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

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

  * kcore annotation improvements, including build-id cache support,
    multi map 'call' instruction navigation fixes, kcore address
    validation, objdump workarounds. From Adrian Hunter.

  * 'trace' beautifiers for lots of syscall arguments, from Arnaldo Carvalho de Melo.

  * More compact 'trace' output by suppressing zeroed args, from Arnaldo Carvalho de Melo.

  * Show thread COMM by default in 'trace', from Arnaldo Carvalho de Melo.

  * Show path associated with fd in live sessions, using a 'vfs_getname'
    'perf probe' created dynamic tracepoint or by looking at /proc/pid/fd, from Arnaldo Carvalho de Melo.

  * Memory and mmap leak fixes from Chenggang Qin.

  * Add option to show full timestamp in 'trace', from David Ahern.

  * Add 'record' command in 'trace', to record raw_syscalls:*, from David Ahern.

  * Add summary option to dump syscall statistics in 'trace', from David Ahern.

  * Fix comm resolution in 'trace' when reading events from file, from David Ahern.

  * Improved messages when doing profiling in all or a subset of CPUs
    using a workload as the session delimitator, as in:

     'perf stat --cpu 0,2 sleep 10s'

    from Arnaldo Carvalho de Melo.

  * Add units to nanosec-based counters in 'perf stat', from David Ahern.

  * Assorted build fixes for from David Ahern and Jiri Olsa.

  * 'perf lock' fixes and cleanups, from Davidlohr Bueso.

  * Memory leak fixes in 'perf test', from Felipe Pena.

  * Build system super speedups, from Ingo Molnar.

  * Fix mmap_read event overflow, from Jiri Olsa.

  * Code cleanups from Jiri Olsa.

  * Allow specifying B/K/M/G unit to the --mmap-pages arguments, from Jiri Olsa.

  * Separate the GTK support in a separate libperf-gtk.so DSO, that is
    only loaded when --gtk is specified, from Namhyung Kim.

  * Fixes for some memory leaks, from Namhyumg Kim.

  * Fix srcline sort key behavior, from Namhyung Kim.

  * Fix failing assertions in numa bench, from Petr Holasek.

  * perf bash completion fixes and improvements from Ramkumar Ramachandra.

  * Improve error messages in 'trace', providing hints about system configuration
    steps needed for using it, from Ramkumar Ramachandra.

  * Remove bogus info when using 'perf stat' -e cycles/instructions, from
    Ramkumar Ramachandra.

  * Support for Openembedded/Yocto -dbg packages, from Ricardo Ribalda Delgado.

  * Implement addr2line directly using libbfd, from Roberto Vitillo.

  * Add new option --ignore-vmlinux for perf top, from Willy Tarreau.

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

41 files changed, 1789 insertions, 395 deletions

diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index 15a77b7c0e36..ce7a804b2951 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -40,7 +40,7 @@ else
 	VC=unset
 fi
 test "$VN" = "$VC" || {
-	echo >&2 "PERF_VERSION = $VN"
+	echo >&2 "  PERF_VERSION = $VN"
 	echo "#define PERF_VERSION \"$VN\"" >$GVF
 }
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 7eae5488ecea..cf6242c92ee2 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -825,20 +825,16 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 		dl->ops.target.offset = dl->ops.target.addr -
 					map__rip_2objdump(map, sym->start);
 
-	/*
-	 * kcore has no symbols, so add the call target name if it is on the
-	 * same map.
-	 */
+	/* kcore has no symbols, so add the call target name */
 	if (dl->ins && ins__is_call(dl->ins) && !dl->ops.target.name) {
-		struct symbol *s;
-		u64 ip = dl->ops.target.addr;
-
-		if (ip >= map->start && ip <= map->end) {
-			ip = map->map_ip(map, ip);
-			s = map__find_symbol(map, ip, NULL);
-			if (s && s->start == ip)
-				dl->ops.target.name = strdup(s->name);
-		}
+		struct addr_map_symbol target = {
+			.map = map,
+			.addr = dl->ops.target.addr,
+		};
+
+		if (!map_groups__find_ams(&target, NULL) &&
+		    target.sym->start == target.al_addr)
+			dl->ops.target.name = strdup(target.sym->name);
 	}
 
 	disasm__add(&notes->src->source, dl);
@@ -879,6 +875,8 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
 	FILE *file;
 	int err = 0;
 	char symfs_filename[PATH_MAX];
+	struct kcore_extract kce;
+	bool delete_extract = false;
 
 	if (filename) {
 		snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
@@ -940,6 +938,23 @@ fallback:
 	pr_debug("annotating [%p] %30s : [%p] %30s\n",
 		 dso, dso->long_name, sym, sym->name);
 
+	if (dso__is_kcore(dso)) {
+		kce.kcore_filename = symfs_filename;
+		kce.addr = map__rip_2objdump(map, sym->start);
+		kce.offs = sym->start;
+		kce.len = sym->end + 1 - sym->start;
+		if (!kcore_extract__create(&kce)) {
+			delete_extract = true;
+			strlcpy(symfs_filename, kce.extract_filename,
+				sizeof(symfs_filename));
+			if (free_filename) {
+				free(filename);
+				free_filename = false;
+			}
+			filename = symfs_filename;
+		}
+	}
+
 	snprintf(command, sizeof(command),
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
@@ -972,6 +987,8 @@ fallback:
 
 	pclose(file);
 out_free_filename:
+	if (delete_extract)
+		kcore_extract__delete(&kce);
 	if (free_filename)
 		free(filename);
 	return err;
@@ -1070,7 +1087,7 @@ static void symbol__free_source_line(struct symbol *sym, int len)
 			  (sizeof(src_line->p) * (src_line->nr_pcnt - 1));
 
 	for (i = 0; i < len; i++) {
-		free(src_line->path);
+		free_srcline(src_line->path);
 		src_line = (void *)src_line + sizeof_src_line;
 	}
 
@@ -1081,13 +1098,11 @@ static void symbol__free_source_line(struct symbol *sym, int len)
 /* Get the filename:line for the colored entries */
 static int symbol__get_source_line(struct symbol *sym, struct map *map,
 				   struct perf_evsel *evsel,
-				   struct rb_root *root, int len,
-				   const char *filename)
+				   struct rb_root *root, int len)
 {
 	u64 start;
 	int i, k;
 	int evidx = evsel->idx;
-	char cmd[PATH_MAX * 2];
 	struct source_line *src_line;
 	struct annotation *notes = symbol__annotation(sym);
 	struct sym_hist *h = annotation__histogram(notes, evidx);
@@ -1115,10 +1130,7 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
 	start = map__rip_2objdump(map, sym->start);
 
 	for (i = 0; i < len; i++) {
-		char *path = NULL;
-		size_t line_len;
 		u64 offset;
-		FILE *fp;
 		double percent_max = 0.0;
 
 		src_line->nr_pcnt = nr_pcnt;
@@ -1135,23 +1147,9 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
 			goto next;
 
 		offset = start + i;
-		sprintf(cmd, "addr2line -e %s %016" PRIx64, filename, offset);
-		fp = popen(cmd, "r");
-		if (!fp)
-			goto next;
-
-		if (getline(&path, &line_len, fp) < 0 || !line_len)
-			goto next_close;
-
-		src_line->path = malloc(sizeof(char) * line_len + 1);
-		if (!src_line->path)
-			goto next_close;
-
-		strcpy(src_line->path, path);
+		src_line->path = get_srcline(map->dso, offset);
 		insert_source_line(&tmp_root, src_line);
 
-	next_close:
-		pclose(fp);
 	next:
 		src_line = (void *)src_line + sizeof_src_line;
 	}
@@ -1192,7 +1190,7 @@ static void print_summary(struct rb_root *root, const char *filename)
 
 		path = src_line->path;
 		color = get_percent_color(percent_max);
-		color_fprintf(stdout, color, " %s", path);
+		color_fprintf(stdout, color, " %s\n", path);
 
 		node = rb_next(node);
 	}
@@ -1356,7 +1354,6 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map,
 			 bool full_paths, int min_pcnt, int max_lines)
 {
 	struct dso *dso = map->dso;
-	const char *filename = dso->long_name;
 	struct rb_root source_line = RB_ROOT;
 	u64 len;
 
@@ -1366,9 +1363,8 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map,
 	len = symbol__size(sym);
 
 	if (print_lines) {
-		symbol__get_source_line(sym, map, evsel, &source_line,
-					len, filename);
-		print_summary(&source_line, filename);
+		symbol__get_source_line(sym, map, evsel, &source_line, len);
+		print_summary(&source_line, dso->long_name);
 	}
 
 	symbol__annotate_printf(sym, map, evsel, full_paths,
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index af755156d278..834b7b57b788 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -150,7 +150,7 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map,
 			 struct perf_evsel *evsel, bool print_lines,
 			 bool full_paths, int min_pcnt, int max_lines);
 
-#ifdef SLANG_SUPPORT
+#ifdef HAVE_SLANG_SUPPORT
 int symbol__tui_annotate(struct symbol *sym, struct map *map,
 			 struct perf_evsel *evsel,
 			 struct hist_browser_timer *hbt);
@@ -165,30 +165,6 @@ static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused,
 }
 #endif
 
-#ifdef GTK2_SUPPORT
-int symbol__gtk_annotate(struct symbol *sym, struct map *map,
-			 struct perf_evsel *evsel,
-			 struct hist_browser_timer *hbt);
-
-static inline int hist_entry__gtk_annotate(struct hist_entry *he,
-					   struct perf_evsel *evsel,
-					   struct hist_browser_timer *hbt)
-{
-	return symbol__gtk_annotate(he->ms.sym, he->ms.map, evsel, hbt);
-}
-
-void perf_gtk__show_annotations(void);
-#else
-static inline int hist_entry__gtk_annotate(struct hist_entry *he __maybe_unused,
-				struct perf_evsel *evsel __maybe_unused,
-				struct hist_browser_timer *hbt __maybe_unused)
-{
-	return 0;
-}
-
-static inline void perf_gtk__show_annotations(void) {}
-#endif
-
 extern const char	*disassembler_style;
 
 #endif	/* __PERF_ANNOTATE_H */
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 26e367239873..7b176dd02e1a 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -70,8 +70,7 @@ extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2
 extern char *perf_pathdup(const char *fmt, ...)
 	__attribute__((format (printf, 1, 2)));
 
-#ifndef HAVE_STRLCPY
+/* Matches the libc/libbsd function attribute so we declare this unconditionally: */
 extern size_t strlcpy(char *dest, const char *src, size_t size);
-#endif
 
 #endif /* __PERF_CACHE_H */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index e3c1ff8512c8..af4c687cc49b 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -7,19 +7,20 @@
 char dso__symtab_origin(const struct dso *dso)
 {
 	static const char origin[] = {
-		[DSO_BINARY_TYPE__KALLSYMS]		= 'k',
-		[DSO_BINARY_TYPE__VMLINUX]		= 'v',
-		[DSO_BINARY_TYPE__JAVA_JIT]		= 'j',
-		[DSO_BINARY_TYPE__DEBUGLINK]		= 'l',
-		[DSO_BINARY_TYPE__BUILD_ID_CACHE]	= 'B',
-		[DSO_BINARY_TYPE__FEDORA_DEBUGINFO]	= 'f',
-		[DSO_BINARY_TYPE__UBUNTU_DEBUGINFO]	= 'u',
-		[DSO_BINARY_TYPE__BUILDID_DEBUGINFO]	= 'b',
-		[DSO_BINARY_TYPE__SYSTEM_PATH_DSO]	= 'd',
-		[DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE]	= 'K',
-		[DSO_BINARY_TYPE__GUEST_KALLSYMS]	= 'g',
-		[DSO_BINARY_TYPE__GUEST_KMODULE]	= 'G',
-		[DSO_BINARY_TYPE__GUEST_VMLINUX]	= 'V',
+		[DSO_BINARY_TYPE__KALLSYMS]			= 'k',
+		[DSO_BINARY_TYPE__VMLINUX]			= 'v',
+		[DSO_BINARY_TYPE__JAVA_JIT]			= 'j',
+		[DSO_BINARY_TYPE__DEBUGLINK]			= 'l',
+		[DSO_BINARY_TYPE__BUILD_ID_CACHE]		= 'B',
+		[DSO_BINARY_TYPE__FEDORA_DEBUGINFO]		= 'f',
+		[DSO_BINARY_TYPE__UBUNTU_DEBUGINFO]		= 'u',
+		[DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO]	= 'o',
+		[DSO_BINARY_TYPE__BUILDID_DEBUGINFO]		= 'b',
+		[DSO_BINARY_TYPE__SYSTEM_PATH_DSO]		= 'd',
+		[DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE]		= 'K',
+		[DSO_BINARY_TYPE__GUEST_KALLSYMS]		= 'g',
+		[DSO_BINARY_TYPE__GUEST_KMODULE]		= 'G',
+		[DSO_BINARY_TYPE__GUEST_VMLINUX]		= 'V',
 	};
 
 	if (dso == NULL || dso->symtab_type == DSO_BINARY_TYPE__NOT_FOUND)
@@ -64,6 +65,28 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
 			 symbol_conf.symfs, dso->long_name);
 		break;
 
