Merge commit 'v2.6.34-rc6' into core/locking

Merge reason: Further lockdep patches depend on per cpu updates
made in -rc1.

34 files changed, 1155 insertions, 729 deletions

diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index bdd3b7ecad0a..bd498d496952 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -24,7 +24,10 @@ DOC_MAN1=$(patsubst %.txt,%.1,$(MAN1_TXT))
 DOC_MAN5=$(patsubst %.txt,%.5,$(MAN5_TXT))
 DOC_MAN7=$(patsubst %.txt,%.7,$(MAN7_TXT))
 
+# Make the path relative to DESTDIR, not prefix
+ifndef DESTDIR
 prefix?=$(HOME)
+endif
 bindir?=$(prefix)/bin
 htmldir?=$(prefix)/share/doc/perf-doc
 pdfdir?=$(prefix)/share/doc/perf-doc
@@ -32,7 +35,6 @@ mandir?=$(prefix)/share/man
 man1dir=$(mandir)/man1
 man5dir=$(mandir)/man5
 man7dir=$(mandir)/man7
-# DESTDIR=
 
 ASCIIDOC=asciidoc
 ASCIIDOC_EXTRA = --unsafe
diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
new file mode 100644
index 000000000000..b317102138c8
--- /dev/null
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -0,0 +1,29 @@
+perf-lock(1)
+============
+
+NAME
+----
+perf-lock - Analyze lock events
+
+SYNOPSIS
+--------
+[verse]
+'perf lock' {record|report|trace}
+
+DESCRIPTION
+-----------
+You can analyze various lock behaviours
+and statistics with this 'perf lock' command.
+
+  'perf lock record <command>' records lock events
+  between start and end <command>. And this command
+  produces the file "perf.data" which contains tracing
+  results of lock events.
+
+  'perf lock trace' shows raw lock events.
+
+  'perf lock report' reports statistical data.
+
+SEE ALSO
+--------
+linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 2de34075f6a4..34202b1be0bb 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -41,7 +41,8 @@ OPTIONS
 
 -d::
 --del=::
-        Delete a probe event.
+        Delete probe events. This accepts glob wildcards('*', '?') and character
+        classes(e.g. [a-z], [!A-Z]).
 
 -l::
 --list::
@@ -50,17 +51,29 @@ OPTIONS
 -L::
 --line=::
         Show source code lines which can be probed. This needs an argument
-        which specifies a range of the source code.
+        which specifies a range of the source code. (see LINE SYNTAX for detail)
+
+-f::
+--force::
+        Forcibly add events with existing name.
 
 PROBE SYNTAX
 ------------
 Probe points are defined by following syntax.
 
- "[EVENT=]FUNC[+OFFS|:RLN|%return][@SRC]|SRC:ALN [ARG ...]"
+    1) Define event based on function name
+     [EVENT=]FUNC[@SRC][:RLN|+OFFS|%return|;PTN] [ARG ...]
+
+    2) Define event based on source file with line number
+     [EVENT=]SRC:ALN [ARG ...]
+
+    3) Define event based on source file with lazy pattern
+     [EVENT=]SRC;PTN [ARG ...]
+
 
 'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function. Currently, event group name is set as 'probe'.
-'FUNC' specifies a probed function name, and it may have one of the following options; '+OFFS' is the offset from function entry address in bytes, 'RLN' is the relative-line number from function entry line, and '%return' means that it probes function return. In addition, 'SRC' specifies a source file which has that function.
-It is also possible to specify a probe point by the source line number by using 'SRC:ALN' syntax, where 'SRC' is the source file path and 'ALN' is the line number.
+'FUNC' specifies a probed function name, and it may have one of the following options; '+OFFS' is the offset from function entry address in bytes, ':RLN' is the relative-line number from function entry line, and '%return' means that it probes function return. And ';PTN' means lazy matching pattern (see LAZY MATCHING). Note that ';PTN' must be the end of the probe point definition.  In addition, '@SRC' specifies a source file which has that function.
+It is also possible to specify a probe point by the source line number or lazy matching by using 'SRC:ALN' or 'SRC;PTN' syntax, where 'SRC' is the source file path, ':ALN' is the line number and ';PTN' is the lazy matching pattern.
 'ARG' specifies the arguments of this probe point. You can use the name of local variable, or kprobe-tracer argument format (e.g. $retval, %ax, etc).
 
 LINE SYNTAX
@@ -76,6 +89,41 @@ and 'ALN2' is end line number in the file. It is also possible to specify how
 many lines to show by using 'NUM'.
 So, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function.
 
+LAZY MATCHING
+-------------
+ The lazy line matching is similar to glob matching but ignoring spaces in both of pattern and target. So this accepts wildcards('*', '?') and character classes(e.g. [a-z], [!A-Z]).
+
+e.g.
+ 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on.
+
+This provides some sort of flexibility and robustness to probe point definitions against minor code changes. For example, actual 10th line of schedule() can be moved easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist in the function.)
+
+
+EXAMPLES
+--------
+Display which lines in schedule() can be probed:
+
+ ./perf probe --line schedule
+
+Add a probe on schedule() function 12th line with recording cpu local variable:
+
+ ./perf probe schedule:12 cpu
+ or
+ ./perf probe --add='schedule:12 cpu'
+
+ this will add one or more probes which has the name start with "schedule".
+
+ Add probes on lines in schedule() function which calls update_rq_clock().
+
+ ./perf probe 'schedule;update_rq_clock*'
+ or
+ ./perf probe --add='schedule;update_rq_clock*'
+
+Delete all probes on schedule().
+
+ ./perf probe --del='schedule*'
+
+
 SEE ALSO
 --------
 linkperf:perf-trace[1], linkperf:perf-record[1]
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 54a5b50ff312..bc0f670a8338 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -200,7 +200,7 @@ endif
 
 CFLAGS = -ggdb3 -Wall -Wextra -std=gnu99 -Werror $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
 EXTLIBS = -lpthread -lrt -lelf -lm
-ALL_CFLAGS = $(CFLAGS)
+ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
 ALL_LDFLAGS = $(LDFLAGS)
 STRIP ?= strip
 
@@ -216,7 +216,10 @@ STRIP ?= strip
 # runtime figures out where they are based on the path to the executable.
 # This can help installing the suite in a relocatable way.
 
+# Make the path relative to DESTDIR, not to prefix
+ifndef DESTDIR
 prefix = $(HOME)
+endif
 bindir_relative = bin
 bindir = $(prefix)/$(bindir_relative)
 mandir = share/man
@@ -233,7 +236,6 @@ sysconfdir = $(prefix)/etc
 ETC_PERFCONFIG = etc/perfconfig
 endif
 lib = lib
-# DESTDIR=
 
 export prefix bindir sharedir sysconfdir
 
@@ -387,6 +389,7 @@ LIB_H += util/thread.h
 LIB_H += util/trace-event.h
 LIB_H += util/probe-finder.h
 LIB_H += util/probe-event.h
+LIB_H += util/cpumap.h
 
 LIB_OBJS += util/abspath.o
 LIB_OBJS += util/alias.o
@@ -433,6 +436,7 @@ LIB_OBJS += util/sort.o
 LIB_OBJS += util/hist.o
 LIB_OBJS += util/probe-event.o
 LIB_OBJS += util/util.o
+LIB_OBJS += util/cpumap.o
 
 BUILTIN_OBJS += builtin-annotate.o
 
@@ -488,24 +492,24 @@ ifeq ($(uname_S),Darwin)
         PTHREAD_LIBS =
 endif
 
-ifeq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
-ifneq ($(shell sh -c "(echo '\#include <gnu/libc-version.h>'; echo 'int main(void) { const char * version = gnu_get_libc_version(); return (long)version; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
+ifeq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
+ifneq ($(shell sh -c "(echo '\#include <gnu/libc-version.h>'; echo 'int main(void) { const char * version = gnu_get_libc_version(); return (long)version; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
         msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
 endif
 
-        ifneq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ_MMAP, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
+        ifneq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ_MMAP, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
                 BASIC_CFLAGS += -DLIBELF_NO_MMAP
         endif
 else
         msg := $(error No libelf.h/libelf found, please install libelf-dev/elfutils-libelf-devel and glibc-dev[el]);
 endif
 
-ifneq ($(shell sh -c "(echo '\#ifndef _MIPS_SZLONG'; echo '\#define _MIPS_SZLONG 0'; echo '\#endif'; echo '\#include <dwarf.h>'; echo '\#include <libdwarf.h>'; echo 'int main(void) { Dwarf_Debug dbg; Dwarf_Error err; Dwarf_Ranges *rng; dwarf_init(0, DW_DLC_READ, 0, 0, &dbg, &err); dwarf_get_ranges(dbg, 0, &rng, 0, 0, &err); return (long)dbg; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -I/usr/include/libdwarf -ldwarf -lelf -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
-        msg := $(warning No libdwarf.h found or old libdwarf.h found, disables dwarf support. Please install libdwarf-dev/libdwarf-devel >= 20081231);
-        BASIC_CFLAGS += -DNO_LIBDWARF
+ifneq ($(shell sh -c "(echo '\#include <dwarf.h>'; echo '\#include <libdw.h>'; echo 'int main(void) { Dwarf *dbg; dbg = dwarf_begin(0, DWARF_C_READ); return (long)dbg; }') | $(CC) -x c - $(ALL_CFLAGS) -I/usr/include/elfutils -ldw -lelf -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
+        msg := $(warning No libdw.h found or old libdw.h found, disables dwarf support. Please install elfutils-devel/elfutils-dev);
+        BASIC_CFLAGS += -DNO_DWARF_SUPPORT
 else
-        BASIC_CFLAGS += -I/usr/include/libdwarf
-        EXTLIBS += -lelf -ldwarf
+        BASIC_CFLAGS += -I/usr/include/elfutils
+        EXTLIBS += -lelf -ldw
         LIB_OBJS += util/probe-finder.o
 endif
 
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 5ec5de995872..6ad7148451c5 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -116,7 +116,7 @@ static int perf_session__add_hist_entry(struct perf_session *self,
                 return 0;
         }
 
-        he = __perf_session__add_hist_entry(self, al, NULL, count, &hit);
+        he = __perf_session__add_hist_entry(&self->hists, al, NULL, count, &hit);
         if (he == NULL)
                 return -ENOMEM;
 
@@ -564,8 +564,8 @@ static int __cmd_annotate(void)
         if (verbose > 2)
                 dsos__fprintf(stdout);
 
