Skip to content
  1. Dec 28, 2021
  3. Dec 27, 2021
    • Krzysztof Kozlowski's avatar
      nfc: uapi: use kernel size_t to fix user-space builds · 79b69a83
      Krzysztof Kozlowski authored 
      Fix user-space builds if it includes /usr/include/linux/nfc.h before
some of other headers:

  /usr/include/linux/nfc.h:281:9: error: unknown type name ‘size_t’
    281 |         size_t service_name_len;
        |         ^~~~~~

Fixes: d646960f

 ("NFC: Initial LLCP support")
Cc: <stable@vger.kernel.org>
Signed-off-by: default avatarKrzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      79b69a83
    • Dmitry V. Levin's avatar
      uapi: fix linux/nfc.h userspace compilation errors · 7175f02c
      Dmitry V. Levin authored 
      Replace sa_family_t with __kernel_sa_family_t to fix the following
linux/nfc.h userspace compilation errors:

/usr/include/linux/nfc.h:266:2: error: unknown type name 'sa_family_t'
  sa_family_t sa_family;
/usr/include/linux/nfc.h:274:2: error: unknown type name 'sa_family_t'
  sa_family_t sa_family;

Fixes: 23b7869c ("NFC: add the NFC socket raw protocol")
Fixes: d646960f

 ("NFC: Initial LLCP support")
Cc: <stable@vger.kernel.org>
Signed-off-by: default avatarDmitry V. Levin <ldv@altlinux.org>
Reviewed-by: default avatarKrzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      7175f02c
    • Matthias-Christian Ott's avatar
      net: usb: pegasus: Do not drop long Ethernet frames · ca506fca
      Matthias-Christian Ott authored 
      The D-Link DSB-650TX (2001:4002) is unable to receive Ethernet frames
that are longer than 1518 octets, for example, Ethernet frames that
contain 802.1Q VLAN tags.

The frames are sent to the pegasus driver via USB but the driver
discards them because they have the Long_pkt field set to 1 in the
received status report. The function read_bulk_callback of the pegasus
driver treats such received "packets" (in the terminology of the
hardware) as errors but the field simply does just indicate that the
Ethernet frame (MAC destination to FCS) is longer than 1518 octets.

It seems that in the 1990s there was a distinction between
"giant" (> 1518) and "runt" (< 64) frames and the hardware includes
flags to indicate this distinction. It seems that the purpose of the
distinction "giant" frames was to not allow infinitely long frames due
to transmission errors and to allow hardware to have an upper limit of
the frame size. However, the hardware already has such limit with its
2048 octet receive buffer and, therefore, Long_pkt is merely a
convention and should not be treated as a receive error.

Actually, the hardware is even able to receive Ethernet frames with 2048
octets which exceeds the claimed limit frame size limit of the driver of
1536 octets (PEGASUS_MTU).

Fixes: 1da177e4

 ("Linux-2.6.12-rc2")
Signed-off-by: default avatarMatthias-Christian Ott <ott@mirix.org>
Reviewed-by: default avatarAndrew Lunn <andrew@lunn.ch>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      ca506fca
    • Zekun Shen's avatar
      atlantic: Fix buff_ring OOB in aq_ring_rx_clean · 5f501532
      Zekun Shen authored 
      

The function obtain the next buffer without boundary check.
We should return with I/O error code.

The bug is found by fuzzing and the crash report is attached.
It is an OOB bug although reported as use-after-free.

