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

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

 * Fix include order for bison/flex-generated C files, from Ben Hutchings

 * Build fixes and documentation corrections from David Ahern

 * Group parsing support, from Jiri Olsa

 * UI/gtk refactorings and improvements from Namhyung Kim

 * NULL deref fix for perf script, from Namhyung Kim

 * Assorted cleanups from Robert Richter

 * Let O= makes handle relative paths, from Steven Rostedt

 * perf script python fixes, from Feng Tang.

 * Improve 'perf lock' error message when the needed tracepoints
   are not present, from David Ahern.

 * Initial bash completion support, from Frederic Weisbecker

 * Allow building without libelf, from Namhyung Kim.

 * Support DWARF CFI based unwind to have callchains when %bp
   based unwinding is not possible, from Jiri Olsa.

 * Symbol resolution fixes, while fixing support PPC64 files with an .opt ELF
   section was the end goal, several fixes for code that handles all
   architectures and cleanups are included, from Cody Schafer.

 * Add a description for the JIT interface, from Andi Kleen.

 * Assorted fixes for Documentation and build in 32 bit, from Robert Richter

 * Add support for non-tracepoint events in perf script python, from Feng Tang

 * Cache the libtraceevent event_format associated to each evsel early, so that we
   avoid relookups, i.e. calling pevent_find_event repeatedly when processing
   tracepoint events.

   [ This is to reduce the surface contact with libtraceevents and make clear what
     is that the perf tools needs from that lib: so far parsing the common and per
     event fields. ]

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 117 insertions, 36 deletions

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8e4f0755d2a..f7bb7ae328d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -15,6 +15,8 @@
 #include "util.h"
 #include "cpumap.h"
 #include "event-parse.h"
+#include "perf_regs.h"
+#include "unwind.h"
 
 static int perf_session__open(struct perf_session *self, bool force)
 {
@@ -80,14 +82,12 @@ out_close:
 	return -1;
 }
 
-void perf_session__update_sample_type(struct perf_session *self)
+void perf_session__set_id_hdr_size(struct perf_session *session)
 {
-	self->sample_type = perf_evlist__sample_type(self->evlist);
-	self->sample_size = __perf_evsel__sample_size(self->sample_type);
-	self->sample_id_all = perf_evlist__sample_id_all(self->evlist);
-	self->id_hdr_size = perf_evlist__id_hdr_size(self->evlist);
-	self->host_machine.id_hdr_size = self->id_hdr_size;
-	machines__set_id_hdr_size(&self->machines, self->id_hdr_size);
+	u16 id_hdr_size = perf_evlist__id_hdr_size(session->evlist);
+
+	session->host_machine.id_hdr_size = id_hdr_size;
+	machines__set_id_hdr_size(&session->machines, id_hdr_size);
 }
 
 int perf_session__create_kernel_maps(struct perf_session *self)
@@ -147,7 +147,7 @@ struct perf_session *perf_session__new(const char *filename, int mode,
 	if (mode == O_RDONLY) {
 		if (perf_session__open(self, force) < 0)
 			goto out_delete;
-		perf_session__update_sample_type(self);
+		perf_session__set_id_hdr_size(self);
 	} else if (mode == O_WRONLY) {
 		/*
 		 * In O_RDONLY mode this will be performed when reading the
@@ -158,7 +158,7 @@ struct perf_session *perf_session__new(const char *filename, int mode,
 	}
 
 	if (tool && tool->ordering_requires_timestamps &&
-	    tool->ordered_samples && !self->sample_id_all) {
+	    tool->ordered_samples && !perf_evlist__sample_id_all(self->evlist)) {
 		dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
 		tool->ordered_samples = false;
 	}
@@ -290,10 +290,11 @@ struct branch_info *machine__resolve_bstack(struct machine *self,
 	return bi;
 }
 
