Linux-libre 4.4-gnupck-4.4-gnu

74 files changed, 2756 insertions, 658 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index e5f18a288..591b3fe3e 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -5,6 +5,7 @@ libperf-y += build-id.o
 libperf-y += config.o
 libperf-y += ctype.o
 libperf-y += db-export.o
+libperf-y += env.o
 libperf-y += environment.o
 libperf-y += event.o
 libperf-y += evlist.o
@@ -86,6 +87,7 @@ libperf-$(CONFIG_AUXTRACE) += intel-bts.o
 libperf-y += parse-branch-options.o
 libperf-y += parse-regs-options.o
 
+libperf-$(CONFIG_LIBBPF) += bpf-loader.o
 libperf-$(CONFIG_LIBELF) += symbol-elf.o
 libperf-$(CONFIG_LIBELF) += probe-file.o
 libperf-$(CONFIG_LIBELF) += probe-event.o
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index d1eece70b..1dd1949b0 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -548,8 +548,11 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 
 	pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr));
 
-	if (addr < sym->start || addr >= sym->end)
+	if (addr < sym->start || addr >= sym->end) {
+		pr_debug("%s(%d): ERANGE! sym->name=%s, start=%#" PRIx64 ", addr=%#" PRIx64 ", end=%#" PRIx64 "\n",
+		       __func__, __LINE__, sym->name, sym->start, addr, sym->end);
 		return -ERANGE;
+	}
 
 	offset = addr - sym->start;
 	h = annotation__histogram(notes, evidx);
@@ -1081,6 +1084,7 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
 	struct kcore_extract kce;
 	bool delete_extract = false;
 	int lineno = 0;
+	int nline;
 
 	if (filename)
 		symbol__join_symfs(symfs_filename, filename);
@@ -1176,6 +1180,9 @@ fallback:
 
 		ret = decompress_to_file(m.ext, symfs_filename, fd);
 
+		if (ret)
+			pr_err("Cannot decompress %s %s\n", m.ext, symfs_filename);
+
 		free(m.ext);
 		close(fd);
 
@@ -1201,13 +1208,25 @@ fallback:
 	pr_debug("Executing: %s\n", command);
 
 	file = popen(command, "r");
-	if (!file)
+	if (!file) {
+		pr_err("Failure running %s\n", command);
+		/*
+		 * If we were using debug info should retry with
+		 * original binary.
+		 */
 		goto out_remove_tmp;
+	}
 
-	while (!feof(file))
+	nline = 0;
+	while (!feof(file)) {
 		if (symbol__parse_objdump_line(sym, map, file, privsize,
 			    &lineno) < 0)
 			break;
+		nline++;
+	}
+
+	if (nline == 0)
+		pr_err("No output from %s\n", command);
 
 	/*
 	 * kallsyms does not have symbol sizes so there may a nop at the end.
@@ -1601,6 +1620,7 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map,
 	len = symbol__size(sym);
 
 	if (print_lines) {
+		srcline_full_filename = full_paths;
 		symbol__get_source_line(sym, map, evsel, &source_line, len);
 		print_summary(&source_line, dso->long_name);
 	}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index e9996092a..cea323d9e 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -122,7 +122,7 @@ struct annotated_source {
 	struct list_head   source;
 	struct source_line *lines;
 	int    		   nr_histograms;
-	int    		   sizeof_sym_hist;
+	size_t		   sizeof_sym_hist;
 	struct cyc_hist	   *cycles_hist;
 	struct sym_hist	   histograms[0];
 };
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index a980e7c50..7f10430af 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -926,6 +926,8 @@ s64 perf_event__process_auxtrace(struct perf_tool *tool,
 #define PERF_ITRACE_DEFAULT_PERIOD		100000
 #define PERF_ITRACE_DEFAULT_CALLCHAIN_SZ	16
 #define PERF_ITRACE_MAX_CALLCHAIN_SZ		1024
+#define PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ	64
+#define PERF_ITRACE_MAX_LAST_BRANCH_SZ		1024
 
 void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
 {
@@ -936,6 +938,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
 	synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
 	synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
 	synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
+	synth_opts->last_branch_sz = PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ;
 }
 
 /*
@@ -950,6 +953,7 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 	const char *p;
 	char *endptr;
 	bool period_type_set = false;
+	bool period_set = false;
 
 	synth_opts->set = true;
 
@@ -971,6 +975,7 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 				p += 1;
 			if (isdigit(*p)) {
 				synth_opts->period = strtoull(p, &endptr, 10);
+				period_set = true;
 				p = endptr;
 				while (*p == ' ' || *p == ',')
 					p += 1;
@@ -1041,6 +1046,23 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 				synth_opts->callchain_sz = val;
 			}
 			break;
+		case 'l':
+			synth_opts->last_branch = true;
+			synth_opts->last_branch_sz =
+					PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ;
+			while (*p == ' ' || *p == ',')
+				p += 1;
+			if (isdigit(*p)) {
+				unsigned int val;
+
+				val = strtoul(p, &endptr, 10);
+				p = endptr;
+				if (!val ||
+				    val > PERF_ITRACE_MAX_LAST_BRANCH_SZ)
+					goto out_err;
+				synth_opts->last_branch_sz = val;
+			}
+			break;
 		case ' ':
 		case ',':
 			break;
@@ -1053,7 +1075,7 @@ out:
 		if (!period_type_set)
 			synth_opts->period_type =
 					PERF_ITRACE_DEFAULT_PERIOD_TYPE;
-		if (!synth_opts->period)
+		if (!period_set)
 			synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
 	}
 
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index bf72b77a5..b86f90db1 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -63,7 +63,9 @@ enum itrace_period_type {
  * @calls: limit branch samples to calls (can be combined with @returns)
  * @returns: limit branch samples to returns (can be combined with @calls)
  * @callchain: add callchain to 'instructions' events
+ * @last_branch: add branch context to 'instruction' events
  * @callchain_sz: maximum callchain size
+ * @last_branch_sz: branch context size
  * @period: 'instructions' events period
  * @period_type: 'instructions' events period type
  */
@@ -79,7 +81,9 @@ struct itrace_synth_opts {
 	bool			calls;
 	bool			returns;
 	bool			callchain;
+	bool			last_branch;
 	unsigned int		callchain_sz;
+	unsigned int		last_branch_sz;
 	unsigned long long	period;
 	enum itrace_period_type	period_type;
 };
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
new file mode 100644
index 000000000..4c5041137
--- /dev/null
+++ b/tools/perf/util/bpf-loader.c
@@ -0,0 +1,457 @@
+/*
+ * bpf-loader.c
+ *
+ * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015 Huawei Inc.
+ */
+
+#include <bpf/libbpf.h>
+#include <linux/err.h>
+#include "perf.h"
+#include "debug.h"
+#include "bpf-loader.h"
+#include "probe-event.h"
+#include "probe-finder.h" // for MAX_PROBES
+#include "llvm-utils.h"
+
+#define DEFINE_PRINT_FN(name, level) \
+static int libbpf_##name(const char *fmt, ...)	\
+{						\
+	va_list args;				\
+	int ret;				\
+						\
+	va_start(args, fmt);			\
+	ret = veprintf(level, verbose, pr_fmt(fmt), args);\
+	va_end(args);				\
+	return ret;				\
+}
+
+DEFINE_PRINT_FN(warning, 1)
+DEFINE_PRINT_FN(info, 1)
+DEFINE_PRINT_FN(debug, 1)
+
+struct bpf_prog_priv {
+	struct perf_probe_event pev;
+};
+
+static bool libbpf_initialized;
+
+struct bpf_object *
+bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name)
+{
+	struct bpf_object *obj;
+
+	if (!libbpf_initialized) {
+		libbpf_set_print(libbpf_warning,
+				 libbpf_info,
+				 libbpf_debug);
+		libbpf_initialized = true;
+	}
+
+	obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, name);
+	if (IS_ERR(obj)) {
+		pr_debug("bpf: failed to load buffer\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	return obj;
+}
+
+struct bpf_object *bpf__prepare_load(const char *filename, bool source)
+{
+	struct bpf_object *obj;
+
+	if (!libbpf_initialized) {
+		libbpf_set_print(libbpf_warning,
+				 libbpf_info,
+				 libbpf_debug);
+		libbpf_initialized = true;
+	}
+
+	if (source) {
+		int err;
+		void *obj_buf;
+		size_t obj_buf_sz;
+
+		err = llvm__compile_bpf(filename, &obj_buf, &obj_buf_sz);
+		if (err)
+			return ERR_PTR(-BPF_LOADER_ERRNO__COMPILE);
+		obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, filename);
+		free(obj_buf);
+	} else
+		obj = bpf_object__open(filename);
+
+	if (IS_ERR(obj)) {
+		pr_debug("bpf: failed to load %s\n", filename);
+		return obj;
+	}
+
+	return obj;
+}
+
+void bpf__clear(void)
+{
+	struct bpf_object *obj, *tmp;
+
+	bpf_object__for_each_safe(obj, tmp) {
+		bpf__unprobe(obj);
+		bpf_object__close(obj);
+	}
+}
+
+static void
+bpf_prog_priv__clear(struct bpf_program *prog __maybe_unused,
+		     void *_priv)
+{
+	struct bpf_prog_priv *priv = _priv;
+
+	cleanup_perf_probe_events(&priv->pev, 1);
+	free(priv);
+}
+
+static int
+config_bpf_program(struct bpf_program *prog)
+{
+	struct perf_probe_event *pev = NULL;
+	struct bpf_prog_priv *priv = NULL;
+	const char *config_str;
+	int err;
+
+	config_str = bpf_program__title(prog, false);
+	if (IS_ERR(config_str)) {
+		pr_debug("bpf: unable to get title for program\n");
+		return PTR_ERR(config_str);
+	}
+
+	priv = calloc(sizeof(*priv), 1);
+	if (!priv) {
+		pr_debug("bpf: failed to alloc priv\n");
+		return -ENOMEM;
+	}
+	pev = &priv->pev;
+
+	pr_debug("bpf: config program '%s'\n", config_str);
+	err = parse_perf_probe_command(config_str, pev);
+	if (err < 0) {
+		pr_debug("bpf: '%s' is not a valid config string\n",
+			 config_str);
+		err = -BPF_LOADER_ERRNO__CONFIG;
+		goto errout;
+	}
+
+	if (pev->group && strcmp(pev->group, PERF_BPF_PROBE_GROUP)) {
+		pr_debug("bpf: '%s': group for event is set and not '%s'.\n",
+			 config_str, PERF_BPF_PROBE_GROUP);
+		err = -BPF_LOADER_ERRNO__GROUP;
+		goto errout;
+	} else if (!pev->group)
+		pev->group = strdup(PERF_BPF_PROBE_GROUP);
+
+	if (!pev->group) {
+		pr_debug("bpf: strdup failed\n");
+		err = -ENOMEM;
+		goto errout;
+	}
+
+	if (!pev->event) {
+		pr_debug("bpf: '%s': event name is missing. Section name should be 'key=value'\n",
+			 config_str);
+		err = -BPF_LOADER_ERRNO__EVENTNAME;
+		goto errout;
+	}
+	pr_debug("bpf: config '%s' is ok\n", config_str);
+
+	err = bpf_program__set_private(prog, priv, bpf_prog_priv__clear);
+	if (err) {
+		pr_debug("Failed to set priv for program '%s'\n", config_str);
+		goto errout;
+	}
+
+	return 0;
+
+errout:
+	if (pev)
+		clear_perf_probe_event(pev);
+	free(priv);
+	return err;
+}
+
+static int bpf__prepare_probe(void)
+{
+	static int err = 0;
+	static bool initialized = false;
+
+	/*
+	 * Make err static, so if init failed the first, bpf__prepare_probe()
+	 * fails each time without calling init_probe_symbol_maps multiple
+	 * times.
+	 */
+	if (initialized)
+		return err;
+
+	initialized = true;
+	err = init_probe_symbol_maps(false);
+	if (err < 0)
+		pr_debug("Failed to init_probe_symbol_maps\n");
+	probe_conf.max_probes = MAX_PROBES;
+	return err;
+}
+
+int bpf__probe(struct bpf_object *obj)
+{
+	int err = 0;
+	struct bpf_program *prog;
+	struct bpf_prog_priv *priv;
+	struct perf_probe_event *pev;
+
+	err = bpf__prepare_probe();
+	if (err) {
+		pr_debug("bpf__prepare_probe failed\n");
+		return err;
+	}
+
+	bpf_object__for_each_program(prog, obj) {
+		err = config_bpf_program(prog);
+		if (err)
+			goto out;
+
+		err = bpf_program__get_private(prog, (void **)&priv);
+		if (err || !priv)
+			goto out;
+		pev = &priv->pev;
+
+		err = convert_perf_probe_events(pev, 1);
+		if (err < 0) {
+			pr_debug("bpf_probe: failed to convert perf probe events");
+			goto out;
+		}
+
+		err = apply_perf_probe_events(pev, 1);
+		if (err < 0) {
+			pr_debug("bpf_probe: failed to apply perf probe events");
+			goto out;
+		}
+	}
+out:
+	return err < 0 ? err : 0;
+}
+
+#define EVENTS_WRITE_BUFSIZE  4096
+int bpf__unprobe(struct bpf_object *obj)
+{
+	int err, ret = 0;
+	struct bpf_program *prog;
+	struct bpf_prog_priv *priv;
+
+	bpf_object__for_each_program(prog, obj) {
+		int i;
+
+		err = bpf_program__get_private(prog, (void **)&priv);
+		if (err || !priv)
+			continue;
+
+		for (i = 0; i < priv->pev.ntevs; i++) {
+			struct probe_trace_event *tev = &priv->pev.tevs[i];
+			char name_buf[EVENTS_WRITE_BUFSIZE];
+			struct strfilter *delfilter;
+
+			snprintf(name_buf, EVENTS_WRITE_BUFSIZE,
+				 "%s:%s", tev->group, tev->event);
+			name_buf[EVENTS_WRITE_BUFSIZE - 1] = '\0';
+
+			delfilter = strfilter__new(name_buf, NULL);
+			if (!delfilter) {
+				pr_debug("Failed to create filter for unprobing\n");
+				ret = -ENOMEM;
+				continue;
+			}
+
+			err = del_perf_probe_events(delfilter);
+			strfilter__delete(delfilter);
+			if (err) {
+				pr_debug("Failed to delete %s\n", name_buf);
+				ret = err;
+				continue;
+			}
+		}
+	}
+	return ret;
+}
+
+int bpf__load(struct bpf_object *obj)
+{
+	int err;
+
+	err = bpf_object__load(obj);
+	if (err) {
+		pr_debug("bpf: load objects failed\n");
+		return err;
+	}
+	return 0;
+}
+
+int bpf__foreach_tev(struct bpf_object *obj,
+		     bpf_prog_iter_callback_t func,
+		     void *arg)
+{
+	struct bpf_program *prog;
+	int err;
+
+	bpf_object__for_each_program(prog, obj) {
+		struct probe_trace_event *tev;
+		struct perf_probe_event *pev;
+		struct bpf_prog_priv *priv;
+		int i, fd;
+
+		err = bpf_program__get_private(prog,
+				(void **)&priv);
+		if (err || !priv) {
+			pr_debug("bpf: failed to get private field\n");
+			return -BPF_LOADER_ERRNO__INTERNAL;
+		}
+
+		pev = &priv->pev;
+		for (i = 0; i < pev->ntevs; i++) {
+			tev = &pev->tevs[i];
+
+			fd = bpf_program__fd(prog);
+			if (fd < 0) {
+				pr_debug("bpf: failed to get file descriptor\n");
+				return fd;
+			}
+
+			err = (*func)(tev, fd, arg);
+			if (err) {
+				pr_debug("bpf: call back failed, stop iterate\n");
+				return err;
+			}
+		}
+	}
+	return 0;
+}
+
+#define ERRNO_OFFSET(e)		((e) - __BPF_LOADER_ERRNO__START)
+#define ERRCODE_OFFSET(c)	ERRNO_OFFSET(BPF_LOADER_ERRNO__##c)
+#define NR_ERRNO	(__BPF_LOADER_ERRNO__END - __BPF_LOADER_ERRNO__START)
+
+static const char *bpf_loader_strerror_table[NR_ERRNO] = {
+	[ERRCODE_OFFSET(CONFIG)]	= "Invalid config string",
+	[ERRCODE_OFFSET(GROUP)]		= "Invalid group name",
+	[ERRCODE_OFFSET(EVENTNAME)]	= "No event name found in config string",
+	[ERRCODE_OFFSET(INTERNAL)]	= "BPF loader internal error",
+	[ERRCODE_OFFSET(COMPILE)]	= "Error when compiling BPF scriptlet",
+};
+
+static int
+bpf_loader_strerror(int err, char *buf, size_t size)
+{
+	char sbuf[STRERR_BUFSIZE];
+	const char *msg;
+
+	if (!buf || !size)
+		return -1;
+
+	err = err > 0 ? err : -err;
+
+	if (err >= __LIBBPF_ERRNO__START)
+		return libbpf_strerror(err, buf, size);
+
+	if (err >= __BPF_LOADER_ERRNO__START && err < __BPF_LOADER_ERRNO__END) {
+		msg = bpf_loader_strerror_table[ERRNO_OFFSET(err)];
+		snprintf(buf, size, "%s", msg);
+		buf[size - 1] = '\0';
+		return 0;
+	}
+
+	if (err >= __BPF_LOADER_ERRNO__END)
+		snprintf(buf, size, "Unknown bpf loader error %d", err);
+	else
+		snprintf(buf, size, "%s",
+			 strerror_r(err, sbuf, sizeof(sbuf)));
+
+	buf[size - 1] = '\0';
+	return -1;
+}
+
+#define bpf__strerror_head(err, buf, size) \
+	char sbuf[STRERR_BUFSIZE], *emsg;\
+	if (!size)\
+		return 0;\
+	if (err < 0)\
+		err = -err;\
+	bpf_loader_strerror(err, sbuf, sizeof(sbuf));\
+	emsg = sbuf;\
+	switch (err) {\
+	default:\
+		scnprintf(buf, size, "%s", emsg);\
+		break;
+
+#define bpf__strerror_entry(val, fmt...)\
+	case val: {\
+		scnprintf(buf, size, fmt);\
+		break;\
+	}
+
+#define bpf__strerror_end(buf, size)\
+	}\
+	buf[size - 1] = '\0';
+
+int bpf__strerror_prepare_load(const char *filename, bool source,
+			       int err, char *buf, size_t size)
+{
+	size_t n;
+	int ret;
+
+	n = snprintf(buf, size, "Failed to load %s%s: ",
+			 filename, source ? " from source" : "");
+	if (n >= size) {
+		buf[size - 1] = '\0';
+		return 0;
+	}
+	buf += n;
+	size -= n;
+
+	ret = bpf_loader_strerror(err, buf, size);
+	buf[size - 1] = '\0';
+	return ret;
+}
+
+int bpf__strerror_probe(struct bpf_object *obj __maybe_unused,
+			int err, char *buf, size_t size)
+{
+	bpf__strerror_head(err, buf, size);
+	bpf__strerror_entry(EEXIST, "Probe point exist. Try use 'perf probe -d \"*\"'");
+	bpf__strerror_entry(EACCES, "You need to be root");
+	bpf__strerror_entry(EPERM, "You need to be root, and /proc/sys/kernel/kptr_restrict should be 0");
+	bpf__strerror_entry(ENOENT, "You need to check probing points in BPF file");
+	bpf__strerror_end(buf, size);
+	return 0;
+}
+
+int bpf__strerror_load(struct bpf_object *obj,
+		       int err, char *buf, size_t size)
+{
+	bpf__strerror_head(err, buf, size);
+	case LIBBPF_ERRNO__KVER: {
+		unsigned int obj_kver = bpf_object__get_kversion(obj);
+		unsigned int real_kver;
+
+		if (fetch_kernel_version(&real_kver, NULL, 0)) {
+			scnprintf(buf, size, "Unable to fetch kernel version");
+			break;
+		}
+
+		if (obj_kver != real_kver) {
+			scnprintf(buf, size,
+				  "'version' ("KVER_FMT") doesn't match running kernel ("KVER_FMT")",
+				  KVER_PARAM(obj_kver),
+				  KVER_PARAM(real_kver));
+			break;
+		}
+
+		scnprintf(buf, size, "Failed to load program for unknown reason");
+		break;
+	}
+	bpf__strerror_end(buf, size);
+	return 0;
+}
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
new file mode 100644
index 000000000..9caf3ae4a
--- /dev/null
+++ b/tools/perf/util/bpf-loader.h
@@ -0,0 +1,118 @@
+/*
+ * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015, Huawei Inc.
+ */
+#ifndef __BPF_LOADER_H
+#define __BPF_LOADER_H
+
+#include <linux/compiler.h>
+#include <linux/err.h>
+#include <string.h>
+#include <bpf/libbpf.h>
+#include "probe-event.h"
+#include "debug.h"
+
+enum bpf_loader_errno {
+	__BPF_LOADER_ERRNO__START = __LIBBPF_ERRNO__START - 100,
+	/* Invalid config string */
+	BPF_LOADER_ERRNO__CONFIG = __BPF_LOADER_ERRNO__START,
+	BPF_LOADER_ERRNO__GROUP,	/* Invalid group name */
+	BPF_LOADER_ERRNO__EVENTNAME,	/* Event name is missing */
+	BPF_LOADER_ERRNO__INTERNAL,	/* BPF loader internal error */
+	BPF_LOADER_ERRNO__COMPILE,	/* Error when compiling BPF scriptlet */
+	__BPF_LOADER_ERRNO__END,
+};
+
+struct bpf_object;
+#define PERF_BPF_PROBE_GROUP "perf_bpf_probe"
+
+typedef int (*bpf_prog_iter_callback_t)(struct probe_trace_event *tev,
+					int fd, void *arg);
+
+#ifdef HAVE_LIBBPF_SUPPORT
+struct bpf_object *bpf__prepare_load(const char *filename, bool source);
+int bpf__strerror_prepare_load(const char *filename, bool source,
+			       int err, char *buf, size_t size);
+
+struct bpf_object *bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz,
+					    const char *name);
+
+void bpf__clear(void);
+
+int bpf__probe(struct bpf_object *obj);
+int bpf__unprobe(struct bpf_object *obj);
+int bpf__strerror_probe(struct bpf_object *obj, int err,
+			char *buf, size_t size);
+
+int bpf__load(struct bpf_object *obj);
+int bpf__strerror_load(struct bpf_object *obj, int err,
+		       char *buf, size_t size);
+int bpf__foreach_tev(struct bpf_object *obj,
+		     bpf_prog_iter_callback_t func, void *arg);
+#else
+static inline struct bpf_object *
+bpf__prepare_load(const char *filename __maybe_unused,
+		  bool source __maybe_unused)
+{
+	pr_debug("ERROR: eBPF object loading is disabled during compiling.\n");
+	return ERR_PTR(-ENOTSUP);
+}
+
+static inline struct bpf_object *
+bpf__prepare_load_buffer(void *obj_buf __maybe_unused,
+					   size_t obj_buf_sz __maybe_unused)
+{
+	return ERR_PTR(-ENOTSUP);
+}
+
+static inline void bpf__clear(void) { }
+
+static inline int bpf__probe(struct bpf_object *obj __maybe_unused) { return 0;}
+static inline int bpf__unprobe(struct bpf_object *obj __maybe_unused) { return 0;}
+static inline int bpf__load(struct bpf_object *obj __maybe_unused) { return 0; }
+
+static inline int
+bpf__foreach_tev(struct bpf_object *obj __maybe_unused,
+		 bpf_prog_iter_callback_t func __maybe_unused,
+		 void *arg __maybe_unused)
+{
+	return 0;
+}
+
+static inline int
+__bpf_strerror(char *buf, size_t size)
+{
+	if (!size)
+		return 0;
+	strncpy(buf,
+		"ERROR: eBPF object loading is disabled during compiling.\n",
+		size);
+	buf[size - 1] = '\0';
+	return 0;
+}
+
+static inline
+int bpf__strerror_prepare_load(const char *filename __maybe_unused,
+			       bool source __maybe_unused,
+			       int err __maybe_unused,
+			       char *buf, size_t size)
+{
+	return __bpf_strerror(buf, size);
+}
+
+static inline int
+bpf__strerror_probe(struct bpf_object *obj __maybe_unused,
+		    int err __maybe_unused,
+		    char *buf, size_t size)
+{
+	return __bpf_strerror(buf, size);
+}
+
+static inline int bpf__strerror_load(struct bpf_object *obj __maybe_unused,
+				     int err __maybe_unused,
+				     char *buf, size_t size)
+{
+	return __bpf_strerror(buf, size);
+}
+#endif
+#endif
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index d909459fb..6a7e273a5 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -76,6 +76,7 @@ struct perf_tool build_id__mark_dso_hit_ops = {
 	.exit	= perf_event__exit_del_thread,
 	.attr		 = perf_event__process_attr,
 	.build_id	 = perf_event__process_build_id,
+	.ordered_events	 = true,
 };
 
 int build_id__sprintf(const u8 *build_id, int len, char *bf)
@@ -90,7 +91,7 @@ int build_id__sprintf(const u8 *build_id, int len, char *bf)
 		bid += 2;
 	}
 
-	return raw - build_id;
+	return (bid - bf) + 1;
 }
 
 int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id)
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 773fe13ce..735ad48e1 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -51,10 +51,12 @@ static int parse_callchain_order(const char *value)
 {
 	if (!strncmp(value, "caller", strlen(value))) {
 		callchain_param.order = ORDER_CALLER;
+		callchain_param.order_set = true;
 		return 0;
 	}
 	if (!strncmp(value, "callee", strlen(value))) {
 		callchain_param.order = ORDER_CALLEE;
+		callchain_param.order_set = true;
 		return 0;
 	}
 	return -1;
@@ -77,12 +79,14 @@ static int parse_callchain_sort_key(const char *value)
 	return -1;
 }
 
-int
-parse_callchain_report_opt(const char *arg)
+static int
+__parse_callchain_report_opt(const char *arg, bool allow_record_opt)
 {
 	char *tok;
 	char *endptr;
 	bool minpcnt_set = false;
+	bool record_opt_set = false;
+	bool try_stack_size = false;
 
 	symbol_conf.use_callchain = true;
 
@@ -100,6 +104,28 @@ parse_callchain_report_opt(const char *arg)
 		    !parse_callchain_order(tok) ||
 		    !parse_callchain_sort_key(tok)) {
 			/* parsing ok - move on to the next */
+			try_stack_size = false;
+			goto next;
+		} else if (allow_record_opt && !record_opt_set) {
+			if (parse_callchain_record(tok, &callchain_param))
+				goto try_numbers;
+
+			/* assume that number followed by 'dwarf' is stack size */
+			if (callchain_param.record_mode == CALLCHAIN_DWARF)
+				try_stack_size = true;
+
+			record_opt_set = true;
+			goto next;
+		}
+
+try_numbers:
+		if (try_stack_size) {
+			unsigned long size = 0;
+
+			if (get_stack_size(tok, &size) < 0)
+				return -1;
+			callchain_param.dump_size = size;
+			try_stack_size = false;
 		} else if (!minpcnt_set) {
 			/* try to get the min percent */
 			callchain_param.min_percent = strtod(tok, &endptr);
@@ -112,7 +138,7 @@ parse_callchain_report_opt(const char *arg)
 			if (tok == endptr)
 				return -1;
 		}
-
+next:
 		arg = NULL;
 	}
 
@@ -123,6 +149,16 @@ parse_callchain_report_opt(const char *arg)
 	return 0;
 }
 
+int parse_callchain_report_opt(const char *arg)
+{
+	return __parse_callchain_report_opt(arg, false);
+}
+
+int parse_callchain_top_opt(const char *arg)
+{
+	return __parse_callchain_report_opt(arg, true);
+}
+
 int perf_callchain_config(const char *var, const char *value)
 {
 	char *endptr;
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index acee2b3cd..fce8161e5 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -7,6 +7,30 @@
 #include "event.h"
 #include "symbol.h"
 
+#define HELP_PAD "\t\t\t\t"
+
+#define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace):\n\n"
+
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+# define RECORD_MODE_HELP  HELP_PAD "record_mode:\tcall graph recording mode (fp|dwarf|lbr)\n"
+#else
+# define RECORD_MODE_HELP  HELP_PAD "record_mode:\tcall graph recording mode (fp|lbr)\n"
+#endif
+
+#define RECORD_SIZE_HELP						\
+	HELP_PAD "record_size:\tif record_mode is 'dwarf', max size of stack recording (<bytes>)\n" \
+	HELP_PAD "\t\tdefault: 8192 (bytes)\n"
+
+#define CALLCHAIN_RECORD_HELP  CALLCHAIN_HELP RECORD_MODE_HELP RECORD_SIZE_HELP
+
+#define CALLCHAIN_REPORT_HELP						\
+	HELP_PAD "print_type:\tcall graph printing style (graph|flat|fractal|none)\n" \
+	HELP_PAD "threshold:\tminimum call graph inclusion threshold (<percent>)\n" \
+	HELP_PAD "print_limit:\tmaximum number of call graph entry (<number>)\n" \
+	HELP_PAD "order:\t\tcall graph order (caller|callee)\n" \
+	HELP_PAD "sort_key:\tcall graph sort key (function|address)\n"	\
+	HELP_PAD "branch:\t\tinclude last branch info to call graph (branch)\n"
+
 enum perf_call_graph_mode {
 	CALLCHAIN_NONE,
 	CALLCHAIN_FP,
@@ -63,6 +87,7 @@ struct callchain_param {
 	double			min_percent;
 	sort_chain_func_t	sort;
 	enum chain_order	order;
+	bool			order_set;
 	enum chain_key		key;
 	bool			branch_callstack;
 };
@@ -180,6 +205,7 @@ extern const char record_callchain_help[];
 extern int parse_callchain_record(const char *arg, struct callchain_param *param);
 int parse_callchain_record_opt(const char *arg, struct callchain_param *param);
 int parse_callchain_report_opt(const char *arg);
+int parse_callchain_top_opt(const char *arg);
 int perf_callchain_config(const char *var, const char *value);
 
 static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 3667e2123..10af1e752 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -203,6 +203,23 @@ struct cpu_map *cpu_map__dummy_new(void)
 	return cpus;
 }
 
+struct cpu_map *cpu_map__empty_new(int nr)
+{
+	struct cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int) * nr);
+
+	if (cpus != NULL) {
+		int i;
+
+		cpus->nr = nr;
+		for (i = 0; i < nr; i++)
+			cpus->map[i] = -1;
+
+		atomic_set(&cpus->refcnt, 1);
+	}
+
+	return cpus;
+}
+
 static void cpu_map__delete(struct cpu_map *map)
 {
 	if (map) {
@@ -225,32 +242,32 @@ void cpu_map__put(struct cpu_map *map)
 		cpu_map__delete(map);
 }
 
-int cpu_map__get_socket(struct cpu_map *map, int idx)
+static int cpu__get_topology_int(int cpu, const char *name, int *value)
 {
-	FILE *fp;
-	const char *mnt;
 	char path[PATH_MAX];
-	int cpu, ret;
 
-	if (idx > map->nr)
-		return -1;
+	snprintf(path, PATH_MAX,
+		"devices/system/cpu/cpu%d/topology/%s", cpu, name);
 
-	cpu = map->map[idx];
+	return sysfs__read_int(path, value);
+}
 
-	mnt = sysfs__mountpoint();
-	if (!mnt)
-		return -1;
+int cpu_map__get_socket_id(int cpu)
+{
+	int value, ret = cpu__get_topology_int(cpu, "physical_package_id", &value);
+	return ret ?: value;
+}
 
-	snprintf(path, PATH_MAX,
-		"%s/devices/system/cpu/cpu%d/topology/physical_package_id",
-		mnt, cpu);
+int cpu_map__get_socket(struct cpu_map *map, int idx, void *data __maybe_unused)
+{
+	int cpu;
 
-	fp = fopen(path, "r");
-	if (!fp)
+	if (idx > map->nr)
 		return -1;
-	ret = fscanf(fp, "%d", &cpu);
-	fclose(fp);
-	return ret == 1 ? cpu : -1;
+
+	cpu = map->map[idx];
+
+	return cpu_map__get_socket_id(cpu);
 }
 
 static int cmp_ids(const void *a, const void *b)
@@ -258,8 +275,9 @@ static int cmp_ids(const void *a, const void *b)
 	return *(int *)a - *(int *)b;
 }
 
-static int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
-			      int (*f)(struct cpu_map *map, int cpu))
+int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
+		       int (*f)(struct cpu_map *map, int cpu, void *data),
+		       void *data)
 {
 	struct cpu_map *c;
 	int nr = cpus->nr;
@@ -271,7 +289,7 @@ static int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
 		return -1;
 
 	for (cpu = 0; cpu < nr; cpu++) {
-		s1 = f(cpus, cpu);
+		s1 = f(cpus, cpu, data);
 		for (s2 = 0; s2 < c->nr; s2++) {
 			if (s1 == c->map[s2])
 				break;
@@ -284,40 +302,29 @@ static int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
 	/* ensure we process id in increasing order */
 	qsort(c->map, c->nr, sizeof(int), cmp_ids);
 
-	atomic_set(&cpus->refcnt, 1);
+	atomic_set(&c->refcnt, 1);
 	*res = c;
 	return 0;
 }
 
-int cpu_map__get_core(struct cpu_map *map, int idx)
+int cpu_map__get_core_id(int cpu)
 {
-	FILE *fp;
-	const char *mnt;
-	char path[PATH_MAX];
-	int cpu, ret, s;
+	int value, ret = cpu__get_topology_int(cpu, "core_id", &value);
+	return ret ?: value;
+}
+
+int cpu_map__get_core(struct cpu_map *map, int idx, void *data)
+{
+	int cpu, s;
 
 	if (idx > map->nr)
 		return -1;
 
 	cpu = map->map[idx];
 
-	mnt = sysfs__mountpoint();
-	if (!mnt)
-		return -1;
-
-	snprintf(path, PATH_MAX,
-		"%s/devices/system/cpu/cpu%d/topology/core_id",
-		mnt, cpu);
-
-	fp = fopen(path, "r");
-	if (!fp)
-		return -1;
-	ret = fscanf(fp, "%d", &cpu);
-	fclose(fp);
-	if (ret != 1)
-		return -1;
+	cpu = cpu_map__get_core_id(cpu);
 
-	s = cpu_map__get_socket(map, idx);
+	s = cpu_map__get_socket(map, idx, data);
 	if (s == -1)
 		return -1;
 
@@ -332,12 +339,12 @@ int cpu_map__get_core(struct cpu_map *map, int idx)
 
 int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp)
 {
-	return cpu_map__build_map(cpus, sockp, cpu_map__get_socket);
+	return cpu_map__build_map(cpus, sockp, cpu_map__get_socket, NULL);
 }
 
 int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep)
 {
-	return cpu_map__build_map(cpus, corep, cpu_map__get_core);
+	return cpu_map__build_map(cpus, corep, cpu_map__get_core, NULL);
 }
 
 /* setup simple routines to easily access node numbers given a cpu number */
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 0af9cecb4..85f777245 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -15,11 +15,14 @@ struct cpu_map {
 };
 
 struct cpu_map *cpu_map__new(const char *cpu_list);
+struct cpu_map *cpu_map__empty_new(int nr);
 struct cpu_map *cpu_map__dummy_new(void);
 struct cpu_map *cpu_map__read(FILE *file);
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
-int cpu_map__get_socket(struct cpu_map *map, int idx);
-int cpu_map__get_core(struct cpu_map *map, int idx);
+int cpu_map__get_socket_id(int cpu);
+int cpu_map__get_socket(struct cpu_map *map, int idx, void *data);
+int cpu_map__get_core_id(int cpu);
+int cpu_map__get_core(struct cpu_map *map, int idx, void *data);
 int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp);
 int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep);
 
@@ -85,4 +88,7 @@ static inline int cpu__get_node(int cpu)
 	return cpunode_map[cpu];
 }
 
+int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
+		       int (*f)(struct cpu_map *map, int cpu, void *data),
+		       void *data);
 #endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 7c0c08386..425df5c86 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -933,6 +933,7 @@ static struct dso *__dso__findlink_by_longname(struct rb_root *root,
 		/* Add new node and rebalance tree */
 		rb_link_node(&dso->rb_node, parent, p);
 		rb_insert_color(&dso->rb_node, root);
+		dso->root = root;
 	}
 	return NULL;
 }
@@ -945,15 +946,30 @@ static inline struct dso *__dso__find_by_longname(struct rb_root *root,
 
 void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
 {
+	struct rb_root *root = dso->root;
+
 	if (name == NULL)
 		return;
 
 	if (dso->long_name_allocated)
 		free((char *)dso->long_name);
 
+	if (root) {
+		rb_erase(&dso->rb_node, root);
+		/*
+		 * __dso__findlink_by_longname() isn't guaranteed to add it
+		 * back, so a clean removal is required here.
+		 */
+		RB_CLEAR_NODE(&dso->rb_node);
+		dso->root = NULL;
+	}
+
 	dso->long_name		 = name;
 	dso->long_name_len	 = strlen(name);
 	dso->long_name_allocated = name_allocated;
+
+	if (root)
+		__dso__findlink_by_longname(root, dso, NULL);
 }
 
 void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated)
@@ -1046,6 +1062,7 @@ struct dso *dso__new(const char *name)
 		dso->kernel = DSO_TYPE_USER;
 		dso->needs_swap = DSO_SWAP__UNSET;
 		RB_CLEAR_NODE(&dso->rb_node);
+		dso->root = NULL;
 		INIT_LIST_HEAD(&dso->node);
 		INIT_LIST_HEAD(&dso->data.open_entry);
 		pthread_mutex_init(&dso->lock, NULL);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index fc8db9c76..45ec4d0a5 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -135,6 +135,7 @@ struct dso {
 	pthread_mutex_t	 lock;
 	struct list_head node;
 	struct rb_node	 rb_node;	/* rbtree node sorted by long name */
+	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 {
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
new file mode 100644
index 000000000..6af4f7c36
--- /dev/null
+++ b/tools/perf/util/env.c
@@ -0,0 +1,86 @@
+#include "cpumap.h"
+#include "env.h"
+#include "util.h"
+
+struct perf_env perf_env;
+
+void perf_env__exit(struct perf_env *env)
+{
+	zfree(&env->hostname);
+	zfree(&env->os_release);
+	zfree(&env->version);
+	zfree(&env->arch);
+	zfree(&env->cpu_desc);
+	zfree(&env->cpuid);
+	zfree(&env->cmdline);
+	zfree(&env->cmdline_argv);
+	zfree(&env->sibling_cores);
+	zfree(&env->sibling_threads);
+	zfree(&env->numa_nodes);
+	zfree(&env->pmu_mappings);
+	zfree(&env->cpu);
+}
+
+int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[])
+{
+	int i;
+
+	/*
+	 * If env->cmdline_argv has already been set, do not override it.  This allows
+	 * a command to set the cmdline, parse args and then call another
+	 * builtin function that implements a command -- e.g, cmd_kvm calling
+	 * cmd_record.
+	 */
+	if (env->cmdline_argv != NULL)
+		return 0;
+
+	/* do not include NULL termination */
+	env->cmdline_argv = calloc(argc, sizeof(char *));
+	if (env->cmdline_argv == NULL)
+		goto out_enomem;
+
+	/*
+	 * Must copy argv contents because it gets moved around during option
+	 * parsing:
+	 */
+	for (i = 0; i < argc ; i++) {
+		env->cmdline_argv[i] = argv[i];
+		if (env->cmdline_argv[i] == NULL)
+			goto out_free;
+	}
+
+	env->nr_cmdline = argc;
+
+	return 0;
+out_free:
+	zfree(&env->cmdline_argv);
+out_enomem:
+	return -ENOMEM;
+}
+
+int perf_env__read_cpu_topology_map(struct perf_env *env)
+{
+	int cpu, nr_cpus;
+
+	if (env->cpu != NULL)
+		return 0;
+
+	if (env->nr_cpus_avail == 0)
+		env->nr_cpus_avail = sysconf(_SC_NPROCESSORS_CONF);
+
+	nr_cpus = env->nr_cpus_avail;
+	if (nr_cpus == -1)
+		return -EINVAL;
+
+	env->cpu = calloc(nr_cpus, sizeof(env->cpu[0]));
+	if (env->cpu == NULL)
+		return -ENOMEM;
+
+	for (cpu = 0; cpu < nr_cpus; ++cpu) {
+		env->cpu[cpu].core_id	= cpu_map__get_core_id(cpu);
+		env->cpu[cpu].socket_id	= cpu_map__get_socket_id(cpu);
+	}
+
+	env->nr_cpus_avail = nr_cpus;
+	return 0;
+}
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
new file mode 100644
index 000000000..0132b9557
--- /dev/null
+++ b/tools/perf/util/env.h
@@ -0,0 +1,44 @@
+#ifndef __PERF_ENV_H
+#define __PERF_ENV_H
+
+struct cpu_topology_map {
+	int	socket_id;
+	int	core_id;
+};
+
+struct perf_env {
+	char			*hostname;
+	char			*os_release;
+	char			*version;
+	char			*arch;
+	int			nr_cpus_online;
+	int			nr_cpus_avail;
+	char			*cpu_desc;
+	char			*cpuid;
+	unsigned long long	total_mem;
+	unsigned int		msr_pmu_type;
+
+	int			nr_cmdline;
+	int			nr_sibling_cores;
+	int			nr_sibling_threads;
+	int			nr_numa_nodes;
+	int			nr_pmu_mappings;
+	int			nr_groups;
+	char			*cmdline;
+	const char		**cmdline_argv;
+	char			*sibling_cores;
+	char			*sibling_threads;
+	char			*numa_nodes;
+	char			*pmu_mappings;
+	struct cpu_topology_map	*cpu;
+};
+
+extern struct perf_env perf_env;
+
+void perf_env__exit(struct perf_env *env);
+
+int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]);
+
+int perf_env__read_cpu_topology_map(struct perf_env *env);
+
+#endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 7ff61274e..8b10621b4 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -67,7 +67,8 @@ static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len,
 	char filename[PATH_MAX];
 	char bf[4096];
 	int fd;
-	size_t size = 0, n;
+	size_t size = 0;
+	ssize_t n;
 	char *nl, *name, *tgids, *ppids;
 
 	*tgid = -1;
@@ -167,7 +168,7 @@ static int perf_event__prepare_comm(union perf_event *event, pid_t pid,
 	return 0;
 }
 
-static pid_t perf_event__synthesize_comm(struct perf_tool *tool,
+pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 					 union perf_event *event, pid_t pid,
 					 perf_event__handler_t process,
 					 struct machine *machine)
@@ -378,7 +379,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
 		size_t size;
 
-		if (pos->dso->kernel)
+		if (__map__is_kernel(pos))
 			continue;
 
 		size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
@@ -649,12 +650,12 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 	size_t size;
 	const char *mmap_name;
 	char name_buff[PATH_MAX];
-	struct map *map;
+	struct map *map = machine__kernel_map(machine);
 	struct kmap *kmap;
 	int err;
 	union perf_event *event;
 
-	if (machine->vmlinux_maps[0] == NULL)
+	if (map == NULL)
 		return -1;
 
 	/*
@@ -680,7 +681,6 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
 	}
 
-	map = machine->vmlinux_maps[MAP__FUNCTION];
 	kmap = map__kmap(map);
 	size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
 			"%s%s", mmap_name, kmap->ref_reloc_sym->name) + 1;
@@ -1008,7 +1008,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
 	 * it now.
 	 */
 	if (cpumode == PERF_RECORD_MISC_KERNEL &&
-	    machine->vmlinux_maps[MAP__FUNCTION] == NULL)
+	    machine__kernel_map(machine) == NULL)
 		machine__create_kernel_maps(machine);
 
 	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, al);
@@ -1021,6 +1021,14 @@ int perf_event__preprocess_sample(const union perf_event *event,
 
 	al->sym = NULL;
 	al->cpu = sample->cpu;
+	al->socket = -1;
+
+	if (al->cpu >= 0) {
+		struct perf_env *env = machine->env;
+
+		if (env && env->cpu)
+			al->socket = env->cpu[al->cpu].socket_id;
+	}
 
 	if (al->map) {
 		struct dso *dso = al->map->dso;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index f729df5e2..a0dbcbd4f 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -257,6 +257,7 @@ struct events_stats {
 	u64 total_non_filtered_period;
 	u64 total_lost;
 	u64 total_lost_samples;
+	u64 total_aux_lost;
 	u64 total_invalid_chains;
 	u32 nr_events[PERF_RECORD_HEADER_MAX];
 	u32 nr_non_filtered_samples;
@@ -478,6 +479,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 				  const struct perf_sample *sample,
 				  bool swapped);
 
+pid_t perf_event__synthesize_comm(struct perf_tool *tool,
+				  union perf_event *event, pid_t pid,
+				  perf_event__handler_t process,
+				  struct machine *machine);
+
 int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       union perf_event *event,
 				       pid_t pid, pid_t tgid,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c8fc8a258..d1392194a 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -25,6 +25,7 @@
 #include <linux/bitops.h>
 #include <linux/hash.h>
 #include <linux/log2.h>
+#include <linux/err.h>
 
 static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx);
 static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx);
@@ -164,6 +165,13 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
 	__perf_evlist__propagate_maps(evlist, entry);
 }
 
+void perf_evlist__remove(struct perf_evlist *evlist, struct perf_evsel *evsel)
+{
+	evsel->evlist = NULL;
+	list_del_init(&evsel->node);
+	evlist->nr_entries -= 1;
+}
+
 void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
 				   struct list_head *list)
 {
@@ -197,6 +205,20 @@ void perf_evlist__set_leader(struct perf_evlist *evlist)
 	}
 }
 
+void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr)
+{
+	attr->precise_ip = 3;
+
+	while (attr->precise_ip != 0) {
+		int fd = sys_perf_event_open(attr, 0, -1, -1, 0);
+		if (fd != -1) {
+			close(fd);
+			break;
+		}
+		--attr->precise_ip;
+	}
+}
+
 int perf_evlist__add_default(struct perf_evlist *evlist)
 {
 	struct perf_event_attr attr = {
@@ -207,13 +229,15 @@ int perf_evlist__add_default(struct perf_evlist *evlist)
 
 	event_attr_init(&attr);
 
+	perf_event_attr__set_max_precise_ip(&attr);
+
 	evsel = perf_evsel__new(&attr);
 	if (evsel == NULL)
 		goto error;
 
-	/* use strdup() because free(evsel) assumes name is allocated */
-	evsel->name = strdup("cycles");
-	if (!evsel->name)
+	/* use asprintf() because free(evsel) assumes name is allocated */
+	if (asprintf(&evsel->name, "cycles%.*s",
+		     attr.precise_ip ? attr.precise_ip + 1 : 0, ":ppp") < 0)
 		goto error_free;
 
 	perf_evlist__add(evlist, evsel);
@@ -293,7 +317,7 @@ int perf_evlist__add_newtp(struct perf_evlist *evlist,
 {
 	struct perf_evsel *evsel = perf_evsel__newtp(sys, name);
 
-	if (evsel == NULL)
+	if (IS_ERR(evsel))
 		return -1;
 
 	evsel->handler = handler;
@@ -616,6 +640,21 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
 	return NULL;
 }
 
+struct perf_evsel *perf_evlist__id2evsel_strict(struct perf_evlist *evlist,
+						u64 id)
+{
+	struct perf_sample_id *sid;
+
+	if (!id)
+		return NULL;
+
+	sid = perf_evlist__id2sid(evlist, id);
+	if (sid)
+		return sid->evsel;
+
+	return NULL;
+}
+
 static int perf_evlist__event2id(struct perf_evlist *evlist,
 				 union perf_event *event, u64 *id)
 {
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 115d8b53c..a459fe71b 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -73,6 +73,7 @@ void perf_evlist__exit(struct perf_evlist *evlist);
 void perf_evlist__delete(struct perf_evlist *evlist);
 
 void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry);
+void perf_evlist__remove(struct perf_evlist *evlist, struct perf_evsel *evsel);
 int perf_evlist__add_default(struct perf_evlist *evlist);
 int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
 				     struct perf_event_attr *attrs, size_t nr_attrs);
@@ -104,6 +105,8 @@ int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mas
 int perf_evlist__poll(struct perf_evlist *evlist, int timeout);
 
 struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
+struct perf_evsel *perf_evlist__id2evsel_strict(struct perf_evlist *evlist,
+						u64 id);
 
 struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id);
 
@@ -287,4 +290,6 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 
 void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 				     struct perf_evsel *tracking_evsel);
+
+void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5410483d5..397fb4ed3 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -9,10 +9,11 @@
 
 #include <byteswap.h>
 #include <linux/bitops.h>
-#include <api/fs/debugfs.h>
+#include <api/fs/tracing_path.h>
 #include <traceevent/event-parse.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/perf_event.h>
+#include <linux/err.h>
 #include <sys/resource.h>
 #include "asm/bug.h"
 #include "callchain.h"
@@ -207,6 +208,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->unit	   = "";
 	evsel->scale	   = 1.0;
 	evsel->evlist	   = NULL;
+	evsel->bpf_fd	   = -1;
 	INIT_LIST_HEAD(&evsel->node);
 	INIT_LIST_HEAD(&evsel->config_terms);
 	perf_evsel__object.init(evsel);
@@ -225,11 +227,17 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 	return evsel;
 }
 
+/*
+ * Returns pointer with encoded error via <linux/err.h> interface.
+ */
 struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx)
 {
 	struct perf_evsel *evsel = zalloc(perf_evsel__object.size);
+	int err = -ENOMEM;
 
-	if (evsel != NULL) {
+	if (evsel == NULL) {
+		goto out_err;
+	} else {
 		struct perf_event_attr attr = {
 			.type	       = PERF_TYPE_TRACEPOINT,
 			.sample_type   = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
@@ -240,8 +248,10 @@ struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int
 			goto out_free;
 
 		evsel->tp_format = trace_event__tp_format(sys, name);
-		if (evsel->tp_format == NULL)
+		if (IS_ERR(evsel->tp_format)) {
+			err = PTR_ERR(evsel->tp_format);
 			goto out_free;
+		}
 
 		event_attr_init(&attr);
 		attr.config = evsel->tp_format->id;
@@ -254,7 +264,8 @@ struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int
 out_free:
 	zfree(&evsel->name);
 	free(evsel);
-	return NULL;
+out_err:
+	return ERR_PTR(err);
 }
 
 const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX] = {
@@ -642,6 +653,15 @@ static void apply_config_terms(struct perf_evsel *evsel,
 		case PERF_EVSEL__CONFIG_TERM_STACK_USER:
 			dump_size = term->val.stack_user;
 			break;
+		case PERF_EVSEL__CONFIG_TERM_INHERIT:
+			/*
+			 * attr->inherit should has already been set by
+			 * perf_evsel__config. If user explicitly set
+			 * inherit using config terms, override global
+			 * opt->no_inherit setting.
+			 */
+			attr->inherit = term->val.inherit ? 1 : 0;
+			break;
 		default:
 			break;
 		}
@@ -872,6 +892,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 		attr->clockid = opts->clockid;
 	}
 
+	if (evsel->precise_max)
+		perf_event_attr__set_max_precise_ip(attr);
+
 	/*
 	 * Apply event specific term settings,
 	 * it overloads any global configuration.
@@ -1168,7 +1191,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value)
 		bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU),
 		bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
 		bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
-		bit_name(IDENTIFIER), bit_name(REGS_INTR),
+		bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC),
 		{ .name = NULL, }
 	};
 #undef bit_name
@@ -1249,6 +1272,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(bp_type, p_unsigned);
 	PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex);
 	PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex);
+	PRINT_ATTRf(branch_sample_type, p_unsigned);
 	PRINT_ATTRf(sample_regs_user, p_hex);
 	PRINT_ATTRf(sample_stack_user, p_unsigned);
 	PRINT_ATTRf(clockid, p_signed);
@@ -1333,6 +1357,22 @@ retry_open:
 					  err);
 				goto try_fallback;
 			}
+
+			if (evsel->bpf_fd >= 0) {
+				int evt_fd = FD(evsel, cpu, thread);
+				int bpf_fd = evsel->bpf_fd;
+
+				err = ioctl(evt_fd,
+					    PERF_EVENT_IOC_SET_BPF,
+					    bpf_fd);
+				if (err && errno != EEXIST) {
+					pr_err("failed to attach bpf fd %d: %s\n",
+					       bpf_fd, strerror(errno));
+					err = -EINVAL;
+					goto out_close;
+				}
+			}
+
 			set_rlimit = NO_CHANGE;
 
 			/*
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index ef8925f72..0e49bd742 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -43,6 +43,7 @@ enum {
 	PERF_EVSEL__CONFIG_TERM_TIME,
 	PERF_EVSEL__CONFIG_TERM_CALLGRAPH,
 	PERF_EVSEL__CONFIG_TERM_STACK_USER,
+	PERF_EVSEL__CONFIG_TERM_INHERIT,
 	PERF_EVSEL__CONFIG_TERM_MAX,
 };
 
@@ -55,6 +56,7 @@ struct perf_evsel_config_term {
 		bool	time;
 		char	*callgraph;
 		u64	stack_user;
+		bool	inherit;
 	} val;
 };
 
@@ -90,9 +92,9 @@ struct perf_evsel {
 	double			scale;
 	const char		*unit;
 	struct event_format	*tp_format;
+	off_t			id_offset;
 	union {
 		void		*priv;
-		off_t		id_offset;
 		u64		db_id;
 	};
 	struct cgroup_sel	*cgrp;
@@ -111,6 +113,7 @@ struct perf_evsel {
 	bool			system_wide;
 	bool			tracking;
 	bool			per_pkg;
+	bool			precise_max;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
@@ -120,6 +123,7 @@ struct perf_evsel {
 	char			*group_name;
 	bool			cmdline_group_boundary;
 	struct list_head	config_terms;
+	int			bpf_fd;
 };
 
 union u64_swap {
@@ -130,7 +134,6 @@ union u64_swap {
 struct cpu_map;
 struct target;
 struct thread_map;
-struct perf_evlist;
 struct record_opts;
 
 static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
@@ -162,6 +165,9 @@ static inline struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr)
 
 struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx);
 
+/*
+ * Returns pointer with encoded error via <linux/err.h> interface.
+ */
 static inline struct perf_evsel *perf_evsel__newtp(const char *sys, const char *name)
 {
 	return perf_evsel__newtp_idx(sys, name, 0);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index fce6634ae..43838003c 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -24,9 +24,6 @@
 #include "build-id.h"
 #include "data.h"
 
-static u32 header_argc;
-static const char **header_argv;
-
 /*
  * magic2 = "PERFILE2"
  * must be a numerical value to let the endianness
@@ -88,6 +85,9 @@ int write_padded(int fd, const void *bf, size_t count, size_t count_aligned)
 	return err;
 }
 
+#define string_size(str)						\
+	(PERF_ALIGN((strlen(str) + 1), NAME_ALIGN) + sizeof(u32))
+
 static int do_write_string(int fd, const char *str)
 {
 	u32 len, olen;
@@ -135,37 +135,6 @@ static char *do_read_string(int fd, struct perf_header *ph)
 	return NULL;
 }
 
-int
-perf_header__set_cmdline(int argc, const char **argv)
-{
-	int i;
-
-	/*
-	 * If header_argv has already been set, do not override it.
-	 * This allows a command to set the cmdline, parse args and
-	 * then call another builtin function that implements a
-	 * command -- e.g, cmd_kvm calling cmd_record.
-	 */
-	if (header_argv)
-		return 0;
-
-	header_argc = (u32)argc;
-
-	/* do not include NULL termination */
-	header_argv = calloc(argc, sizeof(char *));
-	if (!header_argv)
-		return -ENOMEM;
-
-	/*
-	 * must copy argv contents because it gets moved
-	 * around during option parsing
-	 */
-	for (i = 0; i < argc ; i++)
-		header_argv[i] = argv[i];
-
-	return 0;
-}
-
 static int write_tracing_data(int fd, struct perf_header *h __maybe_unused,
 			    struct perf_evlist *evlist)
 {
@@ -402,8 +371,8 @@ static int write_cmdline(int fd, struct perf_header *h __maybe_unused,
 {
 	char buf[MAXPATHLEN];
 	char proc[32];
-	u32 i, n;
-	int ret;
+	u32 n;
+	int i, ret;
 
 	/*
 	 * actual atual path to perf binary
@@ -417,7 +386,7 @@ static int write_cmdline(int fd, struct perf_header *h __maybe_unused,
 	buf[ret] = '\0';
 
 	/* account for binary path */
-	n = header_argc + 1;
+	n = perf_env.nr_cmdline + 1;
 
 	ret = do_write(fd, &n, sizeof(n));
 	if (ret < 0)
@@ -427,8 +396,8 @@ static int write_cmdline(int fd, struct perf_header *h __maybe_unused,
 	if (ret < 0)
 		return ret;
 
-	for (i = 0 ; i < header_argc; i++) {
-		ret = do_write_string(fd, header_argv[i]);
+	for (i = 0 ; i < perf_env.nr_cmdline; i++) {
+		ret = do_write_string(fd, perf_env.cmdline_argv[i]);
 		if (ret < 0)
 			return ret;
 	}
@@ -441,6 +410,7 @@ static int write_cmdline(int fd, struct perf_header *h __maybe_unused,
 	"/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list"
 
 struct cpu_topo {
+	u32 cpu_nr;
 	u32 core_sib;
 	u32 thread_sib;
 	char **core_siblings;
@@ -551,7 +521,7 @@ static struct cpu_topo *build_cpu_topology(void)
 		return NULL;
 
 	tp = addr;
-
+	tp->cpu_nr = nr;
 	addr += sizeof(*tp);
 	tp->core_siblings = addr;
 	addr += sz;
@@ -574,7 +544,7 @@ static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused,
 {
 	struct cpu_topo *tp;
 	u32 i;
-	int ret;
+	int ret, j;
 
 	tp = build_cpu_topology();
 	if (!tp)
@@ -598,6 +568,21 @@ static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused,
 		if (ret < 0)
 			break;
 	}
+
+	ret = perf_env__read_cpu_topology_map(&perf_env);
+	if (ret < 0)
+		goto done;
+
+	for (j = 0; j < perf_env.nr_cpus_avail; j++) {
+		ret = do_write(fd, &perf_env.cpu[j].core_id,
+			       sizeof(perf_env.cpu[j].core_id));
+		if (ret < 0)
+			return ret;
+		ret = do_write(fd, &perf_env.cpu[j].socket_id,
+			       sizeof(perf_env.cpu[j].socket_id));
+		if (ret < 0)
+			return ret;
+	}
 done:
 	free_cpu_topo(tp);
 	return ret;
@@ -938,6 +923,7 @@ static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused,
 {
 	int nr, i;
 	char *str;
+	int cpu_nr = ph->env.nr_cpus_online;
 
 	nr = ph->env.nr_sibling_cores;
 	str = ph->env.sibling_cores;
@@ -954,6 +940,13 @@ static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused,
 		fprintf(fp, "# sibling threads : %s\n", str);
 		str += strlen(str) + 1;
 	}
+
+	if (ph->env.cpu != NULL) {
+		for (i = 0; i < cpu_nr; i++)
+			fprintf(fp, "# CPU %d: Core ID %d, Socket ID %d\n", i,
+				ph->env.cpu[i].core_id, ph->env.cpu[i].socket_id);
+	} else
+		fprintf(fp, "# Core ID and Socket ID information is not available\n");
 }
 
 static void free_event_desc(struct perf_evsel *events)
@@ -1582,7 +1575,7 @@ error:
 	return -1;
 }
 
-static int process_cpu_topology(struct perf_file_section *section __maybe_unused,
+static int process_cpu_topology(struct perf_file_section *section,
 				struct perf_header *ph, int fd,
 				void *data __maybe_unused)
 {
@@ -1590,15 +1583,22 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused
 	u32 nr, i;
 	char *str;
 	struct strbuf sb;
+	int cpu_nr = ph->env.nr_cpus_online;
+	u64 size = 0;
+
+	ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu));
+	if (!ph->env.cpu)
+		return -1;
 
 	ret = readn(fd, &nr, sizeof(nr));
 	if (ret != sizeof(nr))
-		return -1;
+		goto free_cpu;
 
 	if (ph->needs_swap)
 		nr = bswap_32(nr);
 
 	ph->env.nr_sibling_cores = nr;
+	size += sizeof(u32);
 	strbuf_init(&sb, 128);
 
 	for (i = 0; i < nr; i++) {
@@ -1608,6 +1608,7 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused
 
 		/* include a NULL character at the end */
 		strbuf_add(&sb, str, strlen(str) + 1);
+		size += string_size(str);
 		free(str);
 	}
 	ph->env.sibling_cores = strbuf_detach(&sb, NULL);
@@ -1620,6 +1621,7 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused
 		nr = bswap_32(nr);
 
 	ph->env.nr_sibling_threads = nr;
+	size += sizeof(u32);
 
 	for (i = 0; i < nr; i++) {
 		str = do_read_string(fd, ph);
@@ -1628,13 +1630,57 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused
 
 		/* include a NULL character at the end */
 		strbuf_add(&sb, str, strlen(str) + 1);
+		size += string_size(str);
 		free(str);
 	}
 	ph->env.sibling_threads = strbuf_detach(&sb, NULL);
+
+	/*
+	 * The header may be from old perf,
+	 * which doesn't include core id and socket id information.
+	 */
+	if (section->size <= size) {
+		zfree(&ph->env.cpu);
+		return 0;
+	}
+
+	for (i = 0; i < (u32)cpu_nr; i++) {
+		ret = readn(fd, &nr, sizeof(nr));
+		if (ret != sizeof(nr))
+			goto free_cpu;
+
+		if (ph->needs_swap)
+			nr = bswap_32(nr);
+
+		if (nr > (u32)cpu_nr) {
+			pr_debug("core_id number is too big."
+				 "You may need to upgrade the perf tool.\n");
+			goto free_cpu;
+		}
+		ph->env.cpu[i].core_id = nr;
+
+		ret = readn(fd, &nr, sizeof(nr));
+		if (ret != sizeof(nr))
+			goto free_cpu;
+
+		if (ph->needs_swap)
+			nr = bswap_32(nr);
+
+		if (nr > (u32)cpu_nr) {
+			pr_debug("socket_id number is too big."
+				 "You may need to upgrade the perf tool.\n");
+			goto free_cpu;
+		}
+
+		ph->env.cpu[i].socket_id = nr;
+	}
+
 	return 0;
 
 error:
 	strbuf_release(&sb);
+free_cpu:
+	zfree(&ph->env.cpu);
 	return -1;
 }
 
@@ -1737,6 +1783,9 @@ static int process_pmu_mappings(struct perf_file_section *section __maybe_unused
 		/* include a NULL character at the end */
 		strbuf_add(&sb, "", 1);
 
+		if (!strcmp(name, "msr"))
+			ph->env.msr_pmu_type = type;
+
 		free(name);
 		pmu_num--;
 	}
@@ -2515,6 +2564,7 @@ int perf_session__read_header(struct perf_session *session)
 		return -ENOMEM;
 
 	session->evlist->env = &header->env;
+	session->machines.host.env = &header->env;
 	if (perf_data_file__is_pipe(file))
 		return perf_header__read_pipe(session);
 
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 396e4965f..05f27cb6b 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -7,7 +7,7 @@
 #include <linux/bitmap.h>
 #include <linux/types.h>
 #include "event.h"
-
+#include "env.h"
 
 enum {
 	HEADER_RESERVED		= 0,	/* always cleared */
@@ -66,31 +66,6 @@ struct perf_header;
 int perf_file_header__read(struct perf_file_header *header,
 			   struct perf_header *ph, int fd);
 
-struct perf_env {
-	char			*hostname;
-	char			*os_release;
-	char			*version;
-	char			*arch;
-	int			nr_cpus_online;
-	int			nr_cpus_avail;
-	char			*cpu_desc;
-	char			*cpuid;
-	unsigned long long	total_mem;
-
-	int			nr_cmdline;
-	int			nr_sibling_cores;
-	int			nr_sibling_threads;
-	int			nr_numa_nodes;
-	int			nr_pmu_mappings;
-	int			nr_groups;
-	char			*cmdline;
-	const char		**cmdline_argv;
-	char			*sibling_cores;
-	char			*sibling_threads;
-	char			*numa_nodes;
-	char			*pmu_mappings;
-};
-
 struct perf_header {
 	enum perf_header_version	version;
 	bool				needs_swap;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 08b6cd945..4fd37d670 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -15,6 +15,8 @@ static bool hists__filter_entry_by_thread(struct hists *hists,
 					  struct hist_entry *he);
 static bool hists__filter_entry_by_symbol(struct hists *hists,
 					  struct hist_entry *he);
+static bool hists__filter_entry_by_socket(struct hists *hists,
+					  struct hist_entry *he);
 
 u16 hists__col_len(struct hists *hists, enum hist_column col)
 {
@@ -130,6 +132,18 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 			hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
 					   symlen);
 		}
+
+		if (h->mem_info->iaddr.sym) {
+			symlen = (int)h->mem_info->iaddr.sym->namelen + 4
+			       + unresolved_col_width + 2;
+			hists__new_col_len(hists, HISTC_MEM_IADDR_SYMBOL,
+					   symlen);
+		} else {
+			symlen = unresolved_col_width + 4 + 2;
+			hists__new_col_len(hists, HISTC_MEM_IADDR_SYMBOL,
+					   symlen);
+		}
+
 		if (h->mem_info->daddr.map) {
 			symlen = dso__name_len(h->mem_info->daddr.map->dso);
 			hists__new_col_len(hists, HISTC_MEM_DADDR_DSO,
@@ -141,9 +155,12 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	} else {
 		symlen = unresolved_col_width + 4 + 2;
 		hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen);
+		hists__new_col_len(hists, HISTC_MEM_IADDR_SYMBOL, symlen);
 		hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO);
 	}
 
+	hists__new_col_len(hists, HISTC_CPU, 3);
+	hists__new_col_len(hists, HISTC_SOCKET, 6);
 	hists__new_col_len(hists, HISTC_MEM_LOCKED, 6);
 	hists__new_col_len(hists, HISTC_MEM_TLB, 22);
 	hists__new_col_len(hists, HISTC_MEM_SNOOP, 12);
@@ -452,6 +469,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 			.map	= al->map,
 			.sym	= al->sym,
 		},
+		.socket	 = al->socket,
 		.cpu	 = al->cpu,
 		.cpumode = al->cpumode,
 		.ip	 = al->addr,
@@ -690,7 +708,7 @@ iter_finish_normal_entry(struct hist_entry_iter *iter,
 }
 
 static int
-iter_prepare_cumulative_entry(struct hist_entry_iter *iter __maybe_unused,
+iter_prepare_cumulative_entry(struct hist_entry_iter *iter,
 			      struct addr_location *al __maybe_unused)
 {
 	struct hist_entry **he_cache;
@@ -702,7 +720,7 @@ iter_prepare_cumulative_entry(struct hist_entry_iter *iter __maybe_unused,
 	 * cumulated only one time to prevent entries more than 100%
 	 * overhead.
 	 */
-	he_cache = malloc(sizeof(*he_cache) * (PERF_MAX_STACK_DEPTH + 1));
+	he_cache = malloc(sizeof(*he_cache) * (iter->max_stack + 1));
 	if (he_cache == NULL)
 		return -ENOMEM;
 
@@ -863,6 +881,8 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 	if (err)
 		return err;
 
+	iter->max_stack = max_stack_depth;
+
 	err = iter->ops->prepare_entry(iter, al);
 	if (err)
 		goto out;
@@ -1024,6 +1044,7 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he)
 	hists__filter_entry_by_dso(hists, he);
 	hists__filter_entry_by_thread(hists, he);
 	hists__filter_entry_by_symbol(hists, he);
+	hists__filter_entry_by_socket(hists, he);
 }
 
 void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
@@ -1143,7 +1164,7 @@ void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 	struct perf_evsel *evsel = hists_to_evsel(hists);
 	bool use_callchain;
 
-	if (evsel && !symbol_conf.show_ref_callgraph)
+	if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph)
 		use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN;
 	else
 		use_callchain = symbol_conf.use_callchain;
@@ -1292,6 +1313,37 @@ void hists__filter_by_symbol(struct hists *hists)
 	}
 }
 
+static bool hists__filter_entry_by_socket(struct hists *hists,
+					  struct hist_entry *he)
+{
+	if ((hists->socket_filter > -1) &&
+	    (he->socket != hists->socket_filter)) {
+		he->filtered |= (1 << HIST_FILTER__SOCKET);
+		return true;
+	}
+
+	return false;
+}
+
+void hists__filter_by_socket(struct hists *hists)
+{
+	struct rb_node *nd;
+
+	hists->stats.nr_non_filtered_samples = 0;
+
+	hists__reset_filter_stats(hists);
+	hists__reset_col_len(hists);
+
+	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		if (hists__filter_entry_by_socket(hists, h))
+			continue;
+
+		hists__remove_entry_filter(hists, h, HIST_FILTER__SOCKET);
+	}
+}
+
 void events_stats__inc(struct events_stats *stats, u32 type)
 {
 	++stats->nr_events[0];
@@ -1517,6 +1569,7 @@ static int hists_evsel__init(struct perf_evsel *evsel)
 	hists->entries_collapsed = RB_ROOT;
 	hists->entries = RB_ROOT;
 	pthread_mutex_init(&hists->lock, NULL);
+	hists->socket_filter = -1;
 	return 0;
 }
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index de6d58e7f..a48a2078d 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -20,6 +20,7 @@ enum hist_filter {
 	HIST_FILTER__SYMBOL,
 	HIST_FILTER__GUEST,
 	HIST_FILTER__HOST,
+	HIST_FILTER__SOCKET,
 };
 
 enum hist_column {
@@ -29,6 +30,7 @@ enum hist_column {
 	HISTC_COMM,
 	HISTC_PARENT,
 	HISTC_CPU,
+	HISTC_SOCKET,
 	HISTC_SRCLINE,
 	HISTC_SRCFILE,
 	HISTC_MISPREDICT,
@@ -47,6 +49,7 @@ enum hist_column {
 	HISTC_MEM_LVL,
 	HISTC_MEM_SNOOP,
 	HISTC_MEM_DCACHELINE,
+	HISTC_MEM_IADDR_SYMBOL,
 	HISTC_TRANSACTION,
 	HISTC_CYCLES,
 	HISTC_NR_COLS, /* Last entry */
@@ -70,6 +73,7 @@ struct hists {
 	struct events_stats	stats;
 	u64			event_stream;
 	u16			col_len[HISTC_NR_COLS];
+	int			socket_filter;
 };
 
 struct hist_entry_iter;
@@ -87,6 +91,7 @@ struct hist_entry_iter {
 	int curr;
 
 	bool hide_unresolved;
+	int max_stack;
 
 	struct perf_evsel *evsel;
 	struct perf_sample *sample;
@@ -144,11 +149,12 @@ size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp);
 void hists__filter_by_dso(struct hists *hists);
 void hists__filter_by_thread(struct hists *hists);
 void hists__filter_by_symbol(struct hists *hists);
+void hists__filter_by_socket(struct hists *hists);
 
 static inline bool hists__has_filter(struct hists *hists)
 {
 	return hists->thread_filter || hists->dso_filter ||
-		hists->symbol_filter_str;
+		hists->symbol_filter_str || (hists->socket_filter > -1);
 }
 
 u16 hists__col_len(struct hists *hists, enum hist_column col);
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index 8f149655f..07c644ed6 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -5,4 +5,12 @@
 const char *get_arch_regstr(unsigned int n);
 #endif
 
+#ifdef HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
+/*
+ * Arch should support fetching the offset of a register in pt_regs
+ * by its name. See kernel's regs_query_register_offset in
+ * arch/xxx/kernel/ptrace.c.
+ */
+int regs_query_register_offset(const char *name);
+#endif
 #endif
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 2386322ec..0611d619a 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -7,6 +7,17 @@ $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_table
 	$(call rule_mkdir)
 	@$(call echo-cmd,gen)$(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@ || rm -f $@
 
-$(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
+$(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/intel-pt-insn-decoder.c util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
+	@(test -d ../../kernel -a -d ../../tools -a -d ../perf && (( \
+	diff -B -I'^#include' util/intel-pt-decoder/insn.c ../../arch/x86/lib/insn.c >/dev/null && \
+	diff -B -I'^#include' util/intel-pt-decoder/inat.c ../../arch/x86/lib/inat.c >/dev/null && \
+	diff -B util/intel-pt-decoder/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null && \
+	diff -B util/intel-pt-decoder/gen-insn-attr-x86.awk ../../arch/x86/tools/gen-insn-attr-x86.awk >/dev/null && \
+	diff -B -I'^#include' util/intel-pt-decoder/insn.h ../../arch/x86/include/asm/insn.h >/dev/null && \
+	diff -B -I'^#include' util/intel-pt-decoder/inat.h ../../arch/x86/include/asm/inat.h >/dev/null && \
+	diff -B -I'^#include' util/intel-pt-decoder/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) \
+	|| echo "Warning: Intel PT: x86 instruction decoder differs from kernel" >&2 )) || true
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)
 
 CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder -Wno-override-init
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 22ba50224..9409d014b 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -650,7 +650,7 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info)
 		if (data->from_mtc && timestamp < data->timestamp &&
 		    data->timestamp - timestamp < decoder->tsc_slip)
 			return 1;
-		while (timestamp < data->timestamp)
+		if (timestamp < data->timestamp)
 			timestamp += (1ULL << 56);
 		if (pkt_info->last_packet_type != INTEL_PT_CYC) {
 			if (data->from_mtc)
@@ -1191,7 +1191,7 @@ static void intel_pt_calc_tsc_timestamp(struct intel_pt_decoder *decoder)
 					timestamp);
 			timestamp = decoder->timestamp;
 		}
-		while (timestamp < decoder->timestamp) {
+		if (timestamp < decoder->timestamp) {
 			intel_pt_log_to("Wraparound timestamp", timestamp);
 			timestamp += (1ULL << 56);
 			decoder->tsc_timestamp = timestamp;
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.c b/tools/perf/util/intel-pt-decoder/intel-pt-log.c
index d09c7d9f9..319bef33a 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-log.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.c
@@ -29,18 +29,18 @@
 
 static FILE *f;
 static char log_name[MAX_LOG_NAME];
-static bool enable_logging;
+bool intel_pt_enable_logging;
 
 void intel_pt_log_enable(void)
 {
-	enable_logging = true;
+	intel_pt_enable_logging = true;
 }
 
 void intel_pt_log_disable(void)
 {
 	if (f)
 		fflush(f);
-	enable_logging = false;
+	intel_pt_enable_logging = false;
 }
 
 void intel_pt_log_set_name(const char *name)
@@ -80,7 +80,7 @@ static void intel_pt_print_no_data(uint64_t pos, int indent)
 
 static int intel_pt_log_open(void)
 {
-	if (!enable_logging)
+	if (!intel_pt_enable_logging)
 		return -1;
 
 	if (f)
@@ -91,15 +91,15 @@ static int intel_pt_log_open(void)
 
 	f = fopen(log_name, "w+");
 	if (!f) {
-		enable_logging = false;
+		intel_pt_enable_logging = false;
 		return -1;
 	}
 
 	return 0;
 }
 
-void intel_pt_log_packet(const struct intel_pt_pkt *packet, int pkt_len,
-			 uint64_t pos, const unsigned char *buf)
+void __intel_pt_log_packet(const struct intel_pt_pkt *packet, int pkt_len,
+			   uint64_t pos, const unsigned char *buf)
 {
 	char desc[INTEL_PT_PKT_DESC_MAX];
 
@@ -111,7 +111,7 @@ void intel_pt_log_packet(const struct intel_pt_pkt *packet, int pkt_len,
 	fprintf(f, "%s\n", desc);
 }
 
-void intel_pt_log_insn(struct intel_pt_insn *intel_pt_insn, uint64_t ip)
+void __intel_pt_log_insn(struct intel_pt_insn *intel_pt_insn, uint64_t ip)
 {
 	char desc[INTEL_PT_INSN_DESC_MAX];
 	size_t len = intel_pt_insn->length;
@@ -128,7 +128,8 @@ void intel_pt_log_insn(struct intel_pt_insn *intel_pt_insn, uint64_t ip)
 		fprintf(f, "Bad instruction!\n");
 }
 
-void intel_pt_log_insn_no_data(struct intel_pt_insn *intel_pt_insn, uint64_t ip)
+void __intel_pt_log_insn_no_data(struct intel_pt_insn *intel_pt_insn,
+				 uint64_t ip)
 {
 	char desc[INTEL_PT_INSN_DESC_MAX];
 
@@ -142,7 +143,7 @@ void intel_pt_log_insn_no_data(struct intel_pt_insn *intel_pt_insn, uint64_t ip)
 		fprintf(f, "Bad instruction!\n");
 }
 
-void intel_pt_log(const char *fmt, ...)
+void __intel_pt_log(const char *fmt, ...)
 {
 	va_list args;
 
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.h b/tools/perf/util/intel-pt-decoder/intel-pt-log.h
index db3942f83..debe751dc 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-log.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.h
@@ -25,20 +25,46 @@ void intel_pt_log_enable(void);
 void intel_pt_log_disable(void);
 void intel_pt_log_set_name(const char *name);
 
-void intel_pt_log_packet(const struct intel_pt_pkt *packet, int pkt_len,
-			 uint64_t pos, const unsigned char *buf);
+void __intel_pt_log_packet(const struct intel_pt_pkt *packet, int pkt_len,
+			   uint64_t pos, const unsigned char *buf);
 
 struct intel_pt_insn;
 
-void intel_pt_log_insn(struct intel_pt_insn *intel_pt_insn, uint64_t ip);
-void intel_pt_log_insn_no_data(struct intel_pt_insn *intel_pt_insn,
-			       uint64_t ip);
+void __intel_pt_log_insn(struct intel_pt_insn *intel_pt_insn, uint64_t ip);
+void __intel_pt_log_insn_no_data(struct intel_pt_insn *intel_pt_insn,
+				 uint64_t ip);
 
 __attribute__((format(printf, 1, 2)))
-void intel_pt_log(const char *fmt, ...);
+void __intel_pt_log(const char *fmt, ...);
+
+#define intel_pt_log(fmt, ...) \
+	do { \
+		if (intel_pt_enable_logging) \
+			__intel_pt_log(fmt, ##__VA_ARGS__); \
+	} while (0)
+
+#define intel_pt_log_packet(arg, ...) \
+	do { \
+		if (intel_pt_enable_logging) \
+			__intel_pt_log_packet(arg, ##__VA_ARGS__); \
+	} while (0)
+
+#define intel_pt_log_insn(arg, ...) \
+	do { \
+		if (intel_pt_enable_logging) \
+			__intel_pt_log_insn(arg, ##__VA_ARGS__); \
+	} while (0)
+
+#define intel_pt_log_insn_no_data(arg, ...) \
+	do { \
+		if (intel_pt_enable_logging) \
+			__intel_pt_log_insn_no_data(arg, ##__VA_ARGS__); \
+	} while (0)
 
 #define x64_fmt "0x%" PRIx64
 
+extern bool intel_pt_enable_logging;
+
 static inline void intel_pt_log_at(const char *msg, uint64_t u)
 {
 	intel_pt_log("%s at " x64_fmt "\n", msg, u);
diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
index 816488c0b..d388de72e 100644
--- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
+++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
@@ -353,8 +353,12 @@ AVXcode: 1
 17: vmovhps Mq,Vq (v1) | vmovhpd Mq,Vq (66),(v1)
 18: Grp16 (1A)
 19:
-1a: BNDCL Ev,Gv | BNDCU Ev,Gv | BNDMOV Gv,Ev | BNDLDX Gv,Ev,Gv
-1b: BNDCN Ev,Gv | BNDMOV Ev,Gv | BNDMK Gv,Ev | BNDSTX Ev,GV,Gv
+# Intel SDM opcode map does not list MPX instructions. For now using Gv for
+# bnd registers and Ev for everything else is OK because the instruction
+# decoder does not use the information except as an indication that there is
+# a ModR/M byte.
+1a: BNDCL Gv,Ev (F3) | BNDCU Gv,Ev (F2) | BNDMOV Gv,Ev (66) | BNDLDX Gv,Ev
+1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv
 1c:
 1d:
 1e:
@@ -732,6 +736,12 @@ bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
 be: vfnmsub231ps/d Vx,Hx,Wx (66),(v)
 bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
 # 0x0f 0x38 0xc0-0xff
+c8: sha1nexte Vdq,Wdq
+c9: sha1msg1 Vdq,Wdq
+ca: sha1msg2 Vdq,Wdq
+cb: sha256rnds2 Vdq,Wdq
+cc: sha256msg1 Vdq,Wdq
+cd: sha256msg2 Vdq,Wdq
 db: VAESIMC Vdq,Wdq (66),(v1)
 dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
 dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
@@ -790,6 +800,7 @@ AVXcode: 3
 61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
 62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
 63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
+cc: sha1rnds4 Vdq,Wdq,Ib
 df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
 f0: RORX Gy,Ey,Ib (F2),(v)
 EndTable
@@ -874,7 +885,7 @@ GrpTable: Grp7
 2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B)
 3: LIDT Ms
 4: SMSW Mw/Rv
-5:
+5: rdpkru (110),(11B) | wrpkru (111),(11B)
 6: LMSW Ew
 7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B)
 EndTable
@@ -888,6 +899,9 @@ EndTable
 
 GrpTable: Grp9
 1: CMPXCHG8B/16B Mq/Mdq
+3: xrstors
+4: xsavec
+5: xsaves
 6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B)
 7: VMPTRST Mq | VMPTRST Mq (F3) | RDSEED Rv (11B)
 EndTable
@@ -932,8 +946,8 @@ GrpTable: Grp15
 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B)
 4: XSAVE
 5: XRSTOR | lfence (11B)
-6: XSAVEOPT | mfence (11B)
-7: clflush | sfence (11B)
+6: XSAVEOPT | clwb (66) | mfence (11B)
+7: clflush | clflushopt (66) | sfence (11B) | pcommit (66),(11B)
 EndTable
 
 GrpTable: Grp16
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 535d86f8e..97f963a3d 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -22,6 +22,7 @@
 #include "../perf.h"
 #include "session.h"
 #include "machine.h"
+#include "sort.h"
 #include "tool.h"
 #include "event.h"
 #include "evlist.h"
@@ -63,6 +64,7 @@ struct intel_pt {
 	bool data_queued;
 	bool est_tsc;
 	bool sync_switch;
+	bool mispred_all;
 	int have_sched_switch;
 	u32 pmu_type;
 	u64 kernel_start;
@@ -115,6 +117,9 @@ struct intel_pt_queue {
 	void *decoder;
 	const struct intel_pt_state *state;
 	struct ip_callchain *chain;
+	struct branch_stack *last_branch;
+	struct branch_stack *last_branch_rb;
+	size_t last_branch_pos;
 	union perf_event *event_buf;
 	bool on_heap;
 	bool stop;
@@ -675,6 +680,19 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 			goto out_free;
 	}
 
+	if (pt->synth_opts.last_branch) {
+		size_t sz = sizeof(struct branch_stack);
+
+		sz += pt->synth_opts.last_branch_sz *
+		      sizeof(struct branch_entry);
+		ptq->last_branch = zalloc(sz);
+		if (!ptq->last_branch)
+			goto out_free;
+		ptq->last_branch_rb = zalloc(sz);
+		if (!ptq->last_branch_rb)
+			goto out_free;
+	}
+
 	ptq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
 	if (!ptq->event_buf)
 		goto out_free;
@@ -720,7 +738,7 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 
 		if (!params.period) {
 			params.period_type = INTEL_PT_PERIOD_INSTRUCTIONS;
-			params.period = 1000;
+			params.period = 1;
 		}
 	}
 
@@ -732,6 +750,8 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 
 out_free:
 	zfree(&ptq->event_buf);
+	zfree(&ptq->last_branch);
+	zfree(&ptq->last_branch_rb);
 	zfree(&ptq->chain);
 	free(ptq);
 	return NULL;
@@ -746,6 +766,8 @@ static void intel_pt_free_queue(void *priv)
 	thread__zput(ptq->thread);
 	intel_pt_decoder_free(ptq->decoder);
 	zfree(&ptq->event_buf);
+	zfree(&ptq->last_branch);
+	zfree(&ptq->last_branch_rb);
 	zfree(&ptq->chain);
 	free(ptq);
 }
@@ -876,6 +898,58 @@ static int intel_pt_setup_queues(struct intel_pt *pt)
 	return 0;
 }
 
+static inline void intel_pt_copy_last_branch_rb(struct intel_pt_queue *ptq)
+{
+	struct branch_stack *bs_src = ptq->last_branch_rb;
+	struct branch_stack *bs_dst = ptq->last_branch;
+	size_t nr = 0;
+
+	bs_dst->nr = bs_src->nr;
+
+	if (!bs_src->nr)
+		return;
+
+	nr = ptq->pt->synth_opts.last_branch_sz - ptq->last_branch_pos;
+	memcpy(&bs_dst->entries[0],
+	       &bs_src->entries[ptq->last_branch_pos],
+	       sizeof(struct branch_entry) * nr);
+
+	if (bs_src->nr >= ptq->pt->synth_opts.last_branch_sz) {
+		memcpy(&bs_dst->entries[nr],
+		       &bs_src->entries[0],
+		       sizeof(struct branch_entry) * ptq->last_branch_pos);
+	}
+}
+
+static inline void intel_pt_reset_last_branch_rb(struct intel_pt_queue *ptq)
+{
+	ptq->last_branch_pos = 0;
+	ptq->last_branch_rb->nr = 0;
+}
+
+static void intel_pt_update_last_branch_rb(struct intel_pt_queue *ptq)
+{
+	const struct intel_pt_state *state = ptq->state;
+	struct branch_stack *bs = ptq->last_branch_rb;
+	struct branch_entry *be;
+
+	if (!ptq->last_branch_pos)
+		ptq->last_branch_pos = ptq->pt->synth_opts.last_branch_sz;
+
+	ptq->last_branch_pos -= 1;
+
+	be              = &bs->entries[ptq->last_branch_pos];
+	be->from        = state->from_ip;
+	be->to          = state->to_ip;
+	be->flags.abort = !!(state->flags & INTEL_PT_ABORT_TX);
+	be->flags.in_tx = !!(state->flags & INTEL_PT_IN_TX);
+	/* No support for mispredict */
+	be->flags.mispred = ptq->pt->mispred_all;
+
+	if (bs->nr < ptq->pt->synth_opts.last_branch_sz)
+		bs->nr += 1;
+}
+
 static int intel_pt_inject_event(union perf_event *event,
 				 struct perf_sample *sample, u64 type,
 				 bool swapped)
@@ -890,6 +964,13 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 	struct intel_pt *pt = ptq->pt;
 	union perf_event *event = ptq->event_buf;
 	struct perf_sample sample = { .ip = 0, };
+	struct dummy_branch_stack {
+		u64			nr;
+		struct branch_entry	entries;
+	} dummy_bs;
+
+	if (pt->branches_filter && !(pt->branches_filter & ptq->flags))
+		return 0;
 
 	event->sample.header.type = PERF_RECORD_SAMPLE;
 	event->sample.header.misc = PERF_RECORD_MISC_USER;
@@ -909,8 +990,20 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 	sample.flags = ptq->flags;
 	sample.insn_len = ptq->insn_len;
 
-	if (pt->branches_filter && !(pt->branches_filter & ptq->flags))
-		return 0;
+	/*
+	 * perf report cannot handle events without a branch stack when using
+	 * SORT_MODE__BRANCH so make a dummy one.
+	 */
+	if (pt->synth_opts.last_branch && sort__mode == SORT_MODE__BRANCH) {
+		dummy_bs = (struct dummy_branch_stack){
+			.nr = 1,
+			.entries = {
+				.from = sample.ip,
+				.to = sample.addr,
+			},
+		};
+		sample.branch_stack = (struct branch_stack *)&dummy_bs;
+	}
 
 	if (pt->synth_opts.inject) {
 		ret = intel_pt_inject_event(event, &sample,
@@ -961,6 +1054,11 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
 		sample.callchain = ptq->chain;
 	}
 
+	if (pt->synth_opts.last_branch) {
+		intel_pt_copy_last_branch_rb(ptq);
+		sample.branch_stack = ptq->last_branch;
+	}
+
 	if (pt->synth_opts.inject) {
 		ret = intel_pt_inject_event(event, &sample,
 					    pt->instructions_sample_type,
@@ -974,6 +1072,9 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
 		pr_err("Intel Processor Trace: failed to deliver instruction event, error %d\n",
 		       ret);
 
+	if (pt->synth_opts.last_branch)
+		intel_pt_reset_last_branch_rb(ptq);
+
 	return ret;
 }
 
@@ -1008,6 +1109,11 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
 		sample.callchain = ptq->chain;
 	}
 
+	if (pt->synth_opts.last_branch) {
+		intel_pt_copy_last_branch_rb(ptq);
+		sample.branch_stack = ptq->last_branch;
+	}
+
 	if (pt->synth_opts.inject) {
 		ret = intel_pt_inject_event(event, &sample,
 					    pt->transactions_sample_type,
@@ -1021,6 +1127,9 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
 		pr_err("Intel Processor Trace: failed to deliver transaction event, error %d\n",
 		       ret);
 
+	if (pt->synth_opts.callchain)
+		intel_pt_reset_last_branch_rb(ptq);
+
 	return ret;
 }
 
@@ -1116,6 +1225,9 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 			return err;
 	}
 
+	if (pt->synth_opts.last_branch)
+		intel_pt_update_last_branch_rb(ptq);
+
 	if (!pt->sync_switch)
 		return 0;
 
@@ -1145,16 +1257,18 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 	return 0;
 }
 
-static u64 intel_pt_switch_ip(struct machine *machine, u64 *ptss_ip)
+static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip)
 {
+	struct machine *machine = pt->machine;
 	struct map *map;
 	struct symbol *sym, *start;
 	u64 ip, switch_ip = 0;
+	const char *ptss;
 
 	if (ptss_ip)
 		*ptss_ip = 0;
 
-	map = machine__kernel_map(machine, MAP__FUNCTION);
+	map = machine__kernel_map(machine);
 	if (!map)
 		return 0;
 
@@ -1177,8 +1291,13 @@ static u64 intel_pt_switch_ip(struct machine *machine, u64 *ptss_ip)
 	if (!switch_ip || !ptss_ip)
 		return 0;
 
+	if (pt->have_sched_switch == 1)
+		ptss = "perf_trace_sched_switch";
+	else
+		ptss = "__perf_event_task_sched_out";
+
 	for (sym = start; sym; sym = dso__next_symbol(sym)) {
-		if (!strcmp(sym->name, "perf_trace_sched_switch")) {
+		if (!strcmp(sym->name, ptss)) {
 			ip = map->unmap_ip(map, sym->start);
 			if (ip >= map->start && ip < map->end) {
 				*ptss_ip = ip;
@@ -1198,11 +1317,11 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 
 	if (!pt->kernel_start) {
 		pt->kernel_start = machine__kernel_start(pt->machine);
-		if (pt->per_cpu_mmaps && pt->have_sched_switch &&
+		if (pt->per_cpu_mmaps &&
+		    (pt->have_sched_switch == 1 || pt->have_sched_switch == 3) &&
 		    !pt->timeless_decoding && intel_pt_tracing_kernel(pt) &&
 		    !pt->sampling_mode) {
-			pt->switch_ip = intel_pt_switch_ip(pt->machine,
-							   &pt->ptss_ip);
+			pt->switch_ip = intel_pt_switch_ip(pt, &pt->ptss_ip);
 			if (pt->switch_ip) {
 				intel_pt_log("switch_ip: %"PRIx64" ptss_ip: %"PRIx64"\n",
 					     pt->switch_ip, pt->ptss_ip);
@@ -1387,31 +1506,18 @@ static struct intel_pt_queue *intel_pt_cpu_to_ptq(struct intel_pt *pt, int cpu)
 	return NULL;
 }
 
-static int intel_pt_process_switch(struct intel_pt *pt,
-				   struct perf_sample *sample)
+static int intel_pt_sync_switch(struct intel_pt *pt, int cpu, pid_t tid,
+				u64 timestamp)
 {
 	struct intel_pt_queue *ptq;
-	struct perf_evsel *evsel;
-	pid_t tid;
-	int cpu, err;
-
-	evsel = perf_evlist__id2evsel(pt->session->evlist, sample->id);
-	if (evsel != pt->switch_evsel)
-		return 0;
-
-	tid = perf_evsel__intval(evsel, sample, "next_pid");
-	cpu = sample->cpu;
-
-	intel_pt_log("sched_switch: cpu %d tid %d time %"PRIu64" tsc %#"PRIx64"\n",
-		     cpu, tid, sample->time, perf_time_to_tsc(sample->time,
-		     &pt->tc));
+	int err;
 
 	if (!pt->sync_switch)
-		goto out;
+		return 1;
 
 	ptq = intel_pt_cpu_to_ptq(pt, cpu);
 	if (!ptq)
-		goto out;
+		return 1;
 
 	switch (ptq->switch_state) {
 	case INTEL_PT_SS_NOT_TRACING:
@@ -1424,7 +1530,7 @@ static int intel_pt_process_switch(struct intel_pt *pt,
 		return 0;
 	case INTEL_PT_SS_EXPECTING_SWITCH_EVENT:
 		if (!ptq->on_heap) {
-			ptq->timestamp = perf_time_to_tsc(sample->time,
+			ptq->timestamp = perf_time_to_tsc(timestamp,
 							  &pt->tc);
 			err = auxtrace_heap__add(&pt->heap, ptq->queue_nr,
 						 ptq->timestamp);
@@ -1441,10 +1547,76 @@ static int intel_pt_process_switch(struct intel_pt *pt,
 	default:
 		break;
 	}
-out:
+
+	return 1;
+}
+
+static int intel_pt_process_switch(struct intel_pt *pt,
+				   struct perf_sample *sample)
+{
+	struct perf_evsel *evsel;
+	pid_t tid;
+	int cpu, ret;
+
+	evsel = perf_evlist__id2evsel(pt->session->evlist, sample->id);
+	if (evsel != pt->switch_evsel)
+		return 0;
+
+	tid = perf_evsel__intval(evsel, sample, "next_pid");
+	cpu = sample->cpu;
+
+	intel_pt_log("sched_switch: cpu %d tid %d time %"PRIu64" tsc %#"PRIx64"\n",
+		     cpu, tid, sample->time, perf_time_to_tsc(sample->time,
+		     &pt->tc));
+
+	ret = intel_pt_sync_switch(pt, cpu, tid, sample->time);
+	if (ret <= 0)
+		return ret;
+
 	return machine__set_current_tid(pt->machine, cpu, -1, tid);
 }
 
+static int intel_pt_context_switch(struct intel_pt *pt, union perf_event *event,
+				   struct perf_sample *sample)
+{
+	bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
+	pid_t pid, tid;
+	int cpu, ret;
+
+	cpu = sample->cpu;
+
+	if (pt->have_sched_switch == 3) {
+		if (!out)
+			return 0;
+		if (event->header.type != PERF_RECORD_SWITCH_CPU_WIDE) {
+			pr_err("Expecting CPU-wide context switch event\n");
+			return -EINVAL;
+		}
+		pid = event->context_switch.next_prev_pid;
+		tid = event->context_switch.next_prev_tid;
+	} else {
+		if (out)
+			return 0;
+		pid = sample->pid;
+		tid = sample->tid;
+	}
+
+	if (tid == -1) {
+		pr_err("context_switch event has no tid\n");
+		return -EINVAL;
+	}
+
+	intel_pt_log("context_switch: cpu %d pid %d tid %d time %"PRIu64" tsc %#"PRIx64"\n",
+		     cpu, pid, tid, sample->time, perf_time_to_tsc(sample->time,
+		     &pt->tc));
+
+	ret = intel_pt_sync_switch(pt, cpu, tid, sample->time);
+	if (ret <= 0)
+		return ret;
+
+	return machine__set_current_tid(pt->machine, cpu, pid, tid);
+}
+
 static int intel_pt_process_itrace_start(struct intel_pt *pt,
 					 union perf_event *event,
 					 struct perf_sample *sample)
@@ -1515,6 +1687,9 @@ static int intel_pt_process_event(struct perf_session *session,
 		err = intel_pt_process_switch(pt, sample);
 	else if (event->header.type == PERF_RECORD_ITRACE_START)
 		err = intel_pt_process_itrace_start(pt, event, sample);
+	else if (event->header.type == PERF_RECORD_SWITCH ||
+		 event->header.type == PERF_RECORD_SWITCH_CPU_WIDE)
+		err = intel_pt_context_switch(pt, event, sample);
 
 	intel_pt_log("event %s (%u): cpu %d time %"PRIu64" tsc %#"PRIx64"\n",
 		     perf_event__name(event->header.type), event->header.type,
@@ -1700,6 +1875,8 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 		pt->instructions_sample_period = attr.sample_period;
 		if (pt->synth_opts.callchain)
 			attr.sample_type |= PERF_SAMPLE_CALLCHAIN;
+		if (pt->synth_opts.last_branch)
+			attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
 		pr_debug("Synthesizing 'instructions' event with id %" PRIu64 " sample type %#" PRIx64 "\n",
 			 id, (u64)attr.sample_type);
 		err = intel_pt_synth_event(session, &attr, id);
@@ -1719,6 +1896,8 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 		attr.sample_period = 1;
 		if (pt->synth_opts.callchain)
 			attr.sample_type |= PERF_SAMPLE_CALLCHAIN;
+		if (pt->synth_opts.last_branch)
+			attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
 		pr_debug("Synthesizing 'transactions' event with id %" PRIu64 " sample type %#" PRIx64 "\n",
 			 id, (u64)attr.sample_type);
 		err = intel_pt_synth_event(session, &attr, id);
@@ -1745,6 +1924,7 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 		attr.sample_period = 1;
 		attr.sample_type |= PERF_SAMPLE_ADDR;
 		attr.sample_type &= ~(u64)PERF_SAMPLE_CALLCHAIN;
+		attr.sample_type &= ~(u64)PERF_SAMPLE_BRANCH_STACK;
 		pr_debug("Synthesizing 'branches' event with id %" PRIu64 " sample type %#" PRIx64 "\n",
 			 id, (u64)attr.sample_type);
 		err = intel_pt_synth_event(session, &attr, id);
@@ -1777,6 +1957,28 @@ static struct perf_evsel *intel_pt_find_sched_switch(struct perf_evlist *evlist)
 	return NULL;
 }
 
+static bool intel_pt_find_switch(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		if (evsel->attr.context_switch)
+			return true;
+	}
+
+	return false;
+}
+
+static int intel_pt_perf_config(const char *var, const char *value, void *data)
+{
+	struct intel_pt *pt = data;
+
+	if (!strcmp(var, "intel-pt.mispred-all"))
+		pt->mispred_all = perf_config_bool(var, value);
+
+	return 0;
+}
+
 static const char * const intel_pt_info_fmts[] = {
 	[INTEL_PT_PMU_TYPE]		= "  PMU Type            %"PRId64"\n",
 	[INTEL_PT_TIME_SHIFT]		= "  Time Shift          %"PRIu64"\n",
@@ -1821,6 +2023,8 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 	if (!pt)
 		return -ENOMEM;
 
+	perf_config(intel_pt_perf_config, pt);
+
 	err = auxtrace_queues__init(&pt->queues);
 	if (err)
 		goto err_free;
@@ -1888,6 +2092,10 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 			pr_err("%s: missing sched_switch event\n", __func__);
 			goto err_delete_thread;
 		}
+	} else if (pt->have_sched_switch == 2 &&
+		   !intel_pt_find_switch(session->evlist)) {
+		pr_err("%s: missing context_switch attribute flag\n", __func__);
+		goto err_delete_thread;
 	}
 
 	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 4f6a4780b..00724d496 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -4,17 +4,18 @@
  */
 
 #include <stdio.h>
-#include <sys/utsname.h>
 #include "util.h"
 #include "debug.h"
 #include "llvm-utils.h"
 #include "cache.h"
 
 #define CLANG_BPF_CMD_DEFAULT_TEMPLATE				\
-		"$CLANG_EXEC -D__KERNEL__ $CLANG_OPTIONS "	\
-		"$KERNEL_INC_OPTIONS -Wno-unused-value "	\
-		"-Wno-pointer-sign -working-directory "		\
-		"$WORKING_DIR -c \"$CLANG_SOURCE\" -target bpf -O2 -o -"
+		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
+		"-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE "	\
+		"$CLANG_OPTIONS $KERNEL_INC_OPTIONS "		\
+		"-Wno-unused-value -Wno-pointer-sign "		\
+		"-working-directory $WORKING_DIR "		\
+		"-c \"$CLANG_SOURCE\" -target bpf -O2 -o -"
 
 struct llvm_param llvm_param = {
 	.clang_path = "clang",
@@ -214,18 +215,19 @@ static int detect_kbuild_dir(char **kbuild_dir)
 	const char *suffix_dir = "";
 
 	char *autoconf_path;
-	struct utsname utsname;
 
 	int err;
 
 	if (!test_dir) {
-		err = uname(&utsname);
-		if (err) {
-			pr_warning("uname failed: %s\n", strerror(errno));
+		/* _UTSNAME_LENGTH is 65 */
+		char release[128];
+
+		err = fetch_kernel_version(NULL, release,
+					   sizeof(release));
+		if (err)
 			return -EINVAL;
-		}
 
-		test_dir = utsname.release;
+		test_dir = release;
 		prefix_dir = "/lib/modules/";
 		suffix_dir = "/build";
 	}
@@ -326,13 +328,15 @@ get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts)
 int llvm__compile_bpf(const char *path, void **p_obj_buf,
 		      size_t *p_obj_buf_sz)
 {
-	int err;
-	char clang_path[PATH_MAX];
+	size_t obj_buf_sz;
+	void *obj_buf = NULL;
+	int err, nr_cpus_avail;
+	unsigned int kernel_version;
+	char linux_version_code_str[64];
 	const char *clang_opt = llvm_param.clang_opt;
-	const char *template = llvm_param.clang_bpf_cmd_template;
+	char clang_path[PATH_MAX], nr_cpus_avail_str[64];
 	char *kbuild_dir = NULL, *kbuild_include_opts = NULL;
-	void *obj_buf = NULL;
-	size_t obj_buf_sz;
+	const char *template = llvm_param.clang_bpf_cmd_template;
 
 	if (!template)
 		template = CLANG_BPF_CMD_DEFAULT_TEMPLATE;
@@ -354,6 +358,24 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	 */
 	get_kbuild_opts(&kbuild_dir, &kbuild_include_opts);
 
+	nr_cpus_avail = sysconf(_SC_NPROCESSORS_CONF);
+	if (nr_cpus_avail <= 0) {
+		pr_err(
+"WARNING:\tunable to get available CPUs in this system: %s\n"
+"        \tUse 128 instead.\n", strerror(errno));
+		nr_cpus_avail = 128;
+	}
+	snprintf(nr_cpus_avail_str, sizeof(nr_cpus_avail_str), "%d",
+		 nr_cpus_avail);
+
+	if (fetch_kernel_version(&kernel_version, NULL, 0))
+		kernel_version = 0;
+
+	snprintf(linux_version_code_str, sizeof(linux_version_code_str),
+		 "0x%x", kernel_version);
+
+	force_set_env("NR_CPUS", nr_cpus_avail_str);
+	force_set_env("LINUX_VERSION_CODE", linux_version_code_str);
 	force_set_env("CLANG_EXEC", clang_path);
 	force_set_env("CLANG_OPTIONS", clang_opt);
 	force_set_env("KERNEL_INC_OPTIONS", kbuild_include_opts);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 6309f7ceb..8b303ff20 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -35,6 +35,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	machine->last_match = NULL;
 
 	machine->vdso_info = NULL;
+	machine->env = NULL;
 
 	machine->pid = pid;
 
@@ -90,6 +91,7 @@ static void dsos__purge(struct dsos *dsos)
 
 	list_for_each_entry_safe(pos, n, &dsos->head, node) {
 		RB_CLEAR_NODE(&pos->rb_node);
+		pos->root = NULL;
 		list_del_init(&pos->node);
 		dso__put(pos);
 	}
@@ -624,7 +626,7 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
 {
 	int i;
 	size_t printed = 0;
-	struct dso *kdso = machine->vmlinux_maps[MAP__FUNCTION]->dso;
+	struct dso *kdso = machine__kernel_map(machine)->dso;
 
 	if (kdso->has_build_id) {
 		char filename[PATH_MAX];
@@ -740,6 +742,7 @@ int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 
 	for (type = 0; type < MAP__NR_TYPES; ++type) {
 		struct kmap *kmap;
+		struct map *map;
 
 		machine->vmlinux_maps[type] = map__new2(start, kernel, type);
 		if (machine->vmlinux_maps[type] == NULL)
@@ -748,13 +751,13 @@ int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 		machine->vmlinux_maps[type]->map_ip =
 			machine->vmlinux_maps[type]->unmap_ip =
 				identity__map_ip;
-		kmap = map__kmap(machine->vmlinux_maps[type]);
+		map = __machine__kernel_map(machine, type);
+		kmap = map__kmap(map);
 		if (!kmap)
 			return -1;
 
 		kmap->kmaps = &machine->kmaps;
-		map_groups__insert(&machine->kmaps,
-				   machine->vmlinux_maps[type]);
+		map_groups__insert(&machine->kmaps, map);
 	}
 
 	return 0;
@@ -766,13 +769,13 @@ void machine__destroy_kernel_maps(struct machine *machine)
 
 	for (type = 0; type < MAP__NR_TYPES; ++type) {
 		struct kmap *kmap;
+		struct map *map = __machine__kernel_map(machine, type);
 
-		if (machine->vmlinux_maps[type] == NULL)
+		if (map == NULL)
 			continue;
 
-		kmap = map__kmap(machine->vmlinux_maps[type]);
-		map_groups__remove(&machine->kmaps,
-				   machine->vmlinux_maps[type]);
+		kmap = map__kmap(map);
+		map_groups__remove(&machine->kmaps, map);
 		if (kmap && kmap->ref_reloc_sym) {
 			/*
 			 * ref_reloc_sym is shared among all maps, so free just
@@ -866,7 +869,7 @@ int machines__create_kernel_maps(struct machines *machines, pid_t pid)
 int machine__load_kallsyms(struct machine *machine, const char *filename,
 			   enum map_type type, symbol_filter_t filter)
 {
-	struct map *map = machine->vmlinux_maps[type];
+	struct map *map = machine__kernel_map(machine);
 	int ret = dso__load_kallsyms(map->dso, filename, map, filter);
 
 	if (ret > 0) {
@@ -885,7 +888,7 @@ int machine__load_kallsyms(struct machine *machine, const char *filename,
 int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
 			       symbol_filter_t filter)
 {
-	struct map *map = machine->vmlinux_maps[type];
+	struct map *map = machine__kernel_map(machine);
 	int ret = dso__load_vmlinux_path(map->dso, map, filter);
 
 	if (ret > 0)
@@ -1243,8 +1246,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 			/*
 			 * preload dso of guest kernel and modules
 			 */
-			dso__load(kernel, machine->vmlinux_maps[MAP__FUNCTION],
-				  NULL);
+			dso__load(kernel, machine__kernel_map(machine), NULL);
 		}
 	}
 	return 0;
@@ -1830,7 +1832,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	}
 
 check_calls:
-	if (chain->nr > PERF_MAX_STACK_DEPTH) {
+	if (chain->nr > PERF_MAX_STACK_DEPTH && (int)chain->nr > max_stack) {
 		pr_warning("corrupted callchain. skipping...\n");
 		return 0;
 	}
@@ -1996,7 +1998,7 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 
 int machine__get_kernel_start(struct machine *machine)
 {
-	struct map *map = machine__kernel_map(machine, MAP__FUNCTION);
+	struct map *map = machine__kernel_map(machine);
 	int err = 0;
 
 	/*
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index ea5cb4a62..2c2b443df 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -34,6 +34,7 @@ struct machine {
 	struct list_head  dead_threads;
 	struct thread	  *last_match;
 	struct vdso_info  *vdso_info;
+	struct perf_env   *env;
 	struct dsos	  dsos;
 	struct map_groups kmaps;
 	struct map	  *vmlinux_maps[MAP__NR_TYPES];
@@ -47,11 +48,17 @@ struct machine {
 };
 
 static inline
-struct map *machine__kernel_map(struct machine *machine, enum map_type type)
+struct map *__machine__kernel_map(struct machine *machine, enum map_type type)
 {
 	return machine->vmlinux_maps[type];
 }
 
+static inline
+struct map *machine__kernel_map(struct machine *machine)
+{
+	return __machine__kernel_map(machine, MAP__FUNCTION);
+}
+
 int machine__get_kernel_start(struct machine *machine);
 
 static inline u64 machine__kernel_start(struct machine *machine)
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index b1c475d9b..afc6b56cf 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -235,7 +235,7 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
  */
 bool __map__is_kernel(const struct map *map)
 {
-	return map->groups->machine->vmlinux_maps[map->type] == map;
+	return __machine__kernel_map(map->groups->machine, map->type) == map;
 }
 
 static void map__exit(struct map *map)
@@ -553,13 +553,9 @@ struct symbol *map_groups__find_symbol(struct map_groups *mg,
 	return NULL;
 }
 
-struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
-					       enum map_type type,
-					       const char *name,
-					       struct map **mapp,
-					       symbol_filter_t filter)
+struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
+					 struct map **mapp, symbol_filter_t filter)
 {
-	struct maps *maps = &mg->maps[type];
 	struct symbol *sym;
 	struct rb_node *nd;
 
@@ -583,6 +579,17 @@ out:
 	return sym;
 }
 
+struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
+					       enum map_type type,
+					       const char *name,
+					       struct map **mapp,
+					       symbol_filter_t filter)
+{
+	struct symbol *sym = maps__find_symbol_by_name(&mg->maps[type], name, mapp, filter);
+
+	return sym;
+}
+
 int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
 {
 	if (ams->addr < ams->map->start || ams->addr >= ams->map->end) {
@@ -637,6 +644,12 @@ size_t map_groups__fprintf(struct map_groups *mg, FILE *fp)
 	return printed;
 }
 
+static void __map_groups__insert(struct map_groups *mg, struct map *map)
+{
+	__maps__insert(&mg->maps[map->type], map);
+	map->groups = mg;
+}
+
 static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
 {
 	struct rb_root *root;
@@ -675,7 +688,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
 			}
 
 			before->end = map->start;
-			__maps__insert(maps, before);
+			__map_groups__insert(pos->groups, before);
 			if (verbose >= 2)
 				map__fprintf(before, fp);
 		}
@@ -689,7 +702,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
 			}
 
 			after->start = map->end;
-			__maps__insert(maps, after);
+			__map_groups__insert(pos->groups, after);
 			if (verbose >= 2)
 				map__fprintf(after, fp);
 		}
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 57829e89b..7309d64ce 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -190,6 +190,8 @@ void maps__remove(struct maps *maps, struct map *map);
 struct map *maps__find(struct maps *maps, u64 addr);
 struct map *maps__first(struct maps *maps);
 struct map *map__next(struct map *map);
+struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
+                                         struct map **mapp, symbol_filter_t filter);
 void map_groups__init(struct map_groups *mg, struct machine *machine);
 void map_groups__exit(struct map_groups *mg);
 int map_groups__clone(struct map_groups *mg,
diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c
index a3b1e13a0..355eecf6b 100644
--- a/tools/perf/util/parse-branch-options.c
+++ b/tools/perf/util/parse-branch-options.c
@@ -27,6 +27,7 @@ static const struct branch_mode branch_modes[] = {
 	BRANCH_OPT("no_tx", PERF_SAMPLE_BRANCH_NO_TX),
 	BRANCH_OPT("cond", PERF_SAMPLE_BRANCH_COND),
 	BRANCH_OPT("ind_jmp", PERF_SAMPLE_BRANCH_IND_JUMP),
+	BRANCH_OPT("call", PERF_SAMPLE_BRANCH_CALL),
 	BRANCH_END
 };
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 21ed6ee63..6fc8cd753 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1,4 +1,5 @@
 #include <linux/hw_breakpoint.h>
+#include <linux/err.h>
 #include "util.h"
 #include "../perf.h"
 #include "evlist.h"
@@ -10,8 +11,9 @@
 #include "symbol.h"
 #include "cache.h"
 #include "header.h"
+#include "bpf-loader.h"
 #include "debug.h"
-#include <api/fs/debugfs.h>
+#include <api/fs/tracing_path.h>
 #include "parse-events-bison.h"
 #define YY_EXTRA_TYPE int
 #include "parse-events-flex.h"
@@ -26,6 +28,8 @@
 extern int parse_events_debug;
 #endif
 int parse_events_parse(void *data, void *scanner);
+static int get_config_terms(struct list_head *head_config,
+			    struct list_head *head_terms __maybe_unused);
 
 static struct perf_pmu_event_symbol *perf_pmu_events_list;
 /*
@@ -120,6 +124,10 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
 		.symbol = "dummy",
 		.alias  = "",
 	},
+	[PERF_COUNT_SW_BPF_OUTPUT] = {
+		.symbol = "bpf-output",
+		.alias  = "",
+	},
 };
 
 #define __PERF_EVENT_FIELD(config, name) \
@@ -386,32 +394,72 @@ int parse_events_add_cache(struct list_head *list, int *idx,
 	return add_event(list, idx, &attr, name, NULL);
 }
 
+static void tracepoint_error(struct parse_events_error *e, int err,
+			     char *sys, char *name)
+{
+	char help[BUFSIZ];
+
+	/*
+	 * We get error directly from syscall errno ( > 0),
+	 * or from encoded pointer's error ( < 0).
+	 */
+	err = abs(err);
+
+	switch (err) {
+	case EACCES:
+		e->str = strdup("can't access trace events");
+		break;
+	case ENOENT:
+		e->str = strdup("unknown tracepoint");
+		break;
+	default:
+		e->str = strdup("failed to add tracepoint");
+		break;
+	}
+
+	tracing_path__strerror_open_tp(err, help, sizeof(help), sys, name);
+	e->help = strdup(help);
+}
+
 static int add_tracepoint(struct list_head *list, int *idx,
-			  char *sys_name, char *evt_name)
+			  char *sys_name, char *evt_name,
+			  struct parse_events_error *err,
+			  struct list_head *head_config)
 {
 	struct perf_evsel *evsel;
 
 	evsel = perf_evsel__newtp_idx(sys_name, evt_name, (*idx)++);
-	if (!evsel)
-		return -ENOMEM;
+	if (IS_ERR(evsel)) {
+		tracepoint_error(err, PTR_ERR(evsel), sys_name, evt_name);
+		return PTR_ERR(evsel);
+	}
 
-	list_add_tail(&evsel->node, list);
+	if (head_config) {
+		LIST_HEAD(config_terms);
 
+		if (get_config_terms(head_config, &config_terms))
+			return -ENOMEM;
+		list_splice(&config_terms, &evsel->config_terms);
+	}
+
+	list_add_tail(&evsel->node, list);
 	return 0;
 }
 
 static int add_tracepoint_multi_event(struct list_head *list, int *idx,
-				      char *sys_name, char *evt_name)
+				      char *sys_name, char *evt_name,
+				      struct parse_events_error *err,
+				      struct list_head *head_config)
 {
 	char evt_path[MAXPATHLEN];
 	struct dirent *evt_ent;
 	DIR *evt_dir;
-	int ret = 0;
+	int ret = 0, found = 0;
 
 	snprintf(evt_path, MAXPATHLEN, "%s/%s", tracing_events_path, sys_name);
 	evt_dir = opendir(evt_path);
 	if (!evt_dir) {
-		perror("Can't open event dir");
+		tracepoint_error(err, errno, sys_name, evt_name);
 		return -1;
 	}
 
@@ -425,7 +473,15 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 		if (!strglobmatch(evt_ent->d_name, evt_name))
 			continue;
 
-		ret = add_tracepoint(list, idx, sys_name, evt_ent->d_name);
+		found++;
+
+		ret = add_tracepoint(list, idx, sys_name, evt_ent->d_name,
+				     err, head_config);
+	}
+
+	if (!found) {
+		tracepoint_error(err, ENOENT, sys_name, evt_name);
+		ret = -1;
 	}
 
 	closedir(evt_dir);
@@ -433,15 +489,21 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 }
 
 static int add_tracepoint_event(struct list_head *list, int *idx,
-				char *sys_name, char *evt_name)
+				char *sys_name, char *evt_name,
+				struct parse_events_error *err,
+				struct list_head *head_config)
 {
 	return strpbrk(evt_name, "*?") ?
-	       add_tracepoint_multi_event(list, idx, sys_name, evt_name) :
-	       add_tracepoint(list, idx, sys_name, evt_name);
+	       add_tracepoint_multi_event(list, idx, sys_name, evt_name,
+					  err, head_config) :
+	       add_tracepoint(list, idx, sys_name, evt_name,
+			      err, head_config);
 }
 
 static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
-				    char *sys_name, char *evt_name)
+				    char *sys_name, char *evt_name,
+				    struct parse_events_error *err,
+				    struct list_head *head_config)
 {
 	struct dirent *events_ent;
 	DIR *events_dir;
@@ -449,7 +511,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 
 	events_dir = opendir(tracing_events_path);
 	if (!events_dir) {
-		perror("Can't open event dir");
+		tracepoint_error(err, errno, sys_name, evt_name);
 		return -1;
 	}
 
@@ -465,20 +527,136 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 			continue;
 
 		ret = add_tracepoint_event(list, idx, events_ent->d_name,
-					   evt_name);
+					   evt_name, err, head_config);
 	}
 
 	closedir(events_dir);
 	return ret;
 }
 
-int parse_events_add_tracepoint(struct list_head *list, int *idx,
-				char *sys, char *event)
+struct __add_bpf_event_param {
+	struct parse_events_evlist *data;
+	struct list_head *list;
+};
+
+static int add_bpf_event(struct probe_trace_event *tev, int fd,
+			 void *_param)
 {
-	if (strpbrk(sys, "*?"))
-		return add_tracepoint_multi_sys(list, idx, sys, event);
-	else
-		return add_tracepoint_event(list, idx, sys, event);
+	LIST_HEAD(new_evsels);
+	struct __add_bpf_event_param *param = _param;
+	struct parse_events_evlist *evlist = param->data;
+	struct list_head *list = param->list;
+	struct perf_evsel *pos;
+	int err;
+
+	pr_debug("add bpf event %s:%s and attach bpf program %d\n",
+		 tev->group, tev->event, fd);
+
+	err = parse_events_add_tracepoint(&new_evsels, &evlist->idx, tev->group,
+					  tev->event, evlist->error, NULL);
+	if (err) {
+		struct perf_evsel *evsel, *tmp;
+
+		pr_debug("Failed to add BPF event %s:%s\n",
+			 tev->group, tev->event);
+		list_for_each_entry_safe(evsel, tmp, &new_evsels, node) {
+			list_del(&evsel->node);
+			perf_evsel__delete(evsel);
+		}
+		return err;
+	}
+	pr_debug("adding %s:%s\n", tev->group, tev->event);
+
+	list_for_each_entry(pos, &new_evsels, node) {
+		pr_debug("adding %s:%s to %p\n",
+			 tev->group, tev->event, pos);
+		pos->bpf_fd = fd;
+	}
+	list_splice(&new_evsels, list);
+	return 0;
+}
+
+int parse_events_load_bpf_obj(struct parse_events_evlist *data,
+			      struct list_head *list,
+			      struct bpf_object *obj)
+{
+	int err;
+	char errbuf[BUFSIZ];
+	struct __add_bpf_event_param param = {data, list};
+	static bool registered_unprobe_atexit = false;
+
+	if (IS_ERR(obj) || !obj) {
+		snprintf(errbuf, sizeof(errbuf),
+			 "Internal error: load bpf obj with NULL");
+		err = -EINVAL;
+		goto errout;
+	}
+
+	/*
+	 * Register atexit handler before calling bpf__probe() so
+	 * bpf__probe() don't need to unprobe probe points its already
+	 * created when failure.
+	 */
+	if (!registered_unprobe_atexit) {
+		atexit(bpf__clear);
+		registered_unprobe_atexit = true;
+	}
+
+	err = bpf__probe(obj);
+	if (err) {
+		bpf__strerror_probe(obj, err, errbuf, sizeof(errbuf));
+		goto errout;
+	}
+
+	err = bpf__load(obj);
+	if (err) {
+		bpf__strerror_load(obj, err, errbuf, sizeof(errbuf));
+		goto errout;
+	}
+
+	err = bpf__foreach_tev(obj, add_bpf_event, &param);
+	if (err) {
+		snprintf(errbuf, sizeof(errbuf),
+			 "Attach events in BPF object failed");
+		goto errout;
+	}
+
+	return 0;
+errout:
+	data->error->help = strdup("(add -v to see detail)");
+	data->error->str = strdup(errbuf);
+	return err;
+}
+
+int parse_events_load_bpf(struct parse_events_evlist *data,
+			  struct list_head *list,
+			  char *bpf_file_name,
+			  bool source)
+{
+	struct bpf_object *obj;
+
+	obj = bpf__prepare_load(bpf_file_name, source);
+	if (IS_ERR(obj)) {
+		char errbuf[BUFSIZ];
+		int err;
+
+		err = PTR_ERR(obj);
+
+		if (err == -ENOTSUP)
+			snprintf(errbuf, sizeof(errbuf),
+				 "BPF support is not compiled");
+		else
+			bpf__strerror_prepare_load(bpf_file_name,
+						   source,
+						   -err, errbuf,
+						   sizeof(errbuf));
+
+		data->error->help = strdup("(add -v to see detail)");
+		data->error->str = strdup(errbuf);
+		return err;
+	}
+
+	return parse_events_load_bpf_obj(data, list, obj);
 }
 
 static int
@@ -565,9 +743,13 @@ static int check_type_val(struct parse_events_term *term,
 	return -EINVAL;
 }
 
-static int config_term(struct perf_event_attr *attr,
-		       struct parse_events_term *term,
-		       struct parse_events_error *err)
+typedef int config_term_func_t(struct perf_event_attr *attr,
+			       struct parse_events_term *term,
+			       struct parse_events_error *err);
+
+static int config_term_common(struct perf_event_attr *attr,
+			      struct parse_events_term *term,
+			      struct parse_events_error *err)
 {
 #define CHECK_TYPE_VAL(type)						   \
 do {									   \
@@ -576,12 +758,6 @@ do {									   \
 } while (0)
 
 	switch (term->type_term) {
-	case PARSE_EVENTS__TERM_TYPE_USER:
-		/*
-		 * Always succeed for sysfs terms, as we dont know
-		 * at this point what type they need to have.
-		 */
-		return 0;
 	case PARSE_EVENTS__TERM_TYPE_CONFIG:
 		CHECK_TYPE_VAL(NUM);
 		attr->config = term->val.num;
@@ -620,10 +796,19 @@ do {									   \
 	case PARSE_EVENTS__TERM_TYPE_STACKSIZE:
 		CHECK_TYPE_VAL(NUM);
 		break;
+	case PARSE_EVENTS__TERM_TYPE_INHERIT:
+		CHECK_TYPE_VAL(NUM);
+		break;
+	case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
+		CHECK_TYPE_VAL(NUM);
+		break;
 	case PARSE_EVENTS__TERM_TYPE_NAME:
 		CHECK_TYPE_VAL(STR);
 		break;
 	default:
+		err->str = strdup("unknown term");
+		err->idx = term->err_term;
+		err->help = parse_events_formats_error_string(NULL);
 		return -EINVAL;
 	}
 
@@ -631,9 +816,46 @@ do {									   \
 #undef CHECK_TYPE_VAL
 }
 
+static int config_term_pmu(struct perf_event_attr *attr,
+			   struct parse_events_term *term,
+			   struct parse_events_error *err)
+{
+	if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER)
+		/*
+		 * Always succeed for sysfs terms, as we dont know
+		 * at this point what type they need to have.
+		 */
+		return 0;
+	else
+		return config_term_common(attr, term, err);
+}
+
+static int config_term_tracepoint(struct perf_event_attr *attr,
+				  struct parse_events_term *term,
+				  struct parse_events_error *err)
+{
+	switch (term->type_term) {
+	case PARSE_EVENTS__TERM_TYPE_CALLGRAPH:
+	case PARSE_EVENTS__TERM_TYPE_STACKSIZE:
+	case PARSE_EVENTS__TERM_TYPE_INHERIT:
+	case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
+		return config_term_common(attr, term, err);
+	default:
+		if (err) {
+			err->idx = term->err_term;
+			err->str = strdup("unknown term");
+			err->help = strdup("valid terms: call-graph,stack-size\n");
+		}
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int config_attr(struct perf_event_attr *attr,
 		       struct list_head *head,
-		       struct parse_events_error *err)
+		       struct parse_events_error *err,
+		       config_term_func_t config_term)
 {
 	struct parse_events_term *term;
 
@@ -680,6 +902,12 @@ do {								\
 		case PARSE_EVENTS__TERM_TYPE_STACKSIZE:
 			ADD_CONFIG_TERM(STACK_USER, stack_user, term->val.num);
 			break;
+		case PARSE_EVENTS__TERM_TYPE_INHERIT:
+			ADD_CONFIG_TERM(INHERIT, inherit, term->val.num ? 1 : 0);
+			break;
+		case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
+			ADD_CONFIG_TERM(INHERIT, inherit, term->val.num ? 0 : 1);
+			break;
 		default:
 			break;
 		}
@@ -688,6 +916,27 @@ do {								\
 	return 0;
 }
 
+int parse_events_add_tracepoint(struct list_head *list, int *idx,
+				char *sys, char *event,
+				struct parse_events_error *err,
+				struct list_head *head_config)
+{
+	if (head_config) {
+		struct perf_event_attr attr;
+
+		if (config_attr(&attr, head_config, err,
+				config_term_tracepoint))
+			return -EINVAL;
+	}
+
+	if (strpbrk(sys, "*?"))
+		return add_tracepoint_multi_sys(list, idx, sys, event,
+						err, head_config);
+	else
+		return add_tracepoint_event(list, idx, sys, event,
+					    err, head_config);
+}
+
 int parse_events_add_numeric(struct parse_events_evlist *data,
 			     struct list_head *list,
 			     u32 type, u64 config,
@@ -701,7 +950,8 @@ int parse_events_add_numeric(struct parse_events_evlist *data,
 	attr.config = config;
 
 	if (head_config) {
-		if (config_attr(&attr, head_config, data->error))
+		if (config_attr(&attr, head_config, data->error,
+				config_term_common))
 			return -EINVAL;
 
 		if (get_config_terms(head_config, &config_terms))
@@ -761,7 +1011,7 @@ int parse_events_add_pmu(struct parse_events_evlist *data,
 	 * Configure hardcoded terms first, no need to check
 	 * return value when called with fail == 0 ;)
 	 */
-	if (config_attr(&attr, head_config, data->error))
+	if (config_attr(&attr, head_config, data->error, config_term_pmu))
 		return -EINVAL;
 
 	if (get_config_terms(head_config, &config_terms))
@@ -793,6 +1043,11 @@ void parse_events__set_leader(char *name, struct list_head *list)
 {
 	struct perf_evsel *leader;
 
+	if (list_empty(list)) {
+		WARN_ONCE(true, "WARNING: failed to set leader: empty list");
+		return;
+	}
+
 	__perf_evlist__set_leader(list);
 	leader = list_entry(list->next, struct perf_evsel, node);
 	leader->group_name = name ? strdup(name) : NULL;
@@ -819,6 +1074,7 @@ struct event_modifier {
 	int eG;
 	int eI;
 	int precise;
+	int precise_max;
 	int exclude_GH;
 	int sample_read;
 	int pinned;
@@ -834,6 +1090,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
 	int eG = evsel ? evsel->attr.exclude_guest : 0;
 	int eI = evsel ? evsel->attr.exclude_idle : 0;
 	int precise = evsel ? evsel->attr.precise_ip : 0;
+	int precise_max = 0;
 	int sample_read = 0;
 	int pinned = evsel ? evsel->attr.pinned : 0;
 
@@ -870,6 +1127,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
 			/* use of precise requires exclude_guest */
 			if (!exclude_GH)
 				eG = 1;
+		} else if (*str == 'P') {
+			precise_max = 1;
 		} else if (*str == 'S') {
 			sample_read = 1;
 		} else if (*str == 'D') {
@@ -900,6 +1159,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
 	mod->eG = eG;
 	mod->eI = eI;
 	mod->precise = precise;
+	mod->precise_max = precise_max;
 	mod->exclude_GH = exclude_GH;
 	mod->sample_read = sample_read;
 	mod->pinned = pinned;
@@ -916,7 +1176,7 @@ static int check_modifier(char *str)
 	char *p = str;
 
 	/* The sizeof includes 0 byte as well. */
-	if (strlen(str) > (sizeof("ukhGHpppSDI") - 1))
+	if (strlen(str) > (sizeof("ukhGHpppPSDI") - 1))
 		return -1;
 
 	while (*p) {
@@ -955,6 +1215,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add)
 		evsel->attr.exclude_idle   = mod.eI;
 		evsel->exclude_GH          = mod.exclude_GH;
 		evsel->sample_read         = mod.sample_read;
+		evsel->precise_max         = mod.precise_max;
 
 		if (perf_evsel__is_group_leader(evsel))
 			evsel->attr.pinned = mod.pinned;
@@ -1142,6 +1403,11 @@ int parse_events(struct perf_evlist *evlist, const char *str,
 	if (!ret) {
 		struct perf_evsel *last;
 
+		if (list_empty(&data.list)) {
+			WARN_ONCE(true, "WARNING: event parser found nothing");
+			return -1;
+		}
+
 		perf_evlist__splice_list_tail(evlist, &data.list);
 		evlist->nr_groups += data.nr_groups;
 		last = perf_evlist__last(evlist);
@@ -1251,6 +1517,12 @@ foreach_evsel_in_last_glob(struct perf_evlist *evlist,
 	struct perf_evsel *last = NULL;
 	int err;
 
+	/*
+	 * Don't return when list_empty, give func a chance to report
+	 * error when it found last == NULL.
+	 *
+	 * So no need to WARN here, let *func do this.
+	 */
 	if (evlist->nr_entries > 0)
 		last = perf_evlist__last(evlist);
 
@@ -1419,7 +1691,7 @@ restart:
 		printf("  %-50s [%s]\n", evt_list[evt_i++],
 				event_type_descriptors[PERF_TYPE_TRACEPOINT]);
 	}
-	if (evt_num)
+	if (evt_num && pager_in_use())
 		printf("\n");
 
 out_free:
@@ -1575,7 +1847,7 @@ restart:
 		printf("  %-50s [%s]\n", evt_list[evt_i++],
 				event_type_descriptors[PERF_TYPE_HW_CACHE]);
 	}
-	if (evt_num)
+	if (evt_num && pager_in_use())
 		printf("\n");
 
 out_free:
@@ -1611,7 +1883,7 @@ restart:
 
 	for (i = 0; i < max; i++, syms++) {
 
-		if (event_glob != NULL &&
+		if (event_glob != NULL && syms->symbol != NULL &&
 		    !(strglobmatch(syms->symbol, event_glob) ||
 		      (syms->alias && strglobmatch(syms->alias, event_glob))))
 			continue;
@@ -1648,7 +1920,7 @@ restart:
 		}
 		printf("  %-50s [%s]\n", evt_list[evt_i++], event_type_descriptors[type]);
 	}
-	if (evt_num)
+	if (evt_num && pager_in_use())
 		printf("\n");
 
 out_free:
@@ -1689,13 +1961,14 @@ void print_events(const char *event_glob, bool name_only)
 		printf("  %-50s [%s]\n",
 		       "cpu/t1=v1[,t2=v2,t3 ...]/modifier",
 		       event_type_descriptors[PERF_TYPE_RAW]);
-		printf("   (see 'man perf-list' on how to encode it)\n");
-		printf("\n");
+		if (pager_in_use())
+			printf("   (see 'man perf-list' on how to encode it)\n\n");
 
 		printf("  %-50s [%s]\n",
 		       "mem:<addr>[/len][:access]",
 			event_type_descriptors[PERF_TYPE_BREAKPOINT]);
-		printf("\n");
+		if (pager_in_use())
+			printf("\n");
 	}
 
 	print_tracepoint_events(NULL, NULL, name_only);
@@ -1811,3 +2084,29 @@ void parse_events_evlist_error(struct parse_events_evlist *data,
 	err->str = strdup(str);
 	WARN_ONCE(!err->str, "WARNING: failed to allocate error string");
 }
+
+/*
+ * Return string contains valid config terms of an event.
+ * @additional_terms: For terms such as PMU sysfs terms.
+ */
+char *parse_events_formats_error_string(char *additional_terms)
+{
+	char *str;
+	static const char *static_terms = "config,config1,config2,name,"
+					  "period,freq,branch_type,time,"
+					  "call-graph,stack-size\n";
+
+	/* valid terms */
+	if (additional_terms) {
+		if (!asprintf(&str, "valid terms: %s,%s",
+			      additional_terms, static_terms))
+			goto fail;
+	} else {
+		if (!asprintf(&str, "valid terms: %s", static_terms))
+			goto fail;
+	}
+	return str;
+
+fail:
+	return NULL;
+}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index a09b0e210..f1a6db107 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -67,6 +67,8 @@ enum {
 	PARSE_EVENTS__TERM_TYPE_TIME,
 	PARSE_EVENTS__TERM_TYPE_CALLGRAPH,
 	PARSE_EVENTS__TERM_TYPE_STACKSIZE,
+	PARSE_EVENTS__TERM_TYPE_NOINHERIT,
+	PARSE_EVENTS__TERM_TYPE_INHERIT
 };
 
 struct parse_events_term {
@@ -118,7 +120,18 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add);
 int parse_events__modifier_group(struct list_head *list, char *event_mod);
 int parse_events_name(struct list_head *list, char *name);
 int parse_events_add_tracepoint(struct list_head *list, int *idx,
-				char *sys, char *event);
+				char *sys, char *event,
+				struct parse_events_error *error,
+				struct list_head *head_config);
+int parse_events_load_bpf(struct parse_events_evlist *data,
+			  struct list_head *list,
+			  char *bpf_file_name,
+			  bool source);
+/* Provide this function for perf test */
+struct bpf_object;
+int parse_events_load_bpf_obj(struct parse_events_evlist *data,
+			      struct list_head *list,
+			      struct bpf_object *obj);
 int parse_events_add_numeric(struct parse_events_evlist *data,
 			     struct list_head *list,
 			     u32 type, u64 config,
@@ -155,5 +168,6 @@ int print_hwcache_events(const char *event_glob, bool name_only);
 extern int is_valid_tracepoint(const char *event_string);
 
 int valid_event_mount(const char *eventfs);
+char *parse_events_formats_error_string(char *additional_terms);
 
 #endif /* __PERF_PARSE_EVENTS_H */
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 936d566f4..58c5831ff 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -115,6 +115,8 @@ do {							\
 group		[^,{}/]*[{][^}]*[}][^,{}/]*
 event_pmu	[^,{}/]+[/][^/]*[/][^,{}/]*
 event		[^,{}/]+
+bpf_object	.*\.(o|bpf)
+bpf_source	.*\.c
 
 num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]+
@@ -122,7 +124,7 @@ num_raw_hex	[a-fA-F0-9]+
 name		[a-zA-Z_*?][a-zA-Z0-9_*?.]*
 name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.]*
 /* If you add a modifier you need to update check_modifier() */
-modifier_event	[ukhpGHSDI]+
+modifier_event	[ukhpPGHSDI]+
 modifier_bp	[rwx]{1,3}
 
 %%
@@ -159,6 +161,8 @@ modifier_bp	[rwx]{1,3}
 		}
 
 {event_pmu}	|
+{bpf_object}	|
+{bpf_source}	|
 {event}		{
 			BEGIN(INITIAL);
 			REWIND(1);
@@ -174,7 +178,7 @@ modifier_bp	[rwx]{1,3}
 
 <config>{
 	/*
-	 * Please update formats_error_string any time
+	 * Please update parse_events_formats_error_string any time
 	 * new static term is added.
 	 */
 config			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
@@ -187,6 +191,8 @@ branch_type		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE
 time			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_TIME); }
 call-graph		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CALLGRAPH); }
 stack-size		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_STACKSIZE); }
+inherit			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_INHERIT); }
+no-inherit		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
 ,			{ return ','; }
 "/"			{ BEGIN(INITIAL); return '/'; }
 {name_minus}		{ return str(yyscanner, PE_NAME); }
@@ -264,6 +270,8 @@ r{num_raw_hex}		{ return raw(yyscanner); }
 {num_hex}		{ return value(yyscanner, 16); }
 
 {modifier_event}	{ return str(yyscanner, PE_MODIFIER_EVENT); }
+{bpf_object}		{ return str(yyscanner, PE_BPF_OBJECT); }
+{bpf_source}		{ return str(yyscanner, PE_BPF_SOURCE); }
 {name}			{ return pmu_str_check(yyscanner); }
 "/"			{ BEGIN(config); return '/'; }
 -			{ return '-'; }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 9cd70819c..ad379968d 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -42,6 +42,7 @@ static inc_group_count(struct list_head *list,
 %token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_RAW PE_TERM
 %token PE_EVENT_NAME
 %token PE_NAME
+%token PE_BPF_OBJECT PE_BPF_SOURCE
 %token PE_MODIFIER_EVENT PE_MODIFIER_BP
 %token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT
 %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP
@@ -53,6 +54,8 @@ static inc_group_count(struct list_head *list,
 %type <num> PE_RAW
 %type <num> PE_TERM
 %type <str> PE_NAME
+%type <str> PE_BPF_OBJECT
+%type <str> PE_BPF_SOURCE
 %type <str> PE_NAME_CACHE_TYPE
 %type <str> PE_NAME_CACHE_OP_RESULT
 %type <str> PE_MODIFIER_EVENT
@@ -67,8 +70,10 @@ static inc_group_count(struct list_head *list,
 %type <head> event_legacy_cache
 %type <head> event_legacy_mem
 %type <head> event_legacy_tracepoint
+%type <tracepoint_name> tracepoint_name
 %type <head> event_legacy_numeric
 %type <head> event_legacy_raw
+%type <head> event_bpf_file
 %type <head> event_def
 %type <head> event_mod
 %type <head> event_name
@@ -84,6 +89,10 @@ static inc_group_count(struct list_head *list,
 	u64 num;
 	struct list_head *head;
 	struct parse_events_term *term;
+	struct tracepoint_name {
+		char *sys;
+		char *event;
+	} tracepoint_name;
 }
 %%
 
@@ -198,7 +207,8 @@ event_def: event_pmu |
 	   event_legacy_mem |
 	   event_legacy_tracepoint sep_dc |
 	   event_legacy_numeric sep_dc |
-	   event_legacy_raw sep_dc
+	   event_legacy_raw sep_dc |
+	   event_bpf_file
 
 event_pmu:
 PE_NAME '/' event_config '/'
@@ -368,36 +378,60 @@ PE_PREFIX_MEM PE_VALUE sep_dc
 }
 
 event_legacy_tracepoint:
-PE_NAME '-' PE_NAME ':' PE_NAME
+tracepoint_name
 {
 	struct parse_events_evlist *data = _data;
+	struct parse_events_error *error = data->error;
 	struct list_head *list;
-	char sys_name[128];
-	snprintf(&sys_name, 128, "%s-%s", $1, $3);
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_tracepoint(list, &data->idx, &sys_name, $5));
+	if (error)
+		error->idx = @1.first_column;
+
+	if (parse_events_add_tracepoint(list, &data->idx, $1.sys, $1.event,
+					error, NULL))
+		return -1;
+
 	$$ = list;
 }
 |
-PE_NAME ':' PE_NAME
+tracepoint_name '/' event_config '/'
 {
 	struct parse_events_evlist *data = _data;
+	struct parse_events_error *error = data->error;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	if (parse_events_add_tracepoint(list, &data->idx, $1, $3)) {
-		struct parse_events_error *error = data->error;
+	if (error)
+		error->idx = @1.first_column;
 
-		if (error) {
-			error->idx = @1.first_column;
-			error->str = strdup("unknown tracepoint");
-		}
+	if (parse_events_add_tracepoint(list, &data->idx, $1.sys, $1.event,
+					error, $3))
 		return -1;
-	}
+
 	$$ = list;
 }
 
+tracepoint_name:
+PE_NAME '-' PE_NAME ':' PE_NAME
+{
+	char sys_name[128];
+	struct tracepoint_name tracepoint;
+
+	snprintf(&sys_name, 128, "%s-%s", $1, $3);
+	tracepoint.sys = &sys_name;
+	tracepoint.event = $5;
+
+	$$ = tracepoint;
+}
+|
+PE_NAME ':' PE_NAME
+{
+	struct tracepoint_name tracepoint = {$1, $3};
+
+	$$ = tracepoint;
+}
+
 event_legacy_numeric:
 PE_VALUE ':' PE_VALUE
 {
@@ -420,6 +454,28 @@ PE_RAW
 	$$ = list;
 }
 
+event_bpf_file:
+PE_BPF_OBJECT
+{
+	struct parse_events_evlist *data = _data;
+	struct parse_events_error *error = data->error;
+	struct list_head *list;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_load_bpf(data, list, $1, false));
+	$$ = list;
+}
+|
+PE_BPF_SOURCE
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *list;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_load_bpf(data, list, $1, true));
+	$$ = list;
+}
+
 start_terms: event_config
 {
 	struct parse_events_terms *data = _data;
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index 01626be2a..9fca09296 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -2,10 +2,13 @@
 #include "parse-options.h"
 #include "cache.h"
 #include "header.h"
+#include <linux/string.h>
 
 #define OPT_SHORT 1
 #define OPT_UNSET 2
 
+static struct strbuf error_buf = STRBUF_INIT;
+
 static int opterror(const struct option *opt, const char *reason, int flags)
 {
 	if (flags & OPT_SHORT)
@@ -372,7 +375,8 @@ void parse_options_start(struct parse_opt_ctx_t *ctx,
 }
 
 static int usage_with_options_internal(const char * const *,
-				       const struct option *, int);
+				       const struct option *, int,
+				       struct parse_opt_ctx_t *);
 
 int parse_options_step(struct parse_opt_ctx_t *ctx,
 		       const struct option *options,
@@ -396,8 +400,9 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 
 		if (arg[1] != '-') {
 			ctx->opt = ++arg;
-			if (internal_help && *ctx->opt == 'h')
-				return usage_with_options_internal(usagestr, options, 0);
+			if (internal_help && *ctx->opt == 'h') {
+				return usage_with_options_internal(usagestr, options, 0, ctx);
+			}
 			switch (parse_short_opt(ctx, options)) {
 			case -1:
 				return parse_options_usage(usagestr, options, arg, 1);
@@ -412,7 +417,7 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 				check_typos(arg, options);
 			while (ctx->opt) {
 				if (internal_help && *ctx->opt == 'h')
-					return usage_with_options_internal(usagestr, options, 0);
+					return usage_with_options_internal(usagestr, options, 0, ctx);
 				arg = ctx->opt;
 				switch (parse_short_opt(ctx, options)) {
 				case -1:
@@ -445,9 +450,9 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 
 		arg += 2;
 		if (internal_help && !strcmp(arg, "help-all"))
-			return usage_with_options_internal(usagestr, options, 1);
+			return usage_with_options_internal(usagestr, options, 1, ctx);
 		if (internal_help && !strcmp(arg, "help"))
-			return usage_with_options_internal(usagestr, options, 0);
+			return usage_with_options_internal(usagestr, options, 0, ctx);
 		if (!strcmp(arg, "list-opts"))
 			return PARSE_OPT_LIST_OPTS;
 		if (!strcmp(arg, "list-cmds"))
@@ -496,7 +501,7 @@ int parse_options_subcommand(int argc, const char **argv, const struct option *o
 {
 	struct parse_opt_ctx_t ctx;
 
-	perf_header__set_cmdline(argc, argv);
+	perf_env__set_cmdline(&perf_env, argc, argv);
 
 	/* build usage string if it's not provided */
 	if (subcommands && !usagestr[0]) {
@@ -537,9 +542,11 @@ int parse_options_subcommand(int argc, const char **argv, const struct option *o
 		exit(130);
 	default: /* PARSE_OPT_UNKNOWN */
 		if (ctx.argv[0][1] == '-') {
-			error("unknown option `%s'", ctx.argv[0] + 2);
+			strbuf_addf(&error_buf, "unknown option `%s'",
+				    ctx.argv[0] + 2);
 		} else {
-			error("unknown switch `%c'", *ctx.opt);
+			strbuf_addf(&error_buf, "unknown switch `%c'",
+				    *ctx.opt);
 		}
 		usage_with_options(usagestr, options);
 	}
@@ -642,13 +649,93 @@ static void print_option_help(const struct option *opts, int full)
 	fprintf(stderr, "%*s%s\n", pad + USAGE_GAP, "", opts->help);
 }
 
+static int option__cmp(const void *va, const void *vb)
+{
+	const struct option *a = va, *b = vb;
+	int sa = tolower(a->short_name), sb = tolower(b->short_name), ret;
+
+	if (sa == 0)
+		sa = 'z' + 1;
+	if (sb == 0)
+		sb = 'z' + 1;
+
+	ret = sa - sb;
+
+	if (ret == 0) {
+		const char *la = a->long_name ?: "",
+			   *lb = b->long_name ?: "";
+		ret = strcmp(la, lb);
+	}
+
+	return ret;
+}
+
+static struct option *options__order(const struct option *opts)
+{
+	int nr_opts = 0;
+	const struct option *o = opts;
+	struct option *ordered;
+
+	for (o = opts; o->type != OPTION_END; o++)
+		++nr_opts;
+
+	ordered = memdup(opts, sizeof(*o) * (nr_opts + 1));
+	if (ordered == NULL)
+		goto out;
+
+	qsort(ordered, nr_opts, sizeof(*o), option__cmp);
+out:
+	return ordered;
+}
+
+static bool option__in_argv(const struct option *opt, const struct parse_opt_ctx_t *ctx)
+{
+	int i;
+
+	for (i = 1; i < ctx->argc; ++i) {
+		const char *arg = ctx->argv[i];
+
+		if (arg[0] != '-') {
+			if (arg[1] == '\0') {
+				if (arg[0] == opt->short_name)
+					return true;
+				continue;
+			}
+
+			if (opt->long_name && strcmp(opt->long_name, arg) == 0)
+				return true;
+
+			if (opt->help && strcasestr(opt->help, arg) != NULL)
+				return true;
+
+			continue;
+		}
+
+		if (arg[1] == opt->short_name ||
+		    (arg[1] == '-' && opt->long_name && strcmp(opt->long_name, arg + 2) == 0))
+			return true;
+	}
+
+	return false;
+}
+
 int usage_with_options_internal(const char * const *usagestr,
-				const struct option *opts, int full)
+				const struct option *opts, int full,
+				struct parse_opt_ctx_t *ctx)
 {
+	struct option *ordered;
+
 	if (!usagestr)
 		return PARSE_OPT_HELP;
 
-	fprintf(stderr, "\n usage: %s\n", *usagestr++);
+	setup_pager();
+
+	if (strbuf_avail(&error_buf)) {
+		fprintf(stderr, "  Error: %s\n", error_buf.buf);
+		strbuf_release(&error_buf);
+	}
+
+	fprintf(stderr, "\n Usage: %s\n", *usagestr++);
 	while (*usagestr && **usagestr)
 		fprintf(stderr, "    or: %s\n", *usagestr++);
 	while (*usagestr) {
@@ -661,11 +748,20 @@ int usage_with_options_internal(const char * const *usagestr,
 	if (opts->type != OPTION_GROUP)
 		fputc('\n', stderr);
 
-	for (  ; opts->type != OPTION_END; opts++)
+	ordered = options__order(opts);
+	if (ordered)
+		opts = ordered;
+
+	for (  ; opts->type != OPTION_END; opts++) {
+		if (ctx && ctx->argc > 1 && !option__in_argv(opts, ctx))
+			continue;
 		print_option_help(opts, full);
+	}
 
 	fputc('\n', stderr);
 
+	free(ordered);
+
 	return PARSE_OPT_HELP;
 }
 
@@ -673,7 +769,22 @@ void usage_with_options(const char * const *usagestr,
 			const struct option *opts)
 {
 	exit_browser(false);
-	usage_with_options_internal(usagestr, opts, 0);
+	usage_with_options_internal(usagestr, opts, 0, NULL);
+	exit(129);
+}
+
+void usage_with_options_msg(const char * const *usagestr,
+			    const struct option *opts, const char *fmt, ...)
+{
+	va_list ap;
+
+	exit_browser(false);
+
+	va_start(ap, fmt);
+	strbuf_addv(&error_buf, fmt, ap);
+	va_end(ap);
+
+	usage_with_options_internal(usagestr, opts, 0, NULL);
 	exit(129);
 }
 
@@ -684,7 +795,7 @@ int parse_options_usage(const char * const *usagestr,
 	if (!usagestr)
 		goto opt;
 
-	fprintf(stderr, "\n usage: %s\n", *usagestr++);
+	fprintf(stderr, "\n Usage: %s\n", *usagestr++);
 	while (*usagestr && **usagestr)
 		fprintf(stderr, "    or: %s\n", *usagestr++);
 	while (*usagestr) {
@@ -698,24 +809,23 @@ int parse_options_usage(const char * const *usagestr,
 opt:
 	for (  ; opts->type != OPTION_END; opts++) {
 		if (short_opt) {
-			if (opts->short_name == *optstr)
+			if (opts->short_name == *optstr) {
+				print_option_help(opts, 0);
 				break;
+			}
 			continue;
 		}
 
 		if (opts->long_name == NULL)
 			continue;
 
-		if (!prefixcmp(optstr, opts->long_name))
-			break;
-		if (!prefixcmp(optstr, "no-") &&
-		    !prefixcmp(optstr + 3, opts->long_name))
-			break;
+		if (!prefixcmp(opts->long_name, optstr))
+			print_option_help(opts, 0);
+		if (!prefixcmp("no-", optstr) &&
+		    !prefixcmp(opts->long_name, optstr + 3))
+			print_option_help(opts, 0);
 	}
 
-	if (opts->type != OPTION_END)
-		print_option_help(opts, 0);
-
 	return PARSE_OPT_HELP;
 }
 
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index 367d8b816..a8e407bc2 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -111,6 +111,7 @@ struct option {
 #define OPT_GROUP(h)                { .type = OPTION_GROUP, .help = (h) }
 #define OPT_BIT(s, l, v, h, b)      { .type = OPTION_BIT, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h), .defval = (b) }
 #define OPT_BOOLEAN(s, l, v, h)     { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), .value = check_vtype(v, bool *), .help = (h) }
+#define OPT_BOOLEAN_FLAG(s, l, v, h, f)     { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), .value = check_vtype(v, bool *), .help = (h), .flags = (f) }
 #define OPT_BOOLEAN_SET(s, l, v, os, h) \
 	{ .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), \
 	.value = check_vtype(v, bool *), .help = (h), \
@@ -160,6 +161,10 @@ extern int parse_options_subcommand(int argc, const char **argv,
 
 extern NORETURN void usage_with_options(const char * const *usagestr,
                                         const struct option *options);
+extern NORETURN __attribute__((format(printf,3,4)))
+void usage_with_options_msg(const char * const *usagestr,
+			    const struct option *options,
+			    const char *fmt, ...);
 
 /*----- incremantal advanced APIs -----*/
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 89c91a1a6..e4b173dec 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -626,38 +626,26 @@ static int pmu_resolve_param_term(struct parse_events_term *term,
 	return -1;
 }
 
-static char *formats_error_string(struct list_head *formats)
+static char *pmu_formats_string(struct list_head *formats)
 {
 	struct perf_pmu_format *format;
-	char *err, *str;
-	static const char *static_terms = "config,config1,config2,name,"
-					  "period,freq,branch_type,time,"
-					  "call-graph,stack-size\n";
+	char *str;
+	struct strbuf buf;
 	unsigned i = 0;
 
-	if (!asprintf(&str, "valid terms:"))
+	if (!formats)
 		return NULL;
 
+	strbuf_init(&buf, 0);
 	/* sysfs exported terms */
-	list_for_each_entry(format, formats, list) {
-		char c = i++ ? ',' : ' ';
-
-		err = str;
-		if (!asprintf(&str, "%s%c%s", err, c, format->name))
-			goto fail;
-		free(err);
-	}
+	list_for_each_entry(format, formats, list)
+		strbuf_addf(&buf, i++ ? ",%s" : "%s",
+			    format->name);
 
-	/* static terms */
-	err = str;
-	if (!asprintf(&str, "%s,%s", err, static_terms))
-		goto fail;
+	str = strbuf_detach(&buf, NULL);
+	strbuf_release(&buf);
 
-	free(err);
 	return str;
-fail:
-	free(err);
-	return NULL;
 }
 
 /*
@@ -693,9 +681,12 @@ static int pmu_config_term(struct list_head *formats,
 		if (verbose)
 			printf("Invalid event/parameter '%s'\n", term->config);
 		if (err) {
+			char *pmu_term = pmu_formats_string(formats);
+
 			err->idx  = term->err_term;
 			err->str  = strdup("unknown term");
-			err->help = formats_error_string(formats);
+			err->help = parse_events_formats_error_string(pmu_term);
+			free(pmu_term);
 		}
 		return -EINVAL;
 	}
@@ -1017,7 +1008,8 @@ void print_pmu_events(const char *event_glob, bool name_only)
 				goto out_enomem;
 			j++;
 		}
-		if (pmu->selectable) {
+		if (pmu->selectable &&
+		    (event_glob == NULL || strglobmatch(pmu->name, event_glob))) {
 			char *s;
 			if (asprintf(&s, "%s//", pmu->name) < 0)
 				goto out_enomem;
@@ -1035,7 +1027,7 @@ void print_pmu_events(const char *event_glob, bool name_only)
 		printf("  %-50s [Kernel PMU event]\n", aliases[j]);
 		printed++;
 	}
-	if (printed)
+	if (printed && pager_in_use())
 		printf("\n");
 out_free:
 	for (j = 0; j < len; j++)
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index c6f9af78f..03875f915 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -40,8 +40,7 @@
 #include "color.h"
 #include "symbol.h"
 #include "thread.h"
-#include <api/fs/debugfs.h>
-#include <api/fs/tracefs.h>
+#include <api/fs/fs.h>
 #include "trace-event.h"	/* For __maybe_unused */
 #include "probe-event.h"
 #include "probe-finder.h"
@@ -72,7 +71,7 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp);
 static struct machine *host_machine;
 
 /* Initialize symbol maps and path of vmlinux/modules */
-static int init_symbol_maps(bool user_only)
+int init_probe_symbol_maps(bool user_only)
 {
 	int ret;
 
@@ -102,7 +101,7 @@ out:
 	return ret;
 }
 
-static void exit_symbol_maps(void)
+void exit_probe_symbol_maps(void)
 {
 	if (host_machine) {
 		machine__delete(host_machine);
@@ -127,17 +126,19 @@ static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void)
 {
 	/* kmap->ref_reloc_sym should be set if host_machine is initialized */
 	struct kmap *kmap;
+	struct map *map = machine__kernel_map(host_machine);
 
-	if (map__load(host_machine->vmlinux_maps[MAP__FUNCTION], NULL) < 0)
+	if (map__load(map, NULL) < 0)
 		return NULL;
 
-	kmap = map__kmap(host_machine->vmlinux_maps[MAP__FUNCTION]);
+	kmap = map__kmap(map);
 	if (!kmap)
 		return NULL;
 	return kmap->ref_reloc_sym;
 }
 
-static u64 kernel_get_symbol_address_by_name(const char *name, bool reloc)
+static int kernel_get_symbol_address_by_name(const char *name, u64 *addr,
+					     bool reloc, bool reladdr)
 {
 	struct ref_reloc_sym *reloc_sym;
 	struct symbol *sym;
@@ -146,12 +147,14 @@ static u64 kernel_get_symbol_address_by_name(const char *name, bool reloc)
 	/* ref_reloc_sym is just a label. Need a special fix*/
 	reloc_sym = kernel_get_ref_reloc_sym();
 	if (reloc_sym && strcmp(name, reloc_sym->name) == 0)
-		return (reloc) ? reloc_sym->addr : reloc_sym->unrelocated_addr;
+		*addr = (reloc) ? reloc_sym->addr : reloc_sym->unrelocated_addr;
 	else {
 		sym = __find_kernel_function_by_name(name, &map);
-		if (sym)
-			return map->unmap_ip(map, sym->start) -
-				((reloc) ? 0 : map->reloc);
+		if (!sym)
+			return -ENOENT;
+		*addr = map->unmap_ip(map, sym->start) -
+			((reloc) ? 0 : map->reloc) -
+			((reladdr) ? map->start : 0);
 	}
 	return 0;
 }
@@ -245,12 +248,14 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
 static bool kprobe_blacklist__listed(unsigned long address);
 static bool kprobe_warn_out_range(const char *symbol, unsigned long address)
 {
-	u64 etext_addr;
+	u64 etext_addr = 0;
+	int ret;
 
 	/* Get the address of _etext for checking non-probable text symbol */
-	etext_addr = kernel_get_symbol_address_by_name("_etext", false);
+	ret = kernel_get_symbol_address_by_name("_etext", &etext_addr,
+						false, false);
 
-	if (etext_addr != 0 && etext_addr < address)
+	if (ret == 0 && etext_addr < address)
 		pr_warning("%s is out of .text, skip it.\n", symbol);
 	else if (kprobe_blacklist__listed(address))
 		pr_warning("%s is blacklisted function, skip it.\n", symbol);
@@ -282,7 +287,7 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso)
 		return -ENOENT;
 	}
 
-	map = host_machine->vmlinux_maps[MAP__FUNCTION];
+	map = machine__kernel_map(host_machine);
 	dso = map->dso;
 
 	vmlinux_name = symbol_conf.vmlinux_name;
@@ -436,19 +441,22 @@ static char *debuginfo_cache_path;
 
 static struct debuginfo *debuginfo_cache__open(const char *module, bool silent)
 {
-	if ((debuginfo_cache_path && !strcmp(debuginfo_cache_path, module)) ||
-	    (!debuginfo_cache_path && !module && debuginfo_cache))
+	const char *path = module;
+
+	/* If the module is NULL, it should be the kernel. */
+	if (!module)
+		path = "kernel";
+
+	if (debuginfo_cache_path && !strcmp(debuginfo_cache_path, path))
 		goto out;
 
 	/* Copy module path */
 	free(debuginfo_cache_path);
-	if (module) {
-		debuginfo_cache_path = strdup(module);
-		if (!debuginfo_cache_path) {
-			debuginfo__delete(debuginfo_cache);
-			debuginfo_cache = NULL;
-			goto out;
-		}
+	debuginfo_cache_path = strdup(path);
+	if (!debuginfo_cache_path) {
+		debuginfo__delete(debuginfo_cache);
+		debuginfo_cache = NULL;
+		goto out;
 	}
 
 	debuginfo_cache = open_debuginfo(module, silent);
@@ -517,8 +525,10 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
 			goto error;
 		addr += stext;
 	} else if (tp->symbol) {
-		addr = kernel_get_symbol_address_by_name(tp->symbol, false);
-		if (addr == 0)
+		/* If the module is given, this returns relative address */
+		ret = kernel_get_symbol_address_by_name(tp->symbol, &addr,
+							false, !!tp->module);
+		if (ret != 0)
 			goto error;
 		addr += tp->offset;
 	}
@@ -861,11 +871,11 @@ int show_line_range(struct line_range *lr, const char *module, bool user)
 {
 	int ret;
 
-	ret = init_symbol_maps(user);
+	ret = init_probe_symbol_maps(user);
 	if (ret < 0)
 		return ret;
 	ret = __show_line_range(lr, module, user);
-	exit_symbol_maps();
+	exit_probe_symbol_maps();
 
 	return ret;
 }
@@ -943,7 +953,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 	int i, ret = 0;
 	struct debuginfo *dinfo;
 
-	ret = init_symbol_maps(pevs->uprobes);
+	ret = init_probe_symbol_maps(pevs->uprobes);
 	if (ret < 0)
 		return ret;
 
@@ -960,7 +970,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 
 	debuginfo__delete(dinfo);
 out:
-	exit_symbol_maps();
+	exit_probe_symbol_maps();
 	return ret;
 }
 
@@ -1884,13 +1894,17 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
 			goto out;
 		sym = map__find_symbol(map, addr, NULL);
 	} else {
-		if (tp->symbol)
-			addr = kernel_get_symbol_address_by_name(tp->symbol, true);
+		if (tp->symbol && !addr) {
+			if (kernel_get_symbol_address_by_name(tp->symbol,
+						&addr, true, false) < 0)
+				goto out;
+		}
 		if (addr) {
 			addr += tp->offset;
 			sym = __find_kernel_function(addr, &map);
 		}
 	}
+
 	if (!sym)
 		goto out;
 
@@ -2055,7 +2069,7 @@ static void kprobe_blacklist__delete(struct list_head *blacklist)
 static int kprobe_blacklist__load(struct list_head *blacklist)
 {
 	struct kprobe_blacklist_node *node;
-	const char *__debugfs = debugfs_find_mountpoint();
+	const char *__debugfs = debugfs__mountpoint();
 	char buf[PATH_MAX], *p;
 	FILE *fp;
 	int ret;
@@ -2181,9 +2195,9 @@ out:
 }
 
 /* Show an event */
-static int show_perf_probe_event(const char *group, const char *event,
-				 struct perf_probe_event *pev,
-				 const char *module, bool use_stdout)
+int show_perf_probe_event(const char *group, const char *event,
+			  struct perf_probe_event *pev,
+			  const char *module, bool use_stdout)
 {
 	struct strbuf buf = STRBUF_INIT;
 	int ret;
@@ -2264,7 +2278,7 @@ int show_perf_probe_events(struct strfilter *filter)
 
 	setup_pager();
 
-	ret = init_symbol_maps(false);
+	ret = init_probe_symbol_maps(false);
 	if (ret < 0)
 		return ret;
 
@@ -2280,7 +2294,7 @@ int show_perf_probe_events(struct strfilter *filter)
 		close(kp_fd);
 	if (up_fd > 0)
 		close(up_fd);
-	exit_symbol_maps();
+	exit_probe_symbol_maps();
 
 	return ret;
 }
@@ -2289,36 +2303,41 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 			      struct strlist *namelist, bool allow_suffix)
 {
 	int i, ret;
-	char *p;
+	char *p, *nbase;
 
 	if (*base == '.')
 		base++;
+	nbase = strdup(base);
+	if (!nbase)
+		return -ENOMEM;
+
+	/* Cut off the dot suffixes (e.g. .const, .isra)*/
+	p = strchr(nbase, '.');
+	if (p && p != nbase)
+		*p = '\0';
 
-	/* Try no suffix */
-	ret = e_snprintf(buf, len, "%s", base);
+	/* Try no suffix number */
+	ret = e_snprintf(buf, len, "%s", nbase);
 	if (ret < 0) {
 		pr_debug("snprintf() failed: %d\n", ret);
-		return ret;
+		goto out;
 	}
-	/* Cut off the postfixes (e.g. .const, .isra)*/
-	p = strchr(buf, '.');
-	if (p && p != buf)
-		*p = '\0';
 	if (!strlist__has_entry(namelist, buf))
-		return 0;
+		goto out;
 
 	if (!allow_suffix) {
 		pr_warning("Error: event \"%s\" already exists. "
-			   "(Use -f to force duplicates.)\n", base);
-		return -EEXIST;
+			   "(Use -f to force duplicates.)\n", buf);
+		ret = -EEXIST;
+		goto out;
 	}
 
 	/* Try to add suffix */
 	for (i = 1; i < MAX_EVENT_INDEX; i++) {
-		ret = e_snprintf(buf, len, "%s_%d", base, i);
+		ret = e_snprintf(buf, len, "%s_%d", nbase, i);
 		if (ret < 0) {
 			pr_debug("snprintf() failed: %d\n", ret);
-			return ret;
+			goto out;
 		}
 		if (!strlist__has_entry(namelist, buf))
 			break;
@@ -2328,6 +2347,8 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 		ret = -ERANGE;
 	}
 
+out:
+	free(nbase);
 	return ret;
 }
 
@@ -2400,7 +2421,6 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 {
 	int i, fd, ret;
 	struct probe_trace_event *tev = NULL;
-	const char *event = NULL, *group = NULL;
 	struct strlist *namelist;
 
 	fd = probe_file__open(PF_FL_RW | (pev->uprobes ? PF_FL_UPROBE : 0));
@@ -2416,7 +2436,6 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 	}
 
 	ret = 0;
-	pr_info("Added new event%s\n", (ntevs > 1) ? "s:" : ":");
 	for (i = 0; i < ntevs; i++) {
 		tev = &tevs[i];
 		/* Skip if the symbol is out of .text or blacklisted */
@@ -2433,13 +2452,6 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 		if (ret < 0)
 			break;
 
-		/* We use tev's name for showing new events */
-		show_perf_probe_event(tev->group, tev->event, pev,
-				      tev->point.module, false);
-		/* Save the last valid name */
-		event = tev->event;
-		group = tev->group;
-
 		/*
 		 * Probes after the first probe which comes from same
 		 * user input are always allowed to add suffix, because
@@ -2451,13 +2463,6 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 	if (ret == -EINVAL && pev->uprobes)
 		warn_uprobe_event_compat(tev);
 
-	/* Note that it is possible to skip all events because of blacklist */
-	if (ret >= 0 && event) {
-		/* Show how to use the event. */
-		pr_info("\nYou can now use it in all perf tools, such as:\n\n");
-		pr_info("\tperf record -e %s:%s -aR sleep 1\n\n", group, event);
-	}
-
 	strlist__delete(namelist);
 close_out:
 	close(fd);
@@ -2538,7 +2543,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 		goto out;
 	}
 
-	if (!pev->uprobes && !pp->retprobe) {
+	/* Note that the symbols in the kmodule are not relocated */
+	if (!pev->uprobes && !pp->retprobe && !pev->target) {
 		reloc_sym = kernel_get_ref_reloc_sym();
 		if (!reloc_sym) {
 			pr_warning("Relocated base symbol is not found!\n");
@@ -2575,8 +2581,9 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 		}
 		/* Add one probe point */
 		tp->address = map->unmap_ip(map, sym->start) + pp->offset;
-		/* If we found a wrong one, mark it by NULL symbol */
-		if (!pev->uprobes &&
+
+		/* Check the kprobe (not in module) is within .text  */
+		if (!pev->uprobes && !pev->target &&
 		    kprobe_warn_out_range(sym->name, tp->address)) {
 			tp->symbol = NULL;	/* Skip it */
 			skipped++;
@@ -2760,63 +2767,71 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev,
 	return find_probe_trace_events_from_map(pev, tevs);
 }
 
-struct __event_package {
-	struct perf_probe_event		*pev;
-	struct probe_trace_event	*tevs;
-	int				ntevs;
-};
-
-int add_perf_probe_events(struct perf_probe_event *pevs, int npevs)
+int convert_perf_probe_events(struct perf_probe_event *pevs, int npevs)
 {
-	int i, j, ret;
-	struct __event_package *pkgs;
-
-	ret = 0;
-	pkgs = zalloc(sizeof(struct __event_package) * npevs);
-
-	if (pkgs == NULL)
-		return -ENOMEM;
-
-	ret = init_symbol_maps(pevs->uprobes);
-	if (ret < 0) {
-		free(pkgs);
-		return ret;
-	}
+	int i, ret;
 
 	/* Loop 1: convert all events */
 	for (i = 0; i < npevs; i++) {
-		pkgs[i].pev = &pevs[i];
 		/* Init kprobe blacklist if needed */
-		if (!pkgs[i].pev->uprobes)
+		if (!pevs[i].uprobes)
 			kprobe_blacklist__init();
 		/* Convert with or without debuginfo */
-		ret  = convert_to_probe_trace_events(pkgs[i].pev,
-						     &pkgs[i].tevs);
+		ret  = convert_to_probe_trace_events(&pevs[i], &pevs[i].tevs);
 		if (ret < 0)
-			goto end;
-		pkgs[i].ntevs = ret;
+			return ret;
+		pevs[i].ntevs = ret;
 	}
 	/* This just release blacklist only if allocated */
 	kprobe_blacklist__release();
 
+	return 0;
+}
+
+int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs)
+{
+	int i, ret = 0;
+
 	/* Loop 2: add all events */
 	for (i = 0; i < npevs; i++) {
-		ret = __add_probe_trace_events(pkgs[i].pev, pkgs[i].tevs,
-					       pkgs[i].ntevs,
+		ret = __add_probe_trace_events(&pevs[i], pevs[i].tevs,
+					       pevs[i].ntevs,
 					       probe_conf.force_add);
 		if (ret < 0)
 			break;
 	}
-end:
+	return ret;
+}
+
+void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs)
+{
+	int i, j;
+
 	/* Loop 3: cleanup and free trace events  */
 	for (i = 0; i < npevs; i++) {
-		for (j = 0; j < pkgs[i].ntevs; j++)
-			clear_probe_trace_event(&pkgs[i].tevs[j]);
-		zfree(&pkgs[i].tevs);
+		for (j = 0; j < pevs[i].ntevs; j++)
+			clear_probe_trace_event(&pevs[i].tevs[j]);
+		zfree(&pevs[i].tevs);
+		pevs[i].ntevs = 0;
+		clear_perf_probe_event(&pevs[i]);
 	}
-	free(pkgs);
-	exit_symbol_maps();
+}
 
+int add_perf_probe_events(struct perf_probe_event *pevs, int npevs)
+{
+	int ret;
+
+	ret = init_probe_symbol_maps(pevs->uprobes);
+	if (ret < 0)
+		return ret;
+
+	ret = convert_perf_probe_events(pevs, npevs);
+	if (ret == 0)
+		ret = apply_perf_probe_events(pevs, npevs);
+
+	cleanup_perf_probe_events(pevs, npevs);
+
+	exit_probe_symbol_maps();
 	return ret;
 }
 
@@ -2828,8 +2843,6 @@ int del_perf_probe_events(struct strfilter *filter)
 	if (!str)
 		return -EINVAL;
 
-	pr_debug("Delete filter: \'%s\'\n", str);
-
 	/* Get current event names */
 	ret = probe_file__open_both(&kfd, &ufd, PF_FL_RW);
 	if (ret < 0)
@@ -2844,9 +2857,6 @@ int del_perf_probe_events(struct strfilter *filter)
 		ret = ret2;
 		goto error;
 	}
-	if (ret == -ENOENT && ret2 == -ENOENT)
-		pr_debug("\"%s\" does not hit any event.\n", str);
-		/* Note that this is silently ignored */
 	ret = 0;
 
 error:
@@ -2881,7 +2891,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
 	struct map *map;
 	int ret;
 
-	ret = init_symbol_maps(user);
+	ret = init_probe_symbol_maps(user);
 	if (ret < 0)
 		return ret;
 
@@ -2911,7 +2921,7 @@ end:
 	if (user) {
 		map__put(map);
 	}
-	exit_symbol_maps();
+	exit_probe_symbol_maps();
 
 	return ret;
 }
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 6e7ec68a4..ba926c30f 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -87,6 +87,8 @@ struct perf_probe_event {
 	bool			uprobes;	/* Uprobe event flag */
 	char			*target;	/* Target binary */
 	struct perf_probe_arg	*args;	/* Arguments */
+	struct probe_trace_event *tevs;
+	int			ntevs;
 };
 
 /* Line range */
@@ -108,6 +110,8 @@ struct variable_list {
 };
 
 struct map;
+int init_probe_symbol_maps(bool user_only);
+void exit_probe_symbol_maps(void);
 
 /* Command string to events */
 extern int parse_perf_probe_command(const char *cmd,
@@ -138,7 +142,14 @@ extern void line_range__clear(struct line_range *lr);
 extern int line_range__init(struct line_range *lr);
 
 extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+extern int convert_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+extern int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+extern void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs);
 extern int del_perf_probe_events(struct strfilter *filter);
+
+extern int show_perf_probe_event(const char *group, const char *event,
+				 struct perf_probe_event *pev,
+				 const char *module, bool use_stdout);
 extern int show_perf_probe_events(struct strfilter *filter);
 extern int show_line_range(struct line_range *lr, const char *module,
 			   bool user);
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index bbb243717..e3b3b92e4 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -22,8 +22,7 @@
 #include "color.h"
 #include "symbol.h"
 #include "thread.h"
-#include <api/fs/debugfs.h>
-#include <api/fs/tracefs.h>
+#include <api/fs/tracing_path.h>
 #include "probe-event.h"
 #include "probe-file.h"
 #include "session.h"
@@ -73,21 +72,11 @@ static void print_both_open_warning(int kerr, int uerr)
 static int open_probe_events(const char *trace_file, bool readwrite)
 {
 	char buf[PATH_MAX];
-	const char *__debugfs;
 	const char *tracing_dir = "";
 	int ret;
 
-	__debugfs = tracefs_find_mountpoint();
-	if (__debugfs == NULL) {
-		tracing_dir = "tracing/";
-
-		__debugfs = debugfs_find_mountpoint();
-		if (__debugfs == NULL)
-			return -ENOTSUP;
-	}
-
 	ret = e_snprintf(buf, PATH_MAX, "%s/%s%s",
-			 __debugfs, tracing_dir, trace_file);
+			 tracing_path, tracing_dir, trace_file);
 	if (ret >= 0) {
 		pr_debug("Opening %s write=%d\n", buf, readwrite);
 		if (readwrite && !probe_event_dry_run)
@@ -149,6 +138,9 @@ struct strlist *probe_file__get_rawlist(int fd)
 	char *p;
 	struct strlist *sl;
 
+	if (fd < 0)
+		return NULL;
+
 	sl = strlist__new(NULL, NULL);
 
 	fp = fdopen(dup(fd), "r");
@@ -267,7 +259,6 @@ static int __del_trace_probe_event(int fd, struct str_node *ent)
 		goto error;
 	}
 
-	pr_info("Removed event: %s\n", ent->s);
 	return 0;
 error:
 	pr_warning("Failed to delete event: %s\n",
@@ -275,13 +266,17 @@ error:
 	return ret;
 }
 
-int probe_file__del_events(int fd, struct strfilter *filter)
+int probe_file__get_events(int fd, struct strfilter *filter,
+			   struct strlist *plist)
 {
 	struct strlist *namelist;
 	struct str_node *ent;
 	const char *p;
 	int ret = -ENOENT;
 
+	if (!plist)
+		return -EINVAL;
+
 	namelist = __probe_file__get_namelist(fd, true);
 	if (!namelist)
 		return -ENOENT;
@@ -290,12 +285,43 @@ int probe_file__del_events(int fd, struct strfilter *filter)
 		p = strchr(ent->s, ':');
 		if ((p && strfilter__compare(filter, p + 1)) ||
 		    strfilter__compare(filter, ent->s)) {
-			ret = __del_trace_probe_event(fd, ent);
-			if (ret < 0)
-				break;
+			strlist__add(plist, ent->s);
+			ret = 0;
 		}
 	}
 	strlist__delete(namelist);
 
 	return ret;
 }
+
+int probe_file__del_strlist(int fd, struct strlist *namelist)
+{
+	int ret = 0;
+	struct str_node *ent;
+
+	strlist__for_each(ent, namelist) {
+		ret = __del_trace_probe_event(fd, ent);
+		if (ret < 0)
+			break;
+	}
+	return ret;
+}
+
+int probe_file__del_events(int fd, struct strfilter *filter)
+{
+	struct strlist *namelist;
+	int ret;
+
+	namelist = strlist__new(NULL, NULL);
+	if (!namelist)
+		return -ENOMEM;
+
+	ret = probe_file__get_events(fd, filter, namelist);
+	if (ret < 0)
+		return ret;
+
+	ret = probe_file__del_strlist(fd, namelist);
+	strlist__delete(namelist);
+
+	return ret;
+}
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index ada94a242..18ac9cf51 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -14,5 +14,9 @@ struct strlist *probe_file__get_namelist(int fd);
 struct strlist *probe_file__get_rawlist(int fd);
 int probe_file__add_event(int fd, struct probe_trace_event *tev);
 int probe_file__del_events(int fd, struct strfilter *filter);
+int probe_file__get_events(int fd, struct strfilter *filter,
+				  struct strlist *plist);
+int probe_file__del_strlist(int fd, struct strlist *namelist);
+
 
 #endif
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 29c43c068..05012bb17 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -70,6 +70,7 @@ static int debuginfo__init_offline_dwarf(struct debuginfo *dbg,
 	if (!dbg->dwfl)
 		goto error;
 
+	dwfl_report_begin(dbg->dwfl);
 	dbg->mod = dwfl_report_offline(dbg->dwfl, "", "", fd);
 	if (!dbg->mod)
 		goto error;
@@ -78,6 +79,8 @@ static int debuginfo__init_offline_dwarf(struct debuginfo *dbg,
 	if (!dbg->dbg)
 		goto error;
 
+	dwfl_report_end(dbg->dwfl, NULL, NULL);
+
 	return 0;
 error:
 	if (dbg->dwfl)
@@ -591,6 +594,7 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
 /* Convert subprogram DIE to trace point */
 static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
 				  Dwarf_Addr paddr, bool retprobe,
+				  const char *function,
 				  struct probe_trace_point *tp)
 {
 	Dwarf_Addr eaddr, highaddr;
@@ -634,8 +638,10 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
 	/* Return probe must be on the head of a subprogram */
 	if (retprobe) {
 		if (eaddr != paddr) {
-			pr_warning("Return probe must be on the head of"
-				   " a real function.\n");
+			pr_warning("Failed to find \"%s%%return\",\n"
+				   " because %s is an inlined function and"
+				   " has no return point.\n", function,
+				   function);
 			return -EINVAL;
 		}
 		tp->retprobe = true;
@@ -1175,8 +1181,9 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf)
 {
 	struct trace_event_finder *tf =
 			container_of(pf, struct trace_event_finder, pf);
+	struct perf_probe_point *pp = &pf->pev->point;
 	struct probe_trace_event *tev;
-	struct perf_probe_arg *args;
+	struct perf_probe_arg *args = NULL;
 	int ret, i;
 
 	/* Check number of tevs */
@@ -1189,21 +1196,25 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf)
 
 	/* Trace point should be converted from subprogram DIE */
 	ret = convert_to_trace_point(&pf->sp_die, tf->mod, pf->addr,
-				     pf->pev->point.retprobe, &tev->point);
+				     pp->retprobe, pp->function, &tev->point);
 	if (ret < 0)
-		return ret;
+		goto end;
 
 	tev->point.realname = strdup(dwarf_diename(sc_die));
-	if (!tev->point.realname)
-		return -ENOMEM;
+	if (!tev->point.realname) {
+		ret = -ENOMEM;
+		goto end;
+	}
 
 	pr_debug("Probe point found: %s+%lu\n", tev->point.symbol,
 		 tev->point.offset);
 
 	/* Expand special probe argument if exist */
 	args = zalloc(sizeof(struct perf_probe_arg) * MAX_PROBE_ARGS);
-	if (args == NULL)
-		return -ENOMEM;
+	if (args == NULL) {
+		ret = -ENOMEM;
+		goto end;
+	}
 
 	ret = expand_probe_args(sc_die, pf, args);
 	if (ret < 0)
@@ -1227,6 +1238,10 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf)
 	}
 
 end:
+	if (ret) {
+		clear_probe_trace_event(tev);
+		tf->ntevs--;
+	}
 	free(args);
 	return ret;
 }
@@ -1239,7 +1254,7 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 	struct trace_event_finder tf = {
 			.pf = {.pev = pev, .callback = add_probe_trace_event},
 			.max_tevs = probe_conf.max_probes, .mod = dbg->mod};
-	int ret;
+	int ret, i;
 
 	/* Allocate result tevs array */
 	*tevs = zalloc(sizeof(struct probe_trace_event) * tf.max_tevs);
@@ -1251,6 +1266,8 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 
 	ret = debuginfo__find_probes(dbg, &tf.pf);
 	if (ret < 0) {
+		for (i = 0; i < tf.ntevs; i++)
+			clear_probe_trace_event(&tf.tevs[i]);
 		zfree(tevs);
 		return ret;
 	}
@@ -1319,6 +1336,7 @@ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf)
 {
 	struct available_var_finder *af =
 			container_of(pf, struct available_var_finder, pf);
+	struct perf_probe_point *pp = &pf->pev->point;
 	struct variable_list *vl;
 	Dwarf_Die die_mem;
 	int ret;
@@ -1332,7 +1350,7 @@ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf)
 
 	/* Trace point should be converted from subprogram DIE */
 	ret = convert_to_trace_point(&pf->sp_die, af->mod, pf->addr,
-				     pf->pev->point.retprobe, &vl->point);
+				     pp->retprobe, pp->function, &vl->point);
 	if (ret < 0)
 		return ret;
 
@@ -1399,6 +1417,41 @@ int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 	return (ret < 0) ? ret : af.nvls;
 }
 
+/* For the kernel module, we need a special code to get a DIE */
+static int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs)
+{
+	int n, i;
+	Elf32_Word shndx;
+	Elf_Scn *scn;
+	Elf *elf;
+	GElf_Shdr mem, *shdr;
+	const char *p;
+
+	elf = dwfl_module_getelf(dbg->mod, &dbg->bias);
+	if (!elf)
+		return -EINVAL;
+
+	/* Get the number of relocations */
+	n = dwfl_module_relocations(dbg->mod);
+	if (n < 0)
+		return -ENOENT;
+	/* Search the relocation related .text section */
+	for (i = 0; i < n; i++) {
+		p = dwfl_module_relocation_info(dbg->mod, i, &shndx);
+		if (strcmp(p, ".text") == 0) {
+			/* OK, get the section header */
+			scn = elf_getscn(elf, shndx);
+			if (!scn)
+				return -ENOENT;
+			shdr = gelf_getshdr(scn, &mem);
+			if (!shdr)
+				return -ENOENT;
+			*offs = shdr->sh_addr;
+		}
+	}
+	return 0;
+}
+
 /* Reverse search */
 int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
 				struct perf_probe_point *ppt)
@@ -1407,9 +1460,16 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
 	Dwarf_Addr _addr = 0, baseaddr = 0;
 	const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp;
 	int baseline = 0, lineno = 0, ret = 0;
+	bool reloc = false;
 
+retry:
 	/* Find cu die */
 	if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) {
+		if (!reloc && debuginfo__get_text_offset(dbg, &baseaddr) == 0) {
+			addr += baseaddr;
+			reloc = true;
+			goto retry;
+		}
 		pr_warning("Failed to find debug information for address %lx\n",
 			   addr);
 		ret = -EINVAL;
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 6324fe6b1..98f127abf 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -67,6 +67,7 @@ static char pyrf_mmap_event__doc[] = PyDoc_STR("perf mmap event object.");
 static PyMemberDef pyrf_mmap_event__members[] = {
 	sample_members
 	member_def(perf_event_header, type, T_UINT, "event type"),
+	member_def(perf_event_header, misc, T_UINT, "event misc"),
 	member_def(mmap_event, pid, T_UINT, "event pid"),
 	member_def(mmap_event, tid, T_UINT, "event tid"),
 	member_def(mmap_event, start, T_ULONGLONG, "start of the map"),
@@ -297,6 +298,43 @@ static PyTypeObject pyrf_sample_event__type = {
 	.tp_repr	= (reprfunc)pyrf_sample_event__repr,
 };
 
+static char pyrf_context_switch_event__doc[] = PyDoc_STR("perf context_switch event object.");
+
+static PyMemberDef pyrf_context_switch_event__members[] = {
+	sample_members
+	member_def(perf_event_header, type, T_UINT, "event type"),
+	member_def(context_switch_event, next_prev_pid, T_UINT, "next/prev pid"),
+	member_def(context_switch_event, next_prev_tid, T_UINT, "next/prev tid"),
+	{ .name = NULL, },
+};
+
+static PyObject *pyrf_context_switch_event__repr(struct pyrf_event *pevent)
+{
+	PyObject *ret;
+	char *s;
+
+	if (asprintf(&s, "{ type: context_switch, next_prev_pid: %u, next_prev_tid: %u, switch_out: %u }",
+		     pevent->event.context_switch.next_prev_pid,
+		     pevent->event.context_switch.next_prev_tid,
+		     !!(pevent->event.header.misc & PERF_RECORD_MISC_SWITCH_OUT)) < 0) {
+		ret = PyErr_NoMemory();
+	} else {
+		ret = PyString_FromString(s);
+		free(s);
+	}
+	return ret;
+}
+
+static PyTypeObject pyrf_context_switch_event__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.context_switch_event",
+	.tp_basicsize	= sizeof(struct pyrf_event),
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= pyrf_context_switch_event__doc,
+	.tp_members	= pyrf_context_switch_event__members,
+	.tp_repr	= (reprfunc)pyrf_context_switch_event__repr,
+};
+
 static int pyrf_event__setup_types(void)
 {
 	int err;
@@ -306,6 +344,7 @@ static int pyrf_event__setup_types(void)
 	pyrf_lost_event__type.tp_new =
 	pyrf_read_event__type.tp_new =
 	pyrf_sample_event__type.tp_new =
+	pyrf_context_switch_event__type.tp_new =
 	pyrf_throttle_event__type.tp_new = PyType_GenericNew;
 	err = PyType_Ready(&pyrf_mmap_event__type);
 	if (err < 0)
@@ -328,6 +367,9 @@ static int pyrf_event__setup_types(void)
 	err = PyType_Ready(&pyrf_sample_event__type);
 	if (err < 0)
 		goto out;
+	err = PyType_Ready(&pyrf_context_switch_event__type);
+	if (err < 0)
+		goto out;
 out:
 	return err;
 }
@@ -342,6 +384,8 @@ static PyTypeObject *pyrf_event__type[] = {
 	[PERF_RECORD_FORK]	 = &pyrf_task_event__type,
 	[PERF_RECORD_READ]	 = &pyrf_read_event__type,
 	[PERF_RECORD_SAMPLE]	 = &pyrf_sample_event__type,
+	[PERF_RECORD_SWITCH]	 = &pyrf_context_switch_event__type,
+	[PERF_RECORD_SWITCH_CPU_WIDE]  = &pyrf_context_switch_event__type,
 };
 
 static PyObject *pyrf_event__new(union perf_event *event)
@@ -349,8 +393,10 @@ static PyObject *pyrf_event__new(union perf_event *event)
 	struct pyrf_event *pevent;
 	PyTypeObject *ptype;
 
-	if (event->header.type < PERF_RECORD_MMAP ||
-	    event->header.type > PERF_RECORD_SAMPLE)
+	if ((event->header.type < PERF_RECORD_MMAP ||
+	     event->header.type > PERF_RECORD_SAMPLE) &&
+	    !(event->header.type == PERF_RECORD_SWITCH ||
+	      event->header.type == PERF_RECORD_SWITCH_CPU_WIDE))
 		return NULL;
 
 	ptype = pyrf_event__type[event->header.type];
@@ -528,6 +574,7 @@ static int pyrf_evsel__init(struct pyrf_evsel *pevsel,
 		"exclude_hv",
 		"exclude_idle",
 		"mmap",
+		"context_switch",
 		"comm",
 		"freq",
 		"inherit_stat",
@@ -553,6 +600,7 @@ static int pyrf_evsel__init(struct pyrf_evsel *pevsel,
 	    exclude_hv = 0,
 	    exclude_idle = 0,
 	    mmap = 0,
+	    context_switch = 0,
 	    comm = 0,
 	    freq = 1,
 	    inherit_stat = 0,
@@ -565,13 +613,13 @@ static int pyrf_evsel__init(struct pyrf_evsel *pevsel,
 	int idx = 0;
 
 	if (!PyArg_ParseTupleAndKeywords(args, kwargs,
-					 "|iKiKKiiiiiiiiiiiiiiiiiiiiiKK", kwlist,
+					 "|iKiKKiiiiiiiiiiiiiiiiiiiiiiKK", kwlist,
 					 &attr.type, &attr.config, &attr.sample_freq,
 					 &sample_period, &attr.sample_type,
 					 &attr.read_format, &disabled, &inherit,
 					 &pinned, &exclusive, &exclude_user,
 					 &exclude_kernel, &exclude_hv, &exclude_idle,
-					 &mmap, &comm, &freq, &inherit_stat,
+					 &mmap, &context_switch, &comm, &freq, &inherit_stat,
 					 &enable_on_exec, &task, &watermark,
 					 &precise_ip, &mmap_data, &sample_id_all,
 					 &attr.wakeup_events, &attr.bp_type,
@@ -595,6 +643,7 @@ static int pyrf_evsel__init(struct pyrf_evsel *pevsel,
 	attr.exclude_hv	    = exclude_hv;
 	attr.exclude_idle   = exclude_idle;
 	attr.mmap	    = mmap;
+	attr.context_switch = context_switch;
 	attr.comm	    = comm;
 	attr.freq	    = freq;
 	attr.inherit_stat   = inherit_stat;
@@ -1019,6 +1068,8 @@ static struct {
 	PERF_CONST(RECORD_LOST_SAMPLES),
 	PERF_CONST(RECORD_SWITCH),
 	PERF_CONST(RECORD_SWITCH_CPU_WIDE),
+
+	PERF_CONST(RECORD_MISC_SWITCH_OUT),
 	{ .name = NULL, },
 };
 
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 1bd593bbf..544509c15 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -221,6 +221,7 @@ static void define_event_symbols(struct event_format *event,
 		break;
 	case PRINT_BSTRING:
 	case PRINT_DYNAMIC_ARRAY:
+	case PRINT_DYNAMIC_ARRAY_LEN:
 	case PRINT_STRING:
 	case PRINT_BITMASK:
 		break;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index ace248498..a8e825fca 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -251,6 +251,7 @@ static void define_event_symbols(struct event_format *event,
 		/* gcc warns for these? */
 	case PRINT_BSTRING:
 	case PRINT_DYNAMIC_ARRAY:
+	case PRINT_DYNAMIC_ARRAY_LEN:
 	case PRINT_FUNC:
 	case PRINT_BITMASK:
 		/* we should warn... */
@@ -318,7 +319,7 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
 
 	if (thread__resolve_callchain(al->thread, evsel,
 				      sample, NULL, NULL,
-				      PERF_MAX_STACK_DEPTH) != 0) {
+				      scripting_max_stack) != 0) {
 		pr_err("Failed to resolve callchain. Skipping\n");
 		goto exit;
 	}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index fc3f7c922..c35ffdd36 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -29,7 +29,7 @@ static int perf_session__open(struct perf_session *session)
 	struct perf_data_file *file = session->file;
 
 	if (perf_session__read_header(session) < 0) {
-		pr_err("incompatible file format (rerun with -v to learn more)");
+		pr_err("incompatible file format (rerun with -v to learn more)\n");
 		return -1;
 	}
 
@@ -37,17 +37,17 @@ static int perf_session__open(struct perf_session *session)
 		return 0;
 
 	if (!perf_evlist__valid_sample_type(session->evlist)) {
-		pr_err("non matching sample_type");
+		pr_err("non matching sample_type\n");
 		return -1;
 	}
 
 	if (!perf_evlist__valid_sample_id_all(session->evlist)) {
-		pr_err("non matching sample_id_all");
+		pr_err("non matching sample_id_all\n");
 		return -1;
 	}
 
 	if (!perf_evlist__valid_read_format(session->evlist)) {
-		pr_err("non matching read_format");
+		pr_err("non matching read_format\n");
 		return -1;
 	}
 
@@ -138,6 +138,8 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 			perf_session__set_id_hdr_size(session);
 			perf_session__set_comm_exec(session);
 		}
+	} else  {
+		session->machines.host.env = &perf_env;
 	}
 
 	if (!file || perf_data_file__is_write(file)) {
@@ -170,30 +172,13 @@ static void perf_session__delete_threads(struct perf_session *session)
 	machine__delete_threads(&session->machines.host);
 }
 
-static void perf_session_env__exit(struct perf_env *env)
-{
-	zfree(&env->hostname);
-	zfree(&env->os_release);
-	zfree(&env->version);
-	zfree(&env->arch);
-	zfree(&env->cpu_desc);
-	zfree(&env->cpuid);
-
-	zfree(&env->cmdline);
-	zfree(&env->cmdline_argv);
-	zfree(&env->sibling_cores);
-	zfree(&env->sibling_threads);
-	zfree(&env->numa_nodes);
-	zfree(&env->pmu_mappings);
-}
-
 void perf_session__delete(struct perf_session *session)
 {
 	auxtrace__free(session);
 	auxtrace_index__free(&session->auxtrace_index);
 	perf_session__destroy_kernel_maps(session);
 	perf_session__delete_threads(session);
-	perf_session_env__exit(&session->header.env);
+	perf_env__exit(&session->header.env);
 	machines__exit(&session->machines);
 	if (session->file)
 		perf_data_file__close(session->file);
@@ -1079,11 +1064,11 @@ static int machines__deliver_event(struct machines *machines,
 
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:
-		dump_sample(evsel, event, sample);
 		if (evsel == NULL) {
 			++evlist->stats.nr_unknown_id;
 			return 0;
 		}
+		dump_sample(evsel, event, sample);
 		if (machine == NULL) {
 			++evlist->stats.nr_unprocessable_samples;
 			return 0;
@@ -1116,6 +1101,9 @@ static int machines__deliver_event(struct machines *machines,
 	case PERF_RECORD_UNTHROTTLE:
 		return tool->unthrottle(tool, event, sample, machine);
 	case PERF_RECORD_AUX:
+		if (tool->aux == perf_event__process_aux &&
+		    (event->aux.flags & PERF_AUX_FLAG_TRUNCATED))
+			evlist->stats.total_aux_lost += 1;
 		return tool->aux(tool, event, sample, machine);
 	case PERF_RECORD_ITRACE_START:
 		return tool->itrace_start(tool, event, sample, machine);
@@ -1323,7 +1311,7 @@ struct thread *perf_session__findnew(struct perf_session *session, pid_t pid)
 	return machine__findnew_thread(&session->machines.host, -1, pid);
 }
 
-static struct thread *perf_session__register_idle_thread(struct perf_session *session)
+struct thread *perf_session__register_idle_thread(struct perf_session *session)
 {
 	struct thread *thread;
 
@@ -1361,6 +1349,13 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
 		}
 	}
 
+	if (session->tool->aux == perf_event__process_aux &&
+	    stats->total_aux_lost != 0) {
+		ui__warning("AUX data lost %" PRIu64 " times out of %u!\n\n",
+			    stats->total_aux_lost,
+			    stats->nr_events[PERF_RECORD_AUX]);
+	}
+
 	if (stats->nr_unknown_events != 0) {
 		ui__warning("Found %u unknown events!\n\n"
 			    "Is this an older tool processing a perf.data "
@@ -1805,7 +1800,7 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
 
 		if (thread__resolve_callchain(al->thread, evsel,
 					      sample, NULL, NULL,
-					      PERF_MAX_STACK_DEPTH) != 0) {
+					      stack_depth) != 0) {
 			if (verbose)
 				error("Failed to resolve callchain. Skipping\n");
 			return;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index b44afc75d..3e900c0ef 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -89,6 +89,8 @@ struct machine *perf_session__findnew_machine(struct perf_session *session, pid_
 }
 
 struct thread *perf_session__findnew(struct perf_session *session, pid_t pid);
+struct thread *perf_session__register_idle_thread(struct perf_session *session);
+
 size_t perf_session__fprintf(struct perf_session *session, FILE *fp);
 
 size_t perf_session__fprintf_dsos(struct perf_session *session, FILE *fp);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 7e3871606..2d8ccd4d9 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -21,6 +21,7 @@ int		sort__need_collapse = 0;
 int		sort__has_parent = 0;
 int		sort__has_sym = 0;
 int		sort__has_dso = 0;
+int		sort__has_socket = 0;
 enum sort_mode	sort__mode = SORT_MODE__NORMAL;
 
 
@@ -328,8 +329,8 @@ static char *get_srcfile(struct hist_entry *e)
 	char *sf, *p;
 	struct map *map = e->ms.map;
 
-	sf = get_srcline(map->dso, map__rip_2objdump(map, e->ip),
-			 e->ms.sym, true);
+	sf = __get_srcline(map->dso, map__rip_2objdump(map, e->ip),
+			 e->ms.sym, false, true);
 	if (!strcmp(sf, SRCLINE_UNKNOWN))
 		return no_srcfile;
 	p = strchr(sf, ':');
@@ -421,6 +422,27 @@ struct sort_entry sort_cpu = {
 	.se_width_idx	= HISTC_CPU,
 };
 
+/* --sort socket */
+
+static int64_t
+sort__socket_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return right->socket - left->socket;
+}
+
+static int hist_entry__socket_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width)
+{
+	return repsep_snprintf(bf, size, "%*.*d", width, width-3, he->socket);
+}
+
+struct sort_entry sort_socket = {
+	.se_header      = "Socket",
+	.se_cmp	        = sort__socket_cmp,
+	.se_snprintf    = hist_entry__socket_snprintf,
+	.se_width_idx	= HISTC_SOCKET,
+};
+
 /* sort keys for branch stacks */
 
 static int64_t
@@ -633,6 +655,35 @@ static int hist_entry__daddr_snprintf(struct hist_entry *he, char *bf,
 }
 
 static int64_t
+sort__iaddr_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	uint64_t l = 0, r = 0;
+
+	if (left->mem_info)
+		l = left->mem_info->iaddr.addr;
+	if (right->mem_info)
+		r = right->mem_info->iaddr.addr;
+
+	return (int64_t)(r - l);
+}
+
+static int hist_entry__iaddr_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width)
+{
+	uint64_t addr = 0;
+	struct map *map = NULL;
+	struct symbol *sym = NULL;
+
+	if (he->mem_info) {
+		addr = he->mem_info->iaddr.addr;
+		map  = he->mem_info->iaddr.map;
+		sym  = he->mem_info->iaddr.sym;
+	}
+	return _hist_entry__sym_snprintf(map, sym, addr, he->level, bf, size,
+					 width);
+}
+
+static int64_t
 sort__dso_daddr_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	struct map *map_l = NULL;
@@ -1055,6 +1106,13 @@ struct sort_entry sort_mem_daddr_sym = {
 	.se_width_idx	= HISTC_MEM_DADDR_SYMBOL,
 };
 
+struct sort_entry sort_mem_iaddr_sym = {
+	.se_header	= "Code Symbol",
+	.se_cmp		= sort__iaddr_cmp,
+	.se_snprintf	= hist_entry__iaddr_snprintf,
+	.se_width_idx	= HISTC_MEM_IADDR_SYMBOL,
+};
+
 struct sort_entry sort_mem_daddr_dso = {
 	.se_header	= "Data Object",
 	.se_cmp		= sort__dso_daddr_cmp,
@@ -1248,6 +1306,7 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_SYM, "symbol", sort_sym),
 	DIM(SORT_PARENT, "parent", sort_parent),
 	DIM(SORT_CPU, "cpu", sort_cpu),
+	DIM(SORT_SOCKET, "socket", sort_socket),
 	DIM(SORT_SRCLINE, "srcline", sort_srcline),
 	DIM(SORT_SRCFILE, "srcfile", sort_srcfile),
 	DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
@@ -1276,6 +1335,7 @@ static struct sort_dimension bstack_sort_dimensions[] = {
 
 static struct sort_dimension memory_sort_dimensions[] = {
 	DIM(SORT_MEM_DADDR_SYMBOL, "symbol_daddr", sort_mem_daddr_sym),
+	DIM(SORT_MEM_IADDR_SYMBOL, "symbol_iaddr", sort_mem_iaddr_sym),
 	DIM(SORT_MEM_DADDR_DSO, "dso_daddr", sort_mem_daddr_dso),
 	DIM(SORT_MEM_LOCKED, "locked", sort_mem_locked),
 	DIM(SORT_MEM_TLB, "tlb", sort_mem_tlb),
@@ -1517,6 +1577,12 @@ static int __hpp_dimension__add_output(struct hpp_dimension *hd)
 	return 0;
 }
 
+int hpp_dimension__add_output(unsigned col)
+{
+	BUG_ON(col >= PERF_HPP__MAX_INDEX);
+	return __hpp_dimension__add_output(&hpp_sort_dimensions[col]);
+}
+
 int sort_dimension__add(const char *tok)
 {
 	unsigned int i;
@@ -1550,6 +1616,8 @@ int sort_dimension__add(const char *tok)
 
 		} else if (sd->entry == &sort_dso) {
 			sort__has_dso = 1;
+		} else if (sd->entry == &sort_socket) {
+			sort__has_socket = 1;
 		}
 
 		return __sort_dimension__add(sd);
@@ -1855,8 +1923,6 @@ static int __setup_output_field(void)
 	if (field_order == NULL)
 		return 0;
 
-	reset_dimensions();
-
 	strp = str = strdup(field_order);
 	if (str == NULL) {
 		error("Not enough memory to setup output fields");
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 3c2a399f8..31228851e 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -34,6 +34,7 @@ extern int have_ignore_callees;
 extern int sort__need_collapse;
 extern int sort__has_parent;
 extern int sort__has_sym;
+extern int sort__has_socket;
 extern enum sort_mode sort__mode;
 extern struct sort_entry sort_comm;
 extern struct sort_entry sort_dso;
@@ -90,6 +91,7 @@ struct hist_entry {
 	struct comm		*comm;
 	u64			ip;
 	u64			transaction;
+	s32			socket;
 	s32			cpu;
 	u8			cpumode;
 
@@ -172,6 +174,7 @@ enum sort_type {
 	SORT_SYM,
 	SORT_PARENT,
 	SORT_CPU,
+	SORT_SOCKET,
 	SORT_SRCLINE,
 	SORT_SRCFILE,
 	SORT_LOCAL_WEIGHT,
@@ -198,6 +201,7 @@ enum sort_type {
 	SORT_MEM_LVL,
 	SORT_MEM_SNOOP,
 	SORT_MEM_DCACHELINE,
+	SORT_MEM_IADDR_SYMBOL,
 };
 
 /*
@@ -230,4 +234,6 @@ void perf_hpp__set_elide(int idx, bool elide);
 int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset);
 
 bool is_strict_order(const char *order);
+
+int hpp_dimension__add_output(unsigned col);
 #endif	/* __PERF_SORT_H */
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index fc08248f0..b4db3f48e 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -149,8 +149,11 @@ static void addr2line_cleanup(struct a2l_data *a2l)
 	free(a2l);
 }
 
+#define MAX_INLINE_NEST 1024
+
 static int addr2line(const char *dso_name, u64 addr,
-		     char **file, unsigned int *line, struct dso *dso)
+		     char **file, unsigned int *line, struct dso *dso,
+		     bool unwind_inlines)
 {
 	int ret = 0;
 	struct a2l_data *a2l = dso->a2l;
@@ -170,6 +173,15 @@ static int addr2line(const char *dso_name, u64 addr,
 
 	bfd_map_over_sections(a2l->abfd, find_address_in_section, a2l);
 
+	if (a2l->found && unwind_inlines) {
+		int cnt = 0;
+
+		while (bfd_find_inliner_info(a2l->abfd, &a2l->filename,
+					     &a2l->funcname, &a2l->line) &&
+		       cnt++ < MAX_INLINE_NEST)
+			;
+	}
+
 	if (a2l->found && a2l->filename) {
 		*file = strdup(a2l->filename);
 		*line = a2l->line;
@@ -197,7 +209,8 @@ void dso__free_a2l(struct dso *dso)
 
 static int addr2line(const char *dso_name, u64 addr,
 		     char **file, unsigned int *line_nr,
-		     struct dso *dso __maybe_unused)
+		     struct dso *dso __maybe_unused,
+		     bool unwind_inlines __maybe_unused)
 {
 	FILE *fp;
 	char cmd[PATH_MAX];
@@ -254,8 +267,8 @@ void dso__free_a2l(struct dso *dso __maybe_unused)
  */
 #define A2L_FAIL_LIMIT 123
 
-char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
-		  bool show_sym)
+char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
+		  bool show_sym, bool unwind_inlines)
 {
 	char *file = NULL;
 	unsigned line = 0;
@@ -276,7 +289,7 @@ char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 	if (!strncmp(dso_name, "/tmp/perf-", 10))
 		goto out;
 
-	if (!addr2line(dso_name, addr, &file, &line, dso))
+	if (!addr2line(dso_name, addr, &file, &line, dso, unwind_inlines))
 		goto out;
 
 	if (asprintf(&srcline, "%s:%u",
@@ -310,3 +323,9 @@ void free_srcline(char *srcline)
 	if (srcline && strcmp(srcline, SRCLINE_UNKNOWN) != 0)
 		free(srcline);
 }
+
+char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
+		  bool show_sym)
+{
+	return __get_srcline(dso, addr, sym, show_sym, false);
+}
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 2a5d8d769..6ac031468 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -413,6 +413,11 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 			ratio = total / avg;
 
 		fprintf(out, " # %8.0f cycles / elision       ", ratio);
+	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) {
+		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
+			fprintf(out, " # %8.3f CPUs utilized          ", avg / ratio);
+		else
+			fprintf(out, "                                   ");
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
 
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 2d065d065..2d9d8306d 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -67,7 +67,7 @@ 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 *ps = evsel->priv;
+	struct perf_stat_evsel *ps = evsel->priv;
 
 	return ps->id == id;
 }
@@ -84,7 +84,7 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = {
 
 void perf_stat_evsel_id_init(struct perf_evsel *evsel)
 {
-	struct perf_stat *ps = evsel->priv;
+	struct perf_stat_evsel *ps = evsel->priv;
 	int i;
 
 	/* ps->id is 0 hence PERF_STAT_EVSEL_ID__NONE by default */
@@ -100,7 +100,7 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel)
 void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 {
 	int i;
-	struct perf_stat *ps = evsel->priv;
+	struct perf_stat_evsel *ps = evsel->priv;
 
 	for (i = 0; i < 3; i++)
 		init_stats(&ps->res_stats[i]);
@@ -110,7 +110,7 @@ void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 
 int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 {
-	evsel->priv = zalloc(sizeof(struct perf_stat));
+	evsel->priv = zalloc(sizeof(struct perf_stat_evsel));
 	if (evsel->priv == NULL)
 		return -ENOMEM;
 	perf_evsel__reset_stat_priv(evsel);
@@ -230,7 +230,7 @@ static int check_per_pkg(struct perf_evsel *counter,
 	if (!(vals->run && vals->ena))
 		return 0;
 
-	s = cpu_map__get_socket(cpus, cpu);
+	s = cpu_map__get_socket(cpus, cpu, NULL);
 	if (s < 0)
 		return -1;
 
@@ -272,6 +272,7 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel
 			aggr->ena += count->ena;
 			aggr->run += count->run;
 		}
+	case AGGR_UNSET:
 	default:
 		break;
 	}
@@ -304,7 +305,7 @@ 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 *ps = counter->priv;
+	struct perf_stat_evsel *ps = counter->priv;
 	u64 *count = counter->counts->aggr.values;
 	int i, ret;
 
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 62448c817..da1d11c4f 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -20,7 +20,7 @@ enum perf_stat_evsel_id {
 	PERF_STAT_EVSEL_ID__MAX,
 };
 
-struct perf_stat {
+struct perf_stat_evsel {
 	struct stats		res_stats[3];
 	enum perf_stat_evsel_id	id;
 };
@@ -31,6 +31,7 @@ enum aggr_mode {
 	AGGR_SOCKET,
 	AGGR_CORE,
 	AGGR_THREAD,
+	AGGR_UNSET,
 };
 
 struct perf_stat_config {
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 4abe23550..25671fa16 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -82,23 +82,22 @@ void strbuf_add(struct strbuf *sb, const void *data, size_t len)
 	strbuf_setlen(sb, sb->len + len);
 }
 
-void strbuf_addf(struct strbuf *sb, const char *fmt, ...)
+void strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap)
 {
 	int len;
-	va_list ap;
+	va_list ap_saved;
 
 	if (!strbuf_avail(sb))
 		strbuf_grow(sb, 64);
-	va_start(ap, fmt);
+
+	va_copy(ap_saved, ap);
 	len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap);
-	va_end(ap);
 	if (len < 0)
 		die("your vsnprintf is broken");
 	if (len > strbuf_avail(sb)) {
 		strbuf_grow(sb, len);
-		va_start(ap, fmt);
-		len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap);
-		va_end(ap);
+		len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap_saved);
+		va_end(ap_saved);
 		if (len > strbuf_avail(sb)) {
 			die("this should not happen, your vsnprintf is broken");
 		}
@@ -106,6 +105,15 @@ void strbuf_addf(struct strbuf *sb, const char *fmt, ...)
 	strbuf_setlen(sb, sb->len + len);
 }
 
+void strbuf_addf(struct strbuf *sb, const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	strbuf_addv(sb, fmt, ap);
+	va_end(ap);
+}
+
 ssize_t strbuf_read(struct strbuf *sb, int fd, ssize_t hint)
 {
 	size_t oldlen = sb->len;
diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h
index 436ac319f..529f2f035 100644
--- a/tools/perf/util/strbuf.h
+++ b/tools/perf/util/strbuf.h
@@ -39,6 +39,7 @@
  */
 
 #include <assert.h>
+#include <stdarg.h>
 
 extern char strbuf_slopbuf[];
 struct strbuf {
@@ -85,6 +86,7 @@ static inline void strbuf_addstr(struct strbuf *sb, const char *s) {
 
 __attribute__((format(printf,2,3)))
 extern void strbuf_addf(struct strbuf *sb, const char *fmt, ...);
+extern void strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap);
 
 /* XXX: if read fails, any partial read is undone */
 extern ssize_t strbuf_read(struct strbuf *, int fd, ssize_t hint);
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index fd8477cac..48906333a 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -337,7 +337,7 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
 		  symbol_filter_t filter __maybe_unused,
 		  int kmodule __maybe_unused)
 {
-	unsigned char *build_id[BUILD_ID_SIZE];
+	unsigned char build_id[BUILD_ID_SIZE];
 	int ret;
 
 	ret = fd__is_64_bit(ss->fd);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 1f97ffb15..cd08027a6 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -624,7 +624,7 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
 	 * symbols, setting length to 0, and rely on
 	 * symbols__fixup_end() to fix it up.
 	 */
-	sym = symbol__new(start, 0, kallsyms2elf_type(type), name);
+	sym = symbol__new(start, 0, kallsyms2elf_binding(type), name);
 	if (sym == NULL)
 		return -ENOMEM;
 	/*
@@ -654,19 +654,24 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map,
 	struct map_groups *kmaps = map__kmaps(map);
 	struct map *curr_map;
 	struct symbol *pos;
-	int count = 0, moved = 0;
+	int count = 0;
+	struct rb_root old_root = dso->symbols[map->type];
 	struct rb_root *root = &dso->symbols[map->type];
 	struct rb_node *next = rb_first(root);
 
 	if (!kmaps)
 		return -1;
 
+	*root = RB_ROOT;
+
 	while (next) {
 		char *module;
 
 		pos = rb_entry(next, struct symbol, rb_node);
 		next = rb_next(&pos->rb_node);
 
+		rb_erase_init(&pos->rb_node, &old_root);
+
 		module = strchr(pos->name, '\t');
 		if (module)
 			*module = '\0';
@@ -674,28 +679,21 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map,
 		curr_map = map_groups__find(kmaps, map->type, pos->start);
 
 		if (!curr_map || (filter && filter(curr_map, pos))) {
-			rb_erase_init(&pos->rb_node, root);
 			symbol__delete(pos);
-		} else {
-			pos->start -= curr_map->start - curr_map->pgoff;
-			if (pos->end)
-				pos->end -= curr_map->start - curr_map->pgoff;
-			if (curr_map != map) {
-				rb_erase_init(&pos->rb_node, root);
-				symbols__insert(
-					&curr_map->dso->symbols[curr_map->type],
-					pos);
-				++moved;
-			} else {
-				++count;
-			}
+			continue;
 		}
+
+		pos->start -= curr_map->start - curr_map->pgoff;
+		if (pos->end)
+			pos->end -= curr_map->start - curr_map->pgoff;
+		symbols__insert(&curr_map->dso->symbols[curr_map->type], pos);
+		++count;
 	}
 
 	/* Symbols have been adjusted */
 	dso->adjust_symbols = 1;
 
-	return count + moved;
+	return count;
 }
 
 /*
@@ -1406,6 +1404,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	struct symsrc ss_[2];
 	struct symsrc *syms_ss = NULL, *runtime_ss = NULL;
 	bool kmod;
+	unsigned char build_id[BUILD_ID_SIZE];
 
 	pthread_mutex_lock(&dso->lock);
 
@@ -1437,9 +1436,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 		if (lstat(dso->name, &st) < 0)
 			goto out;
 
-		if (st.st_uid && (st.st_uid != geteuid())) {
+		if (!symbol_conf.force && st.st_uid && (st.st_uid != geteuid())) {
 			pr_warning("File %s not owned by current user or root, "
-				"ignoring it.\n", dso->name);
+				   "ignoring it (use -f to override).\n", dso->name);
 			goto out;
 		}
 
@@ -1461,6 +1460,14 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE ||
 		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
 
+
+	/*
+	 * Read the build id if possible. This is required for
+	 * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
+	 */
+	if (filename__read_build_id(dso->name, build_id, BUILD_ID_SIZE) > 0)
+		dso__set_build_id(dso, build_id);
+
 	/*
 	 * Iterate over candidate debug images.
 	 * Keep track of "interesting" ones (those which have a symtab, dynsym,
@@ -1607,6 +1614,15 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 	int i, err = 0;
 	char *filename = NULL;
 
+	pr_debug("Looking at the vmlinux_path (%d entries long)\n",
+		 vmlinux_path__nr_entries + 1);
+
+	for (i = 0; i < vmlinux_path__nr_entries; ++i) {
+		err = dso__load_vmlinux(dso, map, vmlinux_path[i], false, filter);
+		if (err > 0)
+			goto out;
+	}
+
 	if (!symbol_conf.ignore_vmlinux_buildid)
 		filename = dso__build_id_filename(dso, NULL, 0);
 	if (filename != NULL) {
@@ -1615,15 +1631,6 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 			goto out;
 		free(filename);
 	}
-
-	pr_debug("Looking at the vmlinux_path (%d entries long)\n",
-		 vmlinux_path__nr_entries + 1);
-
-	for (i = 0; i < vmlinux_path__nr_entries; ++i) {
-		err = dso__load_vmlinux(dso, map, vmlinux_path[i], false, filter);
-		if (err > 0)
-			break;
-	}
 out:
 	return err;
 }
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 440ba8ae8..dcd786e36 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -84,6 +84,7 @@ struct symbol_conf {
 	unsigned short	priv_size;
 	unsigned short	nr_events;
 	bool		try_vmlinux_path,
+			force,
 			ignore_vmlinux,
 			ignore_vmlinux_buildid,
 			show_kernel_path,
@@ -191,6 +192,7 @@ struct addr_location {
 	u8	      filtered;
 	u8	      cpumode;
 	s32	      cpu;
+	s32	      socket;
 };
 
 struct symsrc {
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 22245986e..d995743cb 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -38,7 +38,7 @@
 
 #include "../perf.h"
 #include "trace-event.h"
-#include <api/fs/debugfs.h>
+#include <api/fs/tracing_path.h>
 #include "evsel.h"
 #include "debug.h"
 
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index b90e646c7..802bb868d 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -7,7 +7,9 @@
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <linux/kernel.h>
+#include <linux/err.h>
 #include <traceevent/event-parse.h>
+#include <api/fs/tracing_path.h>
 #include "trace-event.h"
 #include "machine.h"
 #include "util.h"
@@ -65,6 +67,9 @@ void trace_event__cleanup(struct trace_event *t)
 	pevent_free(t->pevent);
 }
 
+/*
+ * Returns pointer with encoded error via <linux/err.h> interface.
+ */
 static struct event_format*
 tp_format(const char *sys, const char *name)
 {
@@ -73,12 +78,14 @@ tp_format(const char *sys, const char *name)
 	char path[PATH_MAX];
 	size_t size;
 	char *data;
+	int err;
 
 	scnprintf(path, PATH_MAX, "%s/%s/%s/format",
 		  tracing_events_path, sys, name);
 
-	if (filename__read_str(path, &data, &size))
-		return NULL;
+	err = filename__read_str(path, &data, &size);
+	if (err)
+		return ERR_PTR(err);
 
 	pevent_parse_format(pevent, &event, data, size, sys);
 
@@ -86,11 +93,14 @@ tp_format(const char *sys, const char *name)
 	return event;
 }
 
+/*
+ * Returns pointer with encoded error via <linux/err.h> interface.
+ */
 struct event_format*
 trace_event__tp_format(const char *sys, const char *name)
 {
 	if (!tevent_initialized && trace_event__init2())
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	return tp_format(sys, name);
 }
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index da6cc4cc2..b85ee55cc 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -78,6 +78,8 @@ struct scripting_ops {
 	int (*generate_script) (struct pevent *pevent, const char *outfile);
 };
 
+extern unsigned int scripting_max_stack;
+
 int script_spec_register(const char *spec, struct scripting_ops *ops);
 
 void setup_perl_scripting(void);
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 4c00507ee..c83832b55 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -330,6 +330,7 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
 	struct map *map;
 	unw_dyn_info_t di;
 	u64 table_data, segbase, fde_count;
+	int ret = -EINVAL;
 
 	map = find_map(ip, ui);
 	if (!map || !map->dso)
@@ -348,29 +349,33 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
 		di.u.rti.table_data = map->start + table_data;
 		di.u.rti.table_len  = fde_count * sizeof(struct table_entry)
 				      / sizeof(unw_word_t);
-		return dwarf_search_unwind_table(as, ip, &di, pi,
-						 need_unwind_info, arg);
+		ret = dwarf_search_unwind_table(as, ip, &di, pi,
+						need_unwind_info, arg);
 	}
 
 #ifndef NO_LIBUNWIND_DEBUG_FRAME
 	/* Check the .debug_frame section for unwinding info */
-	if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
+	if (ret < 0 &&
+	    !read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
 		int fd = dso__data_get_fd(map->dso, ui->machine);
 		int is_exec = elf_is_exec(fd, map->dso->name);
 		unw_word_t base = is_exec ? 0 : map->start;
+		const char *symfile;
 
 		if (fd >= 0)
 			dso__data_put_fd(map->dso);
 
+		symfile = map->dso->symsrc_filename ?: map->dso->name;
+
 		memset(&di, 0, sizeof(di));
-		if (dwarf_find_debug_frame(0, &di, ip, base, map->dso->name,
+		if (dwarf_find_debug_frame(0, &di, ip, base, symfile,
 					   map->start, map->end))
 			return dwarf_search_unwind_table(as, ip, &di, pi,
 							 need_unwind_info, arg);
 	}
 #endif
 
-	return -EINVAL;
+	return ret;
 }
 
 static int access_fpreg(unw_addr_space_t __maybe_unused as,
@@ -461,7 +466,7 @@ static int access_mem(unw_addr_space_t __maybe_unused as,
 		if (ret) {
 			pr_debug("unwind: access_mem %p not inside range"
 				 " 0x%" PRIx64 "-0x%" PRIx64 "\n",
-				 (void *) addr, start, end);
+				 (void *) (uintptr_t) addr, start, end);
 			*valp = 0;
 			return ret;
 		}
@@ -471,7 +476,7 @@ static int access_mem(unw_addr_space_t __maybe_unused as,
 	offset = addr - start;
 	*valp  = *(unw_word_t *)&stack->data[offset];
 	pr_debug("unwind: access_mem addr %p val %lx, offset %d\n",
-		 (void *) addr, (unsigned long)*valp, offset);
+		 (void *) (uintptr_t) addr, (unsigned long)*valp, offset);
 	return 0;
 }
 
diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c
index 4007aca8e..6adfa18cd 100644
--- a/tools/perf/util/usage.c
+++ b/tools/perf/util/usage.c
@@ -50,6 +50,11 @@ void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN)
 	die_routine = routine;
 }
 
+void set_warning_routine(void (*routine)(const char *err, va_list params))
+{
+	warn_routine = routine;
+}
+
 void usage(const char *err)
 {
 	usage_routine(err);
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index c2cd9bf23..47b1e36c7 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -3,6 +3,7 @@
 #include "debug.h"
 #include <api/fs/fs.h>
 #include <sys/mman.h>
+#include <sys/utsname.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
 #include <execinfo.h>
 #endif
@@ -17,7 +18,7 @@
 #include "callchain.h"
 
 struct callchain_param	callchain_param = {
-	.mode	= CHAIN_GRAPH_REL,
+	.mode	= CHAIN_GRAPH_ABS,
 	.min_percent = 0.5,
 	.order  = ORDER_CALLEE,
 	.key	= CCKEY_FUNCTION
@@ -34,9 +35,6 @@ bool test_attr__enabled;
 bool perf_host  = true;
 bool perf_guest = false;
 
-char tracing_path[PATH_MAX + 1]        = "/sys/kernel/debug/tracing";
-char tracing_events_path[PATH_MAX + 1] = "/sys/kernel/debug/tracing/events";
-
 void event_attr_init(struct perf_event_attr *attr)
 {
 	if (!perf_host)
@@ -390,73 +388,6 @@ void set_term_quiet_input(struct termios *old)
 	tcsetattr(0, TCSANOW, &tc);
 }
 
-static void set_tracing_events_path(const char *tracing, const char *mountpoint)
-{
-	snprintf(tracing_path, sizeof(tracing_path), "%s/%s",
-		 mountpoint, tracing);
-	snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s%s",
-		 mountpoint, tracing, "events");
-}
-
-static const char *__perf_tracefs_mount(const char *mountpoint)
-{
-	const char *mnt;
-
-	mnt = tracefs_mount(mountpoint);
-	if (!mnt)
-		return NULL;
-
-	set_tracing_events_path("", mnt);
-
-	return mnt;
-}
-
-static const char *__perf_debugfs_mount(const char *mountpoint)
-{
-	const char *mnt;
-
-	mnt = debugfs_mount(mountpoint);
-	if (!mnt)
-		return NULL;
-
-	set_tracing_events_path("tracing/", mnt);
-
-	return mnt;
-}
-
-const char *perf_debugfs_mount(const char *mountpoint)
-{
-	const char *mnt;
-
-	mnt = __perf_tracefs_mount(mountpoint);
-	if (mnt)
-		return mnt;
-
-	mnt = __perf_debugfs_mount(mountpoint);
-
-	return mnt;
-}
-
-void perf_debugfs_set_path(const char *mntpt)
-{
-	set_tracing_events_path("tracing/", mntpt);
-}
-
-char *get_tracing_file(const char *name)
-{
-	char *file;
-
-	if (asprintf(&file, "%s/%s", tracing_path, name) < 0)
-		return NULL;
-
-	return file;
-}
-
-void put_tracing_file(char *file)
-{
-	free(file);
-}
-
 int parse_nsec_time(const char *str, u64 *ptime)
 {
 	u64 time_sec, time_nsec;
@@ -735,3 +666,32 @@ bool find_process(const char *name)
 	closedir(dir);
 	return ret ? false : true;
 }
+
+int
+fetch_kernel_version(unsigned int *puint, char *str,
+		     size_t str_size)
+{
+	struct utsname utsname;
+	int version, patchlevel, sublevel, err;
+
+	if (uname(&utsname))
+		return -1;
+
+	if (str && str_size) {
+		strncpy(str, utsname.release, str_size);
+		str[str_size - 1] = '\0';
+	}
+
+	err = sscanf(utsname.release, "%d.%d.%d",
+		     &version, &patchlevel, &sublevel);
+
+	if (err != 3) {
+		pr_debug("Unablt to get kernel version from uname '%s'\n",
+			 utsname.release);
+		return -1;
+	}
+
+	if (puint)
+		*puint = (version << 16) + (patchlevel << 8) + sublevel;
+	return 0;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 291be1d84..dcc659017 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -74,8 +74,7 @@
 #include <linux/magic.h>
 #include <linux/types.h>
 #include <sys/ttydefaults.h>
-#include <api/fs/debugfs.h>
-#include <api/fs/tracefs.h>
+#include <api/fs/tracing_path.h>
 #include <termios.h>
 #include <linux/bitops.h>
 #include <termios.h>
@@ -83,12 +82,6 @@
 extern const char *graph_line;
 extern const char *graph_dotted_line;
 extern char buildid_dir[];
-extern char tracing_path[];
-extern char tracing_events_path[];
-extern void perf_debugfs_set_path(const char *mountpoint);
-const char *perf_debugfs_mount(const char *mountpoint);
-char *get_tracing_file(const char *name);
-void put_tracing_file(char *file);
 
 /* On most systems <limits.h> would have given us this, but
  * not on some systems (e.g. GNU/Hurd).
@@ -152,6 +145,7 @@ extern void warning(const char *err, ...) __attribute__((format (printf, 1, 2)))
 
 
 extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN);
+extern void set_warning_routine(void (*routine)(const char *err, va_list params));
 
 extern int prefixcmp(const char *str, const char *prefix);
 extern void set_buildid_dir(const char *dir);
@@ -321,6 +315,8 @@ struct symbol;
 extern bool srcline_full_filename;
 char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 		  bool show_sym);
+char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
+		  bool show_sym, bool unwind_inlines);
 void free_srcline(char *srcline);
 
 int filename__read_str(const char *filename, char **buf, size_t *sizep);
@@ -354,4 +350,12 @@ static inline char *asprintf_expr_not_in_ints(const char *var, size_t nints, int
 
 int get_stack_size(const char *str, unsigned long *_size);
 
+int fetch_kernel_version(unsigned int *puint,
+			 char *str, size_t str_sz);
+#define KVER_VERSION(x)		(((x) >> 16) & 0xff)
+#define KVER_PATCHLEVEL(x)	(((x) >> 8) & 0xff)
+#define KVER_SUBLEVEL(x)	((x) & 0xff)
+#define KVER_FMT	"%d.%d.%d"
+#define KVER_PARAM(x)	KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x)
+
 #endif /* GIT_COMPAT_UTIL_H */