Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "Features:

   - Add "uretprobes" - an optimization to uprobes, like kretprobes are
     an optimization to kprobes.  "perf probe -x file sym%return" now
     works like kretprobes.  By Oleg Nesterov.

   - Introduce per core aggregation in 'perf stat', from Stephane
     Eranian.

   - Add memory profiling via PEBS, from Stephane Eranian.

   - Event group view for 'annotate' in --stdio, --tui and --gtk, from
     Namhyung Kim.

   - Add support for AMD NB and L2I "uncore" counters, by Jacob Shin.

   - Add Ivy Bridge-EP uncore support, by Zheng Yan

   - IBM zEnterprise EC12 oprofile support patchlet from Robert Richter.

   - Add perf test entries for checking breakpoint overflow signal
     handler issues, from Jiri Olsa.

   - Add perf test entry for for checking number of EXIT events, from
     Namhyung Kim.

   - Add perf test entries for checking --cpu in record and stat, from
     Jiri Olsa.

   - Introduce perf stat --repeat forever, from Frederik Deweerdt.

   - Add --no-demangle to report/top, from Namhyung Kim.

   - PowerPC fixes plus a couple of cleanups/optimizations in uprobes
     and trace_uprobes, by Oleg Nesterov.

  Various fixes and refactorings:

   - Fix dependency of the python binding wrt libtraceevent, from
     Naohiro Aota.

   - Simplify some perf_evlist methods and to allow 'stat' to share code
     with 'record' and 'trace', by Arnaldo Carvalho de Melo.

   - Remove dead code in related to libtraceevent integration, from
     Namhyung Kim.

   - Revert "perf sched: Handle PERF_RECORD_EXIT events" to get 'perf
     sched lat' back working, by Arnaldo Carvalho de Melo

   - We don't use Newt anymore, just plain libslang, by Arnaldo Carvalho
     de Melo.

   - Kill a bunch of die() calls, from Namhyung Kim.

   - Fix build on non-glibc systems due to libio.h absence, from Cody P
     Schafer.

   - Remove some perf_session and tracing dead code, from David Ahern.

   - Honor parallel jobs, fix from Borislav Petkov

   - Introduce tools/lib/lk library, initially just removing duplication
     among tools/perf and tools/vm.  from Borislav Petkov

  ... and many more I missed to list, see the shortlog and git log for
  more details."

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (136 commits)
  perf/x86/intel/P4: Robistify P4 PMU types
  perf/x86/amd: Fix AMD NB and L2I "uncore" support
  perf/x86/amd: Remove old-style NB counter support from perf_event_amd.c
  perf/x86: Check all MSRs before passing hw check
  perf/x86/amd: Add support for AMD NB and L2I "uncore" counters
  perf/x86/intel: Add Ivy Bridge-EP uncore support
  perf/x86/intel: Fix SNB-EP CBO and PCU uncore PMU filter management
  perf/x86: Avoid kfree() in CPU_{STARTING,DYING}
  uprobes/perf: Avoid perf_trace_buf_prepare/submit if ->perf_events is empty
  uprobes/tracing: Don't pass addr=ip to perf_trace_buf_submit()
  uprobes/tracing: Change create_trace_uprobe() to support uretprobes
  uprobes/tracing: Make seq_printf() code uretprobe-friendly
  uprobes/tracing: Make register_uprobe_event() paths uretprobe-friendly
  uprobes/tracing: Make uprobe_{trace,perf}_print() uretprobe-friendly
  uprobes/tracing: Introduce is_ret_probe() and uretprobe_dispatcher()
  uprobes/tracing: Introduce uprobe_{trace,perf}_print() helpers
  uprobes/tracing: Generalize struct uprobe_trace_entry_head
  uprobes/tracing: Kill the pointless local_save_flags/preempt_count calls
  uprobes/tracing: Kill the pointless seq_print_ip_sym() call
  uprobes/tracing: Kill the pointless task_pt_regs() calls
  ...

1 files changed, 44 insertions, 29 deletions

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c8be0fbc5145..f7c727801aab 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -7,7 +7,7 @@
  * Released under the GPL v2. (and only v2, not any later version)
  */
 #include "util.h"
-#include "debugfs.h"
+#include <lk/debugfs.h>
 #include <poll.h>
 #include "cpumap.h"
 #include "thread_map.h"
@@ -38,13 +38,12 @@ void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
 	evlist->workload.pid = -1;
 }
 
-struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
-				     struct thread_map *threads)
+struct perf_evlist *perf_evlist__new(void)
 {
 	struct perf_evlist *evlist = zalloc(sizeof(*evlist));
 
 	if (evlist != NULL)
-		perf_evlist__init(evlist, cpus, threads);
+		perf_evlist__init(evlist, NULL, NULL);
 
 	return evlist;
 }
@@ -228,12 +227,14 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 {
 	int cpu, thread;
 	struct perf_evsel *pos;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = thread_map__nr(evlist->threads);
 
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		list_for_each_entry(pos, &evlist->entries, node) {
 			if (!perf_evsel__is_group_leader(pos))
 				continue;
-			for (thread = 0; thread < evlist->threads->nr; thread++)
+			for (thread = 0; thread < nr_threads; thread++)
 				ioctl(FD(pos, cpu, thread),
 				      PERF_EVENT_IOC_DISABLE, 0);
 		}
@@ -244,12 +245,14 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 {
 	int cpu, thread;
 	struct perf_evsel *pos;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = thread_map__nr(evlist->threads);
 
