULL && try_module_get(type->owner)) { + rcu_read_unlock(); return type; + } + rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES @@ -7821,11 +7867,12 @@ static int nft_flowtable_parse_hook(const struct nft_ctx *ctx, return err; } +/* call under rcu_read_lock */ static const struct nf_flowtable_type *__nft_flowtable_type_get(u8 family) { const struct nf_flowtable_type *type; - list_for_each_entry(type, &nf_tables_flowtables, list) { + list_for_each_entry_rcu(type, &nf_tables_flowtables, list) { if (family == type->family) return type; } @@ -7837,9 +7884,13 @@ nft_flowtable_type_get(struct net *net, u8 family) { const struct nf_flowtable_type *type; + rcu_read_lock(); type = __nft_flowtable_type_get(family); - if (type != NULL && try_module_get(type->owner)) + if (type != NULL && try_module_get(type->owner)) { + rcu_read_unlock(); return type; + } + rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES @@ -7937,7 +7988,7 @@ err_unregister_net_hooks: return err; } -static void nft_flowtable_hooks_destroy(struct list_head *hook_list) +static void nft_hooks_destroy(struct list_head *hook_list) { struct nft_hook *hook, *next; @@ -8030,9 +8081,9 @@ static int nf_tables_newflowtable(struct sk_buff *skb, u8 family = info->nfmsg->nfgen_family; const struct nf_flowtable_type *type; struct nft_flowtable *flowtable; - struct nft_hook *hook, *next; struct net *net = info->net; struct nft_table *table; + struct nft_trans *trans; struct nft_ctx ctx; int err; @@ -8112,34 +8163,34 @@ static int nf_tables_newflowtable(struct sk_buff *skb, err = nft_flowtable_parse_hook(&ctx, nla[NFTA_FLOWTABLE_HOOK], &flowtable_hook, flowtable, true); if (err < 0) - goto err4; + goto err_flowtable_parse_hooks; list_splice(&flowtable_hook.list, &flowtable->hook_list); flowtable->data.priority = flowtable_hook.priority; flowtable->hooknum = flowtable_hook.num; + trans = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable); + if (IS_ERR(trans)) { + err = PTR_ERR(trans); + goto err_flowtable_trans; + } + + /* This must be LAST to ensure no packets are walking over this flowtable. */ err = nft_register_flowtable_net_hooks(ctx.net, table, &flowtable->hook_list, flowtable); - if (err < 0) { - nft_flowtable_hooks_destroy(&flowtable->hook_list); - goto err4; - } - - err = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable); if (err < 0) - goto err5; + goto err_flowtable_hooks; list_add_tail_rcu(&flowtable->list, &table->flowtables); return 0; -err5: - list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { - nft_unregister_flowtable_hook(net, flowtable, hook); - list_del_rcu(&hook->list); - kfree_rcu(hook, rcu); - } -err4: + +err_flowtable_hooks: + nft_trans_destroy(trans); +err_flowtable_trans: + nft_hooks_destroy(&flowtable->hook_list); +err_flowtable_parse_hooks: flowtable->data.type->free(&flowtable->data); err3: module_put(type->owner); @@ -8892,7 +8943,7 @@ static void nft_commit_release(struct nft_trans *trans) break; case NFT_MSG_DELFLOWTABLE: if (nft_trans_flowtable_update(trans)) - nft_flowtable_hooks_destroy(&nft_trans_flowtable_hooks(trans)); + nft_hooks_destroy(&nft_trans_flowtable_hooks(trans)); else nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); break; @@ -9849,7 +9900,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) break; case NFT_MSG_NEWFLOWTABLE: if (nft_trans_flowtable_update(trans)) - nft_flowtable_hooks_destroy(&nft_trans_flowtable_hooks(trans)); + nft_hooks_destroy(&nft_trans_flowtable_hooks(trans)); else nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); break; @@ -9877,10 +9928,11 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) struct nft_trans *trans, *next; LIST_HEAD(set_update_list); struct nft_trans_elem *te; + int err = 0; if (action == NFNL_ABORT_VALIDATE && nf_tables_validate(net) < 0) - return -EAGAIN; + err = -EAGAIN; list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list, list) { @@ -10051,12 +10103,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nf_tables_abort_release(trans); } - if (action == NFNL_ABORT_AUTOLOAD) - nf_tables_module_autoload(net); - else - nf_tables_module_autoload_cleanup(net); - - return 0; + return err; } static int nf_tables_abort(struct net *net, struct sk_buff *skb, @@ -10070,6 +10117,16 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb, ret = __nf_tables_abort(net, action); nft_gc_seq_end(nft_net, gc_seq); + WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); + + /* module autoload needs to happen after GC sequence update because it + * temporarily releases and grabs mutex again. + */ + if (action == NFNL_ABORT_AUTOLOAD) + nf_tables_module_autoload(net); + else + nf_tables_module_autoload_cleanup(net); + mutex_unlock(&nft_net->commit_mutex); return ret; @@ -10867,9 +10924,10 @@ static void __net_exit nf_tables_exit_net(struct net *net) gc_seq = nft_gc_seq_begin(nft_net); - if (!list_empty(&nft_net->commit_list) || - !list_empty(&nft_net->module_list)) - __nf_tables_abort(net, NFNL_ABORT_NONE); + WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); + + if (!list_empty(&nft_net->module_list)) + nf_tables_module_autoload_cleanup(net); __nft_release_tables(net); @@ -10961,6 +11019,7 @@ static void __exit nf_tables_module_exit(void) unregister_netdevice_notifier(&nf_tables_flowtable_notifier); nft_chain_filter_fini(); nft_chain_route_fini(); + nf_tables_trans_destroy_flush_work(); unregister_pernet_subsys(&nf_tables_net_ops); cancel_work_sync(&trans_gc_work); cancel_work_sync(&trans_destroy_work); diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 274b6f7e6bb57e4f270262ef923ebf8d7f1cf02c..d170758a1eb5d08929cc4cd8e8acd350e793524e 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -338,7 +338,9 @@ static void nft_netdev_event(unsigned long event, struct net_device *dev, return; if (n > 1) { - nf_unregister_net_hook(ctx->net, &found->ops); + if (!(ctx->chain->table->flags & NFT_TABLE_F_DORMANT)) + nf_unregister_net_hook(ctx->net, &found->ops); + list_del_rcu(&found->list); kfree_rcu(found, rcu); return; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 6952da7dfc02cd687b1de013744de5f5b1d5fc99..e4b8c02c5e6ae83edfeea5cebcd40314c74bd24c 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -135,7 +135,7 @@ static void nft_target_eval_bridge(const struct nft_expr *expr, static const struct nla_policy nft_target_policy[NFTA_TARGET_MAX + 1] = { [NFTA_TARGET_NAME] = { .type = NLA_NUL_STRING }, - [NFTA_TARGET_REV] = { .type = NLA_U32 }, + [NFTA_TARGET_REV] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_TARGET_INFO] = { .type = NLA_BINARY }, }; @@ -200,6 +200,7 @@ static const struct nla_policy nft_rule_compat_policy[NFTA_RULE_COMPAT_MAX + 1] static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv) { struct nlattr *tb[NFTA_RULE_COMPAT_MAX+1]; + u32 l4proto; u32 flags; int err; @@ -212,12 +213,18 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv) return -EINVAL; flags = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_FLAGS])); - if (flags & ~NFT_RULE_COMPAT_F_MASK) + if (flags & NFT_RULE_COMPAT_F_UNUSED || + flags & ~NFT_RULE_COMPAT_F_MASK) return -EINVAL; if (flags & NFT_RULE_COMPAT_F_INV) *inv = true; - *proto = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO])); + l4proto = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO])); + if (l4proto > U16_MAX) + return -EINVAL; + + *proto = l4proto; + return 0; } @@ -351,10 +358,20 @@ static int nft_target_validate(const struct nft_ctx *ctx, if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET && ctx->family != NFPROTO_BRIDGE && ctx->family != NFPROTO_ARP) return -EOPNOTSUPP; + ret = nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING)); + if (ret) + return ret; + if (nft_is_base_chain(ctx->chain)) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); @@ -418,7 +435,7 @@ static void nft_match_eval(const struct nft_expr *expr, static const struct nla_policy nft_match_policy[NFTA_MATCH_MAX + 1] = { [NFTA_MATCH_NAME] = { .type = NLA_NUL_STRING }, - [NFTA_MATCH_REV] = { .type = NLA_U32 }, + [NFTA_MATCH_REV] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_MATCH_INFO] = { .type = NLA_BINARY }, }; @@ -600,10 +617,20 @@ static int nft_match_validate(const struct nft_ctx *ctx, if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET && ctx->family != NFPROTO_BRIDGE && ctx->family != NFPROTO_ARP) return -EOPNOTSUPP; + ret = nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING)); + if (ret) + return ret; + if (nft_is_base_chain(ctx->chain)) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); @@ -721,7 +748,7 @@ out_put: static const struct nla_policy nfnl_compat_policy_get[NFTA_COMPAT_MAX+1] = { [NFTA_COMPAT_NAME] = { .type = NLA_NUL_STRING, .len = NFT_COMPAT_NAME_MAX-1 }, - [NFTA_COMPAT_REV] = { .type = NLA_U32 }, + [NFTA_COMPAT_REV] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_COMPAT_TYPE] = { .type = NLA_U32 }, }; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 1101665f5253768fc85230e0650634be217c60af..2bfe3cdfbd581922dc2d61b03b8320a0f967006c 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -484,6 +484,9 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, break; #endif case NFT_CT_ID: + if (tb[NFTA_CT_DIRECTION]) + return -EINVAL; + len = sizeof(u32); break; default: @@ -1234,14 +1237,13 @@ static int nft_ct_expect_obj_init(const struct nft_ctx *ctx, switch (priv->l3num) { case NFPROTO_IPV4: case NFPROTO_IPV6: - if (priv->l3num != ctx->family) - return -EINVAL; + if (priv->l3num == ctx->family || ctx->family == NFPROTO_INET) + break; - fallthrough; - case NFPROTO_INET: - break; + return -EINVAL; + case NFPROTO_INET: /* tuple.src.l3num supports NFPROTO_IPV4/6 only */ default: - return -EOPNOTSUPP; + return -EAFNOSUPPORT; } priv->l4proto = nla_get_u8(tb[NFTA_CT_EXPECT_L4PROTO]); diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 3d9f6dda5aeb20f40d72a27b51b9f5a8ac8303e9..7a8707632a8157a236c1795b52fa2e8cdbd6b77e 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -250,9 +250,14 @@ static int nft_flow_route(const struct nft_pktinfo *pkt, break; } + if (!dst_hold_safe(this_dst)) + return -ENOENT; + nf_route(nft_net(pkt), &other_dst, &fl, false, nft_pf(pkt)); - if (!other_dst) + if (!other_dst) { + dst_release(this_dst); return -ENOENT; + } nft_default_forward_path(route, this_dst, dir); nft_default_forward_path(route, other_dst, !dir); @@ -349,8 +354,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, if (!flow) goto err_flow_alloc; - if (flow_offload_route_init(flow, &route) < 0) - goto err_flow_add; + flow_offload_route_init(flow, &route); if (tcph) { ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; @@ -361,12 +365,12 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, if (ret < 0) goto err_flow_add; - dst_release(route.tuple[!dir].dst); return; err_flow_add: flow_offload_free(flow); err_flow_alloc: + dst_release(route.tuple[dir].dst); dst_release(route.tuple[!dir].dst); err_flow_route: clear_bit(IPS_OFFLOAD_BIT, &ct->status); diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 4e1cc31729b803b612d7eca9fde3f788a74eae7e..2299ced939c47fdfbc72dc1e0d746b82298e6d71 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -342,9 +342,6 @@ #include "nft_set_pipapo_avx2.h" #include "nft_set_pipapo.h" -/* Current working bitmap index, toggled between field matches */ -static DEFINE_PER_CPU(bool, nft_pipapo_scratch_index); - /** * pipapo_refill() - For each set bit, set bits from selected mapping table item * @map: Bitmap to be scanned for set bits @@ -412,6 +409,7 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) { struct nft_pipapo *priv = nft_set_priv(set); + struct nft_pipapo_scratch *scratch; unsigned long *res_map, *fill_map; u8 genmask = nft_genmask_cur(net); const u8 *rp = (const u8 *)key; @@ -422,15 +420,17 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, local_bh_disable(); - map_index = raw_cpu_read(nft_pipapo_scratch_index); - m = rcu_dereference(priv->match); if (unlikely(!m || !*raw_cpu_ptr(m->scratch))) goto out; - res_map = *raw_cpu_ptr(m->scratch) + (map_index ? m->bsize_max : 0); - fill_map = *raw_cpu_ptr(m->scratch) + (map_index ? 0 : m->bsize_max); + scratch = *raw_cpu_ptr(m->scratch); + + map_index = scratch->map_index; + + res_map = scratch->map + (map_index ? m->bsize_max : 0); + fill_map = scratch->map + (map_index ? 0 : m->bsize_max); memset(res_map, 0xff, m->bsize_max * sizeof(*res_map)); @@ -460,7 +460,7 @@ next_match: b = pipapo_refill(res_map, f->bsize, f->rules, fill_map, f->mt, last); if (b < 0) { - raw_cpu_write(nft_pipapo_scratch_index, map_index); + scratch->map_index = map_index; local_bh_enable(); return false; @@ -477,7 +477,7 @@ next_match: * current inactive bitmap is clean and can be reused as * *next* bitmap (not initial) for the next packet. */ - raw_cpu_write(nft_pipapo_scratch_index, map_index); + scratch->map_index = map_index; local_bh_enable(); return true; @@ -1101,6 +1101,25 @@ static void pipapo_map(struct nft_pipapo_match *m, f->mt[map[i].to + j].e = e; } +/** + * pipapo_free_scratch() - Free per-CPU map at original (not aligned) address + * @m: Matching data + * @cpu: CPU number + */ +static void pipapo_free_scratch(const struct nft_pipapo_match *m, unsigned int cpu) +{ + struct nft_pipapo_scratch *s; + void *mem; + + s = *per_cpu_ptr(m->scratch, cpu); + if (!s) + return; + + mem = s; + mem -= s->align_off; + kfree(mem); +} + /** * pipapo_realloc_scratch() - Reallocate scratch maps for partial match results * @clone: Copy of matching data with pending insertions and deletions @@ -1114,12 +1133,13 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone, int i; for_each_possible_cpu(i) { - unsigned long *scratch; + struct nft_pipapo_scratch *scratch; #ifdef NFT_PIPAPO_ALIGN - unsigned long *scratch_aligned; + void *scratch_aligned; + u32 align_off; #endif - - scratch = kzalloc_node(bsize_max * sizeof(*scratch) * 2 + + scratch = kzalloc_node(struct_size(scratch, map, + bsize_max * 2) + NFT_PIPAPO_ALIGN_HEADROOM, GFP_KERNEL, cpu_to_node(i)); if (!scratch) { @@ -1133,14 +1153,25 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone, return -ENOMEM; } - kfree(*per_cpu_ptr(clone->scratch, i)); - - *per_cpu_ptr(clone->scratch, i) = scratch; + pipapo_free_scratch(clone, i); #ifdef NFT_PIPAPO_ALIGN - scratch_aligned = NFT_PIPAPO_LT_ALIGN(scratch); - *per_cpu_ptr(clone->scratch_aligned, i) = scratch_aligned; + /* Align &scratch->map (not the struct itself): the extra + * %NFT_PIPAPO_ALIGN_HEADROOM bytes passed to kzalloc_node() + * above guarantee we can waste up to those bytes in order + * to align the map field regardless of its offset within + * the struct. + */ + BUILD_BUG_ON(offsetof(struct nft_pipapo_scratch, map) > NFT_PIPAPO_ALIGN_HEADROOM); + + scratch_aligned = NFT_PIPAPO_LT_ALIGN(&scratch->map); + scratch_aligned -= offsetof(struct nft_pipapo_scratch, map); + align_off = scratch_aligned - (void *)scratch; + + scratch = scratch_aligned; + scratch->align_off = align_off; #endif + *per_cpu_ptr(clone->scratch, i) = scratch; } return 0; @@ -1294,11 +1325,6 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old) if (!new->scratch) goto out_scratch; -#ifdef NFT_PIPAPO_ALIGN - new->scratch_aligned = alloc_percpu(*new->scratch_aligned); - if (!new->scratch_aligned) - goto out_scratch; -#endif for_each_possible_cpu(i) *per_cpu_ptr(new->scratch, i) = NULL; @@ -1350,10 +1376,7 @@ out_lt: } out_scratch_realloc: for_each_possible_cpu(i) - kfree(*per_cpu_ptr(new->scratch, i)); -#ifdef NFT_PIPAPO_ALIGN - free_percpu(new->scratch_aligned); -#endif + pipapo_free_scratch(new, i); out_scratch: free_percpu(new->scratch); kfree(new); @@ -1638,13 +1661,9 @@ static void pipapo_free_match(struct nft_pipapo_match *m) int i; for_each_possible_cpu(i) - kfree(*per_cpu_ptr(m->scratch, i)); + pipapo_free_scratch(m, i); -#ifdef NFT_PIPAPO_ALIGN - free_percpu(m->scratch_aligned); -#endif free_percpu(m->scratch); - pipapo_free_fields(m); kfree(m); @@ -1975,6 +1994,8 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, rules_fx = rules_f0; nft_pipapo_for_each_field(f, i, m) { + bool last = i == m->field_count - 1; + if (!pipapo_match_field(f, start, rules_fx, match_start, match_end)) break; @@ -1987,16 +2008,18 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, match_start += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); match_end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); - } - if (i == m->field_count) { - priv->dirty = true; - pipapo_drop(m, rulemap); - return; + if (last && f->mt[rulemap[i].to].e == e) { + priv->dirty = true; + pipapo_drop(m, rulemap); + return; + } } first_rule += rules_f0; } + + WARN_ON_ONCE(1); /* elem_priv not found */ } /** @@ -2132,7 +2155,7 @@ static int nft_pipapo_init(const struct nft_set *set, m->field_count = field_count; m->bsize_max = 0; - m->scratch = alloc_percpu(unsigned long *); + m->scratch = alloc_percpu(struct nft_pipapo_scratch *); if (!m->scratch) { err = -ENOMEM; goto out_scratch; @@ -2140,16 +2163,6 @@ static int nft_pipapo_init(const struct nft_set *set, for_each_possible_cpu(i) *per_cpu_ptr(m->scratch, i) = NULL; -#ifdef NFT_PIPAPO_ALIGN - m->scratch_aligned = alloc_percpu(unsigned long *); - if (!m->scratch_aligned) { - err = -ENOMEM; - goto out_free; - } - for_each_possible_cpu(i) - *per_cpu_ptr(m->scratch_aligned, i) = NULL; -#endif - rcu_head_init(&m->rcu); nft_pipapo_for_each_field(f, i, m) { @@ -2180,9 +2193,6 @@ static int nft_pipapo_init(const struct nft_set *set, return 0; out_free: -#ifdef NFT_PIPAPO_ALIGN - free_percpu(m->scratch_aligned); -#endif free_percpu(m->scratch); out_scratch: kfree(m); @@ -2234,13 +2244,8 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, if (m) { rcu_barrier(); - nft_set_pipapo_match_destroy(ctx, set, m); - -#ifdef NFT_PIPAPO_ALIGN - free_percpu(m->scratch_aligned); -#endif for_each_possible_cpu(cpu) - kfree(*per_cpu_ptr(m->scratch, cpu)); + pipapo_free_scratch(m, cpu); free_percpu(m->scratch); pipapo_free_fields(m); kfree(m); @@ -2250,14 +2255,10 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, if (priv->clone) { m = priv->clone; - if (priv->dirty) - nft_set_pipapo_match_destroy(ctx, set, m); + nft_set_pipapo_match_destroy(ctx, set, m); -#ifdef NFT_PIPAPO_ALIGN - free_percpu(priv->clone->scratch_aligned); -#endif for_each_possible_cpu(cpu) - kfree(*per_cpu_ptr(priv->clone->scratch, cpu)); + pipapo_free_scratch(priv->clone, cpu); free_percpu(priv->clone->scratch); pipapo_free_fields(priv->clone); diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index 25a75591583ebec982a53a67135721c7f4902047..30a3d092cd841cf0b5faeb3e8c2dda9b46ea0549 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -130,21 +130,29 @@ struct nft_pipapo_field { union nft_pipapo_map_bucket *mt; }; +/** + * struct nft_pipapo_scratch - percpu data used for lookup and matching + * @map_index: Current working bitmap index, toggled between field matches + * @align_off: Offset to get the originally allocated address + * @map: store partial matching results during lookup + */ +struct nft_pipapo_scratch { + u8 map_index; + u32 align_off; + unsigned long map[]; +}; + /** * struct nft_pipapo_match - Data used for lookup and matching * @field_count Amount of fields in set * @scratch: Preallocated per-CPU maps for partial matching results - * @scratch_aligned: Version of @scratch aligned to NFT_PIPAPO_ALIGN bytes * @bsize_max: Maximum lookup table bucket size of all fields, in longs * @rcu Matching data is swapped on commits * @f: Fields, with lookup and mapping tables */ struct nft_pipapo_match { int field_count; -#ifdef NFT_PIPAPO_ALIGN - unsigned long * __percpu *scratch_aligned; -#endif - unsigned long * __percpu *scratch; + struct nft_pipapo_scratch * __percpu *scratch; size_t bsize_max; struct rcu_head rcu; struct nft_pipapo_field f[]; diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index 52e0d026d30ad2c92f63f589727cdc0b39d7092b..a3a8ddca991894b28aa1a1cd7c84ba0380366b5f 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -57,7 +57,7 @@ /* Jump to label if @reg is zero */ #define NFT_PIPAPO_AVX2_NOMATCH_GOTO(reg, label) \ - asm_volatile_goto("vptest %%ymm" #reg ", %%ymm" #reg ";" \ + asm goto("vptest %%ymm" #reg ", %%ymm" #reg ";" \ "je %l[" #label "]" : : : : label) /* Store 256 bits from YMM register into memory. Contrary to bucket load @@ -71,9 +71,6 @@ #define NFT_PIPAPO_AVX2_ZERO(reg) \ asm volatile("vpxor %ymm" #reg ", %ymm" #reg ", %ymm" #reg) -/* Current working bitmap index, toggled between field matches */ -static DEFINE_PER_CPU(bool, nft_pipapo_avx2_scratch_index); - /** * nft_pipapo_avx2_prepare() - Prepare before main algorithm body * @@ -1120,11 +1117,12 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) { struct nft_pipapo *priv = nft_set_priv(set); - unsigned long *res, *fill, *scratch; + struct nft_pipapo_scratch *scratch; u8 genmask = nft_genmask_cur(net); const u8 *rp = (const u8 *)key; struct nft_pipapo_match *m; struct nft_pipapo_field *f; + unsigned long *res, *fill; bool map_index; int i, ret = 0; @@ -1141,15 +1139,16 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, */ kernel_fpu_begin_mask(0); - scratch = *raw_cpu_ptr(m->scratch_aligned); + scratch = *raw_cpu_ptr(m->scratch); if (unlikely(!scratch)) { kernel_fpu_end(); return false; } - map_index = raw_cpu_read(nft_pipapo_avx2_scratch_index); - res = scratch + (map_index ? m->bsize_max : 0); - fill = scratch + (map_index ? 0 : m->bsize_max); + map_index = scratch->map_index; + + res = scratch->map + (map_index ? m->bsize_max : 0); + fill = scratch->map + (map_index ? 0 : m->bsize_max); /* Starting map doesn't need to be set for this implementation */ @@ -1221,7 +1220,7 @@ next_match: out: if (i % 2) - raw_cpu_write(nft_pipapo_avx2_scratch_index, !map_index); + scratch->map_index = !map_index; kernel_fpu_end(); return ret >= 0; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index e34662f4a71e0f821e1557c6bc743638669bbabd..5bf5572e945cc3ed2e912b8dcf9f460a40086366 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -235,7 +235,7 @@ static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, static const struct nft_rbtree_elem * nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, - struct nft_rbtree_elem *rbe, u8 genmask) + struct nft_rbtree_elem *rbe) { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); @@ -254,7 +254,7 @@ nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, while (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); if (nft_rbtree_interval_end(rbe_prev) && - nft_set_elem_active(&rbe_prev->ext, genmask)) + nft_set_elem_active(&rbe_prev->ext, NFT_GENMASK_ANY)) break; prev = rb_prev(prev); @@ -365,7 +365,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, nft_set_elem_active(&rbe->ext, cur_genmask)) { const struct nft_rbtree_elem *removed_end; - removed_end = nft_rbtree_gc_elem(set, priv, rbe, genmask); + removed_end = nft_rbtree_gc_elem(set, priv, rbe); if (IS_ERR(removed_end)) return PTR_ERR(removed_end); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 6857a4965fe87ecfac0b33bee584fc59d266e903..e9b81cba1e2b4107aa859d7963975561bd1958b2 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -167,7 +167,7 @@ static inline u32 netlink_group_mask(u32 group) static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb, gfp_t gfp_mask) { - unsigned int len = skb_end_offset(skb); + unsigned int len = skb->len; struct sk_buff *new; new = alloc_skb(len, gfp_mask); diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index ec5747969f964623802b4aa0e59bab5428ebb91f..f0879295de110a2a256b4857550b128cab9067c5 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -453,16 +453,16 @@ static int nr_create(struct net *net, struct socket *sock, int protocol, nr_init_timers(sk); nr->t1 = - msecs_to_jiffies(sysctl_netrom_transport_timeout); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_timeout)); nr->t2 = - msecs_to_jiffies(sysctl_netrom_transport_acknowledge_delay); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_acknowledge_delay)); nr->n2 = - msecs_to_jiffies(sysctl_netrom_transport_maximum_tries); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_maximum_tries)); nr->t4 = - msecs_to_jiffies(sysctl_netrom_transport_busy_delay); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_busy_delay)); nr->idle = - msecs_to_jiffies(sysctl_netrom_transport_no_activity_timeout); - nr->window = sysctl_netrom_transport_requested_window_size; + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_no_activity_timeout)); + nr->window = READ_ONCE(sysctl_netrom_transport_requested_window_size); nr->bpqext = 1; nr->state = NR_STATE_0; @@ -954,7 +954,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) * G8PZT's Xrouter which is sending packets with command type 7 * as an extension of the protocol. */ - if (sysctl_netrom_reset_circuit && + if (READ_ONCE(sysctl_netrom_reset_circuit) && (frametype != NR_RESET || flags != 0)) nr_transmit_reset(skb, 1); diff --git a/net/netrom/nr_dev.c b/net/netrom/nr_dev.c index 3aaac4a22b38763cd855e494b2c19fdf3bcbd54e..2c34389c3ce6f16acf669fa14c7b38a7d63dda4b 100644 --- a/net/netrom/nr_dev.c +++ b/net/netrom/nr_dev.c @@ -81,7 +81,7 @@ static int nr_header(struct sk_buff *skb, struct net_device *dev, buff[6] |= AX25_SSSID_SPARE; buff += AX25_ADDR_LEN; - *buff++ = sysctl_netrom_network_ttl_initialiser; + *buff++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); *buff++ = NR_PROTO_IP; *buff++ = NR_PROTO_IP; diff --git a/net/netrom/nr_in.c b/net/netrom/nr_in.c index 2f084b6f69d7e05b51d1673157e8e72f3b9e2635..97944db6b5ac64387d8c8d53dc551bb11f1789f1 100644 --- a/net/netrom/nr_in.c +++ b/net/netrom/nr_in.c @@ -97,7 +97,7 @@ static int nr_state1_machine(struct sock *sk, struct sk_buff *skb, break; case NR_RESET: - if (sysctl_netrom_reset_circuit) + if (READ_ONCE(sysctl_netrom_reset_circuit)) nr_disconnect(sk, ECONNRESET); break; @@ -128,7 +128,7 @@ static int nr_state2_machine(struct sock *sk, struct sk_buff *skb, break; case NR_RESET: - if (sysctl_netrom_reset_circuit) + if (READ_ONCE(sysctl_netrom_reset_circuit)) nr_disconnect(sk, ECONNRESET); break; @@ -262,7 +262,7 @@ static int nr_state3_machine(struct sock *sk, struct sk_buff *skb, int frametype break; case NR_RESET: - if (sysctl_netrom_reset_circuit) + if (READ_ONCE(sysctl_netrom_reset_circuit)) nr_disconnect(sk, ECONNRESET); break; diff --git a/net/netrom/nr_out.c b/net/netrom/nr_out.c index 44929657f5b717de639c13334f17f42f652a78cc..5e531394a724b7f919f22ae2be42c8feaafdc22e 100644 --- a/net/netrom/nr_out.c +++ b/net/netrom/nr_out.c @@ -204,7 +204,7 @@ void nr_transmit_buffer(struct sock *sk, struct sk_buff *skb) dptr[6] |= AX25_SSSID_SPARE; dptr += AX25_ADDR_LEN; - *dptr++ = sysctl_netrom_network_ttl_initialiser; + *dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); if (!nr_route_frame(skb, NULL)) { kfree_skb(skb); diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index baea3cbd76ca5bb5803974a75c3f10f87cc80140..70480869ad1c566a8ab8a28c0d39bdae056ec596 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -153,7 +153,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, nr_neigh->digipeat = NULL; nr_neigh->ax25 = NULL; nr_neigh->dev = dev; - nr_neigh->quality = sysctl_netrom_default_path_quality; + nr_neigh->quality = READ_ONCE(sysctl_netrom_default_path_quality); nr_neigh->locked = 0; nr_neigh->count = 0; nr_neigh->number = nr_neigh_no++; @@ -728,7 +728,7 @@ void nr_link_failed(ax25_cb *ax25, int reason) nr_neigh->ax25 = NULL; ax25_cb_put(ax25); - if (++nr_neigh->failed < sysctl_netrom_link_fails_count) { + if (++nr_neigh->failed < READ_ONCE(sysctl_netrom_link_fails_count)) { nr_neigh_put(nr_neigh); return; } @@ -766,7 +766,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) if (ax25 != NULL) { ret = nr_add_node(nr_src, "", &ax25->dest_addr, ax25->digipeat, ax25->ax25_dev->dev, 0, - sysctl_netrom_obsolescence_count_initialiser); + READ_ONCE(sysctl_netrom_obsolescence_count_initialiser)); if (ret) return ret; } @@ -780,7 +780,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) return ret; } - if (!sysctl_netrom_routing_control && ax25 != NULL) + if (!READ_ONCE(sysctl_netrom_routing_control) && ax25 != NULL) return 0; /* Its Time-To-Live has expired */ diff --git a/net/netrom/nr_subr.c b/net/netrom/nr_subr.c index e2d2af924cff4a4103e59e04a6efe69c6fcca23e..c3bbd5880850bb047c7375e2c1b8acf6e80e0231 100644 --- a/net/netrom/nr_subr.c +++ b/net/netrom/nr_subr.c @@ -182,7 +182,8 @@ void nr_write_internal(struct sock *sk, int frametype) *dptr++ = nr->my_id; *dptr++ = frametype; *dptr++ = nr->window; - if (nr->bpqext) *dptr++ = sysctl_netrom_network_ttl_initialiser; + if (nr->bpqext) + *dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); break; case NR_DISCREQ: @@ -236,7 +237,7 @@ void __nr_transmit_reply(struct sk_buff *skb, int mine, unsigned char cmdflags) dptr[6] |= AX25_SSSID_SPARE; dptr += AX25_ADDR_LEN; - *dptr++ = sysctl_netrom_network_ttl_initialiser; + *dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); if (mine) { *dptr++ = 0; diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 7535afd1537e9367aa7c7e22f93fb555e8320c5f..f76a2d80603405a4a444856de243be2e7cb843a2 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1207,6 +1207,10 @@ void nci_free_device(struct nci_dev *ndev) { nfc_free_device(ndev->nfc_dev); nci_hci_deallocate(ndev); + + /* drop partial rx data packet if present */ + if (ndev->rx_data_reassembly) + kfree_skb(ndev->rx_data_reassembly); kfree(ndev); } EXPORT_SYMBOL(nci_free_device); @@ -1508,6 +1512,11 @@ static void nci_rx_work(struct work_struct *work) nfc_send_to_raw_sock(ndev->nfc_dev, skb, RAW_PAYLOAD_NCI, NFC_DIRECTION_RX); + if (!nci_plen(skb->data)) { + kfree_skb(skb); + break; + } + /* Process frame */ switch (nci_mt(skb->data)) { case NCI_MT_RSP_PKT: diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index 0f23e5e8e03ebaaaefbc567153e3da531aecb3ca..3e0fc71d95a1436f56e6e3b273b6697cc96a4a8e 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -76,13 +76,15 @@ EXPORT_SYMBOL_GPL(nsh_pop); static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, netdev_features_t features) { + unsigned int outer_hlen, mac_len, nsh_len; struct sk_buff *segs = ERR_PTR(-EINVAL); u16 mac_offset = skb->mac_header; - unsigned int nsh_len, mac_len; - __be16 proto; + __be16 outer_proto, proto; skb_reset_network_header(skb); + outer_proto = skb->protocol; + outer_hlen = skb_mac_header_len(skb); mac_len = skb->mac_len; if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN))) @@ -112,10 +114,10 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, } for (skb = segs; skb; skb = skb->next) { - skb->protocol = htons(ETH_P_NSH); - __skb_push(skb, nsh_len); - skb->mac_header = mac_offset; - skb->network_header = skb->mac_header + mac_len; + skb->protocol = outer_proto; + __skb_push(skb, nsh_len + outer_hlen); + skb_reset_mac_header(skb); + skb_set_network_header(skb, outer_hlen); skb->mac_len = mac_len; } diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 0591cfb289d50583ac1bf278eef6e76a1707a7c6..2302bae1e0128b526aa68380f4e6410ed54eed06 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1711,8 +1711,9 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, if (ct_info.timeout[0]) { if (nf_ct_set_timeout(net, ct_info.ct, family, key->ip.proto, ct_info.timeout)) - pr_info_ratelimited("Failed to associated timeout " - "policy `%s'\n", ct_info.timeout); + OVS_NLERR(log, + "Failed to associated timeout policy '%s'", + ct_info.timeout); else ct_info.nf_ct_timeout = rcu_dereference( nf_ct_timeout_find(ct_info.ct)->timeout); @@ -1919,9 +1920,9 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net) for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) { struct hlist_head *head = &info->limits[i]; struct ovs_ct_limit *ct_limit; + struct hlist_node *next; - hlist_for_each_entry_rcu(ct_limit, head, hlist_node, - lockdep_ovsl_is_held()) + hlist_for_each_entry_safe(ct_limit, next, head, hlist_node) kfree_rcu(ct_limit, rcu); } kfree(info->limits); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index ead5418c126e37e26bc7ddeed2f815d6642cf49d..e3c85ceb1f0a5ce4388c607c4496eabcf68b384e 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -47,6 +47,7 @@ struct ovs_len_tbl { #define OVS_ATTR_NESTED -1 #define OVS_ATTR_VARIABLE -2 +#define OVS_COPY_ACTIONS_MAX_DEPTH 16 static bool actions_may_change_flow(const struct nlattr *actions) { @@ -2543,13 +2544,15 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log); + u32 mpls_label_count, bool log, + u32 depth); static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log, bool last) + u32 mpls_label_count, bool log, bool last, + u32 depth) { const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1]; const struct nlattr *probability, *actions; @@ -2600,7 +2603,8 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, return err; err = __ovs_nla_copy_actions(net, actions, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -2615,7 +2619,8 @@ static int validate_and_copy_dec_ttl(struct net *net, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log) + u32 mpls_label_count, bool log, + u32 depth) { const struct nlattr *attrs[OVS_DEC_TTL_ATTR_MAX + 1]; int start, action_start, err, rem; @@ -2658,7 +2663,8 @@ static int validate_and_copy_dec_ttl(struct net *net, return action_start; err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type, - vlan_tci, mpls_label_count, log); + vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -2672,7 +2678,8 @@ static int validate_and_copy_clone(struct net *net, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log, bool last) + u32 mpls_label_count, bool log, bool last, + u32 depth) { int start, err; u32 exec; @@ -2692,7 +2699,8 @@ static int validate_and_copy_clone(struct net *net, return err; err = __ovs_nla_copy_actions(net, attr, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3061,7 +3069,7 @@ static int validate_and_copy_check_pkt_len(struct net *net, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, u32 mpls_label_count, - bool log, bool last) + bool log, bool last, u32 depth) { const struct nlattr *acts_if_greater, *acts_if_lesser_eq; struct nlattr *a[OVS_CHECK_PKT_LEN_ATTR_MAX + 1]; @@ -3109,7 +3117,8 @@ static int validate_and_copy_check_pkt_len(struct net *net, return nested_acts_start; err = __ovs_nla_copy_actions(net, acts_if_lesser_eq, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3122,7 +3131,8 @@ static int validate_and_copy_check_pkt_len(struct net *net, return nested_acts_start; err = __ovs_nla_copy_actions(net, acts_if_greater, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3150,12 +3160,16 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log) + u32 mpls_label_count, bool log, + u32 depth) { u8 mac_proto = ovs_key_mac_proto(key); const struct nlattr *a; int rem, err; + if (depth > OVS_COPY_ACTIONS_MAX_DEPTH) + return -EOVERFLOW; + nla_for_each_nested(a, attr, rem) { /* Expected argument lengths, (u32)-1 for variable length. */ static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = { @@ -3350,7 +3364,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, err = validate_and_copy_sample(net, a, key, sfa, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, depth); if (err) return err; skip_copy = true; @@ -3421,7 +3435,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, err = validate_and_copy_clone(net, a, key, sfa, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, depth); if (err) return err; skip_copy = true; @@ -3435,7 +3449,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, + depth); if (err) return err; skip_copy = true; @@ -3445,7 +3460,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, case OVS_ACTION_ATTR_DEC_TTL: err = validate_and_copy_dec_ttl(net, a, key, sfa, eth_type, vlan_tci, - mpls_label_count, log); + mpls_label_count, log, + depth); if (err) return err; skip_copy = true; @@ -3485,7 +3501,8 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, (*sfa)->orig_len = nla_len(attr); err = __ovs_nla_copy_actions(net, attr, key, sfa, key->eth.type, - key->eth.vlan.tci, mpls_label_count, log); + key->eth.vlan.tci, mpls_label_count, log, + 0); if (err) ovs_nla_free_flow_actions(*sfa); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 51882f07ef70c47b9409a019797a2edee68f8014..7188ca8d84693a179349129acb42596520d1bb25 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3284,7 +3284,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; - char name[sizeof(uaddr->sa_data) + 1]; + char name[sizeof(uaddr->sa_data_min) + 1]; /* * Check legality @@ -3295,8 +3295,8 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, /* uaddr->sa_data comes from the userspace, it's not guaranteed to be * zero-terminated. */ - memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data)); - name[sizeof(uaddr->sa_data)] = 0; + memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data_min)); + name[sizeof(uaddr->sa_data_min)] = 0; return packet_do_bind(sk, name, 0, 0); } @@ -3566,11 +3566,11 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, return -EOPNOTSUPP; uaddr->sa_family = AF_PACKET; - memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data)); + memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data_min)); rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) - strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); + strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data_min)); rcu_read_unlock(); return sizeof(*uaddr); @@ -3981,7 +3981,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, if (val < 0 || val > 1) return -EINVAL; - po->prot_hook.ignore_outgoing = !!val; + WRITE_ONCE(po->prot_hook.ignore_outgoing, !!val); return 0; } case PACKET_TX_HAS_OFF: @@ -4110,7 +4110,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, 0); break; case PACKET_IGNORE_OUTGOING: - val = po->prot_hook.ignore_outgoing; + val = READ_ONCE(po->prot_hook.ignore_outgoing); break; case PACKET_ROLLOVER_STATS: if (!po->rollover) diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c index ff5f49ab236edea3c5e8a5a5892ae499d33fb122..39a6c5713d0b21df0889b0da51761a0195756dd3 100644 --- a/net/phonet/datagram.c +++ b/net/phonet/datagram.c @@ -35,10 +35,10 @@ static int pn_ioctl(struct sock *sk, int cmd, unsigned long arg) switch (cmd) { case SIOCINQ: - lock_sock(sk); + spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); answ = skb ? skb->len : 0; - release_sock(sk); + spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(answ, (int __user *)arg); case SIOCPNADDRESOURCE: diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 83ea13a50690b88f6d51c995e7c8b766baea3c2d..607f54c23647a04794944785b24006955e372125 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -917,6 +917,37 @@ static int pep_sock_enable(struct sock *sk, struct sockaddr *addr, int len) return 0; } +static unsigned int pep_first_packet_length(struct sock *sk) +{ + struct pep_sock *pn = pep_sk(sk); + struct sk_buff_head *q; + struct sk_buff *skb; + unsigned int len = 0; + bool found = false; + + if (sock_flag(sk, SOCK_URGINLINE)) { + q = &pn->ctrlreq_queue; + spin_lock_bh(&q->lock); + skb = skb_peek(q); + if (skb) { + len = skb->len; + found = true; + } + spin_unlock_bh(&q->lock); + } + + if (likely(!found)) { + q = &sk->sk_receive_queue; + spin_lock_bh(&q->lock); + skb = skb_peek(q); + if (skb) + len = skb->len; + spin_unlock_bh(&q->lock); + } + + return len; +} + static int pep_ioctl(struct sock *sk, int cmd, unsigned long arg) { struct pep_sock *pn = pep_sk(sk); @@ -930,15 +961,7 @@ static int pep_ioctl(struct sock *sk, int cmd, unsigned long arg) break; } - lock_sock(sk); - if (sock_flag(sk, SOCK_URGINLINE) && - !skb_queue_empty(&pn->ctrlreq_queue)) - answ = skb_peek(&pn->ctrlreq_queue)->len; - else if (!skb_queue_empty(&sk->sk_receive_queue)) - answ = skb_peek(&sk->sk_receive_queue)->len; - else - answ = 0; - release_sock(sk); + answ = pep_first_packet_length(sk); ret = put_user(answ, (int __user *)arg); break; diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index 59aebe29689077bfa77d37516aea4617fe3b8a50..dd4c7e9a634fbe29645107de04a90688cdfb1a01 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -193,7 +193,7 @@ void rtm_phonet_notify(int event, struct net_device *dev, u8 dst) struct sk_buff *skb; int err = -ENOBUFS; - skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + + skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(1) + nla_total_size(4), GFP_KERNEL); if (skb == NULL) goto errout; diff --git a/net/rds/rdma.c b/net/rds/rdma.c index fba82d36593add3317e89104aabbd69a0281cb33..00dbcd4d28e68097c612c628b7d4193124be4c9c 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -301,6 +301,9 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, kfree(sg); } ret = PTR_ERR(trans_private); + /* Trigger connection so that its ready for the next retry */ + if (ret == -ENODEV && cp) + rds_conn_connect_if_down(cp->cp_conn); goto out; } diff --git a/net/rds/send.c b/net/rds/send.c index 0c5504068e3c2da92eeb61305e4c95fbc90a4ee2..0005fb43f2dfa537b712381b412fd707e63160b9 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -103,13 +103,12 @@ EXPORT_SYMBOL_GPL(rds_send_path_reset); static int acquire_in_xmit(struct rds_conn_path *cp) { - return test_and_set_bit(RDS_IN_XMIT, &cp->cp_flags) == 0; + return test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags) == 0; } static void release_in_xmit(struct rds_conn_path *cp) { - clear_bit(RDS_IN_XMIT, &cp->cp_flags); - smp_mb__after_atomic(); + clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags); /* * We don't use wait_on_bit()/wake_up_bit() because our waking is in a * hot path and finding waiters is very rare. We don't want to walk @@ -1314,12 +1313,8 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) /* Parse any control messages the user may have included. */ ret = rds_cmsg_send(rs, rm, msg, &allocated_mr, &vct); - if (ret) { - /* Trigger connection so that its ready for the next retry */ - if (ret == -EAGAIN) - rds_conn_connect_if_down(conn); + if (ret) goto out; - } if (rm->rdma.op_active && !conn->c_trans->xmit_rdma) { printk_ratelimited(KERN_NOTICE "rdma_op %p conn xmit_rdma %p\n", diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index aab06970139823828e313651ba98f34f957c619e..5d91ef562ff78b4e44a6cc5c56e4d2d856aedb70 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -41,6 +41,14 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, _enter("%d", conn->debug_id); + if (sp && sp->hdr.type == RXRPC_PACKET_TYPE_ACK) { + if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), + &pkt.ack, sizeof(pkt.ack)) < 0) + return; + if (pkt.ack.reason == RXRPC_ACK_PING_RESPONSE) + return; + } + chan = &conn->channels[channel]; /* If the last call got moved on whilst we were waiting to run, just diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 24cf0bf7c80e5f5404aad0783d8fc84f7f41448e..9c4a80fce794ffc592468a35f87be425344aa55e 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -45,23 +45,6 @@ if NET_SCHED comment "Queueing/Scheduling" -config NET_SCH_CBQ - tristate "Class Based Queueing (CBQ)" - help - Say Y here if you want to use the Class-Based Queueing (CBQ) packet - scheduling algorithm. This algorithm classifies the waiting packets - into a tree-like hierarchy of classes; the leaves of this tree are - in turn scheduled by separate algorithms. - - See the top of for more details. - - CBQ is a commonly used scheduler, so if you're unsure, you should - say Y here. Then say Y to all the queueing algorithms below that you - want to use as leaf disciplines. - - To compile this code as a module, choose M here: the - module will be called sch_cbq. - config NET_SCH_HTB tristate "Hierarchical Token Bucket (HTB)" help @@ -85,20 +68,6 @@ config NET_SCH_HFSC To compile this code as a module, choose M here: the module will be called sch_hfsc. -config NET_SCH_ATM - tristate "ATM Virtual Circuits (ATM)" - depends on ATM - help - Say Y here if you want to use the ATM pseudo-scheduler. This - provides a framework for invoking classifiers, which in turn - select classes of this queuing discipline. Each class maps - the flow(s) it is handling to a given virtual circuit. - - See the top of for more details. - - To compile this code as a module, choose M here: the - module will be called sch_atm. - config NET_SCH_PRIO tristate "Multi Band Priority Queueing (PRIO)" help @@ -217,17 +186,6 @@ config NET_SCH_GRED To compile this code as a module, choose M here: the module will be called sch_gred. -config NET_SCH_DSMARK - tristate "Differentiated Services marker (DSMARK)" - help - Say Y if you want to schedule packets according to the - Differentiated Services architecture proposed in RFC 2475. - Technical information on this method, with pointers to associated - RFCs, is available at . - - To compile this code as a module, choose M here: the - module will be called sch_dsmark. - config NET_SCH_NETEM tristate "Network emulator (NETEM)" help diff --git a/net/sched/Makefile b/net/sched/Makefile index 8a33a35fc50d5d0c859e49e00934aec0241d277f..a66ac1e7b79b5c21d5dab478befe5624cafab2e7 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -33,20 +33,17 @@ obj-$(CONFIG_NET_ACT_TUNNEL_KEY)+= act_tunnel_key.o obj-$(CONFIG_NET_ACT_CT) += act_ct.o obj-$(CONFIG_NET_ACT_GATE) += act_gate.o obj-$(CONFIG_NET_SCH_FIFO) += sch_fifo.o -obj-$(CONFIG_NET_SCH_CBQ) += sch_cbq.o obj-$(CONFIG_NET_SCH_HTB) += sch_htb.o obj-$(CONFIG_NET_SCH_HFSC) += sch_hfsc.o obj-$(CONFIG_NET_SCH_RED) += sch_red.o obj-$(CONFIG_NET_SCH_GRED) += sch_gred.o obj-$(CONFIG_NET_SCH_INGRESS) += sch_ingress.o -obj-$(CONFIG_NET_SCH_DSMARK) += sch_dsmark.o obj-$(CONFIG_NET_SCH_SFB) += sch_sfb.o obj-$(CONFIG_NET_SCH_SFQ) += sch_sfq.o obj-$(CONFIG_NET_SCH_TBF) += sch_tbf.o obj-$(CONFIG_NET_SCH_TEQL) += sch_teql.o obj-$(CONFIG_NET_SCH_PRIO) += sch_prio.o obj-$(CONFIG_NET_SCH_MULTIQ) += sch_multiq.o -obj-$(CONFIG_NET_SCH_ATM) += sch_atm.o obj-$(CONFIG_NET_SCH_NETEM) += sch_netem.o obj-$(CONFIG_NET_SCH_DRR) += sch_drr.o obj-$(CONFIG_NET_SCH_PLUG) += sch_plug.o diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index d98758a639340517aa6a40e20e76156cffd26178..744ff9729469e88609cd2d1558c360a622ce884a 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -239,13 +239,13 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, struct tcf_skbmod *d = to_skbmod(a); unsigned char *b = skb_tail_pointer(skb); struct tcf_skbmod_params *p; - struct tc_skbmod opt = { - .index = d->tcf_index, - .refcnt = refcount_read(&d->tcf_refcnt) - ref, - .