1 files changed, 126 insertions, 17 deletions

diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index 534e20d14d6..53abcbefa0b 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -469,7 +469,8 @@ static void update_counter_times(struct perf_counter *counter)
 	struct perf_counter_context *ctx = counter->ctx;
 	u64 run_end;
 
-	if (counter->state < PERF_COUNTER_STATE_INACTIVE)
+	if (counter->state < PERF_COUNTER_STATE_INACTIVE ||
+	    counter->group_leader->state < PERF_COUNTER_STATE_INACTIVE)
 		return;
 
 	counter->total_time_enabled = ctx->time - counter->tstamp_enabled;
@@ -518,7 +519,7 @@ static void __perf_counter_disable(void *info)
 	 */
 	if (counter->state >= PERF_COUNTER_STATE_INACTIVE) {
 		update_context_time(ctx);
-		update_counter_times(counter);
+		update_group_times(counter);
 		if (counter == counter->group_leader)
 			group_sched_out(counter, cpuctx, ctx);
 		else
@@ -573,7 +574,7 @@ static void perf_counter_disable(struct perf_counter *counter)
 	 * in, so we can change the state safely.
 	 */
 	if (counter->state == PERF_COUNTER_STATE_INACTIVE) {
-		update_counter_times(counter);
+		update_group_times(counter);
 		counter->state = PERF_COUNTER_STATE_OFF;
 	}
 
@@ -851,6 +852,27 @@ retry:
 }
 
 /*
+ * Put a counter into inactive state and update time fields.
+ * Enabling the leader of a group effectively enables all
+ * the group members that aren't explicitly disabled, so we
+ * have to update their ->tstamp_enabled also.
+ * Note: this works for group members as well as group leaders
+ * since the non-leader members' sibling_lists will be empty.
+ */
+static void __perf_counter_mark_enabled(struct perf_counter *counter,
+					struct perf_counter_context *ctx)
+{
+	struct perf_counter *sub;
+
+	counter->state = PERF_COUNTER_STATE_INACTIVE;
+	counter->tstamp_enabled = ctx->time - counter->total_time_enabled;
+	list_for_each_entry(sub, &counter->sibling_list, list_entry)
+		if (sub->state >= PERF_COUNTER_STATE_INACTIVE)
+			sub->tstamp_enabled =
+				ctx->time - sub->total_time_enabled;
+}
+
+/*
  * Cross CPU call to enable a performance counter
  */
 static void __perf_counter_enable(void *info)
@@ -877,8 +899,7 @@ static void __perf_counter_enable(void *info)
 
 	if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
 		goto unlock;
-	counter->state = PERF_COUNTER_STATE_INACTIVE;
-	counter->tstamp_enabled = ctx->time - counter->total_time_enabled;
+	__perf_counter_mark_enabled(counter, ctx);
 
 	/*
 	 * If the counter is in a group and isn't the group leader,
@@ -971,11 +992,9 @@ static void perf_counter_enable(struct perf_counter *counter)
 	 * Since we have the lock this context can't be scheduled
 	 * in, so we can change the state safely.
 	 */
-	if (counter->state == PERF_COUNTER_STATE_OFF) {
-		counter->state = PERF_COUNTER_STATE_INACTIVE;
-		counter->tstamp_enabled =
-			ctx->time - counter->total_time_enabled;
-	}
+	if (counter->state == PERF_COUNTER_STATE_OFF)
+		__perf_counter_mark_enabled(counter, ctx);
+
  out:
 	spin_unlock_irq(&ctx->lock);
 }
@@ -1479,9 +1498,7 @@ static void perf_counter_enable_on_exec(struct task_struct *task)
 		counter->attr.enable_on_exec = 0;
 		if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
 			continue;
-		counter->state = PERF_COUNTER_STATE_INACTIVE;
-		counter->tstamp_enabled =
-			ctx->time - counter->total_time_enabled;
+		__perf_counter_mark_enabled(counter, ctx);
 		enabled = 1;
 	}
 
@@ -1503,10 +1520,21 @@ static void perf_counter_enable_on_exec(struct task_struct *task)
  */
 static void __perf_counter_read(void *info)
 {
+	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
 	struct perf_counter *counter = info;
 	struct perf_counter_context *ctx = counter->ctx;
 	unsigned long flags;
 
+	/*
+	 * If this is a task context, we need to check whether it is
+	 * the current task context of this cpu.  If not it has been
+	 * scheduled out before the smp call arrived.  In that case
+	 * counter->count would have been updated to a recent sample
+	 * when the counter was scheduled out.
+	 */
+	if (ctx->task && cpuctx->task_ctx != ctx)
+		return;
+
 	local_irq_save(flags);
 	if (ctx->is_active)
 		update_context_time(ctx);
@@ -1664,6 +1692,11 @@ static void free_counter(struct perf_counter *counter)
 			atomic_dec(&nr_task_counters);
 	}
 
+	if (counter->output) {
+		fput(counter->output->filp);
+		counter->output = NULL;
+	}
+
 	if (counter->destroy)
 		counter->destroy(counter);
 
