perf/core: Simplify __detach_global_ctx_data()

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>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260211223222.3119790-4-namhyung@kernel.org

diff --git a/kernel/events/core.c b/kernel/events/core.c
index d357714fc02ebeb496c4d6440fafed471dd6f3e0..5eeae8636996cc8c4c32dd18d51da908a3594c11 100644 (file)
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5560,22 +5560,15 @@ 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)