Merge drm/drm-fixes into drm-misc-fixes

We haven't backmerged for a while and this creates some coherency issues
across DRM drivers.

Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>

37 files changed, 1652 insertions, 232 deletions

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 5f6dbbf5d749..c8b01176c9e1 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -10,6 +10,10 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <libgen.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
+#include <linux/btf.h>
 #include "util.h"
 #include "ui/ui.h"
 #include "sort.h"
@@ -24,6 +28,7 @@
 #include "annotate.h"
 #include "evsel.h"
 #include "evlist.h"
+#include "bpf-event.h"
 #include "block-range.h"
 #include "string2.h"
 #include "arch/common.h"
@@ -31,6 +36,7 @@
 #include <pthread.h>
 #include <linux/bitops.h>
 #include <linux/kernel.h>
+#include <bpf/libbpf.h>
 
 /* FIXME: For the HE_COLORSET */
 #include "ui/browser.h"
@@ -1615,6 +1621,9 @@ int symbol__strerror_disassemble(struct symbol *sym __maybe_unused, struct map *
 			  "  --vmlinux vmlinux\n", build_id_msg ?: "");
 	}
 		break;
+	case SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF:
+		scnprintf(buf, buflen, "Please link with binutils's libopcode to enable BPF annotation");
+		break;
 	default:
 		scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum);
 		break;
@@ -1674,6 +1683,156 @@ fallback:
 	return 0;
 }
 
+#if defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
+#define PACKAGE "perf"
+#include <bfd.h>
+#include <dis-asm.h>
+
+static int symbol__disassemble_bpf(struct symbol *sym,
+				   struct annotate_args *args)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct annotation_options *opts = args->options;
+	struct bpf_prog_info_linear *info_linear;
+	struct bpf_prog_linfo *prog_linfo = NULL;
+	struct bpf_prog_info_node *info_node;
+	int len = sym->end - sym->start;
+	disassembler_ftype disassemble;
+	struct map *map = args->ms.map;
+	struct disassemble_info info;
+	struct dso *dso = map->dso;
+	int pc = 0, count, sub_id;
+	struct btf *btf = NULL;
+	char tpath[PATH_MAX];
+	size_t buf_size;
+	int nr_skip = 0;
+	int ret = -1;
+	char *buf;
+	bfd *bfdf;
+	FILE *s;
+
+	if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO)
+		return -1;
+
+	pr_debug("%s: handling sym %s addr %lx len %lx\n", __func__,
+		 sym->name, sym->start, sym->end - sym->start);
+
+	memset(tpath, 0, sizeof(tpath));
+	perf_exe(tpath, sizeof(tpath));
+
+	bfdf = bfd_openr(tpath, NULL);
+	assert(bfdf);
+	assert(bfd_check_format(bfdf, bfd_object));
+
+	s = open_memstream(&buf, &buf_size);
+	if (!s)
+		goto out;
+	init_disassemble_info(&info, s,
+			      (fprintf_ftype) fprintf);
+
+	info.arch = bfd_get_arch(bfdf);
+	info.mach = bfd_get_mach(bfdf);
+
+	info_node = perf_env__find_bpf_prog_info(dso->bpf_prog.env,
+						 dso->bpf_prog.id);
+	if (!info_node)
+		goto out;
+	info_linear = info_node->info_linear;
+	sub_id = dso->bpf_prog.sub_id;
+
+	info.buffer = (void *)(info_linear->info.jited_prog_insns);
+	info.buffer_length = info_linear->info.jited_prog_len;
+
+	if (info_linear->info.nr_line_info)
+		prog_linfo = bpf_prog_linfo__new(&info_linear->info);
+
+	if (info_linear->info.btf_id) {
+		struct btf_node *node;
+
+		node = perf_env__find_btf(dso->bpf_prog.env,
+					  info_linear->info.btf_id);
+		if (node)
+			btf = btf__new((__u8 *)(node->data),
+				       node->data_size);
+	}
+
+	disassemble_init_for_target(&info);
+
+#ifdef DISASM_FOUR_ARGS_SIGNATURE
+	disassemble = disassembler(info.arch,
+				   bfd_big_endian(bfdf),
+				   info.mach,
+				   bfdf);
+#else
+	disassemble = disassembler(bfdf);
+#endif
+	assert(disassemble);
+
+	fflush(s);
+	do {
+		const struct bpf_line_info *linfo = NULL;
+		struct disasm_line *dl;
+		size_t prev_buf_size;
+		const char *srcline;
+		u64 addr;
+
+		addr = pc + ((u64 *)(info_linear->info.jited_ksyms))[sub_id];
+		count = disassemble(pc, &info);
+
+		if (prog_linfo)
+			linfo = bpf_prog_linfo__lfind_addr_func(prog_linfo,
+								addr, sub_id,
+								nr_skip);
+
+		if (linfo && btf) {
+			srcline = btf__name_by_offset(btf, linfo->line_off);
+			nr_skip++;
+		} else
+			srcline = NULL;
+
+		fprintf(s, "\n");
+		prev_buf_size = buf_size;
+		fflush(s);
+
+		if (!opts->hide_src_code && srcline) {
+			args->offset = -1;
+			args->line = strdup(srcline);
+			args->line_nr = 0;
+			args->ms.sym  = sym;
+			dl = disasm_line__new(args);
+			if (dl) {
+				annotation_line__add(&dl->al,
+						     &notes->src->source);
+			}
+		}
+
+		args->offset = pc;
+		args->line = buf + prev_buf_size;
+		args->line_nr = 0;
+		args->ms.sym  = sym;
+		dl = disasm_line__new(args);
+		if (dl)
+			annotation_line__add(&dl->al, &notes->src->source);
+
+		pc += count;
+	} while (count > 0 && pc < len);
+
+	ret = 0;
+out:
+	free(prog_linfo);
+	free(btf);
+	fclose(s);
+	bfd_close(bfdf);
+	return ret;
+}
+#else // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
+static int symbol__disassemble_bpf(struct symbol *sym __maybe_unused,
+				   struct annotate_args *args __maybe_unused)
+{
+	return SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF;
+}
+#endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
+
 static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 {
 	struct annotation_options *opts = args->options;
@@ -1701,7 +1860,9 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 	pr_debug("annotating [%p] %30s : [%p] %30s\n",
 		 dso, dso->long_name, sym, sym->name);
 
-	if (dso__is_kcore(dso)) {
+	if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) {
+		return symbol__disassemble_bpf(sym, args);
+	} else if (dso__is_kcore(dso)) {
 		kce.kcore_filename = symfs_filename;
 		kce.addr = map__rip_2objdump(map, sym->start);
 		kce.offs = sym->start;
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index df34fe483164..5bc0cf655d37 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -369,6 +369,7 @@ enum symbol_disassemble_errno {
 	__SYMBOL_ANNOTATE_ERRNO__START		= -10000,
 
 	SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX	= __SYMBOL_ANNOTATE_ERRNO__START,
+	SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF,
 
 	__SYMBOL_ANNOTATE_ERRNO__END,
 };
diff --git a/tools/perf/util/archinsn.h b/tools/perf/util/archinsn.h
new file mode 100644
index 000000000000..448cbb6b8d7e
--- /dev/null
+++ b/tools/perf/util/archinsn.h
@@ -0,0 +1,12 @@
+#ifndef INSN_H
+#define INSN_H 1
+
+struct perf_sample;
+struct machine;
+struct thread;
+
+void arch_fetch_insn(struct perf_sample *sample,
+		     struct thread *thread,
+		     struct machine *machine);
+
+#endif
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 028c8ec1f62a..2a4a0da35632 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -3,11 +3,17 @@
 #include <stdlib.h>
 #include <bpf/bpf.h>
 #include <bpf/btf.h>
+#include <bpf/libbpf.h>
 #include <linux/btf.h>
+#include <linux/err.h>
 #include "bpf-event.h"
 #include "debug.h"
 #include "symbol.h"
 #include "machine.h"
+#include "env.h"
+#include "session.h"
+#include "map.h"
+#include "evlist.h"
 
 #define ptr_to_u64(ptr)    ((__u64)(unsigned long)(ptr))
 
@@ -21,15 +27,122 @@ static int snprintf_hex(char *buf, size_t size, unsigned char *data, size_t len)
 	return ret;
 }
 
+static int machine__process_bpf_event_load(struct machine *machine,
+					   union perf_event *event,
+					   struct perf_sample *sample __maybe_unused)
+{
+	struct bpf_prog_info_linear *info_linear;
+	struct bpf_prog_info_node *info_node;
+	struct perf_env *env = machine->env;
+	int id = event->bpf_event.id;
+	unsigned int i;
+
+	/* perf-record, no need to handle bpf-event */
+	if (env == NULL)
+		return 0;
+
+	info_node = perf_env__find_bpf_prog_info(env, id);
+	if (!info_node)
+		return 0;
+	info_linear = info_node->info_linear;
+
+	for (i = 0; i < info_linear->info.nr_jited_ksyms; i++) {
+		u64 *addrs = (u64 *)(uintptr_t)(info_linear->info.jited_ksyms);
+		u64 addr = addrs[i];
+		struct map *map;
+
+		map = map_groups__find(&machine->kmaps, addr);
+
+		if (map) {
+			map->dso->binary_type = DSO_BINARY_TYPE__BPF_PROG_INFO;
+			map->dso->bpf_prog.id = id;
+			map->dso->bpf_prog.sub_id = i;
+			map->dso->bpf_prog.env = env;
+		}
+	}
+	return 0;
+}
+
 int machine__process_bpf_event(struct machine *machine __maybe_unused,
 			       union perf_event *event,
 			       struct perf_sample *sample __maybe_unused)
 {
 	if (dump_trace)
 		perf_event__fprintf_bpf_event(event, stdout);
+
+	switch (event->bpf_event.type) {
+	case PERF_BPF_EVENT_PROG_LOAD:
+		return machine__process_bpf_event_load(machine, event, sample);
+
+	case PERF_BPF_EVENT_PROG_UNLOAD:
+		/*
+		 * Do not free bpf_prog_info and btf of the program here,
+		 * as annotation still need them. They will be freed at
+		 * the end of the session.
+		 */
+		break;
+	default:
+		pr_debug("unexpected bpf_event type of %d\n",
+			 event->bpf_event.type);
+		break;
+	}
 	return 0;
 }
 
