linux-kernel - [PATCH v2 1/3] perf pmus: Describe semantics of 'core_pmus' and 'other

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20230615051700.1833-2-ravi.bangoria@amd.com>
Date:   Thu, 15 Jun 2023 10:46:58 +0530
From:   Ravi Bangoria <ravi.bangoria@....com>
To:     <acme@...nel.org>
CC:     <ravi.bangoria@....com>, <irogers@...gle.com>, <jolsa@...nel.org>,
        <namhyung@...nel.org>, <peterz@...radead.org>,
        <james.clark@....com>, <alisaidi@...zon.com>, <leo.yan@...aro.org>,
        <adrian.hunter@...el.com>, <kan.liang@...ux.intel.com>,
        <mark.rutland@....com>, <maddy@...ux.ibm.com>,
        <tmricht@...ux.ibm.com>, <linux-perf-users@...r.kernel.org>,
        <linux-kernel@...r.kernel.org>, <sandipan.das@....com>,
        <ananth.narayan@....com>, <santosh.shukla@....com>
Subject: [PATCH v2 1/3] perf pmus: Describe semantics of 'core_pmus' and 'other_pmus'

Notion of 'core_pmus' and 'other_pmus' are independent of hw core and
uncore pmus. For example, AMD IBS PMUs are present in each SMT-thread
but they belongs to 'other_pmus'. Add a comment describing what these
list contains and how they are treated.

Signed-off-by: Ravi Bangoria <ravi.bangoria@....com>
---
 tools/perf/util/pmus.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index e1d0a93147e5..8c50ab8894b7 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -12,6 +12,21 @@
 #include "pmu.h"
 #include "print-events.h"
 
+/*
+ * core_pmus:  A PMU belongs to core_pmus if it's name is "cpu" or it's sysfs
+ *             directory contains "cpus" file. All PMUs belonging to core_pmus
+ *             must have pmu->is_core=1. If there are more than one PMU in
+ *             this list, perf interprets it as a heterogeneous platform.
+ *             (FWIW, certain ARM platforms having heterogeneous cores uses
+ *             homogeneous PMU, and thus they are treated as homogeneous
+ *             platform by perf because core_pmus will have only one entry)
+ * other_pmus: All other PMUs which are not part of core_pmus list. It doesn't
+ *             matter whether PMU is present per SMT-thread or outside of the
+ *             core in the hw. For e.g., an instance of AMD ibs_fetch// and
+ *             ibs_op// PMUs is present in each hw SMT thread, however they
+ *             are captured under other_pmus. PMUs belonging to other_pmus
+ *             must have pmu->is_core=0 but pmu->is_uncore could be 0 or 1.
+ */
 static LIST_HEAD(core_pmus);
 static LIST_HEAD(other_pmus);
 static bool read_sysfs_core_pmus;
-- 
2.40.1