 41ef8f8266
			
		
	
	
	41ef8f8266
	
	
	
		
			
			We (Linux Kernel Performance project) found a regression
introduced by commit:
  5a505085f0 mm/rmap: Convert the struct anon_vma::mutex to an rwsem
which converted all anon_vma::mutex locks rwsem write locks.
The semantics are the same, but the behavioral difference is
quite huge in some cases. After investigating it we found the
root cause: mutexes support lock stealing while rwsems don't.
Here is the link for the detailed regression report:
  https://lkml.org/lkml/2013/1/29/84
Ingo suggested adding write lock stealing to rwsems:
    "I think we should allow lock-steal between rwsem writers - that
     will not hurt fairness as most rwsem fairness concerns relate to
     reader vs. writer fairness"
And here is the rwsem-spinlock version.
With this patch, we got a double performance increase in one
test box with following aim7 workfile:
    FILESIZE: 1M
    POOLSIZE: 10M
    10 fork_test
 /usr/bin/time output w/o patch                       /usr/bin/time_output with patch
 -- Percent of CPU this job got: 369%                 Percent of CPU this job got: 537%
 Voluntary context switches: 640595016                Voluntary context switches: 157915561
We got a 45% increase in CPU usage and saved about 3/4 voluntary context switches.
Reported-by: LKP project <lkp@linux.intel.com>
Suggested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Cc: Alex Shi <alex.shi@intel.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Anton Blanchard <anton@samba.org>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: paul.gortmaker@windriver.com
Link: http://lkml.kernel.org/r/1359716356-23865-1-git-send-email-yuanhan.liu@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
		
	
			
		
			
				
	
	
		
			302 lines
		
	
	
	
		
			6.7 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
			
		
		
	
	
			302 lines
		
	
	
	
		
