1 files changed, 198 insertions, 122 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 78ae7b6f90fd..9efd0d7775e7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -375,6 +375,7 @@ enum event_type_t {
 	EVENT_TIME = 0x4,
 	/* see ctx_resched() for details */
 	EVENT_CPU = 0x8,
+	EVENT_CGROUP = 0x10,
 	EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
 };
 
@@ -449,8 +450,8 @@ static void update_perf_cpu_limits(void)
 
 static bool perf_rotate_context(struct perf_cpu_pmu_context *cpc);
 
-int perf_proc_update_handler(struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos)
+int perf_event_max_sample_rate_handler(struct ctl_table *table, int write,
+				       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
 	int perf_cpu = sysctl_perf_cpu_time_max_percent;
@@ -684,20 +685,26 @@ do {									\
 	___p;								\
 })
 
-static void perf_ctx_disable(struct perf_event_context *ctx)
+static void perf_ctx_disable(struct perf_event_context *ctx, bool cgroup)
 {
 	struct perf_event_pmu_context *pmu_ctx;
 
-	list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry)
+	list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
+		if (cgroup && !pmu_ctx->nr_cgroups)
+			continue;
 		perf_pmu_disable(pmu_ctx->pmu);
+	}
 }
 
-static void perf_ctx_enable(struct perf_event_context *ctx)
+static void perf_ctx_enable(struct perf_event_context *ctx, bool cgroup)
 {
 	struct perf_event_pmu_context *pmu_ctx;
 
-	list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry)
+	list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
+		if (cgroup && !pmu_ctx->nr_cgroups)
+			continue;
 		perf_pmu_enable(pmu_ctx->pmu);
+	}
 }
 
 static void ctx_sched_out(struct perf_event_context *ctx, enum event_type_t event_type);
@@ -856,9 +863,9 @@ static void perf_cgroup_switch(struct task_struct *task)
 		return;
 
 	perf_ctx_lock(cpuctx, cpuctx->task_ctx);
-	perf_ctx_disable(&cpuctx->ctx);
+	perf_ctx_disable(&cpuctx->ctx, true);
 
-	ctx_sched_out(&cpuctx->ctx, EVENT_ALL);
+	ctx_sched_out(&cpuctx->ctx, EVENT_ALL|EVENT_CGROUP);
 	/*
 	 * must not be done before ctxswout due
 	 * to update_cgrp_time_from_cpuctx() in
@@ -870,9 +877,9 @@ static void perf_cgroup_switch(struct task_struct *task)
 	 * perf_cgroup_set_timestamp() in ctx_sched_in()
 	 * to not have to pass task around
 	 */
-	ctx_sched_in(&cpuctx->ctx, EVENT_ALL);
+	ctx_sched_in(&cpuctx->ctx, EVENT_ALL|EVENT_CGROUP);
 
-	perf_ctx_enable(&cpuctx->ctx);
+	perf_ctx_enable(&cpuctx->ctx, true);
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 }
 
@@ -965,6 +972,8 @@ perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ct
 	if (!is_cgroup_event(event))
 		return;
 
+	event->pmu_ctx->nr_cgroups++;
+
 	/*
 	 * Because cgroup events are always per-cpu events,
 	 * @ctx == &cpuctx->ctx.
@@ -985,6 +994,8 @@ perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *c
 	if (!is_cgroup_event(event))
 		return;
 
+	event->pmu_ctx->nr_cgroups--;
+
 	/*
 	 * Because cgroup events are always per-cpu events,
 	 * @ctx == &cpuctx->ctx.
@@ -1803,31 +1814,34 @@ static inline void perf_event__state_init(struct perf_event *event)
 					      PERF_EVENT_STATE_INACTIVE;
 }
 
-static void __perf_event_read_size(struct perf_event *event, int nr_siblings)
+static int __perf_event_read_size(u64 read_format, int nr_siblings)
 {
 	int entry = sizeof(u64); /* value */
 	int size = 0;
 	int nr = 1;
 
-	if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
 		size += sizeof(u64);
 
-	if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
 		size += sizeof(u64);
 