+	case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
+	{
+		char *last_slash;
+		size_t len;
+		size_t dir_size;
+
+		last_slash = dso->long_name + dso->long_name_len;
+		while (last_slash != dso->long_name && *last_slash != '/')
+			last_slash--;
+
+		len = scnprintf(file, size, "%s", symbol_conf.symfs);
+		dir_size = last_slash - dso->long_name + 2;
+		if (dir_size > (size - len)) {
+			ret = -1;
+			break;
+		}
+		len += scnprintf(file + len, dir_size, "%s",  dso->long_name);
+		len += scnprintf(file + len , size - len, ".debug%s",
+								last_slash);
+		break;
+	}
+
 	case DSO_BINARY_TYPE__BUILDID_DEBUGINFO:
 		if (!dso->has_build_id) {
 			ret = -1;
@@ -427,6 +450,7 @@ struct dso *dso__new(const char *name)
 		dso->rel = 0;
 		dso->sorted_by_name = 0;
 		dso->has_build_id = 0;
+		dso->has_srcline = 1;
 		dso->kernel = DSO_TYPE_USER;
 		dso->needs_swap = DSO_SWAP__UNSET;
 		INIT_LIST_HEAD(&dso->node);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index b793053335d6..9ac666abbe7e 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -6,6 +6,7 @@
 #include <stdbool.h>
 #include "types.h"
 #include "map.h"
+#include "build-id.h"
 
 enum dso_binary_type {
 	DSO_BINARY_TYPE__KALLSYMS = 0,
@@ -23,6 +24,7 @@ enum dso_binary_type {
 	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
 	DSO_BINARY_TYPE__KCORE,
 	DSO_BINARY_TYPE__GUEST_KCORE,
+	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
 	DSO_BINARY_TYPE__NOT_FOUND,
 };
 
@@ -81,6 +83,7 @@ struct dso {
 	enum dso_binary_type	data_type;
 	u8		 adjust_symbols:1;
 	u8		 has_build_id:1;
+	u8		 has_srcline:1;
 	u8		 hit:1;
 	u8		 annotate_warned:1;
 	u8		 sname_alloc:1;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 17d9e167a7b9..752709ccfb00 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -61,6 +61,12 @@ struct read_event {
 	u64 id;
 };
 
+struct throttle_event {
+	struct perf_event_header header;
+	u64 time;
+	u64 id;
+	u64 stream_id;
+};
 
 #define PERF_SAMPLE_MASK				\
 	(PERF_SAMPLE_IP | PERF_SAMPLE_TID |		\
@@ -69,6 +75,9 @@ struct read_event {
 	 PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD |		\
 	 PERF_SAMPLE_IDENTIFIER)
 
+/* perf sample has 16 bits size limit */
+#define PERF_SAMPLE_MAX_SIZE (1 << 16)
+
 struct sample_event {
 	struct perf_event_header        header;
 	u64 array[];
@@ -178,6 +187,7 @@ union perf_event {
 	struct fork_event		fork;
 	struct lost_event		lost;
 	struct read_event		read;
+	struct throttle_event		throttle;
 	struct sample_event		sample;
 	struct attr_event		attr;
 	struct event_type_event		event_type;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index f9f77bee0b1b..cb9523f50a37 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -18,6 +18,7 @@
 #include <unistd.h>
 
 #include "parse-events.h"
+#include "parse-options.h"
 
 #include <sys/mman.h>
 
@@ -49,6 +50,18 @@ struct perf_evlist *perf_evlist__new(void)
 	return evlist;
 }
 
+struct perf_evlist *perf_evlist__new_default(void)
+{
+	struct perf_evlist *evlist = perf_evlist__new();
+
+	if (evlist && perf_evlist__add_default(evlist)) {
+		perf_evlist__delete(evlist);
+		evlist = NULL;
+	}
+
+	return evlist;
+}
+
 /**
  * perf_evlist__set_id_pos - set the positions of event ids.
  * @evlist: selected event list
@@ -527,7 +540,7 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 		if ((old & md->mask) + size != ((old + size) & md->mask)) {
 			unsigned int offset = old;
 			unsigned int len = min(sizeof(*event), size), cpy;
-			void *dst = &md->event_copy;
+			void *dst = md->event_copy;
 
 			do {
 				cpy = min(md->mask + 1 - (offset & md->mask), len);
@@ -537,7 +550,7 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 				len -= cpy;
 			} while (len);
 
-			event = &md->event_copy;
+			event = (union perf_event *) md->event_copy;
 		}
 
 		old += size;
@@ -672,6 +685,59 @@ out_unmap:
 	return -1;
 }
 
+static size_t perf_evlist__mmap_size(unsigned long pages)
+{
+	/* 512 kiB: default amount of unprivileged mlocked memory */
+	if (pages == UINT_MAX)
+		pages = (512 * 1024) / page_size;
+	else if (!is_power_of_2(pages))
+		return 0;
+
+	return (pages + 1) * page_size;
+}
+
+int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
+				  int unset __maybe_unused)
+{
+	unsigned int pages, val, *mmap_pages = opt->value;
+	size_t size;
+	static struct parse_tag tags[] = {
+		{ .tag  = 'B', .mult = 1       },
+		{ .tag  = 'K', .mult = 1 << 10 },
+		{ .tag  = 'M', .mult = 1 << 20 },
+		{ .tag  = 'G', .mult = 1 << 30 },
+		{ .tag  = 0 },
+	};
+
+	val = parse_tag_value(str, tags);
+	if (val != (unsigned int) -1) {
+		/* we got file size value */
+		pages = PERF_ALIGN(val, page_size) / page_size;
+		if (!is_power_of_2(pages)) {
+			pages = next_pow2(pages);
+			pr_info("rounding mmap pages size to %u (%u pages)\n",
+				pages * page_size, pages);
+		}
+	} else {
+		/* we got pages count value */
+		char *eptr;
+		pages = strtoul(str, &eptr, 10);
+		if (*eptr != '\0') {
+			pr_err("failed to parse --mmap_pages/-m value\n");
+			return -1;
+		}
+	}
+
+	size = perf_evlist__mmap_size(pages);
+	if (!size) {
+		pr_err("--mmap_pages/-m value must be a power of two.");
+		return -1;
+	}
+
+	*mmap_pages = pages;
+	return 0;
+}
+
 /** perf_evlist__mmap - Create per cpu maps to receive events
  *
  * @evlist - list of events
@@ -695,14 +761,6 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	const struct thread_map *threads = evlist->threads;
 	int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE), mask;
 
-        /* 512 kiB: default amount of unprivileged mlocked memory */
-        if (pages == UINT_MAX)
-                pages = (512 * 1024) / page_size;
-	else if (!is_power_of_2(pages))
-		return -EINVAL;
-
-	mask = pages * page_size - 1;
-
 	if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
 		return -ENOMEM;
 
@@ -710,7 +768,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 		return -ENOMEM;
 
 	evlist->overwrite = overwrite;
-	evlist->mmap_len = (pages + 1) * page_size;
+	evlist->mmap_len = perf_evlist__mmap_size(pages);
+	pr_debug("mmap size %luB\n", evlist->mmap_len);
+	mask = evlist->mmap_len - page_size - 1;
 
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 880d7139d2fb..722618f84c53 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -21,7 +21,7 @@ struct perf_mmap {
 	void		 *base;
 	int		 mask;
 	unsigned int	 prev;
-	union perf_event event_copy;
+	char		 event_copy[PERF_SAMPLE_MAX_SIZE];
 };
 
 struct perf_evlist {
@@ -31,7 +31,7 @@ struct perf_evlist {
 	int		 nr_groups;
 	int		 nr_fds;
 	int		 nr_mmaps;
-	int		 mmap_len;
+	size_t		 mmap_len;
 	int		 id_pos;
 	int		 is_pos;
 	u64		 combined_sample_type;
@@ -53,6 +53,7 @@ struct perf_evsel_str_handler {
 };
 
 struct perf_evlist *perf_evlist__new(void);
+struct perf_evlist *perf_evlist__new_default(void);
 void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
 		       struct thread_map *threads);
 void perf_evlist__exit(struct perf_evlist *evlist);
@@ -103,6 +104,10 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist,
 				  bool want_signal);
 int perf_evlist__start_workload(struct perf_evlist *evlist);
 
+int perf_evlist__parse_mmap_pages(const struct option *opt,
+				  const char *str,
+				  int unset);
+
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 		      bool overwrite);
 void perf_evlist__munmap(struct perf_evlist *evlist);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index abe69af58b62..bfebc1ea3c51 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1456,6 +1456,9 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 			array = (void *)array + sz;
 			OVERFLOW_CHECK_u64(array);
 			data->user_stack.size = *array++;
+			if (WARN_ONCE(data->user_stack.size > sz,
+				      "user stack dump failure\n"))
+				return -EFAULT;
 		}
 	}
 
diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh
index 3ac38031d534..36a885d2cd22 100755
--- a/tools/perf/util/generate-cmdlist.sh
+++ b/tools/perf/util/generate-cmdlist.sh
@@ -22,7 +22,7 @@ do
      }' "Documentation/perf-$cmd.txt"
 done
 
-echo "#ifdef LIBELF_SUPPORT"
+echo "#ifdef HAVE_LIBELF_SUPPORT"
 sed -n -e 's/^perf-\([^ 	]*\)[ 	].* full.*/\1/p' command-list.txt |
 sort |
 while read cmd
@@ -35,5 +35,5 @@ do
 	    p
      }' "Documentation/perf-$cmd.txt"
 done
-echo "#endif /* LIBELF_SUPPORT */"
+echo "#endif /* HAVE_LIBELF_SUPPORT */"
 echo "};"
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index f3278a388e9a..cca03831f41a 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -535,6 +535,7 @@ void hist_entry__free(struct hist_entry *he)
 {
 	free(he->branch_info);
 	free(he->mem_info);
+	free_srcline(he->srcline);
 	free(he);
 }
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 6a048c09cd64..20b175808cd3 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -187,7 +187,7 @@ struct hist_browser_timer {
 	int refresh;
 };
 
-#ifdef SLANG_SUPPORT
+#ifdef HAVE_SLANG_SUPPORT
 #include "../ui/keysyms.h"
 int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
 			     struct hist_browser_timer *hbt);
@@ -228,20 +228,5 @@ static inline int script_browse(const char *script_opt __maybe_unused)
 #define K_SWITCH_INPUT_DATA -3000
 #endif
 
-#ifdef GTK2_SUPPORT
-int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help,
-				  struct hist_browser_timer *hbt __maybe_unused,
-				  float min_pcnt);
-#else
-static inline
-int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __maybe_unused,
-				  const char *help __maybe_unused,
-				  struct hist_browser_timer *hbt __maybe_unused,
-				  float min_pcnt __maybe_unused)
-{
-	return 0;
-}
-#endif
-
 unsigned int hists__sort_list_width(struct hists *self);
 #endif	/* __PERF_HIST_H */
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index cf6727e99c44..8f149655f497 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -1,7 +1,7 @@
 #ifndef _PERF_DWARF_REGS_H_
 #define _PERF_DWARF_REGS_H_
 
-#ifdef DWARF_SUPPORT
+#ifdef HAVE_DWARF_SUPPORT
 const char *get_arch_regstr(unsigned int n);
 #endif
 
diff --git a/tools/perf/util/include/linux/compiler.h b/tools/perf/util/include/linux/compiler.h
index 96b919dae11c..b003ad7200b2 100644
--- a/tools/perf/util/include/linux/compiler.h
+++ b/tools/perf/util/include/linux/compiler.h
@@ -2,20 +2,29 @@
 #define _PERF_LINUX_COMPILER_H_
 
 #ifndef __always_inline
-#define __always_inline	inline
+# define __always_inline	inline __attribute__((always_inline))
 #endif
+
 #define __user
+
 #ifndef __attribute_const__
-#define __attribute_const__
+# define __attribute_const__
 #endif
 
 #ifndef __maybe_unused
-#define __maybe_unused		__attribute__((unused))
+# define __maybe_unused		__attribute__((unused))
+#endif
+
+#ifndef __packed
+# define __packed		__attribute__((__packed__))
 #endif
-#define __packed	__attribute__((__packed__))
 
 #ifndef __force
-#define __force
+# define __force
+#endif
+
+#ifndef __weak
+# define __weak			__attribute__((weak))
 #endif
 
