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:

Infrastructure changes:

 - Add gzip decompression support for kernel modules (Namhyung Kim)

 - More prep patches for Intel PT, including a a thread stack and
   more stuff made available via the database export mechanism (Adrian Hunter)

 - Optimize checking that tracepoint events are defined in perf script perl/python (Jiri Olsa)

 - Do not free pevent when deleting tracepoint evsel (Jiri Olsa)

 - Fix build-id matching for vmlinux (Namhyung Kim)

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

32 files changed, 1966 insertions, 429 deletions

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 3caf7dab50e..aecf61dcd75 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -66,6 +66,9 @@ include config/utilities.mak
 #
 # Define NO_PERF_READ_VDSOX32 if you do not want to build perf-read-vdsox32
 # for reading the x32 mode 32-bit compatibility VDSO in 64-bit mode
+#
+# Define NO_ZLIB if you do not want to support compressed kernel modules
+
 
 ifeq ($(srctree),)
 srctree := $(patsubst %/,%,$(dir $(shell pwd)))
@@ -317,6 +320,7 @@ LIB_H += ui/util.h
 LIB_H += ui/ui.h
 LIB_H += util/data.h
 LIB_H += util/kvm-stat.h
+LIB_H += util/thread-stack.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -394,6 +398,7 @@ LIB_OBJS += $(OUTPUT)util/srcline.o
 LIB_OBJS += $(OUTPUT)util/data.o
 LIB_OBJS += $(OUTPUT)util/tsc.o
 LIB_OBJS += $(OUTPUT)util/cloexec.o
+LIB_OBJS += $(OUTPUT)util/thread-stack.o
 
 LIB_OBJS += $(OUTPUT)ui/setup.o
 LIB_OBJS += $(OUTPUT)ui/helpline.o
@@ -582,6 +587,10 @@ ifndef NO_LIBNUMA
   BUILTIN_OBJS += $(OUTPUT)bench/numa.o
 endif
 
+ifndef NO_ZLIB
+  LIB_OBJS += $(OUTPUT)util/zlib.o
+endif
+
 ifdef ASCIIDOC8
   export ASCIIDOC8
 endif
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 5091a27e6d2..582c4da155e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -200,6 +200,17 @@ static int process_buildids(struct record *rec)
 	if (size == 0)
 		return 0;
 
+	/*
+	 * During this process, it'll load kernel map and replace the
+	 * dso->long_name to a real pathname it found.  In this case
+	 * we prefer the vmlinux path like
+	 *   /lib/modules/3.16.4/build/vmlinux
+	 *
+	 * rather than build-id path (in debug directory).
+	 *   $HOME/.debug/.build-id/f0/6e17aa50adf4d00b88925e03775de107611551
+	 */
+	symbol_conf.ignore_vmlinux_buildid = true;
+
 	return __perf_session__process_events(session, start,
 					      size - start,
 					      size, &build_id__mark_dso_hit_ops);
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 71264e41fa8..79f906c7124 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -200,7 +200,8 @@ CORE_FEATURE_TESTS =			\
 	libunwind			\
 	stackprotector-all		\
 	timerfd				\
-	libdw-dwarf-unwind
+	libdw-dwarf-unwind		\
+	zlib
 
 LIB_FEATURE_TESTS =			\
 	dwarf				\
@@ -214,7 +215,8 @@ LIB_FEATURE_TESTS =			\
 	libpython			\
 	libslang			\
 	libunwind			\
-	libdw-dwarf-unwind
+	libdw-dwarf-unwind		\
+	zlib
 
 VF_FEATURE_TESTS =			\
 	backtrace			\
@@ -604,6 +606,15 @@ ifneq ($(filter -lbfd,$(EXTLIBS)),)
   CFLAGS += -DHAVE_LIBBFD_SUPPORT
 endif
 
+ifndef NO_ZLIB
+  ifeq ($(feature-zlib), 1)
+    CFLAGS += -DHAVE_ZLIB_SUPPORT
+    EXTLIBS += -lz
+  else
+    NO_ZLIB := 1
+  endif
+endif
+
 ifndef NO_BACKTRACE
   ifeq ($(feature-backtrace), 1)
     CFLAGS += -DHAVE_BACKTRACE_SUPPORT
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 7c68ec74a80..53f19b5dbc3 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -29,7 +29,8 @@ FILES=					\
 	test-timerfd.bin		\
 	test-libdw-dwarf-unwind.bin	\
 	test-compile-32.bin		\
-	test-compile-x32.bin
+	test-compile-x32.bin		\
+	test-zlib.bin
 
 CC := $(CROSS_COMPILE)gcc -MD
 PKG_CONFIG := $(CROSS_COMPILE)pkg-config
@@ -41,7 +42,7 @@ BUILD = $(CC) $(CFLAGS) -o $(OUTPUT)$@ $(patsubst %.bin,%.c,$@) $(LDFLAGS)
 ###############################
 
 test-all.bin:
-	$(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl
+	$(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz
 
 test-hello.bin:
 	$(BUILD)
@@ -139,6 +140,9 @@ test-compile-32.bin:
 test-compile-x32.bin:
 	$(CC) -mx32 -o $(OUTPUT)$@ test-compile.c
 
+test-zlib.bin:
+	$(BUILD) -lz
+
 -include *.d
 
 ###############################
diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c
index a7d022e161c..652e0098eba 100644
--- a/tools/perf/config/feature-checks/test-all.c
+++ b/tools/perf/config/feature-checks/test-all.c
@@ -93,6 +93,10 @@
 # include "test-sync-compare-and-swap.c"
 #undef main
 
+#define main main_test_zlib
+# include "test-zlib.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
@@ -116,6 +120,7 @@ int main(int argc, char *argv[])
 	main_test_stackprotector_all();
 	main_test_libdw_dwarf_unwind();
 	main_test_sync_compare_and_swap(argc, argv);
+	main_test_zlib();
 
 	return 0;
 }
diff --git a/tools/perf/config/feature-checks/test-zlib.c b/tools/perf/config/feature-checks/test-zlib.c
new file mode 100644
index 00000000000..e111fff6240
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-zlib.c
@@ -0,0 +1,9 @@
+#include <zlib.h>
+
+int main(void)
+{
+	z_stream zs;
+
+	inflateInit(&zs);
+	return 0;
+}
diff --git a/tools/perf/scripts/python/bin/export-to-postgresql-report b/tools/perf/scripts/python/bin/export-to-postgresql-report
index a8fdd15f85b..cd335b6e2a0 100644
--- a/tools/perf/scripts/python/bin/export-to-postgresql-report
+++ b/tools/perf/scripts/python/bin/export-to-postgresql-report
@@ -1,6 +1,6 @@
 #!/bin/bash
 # description: export perf data to a postgresql database
-# args: [database name] [columns]
+# args: [database name] [columns] [calls]
 n_args=0
 for i in "$@"
 do
@@ -9,11 +9,16 @@ do
     fi
     n_args=$(( $n_args + 1 ))
 done
-if [ "$n_args" -gt 2 ] ; then
-    echo "usage: export-to-postgresql-report [database name] [columns]"
+if [ "$n_args" -gt 3 ] ; then
+    echo "usage: export-to-postgresql-report [database name] [columns] [calls]"
     exit
 fi
-if [ "$n_args" -gt 1 ] ; then
+if [ "$n_args" -gt 2 ] ; then
+    dbname=$1
+    columns=$2
+    calls=$3
+    shift 3
+elif [ "$n_args" -gt 1 ] ; then
     dbname=$1
     columns=$2
     shift 2
@@ -21,4 +26,4 @@ elif [ "$n_args" -gt 0 ] ; then
     dbname=$1
     shift
 fi
-perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-postgresql.py $dbname $columns
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-postgresql.py $dbname $columns $calls
diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index d8f6df0093d..4cdafd88007 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -40,10 +40,12 @@ sys.path.append(os.environ['PERF_EXEC_PATH'] + \
 #from Core import *
 
 perf_db_export_mode = True
+perf_db_export_calls = False
 
 def usage():
-	print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>]"
+	print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>]"
 	print >> sys.stderr, "where:	columns		'all' or 'branches'"
+	print >> sys.stderr, "		calls		'calls' => create calls table"
 	raise Exception("Too few arguments")
 
 if (len(sys.argv) < 2):
@@ -61,6 +63,12 @@ if columns not in ("all", "branches"):
 
 branches = (columns == "branches")
 
+if (len(sys.argv) >= 4):
+	if (sys.argv[3] == "calls"):
+		perf_db_export_calls = True
+	else:
+		usage()
+
 output_dir_name = os.getcwd() + "/" + dbname + "-perf-data"
 os.mkdir(output_dir_name)
 
@@ -123,6 +131,10 @@ do_query(query, 'CREATE TABLE symbols ('
 		'sym_end	bigint,'
 		'binding	integer,'
 		'name		varchar(2048))')
+do_query(query, 'CREATE TABLE branch_types ('
+		'id		integer		NOT NULL,'
+		'name		varchar(80))')
+
 if branches:
 	do_query(query, 'CREATE TABLE samples ('
 		'id		bigint		NOT NULL,'
@@ -139,7 +151,9 @@ if branches:
 		'to_dso_id	bigint,'
 		'to_symbol_id	bigint,'
 		'to_sym_offset	bigint,'
-		'to_ip		bigint)')
+		'to_ip		bigint,'
+		'branch_type	integer,'
+		'in_tx		boolean)')
 else:
 	do_query(query, 'CREATE TABLE samples ('
 		'id		bigint		NOT NULL,'
@@ -160,7 +174,28 @@ else:
 		'period		bigint,'
 		'weight		bigint,'
 		'transaction	bigint,'
-		'data_src	bigint)')
+		'data_src	bigint,'
+		'branch_type	integer,'
+		'in_tx		boolean)')
+
+if perf_db_export_calls:
+	do_query(query, 'CREATE TABLE call_paths ('
+		'id		bigint		NOT NULL,'
+		'parent_id	bigint,'
+		'symbol_id	bigint,'
+		'ip		bigint)')
+	do_query(query, 'CREATE TABLE calls ('
+		'id		bigint		NOT NULL,'
+		'thread_id	bigint,'
+		'comm_id	bigint,'
+		'call_path_id	bigint,'
+		'call_time	bigint,'
+		'return_time	bigint,'
+		'branch_count	bigint,'
+		'call_id	bigint,'
+		'return_id	bigint,'
+		'parent_call_path_id	bigint,'
+		'flags		integer)')
 
 do_query(query, 'CREATE VIEW samples_view AS '
 	'SELECT '
@@ -178,7 +213,9 @@ do_query(query, 'CREATE VIEW samples_view AS '
 		'to_hex(to_ip) AS to_ip_hex,'
 		'(SELECT name FROM symbols WHERE id = to_symbol_id) AS to_symbol,'
 		'to_sym_offset,'
-		'(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name'
+		'(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name,'
+		'(SELECT name FROM branch_types WHERE id = branch_type) AS branch_type_name,'
+		'in_tx'
 	' FROM samples')
 