-	if (event->attr.read_format & PERF_FORMAT_ID)
+	if (read_format & PERF_FORMAT_ID)
 		entry += sizeof(u64);
 
-	if (event->attr.read_format & PERF_FORMAT_LOST)
+	if (read_format & PERF_FORMAT_LOST)
 		entry += sizeof(u64);
 
-	if (event->attr.read_format & PERF_FORMAT_GROUP) {
+	if (read_format & PERF_FORMAT_GROUP) {
 		nr += nr_siblings;
 		size += sizeof(u64);
 	}
 
-	size += entry * nr;
-	event->read_size = size;
+	/*
+	 * Since perf_event_validate_size() limits this to 16k and inhibits
+	 * adding more siblings, this will never overflow.
+	 */
+	return size + nr * entry;
 }
 
 static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
@@ -1877,8 +1891,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
  */
 static void perf_event__header_size(struct perf_event *event)
 {
-	__perf_event_read_size(event,
-			       event->group_leader->nr_siblings);
+	event->read_size =
+		__perf_event_read_size(event->attr.read_format,
+				       event->group_leader->nr_siblings);
 	__perf_event_header_size(event, event->attr.sample_type);
 }
 
@@ -1909,23 +1924,44 @@ static void perf_event__id_header_size(struct perf_event *event)
 	event->id_header_size = size;
 }
 
+/*
+ * Check that adding an event to the group does not result in anybody
+ * overflowing the 64k event limit imposed by the output buffer.
+ *
+ * Specifically, check that the read_size for the event does not exceed 16k,
+ * read_size being the one term that grows with groups size. Since read_size
+ * depends on per-event read_format, also (re)check the existing events.
+ *
+ * This leaves 48k for the constant size fields and things like callchains,
+ * branch stacks and register sets.
+ */
 static bool perf_event_validate_size(struct perf_event *event)
 {
-	/*
-	 * The values computed here will be over-written when we actually
-	 * attach the event.
-	 */
-	__perf_event_read_size(event, event->group_leader->nr_siblings + 1);
-	__perf_event_header_size(event, event->attr.sample_type & ~PERF_SAMPLE_READ);
-	perf_event__id_header_size(event);
+	struct perf_event *sibling, *group_leader = event->group_leader;
+
+	if (__perf_event_read_size(event->attr.read_format,
+				   group_leader->nr_siblings + 1) > 16*1024)
+		return false;
+
+	if (__perf_event_read_size(group_leader->attr.read_format,
+				   group_leader->nr_siblings + 1) > 16*1024)
+		return false;
 
 	/*
-	 * Sum the lot; should not exceed the 64k limit we have on records.
-	 * Conservative limit to allow for callchains and other variable fields.
+	 * When creating a new group leader, group_leader->ctx is initialized
+	 * after the size has been validated, but we cannot safely use
+	 * for_each_sibling_event() until group_leader->ctx is set. A new group
+	 * leader cannot have any siblings yet, so we can safely skip checking
+	 * the non-existent siblings.
 	 */
-	if (event->read_size + event->header_size +
-	    event->id_header_size + sizeof(struct perf_event_header) >= 16*1024)
-		return false;
+	if (event == group_leader)
+		return true;
+
+	for_each_sibling_event(sibling, group_leader) {
+		if (__perf_event_read_size(sibling->attr.read_format,
+					   group_leader->nr_siblings + 1) > 16*1024)
+			return false;
+	}
 
 	return true;
 }
@@ -1954,6 +1990,7 @@ static void perf_group_attach(struct perf_event *event)
 
 	list_add_tail(&event->sibling_list, &group_leader->sibling_list);
 	group_leader->nr_siblings++;
+	group_leader->group_generation++;
 
 	perf_event__header_size(group_leader);
 
@@ -2144,6 +2181,7 @@ static void perf_group_detach(struct perf_event *event)
 	if (leader != event) {
 		list_del_init(&event->sibling_list);
 		event->group_leader->nr_siblings--;
+		event->group_leader->group_generation++;
 		goto out;
 	}
 
@@ -2677,9 +2715,9 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
 
 	event_type &= EVENT_ALL;
 
