[PATCH v1 0/7] Refactor cpuid and metric table lookup code

[PATCH v1 0/7] Refactor cpuid and metric table lookup code

[Ian Rogers]

Xu Yang <xu.yang_2@nxp.com> reported issues with the system metric
lookup:
https://lore.kernel.org/linux-perf-users/20241106085441.3945502-1-xu.yang_2@nxp.com/
These patches remove a lot of the logic relating CPUIDs to PMUs so
that the PMU isn't part of the question when finding a metric table.
For time reasons, it doesn't go as far as allowing system metrics
without a metric table as a metric table is needed for metrics to
refer to other metrics, and the refactoring of that resolution is a
hassle.

Ian Rogers (7):
  perf header: Move is_cpu_online to numa bench
  perf header: Refactor get_cpuid to take a CPU for ARM
  perf arm64 header: Use cpu argument in get_cpuid
  perf header: Avoid transitive PMU includes
  perf header: Pass a perf_cpu rather than a PMU to get_cpuid_str
  perf jevents: Add map_for_cpu
  perf pmu: Move pmu_metrics_table__find and remove ARM override

 tools/perf/arch/arm64/util/arm-spe.c     | 14 +---
 tools/perf/arch/arm64/util/header.c      | 73 ++++++++++-----------
 tools/perf/arch/arm64/util/pmu.c         | 20 ------
 tools/perf/arch/loongarch/util/header.c  |  4 +-
 tools/perf/arch/powerpc/util/header.c    |  4 +-
 tools/perf/arch/riscv/util/header.c      |  4 +-
 tools/perf/arch/s390/util/header.c       |  6 +-
 tools/perf/arch/x86/util/auxtrace.c      |  3 +-
 tools/perf/arch/x86/util/header.c        |  5 +-
 tools/perf/bench/numa.c                  | 51 +++++++++++++++
 tools/perf/builtin-kvm.c                 |  4 +-
 tools/perf/pmu-events/empty-pmu-events.c | 39 ++++++-----
 tools/perf/pmu-events/jevents.py         | 39 ++++++-----
 tools/perf/pmu-events/pmu-events.h       |  2 +-
 tools/perf/tests/expr.c                  |  5 +-
 tools/perf/util/env.c                    |  4 +-
 tools/perf/util/expr.c                   |  6 +-
 tools/perf/util/header.c                 | 82 ++++++++----------------
 tools/perf/util/header.h                 | 23 +++----
 tools/perf/util/pmu.c                    | 25 --------
 tools/perf/util/pmu.h                    |  2 -
 tools/perf/util/probe-event.c            |  1 +
 22 files changed, 187 insertions(+), 229 deletions(-)

-- 
2.47.0.199.ga7371fff76-goog

[PATCH v1 1/7] perf header: Move is_cpu_online to numa bench

[Ian Rogers]

The helper function is only used in the NUMA benchmark as typically
online CPUs are determined through
perf_cpu_map__new_online_cpus(). Reduce the scope of the function for
now.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/bench/numa.c  | 51 ++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/header.c | 51 ----------------------------------------
 tools/perf/util/header.h |  1 -
 3 files changed, 51 insertions(+), 52 deletions(-)

diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 1fbd7c947abc..611451dbc234 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -533,6 +533,57 @@ static int parse_cpu_list(const char *arg)
 	return 0;
 }
 
+/*
+ * Check whether a CPU is online
+ *
+ * Returns:
+ *     1 -> if CPU is online
+ *     0 -> if CPU is offline
+ *    -1 -> error case
+ */
+static int is_cpu_online(unsigned int cpu)
+{
+	char *str;
+	size_t strlen;
+	char buf[256];
+	int status = -1;
+	struct stat statbuf;
+
+	snprintf(buf, sizeof(buf),
+		"/sys/devices/system/cpu/cpu%d", cpu);
+	if (stat(buf, &statbuf) != 0)
+		return 0;
+
+	/*
+	 * Check if /sys/devices/system/cpu/cpux/online file
+	 * exists. Some cases cpu0 won't have online file since
+	 * it is not expected to be turned off generally.
+	 * In kernels without CONFIG_HOTPLUG_CPU, this
+	 * file won't exist
+	 */
+	snprintf(buf, sizeof(buf),
+		"/sys/devices/system/cpu/cpu%d/online", cpu);
+	if (stat(buf, &statbuf) != 0)
+		return 1;
+
+	/*
+	 * Read online file using sysfs__read_str.
+	 * If read or open fails, return -1.
+	 * If read succeeds, return value from file
+	 * which gets stored in "str"
+	 */
+	snprintf(buf, sizeof(buf),
+		"devices/system/cpu/cpu%d/online", cpu);
+
+	if (sysfs__read_str(buf, &str, &strlen) < 0)
+		return status;
+
+	status = atoi(str);
+
+	free(str);
+	return status;
+}
+
 static int parse_setup_cpu_list(void)
 {
 	struct thread_data *td;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index a6386d12afd7..55c28e4377ec 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -987,57 +987,6 @@ static int write_dir_format(struct feat_fd *ff,
 	return do_write(ff, &data->dir.version, sizeof(data->dir.version));
 }
 
-/*
- * Check whether a CPU is online
- *
- * Returns:
- *     1 -> if CPU is online
- *     0 -> if CPU is offline
- *    -1 -> error case
- */
-int is_cpu_online(unsigned int cpu)
-{
-	char *str;
-	size_t strlen;
-	char buf[256];
-	int status = -1;
-	struct stat statbuf;
-
-	snprintf(buf, sizeof(buf),
-		"/sys/devices/system/cpu/cpu%d", cpu);
-	if (stat(buf, &statbuf) != 0)
-		return 0;
-
-	/*
-	 * Check if /sys/devices/system/cpu/cpux/online file
-	 * exists. Some cases cpu0 won't have online file since
-	 * it is not expected to be turned off generally.
-	 * In kernels without CONFIG_HOTPLUG_CPU, this
-	 * file won't exist
-	 */
-	snprintf(buf, sizeof(buf),
-		"/sys/devices/system/cpu/cpu%d/online", cpu);
-	if (stat(buf, &statbuf) != 0)
-		return 1;
-
-	/*
-	 * Read online file using sysfs__read_str.
-	 * If read or open fails, return -1.
-	 * If read succeeds, return value from file
-	 * which gets stored in "str"
-	 */
-	snprintf(buf, sizeof(buf),
-		"devices/system/cpu/cpu%d/online", cpu);
-
-	if (sysfs__read_str(buf, &str, &strlen) < 0)
-		return status;
-
-	status = atoi(str);
-
-	free(str);
-	return status;
-}
-
 #ifdef HAVE_LIBBPF_SUPPORT
 static int write_bpf_prog_info(struct feat_fd *ff,
 			       struct evlist *evlist __maybe_unused)
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index a63a361f20f4..e91e89d22537 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -196,7 +196,6 @@ int write_padded(struct feat_fd *fd, const void *bf,
 
