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

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

User visible changes:

  o Support S/390 in 'perf kvm stat' (Alexander Yarygin)

Developer Stuff:

  o Various fixes and prep work related to supporting Intel PT (Adrian Hunter)

  o Introduce multiple debug variables control (Jiri Olsa)

  o Add callchain and additional sample information for python scripts (Joseph Schuchart)

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

37 files changed, 620 insertions, 101 deletions

diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 48b6d3f50012..437ee09727e6 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -626,7 +626,7 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
 
 int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample)
 {
-	if (!symbol_conf.use_callchain)
+	if (!symbol_conf.use_callchain || sample->callchain == NULL)
 		return 0;
 	return callchain_append(he->callchain, &callchain_cursor, sample->period);
 }
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index ee370a7f2444..29d720cf5844 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -7,6 +7,7 @@
 
 #include "data.h"
 #include "util.h"
+#include "debug.h"
 
 static bool check_pipe(struct perf_data_file *file)
 {
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 299b55586502..71d419362634 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -16,11 +16,11 @@
 int verbose;
 bool dump_trace = false, quiet = false;
 
-static int _eprintf(int level, const char *fmt, va_list args)
+static int _eprintf(int level, int var, const char *fmt, va_list args)
 {
 	int ret = 0;
 
-	if (verbose >= level) {
+	if (var >= level) {
 		if (use_browser >= 1)
 			ui_helpline__vshow(fmt, args);
 		else
@@ -30,13 +30,13 @@ static int _eprintf(int level, const char *fmt, va_list args)
 	return ret;
 }
 
-int eprintf(int level, const char *fmt, ...)
+int eprintf(int level, int var, const char *fmt, ...)
 {
 	va_list args;
 	int ret;
 
 	va_start(args, fmt);
-	ret = _eprintf(level, fmt, args);
+	ret = _eprintf(level, var, fmt, args);
 	va_end(args);
 
 	return ret;
@@ -51,9 +51,9 @@ void pr_stat(const char *fmt, ...)
 	va_list args;
 
 	va_start(args, fmt);
-	_eprintf(1, fmt, args);
+	_eprintf(1, verbose, fmt, args);
 	va_end(args);
-	eprintf(1, "\n");
+	eprintf(1, verbose, "\n");
 }
 
 int dump_printf(const char *fmt, ...)
@@ -105,3 +105,47 @@ void trace_event(union perf_event *event)
 	}
 	printf(".\n");
 }
+
+static struct debug_variable {
+	const char *name;
+	int *ptr;
+} debug_variables[] = {
+	{ .name = "verbose", .ptr = &verbose },
+	{ .name = NULL, }
+};
+
+int perf_debug_option(const char *str)
+{
+	struct debug_variable *var = &debug_variables[0];
+	char *vstr, *s = strdup(str);
+	int v = 1;
+
+	vstr = strchr(s, '=');
+	if (vstr)
+		*vstr++ = 0;
+
+	while (var->name) {
+		if (!strcmp(s, var->name))
+			break;
+		var++;
+	}
+
+	if (!var->name) {
+		pr_err("Unknown debug variable name '%s'\n", s);
+		free(s);
+		return -1;
+	}
+
+	if (vstr) {
+		v = atoi(vstr);
+		/*
+		 * Allow only values in range (0, 10),
+		 * otherwise set 0.
+		 */
+		v = (v < 0) || (v > 10) ? 0 : v;
+	}
+
+	*var->ptr = v;
+	free(s);
+	return 0;
+}
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 443694c36b03..89fb6b0f7ab2 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -11,6 +11,24 @@
 extern int verbose;
 extern bool quiet, dump_trace;
 
+#ifndef pr_fmt
+#define pr_fmt(fmt) fmt
+#endif
+
+#define pr_err(fmt, ...) \
+	eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_warning(fmt, ...) \
+	eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_info(fmt, ...) \
+	eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug(fmt, ...) \
+	eprintf(1, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debugN(n, fmt, ...) \
+	eprintf(n, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__)
+
 int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
 void trace_event(union perf_event *event);
 
@@ -19,4 +37,8 @@ int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
 
 void pr_stat(const char *fmt, ...);
 
+int eprintf(int level, int var, const char *fmt, ...) __attribute__((format(printf, 3, 4)));
+
+int perf_debug_option(const char *str);
+
 #endif	/* __PERF_DEBUG_H */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 819f10414f08..fc006fed8877 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -703,6 +703,7 @@ struct dso *dso__new(const char *name)
 		dso->data.fd = -1;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND;
+		dso->is_64_bit = (sizeof(void *) == 8);
 		dso->loaded = 0;
 		dso->rel = 0;
 		dso->sorted_by_name = 0;
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index ad553ba257bf..c239e86541a3 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -90,6 +90,7 @@ struct dso {
 	u8		 annotate_warned:1;
 	u8		 short_name_allocated:1;
 	u8		 long_name_allocated:1;
+	u8		 is_64_bit:1;
 	u8		 sorted_by_name;
 	u8		 loaded;
 	u8		 rel;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index d0281bdfa582..7e0e8ae568ec 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -603,7 +603,14 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 
 size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
 {
-	return fprintf(fp, ": %s:%d\n", event->comm.comm, event->comm.tid);
+	const char *s;
+
+	if (event->header.misc & PERF_RECORD_MISC_COMM_EXEC)
+		s = " exec";
+	else
+		s = "";
+
+	return fprintf(fp, "%s: %s:%d\n", s, event->comm.comm, event->comm.tid);
 }
 
 int perf_event__process_comm(struct perf_tool *tool __maybe_unused,
@@ -781,6 +788,7 @@ try_again:
 		    cpumode == PERF_RECORD_MISC_USER &&
 		    machine && mg != &machine->kmaps) {
 			mg = &machine->kmaps;
+			load_map = true;
 			goto try_again;
 		}
 	} else {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c51223ac25f4..814e954c1318 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -606,12 +606,17 @@ static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 	return evlist->mmap != NULL ? 0 : -ENOMEM;
 }
 
-static int __perf_evlist__mmap(struct perf_evlist *evlist,
-			       int idx, int prot, int mask, int fd)
+struct mmap_params {
+	int prot;
+	int mask;
+};
+
+static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
+			       struct mmap_params *mp, int fd)
 {
 	evlist->mmap[idx].prev = 0;
-	evlist->mmap[idx].mask = mask;
-	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot,
+	evlist->mmap[idx].mask = mp->mask;
+	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot,
 				      MAP_SHARED, fd, 0);
 	if (evlist->mmap[idx].base == MAP_FAILED) {
 		pr_debug2("failed to mmap perf event ring buffer, error %d\n",
@@ -625,8 +630,8 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist,
 }
 
