[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250324173121.1275209-3-mizhang@google.com>
Date: Mon, 24 Mar 2025 17:30:42 +0000
From: Mingwei Zhang <mizhang@...gle.com>
To: Peter Zijlstra <peterz@...radead.org>, Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>, Namhyung Kim <namhyung@...nel.org>,
Sean Christopherson <seanjc@...gle.com>, Paolo Bonzini <pbonzini@...hat.com>
Cc: Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>, Jiri Olsa <jolsa@...nel.org>,
Ian Rogers <irogers@...gle.com>, Adrian Hunter <adrian.hunter@...el.com>, Liang@...gle.com,
Kan <kan.liang@...ux.intel.com>, "H. Peter Anvin" <hpa@...or.com>,
linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org,
kvm@...r.kernel.org, linux-kselftest@...r.kernel.org,
Mingwei Zhang <mizhang@...gle.com>, Yongwei Ma <yongwei.ma@...el.com>,
Xiong Zhang <xiong.y.zhang@...ux.intel.com>, Dapeng Mi <dapeng1.mi@...ux.intel.com>,
Jim Mattson <jmattson@...gle.com>, Sandipan Das <sandipan.das@....com>,
Zide Chen <zide.chen@...el.com>, Eranian Stephane <eranian@...gle.com>,
Das Sandipan <Sandipan.Das@....com>, Shukla Manali <Manali.Shukla@....com>,
Nikunj Dadhania <nikunj.dadhania@....com>
Subject: [PATCH v4 02/38] perf: Skip pmu_ctx based on event_type
From: Kan Liang <kan.liang@...ux.intel.com>
To optimize the cgroup context switch, the perf_event_pmu_context
iteration skips the PMUs without cgroup events. A bool cgroup was
introduced to indicate the case. It can work, but this way is hard to
extend for other cases, e.g. skipping non-passthrough PMUs. It doesn't
make sense to keep adding bool variables.
Pass the event_type instead of the specific bool variable. Check both
the event_type and related pmu_ctx variables to decide whether skipping
a PMU.
Event flags, e.g., EVENT_CGROUP, should be cleard in the ctx->is_active.
Add EVENT_FLAGS to indicate such event flags.
No functional change.
Signed-off-by: Kan Liang <kan.liang@...ux.intel.com>
Tested-by: Yongwei Ma <yongwei.ma@...el.com>
Signed-off-by: Mingwei Zhang <mizhang@...gle.com>
---
kernel/events/core.c | 73 ++++++++++++++++++++++++--------------------
1 file changed, 40 insertions(+), 33 deletions(-)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index be623701dc48..8d3a0cc59fb4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -163,7 +163,7 @@ enum event_type_t {
/* see ctx_resched() for details */
EVENT_CPU = 0x10,
EVENT_CGROUP = 0x20,
-
+ EVENT_FLAGS = EVENT_CGROUP,
/* compound helpers */
EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
EVENT_TIME_FROZEN = EVENT_TIME | EVENT_FROZEN,
@@ -733,27 +733,37 @@ do { \
___p; \
})
-#define for_each_epc(_epc, _ctx, _pmu, _cgroup) \
+static bool perf_skip_pmu_ctx(struct perf_event_pmu_context *pmu_ctx,
+ enum event_type_t event_type)
+{
+ if ((event_type & EVENT_CGROUP) && !pmu_ctx->nr_cgroups)
+ return true;
+ return false;
+}
+
+#define for_each_epc(_epc, _ctx, _pmu, _event_type) \
list_for_each_entry(_epc, &((_ctx)->pmu_ctx_list), pmu_ctx_entry) \
- if (_cgroup && !_epc->nr_cgroups) \
+ if (perf_skip_pmu_ctx(_epc, _event_type)) \
continue; \
else if (_pmu && _epc->pmu != _pmu) \
continue; \
else
-static void perf_ctx_disable(struct perf_event_context *ctx, bool cgroup)
+static void perf_ctx_disable(struct perf_event_context *ctx,
