[PATCH 3/3] perf/core: Simplify __detach_global_ctx_data()

[Namhyung Kim <namhyung@kernel.org>]

Like in the attach_global_ctx_data() it has a O(N^2) loop to delete task
context data for each thread.  But perf_free_ctx_data_rcu() can be
called under RCU read lock, so just calls it directly rather than
iterating the whole thread list again.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 kernel/events/core.c | 15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5b05a71edeb47955..e67e1baa99d1e5a9 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5561,22 +5561,15 @@ static void __detach_global_ctx_data(void)
 	struct task_struct *g, *p;
 	struct perf_ctx_data *cd;
 
-again:
 	scoped_guard (rcu) {
 		for_each_process_thread(g, p) {
 			cd = rcu_dereference(p->perf_ctx_data);
-			if (!cd || !cd->global)
-				continue;
-			cd->global = 0;
-			get_task_struct(p);
-			goto detach;
+			if (cd && cd->global) {
+				cd->global = 0;
+				detach_task_ctx_data(p);
+			}
 		}
 	}
-	return;
-detach:
-	detach_task_ctx_data(p);
-	put_task_struct(p);
-	goto again;
 }
 
 static void detach_global_ctx_data(void)
-- 
2.53.0.273.g2a3d683680-goog