Merge tag 'perf-core-for-mingo-5.1-20190321' of...

Merge tag 'perf-core-for-mingo-5.1-20190321' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/core improvements and fixes from Arnaldo:

BPF:

  Song Liu:

  - Add support for annotating BPF programs, using the PERF_RECORD_BPF_EVENT
    and PERF_RECORD_KSYMBOL recently added to the kernel and plugging
    binutils's libopcodes disassembly of BPF programs with the existing
    annotation interfaces in 'perf annotate', 'perf report' and 'perf top'
    various output formats (--stdio, --stdio2, --tui).

perf list:

  Andi Kleen:

  - Filter metrics when using substring search.

perf record:

  Andi Kleen:

  - Allow to limit number of reported perf.data files

  - Clarify help for --switch-output.

perf report:

  Andi Kleen

  - Indicate JITed code better.

  - Show all sort keys in help output.

perf script:

  Andi Kleen:

  - Support relative time.

perf stat:

  Andi Kleen:

  - Improve scaling.

General:

  Changbin Du:

  - Fix some mostly error path memory and reference count leaks found
    using gcc's ASan and UBSan.

Vendor events:

  Mamatha Inamdar:

  - Remove P8 HW events which are not supported.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

tools/build/Makefile.feature

@@ -66,7 +66,8 @@ FEATURE_TESTS_BASIC :=                  \
         sched_getcpu			\
         sdt				\
         setns				\
-        libaio
+        libaio				\
+        disassembler-four-args
 
 # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
 # of all feature tests
@@ -118,7 +119,8 @@ FEATURE_DISPLAY ?=              \
          lzma                   \
          get_cpuid              \
          bpf			\
-         libaio
+         libaio			\
+         disassembler-four-args
 
 # Set FEATURE_CHECK_(C|LD)FLAGS-all for all FEATURE_TESTS features.
 # If in the future we need per-feature checks/flags for features not

tools/build/feature/test-all.c

@@ -178,6 +178,10 @@
 # include "test-reallocarray.c"
 #undef main
 
+#define main main_test_disassembler_four_args
+# include "test-disassembler-four-args.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
@@ -219,6 +223,7 @@ int main(int argc, char *argv[])
 	main_test_setns();
 	main_test_libaio();
 	main_test_reallocarray();
+	main_test_disassembler_four_args();
 
 	return 0;
 }

tools/lib/bpf/libbpf.c

@@ -112,6 +112,11 @@ void libbpf_print(enum libbpf_print_level level, const char *format, ...)
 # define LIBBPF_ELF_C_READ_MMAP ELF_C_READ
 #endif
 
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+	return (__u64) (unsigned long) ptr;
+}
+
 struct bpf_capabilities {
 	/* v4.14: kernel support for program & map names. */
 	__u32 name:1;
@@ -622,7 +627,7 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
 	bool strict = !(flags & MAPS_RELAX_COMPAT);
 	int i, map_idx, map_def_sz, nr_maps = 0;
 	Elf_Scn *scn;
-	Elf_Data *data;
+	Elf_Data *data = NULL;
 	Elf_Data *symbols = obj->efile.symbols;
 