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
-				       int prot, int mask, int cpu, int thread,
-				       int *output)
+				       struct mmap_params *mp, int cpu,
+				       int thread, int *output)
 {
 	struct perf_evsel *evsel;
 
@@ -635,8 +640,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 
 		if (*output == -1) {
 			*output = fd;
-			if (__perf_evlist__mmap(evlist, idx, prot, mask,
-						*output) < 0)
+			if (__perf_evlist__mmap(evlist, idx, mp, *output) < 0)
 				return -1;
 		} else {
 			if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
@@ -651,8 +655,8 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 	return 0;
 }
 
-static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot,
-				     int mask)
+static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
+				     struct mmap_params *mp)
 {
 	int cpu, thread;
 	int nr_cpus = cpu_map__nr(evlist->cpus);
@@ -663,8 +667,8 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot,
 		int output = -1;
 
 		for (thread = 0; thread < nr_threads; thread++) {
-			if (perf_evlist__mmap_per_evsel(evlist, cpu, prot, mask,
-							cpu, thread, &output))
+			if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
+							thread, &output))
 				goto out_unmap;
 		}
 	}
@@ -677,8 +681,8 @@ out_unmap:
 	return -1;
 }
 
-static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot,
-					int mask)
+static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist,
+					struct mmap_params *mp)
 {
 	int thread;
 	int nr_threads = thread_map__nr(evlist->threads);
@@ -687,8 +691,8 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot,
 	for (thread = 0; thread < nr_threads; thread++) {
 		int output = -1;
 
-		if (perf_evlist__mmap_per_evsel(evlist, thread, prot, mask, 0,
-						thread, &output))
+		if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
+						&output))
 			goto out_unmap;
 	}
 
@@ -793,7 +797,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	struct perf_evsel *evsel;
 	const struct cpu_map *cpus = evlist->cpus;
 	const struct thread_map *threads = evlist->threads;
-	int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE), mask;
+	struct mmap_params mp = {
+		.prot = PROT_READ | (overwrite ? 0 : PROT_WRITE),
+	};
 
 	if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
 		return -ENOMEM;
@@ -804,7 +810,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	evlist->overwrite = overwrite;
 	evlist->mmap_len = perf_evlist__mmap_size(pages);
 	pr_debug("mmap size %zuB\n", evlist->mmap_len);
-	mask = evlist->mmap_len - page_size - 1;
+	mp.mask = evlist->mmap_len - page_size - 1;
 
 	evlist__for_each(evlist, evsel) {
 		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
@@ -814,9 +820,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	}
 
 	if (cpu_map__empty(cpus))
-		return perf_evlist__mmap_per_thread(evlist, prot, mask);
+		return perf_evlist__mmap_per_thread(evlist, &mp);
 
-	return perf_evlist__mmap_per_cpu(evlist, prot, mask);
+	return perf_evlist__mmap_per_cpu(evlist, &mp);
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 8606175fe1e8..90f58cdd0fb0 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -623,7 +623,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 		attr->mmap_data = track;
 	}
 
-	if (opts->call_graph_enabled)
+	if (opts->call_graph_enabled && !evsel->no_aux_samples)
 		perf_evsel__config_callgraph(evsel, opts);
 
 	if (target__has_cpu(&opts->target))
@@ -637,7 +637,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	     target__has_cpu(&opts->target) || per_cpu))
 		perf_evsel__set_sample_bit(evsel, TIME);
 
-	if (opts->raw_samples) {
+	if (opts->raw_samples && !evsel->no_aux_samples) {
 		perf_evsel__set_sample_bit(evsel, TIME);
 		perf_evsel__set_sample_bit(evsel, RAW);
 		perf_evsel__set_sample_bit(evsel, CPU);
@@ -650,7 +650,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 		attr->watermark = 0;
 		attr->wakeup_events = 1;
 	}
-	if (opts->branch_stack) {
+	if (opts->branch_stack && !evsel->no_aux_samples) {
 		perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
 		attr->branch_sample_type = opts->branch_stack;
 	}
@@ -681,6 +681,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel) &&
 		!opts->initial_delay)
 		attr->enable_on_exec = 1;
+
+	if (evsel->immediate) {
+		attr->disabled = 0;
+		attr->enable_on_exec = 0;
+	}
 }
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
@@ -960,6 +965,7 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)
 	ret += PRINT_ATTR2(exclude_user, exclude_kernel);
 	ret += PRINT_ATTR2(exclude_hv, exclude_idle);
 	ret += PRINT_ATTR2(mmap, comm);
+	ret += PRINT_ATTR2(mmap2, comm_exec);
 	ret += PRINT_ATTR2(freq, inherit_stat);
 	ret += PRINT_ATTR2(enable_on_exec, task);
 	ret += PRINT_ATTR2(watermark, precise_ip);
@@ -967,7 +973,6 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)
 	ret += PRINT_ATTR2(exclude_host, exclude_guest);
 	ret += PRINT_ATTR2N("excl.callchain_kern", exclude_callchain_kernel,
 			    "excl.callchain_user", exclude_callchain_user);
-	ret += PRINT_ATTR_U32(mmap2);
 
 	ret += PRINT_ATTR_U32(wakeup_events);
 	ret += PRINT_ATTR_U32(wakeup_watermark);
@@ -1940,6 +1945,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
 		if_print(mmap);
 		if_print(mmap2);
 		if_print(comm);
+		if_print(comm_exec);
 		if_print(freq);
 		if_print(inherit_stat);
 		if_print(enable_on_exec);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index a52e9a5bb2d0..d7f93ce0ebc1 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -83,6 +83,8 @@ struct perf_evsel {
 	int			is_pos;
 	bool 			supported;
 	bool 			needs_swap;
+	bool			no_aux_samples;
+	bool			immediate;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h
index 9844c31b7c2b..09e8e7aea7c6 100644
--- a/tools/perf/util/include/linux/kernel.h
+++ b/tools/perf/util/include/linux/kernel.h
@@ -94,27 +94,6 @@ static inline int scnprintf(char * buf, size_t size, const char * fmt, ...)
 	return (i >= ssize) ? (ssize - 1) : i;
 }
 