-int machine__resolve_callchain(struct machine *self,
-			       struct thread *thread,
-			       struct ip_callchain *chain,
-			       struct symbol **parent)
+static int machine__resolve_callchain_sample(struct machine *machine,
+					     struct thread *thread,
+					     struct ip_callchain *chain,
+					     struct symbol **parent)
+
 {
 	u8 cpumode = PERF_RECORD_MISC_USER;
 	unsigned int i;
@@ -318,11 +319,14 @@ int machine__resolve_callchain(struct machine *self,
 		if (ip >= PERF_CONTEXT_MAX) {
 			switch (ip) {
 			case PERF_CONTEXT_HV:
-				cpumode = PERF_RECORD_MISC_HYPERVISOR;	break;
+				cpumode = PERF_RECORD_MISC_HYPERVISOR;
+				break;
 			case PERF_CONTEXT_KERNEL:
-				cpumode = PERF_RECORD_MISC_KERNEL;	break;
+				cpumode = PERF_RECORD_MISC_KERNEL;
+				break;
 			case PERF_CONTEXT_USER:
-				cpumode = PERF_RECORD_MISC_USER;	break;
+				cpumode = PERF_RECORD_MISC_USER;
+				break;
 			default:
 				pr_debug("invalid callchain context: "
 					 "%"PRId64"\n", (s64) ip);
@@ -337,7 +341,7 @@ int machine__resolve_callchain(struct machine *self,
 		}
 
 		al.filtered = false;
-		thread__find_addr_location(thread, self, cpumode,
+		thread__find_addr_location(thread, machine, cpumode,
 					   MAP__FUNCTION, ip, &al, NULL);
 		if (al.sym != NULL) {
 			if (sort__has_parent && !*parent &&
@@ -356,6 +360,40 @@ int machine__resolve_callchain(struct machine *self,
 	return 0;
 }
 
+static int unwind_entry(struct unwind_entry *entry, void *arg)
+{
+	struct callchain_cursor *cursor = arg;
+	return callchain_cursor_append(cursor, entry->ip,
+				       entry->map, entry->sym);
+}
+
+int machine__resolve_callchain(struct machine *machine,
+			       struct perf_evsel *evsel,
+			       struct thread *thread,
+			       struct perf_sample *sample,
+			       struct symbol **parent)
+
+{
+	int ret;
+
+	callchain_cursor_reset(&callchain_cursor);
+
+	ret = machine__resolve_callchain_sample(machine, thread,
+						sample->callchain, parent);
+	if (ret)
+		return ret;
+
+	/* Can we do dwarf post unwind? */
+	if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) &&
+	      (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER)))
+		return 0;
+
+	return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
+				   thread, evsel->attr.sample_regs_user,
+				   sample);
+
+}
+
 static int process_event_synth_tracing_data_stub(union perf_event *event __used,
 						 struct perf_session *session __used)
 {
@@ -673,7 +711,8 @@ static void flush_sample_queue(struct perf_session *s,
 		if (iter->timestamp > limit)
 			break;
 
-		ret = perf_session__parse_sample(s, iter->event, &sample);
+		ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample,
+						s->header.needs_swap);
 		if (ret)
 			pr_err("Can't parse sample, err = %d\n", ret);
 		else
@@ -861,20 +900,50 @@ static void branch_stack__printf(struct perf_sample *sample)
 			sample->branch_stack->entries[i].to);
 }
 
+static void regs_dump__printf(u64 mask, u64 *regs)
+{
+	unsigned rid, i = 0;
+
+	for_each_set_bit(rid, (unsigned long *) &mask, sizeof(mask) * 8) {
+		u64 val = regs[i++];
+
+		printf(".... %-5s 0x%" PRIx64 "\n",
+		       perf_reg_name(rid), val);
+	}
+}
+
+static void regs_user__printf(struct perf_sample *sample, u64 mask)
+{
+	struct regs_dump *user_regs = &sample->user_regs;
+
+	if (user_regs->regs) {
+		printf("... user regs: mask 0x%" PRIx64 "\n", mask);
+		regs_dump__printf(mask, user_regs->regs);
+	}
+}
+
+static void stack_user__printf(struct stack_dump *dump)
+{
+	printf("... ustack: size %" PRIu64 ", offset 0x%x\n",
+	       dump->size, dump->offset);
+}
+
 static void perf_session__print_tstamp(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_sample *sample)
 {
+	u64 sample_type = perf_evlist__sample_type(session->evlist);
+
 	if (event->header.type != PERF_RECORD_SAMPLE &&
-	    !session->sample_id_all) {
+	    !perf_evlist__sample_id_all(session->evlist)) {
 		fputs("-1 -1 ", stdout);
 		return;
 	}
 
-	if ((session->sample_type & PERF_SAMPLE_CPU))
+	if ((sample_type & PERF_SAMPLE_CPU))
 		printf("%u ", sample->cpu);
 
-	if (session->sample_type & PERF_SAMPLE_TIME)
+	if (sample_type & PERF_SAMPLE_TIME)
 		printf("%" PRIu64 " ", sample->time);
 }
 
@@ -896,9 +965,11 @@ static void dump_event(struct perf_session *session, union perf_event *event,
 	       event->header.size, perf_event__name(event->header.type));
 }
 