 #define MAX_CACHE_LVL 4
 
-int is_cpu_online(unsigned int cpu);
 int build_caches_for_cpu(u32 cpu, struct cpu_cache_level caches[], u32 *cntp);
 
 /*
-- 
2.47.0.199.ga7371fff76-goog

[PATCH v1 2/7] perf header: Refactor get_cpuid to take a CPU for ARM

[Ian Rogers]

ARM BIG.little has no notion of a constant CPUID for both core
types. To reflect this reality, change the get_cpuid function to also
pass in a possibly unused logical cpu. If the dummy value (-1) is
passed in then ARM can, as currently happens, select the first logical
CPU's "CPUID". The changes to ARM getcpuid happen in a follow up
change.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/arch/arm64/util/header.c     | 2 +-
 tools/perf/arch/loongarch/util/header.c | 2 +-
 tools/perf/arch/powerpc/util/header.c   | 2 +-
 tools/perf/arch/riscv/util/header.c     | 2 +-
 tools/perf/arch/s390/util/header.c      | 2 +-
 tools/perf/arch/x86/util/auxtrace.c     | 3 ++-
 tools/perf/arch/x86/util/header.c       | 2 +-
 tools/perf/builtin-kvm.c                | 4 +++-
 tools/perf/util/env.c                   | 3 ++-
 tools/perf/util/header.c                | 9 +++++----
 tools/perf/util/header.h                | 2 +-
 11 files changed, 19 insertions(+), 14 deletions(-)

diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c
index 741df3614a09..760c21784713 100644
--- a/tools/perf/arch/arm64/util/header.c
+++ b/tools/perf/arch/arm64/util/header.c
@@ -50,7 +50,7 @@ static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus)
 	return ret;
 }
 
-int get_cpuid(char *buf, size_t sz)
+int get_cpuid(char *buf, size_t sz, struct perf_cpu cpu __maybe_unused)
 {
 	struct perf_cpu_map *cpus = perf_cpu_map__new_online_cpus();
 	int ret;
diff --git a/tools/perf/arch/loongarch/util/header.c b/tools/perf/arch/loongarch/util/header.c
index d962dff55512..f1f0b116962d 100644
--- a/tools/perf/arch/loongarch/util/header.c
+++ b/tools/perf/arch/loongarch/util/header.c
@@ -70,7 +70,7 @@ static char *_get_cpuid(void)
 	return cpuid;
 }
 
-int get_cpuid(char *buffer, size_t sz)
+int get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 {
 	int ret = 0;
 	char *cpuid = _get_cpuid();
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index 251cdbf58a4d..6d1a63a2922f 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -24,7 +24,7 @@ static bool is_compat_mode(void)
 }
 
 int
-get_cpuid(char *buffer, size_t sz)
+get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 {
 	unsigned long pvr;
 	int nb;
diff --git a/tools/perf/arch/riscv/util/header.c b/tools/perf/arch/riscv/util/header.c
index 1b29030021ee..ebac294c877f 100644
--- a/tools/perf/arch/riscv/util/header.c
+++ b/tools/perf/arch/riscv/util/header.c
@@ -81,7 +81,7 @@ static char *_get_cpuid(void)
 	return cpuid;
 }
 
-int get_cpuid(char *buffer, size_t sz)
+int get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 {
 	char *cpuid = _get_cpuid();
 	int ret = 0;
diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c
index 7933f6871c81..2add1a561242 100644
--- a/tools/perf/arch/s390/util/header.c
+++ b/tools/perf/arch/s390/util/header.c
@@ -27,7 +27,7 @@
 #define SYSINFO		"/proc/sysinfo"
 #define SRVLVL		"/proc/service_levels"
 
-int get_cpuid(char *buffer, size_t sz)
+int get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 {
 	char *cp, *line = NULL, *line2;
 	char type[8], model[33], version[8], manufacturer[32], authorization[8];
diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c
index 354780ff1605..ecbf61a7eb3a 100644
--- a/tools/perf/arch/x86/util/auxtrace.c
+++ b/tools/perf/arch/x86/util/auxtrace.c
@@ -55,11 +55,12 @@ struct auxtrace_record *auxtrace_record__init(struct evlist *evlist,
 					      int *err)
 {
 	char buffer[64];
+	struct perf_cpu cpu = perf_cpu_map__min(evlist->core.all_cpus);
 	int ret;
 
 	*err = 0;
 
-	ret = get_cpuid(buffer, sizeof(buffer));
+	ret = get_cpuid(buffer, sizeof(buffer), cpu);
 	if (ret) {
 		*err = ret;
 		return NULL;
diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c
index a51444a77a5f..690f86cbbb1c 100644
--- a/tools/perf/arch/x86/util/header.c
+++ b/tools/perf/arch/x86/util/header.c
@@ -58,7 +58,7 @@ __get_cpuid(char *buffer, size_t sz, const char *fmt)
 }
 
 int
-get_cpuid(char *buffer, size_t sz)
+get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 {
 	return __get_cpuid(buffer, sz, "%s,%u,%u,%u$");
 }
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 099ce3ebf67c..274568d712d1 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1226,7 +1226,9 @@ static int cpu_isa_config(struct perf_kvm_stat *kvm)
 	int err;
 
 	if (kvm->live) {
-		err = get_cpuid(buf, sizeof(buf));
+		struct perf_cpu cpu = {-1};
+
+		err = get_cpuid(buf, sizeof(buf), cpu);
 		if (err != 0) {
 			pr_err("Failed to look up CPU type: %s\n",
 			       str_error_r(err, buf, sizeof(buf)));
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index ccb464026642..93cabdd7ff43 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -373,7 +373,8 @@ int perf_env__read_pmu_mappings(struct perf_env *env)
 int perf_env__read_cpuid(struct perf_env *env)
 {
 	char cpuid[128];
-	int err = get_cpuid(cpuid, sizeof(cpuid));
+	struct perf_cpu cpu = {-1};
+	int err = get_cpuid(cpuid, sizeof(cpuid), cpu);
 
 	if (err)
 		return err;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 55c28e4377ec..60b42ddc3dac 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -856,18 +856,19 @@ int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
  * default get_cpuid(): nothing gets recorded
  * actual implementation must be in arch/$(SRCARCH)/util/header.c
  */
-int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused)
+int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused,
+		     struct perf_cpu cpu __maybe_unused)
 {
 	return ENOSYS; /* Not implemented */
 }
 
