Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1443169 > unrolled thread

[PATCH v2] locking/pvqspinlock: restore/set vcpu_hashed state after failing adaptive locking spinning

Started byWanpeng Li <kernellwp@gmail.com>
First post2016-07-14 10:20 +0200
Last post2016-07-14 13:30 +0200
Articles 3 — 2 participants

Back to article view | Back to linux.kernel


Contents

  [PATCH v2] locking/pvqspinlock: restore/set vcpu_hashed state after failing adaptive locking spinning Wanpeng Li <kernellwp@gmail.com> - 2016-07-14 10:20 +0200
    Re: [PATCH v2] locking/pvqspinlock: restore/set vcpu_hashed state  after failing adaptive locking spinning Peter Zijlstra <peterz@infradead.org> - 2016-07-14 13:30 +0200
      Re: [PATCH v2] locking/pvqspinlock: restore/set vcpu_hashed state  after failing adaptive locking spinning Wanpeng Li <kernellwp@gmail.com> - 2016-07-14 13:30 +0200

#1443169 — [PATCH v2] locking/pvqspinlock: restore/set vcpu_hashed state after failing adaptive locking spinning

FromWanpeng Li <kernellwp@gmail.com>
Date2016-07-14 10:20 +0200
Subject[PATCH v2] locking/pvqspinlock: restore/set vcpu_hashed state after failing adaptive locking spinning
Message-ID<rUK2l-75j-221@gated-at.bofh.it>
From: Wanpeng Li <wanpeng.li@hotmail.com>

When the lock holder vCPU is racing with the queue head:

   CPU 0 (lock holder)    CPU1 (queue head)
   ===================    =================
   spin_lock();           spin_lock();
    pv_kick_node():        pv_wait_head_or_lock():
                            if (!lp) {
                             lp = pv_hash(lock, pn);
                             xchg(&l->locked, _Q_SLOW_VAL);
                            }
                            WRITE_ONCE(pn->state, vcpu_halted);
     cmpxchg(&pn->state, 
      vcpu_halted, vcpu_hashed);
     WRITE_ONCE(l->locked, _Q_SLOW_VAL);
     (void)pv_hash(lock, pn);

In this case, lock holder inserts the pv_node of queue head into the 
hash table and set _Q_SLOW_VAL unnecessary. This patch avoids it by 
restoring/setting vcpu_halted state after failing adaptive locking 
spinning.

Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Waiman Long <Waiman.Long@hpe.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
---
v1 -> v2:
 * adjust patch description

 kernel/locking/qspinlock_paravirt.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 21ede57..ac7d20b 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -450,7 +450,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 				goto gotlock;
 			}
 		}
-		WRITE_ONCE(pn->state, vcpu_halted);
+		WRITE_ONCE(pn->state, vcpu_hashed);
 		qstat_inc(qstat_pv_wait_head, true);
 		qstat_inc(qstat_pv_wait_again, waitcnt);
 		pv_wait(&l->locked, _Q_SLOW_VAL);
-- 
1.9.1

[toc] | [next] | [standalone]


#1443367 — Re: [PATCH v2] locking/pvqspinlock: restore/set vcpu_hashed state after failing adaptive locking spinning

FromPeter Zijlstra <peterz@infradead.org>
Date2016-07-14 13:30 +0200
SubjectRe: [PATCH v2] locking/pvqspinlock: restore/set vcpu_hashed state after failing adaptive locking spinning
Message-ID<rUN06-BW-19@gated-at.bofh.it>
In reply to#1443169
On Thu, Jul 14, 2016 at 04:15:56PM +0800, Wanpeng Li wrote:
> In this case, lock holder inserts the pv_node of queue head into the 
> hash table and set _Q_SLOW_VAL unnecessary. This patch avoids it by 
> restoring/setting vcpu_halted state after failing adaptive locking 
                        ^^^^^^
> spinning.
> 

> -		WRITE_ONCE(pn->state, vcpu_halted);
> +		WRITE_ONCE(pn->state, vcpu_hashed);
                                           ^^^^^^

The Changelog meant so say vcpu_hashed, surely?

[toc] | [prev] | [next] | [standalone]


#1443368 — Re: [PATCH v2] locking/pvqspinlock: restore/set vcpu_hashed state after failing adaptive locking spinning

FromWanpeng Li <kernellwp@gmail.com>
Date2016-07-14 13:30 +0200
SubjectRe: [PATCH v2] locking/pvqspinlock: restore/set vcpu_hashed state after failing adaptive locking spinning
Message-ID<rUN06-BW-21@gated-at.bofh.it>
In reply to#1443367
2016-07-14 19:26 GMT+08:00 Peter Zijlstra <peterz@infradead.org>:
> On Thu, Jul 14, 2016 at 04:15:56PM +0800, Wanpeng Li wrote:
>> In this case, lock holder inserts the pv_node of queue head into the
>> hash table and set _Q_SLOW_VAL unnecessary. This patch avoids it by
>> restoring/setting vcpu_halted state after failing adaptive locking
>                         ^^^^^^
>> spinning.
>>
>
>> -             WRITE_ONCE(pn->state, vcpu_halted);
>> +             WRITE_ONCE(pn->state, vcpu_hashed);
>                                            ^^^^^^
>
> The Changelog meant so say vcpu_hashed, surely?

Oh, there is a typo in changelog, I will fix it.

Regards,
Wanpeng Li

[toc] | [prev] | [standalone]


Back to top | Article view | linux.kernel


csiph-web