Merge branch 'perf/core' of git://git.kernel.org/pub/scm/linux/kernel…

…/git/acme/linux-2.6 into perf/core

Makefile

@@ -411,7 +411,7 @@ endif
 no-dot-config-targets := clean mrproper distclean \
 			 cscope TAGS tags help %docs check% \
 			 include/linux/version.h headers_% \
-			 kernelrelease kernelversion
+			 kernelrelease kernelversion %src-pkg
 
 config-targets := 0
 mixed-targets  := 0
@@ -1215,6 +1215,8 @@ distclean: mrproper
 # rpm target kept for backward compatibility
 package-dir	:= $(srctree)/scripts/package
 
+%src-pkg: FORCE
+	$(Q)$(MAKE) $(build)=$(package-dir) $@
 %pkg: include/config/kernel.release FORCE
 	$(Q)$(MAKE) $(build)=$(package-dir) $@
 rpm: include/config/kernel.release FORCE

scripts/package/Makefile

@@ -111,13 +111,38 @@ tar%pkg: FORCE
 clean-dirs += $(objtree)/tar-install/
 
 
+# perf-pkg - generate a source tarball with perf source
+# ---------------------------------------------------------------------------
+
+perf-tar=perf-$(KERNELVERSION)
+
+quiet_cmd_perf_tar = TAR
+      cmd_perf_tar = \
+git archive --prefix=$(perf-tar)/ HEAD^{tree}                       \
+	$$(cat $(srctree)/tools/perf/MANIFEST) -o $(perf-tar).tar;  \
+mkdir -p $(perf-tar);                                               \
+git rev-parse HEAD > $(perf-tar)/HEAD;                              \
+tar rf $(perf-tar).tar $(perf-tar)/HEAD;                            \
+rm -r $(perf-tar);                                                  \
+$(if $(findstring tar-src,$@),,                                     \
+$(if $(findstring bz2,$@),bzip2,                                    \
+$(if $(findstring gz,$@),gzip,                                      \
+$(error unknown target $@)))                                       \
+	-f -9 $(perf-tar).tar)
+
+perf-%pkg: FORCE
+	$(call cmd,perf_tar)
+
 # Help text displayed when executing 'make help'
 # ---------------------------------------------------------------------------
 help: FORCE
-	@echo '  rpm-pkg         - Build both source and binary RPM kernel packages'
-	@echo '  binrpm-pkg      - Build only the binary kernel package'
-	@echo '  deb-pkg         - Build the kernel as an deb package'
-	@echo '  tar-pkg         - Build the kernel as an uncompressed tarball'
-	@echo '  targz-pkg       - Build the kernel as a gzip compressed tarball'
-	@echo '  tarbz2-pkg      - Build the kernel as a bzip2 compressed tarball'
+	@echo '  rpm-pkg             - Build both source and binary RPM kernel packages'
+	@echo '  binrpm-pkg          - Build only the binary kernel package'
+	@echo '  deb-pkg             - Build the kernel as an deb package'
+	@echo '  tar-pkg             - Build the kernel as an uncompressed tarball'
+	@echo '  targz-pkg           - Build the kernel as a gzip compressed tarball'
+	@echo '  tarbz2-pkg          - Build the kernel as a bzip2 compressed tarball'
+	@echo '  perf-tar-src-pkg    - Build $(perf-tar).tar source tarball'
+	@echo '  perf-targz-src-pkg  - Build $(perf-tar).tar.gz source tarball'
+	@echo '  perf-tarbz2-src-pkg - Build $(perf-tar).tar.bz2 source tarball'
 

tools/perf/Documentation/perf-record.txt

@@ -103,6 +103,13 @@ OPTIONS
 --raw-samples::
 Collect raw sample records from all opened counters (default for tracepoint counters).
 
+-C::
+--cpu::
+Collect samples only on the list of cpus provided. Multiple CPUs can be provided as a
+comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+In per-thread mode with inheritance mode on (default), samples are captured only when
+the thread executes on the designated CPUs. Default is to monitor all CPUs.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]

tools/perf/Documentation/perf-stat.txt

@@ -46,6 +46,13 @@ OPTIONS
 -B::
         print large numbers with thousands' separators according to locale
 
+-C::
+--cpu=::
+Count only on the list of cpus provided. Multiple CPUs can be provided as a
+comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+In per-thread mode, this option is ignored. The -a option is still necessary
+to activate system-wide monitoring. Default is to count on all CPUs.
+
 EXAMPLES
 --------
 

tools/perf/Documentation/perf-top.txt

@@ -25,9 +25,11 @@ OPTIONS
 --count=<count>::
 	Event period to sample.
 
--C <cpu>::
---CPU=<cpu>::
-	CPU to profile.
+-C <cpu-list>::
+--cpu=<cpu>::
+Monitor only on the list of cpus provided. Multiple CPUs can be provided as a
+comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+Default is to monitor all CPUS.
 
