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 <[email protected]>
Signed-off-by: Peter Zijlstra <[email protected]>
Cc: [email protected]
Cc: Mike Galbraith <[email protected]>
Cc: [email protected]
Cc: Arjan van de Ven <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: Linus Torvalds <[email protected]>
Cc: Andrew Morton <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
diff --git a/include/linux/preempt_mask.h b/include/linux/preempt_mask.h
index d169820..b8d96bc 100644
--- a/include/linux/preempt_mask.h
+++ b/include/linux/preempt_mask.h
@@ -79,6 +79,21 @@
#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
* held spinlocks in non-preemptible kernels. Thus it should not be
diff --git a/include/linux/rwlock_api_smp.h b/include/linux/rwlock_api_smp.h
index 9c9f0495..5b9b84b 100644
--- a/include/linux/rwlock_api_smp.h
+++ b/include/linux/rwlock_api_smp.h
@@ -172,8 +172,7 @@
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_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 @@
{
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 @@
{
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 */
diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h
index bdb9993..42dfab8 100644
--- a/include/linux/spinlock_api_smp.h
+++ b/include/linux/spinlock_api_smp.h
@@ -131,8 +131,7 @@
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 @@
{
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;
}
diff --git a/include/linux/spinlock_api_up.h b/include/linux/spinlock_api_up.h
index af1f472..d0d1888 100644
--- a/include/linux/spinlock_api_up.h
+++ b/include/linux/spinlock_api_up.h
@@ -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)