 
@@ -234,7 +271,11 @@ comm_file		= open_output_file("comm_table.bin")
 comm_thread_file	= open_output_file("comm_thread_table.bin")
 dso_file		= open_output_file("dso_table.bin")
 symbol_file		= open_output_file("symbol_table.bin")
+branch_type_file	= open_output_file("branch_type_table.bin")
 sample_file		= open_output_file("sample_table.bin")
+if perf_db_export_calls:
+	call_path_file		= open_output_file("call_path_table.bin")
+	call_file		= open_output_file("call_table.bin")
 
 def trace_begin():
 	print datetime.datetime.today(), "Writing to intermediate files..."
@@ -245,6 +286,9 @@ def trace_begin():
 	comm_table(0, "unknown")
 	dso_table(0, 0, "unknown", "unknown", "")
 	symbol_table(0, 0, 0, 0, 0, "unknown")
+	sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
+	if perf_db_export_calls:
+		call_path_table(0, 0, 0, 0)
 
 unhandled_count = 0
 
@@ -257,7 +301,11 @@ def trace_end():
 	copy_output_file(comm_thread_file,	"comm_threads")
 	copy_output_file(dso_file,		"dsos")
 	copy_output_file(symbol_file,		"symbols")
+	copy_output_file(branch_type_file,	"branch_types")
 	copy_output_file(sample_file,		"samples")
+	if perf_db_export_calls:
+		copy_output_file(call_path_file,	"call_paths")
+		copy_output_file(call_file,		"calls")
 
 	print datetime.datetime.today(), "Removing intermediate files..."
 	remove_output_file(evsel_file)
@@ -267,7 +315,11 @@ def trace_end():
 	remove_output_file(comm_thread_file)
 	remove_output_file(dso_file)
 	remove_output_file(symbol_file)
+	remove_output_file(branch_type_file)
 	remove_output_file(sample_file)
+	if perf_db_export_calls:
+		remove_output_file(call_path_file)
+		remove_output_file(call_file)
 	os.rmdir(output_dir_name)
 	print datetime.datetime.today(), "Adding primary keys"
 	do_query(query, 'ALTER TABLE selected_events ADD PRIMARY KEY (id)')
@@ -277,7 +329,11 @@ def trace_end():
 	do_query(query, 'ALTER TABLE comm_threads    ADD PRIMARY KEY (id)')
 	do_query(query, 'ALTER TABLE dsos            ADD PRIMARY KEY (id)')
 	do_query(query, 'ALTER TABLE symbols         ADD PRIMARY KEY (id)')
+	do_query(query, 'ALTER TABLE branch_types    ADD PRIMARY KEY (id)')
 	do_query(query, 'ALTER TABLE samples         ADD PRIMARY KEY (id)')
+	if perf_db_export_calls:
+		do_query(query, 'ALTER TABLE call_paths      ADD PRIMARY KEY (id)')
+		do_query(query, 'ALTER TABLE calls           ADD PRIMARY KEY (id)')
 
 	print datetime.datetime.today(), "Adding foreign keys"
 	do_query(query, 'ALTER TABLE threads '
@@ -299,6 +355,18 @@ def trace_end():
 					'ADD CONSTRAINT symbolfk   FOREIGN KEY (symbol_id)    REFERENCES symbols    (id),'
 					'ADD CONSTRAINT todsofk    FOREIGN KEY (to_dso_id)    REFERENCES dsos       (id),'
 					'ADD CONSTRAINT tosymbolfk FOREIGN KEY (to_symbol_id) REFERENCES symbols    (id)')
+	if perf_db_export_calls:
+		do_query(query, 'ALTER TABLE call_paths '
+					'ADD CONSTRAINT parentfk    FOREIGN KEY (parent_id)    REFERENCES call_paths (id),'
+					'ADD CONSTRAINT symbolfk    FOREIGN KEY (symbol_id)    REFERENCES symbols    (id)')
+		do_query(query, 'ALTER TABLE calls '
+					'ADD CONSTRAINT threadfk    FOREIGN KEY (thread_id)    REFERENCES threads    (id),'
+					'ADD CONSTRAINT commfk      FOREIGN KEY (comm_id)      REFERENCES comms      (id),'
+					'ADD CONSTRAINT call_pathfk FOREIGN KEY (call_path_id) REFERENCES call_paths (id),'
+					'ADD CONSTRAINT callfk      FOREIGN KEY (call_id)      REFERENCES samples    (id),'
+					'ADD CONSTRAINT returnfk    FOREIGN KEY (return_id)    REFERENCES samples    (id),'
+					'ADD CONSTRAINT parent_call_pathfk FOREIGN KEY (parent_call_path_id) REFERENCES call_paths (id)')
+		do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)')
 
 	if (unhandled_count):
 		print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events"
@@ -352,9 +420,25 @@ def symbol_table(symbol_id, dso_id, sym_start, sym_end, binding, symbol_name, *x
 	value = struct.pack(fmt, 6, 8, symbol_id, 8, dso_id, 8, sym_start, 8, sym_end, 4, binding, n, symbol_name)
 	symbol_file.write(value)
 
-def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, *x):
+def branch_type_table(branch_type, name, *x):
+	n = len(name)
+	fmt = "!hiii" + str(n) + "s"
+	value = struct.pack(fmt, 2, 4, branch_type, n, name)
+	branch_type_file.write(value)
+
+def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, branch_type, in_tx, *x):
 	if branches:
-		value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiq", 15, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip)
+		value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiiiB", 17, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 4, branch_type, 1, in_tx)
 	else:
-		value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiq", 19, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src)
+		value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiqiiiB", 21, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src, 4, branch_type, 1, in_tx)
 	sample_file.write(value)
+
+def call_path_table(cp_id, parent_id, symbol_id, ip, *x):
+	fmt = "!hiqiqiqiq"
+	value = struct.pack(fmt, 4, 8, cp_id, 8, parent_id, 8, symbol_id, 8, ip)
+	call_path_file.write(value)
+
+def call_return_table(cr_id, thread_id, comm_id, call_path_id, call_time, return_time, branch_count, call_id, return_id, parent_call_path_id, flags, *x):
+	fmt = "!hiqiqiqiqiqiqiqiqiqiqii"
+	value = struct.pack(fmt, 11, 8, cr_id, 8, thread_id, 8, comm_id, 8, call_path_id, 8, call_time, 8, return_time, 8, branch_count, 8, call_id, 8, return_id, 8, parent_call_path_id, 4, flags)
+	call_file.write(value)
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 2e7c68e3933..dd2a3e52ada 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -15,6 +15,8 @@
 #include "debug.h"
 #include "session.h"
 #include "tool.h"
+#include "header.h"
+#include "vdso.h"
 
 int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 			   union perf_event *event,
@@ -105,3 +107,335 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
 			 build_id_hex, build_id_hex + 2);
 	return bf;
 }
+
+#define dsos__for_each_with_build_id(pos, head)	\
+	list_for_each_entry(pos, head, node)	\
+		if (!pos->has_build_id)		\
+			continue;		\
+		else
+
+static int write_buildid(const char *name, size_t name_len, u8 *build_id,
+			 pid_t pid, u16 misc, int fd)
+{
+	int err;
+	struct build_id_event b;
+	size_t len;
+
+	len = name_len + 1;
+	len = PERF_ALIGN(len, NAME_ALIGN);
+
+	memset(&b, 0, sizeof(b));
+	memcpy(&b.build_id, build_id, BUILD_ID_SIZE);
+	b.pid = pid;
+	b.header.misc = misc;
+	b.header.size = sizeof(b) + len;
+
+	err = writen(fd, &b, sizeof(b));
+	if (err < 0)
+		return err;
+
+	return write_padded(fd, name, name_len + 1, len);
+}
+
+static int __dsos__write_buildid_table(struct list_head *head,
+				       struct machine *machine,
+				       pid_t pid, u16 misc, int fd)
+{
+	char nm[PATH_MAX];
+	struct dso *pos;
+
+	dsos__for_each_with_build_id(pos, head) {
+		int err;
+		const char *name;
+		size_t name_len;
+
+		if (!pos->hit)
+			continue;
+
+		if (dso__is_vdso(pos)) {
+			name = pos->short_name;
+			name_len = pos->short_name_len + 1;
+		} else if (dso__is_kcore(pos)) {
+			machine__mmap_name(machine, nm, sizeof(nm));
+			name = nm;
+			name_len = strlen(nm) + 1;
+		} else {
+			name = pos->long_name;
+			name_len = pos->long_name_len + 1;
+		}
+
+		err = write_buildid(name, name_len, pos->build_id,
+				    pid, misc, fd);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int machine__write_buildid_table(struct machine *machine, int fd)
+{
+	int err;
+	u16 kmisc = PERF_RECORD_MISC_KERNEL,
+	    umisc = PERF_RECORD_MISC_USER;
+
+	if (!machine__is_host(machine)) {
+		kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
+		umisc = PERF_RECORD_MISC_GUEST_USER;
+	}
+
+	err = __dsos__write_buildid_table(&machine->kernel_dsos.head, machine,
+					  machine->pid, kmisc, fd);
+	if (err == 0)
+		err = __dsos__write_buildid_table(&machine->user_dsos.head,
+						  machine, machine->pid, umisc,
+						  fd);
+	return err;
+}
+
+int perf_session__write_buildid_table(struct perf_session *session, int fd)
+{
+	struct rb_node *nd;
+	int err = machine__write_buildid_table(&session->machines.host, fd);
+
+	if (err)
+		return err;
+
+	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		err = machine__write_buildid_table(pos, fd);
+		if (err)
+			break;
+	}
+	return err;
+}
+
+static int __dsos__hit_all(struct list_head *head)
+{
+	struct dso *pos;
+
+	list_for_each_entry(pos, head, node)
+		pos->hit = true;
+
+	return 0;
+}
+
+static int machine__hit_all_dsos(struct machine *machine)
+{
+	int err;
+
+	err = __dsos__hit_all(&machine->kernel_dsos.head);
+	if (err)
+		return err;
+
+	return __dsos__hit_all(&machine->user_dsos.head);
+}
+
+int dsos__hit_all(struct perf_session *session)
+{
+	struct rb_node *nd;
+	int err;
+
+	err = machine__hit_all_dsos(&session->machines.host);
+	if (err)
+		return err;
+
+	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+
+		err = machine__hit_all_dsos(pos);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
+			  const char *name, bool is_kallsyms, bool is_vdso)
+{
+	const size_t size = PATH_MAX;
+	char *realname, *filename = zalloc(size),
+	     *linkname = zalloc(size), *targetname;
+	int len, err = -1;
+	bool slash = is_kallsyms || is_vdso;
+
+	if (is_kallsyms) {
+		if (symbol_conf.kptr_restrict) {
+			pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
+			err = 0;
+			goto out_free;
+		}
+		realname = (char *) name;
+	} else
+		realname = realpath(name, NULL);
+
+	if (realname == NULL || filename == NULL || linkname == NULL)
+		goto out_free;
+
+	len = scnprintf(filename, size, "%s%s%s",
+		       debugdir, slash ? "/" : "",
+		       is_vdso ? DSO__NAME_VDSO : realname);
+	if (mkdir_p(filename, 0755))
+		goto out_free;
+
+	snprintf(filename + len, size - len, "/%s", sbuild_id);
+
+	if (access(filename, F_OK)) {
+		if (is_kallsyms) {
+			 if (copyfile("/proc/kallsyms", filename))
+				goto out_free;
+		} else if (link(realname, filename) && copyfile(name, filename))
+			goto out_free;
+	}
+
+	len = scnprintf(linkname, size, "%s/.build-id/%.2s",
+		       debugdir, sbuild_id);
+
+	if (access(linkname, X_OK) && mkdir_p(linkname, 0755))
+		goto out_free;
+
+	snprintf(linkname + len, size - len, "/%s", sbuild_id + 2);
+	targetname = filename + strlen(debugdir) - 5;
+	memcpy(targetname, "../..", 5);
+
+	if (symlink(targetname, linkname) == 0)
+		err = 0;
+out_free:
+	if (!is_kallsyms)
+		free(realname);
+	free(filename);
+	free(linkname);
+	return err;
+}
+
+static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
+				 const char *name, const char *debugdir,
+				 bool is_kallsyms, bool is_vdso)
+{
+	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+	build_id__sprintf(build_id, build_id_size, sbuild_id);
+
+	return build_id_cache__add_s(sbuild_id, debugdir, name,
+				     is_kallsyms, is_vdso);
+}
+
+int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir)
+{
+	const size_t size = PATH_MAX;
+	char *filename = zalloc(size),
+	     *linkname = zalloc(size);
+	int err = -1;
+
+	if (filename == NULL || linkname == NULL)
+		goto out_free;
+
+	snprintf(linkname, size, "%s/.build-id/%.2s/%s",
+		 debugdir, sbuild_id, sbuild_id + 2);
+
+	if (access(linkname, F_OK))
+		goto out_free;
+
+	if (readlink(linkname, filename, size - 1) < 0)
+		goto out_free;
+
+	if (unlink(linkname))
+		goto out_free;
+
+	/*
+	 * Since the link is relative, we must make it absolute:
+	 */
+	snprintf(linkname, size, "%s/.build-id/%.2s/%s",
+		 debugdir, sbuild_id, filename);
+
+	if (unlink(linkname))
+		goto out_free;
+
+	err = 0;
+out_free:
+	free(filename);
+	free(linkname);
+	return err;
+}
+
+static int dso__cache_build_id(struct dso *dso, struct machine *machine,
+			       const char *debugdir)
+{
+	bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
+	bool is_vdso = dso__is_vdso(dso);
+	const char *name = dso->long_name;
+	char nm[PATH_MAX];
+
+	if (dso__is_kcore(dso)) {
+		is_kallsyms = true;
+		machine__mmap_name(machine, nm, sizeof(nm));
+		name = nm;
+	}
+	return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name,
+				     debugdir, is_kallsyms, is_vdso);
+}
+
+static int __dsos__cache_build_ids(struct list_head *head,
+				   struct machine *machine, const char *debugdir)
+{
+	struct dso *pos;
+	int err = 0;
+
+	dsos__for_each_with_build_id(pos, head)
+		if (dso__cache_build_id(pos, machine, debugdir))
+			err = -1;
+
+	return err;
+}
+
+static int machine__cache_build_ids(struct machine *machine, const char *debugdir)
+{
+	int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine,
+					  debugdir);
+	ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine,
+				       debugdir);
+	return ret;
+}
+
+int perf_session__cache_build_ids(struct perf_session *session)
+{
+	struct rb_node *nd;
+	int ret;
+	char debugdir[PATH_MAX];
+
+	snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir);
+
+	if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
+		return -1;
+
+	ret = machine__cache_build_ids(&session->machines.host, debugdir);
+
+	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		ret |= machine__cache_build_ids(pos, debugdir);
+	}
+	return ret ? -1 : 0;
+}
+
+static bool machine__read_build_ids(struct machine *machine, bool with_hits)
+{
+	bool ret;
+
+	ret  = __dsos__read_build_ids(&machine->kernel_dsos.head, with_hits);
+	ret |= __dsos__read_build_ids(&machine->user_dsos.head, with_hits);
+	return ret;
+}
+
+bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
+{
+	struct rb_node *nd;
+	bool ret = machine__read_build_ids(&session->machines.host, with_hits);
+
+	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		ret |= machine__read_build_ids(pos, with_hits);
+	}
+
+	return ret;
+}
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index ae392561470..666a3bd4f64 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -15,4 +15,15 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
 			   struct perf_sample *sample, struct perf_evsel *evsel,
 			   struct machine *machine);
+
+int dsos__hit_all(struct perf_session *session);
+
+bool perf_session__read_build_ids(struct perf_session *session, bool with_hits);
+int perf_session__write_buildid_table(struct perf_session *session, int fd);
+int perf_session__cache_build_ids(struct perf_session *session);
+
+int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
+			  const char *name, bool is_kallsyms, bool is_vdso);
+int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);
+
 #endif
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index be128b075a3..c81dae39976 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -21,16 +21,76 @@
 #include "comm.h"
 #include "symbol.h"
 #include "event.h"
+#include "util.h"
+#include "thread-stack.h"
 #include "db-export.h"
 