 #endif
diff --git a/tools/perf/util/intlist.c b/tools/perf/util/intlist.c
index 11a8d86f7fea..89715b64a315 100644
--- a/tools/perf/util/intlist.c
+++ b/tools/perf/util/intlist.c
@@ -20,6 +20,7 @@ static struct rb_node *intlist__node_new(struct rblist *rblist __maybe_unused,
 
 	if (node != NULL) {
 		node->i = i;
+		node->priv = NULL;
 		rc = &node->rb_node;
 	}
 
@@ -57,22 +58,36 @@ void intlist__remove(struct intlist *ilist, struct int_node *node)
 	rblist__remove_node(&ilist->rblist, &node->rb_node);
 }
 
-struct int_node *intlist__find(struct intlist *ilist, int i)
+static struct int_node *__intlist__findnew(struct intlist *ilist,
+					   int i, bool create)
 {
-	struct int_node *node;
+	struct int_node *node = NULL;
 	struct rb_node *rb_node;
 
 	if (ilist == NULL)
 		return NULL;
 
-	node = NULL;
-	rb_node = rblist__find(&ilist->rblist, (void *)((long)i));
+	if (create)
+		rb_node = rblist__findnew(&ilist->rblist, (void *)((long)i));
+	else
+		rb_node = rblist__find(&ilist->rblist, (void *)((long)i));
+
 	if (rb_node)
 		node = container_of(rb_node, struct int_node, rb_node);
 
 	return node;
 }
 
+struct int_node *intlist__find(struct intlist *ilist, int i)
+{
+	return __intlist__findnew(ilist, i, false);
+}
+
+struct int_node *intlist__findnew(struct intlist *ilist, int i)
+{
+	return __intlist__findnew(ilist, i, true);
+}
+
 static int intlist__parse_list(struct intlist *ilist, const char *s)
 {
 	char *sep;
diff --git a/tools/perf/util/intlist.h b/tools/perf/util/intlist.h
index 62351dad848f..aa6877d36858 100644
--- a/tools/perf/util/intlist.h
+++ b/tools/perf/util/intlist.h
@@ -9,6 +9,7 @@
 struct int_node {
 	struct rb_node rb_node;
 	int i;
+	void *priv;
 };
 
 struct intlist {
@@ -23,6 +24,7 @@ int intlist__add(struct intlist *ilist, int i);
 
 struct int_node *intlist__entry(const struct intlist *ilist, unsigned int idx);
 struct int_node *intlist__find(struct intlist *ilist, int i);
+struct int_node *intlist__findnew(struct intlist *ilist, int i);
 
 static inline bool intlist__has_entry(struct intlist *ilist, int i)
 {
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 6188d2876a71..6b861aefd99a 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -46,6 +46,23 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	return 0;
 }
 
+struct machine *machine__new_host(void)
+{
+	struct machine *machine = malloc(sizeof(*machine));
+
+	if (machine != NULL) {
+		machine__init(machine, "", HOST_KERNEL_ID);
+
+		if (machine__create_kernel_maps(machine) < 0)
+			goto out_delete;
+	}
+
+	return machine;
+out_delete:
+	free(machine);
+	return NULL;
+}
+
 static void dsos__delete(struct list_head *dsos)
 {
 	struct dso *pos, *n;
@@ -776,75 +793,44 @@ static int machine__set_modules_path(struct machine *machine)
 	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path);
 }
 
-static int machine__create_modules(struct machine *machine)
+static int machine__create_module(void *arg, const char *name, u64 start)
 {
-	char *line = NULL;
-	size_t n;
-	FILE *file;
+	struct machine *machine = arg;
 	struct map *map;
+
+	map = machine__new_module(machine, start, name);
+	if (map == NULL)
+		return -1;
+
+	dso__kernel_module_get_build_id(map->dso, machine->root_dir);
+
+	return 0;
+}
+
+static int machine__create_modules(struct machine *machine)
+{
 	const char *modules;
 	char path[PATH_MAX];
 
-	if (machine__is_default_guest(machine))
+	if (machine__is_default_guest(machine)) {
 		modules = symbol_conf.default_guest_modules;
-	else {
-		sprintf(path, "%s/proc/modules", machine->root_dir);
+	} else {
+		snprintf(path, PATH_MAX, "%s/proc/modules", machine->root_dir);
 		modules = path;
 	}
 
 	if (symbol__restricted_filename(modules, "/proc/modules"))
 		return -1;
 
-	file = fopen(modules, "r");
-	if (file == NULL)
+	if (modules__parse(modules, machine, machine__create_module))
 		return -1;
 
-	while (!feof(file)) {
-		char name[PATH_MAX];
-		u64 start;
-		char *sep;
-		int line_len;
-
-		line_len = getline(&line, &n, file);
-		if (line_len < 0)
-			break;
-
-		if (!line)
-			goto out_failure;
-
-		line[--line_len] = '\0'; /* \n */
-
-		sep = strrchr(line, 'x');
-		if (sep == NULL)
-			continue;
-
-		hex2u64(sep + 1, &start);
-
-		sep = strchr(line, ' ');
-		if (sep == NULL)
-			continue;
-
-		*sep = '\0';
-
-		snprintf(name, sizeof(name), "[%s]", line);
-		map = machine__new_module(machine, start, name);
-		if (map == NULL)
-			goto out_delete_line;
-		dso__kernel_module_get_build_id(map->dso, machine->root_dir);
-	}
+	if (!machine__set_modules_path(machine))
+		return 0;
 
-	free(line);
-	fclose(file);
+	pr_debug("Problems setting modules path maps, continuing anyway...\n");
 
-	if (machine__set_modules_path(machine) < 0) {
-		pr_debug("Problems setting modules path maps, continuing anyway...\n");
-	}
 	return 0;
-
-out_delete_line:
-	free(line);
-out_failure:
-	return -1;
 }
 
 int machine__create_kernel_maps(struct machine *machine)
@@ -1376,3 +1362,26 @@ int machine__resolve_callchain(struct machine *machine,
 				   sample);
 
 }
+
+int machine__for_each_thread(struct machine *machine,
+			     int (*fn)(struct thread *thread, void *p),
+			     void *priv)
+{
+	struct rb_node *nd;
+	struct thread *thread;
+	int rc = 0;
+
+	for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
+		thread = rb_entry(nd, struct thread, rb_node);
+		rc = fn(thread, priv);
+		if (rc != 0)
+			return rc;
+	}
+
+	list_for_each_entry(thread, &machine->dead_threads, node) {
+		rc = fn(thread, priv);
+		if (rc != 0)
+			return rc;
+	}
+	return rc;
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 58a6be1fc739..d44c09bdc45e 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -74,6 +74,7 @@ char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
 void machines__set_symbol_filter(struct machines *machines,
 				 symbol_filter_t symbol_filter);
 
+struct machine *machine__new_host(void);
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
 void machine__exit(struct machine *machine);
 void machine__delete_dead_threads(struct machine *machine);
@@ -165,4 +166,8 @@ void machines__destroy_kernel_maps(struct machines *machines);
 
 size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
 
+int machine__for_each_thread(struct machine *machine,
+			     int (*fn)(struct thread *thread, void *p),
+			     void *priv);
+
 #endif /* __PERF_MACHINE_H */
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 4f6680d2043b..ef5bc913ca7a 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -172,7 +172,7 @@ int map__load(struct map *map, symbol_filter_t filter)
 		pr_warning(", continuing without symbols\n");
 		return -1;
 	} else if (nr == 0) {
-#ifdef LIBELF_SUPPORT
+#ifdef HAVE_LIBELF_SUPPORT
 		const size_t len = strlen(name);
 		const size_t real_len = len - sizeof(DSO__DELETED);
 
@@ -252,10 +252,16 @@ size_t map__fprintf_dsoname(struct map *map, FILE *fp)
 	return fprintf(fp, "%s", dsoname);
 }
 
-/*
+/**
+ * map__rip_2objdump - convert symbol start address to objdump address.
+ * @map: memory map
+ * @rip: symbol start address
+ *
  * objdump wants/reports absolute IPs for ET_EXEC, and RIPs for ET_DYN.
  * map->dso->adjust_symbols==1 for ET_EXEC-like cases except ET_REL which is
  * relative to section start.
+ *
+ * Return: Address suitable for passing to "objdump --start-address="
  */
 u64 map__rip_2objdump(struct map *map, u64 rip)
 {
@@ -268,6 +274,29 @@ u64 map__rip_2objdump(struct map *map, u64 rip)
 	return map->unmap_ip(map, rip);
 }
 
+/**
+ * map__objdump_2mem - convert objdump address to a memory address.
+ * @map: memory map
+ * @ip: objdump address
+ *
+ * Closely related to map__rip_2objdump(), this function takes an address from
+ * objdump and converts it to a memory address.  Note this assumes that @map
+ * contains the address.  To be sure the result is valid, check it forwards
+ * e.g. map__rip_2objdump(map->map_ip(map, map__objdump_2mem(map, ip))) == ip
+ *
+ * Return: Memory address.
+ */
+u64 map__objdump_2mem(struct map *map, u64 ip)
+{
+	if (!map->dso->adjust_symbols)
+		return map->unmap_ip(map, ip);
+
+	if (map->dso->rel)
+		return map->unmap_ip(map, ip + map->pgoff);
+
+	return ip;
+}
+
 void map_groups__init(struct map_groups *mg)
 {
 	int i;
@@ -371,6 +400,23 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
 	return NULL;
 }
 
+int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
+{
+	if (ams->addr < ams->map->start || ams->addr > ams->map->end) {
+		if (ams->map->groups == NULL)
+			return -1;
+		ams->map = map_groups__find(ams->map->groups, ams->map->type,
+					    ams->addr);
+		if (ams->map == NULL)
+			return -1;
+	}
+
+	ams->al_addr = ams->map->map_ip(ams->map, ams->addr);
+	ams->sym = map__find_symbol(ams->map, ams->al_addr, filter);
+
+	return ams->sym ? 0 : -1;
+}
+
 size_t __map_groups__fprintf_maps(struct map_groups *mg,
 				  enum map_type type, int verbose, FILE *fp)
 {
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 4886ca280536..e4e259c3ba16 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -84,6 +84,9 @@ static inline u64 identity__map_ip(struct map *map __maybe_unused, u64 ip)
 /* rip/ip <-> addr suitable for passing to `objdump --start-address=` */
 u64 map__rip_2objdump(struct map *map, u64 rip);
 
+/* objdump address -> memory address */
+u64 map__objdump_2mem(struct map *map, u64 ip);
+
 struct symbol;
 
 typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
@@ -167,6 +170,10 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
 					       struct map **mapp,
 					       symbol_filter_t filter);
 
+struct addr_map_symbol;
+
+int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter);
+
 static inline
 struct symbol *map_groups__find_function_by_name(struct map_groups *mg,
 						 const char *name, struct map **mapp,
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 91346b753960..343299575b30 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -126,6 +126,37 @@ modifier_bp	[rwx]{1,3}
 
 }
 
+<config>{
+config			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
+config1			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); }
+config2			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); }
+name			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NAME); }
+period			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); }
+branch_type		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); }
+,			{ return ','; }
+"/"			{ BEGIN(INITIAL); return '/'; }
+{name_minus}		{ return str(yyscanner, PE_NAME); }
+}
+
+<mem>{
+{modifier_bp}		{ return str(yyscanner, PE_MODIFIER_BP); }
+:			{ return ':'; }
+{num_dec}		{ return value(yyscanner, 10); }
+{num_hex}		{ return value(yyscanner, 16); }
+	/*
+	 * We need to separate 'mem:' scanner part, in order to get specific
+	 * modifier bits parsed out. Otherwise we would need to handle PE_NAME
+	 * and we'd need to parse it manually. During the escape from <mem>
+	 * state we need to put the escaping char back, so we dont miss it.
+	 */
+.			{ unput(*yytext); BEGIN(INITIAL); }
+	/*
+	 * We destroy the scanner after reaching EOF,
+	 * but anyway just to be sure get back to INIT state.
+	 */
+<<EOF>>			{ BEGIN(INITIAL); }
+}
+
 cpu-cycles|cycles				{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); }
 stalled-cycles-frontend|idle-cycles-frontend	{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
 stalled-cycles-backend|idle-cycles-backend	{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
@@ -162,18 +193,6 @@ speculative-read|speculative-load	|
 refs|Reference|ops|access		|
 misses|miss				{ return str(yyscanner, PE_NAME_CACHE_OP_RESULT); }
 