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, - }; + struct tc_skbmod opt; struct tcf_t t; + memset(&opt, 0, sizeof(opt)); + opt.index = d->tcf_index; + opt.refcnt = refcount_read(&d->tcf_refcnt) - ref, + opt.bindcnt = atomic_read(&d->tcf_bindcnt) - bind; spin_lock_bh(&d->tcf_lock); opt.action = d->tcf_action; p = rcu_dereference_protected(d->skbmod_p, diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index e8f988e1c7e649e8c1675dcac236ccd7b34dde04..334a563e0bc14488fa03daade880ec2215b833db 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -806,7 +806,7 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len) notify = !sch->q.qlen && !WARN_ON_ONCE(!n && !qdisc_is_offloaded); /* TODO: perform the search on a per txq basis */ - sch = qdisc_lookup(qdisc_dev(sch), TC_H_MAJ(parentid)); + sch = qdisc_lookup_rcu(qdisc_dev(sch), TC_H_MAJ(parentid)); if (sch == NULL) { WARN_ON_ONCE(parentid != TC_H_ROOT); break; diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c deleted file mode 100644 index 4a981ca90b0bfeb3a3b6b2ad21a3b4cb5372db37..0000000000000000000000000000000000000000 --- a/net/sched/sch_atm.c +++ /dev/null @@ -1,706 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* net/sched/sch_atm.c - ATM VC selection "queueing discipline" */ - -/* Written 1998-2000 by Werner Almesberger, EPFL ICA */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include /* for fput */ -#include -#include -#include - -/* - * The ATM queuing discipline provides a framework for invoking classifiers - * (aka "filters"), which in turn select classes of this queuing discipline. - * Each class maps the flow(s) it is handling to a given VC. Multiple classes - * may share the same VC. - * - * When creating a class, VCs are specified by passing the number of the open - * socket descriptor by which the calling process references the VC. The kernel - * keeps the VC open at least until all classes using it are removed. - * - * In this file, most functions are named atm_tc_* to avoid confusion with all - * the atm_* in net/atm. This naming convention differs from what's used in the - * rest of net/sched. - * - * Known bugs: - * - sometimes messes up the IP stack - * - any manipulations besides the few operations described in the README, are - * untested and likely to crash the system - * - should lock the flow while there is data in the queue (?) - */ - -#define VCC2FLOW(vcc) ((struct atm_flow_data *) ((vcc)->user_back)) - -struct atm_flow_data { - struct Qdisc_class_common common; - struct Qdisc *q; /* FIFO, TBF, etc. */ - struct tcf_proto __rcu *filter_list; - struct tcf_block *block; - struct atm_vcc *vcc; /* VCC; NULL if VCC is closed */ - void (*old_pop)(struct atm_vcc *vcc, - struct sk_buff *skb); /* chaining */ - struct atm_qdisc_data *parent; /* parent qdisc */ - struct socket *sock; /* for closing */ - int ref; /* reference count */ - struct gnet_stats_basic_sync bstats; - struct gnet_stats_queue qstats; - struct list_head list; - struct atm_flow_data *excess; /* flow for excess traffic; - NULL to set CLP instead */ - int hdr_len; - unsigned char hdr[]; /* header data; MUST BE LAST */ -}; - -struct atm_qdisc_data { - struct atm_flow_data link; /* unclassified skbs go here */ - struct list_head flows; /* NB: "link" is also on this - list */ - struct tasklet_struct task; /* dequeue tasklet */ -}; - -/* ------------------------- Class/flow operations ------------------------- */ - -static inline struct atm_flow_data *lookup_flow(struct Qdisc *sch, u32 classid) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - - list_for_each_entry(flow, &p->flows, list) { - if (flow->common.classid == classid) - return flow; - } - return NULL; -} - -static int atm_tc_graft(struct Qdisc *sch, unsigned long arg, - struct Qdisc *new, struct Qdisc **old, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)arg; - - pr_debug("atm_tc_graft(sch %p,[qdisc %p],flow %p,new %p,old %p)\n", - sch, p, flow, new, old); - if (list_empty(&flow->list)) - return -EINVAL; - if (!new) - new = &noop_qdisc; - *old = flow->q; - flow->q = new; - if (*old) - qdisc_reset(*old); - return 0; -} - -static struct Qdisc *atm_tc_leaf(struct Qdisc *sch, unsigned long cl) -{ - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - - pr_debug("atm_tc_leaf(sch %p,flow %p)\n", sch, flow); - return flow ? flow->q : NULL; -} - -static unsigned long atm_tc_find(struct Qdisc *sch, u32 classid) -{ - struct atm_qdisc_data *p __maybe_unused = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("%s(sch %p,[qdisc %p],classid %x)\n", __func__, sch, p, classid); - flow = lookup_flow(sch, classid); - pr_debug("%s: flow %p\n", __func__, flow); - return (unsigned long)flow; -} - -static unsigned long atm_tc_bind_filter(struct Qdisc *sch, - unsigned long parent, u32 classid) -{ - struct atm_qdisc_data *p __maybe_unused = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("%s(sch %p,[qdisc %p],classid %x)\n", __func__, sch, p, classid); - flow = lookup_flow(sch, classid); - if (flow) - flow->ref++; - pr_debug("%s: flow %p\n", __func__, flow); - return (unsigned long)flow; -} - -/* - * atm_tc_put handles all destructions, including the ones that are explicitly - * requested (atm_tc_destroy, etc.). The assumption here is that we never drop - * anything that still seems to be in use. - */ -static void atm_tc_put(struct Qdisc *sch, unsigned long cl) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - - pr_debug("atm_tc_put(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - if (--flow->ref) - return; - pr_debug("atm_tc_put: destroying\n"); - list_del_init(&flow->list); - pr_debug("atm_tc_put: qdisc %p\n", flow->q); - qdisc_put(flow->q); - tcf_block_put(flow->block); - if (flow->sock) { - pr_debug("atm_tc_put: f_count %ld\n", - file_count(flow->sock->file)); - flow->vcc->pop = flow->old_pop; - sockfd_put(flow->sock); - } - if (flow->excess) - atm_tc_put(sch, (unsigned long)flow->excess); - if (flow != &p->link) - kfree(flow); - /* - * If flow == &p->link, the qdisc no longer works at this point and - * needs to be removed. (By the caller of atm_tc_put.) - */ -} - -static void sch_atm_pop(struct atm_vcc *vcc, struct sk_buff *skb) -{ - struct atm_qdisc_data *p = VCC2FLOW(vcc)->parent; - - pr_debug("sch_atm_pop(vcc %p,skb %p,[qdisc %p])\n", vcc, skb, p); - VCC2FLOW(vcc)->old_pop(vcc, skb); - tasklet_schedule(&p->task); -} - -static const u8 llc_oui_ip[] = { - 0xaa, /* DSAP: non-ISO */ - 0xaa, /* SSAP: non-ISO */ - 0x03, /* Ctrl: Unnumbered Information Command PDU */ - 0x00, /* OUI: EtherType */ - 0x00, 0x00, - 0x08, 0x00 -}; /* Ethertype IP (0800) */ - -static const struct nla_policy atm_policy[TCA_ATM_MAX + 1] = { - [TCA_ATM_FD] = { .type = NLA_U32 }, - [TCA_ATM_EXCESS] = { .type = NLA_U32 }, -}; - -static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, - struct nlattr **tca, unsigned long *arg, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)*arg; - struct atm_flow_data *excess = NULL; - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_ATM_MAX + 1]; - struct socket *sock; - int fd, error, hdr_len; - void *hdr; - - pr_debug("atm_tc_change(sch %p,[qdisc %p],classid %x,parent %x," - "flow %p,opt %p)\n", sch, p, classid, parent, flow, opt); - /* - * The concept of parents doesn't apply for this qdisc. - */ - if (parent && parent != TC_H_ROOT && parent != sch->handle) - return -EINVAL; - /* - * ATM classes cannot be changed. In order to change properties of the - * ATM connection, that socket needs to be modified directly (via the - * native ATM API. In order to send a flow to a different VC, the old - * class needs to be removed and a new one added. (This may be changed - * later.) - */ - if (flow) - return -EBUSY; - if (opt == NULL) - return -EINVAL; - - error = nla_parse_nested_deprecated(tb, TCA_ATM_MAX, opt, atm_policy, - NULL); - if (error < 0) - return error; - - if (!tb[TCA_ATM_FD]) - return -EINVAL; - fd = nla_get_u32(tb[TCA_ATM_FD]); - pr_debug("atm_tc_change: fd %d\n", fd); - if (tb[TCA_ATM_HDR]) { - hdr_len = nla_len(tb[TCA_ATM_HDR]); - hdr = nla_data(tb[TCA_ATM_HDR]); - } else { - hdr_len = RFC1483LLC_LEN; - hdr = NULL; /* default LLC/SNAP for IP */ - } - if (!tb[TCA_ATM_EXCESS]) - excess = NULL; - else { - excess = (struct atm_flow_data *) - atm_tc_find(sch, nla_get_u32(tb[TCA_ATM_EXCESS])); - if (!excess) - return -ENOENT; - } - pr_debug("atm_tc_change: type %d, payload %d, hdr_len %d\n", - opt->nla_type, nla_len(opt), hdr_len); - sock = sockfd_lookup(fd, &error); - if (!sock) - return error; /* f_count++ */ - pr_debug("atm_tc_change: f_count %ld\n", file_count(sock->file)); - if (sock->ops->family != PF_ATMSVC && sock->ops->family != PF_ATMPVC) { - error = -EPROTOTYPE; - goto err_out; - } - /* @@@ should check if the socket is really operational or we'll crash - on vcc->send */ - if (classid) { - if (TC_H_MAJ(classid ^ sch->handle)) { - pr_debug("atm_tc_change: classid mismatch\n"); - error = -EINVAL; - goto err_out; - } - } else { - int i; - unsigned long cl; - - for (i = 1; i < 0x8000; i++) { - classid = TC_H_MAKE(sch->handle, 0x8000 | i); - cl = atm_tc_find(sch, classid); - if (!cl) - break; - } - } - pr_debug("atm_tc_change: new id %x\n", classid); - flow = kzalloc(sizeof(struct atm_flow_data) + hdr_len, GFP_KERNEL); - pr_debug("atm_tc_change: flow %p\n", flow); - if (!flow) { - error = -ENOBUFS; - goto err_out; - } - - error = tcf_block_get(&flow->block, &flow->filter_list, sch, - extack); - if (error) { - kfree(flow); - goto err_out; - } - - flow->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid, - extack); - if (!flow->q) - flow->q = &noop_qdisc; - pr_debug("atm_tc_change: qdisc %p\n", flow->q); - flow->sock = sock; - flow->vcc = ATM_SD(sock); /* speedup */ - flow->vcc->user_back = flow; - pr_debug("atm_tc_change: vcc %p\n", flow->vcc); - flow->old_pop = flow->vcc->pop; - flow->parent = p; - flow->vcc->pop = sch_atm_pop; - flow->common.classid = classid; - flow->ref = 1; - flow->excess = excess; - list_add(&flow->list, &p->link.list); - flow->hdr_len = hdr_len; - if (hdr) - memcpy(flow->hdr, hdr, hdr_len); - else - memcpy(flow->hdr, llc_oui_ip, sizeof(llc_oui_ip)); - *arg = (unsigned long)flow; - return 0; -err_out: - sockfd_put(sock); - return error; -} - -static int atm_tc_delete(struct Qdisc *sch, unsigned long arg, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)arg; - - pr_debug("atm_tc_delete(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - if (list_empty(&flow->list)) - return -EINVAL; - if (rcu_access_pointer(flow->filter_list) || flow == &p->link) - return -EBUSY; - /* - * Reference count must be 2: one for "keepalive" (set at class - * creation), and one for the reference held when calling delete. - */ - if (flow->ref < 2) { - pr_err("atm_tc_delete: flow->ref == %d\n", flow->ref); - return -EINVAL; - } - if (flow->ref > 2) - return -EBUSY; /* catch references via excess, etc. */ - atm_tc_put(sch, arg); - return 0; -} - -static void atm_tc_walk(struct Qdisc *sch, struct qdisc_walker *walker) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("atm_tc_walk(sch %p,[qdisc %p],walker %p)\n", sch, p, walker); - if (walker->stop) - return; - list_for_each_entry(flow, &p->flows, list) { - if (!tc_qdisc_stats_dump(sch, (unsigned long)flow, walker)) - break; - } -} - -static struct tcf_block *atm_tc_tcf_block(struct Qdisc *sch, unsigned long cl, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - - pr_debug("atm_tc_find_tcf(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - return flow ? flow->block : p->link.block; -} - -/* --------------------------- Qdisc operations ---------------------------- */ - -static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch, - struct sk_buff **to_free) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - struct tcf_result res; - int result; - int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - - pr_debug("atm_tc_enqueue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p); - result = TC_ACT_OK; /* be nice to gcc */ - flow = NULL; - if (TC_H_MAJ(skb->priority) != sch->handle || - !(flow = (struct atm_flow_data *)atm_tc_find(sch, skb->priority))) { - struct tcf_proto *fl; - - list_for_each_entry(flow, &p->flows, list) { - fl = rcu_dereference_bh(flow->filter_list); - if (fl) { - result = tcf_classify(skb, NULL, fl, &res, true); - if (result < 0) - continue; - if (result == TC_ACT_SHOT) - goto done; - - flow = (struct atm_flow_data *)res.class; - if (!flow) - flow = lookup_flow(sch, res.classid); - goto drop; - } - } - flow = NULL; -done: - ; - } - if (!flow) { - flow = &p->link; - } else { - if (flow->vcc) - ATM_SKB(skb)->atm_options = flow->vcc->atm_options; - /*@@@ looks good ... but it's not supposed to work :-) */ -#ifdef CONFIG_NET_CLS_ACT - switch (result) { - case TC_ACT_QUEUED: - case TC_ACT_STOLEN: - case TC_ACT_TRAP: - __qdisc_drop(skb, to_free); - return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - case TC_ACT_SHOT: - __qdisc_drop(skb, to_free); - goto drop; - case TC_ACT_RECLASSIFY: - if (flow->excess) - flow = flow->excess; - else - ATM_SKB(skb)->atm_options |= ATM_ATMOPT_CLP; - break; - } -#endif - } - - ret = qdisc_enqueue(skb, flow->q, to_free); - if (ret != NET_XMIT_SUCCESS) { -drop: __maybe_unused - if (net_xmit_drop_count(ret)) { - qdisc_qstats_drop(sch); - if (flow) - flow->qstats.drops++; - } - return ret; - } - /* - * Okay, this may seem weird. We pretend we've dropped the packet if - * it goes via ATM. The reason for this is that the outer qdisc - * expects to be able to q->dequeue the packet later on if we return - * success at this place. Also, sch->q.qdisc needs to reflect whether - * there is a packet egligible for dequeuing or not. Note that the - * statistics of the outer qdisc are necessarily wrong because of all - * this. There's currently no correct solution for this. - */ - if (flow == &p->link) { - sch->q.qlen++; - return NET_XMIT_SUCCESS; - } - tasklet_schedule(&p->task); - return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; -} - -/* - * Dequeue packets and send them over ATM. Note that we quite deliberately - * avoid checking net_device's flow control here, simply because sch_atm - * uses its own channels, which have nothing to do with any CLIP/LANE/or - * non-ATM interfaces. - */ - -static void sch_atm_dequeue(struct tasklet_struct *t) -{ - struct atm_qdisc_data *p = from_tasklet(p, t, task); - struct Qdisc *sch = qdisc_from_priv(p); - struct atm_flow_data *flow; - struct sk_buff *skb; - - pr_debug("sch_atm_dequeue(sch %p,[qdisc %p])\n", sch, p); - list_for_each_entry(flow, &p->flows, list) { - if (flow == &p->link) - continue; - /* - * If traffic is properly shaped, this won't generate nasty - * little bursts. Otherwise, it may ... (but that's okay) - */ - while ((skb = flow->q->ops->peek(flow->q))) { - if (!atm_may_send(flow->vcc, skb->truesize)) - break; - - skb = qdisc_dequeue_peeked(flow->q); - if (unlikely(!skb)) - break; - - qdisc_bstats_update(sch, skb); - bstats_update(&flow->bstats, skb); - pr_debug("atm_tc_dequeue: sending on class %p\n", flow); - /* remove any LL header somebody else has attached */ - skb_pull(skb, skb_network_offset(skb)); - if (skb_headroom(skb) < flow->hdr_len) { - struct sk_buff *new; - - new = skb_realloc_headroom(skb, flow->hdr_len); - dev_kfree_skb(skb); - if (!new) - continue; - skb = new; - } - pr_debug("sch_atm_dequeue: ip %p, data %p\n", - skb_network_header(skb), skb->data); - ATM_SKB(skb)->vcc = flow->vcc; - memcpy(skb_push(skb, flow->hdr_len), flow->hdr, - flow->hdr_len); - refcount_add(skb->truesize, - &sk_atm(flow->vcc)->sk_wmem_alloc); - /* atm.atm_options are already set by atm_tc_enqueue */ - flow->vcc->send(flow->vcc, skb); - } - } -} - -static struct sk_buff *atm_tc_dequeue(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct sk_buff *skb; - - pr_debug("atm_tc_dequeue(sch %p,[qdisc %p])\n", sch, p); - tasklet_schedule(&p->task); - skb = qdisc_dequeue_peeked(p->link.q); - if (skb) - sch->q.qlen--; - return skb; -} - -static struct sk_buff *atm_tc_peek(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - - pr_debug("atm_tc_peek(sch %p,[qdisc %p])\n", sch, p); - - return p->link.q->ops->peek(p->link.q); -} - -static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - int err; - - pr_debug("atm_tc_init(sch %p,[qdisc %p],opt %p)\n", sch, p, opt); - INIT_LIST_HEAD(&p->flows); - INIT_LIST_HEAD(&p->link.list); - gnet_stats_basic_sync_init(&p->link.bstats); - list_add(&p->link.list, &p->flows); - p->link.q = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, sch->handle, extack); - if (!p->link.q) - p->link.q = &noop_qdisc; - pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); - p->link.vcc = NULL; - p->link.sock = NULL; - p->link.common.classid = sch->handle; - p->link.ref = 1; - - err = tcf_block_get(&p->link.block, &p->link.filter_list, sch, - extack); - if (err) - return err; - - tasklet_setup(&p->task, sch_atm_dequeue); - return 0; -} - -static void atm_tc_reset(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("atm_tc_reset(sch %p,[qdisc %p])\n", sch, p); - list_for_each_entry(flow, &p->flows, list) - qdisc_reset(flow->q); -} - -static void atm_tc_destroy(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow, *tmp; - - pr_debug("atm_tc_destroy(sch %p,[qdisc %p])\n", sch, p); - list_for_each_entry(flow, &p->flows, list) { - tcf_block_put(flow->block); - flow->block = NULL; - } - - list_for_each_entry_safe(flow, tmp, &p->flows, list) { - if (flow->ref > 1) - pr_err("atm_destroy: %p->ref = %d\n", flow, flow->ref); - atm_tc_put(sch, (unsigned long)flow); - } - tasklet_kill(&p->task); -} - -static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, - struct sk_buff *skb, struct tcmsg *tcm) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - struct nlattr *nest; - - pr_debug("atm_tc_dump_class(sch %p,[qdisc %p],flow %p,skb %p,tcm %p)\n", - sch, p, flow, skb, tcm); - if (list_empty(&flow->list)) - return -EINVAL; - tcm->tcm_handle = flow->common.classid; - tcm->tcm_info = flow->q->handle; - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - - if (nla_put(skb, TCA_ATM_HDR, flow->hdr_len, flow->hdr)) - goto nla_put_failure; - if (flow->vcc) { - struct sockaddr_atmpvc pvc; - int state; - - memset(&pvc, 0, sizeof(pvc)); - pvc.sap_family = AF_ATMPVC; - pvc.sap_addr.itf = flow->vcc->dev ? flow->vcc->dev->number : -1; - pvc.sap_addr.vpi = flow->vcc->vpi; - pvc.sap_addr.vci = flow->vcc->vci; - if (nla_put(skb, TCA_ATM_ADDR, sizeof(pvc), &pvc)) - goto nla_put_failure; - state = ATM_VF2VS(flow->vcc->flags); - if (nla_put_u32(skb, TCA_ATM_STATE, state)) - goto nla_put_failure; - } - if (flow->excess) { - if (nla_put_u32(skb, TCA_ATM_EXCESS, flow->common.classid)) - goto nla_put_failure; - } else { - if (nla_put_u32(skb, TCA_ATM_EXCESS, 0)) - goto nla_put_failure; - } - return nla_nest_end(skb, nest); - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} -static int -atm_tc_dump_class_stats(struct Qdisc *sch, unsigned long arg, - struct gnet_dump *d) -{ - struct atm_flow_data *flow = (struct atm_flow_data *)arg; - - if (gnet_stats_copy_basic(d, NULL, &flow->bstats, true) < 0 || - gnet_stats_copy_queue(d, NULL, &flow->qstats, flow->q->q.qlen) < 0) - return -1; - - return 0; -} - -static int atm_tc_dump(struct Qdisc *sch, struct sk_buff *skb) -{ - return 0; -} - -static const struct Qdisc_class_ops atm_class_ops = { - .graft = atm_tc_graft, - .leaf = atm_tc_leaf, - .find = atm_tc_find, - .change = atm_tc_change, - .delete = atm_tc_delete, - .walk = atm_tc_walk, - .tcf_block = atm_tc_tcf_block, - .bind_tcf = atm_tc_bind_filter, - .unbind_tcf = atm_tc_put, - .dump = atm_tc_dump_class, - .dump_stats = atm_tc_dump_class_stats, -}; - -static struct Qdisc_ops atm_qdisc_ops __read_mostly = { - .cl_ops = &atm_class_ops, - .id = "atm", - .priv_size = sizeof(struct atm_qdisc_data), - .enqueue = atm_tc_enqueue, - .dequeue = atm_tc_dequeue, - .peek = atm_tc_peek, - .init = atm_tc_init, - .reset = atm_tc_reset, - .destroy = atm_tc_destroy, - .dump = atm_tc_dump, - .owner = THIS_MODULE, -}; - -static int __init atm_init(void) -{ - return register_qdisc(&atm_qdisc_ops); -} - -static void __exit atm_exit(void) -{ - unregister_qdisc(&atm_qdisc_ops); -} - -module_init(atm_init) -module_exit(atm_exit) -MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c deleted file mode 100644 index 36db5f6782f2cfd84888ec6b3ab18a675412f8b7..0000000000000000000000000000000000000000 --- a/net/sched/sch_cbq.c +++ /dev/null @@ -1,1727 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * net/sched/sch_cbq.c Class-Based Queueing discipline. - * - * Authors: Alexey Kuznetsov, - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - - -/* Class-Based Queueing (CBQ) algorithm. - ======================================= - - Sources: [1] Sally Floyd and Van Jacobson, "Link-sharing and Resource - Management Models for Packet Networks", - IEEE/ACM Transactions on Networking, Vol.3, No.4, 1995 - - [2] Sally Floyd, "Notes on CBQ and Guaranteed Service", 1995 - - [3] Sally Floyd, "Notes on Class-Based Queueing: Setting - Parameters", 1996 - - [4] Sally Floyd and Michael Speer, "Experimental Results - for Class-Based Queueing", 1998, not published. - - ----------------------------------------------------------------------- - - Algorithm skeleton was taken from NS simulator cbq.cc. - If someone wants to check this code against the LBL version, - he should take into account that ONLY the skeleton was borrowed, - the implementation is different. Particularly: - - --- The WRR algorithm is different. Our version looks more - reasonable (I hope) and works when quanta are allowed to be - less than MTU, which is always the case when real time classes - have small rates. Note, that the statement of [3] is - incomplete, delay may actually be estimated even if class - per-round allotment is less than MTU. Namely, if per-round - allotment is W*r_i, and r_1+...+r_k = r < 1 - - delay_i <= ([MTU/(W*r_i)]*W*r + W*r + k*MTU)/B - - In the worst case we have IntServ estimate with D = W*r+k*MTU - and C = MTU*r. The proof (if correct at all) is trivial. - - - --- It seems that cbq-2.0 is not very accurate. At least, I cannot - interpret some places, which look like wrong translations - from NS. Anyone is advised to find these differences - and explain to me, why I am wrong 8). - - --- Linux has no EOI event, so that we cannot estimate true class - idle time. Workaround is to consider the next dequeue event - as sign that previous packet is finished. This is wrong because of - internal device queueing, but on a permanently loaded link it is true. - Moreover, combined with clock integrator, this scheme looks - very close to an ideal solution. */ - -struct cbq_sched_data; - - -struct cbq_class { - struct Qdisc_class_common common; - struct cbq_class *next_alive; /* next class with backlog in this priority band */ - -/* Parameters */ - unsigned char priority; /* class priority */ - unsigned char priority2; /* priority to be used after overlimit */ - unsigned char ewma_log; /* time constant for idle time calculation */ - - u32 defmap; - - /* Link-sharing scheduler parameters */ - long maxidle; /* Class parameters: see below. */ - long offtime; - long minidle; - u32 avpkt; - struct qdisc_rate_table *R_tab; - - /* General scheduler (WRR) parameters */ - long allot; - long quantum; /* Allotment per WRR round */ - long weight; /* Relative allotment: see below */ - - struct Qdisc *qdisc; /* Ptr to CBQ discipline */ - struct cbq_class *split; /* Ptr to split node */ - struct cbq_class *share; /* Ptr to LS parent in the class tree */ - struct cbq_class *tparent; /* Ptr to tree parent in the class tree */ - struct cbq_class *borrow; /* NULL if class is bandwidth limited; - parent otherwise */ - struct cbq_class *sibling; /* Sibling chain */ - struct cbq_class *children; /* Pointer to children chain */ - - struct Qdisc *q; /* Elementary queueing discipline */ - - -/* Variables */ - unsigned char cpriority; /* Effective priority */ - unsigned char delayed; - unsigned char level; /* level of the class in hierarchy: - 0 for leaf classes, and maximal - level of children + 1 for nodes. - */ - - psched_time_t last; /* Last end of service */ - psched_time_t undertime; - long avgidle; - long deficit; /* Saved deficit for WRR */ - psched_time_t penalized; - struct gnet_stats_basic_sync bstats; - struct gnet_stats_queue qstats; - struct net_rate_estimator __rcu *rate_est; - struct tc_cbq_xstats xstats; - - struct tcf_proto __rcu *filter_list; - struct tcf_block *block; - - int filters; - - struct cbq_class *defaults[TC_PRIO_MAX + 1]; -}; - -struct cbq_sched_data { - struct Qdisc_class_hash clhash; /* Hash table of all classes */ - int nclasses[TC_CBQ_MAXPRIO + 1]; - unsigned int quanta[TC_CBQ_MAXPRIO + 1]; - - struct cbq_class link; - - unsigned int activemask; - struct cbq_class *active[TC_CBQ_MAXPRIO + 1]; /* List of all classes - with backlog */ - -#ifdef CONFIG_NET_CLS_ACT - struct cbq_class *rx_class; -#endif - struct cbq_class *tx_class; - struct cbq_class *tx_borrowed; - int tx_len; - psched_time_t now; /* Cached timestamp */ - unsigned int pmask; - - struct qdisc_watchdog watchdog; /* Watchdog timer, - started when CBQ has - backlog, but cannot - transmit just now */ - psched_tdiff_t wd_expires; - int toplevel; - u32 hgenerator; -}; - - -#define L2T(cl, len) qdisc_l2t((cl)->R_tab, len) - -static inline struct cbq_class * -cbq_class_lookup(struct cbq_sched_data *q, u32 classid) -{ - struct Qdisc_class_common *clc; - - clc = qdisc_class_find(&q->clhash, classid); - if (clc == NULL) - return NULL; - return container_of(clc, struct cbq_class, common); -} - -#ifdef CONFIG_NET_CLS_ACT - -static struct cbq_class * -cbq_reclassify(struct sk_buff *skb, struct cbq_class *this) -{ - struct cbq_class *cl; - - for (cl = this->tparent; cl; cl = cl->tparent) { - struct cbq_class *new = cl->defaults[TC_PRIO_BESTEFFORT]; - - if (new != NULL && new != this) - return new; - } - return NULL; -} - -#endif - -/* Classify packet. The procedure is pretty complicated, but - * it allows us to combine link sharing and priority scheduling - * transparently. - * - * Namely, you can put link sharing rules (f.e. route based) at root of CBQ, - * so that it resolves to split nodes. Then packets are classified - * by logical priority, or a more specific classifier may be attached - * to the split node. - */ - -static struct cbq_class * -cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *head = &q->link; - struct cbq_class **defmap; - struct cbq_class *cl = NULL; - u32 prio = skb->priority; - struct tcf_proto *fl; - struct tcf_result res; - - /* - * Step 1. If skb->priority points to one of our classes, use it. - */ - if (TC_H_MAJ(prio ^ sch->handle) == 0 && - (cl = cbq_class_lookup(q, prio)) != NULL) - return cl; - - *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - for (;;) { - int result = 0; - defmap = head->defaults; - - fl = rcu_dereference_bh(head->filter_list); - /* - * Step 2+n. Apply classifier. - */ - result = tcf_classify(skb, NULL, fl, &res, true); - if (!fl || result < 0) - goto fallback; - if (result == TC_ACT_SHOT) - return NULL; - - cl = (void *)res.class; - if (!cl) { - if (TC_H_MAJ(res.classid)) - cl = cbq_class_lookup(q, res.classid); - else if ((cl = defmap[res.classid & TC_PRIO_MAX]) == NULL) - cl = defmap[TC_PRIO_BESTEFFORT]; - - if (cl == NULL) - goto fallback; - } - if (cl->level >= head->level) - goto fallback; -#ifdef CONFIG_NET_CLS_ACT - switch (result) { - case TC_ACT_QUEUED: - case TC_ACT_STOLEN: - case TC_ACT_TRAP: - *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - fallthrough; - case TC_ACT_RECLASSIFY: - return cbq_reclassify(skb, cl); - } -#endif - if (cl->level == 0) - return cl; - - /* - * Step 3+n. If classifier selected a link sharing class, - * apply agency specific classifier. - * Repeat this procedure until we hit a leaf node. - */ - head = cl; - } - -fallback: - cl = head; - - /* - * Step 4. No success... - */ - if (TC_H_MAJ(prio) == 0 && - !(cl = head->defaults[prio & TC_PRIO_MAX]) && - !(cl = head->defaults[TC_PRIO_BESTEFFORT])) - return head; - - return cl; -} - -/* - * A packet has just been enqueued on the empty class. - * cbq_activate_class adds it to the tail of active class list - * of its priority band. - */ - -static inline void cbq_activate_class(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - int prio = cl->cpriority; - struct cbq_class *cl_tail; - - cl_tail = q->active[prio]; - q->active[prio] = cl; - - if (cl_tail != NULL) { - cl->next_alive = cl_tail->next_alive; - cl_tail->next_alive = cl; - } else { - cl->next_alive = cl; - q->activemask |= (1<qdisc); - int prio = this->cpriority; - struct cbq_class *cl; - struct cbq_class *cl_prev = q->active[prio]; - - do { - cl = cl_prev->next_alive; - if (cl == this) { - cl_prev->next_alive = cl->next_alive; - cl->next_alive = NULL; - - if (cl == q->active[prio]) { - q->active[prio] = cl_prev; - if (cl == q->active[prio]) { - q->active[prio] = NULL; - q->activemask &= ~(1<active[prio]); -} - -static void -cbq_mark_toplevel(struct cbq_sched_data *q, struct cbq_class *cl) -{ - int toplevel = q->toplevel; - - if (toplevel > cl->level) { - psched_time_t now = psched_get_time(); - - do { - if (cl->undertime < now) { - q->toplevel = cl->level; - return; - } - } while ((cl = cl->borrow) != NULL && toplevel > cl->level); - } -} - -static int -cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch, - struct sk_buff **to_free) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - int ret; - struct cbq_class *cl = cbq_classify(skb, sch, &ret); - -#ifdef CONFIG_NET_CLS_ACT - q->rx_class = cl; -#endif - if (cl == NULL) { - if (ret & __NET_XMIT_BYPASS) - qdisc_qstats_drop(sch); - __qdisc_drop(skb, to_free); - return ret; - } - - ret = qdisc_enqueue(skb, cl->q, to_free); - if (ret == NET_XMIT_SUCCESS) { - sch->q.qlen++; - cbq_mark_toplevel(q, cl); - if (!cl->next_alive) - cbq_activate_class(cl); - return ret; - } - - if (net_xmit_drop_count(ret)) { - qdisc_qstats_drop(sch); - cbq_mark_toplevel(q, cl); - cl->qstats.drops++; - } - return ret; -} - -/* Overlimit action: penalize leaf class by adding offtime */ -static void cbq_overlimit(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - psched_tdiff_t delay = cl->undertime - q->now; - - if (!cl->delayed) { - delay += cl->offtime; - - /* - * Class goes to sleep, so that it will have no - * chance to work avgidle. Let's forgive it 8) - * - * BTW cbq-2.0 has a crap in this - * place, apparently they forgot to shift it by cl->ewma_log. - */ - if (cl->avgidle < 0) - delay -= (-cl->avgidle) - ((-cl->avgidle) >> cl->ewma_log); - if (cl->avgidle < cl->minidle) - cl->avgidle = cl->minidle; - if (delay <= 0) - delay = 1; - cl->undertime = q->now + delay; - - cl->xstats.overactions++; - cl->delayed = 1; - } - if (q->wd_expires == 0 || q->wd_expires > delay) - q->wd_expires = delay; - - /* Dirty work! We must schedule wakeups based on - * real available rate, rather than leaf rate, - * which may be tiny (even zero). - */ - if (q->toplevel == TC_CBQ_MAXLEVEL) { - struct cbq_class *b; - psched_tdiff_t base_delay = q->wd_expires; - - for (b = cl->borrow; b; b = b->borrow) { - delay = b->undertime - q->now; - if (delay < base_delay) { - if (delay <= 0) - delay = 1; - base_delay = delay; - } - } - - q->wd_expires = base_delay; - } -} - -/* - * It is mission critical procedure. - * - * We "regenerate" toplevel cutoff, if transmitting class - * has backlog and it is not regulated. It is not part of - * original CBQ description, but looks more reasonable. - * Probably, it is wrong. This question needs further investigation. - */ - -static inline void -cbq_update_toplevel(struct cbq_sched_data *q, struct cbq_class *cl, - struct cbq_class *borrowed) -{ - if (cl && q->toplevel >= borrowed->level) { - if (cl->q->q.qlen > 1) { - do { - if (borrowed->undertime == PSCHED_PASTPERFECT) { - q->toplevel = borrowed->level; - return; - } - } while ((borrowed = borrowed->borrow) != NULL); - } -#if 0 - /* It is not necessary now. Uncommenting it - will save CPU cycles, but decrease fairness. - */ - q->toplevel = TC_CBQ_MAXLEVEL; -#endif - } -} - -static void -cbq_update(struct cbq_sched_data *q) -{ - struct cbq_class *this = q->tx_class; - struct cbq_class *cl = this; - int len = q->tx_len; - psched_time_t now; - - q->tx_class = NULL; - /* Time integrator. We calculate EOS time - * by adding expected packet transmission time. - */ - now = q->now + L2T(&q->link, len); - - for ( ; cl; cl = cl->share) { - long avgidle = cl->avgidle; - long idle; - - _bstats_update(&cl->bstats, len, 1); - - /* - * (now - last) is total time between packet right edges. - * (last_pktlen/rate) is "virtual" busy time, so that - * - * idle = (now - last) - last_pktlen/rate - */ - - idle = now - cl->last; - if ((unsigned long)idle > 128*1024*1024) { - avgidle = cl->maxidle; - } else { - idle -= L2T(cl, len); - - /* true_avgidle := (1-W)*true_avgidle + W*idle, - * where W=2^{-ewma_log}. But cl->avgidle is scaled: - * cl->avgidle == true_avgidle/W, - * hence: - */ - avgidle += idle - (avgidle>>cl->ewma_log); - } - - if (avgidle <= 0) { - /* Overlimit or at-limit */ - - if (avgidle < cl->minidle) - avgidle = cl->minidle; - - cl->avgidle = avgidle; - - /* Calculate expected time, when this class - * will be allowed to send. - * It will occur, when: - * (1-W)*true_avgidle + W*delay = 0, i.e. - * idle = (1/W - 1)*(-true_avgidle) - * or - * idle = (1 - W)*(-cl->avgidle); - */ - idle = (-avgidle) - ((-avgidle) >> cl->ewma_log); - - /* - * That is not all. - * To maintain the rate allocated to the class, - * we add to undertime virtual clock, - * necessary to complete transmitted packet. - * (len/phys_bandwidth has been already passed - * to the moment of cbq_update) - */ - - idle -= L2T(&q->link, len); - idle += L2T(cl, len); - - cl->undertime = now + idle; - } else { - /* Underlimit */ - - cl->undertime = PSCHED_PASTPERFECT; - if (avgidle > cl->maxidle) - cl->avgidle = cl->maxidle; - else - cl->avgidle = avgidle; - } - if ((s64)(now - cl->last) > 0) - cl->last = now; - } - - cbq_update_toplevel(q, this, q->tx_borrowed); -} - -static inline struct cbq_class * -cbq_under_limit(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - struct cbq_class *this_cl = cl; - - if (cl->tparent == NULL) - return cl; - - if (cl->undertime == PSCHED_PASTPERFECT || q->now >= cl->undertime) { - cl->delayed = 0; - return cl; - } - - do { - /* It is very suspicious place. Now overlimit - * action is generated for not bounded classes - * only if link is completely congested. - * Though it is in agree with ancestor-only paradigm, - * it looks very stupid. Particularly, - * it means that this chunk of code will either - * never be called or result in strong amplification - * of burstiness. Dangerous, silly, and, however, - * no another solution exists. - */ - cl = cl->borrow; - if (!cl) { - this_cl->qstats.overlimits++; - cbq_overlimit(this_cl); - return NULL; - } - if (cl->level > q->toplevel) - return NULL; - } while (cl->undertime != PSCHED_PASTPERFECT && q->now < cl->undertime); - - cl->delayed = 0; - return cl; -} - -static inline struct sk_buff * -cbq_dequeue_prio(struct Qdisc *sch, int prio) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl_tail, *cl_prev, *cl; - struct sk_buff *skb; - int deficit; - - cl_tail = cl_prev = q->active[prio]; - cl = cl_prev->next_alive; - - do { - deficit = 0; - - /* Start round */ - do { - struct cbq_class *borrow = cl; - - if (cl->q->q.qlen && - (borrow = cbq_under_limit(cl)) == NULL) - goto skip_class; - - if (cl->deficit <= 0) { - /* Class exhausted its allotment per - * this round. Switch to the next one. - */ - deficit = 1; - cl->deficit += cl->quantum; - goto next_class; - } - - skb = cl->q->dequeue(cl->q); - - /* Class did not give us any skb :-( - * It could occur even if cl->q->q.qlen != 0 - * f.e. if cl->q == "tbf" - */ - if (skb == NULL) - goto skip_class; - - cl->deficit -= qdisc_pkt_len(skb); - q->tx_class = cl; - q->tx_borrowed = borrow; - if (borrow != cl) { -#ifndef CBQ_XSTATS_BORROWS_BYTES - borrow->xstats.borrows++; - cl->xstats.borrows++; -#else - borrow->xstats.borrows += qdisc_pkt_len(skb); - cl->xstats.borrows += qdisc_pkt_len(skb); -#endif - } - q->tx_len = qdisc_pkt_len(skb); - - if (cl->deficit <= 0) { - q->active[prio] = cl; - cl = cl->next_alive; - cl->deficit += cl->quantum; - } - return skb; - -skip_class: - if (cl->q->q.qlen == 0 || prio != cl->cpriority) { - /* Class is empty or penalized. - * Unlink it from active chain. - */ - cl_prev->next_alive = cl->next_alive; - cl->next_alive = NULL; - - /* Did cl_tail point to it? */ - if (cl == cl_tail) { - /* Repair it! */ - cl_tail = cl_prev; - - /* Was it the last class in this band? */ - if (cl == cl_tail) { - /* Kill the band! */ - q->active[prio] = NULL; - q->activemask &= ~(1<q->q.qlen) - cbq_activate_class(cl); - return NULL; - } - - q->active[prio] = cl_tail; - } - if (cl->q->q.qlen) - cbq_activate_class(cl); - - cl = cl_prev; - } - -next_class: - cl_prev = cl; - cl = cl->next_alive; - } while (cl_prev != cl_tail); - } while (deficit); - - q->active[prio] = cl_prev; - - return NULL; -} - -static inline struct sk_buff * -cbq_dequeue_1(struct Qdisc *sch) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct sk_buff *skb; - unsigned int activemask; - - activemask = q->activemask & 0xFF; - while (activemask) { - int prio = ffz(~activemask); - activemask &= ~(1<tx_class) - cbq_update(q); - - q->now = now; - - for (;;) { - q->wd_expires = 0; - - skb = cbq_dequeue_1(sch); - if (skb) { - qdisc_bstats_update(sch, skb); - sch->q.qlen--; - return skb; - } - - /* All the classes are overlimit. - * - * It is possible, if: - * - * 1. Scheduler is empty. - * 2. Toplevel cutoff inhibited borrowing. - * 3. Root class is overlimit. - * - * Reset 2d and 3d conditions and retry. - * - * Note, that NS and cbq-2.0 are buggy, peeking - * an arbitrary class is appropriate for ancestor-only - * sharing, but not for toplevel algorithm. - * - * Our version is better, but slower, because it requires - * two passes, but it is unavoidable with top-level sharing. - */ - - if (q->toplevel == TC_CBQ_MAXLEVEL && - q->link.undertime == PSCHED_PASTPERFECT) - break; - - q->toplevel = TC_CBQ_MAXLEVEL; - q->link.undertime = PSCHED_PASTPERFECT; - } - - /* No packets in scheduler or nobody wants to give them to us :-( - * Sigh... start watchdog timer in the last case. - */ - - if (sch->q.qlen) { - qdisc_qstats_overlimit(sch); - if (q->wd_expires) - qdisc_watchdog_schedule(&q->watchdog, - now + q->wd_expires); - } - return NULL; -} - -/* CBQ class maintenance routines */ - -static void cbq_adjust_levels(struct cbq_class *this) -{ - if (this == NULL) - return; - - do { - int level = 0; - struct cbq_class *cl; - - cl = this->children; - if (cl) { - do { - if (cl->level > level) - level = cl->level; - } while ((cl = cl->sibling) != this->children); - } - this->level = level + 1; - } while ((this = this->tparent) != NULL); -} - -static void cbq_normalize_quanta(struct cbq_sched_data *q, int prio) -{ - struct cbq_class *cl; - unsigned int h; - - if (q->quanta[prio] == 0) - return; - - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - /* BUGGGG... Beware! This expression suffer of - * arithmetic overflows! - */ - if (cl->priority == prio) { - cl->quantum = (cl->weight*cl->allot*q->nclasses[prio])/ - q->quanta[prio]; - } - if (cl->quantum <= 0 || - cl->quantum > 32*qdisc_dev(cl->qdisc)->mtu) { - pr_warn("CBQ: class %08x has bad quantum==%ld, repaired.\n", - cl->common.classid, cl->quantum); - cl->quantum = qdisc_dev(cl->qdisc)->mtu/2 + 1; - } - } - } -} - -static void cbq_sync_defmap(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - struct cbq_class *split = cl->split; - unsigned int h; - int i; - - if (split == NULL) - return; - - for (i = 0; i <= TC_PRIO_MAX; i++) { - if (split->defaults[i] == cl && !