1 files changed, 442 insertions, 148 deletions

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0baf75f12b7c..ed9dc2555ec7 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -15,6 +15,14 @@
 #include "cpumap.h"
 #include "perf_regs.h"
 #include "asm/bug.h"
+#include "auxtrace.h"
+#include "thread-stack.h"
+
+static int perf_session__deliver_event(struct perf_session *session,
+				       union perf_event *event,
+				       struct perf_sample *sample,
+				       struct perf_tool *tool,
+				       u64 file_offset);
 
 static int perf_session__open(struct perf_session *session)
 {
@@ -86,6 +94,23 @@ static void perf_session__set_comm_exec(struct perf_session *session)
 	machines__set_comm_exec(&session->machines, comm_exec);
 }
 
+static int ordered_events__deliver_event(struct ordered_events *oe,
+					 struct ordered_event *event)
+{
+	struct perf_sample sample;
+	struct perf_session *session = container_of(oe, struct perf_session,
+						    ordered_events);
+	int ret = perf_evlist__parse_sample(session->evlist, event->event, &sample);
+
+	if (ret) {
+		pr_err("Can't parse sample, err = %d\n", ret);
+		return ret;
+	}
+
+	return perf_session__deliver_event(session, event->event, &sample,
+					   session->tool, event->file_offset);
+}
+
 struct perf_session *perf_session__new(struct perf_data_file *file,
 				       bool repipe, struct perf_tool *tool)
 {
@@ -95,8 +120,10 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 		goto out;
 
 	session->repipe = repipe;
-	ordered_events__init(&session->ordered_events);
+	session->tool   = tool;
+	INIT_LIST_HEAD(&session->auxtrace_index);
 	machines__init(&session->machines);
+	ordered_events__init(&session->ordered_events, ordered_events__deliver_event);
 
 	if (file) {
 		if (perf_data_file__open(file))
@@ -138,11 +165,6 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 	return NULL;
 }
 
-static void perf_session__delete_dead_threads(struct perf_session *session)
-{
-	machine__delete_dead_threads(&session->machines.host);
-}
-
 static void perf_session__delete_threads(struct perf_session *session)
 {
 	machine__delete_threads(&session->machines.host);
@@ -166,8 +188,9 @@ static void perf_session_env__delete(struct perf_session_env *env)
 
 void perf_session__delete(struct perf_session *session)
 {
+	auxtrace__free(session);
+	auxtrace_index__free(&session->auxtrace_index);
 	perf_session__destroy_kernel_maps(session);
-	perf_session__delete_dead_threads(session);
 	perf_session__delete_threads(session);
 	perf_session_env__delete(&session->header.env);
 	machines__exit(&session->machines);
@@ -215,10 +238,17 @@ static int process_event_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
+static int process_build_id_stub(struct perf_tool *tool __maybe_unused,
+				 union perf_event *event __maybe_unused,
+				 struct perf_session *session __maybe_unused)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
 static int process_finished_round_stub(struct perf_tool *tool __maybe_unused,
 				       union perf_event *event __maybe_unused,
-				       struct perf_session *perf_session
-				       __maybe_unused)
+				       struct ordered_events *oe __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
@@ -226,7 +256,7 @@ static int process_finished_round_stub(struct perf_tool *tool __maybe_unused,
 
 static int process_finished_round(struct perf_tool *tool,
 				  union perf_event *event,
-				  struct perf_session *session);
+				  struct ordered_events *oe);
 
 static int process_id_index_stub(struct perf_tool *tool __maybe_unused,
 				 union perf_event *event __maybe_unused,
@@ -237,6 +267,49 @@ static int process_id_index_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
+static int process_event_auxtrace_info_stub(struct perf_tool *tool __maybe_unused,
+				union perf_event *event __maybe_unused,
+				struct perf_session *session __maybe_unused)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
+static int skipn(int fd, off_t n)
+{
+	char buf[4096];
+	ssize_t ret;
+
+	while (n > 0) {
+		ret = read(fd, buf, min(n, (off_t)sizeof(buf)));
+		if (ret <= 0)
+			return ret;
+		n -= ret;
+	}
+
+	return 0;
+}
+
+static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
+				       union perf_event *event,
+				       struct perf_session *session
+				       __maybe_unused)
+{
+	dump_printf(": unhandled!\n");
+	if (perf_data_file__is_pipe(session->file))
+		skipn(perf_data_file__fd(session->file), event->auxtrace.size);
+	return event->auxtrace.size;
+}
+
+static
+int process_event_auxtrace_error_stub(struct perf_tool *tool __maybe_unused,
+				      union perf_event *event __maybe_unused,
+				      struct perf_session *session __maybe_unused)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
 void perf_tool__fill_defaults(struct perf_tool *tool)
 {
 	if (tool->sample == NULL)
@@ -253,6 +326,12 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->exit = process_event_stub;
 	if (tool->lost == NULL)
 		tool->lost = perf_event__process_lost;
+	if (tool->lost_samples == NULL)
+		tool->lost_samples = perf_event__process_lost_samples;
+	if (tool->aux == NULL)
+		tool->aux = perf_event__process_aux;
+	if (tool->itrace_start == NULL)
+		tool->itrace_start = perf_event__process_itrace_start;
 	if (tool->read == NULL)
 		tool->read = process_event_sample_stub;
 	if (tool->throttle == NULL)
@@ -264,7 +343,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 	if (tool->tracing_data == NULL)
 		tool->tracing_data = process_event_synth_tracing_data_stub;
 	if (tool->build_id == NULL)
-		tool->build_id = process_finished_round_stub;
+		tool->build_id = process_build_id_stub;
 	if (tool->finished_round == NULL) {
 		if (tool->ordered_events)
 			tool->finished_round = process_finished_round;
@@ -273,6 +352,12 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 	}
 	if (tool->id_index == NULL)
 		tool->id_index = process_id_index_stub;
+	if (tool->auxtrace_info == NULL)
+		tool->auxtrace_info = process_event_auxtrace_info_stub;
+	if (tool->auxtrace == NULL)
+		tool->auxtrace = process_event_auxtrace_stub;
+	if (tool->auxtrace_error == NULL)
+		tool->auxtrace_error = process_event_auxtrace_error_stub;
 }
 
