Message-ID: <81fc4d10-1245-59e8-8575-1f790c4e1097@linux.intel.com>
Date:   Wed, 21 Jun 2017 18:39:24 +0300
From:   Alexey Budankov <alexey.budankov@...ux.intel.com>
To:     Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...hat.com>,
        Arnaldo Carvalho de Melo <acme@...nel.org>,
        Alexander Shishkin <alexander.shishkin@...ux.intel.com>
Cc:     Andi Kleen <ak@...ux.intel.com>, Kan Liang <kan.liang@...el.com>,
        Dmitri Prokhorov <Dmitry.Prohorov@...el.com>,
        Valery Cherepennikov <valery.cherepennikov@...el.com>,
        Mark Rutland <mark.rutland@....com>,
        David Carrillo-Cisneros <davidcc@...gle.com>,
        Stephane Eranian <eranian@...gle.com>,
        linux-kernel <linux-kernel@...r.kernel.org>
Subject: [PATCH v4 1/4] perf/core: addressing 4x slowdown during per-process
 profiling of STREAM benchmark on Intel Xeon Phi

perf/core: use rb trees for pinned/flexible groups

By default, the userspace perf tool opens per-cpu task-bound events
when sampling, so for N logical events requested by the user, the tool
will open N * NR_CPUS events.

In the kernel, we mux events with a hrtimer, periodically rotating the
flexible group list and trying to schedule each group in turn. We skip 
groups whose cpu filter doesn't match. So when we get unlucky, we can 
walk N * (NR_CPUS - 1) groups pointlessly for each hrtimer invocation.

This has been observed to result in significant overhead when running
the STREAM benchmark on 272 core Xeon Phi systems.

One way to avoid this is to place our events into an rb tree sorted by
CPU, so that our hrtimer can skip to the current CPU's list and ignore
everything else.

As a step towards that, this patch introduces rb tree for group lists.

Signed-off-by: Alexey Budankov <alexey.budankov@...ux.intel.com>
---

  include/linux/perf_event.h |  33 +++-
  kernel/events/core.c       | 463 
+++++++++++++++++++++++++++++++++++----------
  2 files changed, 397 insertions(+), 99 deletions(-)

1. introduced group_node, group_list, group_list_entry into
    struct perf_event type;

2. introduced perf_event_groups type for pinned and flexible groups;
    new type objects combine rb tree and list for safe whole tree
    iterations;

3. introduced new functions:

    get_event_groups()
    add_event_to_groups()
    del_event_from_groups()

    perf_event_groups_empty()
    perf_event_groups_init()
    perf_event_groups_insert()
    perf_event_groups_delete()
    perf_event_groups_rotate(..., int cpu)
    perf_event_groups_iterate_cpu(..., int cpu)
    perf_event_groups_iterate()

    struct group_sched_params
    group_sched_out_callback()
    sched_in_group()
    ctx_pinned_sched_in_callback()
    ctx_flexible_sched_in_callback()

    struct inherit_task_group_params
    inherit_task_group_callback()

    see comments in the patch for more details;

4. removed functions:

    ctx_group_list()
    ctx_pinned_sched_in()
    ctx_flexible_sched_in()

5. functions changed to adopt new API:

    perf_event_alloc(),
    perf_event_init_context(),
    __perf_event_init_context(),
    list_add_event(),
    list_del_event(),
    ctx_sched_in(),
    ctx_sched_out(),
    perf_event_context_sched_in(),
    inherit_task_group(),
    rotate_ctx()

The patch was tested under perf_fuzzer and tests on Xeon Phi: 
https://github.com/deater/perf_event_tests.
No new issues were found in comparison to the clean kernel.

---

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 24a6358..d2fb0e7 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -572,6 +572,26 @@ struct perf_event {
  	 */
  	struct list_head		group_entry;
  	struct list_head		sibling_list;
+	/*
+	 * Node on the pinned or flexible tree located at the event context;
+	 * the node may be empty in case its event is not directly attached
+	 * to the tree but to group_list list of the event directly
+	 * attached to the tree;
+	 */
+	struct rb_node            	group_node;
+	/*
+	 * List keeps groups allocated for the same cpu;
+	 * the list may be empty in case its event is not directly
+	 * attached to the tree but to group_list list of the event directly
+	 * attached to the tree;
+	 */
+	struct list_head 	       	group_list;
+	/*
+	 * Entry into the group_list list above;
+	 * the entry may be attached to the self group_list list above
+	 * in case the event is directly attached to the tree;
+	 */
+	struct list_head		group_list_entry;

