[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <ff979a43-045a-dc56-64d1-2c31dd4db381@linux.alibaba.com>
Date: Thu, 9 Sep 2021 11:13:21 +0800
From: 王贇 <yun.wang@...ux.alibaba.com>
To: Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Jiri Olsa <jolsa@...hat.com>,
Namhyung Kim <namhyung@...nel.org>,
Alexei Starovoitov <ast@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>,
Andrii Nakryiko <andrii@...nel.org>,
Martin KaFai Lau <kafai@...com>,
Song Liu <songliubraving@...com>, Yonghong Song <yhs@...com>,
John Fastabend <john.fastabend@...il.com>,
KP Singh <kpsingh@...nel.org>,
"open list:PERFORMANCE EVENTS SUBSYSTEM"
<linux-perf-users@...r.kernel.org>,
"open list:PERFORMANCE EVENTS SUBSYSTEM"
<linux-kernel@...r.kernel.org>,
"open list:BPF (Safe dynamic programs and tools)"
<netdev@...r.kernel.org>,
"open list:BPF (Safe dynamic programs and tools)"
<bpf@...r.kernel.org>
Subject: [RFC PATCH] perf: fix panic by mark recursion inside
perf_log_throttle
When running with ftrace function enabled, we observed panic
as below:
traps: PANIC: double fault, error_code: 0x0
[snip]
RIP: 0010:perf_swevent_get_recursion_context+0x0/0x70
[snip]
Call Trace:
<NMI>
perf_trace_buf_alloc+0x26/0xd0
perf_ftrace_function_call+0x18f/0x2e0
kernelmode_fixup_or_oops+0x5/0x120
__bad_area_nosemaphore+0x1b8/0x280
do_user_addr_fault+0x410/0x920
exc_page_fault+0x92/0x300
asm_exc_page_fault+0x1e/0x30
RIP: 0010:__get_user_nocheck_8+0x6/0x13
perf_callchain_user+0x266/0x2f0
get_perf_callchain+0x194/0x210
perf_callchain+0xa3/0xc0
perf_prepare_sample+0xa5/0xa60
perf_event_output_forward+0x7b/0x1b0
__perf_event_overflow+0x67/0x120
perf_swevent_overflow+0xcb/0x110
perf_swevent_event+0xb0/0xf0
perf_tp_event+0x292/0x410
perf_trace_run_bpf_submit+0x87/0xc0
perf_trace_lock_acquire+0x12b/0x170
lock_acquire+0x1bf/0x2e0
perf_output_begin+0x70/0x4b0
perf_log_throttle+0xe2/0x1a0
perf_event_nmi_handler+0x30/0x50
nmi_handle+0xba/0x2a0
default_do_nmi+0x45/0xf0
exc_nmi+0x155/0x170
end_repeat_nmi+0x16/0x55
According to the trace we know the story is like this, the NMI
triggered perf IRQ throttling and call perf_log_throttle(),
which triggered the swevent overflow, and the overflow process
do perf_callchain_user() which triggered a user PF, and the PF
process triggered perf ftrace which finally lead into a suspected
stack overflow.
This patch marking the context as recursion during perf_log_throttle()
, so no more swevent during the process and no more panic.
Signed-off-by: Michael Wang <yun.wang@...ux.alibaba.com>
---
kernel/events/core.c | 14 +++++++++-----
1 file changed, 9 insertions(+), 5 deletions(-)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 744e872..6063443 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8716,6 +8716,7 @@ static void perf_log_throttle(struct perf_event *event, int enable)
struct perf_output_handle handle;
struct perf_sample_data sample;
int ret;
+ int rctx;
struct {
struct perf_event_header header;
@@ -8738,14 +8739,17 @@ static void perf_log_throttle(struct perf_event *event, int enable)
perf_event_header__init_id(&throttle_event.header, &sample, event);
+ rctx = perf_swevent_get_recursion_context();
ret = perf_output_begin(&handle, &sample, event,
throttle_event.header.size);
- if (ret)
- return;
+ if (!ret) {
+ perf_output_put(&handle, throttle_event);
+ perf_event__output_id_sample(event, &handle, &sample);
+ perf_output_end(&handle);
+ }
- perf_output_put(&handle, throttle_event);
- perf_event__output_id_sample(event, &handle, &sample);
- perf_output_end(&handle);
+ if (rctx >= 0)
+ perf_swevent_put_recursion_context(rctx);
}
/*
--
1.8.3.1
Powered by blists - more mailing lists