Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "The main changes in this cycle were:

  Kernel:

   - kprobes updates: use better W^X patterns for code modifications,
     improve optprobes, remove jprobes. (Masami Hiramatsu, Kees Cook)

   - core fixes: event timekeeping (enabled/running times statistics)
     fixes, perf_event_read() locking fixes and cleanups, etc. (Peter
     Zijlstra)

   - Extend x86 Intel free-running PEBS support and support x86
     user-register sampling in perf record and perf script. (Andi Kleen)

  Tooling:

   - Completely rework the way inline frames are handled. Instead of
     querying for the inline nodes on-demand in the individual tools, we
     now create proper callchain nodes for inlined frames. (Milian
     Wolff)

   - 'perf trace' updates (Arnaldo Carvalho de Melo)

   - Implement a way to print formatted output to per-event files in
     'perf script' to facilitate generate flamegraphs, elliminating the
     need to write scripts to do that separation (yuzhoujian, Arnaldo
     Carvalho de Melo)

   - Update vendor events JSON metrics for Intel's Broadwell, Broadwell
     Server, Haswell, Haswell Server, IvyBridge, IvyTown, JakeTown,
     Sandy Bridge, Skylake, SkyLake Server - and Goldmont Plus V1 (Andi
     Kleen, Kan Liang)

   - Multithread the synthesizing of PERF_RECORD_ events for
     pre-existing threads in 'perf top', speeding up that phase, greatly
     improving the user experience in systems such as Intel's Knights
     Mill (Kan Liang)

   - Introduce the concept of weak groups in 'perf stat': try to set up
     a group, but if it's not schedulable fallback to not using a group.
     That gives us the best of both worlds: groups if they work, but
     still a usable fallback if they don't. E.g: (Andi Kleen)

   - perf sched timehist enhancements (David Ahern)

   - ... various other enhancements, updates, cleanups and fixes"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (139 commits)
  kprobes: Don't spam the build log with deprecation warnings
  arm/kprobes: Remove jprobe test case
  arm/kprobes: Fix kretprobe test to check correct counter
  perf srcline: Show correct function name for srcline of callchains
  perf srcline: Fix memory leak in addr2inlines()
  perf trace beauty kcmp: Beautify arguments
  perf trace beauty: Implement pid_fd beautifier
  tools include uapi: Grab a copy of linux/kcmp.h
  perf callchain: Fix double mapping al->addr for children without self period
  perf stat: Make --per-thread update shadow stats to show metrics
  perf stat: Move the shadow stats scale computation in perf_stat__update_shadow_stats
  perf tools: Add perf_data_file__write function
  perf tools: Add struct perf_data_file
  perf tools: Rename struct perf_data_file to perf_data
  perf script: Print information about per-event-dump files
  perf trace beauty prctl: Generate 'option' string table from kernel headers
  tools include uapi: Grab a copy of linux/prctl.h
  perf script: Allow creating per-event dump files
  perf evsel: Restore evsel->priv as a tool private area
  perf script: Use event_format__fprintf()
  ...

68 files changed, 2240 insertions, 917 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 94518c1bf8b6..a3de7916fe63 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -13,6 +13,7 @@ libperf-y += find_bit.o
 libperf-y += kallsyms.o
 libperf-y += levenshtein.o
 libperf-y += llvm-utils.o
+libperf-y += mmap.o
 libperf-y += memswap.o
 libperf-y += parse-events.o
 libperf-y += perf_regs.o
@@ -34,6 +35,7 @@ libperf-y += dso.o
 libperf-y += symbol.o
 libperf-y += symbol_fprintf.o
 libperf-y += color.o
+libperf-y += metricgroup.o
 libperf-y += header.o
 libperf-y += callchain.o
 libperf-y += values.o
@@ -78,6 +80,7 @@ libperf-y += data.o
 libperf-y += tsc.o
 libperf-y += cloexec.o
 libperf-y += call-path.o
+libperf-y += rwsem.o
 libperf-y += thread-stack.o
 libperf-$(CONFIG_AUXTRACE) += auxtrace.o
 libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index aa66791b1bfc..da1c4c4a0dd8 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -49,10 +49,9 @@ struct arch {
 	void		*priv;
 	unsigned int	model;
 	unsigned int	family;
-	int		(*init)(struct arch *arch);
+	int		(*init)(struct arch *arch, char *cpuid);
 	bool		(*ins_is_fused)(struct arch *arch, const char *ins1,
 					const char *ins2);
-	int		(*cpuid_parse)(struct arch *arch, char *cpuid);
 	struct		{
 		char comment_char;
 		char skip_functions_char;
@@ -132,10 +131,10 @@ static struct arch architectures[] = {
 	},
 	{
 		.name = "x86",
+		.init = x86__annotate_init,
 		.instructions = x86__instructions,
 		.nr_instructions = ARRAY_SIZE(x86__instructions),
 		.ins_is_fused = x86__ins_is_fused,
-		.cpuid_parse = x86__cpuid_parse,
 		.objdump =  {
 			.comment_char = '#',
 		},
@@ -1457,16 +1456,13 @@ int symbol__disassemble(struct symbol *sym, struct map *map,
 		*parch = arch;
 
 	if (arch->init) {
-		err = arch->init(arch);
+		err = arch->init(arch, cpuid);
 		if (err) {
 			pr_err("%s: failed to initialize %s arch priv area\n", __func__, arch->name);
 			return err;
 		}
 	}
 
-	if (arch->cpuid_parse && cpuid)
-		arch->cpuid_parse(arch, cpuid);
-
 	pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
 		 symfs_filename, sym->name, map->unmap_ip(map, sym->start),
 		 map->unmap_ip(map, sym->end));
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 5547457566a7..a33491416400 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -208,7 +208,7 @@ static int auxtrace_queues__grow(struct auxtrace_queues *queues,
 
 static void *auxtrace_copy_data(u64 size, struct perf_session *session)
 {
-	int fd = perf_data_file__fd(session->file);
+	int fd = perf_data__fd(session->data);
 	void *p;
 	ssize_t ret;
 
@@ -305,7 +305,7 @@ static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues,
 	if (session->one_mmap) {
 		buffer->data = buffer->data_offset - session->one_mmap_offset +
 			       session->one_mmap_addr;
-	} else if (perf_data_file__is_pipe(session->file)) {
+	} else if (perf_data__is_pipe(session->data)) {
 		buffer->data = auxtrace_copy_data(buffer->size, session);
 		if (!buffer->data)
 			return -ENOMEM;
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 6031933d811c..082505d08d72 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -567,6 +567,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 		call->ip = cursor_node->ip;
 		call->ms.sym = cursor_node->sym;
 		call->ms.map = map__get(cursor_node->map);
+		call->srcline = cursor_node->srcline;
 
 		if (cursor_node->branch) {
 			call->branch_count = 1;
@@ -645,103 +646,120 @@ enum match_result {
 	MATCH_GT,
 };
 
-static enum match_result match_chain_srcline(struct callchain_cursor_node *node,
-					     struct callchain_list *cnode)
+static enum match_result match_chain_strings(const char *left,
+					     const char *right)
 {
-	char *left = NULL;
-	char *right = NULL;
 	enum match_result ret = MATCH_EQ;
 	int cmp;
 
-	if (cnode->ms.map)
-		left = get_srcline(cnode->ms.map->dso,
-				 map__rip_2objdump(cnode->ms.map, cnode->ip),
-				 cnode->ms.sym, true, false);
-	if (node->map)
-		right = get_srcline(node->map->dso,
-				  map__rip_2objdump(node->map, node->ip),
-				  node->sym, true, false);
-
 	if (left && right)
 		cmp = strcmp(left, right);
 	else if (!left && right)
 		cmp = 1;
 	else if (left && !right)
 		cmp = -1;
-	else if (cnode->ip == node->ip)
-		cmp = 0;
 	else
-		cmp = (cnode->ip < node->ip) ? -1 : 1;
+		return MATCH_ERROR;
 
 	if (cmp != 0)
 		ret = cmp < 0 ? MATCH_LT : MATCH_GT;
 
-	free_srcline(left);
-	free_srcline(right);
 	return ret;
 }
 
+/*
+ * We need to always use relative addresses because we're aggregating
+ * callchains from multiple threads, i.e. different address spaces, so
+ * comparing absolute addresses make no sense as a symbol in a DSO may end up
+ * in a different address when used in a different binary or even the same
+ * binary but with some sort of address randomization technique, thus we need
+ * to compare just relative addresses. -acme
+ */
+static enum match_result match_chain_dso_addresses(struct map *left_map, u64 left_ip,
+						   struct map *right_map, u64 right_ip)
+{
+	struct dso *left_dso = left_map ? left_map->dso : NULL;
+	struct dso *right_dso = right_map ? right_map->dso : NULL;
+
+	if (left_dso != right_dso)
+		return left_dso < right_dso ? MATCH_LT : MATCH_GT;
+
+	if (left_ip != right_ip)
+ 		return left_ip < right_ip ? MATCH_LT : MATCH_GT;
+
+	return MATCH_EQ;
+}
+
 static enum match_result match_chain(struct callchain_cursor_node *node,
 				     struct callchain_list *cnode)
 {
-	struct symbol *sym = node->sym;
-	u64 left, right;
-	struct dso *left_dso = NULL;
-	struct dso *right_dso = NULL;
-
-	if (callchain_param.key == CCKEY_SRCLINE) {
-		enum match_result match = match_chain_srcline(node, cnode);
+	enum match_result match = MATCH_ERROR;
 
+	switch (callchain_param.key) {
+	case CCKEY_SRCLINE:
+		match = match_chain_strings(cnode->srcline, node->srcline);
 		if (match != MATCH_ERROR)
-			return match;
-	}
-
-	if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) {
-		left = cnode->ms.sym->start;
-		right = sym->start;
-		left_dso = cnode->ms.map->dso;
-		right_dso = node->map->dso;
-	} else {
-		left = cnode->ip;
-		right = node->ip;
+			break;
+		/* otherwise fall-back to symbol-based comparison below */
+		__fallthrough;
+	case CCKEY_FUNCTION:
+		if (node->sym && cnode->ms.sym) {
+			/*
+			 * Compare inlined frames based on their symbol name
+			 * because different inlined frames will have the same
+			 * symbol start. Otherwise do a faster comparison based
+			 * on the symbol start address.
+			 */
+			if (cnode->ms.sym->inlined || node->sym->inlined) {
+				match = match_chain_strings(cnode->ms.sym->name,
+							    node->sym->name);
+				if (match != MATCH_ERROR)
+					break;
+			} else {
+				match = match_chain_dso_addresses(cnode->ms.map, cnode->ms.sym->start,
+								  node->map, node->sym->start);
+				break;
+			}
+		}
+		/* otherwise fall-back to IP-based comparison below */
+		__fallthrough;
+	case CCKEY_ADDRESS:
+	default:
+		match = match_chain_dso_addresses(cnode->ms.map, cnode->ip, node->map, node->ip);
+		break;
 	}
 
-	if (left == right && left_dso == right_dso) {
-		if (node->branch) {
-			cnode->branch_count++;
+	if (match == MATCH_EQ && node->branch) {
+		cnode->branch_count++;
 
-			if (node->branch_from) {
-				/*
-				 * It's "to" of a branch
-				 */
-				cnode->brtype_stat.branch_to = true;
+		if (node->branch_from) {
+			/*
+			 * It's "to" of a branch
+			 */
+			cnode->brtype_stat.branch_to = true;
 
-				if (node->branch_flags.predicted)
-					cnode->predicted_count++;
+			if (node->branch_flags.predicted)
+				cnode->predicted_count++;
 
-				if (node->branch_flags.abort)
-					cnode->abort_count++;
+			if (node->branch_flags.abort)
+				cnode->abort_count++;
 
-				branch_type_count(&cnode->brtype_stat,
-						  &node->branch_flags,
-						  node->branch_from,
-						  node->ip);
-			} else {
-				/*
-				 * It's "from" of a branch
-				 */
-				cnode->brtype_stat.branch_to = false;
-				cnode->cycles_count +=
-					node->branch_flags.cycles;
-				cnode->iter_count += node->nr_loop_iter;
-				cnode->iter_cycles += node->iter_cycles;
-			}
+			branch_type_count(&cnode->brtype_stat,
+					  &node->branch_flags,
+					  node->branch_from,
+					  node->ip);
+		} else {
+			/*
+			 * It's "from" of a branch
+			 */
+			cnode->brtype_stat.branch_to = false;
+			cnode->cycles_count += node->branch_flags.cycles;
+			cnode->iter_count += node->nr_loop_iter;
+			cnode->iter_cycles += node->iter_cycles;
 		}
-
-		return MATCH_EQ;
 	}
 
-	return left > right ? MATCH_GT : MATCH_LT;
+	return match;
 }
 
 /*
@@ -970,7 +988,7 @@ merge_chain_branch(struct callchain_cursor *cursor,
 	list_for_each_entry_safe(list, next_list, &src->val, list) {
 		callchain_cursor_append(cursor, list->ip,
 					list->ms.map, list->ms.sym,
-					false, NULL, 0, 0, 0);
+					false, NULL, 0, 0, 0, list->srcline);
 		list_del(&list->list);
 		map__zput(list->ms.map);
 		free(list);
@@ -1010,7 +1028,8 @@ int callchain_merge(struct callchain_cursor *cursor,
 int callchain_cursor_append(struct callchain_cursor *cursor,
 			    u64 ip, struct map *map, struct symbol *sym,
 			    bool branch, struct branch_flags *flags,
-			    int nr_loop_iter, u64 iter_cycles, u64 branch_from)
+			    int nr_loop_iter, u64 iter_cycles, u64 branch_from,
+			    const char *srcline)
 {
 	struct callchain_cursor_node *node = *cursor->last;
 
@@ -1029,6 +1048,7 @@ int callchain_cursor_append(struct callchain_cursor *cursor,
 	node->branch = branch;
 	node->nr_loop_iter = nr_loop_iter;
 	node->iter_cycles = iter_cycles;
+	node->srcline = srcline;
 
 	if (flags)
 		memcpy(&node->branch_flags, flags,
@@ -1071,10 +1091,8 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *
 {
 	al->map = node->map;
 	al->sym = node->sym;
-	if (node->map)
-		al->addr = node->map->map_ip(node->map, node->ip);
-	else
-		al->addr = node->ip;
+	al->srcline = node->srcline;
+	al->addr = node->ip;
 
 	if (al->sym == NULL) {
 		if (hide_unresolved)
@@ -1116,16 +1134,15 @@ char *callchain_list__sym_name(struct callchain_list *cl,
 	int printed;
 
 	if (cl->ms.sym) {
-		if (show_srcline && cl->ms.map && !cl->srcline)
-			cl->srcline = get_srcline(cl->ms.map->dso,
-						  map__rip_2objdump(cl->ms.map,
-								    cl->ip),
-						  cl->ms.sym, false, show_addr);
-		if (cl->srcline)
-			printed = scnprintf(bf, bfsize, "%s %s",
-					cl->ms.sym->name, cl->srcline);
+		const char *inlined = cl->ms.sym->inlined ? " (inlined)" : "";
+
+		if (show_srcline && cl->srcline)
+			printed = scnprintf(bf, bfsize, "%s %s%s",
+					    cl->ms.sym->name, cl->srcline,
+					    inlined);
 		else
-			printed = scnprintf(bf, bfsize, "%s", cl->ms.sym->name);
+			printed = scnprintf(bf, bfsize, "%s%s",
+					    cl->ms.sym->name, inlined);
 	} else
 		printed = scnprintf(bf, bfsize, "%#" PRIx64, cl->ip);
 
@@ -1533,7 +1550,7 @@ int callchain_cursor__copy(struct callchain_cursor *dst,
 					     node->branch, &node->branch_flags,
 					     node->nr_loop_iter,
 					     node->iter_cycles,
-					     node->branch_from);
+					     node->branch_from, node->srcline);
 		if (rc)
 			break;
 
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index f967aa47d0a1..b79ef2478a57 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -122,7 +122,7 @@ struct callchain_list {
 	u64			iter_count;
 	u64			iter_cycles;
 	struct branch_type_stat brtype_stat;
-	char		       *srcline;
+	const char		*srcline;
 	struct list_head	list;
 };
 
@@ -136,6 +136,7 @@ struct callchain_cursor_node {
 	u64				ip;
 	struct map			*map;
 	struct symbol			*sym;
+	const char			*srcline;
 	bool				branch;
 	struct branch_flags		branch_flags;
 	u64				branch_from;
@@ -202,7 +203,8 @@ static inline void callchain_cursor_reset(struct callchain_cursor *cursor)
 int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
 			    struct map *map, struct symbol *sym,
 			    bool branch, struct branch_flags *flags,
-			    int nr_loop_iter, u64 iter_cycles, u64 branch_from);
+			    int nr_loop_iter, u64 iter_cycles, u64 branch_from,
+			    const char *srcline);
 
 /* Close a cursor writing session. Initialize for the reader */
 static inline void callchain_cursor_commit(struct callchain_cursor *cursor)
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index 8808570f8e9c..7798a2cc8a86 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -6,6 +6,7 @@
 #include <stdio.h>
 #include <string.h>
 #include <linux/refcount.h>
+#include "rwsem.h"
 
 struct comm_str {
 	char *str;
@@ -15,6 +16,7 @@ struct comm_str {
 
 /* Should perhaps be moved to struct machine */
 static struct rb_root comm_str_root;
+static struct rw_semaphore comm_str_lock = {.lock = PTHREAD_RWLOCK_INITIALIZER,};
 
 static struct comm_str *comm_str__get(struct comm_str *cs)
 {
@@ -26,7 +28,9 @@ static struct comm_str *comm_str__get(struct comm_str *cs)
 static void comm_str__put(struct comm_str *cs)
 {
 	if (cs && refcount_dec_and_test(&cs->refcnt)) {
+		down_write(&comm_str_lock);
 		rb_erase(&cs->rb_node, &comm_str_root);
+		up_write(&comm_str_lock);
 		zfree(&cs->str);
 		free(cs);
 	}
@@ -51,7 +55,8 @@ static struct comm_str *comm_str__alloc(const char *str)
 	return cs;
 }
 
-static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root)
+static
+struct comm_str *__comm_str__findnew(const char *str, struct rb_root *root)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
@@ -82,6 +87,17 @@ static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root)
 	return new;
 }
 
+static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root)
+{
+	struct comm_str *cs;
+
+	down_write(&comm_str_lock);
+	cs = __comm_str__findnew(str, root);
+	up_write(&comm_str_lock);
+
+	return cs;
+}
+
 struct comm *comm__new(const char *str, u64 timestamp, bool exec)
 {
 	struct comm *comm = zalloc(sizeof(*comm));
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 4b893c622236..84eb9393c7db 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -701,10 +701,7 @@ struct perf_config_set *perf_config_set__new(void)
 
 	if (set) {
 		INIT_LIST_HEAD(&set->sections);
-		if (perf_config_set__init(set) < 0) {
-			perf_config_set__delete(set);
-			set = NULL;
-		}
+		perf_config_set__init(set);
 	}
 
 	return set;
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 2346cecb8ea2..5744c12641a5 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -1577,10 +1577,10 @@ int bt_convert__perf2ctf(const char *input, const char *path,
 			 struct perf_data_convert_opts *opts)
 {
 	struct perf_session *session;
-	struct perf_data_file file = {
-		.path = input,
-		.mode = PERF_DATA_MODE_READ,
-		.force = opts->force,
+	struct perf_data data = {
+		.file.path = input,
+		.mode      = PERF_DATA_MODE_READ,
+		.force     = opts->force,
 	};
 	struct convert c = {
 		.tool = {
@@ -1619,7 +1619,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
 
 	err = -1;
 	/* perf.data session */
-	session = perf_session__new(&file, 0, &c.tool);
+	session = perf_session__new(&data, 0, &c.tool);
 	if (!session)
 		goto free_writer;
 
@@ -1650,7 +1650,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
 
 	fprintf(stderr,
 		"[ perf data convert: Converted '%s' into CTF data '%s' ]\n",
-		file.path, path);
+		data.file.path, path);
 
 	fprintf(stderr,
 		"[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples",
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 79192758bdb3..48094fde0a68 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -4,6 +4,7 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <errno.h>
+#include <fcntl.h>
 #include <unistd.h>
 #include <string.h>
 
@@ -21,56 +22,56 @@
 #endif
 #endif
 
-static bool check_pipe(struct perf_data_file *file)
+static bool check_pipe(struct perf_data *data)
 {
 	struct stat st;
 	bool is_pipe = false;
-	int fd = perf_data_file__is_read(file) ?
+	int fd = perf_data__is_read(data) ?
 		 STDIN_FILENO : STDOUT_FILENO;
 
-	if (!file->path) {
+	if (!data->file.path) {
 		if (!fstat(fd, &st) && S_ISFIFO(st.st_mode))
 			is_pipe = true;
 	} else {
-		if (!strcmp(file->path, "-"))
+		if (!strcmp(data->file.path, "-"))
 			is_pipe = true;
 	}
 
 	if (is_pipe)
-		file->fd = fd;
+		data->file.fd = fd;
 
-	return file->is_pipe = is_pipe;
+	return data->is_pipe = is_pipe;
 }
 
-static int check_backup(struct perf_data_file *file)
+static int check_backup(struct perf_data *data)
 {
 	struct stat st;
 
-	if (!stat(file->path, &st) && st.st_size) {
+	if (!stat(data->file.path, &st) && st.st_size) {
 		/* TODO check errors properly */
 		char oldname[PATH_MAX];
 		snprintf(oldname, sizeof(oldname), "%s.old",
-			 file->path);
+			 data->file.path);
 		unlink(oldname);
-		rename(file->path, oldname);
+		rename(data->file.path, oldname);
 	}
 
 	return 0;
 }
 
-static int open_file_read(struct perf_data_file *file)
+static int open_file_read(struct perf_data *data)
 {
 	struct stat st;
 	int fd;
 	char sbuf[STRERR_BUFSIZE];
 
-	fd = open(file->path, O_RDONLY);
+	fd = open(data->file.path, O_RDONLY);
 	if (fd < 0) {
 		int err = errno;
 
-		pr_err("failed to open %s: %s", file->path,
+		pr_err("failed to open %s: %s", data->file.path,
 			str_error_r(err, sbuf, sizeof(sbuf)));
-		if (err == ENOENT && !strcmp(file->path, "perf.data"))
+		if (err == ENOENT && !strcmp(data->file.path, "perf.data"))
 			pr_err("  (try 'perf record' first)");
 		pr_err("\n");
 		return -err;
@@ -79,19 +80,19 @@ static int open_file_read(struct perf_data_file *file)
 	if (fstat(fd, &st) < 0)
 		goto out_close;
 
