1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
|
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 4 Jul 2024 19:03:40 +0200
Subject: [PATCH 6/7] perf: Don't disable preemption in perf_pending_task().
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.10/older/patches-6.10.2-rt14.tar.xz
perf_pending_task() is invoked in task context and disables preemption
because perf_swevent_get_recursion_context() used to access per-CPU
variables. The other reason is to create a RCU read section while
accessing the perf_event.
The recursion counter is no longer a per-CPU accounter so disabling
preemption is no longer required. The RCU section is needed and must be
created explicit.
Replace the preemption-disable section with a explicit RCU-read section.
Tested-by: Marco Elver <elver@google.com>
Link: https://lore.kernel.org/r/20240704170424.1466941-7-bigeasy@linutronix.de
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/events/core.c | 11 +++++------
1 file changed, 5 insertions(+), 6 deletions(-)
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5208,10 +5208,9 @@ static void perf_pending_task_sync(struc
}
/*
- * All accesses related to the event are within the same
- * non-preemptible section in perf_pending_task(). The RCU
- * grace period before the event is freed will make sure all
- * those accesses are complete by then.
+ * All accesses related to the event are within the same RCU section in
+ * perf_pending_task(). The RCU grace period before the event is freed
+ * will make sure all those accesses are complete by then.
*/
rcuwait_wait_event(&event->pending_work_wait, !event->pending_work, TASK_UNINTERRUPTIBLE);
}
@@ -6842,7 +6841,7 @@ static void perf_pending_task(struct cal
* critical section as the ->pending_work reset. See comment in
* perf_pending_task_sync().
*/
- preempt_disable_notrace();
+ rcu_read_lock();
/*
* If we 'fail' here, that's OK, it means recursion is already disabled
* and we won't recurse 'further'.
@@ -6855,10 +6854,10 @@ static void perf_pending_task(struct cal
local_dec(&event->ctx->nr_pending);
rcuwait_wake_up(&event->pending_work_wait);
}
+ rcu_read_unlock();
if (rctx >= 0)
perf_swevent_put_recursion_context(rctx);
- preempt_enable_notrace();
}
#ifdef CONFIG_GUEST_PERF_EVENTS
|
