search for: clear_io_sync

...ch_spin_unlock > +#define arch_spin_trylock arch_spin_trylock > +#define arch_spin_lock arch_spin_lock > +#define arch_spin_lock_flags arch_spin_lock_flags > +#define arch_spin_unlock arch_spin_unlock > + > +static inline int arch_spin_trylock(arch_spinlock_t *lock) > +{ > + CLEAR_IO_SYNC; > + return queued_spin_trylock(lock); > +} > + > +static inline void arch_spin_lock(arch_spinlock_t *lock) > +{ > + CLEAR_IO_SYNC; > + queued_spin_lock(lock); > +} > + > +static inline > +void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) > +{...

...ch_spin_unlock > +#define arch_spin_trylock arch_spin_trylock > +#define arch_spin_lock arch_spin_lock > +#define arch_spin_lock_flags arch_spin_lock_flags > +#define arch_spin_unlock arch_spin_unlock > + > +static inline int arch_spin_trylock(arch_spinlock_t *lock) > +{ > + CLEAR_IO_SYNC; > + return queued_spin_trylock(lock); > +} > + > +static inline void arch_spin_lock(arch_spinlock_t *lock) > +{ > + CLEAR_IO_SYNC; > + queued_spin_lock(lock); > +} > + > +static inline > +void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) > +{...

...+#undef arch_spin_lock_flags +#undef arch_spin_unlock +#define arch_spin_trylock arch_spin_trylock +#define arch_spin_lock arch_spin_lock +#define arch_spin_lock_flags arch_spin_lock_flags +#define arch_spin_unlock arch_spin_unlock + +static inline int arch_spin_trylock(arch_spinlock_t *lock) +{ + CLEAR_IO_SYNC; + return queued_spin_trylock(lock); +} + +static inline void arch_spin_lock(arch_spinlock_t *lock) +{ + CLEAR_IO_SYNC; + queued_spin_lock(lock); +} + +static inline +void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) +{ + CLEAR_IO_SYNC; + queued_spin_lock(lock); +} + +static inl...

Hi All, this is the fairlock patchset. You can apply them and build successfully. patches are based on linux-next qspinlock can avoid waiter starved issue. It has about the same speed in single-thread and it can be much faster in high contention situations especially when the spinlock is embedded within the data structure to be protected. v7 -> v8: add one patch to drop a function call

Hi All, this is the fairlock patchset. You can apply them and build successfully. patches are based on linux-next qspinlock can avoid waiter starved issue. It has about the same speed in single-thread and it can be much faster in high contention situations especially when the spinlock is embedded within the data structure to be protected. v7 -> v8: add one patch to drop a function call

...lock_t *lock); > -extern void __rw_yield(arch_rwlock_t *lock); > -#else /* SPLPAR */ > -#define __spin_yield(x) barrier() > -#define __rw_yield(x) barrier() > -#define SHARED_PROCESSOR 0 > -#endif > - > ?static inline void arch_spin_lock(arch_spinlock_t *lock) > ?{ > ? CLEAR_IO_SYNC; > @@ -169,6 +171,7 @@ extern void arch_spin_unlock_wait(arch_spinlock_t > *lock); > ? do { while (arch_spin_is_locked(lock)) cpu_relax(); } while > (0) > ?#endif > ? > +#endif /* !CONFIG_QUEUED_SPINLOCKS */ > ?/* > ? * Read-write spinlocks, allowing multiple readers >...

...lock_t *lock); > -extern void __rw_yield(arch_rwlock_t *lock); > -#else /* SPLPAR */ > -#define __spin_yield(x) barrier() > -#define __rw_yield(x) barrier() > -#define SHARED_PROCESSOR 0 > -#endif > - > ?static inline void arch_spin_lock(arch_spinlock_t *lock) > ?{ > ? CLEAR_IO_SYNC; > @@ -169,6 +171,7 @@ extern void arch_spin_unlock_wait(arch_spinlock_t > *lock); > ? do { while (arch_spin_is_locked(lock)) cpu_relax(); } while > (0) > ?#endif > ? > +#endif /* !CONFIG_QUEUED_SPINLOCKS */ > ?/* > ? * Read-write spinlocks, allowing multiple readers >...

Hi All, this is the fairlock patchset. You can apply them and build successfully. patches are based on linux-next qspinlock can avoid waiter starved issue. It has about the same speed in single-thread and it can be much faster in high contention situations especially when the spinlock is embedded within the data structure to be protected. v8 -> v9: mv qspinlocm config entry to

Hi All, this is the fairlock patchset. You can apply them and build successfully. patches are based on linux-next qspinlock can avoid waiter starved issue. It has about the same speed in single-thread and it can be much faster in high contention situations especially when the spinlock is embedded within the data structure to be protected. v8 -> v9: mv qspinlocm config entry to

...t;lppaca_ptr)) -extern void __spin_yield(arch_spinlock_t *lock); -extern void __rw_yield(arch_rwlock_t *lock); -#else /* SPLPAR */ -#define __spin_yield(x) barrier() -#define __rw_yield(x) barrier() -#define SHARED_PROCESSOR 0 -#endif - static inline void arch_spin_lock(arch_spinlock_t *lock) { CLEAR_IO_SYNC; @@ -169,6 +171,7 @@ extern void arch_spin_unlock_wait(arch_spinlock_t *lock); do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) #endif +#endif /* !CONFIG_QUEUED_SPINLOCKS */ /* * Read-write spinlocks, allowing multiple readers * but only one writer. diff --git a/arch/powerp...

