| 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
| ||
|
Date: Mon, 7 Aug 2023 15:20:49 +0100
From: James Clark <james.clark@....com>
To: linux-perf-users@...r.kernel.org, irogers@...gle.com,
john.g.garry@...cle.com, renyu.zj@...ux.alibaba.com
Cc: James Clark <james.clark@....com>, Will Deacon <will@...nel.org>,
Mike Leach <mike.leach@...aro.org>,
Leo Yan <leo.yan@...aro.org>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Jiri Olsa <jolsa@...nel.org>,
Namhyung Kim <namhyung@...nel.org>,
Adrian Hunter <adrian.hunter@...el.com>,
Suzuki K Poulose <suzuki.poulose@....com>,
Kajol Jain <kjain@...ux.ibm.com>,
Kan Liang <kan.liang@...ux.intel.com>,
Nick Forrington <nick.forrington@....com>,
Eduard Zingerman <eddyz87@...il.com>,
Rob Herring <robh@...nel.org>, linux-kernel@...r.kernel.org,
linux-arm-kernel@...ts.infradead.org, coresight@...ts.linaro.org
Subject: [PATCH v4 5/6] perf vendor events arm64: Update stall_slot workaround for N2 r0p3
N2 r0p3 doesn't require the workaround [1], so gating on (#slots - 5) no
longer works because all N2s have 5 slots. Add a new expression builtin
that identifies the need for the workaround correctly.
[1]: https://gitlab.arm.com/telemetry-solution/telemetry-solution/-/blob/main/data/pmu/cpu/neoverse/neoverse-n2-r0p3.json
Signed-off-by: James Clark <james.clark@....com>
---
tools/perf/arch/arm64/util/pmu.c | 21 +++++++++++++++++++
.../arm64/arm/neoverse-n2-v2/metrics.json | 8 +++----
tools/perf/util/expr.c | 4 ++++
tools/perf/util/pmu.c | 6 ++++++
tools/perf/util/pmu.h | 1 +
5 files changed, 36 insertions(+), 4 deletions(-)
diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c
index 561de0cb6b95..30e2385a83cf 100644
--- a/tools/perf/arch/arm64/util/pmu.c
+++ b/tools/perf/arch/arm64/util/pmu.c
@@ -2,6 +2,7 @@
#include <internal/cpumap.h>
#include "../../../util/cpumap.h"
+#include "../../../util/header.h"
#include "../../../util/pmu.h"
#include "../../../util/pmus.h"
#include <api/fs/fs.h>
@@ -62,3 +63,23 @@ double perf_pmu__cpu_slots_per_cycle(void)
return slots ? (double)slots : NAN;
}
+
+double perf_pmu__no_stall_errata(void)
+{
+ struct perf_pmu *pmu = pmu__find_core_pmu();
+ char *cpuid = perf_pmu__getcpuid(pmu);
+ bool n2_r0p3_plus;
+ bool not_n2;
+
+ if (!cpuid)
+ return NAN;
+
+ /* N2 r0p3+ doesn't need CPU_CYCLES to be subtracted from slots. */
+ n2_r0p3_plus = !strcmp_cpuid_str("0x00000000410fd493", cpuid);
+
+ /* Anything other than N2 doesn't need the workaround either */
+ not_n2 = strcmp_cpuid_str("0x00000000410fd490", cpuid);
+
+ free(cpuid);
+ return n2_r0p3_plus || not_n2;
+}
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json
index 8ad15b726dca..9b912a9427f6 100644
--- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json
@@ -1,15 +1,15 @@
[
{
"ArchStdEvent": "FRONTEND_BOUND",
- "MetricExpr": "((stall_slot_frontend) if (#slots - 5) else (stall_slot_frontend - cpu_cycles)) / (#slots * cpu_cycles)"
+ "MetricExpr": "((stall_slot_frontend) if (#no_stall_errata) else (stall_slot_frontend - cpu_cycles)) / (#slots * cpu_cycles)"
},
{
"ArchStdEvent": "BAD_SPECULATION",
- "MetricExpr": "(1 - op_retired / op_spec) * (1 - (stall_slot if (#slots - 5) else (stall_slot - cpu_cycles)) / (#slots * cpu_cycles))"
+ "MetricExpr": "(1 - op_retired / op_spec) * (1 - (stall_slot if (#no_stall_errata) else (stall_slot - cpu_cycles)) / (#slots * cpu_cycles))"
},
{
"ArchStdEvent": "RETIRING",
- "MetricExpr": "(op_retired / op_spec) * (1 - (stall_slot if (#slots - 5) else (stall_slot - cpu_cycles)) / (#slots * cpu_cycles))"
+ "MetricExpr": "(op_retired / op_spec) * (1 - (stall_slot if (#no_stall_errata) else (stall_slot - cpu_cycles)) / (#slots * cpu_cycles))"
},
{
"ArchStdEvent": "BACKEND_BOUND"
@@ -201,7 +201,7 @@
"ScaleUnit": "100%"
},
{
- "MetricExpr": "OP_RETIRED / OP_SPEC * (1 - (STALL_SLOT if (#slots - 5) else (STALL_SLOT - CPU_CYCLES)) / (#slots * CPU_CYCLES))",
+ "MetricExpr": "OP_RETIRED / OP_SPEC * (1 - (STALL_SLOT if (#no_stall_errata) else (STALL_SLOT - CPU_CYCLES)) / (#slots * CPU_CYCLES))",
"BriefDescription": "The truly effective ratio of micro-operations executed by the CPU, which means that misprediction and stall are not included",
"MetricGroup": "PEutilization",
"MetricName": "cpu_utilization",
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index 7410a165f68b..3bae19785796 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -465,6 +465,10 @@ double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx
result = perf_pmu__cpu_slots_per_cycle();
goto out;
}
+ if (!strcmp("#no_stall_errata", literal)) {
+ result = perf_pmu__no_stall_errata();
+ goto out;
+ }
if (!strcmp("#has_pmem", literal)) {
result = has_pmem();
goto out;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index b6654b9f55d2..d37dc7202ddb 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1779,3 +1779,9 @@ void perf_pmu__delete(struct perf_pmu *pmu)
zfree(&pmu->alias_name);
free(pmu);
}
+
+__weak double perf_pmu__no_stall_errata(void)
+{
+ /* Only exists on Arm */
+ return NAN;
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 203b92860e3c..57c002308f9a 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -288,5 +288,6 @@ int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename,
struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name);
struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus);
void perf_pmu__delete(struct perf_pmu *pmu);
+double perf_pmu__no_stall_errata(void);
#endif /* __PMU_H */
--
2.34.1
Powered by blists - more mailing lists