+static int perf_env__fetch_btf(struct perf_env *env,
+			       u32 btf_id,
+			       struct btf *btf)
+{
+	struct btf_node *node;
+	u32 data_size;
+	const void *data;
+
+	data = btf__get_raw_data(btf, &data_size);
+
+	node = malloc(data_size + sizeof(struct btf_node));
+	if (!node)
+		return -1;
+
+	node->id = btf_id;
+	node->data_size = data_size;
+	memcpy(node->data, data, data_size);
+
+	perf_env__insert_btf(env, node);
+	return 0;
+}
+
+static int synthesize_bpf_prog_name(char *buf, int size,
+				    struct bpf_prog_info *info,
+				    struct btf *btf,
+				    u32 sub_id)
+{
+	u8 (*prog_tags)[BPF_TAG_SIZE] = (void *)(uintptr_t)(info->prog_tags);
+	void *func_infos = (void *)(uintptr_t)(info->func_info);
+	u32 sub_prog_cnt = info->nr_jited_ksyms;
+	const struct bpf_func_info *finfo;
+	const char *short_name = NULL;
+	const struct btf_type *t;
+	int name_len;
+
+	name_len = snprintf(buf, size, "bpf_prog_");
+	name_len += snprintf_hex(buf + name_len, size - name_len,
+				 prog_tags[sub_id], BPF_TAG_SIZE);
+	if (btf) {
+		finfo = func_infos + sub_id * info->func_info_rec_size;
+		t = btf__type_by_id(btf, finfo->type_id);
+		short_name = btf__name_by_offset(btf, t->name_off);
+	} else if (sub_id == 0 && sub_prog_cnt == 1) {
+		/* no subprog */
+		if (info->name[0])
+			short_name = info->name;
+	} else
+		short_name = "F";
+	if (short_name)
+		name_len += snprintf(buf + name_len, size - name_len,
+				     "_%s", short_name);
+	return name_len;
+}
+
 /*
  * Synthesize PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT for one bpf
  * program. One PERF_RECORD_BPF_EVENT is generated for the program. And
@@ -40,7 +153,7 @@ int machine__process_bpf_event(struct machine *machine __maybe_unused,
  *   -1 for failures;
  *   -2 for lack of kernel support.
  */
-static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool,
+static int perf_event__synthesize_one_bpf_prog(struct perf_session *session,
 					       perf_event__handler_t process,
 					       struct machine *machine,
 					       int fd,
@@ -49,102 +162,71 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool,
 {
 	struct ksymbol_event *ksymbol_event = &event->ksymbol_event;
 	struct bpf_event *bpf_event = &event->bpf_event;
-	u32 sub_prog_cnt, i, func_info_rec_size = 0;
-	u8 (*prog_tags)[BPF_TAG_SIZE] = NULL;
-	struct bpf_prog_info info = { .type = 0, };
-	u32 info_len = sizeof(info);
-	void *func_infos = NULL;
-	u64 *prog_addrs = NULL;
+	struct bpf_prog_info_linear *info_linear;
+	struct perf_tool *tool = session->tool;
+	struct bpf_prog_info_node *info_node;
+	struct bpf_prog_info *info;
 	struct btf *btf = NULL;
-	u32 *prog_lens = NULL;
-	bool has_btf = false;
-	char errbuf[512];
+	struct perf_env *env;
+	u32 sub_prog_cnt, i;
 	int err = 0;
+	u64 arrays;
+
+	/*
+	 * for perf-record and perf-report use header.env;
+	 * otherwise, use global perf_env.
+	 */
+	env = session->data ? &session->header.env : &perf_env;
 
-	/* Call bpf_obj_get_info_by_fd() to get sizes of arrays */
-	err = bpf_obj_get_info_by_fd(fd, &info, &info_len);
+	arrays = 1UL << BPF_PROG_INFO_JITED_KSYMS;
+	arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS;
+	arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO;
+	arrays |= 1UL << BPF_PROG_INFO_PROG_TAGS;
+	arrays |= 1UL << BPF_PROG_INFO_JITED_INSNS;
+	arrays |= 1UL << BPF_PROG_INFO_LINE_INFO;
+	arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO;
 
-	if (err) {
-		pr_debug("%s: failed to get BPF program info: %s, aborting\n",
-			 __func__, str_error_r(errno, errbuf, sizeof(errbuf)));
+	info_linear = bpf_program__get_prog_info_linear(fd, arrays);
+	if (IS_ERR_OR_NULL(info_linear)) {
+		info_linear = NULL;
+		pr_debug("%s: failed to get BPF program info. aborting\n", __func__);
 		return -1;
 	}
-	if (info_len < offsetof(struct bpf_prog_info, prog_tags)) {
+
+	if (info_linear->info_len < offsetof(struct bpf_prog_info, prog_tags)) {
 		pr_debug("%s: the kernel is too old, aborting\n", __func__);
 		return -2;
 	}
 
+	info = &info_linear->info;
+
 	/* number of ksyms, func_lengths, and tags should match */
-	sub_prog_cnt = info.nr_jited_ksyms;
-	if (sub_prog_cnt != info.nr_prog_tags ||
-	    sub_prog_cnt != info.nr_jited_func_lens)
+	sub_prog_cnt = info->nr_jited_ksyms;
+	if (sub_prog_cnt != info->nr_prog_tags ||
+	    sub_prog_cnt != info->nr_jited_func_lens)
 		return -1;
 
 	/* check BTF func info support */
-	if (info.btf_id && info.nr_func_info && info.func_info_rec_size) {
+	if (info->btf_id && info->nr_func_info && info->func_info_rec_size) {
 		/* btf func info number should be same as sub_prog_cnt */
-		if (sub_prog_cnt != info.nr_func_info) {
+		if (sub_prog_cnt != info->nr_func_info) {
 			pr_debug("%s: mismatch in BPF sub program count and BTF function info count, aborting\n", __func__);
-			return -1;
-		}
-		if (btf__get_from_id(info.btf_id, &btf)) {
-			pr_debug("%s: failed to get BTF of id %u, aborting\n", __func__, info.btf_id);
-			return -1;
+			err = -1;
+			goto out;
 		}
-		func_info_rec_size = info.func_info_rec_size;
-		func_infos = calloc(sub_prog_cnt, func_info_rec_size);
-		if (!func_infos) {
-			pr_debug("%s: failed to allocate memory for func_infos, aborting\n", __func__);
-			return -1;
+		if (btf__get_from_id(info->btf_id, &btf)) {
+			pr_debug("%s: failed to get BTF of id %u, aborting\n", __func__, info->btf_id);
+			err = -1;
+			btf = NULL;
+			goto out;
 		}
-		has_btf = true;
-	}
-
-	/*
-	 * We need address, length, and tag for each sub program.
-	 * Allocate memory and call bpf_obj_get_info_by_fd() again
-	 */
-	prog_addrs = calloc(sub_prog_cnt, sizeof(u64));
-	if (!prog_addrs) {
-		pr_debug("%s: failed to allocate memory for prog_addrs, aborting\n", __func__);
-		goto out;
-	}
-	prog_lens = calloc(sub_prog_cnt, sizeof(u32));
-	if (!prog_lens) {
-		pr_debug("%s: failed to allocate memory for prog_lens, aborting\n", __func__);
-		goto out;
-	}
-	prog_tags = calloc(sub_prog_cnt, BPF_TAG_SIZE);
-	if (!prog_tags) {
-		pr_debug("%s: failed to allocate memory for prog_tags, aborting\n", __func__);
-		goto out;
-	}
-
-	memset(&info, 0, sizeof(info));
-	info.nr_jited_ksyms = sub_prog_cnt;
-	info.nr_jited_func_lens = sub_prog_cnt;
-	info.nr_prog_tags = sub_prog_cnt;
-	info.jited_ksyms = ptr_to_u64(prog_addrs);
-	info.jited_func_lens = ptr_to_u64(prog_lens);
-	info.prog_tags = ptr_to_u64(prog_tags);
-	info_len = sizeof(info);
-	if (has_btf) {
-		info.nr_func_info = sub_prog_cnt;
-		info.func_info_rec_size = func_info_rec_size;
-		info.func_info = ptr_to_u64(func_infos);
-	}
-
-	err = bpf_obj_get_info_by_fd(fd, &info, &info_len);
-	if (err) {
-		pr_debug("%s: failed to get BPF program info, aborting\n", __func__);
-		goto out;
+		perf_env__fetch_btf(env, info->btf_id, btf);
 	}
 
 	/* Synthesize PERF_RECORD_KSYMBOL */
 	for (i = 0; i < sub_prog_cnt; i++) {
-		const struct bpf_func_info *finfo;
-		const char *short_name = NULL;
-		const struct btf_type *t;
+		__u32 *prog_lens = (__u32 *)(uintptr_t)(info->jited_func_lens);
+		__u64 *prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms);
 		int name_len;
 
 		*ksymbol_event = (struct ksymbol_event){
@@ -157,26 +239,9 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool,
 			.ksym_type = PERF_RECORD_KSYMBOL_TYPE_BPF,
 			.flags = 0,
 		};
-		name_len = snprintf(ksymbol_event->name, KSYM_NAME_LEN,
-				    "bpf_prog_");
-		name_len += snprintf_hex(ksymbol_event->name + name_len,
-					 KSYM_NAME_LEN - name_len,
-					 prog_tags[i], BPF_TAG_SIZE);
-		if (has_btf) {
-			finfo = func_infos + i * info.func_info_rec_size;
-			t = btf__type_by_id(btf, finfo->type_id);
-			short_name = btf__name_by_offset(btf, t->name_off);
-		} else if (i == 0 && sub_prog_cnt == 1) {
-			/* no subprog */
-			if (info.name[0])
-				short_name = info.name;
-		} else
-			short_name = "F";
-		if (short_name)
-			name_len += snprintf(ksymbol_event->name + name_len,
-					     KSYM_NAME_LEN - name_len,
-					     "_%s", short_name);
 
+		name_len = synthesize_bpf_prog_name(ksymbol_event->name,
+						    KSYM_NAME_LEN, info, btf, i);
 		ksymbol_event->header.size += PERF_ALIGN(name_len + 1,
 							 sizeof(u64));
 
@@ -186,8 +251,8 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool,
 						     machine, process);
 	}
 
-	/* Synthesize PERF_RECORD_BPF_EVENT */
-	if (opts->bpf_event) {
+	if (!opts->no_bpf_event) {
+		/* Synthesize PERF_RECORD_BPF_EVENT */
 		*bpf_event = (struct bpf_event){
 			.header = {
 				.type = PERF_RECORD_BPF_EVENT,
@@ -195,25 +260,38 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool,
 			},
 			.type = PERF_BPF_EVENT_PROG_LOAD,
 			.flags = 0,
-			.id = info.id,
+			.id = info->id,
 		};
-		memcpy(bpf_event->tag, prog_tags[i], BPF_TAG_SIZE);
+		memcpy(bpf_event->tag, info->tag, BPF_TAG_SIZE);
 		memset((void *)event + event->header.size, 0, machine->id_hdr_size);
 		event->header.size += machine->id_hdr_size;
+
+		/* save bpf_prog_info to env */
+		info_node = malloc(sizeof(struct bpf_prog_info_node));
+		if (!info_node) {
+			err = -1;
+			goto out;
+		}
+
+		info_node->info_linear = info_linear;
+		perf_env__insert_bpf_prog_info(env, info_node);
+		info_linear = NULL;
+
+		/*
+		 * process after saving bpf_prog_info to env, so that
+		 * required information is ready for look up
+		 */
 		err = perf_tool__process_synth_event(tool, event,
 						     machine, process);
 	}
 
 out:
-	free(prog_tags);
-	free(prog_lens);
-	free(prog_addrs);
-	free(func_infos);
+	free(info_linear);
 	free(btf);
 	return err ? -1 : 0;
 }
 
-int perf_event__synthesize_bpf_events(struct perf_tool *tool,
+int perf_event__synthesize_bpf_events(struct perf_session *session,
 				      perf_event__handler_t process,
 				      struct machine *machine,
 				      struct record_opts *opts)
@@ -247,7 +325,7 @@ int perf_event__synthesize_bpf_events(struct perf_tool *tool,
 			continue;
 		}
 
