1 files changed, 768 insertions, 467 deletions

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 2c0d30f08e78..4236503c8f6c 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
+#include <signal.h>
 #include <inttypes.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
@@ -11,6 +12,7 @@
 #include <sys/types.h>
 #include <sys/mman.h>
 #include <perf/cpumap.h>
+#include <perf/event.h>
 
 #include "map_symbol.h"
 #include "branch.h"
@@ -32,85 +34,33 @@
 #include "stat.h"
 #include "tsc.h"
 #include "ui/progress.h"
-#include "../perf.h"
+#include "util.h"
 #include "arch/common.h"
 #include "units.h"
+#include "annotate.h"
+#include "perf.h"
 #include <internal/lib.h>
 
-#ifdef HAVE_ZSTD_SUPPORT
-static int perf_session__process_compressed_event(struct perf_session *session,
-						  union perf_event *event, u64 file_offset)
-{
-	void *src;
-	size_t decomp_size, src_size;
-	u64 decomp_last_rem = 0;
-	size_t mmap_len, decomp_len = session->header.env.comp_mmap_len;
-	struct decomp *decomp, *decomp_last = session->active_decomp->decomp_last;
-
-	if (decomp_last) {
-		decomp_last_rem = decomp_last->size - decomp_last->head;
-		decomp_len += decomp_last_rem;
-	}
-
-	mmap_len = sizeof(struct decomp) + decomp_len;
-	decomp = mmap(NULL, mmap_len, PROT_READ|PROT_WRITE,
-		      MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
-	if (decomp == MAP_FAILED) {
-		pr_err("Couldn't allocate memory for decompression\n");
-		return -1;
-	}
-
-	decomp->file_pos = file_offset;
-	decomp->mmap_len = mmap_len;
-	decomp->head = 0;
-
-	if (decomp_last_rem) {
-		memcpy(decomp->data, &(decomp_last->data[decomp_last->head]), decomp_last_rem);
-		decomp->size = decomp_last_rem;
-	}
-
-	src = (void *)event + sizeof(struct perf_record_compressed);
-	src_size = event->pack.header.size - sizeof(struct perf_record_compressed);
-
-	decomp_size = zstd_decompress_stream(session->active_decomp->zstd_decomp, src, src_size,
-				&(decomp->data[decomp_last_rem]), decomp_len - decomp_last_rem);
-	if (!decomp_size) {
-		munmap(decomp, mmap_len);
-		pr_err("Couldn't decompress data\n");
-		return -1;
-	}
-
-	decomp->size += decomp_size;
-
-	if (session->active_decomp->decomp == NULL)
-		session->active_decomp->decomp = decomp;
-	else
-		session->active_decomp->decomp_last->next = decomp;
-
-	session->active_decomp->decomp_last = decomp;
-
-	pr_debug("decomp (B): %zd to %zd\n", src_size, decomp_size);
-
-	return 0;
-}
-#else /* !HAVE_ZSTD_SUPPORT */
-#define perf_session__process_compressed_event perf_session__process_compressed_event_stub
-#endif
-
 static int perf_session__deliver_event(struct perf_session *session,
 				       union perf_event *event,
-				       struct perf_tool *tool,
-				       u64 file_offset);
+				       const struct perf_tool *tool,
+				       u64 file_offset,
+				       const char *file_path);
 
-static int perf_session__open(struct perf_session *session, int repipe_fd)
+static int perf_session__open(struct perf_session *session)
 {
 	struct perf_data *data = session->data;
 
-	if (perf_session__read_header(session, repipe_fd) < 0) {
+	if (perf_session__read_header(session) < 0) {
 		pr_err("incompatible file format (rerun with -v to learn more)\n");
 		return -1;
 	}
 
+	if (perf_header__has_feat(&session->header, HEADER_AUXTRACE)) {
+		/* Auxiliary events may reference exited threads, hold onto dead ones. */
+		symbol_conf.keep_exited_threads = true;
+	}
+
 	if (perf_data__is_pipe(data))
 		return 0;
 
@@ -182,12 +132,14 @@ static int ordered_events__deliver_event(struct ordered_events *oe,
 						    ordered_events);
 
 	return perf_session__deliver_event(session, event->event,
-					   session->tool, event->file_offset);
+					   session->tool, event->file_offset,
+					   event->file_path);
 }
 
 struct perf_session *__perf_session__new(struct perf_data *data,
-					 bool repipe, int repipe_fd,
-					 struct perf_tool *tool)
+					 struct perf_tool *tool,
+					 bool trace_event_repipe,
+					 struct perf_env *host_env)
 {
 	int ret = -ENOMEM;
 	struct perf_session *session = zalloc(sizeof(*session));
@@ -195,7 +147,7 @@ struct perf_session *__perf_session__new(struct perf_data *data,
 	if (!session)
 		goto out;
 
-	session->repipe = repipe;
+	session->trace_event_repipe = trace_event_repipe;
 	session->tool   = tool;
 	session->decomp_data.zstd_decomp = &session->zstd_data;
 	session->active_decomp = &session->decomp_data;
@@ -213,7 +165,7 @@ struct perf_session *__perf_session__new(struct perf_data *data,
 		session->data = data;
 
 		if (perf_data__is_read(data)) {
-			ret = perf_session__open(session, repipe_fd);
+			ret = perf_session__open(session);
 			if (ret < 0)
 				goto out_delete;
 
@@ -226,7 +178,7 @@ struct perf_session *__perf_session__new(struct perf_data *data,
 				perf_session__set_comm_exec(session);
 			}
 
-			evlist__init_trace_event_sample_raw(session->evlist);
+			evlist__init_trace_event_sample_raw(session->evlist, &session->header.env);
 
 			/* Open the directory data. */
 			if (data->is_dir) {
@@ -240,8 +192,11 @@ struct perf_session *__perf_session__new(struct perf_data *data,
 				symbol_conf.kallsyms_name = perf_data__kallsyms_name(data);
 		}
 	} else  {
-		session->machines.host.env = &perf_env;
+		assert(host_env != NULL);
+		session->machines.host.env = host_env;
 	}
+	if (session->evlist)
+		session->evlist->session = session;
 
 	session->machines.host.single_address_space =
 		perf_env__single_address_space(session->machines.host.env);
@@ -273,11 +228,6 @@ struct perf_session *__perf_session__new(struct perf_data *data,
 	return ERR_PTR(ret);
 }
 
-static void perf_session__delete_threads(struct perf_session *session)
-{
-	machine__delete_threads(&session->machines.host);
-}
-
 static void perf_decomp__release_events(struct decomp *next)
 {
 	struct decomp *decomp;
@@ -299,8 +249,8 @@ void perf_session__delete(struct perf_session *session)
 		return;
 	auxtrace__free(session);
 	auxtrace_index__free(&session->auxtrace_index);
+	debuginfo_cache__delete();
 	perf_session__destroy_kernel_maps(session);
-	perf_session__delete_threads(session);
 	perf_decomp__release_events(session->decomp_data.decomp);
 	perf_env__exit(&session->header.env);
 	machines__exit(&session->machines);
@@ -309,256 +259,12 @@ void perf_session__delete(struct perf_session *session)
 			evlist__delete(session->evlist);
 		perf_data__close(session->data);
 	}
+#ifdef HAVE_LIBTRACEEVENT
 	trace_event__cleanup(&session->tevent);
+#endif
 	free(session);
 }
 