-int eprintf(int level,
-	    const char *fmt, ...) __attribute__((format(printf, 2, 3)));
-
-#ifndef pr_fmt
-#define pr_fmt(fmt) fmt
-#endif
-
-#define pr_err(fmt, ...) \
-	eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_warning(fmt, ...) \
-	eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_info(fmt, ...) \
-	eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_debug(fmt, ...) \
-	eprintf(1, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_debugN(n, fmt, ...) \
-	eprintf(n, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__)
-
 /*
  * This looks more complex than it should be. But we need to
  * get the type for the ~ right in round_down (it needs to be
diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h
new file mode 100644
index 000000000000..0b5a8cd2ee79
--- /dev/null
+++ b/tools/perf/util/kvm-stat.h
@@ -0,0 +1,140 @@
+#ifndef __PERF_KVM_STAT_H
+#define __PERF_KVM_STAT_H
+
+#include "../perf.h"
+#include "evsel.h"
+#include "evlist.h"
+#include "session.h"
+#include "tool.h"
+#include "stat.h"
+
+struct event_key {
+	#define INVALID_KEY     (~0ULL)
+	u64 key;
+	int info;
+	struct exit_reasons_table *exit_reasons;
+};
+
+struct kvm_event_stats {
+	u64 time;
+	struct stats stats;
+};
+
+struct kvm_event {
+	struct list_head hash_entry;
+	struct rb_node rb;
+
+	struct event_key key;
+
+	struct kvm_event_stats total;
+
+	#define DEFAULT_VCPU_NUM 8
+	int max_vcpu;
+	struct kvm_event_stats *vcpu;
+};
+
+typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int);
+
+struct kvm_event_key {
+	const char *name;
+	key_cmp_fun key;
+};
+
+struct perf_kvm_stat;
+
+struct child_event_ops {
+	void (*get_key)(struct perf_evsel *evsel,
+			struct perf_sample *sample,
+			struct event_key *key);
+	const char *name;
+};
+
+struct kvm_events_ops {
+	bool (*is_begin_event)(struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       struct event_key *key);
+	bool (*is_end_event)(struct perf_evsel *evsel,
+			     struct perf_sample *sample, struct event_key *key);
+	struct child_event_ops *child_ops;
+	void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key,
+			   char *decode);
+	const char *name;
+};
+
+struct exit_reasons_table {
+	unsigned long exit_code;
+	const char *reason;
+};
+
+#define EVENTS_BITS		12
+#define EVENTS_CACHE_SIZE	(1UL << EVENTS_BITS)
+
+struct perf_kvm_stat {
+	struct perf_tool    tool;
+	struct record_opts  opts;
+	struct perf_evlist  *evlist;
+	struct perf_session *session;
+
+	const char *file_name;
+	const char *report_event;
+	const char *sort_key;
+	int trace_vcpu;
+
+	struct exit_reasons_table *exit_reasons;
+	const char *exit_reasons_isa;
+
+	struct kvm_events_ops *events_ops;
+	key_cmp_fun compare;
+	struct list_head kvm_events_cache[EVENTS_CACHE_SIZE];
+
+	u64 total_time;
+	u64 total_count;
+	u64 lost_events;
+	u64 duration;
+
+	const char *pid_str;
+	struct intlist *pid_list;
+
+	struct rb_root result;
+
+	int timerfd;
+	unsigned int display_time;
+	bool live;
+};
+
+struct kvm_reg_events_ops {
+	const char *name;
+	struct kvm_events_ops *ops;
+};
+
+void exit_event_get_key(struct perf_evsel *evsel,
+			struct perf_sample *sample,
+			struct event_key *key);
+bool exit_event_begin(struct perf_evsel *evsel,
+		      struct perf_sample *sample,
+		      struct event_key *key);
+bool exit_event_end(struct perf_evsel *evsel,
+		    struct perf_sample *sample,
+		    struct event_key *key);
+void exit_event_decode_key(struct perf_kvm_stat *kvm,
+			   struct event_key *key,
+			   char *decode);
+
+bool kvm_exit_event(struct perf_evsel *evsel);
+bool kvm_entry_event(struct perf_evsel *evsel);
+
+#define define_exit_reasons_table(name, symbols)	\
+	static struct exit_reasons_table name[] = {	\
+		symbols, { -1, NULL }			\
+	}
+
+/*
+ * arch specific callbacks and data structures
+ */
+int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid);
+
+extern const char * const kvm_events_tp[];
+extern struct kvm_reg_events_ops kvm_reg_events_ops[];
+extern const char * const kvm_skip_events[];
+
+#endif /* __PERF_KVM_STAT_H */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index e9b943acaa5e..93c8b6fbc799 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -34,7 +34,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 		return -ENOMEM;
 
 	if (pid != HOST_KERNEL_ID) {
-		struct thread *thread = machine__findnew_thread(machine, 0,
+		struct thread *thread = machine__findnew_thread(machine, -1,
 								pid);
 		char comm[64];
 
@@ -272,6 +272,52 @@ void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size)
 	return;
 }
 
+static void machine__update_thread_pid(struct machine *machine,
+				       struct thread *th, pid_t pid)
+{
+	struct thread *leader;
+
+	if (pid == th->pid_ || pid == -1 || th->pid_ != -1)
+		return;
+
+	th->pid_ = pid;
+
+	if (th->pid_ == th->tid)
+		return;
+
+	leader = machine__findnew_thread(machine, th->pid_, th->pid_);
+	if (!leader)
+		goto out_err;
+
+	if (!leader->mg)
+		leader->mg = map_groups__new();
+
+	if (!leader->mg)
+		goto out_err;
+
+	if (th->mg == leader->mg)
+		return;
+
+	if (th->mg) {
+		/*
+		 * Maps are created from MMAP events which provide the pid and
+		 * tid.  Consequently there never should be any maps on a thread
+		 * with an unknown pid.  Just print an error if there are.
+		 */
+		if (!map_groups__empty(th->mg))
+			pr_err("Discarding thread maps for %d:%d\n",
+			       th->pid_, th->tid);
+		map_groups__delete(th->mg);
+	}
+
+	th->mg = map_groups__get(leader->mg);
+
+	return;
+
+out_err:
+	pr_err("Failed to join map groups for %d:%d\n", th->pid_, th->tid);
+}
+
 static struct thread *__machine__findnew_thread(struct machine *machine,
 						pid_t pid, pid_t tid,
 						bool create)
@@ -285,10 +331,10 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 	 * so most of the time we dont have to look up
 	 * the full rbtree:
 	 */
-	if (machine->last_match && machine->last_match->tid == tid) {
-		if (pid && pid != machine->last_match->pid_)
-			machine->last_match->pid_ = pid;
-		return machine->last_match;
+	th = machine->last_match;
+	if (th && th->tid == tid) {
+		machine__update_thread_pid(machine, th, pid);
+		return th;
 	}
 
 	while (*p != NULL) {
@@ -297,8 +343,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 
 		if (th->tid == tid) {
 			machine->last_match = th;
-			if (pid && pid != th->pid_)
-				th->pid_ = pid;
+			machine__update_thread_pid(machine, th, pid);
 			return th;
 		}
 