-	if (!file->force && st.st_uid && (st.st_uid != geteuid())) {
+	if (!data->force && st.st_uid && (st.st_uid != geteuid())) {
 		pr_err("File %s not owned by current user or root (use -f to override)\n",
-		       file->path);
+		       data->file.path);
 		goto out_close;
 	}
 
 	if (!st.st_size) {
-		pr_info("zero-sized file (%s), nothing to do!\n",
-			file->path);
+		pr_info("zero-sized data (%s), nothing to do!\n",
+			data->file.path);
 		goto out_close;
 	}
 
-	file->size = st.st_size;
+	data->size = st.st_size;
 	return fd;
 
  out_close:
@@ -99,49 +100,49 @@ static int open_file_read(struct perf_data_file *file)
 	return -1;
 }
 
-static int open_file_write(struct perf_data_file *file)
+static int open_file_write(struct perf_data *data)
 {
 	int fd;
 	char sbuf[STRERR_BUFSIZE];
 
-	if (check_backup(file))
+	if (check_backup(data))
 		return -1;
 
-	fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC|O_CLOEXEC,
+	fd = open(data->file.path, O_CREAT|O_RDWR|O_TRUNC|O_CLOEXEC,
 		  S_IRUSR|S_IWUSR);
 
 	if (fd < 0)
-		pr_err("failed to open %s : %s\n", file->path,
+		pr_err("failed to open %s : %s\n", data->file.path,
 			str_error_r(errno, sbuf, sizeof(sbuf)));
 
 	return fd;
 }
 
-static int open_file(struct perf_data_file *file)
+static int open_file(struct perf_data *data)
 {
 	int fd;
 
-	fd = perf_data_file__is_read(file) ?
-	     open_file_read(file) : open_file_write(file);
+	fd = perf_data__is_read(data) ?
+	     open_file_read(data) : open_file_write(data);
 
-	file->fd = fd;
+	data->file.fd = fd;
 	return fd < 0 ? -1 : 0;
 }
 
-int perf_data_file__open(struct perf_data_file *file)
+int perf_data__open(struct perf_data *data)
 {
-	if (check_pipe(file))
+	if (check_pipe(data))
 		return 0;
 
-	if (!file->path)
-		file->path = "perf.data";
+	if (!data->file.path)
+		data->file.path = "perf.data";
 
-	return open_file(file);
+	return open_file(data);
 }
 
-void perf_data_file__close(struct perf_data_file *file)
+void perf_data__close(struct perf_data *data)
 {
-	close(file->fd);
+	close(data->file.fd);
 }
 
 ssize_t perf_data_file__write(struct perf_data_file *file,
@@ -150,42 +151,48 @@ ssize_t perf_data_file__write(struct perf_data_file *file,
 	return writen(file->fd, buf, size);
 }
 
-int perf_data_file__switch(struct perf_data_file *file,
+ssize_t perf_data__write(struct perf_data *data,
+			      void *buf, size_t size)
+{
+	return perf_data_file__write(&data->file, buf, size);
+}
+
+int perf_data__switch(struct perf_data *data,
 			   const char *postfix,
 			   size_t pos, bool at_exit)
 {
 	char *new_filepath;
 	int ret;
 
-	if (check_pipe(file))
+	if (check_pipe(data))
 		return -EINVAL;
-	if (perf_data_file__is_read(file))
+	if (perf_data__is_read(data))
 		return -EINVAL;
 
-	if (asprintf(&new_filepath, "%s.%s", file->path, postfix) < 0)
+	if (asprintf(&new_filepath, "%s.%s", data->file.path, postfix) < 0)
 		return -ENOMEM;
 
 	/*
 	 * Only fire a warning, don't return error, continue fill
 	 * original file.
 	 */
-	if (rename(file->path, new_filepath))
-		pr_warning("Failed to rename %s to %s\n", file->path, new_filepath);
+	if (rename(data->file.path, new_filepath))
+		pr_warning("Failed to rename %s to %s\n", data->file.path, new_filepath);
 
 	if (!at_exit) {
-		close(file->fd);
-		ret = perf_data_file__open(file);
+		close(data->file.fd);
+		ret = perf_data__open(data);
 		if (ret < 0)
 			goto out;
 
-		if (lseek(file->fd, pos, SEEK_SET) == (off_t)-1) {
+		if (lseek(data->file.fd, pos, SEEK_SET) == (off_t)-1) {
 			ret = -errno;
 			pr_debug("Failed to lseek to %zu: %s",
 				 pos, strerror(errno));
 			goto out;
 		}
 	}
-	ret = file->fd;
+	ret = data->file.fd;
 out:
 	free(new_filepath);
 	return ret;
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index 80241ba78101..4828f7feea89 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -10,51 +10,57 @@ enum perf_data_mode {
 };
 
 struct perf_data_file {
-	const char		*path;
-	int			 fd;
+	const char	*path;
+	int		 fd;
+};
+
+struct perf_data {
+	struct perf_data_file	 file;
 	bool			 is_pipe;
 	bool			 force;
 	unsigned long		 size;
 	enum perf_data_mode	 mode;
 };
 
-static inline bool perf_data_file__is_read(struct perf_data_file *file)
+static inline bool perf_data__is_read(struct perf_data *data)
 {
-	return file->mode == PERF_DATA_MODE_READ;
+	return data->mode == PERF_DATA_MODE_READ;
 }
 
-static inline bool perf_data_file__is_write(struct perf_data_file *file)
+static inline bool perf_data__is_write(struct perf_data *data)
 {
-	return file->mode == PERF_DATA_MODE_WRITE;
+	return data->mode == PERF_DATA_MODE_WRITE;
 }
 
-static inline int perf_data_file__is_pipe(struct perf_data_file *file)
+static inline int perf_data__is_pipe(struct perf_data *data)
 {
-	return file->is_pipe;
+	return data->is_pipe;
 }
 
-static inline int perf_data_file__fd(struct perf_data_file *file)
+static inline int perf_data__fd(struct perf_data *data)
 {
-	return file->fd;
+	return data->file.fd;
 }
 
-static inline unsigned long perf_data_file__size(struct perf_data_file *file)
+static inline unsigned long perf_data__size(struct perf_data *data)
 {
-	return file->size;
+	return data->size;
 }
 
-int perf_data_file__open(struct perf_data_file *file);
-void perf_data_file__close(struct perf_data_file *file);
+int perf_data__open(struct perf_data *data);
+void perf_data__close(struct perf_data *data);
+ssize_t perf_data__write(struct perf_data *data,
+			      void *buf, size_t size);
 ssize_t perf_data_file__write(struct perf_data_file *file,
 			      void *buf, size_t size);
 /*
  * If at_exit is set, only rename current perf.data to
- * perf.data.<postfix>, continue write on original file.
+ * perf.data.<postfix>, continue write on original data.
  * Set at_exit when flushing the last output.
  *
  * Return value is fd of new output.
  */
-int perf_data_file__switch(struct perf_data_file *file,
+int perf_data__switch(struct perf_data *data,
 			   const char *postfix,
 			   size_t pos, bool at_exit);
 #endif /* __PERF_DATA_H */
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index dc8b53b6950e..f3a71db83947 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -112,50 +112,53 @@ int dump_printf(const char *fmt, ...)
 	return ret;
 }
 
-static void trace_event_printer(enum binary_printer_ops op,
-				unsigned int val, void *extra)
+static int trace_event_printer(enum binary_printer_ops op,
+			       unsigned int val, void *extra, FILE *fp)
 {
 	const char *color = PERF_COLOR_BLUE;
 	union perf_event *event = (union perf_event *)extra;
 	unsigned char ch = (unsigned char)val;
+	int printed = 0;
 
 	switch (op) {
 	case BINARY_PRINT_DATA_BEGIN:
-		printf(".");
-		color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n",
-				event->header.size);
+		printed += fprintf(fp, ".");
+		printed += color_fprintf(fp, color, "\n. ... raw event: size %d bytes\n",
+					 event->header.size);
 		break;
 	case BINARY_PRINT_LINE_BEGIN:
-		printf(".");
+		printed += fprintf(fp, ".");
 		break;
 	case BINARY_PRINT_ADDR:
-		color_fprintf(stdout, color, "  %04x: ", val);
+		printed += color_fprintf(fp, color, "  %04x: ", val);
 		break;
 	case BINARY_PRINT_NUM_DATA:
-		color_fprintf(stdout, color, " %02x", val);
+		printed += color_fprintf(fp, color, " %02x", val);
 		break;
 	case BINARY_PRINT_NUM_PAD:
-		color_fprintf(stdout, color, "   ");
+		printed += color_fprintf(fp, color, "   ");
 		break;
 	case BINARY_PRINT_SEP:
-		color_fprintf(stdout, color, "  ");
+		printed += color_fprintf(fp, color, "  ");
 		break;
 	case BINARY_PRINT_CHAR_DATA:
-		color_fprintf(stdout, color, "%c",
+		printed += color_fprintf(fp, color, "%c",
 			      isprint(ch) ? ch : '.');
 		break;
 	case BINARY_PRINT_CHAR_PAD:
-		color_fprintf(stdout, color, " ");
+		printed += color_fprintf(fp, color, " ");
 		break;
 	case BINARY_PRINT_LINE_END:
-		color_fprintf(stdout, color, "\n");
+		printed += color_fprintf(fp, color, "\n");
 		break;
 	case BINARY_PRINT_DATA_END:
-		printf("\n");
+		printed += fprintf(fp, "\n");
 		break;
 	default:
 		break;
 	}
+
+	return printed;
 }
 
 void trace_event(union perf_event *event)
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 00c98c968cb1..d5b6f7f5baff 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -7,9 +7,11 @@
 #include <sys/stat.h>
 #include <unistd.h>
 #include <errno.h>
+#include <fcntl.h>
 #include "compress.h"
 #include "path.h"
 #include "symbol.h"
+#include "srcline.h"
 #include "dso.h"
 #include "machine.h"
 #include "auxtrace.h"
@@ -1201,6 +1203,8 @@ struct dso *dso__new(const char *name)
 		for (i = 0; i < MAP__NR_TYPES; ++i)
 			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
 		dso->data.cache = RB_ROOT;
+		dso->inlined_nodes = RB_ROOT;
+		dso->srclines = RB_ROOT;
 		dso->data.fd = -1;
 		dso->data.status = DSO_DATA_STATUS_UNKNOWN;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
@@ -1232,6 +1236,10 @@ void dso__delete(struct dso *dso)
 	if (!RB_EMPTY_NODE(&dso->rb_node))
 		pr_err("DSO %s is still in rbtree when being deleted!\n",
 		       dso->long_name);
+
+	/* free inlines first, as they reference symbols */
+	inlines__tree_delete(&dso->inlined_nodes);
+	srcline__tree_delete(&dso->srclines);
 	for (i = 0; i < MAP__NR_TYPES; ++i)
 		symbols__delete(&dso->symbols[i]);
 
@@ -1366,9 +1374,9 @@ void __dsos__add(struct dsos *dsos, struct dso *dso)
 
 void dsos__add(struct dsos *dsos, struct dso *dso)
 {
-	pthread_rwlock_wrlock(&dsos->lock);
+	down_write(&dsos->lock);
 	__dsos__add(dsos, dso);
-	pthread_rwlock_unlock(&dsos->lock);
+	up_write(&dsos->lock);
 }
 
 struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
@@ -1387,9 +1395,9 @@ struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
 struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
 {
 	struct dso *dso;
-	pthread_rwlock_rdlock(&dsos->lock);
+	down_read(&dsos->lock);
 	dso = __dsos__find(dsos, name, cmp_short);
-	pthread_rwlock_unlock(&dsos->lock);
+	up_read(&dsos->lock);
 	return dso;
 }
 
@@ -1416,9 +1424,9 @@ struct dso *__dsos__findnew(struct dsos *dsos, const char *name)
 struct dso *dsos__findnew(struct dsos *dsos, const char *name)
 {
 	struct dso *dso;
-	pthread_rwlock_wrlock(&dsos->lock);
+	down_write(&dsos->lock);
 	dso = dso__get(__dsos__findnew(dsos, name));
-	pthread_rwlock_unlock(&dsos->lock);
+	up_write(&dsos->lock);
 	return dso;
 }
 
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 926ff2e7f668..c229dbe0277a 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -7,7 +7,7 @@
 #include <linux/rbtree.h>
 #include <sys/types.h>
 #include <stdbool.h>
-#include <pthread.h>
+#include "rwsem.h"
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include "map.h"
@@ -130,7 +130,7 @@ struct dso_cache {
 struct dsos {
 	struct list_head head;
 	struct rb_root	 root;	/* rbtree root sorted by long name */
-	pthread_rwlock_t lock;
+	struct rw_semaphore lock;
 };
 
 struct auxtrace_cache;
@@ -142,6 +142,8 @@ struct dso {
 	struct rb_root	 *root;		/* root of rbtree that rb_node is in */
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
+	struct rb_root	 inlined_nodes;
+	struct rb_root	 srclines;
 	struct {
 		u64		addr;
 		struct symbol	*symbol;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index fc690fecbfd6..97a8ef9980db 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <dirent.h>
 #include <errno.h>
+#include <fcntl.h>
 #include <inttypes.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -678,21 +679,21 @@ out:
 	return err;
 }
 
-int perf_event__synthesize_threads(struct perf_tool *tool,
-				   perf_event__handler_t process,
-				   struct machine *machine,
-				   bool mmap_data,
-				   unsigned int proc_map_timeout)
+static int __perf_event__synthesize_threads(struct perf_tool *tool,
+					    perf_event__handler_t process,
+					    struct machine *machine,
+					    bool mmap_data,
+					    unsigned int proc_map_timeout,
+					    struct dirent **dirent,
+					    int start,
+					    int num)
 {
-	DIR *proc;
-	char proc_path[PATH_MAX];
-	struct dirent *dirent;
 	union perf_event *comm_event, *mmap_event, *fork_event;
 	union perf_event *namespaces_event;
 	int err = -1;
-
-	if (machine__is_default_guest(machine))
-		return 0;
+	char *end;
+	pid_t pid;
+	int i;
 
 	comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
 	if (comm_event == NULL)
@@ -712,31 +713,25 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	if (namespaces_event == NULL)
 		goto out_free_fork;
 
-	snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
-	proc = opendir(proc_path);
-
-	if (proc == NULL)
-		goto out_free_namespaces;
-
-	while ((dirent = readdir(proc)) != NULL) {
-		char *end;
-		pid_t pid = strtol(dirent->d_name, &end, 10);
+	for (i = start; i < start + num; i++) {
+		if (!isdigit(dirent[i]->d_name[0]))
+			continue;
 
-		if (*end) /* only interested in proper numerical dirents */
+		pid = (pid_t)strtol(dirent[i]->d_name, &end, 10);
+		/* only interested in proper numerical dirents */
+		if (*end)
 			continue;
 		/*
- 		 * We may race with exiting thread, so don't stop just because
- 		 * one thread couldn't be synthesized.
- 		 */
+		 * We may race with exiting thread, so don't stop just because
+		 * one thread couldn't be synthesized.
+		 */
 		__event__synthesize_thread(comm_event, mmap_event, fork_event,
 					   namespaces_event, pid, 1, process,
 					   tool, machine, mmap_data,
 					   proc_map_timeout);
 	}
-
 	err = 0;
-	closedir(proc);
-out_free_namespaces:
+
 	free(namespaces_event);
 out_free_fork:
 	free(fork_event);
@@ -748,6 +743,118 @@ out:
 	return err;
 }
 
+struct synthesize_threads_arg {
+	struct perf_tool *tool;
+	perf_event__handler_t process;
+	struct machine *machine;
+	bool mmap_data;
+	unsigned int proc_map_timeout;
+	struct dirent **dirent;
+	int num;
+	int start;
+};
+
+static void *synthesize_threads_worker(void *arg)
+{
+	struct synthesize_threads_arg *args = arg;
+
+	__perf_event__synthesize_threads(args->tool, args->process,
+					 args->machine, args->mmap_data,
+					 args->proc_map_timeout, args->dirent,
+					 args->start, args->num);
+	return NULL;
+}
+
+int perf_event__synthesize_threads(struct perf_tool *tool,
+				   perf_event__handler_t process,
+				   struct machine *machine,
+				   bool mmap_data,
+				   unsigned int proc_map_timeout,
+				   unsigned int nr_threads_synthesize)
+{
+	struct synthesize_threads_arg *args = NULL;
+	pthread_t *synthesize_threads = NULL;
+	char proc_path[PATH_MAX];
+	struct dirent **dirent;
+	int num_per_thread;
+	int m, n, i, j;
+	int thread_nr;
+	int base = 0;
+	int err = -1;
+
+
+	if (machine__is_default_guest(machine))
+		return 0;
+
+	snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
+	n = scandir(proc_path, &dirent, 0, alphasort);
+	if (n < 0)
+		return err;
+
+	if (nr_threads_synthesize == UINT_MAX)
+		thread_nr = sysconf(_SC_NPROCESSORS_ONLN);
+	else
+		thread_nr = nr_threads_synthesize;
+
+	if (thread_nr <= 1) {
+		err = __perf_event__synthesize_threads(tool, process,
+						       machine, mmap_data,
+						       proc_map_timeout,
+						       dirent, base, n);
+		goto free_dirent;
+	}
+	if (thread_nr > n)
+		thread_nr = n;
+
+	synthesize_threads = calloc(sizeof(pthread_t), thread_nr);
+	if (synthesize_threads == NULL)
+		goto free_dirent;
+
+	args = calloc(sizeof(*args), thread_nr);
+	if (args == NULL)
+		goto free_threads;
+
+	num_per_thread = n / thread_nr;
+	m = n % thread_nr;
+	for (i = 0; i < thread_nr; i++) {
+		args[i].tool = tool;
+		args[i].process = process;
+		args[i].machine = machine;
+		args[i].mmap_data = mmap_data;
+		args[i].proc_map_timeout = proc_map_timeout;
+		args[i].dirent = dirent;
+	}
+	for (i = 0; i < m; i++) {
+		args[i].num = num_per_thread + 1;
+		args[i].start = i * args[i].num;
+	}
+	if (i != 0)
+		base = args[i-1].start + args[i-1].num;
+	for (j = i; j < thread_nr; j++) {
+		args[j].num = num_per_thread;
+		args[j].start = base + (j - i) * args[i].num;
+	}
+
+	for (i = 0; i < thread_nr; i++) {
+		if (pthread_create(&synthesize_threads[i], NULL,
+				   synthesize_threads_worker, &args[i]))
+			goto out_join;
+	}
+	err = 0;
+out_join:
+	for (i = 0; i < thread_nr; i++)
+		pthread_join(synthesize_threads[i], NULL);
+	free(args);
+free_threads:
+	free(synthesize_threads);
+free_dirent:
+	for (i = 0; i < n; i++)
+		free(dirent[i]);
+	free(dirent);
+
+	return err;
+}
+
 struct process_symbol_args {
 	const char *name;
 	u64	   start;
@@ -1498,6 +1605,7 @@ int machine__resolve(struct machine *machine, struct addr_location *al,
 	al->sym = NULL;
 	al->cpu = sample->cpu;
 	al->socket = -1;
+	al->srcline = NULL;
 
 	if (al->cpu >= 0) {
 		struct perf_env *env = machine->env;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 5524ee69279c..1ae95efbfb95 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -681,7 +681,8 @@ int perf_event__synthesize_cpu_map(struct perf_tool *tool,
 int perf_event__synthesize_threads(struct perf_tool *tool,
 				   perf_event__handler_t process,
 				   struct machine *machine, bool mmap_data,
-				   unsigned int proc_map_timeout);
+				   unsigned int proc_map_timeout,
+				   unsigned int nr_threads_synthesize);
 int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 				       perf_event__handler_t process,
 				       struct machine *machine);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 6a0d7ffbeba0..c6c891e154a6 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -33,9 +33,6 @@
 #include <linux/log2.h>
 #include <linux/err.h>
 
-static void perf_mmap__munmap(struct perf_mmap *map);
-static void perf_mmap__put(struct perf_mmap *map);
-
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 #define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
 
@@ -704,129 +701,6 @@ static int perf_evlist__resume(struct perf_evlist *evlist)
 	return perf_evlist__set_paused(evlist, false);
 }
 
-/* When check_messup is true, 'end' must points to a good entry */
-static union perf_event *
-perf_mmap__read(struct perf_mmap *md, bool check_messup, u64 start,
-		u64 end, u64 *prev)
-{
-	unsigned char *data = md->base + page_size;
-	union perf_event *event = NULL;
-	int diff = end - start;
-
-	if (check_messup) {
-		/*
-		 * If we're further behind than half the buffer, there's a chance
-		 * the writer will bite our tail and mess up the samples under us.
-		 *
-		 * If we somehow ended up ahead of the 'end', we got messed up.
-		 *
-		 * In either case, truncate and restart at 'end'.
-		 */
-		if (diff > md->mask / 2 || diff < 0) {
-			fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");
-
-			/*
-			 * 'end' points to a known good entry, start there.
-			 */
-			start = end;
-			diff = 0;
-		}
-	}
-
-	if (diff >= (int)sizeof(event->header)) {
-		size_t size;
-
-		event = (union perf_event *)&data[start & md->mask];
-		size = event->header.size;
-
-		if (size < sizeof(event->header) || diff < (int)size) {
-			event = NULL;
-			goto broken_event;
-		}
-
-		/*
-		 * Event straddles the mmap boundary -- header should always
-		 * be inside due to u64 alignment of output.
-		 */
-		if ((start & md->mask) + size != ((start + size) & md->mask)) {
-			unsigned int offset = start;
-			unsigned int len = min(sizeof(*event), size), cpy;
-			void *dst = md->event_copy;
-
-			do {
-				cpy = min(md->mask + 1 - (offset & md->mask), len);
-				memcpy(dst, &data[offset & md->mask], cpy);
-				offset += cpy;
-				dst += cpy;
-				len -= cpy;
-			} while (len);
-
-			event = (union perf_event *) md->event_copy;
-		}
-
-		start += size;
-	}
-
-broken_event:
-	if (prev)
-		*prev = start;
-
-	return event;
-}
-
-union perf_event *perf_mmap__read_forward(struct perf_mmap *md, bool check_messup)
-{
-	u64 head;
-	u64 old = md->prev;
-
-	/*
-	 * Check if event was unmapped due to a POLLHUP/POLLERR.
-	 */
-	if (!refcount_read(&md->refcnt))
-		return NULL;
-
-	head = perf_mmap__read_head(md);
-
-	return perf_mmap__read(md, check_messup, old, head, &md->prev);
-}
-
-union perf_event *
-perf_mmap__read_backward(struct perf_mmap *md)
-{
-	u64 head, end;
-	u64 start = md->prev;
-
-	/*
-	 * Check if event was unmapped due to a POLLHUP/POLLERR.
-	 */
-	if (!refcount_read(&md->refcnt))
-		return NULL;
-
-	head = perf_mmap__read_head(md);
-	if (!head)
-		return NULL;
-
-	/*
-	 * 'head' pointer starts from 0. Kernel minus sizeof(record) form
-	 * it each time when kernel writes to it, so in fact 'head' is
-	 * negative. 'end' pointer is made manually by adding the size of
-	 * the ring buffer to 'head' pointer, means the validate data can
-	 * read is the whole ring buffer. If 'end' is positive, the ring
-	 * buffer has not fully filled, so we must adjust 'end' to 0.
-	 *
-	 * However, since both 'head' and 'end' is unsigned, we can't
-	 * simply compare 'end' against 0. Here we compare '-head' and
-	 * the size of the ring buffer, where -head is the number of bytes
-	 * kernel write to the ring buffer.
-	 */
-	if (-head < (u64)(md->mask + 1))
-		end = 0;
-	else
-		end = head + md->mask + 1;
-
-	return perf_mmap__read(md, false, start, end, &md->prev);
-}
-
 union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int idx)
 {
 	struct perf_mmap *md = &evlist->mmap[idx];
@@ -857,96 +731,16 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 	return perf_evlist__mmap_read_forward(evlist, idx);
 }
 