 	if (obj->efile.maps_shndx < 0)
@@ -2999,3 +3004,249 @@ bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
 	ring_buffer_write_tail(header, data_tail);
 	return ret;
 }
+
+struct bpf_prog_info_array_desc {
+	int	array_offset;	/* e.g. offset of jited_prog_insns */
+	int	count_offset;	/* e.g. offset of jited_prog_len */
+	int	size_offset;	/* > 0: offset of rec size,
+				 * < 0: fix size of -size_offset
+				 */
+};
+
+static struct bpf_prog_info_array_desc bpf_prog_info_array_desc[] = {
+	[BPF_PROG_INFO_JITED_INSNS] = {
+		offsetof(struct bpf_prog_info, jited_prog_insns),
+		offsetof(struct bpf_prog_info, jited_prog_len),
+		-1,
+	},
+	[BPF_PROG_INFO_XLATED_INSNS] = {
+		offsetof(struct bpf_prog_info, xlated_prog_insns),
+		offsetof(struct bpf_prog_info, xlated_prog_len),
+		-1,
+	},
+	[BPF_PROG_INFO_MAP_IDS] = {
+		offsetof(struct bpf_prog_info, map_ids),
+		offsetof(struct bpf_prog_info, nr_map_ids),
+		-(int)sizeof(__u32),
+	},
+	[BPF_PROG_INFO_JITED_KSYMS] = {
+		offsetof(struct bpf_prog_info, jited_ksyms),
+		offsetof(struct bpf_prog_info, nr_jited_ksyms),
+		-(int)sizeof(__u64),
+	},
+	[BPF_PROG_INFO_JITED_FUNC_LENS] = {
+		offsetof(struct bpf_prog_info, jited_func_lens),
+		offsetof(struct bpf_prog_info, nr_jited_func_lens),
+		-(int)sizeof(__u32),
+	},
+	[BPF_PROG_INFO_FUNC_INFO] = {
+		offsetof(struct bpf_prog_info, func_info),
+		offsetof(struct bpf_prog_info, nr_func_info),
+		offsetof(struct bpf_prog_info, func_info_rec_size),
+	},
+	[BPF_PROG_INFO_LINE_INFO] = {
+		offsetof(struct bpf_prog_info, line_info),
+		offsetof(struct bpf_prog_info, nr_line_info),
+		offsetof(struct bpf_prog_info, line_info_rec_size),
+	},
+	[BPF_PROG_INFO_JITED_LINE_INFO] = {
+		offsetof(struct bpf_prog_info, jited_line_info),
+		offsetof(struct bpf_prog_info, nr_jited_line_info),
+		offsetof(struct bpf_prog_info, jited_line_info_rec_size),
+	},
+	[BPF_PROG_INFO_PROG_TAGS] = {
+		offsetof(struct bpf_prog_info, prog_tags),
+		offsetof(struct bpf_prog_info, nr_prog_tags),
+		-(int)sizeof(__u8) * BPF_TAG_SIZE,
+	},
+
+};
+
+static __u32 bpf_prog_info_read_offset_u32(struct bpf_prog_info *info, int offset)
+{
+	__u32 *array = (__u32 *)info;
+
+	if (offset >= 0)
+		return array[offset / sizeof(__u32)];
+	return -(int)offset;
+}
+
+static __u64 bpf_prog_info_read_offset_u64(struct bpf_prog_info *info, int offset)
+{
+	__u64 *array = (__u64 *)info;
+
+	if (offset >= 0)
+		return array[offset / sizeof(__u64)];
+	return -(int)offset;
+}
+
+static void bpf_prog_info_set_offset_u32(struct bpf_prog_info *info, int offset,
+					 __u32 val)
+{
+	__u32 *array = (__u32 *)info;
+
+	if (offset >= 0)
+		array[offset / sizeof(__u32)] = val;
+}
+
+static void bpf_prog_info_set_offset_u64(struct bpf_prog_info *info, int offset,
+					 __u64 val)
+{
+	__u64 *array = (__u64 *)info;
+
+	if (offset >= 0)
+		array[offset / sizeof(__u64)] = val;
+}
+
+struct bpf_prog_info_linear *
+bpf_program__get_prog_info_linear(int fd, __u64 arrays)
+{
+	struct bpf_prog_info_linear *info_linear;
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
+	__u32 data_len = 0;
+	int i, err;
+	void *ptr;
+
+	if (arrays >> BPF_PROG_INFO_LAST_ARRAY)
+		return ERR_PTR(-EINVAL);
+
+	/* step 1: get array dimensions */
+	err = bpf_obj_get_info_by_fd(fd, &info, &info_len);
+	if (err) {
+		pr_debug("can't get prog info: %s", strerror(errno));
+		return ERR_PTR(-EFAULT);
+	}
+
+	/* step 2: calculate total size of all arrays */
+	for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
+		bool include_array = (arrays & (1UL << i)) > 0;
+		struct bpf_prog_info_array_desc *desc;
+		__u32 count, size;
+
+		desc = bpf_prog_info_array_desc + i;
+
+		/* kernel is too old to support this field */
+		if (info_len < desc->array_offset + sizeof(__u32) ||
+		    info_len < desc->count_offset + sizeof(__u32) ||
+		    (desc->size_offset > 0 && info_len < desc->size_offset))
+			include_array = false;
+
+		if (!include_array) {
+			arrays &= ~(1UL << i);	/* clear the bit */
+			continue;
+		}
+
+		count = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
+		size  = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
+
+		data_len += count * size;
+	}
+
+	/* step 3: allocate continuous memory */
+	data_len = roundup(data_len, sizeof(__u64));
+	info_linear = malloc(sizeof(struct bpf_prog_info_linear) + data_len);
+	if (!info_linear)
+		return ERR_PTR(-ENOMEM);
+
+	/* step 4: fill data to info_linear->info */
+	info_linear->arrays = arrays;
+	memset(&info_linear->info, 0, sizeof(info));
+	ptr = info_linear->data;
+
+	for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
+		struct bpf_prog_info_array_desc *desc;
+		__u32 count, size;
+
+		if ((arrays & (1UL << i)) == 0)
+			continue;
+
+		desc  = bpf_prog_info_array_desc + i;
+		count = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
+		size  = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
+		bpf_prog_info_set_offset_u32(&info_linear->info,
+					     desc->count_offset, count);
+		bpf_prog_info_set_offset_u32(&info_linear->info,
+					     desc->size_offset, size);
+		bpf_prog_info_set_offset_u64(&info_linear->info,
+					     desc->array_offset,
+					     ptr_to_u64(ptr));
+		ptr += count * size;
+	}
+
+	/* step 5: call syscall again to get required arrays */
+	err = bpf_obj_get_info_by_fd(fd, &info_linear->info, &info_len);
+	if (err) {
+		pr_debug("can't get prog info: %s", strerror(errno));
+		free(info_linear);
+		return ERR_PTR(-EFAULT);
+	}
+
+	/* step 6: verify the data */
+	for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
+		struct bpf_prog_info_array_desc *desc;
+		__u32 v1, v2;
+
+		if ((arrays & (1UL << i)) == 0)
+			continue;
+
+		desc = bpf_prog_info_array_desc + i;
+		v1 = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
+		v2 = bpf_prog_info_read_offset_u32(&info_linear->info,
+						   desc->count_offset);
+		if (v1 != v2)
+			pr_warning("%s: mismatch in element count\n", __func__);
+
+		v1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
+		v2 = bpf_prog_info_read_offset_u32(&info_linear->info,
+						   desc->size_offset);
+		if (v1 != v2)
+			pr_warning("%s: mismatch in rec size\n", __func__);
+	}
+
+	/* step 7: update info_len and data_len */
+	info_linear->info_len = sizeof(struct bpf_prog_info);
+	info_linear->data_len = data_len;
+
+	return info_linear;
+}
+
+void bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear)
+{
+	int i;
+
+	for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
+		struct bpf_prog_info_array_desc *desc;
+		__u64 addr, offs;
+
+		if ((info_linear->arrays & (1UL << i)) == 0)
+			continue;
+
+		desc = bpf_prog_info_array_desc + i;
+		addr = bpf_prog_info_read_offset_u64(&info_linear->info,
+						     desc->array_offset);
+		offs = addr - ptr_to_u64(info_linear->data);
+		bpf_prog_info_set_offset_u64(&info_linear->info,
+					     desc->array_offset, offs);
+	}
+}
+
+void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear)
+{
+	int i;
+
+	for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) {
+		struct bpf_prog_info_array_desc *desc;
+		__u64 addr, offs;
+
+		if ((info_linear->arrays & (1UL << i)) == 0)
+			continue;
+
+		desc = bpf_prog_info_array_desc + i;
+		offs = bpf_prog_info_read_offset_u64(&info_linear->info,
+						     desc->array_offset);
+		addr = offs + ptr_to_u64(info_linear->data);
+		bpf_prog_info_set_offset_u64(&info_linear->info,
+					     desc->array_offset, addr);
+	}
+}

