| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Tue, 6 Dec 2011 01:43:32 -0800
From: tip-bot for Peter Zijlstra <a.p.zijlstra@...llo.nl>
To: linux-tip-commits@...r.kernel.org
Cc: linux-kernel@...r.kernel.org, gleb@...hat.com, hpa@...or.com,
mingo@...hat.com, a.p.zijlstra@...llo.nl, tglx@...utronix.de,
mingo@...e.hu
Subject: [tip:perf/core] perf: Avoid a useless pmu_disable() in the perf-tick
Commit-ID: 0f5a2601284237e2ba089389fd75d67f77626cef
Gitweb: http://git.kernel.org/tip/0f5a2601284237e2ba089389fd75d67f77626cef
Author: Peter Zijlstra <a.p.zijlstra@...llo.nl>
AuthorDate: Wed, 16 Nov 2011 14:38:16 +0100
Committer: Ingo Molnar <mingo@...e.hu>
CommitDate: Tue, 6 Dec 2011 08:33:52 +0100
perf: Avoid a useless pmu_disable() in the perf-tick
Gleb writes:
> Currently pmu is disabled and re-enabled on each timer interrupt even
> when no rotation or frequency adjustment is needed. On Intel CPU this
> results in two writes into PERF_GLOBAL_CTRL MSR per tick. On bare metal
> it does not cause significant slowdown, but when running perf in a virtual
> machine it leads to 20% slowdown on my machine.
Cure this by keeping a perf_event_context::nr_freq counter that counts the
number of active events that require frequency adjustments and use this in a
similar fashion to the already existing nr_events != nr_active test in
perf_rotate_context().
By being able to exclude both rotation and frequency adjustments a-priory for
the common case we can avoid the otherwise superfluous PMU disable.
Suggested-by: Gleb Natapov <gleb@...hat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@...llo.nl>
Link: http://lkml.kernel.org/n/tip-515yhoatehd3gza7we9fapaa@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@...e.hu>
---
include/linux/perf_event.h | 1 +
kernel/events/core.c | 48 +++++++++++++++++++++++++++++--------------
2 files changed, 33 insertions(+), 16 deletions(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index b1f8912..cb44c9e 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -890,6 +890,7 @@ struct perf_event_context {
int nr_active;
int is_active;
int nr_stat;
+ int nr_freq;
int rotate_disable;
atomic_t refcount;
struct task_struct *task;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a355ffb..b3fed52 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1130,6 +1130,8 @@ event_sched_out(struct perf_event *event,
if (!is_software_event(event))
cpuctx->active_oncpu--;
ctx->nr_active--;
+ if (event->attr.freq && event->attr.sample_freq)
+ ctx->nr_freq--;
if (event->attr.exclusive || !cpuctx->active_oncpu)
cpuctx->exclusive = 0;
}
@@ -1407,6 +1409,8 @@ event_sched_in(struct perf_event *event,
if (!is_software_event(event))
cpuctx->active_oncpu++;
ctx->nr_active++;
+ if (event->attr.freq && event->attr.sample_freq)
+ ctx->nr_freq++;
if (event->attr.exclusive)
cpuctx->exclusive = 1;
@@ -2329,6 +2333,9 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx, u64 period)
u64 interrupts, now;
s64 delta;
+ if (!ctx->nr_freq)
+ return;
+
list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
if (event->state != PERF_EVENT_STATE_ACTIVE)
continue;
@@ -2384,12 +2391,14 @@ static void perf_rotate_context(struct perf_cpu_context *cpuctx)
{
u64 interval = (u64)cpuctx->jiffies_interval * TICK_NSEC;
struct perf_event_context *ctx = NULL;
- int rotate = 0, remove = 1;
+ int rotate = 0, remove = 1, freq = 0;
if (cpuctx->ctx.nr_events) {
remove = 0;
if (cpuctx->ctx.nr_events != cpuctx->ctx.nr_active)
rotate = 1;
+ if (cpuctx->ctx.nr_freq)
+ freq = 1;
}
ctx = cpuctx->task_ctx;
@@ -2397,33 +2406,40 @@ static void perf_rotate_context(struct perf_cpu_context *cpuctx)
remove = 0;
if (ctx->nr_events != ctx->nr_active)
rotate = 1;
+ if (ctx->nr_freq)
+ freq = 1;
}
+ if (!rotate && !freq)
+ goto done;
+
perf_ctx_lock(cpuctx, cpuctx->task_ctx);
perf_pmu_disable(cpuctx->ctx.pmu);
- perf_ctx_adjust_freq(&cpuctx->ctx, interval);
- if (ctx)
- perf_ctx_adjust_freq(ctx, interval);
- if (!rotate)
- goto done;
+ if (freq) {
+ perf_ctx_adjust_freq(&cpuctx->ctx, interval);
+ if (ctx)
+ perf_ctx_adjust_freq(ctx, interval);
+ }
- cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
- if (ctx)
- ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE);
+ if (rotate) {
+ cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
+ if (ctx)
+ ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE);
- rotate_ctx(&cpuctx->ctx);
- if (ctx)
- rotate_ctx(ctx);
+ rotate_ctx(&cpuctx->ctx);
+ if (ctx)
+ rotate_ctx(ctx);
+
+ perf_event_sched_in(cpuctx, ctx, current);
+ }
- perf_event_sched_in(cpuctx, ctx, current);
+ perf_pmu_enable(cpuctx->ctx.pmu);
+ perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
done:
if (remove)
list_del_init(&cpuctx->rotation_list);
-
- perf_pmu_enable(cpuctx->ctx.pmu);
- perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
}
void perf_event_task_tick(void)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists