[PATCH 00/23] perf tools: Several memory events updates

[PATCH 00/23] perf tools: Several memory events updates

[Jiri Olsa]

hi,
this is generic part of the c2c patchset. It contains
several enhancements for perf mem and script commands:

  - display memory events properties in perf script
  - perf mem DATALA events support
  - few other assorted fixes/options

Also available in here:
  git://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf.git
  perf/mem

thanks,
jirka


---
Jiri Olsa (23):
      perf record: Add --all-user/--all-kernel options
      perf tools: Make cl_address global
      perf tools: Introduce cl_offset function
      perf tools: Add monitored events array
      perf mem: Add -e record option
      perf mem: Check for memory events support
      perf mem: Introduce perf_mem_events__name function
      perf mem: Add -l/--ldlat option
      perf mem: Add -u/-k options
      perf x86 intel: Add DATALA events into sysfs
      perf mem: Add Intel DATALA memory events
      perf tools: Use ARRAY_SIZE in mem sort display functions
      perf tools: Introduce perf_mem__tlb_scnprintf function
      perf tools: Introduce perf_mem__lvl_scnprintf function
      perf tools: Introduce perf_mem__snp_scnprintf function
      perf tools: Introduce perf_mem__lck_scnprintf function
      perf tools: Change perf_mem__tlb_scnprintf to return nb of displayed bytes
      perf tools: Change perf_mem__lvl_scnprintf to return nb of displayed bytes
      perf tools: Change perf_mem__snp_scnprintf to return nb of displayed bytes
      perf tools: Change perf_mem__lck_scnprintf to return nb of displayed bytes
      perf script: Add data_src and weight column definitions
      perf script: Display addr/data_src/weight columns for raw events
      perf script: Display data_src values

 arch/x86/kernel/cpu/perf_event_intel.c   |  39 +++++++++++++
 tools/perf/Documentation/perf-record.txt |   6 ++
 tools/perf/builtin-mem.c                 |  96 +++++++++++++++++++++++++++---
 tools/perf/builtin-record.c              |   4 ++
 tools/perf/builtin-script.c              |  41 ++++++++++++-
 tools/perf/perf.h                        |   2 +
 tools/perf/util/Build                    |   1 +
 tools/perf/util/evsel.c                  |  10 ++++
 tools/perf/util/mem-events.c             | 289 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/mem-events.h             |  56 ++++++++++++++++++
 tools/perf/util/sort.c                   | 148 ++--------------------------------------------
 tools/perf/util/sort.h                   |  11 ++++
 12 files changed, 551 insertions(+), 152 deletions(-)
 create mode 100644 tools/perf/util/mem-events.c
 create mode 100644 tools/perf/util/mem-events.h

[PATCH 01/23] perf record: Add --all-user/--all-kernel options

[Jiri Olsa]

Allow user to easily switch all events to user or
kernel space with simple --all-user or --all-kernel
options.

This will be handy within perf mem/c2c wrappers to
switch easily monitoring modes.

Link: http://lkml.kernel.org/n/tip-hdd2u0y1o8cwfpplrpzc1iqd@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/Documentation/perf-record.txt |  6 ++++++
 tools/perf/builtin-record.c              |  4 ++++
 tools/perf/perf.h                        |  2 ++
 tools/perf/util/evsel.c                  | 10 ++++++++++
 4 files changed, 22 insertions(+)

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index fbceb631387c..19aa17532a16 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -341,6 +341,12 @@ Specify vmlinux path which has debuginfo.
 --buildid-all::
 Record build-id of all DSOs regardless whether it's actually hit or not.
 
+--all-kernel::
+Configure all used events to run in kernel space.
+
+--all-user::
+Configure all used events to run in user space.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index caa8235ed027..b64f31a4c993 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1151,6 +1151,10 @@ struct option __record_options[] = {
 			"per thread proc mmap processing timeout in ms"),
 	OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events,
 		    "Record context switch events"),
+	OPT_BOOLEAN(0, "all-kernel", &record.opts.all_kernel,
+		    "Configure all used events to run in kernel space."),
+	OPT_BOOLEAN(0, "all-user", &record.opts.all_user,
+		    "Configure all used events to run in user space."),
 	OPT_STRING(0, "clang-path", &llvm_param.clang_path, "clang path",
 		   "clang binary to use for compiling BPF scriptlets"),
 	OPT_STRING(0, "clang-opt", &llvm_param.clang_opt, "clang options",
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 90129accffbe..5381a01c0610 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -58,6 +58,8 @@ struct record_opts {
 	bool	     full_auxtrace;
 	bool	     auxtrace_snapshot_mode;
 	bool	     record_switch_events;
+	bool	     all_kernel;
+	bool	     all_user;
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int auxtrace_mmap_pages;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 467808680ee4..6ae20d0056de 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -898,6 +898,16 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	if (evsel->precise_max)
 		perf_event_attr__set_max_precise_ip(attr);
 
+	if (opts->all_user) {
+		attr->exclude_kernel = 1;
+		attr->exclude_user   = 0;
+	}
+
+	if (opts->all_kernel) {
+		attr->exclude_kernel = 0;
+		attr->exclude_user   = 1;
+	}
+
 	/*
 	 * Apply event specific term settings,
 	 * it overloads any global configuration.
-- 
2.4.3

[PATCH 02/23] perf tools: Make cl_address global

[Jiri Olsa]

It'll be used in following patches.

Link: http://lkml.kernel.org/n/tip-up22drulx98h0nskjtpngr5s@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/util/sort.c | 6 ------
 tools/perf/util/sort.h | 5 +++++
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index de715756f281..3305149326bb 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1020,12 +1020,6 @@ static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
-static inline  u64 cl_address(u64 address)
-{
-	/* return the cacheline of the address */
-	return (address & ~(cacheline_size - 1));
-}
-
 static int64_t
 sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right)
 {
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 89a1273fd2da..46f159f9d947 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -162,6 +162,11 @@ static inline float hist_entry__get_percent_limit(struct hist_entry *he)
 	return period * 100.0 / total_period;
 }
 
+static inline u64 cl_address(u64 address)
+{
+	/* return the cacheline of the address */
+	return (address & ~(cacheline_size - 1));
+}
 
 enum sort_mode {
 	SORT_MODE__NORMAL,
-- 
2.4.3

[PATCH 03/23] perf tools: Introduce cl_offset function

[Jiri Olsa]

It'll be used in following patches.

Link: http://lkml.kernel.org/n/tip-m7dfmhya60y30hzhboeaczqk@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/util/sort.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 46f159f9d947..5b9c6246de6d 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -168,6 +168,12 @@ static inline u64 cl_address(u64 address)
 	return (address & ~(cacheline_size - 1));
 }
 
+static inline u64 cl_offset(u64 address)
+{
+	/* return the cacheline of the address */
+	return (address & (cacheline_size - 1));
+}
+
 enum sort_mode {
 	SORT_MODE__NORMAL,
 	SORT_MODE__BRANCH,
-- 
2.4.3

[PATCH 04/23] perf tools: Add monitored events array

[Jiri Olsa]

It will ease up configuration of memory events
and addition of other memory events in following
patches.

Link: http://lkml.kernel.org/n/tip-5n4yyd6dlrjhpd9rmaa2sycs@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-mem.c     | 17 +++++++++--------
 tools/perf/util/Build        |  1 +
 tools/perf/util/mem-events.c | 10 ++++++++++
 tools/perf/util/mem-events.h | 20 ++++++++++++++++++++
 4 files changed, 40 insertions(+), 8 deletions(-)
 create mode 100644 tools/perf/util/mem-events.c
 create mode 100644 tools/perf/util/mem-events.h

diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 390170041696..36c56a4b778b 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -6,6 +6,7 @@
 #include "util/tool.h"
 #include "util/session.h"
 #include "util/data.h"
+#include "util/mem-events.h"
 
 #define MEM_OPERATION_LOAD	0x1
 #define MEM_OPERATION_STORE	0x2
@@ -34,20 +35,20 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 
 	rec_argv[i++] = "record";
 
-	if (mem->operation & MEM_OPERATION_LOAD)
+	if (mem->operation & MEM_OPERATION_LOAD) {
+		perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true;
 		rec_argv[i++] = "-W";
+	}
 
 	rec_argv[i++] = "-d";
 
-	if (mem->operation & MEM_OPERATION_LOAD) {
-		rec_argv[i++] = "-e";
-		rec_argv[i++] = "cpu/mem-loads/pp";
-	}
+	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+		if (!perf_mem_events[j].record)
+			continue;
 
-	if (mem->operation & MEM_OPERATION_STORE) {
 		rec_argv[i++] = "-e";
-		rec_argv[i++] = "cpu/mem-stores/pp";
-	}
+		rec_argv[i++] = perf_mem_events[j].name;
+	};
 
 	for (j = 1; j < argc; j++, i++)
 		rec_argv[i] = argv[j];
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index a34752d28488..df2b690970ac 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -82,6 +82,7 @@ libperf-y += parse-branch-options.o
 libperf-y += parse-regs-options.o
 libperf-y += term.o
 libperf-y += help-unknown-cmd.o
+libperf-y += mem-events.o
 
 libperf-$(CONFIG_LIBBPF) += bpf-loader.o
 libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
new file mode 100644
index 000000000000..c6ba0a19ec9a
--- /dev/null
+++ b/tools/perf/util/mem-events.c
@@ -0,0 +1,10 @@
+#include "mem-events.h"
+
+#define E(n) { .name = n }
+
+struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
+	E("cpu/mem-loads,ldlat=30/P"),
+	E("cpu/mem-stores/P"),
+};
+
+#undef E
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
new file mode 100644
index 000000000000..ee5fde222389
--- /dev/null
+++ b/tools/perf/util/mem-events.h
@@ -0,0 +1,20 @@
+#ifndef __PERF_MEM_EVENTS_H
+#define __PERF_MEM_EVENTS_H
+
+#include <stdbool.h>
+
+struct perf_mem_event {
+	bool		record;
+	const char	*name;
+};
+
+enum {
+	PERF_MEM_EVENTS__LOAD,
+	PERF_MEM_EVENTS__STORE,
+	PERF_MEM_EVENTS__MAX,
+};
+
+extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
+
+#endif /* __PERF_MEM_EVENTS_H */
+
-- 
2.4.3

[PATCH 05/23] perf mem: Add -e record option

[Jiri Olsa]

Adding -e option for perf mem record command,
to be able to specify memory event directly.

Get list of available events:

  $ perf mem record -e list
  ldlat-loads
  ldlat-stores

Monitor ldlat-loads:
  $ perf mem record -e ldlat-loads true

Link: http://lkml.kernel.org/n/tip-x5famenpxjfmhojzo95sf26s@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-mem.c     | 63 +++++++++++++++++++++++++++++++++++++++++---
 tools/perf/util/mem-events.c | 47 ++++++++++++++++++++++++++++++---
 tools/perf/util/mem-events.h |  3 +++
 3 files changed, 106 insertions(+), 7 deletions(-)

diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 36c56a4b778b..b3f8a89ede40 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -7,6 +7,7 @@
 #include "util/session.h"
 #include "util/data.h"
 #include "util/mem-events.h"
+#include "util/debug.h"
 
 #define MEM_OPERATION_LOAD	0x1
 #define MEM_OPERATION_STORE	0x2
@@ -22,11 +23,55 @@ struct perf_mem {
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
+static int parse_record_events(const struct option *opt,
+			       const char *str, int unset __maybe_unused)
+{
+	struct perf_mem *mem = *(struct perf_mem **)opt->value;
+	int j;
+
+	if (strcmp(str, "list")) {
+		if (!perf_mem_events__parse(str)) {
+			mem->operation = 0;
+			return 0;
+		}
+		exit(-1);
+	}
+
+	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+		struct perf_mem_event *e = &perf_mem_events[j];
+
+		fprintf(stderr, "%-20s%s",
+			e->tag, verbose ? "" : "\n");
+		if (verbose)
+			fprintf(stderr, " [%s]\n", e->name);
+	}
+	exit(0);
+}
+
+static const char * const __usage[] = {
+	"perf mem record [<options>] [<command>]",
+	"perf mem record [<options>] -- <command> [<options>]",
+	NULL
+};
+
+static const char * const *record_mem_usage = __usage;
+
 static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 {
 	int rec_argc, i = 0, j;
 	const char **rec_argv;
 	int ret;
+	struct option options[] = {
+	OPT_CALLBACK('e', "event", &mem, "event",
+		     "event selector. use 'perf mem record -e list' to list available events",
+		     parse_record_events),
+	OPT_INCR('v', "verbose", &verbose,
+		 "be more verbose (show counter open errors, etc)"),
+	OPT_END()
+	};
+
+	argc = parse_options(argc, argv, options, record_mem_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
 
 	rec_argc = argc + 7; /* max number of arguments */
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
@@ -35,10 +80,11 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 
 	rec_argv[i++] = "record";
 
-	if (mem->operation & MEM_OPERATION_LOAD) {
+	if (mem->operation & MEM_OPERATION_LOAD)
 		perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true;
+
+	if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record)
 		rec_argv[i++] = "-W";
-	}
 
 	rec_argv[i++] = "-d";
 
@@ -50,9 +96,19 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 		rec_argv[i++] = perf_mem_events[j].name;
 	};
 
-	for (j = 1; j < argc; j++, i++)
+	for (j = 0; j < argc; j++, i++)
 		rec_argv[i] = argv[j];
 
+	if (verbose > 0) {
+		pr_debug("calling: record ");
+
+		while (rec_argv[j]) {
+			pr_debug("%s ", rec_argv[j]);
+			j++;
+		}
+		pr_debug("\n");
+	}
+
 	ret = cmd_record(i, rec_argv, NULL);
 	free(rec_argv);
 	return ret;
@@ -299,7 +355,6 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
 		NULL
 	};
 