+struct deferred_export {
+	struct list_head node;
+	struct comm *comm;
+};
+
+static int db_export__deferred(struct db_export *dbe)
+{
+	struct deferred_export *de;
+	int err;
+
+	while (!list_empty(&dbe->deferred)) {
+		de = list_entry(dbe->deferred.next, struct deferred_export,
+				node);
+		err = dbe->export_comm(dbe, de->comm);
+		list_del(&de->node);
+		free(de);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static void db_export__free_deferred(struct db_export *dbe)
+{
+	struct deferred_export *de;
+
+	while (!list_empty(&dbe->deferred)) {
+		de = list_entry(dbe->deferred.next, struct deferred_export,
+				node);
+		list_del(&de->node);
+		free(de);
+	}
+}
+
+static int db_export__defer_comm(struct db_export *dbe, struct comm *comm)
+{
+	struct deferred_export *de;
+
+	de = zalloc(sizeof(struct deferred_export));
+	if (!de)
+		return -ENOMEM;
+
+	de->comm = comm;
+	list_add_tail(&de->node, &dbe->deferred);
+
+	return 0;
+}
+
 int db_export__init(struct db_export *dbe)
 {
 	memset(dbe, 0, sizeof(struct db_export));
+	INIT_LIST_HEAD(&dbe->deferred);
 	return 0;
 }
 
-void db_export__exit(struct db_export *dbe __maybe_unused)
+int db_export__flush(struct db_export *dbe)
+{
+	return db_export__deferred(dbe);
+}
+
+void db_export__exit(struct db_export *dbe)
 {
+	db_export__free_deferred(dbe);
+	call_return_processor__free(dbe->crp);
+	dbe->crp = NULL;
 }
 
 int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel)
@@ -112,7 +172,10 @@ int db_export__comm(struct db_export *dbe, struct comm *comm,
 	comm->db_id = ++dbe->comm_last_db_id;
 
 	if (dbe->export_comm) {
-		err = dbe->export_comm(dbe, comm);
+		if (main_thread->comm_set)
+			err = dbe->export_comm(dbe, comm);
+		else
+			err = db_export__defer_comm(dbe, comm);
 		if (err)
 			return err;
 	}
@@ -208,6 +271,15 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al,
 	return 0;
 }
 
+int db_export__branch_type(struct db_export *dbe, u32 branch_type,
+			   const char *name)
+{
+	if (dbe->export_branch_type)
+		return dbe->export_branch_type(dbe, branch_type, name);
+
+	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)
@@ -261,6 +333,13 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 				     &es.addr_sym_db_id, &es.addr_offset);
 		if (err)
 			return err;
+		if (dbe->crp) {
+			err = thread_stack__process(thread, comm, sample, al,
+						    &addr_al, es.db_id,
+						    dbe->crp);
+			if (err)
+				return err;
+		}
 	}
 
 	if (dbe->export_sample)
@@ -268,3 +347,82 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 
 	return 0;
 }
+
+static struct {
+	u32 branch_type;
+	const char *name;
+} branch_types[] = {
+	{0, "no branch"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL, "call"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN, "return"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL, "conditional jump"},
+	{PERF_IP_FLAG_BRANCH, "unconditional jump"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_INTERRUPT,
+	 "software interrupt"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_INTERRUPT,
+	 "return from interrupt"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_SYSCALLRET,
+	 "system call"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_SYSCALLRET,
+	 "return from system call"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_ASYNC, "asynchronous branch"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |
+	 PERF_IP_FLAG_INTERRUPT, "hardware interrupt"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT, "transaction abort"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_BEGIN, "trace begin"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_END, "trace end"},
+	{0, NULL}
+};
+
+int db_export__branch_types(struct db_export *dbe)
+{
+	int i, err = 0;
+
+	for (i = 0; branch_types[i].name ; i++) {
+		err = db_export__branch_type(dbe, branch_types[i].branch_type,
+					     branch_types[i].name);
+		if (err)
+			break;
+	}
+	return err;
+}
+
+int db_export__call_path(struct db_export *dbe, struct call_path *cp)
+{
+	int err;
+
+	if (cp->db_id)
+		return 0;
+
+	if (cp->parent) {
+		err = db_export__call_path(dbe, cp->parent);
+		if (err)
+			return err;
+	}
+
+	cp->db_id = ++dbe->call_path_last_db_id;
+
+	if (dbe->export_call_path)
+		return dbe->export_call_path(dbe, cp);
+
+	return 0;
+}
+
+int db_export__call_return(struct db_export *dbe, struct call_return *cr)
+{
+	int err;
+
+	if (cr->db_id)
+		return 0;
+
+	err = db_export__call_path(dbe, cr->cp);
+	if (err)
+		return err;
+
+	cr->db_id = ++dbe->call_return_last_db_id;
+
+	if (dbe->export_call_return)
+		return dbe->export_call_return(dbe, cr);
+
+	return 0;
+}
diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h
index b3643e8e575..adbd22d6679 100644
--- a/tools/perf/util/db-export.h
+++ b/tools/perf/util/db-export.h
@@ -17,6 +17,7 @@
 #define __PERF_DB_EXPORT_H
 
 #include <linux/types.h>
+#include <linux/list.h>
 
 struct perf_evsel;
 struct machine;
@@ -25,6 +26,9 @@ struct comm;
 struct dso;
 struct perf_sample;
 struct addr_location;
+struct call_return_processor;
+struct call_path;
+struct call_return;
 
 struct export_sample {
 	union perf_event	*event;
@@ -54,7 +58,13 @@ struct db_export {
 			  struct machine *machine);
 	int (*export_symbol)(struct db_export *dbe, struct symbol *sym,
 			     struct dso *dso);
+	int (*export_branch_type)(struct db_export *dbe, u32 branch_type,
+				  const char *name);
 	int (*export_sample)(struct db_export *dbe, struct export_sample *es);
+	int (*export_call_path)(struct db_export *dbe, struct call_path *cp);
+	int (*export_call_return)(struct db_export *dbe,
+				  struct call_return *cr);
+	struct call_return_processor *crp;
 	u64 evsel_last_db_id;
 	u64 machine_last_db_id;
 	u64 thread_last_db_id;
@@ -63,9 +73,13 @@ struct db_export {
 	u64 dso_last_db_id;
 	u64 symbol_last_db_id;
 	u64 sample_last_db_id;
+	u64 call_path_last_db_id;
+	u64 call_return_last_db_id;
+	struct list_head deferred;
 };
 
 int db_export__init(struct db_export *dbe);
+int db_export__flush(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);
@@ -79,8 +93,15 @@ 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__branch_type(struct db_export *dbe, u32 branch_type,
+			   const char *name);
 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);
 
+int db_export__branch_types(struct db_export *dbe);
+
+int db_export__call_path(struct db_export *dbe, struct call_path *cp);
+int db_export__call_return(struct db_export *dbe, struct call_return *cr);
+
 #endif
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 0247acfdfac..45be944d450 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -21,8 +21,10 @@ char dso__symtab_origin(const struct dso *dso)
 		[DSO_BINARY_TYPE__BUILDID_DEBUGINFO]		= 'b',
 		[DSO_BINARY_TYPE__SYSTEM_PATH_DSO]		= 'd',
 		[DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE]		= 'K',
+		[DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP]	= 'm',
 		[DSO_BINARY_TYPE__GUEST_KALLSYMS]		= 'g',
 		[DSO_BINARY_TYPE__GUEST_KMODULE]		= 'G',
+		[DSO_BINARY_TYPE__GUEST_KMODULE_COMP]		= 'M',
 		[DSO_BINARY_TYPE__GUEST_VMLINUX]		= 'V',
 	};
 
@@ -112,11 +114,13 @@ int dso__read_binary_type_filename(const struct dso *dso,
 		break;
 
 	case DSO_BINARY_TYPE__GUEST_KMODULE:
+	case DSO_BINARY_TYPE__GUEST_KMODULE_COMP:
 		path__join3(filename, size, symbol_conf.symfs,
 			    root_dir, dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
+	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP:
 		__symbol__join_symfs(filename, size, dso->long_name);
 		break;
 
@@ -137,6 +141,73 @@ int dso__read_binary_type_filename(const struct dso *dso,
 	return ret;
 }
 
+static const struct {
+	const char *fmt;
+	int (*decompress)(const char *input, int output);
+} compressions[] = {
+#ifdef HAVE_ZLIB_SUPPORT
+	{ "gz", gzip_decompress_to_file },
+#endif
+	{ NULL, NULL },
+};
+
+bool is_supported_compression(const char *ext)
+{
+	unsigned i;
+
+	for (i = 0; compressions[i].fmt; i++) {
+		if (!strcmp(ext, compressions[i].fmt))
+			return true;
+	}
+	return false;
+}
+
+bool is_kmodule_extension(const char *ext)
+{
+	if (strncmp(ext, "ko", 2))
+		return false;
+
+	if (ext[2] == '\0' || (ext[2] == '.' && is_supported_compression(ext+3)))
+		return true;
+
+	return false;
+}
+
+bool is_kernel_module(const char *pathname, bool *compressed)
+{
+	const char *ext = strrchr(pathname, '.');
+
+	if (ext == NULL)
+		return false;
+
+	if (is_supported_compression(ext + 1)) {
+		if (compressed)
+			*compressed = true;
+		ext -= 3;
+	} else if (compressed)
+		*compressed = false;
+
+	return is_kmodule_extension(ext + 1);
+}
+
+bool decompress_to_file(const char *ext, const char *filename, int output_fd)
+{
+	unsigned i;
+
+	for (i = 0; compressions[i].fmt; i++) {
+		if (!strcmp(ext, compressions[i].fmt))
+			return !compressions[i].decompress(filename,
+							   output_fd);
+	}
+	return false;
+}
+
+bool dso__needs_decompress(struct dso *dso)
+{
+	return dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
+		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
+}
+
 /*
  * Global list of open DSOs and the counter.
  */
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index a316e4af321..3782c82c6e4 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -22,7 +22,9 @@ enum dso_binary_type {
 	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
 	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
 	DSO_BINARY_TYPE__GUEST_KMODULE,
+	DSO_BINARY_TYPE__GUEST_KMODULE_COMP,
 	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP,
 	DSO_BINARY_TYPE__KCORE,
 	DSO_BINARY_TYPE__GUEST_KCORE,
 	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
@@ -185,6 +187,11 @@ int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir);
 char dso__symtab_origin(const struct dso *dso);
 int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type,
 				   char *root_dir, char *filename, size_t size);
+bool is_supported_compression(const char *ext);
+bool is_kmodule_extension(const char *ext);
+bool is_kernel_module(const char *pathname, bool *compressed);
+bool decompress_to_file(const char *ext, const char *filename, int output_fd);
+bool dso__needs_decompress(struct dso *dso);
 