-        perf_session__collapse_resort(session);
-        perf_session__output_resort(session, session->event_total[0]);
+        perf_session__collapse_resort(&session->hists);
+        perf_session__output_resort(&session->hists, session->event_total[0]);
         perf_session__find_annotations(session);
 out_delete:
         perf_session__delete(session);
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 18b3f505f9db..1ea15d8aeed1 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -26,7 +26,8 @@ static int perf_session__add_hist_entry(struct perf_session *self,
                                         struct addr_location *al, u64 count)
 {
         bool hit;
-        struct hist_entry *he = __perf_session__add_hist_entry(self, al, NULL,
+        struct hist_entry *he = __perf_session__add_hist_entry(&self->hists,
+                                                               al, NULL,
                                                                count, &hit);
         if (he == NULL)
                 return -ENOMEM;
@@ -114,7 +115,7 @@ static void perf_session__resort_hist_entries(struct perf_session *self)
 
 static void perf_session__set_hist_entries_positions(struct perf_session *self)
 {
-        perf_session__output_resort(self, self->events_stats.total);
+        perf_session__output_resort(&self->hists, self->events_stats.total);
         perf_session__resort_hist_entries(self);
 }
 
@@ -166,13 +167,15 @@ static int __cmd_diff(void)
                         goto out_delete;
         }
 
-        perf_session__output_resort(session[1], session[1]->events_stats.total);
+        perf_session__output_resort(&session[1]->hists,
+                                    session[1]->events_stats.total);
         if (show_displacement)
                 perf_session__set_hist_entries_positions(session[0]);
 
         perf_session__match_hists(session[0], session[1]);
-        perf_session__fprintf_hists(session[1], session[0],
-                                    show_displacement, stdout);
+        perf_session__fprintf_hists(&session[1]->hists, session[0],
+                                    show_displacement, stdout,
+                                    session[1]->events_stats.total);
 out_delete:
         for (i = 0; i < 2; ++i)
                 perf_session__delete(session[i]);
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index fb9ab2ad3f92..e12c844df1e2 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -460,6 +460,150 @@ process_raw_event(void *data, int cpu,
                 process_lock_release_event(data, event, cpu, timestamp, thread);
 }
 
+struct raw_event_queue {
+        u64                     timestamp;
+        int                     cpu;
+        void                    *data;
+        struct thread           *thread;
+        struct list_head        list;
+};
+
+static LIST_HEAD(raw_event_head);
+
+#define FLUSH_PERIOD    (5 * NSEC_PER_SEC)
+
+static u64 flush_limit = ULLONG_MAX;
+static u64 last_flush = 0;
+struct raw_event_queue *last_inserted;
+
+static void flush_raw_event_queue(u64 limit)
+{
+        struct raw_event_queue *tmp, *iter;
+
+        list_for_each_entry_safe(iter, tmp, &raw_event_head, list) {
+                if (iter->timestamp > limit)
+                        return;
+
+                if (iter == last_inserted)
+                        last_inserted = NULL;
+
+                process_raw_event(iter->data, iter->cpu, iter->timestamp,
+                                  iter->thread);
+
+                last_flush = iter->timestamp;
+                list_del(&iter->list);
+                free(iter->data);
+                free(iter);
+        }
+}
+
+static void __queue_raw_event_end(struct raw_event_queue *new)
+{
+        struct raw_event_queue *iter;
+
+        list_for_each_entry_reverse(iter, &raw_event_head, list) {
+                if (iter->timestamp < new->timestamp) {
+                        list_add(&new->list, &iter->list);
+                        return;
+                }
+        }
+
+        list_add(&new->list, &raw_event_head);
+}
+
+static void __queue_raw_event_before(struct raw_event_queue *new,
+                                     struct raw_event_queue *iter)
+{
+        list_for_each_entry_continue_reverse(iter, &raw_event_head, list) {
+                if (iter->timestamp < new->timestamp) {
+                        list_add(&new->list, &iter->list);
+                        return;
+                }
+        }
+
+        list_add(&new->list, &raw_event_head);
+}
+
+static void __queue_raw_event_after(struct raw_event_queue *new,
+                                     struct raw_event_queue *iter)
+{
+        list_for_each_entry_continue(iter, &raw_event_head, list) {
+                if (iter->timestamp > new->timestamp) {
+                        list_add_tail(&new->list, &iter->list);
+                        return;
+                }
+        }
+        list_add_tail(&new->list, &raw_event_head);
+}
+
+/* The queue is ordered by time */
+static void __queue_raw_event(struct raw_event_queue *new)
+{
+        if (!last_inserted) {
+                __queue_raw_event_end(new);
+                return;
+        }
+
+        /*
+         * Most of the time the current event has a timestamp
+         * very close to the last event inserted, unless we just switched
+         * to another event buffer. Having a sorting based on a list and
+         * on the last inserted event that is close to the current one is
+         * probably more efficient than an rbtree based sorting.
+         */
+        if (last_inserted->timestamp >= new->timestamp)
+                __queue_raw_event_before(new, last_inserted);
+        else
+                __queue_raw_event_after(new, last_inserted);
+}
+
+static void queue_raw_event(void *data, int raw_size, int cpu,
+                            u64 timestamp, struct thread *thread)
+{
+        struct raw_event_queue *new;
+
+        if (flush_limit == ULLONG_MAX)
+                flush_limit = timestamp + FLUSH_PERIOD;
+
+        if (timestamp < last_flush) {
+                printf("Warning: Timestamp below last timeslice flush\n");
+                return;
+        }
+
+        new = malloc(sizeof(*new));
+        if (!new)
+                die("Not enough memory\n");
+
+        new->timestamp = timestamp;
+        new->cpu = cpu;
+        new->thread = thread;
+
+        new->data = malloc(raw_size);
+        if (!new->data)
+                die("Not enough memory\n");
+
+        memcpy(new->data, data, raw_size);
+
+        __queue_raw_event(new);
+        last_inserted = new;
+
+        /*
+         * We want to have a slice of events covering 2 * FLUSH_PERIOD
+         * If FLUSH_PERIOD is big enough, it ensures every events that occured
+         * in the first half of the timeslice have all been buffered and there
+         * are none remaining (we need that because of the weakly ordered
+         * event recording we have). Then once we reach the 2 * FLUSH_PERIOD
+         * timeslice, we flush the first half to be gentle with the memory
+         * (the second half can still get new events in the middle, so wait
+         * another period to flush it)
+         */
+        if (new->timestamp > flush_limit &&
+                new->timestamp - flush_limit > FLUSH_PERIOD) {
+                flush_limit += FLUSH_PERIOD;
+                flush_raw_event_queue(flush_limit);
+        }
+}
+
 static int process_sample_event(event_t *event, struct perf_session *session)
 {
         struct thread *thread;
@@ -480,7 +624,7 @@ static int process_sample_event(event_t *event, struct perf_session *session)
         if (profile_cpu != -1 && profile_cpu != (int) data.cpu)
                 return 0;
 
-        process_raw_event(data.raw_data, data.cpu, data.time, thread);
+        queue_raw_event(data.raw_data, data.raw_size, data.cpu, data.time, thread);
 
         return 0;
 }
@@ -576,6 +720,7 @@ static void __cmd_report(void)
         setup_pager();
         select_key();
         read_events();
+        flush_raw_event_queue(ULLONG_MAX);
         sort_result();
         print_result();
 }
@@ -608,7 +753,6 @@ static const char *record_args[] = {
         "record",
         "-a",
         "-R",
-        "-M",
         "-f",
         "-m", "1024",
         "-c", "1",
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index ad47bd4c50ef..152d6c9b1fa4 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -47,7 +47,6 @@
 #include "util/probe-event.h"
 
 #define MAX_PATH_LEN 256
-#define MAX_PROBES 128
 
 /* Session management structure */
 static struct {
@@ -128,7 +127,7 @@ static void evaluate_probe_point(struct probe_point *pp)
                     pp->function);
 }
 
-#ifndef NO_LIBDWARF
+#ifndef NO_DWARF_SUPPORT
 static int open_vmlinux(void)
 {
         if (map__load(session.kmaps[MAP__FUNCTION], NULL) < 0) {
@@ -156,14 +155,16 @@ static const char * const probe_usage[] = {
         "perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]",
         "perf probe [<options>] --del '[GROUP:]EVENT' ...",
         "perf probe --list",
+#ifndef NO_DWARF_SUPPORT
         "perf probe --line 'LINEDESC'",
+#endif
         NULL
 };
 
 static const struct option options[] = {
         OPT_BOOLEAN('v', "verbose", &verbose,
                     "be more verbose (show parsed arguments, etc)"),
-#ifndef NO_LIBDWARF
+#ifndef NO_DWARF_SUPPORT
         OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
                    "file", "vmlinux pathname"),
 #endif
@@ -172,30 +173,32 @@ static const struct option options[] = {
         OPT_CALLBACK('d', "del", NULL, "[GROUP:]EVENT", "delete a probe event.",
                 opt_del_probe_event),
         OPT_CALLBACK('a', "add", NULL,
-#ifdef NO_LIBDWARF
-                "[EVENT=]FUNC[+OFFS|%return] [ARG ...]",
+#ifdef NO_DWARF_SUPPORT
+                "[EVENT=]FUNC[+OFF|%return] [ARG ...]",
 #else
-                "[EVENT=]FUNC[+OFFS|%return|:RLN][@SRC]|SRC:ALN [ARG ...]",
+                "[EVENT=]FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT"
+                " [ARG ...]",
 #endif
                 "probe point definition, where\n"
                 "\t\tGROUP:\tGroup name (optional)\n"
                 "\t\tEVENT:\tEvent name\n"
                 "\t\tFUNC:\tFunction name\n"
-                "\t\tOFFS:\tOffset from function entry (in byte)\n"
+                "\t\tOFF:\tOffset from function entry (in byte)\n"
                 "\t\t%return:\tPut the probe at function return\n"
-#ifdef NO_LIBDWARF
+#ifdef NO_DWARF_SUPPORT
                 "\t\tARG:\tProbe argument (only \n"
 #else
                 "\t\tSRC:\tSource code path\n"
-                "\t\tRLN:\tRelative line number from function entry.\n"
-                "\t\tALN:\tAbsolute line number in file.\n"
+                "\t\tRL:\tRelative line number from function entry.\n"
+                "\t\tAL:\tAbsolute line number in file.\n"
+                "\t\tPT:\tLazy expression of line code.\n"
                 "\t\tARG:\tProbe argument (local variable name or\n"
 #endif
                 "\t\t\tkprobe-tracer argument format.)\n",
                 opt_add_probe_event),
         OPT_BOOLEAN('f', "force", &session.force_add, "forcibly add events"
                     " with existing name"),
-#ifndef NO_LIBDWARF
+#ifndef NO_DWARF_SUPPORT
         OPT_CALLBACK('L', "line", NULL,
                      "FUNC[:RLN[+NUM|:RLN2]]|SRC:ALN[+NUM|:ALN2]",
                      "Show source code lines.", opt_show_lines),
@@ -223,7 +226,7 @@ static void init_vmlinux(void)
 int cmd_probe(int argc, const char **argv, const char *prefix __used)
 {
         int i, ret;
-#ifndef NO_LIBDWARF
+#ifndef NO_DWARF_SUPPORT
         int fd;
 #endif
         struct probe_point *pp;
@@ -259,7 +262,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
                 return 0;
         }
 
