From: Chris Wilson <chris@chris-wilson.co.uk>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
Waiman Long <waiman.long@hpe.com>, Jason Low <jason.low2@hpe.com>,
Ding Tianhong <dingtianhong@huawei.com>,
Thomas Gleixner <tglx@linutronix.de>,
Will Deacon <Will.Deacon@arm.com>, Ingo Molnar <mingo@redhat.com>,
Imre Deak <imre.deak@intel.com>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Davidlohr Bueso <dave@stgolabs.net>,
Tim Chen <tim.c.chen@linux.intel.com>,
Terry Rudd <terry.rudd@hpe.com>,
"Paul E. McKenney" <paulmck@us.ibm.com>,
Jason Low <jason.low2@hp.com>,
Daniel Vetter <daniel.vetter@ffwll.ch>
Subject: Re: [PATCH -v4 5/8] locking/mutex: Add lock handoff to avoid starvation
Date: Tue, 27 Dec 2016 13:55:41 +0000 [thread overview]
Message-ID: <20161227135541.GB1717@nuc-i3427.alporthouse.com> (raw)
In-Reply-To: <20161007150211.196801561@infradead.org>
On Fri, Oct 07, 2016 at 04:52:48PM +0200, Peter Zijlstra wrote:
> Implement lock handoff to avoid lock starvation.
>
> Lock starvation is possible because mutex_lock() allows lock stealing,
> where a running (or optimistic spinning) task beats the woken waiter
> to the acquire.
>
> Lock stealing is an important performance optimization because waiting
> for a waiter to wake up and get runtime can take a significant time,
> during which everyboy would stall on the lock.
>
> The down-side is of course that it allows for starvation.
>
> This patch has the waiter requesting a handoff if it fails to acquire
> the lock upon waking. This re-introduces some of the wait time,
> because once we do a handoff we have to wait for the waiter to wake up
> again.
>
> A future patch will add a round of optimistic spinning to attempt to
> alleviate this penalty, but if that turns out to not be enough, we can
> add a counter and only request handoff after multiple failed wakeups.
>
> There are a few tricky implementation details:
>
> - accepting a handoff must only be done in the wait-loop. Since the
> handoff condition is owner == current, it can easily cause
> recursive locking trouble.
>
> - accepting the handoff must be careful to provide the ACQUIRE
> semantics.
>
> - having the HANDOFF bit set on unlock requires care, we must not
> clear the owner.
>
> - we must be careful to not leave HANDOFF set after we've acquired
> the lock. The tricky scenario is setting the HANDOFF bit on an
> unlocked mutex.
There's a hole along the interruptible path - we leave the HANDOFF bit
set, even though the first waiter returns with -EINTR. The unlock then
sees the HANDOFF, assigns it to the next waiter, but that waiter does a
racy check to decide if it is first, decides it is not and so skips the
trylock and also returns with -EINTR. (i.e. invalidating the
/*
* Here we order against unlock; we must either see it change
* state back to RUNNING and fall through the next schedule(),
* or we must see its unlock and acquire.
*/
as we may not reach the next schedule). Repeating the
__mutex_waiter_is_first() after acquiring the wait_lock is sufficient,
as is clearing the HANDOFF bit before -EINTR.
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 9b349619f431..6f7e3bf0d595 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -684,6 +684,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
* against mutex_unlock() and wake-ups do not go missing.
*/
if (unlikely(signal_pending_state(state, task))) {
+ if (first)
+ __mutex_clear_flag(lock, MUTEX_FLAG_HANDOFF);
ret = -EINTR;
goto err;
}
Though I expect you will be able to find a better solution.