			6.7 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
| /* rwsem-spinlock.c: R/W semaphores: contention handling functions for
 | |
|  * generic spinlock implementation
 | |
|  *
 | |
|  * Copyright (c) 2001   David Howells (dhowells@redhat.com).
 | |
|  * - Derived partially from idea by Andrea Arcangeli <andrea@suse.de>
 | |
|  * - Derived also from comments by Linus
 | |
|  */
 | |
| #include <linux/rwsem.h>
 | |
| #include <linux/sched.h>
 | |
| #include <linux/export.h>
 | |
| 
 | |
| struct rwsem_waiter {
 | |
| 	struct list_head list;
 | |
| 	struct task_struct *task;
 | |
| 	unsigned int flags;
 | |
| #define RWSEM_WAITING_FOR_READ	0x00000001
 | |
| #define RWSEM_WAITING_FOR_WRITE	0x00000002
 | |
| };
 | |
| 
 | |
| int rwsem_is_locked(struct rw_semaphore *sem)
 | |
| {
 | |
| 	int ret = 1;
 | |
| 	unsigned long flags;
 | |
| 
 | |
| 	if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) {
 | |
| 		ret = (sem->activity != 0);
 | |
| 		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 | |
| 	}
 | |
| 	return ret;
 | |
| }
 | |
| EXPORT_SYMBOL(rwsem_is_locked);
 | |
| 
 | |
| /*
 | |
|  * initialise the semaphore
 | |
|  */
 | |
| void __init_rwsem(struct rw_semaphore *sem, const char *name,
 | |
| 		  struct lock_class_key *key)
 | |
| {
 | |
| #ifdef CONFIG_DEBUG_LOCK_ALLOC
 | |
| 	/*
 | |
| 	 * Make sure we are not reinitializing a held semaphore:
 | |
| 	 */
 | |
| 	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
 | |
| 	lockdep_init_map(&sem->dep_map, name, key, 0);
 | |
| #endif
 | |
| 	sem->activity = 0;
 | |
| 	raw_spin_lock_init(&sem->wait_lock);
 | |
| 	INIT_LIST_HEAD(&sem->wait_list);
 | |
| }
 | |
| EXPORT_SYMBOL(__init_rwsem);
 | |
| 
 | |
| /*
 | |
|  * handle the lock release when processes blocked on it that can now run
 | |
|  * - if we come here, then:
 | |
|  *   - the 'active count' _reached_ zero
 | |
|  *   - the 'waiting count' is non-zero
 | |
|  * - the spinlock must be held by the caller
 | |
|  * - woken process blocks are discarded from the list after having task zeroed
 | |
|  * - writers are only woken if wakewrite is non-zero
 | |
|  */
 | |
| static inline struct rw_semaphore *
 | |
| __rwsem_do_wake(struct rw_semaphore *sem, int wakewrite)
 | |
| {
 | |
| 	struct rwsem_waiter *waiter;
 | |
| 	struct task_struct *tsk;
 | |
| 	int woken;
 | |
| 
 | |
| 	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
 | |
| 
 | |
| 	if (!wakewrite) {
 | |
| 		if (waiter->flags & RWSEM_WAITING_FOR_WRITE)
 | |
| 			goto out;
 | |
| 		goto dont_wake_writers;
 | |
| 	}
 | |
| 
 | |
| 	/*
 | |
| 	 * as we support write lock stealing, we can't set sem->activity
 | |
| 	 * to -1 here to indicate we get the lock. Instead, we wake it up
 | |
| 	 * to let it go get it again.
 | |
| 	 */
 | |
| 	if (waiter->flags & RWSEM_WAITING_FOR_WRITE) {
 | |
| 		wake_up_process(waiter->task);
 | |
| 		goto out;
 | |
| 	}
 | |
| 
 | |
| 	/* grant an infinite number of read locks to the front of the queue */
 | |
|  dont_wake_writers:
 | |
| 	woken = 0;
 | |
| 	while (waiter->flags & RWSEM_WAITING_FOR_READ) {
 | |
| 		struct list_head *next = waiter->list.next;
 | |
| 
 | |
| 		list_del(&waiter->list);
 | |
| 		tsk = waiter->task;
 | |
| 		smp_mb();
 | |
| 		waiter->task = NULL;
 | |
| 		wake_up_process(tsk);
 | |
| 		put_task_struct(tsk);
 | |
| 		woken++;
 | |
| 		if (list_empty(&sem->wait_list))
 | |
| 			break;
 | |
| 		waiter = list_entry(next, struct rwsem_waiter, list);
 | |
| 	}
 | |
| 
 | |
| 	sem->activity += woken;
 | |
| 
 | |
|  out:
 | |
| 	return sem;
 | |
| }
 | |
| 
 | |
| /*
 | |
|  * wake a single writer
 | |
|  */
 | |
| static inline struct rw_semaphore *
 | |
| __rwsem_wake_one_writer(struct rw_semaphore *sem)
 | |
| {
 | |
| 	struct rwsem_waiter *waiter;
 | |
| 
 | |
| 	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
 | |
| 	wake_up_process(waiter->task);
 | |
| 
 | |
| 	return sem;
 | |
| }
 | |
| 
 | |
| /*
 | |
|  * get a read lock on the semaphore
 | |
|  */
 | |
| void __sched __down_read(struct rw_semaphore *sem)
 | |
| {
 | |
| 	struct rwsem_waiter waiter;
 | |
| 	struct task_struct *tsk;
 | |
| 	unsigned long flags;
 | |
| 
 | |
| 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 | |
| 
 | |
| 	if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
 | |
| 		/* granted */
 | |
| 		sem->activity++;
 | |
| 		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 | |
| 		goto out;
 | |
| 	}
 | |
| 
 | |
| 	tsk = current;
 | |
| 	set_task_state(tsk, TASK_UNINTERRUPTIBLE);