-static void dump_sample(struct perf_session *session, union perf_event *event,
+static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
 			struct perf_sample *sample)
 {
+	u64 sample_type;
+
 	if (!dump_trace)
 		return;
 
@@ -906,11 +977,19 @@ static void dump_sample(struct perf_session *session, union perf_event *event,
 	       event->header.misc, sample->pid, sample->tid, sample->ip,
 	       sample->period, sample->addr);
 
-	if (session->sample_type & PERF_SAMPLE_CALLCHAIN)
+	sample_type = evsel->attr.sample_type;
+
+	if (sample_type & PERF_SAMPLE_CALLCHAIN)
 		callchain__printf(sample);
 
-	if (session->sample_type & PERF_SAMPLE_BRANCH_STACK)
+	if (sample_type & PERF_SAMPLE_BRANCH_STACK)
 		branch_stack__printf(sample);
+
+	if (sample_type & PERF_SAMPLE_REGS_USER)
+		regs_user__printf(sample, evsel->attr.sample_regs_user);
+
+	if (sample_type & PERF_SAMPLE_STACK_USER)
+		stack_user__printf(&sample->user_stack);
 }
 
 static struct machine *
@@ -968,7 +1047,7 @@ static int perf_session_deliver_event(struct perf_session *session,
 
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:
-		dump_sample(session, event, sample);
+		dump_sample(evsel, event, sample);
 		if (evsel == NULL) {
 			++session->hists.stats.nr_unknown_id;
 			return 0;
@@ -1006,7 +1085,7 @@ static int perf_session__preprocess_sample(struct perf_session *session,
 					   union perf_event *event, struct perf_sample *sample)
 {
 	if (event->header.type != PERF_RECORD_SAMPLE ||
-	    !(session->sample_type & PERF_SAMPLE_CALLCHAIN))
+	    !(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_CALLCHAIN))
 		return 0;
 
 	if (!ip_callchain__valid(sample->callchain, event)) {
@@ -1030,7 +1109,7 @@ static int perf_session__process_user_event(struct perf_session *session, union
 	case PERF_RECORD_HEADER_ATTR:
 		err = tool->attr(event, &session->evlist);
 		if (err == 0)
-			perf_session__update_sample_type(session);
+			perf_session__set_id_hdr_size(session);
 		return err;
 	case PERF_RECORD_HEADER_EVENT_TYPE:
 		return tool->event_type(tool, event);
@@ -1065,7 +1144,7 @@ static int perf_session__process_event(struct perf_session *session,
 	int ret;
 
 	if (session->header.needs_swap)
-		event_swap(event, session->sample_id_all);
+		event_swap(event, perf_evlist__sample_id_all(session->evlist));
 
 	if (event->header.type >= PERF_RECORD_HEADER_MAX)
 		return -EINVAL;
@@ -1078,7 +1157,8 @@ static int perf_session__process_event(struct perf_session *session,
 	/*
 	 * For all kernel events we get the sample data
 	 */
-	ret = perf_session__parse_sample(session, event, &sample);
+	ret = perf_evlist__parse_sample(session->evlist, event, &sample,
+					session->header.needs_swap);
 	if (ret)
 		return ret;
 
@@ -1389,9 +1469,9 @@ int perf_session__process_events(struct perf_session *self,
 	return err;
 }
 
-bool perf_session__has_traces(struct perf_session *self, const char *msg)
+bool perf_session__has_traces(struct perf_session *session, const char *msg)
 {
-	if (!(self->sample_type & PERF_SAMPLE_RAW)) {
+	if (!(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_RAW)) {
 		pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg);
 		return false;
 	}
@@ -1492,9 +1572,9 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 	return NULL;
 }
 
-void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
-			  struct machine *machine, int print_sym,
-			  int print_dso, int print_symoffset)
+void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
+			  struct perf_sample *sample, struct machine *machine,
+			  int print_sym, int print_dso, int print_symoffset)
 {
 	struct addr_location al;
 	struct callchain_cursor_node *node;
@@ -1508,8 +1588,9 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
 
 	if (symbol_conf.use_callchain && sample->callchain) {
 
-		if (machine__resolve_callchain(machine, al.thread,
-						sample->callchain, NULL) != 0) {
+
+		if (machine__resolve_callchain(machine, evsel, al.thread,
+					       sample, NULL) != 0) {
 			if (verbose)
 				error("Failed to resolve callchain. Skipping\n");
 			return;