From b3e0b1b6d841a4b2f64fc09ea728913da8218424 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 16 Oct 2015 14:39:38 +0200 Subject: [PATCH] locking, sched: Introduce smp_cond_acquire() and use it Introduce smp_cond_acquire() which combines a control dependency and a read barrier to form acquire semantics. This primitive has two benefits: - it documents control dependencies, - its typically cheaper than using smp_load_acquire() in a loop. Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/compiler.h | 17 +++++++++++++++++ kernel/locking/qspinlock.c | 3 +-- kernel/sched/core.c | 8 +------- kernel/sched/sched.h | 2 +- 4 files changed, 20 insertions(+), 10 deletions(-) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 4dac1036594f..00b042c49ccd 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -299,6 +299,23 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s __u.__val; \ }) +/** + * smp_cond_acquire() - Spin wait for cond with ACQUIRE ordering + * @cond: boolean expression to wait for + * + * Equivalent to using smp_load_acquire() on the condition variable but employs + * the control dependency of the wait to reduce the barrier on many platforms. + * + * The control dependency provides a LOAD->STORE order, the additional RMB + * provides LOAD->LOAD order, together they provide LOAD->{LOAD,STORE} order, + * aka. ACQUIRE. + */ +#define smp_cond_acquire(cond) do { \ + while (!(cond)) \ + cpu_relax(); \ + smp_rmb(); /* ctrl + rmb := acquire */ \ +} while (0) + #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index 986207887def..ed9d96708f93 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -433,8 +433,7 @@ queue: * */ pv_wait_head(lock, node); - while ((val = smp_load_acquire(&lock->val.counter)) & _Q_LOCKED_PENDING_MASK) - cpu_relax(); + smp_cond_acquire(!((val = atomic_read(&lock->val)) & _Q_LOCKED_PENDING_MASK)); /* * claim the lock: diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7063c6a07440..9f7862da2cd1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1968,19 +1968,13 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) /* * If the owning (remote) cpu is still in the middle of schedule() with * this task as prev, wait until its done referencing the task. - */ - while (p->on_cpu) - cpu_relax(); - /* - * Combined with the control dependency above, we have an effective - * smp_load_acquire() without the need for full barriers. * * Pairs with the smp_store_release() in finish_lock_switch(). * * This ensures that tasks getting woken will be fully ordered against * their previous state and preserve Program Order. */ - smp_rmb(); + smp_cond_acquire(!p->on_cpu); p->sched_contributes_to_load = !!task_contributes_to_load(p); p->state = TASK_WAKING; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index b242775bf670..1e0bb4afe3fd 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1076,7 +1076,7 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) * In particular, the load of prev->state in finish_task_switch() must * happen before this. * - * Pairs with the control dependency and rmb in try_to_wake_up(). + * Pairs with the smp_cond_acquire() in try_to_wake_up(). */ smp_store_release(&prev->on_cpu, 0); #endif -- 2.39.5