-void perf_mmap__read_catchup(struct perf_mmap *md)
-{
-	u64 head;
-
-	if (!refcount_read(&md->refcnt))
-		return;
-
-	head = perf_mmap__read_head(md);
-	md->prev = head;
-}
-
 void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx)
 {
 	perf_mmap__read_catchup(&evlist->mmap[idx]);
 }
 
-static bool perf_mmap__empty(struct perf_mmap *md)
-{
-	return perf_mmap__read_head(md) == md->prev && !md->auxtrace_mmap.base;
-}
-
-static void perf_mmap__get(struct perf_mmap *map)
-{
-	refcount_inc(&map->refcnt);
-}
-
-static void perf_mmap__put(struct perf_mmap *md)
-{
-	BUG_ON(md->base && refcount_read(&md->refcnt) == 0);
-
-	if (refcount_dec_and_test(&md->refcnt))
-		perf_mmap__munmap(md);
-}
-
-void perf_mmap__consume(struct perf_mmap *md, bool overwrite)
-{
-	if (!overwrite) {
-		u64 old = md->prev;
-
-		perf_mmap__write_tail(md, old);
-	}
-
-	if (refcount_read(&md->refcnt) == 1 && perf_mmap__empty(md))
-		perf_mmap__put(md);
-}
-
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
 {
 	perf_mmap__consume(&evlist->mmap[idx], evlist->overwrite);
 }
 
-int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused,
-			       struct auxtrace_mmap_params *mp __maybe_unused,
-			       void *userpg __maybe_unused,
-			       int fd __maybe_unused)
-{
-	return 0;
-}
-
-void __weak auxtrace_mmap__munmap(struct auxtrace_mmap *mm __maybe_unused)
-{
-}
-
-void __weak auxtrace_mmap_params__init(
-			struct auxtrace_mmap_params *mp __maybe_unused,
-			off_t auxtrace_offset __maybe_unused,
-			unsigned int auxtrace_pages __maybe_unused,
-			bool auxtrace_overwrite __maybe_unused)
-{
-}
-
-void __weak auxtrace_mmap_params__set_idx(
-			struct auxtrace_mmap_params *mp __maybe_unused,
-			struct perf_evlist *evlist __maybe_unused,
-			int idx __maybe_unused,
-			bool per_cpu __maybe_unused)
-{
-}
-
-static void perf_mmap__munmap(struct perf_mmap *map)
-{
-	if (map->base != NULL) {
-		munmap(map->base, perf_mmap__mmap_len(map));
-		map->base = NULL;
-		map->fd = -1;
-		refcount_set(&map->refcnt, 0);
-	}
-	auxtrace_mmap__munmap(&map->auxtrace_mmap);
-}
-
 static void perf_evlist__munmap_nofree(struct perf_evlist *evlist)
 {
 	int i;
@@ -995,48 +789,6 @@ static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 	return map;
 }
 
-struct mmap_params {
-	int prot;
-	int mask;
-	struct auxtrace_mmap_params auxtrace_mp;
-};
-
-static int perf_mmap__mmap(struct perf_mmap *map,
-			   struct mmap_params *mp, int fd)
-{
-	/*
-	 * The last one will be done at perf_evlist__mmap_consume(), so that we
-	 * make sure we don't prevent tools from consuming every last event in
-	 * the ring buffer.
-	 *
-	 * I.e. we can get the POLLHUP meaning that the fd doesn't exist
-	 * anymore, but the last events for it are still in the ring buffer,
-	 * waiting to be consumed.
-	 *
-	 * Tools can chose to ignore this at their own discretion, but the
-	 * evlist layer can't just drop it when filtering events in
-	 * perf_evlist__filter_pollfd().
-	 */
-	refcount_set(&map->refcnt, 2);
-	map->prev = 0;
-	map->mask = mp->mask;
-	map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot,
-			 MAP_SHARED, fd, 0);
-	if (map->base == MAP_FAILED) {
-		pr_debug2("failed to mmap perf event ring buffer, error %d\n",
-			  errno);
-		map->base = NULL;
-		return -1;
-	}
-	map->fd = fd;
-
-	if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
-				&mp->auxtrace_mp, map->base, fd))
-		return -1;
-
-	return 0;
-}
-
 static bool
 perf_evlist__should_poll(struct perf_evlist *evlist __maybe_unused,
 			 struct perf_evsel *evsel)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index c1750a400bb7..e72ae64c11ac 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -7,12 +7,13 @@
 #include <linux/refcount.h>
 #include <linux/list.h>
 #include <api/fd/array.h>
+#include <fcntl.h>
 #include <stdio.h>
 #include "../perf.h"
 #include "event.h"
 #include "evsel.h"
+#include "mmap.h"
 #include "util.h"
-#include "auxtrace.h"
 #include <signal.h>
 #include <unistd.h>
 
@@ -24,55 +25,6 @@ struct record_opts;
 #define PERF_EVLIST__HLIST_BITS 8
 #define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
 
-/**
- * struct perf_mmap - perf's ring buffer mmap details
- *
- * @refcnt - e.g. code using PERF_EVENT_IOC_SET_OUTPUT to share this
- */
-struct perf_mmap {
-	void		 *base;
-	int		 mask;
-	int		 fd;
-	refcount_t	 refcnt;
-	u64		 prev;
-	struct auxtrace_mmap auxtrace_mmap;
-	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);
-};
-
-static inline size_t
-perf_mmap__mmap_len(struct perf_mmap *map)
-{
-	return map->mask + 1 + page_size;
-}
-
-/*
- * State machine of bkw_mmap_state:
- *
- *                     .________________(forbid)_____________.
- *                     |                                     V
- * NOTREADY --(0)--> RUNNING --(1)--> DATA_PENDING --(2)--> EMPTY
- *                     ^  ^              |   ^               |
- *                     |  |__(forbid)____/   |___(forbid)___/|
- *                     |                                     |
- *                      \_________________(3)_______________/
- *
- * NOTREADY     : Backward ring buffers are not ready
- * RUNNING      : Backward ring buffers are recording
- * DATA_PENDING : We are required to collect data from backward ring buffers
- * EMPTY        : We have collected data from backward ring buffers.
- *
- * (0): Setup backward ring buffer
- * (1): Pause ring buffers for reading
- * (2): Read from ring buffers
- * (3): Resume ring buffers for recording
- */
-enum bkw_mmap_state {
-	BKW_MMAP_NOTREADY,
-	BKW_MMAP_RUNNING,
-	BKW_MMAP_DATA_PENDING,
-	BKW_MMAP_EMPTY,
-};
-
 struct perf_evlist {
 	struct list_head entries;
 	struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
@@ -177,12 +129,6 @@ struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id);
 
 void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist, enum bkw_mmap_state state);
 
-union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_messup);
-union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
-
-void perf_mmap__read_catchup(struct perf_mmap *md);
-void perf_mmap__consume(struct perf_mmap *md, bool overwrite);
-
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx);
 
 union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist,
@@ -286,25 +232,6 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp);
 int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size);
 int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size);
 
-static inline u64 perf_mmap__read_head(struct perf_mmap *mm)
-{
-	struct perf_event_mmap_page *pc = mm->base;
-	u64 head = ACCESS_ONCE(pc->data_head);
-	rmb();
-	return head;
-}
-
-static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail)
-{
-	struct perf_event_mmap_page *pc = md->base;
-
-	/*
-	 * ensure all reads are done before we write the tail out.
-	 */
-	mb();
-	pc->data_tail = tail;
-}
-
 bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str);
 void perf_evlist__to_front(struct perf_evlist *evlist,
 			   struct perf_evsel *move_evsel);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 0dccdb89572c..f894893c203d 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -683,7 +683,7 @@ void perf_evsel__config_callchain(struct perf_evsel *evsel,
 		if (!function) {
 			perf_evsel__set_sample_bit(evsel, REGS_USER);
 			perf_evsel__set_sample_bit(evsel, STACK_USER);
-			attr->sample_regs_user = PERF_REGS_MASK;
+			attr->sample_regs_user |= PERF_REGS_MASK;
 			attr->sample_stack_user = param->dump_size;
 			attr->exclude_callchain_user = 1;
 		} else {
@@ -936,6 +936,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		perf_evsel__set_sample_bit(evsel, REGS_INTR);
 	}
 
+	if (opts->sample_user_regs) {
+		attr->sample_regs_user |= opts->sample_user_regs;
+		perf_evsel__set_sample_bit(evsel, REGS_USER);
+	}
+
 	if (target__has_cpu(&opts->target) || opts->sample_cpu)
 		perf_evsel__set_sample_bit(evsel, CPU);
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index b4df79d72329..9277df96ffda 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -69,6 +69,8 @@ struct perf_evsel_config_term {
 	} val;
 };
 
+struct perf_stat_evsel;
+
 /** struct perf_evsel - event selector
  *
  * @evlist - evlist this evsel is in, if it is in one.
@@ -102,6 +104,7 @@ struct perf_evsel {
 	const char		*unit;
 	struct event_format	*tp_format;
 	off_t			id_offset;
+	struct perf_stat_evsel  *stats;
 	void			*priv;
 	u64			db_id;
 	struct cgroup_sel	*cgrp;
@@ -138,6 +141,7 @@ struct perf_evsel {
 	const char *		metric_name;
 	struct perf_evsel	**metric_events;
 	bool			collect_stat;
+	bool			weak_group;
 };
 
 union u64_swap {
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index 1fd7c2e46db2..06dfb027879d 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -158,7 +158,7 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
 				}
 			}
 
-			if (print_dso) {
+			if (print_dso && (!node->sym || !node->sym->inlined)) {
 				printed += fprintf(fp, " (");
 				printed += map__fprintf_dsoname(node->map, fp);
 				printed += fprintf(fp, ")");
@@ -167,41 +167,12 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
 			if (print_srcline)
 				printed += map__fprintf_srcline(node->map, addr, "\n  ", fp);
 
+			if (node->sym && node->sym->inlined)
+				printed += fprintf(fp, " (inlined)");
+
 			if (!print_oneline)
 				printed += fprintf(fp, "\n");
 
-			if (symbol_conf.inline_name && node->map) {
-				struct inline_node *inode;
-
-				addr = map__rip_2objdump(node->map, node->ip),
-				inode = dso__parse_addr_inlines(node->map->dso, addr);
-
-				if (inode) {
-					struct inline_list *ilist;
-
-					list_for_each_entry(ilist, &inode->val, list) {
-						if (print_arrow)
-							printed += fprintf(fp, " <-");
-
-						/* IP is same, just skip it */
-						if (print_ip)
-							printed += fprintf(fp, "%c%16s",
-									   s, "");
-						if (print_sym)
-							printed += fprintf(fp, " %s",
-									   ilist->funcname);
-						if (print_srcline)
-							printed += fprintf(fp, "\n  %s:%d",
-									   ilist->filename,
-									   ilist->line_nr);
-						if (!print_oneline)
-							printed += fprintf(fp, "\n");
-					}
-
-					inline_node__delete(inode);
-				}
-			}
-
 			if (symbol_conf.bt_stop_list &&
 			    node->sym &&
 			    strlist__has_entry(symbol_conf.bt_stop_list,
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index ba0cea8fef72..7c0e9d587bfa 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1763,7 +1763,7 @@ process_event_desc(struct feat_fd *ff, void *data __maybe_unused)
 
 	session = container_of(ff->ph, struct perf_session, header);
 
-	if (session->file->is_pipe) {
+	if (session->data->is_pipe) {
 		/* Save events for reading later by print_event_desc,
 		 * since they can't be read again in pipe mode. */
 		ff->events = events;
@@ -1772,7 +1772,7 @@ process_event_desc(struct feat_fd *ff, void *data __maybe_unused)
 	for (evsel = events; evsel->attr.size; evsel++)
 		perf_evlist__set_event_name(session->evlist, evsel);
 
-	if (!session->file->is_pipe)
+	if (!session->data->is_pipe)
 		free_event_desc(events);
 
 	return 0;
@@ -2249,7 +2249,7 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full)
 {
 	struct header_print_data hd;
 	struct perf_header *header = &session->header;
-	int fd = perf_data_file__fd(session->file);
+	int fd = perf_data__fd(session->data);
 	struct stat st;
 	int ret, bit;
 
@@ -2265,7 +2265,7 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full)
 	perf_header__process_sections(header, fd, &hd,
 				      perf_file_section__fprintf_info);
 
-	if (session->file->is_pipe)
+	if (session->data->is_pipe)
 		return 0;
 
 	fprintf(fp, "# missing features: ");
@@ -2758,7 +2758,7 @@ static int perf_header__read_pipe(struct perf_session *session)
 	struct perf_pipe_file_header f_header;
 
 	if (perf_file_header__read_pipe(&f_header, header,
-					perf_data_file__fd(session->file),
+					perf_data__fd(session->data),
 					session->repipe) < 0) {
 		pr_debug("incompatible file format\n");
 		return -EINVAL;
@@ -2861,13 +2861,13 @@ static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist,
 
 int perf_session__read_header(struct perf_session *session)
 {
-	struct perf_data_file *file = session->file;
+	struct perf_data *data = session->data;
 	struct perf_header *header = &session->header;
 	struct perf_file_header	f_header;
 	struct perf_file_attr	f_attr;
 	u64			f_id;
 	int nr_attrs, nr_ids, i, j;
-	int fd = perf_data_file__fd(file);
+	int fd = perf_data__fd(data);
 
 	session->evlist = perf_evlist__new();
 	if (session->evlist == NULL)
@@ -2875,7 +2875,7 @@ int perf_session__read_header(struct perf_session *session)
 
 	session->evlist->env = &header->env;
 	session->machines.host.env = &header->env;
-	if (perf_data_file__is_pipe(file))
+	if (perf_data__is_pipe(data))
 		return perf_header__read_pipe(session);
 
 	if (perf_file_header__read(&f_header, header, fd) < 0)
@@ -2890,7 +2890,7 @@ int perf_session__read_header(struct perf_session *session)
 	if (f_header.data.size == 0) {
 		pr_warning("WARNING: The %s file's data size field is 0 which is unexpected.\n"
 			   "Was the 'perf record' command properly terminated?\n",
-			   file->path);
+			   data->file.path);
 	}
 
 	nr_attrs = f_header.attrs.size / f_header.attr_size;
@@ -3398,7 +3398,7 @@ int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused,
 				     struct perf_session *session)
 {
 	ssize_t size_read, padding, size = event->tracing_data.size;
-	int fd = perf_data_file__fd(session->file);
+	int fd = perf_data__fd(session->data);
 	off_t offset = lseek(fd, 0, SEEK_CUR);
 	char buf[BUFSIZ];
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 097473600d94..b6140950301e 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -597,6 +597,7 @@ __hists__add_entry(struct hists *hists,
 			.map	= al->map,
 			.sym	= al->sym,
 		},
+		.srcline = al->srcline ? strdup(al->srcline) : NULL,
 		.socket	 = al->socket,
 		.cpu	 = al->cpu,
 		.cpumode = al->cpumode,
@@ -951,6 +952,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
 			.map = al->map,
 			.sym = al->sym,
 		},
+		.srcline = al->srcline ? strdup(al->srcline) : NULL,
 		.parent = iter->parent,
 		.raw_data = sample->raw_data,
 		.raw_size = sample->raw_size,
@@ -1142,11 +1144,6 @@ void hist_entry__delete(struct hist_entry *he)
 		zfree(&he->mem_info);
 	}
 
-	if (he->inline_node) {
-		inline_node__delete(he->inline_node);
-		he->inline_node = NULL;
-	}
-
 	zfree(&he->stat_acc);
 	free_srcline(he->srcline);
 	if (he->srcfile && he->srcfile[0])
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 218ee2bac9a5..5325e65f9711 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -500,7 +500,7 @@ static int intel_bts_process_queue(struct intel_bts_queue *btsq, u64 *timestamp)
 	}
 
 	if (!buffer->data) {
-		int fd = perf_data_file__fd(btsq->bts->session->file);
+		int fd = perf_data__fd(btsq->bts->session->data);
 
 		buffer->data = auxtrace_buffer__get_data(buffer, fd);
 		if (!buffer->data) {
@@ -664,10 +664,10 @@ static int intel_bts_process_auxtrace_event(struct perf_session *session,
 	if (!bts->data_queued) {
 		struct auxtrace_buffer *buffer;
 		off_t data_offset;
-		int fd = perf_data_file__fd(session->file);
+		int fd = perf_data__fd(session->data);
 		int err;
 
-		if (perf_data_file__is_pipe(session->file)) {
+		if (perf_data__is_pipe(session->data)) {
 			data_offset = 0;
 		} else {
 			data_offset = lseek(fd, 0, SEEK_CUR);
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index b58f9fd1e2ee..23f9ba676df0 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -271,7 +271,7 @@ next:
 	ptq->buffer = buffer;
 
 	if (!buffer->data) {
-		int fd = perf_data_file__fd(ptq->pt->session->file);
+		int fd = perf_data__fd(ptq->pt->session->data);
 
 		buffer->data = auxtrace_buffer__get_data(buffer, fd);
 		if (!buffer->data)
@@ -2084,10 +2084,10 @@ static int intel_pt_process_auxtrace_event(struct perf_session *session,
 	if (!pt->data_queued) {
 		struct auxtrace_buffer *buffer;
 		off_t data_offset;
-		int fd = perf_data_file__fd(session->file);
+		int fd = perf_data__fd(session->data);
 		int err;
 
-		if (perf_data_file__is_pipe(session->file)) {
+		if (perf_data__is_pipe(session->data)) {
 			data_offset = 0;
 		} else {
 			data_offset = lseek(fd, 0, SEEK_CUR);
diff --git a/tools/perf/util/jit.h b/tools/perf/util/jit.h
index c2582fa9fe21..6817ffc2a059 100644
--- a/tools/perf/util/jit.h
+++ b/tools/perf/util/jit.h
@@ -4,7 +4,7 @@
 
 #include <data.h>
 
-int jit_process(struct perf_session *session, struct perf_data_file *output,
+int jit_process(struct perf_session *session, struct perf_data *output,
 		struct machine *machine, char *filename, pid_t pid, u64 *nbytes);
 
 int jit_inject_record(const char *filename);
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index 36483db032e8..a1863000e972 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -30,7 +30,7 @@
 #include "sane_ctype.h"
 
 struct jit_buf_desc {
-	struct perf_data_file *output;
+	struct perf_data *output;
 	struct perf_session *session;
 	struct machine *machine;
 	union jr_entry   *entry;
@@ -61,8 +61,8 @@ struct debug_line_info {
 
 struct jit_tool {
 	struct perf_tool tool;
-	struct perf_data_file	output;
-	struct perf_data_file	input;
+	struct perf_data	output;
+	struct perf_data	input;
 	u64 bytes_written;
 };
 
@@ -357,7 +357,7 @@ jit_inject_event(struct jit_buf_desc *jd, union perf_event *event)
 {
 	ssize_t size;
 
-	size = perf_data_file__write(jd->output, event, event->header.size);
+	size = perf_data__write(jd->output, event, event->header.size);
 	if (size < 0)
 		return -1;
 
@@ -752,7 +752,7 @@ jit_detect(char *mmap_name, pid_t pid)
 
 int
 jit_process(struct perf_session *session,
-	    struct perf_data_file *output,
+	    struct perf_data *output,
 	    struct machine *machine,
 	    char *filename,
 	    pid_t pid,
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index bd5d5b5e2218..6a8d03c3d9b7 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -31,7 +31,21 @@ static void dsos__init(struct dsos *dsos)
 {
 	INIT_LIST_HEAD(&dsos->head);
 	dsos->root = RB_ROOT;
-	pthread_rwlock_init(&dsos->lock, NULL);
+	init_rwsem(&dsos->lock);
+}
+
+static void machine__threads_init(struct machine *machine)
+{
+	int i;
+
+	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+		struct threads *threads = &machine->threads[i];
+		threads->entries = RB_ROOT;
+		init_rwsem(&threads->lock);
+		threads->nr = 0;
+		INIT_LIST_HEAD(&threads->dead);
+		threads->last_match = NULL;
+	}
 }
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
@@ -41,11 +55,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	RB_CLEAR_NODE(&machine->rb_node);
 	dsos__init(&machine->dsos);
 
-	machine->threads = RB_ROOT;
-	pthread_rwlock_init(&machine->threads_lock, NULL);
-	machine->nr_threads = 0;
-	INIT_LIST_HEAD(&machine->dead_threads);
-	machine->last_match = NULL;
+	machine__threads_init(machine);
 
 	machine->vdso_info = NULL;
 	machine->env = NULL;
@@ -121,7 +131,7 @@ static void dsos__purge(struct dsos *dsos)
 {
 	struct dso *pos, *n;
 