[    4.804724] BUG: KASAN: use-after-free in aq_ring_rx_clean+0x1e88/0x2730 [atlantic]
[    4.805661] Read of size 4 at addr ffff888034fe93a8 by task ksoftirqd/0/9
[    4.806505]
[    4.806703] CPU: 0 PID: 9 Comm: ksoftirqd/0 Tainted: G        W         5.6.0 #34
[    4.809030] Call Trace:
[    4.809343]  dump_stack+0x76/0xa0
[    4.809755]  print_address_description.constprop.0+0x16/0x200
[    4.810455]  ? aq_ring_rx_clean+0x1e88/0x2730 [atlantic]
[    4.811234]  ? aq_ring_rx_clean+0x1e88/0x2730 [atlantic]
[    4.813183]  __kasan_report.cold+0x37/0x7c
[    4.813715]  ? aq_ring_rx_clean+0x1e88/0x2730 [atlantic]
[    4.814393]  kasan_report+0xe/0x20
[    4.814837]  aq_ring_rx_clean+0x1e88/0x2730 [atlantic]
[    4.815499]  ? hw_atl_b0_hw_ring_rx_receive+0x9a5/0xb90 [atlantic]
[    4.816290]  aq_vec_poll+0x179/0x5d0 [atlantic]
[    4.816870]  ? _GLOBAL__sub_I_65535_1_aq_pci_func_init+0x20/0x20 [atlantic]
[    4.817746]  ? __next_timer_interrupt+0xba/0xf0
[    4.818322]  net_rx_action+0x363/0xbd0
[    4.818803]  ? call_timer_fn+0x240/0x240
[    4.819302]  ? __switch_to_asm+0x40/0x70
[    4.819809]  ? napi_busy_loop+0x520/0x520
[    4.820324]  __do_softirq+0x18c/0x634
[    4.820797]  ? takeover_tasklets+0x5f0/0x5f0
[    4.821343]  run_ksoftirqd+0x15/0x20
[    4.821804]  smpboot_thread_fn+0x2f1/0x6b0
[    4.822331]  ? smpboot_unregister_percpu_thread+0x160/0x160
[    4.823041]  ? __kthread_parkme+0x80/0x100
[    4.823571]  ? smpboot_unregister_percpu_thread+0x160/0x160
[    4.824301]  kthread+0x2b5/0x3b0
[    4.824723]  ? kthread_create_on_node+0xd0/0xd0
[    4.825304]  ret_from_fork+0x35/0x40

Signed-off-by: default avatarZekun Shen <bruceshenzk@gmail.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      5f501532
    • yangxingwu's avatar
      net: udp: fix alignment problem in udp4_seq_show() · 6c25449e
      yangxingwu authored 
      

$ cat /pro/net/udp

before:

  sl  local_address rem_address   st tx_queue rx_queue tr tm->when
26050: 0100007F:0035 00000000:0000 07 00000000:00000000 00:00000000
26320: 0100007F:0143 00000000:0000 07 00000000:00000000 00:00000000
27135: 00000000:8472 00000000:0000 07 00000000:00000000 00:00000000

after:

   sl  local_address rem_address   st tx_queue rx_queue tr tm->when
26050: 0100007F:0035 00000000:0000 07 00000000:00000000 00:00000000
26320: 0100007F:0143 00000000:0000 07 00000000:00000000 00:00000000
27135: 00000000:8472 00000000:0000 07 00000000:00000000 00:00000000

Signed-off-by: default avataryangxingwu <xingwu.yang@gmail.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      6c25449e
    • Karsten Graul's avatar
      net/smc: fix using of uninitialized completions · 6d7373da
      Karsten Graul authored 
      In smc_wr_tx_send_wait() the completion on index specified by
pend->idx is initialized and after smc_wr_tx_send() was called the wait
for completion starts. pend->idx is used to get the correct index for
the wait, but the pend structure could already be cleared in
smc_wr_tx_process_cqe().
Introduce pnd_idx to hold and use a local copy of the correct index.

Fixes: 09c61d24

 ("net/smc: wait for departure of an IB message")
Signed-off-by: default avatarKarsten Graul <kgraul@linux.ibm.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      6d7373da
    • William Zhao's avatar
      ip6_vti: initialize __ip6_tnl_parm struct in vti6_siocdevprivate · c1833c39
      William Zhao authored 
      

The "__ip6_tnl_parm" struct was left uninitialized causing an invalid
load of random data when the "__ip6_tnl_parm" struct was used elsewhere.
As an example, in the function "ip6_tnl_xmit_ctl()", it tries to access
the "collect_md" member. With "__ip6_tnl_parm" being uninitialized and
containing random data, the UBSAN detected that "collect_md" held a
non-boolean value.