-		err = perf_event__synthesize_one_bpf_prog(tool, process,
+		err = perf_event__synthesize_one_bpf_prog(session, process,
 							  machine, fd,
 							  event, opts);
 		close(fd);
@@ -261,3 +339,142 @@ int perf_event__synthesize_bpf_events(struct perf_tool *tool,
 	free(event);
 	return err;
 }
+
+static void perf_env__add_bpf_info(struct perf_env *env, u32 id)
+{
+	struct bpf_prog_info_linear *info_linear;
+	struct bpf_prog_info_node *info_node;
+	struct btf *btf = NULL;
+	u64 arrays;
+	u32 btf_id;
+	int fd;
+
+	fd = bpf_prog_get_fd_by_id(id);
+	if (fd < 0)
+		return;
+
+	arrays = 1UL << BPF_PROG_INFO_JITED_KSYMS;
+	arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS;
+	arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO;
+	arrays |= 1UL << BPF_PROG_INFO_PROG_TAGS;
+	arrays |= 1UL << BPF_PROG_INFO_JITED_INSNS;
+	arrays |= 1UL << BPF_PROG_INFO_LINE_INFO;
+	arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO;
+
+	info_linear = bpf_program__get_prog_info_linear(fd, arrays);
+	if (IS_ERR_OR_NULL(info_linear)) {
+		pr_debug("%s: failed to get BPF program info. aborting\n", __func__);
+		goto out;
+	}
+
+	btf_id = info_linear->info.btf_id;
+
+	info_node = malloc(sizeof(struct bpf_prog_info_node));
+	if (info_node) {
+		info_node->info_linear = info_linear;
+		perf_env__insert_bpf_prog_info(env, info_node);
+	} else
+		free(info_linear);
+
+	if (btf_id == 0)
+		goto out;
+
+	if (btf__get_from_id(btf_id, &btf)) {
+		pr_debug("%s: failed to get BTF of id %u, aborting\n",
+			 __func__, btf_id);
+		goto out;
+	}
+	perf_env__fetch_btf(env, btf_id, btf);
+
+out:
+	free(btf);
+	close(fd);
+}
+
+static int bpf_event__sb_cb(union perf_event *event, void *data)
+{
+	struct perf_env *env = data;
+
+	if (event->header.type != PERF_RECORD_BPF_EVENT)
+		return -1;
+
+	switch (event->bpf_event.type) {
+	case PERF_BPF_EVENT_PROG_LOAD:
+		perf_env__add_bpf_info(env, event->bpf_event.id);
+
+	case PERF_BPF_EVENT_PROG_UNLOAD:
+		/*
+		 * Do not free bpf_prog_info and btf of the program here,
+		 * as annotation still need them. They will be freed at
+		 * the end of the session.
+		 */
+		break;
+	default:
+		pr_debug("unexpected bpf_event type of %d\n",
+			 event->bpf_event.type);
+		break;
+	}
+
+	return 0;
+}
+
+int bpf_event__add_sb_event(struct perf_evlist **evlist,
+			    struct perf_env *env)
+{
+	struct perf_event_attr attr = {
+		.type	          = PERF_TYPE_SOFTWARE,
+		.config           = PERF_COUNT_SW_DUMMY,
+		.sample_id_all    = 1,
+		.watermark        = 1,
+		.bpf_event        = 1,
+		.size	   = sizeof(attr), /* to capture ABI version */
+	};
+
+	/*
+	 * Older gcc versions don't support designated initializers, like above,
+	 * for unnamed union members, such as the following:
+	 */
+	attr.wakeup_watermark = 1;
+
+	return perf_evlist__add_sb_event(evlist, &attr, bpf_event__sb_cb, env);
+}
+
+void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
+				    struct perf_env *env,
+				    FILE *fp)
+{
+	__u32 *prog_lens = (__u32 *)(uintptr_t)(info->jited_func_lens);
+	__u64 *prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms);
+	char name[KSYM_NAME_LEN];
+	struct btf *btf = NULL;
+	u32 sub_prog_cnt, i;
+
+	sub_prog_cnt = info->nr_jited_ksyms;
+	if (sub_prog_cnt != info->nr_prog_tags ||
+	    sub_prog_cnt != info->nr_jited_func_lens)
+		return;
+
+	if (info->btf_id) {
+		struct btf_node *node;
+
+		node = perf_env__find_btf(env, info->btf_id);
+		if (node)
+			btf = btf__new((__u8 *)(node->data),
+				       node->data_size);
+	}
+
+	if (sub_prog_cnt == 1) {
+		synthesize_bpf_prog_name(name, KSYM_NAME_LEN, info, btf, 0);
+		fprintf(fp, "# bpf_prog_info %u: %s addr 0x%llx size %u\n",
+			info->id, name, prog_addrs[0], prog_lens[0]);
+		return;
+	}
+
+	fprintf(fp, "# bpf_prog_info %u:\n", info->id);
+	for (i = 0; i < sub_prog_cnt; i++) {
+		synthesize_bpf_prog_name(name, KSYM_NAME_LEN, info, btf, i);
+
+		fprintf(fp, "# \tsub_prog %u: %s addr 0x%llx size %u\n",
+			i, name, prog_addrs[i], prog_lens[i]);
+	}
+}
diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h
index 7890067e1a37..04c33b3bfe28 100644
--- a/tools/perf/util/bpf-event.h
+++ b/tools/perf/util/bpf-event.h
@@ -3,22 +3,45 @@
 #define __PERF_BPF_EVENT_H
 
 #include <linux/compiler.h>
+#include <linux/rbtree.h>
+#include <pthread.h>
+#include <api/fd/array.h>
 #include "event.h"
+#include <stdio.h>
 
 struct machine;
 union perf_event;
+struct perf_env;
 struct perf_sample;
-struct perf_tool;
 struct record_opts;
+struct evlist;
+struct target;
+
+struct bpf_prog_info_node {
+	struct bpf_prog_info_linear	*info_linear;
+	struct rb_node			rb_node;
+};
+
+struct btf_node {
+	struct rb_node	rb_node;
+	u32		id;
+	u32		data_size;
+	char		data[];
+};
 
 #ifdef HAVE_LIBBPF_SUPPORT
 int machine__process_bpf_event(struct machine *machine, union perf_event *event,
 			       struct perf_sample *sample);
 
-int perf_event__synthesize_bpf_events(struct perf_tool *tool,
+int perf_event__synthesize_bpf_events(struct perf_session *session,
 				      perf_event__handler_t process,
 				      struct machine *machine,
 				      struct record_opts *opts);
+int bpf_event__add_sb_event(struct perf_evlist **evlist,
+				 struct perf_env *env);
+void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
+				    struct perf_env *env,
+				    FILE *fp);
 #else
 static inline int machine__process_bpf_event(struct machine *machine __maybe_unused,
 					     union perf_event *event __maybe_unused,
@@ -27,12 +50,25 @@ static inline int machine__process_bpf_event(struct machine *machine __maybe_unu
 	return 0;
 }
 
-static inline int perf_event__synthesize_bpf_events(struct perf_tool *tool __maybe_unused,
+static inline int perf_event__synthesize_bpf_events(struct perf_session *session __maybe_unused,
 						    perf_event__handler_t process __maybe_unused,
 						    struct machine *machine __maybe_unused,
 						    struct record_opts *opts __maybe_unused)
 {
 	return 0;
 }
+
+static inline int bpf_event__add_sb_event(struct perf_evlist **evlist __maybe_unused,
+					  struct perf_env *env __maybe_unused)
+{
+	return 0;
+}
+
+static inline void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info __maybe_unused,
+						  struct perf_env *env __maybe_unused,
+						  FILE *fp __maybe_unused)
+{
+
+}
 #endif // HAVE_LIBBPF_SUPPORT
 #endif
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index bff0d17920ed..0c5517a8d0b7 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -185,6 +185,7 @@ char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size)
 	return bf;
 }
 
+/* The caller is responsible to free the returned buffer. */
 char *build_id_cache__origname(const char *sbuild_id)
 {
 	char *linkname;
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index fa092511c52b..7e3c1b60120c 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -633,11 +633,10 @@ static int collect_config(const char *var, const char *value,
 	}
 
 	ret = set_value(item, value);
-	return ret;
 
 out_free:
 	free(key);
-	return -1;
+	return ret;
 }
 
 int perf_config_set__collect(struct perf_config_set *set, const char *file_name,
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index ba4c623cd8de..39fe21e1cf93 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -387,6 +387,7 @@ cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder,
 		break;
 	case OCSD_INSTR_ISB:
 	case OCSD_INSTR_DSB_DMB:
+	case OCSD_INSTR_WFI_WFE:
 	case OCSD_INSTR_OTHER:
 	default:
 		packet->last_instr_taken_branch = false;
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index e098e189f93e..6a64f713710d 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -14,6 +14,7 @@
 #include "data.h"
 #include "util.h"
 #include "debug.h"
+#include "header.h"
 
 static void close_dir(struct perf_data_file *files, int nr)
 {
@@ -34,12 +35,16 @@ int perf_data__create_dir(struct perf_data *data, int nr)
 	struct perf_data_file *files = NULL;
 	int i, ret = -1;
 
+	if (WARN_ON(!data->is_dir))
+		return -EINVAL;
+
 	files = zalloc(nr * sizeof(*files));
 	if (!files)
 		return -ENOMEM;
 
-	data->dir.files = files;
-	data->dir.nr    = nr;
+	data->dir.version = PERF_DIR_VERSION;
+	data->dir.files   = files;
+	data->dir.nr      = nr;
 
 	for (i = 0; i < nr; i++) {
 		struct perf_data_file *file = &files[i];
@@ -69,6 +74,13 @@ int perf_data__open_dir(struct perf_data *data)
 	DIR *dir;
 	int nr = 0;
 
+	if (WARN_ON(!data->is_dir))
+		return -EINVAL;
+
+	/* The version is provided by DIR_FORMAT feature. */
+	if (WARN_ON(data->dir.version != PERF_DIR_VERSION))
+		return -1;
+
 	dir = opendir(data->path);
 	if (!dir)
 		return -EINVAL;
@@ -118,6 +130,26 @@ out_err:
 	return ret;
 }
 
+int perf_data__update_dir(struct perf_data *data)
+{
+	int i;
+
+	if (WARN_ON(!data->is_dir))
+		return -EINVAL;
+
+	for (i = 0; i < data->dir.nr; i++) {
+		struct perf_data_file *file = &data->dir.files[i];
+		struct stat st;
+
+		if (fstat(file->fd, &st))
+			return -1;
+
+		file->size = st.st_size;
+	}
+
+	return 0;
+}
+
 static bool check_pipe(struct perf_data *data)
 {
 	struct stat st;
@@ -173,6 +205,16 @@ static int check_backup(struct perf_data *data)
 	return 0;
 }
 
+static bool is_dir(struct perf_data *data)
+{
+	struct stat st;
+
+	if (stat(data->path, &st))
+		return false;
+
+	return (st.st_mode & S_IFMT) == S_IFDIR;
+}
+
 static int open_file_read(struct perf_data *data)
 {
 	struct stat st;
@@ -254,6 +296,30 @@ static int open_file_dup(struct perf_data *data)
 	return open_file(data);
 }
 
+static int open_dir(struct perf_data *data)
+{
+	int ret;
+
+	/*
+	 * So far we open only the header, so we can read the data version and
+	 * layout.
+	 */
+	if (asprintf(&data->file.path, "%s/header", data->path) < 0)
+		return -1;
+
+	if (perf_data__is_write(data) &&
+	    mkdir(data->path, S_IRWXU) < 0)
+		return -1;
+
+	ret = open_file(data);
+
+	/* Cleanup whatever we managed to create so far. */
+	if (ret && perf_data__is_write(data))
+		rm_rf_perf_data(data->path);
+
+	return ret;
+}
+
 int perf_data__open(struct perf_data *data)
 {
 	if (check_pipe(data))
@@ -265,11 +331,18 @@ int perf_data__open(struct perf_data *data)
 	if (check_backup(data))
 		return -1;
 
-	return open_file_dup(data);
+	if (perf_data__is_read(data))
+		data->is_dir = is_dir(data);
+
+	return perf_data__is_dir(data) ?
+	       open_dir(data) : open_file_dup(data);
 }
 
 void perf_data__close(struct perf_data *data)
 {
+	if (perf_data__is_dir(data))
+		perf_data__close_dir(data);
+
 	zfree(&data->file.path);
 	close(data->file.fd);
 }
@@ -288,9 +361,9 @@ ssize_t perf_data__write(struct perf_data *data,
 
 int perf_data__switch(struct perf_data *data,
 			   const char *postfix,
-			   size_t pos, bool at_exit)
+			   size_t pos, bool at_exit,
+			   char **new_filepath)
 {
-	char *new_filepath;
 	int ret;
 
 	if (check_pipe(data))
@@ -298,15 +371,15 @@ int perf_data__switch(struct perf_data *data,
 	if (perf_data__is_read(data))
 		return -EINVAL;
 
-	if (asprintf(&new_filepath, "%s.%s", data->path, postfix) < 0)
+	if (asprintf(new_filepath, "%s.%s", data->path, postfix) < 0)
 		return -ENOMEM;
 