-static int process_event_synth_tracing_data_stub(struct perf_session *session
-						 __maybe_unused,
-						 union perf_event *event
-						 __maybe_unused)
-{
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
-static int process_event_synth_attr_stub(struct perf_tool *tool __maybe_unused,
-					 union perf_event *event __maybe_unused,
-					 struct evlist **pevlist
-					 __maybe_unused)
-{
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
-static int process_event_synth_event_update_stub(struct perf_tool *tool __maybe_unused,
-						 union perf_event *event __maybe_unused,
-						 struct evlist **pevlist
-						 __maybe_unused)
-{
-	if (dump_trace)
-		perf_event__fprintf_event_update(event, stdout);
-
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
-static int process_event_sample_stub(struct perf_tool *tool __maybe_unused,
-				     union perf_event *event __maybe_unused,
-				     struct perf_sample *sample __maybe_unused,
-				     struct evsel *evsel __maybe_unused,
-				     struct machine *machine __maybe_unused)
-{
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
-static int process_event_stub(struct perf_tool *tool __maybe_unused,
-			      union perf_event *event __maybe_unused,
-			      struct perf_sample *sample __maybe_unused,
-			      struct machine *machine __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 ordered_events *oe __maybe_unused)
-{
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
-static int process_finished_round(struct perf_tool *tool,
-				  union perf_event *event,
-				  struct ordered_events *oe);
-
-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_session *session __maybe_unused,
-				       union perf_event *event)
-{
-	dump_printf(": unhandled!\n");
-	if (perf_data__is_pipe(session->data))
-		skipn(perf_data__fd(session->data), event->auxtrace.size);
-	return event->auxtrace.size;
-}
-
-static int process_event_op2_stub(struct perf_session *session __maybe_unused,
-				  union perf_event *event __maybe_unused)
-{
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
-
-static
-int process_event_thread_map_stub(struct perf_session *session __maybe_unused,
-				  union perf_event *event __maybe_unused)
-{
-	if (dump_trace)
-		perf_event__fprintf_thread_map(event, stdout);
-
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
-static
-int process_event_cpu_map_stub(struct perf_session *session __maybe_unused,
-			       union perf_event *event __maybe_unused)
-{
-	if (dump_trace)
-		perf_event__fprintf_cpu_map(event, stdout);
-
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
-static
-int process_event_stat_config_stub(struct perf_session *session __maybe_unused,
-				   union perf_event *event __maybe_unused)
-{
-	if (dump_trace)
-		perf_event__fprintf_stat_config(event, stdout);
-
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
-static int process_stat_stub(struct perf_session *perf_session __maybe_unused,
-			     union perf_event *event)
-{
-	if (dump_trace)
-		perf_event__fprintf_stat(event, stdout);
-
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
-static int process_stat_round_stub(struct perf_session *perf_session __maybe_unused,
-				   union perf_event *event)
-{
-	if (dump_trace)
-		perf_event__fprintf_stat_round(event, stdout);
-
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
-static int process_event_time_conv_stub(struct perf_session *perf_session __maybe_unused,
-					union perf_event *event)
-{
-	if (dump_trace)
-		perf_event__fprintf_time_conv(event, stdout);
-
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
-static int perf_session__process_compressed_event_stub(struct perf_session *session __maybe_unused,
-						       union perf_event *event __maybe_unused,
-						       u64 file_offset __maybe_unused)
-{
-       dump_printf(": unhandled!\n");
-       return 0;
-}
-
-void perf_tool__fill_defaults(struct perf_tool *tool)
-{
-	if (tool->sample == NULL)
-		tool->sample = process_event_sample_stub;
-	if (tool->mmap == NULL)
-		tool->mmap = process_event_stub;
-	if (tool->mmap2 == NULL)
-		tool->mmap2 = process_event_stub;
-	if (tool->comm == NULL)
-		tool->comm = process_event_stub;
-	if (tool->namespaces == NULL)
-		tool->namespaces = process_event_stub;
-	if (tool->cgroup == NULL)
-		tool->cgroup = process_event_stub;
-	if (tool->fork == NULL)
-		tool->fork = process_event_stub;
-	if (tool->exit == NULL)
-		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->context_switch == NULL)
-		tool->context_switch = perf_event__process_switch;
-	if (tool->ksymbol == NULL)
-		tool->ksymbol = perf_event__process_ksymbol;
-	if (tool->bpf == NULL)
-		tool->bpf = perf_event__process_bpf;
-	if (tool->text_poke == NULL)
-		tool->text_poke = perf_event__process_text_poke;
-	if (tool->aux_output_hw_id == NULL)
-		tool->aux_output_hw_id = perf_event__process_aux_output_hw_id;
-	if (tool->read == NULL)
-		tool->read = process_event_sample_stub;
-	if (tool->throttle == NULL)
-		tool->throttle = process_event_stub;
-	if (tool->unthrottle == NULL)
-		tool->unthrottle = process_event_stub;
-	if (tool->attr == NULL)
-		tool->attr = process_event_synth_attr_stub;
-	if (tool->event_update == NULL)
-		tool->event_update = process_event_synth_event_update_stub;
-	if (tool->tracing_data == NULL)
-		tool->tracing_data = process_event_synth_tracing_data_stub;
-	if (tool->build_id == NULL)
-		tool->build_id = process_event_op2_stub;
-	if (tool->finished_round == NULL) {
-		if (tool->ordered_events)
-			tool->finished_round = process_finished_round;
-		else
-			tool->finished_round = process_finished_round_stub;
-	}
-	if (tool->id_index == NULL)
-		tool->id_index = process_event_op2_stub;
-	if (tool->auxtrace_info == NULL)
-		tool->auxtrace_info = process_event_op2_stub;
-	if (tool->auxtrace == NULL)
-		tool->auxtrace = process_event_auxtrace_stub;
-	if (tool->auxtrace_error == NULL)
-		tool->auxtrace_error = process_event_op2_stub;
-	if (tool->thread_map == NULL)
-		tool->thread_map = process_event_thread_map_stub;
-	if (tool->cpu_map == NULL)
-		tool->cpu_map = process_event_cpu_map_stub;
-	if (tool->stat_config == NULL)
-		tool->stat_config = process_event_stat_config_stub;
-	if (tool->stat == NULL)
-		tool->stat = process_stat_stub;
-	if (tool->stat_round == NULL)
-		tool->stat_round = process_stat_round_stub;
-	if (tool->time_conv == NULL)
-		tool->time_conv = process_event_time_conv_stub;
-	if (tool->feature == NULL)
-		tool->feature = process_event_op2_stub;
-	if (tool->compressed == NULL)
-		tool->compressed = perf_session__process_compressed_event;
-}
-
 static void swap_sample_id_all(union perf_event *event, void *data)
 {
 	void *end = (void *) event + event->header.size;
@@ -833,8 +539,8 @@ static void perf_event__hdr_attr_swap(union perf_event *event,
 	perf_event__attr_swap(&event->attr.attr);
 
 	size = event->header.size;
-	size -= (void *)&event->attr.id - (void *)event;
-	mem_bswap_64(event->attr.id, size);
+	size -= perf_record_header_attr_id(event) - (void *)event;
+	mem_bswap_64(perf_record_header_attr_id(event), size);
 }
 
 static void perf_event__event_update_swap(union perf_event *event,
@@ -892,6 +598,10 @@ static void perf_event__auxtrace_error_swap(union perf_event *event,
 	event->auxtrace_error.ip   = bswap_64(event->auxtrace_error.ip);
 	if (event->auxtrace_error.fmt)
 		event->auxtrace_error.time = bswap_64(event->auxtrace_error.time);
+	if (event->auxtrace_error.fmt >= 2) {
+		event->auxtrace_error.machine_pid = bswap_32(event->auxtrace_error.machine_pid);
+		event->auxtrace_error.vcpu = bswap_32(event->auxtrace_error.vcpu);
+	}
 }
 
 static void perf_event__thread_map_swap(union perf_event *event,
@@ -909,33 +619,38 @@ static void perf_event__cpu_map_swap(union perf_event *event,
 				     bool sample_id_all __maybe_unused)
 {
 	struct perf_record_cpu_map_data *data = &event->cpu_map.data;
-	struct cpu_map_entries *cpus;
-	struct perf_record_record_cpu_map *mask;
-	unsigned i;
 
 	data->type = bswap_16(data->type);
 
 	switch (data->type) {
 	case PERF_CPU_MAP__CPUS:
-		cpus = (struct cpu_map_entries *)data->data;
-
-		cpus->nr = bswap_16(cpus->nr);
+		data->cpus_data.nr = bswap_16(data->cpus_data.nr);
 
-		for (i = 0; i < cpus->nr; i++)
-			cpus->cpu[i] = bswap_16(cpus->cpu[i]);
+		for (unsigned i = 0; i < data->cpus_data.nr; i++)
+			data->cpus_data.cpu[i] = bswap_16(data->cpus_data.cpu[i]);
 		break;
 	case PERF_CPU_MAP__MASK:
-		mask = (struct perf_record_record_cpu_map *)data->data;
+		data->mask32_data.long_size = bswap_16(data->mask32_data.long_size);
 