The UBSAN issue is as follows:
===============================================================
UBSAN: invalid-load in net/ipv6/ip6_tunnel.c:1025:14
load of value 30 is not a valid value for type '_Bool'
CPU: 1 PID: 228 Comm: kworker/1:3 Not tainted 5.16.0-rc4+ #8
Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
Workqueue: ipv6_addrconf addrconf_dad_work
Call Trace:
<TASK>
dump_stack_lvl+0x44/0x57
ubsan_epilogue+0x5/0x40
__ubsan_handle_load_invalid_value+0x66/0x70
? __cpuhp_setup_state+0x1d3/0x210
ip6_tnl_xmit_ctl.cold.52+0x2c/0x6f [ip6_tunnel]
vti6_tnl_xmit+0x79c/0x1e96 [ip6_vti]
? lock_is_held_type+0xd9/0x130
? vti6_rcv+0x100/0x100 [ip6_vti]
? lock_is_held_type+0xd9/0x130
? rcu_read_lock_bh_held+0xc0/0xc0
? lock_acquired+0x262/0xb10
dev_hard_start_xmit+0x1e6/0x820
__dev_queue_xmit+0x2079/0x3340
? mark_lock.part.52+0xf7/0x1050
? netdev_core_pick_tx+0x290/0x290
? kvm_clock_read+0x14/0x30
? kvm_sched_clock_read+0x5/0x10
? sched_clock_cpu+0x15/0x200
? find_held_lock+0x3a/0x1c0
? lock_release+0x42f/0xc90
? lock_downgrade+0x6b0/0x6b0
? mark_held_locks+0xb7/0x120
? neigh_connected_output+0x31f/0x470
? lockdep_hardirqs_on+0x79/0x100
? neigh_connected_output+0x31f/0x470
? ip6_finish_output2+0x9b0/0x1d90
? rcu_read_lock_bh_held+0x62/0xc0
? ip6_finish_output2+0x9b0/0x1d90
ip6_finish_output2+0x9b0/0x1d90
? ip6_append_data+0x330/0x330
? ip6_mtu+0x166/0x370
? __ip6_finish_output+0x1ad/0xfb0
? nf_hook_slow+0xa6/0x170
ip6_output+0x1fb/0x710
? nf_hook.constprop.32+0x317/0x430
? ip6_finish_output+0x180/0x180
? __ip6_finish_output+0xfb0/0xfb0
? lock_is_held_type+0xd9/0x130
ndisc_send_skb+0xb33/0x1590
? __sk_mem_raise_allocated+0x11cf/0x1560
? dst_output+0x4a0/0x4a0
? ndisc_send_rs+0x432/0x610
addrconf_dad_completed+0x30c/0xbb0
? addrconf_rs_timer+0x650/0x650
? addrconf_dad_work+0x73c/0x10e0
addrconf_dad_work+0x73c/0x10e0
? addrconf_dad_completed+0xbb0/0xbb0
? rcu_read_lock_sched_held+0xaf/0xe0
? rcu_read_lock_bh_held+0xc0/0xc0
process_one_work+0x97b/0x1740
? pwq_dec_nr_in_flight+0x270/0x270
worker_thread+0x87/0xbf0
? process_one_work+0x1740/0x1740
kthread+0x3ac/0x490
? set_kthread_struct+0x100/0x100
ret_from_fork+0x22/0x30
</TASK>
===============================================================

The solution is to initialize "__ip6_tnl_parm" struct to zeros in the
"vti6_siocdevprivate()" function.

Signed-off-by: default avatarWilliam Zhao <wizhao@redhat.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      c1833c39
  5. Dec 26, 2021
    • Ma Xinjian's avatar
      selftests: mptcp: Remove the deprecated config NFT_COUNTER · e6007b85
      Ma Xinjian authored 
      

NFT_COUNTER was removed since
390ad4295aa ("netfilter: nf_tables: make counter support built-in")
LKP/0Day will check if all configs listing under selftests are able to
be enabled properly.

