From: Pavel Begunkov <[email protected]>
To: Gabriel Krisman Bertazi <[email protected]>,
syzbot <[email protected]>
Cc: [email protected], [email protected],
[email protected], [email protected]
Subject: Re: [PATCH] io_uring: Don't set affinity on a dying sqpoll thread
Date: Tue, 29 Aug 2023 14:21:46 +0100 [thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>
...
> Jens,
>
> I'm not sure I got the whole story on this one, but it seems fairly
> trivial to reproduce and I can't see another way it could be
> triggered. What do you think?
Right, it can be null and that should be checked. I haven't taken
a look at the report but the patch looks good regardless, thanks
> -- >8 --
> Subject: [PATCH] io_uring: Don't set affinity on a dying sqpoll thread
>
> Syzbot reported a null-ptr-deref of sqd->thread inside
> io_sqpoll_wq_cpu_affinity. It turns out the sqd->thread can go away
> from under us during io_uring_register, in case the process gets a
> fatal signal during io_uring_register.
>
> It is not particularly hard to hit the race, and while I am not sure
> this is the exact case hit by syzbot, it solves it. Finally, checking
> ->thread is enough to close the race because we locked sqd while
> "parking" the thread, thus preventing it from going away.
>
> I reproduced it fairly consistently with a program that does:
>
> int main(void) {
> ...
> io_uring_queue_init(RING_LEN, &ring1, IORING_SETUP_SQPOLL);
> while (1) {
> io_uring_register_iowq_aff(ring, 1, &mask);
> }
> }
>
> Executed in a loop with timeout to trigger SIGTERM:
> while true; do timeout 1 /a.out ; done
>
> This will hit the following BUG() in very few attempts.
>
> BUG: kernel NULL pointer dereference, address: 00000000000007a8
> PGD 800000010e949067 P4D 800000010e949067 PUD 10e46e067 PMD 0
> Oops: 0000 [#1] PREEMPT SMP PTI
> CPU: 0 PID: 15715 Comm: dead-sqpoll Not tainted 6.5.0-rc7-next-20230825-g193296236fa0-dirty #23
> Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
> RIP: 0010:io_sqpoll_wq_cpu_affinity+0x27/0x70
> Code: 90 90 90 0f 1f 44 00 00 55 53 48 8b 9f 98 03 00 00 48 85 db 74 4f
> 48 89 df 48 89 f5 e8 e2 f8 ff ff 48 8b 43 38 48 85 c0 74 22 <48> 8b b8
> a8 07 00 00 48 89 ee e8 ba b1 00 00 48 89 df 89 c5 e8 70
> RSP: 0018:ffffb04040ea7e70 EFLAGS: 00010282
> RAX: 0000000000000000 RBX: ffff93c010749e40 RCX: 0000000000000001
> RDX: 0000000000000000 RSI: ffffffffa7653331 RDI: 00000000ffffffff
> RBP: ffffb04040ea7eb8 R08: 0000000000000000 R09: c0000000ffffdfff
> R10: ffff93c01141b600 R11: ffffb04040ea7d18 R12: ffff93c00ea74840
> R13: 0000000000000011 R14: 0000000000000000 R15: ffff93c00ea74800
> FS: 00007fb7c276ab80(0000) GS:ffff93c36f200000(0000) knlGS:0000000000000000
> CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> CR2: 00000000000007a8 CR3: 0000000111634003 CR4: 0000000000370ef0
> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
> Call Trace:
> <TASK>
> ? __die_body+0x1a/0x60
> ? page_fault_oops+0x154/0x440
> ? do_user_addr_fault+0x174/0x7b0
> ? exc_page_fault+0x63/0x140
> ? asm_exc_page_fault+0x22/0x30
> ? io_sqpoll_wq_cpu_affinity+0x27/0x70
> __io_register_iowq_aff+0x2b/0x60
> __io_uring_register+0x614/0xa70
> __x64_sys_io_uring_register+0xaa/0x1a0
> do_syscall_64+0x3a/0x90
> entry_SYSCALL_64_after_hwframe+0x6e/0xd8
> RIP: 0033:0x7fb7c226fec9
> Code: 2e 00 b8 ca 00 00 00 0f 05 eb a5 66 0f 1f 44 00 00 48 89 f8 48 89
> f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01
> f0 ff ff 73 01 c3 48 8b 0d 97 7f 2d 00 f7 d8 64 89 01 48
> RSP: 002b:00007ffe2c0674f8 EFLAGS: 00000246 ORIG_RAX: 00000000000001ab
> RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fb7c226fec9
> RDX: 00007ffe2c067530 RSI: 0000000000000011 RDI: 0000000000000003
> RBP: 00007ffe2c0675d0 R08: 00007ffe2c067550 R09: 00007ffe2c067550
> R10: 0000000000000001 R11: 0000000000000246 R12: 0000000000000000
> R13: 00007ffe2c067750 R14: 0000000000000000 R15: 0000000000000000
> </TASK>
> Modules linked in:
> CR2: 00000000000007a8
> ---[ end trace 0000000000000000 ]---
>
> Reported-by: [email protected]
> Fixes: ebdfefc09c6d ("io_uring/sqpoll: fix io-wq affinity when IORING_SETUP_SQPOLL is used")
> Signed-off-by: Gabriel Krisman Bertazi <[email protected]>
> ---
> io_uring/sqpoll.c | 4 +++-
> 1 file changed, 3 insertions(+), 1 deletion(-)
>
> diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
> index ee2d2c687fda..bd6c2c7959a5 100644
> --- a/io_uring/sqpoll.c
> +++ b/io_uring/sqpoll.c
> @@ -430,7 +430,9 @@ __cold int io_sqpoll_wq_cpu_affinity(struct io_ring_ctx *ctx,
>
> if (sqd) {
> io_sq_thread_park(sqd);
> - ret = io_wq_cpu_affinity(sqd->thread->io_uring, mask);
> + /* Don't set affinity for a dying thread */
> + if (sqd->thread)
> + ret = io_wq_cpu_affinity(sqd->thread->io_uring, mask);
> io_sq_thread_unpark(sqd);
> }
>
--
Pavel Begunkov
next prev parent reply other threads:[~2023-08-29 13:28 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-08-28 9:59 [syzbot] [io-uring?] general protection fault in io_sqpoll_wq_cpu_affinity syzbot
2023-08-28 23:42 ` [PATCH] io_uring: Don't set affinity on a dying sqpoll thread Gabriel Krisman Bertazi
2023-08-29 13:21 ` Pavel Begunkov [this message]
2023-08-29 14:04 ` Jens Axboe
2023-08-29 17:37 ` Jens Axboe
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 \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
/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