All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ian Rogers <irogers@google.com>
To: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	 Arnaldo Carvalho de Melo <acme@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>, Jiri Olsa <jolsa@kernel.org>,
	 Ian Rogers <irogers@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	 James Clark <james.clark@linaro.org>
Cc: linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH v3 14/30] perf header: Support CPUID matching across all architectures
Date: Fri, 20 Nov 2026 14:13:15 -0800	[thread overview]
Message-ID: <20261120221332.2245191-15-irogers@google.com> (raw)
In-Reply-To: <20261120221332.2245191-1-irogers@google.com>

strcmp_cpuid_str() had architecture specific overrides of a __weak
regular expression matching implementation in arch/x86/util/header.c
and arch/arm64/util/header.c, so a CPUID could only be compared using
the rules of the architecture perf was built for. In addition, the
HEADER_CPUID strings written by get_cpuid() on x86 ("vendor,family,
model,step" in decimal) and PowerPC ("pvr_ver,pvr_rev" in decimal)
differ from the get_cpuid_str() formats ("vendor-family-model-stepping"
in hex and "0x%.8lx") matched against the pmu-events mapfile.csv
tables. As a result, finding the core events or metrics table for the
CPUID of a perf_env, such as from a perf.data file recorded on a
different architecture, failed.

Move the architecture specific comparisons into util/header.c and
select them using the ELF machine of the CPUIDs: EM_NONE for the test
and common tables compares exactly, arm64 compares MIDR part, variant
and revision fields, x86 matches with an optional stepping and other
architectures match a regular expression. Convert x86 and PowerPC
HEADER_CPUID strings before matching.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/arch/arm64/util/header.c |  48 ---------
 tools/perf/arch/x86/util/header.c   |  64 -----------
 tools/perf/util/header.c            | 161 +++++++++++++++++++++++++++-
 3 files changed, 156 insertions(+), 117 deletions(-)

diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c
index ee28add836b5..181836613087 100644
--- a/tools/perf/arch/arm64/util/header.c
+++ b/tools/perf/arch/arm64/util/header.c
@@ -1,5 +1,3 @@
-#include <linux/bits.h>
-#include <linux/bitfield.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <perf/cpumap.h>
@@ -10,8 +8,6 @@
 
 #define MIDR "/regs/identification/midr_el1"
 #define MIDR_SIZE 19
-#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 cpu)
 {
@@ -79,47 +75,3 @@ char *get_cpuid_str(struct perf_cpu cpu)
 
 	return buf;
 }
-
-/*
- * Return 0 if idstr is a higher or equal to version of the same part as
- * mapcpuid. Therefore, if mapcpuid has 0 for revision and variant then any
- * version of idstr will match as long as it's the same CPU type.
- *
- * Return 1 if the CPU type is different or the version of idstr is lower.
- */
-int strcmp_cpuid_str(uint16_t e_machine __maybe_unused, const char *mapcpuid, const char *idstr)
-{
-	u64 map_id = strtoull(mapcpuid, NULL, 16);
-	char map_id_variant = FIELD_GET(MIDR_VARIANT_MASK, map_id);
-	char map_id_revision = FIELD_GET(MIDR_REVISION_MASK, map_id);
-	u64 id = strtoull(idstr, NULL, 16);
-	char id_variant = FIELD_GET(MIDR_VARIANT_MASK, id);
-	char id_revision = FIELD_GET(MIDR_REVISION_MASK, id);
-	u64 id_fields = ~(MIDR_VARIANT_MASK | MIDR_REVISION_MASK);
-
-	/* Compare without version first */
-	if ((map_id & id_fields) != (id & id_fields))
-		return 1;
-
-	/*
-	 * ID matches, now compare version.
-	 *
-	 * Arm revisions (like r0p0) are compared here like two digit semver
-	 * values eg. 1.3 < 2.0 < 2.1 < 2.2.
-	 *
-	 *  r = high value = 'Variant' field in MIDR
-	 *  p = low value  = 'Revision' field in MIDR
-	 *
-	 */
-	if (id_variant > map_id_variant)
-		return 0;
-
-	if (id_variant == map_id_variant && id_revision >= map_id_revision)
-		return 0;
-
-	/*
-	 * variant is less than mapfile variant or variants are the same but
-	 * the revision doesn't match. Return no match.
-	 */
-	return 1;
-}
diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c
index b65856f3b846..5203e5cd151c 100644
--- a/tools/perf/arch/x86/util/header.c
+++ b/tools/perf/arch/x86/util/header.c
@@ -5,7 +5,6 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <regex.h>
 