 	/*
 	 * Only fire a warning, don't return error, continue fill
 	 * original file.
 	 */
-	if (rename(data->path, new_filepath))
-		pr_warning("Failed to rename %s to %s\n", data->path, new_filepath);
+	if (rename(data->path, *new_filepath))
+		pr_warning("Failed to rename %s to %s\n", data->path, *new_filepath);
 
 	if (!at_exit) {
 		close(data->file.fd);
@@ -323,6 +396,22 @@ int perf_data__switch(struct perf_data *data,
 	}
 	ret = data->file.fd;
 out:
-	free(new_filepath);
 	return ret;
 }
+
+unsigned long perf_data__size(struct perf_data *data)
+{
+	u64 size = data->file.size;
+	int i;
+
+	if (!data->is_dir)
+		return size;
+
+	for (i = 0; i < data->dir.nr; i++) {
+		struct perf_data_file *file = &data->dir.files[i];
+
+		size += file->size;
+	}
+
+	return size;
+}
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index 14b47be2bd69..259868a39019 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -19,10 +19,12 @@ struct perf_data {
 	const char		*path;
 	struct perf_data_file	 file;
 	bool			 is_pipe;
+	bool			 is_dir;
 	bool			 force;
 	enum perf_data_mode	 mode;
 
 	struct {
+		u64			 version;
 		struct perf_data_file	*files;
 		int			 nr;
 	} dir;
@@ -43,14 +45,14 @@ static inline int perf_data__is_pipe(struct perf_data *data)
 	return data->is_pipe;
 }
 
-static inline int perf_data__fd(struct perf_data *data)
+static inline bool perf_data__is_dir(struct perf_data *data)
 {
-	return data->file.fd;
+	return data->is_dir;
 }
 
-static inline unsigned long perf_data__size(struct perf_data *data)
+static inline int perf_data__fd(struct perf_data *data)
 {
-	return data->file.size;
+	return data->file.fd;
 }
 
 int perf_data__open(struct perf_data *data);
@@ -68,9 +70,11 @@ ssize_t perf_data_file__write(struct perf_data_file *file,
  */
 int perf_data__switch(struct perf_data *data,
 			   const char *postfix,
-			   size_t pos, bool at_exit);
+			   size_t pos, bool at_exit, char **new_filepath);
 
 int perf_data__create_dir(struct perf_data *data, int nr);
 int perf_data__open_dir(struct perf_data *data);
 void perf_data__close_dir(struct perf_data *data);
+int perf_data__update_dir(struct perf_data *data);
+unsigned long perf_data__size(struct perf_data *data);
 #endif /* __PERF_DATA_H */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index ba58ba603b69..e059976d9d93 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -184,6 +184,7 @@ int dso__read_binary_type_filename(const struct dso *dso,
 	case DSO_BINARY_TYPE__KALLSYMS:
 	case DSO_BINARY_TYPE__GUEST_KALLSYMS:
 	case DSO_BINARY_TYPE__JAVA_JIT:
+	case DSO_BINARY_TYPE__BPF_PROG_INFO:
 	case DSO_BINARY_TYPE__NOT_FOUND:
 		ret = -1;
 		break;
@@ -1141,28 +1142,34 @@ void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated)
 
 static void dso__set_basename(struct dso *dso)
 {
-       /*
-        * basename() may modify path buffer, so we must pass
-        * a copy.
-        */
-       char *base, *lname = strdup(dso->long_name);
+	char *base, *lname;
+	int tid;
 
-       if (!lname)
-               return;
-
-       /*
-        * basename() may return a pointer to internal
-        * storage which is reused in subsequent calls
-        * so copy the result.
-        */
-       base = strdup(basename(lname));
+	if (sscanf(dso->long_name, "/tmp/perf-%d.map", &tid) == 1) {
+		if (asprintf(&base, "[JIT] tid %d", tid) < 0)
+			return;
+	} else {
+	      /*
+	       * basename() may modify path buffer, so we must pass
+               * a copy.
+               */
+		lname = strdup(dso->long_name);
+		if (!lname)
+			return;
 
-       free(lname);
+		/*
+		 * basename() may return a pointer to internal
+		 * storage which is reused in subsequent calls
+		 * so copy the result.
+		 */
+		base = strdup(basename(lname));
 
-       if (!base)
-               return;
+		free(lname);
 
-       dso__set_short_name(dso, base, true);
+		if (!base)
+			return;
+	}
+	dso__set_short_name(dso, base, true);
 }
 
 int dso__name_len(const struct dso *dso)
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index bb417c54c25a..6e3f63781e51 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -14,6 +14,7 @@
 
 struct machine;
 struct map;
+struct perf_env;
 
 enum dso_binary_type {
 	DSO_BINARY_TYPE__KALLSYMS = 0,
@@ -35,6 +36,7 @@ enum dso_binary_type {
 	DSO_BINARY_TYPE__KCORE,
 	DSO_BINARY_TYPE__GUEST_KCORE,
 	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
+	DSO_BINARY_TYPE__BPF_PROG_INFO,
 	DSO_BINARY_TYPE__NOT_FOUND,
 };
 
@@ -189,6 +191,12 @@ struct dso {
 		u64		 debug_frame_offset;
 		u64		 eh_frame_hdr_offset;
 	} data;
+	/* bpf prog information */
+	struct {
+		u32		id;
+		u32		sub_id;
+		struct perf_env	*env;
+	} bpf_prog;
 
 	union { /* Tool specific area */
 		void	 *priv;
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 4c23779e271a..c6351b557bb0 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -3,15 +3,163 @@
 #include "env.h"
 #include "sane_ctype.h"
 #include "util.h"
+#include "bpf-event.h"
 #include <errno.h>
 #include <sys/utsname.h>
+#include <bpf/libbpf.h>
 
 struct perf_env perf_env;
 
+void perf_env__insert_bpf_prog_info(struct perf_env *env,
+				    struct bpf_prog_info_node *info_node)
+{
+	__u32 prog_id = info_node->info_linear->info.id;
+	struct bpf_prog_info_node *node;
+	struct rb_node *parent = NULL;
+	struct rb_node **p;
+
+	down_write(&env->bpf_progs.lock);
+	p = &env->bpf_progs.infos.rb_node;
+
+	while (*p != NULL) {
+		parent = *p;
+		node = rb_entry(parent, struct bpf_prog_info_node, rb_node);
+		if (prog_id < node->info_linear->info.id) {
+			p = &(*p)->rb_left;
+		} else if (prog_id > node->info_linear->info.id) {
+			p = &(*p)->rb_right;
+		} else {
+			pr_debug("duplicated bpf prog info %u\n", prog_id);
+			goto out;
+		}
+	}
+
+	rb_link_node(&info_node->rb_node, parent, p);
+	rb_insert_color(&info_node->rb_node, &env->bpf_progs.infos);
+	env->bpf_progs.infos_cnt++;
+out:
+	up_write(&env->bpf_progs.lock);
+}
+
+struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
+							__u32 prog_id)
+{
+	struct bpf_prog_info_node *node = NULL;
+	struct rb_node *n;
+
+	down_read(&env->bpf_progs.lock);
+	n = env->bpf_progs.infos.rb_node;
+
+	while (n) {
+		node = rb_entry(n, struct bpf_prog_info_node, rb_node);
+		if (prog_id < node->info_linear->info.id)
+			n = n->rb_left;
+		else if (prog_id > node->info_linear->info.id)
+			n = n->rb_right;
+		else
+			break;
+	}
+
+	up_read(&env->bpf_progs.lock);
+	return node;
+}
+
+void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
+{
+	struct rb_node *parent = NULL;
+	__u32 btf_id = btf_node->id;
+	struct btf_node *node;
+	struct rb_node **p;
+
+	down_write(&env->bpf_progs.lock);
+	p = &env->bpf_progs.btfs.rb_node;
+
+	while (*p != NULL) {
+		parent = *p;
+		node = rb_entry(parent, struct btf_node, rb_node);
+		if (btf_id < node->id) {
+			p = &(*p)->rb_left;
+		} else if (btf_id > node->id) {
+			p = &(*p)->rb_right;
+		} else {
+			pr_debug("duplicated btf %u\n", btf_id);
+			goto out;
+		}
+	}
+
+	rb_link_node(&btf_node->rb_node, parent, p);
+	rb_insert_color(&btf_node->rb_node, &env->bpf_progs.btfs);
+	env->bpf_progs.btfs_cnt++;
+out:
+	up_write(&env->bpf_progs.lock);
+}
+
+struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id)
+{
+	struct btf_node *node = NULL;
+	struct rb_node *n;
+
+	down_read(&env->bpf_progs.lock);
+	n = env->bpf_progs.btfs.rb_node;
+
+	while (n) {
+		node = rb_entry(n, struct btf_node, rb_node);
+		if (btf_id < node->id)
+			n = n->rb_left;
+		else if (btf_id > node->id)
+			n = n->rb_right;
+		else
+			break;
+	}
+
+	up_read(&env->bpf_progs.lock);
+	return node;
+}
+
+/* purge data in bpf_progs.infos tree */
+static void perf_env__purge_bpf(struct perf_env *env)
+{
+	struct rb_root *root;
+	struct rb_node *next;
+
+	down_write(&env->bpf_progs.lock);
+
+	root = &env->bpf_progs.infos;
+	next = rb_first(root);
+
+	while (next) {
+		struct bpf_prog_info_node *node;
+
+		node = rb_entry(next, struct bpf_prog_info_node, rb_node);
+		next = rb_next(&node->rb_node);
+		rb_erase(&node->rb_node, root);
+		free(node);
+	}
+
+	env->bpf_progs.infos_cnt = 0;
+
+	root = &env->bpf_progs.btfs;
+	next = rb_first(root);
+
+	while (next) {
+		struct btf_node *node;
+
+		node = rb_entry(next, struct btf_node, rb_node);
+		next = rb_next(&node->rb_node);
+		rb_erase(&node->rb_node, root);
+		free(node);
+	}
+
+	env->bpf_progs.btfs_cnt = 0;
+
+	up_write(&env->bpf_progs.lock);
+}
+
 void perf_env__exit(struct perf_env *env)
 {
 	int i;
 
+	perf_env__purge_bpf(env);
 	zfree(&env->hostname);
 	zfree(&env->os_release);
 	zfree(&env->version);
@@ -38,6 +186,13 @@ void perf_env__exit(struct perf_env *env)
 	zfree(&env->memory_nodes);
 }
 
+void perf_env__init(struct perf_env *env)
+{
+	env->bpf_progs.infos = RB_ROOT;
+	env->bpf_progs.btfs = RB_ROOT;
+	init_rwsem(&env->bpf_progs.lock);
+}
+
 int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[])
 {
 	int i;
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index d01b8355f4ca..4f8e2b485c01 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -3,7 +3,9 @@
 #define __PERF_ENV_H
 
 #include <linux/types.h>
+#include <linux/rbtree.h>
 #include "cpumap.h"
+#include "rwsem.h"
 
 struct cpu_topology_map {
 	int	socket_id;
@@ -64,8 +66,23 @@ struct perf_env {
 	struct memory_node	*memory_nodes;
 	unsigned long long	 memory_bsize;
 	u64                     clockid_res_ns;
+
+	/*
+	 * bpf_info_lock protects bpf rbtrees. This is needed because the
+	 * trees are accessed by different threads in perf-top
+	 */
+	struct {
+		struct rw_semaphore	lock;
+		struct rb_root		infos;
+		u32			infos_cnt;
+		struct rb_root		btfs;
+		u32			btfs_cnt;
+	} bpf_progs;
 };
 
+struct bpf_prog_info_node;
+struct btf_node;
+
 extern struct perf_env perf_env;
 
 void perf_env__exit(struct perf_env *env);
@@ -80,4 +97,11 @@ const char *perf_env__arch(struct perf_env *env);
 const char *perf_env__raw_arch(struct perf_env *env);
 int perf_env__nr_cpus_avail(struct perf_env *env);
 
