Skip to contentSkip to conversation

perf: Add support for full Intel event lists v8

PATCH New Andi Kleen 3 participants 13 messages Jul 30, 2014 – Nov 25, 2014 perf events

lore
Share & tools
lore

Andi Kleen

author
#0 lore raw

Since it seems the download mechanism is controversal, I removed the downloader for now until a suitable distribution method with kernel.org can be established. This is just the rest of the perf JSON event code that should hopefully not be controversal.

[v2: Review feedback addressed and some minor improvements] [v3: More review feedback addressed and handle test failures better. Ported to latest tip/core.]
[v4: Addressed Namhyung's feedback]
[v5: Rebase to latest tree. Minor description update.]
[v6: Rebase. Add acked by from Namhyung and address feedback. Some minor fixes. Should be good to go now I hope. The period patch was dropped, as that is already handled. I added an extra patch for a --quiet argument for perf list]
[v7: Address Jiri's feedback. Various changes and some patches were split. perf download uses curl now instead of wget.] [v8: Removed perf download for now. Port to latest tip/perf/core]

perf has high level events which are useful in many cases. However there are some tuning situations where low level events in the CPU are needed. Traditionally this required specifying the event in raw form (very awkward) or using non standard frontends like ocperf or patching in libpfm.

Intel CPUs can have very large event files (Haswell has ~336 core events, much more if you add uncore or all the offcore combinations), which is too large to describe through the kernel interface. It would require tying up significant amounts of unswappable memory for this.

Intel releases these JSON files in a standardized JSON format. perf adds a parser that converts the JSON format into perf event aliases, which then can be used directly as any other perf event.

The parsing is done using a simple existing JSON library.

The events are still abstracted for perf, but the abstraction mechanism is through the file instead of through the kernel.

The JSON format and perf parser has some minor Intelisms, but they are simple and small and optional. It's easy to extend, so it would be possible to use it for other CPUs too, add different pmu attributes, and add new download sites to the downloader tool. For example the format can be used on POWER.

Currently only core events are supported, uncore may come at a later point. No kernel changes, all code in perf user tools only.

Some of the parser files are partially shared with separate event parser library and are thus 2-clause BSD licensed.

Patches also available from
git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-misc perf/json

Example output:

<Put JSON file for CPU in .cache/pmu-events/Vendor-Family-Model-core.json, for example GenuineIntel-6-3E-core.json>
% perf list
...
br_inst_exec.all_branches [Speculative and retired
branches]
br_inst_exec.all_conditional [Speculative and retired
macro-conditional branches]
br_inst_exec.all_direct_jmp [Speculative and retired
macro-unconditional branches excluding calls and indirects]
... 333 more new events ...

% perf stat -e br_inst_exec.all_direct_jmp true

Performance counter stats for 'true':

             6,817      cpu/br_inst_exec.all_direct_jmp/                                   

       0.003503212 seconds time elapsed

One nice feature is that a pointer to the specification update is now included in the description, which will hopefully clear up many problems:

% perf list
...
mem_load_uops_l3_hit_retired.xsnp_hit [Retired load uops which
data sources were L3 and cross-core snoop hits in on-pkg core cache. Supports address when precise. Spec
update: HSM26, HSM30 (Precise event)]
...

-Andi

author
#1 lore raw

PATCH 1/10 perf, tools: Add jsmn `jasmine' JSON parser

From: Andi Kleen <[email protected]>

I need a JSON parser. This adds the simplest JSON parser I could find -- Serge Zaitsev's jsmn `jasmine' -- to the perf library. I merely converted it to (mostly) Linux style and added support for non 0 terminated input.

The parser is quite straight forward and does not copy any data, just returns tokens with offsets into the input buffer. So it's relatively efficient and simple to use.

The code is not fully checkpatch clean, but I didn't want to completely fork the upstream code.

Original source: http://zserge.bitbucket.org/jsmn.html

In addition I added a simple wrapper that mmaps a json file and provides some straight forward access functions.

Used in follow-on patches to parse event files.

v2: Address review feedback.
v3: Minor checkpatch fixes.

---
 tools/perf/Makefile.perf |   4 +
 tools/perf/util/jsmn.c   | 313 +++++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/jsmn.h   |  67 ++++++++++
 tools/perf/util/json.c   | 155 +++++++++++++++++++++++
 tools/perf/util/json.h   |  13 ++
 5 files changed, 552 insertions(+)
 create mode 100644 tools/perf/util/jsmn.c
 create mode 100644 tools/perf/util/jsmn.h
 create mode 100644 tools/perf/util/json.c
 create mode 100644 tools/perf/util/json.h
tools/perf/Makefile.perf +4 -0
index 2240974..074b826 100644
@@ -302,6 +302,8 @@ LIB_H += ui/util.h
 LIB_H += ui/ui.h
 LIB_H += util/data.h
 LIB_H += util/kvm-stat.h
+LIB_H += util/jsmn.h
+LIB_H += util/json.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -377,6 +379,8 @@ LIB_OBJS += $(OUTPUT)util/srcline.o
 LIB_OBJS += $(OUTPUT)util/data.o
 LIB_OBJS += $(OUTPUT)util/tsc.o
 LIB_OBJS += $(OUTPUT)util/cloexec.o
+LIB_OBJS += $(OUTPUT)util/jsmn.o
+LIB_OBJS += $(OUTPUT)util/json.o
 
 LIB_OBJS += $(OUTPUT)ui/setup.o
 LIB_OBJS += $(OUTPUT)ui/helpline.o
tools/perf/util/jsmn.c new file +313 -0