 /*
  * The dso__data_* external interface provides following functions:
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 8c7fe9d64e7..7be38973540 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -143,6 +143,32 @@ struct branch_stack {
 	struct branch_entry	entries[0];
 };
 
+enum {
+	PERF_IP_FLAG_BRANCH		= 1ULL << 0,
+	PERF_IP_FLAG_CALL		= 1ULL << 1,
+	PERF_IP_FLAG_RETURN		= 1ULL << 2,
+	PERF_IP_FLAG_CONDITIONAL	= 1ULL << 3,
+	PERF_IP_FLAG_SYSCALLRET		= 1ULL << 4,
+	PERF_IP_FLAG_ASYNC		= 1ULL << 5,
+	PERF_IP_FLAG_INTERRUPT		= 1ULL << 6,
+	PERF_IP_FLAG_TX_ABORT		= 1ULL << 7,
+	PERF_IP_FLAG_TRACE_BEGIN	= 1ULL << 8,
+	PERF_IP_FLAG_TRACE_END		= 1ULL << 9,
+	PERF_IP_FLAG_IN_TX		= 1ULL << 10,
+};
+
+#define PERF_BRANCH_MASK		(\
+	PERF_IP_FLAG_BRANCH		|\
+	PERF_IP_FLAG_CALL		|\
+	PERF_IP_FLAG_RETURN		|\
+	PERF_IP_FLAG_CONDITIONAL	|\
+	PERF_IP_FLAG_SYSCALLRET		|\
+	PERF_IP_FLAG_ASYNC		|\
+	PERF_IP_FLAG_INTERRUPT		|\
+	PERF_IP_FLAG_TX_ABORT		|\
+	PERF_IP_FLAG_TRACE_BEGIN	|\
+	PERF_IP_FLAG_TRACE_END)
+
 struct perf_sample {
 	u64 ip;
 	u32 pid, tid;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 2f9e68025ed..12b4396c717 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -853,8 +853,6 @@ void perf_evsel__exit(struct perf_evsel *evsel)
 	perf_evsel__free_id(evsel);
 	close_cgroup(evsel->cgrp);
 	zfree(&evsel->group_name);
-	if (evsel->tp_format)
-		pevent_free_format(evsel->tp_format);
 	zfree(&evsel->name);
 	perf_evsel__object.fini(evsel);
 }
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 0ecf4a304cb..76442caca37 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -79,10 +79,7 @@ static int do_write(int fd, const void *buf, size_t size)
 	return 0;
 }
 
-#define NAME_ALIGN 64
-
-static int write_padded(int fd, const void *bf, size_t count,
-			size_t count_aligned)
+int write_padded(int fd, const void *bf, size_t count, size_t count_aligned)
 {
 	static const char zero_buf[NAME_ALIGN];
 	int err = do_write(fd, bf, count);
@@ -171,340 +168,6 @@ perf_header__set_cmdline(int argc, const char **argv)
 	return 0;
 }
 
-#define dsos__for_each_with_build_id(pos, head)	\
-	list_for_each_entry(pos, head, node)	\
-		if (!pos->has_build_id)		\
-			continue;		\
-		else
-
-static int write_buildid(const char *name, size_t name_len, u8 *build_id,
-			 pid_t pid, u16 misc, int fd)
-{
-	int err;
-	struct build_id_event b;
-	size_t len;
-
-	len = name_len + 1;
-	len = PERF_ALIGN(len, NAME_ALIGN);
-
-	memset(&b, 0, sizeof(b));
-	memcpy(&b.build_id, build_id, BUILD_ID_SIZE);
-	b.pid = pid;
-	b.header.misc = misc;
-	b.header.size = sizeof(b) + len;
-
-	err = do_write(fd, &b, sizeof(b));
-	if (err < 0)
-		return err;
-
-	return write_padded(fd, name, name_len + 1, len);
-}
-
-static int __dsos__hit_all(struct list_head *head)
-{
-	struct dso *pos;
-
-	list_for_each_entry(pos, head, node)
-		pos->hit = true;
-
-	return 0;
-}
-
-static int machine__hit_all_dsos(struct machine *machine)
-{
-	int err;
-
-	err = __dsos__hit_all(&machine->kernel_dsos.head);
-	if (err)
-		return err;
-
-	return __dsos__hit_all(&machine->user_dsos.head);
-}
-
-int dsos__hit_all(struct perf_session *session)
-{
-	struct rb_node *nd;
-	int err;
-
-	err = machine__hit_all_dsos(&session->machines.host);
-	if (err)
-		return err;
-
-	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
-		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-
-		err = machine__hit_all_dsos(pos);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-static int __dsos__write_buildid_table(struct list_head *head,
-				       struct machine *machine,
-				       pid_t pid, u16 misc, int fd)
-{
-	char nm[PATH_MAX];
-	struct dso *pos;
-
-	dsos__for_each_with_build_id(pos, head) {
-		int err;
-		const char *name;
-		size_t name_len;
-
-		if (!pos->hit)
-			continue;
-
-		if (dso__is_vdso(pos)) {
-			name = pos->short_name;
-			name_len = pos->short_name_len + 1;
-		} else if (dso__is_kcore(pos)) {
-			machine__mmap_name(machine, nm, sizeof(nm));
-			name = nm;
-			name_len = strlen(nm) + 1;
-		} else {
-			name = pos->long_name;
-			name_len = pos->long_name_len + 1;
-		}
-
-		err = write_buildid(name, name_len, pos->build_id,
-				    pid, misc, fd);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-static int machine__write_buildid_table(struct machine *machine, int fd)
-{
-	int err;
-	u16 kmisc = PERF_RECORD_MISC_KERNEL,
-	    umisc = PERF_RECORD_MISC_USER;
-
-	if (!machine__is_host(machine)) {
-		kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
-		umisc = PERF_RECORD_MISC_GUEST_USER;
-	}
-
-	err = __dsos__write_buildid_table(&machine->kernel_dsos.head, machine,
-					  machine->pid, kmisc, fd);
-	if (err == 0)
-		err = __dsos__write_buildid_table(&machine->user_dsos.head,
-						  machine, machine->pid, umisc,
-						  fd);
-	return err;
-}
-
-static int dsos__write_buildid_table(struct perf_header *header, int fd)
-{
-	struct perf_session *session = container_of(header,
-			struct perf_session, header);
-	struct rb_node *nd;
-	int err = machine__write_buildid_table(&session->machines.host, fd);
-
-	if (err)
-		return err;
-
-	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
-		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		err = machine__write_buildid_table(pos, fd);
-		if (err)
-			break;
-	}
-	return err;
-}
-
-int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
-			  const char *name, bool is_kallsyms, bool is_vdso)
-{
-	const size_t size = PATH_MAX;
-	char *realname, *filename = zalloc(size),
-	     *linkname = zalloc(size), *targetname;
-	int len, err = -1;
-	bool slash = is_kallsyms || is_vdso;
-
-	if (is_kallsyms) {
-		if (symbol_conf.kptr_restrict) {
-			pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
-			err = 0;
-			goto out_free;
-		}
-		realname = (char *) name;
-	} else
-		realname = realpath(name, NULL);
-
-	if (realname == NULL || filename == NULL || linkname == NULL)
-		goto out_free;
-
-	len = scnprintf(filename, size, "%s%s%s",
-		       debugdir, slash ? "/" : "",
-		       is_vdso ? DSO__NAME_VDSO : realname);
-	if (mkdir_p(filename, 0755))
-		goto out_free;
-
-	snprintf(filename + len, size - len, "/%s", sbuild_id);
-
-	if (access(filename, F_OK)) {
-		if (is_kallsyms) {
-			 if (copyfile("/proc/kallsyms", filename))
-				goto out_free;
-		} else if (link(realname, filename) && copyfile(name, filename))
-			goto out_free;
-	}
-
-	len = scnprintf(linkname, size, "%s/.build-id/%.2s",
-		       debugdir, sbuild_id);
-
-	if (access(linkname, X_OK) && mkdir_p(linkname, 0755))
-		goto out_free;
-
-	snprintf(linkname + len, size - len, "/%s", sbuild_id + 2);
-	targetname = filename + strlen(debugdir) - 5;
-	memcpy(targetname, "../..", 5);
-
-	if (symlink(targetname, linkname) == 0)
-		err = 0;
-out_free:
-	if (!is_kallsyms)
-		free(realname);
-	free(filename);
-	free(linkname);
-	return err;
-}
-
-static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
-				 const char *name, const char *debugdir,
-				 bool is_kallsyms, bool is_vdso)
-{
-	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
-
-	build_id__sprintf(build_id, build_id_size, sbuild_id);
-
-	return build_id_cache__add_s(sbuild_id, debugdir, name,
-				     is_kallsyms, is_vdso);
-}
-
-int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir)
-{
-	const size_t size = PATH_MAX;
-	char *filename = zalloc(size),
-	     *linkname = zalloc(size);
-	int err = -1;
-
-	if (filename == NULL || linkname == NULL)
-		goto out_free;
-
-	snprintf(linkname, size, "%s/.build-id/%.2s/%s",
-		 debugdir, sbuild_id, sbuild_id + 2);
-
-	if (access(linkname, F_OK))
-		goto out_free;
-
-	if (readlink(linkname, filename, size - 1) < 0)
-		goto out_free;
-
-	if (unlink(linkname))
-		goto out_free;
-
-	/*
-	 * Since the link is relative, we must make it absolute:
-	 */
-	snprintf(linkname, size, "%s/.build-id/%.2s/%s",
-		 debugdir, sbuild_id, filename);
-
-	if (unlink(linkname))
-		goto out_free;
-
-	err = 0;
-out_free:
-	free(filename);
-	free(linkname);
-	return err;
-}
-
-static int dso__cache_build_id(struct dso *dso, struct machine *machine,
-			       const char *debugdir)
-{
-	bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
-	bool is_vdso = dso__is_vdso(dso);
-	const char *name = dso->long_name;
-	char nm[PATH_MAX];
-
-	if (dso__is_kcore(dso)) {
-		is_kallsyms = true;
-		machine__mmap_name(machine, nm, sizeof(nm));
-		name = nm;
-	}
-	return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name,
-				     debugdir, is_kallsyms, is_vdso);
-}
-
-static int __dsos__cache_build_ids(struct list_head *head,
-				   struct machine *machine, const char *debugdir)
-{
-	struct dso *pos;
-	int err = 0;
-
-	dsos__for_each_with_build_id(pos, head)
-		if (dso__cache_build_id(pos, machine, debugdir))
-			err = -1;
-
-	return err;
-}
-
-static int machine__cache_build_ids(struct machine *machine, const char *debugdir)
-{
-	int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine,
-					  debugdir);
-	ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine,
-				       debugdir);
-	return ret;
-}
-
-static int perf_session__cache_build_ids(struct perf_session *session)
-{
-	struct rb_node *nd;
-	int ret;
-	char debugdir[PATH_MAX];
-
-	snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir);
-
-	if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
-		return -1;
-
-	ret = machine__cache_build_ids(&session->machines.host, debugdir);
-
-	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
-		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		ret |= machine__cache_build_ids(pos, debugdir);
-	}
-	return ret ? -1 : 0;
-}
-
-static bool machine__read_build_ids(struct machine *machine, bool with_hits)
-{
-	bool ret;
-
-	ret  = __dsos__read_build_ids(&machine->kernel_dsos.head, with_hits);
-	ret |= __dsos__read_build_ids(&machine->user_dsos.head, with_hits);
-	return ret;
-}
-
-static bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
-{
-	struct rb_node *nd;
-	bool ret = machine__read_build_ids(&session->machines.host, with_hits);
-
-	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
-		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		ret |= machine__read_build_ids(pos, with_hits);
-	}
-
-	return ret;
-}
-
 static int write_tracing_data(int fd, struct perf_header *h __maybe_unused,
 			    struct perf_evlist *evlist)
 {
@@ -523,7 +186,7 @@ static int write_build_id(int fd, struct perf_header *h,
 	if (!perf_session__read_build_ids(session, true))
 		return -1;
 