-<config>{
-config			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
-config1			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); }
-config2			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); }
-name			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NAME); }
-period			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); }
-branch_type		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); }
-,			{ return ','; }
-"/"			{ BEGIN(INITIAL); return '/'; }
-{name_minus}		{ return str(yyscanner, PE_NAME); }
-}
-
 mem:			{ BEGIN(mem); return PE_PREFIX_MEM; }
 r{num_raw_hex}		{ return raw(yyscanner); }
 {num_dec}		{ return value(yyscanner, 10); }
@@ -189,25 +208,7 @@ r{num_raw_hex}		{ return raw(yyscanner); }
 "}"			{ return '}'; }
 =			{ return '='; }
 \n			{ }
-
-<mem>{
-{modifier_bp}		{ return str(yyscanner, PE_MODIFIER_BP); }
-:			{ return ':'; }
-{num_dec}		{ return value(yyscanner, 10); }
-{num_hex}		{ return value(yyscanner, 16); }
-	/*
-	 * We need to separate 'mem:' scanner part, in order to get specific
-	 * modifier bits parsed out. Otherwise we would need to handle PE_NAME
-	 * and we'd need to parse it manually. During the escape from <mem>
-	 * state we need to put the escaping char back, so we dont miss it.
-	 */
-.			{ unput(*yytext); BEGIN(INITIAL); }
-	/*
-	 * We destroy the scanner after reaching EOF,
-	 * but anyway just to be sure get back to INIT state.
-	 */
-<<EOF>>			{ BEGIN(INITIAL); }
-}
+.			{ }
 
 %%
 
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
index a8c49548ca48..5d13cb45b317 100644
--- a/tools/perf/util/path.c
+++ b/tools/perf/util/path.c
@@ -22,19 +22,23 @@ static const char *get_perf_dir(void)
 	return ".";
 }
 
-#ifndef HAVE_STRLCPY
-size_t strlcpy(char *dest, const char *src, size_t size)
+/*
+ * If libc has strlcpy() then that version will override this
+ * implementation:
+ */
+size_t __weak strlcpy(char *dest, const char *src, size_t size)
 {
 	size_t ret = strlen(src);
 
 	if (size) {
 		size_t len = (ret >= size) ? size - 1 : ret;
+
 		memcpy(dest, src, len);
 		dest[len] = '\0';
 	}
+
 	return ret;
 }
-#endif
 
 static char *get_pathname(void)
 {
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index 5a4f2b6f3738..a3d42cd74919 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -1,7 +1,7 @@
 #ifndef __PERF_REGS_H
 #define __PERF_REGS_H
 
-#ifdef HAVE_PERF_REGS
+#ifdef HAVE_PERF_REGS_SUPPORT
 #include <perf_regs.h>
 #else
 #define PERF_REGS_MASK	0
@@ -10,5 +10,5 @@ static inline const char *perf_reg_name(int id __maybe_unused)
 {
 	return NULL;
 }
-#endif /* HAVE_PERF_REGS */
+#endif /* HAVE_PERF_REGS_SUPPORT */
 #endif /* __PERF_REGS_H */
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index aa04bf9c9ad7..779b2dacd43f 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -201,7 +201,7 @@ static int convert_to_perf_probe_point(struct probe_trace_point *tp,
 	return 0;
 }
 
-#ifdef DWARF_SUPPORT
+#ifdef HAVE_DWARF_SUPPORT
 /* Open new debuginfo of given module */
 static struct debuginfo *open_debuginfo(const char *module)
 {
@@ -630,7 +630,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 	return ret;
 }
 
-#else	/* !DWARF_SUPPORT */
+#else	/* !HAVE_DWARF_SUPPORT */
 
 static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
 					struct perf_probe_point *pp)
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 3b7d63018960..3f0c29dd6ac5 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -14,7 +14,7 @@ static inline int is_c_varname(const char *name)
 	return isalpha(name[0]) || name[0] == '_';
 }
 
-#ifdef DWARF_SUPPORT
+#ifdef HAVE_DWARF_SUPPORT
 
 #include "dwarf-aux.h"
 
@@ -105,6 +105,6 @@ struct line_finder {
 	int			found;
 };
 
-#endif /* DWARF_SUPPORT */
+#endif /* HAVE_DWARF_SUPPORT */
 
 #endif /*_PROBE_FINDER_H */
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 71b5412bbbb9..06efd027b1db 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -33,13 +33,6 @@ int eprintf(int level, const char *fmt, ...)
 # define PyVarObject_HEAD_INIT(type, size) PyObject_HEAD_INIT(type) size,
 #endif
 
-struct throttle_event {
-	struct perf_event_header header;
-	u64			 time;
-	u64			 id;
-	u64			 stream_id;
-};
-
 PyMODINIT_FUNC initperf(void);
 
 #define member_def(type, member, ptype, help) \
@@ -1036,6 +1029,7 @@ PyMODINIT_FUNC initperf(void)
 	    pyrf_cpu_map__setup_types() < 0)
 		return;
 
+	/* The page_size is placed in util object. */
 	page_size = sysconf(_SC_PAGE_SIZE);
 
 	Py_INCREF(&pyrf_evlist__type);
diff --git a/tools/perf/util/rblist.c b/tools/perf/util/rblist.c
index a16cdd2625ad..0dfe27d99458 100644
--- a/tools/perf/util/rblist.c
+++ b/tools/perf/util/rblist.c
@@ -48,10 +48,12 @@ void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node)
 	rblist->node_delete(rblist, rb_node);
 }
 
-struct rb_node *rblist__find(struct rblist *rblist, const void *entry)
+static struct rb_node *__rblist__findnew(struct rblist *rblist,
+					 const void *entry,
+					 bool create)
 {
 	struct rb_node **p = &rblist->entries.rb_node;
-	struct rb_node *parent = NULL;
+	struct rb_node *parent = NULL, *new_node = NULL;
 
 	while (*p != NULL) {
 		int rc;
@@ -67,7 +69,26 @@ struct rb_node *rblist__find(struct rblist *rblist, const void *entry)
 			return parent;
 	}
 
-	return NULL;
+	if (create) {
+		new_node = rblist->node_new(rblist, entry);
+		if (new_node) {
+			rb_link_node(new_node, parent, p);
+			rb_insert_color(new_node, &rblist->entries);
+			++rblist->nr_entries;
+		}
+	}
+
+	return new_node;
+}
+
+struct rb_node *rblist__find(struct rblist *rblist, const void *entry)
+{
+	return __rblist__findnew(rblist, entry, false);
+}
+
+struct rb_node *rblist__findnew(struct rblist *rblist, const void *entry)
+{
+	return __rblist__findnew(rblist, entry, true);
 }
 
 void rblist__init(struct rblist *rblist)
diff --git a/tools/perf/util/rblist.h b/tools/perf/util/rblist.h
index 6d0cae5ae83d..ff9913b994c2 100644
--- a/tools/perf/util/rblist.h
+++ b/tools/perf/util/rblist.h
@@ -32,6 +32,7 @@ void rblist__delete(struct rblist *rblist);
 int rblist__add_node(struct rblist *rblist, const void *new_entry);
 void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node);
 struct rb_node *rblist__find(struct rblist *rblist, const void *entry);
+struct rb_node *rblist__findnew(struct rblist *rblist, const void *entry);
 struct rb_node *rblist__entry(const struct rblist *rblist, unsigned int idx);
 
 static inline bool rblist__empty(const struct rblist *rblist)
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index b97f468af955..d1e449534b33 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -397,6 +397,17 @@ static void perf_event__read_swap(union perf_event *event, bool sample_id_all)
 		swap_sample_id_all(event, &event->read + 1);
 }
 
+static void perf_event__throttle_swap(union perf_event *event,
+				      bool sample_id_all)
+{
+	event->throttle.time	  = bswap_64(event->throttle.time);
+	event->throttle.id	  = bswap_64(event->throttle.id);
+	event->throttle.stream_id = bswap_64(event->throttle.stream_id);
+
+	if (sample_id_all)
+		swap_sample_id_all(event, &event->throttle + 1);
+}
+
 static u8 revbyte(u8 b)
 {
 	int rev = (b >> 4) | ((b & 0xf) << 4);
@@ -482,6 +493,8 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_EXIT]		  = perf_event__task_swap,
 	[PERF_RECORD_LOST]		  = perf_event__all64_swap,
 	[PERF_RECORD_READ]		  = perf_event__read_swap,
+	[PERF_RECORD_THROTTLE]		  = perf_event__throttle_swap,
+	[PERF_RECORD_UNTHROTTLE]	  = perf_event__throttle_swap,
 	[PERF_RECORD_SAMPLE]		  = perf_event__all64_swap,
 	[PERF_RECORD_HEADER_ATTR]	  = perf_event__hdr_attr_swap,
 	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index b4ecc0e4c908..32c56377e008 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -243,50 +243,32 @@ struct sort_entry sort_sym = {
 static int64_t
 sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	return (int64_t)(right->ip - left->ip);
+	if (!left->srcline) {
+		if (!left->ms.map)
+			left->srcline = SRCLINE_UNKNOWN;
+		else {
+			struct map *map = left->ms.map;
+			left->srcline = get_srcline(map->dso,
+					    map__rip_2objdump(map, left->ip));
+		}
+	}
+	if (!right->srcline) {
+		if (!right->ms.map)
+			right->srcline = SRCLINE_UNKNOWN;
+		else {
+			struct map *map = right->ms.map;
+			right->srcline = get_srcline(map->dso,
+					    map__rip_2objdump(map, right->ip));
+		}
+	}
+	return strcmp(left->srcline, right->srcline);
 }
 
 static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf,
 					size_t size,
 					unsigned int width __maybe_unused)
 {
-	FILE *fp = NULL;
-	char cmd[PATH_MAX + 2], *path = self->srcline, *nl;
-	size_t line_len;
-
-	if (path != NULL)
-		goto out_path;
-
-	if (!self->ms.map)
-		goto out_ip;
-
-	if (!strncmp(self->ms.map->dso->long_name, "/tmp/perf-", 10))
-		goto out_ip;
-
-	snprintf(cmd, sizeof(cmd), "addr2line -e %s %016" PRIx64,
-		 self->ms.map->dso->long_name, self->ip);
-	fp = popen(cmd, "r");
-	if (!fp)
-		goto out_ip;
-
-	if (getline(&path, &line_len, fp) < 0 || !line_len)
-		goto out_ip;
-	self->srcline = strdup(path);
-	if (self->srcline == NULL)
-		goto out_ip;
-
-	nl = strchr(self->srcline, '\n');
-	if (nl != NULL)
-		*nl = '\0';
-	path = self->srcline;
-out_path:
-	if (fp)
-		pclose(fp);
-	return repsep_snprintf(bf, size, "%s", path);
-out_ip:
-	if (fp)
-		pclose(fp);
-	return repsep_snprintf(bf, size, "%-#*llx", BITS_PER_LONG / 4, self->ip);
+	return repsep_snprintf(bf, size, "%s", self->srcline);
 }
 
