s390/spinlock: optimize spin_unlock code

Use a memory barrier + store sequence instead of a load + compare and swap
sequence to unlock a spinlock and an rw lock.
For the spinlock case this saves us two memory reads and a not needed cpu
serialization after the compare and swap instruction stored the new value.

The kernel size (performance_defconfig) gets reduced by ~14k.

Average execution time of a tight inlined spin_unlock loop drops from
5.8ns to 0.7ns on a zEC12 machine.

An artificial stress test case where several counters are protected with
a single spinlock and which are only incremented while holding the spinlock
shows ~30% improvement on a 4 cpu machine.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
This commit is contained in:
Heiko Carstens
2014-09-08 08:20:43 +02:00
committed by Martin Schwidefsky
parent 3d1e220d08
commit 4423028203
2 changed files with 18 additions and 9 deletions

View File

@@ -64,11 +64,6 @@ static inline int arch_spin_trylock_once(arch_spinlock_t *lp)
_raw_compare_and_swap(&lp->lock, 0, SPINLOCK_LOCKVAL));
}
static inline int arch_spin_tryrelease_once(arch_spinlock_t *lp)
{
return _raw_compare_and_swap(&lp->lock, SPINLOCK_LOCKVAL, 0);
}
static inline void arch_spin_lock(arch_spinlock_t *lp)
{
if (!arch_spin_trylock_once(lp))
@@ -91,7 +86,13 @@ static inline int arch_spin_trylock(arch_spinlock_t *lp)
static inline void arch_spin_unlock(arch_spinlock_t *lp)
{
arch_spin_tryrelease_once(lp);
typecheck(unsigned int, lp->lock);
asm volatile(
__ASM_BARRIER
"st %1,%0\n"
: "+Q" (lp->lock)
: "d" (0)
: "cc", "memory");
}
static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
@@ -179,7 +180,13 @@ static inline void arch_write_lock_flags(arch_rwlock_t *rw, unsigned long flags)
static inline void arch_write_unlock(arch_rwlock_t *rw)
{
_raw_compare_and_swap(&rw->lock, 0x80000000, 0);
typecheck(unsigned int, rw->lock);
asm volatile(
__ASM_BARRIER
"st %1,%0\n"
: "+Q" (rw->lock)
: "d" (0)
: "cc", "memory");
}
static inline int arch_read_trylock(arch_rwlock_t *rw)