This is a note to let you know that I've just added the patch titled
Revert "perf: Rework perf_event_exit_event()"
to the 5.10-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
revert-perf-rework-perf_event_exit_event.patch
and it can be found in the queue-5.10 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 4087e59c499baa79aa466fb317874c3a401be38e
Author: Sasha Levin <sashal@xxxxxxxxxx>
Date: Wed Nov 24 19:18:11 2021 -0500
Revert "perf: Rework perf_event_exit_event()"
This reverts commit 94902ee2996a7f71471138093495df452dab87b6 which is
upstream commit ef54c1a476aef7eef26fe13ea10dc090952c00f8.
Reverting for now due to issues that need to get fixed upstream.
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c095e713cf08f..ce14fb2772b5b 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -607,7 +607,6 @@ struct swevent_hlist {
#define PERF_ATTACH_TASK_DATA 0x08
#define PERF_ATTACH_ITRACE 0x10
#define PERF_ATTACH_SCHED_CB 0x20
-#define PERF_ATTACH_CHILD 0x40
struct perf_cgroup;
struct perf_buffer;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 908417736f4e9..639b99a318db1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2209,26 +2209,6 @@ static void perf_group_detach(struct perf_event *event)
perf_event__header_size(leader);
}
-static void sync_child_event(struct perf_event *child_event);
-
-static void perf_child_detach(struct perf_event *event)
-{
- struct perf_event *parent_event = event->parent;
-
- if (!(event->attach_state & PERF_ATTACH_CHILD))
- return;
-
- event->attach_state &= ~PERF_ATTACH_CHILD;
-
- if (WARN_ON_ONCE(!parent_event))
- return;
-
- lockdep_assert_held(&parent_event->child_mutex);
-
- sync_child_event(event);
- list_del_init(&event->child_list);
-}
-
static bool is_orphaned_event(struct perf_event *event)
{
return event->state == PERF_EVENT_STATE_DEAD;
@@ -2336,7 +2316,6 @@ group_sched_out(struct perf_event *group_event,
}
#define DETACH_GROUP 0x01UL
-#define DETACH_CHILD 0x02UL
/*
* Cross CPU call to remove a performance event
@@ -2360,8 +2339,6 @@ __perf_remove_from_context(struct perf_event *event,
event_sched_out(event, cpuctx, ctx);
if (flags & DETACH_GROUP)
perf_group_detach(event);
- if (flags & DETACH_CHILD)
- perf_child_detach(event);
list_del_event(event, ctx);
if (!ctx->nr_events && ctx->is_active) {
@@ -2390,21 +2367,25 @@ static void perf_remove_from_context(struct perf_event *event, unsigned long fla
lockdep_assert_held(&ctx->mutex);
+ event_function_call(event, __perf_remove_from_context, (void *)flags);
+
/*
- * Because of perf_event_exit_task(), perf_remove_from_context() ought
- * to work in the face of TASK_TOMBSTONE, unlike every other
- * event_function_call() user.
+ * The above event_function_call() can NO-OP when it hits
+ * TASK_TOMBSTONE. In that case we must already have been detached
+ * from the context (by perf_event_exit_event()) but the grouping
+ * might still be in-tact.
*/
- raw_spin_lock_irq(&ctx->lock);
- if (!ctx->is_active) {
- __perf_remove_from_context(event, __get_cpu_context(ctx),
- ctx, (void *)flags);
+ WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
+ if ((flags & DETACH_GROUP) &&
+ (event->attach_state & PERF_ATTACH_GROUP)) {
+ /*
+ * Since in that case we cannot possibly be scheduled, simply
+ * detach now.