313 lines not on this page · raw message

tools/perf/util/jsmn.h new file +67 -0

67 lines not on this page · raw message

tools/perf/util/json.c new file +155 -0

155 lines not on this page · raw message

tools/perf/util/json.h new file +13 -0
new file mode 100644
index 0000000..37dd9e9
@@ -0,0 +1,13 @@
+#ifndef JSON_H
+#define JSON_H 1
+
+#include "jsmn.h"
+
+jsmntok_t *parse_json(const char *fn, char **map, size_t *size, int *len);
+void free_json(char *map, size_t size, jsmntok_t *tokens);
+int json_line(char *map, jsmntok_t *t);
+const char *json_name(jsmntok_t *t);
+int json_streq(char *map, jsmntok_t *t, const char *s);
+int json_len(jsmntok_t *t);
+
+#endif
Signature · 1 line
1.9.3
author
#2 lore raw

PATCH 2/10 perf, tools: Add support for text descriptions of events and alias add

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

Change pmu.c to allow descriptions of events and add interfaces to add aliases at runtime from another file. To be used by jevents in a followon patch

v2: Move perf list changes to other patch.

---
 tools/perf/util/pmu.c | 43 ++++++++++++++++++++++++++++++-------------
 1 file changed, 30 insertions(+), 13 deletions(-)
tools/perf/util/pmu.c +30 -13
index 7a811eb..f9c7046 100644
@@ -14,6 +14,7 @@
 
 struct perf_pmu_alias {
 	char *name;
+	char *desc;
 	struct list_head terms;
 	struct list_head list;
 	char unit[UNIT_MAX_LEN+1];
@@ -171,17 +172,12 @@ error:
 	return -1;
 }
 
-static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file)
+static int __perf_pmu__new_alias(struct list_head *list, char *name,
+				 char *dir, char *desc, char *val)
 {
 	struct perf_pmu_alias *alias;
-	char buf[256];
 	int ret;
 
-	ret = fread(buf, 1, sizeof(buf), file);
-	if (ret == 0)
-		return -EINVAL;
-	buf[ret] = 0;
-
 	alias = malloc(sizeof(*alias));
 	if (!alias)
 		return -ENOMEM;
@@ -190,24 +186,45 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 	alias->scale = 1.0;
 	alias->unit[0] = '\0';
 
-	ret = parse_events_terms(&alias->terms, buf);
+	ret = parse_events_terms(&alias->terms, val);
 	if (ret) {
+		pr_err("Cannot parse alias %s: %d\n", val, ret);
 		free(alias);
 		return ret;
 	}
 
 	alias->name = strdup(name);
-	/*
-	 * load unit name and scale if available
-	 */
-	perf_pmu__parse_unit(alias, dir, name);
-	perf_pmu__parse_scale(alias, dir, name);
 
+	if (dir) {
+		/*
+		 * load unit name and scale if available
+		 */
+		perf_pmu__parse_unit(alias, dir, name);
+		perf_pmu__parse_scale(alias, dir, name);
+	}
+
+	alias->desc = desc ? strdup(desc) : NULL;
 	list_add_tail(&alias->list, list);
 
 	return 0;
 }
 
+static int perf_pmu__new_alias(struct list_head *list,
+			       char *dir,
+			       char *name,
+			       FILE *file)
+{
+	char buf[256];
+	int ret;
+
+	ret = fread(buf, 1, sizeof(buf), file);
+	if (ret == 0)
+		return -EINVAL;
+	buf[ret] = 0;
+
+	return __perf_pmu__new_alias(list, name, dir, NULL, buf);
+}
+
 /*
  * Process all the sysfs attributes located under the directory
  * specified in 'dir' parameter.
Signature · 1 line
1.9.3
author
#3 lore raw

PATCH 3/10 perf, tools, list: Update perf list to output descriptions

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

Add support to perf list to print aliases with descriptions. Support word wrapping for descriptions.
Fix up the sorting code to put aliases with descriptions last.

---
 tools/perf/util/pmu.c | 84 +++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 68 insertions(+), 16 deletions(-)
tools/perf/util/pmu.c +68 -16
index f9c7046..baec090 100644
@@ -737,11 +737,51 @@ static char *format_alias_or(char *buf, int len, struct perf_pmu *pmu,
 	return buf;
 }
 
-static int cmp_string(const void *a, const void *b)
+struct pair {
+	char *name;
+	char *desc;
+};
+
+static int cmp_pair(const void *a, const void *b)
+{
+	const struct pair *as = a;
+	const struct pair *bs = b;
+
+	/* Put downloaded event list last */
+	if (!!as->desc != !!bs->desc)
+		return !!as->desc - !!bs->desc;
+	return strcmp(as->name, bs->name);
+}
+
+static void wordwrap(char *s, int start, int max, int corr)
+{
+	int column = start;
+	int n;
+
+	while (*s) {
+		int wlen = strcspn(s, " \t");
+
+		if (column + wlen >= max && column > start) {
+			printf("\n%*s", start, "");
+			column = start + corr;
+		}
+		n = printf("%s%.*s", column > start ? " " : "", wlen, s);
+		if (n <= 0)
+			break;
+		s += wlen;
+		column += n;
+		while (isspace(*s))
+			s++;
+	}
+}
+
+static int get_columns(void)
 {
-	const char * const *as = a;
-	const char * const *bs = b;
-	return strcmp(*as, *bs);
+	/*
+	 * Should ask the terminal with TIOCGWINSZ here, but we
+	 * need the original fd before the pager.
+	 */
+	return 79;
 }
 
