From: Waiman Long <longman@redhat.com>
To: Will Deacon <will.deacon@arm.com>, linux-kernel@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org, peterz@infradead.org,
mingo@kernel.org, boqun.feng@gmail.com,
paulmck@linux.vnet.ibm.com
Subject: Re: [PATCH v2 04/13] locking/qspinlock: Remove unbounded cmpxchg loop from locking slowpath
Date: Wed, 11 Apr 2018 16:35:25 -0400 [thread overview]
Message-ID: <d0fb47ef-bfd7-a2b8-7c0d-14d8f18aa608@redhat.com> (raw)
In-Reply-To: <674fd9c0-e3f3-9ae0-dd0a-7ccc085c1706@redhat.com>
On 04/11/2018 03:34 PM, Waiman Long wrote:
> On 04/11/2018 02:01 PM, Will Deacon wrote:
>> @@ -485,15 +499,15 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
>> * claim the lock:
>> *
>> * n,0,0 -> 0,0,1 : lock, uncontended
>> - * *,0,0 -> *,0,1 : lock, contended
>> + * *,*,0 -> *,*,1 : lock, contended
>> *
>> - * If the queue head is the only one in the queue (lock value == tail),
>> - * clear the tail code and grab the lock. Otherwise, we only need
>> - * to grab the lock.
>> + * If the queue head is the only one in the queue (lock value == tail)
>> + * and nobody is pending, clear the tail code and grab the lock.
>> + * Otherwise, we only need to grab the lock.
>> */
>> for (;;) {
>> /* In the PV case we might already have _Q_LOCKED_VAL set */
>> - if ((val & _Q_TAIL_MASK) != tail) {
>> + if ((val & _Q_TAIL_MASK) != tail || (val & _Q_PENDING_MASK)) {
>> set_locked(lock);
>> break;
>> }
> I don't think it is right to just grab the lock when the pending bit is
> set. I believe it will cause problem.
>
> Preserving the the pending bit should be just
>
> diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
> index 35367cc..76d9124 100644
> --- a/kernel/locking/qspinlock.c
> +++ b/kernel/locking/qspinlock.c
> @@ -511,7 +511,8 @@ void queued_spin_lock_slowpath(struct qspinlock
> *lock, u32 v
> * necessary acquire semantics required for locking. At most
> * two iterations of this loop may be ran.
> */
> - old = atomic_cmpxchg_relaxed(&lock->val, val,
> _Q_LOCKED_VAL);
> + old = atomic_cmpxchg_relaxed(&lock->val, val,
> + _Q_LOCKED_VAL | (val & _Q_PENDING_MASK));
> if (old == val)
> goto release; /* No contention */
After some more thought and reviewing the rests of the patchset, I now
think your change here is OK. Sorry for the noise.
Cheers,
Longman
next prev parent reply other threads:[~2018-04-11 20:35 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-04-11 18:01 [PATCH v2 00/13] kernel/locking: qspinlock improvements Will Deacon
2018-04-11 18:01 ` [PATCH v2 01/13] barriers: Introduce smp_cond_load_relaxed and atomic_cond_read_relaxed Will Deacon
2018-04-11 18:01 ` [PATCH v2 02/13] locking/qspinlock: Bound spinning on pending->locked transition in slowpath Will Deacon
2018-04-11 18:01 ` [PATCH v2 03/13] locking/qspinlock/x86: Increase _Q_PENDING_LOOPS upper bound Will Deacon
2018-04-11 18:01 ` [PATCH v2 04/13] locking/qspinlock: Remove unbounded cmpxchg loop from locking slowpath Will Deacon
2018-04-11 19:34 ` Waiman Long
2018-04-11 20:35 ` Waiman Long [this message]
2018-04-11 19:53 ` Waiman Long
2018-04-12 14:06 ` Will Deacon
2018-04-12 14:16 ` Waiman Long
2018-04-12 14:18 ` Will Deacon
2018-04-11 18:01 ` [PATCH v2 05/13] locking/qspinlock: Kill cmpxchg loop when claiming lock from head of queue Will Deacon
2018-04-11 18:01 ` [PATCH v2 06/13] locking/qspinlock: Use atomic_cond_read_acquire Will Deacon
2018-04-11 18:01 ` [PATCH v2 07/13] locking/mcs: Use smp_cond_load_acquire() in mcs spin loop Will Deacon
2018-04-11 18:01 ` [PATCH v2 08/13] locking/qspinlock: Use smp_cond_load_relaxed to wait for next node Will Deacon
2018-04-11 18:01 ` [PATCH v2 09/13] locking/qspinlock: Merge struct __qspinlock into struct qspinlock Will Deacon
2018-04-11 19:13 ` Waiman Long
2018-04-11 18:01 ` [PATCH v2 10/13] locking/qspinlock: Make queued_spin_unlock use smp_store_release Will Deacon
2018-04-11 18:01 ` [PATCH v2 11/13] locking/qspinlock: Elide back-to-back RELEASE operations with smp_wmb() Will Deacon
2018-04-11 18:01 ` [PATCH v2 12/13] locking/qspinlock: Use try_cmpxchg instead of cmpxchg when locking Will Deacon
2018-04-11 18:01 ` [PATCH v2 13/13] locking/qspinlock: Add stat tracking for pending vs slowpath Will Deacon
2018-04-13 9:24 ` [PATCH v2 00/13] kernel/locking: qspinlock improvements Catalin Marinas
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=d0fb47ef-bfd7-a2b8-7c0d-14d8f18aa608@redhat.com \
--to=longman@redhat.com \
--cc=boqun.feng@gmail.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=paulmck@linux.vnet.ibm.com \
--cc=peterz@infradead.org \
--cc=will.deacon@arm.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).