(cl->defmap & (1<defaults[i] = NULL; - } - - for (i = 0; i <= TC_PRIO_MAX; i++) { - int level = split->level; - - if (split->defaults[i]) - continue; - - for (h = 0; h < q->clhash.hashsize; h++) { - struct cbq_class *c; - - hlist_for_each_entry(c, &q->clhash.hash[h], - common.hnode) { - if (c->split == split && c->level < level && - c->defmap & (1<defaults[i] = c; - level = c->level; - } - } - } - } -} - -static void cbq_change_defmap(struct cbq_class *cl, u32 splitid, u32 def, u32 mask) -{ - struct cbq_class *split = NULL; - - if (splitid == 0) { - split = cl->split; - if (!split) - return; - splitid = split->common.classid; - } - - if (split == NULL || split->common.classid != splitid) { - for (split = cl->tparent; split; split = split->tparent) - if (split->common.classid == splitid) - break; - } - - if (split == NULL) - return; - - if (cl->split != split) { - cl->defmap = 0; - cbq_sync_defmap(cl); - cl->split = split; - cl->defmap = def & mask; - } else - cl->defmap = (cl->defmap & ~mask) | (def & mask); - - cbq_sync_defmap(cl); -} - -static void cbq_unlink_class(struct cbq_class *this) -{ - struct cbq_class *cl, **clp; - struct cbq_sched_data *q = qdisc_priv(this->qdisc); - - qdisc_class_hash_remove(&q->clhash, &this->common); - - if (this->tparent) { - clp = &this->sibling; - cl = *clp; - do { - if (cl == this) { - *clp = cl->sibling; - break; - } - clp = &cl->sibling; - } while ((cl = *clp) != this->sibling); - - if (this->tparent->children == this) { - this->tparent->children = this->sibling; - if (this->sibling == this) - this->tparent->children = NULL; - } - } else { - WARN_ON(this->sibling != this); - } -} - -static void cbq_link_class(struct cbq_class *this) -{ - struct cbq_sched_data *q = qdisc_priv(this->qdisc); - struct cbq_class *parent = this->tparent; - - this->sibling = this; - qdisc_class_hash_insert(&q->clhash, &this->common); - - if (parent == NULL) - return; - - if (parent->children == NULL) { - parent->children = this; - } else { - this->sibling = parent->children->sibling; - parent->children->sibling = this; - } -} - -static void -cbq_reset(struct Qdisc *sch) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl; - int prio; - unsigned int h; - - q->activemask = 0; - q->pmask = 0; - q->tx_class = NULL; - q->tx_borrowed = NULL; - qdisc_watchdog_cancel(&q->watchdog); - q->toplevel = TC_CBQ_MAXLEVEL; - q->now = psched_get_time(); - - for (prio = 0; prio <= TC_CBQ_MAXPRIO; prio++) - q->active[prio] = NULL; - - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - qdisc_reset(cl->q); - - cl->next_alive = NULL; - cl->undertime = PSCHED_PASTPERFECT; - cl->avgidle = cl->maxidle; - cl->deficit = cl->quantum; - cl->cpriority = cl->priority; - } - } -} - - -static void cbq_set_lss(struct cbq_class *cl, struct tc_cbq_lssopt *lss) -{ - if (lss->change & TCF_CBQ_LSS_FLAGS) { - cl->share = (lss->flags & TCF_CBQ_LSS_ISOLATED) ? NULL : cl->tparent; - cl->borrow = (lss->flags & TCF_CBQ_LSS_BOUNDED) ? NULL : cl->tparent; - } - if (lss->change & TCF_CBQ_LSS_EWMA) - cl->ewma_log = lss->ewma_log; - if (lss->change & TCF_CBQ_LSS_AVPKT) - cl->avpkt = lss->avpkt; - if (lss->change & TCF_CBQ_LSS_MINIDLE) - cl->minidle = -(long)lss->minidle; - if (lss->change & TCF_CBQ_LSS_MAXIDLE) { - cl->maxidle = lss->maxidle; - cl->avgidle = lss->maxidle; - } - if (lss->change & TCF_CBQ_LSS_OFFTIME) - cl->offtime = lss->offtime; -} - -static void cbq_rmprio(struct cbq_sched_data *q, struct cbq_class *cl) -{ - q->nclasses[cl->priority]--; - q->quanta[cl->priority] -= cl->weight; - cbq_normalize_quanta(q, cl->priority); -} - -static void cbq_addprio(struct cbq_sched_data *q, struct cbq_class *cl) -{ - q->nclasses[cl->priority]++; - q->quanta[cl->priority] += cl->weight; - cbq_normalize_quanta(q, cl->priority); -} - -static int cbq_set_wrr(struct cbq_class *cl, struct tc_cbq_wrropt *wrr) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - - if (wrr->allot) - cl->allot = wrr->allot; - if (wrr->weight) - cl->weight = wrr->weight; - if (wrr->priority) { - cl->priority = wrr->priority - 1; - cl->cpriority = cl->priority; - if (cl->priority >= cl->priority2) - cl->priority2 = TC_CBQ_MAXPRIO - 1; - } - - cbq_addprio(q, cl); - return 0; -} - -static int cbq_set_fopt(struct cbq_class *cl, struct tc_cbq_fopt *fopt) -{ - cbq_change_defmap(cl, fopt->split, fopt->defmap, fopt->defchange); - return 0; -} - -static const struct nla_policy cbq_policy[TCA_CBQ_MAX + 1] = { - [TCA_CBQ_LSSOPT] = { .len = sizeof(struct tc_cbq_lssopt) }, - [TCA_CBQ_WRROPT] = { .len = sizeof(struct tc_cbq_wrropt) }, - [TCA_CBQ_FOPT] = { .len = sizeof(struct tc_cbq_fopt) }, - [TCA_CBQ_OVL_STRATEGY] = { .len = sizeof(struct tc_cbq_ovl) }, - [TCA_CBQ_RATE] = { .len = sizeof(struct tc_ratespec) }, - [TCA_CBQ_RTAB] = { .type = NLA_BINARY, .len = TC_RTAB_SIZE }, - [TCA_CBQ_POLICE] = { .len = sizeof(struct tc_cbq_police) }, -}; - -static int cbq_opt_parse(struct nlattr *tb[TCA_CBQ_MAX + 1], - struct nlattr *opt, - struct netlink_ext_ack *extack) -{ - int err; - - if (!opt) { - NL_SET_ERR_MSG(extack, "CBQ options are required for this operation"); - return -EINVAL; - } - - err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, - cbq_policy, extack); - if (err < 0) - return err; - - if (tb[TCA_CBQ_WRROPT]) { - const struct tc_cbq_wrropt *wrr = nla_data(tb[TCA_CBQ_WRROPT]); - - if (wrr->priority > TC_CBQ_MAXPRIO) { - NL_SET_ERR_MSG(extack, "priority is bigger than TC_CBQ_MAXPRIO"); - err = -EINVAL; - } - } - return err; -} - -static int cbq_init(struct Qdisc *sch, struct nlattr *opt, - struct netlink_ext_ack *extack) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct nlattr *tb[TCA_CBQ_MAX + 1]; - struct tc_ratespec *r; - int err; - - qdisc_watchdog_init(&q->watchdog, sch); - - err = cbq_opt_parse(tb, opt, extack); - if (err < 0) - return err; - - if (!tb[TCA_CBQ_RTAB] || !tb[TCA_CBQ_RATE]) { - NL_SET_ERR_MSG(extack, "Rate specification missing or incomplete"); - return -EINVAL; - } - - r = nla_data(tb[TCA_CBQ_RATE]); - - q->link.R_tab = qdisc_get_rtab(r, tb[TCA_CBQ_RTAB], extack); - if (!q->link.R_tab) - return -EINVAL; - - err = tcf_block_get(&q->link.block, &q->link.filter_list, sch, extack); - if (err) - goto put_rtab; - - err = qdisc_class_hash_init(&q->clhash); - if (err < 0) - goto put_block; - - q->link.sibling = &q->link; - q->link.common.classid = sch->handle; - q->link.qdisc = sch; - q->link.q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - sch->handle, NULL); - if (!q->link.q) - q->link.q = &noop_qdisc; - else - qdisc_hash_add(q->link.q, true); - - q->link.priority = TC_CBQ_MAXPRIO - 1; - q->link.priority2 = TC_CBQ_MAXPRIO - 1; - q->link.cpriority = TC_CBQ_MAXPRIO - 1; - q->link.allot = psched_mtu(qdisc_dev(sch)); - q->link.quantum = q->link.allot; - q->link.weight = q->link.R_tab->rate.rate; - - q->link.ewma_log = TC_CBQ_DEF_EWMA; - q->link.avpkt = q->link.allot/2; - q->link.minidle = -0x7FFFFFFF; - - q->toplevel = TC_CBQ_MAXLEVEL; - q->now = psched_get_time(); - - cbq_link_class(&q->link); - - if (tb[TCA_CBQ_LSSOPT]) - cbq_set_lss(&q->link, nla_data(tb[TCA_CBQ_LSSOPT])); - - cbq_addprio(q, &q->link); - return 0; - -put_block: - tcf_block_put(q->link.block); - -put_rtab: - qdisc_put_rtab(q->link.R_tab); - return err; -} - -static int cbq_dump_rate(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - - if (nla_put(skb, TCA_CBQ_RATE, sizeof(cl->R_tab->rate), &cl->R_tab->rate)) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_lss(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cbq_lssopt opt; - - opt.flags = 0; - if (cl->borrow == NULL) - opt.flags |= TCF_CBQ_LSS_BOUNDED; - if (cl->share == NULL) - opt.flags |= TCF_CBQ_LSS_ISOLATED; - opt.ewma_log = cl->ewma_log; - opt.level = cl->level; - opt.avpkt = cl->avpkt; - opt.maxidle = cl->maxidle; - opt.minidle = (u32)(-cl->minidle); - opt.offtime = cl->offtime; - opt.change = ~0; - if (nla_put(skb, TCA_CBQ_LSSOPT, sizeof(opt), &opt)) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_wrr(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cbq_wrropt opt; - - memset(&opt, 0, sizeof(opt)); - opt.flags = 0; - opt.allot = cl->allot; - opt.priority = cl->priority + 1; - opt.cpriority = cl->cpriority + 1; - opt.weight = cl->weight; - if (nla_put(skb, TCA_CBQ_WRROPT, sizeof(opt), &opt)) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_fopt(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cbq_fopt opt; - - if (cl->split || cl->defmap) { - opt.split = cl->split ? cl->split->common.classid : 0; - opt.defmap = cl->defmap; - opt.defchange = ~0; - if (nla_put(skb, TCA_CBQ_FOPT, sizeof(opt), &opt)) - goto nla_put_failure; - } - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_attr(struct sk_buff *skb, struct cbq_class *cl) -{ - if (cbq_dump_lss(skb, cl) < 0 || - cbq_dump_rate(skb, cl) < 0 || - cbq_dump_wrr(skb, cl) < 0 || - cbq_dump_fopt(skb, cl) < 0) - return -1; - return 0; -} - -static int cbq_dump(struct Qdisc *sch, struct sk_buff *skb) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct nlattr *nest; - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - if (cbq_dump_attr(skb, &q->link) < 0) - goto nla_put_failure; - return nla_nest_end(skb, nest); - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static int -cbq_dump_stats(struct Qdisc *sch, struct gnet_dump *d) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - - q->link.xstats.avgidle = q->link.avgidle; - return gnet_stats_copy_app(d, &q->link.xstats, sizeof(q->link.xstats)); -} - -static int -cbq_dump_class(struct Qdisc *sch, unsigned long arg, - struct sk_buff *skb, struct tcmsg *tcm) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - struct nlattr *nest; - - if (cl->tparent) - tcm->tcm_parent = cl->tparent->common.classid; - else - tcm->tcm_parent = TC_H_ROOT; - tcm->tcm_handle = cl->common.classid; - tcm->tcm_info = cl->q->handle; - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - if (cbq_dump_attr(skb, cl) < 0) - goto nla_put_failure; - return nla_nest_end(skb, nest); - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static int -cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, - struct gnet_dump *d) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)arg; - __u32 qlen; - - cl->xstats.avgidle = cl->avgidle; - cl->xstats.undertime = 0; - qdisc_qstats_qlen_backlog(cl->q, &qlen, &cl->qstats.backlog); - - if (cl->undertime != PSCHED_PASTPERFECT) - cl->xstats.undertime = cl->undertime - q->now; - - if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || - gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || - gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0) - return -1; - - return gnet_stats_copy_app(d, &cl->xstats, sizeof(cl->xstats)); -} - -static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old, struct netlink_ext_ack *extack) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - if (new == NULL) { - new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - cl->common.classid, extack); - if (new == NULL) - return -ENOBUFS; - } - - *old = qdisc_replace(sch, new, &cl->q); - return 0; -} - -static struct Qdisc *cbq_leaf(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - return cl->q; -} - -static void cbq_qlen_notify(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - cbq_deactivate_class(cl); -} - -static unsigned long cbq_find(struct Qdisc *sch, u32 classid) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - - return (unsigned long)cbq_class_lookup(q, classid); -} - -static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - - WARN_ON(cl->filters); - - tcf_block_put(cl->block); - qdisc_put(cl->q); - qdisc_put_rtab(cl->R_tab); - gen_kill_estimator(&cl->rate_est); - if (cl != &q->link) - kfree(cl); -} - -static void cbq_destroy(struct Qdisc *sch) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct hlist_node *next; - struct cbq_class *cl; - unsigned int h; - -#ifdef CONFIG_NET_CLS_ACT - q->rx_class = NULL; -#endif - /* - * Filters must be destroyed first because we don't destroy the - * classes from root to leafs which means that filters can still - * be bound to classes which have been destroyed already. --TGR '04 - */ - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - tcf_block_put(cl->block); - cl->block = NULL; - } - } - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry_safe(cl, next, &q->clhash.hash[h], - common.hnode) - cbq_destroy_class(sch, cl); - } - qdisc_class_hash_destroy(&q->clhash); -} - -static int -cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **tca, - unsigned long *arg, struct netlink_ext_ack *extack) -{ - int err; - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)*arg; - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_CBQ_MAX + 1]; - struct cbq_class *parent; - struct qdisc_rate_table *rtab = NULL; - - err = cbq_opt_parse(tb, opt, extack); - if (err < 0) - return err; - - if (tb[TCA_CBQ_OVL_STRATEGY] || tb[TCA_CBQ_POLICE]) { - NL_SET_ERR_MSG(extack, "Neither overlimit strategy nor policing attributes can be used for changing class params"); - return -EOPNOTSUPP; - } - - if (cl) { - /* Check parent */ - if (parentid) { - if (cl->tparent && - cl->tparent->common.classid != parentid) { - NL_SET_ERR_MSG(extack, "Invalid parent id"); - return -EINVAL; - } - if (!cl->tparent && parentid != TC_H_ROOT) { - NL_SET_ERR_MSG(extack, "Parent must be root"); - return -EINVAL; - } - } - - if (tb[TCA_CBQ_RATE]) { - rtab = qdisc_get_rtab(nla_data(tb[TCA_CBQ_RATE]), - tb[TCA_CBQ_RTAB], extack); - if (rtab == NULL) - return -EINVAL; - } - - if (tca[TCA_RATE]) { - err = gen_replace_estimator(&cl->bstats, NULL, - &cl->rate_est, - NULL, - true, - tca[TCA_RATE]); - if (err) { - NL_SET_ERR_MSG(extack, "Failed to replace specified rate estimator"); - qdisc_put_rtab(rtab); - return err; - } - } - - /* Change class parameters */ - sch_tree_lock(sch); - - if (cl->next_alive != NULL) - cbq_deactivate_class(cl); - - if (rtab) { - qdisc_put_rtab(cl->R_tab); - cl->R_tab = rtab; - } - - if (tb[TCA_CBQ_LSSOPT]) - cbq_set_lss(cl, nla_data(tb[TCA_CBQ_LSSOPT])); - - if (tb[TCA_CBQ_WRROPT]) { - cbq_rmprio(q, cl); - cbq_set_wrr(cl, nla_data(tb[TCA_CBQ_WRROPT])); - } - - if (tb[TCA_CBQ_FOPT]) - cbq_set_fopt(cl, nla_data(tb[TCA_CBQ_FOPT])); - - if (cl->q->q.qlen) - cbq_activate_class(cl); - - sch_tree_unlock(sch); - - return 0; - } - - if (parentid == TC_H_ROOT) - return -EINVAL; - - if (!tb[TCA_CBQ_WRROPT] || !tb[TCA_CBQ_RATE] || !tb[TCA_CBQ_LSSOPT]) { - NL_SET_ERR_MSG(extack, "One of the following attributes MUST be specified: WRR, rate or link sharing"); - return -EINVAL; - } - - rtab = qdisc_get_rtab(nla_data(tb[TCA_CBQ_RATE]), tb[TCA_CBQ_RTAB], - extack); - if (rtab == NULL) - return -EINVAL; - - if (classid) { - err = -EINVAL; - if (TC_H_MAJ(classid ^ sch->handle) || - cbq_class_lookup(q, classid)) { - NL_SET_ERR_MSG(extack, "Specified class not found"); - goto failure; - } - } else { - int i; - classid = TC_H_MAKE(sch->handle, 0x8000); - - for (i = 0; i < 0x8000; i++) { - if (++q->hgenerator >= 0x8000) - q->hgenerator = 1; - if (cbq_class_lookup(q, classid|q->hgenerator) == NULL) - break; - } - err = -ENOSR; - if (i >= 0x8000) { - NL_SET_ERR_MSG(extack, "Unable to generate classid"); - goto failure; - } - classid = classid|q->hgenerator; - } - - parent = &q->link; - if (parentid) { - parent = cbq_class_lookup(q, parentid); - err = -EINVAL; - if (!parent) { - NL_SET_ERR_MSG(extack, "Failed to find parentid"); - goto failure; - } - } - - err = -ENOBUFS; - cl = kzalloc(sizeof(*cl), GFP_KERNEL); - if (cl == NULL) - goto failure; - - gnet_stats_basic_sync_init(&cl->bstats); - err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); - if (err) { - kfree(cl); - goto failure; - } - - if (tca[TCA_RATE]) { - err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, true, tca[TCA_RATE]); - if (err) { - NL_SET_ERR_MSG(extack, "Couldn't create new estimator"); - tcf_block_put(cl->block); - kfree(cl); - goto failure; - } - } - - cl->R_tab = rtab; - rtab = NULL; - cl->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid, - NULL); - if (!cl->q) - cl->q = &noop_qdisc; - else - qdisc_hash_add(cl->q, true); - - cl->common.classid = classid; - cl->tparent = parent; - cl->qdisc = sch; - cl->allot = parent->allot; - cl->quantum = cl->allot; - cl->weight = cl->R_tab->rate.rate; - - sch_tree_lock(sch); - cbq_link_class(cl); - cl->borrow = cl->tparent; - if (cl->tparent != &q->link) - cl->share = cl->tparent; - cbq_adjust_levels(parent); - cl->minidle = -0x7FFFFFFF; - cbq_set_lss(cl, nla_data(tb[TCA_CBQ_LSSOPT])); - cbq_set_wrr(cl, nla_data(tb[TCA_CBQ_WRROPT])); - if (cl->ewma_log == 0) - cl->ewma_log = q->link.ewma_log; - if (cl->maxidle == 0) - cl->maxidle = q->link.maxidle; - if (cl->avpkt == 0) - cl->avpkt = q->link.avpkt; - if (tb[TCA_CBQ_FOPT]) - cbq_set_fopt(cl, nla_data(tb[TCA_CBQ_FOPT])); - sch_tree_unlock(sch); - - qdisc_class_hash_grow(sch, &q->clhash); - - *arg = (unsigned long)cl; - return 0; - -failure: - qdisc_put_rtab(rtab); - return err; -} - -static int cbq_delete(struct Qdisc *sch, unsigned long arg, - struct netlink_ext_ack *extack) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)arg; - - if (cl->filters || cl->children || cl == &q->link) - return -EBUSY; - - sch_tree_lock(sch); - - qdisc_purge_queue(cl->q); - - if (cl->next_alive) - cbq_deactivate_class(cl); - - if (q->tx_borrowed == cl) - q->tx_borrowed = q->tx_class; - if (q->tx_class == cl) { - q->tx_class = NULL; - q->tx_borrowed = NULL; - } -#ifdef CONFIG_NET_CLS_ACT - if (q->rx_class == cl) - q->rx_class = NULL; -#endif - - cbq_unlink_class(cl); - cbq_adjust_levels(cl->tparent); - cl->defmap = 0; - cbq_sync_defmap(cl); - - cbq_rmprio(q, cl); - sch_tree_unlock(sch); - - cbq_destroy_class(sch, cl); - return 0; -} - -static struct tcf_block *cbq_tcf_block(struct Qdisc *sch, unsigned long arg, - struct netlink_ext_ack *extack) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)arg; - - if (cl == NULL) - cl = &q->link; - - return cl->block; -} - -static unsigned long cbq_bind_filter(struct Qdisc *sch, unsigned long parent, - u32 classid) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *p = (struct cbq_class *)parent; - struct cbq_class *cl = cbq_class_lookup(q, classid); - - if (cl) { - if (p && p->level <= cl->level) - return 0; - cl->filters++; - return (unsigned long)cl; - } - return 0; -} - -static void cbq_unbind_filter(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - cl->filters--; -} - -static void cbq_walk(struct Qdisc *sch, struct qdisc_walker *arg) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl; - unsigned int h; - - if (arg->stop) - return; - - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - if (!tc_qdisc_stats_dump(sch, (unsigned long)cl, arg)) - return; - } - } -} - -static const struct Qdisc_class_ops cbq_class_ops = { - .graft = cbq_graft, - .leaf = cbq_leaf, - .qlen_notify = cbq_qlen_notify, - .find = cbq_find, - .change = cbq_change_class, - .delete = cbq_delete, - .walk = cbq_walk, - .tcf_block = cbq_tcf_block, - .bind_tcf = cbq_bind_filter, - .unbind_tcf = cbq_unbind_filter, - .dump = cbq_dump_class, - .dump_stats = cbq_dump_class_stats, -}; - -static struct Qdisc_ops cbq_qdisc_ops __read_mostly = { - .next = NULL, - .cl_ops = &cbq_class_ops, - .id = "cbq", - .priv_size = sizeof(struct cbq_sched_data), - .enqueue = cbq_enqueue, - .dequeue = cbq_dequeue, - .peek = qdisc_peek_dequeued, - .init = cbq_init, - .reset = cbq_reset, - .destroy = cbq_destroy, - .change = NULL, - .dump = cbq_dump, - .dump_stats = cbq_dump_stats, - .owner = THIS_MODULE, -}; - -static int __init cbq_module_init(void) -{ - return register_qdisc(&cbq_qdisc_ops); -} -static void __exit cbq_module_exit(void) -{ - unregister_qdisc(&cbq_qdisc_ops); -} -module_init(cbq_module_init) -module_exit(cbq_module_exit) -MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c deleted file mode 100644 index 401ffaf87d6221cda528dbfcbf2f0fe3d4c81585..0000000000000000000000000000000000000000 --- a/net/sched/sch_dsmark.c +++ /dev/null @@ -1,518 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* net/sched/sch_dsmark.c - Differentiated Services field marker */ - -/* Written 1998-2000 by Werner Almesberger, EPFL ICA */ - - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -/* - * classid class marking - * ------- ----- ------- - * n/a 0 n/a - * x:0 1 use entry [0] - * ... ... ... - * x:y y>0 y+1 use entry [y] - * ... ... ... - * x:indices-1 indices use entry [indices-1] - * ... ... ... - * x:y y+1 use entry [y & (indices-1)] - * ... ... ... - * 0xffff 0x10000 use entry [indices-1] - */ - - -#define NO_DEFAULT_INDEX (1 << 16) - -struct mask_value { - u8 mask; - u8 value; -}; - -struct dsmark_qdisc_data { - struct Qdisc *q; - struct tcf_proto __rcu *filter_list; - struct tcf_block *block; - struct mask_value *mv; - u16 indices; - u8 set_tc_index; - u32 default_index; /* index range is 0...0xffff */ -#define DSMARK_EMBEDDED_SZ 16 - struct mask_value embedded[DSMARK_EMBEDDED_SZ]; -}; - -static inline int dsmark_valid_index(struct dsmark_qdisc_data *p, u16 index) -{ - return index <= p->indices && index > 0; -} - -/* ------------------------- Class/flow operations ------------------------- */ - -static int dsmark_graft(struct Qdisc *sch, unsigned long arg, - struct Qdisc *new, struct Qdisc **old, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p],new %p,old %p)\n", - __func__, sch, p, new, old); - - if (new == NULL) { - new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - sch->handle, NULL); - if (new == NULL) - new = &noop_qdisc; - } - - *old = qdisc_replace(sch, new, &p->q); - return 0; -} - -static struct Qdisc *dsmark_leaf(struct Qdisc *sch, unsigned long arg) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - return p->q; -} - -static unsigned long dsmark_find(struct Qdisc *sch, u32 classid) -{ - return TC_H_MIN(classid) + 1; -} - -static unsigned long dsmark_bind_filter(struct Qdisc *sch, - unsigned long parent, u32 classid) -{ - pr_debug("%s(sch %p,[qdisc %p],classid %x)\n", - __func__, sch, qdisc_priv(sch), classid); - - return dsmark_find(sch, classid); -} - -static void dsmark_unbind_filter(struct Qdisc *sch, unsigned long cl) -{ -} - -static const struct nla_policy dsmark_policy[TCA_DSMARK_MAX + 1] = { - [TCA_DSMARK_INDICES] = { .type = NLA_U16 }, - [TCA_DSMARK_DEFAULT_INDEX] = { .type = NLA_U16 }, - [TCA_DSMARK_SET_TC_INDEX] = { .type = NLA_FLAG }, - [TCA_DSMARK_MASK] = { .type = NLA_U8 }, - [TCA_DSMARK_VALUE] = { .type = NLA_U8 }, -}; - -static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent, - struct nlattr **tca, unsigned long *arg, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_DSMARK_MAX + 1]; - int err = -EINVAL; - - pr_debug("%s(sch %p,[qdisc %p],classid %x,parent %x), arg 0x%lx\n", - __func__, sch, p, classid, parent, *arg); - - if (!dsmark_valid_index(p, *arg)) { - err = -ENOENT; - goto errout; - } - - if (!opt) - goto errout; - - err = nla_parse_nested_deprecated(tb, TCA_DSMARK_MAX, opt, - dsmark_policy, NULL); - if (err < 0) - goto errout; - - if (tb[TCA_DSMARK_VALUE]) - p->mv[*arg - 1].value = nla_get_u8(tb[TCA_DSMARK_VALUE]); - - if (tb[TCA_DSMARK_MASK]) - p->mv[*arg - 1].mask = nla_get_u8(tb[TCA_DSMARK_MASK]); - - err = 0; - -errout: - return err; -} - -static int dsmark_delete(struct Qdisc *sch, unsigned long arg, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - if (!dsmark_valid_index(p, arg)) - return -EINVAL; - - p->mv[arg - 1].mask = 0xff; - p->mv[arg - 1].value = 0; - - return 0; -} - -static void dsmark_walk(struct Qdisc *sch, struct qdisc_walker *walker) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - int i; - - pr_debug("%s(sch %p,[qdisc %p],walker %p)\n", - __func__, sch, p, walker); - - if (walker->stop) - return; - - for (i = 0; i < p->indices; i++) { - if (p->mv[i].mask == 0xff && !p->mv[i].value) { - walker->count++; - continue; - } - if (!tc_qdisc_stats_dump(sch, i + 1, walker)) - break; - } -} - -static struct tcf_block *dsmark_tcf_block(struct Qdisc *sch, unsigned long cl, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - return p->block; -} - -/* --------------------------- Qdisc operations ---------------------------- */ - -static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, - struct sk_buff **to_free) -{ - unsigned int len = qdisc_pkt_len(skb); - struct dsmark_qdisc_data *p = qdisc_priv(sch); - int err; - - pr_debug("%s(skb %p,sch %p,[qdisc %p])\n", __func__, skb, sch, p); - - if (p->set_tc_index) { - int wlen = skb_network_offset(skb); - - switch (skb_protocol(skb, true)) { - case htons(ETH_P_IP): - wlen += sizeof(struct iphdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) - goto drop; - - skb->tc_index = ipv4_get_dsfield(ip_hdr(skb)) - & ~INET_ECN_MASK; - break; - - case htons(ETH_P_IPV6): - wlen += sizeof(struct ipv6hdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) - goto drop; - - skb->tc_index = ipv6_get_dsfield(ipv6_hdr(skb)) - & ~INET_ECN_MASK; - break; - default: - skb->tc_index = 0; - break; - } - } - - if (TC_H_MAJ(skb->priority) == sch->handle) - skb->tc_index = TC_H_MIN(skb->priority); - else { - struct tcf_result res; - struct tcf_proto *fl = rcu_dereference_bh(p->filter_list); - int result = tcf_classify(skb, NULL, fl, &res, false); - - pr_debug("result %d class 0x%04x\n", result, res.classid); - - switch (result) { -#ifdef CONFIG_NET_CLS_ACT - case TC_ACT_QUEUED: - case TC_ACT_STOLEN: - case TC_ACT_TRAP: - __qdisc_drop(skb, to_free); - return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - - case TC_ACT_SHOT: - goto drop; -#endif - case TC_ACT_OK: - skb->tc_index = TC_H_MIN(res.classid); - break; - - default: - if (p->default_index != NO_DEFAULT_INDEX) - skb->tc_index = p->default_index; - break; - } - } - - err = qdisc_enqueue(skb, p->q, to_free); - if (err != NET_XMIT_SUCCESS) { - if (net_xmit_drop_count(err)) - qdisc_qstats_drop(sch); - return err; - } - - sch->qstats.backlog += len; - sch->q.qlen++; - - return NET_XMIT_SUCCESS; - -drop: - qdisc_drop(skb, sch, to_free); - return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; -} - -static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct sk_buff *skb; - u32 index; - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - - skb = qdisc_dequeue_peeked(p->q); - if (skb == NULL) - return NULL; - - qdisc_bstats_update(sch, skb); - qdisc_qstats_backlog_dec(sch, skb); - sch->q.qlen--; - - index = skb->tc_index & (p->indices - 1); - pr_debug("index %d->%d\n", skb->tc_index, index); - - switch (skb_protocol(skb, true)) { - case htons(ETH_P_IP): - ipv4_change_dsfield(ip_hdr(skb), p->mv[index].mask, - p->mv[index].value); - break; - case htons(ETH_P_IPV6): - ipv6_change_dsfield(ipv6_hdr(skb), p->mv[index].mask, - p->mv[index].value); - break; - default: - /* - * Only complain if a change was actually attempted. - * This way, we can send non-IP traffic through dsmark - * and don't need yet another qdisc as a bypass. - */ - if (p->mv[index].mask != 0xff || p->mv[index].value) - pr_warn("%s: unsupported protocol %d\n", - __func__, ntohs(skb_protocol(skb, true))); - break; - } - - return skb; -} - -static struct sk_buff *dsmark_peek(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - - return p->q->ops->peek(p->q); -} - -static int dsmark_init(struct Qdisc *sch, struct nlattr *opt, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *tb[TCA_DSMARK_MAX + 1]; - int err = -EINVAL; - u32 default_index = NO_DEFAULT_INDEX; - u16 indices; - int i; - - pr_debug("%s(sch %p,[qdisc %p],opt %p)\n", __func__, sch, p, opt); - - if (!opt) - goto errout; - - err = tcf_block_get(&p->block, &p->filter_list, sch, extack); - if (err) - return err; - - err = nla_parse_nested_deprecated(tb, TCA_DSMARK_MAX, opt, - dsmark_policy, NULL); - if (err < 0) - goto errout; - - err = -EINVAL; - if (!tb[TCA_DSMARK_INDICES]) - goto errout; - indices = nla_get_u16(tb[TCA_DSMARK_INDICES]); - - if (hweight32(indices) != 1) - goto errout; - - if (tb[TCA_DSMARK_DEFAULT_INDEX]) - default_index = nla_get_u16(tb[TCA_DSMARK_DEFAULT_INDEX]); - - if (indices <= DSMARK_EMBEDDED_SZ) - p->mv = p->embedded; - else - p->mv = kmalloc_array(indices, sizeof(*p->mv), GFP_KERNEL); - if (!p->mv) { - err = -ENOMEM; - goto errout; - } - for (i = 0; i < indices; i++) { - p->mv[i].mask = 0xff; - p->mv[i].value = 0; - } - p->indices = indices; - p->default_index = default_index; - p->set_tc_index = nla_get_flag(tb[TCA_DSMARK_SET_TC_INDEX]); - - p->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle, - NULL); - if (p->q == NULL) - p->q = &noop_qdisc; - else - qdisc_hash_add(p->q, true); - - pr_debug("%s: qdisc %p\n", __func__, p->q); - - err = 0; -errout: - return err; -} - -static void dsmark_reset(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - if (p->q) - qdisc_reset(p->q); -} - -static void dsmark_destroy(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - - tcf_block_put(p->block); - qdisc_put(p->q); - if (p->mv != p->embedded) - kfree(p->mv); -} - -static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, - struct sk_buff *skb, struct tcmsg *tcm) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *opts = NULL; - - pr_debug("%s(sch %p,[qdisc %p],class %ld\n", __func__, sch, p, cl); - - if (!dsmark_valid_index(p, cl)) - return -EINVAL; - - tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle), cl - 1); - tcm->tcm_info = p->q->handle; - - opts = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (opts == NULL) - goto nla_put_failure; - if (nla_put_u8(skb, TCA_DSMARK_MASK, p->mv[cl - 1].mask) || - nla_put_u8(skb, TCA_DSMARK_VALUE, p->mv[cl - 1].value)) - goto nla_put_failure; - - return nla_nest_end(skb, opts); - -nla_put_failure: - nla_nest_cancel(skb, opts); - return -EMSGSIZE; -} - -static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *opts = NULL; - - opts = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (opts == NULL) - goto nla_put_failure; - if (nla_put_u16(skb, TCA_DSMARK_INDICES, p->indices)) - goto nla_put_failure; - - if (p->default_index != NO_DEFAULT_INDEX && - nla_put_u16(skb, TCA_DSMARK_DEFAULT_INDEX, p->default_index)) - goto nla_put_failure; - - if (p->set_tc_index && - nla_put_flag(skb, TCA_DSMARK_SET_TC_INDEX)) - goto nla_put_failure; - - return nla_nest_end(skb, opts); - -nla_put_failure: - nla_nest_cancel(skb, opts); - return -EMSGSIZE; -} - -static const struct Qdisc_class_ops dsmark_class_ops = { - .graft = dsmark_graft, - .leaf = dsmark_leaf, - .find = dsmark_find, - .change = dsmark_change, - .delete = dsmark_delete, - .walk = dsmark_walk, - .tcf_block = dsmark_tcf_block, - .bind_tcf = dsmark_bind_filter, - .unbind_tcf = dsmark_unbind_filter, - .dump = dsmark_dump_class, -}; - -static struct Qdisc_ops dsmark_qdisc_ops __read_mostly = { - .next = NULL, - .cl_ops = &dsmark_class_ops, - .id = "dsmark", - .priv_size = sizeof(struct dsmark_qdisc_data), - .enqueue = dsmark_enqueue, - .dequeue = dsmark_dequeue, - .peek = dsmark_peek, - .init = dsmark_init, - .reset = dsmark_reset, - .destroy = dsmark_destroy, - .change = NULL, - .dump = dsmark_dump, - .owner = THIS_MODULE, -}; - -static int __init dsmark_module_init(void) -{ - return register_qdisc(&dsmark_qdisc_ops); -} - -static void __exit dsmark_module_exit(void) -{ - unregister_qdisc(&dsmark_qdisc_ops); -} - -module_init(dsmark_module_init) -module_exit(dsmark_module_exit) - -MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 8d5eebb2dd1b1f52bcff7900ca36aa24fb32cd10..1d4638aa4254fd00384f977f888a836f3154ef05 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -765,7 +765,8 @@ static const struct nla_policy entry_policy[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { }; static const struct nla_policy taprio_tc_policy[TCA_TAPRIO_TC_ENTRY_MAX + 1] = { - [TCA_TAPRIO_TC_ENTRY_INDEX] = { .type = NLA_U32 }, + [TCA_TAPRIO_TC_ENTRY_INDEX] = NLA_POLICY_MAX(NLA_U32, + TC_QOPT_MAX_QUEUE), [TCA_TAPRIO_TC_ENTRY_MAX_SDU] = { .type = NLA_U32 }, }; diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index ace861173532159295bfdbd49164e30cd1d159f6..6de53431629ca8921eaabd9c997744b913d59f39 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -209,13 +209,18 @@ int smc_ib_find_route(struct net *net, __be32 saddr, __be32 daddr, if (IS_ERR(rt)) goto out; if (rt->rt_uses_gateway && rt->rt_gw_family != AF_INET) - goto out; - neigh = rt->dst.ops->neigh_lookup(&rt->dst, NULL, &fl4.daddr); - if (neigh) { - memcpy(nexthop_mac, neigh->ha, ETH_ALEN); - *uses_gateway = rt->rt_uses_gateway; - return 0; - } + goto out_rt; + neigh = dst_neigh_lookup(&rt->dst, &fl4.daddr); + if (!neigh) + goto out_rt; + memcpy(nexthop_mac, neigh->ha, ETH_ALEN); + *uses_gateway = rt->rt_uses_gateway; + neigh_release(neigh); + ip_rt_put(rt); + return 0; + +out_rt: + ip_rt_put(rt); out: return -ENOENT; } diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 25fb2fd186e22f5132a1c67d2ac3d8c5658a9fe2..21b8bf23e4ee67dc8dfa264d44eb6293e2554245 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -802,6 +802,16 @@ static void smc_pnet_create_pnetids_list(struct net *net) u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct net_device *dev; + /* Newly created netns do not have devices. + * Do not even acquire rtnl. + */ + if (list_empty(&net->dev_base_head)) + return; + + /* Note: This might not be needed, because smc_pnet_netdev_event() + * is also calling smc_pnet_add_base_pnetid() when handling + * NETDEV_UP event. + */ rtnl_lock(); for_each_netdev(net, dev) smc_pnet_add_base_pnetid(net, dev, ndev_pnetid); diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c index d435bffc6199978500dc9106ee63cad8a158f87e..97ff11973c49377cbff0ad36f4b266cc54b1c045 100644 --- a/net/sunrpc/addr.c +++ b/net/sunrpc/addr.c @@ -284,10 +284,10 @@ char *rpc_sockaddr2uaddr(const struct sockaddr *sap, gfp_t gfp_flags) } if (snprintf(portbuf, sizeof(portbuf), - ".%u.%u", port >> 8, port & 0xff) > (int)sizeof(portbuf)) + ".%u.%u", port >> 8, port & 0xff) >= (int)sizeof(portbuf)) return NULL; - if (strlcat(addrbuf, portbuf, sizeof(addrbuf)) > sizeof(addrbuf)) + if (strlcat(addrbuf, portbuf, sizeof(addrbuf)) >= sizeof(addrbuf)) return NULL; return kstrdup(addrbuf, gfp_flags); diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index d79f12c2550ac36b0c85aad2cb919e1d0cf2f4bb..cb32ab9a839521f2dffdffd363bb763983e1c6c4 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -250,8 +250,8 @@ static int gssx_dec_option_array(struct xdr_stream *xdr, creds = kzalloc(sizeof(struct svc_cred), GFP_KERNEL); if (!creds) { - kfree(oa->data); - return -ENOMEM; + err = -ENOMEM; + goto free_oa; } oa->data[0].option.data = CREDS_VALUE; @@ -265,29 +265,40 @@ static int gssx_dec_option_array(struct xdr_stream *xdr, /* option buffer */ p = xdr_inline_decode(xdr, 4); - if (unlikely(p == NULL)) - return -ENOSPC; + if (unlikely(p == NULL)) { + err = -ENOSPC; + goto free_creds; + } length = be32_to_cpup(p); p = xdr_inline_decode(xdr, length); - if (unlikely(p == NULL)) - return -ENOSPC; + if (unlikely(p == NULL)) { + err = -ENOSPC; + goto free_creds; + } if (length == sizeof(CREDS_VALUE) && memcmp(p, CREDS_VALUE, sizeof(CREDS_VALUE)) == 0) { /* We have creds here. parse them */ err = gssx_dec_linux_creds(xdr, creds); if (err) - return err; + goto free_creds; oa->data[0].value.len = 1; /* presence */ } else { /* consume uninteresting buffer */ err = gssx_dec_buffer(xdr, &dummy); if (err) - return err; + goto free_creds; } } return 0; + +free_creds: + kfree(creds); +free_oa: + kfree(oa->data); + oa->data = NULL; + return err; } static int gssx_dec_status(struct xdr_stream *xdr, diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 61e5c77462e94012d593faa1515288faf9ca307d..b774028e4aa8f47bf4714925be986a9848ef7f1d 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -398,7 +398,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, clnt->cl_maxproc = version->nrprocs; clnt->cl_prog = args->prognumber ? : program->number; clnt->cl_vers = version->number; - clnt->cl_stats = program->stats; + clnt->cl_stats = args->stats ? : program->stats; clnt->cl_metrics = rpc_alloc_iostats(clnt); rpc_init_pipe_dir_head(&clnt->cl_pipedir_objects); err = -ENOMEM; @@ -677,6 +677,7 @@ struct rpc_clnt *rpc_clone_client(struct rpc_clnt *clnt) .version = clnt->cl_vers, .authflavor = clnt->cl_auth->au_flavor, .cred = clnt->cl_cred, + .stats = clnt->cl_stats, }; return __rpc_clone_client(&args, clnt); } @@ -699,6 +700,7 @@ rpc_clone_client_set_auth(struct rpc_clnt *clnt, rpc_authflavor_t flavor) .version = clnt->cl_vers, .authflavor = flavor, .cred = clnt->cl_cred, + .stats = clnt->cl_stats, }; return __rpc_clone_client(&args, clnt); } @@ -1044,6 +1046,7 @@ struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *old, .version = vers, .authflavor = old->cl_auth->au_flavor, .cred = old->cl_cred, + .stats = old->cl_stats, }; struct rpc_clnt *clnt; int err; diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 8117d0e08d5a2799909b6cb2a5e7fd0a234f596c..1393eefbf2187ae71e782dad0cdfe7ce48eb4ab6 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -696,8 +696,8 @@ static int svc_alloc_arg(struct svc_rqst *rqstp) /* Made progress, don't sleep yet */ continue; - set_current_state(TASK_INTERRUPTIBLE); - if (signalled() || kthread_should_stop()) { + set_current_state(TASK_IDLE); + if (kthread_should_stop()) { set_current_state(TASK_RUNNING); return -EINTR; } @@ -733,7 +733,7 @@ rqst_should_sleep(struct svc_rqst *rqstp) return false; /* are we shutting down? */ - if (signalled() || kthread_should_stop()) + if (kthread_should_stop()) return false; /* are we freezing? */ @@ -755,11 +755,7 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout) if (rqstp->rq_xprt) goto out_found; - /* - * We have to be able to interrupt this wait - * to bring down the daemons ... - */ - set_current_state(TASK_INTERRUPTIBLE); + set_current_state(TASK_IDLE); smp_mb__before_atomic(); clear_bit(SP_CONGESTED, &pool->sp_flags); clear_bit(RQ_BUSY, &rqstp->rq_flags); @@ -781,7 +777,7 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout) if (!time_left) atomic_long_inc(&pool->sp_stats.threads_timedout); - if (signalled() || kthread_should_stop()) + if (kthread_should_stop()) return ERR_PTR(-EINTR); return ERR_PTR(-EAGAIN); out_found: @@ -879,7 +875,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) try_to_freeze(); cond_resched(); err = -EINTR; - if (signalled() || kthread_should_stop()) + if (kthread_should_stop()) goto out; xprt = svc_get_next_xprt(rqstp, timeout); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 656cec2083718580f9060e9a370e88b95e5c4b4d..ab453ede54f0cd7be590495952a3feb71d92aef1 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1164,7 +1164,7 @@ xprt_request_enqueue_receive(struct rpc_task *task) spin_unlock(&xprt->queue_lock); /* Turn off autodisconnect */ - del_singleshot_timer_sync(&xprt->timer); + del_timer_sync(&xprt->timer); return 0; } diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 8cc42aea19c7ecf7cb10e516f7578b94a0ddce47..2e14d4c37e2dcc6c8a1243e1ce9bd4a19b658360 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -19,6 +19,35 @@ #include #include +static bool switchdev_obj_eq(const struct switchdev_obj *a, + const struct switchdev_obj *b) +{ + const struct switchdev_obj_port_vlan *va, *vb; + const struct switchdev_obj_port_mdb *ma, *mb; + + if (a->id != b->id || a->orig_dev != b->orig_dev) + return false; + + switch (a->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + va = SWITCHDEV_OBJ_PORT_VLAN(a); + vb = SWITCHDEV_OBJ_PORT_VLAN(b); + return va->flags == vb->flags && + va->vid == vb->vid && + va->changed == vb->changed; + case SWITCHDEV_OBJ_ID_PORT_MDB: + case SWITCHDEV_OBJ_ID_HOST_MDB: + ma = SWITCHDEV_OBJ_PORT_MDB(a); + mb = SWITCHDEV_OBJ_PORT_MDB(b); + return ma->vid == mb->vid && + ether_addr_equal(ma->addr, mb->addr); + default: + break; + } + + BUG(); +} + static LIST_HEAD(deferred); static DEFINE_SPINLOCK(deferred_lock); @@ -307,6 +336,50 @@ int switchdev_port_obj_del(struct net_device *dev, } EXPORT_SYMBOL_GPL(switchdev_port_obj_del); +/** + * switchdev_port_obj_act_is_deferred - Is object action pending? + * + * @dev: port device + * @nt: type of action; add or delete + * @obj: object to test + * + * Returns true if a deferred item is pending, which is + * equivalent to the action @nt on an object @obj. + * + * rtnl_lock must be held. + */ +bool switchdev_port_obj_act_is_deferred(struct net_device *dev, + enum switchdev_notifier_type nt, + const struct switchdev_obj *obj) +{ + struct switchdev_deferred_item *dfitem; + bool found = false; + + ASSERT_RTNL(); + + spin_lock_bh(&deferred_lock); + + list_for_each_entry(dfitem, &deferred, list) { + if (dfitem->dev != dev) + continue; + + if ((dfitem->func == switchdev_port_obj_add_deferred && + nt == SWITCHDEV_PORT_OBJ_ADD) || + (dfitem->func == switchdev_port_obj_del_deferred && + nt == SWITCHDEV_PORT_OBJ_DEL)) { + if (switchdev_obj_eq((const void *)dfitem->data, obj)) { + found = true; + break; + } + } + } + + spin_unlock_bh(&deferred_lock); + + return found; +} +EXPORT_SYMBOL_GPL(switchdev_port_obj_act_is_deferred); + static ATOMIC_NOTIFIER_HEAD(switchdev_notif_chain); static BLOCKING_NOTIFIER_HEAD(switchdev_blocking_notif_chain); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index cdcd2731860ba14727c6742749d7c960239b3929..1cb9935620886c459062295c0e47ceb25de2dcd6 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -1088,6 +1088,12 @@ int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info) #ifdef CONFIG_TIPC_MEDIA_UDP if (attrs[TIPC_NLA_BEARER_UDP_OPTS]) { + if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) { + rtnl_unlock(); + NL_SET_ERR_MSG(info->extack, "UDP option is unsupported"); + return -EINVAL; + } + err = tipc_udp_nl_bearer_add(b, attrs[TIPC_NLA_BEARER_UDP_OPTS]); if (err) { diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 5c9fd4791c4ba1976f1d3d7fcb9ad458df1436f7..76284fc538ebdd38d52c879bd4fc58c84abc6371 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -142,9 +142,9 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (fragid == FIRST_FRAGMENT) { if (unlikely(head)) goto err; - *buf = NULL; if (skb_has_frag_list(frag) && __skb_linearize(frag)) goto err; + *buf = NULL; frag = skb_unshare(frag, GFP_ATOMIC); if (unlikely(!frag)) goto err; @@ -156,6 +156,11 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (!head) goto err; + /* Either the input skb ownership is transferred to headskb + * or the input skb is freed, clear the reference to avoid + * bad access on error path. + */ + *buf = NULL; if (skb_try_coalesce(head, frag, &headstolen, &delta)) { kfree_skb_partial(frag, headstolen); } else { @@ -179,7 +184,6 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) *headbuf = NULL; return 1; } - *buf = NULL; return 0; err: kfree_skb(*buf); diff --git a/net/tls/tls.h b/net/tls/tls.h index 0672acab27731d14214a6387e29bd3d51f3f19d9..4922668fefaa87b60ba8dfc35265230d52df4298 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -97,6 +97,7 @@ void tls_update_rx_zc_capable(struct tls_context *tls_ctx); void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx); void tls_sw_strparser_done(struct tls_context *tls_ctx); int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); +void tls_sw_splice_eof(struct socket *sock); int tls_sw_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags); int tls_sw_sendpage(struct sock *sk, struct page *page, diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 338a443fa47b28010122494e08f78ae344a682f5..6b7189a520af77246d081556ea884817e3e8b116 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -922,6 +922,7 @@ static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG] ops[TLS_BASE][TLS_BASE] = *base; ops[TLS_SW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE]; + ops[TLS_SW ][TLS_BASE].splice_eof = tls_sw_splice_eof; ops[TLS_SW ][TLS_BASE].sendpage_locked = tls_sw_sendpage_locked; ops[TLS_BASE][TLS_SW ] = ops[TLS_BASE][TLS_BASE]; @@ -990,6 +991,7 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], prot[TLS_SW][TLS_BASE] = prot[TLS_BASE][TLS_BASE]; prot[TLS_SW][TLS_BASE].sendmsg = tls_sw_sendmsg; + prot[TLS_SW][TLS_BASE].splice_eof = tls_sw_splice_eof; prot[TLS_SW][TLS_BASE].sendpage = tls_sw_sendpage; prot[TLS_BASE][TLS_SW] = prot[TLS_BASE][TLS_BASE]; @@ -1096,7 +1098,7 @@ static u16 tls_user_config(struct tls_context *ctx, bool tx) return 0; } -static int tls_get_info(const struct sock *sk, struct sk_buff *skb) +static int tls_get_info(struct sock *sk, struct sk_buff *skb) { u16 version, cipher_type; struct tls_context *ctx; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 0323040d34bc60fd140b6dd2a474cb24bba0978f..348abadbc2d82a18ef6857010474d97922fba614 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -51,6 +51,7 @@ struct tls_decrypt_arg { struct_group(inargs, bool zc; bool async; + bool async_done; u8 tail; ); @@ -62,6 +63,7 @@ struct tls_decrypt_ctx { u8 iv[MAX_IV_SIZE]; u8 aad[TLS_MAX_AAD_SIZE]; u8 tail; + bool free_sgout; struct scatterlist sg[]; }; @@ -186,7 +188,6 @@ static void tls_decrypt_done(crypto_completion_data_t *data, int err) struct aead_request *aead_req = crypto_get_completion_data(data); struct crypto_aead *aead = crypto_aead_reqtfm(aead_req); struct scatterlist *sgout = aead_req->dst; - struct scatterlist *sgin = aead_req->src; struct tls_sw_context_rx *ctx; struct tls_decrypt_ctx *dctx; struct tls_context *tls_ctx; @@ -195,6 +196,17 @@ static void tls_decrypt_done(crypto_completion_data_t *data, int err) struct sock *sk; int aead_size; + /* If requests get too backlogged crypto API returns -EBUSY and calls + * ->complete(-EINPROGRESS) immediately followed by ->complete(0) + * to make waiting for backlog to flush with crypto_wait_req() easier. + * First wait converts -EBUSY -> -EINPROGRESS, and the second one + * -EINPROGRESS -> 0. + * We have a single struct crypto_async_request per direction, this + * scheme doesn't help us, so just ignore the first ->complete(). + */ + if (err == -EINPROGRESS) + return; + aead_size = sizeof(*aead_req) + crypto_aead_reqsize(aead); aead_size = ALIGN(aead_size, __alignof__(*dctx)); dctx = (void *)((u8 *)aead_req + aead_size); @@ -212,7 +224,7 @@ static void tls_decrypt_done(crypto_completion_data_t *data, int err) } /* Free the destination pages if skb was not decrypted inplace */ - if (sgout != sgin) { + if (dctx->free_sgout) { /* Skip the first S/G entry as it points to AAD */ for_each_sg(sg_next(sgout), sg, UINT_MAX, pages) { if (!sg) @@ -223,10 +235,17 @@ static void tls_decrypt_done(crypto_completion_data_t *data, int err) kfree(aead_req); - spin_lock_bh(&ctx->decrypt_compl_lock); - if (!atomic_dec_return(&ctx->decrypt_pending)) + if (atomic_dec_and_test(&ctx->decrypt_pending)) complete(&ctx->async_wait.completion); - spin_unlock_bh(&ctx->decrypt_compl_lock); +} + +static int tls_decrypt_async_wait(struct tls_sw_context_rx *ctx) +{ + if (!atomic_dec_and_test(&ctx->decrypt_pending)) + crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + atomic_inc(&ctx->decrypt_pending); + + return ctx->async_wait.err; } static int tls_do_decryption(struct sock *sk, @@ -252,6 +271,7 @@ static int tls_do_decryption(struct sock *sk, aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG, tls_decrypt_done, aead_req); + DEBUG_NET_WARN_ON_ONCE(atomic_read(&ctx->decrypt_pending) < 1); atomic_inc(&ctx->decrypt_pending); } else { aead_request_set_callback(aead_req, @@ -260,12 +280,19 @@ static int tls_do_decryption(struct sock *sk, } ret = crypto_aead_decrypt(aead_req); - if (ret == -EINPROGRESS) { - if (darg->async) - return 0; + if (ret == -EINPROGRESS) + return 0; - ret = crypto_wait_req(ret, &ctx->async_wait); + if (ret == -EBUSY) { + ret = tls_decrypt_async_wait(ctx); + darg->async_done = true; + /* all completions have run, we're not doing async anymore */ + darg->async = false; + return ret; + ret = ret ?: -EINPROGRESS; } + + atomic_dec(&ctx->decrypt_pending); darg->async = false; return ret; @@ -439,9 +466,10 @@ static void tls_encrypt_done(crypto_completion_data_t *data, int err) struct scatterlist *sge; struct sk_msg *msg_en; struct tls_rec *rec; - bool ready = false; struct sock *sk; - int pending; + + if (err == -EINPROGRESS) /* see the comment in tls_decrypt_done() */ + return; rec = container_of(aead_req, struct tls_rec, aead_req); msg_en = &rec->msg_encrypted; @@ -477,23 +505,25 @@ static void tls_encrypt_done(crypto_completion_data_t *data, int err) /* If received record is at head of tx_list, schedule tx */ first_rec = list_first_entry(&ctx->tx_list, struct tls_rec, list); - if (rec == first_rec) - ready = true; + if (rec == first_rec) { + /* Schedule the transmission */ + if (!test_and_set_bit(BIT_TX_SCHEDULED, + &ctx->tx_bitmask)) + schedule_delayed_work(&ctx->tx_work.work, 1); + } } - spin_lock_bh(&ctx->encrypt_compl_lock); - pending = atomic_dec_return(&ctx->encrypt_pending); - - if (!pending && ctx->async_notify) + if (atomic_dec_and_test(&ctx->encrypt_pending)) complete(&ctx->async_wait.completion); - spin_unlock_bh(&ctx->encrypt_compl_lock); +} - if (!ready) - return; +static int tls_encrypt_async_wait(struct tls_sw_context_tx *ctx) +{ + if (!atomic_dec_and_test(&ctx->encrypt_pending)) + crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + atomic_inc(&ctx->encrypt_pending); - /* Schedule the transmission */ - if (!test_and_set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) - schedule_delayed_work(&ctx->tx_work.work, 1); + return ctx->async_wait.err; } static int tls_do_encryption(struct sock *sk, @@ -542,9 +572,14 @@ static int tls_do_encryption(struct sock *sk, /* Add the record in tx_list */ list_add_tail((struct list_head *)&rec->list, &ctx->tx_list); + DEBUG_NET_WARN_ON_ONCE(atomic_read(&ctx->encrypt_pending) < 1); atomic_inc(&ctx->encrypt_pending); rc = crypto_aead_encrypt(aead_req); + if (rc == -EBUSY) { + rc = tls_encrypt_async_wait(ctx); + rc = rc ?: -EINPROGRESS; + } if (!rc || rc != -EINPROGRESS) { atomic_dec(&ctx->encrypt_pending); sge->offset -= prot->prepend_size; @@ -953,7 +988,6 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) int num_zc = 0; int orig_size; int ret = 0; - int pending; if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_CMSG_COMPAT)) @@ -1122,24 +1156,12 @@ trim_sgl: if (!num_async) { goto send_end; } else if (num_zc) { - /* Wait for pending encryptions to get completed */ - spin_lock_bh(&ctx->encrypt_compl_lock); - ctx->async_notify = true; - - pending = atomic_read(&ctx->encrypt_pending); - spin_unlock_bh(&ctx->encrypt_compl_lock); - if (pending) - crypto_wait_req(-EINPROGRESS, &ctx->async_wait); - else - reinit_completion(&ctx->async_wait.completion); - - /* There can be no concurrent accesses, since we have no - * pending encrypt operations - */ - WRITE_ONCE(ctx->async_notify, false); + int err; - if (ctx->async_wait.err) { - ret = ctx->async_wait.err; + /* Wait for pending encryptions to get completed */ + err = tls_encrypt_async_wait(ctx); + if (err) { + ret = err; copied = 0; } } @@ -1158,6 +1180,67 @@ send_end: return copied > 0 ? copied : ret; } +/* + * Handle unexpected EOF during splice without SPLICE_F_MORE set. + */ +void tls_sw_splice_eof(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + struct tls_rec *rec; + struct sk_msg *msg_pl; + ssize_t copied = 0; + bool retrying = false; + int ret = 0; + + if (!ctx->open_rec) + return; + + mutex_lock(&tls_ctx->tx_lock); + lock_sock(sk); + +retry: + /* same checks as in tls_sw_push_pending_record() */ + rec = ctx->open_rec; + if (!rec) + goto unlock; + + msg_pl = &rec->msg_plaintext; + if (msg_pl->sg.size == 0) + goto unlock; + + /* Check the BPF advisor and perform transmission. */ + ret = bpf_exec_tx_verdict(msg_pl, sk, false, TLS_RECORD_TYPE_DATA, + &copied, 0); + switch (ret) { + case 0: + case -EAGAIN: + if (retrying) + goto unlock; + retrying = true; + goto retry; + case -EINPROGRESS: + break; + default: + goto unlock; + } + + /* Wait for pending encryptions to get completed */ + if (tls_encrypt_async_wait(ctx)) + goto unlock; + + /* Transmit if any encryptions have completed */ + if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) { + cancel_delayed_work(&ctx->tx_work.work); + tls_tx_records(sk, 0); + } + +unlock: + release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); +} + static int tls_sw_do_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { @@ -1595,12 +1678,16 @@ static int tls_decrypt_sg(struct sock *sk, struct iov_iter *out_iov, } else if (out_sg) { memcpy(sgout, out_sg, n_sgout * sizeof(*sgout)); } + dctx->free_sgout = !!pages; /* Prepare and submit AEAD request */ err = tls_do_decryption(sk, sgin, sgout, dctx->iv, data_len + prot->tail_size, aead_req, darg); - if (err) + if (err) { + if (darg->async_done) + goto exit_free_skb; goto exit_free_pages; + } darg->skb = clear_skb ?: tls_strp_msg(ctx); clear_skb = NULL; @@ -1612,6 +1699,9 @@ static int tls_decrypt_sg(struct sock *sk, struct iov_iter *out_iov, return err; } + if (unlikely(darg->async_done)) + return 0; + if (prot->tail_size) darg->tail = dctx->tail; @@ -1783,7 +1873,8 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, u8 *control, size_t skip, size_t len, - bool is_peek) + bool is_peek, + bool *more) { struct sk_buff *skb = skb_peek(&ctx->rx_list); struct tls_msg *tlm; @@ -1796,7 +1887,7 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, err = tls_record_content_type(msg, tlm, control); if (err <= 0) - goto out; + goto more; if (skip < rxm->full_len) break; @@ -1814,12 +1905,12 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, err = tls_record_content_type(msg, tlm, control); if (err <= 0) - goto out; + goto more; err = skb_copy_datagram_msg(skb, rxm->offset + skip, msg, chunk); if (err < 0) - goto out; + goto more; len = len - chunk; copied = copied + chunk; @@ -1855,6 +1946,10 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, out: return copied ? : err; +more: + if (more) + *more = true; + goto out; } static bool @@ -1954,10 +2049,12 @@ int tls_sw_recvmsg(struct sock *sk, struct strp_msg *rxm; struct tls_msg *tlm; ssize_t copied = 0; + ssize_t peeked = 0; bool async = false; int target, err; bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); bool is_peek = flags & MSG_PEEK; + bool rx_more = false; bool released = true; bool bpf_strp_enabled; bool zc_capable; @@ -1965,10 +2062,10 @@ int tls_sw_recvmsg(struct sock *sk, if (unlikely(flags & MSG_ERRQUEUE)) return sock_recv_errqueue(sk, msg, len, SOL_IP, IP_RECVERR); - psock = sk_psock_get(sk); err = tls_rx_reader_lock(sk, ctx, flags & MSG_DONTWAIT); if (err < 0) return err; + psock = sk_psock_get(sk); bpf_strp_enabled = sk_psock_strp_enabled(psock); /* If crypto failed the connection is broken */ @@ -1977,12 +2074,12 @@ int tls_sw_recvmsg(struct sock *sk, goto end; /* Process pending decrypted records. It must be non-zero-copy */ - err = process_rx_list(ctx, msg, &control, 0, len, is_peek); + err = process_rx_list(ctx, msg, &control, 0, len, is_peek, &rx_more); if (err < 0) goto end; copied = err; - if (len <= copied) + if (len <= copied || (copied && control != TLS_RECORD_TYPE_DATA) || rx_more) goto end; target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); @@ -2075,6 +2172,8 @@ put_on_rx_list: decrypted += chunk; len -= chunk; __skb_queue_tail(&ctx->rx_list, skb); + if (unlikely(control != TLS_RECORD_TYPE_DATA)) + break; continue; } @@ -2098,8 +2197,10 @@ put_on_rx_list: if (err < 0) goto put_on_rx_list_err; - if (is_peek) + if (is_peek) { + peeked += chunk; goto put_on_rx_list; + } if (partially_consumed) { rxm->offset += chunk; @@ -2123,16 +2224,10 @@ put_on_rx_list: recv_end: if (async) { - int ret, pending; + int ret; /* Wait for all previously submitted records to be decrypted */ - spin_lock_bh(&ctx->decrypt_compl_lock); - reinit_completion(&ctx->async_wait.completion); - pending = atomic_read(&ctx->decrypt_pending); - spin_unlock_bh(&ctx->decrypt_compl_lock); - ret = 0; - if (pending) - ret = crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + ret = tls_decrypt_async_wait(ctx); __skb_queue_purge(&ctx->async_hold); if (ret) { @@ -2143,13 +2238,15 @@ recv_end: } /* Drain records from the rx_list & copy if required */ - if (is_peek || is_kvec) - err = process_rx_list(ctx, msg, &control, copied, - decrypted, is_peek); + if (is_peek) + err = process_rx_list(ctx, msg, &control, copied + peeked, + decrypted - peeked, is_peek, NULL); else err = process_rx_list(ctx, msg, &control, 0, - async_copy_bytes, is_peek); - decrypted += max(err, 0); + async_copy_bytes, is_peek, NULL); + + /* we could have copied less than we wanted, and possibly nothing */ + decrypted += max(err, 0) - async_copy_bytes; } copied += decrypted; @@ -2351,16 +2448,9 @@ void tls_sw_release_resources_tx(struct sock *sk) struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); struct tls_rec *rec, *tmp; - int pending; /* Wait for any pending async encryptions to complete */ - spin_lock_bh(&ctx->encrypt_compl_lock); - ctx->async_notify = true; - pending = atomic_read(&ctx->encrypt_pending); - spin_unlock_bh(&ctx->encrypt_compl_lock); - - if (pending) - crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + tls_encrypt_async_wait(ctx); tls_tx_records(sk, -1); @@ -2513,6 +2603,48 @@ void tls_update_rx_zc_capable(struct tls_context *tls_ctx) tls_ctx->prot_info.version != TLS_1_3_VERSION; } +static struct tls_sw_context_tx *init_ctx_tx(struct tls_context *ctx, struct sock *sk) +{ + struct tls_sw_context_tx *sw_ctx_tx; + + if (!ctx->priv_ctx_tx) { + sw_ctx_tx = kzalloc(sizeof(*sw_ctx_tx), GFP_KERNEL); + if (!sw_ctx_tx) + return NULL; + } else { + sw_ctx_tx = ctx->priv_ctx_tx; + } + + crypto_init_wait(&sw_ctx_tx->async_wait); + atomic_set(&sw_ctx_tx->encrypt_pending, 1); + INIT_LIST_HEAD(&sw_ctx_tx->tx_list); + INIT_DELAYED_WORK(&sw_ctx_tx->tx_work.work, tx_work_handler); + sw_ctx_tx->tx_work.sk = sk; + + return sw_ctx_tx; +} + +static struct tls_sw_context_rx *init_ctx_rx(struct tls_context *ctx) +{ + struct tls_sw_context_rx *sw_ctx_rx; + + if (!ctx->priv_ctx_rx) { + sw_ctx_rx = kzalloc(sizeof(*sw_ctx_rx), GFP_KERNEL); + if (!sw_ctx_rx) + return NULL; + } else { + sw_ctx_rx = ctx->priv_ctx_rx; + } + + crypto_init_wait(&sw_ctx_rx->async_wait); + atomic_set(&sw_ctx_rx->decrypt_pending, 1); + init_waitqueue_head(&sw_ctx_rx->wq); + skb_queue_head_init(&sw_ctx_rx->rx_list); + skb_queue_head_init(&sw_ctx_rx->async_hold); + + return sw_ctx_rx; +} + int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) { struct tls_context *tls_ctx = tls_get_ctx(sk); @@ -2534,48 +2666,22 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) } if (tx) { - if (!ctx->priv_ctx_tx) { - sw_ctx_tx = kzalloc(sizeof(*sw_ctx_tx), GFP_KERNEL); - if (!sw_ctx_tx) { - rc = -ENOMEM; - goto out; - } - ctx->priv_ctx_tx = sw_ctx_tx; - } else { - sw_ctx_tx = - (struct tls_sw_context_tx *)ctx->priv_ctx_tx; - } - } else { - if (!ctx->priv_ctx_rx) { - sw_ctx_rx = kzalloc(sizeof(*sw_ctx_rx), GFP_KERNEL); - if (!sw_ctx_rx) { - rc = -ENOMEM; - goto out; - } - ctx->priv_ctx_rx = sw_ctx_rx; - } else { - sw_ctx_rx = - (struct tls_sw_context_rx *)ctx->priv_ctx_rx; - } - } + ctx->priv_ctx_tx = init_ctx_tx(ctx, sk); + if (!ctx->priv_ctx_tx) + return -ENOMEM; - if (tx) { - crypto_init_wait(&sw_ctx_tx->async_wait); - spin_lock_init(&sw_ctx_tx->encrypt_compl_lock); + sw_ctx_tx = ctx->priv_ctx_tx; crypto_info = &ctx->crypto_send.info; cctx = &ctx->tx; aead = &sw_ctx_tx->aead_send; - INIT_LIST_HEAD(&sw_ctx_tx->tx_list); - INIT_DELAYED_WORK(&sw_ctx_tx->tx_work.work, tx_work_handler); - sw_ctx_tx->tx_work.sk = sk; } else { - crypto_init_wait(&sw_ctx_rx->async_wait); - spin_lock_init(&sw_ctx_rx->decrypt_compl_lock); - init_waitqueue_head(&sw_ctx_rx->wq); + ctx->priv_ctx_rx = init_ctx_rx(ctx); + if (!ctx->priv_ctx_rx) + return -ENOMEM; + + sw_ctx_rx = ctx->priv_ctx_rx; crypto_info = &ctx->crypto_recv.info; cctx = &ctx->rx; - skb_queue_head_init(&sw_ctx_rx->rx_list); - skb_queue_head_init(&sw_ctx_rx->async_hold); aead = &sw_ctx_rx->aead_recv; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index e1af94393789fe3cc09e8f06ee51b4090f8002d9..f28e2956fea58fee54d4a109657630e2a2bcee03 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -968,11 +968,11 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, sk->sk_write_space = unix_write_space; sk->sk_max_ack_backlog = net->unx.sysctl_max_dgram_qlen; sk->sk_destruct = unix_sock_destructor; - u = unix_sk(sk); + u = unix_sk(sk); + u->inflight = 0; u->path.dentry = NULL; u->path.mnt = NULL; spin_lock_init(&u->lock); - atomic_long_set(&u->inflight, 0); INIT_LIST_HEAD(&u->link); mutex_init(&u->iolock); /* single task reading lock */ mutex_init(&u->bindlock); /* single task binding lock */ @@ -2675,9 +2675,13 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, WRITE_ONCE(u->oob_skb, NULL); consume_skb(skb); } - } else if (!(flags & MSG_PEEK)) { + } else if (flags & MSG_PEEK) { + skb = NULL; + } else { skb_unlink(skb, &sk->sk_receive_queue); - consume_skb(skb); + WRITE_ONCE(u->oob_skb, NULL); + if (!WARN_ON_ONCE(skb_unref(skb))) + kfree_skb(skb); skb = skb_peek(&sk->sk_receive_queue); } } @@ -2751,18 +2755,16 @@ redo: last = skb = skb_peek(&sk->sk_receive_queue); last_len = last ? last->len : 0; +again: #if IS_ENABLED(CONFIG_AF_UNIX_OOB) if (skb) { skb = manage_oob(skb, sk, flags, copied); - if (!skb) { + if (!skb && copied) { unix_state_unlock(sk); - if (copied) - break; - goto redo; + break; } } #endif -again: if (skb == NULL) { if (copied >= target) goto unlock; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index dc27635403932154f3dec069c2e10d2ae365d8cb..d2fc795394a52864ed4410ba512f5ef013ae6365 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -166,17 +166,18 @@ static void scan_children(struct sock *x, void (*func)(struct unix_sock *), static void dec_inflight(struct unix_sock *usk) { - atomic_long_dec(&usk->inflight); + usk->inflight--; } static void inc_inflight(struct unix_sock *usk) { - atomic_long_inc(&usk->inflight); + usk->inflight++; } static void inc_inflight_move_tail(struct unix_sock *u) { - atomic_long_inc(&u->inflight); + u->inflight++; + /* If this still might be part of a cycle, move it to the end * of the list, so that it's checked even if it was already * passed over @@ -198,7 +199,7 @@ void wait_for_unix_gc(void) if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC && !READ_ONCE(gc_in_progress)) unix_gc(); - wait_event(unix_gc_wait, gc_in_progress == false); + wait_event(unix_gc_wait, !READ_ONCE(gc_in_progress)); } /* The external entry point: unix_gc() */ @@ -234,20 +235,34 @@ void unix_gc(void) * receive queues. Other, non candidate sockets _can_ be * added to queue, so we must make sure only to touch * candidates. + * + * Embryos, though never candidates themselves, affect which + * candidates are reachable by the garbage collector. Before + * being added to a listener's queue, an embryo may already + * receive data carrying SCM_RIGHTS, potentially making the + * passed socket a candidate that is not yet reachable by the + * collector. It becomes reachable once the embryo is + * enqueued. Therefore, we must ensure that no SCM-laden + * embryo appears in a (candidate) listener's queue between + * consecutive scan_children() calls. */ list_for_each_entry_safe(u, next, &gc_inflight_list, link) { + struct sock *sk = &u->sk; long total_refs; - long inflight_refs; - total_refs = file_count(u->sk.sk_socket->file); - inflight_refs = atomic_long_read(&u->inflight); + total_refs = file_count(sk->sk_socket->file); - BUG_ON(inflight_refs < 1); - BUG_ON(total_refs < inflight_refs); - if (total_refs == inflight_refs) { + BUG_ON(!u->inflight); + BUG_ON(total_refs < u->inflight); + if (total_refs == u->inflight) { list_move_tail(&u->link, &gc_candidates); __set_bit(UNIX_GC_CANDIDATE, &u->gc_flags); __set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); + + if (sk->sk_state == TCP_LISTEN) { + unix_state_lock_nested(sk, U_LOCK_GC_LISTENER); + unix_state_unlock(sk); + } } } @@ -271,7 +286,7 @@ void unix_gc(void) /* Move cursor to after the current position. */ list_move(&cursor, &u->link); - if (atomic_long_read(&u->inflight) > 0) { + if (u->inflight) { list_move_tail(&u->link, ¬_cycle_list); __clear_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); scan_children(&u->sk, inc_inflight_move_tail, NULL); @@ -284,9 +299,17 @@ void unix_gc(void) * which are creating the cycle(s). */ skb_queue_head_init(&hitlist); - list_for_each_entry(u, &gc_candidates, link) + list_for_each_entry(u, &gc_candidates, link) { scan_children(&u->sk, inc_inflight, &hitlist); +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (u->oob_skb) { + kfree_skb(u->oob_skb); + u->oob_skb = NULL; + } +#endif + } + /* not_cycle_list contains those sockets which do not make up a * cycle. Restore these to the inflight list. */ diff --git a/net/unix/scm.c b/net/unix/scm.c index e8e2a00bb0f58512a82eaa577d456a7f8b50754c..4eff7da9f6f966f2524a85a5c0e15ddba1b791d2 100644 --- a/net/unix/scm.c +++ b/net/unix/scm.c @@ -34,10 +34,8 @@ struct sock *unix_get_socket(struct file *filp) /* PF_UNIX ? */ if (s && sock->ops && sock->ops->family == PF_UNIX) u_sock = s; - } else { - /* Could be an io_uring instance */ - u_sock = io_uring_get_socket(filp); } + return u_sock; } EXPORT_SYMBOL(unix_get_socket); @@ -54,12 +52,13 @@ void unix_inflight(struct user_struct *user, struct file *fp) if (s) { struct unix_sock *u = unix_sk(s); - if (atomic_long_inc_return(&u->inflight) == 1) { + if (!u->inflight) { BUG_ON(!list_empty(&u->link)); list_add_tail(&u->link, &gc_inflight_list); } else { BUG_ON(list_empty(&u->link)); } + u->inflight++; /* Paired with READ_ONCE() in wait_for_unix_gc() */ WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1); } @@ -76,10 +75,11 @@ void unix_notinflight(struct user_struct *user, struct file *fp) if (s) { struct unix_sock *u = unix_sk(s); - BUG_ON(!atomic_long_read(&u->inflight)); + BUG_ON(!u->inflight); BUG_ON(list_empty(&u->link)); - if (atomic_long_dec_and_test(&u->inflight)) + u->inflight--; + if (!u->inflight) list_del_init(&u->link); /* Paired with READ_ONCE() in wait_for_unix_gc() */ WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 16575ea83659028bca6ef49d1b3382b88bfd93e7..5434c9f11d28dfa66afc5ee174a20097f00b09ee 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -109,7 +109,6 @@ virtio_transport_send_pkt_work(struct work_struct *work) if (!skb) break; - virtio_transport_deliver_tap_pkt(skb); reply = virtio_vsock_skb_reply(skb); sg_init_one(&hdr, virtio_vsock_hdr(skb), sizeof(*virtio_vsock_hdr(skb))); @@ -128,6 +127,8 @@ virtio_transport_send_pkt_work(struct work_struct *work) break; } + virtio_transport_deliver_tap_pkt(skb); + if (reply) { struct virtqueue *rx_vq = vsock->vqs[VSOCK_VQ_RX]; int val; diff --git a/net/wireless/core.c b/net/wireless/core.c index 8809e668ed91231303e4f4a14e658dcfb69f688d..3fcddc8687ed42e405c4dd66e4c046f44db10ccd 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1671,6 +1671,7 @@ void wiphy_delayed_work_queue(struct wiphy *wiphy, unsigned long delay) { if (!delay) { + del_timer(&dwork->timer); wiphy_work_queue(wiphy, &dwork->work); return; } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 70fb14b8bab07e2e9d30b25d6de1cd00a858a428..a00df7b89ca86418683e11597c0a309b11e7d0d6 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3960,6 +3960,7 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback * if_idx++; } + if_start = 0; wp_idx++; } out: @@ -4136,6 +4137,8 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) if (ntype != NL80211_IFTYPE_MESH_POINT) return -EINVAL; + if (otype != NL80211_IFTYPE_MESH_POINT) + return -EINVAL; if (netif_running(dev)) return -EBUSY; @@ -13799,6 +13802,8 @@ static int nl80211_set_coalesce(struct sk_buff *skb, struct genl_info *info) error: for (i = 0; i < new_coalesce.n_rules; i++) { tmp_rule = &new_coalesce.rules[i]; + if (!tmp_rule) + continue; for (j = 0; j < tmp_rule->n_patterns; j++) kfree(tmp_rule->patterns[j].mask); kfree(tmp_rule->patterns); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index a405c3edbc47ec47f46d10f50c44959cc8ab759b..cb5c3224e038a09b09b6a8fba2c338c528fb07de 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1018,7 +1018,7 @@ TRACE_EVENT(rdev_get_mpp, TRACE_EVENT(rdev_dump_mpp, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int _idx, u8 *dst, u8 *mpp), - TP_ARGS(wiphy, netdev, _idx, mpp, dst), + TP_ARGS(wiphy, netdev, _idx, dst, mpp), TP_STRUCT__entry( WIPHY_ENTRY NETDEV_ENTRY diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 5c7ad301d742e8776320c51d13c7d9eff0793992..5a8b2ea56564e3ece38d2c29ac3e7fc4decf90c1 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -460,12 +460,12 @@ static int x25_getsockopt(struct socket *sock, int level, int optname, if (get_user(len, optlen)) goto out; - len = min_t(unsigned int, len, sizeof(int)); - rc = -EINVAL; if (len < 0) goto out; + len = min_t(unsigned int, len, sizeof(int)); + rc = -EFAULT; if (put_user(len, optlen)) goto out; diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 5c8e02d56fd43ce2cab700851f98a005f25b302d..e3bdfc517424d2d5001af4f9e3f9a894376b211e 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -1127,6 +1127,8 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname, struct xsk_queue **q; int entries; + if (optlen < sizeof(entries)) + return -EINVAL; if (copy_from_sockptr(&entries, optval, sizeof(entries))) return -EFAULT; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index ac1a645afa8dfce079cab7a577143f87ab347885..4bba890ff3bc05886f90fa7fb2e45e6a98a5900f 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -180,6 +180,8 @@ static int xfrm4_remove_beet_encap(struct xfrm_state *x, struct sk_buff *skb) int optlen = 0; int err = -EINVAL; + skb->protocol = htons(ETH_P_IP); + if (unlikely(XFRM_MODE_SKB_CB(skb)->protocol == IPPROTO_BEETPH)) { struct ip_beet_phdr *ph; int phlen; @@ -232,8 +234,7 @@ static int xfrm4_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb) { int err = -EINVAL; - if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP) - goto out; + skb->protocol = htons(ETH_P_IP); if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto out; @@ -270,8 +271,8 @@ static int xfrm6_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb) { int err = -EINVAL; - if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPV6) - goto out; + skb->protocol = htons(ETH_P_IPV6); + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto out; @@ -301,6 +302,8 @@ static int xfrm6_remove_beet_encap(struct xfrm_state *x, struct sk_buff *skb) int size = sizeof(struct ipv6hdr); int err; + skb->protocol = htons(ETH_P_IPV6); + err = skb_cow_head(skb, size + skb->mac_len); if (err) goto out; @@ -332,22 +335,26 @@ out: */ static int xfrm_inner_mode_encap_remove(struct xfrm_state *x, - const struct xfrm_mode *inner_mode, struct sk_buff *skb) { - switch (inner_mode->encap) { + switch (x->props.mode) { case XFRM_MODE_BEET: - if (inner_mode->family == AF_INET) + switch (x->sel.family) { + case AF_INET: return xfrm4_remove_beet_encap(x, skb); - if (inner_mode->family == AF_INET6) + case AF_INET6: return xfrm6_remove_beet_encap(x, skb); + } break; case XFRM_MODE_TUNNEL: - if (inner_mode->family == AF_INET) + switch (XFRM_MODE_SKB_CB(skb)->protocol) { + case IPPROTO_IPIP: return xfrm4_remove_tunnel_encap(x, skb); - if (inner_mode->family == AF_INET6) + case IPPROTO_IPV6: return xfrm6_remove_tunnel_encap(x, skb); break; + } + return -EINVAL; } WARN_ON_ONCE(1); @@ -356,9 +363,7 @@ xfrm_inner_mode_encap_remove(struct xfrm_state *x, static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb) { - const struct xfrm_mode *inner_mode = &x->inner_mode; - - switch (x->outer_mode.family) { + switch (x->props.family) { case AF_INET: xfrm4_extract_header(skb); break; @@ -370,25 +375,7 @@ static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb) return -EAFNOSUPPORT; } - if (x->sel.family == AF_UNSPEC) { - inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); - if (!inner_mode) - return -EAFNOSUPPORT; - } - - switch (inner_mode->family) { - case AF_INET: - skb->protocol = htons(ETH_P_IP); - break; - case AF_INET6: - skb->protocol = htons(ETH_P_IPV6); - break; - default: - WARN_ON_ONCE(1); - break; - } - - return xfrm_inner_mode_encap_remove(x, inner_mode, skb); + return xfrm_inner_mode_encap_remove(x, skb); } /* Remove encapsulation header. @@ -401,11 +388,15 @@ static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb) */ static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb) { + struct xfrm_offload *xo = xfrm_offload(skb); int ihl = skb->data - skb_transport_header(skb); if (skb->transport_header != skb->network_header) { memmove(skb_transport_header(skb), skb_network_header(skb), ihl); + if (xo) + xo->orig_mac_len = + skb_mac_header_was_set(skb) ? skb_mac_header_len(skb) : 0; skb->network_header = skb->transport_header; } ip_hdr(skb)->tot_len = htons(skb->len + ihl); @@ -416,11 +407,15 @@ static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb) static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IPV6) + struct xfrm_offload *xo = xfrm_offload(skb); int ihl = skb->data - skb_transport_header(skb); if (skb->transport_header != skb->network_header) { memmove(skb_transport_header(skb), skb_network_header(skb), ihl); + if (xo) + xo->orig_mac_len = + skb_mac_header_was_set(skb) ? skb_mac_header_len(skb) : 0; skb->network_header = skb->transport_header; } ipv6_hdr(skb)->payload_len = htons(skb->len + ihl - @@ -434,17 +429,16 @@ static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb) } static int xfrm_inner_mode_input(struct xfrm_state *x, - const struct xfrm_mode *inner_mode, struct sk_buff *skb) { - switch (inner_mode->encap) { + switch (x->props.mode) { case XFRM_MODE_BEET: case XFRM_MODE_TUNNEL: return xfrm_prepare_input(x, skb); case XFRM_MODE_TRANSPORT: - if (inner_mode->family == AF_INET) + if (x->props.family == AF_INET) return xfrm4_transport_input(x, skb); - if (inner_mode->family == AF_INET6) + if (x->props.family == AF_INET6) return xfrm6_transport_input(x, skb); break; case XFRM_MODE_ROUTEOPTIMIZATION: @@ -462,7 +456,6 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) { const struct xfrm_state_afinfo *afinfo; struct net *net = dev_net(skb->dev); - const struct xfrm_mode *inner_mode; int err; __be32 seq; __be32 seq_hi; @@ -492,7 +485,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) goto drop; } - family = x->outer_mode.family; + family = x->props.family; /* An encap_type of -1 indicates async resumption. */ if (encap_type == -1) { @@ -676,17 +669,7 @@ resume: XFRM_MODE_SKB_CB(skb)->protocol = nexthdr; - inner_mode = &x->inner_mode; - - if (x->sel.family == AF_UNSPEC) { - inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); - if (inner_mode == NULL) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR); - goto drop; - } - } - - if (xfrm_inner_mode_input(x, inner_mode, skb)) { + if (xfrm_inner_mode_input(x, skb)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR); goto drop; } @@ -701,7 +684,7 @@ resume: * transport mode so the outer address is identical. */ daddr = &x->id.daddr; - family = x->outer_mode.family; + family = x->props.family; err = xfrm_parse_spi(skb, nexthdr, &spi, &seq); if (err < 0) { @@ -732,7 +715,7 @@ resume: err = -EAFNOSUPPORT; rcu_read_lock(); - afinfo = xfrm_state_afinfo_get_rcu(x->inner_mode.family); + afinfo = xfrm_state_afinfo_get_rcu(x->props.family); if (likely(afinfo)) err = afinfo->transport_finish(skb, xfrm_gro || async); rcu_read_unlock(); diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 9a5e79a38c6797e86648178090601471c2e68584..07a7ee43b8ae26c7198a669b315c3f0c846bbb14 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -414,7 +414,7 @@ static int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb) IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE; skb->protocol = htons(ETH_P_IP); - switch (x->outer_mode.encap) { + switch (x->props.mode) { case XFRM_MODE_BEET: return xfrm4_beet_encap_add(x, skb); case XFRM_MODE_TUNNEL: @@ -437,7 +437,7 @@ static int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) skb->ignore_df = 1; skb->protocol = htons(ETH_P_IPV6); - switch (x->outer_mode.encap) { + switch (x->props.mode) { case XFRM_MODE_BEET: return xfrm6_beet_encap_add(x, skb); case XFRM_MODE_TUNNEL: @@ -453,22 +453,22 @@ static int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb) { - switch (x->outer_mode.encap) { + switch (x->props.mode) { case XFRM_MODE_BEET: case XFRM_MODE_TUNNEL: - if (x->outer_mode.family == AF_INET) + if (x->props.family == AF_INET) return xfrm4_prepare_output(x, skb); - if (x->outer_mode.family == AF_INET6) + if (x->props.family == AF_INET6) return xfrm6_prepare_output(x, skb); break; case XFRM_MODE_TRANSPORT: - if (x->outer_mode.family == AF_INET) + if (x->props.family == AF_INET) return xfrm4_transport_output(x, skb); - if (x->outer_mode.family == AF_INET6) + if (x->props.family == AF_INET6) return xfrm6_transport_output(x, skb); break; case XFRM_MODE_ROUTEOPTIMIZATION: - if (x->outer_mode.family == AF_INET6) + if (x->props.family == AF_INET6) return xfrm6_ro_output(x, skb); WARN_ON_ONCE(1); break; @@ -866,21 +866,10 @@ static int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb) { - const struct xfrm_mode *inner_mode; - - if (x->sel.family == AF_UNSPEC) - inner_mode = xfrm_ip2inner_mode(x, - xfrm_af2proto(skb_dst(skb)->ops->family)); - else - inner_mode = &x->inner_mode; - - if (inner_mode == NULL) - return -EAFNOSUPPORT; - - switch (inner_mode->family) { - case AF_INET: + switch (skb->protocol) { + case htons(ETH_P_IP): return xfrm4_extract_output(x, skb); - case AF_INET6: + case htons(ETH_P_IPV6): return xfrm6_extract_output(x, skb); } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index d042ca01211faf797d70a8959777e5e42ff33b17..0cc4ed29e9015105cc3756f29a6b7c506dbb37af 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1979,6 +1979,9 @@ static int copy_to_user_tmpl(struct xfrm_policy *xp, struct sk_buff *skb) if (xp->xfrm_nr == 0) return 0; + if (xp->xfrm_nr > XFRM_MAX_DEPTH) + return -ENOBUFS; + for (i = 0; i < xp->xfrm_nr; i++) { struct xfrm_user_tmpl *up = &vec[i]; struct xfrm_tmpl *kp = &xp->xfrm_vec[i]; diff --git a/rust/Makefile b/rust/Makefile index 7700d3853404e5553c8f06b862608de7a89fae80..6d0c0e9757f21dd6b1d20d28f4e4e817666e0153 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -322,10 +322,9 @@ $(obj)/exports_kernel_generated.h: $(obj)/kernel.o FORCE quiet_cmd_rustc_procmacro = $(RUSTC_OR_CLIPPY_QUIET) P $@ cmd_rustc_procmacro = \ $(RUSTC_OR_CLIPPY) $(rust_common_flags) \ - --emit=dep-info,link --extern proc_macro \ - --crate-type proc-macro --out-dir $(objtree)/$(obj) \ + --emit=dep-info=$(depfile) --emit=link=$@ --extern proc_macro \ + --crate-type proc-macro \ --crate-name $(patsubst lib%.so,%,$(notdir $@)) $<; \ - mv $(objtree)/$(obj)/$(patsubst lib%.so,%,$(notdir $@)).d $(depfile); \ sed -i '/^\#/d' $(depfile) # Procedural macros can only be used with the `rustc` that compiled it. @@ -339,10 +338,10 @@ quiet_cmd_rustc_library = $(if $(skip_clippy),RUSTC,$(RUSTC_OR_CLIPPY_QUIET)) L OBJTREE=$(abspath $(objtree)) \ $(if $(skip_clippy),$(RUSTC),$(RUSTC_OR_CLIPPY)) \ $(filter-out $(skip_flags),$(rust_flags) $(rustc_target_flags)) \ - --emit=dep-info,obj,metadata --crate-type rlib \ - --out-dir $(objtree)/$(obj) -L$(objtree)/$(obj) \ + --emit=dep-info=$(depfile) --emit=obj=$@ \ + --emit=metadata=$(dir $@)$(patsubst %.o,lib%.rmeta,$(notdir $@)) \ + --crate-type rlib -L$(objtree)/$(obj) \ --crate-name $(patsubst %.o,%,$(notdir $@)) $<; \ - mv $(objtree)/$(obj)/$(patsubst %.o,%,$(notdir $@)).d $(depfile); \ sed -i '/^\#/d' $(depfile) \ $(if $(rustc_objcopy),;$(OBJCOPY) $(rustc_objcopy) $@) diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs index 466b2a8fe569b60994294d3e1ca35de511631246..4a3a6306cfe193e800dd8ba3e0ef7f6401fea9b0 100644 --- a/rust/kernel/error.rs +++ b/rust/kernel/error.rs @@ -25,7 +25,7 @@ pub struct Error(core::ffi::c_int); impl Error { /// Returns the kernel error code. - pub fn to_kernel_errno(self) -> core::ffi::c_int { + pub fn to_errno(self) -> core::ffi::c_int { self.0 } } diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index abd46261d3855b635ad45d33a6f52f62143434ac..43cf5f6bde9c20004bdbca305454d59814ab5ad7 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -37,7 +37,7 @@ const __LOG_PREFIX: &[u8] = b"rust_kernel\0"; /// The top level entrypoint to implementing a kernel module. /// /// For any teardown or cleanup operations, your type may implement [`Drop`]. -pub trait Module: Sized + Sync { +pub trait Module: Sized + Sync + Send { /// Called at module initialization time. /// /// Use this method to perform whatever setup or registration your module diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs index 91764bfb1f893add8230f947234454f0db922d38..f2efa86a747a3552be9deb1ff61c4994aaf9ec8b 100644 --- a/rust/macros/lib.rs +++ b/rust/macros/lib.rs @@ -27,18 +27,6 @@ use proc_macro::TokenStream; /// author: b"Rust for Linux Contributors", /// description: b"My very own kernel module!", /// license: b"GPL", -/// params: { -/// my_i32: i32 { -/// default: 42, -/// permissions: 0o000, -/// description: b"Example of i32", -/// }, -/// writeable_i32: i32 { -/// default: 42, -/// permissions: 0o644, -/// description: b"Example of i32", -/// }, -/// }, /// } /// /// struct MyModule; diff --git a/rust/macros/module.rs b/rust/macros/module.rs index 186a5b8be23cd69900d25d8c2fe822c5b81411d2..031028b3dc41bd15a06fc9330a0217ba53619c14 100644 --- a/rust/macros/module.rs +++ b/rust/macros/module.rs @@ -179,17 +179,6 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { /// Used by the printing macros, e.g. [`info!`]. const __LOG_PREFIX: &[u8] = b\"{name}\\0\"; - /// The \"Rust loadable module\" mark, for `scripts/is_rust_module.sh`. - // - // This may be best done another way later on, e.g. as a new modinfo - // key or a new section. For the moment, keep it simple. - #[cfg(MODULE)] - #[doc(hidden)] - #[used] - static __IS_RUST_MODULE: () = (); - - static mut __MOD: Option<{type_}> = None; - // SAFETY: `__this_module` is constructed by the kernel at load time and will not be // freed until the module is unloaded. #[cfg(MODULE)] @@ -201,76 +190,132 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { kernel::ThisModule::from_ptr(core::ptr::null_mut()) }}; - // Loadable modules need to export the `{{init,cleanup}}_module` identifiers. - #[cfg(MODULE)] - #[doc(hidden)] - #[no_mangle] - pub extern \"C\" fn init_module() -> core::ffi::c_int {{ - __init() - }} - - #[cfg(MODULE)] - #[doc(hidden)] - #[no_mangle] - pub extern \"C\" fn cleanup_module() {{ - __exit() - }} + // Double nested modules, since then nobody can access the public items inside. + mod __module_init {{ + mod __module_init {{ + use super::super::{type_}; + + /// The \"Rust loadable module\" mark. + // + // This may be best done another way later on, e.g. as a new modinfo + // key or a new section. For the moment, keep it simple. + #[cfg(MODULE)] + #[doc(hidden)] + #[used] + static __IS_RUST_MODULE: () = (); + + static mut __MOD: Option<{type_}> = None; + + // Loadable modules need to export the `{{init,cleanup}}_module` identifiers. + /// # Safety + /// + /// This function must not be called after module initialization, because it may be + /// freed after that completes. + #[cfg(MODULE)] + #[doc(hidden)] + #[no_mangle] + #[link_section = \".init.text\"] + pub unsafe extern \"C\" fn init_module() -> core::ffi::c_int {{ + // SAFETY: This function is inaccessible to the outside due to the double + // module wrapping it. It is called exactly once by the C side via its + // unique name. + unsafe {{ __init() }} + }} - // Built-in modules are initialized through an initcall pointer - // and the identifiers need to be unique. - #[cfg(not(MODULE))] - #[cfg(not(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS))] - #[doc(hidden)] - #[link_section = \"{initcall_section}\"] - #[used] - pub static __{name}_initcall: extern \"C\" fn() -> core::ffi::c_int = __{name}_init; + #[cfg(MODULE)] + #[doc(hidden)] + #[no_mangle] + pub extern \"C\" fn cleanup_module() {{ + // SAFETY: + // - This function is inaccessible to the outside due to the double + // module wrapping it. It is called exactly once by the C side via its + // unique name, + // - furthermore it is only called after `init_module` has returned `0` + // (which delegates to `__init`). + unsafe {{ __exit() }} + }} - #[cfg(not(MODULE))] - #[cfg(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS)] - core::arch::global_asm!( - r#\".section \"{initcall_section}\", \"a\" - __{name}_initcall: - .long __{name}_init - . - .previous - \"# - ); + // Built-in modules are initialized through an initcall pointer + // and the identifiers need to be unique. + #[cfg(not(MODULE))] + #[cfg(not(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS))] + #[doc(hidden)] + #[link_section = \"{initcall_section}\"] + #[used] + pub static __{name}_initcall: extern \"C\" fn() -> core::ffi::c_int = __{name}_init; + + #[cfg(not(MODULE))] + #[cfg(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS)] + core::arch::global_asm!( + r#\".section \"{initcall_section}\", \"a\" + __{name}_initcall: + .long __{name}_init - . + .previous + \"# + ); + + #[cfg(not(MODULE))] + #[doc(hidden)] + #[no_mangle] + pub extern \"C\" fn __{name}_init() -> core::ffi::c_int {{ + // SAFETY: This function is inaccessible to the outside due to the double + // module wrapping it. It is called exactly once by the C side via its + // placement above in the initcall section. + unsafe {{ __init() }} + }} - #[cfg(not(MODULE))] - #[doc(hidden)] - #[no_mangle] - pub extern \"C\" fn __{name}_init() -> core::ffi::c_int {{ - __init() - }} + #[cfg(not(MODULE))] + #[doc(hidden)] + #[no_mangle] + pub extern \"C\" fn __{name}_exit() {{ + // SAFETY: + // - This function is inaccessible to the outside due to the double + // module wrapping it. It is called exactly once by the C side via its + // unique name, + // - furthermore it is only called after `__{name}_init` has returned `0` + // (which delegates to `__init`). + unsafe {{ __exit() }} + }} - #[cfg(not(MODULE))] - #[doc(hidden)] - #[no_mangle] - pub extern \"C\" fn __{name}_exit() {{ - __exit() - }} + /// # Safety + /// + /// This function must only be called once. + unsafe fn __init() -> core::ffi::c_int {{ + match <{type_} as kernel::Module>::init(&super::super::THIS_MODULE) {{ + Ok(m) => {{ + // SAFETY: No data race, since `__MOD` can only be accessed by this + // module and there only `__init` and `__exit` access it. These + // functions are only called once and `__exit` cannot be called + // before or during `__init`. + unsafe {{ + __MOD = Some(m); + }} + return 0; + }} + Err(e) => {{ + return e.to_errno(); + }} + }} + }} - fn __init() -> core::ffi::c_int {{ - match <{type_} as kernel::Module>::init(&THIS_MODULE) {{ - Ok(m) => {{ + /// # Safety + /// + /// This function must + /// - only be called once, + /// - be called after `__init` has been called and returned `0`. + unsafe fn __exit() {{ + // SAFETY: No data race, since `__MOD` can only be accessed by this module + // and there only `__init` and `__exit` access it. These functions are only + // called once and `__init` was already called. unsafe {{ - __MOD = Some(m); + // Invokes `drop()` on `__MOD`, which should be used for cleanup. + __MOD = None; }} - return 0; - }} - Err(e) => {{ - return e.to_kernel_errno(); }} - }} - }} - fn __exit() {{ - unsafe {{ - // Invokes `drop()` on `__MOD`, which should be used for cleanup. - __MOD = None; + {modinfo} }} }} - - {modinfo} ", type_ = info.type_, name = info.name, diff --git a/samples/bpf/asm_goto_workaround.h b/samples/bpf/asm_goto_workaround.h index 7048bb3594d65be6d132d4103ee801fadf087b7e..634e81d83efd9577337e37f1ce42911574b0adf9 100644 --- a/samples/bpf/asm_goto_workaround.h +++ b/samples/bpf/asm_goto_workaround.h @@ -4,14 +4,14 @@ #define __ASM_GOTO_WORKAROUND_H /* - * This will bring in asm_volatile_goto and asm_inline macro definitions + * This will bring in asm_goto_output and asm_inline macro definitions * if enabled by compiler and config options. */ #include -#ifdef asm_volatile_goto -#undef asm_volatile_goto -#define asm_volatile_goto(x...) asm volatile("invalid use of asm_volatile_goto") +#ifdef asm_goto_output +#undef asm_goto_output +#define asm_goto_output(x...) asm volatile("invalid use of asm_goto_output") #endif /* diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 41f3602fc8de75b49a733b8e0d8359cf114edcc6..1827bc1db1e98f5d4bfd84ac206f2cce5accefd9 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -277,17 +277,20 @@ $(obj)/%.lst: $(src)/%.c FORCE rust_allowed_features := core_ffi_c +# `--out-dir` is required to avoid temporaries being created by `rustc` in the +# current working directory, which may be not accessible in the out-of-tree +# modules case. rust_common_cmd = \ RUST_MODFILE=$(modfile) $(RUSTC_OR_CLIPPY) $(rust_flags) \ -Zallow-features=$(rust_allowed_features) \ -Zcrate-attr=no_std \ -Zcrate-attr='feature($(rust_allowed_features))' \ --extern alloc --extern kernel \ - --crate-type rlib --out-dir $(obj) -L $(objtree)/rust/ \ - --crate-name $(basename $(notdir $@)) + --crate-type rlib -L $(objtree)/rust/ \ + --crate-name $(basename $(notdir $@)) \ + --out-dir $(dir $@) --emit=dep-info=$(depfile) rust_handle_depfile = \ - mv $(obj)/$(basename $(notdir $@)).d $(depfile); \ sed -i '/^\#/d' $(depfile) # `--emit=obj`, `--emit=asm` and `--emit=llvm-ir` imply a single codegen unit @@ -300,7 +303,7 @@ rust_handle_depfile = \ quiet_cmd_rustc_o_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@ cmd_rustc_o_rs = \ - $(rust_common_cmd) --emit=dep-info,obj $<; \ + $(rust_common_cmd) --emit=obj=$@ $<; \ $(rust_handle_depfile) $(obj)/%.o: $(src)/%.rs FORCE @@ -308,7 +311,7 @@ $(obj)/%.o: $(src)/%.rs FORCE quiet_cmd_rustc_rsi_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@ cmd_rustc_rsi_rs = \ - $(rust_common_cmd) --emit=dep-info -Zunpretty=expanded $< >$@; \ + $(rust_common_cmd) -Zunpretty=expanded $< >$@; \ command -v $(RUSTFMT) >/dev/null && $(RUSTFMT) $@; \ $(rust_handle_depfile) @@ -317,7 +320,7 @@ $(obj)/%.rsi: $(src)/%.rs FORCE quiet_cmd_rustc_s_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@ cmd_rustc_s_rs = \ - $(rust_common_cmd) --emit=dep-info,asm $<; \ + $(rust_common_cmd) --emit=asm=$@ $<; \ $(rust_handle_depfile) $(obj)/%.s: $(src)/%.rs FORCE @@ -325,7 +328,7 @@ $(obj)/%.s: $(src)/%.rs FORCE quiet_cmd_rustc_ll_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@ cmd_rustc_ll_rs = \ - $(rust_common_cmd) --emit=dep-info,llvm-ir $<; \ + $(rust_common_cmd) --emit=llvm-ir=$@ $<; \ $(rust_handle_depfile) $(obj)/%.ll: $(src)/%.rs FORCE diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index 6bbba36c596957cab633b51795294af773d8af61..fa5ef41806882d2918a4de27b02b5ca5a7bda3a6 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -65,6 +65,8 @@ KBUILD_CFLAGS += $(call cc-disable-warning, pointer-to-enum-cast) KBUILD_CFLAGS += -Wno-tautological-constant-out-of-range-compare KBUILD_CFLAGS += $(call cc-disable-warning, unaligned-access) KBUILD_CFLAGS += $(call cc-disable-warning, cast-function-type-strict) +KBUILD_CFLAGS += -Wno-enum-compare-conditional +KBUILD_CFLAGS += -Wno-enum-enum-conversion endif endif diff --git a/scripts/Makefile.host b/scripts/Makefile.host index da133780b7518dbcc028dee3c940e857e15a3284..a447c91893de6dcdb6a40e7d14cc535057560704 100644 --- a/scripts/Makefile.host +++ b/scripts/Makefile.host @@ -80,25 +80,28 @@ host-rust := $(addprefix $(obj)/,$(host-rust)) ##### # Handle options to gcc. Support building with separate output directory -_hostc_flags = $(KBUILD_HOSTCFLAGS) $(HOST_EXTRACFLAGS) \ +hostc_flags = -Wp,-MMD,$(depfile) \ + $(KBUILD_HOSTCFLAGS) $(HOST_EXTRACFLAGS) \ $(HOSTCFLAGS_$(target-stem).o) -_hostcxx_flags = $(KBUILD_HOSTCXXFLAGS) $(HOST_EXTRACXXFLAGS) \ +hostcxx_flags = -Wp,-MMD,$(depfile) \ + $(KBUILD_HOSTCXXFLAGS) $(HOST_EXTRACXXFLAGS) \ $(HOSTCXXFLAGS_$(target-stem).o) -_hostrust_flags = $(KBUILD_HOSTRUSTFLAGS) $(HOST_EXTRARUSTFLAGS) \ - $(HOSTRUSTFLAGS_$(target-stem)) + +# `--out-dir` is required to avoid temporaries being created by `rustc` in the +# current working directory, which may be not accessible in the out-of-tree +# modules case. +hostrust_flags = --out-dir $(dir $@) --emit=dep-info=$(depfile) \ + $(KBUILD_HOSTRUSTFLAGS) $(HOST_EXTRARUSTFLAGS) \ + $(HOSTRUSTFLAGS_$(target-stem)) # $(objtree)/$(obj) for including generated headers from checkin source files ifeq ($(KBUILD_EXTMOD),) ifdef building_out_of_srctree -_hostc_flags += -I $(objtree)/$(obj) -_hostcxx_flags += -I $(objtree)/$(obj) +hostc_flags += -I $(objtree)/$(obj) +hostcxx_flags += -I $(objtree)/$(obj) endif endif -hostc_flags = -Wp,-MMD,$(depfile) $(_hostc_flags) -hostcxx_flags = -Wp,-MMD,$(depfile) $(_hostcxx_flags) -hostrust_flags = $(_hostrust_flags) - ##### # Compile programs on the host @@ -149,9 +152,7 @@ $(host-cxxobjs): $(obj)/%.o: $(src)/%.cc FORCE # host-rust -> Executable quiet_cmd_host-rust = HOSTRUSTC $@ cmd_host-rust = \ - $(HOSTRUSTC) $(hostrust_flags) --emit=dep-info,link \ - --out-dir=$(obj)/ $<; \ - mv $(obj)/$(target-stem).d $(depfile); \ + $(HOSTRUSTC) $(hostrust_flags) --emit=link=$@ $<; \ sed -i '/^\#/d' $(depfile) $(host-rust): $(obj)/%: $(src)/%.rs FORCE $(call if_changed_dep,host-rust) diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal index 3af5e5807983a5941bdd87221f2be46f2b72436e..0faee3a477057500a0f269415a0de8a5b631b579 100644 --- a/scripts/Makefile.modfinal +++ b/scripts/Makefile.modfinal @@ -23,7 +23,7 @@ modname = $(notdir $(@:.mod.o=)) part-of-module = y quiet_cmd_cc_o_c = CC [M] $@ - cmd_cc_o_c = $(CC) $(filter-out $(CC_FLAGS_CFI) $(CFLAGS_GCOV), $(c_flags)) -c -o $@ $< + cmd_cc_o_c = $(CC) $(filter-out $(CC_FLAGS_CFI) $(CFLAGS_GCOV) $(CFLAGS_KCSAN), $(c_flags)) -c -o $@ $< %.mod.o: %.mod.c FORCE $(call if_changed_dep,cc_o_c) @@ -41,8 +41,6 @@ quiet_cmd_btf_ko = BTF [M] $@ cmd_btf_ko = \ if [ ! -f vmlinux ]; then \ printf "Skipping BTF generation for %s due to unavailability of vmlinux\n" $@ 1>&2; \ - elif [ -n "$(CONFIG_RUST)" ] && $(srctree)/scripts/is_rust_module.sh $@; then \ - printf "Skipping BTF generation for %s because it's a Rust module\n" $@ 1>&2; \ else \ LLVM_OBJCOPY="$(OBJCOPY)" $(PAHOLE) -J $(PAHOLE_FLAGS) --btf_base vmlinux $@; \ $(RESOLVE_BTFIDS) -b vmlinux $@; \ diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index e41dee64d429c42bb3fe3767a24dcdd4157de878..39aea753d0bdccc1b416eec2757cf3c09eb51afa 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -44,6 +44,7 @@ modpost-args = \ $(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E) \ $(if $(KBUILD_NSDEPS),-d $(MODULES_NSDEPS)) \ $(if $(CONFIG_MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS)$(KBUILD_NSDEPS),-N) \ + $(if $(findstring 1, $(KBUILD_EXTRA_WARN)),-W) \ -o $@ # 'make -i -k' ignores compile errors, and builds as many modules as possible. diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index d5c389df6045ef965364849c68fee591569bcd5c..c2da6ed32104f57fdc621f86b612fd0a43e7d5ba 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -396,8 +396,8 @@ class PrinterRST(Printer): version = version.stdout.decode().rstrip() except: try: - version = subprocess.run(['make', 'kernelversion'], cwd=linuxRoot, - capture_output=True, check=True) + version = subprocess.run(['make', '-s', '--no-print-directory', 'kernelversion'], + cwd=linuxRoot, capture_output=True, check=True) version = version.stdout.decode().rstrip() except: return 'Linux' @@ -495,7 +495,7 @@ eBPF programs can have an associated license, passed along with the bytecode instructions to the kernel when the programs are loaded. The format for that string is identical to the one in use for kernel modules (Dual licenses, such as "Dual BSD/GPL", may be used). Some helper functions are only accessible to -programs that are compatible with the GNU Privacy License (GPL). +programs that are compatible with the GNU General Public License (GNU GPL). In order to use such helpers, the eBPF program must be loaded with the correct license string passed (via **attr**) to the **bpf**\ () system call, and this diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 1e5e66ae5a52202f99c3d93f71ad81b239056217..ecf4250b0d2d25a1a56b13dccab6002fb80aafc2 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -4971,7 +4971,7 @@ sub process { if|for|while|switch|return|case| volatile|__volatile__| __attribute__|format|__extension__| - asm|__asm__)$/x) + asm|__asm__|scoped_guard)$/x) { # cpp #define statements have non-optional spaces, ie # if there is a space between the name and the open diff --git a/scripts/clang-tools/gen_compile_commands.py b/scripts/clang-tools/gen_compile_commands.py index d800b2c0af9771644f51bc0d8fb60d831b0b61f0..4f414ab706bd80e6f5a97a4506a0b8c118896bba 100755 --- a/scripts/clang-tools/gen_compile_commands.py +++ b/scripts/clang-tools/gen_compile_commands.py @@ -170,7 +170,7 @@ def process_line(root_directory, command_prefix, file_path): # escape the pound sign '#', either as '\#' or '$(pound)' (depending on the # kernel version). The compile_commands.json file is not interepreted # by Make, so this code replaces the escaped version with '#'. - prefix = command_prefix.replace('\#', '#').replace('$(pound)', '#') + prefix = command_prefix.replace(r'\#', '#').replace('$(pound)', '#') # Use os.path.abspath() to normalize the path resolving '.' and '..' . abs_path = os.path.abspath(os.path.join(root_directory, file_path)) diff --git a/scripts/gcc-plugins/stackleak_plugin.c b/scripts/gcc-plugins/stackleak_plugin.c index c5c2ce113c9232c331c4ebac2ba4384a24424640..d20c47d21ad8352973c93ccefc7b0931e93de545 100644 --- a/scripts/gcc-plugins/stackleak_plugin.c +++ b/scripts/gcc-plugins/stackleak_plugin.c @@ -467,6 +467,8 @@ static bool stackleak_gate(void) return false; if (STRING_EQUAL(section, ".entry.text")) return false; + if (STRING_EQUAL(section, ".head.text")) + return false; } return track_frame_size >= 0; diff --git a/scripts/is_rust_module.sh b/scripts/is_rust_module.sh deleted file mode 100755 index 28b3831a7593f42b12b4b3e8a67733d9a1c0fe44..0000000000000000000000000000000000000000 --- a/scripts/is_rust_module.sh +++ /dev/null @@ -1,16 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# -# is_rust_module.sh module.ko -# -# Returns `0` if `module.ko` is a Rust module, `1` otherwise. - -set -e - -# Using the `16_` prefix ensures other symbols with the same substring -# are not picked up (even if it would be unlikely). The last part is -# used just in case LLVM decides to use the `.