  	/*
  	 * We need storage to track the entries in perf_pmu_migrate_context; we
@@ -721,6 +741,15 @@ struct perf_event {
  #endif /* CONFIG_PERF_EVENTS */
  };

+/*
+ * event groups keep group leader events arranged as an rb tree with
+ * event->cpu key and as a list for the whole tree iterations;
+ */
+struct perf_event_groups {
+	struct rb_root	 tree;
+	struct list_head list;
+};
+
  /**
   * struct perf_event_context - event context structure
   *
@@ -741,8 +770,8 @@ struct perf_event_context {
  	struct mutex			mutex;

  	struct list_head		active_ctx_list;
-	struct list_head		pinned_groups;
-	struct list_head		flexible_groups;
+	struct perf_event_groups	pinned_groups;
+	struct perf_event_groups        flexible_groups;
  	struct list_head		event_list;
  	int				nr_events;
  	int				nr_active;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index bc63f8d..fc37e30 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1458,8 +1458,12 @@ static enum event_type_t get_event_type(struct 
perf_event *event)
  	return event_type;
  }

-static struct list_head *
-ctx_group_list(struct perf_event *event, struct perf_event_context *ctx)
+/*
+ * Extract pinned or flexible groups from the context
+ * based on event attrs bits;
+ */
+static struct perf_event_groups *
+get_event_groups(struct perf_event *event, struct perf_event_context *ctx)
  {
  	if (event->attr.pinned)
  		return &ctx->pinned_groups;
@@ -1467,6 +1471,223 @@ ctx_group_list(struct perf_event *event, struct 
perf_event_context *ctx)
  		return &ctx->flexible_groups;
  }