+void perf_env__init(struct perf_env *env);
+void perf_env__insert_bpf_prog_info(struct perf_env *env,
+				    struct bpf_prog_info_node *info_node);
+struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
+							__u32 prog_id);
+void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
+struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id);
 #endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index ed20f4379956..6689378ee577 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -19,6 +19,7 @@
 #include "debug.h"
 #include "units.h"
 #include "asm/bug.h"
+#include "bpf-event.h"
 #include <signal.h>
 #include <unistd.h>
 
@@ -230,35 +231,6 @@ void perf_evlist__set_leader(struct perf_evlist *evlist)
 	}
 }
 
-void perf_event_attr__set_max_precise_ip(struct perf_event_attr *pattr)
-{
-	struct perf_event_attr attr = {
-		.type		= PERF_TYPE_HARDWARE,
-		.config		= PERF_COUNT_HW_CPU_CYCLES,
-		.exclude_kernel	= 1,
-		.precise_ip	= 3,
-	};
-
-	event_attr_init(&attr);
-
-	/*
-	 * Unnamed union member, not supported as struct member named
-	 * initializer in older compilers such as gcc 4.4.7
-	 */
-	attr.sample_period = 1;
-
-	while (attr.precise_ip != 0) {
-		int fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
-		if (fd != -1) {
-			close(fd);
-			break;
-		}
-		--attr.precise_ip;
-	}
-
-	pattr->precise_ip = attr.precise_ip;
-}
-
 int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise)
 {
 	struct perf_evsel *evsel = perf_evsel__new_cycles(precise);
@@ -1856,3 +1828,121 @@ struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evsel_list,
 	}
 	return leader;
 }
+
+int perf_evlist__add_sb_event(struct perf_evlist **evlist,
+			      struct perf_event_attr *attr,
+			      perf_evsel__sb_cb_t cb,
+			      void *data)
+{
+	struct perf_evsel *evsel;
+	bool new_evlist = (*evlist) == NULL;
+
+	if (*evlist == NULL)
+		*evlist = perf_evlist__new();
+	if (*evlist == NULL)
+		return -1;
+
+	if (!attr->sample_id_all) {
+		pr_warning("enabling sample_id_all for all side band events\n");
+		attr->sample_id_all = 1;
+	}
+
+	evsel = perf_evsel__new_idx(attr, (*evlist)->nr_entries);
+	if (!evsel)
+		goto out_err;
+
+	evsel->side_band.cb = cb;
+	evsel->side_band.data = data;
+	perf_evlist__add(*evlist, evsel);
+	return 0;
+
+out_err:
+	if (new_evlist) {
+		perf_evlist__delete(*evlist);
+		*evlist = NULL;
+	}
+	return -1;
+}
+
+static void *perf_evlist__poll_thread(void *arg)
+{
+	struct perf_evlist *evlist = arg;
+	bool draining = false;
+	int i;
+
+	while (draining || !(evlist->thread.done)) {
+		if (draining)
+			draining = false;
+		else if (evlist->thread.done)
+			draining = true;
+
+		if (!draining)
+			perf_evlist__poll(evlist, 1000);
+
+		for (i = 0; i < evlist->nr_mmaps; i++) {
+			struct perf_mmap *map = &evlist->mmap[i];
+			union perf_event *event;
+
+			if (perf_mmap__read_init(map))
+				continue;
+			while ((event = perf_mmap__read_event(map)) != NULL) {
+				struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event);
+
+				if (evsel && evsel->side_band.cb)
+					evsel->side_band.cb(event, evsel->side_band.data);
+				else
+					pr_warning("cannot locate proper evsel for the side band event\n");
+
+				perf_mmap__consume(map);
+			}
+			perf_mmap__read_done(map);
+		}
+	}
+	return NULL;
+}
+
+int perf_evlist__start_sb_thread(struct perf_evlist *evlist,
+				 struct target *target)
+{
+	struct perf_evsel *counter;
+
+	if (!evlist)
+		return 0;
+
+	if (perf_evlist__create_maps(evlist, target))
+		goto out_delete_evlist;
+
+	evlist__for_each_entry(evlist, counter) {
+		if (perf_evsel__open(counter, evlist->cpus,
+				     evlist->threads) < 0)
+			goto out_delete_evlist;
+	}
+
+	if (perf_evlist__mmap(evlist, UINT_MAX))
+		goto out_delete_evlist;
+
+	evlist__for_each_entry(evlist, counter) {
+		if (perf_evsel__enable(counter))
+			goto out_delete_evlist;
+	}
+
+	evlist->thread.done = 0;
+	if (pthread_create(&evlist->thread.th, NULL, perf_evlist__poll_thread, evlist))
+		goto out_delete_evlist;
+
+	return 0;
+
+out_delete_evlist:
+	perf_evlist__delete(evlist);
+	evlist = NULL;
+	return -1;
+}
+
+void perf_evlist__stop_sb_thread(struct perf_evlist *evlist)
+{
+	if (!evlist)
+		return;
+	evlist->thread.done = 1;
+	pthread_join(evlist->thread.th, NULL);
+	perf_evlist__delete(evlist);
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 744906dd4887..6a94785b9100 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -54,6 +54,10 @@ struct perf_evlist {
 				       struct perf_sample *sample);
 	u64		first_sample_time;
 	u64		last_sample_time;
+	struct {
+		pthread_t		th;
+		volatile int		done;
+	} thread;
 };
 
 struct perf_evsel_str_handler {
@@ -87,6 +91,14 @@ int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
 
 int perf_evlist__add_dummy(struct perf_evlist *evlist);
 
+int perf_evlist__add_sb_event(struct perf_evlist **evlist,
+			      struct perf_event_attr *attr,
+			      perf_evsel__sb_cb_t cb,
+			      void *data);
+int perf_evlist__start_sb_thread(struct perf_evlist *evlist,
+				 struct target *target);
+void perf_evlist__stop_sb_thread(struct perf_evlist *evlist);
+
 int perf_evlist__add_newtp(struct perf_evlist *evlist,
 			   const char *sys, const char *name, void *handler);
 
@@ -303,8 +315,6 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 				     struct perf_evsel *tracking_evsel);
 
-void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr);
-
 struct perf_evsel *
 perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 3bbf73e979c0..66d066f18b5b 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -295,7 +295,6 @@ struct perf_evsel *perf_evsel__new_cycles(bool precise)
 	if (!precise)
 		goto new_event;
 
-	perf_event_attr__set_max_precise_ip(&attr);
 	/*
 	 * Now let the usual logic to set up the perf_event_attr defaults
 	 * to kick in when we return and before perf_evsel__open() is called.
@@ -305,6 +304,8 @@ new_event:
 	if (evsel == NULL)
 		goto out;
 
+	evsel->precise_max = true;
+
 	/* use asprintf() because free(evsel) assumes name is allocated */
 	if (asprintf(&evsel->name, "cycles%s%s%.*s",
 		     (attr.precise_ip || attr.exclude_kernel) ? ":" : "",
@@ -1036,7 +1037,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	attr->mmap2 = track && !perf_missing_features.mmap2;
 	attr->comm  = track;
 	attr->ksymbol = track && !perf_missing_features.ksymbol;
-	attr->bpf_event = track && opts->bpf_event &&
+	attr->bpf_event = track && !opts->no_bpf_event &&
 		!perf_missing_features.bpf_event;
 
 	if (opts->record_namespaces)
@@ -1083,7 +1084,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	}
 
 	if (evsel->precise_max)
-		perf_event_attr__set_max_precise_ip(attr);
+		attr->precise_ip = 3;
 
 	if (opts->all_user) {
 		attr->exclude_kernel = 1;
@@ -1292,6 +1293,7 @@ void perf_evsel__exit(struct perf_evsel *evsel)
 {
 	assert(list_empty(&evsel->node));
 	assert(evsel->evlist == NULL);
+	perf_evsel__free_counts(evsel);
 	perf_evsel__free_fd(evsel);
 	perf_evsel__free_id(evsel);
 	perf_evsel__free_config_terms(evsel);
@@ -1342,10 +1344,9 @@ void perf_counts_values__scale(struct perf_counts_values *count,
 			count->val = 0;
 		} else if (count->run < count->ena) {
 			scaled = 1;
-			count->val = (u64)((double) count->val * count->ena / count->run + 0.5);
+			count->val = (u64)((double) count->val * count->ena / count->run);
 		}
-	} else
-		count->ena = count->run = 0;
+	}
 
 	if (pscaled)
 		*pscaled = scaled;
@@ -1749,6 +1750,59 @@ static bool ignore_missing_thread(struct perf_evsel *evsel,
 	return true;
 }
 
+static void display_attr(struct perf_event_attr *attr)
+{
+	if (verbose >= 2) {
+		fprintf(stderr, "%.60s\n", graph_dotted_line);
+		fprintf(stderr, "perf_event_attr:\n");
+		perf_event_attr__fprintf(stderr, attr, __open_attr__fprintf, NULL);
+		fprintf(stderr, "%.60s\n", graph_dotted_line);
+	}
+}
+
+static int perf_event_open(struct perf_evsel *evsel,
+			   pid_t pid, int cpu, int group_fd,
+			   unsigned long flags)
+{
+	int precise_ip = evsel->attr.precise_ip;
+	int fd;
+
+	while (1) {
+		pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
+			  pid, cpu, group_fd, flags);
+
+		fd = sys_perf_event_open(&evsel->attr, pid, cpu, group_fd, flags);
+		if (fd >= 0)
+			break;
+
+		/*
+		 * Do quick precise_ip fallback if:
+		 *  - there is precise_ip set in perf_event_attr
+		 *  - maximum precise is requested
+		 *  - sys_perf_event_open failed with ENOTSUP error,
+		 *    which is associated with wrong precise_ip
+		 */
+		if (!precise_ip || !evsel->precise_max || (errno != ENOTSUP))
+			break;
+
+		/*
+		 * We tried all the precise_ip values, and it's
+		 * still failing, so leave it to standard fallback.
+		 */
+		if (!evsel->attr.precise_ip) {
+			evsel->attr.precise_ip = precise_ip;
+			break;
+		}
+
+		pr_debug2("\nsys_perf_event_open failed, error %d\n", -ENOTSUP);
+		evsel->attr.precise_ip--;
+		pr_debug2("decreasing precise_ip by one (%d)\n", evsel->attr.precise_ip);
+		display_attr(&evsel->attr);
+	}
+
+	return fd;
+}
+
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 		     struct thread_map *threads)
 {
@@ -1824,12 +1878,7 @@ retry_sample_id:
 	if (perf_missing_features.sample_id_all)
 		evsel->attr.sample_id_all = 0;
 
-	if (verbose >= 2) {
-		fprintf(stderr, "%.60s\n", graph_dotted_line);
-		fprintf(stderr, "perf_event_attr:\n");
-		perf_event_attr__fprintf(stderr, &evsel->attr, __open_attr__fprintf, NULL);
-		fprintf(stderr, "%.60s\n", graph_dotted_line);
-	}
+	display_attr(&evsel->attr);
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 
@@ -1841,13 +1890,10 @@ retry_sample_id:
 
 			group_fd = get_group_fd(evsel, cpu, thread);
 retry_open:
-			pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
-				  pid, cpus->map[cpu], group_fd, flags);
-
 			test_attr__ready();
 
-			fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu],
-						 group_fd, flags);
+			fd = perf_event_open(evsel, pid, cpus->map[cpu],
+					     group_fd, flags);
 
 			FD(evsel, cpu, thread) = fd;
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index cc578e02e08f..0f2c6c93d721 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -73,6 +73,8 @@ struct perf_evsel_config_term {
 
 struct perf_stat_evsel;
 