-	err = dsos__write_buildid_table(h, fd);
+	err = perf_session__write_buildid_table(session, fd);
 	if (err < 0) {
 		pr_debug("failed to write buildid table\n");
 		return err;
@@ -1606,7 +1269,7 @@ static int __event_process_build_id(struct build_id_event *bev,
 
 		dso__set_build_id(dso, &bev->build_id);
 
-		if (filename[0] == '[')
+		if (!is_kernel_module(filename, NULL))
 			dso->kernel = dso_type;
 
 		build_id__sprintf(dso->build_id, sizeof(dso->build_id),
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 8f5cbaea64a..3bb90ac172a 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -122,10 +122,6 @@ int perf_header__process_sections(struct perf_header *header, int fd,
 
 int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full);
 
-int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
-			  const char *name, bool is_kallsyms, bool is_vdso);
-int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);
-
 int perf_event__synthesize_attr(struct perf_tool *tool,
 				struct perf_event_attr *attr, u32 ids, u64 *id,
 				perf_event__handler_t process);
@@ -151,7 +147,9 @@ int perf_event__process_build_id(struct perf_tool *tool,
 				 struct perf_session *session);
 bool is_perf_magic(u64 magic);
 
-int dsos__hit_all(struct perf_session *session);
+#define NAME_ALIGN 64
+
+int write_padded(int fd, const void *bf, size_t count, size_t count_aligned);
 
 /*
  * arch specific callback
diff --git a/tools/perf/util/include/linux/bitmap.h b/tools/perf/util/include/linux/bitmap.h
index 01ffd12dc79..40bd2148803 100644
--- a/tools/perf/util/include/linux/bitmap.h
+++ b/tools/perf/util/include/linux/bitmap.h
@@ -46,4 +46,21 @@ static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
 		__bitmap_or(dst, src1, src2, nbits);
 }
 
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ */
+static inline int test_and_set_bit(int nr, unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old;
+
+	old = *p;
+	*p = old | mask;
+
+	return (old & mask) != 0;
+}
+
 #endif /* _PERF_BITOPS_H */
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
index dadfa7e5428..c3294163de1 100644
--- a/tools/perf/util/include/linux/bitops.h
+++ b/tools/perf/util/include/linux/bitops.h
@@ -15,6 +15,8 @@
 #define BITS_TO_U64(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
 #define BITS_TO_U32(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
 #define BITS_TO_BYTES(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE)
+#define BIT_WORD(nr)            ((nr) / BITS_PER_LONG)
+#define BIT_MASK(nr)            (1UL << ((nr) % BITS_PER_LONG))
 
 #define for_each_set_bit(bit, addr, size) \
 	for ((bit) = find_first_bit((addr), (size));		\
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 51a630301af..52e94902afb 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -464,6 +464,7 @@ struct map *machine__new_module(struct machine *machine, u64 start,
 {
 	struct map *map;
 	struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename);
+	bool compressed;
 
 	if (dso == NULL)
 		return NULL;
@@ -476,6 +477,11 @@ struct map *machine__new_module(struct machine *machine, u64 start,
 		dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
 	else
 		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
+
+	/* _KMODULE_COMP should be next to _KMODULE */
+	if (is_kernel_module(filename, &compressed) && compressed)
+		dso->symtab_type++;
+
 	map_groups__insert(&machine->kmaps, map);
 	return map;
 }
@@ -861,8 +867,14 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg,
 			struct map *map;
 			char *long_name;
 
-			if (dot == NULL || strcmp(dot, ".ko"))
+			if (dot == NULL)
 				continue;
+
+			/* On some system, modules are compressed like .ko.gz */
+			if (is_supported_compression(dot + 1) &&
+			    is_kmodule_extension(dot - 2))
+				dot -= 3;
+
 			snprintf(dso_name, sizeof(dso_name), "[%.*s]",
 				 (int)(dot - dent->d_name), dent->d_name);
 
@@ -1044,6 +1056,11 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 			dot = strrchr(name, '.');
 			if (dot == NULL)
 				goto out_problem;
+			/* On some system, modules are compressed like .ko.gz */
+			if (is_supported_compression(dot + 1))
+				dot -= 3;
+			if (!is_kmodule_extension(dot + 1))
+				goto out_problem;
 			snprintf(short_module_name, sizeof(short_module_name),
 					"[%.*s]", (int)(dot - name), name);
 			strxfrchar(short_module_name, '-', '_');
@@ -1068,8 +1085,20 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		 * Should be there already, from the build-id table in
 		 * the header.
 		 */
-		struct dso *kernel = __dsos__findnew(&machine->kernel_dsos,
-						     kmmap_prefix);
+		struct dso *kernel = NULL;
+		struct dso *dso;
+
+		list_for_each_entry(dso, &machine->kernel_dsos.head, node) {
+			if (is_kernel_module(dso->long_name, NULL))
+				continue;
+
+			kernel = dso;
+			break;
+		}
+
+		if (kernel == NULL)
+			kernel = __dsos__findnew(&machine->kernel_dsos,
+						 kmmap_prefix);
 		if (kernel == NULL)
 			goto out_problem;
 
@@ -1077,6 +1106,9 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		if (__machine__create_kernel_maps(machine, kernel) < 0)
 			goto out_problem;
 
+		if (strstr(dso->long_name, "vmlinux"))
+			dso__set_short_name(dso, "[kernel.vmlinux]", false);
+
 		machine__set_kernel_mmap_len(machine, event);
 
 		/*
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 0a01bac4ce0..22ebc46226e 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -24,6 +24,7 @@
 #include <string.h>
 #include <ctype.h>
 #include <errno.h>
+#include <linux/bitmap.h>
 
 #include "../util.h"
 #include <EXTERN.h>
@@ -57,7 +58,7 @@ INTERP my_perl;
 #define FTRACE_MAX_EVENT				\
 	((1 << (sizeof(unsigned short) * 8)) - 1)
 
-struct event_format *events[FTRACE_MAX_EVENT];
+static DECLARE_BITMAP(events_defined, FTRACE_MAX_EVENT);
 
 extern struct scripting_context *scripting_context;
 
@@ -238,35 +239,15 @@ static void define_event_symbols(struct event_format *event,
 		define_event_symbols(event, ev_name, args->next);
 }
 
-static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
-{
-	static char ev_name[256];
-	struct event_format *event;
-	int type = evsel->attr.config;
-
-	if (events[type])
-		return events[type];
-
-	events[type] = event = evsel->tp_format;
-	if (!event)
-		return NULL;
-
-	sprintf(ev_name, "%s::%s", event->system, event->name);
-
-	define_event_symbols(event, ev_name, event->print_fmt.args);
-
-	return event;
-}
-
 static void perl_process_tracepoint(struct perf_sample *sample,
 				    struct perf_evsel *evsel,
 				    struct thread *thread)
 {
+	struct event_format *event = evsel->tp_format;
 	struct format_field *field;
 	static char handler[256];
 	unsigned long long val;
 	unsigned long s, ns;
-	struct event_format *event;
 	int pid;
 	int cpu = sample->cpu;
 	void *data = sample->raw_data;
@@ -278,7 +259,6 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 	if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
 		return;
 
-	event = find_cache_event(evsel);
 	if (!event)
 		die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
 
@@ -286,6 +266,9 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 
 	sprintf(handler, "%s::%s", event->system, event->name);
 
+	if (!test_and_set_bit(event->id, events_defined))
+		define_event_symbols(event, handler, event->print_fmt.args);
+
 	s = nsecs / NSECS_PER_SEC;
 	ns = nsecs - s * NSECS_PER_SEC;
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 2fd7ee8f18c..d808a328f4d 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -26,6 +26,7 @@
 #include <string.h>
 #include <stdbool.h>
 #include <errno.h>
+#include <linux/bitmap.h>
 
 #include "../../perf.h"
 #include "../debug.h"
@@ -37,6 +38,7 @@
 #include "../comm.h"
 #include "../machine.h"
 #include "../db-export.h"
+#include "../thread-stack.h"
 #include "../trace-event.h"
 #include "../machine.h"
 
@@ -45,7 +47,7 @@ PyMODINIT_FUNC initperf_trace_context(void);
 #define FTRACE_MAX_EVENT				\
 	((1 << (sizeof(unsigned short) * 8)) - 1)
 
-struct event_format *events[FTRACE_MAX_EVENT];
+static DECLARE_BITMAP(events_defined, FTRACE_MAX_EVENT);
 
 #define MAX_FIELDS	64
 #define N_COMMON_FIELDS	7
@@ -66,7 +68,10 @@ struct tables {
 	PyObject		*comm_thread_handler;
 	PyObject		*dso_handler;
 	PyObject		*symbol_handler;
+	PyObject		*branch_type_handler;
 	PyObject		*sample_handler;
+	PyObject		*call_path_handler;
+	PyObject		*call_return_handler;
 	bool			db_export_mode;
 };
 
@@ -251,31 +256,6 @@ static void define_event_symbols(struct event_format *event,
 		define_event_symbols(event, ev_name, args->next);
 }
 
-static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
-{
-	static char ev_name[256];
-	struct event_format *event;
-	int type = evsel->attr.config;
-
-	/*
- 	 * XXX: Do we really need to cache this since now we have evsel->tp_format
- 	 * cached already? Need to re-read this "cache" routine that as well calls
- 	 * define_event_symbols() :-\
- 	 */
-	if (events[type])
-		return events[type];
-
-	events[type] = event = evsel->tp_format;
-	if (!event)
-		return NULL;
-
-	sprintf(ev_name, "%s__%s", event->system, event->name);
-
-	define_event_symbols(event, ev_name, event->print_fmt.args);
-
-	return event;
-}
-
 static PyObject *get_field_numeric_entry(struct event_format *event,
 		struct format_field *field, void *data)
 {
@@ -399,12 +379,12 @@ static void python_process_tracepoint(struct perf_sample *sample,
 				      struct thread *thread,
 				      struct addr_location *al)
 {
+	struct event_format *event = evsel->tp_format;
 	PyObject *handler, *context, *t, *obj, *callchain;
 	PyObject *dict = NULL;
 	static char handler_name[256];
 	struct format_field *field;
 	unsigned long s, ns;
-	struct event_format *event;
 	unsigned n = 0;
 	int pid;
 	int cpu = sample->cpu;
@@ -416,7 +396,6 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	if (!t)
 		Py_FatalError("couldn't create Python tuple");
 
-	event = find_cache_event(evsel);
 	if (!event)
 		die("ug! no event found for type %d", (int)evsel->attr.config);
 
@@ -424,6 +403,9 @@ static void python_process_tracepoint(struct perf_sample *sample,
 
 	sprintf(handler_name, "%s__%s", event->system, event->name);
 
+	if (!test_and_set_bit(event->id, events_defined))
+		define_event_symbols(event, handler_name, event->print_fmt.args);
+
 	handler = get_handler(handler_name);
 	if (!handler) {
 		dict = PyDict_New();
@@ -664,13 +646,31 @@ static int python_export_symbol(struct db_export *dbe, struct symbol *sym,
 	return 0;
 }
 
+static int python_export_branch_type(struct db_export *dbe, u32 branch_type,
+				     const char *name)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(2);
+
+	tuple_set_s32(t, 0, branch_type);
+	tuple_set_string(t, 1, name);
+
+	call_object(tables->branch_type_handler, t, "branch_type_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);
+	t = tuple_new(21);
 
 	tuple_set_u64(t, 0, es->db_id);
 	tuple_set_u64(t, 1, es->evsel->db_id);
@@ -691,6 +691,8 @@ static int python_export_sample(struct db_export *dbe,
 	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);
+	tuple_set_s32(t, 19, es->sample->flags & PERF_BRANCH_MASK);
+	tuple_set_s32(t, 20, !!(es->sample->flags & PERF_IP_FLAG_IN_TX));
 
 	call_object(tables->sample_handler, t, "sample_table");
 