 void print_pmu_events(const char *event_glob, bool name_only)
@@ -751,21 +791,24 @@ void print_pmu_events(const char *event_glob, bool name_only)
 	char buf[1024];
 	int printed = 0;
 	int len, j;
-	char **aliases;
+	struct pair *aliases;
+	int numdesc = 0;
+	int columns = get_columns();
 
 	pmu = NULL;
 	len = 0;
 	while ((pmu = perf_pmu__scan(pmu)) != NULL)
 		list_for_each_entry(alias, &pmu->aliases, list)
 			len++;
-	aliases = malloc(sizeof(char *) * len);
+	aliases = malloc(sizeof(struct pair) * len);
 	if (!aliases)
 		return;
 	pmu = NULL;
 	j = 0;
 	while ((pmu = perf_pmu__scan(pmu)) != NULL)
 		list_for_each_entry(alias, &pmu->aliases, list) {
-			char *name = format_alias(buf, sizeof(buf), pmu, alias);
+			char *name = alias->desc ? alias->name :
+				format_alias(buf, sizeof(buf), pmu, alias);
 			bool is_cpu = !strcmp(pmu->name, "cpu");
 
 			if (event_glob != NULL &&
@@ -773,22 +816,31 @@ void print_pmu_events(const char *event_glob, bool name_only)
 			      (!is_cpu && strglobmatch(alias->name,
 						       event_glob))))
 				continue;
-			aliases[j] = name;
-			if (is_cpu && !name_only)
-				aliases[j] = format_alias_or(buf, sizeof(buf),
-							      pmu, alias);
-			aliases[j] = strdup(aliases[j]);
+			aliases[j].name = name;
+			if (is_cpu && !name_only && !alias->desc)
+				aliases[j].name = format_alias_or(buf,
+								  sizeof(buf),
+								  pmu, alias);
+			aliases[j].name = strdup(aliases[j].name);
+			aliases[j].desc = alias->desc;
 			j++;
 		}
 	len = j;
-	qsort(aliases, len, sizeof(char *), cmp_string);
+	qsort(aliases, len, sizeof(struct pair), cmp_pair);
 	for (j = 0; j < len; j++) {
 		if (name_only) {
-			printf("%s ", aliases[j]);
+			printf("%s ", aliases[j].name);
 			continue;
 		}
-		printf("  %-50s [Kernel PMU event]\n", aliases[j]);
-		zfree(&aliases[j]);
+		if (aliases[j].desc) {
+			if (numdesc++ == 0 && printed)
+				printf("\n");
+			printf("  %-50s [", aliases[j].name);
+			wordwrap(aliases[j].desc, 53, columns, 1);
+			printf("]\n");
+		} else
+			printf("  %-50s [Kernel PMU event]\n", aliases[j].name);
+		zfree(&aliases[j].name);
 		printed++;
 	}
 	if (printed)
Signature · 1 line
1.9.3
author
#4 lore raw

PATCH 4/10 perf, tools: Allow events with dot

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

The Intel events use a dot to separate event name and unit mask. Allow dot in names in the scanner, and remove special handling of dot as EOF. Also remove the hack in jevents to replace dot with underscore. This way dotted events can be specified directly by the user.

I'm not fully sure this change to the scanner is correct (what was the dot special case good for?), but I haven't found anything that breaks with it so far at least.

---
 tools/perf/util/parse-events.l | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)
tools/perf/util/parse-events.l +1 -2
index 3432995..709fa3b 100644
@@ -81,7 +81,7 @@ num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]+
 num_raw_hex	[a-fA-F0-9]+
 name		[a-zA-Z_*?][a-zA-Z0-9_*?]*
-name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?]*
+name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.]*
 /* If you add a modifier you need to update check_modifier() */
 modifier_event	[ukhpGHSD]+
 modifier_bp	[rwx]{1,3}
@@ -119,7 +119,6 @@ modifier_bp	[rwx]{1,3}
 			return PE_EVENT_NAME;
 		}
 
-.		|
 <<EOF>>		{
 			BEGIN(INITIAL); yyless(0);
 		}
Signature · 1 line
1.9.3
author
#5 lore raw

PATCH 5/10 perf, tools: Add support for reading JSON event files

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

Add a parser for Intel style JSON event files. This allows to use an Intel event list directly with perf. The Intel event lists can be quite large and are too big to store in unswappable kernel memory.

The parser code knows how to convert the JSON fields
to perf fields. The conversion code is straight forward. It knows (very little) Intel specific information, and can be easily extended to handle fields for other CPUs.

The parser code is partially shared with an independent parsing library, which is 2-clause BSD licenced. To avoid any conflicts I marked those files as BSD licenced too. As part of perf they become GPLv2.

The events are handled using the existing alias machinery.

We output the BriefDescription in perf list.

Right now the json file can be specified as an argument to perf stat/record/list. Followon patches will automate this.

