netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jakub Kicinski <kuba@kernel.org>
To: Tariq Toukan <ttoukan.linux@gmail.com>
Cc: netdev@vger.kernel.org, edumazet@google.com, pabeni@redhat.com,
	borisp@nvidia.com, john.fastabend@gmail.com, maximmi@nvidia.com,
	tariqt@nvidia.com, vfedorenko@novek.ru,
	Ran Rozenstein <ranro@nvidia.com>,
	"gal@nvidia.com" <gal@nvidia.com>,
	"David S. Miller" <davem@davemloft.net>
Subject: Re: [PATCH net-next v3 7/7] tls: rx: do not use the standard strparser
Date: Tue, 2 Aug 2022 08:40:21 -0700	[thread overview]
Message-ID: <20220802084021.2ee26764@kernel.org> (raw)
In-Reply-To: <84406eec-289b-edde-759a-cf0b2c39c150@gmail.com>

On Tue, 2 Aug 2022 17:54:01 +0300 Tariq Toukan wrote:
> Hi Jakub,
> 
> The device offload flow got broken, we started getting the call trace 
> below in our regressions tests.
> 
> Bisecting points to this one as the offending commit.
> 
> I taking a look, but I'm less familiar with this change.
> Probably you have a direction?

Sorry about that, I'll take a look. Would you be able to run it thru
decode_stacktrace before I get to the office and start digging?

>   [  407.560799] rcu: INFO: rcu_sched self-detected stall on CPU
>   [  407.561734] rcu: 	1-....: (5248 ticks this GP) 
> idle=51b/1/0x4000000000000000 softirq=41347/41347 fqs=2625
>   [  407.563101] 	(t=5250 jiffies g=65669 q=4492 ncpus=10)
>   [  407.563859] NMI backtrace for cpu 1
>   [  407.564430] CPU: 1 PID: 45266 Comm: iperf Not tainted 
> 5.19.0-rc7_for-upstream_min-debug_5f35d2896553 #1
>   [  407.565766] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), 
> BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
>   [  407.567319] Call Trace:
>   [  407.567772]  <IRQ>
>   [  407.568168]  dump_stack_lvl+0x34/0x44
>   [  407.568763]  nmi_cpu_backtrace.cold+0x30/0x70
>   [  407.569462]  ? lapic_can_unplug_cpu+0x70/0x70
>   [  407.570146]  nmi_trigger_cpumask_backtrace+0xef/0x100
>   [  407.570897]  trigger_single_cpu_backtrace+0x24/0x27
>   [  407.571635]  rcu_dump_cpu_stacks+0xa0/0xd9
>   [  407.572278]  rcu_sched_clock_irq.cold+0x111/0x2d3
>   [  407.573004]  update_process_times+0x5b/0x90
>   [  407.584227]  tick_sched_timer+0x88/0xa0
>   [  407.584855]  ? tick_sched_do_timer+0xf0/0xf0
>   [  407.585515]  __hrtimer_run_queues+0x139/0x290
>   [  407.586199]  hrtimer_interrupt+0x10e/0x240
>   [  407.586844]  __sysvec_apic_timer_interrupt+0x56/0xd0
>   [  407.587575]  sysvec_apic_timer_interrupt+0x6d/0x90
>   [  407.588293]  </IRQ>
>   [  407.588699]  <TASK>
>   [  407.589118]  asm_sysvec_apic_timer_interrupt+0x16/0x20
>   [  407.589886] RIP: 0010:tls_device_decrypted+0x7a/0x2e0
>   [  407.590641] Code: 83 e7 01 45 0f b6 e7 41 83 f7 01 48 85 d2 45 0f 
> b6 ff 74 1b 0f b6 82 83 00 00 00 48 8b 12 c0 e8 06 41 21 c4 83 f0 01 41 
> 21 c7 <48> 85 d2 75 e5 8b 05 d3 71 ca 00 85 c0 0f 8f 4b 01 00 00 48 8b 85
>   [  407.593152] RSP: 0018:ffff8881a113bb60 EFLAGS: 00000202
>   [  407.593927] RAX: 0000000000000003 RBX: ffff88810e2d6000 RCX: 
> 0000000000000000
>   [  407.594913] RDX: ffff8881792b80d8 RSI: ffff88814ef46800 RDI: 
> ffff8881792b8000
>   [  407.595904] RBP: ffff88814ef46800 R08: 7fffffffffffffff R09: 
> 0000000000000001
>   [  407.596907] R10: ffff888105cd2200 R11: 0000000000022dd1 R12: 
> 0000000000000000
>   [  407.597901] R13: ffff888108f45000 R14: ffff8881792b8000 R15: 
> 0000000000000001
>   [  407.598897]  ? tls_rx_rec_wait+0x225/0x250
>   [  407.599539]  tls_rx_one_record+0xe4/0x2d0
>   [  407.600169]  tls_sw_recvmsg+0x380/0x910
>   [  407.600773]  ? 0xffffffff81000000
>   [  407.601336]  inet6_recvmsg+0x47/0xc0
>   [  407.601932]  ____sys_recvmsg+0x109/0x120
>   [  407.602554]  ? _copy_from_user+0x26/0x60
>   [  407.603171]  ? iovec_from_user+0x4a/0x150
>   [  407.603803]  ___sys_recvmsg+0xa4/0xe0
>   [  407.604394]  ? mlx5e_ktls_add_rx+0x349/0x430 [mlx5_core]
>   [  407.605262]  ? mlx5e_ktls_add_rx+0x3af/0x430 [mlx5_core]
>   [  407.606082]  ? tls_device_attach+0x60/0xe0
>   [  407.606721]  ? tls_set_device_offload_rx+0x11b/0x220
>   [  407.607464]  __sys_recvmsg+0x4e/0x90
>   [  407.608050]  do_syscall_64+0x3d/0x90
>   [  407.608631]  entry_SYSCALL_64_after_hwframe+0x46/0xb0
>   [  407.609400] RIP: 0033:0x7f7a41f856dd