+static void
+perf_event_groups_insert(struct perf_event_groups *groups,
+		struct perf_event *event);
+
+static void
+perf_event_groups_delete(struct perf_event_groups *groups,
+		struct perf_event *event);
+
+/*
+ * Helper function to insert event into the pinned or
+ * flexible groups;
+ */
+static void
+add_event_to_groups(struct perf_event *event, struct perf_event_context 
*ctx)
+{
+	struct perf_event_groups *groups;
+
+	groups = get_event_groups(event, ctx);
+	perf_event_groups_insert(groups, event);
+}
+
+/*
+ * Helper function to delete event from its groups;
+ */
+static void
+del_event_from_groups(struct perf_event *event, struct 
perf_event_context *ctx)
+{
+	struct perf_event_groups *groups;
+
+	groups = get_event_groups(event, ctx);
+	perf_event_groups_delete(groups, event);
+}
+
+/*
+ * Helper function to test if event groups are empty;
+ */
+static int
+perf_event_groups_empty(struct perf_event_groups *groups)
+{
+	return list_empty(&groups->list);
+}
+
+/*
+ * Helper function to Initialize event groups object;
+ */
+static void
+perf_event_groups_init(struct perf_event_groups *groups)
+{
+	groups->tree = RB_ROOT;
+	INIT_LIST_HEAD(&groups->list);
+}
+
+/*
+ * Insert a group into a tree using event->cpu as a key. If event->cpu node
+ * is already attached to the tree then the event is added to the attached
+ * group's group_list list.
+ */
+static void
+perf_event_groups_insert(struct perf_event_groups *groups,
+		struct perf_event *event)
+{
+	struct rb_node **node;
+	struct rb_node *parent;
+
+	WARN_ON_ONCE(!groups || !event);
+
+	list_add_tail(&event->group_entry, &groups->list);
+
+	node = &groups->tree.rb_node;
+	parent = *node;
+
+	while (*node) {
+		struct perf_event *node_event = container_of(*node,
+				struct perf_event, group_node);
+
+		parent = *node;
+
+		if (event->cpu < node_event->cpu) {
+			node = &parent->rb_left;
+		} else if (event->cpu > node_event->cpu) {
+			node = &parent->rb_right;
+		} else {
+			list_add_tail(&event->group_list_entry,
+					&node_event->group_list);
+			return;
+		}
+	}
+
+	list_add_tail(&event->group_list_entry, &event->group_list);
+
+	rb_link_node(&event->group_node, parent, node);
+	rb_insert_color(&event->group_node, &groups->tree);
+}
+
+/*
+ * Delete a group from a tree. If the group is directly attached to the 
tree
+ * it also detaches all groups on the group's group_list list.
+ */
+static void
+perf_event_groups_delete(struct perf_event_groups *groups,
+		struct perf_event *event)
+{
+	struct perf_event *next;
+
+	WARN_ON_ONCE(!groups || !event);
+
+	list_del_init(&event->group_list_entry);
+
+	if (!RB_EMPTY_NODE(&event->group_node)) {
+		if (!list_empty(&event->group_list)) {
+			next = list_first_entry(&event->group_list,
+					struct perf_event, group_list_entry);
+			list_replace_init(&event->group_list,
+					&next->group_list);
+			rb_replace_node(&event->group_node,
+					&next->group_node, &groups->tree);
+		} else {
+			rb_erase(&event->group_node, &groups->tree);
+		}
+		RB_CLEAR_NODE(&event->group_node);
+	}
+
+	list_del_init(&event->group_entry);
+}
+
+/*
+ * Find group list by a cpu key and rotate it.
+ */
+static void
+perf_event_groups_rotate(struct perf_event_groups *groups, int cpu)
+{
+	WARN_ON_ONCE(!groups);
+
+	list_rotate_left(&groups->list);
+
+	/* will replace rotation above with mux switch in patch v4-3/4
+
+	struct rb_node *node;
+	struct perf_event *node_event;
+
+	WARN_ON_ONCE(!groups);
+
+	node = groups->tree.rb_node;
+
+	while (node) {
+		node_event = container_of(node,	struct perf_event, group_node);
+
+		if (cpu < node_event->cpu) {
+			node = node->rb_left;
+		} else if (cpu > node_event->cpu) {
+			node = node->rb_right;
+		} else {
+			list_rotate_left(&node_event->group_list);
+			return;
+		}
+	}
+
+	*/
+}
+
+/*
+ * Find group_list list by a cpu key and call provided callback for every
+ * group on the list.
+ */
+
+typedef int(*perf_event_groups_iterate_f)(struct perf_event *, void *);
+
+static void
+perf_event_groups_iterate_cpu(struct perf_event_groups *groups, int cpu,
+		perf_event_groups_iterate_f callback, void *data)
+{
+	struct rb_node *node;
+	struct perf_event *event;
+
+	WARN_ON_ONCE(!groups);
+
+	node = groups->tree.rb_node;
+
+	while (node) {
+		struct perf_event *node_event = container_of(node,
+				struct perf_event, group_node);
+
+		if (cpu < node_event->cpu) {
+			node = node->rb_left;
+		} else if (cpu > node_event->cpu) {
+			node = node->rb_right;
+		} else {
+			list_for_each_entry(event, &node_event->group_list,
+					group_list_entry)
+				callback(event, data);
+			return;
+		}
+	}
+}
+
+/*
+ * Iterate event groups and call provided callback for every group in 
the tree.
+ * Iteration stops if the callback returns non zero.
+ */
+static int
+perf_event_groups_iterate(struct perf_event_groups *groups,
+		perf_event_groups_iterate_f callback, void *data)
+{
+	int ret = 0;
+	struct perf_event *event;
+
+	WARN_ON_ONCE(!groups);
+
+	list_for_each_entry(event, &groups->list, group_entry) {
+		ret = callback(event, data);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
  /*
   * Add a event from the lists for its context.
   * Must be called with ctx->mutex and ctx->lock held.
@@ -1485,12 +1706,8 @@ list_add_event(struct perf_event *event, struct 
perf_event_context *ctx)
  	 * perf_group_detach can, at all times, locate all siblings.
  	 */
  	if (event->group_leader == event) {
-		struct list_head *list;
-
  		event->group_caps = event->event_caps;
-
-		list = ctx_group_list(event, ctx);
-		list_add_tail(&event->group_entry, list);
+		add_event_to_groups(event, ctx);
  	}

  	list_update_cgroup_event(event, ctx, true);
@@ -1681,7 +1898,7 @@ list_del_event(struct perf_event *event, struct 
perf_event_context *ctx)
  	list_del_rcu(&event->event_entry);

  	if (event->group_leader == event)
-		list_del_init(&event->group_entry);
+		del_event_from_groups(event, ctx);

  	update_group_times(event);

@@ -1861,6 +2078,22 @@ group_sched_out(struct perf_event *group_event,
  		cpuctx->exclusive = 0;
  }

