locking: Optimize lock_bh functions

Currently all _bh_ lock functions do two preempt_count operations:

  local_bh_disable();
  preempt_disable();

and for the unlock:

  preempt_enable_no_resched();
  local_bh_enable();

Since its a waste of perfectly good cycles to modify the same variable
twice when you can do it in one go; use the new
__local_bh_{dis,en}able_ip() functions that allow us to provide a
preempt_count value to add/sub.

So define SOFTIRQ_LOCK_OFFSET as the offset a _bh_ lock needs to
add/sub to be done in one go.

As a bonus it gets rid of the preempt_enable_no_resched() usage.

This reduces a 1000 loops of:

  spin_lock_bh(&bh_lock);
  spin_unlock_bh(&bh_lock);

from 53596 cycles to 51995 cycles. I didn't do enough measurements to
say for absolute sure that the result is significant but the the few
runs I did for each suggest it is so.

Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: jacob.jun.pan@linux.intel.com
Cc: Mike Galbraith <bitbucket@online.de>
Cc: hpa@zytor.com
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: lenb@kernel.org
Cc: rjw@rjwysocki.net
Cc: rui.zhang@intel.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20131119151338.GF3694@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Peter Zijlstra 2013-11-19 16:13:38 +01:00 committed by Ingo Molnar
parent c726099ec2
commit 9ea4c38006
5 changed files with 36 additions and 23 deletions

View file

@ -78,6 +78,21 @@
# define PREEMPT_CHECK_OFFSET 0
#endif
/*
* The preempt_count offset needed for things like:
*
* spin_lock_bh()
*
* Which need to disable both preemption (CONFIG_PREEMPT_COUNT) and
* softirqs, such that unlock sequences of:
*
* spin_unlock();
* local_bh_enable();
*
* Work as expected.
*/
#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_CHECK_OFFSET)
/*
* Are we running in atomic context? WARNING: this macro cannot
* always detect atomic context; in particular, it cannot know about

View file

@ -172,8 +172,7 @@ static inline void __raw_read_lock_irq(rwlock_t *lock)
static inline void __raw_read_lock_bh(rwlock_t *lock)
{
local_bh_disable();
preempt_disable();
__local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
LOCK_CONTENDED(lock, do_raw_read_trylock, do_raw_read_lock);
}
@ -200,8 +199,7 @@ static inline void __raw_write_lock_irq(rwlock_t *lock)
static inline void __raw_write_lock_bh(rwlock_t *lock)
{
local_bh_disable();
preempt_disable();
__local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
LOCK_CONTENDED(lock, do_raw_write_trylock, do_raw_write_lock);
}
@ -250,8 +248,7 @@ static inline void __raw_read_unlock_bh(rwlock_t *lock)
{
rwlock_release(&lock->dep_map, 1, _RET_IP_);
do_raw_read_unlock(lock);
preempt_enable_no_resched();
local_bh_enable_ip((unsigned long)__builtin_return_address(0));
__local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
}
static inline void __raw_write_unlock_irqrestore(rwlock_t *lock,
@ -275,8 +272,7 @@ static inline void __raw_write_unlock_bh(rwlock_t *lock)
{
rwlock_release(&lock->dep_map, 1, _RET_IP_);
do_raw_write_unlock(lock);
preempt_enable_no_resched();
local_bh_enable_ip((unsigned long)__builtin_return_address(0));
__local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
}
#endif /* __LINUX_RWLOCK_API_SMP_H */

View file

@ -131,8 +131,7 @@ static inline void __raw_spin_lock_irq(raw_spinlock_t *lock)
static inline void __raw_spin_lock_bh(raw_spinlock_t *lock)
{
local_bh_disable();
preempt_disable();
__local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock);
}
@ -174,20 +173,17 @@ static inline void __raw_spin_unlock_bh(raw_spinlock_t *lock)
{
spin_release(&lock->dep_map, 1, _RET_IP_);
do_raw_spin_unlock(lock);
preempt_enable_no_resched();
local_bh_enable_ip((unsigned long)__builtin_return_address(0));
__local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
}
static inline int __raw_spin_trylock_bh(raw_spinlock_t *lock)
{
local_bh_disable();
preempt_disable();
__local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
if (do_raw_spin_trylock(lock)) {
spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
return 1;
}
preempt_enable_no_resched();
local_bh_enable_ip((unsigned long)__builtin_return_address(0));
__local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
return 0;
}

View file

@ -24,11 +24,14 @@
* flags straight, to suppress compiler warnings of unused lock
* variables, and to add the proper checker annotations:
*/
#define ___LOCK(lock) \
do { __acquire(lock); (void)(lock); } while (0)
#define __LOCK(lock) \
do { preempt_disable(); __acquire(lock); (void)(lock); } while (0)
do { preempt_disable(); ___LOCK(lock); } while (0)
#define __LOCK_BH(lock) \
do { local_bh_disable(); __LOCK(lock); } while (0)
do { __local_bh_disable_ip(_THIS_IP_, SOFTIRQ_LOCK_OFFSET); ___LOCK(lock); } while (0)
#define __LOCK_IRQ(lock) \
do { local_irq_disable(); __LOCK(lock); } while (0)
@ -36,12 +39,15 @@
#define __LOCK_IRQSAVE(lock, flags) \
do { local_irq_save(flags); __LOCK(lock); } while (0)
#define ___UNLOCK(lock) \
do { __release(lock); (void)(lock); } while (0)
#define __UNLOCK(lock) \
do { preempt_enable(); __release(lock); (void)(lock); } while (0)
do { preempt_enable(); ___UNLOCK(lock); } while (0)
#define __UNLOCK_BH(lock) \
do { preempt_enable_no_resched(); local_bh_enable(); \
__release(lock); (void)(lock); } while (0)
do { __local_bh_enable_ip(_THIS_IP_, SOFTIRQ_LOCK_OFFSET); \
___UNLOCK(lock); } while (0)
#define __UNLOCK_IRQ(lock) \
do { local_irq_enable(); __UNLOCK(lock); } while (0)

View file

@ -107,7 +107,7 @@ static void __local_bh_disable(unsigned long ip, unsigned int cnt)
/*
* Were softirqs turned off above:
*/
if (softirq_count() == cnt)
if (softirq_count() == (cnt & SOFTIRQ_MASK))
trace_softirqs_off(ip);
raw_local_irq_restore(flags);
@ -133,7 +133,7 @@ static void __local_bh_enable(unsigned int cnt)
{
WARN_ON_ONCE(!irqs_disabled());
if (softirq_count() == cnt)
if (softirq_count() == (cnt & SOFTIRQ_MASK))
trace_softirqs_on(_RET_IP_);
preempt_count_sub(cnt);
}