-	perf_ctx_disable(&cpuctx->ctx);
+	perf_ctx_disable(&cpuctx->ctx, false);
 	if (task_ctx) {
-		perf_ctx_disable(task_ctx);
+		perf_ctx_disable(task_ctx, false);
 		task_ctx_sched_out(task_ctx, event_type);
 	}
 
@@ -2697,9 +2735,9 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
 
 	perf_event_sched_in(cpuctx, task_ctx);
 
-	perf_ctx_enable(&cpuctx->ctx);
+	perf_ctx_enable(&cpuctx->ctx, false);
 	if (task_ctx)
-		perf_ctx_enable(task_ctx);
+		perf_ctx_enable(task_ctx, false);
 }
 
 void perf_pmu_resched(struct pmu *pmu)
@@ -3244,6 +3282,9 @@ 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);
 
@@ -3290,8 +3331,11 @@ 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)
+	list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
+		if (cgroup && !pmu_ctx->nr_cgroups)
+			continue;
 		__pmu_ctx_sched_out(pmu_ctx, is_active);
+	}
 }
 
 /*
@@ -3482,7 +3526,7 @@ 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);
+			perf_ctx_disable(ctx, false);
 
 			/* PMIs are disabled; ctx->nr_pending is stable. */
 			if (local_read(&ctx->nr_pending) ||
@@ -3502,7 +3546,7 @@ 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);
+			perf_ctx_enable(ctx, false);
 
 			/*
 			 * RCU_INIT_POINTER here is safe because we've not
@@ -3526,13 +3570,13 @@ unlock:
 
 	if (do_switch) {
 		raw_spin_lock(&ctx->lock);
-		perf_ctx_disable(ctx);
+		perf_ctx_disable(ctx, false);
 
 inside_switch:
 		perf_ctx_sched_task_cb(ctx, false);
 		task_ctx_sched_out(ctx, EVENT_ALL);
 
-		perf_ctx_enable(ctx);
+		perf_ctx_enable(ctx, false);
 		raw_spin_unlock(&ctx->lock);
 	}
 }
@@ -3818,47 +3862,32 @@ static int merge_sched_in(struct perf_event *event, void *data)
 	return 0;
 }
 
-static void ctx_pinned_sched_in(struct perf_event_context *ctx, struct pmu *pmu)
+static void pmu_groups_sched_in(struct perf_event_context *ctx,
+				struct perf_event_groups *groups,
+				struct pmu *pmu)
 {
-	struct perf_event_pmu_context *pmu_ctx;
 	int can_add_hw = 1;
-
-	if (pmu) {
-		visit_groups_merge(ctx, &ctx->pinned_groups,
-				   smp_processor_id(), pmu,
-				   merge_sched_in, &can_add_hw);
-	} else {
-		list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
-			can_add_hw = 1;
-			visit_groups_merge(ctx, &ctx->pinned_groups,
-					   smp_processor_id(), pmu_ctx->pmu,
-					   merge_sched_in, &can_add_hw);
-		}
-	}
+	visit_groups_merge(ctx, groups, smp_processor_id(), pmu,
+			   merge_sched_in, &can_add_hw);
 }
 
-static void ctx_flexible_sched_in(struct perf_event_context *ctx, struct pmu *pmu)
+static void ctx_groups_sched_in(struct perf_event_context *ctx,
+				struct perf_event_groups *groups,
+				bool cgroup)
 {
 	struct perf_event_pmu_context *pmu_ctx;
-	int can_add_hw = 1;
 
-	if (pmu) {
-		visit_groups_merge(ctx, &ctx->flexible_groups,
-				   smp_processor_id(), pmu,
-				   merge_sched_in, &can_add_hw);
-	} else {
-		list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
-			can_add_hw = 1;
-			visit_groups_merge(ctx, &ctx->flexible_groups,
-					   smp_processor_id(), pmu_ctx->pmu,
-					   merge_sched_in, &can_add_hw);
-		}
+	list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) {
+		if (cgroup && !pmu_ctx->nr_cgroups)
+			continue;
+		pmu_groups_sched_in(ctx, groups, pmu_ctx->pmu);
 	}
 }
 
