[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CANaxB-z=3y+_Eihq-NGRr7YtnyBBNtRo2r4WgKVgTzcJMwTzvw@mail.gmail.com>
Date: Mon, 16 Oct 2017 16:11:47 -0700
From: Andrei Vagin <avagin@...il.com>
To: Linux Kernel Network Developers <netdev@...r.kernel.org>,
Eric Dumazet <edumazet@...gle.com>
Subject: Re: net-next: WARNING: CPU: 0 PID: 1544 at net/ipv4/tcp_input.c:889
Hi Eric,
Could you take a look at this warning? It may be related with your
recent patches. First time we saw this warning 7 days ago
(net-next/master) and now we see it regularly.
I printed tp->fackets_out and state->reord before the warnings and
here are values for them:
tp->fackets_out = -1 state->reord = 4
In my case, this warning is triggered for connections which have been
restored by CRIU.
Let me know if you need any other information. I can reproduce this
bugs for an hour.
Thanks,
Andrei
On Mon, Oct 9, 2017 at 11:07 AM, Andrei Vagin <avagin@...il.com> wrote:
> Hello,
>
> We run CRIU tests on a daily basis for net-next and today they
> triggered a following warning:
>
>
> [ 58.827039] ------------[ cut here ]------------
> [ 58.827078] WARNING: CPU: 0 PID: 1544 at net/ipv4/tcp_input.c:889
> tcp_update_reordering+0x9f/0xb0
> [ 58.827083] Modules linked in:
> [ 58.827095] CPU: 0 PID: 1544 Comm: sshd Not tainted 4.14.0-rc3+ #1
> [ 58.827101] Hardware name: Google Google Compute Engine/Google
> Compute Engine, BIOS Google 01/01/2011
> [ 58.827106] task: ffff90f2633dcc80 task.stack: ffffb0e302800000
> [ 58.827112] RIP: 0010:tcp_update_reordering+0x9f/0xb0
> [ 58.827117] RSP: 0018:ffffb0e302803b28 EFLAGS: 00010282
> [ 58.827126] RAX: 00000000fffffffd RBX: ffff90f29136e840 RCX: 0000000000000003
> [ 58.827131] RDX: 0000000000000000 RSI: 00000000fffffffd RDI: ffff90f29136de80
> [ 58.827136] RBP: ffffb0e302803b28 R08: 0000000000000044 R09: 00000000e59da6c6
> [ 58.827142] R10: ffffb0e302803b68 R11: 00000000e59da70a R12: 00000000e59da6c6
> [ 58.827147] R13: ffff90f29136e848 R14: ffff90f29136de80 R15: 0000000000000002
> [ 58.827153] FS: 00007f52e8452840(0000) GS:ffff90f29fc00000(0000)
> knlGS:0000000000000000
> [ 58.827158] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [ 58.827163] CR2: 000014727db10a10 CR3: 00000001d0967000 CR4: 00000000001406f0
> [ 58.827172] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> [ 58.827177] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
> [ 58.827182] Call Trace:
> [ 58.827191] tcp_sacktag_write_queue+0x54d/0x860
> [ 58.827206] tcp_ack+0xa71/0x1360
> [ 58.827229] tcp_rcv_established+0x1da/0x560
> [ 58.827241] tcp_v4_do_rcv+0x139/0x1d0
> [ 58.827251] __release_sock+0x6d/0x110
> [ 58.827260] release_sock+0x30/0xb0
> [ 58.827267] tcp_sendmsg+0x37/0x50
> [ 58.827276] inet_sendmsg+0x45/0x1e0
> [ 58.827287] sock_sendmsg+0x38/0x50
> [ 58.827295] sock_write_iter+0x7e/0xd0
> [ 58.827311] __vfs_write+0xd4/0x150
> [ 58.827325] vfs_write+0xcd/0x1d0
> [ 58.827332] ? trace_hardirqs_on_caller+0x11f/0x190
> [ 58.827341] SyS_write+0x49/0xa0
> [ 58.827353] entry_SYSCALL_64_fastpath+0x23/0xc2
> [ 58.827360] RIP: 0033:0x7f52e6186710
> [ 58.827365] RSP: 002b:00007fffd37723b8 EFLAGS: 00000246 ORIG_RAX:
> 0000000000000001
> [ 58.827375] RAX: ffffffffffffffda RBX: 000000002e3e9273 RCX: 00007f52e6186710
> [ 58.827380] RDX: 0000000000000044 RSI: 0000557474a3e160 RDI: 0000000000000003
> [ 58.827385] RBP: 00007f52e7237240 R08: 0000000000000006 R09: 0000000000000001
> [ 58.827390] R10: 0000000000004da8 R11: 0000000000000246 R12: 000000005bb2be1e
> [ 58.827396] R13: 00000000e9218d7d R14: 0000000059b77fb7 R15: 00000000505bdd2c
> [ 58.827414] Code: b8 1d 00 00 00 c0 ea 04 84 d2 74 0b 89 d0 c1 e0
> 1e c1 f8 1f 83 c0 1c 48 8b 57 30 48 98 48 8b 92 00 02 00 00 65 48 ff
> 04 c2 5d c3 <0f> ff 5d c3 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 0f 1f
> 44 00
> [ 58.827724] ---[ end trace b8d78168bbc71c1f ]---
>
> Here is a fill log:
> https://travis-ci.org/avagin/linux/jobs/285457708
Powered by blists - more mailing lists