For the missing configs, it will report something like:
LKP WARN miss config CONFIG_NFT_COUNTER= of net/mptcp/config

- it's not reasonable to keep the deprecated configs.
- configs under kselftests are recommended by corresponding tests.
So if some configs are missing, it will impact the testing results

Reported-by: default avatarkernel test robot <lkp@intel.com>
Signed-off-by: default avatarMa Xinjian <xinjianx.ma@intel.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      e6007b85
    • Xin Long's avatar
      sctp: use call_rcu to free endpoint · 5ec7d18d
      Xin Long authored 
      

This patch is to delay the endpoint free by calling call_rcu() to fix
another use-after-free issue in sctp_sock_dump():

  BUG: KASAN: use-after-free in __lock_acquire+0x36d9/0x4c20
  Call Trace:
    __lock_acquire+0x36d9/0x4c20 kernel/locking/lockdep.c:3218
    lock_acquire+0x1ed/0x520 kernel/locking/lockdep.c:3844
    __raw_spin_lock_bh include/linux/spinlock_api_smp.h:135 [inline]
    _raw_spin_lock_bh+0x31/0x40 kernel/locking/spinlock.c:168
    spin_lock_bh include/linux/spinlock.h:334 [inline]
    __lock_sock+0x203/0x350 net/core/sock.c:2253
    lock_sock_nested+0xfe/0x120 net/core/sock.c:2774
    lock_sock include/net/sock.h:1492 [inline]
    sctp_sock_dump+0x122/0xb20 net/sctp/diag.c:324
    sctp_for_each_transport+0x2b5/0x370 net/sctp/socket.c:5091
    sctp_diag_dump+0x3ac/0x660 net/sctp/diag.c:527
    __inet_diag_dump+0xa8/0x140 net/ipv4/inet_diag.c:1049
    inet_diag_dump+0x9b/0x110 net/ipv4/inet_diag.c:1065
    netlink_dump+0x606/0x1080 net/netlink/af_netlink.c:2244
    __netlink_dump_start+0x59a/0x7c0 net/netlink/af_netlink.c:2352
    netlink_dump_start include/linux/netlink.h:216 [inline]
    inet_diag_handler_cmd+0x2ce/0x3f0 net/ipv4/inet_diag.c:1170
    __sock_diag_cmd net/core/sock_diag.c:232 [inline]
    sock_diag_rcv_msg+0x31d/0x410 net/core/sock_diag.c:263
    netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2477
    sock_diag_rcv+0x2a/0x40 net/core/sock_diag.c:274

This issue occurs when asoc is peeled off and the old sk is freed after
getting it by asoc->base.sk and before calling lock_sock(sk).

To prevent the sk free, as a holder of the sk, ep should be alive when
calling lock_sock(). This patch uses call_rcu() and moves sock_put and
ep free into sctp_endpoint_destroy_rcu(), so that it's safe to try to
hold the ep under rcu_read_lock in sctp_transport_traverse_process().

If sctp_endpoint_hold() returns true, it means this ep is still alive
and we have held it and can continue to dump it; If it returns false,
it means this ep is dead and can be freed after rcu_read_unlock, and
we should skip it.

In sctp_sock_dump(), after locking the sk, if this ep is different from
tsp->asoc->ep, it means during this dumping, this asoc was peeled off
before calling lock_sock(), and the sk should be skipped; If this ep is
the same with tsp->asoc->ep, it means no peeloff happens on this asoc,
and due to lock_sock, no peeloff will happen either until release_sock.

Note that delaying endpoint free won't delay the port release, as the
port release happens in sctp_endpoint_destroy() before calling call_rcu().
Also, freeing endpoint by call_rcu() makes it safe to access the sk by
asoc->base.sk in sctp_assocs_seq_show() and sctp_rcv().

Thanks Jones to bring this issue up.

v1->v2:
  - improve the changelog.
  - add kfree(ep) into sctp_endpoint_destroy_rcu(), as Jakub noticed.