` suffix. -# -# In the future, checking for the `.comment` section may be another -# option, see https://github.com/rust-lang/rust/pull/97550. -${NM} "$*" | grep -qE '^[0-9a-fA-F]+ r _R[^[:space:]]+16___IS_RUST_MODULE[^[:space:]]*$' diff --git a/scripts/kconfig/lexer.l b/scripts/kconfig/lexer.l index cc386e44368346c2309d2f60aab3cad10a5cefb0..2c2b3e6f248caff0b39faa5ece05b82a573879f6 100644 --- a/scripts/kconfig/lexer.l +++ b/scripts/kconfig/lexer.l @@ -302,8 +302,11 @@ static char *expand_token(const char *in, size_t n) new_string(); append_string(in, n); - /* get the whole line because we do not know the end of token. */ - while ((c = input()) != EOF) { + /* + * get the whole line because we do not know the end of token. + * input() returns 0 (not EOF!) when it reachs the end of file. + */ + while ((c = input()) != 0) { if (c == '\n') { unput(c); break; diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 32e573943cf036bda7d45082779917676b7a05fe..458b2948b580d65b9f48821bcc6ea5eb489d3211 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -135,8 +135,13 @@ gen_btf() ${OBJCOPY} --only-section=.BTF --set-section-flags .BTF=alloc,readonly \ --strip-all ${1} ${2} 2>/dev/null # Change e_type to ET_REL so that it can be used to link final vmlinux. - # Unlike GNU ld, lld does not allow an ET_EXEC input. - printf '\1' | dd of=${2} conv=notrunc bs=1 seek=16 status=none + # GNU ld 2.35+ and lld do not allow an ET_EXEC input. + if is_enabled CONFIG_CPU_BIG_ENDIAN; then + et_rel='\0\1' + else + et_rel='\1\0' + fi + printf "${et_rel}" | dd of=${2} conv=notrunc bs=1 seek=16 status=none } # Create ${2} .S file with all symbols from the ${1} object file diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index e6be7fc2625fde34e2ce067539312dd0219140e1..686eed37f9781bd4ae09488d9a94b5692e0bc22d 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -41,6 +41,8 @@ static bool allow_missing_ns_imports; static bool error_occurred; +static bool extra_warn; + /* * Cut off the warnings when there are too many. This typically occurs when * vmlinux is missing. ('make modules' without building vmlinux.) @@ -809,7 +811,7 @@ static void check_section(const char *modname, struct elf_info *elf, #define ALL_INIT_TEXT_SECTIONS \ ".init.text", ".meminit.text" #define ALL_EXIT_TEXT_SECTIONS \ - ".exit.text", ".memexit.text" + ".exit.text" #define ALL_PCI_INIT_SECTIONS \ ".pci_fixup_early", ".pci_fixup_header", ".pci_fixup_final", \ @@ -817,23 +819,22 @@ static void check_section(const char *modname, struct elf_info *elf, ".pci_fixup_resume_early", ".pci_fixup_suspend" #define ALL_XXXINIT_SECTIONS MEM_INIT_SECTIONS -#define ALL_XXXEXIT_SECTIONS MEM_EXIT_SECTIONS #define ALL_INIT_SECTIONS INIT_SECTIONS, ALL_XXXINIT_SECTIONS -#define ALL_EXIT_SECTIONS EXIT_SECTIONS, ALL_XXXEXIT_SECTIONS +#define ALL_EXIT_SECTIONS EXIT_SECTIONS #define DATA_SECTIONS ".data", ".data.rel" -#define TEXT_SECTIONS ".text", ".text.unlikely", ".sched.text", \ - ".kprobes.text", ".cpuidle.text", ".noinstr.text" +#define TEXT_SECTIONS ".text", ".text.*", ".sched.text", \ + ".kprobes.text", ".cpuidle.text", ".noinstr.text", \ + ".ltext", ".ltext.*" #define OTHER_TEXT_SECTIONS ".ref.text", ".head.text", ".spinlock.text", \ - ".fixup", ".entry.text", ".exception.text", ".text.*", \ + ".fixup", ".entry.text", ".exception.text", \ ".coldtext", ".softirqentry.text" #define INIT_SECTIONS ".init.*" #define MEM_INIT_SECTIONS ".meminit.*" #define EXIT_SECTIONS ".exit.*" -#define MEM_EXIT_SECTIONS ".memexit.*" #define ALL_TEXT_SECTIONS ALL_INIT_TEXT_SECTIONS, ALL_EXIT_TEXT_SECTIONS, \ TEXT_SECTIONS, OTHER_TEXT_SECTIONS @@ -862,7 +863,6 @@ enum mismatch { TEXT_TO_ANY_EXIT, DATA_TO_ANY_EXIT, XXXINIT_TO_SOME_INIT, - XXXEXIT_TO_SOME_EXIT, ANY_INIT_TO_ANY_EXIT, ANY_EXIT_TO_ANY_INIT, EXPORT_TO_INIT_EXIT, @@ -937,12 +937,6 @@ static const struct sectioncheck sectioncheck[] = { .bad_tosec = { INIT_SECTIONS, NULL }, .mismatch = XXXINIT_TO_SOME_INIT, }, -/* Do not reference exit code/data from memexit code/data */ -{ - .fromsec = { ALL_XXXEXIT_SECTIONS, NULL }, - .bad_tosec = { EXIT_SECTIONS, NULL }, - .mismatch = XXXEXIT_TO_SOME_EXIT, -}, /* Do not use exit code/data from init code */ { .fromsec = { ALL_INIT_SECTIONS, NULL }, @@ -1085,9 +1079,20 @@ static int secref_whitelist(const struct sectioncheck *mismatch, "*_console"))) return 0; - /* symbols in data sections that may refer to meminit/exit sections */ + /* symbols in data sections that may refer to meminit sections */ if (match(fromsec, PATTERNS(DATA_SECTIONS)) && - match(tosec, PATTERNS(ALL_XXXINIT_SECTIONS, ALL_EXIT_SECTIONS)) && + match(tosec, PATTERNS(ALL_XXXINIT_SECTIONS)) && + match(fromsym, PATTERNS("*driver"))) + return 0; + + /* + * symbols in data sections must not refer to .exit.*, but there are + * quite a few offenders, so hide these unless for W=1 builds until + * these are fixed. + */ + if (!extra_warn && + match(fromsec, PATTERNS(DATA_SECTIONS)) && + match(tosec, PATTERNS(EXIT_SECTIONS)) && match(fromsym, PATTERNS("*driver"))) return 0; @@ -1254,7 +1259,6 @@ static void report_sec_mismatch(const char *modname, case TEXT_TO_ANY_EXIT: case DATA_TO_ANY_EXIT: case XXXINIT_TO_SOME_INIT: - case XXXEXIT_TO_SOME_EXIT: case ANY_INIT_TO_ANY_EXIT: case ANY_EXIT_TO_ANY_INIT: warn("%s: section mismatch in reference: %s (section: %s) -> %s (section: %s)\n", @@ -2290,7 +2294,7 @@ int main(int argc, char **argv) LIST_HEAD(dump_lists); struct dump_list *dl, *dl2; - while ((opt = getopt(argc, argv, "ei:mnT:o:awENd:")) != -1) { + while ((opt = getopt(argc, argv, "ei:mnT:o:aWwENd:")) != -1) { switch (opt) { case 'e': external_module = true; @@ -2315,6 +2319,9 @@ int main(int argc, char **argv) case 'T': files_source = optarg; break; + case 'W': + extra_warn = true; + break; case 'w': warn_unresolved = true; break; diff --git a/scripts/mod/sumversion.c b/scripts/mod/sumversion.c index 6bf9caca096844b554a76abff1a56722e268708c..a72e6cf61a1f0bf18b030e28772fa99e33ae9e2b 100644 --- a/scripts/mod/sumversion.c +++ b/scripts/mod/sumversion.c @@ -326,7 +326,12 @@ static int parse_source_files(const char *objfile, struct md4_ctx *md) /* Sum all files in the same dir or subdirs. */ while ((line = get_line(&pos))) { - char* p = line; + char* p; + + /* trim the leading spaces away */ + while (isspace(*line)) + line++; + p = line; if (strncmp(line, "source_", sizeof("source_")-1) == 0) { p = strrchr(line, ' '); diff --git a/security/apparmor/include/lib.h b/security/apparmor/include/lib.h index f42359f58eb5878bf3241405b4d2845d3c61dca5..d468c8b90298dee2c6736af83f624e94f7031f82 100644 --- a/security/apparmor/include/lib.h +++ b/security/apparmor/include/lib.h @@ -226,7 +226,7 @@ void aa_policy_destroy(struct aa_policy *policy); */ #define fn_label_build(L, P, GFP, FN) \ ({ \ - __label__ __cleanup, __done; \ + __label__ __do_cleanup, __done; \ struct aa_label *__new_; \ \ if ((L)->size > 1) { \ @@ -244,7 +244,7 @@ void aa_policy_destroy(struct aa_policy *policy); __new_ = (FN); \ AA_BUG(!__new_); \ if (IS_ERR(__new_)) \ - goto __cleanup; \ + goto __do_cleanup; \ __lvec[__j++] = __new_; \ } \ for (__j = __count = 0; __j < (L)->size; __j++) \ @@ -266,7 +266,7 @@ void aa_policy_destroy(struct aa_policy *policy); vec_cleanup(profile, __pvec, __count); \ } else \ __new_ = NULL; \ -__cleanup: \ +__do_cleanup: \ vec_cleanup(label, __lvec, (L)->size); \ } else { \ (P) = labels_profile(L); \ diff --git a/security/keys/key.c b/security/keys/key.c index e65240641ca577784fda5bbfc3b835cc63e6885d..f2a84d86eab438f497ddddc997797a365977824d 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -464,7 +464,8 @@ static int __key_instantiate_and_link(struct key *key, if (authkey) key_invalidate(authkey); - key_set_expiry(key, prep->expiry); + if (prep->expiry != TIME64_MAX) + key_set_expiry(key, prep->expiry); } } diff --git a/security/keys/trusted-keys/trusted_tpm2.c b/security/keys/trusted-keys/trusted_tpm2.c index bc700f85f80be73e587522aab8df7b81f6f830c1..ea277c55a38dba9c3333fb52c7800df9356d52cd 100644 --- a/security/keys/trusted-keys/trusted_tpm2.c +++ b/security/keys/trusted-keys/trusted_tpm2.c @@ -38,6 +38,7 @@ static int tpm2_key_encode(struct trusted_key_payload *payload, u8 *end_work = scratch + SCRATCH_SIZE; u8 *priv, *pub; u16 priv_len, pub_len; + int ret; priv_len = get_unaligned_be16(src) + 2; priv = src; @@ -57,8 +58,10 @@ static int tpm2_key_encode(struct trusted_key_payload *payload, unsigned char bool[3], *w = bool; /* tag 0 is emptyAuth */ w = asn1_encode_boolean(w, w + sizeof(bool), true); - if (WARN(IS_ERR(w), "BUG: Boolean failed to encode")) - return PTR_ERR(w); + if (WARN(IS_ERR(w), "BUG: Boolean failed to encode")) { + ret = PTR_ERR(w); + goto err; + } work = asn1_encode_tag(work, end_work, 0, bool, w - bool); } @@ -69,8 +72,10 @@ static int tpm2_key_encode(struct trusted_key_payload *payload, * trigger, so if it does there's something nefarious going on */ if (WARN(work - scratch + pub_len + priv_len + 14 > SCRATCH_SIZE, - "BUG: scratch buffer is too small")) - return -EINVAL; + "BUG: scratch buffer is too small")) { + ret = -EINVAL; + goto err; + } work = asn1_encode_integer(work, end_work, options->keyhandle); work = asn1_encode_octet_string(work, end_work, pub, pub_len); @@ -79,10 +84,18 @@ static int tpm2_key_encode(struct trusted_key_payload *payload, work1 = payload->blob; work1 = asn1_encode_sequence(work1, work1 + sizeof(payload->blob), scratch, work - scratch); - if (WARN(IS_ERR(work1), "BUG: ASN.1 encoder failed")) - return PTR_ERR(work1); + if (IS_ERR(work1)) { + ret = PTR_ERR(work1); + pr_err("BUG: ASN.1 encoder failed with %d\n", ret); + goto err; + } + kfree(scratch); return work1 - payload->blob; + +err: + kfree(scratch); + return ret; } struct tpm2_key_context { diff --git a/security/landlock/fs.c b/security/landlock/fs.c index 64ed7665455fedeb4a35a638cbc9e840b124004d..d328965f32f7f801c6c39af251b6ee1865cf0853 100644 --- a/security/landlock/fs.c +++ b/security/landlock/fs.c @@ -824,8 +824,8 @@ static int current_check_refer_path(struct dentry *const old_dentry, bool allow_parent1, allow_parent2; access_mask_t access_request_parent1, access_request_parent2; struct path mnt_dir; - layer_mask_t layer_masks_parent1[LANDLOCK_NUM_ACCESS_FS], - layer_masks_parent2[LANDLOCK_NUM_ACCESS_FS]; + layer_mask_t layer_masks_parent1[LANDLOCK_NUM_ACCESS_FS] = {}, + layer_masks_parent2[LANDLOCK_NUM_ACCESS_FS] = {}; if (!dom) return 0; diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c index 2ca0ccbd905aeb46d5fdc84ffc5fe6f800cdcc76..d0cb3d0cbf98520f5bd2afce65d4c261b1741393 100644 --- a/security/landlock/syscalls.c +++ b/security/landlock/syscalls.c @@ -32,6 +32,18 @@ #include "ruleset.h" #include "setup.h" +static bool is_initialized(void) +{ + if (likely(landlock_initialized)) + return true; + + pr_warn_once( + "Disabled but requested by user space. " + "You should enable Landlock at boot time: " + "https://docs.kernel.org/userspace-api/landlock.html#boot-time-configuration\n"); + return false; +} + /** * copy_min_struct_from_user - Safe future-proof argument copying * @@ -165,7 +177,7 @@ SYSCALL_DEFINE3(landlock_create_ruleset, /* Build-time checks. */ build_check_abi(); - if (!landlock_initialized) + if (!is_initialized()) return -EOPNOTSUPP; if (flags) { @@ -311,7 +323,7 @@ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd, struct landlock_ruleset *ruleset; int res, err; - if (!landlock_initialized) + if (!is_initialized()) return -EOPNOTSUPP; /* No flag for now. */ @@ -402,7 +414,7 @@ SYSCALL_DEFINE2(landlock_restrict_self, const int, ruleset_fd, const __u32, struct landlock_cred_security *new_llcred; int err; - if (!landlock_initialized) + if (!is_initialized()) return -EOPNOTSUPP; /* diff --git a/security/security.c b/security/security.c index fc15b963e1028dfabfb64d78dea215208b78ddde..1b504c296551cc3cb193a2168c884a6fcef15ebd 100644 --- a/security/security.c +++ b/security/security.c @@ -2186,7 +2186,19 @@ EXPORT_SYMBOL(security_inode_setsecctx); int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) { - return call_int_hook(inode_getsecctx, -EOPNOTSUPP, inode, ctx, ctxlen); + struct security_hook_list *hp; + int rc; + + /* + * Only one module will provide a security context. + */ + hlist_for_each_entry(hp, &security_hook_heads.inode_getsecctx, list) { + rc = hp->hook.inode_getsecctx(inode, ctx, ctxlen); + if (rc != LSM_RET_DEFAULT(inode_getsecctx)) + return rc; + } + + return LSM_RET_DEFAULT(inode_getsecctx); } EXPORT_SYMBOL(security_inode_getsecctx); diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index fbadc61feedd12f126da10e1dfc8f700316d7817..feba69549d086545f97b91e8931ce257de195182 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -1309,7 +1309,8 @@ static int smack_inode_setxattr(struct user_namespace *mnt_userns, check_star = 1; } else if (strcmp(name, XATTR_NAME_SMACKTRANSMUTE) == 0) { check_priv = 1; - if (size != TRANS_TRUE_SIZE || + if (!S_ISDIR(d_backing_inode(dentry)->i_mode) || + size != TRANS_TRUE_SIZE || strncmp(value, TRANS_TRUE, TRANS_TRUE_SIZE) != 0) rc = -EINVAL; } else @@ -2782,6 +2783,15 @@ static int smack_inode_setsecurity(struct inode *inode, const char *name, if (value == NULL || size > SMK_LONGLABEL || size == 0) return -EINVAL; + if (strcmp(name, XATTR_SMACK_TRANSMUTE) == 0) { + if (!S_ISDIR(inode->i_mode) || size != TRANS_TRUE_SIZE || + strncmp(value, TRANS_TRUE, TRANS_TRUE_SIZE) != 0) + return -EINVAL; + + nsp->smk_flags |= SMK_INODE_TRANSMUTE; + return 0; + } + skp = smk_import_entry(value, size); if (IS_ERR(skp)) return PTR_ERR(skp); diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c index f4cd9b58b20547ec29bdfef8a77421b0cb5b596f..a7af085550b2d7f8fc4b4d279084431638b3ccce 100644 --- a/security/tomoyo/common.c +++ b/security/tomoyo/common.c @@ -2648,13 +2648,14 @@ ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head, { int error = buffer_len; size_t avail_len = buffer_len; - char *cp0 = head->write_buf; + char *cp0; int idx; if (!head->write) return -EINVAL; if (mutex_lock_interruptible(&head->io_sem)) return -EINTR; + cp0 = head->write_buf; head->read_user_buf_avail = 0; idx = tomoyo_read_lock(); /* Read a line and dispatch it to the policy handler. */ diff --git a/sound/core/Makefile b/sound/core/Makefile index 2762f03d9b7bc52a5af9eee423c83d68ffd3d880..a7a1590b295266544904f46fa799e2bd25fbe4ed 100644 --- a/sound/core/Makefile +++ b/sound/core/Makefile @@ -30,7 +30,6 @@ snd-ctl-led-objs := control_led.o snd-rawmidi-objs := rawmidi.o snd-timer-objs := timer.o snd-hrtimer-objs := hrtimer.o -snd-rtctimer-objs := rtctimer.o snd-hwdep-objs := hwdep.o snd-seq-device-objs := seq_device.o diff --git a/sound/core/seq/seq_midi.c b/sound/core/seq/seq_midi.c index 4589aac09154260e53d1068ccef96b7ad5577064..b00bbf18a6f5d81b5688bf230c027a6a3d0b3291 100644 --- a/sound/core/seq/seq_midi.c +++ b/sound/core/seq/seq_midi.c @@ -112,6 +112,12 @@ static int dump_midi(struct snd_rawmidi_substream *substream, const char *buf, i return 0; } +/* callback for snd_seq_dump_var_event(), bridging to dump_midi() */ +static int __dump_midi(void *ptr, void *buf, int count) +{ + return dump_midi(ptr, buf, count); +} + static int event_process_midi(struct snd_seq_event *ev, int direct, void *private_data, int atomic, int hop) { @@ -131,7 +137,7 @@ static int event_process_midi(struct snd_seq_event *ev, int direct, pr_debug("ALSA: seq_midi: invalid sysex event flags = 0x%x\n", ev->flags); return 0; } - snd_seq_dump_var_event(ev, (snd_seq_dump_func_t)dump_midi, substream); + snd_seq_dump_var_event(ev, __dump_midi, substream); snd_midi_event_reset_decode(msynth->parser); } else { if (msynth->parser == NULL) diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c index f5cae49500c81447d8bbabf8a800ebd483409d4a..ffd8e7202c334d644cf75da637045eb9014951fa 100644 --- a/sound/core/seq/seq_virmidi.c +++ b/sound/core/seq/seq_virmidi.c @@ -62,6 +62,13 @@ static void snd_virmidi_init_event(struct snd_virmidi *vmidi, /* * decode input event and put to read buffer of each opened file */ + +/* callback for snd_seq_dump_var_event(), bridging to snd_rawmidi_receive() */ +static int dump_to_rawmidi(void *ptr, void *buf, int count) +{ + return snd_rawmidi_receive(ptr, buf, count); +} + static int snd_virmidi_dev_receive_event(struct snd_virmidi_dev *rdev, struct snd_seq_event *ev, bool atomic) @@ -80,7 +87,7 @@ static int snd_virmidi_dev_receive_event(struct snd_virmidi_dev *rdev, if (ev->type == SNDRV_SEQ_EVENT_SYSEX) { if ((ev->flags & SNDRV_SEQ_EVENT_LENGTH_MASK) != SNDRV_SEQ_EVENT_LENGTH_VARIABLE) continue; - snd_seq_dump_var_event(ev, (snd_seq_dump_func_t)snd_rawmidi_receive, vmidi->substream); + snd_seq_dump_var_event(ev, dump_to_rawmidi, vmidi->substream); snd_midi_event_reset_decode(vmidi->parser); } else { len = snd_midi_event_decode(vmidi->parser, msg, sizeof(msg), ev); diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c index 9be2260e4ca2d26b41c9784b686ae6080a0e6954..8753125683692be4e696453e120f68a7a3394311 100644 --- a/sound/firewire/amdtp-stream.c +++ b/sound/firewire/amdtp-stream.c @@ -771,10 +771,14 @@ static int check_cip_header(struct amdtp_stream *s, const __be32 *buf, } else { unsigned int dbc_interval; - if (*data_blocks > 0 && s->ctx_data.tx.dbc_interval > 0) - dbc_interval = s->ctx_data.tx.dbc_interval; - else - dbc_interval = *data_blocks; + if (!(s->flags & CIP_DBC_IS_PAYLOAD_QUADLETS)) { + if (*data_blocks > 0 && s->ctx_data.tx.dbc_interval > 0) + dbc_interval = s->ctx_data.tx.dbc_interval; + else + dbc_interval = *data_blocks; + } else { + dbc_interval = payload_length / sizeof(__be32); + } lost = dbc != ((*data_block_counter + dbc_interval) & 0xff); } @@ -934,7 +938,7 @@ static int generate_device_pkt_descs(struct amdtp_stream *s, // to the reason. unsigned int safe_cycle = increment_ohci_cycle_count(next_cycle, IR_JUMBO_PAYLOAD_MAX_SKIP_CYCLES); - lost = (compare_ohci_cycle_count(safe_cycle, cycle) > 0); + lost = (compare_ohci_cycle_count(safe_cycle, cycle) < 0); } if (lost) { dev_err(&s->unit->device, "Detect discontinuity of cycle: %d %d\n", diff --git a/sound/firewire/amdtp-stream.h b/sound/firewire/amdtp-stream.h index 1f957c946c956a3a32a743e9b7b218526797e4d3..cf9ab347277f2a22388270b9f7ef2cb27271b64e 100644 --- a/sound/firewire/amdtp-stream.h +++ b/sound/firewire/amdtp-stream.h @@ -37,6 +37,9 @@ * the value of current SYT_INTERVAL; e.g. initial value is not zero. * @CIP_UNAWARE_SYT: For outgoing packet, the value in SYT field of CIP is 0xffff. * For incoming packet, the value in SYT field of CIP is not handled. + * @CIP_DBC_IS_PAYLOAD_QUADLETS: Available for incoming packet, and only effective with + * CIP_DBC_IS_END_EVENT flag. The value of dbc field is the number of accumulated quadlets + * in CIP payload, instead of the number of accumulated data blocks. */ enum cip_flags { CIP_NONBLOCKING = 0x00, @@ -51,6 +54,7 @@ enum cip_flags { CIP_NO_HEADER = 0x100, CIP_UNALIGHED_DBC = 0x200, CIP_UNAWARE_SYT = 0x400, + CIP_DBC_IS_PAYLOAD_QUADLETS = 0x800, }; /** diff --git a/sound/hda/intel-sdw-acpi.c b/sound/hda/intel-sdw-acpi.c index b57d72ea4503fa7504757eb6542b51e5b2e7b5e9..4e376994bf78b91e0d4889cf9b225d21c388c984 100644 --- a/sound/hda/intel-sdw-acpi.c +++ b/sound/hda/intel-sdw-acpi.c @@ -41,6 +41,8 @@ static bool is_link_enabled(struct fwnode_handle *fw_node, u8 idx) "intel-quirk-mask", &quirk_mask); + fwnode_handle_put(link); + if (quirk_mask & SDW_INTEL_QUIRK_MASK_BUS_DISABLE) return false; diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index e8819e8a98763cb5a4760768be387a4a387c384d..e8209178d87bbcc88551e6773c90c9fec7d98af2 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -344,6 +344,7 @@ enum { CXT_FIXUP_HP_ZBOOK_MUTE_LED, CXT_FIXUP_HEADSET_MIC, CXT_FIXUP_HP_MIC_NO_PRESENCE, + CXT_PINCFG_SWS_JS201D, }; /* for hda_fixup_thinkpad_acpi() */ @@ -841,6 +842,17 @@ static const struct hda_pintbl cxt_pincfg_lemote[] = { {} }; +/* SuoWoSi/South-holding JS201D with sn6140 */ +static const struct hda_pintbl cxt_pincfg_sws_js201d[] = { + { 0x16, 0x03211040 }, /* hp out */ + { 0x17, 0x91170110 }, /* SPK/Class_D */ + { 0x18, 0x95a70130 }, /* Internal mic */ + { 0x19, 0x03a11020 }, /* Headset Mic */ + { 0x1a, 0x40f001f0 }, /* Not used */ + { 0x21, 0x40f001f0 }, /* Not used */ + {} +}; + static const struct hda_fixup cxt_fixups[] = { [CXT_PINCFG_LENOVO_X200] = { .type = HDA_FIXUP_PINS, @@ -996,6 +1008,10 @@ static const struct hda_fixup cxt_fixups[] = { .chained = true, .chain_id = CXT_FIXUP_HEADSET_MIC, }, + [CXT_PINCFG_SWS_JS201D] = { + .type = HDA_FIXUP_PINS, + .v.pins = cxt_pincfg_sws_js201d, + }, }; static const struct snd_pci_quirk cxt5045_fixups[] = { @@ -1069,6 +1085,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x103c, 0x8457, "HP Z2 G4 mini", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x8458, "HP Z2 G4 mini premium", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN), + SND_PCI_QUIRK(0x14f1, 0x0265, "SWS JS201D", CXT_PINCFG_SWS_JS201D), SND_PCI_QUIRK(0x152d, 0x0833, "OLPC XO-1.5", CXT_FIXUP_OLPC_XO), SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x215e, "Lenovo T410", CXT_PINCFG_LENOVO_TP410), @@ -1109,6 +1126,7 @@ static const struct hda_model_fixup cxt5066_fixup_models[] = { { .id = CXT_FIXUP_HP_ZBOOK_MUTE_LED, .name = "hp-zbook-mute-led" }, { .id = CXT_FIXUP_HP_MIC_NO_PRESENCE, .name = "hp-mic-fix" }, { .id = CXT_PINCFG_LENOVO_NOTEBOOK, .name = "lenovo-20149" }, + { .id = CXT_PINCFG_SWS_JS201D, .name = "sws-js201d" }, {} }; diff --git a/sound/pci/hda/patch_cs8409.c b/sound/pci/hda/patch_cs8409.c index 627899959ffe8c34c76211d51824e1d1e93d33a8..e41316e2e98338a5d69245ed9e9db1b979a2fdf2 100644 --- a/sound/pci/hda/patch_cs8409.c +++ b/sound/pci/hda/patch_cs8409.c @@ -1371,6 +1371,7 @@ void dolphin_fixups(struct hda_codec *codec, const struct hda_fixup *fix, int ac spec->scodecs[CS8409_CODEC1] = &dolphin_cs42l42_1; spec->scodecs[CS8409_CODEC1]->codec = codec; spec->num_scodecs = 2; + spec->gen.suppress_vmaster = 1; codec->patch_ops = cs8409_dolphin_patch_ops; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 62f2137044923d81658346dc9030170f49eedae0..f0b939862a2a6ee83c2e13936d2c83d2b7fc2979 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3681,6 +3681,7 @@ static void alc285_hp_init(struct hda_codec *codec) int i, val; int coef38, coef0d, coef36; + alc_write_coefex_idx(codec, 0x58, 0x00, 0x1888); /* write default value */ alc_update_coef_idx(codec, 0x4a, 1<<15, 1<<15); /* Reset HP JD */ coef38 = alc_read_coef_idx(codec, 0x38); /* Amp control */ coef0d = alc_read_coef_idx(codec, 0x0d); /* Digital Misc control */ @@ -6692,6 +6693,60 @@ static void alc285_fixup_hp_spectre_x360(struct hda_codec *codec, } } +static void alc285_fixup_hp_envy_x360(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + static const struct coef_fw coefs[] = { + WRITE_COEF(0x08, 0x6a0c), WRITE_COEF(0x0d, 0xa023), + WRITE_COEF(0x10, 0x0320), WRITE_COEF(0x1a, 0x8c03), + WRITE_COEF(0x25, 0x1800), WRITE_COEF(0x26, 0x003a), + WRITE_COEF(0x28, 0x1dfe), WRITE_COEF(0x29, 0xb014), + WRITE_COEF(0x2b, 0x1dfe), WRITE_COEF(0x37, 0xfe15), + WRITE_COEF(0x38, 0x7909), WRITE_COEF(0x45, 0xd489), + WRITE_COEF(0x46, 0x00f4), WRITE_COEF(0x4a, 0x21e0), + WRITE_COEF(0x66, 0x03f0), WRITE_COEF(0x67, 0x1000), + WRITE_COEF(0x6e, 0x1005), { } + }; + + static const struct hda_pintbl pincfgs[] = { + { 0x12, 0xb7a60130 }, /* Internal microphone*/ + { 0x14, 0x90170150 }, /* B&O soundbar speakers */ + { 0x17, 0x90170153 }, /* Side speakers */ + { 0x19, 0x03a11040 }, /* Headset microphone */ + { } + }; + + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + snd_hda_apply_pincfgs(codec, pincfgs); + + /* Fixes volume control problem for side speakers */ + alc295_fixup_disable_dac3(codec, fix, action); + + /* Fixes no sound from headset speaker */ + snd_hda_codec_amp_stereo(codec, 0x21, HDA_OUTPUT, 0, -1, 0); + + /* Auto-enable headset mic when plugged */ + snd_hda_jack_set_gating_jack(codec, 0x19, 0x21); + + /* Headset mic volume enhancement */ + snd_hda_codec_set_pin_target(codec, 0x19, PIN_VREF50); + break; + case HDA_FIXUP_ACT_INIT: + alc_process_coef_fw(codec, coefs); + break; + case HDA_FIXUP_ACT_BUILD: + rename_ctl(codec, "Bass Speaker Playback Volume", + "B&O-Tuned Playback Volume"); + rename_ctl(codec, "Front Playback Switch", + "B&O Soundbar Playback Switch"); + rename_ctl(codec, "Bass Speaker Playback Switch", + "Side Speaker Playback Switch"); + break; + } +} + /* for hda_fixup_thinkpad_acpi() */ #include "thinkpad_helper.c" @@ -7130,6 +7185,7 @@ enum { ALC280_FIXUP_HP_9480M, ALC245_FIXUP_HP_X360_AMP, ALC285_FIXUP_HP_SPECTRE_X360_EB1, + ALC285_FIXUP_HP_ENVY_X360, ALC288_FIXUP_DELL_HEADSET_MODE, ALC288_FIXUP_DELL1_MIC_NO_PRESENCE, ALC288_FIXUP_DELL_XPS_13, @@ -9053,6 +9109,12 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_hp_spectre_x360_eb1 }, + [ALC285_FIXUP_HP_ENVY_X360] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_hp_envy_x360, + .chained = true, + .chain_id = ALC285_FIXUP_HP_GPIO_AMP_INIT, + }, [ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_ideapad_s740_coef, @@ -9377,7 +9439,7 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = cs35l41_fixup_i2c_two, .chained = true, - .chain_id = ALC269_FIXUP_THINKPAD_ACPI, + .chain_id = ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK, }, [ALC245_FIXUP_HP_MUTE_LED_COEFBIT] = { .type = HDA_FIXUP_FUNC, @@ -9392,6 +9454,8 @@ static const struct hda_fixup alc269_fixups[] = { [ALC287_FIXUP_THINKPAD_I2S_SPK] = { .type = HDA_FIXUP_FUNC, .v.func = alc287_fixup_bind_dacs, + .chained = true, + .chain_id = ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK, }, [ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD] = { .type = HDA_FIXUP_FUNC, @@ -9431,6 +9495,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x1247, "Acer vCopperbox", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS), SND_PCI_QUIRK(0x1025, 0x1248, "Acer Veriton N4660G", ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1269, "Acer SWIFT SF314-54", ALC256_FIXUP_ACER_HEADSET_MIC), + SND_PCI_QUIRK(0x1025, 0x126a, "Acer Swift SF114-32", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x128f, "Acer Veriton Z6860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1290, "Acer Veriton Z4860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1291, "Acer Veriton Z4660G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), @@ -9591,9 +9656,11 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x8519, "HP Spectre x360 15-df0xxx", ALC285_FIXUP_HP_SPECTRE_X360), SND_PCI_QUIRK(0x103c, 0x8537, "HP ProBook 440 G6", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x85de, "HP Envy x360 13-ar0xxx", ALC285_FIXUP_HP_ENVY_X360), SND_PCI_QUIRK(0x103c, 0x860f, "HP ZBook 15 G6", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x861f, "HP Elite Dragonfly G1", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED), + SND_PCI_QUIRK(0x103c, 0x86c1, "HP Laptop 15-da3001TU", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x86c7, "HP Envy AiO 32", ALC274_FIXUP_HP_ENVY_GPIO), SND_PCI_QUIRK(0x103c, 0x86e7, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1), SND_PCI_QUIRK(0x103c, 0x86e8, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1), @@ -9617,6 +9684,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8786, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8787, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8788, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED), + SND_PCI_QUIRK(0x103c, 0x87b7, "HP Laptop 14-fq0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87e5, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87e7, "HP ProBook 450 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), @@ -9658,6 +9726,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8973, "HP EliteBook 860 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8974, "HP EliteBook 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8975, "HP EliteBook x360 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x897d, "HP mt440 Mobile Thin Client U74", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8981, "HP Elite Dragonfly G3", ALC245_FIXUP_CS35L41_SPI_4), SND_PCI_QUIRK(0x103c, 0x898e, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x898f, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2), @@ -9683,16 +9752,20 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8aa3, "HP ProBook 450 G9 (MB 8AA1)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aa8, "HP EliteBook 640 G9 (MB 8AA6)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aab, "HP EliteBook 650 G9 (MB 8AA9)", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8ab9, "HP EliteBook 840 G8 (MB 8AB8)", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8b0f, "HP Elite mt645 G7 Mobile Thin Client U81", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b2f, "HP 255 15.6 inch G10 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), + SND_PCI_QUIRK(0x103c, 0x8b3f, "HP mt440 Mobile Thin Client U91", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b43, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b44, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b45, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b46, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b47, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8b59, "HP Elite mt645 G7 Mobile Thin Client U89", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b5d, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b5e, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b63, "HP Elite Dragonfly 13.5 inch G4", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), @@ -9720,8 +9793,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8c70, "HP EliteBook 835 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c71, "HP EliteBook 845 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c8a, "HP EliteBook 630", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c8c, "HP EliteBook 660", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c90, "HP EliteBook 640", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c91, "HP EliteBook 660", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8c97, "HP ZBook", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8ca1, "HP ZBook Power", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8ca2, "HP ZBook Power", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), @@ -9827,7 +9906,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10ec, 0x1252, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x1254, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x12cc, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), - SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE), + SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_ASPIRE_HEADSET_MIC), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_AMP), @@ -10043,12 +10122,15 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d05, 0x1147, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x1d05, 0x115c, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x1d05, 0x121b, "TongFang GMxAGxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x1387, "TongFang GMxIXxx", ALC2XX_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1d17, 0x3288, "Haier Boyue G42", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS), SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO), + SND_PCI_QUIRK(0x2782, 0x1707, "Vaio VJFE-ADL", ALC298_FIXUP_SPK_VOLUME), SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC), SND_PCI_QUIRK(0x8086, 0x2080, "Intel NUC 8 Rugged", ALC256_FIXUP_INTEL_NUC8_RUGGED), SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10), @@ -10236,6 +10318,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC295_FIXUP_HP_OMEN, .name = "alc295-hp-omen"}, {.id = ALC285_FIXUP_HP_SPECTRE_X360, .name = "alc285-hp-spectre-x360"}, {.id = ALC285_FIXUP_HP_SPECTRE_X360_EB1, .name = "alc285-hp-spectre-x360-eb1"}, + {.id = ALC285_FIXUP_HP_ENVY_X360, .name = "alc285-hp-envy-x360"}, {.id = ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP, .name = "alc287-ideapad-bass-spk-amp"}, {.id = ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN, .name = "alc287-yoga9-bass-spk-pin"}, {.id = ALC623_FIXUP_LENOVO_THINKSTATION_P340, .name = "alc623-lenovo-thinkstation-p340"}, @@ -10674,6 +10757,8 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { * at most one tbl is allowed to define for the same vendor and same codec */ static const struct snd_hda_pin_quirk alc269_fallback_pin_fixup_tbl[] = { + SND_HDA_PIN_QUIRK(0x10ec0256, 0x1025, "Acer", ALC2XX_FIXUP_HEADSET_MIC, + {0x19, 0x40000000}), SND_HDA_PIN_QUIRK(0x10ec0289, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, {0x19, 0x40000000}, {0x1b, 0x40000000}), @@ -11363,8 +11448,7 @@ static void alc897_hp_automute_hook(struct hda_codec *codec, snd_hda_gen_hp_automute(codec, jack); vref = spec->gen.hp_jack_present ? (PIN_HP | AC_PINCTL_VREF_100) : PIN_HP; - snd_hda_codec_write(codec, 0x1b, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, - vref); + snd_hda_set_pin_ctl(codec, 0x1b, vref); } static void alc897_fixup_lenovo_headset_mic(struct hda_codec *codec, @@ -11373,6 +11457,10 @@ static void alc897_fixup_lenovo_headset_mic(struct hda_codec *codec, struct alc_spec *spec = codec->spec; if (action == HDA_FIXUP_ACT_PRE_PROBE) { spec->gen.hp_automute_hook = alc897_hp_automute_hook; + spec->no_shutup_pins = 1; + } + if (action == HDA_FIXUP_ACT_PROBE) { + snd_hda_set_pin_ctl_cache(codec, 0x1a, PIN_IN | AC_PINCTL_VREF_100); } } diff --git a/sound/sh/aica.c b/sound/sh/aica.c index 6e9d6bd67369afca349114f379875841c7eda79f..8b47bfcd90318414f31af4e942f3e97d5b5cac29 100644 --- a/sound/sh/aica.c +++ b/sound/sh/aica.c @@ -278,7 +278,8 @@ static void run_spu_dma(struct work_struct *work) dreamcastcard->clicks++; if (unlikely(dreamcastcard->clicks >= AICA_PERIOD_NUMBER)) dreamcastcard->clicks %= AICA_PERIOD_NUMBER; - mod_timer(&dreamcastcard->timer, jiffies + 1); + if (snd_pcm_running(dreamcastcard->substream)) + mod_timer(&dreamcastcard->timer, jiffies + 1); } } @@ -290,6 +291,8 @@ static void aica_period_elapsed(struct timer_list *t) /*timer function - so cannot sleep */ int play_period; struct snd_pcm_runtime *runtime; + if (!snd_pcm_running(substream)) + return; runtime = substream->runtime; dreamcastcard = substream->pcm->private_data; /* Have we played out an additional period? */ @@ -350,12 +353,19 @@ static int snd_aicapcm_pcm_open(struct snd_pcm_substream return 0; } +static int snd_aicapcm_pcm_sync_stop(struct snd_pcm_substream *substream) +{ + struct snd_card_aica *dreamcastcard = substream->pcm->private_data; + + del_timer_sync(&dreamcastcard->timer); + cancel_work_sync(&dreamcastcard->spu_dma_work); + return 0; +} + static int snd_aicapcm_pcm_close(struct snd_pcm_substream *substream) { struct snd_card_aica *dreamcastcard = substream->pcm->private_data; - flush_work(&(dreamcastcard->spu_dma_work)); - del_timer(&dreamcastcard->timer); dreamcastcard->substream = NULL; kfree(dreamcastcard->channel); spu_disable(); @@ -401,6 +411,7 @@ static const struct snd_pcm_ops snd_aicapcm_playback_ops = { .prepare = snd_aicapcm_pcm_prepare, .trigger = snd_aicapcm_pcm_trigger, .pointer = snd_aicapcm_pcm_pointer, + .sync_stop = snd_aicapcm_pcm_sync_stop, }; /* TO DO: set up to handle more than one pcm instance */ diff --git a/sound/soc/amd/acp-config.c b/sound/soc/amd/acp-config.c index 9ee71a99a0871e7884f00220972c8dc60df6c8bb..0932473b63945fb3eda1ac6087245e6daa1f71ff 100644 --- a/sound/soc/amd/acp-config.c +++ b/sound/soc/amd/acp-config.c @@ -3,7 +3,7 @@ // This file is provided under a dual BSD/GPLv2 license. When using or // redistributing this file, you may do so under either license. // -// Copyright(c) 2021, 2023 Advanced Micro Devices, Inc. +// Copyright(c) 2021 Advanced Micro Devices, Inc. // // Authors: Ajit Kumar Pandey // @@ -35,19 +35,6 @@ static const struct config_entry config_table[] = { {} }, }, - { - .flags = FLAG_AMD_LEGACY, - .device = ACP_PCI_DEV_ID, - .dmi_table = (const struct dmi_system_id []) { - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Valve"), - DMI_MATCH(DMI_PRODUCT_NAME, "Jupiter"), - }, - }, - {} - }, - }, { .flags = FLAG_AMD_SOF, .device = ACP_PCI_DEV_ID, diff --git a/sound/soc/amd/acp/acp-sof-mach.c b/sound/soc/amd/acp/acp-sof-mach.c index f19f064a752728aaddd7ad8baa0f32f945adc0a3..972600d271586dfcdc3daad1d91124ea3b1a0246 100644 --- a/sound/soc/amd/acp/acp-sof-mach.c +++ b/sound/soc/amd/acp/acp-sof-mach.c @@ -114,16 +114,14 @@ static int acp_sof_probe(struct platform_device *pdev) card->num_controls = ARRAY_SIZE(acp_controls); card->drvdata = (struct acp_card_drvdata *)pdev->id_entry->driver_data; - acp_sofdsp_dai_links_create(card); + ret = acp_sofdsp_dai_links_create(card); + if (ret) + return dev_err_probe(&pdev->dev, ret, "Failed to create DAI links\n"); ret = devm_snd_soc_register_card(&pdev->dev, card); - if (ret) { - dev_err(&pdev->dev, - "devm_snd_soc_register_card(%s) failed: %d\n", - card->name, ret); - return ret; - } - + if (ret) + return dev_err_probe(&pdev->dev, ret, + "Failed to register card(%s)\n", card->name); return 0; } diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 808d0028262339f0a950dc9c89092ae53feea6a1..0568e64d1015063f6e462f61abeecdd42caf0a48 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -199,6 +199,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "21HY"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "21J0"), + } + }, { .driver_data = &acp6x_card, .matches = { @@ -227,6 +234,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "82QF"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "82UU"), + } + }, { .driver_data = &acp6x_card, .matches = { @@ -241,6 +255,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "82YM"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "83AS"), + } + }, { .driver_data = &acp6x_card, .matches = { @@ -297,6 +318,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Redmi Book Pro 15 2022"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."), + DMI_MATCH(DMI_PRODUCT_NAME, "Bravo 15 C7VF"), + } + }, { .driver_data = &acp6x_card, .matches = { diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index fd3dca08460ba6536571741de1ad2205f502a053..aac9140749968e1379ebde2c7cfbe1b0cb3ded19 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -3288,6 +3288,7 @@ static void rt5645_jack_detect_work(struct work_struct *work) report, SND_JACK_HEADPHONE); snd_soc_jack_report(rt5645->mic_jack, report, SND_JACK_MICROPHONE); + mutex_unlock(&rt5645->jd_mutex); return; case 4: val = snd_soc_component_read(rt5645->component, RT5645_A_JD_CTRL1) & 0x0020; @@ -3801,6 +3802,16 @@ static const struct dmi_system_id dmi_platform_data[] = { DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), DMI_EXACT_MATCH(DMI_BOARD_NAME, "Cherry Trail CR"), DMI_EXACT_MATCH(DMI_BOARD_VERSION, "Default string"), + /* + * Above strings are too generic, LattePanda BIOS versions for + * all 4 hw revisions are: + * DF-BI-7-S70CR100-* + * DF-BI-7-S70CR110-* + * DF-BI-7-S70CR200-* + * LP-BS-7-S70CR700-* + * Do a partial match for S70CR to avoid false positive matches. + */ + DMI_MATCH(DMI_BIOS_VERSION, "S70CR"), }, .driver_data = (void *)&lattepanda_board_platform_data, }, diff --git a/sound/soc/codecs/rt5682-sdw.c b/sound/soc/codecs/rt5682-sdw.c index 868a61c8b0608d41fbdddf790aa96959b594051d..7685011a093549400d95c2d250fc35a6ef786cfb 100644 --- a/sound/soc/codecs/rt5682-sdw.c +++ b/sound/soc/codecs/rt5682-sdw.c @@ -787,12 +787,12 @@ static int __maybe_unused rt5682_dev_resume(struct device *dev) return 0; if (!slave->unattach_request) { + mutex_lock(&rt5682->disable_irq_lock); if (rt5682->disable_irq == true) { - mutex_lock(&rt5682->disable_irq_lock); sdw_write_no_pm(slave, SDW_SCP_INTMASK1, SDW_SCP_INT1_IMPL_DEF); rt5682->disable_irq = false; - mutex_unlock(&rt5682->disable_irq_lock); } + mutex_unlock(&rt5682->disable_irq_lock); goto regmap_sync; } diff --git a/sound/soc/codecs/rt711-sdca-sdw.c b/sound/soc/codecs/rt711-sdca-sdw.c index 487d3010ddc19eb98a0c3808f09a64ac94e0f650..931dbc68548ee6c1186a5cf05e46ef49f95834e3 100644 --- a/sound/soc/codecs/rt711-sdca-sdw.c +++ b/sound/soc/codecs/rt711-sdca-sdw.c @@ -443,13 +443,13 @@ static int __maybe_unused rt711_sdca_dev_resume(struct device *dev) return 0; if (!slave->unattach_request) { + mutex_lock(&rt711->disable_irq_lock); if (rt711->disable_irq == true) { - mutex_lock(&rt711->disable_irq_lock); sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK1, SDW_SCP_SDCA_INTMASK_SDCA_0); sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK2, SDW_SCP_SDCA_INTMASK_SDCA_8); rt711->disable_irq = false; - mutex_unlock(&rt711->disable_irq_lock); } + mutex_unlock(&rt711->disable_irq_lock); goto regmap_sync; } diff --git a/sound/soc/codecs/rt711-sdw.c b/sound/soc/codecs/rt711-sdw.c index 9545b8a7eb192673cd8df3214283cf4e57b431e7..af7a0ab5669f491eb64c49671999c95f5485acc1 100644 --- a/sound/soc/codecs/rt711-sdw.c +++ b/sound/soc/codecs/rt711-sdw.c @@ -542,12 +542,12 @@ static int __maybe_unused rt711_dev_resume(struct device *dev) return 0; if (!slave->unattach_request) { + mutex_lock(&rt711->disable_irq_lock); if (rt711->disable_irq == true) { - mutex_lock(&rt711->disable_irq_lock); sdw_write_no_pm(slave, SDW_SCP_INTMASK1, SDW_SCP_INT1_IMPL_DEF); rt711->disable_irq = false; - mutex_unlock(&rt711->disable_irq_lock); } + mutex_unlock(&rt711->disable_irq_lock); goto regmap_sync; } diff --git a/sound/soc/codecs/wcd938x.c b/sound/soc/codecs/wcd938x.c index a2abd1a111612bb54174082d049df46f0120f03d..555b74e7172d89e1492b09506094ebce7182e718 100644 --- a/sound/soc/codecs/wcd938x.c +++ b/sound/soc/codecs/wcd938x.c @@ -210,7 +210,7 @@ struct wcd938x_priv { }; static const SNDRV_CTL_TLVD_DECLARE_DB_MINMAX(ear_pa_gain, 600, -1800); -static const DECLARE_TLV_DB_SCALE(line_gain, -3000, 150, -3000); +static const DECLARE_TLV_DB_SCALE(line_gain, -3000, 150, 0); static const SNDRV_CTL_TLVD_DECLARE_DB_MINMAX(analog_gain, 0, 3000); struct wcd938x_mbhc_zdet_param { @@ -3588,7 +3588,7 @@ static int wcd938x_probe(struct platform_device *pdev) ret = wcd938x_populate_dt_data(wcd938x, dev); if (ret) { dev_err(dev, "%s: Fail to obtain platform data\n", __func__); - return -EINVAL; + return ret; } ret = wcd938x_add_slave_components(wcd938x, dev, &match); diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c index b901e4c65e8a508c370f8ef5ced11a9c6639275e..d215e58c4a7b3ca9622797213d43cd1d7d056a26 100644 --- a/sound/soc/codecs/wm8962.c +++ b/sound/soc/codecs/wm8962.c @@ -2229,6 +2229,9 @@ SND_SOC_DAPM_PGA_E("HPOUT", SND_SOC_NOPM, 0, 0, NULL, 0, hp_event, SND_SOC_DAPM_OUTPUT("HPOUTL"), SND_SOC_DAPM_OUTPUT("HPOUTR"), + +SND_SOC_DAPM_PGA("SPKOUTL Output", WM8962_CLASS_D_CONTROL_1, 6, 0, NULL, 0), +SND_SOC_DAPM_PGA("SPKOUTR Output", WM8962_CLASS_D_CONTROL_1, 7, 0, NULL, 0), }; static const struct snd_soc_dapm_widget wm8962_dapm_spk_mono_widgets[] = { @@ -2236,7 +2239,6 @@ SND_SOC_DAPM_MIXER("Speaker Mixer", WM8962_MIXER_ENABLES, 1, 0, spkmixl, ARRAY_SIZE(spkmixl)), SND_SOC_DAPM_MUX_E("Speaker PGA", WM8962_PWR_MGMT_2, 4, 0, &spkoutl_mux, out_pga_event, SND_SOC_DAPM_POST_PMU), -SND_SOC_DAPM_PGA("Speaker Output", WM8962_CLASS_D_CONTROL_1, 7, 0, NULL, 0), SND_SOC_DAPM_OUTPUT("SPKOUT"), }; @@ -2251,9 +2253,6 @@ SND_SOC_DAPM_MUX_E("SPKOUTL PGA", WM8962_PWR_MGMT_2, 4, 0, &spkoutl_mux, SND_SOC_DAPM_MUX_E("SPKOUTR PGA", WM8962_PWR_MGMT_2, 3, 0, &spkoutr_mux, out_pga_event, SND_SOC_DAPM_POST_PMU), -SND_SOC_DAPM_PGA("SPKOUTR Output", WM8962_CLASS_D_CONTROL_1, 7, 0, NULL, 0), -SND_SOC_DAPM_PGA("SPKOUTL Output", WM8962_CLASS_D_CONTROL_1, 6, 0, NULL, 0), - SND_SOC_DAPM_OUTPUT("SPKOUTL"), SND_SOC_DAPM_OUTPUT("SPKOUTR"), }; @@ -2366,12 +2365,18 @@ static const struct snd_soc_dapm_route wm8962_spk_mono_intercon[] = { { "Speaker PGA", "Mixer", "Speaker Mixer" }, { "Speaker PGA", "DAC", "DACL" }, - { "Speaker Output", NULL, "Speaker PGA" }, - { "Speaker Output", NULL, "SYSCLK" }, - { "Speaker Output", NULL, "TOCLK" }, - { "Speaker Output", NULL, "TEMP_SPK" }, + { "SPKOUTL Output", NULL, "Speaker PGA" }, + { "SPKOUTL Output", NULL, "SYSCLK" }, + { "SPKOUTL Output", NULL, "TOCLK" }, + { "SPKOUTL Output", NULL, "TEMP_SPK" }, - { "SPKOUT", NULL, "Speaker Output" }, + { "SPKOUTR Output", NULL, "Speaker PGA" }, + { "SPKOUTR Output", NULL, "SYSCLK" }, + { "SPKOUTR Output", NULL, "TOCLK" }, + { "SPKOUTR Output", NULL, "TEMP_SPK" }, + + { "SPKOUT", NULL, "SPKOUTL Output" }, + { "SPKOUT", NULL, "SPKOUTR Output" }, }; static const struct snd_soc_dapm_route wm8962_spk_stereo_intercon[] = { @@ -2914,8 +2919,12 @@ static int wm8962_set_fll(struct snd_soc_component *component, int fll_id, int s switch (fll_id) { case WM8962_FLL_MCLK: case WM8962_FLL_BCLK: + fll1 |= (fll_id - 1) << WM8962_FLL_REFCLK_SRC_SHIFT; + break; case WM8962_FLL_OSC: fll1 |= (fll_id - 1) << WM8962_FLL_REFCLK_SRC_SHIFT; + snd_soc_component_update_bits(component, WM8962_PLL2, + WM8962_OSC_ENA, WM8962_OSC_ENA); break; case WM8962_FLL_INT: snd_soc_component_update_bits(component, WM8962_FLL_CONTROL_1, @@ -2924,7 +2933,7 @@ static int wm8962_set_fll(struct snd_soc_component *component, int fll_id, int s WM8962_FLL_FRC_NCO, WM8962_FLL_FRC_NCO); break; default: - dev_err(component->dev, "Unknown FLL source %d\n", ret); + dev_err(component->dev, "Unknown FLL source %d\n", source); return -EINVAL; } diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 2cfca78f0401f51c5ee46f5253aeb896a34376b3..47a4c363227ccd9287103c63822710b45d4cf029 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -740,19 +740,25 @@ static int wm_adsp_request_firmware_file(struct wm_adsp *dsp, const char *filetype) { struct cs_dsp *cs_dsp = &dsp->cs_dsp; + const char *fwf; char *s, c; int ret = 0; + if (dsp->fwf_name) + fwf = dsp->fwf_name; + else + fwf = dsp->cs_dsp.name; + if (system_name && asoc_component_prefix) *filename = kasprintf(GFP_KERNEL, "%s%s-%s-%s-%s-%s.