 struct sort_entry sort_srcline = {
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
new file mode 100644
index 000000000000..d11aefbc4b8d
--- /dev/null
+++ b/tools/perf/util/srcline.c
@@ -0,0 +1,265 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <linux/kernel.h>
+
+#include "util/dso.h"
+#include "util/util.h"
+#include "util/debug.h"
+
+#ifdef HAVE_LIBBFD_SUPPORT
+
+/*
+ * Implement addr2line using libbfd.
+ */
+#define PACKAGE "perf"
+#include <bfd.h>
+
+struct a2l_data {
+	const char 	*input;
+	unsigned long 	addr;
+
+	bool 		found;
+	const char 	*filename;
+	const char 	*funcname;
+	unsigned 	line;
+
+	bfd 		*abfd;
+	asymbol 	**syms;
+};
+
+static int bfd_error(const char *string)
+{
+	const char *errmsg;
+
+	errmsg = bfd_errmsg(bfd_get_error());
+	fflush(stdout);
+
+	if (string)
+		pr_debug("%s: %s\n", string, errmsg);
+	else
+		pr_debug("%s\n", errmsg);
+
+	return -1;
+}
+
+static int slurp_symtab(bfd *abfd, struct a2l_data *a2l)
+{
+	long storage;
+	long symcount;
+	asymbol **syms;
+	bfd_boolean dynamic = FALSE;
+
+	if ((bfd_get_file_flags(abfd) & HAS_SYMS) == 0)
+		return bfd_error(bfd_get_filename(abfd));
+
+	storage = bfd_get_symtab_upper_bound(abfd);
+	if (storage == 0L) {
+		storage = bfd_get_dynamic_symtab_upper_bound(abfd);
+		dynamic = TRUE;
+	}
+	if (storage < 0L)
+		return bfd_error(bfd_get_filename(abfd));
+
+	syms = malloc(storage);
+	if (dynamic)
+		symcount = bfd_canonicalize_dynamic_symtab(abfd, syms);
+	else
+		symcount = bfd_canonicalize_symtab(abfd, syms);
+
+	if (symcount < 0) {
+		free(syms);
+		return bfd_error(bfd_get_filename(abfd));
+	}
+
+	a2l->syms = syms;
+	return 0;
+}
+
+static void find_address_in_section(bfd *abfd, asection *section, void *data)
+{
+	bfd_vma pc, vma;
+	bfd_size_type size;
+	struct a2l_data *a2l = data;
+
+	if (a2l->found)
+		return;
+
+	if ((bfd_get_section_flags(abfd, section) & SEC_ALLOC) == 0)
+		return;
+
+	pc = a2l->addr;
+	vma = bfd_get_section_vma(abfd, section);
+	size = bfd_get_section_size(section);
+
+	if (pc < vma || pc >= vma + size)
+		return;
+
+	a2l->found = bfd_find_nearest_line(abfd, section, a2l->syms, pc - vma,
+					   &a2l->filename, &a2l->funcname,
+					   &a2l->line);
+}
+
+static struct a2l_data *addr2line_init(const char *path)
+{
+	bfd *abfd;
+	struct a2l_data *a2l = NULL;
+
+	abfd = bfd_openr(path, NULL);
+	if (abfd == NULL)
+		return NULL;
+
+	if (!bfd_check_format(abfd, bfd_object))
+		goto out;
+
+	a2l = zalloc(sizeof(*a2l));
+	if (a2l == NULL)
+		goto out;
+
+	a2l->abfd = abfd;
+	a2l->input = strdup(path);
+	if (a2l->input == NULL)
+		goto out;
+
+	if (slurp_symtab(abfd, a2l))
+		goto out;
+
+	return a2l;
+
+out:
+	if (a2l) {
+		free((void *)a2l->input);
+		free(a2l);
+	}
+	bfd_close(abfd);
+	return NULL;
+}
+
+static void addr2line_cleanup(struct a2l_data *a2l)
+{
+	if (a2l->abfd)
+		bfd_close(a2l->abfd);
+	free((void *)a2l->input);
+	free(a2l->syms);
+	free(a2l);
+}
+
+static int addr2line(const char *dso_name, unsigned long addr,
+		     char **file, unsigned int *line)
+{
+	int ret = 0;
+	struct a2l_data *a2l;
+
+	a2l = addr2line_init(dso_name);
+	if (a2l == NULL) {
+		pr_warning("addr2line_init failed for %s\n", dso_name);
+		return 0;
+	}
+
+	a2l->addr = addr;
+	bfd_map_over_sections(a2l->abfd, find_address_in_section, a2l);
+
+	if (a2l->found && a2l->filename) {
+		*file = strdup(a2l->filename);
+		*line = a2l->line;
+
+		if (*file)
+			ret = 1;
+	}
+
+	addr2line_cleanup(a2l);
+	return ret;
+}
+
+#else /* HAVE_LIBBFD_SUPPORT */
+
+static int addr2line(const char *dso_name, unsigned long addr,
+		     char **file, unsigned int *line_nr)
+{
+	FILE *fp;
+	char cmd[PATH_MAX];
+	char *filename = NULL;
+	size_t len;
+	char *sep;
+	int ret = 0;
+
+	scnprintf(cmd, sizeof(cmd), "addr2line -e %s %016"PRIx64,
+		  dso_name, addr);
+
+	fp = popen(cmd, "r");
+	if (fp == NULL) {
+		pr_warning("popen failed for %s\n", dso_name);
+		return 0;
+	}
+
+	if (getline(&filename, &len, fp) < 0 || !len) {
+		pr_warning("addr2line has no output for %s\n", dso_name);
+		goto out;
+	}
+
+	sep = strchr(filename, '\n');
+	if (sep)
+		*sep = '\0';
+
+	if (!strcmp(filename, "??:0")) {
+		pr_debug("no debugging info in %s\n", dso_name);
+		free(filename);
+		goto out;
+	}
+
+	sep = strchr(filename, ':');
+	if (sep) {
+		*sep++ = '\0';
+		*file = filename;
+		*line_nr = strtoul(sep, NULL, 0);
+		ret = 1;
+	}
+out:
+	pclose(fp);
+	return ret;
+}
+#endif /* HAVE_LIBBFD_SUPPORT */
+
+char *get_srcline(struct dso *dso, unsigned long addr)
+{
+	char *file = NULL;
+	unsigned line = 0;
+	char *srcline;
+	char *dso_name = dso->long_name;
+	size_t size;
+
+	if (!dso->has_srcline)
+		return SRCLINE_UNKNOWN;
+
+	if (dso_name[0] == '[')
+		goto out;
+
+	if (!strncmp(dso_name, "/tmp/perf-", 10))
+		goto out;
+
+	if (!addr2line(dso_name, addr, &file, &line))
+		goto out;
+
+	/* just calculate actual length */
+	size = snprintf(NULL, 0, "%s:%u", file, line) + 1;
+
+	srcline = malloc(size);
+	if (srcline)
+		snprintf(srcline, size, "%s:%u", file, line);
+	else
+		srcline = SRCLINE_UNKNOWN;
+
+	free(file);
+	return srcline;
+
+out:
+	dso->has_srcline = 0;
+	return SRCLINE_UNKNOWN;
+}
+
+void free_srcline(char *srcline)
+{
+	if (srcline && strcmp(srcline, SRCLINE_UNKNOWN) != 0)
+		free(srcline);
+}
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index a9c829be5216..eed0b96302af 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -8,7 +8,7 @@
 #include "symbol.h"
 #include "debug.h"
 
-#ifndef HAVE_ELF_GETPHDRNUM
+#ifndef HAVE_ELF_GETPHDRNUM_SUPPORT
 static int elf_getphdrnum(Elf *elf, size_t *dst)
 {
 	GElf_Ehdr gehdr;
@@ -487,27 +487,27 @@ int filename__read_debuglink(const char *filename, char *debuglink,
 
 	ek = elf_kind(elf);
 	if (ek != ELF_K_ELF)
-		goto out_close;
+		goto out_elf_end;
 
 	if (gelf_getehdr(elf, &ehdr) == NULL) {
 		pr_err("%s: cannot get elf header.\n", __func__);
-		goto out_close;
+		goto out_elf_end;
 	}
 
 	sec = elf_section_by_name(elf, &ehdr, &shdr,
 				  ".gnu_debuglink", NULL);
 	if (sec == NULL)
-		goto out_close;
+		goto out_elf_end;
 
 	data = elf_getdata(sec, NULL);
 	if (data == NULL)
-		goto out_close;
+		goto out_elf_end;
 
 	/* the start of this section is a zero-terminated string */
 	strncpy(debuglink, data->d_buf, size);
 
+out_elf_end:
 	elf_end(elf);
-
 out_close:
 	close(fd);
 out:
@@ -1018,6 +1018,601 @@ int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data,
 	return err;
 }
 