tools/lib/bpf/libbpf.h

@@ -378,6 +378,69 @@ LIBBPF_API bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex);
 LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id,
 				 enum bpf_prog_type prog_type, __u32 ifindex);
 
+/*
+ * Get bpf_prog_info in continuous memory
+ *
+ * struct bpf_prog_info has multiple arrays. The user has option to choose
+ * arrays to fetch from kernel. The following APIs provide an uniform way to
+ * fetch these data. All arrays in bpf_prog_info are stored in a single
+ * continuous memory region. This makes it easy to store the info in a
+ * file.
+ *
+ * Before writing bpf_prog_info_linear to files, it is necessary to
+ * translate pointers in bpf_prog_info to offsets. Helper functions
+ * bpf_program__bpil_addr_to_offs() and bpf_program__bpil_offs_to_addr()
+ * are introduced to switch between pointers and offsets.
+ *
+ * Examples:
+ *   # To fetch map_ids and prog_tags:
+ *   __u64 arrays = (1UL << BPF_PROG_INFO_MAP_IDS) |
+ *           (1UL << BPF_PROG_INFO_PROG_TAGS);
+ *   struct bpf_prog_info_linear *info_linear =
+ *           bpf_program__get_prog_info_linear(fd, arrays);
+ *
+ *   # To save data in file
+ *   bpf_program__bpil_addr_to_offs(info_linear);
+ *   write(f, info_linear, sizeof(*info_linear) + info_linear->data_len);
+ *
+ *   # To read data from file
+ *   read(f, info_linear, <proper_size>);
+ *   bpf_program__bpil_offs_to_addr(info_linear);
+ */
+enum bpf_prog_info_array {
+	BPF_PROG_INFO_FIRST_ARRAY = 0,
+	BPF_PROG_INFO_JITED_INSNS = 0,
+	BPF_PROG_INFO_XLATED_INSNS,
+	BPF_PROG_INFO_MAP_IDS,
+	BPF_PROG_INFO_JITED_KSYMS,
+	BPF_PROG_INFO_JITED_FUNC_LENS,
+	BPF_PROG_INFO_FUNC_INFO,
+	BPF_PROG_INFO_LINE_INFO,
+	BPF_PROG_INFO_JITED_LINE_INFO,
+	BPF_PROG_INFO_PROG_TAGS,
+	BPF_PROG_INFO_LAST_ARRAY,
+};
+
+struct bpf_prog_info_linear {
+	/* size of struct bpf_prog_info, when the tool is compiled */
+	__u32			info_len;
+	/* total bytes allocated for data, round up to 8 bytes */
+	__u32			data_len;
+	/* which arrays are included in data */
+	__u64			arrays;
+	struct bpf_prog_info	info;
+	__u8			data[];
+};
+
+LIBBPF_API struct bpf_prog_info_linear *
+bpf_program__get_prog_info_linear(int fd, __u64 arrays);
+
+LIBBPF_API void
+bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear);
+
+LIBBPF_API void
+bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear);
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif

tools/lib/bpf/libbpf.map

@@ -153,4 +153,7 @@ LIBBPF_0.0.2 {
 		xsk_socket__delete;
 		xsk_umem__fd;
 		xsk_socket__fd;
+		bpf_program__get_prog_info_linear;
+		bpf_program__bpil_addr_to_offs;
+		bpf_program__bpil_offs_to_addr;
 } LIBBPF_0.0.1;

tools/perf/Documentation/Build.txt

@@ -47,3 +47,27 @@ Those objects are then used in final linking:
 
 NOTE this description is omitting other libraries involved, only
      focusing on build framework outcomes
+
+3) Build with ASan or UBSan
+==========================
+  $ cd tools/perf
+  $ make DESTDIR=/usr
+  $ make DESTDIR=/usr install
+
+AddressSanitizer (or ASan) is a GCC feature that detects memory corruption bugs
+such as buffer overflows and memory leaks.
+
+  $ cd tools/perf
+  $ make DEBUG=1 EXTRA_CFLAGS='-fno-omit-frame-pointer -fsanitize=address'
+  $ ASAN_OPTIONS=log_path=asan.log ./perf record -a
+
+ASan outputs all detected issues into a log file named 'asan.log.<pid>'.
+
+UndefinedBehaviorSanitizer (or UBSan) is a fast undefined behavior detector
+supported by GCC. UBSan detects undefined behaviors of programs at runtime.
+
+  $ cd tools/perf
+  $ make DEBUG=1 EXTRA_CFLAGS='-fno-omit-frame-pointer -fsanitize=undefined'
+  $ UBSAN_OPTIONS=print_stacktrace=1 ./perf record -a
+
+If UBSan detects any problem at runtime, it outputs a “runtime error:” message.