-static void __pmu_ctx_sched_in(struct perf_event_context *ctx, struct pmu *pmu)
+static void __pmu_ctx_sched_in(struct perf_event_context *ctx,
+			       struct pmu *pmu)
 {
-	ctx_flexible_sched_in(ctx, pmu);
+	pmu_groups_sched_in(ctx, &ctx->flexible_groups, pmu);
 }
 
 static void
@@ -3866,6 +3895,9 @@ 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);
 
@@ -3898,11 +3930,11 @@ 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_pinned_sched_in(ctx, NULL);
+		ctx_groups_sched_in(ctx, &ctx->pinned_groups, cgroup);
 
 	/* Then walk through the lower prio flexible groups */
 	if (is_active & EVENT_FLEXIBLE)
-		ctx_flexible_sched_in(ctx, NULL);
+		ctx_groups_sched_in(ctx, &ctx->flexible_groups, cgroup);
 }
 
 static void perf_event_context_sched_in(struct task_struct *task)
@@ -3917,11 +3949,11 @@ 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);
+		perf_ctx_disable(ctx, false);
 
 		perf_ctx_sched_task_cb(ctx, true);
 
-		perf_ctx_enable(ctx);
+		perf_ctx_enable(ctx, false);
 		perf_ctx_unlock(cpuctx, ctx);
 		goto rcu_unlock;
 	}
@@ -3934,7 +3966,7 @@ static void perf_event_context_sched_in(struct task_struct *task)
 	if (!ctx->nr_events)
 		goto unlock;
 
-	perf_ctx_disable(ctx);
+	perf_ctx_disable(ctx, false);
 	/*
 	 * We want to keep the following priority order:
 	 * cpu pinned (that don't need to move), task pinned,
@@ -3944,7 +3976,7 @@ 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);
+		perf_ctx_disable(&cpuctx->ctx, false);
 		ctx_sched_out(&cpuctx->ctx, EVENT_FLEXIBLE);
 	}
 
@@ -3953,9 +3985,9 @@ 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);
+		perf_ctx_enable(&cpuctx->ctx, false);
 
-	perf_ctx_enable(ctx);
+	perf_ctx_enable(ctx, false);
 
 unlock:
 	perf_ctx_unlock(cpuctx, ctx);
@@ -4425,6 +4457,9 @@ static int __perf_event_read_cpu(struct perf_event *event, int event_cpu)
 {
 	u16 local_pkg, event_pkg;
 
+	if ((unsigned)event_cpu >= nr_cpu_ids)
+		return event_cpu;
+
 	if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) {
 		int local_cpu = smp_processor_id();
 
@@ -4527,6 +4562,8 @@ int perf_event_read_local(struct perf_event *event, u64 *value,
 			  u64 *enabled, u64 *running)
 {
 	unsigned long flags;
+	int event_oncpu;
+	int event_cpu;
 	int ret = 0;
 
 	/*
@@ -4551,15 +4588,22 @@ int perf_event_read_local(struct perf_event *event, u64 *value,
 		goto out;
 	}
 
+	/*
+	 * Get the event CPU numbers, and adjust them to local if the event is
+	 * a per-package event that can be read locally
+	 */
+	event_oncpu = __perf_event_read_cpu(event, event->oncpu);
+	event_cpu = __perf_event_read_cpu(event, event->cpu);
+
 	/* If this is a per-CPU event, it must be for this CPU */
 	if (!(event->attach_state & PERF_ATTACH_TASK) &&
-	    event->cpu != smp_processor_id()) {
+	    event_cpu != smp_processor_id()) {
 		ret = -EINVAL;
 		goto out;
 	}
 
 	/* If this is a pinned event it must be running on this CPU */
-	if (event->attr.pinned && event->oncpu != smp_processor_id()) {
+	if (event->attr.pinned && event_oncpu != smp_processor_id()) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -4569,7 +4613,7 @@ int perf_event_read_local(struct perf_event *event, u64 *value,
 	 * or local to this CPU. Furthermore it means its ACTIVE (otherwise
 	 * oncpu == -1).
 	 */
-	if (event->oncpu == smp_processor_id())
+	if (event_oncpu == smp_processor_id())
 		event->pmu->read(event);
 
