[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20201207170759.GB129853@kernel.org>
Date: Mon, 7 Dec 2020 14:07:59 -0300
From: Arnaldo Carvalho de Melo <acme@...nel.org>
To: kan.liang@...ux.intel.com
Cc: mingo@...nel.org, jolsa@...hat.com, linux-kernel@...r.kernel.org,
namhyung@...nel.org, eranian@...gle.com, ak@...ux.intel.com,
mark.rutland@....com, will@...nel.org, mpe@...erman.id.au
Subject: Re: [PATCH V2 02/12] perf record: Support new sample type for data
page size
Em Mon, Nov 30, 2020 at 09:27:53AM -0800, kan.liang@...ux.intel.com escreveu:
> From: Kan Liang <kan.liang@...ux.intel.com>
>
> Support new sample type PERF_SAMPLE_DATA_PAGE_SIZE for page size.
>
> Add new option --data-page-size to record sample data page size.
So, trying this on a kernel without this feature I get:
[acme@...e perf]$ perf record --data-page-size sleep 1
Error:
The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (cycles:u).
/bin/dmesg | grep -i perf may provide additional information.
[acme@...e perf]$
I'm adding the following patch right after yours, next time please test
this and provide a similar error message.
- Arnaldo
commit 2044fec7fcc6070b09f9b6a67922b0b9e4295dba
Author: Arnaldo Carvalho de Melo <acme@...hat.com>
Date: Mon Dec 7 14:04:05 2020 -0300
perf evsel: Emit warning about kernel not supporting the data page size sample_type bit
Before we had this unhelpful message:
$ perf record --data-page-size sleep 1
Error:
The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (cycles:u).
/bin/dmesg | grep -i perf may provide additional information.
$
Add support to the perf_missing_features variable to remember what
caused evsel__open() to fail and then use that information in
evsel__open_strerror().
$ perf record --data-page-size sleep 1
Error:
Asking for the data page size isn't supported by this kernel.
$
Cc: Kan Liang <kan.liang@...ux.intel.com>
Cc: Namhyung Kim <namhyung@...nel.org>
Cc: Andi Kleen <ak@...ux.intel.com>
Cc: Jiri Olsa <jolsa@...hat.com>
Cc: Mark Rutland <mark.rutland@....com>
Cc: Michael Ellerman <mpe@...erman.id.au>
Cc: Stephane Eranian <eranian@...gle.com>
Cc: Will Deacon <will@...nel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@...hat.com>
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5e6085c3fc761a55..c26ea82220bd8625 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1873,7 +1873,12 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
* Must probe features in the order they were added to the
* perf_event_attr interface.
*/
- if (!perf_missing_features.cgroup && evsel->core.attr.cgroup) {
+ if (!perf_missing_features.data_page_size &&
+ (evsel->core.attr.sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)) {
+ perf_missing_features.data_page_size = true;
+ pr_debug2_peo("Kernel has no PERF_SAMPLE_DATA_PAGE_SIZE support, bailing out\n");
+ goto out_close;
+ } else if (!perf_missing_features.cgroup && evsel->core.attr.cgroup) {
perf_missing_features.cgroup = true;
pr_debug2_peo("Kernel has no cgroup sampling support, bailing out\n");
goto out_close;
@@ -2673,6 +2678,8 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
"We found oprofile daemon running, please stop it and try again.");
break;
case EINVAL:
+ if (evsel->core.attr.sample_type & PERF_SAMPLE_DATA_PAGE_SIZE && perf_missing_features.data_page_size)
+ return scnprintf(msg, size, "Asking for the data page size isn't supported by this kernel.");
if (evsel->core.attr.write_backward && perf_missing_features.write_backward)
return scnprintf(msg, size, "Reading from overwrite event is not supported by this kernel.");
if (perf_missing_features.clockid)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 79a860d8e3eefe23..cd1d8dd431997b84 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -144,6 +144,7 @@ struct perf_missing_features {
bool aux_output;
bool branch_hw_idx;
bool cgroup;
+ bool data_page_size;
};
extern struct perf_missing_features perf_missing_features;
Powered by blists - more mailing lists