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 from Arnaldo Carvalho de Melo:

User visible changes:

 - Don't open the DWARF info multiple times, keeping instead a dwfl handle
   in struct dso, greatly speeding up 'perf report' on powerpc. (Sukadev Bhattiprolu)

 - Introduce PARSE_OPT_DISABLED option flag and use it to avoid showing
   undersired options in tools that provides frontends to 'perf record', like
   sched, kvm, etc (Namhyung Kim)

Infrastructure changes:

 - More Intel PT work, including a facility to export sample data (comms,
   threads, symbol names, etc) in a database friendly way, with an script to use
   this to create a postgresql database. (Adrian Hunter)

 - Use make sure that thread->mg->machine points to the machine where
   the thread exists (it was being set only for the kmaps kernel modules
   case, do it as well for the mmaps) and use it to shorten function
   signatures (Arnaldo Carvalho de Melo)

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

33 files changed, 1256 insertions, 166 deletions

diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index a904a4c..2e7c68e 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -33,8 +33,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 		return -1;
 	}
 
-	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      sample->ip, &al);
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, &al);
 
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index c84d3f8..0022980 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -754,8 +754,8 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
 
 	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain ||
 	    sort__has_parent) {
-		return machine__resolve_callchain(al->machine, evsel, al->thread,
-						  sample, parent, al, max_stack);
+		return thread__resolve_callchain(al->thread, evsel, sample,
+						 parent, al, max_stack);
 	}
 	return 0;
 }
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 94cfefd..3caccc2 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -184,11 +184,9 @@ static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
 }
 
 #ifdef HAVE_SKIP_CALLCHAIN_IDX
-extern int arch_skip_callchain_idx(struct machine *machine,
-			struct thread *thread, struct ip_callchain *chain);
+extern int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain);
 #else
-static inline int arch_skip_callchain_idx(struct machine *machine __maybe_unused,
-			struct thread *thread __maybe_unused,
+static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
 			struct ip_callchain *chain __maybe_unused)
 {
 	return -1;
diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h
index 51c10ab..71c9c39 100644
--- a/tools/perf/util/comm.h
+++ b/tools/perf/util/comm.h
@@ -12,6 +12,10 @@ struct comm {
 	u64 start;
 	struct list_head list;
 	bool exec;
+	union { /* Tool specific area */
+		void	*priv;
+		u64	db_id;
+	};
 };
 
 void comm__free(struct comm *comm);
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
new file mode 100644
index 0000000..be128b0
--- /dev/null
+++ b/tools/perf/util/db-export.c
@@ -0,0 +1,270 @@
+/*
+ * db-export.c: Support for exporting data suitable for import to a database
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <errno.h>
+
+#include "evsel.h"
+#include "machine.h"
+#include "thread.h"
+#include "comm.h"
+#include "symbol.h"
+#include "event.h"
+#include "db-export.h"
+
+int db_export__init(struct db_export *dbe)
+{
+	memset(dbe, 0, sizeof(struct db_export));
+	return 0;
+}
+
+void db_export__exit(struct db_export *dbe __maybe_unused)
+{
+}
+
+int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel)
+{
+	if (evsel->db_id)
+		return 0;
+
+	evsel->db_id = ++dbe->evsel_last_db_id;
+
+	if (dbe->export_evsel)
+		return dbe->export_evsel(dbe, evsel);
+
+	return 0;
+}
+
+int db_export__machine(struct db_export *dbe, struct machine *machine)
+{
+	if (machine->db_id)
+		return 0;
+
+	machine->db_id = ++dbe->machine_last_db_id;
+
+	if (dbe->export_machine)
+		return dbe->export_machine(dbe, machine);
+
+	return 0;
+}
+
+int db_export__thread(struct db_export *dbe, struct thread *thread,
+		      struct machine *machine, struct comm *comm)
+{
+	u64 main_thread_db_id = 0;
+	int err;
+
+	if (thread->db_id)
+		return 0;
+
+	thread->db_id = ++dbe->thread_last_db_id;
+
+	if (thread->pid_ != -1) {
+		struct thread *main_thread;
+
+		if (thread->pid_ == thread->tid) {
+			main_thread = thread;
+		} else {
+			main_thread = machine__findnew_thread(machine,
+							      thread->pid_,
+							      thread->pid_);
+			if (!main_thread)
+				return -ENOMEM;
+			err = db_export__thread(dbe, main_thread, machine,
+						comm);
+			if (err)
+				return err;
+			if (comm) {
+				err = db_export__comm_thread(dbe, comm, thread);
+				if (err)
+					return err;
+			}
+		}
+		main_thread_db_id = main_thread->db_id;
+	}
+
+	if (dbe->export_thread)
+		return dbe->export_thread(dbe, thread, main_thread_db_id,
+					  machine);
+
+	return 0;
+}
+
+int db_export__comm(struct db_export *dbe, struct comm *comm,
+		    struct thread *main_thread)
+{
+	int err;
+
+	if (comm->db_id)
+		return 0;
+
+	comm->db_id = ++dbe->comm_last_db_id;
+
+	if (dbe->export_comm) {
+		err = dbe->export_comm(dbe, comm);
+		if (err)
+			return err;
+	}
+
+	return db_export__comm_thread(dbe, comm, main_thread);
+}
+
+int db_export__comm_thread(struct db_export *dbe, struct comm *comm,
+			   struct thread *thread)
+{
+	u64 db_id;
+
+	db_id = ++dbe->comm_thread_last_db_id;
+
+	if (dbe->export_comm_thread)
+		return dbe->export_comm_thread(dbe, db_id, comm, thread);
+
+	return 0;
+}
+
+int db_export__dso(struct db_export *dbe, struct dso *dso,
+		   struct machine *machine)
+{
+	if (dso->db_id)
+		return 0;
+
+	dso->db_id = ++dbe->dso_last_db_id;
+
+	if (dbe->export_dso)
+		return dbe->export_dso(dbe, dso, machine);
+
+	return 0;
+}
+
+int db_export__symbol(struct db_export *dbe, struct symbol *sym,
+		      struct dso *dso)
+{
+	u64 *sym_db_id = symbol__priv(sym);
+
+	if (*sym_db_id)
+		return 0;
+
+	*sym_db_id = ++dbe->symbol_last_db_id;
+
+	if (dbe->export_symbol)
+		return dbe->export_symbol(dbe, sym, dso);
+
+	return 0;
+}
+
+static struct thread *get_main_thread(struct machine *machine, struct thread *thread)
+{
+	if (thread->pid_ == thread->tid)
+		return thread;
+
+	if (thread->pid_ == -1)
+		return NULL;
+
+	return machine__find_thread(machine, thread->pid_, thread->pid_);
+}
+
+static int db_ids_from_al(struct db_export *dbe, struct addr_location *al,
+			  u64 *dso_db_id, u64 *sym_db_id, u64 *offset)
+{
+	int err;
+
+	if (al->map) {
+		struct dso *dso = al->map->dso;
+
+		err = db_export__dso(dbe, dso, al->machine);
+		if (err)
+			return err;
+		*dso_db_id = dso->db_id;
+
+		if (!al->sym) {
+			al->sym = symbol__new(al->addr, 0, 0, "unknown");
+			if (al->sym)
+				symbols__insert(&dso->symbols[al->map->type],
+						al->sym);
+		}
+
+		if (al->sym) {
+			u64 *db_id = symbol__priv(al->sym);
+
+			err = db_export__symbol(dbe, al->sym, dso);
+			if (err)
+				return err;
+			*sym_db_id = *db_id;
+			*offset = al->addr - al->sym->start;
+		}
+	}
+
+	return 0;
+}
+
+int db_export__sample(struct db_export *dbe, union perf_event *event,
+		      struct perf_sample *sample, struct perf_evsel *evsel,
+		      struct thread *thread, struct addr_location *al)
+{
+	struct export_sample es = {
+		.event = event,
+		.sample = sample,
+		.evsel = evsel,
+		.thread = thread,
+		.al = al,
+	};
+	struct thread *main_thread;
+	struct comm *comm = NULL;
+	int err;
+
+	err = db_export__evsel(dbe, evsel);
+	if (err)
+		return err;
+
+	err = db_export__machine(dbe, al->machine);
+	if (err)
+		return err;
+
+	main_thread = get_main_thread(al->machine, thread);
+	if (main_thread)
+		comm = machine__thread_exec_comm(al->machine, main_thread);
+
+	err = db_export__thread(dbe, thread, al->machine, comm);
+	if (err)
+		return err;
+
+	if (comm) {
+		err = db_export__comm(dbe, comm, main_thread);
+		if (err)
+			return err;
+		es.comm_db_id = comm->db_id;
+	}
+
+	es.db_id = ++dbe->sample_last_db_id;
+
+	err = db_ids_from_al(dbe, al, &es.dso_db_id, &es.sym_db_id, &es.offset);
+	if (err)
+		return err;
+
+	if ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
+	    sample_addr_correlates_sym(&evsel->attr)) {
+		struct addr_location addr_al;
+
+		perf_event__preprocess_sample_addr(event, sample, thread, &addr_al);
+		err = db_ids_from_al(dbe, &addr_al, &es.addr_dso_db_id,
+				     &es.addr_sym_db_id, &es.addr_offset);
+		if (err)
+			return err;
+	}
+
+	if (dbe->export_sample)
+		return dbe->export_sample(dbe, &es);
+
+	return 0;
+}
diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h
new file mode 100644
index 0000000..b3643e8
--- /dev/null
+++ b/tools/perf/util/db-export.h
@@ -0,0 +1,86 @@
+/*
+ * db-export.h: Support for exporting data suitable for import to a database
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef __PERF_DB_EXPORT_H
+#define __PERF_DB_EXPORT_H
+
+#include <linux/types.h>
+
+struct perf_evsel;
+struct machine;
+struct thread;
+struct comm;
+struct dso;
+struct perf_sample;
+struct addr_location;
+
+struct export_sample {
+	union perf_event	*event;
+	struct perf_sample	*sample;
+	struct perf_evsel	*evsel;
+	struct thread		*thread;
+	struct addr_location	*al;
+	u64			db_id;
+	u64			comm_db_id;
+	u64			dso_db_id;
+	u64			sym_db_id;
+	u64			offset; /* ip offset from symbol start */
+	u64			addr_dso_db_id;
+	u64			addr_sym_db_id;
+	u64			addr_offset; /* addr offset from symbol start */
+};
+
+struct db_export {
+	int (*export_evsel)(struct db_export *dbe, struct perf_evsel *evsel);
+	int (*export_machine)(struct db_export *dbe, struct machine *machine);
+	int (*export_thread)(struct db_export *dbe, struct thread *thread,
+			     u64 main_thread_db_id, struct machine *machine);
+	int (*export_comm)(struct db_export *dbe, struct comm *comm);
+	int (*export_comm_thread)(struct db_export *dbe, u64 db_id,
+				  struct comm *comm, struct thread *thread);
+	int (*export_dso)(struct db_export *dbe, struct dso *dso,
+			  struct machine *machine);
+	int (*export_symbol)(struct db_export *dbe, struct symbol *sym,
+			     struct dso *dso);
+	int (*export_sample)(struct db_export *dbe, struct export_sample *es);
+	u64 evsel_last_db_id;
+	u64 machine_last_db_id;
+	u64 thread_last_db_id;
+	u64 comm_last_db_id;
+	u64 comm_thread_last_db_id;
+	u64 dso_last_db_id;
+	u64 symbol_last_db_id;
+	u64 sample_last_db_id;
+};
+
+int db_export__init(struct db_export *dbe);
+void db_export__exit(struct db_export *dbe);
+int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel);
+int db_export__machine(struct db_export *dbe, struct machine *machine);
+int db_export__thread(struct db_export *dbe, struct thread *thread,
+		      struct machine *machine, struct comm *comm);
+int db_export__comm(struct db_export *dbe, struct comm *comm,
+		    struct thread *main_thread);
+int db_export__comm_thread(struct db_export *dbe, struct comm *comm,
+			   struct thread *thread);
+int db_export__dso(struct db_export *dbe, struct dso *dso,
+		   struct machine *machine);
+int db_export__symbol(struct db_export *dbe, struct symbol *sym,
+		      struct dso *dso);
+int db_export__sample(struct db_export *dbe, union perf_event *event,
+		      struct perf_sample *sample, struct perf_evsel *evsel,
+		      struct thread *thread, struct addr_location *al);
+
+#endif
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index acb651a..a316e4a 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -127,6 +127,7 @@ struct dso {
 	const char	 *long_name;
 	u16		 long_name_len;
 	u16		 short_name_len;
+	void		*dwfl;			/* DWARF debug info */
 