-	pthread_rwlock_wrlock(&dsos->lock);
+	down_write(&dsos->lock);
 
 	list_for_each_entry_safe(pos, n, &dsos->head, node) {
 		RB_CLEAR_NODE(&pos->rb_node);
@@ -130,39 +140,49 @@ static void dsos__purge(struct dsos *dsos)
 		dso__put(pos);
 	}
 
-	pthread_rwlock_unlock(&dsos->lock);
+	up_write(&dsos->lock);
 }
 
 static void dsos__exit(struct dsos *dsos)
 {
 	dsos__purge(dsos);
-	pthread_rwlock_destroy(&dsos->lock);
+	exit_rwsem(&dsos->lock);
 }
 
 void machine__delete_threads(struct machine *machine)
 {
 	struct rb_node *nd;
+	int i;
 
-	pthread_rwlock_wrlock(&machine->threads_lock);
-	nd = rb_first(&machine->threads);
-	while (nd) {
-		struct thread *t = rb_entry(nd, struct thread, rb_node);
+	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+		struct threads *threads = &machine->threads[i];
+		down_write(&threads->lock);
+		nd = rb_first(&threads->entries);
+		while (nd) {
+			struct thread *t = rb_entry(nd, struct thread, rb_node);
 
-		nd = rb_next(nd);
-		__machine__remove_thread(machine, t, false);
+			nd = rb_next(nd);
+			__machine__remove_thread(machine, t, false);
+		}
+		up_write(&threads->lock);
 	}
-	pthread_rwlock_unlock(&machine->threads_lock);
 }
 
 void machine__exit(struct machine *machine)
 {
+	int i;
+
 	machine__destroy_kernel_maps(machine);
 	map_groups__exit(&machine->kmaps);
 	dsos__exit(&machine->dsos);
 	machine__exit_vdso(machine);
 	zfree(&machine->root_dir);
 	zfree(&machine->current_tid);
-	pthread_rwlock_destroy(&machine->threads_lock);
+
+	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+		struct threads *threads = &machine->threads[i];
+		exit_rwsem(&threads->lock);
+	}
 }
 
 void machine__delete(struct machine *machine)
@@ -380,10 +400,11 @@ out_err:
  * lookup/new thread inserted.
  */
 static struct thread *____machine__findnew_thread(struct machine *machine,
+						  struct threads *threads,
 						  pid_t pid, pid_t tid,
 						  bool create)
 {
-	struct rb_node **p = &machine->threads.rb_node;
+	struct rb_node **p = &threads->entries.rb_node;
 	struct rb_node *parent = NULL;
 	struct thread *th;
 
@@ -392,14 +413,14 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 	 * so most of the time we dont have to look up
 	 * the full rbtree:
 	 */
-	th = machine->last_match;
+	th = threads->last_match;
 	if (th != NULL) {
 		if (th->tid == tid) {
 			machine__update_thread_pid(machine, th, pid);
 			return thread__get(th);
 		}
 
-		machine->last_match = NULL;
+		threads->last_match = NULL;
 	}
 
 	while (*p != NULL) {
@@ -407,7 +428,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		th = rb_entry(parent, struct thread, rb_node);
 
 		if (th->tid == tid) {
-			machine->last_match = th;
+			threads->last_match = th;
 			machine__update_thread_pid(machine, th, pid);
 			return thread__get(th);
 		}
@@ -424,7 +445,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 	th = thread__new(pid, tid);
 	if (th != NULL) {
 		rb_link_node(&th->rb_node, parent, p);
-		rb_insert_color(&th->rb_node, &machine->threads);
+		rb_insert_color(&th->rb_node, &threads->entries);
 
 		/*
 		 * We have to initialize map_groups separately
@@ -435,7 +456,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		 * leader and that would screwed the rb tree.
 		 */
 		if (thread__init_map_groups(th, machine)) {
-			rb_erase_init(&th->rb_node, &machine->threads);
+			rb_erase_init(&th->rb_node, &threads->entries);
 			RB_CLEAR_NODE(&th->rb_node);
 			thread__put(th);
 			return NULL;
@@ -444,8 +465,8 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		 * It is now in the rbtree, get a ref
 		 */
 		thread__get(th);
-		machine->last_match = th;
-		++machine->nr_threads;
+		threads->last_match = th;
+		++threads->nr;
 	}
 
 	return th;
@@ -453,27 +474,30 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 
 struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid)
 {
-	return ____machine__findnew_thread(machine, pid, tid, true);
+	return ____machine__findnew_thread(machine, machine__threads(machine, tid), pid, tid, true);
 }
 
 struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
 				       pid_t tid)
 {
+	struct threads *threads = machine__threads(machine, tid);
 	struct thread *th;
 
-	pthread_rwlock_wrlock(&machine->threads_lock);
+	down_write(&threads->lock);
 	th = __machine__findnew_thread(machine, pid, tid);
-	pthread_rwlock_unlock(&machine->threads_lock);
+	up_write(&threads->lock);
 	return th;
 }
 
 struct thread *machine__find_thread(struct machine *machine, pid_t pid,
 				    pid_t tid)
 {
+	struct threads *threads = machine__threads(machine, tid);
 	struct thread *th;
-	pthread_rwlock_rdlock(&machine->threads_lock);
-	th =  ____machine__findnew_thread(machine, pid, tid, false);
-	pthread_rwlock_unlock(&machine->threads_lock);
+
+	down_read(&threads->lock);
+	th =  ____machine__findnew_thread(machine, threads, pid, tid, false);
+	up_read(&threads->lock);
 	return th;
 }
 
@@ -565,7 +589,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine,
 {
 	struct dso *dso;
 
-	pthread_rwlock_wrlock(&machine->dsos.lock);
+	down_write(&machine->dsos.lock);
 
 	dso = __dsos__find(&machine->dsos, m->name, true);
 	if (!dso) {
@@ -579,7 +603,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine,
 
 	dso__get(dso);
 out_unlock:
-	pthread_rwlock_unlock(&machine->dsos.lock);
+	up_write(&machine->dsos.lock);
 	return dso;
 }
 
@@ -720,21 +744,25 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
 
 size_t machine__fprintf(struct machine *machine, FILE *fp)
 {
-	size_t ret;
 	struct rb_node *nd;
+	size_t ret;
+	int i;
 
-	pthread_rwlock_rdlock(&machine->threads_lock);
+	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+		struct threads *threads = &machine->threads[i];
 
-	ret = fprintf(fp, "Threads: %u\n", machine->nr_threads);
+		down_read(&threads->lock);
 
-	for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
-		struct thread *pos = rb_entry(nd, struct thread, rb_node);
+		ret = fprintf(fp, "Threads: %u\n", threads->nr);
 
-		ret += thread__fprintf(pos, fp);
-	}
+		for (nd = rb_first(&threads->entries); nd; nd = rb_next(nd)) {
+			struct thread *pos = rb_entry(nd, struct thread, rb_node);
 
-	pthread_rwlock_unlock(&machine->threads_lock);
+			ret += thread__fprintf(pos, fp);
+		}
 
+		up_read(&threads->lock);
+	}
 	return ret;
 }
 
@@ -1293,7 +1321,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		struct dso *kernel = NULL;
 		struct dso *dso;
 
-		pthread_rwlock_rdlock(&machine->dsos.lock);
+		down_read(&machine->dsos.lock);
 
 		list_for_each_entry(dso, &machine->dsos.head, node) {
 
@@ -1323,7 +1351,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 			break;
 		}
 
-		pthread_rwlock_unlock(&machine->dsos.lock);
+		up_read(&machine->dsos.lock);
 
 		if (kernel == NULL)
 			kernel = machine__findnew_dso(machine, kmmap_prefix);
@@ -1480,23 +1508,25 @@ out_problem:
 
 static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock)
 {
-	if (machine->last_match == th)
-		machine->last_match = NULL;
+	struct threads *threads = machine__threads(machine, th->tid);
+
+	if (threads->last_match == th)
+		threads->last_match = NULL;
 
 	BUG_ON(refcount_read(&th->refcnt) == 0);
 	if (lock)
-		pthread_rwlock_wrlock(&machine->threads_lock);
-	rb_erase_init(&th->rb_node, &machine->threads);
+		down_write(&threads->lock);
+	rb_erase_init(&th->rb_node, &threads->entries);
 	RB_CLEAR_NODE(&th->rb_node);
-	--machine->nr_threads;
+	--threads->nr;
 	/*
 	 * Move it first to the dead_threads list, then drop the reference,
 	 * if this is the last reference, then the thread__delete destructor
 	 * will be called and we will remove it from the dead_threads list.
 	 */
-	list_add_tail(&th->node, &machine->dead_threads);
+	list_add_tail(&th->node, &threads->dead);
 	if (lock)
-		pthread_rwlock_unlock(&machine->threads_lock);
+		up_write(&threads->lock);
 	thread__put(th);
 }
 
@@ -1680,6 +1710,26 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
 	return mi;
 }
 
+static char *callchain_srcline(struct map *map, struct symbol *sym, u64 ip)
+{
+	char *srcline = NULL;
+
+	if (!map || callchain_param.key == CCKEY_FUNCTION)
+		return srcline;
+
+	srcline = srcline__tree_find(&map->dso->srclines, ip);
+	if (!srcline) {
+		bool show_sym = false;
+		bool show_addr = callchain_param.key == CCKEY_ADDRESS;
+
+		srcline = get_srcline(map->dso, map__rip_2objdump(map, ip),
+				      sym, show_sym, show_addr);
+		srcline__tree_insert(&map->dso->srclines, ip, srcline);
+	}
+
+	return srcline;
+}
+
 struct iterations {
 	int nr_loop_iter;
 	u64 cycles;
@@ -1699,6 +1749,7 @@ static int add_callchain_ip(struct thread *thread,
 	struct addr_location al;
 	int nr_loop_iter = 0;
 	u64 iter_cycles = 0;
+	const char *srcline = NULL;
 
 	al.filtered = 0;
 	al.sym = NULL;
@@ -1754,9 +1805,10 @@ static int add_callchain_ip(struct thread *thread,
 		iter_cycles = iter->cycles;
 	}
 
+	srcline = callchain_srcline(al.map, al.sym, al.addr);
 	return callchain_cursor_append(cursor, al.addr, al.map, al.sym,
 				       branch, flags, nr_loop_iter,
-				       iter_cycles, branch_from);
+				       iter_cycles, branch_from, srcline);
 }
 
 struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
@@ -2069,15 +2121,54 @@ check_calls:
 	return 0;
 }
 
+static int append_inlines(struct callchain_cursor *cursor,
+			  struct map *map, struct symbol *sym, u64 ip)
+{
+	struct inline_node *inline_node;
+	struct inline_list *ilist;
+	u64 addr;
+	int ret = 1;
+
+	if (!symbol_conf.inline_name || !map || !sym)
+		return ret;
+
+	addr = map__rip_2objdump(map, ip);
+
+	inline_node = inlines__tree_find(&map->dso->inlined_nodes, addr);
+	if (!inline_node) {
+		inline_node = dso__parse_addr_inlines(map->dso, addr, sym);
+		if (!inline_node)
+			return ret;
+		inlines__tree_insert(&map->dso->inlined_nodes, inline_node);
+	}
+
+	list_for_each_entry(ilist, &inline_node->val, list) {
+		ret = callchain_cursor_append(cursor, ip, map,
+					      ilist->symbol, false,
+					      NULL, 0, 0, 0, ilist->srcline);
+
+		if (ret != 0)
+			return ret;
+	}
+
+	return ret;
+}
+
 static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
 	struct callchain_cursor *cursor = arg;
+	const char *srcline = NULL;
 
 	if (symbol_conf.hide_unresolved && entry->sym == NULL)
 		return 0;
+
+	if (append_inlines(cursor, entry->map, entry->sym, entry->ip) == 0)
+		return 0;
+
+	srcline = callchain_srcline(entry->map, entry->sym, entry->ip);
 	return callchain_cursor_append(cursor, entry->ip,
 				       entry->map, entry->sym,
-				       false, NULL, 0, 0, 0);
+				       false, NULL, 0, 0, 0, srcline);
 }
 
 static int thread__resolve_callchain_unwind(struct thread *thread,
@@ -2141,21 +2232,26 @@ int machine__for_each_thread(struct machine *machine,
 			     int (*fn)(struct thread *thread, void *p),
 			     void *priv)
 {
+	struct threads *threads;
 	struct rb_node *nd;
 	struct thread *thread;
 	int rc = 0;
+	int i;
 
-	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;
-	}
+	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+		threads = &machine->threads[i];
+		for (nd = rb_first(&threads->entries); 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;
+		list_for_each_entry(thread, &threads->dead, node) {
+			rc = fn(thread, priv);
+			if (rc != 0)
+				return rc;
+		}
 	}
 	return rc;
 }
@@ -2184,12 +2280,16 @@ int machines__for_each_thread(struct machines *machines,
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
 				  struct target *target, struct thread_map *threads,
 				  perf_event__handler_t process, bool data_mmap,
-				  unsigned int proc_map_timeout)
+				  unsigned int proc_map_timeout,
+				  unsigned int nr_threads_synthesize)
 {
 	if (target__has_task(target))
 		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap, proc_map_timeout);
 	else if (target__has_cpu(target))
-		return perf_event__synthesize_threads(tool, process, machine, data_mmap, proc_map_timeout);
+		return perf_event__synthesize_threads(tool, process,
+						      machine, data_mmap,
+						      proc_map_timeout,
+						      nr_threads_synthesize);
 	/* command specified */
 	return 0;
 }
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index d551aa80a59b..5ce860b64c74 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -7,6 +7,7 @@
 #include "map.h"
 #include "dso.h"
 #include "event.h"
+#include "rwsem.h"
 
 struct addr_location;
 struct branch_stack;
@@ -24,6 +25,17 @@ extern const char *ref_reloc_sym_names[];
 
 struct vdso_info;
 
+#define THREADS__TABLE_BITS	8
+#define THREADS__TABLE_SIZE	(1 << THREADS__TABLE_BITS)
+
+struct threads {
+	struct rb_root	  entries;
+	struct rw_semaphore lock;
+	unsigned int	  nr;
+	struct list_head  dead;
+	struct thread	  *last_match;
+};
+
 struct machine {
 	struct rb_node	  rb_node;
 	pid_t		  pid;
@@ -31,11 +43,7 @@ struct machine {
 	bool		  comm_exec;
 	bool		  kptr_restrict_warned;
 	char		  *root_dir;
-	struct rb_root	  threads;
-	pthread_rwlock_t  threads_lock;
-	unsigned int	  nr_threads;
-	struct list_head  dead_threads;
-	struct thread	  *last_match;
+	struct threads    threads[THREADS__TABLE_SIZE];
 	struct vdso_info  *vdso_info;
 	struct perf_env   *env;
 	struct dsos	  dsos;
@@ -49,6 +57,12 @@ struct machine {
 	};
 };
 
+static inline struct threads *machine__threads(struct machine *machine, pid_t tid)
+{
+	/* Cast it to handle tid == -1 */
+	return &machine->threads[(unsigned int)tid % THREADS__TABLE_SIZE];
+}
+
 static inline
 struct map *__machine__kernel_map(struct machine *machine, enum map_type type)
 {
@@ -244,15 +258,18 @@ int machines__for_each_thread(struct machines *machines,
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
 				  struct target *target, struct thread_map *threads,
 				  perf_event__handler_t process, bool data_mmap,
-				  unsigned int proc_map_timeout);
+				  unsigned int proc_map_timeout,
+				  unsigned int nr_threads_synthesize);
 static inline
 int machine__synthesize_threads(struct machine *machine, struct target *target,
 				struct thread_map *threads, bool data_mmap,
-				unsigned int proc_map_timeout)
+				unsigned int proc_map_timeout,
+				unsigned int nr_threads_synthesize)
 {
 	return __machine__synthesize_threads(machine, NULL, target, threads,
 					     perf_event__process, data_mmap,
-					     proc_map_timeout);
+					     proc_map_timeout,
+					     nr_threads_synthesize);
 }
 
 pid_t machine__get_current_tid(struct machine *machine, int cpu);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 4e7bd2750122..6d40efd74402 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -489,7 +489,7 @@ u64 map__objdump_2mem(struct map *map, u64 ip)
 static void maps__init(struct maps *maps)
 {
 	maps->entries = RB_ROOT;
-	pthread_rwlock_init(&maps->lock, NULL);
+	init_rwsem(&maps->lock);
 }
 
 void map_groups__init(struct map_groups *mg, struct machine *machine)
@@ -518,9 +518,9 @@ static void __maps__purge(struct maps *maps)
 
 static void maps__exit(struct maps *maps)
 {
-	pthread_rwlock_wrlock(&maps->lock);
+	down_write(&maps->lock);
 	__maps__purge(maps);
-	pthread_rwlock_unlock(&maps->lock);
+	up_write(&maps->lock);
 }
 
 void map_groups__exit(struct map_groups *mg)
@@ -587,7 +587,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
 	struct symbol *sym;
 	struct rb_node *nd;
 
-	pthread_rwlock_rdlock(&maps->lock);
+	down_read(&maps->lock);
 
 	for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) {
 		struct map *pos = rb_entry(nd, struct map, rb_node);
@@ -603,7 +603,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
 
 	sym = NULL;
 out:
-	pthread_rwlock_unlock(&maps->lock);
+	up_read(&maps->lock);
 	return sym;
 }
 
@@ -639,7 +639,7 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp)
 	size_t printed = 0;
 	struct rb_node *nd;
 
-	pthread_rwlock_rdlock(&maps->lock);
+	down_read(&maps->lock);
 
 	for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) {
 		struct map *pos = rb_entry(nd, struct map, rb_node);
@@ -651,7 +651,7 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp)
 		}
 	}
 
-	pthread_rwlock_unlock(&maps->lock);
+	up_read(&maps->lock);
 
 	return printed;
 }
@@ -683,7 +683,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
 	struct rb_node *next;
 	int err = 0;
 
-	pthread_rwlock_wrlock(&maps->lock);
+	down_write(&maps->lock);
 
 	root = &maps->entries;
 	next = rb_first(root);
@@ -751,7 +751,7 @@ put_map:
 
 	err = 0;
 out:
-	pthread_rwlock_unlock(&maps->lock);
+	up_write(&maps->lock);
 	return err;
 }
 
@@ -772,7 +772,7 @@ int map_groups__clone(struct thread *thread,
 	struct map *map;
 	struct maps *maps = &parent->maps[type];
 
-	pthread_rwlock_rdlock(&maps->lock);
+	down_read(&maps->lock);
 
 	for (map = maps__first(maps); map; map = map__next(map)) {
 		struct map *new = map__clone(map);
@@ -789,7 +789,7 @@ int map_groups__clone(struct thread *thread,
 
 	err = 0;
 out_unlock:
-	pthread_rwlock_unlock(&maps->lock);
+	up_read(&maps->lock);
 	return err;
 }
 
@@ -816,9 +816,9 @@ static void __maps__insert(struct maps *maps, struct map *map)
 
 void maps__insert(struct maps *maps, struct map *map)
 {
-	pthread_rwlock_wrlock(&maps->lock);
+	down_write(&maps->lock);
 	__maps__insert(maps, map);
-	pthread_rwlock_unlock(&maps->lock);
+	up_write(&maps->lock);
 }
 
 static void __maps__remove(struct maps *maps, struct map *map)
@@ -829,9 +829,9 @@ static void __maps__remove(struct maps *maps, struct map *map)
 
 void maps__remove(struct maps *maps, struct map *map)
 {
-	pthread_rwlock_wrlock(&maps->lock);
+	down_write(&maps->lock);
 	__maps__remove(maps, map);
-	pthread_rwlock_unlock(&maps->lock);
+	up_write(&maps->lock);
 }
 
 struct map *maps__find(struct maps *maps, u64 ip)
@@ -839,7 +839,7 @@ struct map *maps__find(struct maps *maps, u64 ip)
 	struct rb_node **p, *parent = NULL;
 	struct map *m;
 
-	pthread_rwlock_rdlock(&maps->lock);
+	down_read(&maps->lock);
 
 	p = &maps->entries.rb_node;
 	while (*p != NULL) {
@@ -855,7 +855,7 @@ struct map *maps__find(struct maps *maps, u64 ip)
 
 	m = NULL;
 out:
-	pthread_rwlock_unlock(&maps->lock);
+	up_read(&maps->lock);
 	return m;
 }
 
