diff options
| author | Cyrill Gorcunov <gorcunov@openvz.org> | 2010-06-03 01:23:04 +0400 |
|---|---|---|
| committer | Ingo Molnar <mingo@elte.hu> | 2010-06-09 11:12:35 +0200 |
| commit | 68aa00ac0a82e9a876c799bf6be7622b8f1c8517 (patch) | |
| tree | af59ed93f50dd539389956e5fe97f3ac0cd85cbe | |
| parent | 8d2cacbbb8deadfae78aa16e4e1ee619bdd7019e (diff) | |
perf, x86: Make a second write to performance counter if needed
On Netburst PMU we need a second write to a performance counter
due to cpu erratum.
A simple flag test instead of alternative instructions was choosen
because wrmsrl is already a macro and if virtualization is turned
on will need an additional wrapper call which is more expencise.
nb: we should propably switch to jump-labels as only this facility
reach the mainline.
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <20100602212304.GC5264@lenovo>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
| -rw-r--r-- | arch/x86/kernel/cpu/perf_event.c | 12 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/perf_event_p4.c | 9 |
2 files changed, 20 insertions, 1 deletions
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index af04c6fa59c..79e199843db 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -220,6 +220,7 @@ struct x86_pmu { struct perf_event *event); struct event_constraint *event_constraints; void (*quirks)(void); + int perfctr_second_write; int (*cpu_prepare)(int cpu); void (*cpu_starting)(int cpu); @@ -925,8 +926,17 @@ x86_perf_event_set_period(struct perf_event *event) */ atomic64_set(&hwc->prev_count, (u64)-left); - wrmsrl(hwc->event_base + idx, + wrmsrl(hwc->event_base + idx, (u64)(-left) & x86_pmu.cntval_mask); + + /* + * Due to erratum on certan cpu we need + * a second write to be sure the register + * is updated properly + */ + if (x86_pmu.perfctr_second_write) { + wrmsrl(hwc->event_base + idx, (u64)(-left) & x86_pmu.cntval_mask); + } perf_event_update_userpage(event); diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index ae85d69644d..9286e736a70 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -829,6 +829,15 @@ static __initconst const struct x86_pmu p4_pmu = { .max_period = (1ULL << 39) - 1, .hw_config = p4_hw_config, .schedule_events = p4_pmu_schedule_events, + /* + * This handles erratum N15 in intel doc 249199-029, + * the counter may not be updated correctly on write + * so we need a second write operation to do the trick + * (the official workaround didn't work) + * + * the former idea is taken from OProfile code + */ + .perfctr_second_write = 1, }; static __init int p4_pmu_init(void) |