@@ -325,8 +370,10 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 		 * within thread__init_map_groups to find the thread
 		 * leader and that would screwed the rb tree.
 		 */
-		if (thread__init_map_groups(th, machine))
+		if (thread__init_map_groups(th, machine)) {
+			thread__delete(th);
 			return NULL;
+		}
 	}
 
 	return th;
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 25c571f4cba6..845f627e45f4 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -12,6 +12,7 @@
 #include "vdso.h"
 #include "build-id.h"
 #include "util.h"
+#include "debug.h"
 #include <linux/string.h>
 
 const char *map_type__name[MAP__NR_TYPES] = {
@@ -454,6 +455,20 @@ void map_groups__exit(struct map_groups *mg)
 	}
 }
 
+bool map_groups__empty(struct map_groups *mg)
+{
+	int i;
+
+	for (i = 0; i < MAP__NR_TYPES; ++i) {
+		if (maps__first(&mg->maps[i]))
+			return false;
+		if (!list_empty(&mg->removed_maps[i]))
+			return false;
+	}
+
+	return true;
+}
+
 struct map_groups *map_groups__new(void)
 {
 	struct map_groups *mg = malloc(sizeof(*mg));
@@ -554,8 +569,8 @@ int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
 	return ams->sym ? 0 : -1;
 }
 
-size_t __map_groups__fprintf_maps(struct map_groups *mg,
-				  enum map_type type, int verbose, FILE *fp)
+size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
+				  FILE *fp)
 {
 	size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
 	struct rb_node *nd;
@@ -573,17 +588,16 @@ size_t __map_groups__fprintf_maps(struct map_groups *mg,
 	return printed;
 }
 
-size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp)
+static size_t map_groups__fprintf_maps(struct map_groups *mg, FILE *fp)
 {
 	size_t printed = 0, i;
 	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_maps(mg, i, verbose, fp);
+		printed += __map_groups__fprintf_maps(mg, i, fp);
 	return printed;
 }
 
 static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg,
-						 enum map_type type,
-						 int verbose, FILE *fp)
+						 enum map_type type, FILE *fp)
 {
 	struct map *pos;
 	size_t printed = 0;
@@ -600,23 +614,23 @@ static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg,
 }
 
 static size_t map_groups__fprintf_removed_maps(struct map_groups *mg,
-					       int verbose, FILE *fp)
+					       FILE *fp)
 {
 	size_t printed = 0, i;
 	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_removed_maps(mg, i, verbose, fp);
+		printed += __map_groups__fprintf_removed_maps(mg, i, fp);
 	return printed;
 }
 
-size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp)
+size_t map_groups__fprintf(struct map_groups *mg, FILE *fp)
 {
-	size_t printed = map_groups__fprintf_maps(mg, verbose, fp);
+	size_t printed = map_groups__fprintf_maps(mg, fp);
 	printed += fprintf(fp, "Removed maps:\n");
-	return printed + map_groups__fprintf_removed_maps(mg, verbose, fp);
+	return printed + map_groups__fprintf_removed_maps(mg, fp);
 }
 
 int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
-				   int verbose, FILE *fp)
+				   FILE *fp)
 {
 	struct rb_root *root = &mg->maps[map->type];
 	struct rb_node *next = rb_first(root);
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 7758c72522ef..22d13a219590 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -66,6 +66,7 @@ struct map_groups {
 
 struct map_groups *map_groups__new(void);
 void map_groups__delete(struct map_groups *mg);
+bool map_groups__empty(struct map_groups *mg);
 
 static inline struct map_groups *map_groups__get(struct map_groups *mg)
 {
@@ -141,8 +142,8 @@ void map__fixup_end(struct map *map);
 
 void map__reloc_vmlinux(struct map *map);
 
-size_t __map_groups__fprintf_maps(struct map_groups *mg,
-				  enum map_type type, int verbose, FILE *fp);
+size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
+				  FILE *fp);
 void maps__insert(struct rb_root *maps, struct map *map);
 void maps__remove(struct rb_root *maps, struct map *map);
 struct map *maps__find(struct rb_root *maps, u64 addr);
@@ -152,8 +153,7 @@ void map_groups__init(struct map_groups *mg);
 void map_groups__exit(struct map_groups *mg);
 int map_groups__clone(struct map_groups *mg,
 		      struct map_groups *parent, enum map_type type);
-size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp);
-size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp);
+size_t map_groups__fprintf(struct map_groups *mg, FILE *fp);
 
 int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name,
 				     u64 addr);
@@ -210,7 +210,7 @@ struct symbol *map_groups__find_function_by_name(struct map_groups *mg,
 }
 
 int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
-				   int verbose, FILE *fp);
+				   FILE *fp);
 
 struct map *map_groups__find_by_name(struct map_groups *mg,
 				     enum map_type type, const char *name);
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index d8dac8ac5f37..b59ba858e73d 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -98,6 +98,7 @@ struct option {
 	parse_opt_cb *callback;
 	intptr_t defval;
 	bool *set;
+	void *data;
 };
 
 #define check_vtype(v, type) ( BUILD_BUG_ON_ZERO(!__builtin_types_compatible_p(typeof(v), type)) + v )
@@ -131,6 +132,10 @@ struct option {
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\
 	.value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\
 	.flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG}
+#define OPT_CALLBACK_OPTARG(s, l, v, d, a, h, f) \
+	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), \
+	  .value = (v), (a), .help = (h), .callback = (f), \
+	  .flags = PARSE_OPT_OPTARG, .data = (d) }
 
