[PATCH v6 1/8] perf record ibs: Warn about sampling period skew

[Ravi Bangoria]

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@xxxxxxx>
Acked-by: Ian Rogers <irogers@xxxxxxxxxx>
---
 tools/perf/arch/x86/util/evsel.c | 52 ++++++++++++++++++++++++++++++++
 tools/perf/util/evsel.c          |  7 +++++
 tools/perf/util/evsel.h          |  1 +
 3 files changed, 60 insertions(+)

diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c
index 88306183d629..53763e583804 100644
--- a/tools/perf/arch/x86/util/evsel.c
+++ b/tools/perf/arch/x86/util/evsel.c
@@ -5,6 +5,10 @@
 #include "util/env.h"
 #include "util/pmu.h"
 #include "linux/string.h"
+#include "util/debug.h"
+
+#define IBS_FETCH_L3MISSONLY	(1ULL << 59)
+#define IBS_OP_L3MISSONLY	(1ULL << 16)
 
 void arch_evsel__set_sample_weight(struct evsel *evsel)
 {
@@ -60,3 +64,51 @@ bool arch_evsel__must_be_in_group(const struct evsel *evsel)
 		(!strcasecmp(evsel->name, "slots") ||
 		 strcasestr(evsel->name, "topdown"));
 }
+
+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 & IBS_FETCH_L3MISSONLY) {
+			ibs_l3miss_warn();
+			warned_once = 1;
+		}
+	} else if (ibs_op_pmu && ibs_op_pmu->type == evsel_pmu->type) {
+		if (attr->config & IBS_OP_L3MISSONLY) {
+			ibs_l3miss_warn();
+			warned_once = 1;
+		}
+	}
+}
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ce499c5da8d7..8fea51a9cd90 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1091,6 +1091,11 @@ 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)
 {
@@ -1366,6 +1371,8 @@ 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 73ea48e94079..92bed8e2f7d8 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -297,6 +297,7 @@ 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