@@ -699,6 +701,64 @@ static int python_export_sample(struct db_export *dbe,
 	return 0;
 }
 
+static int python_export_call_path(struct db_export *dbe, struct call_path *cp)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+	u64 parent_db_id, sym_db_id;
+
+	parent_db_id = cp->parent ? cp->parent->db_id : 0;
+	sym_db_id = cp->sym ? *(u64 *)symbol__priv(cp->sym) : 0;
+
+	t = tuple_new(4);
+
+	tuple_set_u64(t, 0, cp->db_id);
+	tuple_set_u64(t, 1, parent_db_id);
+	tuple_set_u64(t, 2, sym_db_id);
+	tuple_set_u64(t, 3, cp->ip);
+
+	call_object(tables->call_path_handler, t, "call_path_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_call_return(struct db_export *dbe,
+				     struct call_return *cr)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	u64 comm_db_id = cr->comm ? cr->comm->db_id : 0;
+	PyObject *t;
+
+	t = tuple_new(11);
+
+	tuple_set_u64(t, 0, cr->db_id);
+	tuple_set_u64(t, 1, cr->thread->db_id);
+	tuple_set_u64(t, 2, comm_db_id);
+	tuple_set_u64(t, 3, cr->cp->db_id);
+	tuple_set_u64(t, 4, cr->call_time);
+	tuple_set_u64(t, 5, cr->return_time);
+	tuple_set_u64(t, 6, cr->branch_count);
+	tuple_set_u64(t, 7, cr->call_ref);
+	tuple_set_u64(t, 8, cr->return_ref);
+	tuple_set_u64(t, 9, cr->cp->parent->db_id);
+	tuple_set_s32(t, 10, cr->flags);
+
+	call_object(tables->call_return_handler, t, "call_return_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_process_call_return(struct call_return *cr, void *data)
+{
+	struct db_export *dbe = data;
+
+	return db_export__call_return(dbe, cr);
+}
+
 static void python_process_general_event(struct perf_sample *sample,
 					 struct perf_evsel *evsel,
 					 struct thread *thread,
@@ -831,7 +891,9 @@ error:
 static void set_table_handlers(struct tables *tables)
 {
 	const char *perf_db_export_mode = "perf_db_export_mode";
-	PyObject *db_export_mode;
+	const char *perf_db_export_calls = "perf_db_export_calls";
+	PyObject *db_export_mode, *db_export_calls;
+	bool export_calls = false;
 	int ret;
 
 	memset(tables, 0, sizeof(struct tables));
@@ -848,6 +910,23 @@ static void set_table_handlers(struct tables *tables)
 	if (!ret)
 		return;
 
+	tables->dbe.crp = NULL;
+	db_export_calls = PyDict_GetItemString(main_dict, perf_db_export_calls);
+	if (db_export_calls) {
+		ret = PyObject_IsTrue(db_export_calls);
+		if (ret == -1)
+			handler_call_die(perf_db_export_calls);
+		export_calls = !!ret;
+	}
+
+	if (export_calls) {
+		tables->dbe.crp =
+			call_return_processor__new(python_process_call_return,
+						   &tables->dbe);
+		if (!tables->dbe.crp)
+			Py_FatalError("failed to create calls processor");
+	}
+
 	tables->db_export_mode = true;
 	/*
 	 * Reserve per symbol space for symbol->db_id via symbol__priv()
@@ -861,7 +940,10 @@ static void set_table_handlers(struct tables *tables)
 	SET_TABLE_HANDLER(comm_thread);
 	SET_TABLE_HANDLER(dso);
 	SET_TABLE_HANDLER(symbol);
+	SET_TABLE_HANDLER(branch_type);
 	SET_TABLE_HANDLER(sample);
+	SET_TABLE_HANDLER(call_path);
+	SET_TABLE_HANDLER(call_return);
 }
 
 /*
@@ -910,6 +992,12 @@ static int python_start_script(const char *script, int argc, const char **argv)
 
 	set_table_handlers(tables);
 
+	if (tables->db_export_mode) {
+		err = db_export__branch_types(&tables->dbe);
+		if (err)
+			goto error;
+	}
+
 	return err;
 error:
 	Py_Finalize();
@@ -920,7 +1008,9 @@ error:
 
 static int python_flush_script(void)
 {
-	return 0;
+	struct tables *tables = &tables_global;
+
+	return db_export__flush(&tables->dbe);
 }
 
 /*
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 1e23a5bfb04..efc7eb6b8f0 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -546,6 +546,35 @@ static int dso__swap_init(struct dso *dso, unsigned char eidata)
 	return 0;
 }
 
+static int decompress_kmodule(struct dso *dso, const char *name,
+			      enum dso_binary_type type)
+{
+	int fd;
+	const char *ext = strrchr(name, '.');
+	char tmpbuf[] = "/tmp/perf-kmod-XXXXXX";
+
+	if ((type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP &&
+	     type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP) ||
+	    type != dso->symtab_type)
+		return -1;
+
+	if (!ext || !is_supported_compression(ext + 1))
+		return -1;
+
+	fd = mkstemp(tmpbuf);
+	if (fd < 0)
+		return -1;
+
+	if (!decompress_to_file(ext + 1, name, fd)) {
+		close(fd);
+		fd = -1;
+	}
+
+	unlink(tmpbuf);
+
+	return fd;
+}
+
 bool symsrc__possibly_runtime(struct symsrc *ss)
 {
 	return ss->dynsym || ss->opdsec;
@@ -571,7 +600,11 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 	Elf *elf;
 	int fd;
 
-	fd = open(name, O_RDONLY);
+	if (dso__needs_decompress(dso))
+		fd = decompress_kmodule(dso, name, type);
+	else
+		fd = open(name, O_RDONLY);
+
 	if (fd < 0)
 		return -1;
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 078331140d8..c24c5b83156 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -51,7 +51,9 @@ static enum dso_binary_type binary_type_symtab[] = {
 	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
 	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
 	DSO_BINARY_TYPE__GUEST_KMODULE,
+	DSO_BINARY_TYPE__GUEST_KMODULE_COMP,
 	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP,
 	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
 	DSO_BINARY_TYPE__NOT_FOUND,
 };
@@ -1300,7 +1302,9 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
 		return dso->kernel == DSO_TYPE_GUEST_KERNEL;
 
 	case DSO_BINARY_TYPE__GUEST_KMODULE:
+	case DSO_BINARY_TYPE__GUEST_KMODULE_COMP:
 	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
+	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP:
 		/*
 		 * kernel modules know their symtab type - it's set when
 		 * creating a module dso in machine__new_module().
@@ -1368,7 +1372,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 		return -1;
 
 	kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
-		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE;
+		dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
+		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE ||
+		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
 
 	/*
 	 * Iterate over candidate debug images.
@@ -1505,12 +1511,10 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 			   symbol_filter_t filter)
 {
 	int i, err = 0;
-	char *filename;
+	char *filename = NULL;
 
-	pr_debug("Looking at the vmlinux_path (%d entries long)\n",
-		 vmlinux_path__nr_entries + 1);
-
-	filename = dso__build_id_filename(dso, NULL, 0);
+	if (!symbol_conf.ignore_vmlinux_buildid)
+		filename = dso__build_id_filename(dso, NULL, 0);
 	if (filename != NULL) {
 		err = dso__load_vmlinux(dso, map, filename, true, filter);
 		if (err > 0)
@@ -1518,6 +1522,9 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 		free(filename);
 	}
 