Reported-by: default avatar <syzbot+9276d76e83e3bcde6c99@syzkaller.appspotmail.com>
Reported-by: default avatarLee Jones <lee.jones@linaro.org>
Fixes: d25adbeb

 ("sctp: fix an use-after-free issue in sctp_sock_dump")
Signed-off-by: default avatarXin Long <lucien.xin@gmail.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      5ec7d18d
  7. Dec 25, 2021
  9. Dec 24, 2021
  11. Dec 23, 2021
    • Christophe JAILLET's avatar
      net/mlx5: Fix some error handling paths in 'mlx5e_tc_add_fdb_flow()' · 4390c6ed
      Christophe JAILLET authored 
      All the error handling paths of 'mlx5e_tc_add_fdb_flow()' end to 'err_out'
where 'flow_flag_set(flow, FAILED);' is called.

All but the new error handling paths added by the commits given in the
Fixes tag below.

Fix these error handling paths and branch to 'err_out'.

Fixes: 166f431e ("net/mlx5e: Add indirect tc offload of ovs internal port")
Fixes: b16eb3c8

 ("net/mlx5: Support internal port as decap route device")
Signed-off-by: default avatarChristophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: default avatarRoi Dayan <roid@nvidia.com>
Signed-off-by: default avatarSaeed Mahameed <saeedm@nvidia.com>
(cherry picked from commit 31108d14)
      4390c6ed
    • Chris Mi's avatar
      net/mlx5e: Delete forward rule for ct or sample action · 2820110d
      Chris Mi authored 
      When there is ct or sample action, the ct or sample rule will be deleted
and return. But if there is an extra mirror action, the forward rule can't
be deleted because of the return.

Fix it by removing the return.

Fixes: 69e2916e ("net/mlx5: CT: Add support for mirroring")
Fixes: f94d6389

 ("net/mlx5e: TC, Add support to offload sample action")
Signed-off-by: default avatarChris Mi <cmi@nvidia.com>
Reviewed-by: default avatarRoi Dayan <roid@nvidia.com>
Signed-off-by: default avatarSaeed Mahameed <saeedm@nvidia.com>
      2820110d
    • Maxim Mikityanskiy's avatar
      net/mlx5e: Fix ICOSQ recovery flow for XSK · 19c4aba2
      Maxim Mikityanskiy authored 
      There are two ICOSQs per channel: one is needed for RX, and the other
for async operations (XSK TX, kTLS offload). Currently, the recovery
flow for both is the same, and async ICOSQ is mistakenly treated like
the regular ICOSQ.

This patch prevents running the regular ICOSQ recovery on async ICOSQ.
The purpose of async ICOSQ is to handle XSK wakeup requests and post
kTLS offload RX parameters, it has nothing to do with RQ and XSKRQ UMRs,
so the regular recovery sequence is not applicable here.

Fixes: be5323c8

 ("net/mlx5e: Report and recover from CQE error on ICOSQ")
Signed-off-by: default avatarMaxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: default avatarAya Levin <ayal@nvidia.com>
Signed-off-by: default avatarSaeed Mahameed <saeedm@nvidia.com>
      19c4aba2
    • Maxim Mikityanskiy's avatar
      net/mlx5e: Fix interoperability between XSK and ICOSQ recovery flow · 17958d7c
      Maxim Mikityanskiy authored 
      Both regular RQ and XSKRQ use the same ICOSQ for UMRs. When doing
recovery for the ICOSQ, don't forget to deactivate XSKRQ.

XSK can be opened and closed while channels are active, so a new mutex
prevents the ICOSQ recovery from running at the same time. The ICOSQ
recovery deactivates and reactivates XSKRQ, so any parallel change in
XSK state would break consistency. As the regular RQ is running, it's
not enough to just flush the recovery work, because it can be
rescheduled.