-static int write_cpuid(struct feat_fd *ff,
-		       struct evlist *evlist __maybe_unused)
+static int write_cpuid(struct feat_fd *ff, struct evlist *evlist)
 {
+	struct perf_cpu cpu = perf_cpu_map__min(evlist->core.all_cpus);
 	char buffer[64];
 	int ret;
 
-	ret = get_cpuid(buffer, sizeof(buffer));
+	ret = get_cpuid(buffer, sizeof(buffer), cpu);
 	if (ret)
 		return -1;
 
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index e91e89d22537..b77f89de12dd 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -201,7 +201,7 @@ int build_caches_for_cpu(u32 cpu, struct cpu_cache_level caches[], u32 *cntp);
 /*
  * arch specific callback
  */
-int get_cpuid(char *buffer, size_t sz);
+int get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu);
 
 char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused);
 int strcmp_cpuid_str(const char *s1, const char *s2);
-- 
2.47.0.199.ga7371fff76-goog

[PATCH v1 3/7] perf arm64 header: Use cpu argument in get_cpuid

[Ian Rogers]

Use the cpu to read the MIDR file requested. If the "any" value (-1)
is passed that keep the behavior of returning the first MIDR file that
can be read.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/arch/arm64/util/header.c | 63 ++++++++++++++---------------
 tools/perf/util/header.h            |  1 +
 2 files changed, 31 insertions(+), 33 deletions(-)

diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c
index 760c21784713..f0907daad3ae 100644
--- a/tools/perf/arch/arm64/util/header.c
+++ b/tools/perf/arch/arm64/util/header.c
@@ -14,55 +14,52 @@
 #define MIDR_REVISION_MASK      GENMASK(3, 0)
 #define MIDR_VARIANT_MASK	GENMASK(23, 20)
 
-static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus)
+static int _get_cpuid(char *buf, size_t sz, struct perf_cpu cpu)
 {
+	char path[PATH_MAX];
+	FILE *file;
 	const char *sysfs = sysfs__mountpoint();
-	struct perf_cpu cpu;
-	int idx, ret = EINVAL;
 
+	assert(cpu.cpu != -1);
 	if (!sysfs || sz < MIDR_SIZE)
 		return EINVAL;
 
-	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
-		char path[PATH_MAX];
-		FILE *file;
-
-		scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d" MIDR,
-			  sysfs, cpu.cpu);
-
-		file = fopen(path, "r");
-		if (!file) {
-			pr_debug("fopen failed for file %s\n", path);
-			continue;
-		}
-
-		if (!fgets(buf, MIDR_SIZE, file)) {
-			fclose(file);
-			continue;
-		}
-		fclose(file);
+	scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d" MIDR, sysfs, cpu.cpu);
 
-		/* got midr break loop */
-		ret = 0;
-		break;
+	file = fopen(path, "r");
+	if (!file) {
+		pr_debug("fopen failed for file %s\n", path);
+		return EINVAL;
 	}
 
-	return ret;
+	if (!fgets(buf, MIDR_SIZE, file)) {
+		pr_debug("Failed to read file %s\n", path);
+		fclose(file);
+		return EINVAL;
+	}
+	fclose(file);
+	return 0;
 }
 
-int get_cpuid(char *buf, size_t sz, struct perf_cpu cpu __maybe_unused)
+int get_cpuid(char *buf, size_t sz, struct perf_cpu cpu)
 {
-	struct perf_cpu_map *cpus = perf_cpu_map__new_online_cpus();
-	int ret;
+	struct perf_cpu_map *cpus;
+	int idx;
+
+	if (cpu.cpu != -1)
+		return _get_cpuid(buf, sz, cpu);
 
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus)
 		return EINVAL;
 
-	ret = _get_cpuid(buf, sz, cpus);
-
-	perf_cpu_map__put(cpus);
+	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+		int ret = _get_cpuid(buf, sz, cpu);
 
-	return ret;
+		if (ret == 0)
+			return 0;
+	}
+	return EINVAL;
 }
 
 char *get_cpuid_str(struct perf_pmu *pmu)
@@ -78,7 +75,7 @@ char *get_cpuid_str(struct perf_pmu *pmu)
 		return NULL;
 
 	/* read midr from list of cpus mapped to this pmu */
-	res = _get_cpuid(buf, MIDR_SIZE, pmu->cpus);
+	res = get_cpuid(buf, MIDR_SIZE, perf_cpu_map__min(pmu->cpus));
 	if (res) {
 		pr_err("failed to get cpuid string for PMU %s\n", pmu->name);
 		free(buf);
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index b77f89de12dd..3bb768455a60 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -11,6 +11,7 @@
 #include <linux/types.h>
 #include "env.h"
 #include "pmu.h"
+#include <perf/cpumap.h>
 
 enum {
 	HEADER_RESERVED		= 0,	/* always cleared */
-- 
2.47.0.199.ga7371fff76-goog

[PATCH v1 4/7] perf header: Avoid transitive PMU includes

[Ian Rogers]

Currently satisfied via header.h. Note, pmu.h includes parse-events.h.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/tests/expr.c       | 2 ++
 tools/perf/util/env.c         | 1 +
 tools/perf/util/probe-event.c | 1 +
 3 files changed, 4 insertions(+)

diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index e3aa9d4fcf3a..d60f1ac1d720 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -4,6 +4,8 @@
 #include "util/expr.h"
 #include "util/hashmap.h"
 #include "util/header.h"
+#include "util/pmu.h"
+#include "util/pmus.h"
 #include "util/smt.h"
 #include "tests.h"
 #include <math.h>
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 93cabdd7ff43..e2843ca2edd9 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -12,6 +12,7 @@
 #include <sys/utsname.h>
 #include <stdlib.h>
 #include <string.h>
+#include "pmu.h"
 #include "pmus.h"
 #include "strbuf.h"
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index a580aa2cd512..d399c7e03341 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -40,6 +40,7 @@
 #include "session.h"
 #include "string2.h"
 #include "strbuf.h"
+#include "parse-events.h"
 
 #include <subcmd/pager.h>
 #include <linux/ctype.h>
-- 
2.47.0.199.ga7371fff76-goog

[PATCH v1 5/7] perf header: Pass a perf_cpu rather than a PMU to get_cpuid_str

[Ian Rogers]

On ARM the cpuid is dependent on the core type of the CPU in
question. The PMU was passed for the sake of the CPU map but this
means in places a temporary PMU is created just to pass a CPU
value. Just pass the CPU and fix up the callers.