-#ifndef NO_LIBDWARF
+#ifndef NO_DWARF_SUPPORT
         if (session.show_lines) {
                 if (session.nr_probe != 0 || session.dellist) {
                         pr_warning("  Error: Don't use --line with"
@@ -290,9 +293,9 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
         init_vmlinux();
 
         if (session.need_dwarf)
-#ifdef NO_LIBDWARF
+#ifdef NO_DWARF_SUPPORT
                 die("Debuginfo-analysis is not supported");
-#else   /* !NO_LIBDWARF */
+#else   /* !NO_DWARF_SUPPORT */
                 pr_debug("Some probes require debuginfo.\n");
 
         fd = open_vmlinux();
@@ -312,7 +315,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
                         continue;
 
                 lseek(fd, SEEK_SET, 0);
-                ret = find_probepoint(fd, pp);
+                ret = find_probe_point(fd, pp);
                 if (ret > 0)
                         continue;
                 if (ret == 0) { /* No error but failed to find probe point. */
@@ -333,7 +336,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
         close(fd);
 
 end_dwarf:
-#endif /* !NO_LIBDWARF */
+#endif /* !NO_DWARF_SUPPORT */
 
         /* Synthesize probes without dwarf */
         for (i = 0; i < session.nr_probe; i++) {
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 771533ced6a8..3b8b6387c47c 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -22,6 +22,7 @@
 #include "util/debug.h"
 #include "util/session.h"
 #include "util/symbol.h"
+#include "util/cpumap.h"
 
 #include <unistd.h>
 #include <sched.h>
@@ -244,6 +245,9 @@ static void create_counter(int counter, int cpu, pid_t pid)
 
         attr->sample_type       |= PERF_SAMPLE_IP | PERF_SAMPLE_TID;
 
+        if (nr_counters > 1)
+                attr->sample_type |= PERF_SAMPLE_ID;
+
         if (freq) {
                 attr->sample_type       |= PERF_SAMPLE_PERIOD;
                 attr->freq              = 1;
@@ -391,6 +395,9 @@ static int process_buildids(void)
 {
         u64 size = lseek(output, 0, SEEK_CUR);
 
+        if (size == 0)
+                return 0;
+
         session->fd = output;
         return __perf_session__process_events(session, post_processing_offset,
                                               size - post_processing_offset,
@@ -418,9 +425,6 @@ static int __cmd_record(int argc, const char **argv)
         char buf;
 
         page_size = sysconf(_SC_PAGE_SIZE);
-        nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
-        assert(nr_cpus <= MAX_NR_CPUS);
-        assert(nr_cpus >= 0);
 
         atexit(sig_atexit);
         signal(SIGCHLD, sig_handler);
@@ -544,8 +548,9 @@ static int __cmd_record(int argc, const char **argv)
         if ((!system_wide && !inherit) || profile_cpu != -1) {
                 open_counters(profile_cpu, target_pid);
         } else {
+                nr_cpus = read_cpu_map();
                 for (i = 0; i < nr_cpus; i++)
-                        open_counters(i, target_pid);
+                        open_counters(cpumap[i], target_pid);
         }
 
         if (file_new) {
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index cfc655d40bb7..f815de25d0fc 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -45,28 +45,71 @@ static char		*pretty_printing_style = default_pretty_printing_style;
 
 static char             callchain_default_opt[] = "fractal,0.5";
 
+static struct event_stat_id *get_stats(struct perf_session *self,
+                                       u64 event_stream, u32 type, u64 config)
+{
+        struct rb_node **p = &self->stats_by_id.rb_node;
+        struct rb_node *parent = NULL;
+        struct event_stat_id *iter, *new;
+
+        while (*p != NULL) {
+                parent = *p;
+                iter = rb_entry(parent, struct event_stat_id, rb_node);
+                if (iter->config == config)
+                        return iter;
+
+
+                if (config > iter->config)
+                        p = &(*p)->rb_right;
+                else
+                        p = &(*p)->rb_left;
+        }
+
+        new = malloc(sizeof(struct event_stat_id));
+        if (new == NULL)
+                return NULL;
+        memset(new, 0, sizeof(struct event_stat_id));
+        new->event_stream = event_stream;
+        new->config = config;
+        new->type = type;
+        rb_link_node(&new->rb_node, parent, p);
+        rb_insert_color(&new->rb_node, &self->stats_by_id);
+        return new;
+}
+
 static int perf_session__add_hist_entry(struct perf_session *self,
                                         struct addr_location *al,
-                                        struct ip_callchain *chain, u64 count)
+                                        struct sample_data *data)
 {
         struct symbol **syms = NULL, *parent = NULL;
         bool hit;
         struct hist_entry *he;
+        struct event_stat_id *stats;
+        struct perf_event_attr *attr;
 
-        if ((sort__has_parent || symbol_conf.use_callchain) && chain)
+        if ((sort__has_parent || symbol_conf.use_callchain) && data->callchain)
                 syms = perf_session__resolve_callchain(self, al->thread,
-                                                       chain, &parent);
-        he = __perf_session__add_hist_entry(self, al, parent, count, &hit);
+                                                       data->callchain, &parent);
+
+        attr = perf_header__find_attr(data->id, &self->header);
+        if (attr)
+                stats = get_stats(self, data->id, attr->type, attr->config);
+        else
+                stats = get_stats(self, data->id, 0, 0);
+        if (stats == NULL)
+                return -ENOMEM;
+        he = __perf_session__add_hist_entry(&stats->hists, al, parent,
+                                            data->period, &hit);
         if (he == NULL)
                 return -ENOMEM;
 
         if (hit)
-                he->count += count;
+                he->count += data->period;
 
         if (symbol_conf.use_callchain) {
                 if (!hit)
                         callchain_init(&he->callchain);
-                append_chain(&he->callchain, chain, syms);
+                append_chain(&he->callchain, data->callchain, syms);
                 free(syms);
         }
 
@@ -86,10 +129,30 @@ static int validate_chain(struct ip_callchain *chain, event_t *event)
         return 0;
 }
 
+static int add_event_total(struct perf_session *session,
+                           struct sample_data *data,
+                           struct perf_event_attr *attr)
+{
+        struct event_stat_id *stats;
+
+        if (attr)
+                stats = get_stats(session, data->id, attr->type, attr->config);
+        else
+                stats = get_stats(session, data->id, 0, 0);
+
+        if (!stats)
+                return -ENOMEM;
+
+        stats->stats.total += data->period;
+        session->events_stats.total += data->period;
+        return 0;
+}
+
 static int process_sample_event(event_t *event, struct perf_session *session)
 {
         struct sample_data data = { .period = 1, };
         struct addr_location al;
+        struct perf_event_attr *attr;
 
         event__parse_sample(event, session->sample_type, &data);
 
@@ -123,12 +186,18 @@ static int process_sample_event(event_t *event, struct perf_session *session)
         if (al.filtered || (hide_unresolved && al.sym == NULL))
                 return 0;
 
-        if (perf_session__add_hist_entry(session, &al, data.callchain, data.period)) {
+        if (perf_session__add_hist_entry(session, &al, &data)) {
                 pr_debug("problem incrementing symbol count, skipping event\n");
                 return -1;
         }
 
-        session->events_stats.total += data.period;
+        attr = perf_header__find_attr(data.id, &session->header);
+
+        if (add_event_total(session, &data, attr)) {
+                pr_debug("problem adding event count\n");
+                return -1;
+        }
+
         return 0;
 }
 
@@ -197,6 +266,7 @@ static int __cmd_report(void)
 {
         int ret = -EINVAL;
         struct perf_session *session;
+        struct rb_node *next;
 
         session = perf_session__new(input_name, O_RDONLY, force);
         if (session == NULL)
@@ -224,10 +294,28 @@ static int __cmd_report(void)
         if (verbose > 2)
                 dsos__fprintf(stdout);
 
-        perf_session__collapse_resort(session);
-        perf_session__output_resort(session, session->events_stats.total);
-        fprintf(stdout, "# Samples: %Ld\n#\n", session->events_stats.total);
-        perf_session__fprintf_hists(session, NULL, false, stdout);
+        next = rb_first(&session->stats_by_id);
+        while (next) {
+                struct event_stat_id *stats;
+
+                stats = rb_entry(next, struct event_stat_id, rb_node);
+                perf_session__collapse_resort(&stats->hists);
+                perf_session__output_resort(&stats->hists, stats->stats.total);
+                if (rb_first(&session->stats_by_id) ==
+                    rb_last(&session->stats_by_id))
+                        fprintf(stdout, "# Samples: %Ld\n#\n",
+                                stats->stats.total);
+                else
+                        fprintf(stdout, "# Samples: %Ld %s\n#\n",
+                                stats->stats.total,
+                                __event_name(stats->type, stats->config));
+
+                perf_session__fprintf_hists(&stats->hists, NULL, false, stdout,
+                                            stats->stats.total);
+                fprintf(stdout, "\n\n");
+                next = rb_next(&stats->rb_node);
+        }
+
         if (sort_order == default_sort_order &&
             parent_pattern == default_parent_pattern)
                 fprintf(stdout, "#\n# (For a higher level overview, try: perf report --sort comm,dso)\n#\n");
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e8c85d5aec41..95db31cff6fd 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -45,6 +45,7 @@
 #include "util/event.h"
 #include "util/debug.h"
 #include "util/header.h"
+#include "util/cpumap.h"
 
 #include <sys/prctl.h>
 #include <math.h>
@@ -151,7 +152,7 @@ static void create_perf_stat_counter(int counter, int pid)
                 unsigned int cpu;
 
                 for (cpu = 0; cpu < nr_cpus; cpu++) {
-                        fd[cpu][counter] = sys_perf_event_open(attr, -1, cpu, -1, 0);
+                        fd[cpu][counter] = sys_perf_event_open(attr, -1, cpumap[cpu], -1, 0);
                         if (fd[cpu][counter] < 0 && verbose)
                                 fprintf(stderr, ERR_PERF_OPEN, counter,
                                         fd[cpu][counter], strerror(errno));
@@ -519,9 +520,10 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
                 nr_counters = ARRAY_SIZE(default_attrs);
         }
 