 	/* dso data file */
 	struct {
@@ -138,6 +139,11 @@ struct dso {
 		struct list_head open_entry;
 	} data;
 
+	union { /* Tool specific area */
+		void	 *priv;
+		u64	 db_id;
+	};
+
 	char		 name[0];
 };
 
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 4af6b27..6c6d044 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -28,6 +28,7 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
 	[PERF_RECORD_HEADER_BUILD_ID]		= "BUILD_ID",
 	[PERF_RECORD_FINISHED_ROUND]		= "FINISHED_ROUND",
+	[PERF_RECORD_ID_INDEX]			= "ID_INDEX",
 };
 
 const char *perf_event__name(unsigned int id)
@@ -730,12 +731,12 @@ int perf_event__process(struct perf_tool *tool __maybe_unused,
 	return machine__process_event(machine, event, sample);
 }
 
-void thread__find_addr_map(struct thread *thread,
-			   struct machine *machine, u8 cpumode,
+void thread__find_addr_map(struct thread *thread, u8 cpumode,
 			   enum map_type type, u64 addr,
 			   struct addr_location *al)
 {
 	struct map_groups *mg = thread->mg;
+	struct machine *machine = mg->machine;
 	bool load_map = false;
 
 	al->machine = machine;
@@ -806,14 +807,14 @@ try_again:
 	}
 }
 
-void thread__find_addr_location(struct thread *thread, struct machine *machine,
+void thread__find_addr_location(struct thread *thread,
 				u8 cpumode, enum map_type type, u64 addr,
 				struct addr_location *al)
 {
-	thread__find_addr_map(thread, machine, cpumode, type, addr, al);
+	thread__find_addr_map(thread, cpumode, type, addr, al);
 	if (al->map != NULL)
 		al->sym = map__find_symbol(al->map, al->addr,
-					   machine->symbol_filter);
+					   thread->mg->machine->symbol_filter);
 	else
 		al->sym = NULL;
 }
@@ -842,8 +843,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
 	    machine->vmlinux_maps[MAP__FUNCTION] == NULL)
 		machine__create_kernel_maps(machine);
 
-	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      sample->ip, al);
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, al);
 	dump_printf(" ...... dso: %s\n",
 		    al->map ? al->map->dso->long_name :
 			al->level == 'H' ? "[hypervisor]" : "<not found>");
@@ -902,16 +902,14 @@ bool sample_addr_correlates_sym(struct perf_event_attr *attr)
 
 void perf_event__preprocess_sample_addr(union perf_event *event,
 					struct perf_sample *sample,
-					struct machine *machine,
 					struct thread *thread,
 					struct addr_location *al)
 {
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      sample->addr, al);
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->addr, al);
 	if (!al->map)
-		thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE,
+		thread__find_addr_map(thread, cpumode, MAP__VARIABLE,
 				      sample->addr, al);
 
 	al->cpu = sample->cpu;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 5699e7e..8c7fe9d 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -187,6 +187,7 @@ enum perf_user_event_type { /* above any possible kernel type */
 	PERF_RECORD_HEADER_TRACING_DATA		= 66,
 	PERF_RECORD_HEADER_BUILD_ID		= 67,
 	PERF_RECORD_FINISHED_ROUND		= 68,
+	PERF_RECORD_ID_INDEX			= 69,
 	PERF_RECORD_HEADER_MAX
 };
 
@@ -239,6 +240,19 @@ struct tracing_data_event {
 	u32 size;
 };
 
+struct id_index_entry {
+	u64 id;
+	u64 idx;
+	u64 cpu;
+	u64 tid;
+};
+
+struct id_index_event {
+	struct perf_event_header header;
+	u64 nr;
+	struct id_index_entry entries[0];
+};
+
 union perf_event {
 	struct perf_event_header	header;
 	struct mmap_event		mmap;
@@ -253,6 +267,7 @@ union perf_event {
 	struct event_type_event		event_type;
 	struct tracing_data_event	tracing_data;
 	struct build_id_event		build_id;
+	struct id_index_event		id_index;
 };
 
 void perf_event__print_totals(void);
@@ -322,7 +337,6 @@ bool is_bts_event(struct perf_event_attr *attr);
 bool sample_addr_correlates_sym(struct perf_event_attr *attr);
 void perf_event__preprocess_sample_addr(union perf_event *event,
 					struct perf_sample *sample,
-					struct machine *machine,
 					struct thread *thread,
 					struct addr_location *al);
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 3c9e77d..7e23dae 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -413,7 +413,7 @@ int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 	int nfds = 0;
 	struct perf_evsel *evsel;
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		if (evsel->system_wide)
 			nfds += nr_cpus;
 		else
@@ -527,6 +527,22 @@ static int perf_evlist__id_add_fd(struct perf_evlist *evlist,
 	return 0;
 }
 
+static void perf_evlist__set_sid_idx(struct perf_evlist *evlist,
+				     struct perf_evsel *evsel, int idx, int cpu,
+				     int thread)
+{
+	struct perf_sample_id *sid = SID(evsel, cpu, thread);
+	sid->idx = idx;
+	if (evlist->cpus && cpu >= 0)
+		sid->cpu = evlist->cpus->map[cpu];
+	else
+		sid->cpu = -1;
+	if (!evsel->system_wide && evlist->threads && thread >= 0)
+		sid->tid = evlist->threads->map[thread];
+	else
+		sid->tid = -1;
+}
+
 struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id)
 {
 	struct hlist_head *head;
@@ -805,9 +821,13 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 			return -1;
 		}
 