As there are no longer PMU users in header.h, shuffle forward
declarations earlier to work around build failures.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/arch/arm64/util/arm-spe.c     | 14 ++------------
 tools/perf/arch/arm64/util/header.c      | 12 ++++--------
 tools/perf/arch/loongarch/util/header.c  |  2 +-
 tools/perf/arch/powerpc/util/header.c    |  2 +-
 tools/perf/arch/riscv/util/header.c      |  2 +-
 tools/perf/arch/s390/util/header.c       |  4 ++--
 tools/perf/arch/x86/util/header.c        |  3 +--
 tools/perf/pmu-events/empty-pmu-events.c |  5 ++++-
 tools/perf/pmu-events/jevents.py         |  5 ++++-
 tools/perf/tests/expr.c                  |  7 +++----
 tools/perf/util/expr.c                   |  6 +++---
 tools/perf/util/header.c                 | 22 +++++++++++++++++++++-
 tools/perf/util/header.h                 | 19 ++++++++++---------
 tools/perf/util/pmu.c                    | 20 --------------------
 tools/perf/util/pmu.h                    |  1 -
 15 files changed, 57 insertions(+), 67 deletions(-)

diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 7ccdea3cd461..22b19dcc6beb 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -23,6 +23,7 @@
 #include "../../../util/debug.h"
 #include "../../../util/auxtrace.h"
 #include "../../../util/record.h"
+#include "../../../util/header.h"
 #include "../../../util/arm-spe.h"
 #include <tools/libc_compat.h> // reallocarray
 
@@ -85,22 +86,11 @@ static int arm_spe_save_cpu_header(struct auxtrace_record *itr,
 	struct arm_spe_recording *sper =
 			container_of(itr, struct arm_spe_recording, itr);
 	struct perf_pmu *pmu = NULL;
-	struct perf_pmu tmp_pmu;
-	char cpu_id_str[16];
 	char *cpuid = NULL;
 	u64 val;
 
-	snprintf(cpu_id_str, sizeof(cpu_id_str), "%d", cpu.cpu);
-	tmp_pmu.cpus = perf_cpu_map__new(cpu_id_str);
-	if (!tmp_pmu.cpus)
-		return -ENOMEM;
-
 	/* Read CPU MIDR */
-	cpuid = perf_pmu__getcpuid(&tmp_pmu);
-
-	/* The CPU map will not be used anymore, release it */
-	perf_cpu_map__put(tmp_pmu.cpus);
-
+	cpuid = get_cpuid_allow_env_override(cpu);
 	if (!cpuid)
 		return -ENOMEM;
 	val = strtol(cpuid, NULL, 16);
diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c
index f0907daad3ae..f445a2dd6293 100644
--- a/tools/perf/arch/arm64/util/header.c
+++ b/tools/perf/arch/arm64/util/header.c
@@ -62,22 +62,18 @@ int get_cpuid(char *buf, size_t sz, struct perf_cpu cpu)
 	return EINVAL;
 }
 
-char *get_cpuid_str(struct perf_pmu *pmu)
+char *get_cpuid_str(struct perf_cpu cpu)
 {
-	char *buf = NULL;
+	char *buf = malloc(MIDR_SIZE);
 	int res;
 
-	if (!pmu || !pmu->cpus)
-		return NULL;
-
-	buf = malloc(MIDR_SIZE);
 	if (!buf)
 		return NULL;
 
 	/* read midr from list of cpus mapped to this pmu */
-	res = get_cpuid(buf, MIDR_SIZE, perf_cpu_map__min(pmu->cpus));
+	res = get_cpuid(buf, MIDR_SIZE, cpu);
 	if (res) {
-		pr_err("failed to get cpuid string for PMU %s\n", pmu->name);
+		pr_err("failed to get cpuid string for CPU %d\n", cpu.cpu);
 		free(buf);
 		buf = NULL;
 	}
diff --git a/tools/perf/arch/loongarch/util/header.c b/tools/perf/arch/loongarch/util/header.c
index f1f0b116962d..0c6d823334a2 100644
--- a/tools/perf/arch/loongarch/util/header.c
+++ b/tools/perf/arch/loongarch/util/header.c
@@ -90,7 +90,7 @@ int get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 	return ret;
 }
 
-char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
+char *get_cpuid_str(struct perf_cpu cpu __maybe_unused)
 {
 	return _get_cpuid();
 }
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index 6d1a63a2922f..c7df534dbf8f 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -42,7 +42,7 @@ get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 }
 
 char *
-get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
+get_cpuid_str(struct perf_cpu cpu __maybe_unused)
 {
 	char *bufp;
 	unsigned long pvr;
diff --git a/tools/perf/arch/riscv/util/header.c b/tools/perf/arch/riscv/util/header.c
index ebac294c877f..4b839203d4a5 100644
--- a/tools/perf/arch/riscv/util/header.c
+++ b/tools/perf/arch/riscv/util/header.c
@@ -98,7 +98,7 @@ int get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 }
 
 char *
-get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
+get_cpuid_str(struct perf_cpu cpu __maybe_unused)
 {
 	return _get_cpuid();
 }
diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c
index 2add1a561242..db54677a17d2 100644
--- a/tools/perf/arch/s390/util/header.c
+++ b/tools/perf/arch/s390/util/header.c
@@ -137,11 +137,11 @@ int get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 	return (nbytes >= sz) ? ENOBUFS : 0;
 }
 
-char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
+char *get_cpuid_str(struct perf_cpu cpu)
 {
 	char *buf = malloc(128);
 
-	if (buf && get_cpuid(buf, 128))
+	if (buf && get_cpuid(buf, 128, cpu))
 		zfree(&buf);
 	return buf;
 }
diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c
index 690f86cbbb1c..412977f8aa83 100644
--- a/tools/perf/arch/x86/util/header.c
+++ b/tools/perf/arch/x86/util/header.c
@@ -63,8 +63,7 @@ get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 	return __get_cpuid(buffer, sz, "%s,%u,%u,%u$");
 }
 
