netdev - mlx5_core irisc not responding

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [day] [month] [year] [list]

Date:   Tue, 21 Apr 2020 14:23:38 +1000
From:   Alexey Kardashevskiy <aik@...abs.ru>
To:     "netdev@...r.kernel.org" <netdev@...r.kernel.org>
Cc:     Leon Romanovsky <leon@...nel.org>,
        Saeed Mahameed <saeedm@...lanox.com>
Subject: mlx5_core irisc not responding

Hi!

I got a Mellanox CX4 card constantly complaining  about "irisc not
responding" (below). Is there a way to get a better idea what it is
unhappy about? It is plugged to an experimental POWER9 box which might
have PCI problems. The kernel is v5.6.0.

I thought I try updating the firmware first but mlxup refuses to update
the firmware as it is an OEM adapter (below); and there is no way to
find out which Mellanox PSID corresponds to what I got, any hints? Thanks,



The device is:

root@...ssss2:~# mstflint -d 0001:19:00.0 q
Image type:            FS3
FW Version:            14.26.0226
FW Release Date:       4.8.2019
Product Version:       6.0226
Description:           UID                GuidsNumber
Base GUID:             0894ef030080a89f        8
Base MAC:              00000894ef80a89f        8
Image VSD:             N/A
Device VSD:            N/A
PSID:                  IBM0000000034
Security Attributes:   N/A


root@...swift2:~# ./mlxup
Querying Mellanox devices firmware ...
    Device #1:

----------
      Device Type:      ConnectX4LX

  Part Number:      IBM_CX4LX_2p_10GE_x4_Ax
  Description:      ConnectX-4 LX 10 and 1 G-BaseT dual-port BP; PCIe3.0 x4;
  PSID:             IBM0000000034
  PCI Device Name:  0001:19:00.0
  Base MAC:         0894ef80a89f
  Versions:         Current        Available
     FW             14.26.0226     N/A             Status:           No
matching image found


dmesg (the same for :0001:19:00.1):

[   13.283418] mlx5_core 0001:19:00.0: print_health_info:374:(pid 0):
assert_var[0] 0x00000001
[   13.283447] mlx5_core 0001:19:00.0: print_health_info:374:(pid 0):
assert_var[1] 0x0087f14c
[   13.283481] mlx5_core 0001:19:00.0: print_health_info:374:(pid 0):
assert_var[2] 0x00000000
[   13.283535] mlx5_core 0001:19:00.0: print_health_info:374:(pid 0):
assert_var[3] 0x01020000
[   13.283588] mlx5_core 0001:19:00.0: print_health_info:374:(pid 0):
assert_var[4] 0x00000000
[   13.283631] mlx5_core 0001:19:00.0: print_health_info:377:(pid 0):
assert_exit_ptr 0x0080e428
[   13.283667] mlx5_core 0001:19:00.0: print_health_info:379:(pid 0):
assert_callra 0x0080e070
[   13.283726] mlx5_core 0001:19:00.0: print_health_info:381:(pid 0):
fw_ver 14.26.226
[   13.283786] mlx5_core 0001:19:00.0: print_health_info:382:(pid 0):
hw_id 0x0000020b
[   13.283840] mlx5_core 0001:19:00.0: print_health_info:383:(pid 0):
irisc_index 2
[   13.283908] mlx5_core 0001:19:00.0: print_health_info:385:(pid 0):
synd 0x7: irisc not responding
[   13.283949] mlx5_core 0001:19:00.0: print_health_info:386:(pid 0):
ext_synd 0x00c0
[   13.284014] mlx5_core 0001:19:00.0: print_health_info:388:(pid 0):
raw fw_ver 0xe01a00e2




-- 
Alexey