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>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <5226cedc180a1126ac5cdb48ee9aa9ef8b594452.camel@nvidia.com>
Date: Fri, 19 Apr 2024 15:09:32 +0000
From: Dragos Tatulea <dtatulea@...dia.com>
To: Shay Drori <shayd@...dia.com>, "netdev@...r.kernel.org"
	<netdev@...r.kernel.org>, "oxana@...udflare.com" <oxana@...udflare.com>
CC: "davem@...emloft.net" <davem@...emloft.net>, Rahul Rameshbabu
	<rrameshbabu@...dia.com>, "kernel-team@...udflare.com"
	<kernel-team@...udflare.com>, "kuba@...nel.org" <kuba@...nel.org>,
	"Anatoli.Chechelnickiy@...nterpipe.biz"
	<Anatoli.Chechelnickiy@...nterpipe.biz>, "edumazet@...gle.com"
	<edumazet@...gle.com>, Saeed Mahameed <saeedm@...dia.com>, "leon@...nel.org"
	<leon@...nel.org>, "pabeni@...hat.com" <pabeni@...hat.com>
Subject: Re: mlx5 driver fails to detect NIC in 6.6.28

On Fri, 2024-04-19 at 14:06 +0000, Dragos Tatulea wrote:
> On Fri, 2024-04-19 at 13:45 +0100, Oxana Kharitonova wrote:
> > Hello,
> > 
> > NIC stopped being detected in Linux 6.6.28. The problem was observed on 
> > two servers, after reverting kernel to 6.6.25 (our current stable version) 
> > everything returned to normal.
> > 
> > We suspect commit "net/mlx5e: Do not produce metadata freelist entries in 
> > Tx port ts WQE xmit", but we haven't done bisect yet. 
> > 
> The issue appears only in 6.6.28. Bisectet down to commit "net/mlx5: Register
> devlink first under devlink lock" which was added to 6.6.28. Note that latest
> stable 6.8 doesn't have this issue.
> 
> Tried quickly looking around and found that "net/mlx5: Restore mistakenly
> dropped parts in register devlink flow" was missing. But it didn't help
> unfortunately.
> 
> Adding Shay as he probably has more context.
> 
Was tipped by Shay that the missing commit from stable is 0553e753ea9e
"net/mlx5: E-switch, store eswitch pointer before registering devlink_param".
Tested on my side and it works.

Oxana, would it be a tall ask to get this patch tested on your end as well
before we ask for inclusion in 6.6.x stable? 