-        nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
-        assert(nr_cpus <= MAX_NR_CPUS);
-        assert((int)nr_cpus >= 0);
+        if (system_wide)
+                nr_cpus = read_cpu_map();
+        else
+                nr_cpus = 1;
 
         /*
          * We dont want to block the signals - that would cause
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 31f2e597800c..1f529321607e 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -28,6 +28,7 @@
 #include <linux/rbtree.h>
 #include "util/parse-options.h"
 #include "util/parse-events.h"
+#include "util/cpumap.h"
 
 #include "util/debug.h"
 
@@ -454,7 +455,7 @@ static void print_sym_table(void)
         struct sym_entry *syme, *n;
         struct rb_root tmp = RB_ROOT;
         struct rb_node *nd;
-        int sym_width = 0, dso_width = 0, max_dso_width;
+        int sym_width = 0, dso_width = 0, dso_short_width = 0;
         const int win_width = winsize.ws_col - 1;
 
         samples = userspace_samples = 0;
@@ -544,15 +545,20 @@ static void print_sym_table(void)
                 if (syme->map->dso->long_name_len > dso_width)
                         dso_width = syme->map->dso->long_name_len;
 
+                if (syme->map->dso->short_name_len > dso_short_width)
+                        dso_short_width = syme->map->dso->short_name_len;
+
                 if (syme->name_len > sym_width)
                         sym_width = syme->name_len;
         }
 
         printed = 0;
 
-        max_dso_width = winsize.ws_col - sym_width - 29;
-        if (dso_width > max_dso_width)
-                dso_width = max_dso_width;
+        if (sym_width + dso_width > winsize.ws_col - 29) {
+                dso_width = dso_short_width;
+                if (sym_width + dso_width > winsize.ws_col - 29)
+                        sym_width = winsize.ws_col - dso_width - 29;
+        }
         putchar('\n');
         if (nr_counters == 1)
                 printf("             samples  pcnt");
@@ -1123,7 +1129,7 @@ static void start_counter(int i, int counter)
 
         cpu = profile_cpu;
         if (target_pid == -1 && profile_cpu == -1)
-                cpu = i;
+                cpu = cpumap[i];
 
         attr = attrs + counter;
 
@@ -1347,12 +1353,10 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
                 attrs[counter].sample_period = default_interval;
         }
 
-        nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
-        assert(nr_cpus <= MAX_NR_CPUS);
-        assert(nr_cpus >= 0);
-
         if (target_pid != -1 || profile_cpu != -1)
                 nr_cpus = 1;
+        else
+                nr_cpus = read_cpu_map();
 
         get_term_dimensions(&winsize);
         if (print_entries == 0) {
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 5db687fc13de..407041d20de0 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -573,7 +573,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
 
         if (symbol__init() < 0)
                 return -1;
-        setup_pager();
+        if (!script_name)
+                setup_pager();
 
         session = perf_session__new(input_name, O_RDONLY, 0);
         if (session == NULL)
@@ -608,7 +609,6 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
                         return -1;
                 }
 
-                perf_header__read(&session->header, input);
                 err = scripting_ops->generate_script("perf-trace");
                 goto out;
         }
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index 9afcff2e3ae5..db6ee94d4a8e 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -18,3 +18,4 @@ perf-top			mainporcelain common
 perf-trace                      mainporcelain common
 perf-probe                      mainporcelain common
 perf-kmem                       mainporcelain common
+perf-lock                       mainporcelain common
diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh
index 45fbe2f07b15..910468e6e01c 100644
--- a/tools/perf/perf-archive.sh
+++ b/tools/perf/perf-archive.sh
@@ -9,8 +9,9 @@ fi
 
 DEBUGDIR=~/.debug/
 BUILDIDS=$(mktemp /tmp/perf-archive-buildids.XXXXXX)
+NOBUILDID=0000000000000000000000000000000000000000
 
-perf buildid-list -i $PERF_DATA --with-hits > $BUILDIDS
+perf buildid-list -i $PERF_DATA --with-hits | grep -v "^$NOBUILDID " > $BUILDIDS
 if [ ! -s $BUILDIDS ] ; then
         echo "perf archive: no build-ids found"
         rm -f $BUILDIDS
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 57cb107c1f13..cd32c200cdb3 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -445,7 +445,7 @@ int main(int argc, const char **argv)
 
         /*
          * We use PATH to find perf commands, but we prepend some higher
-         * precidence paths: the "--exec-path" option, the PERF_EXEC_PATH
+         * precedence paths: the "--exec-path" option, the PERF_EXEC_PATH
          * environment, and the $(perfexecdir) from the Makefile at build
          * time.
          */
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 75f941bfba9e..6fb379bc1d1f 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -65,9 +65,7 @@
  * Use the __kuser_memory_barrier helper in the CPU helper page. See
  * arch/arm/kernel/entry-armv.S in the kernel source for details.
  */
-#define rmb()           asm volatile("mov r0, #0xffff0fff; mov lr, pc;" \
-                                     "sub pc, r0, #95" ::: "r0", "lr", "cc", \
-                                     "memory")
+#define rmb()           ((void(*)(void))0xffff0fa0)()
 #define cpu_relax()     asm volatile("":::"memory")
 #endif
 
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
new file mode 100644
index 000000000000..4e01490e51e5
--- /dev/null
+++ b/tools/perf/util/cpumap.c
@@ -0,0 +1,59 @@
+#include "util.h"
+#include "../perf.h"
+#include "cpumap.h"
+#include <assert.h>
+#include <stdio.h>
+
+int cpumap[MAX_NR_CPUS];
+
+static int default_cpu_map(void)
+{
+        int nr_cpus, i;
+
+        nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
+        assert(nr_cpus <= MAX_NR_CPUS);
+        assert((int)nr_cpus >= 0);
+
+        for (i = 0; i < nr_cpus; ++i)
+                cpumap[i] = i;
+
+        return nr_cpus;
+}
+
+int read_cpu_map(void)
+{
+        FILE *onlnf;
+        int nr_cpus = 0;
+        int n, cpu, prev;
+        char sep;
+
+        onlnf = fopen("/sys/devices/system/cpu/online", "r");
+        if (!onlnf)
+                return default_cpu_map();
+
+        sep = 0;
+        prev = -1;
+        for (;;) {
+                n = fscanf(onlnf, "%u%c", &cpu, &sep);
+                if (n <= 0)
+                        break;
+                if (prev >= 0) {
+                        assert(nr_cpus + cpu - prev - 1 < MAX_NR_CPUS);
+                        while (++prev < cpu)
+                                cpumap[nr_cpus++] = prev;
+                }
+                assert (nr_cpus < MAX_NR_CPUS);
+                cpumap[nr_cpus++] = cpu;
+                if (n == 2 && sep == '-')
+                        prev = cpu;
+                else
+                        prev = -1;
+                if (n == 1 || sep == '\n')
+                        break;
+        }
+        fclose(onlnf);
+        if (nr_cpus > 0)
+                return nr_cpus;
+
+        return default_cpu_map();
+}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
new file mode 100644
index 000000000000..86c78bb33098
--- /dev/null
+++ b/tools/perf/util/cpumap.h
@@ -0,0 +1,7 @@
+#ifndef __PERF_CPUMAP_H
+#define __PERF_CPUMAP_H
+
+extern int read_cpu_map(void);
+extern int cpumap[];
+
+#endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 50a7132887f5..a33b94952e34 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -99,6 +99,15 @@ struct events_stats {
         u64 lost;
 };
 
+struct event_stat_id {
+        struct rb_node          rb_node;
+        struct rb_root          hists;
+        struct events_stats     stats;
+        u64                     config;
+        u64                     event_stream;
+        u32                     type;
+};
+
 void event__print_totals(void);
 
 struct perf_session;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index e8daf5ca6fd2..2be33c7dbf03 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -12,12 +12,12 @@ struct callchain_param	callchain_param = {
  * histogram, sorted on item, collects counts
  */
 
-struct hist_entry *__perf_session__add_hist_entry(struct perf_session *self,
+struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists,
                                                   struct addr_location *al,
                                                   struct symbol *sym_parent,
                                                   u64 count, bool *hit)
 {
-        struct rb_node **p = &self->hists.rb_node;
+        struct rb_node **p = &hists->rb_node;
         struct rb_node *parent = NULL;
         struct hist_entry *he;
         struct hist_entry entry = {
@@ -53,7 +53,7 @@ struct hist_entry *__perf_session__add_hist_entry(struct perf_session *self,
                 return NULL;
         *he = entry;
         rb_link_node(&he->rb_node, parent, p);
-        rb_insert_color(&he->rb_node, &self->hists);
+        rb_insert_color(&he->rb_node, hists);
         *hit = false;
         return he;
 }
@@ -130,7 +130,7 @@ static void collapse__insert_entry(struct rb_root *root, struct hist_entry *he)
         rb_insert_color(&he->rb_node, root);
 }
 
-void perf_session__collapse_resort(struct perf_session *self)
+void perf_session__collapse_resort(struct rb_root *hists)
 {
         struct rb_root tmp;
         struct rb_node *next;
@@ -140,17 +140,17 @@ void perf_session__collapse_resort(struct perf_session *self)
                 return;
 
         tmp = RB_ROOT;
-        next = rb_first(&self->hists);
+        next = rb_first(hists);
 
         while (next) {
                 n = rb_entry(next, struct hist_entry, rb_node);
                 next = rb_next(&n->rb_node);
 
-                rb_erase(&n->rb_node, &self->hists);
+                rb_erase(&n->rb_node, hists);
                 collapse__insert_entry(&tmp, n);
         }
 
-        self->hists = tmp;
+        *hists = tmp;
 }
 
 /*
@@ -183,7 +183,7 @@ static void perf_session__insert_output_hist_entry(struct rb_root *root,
         rb_insert_color(&he->rb_node, root);
 }
 
-void perf_session__output_resort(struct perf_session *self, u64 total_samples)
+void perf_session__output_resort(struct rb_root *hists, u64 total_samples)
 {
         struct rb_root tmp;
         struct rb_node *next;
@@ -194,18 +194,18 @@ void perf_session__output_resort(struct perf_session *self, u64 total_samples)
                 total_samples * (callchain_param.min_percent / 100);
 
         tmp = RB_ROOT;
-        next = rb_first(&self->hists);
+        next = rb_first(hists);
 
         while (next) {
                 n = rb_entry(next, struct hist_entry, rb_node);
                 next = rb_next(&n->rb_node);
 
-                rb_erase(&n->rb_node, &self->hists);
+                rb_erase(&n->rb_node, hists);
                 perf_session__insert_output_hist_entry(&tmp, n,
                                                        min_callchain_hits);
         }
 