-char *
-get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
+char *get_cpuid_str(struct perf_cpu cpu __maybe_unused)
 {
 	char *buf = malloc(128);
 
diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c
index 2b7516946ded..1f7f39a89ffd 100644
--- a/tools/perf/pmu-events/empty-pmu-events.c
+++ b/tools/perf/pmu-events/empty-pmu-events.c
@@ -515,13 +515,16 @@ static const struct pmu_events_map *map_for_pmu(struct perf_pmu *pmu)
         } last_map_search;
         static bool has_last_result, has_last_map_search;
         const struct pmu_events_map *map = NULL;
+        struct perf_cpu cpu = {-1};
         char *cpuid = NULL;
         size_t i;
 
         if (has_last_result && last_result.pmu == pmu)
                 return last_result.map;
 
-        cpuid = perf_pmu__getcpuid(pmu);
+        if (pmu)
+                cpu = perf_cpu_map__min(pmu->cpus);
+        cpuid = get_cpuid_allow_env_override(cpu);
 
         /*
          * On some platforms which uses cpus map, cpuid can be NULL for
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 6e71b09dbc2a..17cd1b1c6b66 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -1031,13 +1031,16 @@ static const struct pmu_events_map *map_for_pmu(struct perf_pmu *pmu)
         } last_map_search;
         static bool has_last_result, has_last_map_search;
         const struct pmu_events_map *map = NULL;
+        struct perf_cpu cpu = {-1};
         char *cpuid = NULL;
         size_t i;
 
         if (has_last_result && last_result.pmu == pmu)
                 return last_result.map;
 
-        cpuid = perf_pmu__getcpuid(pmu);
+        if (pmu)
+                cpu = perf_cpu_map__min(pmu->cpus);
+        cpuid = get_cpuid_allow_env_override(cpu);
 
         /*
          * On some platforms which uses cpus map, cpuid can be NULL for
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index d60f1ac1d720..41ff1affdfcd 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -4,10 +4,9 @@
 #include "util/expr.h"
 #include "util/hashmap.h"
 #include "util/header.h"
-#include "util/pmu.h"
-#include "util/pmus.h"
 #include "util/smt.h"
 #include "tests.h"
+#include <perf/cpumap.h>
 #include <math.h>
 #include <stdlib.h>
 #include <string.h>
@@ -78,8 +77,8 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u
 	struct expr_parse_ctx *ctx;
 	bool is_intel = false;
 	char strcmp_cpuid_buf[256];
-	struct perf_pmu *pmu = perf_pmus__find_core_pmu();
-	char *cpuid = perf_pmu__getcpuid(pmu);
+	struct perf_cpu cpu = {-1};
+	char *cpuid = get_cpuid_allow_env_override(cpu);
 	char *escaped_cpuid1, *escaped_cpuid2;
 
 	TEST_ASSERT_VAL("get_cpuid", cpuid);
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index 5e3732bc2fa5..f289044a1f7c 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -8,7 +8,6 @@
 #include "debug.h"
 #include "evlist.h"
 #include "expr.h"
-#include "pmu.h"
 #include "smt.h"
 #include "tool_pmu.h"
 #include <util/expr-bison.h>
@@ -16,6 +15,7 @@
 #include "util/hashmap.h"
 #include "util/header.h"
 #include "util/pmu.h"
+#include <perf/cpumap.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
@@ -456,8 +456,8 @@ double expr__strcmp_cpuid_str(const struct expr_parse_ctx *ctx __maybe_unused,
 		       bool compute_ids __maybe_unused, const char *test_id)
 {
 	double ret;
-	struct perf_pmu *pmu = perf_pmus__find_core_pmu();
-	char *cpuid = perf_pmu__getcpuid(pmu);
+	struct perf_cpu cpu = {-1};
+	char *cpuid = get_cpuid_allow_env_override(cpu);
 
 	if (!cpuid)
 		return NAN;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 60b42ddc3dac..06ca5762f61f 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -819,11 +819,31 @@ static int write_group_desc(struct feat_fd *ff,
  * Each architecture should provide a more precise id string that
  * can be use to match the architecture's "mapfile".
  */
-char * __weak get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
+char * __weak get_cpuid_str(struct perf_cpu cpu __maybe_unused)
 {
 	return NULL;
 }
 
+char *get_cpuid_allow_env_override(struct perf_cpu cpu)
+{
+	char *cpuid;
+	static bool printed;
+
+	cpuid = getenv("PERF_CPUID");
+	if (cpuid)
+		cpuid = strdup(cpuid);
+	if (!cpuid)
+		cpuid = get_cpuid_str(cpu);
+	if (!cpuid)
+		return NULL;
+
+	if (!printed) {
+		pr_debug("Using CPUID %s\n", cpuid);
+		printed = true;
+	}
+	return cpuid;
+}
+
 /* Return zero when the cpuid from the mapfile.csv matches the
  * cpuid string generated on this platform.
  * Otherwise return non-zero.
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 3bb768455a60..5201af6305f4 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -10,9 +10,14 @@
 #include <linux/bitmap.h>
 #include <linux/types.h>
 #include "env.h"
-#include "pmu.h"
 #include <perf/cpumap.h>
 
+struct evlist;
+union perf_event;
+struct perf_header;
+struct perf_session;
+struct perf_tool;
+
 enum {
 	HEADER_RESERVED		= 0,	/* always cleared */
 	HEADER_FIRST_FEATURE	= 1,
@@ -92,8 +97,6 @@ struct perf_pipe_file_header {
 	u64				size;
 };
 
-struct perf_header;
-
 int perf_file_header__read(struct perf_file_header *header,
 			   struct perf_header *ph, int fd);
 
@@ -125,11 +128,6 @@ struct perf_header_feature_ops {
 	bool	   synthesize;
 };
 
-struct evlist;
-struct perf_session;
-struct perf_tool;
-union perf_event;
-
 extern const char perf_version_string[];
 
 int perf_session__read_header(struct perf_session *session);
@@ -204,6 +202,9 @@ int build_caches_for_cpu(u32 cpu, struct cpu_cache_level caches[], u32 *cntp);
  */
 int get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu);
 
-char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused);
+char *get_cpuid_str(struct perf_cpu cpu);
+
+char *get_cpuid_allow_env_override(struct perf_cpu cpu);
+
 int strcmp_cpuid_str(const char *s1, const char *s2);
 #endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 0789758598c0..514cb865f57b 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -818,26 +818,6 @@ static int is_sysfs_pmu_core(const char *name)
 	return file_available(path);
 }
 