-		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
-		    perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
-			return -1;
+		if (evsel->attr.read_format & PERF_FORMAT_ID) {
+			if (perf_evlist__id_add_fd(evlist, evsel, cpu, thread,
+						   fd) < 0)
+				return -1;
+			perf_evlist__set_sid_idx(evlist, evsel, idx, cpu,
+						 thread);
+		}
 	}
 
 	return 0;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 163c560..9797909 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -36,6 +36,9 @@ struct perf_sample_id {
 	struct hlist_node 	node;
 	u64		 	id;
 	struct perf_evsel	*evsel;
+	int			idx;
+	int			cpu;
+	pid_t			tid;
 
 	/* Holds total ID period value for PERF_SAMPLE_READ processing. */
 	u64			period;
@@ -54,6 +57,7 @@ struct cgroup_sel;
  * @is_pos: the position (counting backwards) of the event id (PERF_SAMPLE_ID or
  *          PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if sample_id_all
  *          is used there is an id sample appended to non-sample events
+ * @priv:   And what is in its containing unnamed union are tool specific
  */
 struct perf_evsel {
 	struct list_head	node;
@@ -73,6 +77,7 @@ struct perf_evsel {
 	union {
 		void		*priv;
 		off_t		id_offset;
+		u64		db_id;
 	};
 	struct cgroup_sel	*cgrp;
 	void			*handler;
diff --git a/tools/perf/util/find-vdso-map.c b/tools/perf/util/find-vdso-map.c
new file mode 100644
index 0000000..95ef1cf
--- /dev/null
+++ b/tools/perf/util/find-vdso-map.c
@@ -0,0 +1,30 @@
+static int find_vdso_map(void **start, void **end)
+{
+	FILE *maps;
+	char line[128];
+	int found = 0;
+
+	maps = fopen("/proc/self/maps", "r");
+	if (!maps) {
+		fprintf(stderr, "vdso: cannot open maps\n");
+		return -1;
+	}
+
+	while (!found && fgets(line, sizeof(line), maps)) {
+		int m = -1;
+
+		/* We care only about private r-x mappings. */
+		if (2 != sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n",
+				start, end, &m))
+			continue;
+		if (m < 0)
+			continue;
+
+		if (!strncmp(&line[m], VDSO__MAP_NAME,
+			     sizeof(VDSO__MAP_NAME) - 1))
+			found = 1;
+	}
+
+	fclose(maps);
+	return !found;
+}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 26f5b2f..0ecf4a3 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -601,8 +601,10 @@ static int __write_cpudesc(int fd, const char *cpuinfo_proc)
 			break;
 	}
 
-	if (ret)
+	if (ret) {
+		ret = -1;
 		goto done;
+	}
 
 	s = buf;
 
@@ -965,7 +967,8 @@ static int write_total_mem(int fd, struct perf_header *h __maybe_unused,
 		n = sscanf(buf, "%*s %"PRIu64, &mem);
 		if (n == 1)
 			ret = do_write(fd, &mem, sizeof(mem));
-	}
+	} else
+		ret = -1;
 	free(buf);
 	fclose(fp);
 	return ret;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 34fc7c8..51a6303 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -21,7 +21,7 @@ static void dsos__init(struct dsos *dsos)
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 {
-	map_groups__init(&machine->kmaps);
+	map_groups__init(&machine->kmaps, machine);
 	RB_CLEAR_NODE(&machine->rb_node);
 	dsos__init(&machine->user_dsos);
 	dsos__init(&machine->kernel_dsos);
@@ -32,7 +32,6 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 	machine->vdso_info = NULL;
 
-	machine->kmaps.machine = machine;
 	machine->pid = pid;
 
 	machine->symbol_filter = NULL;
@@ -319,7 +318,7 @@ static void machine__update_thread_pid(struct machine *machine,
 		goto out_err;
 
 	if (!leader->mg)
-		leader->mg = map_groups__new();
+		leader->mg = map_groups__new(machine);
 
 	if (!leader->mg)
 		goto out_err;
@@ -1290,7 +1289,7 @@ static bool symbol__match_regex(struct symbol *sym, regex_t *regex)
 	return 0;
 }
 
-static void ip__resolve_ams(struct machine *machine, struct thread *thread,
+static void ip__resolve_ams(struct thread *thread,
 			    struct addr_map_symbol *ams,
 			    u64 ip)
 {
@@ -1304,7 +1303,7 @@ static void ip__resolve_ams(struct machine *machine, struct thread *thread,
 	 * Thus, we have to try consecutively until we find a match
 	 * or else, the symbol is unknown
 	 */
-	thread__find_cpumode_addr_location(thread, machine, MAP__FUNCTION, ip, &al);
+	thread__find_cpumode_addr_location(thread, MAP__FUNCTION, ip, &al);
 
 	ams->addr = ip;
 	ams->al_addr = al.addr;
@@ -1312,23 +1311,21 @@ static void ip__resolve_ams(struct machine *machine, struct thread *thread,
 	ams->map = al.map;
 }
 
-static void ip__resolve_data(struct machine *machine, struct thread *thread,
+static void ip__resolve_data(struct thread *thread,
 			     u8 m, struct addr_map_symbol *ams, u64 addr)
 {
 	struct addr_location al;
 
 	memset(&al, 0, sizeof(al));
 
-	thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr,
-				   &al);
+	thread__find_addr_location(thread, m, MAP__VARIABLE, addr, &al);
 	if (al.map == NULL) {
 		/*
 		 * some shared data regions have execute bit set which puts
 		 * their mapping in the MAP__FUNCTION type array.
 		 * Check there as a fallback option before dropping the sample.
 		 */
-		thread__find_addr_location(thread, machine, m, MAP__FUNCTION, addr,
-					   &al);
+		thread__find_addr_location(thread, m, MAP__FUNCTION, addr, &al);
 	}
 
 	ams->addr = addr;
@@ -1345,9 +1342,8 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
 	if (!mi)
 		return NULL;
 
-	ip__resolve_ams(al->machine, al->thread, &mi->iaddr, sample->ip);
-	ip__resolve_data(al->machine, al->thread, al->cpumode,
-			 &mi->daddr, sample->addr);
+	ip__resolve_ams(al->thread, &mi->iaddr, sample->ip);
+	ip__resolve_data(al->thread, al->cpumode, &mi->daddr, sample->addr);
 	mi->data_src.val = sample->data_src;
 
 	return mi;
@@ -1364,15 +1360,14 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
 		return NULL;
 
 	for (i = 0; i < bs->nr; i++) {
-		ip__resolve_ams(al->machine, al->thread, &bi[i].to, bs->entries[i].to);
-		ip__resolve_ams(al->machine, al->thread, &bi[i].from, bs->entries[i].from);
+		ip__resolve_ams(al->thread, &bi[i].to, bs->entries[i].to);
+		ip__resolve_ams(al->thread, &bi[i].from, bs->entries[i].from);
 		bi[i].flags = bs->entries[i].flags;
 	}
 	return bi;
 }
 
-static int machine__resolve_callchain_sample(struct machine *machine,
-					     struct thread *thread,
+static int thread__resolve_callchain_sample(struct thread *thread,
 					     struct ip_callchain *chain,
 					     struct symbol **parent,
 					     struct addr_location *root_al,
@@ -1396,7 +1391,7 @@ static int machine__resolve_callchain_sample(struct machine *machine,
 	 * Based on DWARF debug information, some architectures skip
 	 * a callchain entry saved by the kernel.
 	 */
-	skip_idx = arch_skip_callchain_idx(machine, thread, chain);
+	skip_idx = arch_skip_callchain_idx(thread, chain);
 
 	for (i = 0; i < chain_nr; i++) {
 		u64 ip;
@@ -1438,7 +1433,7 @@ static int machine__resolve_callchain_sample(struct machine *machine,
 		}
 
 		al.filtered = 0;
-		thread__find_addr_location(thread, machine, cpumode,
+		thread__find_addr_location(thread, cpumode,
 					   MAP__FUNCTION, ip, &al);
 		if (al.sym != NULL) {
 			if (sort__has_parent && !*parent &&
@@ -1469,19 +1464,15 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 				       entry->map, entry->sym);
 }
 
-int machine__resolve_callchain(struct machine *machine,
-			       struct perf_evsel *evsel,
-			       struct thread *thread,
-			       struct perf_sample *sample,
-			       struct symbol **parent,
-			       struct addr_location *root_al,
-			       int max_stack)
+int thread__resolve_callchain(struct thread *thread,
+			      struct perf_evsel *evsel,
+			      struct perf_sample *sample,
+			      struct symbol **parent,
+			      struct addr_location *root_al,
+			      int max_stack)
 {
-	int ret;
-
-	ret = machine__resolve_callchain_sample(machine, thread,
-						sample->callchain, parent,
-						root_al, max_stack);
+	int ret = thread__resolve_callchain_sample(thread, sample->callchain,
+						   parent, root_al, max_stack);
 	if (ret)
 		return ret;
 
@@ -1495,7 +1486,7 @@ int machine__resolve_callchain(struct machine *machine,
 	    (!sample->user_stack.size))
 		return 0;
 
-	return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
+	return unwind__get_entries(unwind_entry, &callchain_cursor,
 				   thread, sample, max_stack);
 
