Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux…

…/kernel/git/acme/linux into perf/urgent

Pull perf/core fixes and some late updates from Arnaldo Carvalho de Melo:

 * Make clean brace expansion fix for some shells, from Palmer Cox

 * Warn user just once per guest kernel when not finding kernel info,
   from David Ahern

 * perf test fix from Jiri Olsa

 * Fix error handling on event creation in perf top, from David Ahern

 * Fix check on perf_target__strnerror, from Namhyung Kim

 * Save the whole cmdline, from David Ahern

 * Prep work for the DWARF CFI post unwinder, so that it doesn't
   uses perf_session in lots of places, just evlist/evsel is enough.

Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>

tools/perf/Makefile

@@ -319,6 +319,8 @@ LIB_H += $(ARCH_INCLUDE)
 LIB_H += util/cgroup.h
 LIB_H += $(TRACE_EVENT_DIR)event-parse.h
 LIB_H += util/target.h
+LIB_H += util/rblist.h
+LIB_H += util/intlist.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -383,6 +385,8 @@ LIB_OBJS += $(OUTPUT)util/xyarray.o
 LIB_OBJS += $(OUTPUT)util/cpumap.o
 LIB_OBJS += $(OUTPUT)util/cgroup.o
 LIB_OBJS += $(OUTPUT)util/target.o
+LIB_OBJS += $(OUTPUT)util/rblist.o
+LIB_OBJS += $(OUTPUT)util/intlist.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 
@@ -983,7 +987,8 @@ clean:
 	$(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope*
 	$(MAKE) -C Documentation/ clean
 	$(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS
-	$(RM) $(OUTPUT)util/*-{bison,flex}*
+	$(RM) $(OUTPUT)util/*-bison*
+	$(RM) $(OUTPUT)util/*-flex*
 	$(python-clean)
 
 .PHONY: all install clean strip $(LIBTRACEEVENT)

tools/perf/builtin-record.c

@@ -313,7 +313,7 @@ static void perf_record__open(struct perf_record *rec)
 		}
  	}
 
-	perf_session__update_sample_type(session);
+	perf_session__set_id_hdr_size(session);
 }
 
 static int process_buildids(struct perf_record *rec)
@@ -844,8 +844,6 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 	struct perf_record *rec = &record;
 	char errbuf[BUFSIZ];
 
-	perf_header__set_cmdline(argc, argv);
-
 	evsel_list = perf_evlist__new(NULL, NULL);
 	if (evsel_list == NULL)
 		return -ENOMEM;

tools/perf/builtin-report.c

@@ -249,8 +249,9 @@ static int process_read_event(struct perf_tool *tool,
 static int perf_report__setup_sample_type(struct perf_report *rep)
 {
 	struct perf_session *self = rep->session;
+	u64 sample_type = perf_evlist__sample_type(self->evlist);
 
-	if (!self->fd_pipe && !(self->sample_type & PERF_SAMPLE_CALLCHAIN)) {
+	if (!self->fd_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
 		if (sort__has_parent) {
 			ui__error("Selected --sort parent, but no "
 				    "callchain data. Did you call "
@@ -274,7 +275,7 @@ static int perf_report__setup_sample_type(struct perf_report *rep)
 
 	if (sort__branch_mode == 1) {
 		if (!self->fd_pipe &&
-		    !(self->sample_type & PERF_SAMPLE_BRANCH_STACK)) {
+		    !(sample_type & PERF_SAMPLE_BRANCH_STACK)) {
 			ui__error("Selected -b but no branch data. "
 				  "Did you call perf record without -b?\n");
 			return -1;

tools/perf/builtin-test.c

@@ -478,7 +478,6 @@ static int test__basic_mmap(void)
 	unsigned int nr_events[nsyscalls],
 		     expected_nr_events[nsyscalls], i, j;
 	struct perf_evsel *evsels[nsyscalls], *evsel;
-	int sample_size = __perf_evsel__sample_size(attr.sample_type);
 
 	for (i = 0; i < nsyscalls; ++i) {
 		char name[64];
@@ -563,8 +562,7 @@ static int test__basic_mmap(void)
 			goto out_munmap;
 		}
 