-	for (cpu = 0; cpu < cpu_map__nr(evlist->cpus); cpu++) {
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		list_for_each_entry(pos, &evlist->entries, node) {
 			if (!perf_evsel__is_group_leader(pos))
 				continue;
-			for (thread = 0; thread < evlist->threads->nr; thread++)
+			for (thread = 0; thread < nr_threads; thread++)
 				ioctl(FD(pos, cpu, thread),
 				      PERF_EVENT_IOC_ENABLE, 0);
 		}
@@ -258,7 +261,9 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 
 static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
-	int nfds = cpu_map__nr(evlist->cpus) * evlist->threads->nr * evlist->nr_entries;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = thread_map__nr(evlist->threads);
+	int nfds = nr_cpus * nr_threads * evlist->nr_entries;
 	evlist->pollfd = malloc(sizeof(struct pollfd) * nfds);
 	return evlist->pollfd != NULL ? 0 : -ENOMEM;
 }
@@ -417,7 +422,7 @@ static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 {
 	evlist->nr_mmaps = cpu_map__nr(evlist->cpus);
 	if (cpu_map__all(evlist->cpus))
-		evlist->nr_mmaps = evlist->threads->nr;
+		evlist->nr_mmaps = thread_map__nr(evlist->threads);
 	evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
 	return evlist->mmap != NULL ? 0 : -ENOMEM;
 }
@@ -442,11 +447,13 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m
 {
 	struct perf_evsel *evsel;
 	int cpu, thread;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = thread_map__nr(evlist->threads);
 
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		int output = -1;
 
-		for (thread = 0; thread < evlist->threads->nr; thread++) {
+		for (thread = 0; thread < nr_threads; thread++) {
 			list_for_each_entry(evsel, &evlist->entries, node) {
 				int fd = FD(evsel, cpu, thread);
 
@@ -470,7 +477,7 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m
 	return 0;
 
 out_unmap:
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		if (evlist->mmap[cpu].base != NULL) {
 			munmap(evlist->mmap[cpu].base, evlist->mmap_len);
 			evlist->mmap[cpu].base = NULL;
@@ -483,8 +490,9 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in
 {
 	struct perf_evsel *evsel;
 	int thread;
+	int nr_threads = thread_map__nr(evlist->threads);
 
-	for (thread = 0; thread < evlist->threads->nr; thread++) {
+	for (thread = 0; thread < nr_threads; thread++) {
 		int output = -1;
 
 		list_for_each_entry(evsel, &evlist->entries, node) {
@@ -509,7 +517,7 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in
 	return 0;
 
 out_unmap:
-	for (thread = 0; thread < evlist->threads->nr; thread++) {
+	for (thread = 0; thread < nr_threads; thread++) {
 		if (evlist->mmap[thread].base != NULL) {
 			munmap(evlist->mmap[thread].base, evlist->mmap_len);
 			evlist->mmap[thread].base = NULL;
@@ -610,7 +618,7 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist)
 	struct perf_evsel *evsel;
 	int err = 0;
 	const int ncpus = cpu_map__nr(evlist->cpus),
-		  nthreads = evlist->threads->nr;
+		  nthreads = thread_map__nr(evlist->threads);
 
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		if (evsel->filter == NULL)
@@ -629,7 +637,7 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
 	struct perf_evsel *evsel;
 	int err = 0;
 	const int ncpus = cpu_map__nr(evlist->cpus),
-		  nthreads = evlist->threads->nr;
+		  nthreads = thread_map__nr(evlist->threads);
 
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		err = perf_evsel__set_filter(evsel, ncpus, nthreads, filter);
@@ -712,10 +720,20 @@ void perf_evlist__set_selected(struct perf_evlist *evlist,
 	evlist->selected = evsel;
 }
 
+void perf_evlist__close(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	int ncpus = cpu_map__nr(evlist->cpus);
+	int nthreads = thread_map__nr(evlist->threads);
+
+	list_for_each_entry_reverse(evsel, &evlist->entries, node)
+		perf_evsel__close(evsel, ncpus, nthreads);
+}
+
 int perf_evlist__open(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
-	int err, ncpus, nthreads;
+	int err;
 
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		err = perf_evsel__open(evsel, evlist->cpus, evlist->threads);
@@ -725,19 +743,15 @@ int perf_evlist__open(struct perf_evlist *evlist)
 
 	return 0;
 out_err:
-	ncpus = evlist->cpus ? evlist->cpus->nr : 1;
-	nthreads = evlist->threads ? evlist->threads->nr : 1;
-
-	list_for_each_entry_reverse(evsel, &evlist->entries, node)
-		perf_evsel__close(evsel, ncpus, nthreads);
-
+	perf_evlist__close(evlist);
 	errno = -err;
 	return err;
 }
 
 int perf_evlist__prepare_workload(struct perf_evlist *evlist,
-				  struct perf_record_opts *opts,
-				  const char *argv[])
+				  struct perf_target *target,
+				  const char *argv[], bool pipe_output,
+				  bool want_signal)
 {
 	int child_ready_pipe[2], go_pipe[2];
 	char bf;
@@ -759,7 +773,7 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist,
 	}
 
 	if (!evlist->workload.pid) {
-		if (opts->pipe_output)
+		if (pipe_output)
 			dup2(2, 1);
 
 		close(child_ready_pipe[0]);
@@ -787,11 +801,12 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist,
 		execvp(argv[0], (char **)argv);
 
 		perror(argv[0]);
-		kill(getppid(), SIGUSR1);
+		if (want_signal)
+			kill(getppid(), SIGUSR1);
 		exit(-1);
 	}
 
-	if (perf_target__none(&opts->target))
+	if (perf_target__none(target))
 		evlist->threads->map[0] = evlist->workload.pid;
 
 	close(child_ready_pipe[1]);