 #include "../../../util/debug.h"
 #include "../../../util/header.h"
@@ -73,66 +72,3 @@ char *get_cpuid_str(struct perf_cpu cpu __maybe_unused)
 	}
 	return buf;
 }
-
-/* Full CPUID format for x86 is vendor-family-model-stepping */
-static bool is_full_cpuid(const char *id)
-{
-	const char *tmp = id;
-	int count = 0;
-
-	while ((tmp = strchr(tmp, '-')) != NULL) {
-		count++;
-		tmp++;
-	}
-
-	if (count == 3)
-		return true;
-
-	return false;
-}
-
-int strcmp_cpuid_str(uint16_t e_machine __maybe_unused, const char *mapcpuid, const char *id)
-{
-	regex_t re;
-	regmatch_t pmatch[1];
-	int match;
-	bool full_mapcpuid = is_full_cpuid(mapcpuid);
-	bool full_cpuid = is_full_cpuid(id);
-
-	/*
-	 * Full CPUID format is required to identify a platform.
-	 * Error out if the cpuid string is incomplete.
-	 */
-	if (full_mapcpuid && !full_cpuid) {
-		pr_info("Invalid CPUID %s. Full CPUID is required, "
-			"vendor-family-model-stepping\n", id);
-		return 1;
-	}
-
-	if (regcomp(&re, mapcpuid, REG_EXTENDED) != 0) {
-		/* Warn unable to generate match particular string. */
-		pr_info("Invalid regular expression %s\n", mapcpuid);
-		return 1;
-	}
-
-	match = !regexec(&re, id, 1, pmatch, 0);
-	regfree(&re);
-	if (match) {
-		size_t match_len = (pmatch[0].rm_eo - pmatch[0].rm_so);
-		size_t cpuid_len;
-
-		/* If the full CPUID format isn't required,
-		 * ignoring the stepping.
-		 */
-		if (!full_mapcpuid && full_cpuid)
-			cpuid_len = strrchr(id, '-') - id;
-		else
-			cpuid_len = strlen(id);
-
-		/* Verify the entire string matched. */
-		if (match_len == cpuid_len)
-			return 0;
-	}
-
-	return 1;
-}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 3b5a0382fe15..c1f77babcb70 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -11,7 +11,10 @@
 
 #include <byteswap.h>
 #include <dirent.h>
+#include <elf.h>
+#include <linux/bitfield.h>
 #include <linux/bitops.h>
+#include <linux/bits.h>
 #include <linux/compiler.h>
 #include <linux/ctype.h>
 #include <linux/kernel.h>
@@ -957,12 +960,70 @@ char *get_cpuid_allow_env_override(struct perf_cpu cpu)
 	return cpuid;
 }
 