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 1fb9b8589adc..edeb7291c8e1 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -10,6 +10,7 @@
 #include <stdio.h>
 #include <stdbool.h>
 #include <linux/types.h>
+#include "rwsem.h"
 
 enum map_type {
 	MAP__FUNCTION = 0,
@@ -62,7 +63,7 @@ struct kmap {
 
 struct maps {
 	struct rb_root	 entries;
-	pthread_rwlock_t lock;
+	struct rw_semaphore lock;
 };
 
 struct map_groups {
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
new file mode 100644
index 000000000000..0ddd9c199227
--- /dev/null
+++ b/tools/perf/util/metricgroup.c
@@ -0,0 +1,490 @@
+/*
+ * Copyright (c) 2017, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+/* Manage metrics and groups of metrics from JSON files */
+
+#include "metricgroup.h"
+#include "evlist.h"
+#include "strbuf.h"
+#include "pmu.h"
+#include "expr.h"
+#include "rblist.h"
+#include "pmu.h"
+#include <string.h>
+#include <stdbool.h>
+#include <errno.h>
+#include "pmu-events/pmu-events.h"
+#include "strbuf.h"
+#include "strlist.h"
+#include <assert.h>
+#include <ctype.h>
+
+struct metric_event *metricgroup__lookup(struct rblist *metric_events,
+					 struct perf_evsel *evsel,
+					 bool create)
+{
+	struct rb_node *nd;
+	struct metric_event me = {
+		.evsel = evsel
+	};
+	nd = rblist__find(metric_events, &me);
+	if (nd)
+		return container_of(nd, struct metric_event, nd);
+	if (create) {
+		rblist__add_node(metric_events, &me);
+		nd = rblist__find(metric_events, &me);
+		if (nd)
+			return container_of(nd, struct metric_event, nd);
+	}
+	return NULL;
+}
+
+static int metric_event_cmp(struct rb_node *rb_node, const void *entry)
+{
+	struct metric_event *a = container_of(rb_node,
+					      struct metric_event,
+					      nd);
+	const struct metric_event *b = entry;
+
+	if (a->evsel == b->evsel)
+		return 0;
+	if ((char *)a->evsel < (char *)b->evsel)
+		return -1;
+	return +1;
+}
+
+static struct rb_node *metric_event_new(struct rblist *rblist __maybe_unused,
+					const void *entry)
+{
+	struct metric_event *me = malloc(sizeof(struct metric_event));
+
+	if (!me)
+		return NULL;
+	memcpy(me, entry, sizeof(struct metric_event));
+	me->evsel = ((struct metric_event *)entry)->evsel;
+	INIT_LIST_HEAD(&me->head);
+	return &me->nd;
+}
+
+static void metricgroup__rblist_init(struct rblist *metric_events)
+{
+	rblist__init(metric_events);
+	metric_events->node_cmp = metric_event_cmp;
+	metric_events->node_new = metric_event_new;
+}
+
+struct egroup {
+	struct list_head nd;
+	int idnum;
+	const char **ids;
+	const char *metric_name;
+	const char *metric_expr;
+};
+
+static struct perf_evsel *find_evsel(struct perf_evlist *perf_evlist,
+				     const char **ids,
+				     int idnum,
+				     struct perf_evsel **metric_events)
+{
+	struct perf_evsel *ev, *start = NULL;
+	int ind = 0;
+
+	evlist__for_each_entry (perf_evlist, ev) {
+		if (!strcmp(ev->name, ids[ind])) {
+			metric_events[ind] = ev;
+			if (ind == 0)
+				start = ev;
+			if (++ind == idnum) {
+				metric_events[ind] = NULL;
+				return start;
+			}
+		} else {
+			ind = 0;
+			start = NULL;
+		}
+	}
+	/*
+	 * This can happen when an alias expands to multiple
+	 * events, like for uncore events.
+	 * We don't support this case for now.
+	 */
+	return NULL;
+}
+
+static int metricgroup__setup_events(struct list_head *groups,
+				     struct perf_evlist *perf_evlist,
+				     struct rblist *metric_events_list)
+{
+	struct metric_event *me;
+	struct metric_expr *expr;
+	int i = 0;
+	int ret = 0;
+	struct egroup *eg;
+	struct perf_evsel *evsel;
+
+	list_for_each_entry (eg, groups, nd) {
+		struct perf_evsel **metric_events;
+
+		metric_events = calloc(sizeof(void *), eg->idnum + 1);
+		if (!metric_events) {
+			ret = -ENOMEM;
+			break;
+		}
+		evsel = find_evsel(perf_evlist, eg->ids, eg->idnum,
+				   metric_events);
+		if (!evsel) {
+			pr_debug("Cannot resolve %s: %s\n",
+					eg->metric_name, eg->metric_expr);
+			continue;
+		}
+		for (i = 0; i < eg->idnum; i++)
+			metric_events[i]->collect_stat = true;
+		me = metricgroup__lookup(metric_events_list, evsel, true);
+		if (!me) {
+			ret = -ENOMEM;
+			break;
+		}
+		expr = malloc(sizeof(struct metric_expr));
+		if (!expr) {
+			ret = -ENOMEM;
+			break;
+		}
+		expr->metric_expr = eg->metric_expr;
+		expr->metric_name = eg->metric_name;
+		expr->metric_events = metric_events;
+		list_add(&expr->nd, &me->head);
+	}
+	return ret;
+}
+
+static bool match_metric(const char *n, const char *list)
+{
+	int len;
+	char *m;
+
+	if (!list)
+		return false;
+	if (!strcmp(list, "all"))
+		return true;
+	if (!n)
+		return !strcasecmp(list, "No_group");
+	len = strlen(list);
+	m = strcasestr(n, list);
+	if (!m)
+		return false;
+	if ((m == n || m[-1] == ';' || m[-1] == ' ') &&
+	    (m[len] == 0 || m[len] == ';'))
+		return true;
+	return false;
+}
+
+struct mep {
+	struct rb_node nd;
+	const char *name;
+	struct strlist *metrics;
+};
+
+static int mep_cmp(struct rb_node *rb_node, const void *entry)
+{
+	struct mep *a = container_of(rb_node, struct mep, nd);
+	struct mep *b = (struct mep *)entry;
+
+	return strcmp(a->name, b->name);
+}
+
+static struct rb_node *mep_new(struct rblist *rl __maybe_unused,
+					const void *entry)
+{
+	struct mep *me = malloc(sizeof(struct mep));
+
+	if (!me)
+		return NULL;
+	memcpy(me, entry, sizeof(struct mep));
+	me->name = strdup(me->name);
+	if (!me->name)
+		goto out_me;
+	me->metrics = strlist__new(NULL, NULL);
+	if (!me->metrics)
+		goto out_name;
+	return &me->nd;
+out_name:
+	free((char *)me->name);
+out_me:
+	free(me);
+	return NULL;
+}
+
+static struct mep *mep_lookup(struct rblist *groups, const char *name)
+{
+	struct rb_node *nd;
+	struct mep me = {
+		.name = name
+	};
+	nd = rblist__find(groups, &me);
+	if (nd)
+		return container_of(nd, struct mep, nd);
+	rblist__add_node(groups, &me);
+	nd = rblist__find(groups, &me);
+	if (nd)
+		return container_of(nd, struct mep, nd);
+	return NULL;
+}
+
+static void mep_delete(struct rblist *rl __maybe_unused,
+		       struct rb_node *nd)
+{
+	struct mep *me = container_of(nd, struct mep, nd);
+
+	strlist__delete(me->metrics);
+	free((void *)me->name);
+	free(me);
+}
+
+static void metricgroup__print_strlist(struct strlist *metrics, bool raw)
+{
+	struct str_node *sn;
+	int n = 0;
+
+	strlist__for_each_entry (sn, metrics) {
+		if (raw)
+			printf("%s%s", n > 0 ? " " : "", sn->s);
+		else
+			printf("  %s\n", sn->s);
+		n++;
+	}
+	if (raw)
+		putchar('\n');
+}
+
+void metricgroup__print(bool metrics, bool metricgroups, char *filter,
+			bool raw)
+{
+	struct pmu_events_map *map = perf_pmu__find_map();
+	struct pmu_event *pe;
+	int i;
+	struct rblist groups;
+	struct rb_node *node, *next;
+	struct strlist *metriclist = NULL;
+
+	if (!map)
+		return;
+
+	if (!metricgroups) {
+		metriclist = strlist__new(NULL, NULL);
+		if (!metriclist)
+			return;
+	}
+
+	rblist__init(&groups);
+	groups.node_new = mep_new;
+	groups.node_cmp = mep_cmp;
+	groups.node_delete = mep_delete;
+	for (i = 0; ; i++) {
+		const char *g;
+		pe = &map->table[i];
+
+		if (!pe->name && !pe->metric_group && !pe->metric_name)
+			break;
+		if (!pe->metric_expr)
+			continue;
+		g = pe->metric_group;
+		if (!g && pe->metric_name) {
+			if (pe->name)
+				continue;
+			g = "No_group";
+		}
+		if (g) {
+			char *omg;
+			char *mg = strdup(g);
+
+			if (!mg)
+				return;
+			omg = mg;
+			while ((g = strsep(&mg, ";")) != NULL) {
+				struct mep *me;
+				char *s;
+
+				if (*g == 0)
+					g = "No_group";
+				while (isspace(*g))
+					g++;
+				if (filter && !strstr(g, filter))
+					continue;
+				if (raw)
+					s = (char *)pe->metric_name;
+				else {
+					if (asprintf(&s, "%s\n\t[%s]",
+						     pe->metric_name, pe->desc) < 0)
+						return;
+				}
+
+				if (!s)
+					continue;
+
+				if (!metricgroups) {
+					strlist__add(metriclist, s);
+				} else {
+					me = mep_lookup(&groups, g);
+					if (!me)
+						continue;
+					strlist__add(me->metrics, s);
+				}
+			}
+			free(omg);
+		}
+	}
+
+	if (metricgroups && !raw)
+		printf("\nMetric Groups:\n\n");
+	else if (metrics && !raw)
+		printf("\nMetrics:\n\n");
+
+	for (node = rb_first(&groups.entries); node; node = next) {
+		struct mep *me = container_of(node, struct mep, nd);
+
+		if (metricgroups)
+			printf("%s%s%s", me->name, metrics ? ":" : "", raw ? " " : "\n");
+		if (metrics)
+			metricgroup__print_strlist(me->metrics, raw);
+		next = rb_next(node);
+		rblist__remove_node(&groups, node);
+	}
+	if (!metricgroups)
+		metricgroup__print_strlist(metriclist, raw);
+	strlist__delete(metriclist);
+}
+
+static int metricgroup__add_metric(const char *metric, struct strbuf *events,
+				   struct list_head *group_list)
+{
+	struct pmu_events_map *map = perf_pmu__find_map();
+	struct pmu_event *pe;
+	int ret = -EINVAL;
+	int i, j;
+
+	if (!map)
+		return 0;
+
+	for (i = 0; ; i++) {
+		pe = &map->table[i];
+
+		if (!pe->name && !pe->metric_group && !pe->metric_name)
+			break;
+		if (!pe->metric_expr)
+			continue;
+		if (match_metric(pe->metric_group, metric) ||
+		    match_metric(pe->metric_name, metric)) {
+			const char **ids;
+			int idnum;
+			struct egroup *eg;
+
+			pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name);
+
+			if (expr__find_other(pe->metric_expr,
+					     NULL, &ids, &idnum) < 0)
+				continue;
+			if (events->len > 0)
+				strbuf_addf(events, ",");
+			for (j = 0; j < idnum; j++) {
+				pr_debug("found event %s\n", ids[j]);
+				strbuf_addf(events, "%s%s",
+					j == 0 ? "{" : ",",
+					ids[j]);
+			}
+			strbuf_addf(events, "}:W");
+
+			eg = malloc(sizeof(struct egroup));
+			if (!eg) {
+				ret = -ENOMEM;
+				break;
+			}
+			eg->ids = ids;
+			eg->idnum = idnum;
+			eg->metric_name = pe->metric_name;
+			eg->metric_expr = pe->metric_expr;
+			list_add_tail(&eg->nd, group_list);
+			ret = 0;
+		}
+	}
+	return ret;
+}
+
+static int metricgroup__add_metric_list(const char *list, struct strbuf *events,
+				        struct list_head *group_list)
+{
+	char *llist, *nlist, *p;
+	int ret = -EINVAL;
+
+	nlist = strdup(list);
+	if (!nlist)
+		return -ENOMEM;
+	llist = nlist;
+
+	strbuf_init(events, 100);
+	strbuf_addf(events, "%s", "");
+
+	while ((p = strsep(&llist, ",")) != NULL) {
+		ret = metricgroup__add_metric(p, events, group_list);
+		if (ret == -EINVAL) {
+			fprintf(stderr, "Cannot find metric or group `%s'\n",
+					p);
+			break;
+		}
+	}
+	free(nlist);
+	return ret;
+}
+
+static void metricgroup__free_egroups(struct list_head *group_list)
+{
+	struct egroup *eg, *egtmp;
+	int i;
+
+	list_for_each_entry_safe (eg, egtmp, group_list, nd) {
+		for (i = 0; i < eg->idnum; i++)
+			free((char *)eg->ids[i]);
+		free(eg->ids);
+		free(eg);
+	}
+}
+
+int metricgroup__parse_groups(const struct option *opt,
+			   const char *str,
+			   struct rblist *metric_events)
+{
+	struct parse_events_error parse_error;
+	struct perf_evlist *perf_evlist = *(struct perf_evlist **)opt->value;
+	struct strbuf extra_events;
+	LIST_HEAD(group_list);
+	int ret;
+
+	if (metric_events->nr_entries == 0)
+		metricgroup__rblist_init(metric_events);
+	ret = metricgroup__add_metric_list(str, &extra_events, &group_list);
+	if (ret)
+		return ret;
+	pr_debug("adding %s\n", extra_events.buf);
+	memset(&parse_error, 0, sizeof(struct parse_events_error));
+	ret = parse_events(perf_evlist, extra_events.buf, &parse_error);
+	if (ret) {
+		parse_events_print_error(&parse_error, extra_events.buf);
+		goto out;
+	}
+	strbuf_release(&extra_events);
+	ret = metricgroup__setup_events(&group_list, perf_evlist,
+					metric_events);
+out:
+	metricgroup__free_egroups(&group_list);
+	return ret;
+}
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
new file mode 100644
index 000000000000..06854e125ee7
--- /dev/null
+++ b/tools/perf/util/metricgroup.h
@@ -0,0 +1,31 @@
+#ifndef METRICGROUP_H
+#define METRICGROUP_H 1
+
+#include "linux/list.h"
+#include "rblist.h"
+#include <subcmd/parse-options.h>
+#include "evlist.h"
+#include "strbuf.h"
+
+struct metric_event {
+	struct rb_node nd;
+	struct perf_evsel *evsel;
+	struct list_head head; /* list of metric_expr */
+};
+
+struct metric_expr {
+	struct list_head nd;
+	const char *metric_expr;
+	const char *metric_name;
+	struct perf_evsel **metric_events;
+};
+
+struct metric_event *metricgroup__lookup(struct rblist *metric_events,
+					 struct perf_evsel *evsel,
+					 bool create);
+int metricgroup__parse_groups(const struct option *opt,
+			const char *str,
+			struct rblist *metric_events);
+
+void metricgroup__print(bool metrics, bool groups, char *filter, bool raw);
+#endif
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
new file mode 100644
index 000000000000..9fe5f9c7d577
--- /dev/null
+++ b/tools/perf/util/mmap.c
@@ -0,0 +1,352 @@
+/*
+ * Copyright (C) 2011-2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Parts came from evlist.c builtin-{top,stat,record}.c, see those files for further
+ * copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include <sys/mman.h>
+#include <inttypes.h>
+#include <asm/bug.h>
+#include "debug.h"
+#include "event.h"
+#include "mmap.h"
+#include "util.h" /* page_size */
+
+size_t perf_mmap__mmap_len(struct perf_mmap *map)
+{
+	return map->mask + 1 + page_size;
+}
+
+/* When check_messup is true, 'end' must points to a good entry */
+static union perf_event *perf_mmap__read(struct perf_mmap *map, bool check_messup,
+					 u64 start, u64 end, u64 *prev)
+{
+	unsigned char *data = map->base + page_size;
+	union perf_event *event = NULL;
+	int diff = end - start;
+
+	if (check_messup) {
+		/*
+		 * If we're further behind than half the buffer, there's a chance
+		 * the writer will bite our tail and mess up the samples under us.
+		 *
+		 * If we somehow ended up ahead of the 'end', we got messed up.
+		 *
+		 * In either case, truncate and restart at 'end'.
+		 */
+		if (diff > map->mask / 2 || diff < 0) {
+			fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");
+
+			/*
+			 * 'end' points to a known good entry, start there.
+			 */
+			start = end;
+			diff = 0;
+		}
+	}
+
+	if (diff >= (int)sizeof(event->header)) {
+		size_t size;
+
+		event = (union perf_event *)&data[start & map->mask];
+		size = event->header.size;
+
+		if (size < sizeof(event->header) || diff < (int)size) {
+			event = NULL;
+			goto broken_event;
+		}
+
+		/*
+		 * Event straddles the mmap boundary -- header should always
+		 * be inside due to u64 alignment of output.
+		 */
+		if ((start & map->mask) + size != ((start + size) & map->mask)) {
+			unsigned int offset = start;
+			unsigned int len = min(sizeof(*event), size), cpy;
+			void *dst = map->event_copy;
+
+			do {
+				cpy = min(map->mask + 1 - (offset & map->mask), len);
+				memcpy(dst, &data[offset & map->mask], cpy);
+				offset += cpy;
+				dst += cpy;
+				len -= cpy;
+			} while (len);
+
+			event = (union perf_event *)map->event_copy;
+		}
+
+		start += size;
+	}
+
+broken_event:
+	if (prev)
+		*prev = start;
+
+	return event;
+}
+
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_messup)
+{
+	u64 head;
+	u64 old = map->prev;
+
+	/*
+	 * Check if event was unmapped due to a POLLHUP/POLLERR.
+	 */
+	if (!refcount_read(&map->refcnt))
+		return NULL;
+
+	head = perf_mmap__read_head(map);
+
+	return perf_mmap__read(map, check_messup, old, head, &map->prev);
+}
+
+union perf_event *perf_mmap__read_backward(struct perf_mmap *map)
+{
+	u64 head, end;
+	u64 start = map->prev;
+
+	/*
+	 * Check if event was unmapped due to a POLLHUP/POLLERR.
+	 */
+	if (!refcount_read(&map->refcnt))
+		return NULL;
+
+	head = perf_mmap__read_head(map);
+	if (!head)
+		return NULL;
+
+	/*
+	 * 'head' pointer starts from 0. Kernel minus sizeof(record) form
+	 * it each time when kernel writes to it, so in fact 'head' is
+	 * negative. 'end' pointer is made manually by adding the size of
+	 * the ring buffer to 'head' pointer, means the validate data can
+	 * read is the whole ring buffer. If 'end' is positive, the ring
+	 * buffer has not fully filled, so we must adjust 'end' to 0.
+	 *
+	 * However, since both 'head' and 'end' is unsigned, we can't
+	 * simply compare 'end' against 0. Here we compare '-head' and
+	 * the size of the ring buffer, where -head is the number of bytes
+	 * kernel write to the ring buffer.
+	 */
+	if (-head < (u64)(map->mask + 1))
+		end = 0;
+	else
+		end = head + map->mask + 1;
+
+	return perf_mmap__read(map, false, start, end, &map->prev);
+}
+
+void perf_mmap__read_catchup(struct perf_mmap *map)
+{
+	u64 head;
+
+	if (!refcount_read(&map->refcnt))
+		return;
+
+	head = perf_mmap__read_head(map);
+	map->prev = head;
+}
+
+static bool perf_mmap__empty(struct perf_mmap *map)
+{
+	return perf_mmap__read_head(map) == map->prev && !map->auxtrace_mmap.base;
+}
+
+void perf_mmap__get(struct perf_mmap *map)
+{
+	refcount_inc(&map->refcnt);
+}
+
+void perf_mmap__put(struct perf_mmap *map)
+{
+	BUG_ON(map->base && refcount_read(&map->refcnt) == 0);
+
+	if (refcount_dec_and_test(&map->refcnt))
+		perf_mmap__munmap(map);
+}
+
+void perf_mmap__consume(struct perf_mmap *map, bool overwrite)
+{
+	if (!overwrite) {
+		u64 old = map->prev;
+
+		perf_mmap__write_tail(map, old);
+	}
+
+	if (refcount_read(&map->refcnt) == 1 && perf_mmap__empty(map))
+		perf_mmap__put(map);
+}
+
+int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused,
+			       struct auxtrace_mmap_params *mp __maybe_unused,
+			       void *userpg __maybe_unused,
+			       int fd __maybe_unused)
+{
+	return 0;
+}
+
+void __weak auxtrace_mmap__munmap(struct auxtrace_mmap *mm __maybe_unused)
+{
+}
+
+void __weak auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp __maybe_unused,
+				       off_t auxtrace_offset __maybe_unused,
+				       unsigned int auxtrace_pages __maybe_unused,
+				       bool auxtrace_overwrite __maybe_unused)
+{
+}
+
+void __weak auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp __maybe_unused,
+					  struct perf_evlist *evlist __maybe_unused,
+					  int idx __maybe_unused,
+					  bool per_cpu __maybe_unused)
+{
+}
+
+void perf_mmap__munmap(struct perf_mmap *map)
+{
+	if (map->base != NULL) {
+		munmap(map->base, perf_mmap__mmap_len(map));
+		map->base = NULL;
+		map->fd = -1;
+		refcount_set(&map->refcnt, 0);
+	}
+	auxtrace_mmap__munmap(&map->auxtrace_mmap);
+}
+
+int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd)
+{
+	/*
+	 * The last one will be done at perf_evlist__mmap_consume(), so that we
+	 * make sure we don't prevent tools from consuming every last event in
+	 * the ring buffer.
+	 *
+	 * I.e. we can get the POLLHUP meaning that the fd doesn't exist
+	 * anymore, but the last events for it are still in the ring buffer,
+	 * waiting to be consumed.
+	 *
+	 * Tools can chose to ignore this at their own discretion, but the
+	 * evlist layer can't just drop it when filtering events in
+	 * perf_evlist__filter_pollfd().
+	 */
+	refcount_set(&map->refcnt, 2);
+	map->prev = 0;
+	map->mask = mp->mask;
+	map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot,
+			 MAP_SHARED, fd, 0);
+	if (map->base == MAP_FAILED) {
+		pr_debug2("failed to mmap perf event ring buffer, error %d\n",
+			  errno);
+		map->base = NULL;
+		return -1;
+	}
+	map->fd = fd;
+
+	if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
+				&mp->auxtrace_mp, map->base, fd))
+		return -1;
+
+	return 0;
+}
+
+static int backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end)
+{
+	struct perf_event_header *pheader;
+	u64 evt_head = head;
+	int size = mask + 1;
+
+	pr_debug2("backward_rb_find_range: buf=%p, head=%"PRIx64"\n", buf, head);
+	pheader = (struct perf_event_header *)(buf + (head & mask));
+	*start = head;
+	while (true) {
+		if (evt_head - head >= (unsigned int)size) {
+			pr_debug("Finished reading backward ring buffer: rewind\n");
+			if (evt_head - head > (unsigned int)size)
+				evt_head -= pheader->size;
+			*end = evt_head;
+			return 0;
+		}
+
+		pheader = (struct perf_event_header *)(buf + (evt_head & mask));
+
+		if (pheader->size == 0) {
+			pr_debug("Finished reading backward ring buffer: get start\n");
+			*end = evt_head;
+			return 0;
+		}
+
+		evt_head += pheader->size;
+		pr_debug3("move evt_head: %"PRIx64"\n", evt_head);
+	}
+	WARN_ONCE(1, "Shouldn't get here\n");
+	return -1;
+}
+
+static int rb_find_range(void *data, int mask, u64 head, u64 old,
+			 u64 *start, u64 *end, bool backward)
+{
+	if (!backward) {
+		*start = old;
+		*end = head;
+		return 0;
+	}
+
+	return backward_rb_find_range(data, mask, head, start, end);
+}
+
+int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
+		    void *to, int push(void *to, void *buf, size_t size))
+{
+	u64 head = perf_mmap__read_head(md);
+	u64 old = md->prev;
+	u64 end = head, start = old;
+	unsigned char *data = md->base + page_size;
+	unsigned long size;
+	void *buf;
+	int rc = 0;
+
+	if (rb_find_range(data, md->mask, head, old, &start, &end, backward))
+		return -1;
+
+	if (start == end)
+		return 0;
+
+	size = end - start;
+	if (size > (unsigned long)(md->mask) + 1) {
+		WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
+
+		md->prev = head;
+		perf_mmap__consume(md, overwrite || backward);
+		return 0;
+	}
+
+	if ((start & md->mask) + size != (end & md->mask)) {
+		buf = &data[start & md->mask];
+		size = md->mask + 1 - (start & md->mask);
+		start += size;
+
+		if (push(to, buf, size) < 0) {
+			rc = -1;
+			goto out;
+		}
+	}
+
+	buf = &data[start & md->mask];
+	size = end - start;
+	start += size;
+
+	if (push(to, buf, size) < 0) {
+		rc = -1;
+		goto out;
+	}
+
+	md->prev = head;
+	perf_mmap__consume(md, overwrite || backward);
+out:
+	return rc;
+}
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
new file mode 100644
index 000000000000..efd78b827b05
--- /dev/null
+++ b/tools/perf/util/mmap.h
@@ -0,0 +1,97 @@
+#ifndef __PERF_MMAP_H
+#define __PERF_MMAP_H 1
+
+#include <linux/compiler.h>
+#include <linux/refcount.h>
+#include <linux/types.h>
+#include <asm/barrier.h>
+#include <stdbool.h>
+#include "auxtrace.h"
+#include "event.h"
+
+/**
+ * struct perf_mmap - perf's ring buffer mmap details
+ *
+ * @refcnt - e.g. code using PERF_EVENT_IOC_SET_OUTPUT to share this
+ */
+struct perf_mmap {
+	void		 *base;
+	int		 mask;
+	int		 fd;
+	refcount_t	 refcnt;
+	u64		 prev;
+	struct auxtrace_mmap auxtrace_mmap;
+	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);
+};
+
+/*
+ * State machine of bkw_mmap_state:
+ *
+ *                     .________________(forbid)_____________.
+ *                     |                                     V
+ * NOTREADY --(0)--> RUNNING --(1)--> DATA_PENDING --(2)--> EMPTY
+ *                     ^  ^              |   ^               |
+ *                     |  |__(forbid)____/   |___(forbid)___/|
+ *                     |                                     |
+ *                      \_________________(3)_______________/
+ *
+ * NOTREADY     : Backward ring buffers are not ready
+ * RUNNING      : Backward ring buffers are recording
+ * DATA_PENDING : We are required to collect data from backward ring buffers
+ * EMPTY        : We have collected data from backward ring buffers.
+ *
+ * (0): Setup backward ring buffer
+ * (1): Pause ring buffers for reading
+ * (2): Read from ring buffers
+ * (3): Resume ring buffers for recording
+ */
+enum bkw_mmap_state {
+	BKW_MMAP_NOTREADY,
+	BKW_MMAP_RUNNING,
+	BKW_MMAP_DATA_PENDING,
+	BKW_MMAP_EMPTY,
+};
+
+struct mmap_params {
+	int			    prot, mask;
+	struct auxtrace_mmap_params auxtrace_mp;
+};
+
+int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd);
+void perf_mmap__munmap(struct perf_mmap *map);
+
+void perf_mmap__get(struct perf_mmap *map);
+void perf_mmap__put(struct perf_mmap *map);
+
+void perf_mmap__consume(struct perf_mmap *map, bool overwrite);
+
+void perf_mmap__read_catchup(struct perf_mmap *md);
+
+static inline u64 perf_mmap__read_head(struct perf_mmap *mm)
+{
+	struct perf_event_mmap_page *pc = mm->base;
+	u64 head = ACCESS_ONCE(pc->data_head);
+	rmb();
+	return head;
+}
+
+static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail)
+{
+	struct perf_event_mmap_page *pc = md->base;
+
+	/*
+	 * ensure all reads are done before we write the tail out.
+	 */
+	mb();
+	pc->data_tail = tail;
+}
+
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_messup);
+union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
+
+int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
+		    void *to, int push(void *to, void *buf, size_t size));
+
+size_t perf_mmap__mmap_len(struct perf_mmap *map);
+
+#endif /*__PERF_MMAP_H */
diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c
index a58e91197729..5be021701f34 100644
--- a/tools/perf/util/namespaces.c
+++ b/tools/perf/util/namespaces.c
@@ -11,6 +11,7 @@
 #include "event.h"
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <fcntl.h>
 #include <limits.h>
 #include <sched.h>
 #include <stdlib.h>
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index 05d82601c9a6..760558dcfd18 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -9,9 +9,10 @@
 #ifndef __PERF_NAMESPACES_H
 #define __PERF_NAMESPACES_H
 
