search for: h_prod

...rpc/include/asm/paravirt.h > @@ -29,6 +29,16 @@ static inline void yield_to_preempted(int cpu, u32 yield_count) > { > plpar_hcall_norets(H_CONFER, get_hard_smp_processor_id(cpu), yield_count); > } > + > +static inline void prod_cpu(int cpu) > +{ > + plpar_hcall_norets(H_PROD, get_hard_smp_processor_id(cpu)); > +} > + > +static inline void yield_to_any(void) > +{ > + plpar_hcall_norets(H_CONFER, -1, 0); > +} > #else > static inline bool is_shared_processor(void) > { > @@ -45,6 +55,19 @@ static inline void yield_to_preempted(int cpu, u...

...eld_count = be32_to_cpu(lppaca_of(holder_cpu).yield_count); > + * if ((yield_count & 1) == 0) > + * return; > + * > + * a PROD hcall marks the target_cpu proded, which cause the next cede > + * or confer called on the target_cpu invalid. > + */ > + plpar_hcall_norets(H_PROD, > + get_hard_smp_processor_id(holder_cpu)); > +} > +EXPORT_SYMBOL_GPL(__spin_wake_cpu); > + > #ifndef CONFIG_QUEUED_SPINLOCKS > void __spin_yield(arch_spinlock_t *lock) > { > -- > 2.4.11 > -------------- next part -------------- A non-text attachment was scrubbe...

...eld_count = be32_to_cpu(lppaca_of(holder_cpu).yield_count); > + * if ((yield_count & 1) == 0) > + * return; > + * > + * a PROD hcall marks the target_cpu proded, which cause the next cede > + * or confer called on the target_cpu invalid. > + */ > + plpar_hcall_norets(H_PROD, > + get_hard_smp_processor_id(holder_cpu)); > +} > +EXPORT_SYMBOL_GPL(__spin_wake_cpu); > + > #ifndef CONFIG_QUEUED_SPINLOCKS > void __spin_yield(arch_spinlock_t *lock) > { > -- > 2.4.11 > -------------- next part -------------- A non-text attachment was scrubbe...

...+void __spin_wake_cpu(int cpu) +{ + unsigned int holder_cpu = cpu, yield_count; + + BUG_ON(holder_cpu >= nr_cpu_ids); + yield_count = be32_to_cpu(lppaca_of(holder_cpu).yield_count); + if ((yield_count & 1) == 0) + return; /* virtual cpu is currently running */ + rmb(); + plpar_hcall_norets(H_PROD, + get_hard_smp_processor_id(holder_cpu)); +} +EXPORT_SYMBOL_GPL(__spin_wake_cpu); + #ifndef CONFIG_QUEUED_SPINLOCKS void __spin_yield(arch_spinlock_t *lock) { -- 1.9.1

...OW. do NOT code like below. + * yield_count = be32_to_cpu(lppaca_of(holder_cpu).yield_count); + * if ((yield_count & 1) == 0) + * return; + * + * a PROD hcall marks the target_cpu proded, which cause the next cede + * or confer called on the target_cpu invalid. + */ + plpar_hcall_norets(H_PROD, + get_hard_smp_processor_id(holder_cpu)); +} +EXPORT_SYMBOL_GPL(__spin_wake_cpu); + #ifndef CONFIG_QUEUED_SPINLOCKS void __spin_yield(arch_spinlock_t *lock) { -- 2.4.11

...erpc/include/asm/paravirt.h +++ b/arch/powerpc/include/asm/paravirt.h @@ -29,6 +29,16 @@ static inline void yield_to_preempted(int cpu, u32 yield_count) { plpar_hcall_norets(H_CONFER, get_hard_smp_processor_id(cpu), yield_count); } + +static inline void prod_cpu(int cpu) +{ + plpar_hcall_norets(H_PROD, get_hard_smp_processor_id(cpu)); +} + +static inline void yield_to_any(void) +{ + plpar_hcall_norets(H_CONFER, -1, 0); +} #else static inline bool is_shared_processor(void) { @@ -45,6 +55,19 @@ static inline void yield_to_preempted(int cpu, u32 yield_count) { ___bad_yield_to_preempted(); /*...

...erpc/include/asm/paravirt.h +++ b/arch/powerpc/include/asm/paravirt.h @@ -29,6 +29,16 @@ static inline void yield_to_preempted(int cpu, u32 yield_count) { plpar_hcall_norets(H_CONFER, get_hard_smp_processor_id(cpu), yield_count); } + +static inline void prod_cpu(int cpu) +{ + plpar_hcall_norets(H_PROD, get_hard_smp_processor_id(cpu)); +} + +static inline void yield_to_any(void) +{ + plpar_hcall_norets(H_CONFER, -1, 0); +} #else static inline bool is_shared_processor(void) { @@ -45,6 +55,19 @@ static inline void yield_to_preempted(int cpu, u32 yield_count) { ___bad_yield_to_preempted(); /*...