+typedef int (perf_evsel__sb_cb_t)(union perf_event *event, void *data);
+
 /** struct perf_evsel - event selector
  *
  * @evlist - evlist this evsel is in, if it is in one.
@@ -151,6 +153,10 @@ struct perf_evsel {
 	bool			collect_stat;
 	bool			weak_group;
 	const char		*pmu_name;
+	struct {
+		perf_evsel__sb_cb_t	*cb;
+		void			*data;
+	} side_band;
 };
 
 union u64_swap {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 01b324c275b9..b9e693825873 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -18,6 +18,7 @@
 #include <sys/utsname.h>
 #include <linux/time64.h>
 #include <dirent.h>
+#include <bpf/libbpf.h>
 
 #include "evlist.h"
 #include "evsel.h"
@@ -40,6 +41,7 @@
 #include "time-utils.h"
 #include "units.h"
 #include "cputopo.h"
+#include "bpf-event.h"
 
 #include "sane_ctype.h"
 
@@ -861,6 +863,104 @@ static int write_clockid(struct feat_fd *ff,
 			sizeof(ff->ph->env.clockid_res_ns));
 }
 
+static int write_dir_format(struct feat_fd *ff,
+			    struct perf_evlist *evlist __maybe_unused)
+{
+	struct perf_session *session;
+	struct perf_data *data;
+
+	session = container_of(ff->ph, struct perf_session, header);
+	data = session->data;
+
+	if (WARN_ON(!perf_data__is_dir(data)))
+		return -1;
+
+	return do_write(ff, &data->dir.version, sizeof(data->dir.version));
+}
+
+#ifdef HAVE_LIBBPF_SUPPORT
+static int write_bpf_prog_info(struct feat_fd *ff,
+			       struct perf_evlist *evlist __maybe_unused)
+{
+	struct perf_env *env = &ff->ph->env;
+	struct rb_root *root;
+	struct rb_node *next;
+	int ret;
+
+	down_read(&env->bpf_progs.lock);
+
+	ret = do_write(ff, &env->bpf_progs.infos_cnt,
+		       sizeof(env->bpf_progs.infos_cnt));
+	if (ret < 0)
+		goto out;
+
+	root = &env->bpf_progs.infos;
+	next = rb_first(root);
+	while (next) {
+		struct bpf_prog_info_node *node;
+		size_t len;
+
+		node = rb_entry(next, struct bpf_prog_info_node, rb_node);
+		next = rb_next(&node->rb_node);
+		len = sizeof(struct bpf_prog_info_linear) +
+			node->info_linear->data_len;
+
+		/* before writing to file, translate address to offset */
+		bpf_program__bpil_addr_to_offs(node->info_linear);
+		ret = do_write(ff, node->info_linear, len);
+		/*
+		 * translate back to address even when do_write() fails,
+		 * so that this function never changes the data.
+		 */
+		bpf_program__bpil_offs_to_addr(node->info_linear);
+		if (ret < 0)
+			goto out;
+	}
+out:
+	up_read(&env->bpf_progs.lock);
+	return ret;
+}
+#else // HAVE_LIBBPF_SUPPORT
+static int write_bpf_prog_info(struct feat_fd *ff __maybe_unused,
+			       struct perf_evlist *evlist __maybe_unused)
+{
+	return 0;
+}
+#endif // HAVE_LIBBPF_SUPPORT
+
+static int write_bpf_btf(struct feat_fd *ff,
+			 struct perf_evlist *evlist __maybe_unused)
+{
+	struct perf_env *env = &ff->ph->env;
+	struct rb_root *root;
+	struct rb_node *next;
+	int ret;
+
+	down_read(&env->bpf_progs.lock);
+
+	ret = do_write(ff, &env->bpf_progs.btfs_cnt,
+		       sizeof(env->bpf_progs.btfs_cnt));
+
+	if (ret < 0)
+		goto out;
+
+	root = &env->bpf_progs.btfs;
+	next = rb_first(root);
+	while (next) {
+		struct btf_node *node;
+
+		node = rb_entry(next, struct btf_node, rb_node);
+		next = rb_next(&node->rb_node);
+		ret = do_write(ff, &node->id,
+			       sizeof(u32) * 2 + node->data_size);
+		if (ret < 0)
+			goto out;
+	}
+out:
+	up_read(&env->bpf_progs.lock);
+	return ret;
+}
+
 static int cpu_cache_level__sort(const void *a, const void *b)
 {
 	struct cpu_cache_level *cache_a = (struct cpu_cache_level *)a;
@@ -1341,6 +1441,63 @@ static void print_clockid(struct feat_fd *ff, FILE *fp)
 		ff->ph->env.clockid_res_ns * 1000);
 }
 
+static void print_dir_format(struct feat_fd *ff, FILE *fp)
+{
+	struct perf_session *session;
+	struct perf_data *data;
+
+	session = container_of(ff->ph, struct perf_session, header);
+	data = session->data;
+
+	fprintf(fp, "# directory data version : %"PRIu64"\n", data->dir.version);
+}
+
+static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp)
+{
+	struct perf_env *env = &ff->ph->env;
+	struct rb_root *root;
+	struct rb_node *next;
+
+	down_read(&env->bpf_progs.lock);
+
+	root = &env->bpf_progs.infos;
+	next = rb_first(root);
+
+	while (next) {
+		struct bpf_prog_info_node *node;
+
+		node = rb_entry(next, struct bpf_prog_info_node, rb_node);
+		next = rb_next(&node->rb_node);
+
+		bpf_event__print_bpf_prog_info(&node->info_linear->info,
+					       env, fp);
+	}
+
+	up_read(&env->bpf_progs.lock);
+}
+
+static void print_bpf_btf(struct feat_fd *ff, FILE *fp)
+{
+	struct perf_env *env = &ff->ph->env;
+	struct rb_root *root;
+	struct rb_node *next;
+
+	down_read(&env->bpf_progs.lock);
+
+	root = &env->bpf_progs.btfs;
+	next = rb_first(root);
+
+	while (next) {
+		struct btf_node *node;
+
+		node = rb_entry(next, struct btf_node, rb_node);
+		next = rb_next(&node->rb_node);
+		fprintf(fp, "# btf info of id %u\n", node->id);
+	}
+
+	up_read(&env->bpf_progs.lock);
+}
+
 static void free_event_desc(struct perf_evsel *events)
 {
 	struct perf_evsel *evsel;
@@ -2373,6 +2530,139 @@ static int process_clockid(struct feat_fd *ff,
 	return 0;
 }
 
+static int process_dir_format(struct feat_fd *ff,
+			      void *_data __maybe_unused)
+{
+	struct perf_session *session;
+	struct perf_data *data;
+
+	session = container_of(ff->ph, struct perf_session, header);
+	data = session->data;
+
+	if (WARN_ON(!perf_data__is_dir(data)))
+		return -1;
+
+	return do_read_u64(ff, &data->dir.version);
+}
+
+#ifdef HAVE_LIBBPF_SUPPORT
+static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused)
+{
+	struct bpf_prog_info_linear *info_linear;
+	struct bpf_prog_info_node *info_node;
+	struct perf_env *env = &ff->ph->env;
+	u32 count, i;
+	int err = -1;
+
+	if (ff->ph->needs_swap) {
+		pr_warning("interpreting bpf_prog_info from systems with endianity is not yet supported\n");
+		return 0;
+	}
+
+	if (do_read_u32(ff, &count))
+		return -1;
+
+	down_write(&env->bpf_progs.lock);
+
+	for (i = 0; i < count; ++i) {
+		u32 info_len, data_len;
+
+		info_linear = NULL;
+		info_node = NULL;
+		if (do_read_u32(ff, &info_len))
+			goto out;
+		if (do_read_u32(ff, &data_len))
+			goto out;
+
+		if (info_len > sizeof(struct bpf_prog_info)) {
+			pr_warning("detected invalid bpf_prog_info\n");
+			goto out;
+		}
+
+		info_linear = malloc(sizeof(struct bpf_prog_info_linear) +
+				     data_len);
+		if (!info_linear)
+			goto out;
+		info_linear->info_len = sizeof(struct bpf_prog_info);
+		info_linear->data_len = data_len;
+		if (do_read_u64(ff, (u64 *)(&info_linear->arrays)))
+			goto out;
+		if (__do_read(ff, &info_linear->info, info_len))
+			goto out;
+		if (info_len < sizeof(struct bpf_prog_info))
+			memset(((void *)(&info_linear->info)) + info_len, 0,
+			       sizeof(struct bpf_prog_info) - info_len);
+
+		if (__do_read(ff, info_linear->data, data_len))
+			goto out;
+
+		info_node = malloc(sizeof(struct bpf_prog_info_node));
+		if (!info_node)
+			goto out;
+
+		/* after reading from file, translate offset to address */
+		bpf_program__bpil_offs_to_addr(info_linear);
+		info_node->info_linear = info_linear;
+		perf_env__insert_bpf_prog_info(env, info_node);
+	}
+
+	return 0;
+out:
+	free(info_linear);
+	free(info_node);
+	up_write(&env->bpf_progs.lock);
+	return err;
+}
+#else // HAVE_LIBBPF_SUPPORT
+static int process_bpf_prog_info(struct feat_fd *ff __maybe_unused, void *data __maybe_unused)
+{
+	return 0;
+}
+#endif // HAVE_LIBBPF_SUPPORT
+
+static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused)
+{
+	struct perf_env *env = &ff->ph->env;
+	u32 count, i;
+
+	if (ff->ph->needs_swap) {
+		pr_warning("interpreting btf from systems with endianity is not yet supported\n");
+		return 0;
+	}
+
+	if (do_read_u32(ff, &count))
+		return -1;
+
+	down_write(&env->bpf_progs.lock);
+
+	for (i = 0; i < count; ++i) {
+		struct btf_node *node;
+		u32 id, data_size;
+
+		if (do_read_u32(ff, &id))
+			return -1;
+		if (do_read_u32(ff, &data_size))
+			return -1;
+
+		node = malloc(sizeof(struct btf_node) + data_size);
+		if (!node)
+			return -1;
+
+		node->id = id;
+		node->data_size = data_size;
+
+		if (__do_read(ff, node->data, data_size)) {
+			free(node);
+			return -1;
+		}
+
+		perf_env__insert_btf(env, node);
+	}
+
+	up_write(&env->bpf_progs.lock);
+	return 0;
+}
+
 struct feature_ops {
 	int (*write)(struct feat_fd *ff, struct perf_evlist *evlist);
 	void (*print)(struct feat_fd *ff, FILE *fp);
@@ -2432,7 +2722,10 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPN(CACHE,		cache,		true),
 	FEAT_OPR(SAMPLE_TIME,	sample_time,	false),
 	FEAT_OPR(MEM_TOPOLOGY,	mem_topology,	true),
-	FEAT_OPR(CLOCKID,       clockid,        false)
+	FEAT_OPR(CLOCKID,	clockid,	false),
+	FEAT_OPN(DIR_FORMAT,	dir_format,	false),
+	FEAT_OPR(BPF_PROG_INFO, bpf_prog_info,  false),
+	FEAT_OPR(BPF_BTF,       bpf_btf,        false),
 };
 
 struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 0d553ddca0a3..386da49e1bfa 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -39,6 +39,9 @@ enum {
 	HEADER_SAMPLE_TIME,
 	HEADER_MEM_TOPOLOGY,
 	HEADER_CLOCKID,
+	HEADER_DIR_FORMAT,
+	HEADER_BPF_PROG_INFO,
+	HEADER_BPF_BTF,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
@@ -48,6 +51,10 @@ enum perf_header_version {
 	PERF_HEADER_VERSION_2,
 };
 
