Skip to contentSkip to conversation

Use more flexible pattern matching for CPU identification for mapfile.csv

PATCH In review William Cohen 4 participants 4 messages Dec 4, 2017 – Dec 6, 2017 perf events

lore
Share & tools
lore
#0 lore raw

PATCH v4 1/1 Use more flexible pattern matching for CPU identification for mapfile.csv

The powerpc cpuid information includes chip revision information. Changes between chip revisions are usually minor bug fixes and usually do not affect the operation of the performance monitoring hardware. The original mapfile.csv matching requires enumerating every possible cpuid string. When a new minor chip revision is produced a new entry has to be added to the mapfile.csv and the code recompiled to allow perf to have the implementation specific perf events for this new minor revision. For users of various distibutions of Linux having to wait for a new release of the kernel's perf tool to be built with these trivial patches is inconvenient.

Using regular expressions rather than exactly string matching of the entire cpuid string allows developers to write mapfile.csv files that do not require patches and recompiles for each of these minor version changes. If special cases need to be made for some particular versions, they can be placed earlier in the mapfile.csv file before the more general matches.

---
 tools/perf/pmu-events/arch/powerpc/mapfile.csv | 12 ++------
 tools/perf/pmu-events/arch/x86/mapfile.csv     |  5 +---
 tools/perf/pmu-events/jevents.c                | 39 +++++++++++++++++++++++++-
 tools/perf/util/pmu.c                          | 20 ++++++++++++-
 4 files changed, 60 insertions(+), 16 deletions(-)
tools/perf/pmu-events/arch/powerpc/mapfile.csv +2 -10
index a0f3a11ca19f..229150e7ab7d 100644
@@ -13,13 +13,5 @@
 #
 
 # Power8 entries
-004b0000,1,power8,core
-004b0201,1,power8,core
-004c0000,1,power8,core
-004d0000,1,power8,core
-004d0100,1,power8,core
-004d0200,1,power8,core
-004c0100,1,power8,core
-004e0100,1,power9,core
-004e0200,1,power9,core
-004e1200,1,power9,core
+004[bcd][[:xdigit:]]{4},1,power8,core
+004e[[:xdigit:]]{4},1,power9,core
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -4
index fe1a2c47cabf..93656f2fd53a 100644
@@ -23,10 +23,7 @@ GenuineIntel-6-1E,v2,nehalemep,core
 GenuineIntel-6-1F,v2,nehalemep,core
 GenuineIntel-6-1A,v2,nehalemep,core
 GenuineIntel-6-2E,v2,nehalemex,core
-GenuineIntel-6-4E,v24,skylake,core
-GenuineIntel-6-5E,v24,skylake,core
-GenuineIntel-6-8E,v24,skylake,core
-GenuineIntel-6-9E,v24,skylake,core
+GenuineIntel-6-[4589]E,v24,skylake,core
 GenuineIntel-6-37,v13,silvermont,core
 GenuineIntel-6-4D,v13,silvermont,core
 GenuineIntel-6-4C,v13,silvermont,core
tools/perf/pmu-events/jevents.c +38 -1
index 9eb7047bafe4..b578aa26e375 100644
@@ -116,6 +116,43 @@ static void fixdesc(char *s)
 		*e = 0;
 }
 
+/* Add escapes for '\' so they are proper C strings. */
+static char *fixregex(char *s)
+{
+	int len = 0;
+	int esc_count = 0;
+	char *fixed = NULL;
+	char *p, *q;
+
+	/* Count the number of '\' in string */
+	for (p = s; *p; p++) {
+		++len;
+		if (*p == '\\')
+			++esc_count;
+	}
+
+	if (esc_count == 0)
+		return s;
+
+	/* allocate space for a new string */
+	fixed = (char *) malloc(len + 1);
+	if (!fixed)
+		return NULL;
+
+	/* copy over the characters */
+	q = fixed;
+	for (p = s; *p; p++) {
+		if (*p == '\\') {
+			*q = '\\';
+			++q;
+		}
+		*q = *p;
+		++q;
+	}
+	*q = '\0';
+	return fixed;
+}
+
 static struct msrmap {
 	const char *num;
 	const char *pname;
@@ -648,7 +685,7 @@ static int process_mapfile(FILE *outfp, char *fpath)
 		}
 		line[strlen(line)-1] = '\0';
 