-/* Return zero when the cpuid from the mapfile.csv matches the
- * cpuid string generated on this platform.
- * Otherwise return non-zero.
+#define MIDR_REVISION_MASK	GENMASK(3, 0)
+#define MIDR_VARIANT_MASK	GENMASK(23, 20)
+
+/* Is @id a full x86 vendor-family-model-stepping CPUID, with 3 hyphens? */
+static bool is_full_x86_cpuid(const char *id)
+{
+	const char *tmp = id;
+	int count = 0;
+
+	while ((tmp = strchr(tmp, '-')) != NULL) {
+		count++;
+		tmp++;
+	}
+
+	return count == 3;
+}
+
+/*
+ * Compare arm64 MIDR values. Return 0 if @idstr is the same CPU type as
+ * @mapcpuid and its version, the Variant[23:20] and Revision[3:0] fields, is
+ * greater than or equal to that of @mapcpuid. Therefore, if @mapcpuid has 0 for
+ * the revision and variant then any version of @idstr will match as long as
+ * it's the same CPU type.
+ *
+ * Return 1 if the CPU type is different or the version of @idstr is lower.
  */
-int __weak strcmp_cpuid_str(uint16_t e_machine __maybe_unused, const char *mapcpuid,
-			    const char *cpuid)
+static int strcmp_arm64_cpuid_str(const char *mapcpuid, const char *idstr)
+{
+	u64 map_id = strtoull(mapcpuid, NULL, 16);
+	char map_id_variant = FIELD_GET(MIDR_VARIANT_MASK, map_id);
+	char map_id_revision = FIELD_GET(MIDR_REVISION_MASK, map_id);
+	u64 id = strtoull(idstr, NULL, 16);
+	char id_variant = FIELD_GET(MIDR_VARIANT_MASK, id);
+	char id_revision = FIELD_GET(MIDR_REVISION_MASK, id);
+	u64 id_fields = ~(MIDR_VARIANT_MASK | MIDR_REVISION_MASK);
+
+	/* Compare without version first. */
+	if ((map_id & id_fields) != (id & id_fields))
+		return 1;
+
+	/*
+	 * ID matches, now compare version.
+	 *
+	 * Arm revisions (like r0p0) are compared here like two digit semver
+	 * values eg. 1.3 < 2.0 < 2.1 < 2.2.
+	 *
+	 *  r = high value = 'Variant' field in MIDR
+	 *  p = low value  = 'Revision' field in MIDR
+	 */
+	if (id_variant > map_id_variant)
+		return 0;
+
+	if (id_variant == map_id_variant && id_revision >= map_id_revision)
+		return 0;
+
+	/*
+	 * Variant is less than mapfile variant or variants are the same but
+	 * the revision doesn't match. Return no match.
+	 */
+	return 1;
+}
+
+/* Return 0 if all of @cpuid matches the extended regular expression @mapcpuid. */
+static int strcmp_regex_cpuid_str(const char *mapcpuid, const char *cpuid)
 {
 	regex_t re;
 	regmatch_t pmatch[1];
@@ -986,6 +1047,96 @@ int __weak strcmp_cpuid_str(uint16_t e_machine __maybe_unused, const char *mapcp
 	return 1;
 }
 
