search for: arch_spin_lock_flag

...locked(struct qspinlock *lock) > +{ > + smp_mb(); > + return atomic_read(&lock->val); > +} > + > +#include <asm-generic/qspinlock.h> > + > +/* we need override it as ppc has io_sync stuff */ > +#undef arch_spin_trylock > +#undef arch_spin_lock > +#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...

...locked(struct qspinlock *lock) > +{ > + smp_mb(); > + return atomic_read(&lock->val); > +} > + > +#include <asm-generic/qspinlock.h> > + > +/* we need override it as ppc has io_sync stuff */ > +#undef arch_spin_trylock > +#undef arch_spin_lock > +#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...

...byte(lock), 0); +} + +static inline int queued_spin_is_locked(struct qspinlock *lock) +{ + smp_mb(); + return atomic_read(&lock->val); +} + +#include <asm-generic/qspinlock.h> + +/* we need override it as ppc has io_sync stuff */ +#undef arch_spin_trylock +#undef arch_spin_lock +#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 queu...

...inline void arch_spin_lock(arch_spinlock_t *lock) +{ + while (1) { + if (likely(__arch_spin_trylock(lock) == 0)) + break; + do { + HMT_low(); + if (is_shared_processor()) + splpar_spin_yield(lock); + } while (unlikely(lock->slock != 0)); + HMT_medium(); + } +} + +static inline +void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) +{ + unsigned long flags_dis; + + while (1) { + if (likely(__arch_spin_trylock(lock) == 0)) + break; + local_save_flags(flags_dis); + local_irq_restore(flags); + do { + HMT_low(); + if (is_shared_processor()) + splpar_spin_yield(lock); + }...

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

...k, 0, _QSPINLOCK_LOCKED) == 0)) + return 1; + return 0; +} + +/* + * Redefine arch_spin_lock and arch_spin_trylock as inline functions that will + * jump to the unfair versions if the static key paravirt_unfairlocks_enabled + * is true. + */ +#undef arch_spin_lock +#undef arch_spin_trylock +#undef arch_spin_lock_flags + +extern struct static_key paravirt_unfairlocks_enabled; + +/** + * arch_spin_lock - acquire a queue spinlock + * @lock: Pointer to queue spinlock structure + */ +static inline void arch_spin_lock(struct qspinlock *lock) +{ + if (static_key_false(&paravirt_unfairlocks_enabled)) { + queue_spi...

...k, 0, _QSPINLOCK_LOCKED) == 0)) + return 1; + return 0; +} + +/* + * Redefine arch_spin_lock and arch_spin_trylock as inline functions that will + * jump to the unfair versions if the static key paravirt_unfairlocks_enabled + * is true. + */ +#undef arch_spin_lock +#undef arch_spin_trylock +#undef arch_spin_lock_flags + +extern struct static_key paravirt_unfairlocks_enabled; + +/** + * arch_spin_lock - acquire a queue spinlock + * @lock: Pointer to queue spinlock structure + */ +static inline void arch_spin_lock(struct qspinlock *lock) +{ + if (static_key_false(&paravirt_unfairlocks_enabled)) + queue_spin_...

v2 is updated to account for feedback from Will, Peter, and Waiman (thank you), and trims off a couple of RFC and unrelated patches. Thanks, Nick Nicholas Piggin (6): powerpc/powernv: must include hvcall.h to get PAPR defines powerpc/pseries: move some PAPR paravirt functions to their own file powerpc: move spinlock implementation to simple_spinlock powerpc/64s: implement queued

...s lock stealing. + */ + queue_spin_lock_slowpath(lock, -1); +} + +/* + * Redefine arch_spin_lock and arch_spin_trylock as inline functions that will + * jump to the unfair versions if the static key virt_unfairlocks_enabled + * is true. + */ +#undef arch_spin_lock +#undef arch_spin_trylock +#undef arch_spin_lock_flags + +/** + * arch_spin_lock - acquire a queue spinlock + * @lock: Pointer to queue spinlock structure + */ +static inline void arch_spin_lock(struct qspinlock *lock) +{ + if (static_key_false(&virt_unfairlocks_enabled)) + queue_spin_lock_unfair(lock); + else + queue_spin_lock(lock); +} + +/**...

