1 files changed, 106 insertions, 85 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index f04daabfd1cf..af924bc38121 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -153,7 +153,7 @@ enum event_type_t {
  */
 struct static_key_deferred perf_sched_events __read_mostly;
 static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
-static DEFINE_PER_CPU(atomic_t, perf_branch_stack_events);
+static DEFINE_PER_CPU(int, perf_sched_cb_usages);
 
 static atomic_t nr_mmap_events __read_mostly;
 static atomic_t nr_comm_events __read_mostly;
@@ -905,6 +905,15 @@ static void get_ctx(struct perf_event_context *ctx)
 	WARN_ON(!atomic_inc_not_zero(&ctx->refcount));
 }
 
+static void free_ctx(struct rcu_head *head)
+{
+	struct perf_event_context *ctx;
+
+	ctx = container_of(head, struct perf_event_context, rcu_head);
+	kfree(ctx->task_ctx_data);
+	kfree(ctx);
+}
+
 static void put_ctx(struct perf_event_context *ctx)
 {
 	if (atomic_dec_and_test(&ctx->refcount)) {
@@ -912,7 +921,7 @@ static void put_ctx(struct perf_event_context *ctx)
 			put_ctx(ctx->parent_ctx);
 		if (ctx->task)
 			put_task_struct(ctx->task);
-		kfree_rcu(ctx, rcu_head);
+		call_rcu(&ctx->rcu_head, free_ctx);
 	}
 }
 
@@ -1239,9 +1248,6 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 	if (is_cgroup_event(event))
 		ctx->nr_cgroups++;
 
-	if (has_branch_stack(event))
-		ctx->nr_branch_stack++;
-
 	list_add_rcu(&event->event_entry, &ctx->event_list);
 	ctx->nr_events++;
 	if (event->attr.inherit_stat)
@@ -1408,9 +1414,6 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 			cpuctx->cgrp = NULL;
 	}
 
-	if (has_branch_stack(event))
-		ctx->nr_branch_stack--;
-
 	ctx->nr_events--;
 	if (event->attr.inherit_stat)
 		ctx->nr_stat--;
@@ -1881,6 +1884,10 @@ event_sched_in(struct perf_event *event,
 
 	perf_pmu_disable(event->pmu);
 
+	event->tstamp_running += tstamp - event->tstamp_stopped;
+
+	perf_set_shadow_time(event, ctx, tstamp);
+
 	if (event->pmu->add(event, PERF_EF_START)) {
 		event->state = PERF_EVENT_STATE_INACTIVE;
 		event->oncpu = -1;
@@ -1888,10 +1895,6 @@ event_sched_in(struct perf_event *event,
 		goto out;
 	}
 
-	event->tstamp_running += tstamp - event->tstamp_stopped;
-
-	perf_set_shadow_time(event, ctx, tstamp);
-
 	if (!is_software_event(event))
 		cpuctx->active_oncpu++;
 	if (!ctx->nr_active++)
@@ -2559,6 +2562,9 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 			next->perf_event_ctxp[ctxn] = ctx;
 			ctx->task = next;
 			next_ctx->task = task;
+
+			swap(ctx->task_ctx_data, next_ctx->task_ctx_data);
+
 			do_switch = 0;
 
 			perf_event_sync_stat(ctx, next_ctx);
@@ -2577,6 +2583,56 @@ unlock:
 	}
 }
 
+void perf_sched_cb_dec(struct pmu *pmu)
+{
+	this_cpu_dec(perf_sched_cb_usages);
+}
+
+void perf_sched_cb_inc(struct pmu *pmu)
+{
+	this_cpu_inc(perf_sched_cb_usages);
+}
+
+/*
+ * This function provides the context switch callback to the lower code
+ * layer. It is invoked ONLY when the context switch callback is enabled.
+ */
+static void perf_pmu_sched_task(struct task_struct *prev,
+				struct task_struct *next,
+				bool sched_in)
+{
+	struct perf_cpu_context *cpuctx;
+	struct pmu *pmu;
+	unsigned long flags;
+
+	if (prev == next)
+		return;
+
+	local_irq_save(flags);
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		if (pmu->sched_task) {
+			cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+
+			perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+
+			perf_pmu_disable(pmu);
+
+			pmu->sched_task(cpuctx->task_ctx, sched_in);
+
+			perf_pmu_enable(pmu);
+
+			perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
+		}
+	}
+
+	rcu_read_unlock();
+
+	local_irq_restore(flags);
+}
+
 #define for_each_task_context_nr(ctxn)					\
 	for ((ctxn) = 0; (ctxn) < perf_nr_task_contexts; (ctxn)++)
 
