sched, perf: Use a single callback into the scheduler

We can easily use a single callback for both sched-in and sched-out. This
reduces the code footprint in the scheduler path as well as removes
the PMU black spot otherwise present between the out and in callback.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-o56ajxp1edwqg6x9d31wb805@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 17 insertions, 30 deletions

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f32578634d9d..8adf70e9e3cc 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1084,10 +1084,8 @@ extern void perf_pmu_unregister(struct pmu *pmu);
 
 extern int perf_num_counters(void);
 extern const char *perf_pmu_name(void);
-extern void __perf_event_task_sched_in(struct task_struct *prev,
-                                       struct task_struct *task);
-extern void __perf_event_task_sched_out(struct task_struct *prev,
-                                        struct task_struct *next);
+extern void __perf_event_task_sched(struct task_struct *prev,
+                                    struct task_struct *next);
 extern int perf_event_init_task(struct task_struct *child);
 extern void perf_event_exit_task(struct task_struct *child);
 extern void perf_event_free_task(struct task_struct *task);
@@ -1207,20 +1205,13 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
 
 extern struct static_key_deferred perf_sched_events;
 
-static inline void perf_event_task_sched_in(struct task_struct *prev,
+static inline void perf_event_task_sched(struct task_struct *prev,
                                             struct task_struct *task)
 {
-        if (static_key_false(&perf_sched_events.key))
-                __perf_event_task_sched_in(prev, task);
-}
-
-static inline void perf_event_task_sched_out(struct task_struct *prev,
-                                             struct task_struct *next)
-{
         perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0);
 
         if (static_key_false(&perf_sched_events.key))
-                __perf_event_task_sched_out(prev, next);
+                __perf_event_task_sched(prev, task);
 }
 
 extern void perf_event_mmap(struct vm_area_struct *vma);
@@ -1295,11 +1286,8 @@ extern void perf_event_disable(struct perf_event *event);
 extern void perf_event_task_tick(void);
 #else
 static inline void
-perf_event_task_sched_in(struct task_struct *prev,
-                         struct task_struct *task)                      { }
-static inline void
-perf_event_task_sched_out(struct task_struct *prev,
-                          struct task_struct *next)                     { }
+perf_event_task_sched(struct task_struct *prev,
+                      struct task_struct *task)                         { }
 static inline int perf_event_init_task(struct task_struct *child)       { return 0; }
 static inline void perf_event_exit_task(struct task_struct *child)      { }
 static inline void perf_event_free_task(struct task_struct *task)       { }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 00c58df9f4e2..e82c7a1face9 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2039,8 +2039,8 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
  * accessing the event control register. If a NMI hits, then it will
  * not restart the event.
  */
-void __perf_event_task_sched_out(struct task_struct *task,
-                                 struct task_struct *next)
+static void __perf_event_task_sched_out(struct task_struct *task,
+                                        struct task_struct *next)
 {
         int ctxn;
 
@@ -2279,8 +2279,8 @@ static void perf_branch_stack_sched_in(struct task_struct *prev,
  * accessing the event control register. If a NMI hits, then it will
  * keep the event running.
  */
-void __perf_event_task_sched_in(struct task_struct *prev,
-                                struct task_struct *task)
+static void __perf_event_task_sched_in(struct task_struct *prev,
+                                       struct task_struct *task)
 {
         struct perf_event_context *ctx;
         int ctxn;
@@ -2305,6 +2305,12 @@ void __perf_event_task_sched_in(struct task_struct *prev,
                 perf_branch_stack_sched_in(prev, task);
 }
 
+void __perf_event_task_sched(struct task_struct *prev, struct task_struct *next)
+{
+        __perf_event_task_sched_out(prev, next);
+        __perf_event_task_sched_in(prev, next);
+}
+
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
 {
         u64 frequency = event->attr.sample_freq;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4603b9d8f30a..5c692a0a555d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1913,7 +1913,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
                     struct task_struct *next)
 {
         sched_info_switch(prev, next);
-        perf_event_task_sched_out(prev, next);
+        perf_event_task_sched(prev, next);
         fire_sched_out_preempt_notifiers(prev, next);
         prepare_lock_switch(rq, next);
         prepare_arch_switch(next);
@@ -1956,13 +1956,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
          */
         prev_state = prev->state;
         finish_arch_switch(prev);
-#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
-        local_irq_disable();
-#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
-        perf_event_task_sched_in(prev, current);
-#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
-        local_irq_enable();
-#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
         finish_lock_switch(rq, prev);
         finish_arch_post_lock_switch();