tools/perf/Documentation/perf-config.txt

@@ -114,7 +114,7 @@ Given a $HOME/.perfconfig like this:
 
 	[report]
 		# Defaults
-		sort-order = comm,dso,symbol
+		sort_order = comm,dso,symbol
 		percent-limit = 0
 		queue-size = 0
 		children = true

tools/perf/Documentation/perf-record.txt

@@ -495,6 +495,10 @@ overhead. You can still switch them on with:
 
   --switch-output --no-no-buildid  --no-no-buildid-cache
 
+--switch-max-files=N::
+
+When rotating perf.data with --switch-output, only keep N files.
+
 --dry-run::
 Parse options then exit. --dry-run can be used to detect errors in cmdline
 options.

tools/perf/Documentation/perf-script.txt

@@ -380,6 +380,9 @@ include::itrace.txt[]
 	Set the maximum number of program blocks to print with brstackasm for
 	each sample.
 
+--reltime::
+	Print time stamps relative to trace start.
+
 --per-event-dump::
 	Create per event files with a "perf.data.EVENT.dump" name instead of
         printing to stdout, useful, for instance, for generating flamegraphs.

tools/perf/Documentation/perf-stat.txt

@@ -72,9 +72,8 @@ report::
 --all-cpus::
         system-wide collection from all CPUs (default if no target is specified)
 
--c::
---scale::
-	scale/normalize counter values
+--no-scale::
+	Don't scale/normalize counter values
 
 -d::
 --detailed::

tools/perf/Makefile.config

@@ -227,6 +227,8 @@ FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
 
 FEATURE_CHECK_LDFLAGS-libaio = -lrt
 
+FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes
+
 CFLAGS += -fno-omit-frame-pointer
 CFLAGS += -ggdb3
 CFLAGS += -funwind-tables
@@ -713,7 +715,7 @@ else
 endif
 
 ifeq ($(feature-libbfd), 1)
-  EXTLIBS += -lbfd
+  EXTLIBS += -lbfd -lopcodes
 else
   # we are on a system that requires -liberty and (maybe) -lz
   # to link against -lbfd; test each case individually here
@@ -724,12 +726,15 @@ else
   $(call feature_check,libbfd-liberty-z)
 
   ifeq ($(feature-libbfd-liberty), 1)
-    EXTLIBS += -lbfd -liberty
+    EXTLIBS += -lbfd -lopcodes -liberty
+    FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -ldl
   else
     ifeq ($(feature-libbfd-liberty-z), 1)
-      EXTLIBS += -lbfd -liberty -lz
+      EXTLIBS += -lbfd -lopcodes -liberty -lz
+      FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -lz -ldl
     endif
   endif
+  $(call feature_check,disassembler-four-args)
 endif
 
 ifdef NO_DEMANGLE
@@ -808,6 +813,10 @@ ifdef HAVE_KVM_STAT_SUPPORT
     CFLAGS += -DHAVE_KVM_STAT_SUPPORT
 endif
 
+ifeq ($(feature-disassembler-four-args), 1)
+    CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE
+endif
+
 ifeq (${IS_64_BIT}, 1)
   ifndef NO_PERF_READ_VDSO32
     $(call feature_check,compile-32)

tools/perf/bench/epoll-ctl.c

@@ -224,7 +224,7 @@ static int do_threads(struct worker *worker, struct cpu_map *cpu)
 	pthread_attr_t thread_attr, *attrp = NULL;
 	cpu_set_t cpuset;
 	unsigned int i, j;
-	int ret;
+	int ret = 0;
 
 	if (!noaffinity)
 		pthread_attr_init(&thread_attr);

tools/perf/bench/epoll-wait.c

@@ -293,7 +293,7 @@ static int do_threads(struct worker *worker, struct cpu_map *cpu)
 	pthread_attr_t thread_attr, *attrp = NULL;
 	cpu_set_t cpuset;
 	unsigned int i, j;
-	int ret, events = EPOLLIN;
+	int ret = 0, events = EPOLLIN;
 
 	if (oneshot)
 		events |= EPOLLONESHOT;

tools/perf/builtin-list.c

@@ -119,7 +119,7 @@ int cmd_list(int argc, const char **argv)
 						details_flag);
 			print_tracepoint_events(NULL, s, raw_dump);
 			print_sdt_events(NULL, s, raw_dump);
-			metricgroup__print(true, true, NULL, raw_dump, details_flag);
+			metricgroup__print(true, true, s, raw_dump, details_flag);
 			free(s);
 		}
 	}

tools/perf/builtin-record.c

@@ -62,6 +62,9 @@ struct switch_output {
 	unsigned long	 time;
 	const char	*str;
 	bool		 set;
+	char		 **filenames;
+	int		 num_files;
+	int		 cur_file;
 };
 
 struct record {
@@ -892,6 +895,7 @@ record__switch_output(struct record *rec, bool at_exit)
 {
 	struct perf_data *data = &rec->data;
 	int fd, err;
+	char *new_filename;
 
 	/* Same Size:      "2015122520103046"*/
 	char timestamp[] = "InvalidTimestamp";
@@ -912,7 +916,7 @@ record__switch_output(struct record *rec, bool at_exit)
 
 	fd = perf_data__switch(data, timestamp,
 				    rec->session->header.data_offset,
-				    at_exit);
+				    at_exit, &new_filename);
 	if (fd >= 0 && !at_exit) {
 		rec->bytes_written = 0;
 		rec->session->header.data_size = 0;
@@ -922,6 +926,21 @@ record__switch_output(struct record *rec, bool at_exit)
 		fprintf(stderr, "[ perf record: Dump %s.%s ]\n",
 			data->path, timestamp);
 
