search for: plpar_hcall_norets

...de/asm/paravirt.h b/arch/powerpc/include/asm/paravirt.h > index 7a8546660a63..f2d51f929cf5 100644 > --- a/arch/powerpc/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)...

...; + goto yield_to_lpar; > + > + BUG_ON(holder_cpu >= nr_cpu_ids); > + yield_count = be32_to_cpu(lppaca_of(holder_cpu).yield_count); > + > + /* if cpu is running, confer slices to lpar conditionally*/ > + if ((yield_count & 1) == 0) > + goto yield_to_lpar; > + > + plpar_hcall_norets(H_CONFER, > + get_hard_smp_processor_id(holder_cpu), yield_count); > + return; > + > +yield_to_lpar: > + if (confer) > + plpar_hcall_norets(H_CONFER, -1, 0); > +} > +EXPORT_SYMBOL_GPL(__spin_yield_cpu); > + > +void __spin_wake_cpu(int cpu) > +{ > + unsigned int...

...; + goto yield_to_lpar; > + > + BUG_ON(holder_cpu >= nr_cpu_ids); > + yield_count = be32_to_cpu(lppaca_of(holder_cpu).yield_count); > + > + /* if cpu is running, confer slices to lpar conditionally*/ > + if ((yield_count & 1) == 0) > + goto yield_to_lpar; > + > + plpar_hcall_norets(H_CONFER, > + get_hard_smp_processor_id(holder_cpu), yield_count); > + return; > + > +yield_to_lpar: > + if (confer) > + plpar_hcall_norets(H_CONFER, -1, 0); > +} > +EXPORT_SYMBOL_GPL(__spin_yield_cpu); > + > +void __spin_wake_cpu(int cpu) > +{ > + unsigned int...

...h/powerpc/lib/locks.c index a9ebd71..4109679a 100644 --- a/arch/powerpc/lib/locks.c +++ b/arch/powerpc/lib/locks.c @@ -23,6 +23,38 @@ #include <asm/hvcall.h> #include <asm/smp.h> +void __spin_yield_cpu(int cpu) +{ + unsigned int holder_cpu = cpu, yield_count; + + if (cpu == -1) { + plpar_hcall_norets(H_CEDE); + return; + } + 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_CONFER, + get_hard_smp_processor_id(holder_cpu), yield...

...der_cpu = cpu, yield_count; + + if (cpu == -1) + goto yield_to_lpar; + + BUG_ON(holder_cpu >= nr_cpu_ids); + yield_count = be32_to_cpu(lppaca_of(holder_cpu).yield_count); + + /* if cpu is running, confer slices to lpar conditionally*/ + if ((yield_count & 1) == 0) + goto yield_to_lpar; + + plpar_hcall_norets(H_CONFER, + get_hard_smp_processor_id(holder_cpu), yield_count); + return; + +yield_to_lpar: + if (confer) + plpar_hcall_norets(H_CONFER, -1, 0); +} +EXPORT_SYMBOL_GPL(__spin_yield_cpu); + +void __spin_wake_cpu(int cpu) +{ + unsigned int holder_cpu = cpu; + + BUG_ON(holder_cpu >= nr_cpu_ids);...

...y(&shared_processor); +} + +/* If bit 0 is set, the cpu has been preempted */ +static inline u32 yield_count_of(int cpu) +{ + __be32 yield_count = READ_ONCE(lppaca_of(cpu).yield_count); + return be32_to_cpu(yield_count); +} + +static inline void yield_to_preempted(int cpu, u32 yield_count) +{ + plpar_hcall_norets(H_CONFER, get_hard_smp_processor_id(cpu), yield_count); +} +#else +static inline bool is_shared_processor(void) +{ + return false; +} + +static inline u32 yield_count_of(int cpu) +{ + return 0; +} + +extern void ___bad_yield_to_preempted(void); +static inline void yield_to_preempted(int cpu, u32 yi...

