summaryrefslogtreecommitdiff
path: root/arch/s390/include/asm/spinlock.h
diff options
context:
space:
mode:
authorMartin Schwidefsky <schwidefsky@de.ibm.com>2017-03-24 19:25:02 +0300
committerMartin Schwidefsky <schwidefsky@de.ibm.com>2017-09-28 08:29:44 +0300
commitb96f7d881ad94203e997cd2aa7112d4a06d121ef (patch)
tree7c942d7f08610684a3cbce30a3052bde6549b92e /arch/s390/include/asm/spinlock.h
parent8153380379ecc8381f6d55f6497de31a36c75aa5 (diff)
downloadlinux-b96f7d881ad94203e997cd2aa7112d4a06d121ef.tar.xz
s390/spinlock: introduce spinlock wait queueing
The queued spinlock code for s390 follows the principles of the common code qspinlock implementation but with a few notable differences. The format of the spinlock_t locking word differs, s390 needs to store the logical CPU number of the lock holder in the spinlock_t to be able to use the diagnose 9c directed yield hypervisor call. The inline code sequences for spin_lock and spin_unlock are nice and short. The inline portion of a spin_lock now typically looks like this: lhi %r0,0 # 0 indicates an empty lock l %r1,0x3a0 # CPU number + 1 from lowcore cs %r0,%r1,<some_lock> # lock operation jnz call_wait # on failure call wait function locked: ... call_wait: la %r2,<some_lock> brasl %r14,arch_spin_lock_wait j locked A spin_unlock is as simple as before: lhi %r0,0 sth %r0,2(%r2) # unlock operation After a CPU has queued itself it may not enable interrupts again for the arch_spin_lock_flags() variant. The arch_spin_lock_wait_flags wait function is removed. To improve performance the code implements opportunistic lock stealing. If the wait function finds a spinlock_t that indicates that the lock is free but there are queued waiters, the CPU may steal the lock up to three times without queueing itself. The lock stealing update the steal counter in the lock word to prevent more than 3 steals. The counter is reset at the time the CPU next in the queue successfully takes the lock. While the queued spinlocks improve performance in a system with dedicated CPUs, in a virtualized environment with continuously overcommitted CPUs the queued spinlocks can have a negative effect on performance. This is due to the fact that a queued CPU that is preempted by the hypervisor will block the queue at some point even without holding the lock. With the classic spinlock it does not matter if a CPU is preempted that waits for the lock. Therefore use the queued spinlock code only if the system runs with dedicated CPUs and fall back to classic spinlocks when running with shared CPUs. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Diffstat (limited to 'arch/s390/include/asm/spinlock.h')
-rw-r--r--arch/s390/include/asm/spinlock.h18
1 files changed, 7 insertions, 11 deletions
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index 6727cc30d59b..2da4a6d13f54 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -36,15 +36,11 @@ bool arch_vcpu_is_preempted(int cpu);
*/
void arch_lock_relax(int cpu);
+void arch_spin_relax(arch_spinlock_t *lock);
void arch_spin_lock_wait(arch_spinlock_t *);
int arch_spin_trylock_retry(arch_spinlock_t *);
-void arch_spin_lock_wait_flags(arch_spinlock_t *, unsigned long flags);
-
-static inline void arch_spin_relax(arch_spinlock_t *lock)
-{
- arch_lock_relax(lock->lock);
-}
+void arch_spin_lock_setup(int cpu);
static inline u32 arch_spin_lockval(int cpu)
{
@@ -64,8 +60,7 @@ static inline int arch_spin_is_locked(arch_spinlock_t *lp)
static inline int arch_spin_trylock_once(arch_spinlock_t *lp)
{
barrier();
- return likely(arch_spin_value_unlocked(*lp) &&
- __atomic_cmpxchg_bool(&lp->lock, 0, SPINLOCK_LOCKVAL));
+ return likely(__atomic_cmpxchg_bool(&lp->lock, 0, SPINLOCK_LOCKVAL));
}
static inline void arch_spin_lock(arch_spinlock_t *lp)
@@ -78,7 +73,7 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *lp,
unsigned long flags)
{
if (!arch_spin_trylock_once(lp))
- arch_spin_lock_wait_flags(lp, flags);
+ arch_spin_lock_wait(lp);
}
static inline int arch_spin_trylock(arch_spinlock_t *lp)
@@ -95,8 +90,9 @@ static inline void arch_spin_unlock(arch_spinlock_t *lp)
#ifdef CONFIG_HAVE_MARCH_ZEC12_FEATURES
" .long 0xb2fa0070\n" /* NIAI 7 */
#endif
- " st %1,%0\n"
- : "=Q" (lp->lock) : "d" (0) : "cc", "memory");
+ " sth %1,%0\n"
+ : "=Q" (((unsigned short *) &lp->lock)[1])
+ : "d" (0) : "cc", "memory");
}
/*