From: Peter Zijlstra <peterz@infradead.org>
To: Prateek Sood <prsood@codeaurora.org>
Cc: mingo@redhat.com, sramana@codeaurora.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] rwsem: fix missed wakeup due to reordering of load
Date: Thu, 10 Aug 2017 12:44:06 +0200 [thread overview]
Message-ID: <20170810104406.zgpatji2ex2tgre6@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <1501100272-16338-1-git-send-email-prsood@codeaurora.org>
On Thu, Jul 27, 2017 at 01:47:52AM +0530, Prateek Sood wrote:
> diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
> index 34e727f..21c111a 100644
> --- a/kernel/locking/rwsem-xadd.c
> +++ b/kernel/locking/rwsem-xadd.c
> @@ -585,6 +585,40 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
> unsigned long flags;
> DEFINE_WAKE_Q(wake_q);
>
> + /*
> + * If a spinner is present, there is a chance that the load of
> + * rwsem_has_spinner() in rwsem_wake() can be reordered with
> + * respect to decrement of rwsem count in __up_write() leading
> + * to wakeup being missed.
> + *
> + * spinning writer up_write caller
> + * --------------- -----------------------
> + * [S] osq_unlock() [L] osq
> + * spin_lock(wait_lock)
> + * sem->count=0xFFFFFFFF00000001
> + * +0xFFFFFFFF00000000
> + * count=sem->count
> + * MB
> + * sem->count=0xFFFFFFFE00000001
> + * -0xFFFFFFFF00000001
> + * spin_trylock(wait_lock)
> + * return
> + * rwsem_try_write_lock(count)
> + * spin_unlock(wait_lock)
> + * schedule()
> + *
> + * Reordering of atomic_long_sub_return_release() in __up_write()
> + * and rwsem_has_spinner() in rwsem_wake() can cause missing of
> + * wakeup in up_write() context. In spinning writer, sem->count
> + * and local variable count is 0XFFFFFFFE00000001. It would result
> + * in rwsem_try_write_lock() failing to acquire rwsem and spinning
> + * writer going to sleep in rwsem_down_write_failed().
> + *
> + * The smp_rmb() here is to make sure that the spinner state is
> + * consulted after sem->count is updated in up_write context.
I feel that comment can use help.. for example the RMB you add below is
not present at all.
> + */
> + smp_rmb();
> +
> /*
> * If a spinner is present, it is not necessary to do the wakeup.
> * Try to do wakeup only if the trylock succeeds to minimize
Your patch is whitespace damaged, all the indentation on the + lines is
with spaces. Please resend with \t.
next prev parent reply other threads:[~2017-08-10 10:44 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-07-26 20:17 [PATCH] rwsem: fix missed wakeup due to reordering of load Prateek Sood
2017-07-27 15:48 ` Waiman Long
2017-07-27 16:59 ` Peter Zijlstra
2017-08-10 8:32 ` Andrea Parri
2017-08-10 10:41 ` Peter Zijlstra
2017-08-10 10:44 ` Peter Zijlstra [this message]
2017-08-23 11:28 Prateek Sood
2017-08-24 11:29 ` Peter Zijlstra
2017-08-24 12:33 ` Peter Zijlstra
2017-08-24 12:52 ` Peter Zijlstra
2017-09-07 14:08 ` Prateek Sood
2017-09-07 14:30 Prateek Sood
2017-09-19 14:05 ` Andrea Parri
2017-09-20 14:52 ` Davidlohr Bueso
2017-09-20 21:17 ` Andrea Parri
2017-09-27 21:20 ` Davidlohr Bueso
2017-09-26 18:37 ` Prateek Sood
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=20170810104406.zgpatji2ex2tgre6@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=prsood@codeaurora.org \
--cc=sramana@codeaurora.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).