+static int copy_bytes(int from, off_t from_offs, int to, off_t to_offs, u64 len)
+{
+	ssize_t r;
+	size_t n;
+	int err = -1;
+	char *buf = malloc(page_size);
+
+	if (buf == NULL)
+		return -1;
+
+	if (lseek(to, to_offs, SEEK_SET) != to_offs)
+		goto out;
+
+	if (lseek(from, from_offs, SEEK_SET) != from_offs)
+		goto out;
+
+	while (len) {
+		n = page_size;
+		if (len < n)
+			n = len;
+		/* Use read because mmap won't work on proc files */
+		r = read(from, buf, n);
+		if (r < 0)
+			goto out;
+		if (!r)
+			break;
+		n = r;
+		r = write(to, buf, n);
+		if (r < 0)
+			goto out;
+		if ((size_t)r != n)
+			goto out;
+		len -= n;
+	}
+
+	err = 0;
+out:
+	free(buf);
+	return err;
+}
+
+struct kcore {
+	int fd;
+	int elfclass;
+	Elf *elf;
+	GElf_Ehdr ehdr;
+};
+
+static int kcore__open(struct kcore *kcore, const char *filename)
+{
+	GElf_Ehdr *ehdr;
+
+	kcore->fd = open(filename, O_RDONLY);
+	if (kcore->fd == -1)
+		return -1;
+
+	kcore->elf = elf_begin(kcore->fd, ELF_C_READ, NULL);
+	if (!kcore->elf)
+		goto out_close;
+
+	kcore->elfclass = gelf_getclass(kcore->elf);
+	if (kcore->elfclass == ELFCLASSNONE)
+		goto out_end;
+
+	ehdr = gelf_getehdr(kcore->elf, &kcore->ehdr);
+	if (!ehdr)
+		goto out_end;
+
+	return 0;
+
+out_end:
+	elf_end(kcore->elf);
+out_close:
+	close(kcore->fd);
+	return -1;
+}
+
+static int kcore__init(struct kcore *kcore, char *filename, int elfclass,
+		       bool temp)
+{
+	GElf_Ehdr *ehdr;
+
+	kcore->elfclass = elfclass;
+
+	if (temp)
+		kcore->fd = mkstemp(filename);
+	else
+		kcore->fd = open(filename, O_WRONLY | O_CREAT | O_EXCL, 0400);
+	if (kcore->fd == -1)
+		return -1;
+
+	kcore->elf = elf_begin(kcore->fd, ELF_C_WRITE, NULL);
+	if (!kcore->elf)
+		goto out_close;
+
+	if (!gelf_newehdr(kcore->elf, elfclass))
+		goto out_end;
+
+	ehdr = gelf_getehdr(kcore->elf, &kcore->ehdr);
+	if (!ehdr)
+		goto out_end;
+
+	return 0;
+
+out_end:
+	elf_end(kcore->elf);
+out_close:
+	close(kcore->fd);
+	unlink(filename);
+	return -1;
+}
+
+static void kcore__close(struct kcore *kcore)
+{
+	elf_end(kcore->elf);
+	close(kcore->fd);
+}
+
+static int kcore__copy_hdr(struct kcore *from, struct kcore *to, size_t count)
+{
+	GElf_Ehdr *ehdr = &to->ehdr;
+	GElf_Ehdr *kehdr = &from->ehdr;
+
+	memcpy(ehdr->e_ident, kehdr->e_ident, EI_NIDENT);
+	ehdr->e_type      = kehdr->e_type;
+	ehdr->e_machine   = kehdr->e_machine;
+	ehdr->e_version   = kehdr->e_version;
+	ehdr->e_entry     = 0;
+	ehdr->e_shoff     = 0;
+	ehdr->e_flags     = kehdr->e_flags;
+	ehdr->e_phnum     = count;
+	ehdr->e_shentsize = 0;
+	ehdr->e_shnum     = 0;
+	ehdr->e_shstrndx  = 0;
+
+	if (from->elfclass == ELFCLASS32) {
+		ehdr->e_phoff     = sizeof(Elf32_Ehdr);
+		ehdr->e_ehsize    = sizeof(Elf32_Ehdr);
+		ehdr->e_phentsize = sizeof(Elf32_Phdr);
+	} else {
+		ehdr->e_phoff     = sizeof(Elf64_Ehdr);
+		ehdr->e_ehsize    = sizeof(Elf64_Ehdr);
+		ehdr->e_phentsize = sizeof(Elf64_Phdr);
+	}
+
+	if (!gelf_update_ehdr(to->elf, ehdr))
+		return -1;
+
+	if (!gelf_newphdr(to->elf, count))
+		return -1;
+
+	return 0;
+}
+
+static int kcore__add_phdr(struct kcore *kcore, int idx, off_t offset,
+			   u64 addr, u64 len)
+{
+	GElf_Phdr gphdr;
+	GElf_Phdr *phdr;
+
+	phdr = gelf_getphdr(kcore->elf, idx, &gphdr);
+	if (!phdr)
+		return -1;
+
+	phdr->p_type	= PT_LOAD;
+	phdr->p_flags	= PF_R | PF_W | PF_X;
+	phdr->p_offset	= offset;
+	phdr->p_vaddr	= addr;
+	phdr->p_paddr	= 0;
+	phdr->p_filesz	= len;
+	phdr->p_memsz	= len;
+	phdr->p_align	= page_size;
+
+	if (!gelf_update_phdr(kcore->elf, idx, phdr))
+		return -1;
+
+	return 0;
+}
+
+static off_t kcore__write(struct kcore *kcore)
+{
+	return elf_update(kcore->elf, ELF_C_WRITE);
+}
+
+struct phdr_data {
+	off_t offset;
+	u64 addr;
+	u64 len;
+};
+
+struct kcore_copy_info {
+	u64 stext;
+	u64 etext;
+	u64 first_symbol;
+	u64 last_symbol;
+	u64 first_module;
+	u64 last_module_symbol;
+	struct phdr_data kernel_map;
+	struct phdr_data modules_map;
+};
+
+static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,
+					u64 start)
+{
+	struct kcore_copy_info *kci = arg;
+
+	if (!symbol_type__is_a(type, MAP__FUNCTION))
+		return 0;
+
+	if (strchr(name, '[')) {
+		if (start > kci->last_module_symbol)
+			kci->last_module_symbol = start;
+		return 0;
+	}
+
+	if (!kci->first_symbol || start < kci->first_symbol)
+		kci->first_symbol = start;
+
+	if (!kci->last_symbol || start > kci->last_symbol)
+		kci->last_symbol = start;
+
+	if (!strcmp(name, "_stext")) {
+		kci->stext = start;
+		return 0;
+	}
+
+	if (!strcmp(name, "_etext")) {
+		kci->etext = start;
+		return 0;
+	}
+
+	return 0;
+}
+
+static int kcore_copy__parse_kallsyms(struct kcore_copy_info *kci,
+				      const char *dir)
+{
+	char kallsyms_filename[PATH_MAX];
+
+	scnprintf(kallsyms_filename, PATH_MAX, "%s/kallsyms", dir);
+
+	if (symbol__restricted_filename(kallsyms_filename, "/proc/kallsyms"))
+		return -1;
+
+	if (kallsyms__parse(kallsyms_filename, kci,
+			    kcore_copy__process_kallsyms) < 0)
+		return -1;
+
+	return 0;
+}
+
+static int kcore_copy__process_modules(void *arg,
+				       const char *name __maybe_unused,
+				       u64 start)
+{
+	struct kcore_copy_info *kci = arg;
+
+	if (!kci->first_module || start < kci->first_module)
+		kci->first_module = start;
+
+	return 0;
+}
+
+static int kcore_copy__parse_modules(struct kcore_copy_info *kci,
+				     const char *dir)
+{
+	char modules_filename[PATH_MAX];
+
+	scnprintf(modules_filename, PATH_MAX, "%s/modules", dir);
+
+	if (symbol__restricted_filename(modules_filename, "/proc/modules"))
+		return -1;
+
+	if (modules__parse(modules_filename, kci,
+			   kcore_copy__process_modules) < 0)
+		return -1;
+
+	return 0;
+}
+
+static void kcore_copy__map(struct phdr_data *p, u64 start, u64 end, u64 pgoff,
+			    u64 s, u64 e)
+{
+	if (p->addr || s < start || s >= end)
+		return;
+
+	p->addr = s;
+	p->offset = (s - start) + pgoff;
+	p->len = e < end ? e - s : end - s;
+}
+
+static int kcore_copy__read_map(u64 start, u64 len, u64 pgoff, void *data)
+{
+	struct kcore_copy_info *kci = data;
+	u64 end = start + len;
+
+	kcore_copy__map(&kci->kernel_map, start, end, pgoff, kci->stext,
+			kci->etext);
+
+	kcore_copy__map(&kci->modules_map, start, end, pgoff, kci->first_module,
+			kci->last_module_symbol);
+
+	return 0;
+}
+
+static int kcore_copy__read_maps(struct kcore_copy_info *kci, Elf *elf)
+{
+	if (elf_read_maps(elf, true, kcore_copy__read_map, kci) < 0)
+		return -1;
+
+	return 0;
+}
+
+static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir,
+				 Elf *elf)
+{
+	if (kcore_copy__parse_kallsyms(kci, dir))
+		return -1;
+
+	if (kcore_copy__parse_modules(kci, dir))
+		return -1;
+
+	if (kci->stext)
+		kci->stext = round_down(kci->stext, page_size);
+	else
+		kci->stext = round_down(kci->first_symbol, page_size);
+
+	if (kci->etext) {
+		kci->etext = round_up(kci->etext, page_size);
+	} else if (kci->last_symbol) {
+		kci->etext = round_up(kci->last_symbol, page_size);
+		kci->etext += page_size;
+	}
+
+	kci->first_module = round_down(kci->first_module, page_size);
+
+	if (kci->last_module_symbol) {
+		kci->last_module_symbol = round_up(kci->last_module_symbol,
+						   page_size);
+		kci->last_module_symbol += page_size;
+	}
+
+	if (!kci->stext || !kci->etext)
+		return -1;
+
+	if (kci->first_module && !kci->last_module_symbol)
+		return -1;
+
+	return kcore_copy__read_maps(kci, elf);
+}
+
+static int kcore_copy__copy_file(const char *from_dir, const char *to_dir,
+				 const char *name)
+{
+	char from_filename[PATH_MAX];
+	char to_filename[PATH_MAX];
+
+	scnprintf(from_filename, PATH_MAX, "%s/%s", from_dir, name);
+	scnprintf(to_filename, PATH_MAX, "%s/%s", to_dir, name);
+
+	return copyfile_mode(from_filename, to_filename, 0400);
+}
+
+static int kcore_copy__unlink(const char *dir, const char *name)
+{
+	char filename[PATH_MAX];
+
+	scnprintf(filename, PATH_MAX, "%s/%s", dir, name);
+
+	return unlink(filename);
+}
+
+static int kcore_copy__compare_fds(int from, int to)
+{
+	char *buf_from;
+	char *buf_to;
+	ssize_t ret;
+	size_t len;
+	int err = -1;
+
+	buf_from = malloc(page_size);
+	buf_to = malloc(page_size);
+	if (!buf_from || !buf_to)
+		goto out;
+
+	while (1) {
+		/* Use read because mmap won't work on proc files */
+		ret = read(from, buf_from, page_size);
+		if (ret < 0)
+			goto out;
+
+		if (!ret)
+			break;
+
+		len = ret;
+
+		if (readn(to, buf_to, len) != (int)len)
+			goto out;
+
+		if (memcmp(buf_from, buf_to, len))
+			goto out;
+	}
+
+	err = 0;
+out:
+	free(buf_to);
+	free(buf_from);
+	return err;
+}
+
+static int kcore_copy__compare_files(const char *from_filename,
+				     const char *to_filename)
+{
+	int from, to, err = -1;
+
+	from = open(from_filename, O_RDONLY);
+	if (from < 0)
+		return -1;
+
+	to = open(to_filename, O_RDONLY);
+	if (to < 0)
+		goto out_close_from;
+
+	err = kcore_copy__compare_fds(from, to);
+
+	close(to);
+out_close_from:
+	close(from);
+	return err;
+}
+
+static int kcore_copy__compare_file(const char *from_dir, const char *to_dir,
+				    const char *name)
+{
+	char from_filename[PATH_MAX];
+	char to_filename[PATH_MAX];
+
+	scnprintf(from_filename, PATH_MAX, "%s/%s", from_dir, name);
+	scnprintf(to_filename, PATH_MAX, "%s/%s", to_dir, name);
+
+	return kcore_copy__compare_files(from_filename, to_filename);
+}
+
+/**
+ * kcore_copy - copy kallsyms, modules and kcore from one directory to another.
+ * @from_dir: from directory
+ * @to_dir: to directory
+ *
+ * This function copies kallsyms, modules and kcore files from one directory to
+ * another.  kallsyms and modules are copied entirely.  Only code segments are
+ * copied from kcore.  It is assumed that two segments suffice: one for the
+ * kernel proper and one for all the modules.  The code segments are determined
+ * from kallsyms and modules files.  The kernel map starts at _stext or the
+ * lowest function symbol, and ends at _etext or the highest function symbol.
+ * The module map starts at the lowest module address and ends at the highest
+ * module symbol.  Start addresses are rounded down to the nearest page.  End
+ * addresses are rounded up to the nearest page.  An extra page is added to the
+ * highest kernel symbol and highest module symbol to, hopefully, encompass that
+ * symbol too.  Because it contains only code sections, the resulting kcore is
+ * unusual.  One significant peculiarity is that the mapping (start -> pgoff)
+ * is not the same for the kernel map and the modules map.  That happens because
+ * the data is copied adjacently whereas the original kcore has gaps.  Finally,
+ * kallsyms and modules files are compared with their copies to check that
+ * modules have not been loaded or unloaded while the copies were taking place.
+ *
+ * Return: %0 on success, %-1 on failure.
+ */
+int kcore_copy(const char *from_dir, const char *to_dir)
+{
+	struct kcore kcore;
+	struct kcore extract;
+	size_t count = 2;
+	int idx = 0, err = -1;
+	off_t offset = page_size, sz, modules_offset = 0;
+	struct kcore_copy_info kci = { .stext = 0, };
+	char kcore_filename[PATH_MAX];
+	char extract_filename[PATH_MAX];
+
+	if (kcore_copy__copy_file(from_dir, to_dir, "kallsyms"))
+		return -1;
+
+	if (kcore_copy__copy_file(from_dir, to_dir, "modules"))
+		goto out_unlink_kallsyms;
+
+	scnprintf(kcore_filename, PATH_MAX, "%s/kcore", from_dir);
+	scnprintf(extract_filename, PATH_MAX, "%s/kcore", to_dir);
+
+	if (kcore__open(&kcore, kcore_filename))
+		goto out_unlink_modules;
+
+	if (kcore_copy__calc_maps(&kci, from_dir, kcore.elf))
+		goto out_kcore_close;
+
+	if (kcore__init(&extract, extract_filename, kcore.elfclass, false))
+		goto out_kcore_close;
+
+	if (!kci.modules_map.addr)
+		count -= 1;
+
+	if (kcore__copy_hdr(&kcore, &extract, count))
+		goto out_extract_close;
+
+	if (kcore__add_phdr(&extract, idx++, offset, kci.kernel_map.addr,
+			    kci.kernel_map.len))
+		goto out_extract_close;
+
+	if (kci.modules_map.addr) {
+		modules_offset = offset + kci.kernel_map.len;
+		if (kcore__add_phdr(&extract, idx, modules_offset,
+				    kci.modules_map.addr, kci.modules_map.len))
+			goto out_extract_close;
+	}
+
+	sz = kcore__write(&extract);
+	if (sz < 0 || sz > offset)
+		goto out_extract_close;
+
+	if (copy_bytes(kcore.fd, kci.kernel_map.offset, extract.fd, offset,
+		       kci.kernel_map.len))
+		goto out_extract_close;
+
+	if (modules_offset && copy_bytes(kcore.fd, kci.modules_map.offset,
+					 extract.fd, modules_offset,
+					 kci.modules_map.len))
+		goto out_extract_close;
+
+	if (kcore_copy__compare_file(from_dir, to_dir, "modules"))
+		goto out_extract_close;
+
+	if (kcore_copy__compare_file(from_dir, to_dir, "kallsyms"))
+		goto out_extract_close;
+
+	err = 0;
+
+out_extract_close:
+	kcore__close(&extract);
+	if (err)
+		unlink(extract_filename);
+out_kcore_close:
+	kcore__close(&kcore);
+out_unlink_modules:
+	if (err)
+		kcore_copy__unlink(to_dir, "modules");
+out_unlink_kallsyms:
+	if (err)
+		kcore_copy__unlink(to_dir, "kallsyms");
+
+	return err;
+}
+
+int kcore_extract__create(struct kcore_extract *kce)
+{
+	struct kcore kcore;
+	struct kcore extract;
+	size_t count = 1;
+	int idx = 0, err = -1;
+	off_t offset = page_size, sz;
+
+	if (kcore__open(&kcore, kce->kcore_filename))
+		return -1;
+
+	strcpy(kce->extract_filename, PERF_KCORE_EXTRACT);
+	if (kcore__init(&extract, kce->extract_filename, kcore.elfclass, true))
+		goto out_kcore_close;
+
+	if (kcore__copy_hdr(&kcore, &extract, count))
+		goto out_extract_close;
+
+	if (kcore__add_phdr(&extract, idx, offset, kce->addr, kce->len))
+		goto out_extract_close;
+
+	sz = kcore__write(&extract);
+	if (sz < 0 || sz > offset)
+		goto out_extract_close;
+
+	if (copy_bytes(kcore.fd, kce->offs, extract.fd, offset, kce->len))
+		goto out_extract_close;
+
+	err = 0;
+
+out_extract_close:
+	kcore__close(&extract);
+	if (err)
+		unlink(kce->extract_filename);
+out_kcore_close:
+	kcore__close(&kcore);
+
+	return err;
+}
+
+void kcore_extract__delete(struct kcore_extract *kce)
+{
+	unlink(kce->extract_filename);
+}
+
 void symbol__elf_init(void)
 {
 	elf_version(EV_CURRENT);
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 3a802c300fc5..2d2dd0532b5a 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -308,6 +308,21 @@ int file__read_maps(int fd __maybe_unused, bool exe __maybe_unused,
 	return -1;
 }
 
+int kcore_extract__create(struct kcore_extract *kce __maybe_unused)
+{
+	return -1;
+}
+
+void kcore_extract__delete(struct kcore_extract *kce __maybe_unused)
+{
+}
+
+int kcore_copy(const char *from_dir __maybe_unused,
+	       const char *to_dir __maybe_unused)
+{
+	return -1;
+}
+
 void symbol__elf_init(void)
 {
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 7eb0362f4ffd..c0c36965fff0 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -51,6 +51,7 @@ static enum dso_binary_type binary_type_symtab[] = {
 	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
 	DSO_BINARY_TYPE__GUEST_KMODULE,
 	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
 	DSO_BINARY_TYPE__NOT_FOUND,
 };
 