+ enum event_type_t event_type)
{
struct perf_event_pmu_context *pmu_ctx;
- for_each_epc(pmu_ctx, ctx, NULL, cgroup)
+ for_each_epc(pmu_ctx, ctx, NULL, event_type)
perf_pmu_disable(pmu_ctx->pmu);
}
-static void perf_ctx_enable(struct perf_event_context *ctx, bool cgroup)
+static void perf_ctx_enable(struct perf_event_context *ctx,
+ enum event_type_t event_type)
{
struct perf_event_pmu_context *pmu_ctx;
- for_each_epc(pmu_ctx, ctx, NULL, cgroup)
+ for_each_epc(pmu_ctx, ctx, NULL, event_type)
perf_pmu_enable(pmu_ctx->pmu);
}
@@ -913,7 +923,7 @@ static void perf_cgroup_switch(struct task_struct *task)
return;
perf_ctx_lock(cpuctx, cpuctx->task_ctx);
- perf_ctx_disable(&cpuctx->ctx, true);
+ perf_ctx_disable(&cpuctx->ctx, EVENT_CGROUP);
ctx_sched_out(&cpuctx->ctx, NULL, EVENT_ALL|EVENT_CGROUP);
/*
@@ -929,7 +939,7 @@ static void perf_cgroup_switch(struct task_struct *task)
*/
ctx_sched_in(&cpuctx->ctx, NULL, EVENT_ALL|EVENT_CGROUP);
- perf_ctx_enable(&cpuctx->ctx, true);
+ perf_ctx_enable(&cpuctx->ctx, EVENT_CGROUP);
perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
}
@@ -2796,11 +2806,11 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
event_type &= EVENT_ALL;
- for_each_epc(epc, &cpuctx->ctx, pmu, false)
+ for_each_epc(epc, &cpuctx->ctx, pmu, 0)
perf_pmu_disable(epc->pmu);
if (task_ctx) {
- for_each_epc(epc, task_ctx, pmu, false)
+ for_each_epc(epc, task_ctx, pmu, 0)
perf_pmu_disable(epc->pmu);
task_ctx_sched_out(task_ctx, pmu, event_type);
@@ -2820,11 +2830,11 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
perf_event_sched_in(cpuctx, task_ctx, pmu);
- for_each_epc(epc, &cpuctx->ctx, pmu, false)
+ for_each_epc(epc, &cpuctx->ctx, pmu, 0)
perf_pmu_enable(epc->pmu);
if (task_ctx) {
- for_each_epc(epc, task_ctx, pmu, false)
+ for_each_epc(epc, task_ctx, pmu, 0)
perf_pmu_enable(epc->pmu);
}
}
@@ -3374,11 +3384,10 @@ static void
ctx_sched_out(struct perf_event_context *ctx, struct pmu *pmu, enum event_type_t event_type)
{
struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
+ enum event_type_t active_type = event_type & ~EVENT_FLAGS;
struct perf_event_pmu_context *pmu_ctx;
int is_active = ctx->is_active;
- bool cgroup = event_type & EVENT_CGROUP;
- event_type &= ~EVENT_CGROUP;
lockdep_assert_held(&ctx->lock);
@@ -3409,7 +3418,7 @@ ctx_sched_out(struct perf_event_context *ctx, struct pmu *pmu, enum event_type_t
* see __load_acquire() in perf_event_time_now()
*/
barrier();
- ctx->is_active &= ~event_type;
+ ctx->is_active &= ~active_type;
if (!(ctx->is_active & EVENT_ALL)) {
/*
@@ -3430,7 +3439,7 @@ ctx_sched_out(struct perf_event_context *ctx, struct pmu *pmu, enum event_type_t
is_active ^= ctx->is_active; /* changed bits */
- for_each_epc(pmu_ctx, ctx, pmu, cgroup)
+ for_each_epc(pmu_ctx, ctx, pmu, event_type)
__pmu_ctx_sched_out(pmu_ctx, is_active);
}
@@ -3622,7 +3631,7 @@ perf_event_context_sched_out(struct task_struct *task, struct task_struct *next)
raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING);
if (context_equiv(ctx, next_ctx)) {
- perf_ctx_disable(ctx, false);
+ perf_ctx_disable(ctx, 0);
/* PMIs are disabled; ctx->nr_no_switch_fast is stable. */
if (local_read(&ctx->nr_no_switch_fast) ||
@@ -3647,7 +3656,7 @@ perf_event_context_sched_out(struct task_struct *task, struct task_struct *next)