 /* parse_options() will filter out the processed options and leave the
  * non-option argments in argv[].
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 98e304766416..dca9145d704c 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -26,7 +26,6 @@
 #include <errno.h>
 #include <stdio.h>
 #include <unistd.h>
-#include <getopt.h>
 #include <stdlib.h>
 #include <string.h>
 #include <stdarg.h>
diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c
index daa17aeb6c63..a126e6cc6e73 100644
--- a/tools/perf/util/pstack.c
+++ b/tools/perf/util/pstack.c
@@ -6,6 +6,7 @@
 
 #include "util.h"
 #include "pstack.h"
+#include "debug.h"
 #include <linux/kernel.h>
 #include <stdlib.h>
 
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 122669c18ff4..12aa9b0d0ba1 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -14,12 +14,12 @@
  */
 int verbose;
 
-int eprintf(int level, const char *fmt, ...)
+int eprintf(int level, int var, const char *fmt, ...)
 {
 	va_list args;
 	int ret = 0;
 
-	if (verbose >= level) {
+	if (var >= level) {
 		va_start(args, fmt);
 		ret = vfprintf(stderr, fmt, args);
 		va_end(args);
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 049e0a09ccd3..165723152cfb 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -69,15 +69,26 @@ static void perf_probe_sample_identifier(struct perf_evsel *evsel)
 	evsel->attr.sample_type |= PERF_SAMPLE_IDENTIFIER;
 }
 
+static void perf_probe_comm_exec(struct perf_evsel *evsel)
+{
+	evsel->attr.comm_exec = 1;
+}
+
 bool perf_can_sample_identifier(void)
 {
 	return perf_probe_api(perf_probe_sample_identifier);
 }
 
+static bool perf_can_comm_exec(void)
+{
+	return perf_probe_api(perf_probe_comm_exec);
+}
+
 void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 {
 	struct perf_evsel *evsel;
 	bool use_sample_identifier = false;
+	bool use_comm_exec;
 
 	/*
 	 * Set the evsel leader links before we configure attributes,
@@ -89,8 +100,13 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 	if (evlist->cpus->map[0] < 0)
 		opts->no_inherit = true;
 
-	evlist__for_each(evlist, evsel)
+	use_comm_exec = perf_can_comm_exec();
+
+	evlist__for_each(evlist, evsel) {
 		perf_evsel__config(evsel, opts);
+		if (!evsel->idx && use_comm_exec)
+			evsel->attr.comm_exec = 1;
+	}
 
 	if (evlist->nr_entries > 1) {
 		struct perf_evsel *first = perf_evlist__first(evlist);
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index af7da565a750..b2dba9c0a3a1 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -34,6 +34,7 @@
 #include "../event.h"
 #include "../trace-event.h"
 #include "../evsel.h"
+#include "../debug.h"
 
 void boot_Perf__Trace__Context(pTHX_ CV *cv);
 void boot_DynaLoader(pTHX_ CV *cv);
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index e55b65a65558..cbce2545da45 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -27,11 +27,13 @@
 #include <errno.h>
 
 #include "../../perf.h"
+#include "../debug.h"
 #include "../evsel.h"
 #include "../util.h"
 #include "../event.h"
 #include "../thread.h"
 #include "../trace-event.h"
+#include "../machine.h"
 
 PyMODINIT_FUNC initperf_trace_context(void);
 
@@ -50,10 +52,14 @@ static int zero_flag_atom;
 
 static PyObject *main_module, *main_dict;
 
+static void handler_call_die(const char *handler_name) NORETURN;
 static void handler_call_die(const char *handler_name)
 {
 	PyErr_Print();
 	Py_FatalError("problem in Python trace event handler");
+	// Py_FatalError does not return
+	// but we have to make the compiler happy
+	abort();
 }
 
 /*
@@ -97,6 +103,7 @@ static void define_value(enum print_arg_type field_type,
 		retval = PyObject_CallObject(handler, t);
 		if (retval == NULL)
 			handler_call_die(handler_name);
+		Py_DECREF(retval);
 	}
 
 	Py_DECREF(t);
@@ -143,6 +150,7 @@ static void define_field(enum print_arg_type field_type,
 		retval = PyObject_CallObject(handler, t);
 		if (retval == NULL)
 			handler_call_die(handler_name);
+		Py_DECREF(retval);
 	}
 
 	Py_DECREF(t);
@@ -272,12 +280,90 @@ static PyObject *get_field_numeric_entry(struct event_format *event,
 	return obj;
 }
 
+
+static PyObject *python_process_callchain(struct perf_sample *sample,
+					 struct perf_evsel *evsel,
+					 struct addr_location *al)
+{
+	PyObject *pylist;
+
+	pylist = PyList_New(0);
+	if (!pylist)
+		Py_FatalError("couldn't create Python list");
+
+	if (!symbol_conf.use_callchain || !sample->callchain)
+		goto exit;
+
+	if (machine__resolve_callchain(al->machine, evsel, al->thread,
+					   sample, NULL, NULL,
+					   PERF_MAX_STACK_DEPTH) != 0) {
+		pr_err("Failed to resolve callchain. Skipping\n");
+		goto exit;
+	}
+	callchain_cursor_commit(&callchain_cursor);
+
+
+	while (1) {
+		PyObject *pyelem;
+		struct callchain_cursor_node *node;
+		node = callchain_cursor_current(&callchain_cursor);
+		if (!node)
+			break;
+
+		pyelem = PyDict_New();
+		if (!pyelem)
+			Py_FatalError("couldn't create Python dictionary");
+
+
+		pydict_set_item_string_decref(pyelem, "ip",
+				PyLong_FromUnsignedLongLong(node->ip));
+
+		if (node->sym) {
+			PyObject *pysym  = PyDict_New();
+			if (!pysym)
+				Py_FatalError("couldn't create Python dictionary");
+			pydict_set_item_string_decref(pysym, "start",
+					PyLong_FromUnsignedLongLong(node->sym->start));
+			pydict_set_item_string_decref(pysym, "end",
+					PyLong_FromUnsignedLongLong(node->sym->end));
+			pydict_set_item_string_decref(pysym, "binding",
+					PyInt_FromLong(node->sym->binding));
+			pydict_set_item_string_decref(pysym, "name",
+					PyString_FromStringAndSize(node->sym->name,
+							node->sym->namelen));
+			pydict_set_item_string_decref(pyelem, "sym", pysym);
+		}
+
+		if (node->map) {
+			struct map *map = node->map;
+			const char *dsoname = "[unknown]";
+			if (map && map->dso && (map->dso->name || map->dso->long_name)) {
+				if (symbol_conf.show_kernel_path && map->dso->long_name)
+					dsoname = map->dso->long_name;
+				else if (map->dso->name)
+					dsoname = map->dso->name;
+			}
+			pydict_set_item_string_decref(pyelem, "dso",
+					PyString_FromString(dsoname));
+		}
+
+		callchain_cursor_advance(&callchain_cursor);
+		PyList_Append(pylist, pyelem);
+		Py_DECREF(pyelem);
+	}
+
+exit:
+	return pylist;
+}
+
+
 static void python_process_tracepoint(struct perf_sample *sample,
 				      struct perf_evsel *evsel,
 				      struct thread *thread,
 				      struct addr_location *al)
 {
-	PyObject *handler, *retval, *context, *t, *obj, *dict = NULL;
+	PyObject *handler, *retval, *context, *t, *obj, *callchain;
+	PyObject *dict = NULL;
 	static char handler_name[256];
 	struct format_field *field;
 	unsigned long s, ns;
@@ -320,18 +406,23 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	PyTuple_SetItem(t, n++, PyString_FromString(handler_name));
 	PyTuple_SetItem(t, n++, context);
 