@@ -159,10 +160,12 @@ again:
 
 		if (choose_best_symbol(curr, next) == SYMBOL_A) {
 			rb_erase(&next->rb_node, symbols);
+			symbol__delete(next);
 			goto again;
 		} else {
 			nd = rb_next(&curr->rb_node);
 			rb_erase(&curr->rb_node, symbols);
+			symbol__delete(curr);
 		}
 	}
 }
@@ -499,6 +502,64 @@ out_failure:
 	return -1;
 }
 
+int modules__parse(const char *filename, void *arg,
+		   int (*process_module)(void *arg, const char *name,
+					 u64 start))
+{
+	char *line = NULL;
+	size_t n;
+	FILE *file;
+	int err = 0;
+
+	file = fopen(filename, "r");
+	if (file == NULL)
+		return -1;
+
+	while (1) {
+		char name[PATH_MAX];
+		u64 start;
+		char *sep;
+		ssize_t line_len;
+
+		line_len = getline(&line, &n, file);
+		if (line_len < 0) {
+			if (feof(file))
+				break;
+			err = -1;
+			goto out;
+		}
+
+		if (!line) {
+			err = -1;
+			goto out;
+		}
+
+		line[--line_len] = '\0'; /* \n */
+
+		sep = strrchr(line, 'x');
+		if (sep == NULL)
+			continue;
+
+		hex2u64(sep + 1, &start);
+
+		sep = strchr(line, ' ');
+		if (sep == NULL)
+			continue;
+
+		*sep = '\0';
+
+		scnprintf(name, sizeof(name), "[%s]", line);
+
+		err = process_module(arg, name, start);
+		if (err)
+			break;
+	}
+out:
+	free(line);
+	fclose(file);
+	return err;
+}
+
 struct process_kallsyms_args {
 	struct map *map;
 	struct dso *dso;
@@ -739,51 +800,242 @@ bool symbol__restricted_filename(const char *filename,
 	return restricted;
 }
 
-struct kcore_mapfn_data {
-	struct dso *dso;
-	enum map_type type;
-	struct list_head maps;
+struct module_info {
+	struct rb_node rb_node;
+	char *name;
+	u64 start;
 };
 
-static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data)
+static void add_module(struct module_info *mi, struct rb_root *modules)
 {
-	struct kcore_mapfn_data *md = data;
-	struct map *map;
+	struct rb_node **p = &modules->rb_node;
+	struct rb_node *parent = NULL;
+	struct module_info *m;
 
-	map = map__new2(start, md->dso, md->type);
-	if (map == NULL)
+	while (*p != NULL) {
+		parent = *p;
+		m = rb_entry(parent, struct module_info, rb_node);
+		if (strcmp(mi->name, m->name) < 0)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+	rb_link_node(&mi->rb_node, parent, p);
+	rb_insert_color(&mi->rb_node, modules);
+}
+
+static void delete_modules(struct rb_root *modules)
+{
+	struct module_info *mi;
+	struct rb_node *next = rb_first(modules);
+
+	while (next) {
+		mi = rb_entry(next, struct module_info, rb_node);
+		next = rb_next(&mi->rb_node);
+		rb_erase(&mi->rb_node, modules);
+		free(mi->name);
+		free(mi);
+	}
+}
+
+static struct module_info *find_module(const char *name,
+				       struct rb_root *modules)
+{
+	struct rb_node *n = modules->rb_node;
+
+	while (n) {
+		struct module_info *m;
+		int cmp;
+
+		m = rb_entry(n, struct module_info, rb_node);
+		cmp = strcmp(name, m->name);
+		if (cmp < 0)
+			n = n->rb_left;
+		else if (cmp > 0)
+			n = n->rb_right;
+		else
+			return m;
+	}
+
+	return NULL;
+}
+
+static int __read_proc_modules(void *arg, const char *name, u64 start)
+{
+	struct rb_root *modules = arg;
+	struct module_info *mi;
+
+	mi = zalloc(sizeof(struct module_info));
+	if (!mi)
 		return -ENOMEM;
 
-	map->end = map->start + len;
-	map->pgoff = pgoff;
+	mi->name = strdup(name);
+	mi->start = start;
 
-	list_add(&map->node, &md->maps);
+	if (!mi->name) {
+		free(mi);
+		return -ENOMEM;
+	}
+
+	add_module(mi, modules);
+
+	return 0;
+}
+
+static int read_proc_modules(const char *filename, struct rb_root *modules)
+{
+	if (symbol__restricted_filename(filename, "/proc/modules"))
+		return -1;
+
+	if (modules__parse(filename, modules, __read_proc_modules)) {
+		delete_modules(modules);
+		return -1;
+	}
 
 	return 0;
 }
 
+int compare_proc_modules(const char *from, const char *to)
+{
+	struct rb_root from_modules = RB_ROOT;
+	struct rb_root to_modules = RB_ROOT;
+	struct rb_node *from_node, *to_node;
+	struct module_info *from_m, *to_m;
+	int ret = -1;
+
+	if (read_proc_modules(from, &from_modules))
+		return -1;
+
+	if (read_proc_modules(to, &to_modules))
+		goto out_delete_from;
+
+	from_node = rb_first(&from_modules);
+	to_node = rb_first(&to_modules);
+	while (from_node) {
+		if (!to_node)
+			break;
+
+		from_m = rb_entry(from_node, struct module_info, rb_node);
+		to_m = rb_entry(to_node, struct module_info, rb_node);
+
+		if (from_m->start != to_m->start ||
+		    strcmp(from_m->name, to_m->name))
+			break;
+
+		from_node = rb_next(from_node);
+		to_node = rb_next(to_node);
+	}
+
+	if (!from_node && !to_node)
+		ret = 0;
+
+	delete_modules(&to_modules);
+out_delete_from:
+	delete_modules(&from_modules);
+
+	return ret;
+}
+
+static int do_validate_kcore_modules(const char *filename, struct map *map,
+				  struct map_groups *kmaps)
+{
+	struct rb_root modules = RB_ROOT;
+	struct map *old_map;
+	int err;
+
+	err = read_proc_modules(filename, &modules);
+	if (err)
+		return err;
+
+	old_map = map_groups__first(kmaps, map->type);
+	while (old_map) {
+		struct map *next = map_groups__next(old_map);
+		struct module_info *mi;
+
+		if (old_map == map || old_map->start == map->start) {
+			/* The kernel map */
+			old_map = next;
+			continue;
+		}
+
+		/* Module must be in memory at the same address */
+		mi = find_module(old_map->dso->short_name, &modules);
+		if (!mi || mi->start != old_map->start) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		old_map = next;
+	}
+out:
+	delete_modules(&modules);
+	return err;
+}
+
 /*
- * If kallsyms is referenced by name then we look for kcore in the same
+ * If kallsyms is referenced by name then we look for filename in the same
  * directory.
  */
-static bool kcore_filename_from_kallsyms_filename(char *kcore_filename,
-						  const char *kallsyms_filename)
+static bool filename_from_kallsyms_filename(char *filename,
+					    const char *base_name,
+					    const char *kallsyms_filename)
 {
 	char *name;
 
-	strcpy(kcore_filename, kallsyms_filename);
-	name = strrchr(kcore_filename, '/');
+	strcpy(filename, kallsyms_filename);
+	name = strrchr(filename, '/');
 	if (!name)
 		return false;
 
-	if (!strcmp(name, "/kallsyms")) {
-		strcpy(name, "/kcore");
+	name += 1;
+
+	if (!strcmp(name, "kallsyms")) {
+		strcpy(name, base_name);
 		return true;
 	}
 
 	return false;
 }
 
+static int validate_kcore_modules(const char *kallsyms_filename,
+				  struct map *map)
+{
+	struct map_groups *kmaps = map__kmap(map)->kmaps;
+	char modules_filename[PATH_MAX];
+
+	if (!filename_from_kallsyms_filename(modules_filename, "modules",
+					     kallsyms_filename))
+		return -EINVAL;
+
+	if (do_validate_kcore_modules(modules_filename, map, kmaps))
+		return -EINVAL;
+
+	return 0;
+}
+
+struct kcore_mapfn_data {
+	struct dso *dso;
+	enum map_type type;
+	struct list_head maps;
+};
+
+static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data)
+{
+	struct kcore_mapfn_data *md = data;
+	struct map *map;
+
+	map = map__new2(start, md->dso, md->type);
+	if (map == NULL)
+		return -ENOMEM;
+
+	map->end = map->start + len;
+	map->pgoff = pgoff;
+
+	list_add(&map->node, &md->maps);
+
+	return 0;
+}
+
 static int dso__load_kcore(struct dso *dso, struct map *map,
 			   const char *kallsyms_filename)
 {
@@ -800,8 +1052,12 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	if (map != machine->vmlinux_maps[map->type])
 		return -EINVAL;
 
-	if (!kcore_filename_from_kallsyms_filename(kcore_filename,
-						   kallsyms_filename))
+	if (!filename_from_kallsyms_filename(kcore_filename, "kcore",
+					     kallsyms_filename))
+		return -EINVAL;
+
+	/* All modules must be present at their original addresses */
+	if (validate_kcore_modules(kallsyms_filename, map))
 		return -EINVAL;
 
 	md.dso = dso;
@@ -1188,6 +1444,105 @@ out:
 	return err;
 }
 
+static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz)
+{
+	char kallsyms_filename[PATH_MAX];
+	struct dirent *dent;
+	int ret = -1;
+	DIR *d;
+
+	d = opendir(dir);
+	if (!d)
+		return -1;
+
+	while (1) {
+		dent = readdir(d);
+		if (!dent)
+			break;
+		if (dent->d_type != DT_DIR)
+			continue;
+		scnprintf(kallsyms_filename, sizeof(kallsyms_filename),
+			  "%s/%s/kallsyms", dir, dent->d_name);
+		if (!validate_kcore_modules(kallsyms_filename, map)) {
+			strlcpy(dir, kallsyms_filename, dir_sz);
+			ret = 0;
+			break;
+		}
+	}
+
+	closedir(d);
+
+	return ret;
+}
+
+static char *dso__find_kallsyms(struct dso *dso, struct map *map)
+{
+	u8 host_build_id[BUILD_ID_SIZE];
+	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+	bool is_host = false;
+	char path[PATH_MAX];
+
+	if (!dso->has_build_id) {
+		/*
+		 * Last resort, if we don't have a build-id and couldn't find
+		 * any vmlinux file, try the running kernel kallsyms table.
+		 */
+		goto proc_kallsyms;
+	}
+
+	if (sysfs__read_build_id("/sys/kernel/notes", host_build_id,
+				 sizeof(host_build_id)) == 0)
+		is_host = dso__build_id_equal(dso, host_build_id);
+
+	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
+
+	/* Use /proc/kallsyms if possible */
+	if (is_host) {
+		DIR *d;
+		int fd;
+
+		/* If no cached kcore go with /proc/kallsyms */
+		scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s",
+			  buildid_dir, sbuild_id);
+		d = opendir(path);
+		if (!d)
+			goto proc_kallsyms;
+		closedir(d);
+
+		/*
+		 * Do not check the build-id cache, until we know we cannot use
+		 * /proc/kcore.
+		 */
+		fd = open("/proc/kcore", O_RDONLY);
+		if (fd != -1) {
+			close(fd);
+			/* If module maps match go with /proc/kallsyms */
+			if (!validate_kcore_modules("/proc/kallsyms", map))
+				goto proc_kallsyms;
+		}
+
+		/* Find kallsyms in build-id cache with kcore */
+		if (!find_matching_kcore(map, path, sizeof(path)))
+			return strdup(path);
+
+		goto proc_kallsyms;
+	}
+
+	scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s",
+		  buildid_dir, sbuild_id);
+
+	if (access(path, F_OK)) {
+		pr_err("No kallsyms or vmlinux with build-id %s was found\n",
+		       sbuild_id);
+		return NULL;
+	}
+
+	return strdup(path);
+
+proc_kallsyms:
+	return strdup("/proc/kallsyms");
+}
+
 static int dso__load_kernel_sym(struct dso *dso, struct map *map,
 				symbol_filter_t filter)
 {
@@ -1214,7 +1569,7 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map,
 		goto do_kallsyms;
 	}
 
-	if (symbol_conf.vmlinux_name != NULL) {
+	if (!symbol_conf.ignore_vmlinux && symbol_conf.vmlinux_name != NULL) {
 		err = dso__load_vmlinux(dso, map,
 					symbol_conf.vmlinux_name, filter);
 		if (err > 0) {
@@ -1226,7 +1581,7 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map,
 		return err;
 	}
 
-	if (vmlinux_path != NULL) {
+	if (!symbol_conf.ignore_vmlinux && vmlinux_path != NULL) {
 		err = dso__load_vmlinux_path(dso, map, filter);
 		if (err > 0)
 			return err;
@@ -1236,51 +1591,11 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map,
 	if (symbol_conf.symfs[0] != 0)
 		return -1;
 