  reply	other threads:[~2022-08-02 15:41 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-07-22 23:50 [PATCH net-next v3 0/7] tls: rx: decrypt from the TCP queue Jakub Kicinski
2022-07-22 23:50 ` [PATCH net-next v3 1/7] tls: rx: wrap recv_pkt accesses in helpers Jakub Kicinski
2022-07-22 23:50 ` [PATCH net-next v3 2/7] tls: rx: factor SW handling out of tls_rx_one_record() Jakub Kicinski
2022-07-22 23:50 ` [PATCH net-next v3 3/7] tls: rx: don't free the output in case of zero-copy Jakub Kicinski
2022-07-22 23:50 ` [PATCH net-next v3 4/7] tls: rx: device: keep the zero copy status with offload Jakub Kicinski
2022-07-22 23:50 ` [PATCH net-next v3 5/7] tcp: allow tls to decrypt directly from the tcp rcv queue Jakub Kicinski
2022-07-22 23:50 ` [PATCH net-next v3 6/7] tls: rx: device: add input CoW helper Jakub Kicinski
2022-07-22 23:50 ` [PATCH net-next v3 7/7] tls: rx: do not use the standard strparser Jakub Kicinski
2022-07-26  9:27   ` Paolo Abeni
2022-07-26 17:01     ` Jakub Kicinski
2022-07-26 17:26       ` Paolo Abeni
2022-08-02 14:54   ` Tariq Toukan
2022-08-02 15:40     ` Jakub Kicinski [this message]
2022-08-04  1:24     ` Jakub Kicinski
2022-08-04  6:13       ` Tariq Toukan
2022-08-04  8:05       ` Tariq Toukan
2022-08-04 15:35         ` Jakub Kicinski
2022-08-07  6:01           ` Tariq Toukan
2022-08-04 15:59         ` Jakub Kicinski
2022-08-07  6:01           ` Tariq Toukan
2022-08-08  5:24             ` Tariq Toukan
2022-08-08 18:24               ` Jakub Kicinski
2022-08-09  8:47                 ` Tariq Toukan
2023-03-09 15:15   ` Tariq Toukan
2023-03-09 17:54     ` Jakub Kicinski
2023-03-12 17:59       ` Tariq Toukan
2023-03-13 18:22         ` Jakub Kicinski
2023-03-15 20:26           ` Tariq Toukan
2023-03-16  1:41             ` Jakub Kicinski
2022-07-26 22:00 ` [PATCH net-next v3 0/7] tls: rx: decrypt from the TCP queue patchwork-bot+netdevbpf

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220802084021.2ee26764@kernel.org \
    --to=kuba@kernel.org \
    --cc=borisp@nvidia.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=gal@nvidia.com \
    --cc=john.fastabend@gmail.com \
    --cc=maximmi@nvidia.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=ranro@nvidia.com \
    --cc=tariqt@nvidia.com \
    --cc=ttoukan.linux@gmail.com \
    --cc=vfedorenko@novek.ru \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).