...diff --git a/arch/powerpc/include/asm/paravirt.h b/arch/powerpc/include/asm/paravirt.h index 7a8546660a63..5fae9dfa6fe9 100644 --- a/arch/powerpc/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...

...diff --git a/arch/powerpc/include/asm/paravirt.h b/arch/powerpc/include/asm/paravirt.h index 7a8546660a63..f2d51f929cf5 100644 --- a/arch/powerpc/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...

...diff --git a/arch/powerpc/include/asm/paravirt.h b/arch/powerpc/include/asm/paravirt.h index 7a8546660a63..f2d51f929cf5 100644 --- a/arch/powerpc/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...

...7 @@ void splpar_spin_yield(arch_spinlock_t *lock) yield_count = be32_to_cpu(lppaca_of(holder_cpu).yield_count); if ((yield_count & 1) == 0) return; /* virtual cpu is currently running */ - rmb(); + smp_rmb(); if (lock->slock != lock_value) return; /* something has changed */ plpar_hcall_norets(H_CONFER, @@ -56,7 +56,7 @@ void splpar_rw_yield(arch_rwlock_t *rw) yield_count = be32_to_cpu(lppaca_of(holder_cpu).yield_count); if ((yield_count & 1) == 0) return; /* virtual cpu is currently running */ - rmb(); + smp_rmb(); if (rw->lock != lock_value) return; /* something ha...

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

...ch/powerpc/lib/locks.c index f7deebd..6e9d3bb 100644 --- a/arch/powerpc/lib/locks.c +++ b/arch/powerpc/lib/locks.c @@ -23,6 +23,35 @@ #include <asm/hvcall.h> #include <asm/smp.h> +void __spin_yield_cpu(int cpu) +{ + unsigned int holder_cpu = cpu, yield_count; + + if (cpu == -1) { + plpar_hcall_norets(H_CEDE); + return; + } + 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_CONFER, + get_hard_smp_processor_id(holder_cpu), yield...

...ch/powerpc/lib/locks.c index f7deebd..6e9d3bb 100644 --- a/arch/powerpc/lib/locks.c +++ b/arch/powerpc/lib/locks.c @@ -23,6 +23,35 @@ #include <asm/hvcall.h> #include <asm/smp.h> +void __spin_yield_cpu(int cpu) +{ + unsigned int holder_cpu = cpu, yield_count; + + if (cpu == -1) { + plpar_hcall_norets(H_CEDE); + return; + } + 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_CONFER, + get_hard_smp_processor_id(holder_cpu), yield...

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

...ch/powerpc/lib/locks.c index f7deebd..6e9d3bb 100644 --- a/arch/powerpc/lib/locks.c +++ b/arch/powerpc/lib/locks.c @@ -23,6 +23,35 @@ #include <asm/hvcall.h> #include <asm/smp.h> +void __spin_yield_cpu(int cpu) +{ + unsigned int holder_cpu = cpu, yield_count; + + if (cpu == -1) { + plpar_hcall_norets(H_CEDE); + return; + } + 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_CONFER, + get_hard_smp_processor_id(holder_cpu), yield...

...ch/powerpc/lib/locks.c index f7deebd..6e9d3bb 100644 --- a/arch/powerpc/lib/locks.c +++ b/arch/powerpc/lib/locks.c @@ -23,6 +23,35 @@ #include <asm/hvcall.h> #include <asm/smp.h> +void __spin_yield_cpu(int cpu) +{ + unsigned int holder_cpu = cpu, yield_count; + + if (cpu == -1) { + plpar_hcall_norets(H_CEDE); + return; + } + 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_CONFER, + get_hard_smp_processor_id(holder_cpu), yield...

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

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. sorry for not even doing a test on bigendian machine before!!! change from v3: a big change in [PATCH v4 4/6] pv-qspinlock: powerpc support pv-qspinlock no other patch changed. and the patch

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. sorry for not even doing a test on bigendian machine before!!! change from v3: a big change in [PATCH v4 4/6] pv-qspinlock: powerpc support pv-qspinlock no other patch changed. and the patch