-
 	argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands,
 					mem_usage, PARSE_OPT_STOP_AT_NON_OPTION);
 
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index c6ba0a19ec9a..b1507c04b257 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -1,10 +1,51 @@
+#include <stddef.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
 #include "mem-events.h"
+#include "debug.h"
 
-#define E(n) { .name = n }
+#define E(t, n) { .tag = t, .name = n }
 
 struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
-	E("cpu/mem-loads,ldlat=30/P"),
-	E("cpu/mem-stores/P"),
+	E("ldlat-loads",	"cpu/mem-loads,ldlat=30/P"),
+	E("ldlat-stores",	"cpu/mem-stores/P"),
 };
 
 #undef E
+
+int perf_mem_events__parse(const char *str)
+{
+	char *tok, *saveptr = NULL;
+	bool found = false;
+	char *buf;
+	int j;
+
+	/* We need buffer that we know we can write to. */
+	buf = malloc(strlen(str) + 1);
+	if (!buf)
+		return -ENOMEM;
+
+	strcpy(buf, str);
+
+	tok = strtok_r((char *)buf, ",", &saveptr);
+
+	while (tok) {
+		for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+			struct perf_mem_event *e = &perf_mem_events[j];
+
+			if (strstr(e->tag, tok))
+				e->record = found = true;
+		}
+
+		tok = strtok_r(NULL, ",", &saveptr);
+	}
+
+	free(buf);
+
+	if (found)
+		return 0;
+
+	pr_err("failed: event '%s' not found, use '-e list' to get list of available events\n", str);
+	return -1;
+}
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index ee5fde222389..0b5247468462 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -5,6 +5,7 @@
 
 struct perf_mem_event {
 	bool		record;
+	const char	*tag;
 	const char	*name;
 };
 
@@ -16,5 +17,7 @@ enum {
 
 extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
 
+int perf_mem_events__parse(const char *str);
+
 #endif /* __PERF_MEM_EVENTS_H */
 
-- 
2.4.3

[PATCH 06/23] perf mem: Check for memory events support

[Jiri Olsa]

Check if current kernel support available memory events
and display the status within -e  list option:

  $ perf mem record -e list
  [ok] ldlat-loads
  [ok] ldlat-stores

Link: http://lkml.kernel.org/n/tip-r8smhxjfe69q67jwt7mzs0e9@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-mem.c     | 14 +++++++++++++-
 tools/perf/util/mem-events.c | 35 ++++++++++++++++++++++++++++++++---
 tools/perf/util/mem-events.h |  3 +++
 3 files changed, 48 insertions(+), 4 deletions(-)

diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index b3f8a89ede40..e64e0aa7ba0e 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -40,7 +40,8 @@ static int parse_record_events(const struct option *opt,
 	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
 		struct perf_mem_event *e = &perf_mem_events[j];
 
-		fprintf(stderr, "%-20s%s",
+		fprintf(stderr, "%s%-20s%s",
+			e->supported ? "[ok] " : "     ",
 			e->tag, verbose ? "" : "\n");
 		if (verbose)
 			fprintf(stderr, " [%s]\n", e->name);
@@ -92,6 +93,12 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 		if (!perf_mem_events[j].record)
 			continue;
 
+		if (!perf_mem_events[j].supported) {
+			pr_err("failed: event '%s' not supported\n",
+			       perf_mem_events[j].name);
+			return -1;
+		}
+
 		rec_argv[i++] = "-e";
 		rec_argv[i++] = perf_mem_events[j].name;
 	};
@@ -355,6 +362,11 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
 		NULL
 	};
 
+	if (perf_mem_events__init()) {
+		pr_err("failed: memory events not supported\n");
+		return -1;
+	}
+
 	argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands,
 					mem_usage, PARSE_OPT_STOP_AT_NON_OPTION);
 
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index b1507c04b257..e21853fe1312 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -2,15 +2,20 @@
 #include <stdlib.h>
 #include <string.h>
 #include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <api/fs/fs.h>
 #include "mem-events.h"
 #include "debug.h"
 
-#define E(t, n) { .tag = t, .name = n }
+#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
 
 struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
-	E("ldlat-loads",	"cpu/mem-loads,ldlat=30/P"),
-	E("ldlat-stores",	"cpu/mem-stores/P"),
+	E("ldlat-loads",	"cpu/mem-loads,ldlat=30/P",	"mem-loads"),
+	E("ldlat-stores",	"cpu/mem-stores/P",		"mem-stores"),
 };
+#undef E
 
 #undef E
 
@@ -49,3 +54,27 @@ int perf_mem_events__parse(const char *str)
 	pr_err("failed: event '%s' not found, use '-e list' to get list of available events\n", str);
 	return -1;
 }
+
+int perf_mem_events__init(void)
+{
+	const char *mnt = sysfs__mount();
+	bool found = false;
+	int j;
+
+	if (!mnt)
+		return -ENOENT;
+
+	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+		char path[PATH_MAX];
+		struct perf_mem_event *e = &perf_mem_events[j];
+		struct stat st;
+
+		scnprintf(path, PATH_MAX, "%s/devices/cpu/events/%s",
+			  mnt, e->sysfs_name);
+
+		if (!stat(path, &st))
+			e->supported = found = true;
+	}
+
+	return found ? 0 : -ENOENT;
+}
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 0b5247468462..b9a786346c03 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -5,8 +5,10 @@
 
 struct perf_mem_event {
 	bool		record;
+	bool		supported;
 	const char	*tag;
 	const char	*name;
+	const char	*sysfs_name;
 };
 
 enum {
@@ -18,6 +20,7 @@ enum {
 extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
 
 int perf_mem_events__parse(const char *str);
+int perf_mem_events__init(void);
 
 #endif /* __PERF_MEM_EVENTS_H */
 
-- 
2.4.3

[PATCH 07/23] perf mem: Introduce perf_mem_events__name function

[Jiri Olsa]

Wrap perf_mem_events[].name into perf_mem_events__name
function so we could alter the events name if needed.

This will be handy when changing latency settings for
loads event in following patch.

Link: http://lkml.kernel.org/n/tip-76wibzfbjamxfu7vapizsszj@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-mem.c     | 4 ++--
 tools/perf/util/mem-events.c | 5 +++++
 tools/perf/util/mem-events.h | 1 +
 3 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index e64e0aa7ba0e..26b2f9e0b153 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -95,12 +95,12 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 
 		if (!perf_mem_events[j].supported) {
 			pr_err("failed: event '%s' not supported\n",
-			       perf_mem_events[j].name);
+			       perf_mem_events__name(j));
 			return -1;
 		}
 
 		rec_argv[i++] = "-e";
-		rec_argv[i++] = perf_mem_events[j].name;
+		rec_argv[i++] = perf_mem_events__name(j);
 	};
 
 	for (j = 0; j < argc; j++, i++)
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index e21853fe1312..0f62e930de13 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -19,6 +19,11 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
 
 #undef E
 
+char *perf_mem_events__name(int i)
+{
+	return (char *) perf_mem_events[i].name;
+}
+
 int perf_mem_events__parse(const char *str)
 {
 	char *tok, *saveptr = NULL;
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index b9a786346c03..23e3239dfa34 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -22,5 +22,6 @@ extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
 int perf_mem_events__parse(const char *str);
 int perf_mem_events__init(void);
 
+char *perf_mem_events__name(int i);
 #endif /* __PERF_MEM_EVENTS_H */
 
-- 
2.4.3

[PATCH 08/23] perf mem: Add -l/--ldlat option

[Jiri Olsa]

Adding -l/--ldlat option to specify desired latency
for loads event.

Specify 50 as loads event latency:

  $ perf mem record -e ldlat-loads -v -l 50 true
  calling: record -W -d -e cpu/mem-loads,ldlat=50/P true

Link: http://lkml.kernel.org/n/tip-ec2m0cvivkfs8uhtiv411hfc@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-mem.c     |  1 +
 tools/perf/util/mem-events.c | 17 ++++++++++++++++-
 tools/perf/util/mem-events.h |  1 +
 3 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 26b2f9e0b153..94243429bb6e 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -66,6 +66,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	OPT_CALLBACK('e', "event", &mem, "event",
 		     "event selector. use 'perf mem record -e list' to list available events",
 		     parse_record_events),
+	OPT_UINTEGER('l', "ldlat", &perf_mem_events__loads_ldlat, "mem-loads latency"),
 	OPT_INCR('v', "verbose", &verbose,
 		 "be more verbose (show counter open errors, etc)"),
 	OPT_END()
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 0f62e930de13..3772a3a8a6ee 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -9,18 +9,33 @@
 #include "mem-events.h"
 #include "debug.h"
 
+unsigned int perf_mem_events__loads_ldlat = 30;
+
 #define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
 
 struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
-	E("ldlat-loads",	"cpu/mem-loads,ldlat=30/P",	"mem-loads"),
+	E("ldlat-loads",	"cpu/mem-loads,ldlat=%u/P",	"mem-loads"),
 	E("ldlat-stores",	"cpu/mem-stores/P",		"mem-stores"),
 };
 #undef E
 
 #undef E
 
+static char mem_loads_name[100];
+static bool mem_loads_name__init;
+
 char *perf_mem_events__name(int i)
 {
+	if (i == PERF_MEM_EVENTS__LOAD) {
+		if (!mem_loads_name__init) {
+			mem_loads_name__init = true;
+			scnprintf(mem_loads_name, sizeof(mem_loads_name),
+				  perf_mem_events[i].name,
+				  perf_mem_events__loads_ldlat);
+		}
+		return mem_loads_name;
+	}
+
 	return (char *) perf_mem_events[i].name;
 }
 
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 23e3239dfa34..d690907f7e50 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -18,6 +18,7 @@ enum {
 };
 
 extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
+extern unsigned int perf_mem_events__loads_ldlat;
 
 int perf_mem_events__parse(const char *str);
 int perf_mem_events__init(void);
-- 
2.4.3

[PATCH 09/23] perf mem: Add -u/-k options

[Jiri Olsa]

Add -u/-k (--all-user/--all-kernel) options to use
the perf record --all-user/--all-kernel options.

Link: http://lkml.kernel.org/n/tip-adxn5c48oe0gmjrjmq6we27q@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-mem.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 94243429bb6e..cb4aa83162a6 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -62,6 +62,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	int rec_argc, i = 0, j;
 	const char **rec_argv;
 	int ret;
+	bool all_user = false, all_kernel = false;
 	struct option options[] = {
 	OPT_CALLBACK('e', "event", &mem, "event",
 		     "event selector. use 'perf mem record -e list' to list available events",
@@ -69,13 +70,15 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	OPT_UINTEGER('l', "ldlat", &perf_mem_events__loads_ldlat, "mem-loads latency"),
 	OPT_INCR('v', "verbose", &verbose,
 		 "be more verbose (show counter open errors, etc)"),
+	OPT_BOOLEAN('u', "--all-user", &all_user, "collect only user level data"),
+	OPT_BOOLEAN('k', "--all-kernel", &all_kernel, "collect only kernel level data"),
 	OPT_END()
 	};
 
 	argc = parse_options(argc, argv, options, record_mem_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 
-	rec_argc = argc + 7; /* max number of arguments */
+	rec_argc = argc + 9; /* max number of arguments */
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 	if (!rec_argv)
 		return -1;
@@ -104,6 +107,12 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 		rec_argv[i++] = perf_mem_events__name(j);
 	};
 
+	if (all_user)
+		rec_argv[i++] = "--all-user";
+
+	if (all_kernel)
+		rec_argv[i++] = "--all-kernel";
+
 	for (j = 0; j < argc; j++, i++)
 		rec_argv[i] = argv[j];
 
-- 
2.4.3

[PATCH 10/23] perf x86 intel: Add DATALA events into sysfs

[Jiri Olsa]

Adding DATALA events into Haaswell events sysfs
directory, so it's easier to use them.

Adding all DATALA events as specified by Intel SDM
manual 18.10.3 PEBS Data Address Profiling.

