From mboxrd@z Thu Jan 1 00:00:00 1970 From: Waiman Long Subject: [PATCH v10 04/19] qspinlock: Extract out the exchange of tail code word Date: Wed, 7 May 2014 11:01:32 -0400 Message-ID: <1399474907-22206-5-git-send-email-Waiman.Long@hp.com> References: <1399474907-22206-1-git-send-email-Waiman.Long@hp.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <1399474907-22206-1-git-send-email-Waiman.Long@hp.com> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: virtualization-bounces@lists.linux-foundation.org Errors-To: virtualization-bounces@lists.linux-foundation.org To: Thomas Gleixner , Ingo Molnar , "H. Peter Anvin" , Peter Zijlstra Cc: linux-arch@vger.kernel.org, Waiman Long , Rik van Riel , Raghavendra K T , Gleb Natapov , kvm@vger.kernel.org, Konrad Rzeszutek Wilk , Scott J Norton , x86@kernel.org, Paolo Bonzini , linux-kernel@vger.kernel.org, virtualization@lists.linux-foundation.org, Chegu Vinod , David Vrabel , Oleg Nesterov , xen-devel@lists.xenproject.org, Boris Ostrovsky , "Paul E. McKenney" , Linus Torvalds List-Id: linux-arch.vger.kernel.org This patch extracts the logic for the exchange of new and previous tail code words into a new xchg_tail() function which can be optimized in a later patch. Signed-off-by: Waiman Long --- include/asm-generic/qspinlock_types.h | 2 + kernel/locking/qspinlock.c | 61 +++++++++++++++++++++------------ 2 files changed, 41 insertions(+), 22 deletions(-) diff --git a/include/asm-generic/qspinlock_types.h b/include/asm-generic/qspinlock_types.h index bd25081..ed5d89a 100644 --- a/include/asm-generic/qspinlock_types.h +++ b/include/asm-generic/qspinlock_types.h @@ -61,6 +61,8 @@ typedef struct qspinlock { #define _Q_TAIL_CPU_BITS (32 - _Q_TAIL_CPU_OFFSET) #define _Q_TAIL_CPU_MASK _Q_SET_MASK(TAIL_CPU) +#define _Q_TAIL_MASK (_Q_TAIL_IDX_MASK | _Q_TAIL_CPU_MASK) + #define _Q_LOCKED_VAL (1U << _Q_LOCKED_OFFSET) #define _Q_PENDING_VAL (1U << _Q_PENDING_OFFSET) diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index 6467bfc..a49b82b 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -86,6 +86,34 @@ static inline struct mcs_spinlock *decode_tail(u32 tail) #define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK) /** + * xchg_tail - Put in the new queue tail code word & retrieve previous one + * @lock : Pointer to queue spinlock structure + * @tail : The new queue tail code word + * @pval : Pointer to current value of the queue spinlock 32-bit word + * Return: The previous queue tail code word + * + * xchg(lock, tail) + * + * p,*,* -> n,*,* ; prev = xchg(lock, node) + */ +static __always_inline u32 +xchg_tail(struct qspinlock *lock, u32 tail, u32 *pval) +{ + u32 old, new, val = *pval; + + for (;;) { + new = (val & _Q_LOCKED_PENDING_MASK) | tail; + old = atomic_cmpxchg(&lock->val, val, new); + if (old == val) + break; + + val = old; + } + *pval = new; + return old; +} + +/** * trylock_pending - try to acquire queue spinlock using the pending bit * @lock : Pointer to queue spinlock structure * @pval : Pointer to value of the queue spinlock 32-bit word @@ -196,36 +224,25 @@ void queue_spin_lock_slowpath(struct qspinlock *lock, u32 val) node->next = NULL; /* - * we already touched the queueing cacheline; don't bother with pending - * stuff. - * - * trylock || xchg(lock, node) - * - * 0,0,0 -> 0,0,1 ; trylock - * p,y,x -> n,y,x ; prev = xchg(lock, node) + * We touched a (possibly) cold cacheline in the per-cpu queue node; + * attempt the trylock once more in the hope someone let go while we + * weren't watching. */ - for (;;) { - new = _Q_LOCKED_VAL; - if (val) - new = tail | (val & _Q_LOCKED_PENDING_MASK); - - old = atomic_cmpxchg(&lock->val, val, new); - if (old == val) - break; - - val = old; - } + if (queue_spin_trylock(lock)) + goto release; /* - * we won the trylock; forget about queueing. + * we already touched the queueing cacheline; don't bother with pending + * stuff. + * + * p,*,* -> n,*,* */ - if (new == _Q_LOCKED_VAL) - goto release; + old = xchg_tail(lock, tail, &val); /* * if there was a previous node; link it and wait. */ - if (old & ~_Q_LOCKED_PENDING_MASK) { + if (old & _Q_TAIL_MASK) { prev = decode_tail(old); ACCESS_ONCE(prev->next) = node; -- 1.7.1 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from