+	if (rec->switch_output.num_files) {
+		int n = rec->switch_output.cur_file + 1;
+
+		if (n >= rec->switch_output.num_files)
+			n = 0;
+		rec->switch_output.cur_file = n;
+		if (rec->switch_output.filenames[n]) {
+			remove(rec->switch_output.filenames[n]);
+			free(rec->switch_output.filenames[n]);
+		}
+		rec->switch_output.filenames[n] = new_filename;
+	} else {
+		free(new_filename);
+	}
+
 	/* Output tracking events */
 	if (!at_exit) {
 		record__synthesize(rec, false);
@@ -1095,7 +1114,7 @@ static int record__synthesize(struct record *rec, bool tail)
 		return err;
 	}
 
-	err = perf_event__synthesize_bpf_events(tool, process_synthesized_event,
+	err = perf_event__synthesize_bpf_events(session, process_synthesized_event,
 						machine, opts);
 	if (err < 0)
 		pr_warning("Couldn't synthesize bpf events.\n");
@@ -1118,6 +1137,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	struct perf_data *data = &rec->data;
 	struct perf_session *session;
 	bool disabled = false, draining = false;
+	struct perf_evlist *sb_evlist = NULL;
 	int fd;
 
 	atexit(record__sig_exit);
@@ -1218,6 +1238,14 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		goto out_child;
 	}
 
+	if (!opts->no_bpf_event)
+		bpf_event__add_sb_event(&sb_evlist, &session->header.env);
+
+	if (perf_evlist__start_sb_thread(sb_evlist, &rec->opts.target)) {
+		pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n");
+		opts->no_bpf_event = true;
+	}
+
 	err = record__synthesize(rec, false);
 	if (err < 0)
 		goto out_child;
@@ -1468,6 +1496,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
 out_delete_session:
 	perf_session__delete(session);
+
+	if (!opts->no_bpf_event)
+		perf_evlist__stop_sb_thread(sb_evlist);
 	return status;
 }
 
@@ -1872,7 +1903,7 @@ static struct option __record_options[] = {
 	OPT_BOOLEAN(0, "tail-synthesize", &record.opts.tail_synthesize,
 		    "synthesize non-sample events at the end of output"),
 	OPT_BOOLEAN(0, "overwrite", &record.opts.overwrite, "use overwrite mode"),
-	OPT_BOOLEAN(0, "bpf-event", &record.opts.bpf_event, "record bpf events"),
+	OPT_BOOLEAN(0, "no-bpf-event", &record.opts.no_bpf_event, "record bpf events"),
 	OPT_BOOLEAN(0, "strict-freq", &record.opts.strict_freq,
 		    "Fail if the specified frequency can't be used"),
 	OPT_CALLBACK('F', "freq", &record.opts, "freq or 'max'",
@@ -1970,9 +2001,11 @@ static struct option __record_options[] = {
 	OPT_BOOLEAN(0, "timestamp-boundary", &record.timestamp_boundary,
 		    "Record timestamp boundary (time of first/last samples)"),
 	OPT_STRING_OPTARG_SET(0, "switch-output", &record.switch_output.str,
-			  &record.switch_output.set, "signal,size,time",
-			  "Switch output when receive SIGUSR2 or cross size,time threshold",
+			  &record.switch_output.set, "signal or size[BKMG] or time[smhd]",
+			  "Switch output when receiving SIGUSR2 (signal) or cross a size or time threshold",
 			  "signal"),
+	OPT_INTEGER(0, "switch-max-files", &record.switch_output.num_files,
+		   "Limit number of switch output generated files"),
 	OPT_BOOLEAN(0, "dry-run", &dry_run,
 		    "Parse options then exit"),
 #ifdef HAVE_AIO_SUPPORT
@@ -2059,6 +2092,13 @@ int cmd_record(int argc, const char **argv)
 		alarm(rec->switch_output.time);
 	}
 
+	if (rec->switch_output.num_files) {
+		rec->switch_output.filenames = calloc(sizeof(char *),
+						      rec->switch_output.num_files);
+		if (!rec->switch_output.filenames)
+			return -EINVAL;
+	}
+
 	/*
 	 * Allow aliases to facilitate the lookup of symbols for address
 	 * filters. Refer to auxtrace_parse_filters().

tools/perf/builtin-report.c

@@ -1083,10 +1083,9 @@ int cmd_report(int argc, const char **argv)
 	OPT_BOOLEAN(0, "header-only", &report.header_only,
 		    "Show only data header."),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
-		   "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline, ..."
-		   " Please refer the man page for the complete list."),
+		   sort_help("sort by key(s):")),
 	OPT_STRING('F', "fields", &field_order, "key[,keys...]",
-		   "output field(s): overhead, period, sample plus all of sort keys"),
+		   sort_help("output field(s): overhead period sample ")),
 	OPT_BOOLEAN(0, "show-cpu-utilization", &symbol_conf.show_cpu_utilization,
 		    "Show sample percentage for different cpu modes"),
 	OPT_BOOLEAN_FLAG(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,

tools/perf/builtin-script.c

@@ -53,6 +53,8 @@
 
 static char const		*script_name;
 static char const		*generate_script_lang;
+static bool			reltime;
+static u64			initial_time;
 static bool			debug_mode;
 static u64			last_timestamp;
 static u64			nr_unordered;
@@ -686,7 +688,13 @@ static int perf_sample__fprintf_start(struct perf_sample *sample,
 	}
 
 	if (PRINT_FIELD(TIME)) {
-		nsecs = sample->time;
+		u64 t = sample->time;
+		if (reltime) {
+			if (!initial_time)
+				initial_time = sample->time;
+			t = sample->time - initial_time;
+		}
+		nsecs = t;
 		secs = nsecs / NSEC_PER_SEC;
 		nsecs -= secs * NSEC_PER_SEC;
 