-		cpuid = strtok_r(p, ",", &save);
+		cpuid = fixregex(strtok_r(p, ",", &save));
 		version = strtok_r(NULL, ",", &save);
 		fname = strtok_r(NULL, ",", &save);
 		type = strtok_r(NULL, ",", &save);
tools/perf/util/pmu.c +19 -1
index 07cb2ac041d7..fc8866e8b02a 100644
@@ -12,6 +12,7 @@
 #include <dirent.h>
 #include <api/fs/fs.h>
 #include <locale.h>
+#include <regex.h>
 #include "util.h"
 #include "pmu.h"
 #include "parse-events.h"
@@ -570,14 +571,31 @@ struct pmu_events_map *perf_pmu__find_map(void)
 
 	i = 0;
 	for (;;) {
+		regex_t re;
+		regmatch_t pmatch[1];
+		int match;
+
 		map = &pmu_events_map[i++];
 		if (!map->table) {
 			map = NULL;
 			break;
 		}
 
-		if (!strcmp(map->cpuid, cpuid))
+		if (regcomp(&re, map->cpuid, REG_EXTENDED) != 0) {
+			/* Warn unable to generate match particular string. */
+			pr_info("Invalid regular expression %s\n", map->cpuid);
 			break;
+		}
+
+		match = !regexec(&re, cpuid, 1, pmatch, 0);
+		regfree(&re);
+		if (match) {
+			size_t match_len = (pmatch[0].rm_eo - pmatch[0].rm_so);
+
+			/* Verify the entire string matched. */
+			if (match_len == strlen(cpuid))
+				break;
+		}
 	}
 	free(cpuid);
 	return map;
Signature · 1 line
2.13.6
Tested-by on v4 1/1
#1 lore raw
Quoted 11 lines · William Cohen

The powerpc cpuid information includes chip revision information. Changes between chip revisions are usually minor bug fixes and usually do not affect the operation of the performance monitoring hardware. The original mapfile.csv matching requires enumerating every possible cpuid string. When a new minor chip revision is produced a new entry has to be added to the mapfile.csv and the code recompiled to allow perf to have the implementation specific perf events for this new minor revision. For users of various distibutions of Linux having to wait for a new release of the kernel's perf tool to be built with these trivial patches is inconvenient.

Thanks,
Ravi

#2 lore raw

Em Tue, Dec 05, 2017 at 09:25:56AM +0530, Ravi Bangoria escreveu:

Quoted 14 lines · William Cohen
Quoted 11 lines

The powerpc cpuid information includes chip revision information. Changes between chip revisions are usually minor bug fixes and usually do not affect the operation of the performance monitoring hardware. The original mapfile.csv matching requires enumerating every possible cpuid string. When a new minor chip revision is produced a new entry has to be added to the mapfile.csv and the code recompiled to allow perf to have the implementation specific perf events for this new minor revision. For users of various distibutions of Linux having to wait for a new release of the kernel's perf tool to be built with these trivial patches is inconvenient.

Quoted 1 line

Thanks, added to the commit.

- Arnaldo

#3 lore raw

[tip:perf/core] perf vendor events: Use more flexible pattern matching for CPU identification for mapfile.csv

In reply to William Cohen
perf vendor events: Use more flexible pattern matching for CPU identification for mapfile.csv
Commit-ID:  fbc2844e84038ce3687d203ac80b66194e9f21e6
Gitweb:     https://git.kernel.org/tip/fbc2844e84038ce3687d203ac80b66194e9f21e6
Author:     William Cohen <[email protected]>
AuthorDate: Mon, 4 Dec 2017 09:57:28 -0500
Committer:  Arnaldo Carvalho de Melo <[email protected]>
CommitDate: Tue, 5 Dec 2017 15:43:55 -0300

perf vendor events: Use more flexible pattern matching for CPU identification for mapfile.csv

The powerpc cpuid information includes chip revision information. Changes between chip revisions are usually minor bug fixes and usually do not affect the operation of the performance monitoring hardware.

The original mapfile.csv matching requires enumerating every possible cpuid string. When a new minor chip revision is produced a new entry has to be added to the mapfile.csv and the code recompiled to allow perf to have the implementation specific perf events for this new minor revision. For users of various distibutions of Linux having to wait for a new release of the kernel's perf tool to be built with these trivial patches is inconvenient.

Using regular expressions rather than exactly string matching of the entire cpuid string allows developers to write mapfile.csv files that do not require patches and recompiles for each of these minor version changes. If special cases need to be made for some particular versions, they can be placed earlier in the mapfile.csv file before the more general matches.

