diff mbox series

[RFC,v3,07/58] perf: Skip pmu_ctx based on event_type

Message ID 20240801045907.4010984-8-mizhang@google.com (mailing list archive)
State New, archived
Headers show
Series Mediated Passthrough vPMU 3.0 for x86 | expand

Commit Message

Mingwei Zhang Aug. 1, 2024, 4:58 a.m. UTC 
From: Kan Liang <kan.liang@linux.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@linux.intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Signed-off-by: Mingwei Zhang <mizhang@google.com>
---
 kernel/events/core.c | 70 +++++++++++++++++++++++---------------------
 1 file changed, 37 insertions(+), 33 deletions(-)

Comments

Peter Zijlstra Oct. 11, 2024, 11:18 a.m. UTC | #1 
On Thu, Aug 01, 2024 at 04:58:16AM +0000, Mingwei Zhang wrote:
> @@ -3299,9 +3309,6 @@ ctx_sched_out(struct perf_event_context *ctx, enum event_type_t event_type)
>  	struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
>  	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);
>  
> @@ -3336,7 +3343,7 @@ ctx_sched_out(struct perf_event_context *ctx, enum event_type_t event_type)
>  		barrier();
>  	}
>  
> -	ctx->is_active &= ~event_type;
> +	ctx->is_active &= ~(event_type & ~EVENT_FLAGS);
>  	if (!(ctx->is_active & EVENT_ALL))
>  		ctx->is_active = 0;
>  

> @@ -3912,9 +3919,6 @@ ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type)
>  {
>  	struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
>  	int is_active = ctx->is_active;
> -	bool cgroup = event_type & EVENT_CGROUP;
> -
> -	event_type &= ~EVENT_CGROUP;
>  
>  	lockdep_assert_held(&ctx->lock);
>  
> @@ -3932,7 +3936,7 @@ ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type)
>  		barrier();
>  	}
>  
> -	ctx->is_active |= (event_type | EVENT_TIME);
> +	ctx->is_active |= ((event_type & ~EVENT_FLAGS) | EVENT_TIME);
>  	if (ctx->task) {
>  		if (!is_active)
>  			cpuctx->task_ctx = ctx;

Would it make sense to do something like:

	enum event_type_t active_type = event_type & ~EVENT_FLAGS;

	ctx->is_active &= ~active_type;
and
	ctx->is_active |= (active_type | EVENT_TIME);

Or something along those lines; those expressions become a little
unwieldy otherwise.
diff mbox series

Patch

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 45868d276cde..7cb51dbf897a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -376,6 +376,7 @@  enum event_type_t {
 	/* see ctx_resched() for details */
 	EVENT_CPU = 0x8,
 	EVENT_CGROUP = 0x10,
+	EVENT_FLAGS = EVENT_CGROUP,
 	EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
 };
 
@@ -699,23 +700,32 @@  do {									\
 	___p;								\
 })
 
-static void perf_ctx_disable(struct perf_event_context *ctx, bool 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;
+}
+
+static void perf_ctx_disable(struct perf_event_context *ctx, enum event_type_t event_type)
 {
 	struct perf_event_pmu_context *pmu_ctx;
 
 	list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
-		if (cgroup && !pmu_ctx->nr_cgroups)
+		if (perf_skip_pmu_ctx(pmu_ctx, event_type))
 			continue;
 		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;
 
 	list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
-		if (cgroup && !pmu_ctx->nr_cgroups)
+		if (perf_skip_pmu_ctx(pmu_ctx, event_type))
 			continue;
 		perf_pmu_enable(pmu_ctx->pmu);
 	}
@@ -877,7 +887,7 @@  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, EVENT_ALL|EVENT_CGROUP);
 	/*
@@ -893,7 +903,7 @@  static void perf_cgroup_switch(struct task_struct *task)
 	 */
 	ctx_sched_in(&cpuctx->ctx, EVENT_ALL|EVENT_CGROUP);
 
-	perf_ctx_enable(&cpuctx->ctx, true);
+	perf_ctx_enable(&cpuctx->ctx, EVENT_CGROUP);
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 }
 
@@ -2732,9 +2742,9 @@  static void ctx_resched(struct perf_cpu_context *cpuctx,
 
 	event_type &= EVENT_ALL;
 
