search for: arch_rwlock_t

...processor_id() in the lock when it is + * held. Conveniently, we have a word in the paca that holds this + * value. + */ + +#if defined(CONFIG_PPC_SPLPAR) +/* We only yield to the hypervisor if we are in shared processor mode */ +void splpar_spin_yield(arch_spinlock_t *lock); +void splpar_rw_yield(arch_rwlock_t *lock); +#else /* SPLPAR */ +static inline void splpar_spin_yield(arch_spinlock_t *lock) {}; +static inline void splpar_rw_yield(arch_rwlock_t *lock) {}; +#endif + +static inline void spin_yield(arch_spinlock_t *lock) +{ + if (is_shared_processor()) + splpar_spin_yield(lock); + else + barrier();...

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

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

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

...if > ? > +#if defined(CONFIG_PPC_SPLPAR) > +/* We only yield to the hypervisor if we are in shared processor > mode */ > +#define SHARED_PROCESSOR (lppaca_shared_proc(local_paca- > >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 > + > +#ifdef CONFIG_QUEUED_SPINLOCKS > +#include <asm/qspinlock.h> > +#else > ?static __always_inline int arch_spin_valu...

...if > ? > +#if defined(CONFIG_PPC_SPLPAR) > +/* We only yield to the hypervisor if we are in shared processor > mode */ > +#define SHARED_PROCESSOR (lppaca_shared_proc(local_paca- > >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 > + > +#ifdef CONFIG_QUEUED_SPINLOCKS > +#include <asm/qspinlock.h> > +#else > ?static __always_inline int arch_spin_valu...

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

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

...rely on the > * sense running status. > */ > - if (!MACHINE_IS_LPAR || cpu_is_preempted(~owner)) { > + if (!MACHINE_IS_LPAR || arch_vcpu_is_preempted(~owner)) { > smp_yield_cpu(~owner); > first_diag = 0; > } > @@ -165,7 +156,7 @@ void _raw_read_lock_wait(arch_rwlock_t *rw) > owner = 0; > while (1) { > if (count-- <= 0) { > - if (owner && cpu_is_preempted(~owner)) > + if (owner && arch_vcpu_is_preempted(~owner)) > smp_yield_cpu(~owner); > count = spin_retry; > } > @@ -211,7 +202,7 @@ void _raw_w...

...rely on the > * sense running status. > */ > - if (!MACHINE_IS_LPAR || cpu_is_preempted(~owner)) { > + if (!MACHINE_IS_LPAR || arch_vcpu_is_preempted(~owner)) { > smp_yield_cpu(~owner); > first_diag = 0; > } > @@ -165,7 +156,7 @@ void _raw_read_lock_wait(arch_rwlock_t *rw) > owner = 0; > while (1) { > if (count-- <= 0) { > - if (owner && cpu_is_preempted(~owner)) > + if (owner && arch_vcpu_is_preempted(~owner)) > smp_yield_cpu(~owner); > count = spin_retry; > } > @@ -211,7 +202,7 @@ void _raw_w...

...> #endif > > +#if defined(CONFIG_PPC_SPLPAR) > +/* We only yield to the hypervisor if we are in shared processor mode */ > +#define SHARED_PROCESSOR (lppaca_shared_proc(local_paca->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 > + > +#ifdef CONFIG_QUEUED_SPINLOCKS > +#include <asm/qspinlock.h> > +#else > + > +#define arch_spin_re...

...> #endif > > +#if defined(CONFIG_PPC_SPLPAR) > +/* We only yield to the hypervisor if we are in shared processor mode */ > +#define SHARED_PROCESSOR (lppaca_shared_proc(local_paca->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 > + > +#ifdef CONFIG_QUEUED_SPINLOCKS > +#include <asm/qspinlock.h> > +#else > + > +#define arch_spin_re...

...bool vcpu_is_preempted(int cpu) } #endif +#if defined(CONFIG_PPC_SPLPAR) +/* We only yield to the hypervisor if we are in shared processor mode */ +#define SHARED_PROCESSOR (lppaca_shared_proc(local_paca->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 + +#ifdef CONFIG_QUEUED_SPINLOCKS +#include <asm/qspinlock.h> +#else + +#define arch_spin_relax(lock) __spin_yield(lock) + static __always_inline...

...@@ -52,6 +52,20 @@ #define SYNC_IO #endif +#if defined(CONFIG_PPC_SPLPAR) +/* We only yield to the hypervisor if we are in shared processor mode */ +#define SHARED_PROCESSOR (lppaca_shared_proc(local_paca->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 + +#ifdef CONFIG_QUEUED_SPINLOCKS +#include <asm/qspinlock.h> +#else static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) { return lock....

...@@ -52,6 +52,20 @@ #define SYNC_IO #endif +#if defined(CONFIG_PPC_SPLPAR) +/* We only yield to the hypervisor if we are in shared processor mode */ +#define SHARED_PROCESSOR (lppaca_shared_proc(local_paca->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 + +#ifdef CONFIG_QUEUED_SPINLOCKS +#include <asm/qspinlock.h> +#else static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) { return lock....

...> > +/* We only yield to the hypervisor if we are in shared processor > > mode */ > > +#define SHARED_PROCESSOR (lppaca_shared_proc(local_paca- > > > > > > 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 > > + > > +#ifdef CONFIG_QUEUED_SPINLOCKS > > +#include <asm/qspinlock.h> > > +#else &g...

...yield the CPU unconditionally. For LPAR rely on the * sense running status. */ - if (!MACHINE_IS_LPAR || cpu_is_preempted(~owner)) { + if (!MACHINE_IS_LPAR || arch_vcpu_is_preempted(~owner)) { smp_yield_cpu(~owner); first_diag = 0; } @@ -165,7 +156,7 @@ void _raw_read_lock_wait(arch_rwlock_t *rw) owner = 0; while (1) { if (count-- <= 0) { - if (owner && cpu_is_preempted(~owner)) + if (owner && arch_vcpu_is_preempted(~owner)) smp_yield_cpu(~owner); count = spin_retry; } @@ -211,7 +202,7 @@ void _raw_write_lock_wait(arch_rwlock_t *rw, unsigned in...

...yield the CPU unconditionally. For LPAR rely on the * sense running status. */ - if (!MACHINE_IS_LPAR || cpu_is_preempted(~owner)) { + if (!MACHINE_IS_LPAR || arch_vcpu_is_preempted(~owner)) { smp_yield_cpu(~owner); first_diag = 0; } @@ -165,7 +156,7 @@ void _raw_read_lock_wait(arch_rwlock_t *rw) owner = 0; while (1) { if (count-- <= 0) { - if (owner && cpu_is_preempted(~owner)) + if (owner && arch_vcpu_is_preempted(~owner)) smp_yield_cpu(~owner); count = spin_retry; } @@ -211,7 +202,7 @@ void _raw_write_lock_wait(arch_rwlock_t *rw, unsigned in...

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