-        self->hists = tmp;
+        *hists = tmp;
 }
 
 static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
@@ -321,7 +321,7 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
                         new_depth_mask &= ~(1 << (depth - 1));
 
                 /*
-                 * But we keep the older depth mask for the line seperator
+                 * But we keep the older depth mask for the line separator
                  * to keep the level link until we reach the last child
                  */
                 ret += ipchain__fprintf_graph_line(fp, depth, depth_mask,
@@ -456,10 +456,10 @@ static size_t hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self,
 }
 
 static size_t hist_entry__fprintf(struct hist_entry *self,
-                                  struct perf_session *session,
                                   struct perf_session *pair_session,
                                   bool show_displacement,
-                                  long displacement, FILE *fp)
+                                  long displacement, FILE *fp,
+                                  u64 session_total)
 {
         struct sort_entry *se;
         u64 count, total;
@@ -474,7 +474,7 @@ static size_t hist_entry__fprintf(struct hist_entry *self,
                 total = pair_session->events_stats.total;
         } else {
                 count = self->count;
-                total = session->events_stats.total;
+                total = session_total;
         }
 
         if (total)
@@ -496,8 +496,8 @@ static size_t hist_entry__fprintf(struct hist_entry *self,
 
                 if (total > 0)
                         old_percent = (count * 100.0) / total;
-                if (session->events_stats.total > 0)
-                        new_percent = (self->count * 100.0) / session->events_stats.total;
+                if (session_total > 0)
+                        new_percent = (self->count * 100.0) / session_total;
 
                 diff = new_percent - old_percent;
 
@@ -544,16 +544,17 @@ static size_t hist_entry__fprintf(struct hist_entry *self,
                         left_margin -= thread__comm_len(self->thread);
                 }
 
-                hist_entry_callchain__fprintf(fp, self, session->events_stats.total,
+                hist_entry_callchain__fprintf(fp, self, session_total,
                                               left_margin);
         }
 
         return ret;
 }
 
-size_t perf_session__fprintf_hists(struct perf_session *self,
+size_t perf_session__fprintf_hists(struct rb_root *hists,
                                    struct perf_session *pair,
-                                   bool show_displacement, FILE *fp)
+                                   bool show_displacement, FILE *fp,
+                                   u64 session_total)
 {
         struct sort_entry *se;
         struct rb_node *nd;
@@ -641,7 +642,7 @@ size_t perf_session__fprintf_hists(struct perf_session *self,
         fprintf(fp, "\n#\n");
 
 print_entries:
-        for (nd = rb_first(&self->hists); nd; nd = rb_next(nd)) {
+        for (nd = rb_first(hists); nd; nd = rb_next(nd)) {
                 struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
                 if (show_displacement) {
@@ -652,8 +653,13 @@ print_entries:
                                 displacement = 0;
                         ++position;
                 }
-                ret += hist_entry__fprintf(h, self, pair, show_displacement,
-                                           displacement, fp);
+                ret += hist_entry__fprintf(h, pair, show_displacement,
+                                           displacement, fp, session_total);
+                if (h->map == NULL && verbose > 1) {
+                        __map_groups__fprintf_maps(&h->thread->mg,
+                                                   MAP__FUNCTION, fp);
+                        fprintf(fp, "%.10s end\n", graph_dotted_line);
+                }
         }
 
         free(rem_sq_bracket);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index e5f99b24048b..16f360cce5bf 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -10,8 +10,9 @@ struct perf_session;
 struct hist_entry;
 struct addr_location;
 struct symbol;
+struct rb_root;
 
-struct hist_entry *__perf_session__add_hist_entry(struct perf_session *self,
+struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists,
                                                   struct addr_location *al,
                                                   struct symbol *parent,
                                                   u64 count, bool *hit);
@@ -19,9 +20,10 @@ extern int64_t hist_entry__cmp(struct hist_entry *, struct hist_entry *);
 extern int64_t hist_entry__collapse(struct hist_entry *, struct hist_entry *);
 void hist_entry__free(struct hist_entry *);
 
-void perf_session__output_resort(struct perf_session *self, u64 total_samples);
-void perf_session__collapse_resort(struct perf_session *self);
-size_t perf_session__fprintf_hists(struct perf_session *self,
+void perf_session__output_resort(struct rb_root *hists, u64 total_samples);
+void perf_session__collapse_resort(struct rb_root *hists);
+size_t perf_session__fprintf_hists(struct rb_root *hists,
                                    struct perf_session *pair,
-                                   bool show_displacement, FILE *fp);
+                                   bool show_displacement, FILE *fp,
+                                   u64 session_total);
 #endif  /* __PERF_HIST_H */
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 8f0568849691..7c004b6ef24f 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -119,14 +119,14 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
         char c, nc = 0;
         /*
          * <Syntax>
-         * perf probe [EVENT=]SRC:LN
-         * perf probe [EVENT=]FUNC[+OFFS|%return][@SRC]
+         * perf probe [EVENT=]SRC[:LN|;PTN]
+         * perf probe [EVENT=]FUNC[@SRC][+OFFS|%return|:LN|;PAT]
          *
          * TODO:Group name support
          */
 
-        ptr = strchr(arg, '=');
-        if (ptr) {      /* Event name */
+        ptr = strpbrk(arg, ";=@+%");
+        if (ptr && *ptr == '=') {       /* Event name */
                 *ptr = '\0';
                 tmp = ptr + 1;
                 ptr = strchr(arg, ':');
@@ -139,7 +139,7 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
                 arg = tmp;
         }
 
-        ptr = strpbrk(arg, ":+@%");
+        ptr = strpbrk(arg, ";:+@%");
         if (ptr) {
                 nc = *ptr;
                 *ptr++ = '\0';
@@ -156,7 +156,11 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
         while (ptr) {
                 arg = ptr;
                 c = nc;
-                ptr = strpbrk(arg, ":+@%");
+                if (c == ';') { /* Lazy pattern must be the last part */
+                        pp->lazy_line = strdup(arg);
+                        break;
+                }
+                ptr = strpbrk(arg, ";:+@%");
                 if (ptr) {
                         nc = *ptr;
                         *ptr++ = '\0';
@@ -165,13 +169,13 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
                 case ':':       /* Line number */
                         pp->line = strtoul(arg, &tmp, 0);
                         if (*tmp != '\0')
-                                semantic_error("There is non-digit charactor"
-                                                " in line number.");
+                                semantic_error("There is non-digit char"
+                                               " in line number.");
                         break;
                 case '+':       /* Byte offset from a symbol */
                         pp->offset = strtoul(arg, &tmp, 0);
                         if (*tmp != '\0')
-                                semantic_error("There is non-digit charactor"
+                                semantic_error("There is non-digit character"
                                                 " in offset.");
                         break;
                 case '@':       /* File name */
@@ -179,9 +183,6 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
                                 semantic_error("SRC@SRC is not allowed.");
                         pp->file = strdup(arg);
                         DIE_IF(pp->file == NULL);
-                        if (ptr)
-                                semantic_error("@SRC must be the last "
-                                               "option.");
                         break;
                 case '%':       /* Probe places */
                         if (strcmp(arg, "return") == 0) {
@@ -196,11 +197,18 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
         }
 
         /* Exclusion check */
+        if (pp->lazy_line && pp->line)
+                semantic_error("Lazy pattern can't be used with line number.");
+
+        if (pp->lazy_line && pp->offset)
+                semantic_error("Lazy pattern can't be used with offset.");
+
         if (pp->line && pp->offset)
                 semantic_error("Offset can't be used with line number.");
 
-        if (!pp->line && pp->file && !pp->function)
-                semantic_error("File always requires line number.");
+        if (!pp->line && !pp->lazy_line && pp->file && !pp->function)
+                semantic_error("File always requires line number or "
+                               "lazy pattern.");
 
         if (pp->offset && !pp->function)
                 semantic_error("Offset requires an entry function.");
@@ -208,11 +216,13 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
         if (pp->retprobe && !pp->function)
                 semantic_error("Return probe requires an entry function.");
 
-        if ((pp->offset || pp->line) && pp->retprobe)
-                semantic_error("Offset/Line can't be used with return probe.");
+        if ((pp->offset || pp->line || pp->lazy_line) && pp->retprobe)
+                semantic_error("Offset/Line/Lazy pattern can't be used with "
+                               "return probe.");
 
-        pr_debug("symbol:%s file:%s line:%d offset:%d, return:%d\n",
-                 pp->function, pp->file, pp->line, pp->offset, pp->retprobe);
+        pr_debug("symbol:%s file:%s line:%d offset:%d return:%d lazy:%s\n",
+                 pp->function, pp->file, pp->line, pp->offset, pp->retprobe,
+                 pp->lazy_line);
 }
 
 /* Parse perf-probe event definition */
@@ -232,7 +242,7 @@ void parse_perf_probe_event(const char *str, struct probe_point *pp,
 
         /* Parse probe point */
         parse_perf_probe_probepoint(argv[0], pp);
-        if (pp->file || pp->line)
+        if (pp->file || pp->line || pp->lazy_line)
                 *need_dwarf = true;
 
         /* Copy arguments and ensure return probe has no C argument */
@@ -458,6 +468,8 @@ static void clear_probe_point(struct probe_point *pp)
                 free(pp->function);
         if (pp->file)
                 free(pp->file);
+        if (pp->lazy_line)
+                free(pp->lazy_line);
         for (i = 0; i < pp->nr_args; i++)
                 free(pp->args[i]);
         if (pp->args)
@@ -496,8 +508,8 @@ void show_perf_probe_events(void)
         struct str_node *ent;
 
         setup_pager();
-
         memset(&pp, 0, sizeof(pp));
+
         fd = open_kprobe_events(O_RDONLY, 0);
         rawlist = get_trace_kprobe_event_rawlist(fd);
         close(fd);
@@ -719,6 +731,7 @@ void del_trace_kprobe_events(struct strlist *dellist)
 }
 
 #define LINEBUF_SIZE 256
+#define NR_ADDITIONAL_LINES 2
 
 static void show_one_line(FILE *fp, unsigned int l, bool skip, bool show_num)
 {
@@ -779,5 +792,11 @@ void show_line_range(struct line_range *lr)
                         show_one_line(fp, (l++) - lr->offset, false, false);
                 show_one_line(fp, (l++) - lr->offset, false, true);
         }
+
+        if (lr->end == INT_MAX)
+                lr->end = l + NR_ADDITIONAL_LINES;
+        while (l < lr->end && !feof(fp))
+                show_one_line(fp, (l++) - lr->offset, false, false);
+
         fclose(fp);
 }
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 1b2124d12f68..c171a243d05b 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -32,21 +32,13 @@
 #include <stdarg.h>
 #include <ctype.h>
 