...t;lppaca_ptr)) -extern void __spin_yield(arch_spinlock_t *lock); -extern void __rw_yield(arch_rwlock_t *lock); -#else /* SPLPAR */ -#define __spin_yield(x) barrier() -#define __rw_yield(x) barrier() -#define SHARED_PROCESSOR 0 -#endif - static inline void arch_spin_lock(arch_spinlock_t *lock) { CLEAR_IO_SYNC; @@ -169,6 +171,7 @@ extern void arch_spin_unlock_wait(arch_spinlock_t *lock); do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) #endif +#endif /* !CONFIG_QUEUED_SPINLOCKS */ /* * Read-write spinlocks, allowing multiple readers * but only one writer. diff --git a/arch/powerp...

...rch_rwlock_t *lock); > > -#else /* SPLPAR */ > > -#define __spin_yield(x) barrier() > > -#define __rw_yield(x) barrier() > > -#define SHARED_PROCESSOR 0 > > -#endif > > - > > ?static inline void arch_spin_lock(arch_spinlock_t *lock) > > ?{ > > ? CLEAR_IO_SYNC; > > @@ -169,6 +171,7 @@ extern void > > arch_spin_unlock_wait(arch_spinlock_t > > *lock); > > ? do { while (arch_spin_is_locked(lock)) cpu_relax(); } > > while > > (0) > > ?#endif > > ? > > +#endif /* !CONFIG_QUEUED_SPINLOCKS */ > > ?/* &...

From: root <root at ltcalpine2-lp13.aus.stglabs.ibm.com> change from v4: BUG FIX. thanks boqun reporting this issue. struct __qspinlock has different layout in bigendian mahcine. native_queued_spin_unlock() may write value to a wrong address. now fix it. change from v3: a big change in [PATCH v4 4/6] pv-qspinlock: powerpc support pv-qspinlock no other patch changed. and the patch

From: root <root at ltcalpine2-lp13.aus.stglabs.ibm.com> change from v4: BUG FIX. thanks boqun reporting this issue. struct __qspinlock has different layout in bigendian mahcine. native_queued_spin_unlock() may write value to a wrong address. now fix it. change from v3: a big change in [PATCH v4 4/6] pv-qspinlock: powerpc support pv-qspinlock no other patch changed. and the patch

...wpath(struct qspinlock *lock, u32 val); +extern void __pv_init_lock_hash(void); +extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); +extern void __pv_queued_spin_unlock(struct qspinlock *lock); + +static inline void pv_queued_spin_lock(struct qspinlock *lock, u32 val) +{ + CLEAR_IO_SYNC; + pv_lock_op.lock(lock, val); +} + +static inline void pv_queued_spin_unlock(struct qspinlock *lock) +{ + SYNC_IO; + pv_lock_op.unlock(lock); +} + +static inline void pv_wait(u8 *ptr, u8 val, int lockcpu) +{ + pv_lock_op.wait(ptr, val, lockcpu); +} + +static inline void pv_kick(int cpu) +{ + pv_lo...

change fome v1: separate into 6 pathes from one patch some minor code changes. benchmark test results are below. run 3 tests on pseries IBM,8408-E8E with 32cpus, 64GB memory perf bench futex hash perf bench futex lock-pi perf record -advRT || perf bench sched messaging -g 1000 || perf report summary: _____test________________spinlcok______________pv-qspinlcok_____ |futex hash | 556370 ops |

change fome v1: separate into 6 pathes from one patch some minor code changes. benchmark test results are below. run 3 tests on pseries IBM,8408-E8E with 32cpus, 64GB memory perf bench futex hash perf bench futex lock-pi perf record -advRT || perf bench sched messaging -g 1000 || perf report summary: _____test________________spinlcok______________pv-qspinlcok_____ |futex hash | 556370 ops |

change from v2: __spin_yeild_cpu() will yield slices to lpar if target cpu is running. remove unnecessary rmb() in __spin_yield/wake_cpu. __pv_wait() will check the *ptr == val. some commit message change change fome v1: separate into 6 pathes from one patch some minor code changes. I do several tests on pseries IBM,8408-E8E with 32cpus, 64GB memory. benchmark test results are below. 2

change from v2: __spin_yeild_cpu() will yield slices to lpar if target cpu is running. remove unnecessary rmb() in __spin_yield/wake_cpu. __pv_wait() will check the *ptr == val. some commit message change change fome v1: separate into 6 pathes from one patch some minor code changes. I do several tests on pseries IBM,8408-E8E with 32cpus, 64GB memory. benchmark test results are below. 2

...t;lppaca_ptr)) -extern void __spin_yield(arch_spinlock_t *lock); -extern void __rw_yield(arch_rwlock_t *lock); -#else /* SPLPAR */ -#define __spin_yield(x) barrier() -#define __rw_yield(x) barrier() -#define SHARED_PROCESSOR 0 -#endif - static inline void arch_spin_lock(arch_spinlock_t *lock) { CLEAR_IO_SYNC; @@ -169,6 +175,7 @@ extern void arch_spin_unlock_wait(arch_spinlock_t *lock); do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) #endif +#endif /* !CONFIG_QUEUED_SPINLOCKS */ /* * Read-write spinlocks, allowing multiple readers * but only one writer. diff --git a/arch/powerp...