JSON files look like this:

[

  {
    "EventCode": "0x00",
    "UMask": "0x01",
    "EventName": "INST_RETIRED.ANY",
    "BriefDescription": "Instructions retired from execution.",
    "PublicDescription": "Instructions retired from execution.",
    "Counter": "Fixed counter 1",
    "CounterHTOff": "Fixed counter 1",
    "SampleAfterValue": "2000003",
    "MSRIndex": "0",
    "MSRValue": "0",
    "TakenAlone": "0",
    "CounterMask": "0",
    "Invert": "0",
    "AnyThread": "0",
    "EdgeDetect": "0",
    "PEBS": "0",
    "PRECISE_STORE": "0",
    "Errata": "null",
    "Offcore": "0"

}
]

v2: Address review feedback. Rename option to --event-files
v3: Add JSON example
v4: Update manpages.
v5: Don't remove dot in fixname. Fix compile error. Add include protection. Comment realloc.
v6: Include debug/util.h

---
 tools/perf/Documentation/perf-list.txt   |  12 +-
 tools/perf/Documentation/perf-record.txt |   8 +-
 tools/perf/Documentation/perf-stat.txt   |   8 +-
 tools/perf/Makefile.perf                 |   2 +
 tools/perf/builtin-list.c                |   2 +
 tools/perf/builtin-record.c              |   3 +
 tools/perf/builtin-stat.c                |   2 +
 tools/perf/util/jevents.c                | 247 +++++++++++++++++++++++++++++++
 tools/perf/util/jevents.h                |   8 +
 tools/perf/util/json.c                   |   1 +
 tools/perf/util/pmu.c                    |  14 ++
 tools/perf/util/pmu.h                    |   2 +
 12 files changed, 305 insertions(+), 4 deletions(-)
 create mode 100644 tools/perf/util/jevents.c
 create mode 100644 tools/perf/util/jevents.h
tools/perf/Documentation/perf-list.txt +10 -2
index 6fce6a6..da03992 100644
@@ -15,8 +15,16 @@ DESCRIPTION
 This command displays the symbolic event types which can be selected in the
 various perf commands with the -e option.
 
-[[EVENT_MODIFIERS]]
-EVENT MODIFIERS
+OPTIONS
+-------
+--events-file=::
+Specify JSON event list file to use for parsing events. Files can be
+automatically downloaded with perf download.
+The JSON event file can be also specified with the EVENTMAP environment
+variable.
+
+
+[[EVENT_MODIFIERS]] EVENT MODIFIERS
 ---------------
 
 Events can optionally have a modifer by appending a colon and one or
tools/perf/Documentation/perf-record.txt +7 -1
index d460049..62c27fc 100644
@@ -214,6 +214,12 @@ if combined with -a or -C options.
 After starting the program, wait msecs before measuring. This is useful to
 filter out the startup phase of the program, which is often very different.
 
+--events-file=::
+Specify JSON event list file to use for parsing events. Must be specified
+before the -e option. Files can be automatically downloaded with perf download.
+The JSON event file can be also specified with the EVENTMAP environment
+variable.
+
 SEE ALSO
 --------
-linkperf:perf-stat[1], linkperf:perf-list[1]
+linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-download[1]
tools/perf/Documentation/perf-stat.txt +7 -1
index 29ee857..cd9b62f 100644
@@ -142,6 +142,12 @@ filter out the startup phase of the program, which is often very different.
 
 Print statistics of transactional execution if supported.
 
+--events-file=::
+Specify JSON event list file to use for parsing events. Must be specified before
+the -e option. Files can be automatically downloaded with perf download.
+The JSON event file can be also specified with the EVENTMAP environment
+variable.
+
 EXAMPLES
 --------
 
@@ -162,4 +168,4 @@ $ perf stat -- make -j
 
 SEE ALSO
 --------
-linkperf:perf-top[1], linkperf:perf-list[1]
+linkperf:perf-top[1], linkperf:perf-list[1], linkperf:perf-download[1]
tools/perf/Makefile.perf +2 -0
index 074b826..f9cce8e 100644
@@ -304,6 +304,7 @@ LIB_H += util/data.h
 LIB_H += util/kvm-stat.h
 LIB_H += util/jsmn.h
 LIB_H += util/json.h
+LIB_H += util/jevents.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -381,6 +382,7 @@ LIB_OBJS += $(OUTPUT)util/tsc.o
 LIB_OBJS += $(OUTPUT)util/cloexec.o
 LIB_OBJS += $(OUTPUT)util/jsmn.o
 LIB_OBJS += $(OUTPUT)util/json.o
+LIB_OBJS += $(OUTPUT)util/jevents.o
 
 LIB_OBJS += $(OUTPUT)ui/setup.o
 LIB_OBJS += $(OUTPUT)ui/helpline.o
tools/perf/builtin-list.c +2 -0
index 011195e..086c96f 100644
@@ -20,6 +20,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	int i;
 	const struct option list_options[] = {
+		OPT_STRING(0, "events-file", &json_file, "json file",
+			   "Read event json file"),
 		OPT_END()
 	};
 	const char * const list_usage[] = {
tools/perf/builtin-record.c +3 -0
index 4869050..48570821 100644
@@ -25,6 +25,7 @@
 #include "util/cpumap.h"
 #include "util/thread_map.h"
 #include "util/data.h"
+#include "util/pmu.h"
 
 #include <unistd.h>
 #include <sched.h>
@@ -881,6 +882,8 @@ const struct option record_options[] = {
 		    "sample transaction flags (special events only)"),
 	OPT_BOOLEAN(0, "per-thread", &record.opts.target.per_thread,
 		    "use per-thread mmaps"),
+	OPT_STRING(0, "events-file", &json_file, "json file",
+		   "Read event json file"),
 	OPT_END()
 };
 
tools/perf/builtin-stat.c +2 -0
index 3e80aa1..37abdc2 100644
@@ -1668,6 +1668,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "aggregate counts per physical processor core", AGGR_CORE),
 	OPT_UINTEGER('D', "delay", &initial_delay,
 		     "ms to wait before starting measurement after program start"),
+	OPT_STRING(0, "events-file", &json_file, "json file",
+		   "Read event json file"),
 	OPT_END()
 	};
 	const char * const stat_usage[] = {
tools/perf/util/jevents.c new file +247 -0