perf_ctx_sched_task_cb(ctx, false);
perf_event_swap_task_ctx_data(ctx, next_ctx);
- perf_ctx_enable(ctx, false);
+ perf_ctx_enable(ctx, 0);
/*
* RCU_INIT_POINTER here is safe because we've not
@@ -3671,13 +3680,13 @@ perf_event_context_sched_out(struct task_struct *task, struct task_struct *next)
if (do_switch) {
raw_spin_lock(&ctx->lock);
- perf_ctx_disable(ctx, false);
+ perf_ctx_disable(ctx, 0);
inside_switch:
perf_ctx_sched_task_cb(ctx, false);
task_ctx_sched_out(ctx, NULL, EVENT_ALL);
- perf_ctx_enable(ctx, false);
+ perf_ctx_enable(ctx, 0);
raw_spin_unlock(&ctx->lock);
}
}
@@ -3981,11 +3990,9 @@ static void
ctx_sched_in(struct perf_event_context *ctx, struct pmu *pmu, enum event_type_t event_type)
{
struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
+ enum event_type_t active_type = event_type & ~EVENT_FLAGS;
struct perf_event_pmu_context *pmu_ctx;
int is_active = ctx->is_active;
- bool cgroup = event_type & EVENT_CGROUP;
-
- event_type &= ~EVENT_CGROUP;
lockdep_assert_held(&ctx->lock);
@@ -4003,7 +4010,7 @@ ctx_sched_in(struct perf_event_context *ctx, struct pmu *pmu, enum event_type_t
barrier();
}
- ctx->is_active |= (event_type | EVENT_TIME);
+ ctx->is_active |= active_type | EVENT_TIME;
if (ctx->task) {
if (!(is_active & EVENT_ALL))
cpuctx->task_ctx = ctx;
@@ -4018,13 +4025,13 @@ ctx_sched_in(struct perf_event_context *ctx, struct pmu *pmu, enum event_type_t
* in order to give them the best chance of going on.
*/
if (is_active & EVENT_PINNED) {
- for_each_epc(pmu_ctx, ctx, pmu, cgroup)
+ for_each_epc(pmu_ctx, ctx, pmu, event_type)
__pmu_ctx_sched_in(pmu_ctx, EVENT_PINNED);
}
/* Then walk through the lower prio flexible groups */
if (is_active & EVENT_FLEXIBLE) {
- for_each_epc(pmu_ctx, ctx, pmu, cgroup)
+ for_each_epc(pmu_ctx, ctx, pmu, event_type)
__pmu_ctx_sched_in(pmu_ctx, EVENT_FLEXIBLE);
}
}
@@ -4041,11 +4048,11 @@ static void perf_event_context_sched_in(struct task_struct *task)
if (cpuctx->task_ctx == ctx) {
perf_ctx_lock(cpuctx, ctx);
- perf_ctx_disable(ctx, false);
+ perf_ctx_disable(ctx, 0);
perf_ctx_sched_task_cb(ctx, true);
- perf_ctx_enable(ctx, false);
+ perf_ctx_enable(ctx, 0);
perf_ctx_unlock(cpuctx, ctx);
goto rcu_unlock;
}
@@ -4058,7 +4065,7 @@ static void perf_event_context_sched_in(struct task_struct *task)
if (!ctx->nr_events)
goto unlock;
- perf_ctx_disable(ctx, false);
+ perf_ctx_disable(ctx, 0);
/*
* We want to keep the following priority order:
* cpu pinned (that don't need to move), task pinned,
@@ -4068,7 +4075,7 @@ static void perf_event_context_sched_in(struct task_struct *task)
* events, no need to flip the cpuctx's events around.
*/
if (!RB_EMPTY_ROOT(&ctx->pinned_groups.tree)) {
- perf_ctx_disable(&cpuctx->ctx, false);
+ perf_ctx_disable(&cpuctx->ctx, 0);
ctx_sched_out(&cpuctx->ctx, NULL, EVENT_FLEXIBLE);
}
@@ -4077,9 +4084,9 @@ static void perf_event_context_sched_in(struct task_struct *task)
perf_ctx_sched_task_cb(cpuctx->task_ctx, true);
if (!RB_EMPTY_ROOT(&ctx->pinned_groups.tree))
- perf_ctx_enable(&cpuctx->ctx, false);
+ perf_ctx_enable(&cpuctx->ctx, 0);
- perf_ctx_enable(ctx, false);
+ perf_ctx_enable(ctx, 0);
unlock:
perf_ctx_unlock(cpuctx, ctx);
--
2.49.0.395.g12beb8f557-goog
Powered by blists - more mailing lists