@@ -2596,6 +2652,9 @@ void __perf_event_task_sched_out(struct task_struct *task,
 {
 	int ctxn;
 
+	if (__this_cpu_read(perf_sched_cb_usages))
+		perf_pmu_sched_task(task, next, false);
+
 	for_each_task_context_nr(ctxn)
 		perf_event_context_sched_out(task, ctxn, next);
 
@@ -2755,64 +2814,6 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
 }
 
 /*
- * When sampling the branck stack in system-wide, it may be necessary
- * to flush the stack on context switch. This happens when the branch
- * stack does not tag its entries with the pid of the current task.
- * Otherwise it becomes impossible to associate a branch entry with a
- * task. This ambiguity is more likely to appear when the branch stack
- * supports priv level filtering and the user sets it to monitor only
- * at the user level (which could be a useful measurement in system-wide
- * mode). In that case, the risk is high of having a branch stack with
- * branch from multiple tasks. Flushing may mean dropping the existing
- * entries or stashing them somewhere in the PMU specific code layer.
- *
- * This function provides the context switch callback to the lower code
- * layer. It is invoked ONLY when there is at least one system-wide context
- * with at least one active event using taken branch sampling.
- */
-static void perf_branch_stack_sched_in(struct task_struct *prev,
-				       struct task_struct *task)
-{
-	struct perf_cpu_context *cpuctx;
-	struct pmu *pmu;
-	unsigned long flags;
-
-	/* no need to flush branch stack if not changing task */
-	if (prev == task)
-		return;
-
-	local_irq_save(flags);
-
-	rcu_read_lock();
-
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
-
-		/*
-		 * check if the context has at least one
-		 * event using PERF_SAMPLE_BRANCH_STACK
-		 */
-		if (cpuctx->ctx.nr_branch_stack > 0
-		    && pmu->flush_branch_stack) {
-
-			perf_ctx_lock(cpuctx, cpuctx->task_ctx);
-
-			perf_pmu_disable(pmu);
-
-			pmu->flush_branch_stack();
-
-			perf_pmu_enable(pmu);
-
-			perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
-		}
-	}
-
-	rcu_read_unlock();
-
-	local_irq_restore(flags);
-}
-
-/*
  * Called from scheduler to add the events of the current task
  * with interrupts disabled.
  *
@@ -2844,9 +2845,8 @@ void __perf_event_task_sched_in(struct task_struct *prev,
 	if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
 		perf_cgroup_sched_in(prev, task);
 
-	/* check for system-wide branch_stack events */
-	if (atomic_read(this_cpu_ptr(&perf_branch_stack_events)))
-		perf_branch_stack_sched_in(prev, task);
+	if (__this_cpu_read(perf_sched_cb_usages))
+		perf_pmu_sched_task(prev, task, true);
 }
 
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
@@ -3321,12 +3321,15 @@ errout:
  * Returns a matching context with refcount and pincount.
  */
 static struct perf_event_context *
-find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
+find_get_context(struct pmu *pmu, struct task_struct *task,
+		struct perf_event *event)
 {
 	struct perf_event_context *ctx, *clone_ctx = NULL;
 	struct perf_cpu_context *cpuctx;
+	void *task_ctx_data = NULL;
 	unsigned long flags;
 	int ctxn, err;
+	int cpu = event->cpu;
 
 	if (!task) {
 		/* Must be root to operate on a CPU event: */
@@ -3354,11 +3357,24 @@ find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
 	if (ctxn < 0)
 		goto errout;
 