 -d <seconds>::
 --delay=<seconds>::

tools/perf/MANIFEST

@@ -0,0 +1,12 @@
+tools/perf
+include/linux/perf_event.h
+include/linux/rbtree.h
+include/linux/list.h
+include/linux/hash.h
+include/linux/stringify.h
+lib/rbtree.c
+include/linux/swab.h
+arch/*/include/asm/unistd*.h
+include/linux/poison.h
+include/linux/magic.h
+include/linux/hw_breakpoint.h

tools/perf/builtin-annotate.c

@@ -61,11 +61,9 @@ static int hists__add_entry(struct hists *self, struct addr_location *al)
 static int process_sample_event(event_t *event, struct perf_session *session)
 {
 	struct addr_location al;
+	struct sample_data data;
 
-	dump_printf("(IP, %d): %d: %#Lx\n", event->header.misc,
-		    event->ip.pid, event->ip.ip);
-
-	if (event__preprocess_sample(event, session, &al, NULL) < 0) {
+	if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) {
 		pr_warning("problem processing %d event, skipping it.\n",
 			   event->header.type);
 		return -1;

tools/perf/builtin-buildid-cache.c

@@ -78,8 +78,7 @@ static int __cmd_buildid_cache(void)
 	struct str_node *pos;
 	char debugdir[PATH_MAX];
 
-	snprintf(debugdir, sizeof(debugdir), "%s/%s", getenv("HOME"),
-		 DEBUG_CACHE_DIR);
+	snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir);
 
 	if (add_name_list_str) {
 		list = strlist__new(true, add_name_list_str);

tools/perf/builtin-diff.c

@@ -35,10 +35,7 @@ static int diff__process_sample_event(event_t *event, struct perf_session *sessi
 	struct addr_location al;
 	struct sample_data data = { .period = 1, };
 
-	dump_printf("(IP, %d): %d: %#Lx\n", event->header.misc,
-		    event->ip.pid, event->ip.ip);
-
-	if (event__preprocess_sample(event, session, &al, NULL) < 0) {
+	if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) {
 		pr_warning("problem processing %d event, skipping it.\n",
 			   event->header.type);
 		return -1;
@@ -47,8 +44,6 @@ static int diff__process_sample_event(event_t *event, struct perf_session *sessi
 	if (al.filtered || al.sym == NULL)
 		return 0;
 
-	event__parse_sample(event, session->sample_type, &data);
-
 	if (hists__add_entry(&session->hists, &al, data.period)) {
 		pr_warning("problem incrementing symbol period, skipping event\n");
 		return -1;

tools/perf/builtin-record.c

@@ -49,7 +49,6 @@ static int			group				=      0;
 static int			realtime_prio			=      0;
 static bool			raw_samples			=  false;
 static bool			system_wide			=  false;
-static int			profile_cpu			=     -1;
 static pid_t			target_pid			=     -1;
 static pid_t			target_tid			=     -1;
 static pid_t			*all_tids			=      NULL;
@@ -74,6 +73,7 @@ static int			file_new			=      1;
 static off_t			post_processing_offset;
 
 static struct perf_session	*session;
+static const char		*cpu_list;
 
 struct mmap_data {
 	int			counter;
@@ -274,6 +274,9 @@ static void create_counter(int counter, int cpu)
 	if (call_graph)
 		attr->sample_type	|= PERF_SAMPLE_CALLCHAIN;
 
+	if (system_wide)
+		attr->sample_type	|= PERF_SAMPLE_CPU;
+
 	if (raw_samples) {
 		attr->sample_type	|= PERF_SAMPLE_TIME;
 		attr->sample_type	|= PERF_SAMPLE_RAW;
@@ -300,7 +303,7 @@ static void create_counter(int counter, int cpu)
 				die("Permission error - are you root?\n"
 					"\t Consider tweaking"
 					" /proc/sys/kernel/perf_event_paranoid.\n");
-			else if (err ==  ENODEV && profile_cpu != -1) {
+			else if (err ==  ENODEV && cpu_list) {
 				die("No such device - did you specify"
 					" an out-of-range profile CPU?\n");
 			}
@@ -622,10 +625,15 @@ static int __cmd_record(int argc, const char **argv)
 		close(child_ready_pipe[0]);
 	}
 
-	if ((!system_wide && no_inherit) || profile_cpu != -1) {
-		open_counters(profile_cpu);
+	nr_cpus = read_cpu_map(cpu_list);
+	if (nr_cpus < 1) {
+		perror("failed to collect number of CPUs\n");
+		return -1;
+	}
+
+	if (!system_wide && no_inherit && !cpu_list) {
+		open_counters(-1);
 	} else {
-		nr_cpus = read_cpu_map();
 		for (i = 0; i < nr_cpus; i++)
 			open_counters(cpumap[i]);
 	}
@@ -704,7 +712,7 @@ static int __cmd_record(int argc, const char **argv)
 	if (perf_guest)
 		perf_session__process_machines(session, event__synthesize_guest_os);
 
