diff mbox series

[RFC,v3,08/58] perf: Clean up perf ctx time

Message ID 20240801045907.4010984-9-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>

The current perf tracks two timestamps for the normal ctx and cgroup.
The same type of variables and similar codes are used to track the
timestamps. In the following patch, the third timestamp to track the
guest time will be introduced.
To avoid the code duplication, add a new struct perf_time_ctx and factor
out a generic function update_perf_time_ctx().

No functional change.

Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Mingwei Zhang <mizhang@google.com>
---
 include/linux/perf_event.h | 13 +++++----
 kernel/events/core.c       | 59 +++++++++++++++++++-------------------
 2 files changed, 37 insertions(+), 35 deletions(-)

Comments

Peter Zijlstra Oct. 11, 2024, 11:39 a.m. UTC | #1 
On Thu, Aug 01, 2024 at 04:58:17AM +0000, Mingwei Zhang wrote:
> From: Kan Liang <kan.liang@linux.intel.com>
> 
> The current perf tracks two timestamps for the normal ctx and cgroup.
> The same type of variables and similar codes are used to track the
> timestamps. In the following patch, the third timestamp to track the
> guest time will be introduced.
> To avoid the code duplication, add a new struct perf_time_ctx and factor
> out a generic function update_perf_time_ctx().
> 
> No functional change.
> 
> Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
> Signed-off-by: Mingwei Zhang <mizhang@google.com>


--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -801,11 +801,22 @@ static inline u64 perf_cgroup_event_time
 	return now;
 }
 
-static inline void update_perf_time_ctx(struct perf_time_ctx *time, u64 now, bool adv);
-
-static inline void __update_cgrp_time(struct perf_cgroup_info *info, u64 now, bool adv)
+static inline void update_perf_time_ctx(struct perf_time_ctx *time, u64 now, bool adv)
 {
-	update_perf_time_ctx(&info->time, now, adv);
+	if (adv)
+		time->time += now - time->stamp;
+	time->stamp = now;
+
+	/*
+	 * The above: time' = time + (now - timestamp), can be re-arranged
+	 * into: time` = now + (time - timestamp), which gives a single value
+	 * offset to compute future time without locks on.
+	 *
+	 * See perf_event_time_now(), which can be used from NMI context where
+	 * it's (obviously) not possible to acquire ctx->lock in order to read
+	 * both the above values in a consistent manner.
+	 */
+	WRITE_ONCE(time->offset, time->time - time->stamp);
 }
 
 static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, bool final)
@@ -821,7 +832,7 @@ static inline void update_cgrp_time_from
 			cgrp = container_of(css, struct perf_cgroup, css);
 			info = this_cpu_ptr(cgrp->info);
 
-			__update_cgrp_time(info, now, true);
+			update_perf_time_ctx(&info->time, now, true);
 			if (final)
 				__store_release(&info->active, 0);
 		}
@@ -844,7 +855,7 @@ static inline void update_cgrp_time_from
 	 * Do not update time when cgroup is not active
 	 */
 	if (info->active)
-		__update_cgrp_time(info, perf_clock(), true);
+		update_perf_time_ctx(&info->time, perf_clock(), true);
 }
 
 static inline void
@@ -868,7 +879,7 @@ perf_cgroup_set_timestamp(struct perf_cp
 	for (css = &cgrp->css; css; css = css->parent) {
 		cgrp = container_of(css, struct perf_cgroup, css);
 		info = this_cpu_ptr(cgrp->info);
-		__update_cgrp_time(info, ctx->time.stamp, false);
+		update_perf_time_ctx(&info->time, ctx->time.stamp, false);
 		__store_release(&info->active, 1);
 	}
 }
@@ -1478,24 +1489,6 @@ static void perf_unpin_context(struct pe
 	raw_spin_unlock_irqrestore(&ctx->lock, flags);
 }
 
-static inline void update_perf_time_ctx(struct perf_time_ctx *time, u64 now, bool adv)
-{
-	if (adv)
-		time->time += now - time->stamp;
-	time->stamp = now;
-
-	/*
-	 * The above: time' = time + (now - timestamp), can be re-arranged
-	 * into: time` = now + (time - timestamp), which gives a single value
-	 * offset to compute future time without locks on.
-	 *
-	 * See perf_event_time_now(), which can be used from NMI context where
-	 * it's (obviously) not possible to acquire ctx->lock in order to read
-	 * both the above values in a consistent manner.
-	 */
-	WRITE_ONCE(time->offset, time->time - time->stamp);
-}
-
 /*
  * Update the record of the current time in a context.
  */
diff mbox series

Patch

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 45d1ea82aa21..e22cdb6486e6 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -906,6 +906,11 @@  struct perf_event_groups {
 	u64		index;
 };
 
+struct perf_time_ctx {
+	u64		time;
+	u64		stamp;
+	u64		offset;
+};
 
 /**
  * struct perf_event_context - event context structure
@@ -945,9 +950,7 @@  struct perf_event_context {
 	/*
 	 * Context clock, runs when context enabled.
 	 */
-	u64				time;
-	u64				timestamp;
-	u64				timeoffset;
+	struct perf_time_ctx		time;
 