 static void swap_sample_id_all(union perf_event *event, void *data)
@@ -365,6 +450,26 @@ static void perf_event__read_swap(union perf_event *event, bool sample_id_all)
 		swap_sample_id_all(event, &event->read + 1);
 }
 
+static void perf_event__aux_swap(union perf_event *event, bool sample_id_all)
+{
+	event->aux.aux_offset = bswap_64(event->aux.aux_offset);
+	event->aux.aux_size   = bswap_64(event->aux.aux_size);
+	event->aux.flags      = bswap_64(event->aux.flags);
+
+	if (sample_id_all)
+		swap_sample_id_all(event, &event->aux + 1);
+}
+
+static void perf_event__itrace_start_swap(union perf_event *event,
+					  bool sample_id_all)
+{
+	event->itrace_start.pid	 = bswap_32(event->itrace_start.pid);
+	event->itrace_start.tid	 = bswap_32(event->itrace_start.tid);
+
+	if (sample_id_all)
+		swap_sample_id_all(event, &event->itrace_start + 1);
+}
+
 static void perf_event__throttle_swap(union perf_event *event,
 				      bool sample_id_all)
 {
@@ -413,19 +518,42 @@ void perf_event__attr_swap(struct perf_event_attr *attr)
 {
 	attr->type		= bswap_32(attr->type);
 	attr->size		= bswap_32(attr->size);
-	attr->config		= bswap_64(attr->config);
-	attr->sample_period	= bswap_64(attr->sample_period);
-	attr->sample_type	= bswap_64(attr->sample_type);
-	attr->read_format	= bswap_64(attr->read_format);
-	attr->wakeup_events	= bswap_32(attr->wakeup_events);
-	attr->bp_type		= bswap_32(attr->bp_type);
-	attr->bp_addr		= bswap_64(attr->bp_addr);
-	attr->bp_len		= bswap_64(attr->bp_len);
-	attr->branch_sample_type = bswap_64(attr->branch_sample_type);
-	attr->sample_regs_user	 = bswap_64(attr->sample_regs_user);
-	attr->sample_stack_user  = bswap_32(attr->sample_stack_user);
 
-	swap_bitfield((u8 *) (&attr->read_format + 1), sizeof(u64));
+#define bswap_safe(f, n) 					\
+	(attr->size > (offsetof(struct perf_event_attr, f) + 	\
+		       sizeof(attr->f) * (n)))
+#define bswap_field(f, sz) 			\
+do { 						\
+	if (bswap_safe(f, 0))			\
+		attr->f = bswap_##sz(attr->f);	\
+} while(0)
+#define bswap_field_32(f) bswap_field(f, 32)
+#define bswap_field_64(f) bswap_field(f, 64)
+
+	bswap_field_64(config);
+	bswap_field_64(sample_period);
+	bswap_field_64(sample_type);
+	bswap_field_64(read_format);
+	bswap_field_32(wakeup_events);
+	bswap_field_32(bp_type);
+	bswap_field_64(bp_addr);
+	bswap_field_64(bp_len);
+	bswap_field_64(branch_sample_type);
+	bswap_field_64(sample_regs_user);
+	bswap_field_32(sample_stack_user);
+	bswap_field_32(aux_watermark);
+
+	/*
+	 * After read_format are bitfields. Check read_format because
+	 * we are unable to use offsetof on bitfield.
+	 */
+	if (bswap_safe(read_format, 1))
+		swap_bitfield((u8 *) (&attr->read_format + 1),
+			      sizeof(u64));
+#undef bswap_field_64
+#undef bswap_field_32
+#undef bswap_field
+#undef bswap_safe
 }
 
 static void perf_event__hdr_attr_swap(union perf_event *event,
@@ -453,6 +581,40 @@ static void perf_event__tracing_data_swap(union perf_event *event,
 	event->tracing_data.size = bswap_32(event->tracing_data.size);
 }
 