Link: http://lkml.kernel.org/n/tip-dvpk5ys80v41oh5xgqvloviw@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 arch/x86/kernel/cpu/perf_event_intel.c | 39 ++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index fed2ab1f1065..aadccb782e78 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -3253,6 +3253,26 @@ static __init void intel_ht_bug(void)
 EVENT_ATTR_STR(mem-loads,	mem_ld_hsw,	"event=0xcd,umask=0x1,ldlat=3");
 EVENT_ATTR_STR(mem-stores,	mem_st_hsw,	"event=0xd0,umask=0x82")
 
+EVENT_ATTR_STR(mem-stlb-miss-loads,	hsw_stlb_miss_loads,	"event=0xd0,umask=0x11");
+EVENT_ATTR_STR(mem-stlb-miss-stores,	hsw_stlb_miss_stores,	"event=0xd0,umask=0x12");
+EVENT_ATTR_STR(mem-lock-loads,		hsw_lock_loads,		"event=0xd0,umask=0x21");
+EVENT_ATTR_STR(mem-split-loads,		hsw_split_loads,	"event=0xd0,umask=0x41");
+EVENT_ATTR_STR(mem-split-stores,	hsw_split_stores,	"event=0xd0,umask=0x42");
+EVENT_ATTR_STR(mem-all-loads,		hsw_all_loads,		"event=0xd0,umask=0x81");
+EVENT_ATTR_STR(mem-all-stores,		hsw_all_stores,		"event=0xd0,umask=0x82");
+EVENT_ATTR_STR(mem-load-l1-hit,		hsw_load_l1_hit,	"event=0xd1,umask=0x01");
+EVENT_ATTR_STR(mem-load-l2-hit,		hsw_load_l2_hit,	"event=0xd1,umask=0x02");
+EVENT_ATTR_STR(mem-load-l3-hit,		hsw_load_l3_hit,	"event=0xd1,umask=0x04");
+EVENT_ATTR_STR(mem-load-l1-miss,	hsw_load_l1_miss,	"event=0xd1,umask=0x08");
+EVENT_ATTR_STR(mem-load-l2-miss,	hsw_load_l2_miss,	"event=0xd1,umask=0x10");
+EVENT_ATTR_STR(mem-load-l3-miss,	hsw_load_l3_miss,	"event=0xd1,umask=0x20");
+EVENT_ATTR_STR(mem-load-hit-lfb,	hsw_load_hit_lfb,	"event=0xd1,umask=0x40");
+EVENT_ATTR_STR(mem-snp-miss,		hsw_snp_miss,		"event=0xd2,umask=0x01");
+EVENT_ATTR_STR(mem-snp-hit,		hsw_snp_hit,		"event=0xd2,umask=0x02");
+EVENT_ATTR_STR(mem-snp-hitm,		hsw_snp_hitm,		"event=0xd2,umask=0x04");
+EVENT_ATTR_STR(mem-snp-none,		hsw_snp_none,		"event=0xd2,umask=0x08");
+EVENT_ATTR_STR(mem-local-dram,		hsw_local_dram,		"event=0xd3,umask=0x01");
+
 /* Haswell special events */
 EVENT_ATTR_STR(tx-start,	tx_start,	"event=0xc9,umask=0x1");
 EVENT_ATTR_STR(tx-commit,	tx_commit,	"event=0xc9,umask=0x2");
@@ -3282,6 +3302,25 @@ static struct attribute *hsw_events_attrs[] = {
 	EVENT_PTR(cycles_ct),
 	EVENT_PTR(mem_ld_hsw),
 	EVENT_PTR(mem_st_hsw),
+	EVENT_PTR(hsw_stlb_miss_loads),
+	EVENT_PTR(hsw_stlb_miss_stores),
+	EVENT_PTR(hsw_lock_loads),
+	EVENT_PTR(hsw_split_loads),
+	EVENT_PTR(hsw_split_stores),
+	EVENT_PTR(hsw_all_loads),
+	EVENT_PTR(hsw_all_stores),
+	EVENT_PTR(hsw_load_l1_hit),
+	EVENT_PTR(hsw_load_l2_hit),
+	EVENT_PTR(hsw_load_l3_hit),
+	EVENT_PTR(hsw_load_l1_miss),
+	EVENT_PTR(hsw_load_l2_miss),
+	EVENT_PTR(hsw_load_l3_miss),
+	EVENT_PTR(hsw_load_hit_lfb),
+	EVENT_PTR(hsw_snp_miss),
+	EVENT_PTR(hsw_snp_hit),
+	EVENT_PTR(hsw_snp_hitm),
+	EVENT_PTR(hsw_snp_none),
+	EVENT_PTR(hsw_local_dram),
 	NULL
 };
 
-- 
2.4.3

[PATCH 11/23] perf mem: Add Intel DATALA memory events

[Jiri Olsa]

Adding Intel DATALA memory events into
perf mem record command:

  $ perf mem record -e list
  [ok] ldlat-loads
  [ok] ldlat-stores
       stlb-miss-loads
       stlb-miss-stores
       lock-loads
       split-loads
       split-stores
       all-loads
       all-stores
       l1-hit
       l2-hit
       l3-hit
       l1-miss
       l2-miss
       l3-miss
       lfb
       snp-miss
       snp-hit
       snp-hitm
       snp-none
       local-dram

All events from above lists are compiled in, but only
those with [ok] are supported by kernel/HW. You need
previous DATALA patch to support all of them.

Link: http://lkml.kernel.org/n/tip-cximteb8r1a6750wz8sgeajh@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/util/mem-events.c | 19 +++++++++++++++++++
 tools/perf/util/mem-events.h | 19 +++++++++++++++++++
 2 files changed, 38 insertions(+)

diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 3772a3a8a6ee..92d3bc9914e6 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -16,6 +16,25 @@ unsigned int perf_mem_events__loads_ldlat = 30;
 struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
 	E("ldlat-loads",	"cpu/mem-loads,ldlat=%u/P",	"mem-loads"),
 	E("ldlat-stores",	"cpu/mem-stores/P",		"mem-stores"),
+	E("stlb-miss-loads",	"cpu/mem-stlb-miss-loads/P",	"mem-stlb-miss-loads"),
+	E("stlb-miss-stores",	"cpu/mem-stlb-miss-stores/P",	"mem-stlb-miss-stores"),
+	E("lock-loads",		"cpu/mem-lock-loads/P",		"mem-lock-loads"),
+	E("split-loads",	"cpu/mem-split-loads/P",	"mem-split-loads"),
+	E("split-stores",	"cpu/mem-split-stores/P",	"mem-split-stores"),
+	E("all-loads",		"cpu/mem-all-loads/P",		"mem-all-loads"),
+	E("all-stores",		"cpu/mem-all-stores/P",		"mem-all-stores"),
+	E("l1-hit",		"cpu/mem-load-l1-hit/P",	"mem-load-l1-hit"),
+	E("l2-hit",		"cpu/mem-load-l2-hit/P",	"mem-load-l2-hit"),
+	E("l3-hit",		"cpu/mem-load-l3-hit/P",	"mem-load-l3-hit"),
+	E("l1-miss",		"cpu/mem-load-l1-miss/P",	"mem-load-l1-miss"),
+	E("l2-miss",		"cpu/mem-load-l2-miss/P",	"mem-load-l2-miss"),
+	E("l3-miss",		"cpu/mem-load-l3-miss/P",	"mem-load-l3-miss"),
+	E("lfb",		"cpu/mem-load-hit-lfb/P",	"mem-load-hit-lfb"),
+	E("snp-miss",		"cpu/mem-snp-miss/P",		"mem-snp-miss"),
+	E("snp-hit",		"cpu/mem-snp-hit/P",		"mem-snp-hit"),
+	E("snp-hitm",		"cpu/mem-snp-hitm/P",		"mem-snp-hitm"),
+	E("snp-none",		"cpu/mem-snp-none/P",		"mem-snp-none"),
+	E("local-dram",		"cpu/mem-local-dram/P",		"mem-local-dram"),
 };
 #undef E
 
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index d690907f7e50..4abf606b256b 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -14,6 +14,25 @@ struct perf_mem_event {
 enum {
 	PERF_MEM_EVENTS__LOAD,
 	PERF_MEM_EVENTS__STORE,
+	PERF_MEM_EVENTS__STLB_MISS_LOADS,
+	PERF_MEM_EVENTS__STLB_MISS_STORES,
+	PERF_MEM_EVENTS__LOCK_LOADS,
+	PERF_MEM_EVENTS__SPLIT_LOADS,
+	PERF_MEM_EVENTS__SPLIT_STORES,
+	PERF_MEM_EVENTS__ALL_LOADS,
+	PERF_MEM_EVENTS__ALL_STORES,
+	PERF_MEM_EVENTS__L1_HIT,
+	PERF_MEM_EVENTS__L2_HIT,
+	PERF_MEM_EVENTS__L3_HIT,
+	PERF_MEM_EVENTS__L1_MISS,
+	PERF_MEM_EVENTS__L2_MISS,
+	PERF_MEM_EVENTS__L3_MISS,
+	PERF_MEM_EVENTS__LFB,
+	PERF_MEM_EVENTS__SNP_MISS,
+	PERF_MEM_EVENTS__SNP_HIT,
+	PERF_MEM_EVENTS__SNP_HITM,
+	PERF_MEM_EVENTS__SNP_NONE,
+	PERF_MEM_EVENTS__LOCAL_DRAM,
 	PERF_MEM_EVENTS__MAX,
 };
 
-- 
2.4.3

[PATCH 12/23] perf tools: Use ARRAY_SIZE in mem sort display functions

[Jiri Olsa]

There's no need to define extra macros for that.

Link: http://lkml.kernel.org/n/tip-ib5fkxt3i5bp1pi9ym6etx8p@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/util/sort.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 3305149326bb..5cb3e13b8f2e 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -843,7 +843,6 @@ static const char * const tlb_access[] = {
 	"Walker",
 	"Fault",
 };
-#define NUM_TLB_ACCESS (sizeof(tlb_access)/sizeof(const char *))
 
 static int hist_entry__tlb_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
@@ -865,7 +864,7 @@ static int hist_entry__tlb_snprintf(struct hist_entry *he, char *bf,
 	/* already taken care of */
 	m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS);
 
-	for (i = 0; m && i < NUM_TLB_ACCESS; i++, m >>= 1) {
+	for (i = 0; m && i < ARRAY_SIZE(tlb_access); i++, m >>= 1) {
 		if (!(m & 0x1))
 			continue;
 		if (l) {
@@ -920,7 +919,6 @@ static const char * const mem_lvl[] = {
 	"I/O",
 	"Uncached",
 };
-#define NUM_MEM_LVL (sizeof(mem_lvl)/sizeof(const char *))
 
 static int hist_entry__lvl_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
@@ -942,7 +940,7 @@ static int hist_entry__lvl_snprintf(struct hist_entry *he, char *bf,
 	/* already taken care of */
 	m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
 
-	for (i = 0; m && i < NUM_MEM_LVL; i++, m >>= 1) {
+	for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
 		if (!(m & 0x1))
 			continue;
 		if (l) {
@@ -988,7 +986,6 @@ static const char * const snoop_access[] = {
 	"Hit",
 	"HitM",
 };
-#define NUM_SNOOP_ACCESS (sizeof(snoop_access)/sizeof(const char *))
 
 static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
@@ -1003,7 +1000,7 @@ static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
 	if (he->mem_info)
 		m = he->mem_info->data_src.mem_snoop;
 
-	for (i = 0; m && i < NUM_SNOOP_ACCESS; i++, m >>= 1) {
+	for (i = 0; m && i < ARRAY_SIZE(snoop_access); i++, m >>= 1) {
 		if (!(m & 0x1))
 			continue;
 		if (l) {
-- 
2.4.3

[PATCH 13/23] perf tools: Introduce perf_mem__tlb_scnprintf function

[Jiri Olsa]

Move meminfo's tlb display function into mem-events.c
object, so it could be reused later from script code.

Link: http://lkml.kernel.org/n/tip-kdsvxdm3ucwknyvkluwavydh@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/util/mem-events.c | 47 ++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/mem-events.h |  3 +++
 tools/perf/util/sort.c       | 44 ++---------------------------------------
 3 files changed, 52 insertions(+), 42 deletions(-)

diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 92d3bc9914e6..68f6f8e4922a 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -8,6 +8,7 @@
 #include <api/fs/fs.h>
 #include "mem-events.h"
 #include "debug.h"
+#include "symbol.h"
 
 unsigned int perf_mem_events__loads_ldlat = 30;
 
@@ -117,3 +118,49 @@ int perf_mem_events__init(void)
 
 	return found ? 0 : -ENOENT;
 }
+
+static const char * const tlb_access[] = {
+	"N/A",
+	"HIT",
+	"MISS",
+	"L1",
+	"L2",
+	"Walker",
+	"Fault",
+};
+
+void perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	size_t l = 0, i;
+	u64 m = PERF_MEM_TLB_NA;
+	u64 hit, miss;
+
+	sz -= 1; /* -1 for null termination */
+	out[0] = '\0';
+
+	if (mem_info)
+		m = mem_info->data_src.mem_dtlb;
+
+	hit = m & PERF_MEM_TLB_HIT;
+	miss = m & PERF_MEM_TLB_MISS;
+
+	/* already taken care of */
+	m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS);
+
+	for (i = 0; m && i < ARRAY_SIZE(tlb_access); i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		strncat(out, tlb_access[i], sz - l);
+		l += strlen(tlb_access[i]);
+	}
+	if (*out == '\0')
+		strcpy(out, "N/A");
+	if (hit)
+		strncat(out, " hit", sz - l);
+	if (miss)
+		strncat(out, " miss", sz - l);
+}
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 4abf606b256b..1af23966e3fc 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -43,5 +43,8 @@ int perf_mem_events__parse(const char *str);
 int perf_mem_events__init(void);
 
 char *perf_mem_events__name(int i);
+
+struct mem_info;
+void perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 #endif /* __PERF_MEM_EVENTS_H */
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 5cb3e13b8f2e..b7834a5a002d 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -6,6 +6,7 @@
 #include "evsel.h"
 #include "evlist.h"
 #include <traceevent/event-parse.h>
+#include "mem-events.h"
 
 regex_t		parent_regex;
 const char	default_parent_pattern[] = "^sys_|^do_page_fault";
@@ -834,53 +835,12 @@ sort__tlb_cmp(struct hist_entry *left, struct hist_entry *right)
 	return (int64_t)(data_src_r.mem_dtlb - data_src_l.mem_dtlb);
 }
 
-static const char * const tlb_access[] = {
-	"N/A",
-	"HIT",
-	"MISS",
-	"L1",
-	"L2",
-	"Walker",
-	"Fault",
-};
-
 static int hist_entry__tlb_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
 	char out[64];
-	size_t sz = sizeof(out) - 1; /* -1 for null termination */
-	size_t l = 0, i;
-	u64 m = PERF_MEM_TLB_NA;
-	u64 hit, miss;
-
-	out[0] = '\0';
-
-	if (he->mem_info)
-		m = he->mem_info->data_src.mem_dtlb;
-
-	hit = m & PERF_MEM_TLB_HIT;
-	miss = m & PERF_MEM_TLB_MISS;
-
-	/* already taken care of */
-	m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS);
-
-	for (i = 0; m && i < ARRAY_SIZE(tlb_access); i++, m >>= 1) {
-		if (!(m & 0x1))
-			continue;
-		if (l) {
-			strcat(out, " or ");
-			l += 4;
-		}
-		strncat(out, tlb_access[i], sz - l);
-		l += strlen(tlb_access[i]);
-	}
-	if (*out == '\0')
-		strcpy(out, "N/A");
-	if (hit)
-		strncat(out, " hit", sz - l);
-	if (miss)
-		strncat(out, " miss", sz - l);
 
+	perf_mem__tlb_scnprintf(out, sizeof(out), he->mem_info);
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
-- 
2.4.3

[PATCH 14/23] perf tools: Introduce perf_mem__lvl_scnprintf function

[Jiri Olsa]

Move meminfo's lvl display function into mem-events.c
object, so it could be reused later from script code.