+struct group_sched_params {
+	struct perf_cpu_context *cpuctx;
+	struct perf_event_context *ctx;
+	int can_add_hw;
+};
+
+static int
+group_sched_out_callback(struct perf_event *event, void *data)
+{
+	struct group_sched_params *params = data;
+
+	group_sched_out(event, params->cpuctx, params->ctx);
+
+	return 0;
+}
+
  #define DETACH_GROUP	0x01UL

  /*
@@ -2209,6 +2442,60 @@ static int group_can_go_on(struct perf_event *event,
  	return can_add_hw;
  }

+static void
+sched_in_group(struct perf_event *event, struct perf_cpu_context *cpuctx,
+		struct perf_event_context *ctx,	int *can_add_hw)
+{
+	/* Ignore events in OFF or ERROR state */
+	if (event->state <= PERF_EVENT_STATE_OFF)
+		return;
+	/*
+	 * Listen to the 'cpu' scheduling filter constraint
+	 * of events:
+	 */
+	if (!event_filter_match(event))
+		return;
+
+	/* may need to reset tstamp_enabled */
+	if (is_cgroup_event(event))
+		perf_cgroup_mark_enabled(event, ctx);
+
+	if (group_can_go_on(event, cpuctx, *can_add_hw)) {
+		if (group_sched_in(event, cpuctx, ctx))
+			*can_add_hw = 0;
+	}
+}
+
+static int
+ctx_pinned_sched_in_callback(struct perf_event *event, void *data)
+{
+	struct group_sched_params *params = data;
+	int can_add_hw = 1;
+
+	sched_in_group(event, params->cpuctx, params->ctx, &can_add_hw);
+
+	/*
+	 * If this pinned group hasn't been scheduled,
+	 * put it in error state.
+	 */
+	if (event->state == PERF_EVENT_STATE_INACTIVE) {
+		update_group_times(event);
+		event->state = PERF_EVENT_STATE_ERROR;
+	}
+
+	return 0;
+}
+
+static int
+ctx_flexible_sched_in_callback(struct perf_event *event, void *data)
+{
+	struct group_sched_params *params = data;
+
+	sched_in_group(event, params->cpuctx, params->ctx, &params->can_add_hw);
+
+	return 0;
+}
+
  static void add_event_to_ctx(struct perf_event *event,
  			       struct perf_event_context *ctx)
  {
@@ -2705,6 +2992,12 @@ static void ctx_sched_out(struct 
perf_event_context *ctx,
  {
  	int is_active = ctx->is_active;
  	struct perf_event *event;
+	struct group_sched_params params = {
+			.cpuctx = cpuctx,
+			.ctx = ctx,
+			.can_add_hw = 0
+	};
+	int cpu = smp_processor_id();

  	lockdep_assert_held(&ctx->lock);

@@ -2751,13 +3044,13 @@ static void ctx_sched_out(struct 
perf_event_context *ctx,

  	perf_pmu_disable(ctx->pmu);
  	if (is_active & EVENT_PINNED) {
-		list_for_each_entry(event, &ctx->pinned_groups, group_entry)
-			group_sched_out(event, cpuctx, ctx);
+		perf_event_groups_iterate(&ctx->pinned_groups,
+				group_sched_out_callback, &params);
  	}

  	if (is_active & EVENT_FLEXIBLE) {
-		list_for_each_entry(event, &ctx->flexible_groups, group_entry)
-			group_sched_out(event, cpuctx, ctx);
+		perf_event_groups_iterate(&ctx->flexible_groups,
+				group_sched_out_callback, &params);
  	}
  	perf_pmu_enable(ctx->pmu);
  }
@@ -3052,72 +3345,17 @@ static void cpu_ctx_sched_out(struct 
perf_cpu_context *cpuctx,
  }

