linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Kim Phillips <kim.phillips@amd.com>
To: Stephane Eranian <eranian@google.com>, linux-kernel@vger.kernel.org
Cc: peterz@infradead.org, acme@redhat.com, jolsa@redhat.com,
	namhyung@kernel.org, irogers@google.com
Subject: Re: [PATCH v1 12/13] perf tools: improve error handling of AMD Branch Sampling
Date: Mon, 4 Oct 2021 16:57:37 -0500	[thread overview]
Message-ID: <3fa173c8-2f36-adf5-c55b-ff356c49715f@amd.com> (raw)
In-Reply-To: <20210909075700.4025355-13-eranian@google.com>

[-- Attachment #1: Type: text/plain, Size: 1163 bytes --]

On 9/9/21 2:56 AM, Stephane Eranian wrote:
> This patch improves the error message printed by perf when perf_event_open()
> fails on AMD Zen3 when using the branch sampling feature. In the case of
> EINVAL, there are two main reasons: frequency mode or period is smaller than
> the depth of the branch sampling buffer (16). The patch checks the parameters
> of the call and tries to print a relevant message to explain the error:
> 
> $ perf record -b -e cpu/branch-brs/ -c 10 ls
> Error:
> AMD Branch Sampling does not support sampling period smaller than what is reported in /sys/devices/cpu/caps/branches.
> 
> $ perf record -b -e cpu/branch-brs/ ls
> Error:
> AMD Branch Sampling does not support frequency mode sampling, must pass a fixed sampling period via -c option or cpu/branch-brs,period=xxxx/.
> 
> Signed-off-by: Stephane Eranian <eranian@google.com>
> ---

Hi Stephane,

I've rewritten this patch based on Arnaldo's comments to the previous 
(11/13) patch.  The new version attached depends on this 2-patch series:

https://lore.kernel.org/lkml/20211004214114.188477-1-kim.phillips@amd.com/T/#mc4c9c582e3816ab31af6d0187e6803de1a98ac84

Thanks,

Kim

[-- Attachment #2: 0003-perf-tools-Improve-error-handling-of-AMD-Branch-Samp.patch --]
[-- Type: text/x-patch, Size: 2583 bytes --]

From a4cbab762719b30bddec2e278cf8b8eb82e83865 Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Thu, 9 Sep 2021 00:56:59 -0700
Subject: [PATCH] perf tools: Improve error handling of AMD Branch Sampling

This patch improves the error message printed by perf when
perf_event_open() fails on AMD Zen3 when using the branch sampling
feature. In the case of EINVAL, there are two main reasons: frequency
mode or period is smaller than the depth of the branch sampling
buffer (16). The patch checks the parameters of the call and tries
to print a relevant message to explain the error:

$ perf record -b -e cpu/branch-brs/ -c 10 ls
Error:
AMD Branch Sampling does not support sampling period smaller than what is reported in /sys/devices/cpu/caps/branches.

$ perf record -b -e cpu/branch-brs/ ls
Error:
AMD Branch Sampling does not support frequency mode sampling, must pass a fixed sampling period via -c option or cpu/branch-brs,period=xxxx/.

Signed-off-by: Stephane Eranian <eranian@google.com>
[Rebased on commit 9fe8895a27a84 ("perf env: Add perf_env__cpuid, perf_env__{nr_}pmu_mappings")]
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
---
 tools/perf/util/evsel.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f8a9cbd99314..e1f5eff07355 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2753,6 +2753,12 @@ static bool is_amd_ibs(struct evsel *evsel)
 	return evsel->core.attr.precise_ip || !strncmp(evsel->pmu_name, "ibs", 3);
 }
 
+static bool is_amd_brs(struct evsel *evsel)
+{
+	return ((evsel->core.attr.config & 0xff) == 0xc4) &&
+	       (evsel->core.attr.sample_type & PERF_SAMPLE_BRANCH_STACK);
+}
+
 int evsel__open_strerror(struct evsel *evsel, struct target *target,
 			 int err, char *msg, size_t size)
 {
@@ -2863,6 +2869,14 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
 					return scnprintf(msg, size,
 	"AMD IBS may only be available in system-wide/per-cpu mode.  Try using -a, or -C and workload affinity");
 			}
+			if (is_amd_brs(evsel)) {
+				if (evsel->core.attr.freq)
+					return scnprintf(msg, size,
+	"AMD Branch Sampling does not support frequency mode sampling, must pass a fixed sampling period via -c option or cpu/branch-brs,period=xxxx/.");
+				/* another reason is that the period is too small */
+				return scnprintf(msg, size,
+	"AMD Branch Sampling does not support sampling period smaller than what is reported in /sys/devices/cpu/caps/branches.");
+			}
 		}
 
 		break;
-- 
2.31.1


  reply	other threads:[~2021-10-04 21:57 UTC|newest]