+#include "string.h"
 #include "event.h"
 #include "debug.h"
 #include "util.h"
 #include "probe-finder.h"
 
 
-/* Dwarf_Die Linkage to parent Die */
-struct die_link {
-        struct die_link *parent;        /* Parent die */
-        Dwarf_Die die;                  /* Current die */
-};
-
-static Dwarf_Debug __dw_debug;
-static Dwarf_Error __dw_error;
-
 /*
  * Generic dwarf analysis helpers
  */
@@ -113,281 +105,190 @@ static int strtailcmp(const char *s1, const char *s2)
         return 0;
 }
 
-/* Find the fileno of the target file. */
-static Dwarf_Unsigned cu_find_fileno(Dwarf_Die cu_die, const char *fname)
-{
-        Dwarf_Signed cnt, i;
-        Dwarf_Unsigned found = 0;
-        char **srcs;
-        int ret;
+/* Line number list operations */
 
-        if (!fname)
-                return 0;
+/* Add a line to line number list */
+static void line_list__add_line(struct list_head *head, unsigned int line)
+{
+        struct line_node *ln;
+        struct list_head *p;
 
-        ret = dwarf_srcfiles(cu_die, &srcs, &cnt, &__dw_error);
-        if (ret == DW_DLV_OK) {
-                for (i = 0; i < cnt && !found; i++) {
-                        if (strtailcmp(srcs[i], fname) == 0)
-                                found = i + 1;
-                        dwarf_dealloc(__dw_debug, srcs[i], DW_DLA_STRING);
-                }
-                for (; i < cnt; i++)
-                        dwarf_dealloc(__dw_debug, srcs[i], DW_DLA_STRING);
-                dwarf_dealloc(__dw_debug, srcs, DW_DLA_LIST);
+        /* Reverse search, because new line will be the last one */
+        list_for_each_entry_reverse(ln, head, list) {
+                if (ln->line < line) {
+                        p = &ln->list;
+                        goto found;
+                } else if (ln->line == line)    /* Already exist */
+                        return ;
         }
-        if (found)
-                pr_debug("found fno: %d\n", (int)found);
-        return found;
+        /* List is empty, or the smallest entry */
+        p = head;
+found:
+        pr_debug("line list: add a line %u\n", line);
+        ln = zalloc(sizeof(struct line_node));
+        DIE_IF(ln == NULL);
+        ln->line = line;
+        INIT_LIST_HEAD(&ln->list);
+        list_add(&ln->list, p);
 }
 
-static int cu_get_filename(Dwarf_Die cu_die, Dwarf_Unsigned fno, char **buf)
+/* Check if the line in line number list */
+static int line_list__has_line(struct list_head *head, unsigned int line)
 {
-        Dwarf_Signed cnt, i;
-        char **srcs;
-        int ret = 0;
-
-        if (!buf || !fno)
-                return -EINVAL;
-
-        ret = dwarf_srcfiles(cu_die, &srcs, &cnt, &__dw_error);
-        if (ret == DW_DLV_OK) {
-                if ((Dwarf_Unsigned)cnt > fno - 1) {
-                        *buf = strdup(srcs[fno - 1]);
-                        ret = 0;
-                        pr_debug("found filename: %s\n", *buf);
-                } else
-                        ret = -ENOENT;
-                for (i = 0; i < cnt; i++)
-                        dwarf_dealloc(__dw_debug, srcs[i], DW_DLA_STRING);
-                dwarf_dealloc(__dw_debug, srcs, DW_DLA_LIST);
-        } else
-                ret = -EINVAL;
-        return ret;
+        struct line_node *ln;
+
+        /* Reverse search, because new line will be the last one */
+        list_for_each_entry(ln, head, list)
+                if (ln->line == line)
+                        return 1;
+
+        return 0;
 }
 
-/* Compare diename and tname */
-static int die_compare_name(Dwarf_Die dw_die, const char *tname)
+/* Init line number list */
+static void line_list__init(struct list_head *head)
 {
-        char *name;
-        int ret;
-        ret = dwarf_diename(dw_die, &name, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        if (ret == DW_DLV_OK) {
-                ret = strcmp(tname, name);
-                dwarf_dealloc(__dw_debug, name, DW_DLA_STRING);
-        } else
-                ret = -1;
-        return ret;
+        INIT_LIST_HEAD(head);
 }
 
-/* Check the address is in the subprogram(function). */
-static int die_within_subprogram(Dwarf_Die sp_die, Dwarf_Addr addr,
-                                 Dwarf_Signed *offs)
+/* Free line number list */
+static void line_list__free(struct list_head *head)
 {
-        Dwarf_Addr lopc, hipc;
-        int ret;
-
-        /* TODO: check ranges */
-        ret = dwarf_lowpc(sp_die, &lopc, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        if (ret == DW_DLV_NO_ENTRY)
-                return 0;
-        ret = dwarf_highpc(sp_die, &hipc, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        if (lopc <= addr && addr < hipc) {
-                *offs = addr - lopc;
-                return 1;
-        } else
-                return 0;
+        struct line_node *ln;
+        while (!list_empty(head)) {
+                ln = list_first_entry(head, struct line_node, list);
+                list_del(&ln->list);
+                free(ln);
+        }
 }
 
-/* Check the die is inlined function */
-static Dwarf_Bool die_inlined_subprogram(Dwarf_Die dw_die)
+/* Dwarf wrappers */
+
+/* Find the realpath of the target file. */
+static const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname)
 {
-        /* TODO: check strictly */
-        Dwarf_Bool inl;
+        Dwarf_Files *files;
+        size_t nfiles, i;
+        const char *src = NULL;
         int ret;
 
-        ret = dwarf_hasattr(dw_die, DW_AT_inline, &inl, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        return inl;
-}
+        if (!fname)
+                return NULL;
 
-/* Get the offset of abstruct_origin */
-static Dwarf_Off die_get_abstract_origin(Dwarf_Die dw_die)
-{
-        Dwarf_Attribute attr;
-        Dwarf_Off cu_offs;
-        int ret;
+        ret = dwarf_getsrcfiles(cu_die, &files, &nfiles);
+        if (ret != 0)
+                return NULL;
 
-        ret = dwarf_attr(dw_die, DW_AT_abstract_origin, &attr, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        ret = dwarf_formref(attr, &cu_offs, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        dwarf_dealloc(__dw_debug, attr, DW_DLA_ATTR);
-        return cu_offs;
+        for (i = 0; i < nfiles; i++) {
+                src = dwarf_filesrc(files, i, NULL, NULL);
+                if (strtailcmp(src, fname) == 0)
+                        break;
+        }
+        return src;
 }
 
-/* Get entry pc(or low pc, 1st entry of ranges)  of the die */
-static Dwarf_Addr die_get_entrypc(Dwarf_Die dw_die)
+struct __addr_die_search_param {
+        Dwarf_Addr      addr;
+        Dwarf_Die       *die_mem;
+};
+
+static int __die_search_func_cb(Dwarf_Die *fn_die, void *data)
 {
-        Dwarf_Attribute attr;
-        Dwarf_Addr addr;
-        Dwarf_Off offs;
-        Dwarf_Ranges *ranges;
-        Dwarf_Signed cnt;
-        int ret;
+        struct __addr_die_search_param *ad = data;
 
-        /* Try to get entry pc */
-        ret = dwarf_attr(dw_die, DW_AT_entry_pc, &attr, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        if (ret == DW_DLV_OK) {
-                ret = dwarf_formaddr(attr, &addr, &__dw_error);
-                DIE_IF(ret != DW_DLV_OK);
-                dwarf_dealloc(__dw_debug, attr, DW_DLA_ATTR);
-                return addr;
+        if (dwarf_tag(fn_die) == DW_TAG_subprogram &&
+            dwarf_haspc(fn_die, ad->addr)) {
+                memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die));
+                return DWARF_CB_ABORT;
         }
+        return DWARF_CB_OK;
+}
 
-        /* Try to get low pc */
-        ret = dwarf_lowpc(dw_die, &addr, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        if (ret == DW_DLV_OK)
-                return addr;
-
-        /* Try to get ranges */
-        ret = dwarf_attr(dw_die, DW_AT_ranges, &attr, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        ret = dwarf_formref(attr, &offs, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        ret = dwarf_get_ranges(__dw_debug, offs, &ranges, &cnt, NULL,
-                                &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        addr = ranges[0].dwr_addr1;
-        dwarf_ranges_dealloc(__dw_debug, ranges, cnt);
-        return addr;
+/* Search a real subprogram including this line, */
+static Dwarf_Die *die_get_real_subprogram(Dwarf_Die *cu_die, Dwarf_Addr addr,
+                                          Dwarf_Die *die_mem)
+{
+        struct __addr_die_search_param ad;
+        ad.addr = addr;
+        ad.die_mem = die_mem;
+        /* dwarf_getscopes can't find subprogram. */
+        if (!dwarf_getfuncs(cu_die, __die_search_func_cb, &ad, 0))
+                return NULL;
+        else
+                return die_mem;
 }
 
-/*
- * Search a Die from Die tree.
- * Note: cur_link->die should be deallocated in this function.
- */
-static int __search_die_tree(struct die_link *cur_link,
-                             int (*die_cb)(struct die_link *, void *),
-                             void *data)
+/* Similar to dwarf_getfuncs, but returns inlined_subroutine if exists. */
+static Dwarf_Die *die_get_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
+                                     Dwarf_Die *die_mem)
 {
-        Dwarf_Die new_die;
-        struct die_link new_link;
+        Dwarf_Die child_die;
         int ret;
 
-        if (!die_cb)
-                return 0;
-
-        /* Check current die */
-        while (!(ret = die_cb(cur_link, data))) {
-                /* Check child die */
-                ret = dwarf_child(cur_link->die, &new_die, &__dw_error);
-                DIE_IF(ret == DW_DLV_ERROR);
-                if (ret == DW_DLV_OK) {
-                        new_link.parent = cur_link;
-                        new_link.die = new_die;
-                        ret = __search_die_tree(&new_link, die_cb, data);
-                        if (ret)
-                                break;
-                }
+        ret = dwarf_child(sp_die, die_mem);
+        if (ret != 0)
+                return NULL;
 
-                /* Move to next sibling */
-                ret = dwarf_siblingof(__dw_debug, cur_link->die, &new_die,
-                                      &__dw_error);
-                DIE_IF(ret == DW_DLV_ERROR);
-                dwarf_dealloc(__dw_debug, cur_link->die, DW_DLA_DIE);
-                cur_link->die = new_die;
-                if (ret == DW_DLV_NO_ENTRY)
-                        return 0;
-        }
-        dwarf_dealloc(__dw_debug, cur_link->die, DW_DLA_DIE);
-        return ret;
-}
+        do {
+                if (dwarf_tag(die_mem) == DW_TAG_inlined_subroutine &&
+                    dwarf_haspc(die_mem, addr))
+                        return die_mem;
 
