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>

1 files changed, 4 insertions, 8 deletions

diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h
index bdb9993f0fda..42dfab89e740 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_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;
 }