+	/* ip unwinding */
+	callchain = python_process_callchain(sample, evsel, al);
+
 	if (handler) {
 		PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
 		PyTuple_SetItem(t, n++, PyInt_FromLong(s));
 		PyTuple_SetItem(t, n++, PyInt_FromLong(ns));
 		PyTuple_SetItem(t, n++, PyInt_FromLong(pid));
 		PyTuple_SetItem(t, n++, PyString_FromString(comm));
+		PyTuple_SetItem(t, n++, callchain);
 	} else {
 		pydict_set_item_string_decref(dict, "common_cpu", PyInt_FromLong(cpu));
 		pydict_set_item_string_decref(dict, "common_s", PyInt_FromLong(s));
 		pydict_set_item_string_decref(dict, "common_ns", PyInt_FromLong(ns));
 		pydict_set_item_string_decref(dict, "common_pid", PyInt_FromLong(pid));
 		pydict_set_item_string_decref(dict, "common_comm", PyString_FromString(comm));
+		pydict_set_item_string_decref(dict, "common_callchain", callchain);
 	}
 	for (field = event->format.fields; field; field = field->next) {
 		if (field->flags & FIELD_IS_STRING) {
@@ -351,6 +442,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 			pydict_set_item_string_decref(dict, field->name, obj);
 
 	}
+
 	if (!handler)
 		PyTuple_SetItem(t, n++, dict);
 
@@ -361,6 +453,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 		retval = PyObject_CallObject(handler, t);
 		if (retval == NULL)
 			handler_call_die(handler_name);
+		Py_DECREF(retval);
 	} else {
 		handler = PyDict_GetItemString(main_dict, "trace_unhandled");
 		if (handler && PyCallable_Check(handler)) {
@@ -368,6 +461,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 			retval = PyObject_CallObject(handler, t);
 			if (retval == NULL)
 				handler_call_die("trace_unhandled");
+			Py_DECREF(retval);
 		}
 		Py_DECREF(dict);
 	}
@@ -380,7 +474,7 @@ static void python_process_general_event(struct perf_sample *sample,
 					 struct thread *thread,
 					 struct addr_location *al)
 {
-	PyObject *handler, *retval, *t, *dict;
+	PyObject *handler, *retval, *t, *dict, *callchain, *dict_sample;
 	static char handler_name[64];
 	unsigned n = 0;
 
@@ -396,6 +490,10 @@ static void python_process_general_event(struct perf_sample *sample,
 	if (!dict)
 		Py_FatalError("couldn't create Python dictionary");
 
+	dict_sample = PyDict_New();
+	if (!dict_sample)
+		Py_FatalError("couldn't create Python dictionary");
+
 	snprintf(handler_name, sizeof(handler_name), "%s", "process_event");
 
 	handler = PyDict_GetItemString(main_dict, handler_name);
@@ -405,8 +503,21 @@ static void python_process_general_event(struct perf_sample *sample,
 	pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
 	pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize(
 			(const char *)&evsel->attr, sizeof(evsel->attr)));
-	pydict_set_item_string_decref(dict, "sample", PyString_FromStringAndSize(
-			(const char *)sample, sizeof(*sample)));
+
+	pydict_set_item_string_decref(dict_sample, "pid",
+			PyInt_FromLong(sample->pid));
+	pydict_set_item_string_decref(dict_sample, "tid",
+			PyInt_FromLong(sample->tid));
+	pydict_set_item_string_decref(dict_sample, "cpu",
+			PyInt_FromLong(sample->cpu));
+	pydict_set_item_string_decref(dict_sample, "ip",
+			PyLong_FromUnsignedLongLong(sample->ip));
+	pydict_set_item_string_decref(dict_sample, "time",
+			PyLong_FromUnsignedLongLong(sample->time));
+	pydict_set_item_string_decref(dict_sample, "period",
+			PyLong_FromUnsignedLongLong(sample->period));
+	pydict_set_item_string_decref(dict, "sample", dict_sample);
+
 	pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize(
 			(const char *)sample->raw_data, sample->raw_size));
 	pydict_set_item_string_decref(dict, "comm",
@@ -420,6 +531,10 @@ static void python_process_general_event(struct perf_sample *sample,
 			PyString_FromString(al->sym->name));
 	}
 
+	/* ip unwinding */
+	callchain = python_process_callchain(sample, evsel, al);
+	pydict_set_item_string_decref(dict, "callchain", callchain);
+
 	PyTuple_SetItem(t, n++, dict);
 	if (_PyTuple_Resize(&t, n) == -1)
 		Py_FatalError("error resizing Python tuple");
@@ -427,6 +542,7 @@ static void python_process_general_event(struct perf_sample *sample,
 	retval = PyObject_CallObject(handler, t);
 	if (retval == NULL)
 		handler_call_die(handler_name);
+	Py_DECREF(retval);
 exit:
 	Py_DECREF(dict);
 	Py_DECREF(t);
@@ -548,8 +664,7 @@ static int python_stop_script(void)
 	retval = PyObject_CallObject(handler, NULL);
 	if (retval == NULL)
 		handler_call_die("trace_end");
-	else
-		Py_DECREF(retval);
+	Py_DECREF(retval);
 out:
 	Py_XDECREF(main_dict);
 	Py_XDECREF(main_module);
@@ -616,6 +731,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 		fprintf(ofp, "common_nsecs, ");
 		fprintf(ofp, "common_pid, ");
 		fprintf(ofp, "common_comm,\n\t");
+		fprintf(ofp, "common_callchain, ");
 
 		not_first = 0;
 		count = 0;
@@ -659,7 +775,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 				fprintf(ofp, "%%u");
 		}
 
