From 27d7be1801a4824ecccbc735593101d72c038f13 Mon Sep 17 00:00:00 2001 From: Manfred Spraul Date: Mon, 27 Feb 2017 14:28:15 -0800 Subject: ipc/sem.c: avoid using spin_unlock_wait() a) The ACQUIRE in spin_lock() applies to the read, not to the store, at least for powerpc. This forces to add a smp_mb() into the fast path. b) The memory barrier provided by spin_unlock_wait() is right now arch dependent. Therefore: Use spin_lock()/spin_unlock() instead of spin_unlock_wait(). Advantage: faster single op semop calls(), observed +8.9% on x86. (the other solution would be arch dependencies in ipc/sem). Disadvantage: slower complex op semop calls, if (and only if) there are no sleeping operations. The next patch adds hysteresis, this further reduces the probability that the slow path is used. Link: http://lkml.kernel.org/r/1476851896-3590-2-git-send-email-manfred@colorfullife.com Signed-off-by: Manfred Spraul Cc: Peter Zijlstra Cc: Davidlohr Bueso Cc: Thomas Gleixner Cc: Ingo Molnar Cc: H. Peter Anvin Cc: <1vier1@web.de> Cc: kernel test robot Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/sem.c | 25 +++---------------------- 1 file changed, 3 insertions(+), 22 deletions(-) (limited to 'ipc') diff --git a/ipc/sem.c b/ipc/sem.c index 3ec5742b5640..fe5db1ed081b 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -278,24 +278,13 @@ static void complexmode_enter(struct sem_array *sma) return; } - /* We need a full barrier after seting complex_mode: - * The write to complex_mode must be visible - * before we read the first sem->lock spinlock state. - */ - smp_store_mb(sma->complex_mode, true); + sma->complex_mode = true; for (i = 0; i < sma->sem_nsems; i++) { sem = sma->sem_base + i; - spin_unlock_wait(&sem->lock); + spin_lock(&sem->lock); + spin_unlock(&sem->lock); } - /* - * spin_unlock_wait() is not a memory barriers, it is only a - * control barrier. The code must pair with spin_unlock(&sem->lock), - * thus just the control barrier is insufficient. - * - * smp_rmb() is sufficient, as writes cannot pass the control barrier. - */ - smp_rmb(); } /* @@ -361,14 +350,6 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops, */ spin_lock(&sem->lock); - /* - * See 51d7d5205d33 - * ("powerpc: Add smp_mb() to arch_spin_is_locked()"): - * A full barrier is required: the write of sem->lock - * must be visible before the read is executed - */ - smp_mb(); - if (!smp_load_acquire(&sma->complex_mode)) { /* fast path successful! */ return sops->sem_num; -- cgit v1.2.3