Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
Received-SPF: Pass (protection.outlook.com: domain of amd.com designates
 165.204.84.17 as permitted sender) receiver=protection.outlook.com;
 client-ip=165.204.84.17; helo=SATLEXMB04.amd.com; pr=C
From:   Ravi Bangoria <ravi.bangoria@amd.com>
To:     <acme@kernel.org>
CC:     <ravi.bangoria@amd.com>, <irogers@google.com>,
        <peterz@infradead.org>, <rrichter@amd.com>, <mingo@redhat.com>,
        <mark.rutland@arm.com>, <jolsa@kernel.org>, <namhyung@kernel.org>,
        <tglx@linutronix.de>, <bp@alien8.de>, <james.clark@arm.com>,
        <leo.yan@linaro.org>, <kan.liang@linux.intel.com>,
        <ak@linux.intel.com>, <eranian@google.com>,
        <like.xu.linux@gmail.com>, <x86@kernel.org>,
        <linux-perf-users@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
        <sandipan.das@amd.com>, <ananth.narayan@amd.com>,
        <kim.phillips@amd.com>, <santosh.shukla@amd.com>
Subject: [PATCH v4 1/5] perf record ibs: Warn about sampling period skew
Date:   Mon, 23 May 2022 09:09:41 +0530
Message-ID: <20220523033945.1612-2-ravi.bangoria@amd.com>
In-Reply-To: <20220523033945.1612-1-ravi.bangoria@amd.com>
References: <20220523033945.1612-1-ravi.bangoria@amd.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 23 May 2022 03:40:27.2922
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: aa8d7b16-078f-4f79-117e-08da3c6dfa41
X-MS-Exchange-CrossTenant-Id: 3dd8961f-e488-4e60-8e11-a82d994e183d
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=3dd8961f-e488-4e60-8e11-a82d994e183d;Ip=[165.204.84.17];Helo=[SATLEXMB04.amd.com]
X-MS-Exchange-CrossTenant-AuthSource: DM6NAM11FT033.eop-nam11.prod.protection.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: DM6PR12MB4878
X-Spam-Status: No, score=-2.0 required=5.0 tests=BAYES_00,DKIM_SIGNED,
	DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS,
	MAILING_LIST_MULTI,RDNS_NONE,SPF_HELO_NONE,T_SCC_BODY_TEXT_LINE
	autolearn=no autolearn_force=no version=3.4.6
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on
	lindbergh.monkeyblade.net
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

Samples without an L3 miss are discarded and counter is reset with
random value (between 1-15 for fetch pmu and 1-127 for op pmu) when
IBS L3 miss filtering is enabled. This causes a sampling period skew
but there is no way to reconstruct aggregated sampling period. So
print a warning at perf record if user sets l3missonly=1.

Ex:
  # perf record -c 10000 -C 0 -e ibs_op/l3missonly=1/
  WARNING: Hw internally resets sampling period when L3 Miss Filtering is enabled
  and tagged operation does not cause L3 Miss. This causes sampling period skew.

Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Acked-by: Ian Rogers <irogers@google.com>
---
 tools/perf/arch/x86/util/evsel.c | 50 ++++++++++++++++++++++++++++++++
 tools/perf/util/evsel.c          |  7 +++++
 tools/perf/util/evsel.h          |  1 +
 3 files changed, 58 insertions(+)

diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c
index ac2899a25b7a..e8ff4ddb53c9 100644
--- a/tools/perf/arch/x86/util/evsel.c
+++ b/tools/perf/arch/x86/util/evsel.c
@@ -4,6 +4,8 @@
 #include "util/evsel.h"
 #include "util/env.h"
 #include "linux/string.h"
+#include "util/pmu.h"
+#include "util/debug.h"
 
 void arch_evsel__set_sample_weight(struct evsel *evsel)
 {
@@ -29,3 +31,51 @@ void arch_evsel__fixup_new_cycles(struct perf_event_attr *attr)
 
 	free(env.cpuid);
 }
+
+static void ibs_l3miss_warn(void)
+{
+	pr_warning(
+"WARNING: Hw internally resets sampling period when L3 Miss Filtering is enabled\n"
+"and tagged operation does not cause L3 Miss. This causes sampling period skew.\n");
+}
+
+void arch__post_evsel_config(struct evsel *evsel, struct perf_event_attr *attr)
+{
+	struct perf_pmu *evsel_pmu, *ibs_fetch_pmu, *ibs_op_pmu;
+	static int warned_once;
+	/* 0: Uninitialized, 1: Yes, -1: No */
+	static int is_amd;
+
+	if (warned_once || is_amd == -1)
+		return;
+
+	if (!is_amd) {
+		struct perf_env *env = evsel__env(evsel);
+
+		if (!perf_env__cpuid(env) || !env->cpuid ||
+		    !strstarts(env->cpuid, "AuthenticAMD")) {
+			is_amd = -1;
+			return;
+		}
+		is_amd = 1;
+	}
+
+	evsel_pmu = evsel__find_pmu(evsel);
+	if (!evsel_pmu)
+		return;
+
+	ibs_fetch_pmu = perf_pmu__find("ibs_fetch");
+	ibs_op_pmu = perf_pmu__find("ibs_op");
+
+	if (ibs_fetch_pmu && ibs_fetch_pmu->type == evsel_pmu->type) {
+		if (attr->config & (1ULL << 59)) {
+			ibs_l3miss_warn();
+			warned_once = 1;
+		}
+	} else if (ibs_op_pmu && ibs_op_pmu->type == evsel_pmu->type) {
+		if (attr->config & (1ULL << 16)) {
+			ibs_l3miss_warn();
+			warned_once = 1;
+		}
+	}
+}
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 2a1729e7aee4..e9be9b94a062 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1064,6 +1064,11 @@ void __weak arch_evsel__fixup_new_cycles(struct perf_event_attr *attr __maybe_un
 {
 }
 
+void __weak arch__post_evsel_config(struct evsel *evsel __maybe_unused,
+				    struct perf_event_attr *attr __maybe_unused)
+{
+}
+
 static void evsel__set_default_freq_period(struct record_opts *opts,
 					   struct perf_event_attr *attr)
 {
@@ -1339,6 +1344,8 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
 	 */
 	if (evsel__is_dummy_event(evsel))
 		evsel__reset_sample_bit(evsel, BRANCH_STACK);
+
+	arch__post_evsel_config(evsel, attr);
 }
 
 int evsel__set_filter(struct evsel *evsel, const char *filter)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 041b42d33bf5..207de5082ee9 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -281,6 +281,7 @@ void evsel__set_sample_id(struct evsel *evsel, bool use_sample_identifier);
 
 void arch_evsel__set_sample_weight(struct evsel *evsel);
 void arch_evsel__fixup_new_cycles(struct perf_event_attr *attr);
+void arch__post_evsel_config(struct evsel *evsel, struct perf_event_attr *attr);
 
 int evsel__set_filter(struct evsel *evsel, const char *filter);
 int evsel__append_tp_filter(struct evsel *evsel, const char *filter);
-- 
2.31.1