---
 tools/perf/pmu-events/arch/powerpc/mapfile.csv | 12 ++------
 tools/perf/pmu-events/arch/x86/mapfile.csv     |  5 +---
 tools/perf/pmu-events/jevents.c                | 39 +++++++++++++++++++++++++-
 tools/perf/util/pmu.c                          | 20 ++++++++++++-
 4 files changed, 60 insertions(+), 16 deletions(-)
tools/perf/pmu-events/arch/powerpc/mapfile.csv +2 -10
index a0f3a11..229150e 100644
@@ -13,13 +13,5 @@
 #
 
 # Power8 entries
-004b0000,1,power8,core
-004b0201,1,power8,core
-004c0000,1,power8,core
-004d0000,1,power8,core
-004d0100,1,power8,core
-004d0200,1,power8,core
-004c0100,1,power8,core
-004e0100,1,power9,core
-004e0200,1,power9,core
-004e1200,1,power9,core
+004[bcd][[:xdigit:]]{4},1,power8,core
+004e[[:xdigit:]]{4},1,power9,core
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -4
index fe1a2c4..93656f2 100644
@@ -23,10 +23,7 @@ GenuineIntel-6-1E,v2,nehalemep,core
 GenuineIntel-6-1F,v2,nehalemep,core
 GenuineIntel-6-1A,v2,nehalemep,core
 GenuineIntel-6-2E,v2,nehalemex,core
-GenuineIntel-6-4E,v24,skylake,core
-GenuineIntel-6-5E,v24,skylake,core
-GenuineIntel-6-8E,v24,skylake,core
-GenuineIntel-6-9E,v24,skylake,core
+GenuineIntel-6-[4589]E,v24,skylake,core
 GenuineIntel-6-37,v13,silvermont,core
 GenuineIntel-6-4D,v13,silvermont,core
 GenuineIntel-6-4C,v13,silvermont,core
tools/perf/pmu-events/jevents.c +38 -1
index 9eb7047..b578aa2 100644
@@ -116,6 +116,43 @@ static void fixdesc(char *s)
 		*e = 0;
 }
 
+/* Add escapes for '\' so they are proper C strings. */
+static char *fixregex(char *s)
+{
+	int len = 0;
+	int esc_count = 0;
+	char *fixed = NULL;
+	char *p, *q;
+
+	/* Count the number of '\' in string */
+	for (p = s; *p; p++) {
+		++len;
+		if (*p == '\\')
+			++esc_count;
+	}
+
+	if (esc_count == 0)
+		return s;
+
+	/* allocate space for a new string */
+	fixed = (char *) malloc(len + 1);
+	if (!fixed)
+		return NULL;
+
+	/* copy over the characters */
+	q = fixed;
+	for (p = s; *p; p++) {
+		if (*p == '\\') {
+			*q = '\\';
+			++q;
+		}
+		*q = *p;
+		++q;
+	}
+	*q = '\0';
+	return fixed;
+}
+
 static struct msrmap {
 	const char *num;
 	const char *pname;
@@ -648,7 +685,7 @@ static int process_mapfile(FILE *outfp, char *fpath)
 		}
 		line[strlen(line)-1] = '\0';
 
-		cpuid = strtok_r(p, ",", &save);
+		cpuid = fixregex(strtok_r(p, ",", &save));
 		version = strtok_r(NULL, ",", &save);
 		fname = strtok_r(NULL, ",", &save);
 		type = strtok_r(NULL, ",", &save);
tools/perf/util/pmu.c +19 -1
index 8b7c151..57e38fd 100644
@@ -12,6 +12,7 @@
 #include <dirent.h>
 #include <api/fs/fs.h>
 #include <locale.h>
+#include <regex.h>
 #include "util.h"
 #include "pmu.h"
 #include "parse-events.h"
@@ -609,14 +610,31 @@ struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu)
 
 	i = 0;
 	for (;;) {
+		regex_t re;
+		regmatch_t pmatch[1];
+		int match;
+
 		map = &pmu_events_map[i++];
 		if (!map->table) {
 			map = NULL;
 			break;
 		}
 
-		if (!strcmp(map->cpuid, cpuid))
+		if (regcomp(&re, map->cpuid, REG_EXTENDED) != 0) {
+			/* Warn unable to generate match particular string. */
+			pr_info("Invalid regular expression %s\n", map->cpuid);
 			break;
+		}
+
+		match = !regexec(&re, cpuid, 1, pmatch, 0);
+		regfree(&re);
+		if (match) {
+			size_t match_len = (pmatch[0].rm_eo - pmatch[0].rm_so);
+
+			/* Verify the entire string matched. */
+			if (match_len == strlen(cpuid))
+				break;
+		}
 	}
 	free(cpuid);
 	return map;