-/* Search a die in its children's die tree */
-static int search_die_from_children(Dwarf_Die parent_die,
-                                    int (*die_cb)(struct die_link *, void *),
-                                    void *data)
-{
-        struct die_link new_link;
-        int ret;
+                if (die_get_inlinefunc(die_mem, addr, &child_die)) {
+                        memcpy(die_mem, &child_die, sizeof(Dwarf_Die));
+                        return die_mem;
+                }
+        } while (dwarf_siblingof(die_mem, die_mem) == 0);
 
-        new_link.parent = NULL;
-        ret = dwarf_child(parent_die, &new_link.die, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        if (ret == DW_DLV_OK)
-                return __search_die_tree(&new_link, die_cb, data);
-        else
-                return 0;
+        return NULL;
 }
 
-/* Find a locdesc corresponding to the address */
-static int attr_get_locdesc(Dwarf_Attribute attr, Dwarf_Locdesc *desc,
-                            Dwarf_Addr addr)
+/* Compare diename and tname */
+static bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
 {
-        Dwarf_Signed lcnt;
-        Dwarf_Locdesc **llbuf;
-        int ret, i;
-
-        ret = dwarf_loclist_n(attr, &llbuf, &lcnt, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        ret = DW_DLV_NO_ENTRY;
-        for (i = 0; i < lcnt; ++i) {
-                if (llbuf[i]->ld_lopc <= addr &&
-                    llbuf[i]->ld_hipc > addr) {
-                        memcpy(desc, llbuf[i], sizeof(Dwarf_Locdesc));
-                        desc->ld_s =
-                                malloc(sizeof(Dwarf_Loc) * llbuf[i]->ld_cents);
-                        DIE_IF(desc->ld_s == NULL);
-                        memcpy(desc->ld_s, llbuf[i]->ld_s,
-                                sizeof(Dwarf_Loc) * llbuf[i]->ld_cents);
-                        ret = DW_DLV_OK;
-                        break;
-                }
-                dwarf_dealloc(__dw_debug, llbuf[i]->ld_s, DW_DLA_LOC_BLOCK);
-                dwarf_dealloc(__dw_debug, llbuf[i], DW_DLA_LOCDESC);
-        }
-        /* Releasing loop */
-        for (; i < lcnt; ++i) {
-                dwarf_dealloc(__dw_debug, llbuf[i]->ld_s, DW_DLA_LOC_BLOCK);
-                dwarf_dealloc(__dw_debug, llbuf[i], DW_DLA_LOCDESC);
-        }
-        dwarf_dealloc(__dw_debug, llbuf, DW_DLA_LIST);
-        return ret;
+        const char *name;
+        name = dwarf_diename(dw_die);
+        DIE_IF(name == NULL);
+        return strcmp(tname, name);
 }
 
-/* Get decl_file attribute value (file number) */
-static Dwarf_Unsigned die_get_decl_file(Dwarf_Die sp_die)
+/* Get entry pc(or low pc, 1st entry of ranges)  of the die */
+static Dwarf_Addr die_get_entrypc(Dwarf_Die *dw_die)
 {
-        Dwarf_Attribute attr;
-        Dwarf_Unsigned fno;
+        Dwarf_Addr epc;
         int ret;
 
-        ret = dwarf_attr(sp_die, DW_AT_decl_file, &attr, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        dwarf_formudata(attr, &fno, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        dwarf_dealloc(__dw_debug, attr, DW_DLA_ATTR);
-        return fno;
+        ret = dwarf_entrypc(dw_die, &epc);
+        DIE_IF(ret == -1);
+        return epc;
 }
 
-/* Get decl_line attribute value (line number) */
-static Dwarf_Unsigned die_get_decl_line(Dwarf_Die sp_die)
+/* Get a variable die */
+static Dwarf_Die *die_find_variable(Dwarf_Die *sp_die, const char *name,
+                                    Dwarf_Die *die_mem)
 {
-        Dwarf_Attribute attr;
-        Dwarf_Unsigned lno;
+        Dwarf_Die child_die;
+        int tag;
         int ret;
 
-        ret = dwarf_attr(sp_die, DW_AT_decl_line, &attr, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        dwarf_formudata(attr, &lno, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        dwarf_dealloc(__dw_debug, attr, DW_DLA_ATTR);
-        return lno;
+        ret = dwarf_child(sp_die, die_mem);
+        if (ret != 0)
+                return NULL;
+
+        do {
+                tag = dwarf_tag(die_mem);
+                if ((tag == DW_TAG_formal_parameter ||
+                     tag == DW_TAG_variable) &&
+                    (die_compare_name(die_mem, name) == 0))
+                        return die_mem;
+
+                if (die_find_variable(die_mem, name, &child_die)) {
+                        memcpy(die_mem, &child_die, sizeof(Dwarf_Die));
+                        return die_mem;
+                }
+        } while (dwarf_siblingof(die_mem, die_mem) == 0);
+
+        return NULL;
 }
 
 /*
@@ -395,47 +296,45 @@ static Dwarf_Unsigned die_get_decl_line(Dwarf_Die sp_die)
  */
 
 /* Show a location */
-static void show_location(Dwarf_Loc *loc, struct probe_finder *pf)
+static void show_location(Dwarf_Op *op, struct probe_finder *pf)
 {
-        Dwarf_Small op;
-        Dwarf_Unsigned regn;
-        Dwarf_Signed offs;
+        unsigned int regn;
+        Dwarf_Word offs = 0;
         int deref = 0, ret;
         const char *regs;
 
-        op = loc->lr_atom;
-
+        /* TODO: support CFA */
         /* If this is based on frame buffer, set the offset */
-        if (op == DW_OP_fbreg) {
+        if (op->atom == DW_OP_fbreg) {
+                if (pf->fb_ops == NULL)
+                        die("The attribute of frame base is not supported.\n");
                 deref = 1;
-                offs = (Dwarf_Signed)loc->lr_number;
-                op = pf->fbloc.ld_s[0].lr_atom;
-                loc = &pf->fbloc.ld_s[0];
-        } else
-                offs = 0;
+                offs = op->number;
+                op = &pf->fb_ops[0];
+        }
 
-        if (op >= DW_OP_breg0 && op <= DW_OP_breg31) {
-                regn = op - DW_OP_breg0;
-                offs += (Dwarf_Signed)loc->lr_number;
+        if (op->atom >= DW_OP_breg0 && op->atom <= DW_OP_breg31) {
+                regn = op->atom - DW_OP_breg0;
+                offs += op->number;
                 deref = 1;
-        } else if (op >= DW_OP_reg0 && op <= DW_OP_reg31) {
-                regn = op - DW_OP_reg0;
-        } else if (op == DW_OP_bregx) {
-                regn = loc->lr_number;
-                offs += (Dwarf_Signed)loc->lr_number2;
+        } else if (op->atom >= DW_OP_reg0 && op->atom <= DW_OP_reg31) {
+                regn = op->atom - DW_OP_reg0;
+        } else if (op->atom == DW_OP_bregx) {
+                regn = op->number;
+                offs += op->number2;
                 deref = 1;
-        } else if (op == DW_OP_regx) {
-                regn = loc->lr_number;
+        } else if (op->atom == DW_OP_regx) {
+                regn = op->number;
         } else
-                die("Dwarf_OP %d is not supported.", op);
+                die("DW_OP %d is not supported.", op->atom);
 
         regs = get_arch_regstr(regn);
         if (!regs)
-                die("%lld exceeds max register number.", regn);
+                die("%u exceeds max register number.", regn);
 
         if (deref)
-                ret = snprintf(pf->buf, pf->len,
-                                 " %s=%+lld(%s)", pf->var, offs, regs);
+                ret = snprintf(pf->buf, pf->len, " %s=%+jd(%s)",
+                               pf->var, (intmax_t)offs, regs);
         else
                 ret = snprintf(pf->buf, pf->len, " %s=%s", pf->var, regs);
         DIE_IF(ret < 0);
@@ -443,52 +342,36 @@ static void show_location(Dwarf_Loc *loc, struct probe_finder *pf)
 }
 
 /* Show a variables in kprobe event format */
-static void show_variable(Dwarf_Die vr_die, struct probe_finder *pf)
+static void show_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 {
         Dwarf_Attribute attr;
-        Dwarf_Locdesc ld;
+        Dwarf_Op *expr;
+        size_t nexpr;
         int ret;
 
-        ret = dwarf_attr(vr_die, DW_AT_location, &attr, &__dw_error);
-        if (ret != DW_DLV_OK)
+        if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL)
                 goto error;
-        ret = attr_get_locdesc(attr, &ld, (pf->addr - pf->cu_base));
-        if (ret != DW_DLV_OK)
+        /* TODO: handle more than 1 exprs */
+        ret = dwarf_getlocation_addr(&attr, pf->addr, &expr, &nexpr, 1);
+        if (ret <= 0 || nexpr == 0)
                 goto error;
-        /* TODO? */
-        DIE_IF(ld.ld_cents != 1);
-        show_location(&ld.ld_s[0], pf);
-        free(ld.ld_s);
-        dwarf_dealloc(__dw_debug, attr, DW_DLA_ATTR);
+
+        show_location(expr, pf);
+        /* *expr will be cached in libdw. Don't free it. */
         return ;
 error:
+        /* TODO: Support const_value */
         die("Failed to find the location of %s at this address.\n"
             " Perhaps, it has been optimized out.", pf->var);
 }
 
-static int variable_callback(struct die_link *dlink, void *data)
-{
-        struct probe_finder *pf = (struct probe_finder *)data;
-        Dwarf_Half tag;
-        int ret;
-
-        ret = dwarf_tag(dlink->die, &tag, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        if ((tag == DW_TAG_formal_parameter ||
-             tag == DW_TAG_variable) &&
-            (die_compare_name(dlink->die, pf->var) == 0)) {
-                show_variable(dlink->die, pf);
-                return 1;
-        }
-        /* TODO: Support struct members and arrays */
-        return 0;
-}
-
 /* Find a variable in a subprogram die */
-static void find_variable(Dwarf_Die sp_die, struct probe_finder *pf)
+static void find_variable(Dwarf_Die *sp_die, struct probe_finder *pf)
 {
         int ret;
+        Dwarf_Die vr_die;
 