Link: http://lkml.kernel.org/n/tip-ujrrar78msnlkbvrgujwc7z1@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/util/mem-events.c | 53 ++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/mem-events.h |  1 +
 tools/perf/util/sort.c       | 50 +----------------------------------------
 3 files changed, 55 insertions(+), 49 deletions(-)

diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 68f6f8e4922a..f291f93ac11d 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -164,3 +164,56 @@ void perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 	if (miss)
 		strncat(out, " miss", sz - l);
 }
+
+static const char * const mem_lvl[] = {
+	"N/A",
+	"HIT",
+	"MISS",
+	"L1",
+	"LFB",
+	"L2",
+	"L3",
+	"Local RAM",
+	"Remote RAM (1 hop)",
+	"Remote RAM (2 hops)",
+	"Remote Cache (1 hop)",
+	"Remote Cache (2 hops)",
+	"I/O",
+	"Uncached",
+};
+
+void perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	size_t i, l = 0;
+	u64 m =  PERF_MEM_LVL_NA;
+	u64 hit, miss;
+
+	if (mem_info)
+		m  = mem_info->data_src.mem_lvl;
+
+	sz -= 1; /* -1 for null termination */
+	out[0] = '\0';
+
+	hit = m & PERF_MEM_LVL_HIT;
+	miss = m & PERF_MEM_LVL_MISS;
+
+	/* already taken care of */
+	m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
+
+	for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		strncat(out, mem_lvl[i], sz - l);
+		l += strlen(mem_lvl[i]);
+	}
+	if (*out == '\0')
+		strcpy(out, "N/A");
+	if (hit)
+		strncat(out, " hit", sz - l);
+	if (miss)
+		strncat(out, " miss", sz - l);
+}
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 1af23966e3fc..fc6d94fc96e8 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -46,5 +46,6 @@ char *perf_mem_events__name(int i);
 
 struct mem_info;
 void perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+void perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 #endif /* __PERF_MEM_EVENTS_H */
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index b7834a5a002d..c7b52f4987d8 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -863,60 +863,12 @@ sort__lvl_cmp(struct hist_entry *left, struct hist_entry *right)
 	return (int64_t)(data_src_r.mem_lvl - data_src_l.mem_lvl);
 }
 
-static const char * const mem_lvl[] = {
-	"N/A",
-	"HIT",
-	"MISS",
-	"L1",
-	"LFB",
-	"L2",
-	"L3",
-	"Local RAM",
-	"Remote RAM (1 hop)",
-	"Remote RAM (2 hops)",
-	"Remote Cache (1 hop)",
-	"Remote Cache (2 hops)",
-	"I/O",
-	"Uncached",
-};
-
 static int hist_entry__lvl_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
 	char out[64];
-	size_t sz = sizeof(out) - 1; /* -1 for null termination */
-	size_t i, l = 0;
-	u64 m =  PERF_MEM_LVL_NA;
-	u64 hit, miss;
-
-	if (he->mem_info)
-		m  = he->mem_info->data_src.mem_lvl;
-
-	out[0] = '\0';
-
-	hit = m & PERF_MEM_LVL_HIT;
-	miss = m & PERF_MEM_LVL_MISS;
-
-	/* already taken care of */
-	m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
-
-	for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
-		if (!(m & 0x1))
-			continue;
-		if (l) {
-			strcat(out, " or ");
-			l += 4;
-		}
-		strncat(out, mem_lvl[i], sz - l);
-		l += strlen(mem_lvl[i]);
-	}
-	if (*out == '\0')
-		strcpy(out, "N/A");
-	if (hit)
-		strncat(out, " hit", sz - l);
-	if (miss)
-		strncat(out, " miss", sz - l);
 
+	perf_mem__lvl_scnprintf(out, sizeof(out), he->mem_info);
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
-- 
2.4.3

[PATCH 15/23] perf tools: Introduce perf_mem__snp_scnprintf function

[Jiri Olsa]

Move meminfo's snp display function into mem-events.c
object, so it could be reused later from script code.

Link: http://lkml.kernel.org/n/tip-zhd9q561o49xzhrtg8cz5jui@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/util/mem-events.c | 34 ++++++++++++++++++++++++++++++++++
 tools/perf/util/mem-events.h |  1 +
 tools/perf/util/sort.c       | 31 +------------------------------
 3 files changed, 36 insertions(+), 30 deletions(-)

diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index f291f93ac11d..1d57defe6ea7 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -217,3 +217,37 @@ void perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 	if (miss)
 		strncat(out, " miss", sz - l);
 }
+
+static const char * const snoop_access[] = {
+	"N/A",
+	"None",
+	"Miss",
+	"Hit",
+	"HitM",
+};
+
+void perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	size_t i, l = 0;
+	u64 m = PERF_MEM_SNOOP_NA;
+
+	sz -= 1; /* -1 for null termination */
+	out[0] = '\0';
+
+	if (mem_info)
+		m = mem_info->data_src.mem_snoop;
+
+	for (i = 0; m && i < ARRAY_SIZE(snoop_access); i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		strncat(out, snoop_access[i], sz - l);
+		l += strlen(snoop_access[i]);
+	}
+
+	if (*out == '\0')
+		strcpy(out, "N/A");
+}
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index fc6d94fc96e8..7b9e172cfa72 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -47,5 +47,6 @@ char *perf_mem_events__name(int i);
 struct mem_info;
 void perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 void perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+void perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 #endif /* __PERF_MEM_EVENTS_H */
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index c7b52f4987d8..de936ce324b7 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -891,41 +891,12 @@ sort__snoop_cmp(struct hist_entry *left, struct hist_entry *right)
 	return (int64_t)(data_src_r.mem_snoop - data_src_l.mem_snoop);
 }
 
-static const char * const snoop_access[] = {
-	"N/A",
-	"None",
-	"Miss",
-	"Hit",
-	"HitM",
-};
-
 static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
 	char out[64];
-	size_t sz = sizeof(out) - 1; /* -1 for null termination */
-	size_t i, l = 0;
-	u64 m = PERF_MEM_SNOOP_NA;
-
-	out[0] = '\0';
-
-	if (he->mem_info)
-		m = he->mem_info->data_src.mem_snoop;
-
-	for (i = 0; m && i < ARRAY_SIZE(snoop_access); i++, m >>= 1) {
-		if (!(m & 0x1))
-			continue;
-		if (l) {
-			strcat(out, " or ");
-			l += 4;
-		}
-		strncat(out, snoop_access[i], sz - l);
-		l += strlen(snoop_access[i]);
-	}
-
-	if (*out == '\0')
-		strcpy(out, "N/A");
 
+	perf_mem__snp_scnprintf(out, sizeof(out), he->mem_info);
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
-- 
2.4.3

[PATCH 16/23] perf tools: Introduce perf_mem__lck_scnprintf function

[Jiri Olsa]

Move meminfo's lck display function into mem-events.c
object, so it could be reused later from script code.

Link: http://lkml.kernel.org/n/tip-qiwjnu0m6vzknv25t5ggund6@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/util/mem-events.c | 16 ++++++++++++++++
 tools/perf/util/mem-events.h |  2 ++
 tools/perf/util/sort.c       | 14 ++------------
 3 files changed, 20 insertions(+), 12 deletions(-)

diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 1d57defe6ea7..915fae6ad3ee 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -251,3 +251,19 @@ void perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 	if (*out == '\0')
 		strcpy(out, "N/A");
 }
+
+void perf_mem__lck_scnprintf(char *out, size_t sz __maybe_unused,
+			     struct mem_info *mem_info)
+{
+	u64 mask = PERF_MEM_LOCK_NA;
+
+	if (mem_info)
+		mask = mem_info->data_src.mem_lock;
+
+	if (mask & PERF_MEM_LOCK_NA)
+		strncat(out, "N/A", 3);
+	else if (mask & PERF_MEM_LOCK_LOCKED)
+		strncat(out, "Yes", 3);
+	else
+		strncat(out, "No", 2);
+}
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 7b9e172cfa72..0dd2efb37c44 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -48,5 +48,7 @@ struct mem_info;
 void perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 void perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 void perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+void perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+
 #endif /* __PERF_MEM_EVENTS_H */
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index de936ce324b7..e9553738f2ce 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -800,19 +800,9 @@ sort__locked_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__locked_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	const char *out;
-	u64 mask = PERF_MEM_LOCK_NA;
-
-	if (he->mem_info)
-		mask = he->mem_info->data_src.mem_lock;
-
-	if (mask & PERF_MEM_LOCK_NA)
-		out = "N/A";
-	else if (mask & PERF_MEM_LOCK_LOCKED)
-		out = "Yes";
-	else
-		out = "No";
+	char out[10];
 
+	perf_mem__lck_scnprintf(out, sizeof(out), he->mem_info);
 	return repsep_snprintf(bf, size, "%.*s", width, out);
 }
 
-- 
2.4.3

[PATCH 17/23] perf tools: Change perf_mem__tlb_scnprintf to return nb of displayed bytes

[Jiri Olsa]

Moving strncat/strcpy calls into scnprintf to easily track
number of displayed bytes. It will be used in following patch.

Link: http://lkml.kernel.org/n/tip-9q9h9trua9zljnw26c56memh@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/util/mem-events.c | 13 +++++++------
 tools/perf/util/mem-events.h |  2 +-
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 915fae6ad3ee..440221ca4f8a 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -129,7 +129,7 @@ static const char * const tlb_access[] = {
 	"Fault",
 };
 
-void perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 {
 	size_t l = 0, i;
 	u64 m = PERF_MEM_TLB_NA;
@@ -154,15 +154,16 @@ void perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 			strcat(out, " or ");
 			l += 4;
 		}
-		strncat(out, tlb_access[i], sz - l);
-		l += strlen(tlb_access[i]);
+		l += scnprintf(out + l, sz - l, tlb_access[i]);
 	}
 	if (*out == '\0')
-		strcpy(out, "N/A");
+		l += scnprintf(out, sz - l, "N/A");
 	if (hit)
-		strncat(out, " hit", sz - l);
+		l += scnprintf(out + l, sz - l, " hit");
 	if (miss)
-		strncat(out, " miss", sz - l);
+		l += scnprintf(out + l, sz - l, " miss");
+
+	return l;
 }
 
 static const char * const mem_lvl[] = {
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 0dd2efb37c44..ce9ed0540014 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -45,7 +45,7 @@ int perf_mem_events__init(void);
 char *perf_mem_events__name(int i);
 
 struct mem_info;
-void perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 void perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 void perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 void perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
-- 
2.4.3

[PATCH 18/23] perf tools: Change perf_mem__lvl_scnprintf to return nb of displayed bytes

[Jiri Olsa]

Moving strncat/strcpy calls into scnprintf to easily track
number of displayed bytes. It will be used in following patch.

Link: http://lkml.kernel.org/n/tip-9q9h9trua9zljnw26c56memh@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/util/mem-events.c | 13 +++++++------
 tools/perf/util/mem-events.h |  2 +-
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 440221ca4f8a..5f713d77ac8a 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -183,7 +183,7 @@ static const char * const mem_lvl[] = {
 	"Uncached",
 };
 
-void perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 {
 	size_t i, l = 0;
 	u64 m =  PERF_MEM_LVL_NA;
@@ -208,15 +208,16 @@ void perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 			strcat(out, " or ");
 			l += 4;
 		}
-		strncat(out, mem_lvl[i], sz - l);
-		l += strlen(mem_lvl[i]);
+		l += scnprintf(out + l, sz - l, mem_lvl[i]);
 	}
 	if (*out == '\0')
-		strcpy(out, "N/A");
+		l += scnprintf(out, sz - l, "N/A");
 	if (hit)
-		strncat(out, " hit", sz - l);
+		l += scnprintf(out + l, sz - l, " hit");
 	if (miss)
-		strncat(out, " miss", sz - l);
+		l += scnprintf(out + l, sz - l, " miss");
+
+	return l;
 }
 
 static const char * const snoop_access[] = {
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index ce9ed0540014..a06efff4ef09 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -46,7 +46,7 @@ char *perf_mem_events__name(int i);
 
 struct mem_info;
 int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
-void perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 void perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 void perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 
-- 
2.4.3

[PATCH 19/23] perf tools: Change perf_mem__snp_scnprintf to return nb of displayed bytes

[Jiri Olsa]

Moving strncat/strcpy calls into scnprintf to easily track
number of displayed bytes. It will be used in following patch.