-#include "../perf.h"
-#include <linux/list.h>
+#include <sys/types.h>
+#include <linux/perf_event.h>
 #include <linux/refcount.h>
+#include <linux/types.h>
 
 struct namespaces_event;
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 56694e3409ea..a7fcd95961ef 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -29,6 +29,7 @@
 #include "probe-file.h"
 #include "asm/bug.h"
 #include "util/parse-branch-options.h"
+#include "metricgroup.h"
 
 #define MAX_NAME_LEN 100
 
@@ -1220,11 +1221,17 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 	struct perf_pmu_info info;
 	struct perf_pmu *pmu;
 	struct perf_evsel *evsel;
+	struct parse_events_error *err = parse_state->error;
 	LIST_HEAD(config_terms);
 
 	pmu = perf_pmu__find(name);
-	if (!pmu)
+	if (!pmu) {
+		if (asprintf(&err->str,
+				"Cannot find PMU `%s'. Missing kernel support?",
+				name) < 0)
+			err->str = NULL;
 		return -EINVAL;
+	}
 
 	if (pmu->default_config) {
 		memcpy(&attr, pmu->default_config,
@@ -1368,6 +1375,7 @@ struct event_modifier {
 	int exclude_GH;
 	int sample_read;
 	int pinned;
+	int weak;
 };
 
 static int get_event_modifier(struct event_modifier *mod, char *str,
@@ -1386,6 +1394,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
 
 	int exclude = eu | ek | eh;
 	int exclude_GH = evsel ? evsel->exclude_GH : 0;
+	int weak = 0;
 
 	memset(mod, 0, sizeof(*mod));
 
@@ -1423,6 +1432,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
 			sample_read = 1;
 		} else if (*str == 'D') {
 			pinned = 1;
+		} else if (*str == 'W') {
+			weak = 1;
 		} else
 			break;
 
@@ -1453,6 +1464,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
 	mod->exclude_GH = exclude_GH;
 	mod->sample_read = sample_read;
 	mod->pinned = pinned;
+	mod->weak = weak;
 
 	return 0;
 }
@@ -1466,7 +1478,7 @@ static int check_modifier(char *str)
 	char *p = str;
 
 	/* The sizeof includes 0 byte as well. */
-	if (strlen(str) > (sizeof("ukhGHpppPSDI") - 1))
+	if (strlen(str) > (sizeof("ukhGHpppPSDIW") - 1))
 		return -1;
 
 	while (*p) {
@@ -1506,6 +1518,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add)
 		evsel->exclude_GH          = mod.exclude_GH;
 		evsel->sample_read         = mod.sample_read;
 		evsel->precise_max         = mod.precise_max;
+		evsel->weak_group	   = mod.weak;
 
 		if (perf_evsel__is_group_leader(evsel))
 			evsel->attr.pinned = mod.pinned;
@@ -1728,8 +1741,8 @@ static int get_term_width(void)
 	return ws.ws_col > MAX_WIDTH ? MAX_WIDTH : ws.ws_col;
 }
 
-static void parse_events_print_error(struct parse_events_error *err,
-				     const char *event)
+void parse_events_print_error(struct parse_events_error *err,
+			      const char *event)
 {
 	const char *str = "invalid or unsupported event: ";
 	char _buf[MAX_WIDTH];
@@ -1784,8 +1797,6 @@ static void parse_events_print_error(struct parse_events_error *err,
 		zfree(&err->str);
 		zfree(&err->help);
 	}
-
-	fprintf(stderr, "Run 'perf list' for a list of valid events\n");
 }
 
 #undef MAX_WIDTH
@@ -1797,8 +1808,10 @@ int parse_events_option(const struct option *opt, const char *str,
 	struct parse_events_error err = { .idx = 0, };
 	int ret = parse_events(evlist, str, &err);
 
-	if (ret)
+	if (ret) {
 		parse_events_print_error(&err, str);
+		fprintf(stderr, "Run 'perf list' for a list of valid events\n");
+	}
 
 	return ret;
 }
@@ -2376,6 +2389,8 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag,
 	print_tracepoint_events(NULL, NULL, name_only);
 
 	print_sdt_events(NULL, NULL, name_only);
+
+	metricgroup__print(true, true, NULL, name_only);
 }
 
 int parse_events__is_hardcoded_term(struct parse_events_term *term)
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index eed50b54bab3..be337c266697 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -203,6 +203,9 @@ int is_valid_tracepoint(const char *event_string);
 int valid_event_mount(const char *eventfs);
 char *parse_events_formats_error_string(char *additional_terms);
 
+void parse_events_print_error(struct parse_events_error *err,
+			      const char *event);
+
 #ifdef HAVE_LIBELF_SUPPORT
 /*
  * If the probe point starts with '%',
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 025729510525..655ecff636a8 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -179,7 +179,7 @@ name		[a-zA-Z_*?][a-zA-Z0-9_*?.]*
 name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
 drv_cfg_term	[a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)?
 /* If you add a modifier you need to update check_modifier() */
-modifier_event	[ukhpPGHSDI]+
+modifier_event	[ukhpPGHSDIW]+
 modifier_bp	[rwx]{1,3}
 
 %%
@@ -306,6 +306,7 @@ cpu-migrations|migrations			{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COU
 alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
 emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
 dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
+duration_time					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
 bpf-output					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
 
 	/*
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index b10b35a63138..07cb2ac041d7 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -3,6 +3,7 @@
 #include <linux/compiler.h>
 #include <sys/types.h>
 #include <errno.h>
+#include <fcntl.h>
 #include <sys/stat.h>
 #include <unistd.h>
 #include <stdio.h>
@@ -541,16 +542,8 @@ char * __weak get_cpuid_str(void)
 	return NULL;
 }
 
-/*
- * From the pmu_events_map, find the table of PMU events that corresponds
- * to the current running CPU. Then, add all PMU events from that table
- * as aliases.
- */
-static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
+static char *perf_pmu__getcpuid(void)
 {
-	int i;
-	struct pmu_events_map *map;
-	struct pmu_event *pe;
 	char *cpuid;
 	static bool printed;
 
@@ -560,22 +553,50 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
 	if (!cpuid)
 		cpuid = get_cpuid_str();
 	if (!cpuid)
-		return;
+		return NULL;
 
 	if (!printed) {
 		pr_debug("Using CPUID %s\n", cpuid);
 		printed = true;
 	}
+	return cpuid;
+}
+
+struct pmu_events_map *perf_pmu__find_map(void)
+{
+	struct pmu_events_map *map;
+	char *cpuid = perf_pmu__getcpuid();
+	int i;
 
 	i = 0;
-	while (1) {
+	for (;;) {
 		map = &pmu_events_map[i++];
-		if (!map->table)
-			goto out;
+		if (!map->table) {
+			map = NULL;
+			break;
+		}
 
 		if (!strcmp(map->cpuid, cpuid))
 			break;
 	}
+	free(cpuid);
+	return map;
+}
+
+/*
+ * From the pmu_events_map, find the table of PMU events that corresponds
+ * to the current running CPU. Then, add all PMU events from that table
+ * as aliases.
+ */
+static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
+{
+	int i;
+	struct pmu_events_map *map;
+	struct pmu_event *pe;
+
+	map = perf_pmu__find_map();
+	if (!map)
+		return;
 
 	/*
 	 * Found a matching PMU events table. Create aliases
@@ -585,8 +606,11 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
 		const char *pname;
 
 		pe = &map->table[i++];
-		if (!pe->name)
+		if (!pe->name) {
+			if (pe->metric_group || pe->metric_name)
+				continue;
 			break;
+		}
 
 		pname = pe->pmu ? pe->pmu : "cpu";
 		if (strncmp(pname, name, strlen(pname)))
@@ -600,9 +624,6 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
 				(char *)pe->metric_expr,
 				(char *)pe->metric_name);
 	}
-
-out:
-	free(cpuid);
 }
 
 struct perf_event_attr * __weak
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index eca99435f4a0..27c75e635866 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -92,4 +92,6 @@ int perf_pmu__test(void);
 
 struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);
 
+struct pmu_events_map *perf_pmu__find_map(void);
+
 #endif /* __PMU_H */
diff --git a/tools/perf/util/print_binary.c b/tools/perf/util/print_binary.c
index 779e35c9e566..23e367063446 100644
--- a/tools/perf/util/print_binary.c
+++ b/tools/perf/util/print_binary.c
@@ -3,40 +3,42 @@
 #include <linux/log2.h>
 #include "sane_ctype.h"
 
-void print_binary(unsigned char *data, size_t len,
-		  size_t bytes_per_line, print_binary_t printer,
-		  void *extra)
+int binary__fprintf(unsigned char *data, size_t len,
+		    size_t bytes_per_line, binary__fprintf_t printer,
+		    void *extra, FILE *fp)
 {
 	size_t i, j, mask;
+	int printed = 0;
 
 	if (!printer)
-		return;
+		return 0;
 
 	bytes_per_line = roundup_pow_of_two(bytes_per_line);
 	mask = bytes_per_line - 1;
 
-	printer(BINARY_PRINT_DATA_BEGIN, 0, extra);
+	printed += printer(BINARY_PRINT_DATA_BEGIN, 0, extra, fp);
 	for (i = 0; i < len; i++) {
 		if ((i & mask) == 0) {
-			printer(BINARY_PRINT_LINE_BEGIN, -1, extra);
-			printer(BINARY_PRINT_ADDR, i, extra);
+			printed += printer(BINARY_PRINT_LINE_BEGIN, -1, extra, fp);
+			printed += printer(BINARY_PRINT_ADDR, i, extra, fp);
 		}
 
-		printer(BINARY_PRINT_NUM_DATA, data[i], extra);
+		printed += printer(BINARY_PRINT_NUM_DATA, data[i], extra, fp);
 
 		if (((i & mask) == mask) || i == len - 1) {
 			for (j = 0; j < mask-(i & mask); j++)
-				printer(BINARY_PRINT_NUM_PAD, -1, extra);
+				printed += printer(BINARY_PRINT_NUM_PAD, -1, extra, fp);
 
-			printer(BINARY_PRINT_SEP, i, extra);
+			printer(BINARY_PRINT_SEP, i, extra, fp);
 			for (j = i & ~mask; j <= i; j++)
-				printer(BINARY_PRINT_CHAR_DATA, data[j], extra);
+				printed += printer(BINARY_PRINT_CHAR_DATA, data[j], extra, fp);
 			for (j = 0; j < mask-(i & mask); j++)
-				printer(BINARY_PRINT_CHAR_PAD, i, extra);
-			printer(BINARY_PRINT_LINE_END, -1, extra);
+				printed += printer(BINARY_PRINT_CHAR_PAD, i, extra, fp);
+			printed += printer(BINARY_PRINT_LINE_END, -1, extra, fp);
 		}
 	}
-	printer(BINARY_PRINT_DATA_END, -1, extra);
+	printed += printer(BINARY_PRINT_DATA_END, -1, extra, fp);
+	return printed;
 }
 
 int is_printable_array(char *p, unsigned int len)
diff --git a/tools/perf/util/print_binary.h b/tools/perf/util/print_binary.h
index 2be3075e2b05..2a1554afc957 100644
--- a/tools/perf/util/print_binary.h
+++ b/tools/perf/util/print_binary.h
@@ -3,6 +3,7 @@
 #define PERF_PRINT_BINARY_H
 
 #include <stddef.h>
+#include <stdio.h>
 
 enum binary_printer_ops {
 	BINARY_PRINT_DATA_BEGIN,
@@ -17,12 +18,19 @@ enum binary_printer_ops {
 	BINARY_PRINT_DATA_END,
 };
 
-typedef void (*print_binary_t)(enum binary_printer_ops op,
-			       unsigned int val, void *extra);
+typedef int (*binary__fprintf_t)(enum binary_printer_ops op,
+				 unsigned int val, void *extra, FILE *fp);
 
-void print_binary(unsigned char *data, size_t len,
-		  size_t bytes_per_line, print_binary_t printer,
-		  void *extra);
+int binary__fprintf(unsigned char *data, size_t len,
+		    size_t bytes_per_line, binary__fprintf_t printer,
+		    void *extra, FILE *fp);
+
+static inline void print_binary(unsigned char *data, size_t len,
+				size_t bytes_per_line, binary__fprintf_t printer,
+				void *extra)
+{
+	binary__fprintf(data, len, bytes_per_line, printer, extra, stdout);
+}
 
 int is_printable_array(char *p, unsigned int len);
 
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index cdf8d83a484c..4ae1123c6794 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -15,6 +15,7 @@
  *
  */
 #include <errno.h>
+#include <fcntl.h>
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <sys/uio.h>
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index e66dc495809a..b4f2f06722a7 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,6 +10,7 @@ util/ctype.c
 util/evlist.c
 util/evsel.c
 util/cpumap.c
+util/mmap.c
 util/namespaces.c
 ../lib/bitmap.c
 ../lib/find_bit.c
diff --git a/tools/perf/util/rb_resort.h b/tools/perf/util/rb_resort.h
index 7d8972b33f6b..a920f702a74d 100644
--- a/tools/perf/util/rb_resort.h
+++ b/tools/perf/util/rb_resort.h
@@ -144,7 +144,8 @@ struct __name##_sorted *__name = __name##_sorted__new
 				  __ilist->rblist.nr_entries)
 
 /* For 'struct machine->threads' */
-#define DECLARE_RESORT_RB_MACHINE_THREADS(__name, __machine)			\
-	DECLARE_RESORT_RB(__name)(&__machine->threads, __machine->nr_threads)
+#define DECLARE_RESORT_RB_MACHINE_THREADS(__name, __machine, hash_bucket)	\
+	DECLARE_RESORT_RB(__name)(&__machine->threads[hash_bucket].entries,	\
+				  __machine->threads[hash_bucket].nr)
 
 #endif /* _PERF_RESORT_RB_H_ */
diff --git a/tools/perf/util/rwsem.c b/tools/perf/util/rwsem.c
new file mode 100644
index 000000000000..5e52e7baa7b6
--- /dev/null
+++ b/tools/perf/util/rwsem.c
@@ -0,0 +1,32 @@
+#include "util.h"
+#include "rwsem.h"
+
+int init_rwsem(struct rw_semaphore *sem)
+{
+	return pthread_rwlock_init(&sem->lock, NULL);
+}
+
+int exit_rwsem(struct rw_semaphore *sem)
+{
+	return pthread_rwlock_destroy(&sem->lock);
+}
+
+int down_read(struct rw_semaphore *sem)
+{
+	return perf_singlethreaded ? 0 : pthread_rwlock_rdlock(&sem->lock);
+}
+
+int up_read(struct rw_semaphore *sem)
+{
+	return perf_singlethreaded ? 0 : pthread_rwlock_unlock(&sem->lock);
+}
+
+int down_write(struct rw_semaphore *sem)
+{
+	return perf_singlethreaded ? 0 : pthread_rwlock_wrlock(&sem->lock);
+}
+
+int up_write(struct rw_semaphore *sem)
+{
+	return perf_singlethreaded ? 0 : pthread_rwlock_unlock(&sem->lock);
+}
diff --git a/tools/perf/util/rwsem.h b/tools/perf/util/rwsem.h
new file mode 100644
index 000000000000..94565ad4d494
--- /dev/null
+++ b/tools/perf/util/rwsem.h
@@ -0,0 +1,19 @@
+#ifndef _PERF_RWSEM_H
+#define _PERF_RWSEM_H
+
+#include <pthread.h>
+
+struct rw_semaphore {
+	pthread_rwlock_t lock;
+};
+
+int init_rwsem(struct rw_semaphore *sem);
+int exit_rwsem(struct rw_semaphore *sem);
+
+int down_read(struct rw_semaphore *sem);
+int up_read(struct rw_semaphore *sem);
+
+int down_write(struct rw_semaphore *sem);
+int up_write(struct rw_semaphore *sem);
+
+#endif /* _PERF_RWSEM_H */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index da55081aefc6..5c412310f266 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -33,14 +33,14 @@ static int perf_session__deliver_event(struct perf_session *session,
 
 static int perf_session__open(struct perf_session *session)
 {
-	struct perf_data_file *file = session->file;
+	struct perf_data *data = session->data;
 
 	if (perf_session__read_header(session) < 0) {
 		pr_err("incompatible file format (rerun with -v to learn more)\n");
 		return -1;
 	}
 
-	if (perf_data_file__is_pipe(file))
+	if (perf_data__is_pipe(data))
 		return 0;
 
 	if (perf_header__has_feat(&session->header, HEADER_STAT))
@@ -121,7 +121,7 @@ static int ordered_events__deliver_event(struct ordered_events *oe,
 					   session->tool, event->file_offset);
 }
 
-struct perf_session *perf_session__new(struct perf_data_file *file,
+struct perf_session *perf_session__new(struct perf_data *data,
 				       bool repipe, struct perf_tool *tool)
 {
 	struct perf_session *session = zalloc(sizeof(*session));
@@ -135,13 +135,13 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 	machines__init(&session->machines);
 	ordered_events__init(&session->ordered_events, ordered_events__deliver_event);
 
-	if (file) {
-		if (perf_data_file__open(file))
+	if (data) {
+		if (perf_data__open(data))
 			goto out_delete;
 
-		session->file = file;
+		session->data = data;
 
-		if (perf_data_file__is_read(file)) {
+		if (perf_data__is_read(data)) {
 			if (perf_session__open(session) < 0)
 				goto out_close;
 
@@ -149,7 +149,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 			 * set session attributes that are present in perf.data
 			 * but not in pipe-mode.
 			 */
-			if (!file->is_pipe) {
+			if (!data->is_pipe) {
 				perf_session__set_id_hdr_size(session);
 				perf_session__set_comm_exec(session);
 			}
@@ -158,7 +158,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 		session->machines.host.env = &perf_env;
 	}
 