+	if (event->attach_state & PERF_ATTACH_TASK_DATA) {
+		task_ctx_data = kzalloc(pmu->task_ctx_size, GFP_KERNEL);
+		if (!task_ctx_data) {
+			err = -ENOMEM;
+			goto errout;
+		}
+	}
+
 retry:
 	ctx = perf_lock_task_context(task, ctxn, &flags);
 	if (ctx) {
 		clone_ctx = unclone_ctx(ctx);
 		++ctx->pin_count;
+
+		if (task_ctx_data && !ctx->task_ctx_data) {
+			ctx->task_ctx_data = task_ctx_data;
+			task_ctx_data = NULL;
+		}
 		raw_spin_unlock_irqrestore(&ctx->lock, flags);
 
 		if (clone_ctx)
@@ -3369,6 +3385,11 @@ retry:
 		if (!ctx)
 			goto errout;
 
+		if (task_ctx_data) {
+			ctx->task_ctx_data = task_ctx_data;
+			task_ctx_data = NULL;
+		}
+
 		err = 0;
 		mutex_lock(&task->perf_event_mutex);
 		/*
@@ -3395,9 +3416,11 @@ retry:
 		}
 	}
 
+	kfree(task_ctx_data);
 	return ctx;
 
 errout:
+	kfree(task_ctx_data);
 	return ERR_PTR(err);
 }
 
@@ -3423,10 +3446,6 @@ static void unaccount_event_cpu(struct perf_event *event, int cpu)
 	if (event->parent)
 		return;
 
-	if (has_branch_stack(event)) {
-		if (!(event->attach_state & PERF_ATTACH_TASK))
-			atomic_dec(&per_cpu(perf_branch_stack_events, cpu));
-	}
 	if (is_cgroup_event(event))
 		atomic_dec(&per_cpu(perf_cgroup_events, cpu));
 }
@@ -4427,7 +4446,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 	 * If we have rb pages ensure they're a power-of-two number, so we
 	 * can do bitmasks instead of modulo.
 	 */
-	if (nr_pages != 0 && !is_power_of_2(nr_pages))
+	if (!is_power_of_2(nr_pages))
 		return -EINVAL;
 
 	if (vma_size != PAGE_SIZE * (1 + nr_pages))
@@ -6123,6 +6142,7 @@ static int perf_swevent_add(struct perf_event *event, int flags)
 	}
 
 	hlist_add_head_rcu(&event->hlist_entry, head);
+	perf_event_update_userpage(event);
 
 	return 0;
 }
@@ -6592,6 +6612,7 @@ static int cpu_clock_event_add(struct perf_event *event, int flags)
 {
 	if (flags & PERF_EF_START)
 		cpu_clock_event_start(event, flags);
+	perf_event_update_userpage(event);
 
 	return 0;
 }
@@ -6666,6 +6687,7 @@ static int task_clock_event_add(struct perf_event *event, int flags)
 {
 	if (flags & PERF_EF_START)
 		task_clock_event_start(event, flags);
+	perf_event_update_userpage(event);
 
 	return 0;
 }
@@ -7079,10 +7101,6 @@ static void account_event_cpu(struct perf_event *event, int cpu)
 	if (event->parent)
 		return;
 
-	if (has_branch_stack(event)) {
-		if (!(event->attach_state & PERF_ATTACH_TASK))
-			atomic_inc(&per_cpu(perf_branch_stack_events, cpu));
-	}
 	if (is_cgroup_event(event))
 		atomic_inc(&per_cpu(perf_cgroup_events, cpu));
 }
@@ -7214,6 +7232,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP))
 		goto err_ns;
 
+	if (!has_branch_stack(event))
+		event->attr.branch_sample_type = 0;
+
 	pmu = perf_init_event(event);
 	if (!pmu)
 		goto err_ns;
@@ -7576,7 +7597,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	/*
 	 * Get the target context (task or percpu):
 	 */
-	ctx = find_get_context(pmu, task, event->cpu);
+	ctx = find_get_context(pmu, task, event);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
 		goto err_alloc;
@@ -7782,7 +7803,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 
 	account_event(event);
 
-	ctx = find_get_context(event->pmu, task, cpu);
+	ctx = find_get_context(event->pmu, task, event);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
 		goto err_free;