Link: http://lkml.kernel.org/n/tip-dvtk0c7clgi857x699mk08ya@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/util/mem-events.c | 9 +++++----
 tools/perf/util/mem-events.h | 2 +-
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 5f713d77ac8a..aaeb619a9e77 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -228,7 +228,7 @@ static const char * const snoop_access[] = {
 	"HitM",
 };
 
-void perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 {
 	size_t i, l = 0;
 	u64 m = PERF_MEM_SNOOP_NA;
@@ -246,12 +246,13 @@ void perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 			strcat(out, " or ");
 			l += 4;
 		}
-		strncat(out, snoop_access[i], sz - l);
-		l += strlen(snoop_access[i]);
+		l += scnprintf(out + l, sz - l, snoop_access[i]);
 	}
 
 	if (*out == '\0')
-		strcpy(out, "N/A");
+		l += scnprintf(out, sz - l, "N/A");
+
+	return l;
 }
 
 void perf_mem__lck_scnprintf(char *out, size_t sz __maybe_unused,
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index a06efff4ef09..4b5d0b93979b 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -47,7 +47,7 @@ char *perf_mem_events__name(int i);
 struct mem_info;
 int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
-void perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 void perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 
 #endif /* __PERF_MEM_EVENTS_H */
-- 
2.4.3

[PATCH 20/23] perf tools: Change perf_mem__lck_scnprintf to return nb of displayed bytes

[Jiri Olsa]

Moving strncat call into scnprintf to easily track
number of displayed bytes. It will be used in following patch.

Link: http://lkml.kernel.org/n/tip-oqjs8kf50g0n65uj8sfqlb8y@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/util/mem-events.c | 12 +++++++-----
 tools/perf/util/mem-events.h |  2 +-
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index aaeb619a9e77..0da707da127c 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -255,18 +255,20 @@ int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 	return l;
 }
 
-void perf_mem__lck_scnprintf(char *out, size_t sz __maybe_unused,
-			     struct mem_info *mem_info)
+int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 {
 	u64 mask = PERF_MEM_LOCK_NA;
+	int l;
 
 	if (mem_info)
 		mask = mem_info->data_src.mem_lock;
 
 	if (mask & PERF_MEM_LOCK_NA)
-		strncat(out, "N/A", 3);
+		l = scnprintf(out, sz, "N/A");
 	else if (mask & PERF_MEM_LOCK_LOCKED)
-		strncat(out, "Yes", 3);
+		l = scnprintf(out, sz, "Yes");
 	else
-		strncat(out, "No", 2);
+		l = scnprintf(out, sz, "No");
+
+	return l;
 }
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 4b5d0b93979b..759d35da2d6a 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -48,7 +48,7 @@ struct mem_info;
 int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
-void perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 
 #endif /* __PERF_MEM_EVENTS_H */
 
-- 
2.4.3

[PATCH 21/23] perf script: Add data_src and weight column definitions

[Jiri Olsa]

Adding data_src and weight column definitions, so it's
displayed for related sample types.

Link: http://lkml.kernel.org/n/tip-d9d387o10v7ega0mbd4b2zpo@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-script.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c691214d820f..b7f1e8e22dcf 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -58,6 +58,8 @@ enum perf_output_field {
 	PERF_OUTPUT_IREGS	    = 1U << 14,
 	PERF_OUTPUT_BRSTACK	    = 1U << 15,
 	PERF_OUTPUT_BRSTACKSYM	    = 1U << 16,
+	PERF_OUTPUT_DATA_SRC	    = 1U << 17,
+	PERF_OUTPUT_WEIGHT	    = 1U << 18,
 };
 
 struct output_option {
@@ -81,6 +83,8 @@ struct output_option {
 	{.str = "iregs", .field = PERF_OUTPUT_IREGS},
 	{.str = "brstack", .field = PERF_OUTPUT_BRSTACK},
 	{.str = "brstacksym", .field = PERF_OUTPUT_BRSTACKSYM},
+	{.str = "data_src", .field = PERF_OUTPUT_DATA_SRC},
+	{.str = "weight",   .field = PERF_OUTPUT_WEIGHT},
 };
 
 /* default set to maintain compatibility with current format */
@@ -242,6 +246,16 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 					   PERF_OUTPUT_ADDR, allow_user_set))
 		return -EINVAL;
 
+	if (PRINT_FIELD(DATA_SRC) &&
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC",
+					PERF_OUTPUT_DATA_SRC))
+		return -EINVAL;
+
+	if (PRINT_FIELD(WEIGHT) &&
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT, "WEIGHT",
+					PERF_OUTPUT_WEIGHT))
+		return -EINVAL;
+
 	if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
 		pr_err("Display of symbols requested but neither sample IP nor "
 			   "sample address\nis selected. Hence, no addresses to convert "
@@ -673,6 +687,12 @@ static void process_event(struct perf_script *script, union perf_event *event,
 	if (PRINT_FIELD(ADDR))
 		print_sample_addr(event, sample, thread, attr);
 
+	if (PRINT_FIELD(DATA_SRC))
+		printf("%16" PRIx64, sample->data_src);
+
+	if (PRINT_FIELD(WEIGHT))
+		printf("%16" PRIu64, sample->weight);
+
 	if (PRINT_FIELD(IP)) {
 		if (!symbol_conf.use_callchain)
 			printf(" ");
-- 
2.4.3

[PATCH 22/23] perf script: Display addr/data_src/weight columns for raw events

[Jiri Olsa]

Adding addr/data_src/weight columns for raw events.

Example:
  $ perf script
  ...
  true 11883 322960.489590: ...  ffff8801aa0b8400        68501042             246 ffffffff813b2cd
  true 11883 322960.489600: ...  ffff8800b90b38d8        68501042             251 ffffffff811d0b7
  true 11883 322960.489612: ...  ffff880196893130        6a100142              94 ffffffff8177fb8
  true 11883 322960.489637: ...  ffff880164277b40        68100842             101 ffffffff813b2cd
  true 11883 322960.489683: ...  ffff880035d3d818        68501042             201 ffffffff811d0b7
  true 11883 322960.489733: ...      7fb9616efcf0        68100242             199     7fb961aaba9
  true 11883 322960.489818: ...  ffffea000481c39c        6a100142             122 ffffffff811b634

                                 ^^^^^^^^^^^^^^^^        ^^^^^^^^             ^^^
                                             addr        data_src          weight

Link: http://lkml.kernel.org/n/tip-y761oo0pgvg82uco3ca9iwix@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-script.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index b7f1e8e22dcf..f4caf4898245 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -135,7 +135,8 @@ static struct {
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
 			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_PERIOD,
+			      PERF_OUTPUT_PERIOD |  PERF_OUTPUT_ADDR |
+			      PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT,
 
 		.invalid_fields = PERF_OUTPUT_TRACE,
 	},
-- 
2.4.3

[PATCH 23/23] perf script: Display data_src values

[Jiri Olsa]

Adding support to display data_src values,
for events with data_src data in sample.

Example:
  $ perf script
  ...
           rcuos/3    32 [002] ... 68501042 Local RAM hit|SNP None or Hit|TLB L1 or L2 hit|LCK No   ...
           rcuos/3    32 [002] ... 68100142 L1 hit|SNP None|TLB L1 or L2 hit|LCK No                 ...
           swapper     0 [002] ... 68100242 LFB hit|SNP None|TLB L1 or L2 hit|LCK No                ...
           swapper     0 [000] ... 68100142 L1 hit|SNP None|TLB L1 or L2 hit|LCK No                 ...
           swapper     0 [000] ... 50100142 L1 hit|SNP None|TLB L2 miss|LCK No                      ...
           rcuos/3    32 [002] ... 68100142 L1 hit|SNP None|TLB L1 or L2 hit|LCK No                 ...
   plugin-containe 16538 [000] ... 6a100142 L1 hit|SNP None|TLB L1 or L2 hit|LCK Yes                ...
           gkrellm  1736 [000] ... 68100242 LFB hit|SNP None|TLB L1 or L2 hit|LCK No                ...
           gkrellm  1736 [000] ... 6a100142 L1 hit|SNP None|TLB L1 or L2 hit|LCK Yes                ...

                                   ^^^^^^^^ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                             data_src value                     data_src translation

Link: http://lkml.kernel.org/n/tip-48x7lm7d765bzo3oghap376m@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-script.c  | 20 +++++++++++++++++++-
 tools/perf/util/mem-events.c | 15 +++++++++++++++
 tools/perf/util/mem-events.h |  2 ++
 3 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index f4caf4898245..8ff5ff0fe38c 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -23,6 +23,7 @@
 #include "util/stat.h"
 #include <linux/bitmap.h>
 #include "asm/bug.h"
+#include "util/mem-events.h"
 
 static char const		*script_name;
 static char const		*generate_script_lang;
@@ -649,6 +650,23 @@ static int perf_evlist__max_name_len(struct perf_evlist *evlist)
 	return max;
 }
 
+static size_t data_src__printf(u64 data_src)
+{
+	struct mem_info mi = { .data_src.val = data_src };
+	char decode[100];
+	char out[100];
+	static int maxlen;
+	int len;
+
+	perf_script__meminfo_scnprintf(decode, 100, &mi);
+
+	len = scnprintf(out, 100, "%16" PRIx64 " %s", data_src, decode);
+	if (maxlen < len)
+		maxlen = len;
+
+	return printf("%-*s", maxlen, out);
+}
+
 static void process_event(struct perf_script *script, union perf_event *event,
 			  struct perf_sample *sample, struct perf_evsel *evsel,
 			  struct addr_location *al)
@@ -689,7 +707,7 @@ static void process_event(struct perf_script *script, union perf_event *event,
 		print_sample_addr(event, sample, thread, attr);
 
 	if (PRINT_FIELD(DATA_SRC))
-		printf("%16" PRIx64, sample->data_src);
+		data_src__printf(sample->data_src);
 
 	if (PRINT_FIELD(WEIGHT))
 		printf("%16" PRIu64, sample->weight);
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 0da707da127c..31e079a1ab7b 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -272,3 +272,18 @@ int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 
 	return l;
 }
+
+int perf_script__meminfo_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	int i = 0;
+
+	i += perf_mem__lvl_scnprintf(out, sz, mem_info);
+	i += scnprintf(out + i, sz - i, "|SNP ");
+	i += perf_mem__snp_scnprintf(out + i, sz - i, mem_info);
+	i += scnprintf(out + i, sz - i, "|TLB ");
+	i += perf_mem__tlb_scnprintf(out + i, sz - i, mem_info);
+	i += scnprintf(out + i, sz - i, "|LCK ");
+	i += perf_mem__lck_scnprintf(out + i, sz - i, mem_info);
+
+	return i;
+}
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 759d35da2d6a..0f63d6a1c53a 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -50,5 +50,7 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 
+int perf_script__meminfo_scnprintf(char *bf, size_t size, struct mem_info *mem_info);
+
 #endif /* __PERF_MEM_EVENTS_H */
 
-- 
2.4.3

Re: [PATCH 01/23] perf record: Add --all-user/--all-kernel options

[Arnaldo Carvalho de Melo]

Em Mon, Feb 15, 2016 at 09:34:31AM +0100, Jiri Olsa escreveu:
> Allow user to easily switch all events to user or
> kernel space with simple --all-user or --all-kernel
> options.
> 
> This will be handy within perf mem/c2c wrappers to
> switch easily monitoring modes.

Humm, some oddities:

  # perf record --all-user -e cycles -a
  # perf report --tui       # And then notice there are some kernel samples, zoom into kernel DSO
  Samples: 7  of event 'cycles', Event count (approx.): 3158810, DSO: [kernel.vmlinux]
  Overhead  Comman  Symbol
    84.05%  chrome  [k] page_fault
    15.73%  chrome  [k] entry_SYSCALL_64
     0.22%  chrome  [k] apic_timer_interrupt

Ditto when using --all-kernel, some userspace samples are there, also perhaps we
should show "cycles:u" or "cycles:k" when this --all-user or --all-kernel features
are used.

Need to investigate why there are kernel samples when --all-user is used and
the other way around as well.

Also if I use both it quietly accepts and shows just one of them, I guess we
should bail out in case someone tries both.

- Arnaldo 

> Link: http://lkml.kernel.org/n/tip-hdd2u0y1o8cwfpplrpzc1iqd@git.kernel.org
> Signed-off-by: Jiri Olsa <jolsa@kernel.org>
> ---
>  tools/perf/Documentation/perf-record.txt |  6 ++++++
>  tools/perf/builtin-record.c              |  4 ++++
>  tools/perf/perf.h                        |  2 ++
>  tools/perf/util/evsel.c                  | 10 ++++++++++
>  4 files changed, 22 insertions(+)
> 
> diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
> index fbceb631387c..19aa17532a16 100644
> --- a/tools/perf/Documentation/perf-record.txt
> +++ b/tools/perf/Documentation/perf-record.txt
> @@ -341,6 +341,12 @@ Specify vmlinux path which has debuginfo.
>  --buildid-all::
>  Record build-id of all DSOs regardless whether it's actually hit or not.
>  
> +--all-kernel::
> +Configure all used events to run in kernel space.
> +
> +--all-user::
> +Configure all used events to run in user space.
> +
>  SEE ALSO
>  --------
>  linkperf:perf-stat[1], linkperf:perf-list[1]
> diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
> index caa8235ed027..b64f31a4c993 100644
> --- a/tools/perf/builtin-record.c
> +++ b/tools/perf/builtin-record.c
> @@ -1151,6 +1151,10 @@ struct option __record_options[] = {
>  			"per thread proc mmap processing timeout in ms"),
>  	OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events,
>  		    "Record context switch events"),
> +	OPT_BOOLEAN(0, "all-kernel", &record.opts.all_kernel,
> +		    "Configure all used events to run in kernel space."),
> +	OPT_BOOLEAN(0, "all-user", &record.opts.all_user,
> +		    "Configure all used events to run in user space."),
>  	OPT_STRING(0, "clang-path", &llvm_param.clang_path, "clang path",
>  		   "clang binary to use for compiling BPF scriptlets"),
>  	OPT_STRING(0, "clang-opt", &llvm_param.clang_opt, "clang options",
> diff --git a/tools/perf/perf.h b/tools/perf/perf.h
> index 90129accffbe..5381a01c0610 100644
> --- a/tools/perf/perf.h
> +++ b/tools/perf/perf.h
> @@ -58,6 +58,8 @@ struct record_opts {
>  	bool	     full_auxtrace;
>  	bool	     auxtrace_snapshot_mode;
>  	bool	     record_switch_events;
> +	bool	     all_kernel;
> +	bool	     all_user;
>  	unsigned int freq;
>  	unsigned int mmap_pages;
>  	unsigned int auxtrace_mmap_pages;
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index 467808680ee4..6ae20d0056de 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -898,6 +898,16 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
>  	if (evsel->precise_max)
>  		perf_event_attr__set_max_precise_ip(attr);
>  
> +	if (opts->all_user) {
> +		attr->exclude_kernel = 1;
> +		attr->exclude_user   = 0;
> +	}
> +
> +	if (opts->all_kernel) {
> +		attr->exclude_kernel = 0;
> +		attr->exclude_user   = 1;
> +	}
> +
>  	/*
>  	 * Apply event specific term settings,
>  	 * it overloads any global configuration.
> -- 
> 2.4.3

Re: [PATCH 01/23] perf record: Add --all-user/--all-kernel options

[Andi Kleen]

> Need to investigate why there are kernel samples when --all-user is used and
> the other way around as well.