+static void perf_event__auxtrace_info_swap(union perf_event *event,
+					   bool sample_id_all __maybe_unused)
+{
+	size_t size;
+
+	event->auxtrace_info.type = bswap_32(event->auxtrace_info.type);
+
+	size = event->header.size;
+	size -= (void *)&event->auxtrace_info.priv - (void *)event;
+	mem_bswap_64(event->auxtrace_info.priv, size);
+}
+
+static void perf_event__auxtrace_swap(union perf_event *event,
+				      bool sample_id_all __maybe_unused)
+{
+	event->auxtrace.size      = bswap_64(event->auxtrace.size);
+	event->auxtrace.offset    = bswap_64(event->auxtrace.offset);
+	event->auxtrace.reference = bswap_64(event->auxtrace.reference);
+	event->auxtrace.idx       = bswap_32(event->auxtrace.idx);
+	event->auxtrace.tid       = bswap_32(event->auxtrace.tid);
+	event->auxtrace.cpu       = bswap_32(event->auxtrace.cpu);
+}
+
+static void perf_event__auxtrace_error_swap(union perf_event *event,
+					    bool sample_id_all __maybe_unused)
+{
+	event->auxtrace_error.type = bswap_32(event->auxtrace_error.type);
+	event->auxtrace_error.code = bswap_32(event->auxtrace_error.code);
+	event->auxtrace_error.cpu  = bswap_32(event->auxtrace_error.cpu);
+	event->auxtrace_error.pid  = bswap_32(event->auxtrace_error.pid);
+	event->auxtrace_error.tid  = bswap_32(event->auxtrace_error.tid);
+	event->auxtrace_error.ip   = bswap_64(event->auxtrace_error.ip);
+}
+
 typedef void (*perf_event__swap_op)(union perf_event *event,
 				    bool sample_id_all);
 
@@ -467,11 +629,17 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_THROTTLE]		  = perf_event__throttle_swap,
 	[PERF_RECORD_UNTHROTTLE]	  = perf_event__throttle_swap,
 	[PERF_RECORD_SAMPLE]		  = perf_event__all64_swap,
+	[PERF_RECORD_AUX]		  = perf_event__aux_swap,
+	[PERF_RECORD_ITRACE_START]	  = perf_event__itrace_start_swap,
+	[PERF_RECORD_LOST_SAMPLES]	  = perf_event__all64_swap,
 	[PERF_RECORD_HEADER_ATTR]	  = perf_event__hdr_attr_swap,
 	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
 	[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
 	[PERF_RECORD_HEADER_BUILD_ID]	  = NULL,
 	[PERF_RECORD_ID_INDEX]		  = perf_event__all64_swap,
+	[PERF_RECORD_AUXTRACE_INFO]	  = perf_event__auxtrace_info_swap,
+	[PERF_RECORD_AUXTRACE]		  = perf_event__auxtrace_swap,
+	[PERF_RECORD_AUXTRACE_ERROR]	  = perf_event__auxtrace_error_swap,
 	[PERF_RECORD_HEADER_MAX]	  = NULL,
 };
 
@@ -514,54 +682,82 @@ static perf_event__swap_op perf_event__swap_ops[] = {
  *      Flush every events below timestamp 7
  *      etc...
  */
-static int process_finished_round(struct perf_tool *tool,
+static int process_finished_round(struct perf_tool *tool __maybe_unused,
 				  union perf_event *event __maybe_unused,
-				  struct perf_session *session)
+				  struct ordered_events *oe)
 {
-	return ordered_events__flush(session, tool, OE_FLUSH__ROUND);
+	if (dump_trace)
+		fprintf(stdout, "\n");
+	return ordered_events__flush(oe, OE_FLUSH__ROUND);
 }
 
-int perf_session_queue_event(struct perf_session *s, union perf_event *event,
-			     struct perf_tool *tool, struct perf_sample *sample,
-			     u64 file_offset)
+int perf_session__queue_event(struct perf_session *s, union perf_event *event,
+			      struct perf_sample *sample, u64 file_offset)
 {
-	struct ordered_events *oe = &s->ordered_events;
-	u64 timestamp = sample->time;
-	struct ordered_event *new;
-
-	if (!timestamp || timestamp == ~0ULL)
-		return -ETIME;
+	return ordered_events__queue(&s->ordered_events, event, sample, file_offset);
+}
 
-	if (timestamp < oe->last_flush) {
-		pr_oe_time(timestamp,      "out of order event\n");
-		pr_oe_time(oe->last_flush, "last flush, last_flush_type %d\n",
-			   oe->last_flush_type);
+static void callchain__lbr_callstack_printf(struct perf_sample *sample)
+{
+	struct ip_callchain *callchain = sample->callchain;
+	struct branch_stack *lbr_stack = sample->branch_stack;
+	u64 kernel_callchain_nr = callchain->nr;
+	unsigned int i;
 
-		s->stats.nr_unordered_events++;
+	for (i = 0; i < kernel_callchain_nr; i++) {
+		if (callchain->ips[i] == PERF_CONTEXT_USER)
+			break;
 	}
 