+/*
+ * Compare x86 CPUIDs of the form vendor-family-model[-stepping]. A full
+ * @mapcpuid is stepping specific and requires a full @cpuid, otherwise the
+ * stepping of a full @cpuid is ignored.
+ */
+static int strcmp_x86_cpuid_str(const char *mapcpuid, const char *cpuid)
+{
+	unsigned int family, model, step;
+	char norm_buf[128], buf[128];
+	char vendor[32], extra;
+	bool full_mapcpuid, full_cpuid;
+
+	/* x86 get_cpuid() writes "vendor,family,model,step" in decimal. */
+	if (sscanf(cpuid, "%31[^,],%u,%u,%u%c", vendor, &family, &model, &step, &extra) == 4) {
+		snprintf(norm_buf, sizeof(norm_buf), "%s-%u-%X-%X", vendor, family, model, step);
+		cpuid = norm_buf;
+	}
+
+	full_mapcpuid = is_full_x86_cpuid(mapcpuid);
+	full_cpuid = is_full_x86_cpuid(cpuid);
+
+	/*
+	 * Full CPUID format is required to identify a stepping specific
+	 * platform. Error out if the cpuid string is incomplete.
+	 */
+	if (full_mapcpuid && !full_cpuid) {
+		pr_info("Invalid CPUID %s. Full CPUID is required, vendor-family-model-stepping\n",
+			cpuid);
+		return 1;
+	}
+
+	/* If the full CPUID format isn't required, ignore the stepping. */
+	if (!full_mapcpuid && full_cpuid) {
+		int len = strrchr(cpuid, '-') - cpuid;
+
+		snprintf(buf, sizeof(buf), "%.*s", len, cpuid);
+		cpuid = buf;
+	}
+	return strcmp_regex_cpuid_str(mapcpuid, cpuid);
+}
+
+/* Compare PowerPC PVR CPUIDs, matching @cpuid against the regex @mapcpuid. */
+static int strcmp_powerpc_cpuid_str(const char *mapcpuid, const char *cpuid)
+{
+	unsigned long pvr_ver, pvr_rev;
+	char norm_buf[32], extra;
+
+	/* PowerPC get_cpuid() writes "pvr_ver,pvr_rev" in decimal. */
+	if (sscanf(cpuid, "%lu,%lu%c", &pvr_ver, &pvr_rev, &extra) == 2) {
+		unsigned long pvr = ((pvr_ver & 0xffff) << 16) | (pvr_rev & 0xffff);
+
+		snprintf(norm_buf, sizeof(norm_buf), "0x%.8lx", pvr);
+		cpuid = norm_buf;
+	}
+	return strcmp_regex_cpuid_str(mapcpuid, cpuid);
+}
+
+/**
+ * strcmp_cpuid_str - Compare a pmu-events mapfile.csv CPUID with a CPUID.
+ * @e_machine: The ELF machine of the CPUIDs' architecture.
+ * @mapcpuid: The CPUID from the mapfile.csv, a regular expression for most
+ *            architectures.
+ * @cpuid: The CPUID from get_cpuid_str() or HEADER_CPUID.
+ *
+ * The test and common tables use EM_NONE and are compared exactly, arm64
+ * compares MIDR values and other architectures match @cpuid against the
+ * regular expression @mapcpuid. HEADER_CPUID values written by get_cpuid() on
+ * x86 and PowerPC differ from the get_cpuid_str() format of the mapfile.csv
+ * and are converted before matching.
+ *
+ * Return: 0 if the CPUIDs match, otherwise 1.
+ */
+int strcmp_cpuid_str(uint16_t e_machine, const char *mapcpuid, const char *cpuid)
+{
+	switch (e_machine) {
+	case EM_NONE:
+		return strcmp(mapcpuid, cpuid) ? 1 : 0;
+	case EM_AARCH64:
+		return strcmp_arm64_cpuid_str(mapcpuid, cpuid);
+	case EM_386:
+	case EM_X86_64:
+		return strcmp_x86_cpuid_str(mapcpuid, cpuid);
+	case EM_PPC:
+	case EM_PPC64:
+		return strcmp_powerpc_cpuid_str(mapcpuid, cpuid);
+	default:
+		return strcmp_regex_cpuid_str(mapcpuid, cpuid);
+	}
+}
+
 /*
  * default get_cpuid(): nothing gets recorded
  * actual implementation must be in arch/$(SRCARCH)/util/header.c
-- 
2.56.1.750.gf70dc682cf-goog


