[PATCH 3/3] perf: Allow kernel filters on cpu events

[Alexander Shishkin]

While supporting file-based address filters for cpu events requires some
extra context switch handling, kernel address filters are easy, since the
kernel mapping is preserved across address spaces. It is also useful as
it permits tracing scheduling paths of the kernel.

This patch allows setting up kernel filters for cpu events.

Signed-off-by: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Mathieu Poirier <mathieu.poirier@xxxxxxxxxx>
---
 include/linux/perf_event.h |  2 ++
 kernel/events/core.c       | 42 ++++++++++++++++++++++++++++--------------
 2 files changed, 30 insertions(+), 14 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index fcb37c81ca..f4ea0600b2 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -486,6 +486,7 @@ struct perf_addr_filter {
  * @list:	list of filters for this event
  * @lock:	spinlock that serializes accesses to the @list and event's
  *		(and its children's) filter generations.
+ * @nr_file_filters:	number of file-based filters
  *
  * A child event will use parent's @list (and therefore @lock), so they are
  * bundled together; see perf_event_addr_filters().
@@ -493,6 +494,7 @@ struct perf_addr_filter {
 struct perf_addr_filters_head {
 	struct list_head	list;
 	raw_spinlock_t		lock;
+	unsigned int		nr_file_filters;
 };
 
 /**
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 36770a13ef..2eeb8fec2f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8093,6 +8093,9 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 	if (task == TASK_TOMBSTONE)
 		return;
 
+	if (!ifh->nr_file_filters)
+		return;
+
 	mm = get_task_mm(event->ctx->task);
 	if (!mm)
 		goto restart;
@@ -8269,6 +8272,18 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 				if (!filename)
 					goto fail;
 
+				/*
+				 * For now, we only support file-based filters
+				 * in per-task events; doing so for CPU-wide
+				 * events requires additional context switching
+				 * trickery, since same object code will be
+				 * mapped at different virtual addresses in
+				 * different processes.
+				 */
+				ret = -EOPNOTSUPP;
+				if (!event->ctx->task)
+					goto fail_free_name;
+
 				/* look up the path and grab its inode */
 				ret = kern_path(filename, LOOKUP_FOLLOW, &path);
 				if (ret)
@@ -8284,6 +8299,8 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 				    !S_ISREG(filter->inode->i_mode))
 					/* free_filters_list() will iput() */
 					goto fail;
+
+				event->addr_filters.nr_file_filters++;
 			}
 
 			/* ready to consume more filters */
@@ -8323,24 +8340,13 @@ perf_event_set_addr_filter(struct perf_event *event, char *filter_str)
 	if (WARN_ON_ONCE(event->parent))
 		return -EINVAL;
 
-	/*
-	 * For now, we only support filtering in per-task events; doing so
-	 * for CPU-wide events requires additional context switching trickery,
-	 * since same object code will be mapped at different virtual
-	 * addresses in different processes.
-	 */
-	if (!event->ctx->task)
-		return -EOPNOTSUPP;
-
 	ret = perf_event_parse_addr_filter(event, filter_str, &filters);
 	if (ret)
-		return ret;
+		goto fail_clear_files;
 
 	ret = event->pmu->addr_filters_validate(&filters);
-	if (ret) {
-		free_filters_list(&filters);
-		return ret;
-	}
+	if (ret)
+		goto fail_free_filters;
 
 	/* remove existing filters, if any */
 	perf_addr_filters_splice(event, &filters);
@@ -8349,6 +8355,14 @@ perf_event_set_addr_filter(struct perf_event *event, char *filter_str)
 	perf_event_for_each_child(event, perf_event_addr_filters_apply);
 
 	return ret;
+
+fail_free_filters:
+	free_filters_list(&filters);
+
+fail_clear_files:
+	event->addr_filters.nr_file_filters = 0;
+
+	return ret;
 }
 
 static int perf_event_set_filter(struct perf_event *event, void __user *arg)
-- 
2.11.0