-	new = ordered_events__new(oe, timestamp, event);
-	if (!new) {
-		ordered_events__flush(s, tool, OE_FLUSH__HALF);
-		new = ordered_events__new(oe, timestamp, event);
-	}
+	if ((i != kernel_callchain_nr) && lbr_stack->nr) {
+		u64 total_nr;
+		/*
+		 * LBR callstack can only get user call chain,
+		 * i is kernel call chain number,
+		 * 1 is PERF_CONTEXT_USER.
+		 *
+		 * The user call chain is stored in LBR registers.
+		 * LBR are pair registers. The caller is stored
+		 * in "from" register, while the callee is stored
+		 * in "to" register.
+		 * For example, there is a call stack
+		 * "A"->"B"->"C"->"D".
+		 * The LBR registers will recorde like
+		 * "C"->"D", "B"->"C", "A"->"B".
+		 * So only the first "to" register and all "from"
+		 * registers are needed to construct the whole stack.
+		 */
+		total_nr = i + 1 + lbr_stack->nr + 1;
+		kernel_callchain_nr = i + 1;
 
-	if (!new)
-		return -ENOMEM;
+		printf("... LBR call chain: nr:%" PRIu64 "\n", total_nr);
 
-	new->file_offset = file_offset;
-	return 0;
+		for (i = 0; i < kernel_callchain_nr; i++)
+			printf("..... %2d: %016" PRIx64 "\n",
+			       i, callchain->ips[i]);
+
+		printf("..... %2d: %016" PRIx64 "\n",
+		       (int)(kernel_callchain_nr), lbr_stack->entries[0].to);
+		for (i = 0; i < lbr_stack->nr; i++)
+			printf("..... %2d: %016" PRIx64 "\n",
+			       (int)(i + kernel_callchain_nr + 1), lbr_stack->entries[i].from);
+	}
 }
 
-static void callchain__printf(struct perf_sample *sample)
+static void callchain__printf(struct perf_evsel *evsel,
+			      struct perf_sample *sample)
 {
 	unsigned int i;
+	struct ip_callchain *callchain = sample->callchain;
 
-	printf("... chain: nr:%" PRIu64 "\n", sample->callchain->nr);
+	if (has_branch_callstack(evsel))
+		callchain__lbr_callstack_printf(sample);
 
-	for (i = 0; i < sample->callchain->nr; i++)
+	printf("... FP chain: nr:%" PRIu64 "\n", callchain->nr);
+
+	for (i = 0; i < callchain->nr; i++)
 		printf("..... %2d: %016" PRIx64 "\n",
-		       i, sample->callchain->ips[i]);
+		       i, callchain->ips[i]);
 }
 
 static void branch_stack__printf(struct perf_sample *sample)
@@ -636,14 +832,14 @@ static void stack_user__printf(struct stack_dump *dump)
 	       dump->size, dump->offset);
 }
 
-static void perf_session__print_tstamp(struct perf_session *session,
+static void perf_evlist__print_tstamp(struct perf_evlist *evlist,
 				       union perf_event *event,
 				       struct perf_sample *sample)
 {
-	u64 sample_type = __perf_evlist__combined_sample_type(session->evlist);
+	u64 sample_type = __perf_evlist__combined_sample_type(evlist);
 
 	if (event->header.type != PERF_RECORD_SAMPLE &&
-	    !perf_evlist__sample_id_all(session->evlist)) {
+	    !perf_evlist__sample_id_all(evlist)) {
 		fputs("-1 -1 ", stdout);
 		return;
 	}
@@ -685,7 +881,7 @@ static void sample_read__printf(struct perf_sample *sample, u64 read_format)
 			sample->read.one.id, sample->read.one.value);
 }
 
-static void dump_event(struct perf_session *session, union perf_event *event,
+static void dump_event(struct perf_evlist *evlist, union perf_event *event,
 		       u64 file_offset, struct perf_sample *sample)
 {
 	if (!dump_trace)
@@ -697,7 +893,7 @@ static void dump_event(struct perf_session *session, union perf_event *event,
 	trace_event(event);
 
 	if (sample)
-		perf_session__print_tstamp(session, event, sample);
+		perf_evlist__print_tstamp(evlist, event, sample);
 
 	printf("%#" PRIx64 " [%#x]: PERF_RECORD_%s", file_offset,
 	       event->header.size, perf_event__name(event->header.type));
@@ -718,9 +914,9 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
 	sample_type = evsel->attr.sample_type;
 
 	if (sample_type & PERF_SAMPLE_CALLCHAIN)
-		callchain__printf(sample);
+		callchain__printf(evsel, sample);
 
-	if (sample_type & PERF_SAMPLE_BRANCH_STACK)
+	if ((sample_type & PERF_SAMPLE_BRANCH_STACK) && !has_branch_callstack(evsel))
 		branch_stack__printf(sample);
 
 	if (sample_type & PERF_SAMPLE_REGS_USER)
@@ -745,8 +941,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
 		sample_read__printf(sample, evsel->attr.read_format);
 }
 
-static struct machine *
-	perf_session__find_machine_for_cpumode(struct perf_session *session,
+static struct machine *machines__find_for_cpumode(struct machines *machines,
 					       union perf_event *event,
 					       struct perf_sample *sample)
 {
@@ -764,26 +959,24 @@ static struct machine *
 		else
 			pid = sample->pid;
 