-		mask->nr = bswap_16(mask->nr);
-		mask->long_size = bswap_16(mask->long_size);
-
-		switch (mask->long_size) {
-		case 4: mem_bswap_32(&mask->mask, mask->nr); break;
-		case 8: mem_bswap_64(&mask->mask, mask->nr); break;
+		switch (data->mask32_data.long_size) {
+		case 4:
+			data->mask32_data.nr = bswap_16(data->mask32_data.nr);
+			for (unsigned i = 0; i < data->mask32_data.nr; i++)
+				data->mask32_data.mask[i] = bswap_32(data->mask32_data.mask[i]);
+			break;
+		case 8:
+			data->mask64_data.nr = bswap_16(data->mask64_data.nr);
+			for (unsigned i = 0; i < data->mask64_data.nr; i++)
+				data->mask64_data.mask[i] = bswap_64(data->mask64_data.mask[i]);
+			break;
 		default:
 			pr_err("cpu_map swap: unsupported long size\n");
 		}
+		break;
+	case PERF_CPU_MAP__RANGE_CPUS:
+		data->range_cpu_data.start_cpu = bswap_16(data->range_cpu_data.start_cpu);
+		data->range_cpu_data.end_cpu = bswap_16(data->range_cpu_data.end_cpu);
+		break;
 	default:
 		break;
 	}
@@ -1005,6 +720,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_CGROUP]		  = perf_event__cgroup_swap,
 	[PERF_RECORD_TEXT_POKE]		  = perf_event__text_poke_swap,
 	[PERF_RECORD_AUX_OUTPUT_HW_ID]	  = perf_event__all64_swap,
+	[PERF_RECORD_CALLCHAIN_DEFERRED]  = 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,
@@ -1062,9 +778,9 @@ 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 __maybe_unused,
-				  union perf_event *event __maybe_unused,
-				  struct ordered_events *oe)
+int perf_event__process_finished_round(const struct perf_tool *tool __maybe_unused,
+				       union perf_event *event __maybe_unused,
+				       struct ordered_events *oe)
 {
 	if (dump_trace)
 		fprintf(stdout, "\n");
@@ -1072,9 +788,9 @@ static int process_finished_round(struct perf_tool *tool __maybe_unused,
 }
 
 int perf_session__queue_event(struct perf_session *s, union perf_event *event,
-			      u64 timestamp, u64 file_offset)
+			      u64 timestamp, u64 file_offset, const char *file_path)
 {
-	return ordered_events__queue(&s->ordered_events, event, timestamp, file_offset);
+	return ordered_events__queue(&s->ordered_events, event, timestamp, file_offset, file_path);
 }
 
 static void callchain__lbr_callstack_printf(struct perf_sample *sample)
@@ -1139,34 +855,68 @@ static void callchain__printf(struct evsel *evsel,
 	for (i = 0; i < callchain->nr; i++)
 		printf("..... %2d: %016" PRIx64 "\n",
 		       i, callchain->ips[i]);
+
+	if (sample->deferred_callchain)
+		printf("...... (deferred)\n");
 }
 
-static void branch_stack__printf(struct perf_sample *sample, bool callstack)
+static void branch_stack__printf(struct perf_sample *sample,
+				 struct evsel *evsel)
 {
 	struct branch_entry *entries = perf_sample__branch_entries(sample);
+	bool callstack = evsel__has_branch_callstack(evsel);
+	u64 *branch_stack_cntr = sample->branch_stack_cntr;
 	uint64_t i;
 
-	printf("%s: nr:%" PRIu64 "\n",
-		!callstack ? "... branch stack" : "... branch callstack",
-		sample->branch_stack->nr);
+	if (!callstack) {
+		printf("%s: nr:%" PRIu64 "\n", "... branch stack", sample->branch_stack->nr);
+	} else {
+		/* the reason of adding 1 to nr is because after expanding
+		 * branch stack it generates nr + 1 callstack records. e.g.,
+		 *         B()->C()
+		 *         A()->B()
+		 * the final callstack should be:
+		 *         C()
+		 *         B()
+		 *         A()
+		 */
+		printf("%s: nr:%" PRIu64 "\n", "... branch callstack", sample->branch_stack->nr+1);
+	}
 
 	for (i = 0; i < sample->branch_stack->nr; i++) {
 		struct branch_entry *e = &entries[i];
 
 		if (!callstack) {
-			printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n",
+			printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x %s %s\n",
 				i, e->from, e->to,
 				(unsigned short)e->flags.cycles,
 				e->flags.mispred ? "M" : " ",
 				e->flags.predicted ? "P" : " ",
 				e->flags.abort ? "A" : " ",
 				e->flags.in_tx ? "T" : " ",
-				(unsigned)e->flags.reserved);
+				(unsigned)e->flags.reserved,
+				get_branch_type(e),
+				e->flags.spec ? branch_spec_desc(e->flags.spec) : "");
 		} else {
-			printf("..... %2"PRIu64": %016" PRIx64 "\n",
-				i, i > 0 ? e->from : e->to);
+			if (i == 0) {
+				printf("..... %2"PRIu64": %016" PRIx64 "\n"
+				       "..... %2"PRIu64": %016" PRIx64 "\n",
+						i, e->to, i+1, e->from);
+			} else {
+				printf("..... %2"PRIu64": %016" PRIx64 "\n", i+1, e->from);
+			}
 		}
 	}
+
+	if (branch_stack_cntr) {
+		unsigned int br_cntr_width, br_cntr_nr;
+
+		perf_env__find_br_cntr_info(evsel__env(evsel), &br_cntr_nr, &br_cntr_width);
+		printf("... branch stack counters: nr:%" PRIu64 " (counter width: %u max counter nr:%u)\n",
+			sample->branch_stack->nr, br_cntr_width, br_cntr_nr);
+		for (i = 0; i < sample->branch_stack->nr; i++)
+			printf("..... %2"PRIu64": %016" PRIx64 "\n", i, branch_stack_cntr[i]);
+	}
 }
 
 static void regs_dump__printf(u64 mask, u64 *regs, const char *arch)
@@ -1209,7 +959,12 @@ static void regs__printf(const char *type, struct regs_dump *regs, const char *a
 
 static void regs_user__printf(struct perf_sample *sample, const char *arch)
 {
-	struct regs_dump *user_regs = &sample->user_regs;
+	struct regs_dump *user_regs;
+
+	if (!sample->user_regs)
+		return;
+
+	user_regs = perf_sample__user_regs(sample);
 
 	if (user_regs->regs)
 		regs__printf("user", user_regs, arch);
@@ -1217,7 +972,12 @@ static void regs_user__printf(struct perf_sample *sample, const char *arch)
 
 static void regs_intr__printf(struct perf_sample *sample, const char *arch)
 {
-	struct regs_dump *intr_regs = &sample->intr_regs;
+	struct regs_dump *intr_regs;
+
+	if (!sample->intr_regs)
+		return;
+
+	intr_regs = perf_sample__intr_regs(sample);
 
 	if (intr_regs->regs)
 		regs__printf("intr", intr_regs, arch);
@@ -1259,31 +1019,36 @@ static void sample_read__printf(struct perf_sample *sample, u64 read_format)
 		       sample->read.time_running);
 
 	if (read_format & PERF_FORMAT_GROUP) {
-		u64 i;
+		struct sample_read_value *value = sample->read.group.values;
 
 		printf(".... group nr %" PRIu64 "\n", sample->read.group.nr);
 
-		for (i = 0; i < sample->read.group.nr; i++) {
-			struct sample_read_value *value;
-
-			value = &sample->read.group.values[i];
+		sample_read_group__for_each(value, sample->read.group.nr, read_format) {
 			printf("..... id %016" PRIx64
-			       ", value %016" PRIx64 "\n",
+			       ", value %016" PRIx64,
 			       value->id, value->value);
+			if (read_format & PERF_FORMAT_LOST)
+				printf(", lost %" PRIu64, value->lost);
+			printf("\n");
 		}
-	} else
-		printf("..... id %016" PRIx64 ", value %016" PRIx64 "\n",
+	} else {
+		printf("..... id %016" PRIx64 ", value %016" PRIx64,
 			sample->read.one.id, sample->read.one.value);
+		if (read_format & PERF_FORMAT_LOST)
+			printf(", lost %" PRIu64, sample->read.one.lost);
+		printf("\n");
+	}
 }
 
 static void dump_event(struct evlist *evlist, union perf_event *event,
-		       u64 file_offset, struct perf_sample *sample)
+		       u64 file_offset, struct perf_sample *sample,
+		       const char *file_path)
 {
 	if (!dump_trace)
 		return;
 