@@ -694,7 +702,7 @@ static int perf_sample__fprintf_start(struct perf_sample *sample,
 			printed += fprintf(fp, "%5lu.%09llu: ", secs, nsecs);
 		else {
 			char sample_time[32];
-			timestamp__scnprintf_usec(sample->time, sample_time, sizeof(sample_time));
+			timestamp__scnprintf_usec(t, sample_time, sizeof(sample_time));
 			printed += fprintf(fp, "%12s: ", sample_time);
 		}
 	}
@@ -3413,6 +3421,7 @@ int cmd_script(int argc, const char **argv)
 		     "Set the maximum stack depth when parsing the callchain, "
 		     "anything beyond the specified depth will be ignored. "
 		     "Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)),
+	OPT_BOOLEAN(0, "reltime", &reltime, "Show time stamps relative to start"),
 	OPT_BOOLEAN('I', "show-info", &show_full_info,
 		    "display extended information from perf.data file"),
 	OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path,
@@ -3487,6 +3496,11 @@ int cmd_script(int argc, const char **argv)
 		}
 	}
 
+	if (script.time_str && reltime) {
+		fprintf(stderr, "Don't combine --reltime with --time\n");
+		return -1;
+	}
+
 	if (itrace_synth_opts.callchain &&
 	    itrace_synth_opts.callchain_sz > scripting_max_stack)
 		scripting_max_stack = itrace_synth_opts.callchain_sz;

tools/perf/builtin-stat.c

@@ -718,7 +718,8 @@ static struct option stat_options[] = {
 		    "system-wide collection from all CPUs"),
 	OPT_BOOLEAN('g', "group", &group,
 		    "put the counters into a counter group"),
-	OPT_BOOLEAN('c', "scale", &stat_config.scale, "scale/normalize counters"),
+	OPT_BOOLEAN(0, "scale", &stat_config.scale,
+		    "Use --no-scale to disable counter scaling for multiplexing"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
 	OPT_INTEGER('r', "repeat", &stat_config.run_count,

tools/perf/builtin-top.c

@@ -1189,30 +1189,26 @@ static int __cmd_top(struct perf_top *top)
 	pthread_t thread, thread_process;
 	int ret;
 
-	top->session = perf_session__new(NULL, false, NULL);
-	if (top->session == NULL)
-		return -1;
-
 	if (!top->annotation_opts.objdump_path) {
 		ret = perf_env__lookup_objdump(&top->session->header.env,
 					       &top->annotation_opts.objdump_path);
 		if (ret)
-			goto out_delete;
+			return ret;
 	}
 
 	ret = callchain_param__setup_sample_type(&callchain_param);
 	if (ret)
-		goto out_delete;
+		return ret;
 
 	if (perf_session__register_idle_thread(top->session) < 0)
-		goto out_delete;
+		return ret;
 
 	if (top->nr_threads_synthesize > 1)
 		perf_set_multithreaded();
 
 	init_process_thread(top);
 
-	ret = perf_event__synthesize_bpf_events(&top->tool, perf_event__process,
+	ret = perf_event__synthesize_bpf_events(top->session, perf_event__process,
 						&top->session->machines.host,
 						&top->record_opts);
 	if (ret < 0)
@@ -1227,13 +1223,18 @@ static int __cmd_top(struct perf_top *top)
 
 	if (perf_hpp_list.socket) {
 		ret = perf_env__read_cpu_topology_map(&perf_env);
-		if (ret < 0)
-			goto out_err_cpu_topo;
+		if (ret < 0) {
+			char errbuf[BUFSIZ];
+			const char *err = str_error_r(-ret, errbuf, sizeof(errbuf));
+
+			ui__error("Could not read the CPU topology map: %s\n", err);
+			return ret;
+		}
 	}
 
 	ret = perf_top__start_counters(top);
 	if (ret)
-		goto out_delete;
+		return ret;
 
 	top->session->evlist = top->evlist;
 	perf_session__set_id_hdr_size(top->session);
@@ -1252,7 +1253,7 @@ static int __cmd_top(struct perf_top *top)
 	ret = -1;
 	if (pthread_create(&thread_process, NULL, process_thread, top)) {
 		ui__error("Could not create process thread.\n");
-		goto out_delete;
+		return ret;
 	}
 
 	if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui :
@@ -1296,19 +1297,7 @@ static int __cmd_top(struct perf_top *top)
 out_join_thread:
 	pthread_cond_signal(&top->qe.cond);
 	pthread_join(thread_process, NULL);
-out_delete:
-	perf_session__delete(top->session);
-	top->session = NULL;
-
 	return ret;
-
-out_err_cpu_topo: {
-	char errbuf[BUFSIZ];
-	const char *err = str_error_r(-ret, errbuf, sizeof(errbuf));
-
-	ui__error("Could not read the CPU topology map: %s\n", err);
-	goto out_delete;
-}
 }
 
 static int
@@ -1480,6 +1469,7 @@ int cmd_top(int argc, const char **argv)
 		    "Display raw encoding of assembly instructions (default)"),
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
 		    "Enable kernel symbol demangling"),
+	OPT_BOOLEAN(0, "no-bpf-event", &top.record_opts.no_bpf_event, "do not record bpf events"),
 	OPT_STRING(0, "objdump", &top.annotation_opts.objdump_path, "path",
 		    "objdump binary to use for disassembly and annotations"),
 	OPT_STRING('M', "disassembler-style", &top.annotation_opts.disassembler_style, "disassembler style",
@@ -1511,6 +1501,7 @@ int cmd_top(int argc, const char **argv)
 			"number of thread to run event synthesize"),
 	OPT_END()
 	};
+	struct perf_evlist *sb_evlist = NULL;
 	const char * const top_usage[] = {
 		"perf top [<options>]",
 		NULL
@@ -1628,8 +1619,9 @@ int cmd_top(int argc, const char **argv)
 	annotation_config__init();
 