-		machine = perf_session__find_machine(session, pid);
+		machine = machines__find(machines, pid);
 		if (!machine)
-			machine = perf_session__findnew_machine(session,
-						DEFAULT_GUEST_KERNEL_ID);
+			machine = machines__find(machines, DEFAULT_GUEST_KERNEL_ID);
 		return machine;
 	}
 
-	return &session->machines.host;
+	return &machines->host;
 }
 
-static int deliver_sample_value(struct perf_session *session,
+static int deliver_sample_value(struct perf_evlist *evlist,
 				struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,
 				struct sample_read_value *v,
 				struct machine *machine)
 {
-	struct perf_sample_id *sid;
+	struct perf_sample_id *sid = perf_evlist__id2sid(evlist, v->id);
 
-	sid = perf_evlist__id2sid(session->evlist, v->id);
 	if (sid) {
 		sample->id     = v->id;
 		sample->period = v->value - sid->period;
@@ -791,14 +984,14 @@ static int deliver_sample_value(struct perf_session *session,
 	}
 
 	if (!sid || sid->evsel == NULL) {
-		++session->stats.nr_unknown_id;
+		++evlist->stats.nr_unknown_id;
 		return 0;
 	}
 
 	return tool->sample(tool, event, sample, sid->evsel, machine);
 }
 
-static int deliver_sample_group(struct perf_session *session,
+static int deliver_sample_group(struct perf_evlist *evlist,
 				struct perf_tool *tool,
 				union  perf_event *event,
 				struct perf_sample *sample,
@@ -808,7 +1001,7 @@ static int deliver_sample_group(struct perf_session *session,
 	u64 i;
 
 	for (i = 0; i < sample->read.group.nr; i++) {
-		ret = deliver_sample_value(session, tool, event, sample,
+		ret = deliver_sample_value(evlist, tool, event, sample,
 					   &sample->read.group.values[i],
 					   machine);
 		if (ret)
@@ -819,7 +1012,7 @@ static int deliver_sample_group(struct perf_session *session,
 }
 
 static int
-perf_session__deliver_sample(struct perf_session *session,
+ perf_evlist__deliver_sample(struct perf_evlist *evlist,
 			     struct perf_tool *tool,
 			     union  perf_event *event,
 			     struct perf_sample *sample,
@@ -836,44 +1029,45 @@ perf_session__deliver_sample(struct perf_session *session,
 
 	/* For PERF_SAMPLE_READ we have either single or group mode. */
 	if (read_format & PERF_FORMAT_GROUP)
-		return deliver_sample_group(session, tool, event, sample,
+		return deliver_sample_group(evlist, tool, event, sample,
 					    machine);
 	else
-		return deliver_sample_value(session, tool, event, sample,
+		return deliver_sample_value(evlist, tool, event, sample,
 					    &sample->read.one, machine);
 }
 
-int perf_session__deliver_event(struct perf_session *session,
-				union perf_event *event,
-				struct perf_sample *sample,
-				struct perf_tool *tool, u64 file_offset)
+static int machines__deliver_event(struct machines *machines,
+				   struct perf_evlist *evlist,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct perf_tool *tool, u64 file_offset)
 {
 	struct perf_evsel *evsel;
 	struct machine *machine;
 
-	dump_event(session, event, file_offset, sample);
+	dump_event(evlist, event, file_offset, sample);
 
-	evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+	evsel = perf_evlist__id2evsel(evlist, sample->id);
 
-	machine = perf_session__find_machine_for_cpumode(session, event,
-							 sample);
+	machine = machines__find_for_cpumode(machines, event, sample);
 
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:
 		dump_sample(evsel, event, sample);
 		if (evsel == NULL) {
-			++session->stats.nr_unknown_id;
+			++evlist->stats.nr_unknown_id;
 			return 0;
 		}
 		if (machine == NULL) {
-			++session->stats.nr_unprocessable_samples;
+			++evlist->stats.nr_unprocessable_samples;
 			return 0;
 		}
-		return perf_session__deliver_sample(session, tool, event,
-						    sample, evsel, machine);
+		return perf_evlist__deliver_sample(evlist, tool, event, sample, evsel, machine);
 	case PERF_RECORD_MMAP:
 		return tool->mmap(tool, event, sample, machine);
 	case PERF_RECORD_MMAP2:
+		if (event->header.misc & PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT)
+			++evlist->stats.nr_proc_map_timeout;
 		return tool->mmap2(tool, event, sample, machine);
 	case PERF_RECORD_COMM:
 		return tool->comm(tool, event, sample, machine);
@@ -883,29 +1077,56 @@ int perf_session__deliver_event(struct perf_session *session,
 		return tool->exit(tool, event, sample, machine);
 	case PERF_RECORD_LOST:
 		if (tool->lost == perf_event__process_lost)
-			session->stats.total_lost += event->lost.lost;
+			evlist->stats.total_lost += event->lost.lost;
 		return tool->lost(tool, event, sample, machine);
+	case PERF_RECORD_LOST_SAMPLES:
+		if (tool->lost_samples == perf_event__process_lost_samples)
+			evlist->stats.total_lost_samples += event->lost_samples.lost;
+		return tool->lost_samples(tool, event, sample, machine);
 	case PERF_RECORD_READ:
 		return tool->read(tool, event, sample, evsel, machine);
 	case PERF_RECORD_THROTTLE:
 		return tool->throttle(tool, event, sample, machine);
 	case PERF_RECORD_UNTHROTTLE:
 		return tool->unthrottle(tool, event, sample, machine);
+	case PERF_RECORD_AUX:
+		return tool->aux(tool, event, sample, machine);
+	case PERF_RECORD_ITRACE_START:
+		return tool->itrace_start(tool, event, sample, machine);
 	default:
-		++session->stats.nr_unknown_events;
+		++evlist->stats.nr_unknown_events;
 		return -1;
 	}
 }
 