-		err = perf_event__parse_sample(event, attr.sample_type, sample_size,
-					       false, &sample, false);
+		err = perf_evlist__parse_sample(evlist, event, &sample, false);
 		if (err) {
 			pr_err("Can't parse sample, err = %d\n", err);
 			goto out_munmap;
@@ -661,12 +659,12 @@ static int test__PERF_RECORD(void)
 	const char *cmd = "sleep";
 	const char *argv[] = { cmd, "1", NULL, };
 	char *bname;
-	u64 sample_type, prev_time = 0;
+	u64 prev_time = 0;
 	bool found_cmd_mmap = false,
 	     found_libc_mmap = false,
 	     found_vdso_mmap = false,
 	     found_ld_mmap = false;
-	int err = -1, errs = 0, i, wakeups = 0, sample_size;
+	int err = -1, errs = 0, i, wakeups = 0;
 	u32 cpu;
 	int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, };
 
@@ -756,13 +754,6 @@ static int test__PERF_RECORD(void)
 		goto out_delete_evlist;
 	}
 
-	/*
-	 * We'll need these two to parse the PERF_SAMPLE_* fields in each
-	 * event.
-	 */
-	sample_type = perf_evlist__sample_type(evlist);
-	sample_size = __perf_evsel__sample_size(sample_type);
-
 	/*
 	 * Now that all is properly set up, enable the events, they will
 	 * count just on workload.pid, which will start...
@@ -788,9 +779,7 @@ static int test__PERF_RECORD(void)
 				if (type < PERF_RECORD_MAX)
 					nr_events[type]++;
 
-				err = perf_event__parse_sample(event, sample_type,
-							       sample_size, true,
-							       &sample, false);
+				err = perf_evlist__parse_sample(evlist, event, &sample, false);
 				if (err < 0) {
 					if (verbose)
 						perf_event__fprintf(event, stderr);

tools/perf/builtin-top.c

@@ -38,6 +38,7 @@
 #include "util/cpumap.h"
 #include "util/xyarray.h"
 #include "util/sort.h"
+#include "util/intlist.h"
 
 #include "util/debug.h"
 
@@ -706,8 +707,16 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	int err;
 
 	if (!machine && perf_guest) {
-		pr_err("Can't find guest [%d]'s kernel information\n",
-			event->ip.pid);
+		static struct intlist *seen;
+
+		if (!seen)
+			seen = intlist__new();
+
+		if (!intlist__has_entry(seen, event->ip.pid)) {
+			pr_err("Can't find guest [%d]'s kernel information\n",
+				event->ip.pid);
+			intlist__add(seen, event->ip.pid);
+		}
 		return;
 	}
 
@@ -811,7 +820,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 	int ret;
 
 	while ((event = perf_evlist__mmap_read(top->evlist, idx)) != NULL) {
-		ret = perf_session__parse_sample(session, event, &sample);
+		ret = perf_evlist__parse_sample(top->evlist, event, &sample, false);
 		if (ret) {
 			pr_err("Can't parse sample, err = %d\n", ret);
 			continue;
@@ -943,8 +952,10 @@ static void perf_top__start_counters(struct perf_top *top)
 			 * based cpu-clock-tick sw counter, which
 			 * is always available even if no PMU support:
 			 */
-			if (attr->type == PERF_TYPE_HARDWARE &&
-			    attr->config == PERF_COUNT_HW_CPU_CYCLES) {
+			if ((err == ENOENT || err == ENXIO) &&
+			    (attr->type == PERF_TYPE_HARDWARE) &&
+			    (attr->config == PERF_COUNT_HW_CPU_CYCLES)) {
+
 				if (verbose)
 					ui__warning("Cycles event not supported,\n"
 						    "trying to fall back to cpu-clock-ticks\n");
@@ -1032,7 +1043,7 @@ static int __cmd_top(struct perf_top *top)
 					       &top->session->host_machine);
 	perf_top__start_counters(top);
 	top->session->evlist = top->evlist;
-	perf_session__update_sample_type(top->session);
+	perf_session__set_id_hdr_size(top->session);
 
 	/* Wait for a minimal set of events before starting the snapshot */
 	poll(top->evlist->pollfd, top->evlist->nr_fds, 100);

tools/perf/util/event.h

@@ -197,9 +197,6 @@ int perf_event__preprocess_sample(const union perf_event *self,
 
 const char *perf_event__name(unsigned int id);
 