247 lines not on this page · raw message

tools/perf/util/jevents.h new file +8 -0
new file mode 100644
index 0000000..fbc4549
@@ -0,0 +1,8 @@
+#ifndef JEVENTS_H
+#define JEVENTS_H 1
+
+int json_events(const char *fn,
+		int (*func)(void *data, char *name, char *event, char *desc),
+		void *data);
+
+#endif
tools/perf/util/json.c +1 -0
index cac1b83..82981d2 100644
@@ -37,6 +37,7 @@
 #include <unistd.h>
 #include "jsmn.h"
 #include "json.h"
+#include "util/debug.h"
 #include <linux/kernel.h>
 
 static char *mapfile(const char *fn, size_t *size)
tools/perf/util/pmu.c +14 -0
index baec090..9f154af 100644
@@ -9,6 +9,9 @@
 #include "pmu.h"
 #include "parse-events.h"
 #include "cpumap.h"
+#include "jevents.h"
+
+const char *json_file;
 
 #define UNIT_MAX_LEN	31 /* max length for event unit name */
 
@@ -273,6 +276,14 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 	return ret;
 }
 
+static int add_alias(void *data, char *name, char *event, char *desc)
+{
+	struct list_head *head = (struct list_head *)data;
+
+	__perf_pmu__new_alias(head, name, NULL, desc, event);
+	return 0;
+}
+
 /*
  * Reading the pmu event aliases definition, which should be located at:
  * /sys/bus/event_source/devices/<dev>/events as sysfs group attributes.
@@ -422,6 +433,9 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	if (pmu_aliases(name, &aliases))
 		return NULL;
 
+	if (!strcmp(name, "cpu") && json_file)
+		json_events(json_file, add_alias, &aliases);
+
 	if (pmu_type(name, &type))
 		return NULL;
 
tools/perf/util/pmu.h +2 -0
index c14a543..583d21e 100644
@@ -46,4 +46,6 @@ void print_pmu_events(const char *event_glob, bool name_only);
 bool pmu_have_event(const char *pname, const char *name);
 
 int perf_pmu__test(void);
+
+extern const char *json_file;
 #endif /* __PMU_H */
Signature · 1 line
1.9.3
author
#6 lore raw

PATCH 6/10 perf, tools: Automatically look for event file name for cpu

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

When no JSON event file is specified automatically look for a suitable file in ~/.cache/pmu-events.

The event file format is per architecture, but can be extended for other architectures.

v2: Supports XDG_CACHE_HOME and defaults to ~/.cache/pmu-events
v3: Minor updates and handle EVENTMAP.
v4: Unify with header.c. Now uses CPUID directly.

---
 tools/perf/arch/x86/util/header.c | 19 ++++++++++++++++---
 tools/perf/util/jevents.c         | 40 +++++++++++++++++++++++++++++++++++++++
 tools/perf/util/jevents.h         |  1 +
 tools/perf/util/pmu.c             |  2 +-
 4 files changed, 58 insertions(+), 4 deletions(-)
tools/perf/arch/x86/util/header.c +16 -3
index 146d12a..76e0ece 100644
@@ -5,6 +5,7 @@
 #include <string.h>
 
 #include "../../util/header.h"
+#include "../../util/jevents.h"
 
 static inline void
 cpuid(unsigned int op, unsigned int *a, unsigned int *b, unsigned int *c,
@@ -19,8 +20,8 @@ cpuid(unsigned int op, unsigned int *a, unsigned int *b, unsigned int *c,
 			: "a" (op));
 }
 
-int
-get_cpuid(char *buffer, size_t sz)
+static int
+__get_cpuid(char *buffer, size_t sz, const char *fmt)
 {
 	unsigned int a, b, c, d, lvl;
 	int family = -1, model = -1, step = -1;
@@ -48,7 +49,7 @@ get_cpuid(char *buffer, size_t sz)
 		if (family >= 0x6)
 			model += ((a >> 16) & 0xf) << 4;
 	}
-	nb = scnprintf(buffer, sz, "%s,%u,%u,%u$", vendor, family, model, step);
+	nb = scnprintf(buffer, sz, fmt, vendor, family, model, step);
 
 	/* look for end marker to ensure the entire data fit */
 	if (strchr(buffer, '$')) {
@@ -57,3 +58,15 @@ get_cpuid(char *buffer, size_t sz)
 	}
 	return -1;
 }
+
+int get_cpuid(char *buffer, size_t sz)
+{
+	return __get_cpuid(buffer, sz, "%s,%u,%u,%u$");
+}
+
+char *get_cpu_str(void)
+{
+	char *buf = malloc(128);
+	__get_cpuid(buf, 128, "%s-%d-%X-core");
+	return buf;
+}
tools/perf/util/jevents.c +40 -0
index 023757c..ef4c047 100644
@@ -39,6 +39,44 @@
 #include "json.h"
 #include "jevents.h"
 
