@@ -10,9 +10,6 @@
*/
typedef struct {
arch_rwlock_t raw_lock;
-#ifdef CONFIG_GENERIC_LOCKBREAK
- unsigned int break_lock;
-#endif
#ifdef CONFIG_DEBUG_SPINLOCK
unsigned int magic, owner_cpu;
void *owner;
@@ -107,16 +107,11 @@ do { \
#define raw_spin_is_locked(lock) arch_spin_is_locked(&(lock)->raw_lock)
-#ifdef CONFIG_GENERIC_LOCKBREAK
-#define raw_spin_is_contended(lock) ((lock)->break_lock)
-#else
-
#ifdef arch_spin_is_contended
#define raw_spin_is_contended(lock) arch_spin_is_contended(&(lock)->raw_lock)
#else
#define raw_spin_is_contended(lock) (((void)(lock), 0))
#endif /*arch_spin_is_contended*/
-#endif
/*
* This barrier must provide two things:
@@ -19,9 +19,6 @@
typedef struct raw_spinlock {
arch_spinlock_t raw_lock;
-#ifdef CONFIG_GENERIC_LOCKBREAK
- unsigned int break_lock;
-#endif
#ifdef CONFIG_DEBUG_SPINLOCK
unsigned int magic, owner_cpu;
void *owner;
@@ -66,12 +66,8 @@ void __lockfunc __raw_##op##_lock(locktype##_t *lock) \
break; \
preempt_enable(); \
\
- if (!(lock)->break_lock) \
- (lock)->break_lock = 1; \
- \
arch_##op##_relax(&lock->raw_lock); \
} \
- (lock)->break_lock = 0; \
} \
\
unsigned long __lockfunc __raw_##op##_lock_irqsave(locktype##_t *lock) \
@@ -86,12 +82,9 @@ unsigned long __lockfunc __raw_##op##_lock_irqsave(locktype##_t *lock) \
local_irq_restore(flags); \
preempt_enable(); \
\
- if (!(lock)->break_lock) \
- (lock)->break_lock = 1; \
- \
arch_##op##_relax(&lock->raw_lock); \
} \
- (lock)->break_lock = 0; \
+ \
return flags; \
} \
\
When CONFIG_GENERIC_LOCKBEAK=y, locking structures grow an extra int break_lock field which is used to implement raw_spin_is_contended() by setting the field to 1 when waiting on a lock and clearing it to zero when holding a lock. However, there are a few problems with this approach: - There is a write-write race between a CPU successfully taking the lock (and subsequently writing break_lock = 0) and a waiter waiting on the lock (and subsequently writing break_lock = 1). This could result in a contended lock being reported as uncontended and vice-versa. - On machines with store buffers, nothing guarantees that the writes to break_lock are visible to other CPUs at any particular time. - READ_ONCE/WRITE_ONCE are not used, so the field is potentially susceptible to harmful compiler optimisations, Consequently, the usefulness of this field is unclear and we'd be better off removing it and allowing architectures to implement raw_spin_is_contended() by providing a definition of arch_spin_is_contended(), as they can when CONFIG_GENERIC_LOCKBREAK=n. Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Signed-off-by: Will Deacon <will.deacon@arm.com> --- include/linux/rwlock_types.h | 3 --- include/linux/spinlock.h | 5 ----- include/linux/spinlock_types.h | 3 --- kernel/locking/spinlock.c | 9 +-------- 4 files changed, 1 insertion(+), 19 deletions(-) -- 2.1.4