-	if (!file || perf_data_file__is_write(file)) {
+	if (!data || perf_data__is_write(data)) {
 		/*
 		 * In O_RDONLY mode this will be performed when reading the
 		 * kernel MMAP event, in perf_event__process_mmap().
@@ -171,7 +171,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 	 * In pipe-mode, evlist is empty until PERF_RECORD_HEADER_ATTR is
 	 * processed, so perf_evlist__sample_id_all is not meaningful here.
 	 */
-	if ((!file || !file->is_pipe) && tool && tool->ordering_requires_timestamps &&
+	if ((!data || !data->is_pipe) && tool && tool->ordering_requires_timestamps &&
 	    tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) {
 		dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
 		tool->ordered_events = false;
@@ -180,7 +180,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 	return session;
 
  out_close:
-	perf_data_file__close(file);
+	perf_data__close(data);
  out_delete:
 	perf_session__delete(session);
  out:
@@ -202,8 +202,8 @@ void perf_session__delete(struct perf_session *session)
 	perf_session__delete_threads(session);
 	perf_env__exit(&session->header.env);
 	machines__exit(&session->machines);
-	if (session->file)
-		perf_data_file__close(session->file);
+	if (session->data)
+		perf_data__close(session->data);
 	free(session);
 }
 
@@ -291,8 +291,8 @@ static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
 				       __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
-	if (perf_data_file__is_pipe(session->file))
-		skipn(perf_data_file__fd(session->file), event->auxtrace.size);
+	if (perf_data__is_pipe(session->data))
+		skipn(perf_data__fd(session->data), event->auxtrace.size);
 	return event->auxtrace.size;
 }
 
@@ -1350,7 +1350,7 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 {
 	struct ordered_events *oe = &session->ordered_events;
 	struct perf_tool *tool = session->tool;
-	int fd = perf_data_file__fd(session->file);
+	int fd = perf_data__fd(session->data);
 	int err;
 
 	dump_event(session->evlist, event, file_offset, NULL);
@@ -1450,10 +1450,10 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
 		goto out_parse_sample;
 	}
 
-	if (perf_data_file__is_pipe(session->file))
+	if (perf_data__is_pipe(session->data))
 		return -1;
 
-	fd = perf_data_file__fd(session->file);
+	fd = perf_data__fd(session->data);
 	hdr_sz = sizeof(struct perf_event_header);
 
 	if (buf_sz < hdr_sz)
@@ -1688,7 +1688,7 @@ static int __perf_session__process_pipe_events(struct perf_session *session)
 {
 	struct ordered_events *oe = &session->ordered_events;
 	struct perf_tool *tool = session->tool;
-	int fd = perf_data_file__fd(session->file);
+	int fd = perf_data__fd(session->data);
 	union perf_event *event;
 	uint32_t size, cur_size = 0;
 	void *buf = NULL;
@@ -1829,7 +1829,7 @@ static int __perf_session__process_events(struct perf_session *session,
 {
 	struct ordered_events *oe = &session->ordered_events;
 	struct perf_tool *tool = session->tool;
-	int fd = perf_data_file__fd(session->file);
+	int fd = perf_data__fd(session->data);
 	u64 head, page_offset, file_offset, file_pos, size;
 	int err, mmap_prot, mmap_flags, map_idx = 0;
 	size_t	mmap_size;
@@ -1850,7 +1850,7 @@ static int __perf_session__process_events(struct perf_session *session,
 	if (data_offset + data_size < file_size)
 		file_size = data_offset + data_size;
 
-	ui_progress__init(&prog, file_size, "Processing events...");
+	ui_progress__init_size(&prog, file_size, "Processing events...");
 
 	mmap_size = MMAP_SIZE;
 	if (mmap_size > file_size) {
@@ -1946,13 +1946,13 @@ out_err:
 
 int perf_session__process_events(struct perf_session *session)
 {
-	u64 size = perf_data_file__size(session->file);
+	u64 size = perf_data__size(session->data);
 	int err;
 
 	if (perf_session__register_idle_thread(session) < 0)
 		return -ENOMEM;
 
-	if (!perf_data_file__is_pipe(session->file))
+	if (!perf_data__is_pipe(session->data))
 		err = __perf_session__process_events(session,
 						     session->header.data_offset,
 						     session->header.data_size, size);
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 3f63ee12471d..da1434a7c120 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -33,13 +33,13 @@ struct perf_session {
 	void			*one_mmap_addr;
 	u64			one_mmap_offset;
 	struct ordered_events	ordered_events;
-	struct perf_data_file	*file;
+	struct perf_data	*data;
 	struct perf_tool	*tool;
 };
 
 struct perf_tool;
 
-struct perf_session *perf_session__new(struct perf_data_file *file,
+struct perf_session *perf_session__new(struct perf_data *data,
 				       bool repipe, struct perf_tool *tool);
 void perf_session__delete(struct perf_session *session);
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 84a33f1e9ec9..a00eacdf02ed 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -226,6 +226,9 @@ static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
 	if (sym_l == sym_r)
 		return 0;
 
+	if (sym_l->inlined || sym_r->inlined)
+		return strcmp(sym_l->name, sym_r->name);
+
 	if (sym_l->start != sym_r->start)
 		return (int64_t)(sym_r->start - sym_l->start);
 
@@ -284,6 +287,9 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
 			ret += repsep_snprintf(bf + ret, size - ret, "%.*s",
 					       width - ret,
 					       sym->name);
+			if (sym->inlined)
+				ret += repsep_snprintf(bf + ret, size - ret,
+						       " (inlined)");
 		}
 	} else {
 		size_t len = BITS_PER_LONG / 4;
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index b2b55e5149a7..f5901c10a563 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -130,7 +130,6 @@ struct hist_entry {
 	};
 	char			*srcline;
 	char			*srcfile;
-	struct inline_node	*inline_node;
 	struct symbol		*parent;
 	struct branch_info	*branch_info;
 	struct hists		*hists;
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index 4105682afc7a..d19f05c56de6 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -11,7 +11,7 @@
 #include "util/debug.h"
 #include "util/callchain.h"
 #include "srcline.h"
-
+#include "string2.h"
 #include "symbol.h"
 
 bool srcline_full_filename;
@@ -34,28 +34,17 @@ static const char *dso__name(struct dso *dso)
 	return dso_name;
 }
 
-static int inline_list__append(char *filename, char *funcname, int line_nr,
-			       struct inline_node *node, struct dso *dso)
+static int inline_list__append(struct symbol *symbol, char *srcline,
+			       struct inline_node *node)
 {
 	struct inline_list *ilist;
-	char *demangled;
 
 	ilist = zalloc(sizeof(*ilist));
 	if (ilist == NULL)
 		return -1;
 
-	ilist->filename = filename;
-	ilist->line_nr = line_nr;
-
-	if (dso != NULL) {
-		demangled = dso__demangle_sym(dso, 0, funcname);
-		if (demangled == NULL) {
-			ilist->funcname = funcname;
-		} else {
-			ilist->funcname = demangled;
-			free(funcname);
-		}
-	}
+	ilist->symbol = symbol;
+	ilist->srcline = srcline;
 
 	if (callchain_param.order == ORDER_CALLEE)
 		list_add_tail(&ilist->list, &node->val);
@@ -65,6 +54,65 @@ static int inline_list__append(char *filename, char *funcname, int line_nr,
 	return 0;
 }
 
+/* basename version that takes a const input string */
+static const char *gnu_basename(const char *path)
+{
+	const char *base = strrchr(path, '/');
+
+	return base ? base + 1 : path;
+}
+
+static char *srcline_from_fileline(const char *file, unsigned int line)
+{
+	char *srcline;
+
+	if (!file)
+		return NULL;
+
+	if (!srcline_full_filename)
+		file = gnu_basename(file);
+
+	if (asprintf(&srcline, "%s:%u", file, line) < 0)
+		return NULL;
+
+	return srcline;
+}
+
+static struct symbol *new_inline_sym(struct dso *dso,
+				     struct symbol *base_sym,
+				     const char *funcname)
+{
+	struct symbol *inline_sym;
+	char *demangled = NULL;
+
+	if (dso) {
+		demangled = dso__demangle_sym(dso, 0, funcname);
+		if (demangled)
+			funcname = demangled;
+	}
+
+	if (base_sym && strcmp(funcname, base_sym->name) == 0) {
+		/* reuse the real, existing symbol */
+		inline_sym = base_sym;
+		/* ensure that we don't alias an inlined symbol, which could
+		 * lead to double frees in inline_node__delete
+		 */
+		assert(!base_sym->inlined);
+	} else {
+		/* create a fake symbol for the inline frame */
+		inline_sym = symbol__new(base_sym ? base_sym->start : 0,
+					 base_sym ? base_sym->end : 0,
+					 base_sym ? base_sym->binding : 0,
+					 funcname);
+		if (inline_sym)
+			inline_sym->inlined = 1;
+	}
+
+	free(demangled);
+
+	return inline_sym;
+}
+
 #ifdef HAVE_LIBBFD_SUPPORT
 
 /*
@@ -208,18 +256,23 @@ static void addr2line_cleanup(struct a2l_data *a2l)
 #define MAX_INLINE_NEST 1024
 
 static int inline_list__append_dso_a2l(struct dso *dso,
-				       struct inline_node *node)
+				       struct inline_node *node,
+				       struct symbol *sym)
 {
 	struct a2l_data *a2l = dso->a2l;
-	char *funcname = a2l->funcname ? strdup(a2l->funcname) : NULL;
-	char *filename = a2l->filename ? strdup(a2l->filename) : NULL;
+	struct symbol *inline_sym = new_inline_sym(dso, sym, a2l->funcname);
+	char *srcline = NULL;
 
-	return inline_list__append(filename, funcname, a2l->line, node, dso);
+	if (a2l->filename)
+		srcline = srcline_from_fileline(a2l->filename, a2l->line);
+
+	return inline_list__append(inline_sym, srcline, node);
 }
 
 static int addr2line(const char *dso_name, u64 addr,
 		     char **file, unsigned int *line, struct dso *dso,
-		     bool unwind_inlines, struct inline_node *node)
+		     bool unwind_inlines, struct inline_node *node,
+		     struct symbol *sym)
 {
 	int ret = 0;
 	struct a2l_data *a2l = dso->a2l;
@@ -245,7 +298,7 @@ static int addr2line(const char *dso_name, u64 addr,
 	if (unwind_inlines) {
 		int cnt = 0;
 
-		if (node && inline_list__append_dso_a2l(dso, node))
+		if (node && inline_list__append_dso_a2l(dso, node, sym))
 			return 0;
 
 		while (bfd_find_inliner_info(a2l->abfd, &a2l->filename,
@@ -256,7 +309,7 @@ static int addr2line(const char *dso_name, u64 addr,
 				a2l->filename = NULL;
 
 			if (node != NULL) {
-				if (inline_list__append_dso_a2l(dso, node))
+				if (inline_list__append_dso_a2l(dso, node, sym))
 					return 0;
 				// found at least one inline frame
 				ret = 1;
@@ -288,7 +341,7 @@ void dso__free_a2l(struct dso *dso)
 }
 
 static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
-	struct dso *dso)
+					struct dso *dso, struct symbol *sym)
 {
 	struct inline_node *node;
 
@@ -301,17 +354,8 @@ static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
 	INIT_LIST_HEAD(&node->val);
 	node->addr = addr;
 
-	if (!addr2line(dso_name, addr, NULL, NULL, dso, TRUE, node))
-		goto out_free_inline_node;
-
-	if (list_empty(&node->val))
-		goto out_free_inline_node;
-
+	addr2line(dso_name, addr, NULL, NULL, dso, true, node, sym);
 	return node;
-
-out_free_inline_node:
-	inline_node__delete(node);
-	return NULL;
 }
 
 #else /* HAVE_LIBBFD_SUPPORT */
@@ -341,7 +385,8 @@ static int addr2line(const char *dso_name, u64 addr,
 		     char **file, unsigned int *line_nr,
 		     struct dso *dso __maybe_unused,
 		     bool unwind_inlines __maybe_unused,
-		     struct inline_node *node __maybe_unused)
+		     struct inline_node *node __maybe_unused,
+		     struct symbol *sym __maybe_unused)
 {
 	FILE *fp;
 	char cmd[PATH_MAX];
@@ -381,16 +426,18 @@ void dso__free_a2l(struct dso *dso __maybe_unused)
 }
 
 static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
-	struct dso *dso __maybe_unused)
+					struct dso *dso __maybe_unused,
+					struct symbol *sym)
 {
 	FILE *fp;
 	char cmd[PATH_MAX];
 	struct inline_node *node;
 	char *filename = NULL;
-	size_t len;
+	char *funcname = NULL;
+	size_t filelen, funclen;
 	unsigned int line_nr = 0;
 
-	scnprintf(cmd, sizeof(cmd), "addr2line -e %s -i %016"PRIx64,
+	scnprintf(cmd, sizeof(cmd), "addr2line -e %s -i -f %016"PRIx64,
 		  dso_name, addr);
 
 	fp = popen(cmd, "r");
@@ -408,26 +455,34 @@ static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
 	INIT_LIST_HEAD(&node->val);
 	node->addr = addr;
 
-	while (getline(&filename, &len, fp) != -1) {
-		if (filename_split(filename, &line_nr) != 1) {
-			free(filename);
+	/* addr2line -f generates two lines for each inlined functions */
+	while (getline(&funcname, &funclen, fp) != -1) {
+		char *srcline;
+		struct symbol *inline_sym;
+
+		rtrim(funcname);
+
+		if (getline(&filename, &filelen, fp) == -1)
 			goto out;
-		}
 
-		if (inline_list__append(filename, NULL, line_nr, node,
-					NULL) != 0)
+		if (filename_split(filename, &line_nr) != 1)
 			goto out;
 
-		filename = NULL;
+		srcline = srcline_from_fileline(filename, line_nr);
+		inline_sym = new_inline_sym(dso, sym, funcname);
+
+		if (inline_list__append(inline_sym, srcline, node) != 0) {
+			free(srcline);
+			if (inline_sym && inline_sym->inlined)
+				symbol__delete(inline_sym);
+			goto out;
+		}
 	}
 
 out:
 	pclose(fp);
-
-	if (list_empty(&node->val)) {
-		inline_node__delete(node);
-		return NULL;
-	}
+	free(filename);
+	free(funcname);
 
 	return node;
 }
@@ -455,19 +510,18 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 	if (dso_name == NULL)
 		goto out;
 
-	if (!addr2line(dso_name, addr, &file, &line, dso, unwind_inlines, NULL))
+	if (!addr2line(dso_name, addr, &file, &line, dso,
+		       unwind_inlines, NULL, sym))
 		goto out;
 
-	if (asprintf(&srcline, "%s:%u",
-				srcline_full_filename ? file : basename(file),
-				line) < 0) {
-		free(file);
+	srcline = srcline_from_fileline(file, line);
+	free(file);
+
+	if (!srcline)
 		goto out;
-	}
 
 	dso->a2l_fails = 0;
 
-	free(file);
 	return srcline;
 
 out:
@@ -501,7 +555,74 @@ char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 	return __get_srcline(dso, addr, sym, show_sym, show_addr, false);
 }
 
-struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr)
+struct srcline_node {
+	u64			addr;
+	char			*srcline;
+	struct rb_node		rb_node;
+};
+
+void srcline__tree_insert(struct rb_root *tree, u64 addr, char *srcline)
+{
+	struct rb_node **p = &tree->rb_node;
+	struct rb_node *parent = NULL;
+	struct srcline_node *i, *node;
+
+	node = zalloc(sizeof(struct srcline_node));
+	if (!node) {
+		perror("not enough memory for the srcline node");
+		return;
+	}
+
+	node->addr = addr;
+	node->srcline = srcline;
+
+	while (*p != NULL) {
+		parent = *p;
+		i = rb_entry(parent, struct srcline_node, rb_node);
+		if (addr < i->addr)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+	rb_link_node(&node->rb_node, parent, p);
+	rb_insert_color(&node->rb_node, tree);
+}
+
+char *srcline__tree_find(struct rb_root *tree, u64 addr)
+{
+	struct rb_node *n = tree->rb_node;
+
+	while (n) {
+		struct srcline_node *i = rb_entry(n, struct srcline_node,
+						  rb_node);
+
+		if (addr < i->addr)
+			n = n->rb_left;
+		else if (addr > i->addr)
+			n = n->rb_right;
+		else
+			return i->srcline;
+	}
+
+	return NULL;
+}
+
+void srcline__tree_delete(struct rb_root *tree)
+{
+	struct srcline_node *pos;
+	struct rb_node *next = rb_first(tree);
+
+	while (next) {
+		pos = rb_entry(next, struct srcline_node, rb_node);
+		next = rb_next(&pos->rb_node);
+		rb_erase(&pos->rb_node, tree);
+		free_srcline(pos->srcline);
+		zfree(&pos);
+	}
+}
+
+struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr,
+					    struct symbol *sym)
 {
 	const char *dso_name;
 
@@ -509,7 +630,7 @@ struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr)
 	if (dso_name == NULL)
 		return NULL;
 
-	return addr2inlines(dso_name, addr, dso);
+	return addr2inlines(dso_name, addr, dso, sym);
 }
 
 void inline_node__delete(struct inline_node *node)
@@ -518,10 +639,63 @@ void inline_node__delete(struct inline_node *node)
 
 	list_for_each_entry_safe(ilist, tmp, &node->val, list) {
 		list_del_init(&ilist->list);
-		zfree(&ilist->filename);
-		zfree(&ilist->funcname);
+		free_srcline(ilist->srcline);
+		/* only the inlined symbols are owned by the list */
+		if (ilist->symbol && ilist->symbol->inlined)
+			symbol__delete(ilist->symbol);
 		free(ilist);
 	}
 
 	free(node);
 }
+
+void inlines__tree_insert(struct rb_root *tree, struct inline_node *inlines)
+{
+	struct rb_node **p = &tree->rb_node;
+	struct rb_node *parent = NULL;
+	const u64 addr = inlines->addr;
+	struct inline_node *i;
+
+	while (*p != NULL) {
+		parent = *p;
+		i = rb_entry(parent, struct inline_node, rb_node);
+		if (addr < i->addr)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+	rb_link_node(&inlines->rb_node, parent, p);
+	rb_insert_color(&inlines->rb_node, tree);
+}
+
+struct inline_node *inlines__tree_find(struct rb_root *tree, u64 addr)
+{
+	struct rb_node *n = tree->rb_node;
+
+	while (n) {
+		struct inline_node *i = rb_entry(n, struct inline_node,
+						 rb_node);
+
+		if (addr < i->addr)
+			n = n->rb_left;
+		else if (addr > i->addr)
+			n = n->rb_right;
+		else
+			return i;
+	}
+
+	return NULL;
+}
+
+void inlines__tree_delete(struct rb_root *tree)
+{
+	struct inline_node *pos;
+	struct rb_node *next = rb_first(tree);
+
+	while (next) {
+		pos = rb_entry(next, struct inline_node, rb_node);
+		next = rb_next(&pos->rb_node);
+		rb_erase(&pos->rb_node, tree);
+		inline_node__delete(pos);
+	}
+}
diff --git a/tools/perf/util/srcline.h b/tools/perf/util/srcline.h
index 8e73f607dfa3..847b7086182c 100644
--- a/tools/perf/util/srcline.h
+++ b/tools/perf/util/srcline.h
@@ -3,6 +3,7 @@
 #define PERF_SRCLINE_H
 
 #include <linux/list.h>
+#include <linux/rbtree.h>
 #include <linux/types.h>
 
 struct dso;
@@ -15,21 +16,38 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 		  bool show_sym, bool show_addr, bool unwind_inlines);
 void free_srcline(char *srcline);
 
+/* insert the srcline into the DSO, which will take ownership */
+void srcline__tree_insert(struct rb_root *tree, u64 addr, char *srcline);
+/* find previously inserted srcline */
+char *srcline__tree_find(struct rb_root *tree, u64 addr);
+/* delete all srclines within the tree */
+void srcline__tree_delete(struct rb_root *tree);
+
 #define SRCLINE_UNKNOWN  ((char *) "??:0")
 
 struct inline_list {
-	char			*filename;
-	char			*funcname;
-	unsigned int		line_nr;
+	struct symbol		*symbol;
+	char			*srcline;
 	struct list_head	list;
 };
 
 struct inline_node {
 	u64			addr;
 	struct list_head	val;
+	struct rb_node		rb_node;
 };
 
-struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr);
+/* parse inlined frames for the given address */
+struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr,
+					    struct symbol *sym);
+/* free resources associated to the inline node list */
 void inline_node__delete(struct inline_node *node);
 
+/* insert the inline node list into the DSO, which will take ownership */
+void inlines__tree_insert(struct rb_root *tree, struct inline_node *inlines);
+/* find previously inserted inline node list */
+struct inline_node *inlines__tree_find(struct rb_root *tree, u64 addr);
+/* delete all nodes within the tree of inline_node s */
+void inlines__tree_delete(struct rb_root *tree);
+
 #endif /* PERF_SRCLINE_H */
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 37363869c9a1..855e35cbb1dc 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -7,6 +7,7 @@
 #include "rblist.h"
 #include "evlist.h"
 #include "expr.h"
+#include "metricgroup.h"
 
 enum {
 	CTX_BIT_USER	= 1 << 0,
@@ -56,7 +57,6 @@ struct saved_value {
 	struct rb_node rb_node;
 	struct perf_evsel *evsel;
 	int cpu;
-	int ctx;
 	struct stats stats;
 };
 
@@ -67,8 +67,6 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
 					     rb_node);
 	const struct saved_value *b = entry;
 
-	if (a->ctx != b->ctx)
-		return a->ctx - b->ctx;
 	if (a->cpu != b->cpu)
 		return a->cpu - b->cpu;
 	if (a->evsel == b->evsel)
@@ -90,13 +88,12 @@ static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused,
 }
 
 static struct saved_value *saved_value_lookup(struct perf_evsel *evsel,
-					      int cpu, int ctx,
+					      int cpu,
 					      bool create)
 {
 	struct rb_node *nd;
 	struct saved_value dm = {
 		.cpu = cpu,
-		.ctx = ctx,
 		.evsel = evsel,
 	};
 	nd = rblist__find(&runtime_saved_values, &dm);
@@ -182,59 +179,60 @@ void perf_stat__reset_shadow_stats(void)
  * more semantic information such as miss/hit ratios,
  * instruction rates, etc:
  */
-void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
+void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,
 				    int cpu)
 {
 	int ctx = evsel_context(counter);
 