 }
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 2b651a7..e8b7779 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -40,6 +40,10 @@ struct machine {
 	u64		  kernel_start;
 	symbol_filter_t	  symbol_filter;
 	pid_t		  *current_tid;
+	union { /* Tool specific area */
+		void	  *priv;
+		u64	  db_id;
+	};
 };
 
 static inline
@@ -122,13 +126,12 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
 					   struct addr_location *al);
 struct mem_info *sample__resolve_mem(struct perf_sample *sample,
 				     struct addr_location *al);
-int machine__resolve_callchain(struct machine *machine,
-			       struct perf_evsel *evsel,
-			       struct thread *thread,
-			       struct perf_sample *sample,
-			       struct symbol **parent,
-			       struct addr_location *root_al,
-			       int max_stack);
+int thread__resolve_callchain(struct thread *thread,
+			      struct perf_evsel *evsel,
+			      struct perf_sample *sample,
+			      struct symbol **parent,
+			      struct addr_location *root_al,
+			      int max_stack);
 
 /*
  * Default guest kernel is defined by parameter --guestkallsyms
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 2137c45..040a785 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -413,14 +413,14 @@ u64 map__objdump_2mem(struct map *map, u64 ip)
 	return ip + map->reloc;
 }
 
-void map_groups__init(struct map_groups *mg)
+void map_groups__init(struct map_groups *mg, struct machine *machine)
 {
 	int i;
 	for (i = 0; i < MAP__NR_TYPES; ++i) {
 		mg->maps[i] = RB_ROOT;
 		INIT_LIST_HEAD(&mg->removed_maps[i]);
 	}
-	mg->machine = NULL;
+	mg->machine = machine;
 	mg->refcnt = 1;
 }
 
@@ -471,12 +471,12 @@ bool map_groups__empty(struct map_groups *mg)
 	return true;
 }
 
-struct map_groups *map_groups__new(void)
+struct map_groups *map_groups__new(struct machine *machine)
 {
 	struct map_groups *mg = malloc(sizeof(*mg));
 
 	if (mg != NULL)
-		map_groups__init(mg);
+		map_groups__init(mg, machine);
 
 	return mg;
 }
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 2f83954..6951a9d 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -64,7 +64,7 @@ struct map_groups {
 	int		 refcnt;
 };
 
-struct map_groups *map_groups__new(void);
+struct map_groups *map_groups__new(struct machine *machine);
 void map_groups__delete(struct map_groups *mg);
 bool map_groups__empty(struct map_groups *mg);
 
@@ -150,7 +150,7 @@ void maps__remove(struct rb_root *maps, struct map *map);
 struct map *maps__find(struct rb_root *maps, u64 addr);
 struct map *maps__first(struct rb_root *maps);
 struct map *maps__next(struct map *map);
-void map_groups__init(struct map_groups *mg);
+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,
 		      struct map_groups *parent, enum map_type type);
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index bf48092..f62dee7b 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -42,7 +42,26 @@ static int get_value(struct parse_opt_ctx_t *p,
 		return opterror(opt, "takes no value", flags);
 	if (unset && (opt->flags & PARSE_OPT_NONEG))
 		return opterror(opt, "isn't available", flags);
-
+	if (opt->flags & PARSE_OPT_DISABLED)
+		return opterror(opt, "is not usable", flags);
+
+	if (opt->flags & PARSE_OPT_EXCLUSIVE) {
+		if (p->excl_opt) {
+			char msg[128];
+
+			if (((flags & OPT_SHORT) && p->excl_opt->short_name) ||
+			    p->excl_opt->long_name == NULL) {
+				scnprintf(msg, sizeof(msg), "cannot be used with switch `%c'",
+					  p->excl_opt->short_name);
+			} else {
+				scnprintf(msg, sizeof(msg), "cannot be used with %s",
+					  p->excl_opt->long_name);
+			}
+			opterror(opt, msg, flags);
+			return -3;
+		}
+		p->excl_opt = opt;
+	}
 	if (!(flags & OPT_SHORT) && p->opt) {
 		switch (opt->type) {
 		case OPTION_CALLBACK:
@@ -343,13 +362,14 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 		       const char * const usagestr[])
 {
 	int internal_help = !(ctx->flags & PARSE_OPT_NO_INTERNAL_HELP);
+	int excl_short_opt = 1;
+	const char *arg;
 
 	/* we must reset ->opt, unknown short option leave it dangling */
 	ctx->opt = NULL;
 
 	for (; ctx->argc; ctx->argc--, ctx->argv++) {
-		const char *arg = ctx->argv[0];
-
+		arg = ctx->argv[0];
 		if (*arg != '-' || !arg[1]) {
 			if (ctx->flags & PARSE_OPT_STOP_AT_NON_OPTION)
 				break;
@@ -358,19 +378,21 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 		}
 
 		if (arg[1] != '-') {
-			ctx->opt = arg + 1;
+			ctx->opt = ++arg;
 			if (internal_help && *ctx->opt == 'h')
 				return usage_with_options_internal(usagestr, options, 0);
 			switch (parse_short_opt(ctx, options)) {
 			case -1:
-				return parse_options_usage(usagestr, options, arg + 1, 1);
+				return parse_options_usage(usagestr, options, arg, 1);
 			case -2:
 				goto unknown;
+			case -3:
+				goto exclusive;
 			default:
 				break;
 			}
 			if (ctx->opt)
-				check_typos(arg + 1, options);
+				check_typos(arg, options);
 			while (ctx->opt) {
 				if (internal_help && *ctx->opt == 'h')
 					return usage_with_options_internal(usagestr, options, 0);
@@ -387,6 +409,8 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 					ctx->argv[0] = strdup(ctx->opt - 1);
 					*(char *)ctx->argv[0] = '-';
 					goto unknown;
+				case -3:
+					goto exclusive;
 				default:
 					break;
 				}
@@ -402,19 +426,23 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 			break;
 		}
 
-		if (internal_help && !strcmp(arg + 2, "help-all"))
+		arg += 2;
+		if (internal_help && !strcmp(arg, "help-all"))
 			return usage_with_options_internal(usagestr, options, 1);
-		if (internal_help && !strcmp(arg + 2, "help"))
+		if (internal_help && !strcmp(arg, "help"))
 			return usage_with_options_internal(usagestr, options, 0);
-		if (!strcmp(arg + 2, "list-opts"))
+		if (!strcmp(arg, "list-opts"))
 			return PARSE_OPT_LIST_OPTS;
-		if (!strcmp(arg + 2, "list-cmds"))
+		if (!strcmp(arg, "list-cmds"))
 			return PARSE_OPT_LIST_SUBCMDS;
-		switch (parse_long_opt(ctx, arg + 2, options)) {
+		switch (parse_long_opt(ctx, arg, options)) {
 		case -1:
-			return parse_options_usage(usagestr, options, arg + 2, 0);
+			return parse_options_usage(usagestr, options, arg, 0);
 		case -2:
 			goto unknown;
+		case -3:
+			excl_short_opt = 0;
+			goto exclusive;
 		default:
 			break;
 		}
@@ -426,6 +454,17 @@ unknown:
 		ctx->opt = NULL;
 	}
 	return PARSE_OPT_DONE;
+
+exclusive:
+	parse_options_usage(usagestr, options, arg, excl_short_opt);
+	if ((excl_short_opt && ctx->excl_opt->short_name) ||
+	    ctx->excl_opt->long_name == NULL) {
+		char opt = ctx->excl_opt->short_name;
+		parse_options_usage(NULL, options, &opt, 1);
+	} else {
+		parse_options_usage(NULL, options, ctx->excl_opt->long_name, 0);
+	}
+	return PARSE_OPT_HELP;
 }
 
 int parse_options_end(struct parse_opt_ctx_t *ctx)
@@ -509,6 +548,8 @@ static void print_option_help(const struct option *opts, int full)
 	}
 	if (!full && (opts->flags & PARSE_OPT_HIDDEN))
 		return;
+	if (opts->flags & PARSE_OPT_DISABLED)
+		return;
 
 	pos = fprintf(stderr, "    ");
 	if (opts->short_name)
@@ -679,3 +720,16 @@ int parse_opt_verbosity_cb(const struct option *opt,
 	}
 	return 0;
 }
+
+void set_option_flag(struct option *opts, int shortopt, const char *longopt,
+		     int flag)
+{
+	for (; opts->type != OPTION_END; opts++) {
+		if ((shortopt && opts->short_name == shortopt) ||
+		    (opts->long_name && longopt &&
+		     !strcmp(opts->long_name, longopt))) {
+			opts->flags |= flag;
+			break;
+		}
+	}
+}
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index b59ba85..97b153f 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -38,6 +38,8 @@ enum parse_opt_option_flags {
 	PARSE_OPT_NONEG   = 4,
 	PARSE_OPT_HIDDEN  = 8,
 	PARSE_OPT_LASTARG_DEFAULT = 16,
+	PARSE_OPT_DISABLED = 32,
+	PARSE_OPT_EXCLUSIVE = 64,
 };
 
 struct option;
@@ -173,6 +175,7 @@ struct parse_opt_ctx_t {
 	const char **out;
 	int argc, cpidx;
 	const char *opt;
+	const struct option *excl_opt;
 	int flags;
 };
 
@@ -211,4 +214,5 @@ extern int parse_opt_verbosity_cb(const struct option *, const char *, int);
 
 extern const char *parse_options_fix_filename(const char *prefix, const char *file);
 