This is a known issue due to skid. PEBS usually avoids it.

-Andi

Re: [PATCH 01/23] perf record: Add --all-user/--all-kernel options

[Arnaldo Carvalho de Melo]

Em Tue, Feb 16, 2016 at 07:10:37PM -0800, Andi Kleen escreveu:
> > Need to investigate why there are kernel samples when --all-user is used and
> > the other way around as well.

> This is a known issue due to skid. PEBS usually avoids it.

Right, thanks for pointing this out, we have to detect that :p is not
being used and warn the user about this possibility, i.e. user asks for
just kernel samples, tool finds user samples, tell that using :p+ may
help.

Now, using plain:

 # perf record --all-user -a sleep 2

will make it use the default which is 'cycles' with the highest
precision available on the machine, and that leaves just a few samples
that supposedly have the MISC_KERNEL bit set in the perf_event_attr
header, those are not mapping to any mmap area known to the tool, I'm
investigating what this is.

I'll apply the patch as-is, we'll check later OPT_ magic to tell that
those options are mutually exclusive.

- Arnaldo

Re: [PATCH 01/23] perf record: Add --all-user/--all-kernel options

[Jiri Olsa]

On Tue, Feb 16, 2016 at 01:56:01PM -0300, Arnaldo Carvalho de Melo wrote:
> Em Mon, Feb 15, 2016 at 09:34:31AM +0100, Jiri Olsa escreveu:
> > Allow user to easily switch all events to user or
> > kernel space with simple --all-user or --all-kernel
> > options.
> > 
> > This will be handy within perf mem/c2c wrappers to
> > switch easily monitoring modes.
> 
> Humm, some oddities:
> 
>   # perf record --all-user -e cycles -a
>   # perf report --tui       # And then notice there are some kernel samples, zoom into kernel DSO
>   Samples: 7  of event 'cycles', Event count (approx.): 3158810, DSO: [kernel.vmlinux]
>   Overhead  Comman  Symbol
>     84.05%  chrome  [k] page_fault
>     15.73%  chrome  [k] entry_SYSCALL_64
>      0.22%  chrome  [k] apic_timer_interrupt
> 
> Ditto when using --all-kernel, some userspace samples are there, also perhaps we
> should show "cycles:u" or "cycles:k" when this --all-user or --all-kernel features
> are used.
> 
> Need to investigate why there are kernel samples when --all-user is used and
> the other way around as well.
> 
> Also if I use both it quietly accepts and shows just one of them, I guess we
> should bail out in case someone tries both.

right, that should be handled with warning and exit
I'll do it in next version

thanks,
jirka

Re: [PATCH 01/23] perf record: Add --all-user/--all-kernel options

[Arnaldo Carvalho de Melo]

Em Wed, Feb 17, 2016 at 03:39:38PM +0100, Jiri Olsa escreveu:
> On Tue, Feb 16, 2016 at 01:56:01PM -0300, Arnaldo Carvalho de Melo wrote:
> > Em Mon, Feb 15, 2016 at 09:34:31AM +0100, Jiri Olsa escreveu:
> > > Allow user to easily switch all events to user or
> > > kernel space with simple --all-user or --all-kernel
> > > options.
> > > 
> > > This will be handy within perf mem/c2c wrappers to
> > > switch easily monitoring modes.
> > 
> > Humm, some oddities:
> > 
> >   # perf record --all-user -e cycles -a
> >   # perf report --tui       # And then notice there are some kernel samples, zoom into kernel DSO
> >   Samples: 7  of event 'cycles', Event count (approx.): 3158810, DSO: [kernel.vmlinux]
> >   Overhead  Comman  Symbol
> >     84.05%  chrome  [k] page_fault
> >     15.73%  chrome  [k] entry_SYSCALL_64
> >      0.22%  chrome  [k] apic_timer_interrupt
> > 
> > Ditto when using --all-kernel, some userspace samples are there, also perhaps we
> > should show "cycles:u" or "cycles:k" when this --all-user or --all-kernel features
> > are used.
> > 
> > Need to investigate why there are kernel samples when --all-user is used and
> > the other way around as well.
> > 
> > Also if I use both it quietly accepts and shows just one of them, I guess we
> > should bail out in case someone tries both.
> 
> right, that should be handled with warning and exit
> I'll do it in next version

Ok, so I'll wait for it then,

builtin-probe.c uses things like:

        set_option_flag(options, 'a', "add", PARSE_OPT_EXCLUSIVE); 
        set_option_flag(options, 'd', "del", PARSE_OPT_EXCLUSIVE);

We have:

#define OPT_BOOLEAN_FLAG(s, l, v, h, f)     { .type = OPTION_BOOLEAN,
.short_name = (s), .long_name = (l), .value = check_vtype(v, bool *),
.help = (h), .flags = (f) }


That allows setting that PARSE_OPT_EXCLUSIVE flag, but we don't have
_FLAG variants for all opt types, for instance there is no
OPT_CALLBACK_FLAG() that could be used in builtin-probe.c to avoid those
unconditional set_option_flag(EXCLUSIVE) :-\

- Arnaldo

Re: [PATCH 01/23] perf record: Add --all-user/--all-kernel options

[Andi Kleen]

On Wed, Feb 17, 2016 at 11:26:16AM -0300, Arnaldo Carvalho de Melo wrote:
> Em Tue, Feb 16, 2016 at 07:10:37PM -0800, Andi Kleen escreveu:
> > > Need to investigate why there are kernel samples when --all-user is used and
> > > the other way around as well.
> 
> > This is a known issue due to skid. PEBS usually avoids it.
> 
> Right, thanks for pointing this out, we have to detect that :p is not
> being used and warn the user about this possibility, i.e. user asks for
> just kernel samples, tool finds user samples, tell that using :p+ may
> help.

If you're really so worried about it the kernel driver could filter it.

-Andi

[tip:perf/core] perf record: Add --all-user/--all-kernel options

[tip-bot for Jiri Olsa]

Commit-ID:  85723885feb823b4fc352b727ece0b6d00306c4d
Gitweb:     http://git.kernel.org/tip/85723885feb823b4fc352b727ece0b6d00306c4d
Author:     Jiri Olsa <jolsa@kernel.org>
AuthorDate: Mon, 15 Feb 2016 09:34:31 +0100
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Thu, 18 Feb 2016 10:48:44 -0300

perf record: Add --all-user/--all-kernel options

Allow user to easily switch all events to user or kernel space with simple
--all-user or --all-kernel options.

This will be handy within perf mem/c2c wrappers to switch easily monitoring
modes.

Committer note:

Testing it:

  # perf record --all-kernel --all-user -a sleep 2
   Error: option `all-user' cannot be used with all-kernel
   Usage: perf record [<options>] [<command>]
      or: perf record [<options>] -- <command> [<options>]

        --all-user        Configure all used events to run in user space.
        --all-kernel      Configure all used events to run in kernel space.
  # perf record --all-user --all-kernel -a sleep 2
   Error: option `all-kernel' cannot be used with all-user
   Usage: perf record [<options>] [<command>]
      or: perf record [<options>] -- <command> [<options>]

        --all-kernel      Configure all used events to run in kernel space.
        --all-user        Configure all used events to run in user space.
  # perf record --all-user -a sleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 1.416 MB perf.data (162 samples) ]
  # perf report | grep '\[k\]'
  # perf record --all-kernel -a sleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 1.423 MB perf.data (296 samples) ]
  # perf report | grep '\[\.\]'
  #

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1455525293-8671-2-git-send-email-jolsa@kernel.org
[ Made those options to be mutually exclusive ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-record.txt |  6 ++++++
 tools/perf/builtin-record.c              |  6 ++++++
 tools/perf/perf.h                        |  2 ++
 tools/perf/util/evsel.c                  | 10 ++++++++++
 4 files changed, 24 insertions(+)

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index fbceb63..19aa175 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -341,6 +341,12 @@ Specify vmlinux path which has debuginfo.
 --buildid-all::
 Record build-id of all DSOs regardless whether it's actually hit or not.
 
+--all-kernel::
+Configure all used events to run in kernel space.
+
+--all-user::
+Configure all used events to run in user space.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0ee0d5c..cf3a28d 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1140,6 +1140,12 @@ struct option __record_options[] = {
 			"per thread proc mmap processing timeout in ms"),
 	OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events,
 		    "Record context switch events"),
+	OPT_BOOLEAN_FLAG(0, "all-kernel", &record.opts.all_kernel,
+			 "Configure all used events to run in kernel space.",
+			 PARSE_OPT_EXCLUSIVE),
+	OPT_BOOLEAN_FLAG(0, "all-user", &record.opts.all_user,
+			 "Configure all used events to run in user space.",
+			 PARSE_OPT_EXCLUSIVE),
 	OPT_STRING(0, "clang-path", &llvm_param.clang_path, "clang path",
 		   "clang binary to use for compiling BPF scriptlets"),
 	OPT_STRING(0, "clang-opt", &llvm_param.clang_opt, "clang options",
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 90129ac..5381a01 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -58,6 +58,8 @@ struct record_opts {
 	bool	     full_auxtrace;
 	bool	     auxtrace_snapshot_mode;
 	bool	     record_switch_events;
+	bool	     all_kernel;
+	bool	     all_user;
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int auxtrace_mmap_pages;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 4678086..6ae20d0 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -898,6 +898,16 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	if (evsel->precise_max)
 		perf_event_attr__set_max_precise_ip(attr);
 
+	if (opts->all_user) {
+		attr->exclude_kernel = 1;
+		attr->exclude_user   = 0;
+	}
+
+	if (opts->all_kernel) {
+		attr->exclude_kernel = 0;
+		attr->exclude_user   = 1;
+	}
+
 	/*
 	 * Apply event specific term settings,
 	 * it overloads any global configuration.

Re: [PATCH 04/23] perf tools: Add monitored events array

[Arnaldo Carvalho de Melo]

Em Mon, Feb 15, 2016 at 09:34:34AM +0100, Jiri Olsa escreveu:
> It will ease up configuration of memory events
> and addition of other memory events in following
> patches.
> 
> Link: http://lkml.kernel.org/n/tip-5n4yyd6dlrjhpd9rmaa2sycs@git.kernel.org
> Signed-off-by: Jiri Olsa <jolsa@kernel.org>

Please check your .git/hooks, fixing it this time:


[acme@jouet linux]$ am /wb/1.patch 
Applying: perf tools: Add monitored events array
/home/acme/git/linux/.git/rebase-apply/patch:104: new blank line at EOF.
+
warning: 1 line adds whitespace errors.
tools/perf/util/mem-events.h:20: new blank line at EOF.
[acme@jouet linux]$

Re: [PATCH 04/23] perf tools: Add monitored events array

[Jiri Olsa]

On Tue, Feb 23, 2016 at 12:10:35PM -0300, Arnaldo Carvalho de Melo wrote:
> Em Mon, Feb 15, 2016 at 09:34:34AM +0100, Jiri Olsa escreveu:
> > It will ease up configuration of memory events
> > and addition of other memory events in following
> > patches.
> > 
> > Link: http://lkml.kernel.org/n/tip-5n4yyd6dlrjhpd9rmaa2sycs@git.kernel.org
> > Signed-off-by: Jiri Olsa <jolsa@kernel.org>
> 
> Please check your .git/hooks, fixing it this time:

hum, I don't have any ;-) will check, thanks

jirka

> 
> 
> [acme@jouet linux]$ am /wb/1.patch 
> Applying: perf tools: Add monitored events array
> /home/acme/git/linux/.git/rebase-apply/patch:104: new blank line at EOF.
> +
> warning: 1 line adds whitespace errors.
> tools/perf/util/mem-events.h:20: new blank line at EOF.
> [acme@jouet linux]$

Re: [PATCH 06/23] perf mem: Check for memory events support

[Arnaldo Carvalho de Melo]

Em Mon, Feb 15, 2016 at 09:34:36AM +0100, Jiri Olsa escreveu:
> Check if current kernel support available memory events
> and display the status within -e  list option:
> 
>   $ perf mem record -e list
>   [ok] ldlat-loads
>   [ok] ldlat-stores

Can't this be:

  $ perf mem record -e list
  ldlat-loads:  Available on this machine
  ldlat-stores: Available on this machine