-char *perf_pmu__getcpuid(struct perf_pmu *pmu)
-{
-	char *cpuid;
-	static bool printed;
-
-	cpuid = getenv("PERF_CPUID");
-	if (cpuid)
-		cpuid = strdup(cpuid);
-	if (!cpuid)
-		cpuid = get_cpuid_str(pmu);
-	if (!cpuid)
-		return NULL;
-
-	if (!printed) {
-		pr_debug("Using CPUID %s\n", cpuid);
-		printed = true;
-	}
-	return cpuid;
-}
-
 __weak const struct pmu_metrics_table *pmu_metrics_table__find(void)
 {
 	return perf_pmu__find_metrics_table(NULL);
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index b86b3c3685a2..fba3fc608b64 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -260,7 +260,6 @@ void perf_pmu__arch_init(struct perf_pmu *pmu);
 void pmu_add_cpu_aliases_table(struct perf_pmu *pmu,
 			       const struct pmu_events_table *table);
 
-char *perf_pmu__getcpuid(struct perf_pmu *pmu);
 const struct pmu_metrics_table *pmu_metrics_table__find(void);
 bool pmu_uncore_identifier_match(const char *compat, const char *id);
 
-- 
2.47.0.199.ga7371fff76-goog

[PATCH v1 6/7] perf jevents: Add map_for_cpu

[Ian Rogers]

The PMU is no longer part of the map finding process and for metrics
doesn't make sense as they lack a PMU.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/pmu-events/empty-pmu-events.c | 20 +++++++++++++-------
 tools/perf/pmu-events/jevents.py         | 20 +++++++++++++-------
 2 files changed, 26 insertions(+), 14 deletions(-)

diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c
index 1f7f39a89ffd..2151e8a43f16 100644
--- a/tools/perf/pmu-events/empty-pmu-events.c
+++ b/tools/perf/pmu-events/empty-pmu-events.c
@@ -503,11 +503,11 @@ int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table,
         return 0;
 }
 
-static const struct pmu_events_map *map_for_pmu(struct perf_pmu *pmu)
+static const struct pmu_events_map *map_for_cpu(struct perf_cpu cpu)
 {
         static struct {
                 const struct pmu_events_map *map;
-                struct perf_pmu *pmu;
+                struct perf_cpu cpu;
         } last_result;
         static struct {
                 const struct pmu_events_map *map;
@@ -515,15 +515,12 @@ static const struct pmu_events_map *map_for_pmu(struct perf_pmu *pmu)
         } last_map_search;
         static bool has_last_result, has_last_map_search;
         const struct pmu_events_map *map = NULL;
-        struct perf_cpu cpu = {-1};
         char *cpuid = NULL;
         size_t i;
 
-        if (has_last_result && last_result.pmu == pmu)
+        if (has_last_result && last_result.cpu.cpu == cpu.cpu)
                 return last_result.map;
 
-        if (pmu)
-                cpu = perf_cpu_map__min(pmu->cpus);
         cpuid = get_cpuid_allow_env_override(cpu);
 
         /*
@@ -555,12 +552,21 @@ static const struct pmu_events_map *map_for_pmu(struct perf_pmu *pmu)
                has_last_map_search = true;
         }
 out_update_last_result:
-        last_result.pmu = pmu;
+        last_result.cpu = cpu;
         last_result.map = map;
         has_last_result = true;
         return map;
 }
 
+static const struct pmu_events_map *map_for_pmu(struct perf_pmu *pmu)
+{
+        struct perf_cpu cpu = {-1};
+
+        if (pmu)
+                cpu = perf_cpu_map__min(pmu->cpus);
+        return map_for_cpu(cpu);
+}
+
 const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu)
 {
         const struct pmu_events_map *map = map_for_pmu(pmu);
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 17cd1b1c6b66..6d6780ca0889 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -1019,11 +1019,11 @@ int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table,
         return 0;
 }
 
-static const struct pmu_events_map *map_for_pmu(struct perf_pmu *pmu)
+static const struct pmu_events_map *map_for_cpu(struct perf_cpu cpu)
 {
         static struct {
                 const struct pmu_events_map *map;
-                struct perf_pmu *pmu;
+                struct perf_cpu cpu;
         } last_result;
         static struct {
                 const struct pmu_events_map *map;
@@ -1031,15 +1031,12 @@ static const struct pmu_events_map *map_for_pmu(struct perf_pmu *pmu)
         } last_map_search;
         static bool has_last_result, has_last_map_search;
         const struct pmu_events_map *map = NULL;
-        struct perf_cpu cpu = {-1};
         char *cpuid = NULL;
         size_t i;
 
-        if (has_last_result && last_result.pmu == pmu)
+        if (has_last_result && last_result.cpu.cpu == cpu.cpu)
                 return last_result.map;
 
-        if (pmu)
-                cpu = perf_cpu_map__min(pmu->cpus);
         cpuid = get_cpuid_allow_env_override(cpu);
 
         /*
@@ -1071,12 +1068,21 @@ static const struct pmu_events_map *map_for_pmu(struct perf_pmu *pmu)
                has_last_map_search = true;
         }
 out_update_last_result:
-        last_result.pmu = pmu;
+        last_result.cpu = cpu;
         last_result.map = map;
         has_last_result = true;
         return map;
 }
 
+static const struct pmu_events_map *map_for_pmu(struct perf_pmu *pmu)
+{
+        struct perf_cpu cpu = {-1};
+
+        if (pmu)
+                cpu = perf_cpu_map__min(pmu->cpus);
+        return map_for_cpu(cpu);
+}
+
 const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu)
 {
         const struct pmu_events_map *map = map_for_pmu(pmu);
-- 
2.47.0.199.ga7371fff76-goog

[PATCH v1 7/7] perf pmu: Move pmu_metrics_table__find and remove ARM override

[Ian Rogers]