-int perf_event__parse_sample(const union perf_event *event, u64 type,
-			     int sample_size, bool sample_id_all,
-			     struct perf_sample *sample, bool swapped);
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
 				  const struct perf_sample *sample,
 				  bool swapped);

tools/perf/util/evlist.c

@@ -881,3 +881,10 @@ int perf_evlist__start_workload(struct perf_evlist *evlist)
 
 	return 0;
 }
+
+int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
+			      struct perf_sample *sample, bool swapped)
+{
+	struct perf_evsel *e = list_entry(evlist->entries.next, struct perf_evsel, node);
+	return perf_evsel__parse_sample(e, event, sample, swapped);
+}

tools/perf/util/evlist.h

@@ -122,6 +122,9 @@ u64 perf_evlist__sample_type(const struct perf_evlist *evlist);
 bool perf_evlist__sample_id_all(const const struct perf_evlist *evlist);
 u16 perf_evlist__id_hdr_size(const struct perf_evlist *evlist);
 
+int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
+			      struct perf_sample *sample, bool swapped);
+
 bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist);
 bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist);
 

tools/perf/util/evsel.c

@@ -20,7 +20,7 @@
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 #define GROUP_FD(group_fd, cpu) (*(int *)xyarray__entry(group_fd, cpu, 0))
 
-int __perf_evsel__sample_size(u64 sample_type)
+static int __perf_evsel__sample_size(u64 sample_type)
 {
 	u64 mask = sample_type & PERF_SAMPLE_MASK;
 	int size = 0;
@@ -53,6 +53,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->attr	   = *attr;
 	INIT_LIST_HEAD(&evsel->node);
 	hists__init(&evsel->hists);
+	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
 }
 
 struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
@@ -728,10 +729,10 @@ static bool sample_overlap(const union perf_event *event,
 	return false;
 }
 
-int perf_event__parse_sample(const union perf_event *event, u64 type,
-			     int sample_size, bool sample_id_all,
+int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 			     struct perf_sample *data, bool swapped)
 {
+	u64 type = evsel->attr.sample_type;
 	const u64 *array;
 
 	/*
@@ -746,14 +747,14 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	data->period = 1;
 
 	if (event->header.type != PERF_RECORD_SAMPLE) {
-		if (!sample_id_all)
+		if (!evsel->attr.sample_id_all)
 			return 0;
 		return perf_event__parse_id_sample(event, type, data, swapped);
 	}
 
 	array = event->sample.array;
 
-	if (sample_size + sizeof(event->header) > event->header.size)
+	if (evsel->sample_size + sizeof(event->header) > event->header.size)
 		return -EFAULT;
 
 	if (type & PERF_SAMPLE_IP) {
@@ -895,7 +896,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 		u.val32[1] = sample->tid;
 		if (swapped) {
 			/*
-			 * Inverse of what is done in perf_event__parse_sample
+			 * Inverse of what is done in perf_evsel__parse_sample
 			 */
 			u.val32[0] = bswap_32(u.val32[0]);
 			u.val32[1] = bswap_32(u.val32[1]);
@@ -930,7 +931,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 		u.val32[0] = sample->cpu;
 		if (swapped) {
 			/*
-			 * Inverse of what is done in perf_event__parse_sample
+			 * Inverse of what is done in perf_evsel__parse_sample
 			 */
 			u.val32[0] = bswap_32(u.val32[0]);
 			u.val64 = bswap_64(u.val64);

tools/perf/util/evsel.h

@@ -65,6 +65,7 @@ struct perf_evsel {
 		void		*func;
 		void		*data;
 	} handler;
+	unsigned int		sample_size;
 	bool 			supported;
 };
 
@@ -177,13 +178,8 @@ static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
 	return __perf_evsel__read(evsel, ncpus, nthreads, true);
 }
 
-int __perf_evsel__sample_size(u64 sample_type);
-
-static inline int perf_evsel__sample_size(struct perf_evsel *evsel)
-{
-	return __perf_evsel__sample_size(evsel->attr.sample_type);
-}
-
 void hists__init(struct hists *hists);
 
+int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
+			     struct perf_sample *sample, bool swapped);
 #endif /* __PERF_EVSEL_H */

tools/perf/util/header.c

@@ -174,6 +174,15 @@ perf_header__set_cmdline(int argc, const char **argv)
 {
 	int i;
 
+	/*
+	 * If header_argv has already been set, do not override it.
+	 * This allows a command to set the cmdline, parse args and
+	 * then call another builtin function that implements a
+	 * command -- e.g, cmd_kvm calling cmd_record.
+	 */
+	if (header_argv)
+		return 0;
+
 	header_argc = (u32)argc;
 
 	/* do not include NULL termination */