From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751801AbdJEN42 (ORCPT ); Thu, 5 Oct 2017 09:56:28 -0400 Received: from bombadil.infradead.org ([65.50.211.133]:55410 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751744AbdJEN4Z (ORCPT ); Thu, 5 Oct 2017 09:56:25 -0400 Date: Thu, 5 Oct 2017 15:56:18 +0200 From: Peter Zijlstra To: Will Deacon Cc: linux-kernel@vger.kernel.org, linux-arm-kernel@lists.infradead.org, Jeremy.Linton@arm.com, mingo@redhat.com, longman@redhat.com, boqun.feng@gmail.com, paulmck@linux.vnet.ibm.com Subject: Re: [PATCH 5/6] kernel/locking: Prevent slowpath writers getting held up by fastpath Message-ID: <20171005135618.yufhaklq5cefaiyn@hirez.programming.kicks-ass.net> References: <1507208097-825-1-git-send-email-will.deacon@arm.com> <1507208097-825-6-git-send-email-will.deacon@arm.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1507208097-825-6-git-send-email-will.deacon@arm.com> User-Agent: NeoMutt/20170609 (1.8.3) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, Oct 05, 2017 at 01:54:56PM +0100, Will Deacon wrote: > When a prospective writer takes the qrwlock locking slowpath due to the > lock being held, it attempts to cmpxchg the wmode field from 0 to > _QW_WAITING so that concurrent lockers also take the slowpath and queue > on the spinlock accordingly, allowing the lockers to drain. > > Unfortunately, this isn't fair, because a fastpath writer that comes in > after the lock is made available but before the _QW_WAITING flag is set > can effectively jump the queue. If there is a steady stream of prospective > writers, then the waiter will be held off indefinitely. > > This patch restores fairness by separating _QW_WAITING and _QW_LOCKED > into two bits in the wmode byte and having the waiter set _QW_WAITING > unconditionally. This then forces the slow-path for concurrent lockers, > but requires that a writer unlock operation performs an > atomic_sub_release instead of a store_release so that the waiting status > is preserved. > diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h > index 02c0a768e6b0..8b7edef500e5 100644 > --- a/include/asm-generic/qrwlock.h > +++ b/include/asm-generic/qrwlock.h > @@ -41,7 +41,7 @@ > * +----+----+----+----+ > */ > #define _QW_WAITING 1 /* A writer is waiting */ > -#define _QW_LOCKED 0xff /* A writer holds the lock */ > +#define _QW_LOCKED 2 /* A writer holds the lock */ > #define _QW_WMASK 0xff /* Writer mask */ > #define _QR_SHIFT 8 /* Reader count shift */ > #define _QR_BIAS (1U << _QR_SHIFT) > @@ -134,7 +134,7 @@ static inline void queued_read_unlock(struct qrwlock *lock) > */ > static inline void queued_write_unlock(struct qrwlock *lock) > { > - smp_store_release(&lock->wmode, 0); > + (void)atomic_sub_return_release(_QW_LOCKED, &lock->cnts); > } That is a fairly painful hit on x86. Changes a regular store into an "LOCK XADD" +20 cycles right there. Can't we steal one of the reader bits for waiting? diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h index 7d026bf27713..5524801a02a5 100644 --- a/include/asm-generic/qrwlock.h +++ b/include/asm-generic/qrwlock.h @@ -40,10 +40,10 @@ * | rd | wr | * +----+----+----+----+ */ -#define _QW_WAITING 1 /* A writer is waiting */ -#define _QW_LOCKED 0xff /* A writer holds the lock */ -#define _QW_WMASK 0xff /* Writer mask */ -#define _QR_SHIFT 8 /* Reader count shift */ +#define _QW_WAITING 0x100 /* A writer is waiting */ +#define _QW_LOCKED 0x0ff /* A writer holds the lock */ +#define _QW_WMASK 0x1ff /* Writer mask */ +#define _QR_SHIFT 9 /* Reader count shift */ #define _QR_BIAS (1U << _QR_SHIFT) /* diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c index 2655f26ec882..5f75caea97e0 100644 --- a/kernel/locking/qrwlock.c +++ b/kernel/locking/qrwlock.c @@ -54,7 +54,7 @@ struct __qrwlock { static __always_inline void rspin_until_writer_unlock(struct qrwlock *lock, u32 cnts) { - while ((cnts & _QW_WMASK) == _QW_LOCKED) { + while ((cnts & _QW_LOCKED)) { cpu_relax(); cnts = atomic_read_acquire(&lock->cnts); } @@ -120,21 +120,10 @@ void queued_write_lock_slowpath(struct qrwlock *lock) (atomic_cmpxchg_acquire(&lock->cnts, 0, _QW_LOCKED) == 0)) goto unlock; - /* - * Set the waiting flag to notify readers that a writer is pending, - * or wait for a previous writer to go away. - */ - for (;;) { - struct __qrwlock *l = (struct __qrwlock *)lock; - - if (!READ_ONCE(l->wmode) && - (cmpxchg_relaxed(&l->wmode, 0, _QW_WAITING) == 0)) - break; - - cpu_relax(); - } + /* Set the waiting flag to notify readers that a writer is pending */ + atomic_add(_QW_WAITING, &lock->cnts); - /* When no more readers, set the locked flag */ + /* When no more readers or writers, set the locked flag */ for (;;) { cnts = atomic_read(&lock->cnts); if ((cnts == _QW_WAITING) &&