%s", dir, dsp->part, - dsp->fwf_name, wm_adsp_fw[dsp->fw].file, system_name, + fwf, wm_adsp_fw[dsp->fw].file, system_name, asoc_component_prefix, filetype); else if (system_name) *filename = kasprintf(GFP_KERNEL, "%s%s-%s-%s-%s.%s", dir, dsp->part, - dsp->fwf_name, wm_adsp_fw[dsp->fw].file, system_name, + fwf, wm_adsp_fw[dsp->fw].file, system_name, filetype); else - *filename = kasprintf(GFP_KERNEL, "%s%s-%s-%s.%s", dir, dsp->part, dsp->fwf_name, + *filename = kasprintf(GFP_KERNEL, "%s%s-%s-%s.%s", dir, dsp->part, fwf, wm_adsp_fw[dsp->fw].file, filetype); if (*filename == NULL) @@ -842,29 +848,18 @@ static int wm_adsp_request_firmware_files(struct wm_adsp *dsp, } adsp_err(dsp, "Failed to request firmware <%s>%s-%s-%s<-%s<%s>>.wmfw\n", - cirrus_dir, dsp->part, dsp->fwf_name, wm_adsp_fw[dsp->fw].file, - system_name, asoc_component_prefix); + cirrus_dir, dsp->part, + dsp->fwf_name ? dsp->fwf_name : dsp->cs_dsp.name, + wm_adsp_fw[dsp->fw].file, system_name, asoc_component_prefix); return -ENOENT; } static int wm_adsp_common_init(struct wm_adsp *dsp) { - char *p; - INIT_LIST_HEAD(&dsp->compr_list); INIT_LIST_HEAD(&dsp->buffer_list); - if (!dsp->fwf_name) { - p = devm_kstrdup(dsp->cs_dsp.dev, dsp->cs_dsp.name, GFP_KERNEL); - if (!p) - return -ENOMEM; - - dsp->fwf_name = p; - for (; *p != 0; ++p) - *p = tolower(*p); - } - return 0; } diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 797d0a48d6066221a2f987aa056e949b9d9e6532..094445036c20ff9583b2b0116dd5676c36e88814 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -685,6 +685,18 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_SSP0_AIF1 | BYT_RT5640_MCLK_EN), }, + { /* Chuwi Vi8 dual-boot (CWI506) */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Insyde"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "i86"), + /* The above are too generic, also match BIOS info */ + DMI_MATCH(DMI_BIOS_VERSION, "CHUWI2.D86JHBNR02"), + }, + .driver_data = (void *)(BYTCR_INPUT_DEFAULTS | + BYT_RT5640_MONO_SPEAKER | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), + }, { /* Chuwi Vi10 (CWI505) */ .matches = { diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 985012f2003e2286433ab40b471b720314eaf0fe..d1e6e4208c376a266f2963f191137a72b53f1bb4 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -224,6 +224,17 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { SOF_SDW_PCH_DMIC | RT711_JD2_100K), }, + { + /* NUC15 LAPRC710 skews */ + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Intel Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "LAPRC710"), + }, + .driver_data = (void *)(SOF_SDW_TGL_HDMI | + SOF_SDW_PCH_DMIC | + RT711_JD2_100K), + }, /* TigerLake-SDCA devices */ { .callback = sof_sdw_quirk_cb, diff --git a/sound/soc/meson/Kconfig b/sound/soc/meson/Kconfig index b93ea33739f29ddd9b987d7896e9fa2f37c58ccf..6458d5dc4902f665211bb9e4ae7d274e4bff2fdc 100644 --- a/sound/soc/meson/Kconfig +++ b/sound/soc/meson/Kconfig @@ -99,6 +99,7 @@ config SND_MESON_AXG_PDM config SND_MESON_CARD_UTILS tristate + select SND_DYNAMIC_MINORS config SND_MESON_CODEC_GLUE tristate diff --git a/sound/soc/meson/aiu.c b/sound/soc/meson/aiu.c index 88e611e64d14f54fcd10caa5c5c0e49f43dec680..077b9c0b6c4caeed710422f202daf7cc410923a2 100644 --- a/sound/soc/meson/aiu.c +++ b/sound/soc/meson/aiu.c @@ -218,11 +218,12 @@ static const char * const aiu_spdif_ids[] = { static int aiu_clk_get(struct device *dev) { struct aiu *aiu = dev_get_drvdata(dev); + struct clk *pclk; int ret; - aiu->pclk = devm_clk_get(dev, "pclk"); - if (IS_ERR(aiu->pclk)) - return dev_err_probe(dev, PTR_ERR(aiu->pclk), "Can't get the aiu pclk\n"); + pclk = devm_clk_get_enabled(dev, "pclk"); + if (IS_ERR(pclk)) + return dev_err_probe(dev, PTR_ERR(pclk), "Can't get the aiu pclk\n"); aiu->spdif_mclk = devm_clk_get(dev, "spdif_mclk"); if (IS_ERR(aiu->spdif_mclk)) @@ -239,18 +240,6 @@ static int aiu_clk_get(struct device *dev) if (ret) return dev_err_probe(dev, ret, "Can't get the spdif clocks\n"); - ret = clk_prepare_enable(aiu->pclk); - if (ret) { - dev_err(dev, "peripheral clock enable failed\n"); - return ret; - } - - ret = devm_add_action_or_reset(dev, - (void(*)(void *))clk_disable_unprepare, - aiu->pclk); - if (ret) - dev_err(dev, "failed to add reset action on pclk"); - return ret; } diff --git a/sound/soc/meson/aiu.h b/sound/soc/meson/aiu.h index 393b6c2307e49ff212c6e9676b3072a6f82b587b..0f94c8bf608181112d78402532b832eb50c2d409 100644 --- a/sound/soc/meson/aiu.h +++ b/sound/soc/meson/aiu.h @@ -33,7 +33,6 @@ struct aiu_platform_data { }; struct aiu { - struct clk *pclk; struct clk *spdif_mclk; struct aiu_interface i2s; struct aiu_interface spdif; diff --git a/sound/soc/meson/axg-card.c b/sound/soc/meson/axg-card.c index 2b77010c2c5ce8398c330e8c8e13cc9248daa828..cbbaa55d92a662c6f43ba90b7d0f1a508899e0eb 100644 --- a/sound/soc/meson/axg-card.c +++ b/sound/soc/meson/axg-card.c @@ -320,6 +320,7 @@ static int axg_card_add_link(struct snd_soc_card *card, struct device_node *np, dai_link->cpus = cpu; dai_link->num_cpus = 1; + dai_link->nonatomic = true; ret = meson_card_parse_dai(card, np, &dai_link->cpus->of_node, &dai_link->cpus->dai_name); diff --git a/sound/soc/meson/axg-fifo.c b/sound/soc/meson/axg-fifo.c index bccfb770b339118a9997d37164721753b75ae2b8..94b169a5493b5f9a753fd7de14be602e907be85c 100644 --- a/sound/soc/meson/axg-fifo.c +++ b/sound/soc/meson/axg-fifo.c @@ -3,6 +3,7 @@ // Copyright (c) 2018 BayLibre, SAS. // Author: Jerome Brunet +#include #include #include #include @@ -145,8 +146,8 @@ int axg_fifo_pcm_hw_params(struct snd_soc_component *component, /* Enable irq if necessary */ irq_en = runtime->no_period_wakeup ? 0 : FIFO_INT_COUNT_REPEAT; regmap_update_bits(fifo->map, FIFO_CTRL0, - CTRL0_INT_EN(FIFO_INT_COUNT_REPEAT), - CTRL0_INT_EN(irq_en)); + CTRL0_INT_EN, + FIELD_PREP(CTRL0_INT_EN, irq_en)); return 0; } @@ -176,9 +177,9 @@ int axg_fifo_pcm_hw_free(struct snd_soc_component *component, { struct axg_fifo *fifo = axg_fifo_data(ss); - /* Disable the block count irq */ + /* Disable irqs */ regmap_update_bits(fifo->map, FIFO_CTRL0, - CTRL0_INT_EN(FIFO_INT_COUNT_REPEAT), 0); + CTRL0_INT_EN, 0); return 0; } @@ -187,13 +188,13 @@ EXPORT_SYMBOL_GPL(axg_fifo_pcm_hw_free); static void axg_fifo_ack_irq(struct axg_fifo *fifo, u8 mask) { regmap_update_bits(fifo->map, FIFO_CTRL1, - CTRL1_INT_CLR(FIFO_INT_MASK), - CTRL1_INT_CLR(mask)); + CTRL1_INT_CLR, + FIELD_PREP(CTRL1_INT_CLR, mask)); /* Clear must also be cleared */ regmap_update_bits(fifo->map, FIFO_CTRL1, - CTRL1_INT_CLR(FIFO_INT_MASK), - 0); + CTRL1_INT_CLR, + FIELD_PREP(CTRL1_INT_CLR, 0)); } static irqreturn_t axg_fifo_pcm_irq_block(int irq, void *dev_id) @@ -203,18 +204,26 @@ static irqreturn_t axg_fifo_pcm_irq_block(int irq, void *dev_id) unsigned int status; regmap_read(fifo->map, FIFO_STATUS1, &status); + status = FIELD_GET(STATUS1_INT_STS, status); + axg_fifo_ack_irq(fifo, status); - status = STATUS1_INT_STS(status) & FIFO_INT_MASK; + /* Use the thread to call period elapsed on nonatomic links */ if (status & FIFO_INT_COUNT_REPEAT) - snd_pcm_period_elapsed(ss); - else - dev_dbg(axg_fifo_dev(ss), "unexpected irq - STS 0x%02x\n", - status); + return IRQ_WAKE_THREAD; - /* Ack irqs */ - axg_fifo_ack_irq(fifo, status); + dev_dbg(axg_fifo_dev(ss), "unexpected irq - STS 0x%02x\n", + status); + + return IRQ_NONE; +} + +static irqreturn_t axg_fifo_pcm_irq_block_thread(int irq, void *dev_id) +{ + struct snd_pcm_substream *ss = dev_id; + + snd_pcm_period_elapsed(ss); - return IRQ_RETVAL(status); + return IRQ_HANDLED; } int axg_fifo_pcm_open(struct snd_soc_component *component, @@ -242,8 +251,9 @@ int axg_fifo_pcm_open(struct snd_soc_component *component, if (ret) return ret; - ret = request_irq(fifo->irq, axg_fifo_pcm_irq_block, 0, - dev_name(dev), ss); + ret = request_threaded_irq(fifo->irq, axg_fifo_pcm_irq_block, + axg_fifo_pcm_irq_block_thread, + IRQF_ONESHOT, dev_name(dev), ss); if (ret) return ret; @@ -254,15 +264,15 @@ int axg_fifo_pcm_open(struct snd_soc_component *component, /* Setup status2 so it reports the memory pointer */ regmap_update_bits(fifo->map, FIFO_CTRL1, - CTRL1_STATUS2_SEL_MASK, - CTRL1_STATUS2_SEL(STATUS2_SEL_DDR_READ)); + CTRL1_STATUS2_SEL, + FIELD_PREP(CTRL1_STATUS2_SEL, STATUS2_SEL_DDR_READ)); /* Make sure the dma is initially disabled */ __dma_enable(fifo, false); /* Disable irqs until params are ready */ regmap_update_bits(fifo->map, FIFO_CTRL0, - CTRL0_INT_EN(FIFO_INT_MASK), 0); + CTRL0_INT_EN, 0); /* Clear any pending interrupt */ axg_fifo_ack_irq(fifo, FIFO_INT_MASK); diff --git a/sound/soc/meson/axg-fifo.h b/sound/soc/meson/axg-fifo.h index b63acd723c870c58d4406596057002fc925d26a2..5b7d32c37991be99a45205f7aec1044c3b8acd79 100644 --- a/sound/soc/meson/axg-fifo.h +++ b/sound/soc/meson/axg-fifo.h @@ -42,21 +42,19 @@ struct snd_soc_pcm_runtime; #define FIFO_CTRL0 0x00 #define CTRL0_DMA_EN BIT(31) -#define CTRL0_INT_EN(x) ((x) << 16) +#define CTRL0_INT_EN GENMASK(23, 16) #define CTRL0_SEL_MASK GENMASK(2, 0) #define CTRL0_SEL_SHIFT 0 #define FIFO_CTRL1 0x04 -#define CTRL1_INT_CLR(x) ((x) << 0) -#define CTRL1_STATUS2_SEL_MASK GENMASK(11, 8) -#define CTRL1_STATUS2_SEL(x) ((x) << 8) +#define CTRL1_INT_CLR GENMASK(7, 0) +#define CTRL1_STATUS2_SEL GENMASK(11, 8) #define STATUS2_SEL_DDR_READ 0 -#define CTRL1_FRDDR_DEPTH_MASK GENMASK(31, 24) -#define CTRL1_FRDDR_DEPTH(x) ((x) << 24) +#define CTRL1_FRDDR_DEPTH GENMASK(31, 24) #define FIFO_START_ADDR 0x08 #define FIFO_FINISH_ADDR 0x0c #define FIFO_INT_ADDR 0x10 #define FIFO_STATUS1 0x14 -#define STATUS1_INT_STS(x) ((x) << 0) +#define STATUS1_INT_STS GENMASK(7, 0) #define FIFO_STATUS2 0x18 #define FIFO_INIT_ADDR 0x24 #define FIFO_CTRL2 0x28 diff --git a/sound/soc/meson/axg-frddr.c b/sound/soc/meson/axg-frddr.c index 61f9d417fd608a5a93b25e6b6879aab8a70bc446..f0a9e181ee72ad878793cba0264b1c57c9e4bf21 100644 --- a/sound/soc/meson/axg-frddr.c +++ b/sound/soc/meson/axg-frddr.c @@ -7,6 +7,7 @@ * This driver implements the frontend playback DAI of AXG and G12A based SoCs */ +#include #include #include #include @@ -59,8 +60,8 @@ static int axg_frddr_dai_hw_params(struct snd_pcm_substream *substream, /* Trim the FIFO depth if the period is small to improve latency */ depth = min(period, fifo->depth); val = (depth / AXG_FIFO_BURST) - 1; - regmap_update_bits(fifo->map, FIFO_CTRL1, CTRL1_FRDDR_DEPTH_MASK, - CTRL1_FRDDR_DEPTH(val)); + regmap_update_bits(fifo->map, FIFO_CTRL1, CTRL1_FRDDR_DEPTH, + FIELD_PREP(CTRL1_FRDDR_DEPTH, val)); return 0; } diff --git a/sound/soc/meson/axg-tdm-interface.c b/sound/soc/meson/axg-tdm-interface.c index c040c83637e02adae6fce5cb673f09610a5a1bc3..272c3d2d68cb7ffca53f6fc32bfe7022fb44320d 100644 --- a/sound/soc/meson/axg-tdm-interface.c +++ b/sound/soc/meson/axg-tdm-interface.c @@ -12,6 +12,9 @@ #include "axg-tdm.h" +/* Maximum bit clock frequency according the datasheets */ +#define MAX_SCLK 100000000 /* Hz */ + enum { TDM_IFACE_PAD, TDM_IFACE_LOOPBACK, @@ -155,19 +158,27 @@ static int axg_tdm_iface_startup(struct snd_pcm_substream *substream, return -EINVAL; } - /* Apply component wide rate symmetry */ if (snd_soc_component_active(dai->component)) { + /* Apply component wide rate symmetry */ ret = snd_pcm_hw_constraint_single(substream->runtime, SNDRV_PCM_HW_PARAM_RATE, iface->rate); - if (ret < 0) { - dev_err(dai->dev, - "can't set iface rate constraint\n"); - return ret; - } + + } else { + /* Limit rate according to the slot number and width */ + unsigned int max_rate = + MAX_SCLK / (iface->slots * iface->slot_width); + ret = snd_pcm_hw_constraint_minmax(substream->runtime, + SNDRV_PCM_HW_PARAM_RATE, + 0, max_rate); } - return 0; + if (ret < 0) + dev_err(dai->dev, "can't set iface rate constraint\n"); + else + ret = 0; + + return ret; } static int axg_tdm_iface_set_stream(struct snd_pcm_substream *substream, @@ -266,8 +277,8 @@ static int axg_tdm_iface_set_sclk(struct snd_soc_dai *dai, srate = iface->slots * iface->slot_width * params_rate(params); if (!iface->mclk_rate) { - /* If no specific mclk is requested, default to bit clock * 4 */ - clk_set_rate(iface->mclk, 4 * srate); + /* If no specific mclk is requested, default to bit clock * 2 */ + clk_set_rate(iface->mclk, 2 * srate); } else { /* Check if we can actually get the bit clock from mclk */ if (iface->mclk_rate % srate) { @@ -340,26 +351,31 @@ static int axg_tdm_iface_hw_params(struct snd_pcm_substream *substream, return 0; } -static int axg_tdm_iface_hw_free(struct snd_pcm_substream *substream, +static int axg_tdm_iface_trigger(struct snd_pcm_substream *substream, + int cmd, struct snd_soc_dai *dai) { - struct axg_tdm_stream *ts = snd_soc_dai_get_dma_data(dai, substream); + struct axg_tdm_stream *ts = + snd_soc_dai_get_dma_data(dai, substream); - /* Stop all attached formatters */ - axg_tdm_stream_stop(ts); + switch (cmd) { + case SNDRV_PCM_TRIGGER_START: + case SNDRV_PCM_TRIGGER_RESUME: + case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: + axg_tdm_stream_start(ts); + break; + case SNDRV_PCM_TRIGGER_SUSPEND: + case SNDRV_PCM_TRIGGER_PAUSE_PUSH: + case SNDRV_PCM_TRIGGER_STOP: + axg_tdm_stream_stop(ts); + break; + default: + return -EINVAL; + } return 0; } -static int axg_tdm_iface_prepare(struct snd_pcm_substream *substream, - struct snd_soc_dai *dai) -{ - struct axg_tdm_stream *ts = snd_soc_dai_get_dma_data(dai, substream); - - /* Force all attached formatters to update */ - return axg_tdm_stream_reset(ts); -} - static int axg_tdm_iface_remove_dai(struct snd_soc_dai *dai) { if (dai->capture_dma_data) @@ -397,8 +413,7 @@ static const struct snd_soc_dai_ops axg_tdm_iface_ops = { .set_fmt = axg_tdm_iface_set_fmt, .startup = axg_tdm_iface_startup, .hw_params = axg_tdm_iface_hw_params, - .prepare = axg_tdm_iface_prepare, - .hw_free = axg_tdm_iface_hw_free, + .trigger = axg_tdm_iface_trigger, }; /* TDM Backend DAIs */ diff --git a/sound/soc/meson/axg-toddr.c b/sound/soc/meson/axg-toddr.c index e9208e74e9659a4ae9b90e9a8e897d9e000d8704..f875304463e2f6c5038ddfa013fdebaa90e91c59 100644 --- a/sound/soc/meson/axg-toddr.c +++ b/sound/soc/meson/axg-toddr.c @@ -5,6 +5,7 @@ /* This driver implements the frontend capture DAI of AXG based SoCs */ +#include #include #include #include @@ -19,12 +20,9 @@ #define CTRL0_TODDR_EXT_SIGNED BIT(29) #define CTRL0_TODDR_PP_MODE BIT(28) #define CTRL0_TODDR_SYNC_CH BIT(27) -#define CTRL0_TODDR_TYPE_MASK GENMASK(15, 13) -#define CTRL0_TODDR_TYPE(x) ((x) << 13) -#define CTRL0_TODDR_MSB_POS_MASK GENMASK(12, 8) -#define CTRL0_TODDR_MSB_POS(x) ((x) << 8) -#define CTRL0_TODDR_LSB_POS_MASK GENMASK(7, 3) -#define CTRL0_TODDR_LSB_POS(x) ((x) << 3) +#define CTRL0_TODDR_TYPE GENMASK(15, 13) +#define CTRL0_TODDR_MSB_POS GENMASK(12, 8) +#define CTRL0_TODDR_LSB_POS GENMASK(7, 3) #define CTRL1_TODDR_FORCE_FINISH BIT(25) #define CTRL1_SEL_SHIFT 28 @@ -76,12 +74,12 @@ static int axg_toddr_dai_hw_params(struct snd_pcm_substream *substream, width = params_width(params); regmap_update_bits(fifo->map, FIFO_CTRL0, - CTRL0_TODDR_TYPE_MASK | - CTRL0_TODDR_MSB_POS_MASK | - CTRL0_TODDR_LSB_POS_MASK, - CTRL0_TODDR_TYPE(type) | - CTRL0_TODDR_MSB_POS(TODDR_MSB_POS) | - CTRL0_TODDR_LSB_POS(TODDR_MSB_POS - (width - 1))); + CTRL0_TODDR_TYPE | + CTRL0_TODDR_MSB_POS | + CTRL0_TODDR_LSB_POS, + FIELD_PREP(CTRL0_TODDR_TYPE, type) | + FIELD_PREP(CTRL0_TODDR_MSB_POS, TODDR_MSB_POS) | + FIELD_PREP(CTRL0_TODDR_LSB_POS, TODDR_MSB_POS - (width - 1))); return 0; } diff --git a/sound/soc/meson/t9015.c b/sound/soc/meson/t9015.c index 9c6b4dac689320d1f6a1ce5ce81e518fbffee44d..571f65788c592050abdca264f5656d4d1a9d99f6 100644 --- a/sound/soc/meson/t9015.c +++ b/sound/soc/meson/t9015.c @@ -48,7 +48,6 @@ #define POWER_CFG 0x10 struct t9015 { - struct clk *pclk; struct regulator *avdd; }; @@ -249,6 +248,7 @@ static int t9015_probe(struct platform_device *pdev) struct t9015 *priv; void __iomem *regs; struct regmap *regmap; + struct clk *pclk; int ret; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); @@ -256,26 +256,14 @@ static int t9015_probe(struct platform_device *pdev) return -ENOMEM; platform_set_drvdata(pdev, priv); - priv->pclk = devm_clk_get(dev, "pclk"); - if (IS_ERR(priv->pclk)) - return dev_err_probe(dev, PTR_ERR(priv->pclk), "failed to get core clock\n"); + pclk = devm_clk_get_enabled(dev, "pclk"); + if (IS_ERR(pclk)) + return dev_err_probe(dev, PTR_ERR(pclk), "failed to get core clock\n"); priv->avdd = devm_regulator_get(dev, "AVDD"); if (IS_ERR(priv->avdd)) return dev_err_probe(dev, PTR_ERR(priv->avdd), "failed to AVDD\n"); - ret = clk_prepare_enable(priv->pclk); - if (ret) { - dev_err(dev, "core clock enable failed\n"); - return ret; - } - - ret = devm_add_action_or_reset(dev, - (void(*)(void *))clk_disable_unprepare, - priv->pclk); - if (ret) - return ret; - ret = device_reset(dev); if (ret) { dev_err(dev, "reset failed\n"); diff --git a/sound/soc/rockchip/rockchip_i2s_tdm.c b/sound/soc/rockchip/rockchip_i2s_tdm.c index 2550bd2a5e78c547bb358fae4ca969f2f638143f..2e36a97077b99c86d5aeeac039b4e7d3fdbf7545 100644 --- a/sound/soc/rockchip/rockchip_i2s_tdm.c +++ b/sound/soc/rockchip/rockchip_i2s_tdm.c @@ -27,8 +27,6 @@ #define DEFAULT_MCLK_FS 256 #define CH_GRP_MAX 4 /* The max channel 8 / 2 */ #define MULTIPLEX_CH_MAX 10 -#define CLK_PPM_MIN -1000 -#define CLK_PPM_MAX 1000 #define TRCM_TXRX 0 #define TRCM_TX 1 @@ -55,20 +53,6 @@ struct rk_i2s_tdm_dev { struct clk *hclk; struct clk *mclk_tx; struct clk *mclk_rx; - /* The mclk_tx_src is parent of mclk_tx */ - struct clk *mclk_tx_src; - /* The mclk_rx_src is parent of mclk_rx */ - struct clk *mclk_rx_src; - /* - * The mclk_root0 and mclk_root1 are root parent and supplies for - * the different FS. - * - * e.g: - * mclk_root0 is VPLL0, used for FS=48000Hz - * mclk_root1 is VPLL1, used for FS=44100Hz - */ - struct clk *mclk_root0; - struct clk *mclk_root1; struct regmap *regmap; struct regmap *grf; struct snd_dmaengine_dai_dma_data capture_dma_data; @@ -78,19 +62,11 @@ struct rk_i2s_tdm_dev { struct rk_i2s_soc_data *soc_data; bool is_master_mode; bool io_multiplex; - bool mclk_calibrate; bool tdm_mode; - unsigned int mclk_rx_freq; - unsigned int mclk_tx_freq; - unsigned int mclk_root0_freq; - unsigned int mclk_root1_freq; - unsigned int mclk_root0_initial_freq; - unsigned int mclk_root1_initial_freq; unsigned int frame_width; unsigned int clk_trcm; unsigned int i2s_sdis[CH_GRP_MAX]; unsigned int i2s_sdos[CH_GRP_MAX]; - int clk_ppm; int refcount; spinlock_t lock; /* xfer lock */ bool has_playback; @@ -116,12 +92,6 @@ static void i2s_tdm_disable_unprepare_mclk(struct rk_i2s_tdm_dev *i2s_tdm) { clk_disable_unprepare(i2s_tdm->mclk_tx); clk_disable_unprepare(i2s_tdm->mclk_rx); - if (i2s_tdm->mclk_calibrate) { - clk_disable_unprepare(i2s_tdm->mclk_tx_src); - clk_disable_unprepare(i2s_tdm->mclk_rx_src); - clk_disable_unprepare(i2s_tdm->mclk_root0); - clk_disable_unprepare(i2s_tdm->mclk_root1); - } } /** @@ -144,29 +114,9 @@ static int i2s_tdm_prepare_enable_mclk(struct rk_i2s_tdm_dev *i2s_tdm) ret = clk_prepare_enable(i2s_tdm->mclk_rx); if (ret) goto err_mclk_rx; - if (i2s_tdm->mclk_calibrate) { - ret = clk_prepare_enable(i2s_tdm->mclk_tx_src); - if (ret) - goto err_mclk_rx; - ret = clk_prepare_enable(i2s_tdm->mclk_rx_src); - if (ret) - goto err_mclk_rx_src; - ret = clk_prepare_enable(i2s_tdm->mclk_root0); - if (ret) - goto err_mclk_root0; - ret = clk_prepare_enable(i2s_tdm->mclk_root1); - if (ret) - goto err_mclk_root1; - } return 0; -err_mclk_root1: - clk_disable_unprepare(i2s_tdm->mclk_root0); -err_mclk_root0: - clk_disable_unprepare(i2s_tdm->mclk_rx_src); -err_mclk_rx_src: - clk_disable_unprepare(i2s_tdm->mclk_tx_src); err_mclk_rx: clk_disable_unprepare(i2s_tdm->mclk_tx); err_mclk_tx: @@ -566,159 +516,6 @@ static void rockchip_i2s_tdm_xfer_resume(struct snd_pcm_substream *substream, I2S_XFER_RXS_START); } -static int rockchip_i2s_tdm_clk_set_rate(struct rk_i2s_tdm_dev *i2s_tdm, - struct clk *clk, unsigned long rate, - int ppm) -{ - unsigned long rate_target; - int delta, ret; - - if (ppm == i2s_tdm->clk_ppm) - return 0; - - if (ppm < 0) - delta = -1; - else - delta = 1; - - delta *= (int)div64_u64((u64)rate * (u64)abs(ppm) + 500000, - 1000000); - - rate_target = rate + delta; - - if (!rate_target) - return -EINVAL; - - ret = clk_set_rate(clk, rate_target); - if (ret) - return ret; - - i2s_tdm->clk_ppm = ppm; - - return 0; -} - -static int rockchip_i2s_tdm_calibrate_mclk(struct rk_i2s_tdm_dev *i2s_tdm, - struct snd_pcm_substream *substream, - unsigned int lrck_freq) -{ - struct clk *mclk_root; - struct clk *mclk_parent; - unsigned int mclk_root_freq; - unsigned int mclk_root_initial_freq; - unsigned int mclk_parent_freq; - unsigned int div, delta; - u64 ppm; - int ret; - - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - mclk_parent = i2s_tdm->mclk_tx_src; - else - mclk_parent = i2s_tdm->mclk_rx_src; - - switch (lrck_freq) { - case 8000: - case 16000: - case 24000: - case 32000: - case 48000: - case 64000: - case 96000: - case 192000: - mclk_root = i2s_tdm->mclk_root0; - mclk_root_freq = i2s_tdm->mclk_root0_freq; - mclk_root_initial_freq = i2s_tdm->mclk_root0_initial_freq; - mclk_parent_freq = DEFAULT_MCLK_FS * 192000; - break; - case 11025: - case 22050: - case 44100: - case 88200: - case 176400: - mclk_root = i2s_tdm->mclk_root1; - mclk_root_freq = i2s_tdm->mclk_root1_freq; - mclk_root_initial_freq = i2s_tdm->mclk_root1_initial_freq; - mclk_parent_freq = DEFAULT_MCLK_FS * 176400; - break; - default: - dev_err(i2s_tdm->dev, "Invalid LRCK frequency: %u Hz\n", - lrck_freq); - return -EINVAL; - } - - ret = clk_set_parent(mclk_parent, mclk_root); - if (ret) - return ret; - - ret = rockchip_i2s_tdm_clk_set_rate(i2s_tdm, mclk_root, - mclk_root_freq, 0); - if (ret) - return ret; - - delta = abs(mclk_root_freq % mclk_parent_freq - mclk_parent_freq); - ppm = div64_u64((uint64_t)delta * 1000000, (uint64_t)mclk_root_freq); - - if (ppm) { - div = DIV_ROUND_CLOSEST(mclk_root_initial_freq, mclk_parent_freq); - if (!div) - return -EINVAL; - - mclk_root_freq = mclk_parent_freq * round_up(div, 2); - - ret = clk_set_rate(mclk_root, mclk_root_freq); - if (ret) - return ret; - - i2s_tdm->mclk_root0_freq = clk_get_rate(i2s_tdm->mclk_root0); - i2s_tdm->mclk_root1_freq = clk_get_rate(i2s_tdm->mclk_root1); - } - - return clk_set_rate(mclk_parent, mclk_parent_freq); -} - -static int rockchip_i2s_tdm_set_mclk(struct rk_i2s_tdm_dev *i2s_tdm, - struct snd_pcm_substream *substream, - struct clk **mclk) -{ - unsigned int mclk_freq; - int ret; - - if (i2s_tdm->clk_trcm) { - if (i2s_tdm->mclk_tx_freq != i2s_tdm->mclk_rx_freq) { - dev_err(i2s_tdm->dev, - "clk_trcm, tx: %d and rx: %d should be the same\n", - i2s_tdm->mclk_tx_freq, - i2s_tdm->mclk_rx_freq); - return -EINVAL; - } - - ret = clk_set_rate(i2s_tdm->mclk_tx, i2s_tdm->mclk_tx_freq); - if (ret) - return ret; - - ret = clk_set_rate(i2s_tdm->mclk_rx, i2s_tdm->mclk_rx_freq); - if (ret) - return ret; - - /* mclk_rx is also ok. */ - *mclk = i2s_tdm->mclk_tx; - } else { - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { - *mclk = i2s_tdm->mclk_tx; - mclk_freq = i2s_tdm->mclk_tx_freq; - } else { - *mclk = i2s_tdm->mclk_rx; - mclk_freq = i2s_tdm->mclk_rx_freq; - } - - ret = clk_set_rate(*mclk, mclk_freq); - if (ret) - return ret; - } - - return 0; -} - static int rockchip_i2s_ch_to_io(unsigned int ch, bool substream_capture) { if (substream_capture) { @@ -849,19 +646,17 @@ static int rockchip_i2s_tdm_hw_params(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct rk_i2s_tdm_dev *i2s_tdm = to_info(dai); - struct clk *mclk; - int ret = 0; unsigned int val = 0; unsigned int mclk_rate, bclk_rate, div_bclk = 4, div_lrck = 64; + int err; if (i2s_tdm->is_master_mode) { - if (i2s_tdm->mclk_calibrate) - rockchip_i2s_tdm_calibrate_mclk(i2s_tdm, substream, - params_rate(params)); + struct clk *mclk = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) ? + i2s_tdm->mclk_tx : i2s_tdm->mclk_rx; - ret = rockchip_i2s_tdm_set_mclk(i2s_tdm, substream, &mclk); - if (ret) - return ret; + err = clk_set_rate(mclk, DEFAULT_MCLK_FS * params_rate(params)); + if (err) + return err; mclk_rate = clk_get_rate(mclk); bclk_rate = i2s_tdm->frame_width * params_rate(params); @@ -969,96 +764,6 @@ static int rockchip_i2s_tdm_trigger(struct snd_pcm_substream *substream, return 0; } -static int rockchip_i2s_tdm_set_sysclk(struct snd_soc_dai *cpu_dai, int stream, - unsigned int freq, int dir) -{ - struct rk_i2s_tdm_dev *i2s_tdm = to_info(cpu_dai); - - /* Put set mclk rate into rockchip_i2s_tdm_set_mclk() */ - if (i2s_tdm->clk_trcm) { - i2s_tdm->mclk_tx_freq = freq; - i2s_tdm->mclk_rx_freq = freq; - } else { - if (stream == SNDRV_PCM_STREAM_PLAYBACK) - i2s_tdm->mclk_tx_freq = freq; - else - i2s_tdm->mclk_rx_freq = freq; - } - - dev_dbg(i2s_tdm->dev, "The target mclk_%s freq is: %d\n", - stream ? "rx" : "tx", freq); - - return 0; -} - -static int rockchip_i2s_tdm_clk_compensation_info(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_info *uinfo) -{ - uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; - uinfo->count = 1; - uinfo->value.integer.min = CLK_PPM_MIN; - uinfo->value.integer.max = CLK_PPM_MAX; - uinfo->value.integer.step = 1; - - return 0; -} - -static int rockchip_i2s_tdm_clk_compensation_get(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct snd_soc_dai *dai = snd_kcontrol_chip(kcontrol); - struct rk_i2s_tdm_dev *i2s_tdm = snd_soc_dai_get_drvdata(dai); - - ucontrol->value.integer.value[0] = i2s_tdm->clk_ppm; - - return 0; -} - -static int rockchip_i2s_tdm_clk_compensation_put(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct snd_soc_dai *dai = snd_kcontrol_chip(kcontrol); - struct rk_i2s_tdm_dev *i2s_tdm = snd_soc_dai_get_drvdata(dai); - int ret = 0, ppm = 0; - int changed = 0; - unsigned long old_rate; - - if (ucontrol->value.integer.value[0] < CLK_PPM_MIN || - ucontrol->value.integer.value[0] > CLK_PPM_MAX) - return -EINVAL; - - ppm = ucontrol->value.integer.value[0]; - - old_rate = clk_get_rate(i2s_tdm->mclk_root0); - ret = rockchip_i2s_tdm_clk_set_rate(i2s_tdm, i2s_tdm->mclk_root0, - i2s_tdm->mclk_root0_freq, ppm); - if (ret) - return ret; - if (old_rate != clk_get_rate(i2s_tdm->mclk_root0)) - changed = 1; - - if (clk_is_match(i2s_tdm->mclk_root0, i2s_tdm->mclk_root1)) - return changed; - - old_rate = clk_get_rate(i2s_tdm->mclk_root1); - ret = rockchip_i2s_tdm_clk_set_rate(i2s_tdm, i2s_tdm->mclk_root1, - i2s_tdm->mclk_root1_freq, ppm); - if (ret) - return ret; - if (old_rate != clk_get_rate(i2s_tdm->mclk_root1)) - changed = 1; - - return changed; -} - -static struct snd_kcontrol_new rockchip_i2s_tdm_compensation_control = { - .iface = SNDRV_CTL_ELEM_IFACE_PCM, - .name = "PCM Clock Compensation in PPM", - .info = rockchip_i2s_tdm_clk_compensation_info, - .get = rockchip_i2s_tdm_clk_compensation_get, - .put = rockchip_i2s_tdm_clk_compensation_put, -}; - static int rockchip_i2s_tdm_dai_probe(struct snd_soc_dai *dai) { struct rk_i2s_tdm_dev *i2s_tdm = snd_soc_dai_get_drvdata(dai); @@ -1068,9 +773,6 @@ static int rockchip_i2s_tdm_dai_probe(struct snd_soc_dai *dai) if (i2s_tdm->has_playback) dai->playback_dma_data = &i2s_tdm->playback_dma_data; - if (i2s_tdm->mclk_calibrate) - snd_soc_add_dai_controls(dai, &rockchip_i2s_tdm_compensation_control, 1); - return 0; } @@ -1110,7 +812,6 @@ static int rockchip_i2s_tdm_set_bclk_ratio(struct snd_soc_dai *dai, static const struct snd_soc_dai_ops rockchip_i2s_tdm_dai_ops = { .hw_params = rockchip_i2s_tdm_hw_params, .set_bclk_ratio = rockchip_i2s_tdm_set_bclk_ratio, - .set_sysclk = rockchip_i2s_tdm_set_sysclk, .set_fmt = rockchip_i2s_tdm_set_fmt, .set_tdm_slot = rockchip_dai_tdm_slot, .trigger = rockchip_i2s_tdm_trigger, @@ -1433,35 +1134,6 @@ static void rockchip_i2s_tdm_path_config(struct rk_i2s_tdm_dev *i2s_tdm, rockchip_i2s_tdm_tx_path_config(i2s_tdm, num); } -static int rockchip_i2s_tdm_get_calibrate_mclks(struct rk_i2s_tdm_dev *i2s_tdm) -{ - int num_mclks = 0; - - i2s_tdm->mclk_tx_src = devm_clk_get(i2s_tdm->dev, "mclk_tx_src"); - if (!IS_ERR(i2s_tdm->mclk_tx_src)) - num_mclks++; - - i2s_tdm->mclk_rx_src = devm_clk_get(i2s_tdm->dev, "mclk_rx_src"); - if (!IS_ERR(i2s_tdm->mclk_rx_src)) - num_mclks++; - - i2s_tdm->mclk_root0 = devm_clk_get(i2s_tdm->dev, "mclk_root0"); - if (!IS_ERR(i2s_tdm->mclk_root0)) - num_mclks++; - - i2s_tdm->mclk_root1 = devm_clk_get(i2s_tdm->dev, "mclk_root1"); - if (!IS_ERR(i2s_tdm->mclk_root1)) - num_mclks++; - - if (num_mclks < 4 && num_mclks != 0) - return -ENOENT; - - if (num_mclks == 4) - i2s_tdm->mclk_calibrate = 1; - - return 0; -} - static int rockchip_i2s_tdm_path_prepare(struct rk_i2s_tdm_dev *i2s_tdm, struct device_node *np, bool is_rx_path) @@ -1609,11 +1281,6 @@ static int rockchip_i2s_tdm_probe(struct platform_device *pdev) i2s_tdm->io_multiplex = of_property_read_bool(node, "rockchip,io-multiplex"); - ret = rockchip_i2s_tdm_get_calibrate_mclks(i2s_tdm); - if (ret) - return dev_err_probe(i2s_tdm->dev, ret, - "mclk-calibrate clocks missing"); - regs = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(regs)) { return dev_err_probe(i2s_tdm->dev, PTR_ERR(regs), @@ -1666,13 +1333,6 @@ static int rockchip_i2s_tdm_probe(struct platform_device *pdev) goto err_disable_hclk; } - if (i2s_tdm->mclk_calibrate) { - i2s_tdm->mclk_root0_initial_freq = clk_get_rate(i2s_tdm->mclk_root0); - i2s_tdm->mclk_root1_initial_freq = clk_get_rate(i2s_tdm->mclk_root1); - i2s_tdm->mclk_root0_freq = i2s_tdm->mclk_root0_initial_freq; - i2s_tdm->mclk_root1_freq = i2s_tdm->mclk_root1_initial_freq; - } - pm_runtime_enable(&pdev->dev); regmap_update_bits(i2s_tdm->regmap, I2S_DMACR, I2S_DMACR_TDL_MASK, diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 3c5d131a6c2a3fa587b9ed6885973b43c354fdbc..64a6830aca498919638b02ae34219c3d875ddff9 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1020,6 +1020,9 @@ int snd_soc_add_pcm_runtime(struct snd_soc_card *card, if (!snd_soc_is_matching_component(platform, component)) continue; + if (snd_soc_component_is_dummy(component) && component->num_dai) + continue; + snd_soc_rtd_add_component(rtd, component); } } diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c index 2d25748ca70662bf771c6896297ccb6a0fb0798f..b27e89ff6a1673f57db6e253a818d6fbe3d1ab91 100644 --- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -263,7 +263,7 @@ int snd_soc_get_volsw(struct snd_kcontrol *kcontrol, int max = mc->max; int min = mc->min; int sign_bit = mc->sign_bit; - unsigned int mask = (1 << fls(max)) - 1; + unsigned int mask = (1ULL << fls(max)) - 1; unsigned int invert = mc->invert; int val; int ret; diff --git a/sound/soc/sof/ipc3-loader.c b/sound/soc/sof/ipc3-loader.c index bf423ca4e97bb4fe62feb401ff760d9880c6a8d5..6e3ef067211068a615d1f9d7f2ff2155922b0000 100644 --- a/sound/soc/sof/ipc3-loader.c +++ b/sound/soc/sof/ipc3-loader.c @@ -138,8 +138,7 @@ static ssize_t ipc3_fw_ext_man_size(struct snd_sof_dev *sdev, const struct firmw static size_t sof_ipc3_fw_parse_ext_man(struct snd_sof_dev *sdev) { - struct snd_sof_pdata *plat_data = sdev->pdata; - const struct firmware *fw = plat_data->fw; + const struct firmware *fw = sdev->basefw.fw; const struct sof_ext_man_elem_header *elem_hdr; const struct sof_ext_man_header *head; ssize_t ext_man_size; @@ -149,6 +148,8 @@ static size_t sof_ipc3_fw_parse_ext_man(struct snd_sof_dev *sdev) head = (struct sof_ext_man_header *)fw->data; remaining = head->full_size - head->header_size; + if (remaining < 0 || remaining > sdev->basefw.fw->size) + return -EINVAL; ext_man_size = ipc3_fw_ext_man_size(sdev, fw); /* Assert firmware starts with extended manifest */ @@ -310,18 +311,18 @@ static int sof_ipc3_parse_module_memcpy(struct snd_sof_dev *sdev, static int sof_ipc3_load_fw_to_dsp(struct snd_sof_dev *sdev) { - struct snd_sof_pdata *plat_data = sdev->pdata; - const struct firmware *fw = plat_data->fw; + u32 payload_offset = sdev->basefw.payload_offset; + const struct firmware *fw = sdev->basefw.fw; struct snd_sof_fw_header *header; struct snd_sof_mod_hdr *module; int (*load_module)(struct snd_sof_dev *sof_dev, struct snd_sof_mod_hdr *hdr); size_t remaining; int ret, count; - if (!plat_data->fw) + if (!fw) return -EINVAL; - header = (struct snd_sof_fw_header *)(fw->data + plat_data->fw_offset); + header = (struct snd_sof_fw_header *)(fw->data + payload_offset); load_module = sof_ops(sdev)->load_module; if (!load_module) { dev_dbg(sdev->dev, "Using generic module loading\n"); @@ -331,9 +332,8 @@ static int sof_ipc3_load_fw_to_dsp(struct snd_sof_dev *sdev) } /* parse each module */ - module = (struct snd_sof_mod_hdr *)(fw->data + plat_data->fw_offset + - sizeof(*header)); - remaining = fw->size - sizeof(*header) - plat_data->fw_offset; + module = (struct snd_sof_mod_hdr *)(fw->data + payload_offset + sizeof(*header)); + remaining = fw->size - sizeof(*header) - payload_offset; /* check for wrap */ if (remaining > fw->size) { dev_err(sdev->dev, "%s: fw size smaller than header size\n", __func__); @@ -374,19 +374,19 @@ static int sof_ipc3_load_fw_to_dsp(struct snd_sof_dev *sdev) static int sof_ipc3_validate_firmware(struct snd_sof_dev *sdev) { - struct snd_sof_pdata *plat_data = sdev->pdata; - const struct firmware *fw = plat_data->fw; + u32 payload_offset = sdev->basefw.payload_offset; + const struct firmware *fw = sdev->basefw.fw; struct snd_sof_fw_header *header; - size_t fw_size = fw->size - plat_data->fw_offset; + size_t fw_size = fw->size - payload_offset; - if (fw->size <= plat_data->fw_offset) { + if (fw->size <= payload_offset) { dev_err(sdev->dev, "firmware size must be greater than firmware offset\n"); return -EINVAL; } /* Read the header information from the data pointer */ - header = (struct snd_sof_fw_header *)(fw->data + plat_data->fw_offset); + header = (struct snd_sof_fw_header *)(fw->data + payload_offset); /* verify FW sig */ if (strncmp(header->sig, SND_SOF_FW_SIG, SND_SOF_FW_SIG_SIZE) != 0) { diff --git a/sound/soc/sof/ipc4-loader.c b/sound/soc/sof/ipc4-loader.c index e635ae515fa9fd7f574a2d415450ccfb42ac52c5..9f433e9b4cd37337ae62c54c5964b36d275d443c 100644 --- a/sound/soc/sof/ipc4-loader.c +++ b/sound/soc/sof/ipc4-loader.c @@ -17,9 +17,8 @@ static size_t sof_ipc4_fw_parse_ext_man(struct snd_sof_dev *sdev) { struct sof_ipc4_fw_data *ipc4_data = sdev->private; - struct snd_sof_pdata *plat_data = sdev->pdata; struct sof_man4_fw_binary_header *fw_header; - const struct firmware *fw = plat_data->fw; + const struct firmware *fw = sdev->basefw.fw; struct sof_ext_manifest4_hdr *ext_man_hdr; struct sof_man4_module_config *fm_config; struct sof_ipc4_fw_module *fw_module; @@ -138,9 +137,8 @@ static int sof_ipc4_validate_firmware(struct snd_sof_dev *sdev) { struct sof_ipc4_fw_data *ipc4_data = sdev->private; u32 fw_hdr_offset = ipc4_data->manifest_fw_hdr_offset; - struct snd_sof_pdata *plat_data = sdev->pdata; struct sof_man4_fw_binary_header *fw_header; - const struct firmware *fw = plat_data->fw; + const struct firmware *fw = sdev->basefw.fw; struct sof_ext_manifest4_hdr *ext_man_hdr; ext_man_hdr = (struct sof_ext_manifest4_hdr *)fw->data; diff --git a/sound/soc/sof/loader.c b/sound/soc/sof/loader.c index 5f51d936b3067106d016bc6724e49b42ad696bac..ba8e3aae0a5cbed497f38597cae8b5ee9b2f4576 100644 --- a/sound/soc/sof/loader.c +++ b/sound/soc/sof/loader.c @@ -22,7 +22,7 @@ int snd_sof_load_firmware_raw(struct snd_sof_dev *sdev) int ret; /* Don't request firmware again if firmware is already requested */ - if (plat_data->fw) + if (sdev->basefw.fw) return 0; fw_filename = kasprintf(GFP_KERNEL, "%s/%s", @@ -31,7 +31,7 @@ int snd_sof_load_firmware_raw(struct snd_sof_dev *sdev) if (!fw_filename) return -ENOMEM; - ret = request_firmware(&plat_data->fw, fw_filename, sdev->dev); + ret = request_firmware(&sdev->basefw.fw, fw_filename, sdev->dev); if (ret < 0) { dev_err(sdev->dev, @@ -48,7 +48,7 @@ int snd_sof_load_firmware_raw(struct snd_sof_dev *sdev) ext_man_size = sdev->ipc->ops->fw_loader->parse_ext_manifest(sdev); if (ext_man_size > 0) { /* when no error occurred, drop extended manifest */ - plat_data->fw_offset = ext_man_size; + sdev->basefw.payload_offset = ext_man_size; } else if (!ext_man_size) { /* No extended manifest, so nothing to skip during FW load */ dev_dbg(sdev->dev, "firmware doesn't contain extended manifest\n"); @@ -58,6 +58,12 @@ int snd_sof_load_firmware_raw(struct snd_sof_dev *sdev) fw_filename, ret); } + /* + * Until the platform code is switched to use the new container the fw + * and payload offset must be set in plat_data + */ + plat_data->fw = sdev->basefw.fw; + plat_data->fw_offset = sdev->basefw.payload_offset; err: kfree(fw_filename); @@ -100,7 +106,8 @@ int snd_sof_load_firmware_memcpy(struct snd_sof_dev *sdev) return 0; error: - release_firmware(plat_data->fw); + release_firmware(sdev->basefw.fw); + sdev->basefw.fw = NULL; plat_data->fw = NULL; return ret; @@ -185,7 +192,8 @@ EXPORT_SYMBOL(snd_sof_run_firmware); void snd_sof_fw_unload(struct snd_sof_dev *sdev) { /* TODO: support module unloading at runtime */ - release_firmware(sdev->pdata->fw); + release_firmware(sdev->basefw.fw); + sdev->basefw.fw = NULL; sdev->pdata->fw = NULL; } EXPORT_SYMBOL(snd_sof_fw_unload); diff --git a/sound/soc/sof/sof-priv.h b/sound/soc/sof/sof-priv.h index de08825915b35d637f4d0de9335d31b0352ffe70..3d70b57e4864d287fae9a716d1fdb847d42c24cb 100644 --- a/sound/soc/sof/sof-priv.h +++ b/sound/soc/sof/sof-priv.h @@ -136,6 +136,17 @@ struct snd_sof_platform_stream_params { bool cont_update_posn; }; +/** + * struct sof_firmware - Container struct for SOF firmware + * @fw: Pointer to the firmware + * @payload_offset: Offset of the data within the loaded firmware image to be + * loaded to the DSP (skipping for example ext_manifest section) + */ +struct sof_firmware { + const struct firmware *fw; + u32 payload_offset; +}; + /* * SOF DSP HW abstraction operations. * Used to abstract DSP HW architecture and any IO busses between host CPU @@ -487,6 +498,9 @@ struct snd_sof_dev { spinlock_t ipc_lock; /* lock for IPC users */ spinlock_t hw_lock; /* lock for HW IO access */ + /* Main, Base firmware image */ + struct sof_firmware basefw; + /* * ASoC components. plat_drv fields are set dynamically so * can't use const diff --git a/sound/soc/sunxi/sun4i-spdif.c b/sound/soc/sunxi/sun4i-spdif.c index bcceebca915ac80663e3ccbbc8077503f3c6b574..484b0e7c2defa1eae18fccdb428f161b26814bc7 100644 --- a/sound/soc/sunxi/sun4i-spdif.c +++ b/sound/soc/sunxi/sun4i-spdif.c @@ -578,6 +578,11 @@ static const struct of_device_id sun4i_spdif_of_match[] = { .compatible = "allwinner,sun50i-h6-spdif", .data = &sun50i_h6_spdif_quirks, }, + { + .compatible = "allwinner,sun50i-h616-spdif", + /* Essentially the same as the H6, but without RX */ + .data = &sun50i_h6_spdif_quirks, + }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, sun4i_spdif_of_match); diff --git a/sound/soc/tegra/tegra186_dspk.c b/sound/soc/tegra/tegra186_dspk.c index a74c980ee77539cd53dd8006eaea1487b8ecc653..d5a74e25371d245cfffb970fd6b22c83f8c0e7f2 100644 --- a/sound/soc/tegra/tegra186_dspk.c +++ b/sound/soc/tegra/tegra186_dspk.c @@ -1,8 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only +// SPDX-FileCopyrightText: Copyright (c) 2020-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved. // // tegra186_dspk.c - Tegra186 DSPK driver -// -// Copyright (c) 2020 NVIDIA CORPORATION. All rights reserved. #include #include @@ -241,14 +240,14 @@ static int tegra186_dspk_hw_params(struct snd_pcm_substream *substream, return -EINVAL; } - cif_conf.client_bits = TEGRA_ACIF_BITS_24; - switch (params_format(params)) { case SNDRV_PCM_FORMAT_S16_LE: cif_conf.audio_bits = TEGRA_ACIF_BITS_16; + cif_conf.client_bits = TEGRA_ACIF_BITS_16; break; case SNDRV_PCM_FORMAT_S32_LE: cif_conf.audio_bits = TEGRA_ACIF_BITS_32; + cif_conf.client_bits = TEGRA_ACIF_BITS_24; break; default: dev_err(dev, "unsupported format!\n"); diff --git a/sound/soc/ti/davinci-mcasp.c b/sound/soc/ti/davinci-mcasp.c index ca5d1bb6ac59e1768bc458a7ce5952b9bbb22d3b..4edf5b27e136bcdb6b4afc8a02ddbaef1deb2ee1 100644 --- a/sound/soc/ti/davinci-mcasp.c +++ b/sound/soc/ti/davinci-mcasp.c @@ -2416,12 +2416,6 @@ static int davinci_mcasp_probe(struct platform_device *pdev) mcasp_reparent_fck(pdev); - ret = devm_snd_soc_register_component(&pdev->dev, &davinci_mcasp_component, - &davinci_mcasp_dai[mcasp->op_mode], 1); - - if (ret != 0) - goto err; - ret = davinci_mcasp_get_dma_type(mcasp); switch (ret) { case PCM_EDMA: @@ -2448,6 +2442,12 @@ static int davinci_mcasp_probe(struct platform_device *pdev) goto err; } + ret = devm_snd_soc_register_component(&pdev->dev, &davinci_mcasp_component, + &davinci_mcasp_dai[mcasp->op_mode], 1); + + if (ret != 0) + goto err; + no_audio: ret = davinci_mcasp_init_gpiochip(mcasp); if (ret) { diff --git a/sound/usb/Makefile b/sound/usb/Makefile index 9ccb21a4ff8a8cdd2df135d7a738306f65e6ee40..64a718c766a7a52fc575eb8dfd598994e09aceea 100644 --- a/sound/usb/Makefile +++ b/sound/usb/Makefile @@ -12,7 +12,7 @@ snd-usb-audio-objs := card.o \ mixer.o \ mixer_quirks.o \ mixer_scarlett.o \ - mixer_scarlett_gen2.o \ + mixer_scarlett2.o \ mixer_us16x08.o \ mixer_s1810c.o \ pcm.o \ diff --git a/sound/usb/clock.c b/sound/usb/clock.c index 33db334e6556674414047b1a1d660ec3e8083100..a676ad093d18977345d755366c24dce4b70efde8 100644 --- a/sound/usb/clock.c +++ b/sound/usb/clock.c @@ -328,8 +328,16 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip, if (chip->quirk_flags & QUIRK_FLAG_SKIP_CLOCK_SELECTOR) return ret; err = uac_clock_selector_set_val(chip, entity_id, cur); - if (err < 0) + if (err < 0) { + if (pins == 1) { + usb_audio_dbg(chip, + "%s(): selector returned an error, " + "assuming a firmware bug, id %d, ret %d\n", + __func__, clock_id, err); + return ret; + } return err; + } } if (!validate || ret > 0 || !chip->autoclock) diff --git a/sound/usb/format.c b/sound/usb/format.c index ab5fed9f55b60ec8b255448a9cbb435f9e04d96b..3b45d0ee769389aafb3e752cec5b96223c52077b 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -470,9 +470,11 @@ static int validate_sample_rate_table_v2v3(struct snd_usb_audio *chip, int clock) { struct usb_device *dev = chip->dev; + struct usb_host_interface *alts; unsigned int *table; unsigned int nr_rates; int i, err; + u32 bmControls; /* performing the rate verification may lead to unexpected USB bus * behavior afterwards by some unknown reason. Do this only for the @@ -481,6 +483,24 @@ static int validate_sample_rate_table_v2v3(struct snd_usb_audio *chip, if (!