-Chris
--
Chris Wilson, Intel Open Source Technology Centre
next prev parent reply other threads:[~2016-12-27 13:56 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-10-07 14:52 [PATCH -v4 0/8] locking/mutex: Rewrite basic mutex Peter Zijlstra
2016-10-07 14:52 ` [PATCH -v4 1/8] locking/drm: Kill mutex trickery Peter Zijlstra
2016-10-07 15:43 ` Peter Zijlstra
2016-10-07 15:58 ` Linus Torvalds
2016-10-07 16:13 ` Peter Zijlstra
2016-10-07 21:58 ` Waiman Long
2016-10-08 11:58 ` Thomas Gleixner
2016-10-08 14:01 ` Peter Zijlstra
2016-10-08 14:11 ` Thomas Gleixner
2016-10-08 16:42 ` Peter Zijlstra
2016-11-09 10:38 ` Peter Zijlstra
2016-10-18 12:48 ` Peter Zijlstra
2016-10-18 12:57 ` Peter Zijlstra
2016-11-11 11:22 ` Daniel Vetter
2016-11-11 11:38 ` Peter Zijlstra
2016-11-12 10:58 ` Ingo Molnar
2016-11-14 14:04 ` Peter Zijlstra
2016-11-14 14:27 ` Ingo Molnar
2016-10-18 12:57 ` Chris Wilson
2016-10-07 14:52 ` [PATCH -v4 2/8] locking/mutex: Rework mutex::owner Peter Zijlstra
2016-10-12 17:59 ` Davidlohr Bueso
2016-10-12 19:52 ` Jason Low
2016-10-13 15:18 ` Will Deacon
2016-10-07 14:52 ` [PATCH -v4 3/8] locking/mutex: Kill arch specific code Peter Zijlstra
2016-10-07 14:52 ` [PATCH -v4 4/8] locking/mutex: Allow MUTEX_SPIN_ON_OWNER when DEBUG_MUTEXES Peter Zijlstra
2016-10-07 14:52 ` [PATCH -v4 5/8] locking/mutex: Add lock handoff to avoid starvation Peter Zijlstra
2016-10-13 15:14 ` Will Deacon
2016-10-17 9:22 ` Peter Zijlstra
2016-10-17 18:45 ` Waiman Long
2016-10-17 19:07 ` Waiman Long
2016-10-18 13:02 ` Peter Zijlstra
2016-10-18 12:36 ` Peter Zijlstra
2016-12-27 13:55 ` Chris Wilson [this message]
2017-01-09 11:52 ` [PATCH] locking/mutex: Clear mutex-handoff flag on interrupt Chris Wilson
2017-01-11 16:43 ` Peter Zijlstra
2017-01-11 16:57 ` Chris Wilson
2017-01-12 20:58 ` Chris Wilson
2016-10-07 14:52 ` [PATCH -v4 6/8] locking/mutex: Restructure wait loop Peter Zijlstra
2016-10-13 15:17 ` Will Deacon
2016-10-17 10:44 ` Peter Zijlstra
2016-10-17 13:24 ` Peter Zijlstra
2016-10-17 13:45 ` Boqun Feng
2016-10-17 15:49 ` Peter Zijlstra
2016-10-19 17:34 ` Peter Zijlstra
2016-10-24 1:57 ` ciao set_task_state() (was Re: [PATCH -v4 6/8] locking/mutex: Restructure wait loop) Davidlohr Bueso
2016-10-24 13:26 ` Kent Overstreet
2016-10-24 14:27 ` Kent Overstreet
2016-10-25 16:55 ` Eric Wheeler
2016-10-25 17:45 ` Kent Overstreet
2016-10-17 23:16 ` [PATCH -v4 6/8] locking/mutex: Restructure wait loop Waiman Long
2016-10-18 13:14 ` Peter Zijlstra
2016-10-07 14:52 ` [PATCH -v4 7/8] locking/mutex: Simplify some ww_mutex code in __mutex_lock_common() Peter Zijlstra
2016-10-07 14:52 ` [PATCH -v4 8/8] locking/mutex: Enable optimistic spinning of woken waiter Peter Zijlstra
2016-10-13 15:28 ` Will Deacon
2016-10-17 9:32 ` Peter Zijlstra
2016-10-17 23:21 ` Waiman Long
2016-10-18 12:19 ` Peter Zijlstra
2016-10-07 15:20 ` [PATCH -v4 0/8] locking/mutex: Rewrite basic mutex Linus Torvalds
2016-10-11 18:42 ` Jason Low
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=20161227135541.GB1717@nuc-i3427.alporthouse.com \
--to=chris@chris-wilson.co.uk \
--cc=Will.Deacon@arm.com \
--cc=daniel.vetter@ffwll.ch \
--cc=dave@stgolabs.net \
--cc=dingtianhong@huawei.com \
--cc=imre.deak@intel.com \
--cc=jason.low2@hp.com \
--cc=jason.low2@hpe.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=paulmck@us.ibm.com \
--cc=peterz@infradead.org \
--cc=terry.rudd@hpe.com \
--cc=tglx@linutronix.de \
--cc=tim.c.chen@linux.intel.com \
--cc=torvalds@linux-foundation.org \
--cc=waiman.long@hpe.com \
/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).