+	pr_debug("Looking at the vmlinux_path (%d entries long)\n",
+		 vmlinux_path__nr_entries + 1);
+
 	for (i = 0; i < vmlinux_path__nr_entries; ++i) {
 		err = dso__load_vmlinux(dso, map, vmlinux_path[i], false, filter);
 		if (err > 0)
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index eb2c19bf8d9..ded3ca7266d 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -105,6 +105,7 @@ struct symbol_conf {
 	unsigned short	nr_events;
 	bool		try_vmlinux_path,
 			ignore_vmlinux,
+			ignore_vmlinux_buildid,
 			show_kernel_path,
 			use_modules,
 			sort_by_name,
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
new file mode 100644
index 00000000000..9ed59a452d1
--- /dev/null
+++ b/tools/perf/util/thread-stack.c
@@ -0,0 +1,747 @@
+/*
+ * thread-stack.c: Synthesize a thread's stack using call / return events
+ * 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 <linux/rbtree.h>
+#include <linux/list.h>
+#include "thread.h"
+#include "event.h"
+#include "machine.h"
+#include "util.h"
+#include "debug.h"
+#include "symbol.h"
+#include "comm.h"
+#include "thread-stack.h"
+
+#define CALL_PATH_BLOCK_SHIFT 8
+#define CALL_PATH_BLOCK_SIZE (1 << CALL_PATH_BLOCK_SHIFT)
+#define CALL_PATH_BLOCK_MASK (CALL_PATH_BLOCK_SIZE - 1)
+
+struct call_path_block {
+	struct call_path cp[CALL_PATH_BLOCK_SIZE];
+	struct list_head node;
+};
+
+/**
+ * struct call_path_root - root of all call paths.
+ * @call_path: root call path
+ * @blocks: list of blocks to store call paths
+ * @next: next free space
+ * @sz: number of spaces
+ */
+struct call_path_root {
+	struct call_path call_path;
+	struct list_head blocks;
+	size_t next;
+	size_t sz;
+};
+
+/**
+ * struct call_return_processor - provides a call-back to consume call-return
+ *                                information.
+ * @cpr: call path root
+ * @process: call-back that accepts call/return information
+ * @data: anonymous data for call-back
+ */
+struct call_return_processor {
+	struct call_path_root *cpr;
+	int (*process)(struct call_return *cr, void *data);
+	void *data;
+};
+
+#define STACK_GROWTH 2048
+
+/**
+ * struct thread_stack_entry - thread stack entry.
+ * @ret_addr: return address
+ * @timestamp: timestamp (if known)
+ * @ref: external reference (e.g. db_id of sample)
+ * @branch_count: the branch count when the entry was created
+ * @cp: call path
+ * @no_call: a 'call' was not seen
+ */
+struct thread_stack_entry {
+	u64 ret_addr;
+	u64 timestamp;
+	u64 ref;
+	u64 branch_count;
+	struct call_path *cp;
+	bool no_call;
+};
+
+/**
+ * struct thread_stack - thread stack constructed from 'call' and 'return'
+ *                       branch samples.
+ * @stack: array that holds the stack
+ * @cnt: number of entries in the stack
+ * @sz: current maximum stack size
+ * @trace_nr: current trace number
+ * @branch_count: running branch count
+ * @kernel_start: kernel start address
+ * @last_time: last timestamp
+ * @crp: call/return processor
+ * @comm: current comm
+ */
+struct thread_stack {
+	struct thread_stack_entry *stack;
+	size_t cnt;
+	size_t sz;
+	u64 trace_nr;
+	u64 branch_count;
+	u64 kernel_start;
+	u64 last_time;
+	struct call_return_processor *crp;
+	struct comm *comm;
+};
+
+static int thread_stack__grow(struct thread_stack *ts)
+{
+	struct thread_stack_entry *new_stack;
+	size_t sz, new_sz;
+
+	new_sz = ts->sz + STACK_GROWTH;
+	sz = new_sz * sizeof(struct thread_stack_entry);
+
+	new_stack = realloc(ts->stack, sz);
+	if (!new_stack)
+		return -ENOMEM;
+
+	ts->stack = new_stack;
+	ts->sz = new_sz;
+
+	return 0;
+}
+
+static struct thread_stack *thread_stack__new(struct thread *thread,
+					      struct call_return_processor *crp)
+{
+	struct thread_stack *ts;
+
+	ts = zalloc(sizeof(struct thread_stack));
+	if (!ts)
+		return NULL;
+
+	if (thread_stack__grow(ts)) {
+		free(ts);
+		return NULL;
+	}
+
+	if (thread->mg && thread->mg->machine)
+		ts->kernel_start = machine__kernel_start(thread->mg->machine);
+	else
+		ts->kernel_start = 1ULL << 63;
+	ts->crp = crp;
+
+	return ts;
+}
+
+static int thread_stack__push(struct thread_stack *ts, u64 ret_addr)
+{
+	int err = 0;
+
+	if (ts->cnt == ts->sz) {
+		err = thread_stack__grow(ts);
+		if (err) {
+			pr_warning("Out of memory: discarding thread stack\n");
+			ts->cnt = 0;
+		}
+	}
+
+	ts->stack[ts->cnt++].ret_addr = ret_addr;
+
+	return err;
+}
+
+static void thread_stack__pop(struct thread_stack *ts, u64 ret_addr)
+{
+	size_t i;
+
+	/*
+	 * In some cases there may be functions which are not seen to return.
+	 * For example when setjmp / longjmp has been used.  Or the perf context
+	 * switch in the kernel which doesn't stop and start tracing in exactly
+	 * the same code path.  When that happens the return address will be
+	 * further down the stack.  If the return address is not found at all,
+	 * we assume the opposite (i.e. this is a return for a call that wasn't
+	 * seen for some reason) and leave the stack alone.
+	 */
+	for (i = ts->cnt; i; ) {
+		if (ts->stack[--i].ret_addr == ret_addr) {
+			ts->cnt = i;
+			return;
+		}
+	}
+}
+
+static bool thread_stack__in_kernel(struct thread_stack *ts)
+{
+	if (!ts->cnt)
+		return false;
+
+	return ts->stack[ts->cnt - 1].cp->in_kernel;
+}
+
+static int thread_stack__call_return(struct thread *thread,
+				     struct thread_stack *ts, size_t idx,
+				     u64 timestamp, u64 ref, bool no_return)
+{
+	struct call_return_processor *crp = ts->crp;
+	struct thread_stack_entry *tse;
+	struct call_return cr = {
+		.thread = thread,
+		.comm = ts->comm,
+		.db_id = 0,
+	};
+
+	tse = &ts->stack[idx];
+	cr.cp = tse->cp;
+	cr.call_time = tse->timestamp;
+	cr.return_time = timestamp;
+	cr.branch_count = ts->branch_count - tse->branch_count;
+	cr.call_ref = tse->ref;
+	cr.return_ref = ref;
+	if (tse->no_call)
+		cr.flags |= CALL_RETURN_NO_CALL;
+	if (no_return)
+		cr.flags |= CALL_RETURN_NO_RETURN;
+
+	return crp->process(&cr, crp->data);
+}
+
+static int thread_stack__flush(struct thread *thread, struct thread_stack *ts)
+{
+	struct call_return_processor *crp = ts->crp;
+	int err;
+
+	if (!crp) {
+		ts->cnt = 0;
+		return 0;
+	}
+
+	while (ts->cnt) {
+		err = thread_stack__call_return(thread, ts, --ts->cnt,
+						ts->last_time, 0, true);
+		if (err) {
+			pr_err("Error flushing thread stack!\n");
+			ts->cnt = 0;
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
+			u64 to_ip, u16 insn_len, u64 trace_nr)
+{
+	if (!thread)
+		return -EINVAL;
+
+	if (!thread->ts) {
+		thread->ts = thread_stack__new(thread, NULL);
+		if (!thread->ts) {
+			pr_warning("Out of memory: no thread stack\n");
+			return -ENOMEM;
+		}
+		thread->ts->trace_nr = trace_nr;
+	}
+
+	/*
+	 * When the trace is discontinuous, the trace_nr changes.  In that case
+	 * the stack might be completely invalid.  Better to report nothing than
+	 * to report something misleading, so flush the stack.
+	 */
+	if (trace_nr != thread->ts->trace_nr) {
+		if (thread->ts->trace_nr)
+			thread_stack__flush(thread, thread->ts);
+		thread->ts->trace_nr = trace_nr;
+	}
+
+	/* Stop here if thread_stack__process() is in use */
+	if (thread->ts->crp)
+		return 0;
+
+	if (flags & PERF_IP_FLAG_CALL) {
+		u64 ret_addr;
+
+		if (!to_ip)
+			return 0;
+		ret_addr = from_ip + insn_len;
+		if (ret_addr == to_ip)
+			return 0; /* Zero-length calls are excluded */
+		return thread_stack__push(thread->ts, ret_addr);
+	} else if (flags & PERF_IP_FLAG_RETURN) {
+		if (!from_ip)
+			return 0;
+		thread_stack__pop(thread->ts, to_ip);
+	}
+
+	return 0;
+}
+
+void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr)
+{
+	if (!thread || !thread->ts)
+		return;
+
+	if (trace_nr != thread->ts->trace_nr) {
+		if (thread->ts->trace_nr)
+			thread_stack__flush(thread, thread->ts);
+		thread->ts->trace_nr = trace_nr;
+	}
+}
+
+void thread_stack__free(struct thread *thread)
+{
+	if (thread->ts) {
+		thread_stack__flush(thread, thread->ts);
+		zfree(&thread->ts->stack);
+		zfree(&thread->ts);
+	}
+}
+
+void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
+			  size_t sz, u64 ip)
+{
+	size_t i;
+
+	if (!thread || !thread->ts)
+		chain->nr = 1;
+	else
+		chain->nr = min(sz, thread->ts->cnt + 1);
+
+	chain->ips[0] = ip;
+
+	for (i = 1; i < chain->nr; i++)
+		chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr;
+}
+
+static void call_path__init(struct call_path *cp, struct call_path *parent,
+			    struct symbol *sym, u64 ip, bool in_kernel)
+{
+	cp->parent = parent;
+	cp->sym = sym;
+	cp->ip = sym ? 0 : ip;
+	cp->db_id = 0;
+	cp->in_kernel = in_kernel;
+	RB_CLEAR_NODE(&cp->rb_node);
+	cp->children = RB_ROOT;
+}
+
+static struct call_path_root *call_path_root__new(void)
+{
+	struct call_path_root *cpr;
+
+	cpr = zalloc(sizeof(struct call_path_root));
+	if (!cpr)
+		return NULL;
+	call_path__init(&cpr->call_path, NULL, NULL, 0, false);
+	INIT_LIST_HEAD(&cpr->blocks);
+	return cpr;
+}
+
+static void call_path_root__free(struct call_path_root *cpr)
+{
+	struct call_path_block *pos, *n;
+
+	list_for_each_entry_safe(pos, n, &cpr->blocks, node) {
+		list_del(&pos->node);
+		free(pos);
+	}
+	free(cpr);
+}
+
+static struct call_path *call_path__new(struct call_path_root *cpr,
+					struct call_path *parent,
+					struct symbol *sym, u64 ip,
+					bool in_kernel)
+{
+	struct call_path_block *cpb;
+	struct call_path *cp;
+	size_t n;
+
+	if (cpr->next < cpr->sz) {
+		cpb = list_last_entry(&cpr->blocks, struct call_path_block,
+				      node);
+	} else {
+		cpb = zalloc(sizeof(struct call_path_block));
+		if (!cpb)
+			return NULL;
+		list_add_tail(&cpb->node, &cpr->blocks);
+		cpr->sz += CALL_PATH_BLOCK_SIZE;
+	}
+
+	n = cpr->next++ & CALL_PATH_BLOCK_MASK;
+	cp = &cpb->cp[n];
+
+	call_path__init(cp, parent, sym, ip, in_kernel);
+
+	return cp;
+}
+
+static struct call_path *call_path__findnew(struct call_path_root *cpr,
+					    struct call_path *parent,
+					    struct symbol *sym, u64 ip, u64 ks)
+{
+	struct rb_node **p;
+	struct rb_node *node_parent = NULL;
+	struct call_path *cp;
+	bool in_kernel = ip >= ks;
+
+	if (sym)
+		ip = 0;
+
+	if (!parent)
+		return call_path__new(cpr, parent, sym, ip, in_kernel);
+
+	p = &parent->children.rb_node;
+	while (*p != NULL) {
+		node_parent = *p;
+		cp = rb_entry(node_parent, struct call_path, rb_node);
+
+		if (cp->sym == sym && cp->ip == ip)
+			return cp;
+
+		if (sym < cp->sym || (sym == cp->sym && ip < cp->ip))
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	cp = call_path__new(cpr, parent, sym, ip, in_kernel);
+	if (!cp)
+		return NULL;
+
+	rb_link_node(&cp->rb_node, node_parent, p);
+	rb_insert_color(&cp->rb_node, &parent->children);
+
+	return cp;
+}
+
+struct call_return_processor *
+call_return_processor__new(int (*process)(struct call_return *cr, void *data),
+			   void *data)
+{
+	struct call_return_processor *crp;
+
+	crp = zalloc(sizeof(struct call_return_processor));
+	if (!crp)
+		return NULL;
+	crp->cpr = call_path_root__new();
+	if (!crp->cpr)
+		goto out_free;
+	crp->process = process;
+	crp->data = data;
+	return crp;
+
+out_free:
+	free(crp);
+	return NULL;
+}
+
+void call_return_processor__free(struct call_return_processor *crp)
+{
+	if (crp) {
+		call_path_root__free(crp->cpr);
+		free(crp);
+	}
+}
+
+static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
+				 u64 timestamp, u64 ref, struct call_path *cp,
+				 bool no_call)
+{
+	struct thread_stack_entry *tse;
+	int err;
+
+	if (ts->cnt == ts->sz) {
+		err = thread_stack__grow(ts);
+		if (err)
+			return err;
+	}
+
+	tse = &ts->stack[ts->cnt++];
+	tse->ret_addr = ret_addr;
+	tse->timestamp = timestamp;
+	tse->ref = ref;
+	tse->branch_count = ts->branch_count;
+	tse->cp = cp;
+	tse->no_call = no_call;
+
+	return 0;
+}
+
+static int thread_stack__pop_cp(struct thread *thread, struct thread_stack *ts,
+				u64 ret_addr, u64 timestamp, u64 ref,
+				struct symbol *sym)
+{
+	int err;
+
+	if (!ts->cnt)
+		return 1;
+
+	if (ts->cnt == 1) {
+		struct thread_stack_entry *tse = &ts->stack[0];
+
+		if (tse->cp->sym == sym)
+			return thread_stack__call_return(thread, ts, --ts->cnt,
+							 timestamp, ref, false);
+	}
+
+	if (ts->stack[ts->cnt - 1].ret_addr == ret_addr) {
+		return thread_stack__call_return(thread, ts, --ts->cnt,
+						 timestamp, ref, false);
+	} else {
+		size_t i = ts->cnt - 1;
+
+		while (i--) {
+			if (ts->stack[i].ret_addr != ret_addr)
+				continue;
+			i += 1;
+			while (ts->cnt > i) {
+				err = thread_stack__call_return(thread, ts,
+								--ts->cnt,
+								timestamp, ref,
+								true);
+				if (err)
+					return err;
+			}
+			return thread_stack__call_return(thread, ts, --ts->cnt,
+							 timestamp, ref, false);
+		}
+	}
+
+	return 1;
+}
+
+static int thread_stack__bottom(struct thread *thread, struct thread_stack *ts,
+				struct perf_sample *sample,
+				struct addr_location *from_al,
+				struct addr_location *to_al, u64 ref)
+{
+	struct call_path_root *cpr = ts->crp->cpr;
+	struct call_path *cp;
+	struct symbol *sym;
+	u64 ip;
+
+	if (sample->ip) {
+		ip = sample->ip;
+		sym = from_al->sym;
+	} else if (sample->addr) {
+		ip = sample->addr;
+		sym = to_al->sym;
+	} else {
+		return 0;
+	}
+
+	cp = call_path__findnew(cpr, &cpr->call_path, sym, ip,
+				ts->kernel_start);
+	if (!cp)
+		return -ENOMEM;
+
+	return thread_stack__push_cp(thread->ts, ip, sample->time, ref, cp,
+				     true);
+}
+
+static int thread_stack__no_call_return(struct thread *thread,
+					struct thread_stack *ts,
+					struct perf_sample *sample,
+					struct addr_location *from_al,
+					struct addr_location *to_al, u64 ref)
+{
+	struct call_path_root *cpr = ts->crp->cpr;
+	struct call_path *cp, *parent;
+	u64 ks = ts->kernel_start;
+	int err;
+
+	if (sample->ip >= ks && sample->addr < ks) {
+		/* Return to userspace, so pop all kernel addresses */
+		while (thread_stack__in_kernel(ts)) {
+			err = thread_stack__call_return(thread, ts, --ts->cnt,
+							sample->time, ref,
+							true);
+			if (err)
+				return err;
+		}
+
+		/* If the stack is empty, push the userspace address */
+		if (!ts->cnt) {
+			cp = call_path__findnew(cpr, &cpr->call_path,
+						to_al->sym, sample->addr,
+						ts->kernel_start);
+			if (!cp)
+				return -ENOMEM;
+			return thread_stack__push_cp(ts, 0, sample->time, ref,
+						     cp, true);
+		}
+	} else if (thread_stack__in_kernel(ts) && sample->ip < ks) {
+		/* Return to userspace, so pop all kernel addresses */
+		while (thread_stack__in_kernel(ts)) {
+			err = thread_stack__call_return(thread, ts, --ts->cnt,
+							sample->time, ref,
+							true);
+			if (err)
+				return err;
+		}
+	}
+
+	if (ts->cnt)
+		parent = ts->stack[ts->cnt - 1].cp;
+	else
+		parent = &cpr->call_path;
+
+	/* This 'return' had no 'call', so push and pop top of stack */
+	cp = call_path__findnew(cpr, parent, from_al->sym, sample->ip,
+				ts->kernel_start);
+	if (!cp)
+		return -ENOMEM;
+
+	err = thread_stack__push_cp(ts, sample->addr, sample->time, ref, cp,
+				    true);
+	if (err)
+		return err;
+
+	return thread_stack__pop_cp(thread, ts, sample->addr, sample->time, ref,
+				    to_al->sym);
+}
+
+static int thread_stack__trace_begin(struct thread *thread,
+				     struct thread_stack *ts, u64 timestamp,
+				     u64 ref)
+{
+	struct thread_stack_entry *tse;
+	int err;
+
+	if (!ts->cnt)
+		return 0;
+
+	/* Pop trace end */
+	tse = &ts->stack[ts->cnt - 1];
+	if (tse->cp->sym == NULL && tse->cp->ip == 0) {
+		err = thread_stack__call_return(thread, ts, --ts->cnt,
+						timestamp, ref, false);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int thread_stack__trace_end(struct thread_stack *ts,
+				   struct perf_sample *sample, u64 ref)
+{
+	struct call_path_root *cpr = ts->crp->cpr;
+	struct call_path *cp;
+	u64 ret_addr;
+
+	/* No point having 'trace end' on the bottom of the stack */
+	if (!ts->cnt || (ts->cnt == 1 && ts->stack[0].ref == ref))
+		return 0;
+
+	cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp, NULL, 0,
+				ts->kernel_start);
+	if (!cp)
+		return -ENOMEM;
+
+	ret_addr = sample->ip + sample->insn_len;
+
+	return thread_stack__push_cp(ts, ret_addr, sample->time, ref, cp,
+				     false);
+}
+
+int thread_stack__process(struct thread *thread, struct comm *comm,
+			  struct perf_sample *sample,
+			  struct addr_location *from_al,
+			  struct addr_location *to_al, u64 ref,
+			  struct call_return_processor *crp)
+{
+	struct thread_stack *ts = thread->ts;
+	int err = 0;
+
+	if (ts) {
+		if (!ts->crp) {
+			/* Supersede thread_stack__event() */
+			thread_stack__free(thread);
+			thread->ts = thread_stack__new(thread, crp);
+			if (!thread->ts)
+				return -ENOMEM;
+			ts = thread->ts;
+			ts->comm = comm;
+		}
+	} else {
+		thread->ts = thread_stack__new(thread, crp);
+		if (!thread->ts)
+			return -ENOMEM;
+		ts = thread->ts;
+		ts->comm = comm;
+	}
+
+	/* Flush stack on exec */
+	if (ts->comm != comm && thread->pid_ == thread->tid) {
+		err = thread_stack__flush(thread, ts);
+		if (err)
+			return err;
+		ts->comm = comm;
+	}
+
+	/* If the stack is empty, put the current symbol on the stack */
+	if (!ts->cnt) {
+		err = thread_stack__bottom(thread, ts, sample, from_al, to_al,
+					   ref);
+		if (err)
+			return err;
+	}
+
+	ts->branch_count += 1;
+	ts->last_time = sample->time;
+
+	if (sample->flags & PERF_IP_FLAG_CALL) {
+		struct call_path_root *cpr = ts->crp->cpr;
+		struct call_path *cp;
+		u64 ret_addr;
+
+		if (!sample->ip || !sample->addr)
+			return 0;
+
+		ret_addr = sample->ip + sample->insn_len;
+		if (ret_addr == sample->addr)
+			return 0; /* Zero-length calls are excluded */
+
+		cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp,
+					to_al->sym, sample->addr,
+					ts->kernel_start);
+		if (!cp)
+			return -ENOMEM;
+		err = thread_stack__push_cp(ts, ret_addr, sample->time, ref,
+					    cp, false);
+	} else if (sample->flags & PERF_IP_FLAG_RETURN) {
+		if (!sample->ip || !sample->addr)
+			return 0;
+
+		err = thread_stack__pop_cp(thread, ts, sample->addr,
+					   sample->time, ref, from_al->sym);
+		if (err) {
+			if (err < 0)
+				return err;
+			err = thread_stack__no_call_return(thread, ts, sample,
+							   from_al, to_al, ref);
+		}
+	} else if (sample->flags & PERF_IP_FLAG_TRACE_BEGIN) {
+		err = thread_stack__trace_begin(thread, ts, sample->time, ref);
+	} else if (sample->flags & PERF_IP_FLAG_TRACE_END) {
+		err = thread_stack__trace_end(ts, sample, ref);
+	}
+
+	return err;
+}
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
new file mode 100644
index 00000000000..b843bbef8ba
--- /dev/null
+++ b/tools/perf/util/thread-stack.h
@@ -0,0 +1,111 @@
+/*
+ * thread-stack.h: Synthesize a thread's stack using call / return events
+ * 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_THREAD_STACK_H
+#define __PERF_THREAD_STACK_H
+
+#include <sys/types.h>
+
+#include <linux/types.h>
+#include <linux/rbtree.h>
+
+struct thread;
+struct comm;
+struct ip_callchain;
+struct symbol;
+struct dso;
+struct call_return_processor;
+struct comm;
+struct perf_sample;
+struct addr_location;
+
+/*
+ * Call/Return flags.
+ *
+ * CALL_RETURN_NO_CALL: 'return' but no matching 'call'
+ * CALL_RETURN_NO_RETURN: 'call' but no matching 'return'
+ */
+enum {
+	CALL_RETURN_NO_CALL	= 1 << 0,
+	CALL_RETURN_NO_RETURN	= 1 << 1,
+};
+
+/**
+ * struct call_return - paired call/return information.
+ * @thread: thread in which call/return occurred
+ * @comm: comm in which call/return occurred
+ * @cp: call path
+ * @call_time: timestamp of call (if known)
+ * @return_time: timestamp of return (if known)
+ * @branch_count: number of branches seen between call and return
+ * @call_ref: external reference to 'call' sample (e.g. db_id)
+ * @return_ref:  external reference to 'return' sample (e.g. db_id)
+ * @db_id: id used for db-export
+ * @flags: Call/Return flags
+ */
+struct call_return {
+	struct thread *thread;
+	struct comm *comm;
+	struct call_path *cp;
+	u64 call_time;
+	u64 return_time;
+	u64 branch_count;
+	u64 call_ref;
+	u64 return_ref;
+	u64 db_id;
+	u32 flags;
+};
+
+/**
+ * struct call_path - node in list of calls leading to a function call.
+ * @parent: call path to the parent function call
+ * @sym: symbol of function called
+ * @ip: only if sym is null, the ip of the function
+ * @db_id: id used for db-export
+ * @in_kernel: whether function is a in the kernel
+ * @rb_node: node in parent's tree of called functions
+ * @children: tree of call paths of functions called
+ *
+ * In combination with the call_return structure, the call_path structure
+ * defines a context-sensitve call-graph.
+ */
+struct call_path {
+	struct call_path *parent;
+	struct symbol *sym;
+	u64 ip;
+	u64 db_id;
+	bool in_kernel;
+	struct rb_node rb_node;
+	struct rb_root children;
+};
+
+int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
+			u64 to_ip, u16 insn_len, u64 trace_nr);
+void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr);
+void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
+			  size_t sz, u64 ip);
+void thread_stack__free(struct thread *thread);
+
+struct call_return_processor *
+call_return_processor__new(int (*process)(struct call_return *cr, void *data),
+			   void *data);
+void call_return_processor__free(struct call_return_processor *crp);
+int thread_stack__process(struct thread *thread, struct comm *comm,
+			  struct perf_sample *sample,
+			  struct addr_location *from_al,
+			  struct addr_location *to_al, u64 ref,
+			  struct call_return_processor *crp);
+
+#endif
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index bf5bf858b7f..a2157f0ef1d 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -4,6 +4,7 @@
 #include <string.h>
 #include "session.h"
 #include "thread.h"
+#include "thread-stack.h"
 #include "util.h"
 #include "debug.h"
 #include "comm.h"
@@ -66,6 +67,8 @@ void thread__delete(struct thread *thread)
 {
 	struct comm *comm, *tmp;
 