Fixes: be5323c8

 ("net/mlx5e: Report and recover from CQE error on ICOSQ")
Signed-off-by: default avatarMaxim Mikityanskiy <maximmi@nvidia.com>
Signed-off-by: default avatarSaeed Mahameed <saeedm@nvidia.com>
      17958d7c
    • Gal Pressman's avatar
      net/mlx5e: Fix skb memory leak when TC classifier action offloads are disabled · a0cb9096
      Gal Pressman authored 
      When TC classifier action offloads are disabled (CONFIG_MLX5_CLS_ACT in
Kconfig), the mlx5e_rep_tc_receive() function which is responsible for
passing the skb to the stack (or freeing it) is defined as a nop, and
results in leaking the skb memory. Replace the nop with a call to
napi_gro_receive() to resolve the leak.

Fixes: 28e7606f

 ("net/mlx5e: Refactor rx handler of represetor device")
Signed-off-by: default avatarGal Pressman <gal@nvidia.com>
Reviewed-by: default avatarAriel Levkovich <lariel@nvidia.com>
Signed-off-by: default avatarSaeed Mahameed <saeedm@nvidia.com>
      a0cb9096
    • Amir Tzin's avatar
      net/mlx5e: Wrap the tx reporter dump callback to extract the sq · 918fc385
      Amir Tzin authored 
      Function mlx5e_tx_reporter_dump_sq() casts its void * argument to struct
mlx5e_txqsq *, but in TX-timeout-recovery flow the argument is actually
of type struct mlx5e_tx_timeout_ctx *.

 mlx5_core 0000:08:00.1 enp8s0f1: TX timeout detected
 mlx5_core 0000:08:00.1 enp8s0f1: TX timeout on queue: 1, SQ: 0x11ec, CQ: 0x146d, SQ Cons: 0x0 SQ Prod: 0x1, usecs since last trans: 21565000
 BUG: stack guard page was hit at 0000000093f1a2de (stack is 00000000b66ea0dc..000000004d932dae)
 kernel stack overflow (page fault): 0000 [#1] SMP NOPTI
 CPU: 5 PID: 95 Comm: kworker/u20:1 Tainted: G W OE 5.13.0_mlnx #1
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
 Workqueue: mlx5e mlx5e_tx_timeout_work [mlx5_core]
 RIP: 0010:mlx5e_tx_reporter_dump_sq+0xd3/0x180
 [mlx5_core]
 Call Trace:
 mlx5e_tx_reporter_dump+0x43/0x1c0 [mlx5_core]
 devlink_health_do_dump.part.91+0x71/0xd0
 devlink_health_report+0x157/0x1b0
 mlx5e_reporter_tx_timeout+0xb9/0xf0 [mlx5_core]
 ? mlx5e_tx_reporter_err_cqe_recover+0x1d0/0x1d0
 [mlx5_core]
 ? mlx5e_health_queue_dump+0xd0/0xd0 [mlx5_core]
 ? update_load_avg+0x19b/0x550
 ? set_next_entity+0x72/0x80
 ? pick_next_task_fair+0x227/0x340
 ? finish_task_switch+0xa2/0x280
   mlx5e_tx_timeout_work+0x83/0xb0 [mlx5_core]
   process_one_work+0x1de/0x3a0
   worker_thread+0x2d/0x3c0
 ? process_one_work+0x3a0/0x3a0
   kthread+0x115/0x130
 ? kthread_park+0x90/0x90
   ret_from_fork+0x1f/0x30
 --[ end trace 51ccabea504edaff ]---
 RIP: 0010:mlx5e_tx_reporter_dump_sq+0xd3/0x180
 PKRU: 55555554
 Kernel panic - not syncing: Fatal exception
 Kernel Offset: disabled
 end Kernel panic - not syncing: Fatal exception

To fix this bug add a wrapper for mlx5e_tx_reporter_dump_sq() which
extracts the sq from struct mlx5e_tx_timeout_ctx and set it as the
TX-timeout-recovery flow dump callback.