+enum perf_dir_version {
+	PERF_DIR_VERSION	= 1,
+};
+
 struct perf_file_section {
 	u64 offset;
 	u64 size;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index f9eb95bf3938..7ace7a10054d 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -19,6 +19,7 @@
 #include <math.h>
 #include <inttypes.h>
 #include <sys/param.h>
+#include <linux/time64.h>
 
 static bool hists__filter_entry_by_dso(struct hists *hists,
 				       struct hist_entry *he);
@@ -192,6 +193,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	hists__new_col_len(hists, HISTC_MEM_LVL, 21 + 3);
 	hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12);
 	hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12);
+	hists__new_col_len(hists, HISTC_TIME, 12);
 
 	if (h->srcline) {
 		len = MAX(strlen(h->srcline), strlen(sort_srcline.se_header));
@@ -246,6 +248,14 @@ static void he_stat__add_cpumode_period(struct he_stat *he_stat,
 	}
 }
 
+static long hist_time(unsigned long htime)
+{
+	unsigned long time_quantum = symbol_conf.time_quantum;
+	if (time_quantum)
+		return (htime / time_quantum) * time_quantum;
+	return htime;
+}
+
 static void he_stat__add_period(struct he_stat *he_stat, u64 period,
 				u64 weight)
 {
@@ -426,6 +436,13 @@ static int hist_entry__init(struct hist_entry *he,
 			goto err_rawdata;
 	}
 
+	if (symbol_conf.res_sample) {
+		he->res_samples = calloc(sizeof(struct res_sample),
+					symbol_conf.res_sample);
+		if (!he->res_samples)
+			goto err_srcline;
+	}
+
 	INIT_LIST_HEAD(&he->pairs.node);
 	thread__get(he->thread);
 	he->hroot_in  = RB_ROOT_CACHED;
@@ -436,6 +453,9 @@ static int hist_entry__init(struct hist_entry *he,
 
 	return 0;
 
+err_srcline:
+	free(he->srcline);
+
 err_rawdata:
 	free(he->raw_data);
 
@@ -593,6 +613,32 @@ out:
 	return he;
 }
 
+static unsigned random_max(unsigned high)
+{
+	unsigned thresh = -high % high;
+	for (;;) {
+		unsigned r = random();
+		if (r >= thresh)
+			return r % high;
+	}
+}
+
+static void hists__res_sample(struct hist_entry *he, struct perf_sample *sample)
+{
+	struct res_sample *r;
+	int j;
+
+	if (he->num_res < symbol_conf.res_sample) {
+		j = he->num_res++;
+	} else {
+		j = random_max(symbol_conf.res_sample);
+	}
+	r = &he->res_samples[j];
+	r->time = sample->time;
+	r->cpu = sample->cpu;
+	r->tid = sample->tid;
+}
+
 static struct hist_entry*
 __hists__add_entry(struct hists *hists,
 		   struct addr_location *al,
@@ -635,10 +681,13 @@ __hists__add_entry(struct hists *hists,
 		.raw_data = sample->raw_data,
 		.raw_size = sample->raw_size,
 		.ops = ops,
+		.time = hist_time(sample->time),
 	}, *he = hists__findnew_entry(hists, &entry, al, sample_self);
 
 	if (!hists->has_callchains && he && he->callchain_size != 0)
 		hists->has_callchains = true;
+	if (he && symbol_conf.res_sample)
+		hists__res_sample(he, sample);
 	return he;
 }
 
@@ -1062,8 +1111,10 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 
 	err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent,
 					iter->evsel, al, max_stack_depth);
-	if (err)
+	if (err) {
+		map__put(alm);
 		return err;
+	}
 
 	err = iter->ops->prepare_entry(iter, al);
 	if (err)
@@ -1162,6 +1213,7 @@ void hist_entry__delete(struct hist_entry *he)
 		mem_info__zput(he->mem_info);
 	}
 
+	zfree(&he->res_samples);
 	zfree(&he->stat_acc);
 	free_srcline(he->srcline);
 	if (he->srcfile && he->srcfile[0])
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 4af27fbab24f..76ff6c6d03b8 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -31,6 +31,7 @@ enum hist_filter {
 
 enum hist_column {
 	HISTC_SYMBOL,
+	HISTC_TIME,
 	HISTC_DSO,
 	HISTC_THREAD,
 	HISTC_COMM,
@@ -432,9 +433,18 @@ struct hist_browser_timer {
 };
 
 struct annotation_options;
+struct res_sample;
+
+enum rstype {
+	A_NORMAL,
+	A_ASM,
+	A_SOURCE
+};
 
 #ifdef HAVE_SLANG_SUPPORT
 #include "../ui/keysyms.h"
+void attr_to_script(char *buf, struct perf_event_attr *attr);
+
 int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel,
 			     struct hist_browser_timer *hbt,
 			     struct annotation_options *annotation_opts);
@@ -449,7 +459,13 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
 				  struct perf_env *env,
 				  bool warn_lost_event,
 				  struct annotation_options *annotation_options);
-int script_browse(const char *script_opt);
+
+int script_browse(const char *script_opt, struct perf_evsel *evsel);
+
+void run_script(char *cmd);
+int res_sample_browse(struct res_sample *res_samples, int num_res,
+		      struct perf_evsel *evsel, enum rstype rstype);
+void res_sample_init(void);
 #else
 static inline
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused,
@@ -478,11 +494,22 @@ static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused,
 	return 0;
 }
 
-static inline int script_browse(const char *script_opt __maybe_unused)
+static inline int script_browse(const char *script_opt __maybe_unused,
+				struct perf_evsel *evsel __maybe_unused)
 {
 	return 0;
 }
 
+static inline int res_sample_browse(struct res_sample *res_samples __maybe_unused,
+				    int num_res __maybe_unused,
+				    struct perf_evsel *evsel __maybe_unused,
+				    enum rstype rstype __maybe_unused)
+{
+	return 0;
+}
+
+static inline void res_sample_init(void) {}
+
 #define K_LEFT  -1000
 #define K_RIGHT -2000
 #define K_SWITCH_INPUT_DATA -3000
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 6e03db142091..872fab163585 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -251,19 +251,15 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
 		if (!(decoder->tsc_ctc_ratio_n % decoder->tsc_ctc_ratio_d))
 			decoder->tsc_ctc_mult = decoder->tsc_ctc_ratio_n /
 						decoder->tsc_ctc_ratio_d;
-
-		/*
-		 * Allow for timestamps appearing to backwards because a TSC
-		 * packet has slipped past a MTC packet, so allow 2 MTC ticks
-		 * or ...
-		 */
-		decoder->tsc_slip = multdiv(2 << decoder->mtc_shift,
-					decoder->tsc_ctc_ratio_n,
-					decoder->tsc_ctc_ratio_d);
 	}
-	/* ... or 0x100 paranoia */
-	if (decoder->tsc_slip < 0x100)
-		decoder->tsc_slip = 0x100;
+
+	/*
+	 * A TSC packet can slip past MTC packets so that the timestamp appears
+	 * to go backwards. One estimate is that can be up to about 40 CPU
+	 * cycles, which is certainly less than 0x1000 TSC ticks, but accept
+	 * slippage an order of magnitude more to be on the safe side.
+	 */
+	decoder->tsc_slip = 0x10000;
 
 	intel_pt_log("timestamp: mtc_shift %u\n", decoder->mtc_shift);
 	intel_pt_log("timestamp: tsc_ctc_ratio_n %u\n", decoder->tsc_ctc_ratio_n);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 61959aba7e27..3c520baa198c 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1421,6 +1421,20 @@ static void machine__set_kernel_mmap(struct machine *machine,
 		machine->vmlinux_map->end = ~0ULL;
 }
 
+static void machine__update_kernel_mmap(struct machine *machine,
+				     u64 start, u64 end)
+{
+	struct map *map = machine__kernel_map(machine);
+
+	map__get(map);
+	map_groups__remove(&machine->kmaps, map);
+
+	machine__set_kernel_mmap(machine, start, end);
+
+	map_groups__insert(&machine->kmaps, map);
+	map__put(map);
+}
+
 int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
@@ -1453,17 +1467,11 @@ int machine__create_kernel_maps(struct machine *machine)
 			goto out_put;
 		}
 
-		/* we have a real start address now, so re-order the kmaps */
-		map = machine__kernel_map(machine);
-
-		map__get(map);
-		map_groups__remove(&machine->kmaps, map);
-
-		/* assume it's the last in the kmaps */
-		machine__set_kernel_mmap(machine, addr, ~0ULL);
-
-		map_groups__insert(&machine->kmaps, map);
-		map__put(map);
+		/*
+		 * we have a real start address now, so re-order the kmaps
+		 * assume it's the last in the kmaps
+		 */
+		machine__update_kernel_mmap(machine, addr, ~0ULL);
 	}
 
 	if (machine__create_extra_kernel_maps(machine, kernel))
@@ -1599,7 +1607,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		if (strstr(kernel->long_name, "vmlinux"))
 			dso__set_short_name(kernel, "[kernel.vmlinux]", false);
 
-		machine__set_kernel_mmap(machine, event->mmap.start,
+		machine__update_kernel_mmap(machine, event->mmap.start,
 					 event->mmap.start + event->mmap.len);
 
 		/*
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index fbeb0c6efaa6..e32628cd20a7 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -577,10 +577,25 @@ static void __maps__purge(struct maps *maps)
 	}
 }
 
+static void __maps__purge_names(struct maps *maps)
+{
+	struct rb_root *root = &maps->names;
+	struct rb_node *next = rb_first(root);
+
+	while (next) {
+		struct map *pos = rb_entry(next, struct map, rb_node_name);
+
+		next = rb_next(&pos->rb_node_name);
+		rb_erase_init(&pos->rb_node_name, root);
+		map__put(pos);
+	}
+}
+
 static void maps__exit(struct maps *maps)
 {
 	down_write(&maps->lock);
 	__maps__purge(maps);
+	__maps__purge_names(maps);
 	up_write(&maps->lock);
 }
 
@@ -917,6 +932,9 @@ static void __maps__remove(struct maps *maps, struct map *map)
 {
 	rb_erase_init(&map->rb_node, &maps->entries);
 	map__put(map);
+
+	rb_erase_init(&map->rb_node_name, &maps->names);
+	map__put(map);
 }
 
 void maps__remove(struct maps *maps, struct map *map)
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index ea523d3b248f..989fed6f43b5 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -270,6 +270,8 @@ static int __ordered_events__flush(struct ordered_events *oe, enum oe_flush how,
 		"FINAL",
 		"ROUND",
 		"HALF ",
+		"TOP  ",
+		"TIME ",
 	};
 	int err;
 	bool show_progress = false;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 4dcc01b2532c..5ef4939408f2 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -2271,6 +2271,7 @@ static bool is_event_supported(u8 type, unsigned config)
 		perf_evsel__delete(evsel);
 	}
 
+	thread_map__put(tmap);
 	return ret;
 }
 
@@ -2341,6 +2342,7 @@ void print_sdt_events(const char *subsys_glob, const char *event_glob,
 				printf("  %-50s [%s]\n", buf, "SDT event");
 				free(buf);
 			}
+			free(path);
 		} else
 			printf("  %-50s [%s]\n", nd->s, "SDT event");
 		if (nd2) {
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 6199a3174ab9..e0429f4ef335 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -732,10 +732,20 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
 
 		if (!is_arm_pmu_core(name)) {
 			pname = pe->pmu ? pe->pmu : "cpu";
+
+			/*
+			 * uncore alias may be from different PMU
+			 * with common prefix
+			 */
+			if (pmu_is_uncore(name) &&
+			    !strncmp(pname, name, strlen(pname)))
+				goto new_alias;
+
 			if (strcmp(pname, name))
 				continue;
 		}
 
+new_alias:
 		/* need type casts to override 'const' */
 		__perf_pmu__new_alias(head, NULL, (char *)pe->name,
 				(char *)pe->desc, (char *)pe->event,
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index a1b8d9649ca7..198e09ff611e 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -160,8 +160,10 @@ static struct map *kernel_get_module_map(const char *module)
 	if (module && strchr(module, '/'))
 		return dso__new_map(module);
 