@@ -1780,7 +1813,7 @@ static int perf_counter_read_group(struct perf_counter *counter,
 	size += err;
 
 	list_for_each_entry(sub, &leader->sibling_list, list_entry) {
-		err = perf_counter_read_entry(counter, read_format,
+		err = perf_counter_read_entry(sub, read_format,
 				buf + size);
 		if (err < 0)
 			return err;
@@ -1949,6 +1982,8 @@ unlock:
 	return ret;
 }
 
+int perf_counter_set_output(struct perf_counter *counter, int output_fd);
+
 static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct perf_counter *counter = file->private_data;
@@ -1972,6 +2007,9 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case PERF_COUNTER_IOC_PERIOD:
 		return perf_counter_period(counter, (u64 __user *)arg);
 
+	case PERF_COUNTER_IOC_SET_OUTPUT:
+		return perf_counter_set_output(counter, arg);
+
 	default:
 		return -ENOTTY;
 	}
@@ -2008,6 +2046,10 @@ int perf_counter_task_disable(void)
 	return 0;
 }
 
+#ifndef PERF_COUNTER_INDEX_OFFSET
+# define PERF_COUNTER_INDEX_OFFSET 0
+#endif
+
 static int perf_counter_index(struct perf_counter *counter)
 {
 	if (counter->state != PERF_COUNTER_STATE_ACTIVE)
@@ -2238,6 +2280,11 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 
 	WARN_ON_ONCE(counter->ctx->parent_ctx);
 	mutex_lock(&counter->mmap_mutex);
+	if (counter->output) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
 	if (atomic_inc_not_zero(&counter->mmap_count)) {
 		if (nr_pages != counter->data->nr_pages)
 			ret = -EINVAL;
@@ -2623,6 +2670,7 @@ static int perf_output_begin(struct perf_output_handle *handle,
 			     struct perf_counter *counter, unsigned int size,
 			     int nmi, int sample)
 {
+	struct perf_counter *output_counter;
 	struct perf_mmap_data *data;
 	unsigned int offset, head;
 	int have_lost;
@@ -2632,13 +2680,17 @@ static int perf_output_begin(struct perf_output_handle *handle,
 		u64			 lost;
 	} lost_event;
 
+	rcu_read_lock();
 	/*
 	 * For inherited counters we send all the output towards the parent.
 	 */
 	if (counter->parent)
 		counter = counter->parent;
 
-	rcu_read_lock();
+	output_counter = rcu_dereference(counter->output);
+	if (output_counter)
+		counter = output_counter;
+
 	data = rcu_dereference(counter->data);
 	if (!data)
 		goto out;
@@ -4186,6 +4238,57 @@ err_size:
 	goto out;
 }
 
+int perf_counter_set_output(struct perf_counter *counter, int output_fd)
+{
+	struct perf_counter *output_counter = NULL;
+	struct file *output_file = NULL;
+	struct perf_counter *old_output;
+	int fput_needed = 0;
+	int ret = -EINVAL;
+
+	if (!output_fd)
+		goto set;
+
+	output_file = fget_light(output_fd, &fput_needed);
+	if (!output_file)
+		return -EBADF;
+
+	if (output_file->f_op != &perf_fops)
+		goto out;
+
+	output_counter = output_file->private_data;
+
+	/* Don't chain output fds */
+	if (output_counter->output)
+		goto out;
+
+	/* Don't set an output fd when we already have an output channel */
+	if (counter->data)
+		goto out;
+
+	atomic_long_inc(&output_file->f_count);
+
+set:
+	mutex_lock(&counter->mmap_mutex);
+	old_output = counter->output;
+	rcu_assign_pointer(counter->output, output_counter);
+	mutex_unlock(&counter->mmap_mutex);
+
+	if (old_output) {
+		/*
+		 * we need to make sure no existing perf_output_*()
+		 * is still referencing this counter.
+		 */
+		synchronize_rcu();
+		fput(old_output->filp);
+	}
+
+	ret = 0;
+out:
+	fput_light(output_file, fput_needed);
+	return ret;
+}
+
 /**
  * sys_perf_counter_open - open a performance counter, associate it to a task/cpu
  *
@@ -4208,7 +4311,7 @@ SYSCALL_DEFINE5(perf_counter_open,
 	int ret;
 
 	/* for future expandability... */
-	if (flags)
+	if (flags & ~(PERF_FLAG_FD_NO_GROUP | PERF_FLAG_FD_OUTPUT))
 		return -EINVAL;
 
 	ret = perf_copy_attr(attr_uptr, &attr);
@@ -4236,7 +4339,7 @@ SYSCALL_DEFINE5(perf_counter_open,
 	 * Look up the group leader (we will attach this counter to it):
 	 */
 	group_leader = NULL;
-	if (group_fd != -1) {
+	if (group_fd != -1 && !(flags & PERF_FLAG_FD_NO_GROUP)) {
 		ret = -EINVAL;
 		group_file = fget_light(group_fd, &fput_needed);
 		if (!group_file)
@@ -4278,6 +4381,12 @@ SYSCALL_DEFINE5(perf_counter_open,
 	if (!counter_file)
 		goto err_free_put_context;
 
+	if (flags & PERF_FLAG_FD_OUTPUT) {
+		ret = perf_counter_set_output(counter, group_fd);
+		if (ret)
+			goto err_free_put_context;
+	}
+
 	counter->filp = counter_file;
 	WARN_ON_ONCE(ctx->parent_ctx);
 	mutex_lock(&ctx->mutex);