+__attribute__((weak)) char *get_cpu_str(void)
+{
+	return NULL;
+}
+
+static const char *json_default_name(void)
+{
+	char *cache;
+	char *idstr = get_cpu_str();
+	char *res = NULL;
+	char *home = NULL;
+	char *emap;
+
+	emap = getenv("EVENTMAP");
+	if (emap) {
+		if (access(emap, R_OK) == 0)
+			return emap;
+		if (asprintf(&idstr, "%s-core", emap) < 0)
+			return NULL;
+	}
+
+	cache = getenv("XDG_CACHE_HOME");
+	if (!cache) {
+		home = getenv("HOME");
+		if (!home || asprintf(&cache, "%s/.cache", home) < 0)
+			goto out;
+	}
+	if (cache && idstr)
+		res = mkpath("%s/pmu-events/%s.json",
+			     cache,
+			     idstr);
+	if (home)
+		free(cache);
+out:
+	free(idstr);
+	return res;
+}
+
 static void addfield(char *map, char **dst, const char *sep,
 		     const char *a, jsmntok_t *bt)
 {
@@ -171,6 +209,8 @@ int json_events(const char *fn,
 	int i, j, len;
 	char *map;
 
+	if (!fn)
+		fn = json_default_name();
 	tokens = parse_json(fn, &map, &size, &len);
 	if (!tokens)
 		return -EIO;
tools/perf/util/jevents.h +1 -0
index fbc4549..86a94dd 100644
@@ -4,5 +4,6 @@
 int json_events(const char *fn,
 		int (*func)(void *data, char *name, char *event, char *desc),
 		void *data);
+char *get_cpu_str(void);
 
 #endif
tools/perf/util/pmu.c +1 -1
index 9f154af..fa21319 100644
@@ -433,7 +433,7 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	if (pmu_aliases(name, &aliases))
 		return NULL;
 
-	if (!strcmp(name, "cpu") && json_file)
+	if (!strcmp(name, "cpu"))
 		json_events(json_file, add_alias, &aliases);
 
 	if (pmu_type(name, &type))
Signature · 1 line
1.9.3
author
#7 lore raw

PATCH 7/10 perf, tools: Query terminal width and use in perf list

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

Automatically adapt the now wider and word wrapped perf list output to wider terminals. This requires querying the terminal before the auto pager takes over, and exporting this information from the pager subsystem.

---
 tools/perf/util/cache.h |  1 +
 tools/perf/util/pager.c | 15 +++++++++++++++
 tools/perf/util/pmu.c   | 12 ++----------
 3 files changed, 18 insertions(+), 10 deletions(-)
tools/perf/util/cache.h +1 -0
index 7b176dd..07527d6 100644
@@ -31,6 +31,7 @@ extern void setup_pager(void);
 extern const char *pager_program;
 extern int pager_in_use(void);
 extern int pager_use_color;
+int pager_get_columns(void);
 
 char *alias_lookup(const char *alias);
 int split_cmdline(char *cmdline, const char ***argv);
tools/perf/util/pager.c +15 -0
index 31ee02d..9761202 100644
@@ -1,6 +1,7 @@
 #include "cache.h"
 #include "run-command.h"
 #include "sigchain.h"
+#include <sys/ioctl.h>
 
 /*
  * This is split up from the rest of git so that we can do
@@ -8,6 +9,7 @@
  */
 
 static int spawned_pager;
+static int pager_columns;
 
 static void pager_preexec(void)
 {
@@ -47,9 +49,12 @@ static void wait_for_pager_signal(int signo)
 void setup_pager(void)
 {
 	const char *pager = getenv("PERF_PAGER");
+	struct winsize sz;
 
 	if (!isatty(1))
 		return;
+	if (ioctl(1, TIOCGWINSZ, &sz) == 0)
+		pager_columns = sz.ws_col;
 	if (!pager) {
 		if (!pager_program)
 			perf_config(perf_default_config, NULL);
@@ -98,3 +103,13 @@ int pager_in_use(void)
 	env = getenv("PERF_PAGER_IN_USE");
 	return env ? perf_config_bool("PERF_PAGER_IN_USE", env) : 0;
 }
+
+int pager_get_columns(void)
+{
+	char *s;
+
+	s = getenv("COLUMNS");
+	if (s)
+		return atoi(s);
+	return (pager_columns ? pager_columns : 80) - 2;
+}
tools/perf/util/pmu.c +2 -10
index fa21319..8714f9a 100644
@@ -9,6 +9,7 @@
 #include "pmu.h"
 #include "parse-events.h"
 #include "cpumap.h"
+#include "cache.h"
 #include "jevents.h"
 
 const char *json_file;
@@ -789,15 +790,6 @@ static void wordwrap(char *s, int start, int max, int corr)
 	}
 }
 
-static int get_columns(void)
-{
-	/*
-	 * Should ask the terminal with TIOCGWINSZ here, but we
-	 * need the original fd before the pager.
-	 */
-	return 79;
-}
-
 void print_pmu_events(const char *event_glob, bool name_only)
 {
 	struct perf_pmu *pmu;
@@ -807,7 +799,7 @@ void print_pmu_events(const char *event_glob, bool name_only)
 	int len, j;
 	struct pair *aliases;
 	int numdesc = 0;
-	int columns = get_columns();
+	int columns = pager_get_columns();
 
 	pmu = NULL;
 	len = 0;
Signature · 1 line
1.9.3
author
#8 lore raw

PATCH 8/10 perf, tools: Add a new pmu interface to iterate over all events

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

With calling a callback. To be used in test code added in the next patch.

