From 9d4646d14d51d62b967a12452c30ea7edf8dd8fa Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 26 Apr 2018 11:34:25 +0100 Subject: locking/qspinlock: Elide back-to-back RELEASE operations with smp_wmb() The qspinlock slowpath must ensure that the MCS node is fully initialised before it can be reached by another other CPU. This is currently enforced by using a RELEASE operation when updating the tail and also when linking the node into the waitqueue, since the control dependency off xchg_tail is insufficient to enforce sufficient ordering, see: 95bcade33a8a ("locking/qspinlock: Ensure node is initialised before updating prev->next") Back-to-back RELEASE operations may be expensive on some architectures, particularly those that implement them using fences under the hood. We can replace the two RELEASE operations with a single smp_wmb() fence and use RELAXED operations for the subsequent publishing of the node. Signed-off-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Acked-by: Waiman Long Cc: Linus Torvalds Cc: Thomas Gleixner Cc: boqun.feng@gmail.com Cc: linux-arm-kernel@lists.infradead.org Cc: paulmck@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1524738868-31318-12-git-send-email-will.deacon@arm.com Signed-off-by: Ingo Molnar --- kernel/locking/qspinlock.c | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index d6c3b029bd93..956a12983bd0 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -164,10 +164,10 @@ static __always_inline void clear_pending_set_locked(struct qspinlock *lock) static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail) { /* - * Use release semantics to make sure that the MCS node is properly - * initialized before changing the tail code. + * We can use relaxed semantics since the caller ensures that the + * MCS node is properly initialized before updating the tail. */ - return (u32)xchg_release(&lock->tail, + return (u32)xchg_relaxed(&lock->tail, tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET; } @@ -212,10 +212,11 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail) for (;;) { new = (val & _Q_LOCKED_PENDING_MASK) | tail; /* - * Use release semantics to make sure that the MCS node is - * properly initialized before changing the tail code. + * We can use relaxed semantics since the caller ensures that + * the MCS node is properly initialized before updating the + * tail. */ - old = atomic_cmpxchg_release(&lock->val, val, new); + old = atomic_cmpxchg_relaxed(&lock->val, val, new); if (old == val) break; @@ -388,12 +389,18 @@ queue: goto release; /* + * Ensure that the initialisation of @node is complete before we + * publish the updated tail via xchg_tail() and potentially link + * @node into the waitqueue via WRITE_ONCE(prev->next, node) below. + */ + smp_wmb(); + + /* + * Publish the updated tail. * We have already touched the queueing cacheline; don't bother with * pending stuff. * * p,*,* -> n,*,* - * - * RELEASE, such that the stores to @node must be complete. */ old = xchg_tail(lock, tail); next = NULL; @@ -405,14 +412,8 @@ queue: if (old & _Q_TAIL_MASK) { prev = decode_tail(old); - /* - * We must ensure that the stores to @node are observed before - * the write to prev->next. The address dependency from - * xchg_tail is not sufficient to ensure this because the read - * component of xchg_tail is unordered with respect to the - * initialisation of @node. - */ - smp_store_release(&prev->next, node); + /* Link @node into the waitqueue. */ + WRITE_ONCE(prev->next, node); pv_wait_node(node, prev); arch_mcs_spin_lock_contended(&node->locked); -- cgit v1.2.3