+ */
+ raw_spin_lock_irq(&ctx->lock);
+ perf_group_detach(event);
raw_spin_unlock_irq(&ctx->lock);
- return;
}
- raw_spin_unlock_irq(&ctx->lock);
-
- event_function_call(event, __perf_remove_from_context, (void *)flags);
}
/*
@@ -12296,17 +12277,14 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
}
EXPORT_SYMBOL_GPL(perf_pmu_migrate_context);
-static void sync_child_event(struct perf_event *child_event)
+static void sync_child_event(struct perf_event *child_event,
+ struct task_struct *child)
{
struct perf_event *parent_event = child_event->parent;
u64 child_val;
- if (child_event->attr.inherit_stat) {
- struct task_struct *task = child_event->ctx->task;
-
- if (task && task != TASK_TOMBSTONE)
- perf_event_read_event(child_event, task);
- }
+ if (child_event->attr.inherit_stat)
+ perf_event_read_event(child_event, child);
child_val = perf_event_count(child_event);
@@ -12321,53 +12299,60 @@ static void sync_child_event(struct perf_event *child_event)
}
static void
-perf_event_exit_event(struct perf_event *event, struct perf_event_context *ctx)
+perf_event_exit_event(struct perf_event *child_event,
+ struct perf_event_context *child_ctx,
+ struct task_struct *child)
{
- struct perf_event *parent_event = event->parent;
- unsigned long detach_flags = 0;
-
- if (parent_event) {
- /*
- * Do not destroy the 'original' grouping; because of the
- * context switch optimization the original events could've
- * ended up in a random child task.
- *
- * If we were to destroy the original group, all group related
- * operations would cease to function properly after this
- * random child dies.
- *
- * Do destroy all inherited groups, we don't care about those
- * and being thorough is better.
- */
- detach_flags = DETACH_GROUP | DETACH_CHILD;
- mutex_lock(&parent_event->child_mutex);
- }
+ struct perf_event *parent_event = child_event->parent;
- perf_remove_from_context(event, detach_flags);
+ /*
+ * Do not destroy the 'original' grouping; because of the context
+ * switch optimization the original events could've ended up in a
+ * random child task.
+ *
+ * If we were to destroy the original group, all group related
+ * operations would cease to function properly after this random
+ * child dies.
+ *
+ * Do destroy all inherited groups, we don't care about those
+ * and being thorough is better.
+ */
+ raw_spin_lock_irq(&child_ctx->lock);
+ WARN_ON_ONCE(child_ctx->is_active);
- raw_spin_lock_irq(&ctx->lock);
- if (event->state > PERF_EVENT_STATE_EXIT)
- perf_event_set_state(event, PERF_EVENT_STATE_EXIT);
- raw_spin_unlock_irq(&ctx->lock);
+ if (parent_event)
+ perf_group_detach(child_event);
+ list_del_event(child_event, child_ctx);
+ perf_event_set_state(child_event, PERF_EVENT_STATE_EXIT); /* is_event_hup() */
+ raw_spin_unlock_irq(&child_ctx->lock);
/*
- * Child events can be freed.
+ * Parent events are governed by their filedesc, retain them.
*/
- if (parent_event) {
- mutex_unlock(&parent_event->child_mutex);
- /*
- * Kick perf_poll() for is_event_hup();
- */
- perf_event_wakeup(parent_event);
- free_event(event);
- put_event(parent_event);
+ if (!parent_event) {
+ perf_event_wakeup(child_event);
return;
}
+ /*
+ * Child events can be cleaned up.
+ */
+
+ sync_child_event(child_event, child);
/*
- * Parent events are governed by their filedesc, retain them.
+ * Remove this event from the parent's list
+ */
+ WARN_ON_ONCE(parent_event->ctx->parent_ctx);
+ mutex_lock(&parent_event->child_mutex);
+ list_del_init(&child_event->child_list);
+ mutex_unlock(&parent_event->child_mutex);
+
+ /*
+ * Kick perf_poll() for is_event_hup().
*/
- perf_event_wakeup(event);
+ perf_event_wakeup(parent_event);
+ free_event(child_event);
+ put_event(parent_event);
}
static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
@@ -12424,7 +12409,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
perf_event_task(child, child_ctx, 0);
list_for_each_entry_safe(child_event, next, &child_ctx->event_list, event_entry)
- perf_event_exit_event(child_event, child_ctx);
+ perf_event_exit_event(child_event, child_ctx, child);
mutex_unlock(&child_ctx->mutex);
@@ -12684,7 +12669,6 @@ inherit_event(struct perf_event *parent_event,
*/
raw_spin_lock_irqsave(&child_ctx->lock, flags);
add_event_to_ctx(child_event, child_ctx);
- child_event->attach_state |= PERF_ATTACH_CHILD;
raw_spin_unlock_irqrestore(&child_ctx->lock, flags);
/*