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-09  7:56 [PATCH v1 00/13] perf/x86/amd: Add AMD Fam19h Branch Sampling support Stephane Eranian
2021-09-09  7:56 ` [PATCH v1 01/13] perf/core: add union to struct perf_branch_entry Stephane Eranian
2021-09-09 19:03   ` Peter Zijlstra
2021-09-10 12:09     ` Michael Ellerman
2021-09-10 14:16       ` Michael Ellerman
2021-09-15  6:03         ` Stephane Eranian
2021-09-17  6:37           ` Madhavan Srinivasan
2021-09-17  6:48             ` Stephane Eranian
2021-09-17  7:05               ` Michael Ellerman
2021-09-17  7:39                 ` Stephane Eranian
2021-09-17 12:38                   ` Michael Ellerman
2021-09-17 16:42                     ` Stephane Eranian
2021-09-19 10:27                       ` Michael Ellerman
2021-09-09  7:56 ` [PATCH v1 02/13] x86/cpufeatures: add AMD Fam19h Branch Sampling feature Stephane Eranian
2021-09-09  7:56 ` [PATCH v1 03/13] perf/x86/amd: add AMD Fam19h Branch Sampling support Stephane Eranian
2021-09-09 10:44   ` kernel test robot
2021-09-09 15:33   ` kernel test robot
2021-09-09  7:56 ` [PATCH v1 04/13] perf/x86/amd: add branch-brs helper event for Fam19h BRS Stephane Eranian
2021-09-09  7:56 ` [PATCH v1 05/13] perf/x86/amd: enable branch sampling priv level filtering Stephane Eranian
2021-09-09  7:56 ` [PATCH v1 06/13] perf/x86/amd: add AMD branch sampling period adjustment Stephane Eranian
2021-09-09  7:56 ` [PATCH v1 07/13] perf/core: add idle hooks Stephane Eranian
2021-09-09  9:15   ` Peter Zijlstra
2021-09-09 10:42   ` kernel test robot
2021-09-09 11:02   ` kernel test robot
2021-09-09  7:56 ` [PATCH v1 08/13] perf/x86/core: " Stephane Eranian
2021-09-09  9:16   ` Peter Zijlstra
2021-09-09  7:56 ` [PATCH v1 09/13] perf/x86/amd: add idle hooks for branch sampling Stephane Eranian
2021-09-09  9:20   ` Peter Zijlstra
2021-09-09  7:56 ` [PATCH v1 10/13] perf tools: add branch-brs as a new event Stephane Eranian
2021-09-09  7:56 ` [PATCH v1 11/13] perf tools: improve IBS error handling Stephane Eranian
2021-09-13 19:34   ` Arnaldo Carvalho de Melo
2021-10-04 21:57     ` Kim Phillips
2021-10-04 23:44       ` Arnaldo Carvalho de Melo
2021-09-09  7:56 ` [PATCH v1 12/13] perf tools: improve error handling of AMD Branch Sampling Stephane Eranian
2021-10-04 21:57   ` Kim Phillips [this message]
2021-09-09  7:57 ` [PATCH v1 13/13] perf report: add addr_from/addr_to sort dimensions Stephane Eranian
2021-09-09  8:55 ` [PATCH v1 00/13] perf/x86/amd: Add AMD Fam19h Branch Sampling support Peter Zijlstra
2021-09-15  5:55   ` Stephane Eranian
2021-09-15  9:04     ` Peter Zijlstra
2021-10-28 18:30       ` Stephane Eranian
2021-09-27 20:17     ` Song Liu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=3fa173c8-2f36-adf5-c55b-ff356c49715f@amd.com \
    --to=kim.phillips@amd.com \
    --cc=acme@redhat.com \
    --cc=eranian@google.com \
    --cc=irogers@google.com \
    --cc=jolsa@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).