Move pmu_metrics_table__find to the jevents.py generated pmu-events.c
and remove indirection override for ARM. The movement removes
perf_pmu__find_metrics_table that exists to enable the ARM
override. The ARM override isn't necessary as just the CPUID, not PMU,
is used in the metric table lookup. On non-ARM the CPU argument is
just ignored for the CPUID, for ARM -1 is passed so that the CPUID for
the first logical CPU is read.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/arch/arm64/util/pmu.c         | 20 --------------------
 tools/perf/pmu-events/empty-pmu-events.c | 20 ++++----------------
 tools/perf/pmu-events/jevents.py         | 20 ++++----------------
 tools/perf/pmu-events/pmu-events.h       |  2 +-
 tools/perf/util/pmu.c                    |  5 -----
 tools/perf/util/pmu.h                    |  1 -
 6 files changed, 9 insertions(+), 59 deletions(-)

diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c
index a0964b191fcb..895fb0d0610c 100644
--- a/tools/perf/arch/arm64/util/pmu.c
+++ b/tools/perf/arch/arm64/util/pmu.c
@@ -1,29 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <internal/cpumap.h>
-#include "../../../util/cpumap.h"
-#include "../../../util/header.h"
 #include "../../../util/pmu.h"
 #include "../../../util/pmus.h"
 #include "../../../util/tool_pmu.h"
 #include <api/fs/fs.h>
-#include <math.h>
-
-const struct pmu_metrics_table *pmu_metrics_table__find(void)
-{
-	struct perf_pmu *pmu;
-
-	/* Metrics aren't currently supported on heterogeneous Arm systems */
-	if (perf_pmus__num_core_pmus() > 1)
-		return NULL;
-
-	/* Doesn't matter which one here because they'll all be the same */
-	pmu = perf_pmus__find_core_pmu();
-	if (pmu)
-		return perf_pmu__find_metrics_table(pmu);
-
-	return NULL;
-}
 
 u64 tool_pmu__cpu_slots_per_cycle(void)
 {
diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c
index 2151e8a43f16..1c7a2cfa321f 100644
--- a/tools/perf/pmu-events/empty-pmu-events.c
+++ b/tools/perf/pmu-events/empty-pmu-events.c
@@ -587,24 +587,12 @@ const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu)
         return NULL;
 }
 
-const struct pmu_metrics_table *perf_pmu__find_metrics_table(struct perf_pmu *pmu)
+const struct pmu_metrics_table *pmu_metrics_table__find(void)
 {
-        const struct pmu_events_map *map = map_for_pmu(pmu);
-
-        if (!map)
-                return NULL;
-
-        if (!pmu)
-                return &map->metric_table;
-
-        for (size_t i = 0; i < map->metric_table.num_pmus; i++) {
-                const struct pmu_table_entry *table_pmu = &map->metric_table.pmus[i];
-                const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset];
+        struct perf_cpu cpu = {-1};
+        const struct pmu_events_map *map = map_for_cpu(cpu);
 
-                if (pmu__name_match(pmu, pmu_name))
-                           return &map->metric_table;
-        }
-        return NULL;
+        return map ? &map->metric_table : NULL;
 }
 
 const struct pmu_events_table *find_core_events_table(const char *arch, const char *cpuid)
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 6d6780ca0889..d781a377757a 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -1103,24 +1103,12 @@ const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu)
         return NULL;
 }
 
-const struct pmu_metrics_table *perf_pmu__find_metrics_table(struct perf_pmu *pmu)
+const struct pmu_metrics_table *pmu_metrics_table__find(void)
 {
-        const struct pmu_events_map *map = map_for_pmu(pmu);
-
-        if (!map)
-                return NULL;
-
-        if (!pmu)
-                return &map->metric_table;
-
-        for (size_t i = 0; i < map->metric_table.num_pmus; i++) {
-                const struct pmu_table_entry *table_pmu = &map->metric_table.pmus[i];
-                const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset];
+        struct perf_cpu cpu = {-1};
+        const struct pmu_events_map *map = map_for_cpu(cpu);
 
-                if (pmu__name_match(pmu, pmu_name))
-                           return &map->metric_table;
-        }
-        return NULL;
+        return map ? &map->metric_table : NULL;
 }
 
 const struct pmu_events_table *find_core_events_table(const char *arch, const char *cpuid)
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index 5435ad92180c..675562e6f770 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -103,7 +103,7 @@ int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, pm
 				     void *data);
 
 const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu);
-const struct pmu_metrics_table *perf_pmu__find_metrics_table(struct perf_pmu *pmu);
+const struct pmu_metrics_table *pmu_metrics_table__find(void);
 const struct pmu_events_table *find_core_events_table(const char *arch, const char *cpuid);
 const struct pmu_metrics_table *find_core_metrics_table(const char *arch, const char *cpuid);
 int pmu_for_each_core_event(pmu_event_iter_fn fn, void *data);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 514cb865f57b..45838651b361 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -818,11 +818,6 @@ static int is_sysfs_pmu_core(const char *name)
 	return file_available(path);
 }
 
-__weak const struct pmu_metrics_table *pmu_metrics_table__find(void)
-{
-	return perf_pmu__find_metrics_table(NULL);
-}
-
 /**
  * Return the length of the PMU name not including the suffix for uncore PMUs.
  *
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index fba3fc608b64..7b3e71194e49 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -260,7 +260,6 @@ void perf_pmu__arch_init(struct perf_pmu *pmu);
 void pmu_add_cpu_aliases_table(struct perf_pmu *pmu,
 			       const struct pmu_events_table *table);
 
-const struct pmu_metrics_table *pmu_metrics_table__find(void);
 bool pmu_uncore_identifier_match(const char *compat, const char *id);
 
 int perf_pmu__convert_scale(const char *scale, char **end, double *sval);
-- 
2.47.0.199.ga7371fff76-goog

Re: [PATCH v1 0/7] Refactor cpuid and metric table lookup code

[Xu Yang]

Hi Ian Rogers,

On Wed, Nov 06, 2024 at 11:15:53PM -0800, Ian Rogers wrote:
> Xu Yang <xu.yang_2@nxp.com> reported issues with the system metric
> lookup:
> https://lore.kernel.org/linux-perf-users/20241106085441.3945502-1-xu.yang_2@nxp.com/
> These patches remove a lot of the logic relating CPUIDs to PMUs so
> that the PMU isn't part of the question when finding a metric table.
> For time reasons, it doesn't go as far as allowing system metrics
> without a metric table as a metric table is needed for metrics to
> refer to other metrics, and the refactoring of that resolution is a
> hassle.
> 
> Ian Rogers (7):
>   perf header: Move is_cpu_online to numa bench
>   perf header: Refactor get_cpuid to take a CPU for ARM
>   perf arm64 header: Use cpu argument in get_cpuid
>   perf header: Avoid transitive PMU includes
>   perf header: Pass a perf_cpu rather than a PMU to get_cpuid_str
>   perf jevents: Add map_for_cpu
>   perf pmu: Move pmu_metrics_table__find and remove ARM override
> 
>  tools/perf/arch/arm64/util/arm-spe.c     | 14 +---
>  tools/perf/arch/arm64/util/header.c      | 73 ++++++++++-----------
>  tools/perf/arch/arm64/util/pmu.c         | 20 ------
>  tools/perf/arch/loongarch/util/header.c  |  4 +-
>  tools/perf/arch/powerpc/util/header.c    |  4 +-
>  tools/perf/arch/riscv/util/header.c      |  4 +-
>  tools/perf/arch/s390/util/header.c       |  6 +-
>  tools/perf/arch/x86/util/auxtrace.c      |  3 +-
>  tools/perf/arch/x86/util/header.c        |  5 +-
>  tools/perf/bench/numa.c                  | 51 +++++++++++++++