-	/*
-	 * Say the kernel DSO was created when processing the build-id header table,
-	 * we have a build-id, so check if it is the same as the running kernel,
-	 * using it if it is.
-	 */
-	if (dso->has_build_id) {
-		u8 kallsyms_build_id[BUILD_ID_SIZE];
-		char sbuild_id[BUILD_ID_SIZE * 2 + 1];
-
-		if (sysfs__read_build_id("/sys/kernel/notes", kallsyms_build_id,
-					 sizeof(kallsyms_build_id)) == 0) {
-			if (dso__build_id_equal(dso, kallsyms_build_id)) {
-				kallsyms_filename = "/proc/kallsyms";
-				goto do_kallsyms;
-			}
-		}
-		/*
-		 * Now look if we have it on the build-id cache in
-		 * $HOME/.debug/[kernel.kallsyms].
-		 */
-		build_id__sprintf(dso->build_id, sizeof(dso->build_id),
-				  sbuild_id);
-
-		if (asprintf(&kallsyms_allocated_filename,
-			     "%s/.debug/[kernel.kallsyms]/%s",
-			     getenv("HOME"), sbuild_id) == -1) {
-			pr_err("Not enough memory for kallsyms file lookup\n");
-			return -1;
-		}
-
-		kallsyms_filename = kallsyms_allocated_filename;
+	kallsyms_allocated_filename = dso__find_kallsyms(dso, map);
+	if (!kallsyms_allocated_filename)
+		return -1;
 
-		if (access(kallsyms_filename, F_OK)) {
-			pr_err("No kallsyms or vmlinux with build-id %s "
-			       "was found\n", sbuild_id);
-			free(kallsyms_allocated_filename);
-			return -1;
-		}
-	} else {
-		/*
-		 * Last resort, if we don't have a build-id and couldn't find
-		 * any vmlinux file, try the running kernel kallsyms table.
-		 */
-		kallsyms_filename = "/proc/kallsyms";
-	}
+	kallsyms_filename = kallsyms_allocated_filename;
 
 do_kallsyms:
 	err = dso__load_kallsyms(dso, kallsyms_filename, map, filter);
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index fd5b70ea2981..07de8fea2f48 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -13,7 +13,7 @@
 #include <libgen.h>
 #include "build-id.h"
 
-#ifdef LIBELF_SUPPORT
+#ifdef HAVE_LIBELF_SUPPORT
 #include <libelf.h>
 #include <gelf.h>
 #endif
@@ -21,7 +21,7 @@
 
 #include "dso.h"
 
-#ifdef HAVE_CPLUS_DEMANGLE
+#ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
 extern char *cplus_demangle(const char *, int);
 
 static inline char *bfd_demangle(void __maybe_unused *v, const char *c, int i)
@@ -46,7 +46,7 @@ static inline char *bfd_demangle(void __maybe_unused *v,
  * libelf 0.8.x and earlier do not support ELF_C_READ_MMAP;
  * for newer versions we can use mmap to reduce memory usage:
  */
-#ifdef LIBELF_MMAP
+#ifdef HAVE_LIBELF_MMAP_SUPPORT
 # define PERF_ELF_C_READ_MMAP ELF_C_READ_MMAP
 #else
 # define PERF_ELF_C_READ_MMAP ELF_C_READ
@@ -85,6 +85,7 @@ struct symbol_conf {
 	unsigned short	priv_size;
 	unsigned short	nr_events;
 	bool		try_vmlinux_path,
+			ignore_vmlinux,
 			show_kernel_path,
 			use_modules,
 			sort_by_name,
@@ -178,7 +179,7 @@ struct symsrc {
 	int fd;
 	enum dso_binary_type type;
 
-#ifdef LIBELF_SUPPORT
+#ifdef HAVE_LIBELF_SUPPORT
 	Elf *elf;
 	GElf_Ehdr ehdr;
 
@@ -222,6 +223,9 @@ int sysfs__read_build_id(const char *filename, void *bf, size_t size);
 int kallsyms__parse(const char *filename, void *arg,
 		    int (*process_symbol)(void *arg, const char *name,
 					  char type, u64 start));
+int modules__parse(const char *filename, void *arg,
+		   int (*process_module)(void *arg, const char *name,
+					 u64 start));
 int filename__read_debuglink(const char *filename, char *debuglink,
 			     size_t size);
 
@@ -252,4 +256,21 @@ typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data);
 int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data,
 		    bool *is_64_bit);
 
+#define PERF_KCORE_EXTRACT "/tmp/perf-kcore-XXXXXX"
+
+struct kcore_extract {
+	char *kcore_filename;
+	u64 addr;
+	u64 offs;
+	u64 len;
+	char extract_filename[sizeof(PERF_KCORE_EXTRACT)];
+	int fd;
+};
+
+int kcore_extract__create(struct kcore_extract *kce);
+void kcore_extract__delete(struct kcore_extract *kce);
+
+int kcore_copy(const char *from_dir, const char *to_dir);
+int compare_proc_modules(const char *from, const char *to);
+
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index e9e1c03f927d..6681f71f2f95 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -120,42 +120,6 @@ raw_field_value(struct event_format *event, const char *name, void *data)
 	return val;
 }
 
-void *raw_field_ptr(struct event_format *event, const char *name, void *data)
-{
-	struct format_field *field;
-
-	field = pevent_find_any_field(event, name);
-	if (!field)
-		return NULL;
-
-	if (field->flags & FIELD_IS_DYNAMIC) {
-		int offset;
-
-		offset = *(int *)(data + field->offset);
-		offset &= 0xffff;
-
-		return data + offset;
-	}
-
-	return data + field->offset;
-}
-
-int trace_parse_common_type(struct pevent *pevent, void *data)
-{
-	struct pevent_record record;
-
-	record.data = data;
-	return pevent_data_type(pevent, &record);
-}
-
-int trace_parse_common_pid(struct pevent *pevent, void *data)
-{
-	struct pevent_record record;
-
-	record.data = data;
-	return pevent_data_pid(pevent, &record);
-}
-
 unsigned long long read_size(struct event_format *event, void *ptr, int size)
 {
 	return pevent_read_number(event->pevent, ptr, size);
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index fafe1a40444a..04df63114109 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -11,8 +11,6 @@ union perf_event;
 struct perf_tool;
 struct thread;
 
-extern struct pevent *perf_pevent;
-
 int bigendian(void);
 
 struct pevent *read_trace_init(int file_bigendian, int host_bigendian);
@@ -23,26 +21,19 @@ int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size);
 int parse_event_file(struct pevent *pevent,
 		     char *buf, unsigned long size, char *sys);
 
-struct pevent_record *trace_peek_data(struct pevent *pevent, int cpu);
-
 unsigned long long
 raw_field_value(struct event_format *event, const char *name, void *data);
-void *raw_field_ptr(struct event_format *event, const char *name, void *data);
 
 void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size);
 void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size);
 
 ssize_t trace_report(int fd, struct pevent **pevent, bool repipe);
 
-int trace_parse_common_type(struct pevent *pevent, void *data);
-int trace_parse_common_pid(struct pevent *pevent, void *data);
-
 struct event_format *trace_find_next_event(struct pevent *pevent,
 					   struct event_format *event);
 unsigned long long read_size(struct event_format *event, void *ptr, int size);
 unsigned long long eval_flag(const char *flag);
 
-struct pevent_record *trace_read_data(struct pevent *pevent, int cpu);
 int read_tracing_data(int fd, struct list_head *pattrs);
 
 struct tracing_data {
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index cb6bc503a792..ec0c71a2ca2e 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -13,7 +13,7 @@ struct unwind_entry {
 
 typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg);
 
-#ifdef LIBUNWIND_SUPPORT
+#ifdef HAVE_LIBUNWIND_SUPPORT
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			struct machine *machine,
 			struct thread *thread,
@@ -31,5 +31,5 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
 {
 	return 0;
 }
-#endif /* LIBUNWIND_SUPPORT */
+#endif /* HAVE_LIBUNWIND_SUPPORT */
 #endif /* __UNWIND_H */
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 6d17b18e915d..8dc8cf39f4ed 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -1,7 +1,7 @@
 #include "../perf.h"
 #include "util.h"
 #include <sys/mman.h>
-#ifdef BACKTRACE_SUPPORT
+#ifdef HAVE_BACKTRACE_SUPPORT
 #include <execinfo.h>
 #endif
 #include <stdio.h>
@@ -55,17 +55,20 @@ int mkdir_p(char *path, mode_t mode)
 	return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0;
 }
 
-static int slow_copyfile(const char *from, const char *to)
+static int slow_copyfile(const char *from, const char *to, mode_t mode)
 {
-	int err = 0;
+	int err = -1;
 	char *line = NULL;
 	size_t n;
 	FILE *from_fp = fopen(from, "r"), *to_fp;
+	mode_t old_umask;
 
 	if (from_fp == NULL)
 		goto out;
 
+	old_umask = umask(mode ^ 0777);
 	to_fp = fopen(to, "w");
+	umask(old_umask);
 	if (to_fp == NULL)
 		goto out_fclose_from;
 
@@ -82,7 +85,7 @@ out:
 	return err;
 }
 
-int copyfile(const char *from, const char *to)
+int copyfile_mode(const char *from, const char *to, mode_t mode)
 {
 	int fromfd, tofd;
 	struct stat st;
@@ -93,13 +96,13 @@ int copyfile(const char *from, const char *to)
 		goto out;
 
 	if (st.st_size == 0) /* /proc? do it slowly... */
-		return slow_copyfile(from, to);
+		return slow_copyfile(from, to, mode);
 
 	fromfd = open(from, O_RDONLY);
 	if (fromfd < 0)
 		goto out;
 
-	tofd = creat(to, 0755);
+	tofd = creat(to, mode);
 	if (tofd < 0)
 		goto out_close_from;
 
@@ -121,6 +124,11 @@ out:
 	return err;
 }
 
+int copyfile(const char *from, const char *to)
+{
+	return copyfile_mode(from, to, 0755);
+}
+
 unsigned long convert_unit(unsigned long value, char *unit)
 {
 	*unit = ' ';
@@ -204,7 +212,7 @@ int hex2u64(const char *ptr, u64 *long_val)
 }
 
 /* Obtain a backtrace and print it to stdout. */
-#ifdef BACKTRACE_SUPPORT
+#ifdef HAVE_BACKTRACE_SUPPORT
 void dump_stack(void)
 {
 	void *array[16];
@@ -361,3 +369,28 @@ int parse_nsec_time(const char *str, u64 *ptime)
 	*ptime = time_sec * NSEC_PER_SEC + time_nsec;
 	return 0;
 }
+
+unsigned long parse_tag_value(const char *str, struct parse_tag *tags)
+{
+	struct parse_tag *i = tags;
+
+	while (i->tag) {
+		char *s;
+
+		s = strchr(str, i->tag);
+		if (s) {
+			unsigned long int value;
+			char *endptr;
+
+			value = strtoul(str, &endptr, 10);
+			if (s != endptr)
+				break;
+
+			value *= i->mult;
+			return value;
+		}
+		i++;
+	}
+
+	return (unsigned long) -1;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index a53535949043..42dfba70fbfc 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -128,6 +128,8 @@ void put_tracing_file(char *file);
 #endif
 #endif
 
+#define PERF_GTK_DSO  "libperf-gtk.so"
+
 /* General helper functions */
 extern void usage(const char *err) NORETURN;
 extern void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2)));
@@ -241,6 +243,7 @@ static inline int sane_case(int x, int high)
 
 int mkdir_p(char *path, mode_t mode);
 int copyfile(const char *from, const char *to);
+int copyfile_mode(const char *from, const char *to, mode_t mode);
 
 s64 perf_atoll(const char *str);
 char **argv_split(const char *str, int *argcp);
@@ -270,6 +273,13 @@ bool is_power_of_2(unsigned long n)
 	return (n != 0 && ((n & (n - 1)) == 0));
 }
 
+static inline unsigned next_pow2(unsigned x)
+{
+	if (!x)
+		return 1;
+	return 1ULL << (32 - __builtin_clz(x - 1));
+}
+
 size_t hex_width(u64 v);
 int hex2u64(const char *ptr, u64 *val);
 
@@ -281,4 +291,18 @@ void dump_stack(void);
 extern unsigned int page_size;
 
 void get_term_dimensions(struct winsize *ws);
+
+struct parse_tag {
+	char tag;
+	int mult;
+};
+
+unsigned long parse_tag_value(const char *str, struct parse_tag *tags);
+
+#define SRCLINE_UNKNOWN  ((char *) "??:0")
+
+struct dso;
+
+char *get_srcline(struct dso *dso, unsigned long addr);
+void free_srcline(char *srcline);
 #endif /* GIT_COMPAT_UTIL_H */