* [PATCH] perf tools: Detect when pipe is passed as perf data
@ 2020-12-25 22:21 Jiri Olsa
2020-12-29 5:53 ` Namhyung Kim
0 siblings, 1 reply; 3+ messages in thread
From: Jiri Olsa @ 2020-12-25 22:21 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: lkml, Peter Zijlstra, Ingo Molnar, Mark Rutland, Namhyung Kim,
Alexander Shishkin, Michael Petlan, Ian Rogers, Stephane Eranian,
Alexei Budankov
Currently we allow pipe input/output only through '-' string
being passed to '-o' or '-i' options, like:
# mkfifo perf.pipe
# perf record --no-buffering -e 'sched:sched_switch' -o - > perf.pipe &
[1] 354406
# cat perf.pipe | ./perf --no-pager script -i - | head -3
perf 354406 [000] 168190.164921: sched:sched_switch: perf:354406..
migration/0 12 [000] 168190.164928: sched:sched_switch: migration/0:..
perf 354406 [001] 168190.164981: sched:sched_switch: perf:354406..
...
This patch detects if given path is pipe and set the perf data
object accordingly, so it's possible now to do above with:
# mkfifo perf.pipe
# perf record --no-buffering -e 'sched:sched_switch' -o perf.pipe &
[1] 360188
# perf --no-pager script -i ./perf.pipe | head -3
perf 354442 [000] 168275.464895: sched:sched_switch: perf:354442..
migration/0 12 [000] 168275.464902: sched:sched_switch: migration/0:..
perf 354442 [001] 168275.464953: sched:sched_switch: perf:354442..
It's of course possible to combine any of above ways.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/perf/util/data.c | 27 +++++++++++++++++++++------
1 file changed, 21 insertions(+), 6 deletions(-)
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index f29af4fc3d09..767b6c903cf5 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -159,7 +159,7 @@ int perf_data__update_dir(struct perf_data *data)
return 0;
}
-static bool check_pipe(struct perf_data *data)
+static int check_pipe(struct perf_data *data)
{
struct stat st;
bool is_pipe = false;
@@ -172,6 +172,15 @@ static bool check_pipe(struct perf_data *data)
} else {
if (!strcmp(data->path, "-"))
is_pipe = true;
+ else if (!stat(data->path, &st) && S_ISFIFO(st.st_mode)) {
+ int flags = perf_data__is_read(data) ?
+ O_RDONLY : O_WRONLY|O_CREAT|O_TRUNC;
+
+ fd = open(data->path, flags);
+ if (fd < 0)
+ return -EINVAL;
+ is_pipe = true;
+ }
}
if (is_pipe) {
@@ -190,7 +199,8 @@ static bool check_pipe(struct perf_data *data)
}
}
- return data->is_pipe = is_pipe;
+ data->is_pipe = is_pipe;
+ return 0;
}
static int check_backup(struct perf_data *data)
@@ -344,8 +354,11 @@ static int open_dir(struct perf_data *data)
int perf_data__open(struct perf_data *data)
{
- if (check_pipe(data))
- return 0;
+ int err;
+
+ err = check_pipe(data);
+ if (err || data->is_pipe)
+ return err;
/* currently it allows stdio for pipe only */
data->use_stdio = false;
@@ -410,8 +423,10 @@ int perf_data__switch(struct perf_data *data,
{
int ret;
- if (check_pipe(data))
- return -EINVAL;
+ ret = check_pipe(data);
+ if (ret || data->is_pipe)
+ return ret;
+
if (perf_data__is_read(data))
return -EINVAL;
--
2.26.2
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH] perf tools: Detect when pipe is passed as perf data
2020-12-25 22:21 [PATCH] perf tools: Detect when pipe is passed as perf data Jiri Olsa
@ 2020-12-29 5:53 ` Namhyung Kim
2020-12-29 9:45 ` Jiri Olsa
0 siblings, 1 reply; 3+ messages in thread
From: Namhyung Kim @ 2020-12-29 5:53 UTC (permalink / raw)
To: Jiri Olsa
Cc: Arnaldo Carvalho de Melo, lkml, Peter Zijlstra, Ingo Molnar,
Mark Rutland, Alexander Shishkin, Michael Petlan, Ian Rogers,
Stephane Eranian, Alexei Budankov
On Sat, Dec 26, 2020 at 7:21 AM Jiri Olsa <jolsa@kernel.org> wrote:
>
> Currently we allow pipe input/output only through '-' string
> being passed to '-o' or '-i' options, like:
>
> # mkfifo perf.pipe
> # perf record --no-buffering -e 'sched:sched_switch' -o - > perf.pipe &
> [1] 354406
> # cat perf.pipe | ./perf --no-pager script -i - | head -3
> perf 354406 [000] 168190.164921: sched:sched_switch: perf:354406..
> migration/0 12 [000] 168190.164928: sched:sched_switch: migration/0:..
> perf 354406 [001] 168190.164981: sched:sched_switch: perf:354406..
> ...
>
> This patch detects if given path is pipe and set the perf data
> object accordingly, so it's possible now to do above with:
>
> # mkfifo perf.pipe
> # perf record --no-buffering -e 'sched:sched_switch' -o perf.pipe &
> [1] 360188
> # perf --no-pager script -i ./perf.pipe | head -3
> perf 354442 [000] 168275.464895: sched:sched_switch: perf:354442..
> migration/0 12 [000] 168275.464902: sched:sched_switch: migration/0:..
> perf 354442 [001] 168275.464953: sched:sched_switch: perf:354442..
