- Nov 09, 2019
-
-
Magnus Karlsson authored
The need_wakeup flag for Tx might not be set for AF_XDP sockets that are only used to send packets. This happens if there is at least one outstanding packet that has not been completed by the hardware and we get that corresponding completion (which will not generate an interrupt since interrupts are disabled in the napi poll loop) between the time we stopped processing the Tx completions and interrupts are enabled again. In this case, the need_wakeup flag will have been cleared at the end of the Tx completion processing as we believe we will get an interrupt from the outstanding completion at a later point in time. But if this completion interrupt occurs before interrupts are enable, we lose it and should at that point really have set the need_wakeup flag since there are no more outstanding completions that can generate an interrupt to continue the processing. When this happens, user space will see a Tx queue need_wakeup of 0 and skip issuing a syscall, which means will never get into the Tx processing again and we have a deadlock. This patch introduces a quick fix for this issue by just setting the need_wakeup flag for Tx to 1 all the time. I am working on a proper fix for this that will toggle the flag appropriately, but it is more challenging than I anticipated and I am afraid that this patch will not be completed before the merge window closes, therefore this easier fix for now. This fix has a negative performance impact in the range of 0% to 4%. Towards the higher end of the scale if you have driver and application on the same core and issue a lot of packets, and towards no negative impact if you use two cores, lower transmission speeds and/or a workload that also receives packets. Signed-off-by:
Magnus Karlsson <magnus.karlsson@intel.com> Tested-by:
Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by:
Jeff Kirsher <jeffrey.t.kirsher@intel.com>
-
Magnus Karlsson authored
The need_wakeup flag for Tx might not be set for AF_XDP sockets that are only used to send packets. This happens if there is at least one outstanding packet that has not been completed by the hardware and we get that corresponding completion (which will not generate an interrupt since interrupts are disabled in the napi poll loop) between the time we stopped processing the Tx completions and interrupts are enabled again. In this case, the need_wakeup flag will have been cleared at the end of the Tx completion processing as we believe we will get an interrupt from the outstanding completion at a later point in time. But if this completion interrupt occurs before interrupts are enable, we lose it and should at that point really have set the need_wakeup flag since there are no more outstanding completions that can generate an interrupt to continue the processing. When this happens, user space will see a Tx queue need_wakeup of 0 and skip issuing a syscall, which means will never get into the Tx processing again and we have a deadlock. This patch introduces a quick fix for this issue by just setting the need_wakeup flag for Tx to 1 all the time. I am working on a proper fix for this that will toggle the flag appropriately, but it is more challenging than I anticipated and I am afraid that this patch will not be completed before the merge window closes, therefore this easier fix for now. This fix has a negative performance impact in the range of 0% to 4%. Towards the higher end of the scale if you have driver and application on the same core and issue a lot of packets, and towards no negative impact if you use two cores, lower transmission speeds and/or a workload that also receives packets. Signed-off-by:
Magnus Karlsson <magnus.karlsson@intel.com> Tested-by:
Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by:
Jeff Kirsher <jeffrey.t.kirsher@intel.com>
-
Jacob Keller authored
When implementing launch time support in the igb and igc drivers, the skb->tstamp value is assumed to be a s64, but it's declared as a ktime_t value. Although ktime_t is typedef'd to s64 it wasn't always, and the kernel provides accessors for ktime_t values. Use the ktime_to_timespec64 and ktime_set accessors instead of directly assuming that the variable is always an s64. This improves portability if the code is ever moved to another kernel version, or if the definition of ktime_t ever changes again in the future. Signed-off-by:
Jacob Keller <jacob.e.keller@intel.com> Acked-by:
Vinicius Costa Gomes <vinicius.gomes@intel.com> Signed-off-by:
Jeff Kirsher <jeffrey.t.kirsher@intel.com>
-
Arkadiusz Kubalewski authored
This patch contains fix for a problem with command: 'ethtool -m <dev>' which breaks functionality of: 'ethtool <dev>' when called on X722 NIC Disallowed update of link phy_types on X722 NIC Currently correct value cannot be obtained from FW Previously wrong value returned by FW was used and was a root cause for incorrect output of 'ethtool <dev>' command Signed-off-by:
Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com> Tested-by:
Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by:
Jeff Kirsher <jeffrey.t.kirsher@intel.com>
-
Nicholas Nunley authored
Since commit 92418fb1 ("i40e/i40evf: Use usec value instead of reg value for ITR defines") the driver tracks the interrupt throttling intervals in single usec units, although the actual ITRN registers are programmed in 2 usec units. Most register programming flows in the driver correctly handle the conversion, although it is currently not applied when the registers are initialized to their default values. Most of the time this doesn't present a problem since the default values are usually immediately overwritten through the standard adaptive throttling mechanism, or updated manually by the user, but if adaptive throttling is disabled and the interval values are left alone then the incorrect value will persist. Since the intended default interval of 50 usecs (vs. 100 usecs as programmed) performs better for most traffic workloads, this can lead to performance regressions. This patch adds the correct conversion when writing the initial values to the ITRN registers. Signed-off-by:
Nicholas Nunley <nicholas.d.nunley@intel.com> Tested-by:
Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by:
Jeff Kirsher <jeffrey.t.kirsher@intel.com>
-
Colin Ian King authored
Currently the for-loop counter i is a u8 however it is being checked against a maximum value hw->num_tx_sched_layers which is a u16. Hence there is a potential wrap-around of counter i back to zero if hw->num_tx_sched_layers is greater than 255. Fix this by making i a u16. Addresses-Coverity: ("Infinite loop") Fixes: b36c598c ("ice: Updates to Tx scheduler code") Signed-off-by:
Colin Ian King <colin.king@canonical.com> Tested-by:
Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by:
Jeff Kirsher <jeffrey.t.kirsher@intel.com>
-
Eric Dumazet authored
KCSAN reported the following data-race [1] The fix will also prevent the compiler from optimizing out the condition. [1] BUG: KCSAN: data-race in neigh_resolve_output / neigh_resolve_output write to 0xffff8880a41dba78 of 8 bytes by interrupt on cpu 1: neigh_event_send include/net/neighbour.h:443 [inline] neigh_resolve_output+0x78/0x480 net/core/neighbour.c:1474 neigh_output include/net/neighbour.h:511 [inline] ip_finish_output2+0x4af/0xe40 net/ipv4/ip_output.c:228 __ip_finish_output net/ipv4/ip_output.c:308 [inline] __ip_finish_output+0x23a/0x490 net/ipv4/ip_output.c:290 ip_finish_output+0x41/0x160 net/ipv4/ip_output.c:318 NF_HOOK_COND include/linux/netfilter.h:294 [inline] ip_output+0xdf/0x210 net/ipv4/ip_output.c:432 dst_output include/net/dst.h:436 [inline] ip_local_out+0x74/0x90 net/ipv4/ip_output.c:125 __ip_queue_xmit+0x3a8/0xa40 net/ipv4/ip_output.c:532 ip_queue_xmit+0x45/0x60 include/net/ip.h:237 __tcp_transmit_skb+0xe81/0x1d60 net/ipv4/tcp_output.c:1169 tcp_transmit_skb net/ipv4/tcp_output.c:1185 [inline] __tcp_retransmit_skb+0x4bd/0x15f0 net/ipv4/tcp_output.c:2976 tcp_retransmit_skb+0x36/0x1a0 net/ipv4/tcp_output.c:2999 tcp_retransmit_timer+0x719/0x16d0 net/ipv4/tcp_timer.c:515 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:598 tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:618 read to 0xffff8880a41dba78 of 8 bytes by interrupt on cpu 0: neigh_event_send include/net/neighbour.h:442 [inline] neigh_resolve_output+0x57/0x480 net/core/neighbour.c:1474 neigh_output include/net/neighbour.h:511 [inline] ip_finish_output2+0x4af/0xe40 net/ipv4/ip_output.c:228 __ip_finish_output net/ipv4/ip_output.c:308 [inline] __ip_finish_output+0x23a/0x490 net/ipv4/ip_output.c:290 ip_finish_output+0x41/0x160 