-	printf("\n%#" PRIx64 " [%#x]: event: %d\n",
-	       file_offset, event->header.size, event->header.type);
+	printf("\n%#" PRIx64 "@%s [%#x]: event: %d\n",
+	       file_offset, file_path, event->header.size, event->header.type);
 
 	trace_event(event);
 	if (event->header.type == PERF_RECORD_SAMPLE && evlist->trace_event_sample_raw)
@@ -1323,7 +1088,7 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
 		callchain__printf(evsel, sample);
 
 	if (evsel__has_br_stack(evsel))
-		branch_stack__printf(sample, evsel__has_branch_callstack(evsel));
+		branch_stack__printf(sample, evsel);
 
 	if (sample_type & PERF_SAMPLE_REGS_USER)
 		regs_user__printf(sample, arch);
@@ -1338,7 +1103,7 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
 		printf("... weight: %" PRIu64 "", sample->weight);
 			if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) {
 				printf(",0x%"PRIx16"", sample->ins_lat);
-				printf(",0x%"PRIx16"", sample->p_stage_cyc);
+				printf(",0x%"PRIx16"", sample->weight3);
 			}
 		printf("\n");
 	}
@@ -1362,6 +1127,19 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
 		sample_read__printf(sample, evsel->core.attr.read_format);
 }
 
+static void dump_deferred_callchain(struct evsel *evsel, union perf_event *event,
+				    struct perf_sample *sample)
+{
+	if (!dump_trace)
+		return;
+
+	printf("(IP, 0x%x): %d/%d: %#" PRIx64 "\n",
+	       event->header.misc, sample->pid, sample->tid, sample->deferred_cookie);
+
+	if (evsel__has_callchain(evsel))
+		callchain__printf(evsel, sample);
+}
+
 static void dump_read(struct evsel *evsel, union perf_event *event)
 {
 	struct perf_record_read *read_event = &event->read;
@@ -1386,6 +1164,9 @@ static void dump_read(struct evsel *evsel, union perf_event *event)
 
 	if (read_format & PERF_FORMAT_ID)
 		printf("... id           : %" PRI_lu64 "\n", read_event->id);
+
+	if (read_format & PERF_FORMAT_LOST)
+		printf("... lost         : %" PRI_lu64 "\n", read_event->lost);
 }
 
 static struct machine *machines__find_for_cpumode(struct machines *machines,
@@ -1397,12 +1178,21 @@ static struct machine *machines__find_for_cpumode(struct machines *machines,
 	     (sample->cpumode == PERF_RECORD_MISC_GUEST_USER))) {
 		u32 pid;
 
-		if (event->header.type == PERF_RECORD_MMAP
+		if (sample->machine_pid)
+			pid = sample->machine_pid;
+		else if (event->header.type == PERF_RECORD_MMAP
 		    || event->header.type == PERF_RECORD_MMAP2)
 			pid = event->mmap.pid;
 		else
 			pid = sample->pid;
 
+		/*
+		 * Guest code machine is created as needed and does not use
+		 * DEFAULT_GUEST_KERNEL_ID.
+		 */
+		if (symbol_conf.guest_code)
+			return machines__findnew(machines, pid);
+
 		return machines__find_guest(machines, pid);
 	}
 
@@ -1410,22 +1200,28 @@ static struct machine *machines__find_for_cpumode(struct machines *machines,
 }
 
 static int deliver_sample_value(struct evlist *evlist,
-				struct perf_tool *tool,
+				const struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,
 				struct sample_read_value *v,
-				struct machine *machine)
+				struct machine *machine,
+				bool per_thread)
 {
 	struct perf_sample_id *sid = evlist__id2sid(evlist, v->id);
 	struct evsel *evsel;
+	u64 *storage = NULL;
 
 	if (sid) {
+		storage = perf_sample_id__get_period_storage(sid, sample->tid, per_thread);
+	}
+
+	if (storage) {
 		sample->id     = v->id;
-		sample->period = v->value - sid->period;
-		sid->period    = v->value;
+		sample->period = v->value - *storage;
+		*storage       = v->value;
 	}
 
-	if (!sid || sid->evsel == NULL) {
+	if (!storage || sid->evsel == NULL) {
 		++evlist->stats.nr_unknown_id;
 		return 0;
 	}
@@ -1442,18 +1238,23 @@ static int deliver_sample_value(struct evlist *evlist,
 }
 
 static int deliver_sample_group(struct evlist *evlist,
-				struct perf_tool *tool,
+				const struct perf_tool *tool,
 				union  perf_event *event,
 				struct perf_sample *sample,
-				struct machine *machine)
+				struct machine *machine,
+				u64 read_format,
+				bool per_thread)
 {
 	int ret = -EINVAL;
-	u64 i;
+	struct sample_read_value *v = sample->read.group.values;
 
-	for (i = 0; i < sample->read.group.nr; i++) {
-		ret = deliver_sample_value(evlist, tool, event, sample,
-					   &sample->read.group.values[i],
-					   machine);
+	if (tool->dont_split_sample_group)
+		return deliver_sample_value(evlist, tool, event, sample, v, machine,
+					    per_thread);
+
+	sample_read_group__for_each(v, sample->read.group.nr, read_format) {
+		ret = deliver_sample_value(evlist, tool, event, sample, v,
+					   machine, per_thread);
 		if (ret)
 			break;
 	}
@@ -1461,13 +1262,14 @@ static int deliver_sample_group(struct evlist *evlist,
 	return ret;
 }
 
-static int evlist__deliver_sample(struct evlist *evlist, struct perf_tool *tool,
+static int evlist__deliver_sample(struct evlist *evlist, const struct perf_tool *tool,
 				  union  perf_event *event, struct perf_sample *sample,
 				  struct evsel *evsel, struct machine *machine)
 {
 	/* We know evsel != NULL. */
 	u64 sample_type = evsel->core.attr.sample_type;
 	u64 read_format = evsel->core.attr.read_format;
+	bool per_thread = perf_evsel__attr_has_per_thread_sample_period(&evsel->core);
 
 	/* Standard sample delivery. */
 	if (!(sample_type & PERF_SAMPLE_READ))
@@ -1476,22 +1278,124 @@ static int evlist__deliver_sample(struct evlist *evlist, struct perf_tool *tool,
 	/* For PERF_SAMPLE_READ we have either single or group mode. */
 	if (read_format & PERF_FORMAT_GROUP)
 		return deliver_sample_group(evlist, tool, event, sample,
-					    machine);
+					    machine, read_format, per_thread);
 	else
 		return deliver_sample_value(evlist, tool, event, sample,
-					    &sample->read.one, machine);
+					    &sample->read.one, machine,
+					    per_thread);
+}
+
+/*
+ * Samples with deferred callchains should wait for the next matching
+ * PERF_RECORD_CALLCHAIN_RECORD entries.  Keep the events in a list and
+ * deliver them once it finds the callchains.
+ */
+struct deferred_event {
+	struct list_head list;
+	union perf_event *event;
+};
+
+/*
+ * This is called when a deferred callchain record comes up.  Find all matching
+ * samples, merge the callchains and process them.
+ */
+static int evlist__deliver_deferred_callchain(struct evlist *evlist,
+					      const struct perf_tool *tool,
+					      union  perf_event *event,
+					      struct perf_sample *sample,
+					      struct machine *machine)
+{
+	struct deferred_event *de, *tmp;
+	struct evsel *evsel;
+	int ret = 0;
+
+	if (!tool->merge_deferred_callchains) {
+		evsel = evlist__id2evsel(evlist, sample->id);
+		return tool->callchain_deferred(tool, event, sample,
+						evsel, machine);
+	}
+
+	list_for_each_entry_safe(de, tmp, &evlist->deferred_samples, list) {
+		struct perf_sample orig_sample;
+
+		ret = evlist__parse_sample(evlist, de->event, &orig_sample);
+		if (ret < 0) {
+			pr_err("failed to parse original sample\n");
+			break;
+		}
+
+		if (sample->tid != orig_sample.tid)
+			continue;
+
+		if (event->callchain_deferred.cookie == orig_sample.deferred_cookie)
+			sample__merge_deferred_callchain(&orig_sample, sample);
+		else
+			orig_sample.deferred_callchain = false;
+
+		evsel = evlist__id2evsel(evlist, orig_sample.id);
+		ret = evlist__deliver_sample(evlist, tool, de->event,
+					     &orig_sample, evsel, machine);
+
+		if (orig_sample.deferred_callchain)
+			free(orig_sample.callchain);
+
+		list_del(&de->list);
+		free(de->event);
+		free(de);
+
+		if (ret)
+			break;
+	}
+	return ret;
+}
+
+/*
+ * This is called at the end of the data processing for the session.  Flush the
+ * remaining samples as there's no hope for matching deferred callchains.
+ */
+static int session__flush_deferred_samples(struct perf_session *session,
+					   const struct perf_tool *tool)
+{
+	struct evlist *evlist = session->evlist;
+	struct machine *machine = &session->machines.host;
+	struct deferred_event *de, *tmp;
+	struct evsel *evsel;
+	int ret = 0;
+
+	list_for_each_entry_safe(de, tmp, &evlist->deferred_samples, list) {
+		struct perf_sample sample;
+
+		ret = evlist__parse_sample(evlist, de->event, &sample);
+		if (ret < 0) {
+			pr_err("failed to parse original sample\n");
+			break;
+		}
+
+		evsel = evlist__id2evsel(evlist, sample.id);
+		ret = evlist__deliver_sample(evlist, tool, de->event,
+					     &sample, evsel, machine);
+
+		list_del(&de->list);
+		free(de->event);
+		free(de);
+
+		if (ret)
+			break;
+	}
+	return ret;
 }
 