-		fprintf(ofp, "\\n\" %% \\\n\t\t(");
+		fprintf(ofp, "\" %% \\\n\t\t(");
 
 		not_first = 0;
 		count = 0;
@@ -695,7 +811,15 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 				fprintf(ofp, "%s", f->name);
 		}
 
-		fprintf(ofp, "),\n\n");
+		fprintf(ofp, ")\n\n");
+
+		fprintf(ofp, "\t\tfor node in common_callchain:");
+		fprintf(ofp, "\n\t\t\tif 'sym' in node:");
+		fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])");
+		fprintf(ofp, "\n\t\t\telse:");
+		fprintf(ofp, "\n\t\t\t\tprint \"\t[%%x]\" %% (node['ip'])\n\n");
+		fprintf(ofp, "\t\tprint \"\\n\"\n\n");
+
 	}
 
 	fprintf(ofp, "def trace_unhandled(event_name, context, "
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 64a186edc7be..eac14ce0ae8d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1083,13 +1083,14 @@ void perf_event_header__bswap(struct perf_event_header *hdr)
 
 struct thread *perf_session__findnew(struct perf_session *session, pid_t pid)
 {
-	return machine__findnew_thread(&session->machines.host, 0, pid);
+	return machine__findnew_thread(&session->machines.host, -1, pid);
 }
 
 static struct thread *perf_session__register_idle_thread(struct perf_session *session)
 {
-	struct thread *thread = perf_session__findnew(session, 0);
+	struct thread *thread;
 
+	thread = machine__findnew_thread(&session->machines.host, 0, 0);
 	if (thread == NULL || thread__set_comm(thread, "swapper", 0)) {
 		pr_err("problem inserting idle task.\n");
 		thread = NULL;
@@ -1296,8 +1297,10 @@ int __perf_session__process_events(struct perf_session *session,
 	ui_progress__init(&prog, file_size, "Processing events...");
 
 	mmap_size = MMAP_SIZE;
-	if (mmap_size > file_size)
+	if (mmap_size > file_size) {
 		mmap_size = file_size;
+		session->one_mmap = true;
+	}
 
 	memset(mmaps, 0, sizeof(mmaps));
 
@@ -1319,6 +1322,10 @@ remap:
 	mmaps[map_idx] = buf;
 	map_idx = (map_idx + 1) & (ARRAY_SIZE(mmaps) - 1);
 	file_pos = file_offset + head;
+	if (session->one_mmap) {
+		session->one_mmap_addr = buf;
+		session->one_mmap_offset = file_offset;
+	}
 
 more:
 	event = fetch_mmaped_event(session, head, mmap_size, buf);
@@ -1364,6 +1371,7 @@ out_err:
 	ui_progress__finish();
 	perf_session__warn_about_errors(session, tool);
 	perf_session_free_sample_buffers(session);
+	session->one_mmap = false;
 	return err;
 }
 
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 3140f8ae6148..0321013bd9fd 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -36,6 +36,9 @@ struct perf_session {
 	struct trace_event	tevent;
 	struct events_stats	stats;
 	bool			repipe;
+	bool			one_mmap;
+	void			*one_mmap_addr;
+	u64			one_mmap_offset;
 	struct ordered_samples	ordered_samples;
 	struct perf_data_file	*file;
 };
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 6864661a79dd..cef8f426356e 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -49,7 +49,8 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym)
 
 static inline int elf_sym__is_function(const GElf_Sym *sym)
 {
-	return elf_sym__type(sym) == STT_FUNC &&
+	return (elf_sym__type(sym) == STT_FUNC ||
+		elf_sym__type(sym) == STT_GNU_IFUNC) &&
 	       sym->st_name != 0 &&
 	       sym->st_shndx != SHN_UNDEF;
 }
@@ -598,6 +599,8 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 			goto out_elf_end;
 	}
 
+	ss->is_64_bit = (gelf_getclass(elf) == ELFCLASS64);
+
 	ss->symtab = elf_section_by_name(elf, &ehdr, &ss->symshdr, ".symtab",
 			NULL);
 	if (ss->symshdr.sh_type != SHT_SYMTAB)
@@ -698,6 +701,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
 	bool remap_kernel = false, adjust_kernel_syms = false;
 
 	dso->symtab_type = syms_ss->type;
+	dso->is_64_bit = syms_ss->is_64_bit;
 	dso->rel = syms_ss->ehdr.e_type == ET_REL;
 
 	/*
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index bd15f490d04f..101f55d407d0 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -288,6 +288,23 @@ int dso__synthesize_plt_symbols(struct dso *dso __maybe_unused,
 	return 0;
 }
 
+static int fd__is_64_bit(int fd)
+{
+	u8 e_ident[EI_NIDENT];
+
+	if (lseek(fd, 0, SEEK_SET))
+		return -1;
+
+	if (readn(fd, e_ident, sizeof(e_ident)) != sizeof(e_ident))
+		return -1;
+
+	if (memcmp(e_ident, ELFMAG, SELFMAG) ||
+	    e_ident[EI_VERSION] != EV_CURRENT)
+		return -1;
+
+	return e_ident[EI_CLASS] == ELFCLASS64;
+}
+
 int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
 		  struct symsrc *ss,
 		  struct symsrc *runtime_ss __maybe_unused,
@@ -295,6 +312,11 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
 		  int kmodule __maybe_unused)
 {
 	unsigned char *build_id[BUILD_ID_SIZE];
+	int ret;
+
+	ret = fd__is_64_bit(ss->fd);
+	if (ret >= 0)
+		dso->is_64_bit = ret;
 
 	if (filename__read_build_id(ss->name, build_id, BUILD_ID_SIZE) > 0) {
 		dso__set_build_id(dso, build_id);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 2e6a2e219eb9..eb06746b06b2 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -342,6 +342,16 @@ static struct symbol *symbols__first(struct rb_root *symbols)
 	return NULL;
 }
 
+static struct symbol *symbols__next(struct symbol *sym)
+{
+	struct rb_node *n = rb_next(&sym->rb_node);
+
+	if (n)
+		return rb_entry(n, struct symbol, rb_node);
+
+	return NULL;
+}
+
 struct symbol_name_rb_node {
 	struct rb_node	rb_node;
 	struct symbol	sym;
@@ -412,11 +422,16 @@ struct symbol *dso__find_symbol(struct dso *dso,
 	return symbols__find(&dso->symbols[type], addr);
 }
 