net/ipv4/ip_output.c:318 NF_HOOK_COND include/linux/netfilter.h:294 [inline] ip_output+0xdf/0x210 net/ipv4/ip_output.c:432 dst_output include/net/dst.h:436 [inline] ip_local_out+0x74/0x90 net/ipv4/ip_output.c:125 __ip_queue_xmit+0x3a8/0xa40 net/ipv4/ip_output.c:532 ip_queue_xmit+0x45/0x60 include/net/ip.h:237 __tcp_transmit_skb+0xe81/0x1d60 net/ipv4/tcp_output.c:1169 tcp_transmit_skb net/ipv4/tcp_output.c:1185 [inline] __tcp_retransmit_skb+0x4bd/0x15f0 net/ipv4/tcp_output.c:2976 tcp_retransmit_skb+0x36/0x1a0 net/ipv4/tcp_output.c:2999 tcp_retransmit_timer+0x719/0x16d0 net/ipv4/tcp_timer.c:515 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:598 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Signed-off-by:
Eric Dumazet <edumazet@google.com> Reported-by:
syzbot <syzkaller@googlegroups.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Stefano Garzarella authored
The "42f5cda5" commit rightly set SOCK_DONE on peer shutdown, but there is an issue if we receive the SHUTDOWN(RDWR) while the virtio_transport_close_timeout() is scheduled. In this case, when the timeout fires, the SOCK_DONE is already set and the virtio_transport_close_timeout() will not call virtio_transport_reset() and virtio_transport_do_close(). This causes that both sockets remain open and will never be released, preventing the unloading of [virtio|vhost]_transport modules. This patch fixes this issue, calling virtio_transport_reset() and virtio_transport_do_close() when we receive the SHUTDOWN(RDWR) and there is nothing left to read. Fixes: 42f5cda5 ("vsock/virtio: set SOCK_DONE on peer shutdown") Cc: Stephen Barber <smbarber@chromium.org> Signed-off-by:
Stefano Garzarella <sgarzare@redhat.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Merge tag 'mac80211-for-net-2019-11-08' of git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211 Johannes Berg says: ==================== Three small fixes: * we hit a failure path bug related to ieee80211_txq_setup_flows() * also use kvmalloc() to make that less likely * fix a timing value shortly after boot (during INITIAL_JIFFIES) ==================== Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Alexander Sverdlin authored
Octeon's input ring-buffer entry has 14 bits-wide size field, so to account for second possible VLAN header max_mtu must be further reduced. Fixes: 109cc165 ("ethernet/cavium: use core min/max MTU checking") Signed-off-by:
Alexander Sverdlin <alexander.sverdlin@nokia.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
- Nov 08, 2019
-
-
Ahmed Zaki authored
In the first 5 minutes after boot (time of INITIAL_JIFFIES), ieee80211_sta_last_active() returns zero if last_ack is zero. This leads to "inactive time" showing jiffies_to_msecs(jiffies). # iw wlan0 station get fc:ec:da:64:a6:dd Station fc:ec:da:64:a6:dd (on wlan0) inactive time: 4294894049 ms . . connected time: 70 seconds Fix by returning last_rx if last_ack == 0. Signed-off-by:
Ahmed Zaki <anzaki@gmail.com> Link: https://lore.kernel.org/r/20191031121243.27694-1-anzaki@gmail.com Signed-off-by:
Johannes Berg <johannes.berg@intel.com>
-
Toke Høiland-Jørgensen authored
The FQ implementation used by mac80211 allocates memory using kmalloc(), which can fail; and Johannes reported that this actually happens in practice. To avoid this, switch the allocation to kvmalloc() instead; this also brings fq_impl in line with all the FQ qdiscs. Fixes: 557fc4a0 ("fq: add fair queuing framework") Reported-by:
Johannes Berg <johannes@sipsolutions.net> Signed-off-by:
Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/r/20191105155750.547379-1-toke@redhat.com Signed-off-by:
Johannes Berg <johannes.berg@intel.com>
-
Johannes Berg authored
If ieee80211_txq_setup_flows() fails, we don't clean up LED state properly, leading to crashes later on, fix that. Fixes: dc8b274f ("mac80211: Move up init of TXQs") Signed-off-by:
Johannes Berg <johannes.berg@intel.com> Acked-by:
Toke Høiland-Jørgensen <toke@toke.dk> Link: https://lore.kernel.org/r/20191105154110.1ccf7112ba5d.I0ba865792446d051867b33153be65ce6b063d98c@changeid Signed-off-by:
Johannes Berg <johannes.berg@intel.com>
-
David Ahern authored
