[PATCH 34/36] perf mmap: Fix perf backward recording

From: Arnaldo Carvalho de Melo
Date: Wed Dec 06 2017 - 09:44:44 EST


From: Wang Nan <wangnan0@xxxxxxxxxx>

'perf record' backward recording doesn't work as we expected: it never
overwrites when ring buffer gets full.

Test:

Run a busy python printing task background like this:

while True:
print 123

send SIGUSR2 to perf to capture snapshot, then:

# ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit --exclude-perf -a --switch-output
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017110101520743 ]
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017110101521251 ]
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017110101521692 ]
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Dump perf.data.2017110101521936 ]
[ perf record: Captured and wrote 0.826 MB perf.data.<timestamp> ]

# ./perf script -i ./perf.data.2017110101520743 | head -n3
perf 2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 2400, 0, 59, 100, 0)
perf 2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 (4112340, 2, ffffffff, 3df, 100, 0)
python 2545 [000] 12449.310800: raw_syscalls:sys_exit: NR 1 = 4
# ./perf script -i ./perf.data.2017110101521251 | head -n3
perf 2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 2400, 0, 59, 100, 0)
perf 2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 (4112340, 2, ffffffff, 3df, 100, 0)
python 2545 [000] 12449.310800: raw_syscalls:sys_exit: NR 1 = 4
# ./perf script -i ./perf.data.2017110101521692 | head -n3
perf 2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 2400, 0, 59, 100, 0)
perf 2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 (4112340, 2, ffffffff, 3df, 100, 0)
python 2545 [000] 12449.310800: raw_syscalls:sys_exit: NR 1 = 4

Timestamps never change, but my background task is a dead loop, can
easily overwhelm the ring buffer.

This patch fixes it by forcing unsetting PROT_WRITE for a backward ring
buffer, so all backward ring buffers become overwrite ring buffers.

Test result:

# ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit --exclude-perf -a --switch-output
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017110101285323 ]
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017110101290053 ]
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017110101290446 ]
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Dump perf.data.2017110101290837 ]
[ perf record: Captured and wrote 0.826 MB perf.data.<timestamp> ]
# ./perf script -i ./perf.data.2017110101285323 | head -n3
python 2545 [000] 11064.268083: raw_syscalls:sys_exit: NR 1 = 4
python 2545 [000] 11064.268084: raw_syscalls:sys_enter: NR 1 (1, 12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
python 2545 [000] 11064.268086: raw_syscalls:sys_exit: NR 1 = 4
# ./perf script -i ./perf.data.2017110101290 | head -n3
failed to open ./perf.data.2017110101290: No such file or directory
# ./perf script -i ./perf.data.2017110101290053 | head -n3
python 2545 [000] 11071.564062: raw_syscalls:sys_enter: NR 1 (1, 12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
python 2545 [000] 11071.564064: raw_syscalls:sys_exit: NR 1 = 4
python 2545 [000] 11071.564066: raw_syscalls:sys_enter: NR 1 (1, 12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
# ./perf script -i ./perf.data.2017110101290 | head -n3
perf.data.2017110101290053 perf.data.2017110101290446 perf.data.2017110101290837
# ./perf script -i ./perf.data.2017110101290446 | head -n3
sshd 1321 [000] 11075.499473: raw_syscalls:sys_exit: NR 14 = 0
sshd 1321 [000] 11075.499474: raw_syscalls:sys_enter: NR 14 (2, 7ffe98899490, 0, 8, 0, 3000)
sshd 1321 [000] 11075.499474: raw_syscalls:sys_exit: NR 14 = 0
# ./perf script -i ./perf.data.2017110101290837 | head -n3
python 2545 [000] 11079.280844: raw_syscalls:sys_exit: NR 1 = 4
python 2545 [000] 11079.280847: raw_syscalls:sys_enter: NR 1 (1, 12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
python 2545 [000] 11079.280850: raw_syscalls:sys_exit: NR 1 = 4

Signed-off-by: Wang Nan <wangnan0@xxxxxxxxxx>
Acked-by: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Kan Liang <kan.liang@xxxxxxxxx>
Cc: Mengting Zhang <zhangmengting@xxxxxxxxxx>
Link: http://lkml.kernel.org/r/20171204165107.95327-2-wangnan0@xxxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
tools/perf/util/evlist.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 68c1f9546650..b1cea711232b 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -812,6 +812,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
int fd;
int cpu;

+ mp->prot = PROT_READ | PROT_WRITE;
if (evsel->attr.write_backward) {
output = _output_backward;
maps = evlist->backward_mmap;
@@ -824,6 +825,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY)
perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
}
+ mp->prot &= ~PROT_WRITE;
}

if (evsel->system_wide && thread)
@@ -1058,9 +1060,12 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
struct perf_evsel *evsel;
const struct cpu_map *cpus = evlist->cpus;
const struct thread_map *threads = evlist->threads;
- struct mmap_params mp = {
- .prot = PROT_READ | PROT_WRITE,
- };
+ /*
+ * Delay setting mp.prot: set it before calling perf_mmap__mmap.
+ * Its value is decided by evsel's write_backward.
+ * So &mp should not be passed through const pointer.
+ */
+ struct mmap_params mp;

if (!evlist->mmap)
evlist->mmap = perf_evlist__alloc_mmap(evlist);
--
2.13.6