+	count *= counter->scale;
+
 	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK) ||
 	    perf_evsel__match(counter, SOFTWARE, SW_CPU_CLOCK))
-		update_stats(&runtime_nsecs_stats[cpu], count[0]);
+		update_stats(&runtime_nsecs_stats[cpu], count);
 	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
-		update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
+		update_stats(&runtime_cycles_stats[ctx][cpu], count);
 	else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
-		update_stats(&runtime_cycles_in_tx_stats[ctx][cpu], count[0]);
+		update_stats(&runtime_cycles_in_tx_stats[ctx][cpu], count);
 	else if (perf_stat_evsel__is(counter, TRANSACTION_START))
-		update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
+		update_stats(&runtime_transaction_stats[ctx][cpu], count);
 	else if (perf_stat_evsel__is(counter, ELISION_START))
-		update_stats(&runtime_elision_stats[ctx][cpu], count[0]);
+		update_stats(&runtime_elision_stats[ctx][cpu], count);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS))
-		update_stats(&runtime_topdown_total_slots[ctx][cpu], count[0]);
+		update_stats(&runtime_topdown_total_slots[ctx][cpu], count);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED))
-		update_stats(&runtime_topdown_slots_issued[ctx][cpu], count[0]);
+		update_stats(&runtime_topdown_slots_issued[ctx][cpu], count);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED))
-		update_stats(&runtime_topdown_slots_retired[ctx][cpu], count[0]);
+		update_stats(&runtime_topdown_slots_retired[ctx][cpu], count);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES))
-		update_stats(&runtime_topdown_fetch_bubbles[ctx][cpu],count[0]);
+		update_stats(&runtime_topdown_fetch_bubbles[ctx][cpu], count);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
-		update_stats(&runtime_topdown_recovery_bubbles[ctx][cpu], count[0]);
+		update_stats(&runtime_topdown_recovery_bubbles[ctx][cpu], count);
 	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
-		update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count[0]);
+		update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count);
 	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
-		update_stats(&runtime_stalled_cycles_back_stats[ctx][cpu], count[0]);
+		update_stats(&runtime_stalled_cycles_back_stats[ctx][cpu], count);
 	else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
-		update_stats(&runtime_branches_stats[ctx][cpu], count[0]);
+		update_stats(&runtime_branches_stats[ctx][cpu], count);
 	else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
-		update_stats(&runtime_cacherefs_stats[ctx][cpu], count[0]);
+		update_stats(&runtime_cacherefs_stats[ctx][cpu], count);
 	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
-		update_stats(&runtime_l1_dcache_stats[ctx][cpu], count[0]);
+		update_stats(&runtime_l1_dcache_stats[ctx][cpu], count);
 	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
-		update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
+		update_stats(&runtime_ll_cache_stats[ctx][cpu], count);
 	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
-		update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
+		update_stats(&runtime_ll_cache_stats[ctx][cpu], count);
 	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
-		update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]);
+		update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count);
 	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
-		update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]);
+		update_stats(&runtime_itlb_cache_stats[ctx][cpu], count);
 	else if (perf_stat_evsel__is(counter, SMI_NUM))
-		update_stats(&runtime_smi_num_stats[ctx][cpu], count[0]);
+		update_stats(&runtime_smi_num_stats[ctx][cpu], count);
 	else if (perf_stat_evsel__is(counter, APERF))
-		update_stats(&runtime_aperf_stats[ctx][cpu], count[0]);
+		update_stats(&runtime_aperf_stats[ctx][cpu], count);
 
 	if (counter->collect_stat) {
-		struct saved_value *v = saved_value_lookup(counter, cpu, ctx,
-							   true);
-		update_stats(&v->stats, count[0]);
+		struct saved_value *v = saved_value_lookup(counter, cpu, true);
+		update_stats(&v->stats, count);
 	}
 }
 
@@ -628,15 +626,68 @@ static void print_smi_cost(int cpu, struct perf_evsel *evsel,
 	out->print_metric(out->ctx, NULL, "%4.0f", "SMI#", smi_num);
 }
 
+static void generic_metric(const char *metric_expr,
+			   struct perf_evsel **metric_events,
+			   char *name,
+			   const char *metric_name,
+			   double avg,
+			   int cpu,
+			   struct perf_stat_output_ctx *out)
+{
+	print_metric_t print_metric = out->print_metric;
+	struct parse_ctx pctx;
+	double ratio;
+	int i;
+	void *ctxp = out->ctx;
+
+	expr__ctx_init(&pctx);
+	expr__add_id(&pctx, name, avg);
+	for (i = 0; metric_events[i]; i++) {
+		struct saved_value *v;
+		struct stats *stats;
+		double scale;
+
+		if (!strcmp(metric_events[i]->name, "duration_time")) {
+			stats = &walltime_nsecs_stats;
+			scale = 1e-9;
+		} else {
+			v = saved_value_lookup(metric_events[i], cpu, false);
+			if (!v)
+				break;
+			stats = &v->stats;
+			scale = 1.0;
+		}
+		expr__add_id(&pctx, metric_events[i]->name, avg_stats(stats)*scale);
+	}
+	if (!metric_events[i]) {
+		const char *p = metric_expr;
+
+		if (expr__parse(&ratio, &pctx, &p) == 0)
+			print_metric(ctxp, NULL, "%8.1f",
+				metric_name ?
+				metric_name :
+				out->force_header ?  name : "",
+				ratio);
+		else
+			print_metric(ctxp, NULL, NULL,
+				     out->force_header ?
+				     (metric_name ? metric_name : name) : "", 0);
+	} else
+		print_metric(ctxp, NULL, NULL, "", 0);
+}
+
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 				   double avg, int cpu,
-				   struct perf_stat_output_ctx *out)
+				   struct perf_stat_output_ctx *out,
+				   struct rblist *metric_events)
 {
 	void *ctxp = out->ctx;
 	print_metric_t print_metric = out->print_metric;
 	double total, ratio = 0.0, total2;
 	const char *color = NULL;
 	int ctx = evsel_context(evsel);
+	struct metric_event *me;
+	int num = 1;
 
 	if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
@@ -820,33 +871,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 		else
 			print_metric(ctxp, NULL, NULL, name, 0);
 	} else if (evsel->metric_expr) {
-		struct parse_ctx pctx;
-		int i;
-
-		expr__ctx_init(&pctx);
-		expr__add_id(&pctx, evsel->name, avg);
-		for (i = 0; evsel->metric_events[i]; i++) {
-			struct saved_value *v;
-
-			v = saved_value_lookup(evsel->metric_events[i], cpu, ctx, false);
-			if (!v)
-				break;
-			expr__add_id(&pctx, evsel->metric_events[i]->name,
-					     avg_stats(&v->stats));
-		}
-		if (!evsel->metric_events[i]) {
-			const char *p = evsel->metric_expr;
-
-			if (expr__parse(&ratio, &pctx, &p) == 0)
-				print_metric(ctxp, NULL, "%8.1f",
-					evsel->metric_name ?
-					evsel->metric_name :
-					out->force_header ?  evsel->name : "",
-					ratio);
-			else
-				print_metric(ctxp, NULL, NULL, "", 0);
-		} else
-			print_metric(ctxp, NULL, NULL, "", 0);
+		generic_metric(evsel->metric_expr, evsel->metric_events, evsel->name,
+				evsel->metric_name, avg, cpu, out);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
 		char unit_buf[10];
@@ -864,6 +890,20 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 	} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
 		print_smi_cost(cpu, evsel, out);
 	} else {
-		print_metric(ctxp, NULL, NULL, NULL, 0);
+		num = 0;
 	}
+
+	if ((me = metricgroup__lookup(metric_events, evsel, false)) != NULL) {
+		struct metric_expr *mexp;
+
+		list_for_each_entry (mexp, &me->head, nd) {
+			if (num++ > 0)
+				out->new_line(ctxp);
+			generic_metric(mexp->metric_expr, mexp->metric_events,
+					evsel->name, mexp->metric_name,
+					avg, cpu, out);
+		}
+	}
+	if (num == 0)
+		print_metric(ctxp, NULL, NULL, NULL, 0);
 }
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index c9bae5fb8b47..151e9efd7286 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -70,7 +70,7 @@ double rel_stddev_stats(double stddev, double avg)
 bool __perf_evsel_stat__is(struct perf_evsel *evsel,
 			   enum perf_stat_evsel_id id)
 {
-	struct perf_stat_evsel *ps = evsel->priv;
+	struct perf_stat_evsel *ps = evsel->stats;
 
 	return ps->id == id;
 }
@@ -94,7 +94,7 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = {
 
 void perf_stat_evsel_id_init(struct perf_evsel *evsel)
 {
-	struct perf_stat_evsel *ps = evsel->priv;
+	struct perf_stat_evsel *ps = evsel->stats;
 	int i;
 
 	/* ps->id is 0 hence PERF_STAT_EVSEL_ID__NONE by default */
@@ -110,7 +110,7 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel)
 static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 {
 	int i;
-	struct perf_stat_evsel *ps = evsel->priv;
+	struct perf_stat_evsel *ps = evsel->stats;
 
 	for (i = 0; i < 3; i++)
 		init_stats(&ps->res_stats[i]);
@@ -120,8 +120,8 @@ static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 
 static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 {
-	evsel->priv = zalloc(sizeof(struct perf_stat_evsel));
-	if (evsel->priv == NULL)
+	evsel->stats = zalloc(sizeof(struct perf_stat_evsel));
+	if (evsel->stats == NULL)
 		return -ENOMEM;
 	perf_evsel__reset_stat_priv(evsel);
 	return 0;
@@ -129,11 +129,11 @@ static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 
 static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
 {
-	struct perf_stat_evsel *ps = evsel->priv;
+	struct perf_stat_evsel *ps = evsel->stats;
 
 	if (ps)
 		free(ps->group_data);
-	zfree(&evsel->priv);
+	zfree(&evsel->stats);
 }
 
 static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
@@ -278,7 +278,9 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel
 			perf_evsel__compute_deltas(evsel, cpu, thread, count);
 		perf_counts_values__scale(count, config->scale, NULL);
 		if (config->aggr_mode == AGGR_NONE)
-			perf_stat__update_shadow_stats(evsel, count->values, cpu);
+			perf_stat__update_shadow_stats(evsel, count->val, cpu);
+		if (config->aggr_mode == AGGR_THREAD)
+			perf_stat__update_shadow_stats(evsel, count->val, 0);
 		break;
 	case AGGR_GLOBAL:
 		aggr->val += count->val;
@@ -319,9 +321,8 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 			      struct perf_evsel *counter)
 {
 	struct perf_counts_values *aggr = &counter->counts->aggr;
-	struct perf_stat_evsel *ps = counter->priv;
+	struct perf_stat_evsel *ps = counter->stats;
 	u64 *count = counter->counts->aggr.values;
-	u64 val;
 	int i, ret;
 
 	aggr->val = aggr->ena = aggr->run = 0;
@@ -361,8 +362,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	/*
 	 * Save the full runtime - to allow normalization during printout:
 	 */
-	val = counter->scale * *count;
-	perf_stat__update_shadow_stats(counter, &val, 0);
+	perf_stat__update_shadow_stats(counter, *count, 0);
 
 	return 0;
 }
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 96326b1f9443..eefca5c981fd 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -83,7 +83,7 @@ typedef void (*new_line_t )(void *ctx);
 
 void perf_stat__init_shadow_stats(void);
 void perf_stat__reset_shadow_stats(void);
-void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
+void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,
 				    int cpu);
 struct perf_stat_output_ctx {
 	void *ctx;
@@ -92,9 +92,11 @@ struct perf_stat_output_ctx {
 	bool force_header;
 };
 
+struct rblist;
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 				   double avg, int cpu,
-				   struct perf_stat_output_ctx *out);
+				   struct perf_stat_output_ctx *out,
+				   struct rblist *metric_events);
 void perf_stat__collect_metric_expr(struct perf_evlist *);
 
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 6492ef38b090..1b67a8639dfe 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -46,6 +46,7 @@ struct symbol_conf symbol_conf = {
 	.show_hist_headers	= true,
 	.symfs			= "",
 	.event_group		= true,
+	.inline_name		= true,
 };
 
 static enum dso_binary_type binary_type_symtab[] = {
@@ -227,7 +228,7 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
 	struct maps *maps = &mg->maps[type];
 	struct map *next, *curr;
 
-	pthread_rwlock_wrlock(&maps->lock);
+	down_write(&maps->lock);
 
 	curr = maps__first(maps);
 	if (curr == NULL)
@@ -247,7 +248,7 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
 		curr->end = ~0ULL;
 
 out_unlock:
-	pthread_rwlock_unlock(&maps->lock);
+	up_write(&maps->lock);
 }
 
 struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
@@ -1672,7 +1673,7 @@ struct map *map_groups__find_by_name(struct map_groups *mg,
 	struct maps *maps = &mg->maps[type];
 	struct map *map;
 
-	pthread_rwlock_rdlock(&maps->lock);
+	down_read(&maps->lock);
 
 	for (map = maps__first(maps); map; map = map__next(map)) {
 		if (map->dso && strcmp(map->dso->short_name, name) == 0)
@@ -1682,7 +1683,7 @@ struct map *map_groups__find_by_name(struct map_groups *mg,
 	map = NULL;
 
 out_unlock:
-	pthread_rwlock_unlock(&maps->lock);
+	up_read(&maps->lock);
 	return map;
 }
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 6352022593c6..a4f0075b4e5c 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -60,6 +60,7 @@ struct symbol {
 	u8		binding;
 	u8		idle:1;
 	u8		ignore:1;
+	u8		inlined:1;
 	u8		arch_sym;
 	char		name[0];
 };
@@ -209,6 +210,7 @@ struct addr_location {
 	struct thread *thread;
 	struct map    *map;
 	struct symbol *sym;
+	const char    *srcline;
 	u64	      addr;
 	char	      level;
 	u8	      filtered;
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 1dbcd3c8dee0..68b65b10579b 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -46,6 +46,8 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 		thread->cpu = -1;
 		INIT_LIST_HEAD(&thread->namespaces_list);
 		INIT_LIST_HEAD(&thread->comm_list);
+		init_rwsem(&thread->namespaces_lock);
+		init_rwsem(&thread->comm_lock);
 
 		comm_str = malloc(32);
 		if (!comm_str)
@@ -84,18 +86,26 @@ void thread__delete(struct thread *thread)
 		map_groups__put(thread->mg);
 		thread->mg = NULL;
 	}
+	down_write(&thread->namespaces_lock);
 	list_for_each_entry_safe(namespaces, tmp_namespaces,
 				 &thread->namespaces_list, list) {
 		list_del(&namespaces->list);
 		namespaces__free(namespaces);
 	}
+	up_write(&thread->namespaces_lock);
+
+	down_write(&thread->comm_lock);
 	list_for_each_entry_safe(comm, tmp_comm, &thread->comm_list, list) {
 		list_del(&comm->list);
 		comm__free(comm);
 	}
+	up_write(&thread->comm_lock);
+
 	unwind__finish_access(thread);
 	nsinfo__zput(thread->nsinfo);
 
+	exit_rwsem(&thread->namespaces_lock);
+	exit_rwsem(&thread->comm_lock);
 	free(thread);
 }
 
@@ -126,8 +136,8 @@ struct namespaces *thread__namespaces(const struct thread *thread)
 	return list_first_entry(&thread->namespaces_list, struct namespaces, list);
 }
 
-int thread__set_namespaces(struct thread *thread, u64 timestamp,
-			   struct namespaces_event *event)
+static int __thread__set_namespaces(struct thread *thread, u64 timestamp,
+				    struct namespaces_event *event)
 {
 	struct namespaces *new, *curr = thread__namespaces(thread);
 
@@ -150,6 +160,17 @@ int thread__set_namespaces(struct thread *thread, u64 timestamp,
 	return 0;
 }
 
+int thread__set_namespaces(struct thread *thread, u64 timestamp,
+			   struct namespaces_event *event)
+{
+	int ret;
+
+	down_write(&thread->namespaces_lock);
+	ret = __thread__set_namespaces(thread, timestamp, event);
+	up_write(&thread->namespaces_lock);
+	return ret;
+}
+
 struct comm *thread__comm(const struct thread *thread)
 {
 	if (list_empty(&thread->comm_list))
@@ -171,8 +192,8 @@ struct comm *thread__exec_comm(const struct thread *thread)
 	return last;
 }
 
-int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
-		       bool exec)
+static int ____thread__set_comm(struct thread *thread, const char *str,
+				u64 timestamp, bool exec)
 {
 	struct comm *new, *curr = thread__comm(thread);
 
@@ -196,6 +217,17 @@ int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
 	return 0;
 }
 
+int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
+		       bool exec)
+{
+	int ret;
+
+	down_write(&thread->comm_lock);
+	ret = ____thread__set_comm(thread, str, timestamp, exec);
+	up_write(&thread->comm_lock);
+	return ret;
+}
+
 int thread__set_comm_from_proc(struct thread *thread)
 {
 	char path[64];
@@ -213,7 +245,7 @@ int thread__set_comm_from_proc(struct thread *thread)
 	return err;
 }
 
-const char *thread__comm_str(const struct thread *thread)
+static const char *__thread__comm_str(const struct thread *thread)
 {
 	const struct comm *comm = thread__comm(thread);
 
@@ -223,6 +255,17 @@ const char *thread__comm_str(const struct thread *thread)
 	return comm__str(comm);
 }
 
+const char *thread__comm_str(const struct thread *thread)
+{
+	const char *str;
+
+	down_read((struct rw_semaphore *)&thread->comm_lock);
+	str = __thread__comm_str(thread);
+	up_read((struct rw_semaphore *)&thread->comm_lock);
+
+	return str;
+}
+
 /* CHECKME: it should probably better return the max comm len from its comm list */
 int thread__comm_len(struct thread *thread)
 {
@@ -265,7 +308,7 @@ static int __thread__prepare_access(struct thread *thread)
 		struct maps *maps = &thread->mg->maps[i];
 		struct map *map;
 
-		pthread_rwlock_rdlock(&maps->lock);
+		down_read(&maps->lock);
 
 		for (map = maps__first(maps); map; map = map__next(map)) {
 			err = unwind__prepare_access(thread, map, &initialized);
@@ -273,7 +316,7 @@ static int __thread__prepare_access(struct thread *thread)
 				break;
 		}
 
-		pthread_rwlock_unlock(&maps->lock);
+		up_read(&maps->lock);
 	}
 
 	return err;
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index fdcea7c0cac1..40cfa36c022a 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -10,6 +10,7 @@
 #include "symbol.h"
 #include <strlist.h>
 #include <intlist.h>
+#include "rwsem.h"
 
 struct thread_stack;
 struct unwind_libunwind_ops;
@@ -30,7 +31,9 @@ struct thread {
 	int			comm_len;
 	bool			dead; /* if set thread has exited */
 	struct list_head	namespaces_list;
+	struct rw_semaphore	namespaces_lock;
 	struct list_head	comm_list;
+	struct rw_semaphore	comm_lock;
 	u64			db_id;
 
 	void			*priv;
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index 506150a75bd0..9892323cdd7c 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -38,6 +38,7 @@ struct perf_top {
 	int		   sym_pcnt_filter;
 	const char	   *sym_filter;
 	float		   min_percent;
+	unsigned int	   nr_threads_synthesize;
 };
 
 #define CONSOLE_CLEAR ""
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index e7d60d05596d..d7f2113462fb 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -28,7 +28,6 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/wait.h>
-#include <pthread.h>
 #include <fcntl.h>
 #include <unistd.h>
 #include <errno.h>
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 8a9a677f7576..40b425949aa3 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -27,7 +27,6 @@
 #include <sys/stat.h>
 #include <sys/wait.h>
 #include <sys/mman.h>
-#include <pthread.h>
 #include <fcntl.h>
 #include <unistd.h>
 #include <errno.h>
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 3687b720327a..a789f952b3e9 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -7,6 +7,7 @@
 #include <sys/stat.h>
 #include <sys/utsname.h>
 #include <dirent.h>
+#include <fcntl.h>
 #include <inttypes.h>
 #include <signal.h>
 #include <stdio.h>
@@ -23,6 +24,19 @@
 /*
  * XXX We need to find a better place for these things...
  */
+
+bool perf_singlethreaded = true;
+
+void perf_set_singlethreaded(void)
+{
+	perf_singlethreaded = true;
+}
+
+void perf_set_multithreaded(void)
+{
+	perf_singlethreaded = false;
+}
+
 unsigned int page_size;
 int cacheline_size;
 
@@ -175,7 +189,7 @@ out:
 	return err;
 }
 
-int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
+static int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
 {
 	void *ptr;
 	loff_t pgoff;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index b52765e6d7b4..01434509c2e9 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -6,7 +6,6 @@
 /* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */
 #define _DEFAULT_SOURCE 1
 
-#include <fcntl.h>
 #include <stdbool.h>
 #include <stddef.h>
 #include <stdlib.h>
@@ -36,7 +35,6 @@ bool lsdir_no_dot_filter(const char *name, struct dirent *d);
 int copyfile(const char *from, const char *to);
 int copyfile_mode(const char *from, const char *to, mode_t mode);
 int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi);
-int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size);
 
 ssize_t readn(int fd, void *buf, size_t n);
 ssize_t writen(int fd, const void *buf, size_t n);
@@ -65,4 +63,9 @@ int sched_getcpu(void);
 int setns(int fd, int nstype);
 #endif
 
+extern bool perf_singlethreaded;
+
+void perf_set_singlethreaded(void);
+void perf_set_multithreaded(void);
+
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index cffcda448c28..0acb1ec0e2f0 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -320,7 +320,7 @@ struct dso *machine__findnew_vdso(struct machine *machine,
 	struct vdso_info *vdso_info;
 	struct dso *dso = NULL;
 
-	pthread_rwlock_wrlock(&machine->dsos.lock);
+	down_write(&machine->dsos.lock);
 	if (!machine->vdso_info)
 		machine->vdso_info = vdso_info__new();
 
@@ -348,7 +348,7 @@ struct dso *machine__findnew_vdso(struct machine *machine,
 
 out_unlock:
 	dso__get(dso);
-	pthread_rwlock_unlock(&machine->dsos.lock);
+	up_write(&machine->dsos.lock);
 	return dso;
 }
 
diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c
index 008fe68d7b76..a725b958cf31 100644
--- a/tools/perf/util/zlib.c
+++ b/tools/perf/util/zlib.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <fcntl.h>
 #include <stdio.h>
 #include <unistd.h>
 #include <sys/stat.h>