>
> It's of course possible to combine any of above ways.
>
> Signed-off-by: Jiri Olsa <jolsa@kernel.org>
> ---
> tools/perf/util/data.c | 27 +++++++++++++++++++++------
> 1 file changed, 21 insertions(+), 6 deletions(-)
>
> diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
> index f29af4fc3d09..767b6c903cf5 100644
> --- a/tools/perf/util/data.c
> +++ b/tools/perf/util/data.c
> @@ -159,7 +159,7 @@ int perf_data__update_dir(struct perf_data *data)
> return 0;
> }
>
> -static bool check_pipe(struct perf_data *data)
> +static int check_pipe(struct perf_data *data)
> {
> struct stat st;
> bool is_pipe = false;
> @@ -172,6 +172,15 @@ static bool check_pipe(struct perf_data *data)
> } else {
> if (!strcmp(data->path, "-"))
> is_pipe = true;
> + else if (!stat(data->path, &st) && S_ISFIFO(st.st_mode)) {
> + int flags = perf_data__is_read(data) ?
> + O_RDONLY : O_WRONLY|O_CREAT|O_TRUNC;
I don't think we need O_CREAT here (maybe O_TRUNC as well).
Thanks,
Namhyung
> +
> + fd = open(data->path, flags);
> + if (fd < 0)
> + return -EINVAL;
> + is_pipe = true;
> + }
> }
>
> if (is_pipe) {
> @@ -190,7 +199,8 @@ static bool check_pipe(struct perf_data *data)
> }
> }
>
> - return data->is_pipe = is_pipe;
> + data->is_pipe = is_pipe;
> + return 0;
> }
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH] perf tools: Detect when pipe is passed as perf data
2020-12-29 5:53 ` Namhyung Kim
@ 2020-12-29 9:45 ` Jiri Olsa
0 siblings, 0 replies; 3+ messages in thread
From: Jiri Olsa @ 2020-12-29 9:45 UTC (permalink / raw)
To: Namhyung Kim
Cc: Jiri Olsa, Arnaldo Carvalho de Melo, lkml, Peter Zijlstra,
Ingo Molnar, Mark Rutland, Alexander Shishkin, Michael Petlan,
Ian Rogers, Stephane Eranian, Alexei Budankov
On Tue, Dec 29, 2020 at 02:53:36PM +0900, Namhyung Kim wrote:
> On Sat, Dec 26, 2020 at 7:21 AM Jiri Olsa <jolsa@kernel.org> wrote:
> >
> > Currently we allow pipe input/output only through '-' string
> > being passed to '-o' or '-i' options, like:
> >
> > # mkfifo perf.pipe
> > # perf record --no-buffering -e 'sched:sched_switch' -o - > perf.pipe &
> > [1] 354406
> > # cat perf.pipe | ./perf --no-pager script -i - | head -3
> > perf 354406 [000] 168190.164921: sched:sched_switch: perf:354406..
> > migration/0 12 [000] 168190.164928: sched:sched_switch: migration/0:..
> > perf 354406 [001] 168190.164981: sched:sched_switch: perf:354406..
> > ...
> >
> > This patch detects if given path is pipe and set the perf data
> > object accordingly, so it's possible now to do above with:
> >
> > # mkfifo perf.pipe
> > # perf record --no-buffering -e 'sched:sched_switch' -o perf.pipe &
> > [1] 360188
> > # perf --no-pager script -i ./perf.pipe | head -3
> > perf 354442 [000] 168275.464895: sched:sched_switch: perf:354442..
> > migration/0 12 [000] 168275.464902: sched:sched_switch: migration/0:..
> > perf 354442 [001] 168275.464953: sched:sched_switch: perf:354442..
> >
> > It's of course possible to combine any of above ways.
> >
> > Signed-off-by: Jiri Olsa <jolsa@kernel.org>
> > ---
> > tools/perf/util/data.c | 27 +++++++++++++++++++++------
> > 1 file changed, 21 insertions(+), 6 deletions(-)
> >
> > diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
> > index f29af4fc3d09..767b6c903cf5 100644
> > --- a/tools/perf/util/data.c
> > +++ b/tools/perf/util/data.c
> > @@ -159,7 +159,7 @@ int perf_data__update_dir(struct perf_data *data)
> > return 0;
> > }
> >
> > -static bool check_pipe(struct perf_data *data)
> > +static int check_pipe(struct perf_data *data)
> > {
> > struct stat st;
> > bool is_pipe = false;
> > @@ -172,6 +172,15 @@ static bool check_pipe(struct perf_data *data)
> > } else {
> > if (!strcmp(data->path, "-"))
> > is_pipe = true;
> > + else if (!stat(data->path, &st) && S_ISFIFO(st.st_mode)) {
> > + int flags = perf_data__is_read(data) ?
> > + O_RDONLY : O_WRONLY|O_CREAT|O_TRUNC;
>
> I don't think we need O_CREAT here (maybe O_TRUNC as well).
I copied that from bash opening write end like:
openat(AT_FDCWD, "perf.pipe", O_WRONLY|O_CREAT|O_TRUNC, 0666 <detached ...>
however I can't see any check on kernel side for that,
so it can removed.. I'll send new version
thanks,
jirka
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2020-12-29 9:47 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-12-25 22:21 [PATCH] perf tools: Detect when pipe is passed as perf data Jiri Olsa
2020-12-29 5:53 ` Namhyung Kim
2020-12-29 9:45 ` Jiri Olsa
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.