(chip->quirk_flags & QUIRK_FLAG_VALIDATE_RATES)) return 0; /* don't perform the validation as default */ + alts = snd_usb_get_host_interface(chip, fp->iface, fp->altsetting); + if (!alts) + return 0; + + if (fp->protocol == UAC_VERSION_3) { + struct uac3_as_header_descriptor *as = snd_usb_find_csint_desc( + alts->extra, alts->extralen, NULL, UAC_AS_GENERAL); + bmControls = le32_to_cpu(as->bmControls); + } else { + struct uac2_as_header_descriptor *as = snd_usb_find_csint_desc( + alts->extra, alts->extralen, NULL, UAC_AS_GENERAL); + bmControls = as->bmControls; + } + + if (!uac_v2v3_control_is_readable(bmControls, + UAC2_AS_VAL_ALT_SETTINGS)) + return 0; + table = kcalloc(fp->nr_rates, sizeof(*table), GFP_KERNEL); if (!table) return -ENOMEM; diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c index b67617b68e509d2c86d78058f7796a64aab00f41..f4437015d43a7500b809a303f175b211662d500f 100644 --- a/sound/usb/line6/driver.c +++ b/sound/usb/line6/driver.c @@ -202,7 +202,7 @@ int line6_send_raw_message_async(struct usb_line6 *line6, const char *buffer, struct urb *urb; /* create message: */ - msg = kmalloc(sizeof(struct message), GFP_ATOMIC); + msg = kzalloc(sizeof(struct message), GFP_ATOMIC); if (msg == NULL) return -ENOMEM; @@ -688,7 +688,7 @@ static int line6_init_cap_control(struct usb_line6 *line6) int ret; /* initialize USB buffers: */ - line6->buffer_listen = kmalloc(LINE6_BUFSIZE_LISTEN, GFP_KERNEL); + line6->buffer_listen = kzalloc(LINE6_BUFSIZE_LISTEN, GFP_KERNEL); if (!line6->buffer_listen) return -ENOMEM; @@ -697,7 +697,7 @@ static int line6_init_cap_control(struct usb_line6 *line6) return -ENOMEM; if (line6->properties->capabilities & LINE6_CAP_CONTROL_MIDI) { - line6->buffer_message = kmalloc(LINE6_MIDI_MESSAGE_MAXLEN, GFP_KERNEL); + line6->buffer_message = kzalloc(LINE6_MIDI_MESSAGE_MAXLEN, GFP_KERNEL); if (!line6->buffer_message) return -ENOMEM; diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index 1f32e3ae3aa31a6256ad6bd0b8d14cbe4a3f61f4..c8d48566e17598df4e7c390240512ac25c84128d 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -33,7 +33,7 @@ #include "mixer.h" #include "mixer_quirks.h" #include "mixer_scarlett.h" -#include "mixer_scarlett_gen2.h" +#include "mixer_scarlett2.h" #include "mixer_us16x08.h" #include "mixer_s1810c.h" #include "helper.h" @@ -3447,8 +3447,13 @@ int snd_usb_mixer_apply_create_quirk(struct usb_mixer_interface *mixer) case USB_ID(0x1235, 0x8213): /* Focusrite Scarlett 8i6 3rd Gen */ case USB_ID(0x1235, 0x8214): /* Focusrite Scarlett 18i8 3rd Gen */ case USB_ID(0x1235, 0x8215): /* Focusrite Scarlett 18i20 3rd Gen */ + case USB_ID(0x1235, 0x8206): /* Focusrite Clarett 2Pre USB */ + case USB_ID(0x1235, 0x8207): /* Focusrite Clarett 4Pre USB */ + case USB_ID(0x1235, 0x8208): /* Focusrite Clarett 8Pre USB */ + case USB_ID(0x1235, 0x820a): /* Focusrite Clarett+ 2Pre */ + case USB_ID(0x1235, 0x820b): /* Focusrite Clarett+ 4Pre */ case USB_ID(0x1235, 0x820c): /* Focusrite Clarett+ 8Pre */ - err = snd_scarlett_gen2_init(mixer); + err = snd_scarlett2_init(mixer); break; case USB_ID(0x041e, 0x323b): /* Creative Sound Blaster E1 */ diff --git a/sound/usb/mixer_scarlett_gen2.c b/sound/usb/mixer_scarlett2.c similarity index 94% rename from sound/usb/mixer_scarlett_gen2.c rename to sound/usb/mixer_scarlett2.c index 1bcb05c73e0ad3df686dc0fa52abbdbebdd29bdb..bcb8b76174065152c7d350338d227cfc0a6a0b46 100644 --- a/sound/usb/mixer_scarlett_gen2.c +++ b/sound/usb/mixer_scarlett2.c @@ -1,13 +1,16 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Focusrite Scarlett Gen 2/3 and Clarett+ Driver for ALSA + * Focusrite Scarlett 2 Protocol Driver for ALSA + * (including Scarlett 2nd Gen, 3rd Gen, Clarett USB, and Clarett+ + * series products) * * Supported models: * - 6i6/18i8/18i20 Gen 2 * - Solo/2i2/4i4/8i6/18i8/18i20 Gen 3 - * - Clarett+ 8Pre + * - Clarett 2Pre/4Pre/8Pre USB + * - Clarett+ 2Pre/4Pre/8Pre * - * Copyright (c) 2018-2022 by Geoffrey D. Bennett + * Copyright (c) 2018-2023 by Geoffrey D. Bennett * Copyright (c) 2020-2021 by Vladimir Sadovnikov * Copyright (c) 2022 by Christian Colglazier * @@ -56,6 +59,15 @@ * Support for Clarett+ 8Pre added in Aug 2022 by Christian * Colglazier. * + * Support for Clarett 8Pre USB added in Sep 2023 (thanks to Philippe + * Perrot for confirmation). + * + * Support for Clarett+ 4Pre and 2Pre added in Sep 2023 (thanks to + * Gregory Rozzo for donating a 4Pre, and David Sherwood and Patrice + * Peterson for usbmon output). + * + * Support for Clarett 2Pre and 4Pre USB added in Oct 2023. + * * This ALSA mixer gives access to (model-dependent): * - input, output, mixer-matrix muxes * - mixer-matrix gain stages @@ -139,14 +151,14 @@ #include "mixer.h" #include "helper.h" -#include "mixer_scarlett_gen2.h" - -/* device_setup value to enable */ -#define SCARLETT2_ENABLE 0x01 +#include "mixer_scarlett2.h" /* device_setup value to allow turning MSD mode back on */ #define SCARLETT2_MSD_ENABLE 0x02 +/* device_setup value to disable this mixer driver */ +#define SCARLETT2_DISABLE 0x04 + /* some gui mixers can't handle negative ctl values */ #define SCARLETT2_VOLUME_BIAS 127 @@ -317,8 +329,6 @@ struct scarlett2_mux_entry { }; struct scarlett2_device_info { - u32 usb_id; /* USB device identifier */ - /* Gen 3 devices have an internal MSD mode switch that needs * to be disabled in order to access the full functionality of * the device. @@ -389,6 +399,7 @@ struct scarlett2_data { struct mutex data_mutex; /* lock access to this data */ struct delayed_work work; const struct scarlett2_device_info *info; + const char *series_name; __u8 bInterfaceNumber; __u8 bEndpointAddress; __u16 wMaxPacketSize; @@ -440,8 +451,6 @@ struct scarlett2_data { /*** Model-specific data ***/ static const struct scarlett2_device_info s6i6_gen2_info = { - .usb_id = USB_ID(0x1235, 0x8203), - .config_set = SCARLETT2_CONFIG_SET_GEN_2, .level_input_count = 2, .pad_input_count = 2, @@ -486,8 +495,6 @@ static const struct scarlett2_device_info s6i6_gen2_info = { }; static const struct scarlett2_device_info s18i8_gen2_info = { - .usb_id = USB_ID(0x1235, 0x8204), - .config_set = SCARLETT2_CONFIG_SET_GEN_2, .level_input_count = 2, .pad_input_count = 4, @@ -535,8 +542,6 @@ static const struct scarlett2_device_info s18i8_gen2_info = { }; static const struct scarlett2_device_info s18i20_gen2_info = { - .usb_id = USB_ID(0x1235, 0x8201), - .config_set = SCARLETT2_CONFIG_SET_GEN_2, .line_out_hw_vol = 1, @@ -589,8 +594,6 @@ static const struct scarlett2_device_info s18i20_gen2_info = { }; static const struct scarlett2_device_info solo_gen3_info = { - .usb_id = USB_ID(0x1235, 0x8211), - .has_msd_mode = 1, .config_set = SCARLETT2_CONFIG_SET_NO_MIXER, .level_input_count = 1, @@ -602,8 +605,6 @@ static const struct scarlett2_device_info solo_gen3_info = { }; static const struct scarlett2_device_info s2i2_gen3_info = { - .usb_id = USB_ID(0x1235, 0x8210), - .has_msd_mode = 1, .config_set = SCARLETT2_CONFIG_SET_NO_MIXER, .level_input_count = 2, @@ -614,8 +615,6 @@ static const struct scarlett2_device_info s2i2_gen3_info = { }; static const struct scarlett2_device_info s4i4_gen3_info = { - .usb_id = USB_ID(0x1235, 0x8212), - .has_msd_mode = 1, .config_set = SCARLETT2_CONFIG_SET_GEN_3, .level_input_count = 2, @@ -660,8 +659,6 @@ static const struct scarlett2_device_info s4i4_gen3_info = { }; static const struct scarlett2_device_info s8i6_gen3_info = { - .usb_id = USB_ID(0x1235, 0x8213), - .has_msd_mode = 1, .config_set = SCARLETT2_CONFIG_SET_GEN_3, .level_input_count = 2, @@ -713,8 +710,6 @@ static const struct scarlett2_device_info s8i6_gen3_info = { }; static const struct scarlett2_device_info s18i8_gen3_info = { - .usb_id = USB_ID(0x1235, 0x8214), - .has_msd_mode = 1, .config_set = SCARLETT2_CONFIG_SET_GEN_3, .line_out_hw_vol = 1, @@ -783,8 +778,6 @@ static const struct scarlett2_device_info s18i8_gen3_info = { }; static const struct scarlett2_device_info s18i20_gen3_info = { - .usb_id = USB_ID(0x1235, 0x8215), - .has_msd_mode = 1, .config_set = SCARLETT2_CONFIG_SET_GEN_3, .line_out_hw_vol = 1, @@ -847,9 +840,96 @@ static const struct scarlett2_device_info s18i20_gen3_info = { } }, }; -static const struct scarlett2_device_info clarett_8pre_info = { - .usb_id = USB_ID(0x1235, 0x820c), +static const struct scarlett2_device_info clarett_2pre_info = { + .config_set = SCARLETT2_CONFIG_SET_CLARETT, + .line_out_hw_vol = 1, + .level_input_count = 2, + .air_input_count = 2, + + .line_out_descrs = { + "Monitor L", + "Monitor R", + "Headphones L", + "Headphones R", + }, + + .port_count = { + [SCARLETT2_PORT_TYPE_NONE] = { 1, 0 }, + [SCARLETT2_PORT_TYPE_ANALOGUE] = { 2, 4 }, + [SCARLETT2_PORT_TYPE_SPDIF] = { 2, 0 }, + [SCARLETT2_PORT_TYPE_ADAT] = { 8, 0 }, + [SCARLETT2_PORT_TYPE_MIX] = { 10, 18 }, + [SCARLETT2_PORT_TYPE_PCM] = { 4, 12 }, + }, + + .mux_assignment = { { + { SCARLETT2_PORT_TYPE_PCM, 0, 12 }, + { SCARLETT2_PORT_TYPE_ANALOGUE, 0, 4 }, + { SCARLETT2_PORT_TYPE_MIX, 0, 18 }, + { SCARLETT2_PORT_TYPE_NONE, 0, 8 }, + { 0, 0, 0 }, + }, { + { SCARLETT2_PORT_TYPE_PCM, 0, 8 }, + { SCARLETT2_PORT_TYPE_ANALOGUE, 0, 4 }, + { SCARLETT2_PORT_TYPE_MIX, 0, 18 }, + { SCARLETT2_PORT_TYPE_NONE, 0, 8 }, + { 0, 0, 0 }, + }, { + { SCARLETT2_PORT_TYPE_PCM, 0, 2 }, + { SCARLETT2_PORT_TYPE_ANALOGUE, 0, 4 }, + { SCARLETT2_PORT_TYPE_NONE, 0, 26 }, + { 0, 0, 0 }, + } }, +}; + +static const struct scarlett2_device_info clarett_4pre_info = { + .config_set = SCARLETT2_CONFIG_SET_CLARETT, + .line_out_hw_vol = 1, + .level_input_count = 2, + .air_input_count = 4, + + .line_out_descrs = { + "Monitor L", + "Monitor R", + "Headphones 1 L", + "Headphones 1 R", + "Headphones 2 L", + "Headphones 2 R", + }, + .port_count = { + [SCARLETT2_PORT_TYPE_NONE] = { 1, 0 }, + [SCARLETT2_PORT_TYPE_ANALOGUE] = { 8, 6 }, + [SCARLETT2_PORT_TYPE_SPDIF] = { 2, 2 }, + [SCARLETT2_PORT_TYPE_ADAT] = { 8, 0 }, + [SCARLETT2_PORT_TYPE_MIX] = { 10, 18 }, + [SCARLETT2_PORT_TYPE_PCM] = { 8, 18 }, + }, + + .mux_assignment = { { + { SCARLETT2_PORT_TYPE_PCM, 0, 18 }, + { SCARLETT2_PORT_TYPE_ANALOGUE, 0, 6 }, + { SCARLETT2_PORT_TYPE_SPDIF, 0, 2 }, + { SCARLETT2_PORT_TYPE_MIX, 0, 18 }, + { SCARLETT2_PORT_TYPE_NONE, 0, 8 }, + { 0, 0, 0 }, + }, { + { SCARLETT2_PORT_TYPE_PCM, 0, 14 }, + { SCARLETT2_PORT_TYPE_ANALOGUE, 0, 6 }, + { SCARLETT2_PORT_TYPE_SPDIF, 0, 2 }, + { SCARLETT2_PORT_TYPE_MIX, 0, 18 }, + { SCARLETT2_PORT_TYPE_NONE, 0, 8 }, + { 0, 0, 0 }, + }, { + { SCARLETT2_PORT_TYPE_PCM, 0, 12 }, + { SCARLETT2_PORT_TYPE_ANALOGUE, 0, 6 }, + { SCARLETT2_PORT_TYPE_SPDIF, 0, 2 }, + { SCARLETT2_PORT_TYPE_NONE, 0, 24 }, + { 0, 0, 0 }, + } }, +}; + +static const struct scarlett2_device_info clarett_8pre_info = { .config_set = SCARLETT2_CONFIG_SET_CLARETT, .line_out_hw_vol = 1, .level_input_count = 2, @@ -902,25 +982,36 @@ static const struct scarlett2_device_info clarett_8pre_info = { } }, }; -static const struct scarlett2_device_info *scarlett2_devices[] = { +struct scarlett2_device_entry { + const u32 usb_id; /* USB device identifier */ + const struct scarlett2_device_info *info; + const char *series_name; +}; + +static const struct scarlett2_device_entry scarlett2_devices[] = { /* Supported Gen 2 devices */ - &s6i6_gen2_info, - &s18i8_gen2_info, - &s18i20_gen2_info, + { USB_ID(0x1235, 0x8203), &s6i6_gen2_info, "Scarlett Gen 2" }, + { USB_ID(0x1235, 0x8204), &s18i8_gen2_info, "Scarlett Gen 2" }, + { USB_ID(0x1235, 0x8201), &s18i20_gen2_info, "Scarlett Gen 2" }, /* Supported Gen 3 devices */ - &solo_gen3_info, - &s2i2_gen3_info, - &s4i4_gen3_info, - &s8i6_gen3_info, - &s18i8_gen3_info, - &s18i20_gen3_info, - - /* Supported Clarett+ devices */ - &clarett_8pre_info, + { USB_ID(0x1235, 0x8211), &solo_gen3_info, "Scarlett Gen 3" }, + { USB_ID(0x1235, 0x8210), &s2i2_gen3_info, "Scarlett Gen 3" }, + { USB_ID(0x1235, 0x8212), &s4i4_gen3_info, "Scarlett Gen 3" }, + { USB_ID(0x1235, 0x8213), &s8i6_gen3_info, "Scarlett Gen 3" }, + { USB_ID(0x1235, 0x8214), &s18i8_gen3_info, "Scarlett Gen 3" }, + { USB_ID(0x1235, 0x8215), &s18i20_gen3_info, "Scarlett Gen 3" }, + + /* Supported Clarett USB/Clarett+ devices */ + { USB_ID(0x1235, 0x8206), &clarett_2pre_info, "Clarett USB" }, + { USB_ID(0x1235, 0x8207), &clarett_4pre_info, "Clarett USB" }, + { USB_ID(0x1235, 0x8208), &clarett_8pre_info, "Clarett USB" }, + { USB_ID(0x1235, 0x820a), &clarett_2pre_info, "Clarett+" }, + { USB_ID(0x1235, 0x820b), &clarett_4pre_info, "Clarett+" }, + { USB_ID(0x1235, 0x820c), &clarett_8pre_info, "Clarett+" }, /* End of list */ - NULL + { 0, NULL }, }; /* get the starting port index number for a given port type/direction */ @@ -1112,7 +1203,7 @@ static const struct scarlett2_config [SCARLETT2_CONFIG_TALKBACK_MAP] = { .offset = 0xb0, .size = 16, .activate = 10 }, -/* Clarett+ 8Pre */ +/* Clarett USB and Clarett+ devices: 2Pre, 4Pre, 8Pre */ }, { [SCARLETT2_CONFIG_DIM_MUTE] = { .offset = 0x31, .size = 8, .activate = 2 }, @@ -1217,8 +1308,8 @@ static int scarlett2_usb( if (err != req_buf_size) { usb_audio_err( mixer->chip, - "Scarlett Gen 2/3 USB request result cmd %x was %d\n", - cmd, err); + "%s USB request result cmd %x was %d\n", + private->series_name, cmd, err); err = -EINVAL; goto unlock; } @@ -1234,9 +1325,8 @@ static int scarlett2_usb( if (err != resp_buf_size) { usb_audio_err( mixer->chip, - "Scarlett Gen 2/3 USB response result cmd %x was %d " - "expected %zu\n", - cmd, err, resp_buf_size); + "%s USB response result cmd %x was %d expected %zu\n", + private->series_name, cmd, err, resp_buf_size); err = -EINVAL; goto unlock; } @@ -1252,9 +1342,10 @@ static int scarlett2_usb( resp->pad) { usb_audio_err( mixer->chip, - "Scarlett Gen 2/3 USB invalid response; " + "%s USB invalid response; " "cmd tx/rx %d/%d seq %d/%d size %d/%d " "error %d pad %d\n", + private->series_name, le32_to_cpu(req->cmd), le32_to_cpu(resp->cmd), le16_to_cpu(req->seq), le16_to_cpu(resp->seq), resp_size, le16_to_cpu(resp->size), @@ -3810,7 +3901,7 @@ static int scarlett2_find_fc_interface(struct usb_device *dev, /* Initialise private data */ static int scarlett2_init_private(struct usb_mixer_interface *mixer, - const struct scarlett2_device_info *info) + const struct scarlett2_device_entry *entry) { struct scarlett2_data *private = kzalloc(sizeof(struct scarlett2_data), GFP_KERNEL); @@ -3826,7 +3917,8 @@ static int scarlett2_init_private(struct usb_mixer_interface *mixer, mixer->private_free = scarlett2_private_free; mixer->private_suspend = scarlett2_private_suspend; - private->info = info; + private->info = entry->info; + private->series_name = entry->series_name; scarlett2_count_mux_io(private); private->scarlett2_seq = 0; private->mixer = mixer; @@ -4147,19 +4239,28 @@ static int scarlett2_init_notify(struct usb_mixer_interface *mixer) return usb_submit_urb(mixer->urb, GFP_KERNEL); } -static int snd_scarlett_gen2_controls_create(struct usb_mixer_interface *mixer) +static const struct scarlett2_device_entry *get_scarlett2_device_entry( + struct usb_mixer_interface *mixer) { - const struct scarlett2_device_info **info = scarlett2_devices; - int err; + const struct scarlett2_device_entry *entry = scarlett2_devices; - /* Find device in scarlett2_devices */ - while (*info && (*info)->usb_id != mixer->chip->usb_id) - info++; - if (!*info) - return -EINVAL; + /* Find entry in scarlett2_devices */ + while (entry->usb_id && entry->usb_id != mixer->chip->usb_id) + entry++; + if (!entry->usb_id) + return NULL; + + return entry; +} + +static int snd_scarlett2_controls_create( + struct usb_mixer_interface *mixer, + const struct scarlett2_device_entry *entry) +{ + int err; /* Initialise private data */ - err = scarlett2_init_private(mixer, *info); + err = scarlett2_init_private(mixer, entry); if (err < 0) return err; @@ -4240,34 +4341,50 @@ static int snd_scarlett_gen2_controls_create(struct usb_mixer_interface *mixer) return 0; } -int snd_scarlett_gen2_init(struct usb_mixer_interface *mixer) +int snd_scarlett2_init(struct usb_mixer_interface *mixer) { struct snd_usb_audio *chip = mixer->chip; + const struct scarlett2_device_entry *entry; int err; /* only use UAC_VERSION_2 */ if (!mixer->protocol) return 0; - if (!(chip->setup & SCARLETT2_ENABLE)) { + /* find entry in scarlett2_devices */ + entry = get_scarlett2_device_entry(mixer); + if (!entry) { + usb_audio_err(mixer->chip, + "%s: missing device entry for %04x:%04x\n", + __func__, + USB_ID_VENDOR(chip->usb_id), + USB_ID_PRODUCT(chip->usb_id)); + return 0; + } + + if (chip->setup & SCARLETT2_DISABLE) { usb_audio_info(chip, - "Focusrite Scarlett Gen 2/3 Mixer Driver disabled; " - "use options snd_usb_audio vid=0x%04x pid=0x%04x " - "device_setup=1 to enable and report any issues " - "to g@b4.vu", + "Focusrite %s Mixer Driver disabled " + "by modprobe options (snd_usb_audio " + "vid=0x%04x pid=0x%04x device_setup=%d)\n", + entry->series_name, USB_ID_VENDOR(chip->usb_id), - USB_ID_PRODUCT(chip->usb_id)); + USB_ID_PRODUCT(chip->usb_id), + SCARLETT2_DISABLE); return 0; } usb_audio_info(chip, - "Focusrite Scarlett Gen 2/3 Mixer Driver enabled pid=0x%04x", + "Focusrite %s Mixer Driver enabled (pid=0x%04x); " + "report any issues to g@b4.vu", + entry->series_name, USB_ID_PRODUCT(chip->usb_id)); - err = snd_scarlett_gen2_controls_create(mixer); + err = snd_scarlett2_controls_create(mixer, entry); if (err < 0) usb_audio_err(mixer->chip, - "Error initialising Scarlett Mixer Driver: %d", + "Error initialising %s Mixer Driver: %d", + entry->series_name, err); return err; diff --git a/sound/usb/mixer_scarlett2.h b/sound/usb/mixer_scarlett2.h new file mode 100644 index 0000000000000000000000000000000000000000..d209362cf41a6c1b245a356c2afbc69e0f0991ce --- /dev/null +++ b/sound/usb/mixer_scarlett2.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __USB_MIXER_SCARLETT2_H +#define __USB_MIXER_SCARLETT2_H + +int snd_scarlett2_init(struct usb_mixer_interface *mixer); + +#endif /* __USB_MIXER_SCARLETT2_H */ diff --git a/sound/usb/mixer_scarlett_gen2.h b/sound/usb/mixer_scarlett_gen2.h deleted file mode 100644 index 668c6b0cb50a63bf10c6ca99ab49f74f5b3d5872..0000000000000000000000000000000000000000 --- a/sound/usb/mixer_scarlett_gen2.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __USB_MIXER_SCARLETT_GEN2_H -#define __USB_MIXER_SCARLETT_GEN2_H - -int snd_scarlett_gen2_init(struct usb_mixer_interface *mixer); - -#endif /* __USB_MIXER_SCARLETT_GEN2_H */ diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 33380cad3a735d22306fad477711ee0d58381e10..b8a474a2e4d59cab5b50e5dc37e5ba66923b4b71 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2029,10 +2029,14 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_CTL_MSG_DELAY_1M | QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x0499, 0x1509, /* Steinberg UR22 */ QUIRK_FLAG_GENERIC_IMPLICIT_FB), + DEVICE_FLG(0x0499, 0x3108, /* Yamaha YIT-W12TX */ + QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x04d8, 0xfeea, /* Benchmark DAC1 Pre */ QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x04e8, 0xa051, /* Samsung USBC Headset (AKG) */ QUIRK_FLAG_SKIP_CLOCK_SELECTOR | QUIRK_FLAG_CTL_MSG_DELAY_5M), + DEVICE_FLG(0x0525, 0xa4ad, /* Hamedal C20 usb camero */ + QUIRK_FLAG_IFACE_SKIP_CLOSE), DEVICE_FLG(0x054c, 0x0b8c, /* Sony WALKMAN NW-A45 DAC */ QUIRK_FLAG_SET_IFACE_FIRST), DEVICE_FLG(0x0556, 0x0014, /* Phoenix Audio TMX320VC */ @@ -2071,14 +2075,22 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x0763, 0x2031, /* M-Audio Fast Track C600 */ QUIRK_FLAG_GENERIC_IMPLICIT_FB), + DEVICE_FLG(0x07fd, 0x000b, /* MOTU M Series 2nd hardware revision */ + QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x08bb, 0x2702, /* LineX FM Transmitter */ QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x0951, 0x16ad, /* Kingston HyperX */ QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x0b0e, 0x0349, /* Jabra 550a */ QUIRK_FLAG_CTL_MSG_DELAY_1M), + DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */ + QUIRK_FLAG_FIXED_RATE), + DEVICE_FLG(0x0ecb, 0x2069, /* JBL Quantum810 Wireless */ + QUIRK_FLAG_FIXED_RATE), DEVICE_FLG(0x0fd9, 0x0008, /* Hauppauge HVR-950Q */ QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER), + DEVICE_FLG(0x1224, 0x2a25, /* Jieli Technology USB PHY 2.0 */ + QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x1395, 0x740a, /* Sennheiser DECT */ QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x1397, 0x0507, /* Behringer UMC202HD */ @@ -2111,6 +2123,10 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY), DEVICE_FLG(0x1901, 0x0191, /* GE B850V3 CP2114 audio interface */ QUIRK_FLAG_GET_SAMPLE_RATE), + DEVICE_FLG(0x19f7, 0x0035, /* RODE NT-USB+ */ + QUIRK_FLAG_GET_SAMPLE_RATE), + DEVICE_FLG(0x1bcf, 0x2283, /* NexiGo N930AF FHD Webcam */ + QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x2040, 0x7200, /* Hauppauge HVR-950Q */ QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER), DEVICE_FLG(0x2040, 0x7201, /* Hauppauge HVR-950Q-MXL */ @@ -2153,6 +2169,12 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x2912, 0x30c8, /* Audioengine D1 */ QUIRK_FLAG_GET_SAMPLE_RATE), + DEVICE_FLG(0x2b53, 0x0023, /* Fiero SC-01 (firmware v1.0.0 @ 48 kHz) */ + QUIRK_FLAG_GENERIC_IMPLICIT_FB), + DEVICE_FLG(0x2b53, 0x0024, /* Fiero SC-01 (firmware v1.0.0 @ 96 kHz) */ + QUIRK_FLAG_GENERIC_IMPLICIT_FB), + DEVICE_FLG(0x2b53, 0x0031, /* Fiero SC-01 (firmware v1.1.0) */ + QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */ QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x413c, 0xa506, /* Dell AE515 sound bar */ @@ -2161,22 +2183,6 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_ALIGN_TRANSFER), DEVICE_FLG(0x534d, 0x2109, /* MacroSilicon MS2109 */ QUIRK_FLAG_ALIGN_TRANSFER), - DEVICE_FLG(0x1224, 0x2a25, /* Jieli Technology USB PHY 2.0 */ - QUIRK_FLAG_GET_SAMPLE_RATE), - DEVICE_FLG(0x2b53, 0x0023, /* Fiero SC-01 (firmware v1.0.0 @ 48 kHz) */ - QUIRK_FLAG_GENERIC_IMPLICIT_FB), - DEVICE_FLG(0x2b53, 0x0024, /* Fiero SC-01 (firmware v1.0.0 @ 96 kHz) */ - QUIRK_FLAG_GENERIC_IMPLICIT_FB), - DEVICE_FLG(0x2b53, 0x0031, /* Fiero SC-01 (firmware v1.1.0) */ - QUIRK_FLAG_GENERIC_IMPLICIT_FB), - DEVICE_FLG(0x0525, 0xa4ad, /* Hamedal C20 usb camero */ - QUIRK_FLAG_IFACE_SKIP_CLOSE), - DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */ - QUIRK_FLAG_FIXED_RATE), - DEVICE_FLG(0x0ecb, 0x2069, /* JBL Quantum810 Wireless */ - QUIRK_FLAG_FIXED_RATE), - DEVICE_FLG(0x1bcf, 0x2283, /* NexiGo N930AF FHD Webcam */ - QUIRK_FLAG_GET_SAMPLE_RATE), /* Vendor matches */ VENDOR_FLG(0x045e, /* MS Lifecam */ diff --git a/sound/usb/stream.c b/sound/usb/stream.c index 3d4add94e367d63d1329f22ddb78af4264685580..d5409f3879455961182713d24327836219e73457 100644 --- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -300,9 +300,12 @@ static struct snd_pcm_chmap_elem *convert_chmap(int channels, unsigned int bits, c = 0; if (bits) { - for (; bits && *maps; maps++, bits >>= 1) + for (; bits && *maps; maps++, bits >>= 1) { if (bits & 1) chmap->map[c++] = *maps; + if (c == chmap->channels) + break; + } } else { /* If we're missing wChannelConfig, then guess something to make sure the channel map is not skipped entirely */ diff --git a/tools/arch/x86/include/asm/rmwcc.h b/tools/arch/x86/include/asm/rmwcc.h index 11ff975242cac7cff4dfaab3a4591dc4cb82eb1d..e2ff22b379a44c584b7325249c48db9b3368c7d8 100644 --- a/tools/arch/x86/include/asm/rmwcc.h +++ b/tools/arch/x86/include/asm/rmwcc.h @@ -4,7 +4,7 @@ #define __GEN_RMWcc(fullop, var, cc, ...) \ do { \ - asm_volatile_goto (fullop "; j" cc " %l[cc_label]" \ + asm goto (fullop "; j" cc " %l[cc_label]" \ : : "m" (var), ## __VA_ARGS__ \ : "memory" : cc_label); \ return 0; \ diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 41c02b6f6f043b50c3a99abbc4a83a2ba812fdce..7e0b846e17eefc5c9750ac5bac44c2c137514a64 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -2200,7 +2200,7 @@ static int profile_open_perf_events(struct profiler_bpf *obj) int map_fd; profile_perf_events = calloc( - sizeof(int), obj->rodata->num_cpu * obj->rodata->num_metric); + obj->rodata->num_cpu * obj->rodata->num_metric, sizeof(int)); if (!profile_perf_events) { p_err("failed to allocate memory for perf_event array: %s", strerror(errno)); diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index 77058174082d79ddf6f10bf4727df47e879007b5..ef0764d6891e4368bc977d302cd2501f753de856 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -70,6 +70,7 @@ #include #include #include +#include #include #include #include @@ -78,7 +79,7 @@ #include #define BTF_IDS_SECTION ".BTF_ids" -#define BTF_ID "__BTF_ID__" +#define BTF_ID_PREFIX "__BTF_ID__" #define BTF_STRUCT "struct" #define BTF_UNION "union" @@ -89,6 +90,14 @@ #define ADDR_CNT 100 +#if __BYTE_ORDER == __LITTLE_ENDIAN +# define ELFDATANATIVE ELFDATA2LSB +#elif __BYTE_ORDER == __BIG_ENDIAN +# define ELFDATANATIVE ELFDATA2MSB +#else +# error "Unknown machine endianness!" +#endif + struct btf_id { struct rb_node rb_node; char *name; @@ -116,6 +125,7 @@ struct object { int idlist_shndx; size_t strtabidx; unsigned long idlist_addr; + int encoding; } efile; struct rb_root sets; @@ -161,7 +171,7 @@ static int eprintf(int level, int var, const char *fmt, ...) static bool is_btf_id(const char *name) { - return name && !strncmp(name, BTF_ID, sizeof(BTF_ID) - 1); + return name && !strncmp(name, BTF_ID_PREFIX, sizeof(BTF_ID_PREFIX) - 1); } static struct btf_id *btf_id__find(struct rb_root *root, const char *name) @@ -319,6 +329,7 @@ static int elf_collect(struct object *obj) { Elf_Scn *scn = NULL; size_t shdrstrndx; + GElf_Ehdr ehdr; int idx = 0; Elf *elf; int fd; @@ -350,6 +361,13 @@ static int elf_collect(struct object *obj) return -1; } + if (gelf_getehdr(obj->efile.elf, &ehdr) == NULL) { + pr_err("FAILED cannot get ELF header: %s\n", + elf_errmsg(-1)); + return -1; + } + obj->efile.encoding = ehdr.e_ident[EI_DATA]; + /* * Scan all the elf sections and look for save data * from .BTF_ids section and symbols. @@ -441,7 +459,7 @@ static int symbols_collect(struct object *obj) * __BTF_ID__TYPE__vfs_truncate__0 * prefix = ^ */ - prefix = name + sizeof(BTF_ID) - 1; + prefix = name + sizeof(BTF_ID_PREFIX) - 1; /* struct */ if (!strncmp(prefix, BTF_STRUCT, sizeof(BTF_STRUCT) - 1)) { @@ -649,19 +667,18 @@ static int cmp_id(const void *pa, const void *pb) static int sets_patch(struct object *obj) { Elf_Data *data = obj->efile.idlist; - int *ptr = data->d_buf; struct rb_node *next; next = rb_first(&obj->sets); while (next) { - unsigned long addr, idx; + struct btf_id_set8 *set8; + struct btf_id_set *set; + unsigned long addr, off; struct btf_id *id; - int *base; - int cnt; id = rb_entry(next, struct btf_id, rb_node); addr = id->addr[0]; - idx = addr - obj->efile.idlist_addr; + off = addr - obj->efile.idlist_addr; /* sets are unique */ if (id->addr_cnt != 1) { @@ -670,14 +687,39 @@ static int sets_patch(struct object *obj) return -1; } - idx = idx / sizeof(int); - base = &ptr[idx] + (id->is_set8 ? 2 : 1); - cnt = ptr[idx]; + if (id->is_set) { + set = data->d_buf + off; + qsort(set->ids, set->cnt, sizeof(set->ids[0]), cmp_id); + } else { + set8 = data->d_buf + off; + /* + * Make sure id is at the beginning of the pairs + * struct, otherwise the below qsort would not work. + */ + BUILD_BUG_ON(set8->pairs != &set8->pairs[0].id); + qsort(set8->pairs, set8->cnt, sizeof(set8->pairs[0]), cmp_id); - pr_debug("sorting addr %5lu: cnt %6d [%s]\n", - (idx + 1) * sizeof(int), cnt, id->name); + /* + * When ELF endianness does not match endianness of the + * host, libelf will do the translation when updating + * the ELF. This, however, corrupts SET8 flags which are + * already in the target endianness. So, let's bswap + * them to the host endianness and libelf will then + * correctly translate everything. + */ + if (obj->efile.encoding != ELFDATANATIVE) { + int i; + + set8->flags = bswap_32(set8->flags); + for (i = 0; i < set8->cnt; i++) { + set8->pairs[i].flags = + bswap_32(set8->pairs[i].flags); + } + } + } - qsort(base, cnt, id->is_set8 ? sizeof(uint64_t) : sizeof(int), cmp_id); + pr_debug("sorting addr %5lu: cnt %6d [%s]\n", + off, id->is_set ? set->cnt : set8->cnt, id->name); next = rb_next(next); } diff --git a/tools/iio/iio_utils.c b/tools/iio/iio_utils.c index 6a00a6eecaef02bbb911741fc23e39614d8bdc90..c5c5082cb24e5cd05ed3d5f5a7f12c71d853209f 100644 --- a/tools/iio/iio_utils.c +++ b/tools/iio/iio_utils.c @@ -376,7 +376,7 @@ int build_channel_array(const char *device_dir, int buffer_idx, goto error_close_dir; } - seekdir(dp, 0); + rewinddir(dp); while (ent = readdir(dp), ent) { if (strcmp(ent->d_name + strlen(ent->d_name) - strlen("_en"), "_en") == 0) { diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h index 2f882d5cb30f5c014af5deec2738f8460dcc23ad..72ea363d434db09c06c6acc9ed1855dec7188504 100644 --- a/tools/include/linux/btf_ids.h +++ b/tools/include/linux/btf_ids.h @@ -3,11 +3,22 @@ #ifndef _LINUX_BTF_IDS_H #define _LINUX_BTF_IDS_H +#include /* for u32 */ + struct btf_id_set { u32 cnt; u32 ids[]; }; +struct btf_id_set8 { + u32 cnt; + u32 flags; + struct { + u32 id; + u32 flags; + } pairs[]; +}; + #ifdef CONFIG_DEBUG_INFO_BTF #include /* for __PASTE */ diff --git a/tools/include/linux/compiler_types.h b/tools/include/linux/compiler_types.h index 1bdd834bdd57198059c91222036314403191cdbc..d09f9dc172a486875e2e62cf8550a69f24c9beed 100644 --- a/tools/include/linux/compiler_types.h +++ b/tools/include/linux/compiler_types.h @@ -36,8 +36,8 @@ #include #endif -#ifndef asm_volatile_goto -#define asm_volatile_goto(x...) asm goto(x) +#ifndef asm_goto_output +#define asm_goto_output(x...) asm goto(x) #endif #endif /* __LINUX_COMPILER_TYPES_H */ diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h index 4b0673bf52c2e615017bf2b94da1f6fc4392e532..07cfad817d53908f2325505d2b9cb644a808a689 100644 --- a/tools/include/linux/kernel.h +++ b/tools/include/linux/kernel.h @@ -8,6 +8,7 @@ #include #include #include +#include #include #include diff --git a/tools/include/linux/mm.h b/tools/include/linux/mm.h index 43be27bcc897d03c9bca6843eb4c2ae350a070dd..2f401e8c6c0bb2fd0fb560745e83faea1c1608eb 100644 --- a/tools/include/linux/mm.h +++ b/tools/include/linux/mm.h @@ -37,4 +37,9 @@ static inline void totalram_pages_add(long count) { } +static inline int early_pfn_to_nid(unsigned long pfn) +{ + return 0; +} + #endif diff --git a/tools/include/linux/panic.h b/tools/include/linux/panic.h new file mode 100644 index 0000000000000000000000000000000000000000..9c8f17a41ce8ed965fb1015da3ba6e210ca4344d --- /dev/null +++ b/tools/include/linux/panic.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _TOOLS_LINUX_PANIC_H +#define _TOOLS_LINUX_PANIC_H + +#include +#include +#include + +static inline void panic(const char *fmt, ...) +{ + va_list argp; + + va_start(argp, fmt); + vfprintf(stderr, fmt, argp); + va_end(argp); + exit(-1); +} + +#endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 201dc77ebbd77eb59d0d060c713bc485a4e70507..d5d2183730b9f3863326e07f0b8350aac29dda6e 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3109,6 +3109,10 @@ union bpf_attr { * **BPF_FIB_LOOKUP_DIRECT** * Do a direct table lookup vs full lookup using FIB * rules. + * **BPF_FIB_LOOKUP_TBID** + * Used with BPF_FIB_LOOKUP_DIRECT. + * Use the routing table ID present in *params*->tbid + * for the fib lookup. * **BPF_FIB_LOOKUP_OUTPUT** * Perform lookup from an egress perspective (default is * ingress). @@ -3117,6 +3121,11 @@ union bpf_attr { * and *params*->smac will not be set as output. A common * use case is to call **bpf_redirect_neigh**\ () after * doing **bpf_fib_lookup**\ (). + * **BPF_FIB_LOOKUP_SRC** + * Derive and set source IP addr in *params*->ipv{4,6}_src + * for the nexthop. If the src addr cannot be derived, + * **BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this + * case, *params*->dmac and *params*->smac are not set either. * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -6687,6 +6696,8 @@ enum { BPF_FIB_LOOKUP_DIRECT = (1U << 0), BPF_FIB_LOOKUP_OUTPUT = (1U << 1), BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), + BPF_FIB_LOOKUP_TBID = (1U << 3), + BPF_FIB_LOOKUP_SRC = (1U << 4), }; enum { @@ -6699,6 +6710,7 @@ enum { BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */ BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */ BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */ + BPF_FIB_LKUP_RET_NO_SRC_ADDR, /* failed to derive IP src addr */ }; struct bpf_fib_lookup { @@ -6733,6 +6745,9 @@ struct bpf_fib_lookup { __u32 rt_metric; }; + /* input: source address to consider for lookup + * output: source address result from lookup + */ union { __be32 ipv4_src; __u32 ipv6_src[4]; /* in6_addr; network order */ @@ -6747,9 +6762,19 @@ struct bpf_fib_lookup { __u32 ipv6_dst[4]; /* in6_addr; network order */ }; - /* output */ - __be16 h_vlan_proto; - __be16 h_vlan_TCI; + union { + struct { + /* output */ + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + }; + /* input: when accompanied with the + * 'BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID` flags, a + * specific routing table to use for the fib lookup. + */ + __u32 tbid; + }; + __u8 smac[6]; /* ETH_ALEN */ __u8 dmac[6]; /* ETH_ALEN */ }; diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index fddc05c667b5ded3574e80adc4e6241f7604bf81..874fe362375de7d5b74846bd78f52a884163508b 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -35,7 +35,7 @@ extern "C" { #endif -int libbpf_set_memlock_rlim(size_t memlock_bytes); +LIBBPF_API int libbpf_set_memlock_rlim(size_t memlock_bytes); struct bpf_map_create_opts { size_t sz; /* size of this struct for forward/backward compatibility */ diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index e2014b1250ea2f80562e683165b657a1f76001f6..c71d4d0f5c6f33314c6e4ccf0ab94cd52b66ce49 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -70,6 +70,7 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj); static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog); +static int map_set_def_max_entries(struct bpf_map *map); static const char * const attach_type_name[] = { [BPF_CGROUP_INET_INGRESS] = "cgroup_inet_ingress", @@ -4992,6 +4993,9 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b if (bpf_map_type__is_map_in_map(def->type)) { if (map->inner_map) { + err = map_set_def_max_entries(map->inner_map); + if (err) + return err; err = bpf_object__create_map(obj, map->inner_map, true); if (err) { pr_warn("map '%s': failed to create inner map: %d\n", diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 377642ff51fce597329e771eb73b9785844f3d17..8669f6e0f6e2f7382039e724a6f310cc1b37ebdd 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -17,6 +17,20 @@ #include #include "relo_core.h" +/* Android's libc doesn't support AT_EACCESS in faccessat() implementation + * ([0]), and just returns -EINVAL even if file exists and is accessible. + * See [1] for issues caused by this. + * + * So just redefine it to 0 on Android. + * + * [0] https://android.googlesource.com/platform/bionic/+/refs/heads/android13-release/libc/bionic/faccessat.cpp#50 + * [1] https://github.com/libbpf/libbpf-bootstrap/issues/250#issuecomment-1911324250 + */ +#ifdef __ANDROID__ +#undef AT_EACCESS +#define AT_EACCESS 0 +#endif + /* make sure libbpf doesn't use kernel-only integer typedefs */ #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index 61b637f29b82785b066f2e14a2f8159d186eac9a..b871923c7e5cdf3d0af2aa75fd7a1ec584aab523 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -233,10 +233,10 @@ u64 perf_evlist__read_format(struct perf_evlist *evlist) static void perf_evlist__id_hash(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, u64 id) + int cpu_map_idx, int thread, u64 id) { int hash; - struct perf_sample_id *sid = SID(evsel, cpu, thread); + struct perf_sample_id *sid = SID(evsel, cpu_map_idx, thread); sid->id = id; sid->evsel = evsel; @@ -254,21 +254,27 @@ void perf_evlist__reset_id_hash(struct perf_evlist *evlist) void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, u64 id) + int cpu_map_idx, int thread, u64 id) { - perf_evlist__id_hash(evlist, evsel, cpu, thread, id); + if (!SID(evsel, cpu_map_idx, thread)) + return; + + perf_evlist__id_hash(evlist, evsel, cpu_map_idx, thread, id); evsel->id[evsel->ids++] = id; } int perf_evlist__id_add_fd(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, int fd) + int cpu_map_idx, int thread, int fd) { u64 read_data[4] = { 0, }; int id_idx = 1; /* The first entry is the counter value */ u64 id; int ret; + if (!SID(evsel, cpu_map_idx, thread)) + return -1; + ret = ioctl(fd, PERF_EVENT_IOC_ID, &id); if (!ret) goto add; @@ -297,7 +303,7 @@ int perf_evlist__id_add_fd(struct perf_evlist *evlist, id = read_data[id_idx]; add: - perf_evlist__id_add(evlist, evsel, cpu, thread, id); + perf_evlist__id_add(evlist, evsel, cpu_map_idx, thread, id); return 0; } diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h index 850f07070036c787286590870b7cf328216533ee..cf77db75291b9bb93b2ed0414eb3de711c107eff 100644 --- a/tools/lib/perf/include/internal/evlist.h +++ b/tools/lib/perf/include/internal/evlist.h @@ -127,11 +127,11 @@ u64 perf_evlist__read_format(struct perf_evlist *evlist); void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, u64 id); + int cpu_map_idx, int thread, u64 id); int perf_evlist__id_add_fd(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, int fd); + int cpu_map_idx, int thread, int fd); void perf_evlist__reset_id_hash(struct perf_evlist *evlist); diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 7314183cdcb6c008926e112068ca46b76e9a4ad8..b9b0fda8374e25fcfb372417c0aa5786af17318f 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1785,8 +1785,8 @@ static int record__switch_output(struct record *rec, bool at_exit) { struct perf_data *data = &rec->data; + char *new_filename = NULL; int fd, err; - char *new_filename; /* Same Size: "2015122520103046"*/ char timestamp[] = "InvalidTimestamp"; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 76605fde35078e7c32cfb87125cb8a5bb7010f87..7db35dbdfcefe77217182d173c0e118abae8539d 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -2375,7 +2375,6 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, data->period = evsel->core.attr.sample_period; data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; data->misc = event->header.misc; - data->id = -1ULL; data->data_src = PERF_MEM_DATA_SRC_NONE; data->vcpu = -1; diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index bc866d18973e4da49c1fdbc7c758df640aee5665..ef9a3df4596572652a690583a3a53a9123b5a7f0 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -366,7 +366,7 @@ static void print_metric_only(struct perf_stat_config *config, if (color) mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1; - color_snprintf(str, sizeof(str), color ?: "", fmt, val); + color_snprintf(str, sizeof(str), color ?: "", fmt ?: "", val); fprintf(out, "%*s ", mlen, str); } diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index c9bfe4696943b10e4c8a04abd5ed1a55d6207545..cee7fc3b5bb0c0b731e6a5946b9dbc42ca060168 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -279,13 +279,13 @@ struct perf_thread_map *thread_map__new_by_tid_str(const char *tid_str) threads->nr = ntasks; } out: + strlist__delete(slist); if (threads) refcount_set(&threads->refcnt, 1); return threads; out_free_threads: zfree(&threads); - strlist__delete(slist); goto out; } diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 94aa40f6e3482fc13fe13c70be640a19004f8fdd..9a7bdc0e14cc2d41e4be86fc1de81f9bed145f75 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -45,6 +45,7 @@ static int __report_module(struct addr_location *al, u64 ip, { Dwfl_Module *mod; struct dso *dso = NULL; + Dwarf_Addr base; /* * Some callers will use al->sym, so we can't just use the * cheaper thread__find_map() here. @@ -57,24 +58,36 @@ static int __report_module(struct addr_location *al, u64 ip, if (!dso) return 0; + /* + * The generated JIT DSO files only map the code segment without + * ELF headers. Since JIT codes used to be packed in a memory + * segment, calculating the base address using pgoff falls info + * a different code in another DSO. So just use the map->start + * directly to pick the correct one. + */ + if (!strncmp(dso->long_name, "/tmp/jitted-", 12)) + base = al->map->start; + else + base = al->map->start - al->map->pgoff; + mod = dwfl_addrmodule(ui->dwfl, ip); if (mod) { Dwarf_Addr s; dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL); - if (s != al->map->start - al->map->pgoff) - mod = 0; + if (s != base) + mod = NULL; } if (!mod) mod = dwfl_report_elf(ui->dwfl, dso->short_name, dso->long_name, -1, - al->map->start - al->map->pgoff, false); + base, false); if (!mod) { char filename[PATH_MAX]; if (dso__build_id_filename(dso, filename, sizeof(filename), false)) mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1, - al->map->start - al->map->pgoff, false); + base, false); } if (mod) { diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 81b6bd6e1536ab23053caa47099c5a5edd897ba8..b276e36e3fb414802ef8bcb921b17d42c94da025 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -327,7 +327,7 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct unwind_info *ui, maps__for_each_entry(ui->thread->maps, map) { if (map->dso == dso && map->start < base_addr) - base_addr = map->start; + base_addr = map->start - map->pgoff; } base_addr -= dso->data.elf_base_addr; /* Address of .eh_frame_hdr */ diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index 3e1a4c4be001a4359c21d5c0b78049a82a511286..7112d4732d28763ab59af70c45e411ae1c6ee150 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -370,7 +370,7 @@ below the processor's base frequency. Busy% = MPERF_delta/TSC_delta -Bzy_MHz = TSC_delta/APERF_delta/MPERF_delta/measurement_interval +Bzy_MHz = TSC_delta*APERF_delta/MPERF_delta/measurement_interval Note that these calculations depend on TSC_delta, so they are not reliable during intervals when TSC_MHz is not running at the base frequency. diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index b113900d948793ba5e1836fe8a7f14f863d97c25..a41bad8e653bbe56b035cb2ecbf0b5caae44e3ae 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -53,6 +53,8 @@ #define NAME_BYTES 20 #define PATH_BYTES 128 +#define MAX_NOFILE 0x8000 + enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE }; enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC }; enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT }; @@ -1811,9 +1813,10 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) average.packages.rapl_dram_perf_status += p->rapl_dram_perf_status; for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { - if (mp->format == FORMAT_RAW) - continue; - average.packages.counter[i] += p->counter[i]; + if ((mp->format == FORMAT_RAW) && (topo.num_packages == 0)) + average.packages.counter[i] = p->counter[i]; + else + average.packages.counter[i] += p->counter[i]; } return 0; } @@ -1966,7 +1969,7 @@ unsigned long long get_uncore_mhz(int package, int die) { char path[128]; - sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/current_freq_khz", package, + sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_%02d_die_%02d/current_freq_khz", package, die); return (snapshot_sysfs_counter(path) / 1000); @@ -6718,6 +6721,22 @@ void cmdline(int argc, char **argv) } } +void set_rlimit(void) +{ + struct rlimit limit; + + if (getrlimit(RLIMIT_NOFILE, &limit) < 0) + err(1, "Failed to get rlimit"); + + if (limit.rlim_max < MAX_NOFILE) + limit.rlim_max = MAX_NOFILE; + if (limit.rlim_cur < MAX_NOFILE) + limit.rlim_cur = MAX_NOFILE; + + if (setrlimit(RLIMIT_NOFILE, &limit) < 0) + err(1, "Failed to set rlimit"); +} + int main(int argc, char **argv) { outf = stderr; @@ -6730,6 +6749,9 @@ int main(int argc, char **argv) probe_sysfs(); + if (!getuid()) + set_rlimit(); + turbostat_init(); msr_sum_record(); diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c index 5fd9e594079cfda2bd9b2f3343e5698755993b44..ebda9c366b2ba341085587594c22517a40d52062 100644 --- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c +++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c @@ -1241,6 +1241,7 @@ unsigned int get_pkg_num(int cpu) retval = fscanf(fp, "%d\n", &pkg); if (retval != 1) errx(1, "%s: failed to parse", pathname); + fclose(fp); return pkg; } diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index e6c381498e632b828e7e64ffaf74d5c224fd668e..449e45bd69665c7e826b787284a7e5564a0ddc63 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -836,6 +836,7 @@ sub set_value { if ($lvalue =~ /^(TEST|BISECT|CONFIG_BISECT)_TYPE(\[.*\])?$/ && $prvalue !~ /^(config_|)bisect$/ && $prvalue !~ /^build$/ && + $prvalue !