 static int machines__deliver_event(struct machines *machines,
 				   struct evlist *evlist,
 				   union perf_event *event,
 				   struct perf_sample *sample,
-				   struct perf_tool *tool, u64 file_offset)
+				   const struct perf_tool *tool, u64 file_offset,
+				   const char *file_path)
 {
 	struct evsel *evsel;
 	struct machine *machine;
 
-	dump_event(evlist, event, file_offset, sample);
+	dump_event(evlist, event, file_offset, sample, file_path);
 
 	evsel = evlist__id2evsel(evlist, sample->id);
 
@@ -1503,9 +1407,26 @@ static int machines__deliver_event(struct machines *machines,
 			++evlist->stats.nr_unknown_id;
 			return 0;
 		}
-		dump_sample(evsel, event, sample, perf_env__arch(machine->env));
 		if (machine == NULL) {
 			++evlist->stats.nr_unprocessable_samples;
+			dump_sample(evsel, event, sample, perf_env__arch(NULL));
+			return 0;
+		}
+		dump_sample(evsel, event, sample, perf_env__arch(machine->env));
+		if (sample->deferred_callchain && tool->merge_deferred_callchains) {
+			struct deferred_event *de = malloc(sizeof(*de));
+			size_t sz = event->header.size;
+
+			if (de == NULL)
+				return -ENOMEM;
+
+			de->event = malloc(sz);
+			if (de->event == NULL) {
+				free(de);
+				return -ENOMEM;
+			}
+			memcpy(de->event, event, sz);
+			list_add_tail(&de->list, &evlist->deferred_samples);
 			return 0;
 		}
 		return evlist__deliver_sample(evlist, tool, event, sample, evsel, machine);
@@ -1530,7 +1451,9 @@ static int machines__deliver_event(struct machines *machines,
 			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)
+		if (event->header.misc & PERF_RECORD_MISC_LOST_SAMPLES_BPF)
+			evlist->stats.total_dropped_samples += event->lost_samples.lost;
+		else 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:
@@ -1563,6 +1486,10 @@ static int machines__deliver_event(struct machines *machines,
 		return tool->text_poke(tool, event, sample, machine);
 	case PERF_RECORD_AUX_OUTPUT_HW_ID:
 		return tool->aux_output_hw_id(tool, event, sample, machine);
+	case PERF_RECORD_CALLCHAIN_DEFERRED:
+		dump_deferred_callchain(evsel, event, sample);
+		return evlist__deliver_deferred_callchain(evlist, tool, event,
+							  sample, machine);
 	default:
 		++evlist->stats.nr_unknown_events;
 		return -1;
@@ -1571,45 +1498,54 @@ static int machines__deliver_event(struct machines *machines,
 
 static int perf_session__deliver_event(struct perf_session *session,
 				       union perf_event *event,
-				       struct perf_tool *tool,
-				       u64 file_offset)
+				       const struct perf_tool *tool,
+				       u64 file_offset,
+				       const char *file_path)
 {
 	struct perf_sample sample;
-	int ret = evlist__parse_sample(session->evlist, event, &sample);
+	int ret;
 
+	perf_sample__init(&sample, /*all=*/false);
+	ret = evlist__parse_sample(session->evlist, event, &sample);
 	if (ret) {
 		pr_err("Can't parse sample, err = %d\n", ret);
-		return ret;
+		goto out;
 	}
 
 	ret = auxtrace__process_event(session, event, &sample, tool);
 	if (ret < 0)
-		return ret;
-	if (ret > 0)
-		return 0;
+		goto out;
+	if (ret > 0) {
+		ret = 0;
+		goto out;
+	}
 
 	ret = machines__deliver_event(&session->machines, session->evlist,
-				      event, &sample, tool, file_offset);
+				      event, &sample, tool, file_offset, file_path);
 
 	if (dump_trace && sample.aux_sample.size)
 		auxtrace__dump_auxtrace_sample(session, &sample);
-
+out:
+	perf_sample__exit(&sample);
 	return ret;
 }
 
 static s64 perf_session__process_user_event(struct perf_session *session,
 					    union perf_event *event,
-					    u64 file_offset)
+					    u64 file_offset,
+					    const char *file_path)
 {
 	struct ordered_events *oe = &session->ordered_events;
-	struct perf_tool *tool = session->tool;
-	struct perf_sample sample = { .time = 0, };
+	const struct perf_tool *tool = session->tool;
+	struct perf_sample sample;
 	int fd = perf_data__fd(session->data);
-	int err;
+	s64 err;
 
-	if (event->header.type != PERF_RECORD_COMPRESSED ||
-	    tool->compressed == perf_session__process_compressed_event_stub)
-		dump_event(session->evlist, event, file_offset, &sample);
+	perf_sample__init(&sample, /*all=*/true);
+	if ((event->header.type != PERF_RECORD_COMPRESSED &&
+	     event->header.type != PERF_RECORD_COMPRESSED2) ||
+	    perf_tool__compressed_is_stub(tool))
+		dump_event(session->evlist, event, file_offset, &sample, file_path);
 
 	/* These events are processed right away */
 	switch (event->header.type) {
@@ -1619,15 +1555,17 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 			perf_session__set_id_hdr_size(session);
 			perf_session__set_comm_exec(session);
 		}
-		return err;
+		break;
 	case PERF_RECORD_EVENT_UPDATE:
-		return tool->event_update(tool, event, &session->evlist);
+		err = tool->event_update(tool, event, &session->evlist);
+		break;
 	case PERF_RECORD_HEADER_EVENT_TYPE:
 		/*
 		 * Deprecated, but we need to handle it for sake
 		 * of old data files create in pipe mode.
 		 */
-		return 0;
+		err = 0;
+		break;
 	case PERF_RECORD_HEADER_TRACING_DATA:
 		/*
 		 * Setup for reading amidst mmap, but only when we
@@ -1636,45 +1574,74 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 		 */
 		if (!perf_data__is_pipe(session->data))
 			lseek(fd, file_offset, SEEK_SET);
-		return tool->tracing_data(session, event);
+		err = tool->tracing_data(tool, session, event);
+		break;
 	case PERF_RECORD_HEADER_BUILD_ID:
-		return tool->build_id(session, event);
+		err = tool->build_id(tool, session, event);
+		break;
 	case PERF_RECORD_FINISHED_ROUND:
-		return tool->finished_round(tool, event, oe);
+		err = tool->finished_round(tool, event, oe);
+		break;
 	case PERF_RECORD_ID_INDEX:
-		return tool->id_index(session, event);
+		err = tool->id_index(tool, session, event);
+		break;
 	case PERF_RECORD_AUXTRACE_INFO:
-		return tool->auxtrace_info(session, event);
+		err = tool->auxtrace_info(tool, session, event);
+		break;
 	case PERF_RECORD_AUXTRACE:
-		/* setup for reading amidst mmap */
-		lseek(fd, file_offset + event->header.size, SEEK_SET);
-		return tool->auxtrace(session, event);
+		/*
+		 * Setup for reading amidst mmap, but only when we
+		 * are in 'file' mode.  The 'pipe' fd is in proper
+		 * place already.
+		 */
+		if (!perf_data__is_pipe(session->data))
+			lseek(fd, file_offset + event->header.size, SEEK_SET);
+		err = tool->auxtrace(tool, session, event);
+		break;
 	case PERF_RECORD_AUXTRACE_ERROR:
 		perf_session__auxtrace_error_inc(session, event);
-		return tool->auxtrace_error(session, event);
+		err = tool->auxtrace_error(tool, session, event);
+		break;
 	case PERF_RECORD_THREAD_MAP:
-		return tool->thread_map(session, event);
+		err = tool->thread_map(tool, session, event);
+		break;
 	case PERF_RECORD_CPU_MAP:
-		return tool->cpu_map(session, event);
+		err = tool->cpu_map(tool, session, event);
+		break;
 	case PERF_RECORD_STAT_CONFIG:
-		return tool->stat_config(session, event);
+		err = tool->stat_config(tool, session, event);
+		break;
 	case PERF_RECORD_STAT:
-		return tool->stat(session, event);
+		err = tool->stat(tool, session, event);
+		break;
 	case PERF_RECORD_STAT_ROUND:
-		return tool->stat_round(session, event);
+		err = tool->stat_round(tool, session, event);
+		break;
 	case PERF_RECORD_TIME_CONV:
 		session->time_conv = event->time_conv;
-		return tool->time_conv(session, event);
+		err = tool->time_conv(tool, session, event);
+		break;
 	case PERF_RECORD_HEADER_FEATURE:
-		return tool->feature(session, event);
+		err = tool->feature(tool, session, event);
+		break;
 	case PERF_RECORD_COMPRESSED:
-		err = tool->compressed(session, event, file_offset);
+	case PERF_RECORD_COMPRESSED2:
+		err = tool->compressed(tool, session, event, file_offset, file_path);
 		if (err)
-			dump_event(session->evlist, event, file_offset, &sample);
-		return err;
+			dump_event(session->evlist, event, file_offset, &sample, file_path);
+		break;
+	case PERF_RECORD_FINISHED_INIT:
+		err = tool->finished_init(tool, session, event);
+		break;
+	case PERF_RECORD_BPF_METADATA:
+		err = tool->bpf_metadata(tool, session, event);
+		break;
 	default:
-		return -EINVAL;
+		err = -EINVAL;
+		break;
 	}
+	perf_sample__exit(&sample);
+	return err;
 }
 
