perf, core: Rate limit perf_sched_events jump_label patching

jump_lable patching is very expensive operation that involves pausing all
cpus. The patching of perf_sched_events jump_label is easily controllable
from userspace by unprivileged user.

When te user runs a loop like this:

  "while true; do perf stat -e cycles true; done"

... the performance of my test application that just increments a counter
for one second drops by 4%.

This is on a 16 cpu box with my test application using only one of
them. An impact on a real server doing real work will be worse.

Performance of KVM PMU drops nearly 50% due to jump_lable for "perf
record" since KVM PMU implementation creates and destroys perf event
frequently.

This patch introduces a way to rate limit jump_label patching and uses
it to fix the above problem.

I believe that as jump_label use will spread the problem will become more
common and thus solving it in a generic code is appropriate. Also fixing
it in the perf code would result in moving jump_label accounting logic to
perf code with all the ifdefs in case of JUMP_LABEL=n kernel. With this
patch all details are nicely hidden inside jump_label code.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Acked-by: Jason Baron <jbaron@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20111127155909.GO2557@redhat.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>

2 files changed, 27 insertions, 3 deletions

diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 388b0d425b50..a1e7f909c801 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -3,6 +3,7 @@
 
 #include <linux/types.h>
 #include <linux/compiler.h>
+#include <linux/workqueue.h>
 
 #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL)
 
@@ -14,6 +15,12 @@ struct jump_label_key {
 #endif
 };
 
+struct jump_label_key_deferred {
+	struct jump_label_key key;
+	unsigned long timeout;
+	struct delayed_work work;
+};
+
 # include <asm/jump_label.h>
 # define HAVE_JUMP_LABEL
 #endif	/* CC_HAVE_ASM_GOTO && CONFIG_JUMP_LABEL */
@@ -51,8 +58,11 @@ extern void arch_jump_label_transform_static(struct jump_entry *entry,
 extern int jump_label_text_reserved(void *start, void *end);
 extern void jump_label_inc(struct jump_label_key *key);
 extern void jump_label_dec(struct jump_label_key *key);
+extern void jump_label_dec_deferred(struct jump_label_key_deferred *key);
 extern bool jump_label_enabled(struct jump_label_key *key);
 extern void jump_label_apply_nops(struct module *mod);
+extern void jump_label_rate_limit(struct jump_label_key_deferred *key,
+		unsigned long rl);
 
 #else  /* !HAVE_JUMP_LABEL */
 
@@ -68,6 +78,10 @@ static __always_inline void jump_label_init(void)
 {
 }
 
+struct jump_label_key_deferred {
+	struct jump_label_key  key;
+};
+
 static __always_inline bool static_branch(struct jump_label_key *key)
 {
 	if (unlikely(atomic_read(&key->enabled)))
@@ -85,6 +99,11 @@ static inline void jump_label_dec(struct jump_label_key *key)
 	atomic_dec(&key->enabled);
 }
 
+static inline void jump_label_dec_deferred(struct jump_label_key_deferred *key)
+{
+	jump_label_dec(&key->key);
+}
+
 static inline int jump_label_text_reserved(void *start, void *end)
 {
 	return 0;
@@ -102,6 +121,11 @@ static inline int jump_label_apply_nops(struct module *mod)
 {
 	return 0;
 }
+
+static inline void jump_label_rate_limit(struct jump_label_key_deferred *key,
+		unsigned long rl)
+{
+}
 #endif	/* HAVE_JUMP_LABEL */
 
 #endif	/* _LINUX_JUMP_LABEL_H */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index cb44c9e75660..564769cdb473 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1064,12 +1064,12 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
 	}
 }
 
-extern struct jump_label_key perf_sched_events;
+extern struct jump_label_key_deferred perf_sched_events;
 
 static inline void perf_event_task_sched_in(struct task_struct *prev,
 					    struct task_struct *task)
 {
-	if (static_branch(&perf_sched_events))
+	if (static_branch(&perf_sched_events.key))
 		__perf_event_task_sched_in(prev, task);
 }
 
@@ -1078,7 +1078,7 @@ static inline void perf_event_task_sched_out(struct task_struct *prev,
 {
 	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0);
 
-	if (static_branch(&perf_sched_events))
+	if (static_branch(&perf_sched_events.key))
 		__perf_event_task_sched_out(prev, next);
 }