Meet error when build perf tool:

  CC      util/levenshtein.o
  CC      tests/mem.o
  CC      util/mmap.o
bench/numa.c: In function ‘is_cpu_online’:
bench/numa.c:550:21: error: storage size of ‘statbuf’ isn’t known
  550 |         struct stat statbuf;
      |                     ^~~~~~~
bench/numa.c:554:13: error: implicit declaration of function ‘stat’; did you mean ‘strcat’? [-Werror=implicit-function-declaration]
  554 |         if (stat(buf, &statbuf) != 0)
      |             ^~~~
      |             strcat
bench/numa.c:578:13: error: implicit declaration of function ‘sysfs__read_str’ [-Werror=implicit-function-declaration]
  578 |         if (sysfs__read_str(buf, &str, &strlen) < 0)
      |             ^~~~~~~~~~~~~~~
bench/numa.c:550:21: error: unused variable ‘statbuf’ [-Werror=unused-variable]
  550 |         struct stat statbuf;
      |                     ^~~~~~~
  CC      tests/cpumap.o
  CC      tests/stat.o

After remove these errors, my issue is disappeared.

Thanks,
Xu Yang

>  tools/perf/builtin-kvm.c                 |  4 +-
>  tools/perf/pmu-events/empty-pmu-events.c | 39 ++++++-----
>  tools/perf/pmu-events/jevents.py         | 39 ++++++-----
>  tools/perf/pmu-events/pmu-events.h       |  2 +-
>  tools/perf/tests/expr.c                  |  5 +-
>  tools/perf/util/env.c                    |  4 +-
>  tools/perf/util/expr.c                   |  6 +-
>  tools/perf/util/header.c                 | 82 ++++++++----------------
>  tools/perf/util/header.h                 | 23 +++----
>  tools/perf/util/pmu.c                    | 25 --------
>  tools/perf/util/pmu.h                    |  2 -
>  tools/perf/util/probe-event.c            |  1 +
>  22 files changed, 187 insertions(+), 229 deletions(-)
> 
> -- 
> 2.47.0.199.ga7371fff76-goog
> 

Re: [PATCH v1 0/7] Refactor cpuid and metric table lookup code

[Ian Rogers]

On Thu, Nov 7, 2024 at 1:05 AM Xu Yang <xu.yang_2@nxp.com> wrote:
>
> Hi Ian Rogers,
>
> On Wed, Nov 06, 2024 at 11:15:53PM -0800, Ian Rogers wrote:
> > Xu Yang <xu.yang_2@nxp.com> reported issues with the system metric
> > lookup:
> > https://lore.kernel.org/linux-perf-users/20241106085441.3945502-1-xu.yang_2@nxp.com/
> > These patches remove a lot of the logic relating CPUIDs to PMUs so
> > that the PMU isn't part of the question when finding a metric table.
> > For time reasons, it doesn't go as far as allowing system metrics
> > without a metric table as a metric table is needed for metrics to
> > refer to other metrics, and the refactoring of that resolution is a
> > hassle.
> >
> > Ian Rogers (7):
> >   perf header: Move is_cpu_online to numa bench
> >   perf header: Refactor get_cpuid to take a CPU for ARM
> >   perf arm64 header: Use cpu argument in get_cpuid
> >   perf header: Avoid transitive PMU includes
> >   perf header: Pass a perf_cpu rather than a PMU to get_cpuid_str
> >   perf jevents: Add map_for_cpu
> >   perf pmu: Move pmu_metrics_table__find and remove ARM override
> >
> >  tools/perf/arch/arm64/util/arm-spe.c     | 14 +---
> >  tools/perf/arch/arm64/util/header.c      | 73 ++++++++++-----------
> >  tools/perf/arch/arm64/util/pmu.c         | 20 ------
> >  tools/perf/arch/loongarch/util/header.c  |  4 +-
> >  tools/perf/arch/powerpc/util/header.c    |  4 +-
> >  tools/perf/arch/riscv/util/header.c      |  4 +-
> >  tools/perf/arch/s390/util/header.c       |  6 +-
> >  tools/perf/arch/x86/util/auxtrace.c      |  3 +-
> >  tools/perf/arch/x86/util/header.c        |  5 +-
> >  tools/perf/bench/numa.c                  | 51 +++++++++++++++
>
> Meet error when build perf tool:
>
>   CC      util/levenshtein.o
>   CC      tests/mem.o
>   CC      util/mmap.o
> bench/numa.c: In function ‘is_cpu_online’:
> bench/numa.c:550:21: error: storage size of ‘statbuf’ isn’t known
>   550 |         struct stat statbuf;
>       |                     ^~~~~~~
> bench/numa.c:554:13: error: implicit declaration of function ‘stat’; did you mean ‘strcat’? [-Werror=implicit-function-declaration]
>   554 |         if (stat(buf, &statbuf) != 0)
>       |             ^~~~
>       |             strcat
> bench/numa.c:578:13: error: implicit declaration of function ‘sysfs__read_str’ [-Werror=implicit-function-declaration]
>   578 |         if (sysfs__read_str(buf, &str, &strlen) < 0)
>       |             ^~~~~~~~~~~~~~~
> bench/numa.c:550:21: error: unused variable ‘statbuf’ [-Werror=unused-variable]
>   550 |         struct stat statbuf;
>       |                     ^~~~~~~
>   CC      tests/cpumap.o
>   CC      tests/stat.o
>
> After remove these errors, my issue is disappeared.

Thanks, I'll fix this in v2. I'll also add your patch to the front for
the sake of backport fixing. If you could provide tags for my changes
it would be appreciated.

Thanks,
Ian