+void set_option_flag(struct option *opts, int sopt, const char *lopt, int flag);
 #endif /* __PERF_PARSE_OPTIONS_H */
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index e243ad9..881b754 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -747,15 +747,18 @@ void print_pmu_events(const char *event_glob, bool name_only)
 
 	pmu = NULL;
 	len = 0;
-	while ((pmu = perf_pmu__scan(pmu)) != NULL)
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
 		list_for_each_entry(alias, &pmu->aliases, list)
 			len++;
-	aliases = malloc(sizeof(char *) * len);
+		if (pmu->selectable)
+			len++;
+	}
+	aliases = zalloc(sizeof(char *) * len);
 	if (!aliases)
-		return;
+		goto out_enomem;
 	pmu = NULL;
 	j = 0;
-	while ((pmu = perf_pmu__scan(pmu)) != NULL)
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
 		list_for_each_entry(alias, &pmu->aliases, list) {
 			char *name = format_alias(buf, sizeof(buf), pmu, alias);
 			bool is_cpu = !strcmp(pmu->name, "cpu");
@@ -765,13 +768,23 @@ void print_pmu_events(const char *event_glob, bool name_only)
 			      (!is_cpu && strglobmatch(alias->name,
 						       event_glob))))
 				continue;
-			aliases[j] = name;
+
 			if (is_cpu && !name_only)
-				aliases[j] = format_alias_or(buf, sizeof(buf),
-							      pmu, alias);
-			aliases[j] = strdup(aliases[j]);
+				name = format_alias_or(buf, sizeof(buf), pmu, alias);
+
+			aliases[j] = strdup(name);
+			if (aliases[j] == NULL)
+				goto out_enomem;
 			j++;
 		}
+		if (pmu->selectable) {
+			char *s;
+			if (asprintf(&s, "%s//", pmu->name) < 0)
+				goto out_enomem;
+			aliases[j] = s;
+			j++;
+		}
+	}
 	len = j;
 	qsort(aliases, len, sizeof(char *), cmp_string);
 	for (j = 0; j < len; j++) {
@@ -780,12 +793,20 @@ void print_pmu_events(const char *event_glob, bool name_only)
 			continue;
 		}
 		printf("  %-50s [Kernel PMU event]\n", aliases[j]);
-		zfree(&aliases[j]);
 		printed++;
 	}
 	if (printed)
 		printf("\n");
-	free(aliases);
+out_free:
+	for (j = 0; j < len; j++)
+		zfree(&aliases[j]);
+	zfree(&aliases);
+	return;
+
+out_enomem:
+	printf("FATAL: not enough memory to print PMU events\n");
+	if (aliases)
+		goto out_free;
 }
 
 bool pmu_have_event(const char *pname, const char *name)
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index fe9dfbe..8092de7 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -18,6 +18,7 @@ struct perf_event_attr;
 struct perf_pmu {
 	char *name;
 	__u32 type;
+	bool selectable;
 	struct perf_event_attr *default_config;
 	struct cpu_map *cpus;
 	struct list_head format;  /* HEAD struct perf_pmu_format -> list */
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index c150ca4..28eb141 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1910,21 +1910,21 @@ static int show_perf_probe_event(struct perf_probe_event *pev,
 	if (ret < 0)
 		return ret;
 
-	printf("  %-20s (on %s", buf, place);
+	pr_info("  %-20s (on %s", buf, place);
 	if (module)
-		printf(" in %s", module);
+		pr_info(" in %s", module);
 
 	if (pev->nargs > 0) {
-		printf(" with");
+		pr_info(" with");
 		for (i = 0; i < pev->nargs; i++) {
 			ret = synthesize_perf_probe_arg(&pev->args[i],
 							buf, 128);
 			if (ret < 0)
 				break;
-			printf(" %s", buf);
+			pr_info(" %s", buf);
 		}
 	}
-	printf(")\n");
+	pr_info(")\n");
 	free(place);
 	return ret;
 }
@@ -2124,7 +2124,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 	}
 
 	ret = 0;
-	printf("Added new event%s\n", (ntevs > 1) ? "s:" : ":");
+	pr_info("Added new event%s\n", (ntevs > 1) ? "s:" : ":");
 	for (i = 0; i < ntevs; i++) {
 		tev = &tevs[i];
 		if (pev->event)
@@ -2179,8 +2179,8 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 
 	if (ret >= 0) {
 		/* Show how to use the event. */
-		printf("\nYou can now use it in all perf tools, such as:\n\n");
-		printf("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group,
+		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", tev->group,
 			 tev->event);
 	}
 
@@ -2444,7 +2444,7 @@ static int __del_trace_probe_event(int fd, struct str_node *ent)
 		goto error;
 	}
 
-	printf("Removed event: %s\n", ent->s);
+	pr_info("Removed event: %s\n", ent->s);
 	return 0;
 error:
 	pr_warning("Failed to delete event: %s\n",
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 496f21c..2fd7ee8 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -24,6 +24,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <stdbool.h>
 #include <errno.h>
 
 #include "../../perf.h"
@@ -33,6 +34,9 @@
 #include "../util.h"
 #include "../event.h"
 #include "../thread.h"
+#include "../comm.h"
+#include "../machine.h"
+#include "../db-export.h"
 #include "../trace-event.h"
 #include "../machine.h"
 
@@ -53,6 +57,21 @@ static int zero_flag_atom;
 
 static PyObject *main_module, *main_dict;
 
+struct tables {
+	struct db_export	dbe;
+	PyObject		*evsel_handler;
+	PyObject		*machine_handler;
+	PyObject		*thread_handler;
+	PyObject		*comm_handler;
+	PyObject		*comm_thread_handler;
+	PyObject		*dso_handler;
+	PyObject		*symbol_handler;
+	PyObject		*sample_handler;
+	bool			db_export_mode;
+};
+
+static struct tables tables_global;
+
 static void handler_call_die(const char *handler_name) NORETURN;
 static void handler_call_die(const char *handler_name)
 {
@@ -312,9 +331,9 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
 	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) {
+	if (thread__resolve_callchain(al->thread, evsel,
+				      sample, NULL, NULL,
+				      PERF_MAX_STACK_DEPTH) != 0) {
 		pr_err("Failed to resolve callchain. Skipping\n");
 		goto exit;
 	}
@@ -475,6 +494,211 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	Py_DECREF(t);
 }
 
+static PyObject *tuple_new(unsigned int sz)
+{
+	PyObject *t;
+
+	t = PyTuple_New(sz);
+	if (!t)
+		Py_FatalError("couldn't create Python tuple");
+	return t;
+}
+
+static int tuple_set_u64(PyObject *t, unsigned int pos, u64 val)
+{
+#if BITS_PER_LONG == 64
+	return PyTuple_SetItem(t, pos, PyInt_FromLong(val));
+#endif
+#if BITS_PER_LONG == 32
+	return PyTuple_SetItem(t, pos, PyLong_FromLongLong(val));
+#endif
+}
+
+static int tuple_set_s32(PyObject *t, unsigned int pos, s32 val)
+{
+	return PyTuple_SetItem(t, pos, PyInt_FromLong(val));
+}
+
+static int tuple_set_string(PyObject *t, unsigned int pos, const char *s)
+{
+	return PyTuple_SetItem(t, pos, PyString_FromString(s));
+}
+
+static int python_export_evsel(struct db_export *dbe, struct perf_evsel *evsel)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(2);
+
+	tuple_set_u64(t, 0, evsel->db_id);
+	tuple_set_string(t, 1, perf_evsel__name(evsel));
+
+	call_object(tables->evsel_handler, t, "evsel_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_machine(struct db_export *dbe,
+				 struct machine *machine)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(3);
+
+	tuple_set_u64(t, 0, machine->db_id);
+	tuple_set_s32(t, 1, machine->pid);
+	tuple_set_string(t, 2, machine->root_dir ? machine->root_dir : "");
+
+	call_object(tables->machine_handler, t, "machine_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_thread(struct db_export *dbe, struct thread *thread,
+				u64 main_thread_db_id, struct machine *machine)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(5);
+
+	tuple_set_u64(t, 0, thread->db_id);
+	tuple_set_u64(t, 1, machine->db_id);
+	tuple_set_u64(t, 2, main_thread_db_id);
+	tuple_set_s32(t, 3, thread->pid_);
+	tuple_set_s32(t, 4, thread->tid);
+
+	call_object(tables->thread_handler, t, "thread_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_comm(struct db_export *dbe, struct comm *comm)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(2);
+
+	tuple_set_u64(t, 0, comm->db_id);
+	tuple_set_string(t, 1, comm__str(comm));
+
+	call_object(tables->comm_handler, t, "comm_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_comm_thread(struct db_export *dbe, u64 db_id,
+				     struct comm *comm, struct thread *thread)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(3);
+
+	tuple_set_u64(t, 0, db_id);
+	tuple_set_u64(t, 1, comm->db_id);
+	tuple_set_u64(t, 2, thread->db_id);
+
+	call_object(tables->comm_thread_handler, t, "comm_thread_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_dso(struct db_export *dbe, struct dso *dso,
+			     struct machine *machine)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+	PyObject *t;
+
+	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
+
+	t = tuple_new(5);
+
+	tuple_set_u64(t, 0, dso->db_id);
+	tuple_set_u64(t, 1, machine->db_id);
+	tuple_set_string(t, 2, dso->short_name);
+	tuple_set_string(t, 3, dso->long_name);
+	tuple_set_string(t, 4, sbuild_id);
+
+	call_object(tables->dso_handler, t, "dso_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_symbol(struct db_export *dbe, struct symbol *sym,
+				struct dso *dso)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	u64 *sym_db_id = symbol__priv(sym);
+	PyObject *t;
+
+	t = tuple_new(6);
+
+	tuple_set_u64(t, 0, *sym_db_id);
+	tuple_set_u64(t, 1, dso->db_id);
+	tuple_set_u64(t, 2, sym->start);
+	tuple_set_u64(t, 3, sym->end);
+	tuple_set_s32(t, 4, sym->binding);
+	tuple_set_string(t, 5, sym->name);
+
+	call_object(tables->symbol_handler, t, "symbol_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_sample(struct db_export *dbe,
+				struct export_sample *es)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(19);
+
+	tuple_set_u64(t, 0, es->db_id);
+	tuple_set_u64(t, 1, es->evsel->db_id);
+	tuple_set_u64(t, 2, es->al->machine->db_id);
+	tuple_set_u64(t, 3, es->thread->db_id);
+	tuple_set_u64(t, 4, es->comm_db_id);
+	tuple_set_u64(t, 5, es->dso_db_id);
+	tuple_set_u64(t, 6, es->sym_db_id);
+	tuple_set_u64(t, 7, es->offset);
+	tuple_set_u64(t, 8, es->sample->ip);
+	tuple_set_u64(t, 9, es->sample->time);
+	tuple_set_s32(t, 10, es->sample->cpu);
+	tuple_set_u64(t, 11, es->addr_dso_db_id);
+	tuple_set_u64(t, 12, es->addr_sym_db_id);
+	tuple_set_u64(t, 13, es->addr_offset);
+	tuple_set_u64(t, 14, es->sample->addr);
+	tuple_set_u64(t, 15, es->sample->period);
+	tuple_set_u64(t, 16, es->sample->weight);
+	tuple_set_u64(t, 17, es->sample->transaction);
+	tuple_set_u64(t, 18, es->sample->data_src);
+
+	call_object(tables->sample_handler, t, "sample_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
 static void python_process_general_event(struct perf_sample *sample,
 					 struct perf_evsel *evsel,
 					 struct thread *thread,
@@ -551,19 +775,25 @@ exit:
 	Py_DECREF(t);
 }
 