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
-	if (symbol__init(NULL) < 0)
-		return -1;
+	status = symbol__init(NULL);
+	if (status < 0)
+		goto out_delete_evlist;
 
 	sort__setup_elide(stdout);
 
@@ -1639,10 +1631,28 @@ int cmd_top(int argc, const char **argv)
 		signal(SIGWINCH, winch_sig);
 	}
 
+	top.session = perf_session__new(NULL, false, NULL);
+	if (top.session == NULL) {
+		status = -1;
+		goto out_delete_evlist;
+	}
+
+	if (!top.record_opts.no_bpf_event)
+		bpf_event__add_sb_event(&sb_evlist, &perf_env);
+
+	if (perf_evlist__start_sb_thread(sb_evlist, target)) {
+		pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n");
+		opts->no_bpf_event = true;
+	}
+
 	status = __cmd_top(&top);
 
+	if (!opts->no_bpf_event)
+		perf_evlist__stop_sb_thread(sb_evlist);
+
 out_delete_evlist:
 	perf_evlist__delete(top.evlist);
+	perf_session__delete(top.session);
 
 	return status;
 }

tools/perf/perf.c

@@ -298,6 +298,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 		use_pager = 1;
 	commit_pager_choice();
 
+	perf_env__init(&perf_env);
 	perf_env__set_cmdline(&perf_env, argc, argv);
 	status = p->fn(argc, argv);
 	perf_config__exit();

tools/perf/perf.h

@@ -66,7 +66,7 @@ struct record_opts {
 	bool	     ignore_missing_thread;
 	bool	     strict_freq;
 	bool	     sample_id;
-	bool	     bpf_event;
+	bool	     no_bpf_event;
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int auxtrace_mmap_pages;

tools/perf/tests/attr/test-record-C0

 [config]
 command = record
-args    = -C 0 kill >/dev/null 2>&1
+args    = --no-bpf-event -C 0 kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/attr/test-record-basic

 [config]
 command = record
-args    = kill >/dev/null 2>&1
+args    = --no-bpf-event kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/attr/test-record-branch-any

 [config]
 command = record
-args    = -b kill >/dev/null 2>&1
+args    = --no-bpf-event -b kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/attr/test-record-branch-filter-any

 [config]
 command = record
-args    = -j any kill >/dev/null 2>&1
+args    = --no-bpf-event -j any kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/attr/test-record-branch-filter-any_call

 [config]
 command = record
-args    = -j any_call kill >/dev/null 2>&1
+args    = --no-bpf-event -j any_call kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/attr/test-record-branch-filter-any_ret

 [config]
 command = record
-args    = -j any_ret kill >/dev/null 2>&1
+args    = --no-bpf-event -j any_ret kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/attr/test-record-branch-filter-hv

 [config]
 command = record
-args    = -j hv kill >/dev/null 2>&1
+args    = --no-bpf-event -j hv kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/attr/test-record-branch-filter-ind_call

 [config]
 command = record
-args    = -j ind_call kill >/dev/null 2>&1
+args    = --no-bpf-event -j ind_call kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/attr/test-record-branch-filter-k

 [config]
 command = record
-args    = -j k kill >/dev/null 2>&1
+args    = --no-bpf-event -j k kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/attr/test-record-branch-filter-u

 [config]
 command = record
-args    = -j u kill >/dev/null 2>&1
+args    = --no-bpf-event -j u kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/attr/test-record-count

 [config]
 command = record
-args    = -c 123 kill >/dev/null 2>&1
+args    = --no-bpf-event -c 123 kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/attr/test-record-data

 [config]
 command = record
-args    = -d kill >/dev/null 2>&1
+args    = --no-bpf-event -d kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/attr/test-record-freq

 [config]
 command = record
-args    = -F 100 kill >/dev/null 2>&1
+args    = --no-bpf-event -F 100 kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/attr/test-record-graph-default

 [config]
 command = record
-args    = -g kill >/dev/null 2>&1
+args    = --no-bpf-event -g kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/attr/test-record-graph-dwarf

 [config]
 command = record
-args    = --call-graph dwarf -- kill >/dev/null 2>&1
+args    = --no-bpf-event --call-graph dwarf -- kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/attr/test-record-graph-fp

 [config]
 command = record
-args    = --call-graph fp kill >/dev/null 2>&1
+args    = --no-bpf-event --call-graph fp kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/attr/test-record-group

 [config]
 command = record
-args    = --group -e cycles,instructions kill >/dev/null 2>&1
+args    = --no-bpf-event --group -e cycles,instructions kill >/dev/null 2>&1
 ret     = 1
 
 [event-1:base-record]

tools/perf/tests/attr/test-record-group-sampling

 [config]
 command = record
-args    = -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
+args    = --no-bpf-event -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
 ret     = 1
 