~ /^make_warnings_file$/ && $buildonly) { # Note if a test is something other than build, then we diff --git a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c index d2d9e965eba59fb267f257b5b5089ac453740787..f79815b7e951b3aea442de8b14d7c41702462da6 100644 --- a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c +++ b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c @@ -2,6 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include +#include #include #include "bloom_filter_map.skel.h" @@ -21,6 +22,11 @@ static void test_fail_cases(void) if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid value size 0")) close(fd); + /* Invalid value size: too big */ + fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, INT32_MAX, 100, NULL); + if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid value too large")) + close(fd); + /* Invalid max entries size */ fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(value), 0, NULL); if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid max entries size")) diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c index f416032ba858b48e4fba79dd1d629bd268eb13f5..b295f9b721bf89a08067592d46b91ed8c1956c6f 100644 --- a/tools/testing/selftests/bpf/progs/test_map_in_map.c +++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c @@ -21,6 +21,32 @@ struct { __type(value, __u32); } mim_hash SEC(".maps"); +/* The following three maps are used to test + * perf_event_array map can be an inner + * map of hash/array_of_maps. + */ +struct perf_event_array { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __type(key, __u32); + __type(value, __u32); +} inner_map0 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 1); + __type(key, __u32); + __array(values, struct perf_event_array); +} mim_array_pe SEC(".maps") = { + .values = {&inner_map0}}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __uint(max_entries, 1); + __type(key, __u32); + __array(values, struct perf_event_array); +} mim_hash_pe SEC(".maps") = { + .values = {&inner_map0}}; + SEC("xdp") int xdp_mimtest0(struct xdp_md *ctx) { diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index b73152822aa2822909130cdc6d59ffbb1adc41d6..81cd48cc80c23cdddd0c25d322e964127f14b1b8 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -1190,7 +1190,11 @@ static void test_map_in_map(void) goto out_map_in_map; } - bpf_object__load(obj); + err = bpf_object__load(obj); + if (err) { + printf("Failed to load test prog\n"); + goto out_map_in_map; + } map = bpf_object__find_map_by_name(obj, "mim_array"); if (!map) { diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh index 7bf56ea161e35799ecdcc2b32d2459a38046f8a4..616d3581419ca043fc715f9d067341c89513f6eb 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh @@ -11,7 +11,7 @@ ALL_TESTS="single_mask_test identical_filters_test two_masks_test \ multiple_masks_test ctcam_edge_cases_test delta_simple_test \ delta_two_masks_one_key_test delta_simple_rehash_test \ bloom_simple_test bloom_complex_test bloom_delta_test \ - max_erp_entries_test" + max_erp_entries_test max_group_size_test" NUM_NETIFS=2 source $lib_dir/lib.sh source $lib_dir/tc_common.sh @@ -1033,6 +1033,60 @@ max_erp_entries_test() "max chain $chain_failed, mask $mask_failed" } +max_group_size_test() +{ + # The number of ACLs in an ACL group is limited. Once the maximum + # number of ACLs has been reached, filters cannot be added. This test + # verifies that when this limit is reached, insertion fails without + # crashing. + + RET=0 + + local num_acls=32 + local max_size + local ret + + if [[ "$tcflags" != "skip_sw" ]]; then + return 0; + fi + + for ((i=1; i < $num_acls; i++)); do + if [[ $(( i % 2 )) == 1 ]]; then + tc filter add dev $h2 ingress pref $i proto ipv4 \ + flower $tcflags dst_ip 198.51.100.1/32 \ + ip_proto tcp tcp_flags 0x01/0x01 \ + action drop &> /dev/null + else + tc filter add dev $h2 ingress pref $i proto ipv6 \ + flower $tcflags dst_ip 2001:db8:1::1/128 \ + action drop &> /dev/null + fi + + ret=$? + [[ $ret -ne 0 ]] && max_size=$((i - 1)) && break + done + + # We expect to exceed the maximum number of ACLs in a group, so that + # insertion eventually fails. Otherwise, the test should be adjusted to + # add more filters. + check_fail $ret "expected to exceed number of ACLs in a group" + + for ((; i >= 1; i--)); do + if [[ $(( i % 2 )) == 1 ]]; then + tc filter del dev $h2 ingress pref $i proto ipv4 \ + flower $tcflags dst_ip 198.51.100.1/32 \ + ip_proto tcp tcp_flags 0x01/0x01 \ + action drop &> /dev/null + else + tc filter del dev $h2 ingress pref $i proto ipv6 \ + flower $tcflags dst_ip 2001:db8:1::1/128 \ + action drop &> /dev/null + fi + done + + log_test "max ACL group size test ($tcflags). max size $max_size" +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc index b1ede624986676a554514105936698fdd2b0a915..b7c8f29c09a978895c1176e1a39aeda8c97e8416 100644 --- a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc +++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc @@ -18,7 +18,7 @@ echo 'sched:*' > set_event yield -count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -lt 3 ]; then fail "at least fork, exec and exit events should be recorded" fi @@ -29,7 +29,7 @@ echo 1 > events/sched/enable yield -count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -lt 3 ]; then fail "at least fork, exec and exit events should be recorded" fi @@ -40,7 +40,7 @@ echo 0 > events/sched/enable yield -count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -ne 0 ]; then fail "any of scheduler events should not be recorded" fi diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index b5234d6efbe1509a62ece9670123d22c9eb1ec3e..ec40a33c29fda5af9e8c559a8173d0dee008f50c 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -226,13 +226,15 @@ static void clear_log_create_vm_done(struct kvm_vm *vm) } static void dirty_log_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot, - void *bitmap, uint32_t num_pages) + void *bitmap, uint32_t num_pages, + uint32_t *unused) { kvm_vm_get_dirty_log(vcpu->vm, slot, bitmap); } static void clear_log_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot, - void *bitmap, uint32_t num_pages) + void *bitmap, uint32_t num_pages, + uint32_t *unused) { kvm_vm_get_dirty_log(vcpu->vm, slot, bitmap); kvm_vm_clear_dirty_log(vcpu->vm, slot, bitmap, 0, num_pages); @@ -329,10 +331,9 @@ static void dirty_ring_continue_vcpu(void) } static void dirty_ring_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot, - void *bitmap, uint32_t num_pages) + void *bitmap, uint32_t num_pages, + uint32_t *ring_buf_idx) { - /* We only have one vcpu */ - static uint32_t fetch_index = 0; uint32_t count = 0, cleared; bool continued_vcpu = false; @@ -349,11 +350,15 @@ static void dirty_ring_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot, /* Only have one vcpu */ count = dirty_ring_collect_one(vcpu_map_dirty_ring(vcpu), - slot, bitmap, num_pages, &fetch_index); + slot, bitmap, num_pages, + ring_buf_idx); cleared = kvm_vm_reset_dirty_ring(vcpu->vm); - /* Cleared pages should be the same as collected */ + /* + * Cleared pages should be the same as collected, as KVM is supposed to + * clear only the entries that have been harvested. + */ TEST_ASSERT(cleared == count, "Reset dirty pages (%u) mismatch " "with collected (%u)", cleared, count); @@ -392,12 +397,6 @@ static void dirty_ring_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err) } } -static void dirty_ring_before_vcpu_join(void) -{ - /* Kick another round of vcpu just to make sure it will quit */ - sem_post(&sem_vcpu_cont); -} - struct log_mode { const char *name; /* Return true if this mode is supported, otherwise false */ @@ -406,10 +405,10 @@ struct log_mode { void (*create_vm_done)(struct kvm_vm *vm); /* Hook to collect the dirty pages into the bitmap provided */ void (*collect_dirty_pages) (struct kvm_vcpu *vcpu, int slot, - void *bitmap, uint32_t num_pages); + void *bitmap, uint32_t num_pages, + uint32_t *ring_buf_idx); /* Hook to call when after each vcpu run */ void (*after_vcpu_run)(struct kvm_vcpu *vcpu, int ret, int err); - void (*before_vcpu_join) (void); } log_modes[LOG_MODE_NUM] = { { .name = "dirty-log", @@ -428,7 +427,6 @@ struct log_mode { .supported = dirty_ring_supported, .create_vm_done = dirty_ring_create_vm_done, .collect_dirty_pages = dirty_ring_collect_dirty_pages, - .before_vcpu_join = dirty_ring_before_vcpu_join, .after_vcpu_run = dirty_ring_after_vcpu_run, }, }; @@ -471,13 +469,14 @@ static void log_mode_create_vm_done(struct kvm_vm *vm) } static void log_mode_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot, - void *bitmap, uint32_t num_pages) + void *bitmap, uint32_t num_pages, + uint32_t *ring_buf_idx) { struct log_mode *mode = &log_modes[host_log_mode]; TEST_ASSERT(mode->collect_dirty_pages != NULL, "collect_dirty_pages() is required for any log mode!"); - mode->collect_dirty_pages(vcpu, slot, bitmap, num_pages); + mode->collect_dirty_pages(vcpu, slot, bitmap, num_pages, ring_buf_idx); } static void log_mode_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err) @@ -488,14 +487,6 @@ static void log_mode_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err) mode->after_vcpu_run(vcpu, ret, err); } -static void log_mode_before_vcpu_join(void) -{ - struct log_mode *mode = &log_modes[host_log_mode]; - - if (mode->before_vcpu_join) - mode->before_vcpu_join(); -} - static void generate_random_array(uint64_t *guest_array, uint64_t size) { uint64_t i; @@ -696,6 +687,8 @@ static void run_test(enum vm_guest_mode mode, void *arg) struct kvm_vcpu *vcpu; struct kvm_vm *vm; unsigned long *bmap; + uint32_t ring_buf_idx = 0; + int sem_val; if (!log_mode_supported()) { print_skip("Log mode '%s' not supported", @@ -767,10 +760,21 @@ static void run_test(enum vm_guest_mode mode, void *arg) /* Start the iterations */ iteration = 1; sync_global_to_guest(vm, iteration); - host_quit = false; + WRITE_ONCE(host_quit, false); host_dirty_count = 0; host_clear_count = 0; host_track_next_count = 0; + WRITE_ONCE(dirty_ring_vcpu_ring_full, false); + + /* + * Ensure the previous iteration didn't leave a dangling semaphore, i.e. + * that the main task and vCPU worker were synchronized and completed + * verification of all iterations. + */ + sem_getvalue(&sem_vcpu_stop, &sem_val); + TEST_ASSERT_EQ(sem_val, 0); + sem_getvalue(&sem_vcpu_cont, &sem_val); + TEST_ASSERT_EQ(sem_val, 0); pthread_create(&vcpu_thread, NULL, vcpu_worker, vcpu); @@ -778,7 +782,8 @@ static void run_test(enum vm_guest_mode mode, void *arg) /* Give the vcpu thread some time to dirty some pages */ usleep(p->interval * 1000); log_mode_collect_dirty_pages(vcpu, TEST_MEM_SLOT_INDEX, - bmap, host_num_pages); + bmap, host_num_pages, + &ring_buf_idx); /* * See vcpu_sync_stop_requested definition for details on why @@ -796,15 +801,21 @@ static void run_test(enum vm_guest_mode mode, void *arg) assert(host_log_mode == LOG_MODE_DIRTY_RING || atomic_read(&vcpu_sync_stop_requested) == false); vm_dirty_log_verify(mode, bmap); - sem_post(&sem_vcpu_cont); - iteration++; + /* + * Set host_quit before sem_vcpu_cont in the final iteration to + * ensure that the vCPU worker doesn't resume the guest. As + * above, the dirty ring test may stop and wait even when not + * explicitly request to do so, i.e. would hang waiting for a + * "continue" if it's allowed to resume the guest. + */ + if (++iteration == p->iterations) + WRITE_ONCE(host_quit, true); + + sem_post(&sem_vcpu_cont); sync_global_to_guest(vm, iteration); } - /* Tell the vcpu thread to quit */ - host_quit = true; - log_mode_before_vcpu_join(); pthread_join(vcpu_thread, NULL); pr_info("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), " diff --git a/tools/testing/selftests/mqueue/setting b/tools/testing/selftests/mqueue/setting new file mode 100644 index 0000000000000000000000000000000000000000..a953c96aa16e1e814867b33d06e894ffb664bb1b --- /dev/null +++ b/tools/testing/selftests/mqueue/setting @@ -0,0 +1 @@ +timeout=180 diff --git a/tools/testing/selftests/net/cmsg_ipv6.sh b/tools/testing/selftests/net/cmsg_ipv6.sh index 330d0b1ceced3de3bf34c45821cc8a310d06f0bf..c921750ca118ded06c1012f4bad54dd7f66f77cd 100755 --- a/tools/testing/selftests/net/cmsg_ipv6.sh +++ b/tools/testing/selftests/net/cmsg_ipv6.sh @@ -91,7 +91,7 @@ for ovr in setsock cmsg both diff; do check_result $? 0 "TCLASS $prot $ovr - pass" while [ -d /proc/$BG ]; do - $NSEXE ./cmsg_sender -6 -p u $TGT6 1234 + $NSEXE ./cmsg_sender -6 -p $p $m $((TOS2)) $TGT6 1234 done tcpdump -r $TMPF -v 2>&1 | grep "class $TOS2" >> /dev/null @@ -128,7 +128,7 @@ for ovr in setsock cmsg both diff; do check_result $? 0 "HOPLIMIT $prot $ovr - pass" while [ -d /proc/$BG ]; do - $NSEXE ./cmsg_sender -6 -p u $TGT6 1234 + $NSEXE ./cmsg_sender -6 -p $p $m $LIM $TGT6 1234 done tcpdump -r $TMPF -v 2>&1 | grep "hlim $LIM[^0-9]" >> /dev/null diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config index 697994a9278bbe50edc5bfeca33af9eeb7565544..8d7a1a004b7c34397ab192266c4275c78538e71b 100644 --- a/tools/testing/selftests/net/forwarding/config +++ b/tools/testing/selftests/net/forwarding/config @@ -6,14 +6,49 @@ CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_NET_VRF=m CONFIG_BPF_SYSCALL=y CONFIG_CGROUP_BPF=y +CONFIG_DUMMY=m +CONFIG_IPV6=y +CONFIG_IPV6_GRE=m +CONFIG_IPV6_MROUTE=y +CONFIG_IPV6_MROUTE_MULTIPLE_TABLES=y +CONFIG_IPV6_PIMSM_V2=y +CONFIG_IP_MROUTE=y +CONFIG_IP_MROUTE_MULTIPLE_TABLES=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y +CONFIG_MACVLAN=m CONFIG_NET_ACT_CT=m CONFIG_NET_ACT_MIRRED=m CONFIG_NET_ACT_MPLS=m +CONFIG_NET_ACT_PEDIT=m +CONFIG_NET_ACT_POLICE=m +CONFIG_NET_ACT_SAMPLE=m +CONFIG_NET_ACT_SKBEDIT=m +CONFIG_NET_ACT_TUNNEL_KEY=m CONFIG_NET_ACT_VLAN=m CONFIG_NET_CLS_FLOWER=m CONFIG_NET_CLS_MATCHALL=m +CONFIG_NET_CLS_BASIC=m +CONFIG_NET_EMATCH=y +CONFIG_NET_EMATCH_META=m +CONFIG_NET_IPGRE=m +CONFIG_NET_IPGRE_DEMUX=m +CONFIG_NET_IPIP=m +CONFIG_NET_SCH_ETS=m CONFIG_NET_SCH_INGRESS=m CONFIG_NET_ACT_GACT=m +CONFIG_NET_SCH_PRIO=m +CONFIG_NET_SCH_RED=m +CONFIG_NET_SCH_TBF=m +CONFIG_NET_TC_SKB_EXT=y +CONFIG_NET_TEAM=y +CONFIG_NET_TEAM_MODE_LOADBALANCE=y +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=m +CONFIG_NF_FLOW_TABLE=m +CONFIG_NF_TABLES=m CONFIG_VETH=m CONFIG_NAMESPACES=y CONFIG_NET_NS=y +CONFIG_VXLAN=m +CONFIG_XFRM_USER=m diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh index ac97f07e5ce8267441653e359a5caf16a47cbba7..bd3f7d492af2bb5d7b1044e46453309bdad3d4bd 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh @@ -354,7 +354,7 @@ __ping_ipv4() # Send 100 packets and verify that at least 100 packets hit the rule, # to overcome ARP noise. - PING_COUNT=100 PING_TIMEOUT=11 ping_do $dev $dst_ip + PING_COUNT=100 PING_TIMEOUT=20 ping_do $dev $dst_ip check_err $? "Ping failed" tc_check_at_least_x_packets "dev $rp1 egress" 101 10 100 @@ -410,7 +410,7 @@ __ping_ipv6() # Send 100 packets and verify that at least 100 packets hit the rule, # to overcome neighbor discovery noise. - PING_COUNT=100 PING_TIMEOUT=11 ping6_do $dev $dst_ip + PING_COUNT=100 PING_TIMEOUT=20 ping6_do $dev $dst_ip check_err $? "Ping failed" tc_check_at_least_x_packets "dev $rp1 egress" 101 100 diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_ipv6.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_ipv6.sh index d880df89bc8bd51bca702736bad069aa2639f169..e83fde79f40d0f5bc31353a05714e7fd123fc8f8 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_ipv6.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_ipv6.sh @@ -457,7 +457,7 @@ __ping_ipv4() # Send 100 packets and verify that at least 100 packets hit the rule, # to overcome ARP noise. - PING_COUNT=100 PING_TIMEOUT=11 ping_do $dev $dst_ip + PING_COUNT=100 PING_TIMEOUT=20 ping_do $dev $dst_ip check_err $? "Ping failed" tc_check_at_least_x_packets "dev $rp1 egress" 101 10 100 @@ -522,7 +522,7 @@ __ping_ipv6() # Send 100 packets and verify that at least 100 packets hit the rule, # to overcome neighbor discovery noise. - PING_COUNT=100 PING_TIMEOUT=11 ping6_do $dev $dst_ip + PING_COUNT=100 PING_TIMEOUT=20 ping6_do $dev $dst_ip check_err $? "Ping failed" tc_check_at_least_x_packets "dev $rp1 egress" 101 100 diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config index e317c2e44dae840149fad7fe14a3a41d699b063e..4f80014cae4940a3f56ebb313349baa8540c0a0a 100644 --- a/tools/testing/selftests/net/mptcp/config +++ b/tools/testing/selftests/net/mptcp/config @@ -22,8 +22,11 @@ CONFIG_NFT_TPROXY=m CONFIG_NFT_SOCKET=m CONFIG_IP_ADVANCED_ROUTER=y CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_IP6_NF_FILTER=m CONFIG_NET_ACT_CSUM=m CONFIG_NET_ACT_PEDIT=m CONFIG_NET_CLS_ACT=y diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index 400cf1ce96e31d434fe8324ca831c132b3569b4e..3df4a8103c76fec9500a6abb59e38faa75fc3dee 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -56,7 +56,7 @@ __chk_nr() echo "[ skip ] Feature probably not supported" else echo "[ fail ] expected $expected found $nr" - ret=$test_cnt + ret=${KSFT_FAIL} fi else echo "[ ok ]" @@ -100,10 +100,10 @@ wait_msk_nr() printf "%-50s" "$msg" if [ $i -ge $timeout ]; then echo "[ fail ] timeout while expecting $expected max $max last $nr" - ret=$test_cnt + ret=${KSFT_FAIL} elif [ $nr != $expected ]; then echo "[ fail ] expected $expected found $nr" - ret=$test_cnt + ret=${KSFT_FAIL} else echo "[ ok ]" fi diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 18c9b00ca058ea957bf88f42d15b1d1cbfb6f67a..dacf4cf2246daf0f2b28f4449b1da0f8685edfd6 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -439,6 +439,7 @@ do_transfer() local stat_cookierx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv") local stat_csum_err_s=$(get_mib_counter "${listener_ns}" "MPTcpExtDataCsumErr") local stat_csum_err_c=$(get_mib_counter "${connector_ns}" "MPTcpExtDataCsumErr") + local stat_tcpfb_last_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") timeout ${timeout_test} \ ip netns exec ${listener_ns} \ @@ -504,6 +505,7 @@ do_transfer() local stat_cookietx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent") local stat_cookierx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv") local stat_ooo_now=$(get_mib_counter "${listener_ns}" "TcpExtTCPOFOQueue") + local stat_tcpfb_now_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") expect_synrx=$((stat_synrx_last_l)) expect_ackrx=$((stat_ackrx_last_l)) @@ -548,6 +550,11 @@ do_transfer() fi fi + if [ ${stat_ooo_now} -eq 0 ] && [ ${stat_tcpfb_last_l} -ne ${stat_tcpfb_now_l} ]; then + printf "[ FAIL ]\nunexpected fallback to TCP" + rets=1 + fi + if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then printf "[ OK ]" fi diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 2107579e2939d9a6004efc5589d8fc6f1a87c717..635a1624b47dc5e84bf32d5b16a4357f9fdae604 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -144,6 +144,11 @@ check_tools() exit $ksft_skip fi + if ! ss -h | grep -q MPTCP; then + echo "SKIP: ss tool does not support MPTCP" + exit $ksft_skip + fi + # Use the legacy version if available to support old kernel versions if iptables-legacy -V &> /dev/null; then iptables="iptables-legacy" @@ -720,7 +725,7 @@ pm_nl_check_endpoint() [ -n "$_flags" ]; flags="flags $_flags" shift elif [ $1 = "dev" ]; then - [ -n "$2" ]; dev="dev $1" + [ -n "$2" ]; dev="dev $2" shift elif [ $1 = "id" ]; then _id=$2 @@ -1766,7 +1771,10 @@ chk_rm_nr() # in case of simult flush, the subflow removal count on each side is # unreliable count=$((count + cnt)) - [ "$count" != "$rm_subflow_nr" ] && suffix="$count in [$rm_subflow_nr:$((rm_subflow_nr*2))]" + if [ "$count" != "$rm_subflow_nr" ]; then + suffix="$count in [$rm_subflow_nr:$((rm_subflow_nr*2))]" + extra_msg="$extra_msg simult" + fi if [ $count -ge "$rm_subflow_nr" ] && \ [ "$count" -le "$((rm_subflow_nr *2 ))" ]; then echo -n "[ ok ] $suffix" diff --git a/tools/testing/selftests/net/mptcp/settings b/tools/testing/selftests/net/mptcp/settings index 79b65bdf05db6586726cc76d3313f12368d21dc5..abc5648b59abde537dca90791404691050c759e2 100644 --- a/tools/testing/selftests/net/mptcp/settings +++ b/tools/testing/selftests/net/mptcp/settings @@ -1 +1 @@ -timeout=1200 +timeout=1800 diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 4a417f9d51d67cf8f169e03789612cdffc82a525..06ad0510469e39148bdb2ecd89d82ae7b2b9eb01 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -301,10 +301,10 @@ done setup run_test 10 10 0 0 "balanced bwidth" -run_test 10 10 1 50 "balanced bwidth with unbalanced delay" +run_test 10 10 1 25 "balanced bwidth with unbalanced delay" # we still need some additional infrastructure to pass the following test-cases -run_test 30 10 0 0 "unbalanced bwidth" -run_test 30 10 1 50 "unbalanced bwidth with unbalanced delay" -run_test 30 10 50 1 "unbalanced bwidth with opposed, unbalanced delay" +run_test 10 3 0 0 "unbalanced bwidth" +run_test 10 3 1 25 "unbalanced bwidth with unbalanced delay" +run_test 10 3 25 1 "unbalanced bwidth with opposed, unbalanced delay" exit $ret diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 1b6e484e586dcbae980b3ab2daa657e2596abbc8..00ab4c6e404468a942f456f1a9f2d5fef0d992dd 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -1928,6 +1928,13 @@ check_command() { return 0 } +check_running() { + pid=${1} + cmd=${2} + + [ "$(cat /proc/${pid}/cmdline 2>/dev/null | tr -d '\0')" = "{cmd}" ] +} + test_cleanup_vxlanX_exception() { outer="${1}" encap="vxlan" @@ -1958,11 +1965,12 @@ test_cleanup_vxlanX_exception() { ${ns_a} ip link del dev veth_A-R1 & iplink_pid=$! - sleep 1 - if [ "$(cat /proc/${iplink_pid}/cmdline 2>/dev/null | tr -d '\0')" = "iplinkdeldevveth_A-R1" ]; then - err " can't delete veth device in a timely manner, PMTU dst likely leaked" - return 1 - fi + for i in $(seq 1 20); do + check_running ${iplink_pid} "iplinkdeldevveth_A-R1" || return 0 + sleep 0.1 + done + err " can't delete veth device in a timely manner, PMTU dst likely leaked" + return 1 } test_cleanup_ipv6_exception() { diff --git a/tools/testing/selftests/net/reuseaddr_conflict.c b/tools/testing/selftests/net/reuseaddr_conflict.c index 7c5b12664b03b04b62b5060fd6e447e4ae67b89d..bfb07dc495186d86866ce395f49a78190b43353d 100644 --- a/tools/testing/selftests/net/reuseaddr_conflict.c +++ b/tools/testing/selftests/net/reuseaddr_conflict.c @@ -109,6 +109,6 @@ int main(void) 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"); + fprintf(stderr, "Success\n"); return 0; } diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 5b80fb155d549eedf503e9d8ed76153eb162bd14..d89ee6e1926c7e427ae81984da64ea49870ab618 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -926,12 +926,12 @@ TEST_F(tls, recv_partial) memset(recv_mem, 0, sizeof(recv_mem)); EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); - EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_first), - MSG_WAITALL), -1); + EXPECT_EQ(recv(self->cfd, recv_mem, strlen(test_str_first), + MSG_WAITALL), strlen(test_str_first)); EXPECT_EQ(memcmp(test_str_first, recv_mem, strlen(test_str_first)), 0); memset(recv_mem, 0, sizeof(recv_mem)); - EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_second), - MSG_WAITALL), -1); + EXPECT_EQ(recv(self->cfd, recv_mem, strlen(test_str_second), + MSG_WAITALL), strlen(test_str_second)); EXPECT_EQ(memcmp(test_str_second, recv_mem, strlen(test_str_second)), 0); } diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh index c079565add39224eb99e011f941b6f0a11c1648c..9e9b4644e0ea35039f2417678868064442583b7a 100755 --- a/tools/testing/selftests/net/udpgro_fwd.sh +++ b/tools/testing/selftests/net/udpgro_fwd.sh @@ -37,6 +37,10 @@ create_ns() { for ns in $NS_SRC $NS_DST; do ip netns add $ns ip -n $ns link set dev lo up + + # disable route solicitations to decrease 'noise' traffic + ip netns exec $ns sysctl -qw net.ipv6.conf.default.router_solicitations=0 + ip netns exec $ns sysctl -qw net.ipv6.conf.all.router_solicitations=0 done ip link add name veth$SRC type veth peer name veth$DST @@ -78,6 +82,12 @@ create_vxlan_pair() { create_vxlan_endpoint $BASE$ns veth$ns $BM_NET_V6$((3 - $ns)) vxlan6$ns 6 ip -n $BASE$ns addr add dev vxlan6$ns $OL_NET_V6$ns/24 nodad done + + # preload neighbur cache, do avoid some noisy traffic + local addr_dst=$(ip -j -n $BASE$DST link show dev vxlan6$DST |jq -r '.[]["address"]') + local addr_src=$(ip -j -n $BASE$SRC link show dev vxlan6$SRC |jq -r '.[]["address"]') + ip -n $BASE$DST neigh add dev vxlan6$DST lladdr $addr_src $OL_NET_V6$SRC + ip -n $BASE$SRC neigh add dev vxlan6$SRC lladdr $addr_dst $OL_NET_V6$DST } is_ipv6() { @@ -117,7 +127,7 @@ run_test() { # not enable GRO ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 4789 ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 8000 - ip netns exec $NS_DST ./udpgso_bench_rx -C 1000 -R 10 -n 10 -l 1300 $rx_args & + ip netns exec $NS_DST ./udpgso_bench_rx -C 2000 -R 100 -n 10 -l 1300 $rx_args & local spid=$! sleep 0.1 ip netns exec $NS_SRC ./udpgso_bench_tx $family -M 1 -s 13000 -S 1300 -D $dst @@ -166,7 +176,7 @@ run_bench() { # bind the sender and the receiver to different CPUs to try # get reproducible results ip netns exec $NS_DST bash -c "echo 2 > /sys/class/net/veth$DST/queues/rx-0/rps_cpus" - ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 1000 -R 10 & + ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 2000 -R 100 & local spid=$! sleep 0.1 ip netns exec $NS_SRC taskset 0x1 ./udpgso_bench_tx $family -l 3 -S 1300 -D $dst @@ -229,7 +239,7 @@ for family in 4 6; do create_vxlan_pair ip netns exec $NS_DST ethtool -K veth$DST rx-gro-list on - run_test "GRO frag list over UDP tunnel" $OL_NET$DST 1 1 + run_test "GRO frag list over UDP tunnel" $OL_NET$DST 10 10 cleanup # use NAT to circumvent GRO FWD check @@ -242,13 +252,7 @@ for family in 4 6; do # load arp cache before running the test to reduce the amount of # stray traffic on top of the UDP tunnel ip netns exec $NS_SRC $PING -q -c 1 $OL_NET$DST_NAT >/dev/null - run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 1 1 $OL_NET$DST - cleanup - - create_vxlan_pair - run_bench "UDP tunnel fwd perf" $OL_NET$DST - ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on - run_bench "UDP tunnel GRO fwd perf" $OL_NET$DST + run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 10 10 $OL_NET$DST cleanup done diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index f35a924d4a3030780447f2cc137f6ff373ed693c..1cbadd267c963c0c067308d3fb16493625e8f1b7 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -375,7 +375,7 @@ static void do_recv(void) do_flush_udp(fd); tnow = gettimeofday_ms(); - if (tnow > treport) { + if (!cfg_expected_pkt_nr && tnow > treport) { if (packets) fprintf(stderr, "%s rx: %6lu MB/s %8lu calls/s\n", diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/atm.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/atm.json deleted file mode 100644 index f5bc8670a67d1d3eaa36be8009746bf32101b362..0000000000000000000000000000000000000000 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/atm.json +++ /dev/null @@ -1,94 +0,0 @@ -[ - { - "id": "7628", - "name": "Create ATM with default setting", - "category": [ - "qdisc", - "atm" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root atm", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc atm 1: root refcnt", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "390a", - "name": "Delete ATM with valid handle", - "category": [ - "qdisc", - "atm" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true", - "$TC qdisc add dev $DUMMY handle 1: root atm" - ], - "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc atm 1: root refcnt", - "matchCount": "0", - "teardown": [ - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "32a0", - "name": "Show ATM class", - "category": [ - "qdisc", - "atm" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root atm", - "expExitCode": "0", - "verifyCmd": "$TC class show dev $DUMMY", - "matchPattern": "class atm 1: parent 1:", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "6310", - "name": "Dump ATM stats", - "category": [ - "qdisc", - "atm" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root atm", - "expExitCode": "0", - "verifyCmd": "$TC -s qdisc show dev $DUMMY", - "matchPattern": "qdisc atm 1: root refcnt", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - } -] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/cbq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/cbq.json deleted file mode 100644 index 1ab21c83a1223863459876560cfc2e485725de54..0000000000000000000000000000000000000000 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/cbq.json +++ /dev/null @@ -1,184 +0,0 @@ -[ - { - "id": "3460", - "name": "Create CBQ with default setting", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "0592", - "name": "Create CBQ with mpu", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000 mpu 1000", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "4684", - "name": "Create CBQ with valid cell num", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000 cell 128", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "4345", - "name": "Create CBQ with invalid cell num", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000 cell 100", - "expExitCode": "1", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "0", - "teardown": [ - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "4525", - "name": "Create CBQ with valid ewma", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000 ewma 16", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "6784", - "name": "Create CBQ with invalid ewma", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000 ewma 128", - "expExitCode": "1", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "0", - "teardown": [ - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "5468", - "name": "Delete CBQ with handle", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true", - "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000" - ], - "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc cbq 1: root refcnt [0-9]+ rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "0", - "teardown": [ - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "492a", - "name": "Show CBQ class", - "category": [ - "qdisc", - "cbq" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root cbq bandwidth 10000 avpkt 9000", - "expExitCode": "0", - "verifyCmd": "$TC class show dev $DUMMY", - "matchPattern": "class cbq 1: root rate 10Kbit \\(bounded,isolated\\) prio no-transmit", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - } -] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dsmark.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dsmark.json deleted file mode 100644 index c030795f9c37d4405904d3875b187c912f1e4e47..0000000000000000000000000000000000000000 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dsmark.json +++ /dev/null @@ -1,140 +0,0 @@ -[ - { - "id": "6345", - "name": "Create DSMARK with default setting", - "category": [ - "qdisc", - "dsmark" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dsmark indices 1024", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc dsmark 1: root refcnt [0-9]+ indices 0x0400", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "3462", - "name": "Create DSMARK with default_index setting", - "category": [ - "qdisc", - "dsmark" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dsmark indices 1024 default_index 512", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc dsmark 1: root refcnt [0-9]+ indices 0x0400 default_index 0x0200", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "ca95", - "name": "Create DSMARK with set_tc_index flag", - "category": [ - "qdisc", - "dsmark" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dsmark indices 1024 set_tc_index", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc dsmark 1: root refcnt [0-9]+ indices 0x0400 set_tc_index", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "a950", - "name": "Create DSMARK with multiple setting", - "category": [ - "qdisc", - "dsmark" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dsmark indices 1024 default_index 1024 set_tc_index", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc dsmark 1: root refcnt [0-9]+ indices 0x0400 default_index 0x0400 set_tc_index", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "4092", - "name": "Delete DSMARK with handle", - "category": [ - "qdisc", - "dsmark" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true", - "$TC qdisc add dev $DUMMY handle 1: root dsmark indices 1024 default_index 1024" - ], - "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 1: root", - "expExitCode": "0", - "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc dsmark 1: root refcnt [0-9]+ indices 0x0400", - "matchCount": "0", - "teardown": [ - "$IP link del dev $DUMMY type dummy" - ] - }, - { - "id": "5930", - "name": "Show DSMARK class", - "category": [ - "qdisc", - "dsmark" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$IP link add dev $DUMMY type dummy || /bin/true" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dsmark indices 1024", - "expExitCode": "0", - "verifyCmd": "$TC class show dev $DUMMY", - "matchPattern": "class dsmark 1:", - "matchCount": "0", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1: root", - "$IP link del dev $DUMMY type dummy" - ] - } -] diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c index 0ba500056e635be0f5d4ca88827a163c053cc31c..193a984f512c3920d8186fea285dec0711e33994 100644 --- a/tools/testing/selftests/timers/posix_timers.c +++ b/tools/testing/selftests/timers/posix_timers.c @@ -66,7 +66,7 @@ static int check_diff(struct timeval start, struct timeval end) diff = end.tv_usec - start.tv_usec; diff += (end.tv_sec - start.tv_sec) * USECS_PER_SEC; - if (abs(diff - DELAY * USECS_PER_SEC) > USECS_PER_SEC / 2) { + if (llabs(diff - DELAY * USECS_PER_SEC) > USECS_PER_SEC / 2) { printf("Diff too high: %lld..", diff); return -1; } diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c index 48b9a803235a80413f0d94d9eb841d9f045779e8..d13ebde203221ae3fa81835fae684c8e180cf111 100644 --- a/tools/testing/selftests/timers/valid-adjtimex.c +++ b/tools/testing/selftests/timers/valid-adjtimex.c @@ -21,9 +21,6 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. */ - - - #include #include #include @@ -62,45 +59,47 @@ int clear_time_state(void) #define NUM_FREQ_OUTOFRANGE 4 #define NUM_FREQ_INVALID 2 +#define SHIFTED_PPM (1 << 16) + long valid_freq[NUM_FREQ_VALID] = { - -499<<16, - -450<<16, - -400<<16, - -350<<16, - -300<<16, - -250<<16, - -200<<16, - -150<<16, - -100<<16, - -75<<16, - -50<<16, - -25<<16, - -10<<16, - -5<<16, - -1<<16, + -499 * SHIFTED_PPM, + -450 * SHIFTED_PPM, + -400 * SHIFTED_PPM, + -350 * SHIFTED_PPM, + -300 * SHIFTED_PPM, + -250 * SHIFTED_PPM, + -200 * SHIFTED_PPM, + -150 * SHIFTED_PPM, + -100 * SHIFTED_PPM, + -75 * SHIFTED_PPM, + -50 * SHIFTED_PPM, + -25 * SHIFTED_PPM, + -10 * SHIFTED_PPM, + -5 * SHIFTED_PPM, + -1 * SHIFTED_PPM, -1000, - 1<<16, - 5<<16, - 10<<16, - 25<<16, - 50<<16, - 75<<16, - 100<<16, - 150<<16, - 200<<16, - 250<<16, - 300<<16, - 350<<16, - 400<<16, - 450<<16, - 499<<16, + 1 * SHIFTED_PPM, + 5 * SHIFTED_PPM, + 10 * SHIFTED_PPM, + 25 * SHIFTED_PPM, + 50 * SHIFTED_PPM, + 75 * SHIFTED_PPM, + 100 * SHIFTED_PPM, + 150 * SHIFTED_PPM, + 200 * SHIFTED_PPM, + 250 * SHIFTED_PPM, + 300 * SHIFTED_PPM, + 350 * SHIFTED_PPM, + 400 * SHIFTED_PPM, + 450 * SHIFTED_PPM, + 499 * SHIFTED_PPM, }; long outofrange_freq[NUM_FREQ_OUTOFRANGE] = { - -1000<<16, - -550<<16, - 550<<16, - 1000<<16, + -1000 * SHIFTED_PPM, + -550 * SHIFTED_PPM, + 550 * SHIFTED_PPM, + 1000 * SHIFTED_PPM, }; #define LONG_MAX (~0UL>>1) diff --git a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh index 0899019a7fcb4b04bcedca44227f2c2dd5a83597..e14bdd4455f2d2798077b8a701790bcee0732e90 100644 --- a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh +++ b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # Kselftest framework requirement - SKIP code is 4. diff --git a/tools/testing/selftests/vm/ksm_tests.c b/tools/testing/selftests/vm/ksm_tests.c index 0d85be2350fa36a6e982d14edf6d2c0740413a10..a811659307855d4449eb859dad8897c5027dd166 100644 --- a/tools/testing/selftests/vm/ksm_tests.c +++ b/tools/testing/selftests/vm/ksm_tests.c @@ -470,7 +470,7 @@ static int ksm_merge_hugepages_time(int mapping, int prot, int timeout, size_t m if (map_ptr_orig == MAP_FAILED) err(2, "initial mmap"); - if (madvise(map_ptr, len + HPAGE_SIZE, MADV_HUGEPAGE)) + if (madvise(map_ptr, len, MADV_HUGEPAGE)) err(2, "MADV_HUGEPAGE"); pagemap_fd = open("/proc/self/pagemap", O_RDONLY); diff --git a/tools/testing/selftests/vm/map_hugetlb.c b/tools/testing/selftests/vm/map_hugetlb.c index 312889edb84ab799ed6ef99b5d6b15cca57542ae..c65c55b7a789f3cea85691207e8ca35e9443c09c 100644 --- a/tools/testing/selftests/vm/map_hugetlb.c +++ b/tools/testing/selftests/vm/map_hugetlb.c @@ -15,6 +15,7 @@ #include #include #include +#include "vm_util.h" #define LENGTH (256UL*1024*1024) #define PROTECTION (PROT_READ | PROT_WRITE) @@ -70,10 +71,16 @@ int main(int argc, char **argv) { void *addr; int ret; + size_t hugepage_size; size_t length = LENGTH; int flags = FLAGS; int shift = 0; + hugepage_size = default_huge_page_size(); + /* munmap with fail if the length is not page aligned */ + if (hugepage_size > length) + length = hugepage_size; + if (argc > 1) length = atol(argv[1]) << 20; if (argc > 2) { diff --git a/tools/testing/selftests/vm/va_128TBswitch.sh b/tools/testing/selftests/vm/va_128TBswitch.sh index 41580751dc5113d9e853c833e7fbcec541655b42..231622b3a2327567bfd1d542d3d434a3dc74e3f3 100755 --- a/tools/testing/selftests/vm/va_128TBswitch.sh +++ b/tools/testing/selftests/vm/va_128TBswitch.sh @@ -29,9 +29,15 @@ check_supported_x86_64() # See man 1 gzip under '-f'. local pg_table_levels=$(gzip -dcfq "${config}" | grep PGTABLE_LEVELS | cut -d'=' -f 2) + local cpu_supports_pl5=$(awk '/^flags/ {if (/la57/) {print 0;} + else {print 1}; exit}' /proc/cpuinfo 2>/dev/null) + if [[ "${pg_table_levels}" -lt 5 ]]; then echo "$0: PGTABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test" exit $ksft_skip + elif [[ "${cpu_supports_pl5}" -ne 0 ]]; then + echo "$0: CPU does not have the necessary la57 flag to support page table level 5" + exit $ksft_skip fi } diff --git a/tools/testing/selftests/vm/write_hugetlb_memory.sh b/tools/testing/selftests/vm/write_hugetlb_memory.sh index 70a02301f4c276ba6313c3baa1ab3b5058a68b0c..3d2d2eb9d6fff077cca24fd82a2a4990c34706d1 100644 --- a/tools/testing/selftests/vm/write_hugetlb_memory.sh +++ b/tools/testing/selftests/vm/write_hugetlb_memory.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile index 22e28b76f80048f12302d034576a85e1a38f912a..6912e9577b658a7790bed6c9574072d5579e6c45 100644 --- a/tools/tracing/rtla/Makefile +++ b/tools/tracing/rtla/Makefile @@ -28,10 +28,15 @@ FOPTS := -flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong \ -fasynchronous-unwind-tables -fstack-clash-protection WOPTS := -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized +ifeq ($(CC),clang) + FOPTS := $(filter-out -ffat-lto-objects, $(FOPTS)) + WOPTS := $(filter-out -Wno-maybe-uninitialized, $(WOPTS)) +endif + TRACEFS_HEADERS := $$($(PKG_CONFIG) --cflags libtracefs) CFLAGS := -O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS) $(EXTRA_CFLAGS) -LDFLAGS := -ggdb $(EXTRA_LDFLAGS) +LDFLAGS := -flto=auto -ggdb $(EXTRA_LDFLAGS) LIBS := $$($(PKG_CONFIG) --libs libtracefs) SRC := $(wildcard src/*.c) diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c index fe34452fc4ec0a68fc2e543eb1c20602d7142bae..b9658f213cb55d65f0fed83d67f0c0c920a23370 100644 --- a/tools/tracing/rtla/src/osnoise_hist.c +++ b/tools/tracing/rtla/src/osnoise_hist.c @@ -129,8 +129,7 @@ static void osnoise_hist_update_multiple(struct osnoise_tool *tool, int cpu, if (params->output_divisor) duration = duration / params->output_divisor; - if (data->bucket_size) - bucket = duration / data->bucket_size; + bucket = duration / data->bucket_size; total_duration = duration * count; @@ -472,7 +471,11 @@ static void osnoise_hist_usage(char *usage) for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); - exit(1); + + if (usage) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); } /* diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c index 76479bfb292244b0e61fc4b79ffdfe694e770193..6c07f360de72c211e8e4062f163df8518ed3716c 100644 --- a/tools/tracing/rtla/src/osnoise_top.c +++ b/tools/tracing/rtla/src/osnoise_top.c @@ -282,7 +282,11 @@ void osnoise_top_usage(char *usage) for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); - exit(1); + + if (usage) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); } /* diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c index 4b48af8a8309614f94451e5597a7d7f686f7981d..ed08295bfa12c85467bfa5af08a9d6d5183d8486 100644 --- a/tools/tracing/rtla/src/timerlat_hist.c +++ b/tools/tracing/rtla/src/timerlat_hist.c @@ -151,8 +151,7 @@ timerlat_hist_update(struct osnoise_tool *tool, int cpu, if (params->output_divisor) latency = latency / params->output_divisor; - if (data->bucket_size) - bucket = latency / data->bucket_size; + bucket = latency / data->bucket_size; if (!thread) { hist = data->hist[cpu].irq; @@ -475,7 +474,11 @@ static void timerlat_hist_usage(char *usage) for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); - exit(1); + + if (usage) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); } /* diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c index 3342719352222e0911be9c914ca339e2121b6691..8fc0f6aa19dad7ebc44fbf95320991831271091f 100644 --- a/tools/tracing/rtla/src/timerlat_top.c +++ b/tools/tracing/rtla/src/timerlat_top.c @@ -305,7 +305,11 @@ static void timerlat_top_usage(char *usage) for (i = 0; msg[i]; i++) fprintf(stderr, "%s\n", msg[i]); - exit(1); + + if (usage) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); } /* diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c index 663a047f794d2a8269abff7241805d871fc6cb73..8c8d63c7196cf401a851aa123692eb2ab1c4924e 100644 --- a/tools/tracing/rtla/src/utils.c +++ b/tools/tracing/rtla/src/utils.c @@ -243,12 +243,6 @@ static inline int sched_setattr(pid_t pid, const struct sched_attr *attr, return syscall(__NR_sched_setattr, pid, attr, flags); } -static inline int sched_getattr(pid_t pid, struct sched_attr *attr, - unsigned int size, unsigned int flags) -{ - return syscall(__NR_sched_getattr, pid, attr, size, flags); -} - int __set_sched_attr(int pid, struct sched_attr *attr) { int flags = 0; @@ -484,13 +478,13 @@ int parse_prio(char *arg, struct sched_attr *sched_param) if (prio == INVALID_VAL) return -1; - if (prio < sched_get_priority_min(SCHED_OTHER)) + if (prio < MIN_NICE) return -1; - if (prio > sched_get_priority_max(SCHED_OTHER)) + if (prio > MAX_NICE) return -1; sched_param->sched_policy = SCHED_OTHER; - sched_param->sched_priority = prio; + sched_param->sched_nice = prio; break; default: return -1; diff --git a/tools/tracing/rtla/src/utils.h b/tools/tracing/rtla/src/utils.h index 5571afd3b549863922df3d71e8c68a732867c0c2..92da41aaf4c4c8c30e52b79b1edee954c23eaa86 100644 --- a/tools/tracing/rtla/src/utils.h +++ b/tools/tracing/rtla/src/utils.h @@ -7,6 +7,8 @@ */ #define BUFF_U64_STR_SIZE 24 #define MAX_PATH 1024 +#define MAX_NICE 20 +#define MIN_NICE -19 #define container_of(ptr, type, member)({ \ const typeof(((type *)0)->member) *__mptr = (ptr); \ diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 9bfe1d6f6529a2ff67094b66688a697e4605f11b..adaf6f141804fd33d8c2cfbcf1f04cbc75cd02b7 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -88,7 +88,27 @@ static void async_pf_execute(struct work_struct *work) __kvm_vcpu_wake_up(vcpu); mmput(mm); - kvm_put_kvm(vcpu->kvm); +} + +static void kvm_flush_and_free_async_pf_work(struct kvm_async_pf *work) +{ + /* + * The async #PF is "done", but KVM must wait for the work item itself, + * i.e. async_pf_execute(), to run to completion. If KVM is a module, + * KVM must ensure *no* code owned by the KVM (the module) can be run + * after the last call to module_put(). Note, flushing the work item + * is always required when the item is taken off the completion queue. + * E.g. even if the vCPU handles the item in the "normal" path, the VM + * could be terminated before async_pf_execute() completes. + * + * Wake all events skip the queue and go straight done, i.e. don't + * need to be flushed (but sanity check that the work wasn't queued). + */ + if (work->wakeup_all) + WARN_ON_ONCE(work->work.func); + else + flush_work(&work->work); + kmem_cache_free(async_pf_cache, work); } void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) @@ -115,7 +135,6 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) #else if (cancel_work_sync(&work->work)) { mmput(work->mm); - kvm_put_kvm(vcpu->kvm); /* == work->vcpu->kvm */ kmem_cache_free(async_pf_cache, work); } #endif @@ -127,7 +146,10 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) list_first_entry(&vcpu->async_pf.done, typeof(*work), link); list_del(&work->link); - kmem_cache_free(async_pf_cache, work); + + spin_unlock(&vcpu->async_pf.lock); + kvm_flush_and_free_async_pf_work(work); + spin_lock(&vcpu->async_pf.lock); } spin_unlock(&vcpu->async_pf.lock); @@ -152,7 +174,7 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu) list_del(&work->queue); vcpu->async_pf.queued--; - kmem_cache_free(async_pf_cache, work); + kvm_flush_and_free_async_pf_work(work); } } @@ -187,7 +209,6 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, work->arch = *arch; work->mm = current->mm; mmget(work->mm); - kvm_get_kvm(work->vcpu->kvm); INIT_WORK(&work->work, async_pf_execute);