+static int perf_session__deliver_event(struct perf_session *session,
+				       union perf_event *event,
+				       struct perf_sample *sample,
+				       struct perf_tool *tool,
+				       u64 file_offset)
+{
+	int ret;
+
+	ret = auxtrace__process_event(session, event, sample, tool);
+	if (ret < 0)
+		return ret;
+	if (ret > 0)
+		return 0;
+
+	return machines__deliver_event(&session->machines, session->evlist,
+				       event, sample, tool, file_offset);
+}
+
 static s64 perf_session__process_user_event(struct perf_session *session,
 					    union perf_event *event,
-					    struct perf_tool *tool,
 					    u64 file_offset)
 {
+	struct ordered_events *oe = &session->ordered_events;
+	struct perf_tool *tool = session->tool;
 	int fd = perf_data_file__fd(session->file);
 	int err;
 
-	dump_event(session, event, file_offset, NULL);
+	dump_event(session->evlist, event, file_offset, NULL);
 
 	/* These events are processed right away */
 	switch (event->header.type) {
@@ -929,9 +1150,18 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 	case PERF_RECORD_HEADER_BUILD_ID:
 		return tool->build_id(tool, event, session);
 	case PERF_RECORD_FINISHED_ROUND:
-		return tool->finished_round(tool, event, session);
+		return tool->finished_round(tool, event, oe);
 	case PERF_RECORD_ID_INDEX:
 		return tool->id_index(tool, event, session);
+	case PERF_RECORD_AUXTRACE_INFO:
+		return tool->auxtrace_info(tool, event, session);
+	case PERF_RECORD_AUXTRACE:
+		/* setup for reading amidst mmap */
+		lseek(fd, file_offset + event->header.size, SEEK_SET);
+		return tool->auxtrace(tool, event, session);
+	case PERF_RECORD_AUXTRACE_ERROR:
+		perf_session__auxtrace_error_inc(session, event);
+		return tool->auxtrace_error(tool, event, session);
 	default:
 		return -EINVAL;
 	}
@@ -939,15 +1169,17 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 
 int perf_session__deliver_synth_event(struct perf_session *session,
 				      union perf_event *event,
-				      struct perf_sample *sample,
-				      struct perf_tool *tool)
+				      struct perf_sample *sample)
 {
-	events_stats__inc(&session->stats, event->header.type);
+	struct perf_evlist *evlist = session->evlist;
+	struct perf_tool *tool = session->tool;
+
+	events_stats__inc(&evlist->stats, event->header.type);
 
 	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
-		return perf_session__process_user_event(session, event, tool, 0);
+		return perf_session__process_user_event(session, event, 0);
 
-	return perf_session__deliver_event(session, event, sample, tool, 0);
+	return machines__deliver_event(&session->machines, evlist, event, sample, tool, 0);
 }
 
 static void event_swap(union perf_event *event, bool sample_id_all)
@@ -984,7 +1216,7 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
 		return -1;
 
 	if (lseek(fd, file_offset, SEEK_SET) == (off_t)-1 ||
-	    readn(fd, &buf, hdr_sz) != (ssize_t)hdr_sz)
+	    readn(fd, buf, hdr_sz) != (ssize_t)hdr_sz)
 		return -1;
 
 	event = (union perf_event *)buf;
@@ -992,12 +1224,12 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
 	if (session->header.needs_swap)
 		perf_event_header__bswap(&event->header);
 
-	if (event->header.size < hdr_sz)
+	if (event->header.size < hdr_sz || event->header.size > buf_sz)
 		return -1;
 
 	rest = event->header.size - hdr_sz;
 
-	if (readn(fd, &buf, rest) != (ssize_t)rest)
+	if (readn(fd, buf, rest) != (ssize_t)rest)
 		return -1;
 
 	if (session->header.needs_swap)
@@ -1015,34 +1247,33 @@ out_parse_sample:
 }
 
 static s64 perf_session__process_event(struct perf_session *session,
-				       union perf_event *event,
-				       struct perf_tool *tool,
-				       u64 file_offset)
+				       union perf_event *event, u64 file_offset)
 {
+	struct perf_evlist *evlist = session->evlist;
+	struct perf_tool *tool = session->tool;
 	struct perf_sample sample;
 	int ret;
 
 	if (session->header.needs_swap)
-		event_swap(event, perf_evlist__sample_id_all(session->evlist));
+		event_swap(event, perf_evlist__sample_id_all(evlist));
 
 	if (event->header.type >= PERF_RECORD_HEADER_MAX)
 		return -EINVAL;
 
-	events_stats__inc(&session->stats, event->header.type);
+	events_stats__inc(&evlist->stats, event->header.type);
 
