perf: Fix cgroup scheduling in perf_enable_on_exec()

There is a comment that states that perf_event_context_sched_in() will
also switch in the cgroup events, I cannot find it does so. Therefore
all the resulting logic goes out the window too.

Clean that up.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.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>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 7 insertions, 24 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 9d1195af819c..e7bda0ed8d40 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -579,13 +579,7 @@ static inline void perf_cgroup_sched_out(struct task_struct *task,
          * we are holding the rcu lock
          */
         cgrp1 = perf_cgroup_from_task(task, NULL);
-
-        /*
-         * next is NULL when called from perf_event_enable_on_exec()
-         * that will systematically cause a cgroup_switch()
-         */
-        if (next)
-                cgrp2 = perf_cgroup_from_task(next, NULL);
+        cgrp2 = perf_cgroup_from_task(next, NULL);
 
         /*
          * only schedule out current cgroup events if we know
@@ -611,8 +605,6 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev,
          * we are holding the rcu lock
          */
         cgrp1 = perf_cgroup_from_task(task, NULL);
-
-        /* prev can never be NULL */
         cgrp2 = perf_cgroup_from_task(prev, NULL);
 
         /*
@@ -1450,11 +1442,14 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 
         if (is_cgroup_event(event)) {
                 ctx->nr_cgroups--;
+                /*
+                 * Because cgroup events are always per-cpu events, this will
+                 * always be called from the right CPU.
+                 */
                 cpuctx = __get_cpu_context(ctx);
                 /*
-                 * if there are no more cgroup events
-                 * then cler cgrp to avoid stale pointer
-                 * in update_cgrp_time_from_cpuctx()
+                 * If there are no more cgroup events then clear cgrp to avoid
+                 * stale pointer in update_cgrp_time_from_cpuctx().
                  */
                 if (!ctx->nr_cgroups)
                         cpuctx->cgrp = NULL;
@@ -3118,15 +3113,6 @@ static void perf_event_enable_on_exec(int ctxn)
         if (!ctx || !ctx->nr_events)
                 goto out;
 
-        /*
-         * We must ctxsw out cgroup events to avoid conflict
-         * when invoking perf_task_event_sched_in() later on
-         * in this function. Otherwise we end up trying to
-         * ctxswin cgroup events which are already scheduled
-         * in.
-         */
-        perf_cgroup_sched_out(current, NULL);
-
         raw_spin_lock(&ctx->lock);
         task_ctx_sched_out(ctx);
 
@@ -3144,9 +3130,6 @@ static void perf_event_enable_on_exec(int ctxn)
 
         raw_spin_unlock(&ctx->lock);
 
-        /*
-         * Also calls ctxswin for cgroup events, if any:
-         */
         perf_event_context_sched_in(ctx, ctx->task);
 out:
         local_irq_restore(flags);