 int perf_session__deliver_synth_event(struct perf_session *session,
@@ -1682,14 +1649,38 @@ int perf_session__deliver_synth_event(struct perf_session *session,
 				      struct perf_sample *sample)
 {
 	struct evlist *evlist = session->evlist;
-	struct perf_tool *tool = session->tool;
+	const 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, 0);
+		return perf_session__process_user_event(session, event, 0, NULL);
+
+	return machines__deliver_event(&session->machines, evlist, event, sample, tool, 0, NULL);
+}
+
+int perf_session__deliver_synth_attr_event(struct perf_session *session,
+					   const struct perf_event_attr *attr,
+					   u64 id)
+{
+	union {
+		struct {
+			struct perf_record_header_attr attr;
+			u64 ids[1];
+		} attr_id;
+		union perf_event ev;
+	} ev = {
+		.attr_id.attr.header.type = PERF_RECORD_HEADER_ATTR,
+		.attr_id.attr.header.size = sizeof(ev.attr_id),
+		.attr_id.ids[0] = id,
+	};
 
-	return machines__deliver_event(&session->machines, evlist, event, sample, tool, 0);
+	if (attr->size != sizeof(ev.attr_id.attr.attr)) {
+		pr_debug("Unexpected perf_event_attr size\n");
+		return -EINVAL;
+	}
+	ev.attr_id.attr.attr = *attr;
+	return perf_session__deliver_synth_event(session, &ev.ev, NULL);
 }
 
 static void event_swap(union perf_event *event, bool sample_id_all)
@@ -1786,22 +1777,32 @@ int perf_session__peek_events(struct perf_session *session, u64 offset,
 }
 
 static s64 perf_session__process_event(struct perf_session *session,
-				       union perf_event *event, u64 file_offset)
+				       union perf_event *event, u64 file_offset,
+				       const char *file_path)
 {
 	struct evlist *evlist = session->evlist;
-	struct perf_tool *tool = session->tool;
+	const struct perf_tool *tool = session->tool;
 	int ret;
 
 	if (session->header.needs_swap)
 		event_swap(event, evlist__sample_id_all(evlist));
 
-	if (event->header.type >= PERF_RECORD_HEADER_MAX)
-		return -EINVAL;
+	if (event->header.type >= PERF_RECORD_HEADER_MAX) {
+		/* perf should not support unaligned event, stop here. */
+		if (event->header.size % sizeof(u64))
+			return -EINVAL;
+
+		/* This perf is outdated and does not support the latest event type. */
+		ui__warning("Unsupported header type %u, please consider updating perf.\n",
+			    event->header.type);
+		/* Skip unsupported event by returning its size. */
+		return event->header.size;
+	}
 
 	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, file_offset);
+		return perf_session__process_user_event(session, event, file_offset, file_path);
 
 	if (tool->ordered_events) {
 		u64 timestamp = -1ULL;
@@ -1810,12 +1811,12 @@ static s64 perf_session__process_event(struct perf_session *session,
 		if (ret && ret != -1)
 			return ret;
 
-		ret = perf_session__queue_event(session, event, timestamp, file_offset);
+		ret = perf_session__queue_event(session, event, timestamp, file_offset, file_path);
 		if (ret != -ETIME)
 			return ret;
 	}
 
-	return perf_session__deliver_event(session, event, tool, file_offset);
+	return perf_session__deliver_event(session, event, tool, file_offset, file_path);
 }
 
 void perf_event_header__bswap(struct perf_event_header *hdr)
@@ -1969,14 +1970,15 @@ static int perf_session__flush_thread_stacks(struct perf_session *session)
 					 NULL);
 }
 
-volatile int session_done;
+volatile sig_atomic_t session_done;
 
 static int __perf_session__process_decomp_events(struct perf_session *session);
 
 static int __perf_session__process_pipe_events(struct perf_session *session)
 {
 	struct ordered_events *oe = &session->ordered_events;
-	struct perf_tool *tool = session->tool;
+	const struct perf_tool *tool = session->tool;
+	struct ui_progress prog;
 	union perf_event *event;
 	uint32_t size, cur_size = 0;
 	void *buf = NULL;
@@ -1984,8 +1986,18 @@ static int __perf_session__process_pipe_events(struct perf_session *session)
 	u64 head;
 	ssize_t err;
 	void *p;
+	bool update_prog = false;
 
-	perf_tool__fill_defaults(tool);
+	/*
+	 * If it's from a file saving pipe data (by redirection), it would have
+	 * a file name other than "-".  Then we can get the total size and show
+	 * the progress.
+	 */
+	if (strcmp(session->data->path, "-") && session->data->file.size) {
+		ui_progress__init_size(&prog, session->data->file.size,
+				       "Processing events...");
+		update_prog = true;
+	}
 
 	head = 0;
 	cur_size = sizeof(union perf_event);
@@ -2042,7 +2054,7 @@ more:
 		}
 	}
 
-	if ((skip = perf_session__process_event(session, event, head)) < 0) {
+	if ((skip = perf_session__process_event(session, event, head, "pipe")) < 0) {
 		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
 		       head, event->header.size, event->header.type);
 		err = -EINVAL;
@@ -2058,6 +2070,9 @@ more:
 	if (err)
 		goto out_err;
 
+	if (update_prog)
+		ui_progress__update(&prog, size);
+
 	if (!session_done())
 		goto more;
 done:
@@ -2065,12 +2080,17 @@ done:
 	err = ordered_events__flush(oe, OE_FLUSH__FINAL);
 	if (err)
 		goto out_err;
+	err = session__flush_deferred_samples(session, tool);
+	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);
+	if (update_prog)
+		ui_progress__finish();
 	if (!tool->no_warn)
 		perf_session__warn_about_errors(session);
 	ordered_events__free(&session->ordered_events);
@@ -2083,6 +2103,7 @@ prefetch_event(char *buf, u64 head, size_t mmap_size,
 	       bool needs_swap, union perf_event *error)
 {
 	union perf_event *event;
+	u16 event_size;
 
 	/*
 	 * Ensure we have enough space remaining to read
@@ -2095,15 +2116,23 @@ prefetch_event(char *buf, u64 head, size_t mmap_size,
 	if (needs_swap)
 		perf_event_header__bswap(&event->header);
 