 	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
-		return perf_session__process_user_event(session, event, tool, file_offset);
+		return perf_session__process_user_event(session, event, file_offset);
 
 	/*
 	 * For all kernel events we get the sample data
 	 */
-	ret = perf_evlist__parse_sample(session->evlist, event, &sample);
+	ret = perf_evlist__parse_sample(evlist, event, &sample);
 	if (ret)
 		return ret;
 
 	if (tool->ordered_events) {
-		ret = perf_session_queue_event(session, event, tool, &sample,
-					       file_offset);
+		ret = perf_session__queue_event(session, event, &sample, file_offset);
 		if (ret != -ETIME)
 			return ret;
 	}
@@ -1076,54 +1307,95 @@ static struct thread *perf_session__register_idle_thread(struct perf_session *se
 	return thread;
 }
 
-static void perf_session__warn_about_errors(const struct perf_session *session,
-					    const struct perf_tool *tool)
+static void perf_session__warn_about_errors(const struct perf_session *session)
 {
-	if (tool->lost == perf_event__process_lost &&
-	    session->stats.nr_events[PERF_RECORD_LOST] != 0) {
+	const struct events_stats *stats = &session->evlist->stats;
+	const struct ordered_events *oe = &session->ordered_events;
+
+	if (session->tool->lost == perf_event__process_lost &&
+	    stats->nr_events[PERF_RECORD_LOST] != 0) {
 		ui__warning("Processed %d events and lost %d chunks!\n\n"
 			    "Check IO/CPU overload!\n\n",
-			    session->stats.nr_events[0],
-			    session->stats.nr_events[PERF_RECORD_LOST]);
+			    stats->nr_events[0],
+			    stats->nr_events[PERF_RECORD_LOST]);
+	}
+
+	if (session->tool->lost_samples == perf_event__process_lost_samples) {
+		double drop_rate;
+
+		drop_rate = (double)stats->total_lost_samples /
+			    (double) (stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples);
+		if (drop_rate > 0.05) {
+			ui__warning("Processed %" PRIu64 " samples and lost %3.2f%% samples!\n\n",
+				    stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples,
+				    drop_rate * 100.0);
+		}
 	}
 
-	if (session->stats.nr_unknown_events != 0) {
+	if (stats->nr_unknown_events != 0) {
 		ui__warning("Found %u unknown events!\n\n"
 			    "Is this an older tool processing a perf.data "
 			    "file generated by a more recent tool?\n\n"
 			    "If that is not the case, consider "
 			    "reporting to linux-kernel@vger.kernel.org.\n\n",
-			    session->stats.nr_unknown_events);
+			    stats->nr_unknown_events);
 	}
 
-	if (session->stats.nr_unknown_id != 0) {
+	if (stats->nr_unknown_id != 0) {
 		ui__warning("%u samples with id not present in the header\n",
-			    session->stats.nr_unknown_id);
+			    stats->nr_unknown_id);
 	}
 
- 	if (session->stats.nr_invalid_chains != 0) {
- 		ui__warning("Found invalid callchains!\n\n"
- 			    "%u out of %u events were discarded for this reason.\n\n"
- 			    "Consider reporting to linux-kernel@vger.kernel.org.\n\n",
- 			    session->stats.nr_invalid_chains,
- 			    session->stats.nr_events[PERF_RECORD_SAMPLE]);
- 	}
+	if (stats->nr_invalid_chains != 0) {
+		ui__warning("Found invalid callchains!\n\n"
+			    "%u out of %u events were discarded for this reason.\n\n"
+			    "Consider reporting to linux-kernel@vger.kernel.org.\n\n",
+			    stats->nr_invalid_chains,
+			    stats->nr_events[PERF_RECORD_SAMPLE]);
+	}
 
-	if (session->stats.nr_unprocessable_samples != 0) {
+	if (stats->nr_unprocessable_samples != 0) {
 		ui__warning("%u unprocessable samples recorded.\n"
 			    "Do you have a KVM guest running and not using 'perf kvm'?\n",
-			    session->stats.nr_unprocessable_samples);
+			    stats->nr_unprocessable_samples);
 	}
 
-	if (session->stats.nr_unordered_events != 0)
-		ui__warning("%u out of order events recorded.\n", session->stats.nr_unordered_events);
+	if (oe->nr_unordered_events != 0)
+		ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events);
+
+	events_stats__auxtrace_error_warn(stats);
+
+	if (stats->nr_proc_map_timeout != 0) {
+		ui__warning("%d map information files for pre-existing threads were\n"
+			    "not processed, if there are samples for addresses they\n"
+			    "will not be resolved, you may find out which are these\n"
+			    "threads by running with -v and redirecting the output\n"
+			    "to a file.\n"
+			    "The time limit to process proc map is too short?\n"
+			    "Increase it by --proc-map-timeout\n",
+			    stats->nr_proc_map_timeout);
+	}
+}
+
+static int perf_session__flush_thread_stack(struct thread *thread,
+					    void *p __maybe_unused)
+{
+	return thread_stack__flush(thread);
+}
+
+static int perf_session__flush_thread_stacks(struct perf_session *session)
+{
+	return machines__for_each_thread(&session->machines,
+					 perf_session__flush_thread_stack,
+					 NULL);
 }
 
 volatile int session_done;
 