-static void python_process_event(union perf_event *event __maybe_unused,
+static void python_process_event(union perf_event *event,
 				 struct perf_sample *sample,
 				 struct perf_evsel *evsel,
 				 struct thread *thread,
 				 struct addr_location *al)
 {
+	struct tables *tables = &tables_global;
+
 	switch (evsel->attr.type) {
 	case PERF_TYPE_TRACEPOINT:
 		python_process_tracepoint(sample, evsel, thread, al);
 		break;
 	/* Reserve for future process_hw/sw/raw APIs */
 	default:
-		python_process_general_event(sample, evsel, thread, al);
+		if (tables->db_export_mode)
+			db_export__sample(&tables->dbe, event, sample, evsel,
+					  thread, al);
+		else
+			python_process_general_event(sample, evsel, thread, al);
 	}
 }
 
@@ -589,11 +819,57 @@ error:
 	return -1;
 }
 
+#define SET_TABLE_HANDLER_(name, handler_name, table_name) do {		\
+	tables->handler_name = get_handler(#table_name);		\
+	if (tables->handler_name)					\
+		tables->dbe.export_ ## name = python_export_ ## name;	\
+} while (0)
+
+#define SET_TABLE_HANDLER(name) \
+	SET_TABLE_HANDLER_(name, name ## _handler, name ## _table)
+
+static void set_table_handlers(struct tables *tables)
+{
+	const char *perf_db_export_mode = "perf_db_export_mode";
+	PyObject *db_export_mode;
+	int ret;
+
+	memset(tables, 0, sizeof(struct tables));
+	if (db_export__init(&tables->dbe))
+		Py_FatalError("failed to initialize export");
+
+	db_export_mode = PyDict_GetItemString(main_dict, perf_db_export_mode);
+	if (!db_export_mode)
+		return;
+
+	ret = PyObject_IsTrue(db_export_mode);
+	if (ret == -1)
+		handler_call_die(perf_db_export_mode);
+	if (!ret)
+		return;
+
+	tables->db_export_mode = true;
+	/*
+	 * Reserve per symbol space for symbol->db_id via symbol__priv()
+	 */
+	symbol_conf.priv_size = sizeof(u64);
+
+	SET_TABLE_HANDLER(evsel);
+	SET_TABLE_HANDLER(machine);
+	SET_TABLE_HANDLER(thread);
+	SET_TABLE_HANDLER(comm);
+	SET_TABLE_HANDLER(comm_thread);
+	SET_TABLE_HANDLER(dso);
+	SET_TABLE_HANDLER(symbol);
+	SET_TABLE_HANDLER(sample);
+}
+
 /*
  * Start trace script
  */
 static int python_start_script(const char *script, int argc, const char **argv)
 {
+	struct tables *tables = &tables_global;
 	const char **command_line;
 	char buf[PATH_MAX];
 	int i, err = 0;
@@ -632,6 +908,8 @@ static int python_start_script(const char *script, int argc, const char **argv)
 
 	free(command_line);
 
+	set_table_handlers(tables);
+
 	return err;
 error:
 	Py_Finalize();
@@ -650,8 +928,12 @@ static int python_flush_script(void)
  */
 static int python_stop_script(void)
 {
+	struct tables *tables = &tables_global;
+
 	try_call_object("trace_end", NULL);
 
+	db_export__exit(&tables->dbe);
+
 	Py_XDECREF(main_dict);
 	Py_XDECREF(main_module);
 	Py_Finalize();
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 6702ac2..f4478ce 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -228,6 +228,15 @@ static int process_finished_round(struct perf_tool *tool,
 				  union perf_event *event,
 				  struct perf_session *session);
 
+static int process_id_index_stub(struct perf_tool *tool __maybe_unused,
+				 union perf_event *event __maybe_unused,
+				 struct perf_session *perf_session
+				 __maybe_unused)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
 void perf_tool__fill_defaults(struct perf_tool *tool)
 {
 	if (tool->sample == NULL)
@@ -262,6 +271,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		else
 			tool->finished_round = process_finished_round_stub;
 	}
+	if (tool->id_index == NULL)
+		tool->id_index = process_id_index_stub;
 }
  
 static void swap_sample_id_all(union perf_event *event, void *data)
@@ -460,6 +471,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
 	[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
 	[PERF_RECORD_HEADER_BUILD_ID]	  = NULL,
+	[PERF_RECORD_ID_INDEX]		  = perf_event__all64_swap,
 	[PERF_RECORD_HEADER_MAX]	  = NULL,
 };
 
@@ -888,11 +900,26 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 		return tool->build_id(tool, event, session);
 	case PERF_RECORD_FINISHED_ROUND:
 		return tool->finished_round(tool, event, session);
+	case PERF_RECORD_ID_INDEX:
+		return tool->id_index(tool, event, session);
 	default:
 		return -EINVAL;
 	}
 }
 
+int perf_session__deliver_synth_event(struct perf_session *session,
+				      union perf_event *event,
+				      struct perf_sample *sample,
+				      struct perf_tool *tool)
+{
+	events_stats__inc(&session->stats, event->header.type);
+
+	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
+		return perf_session__process_user_event(session, event, tool, 0);
+
+	return perf_session__deliver_event(session, event, sample, tool, 0);
+}
+
 static void event_swap(union perf_event *event, bool sample_id_all)
 {
 	perf_event__swap_op swap;
@@ -1417,9 +1444,9 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
 	if (symbol_conf.use_callchain && sample->callchain) {
 		struct addr_location node_al;
 