  static void
-ctx_pinned_sched_in(struct perf_event_context *ctx,
-		    struct perf_cpu_context *cpuctx)
-{
-	struct perf_event *event;
-
-	list_for_each_entry(event, &ctx->pinned_groups, group_entry) {
-		if (event->state <= PERF_EVENT_STATE_OFF)
-			continue;
-		if (!event_filter_match(event))
-			continue;
-
-		/* may need to reset tstamp_enabled */
-		if (is_cgroup_event(event))
-			perf_cgroup_mark_enabled(event, ctx);
-
-		if (group_can_go_on(event, cpuctx, 1))
-			group_sched_in(event, cpuctx, ctx);
-
-		/*
-		 * If this pinned group hasn't been scheduled,
-		 * put it in error state.
-		 */
-		if (event->state == PERF_EVENT_STATE_INACTIVE) {
-			update_group_times(event);
-			event->state = PERF_EVENT_STATE_ERROR;
-		}
-	}
-}
-
-static void
-ctx_flexible_sched_in(struct perf_event_context *ctx,
-		      struct perf_cpu_context *cpuctx)
-{
-	struct perf_event *event;
-	int can_add_hw = 1;
-
-	list_for_each_entry(event, &ctx->flexible_groups, group_entry) {
-		/* Ignore events in OFF or ERROR state */
-		if (event->state <= PERF_EVENT_STATE_OFF)
-			continue;
-		/*
-		 * Listen to the 'cpu' scheduling filter constraint
-		 * of events:
-		 */
-		if (!event_filter_match(event))
-			continue;
-
-		/* may need to reset tstamp_enabled */
-		if (is_cgroup_event(event))
-			perf_cgroup_mark_enabled(event, ctx);
-
-		if (group_can_go_on(event, cpuctx, can_add_hw)) {
-			if (group_sched_in(event, cpuctx, ctx))
-				can_add_hw = 0;
-		}
-	}
-}
-
-static void
  ctx_sched_in(struct perf_event_context *ctx,
  	     struct perf_cpu_context *cpuctx,
  	     enum event_type_t event_type,
  	     struct task_struct *task)
  {
  	int is_active = ctx->is_active;
-	u64 now;
+	struct group_sched_params params = {
+			.cpuctx = cpuctx,
+			.ctx = ctx
+	};
+	int cpu = smp_processor_id();

  	lockdep_assert_held(&ctx->lock);

@@ -3136,7 +3374,7 @@ ctx_sched_in(struct perf_event_context *ctx,

  	if (is_active & EVENT_TIME) {
  		/* start ctx time */
-		now = perf_clock();
+		u64 now = perf_clock();
  		ctx->timestamp = now;
  		perf_cgroup_set_timestamp(task, ctx);
  	}
@@ -3145,12 +3383,17 @@ ctx_sched_in(struct perf_event_context *ctx,
  	 * First go through the list and put on any pinned groups
  	 * in order to give them the best chance of going on.
  	 */
-	if (is_active & EVENT_PINNED)
-		ctx_pinned_sched_in(ctx, cpuctx);
+	if (is_active & EVENT_PINNED) {
+		perf_event_groups_iterate(&ctx->pinned_groups,
+				ctx_pinned_sched_in_callback, &params);
+	}

  	/* Then walk through the lower prio flexible groups */
-	if (is_active & EVENT_FLEXIBLE)
-		ctx_flexible_sched_in(ctx, cpuctx);
+	if (is_active & EVENT_FLEXIBLE) {
+		params.can_add_hw = 1;
+		perf_event_groups_iterate(&ctx->flexible_groups,
+				ctx_flexible_sched_in_callback, &params);
+	}
  }

  static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
@@ -3181,7 +3424,7 @@ static void perf_event_context_sched_in(struct 
perf_event_context *ctx,
  	 * However, if task's ctx is not carrying any pinned
  	 * events, no need to flip the cpuctx's events around.
  	 */
-	if (!list_empty(&ctx->pinned_groups))
+	if (!perf_event_groups_empty(&ctx->pinned_groups))
  		cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
  	perf_event_sched_in(cpuctx, ctx, task);
  	perf_pmu_enable(ctx->pmu);
@@ -3416,8 +3659,12 @@ static void rotate_ctx(struct perf_event_context 
*ctx)
  	 * Rotate the first entry last of non-pinned groups. Rotation might be
  	 * disabled by the inheritance code.
  	 */
-	if (!ctx->rotate_disable)
-		list_rotate_left(&ctx->flexible_groups);
+	if (!ctx->rotate_disable) {
+		int cpu = smp_processor_id();
+
+		perf_event_groups_rotate(&ctx->flexible_groups, -1);
+		perf_event_groups_rotate(&ctx->flexible_groups, cpu);
+	}
  }