- Arnaldo
 
> Link: http://lkml.kernel.org/n/tip-r8smhxjfe69q67jwt7mzs0e9@git.kernel.org
> Signed-off-by: Jiri Olsa <jolsa@kernel.org>
> ---
>  tools/perf/builtin-mem.c     | 14 +++++++++++++-
>  tools/perf/util/mem-events.c | 35 ++++++++++++++++++++++++++++++++---
>  tools/perf/util/mem-events.h |  3 +++
>  3 files changed, 48 insertions(+), 4 deletions(-)
> 
> diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
> index b3f8a89ede40..e64e0aa7ba0e 100644
> --- a/tools/perf/builtin-mem.c
> +++ b/tools/perf/builtin-mem.c
> @@ -40,7 +40,8 @@ static int parse_record_events(const struct option *opt,
>  	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
>  		struct perf_mem_event *e = &perf_mem_events[j];
>  
> -		fprintf(stderr, "%-20s%s",
> +		fprintf(stderr, "%s%-20s%s",
> +			e->supported ? "[ok] " : "     ",
>  			e->tag, verbose ? "" : "\n");
>  		if (verbose)
>  			fprintf(stderr, " [%s]\n", e->name);
> @@ -92,6 +93,12 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
>  		if (!perf_mem_events[j].record)
>  			continue;
>  
> +		if (!perf_mem_events[j].supported) {
> +			pr_err("failed: event '%s' not supported\n",
> +			       perf_mem_events[j].name);
> +			return -1;
> +		}
> +
>  		rec_argv[i++] = "-e";
>  		rec_argv[i++] = perf_mem_events[j].name;
>  	};
> @@ -355,6 +362,11 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
>  		NULL
>  	};
>  
> +	if (perf_mem_events__init()) {
> +		pr_err("failed: memory events not supported\n");
> +		return -1;
> +	}
> +
>  	argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands,
>  					mem_usage, PARSE_OPT_STOP_AT_NON_OPTION);
>  
> diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
> index b1507c04b257..e21853fe1312 100644
> --- a/tools/perf/util/mem-events.c
> +++ b/tools/perf/util/mem-events.c
> @@ -2,15 +2,20 @@
>  #include <stdlib.h>
>  #include <string.h>
>  #include <errno.h>
> +#include <sys/types.h>
> +#include <sys/stat.h>
> +#include <unistd.h>
> +#include <api/fs/fs.h>
>  #include "mem-events.h"
>  #include "debug.h"
>  
> -#define E(t, n) { .tag = t, .name = n }
> +#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
>  
>  struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
> -	E("ldlat-loads",	"cpu/mem-loads,ldlat=30/P"),
> -	E("ldlat-stores",	"cpu/mem-stores/P"),
> +	E("ldlat-loads",	"cpu/mem-loads,ldlat=30/P",	"mem-loads"),
> +	E("ldlat-stores",	"cpu/mem-stores/P",		"mem-stores"),
>  };
> +#undef E
>  
>  #undef E
>  
> @@ -49,3 +54,27 @@ int perf_mem_events__parse(const char *str)
>  	pr_err("failed: event '%s' not found, use '-e list' to get list of available events\n", str);
>  	return -1;
>  }
> +
> +int perf_mem_events__init(void)
> +{
> +	const char *mnt = sysfs__mount();
> +	bool found = false;
> +	int j;
> +
> +	if (!mnt)
> +		return -ENOENT;
> +
> +	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
> +		char path[PATH_MAX];
> +		struct perf_mem_event *e = &perf_mem_events[j];
> +		struct stat st;
> +
> +		scnprintf(path, PATH_MAX, "%s/devices/cpu/events/%s",
> +			  mnt, e->sysfs_name);
> +
> +		if (!stat(path, &st))
> +			e->supported = found = true;
> +	}
> +
> +	return found ? 0 : -ENOENT;
> +}
> diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
> index 0b5247468462..b9a786346c03 100644
> --- a/tools/perf/util/mem-events.h
> +++ b/tools/perf/util/mem-events.h
> @@ -5,8 +5,10 @@
>  
>  struct perf_mem_event {
>  	bool		record;
> +	bool		supported;
>  	const char	*tag;
>  	const char	*name;
> +	const char	*sysfs_name;
>  };
>  
>  enum {
> @@ -18,6 +20,7 @@ enum {
>  extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
>  
>  int perf_mem_events__parse(const char *str);
> +int perf_mem_events__init(void);
>  
>  #endif /* __PERF_MEM_EVENTS_H */
>  
> -- 
> 2.4.3

Re: [PATCH 06/23] perf mem: Check for memory events support

[Arnaldo Carvalho de Melo]

Em Tue, Feb 23, 2016 at 12:18:14PM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Mon, Feb 15, 2016 at 09:34:36AM +0100, Jiri Olsa escreveu:
> > Check if current kernel support available memory events
> > and display the status within -e  list option:
> > 
> >   $ perf mem record -e list
> >   [ok] ldlat-loads
> >   [ok] ldlat-stores
> 
> Can't this be:
> 
>   $ perf mem record -e list
>   ldlat-loads:  Available on this machine
>   ldlat-stores: Available on this machine

Please check perf/core, I applied a good number of the patches in this
series.

- Arnaldo

Re: [PATCH 06/23] perf mem: Check for memory events support

[Jiri Olsa]

On Tue, Feb 23, 2016 at 12:18:14PM -0300, Arnaldo Carvalho de Melo wrote:
> Em Mon, Feb 15, 2016 at 09:34:36AM +0100, Jiri Olsa escreveu:
> > Check if current kernel support available memory events
> > and display the status within -e  list option:
> > 
> >   $ perf mem record -e list
> >   [ok] ldlat-loads
> >   [ok] ldlat-stores
> 
> Can't this be:
> 
>   $ perf mem record -e list
>   ldlat-loads:  Available on this machine
>   ldlat-stores: Available on this machine

hum IMO that would be quite long list if DATALA events will
get in, so I wanted something short and punchy ;-)

how about plaing it into back as you suggested
with just 'available'

	$ perf mem record -e list
	ldlat-loads:  available
	ldlat-stores: available

jirka

Re: [PATCH 06/23] perf mem: Check for memory events support

[Arnaldo Carvalho de Melo]

Em Tue, Feb 23, 2016 at 04:29:57PM +0100, Jiri Olsa escreveu:
> On Tue, Feb 23, 2016 at 12:18:14PM -0300, Arnaldo Carvalho de Melo wrote:
> > Em Mon, Feb 15, 2016 at 09:34:36AM +0100, Jiri Olsa escreveu:
> > > Check if current kernel support available memory events
> > > and display the status within -e  list option:
> > > 
> > >   $ perf mem record -e list
> > >   [ok] ldlat-loads
> > >   [ok] ldlat-stores

> > Can't this be:

> >   $ perf mem record -e list
> >   ldlat-loads:  Available on this machine
> >   ldlat-stores: Available on this machine
 
> hum IMO that would be quite long list if DATALA events will
> get in, so I wanted something short and punchy ;-)
 
> how about plaing it into back as you suggested
> with just 'available'
> 
> 	$ perf mem record -e list
> 	ldlat-loads:  available
> 	ldlat-stores: available

Fair enough, this is more in line with, say, 'perf test' output, i.e.:

  $ perf foo
  something: status/result

- Arnaldo

Re: [PATCH 06/23] perf mem: Check for memory events support

[Jiri Olsa]

On Tue, Feb 23, 2016 at 12:24:52PM -0300, Arnaldo Carvalho de Melo wrote:
> Em Tue, Feb 23, 2016 at 12:18:14PM -0300, Arnaldo Carvalho de Melo escreveu:
> > Em Mon, Feb 15, 2016 at 09:34:36AM +0100, Jiri Olsa escreveu:
> > > Check if current kernel support available memory events
> > > and display the status within -e  list option:
> > > 
> > >   $ perf mem record -e list
> > >   [ok] ldlat-loads
> > >   [ok] ldlat-stores
> > 
> > Can't this be:
> > 
> >   $ perf mem record -e list
> >   ldlat-loads:  Available on this machine
> >   ldlat-stores: Available on this machine
> 
> Please check perf/core, I applied a good number of the patches in this
> series.

great, I'll rebase the rest and make the change
for this one in next version

thanks,
jirka

[tip:perf/core] perf tools: Make cl_address global

[tip-bot for Jiri Olsa]

Commit-ID:  e95cf700b1b267d912ee779c3ab36e582111a52d
Gitweb:     http://git.kernel.org/tip/e95cf700b1b267d912ee779c3ab36e582111a52d
Author:     Jiri Olsa <jolsa@kernel.org>
AuthorDate: Mon, 15 Feb 2016 09:34:32 +0100
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Tue, 23 Feb 2016 12:09:02 -0300

perf tools: Make cl_address global

It'll be used in following patches.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1455525293-8671-3-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/sort.c | 6 ------
 tools/perf/util/sort.h | 5 +++++
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 6d0f858..5f94ee7 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1015,12 +1015,6 @@ static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
-static inline  u64 cl_address(u64 address)
-{
-	/* return the cacheline of the address */
-	return (address & ~(cacheline_size - 1));
-}
-
 static int64_t
 sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right)
 {
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 89a1273..46f159f 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -162,6 +162,11 @@ static inline float hist_entry__get_percent_limit(struct hist_entry *he)
 	return period * 100.0 / total_period;
 }
 
+static inline u64 cl_address(u64 address)
+{
+	/* return the cacheline of the address */
+	return (address & ~(cacheline_size - 1));
+}
 
 enum sort_mode {
 	SORT_MODE__NORMAL,

[tip:perf/core] perf tools: Introduce cl_offset function

[tip-bot for Jiri Olsa]

Commit-ID:  d392711095f12942a61e2963f5ab0076ac651e73
Gitweb:     http://git.kernel.org/tip/d392711095f12942a61e2963f5ab0076ac651e73
Author:     Jiri Olsa <jolsa@kernel.org>
AuthorDate: Mon, 15 Feb 2016 09:34:33 +0100
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Tue, 23 Feb 2016 12:09:22 -0300

perf tools: Introduce cl_offset function

It'll be used in following patches.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1455525293-8671-4-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/sort.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 46f159f..5b9c624 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -168,6 +168,12 @@ static inline u64 cl_address(u64 address)
 	return (address & ~(cacheline_size - 1));
 }
 
+static inline u64 cl_offset(u64 address)
+{
+	/* return the cacheline of the address */
+	return (address & (cacheline_size - 1));
+}
+
 enum sort_mode {
 	SORT_MODE__NORMAL,
 	SORT_MODE__BRANCH,

[tip:perf/core] perf tools: Add monitored events array

[tip-bot for Jiri Olsa]

Commit-ID:  acbe613e0c03d59cab21aec3565cdb28c7df98c3
Gitweb:     http://git.kernel.org/tip/acbe613e0c03d59cab21aec3565cdb28c7df98c3
Author:     Jiri Olsa <jolsa@kernel.org>
AuthorDate: Mon, 15 Feb 2016 09:34:34 +0100
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Tue, 23 Feb 2016 12:11:06 -0300

perf tools: Add monitored events array

It will ease up configuration of memory events and addition of other
memory events in following patches.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1455525293-8671-5-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-mem.c     | 17 +++++++++--------
 tools/perf/util/Build        |  1 +
 tools/perf/util/mem-events.c | 10 ++++++++++
 tools/perf/util/mem-events.h | 19 +++++++++++++++++++
 4 files changed, 39 insertions(+), 8 deletions(-)

diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 3901700..36c56a4 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -6,6 +6,7 @@
 #include "util/tool.h"
 #include "util/session.h"
 #include "util/data.h"
+#include "util/mem-events.h"
 
 #define MEM_OPERATION_LOAD	0x1
 #define MEM_OPERATION_STORE	0x2
@@ -34,20 +35,20 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 
 	rec_argv[i++] = "record";
 
-	if (mem->operation & MEM_OPERATION_LOAD)
+	if (mem->operation & MEM_OPERATION_LOAD) {
+		perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true;
 		rec_argv[i++] = "-W";
+	}
 
 	rec_argv[i++] = "-d";
 
-	if (mem->operation & MEM_OPERATION_LOAD) {
-		rec_argv[i++] = "-e";
-		rec_argv[i++] = "cpu/mem-loads/pp";
-	}
+	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+		if (!perf_mem_events[j].record)
+			continue;
 
-	if (mem->operation & MEM_OPERATION_STORE) {
 		rec_argv[i++] = "-e";
-		rec_argv[i++] = "cpu/mem-stores/pp";
-	}
+		rec_argv[i++] = perf_mem_events[j].name;
+	};
 
 	for (j = 1; j < argc; j++, i++)
 		rec_argv[i] = argv[j];
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index a34752d..df2b690 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -82,6 +82,7 @@ libperf-y += parse-branch-options.o
 libperf-y += parse-regs-options.o
 libperf-y += term.o
 libperf-y += help-unknown-cmd.o
+libperf-y += mem-events.o
 
 libperf-$(CONFIG_LIBBPF) += bpf-loader.o
 libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
new file mode 100644
index 0000000..c6ba0a1
--- /dev/null
+++ b/tools/perf/util/mem-events.c
@@ -0,0 +1,10 @@
+#include "mem-events.h"
+
+#define E(n) { .name = n }
+
+struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
+	E("cpu/mem-loads,ldlat=30/P"),
+	E("cpu/mem-stores/P"),
+};
+
+#undef E
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
new file mode 100644
index 0000000..c97b214
--- /dev/null
+++ b/tools/perf/util/mem-events.h
@@ -0,0 +1,19 @@
+#ifndef __PERF_MEM_EVENTS_H
+#define __PERF_MEM_EVENTS_H
+
+#include <stdbool.h>
+
+struct perf_mem_event {
+	bool		record;
+	const char	*name;
+};
+
+enum {
+	PERF_MEM_EVENTS__LOAD,
+	PERF_MEM_EVENTS__STORE,
+	PERF_MEM_EVENTS__MAX,
+};
+
+extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
+
+#endif /* __PERF_MEM_EVENTS_H */

[tip:perf/core] perf mem: Add -e record option

[tip-bot for Jiri Olsa]

Commit-ID:  ce1e22b08f0728e840614d3d0fc43fd1d6b7f7a2
Gitweb:     http://git.kernel.org/tip/ce1e22b08f0728e840614d3d0fc43fd1d6b7f7a2
Author:     Jiri Olsa <jolsa@kernel.org>
AuthorDate: Mon, 15 Feb 2016 09:34:35 +0100
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Tue, 23 Feb 2016 12:15:59 -0300

perf mem: Add -e record option

Adding -e option for perf mem record command, to be able to specify
memory event directly.