-static struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
+struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
 {
 	return symbols__first(&dso->symbols[type]);
 }
 
+struct symbol *dso__next_symbol(struct symbol *sym)
+{
+	return symbols__next(sym);
+}
+
 struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
 					const char *name)
 {
@@ -1065,6 +1080,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 			      &is_64_bit);
 	if (err)
 		goto out_err;
+	dso->is_64_bit = is_64_bit;
 
 	if (list_empty(&md.maps)) {
 		err = -EINVAL;
@@ -1663,6 +1679,7 @@ do_kallsyms:
 	free(kallsyms_allocated_filename);
 
 	if (err > 0 && !dso__is_kcore(dso)) {
+		dso->binary_type = DSO_BINARY_TYPE__KALLSYMS;
 		dso__set_long_name(dso, "[kernel.kallsyms]", false);
 		map__fixup_start(map);
 		map__fixup_end(map);
@@ -1710,6 +1727,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
 	if (err > 0)
 		pr_debug("Using %s for symbols\n", kallsyms_filename);
 	if (err > 0 && !dso__is_kcore(dso)) {
+		dso->binary_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
 		machine__mmap_name(machine, path, sizeof(path));
 		dso__set_long_name(dso, strdup(path), true);
 		map__fixup_start(map);
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index a81877b1dee0..ee2d3ccd3ad1 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -216,6 +216,7 @@ struct symsrc {
 	GElf_Shdr dynshdr;
 
 	bool adjust_symbols;
+	bool is_64_bit;
 #endif
 };
 
@@ -239,6 +240,9 @@ struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
 struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
 					const char *name);
 
+struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
+struct symbol *dso__next_symbol(struct symbol *sym);
+
 int filename__read_build_id(const char *filename, void *bf, size_t size);
 int sysfs__read_build_id(const char *filename, void *bf, size_t size);
 int modules__parse(const char *filename, void *arg,
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 2fde0d5e40b5..9692c06a9e21 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -13,7 +13,7 @@ int thread__init_map_groups(struct thread *thread, struct machine *machine)
 	struct thread *leader;
 	pid_t pid = thread->pid_;
 
-	if (pid == thread->tid) {
+	if (pid == thread->tid || pid == -1) {
 		thread->mg = map_groups__new();
 	} else {
 		leader = machine__findnew_thread(machine, pid, pid);
@@ -60,8 +60,10 @@ void thread__delete(struct thread *thread)
 {
 	struct comm *comm, *tmp;
 
-	map_groups__put(thread->mg);
-	thread->mg = NULL;
+	if (thread->mg) {
+		map_groups__put(thread->mg);
+		thread->mg = NULL;
+	}
 	list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) {
 		list_del(&comm->list);
 		comm__free(comm);
@@ -127,12 +129,12 @@ int thread__comm_len(struct thread *thread)
 size_t thread__fprintf(struct thread *thread, FILE *fp)
 {
 	return fprintf(fp, "Thread %d %s\n", thread->tid, thread__comm_str(thread)) +
-	       map_groups__fprintf(thread->mg, verbose, fp);
+	       map_groups__fprintf(thread->mg, fp);
 }
 
 void thread__insert_map(struct thread *thread, struct map *map)
 {
-	map_groups__fixup_overlappings(thread->mg, map, verbose, stderr);
+	map_groups__fixup_overlappings(thread->mg, map, stderr);
 	map_groups__insert(thread->mg, map);
 }
 
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index c3bba883f5c3..eb72716017ac 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -40,6 +40,7 @@
 #include "trace-event.h"
 #include <api/fs/debugfs.h>
 #include "evsel.h"
+#include "debug.h"
 
 #define VERSION "0.5"
 
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index e113e180c48f..54d9e9b548a8 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -22,7 +22,6 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <getopt.h>
 #include <stdarg.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -36,6 +35,7 @@
 #include "../perf.h"
 #include "util.h"
 #include "trace-event.h"
+#include "debug.h"
 
 static int input_fd;
 
diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c
new file mode 100644
index 000000000000..ef4749836ce9
--- /dev/null
+++ b/tools/perf/util/tsc.c
@@ -0,0 +1,25 @@
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+#include "tsc.h"
+
+u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc)
+{
+	u64 t, quot, rem;
+
+	t = ns - tc->time_zero;
+	quot = t / tc->time_mult;
+	rem  = t % tc->time_mult;
+	return (quot << tc->time_shift) +
+	       (rem << tc->time_shift) / tc->time_mult;
+}
+
+u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc)
+{
+	u64 quot, rem;
+
+	quot = cyc >> tc->time_shift;
+	rem  = cyc & ((1 << tc->time_shift) - 1);
+	return tc->time_zero + quot * tc->time_mult +
+	       ((rem * tc->time_mult) >> tc->time_shift);
+}
diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h
new file mode 100644
index 000000000000..4eca84887c8a
--- /dev/null
+++ b/tools/perf/util/tsc.h
@@ -0,0 +1,11 @@
+#ifndef __PERF_TSC_H
+#define __PERF_TSC_H
+
+#include <linux/types.h>
+
+#include "../arch/x86/util/tsc.h"
+
+u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc);
+u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc);
+
+#endif
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 5ec80a575b50..7419768c38b1 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -3,6 +3,7 @@
 #include <elfutils/libdwfl.h>
 #include <inttypes.h>
 #include <errno.h>
+#include "debug.h"
 #include "unwind.h"
 #include "unwind-libdw.h"
 #include "machine.h"
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 25578b98f5c5..92b56db52471 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -30,6 +30,7 @@
 #include "unwind.h"
 #include "symbol.h"
 #include "util.h"
+#include "debug.h"
 
 extern int
 UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index e4132aeeb780..e52e7461911b 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -1,5 +1,6 @@
 #include "../perf.h"
 #include "util.h"
+#include "debug.h"
 #include <api/fs/fs.h>
 #include <sys/mman.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 0ddb3b8a89ec..290582452da3 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -12,6 +12,7 @@
 #include "util.h"
 #include "symbol.h"
 #include "linux/string.h"
+#include "debug.h"
 
 static bool vdso_found;
 static char vdso_file[] = "/tmp/perf-vdso.so-XXXXXX";