Updated with everybody's feedback (thanks all), and more performance results. What I've found is I might have been measuring the worst load point for the paravirt case, and by looking at a range of loads it's clear that queued spinlocks are overall better even on PV, doubly so when you look at the generally much improved worst case latencies. I have defaulted it to N even though

This series adds an option to use queued spinlocks for powerpc, and makes it the default for the Book3S-64 subarch. This effort starts with the generic code so it's very simple but still very performant. There are optimisations that can be made to slowpaths, but I think it's better to attack those incrementally if/when we find things, and try to add the improvements to generic code as

...ck stealing. + */ + queue_spin_lock_slowpath(lock, -1); +} + +/* + * Redefine arch_spin_lock and arch_spin_trylock as inline functions that will + * jump to the unfair versions if the static key paravirt_unfairlocks_enabled + * is true. + */ +#undef arch_spin_lock +#undef arch_spin_trylock +#undef arch_spin_lock_flags + +/** + * arch_spin_lock - acquire a queue spinlock + * @lock: Pointer to queue spinlock structure + */ +static inline void arch_spin_lock(struct qspinlock *lock) +{ + if (static_key_false(&paravirt_unfairlocks_enabled)) + queue_spin_lock_unfair(lock); + else + queue_spin_lock(lock); +} + +...

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

...urn 0; > +} > + > +/* > + * Redefine arch_spin_lock and arch_spin_trylock as inline functions that will > + * jump to the unfair versions if the static key paravirt_unfairlocks_enabled > + * is true. > + */ > +#undef arch_spin_lock > +#undef arch_spin_trylock > +#undef arch_spin_lock_flags > + > +extern struct static_key paravirt_unfairlocks_enabled; > + > +/** > + * arch_spin_lock - acquire a queue spinlock > + * @lock: Pointer to queue spinlock structure > + */ > +static inline void arch_spin_lock(struct qspinlock *lock) > +{ > + if (static_key_false(...

...urn 0; > +} > + > +/* > + * Redefine arch_spin_lock and arch_spin_trylock as inline functions that will > + * jump to the unfair versions if the static key paravirt_unfairlocks_enabled > + * is true. > + */ > +#undef arch_spin_lock > +#undef arch_spin_trylock > +#undef arch_spin_lock_flags > + > +extern struct static_key paravirt_unfairlocks_enabled; > + > +/** > + * arch_spin_lock - acquire a queue spinlock > + * @lock: Pointer to queue spinlock structure > + */ > +static inline void arch_spin_lock(struct qspinlock *lock) > +{ > + if (static_key_false(...

...+} Why is this needed? > +/* > + * Redefine arch_spin_lock and arch_spin_trylock as inline functions that will > + * jump to the unfair versions if the static key virt_unfairlocks_enabled > + * is true. > + */ > +#undef arch_spin_lock > +#undef arch_spin_trylock > +#undef arch_spin_lock_flags > + > +/** > + * arch_spin_lock - acquire a queue spinlock > + * @lock: Pointer to queue spinlock structure > + */ > +static inline void arch_spin_lock(struct qspinlock *lock) > +{ > + if (static_key_false(&virt_unfairlocks_enabled)) > + queue_spin_lock_unfair(lock)...

...+} Why is this needed? > +/* > + * Redefine arch_spin_lock and arch_spin_trylock as inline functions that will > + * jump to the unfair versions if the static key virt_unfairlocks_enabled > + * is true. > + */ > +#undef arch_spin_lock > +#undef arch_spin_trylock > +#undef arch_spin_lock_flags > + > +/** > + * arch_spin_lock - acquire a queue spinlock > + * @lock: Pointer to queue spinlock structure > + */ > +static inline void arch_spin_lock(struct qspinlock *lock) > +{ > + if (static_key_false(&virt_unfairlocks_enabled)) > + queue_spin_lock_unfair(lock)...

v3 is updated to use __pv_queued_spin_unlock, noticed by Waiman (thank you). Thanks, Nick Nicholas Piggin (6): powerpc/powernv: must include hvcall.h to get PAPR defines powerpc/pseries: move some PAPR paravirt functions to their own file powerpc: move spinlock implementation to simple_spinlock powerpc/64s: implement queued spinlocks and rwlocks powerpc/pseries: implement paravirt