  static int perf_rotate_context(struct perf_cpu_context *cpuctx)
@@ -3743,8 +3990,8 @@ static void __perf_event_init_context(struct 
perf_event_context *ctx)
  	raw_spin_lock_init(&ctx->lock);
  	mutex_init(&ctx->mutex);
  	INIT_LIST_HEAD(&ctx->active_ctx_list);
-	INIT_LIST_HEAD(&ctx->pinned_groups);
-	INIT_LIST_HEAD(&ctx->flexible_groups);
+	perf_event_groups_init(&ctx->pinned_groups);
+	perf_event_groups_init(&ctx->flexible_groups);
  	INIT_LIST_HEAD(&ctx->event_list);
  	atomic_set(&ctx->refcount, 1);
  }
@@ -9379,6 +9626,9 @@ perf_event_alloc(struct perf_event_attr *attr, int 
cpu,
  	INIT_LIST_HEAD(&event->group_entry);
  	INIT_LIST_HEAD(&event->event_entry);
  	INIT_LIST_HEAD(&event->sibling_list);
+	RB_CLEAR_NODE(&event->group_node);
+	INIT_LIST_HEAD(&event->group_list);
+	INIT_LIST_HEAD(&event->group_list_entry);
  	INIT_LIST_HEAD(&event->rb_entry);
  	INIT_LIST_HEAD(&event->active_entry);
  	INIT_LIST_HEAD(&event->addr_filters.list);
@@ -10816,6 +11066,23 @@ inherit_task_group(struct perf_event *event, 
struct task_struct *parent,
  	return ret;
  }

+struct inherit_task_group_params {
+	struct task_struct *parent;
+	struct perf_event_context *parent_ctx;
+	struct task_struct *child;
+	int ctxn;
+	int inherited_all;
+};
+
+static int
+inherit_task_group_callback(struct perf_event *event, void *data)
+{
+	struct inherit_task_group_params *params = data;
+
+	return inherit_task_group(event, params->parent, params->parent_ctx,
+			params->child, params->ctxn, &params->inherited_all);
+}
+
  /*
   * Initialize the perf_event context in task_struct
   */
@@ -10825,9 +11092,14 @@ static int perf_event_init_context(struct 
task_struct *child, int ctxn)
  	struct perf_event_context *cloned_ctx;
  	struct perf_event *event;
  	struct task_struct *parent = current;
-	int inherited_all = 1;
  	unsigned long flags;
  	int ret = 0;
+	struct inherit_task_group_params params = {
+			.parent = parent,
+			.child = child,
+			.ctxn = ctxn,
+			.inherited_all = 1
+	};

  	if (likely(!parent->perf_event_ctxp[ctxn]))
  		return 0;
@@ -10840,6 +11112,8 @@ static int perf_event_init_context(struct 
task_struct *child, int ctxn)
  	if (!parent_ctx)
  		return 0;

+	params.parent_ctx = parent_ctx;
+
  	/*
  	 * No need to check if parent_ctx != NULL here; since we saw
  	 * it non-NULL earlier, the only reason for it to become NULL
@@ -10857,13 +11131,10 @@ static int perf_event_init_context(struct 
task_struct *child, int ctxn)
  	 * We dont have to disable NMIs - we are only looking at
  	 * the list, not manipulating it:
  	 */
-	list_for_each_entry(event, &parent_ctx->pinned_groups, group_entry) {
-		ret = inherit_task_group(event, parent, parent_ctx,
-					 child, ctxn, &inherited_all);
-		if (ret)
-			goto out_unlock;
-	}
-
+	ret = perf_event_groups_iterate(&parent_ctx->pinned_groups,
+			inherit_task_group_callback, &params);
+	if (ret)
+		goto out_unlock;
  	/*
  	 * We can't hold ctx->lock when iterating the ->flexible_group list due
  	 * to allocations, but we need to prevent rotation because
@@ -10873,19 +11144,17 @@ static int perf_event_init_context(struct 
task_struct *child, int ctxn)
  	parent_ctx->rotate_disable = 1;
  	raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);

-	list_for_each_entry(event, &parent_ctx->flexible_groups, group_entry) {
-		ret = inherit_task_group(event, parent, parent_ctx,
-					 child, ctxn, &inherited_all);
-		if (ret)
-			goto out_unlock;
-	}
+	ret = perf_event_groups_iterate(&parent_ctx->flexible_groups,
+			inherit_task_group_callback, &params);
+	if (ret)
+		goto out_unlock;

  	raw_spin_lock_irqsave(&parent_ctx->lock, flags);
  	parent_ctx->rotate_disable = 0;

  	child_ctx = child->perf_event_ctxp[ctxn];

-	if (child_ctx && inherited_all) {
+	if (child_ctx && params.inherited_all) {
  		/*
  		 * Mark the child context as a clone of the parent
  		 * context, or of whatever the parent is a clone of.

Powered by blists - more mailing lists