-	if (head + event->header.size <= mmap_size)
+	event_size = event->header.size;
+	if (head + event_size <= mmap_size)
 		return event;
 
 	/* We're not fetching the event so swap back again */
 	if (needs_swap)
 		perf_event_header__bswap(&event->header);
 
-	pr_debug("%s: head=%#" PRIx64 " event->header_size=%#x, mmap_size=%#zx:"
-		 " fuzzed or compressed perf.data?\n",__func__, head, event->header.size, mmap_size);
+	/* Check if the event fits into the next mmapped buf. */
+	if (event_size <= mmap_size - head % page_size) {
+		/* Remap buf and fetch again. */
+		return NULL;
+	}
+
+	/* Invalid input. Event size should never exceed mmap_size. */
+	pr_debug("%s: head=%#" PRIx64 " event->header.size=%#x, mmap_size=%#zx:"
+		 " fuzzed or compressed perf.data?\n", __func__, head, event_size, mmap_size);
 
 	return error;
 }
@@ -2139,7 +2168,8 @@ static int __perf_session__process_decomp_events(struct perf_session *session)
 		size = event->header.size;
 
 		if (size < sizeof(struct perf_event_header) ||
-		    (skip = perf_session__process_event(session, event, decomp->file_pos)) < 0) {
+		    (skip = perf_session__process_event(session, event, decomp->file_pos,
+							decomp->file_path)) < 0) {
 			pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
 				decomp->file_pos + decomp->head, event->header.size, event->header.type);
 			return -EINVAL;
@@ -2170,10 +2200,12 @@ struct reader;
 
 typedef s64 (*reader_cb_t)(struct perf_session *session,
 			   union perf_event *event,
-			   u64 file_offset);
+			   u64 file_offset,
+			   const char *file_path);
 
 struct reader {
 	int		 fd;
+	const char	 *path;
 	u64		 data_size;
 	u64		 data_offset;
 	reader_cb_t	 process;
@@ -2185,6 +2217,8 @@ struct reader {
 	u64		 file_pos;
 	u64		 file_offset;
 	u64		 head;
+	u64		 size;
+	bool		 done;
 	struct zstd_data   zstd_data;
 	struct decomp_data decomp_data;
 };
@@ -2291,7 +2325,7 @@ reader__read_event(struct reader *rd, struct perf_session *session,
 	skip = -EINVAL;
 
 	if (size < sizeof(struct perf_event_header) ||
-	    (skip = rd->process(session, event, rd->file_pos)) < 0) {
+	    (skip = rd->process(session, event, rd->file_pos, rd->path)) < 0) {
 		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d [%s]\n",
 		       rd->file_offset + rd->head, event->header.size,
 		       event->header.type, strerror(-skip));
@@ -2302,6 +2336,7 @@ reader__read_event(struct reader *rd, struct perf_session *session,
 	if (skip)
 		size += skip;
 
+	rd->size += size;
 	rd->head += size;
 	rd->file_pos += size;
 
@@ -2358,27 +2393,27 @@ out:
 
 static s64 process_simple(struct perf_session *session,
 			  union perf_event *event,
-			  u64 file_offset)
+			  u64 file_offset,
+			  const char *file_path)
 {
-	return perf_session__process_event(session, event, file_offset);
+	return perf_session__process_event(session, event, file_offset, file_path);
 }
 
 static int __perf_session__process_events(struct perf_session *session)
 {
 	struct reader rd = {
 		.fd		= perf_data__fd(session->data),
+		.path		= session->data->file.path,
 		.data_size	= session->header.data_size,
 		.data_offset	= session->header.data_offset,
 		.process	= process_simple,
 		.in_place_update = session->data->in_place_update,
 	};
 	struct ordered_events *oe = &session->ordered_events;
-	struct perf_tool *tool = session->tool;
+	const struct perf_tool *tool = session->tool;
 	struct ui_progress prog;
 	int err;
 
-	perf_tool__fill_defaults(tool);
-
 	if (rd.data_size == 0)
 		return -1;
 
@@ -2394,6 +2429,9 @@ static int __perf_session__process_events(struct perf_session *session)
 	err = auxtrace__flush_events(session, tool);
 	if (err)
 		goto out_err;
+	err = session__flush_deferred_samples(session, tool);
+	if (err)
+		goto out_err;
 	err = perf_session__flush_thread_stacks(session);
 out_err:
 	ui_progress__finish();
@@ -2410,6 +2448,137 @@ out_err:
 	return err;
 }
 
+/*
+ * Processing 2 MB of data from each reader in sequence,
+ * because that's the way the ordered events sorting works
+ * most efficiently.
+ */
+#define READER_MAX_SIZE (2 * 1024 * 1024)
+
+/*
+ * This function reads, merge and process directory data.
+ * It assumens the version 1 of directory data, where each
+ * data file holds per-cpu data, already sorted by kernel.
+ */
+static int __perf_session__process_dir_events(struct perf_session *session)
+{
+	struct perf_data *data = session->data;
+	const struct perf_tool *tool = session->tool;
+	int i, ret, readers, nr_readers;
+	struct ui_progress prog;
+	u64 total_size = perf_data__size(session->data);
+	struct reader *rd;
+
+	ui_progress__init_size(&prog, total_size, "Processing events...");
+
+	nr_readers = 1;
+	for (i = 0; i < data->dir.nr; i++) {
+		if (data->dir.files[i].size)
+			nr_readers++;
+	}
+
+	rd = zalloc(nr_readers * sizeof(struct reader));
+	if (!rd)
+		return -ENOMEM;
+
+	rd[0] = (struct reader) {
+		.fd		 = perf_data__fd(session->data),
+		.path		 = session->data->file.path,
+		.data_size	 = session->header.data_size,
+		.data_offset	 = session->header.data_offset,
+		.process	 = process_simple,
+		.in_place_update = session->data->in_place_update,
+	};
+	ret = reader__init(&rd[0], NULL);
+	if (ret)
+		goto out_err;
+	ret = reader__mmap(&rd[0], session);
+	if (ret)
+		goto out_err;
+	readers = 1;
+
+	for (i = 0; i < data->dir.nr; i++) {
+		if (!data->dir.files[i].size)
+			continue;
+		rd[readers] = (struct reader) {
+			.fd		 = data->dir.files[i].fd,
+			.path		 = data->dir.files[i].path,
+			.data_size	 = data->dir.files[i].size,
+			.data_offset	 = 0,
+			.process	 = process_simple,
+			.in_place_update = session->data->in_place_update,
+		};
+		ret = reader__init(&rd[readers], NULL);
+		if (ret)
+			goto out_err;
+		ret = reader__mmap(&rd[readers], session);
+		if (ret)
+			goto out_err;
+		readers++;
+	}
+
+	i = 0;
+	while (readers) {
+		if (session_done())
+			break;
+
+		if (rd[i].done) {
+			i = (i + 1) % nr_readers;
+			continue;
+		}
+		if (reader__eof(&rd[i])) {
+			rd[i].done = true;
+			readers--;
+			continue;
+		}
+
+		session->active_decomp = &rd[i].decomp_data;
+		ret = reader__read_event(&rd[i], session, &prog);
+		if (ret < 0) {
+			goto out_err;
+		} else if (ret == READER_NODATA) {
+			ret = reader__mmap(&rd[i], session);
+			if (ret)
+				goto out_err;
+		}
+
+		if (rd[i].size >= READER_MAX_SIZE) {
+			rd[i].size = 0;
+			i = (i + 1) % nr_readers;
+		}
+	}
+
+	ret = ordered_events__flush(&session->ordered_events, OE_FLUSH__FINAL);
+	if (ret)
+		goto out_err;
+
+	ret = session__flush_deferred_samples(session, tool);
+	if (ret)
+		goto out_err;
+
+	ret = perf_session__flush_thread_stacks(session);
+out_err:
+	ui_progress__finish();
+
+	if (!tool->no_warn)
+		perf_session__warn_about_errors(session);
+
+	/*
+	 * We may switching perf.data output, make ordered_events
+	 * reusable.
+	 */
+	ordered_events__reinit(&session->ordered_events);
+
+	session->one_mmap = false;
+
+	session->active_decomp = &session->decomp_data;
+	for (i = 0; i < nr_readers; i++)
+		reader__release_decomp(&rd[i]);
+	zfree(&rd);
+
+	return ret;
+}
+
 int perf_session__process_events(struct perf_session *session)
 {
 	if (perf_session__register_idle_thread(session) < 0)
@@ -2418,6 +2587,9 @@ int perf_session__process_events(struct perf_session *session)
 	if (perf_data__is_pipe(session->data))
 		return __perf_session__process_pipe_events(session);
 
