[PATCH 03/13] perf trace: Support syscall name globbing

From: Arnaldo Carvalho de Melo
Date: Mon Sep 04 2017 - 10:04:57 EST


From: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>

So now we can use:

# perf trace -e pkey_*
532.784 ( 0.006 ms): pkey/16018 pkey_alloc(init_val: DISABLE_WRITE) = -1 EINVAL Invalid argument
532.795 ( 0.004 ms): pkey/16018 pkey_mprotect(start: 0x7f380d0a6000, len: 4096, prot: READ|WRITE, pkey: -1) = 0
532.801 ( 0.002 ms): pkey/16018 pkey_free(pkey: -1 ) = -1 EINVAL Invalid argument
^C[root@jouet ~]#

Or '-e epoll*', '-e *msg*', etc.

Combining syscall names with perf events, tracepoints, etc, continues to
be valid, i.e. this is possible:

# perf probe -L sys_nanosleep
<SyS_nanosleep@/home/acme/git/linux/kernel/time/hrtimer.c:0>
0 SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
struct timespec __user *, rmtp)
{
struct timespec64 tu;

5 if (get_timespec64(&tu, rqtp))
6 return -EFAULT;

if (!timespec64_valid(&tu))
9 return -EINVAL;

11 current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
12 current->restart_block.nanosleep.rmtp = rmtp;
13 return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
}

# perf probe my_probe="sys_nanosleep:12 rmtp"
Added new event:
probe:my_probe (on sys_nanosleep:12 with rmtp)

You can now use it in all perf tools, such as:

perf record -e probe:my_probe -aR sleep 1

#
# perf trace -e probe:my_probe/max-stack=5/,*sleep sleep 1
0.427 ( 0.003 ms): sleep/16690 nanosleep(rqtp: 0x7ffefc245090) ...
0.430 ( ): probe:my_probe:(ffffffffbd112923) rmtp=0)
sys_nanosleep ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
return_from_SYSCALL_64 ([kernel.kallsyms])
__nanosleep_nocancel (/usr/lib64/libc-2.25.so)
0.427 (1000.208 ms): sleep/16690 ... [continued]: nanosleep()) = 0
#

Cc: Adrian Hunter <adrian.hunter@xxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Wang Nan <wangnan0@xxxxxxxxxx>
Link: http://lkml.kernel.org/n/tip-elycoi8wy6y0w9dkj7ox1mzz@xxxxxxxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
tools/perf/Documentation/perf-trace.txt | 2 +-
tools/perf/builtin-trace.c | 39 +++++++++++++++++++++++++++++----
2 files changed, 36 insertions(+), 5 deletions(-)

diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index c1e3288a2dfb..d53bea6bd571 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -37,7 +37,7 @@ OPTIONS
--expr::
--event::
List of syscalls and other perf events (tracepoints, HW cache events,
- etc) to show.
+ etc) to show. Globbing is supported, e.g.: "epoll_*", "*msg*", etc.
See 'perf list' for a complete list of events.
Prefixing with ! shows all syscalls but the ones specified. You may
need to escape it.
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index d59cdadf3a79..771ddab94bb0 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1261,6 +1261,7 @@ static int trace__read_syscall_info(struct trace *trace, int id)
static int trace__validate_ev_qualifier(struct trace *trace)
{
int err = 0, i;
+ size_t nr_allocated;
struct str_node *pos;

trace->ev_qualifier_ids.nr = strlist__nr_entries(trace->ev_qualifier);
@@ -1274,13 +1275,18 @@ static int trace__validate_ev_qualifier(struct trace *trace)
goto out;
}

+ nr_allocated = trace->ev_qualifier_ids.nr;
i = 0;

strlist__for_each_entry(pos, trace->ev_qualifier) {
const char *sc = pos->s;
- int id = syscalltbl__id(trace->sctbl, sc);
+ int id = syscalltbl__id(trace->sctbl, sc), match_next = -1;

if (id < 0) {
+ id = syscalltbl__strglobmatch_first(trace->sctbl, sc, &match_next);
+ if (id >= 0)
+ goto matches;
+
if (err == 0) {
fputs("Error:\tInvalid syscall ", trace->output);
err = -EINVAL;
@@ -1290,13 +1296,37 @@ static int trace__validate_ev_qualifier(struct trace *trace)

fputs(sc, trace->output);
}
-
+matches:
trace->ev_qualifier_ids.entries[i++] = id;
+ if (match_next == -1)
+ continue;
+
+ while (1) {
+ id = syscalltbl__strglobmatch_next(trace->sctbl, sc, &match_next);
+ if (id < 0)
+ break;
+ if (nr_allocated == trace->ev_qualifier_ids.nr) {
+ void *entries;
+
+ nr_allocated += 8;
+ entries = realloc(trace->ev_qualifier_ids.entries,
+ nr_allocated * sizeof(trace->ev_qualifier_ids.entries[0]));
+ if (entries == NULL) {
+ err = -ENOMEM;
+ fputs("\nError:\t Not enough memory for parsing\n", trace->output);
+ goto out_free;
+ }
+ trace->ev_qualifier_ids.entries = entries;
+ }
+ trace->ev_qualifier_ids.nr++;
+ trace->ev_qualifier_ids.entries[i++] = id;
+ }
}

if (err < 0) {
fputs("\nHint:\ttry 'perf list syscalls:sys_enter_*'"
"\nHint:\tand: 'man syscalls'\n", trace->output);
+out_free:
zfree(&trace->ev_qualifier_ids.entries);
trace->ev_qualifier_ids.nr = 0;
}
@@ -2814,7 +2844,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
struct trace *trace = (struct trace *)opt->value;
const char *s = str;
char *sep = NULL, *lists[2] = { NULL, NULL, };
- int len = strlen(str) + 1, err = -1, list;
+ int len = strlen(str) + 1, err = -1, list, idx;
char *strace_groups_dir = system_path(STRACE_GROUPS_DIR);
char group_name[PATH_MAX];

@@ -2831,7 +2861,8 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
*sep = '\0';

list = 0;
- if (syscalltbl__id(trace->sctbl, s) >= 0) {
+ if (syscalltbl__id(trace->sctbl, s) >= 0 ||
+ syscalltbl__strglobmatch_first(trace->sctbl, s, &idx) >= 0) {
list = 1;
} else {
path__join(group_name, sizeof(group_name), strace_groups_dir, s);
--
2.13.5