g4t3427.houston.hp.com ([15.201.208.55]:16432 "EHLO g4t3427.houston.hp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756436AbaEGPCi (ORCPT ); Wed, 7 May 2014 11:02:38 -0400 From: Waiman Long Subject: [PATCH v10 04/19] qspinlock: Extract out the exchange of tail code word Date: Wed, 7 May 2014 11:01:32 -0400 Message-ID: <1399474907-22206-5-git-send-email-Waiman.Long@hp.com> In-Reply-To: <1399474907-22206-1-git-send-email-Waiman.Long@hp.com> References: <1399474907-22206-1-git-send-email-Waiman.Long@hp.com> Sender: linux-arch-owner@vger.kernel.org List-ID: To: Thomas Gleixner , Ingo Molnar , "H. Peter Anvin" , Peter Zijlstra Cc: linux-arch@vger.kernel.org, x86@kernel.org, linux-kernel@vger.kernel.org, virtualization@lists.linux-foundation.org, xen-devel@lists.xenproject.org, kvm@vger.kernel.org, Paolo Bonzini , Konrad Rzeszutek Wilk , Boris Ostrovsky , "Paul E. McKenney" , Rik van Riel , Linus Torvalds , Raghavendra K T , David Vrabel , Oleg Nesterov , Gleb Natapov , Scott J Norton , Chegu Vinod , Waiman Long Message-ID: <20140507150132.R8CI2Dnu3Ks53CMZE4tI9n7ITru9XrreE88yQshpBog@z> This patch extracts the logic for the exchange of new and previous tail code words into a new xchg_tail() function which can be optimized in a later patch. Signed-off-by: Waiman Long --- include/asm-generic/qspinlock_types.h | 2 + kernel/locking/qspinlock.c | 61 +++++++++++++++++++++------------ 2 files changed, 41 insertions(+), 22 deletions(-) diff --git a/include/asm-generic/qspinlock_types.h b/include/asm-generic/qspinlock_types.h index bd25081..ed5d89a 100644 --- a/include/asm-generic/qspinlock_types.h +++ b/include/asm-generic/qspinlock_types.h @@ -61,6 +61,8 @@ typedef struct qspinlock { #define _Q_TAIL_CPU_BITS (32 - _Q_TAIL_CPU_OFFSET) #define _Q_TAIL_CPU_MASK _Q_SET_MASK(TAIL_CPU) +#define _Q_TAIL_MASK (_Q_TAIL_IDX_MASK | _Q_TAIL_CPU_MASK) + #define _Q_LOCKED_VAL (1U << _Q_LOCKED_OFFSET) #define _Q_PENDING_VAL (1U << _Q_PENDING_OFFSET) diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index 6467bfc..a49b82b 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -86,6 +86,34 @@ static inline struct mcs_spinlock *decode_tail(u32 tail) #define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK) /** + * xchg_tail - Put in the new queue tail code word & retrieve previous one + * @lock : Pointer to queue spinlock structure + * @tail : The new queue tail code word + * @pval : Pointer to current value of the queue spinlock 32-bit word + * Return: The previous queue tail code word + * + * xchg(lock, tail) + * + * p,*,* -> n,*,* ; prev = xchg(lock, node) + */ +static __always_inline u32 +xchg_tail(struct qspinlock *lock, u32 tail, u32 *pval) +{ + u32 old, new, val = *pval; + + for (;;) { + new = (val & _Q_LOCKED_PENDING_MASK) | tail; + old = atomic_cmpxchg(&lock->val, val, new); + if (old == val) + break; + + val = old; + } + *pval = new; + return old; +} + +/** * trylock_pending - try to acquire queue spinlock using the pending bit * @lock : Pointer to queue spinlock structure * @pval : Pointer to value of the queue spinlock 32-bit word @@ -196,36 +224,25 @@ void queue_spin_lock_slowpath(struct qspinlock *lock, u32 val) node->next = NULL; /* - * we already touched the queueing cacheline; don't bother with pending - * stuff. - * - * trylock || xchg(lock, node) - * - * 0,0,0 -> 0,0,1 ; trylock - * p,y,x -> n,y,x ; prev = xchg(lock, node) + * We touched a (possibly) cold cacheline in the per-cpu queue node; + * attempt the trylock once more in the hope someone let go while we + * weren't watching. */ - for (;;) { - new = _Q_LOCKED_VAL; - if (val) - new = tail | (val & _Q_LOCKED_PENDING_MASK); - - old = atomic_cmpxchg(&lock->val, val, new); - if (old == val) - break; - - val = old; - } + if (queue_spin_trylock(lock)) + goto release; /* - * we won the trylock; forget about queueing. + * we already touched the queueing cacheline; don't bother with pending + * stuff. + * + * p,*,* -> n,*,* */ - if (new == _Q_LOCKED_VAL) - goto release; + old = xchg_tail(lock, tail, &val); /* * if there was a previous node; link it and wait. */ - if (old & ~_Q_LOCKED_PENDING_MASK) { + if (old & _Q_TAIL_MASK) { prev = decode_tail(old); ACCESS_ONCE(prev->next) = node; -- 1.7.1