Commit 02e525b2 authored by Peter Zijlstra's avatar Peter Zijlstra Committed by Ingo Molnar
Browse files

locking/percpu-rwsem: Remove preempt_disable variants 



Effective revert commit:

  87709e28 ("fs/locks: Use percpu_down_read_preempt_disable()")

This is causing major pain for PREEMPT_RT.

Sebastian did a lot of lockperf runs on 2 and 4 node machines with all
preemption modes (PREEMPT=n should be an obvious NOP for this patch
and thus serves as a good control) and no results showed significance
over 2-sigma (the PREEMPT=n results were almost empty at 1-sigma).

Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: default avatarSebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
parent 0614621d

fs/locks.c

+16 −16
Original line number Diff line number Diff line
@@ -1058,7 +1058,7 @@ static int flock_lock_inode(struct inode *inode, struct file_lock *request) 
			return -ENOMEM;

	}



	percpu_down_read_preempt_disable(&file_rwsem);

	percpu_down_read(&file_rwsem);

	spin_lock(&ctx->flc_lock);

	if (request->fl_flags & FL_ACCESS)

		goto find_conflict;
@@ -1100,7 +1100,7 @@ static int flock_lock_inode(struct inode *inode, struct file_lock *request) 


out:

	spin_unlock(&ctx->flc_lock);

	percpu_up_read_preempt_enable(&file_rwsem);

	percpu_up_read(&file_rwsem);

	if (new_fl)

		locks_free_lock(new_fl);

	locks_dispose_list(&dispose);
@@ -1138,7 +1138,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, 
		new_fl2 = locks_alloc_lock();

	}



	percpu_down_read_preempt_disable(&file_rwsem);

	percpu_down_read(&file_rwsem);

	spin_lock(&ctx->flc_lock);

	/*

	 * New lock request. Walk all POSIX locks and look for conflicts. If
@@ -1312,7 +1312,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, 
	}

 out:

	spin_unlock(&ctx->flc_lock);

	percpu_up_read_preempt_enable(&file_rwsem);

	percpu_up_read(&file_rwsem);

	/*

	 * Free any unused locks.

	 */
@@ -1584,7 +1584,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) 
		return error;

	}



	percpu_down_read_preempt_disable(&file_rwsem);

	percpu_down_read(&file_rwsem);

	spin_lock(&ctx->flc_lock);



	time_out_leases(inode, &dispose);
@@ -1636,13 +1636,13 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) 
	locks_insert_block(fl, new_fl, leases_conflict);

	trace_break_lease_block(inode, new_fl);

	spin_unlock(&ctx->flc_lock);

	percpu_up_read_preempt_enable(&file_rwsem);

	percpu_up_read(&file_rwsem);



	locks_dispose_list(&dispose);

	error = wait_event_interruptible_timeout(new_fl->fl_wait,

						!new_fl->fl_blocker, break_time);



	percpu_down_read_preempt_disable(&file_rwsem);

	percpu_down_read(&file_rwsem);

	spin_lock(&ctx->flc_lock);

	trace_break_lease_unblock(inode, new_fl);

	locks_delete_block(new_fl);
@@ -1659,7 +1659,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) 
	}

out:

	spin_unlock(&ctx->flc_lock);

	percpu_up_read_preempt_enable(&file_rwsem);

	percpu_up_read(&file_rwsem);

	locks_dispose_list(&dispose);

	locks_free_lock(new_fl);

	return error;
@@ -1729,7 +1729,7 @@ int fcntl_getlease(struct file *filp) 


	ctx = smp_load_acquire(&inode->i_flctx);

	if (ctx && !list_empty_careful(&ctx->flc_lease)) {

		percpu_down_read_preempt_disable(&file_rwsem);

		percpu_down_read(&file_rwsem);

		spin_lock(&ctx->flc_lock);

		time_out_leases(inode, &dispose);

		list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
@@ -1739,7 +1739,7 @@ int fcntl_getlease(struct file *filp) 
			break;

		}

		spin_unlock(&ctx->flc_lock);

		percpu_up_read_preempt_enable(&file_rwsem);

		percpu_up_read(&file_rwsem);



		locks_dispose_list(&dispose);

	}
@@ -1813,7 +1813,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr 
		return -EINVAL;

