From: Waiman Long <longman@redhat.com>
To: 马振华 <mazhenhua@xiaomi.com>, peterz <peterz@infradead.org>,
mingo <mingo@redhat.com>, will <will@kernel.org>,
"boqun.feng" <boqun.feng@gmail.com>,
linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: [BUG]locking/rwsem: only clean RWSEM_FLAG_HANDOFF when already set
Date: Sat, 6 Nov 2021 23:25:38 -0400 [thread overview]
Message-ID: <55bfbf1c-5906-9cc9-ee68-a1c69651bbc3@redhat.com> (raw)
In-Reply-To: <4fafad133b074f279dbab1aa3642e23f@xiaomi.com>
On 11/6/21 08:39, 马振华 wrote:
> Dear longman,
>
> recently , i find a issue which rwsem count is negative value, it
> happened always when a task try to get the lock
> with __down_write_killable , then it is killed
>
> this issue happened like this
>
> CPU2 CPU4
> task A[reader] task B[writer]
> down_read_killable[locked]
> sem->count=0x100
> down_write_killable
> sem->count=0x102[wlist not empty]
> up_read
> count=0x2
> sig kill received
> down_read_killable
> sem->count=0x102[wlist not empty]
> goto branch out_nolock:
> list_del(&waiter.list);
> wait list is empty
> sem->count-RWSEM_FLAG_HANDOFF
> sem->count=0xFE
> list_empty(&sem->wait_list) is TRUE
> sem->count andnot RWSEM_FLAG_WAITERS
> sem->count=0xFC
> up_read
> sem->count -= 0x100
> sem->count=0xFFFFFFFFFFFFFFFC
> DEBUG_RWSEMS_WARN_ON(tmp < 0, sem);
>
> so sem->count will be negative after writer is killed
> i think if flag RWSEM_FLAG_HANDOFF is not set, we shouldn't clean it
Thanks for reporting this possible race condition.
However, I am still trying to figure how it is possible to set the
wstate to WRITER_HANDOFF without actually setting the handoff bit as
well. The statement sequence should be as follows:
wstate = WRITER_HANDOFF;
raw_spin_lock_irq(&sem->wait_lock);
if (rwsem_try_write_lock(sem, wstate))
raw_spin_unlock_irq(&sem->wait_lock);
:
if (signal_pending_state(state, current))
goto out_nolock
The rwsem_try_write_lock() function will make sure that we either
acquire the lock and clear handoff or set the handoff bit. This should
be done before we actually check for signal. I do think that it is
probably safer to use atomic_long_andnot to clear the handoff bit
instead of using atomic_long_add().
Cheers,
Longman
next parent reply other threads:[~2021-11-07 3:26 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <4fafad133b074f279dbab1aa3642e23f@xiaomi.com>
2021-11-07 3:25 ` Waiman Long [this message]
2021-11-07 3:28 ` [BUG]locking/rwsem: only clean RWSEM_FLAG_HANDOFF when already set Waiman Long
[not found] ` <20211107090131.1535-1-hdanton@sina.com>
2021-11-07 15:24 ` Waiman Long
2021-11-07 19:52 ` Waiman Long
2021-11-10 21:38 ` Peter Zijlstra
2021-11-11 2:42 ` Maria Yu
2021-11-11 15:08 ` Peter Zijlstra
2021-11-11 19:14 ` Waiman Long
2021-11-11 19:20 ` Peter Zijlstra
2021-11-11 19:36 ` Waiman Long
2021-11-11 19:52 ` Waiman Long
2021-11-11 20:26 ` Peter Zijlstra
2021-11-11 21:01 ` Waiman Long
2021-11-11 21:25 ` Waiman Long
2021-11-11 21:53 ` Peter Zijlstra
2021-11-11 21:55 ` Waiman Long
2021-11-11 22:00 ` Waiman Long
2021-11-11 21:38 ` Peter Zijlstra
2021-11-11 21:46 ` Waiman Long
2021-11-11 20:35 ` Peter Zijlstra
2021-11-11 20:39 ` Peter Zijlstra
2021-11-11 20:45 ` Waiman Long
2021-11-11 21:27 ` Peter Zijlstra
2021-11-11 21:54 ` Waiman Long
2021-11-11 20:50 ` Peter Zijlstra
2021-11-11 21:09 ` Waiman Long
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=55bfbf1c-5906-9cc9-ee68-a1c69651bbc3@redhat.com \
--to=longman@redhat.com \
--cc=boqun.feng@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mazhenhua@xiaomi.com \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=will@kernel.org \
/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).