Hendrik reported routes in the main table using source address are not removed when the address is removed. The problem is that fib_sync_down_addr does not account for devices in the default VRF which are associated with the main table. Fix by updating the table id reference. Fixes: 5a56a0b3 ("net: Don't delete routes in different VRFs") Reported-by:
Hendrik Donner <hd@os-cillation.de> Signed-off-by:
David Ahern <dsahern@kernel.org> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Eric Dumazet authored
While looking at a syzbot KCSAN report [1], I found multiple issues in this code : 1) fib6_nh->last_probe has an initial value of 0. While probably okay on 64bit kernels, this causes an issue on 32bit kernels since the time_after(jiffies, 0 + interval) might be false ~24 days after boot (for HZ=1000) 2) The data-race found by KCSAN I could use READ_ONCE() and WRITE_ONCE(), but we also can take the opportunity of not piling-up too many rt6_probe_deferred() works by using instead cmpxchg() so that only one cpu wins the race. [1] BUG: KCSAN: data-race in find_match / find_match write to 0xffff8880bb7aabe8 of 8 bytes by interrupt on cpu 1: rt6_probe net/ipv6/route.c:663 [inline] find_match net/ipv6/route.c:757 [inline] find_match+0x5bd/0x790 net/ipv6/route.c:733 __find_rr_leaf+0xe3/0x780 net/ipv6/route.c:831 find_rr_leaf net/ipv6/route.c:852 [inline] rt6_select net/ipv6/route.c:896 [inline] fib6_table_lookup+0x383/0x650 net/ipv6/route.c:2164 ip6_pol_route+0xee/0x5c0 net/ipv6/route.c:2200 ip6_pol_route_output+0x48/0x60 net/ipv6/route.c:2452 fib6_rule_lookup+0x3d6/0x470 net/ipv6/fib6_rules.c:117 ip6_route_output_flags_noref+0x16b/0x230 net/ipv6/route.c:2484 ip6_route_output_flags+0x50/0x1a0 net/ipv6/route.c:2497 ip6_dst_lookup_tail+0x25d/0xc30 net/ipv6/ip6_output.c:1049 ip6_dst_lookup_flow+0x68/0x120 net/ipv6/ip6_output.c:1150 inet6_csk_route_socket+0x2f7/0x420 net/ipv6/inet6_connection_sock.c:106 inet6_csk_xmit+0x91/0x1f0 net/ipv6/inet6_connection_sock.c:121 __tcp_transmit_skb+0xe81/0x1d60 net/ipv4/tcp_output.c:1169 tcp_transmit_skb net/ipv4/tcp_output.c:1185 [inline] tcp_xmit_probe_skb+0x19b/0x1d0 net/ipv4/tcp_output.c:3735 read to 0xffff8880bb7aabe8 of 8 bytes by interrupt on cpu 0: rt6_probe net/ipv6/route.c:657 [inline] find_match net/ipv6/route.c:757 [inline] find_match+0x521/0x790 net/ipv6/route.c:733 __find_rr_leaf+0xe3/0x780 net/ipv6/route.c:831 find_rr_leaf net/ipv6/route.c:852 [inline] rt6_select net/ipv6/route.c:896 [inline] fib6_table_lookup+0x383/0x650 net/ipv6/route.c:2164 ip6_pol_route+0xee/0x5c0 net/ipv6/route.c:2200 ip6_pol_route_output+0x48/0x60 net/ipv6/route.c:2452 fib6_rule_lookup+0x3d6/0x470 net/ipv6/fib6_rules.c:117 ip6_route_output_flags_noref+0x16b/0x230 net/ipv6/route.c:2484 ip6_route_output_flags+0x50/0x1a0 net/ipv6/route.c:2497 ip6_dst_lookup_tail+0x25d/0xc30 net/ipv6/ip6_output.c:1049 ip6_dst_lookup_flow+0x68/0x120 net/ipv6/ip6_output.c:1150 inet6_csk_route_socket+0x2f7/0x420 net/ipv6/inet6_connection_sock.c:106 inet6_csk_xmit+0x91/0x1f0 net/ipv6/inet6_connection_sock.c:121 __tcp_transmit_skb+0xe81/0x1d60 net/ipv4/tcp_output.c:1169 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 18894 Comm: udevd Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: cc3a86c8 ("ipv6: Change rt6_probe to take a fib6_nh") Fixes: f547fac6 ("ipv6: rate-limit probes for neighbourless routes") Signed-off-by:
Eric Dumazet <edumazet@google.com> Reported-by:
syzbot <syzkaller@googlegroups.com> Reviewed-by:
David Ahern <dsahern@gmail.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Salil Mehta authored
This patch fixes the problem of the spin locks, originally meant for the netpoll path of hns driver, causing deadlock in the normal NAPI poll path. The issue happened due to the presence of the stray leftover spin lock code related to the netpoll, whose support was earlier removed from the HNS[1], got activated due to enabling of NET_POLL_CONTROLLER switch. Earlier background: The netpoll handling code originally had this bug(as identified by Marc Zyngier[2]) of wrong spin lock API being used which did not disable the interrupts and hence could cause locking issues. i.e. if the lock were first acquired in context to thread like 'ip' util and this lock if ever got later acquired again in context to the interrupt context like TX/RX (Interrupts could always pre-empt the lock holding task and acquire the lock again) and hence could cause deadlock. Proposed Solution: 1. If the netpoll was enabled in the HNS driver, which is not right now, we could have simply used spin_[un]lock_irqsave() 2. But as netpoll is disabled, therefore, it is best to get rid of the existing locks and stray code for now. This should solve the problem reported by Marc. [1] https://git.kernel.org/torvalds/c/4bd2c03b [2] https://patchwork.ozlabs.org/patch/1189139/ Fixes: 4bd2c03b ("net: hns: remove ndo_poll_controller") Cc: lipeng <lipeng321@huawei.com> Cc: Yisen Zhuang <yisen.zhuang@huawei.com> Cc: Eric Dumazet <edumazet@google.com> Cc: David S. Miller <davem@davemloft.net> Reported-by:
Marc Zyngier <maz@kernel.org> Acked-by:
Marc Zyngier <maz@kernel.org> Tested-by:
Marc Zyngier <maz@kernel.org> Signed-off-by:
Salil Mehta <salil.mehta@huawei.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Aleksander Morgado authored
Exactly same layout as the default DW5821e module, just a different vid/pid. The QMI interface is exposed in USB configuration #1: P: Vendor=413c ProdID=81e0 Rev=03.18 S: Manufacturer=Dell Inc. S: Product=DW5821e-eSIM Snapdragon X20 LTE S: SerialNumber=0123456789ABCDEF C: #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA I: If#=0x0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan I: If#=0x1 Alt= 0 #EPs= 1 Cls=03(HID ) Sub=00 Prot=00 Driver=usbhid I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option Signed-off-by:
Aleksander Morgado <aleksander@aleksander.es> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Oliver Neukum authored
A malicious device may give half an answer when asked for its MTU. The driver will proceed after this with a garbage MTU. Anything but a complete answer must be treated as an error. V2: used sizeof as request by Alexander Reported-and-tested-by:
<syzbot+0631d878823ce2411636@syzkaller.appspotmail.com> Signed-off-by:
Oliver Neukum <oneukum@suse.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Pan Bian authored
The function nfc_put_device(dev) is called twice to drop the reference to dev when there is no associated local llcp. Remove one of them to fix the bug. Fixes: 52feb444 ("NFC: Extend netlink interface for LTO, RW, and MIUX parameters support") Fixes: d9b8d8e1 ("NFC: llcp: Service Name Lookup netlink interface") Signed-off-by:
Pan Bian <bianpan2016@163.com> Reviewed-by:
Johan Hovold <johan@kernel.org> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
- Nov 07, 2019
-
-
Pan Bian authored
The variable nfcid_skb is not changed in the callee nfc_hci_get_param() if error occurs. Consequently, the freed variable nfcid_skb will be freed again, resulting in a double free bug. Set nfcid_skb to NULL after releasing it to fix the bug. Signed-off-by:
Pan Bian <bianpan2016@163.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Huazhong Tan authored
Since old firmware does not support HCLGE_OPC_PF_RST_DONE, it will return -EOPNOTSUPP to the driver when received this command. So for this case, it should just print a warning and return success to the caller. Fixes: 72e2fb07 ("net: hns3: clear reset interrupt status in hclge_irq_handle()") Signed-off-by:
Huazhong Tan <tanhuazhong@huawei.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linuxDavid S. Miller authored
Saeed Mahamees says: ==================== Mellanox, mlx5 fixes 2019-11-06 This series introduces some fixes to mlx5 driver. Please pull and let me know if there is any problem. No -stable this time. ==================== Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Heiner Kallweit authored
Functions like phy_modify_paged() read the current page, on Realtek PHY's this means reading the value of register 0x1f. Add special handling for reading this register, similar to what we do already in r8168g_mdio_write(). Currently we read a random value that by chance seems to be 0 always. Fixes: a2928d28 ("r8169: use paged versions of phylib MDIO access functions") Signed-off-by:
Heiner Kallweit <hkallweit1@gmail.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Jose Abreu says: ==================== net: stmmac: Fixes for -net Misc fixes for stmmac. Patch 1/11 and 2/11, use the correct variable type for bitrev32() calls. Patch 3/11, fixes the random failures the we were seing when running selftests. Patch 4/11, prevents a crash that can occur when receiving AVB packets and with SPH feature enabled on XGMAC. Patch 5/11, fixes the correct settings for CBS on XGMAC. Patch 6/11, corrects the interpretation of AVB feature on XGMAC. Patch 7/11, disables Flow Control for AVB enabled queues on XGMAC. Patch 8/11, disables MMC interrupts on XGMAC, preventing a storm of interrupts. Patch 9/11, fixes the number of packets that were being taken into account in the RX path cleaning function. Patch 10/11, fixes an incorrect descriptor setting that could cause IP misbehavior. Patch 11/11, fixes the IOC generation mechanism when multiple descriptors are used. ==================== Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jose Abreu authored
IOC bit must be only set in the last descriptor. Move the logic up a little bit to make sure it's set in the correct descriptor. Signed-off-by:
Jose Abreu <Jose.Abreu@synopsys.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jose Abreu authored
When using addressing > 32 bits the TSO first descriptor only has the header so we can't set the payload field for this descriptor. Let's reset the variable so that buffer 2 value is zero. Fixes: a993db88 ("net: stmmac: Enable support for > 32 Bits addressing in XGMAC") Signed-off-by:
Jose Abreu <Jose.Abreu@synopsys.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jose Abreu authored
Currently, stmmac_rx() is counting the number of descriptors but it should count the number of packets as specified by the NAPI limit. Fix this. Fixes: ec222003 ("net: stmmac: Prepare to add Split Header support") Signed-off-by:
Jose Abreu <Jose.Abreu@synopsys.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jose Abreu authored
MMC interrupts were being enabled, which is not what we want because it will lead to a storm of interrupts that are not handled at all. Fix it by disabling all MMC interrupts for XGMAC. Fixes: b6cdf09f ("net: stmmac: xgmac: Implement MMC counters") Signed-off-by:
Jose Abreu <Jose.Abreu@synopsys.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jose Abreu authored
When in AVB mode we need to disable flow control to prevent MAC from pausing in TX side. Fixes: ec6ea8e3 ("net: stmmac: Add CBS support in XGMAC2") Signed-off-by:
Jose Abreu <Jose.Abreu@synopsys.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jose Abreu authored
Fix incorrect precedence of operators. For reference: AV implies AV Feature but RAV implies only RX side AV Feature. As we want full AV features we need to check RAV. Fixes: c2b69474 ("net: stmmac: xgmac: Correct RAVSEL field interpretation") Signed-off-by:
Jose Abreu <Jose.Abreu@synopsys.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jose Abreu authored
When we change between Transmission Scheduling Algorithms, we need to clear previous values so that the new chosen algorithm is correctly selected. Fixes: ec6ea8e3 ("net: stmmac: Add CBS support in XGMAC2") Signed-off-by:
Jose Abreu <Jose.Abreu@synopsys.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jose Abreu authored
Split Header length is only available when L34T == 0. Fix this by correctly checking if L34T is zero before trying to get Header length. Fixes: 67afd6d1 ("net: stmmac: Add Split Header support and enable it in XGMAC cores") Signed-off-by:
Jose Abreu <Jose.Abreu@synopsys.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jose Abreu authored
In L2 tests that filter packets by destination MAC address we need to prevent false positives that can occur if we add an address that collides with the existing ones. To fix this, lets manually check if the new address to be added is already present in the NIC and use a different one if so. For Hash filtering this also envolves converting the address to the hash. Fixes: 091810db ("net: stmmac: Introduce selftests support") Signed-off-by:
Jose Abreu <Jose.Abreu@synopsys.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jose Abreu authored
The bitrev32 function returns an u32 var, not an int. Fix it. Fixes: 0efedbf1 ("net: stmmac: xgmac: Fix XGMAC selftests") Signed-off-by:
Jose Abreu <Jose.Abreu@synopsys.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jose Abreu authored
The bitrev32 function returns an u32 var, not an int. Fix it. Fixes: 477286b5 ("stmmac: add GMAC4 core support") Signed-off-by:
Jose Abreu <Jose.Abreu@synopsys.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nfDavid S. Miller authored