Get list of available events:

  $ perf mem record -e list
  ldlat-loads
  ldlat-stores

Monitor ldlat-loads:
  $ perf mem record -e ldlat-loads true

Committer notes:

Further testing:

  # perf mem record -e ldlat-loads true
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.020 MB perf.data (10 samples) ]
  # perf evlist
  cpu/mem-loads,ldlat=30/P
  #

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1455525293-8671-6-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-mem.c     | 63 +++++++++++++++++++++++++++++++++++++++++---
 tools/perf/util/mem-events.c | 47 ++++++++++++++++++++++++++++++---
 tools/perf/util/mem-events.h |  3 +++
 3 files changed, 106 insertions(+), 7 deletions(-)

diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 36c56a4..b3f8a89 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -7,6 +7,7 @@
 #include "util/session.h"
 #include "util/data.h"
 #include "util/mem-events.h"
+#include "util/debug.h"
 
 #define MEM_OPERATION_LOAD	0x1
 #define MEM_OPERATION_STORE	0x2
@@ -22,11 +23,55 @@ struct perf_mem {
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
+static int parse_record_events(const struct option *opt,
+			       const char *str, int unset __maybe_unused)
+{
+	struct perf_mem *mem = *(struct perf_mem **)opt->value;
+	int j;
+
+	if (strcmp(str, "list")) {
+		if (!perf_mem_events__parse(str)) {
+			mem->operation = 0;
+			return 0;
+		}
+		exit(-1);
+	}
+
+	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+		struct perf_mem_event *e = &perf_mem_events[j];
+
+		fprintf(stderr, "%-20s%s",
+			e->tag, verbose ? "" : "\n");
+		if (verbose)
+			fprintf(stderr, " [%s]\n", e->name);
+	}
+	exit(0);
+}
+
+static const char * const __usage[] = {
+	"perf mem record [<options>] [<command>]",
+	"perf mem record [<options>] -- <command> [<options>]",
+	NULL
+};
+
+static const char * const *record_mem_usage = __usage;
+
 static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 {
 	int rec_argc, i = 0, j;
 	const char **rec_argv;
 	int ret;
+	struct option options[] = {
+	OPT_CALLBACK('e', "event", &mem, "event",
+		     "event selector. use 'perf mem record -e list' to list available events",
+		     parse_record_events),
+	OPT_INCR('v', "verbose", &verbose,
+		 "be more verbose (show counter open errors, etc)"),
+	OPT_END()
+	};
+
+	argc = parse_options(argc, argv, options, record_mem_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
 
 	rec_argc = argc + 7; /* max number of arguments */
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
@@ -35,10 +80,11 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 
 	rec_argv[i++] = "record";
 
-	if (mem->operation & MEM_OPERATION_LOAD) {
+	if (mem->operation & MEM_OPERATION_LOAD)
 		perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true;
+
+	if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record)
 		rec_argv[i++] = "-W";
-	}
 
 	rec_argv[i++] = "-d";
 
@@ -50,9 +96,19 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 		rec_argv[i++] = perf_mem_events[j].name;
 	};
 
-	for (j = 1; j < argc; j++, i++)
+	for (j = 0; j < argc; j++, i++)
 		rec_argv[i] = argv[j];
 
+	if (verbose > 0) {
+		pr_debug("calling: record ");
+
+		while (rec_argv[j]) {
+			pr_debug("%s ", rec_argv[j]);
+			j++;
+		}
+		pr_debug("\n");
+	}
+
 	ret = cmd_record(i, rec_argv, NULL);
 	free(rec_argv);
 	return ret;
@@ -299,7 +355,6 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
 		NULL
 	};
 
-
 	argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands,
 					mem_usage, PARSE_OPT_STOP_AT_NON_OPTION);
 
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index c6ba0a1..b1507c0 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -1,10 +1,51 @@
+#include <stddef.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
 #include "mem-events.h"
+#include "debug.h"
 
-#define E(n) { .name = n }
+#define E(t, n) { .tag = t, .name = n }
 
 struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
-	E("cpu/mem-loads,ldlat=30/P"),
-	E("cpu/mem-stores/P"),
+	E("ldlat-loads",	"cpu/mem-loads,ldlat=30/P"),
+	E("ldlat-stores",	"cpu/mem-stores/P"),
 };
 
 #undef E
+
+int perf_mem_events__parse(const char *str)
+{
+	char *tok, *saveptr = NULL;
+	bool found = false;
+	char *buf;
+	int j;
+
+	/* We need buffer that we know we can write to. */
+	buf = malloc(strlen(str) + 1);
+	if (!buf)
+		return -ENOMEM;
+
+	strcpy(buf, str);
+
+	tok = strtok_r((char *)buf, ",", &saveptr);
+
+	while (tok) {
+		for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+			struct perf_mem_event *e = &perf_mem_events[j];
+
+			if (strstr(e->tag, tok))
+				e->record = found = true;
+		}
+
+		tok = strtok_r(NULL, ",", &saveptr);
+	}
+
+	free(buf);
+
+	if (found)
+		return 0;
+
+	pr_err("failed: event '%s' not found, use '-e list' to get list of available events\n", str);
+	return -1;
+}
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index c97b214..2995bae 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -5,6 +5,7 @@
 
 struct perf_mem_event {
 	bool		record;
+	const char	*tag;
 	const char	*name;
 };
 
@@ -16,4 +17,6 @@ enum {
 
 extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
 
+int perf_mem_events__parse(const char *str);
+
 #endif /* __PERF_MEM_EVENTS_H */

[tip:perf/core] perf tools: Use ARRAY_SIZE in mem sort display functions

[tip-bot for Jiri Olsa]

Commit-ID:  b19a1b6a233ede3ffc379b49e3653d6ce80dd743
Gitweb:     http://git.kernel.org/tip/b19a1b6a233ede3ffc379b49e3653d6ce80dd743
Author:     Jiri Olsa <jolsa@kernel.org>
AuthorDate: Mon, 15 Feb 2016 09:34:42 +0100
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Tue, 23 Feb 2016 12:19:10 -0300

perf tools: Use ARRAY_SIZE in mem sort display functions

There's no need to define extra macros for that.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1455525293-8671-13-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/sort.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 5f94ee7..5388f79 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -838,7 +838,6 @@ static const char * const tlb_access[] = {
 	"Walker",
 	"Fault",
 };
-#define NUM_TLB_ACCESS (sizeof(tlb_access)/sizeof(const char *))
 
 static int hist_entry__tlb_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
@@ -860,7 +859,7 @@ static int hist_entry__tlb_snprintf(struct hist_entry *he, char *bf,
 	/* already taken care of */
 	m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS);
 
-	for (i = 0; m && i < NUM_TLB_ACCESS; i++, m >>= 1) {
+	for (i = 0; m && i < ARRAY_SIZE(tlb_access); i++, m >>= 1) {
 		if (!(m & 0x1))
 			continue;
 		if (l) {
@@ -915,7 +914,6 @@ static const char * const mem_lvl[] = {
 	"I/O",
 	"Uncached",
 };
-#define NUM_MEM_LVL (sizeof(mem_lvl)/sizeof(const char *))
 
 static int hist_entry__lvl_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
@@ -937,7 +935,7 @@ static int hist_entry__lvl_snprintf(struct hist_entry *he, char *bf,
 	/* already taken care of */
 	m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
 
-	for (i = 0; m && i < NUM_MEM_LVL; i++, m >>= 1) {
+	for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
 		if (!(m & 0x1))
 			continue;
 		if (l) {
@@ -983,7 +981,6 @@ static const char * const snoop_access[] = {
 	"Hit",
 	"HitM",
 };
-#define NUM_SNOOP_ACCESS (sizeof(snoop_access)/sizeof(const char *))
 
 static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
@@ -998,7 +995,7 @@ static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
 	if (he->mem_info)
 		m = he->mem_info->data_src.mem_snoop;
 
-	for (i = 0; m && i < NUM_SNOOP_ACCESS; i++, m >>= 1) {
+	for (i = 0; m && i < ARRAY_SIZE(snoop_access); i++, m >>= 1) {
 		if (!(m & 0x1))
 			continue;
 		if (l) {

[tip:perf/core] perf script: Add data_src and weight column definitions

[tip-bot for Jiri Olsa]

Commit-ID:  94ddddfab521423d94d6066879b514b9431e5cae
Gitweb:     http://git.kernel.org/tip/94ddddfab521423d94d6066879b514b9431e5cae
Author:     Jiri Olsa <jolsa@kernel.org>
AuthorDate: Mon, 15 Feb 2016 09:34:51 +0100
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Tue, 23 Feb 2016 12:20:02 -0300

perf script: Add data_src and weight column definitions

Adding data_src and weight column definitions, so it's displayed for
related sample types.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1455525293-8671-22-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-script.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c691214..b7f1e8e 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -58,6 +58,8 @@ enum perf_output_field {
 	PERF_OUTPUT_IREGS	    = 1U << 14,
 	PERF_OUTPUT_BRSTACK	    = 1U << 15,
 	PERF_OUTPUT_BRSTACKSYM	    = 1U << 16,
+	PERF_OUTPUT_DATA_SRC	    = 1U << 17,
+	PERF_OUTPUT_WEIGHT	    = 1U << 18,
 };
 
 struct output_option {
@@ -81,6 +83,8 @@ struct output_option {
 	{.str = "iregs", .field = PERF_OUTPUT_IREGS},
 	{.str = "brstack", .field = PERF_OUTPUT_BRSTACK},
 	{.str = "brstacksym", .field = PERF_OUTPUT_BRSTACKSYM},
+	{.str = "data_src", .field = PERF_OUTPUT_DATA_SRC},
+	{.str = "weight",   .field = PERF_OUTPUT_WEIGHT},
 };
 
 /* default set to maintain compatibility with current format */
@@ -242,6 +246,16 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 					   PERF_OUTPUT_ADDR, allow_user_set))
 		return -EINVAL;
 
+	if (PRINT_FIELD(DATA_SRC) &&
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC",
+					PERF_OUTPUT_DATA_SRC))
+		return -EINVAL;
+
+	if (PRINT_FIELD(WEIGHT) &&
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT, "WEIGHT",
+					PERF_OUTPUT_WEIGHT))
+		return -EINVAL;
+
 	if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
 		pr_err("Display of symbols requested but neither sample IP nor "
 			   "sample address\nis selected. Hence, no addresses to convert "
@@ -673,6 +687,12 @@ static void process_event(struct perf_script *script, union perf_event *event,
 	if (PRINT_FIELD(ADDR))
 		print_sample_addr(event, sample, thread, attr);
 
+	if (PRINT_FIELD(DATA_SRC))
+		printf("%16" PRIx64, sample->data_src);
+
+	if (PRINT_FIELD(WEIGHT))
+		printf("%16" PRIu64, sample->weight);
+
 	if (PRINT_FIELD(IP)) {
 		if (!symbol_conf.use_callchain)
 			printf(" ");

[tip:perf/core] perf script: Display addr/data_src/weight columns for raw events

[tip-bot for Jiri Olsa]

Commit-ID:  ff7b191583c368612fde88bf3cff6e3f3b0d73d5
Gitweb:     http://git.kernel.org/tip/ff7b191583c368612fde88bf3cff6e3f3b0d73d5
Author:     Jiri Olsa <jolsa@kernel.org>
AuthorDate: Mon, 15 Feb 2016 09:34:52 +0100
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Tue, 23 Feb 2016 12:20:21 -0300

perf script: Display addr/data_src/weight columns for raw events

Adding addr/data_src/weight columns for raw events.

Example:
  $ perf script
  ...
  true 11883 322960.489590: ...  ffff8801aa0b8400        68501042             246 ffffffff813b2cd
  true 11883 322960.489600: ...  ffff8800b90b38d8        68501042             251 ffffffff811d0b7
  true 11883 322960.489612: ...  ffff880196893130        6a100142              94 ffffffff8177fb8
  true 11883 322960.489637: ...  ffff880164277b40        68100842             101 ffffffff813b2cd
  true 11883 322960.489683: ...  ffff880035d3d818        68501042             201 ffffffff811d0b7
  true 11883 322960.489733: ...      7fb9616efcf0        68100242             199     7fb961aaba9
  true 11883 322960.489818: ...  ffffea000481c39c        6a100142             122 ffffffff811b634

                                 ^^^^^^^^^^^^^^^^        ^^^^^^^^             ^^^
                                             addr        data_src          weight

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1455525293-8671-23-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-script.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index b7f1e8e..f4caf48 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -135,7 +135,8 @@ static struct {
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
 			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_PERIOD,
+			      PERF_OUTPUT_PERIOD |  PERF_OUTPUT_ADDR |
+			      PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT,
 
 		.invalid_fields = PERF_OUTPUT_TRACE,
 	},