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 <[e-mail]>
Signed-off-by: Peter Zijlstra <[e-mail]>
Cc: [e-mail]
Cc: Mike Galbraith <[e-mail]>
Cc: [e-mail]
Cc: Arjan van de Ven <[e-mail]>
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: Linus Torvalds <[e-mail]>
Cc: Andrew Morton <[e-mail]>
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: Ingo Molnar <[e-mail]>

include/linux/preempt_mask.h

···
 #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

include/linux/rwlock_api_smp.h

···
 
 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);
 }
···
 
 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);
 }
···
 {
 	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,
···
 {
 	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 */

include/linux/spinlock_api_smp.h

···
 
 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);
 }
···
 {
 	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;
 }
 

include/linux/spinlock_api_up.h

···
  * 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)
···
 #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)

kernel/softirq.c

···
 	/*
 	 * Were softirqs turned off above:
 	 */
-	if (softirq_count() == cnt)
+	if (softirq_count() == (cnt & SOFTIRQ_MASK))
 		trace_softirqs_off(ip);
 	raw_local_irq_restore(flags);
 
···
 {
 	WARN_ON_ONCE(!irqs_disabled());
 
-	if (softirq_count() == cnt)
+	if (softirq_count() == (cnt & SOFTIRQ_MASK))
 		trace_softirqs_on(_RET_IP_);
 	preempt_count_sub(cnt);
 }