  parent reply	other threads:[~2026-11-20 22:14 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-20 22:13 [PATCH v3 00/30] perf: Per-env PMUs, metric event sharing, and recorded event metrics Ian Rogers
2026-11-20 22:13 ` [PATCH v3 01/30] perf pmus: Don't skip core PMUs as duplicates Ian Rogers
2026-11-20 22:13 ` [PATCH v3 02/30] perf script: Fix metrics computed from samples Ian Rogers
2026-11-20 22:13 ` [PATCH v3 03/30] perf script: Don't drop metric samples for CPUs missing from the evsel Ian Rogers
2026-11-20 22:13 ` [PATCH v3 04/30] perf metricgroup: Don't prefer tool events for displaying a metric Ian Rogers
2026-11-20 22:13 ` [PATCH v3 05/30] perf env: Make lazy perf_env initialization thread-safe Ian Rogers
2026-11-20 22:13 ` [PATCH v3 06/30] perf env: Add host_env() singleton Ian Rogers
2026-11-20 22:13 ` [PATCH v3 07/30] perf pmu: Add from_env parameter to perf_pmu__init() Ian Rogers
2026-11-20 22:13 ` [PATCH v3 08/30] perf pmus: Introduce struct perf_pmus and perf_env__pmus() Ian Rogers
2026-11-20 22:13 ` [PATCH v3 09/30] perf pmus: Pass struct perf_pmus to find helpers Ian Rogers
2026-11-20 22:13 ` [PATCH v3 10/30] perf pmus: Pass struct perf_pmus to scan helpers Ian Rogers
2026-11-20 22:13 ` [PATCH v3 11/30] perf pmu-events: Add e_machine to struct pmu_events_map Ian Rogers
2026-11-20 22:13 ` [PATCH v3 12/30] perf pmu-events: Pass e_machine to find_core_*_table() Ian Rogers
2026-11-20 22:13 ` [PATCH v3 13/30] perf header: Pass e_machine to strcmp_cpuid_str() Ian Rogers
2026-11-20 22:13 ` Ian Rogers [this message]
2026-11-20 22:13 ` [PATCH v3 15/30] perf test: Make the CPUID matching test architecture independent Ian Rogers
2026-11-20 22:13 ` [PATCH v3 16/30] perf test: Add CPUID matching tests for other architectures Ian Rogers
2026-11-20 22:13 ` [PATCH v3 17/30] perf dwarf-regs: Add e_machine__same_arch() Ian Rogers
2026-11-20 22:13 ` [PATCH v3 18/30] perf metricgroup: Pass struct perf_pmus to metricgroup__for_each_metric() Ian Rogers
2026-11-20 22:13 ` [PATCH v3 19/30] perf metricgroup: Move matching of metrics to recorded events from perf script Ian Rogers
2026-11-20 22:13 ` [PATCH v3 20/30] perf parse-events: Decode metric-id terms when adding events Ian Rogers
2026-11-20 22:13 ` [PATCH v3 21/30] perf evsel: Generalize metric_id to a set of metric_ids Ian Rogers
2026-11-20 22:13 ` [PATCH v3 22/30] perf pmu: Add perf_pmu__for_each_name_from_config() Ian Rogers
2026-11-20 22:13 ` [PATCH v3 23/30] perf metricgroup: Share metric events by their counter encoding Ian Rogers
2026-11-20 22:13 ` [PATCH v3 24/30] perf stat: Share events between metrics and command line events Ian Rogers
2026-11-20 22:13 ` [PATCH v3 25/30] perf pmus: Add perf_pmus__read_from_env() Ian Rogers
2026-11-20 22:42   ` sashiko-bot
2026-11-20 22:13 ` [PATCH v3 26/30] perf metricgroup: Improve matching of metrics to recorded events Ian Rogers
2026-11-20 22:13 ` [PATCH v3 27/30] perf metricgroup: Add metricgroup__add_recorded_metrics() Ian Rogers
2026-11-20 22:13 ` [PATCH v3 28/30] perf stat report: Display metrics for recorded events Ian Rogers
2026-11-20 22:13 ` [PATCH v3 29/30] perf script: Display metrics for perf stat record data Ian Rogers
2026-11-20 22:13 ` [PATCH v3 30/30] perf test: Add stat record metrics test Ian Rogers
2026-11-20 22:42 ` [PATCH v3 00/30] perf: Per-env PMUs, metric event sharing, and recorded event metrics sashiko-bot

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20261120221332.2245191-15-irogers@google.com \
    --to=irogers@google.com \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=james.clark@linaro.org \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.