linux/kernel/locking/rwsem.c
Waiman Long 925b9cd1b8 locking/rwsem: Make owner store task pointer of last owning reader
Currently, when a reader acquires a lock, it only sets the
RWSEM_READER_OWNED bit in the owner field. The other bits are simply
not used. When debugging hanging cases involving rwsems and readers,
the owner value does not provide much useful information at all.

This patch modifies the current behavior to always store the task_struct
pointer of the last rwsem-acquiring reader in a reader-owned rwsem. This
may be useful in debugging rwsem hanging cases especially if only one
reader is involved. However, the task in the owner field may not the
real owner or one of the real owners at all when the owner value is
examined, for example, in a crash dump. So it is just an additional
hint about the past history.

If CONFIG_DEBUG_RWSEMS=y is enabled, the owner field will be checked at
unlock time too to make sure the task pointer value is valid. That does
have a slight performance cost and so is only enabled as part of that
debug option.

From the performance point of view, it is expected that the changes
shouldn't have any noticeable performance impact. A rwsem microbenchmark
(with 48 worker threads and 1:1 reader/writer ratio) was ran on a
2-socket 24-core 48-thread Haswell system.  The locking rates on a
4.19-rc1 based kernel were as follows:

  1) Unpatched kernel:				543.3 kops/s
  2) Patched kernel:				549.2 kops/s
  3) Patched kernel (CONFIG_DEBUG_RWSEMS on):	546.6 kops/s

There was actually a slight increase in performance (1.1%) in this
particular case. Maybe it was caused by the elimination of a branch or
just a testing noise. Turning on the CONFIG_DEBUG_RWSEMS option also
had less than the expected impact on performance.

The least significant 2 bits of the owner value are now used to designate
the rwsem is readers owned and the owners are anonymous.

Signed-off-by: Waiman Long <longman@redhat.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Link: http://lkml.kernel.org/r/1536265114-10842-1-git-send-email-longman@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-09-10 12:04:07 +02:00

226 lines
4.5 KiB
C

// SPDX-License-Identifier: GPL-2.0
/* kernel/rwsem.c: R/W semaphores, public implementation
*
* Written by David Howells (dhowells@redhat.com).
* Derived from asm-i386/semaphore.h
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/sched/debug.h>
#include <linux/export.h>
#include <linux/rwsem.h>
#include <linux/atomic.h>
#include "rwsem.h"
/*
* lock for reading
*/
void __sched down_read(struct rw_semaphore *sem)
{
might_sleep();
rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_);
LOCK_CONTENDED(sem, __down_read_trylock, __down_read);
rwsem_set_reader_owned(sem);
}
EXPORT_SYMBOL(down_read);
int __sched down_read_killable(struct rw_semaphore *sem)
{
might_sleep();
rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_);
if (LOCK_CONTENDED_RETURN(sem, __down_read_trylock, __down_read_killable)) {
rwsem_release(&sem->dep_map, 1, _RET_IP_);
return -EINTR;
}
rwsem_set_reader_owned(sem);
return 0;
}
EXPORT_SYMBOL(down_read_killable);
/*
* trylock for reading -- returns 1 if successful, 0 if contention
*/
int down_read_trylock(struct rw_semaphore *sem)
{
int ret = __down_read_trylock(sem);
if (ret == 1) {
rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_);
rwsem_set_reader_owned(sem);
}
return ret;
}
EXPORT_SYMBOL(down_read_trylock);
/*
* lock for writing
*/
void __sched down_write(struct rw_semaphore *sem)
{
might_sleep();
rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
rwsem_set_owner(sem);
}
EXPORT_SYMBOL(down_write);
/*
* lock for writing
*/
int __sched down_write_killable(struct rw_semaphore *sem)
{
might_sleep();
rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock, __down_write_killable)) {
rwsem_release(&sem->dep_map, 1, _RET_IP_);
return -EINTR;
}
rwsem_set_owner(sem);
return 0;
}
EXPORT_SYMBOL(down_write_killable);
/*
* trylock for writing -- returns 1 if successful, 0 if contention
*/
int down_write_trylock(struct rw_semaphore *sem)
{
int ret = __down_write_trylock(sem);
if (ret == 1) {
rwsem_acquire(&sem->dep_map, 0, 1, _RET_IP_);
rwsem_set_owner(sem);
}
return ret;
}
EXPORT_SYMBOL(down_write_trylock);
/*
* release a read lock
*/
void up_read(struct rw_semaphore *sem)
{
rwsem_release(&sem->dep_map, 1, _RET_IP_);
DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED));
rwsem_clear_reader_owned(sem);
__up_read(sem);
}
EXPORT_SYMBOL(up_read);
/*
* release a write lock
*/
void up_write(struct rw_semaphore *sem)
{
rwsem_release(&sem->dep_map, 1, _RET_IP_);
DEBUG_RWSEMS_WARN_ON(sem->owner != current);
rwsem_clear_owner(sem);
__up_write(sem);
}
EXPORT_SYMBOL(up_write);
/*
* downgrade write lock to read lock
*/
void downgrade_write(struct rw_semaphore *sem)
{
lock_downgrade(&sem->dep_map, _RET_IP_);
DEBUG_RWSEMS_WARN_ON(sem->owner != current);
rwsem_set_reader_owned(sem);
__downgrade_write(sem);
}
EXPORT_SYMBOL(downgrade_write);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
void down_read_nested(struct rw_semaphore *sem, int subclass)
{
might_sleep();
rwsem_acquire_read(&sem->dep_map, subclass, 0, _RET_IP_);
LOCK_CONTENDED(sem, __down_read_trylock, __down_read);
rwsem_set_reader_owned(sem);
}
EXPORT_SYMBOL(down_read_nested);
void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest)
{
might_sleep();
rwsem_acquire_nest(&sem->dep_map, 0, 0, nest, _RET_IP_);
LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
rwsem_set_owner(sem);
}
EXPORT_SYMBOL(_down_write_nest_lock);
void down_read_non_owner(struct rw_semaphore *sem)
{
might_sleep();
__down_read(sem);
__rwsem_set_reader_owned(sem, NULL);
}
EXPORT_SYMBOL(down_read_non_owner);
void down_write_nested(struct rw_semaphore *sem, int subclass)
{
might_sleep();
rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_);
LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
rwsem_set_owner(sem);
}
EXPORT_SYMBOL(down_write_nested);
int __sched down_write_killable_nested(struct rw_semaphore *sem, int subclass)
{
might_sleep();
rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_);
if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock, __down_write_killable)) {
rwsem_release(&sem->dep_map, 1, _RET_IP_);
return -EINTR;
}
rwsem_set_owner(sem);
return 0;
}
EXPORT_SYMBOL(down_write_killable_nested);
void up_read_non_owner(struct rw_semaphore *sem)
{
DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED));
__up_read(sem);
}
EXPORT_SYMBOL(up_read_non_owner);
#endif