-		if (machine__resolve_callchain(al->machine, evsel, al->thread,
-					       sample, NULL, NULL,
-					       PERF_MAX_STACK_DEPTH) != 0) {
+		if (thread__resolve_callchain(al->thread, evsel,
+					      sample, NULL, NULL,
+					      PERF_MAX_STACK_DEPTH) != 0) {
 			if (verbose)
 				error("Failed to resolve callchain. Skipping\n");
 			return;
@@ -1594,3 +1621,111 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session,
 out:
 	return err;
 }
+
+int perf_event__process_id_index(struct perf_tool *tool __maybe_unused,
+				 union perf_event *event,
+				 struct perf_session *session)
+{
+	struct perf_evlist *evlist = session->evlist;
+	struct id_index_event *ie = &event->id_index;
+	size_t i, nr, max_nr;
+
+	max_nr = (ie->header.size - sizeof(struct id_index_event)) /
+		 sizeof(struct id_index_entry);
+	nr = ie->nr;
+	if (nr > max_nr)
+		return -EINVAL;
+
+	if (dump_trace)
+		fprintf(stdout, " nr: %zu\n", nr);
+
+	for (i = 0; i < nr; i++) {
+		struct id_index_entry *e = &ie->entries[i];
+		struct perf_sample_id *sid;
+
+		if (dump_trace) {
+			fprintf(stdout,	" ... id: %"PRIu64, e->id);
+			fprintf(stdout,	"  idx: %"PRIu64, e->idx);
+			fprintf(stdout,	"  cpu: %"PRId64, e->cpu);
+			fprintf(stdout,	"  tid: %"PRId64"\n", e->tid);
+		}
+
+		sid = perf_evlist__id2sid(evlist, e->id);
+		if (!sid)
+			return -ENOENT;
+		sid->idx = e->idx;
+		sid->cpu = e->cpu;
+		sid->tid = e->tid;
+	}
+	return 0;
+}
+
+int perf_event__synthesize_id_index(struct perf_tool *tool,
+				    perf_event__handler_t process,
+				    struct perf_evlist *evlist,
+				    struct machine *machine)
+{
+	union perf_event *ev;
+	struct perf_evsel *evsel;
+	size_t nr = 0, i = 0, sz, max_nr, n;
+	int err;
+
+	pr_debug2("Synthesizing id index\n");
+
+	max_nr = (UINT16_MAX - sizeof(struct id_index_event)) /
+		 sizeof(struct id_index_entry);
+
+	evlist__for_each(evlist, evsel)
+		nr += evsel->ids;
+
+	n = nr > max_nr ? max_nr : nr;
+	sz = sizeof(struct id_index_event) + n * sizeof(struct id_index_entry);
+	ev = zalloc(sz);
+	if (!ev)
+		return -ENOMEM;
+
+	ev->id_index.header.type = PERF_RECORD_ID_INDEX;
+	ev->id_index.header.size = sz;
+	ev->id_index.nr = n;
+
+	evlist__for_each(evlist, evsel) {
+		u32 j;
+
+		for (j = 0; j < evsel->ids; j++) {
+			struct id_index_entry *e;
+			struct perf_sample_id *sid;
+
+			if (i >= n) {
+				err = process(tool, ev, NULL, machine);
+				if (err)
+					goto out_err;
+				nr -= n;
+				i = 0;
+			}
+
+			e = &ev->id_index.entries[i++];
+
+			e->id = evsel->id[j];
+
+			sid = perf_evlist__id2sid(evlist, e->id);
+			if (!sid) {
+				free(ev);
+				return -ENOENT;
+			}
+
+			e->idx = sid->idx;
+			e->cpu = sid->cpu;
+			e->tid = sid->tid;
+		}
+	}
+
+	sz = sizeof(struct id_index_event) + nr * sizeof(struct id_index_entry);
+	ev->id_index.header.size = sz;
+	ev->id_index.nr = nr;
+
+	err = process(tool, ev, NULL, machine);
+out_err:
+	free(ev);
+
+	return err;
+}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index a4be851..dc26ebf 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -126,4 +126,19 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session,
 extern volatile int session_done;
 
 #define session_done()	ACCESS_ONCE(session_done)
+
+int perf_session__deliver_synth_event(struct perf_session *session,
+				      union perf_event *event,
+				      struct perf_sample *sample,
+				      struct perf_tool *tool);
+
+int perf_event__process_id_index(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session);
+
+int perf_event__synthesize_id_index(struct perf_tool *tool,
+				    perf_event__handler_t process,
+				    struct perf_evlist *evlist,
+				    struct machine *machine);
+
 #endif /* __PERF_SESSION_H */
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index c414117..bf5bf85 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -15,7 +15,7 @@ int thread__init_map_groups(struct thread *thread, struct machine *machine)
 	pid_t pid = thread->pid_;
 
 	if (pid == thread->tid || pid == -1) {
-		thread->mg = map_groups__new();
+		thread->mg = map_groups__new(machine);
 	} else {
 		leader = machine__findnew_thread(machine, pid, pid);
 		if (leader)
@@ -198,7 +198,6 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
 }
 
 void thread__find_cpumode_addr_location(struct thread *thread,
-					struct machine *machine,
 					enum map_type type, u64 addr,
 					struct addr_location *al)
 {
@@ -211,8 +210,7 @@ void thread__find_cpumode_addr_location(struct thread *thread,
 	};
 
 	for (i = 0; i < ARRAY_SIZE(cpumodes); i++) {
-		thread__find_addr_location(thread, machine, cpumodes[i], type,
-					   addr, al);
+		thread__find_addr_location(thread, cpumodes[i], type, addr, al);
 		if (al->map)
 			break;
 	}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 8c75fa7..d34cf5c 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -23,6 +23,7 @@ struct thread {
 	bool			dead; /* if set thread has exited */
 	struct list_head	comm_list;
 	int			comm_len;
+	u64			db_id;
 
 	void			*priv;
 };
@@ -54,16 +55,15 @@ void thread__insert_map(struct thread *thread, struct map *map);
 int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
 size_t thread__fprintf(struct thread *thread, FILE *fp);
 
-void thread__find_addr_map(struct thread *thread, struct machine *machine,
+void thread__find_addr_map(struct thread *thread,
 			   u8 cpumode, enum map_type type, u64 addr,
 			   struct addr_location *al);
 
-void thread__find_addr_location(struct thread *thread, struct machine *machine,
+void thread__find_addr_location(struct thread *thread,
 				u8 cpumode, enum map_type type, u64 addr,
 				struct addr_location *al);
 
 void thread__find_cpumode_addr_location(struct thread *thread,
-					struct machine *machine,
 					enum map_type type, u64 addr,
 					struct addr_location *al);
 
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index f116369..bb2708b 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -39,7 +39,8 @@ struct perf_tool {
 	event_attr_op	attr;
 	event_op2	tracing_data;
 	event_op2	finished_round,
-			build_id;
+			build_id,
+			id_index;
 	bool		ordered_events;
 	bool		ordering_requires_timestamps;
 };
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 7419768..2dcfe9a 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -26,7 +26,7 @@ static int __report_module(struct addr_location *al, u64 ip,
 	Dwfl_Module *mod;
 	struct dso *dso = NULL;
 
-	thread__find_addr_location(ui->thread, ui->machine,
+	thread__find_addr_location(ui->thread,
 				   PERF_RECORD_MISC_USER,
 				   MAP__FUNCTION, ip, al);
 
@@ -89,7 +89,7 @@ static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr,
 	struct addr_location al;
 	ssize_t size;
 
-	thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
 			      MAP__FUNCTION, addr, &al);
 	if (!al.map) {
 		pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
@@ -164,14 +164,14 @@ frame_callback(Dwfl_Frame *state, void *arg)
 }
 
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
-			struct machine *machine, struct thread *thread,
+			struct thread *thread,
 			struct perf_sample *data,
 			int max_stack)
 {
 	struct unwind_info ui = {
 		.sample		= data,
 		.thread		= thread,
-		.machine	= machine,
+		.machine	= thread->mg->machine,
 		.cb		= cb,
 		.arg		= arg,
 		.max_stack	= max_stack,
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 4d45c0d..371219a 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -284,7 +284,7 @@ static struct map *find_map(unw_word_t ip, struct unwind_info *ui)
 {
 	struct addr_location al;
 
-	thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
 			      MAP__FUNCTION, ip, &al);
 	return al.map;
 }
@@ -374,7 +374,7 @@ static int access_dso_mem(struct unwind_info *ui, unw_word_t addr,
 	struct addr_location al;
 	ssize_t size;
 
-	thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
 			      MAP__FUNCTION, addr, &al);
 	if (!al.map) {
 		pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
@@ -476,14 +476,13 @@ static void put_unwind_info(unw_addr_space_t __maybe_unused as,
 	pr_debug("unwind: put_unwind_info called\n");
 }
 
-static int entry(u64 ip, struct thread *thread, struct machine *machine,
+static int entry(u64 ip, struct thread *thread,
 		 unwind_entry_cb_t cb, void *arg)
 {
 	struct unwind_entry e;
 	struct addr_location al;
 
-	thread__find_addr_location(thread, machine,
-				   PERF_RECORD_MISC_USER,
+	thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
 				   MAP__FUNCTION, ip, &al);
 
 	e.ip = ip;
@@ -586,21 +585,21 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 		unw_word_t ip;
 
 		unw_get_reg(&c, UNW_REG_IP, &ip);
-		ret = ip ? entry(ip, ui->thread, ui->machine, cb, arg) : 0;
+		ret = ip ? entry(ip, ui->thread, cb, arg) : 0;
 	}
 
 	return ret;
 }
 
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
-			struct machine *machine, struct thread *thread,
+			struct thread *thread,
 			struct perf_sample *data, int max_stack)
 {
 	u64 ip;
 	struct unwind_info ui = {
 		.sample       = data,
 		.thread       = thread,
-		.machine      = machine,
+		.machine      = thread->mg->machine,
 	};
 	int ret;
 
@@ -611,7 +610,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 	if (ret)
 		return ret;
 
-	ret = entry(ip, thread, machine, cb, arg);
+	ret = entry(ip, thread, cb, arg);
 	if (ret)
 		return -ENOMEM;
 