-	if (!system_wide && profile_cpu == -1)
+	if (!system_wide && cpu_list)
 		event__synthesize_thread(target_tid, process_synthesized_event,
 					 session);
 	else
@@ -794,8 +802,8 @@ static const struct option options[] = {
 			    "system-wide collection from all CPUs"),
 	OPT_BOOLEAN('A', "append", &append_file,
 			    "append to the output file to do incremental profiling"),
-	OPT_INTEGER('C', "profile_cpu", &profile_cpu,
-			    "CPU to profile on"),
+	OPT_STRING('C', "cpu", &cpu_list, "cpu",
+		    "list of cpus to monitor"),
 	OPT_BOOLEAN('f', "force", &force,
 			"overwrite existing data file (deprecated)"),
 	OPT_U64('c', "count", &user_interval, "event period to sample"),
@@ -825,7 +833,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 	argc = parse_options(argc, argv, options, record_usage,
 			    PARSE_OPT_STOP_AT_NON_OPTION);
 	if (!argc && target_pid == -1 && target_tid == -1 &&
-		!system_wide && profile_cpu == -1)
+		!system_wide && !cpu_list)
 		usage_with_options(record_usage, options);
 
 	if (force && append_file) {

tools/perf/builtin-report.c

@@ -155,30 +155,7 @@ static int process_sample_event(event_t *event, struct perf_session *session)
 	struct addr_location al;
 	struct perf_event_attr *attr;
 
-	event__parse_sample(event, session->sample_type, &data);
-
-	dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc,
-		    data.pid, data.tid, data.ip, data.period);
-
-	if (session->sample_type & PERF_SAMPLE_CALLCHAIN) {
-		unsigned int i;
-
-		dump_printf("... chain: nr:%Lu\n", data.callchain->nr);
-
-		if (!ip_callchain__valid(data.callchain, event)) {
-			pr_debug("call-chain problem with event, "
-				 "skipping it.\n");
-			return 0;
-		}
-
-		if (dump_trace) {
-			for (i = 0; i < data.callchain->nr; i++)
-				dump_printf("..... %2d: %016Lx\n",
-					    i, data.callchain->ips[i]);
-		}
-	}
-
-	if (event__preprocess_sample(event, session, &al, NULL) < 0) {
+	if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) {
 		fprintf(stderr, "problem processing %d event, skipping it.\n",
 			event->header.type);
 		return -1;

tools/perf/builtin-stat.c

@@ -69,7 +69,7 @@ static struct perf_event_attr default_attrs[] = {
 };
 
 static bool			system_wide			=  false;
-static unsigned int		nr_cpus				=  0;
+static int			nr_cpus				=  0;
 static int			run_idx				=  0;
 
 static int			run_count			=  1;
@@ -82,6 +82,7 @@ static int			thread_num			=  0;
 static pid_t			child_pid			= -1;
 static bool			null_run			=  false;
 static bool			big_num				=  false;
+static const char		*cpu_list;
 
 
 static int			*fd[MAX_NR_CPUS][MAX_COUNTERS];
@@ -158,7 +159,7 @@ static int create_perf_stat_counter(int counter)
 				    PERF_FORMAT_TOTAL_TIME_RUNNING;
 
 	if (system_wide) {
-		unsigned int cpu;
+		int cpu;
 
 		for (cpu = 0; cpu < nr_cpus; cpu++) {
 			fd[cpu][counter][0] = sys_perf_event_open(attr,
@@ -208,7 +209,7 @@ static inline int nsec_counter(int counter)
 static void read_counter(int counter)
 {
 	u64 count[3], single_count[3];
-	unsigned int cpu;
+	int cpu;
 	size_t res, nv;
 	int scaled;
 	int i, thread;
@@ -542,6 +543,8 @@ static const struct option options[] = {
 		    "null run - dont start any counters"),
 	OPT_BOOLEAN('B', "big-num", &big_num,
 		    "print large numbers with thousands\' separators"),
+	OPT_STRING('C', "cpu", &cpu_list, "cpu",
+		    "list of cpus to monitor in system-wide"),
 	OPT_END()
 };
 
@@ -566,10 +569,13 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 	}
 
 	if (system_wide)
-		nr_cpus = read_cpu_map();
+		nr_cpus = read_cpu_map(cpu_list);
 	else
 		nr_cpus = 1;
 
+	if (nr_cpus < 1)
+		usage_with_options(stat_usage, options);
+
 	if (target_pid != -1) {
 		target_tid = target_pid;
 		thread_num = find_all_tid(target_pid, &all_tids);