1 files changed, 60 insertions, 16 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index aec8dba2bea4..5de0b801bc7b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1031,7 +1031,7 @@ perf_cgroup_set_timestamp(struct task_struct *task,
 {
 }
 
-void
+static inline void
 perf_cgroup_switch(struct task_struct *task, struct task_struct *next)
 {
 }
@@ -5029,6 +5029,24 @@ static void _perf_event_reset(struct perf_event *event)
 	perf_event_update_userpage(event);
 }
 
+/* Assume it's not an event with inherit set. */
+u64 perf_event_pause(struct perf_event *event, bool reset)
+{
+	struct perf_event_context *ctx;
+	u64 count;
+
+	ctx = perf_event_ctx_lock(event);
+	WARN_ON_ONCE(event->attr.inherit);
+	_perf_event_disable(event);
+	count = local64_read(&event->count);
+	if (reset)
+		local64_set(&event->count, 0);
+	perf_event_ctx_unlock(event, ctx);
+
+	return count;
+}
+EXPORT_SYMBOL_GPL(perf_event_pause);
+
 /*
  * Holding the top-level event's child_mutex means that any
  * descendant process that has inherited this event will block
@@ -5106,16 +5124,11 @@ static int perf_event_check_period(struct perf_event *event, u64 value)
 	return event->pmu->check_period(event, value);
 }
 
-static int perf_event_period(struct perf_event *event, u64 __user *arg)
+static int _perf_event_period(struct perf_event *event, u64 value)
 {
-	u64 value;
-
 	if (!is_sampling_event(event))
 		return -EINVAL;
 
-	if (copy_from_user(&value, arg, sizeof(value)))
-		return -EFAULT;
-
 	if (!value)
 		return -EINVAL;
 
@@ -5133,6 +5146,19 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 	return 0;
 }
 
+int perf_event_period(struct perf_event *event, u64 value)
+{
+	struct perf_event_context *ctx;
+	int ret;
+
+	ctx = perf_event_ctx_lock(event);
+	ret = _perf_event_period(event, value);
+	perf_event_ctx_unlock(event, ctx);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(perf_event_period);
+
 static const struct file_operations perf_fops;
 
 static inline int perf_fget_light(int fd, struct fd *p)
@@ -5176,8 +5202,14 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon
 		return _perf_event_refresh(event, arg);
 
 	case PERF_EVENT_IOC_PERIOD:
-		return perf_event_period(event, (u64 __user *)arg);
+	{
+		u64 value;
 
+		if (copy_from_user(&value, (u64 __user *)arg, sizeof(value)))
+			return -EFAULT;
+
+		return _perf_event_period(event, value);
+	}
 	case PERF_EVENT_IOC_ID:
 	{
 		u64 id = primary_event_id(event);
@@ -10477,12 +10509,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		context = parent_event->overflow_handler_context;
 #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_EVENT_TRACING)
 		if (overflow_handler == bpf_overflow_handler) {
-			struct bpf_prog *prog = bpf_prog_inc(parent_event->prog);
+			struct bpf_prog *prog = parent_event->prog;
 
-			if (IS_ERR(prog)) {
-				err = PTR_ERR(prog);
-				goto err_ns;
-			}
+			bpf_prog_inc(prog);
 			event->prog = prog;
 			event->orig_overflow_handler =
 				parent_event->orig_overflow_handler;
@@ -10535,6 +10564,15 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		goto err_ns;
 	}
 
+	/*
+	 * Disallow uncore-cgroup events, they don't make sense as the cgroup will
+	 * be different on other CPUs in the uncore mask.
+	 */
+	if (pmu->task_ctx_nr == perf_invalid_context && cgroup_fd != -1) {
+		err = -EINVAL;
+		goto err_pmu;
+	}
+
 	if (event->attr.aux_output &&
 	    !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) {
 		err = -EOPNOTSUPP;
@@ -11323,8 +11361,11 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	int err;
 
 	/*
-	 * Get the target context (task or percpu):
+	 * Grouping is not supported for kernel events, neither is 'AUX',
+	 * make sure the caller's intentions are adjusted.
 	 */
+	if (attr->aux_output)
+		return ERR_PTR(-EINVAL);
 
 	event = perf_event_alloc(attr, cpu, task, NULL, NULL,
 				 overflow_handler, context, -1);
@@ -11336,6 +11377,9 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	/* Mark owner so we could distinguish it from user events. */
 	event->owner = TASK_TOMBSTONE;
 
+	/*
+	 * Get the target context (task or percpu):
+	 */
 	ctx = find_get_context(event->pmu, task, event);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
@@ -11787,7 +11831,7 @@ inherit_event(struct perf_event *parent_event,
 						   GFP_KERNEL);
 		if (!child_ctx->task_ctx_data) {
 			free_event(child_event);
-			return NULL;
+			return ERR_PTR(-ENOMEM);
 		}
 	}
 
@@ -11890,7 +11934,7 @@ static int inherit_group(struct perf_event *parent_event,
 		if (IS_ERR(child_ctr))
 			return PTR_ERR(child_ctr);
 
-		if (sub->aux_event == parent_event &&
+		if (sub->aux_event == parent_event && child_ctr &&
 		    !perf_get_aux_event(child_ctr, leader))
 			return -EINVAL;
 	}