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index f50b737..12790cf 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -16,7 +16,6 @@ typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg);
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
-			struct machine *machine,
 			struct thread *thread,
 			struct perf_sample *data, int max_stack);
 /* libunwind specific */
@@ -38,7 +37,6 @@ static inline void unwind__finish_access(struct thread *thread __maybe_unused) {
 static inline int
 unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
 		    void *arg __maybe_unused,
-		    struct machine *machine __maybe_unused,
 		    struct thread *thread __maybe_unused,
 		    struct perf_sample *data __maybe_unused,
 		    int max_stack __maybe_unused)
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index adca693..5c7dd79 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -12,9 +12,16 @@
 #include "util.h"
 #include "symbol.h"
 #include "machine.h"
+#include "thread.h"
 #include "linux/string.h"
 #include "debug.h"
 
+/*
+ * Include definition of find_vdso_map() also used in perf-read-vdso.c for
+ * building perf-read-vdso32 and perf-read-vdsox32.
+ */
+#include "find-vdso-map.c"
+
 #define VDSO__TEMP_FILE_NAME "/tmp/perf-vdso.so-XXXXXX"
 
 struct vdso_file {
@@ -22,10 +29,15 @@ struct vdso_file {
 	bool error;
 	char temp_file_name[sizeof(VDSO__TEMP_FILE_NAME)];
 	const char *dso_name;
+	const char *read_prog;
 };
 
 struct vdso_info {
 	struct vdso_file vdso;
+#if BITS_PER_LONG == 64
+	struct vdso_file vdso32;
+	struct vdso_file vdsox32;
+#endif
 };
 
 static struct vdso_info *vdso_info__new(void)
@@ -35,42 +47,23 @@ static struct vdso_info *vdso_info__new(void)
 			.temp_file_name = VDSO__TEMP_FILE_NAME,
 			.dso_name = DSO__NAME_VDSO,
 		},
+#if BITS_PER_LONG == 64
+		.vdso32  = {
+			.temp_file_name = VDSO__TEMP_FILE_NAME,
+			.dso_name = DSO__NAME_VDSO32,
+			.read_prog = "perf-read-vdso32",
+		},
+		.vdsox32  = {
+			.temp_file_name = VDSO__TEMP_FILE_NAME,
+			.dso_name = DSO__NAME_VDSOX32,
+			.read_prog = "perf-read-vdsox32",
+		},
+#endif
 	};
 
 	return memdup(&vdso_info_init, sizeof(vdso_info_init));
 }
 
-static int find_vdso_map(void **start, void **end)
-{
-	FILE *maps;
-	char line[128];
-	int found = 0;
-
-	maps = fopen("/proc/self/maps", "r");
-	if (!maps) {
-		pr_err("vdso: cannot open maps\n");
-		return -1;
-	}
-
-	while (!found && fgets(line, sizeof(line), maps)) {
-		int m = -1;
-
-		/* We care only about private r-x mappings. */
-		if (2 != sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n",
-				start, end, &m))
-			continue;
-		if (m < 0)
-			continue;
-
-		if (!strncmp(&line[m], VDSO__MAP_NAME,
-			     sizeof(VDSO__MAP_NAME) - 1))
-			found = 1;
-	}
-
-	fclose(maps);
-	return !found;
-}
-
 static char *get_file(struct vdso_file *vdso_file)
 {
 	char *vdso = NULL;
@@ -117,6 +110,12 @@ void vdso__exit(struct machine *machine)
 
 	if (vdso_info->vdso.found)
 		unlink(vdso_info->vdso.temp_file_name);
+#if BITS_PER_LONG == 64
+	if (vdso_info->vdso32.found)
+		unlink(vdso_info->vdso32.temp_file_name);
+	if (vdso_info->vdsox32.found)
+		unlink(vdso_info->vdsox32.temp_file_name);
+#endif
 
 	zfree(&machine->vdso_info);
 }
@@ -135,6 +134,153 @@ static struct dso *vdso__new(struct machine *machine, const char *short_name,
 	return dso;
 }
 
+#if BITS_PER_LONG == 64
+
+static enum dso_type machine__thread_dso_type(struct machine *machine,
+					      struct thread *thread)
+{
+	enum dso_type dso_type = DSO__TYPE_UNKNOWN;
+	struct map *map;
+	struct dso *dso;
+
+	map = map_groups__first(thread->mg, MAP__FUNCTION);
+	for (; map ; map = map_groups__next(map)) {
+		dso = map->dso;
+		if (!dso || dso->long_name[0] != '/')
+			continue;
+		dso_type = dso__type(dso, machine);
+		if (dso_type != DSO__TYPE_UNKNOWN)
+			break;
+	}
+
+	return dso_type;
+}
+
+static int vdso__do_copy_compat(FILE *f, int fd)
+{
+	char buf[4096];
+	size_t count;
+
+	while (1) {
+		count = fread(buf, 1, sizeof(buf), f);
+		if (ferror(f))
+			return -errno;
+		if (feof(f))
+			break;
+		if (count && writen(fd, buf, count) != (ssize_t)count)
+			return -errno;
+	}
+
+	return 0;
+}
+
+static int vdso__copy_compat(const char *prog, int fd)
+{
+	FILE *f;
+	int err;
+
+	f = popen(prog, "r");
+	if (!f)
+		return -errno;
+
+	err = vdso__do_copy_compat(f, fd);
+
+	if (pclose(f) == -1)
+		return -errno;
+
+	return err;
+}
+
+static int vdso__create_compat_file(const char *prog, char *temp_name)
+{
+	int fd, err;
+
+	fd = mkstemp(temp_name);
+	if (fd < 0)
+		return -errno;
+
+	err = vdso__copy_compat(prog, fd);
+
+	if (close(fd) == -1)
+		return -errno;
+
+	return err;
+}
+
+static const char *vdso__get_compat_file(struct vdso_file *vdso_file)
+{
+	int err;
+
+	if (vdso_file->found)
+		return vdso_file->temp_file_name;
+
+	if (vdso_file->error)
+		return NULL;
+
+	err = vdso__create_compat_file(vdso_file->read_prog,
+				       vdso_file->temp_file_name);
+	if (err) {
+		pr_err("%s failed, error %d\n", vdso_file->read_prog, err);
+		vdso_file->error = true;
+		return NULL;
+	}
+
+	vdso_file->found = true;
+
+	return vdso_file->temp_file_name;
+}
+
+static struct dso *vdso__findnew_compat(struct machine *machine,
+					struct vdso_file *vdso_file)
+{
+	const char *file_name;
+	struct dso *dso;
+
+	dso = dsos__find(&machine->user_dsos, vdso_file->dso_name, true);
+	if (dso)
+		return dso;
+
+	file_name = vdso__get_compat_file(vdso_file);
+	if (!file_name)
+		return NULL;
+
+	return vdso__new(machine, vdso_file->dso_name, file_name);
+}
+
+static int vdso__dso_findnew_compat(struct machine *machine,
+				    struct thread *thread,
+				    struct vdso_info *vdso_info,
+				    struct dso **dso)
+{
+	enum dso_type dso_type;
+
+	dso_type = machine__thread_dso_type(machine, thread);
+
+#ifndef HAVE_PERF_READ_VDSO32
+	if (dso_type == DSO__TYPE_32BIT)
+		return 0;
+#endif
+#ifndef HAVE_PERF_READ_VDSOX32
+	if (dso_type == DSO__TYPE_X32BIT)
+		return 0;
+#endif
+
+	switch (dso_type) {
+	case DSO__TYPE_32BIT:
+		*dso = vdso__findnew_compat(machine, &vdso_info->vdso32);
+		return 1;
+	case DSO__TYPE_X32BIT:
+		*dso = vdso__findnew_compat(machine, &vdso_info->vdsox32);
+		return 1;
+	case DSO__TYPE_UNKNOWN:
+	case DSO__TYPE_64BIT:
+	default:
+		return 0;
+	}
+}
+
+#endif
+
 struct dso *vdso__dso_findnew(struct machine *machine,
 			      struct thread *thread __maybe_unused)
 {
@@ -148,6 +294,11 @@ struct dso *vdso__dso_findnew(struct machine *machine,
 	if (!vdso_info)
 		return NULL;
 
+#if BITS_PER_LONG == 64
+	if (vdso__dso_findnew_compat(machine, thread, vdso_info, &dso))
+		return dso;
+#endif
+
 	dso = dsos__find(&machine->user_dsos, DSO__NAME_VDSO, true);
 	if (!dso) {
 		char *file;
@@ -164,5 +315,7 @@ struct dso *vdso__dso_findnew(struct machine *machine,
 
 bool dso__is_vdso(struct dso *dso)
 {
-	return !strcmp(dso->short_name, DSO__NAME_VDSO);
+	return !strcmp(dso->short_name, DSO__NAME_VDSO) ||
+	       !strcmp(dso->short_name, DSO__NAME_VDSO32) ||
+	       !strcmp(dso->short_name, DSO__NAME_VDSOX32);
 }
diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h
index af9d692..d97da16 100644
--- a/tools/perf/util/vdso.h
+++ b/tools/perf/util/vdso.h
@@ -7,7 +7,9 @@
 
 #define VDSO__MAP_NAME "[vdso]"
 
-#define DSO__NAME_VDSO "[vdso]"
+#define DSO__NAME_VDSO    "[vdso]"
+#define DSO__NAME_VDSO32  "[vdso32]"
+#define DSO__NAME_VDSOX32 "[vdsox32]"
 
 static inline bool is_vdso_map(const char *filename)
 {