 	*value = local64_read(&event->count);
@@ -4809,6 +4853,11 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
 	void *task_ctx_data = NULL;
 
 	if (!ctx->task) {
+		/*
+		 * perf_pmu_migrate_context() / __perf_pmu_install_event()
+		 * relies on the fact that find_get_pmu_context() cannot fail
+		 * for CPU contexts.
+		 */
 		struct perf_cpu_pmu_context *cpc;
 
 		cpc = per_cpu_ptr(pmu->cpu_pmu_context, event->cpu);
@@ -5440,7 +5489,7 @@ static int __perf_read_group_add(struct perf_event *leader,
 					u64 read_format, u64 *values)
 {
 	struct perf_event_context *ctx = leader->ctx;
-	struct perf_event *sub;
+	struct perf_event *sub, *parent;
 	unsigned long flags;
 	int n = 1; /* skip @nr */
 	int ret;
@@ -5450,6 +5499,33 @@ static int __perf_read_group_add(struct perf_event *leader,
 		return ret;
 
 	raw_spin_lock_irqsave(&ctx->lock, flags);
+	/*
+	 * Verify the grouping between the parent and child (inherited)
+	 * events is still in tact.
+	 *
+	 * Specifically:
+	 *  - leader->ctx->lock pins leader->sibling_list
+	 *  - parent->child_mutex pins parent->child_list
+	 *  - parent->ctx->mutex pins parent->sibling_list
+	 *
+	 * Because parent->ctx != leader->ctx (and child_list nests inside
+	 * ctx->mutex), group destruction is not atomic between children, also
+	 * see perf_event_release_kernel(). Additionally, parent can grow the
+	 * group.
+	 *
+	 * Therefore it is possible to have parent and child groups in a
+	 * different configuration and summing over such a beast makes no sense
+	 * what so ever.
+	 *
+	 * Reject this.
+	 */
+	parent = leader->parent;
+	if (parent &&
+	    (parent->group_generation != leader->group_generation ||
+	     parent->nr_siblings != leader->nr_siblings)) {
+		ret = -ECHILD;
+		goto unlock;
+	}
 
 	/*
 	 * Since we co-schedule groups, {enabled,running} times of siblings
@@ -5483,8 +5559,9 @@ static int __perf_read_group_add(struct perf_event *leader,
 			values[n++] = atomic64_read(&sub->lost_samples);
 	}
 
+unlock:
 	raw_spin_unlock_irqrestore(&ctx->lock, flags);
-	return 0;
+	return ret;
 }
 
 static int perf_read_group(struct perf_event *event,
@@ -5503,10 +5580,6 @@ static int perf_read_group(struct perf_event *event,
 
 	values[0] = 1 + leader->nr_siblings;
 
-	/*
-	 * By locking the child_mutex of the leader we effectively
-	 * lock the child list of all siblings.. XXX explain how.
-	 */
 	mutex_lock(&leader->child_mutex);
 
 	ret = __perf_read_group_add(leader, read_format, values);
@@ -8249,7 +8322,7 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
 	unsigned int size;
 
 	memset(comm, 0, sizeof(comm));
-	strlcpy(comm, comm_event->task->comm, sizeof(comm));
+	strscpy(comm, comm_event->task->comm, sizeof(comm));
 	size = ALIGN(strlen(comm)+1, sizeof(u64));
 
 	comm_event->comm = comm;
@@ -8631,7 +8704,7 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 	unsigned int size;
 	char tmp[16];
 	char *buf = NULL;
-	char *name;
+	char *name = NULL;
 
 	if (vma->vm_flags & VM_READ)
 		prot |= PROT_READ;
@@ -8678,33 +8751,22 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 
 		goto got_name;
 	} else {
-		if (vma->vm_ops && vma->vm_ops->name) {
+		if (vma->vm_ops && vma->vm_ops->name)
 			name = (char *) vma->vm_ops->name(vma);
-			if (name)
-				goto cpy_name;
+		if (!name)
+			name = (char *)arch_vma_name(vma);
+		if (!name) {
+			if (vma_is_initial_heap(vma))
+				name = "[heap]";
+			else if (vma_is_initial_stack(vma))
+				name = "[stack]";
+			else
+				name = "//anon";
 		}
-
-		name = (char *)arch_vma_name(vma);
-		if (name)
-			goto cpy_name;
-
-		if (vma->vm_start <= vma->vm_mm->start_brk &&
-				vma->vm_end >= vma->vm_mm->brk) {
-			name = "[heap]";
-			goto cpy_name;
-		}
-		if (vma->vm_start <= vma->vm_mm->start_stack &&
-				vma->vm_end >= vma->vm_mm->start_stack) {
-			name = "[stack]";
-			goto cpy_name;
-		}
-
-		name = "//anon";
-		goto cpy_name;
 	}
 
 cpy_name:
-	strlcpy(tmp, name, sizeof(tmp));
+	strscpy(tmp, name, sizeof(tmp));
 	name = tmp;
 got_name:
 	/*
@@ -9128,7 +9190,7 @@ void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister,
 	    ksym_type == PERF_RECORD_KSYMBOL_TYPE_UNKNOWN)
 		goto err;
 
-	strlcpy(name, sym, KSYM_NAME_LEN);
+	strscpy(name, sym, KSYM_NAME_LEN);
 	name_len = strlen(name) + 1;
 	while (!IS_ALIGNED(name_len, sizeof(u64)))
 		name[name_len++] = '\0';
@@ -9595,16 +9657,16 @@ u64 perf_swevent_set_period(struct perf_event *event)
 
 	hwc->last_period = hwc->sample_period;
 
-again:
-	old = val = local64_read(&hwc->period_left);
-	if (val < 0)
-		return 0;
+	old = local64_read(&hwc->period_left);
+	do {
+		val = old;
+		if (val < 0)
+			return 0;
 
-	nr = div64_u64(period + val, period);
-	offset = nr * period;
-	val -= offset;
-	if (local64_cmpxchg(&hwc->period_left, old, val) != old)
-		goto again;
+		nr = div64_u64(period + val, period);
+		offset = nr * period;
+		val -= offset;
+	} while (!local64_try_cmpxchg(&hwc->period_left, &old, val));
 
 	return nr;
 }
@@ -12857,6 +12919,9 @@ static void __perf_pmu_install_event(struct pmu *pmu,
 				     int cpu, struct perf_event *event)
 {
 	struct perf_event_pmu_context *epc;
+	struct perf_event_context *old_ctx = event->ctx;
+
+	get_ctx(ctx); /* normally find_get_context() */
 
 	event->cpu = cpu;
 	epc = find_get_pmu_context(pmu, ctx, event);
@@ -12865,6 +12930,11 @@ static void __perf_pmu_install_event(struct pmu *pmu,
 	if (event->state >= PERF_EVENT_STATE_OFF)
 		event->state = PERF_EVENT_STATE_INACTIVE;
 	perf_install_in_context(ctx, event, cpu);
+
+	/*
+	 * Now that event->ctx is updated and visible, put the old ctx.
+	 */
+	put_ctx(old_ctx);
 }
 
 static void __perf_pmu_install(struct perf_event_context *ctx,
@@ -12903,6 +12973,10 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 	struct perf_event_context *src_ctx, *dst_ctx;
 	LIST_HEAD(events);
 
+	/*
+	 * Since per-cpu context is persistent, no need to grab an extra
+	 * reference.
+	 */
 	src_ctx = &per_cpu_ptr(&perf_cpu_context, src_cpu)->ctx;
 	dst_ctx = &per_cpu_ptr(&perf_cpu_context, dst_cpu)->ctx;
 
@@ -13357,6 +13431,8 @@ static int inherit_group(struct perf_event *parent_event,
 		    !perf_get_aux_event(child_ctr, leader))
 			return -EINVAL;
 	}
+	if (leader)
+		leader->group_generation = parent_event->group_generation;
 	return 0;
 }