---
 tools/perf/util/pmu.c | 18 ++++++++++++++++++
 tools/perf/util/pmu.h |  2 ++
 2 files changed, 20 insertions(+)
tools/perf/util/pmu.c +18 -0
index 8714f9a..397e400 100644
@@ -869,3 +869,21 @@ bool pmu_have_event(const char *pname, const char *name)
 	}
 	return false;
 }
+
+int pmu_iterate_events(int (*func)(const char *pmu, const char *name))
+{
+	int ret = 0;
+	struct perf_pmu *pmu;
+	struct perf_pmu_alias *alias;
+
+	perf_pmu__find("cpu"); /* Load PMUs */
+	pmu = NULL;
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+		list_for_each_entry(alias, &pmu->aliases, list) {
+			ret = func(pmu->name, alias->name);
+			if (ret != 0)
+				break;
+		}
+	}
+	return ret;
+}
tools/perf/util/pmu.h +2 -0
index 583d21e..87a1da4 100644
@@ -47,5 +47,7 @@ bool pmu_have_event(const char *pname, const char *name);
 
 int perf_pmu__test(void);
 
+int pmu_iterate_events(int (*func)(const char *, const char *name));
+
 extern const char *json_file;
 #endif /* __PMU_H */
Signature · 1 line
1.9.3
author
#9 lore raw

PATCH 9/10 perf, tools, test: Add test case for alias and JSON parsing

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

Add a simple test case to perf test that parses all the available events, including json events.

This needs adding an all event iterator to pmu.c

v2: Rename identifiers
v3: Only iterate cpu pmu to avoid bogus errors.
Move pmu iterator to extra patch
v4: Include aliases.c again
v5: Include util/debug.h

---
 tools/perf/Makefile.perf        |  1 +
 tools/perf/tests/aliases.c      | 59 +++++++++++++++++++++++++++++++++++++++++
 tools/perf/tests/builtin-test.c |  4 +++
 tools/perf/tests/tests.h        |  1 +
 4 files changed, 65 insertions(+)
 create mode 100644 tools/perf/tests/aliases.c
tools/perf/Makefile.perf +1 -0
index f9cce8e..664c538 100644
@@ -422,6 +422,7 @@ endif
 LIB_OBJS += $(OUTPUT)tests/code-reading.o
 LIB_OBJS += $(OUTPUT)tests/sample-parsing.o
 LIB_OBJS += $(OUTPUT)tests/parse-no-sample-id-all.o
+LIB_OBJS += $(OUTPUT)tests/aliases.o
 ifndef NO_DWARF_UNWIND
 ifeq ($(ARCH),$(filter $(ARCH),x86 arm))
 LIB_OBJS += $(OUTPUT)tests/dwarf-unwind.o
tools/perf/tests/aliases.c new file +59 -0

59 lines not on this page · raw message

tools/perf/tests/builtin-test.c +4 -0
index 6f8b01b..bb37ac2 100644
@@ -154,6 +154,10 @@ static struct test {
 		.func = test__hists_cumulate,
 	},
 	{
+		.desc = "Test parsing JSON aliases",
+		.func = test__aliases,
+	},
+	{
 		.func = NULL,
 	},
 };
tools/perf/tests/tests.h +1 -0
index ed64790..ab92ad9 100644
@@ -48,6 +48,7 @@ int test__mmap_thread_lookup(void);
 int test__thread_mg_share(void);
 int test__hists_output(void);
 int test__hists_cumulate(void);
+int test__aliases(void);
 
 #if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
Signature · 1 line
1.9.3
author
#10 lore raw

PATCH 10/10 perf, tools: Add a --no-desc flag to perf list

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

Add a --no-desc flag to perf list to not print the event descriptions that were earlier added for JSON events. This may be useful to get a less crowded listing.

It's still default to print descriptions as that is the more useful default for most users.

Before:

% perf list
...
baclears.any [Counts the total number when the front end is
resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end]
br_inst_exec.all_branches [Speculative and retired branches]

After:

% perf list --no-desc
...
baclears.any [Kernel PMU event]
br_inst_exec.all_branches [Kernel PMU event]

v2: Rename --quiet to --no-desc. Add option to man page.

---
 tools/perf/Documentation/perf-list.txt |  5 ++++-
 tools/perf/builtin-list.c              | 14 +++++++++-----
 tools/perf/util/parse-events.c         |  4 ++--
 tools/perf/util/parse-events.h         |  2 +-
 tools/perf/util/pmu.c                  |  4 ++--
 tools/perf/util/pmu.h                  |  2 +-
 6 files changed, 19 insertions(+), 12 deletions(-)
tools/perf/Documentation/perf-list.txt +4 -1
index da03992..3e56fc1 100644
@@ -8,7 +8,7 @@ perf-list - List all symbolic event types
 SYNOPSIS
 --------
 [verse]
-'perf list' [hw|sw|cache|tracepoint|pmu|event_glob]
+'perf list' [--no-desc] [hw|sw|cache|tracepoint|pmu|event_glob]
 
 DESCRIPTION
 -----------
@@ -23,6 +23,9 @@ automatically downloaded with perf download.
 The JSON event file can be also specified with the EVENTMAP environment
 variable.
 
+--no-desc::
+Don't print descriptions.
+
 
 [[EVENT_MODIFIERS]] EVENT MODIFIERS
 ---------------
tools/perf/builtin-list.c +9 -5
index 086c96f..68752a1 100644
@@ -16,16 +16,20 @@
 #include "util/pmu.h"
 #include "util/parse-options.h"
 
+static bool desc_flag = true;
+
 int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	int i;
 	const struct option list_options[] = {
 		OPT_STRING(0, "events-file", &json_file, "json file",
 			   "Read event json file"),
+		OPT_BOOLEAN('d', "desc", &desc_flag,
+			    "Print extra event descriptions. --no-desc to not print."),
 		OPT_END()
 	};
 	const char * const list_usage[] = {
-		"perf list [hw|sw|cache|tracepoint|pmu|event_glob]",
+		"perf list [--events-file FILE] [--no-desc] [hw|sw|cache|tracepoint|pmu|event_glob]",
 		NULL
 	};
 