 	/*
 	 * These fields let us detect when two contexts have both
@@ -1040,9 +1043,7 @@  struct bpf_perf_event_data_kern {
  * This is a per-cpu dynamically allocated data structure.
  */
 struct perf_cgroup_info {
-	u64				time;
-	u64				timestamp;
-	u64				timeoffset;
+	struct perf_time_ctx		time;
 	int				active;
 };
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7cb51dbf897a..c25e2bf27001 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -775,7 +775,7 @@  static inline u64 perf_cgroup_event_time(struct perf_event *event)
 	struct perf_cgroup_info *t;
 
 	t = per_cpu_ptr(event->cgrp->info, event->cpu);
-	return t->time;
+	return t->time.time;
 }
 
 static inline u64 perf_cgroup_event_time_now(struct perf_event *event, u64 now)
@@ -784,20 +784,16 @@  static inline u64 perf_cgroup_event_time_now(struct perf_event *event, u64 now)
 
 	t = per_cpu_ptr(event->cgrp->info, event->cpu);
 	if (!__load_acquire(&t->active))
-		return t->time;
-	now += READ_ONCE(t->timeoffset);
+		return t->time.time;
+	now += READ_ONCE(t->time.offset);
 	return now;
 }
 
+static inline void update_perf_time_ctx(struct perf_time_ctx *time, u64 now, bool adv);
+
 static inline void __update_cgrp_time(struct perf_cgroup_info *info, u64 now, bool adv)
 {
-	if (adv)
-		info->time += now - info->timestamp;
-	info->timestamp = now;
-	/*
-	 * see update_context_time()
-	 */
-	WRITE_ONCE(info->timeoffset, info->time - info->timestamp);
+	update_perf_time_ctx(&info->time, now, adv);
 }
 
 static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, bool final)
@@ -860,7 +856,7 @@  perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx)
 	for (css = &cgrp->css; css; css = css->parent) {
 		cgrp = container_of(css, struct perf_cgroup, css);
 		info = this_cpu_ptr(cgrp->info);
-		__update_cgrp_time(info, ctx->timestamp, false);
+		__update_cgrp_time(info, ctx->time.stamp, false);
 		__store_release(&info->active, 1);
 	}
 }
@@ -1469,18 +1465,11 @@  static void perf_unpin_context(struct perf_event_context *ctx)
 	raw_spin_unlock_irqrestore(&ctx->lock, flags);
 }
 
-/*
- * Update the record of the current time in a context.
- */
-static void __update_context_time(struct perf_event_context *ctx, bool adv)
+static inline void update_perf_time_ctx(struct perf_time_ctx *time, u64 now, bool adv)
 {
-	u64 now = perf_clock();
-
-	lockdep_assert_held(&ctx->lock);
-
 	if (adv)
-		ctx->time += now - ctx->timestamp;
-	ctx->timestamp = now;
+		time->time += now - time->stamp;
+	time->stamp = now;
 
 	/*
 	 * The above: time' = time + (now - timestamp), can be re-arranged
@@ -1491,7 +1480,19 @@  static void __update_context_time(struct perf_event_context *ctx, bool adv)
 	 * it's (obviously) not possible to acquire ctx->lock in order to read
 	 * both the above values in a consistent manner.
 	 */
-	WRITE_ONCE(ctx->timeoffset, ctx->time - ctx->timestamp);
+	WRITE_ONCE(time->offset, time->time - time->stamp);
+}
+
+/*
+ * Update the record of the current time in a context.
+ */
+static void __update_context_time(struct perf_event_context *ctx, bool adv)
+{
+	u64 now = perf_clock();
+
+	lockdep_assert_held(&ctx->lock);
+
+	update_perf_time_ctx(&ctx->time, now, adv);
 }
 
 static void update_context_time(struct perf_event_context *ctx)
@@ -1509,7 +1510,7 @@  static u64 perf_event_time(struct perf_event *event)
 	if (is_cgroup_event(event))
 		return perf_cgroup_event_time(event);
 
-	return ctx->time;
+	return ctx->time.time;
 }
 
 static u64 perf_event_time_now(struct perf_event *event, u64 now)
@@ -1523,9 +1524,9 @@  static u64 perf_event_time_now(struct perf_event *event, u64 now)
 		return perf_cgroup_event_time_now(event, now);
 
 	if (!(__load_acquire(&ctx->is_active) & EVENT_TIME))
-		return ctx->time;
+		return ctx->time.time;
 
-	now += READ_ONCE(ctx->timeoffset);
+	now += READ_ONCE(ctx->time.offset);
 	return now;
 }
 
@@ -11302,14 +11303,14 @@  static void task_clock_event_update(struct perf_event *event, u64 now)
 
 static void task_clock_event_start(struct perf_event *event, int flags)
 {
-	local64_set(&event->hw.prev_count, event->ctx->time);
+	local64_set(&event->hw.prev_count, event->ctx->time.time);
 	perf_swevent_start_hrtimer(event);
 }
 
 static void task_clock_event_stop(struct perf_event *event, int flags)
 {
 	perf_swevent_cancel_hrtimer(event);
-	task_clock_event_update(event, event->ctx->time);
+	task_clock_event_update(event, event->ctx->time.time);
 }
 
 static int task_clock_event_add(struct perf_event *event, int flags)
@@ -11329,8 +11330,8 @@  static void task_clock_event_del(struct perf_event *event, int flags)
 static void task_clock_event_read(struct perf_event *event)
 {
 	u64 now = perf_clock();
-	u64 delta = now - event->ctx->timestamp;
-	u64 time = event->ctx->time + delta;
+	u64 delta = now - event->ctx->time.stamp;
+	u64 time = event->ctx->time.time + delta;
 
 	task_clock_event_update(event, time);
 }