From 59aabfc7e959f5f213e4e5cc7567ab4934da2adf Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 30 Apr 2015 17:12:16 -0400 Subject: [PATCH] locking/rwsem: Reduce spinlock contention in wakeup after up_read()/up_write() In up_write()/up_read(), rwsem_wake() will be called whenever it detects that some writers/readers are waiting. The rwsem_wake() function will take the wait_lock and call __rwsem_do_wake() to do the real wakeup. For a heavily contended rwsem, doing a spin_lock() on wait_lock will cause further contention on the heavily contended rwsem cacheline resulting in delay in the completion of the up_read/up_write operations. This patch makes the wait_lock taking and the call to __rwsem_do_wake() optional if at least one spinning writer is present. The spinning writer will be able to take the rwsem and call rwsem_wake() later when it calls up_write(). With the presence of a spinning writer, rwsem_wake() will now try to acquire the lock using trylock. If that fails, it will just quit. Suggested-by: Peter Zijlstra (Intel) Signed-off-by: Waiman Long Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Davidlohr Bueso Acked-by: Jason Low Cc: Andrew Morton Cc: Borislav Petkov Cc: Douglas Hatch Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Scott J Norton Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1430428337-16802-2-git-send-email-Waiman.Long@hp.com Signed-off-by: Ingo Molnar --- include/linux/osq_lock.h | 5 +++++ kernel/locking/rwsem-xadd.c | 44 +++++++++++++++++++++++++++++++++++++ 2 files changed, 49 insertions(+) diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h index 3a6490e81b28..703ea5c30a33 100644 --- a/include/linux/osq_lock.h +++ b/include/linux/osq_lock.h @@ -32,4 +32,9 @@ static inline void osq_lock_init(struct optimistic_spin_queue *lock) extern bool osq_lock(struct optimistic_spin_queue *lock); extern void osq_unlock(struct optimistic_spin_queue *lock); +static inline bool osq_is_locked(struct optimistic_spin_queue *lock) +{ + return atomic_read(&lock->tail) != OSQ_UNLOCKED_VAL; +} + #endif diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 3417d0172a5d..0f189714e457 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -409,11 +409,24 @@ done: return taken; } +/* + * Return true if the rwsem has active spinner + */ +static inline bool rwsem_has_spinner(struct rw_semaphore *sem) +{ + return osq_is_locked(&sem->osq); +} + #else static bool rwsem_optimistic_spin(struct rw_semaphore *sem) { return false; } + +static inline bool rwsem_has_spinner(struct rw_semaphore *sem) +{ + return false; +} #endif /* @@ -496,7 +509,38 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) { unsigned long flags; + /* + * If a spinner is present, it is not necessary to do the wakeup. + * Try to do wakeup only if the trylock succeeds to minimize + * spinlock contention which may introduce too much delay in the + * unlock operation. + * + * spinning writer up_write/up_read caller + * --------------- ----------------------- + * [S] osq_unlock() [L] osq + * MB RMB + * [RmW] rwsem_try_write_lock() [RmW] spin_trylock(wait_lock) + * + * Here, it is important to make sure that there won't be a missed + * wakeup while the rwsem is free and the only spinning writer goes + * to sleep without taking the rwsem. Even when the spinning writer + * is just going to break out of the waiting loop, it will still do + * a trylock in rwsem_down_write_failed() before sleeping. IOW, if + * rwsem_has_spinner() is true, it will guarantee at least one + * trylock attempt on the rwsem later on. + */ + if (rwsem_has_spinner(sem)) { + /* + * The smp_rmb() here is to make sure that the spinner + * state is consulted before reading the wait_lock. + */ + smp_rmb(); + if (!raw_spin_trylock_irqsave(&sem->wait_lock, flags)) + return sem; + goto locked; + } raw_spin_lock_irqsave(&sem->wait_lock, flags); +locked: /* do nothing if list empty */ if (!list_empty(&sem->wait_list))