perf: Fix software migrate events

Stephane asked about PERF_COUNT_SW_CPU_MIGRATIONS and I realized it
was borken:

 > The problem is that the task isn't actually scheduled while its being
 > migrated (obviously), and if its not scheduled, the counters aren't
 > scheduled either, so there's no observing of the fact.
 >
 > A further problem with migrations is that many migrations happen from
 > softirq context, which is nested inside the 'random' task context of
 > whoemever happens to run at that time, similarly for the wakeup
 > migrations triggered from (soft)irq context. All those end up being
 > accounted in the task that's currently running, eg. your 'ls'.

The below cures this by marking a task as migrated and accounting it
on the subsequent sched_in().

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 29 insertions, 4 deletions

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 61992cf2e977..e86f85abeda7 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -798,11 +798,33 @@ perf_sw_event_sched(u32 event_id, u64 nr, u64 addr)
 
 extern struct static_key_deferred perf_sched_events;
 
+static __always_inline bool
+perf_sw_migrate_enabled(void)
+{
+	if (static_key_false(&perf_swevent_enabled[PERF_COUNT_SW_CPU_MIGRATIONS]))
+		return true;
+	return false;
+}
+
+static inline void perf_event_task_migrate(struct task_struct *task)
+{
+	if (perf_sw_migrate_enabled())
+		task->sched_migrated = 1;
+}
+
 static inline void perf_event_task_sched_in(struct task_struct *prev,
 					    struct task_struct *task)
 {
 	if (static_key_false(&perf_sched_events.key))
 		__perf_event_task_sched_in(prev, task);
+
+	if (perf_sw_migrate_enabled() && task->sched_migrated) {
+		struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]);
+
+		perf_fetch_caller_regs(regs);
+		___perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, regs, 0);
+		task->sched_migrated = 0;
+	}
 }
 
 static inline void perf_event_task_sched_out(struct task_struct *prev,
@@ -925,6 +947,8 @@ perf_aux_output_skip(struct perf_output_handle *handle,
 static inline void *
 perf_get_aux(struct perf_output_handle *handle)				{ return NULL; }
 static inline void
+perf_event_task_migrate(struct task_struct *task)			{ }
+static inline void
 perf_event_task_sched_in(struct task_struct *prev,
 			 struct task_struct *task)			{ }
 static inline void
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 26a2e6122734..2c5e6c3db654 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1356,9 +1356,6 @@ struct task_struct {
 #endif
 
 	struct mm_struct *mm, *active_mm;
-#ifdef CONFIG_COMPAT_BRK
-	unsigned brk_randomized:1;
-#endif
 	/* per-thread vma caching */
 	u32 vmacache_seqnum;
 	struct vm_area_struct *vmacache[VMACACHE_SIZE];
@@ -1381,10 +1378,14 @@ struct task_struct {
 	/* Revert to default priority/policy when forking */
 	unsigned sched_reset_on_fork:1;
 	unsigned sched_contributes_to_load:1;
+	unsigned sched_migrated:1;
 
 #ifdef CONFIG_MEMCG_KMEM
 	unsigned memcg_kmem_skip_account:1;
 #endif
+#ifdef CONFIG_COMPAT_BRK
+	unsigned brk_randomized:1;
+#endif
 
 	unsigned long atomic_flags; /* Flags needing atomic access. */
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fe22f7510bce..8652fd540780 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1049,7 +1049,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 		if (p->sched_class->migrate_task_rq)
 			p->sched_class->migrate_task_rq(p, new_cpu);
 		p->se.nr_migrations++;
-		perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
+		perf_event_task_migrate(p);
 	}
 
 	__set_task_cpu(p, new_cpu);