 | |
| 
 | |
| 	/* set up my own style of waitqueue */
 | |
| 	waiter.task = tsk;
 | |
| 	waiter.flags = RWSEM_WAITING_FOR_READ;
 | |
| 	get_task_struct(tsk);
 | |
| 
 | |
| 	list_add_tail(&waiter.list, &sem->wait_list);
 | |
| 
 | |
| 	/* we don't need to touch the semaphore struct anymore */
 | |
| 	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 | |
| 
 | |
| 	/* wait to be given the lock */
 | |
| 	for (;;) {
 | |
| 		if (!waiter.task)
 | |
| 			break;
 | |
| 		schedule();
 | |
| 		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
 | |
| 	}
 | |
| 
 | |
| 	tsk->state = TASK_RUNNING;
 | |
|  out:
 | |
| 	;
 | |
| }
 | |
| 
 | |
| /*
 | |
|  * trylock for reading -- returns 1 if successful, 0 if contention
 | |
|  */
 | |
| int __down_read_trylock(struct rw_semaphore *sem)
 | |
| {
 | |
| 	unsigned long flags;
 | |
| 	int ret = 0;
 | |
| 
 | |
| 
 | |
| 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 | |
| 
 | |
| 	if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
 | |
| 		/* granted */
 | |
| 		sem->activity++;
 | |
| 		ret = 1;
 | |
| 	}
 | |
| 
 | |
| 	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 | |
| 
 | |
| 	return ret;
 | |
| }
 | |
| 
 | |
| /*
 | |
|  * get a write lock on the semaphore
 | |
|  */
 | |
| void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
 | |
| {
 | |
| 	struct rwsem_waiter waiter;
 | |
| 	struct task_struct *tsk;
 | |
| 	unsigned long flags;
 | |
| 
 | |
| 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 | |
| 
 | |
| 	/* set up my own style of waitqueue */
 | |
| 	tsk = current;
 | |
| 	waiter.task = tsk;
 | |
| 	waiter.flags = RWSEM_WAITING_FOR_WRITE;
 | |
| 	list_add_tail(&waiter.list, &sem->wait_list);
 | |
| 
 | |
| 	/* wait for someone to release the lock */
 | |
| 	for (;;) {
 | |
| 		/*
 | |
| 		 * That is the key to support write lock stealing: allows the
 | |
| 		 * task already on CPU to get the lock soon rather than put
 | |
| 		 * itself into sleep and waiting for system woke it or someone
 | |
| 		 * else in the head of the wait list up.
 | |
| 		 */
 | |
| 		if (sem->activity == 0)
 | |
| 			break;
 | |
| 		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
 | |
| 		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 | |
| 		schedule();
 | |
| 		raw_spin_lock_irqsave(&sem->wait_lock, flags);
 | |
| 	}
 | |
| 	/* got the lock */
 | |
| 	sem->activity = -1;
 | |
| 	list_del(&waiter.list);
 | |
| 
 | |
| 	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 | |
| }
 | |
| 
 | |
| void __sched __down_write(struct rw_semaphore *sem)
 | |
| {
 | |
| 	__down_write_nested(sem, 0);
 | |
| }
 | |
| 
 | |
| /*
 | |
|  * trylock for writing -- returns 1 if successful, 0 if contention
 | |
|  */
 | |
| int __down_write_trylock(struct rw_semaphore *sem)
 | |
| {
 | |
| 	unsigned long flags;
 | |
| 	int ret = 0;
 | |
| 
 | |
| 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 | |
| 
 | |
| 	if (sem->activity == 0) {
 | |
| 		/* got the lock */
 | |
| 		sem->activity = -1;
 | |
| 		ret = 1;
 | |
| 	}
 | |
| 
 | |
| 	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 | |
| 
 | |
| 	return ret;
 | |
| }
 | |
| 
 | |
| /*
 | |
|  * release a read lock on the semaphore
 | |
|  */
 | |
| void __up_read(struct rw_semaphore *sem)
 | |
| {
 | |
| 	unsigned long flags;
 | |
| 
 | |
| 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 | |
| 
 | |
| 	if (--sem->activity == 0 && !list_empty(&sem->wait_list))
 | |
| 		sem = __rwsem_wake_one_writer(sem);
 | |
| 
 | |
| 	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 | |
| }
 | |
| 
 | |
| /*
 | |
|  * release a write lock on the semaphore
 | |
|  */
 | |
| void __up_write(struct rw_semaphore *sem)
 | |
| {
 | |
| 	unsigned long flags;
 | |
| 
 | |
| 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 | |
| 
 | |
| 	sem->activity = 0;
 | |
| 	if (!list_empty(&sem->wait_list))
 | |
| 		sem = __rwsem_do_wake(sem, 1);
 | |
| 
 | |
| 	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 | |
| }
 | |
| 
 | |
| /*
 | |
|  * downgrade a write lock into a read lock
 | |
|  * - just wake up any readers at the front of the queue
 | |
|  */
 | |
| void __downgrade_write(struct rw_semaphore *sem)
 | |
| {
 | |
| 	unsigned long flags;
 | |
| 
 | |
| 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 | |
| 
 | |
| 	sem->activity = 1;
 | |
| 	if (!list_empty(&sem->wait_list))
 | |
| 		sem = __rwsem_do_wake(sem, 0);
 | |
| 
 | |
| 	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 | |
| }
 | |
| 
 |