This is a note to let you know that I've just added the patch titled
perf tool x86: Consolidate is_amd check into single function
to the 6.3-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
perf-tool-x86-consolidate-is_amd-check-into-single-f.patch
and it can be found in the queue-6.3 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit e2c562d23ee72769ca0df876a9640e213aea8531
Author: Ravi Bangoria <ravi.bangoria@xxxxxxx>
Date: Tue Jun 13 15:25:04 2023 +0530
perf tool x86: Consolidate is_amd check into single function
[ Upstream commit 0cd1ca4650c9cf5f318110f67d39cbebae3693b3 ]
There are multiple places where x86 specific code determines AMD vs
Intel arch and acts based on that. Consolidate those checks into a
single function.
Signed-off-by: Ravi Bangoria <ravi.bangoria@xxxxxxx>
Acked-by: Ian Rogers <irogers@xxxxxxxxxx>
Cc: Adrian Hunter <adrian.hunter@xxxxxxxxx>
Cc: Ali Saidi <alisaidi@xxxxxxxxxx>
Cc: Ananth Narayan <ananth.narayan@xxxxxxx>
Cc: James Clark <james.clark@xxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
Cc: Leo Yan <leo.yan@xxxxxxxxxx>
Cc: Madhavan Srinivasan <maddy@xxxxxxxxxxxxx>
Cc: Mark Rutland <mark.rutland@xxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Sandipan Das <sandipan.das@xxxxxxx>
Cc: Santosh Shukla <santosh.shukla@xxxxxxx>
Link: https://lore.kernel.org/r/20230613095506.547-3-ravi.bangoria@xxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Stable-dep-of: 99d4850062a8 ("perf tool x86: Fix perf_env memory leak")
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index 195ccfdef7aa1..005907cb97d8c 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -10,6 +10,7 @@ perf-y += evlist.o
perf-y += mem-events.o
perf-y += evsel.o
perf-y += iostat.o
+perf-y += env.o
perf-$(CONFIG_DWARF) += dwarf-regs.o
perf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
diff --git a/tools/perf/arch/x86/util/env.c b/tools/perf/arch/x86/util/env.c
new file mode 100644
index 0000000000000..33b87f8ac1cc1
--- /dev/null
+++ b/tools/perf/arch/x86/util/env.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "linux/string.h"
+#include "util/env.h"
+#include "env.h"
+
+bool x86__is_amd_cpu(void)
+{
+ struct perf_env env = { .total_mem = 0, };
+ static int is_amd; /* 0: Uninitialized, 1: Yes, -1: No */
+
+ if (is_amd)
+ goto ret;
+
+ perf_env__cpuid(&env);
+ is_amd = env.cpuid && strstarts(env.cpuid, "AuthenticAMD") ? 1 : -1;
+
+ret:
+ return is_amd >= 1 ? true : false;
+}
diff --git a/tools/perf/arch/x86/util/env.h b/tools/perf/arch/x86/util/env.h
new file mode 100644
index 0000000000000..d78f080b6b3f8
--- /dev/null
+++ b/tools/perf/arch/x86/util/env.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _X86_ENV_H
+#define _X86_ENV_H
+
+bool x86__is_amd_cpu(void);
+
+#endif /* _X86_ENV_H */
diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c
index ea3972d785d10..d72390cdf391d 100644
--- a/tools/perf/arch/x86/util/evsel.c
+++ b/tools/perf/arch/x86/util/evsel.c
@@ -7,6 +7,7 @@
#include "linux/string.h"
#include "evsel.h"
#include "util/debug.h"
+#include "env.h"
#define IBS_FETCH_L3MISSONLY (1ULL << 59)
#define IBS_OP_L3MISSONLY (1ULL << 16)
@@ -97,23 +98,10 @@ 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)
+ if (warned_once || !x86__is_amd_cpu())
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;
diff --git a/tools/perf/arch/x86/util/mem-events.c b/tools/perf/arch/x86/util/mem-events.c
index f683ac702247c..efc0fae9ed0a7 100644
--- a/tools/perf/arch/x86/util/mem-events.c
+++ b/tools/perf/arch/x86/util/mem-events.c
@@ -4,6 +4,7 @@
#include "map_symbol.h"
#include "mem-events.h"
#include "linux/string.h"
+#include "env.h"
static char mem_loads_name[100];
static bool mem_loads_name__init;
@@ -26,28 +27,12 @@ static struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX] = {
E("mem-ldst", "ibs_op//", "ibs_op"),
};
-static int perf_mem_is_amd_cpu(void)
-{
- struct perf_env env = { .total_mem = 0, };
-
- perf_env__cpuid(&env);
- if (env.cpuid && strstarts(env.cpuid, "AuthenticAMD"))
- return 1;
- return -1;
-}
-
struct perf_mem_event *perf_mem_events__ptr(int i)
{
- /* 0: Uninitialized, 1: Yes, -1: No */
- static int is_amd;
-
if (i >= PERF_MEM_EVENTS__MAX)
return NULL;
- if (!is_amd)
- is_amd = perf_mem_is_amd_cpu();
-
- if (is_amd == 1)
+ if (x86__is_amd_cpu())
return &perf_mem_events_amd[i];
return &perf_mem_events_intel[i];
