Displaying 20 results from an estimated 43 matches for "lppaca_of".
2020 Jul 06
0
[PATCH v3 2/6] powerpc/pseries: move some PAPR paravirt functions to their own file
...G_PPC_SPLPAR
+DECLARE_STATIC_KEY_FALSE(shared_processor);
+
+static inline bool is_shared_processor(void)
+{
+ return static_branch_unlikely(&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...
2016 Dec 06
1
[PATCH v8 3/6] powerpc: lib/locks.c: Add cpu yield/wake helper function
...pu, yield_count;
As I said at:
https://marc.info/?l=linux-kernel&m=147455748619343&w=2
@holder_cpu is not necessary and doesn't help anything.
> +
> + 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;
> +
> +...
2016 Dec 06
1
[PATCH v8 3/6] powerpc: lib/locks.c: Add cpu yield/wake helper function
...pu, yield_count;
As I said at:
https://marc.info/?l=linux-kernel&m=147455748619343&w=2
@holder_cpu is not necessary and doesn't help anything.
> +
> + 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;
> +
> +...
2016 May 17
0
[PATCH v2 3/6] powerpc: lib/locks.c: cpu yield/wake helper function
...ks.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_count);
+}
+EXPORT_SYMBOL_GPL(__spin_yield_cpu);
+
+void __spin_wake_cpu(int cpu)
+{
+ unsigned int...
2020 Jul 02
0
[PATCH 2/8] powerpc/pseries: use smp_rmb() in H_CONFER spin yield
...hanged, 2 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c
index 6440d5943c00..47a530de733e 100644
--- a/arch/powerpc/lib/locks.c
+++ b/arch/powerpc/lib/locks.c
@@ -30,7 +30,7 @@ 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)...
2016 Dec 05
0
[PATCH v8 3/6] powerpc: lib/locks.c: Add cpu yield/wake helper function
...heck confer. If confer is NULL, we will return
+ * otherwise we confer our slices to lpar.
+ */
+void __spin_yield_cpu(int cpu, int confer)
+{
+ unsigned int holder_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...
2016 Jul 06
1
[PATCH v2 2/4] powerpc/spinlock: support vcpu preempted check
...e we need return false directly if we are running as
> + ?* powerNV. However the yield_count is always zero on powerNV, So
> + ?* skip such machine type check
Or you could use the ppc_md interface callbacks if required, but your
solution works as well
> + ?*/
> + return !!(be32_to_cpu(lppaca_of(cpu).yield_count) & 1);
> +}
> +#endif
> +
> ?static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
> ?{
> ? return lock.slock == 0;
Balbir Singh.
2016 Jul 06
1
[PATCH v2 2/4] powerpc/spinlock: support vcpu preempted check
...e we need return false directly if we are running as
> + ?* powerNV. However the yield_count is always zero on powerNV, So
> + ?* skip such machine type check
Or you could use the ppc_md interface callbacks if required, but your
solution works as well
> + ?*/
> + return !!(be32_to_cpu(lppaca_of(cpu).yield_count) & 1);
> +}
> +#endif
> +
> ?static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
> ?{
> ? return lock.slock == 0;
Balbir Singh.
2016 Jun 28
0
[PATCH v2 2/4] powerpc/spinlock: support vcpu preempted check
...l vcpu_is_preempted(int cpu)
+{
+ /*
+ * pSeries and powerNV can be built into same kernel image. In
+ * principle we need return false directly if we are running as
+ * powerNV. However the yield_count is always zero on powerNV, So
+ * skip such machine type check
+ */
+ return !!(be32_to_cpu(lppaca_of(cpu).yield_count) & 1);
+}
+#endif
+
static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
{
return lock.slock == 0;
--
2.4.11
2016 Jul 21
0
[PATCH v3 2/4] powerpc/spinlock: support vcpu preempted check
...l vcpu_is_preempted(int cpu)
+{
+ /*
+ * pSeries and powerNV can be built into same kernel image. In
+ * principle we need return false directly if we are running as
+ * powerNV. However the yield_count is always zero on powerNV, So
+ * skip such machine type check
+ */
+ return !!(be32_to_cpu(lppaca_of(cpu).yield_count) & 1);
+}
+#endif
+
static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
{
return lock.slock == 0;
--
2.4.11
2020 Jul 02
12
[PATCH 0/8] powerpc: queued spinlocks and rwlocks
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
2020 Jul 03
7
[PATCH v2 0/6] powerpc: queued spinlocks and rwlocks
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
2020 Jul 24
8
[PATCH v4 0/6] powerpc: queued spinlocks and rwlocks
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
2016 May 17
6
[PATCH v3 0/6] powerpc use pv-qpsinlock instead of spinlock
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 |
2016 May 17
6
[PATCH v3 0/6] powerpc use pv-qpsinlock instead of spinlock
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 |
2016 Dec 05
9
[PATCH v8 0/6] Implement qspinlock/pv-qspinlock on ppc
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
2016 Dec 05
9
[PATCH v8 0/6] Implement qspinlock/pv-qspinlock on ppc
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
2016 May 25
10
[PATCH v3 0/6] powerpc use pv-qpsinlock as the default spinlock implemention
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
2016 May 25
10
[PATCH v3 0/6] powerpc use pv-qpsinlock as the default spinlock implemention
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
2020 Jul 06
13
[PATCH v3 0/6] powerpc: queued spinlocks and rwlocks
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