+	thread_stack__free(thread);
+
 	if (thread->mg) {
 		map_groups__put(thread->mg);
 		thread->mg = NULL;
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index d34cf5c0d0d..160fd066a7d 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -8,6 +8,8 @@
 #include "symbol.h"
 #include <strlist.h>
 
+struct thread_stack;
+
 struct thread {
 	union {
 		struct rb_node	 rb_node;
@@ -26,6 +28,7 @@ struct thread {
 	u64			db_id;
 
 	void			*priv;
+	struct thread_stack	*ts;
 };
 
 struct machine;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 80bfdaa0e2a..7dc44cfe25b 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -351,4 +351,9 @@ void mem_bswap_32(void *src, int byte_size);
 
 const char *get_filename_for_perf_kvm(void);
 bool find_process(const char *name);
+
+#ifdef HAVE_ZLIB_SUPPORT
+int gzip_decompress_to_file(const char *input, int output_fd);
+#endif
+
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c
new file mode 100644
index 00000000000..495a449fc25
--- /dev/null
+++ b/tools/perf/util/zlib.c
@@ -0,0 +1,78 @@
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <zlib.h>
+
+#include "util/util.h"
+#include "util/debug.h"
+
+
+#define CHUNK_SIZE  16384
+
+int gzip_decompress_to_file(const char *input, int output_fd)
+{
+	int ret = Z_STREAM_ERROR;
+	int input_fd;
+	void *ptr;
+	int len;
+	struct stat stbuf;
+	unsigned char buf[CHUNK_SIZE];
+	z_stream zs = {
+		.zalloc		= Z_NULL,
+		.zfree		= Z_NULL,
+		.opaque		= Z_NULL,
+		.avail_in	= 0,
+		.next_in	= Z_NULL,
+	};
+
+	input_fd = open(input, O_RDONLY);
+	if (input_fd < 0)
+		return -1;
+
+	if (fstat(input_fd, &stbuf) < 0)
+		goto out_close;
+
+	ptr = mmap(NULL, stbuf.st_size, PROT_READ, MAP_PRIVATE, input_fd, 0);
+	if (ptr == MAP_FAILED)
+		goto out_close;
+
+	if (inflateInit2(&zs, 16 + MAX_WBITS) != Z_OK)
+		goto out_unmap;
+
+	zs.next_in = ptr;
+	zs.avail_in = stbuf.st_size;
+
+	do {
+		zs.next_out = buf;
+		zs.avail_out = CHUNK_SIZE;
+
+		ret = inflate(&zs, Z_NO_FLUSH);
+		switch (ret) {
+		case Z_NEED_DICT:
+			ret = Z_DATA_ERROR;
+			/* fall through */
+		case Z_DATA_ERROR:
+		case Z_MEM_ERROR:
+			goto out;
+		default:
+			break;
+		}
+
+		len = CHUNK_SIZE - zs.avail_out;
+		if (writen(output_fd, buf, len) != len) {
+			ret = Z_DATA_ERROR;
+			goto out;
+		}
+
+	} while (ret != Z_STREAM_END);
+
+out:
+	inflateEnd(&zs);
+out_unmap:
+	munmap(ptr, stbuf.st_size);
+out_close:
+	close(input_fd);
+
+	return ret == Z_STREAM_END ? 0 : -1;
+}