Fixes: 5f29458b

 ("net/mlx5e: Support dump callback in TX reporter")
Signed-off-by: default avatarAya Levin <ayal@nvidia.com>
Signed-off-by: default avatarAmir Tzin <amirtz@nvidia.com>
Signed-off-by: default avatarSaeed Mahameed <saeedm@nvidia.com>
      918fc385
    • Chris Mi's avatar
      net/mlx5: Fix tc max supported prio for nic mode · d671e109
      Chris Mi authored 
      Only prio 1 is supported if firmware doesn't support ignore flow
level for nic mode. The offending commit removed the check wrongly.
Add it back.

Fixes: 9a99c8f1

 ("net/mlx5e: E-Switch, Offload all chain 0 priorities when modify header and forward action is not supported")
Signed-off-by: default avatarChris Mi <cmi@nvidia.com>
Reviewed-by: default avatarRoi Dayan <roid@nvidia.com>
Signed-off-by: default avatarSaeed Mahameed <saeedm@nvidia.com>
      d671e109
    • Moshe Shemesh's avatar
      net/mlx5: Fix SF health recovery flow · 33de865f
      Moshe Shemesh authored 
      SF do not directly control the PCI device. During recovery flow SF
should not be allowed to do pci disable or pci reset, its PF will do it.

It fixes the following kernel trace:
mlx5_core.sf mlx5_core.sf.25: mlx5_health_try_recover:387:(pid 40948): starting health recovery flow
mlx5_core 0000:03:00.0: mlx5_pci_slot_reset was called
mlx5_core 0000:03:00.0: wait vital counter value 0xab175 after 1 iterations
mlx5_core.sf mlx5_core.sf.25: firmware version: 24.32.532
mlx5_core.sf mlx5_core.sf.23: mlx5_health_try_recover:387:(pid 40946): starting health recovery flow
mlx5_core 0000:03:00.0: mlx5_pci_slot_reset was called
mlx5_core 0000:03:00.0: wait vital counter value 0xab193 after 1 iterations
mlx5_core.sf mlx5_core.sf.23: firmware version: 24.32.532
mlx5_core.sf mlx5_core.sf.25: mlx5_cmd_check:813:(pid 40948): ENABLE_HCA(0x104) op_mod(0x0) failed,
status bad resource state(0x9), syndrome (0x658908)
mlx5_core.sf mlx5_core.sf.25: mlx5_function_setup:1292:(pid 40948): enable hca failed
mlx5_core.sf mlx5_core.sf.25: mlx5_health_try_recover:389:(pid 40948): health recovery failed

Fixes: 1958fc2f

 ("net/mlx5: SF, Add auxiliary device driver")
Signed-off-by: default avatarMoshe Shemesh <moshe@nvidia.com>
Signed-off-by: default avatarSaeed Mahameed <saeedm@nvidia.com>
      33de865f
    • Shay Drory's avatar
      net/mlx5: Fix error print in case of IRQ request failed · aa968f92
      Shay Drory authored 
      In case IRQ layer failed to find or to request irq, the driver is
printing the first cpu of the provided affinity as part of the error
print. Empty affinity is a valid input for the IRQ layer, and it is
an error to call cpumask_first() on empty affinity.

Remove the first cpu print from the error message.

Fixes: c36326d3

 ("net/mlx5: Round-Robin EQs over IRQs")
Signed-off-by: default avatarShay Drory <shayd@nvidia.com>
Reviewed-by: default avatarMoshe Shemesh <moshe@nvidia.com>
Signed-off-by: default avatarSaeed Mahameed <saeedm@nvidia.com>
      aa968f92
    • Shay Drory's avatar
      net/mlx5: Use first online CPU instead of hard coded CPU · 26a7993c
      Shay Drory authored 
      Hard coded CPU (0 in our case) might be offline. Hence, use the first
online CPU instead.

Fixes: f891b7cd

 ("net/mlx5: Enable single IRQ for PCI Function")
Signed-off-by: default avatarShay Drory <shayd@nvidia.com>
Reviewed-by: default avatarMoshe Shemesh <moshe@nvidia.com>
Signed-off-by: default avatarSaeed Mahameed <saeedm@nvidia.com>
      26a7993c