Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757295AbaJ2UTs (ORCPT ); Wed, 29 Oct 2014 16:19:48 -0400 Received: from g4t3427.houston.hp.com ([15.201.208.55]:49879 "EHLO g4t3427.houston.hp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757107AbaJ2UTp (ORCPT ); Wed, 29 Oct 2014 16:19:45 -0400 From: Waiman Long 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 , Scott J Norton , Douglas Hatch , Peter Zijlstra , Waiman Long Subject: [PATCH v13 05/11] qspinlock: Optimize for smaller NR_CPUS Date: Wed, 29 Oct 2014 16:19:05 -0400 Message-Id: <1414613951-32532-6-git-send-email-Waiman.Long@hp.com> X-Mailer: git-send-email 1.7.1 In-Reply-To: <1414613951-32532-1-git-send-email-Waiman.Long@hp.com> References: <1414613951-32532-1-git-send-email-Waiman.Long@hp.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Peter Zijlstra When we allow for a max NR_CPUS < 2^14 we can optimize the pending wait-acquire and the xchg_tail() operations. By growing the pending bit to a byte, we reduce the tail to 16bit. This means we can use xchg16 for the tail part and do away with all the repeated compxchg() operations. This in turn allows us to unconditionally acquire; the locked state as observed by the wait loops cannot change. And because both locked and pending are now a full byte we can use simple stores for the state transition, obviating one atomic operation entirely. This optimization is needed to make the qspinlock achieve performance parity with ticket spinlock at light load. All this is horribly broken on Alpha pre EV56 (and any other arch that cannot do single-copy atomic byte stores). Signed-off-by: Peter Zijlstra Signed-off-by: Waiman Long --- include/asm-generic/qspinlock_types.h | 13 ++++++ kernel/locking/qspinlock.c | 71 ++++++++++++++++++++++++++++++++- 2 files changed, 83 insertions(+), 1 deletions(-) diff --git a/include/asm-generic/qspinlock_types.h b/include/asm-generic/qspinlock_types.h index 88d647c..01b46df 100644 --- a/include/asm-generic/qspinlock_types.h +++ b/include/asm-generic/qspinlock_types.h @@ -35,6 +35,14 @@ typedef struct qspinlock { /* * Bitfields in the atomic value: * + * When NR_CPUS < 16K + * 0- 7: locked byte + * 8: pending + * 9-15: not used + * 16-17: tail index + * 18-31: tail cpu (+1) + * + * When NR_CPUS >= 16K * 0- 7: locked byte * 8: pending * 9-10: tail index @@ -47,7 +55,11 @@ typedef struct qspinlock { #define _Q_LOCKED_MASK _Q_SET_MASK(LOCKED) #define _Q_PENDING_OFFSET (_Q_LOCKED_OFFSET + _Q_LOCKED_BITS) +#if CONFIG_NR_CPUS < (1U << 14) +#define _Q_PENDING_BITS 8 +#else #define _Q_PENDING_BITS 1 +#endif #define _Q_PENDING_MASK _Q_SET_MASK(PENDING) #define _Q_TAIL_IDX_OFFSET (_Q_PENDING_OFFSET + _Q_PENDING_BITS) @@ -58,6 +70,7 @@ 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_OFFSET _Q_TAIL_IDX_OFFSET #define _Q_TAIL_MASK (_Q_TAIL_IDX_MASK | _Q_TAIL_CPU_MASK) #define _Q_LOCKED_VAL (1U << _Q_LOCKED_OFFSET) diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index 48bd2ad..7c127b4 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -22,6 +22,7 @@ #include #include #include +#include #include /* @@ -54,6 +55,10 @@ * node; whereby avoiding the need to carry a node from lock to unlock, and * preserving existing lock API. This also makes the unlock code simpler and * faster. + * + * N.B. The current implementation only supports architectures that allow + * atomic operations on smaller 8-bit and 16-bit data types. + * */ #include "mcs_spinlock.h" @@ -94,6 +99,64 @@ static inline struct mcs_spinlock *decode_tail(u32 tail) #define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK) +/* + * By using the whole 2nd least significant byte for the pending bit, we + * can allow better optimization of the lock acquisition for the pending + * bit holder. + */ +#if _Q_PENDING_BITS == 8 + +struct __qspinlock { + union { + atomic_t val; + struct { +#ifdef __LITTLE_ENDIAN + u16 locked_pending; + u16 tail; +#else + u16 tail; + u16 locked_pending; +#endif + }; + }; +}; + +/** + * clear_pending_set_locked - take ownership and clear the pending bit. + * @lock: Pointer to queue spinlock structure + * @val : Current value of the queue spinlock 32-bit word + * + * *,1,0 -> *,0,1 + * + * Lock stealing is not allowed if this function is used. + */ +static __always_inline void +clear_pending_set_locked(struct qspinlock *lock, u32 val) +{ + struct __qspinlock *l = (void *)lock; + + ACCESS_ONCE(l->locked_pending) = _Q_LOCKED_VAL; +} + +/* + * 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 + * 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) +{ + struct __qspinlock *l = (void *)lock; + + return (u32)xchg(&l->tail, tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET; +} + +#else /* _Q_PENDING_BITS == 8 */ + /** * clear_pending_set_locked - take ownership and clear the pending bit. * @lock: Pointer to queue spinlock structure @@ -141,6 +204,7 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail) } return old; } +#endif /* _Q_PENDING_BITS == 8 */ /** * queue_spin_lock_slowpath - acquire the queue spinlock @@ -215,8 +279,13 @@ void queue_spin_lock_slowpath(struct qspinlock *lock, u32 val) * we're pending, wait for the owner to go away. * * *,1,1 -> *,1,0 + * + * this wait loop must be a load-acquire such that we match the + * store-release that clears the locked bit and create lock + * sequentiality; this is because not all clear_pending_set_locked() + * implementations imply full barriers. */ - while ((val = atomic_read(&lock->val)) & _Q_LOCKED_MASK) + while ((val = smp_load_acquire(&lock->val.counter)) & _Q_LOCKED_MASK) cpu_relax(); /* -- 1.7.1 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/