Thanks,
Dragos

> 
> 
> > The kernel log is below.
> > 
> > root@...alhost:~# ifconfig
> > lo: flags=73<UP,LOOPBACK,RUNNING>  mtu 65536
> >        inet 127.0.0.1  netmask 255.0.0.0
> >        inet6 ::1  prefixlen 128  scopeid 0x10<host>
> >        loop  txqueuelen 1000  (Local Loopback)
> >        RX packets 80  bytes 6480 (6.3 KiB)
> >        RX errors 0  dropped 0  overruns 0  frame 0
> >        TX packets 80  bytes 6480 (6.3 KiB)
> >        TX errors 0  dropped 0 overruns 0  carrier 0  collisions 0
> > 
> > root@...alhost:~# lspci | grep Eth
> > c1:00.0 Ethernet controller: Mellanox Technologies MT27710 Family [ConnectX-4 Lx]
> > c1:00.1 Ethernet controller: Mellanox Technologies MT27710 Family [ConnectX-4 Lx]
> > 
> > [   23.519113] RIP: 0010:esw_port_metadata_get (drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c:4095 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c:2442) mlx5_core
> > [   23.524293] usb 2-1: new SuperSpeed USB device number 2 using xhci_hcd
> > [ 23.528602] Code: eb 8e 0f 1f 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 53 48 89 d3 e8 f2 5d ea c9 48 8b 80 b0 09 00 00 <8b> 80 18 11 00 00 88 03 31 c0 80 23 01 5b e9 38 1f f3 c9 0f 1f 84
> > All code
> > ========
> >    0:	eb 8e                	jmp    0xffffffffffffff90
> >    2:	0f 1f 00             	nopl   (%rax)
> >    5:	90                   	nop
> >    6:	90                   	nop
> >    7:	90                   	nop
> >    8:	90                   	nop
> >    9:	90                   	nop
> >    a:	90                   	nop
> >    b:	90                   	nop
> >    c:	90                   	nop
> >    d:	90                   	nop
> >    e:	90                   	nop
> >    f:	90                   	nop
> >   10:	90                   	nop
> >   11:	90                   	nop
> >   12:	90                   	nop
> >   13:	90                   	nop
> >   14:	90                   	nop
> >   15:	0f 1f 44 00 00       	nopl   0x0(%rax,%rax,1)
> >   1a:	53                   	push   %rbx
> >   1b:	48 89 d3             	mov    %rdx,%rbx
> >   1e:	e8 f2 5d ea c9       	call   0xffffffffc9ea5e15
> >   23:	48 8b 80 b0 09 00 00 	mov    0x9b0(%rax),%rax
> >   2a:*	8b 80 18 11 00 00    	mov    0x1118(%rax),%eax		<-- trapping instruction
> >   30:	88 03                	mov    %al,(%rbx)
> >   32:	31 c0                	xor    %eax,%eax
> >   34:	80 23 01             	andb   $0x1,(%rbx)
> >   37:	5b                   	pop    %rbx
> >   38:	e9 38 1f f3 c9       	jmp    0xffffffffc9f31f75
> >   3d:	0f                   	.byte 0xf
> >   3e:	1f                   	(bad)
> >   3f:	84                   	.byte 0x84
> > 
> > Code starting with the faulting instruction
> > ===========================================
> >    0:	8b 80 18 11 00 00    	mov    0x1118(%rax),%eax
> >    6:	88 03                	mov    %al,(%rbx)
> >    8:	31 c0                	xor    %eax,%eax
> >    a:	80 23 01             	andb   $0x1,(%rbx)
> >    d:	5b                   	pop    %rbx
> >    e:	e9 38 1f f3 c9       	jmp    0xffffffffc9f31f4b
> >   13:	0f                   	.byte 0xf
> >   14:	1f                   	(bad)
> >   15:	84                   	.byte 0x84
> > [   23.528604] RSP: 0018:ffffc9000dbbfba8 EFLAGS: 00010282
> > [   23.530802] hub 1-1:1.0: 4 ports detected
> > [   23.537574] RAX: 0000000000000000 RBX: ffffc9000dbbfbfc RCX: 0000000000000028
> > [   23.537576] RDX: ffffc9000dbbfbfc RSI: 0000000000000013 RDI: ffff88811ec38000
> > [   23.537578] RBP: ffffffffc23fa560 R08: 0000000000000000 R09: 0000000000000000
> > [   23.537580] R10: 0000000000036ea0 R11: 0000000000000dc0 R12: ffff889850104f00
> > [   23.547568] usb 2-1: New USB device found, idVendor=05e3, idProduct=0620, bcdDevice=93.03
> > [   23.564222] R13: ffff8881075ca840 R14: ffff88811ec38000 R15: 0000000000000000
> > [   23.564224] FS:  0000000000000000(0000) GS:ffff88843fa00000(0000) knlGS:0000000000000000
> > [   23.564226] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> > [   23.570143] usb 2-1: New USB device strings: Mfr=1, Product=2, SerialNumber=0
> > [   23.574839] CR2: 0000000000001118 CR3: 0000000c7af5c000 CR4: 0000000000350ef0
> > [   23.574841] Call Trace:
> > [   23.574844]  <TASK>
> > [   23.574846] ? __die (arch/x86/kernel/dumpstack.c:421 arch/x86/kernel/dumpstack.c:434) 
> > [   23.590485] ? page_fault_oops (arch/x86/mm/fault.c:707) 
> > [   23.590490] ? get_page_from_freelist (mm/page_alloc.c:1553 mm/page_alloc.c:3177) 
> > [   23.606129] ? exc_page_fault (arch/x86/include/asm/irqflags.h:37 arch/x86/include/asm/irqflags.h:72 arch/x86/mm/fault.c:1504 arch/x86/mm/fault.c:1552) 
> > [   23.655856] ? asm_exc_page_fault (arch/x86/include/asm/idtentry.h:570) 
> > [   23.671501] ? esw_port_metadata_get (drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c:4095 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c:2442) mlx5_core
> > [   23.790812] ? esw_port_metadata_get (drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c:4095 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c:2442) mlx5_core
> > [   23.955180] devlink_nl_param_fill.constprop.0 (net/devlink/param.c:268) 
> > [   23.961276] ? __alloc_skb (net/core/skbuff.c:651 (discriminator 1)) 
> > [   23.974490] ? srso_return_thunk (arch/x86/lib/retpoline.S:217) 
> > [   23.987013] ? __kmalloc_node_track_caller (mm/slab_common.c:1025 mm/slab_common.c:1046) 
> > [   23.987018] ? srso_return_thunk (arch/x86/lib/retpoline.S:217) 
> > [   23.997812] ? kmalloc_reserve (net/core/skbuff.c:584) 
> > [   23.997816] ? srso_return_thunk (arch/x86/lib/retpoline.S:217) 
> > [   24.007217] ? __alloc_skb (net/core/skbuff.c:666) 
> > [   24.007222] devlink_param_notify.constprop.0 (net/devlink/param.c:354 net/devlink/param.c:330) 
> > [   24.055512] devl_params_register (net/devlink/param.c:686 (discriminator 1)) 
> > [   24.055516] esw_offloads_init (drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c:2482) mlx5_core
> > [   24.065009] mlx5_eswitch_init (drivers/net/ethernet/mellanox/mlx5/core/eswitch.c:1872) mlx5_core
> > [   24.165229] mlx5_init_one_devl_locked (drivers/net/ethernet/mellanox/mlx5/core/main.c:1022 drivers/net/ethernet/mellanox/mlx5/core/main.c:1447) mlx5_core
> > [   24.177007] probe_one (drivers/net/ethernet/mellanox/mlx5/core/main.c:1507 drivers/net/ethernet/mellanox/mlx5/core/main.c:1947) mlx5_core
> > [   24.187296] local_pci_probe (drivers/pci/pci-driver.c:325) 
> > [   24.196698] work_for_cpu_fn (kernel/workqueue.c:5618 (discriminator 1)) 
> > [   24.205988] process_one_work (kernel/workqueue.c:2632) 
> > [   24.215612] worker_thread (kernel/workqueue.c:2694 (discriminator 2) kernel/workqueue.c:2781 (discriminator 2)) 
> > [   24.224999] ? __pfx_worker_thread (kernel/workqueue.c:2727) 
> > [   24.234912] kthread (kernel/kthread.c:388) 
> > [   24.243647] ? __pfx_kthread (kernel/kthread.c:341) 
> > [   24.252988] ret_from_fork (arch/x86/kernel/process.c:153) 
> > [   24.262103] ? __pfx_kthread (kernel/kthread.c:341) 
> > [   24.271347] ret_from_fork_asm (arch/x86/entry/entry_64.S:314) 
> > [   24.280754]  </TASK>
> > 
> > 
> 

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