 [event-1:base-record]

tools/perf/tests/attr/test-record-group1

 [config]
 command = record
-args    = -e '{cycles,instructions}' kill >/dev/null 2>&1
+args    = --no-bpf-event -e '{cycles,instructions}' kill >/dev/null 2>&1
 ret     = 1
 
 [event-1:base-record]

tools/perf/tests/attr/test-record-no-buffering

 [config]
 command = record
-args    = --no-buffering kill >/dev/null 2>&1
+args    = --no-bpf-event --no-buffering kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/attr/test-record-no-inherit

 [config]
 command = record
-args    = -i kill >/dev/null 2>&1
+args    = --no-bpf-event -i kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/attr/test-record-no-samples

 [config]
 command = record
-args    = -n kill >/dev/null 2>&1
+args    = --no-bpf-event -n kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/attr/test-record-period

 [config]
 command = record
-args    = -c 100 -P kill >/dev/null 2>&1
+args    = --no-bpf-event -c 100 -P kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/attr/test-record-raw

 [config]
 command = record
-args    = -R kill >/dev/null 2>&1
+args    = --no-bpf-event -R kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-record]

tools/perf/tests/backward-ring-buffer.c

@@ -18,7 +18,7 @@ static void testcase(void)
 	int i;
 
 	for (i = 0; i < NR_ITERS; i++) {
-		char proc_name[10];
+		char proc_name[15];
 
 		snprintf(proc_name, sizeof(proc_name), "p:%d\n", i);
 		prctl(PR_SET_NAME, proc_name);

tools/perf/tests/evsel-tp-sched.c

@@ -85,5 +85,6 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes
 	if (perf_evsel__test_field(evsel, "target_cpu", 4, true))
 		ret = -1;
 
+	perf_evsel__delete(evsel);
 	return ret;
 }

tools/perf/tests/expr.c

@@ -19,7 +19,7 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused)
 	const char *p;
 	const char **other;
 	double val;
-	int ret;
+	int i, ret;
 	struct parse_ctx ctx;
 	int num_other;
 
@@ -56,6 +56,9 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused)
 	TEST_ASSERT_VAL("find other", !strcmp(other[1], "BAZ"));
 	TEST_ASSERT_VAL("find other", !strcmp(other[2], "BOZO"));
 	TEST_ASSERT_VAL("find other", other[3] == NULL);
+
+	for (i = 0; i < num_other; i++)
+		free((void *)other[i]);
 	free((void *)other);
 
 	return 0;

tools/perf/tests/openat-syscall-all-cpus.c

@@ -45,7 +45,7 @@ int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int
 	if (IS_ERR(evsel)) {
 		tracing_path__strerror_open_tp(errno, errbuf, sizeof(errbuf), "syscalls", "sys_enter_openat");
 		pr_debug("%s\n", errbuf);
-		goto out_thread_map_delete;
+		goto out_cpu_map_delete;
 	}
 
 	if (perf_evsel__open(evsel, cpus, threads) < 0) {
@@ -119,6 +119,8 @@ int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int
 	perf_evsel__close_fd(evsel);
 out_evsel_delete:
 	perf_evsel__delete(evsel);
+out_cpu_map_delete:
+	cpu_map__put(cpus);
 out_thread_map_delete:
 	thread_map__put(threads);
 	return err;

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 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
 	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;

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,
 };

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

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;

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,

tools/perf/util/data.c

@@ -361,9 +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))
@@ -371,15 +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);
@@ -396,7 +396,6 @@ int perf_data__switch(struct perf_data *data,
 	}
 	ret = data->file.fd;
 out:
-	free(new_filepath);
 	return ret;
 }
 

tools/perf/util/data.h

@@ -70,7 +70,7 @@ 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);

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)

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;

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;

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 */

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>
 
@@ -1856,3 +1857,121 @@ 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);
+}

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);
 

tools/perf/util/evsel.c

@@ -1036,7 +1036,7 @@ 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)
@@ -1292,6 +1292,7 @@ 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 +1343,9 @@ 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;

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 {

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"
 
@@ -876,6 +878,89 @@ static int write_dir_format(struct feat_fd *ff,
 	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;
@@ -1367,6 +1452,52 @@ static void print_dir_format(struct feat_fd *ff, FILE *fp)
 	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;
@@ -2414,6 +2545,124 @@ static int process_dir_format(struct feat_fd *ff,
 	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);
@@ -2474,7 +2723,9 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPR(SAMPLE_TIME,	sample_time,	false),
 	FEAT_OPR(MEM_TOPOLOGY,	mem_topology,	true),
 	FEAT_OPR(CLOCKID,	clockid,	false),
-	FEAT_OPN(DIR_FORMAT,	dir_format,	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 {

tools/perf/util/header.h

@@ -40,6 +40,8 @@ enum {
 	HEADER_MEM_TOPOLOGY,
 	HEADER_CLOCKID,
 	HEADER_DIR_FORMAT,
+	HEADER_BPF_PROG_INFO,
+	HEADER_BPF_BTF,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };

tools/perf/util/hist.c

@@ -1111,8 +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)

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)

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;

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) {

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;

tools/perf/util/sort.c

@@ -13,6 +13,7 @@
 #include "evsel.h"
 #include "evlist.h"
 #include "strlist.h"
+#include "strbuf.h"
 #include <traceevent/event-parse.h>
 #include "mem-events.h"
 #include "annotate.h"
@@ -3107,3 +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;
+}

tools/perf/util/sort.h

@@ -296,6 +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);

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

tools/perf/util/symbol.c

@@ -1455,6 +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;