...erpc/include/asm/paravirt.h +++ b/arch/powerpc/include/asm/paravirt.h @@ -29,6 +29,16 @@ static inline void yield_to_preempted(int cpu, u32 yield_count) { plpar_hcall_norets(H_CONFER, get_hard_smp_processor_id(cpu), yield_count); } + +static inline void prod_cpu(int cpu) +{ + plpar_hcall_norets(H_PROD, get_hard_smp_processor_id(cpu)); +} + +static inline void yield_to_any(void) +{ + plpar_hcall_norets(H_CONFER, -1, 0); +} #else static inline bool is_shared_processor(void) { @@ -45,6 +55,19 @@ static inline void yield_to_preempted(int cpu, u32 yield_count) { ___bad_yield_to_preempted(); /*...

...ual cpu is currently running */ + rmb(); + plpar_hcall_norets(H_CONFER, + get_hard_smp_processor_id(holder_cpu), yield_count); +} +EXPORT_SYMBOL_GPL(__spin_yield_cpu); + +void __spin_wake_cpu(int cpu) +{ + unsigned int holder_cpu = cpu; + + BUG_ON(holder_cpu >= nr_cpu_ids); + plpar_hcall_norets(H_PROD, + get_hard_smp_processor_id(holder_cpu)); +} +EXPORT_SYMBOL_GPL(__spin_wake_cpu); + +#ifndef CONFIG_QUEUED_SPINLOCKS void __spin_yield(arch_spinlock_t *lock) { unsigned int lock_value, holder_cpu, yield_count; @@ -42,6 +71,7 @@ void __spin_yield(arch_spinlock_t *lock) get_hard_smp_processo...

...ual cpu is currently running */ + rmb(); + plpar_hcall_norets(H_CONFER, + get_hard_smp_processor_id(holder_cpu), yield_count); +} +EXPORT_SYMBOL_GPL(__spin_yield_cpu); + +void __spin_wake_cpu(int cpu) +{ + unsigned int holder_cpu = cpu; + + BUG_ON(holder_cpu >= nr_cpu_ids); + plpar_hcall_norets(H_PROD, + get_hard_smp_processor_id(holder_cpu)); +} +EXPORT_SYMBOL_GPL(__spin_wake_cpu); + +#ifndef CONFIG_QUEUED_SPINLOCKS void __spin_yield(arch_spinlock_t *lock) { unsigned int lock_value, holder_cpu, yield_count; @@ -42,6 +71,7 @@ void __spin_yield(arch_spinlock_t *lock) get_hard_smp_processo...

...ual cpu is currently running */ + rmb(); + plpar_hcall_norets(H_CONFER, + get_hard_smp_processor_id(holder_cpu), yield_count); +} +EXPORT_SYMBOL_GPL(__spin_yield_cpu); + +void __spin_wake_cpu(int cpu) +{ + unsigned int holder_cpu = cpu; + + BUG_ON(holder_cpu >= nr_cpu_ids); + plpar_hcall_norets(H_PROD, + get_hard_smp_processor_id(holder_cpu)); +} +EXPORT_SYMBOL_GPL(__spin_wake_cpu); + +#ifndef CONFIG_QUEUED_SPINLOCKS void __spin_yield(arch_spinlock_t *lock) { unsigned int lock_value, holder_cpu, yield_count; @@ -42,6 +71,7 @@ void __spin_yield(arch_spinlock_t *lock) get_hard_smp_processo...

...ual cpu is currently running */ + rmb(); + plpar_hcall_norets(H_CONFER, + get_hard_smp_processor_id(holder_cpu), yield_count); +} +EXPORT_SYMBOL_GPL(__spin_yield_cpu); + +void __spin_wake_cpu(int cpu) +{ + unsigned int holder_cpu = cpu; + + BUG_ON(holder_cpu >= nr_cpu_ids); + plpar_hcall_norets(H_PROD, + get_hard_smp_processor_id(holder_cpu)); +} +EXPORT_SYMBOL_GPL(__spin_wake_cpu); + +#ifndef CONFIG_QUEUED_SPINLOCKS void __spin_yield(arch_spinlock_t *lock) { unsigned int lock_value, holder_cpu, yield_count; @@ -42,6 +71,7 @@ void __spin_yield(arch_spinlock_t *lock) get_hard_smp_processo...

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

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

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 |

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

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