+	if (perf_data__is_dir(session->data) && session->data->dir.nr)
+		return __perf_session__process_dir_events(session);
+
 	return __perf_session__process_events(session);
 }
 
@@ -2434,6 +2606,18 @@ bool perf_session__has_traces(struct perf_session *session, const char *msg)
 	return false;
 }
 
+bool perf_session__has_switch_events(struct perf_session *session)
+{
+	struct evsel *evsel;
+
+	evlist__for_each_entry(session->evlist, evsel) {
+		if (evsel->core.attr.context_switch)
+			return true;
+	}
+
+	return false;
+}
+
 int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, u64 addr)
 {
 	char *bracket;
@@ -2474,8 +2658,7 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp
 	return machines__fprintf_dsos_buildid(&session->machines, fp, skip, parm);
 }
 
-size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp,
-				       bool skip_empty)
+size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
 {
 	size_t ret;
 	const char *msg = "";
@@ -2485,7 +2668,7 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp,
 
 	ret = fprintf(fp, "\nAggregated stats:%s\n", msg);
 
-	ret += events_stats__fprintf(&session->evlist->stats, fp, skip_empty);
+	ret += events_stats__fprintf(&session->evlist->stats, fp);
 	return ret;
 }
 
@@ -2498,6 +2681,17 @@ size_t perf_session__fprintf(struct perf_session *session, FILE *fp)
 	return machine__fprintf(&session->machines.host, fp);
 }
 
+void perf_session__dump_kmaps(struct perf_session *session)
+{
+	int save_verbose = verbose;
+
+	fflush(stdout);
+	fprintf(stderr, "Kernel and module maps:\n");
+	verbose = 0; /* Suppress verbose to print a summary only */
+	maps__fprintf(machine__kernel_maps(&session->machines.host), stderr);
+	verbose = save_verbose;
+}
+
 struct evsel *perf_session__find_first_evtype(struct perf_session *session,
 					      unsigned int type)
 {
@@ -2515,7 +2709,8 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 {
 	int i, err = -1;
 	struct perf_cpu_map *map;
-	int nr_cpus = min(session->header.env.nr_cpus_avail, MAX_NR_CPUS);
+	int nr_cpus = min(perf_session__env(session)->nr_cpus_avail, MAX_NR_CPUS);
+	struct perf_cpu cpu;
 
 	for (i = 0; i < PERF_TYPE_MAX; ++i) {
 		struct evsel *evsel;
@@ -2537,16 +2732,14 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 		return -1;
 	}
 
-	for (i = 0; i < perf_cpu_map__nr(map); i++) {
-		struct perf_cpu cpu = perf_cpu_map__cpu(map, i);
-
+	perf_cpu_map__for_each_cpu(cpu, i, map) {
 		if (cpu.cpu >= nr_cpus) {
 			pr_err("Requested CPU %d too large. "
 			       "Consider raising MAX_NR_CPUS\n", cpu.cpu);
 			goto out_delete_map;
 		}
 
-		set_bit(cpu.cpu, cpu_bitmap);
+		__set_bit(cpu.cpu, cpu_bitmap);
 	}
 
 	err = 0;
@@ -2567,39 +2760,147 @@ void perf_session__fprintf_info(struct perf_session *session, FILE *fp,
 	fprintf(fp, "# ========\n#\n");
 }
 
-int perf_event__process_id_index(struct perf_session *session,
+static int perf_session__register_guest(struct perf_session *session, pid_t machine_pid)
+{
+	struct machine *machine = machines__findnew(&session->machines, machine_pid);
+	struct thread *thread;
+
+	if (!machine)
+		return -ENOMEM;
+
+	machine->single_address_space = session->machines.host.single_address_space;
+
+	thread = machine__idle_thread(machine);
+	if (!thread)
+		return -ENOMEM;
+	thread__put(thread);
+
+	machine->kallsyms_filename = perf_data__guest_kallsyms_name(session->data, machine_pid);
+
+	return 0;
+}
+
+static int perf_session__set_guest_cpu(struct perf_session *session, pid_t pid,
+				       pid_t tid, int guest_cpu)
+{
+	struct machine *machine = &session->machines.host;
+	struct thread *thread = machine__findnew_thread(machine, pid, tid);
+
+	if (!thread)
+		return -ENOMEM;
+	thread__set_guest_cpu(thread, guest_cpu);
+	thread__put(thread);
+
+	return 0;
+}
+
+int perf_event__process_id_index(const struct perf_tool *tool __maybe_unused,
+				 struct perf_session *session,
 				 union perf_event *event)
 {
 	struct evlist *evlist = session->evlist;
 	struct perf_record_id_index *ie = &event->id_index;
+	size_t sz = ie->header.size - sizeof(*ie);
 	size_t i, nr, max_nr;
+	size_t e1_sz = sizeof(struct id_index_entry);
+	size_t e2_sz = sizeof(struct id_index_entry_2);
+	size_t etot_sz = e1_sz + e2_sz;
+	struct id_index_entry_2 *e2;
+	pid_t last_pid = 0;
 
-	max_nr = (ie->header.size - sizeof(struct perf_record_id_index)) /
-		 sizeof(struct id_index_entry);
+	max_nr = sz / e1_sz;
 	nr = ie->nr;
-	if (nr > max_nr)
+	if (nr > max_nr) {
+		printf("Too big: nr %zu max_nr %zu\n", nr, max_nr);
 		return -EINVAL;
+	}
+
+	if (sz >= nr * etot_sz) {
+		max_nr = sz / etot_sz;
+		if (nr > max_nr) {
+			printf("Too big2: nr %zu max_nr %zu\n", nr, max_nr);
+			return -EINVAL;
+		}
+		e2 = (void *)ie + sizeof(*ie) + nr * e1_sz;
+	} else {
+		e2 = NULL;
+	}
 
 	if (dump_trace)
 		fprintf(stdout, " nr: %zu\n", nr);
 
-	for (i = 0; i < nr; i++) {
+	for (i = 0; i < nr; i++, (e2 ? e2++ : 0)) {
 		struct id_index_entry *e = &ie->entries[i];
 		struct perf_sample_id *sid;
+		int ret;
 
 		if (dump_trace) {
 			fprintf(stdout,	" ... id: %"PRI_lu64, e->id);
 			fprintf(stdout,	"  idx: %"PRI_lu64, e->idx);
 			fprintf(stdout,	"  cpu: %"PRI_ld64, e->cpu);
-			fprintf(stdout,	"  tid: %"PRI_ld64"\n", e->tid);
+			fprintf(stdout, "  tid: %"PRI_ld64, e->tid);
+			if (e2) {
+				fprintf(stdout, "  machine_pid: %"PRI_ld64, e2->machine_pid);
+				fprintf(stdout, "  vcpu: %"PRI_lu64"\n", e2->vcpu);
+			} else {
+				fprintf(stdout, "\n");
+			}
 		}
 
 		sid = evlist__id2sid(evlist, e->id);
 		if (!sid)
 			return -ENOENT;
+
 		sid->idx = e->idx;
 		sid->cpu.cpu = e->cpu;
 		sid->tid = e->tid;
+
+		if (!e2)
+			continue;
+
+		sid->machine_pid = e2->machine_pid;
+		sid->vcpu.cpu = e2->vcpu;
+
+		if (!sid->machine_pid)
+			continue;
+
+		if (sid->machine_pid != last_pid) {
+			ret = perf_session__register_guest(session, sid->machine_pid);
+			if (ret)
+				return ret;
+			last_pid = sid->machine_pid;
+			perf_guest = true;
+		}
+
+		ret = perf_session__set_guest_cpu(session, sid->machine_pid, e->tid, e2->vcpu);
+		if (ret)
+			return ret;
 	}
 	return 0;
 }
+
+int perf_session__dsos_hit_all(struct perf_session *session)
+{
+	struct rb_node *nd;
+	int err;
+
+	err = machine__hit_all_dsos(&session->machines.host);
+	if (err)
+		return err;
+
+	for (nd = rb_first_cached(&session->machines.guests); nd;
+	     nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+
+		err = machine__hit_all_dsos(pos);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+struct perf_env *perf_session__env(struct perf_session *session)
+{
+	return &session->header.env;
+}