	}



	percpu_down_read_preempt_disable(&file_rwsem);

	percpu_down_read(&file_rwsem);

	spin_lock(&ctx->flc_lock);

	time_out_leases(inode, &dispose);

	error = check_conflicting_open(dentry, arg, lease->fl_flags);
@@ -1884,7 +1884,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr 
		lease->fl_lmops->lm_setup(lease, priv);

out:

	spin_unlock(&ctx->flc_lock);

	percpu_up_read_preempt_enable(&file_rwsem);

	percpu_up_read(&file_rwsem);

	locks_dispose_list(&dispose);

	if (is_deleg)

		inode_unlock(inode);
@@ -1907,7 +1907,7 @@ static int generic_delete_lease(struct file *filp, void *owner) 
		return error;

	}



	percpu_down_read_preempt_disable(&file_rwsem);

	percpu_down_read(&file_rwsem);

	spin_lock(&ctx->flc_lock);

	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {

		if (fl->fl_file == filp &&
@@ -1920,7 +1920,7 @@ static int generic_delete_lease(struct file *filp, void *owner) 
	if (victim)

		error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose);

	spin_unlock(&ctx->flc_lock);

	percpu_up_read_preempt_enable(&file_rwsem);

	percpu_up_read(&file_rwsem);

	locks_dispose_list(&dispose);

	return error;

}
@@ -2643,13 +2643,13 @@ locks_remove_lease(struct file *filp, struct file_lock_context *ctx) 
	if (list_empty(&ctx->flc_lease))

		return;



	percpu_down_read_preempt_disable(&file_rwsem);

	percpu_down_read(&file_rwsem);

	spin_lock(&ctx->flc_lock);

	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list)

		if (filp == fl->fl_file)

			lease_modify(fl, F_UNLCK, &dispose);

	spin_unlock(&ctx->flc_lock);

	percpu_up_read_preempt_enable(&file_rwsem);

	percpu_up_read(&file_rwsem);



	locks_dispose_list(&dispose);

}

include/linux/percpu-rwsem.h

+4 −20
Original line number Diff line number Diff line
@@ -29,7 +29,7 @@ static struct percpu_rw_semaphore name = { \ 
extern int __percpu_down_read(struct percpu_rw_semaphore *, int);

extern void __percpu_up_read(struct percpu_rw_semaphore *);



static inline void percpu_down_read_preempt_disable(struct percpu_rw_semaphore *sem)

static inline void percpu_down_read(struct percpu_rw_semaphore *sem)

{

	might_sleep();
@@ -47,16 +47,10 @@ static inline void percpu_down_read_preempt_disable(struct percpu_rw_semaphore * 
	__this_cpu_inc(*sem->read_count);

	if (unlikely(!rcu_sync_is_idle(&sem->rss)))

		__percpu_down_read(sem, false); /* Unconditional memory barrier */

	barrier();

	/*

	 * The barrier() prevents the compiler from

	 * The preempt_enable() prevents the compiler from

	 * bleeding the critical section out.

	 */

}



static inline void percpu_down_read(struct percpu_rw_semaphore *sem)

{

	percpu_down_read_preempt_disable(sem);

	preempt_enable();

}
@@ -83,13 +77,9 @@ static inline int percpu_down_read_trylock(struct percpu_rw_semaphore *sem) 
	return ret;

}



static inline void percpu_up_read_preempt_enable(struct percpu_rw_semaphore *sem)

static inline void percpu_up_read(struct percpu_rw_semaphore *sem)

{

	/*

	 * The barrier() prevents the compiler from

	 * bleeding the critical section out.

	 */

	barrier();

	preempt_disable();

	/*

	 * Same as in percpu_down_read().

	 */
@@ -102,12 +92,6 @@ static inline void percpu_up_read_preempt_enable(struct percpu_rw_semaphore *sem 
	rwsem_release(&sem->rw_sem.dep_map, 1, _RET_IP_);

}



static inline void percpu_up_read(struct percpu_rw_semaphore *sem)

{

	preempt_disable();

	percpu_up_read_preempt_enable(sem);

}



extern void percpu_down_write(struct percpu_rw_semaphore *);

extern void percpu_up_write(struct percpu_rw_semaphore *);