-	perf_ctx_disable(&cpuctx->ctx, false);
+	perf_ctx_disable(&cpuctx->ctx, 0);
 	if (task_ctx) {
-		perf_ctx_disable(task_ctx, false);
+		perf_ctx_disable(task_ctx, 0);
 		task_ctx_sched_out(task_ctx, event_type);
 	}
 
@@ -2752,9 +2762,9 @@  static void ctx_resched(struct perf_cpu_context *cpuctx,
 
 	perf_event_sched_in(cpuctx, task_ctx);
 
-	perf_ctx_enable(&cpuctx->ctx, false);
+	perf_ctx_enable(&cpuctx->ctx, 0);
 	if (task_ctx)
-		perf_ctx_enable(task_ctx, false);
+		perf_ctx_enable(task_ctx, 0);
 }
 
 void perf_pmu_resched(struct pmu *pmu)
@@ -3299,9 +3309,6 @@  ctx_sched_out(struct perf_event_context *ctx, enum event_type_t event_type)
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
 	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);
 
@@ -3336,7 +3343,7 @@  ctx_sched_out(struct perf_event_context *ctx, enum event_type_t event_type)
 		barrier();
 	}
 
-	ctx->is_active &= ~event_type;
+	ctx->is_active &= ~(event_type & ~EVENT_FLAGS);
 	if (!(ctx->is_active & EVENT_ALL))
 		ctx->is_active = 0;
 
@@ -3349,7 +3356,7 @@  ctx_sched_out(struct perf_event_context *ctx, enum event_type_t event_type)
 	is_active ^= ctx->is_active; /* changed bits */
 
 	list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
-		if (cgroup && !pmu_ctx->nr_cgroups)
+		if (perf_skip_pmu_ctx(pmu_ctx, event_type))
 			continue;
 		__pmu_ctx_sched_out(pmu_ctx, is_active);
 	}
@@ -3543,7 +3550,7 @@  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_pending is stable. */
 			if (local_read(&ctx->nr_pending) ||
@@ -3563,7 +3570,7 @@  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
@@ -3587,13 +3594,13 @@  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, EVENT_ALL);
 
-		perf_ctx_enable(ctx, false);
+		perf_ctx_enable(ctx, 0);
 		raw_spin_unlock(&ctx->lock);
 	}
 }
@@ -3890,12 +3897,12 @@  static void pmu_groups_sched_in(struct perf_event_context *ctx,
 
 static void ctx_groups_sched_in(struct perf_event_context *ctx,
 				struct perf_event_groups *groups,
-				bool cgroup)
+				enum event_type_t event_type)
 {
 	struct perf_event_pmu_context *pmu_ctx;
 
 	list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
-		if (cgroup && !pmu_ctx->nr_cgroups)
+		if (perf_skip_pmu_ctx(pmu_ctx, event_type))
 			continue;
 		pmu_groups_sched_in(ctx, groups, pmu_ctx->pmu);
 	}
@@ -3912,9 +3919,6 @@  ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type)
 {
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
 	int is_active = ctx->is_active;
-	bool cgroup = event_type & EVENT_CGROUP;
-
-	event_type &= ~EVENT_CGROUP;
 
 	lockdep_assert_held(&ctx->lock);
 
@@ -3932,7 +3936,7 @@  ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type)
 		barrier();
 	}
 
-	ctx->is_active |= (event_type | EVENT_TIME);
+	ctx->is_active |= ((event_type & ~EVENT_FLAGS) | EVENT_TIME);
 	if (ctx->task) {
 		if (!is_active)
 			cpuctx->task_ctx = ctx;
@@ -3947,11 +3951,11 @@  ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type)
 	 * in order to give them the best chance of going on.
 	 */
 	if (is_active & EVENT_PINNED)
-		ctx_groups_sched_in(ctx, &ctx->pinned_groups, cgroup);
+		ctx_groups_sched_in(ctx, &ctx->pinned_groups, event_type);
 
 	/* Then walk through the lower prio flexible groups */
 	if (is_active & EVENT_FLEXIBLE)
-		ctx_groups_sched_in(ctx, &ctx->flexible_groups, cgroup);
+		ctx_groups_sched_in(ctx, &ctx->flexible_groups, event_type);
 }
 
 static void perf_event_context_sched_in(struct task_struct *task)
@@ -3966,11 +3970,11 @@  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;
 	}
@@ -3983,7 +3987,7 @@  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,
@@ -3993,7 +3997,7 @@  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, EVENT_FLEXIBLE);
 	}
 
@@ -4002,9 +4006,9 @@  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);