@@ -35,7 +39,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 	setup_pager();
 
 	if (argc == 0) {
-		print_events(NULL, false);
+		print_events(NULL, false, !desc_flag);
 		return 0;
 	}
 
@@ -54,15 +58,15 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 			 strcmp(argv[i], "hwcache") == 0)
 			print_hwcache_events(NULL, false);
 		else if (strcmp(argv[i], "pmu") == 0)
-			print_pmu_events(NULL, false);
+			print_pmu_events(NULL, false, !desc_flag);
 		else if (strcmp(argv[i], "--raw-dump") == 0)
-			print_events(NULL, true);
+			print_events(NULL, true, !desc_flag);
 		else {
 			char *sep = strchr(argv[i], ':'), *s;
 			int sep_idx;
 
 			if (sep == NULL) {
-				print_events(argv[i], false);
+				print_events(argv[i], false, !desc_flag);
 				continue;
 			}
 			sep_idx = sep - argv[i];
tools/perf/util/parse-events.c +2 -2
index 1e15df1..e2badf3 100644
@@ -1231,7 +1231,7 @@ static void print_symbol_events(const char *event_glob, unsigned type,
 /*
  * Print the help text for the event symbols:
  */
-void print_events(const char *event_glob, bool name_only)
+void print_events(const char *event_glob, bool name_only, bool quiet)
 {
 	if (!name_only) {
 		printf("\n");
@@ -1246,7 +1246,7 @@ void print_events(const char *event_glob, bool name_only)
 
 	print_hwcache_events(event_glob, name_only);
 
-	print_pmu_events(event_glob, name_only);
+	print_pmu_events(event_glob, name_only, quiet);
 
 	if (event_glob != NULL)
 		return;
tools/perf/util/parse-events.h +1 -1
index df094b4..f3ef0dc 100644
@@ -100,7 +100,7 @@ void parse_events_update_lists(struct list_head *list_event,
 			       struct list_head *list_all);
 void parse_events_error(void *data, void *scanner, char const *msg);
 
-void print_events(const char *event_glob, bool name_only);
+void print_events(const char *event_glob, bool name_only, bool quiet);
 void print_events_type(u8 type);
 void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 			     bool name_only);
tools/perf/util/pmu.c +2 -2
index 397e400..b103932 100644
@@ -790,7 +790,7 @@ static void wordwrap(char *s, int start, int max, int corr)
 	}
 }
 
-void print_pmu_events(const char *event_glob, bool name_only)
+void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag)
 {
 	struct perf_pmu *pmu;
 	struct perf_pmu_alias *alias;
@@ -838,7 +838,7 @@ void print_pmu_events(const char *event_glob, bool name_only)
 			printf("%s ", aliases[j].name);
 			continue;
 		}
-		if (aliases[j].desc) {
+		if (aliases[j].desc && !quiet_flag) {
 			if (numdesc++ == 0 && printed)
 				printf("\n");
 			printf("  %-50s [", aliases[j].name);
tools/perf/util/pmu.h +1 -1
index 87a1da4..9b22d0f 100644
@@ -42,7 +42,7 @@ int perf_pmu__format_parse(char *dir, struct list_head *head);
 
 struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
 
-void print_pmu_events(const char *event_glob, bool name_only);
+void print_pmu_events(const char *event_glob, bool name_only, bool quiet);
 bool pmu_have_event(const char *pname, const char *name);
 
 int perf_pmu__test(void);
Signature · 1 line
1.9.3
#11 lore raw
In reply to Andi Kleen

Andi Kleen [[email protected]] wrote:

| Since it seems the download mechanism is controversal, 
| I removed the downloader for now until a suitable distribution
| method with kernel.org can be established. This is just
| the rest of the perf JSON event code that should hopefully
| not be controversal.

Ingo, Jiri, Andi,

Can we get this patchset merged please ? It is a step forward in eliminating raw event codes right ?

We added hundreds of events to sysfs for Power7. We don't want to do the same for Power8 because this JSON file solution is clearly better.

But we currently have a regression in functionality from Power7 to Power8 :-(

Even if 'perf download' is left out this patchset is still useful IMHO. Users (specially those who currently struggle with raw codes, are highly qualified and) could wget the JSON files as and when needed.

Being able to install the JSON files and download updates is a big plus, but is something thse users can live without for now.

Sukadev

#12 lore raw
Quoted 20 lines · Sukadev Bhattiprolu

Andi Kleen [[email protected]] wrote:

| Since it seems the download mechanism is controversal, 
| I removed the downloader for now until a suitable distribution
| method with kernel.org can be established. This is just
| the rest of the perf JSON event code that should hopefully
| not be controversal.

Ingo, Jiri, Andi,

Can we get this patchset merged please ? It is a step forward in eliminating raw event codes right ?

We added hundreds of events to sysfs for Power7. We don't want to do the same for Power8 because this JSON file solution is clearly better.

But we currently have a regression in functionality from Power7 to Power8 :-(

Quoted 8 lines

Even if 'perf download' is left out this patchset is still useful IMHO. Users (specially those who currently struggle with raw codes, are highly qualified and) could wget the JSON files as and when needed.

Being able to install the JSON files and download updates is a big plus, but is something thse users can live without for now.

hi,
I talked to Andi about this on LinuxCon and he said he works on that.. his current struggle was to get the ftp space IIRC

not sure whats the current status now, but I had the feeling it wont take long..

jirka