-	if (!module)
-		module = "kernel";
+	if (!module) {
+		pos = machine__kernel_map(host_machine);
+		return map__get(pos);
+	}
 
 	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
 		/* short_name is "[module]" */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index db643f3c2b95..b17f1c9bc965 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -132,6 +132,7 @@ struct perf_session *perf_session__new(struct perf_data *data,
 	ordered_events__init(&session->ordered_events,
 			     ordered_events__deliver_event, NULL);
 
+	perf_env__init(&session->header.env);
 	if (data) {
 		if (perf_data__open(data))
 			goto out_delete;
@@ -152,6 +153,10 @@ struct perf_session *perf_session__new(struct perf_data *data,
 			}
 
 			perf_evlist__init_trace_event_sample_raw(session->evlist);
+
+			/* Open the directory data. */
+			if (data->is_dir && perf_data__open_dir(data))
+				goto out_delete;
 		}
 	} else  {
 		session->machines.host.env = &perf_env;
@@ -1843,10 +1848,17 @@ fetch_mmaped_event(struct perf_session *session,
 #define NUM_MMAPS 128
 #endif
 
+struct reader;
+
+typedef s64 (*reader_cb_t)(struct perf_session *session,
+			   union perf_event *event,
+			   u64 file_offset);
+
 struct reader {
-	int	fd;
-	u64	data_size;
-	u64	data_offset;
+	int		 fd;
+	u64		 data_size;
+	u64		 data_offset;
+	reader_cb_t	 process;
 };
 
 static int
@@ -1917,7 +1929,7 @@ more:
 	size = event->header.size;
 
 	if (size < sizeof(struct perf_event_header) ||
-	    (skip = perf_session__process_event(session, event, file_pos)) < 0) {
+	    (skip = rd->process(session, event, file_pos)) < 0) {
 		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
 		       file_offset + head, event->header.size,
 		       event->header.type);
@@ -1943,12 +1955,20 @@ out:
 	return err;
 }
 
+static s64 process_simple(struct perf_session *session,
+			  union perf_event *event,
+			  u64 file_offset)
+{
+	return perf_session__process_event(session, event, file_offset);
+}
+
 static int __perf_session__process_events(struct perf_session *session)
 {
 	struct reader rd = {
 		.fd		= perf_data__fd(session->data),
 		.data_size	= session->header.data_size,
 		.data_offset	= session->header.data_offset,
+		.process	= process_simple,
 	};
 	struct ordered_events *oe = &session->ordered_events;
 	struct perf_tool *tool = session->tool;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index d2299e912e59..5d2518e89fc4 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -3,6 +3,7 @@
 #include <inttypes.h>
 #include <regex.h>
 #include <linux/mman.h>
+#include <linux/time64.h>
 #include "sort.h"
 #include "hist.h"
 #include "comm.h"
@@ -12,9 +13,11 @@
 #include "evsel.h"
 #include "evlist.h"
 #include "strlist.h"
+#include "strbuf.h"
 #include <traceevent/event-parse.h>
 #include "mem-events.h"
 #include "annotate.h"
+#include "time-utils.h"
 #include <linux/kernel.h>
 
 regex_t		parent_regex;
@@ -654,6 +657,42 @@ struct sort_entry sort_socket = {
 	.se_width_idx	= HISTC_SOCKET,
 };
 
+/* --sort time */
+
+static int64_t
+sort__time_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return right->time - left->time;
+}
+
+static int hist_entry__time_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width)
+{
+	unsigned long secs;
+	unsigned long long nsecs;
+	char he_time[32];
+
+	nsecs = he->time;
+	secs = nsecs / NSEC_PER_SEC;
+	nsecs -= secs * NSEC_PER_SEC;
+
+	if (symbol_conf.nanosecs)
+		snprintf(he_time, sizeof he_time, "%5lu.%09llu: ",
+			 secs, nsecs);
+	else
+		timestamp__scnprintf_usec(he->time, he_time,
+					  sizeof(he_time));
+
+	return repsep_snprintf(bf, size, "%-.*s", width, he_time);
+}
+
+struct sort_entry sort_time = {
+	.se_header      = "Time",
+	.se_cmp	        = sort__time_cmp,
+	.se_snprintf    = hist_entry__time_snprintf,
+	.se_width_idx	= HISTC_TIME,
+};
+
 /* --sort trace */
 
 static char *get_trace_output(struct hist_entry *he)
@@ -1634,6 +1673,7 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_DSO_SIZE, "dso_size", sort_dso_size),
 	DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id),
 	DIM(SORT_SYM_IPC_NULL, "ipc_null", sort_sym_ipc_null),
+	DIM(SORT_TIME, "time", sort_time),
 };
 
 #undef DIM
@@ -3068,3 +3108,54 @@ void reset_output_field(void)
 	reset_dimensions();
 	perf_hpp__reset_output_field(&perf_hpp_list);
 }
+
+#define INDENT (3*8 + 1)
+
+static void add_key(struct strbuf *sb, const char *str, int *llen)
+{
+	if (*llen >= 75) {
+		strbuf_addstr(sb, "\n\t\t\t ");
+		*llen = INDENT;
+	}
+	strbuf_addf(sb, " %s", str);
+	*llen += strlen(str) + 1;
+}
+
+static void add_sort_string(struct strbuf *sb, struct sort_dimension *s, int n,
+			    int *llen)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		add_key(sb, s[i].name, llen);
+}
+
+static void add_hpp_sort_string(struct strbuf *sb, struct hpp_dimension *s, int n,
+				int *llen)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		add_key(sb, s[i].name, llen);
+}
+
+const char *sort_help(const char *prefix)
+{
+	struct strbuf sb;
+	char *s;
+	int len = strlen(prefix) + INDENT;
+
+	strbuf_init(&sb, 300);
+	strbuf_addstr(&sb, prefix);
+	add_hpp_sort_string(&sb, hpp_sort_dimensions,
+			    ARRAY_SIZE(hpp_sort_dimensions), &len);
+	add_sort_string(&sb, common_sort_dimensions,
+			    ARRAY_SIZE(common_sort_dimensions), &len);
+	add_sort_string(&sb, bstack_sort_dimensions,
+			    ARRAY_SIZE(bstack_sort_dimensions), &len);
+	add_sort_string(&sb, memory_sort_dimensions,
+			    ARRAY_SIZE(memory_sort_dimensions), &len);
+	s = strbuf_detach(&sb, NULL);
+	strbuf_release(&sb);
+	return s;
+}
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 2fbee0b1011c..ce376a73f964 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -47,6 +47,12 @@ extern struct sort_entry sort_srcline;
 extern enum sort_type sort__first_dimension;
 extern const char default_mem_sort_order[];
 
+struct res_sample {
+	u64 time;
+	int cpu;
+	int tid;
+};
+
 struct he_stat {
 	u64			period;
 	u64			period_sys;
@@ -135,10 +141,13 @@ struct hist_entry {
 	char			*srcfile;
 	struct symbol		*parent;
 	struct branch_info	*branch_info;
+	long			time;
 	struct hists		*hists;
 	struct mem_info		*mem_info;
 	void			*raw_data;
 	u32			raw_size;
+	int			num_res;
+	struct res_sample	*res_samples;
 	void			*trace_output;
 	struct perf_hpp_list	*hpp_list;
 	struct hist_entry	*parent_he;
@@ -231,6 +240,7 @@ enum sort_type {
 	SORT_DSO_SIZE,
 	SORT_CGROUP_ID,
 	SORT_SYM_IPC_NULL,
+	SORT_TIME,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,
@@ -286,6 +296,8 @@ void reset_output_field(void);
 void sort__setup_elide(FILE *fp);
 void perf_hpp__set_elide(int idx, bool elide);
 
+const char *sort_help(const char *prefix);
+
 int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset);
 
 bool is_strict_order(const char *order);
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 4d40515307b8..2856cc9d5a31 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -291,10 +291,8 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel
 		break;
 	case AGGR_GLOBAL:
 		aggr->val += count->val;
-		if (config->scale) {
-			aggr->ena += count->ena;
-			aggr->run += count->run;
-		}
+		aggr->ena += count->ena;
+		aggr->run += count->run;
 	case AGGR_UNSET:
 	default:
 		break;
@@ -442,10 +440,8 @@ int create_perf_stat_counter(struct perf_evsel *evsel,
 	struct perf_event_attr *attr = &evsel->attr;
 	struct perf_evsel *leader = evsel->leader;
 
-	if (config->scale) {
-		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
-				    PERF_FORMAT_TOTAL_TIME_RUNNING;
-	}
+	attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
+			    PERF_FORMAT_TOTAL_TIME_RUNNING;
 
 	/*
 	 * The event is part of non trivial group, let's enable
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 758bf5f74e6e..5cbad55cd99d 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -6,6 +6,7 @@
 #include <string.h>
 #include <linux/kernel.h>
 #include <linux/mman.h>
+#include <linux/time64.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/param.h>
@@ -39,15 +40,18 @@ int vmlinux_path__nr_entries;
 char **vmlinux_path;
 
 struct symbol_conf symbol_conf = {
+	.nanosecs		= false,
 	.use_modules		= true,
 	.try_vmlinux_path	= true,
 	.demangle		= true,
 	.demangle_kernel	= false,
 	.cumulate_callchain	= true,
+	.time_quantum		= 100 * NSEC_PER_MSEC, /* 100ms */
 	.show_hist_headers	= true,
 	.symfs			= "",
 	.event_group		= true,
 	.inline_name		= true,
+	.res_sample		= 0,
 };
 
 static enum dso_binary_type binary_type_symtab[] = {
@@ -1451,6 +1455,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
 	case DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO:
 		return true;
 
+	case DSO_BINARY_TYPE__BPF_PROG_INFO:
 	case DSO_BINARY_TYPE__NOT_FOUND:
 	default:
 		return false;
diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h
index fffea68c1203..6c55fa6fccec 100644
--- a/tools/perf/util/symbol_conf.h
+++ b/tools/perf/util/symbol_conf.h
@@ -8,6 +8,7 @@ struct strlist;
 struct intlist;
 
 struct symbol_conf {
+	bool		nanosecs;
 	unsigned short	priv_size;
 	bool		try_vmlinux_path,
 			init_annotation,
@@ -55,6 +56,7 @@ struct symbol_conf {
 			*sym_list_str,
 			*col_width_list_str,
 			*bt_stop_list_str;
+	unsigned long	time_quantum;
        struct strlist	*dso_list,
 			*comm_list,
 			*sym_list,
@@ -66,6 +68,7 @@ struct symbol_conf {
 	struct intlist	*pid_list,
 			*tid_list;
 	const char	*symfs;
+	int		res_sample;
 };
 
 extern struct symbol_conf symbol_conf;
diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c
index 0f53baec660e..20663a460df3 100644
--- a/tools/perf/util/time-utils.c
+++ b/tools/perf/util/time-utils.c
@@ -453,6 +453,14 @@ int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz)
 	return scnprintf(buf, sz, "%"PRIu64".%06"PRIu64, sec, usec);
 }
 
+int timestamp__scnprintf_nsec(u64 timestamp, char *buf, size_t sz)
+{
+	u64 sec  = timestamp / NSEC_PER_SEC,
+	    nsec = timestamp % NSEC_PER_SEC;
+
+	return scnprintf(buf, sz, "%" PRIu64 ".%09" PRIu64, sec, nsec);
+}
+
 int fetch_current_timestamp(char *buf, size_t sz)
 {
 	struct timeval tv;
diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h
index b923de44e36f..72a42ea1d513 100644
--- a/tools/perf/util/time-utils.h
+++ b/tools/perf/util/time-utils.h
@@ -30,6 +30,7 @@ int perf_time__parse_for_ranges(const char *str, struct perf_session *session,
 				int *range_size, int *range_num);
 
 int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz);
+int timestamp__scnprintf_nsec(u64 timestamp, char *buf, size_t sz);
 
 int fetch_current_timestamp(char *buf, size_t sz);