Pablo Neira Ayuso says: ==================== Netfilter fixes for net The following patchset contains Netfilter fixes for net: 1) Missing register size validation in bitwise and cmp offloads. 2) Fix error code in ip_set_sockfn_get() when copy_to_user() fails, from Dan Carpenter. 3) Oneliner to copy MAC address in IPv6 hash:ip,mac sets, from Stefano Brivio. 4) Missing policy validation in ipset with NL_VALIDATE_STRICT, from Jozsef Kadlecsik. 5) Fix unaligned access to private data area of nf_tables instructions, from Lukas Wunner. 6) Relax check for object updates, reported as a regression by Eric Garver, patch from Fernando Fernandez Mancera. 7) Crash on ebtables dnat extension when used from the output path. From Florian Westphal. 8) Fix bogus EOPNOTSUPP when updating basechain flags. 9) Fix bogus EBUSY when updating a basechain that is already offloaded. ==================== Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Ursula Braun authored
If a pnet table entry is to be added mentioning a valid ethernet interface, but an invalid infiniband or ISM device, the dev_put() operation for the ethernet interface is called twice, resulting in a negative refcount for the ethernet interface, which disables removal of such a network interface. This patch removes one of the dev_put() calls. Fixes: 890a2cb4 ("net/smc: rework pnet table") Signed-off-by:
Ursula Braun <ubraun@linux.ibm.com> Signed-off-by:
Karsten Graul <kgraul@linux.ibm.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Jakub Kicinski says: ==================== net/tls: add a TX lock Some time ago Pooja and Mallesham started reporting crashes with an async accelerator. After trying to poke the existing logic into shape I came to the conclusion that it can't be trusted, and to preserve our sanity we should just add a lock around the TX side. First patch removes the sk_write_pending checks from the write space callbacks. Those don't seem to have a logical justification. Patch 2 adds the TX lock and patch 3 associated test (which should hang with current net). Mallesham reports that even with these fixes applied the async accelerator workload still occasionally hangs waiting for socket memory. I suspect that's strictly related to the way async crypto is integrated in TLS, so I think we should get these into net or net-next and move from there. ==================== Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jakub Kicinski authored
Add a test which spawns 16 threads and performs concurrent send and recv calls on the same socket. Signed-off-by:
Jakub Kicinski <jakub.kicinski@netronome.com> Reviewed-by:
Simon Horman <simon.horman@netronome.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jakub Kicinski authored
TLS TX needs to release and re-acquire the socket lock if send buffer fills up. TLS SW TX path currently depends on only allowing one thread to enter the function by the abuse of sk_write_pending. If another writer is already waiting for memory no new ones are allowed in. This has two problems: - writers don't wake other threads up when they leave the kernel; meaning that this scheme works for single extra thread (second application thread or delayed work) because memory becoming available will send a wake up request, but as Mallesham and Pooja report with larger number of threads it leads to threads being put to sleep indefinitely; - the delayed work does not get _scheduled_ but it may _run_ when other writers are present leading to crashes as writers don't expect state to change under their feet (same records get pushed and freed multiple times); it's hard to reliably bail from the work, however, because the mere presence of a writer does not guarantee that the writer will push pending records before exiting. Ensuring wakeups always happen will make the code basically open code a mutex. Just use a mutex. The TLS HW TX path does not have any locking (not even the sk_write_pending hack), yet it uses a per-socket sg_tx_data array to push records. Fixes: a42055e8 ("net/tls: Add support for async encryption of records for performance") Reported-by:
Mallesham Jatharakonda <mallesh537@gmail.com> Reported-by:
Pooja Trivedi <poojatrivedi@gmail.com> Signed-off-by:
Jakub Kicinski <jakub.kicinski@netronome.com> Reviewed-by:
Simon Horman <simon.horman@netronome.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-