-static int __perf_session__process_pipe_events(struct perf_session *session,
-					       struct perf_tool *tool)
+static int __perf_session__process_pipe_events(struct perf_session *session)
 {
+	struct ordered_events *oe = &session->ordered_events;
+	struct perf_tool *tool = session->tool;
 	int fd = perf_data_file__fd(session->file);
 	union perf_event *event;
 	uint32_t size, cur_size = 0;
@@ -1187,7 +1459,7 @@ more:
 		}
 	}
 
-	if ((skip = perf_session__process_event(session, event, tool, head)) < 0) {
+	if ((skip = perf_session__process_event(session, event, head)) < 0) {
 		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
 		       head, event->header.size, event->header.type);
 		err = -EINVAL;
@@ -1203,11 +1475,18 @@ more:
 		goto more;
 done:
 	/* do the final flush for ordered samples */
-	err = ordered_events__flush(session, tool, OE_FLUSH__FINAL);
+	err = ordered_events__flush(oe, OE_FLUSH__FINAL);
+	if (err)
+		goto out_err;
+	err = auxtrace__flush_events(session, tool);
+	if (err)
+		goto out_err;
+	err = perf_session__flush_thread_stacks(session);
 out_err:
 	free(buf);
-	perf_session__warn_about_errors(session, tool);
+	perf_session__warn_about_errors(session);
 	ordered_events__free(&session->ordered_events);
+	auxtrace__free_events(session);
 	return err;
 }
 
@@ -1253,8 +1532,10 @@ fetch_mmaped_event(struct perf_session *session,
 
 static int __perf_session__process_events(struct perf_session *session,
 					  u64 data_offset, u64 data_size,
-					  u64 file_size, struct perf_tool *tool)
+					  u64 file_size)
 {
+	struct ordered_events *oe = &session->ordered_events;
+	struct perf_tool *tool = session->tool;
 	int fd = perf_data_file__fd(session->file);
 	u64 head, page_offset, file_offset, file_pos, size;
 	int err, mmap_prot, mmap_flags, map_idx = 0;
@@ -1323,8 +1604,7 @@ more:
 	size = event->header.size;
 
 	if (size < sizeof(struct perf_event_header) ||
-	    (skip = perf_session__process_event(session, event, tool, file_pos))
-									< 0) {
+	    (skip = perf_session__process_event(session, event, file_pos)) < 0) {
 		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
 		       file_offset + head, event->header.size,
 		       event->header.type);
@@ -1348,17 +1628,23 @@ more:
 
 out:
 	/* do the final flush for ordered samples */
-	err = ordered_events__flush(session, tool, OE_FLUSH__FINAL);
+	err = ordered_events__flush(oe, OE_FLUSH__FINAL);
+	if (err)
+		goto out_err;
+	err = auxtrace__flush_events(session, tool);
+	if (err)
+		goto out_err;
+	err = perf_session__flush_thread_stacks(session);
 out_err:
 	ui_progress__finish();
-	perf_session__warn_about_errors(session, tool);
+	perf_session__warn_about_errors(session);
 	ordered_events__free(&session->ordered_events);
+	auxtrace__free_events(session);
 	session->one_mmap = false;
 	return err;
 }
 
-int perf_session__process_events(struct perf_session *session,
-				 struct perf_tool *tool)
+int perf_session__process_events(struct perf_session *session)
 {
 	u64 size = perf_data_file__size(session->file);
 	int err;
@@ -1369,10 +1655,9 @@ int perf_session__process_events(struct perf_session *session,
 	if (!perf_data_file__is_pipe(session->file))
 		err = __perf_session__process_events(session,
 						     session->header.data_offset,
-						     session->header.data_size,
-						     size, tool);
+						     session->header.data_size, size);
 	else
-		err = __perf_session__process_pipe_events(session, tool);
+		err = __perf_session__process_pipe_events(session);
 
 	return err;
 }
@@ -1415,6 +1700,9 @@ int maps__set_kallsyms_ref_reloc_sym(struct map **maps,
 
 	for (i = 0; i < MAP__NR_TYPES; ++i) {
 		struct kmap *kmap = map__kmap(maps[i]);
+
+		if (!kmap)
+			continue;
 		kmap->ref_reloc_sym = ref;
 	}
 
@@ -1434,9 +1722,15 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp
 
 size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
 {
-	size_t ret = fprintf(fp, "Aggregated stats:\n");
+	size_t ret;
+	const char *msg = "";
+
+	if (perf_header__has_feat(&session->header, HEADER_AUXTRACE))
+		msg = " (excludes AUX area (e.g. instruction trace) decoded / synthesized events)";
+
+	ret = fprintf(fp, "\nAggregated stats:%s\n", msg);
 
-	ret += events_stats__fprintf(&session->stats, fp);
+	ret += events_stats__fprintf(&session->evlist->stats, fp);
 	return ret;
 }
 
@@ -1601,7 +1895,7 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 	err = 0;
 
 out_delete_map:
-	cpu_map__delete(map);
+	cpu_map__put(map);
 	return err;
 }