[tip:perf/core] perf/core: Allow kernel filters on CPU events

[tip-bot for Alexander Shishkin <tipbot@zytor.com>]

Commit-ID:  6ce77bfd6cedbff61eabf8837dc0901bb671cc86
Gitweb:     http://git.kernel.org/tip/6ce77bfd6cedbff61eabf8837dc0901bb671cc86
Author:     Alexander Shishkin <alexander.shishkin@linux.intel.com>
AuthorDate: Thu, 26 Jan 2017 11:40:57 +0200
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Fri, 10 Feb 2017 09:08:09 +0100

perf/core: Allow kernel filters on CPU events

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@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: vince@deater.net
Link: http://lkml.kernel.org/r/20170126094057.13805-4-alexander.shishkin@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 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 5c58e93..000fdb2 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -482,6 +482,7 @@ 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().
@@ -489,6 +490,7 @@ 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 1730995..a866424 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8090,6 +8090,9 @@ 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;
@@ -8268,6 +8271,18 @@ 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)
@@ -8283,6 +8298,8 @@ 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 */
@@ -8322,24 +8339,13 @@ 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);
@@ -8348,6 +8354,14 @@ 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)