+        /* TODO: Support struct members and arrays */
         if (!is_c_varname(pf->var)) {
                 /* Output raw parameters */
                 ret = snprintf(pf->buf, pf->len, " %s", pf->var);
@@ -499,58 +382,51 @@ static void find_variable(Dwarf_Die sp_die, struct probe_finder *pf)
 
         pr_debug("Searching '%s' variable in context.\n", pf->var);
         /* Search child die for local variables and parameters. */
-        ret = search_die_from_children(sp_die, variable_callback, pf);
-        if (!ret)
+        if (!die_find_variable(sp_die, pf->var, &vr_die))
                 die("Failed to find '%s' in this function.", pf->var);
-}
-
-/* Get a frame base on the address */
-static void get_current_frame_base(Dwarf_Die sp_die, struct probe_finder *pf)
-{
-        Dwarf_Attribute attr;
-        int ret;
-
-        ret = dwarf_attr(sp_die, DW_AT_frame_base, &attr, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        ret = attr_get_locdesc(attr, &pf->fbloc, (pf->addr - pf->cu_base));
-        DIE_IF(ret != DW_DLV_OK);
-        dwarf_dealloc(__dw_debug, attr, DW_DLA_ATTR);
-}
 
-static void free_current_frame_base(struct probe_finder *pf)
-{
-        free(pf->fbloc.ld_s);
-        memset(&pf->fbloc, 0, sizeof(Dwarf_Locdesc));
+        show_variable(&vr_die, pf);
 }
 
 /* Show a probe point to output buffer */
-static void show_probepoint(Dwarf_Die sp_die, Dwarf_Signed offs,
-                            struct probe_finder *pf)
+static void show_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf)
 {
         struct probe_point *pp = pf->pp;
-        char *name;
+        Dwarf_Addr eaddr;
+        Dwarf_Die die_mem;
+        const char *name;
         char tmp[MAX_PROBE_BUFFER];
         int ret, i, len;
+        Dwarf_Attribute fb_attr;
+        size_t nops;
+
+        /* If no real subprogram, find a real one */
+        if (!sp_die || dwarf_tag(sp_die) != DW_TAG_subprogram) {
+                sp_die = die_get_real_subprogram(&pf->cu_die,
+                                                 pf->addr, &die_mem);
+                if (!sp_die)
+                        die("Probe point is not found in subprograms.");
+        }
 
         /* Output name of probe point */
-        ret = dwarf_diename(sp_die, &name, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        if (ret == DW_DLV_OK) {
-                ret = snprintf(tmp, MAX_PROBE_BUFFER, "%s+%u", name,
-                                (unsigned int)offs);
+        name = dwarf_diename(sp_die);
+        if (name) {
+                dwarf_entrypc(sp_die, &eaddr);
+                ret = snprintf(tmp, MAX_PROBE_BUFFER, "%s+%lu", name,
+                                (unsigned long)(pf->addr - eaddr));
                 /* Copy the function name if possible */
                 if (!pp->function) {
                         pp->function = strdup(name);
-                        pp->offset = offs;
+                        pp->offset = (size_t)(pf->addr - eaddr);
                 }
-                dwarf_dealloc(__dw_debug, name, DW_DLA_STRING);
         } else {
                 /* This function has no name. */
-                ret = snprintf(tmp, MAX_PROBE_BUFFER, "0x%llx", pf->addr);
+                ret = snprintf(tmp, MAX_PROBE_BUFFER, "0x%jx",
+                               (uintmax_t)pf->addr);
                 if (!pp->function) {
                         /* TODO: Use _stext */
                         pp->function = strdup("");
-                        pp->offset = (int)pf->addr;
+                        pp->offset = (size_t)pf->addr;
                 }
         }
         DIE_IF(ret < 0);
@@ -558,8 +434,14 @@ static void show_probepoint(Dwarf_Die sp_die, Dwarf_Signed offs,
         len = ret;
         pr_debug("Probe point found: %s\n", tmp);
 
+        /* Get the frame base attribute/ops */
+        dwarf_attr(sp_die, DW_AT_frame_base, &fb_attr);
+        ret = dwarf_getlocation_addr(&fb_attr, pf->addr, &pf->fb_ops, &nops, 1);
+        if (ret <= 0 || nops == 0)
+                pf->fb_ops = NULL;
+
         /* Find each argument */
-        get_current_frame_base(sp_die, pf);
+        /* TODO: use dwarf_cfi_addrframe */
         for (i = 0; i < pp->nr_args; i++) {
                 pf->var = pp->args[i];
                 pf->buf = &tmp[len];
@@ -567,289 +449,325 @@ static void show_probepoint(Dwarf_Die sp_die, Dwarf_Signed offs,
                 find_variable(sp_die, pf);
                 len += strlen(pf->buf);
         }
-        free_current_frame_base(pf);
+
+        /* *pf->fb_ops will be cached in libdw. Don't free it. */
+        pf->fb_ops = NULL;
+
+        if (pp->found == MAX_PROBES)
+                die("Too many( > %d) probe point found.\n", MAX_PROBES);
 
         pp->probes[pp->found] = strdup(tmp);
         pp->found++;
 }
 
-static int probeaddr_callback(struct die_link *dlink, void *data)
+/* Find probe point from its line number */
+static void find_probe_point_by_line(struct probe_finder *pf)
 {
-        struct probe_finder *pf = (struct probe_finder *)data;
-        Dwarf_Half tag;
-        Dwarf_Signed offs;
+        Dwarf_Lines *lines;
+        Dwarf_Line *line;
+        size_t nlines, i;
+        Dwarf_Addr addr;
+        int lineno;
         int ret;
 
-        ret = dwarf_tag(dlink->die, &tag, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        /* Check the address is in this subprogram */
-        if (tag == DW_TAG_subprogram &&
-            die_within_subprogram(dlink->die, pf->addr, &offs)) {
-                show_probepoint(dlink->die, offs, pf);
-                return 1;
+        ret = dwarf_getsrclines(&pf->cu_die, &lines, &nlines);
+        DIE_IF(ret != 0);
+
+        for (i = 0; i < nlines; i++) {
+                line = dwarf_onesrcline(lines, i);
+                dwarf_lineno(line, &lineno);
+                if (lineno != pf->lno)
+                        continue;
+
+                /* TODO: Get fileno from line, but how? */
+                if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0)
+                        continue;
+
+                ret = dwarf_lineaddr(line, &addr);
+                DIE_IF(ret != 0);
+                pr_debug("Probe line found: line[%d]:%d addr:0x%jx\n",
+                         (int)i, lineno, (uintmax_t)addr);
+                pf->addr = addr;
+
+                show_probe_point(NULL, pf);
+                /* Continuing, because target line might be inlined. */
         }
-        return 0;
 }
 
-/* Find probe point from its line number */
-static void find_probe_point_by_line(struct probe_finder *pf)
+/* Find lines which match lazy pattern */
+static int find_lazy_match_lines(struct list_head *head,
+                                 const char *fname, const char *pat)
+{
+        char *fbuf, *p1, *p2;
+        int fd, line, nlines = 0;
+        struct stat st;
+
+        fd = open(fname, O_RDONLY);
+        if (fd < 0)
+                die("failed to open %s", fname);
+        DIE_IF(fstat(fd, &st) < 0);
+        fbuf = malloc(st.st_size + 2);
+        DIE_IF(fbuf == NULL);
+        DIE_IF(read(fd, fbuf, st.st_size) < 0);
+        close(fd);
+        fbuf[st.st_size] = '\n';        /* Dummy line */
+        fbuf[st.st_size + 1] = '\0';
+        p1 = fbuf;
+        line = 1;
+        while ((p2 = strchr(p1, '\n')) != NULL) {
+                *p2 = '\0';
+                if (strlazymatch(p1, pat)) {
+                        line_list__add_line(head, line);
+                        nlines++;
+                }
+                line++;
+                p1 = p2 + 1;
+        }
+        free(fbuf);
+        return nlines;
+}
+
+/* Find probe points from lazy pattern  */
+static void find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
 {
-        Dwarf_Signed cnt, i, clm;
-        Dwarf_Line *lines;
-        Dwarf_Unsigned lineno = 0;
+        Dwarf_Lines *lines;
+        Dwarf_Line *line;
+        size_t nlines, i;
         Dwarf_Addr addr;
-        Dwarf_Unsigned fno;
+        Dwarf_Die die_mem;
+        int lineno;
         int ret;
 
-        ret = dwarf_srclines(pf->cu_die, &lines, &cnt, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
+        if (list_empty(&pf->lcache)) {
+                /* Matching lazy line pattern */
+                ret = find_lazy_match_lines(&pf->lcache, pf->fname,
+                                            pf->pp->lazy_line);
+                if (ret <= 0)
+                        die("No matched lines found in %s.", pf->fname);
+        }
 
-        for (i = 0; i < cnt; i++) {
-                ret = dwarf_line_srcfileno(lines[i], &fno, &__dw_error);
-                DIE_IF(ret != DW_DLV_OK);
-                if (fno != pf->fno)
+        ret = dwarf_getsrclines(&pf->cu_die, &lines, &nlines);
+        DIE_IF(ret != 0);
+        for (i = 0; i < nlines; i++) {
+                line = dwarf_onesrcline(lines, i);
+
+                dwarf_lineno(line, &lineno);
+                if (!line_list__has_line(&pf->lcache, lineno))
                         continue;
 
-                ret = dwarf_lineno(lines[i], &lineno, &__dw_error);
-                DIE_IF(ret != DW_DLV_OK);
-                if (lineno != pf->lno)
+                /* TODO: Get fileno from line, but how? */
+                if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0)
                         continue;
 
-                ret = dwarf_lineoff(lines[i], &clm, &__dw_error);
-                DIE_IF(ret != DW_DLV_OK);
+                ret = dwarf_lineaddr(line, &addr);
+                DIE_IF(ret != 0);
+                if (sp_die) {
+                        /* Address filtering 1: does sp_die include addr? */
+                        if (!dwarf_haspc(sp_die, addr))
+                                continue;
+                        /* Address filtering 2: No child include addr? */
+                        if (die_get_inlinefunc(sp_die, addr, &die_mem))
+                                continue;
+                }
 
-                ret = dwarf_lineaddr(lines[i], &addr, &__dw_error);
-                DIE_IF(ret != DW_DLV_OK);
-                pr_debug("Probe line found: line[%d]:%u,%d addr:0x%llx\n",
-                         (int)i, (unsigned)lineno, (int)clm, addr);
+                pr_debug("Probe line found: line[%d]:%d addr:0x%llx\n",
+                         (int)i, lineno, (unsigned long long)addr);
                 pf->addr = addr;
-                /* Search a real subprogram including this line, */
-                ret = search_die_from_children(pf->cu_die,
-                                               probeaddr_callback, pf);
-                if (ret == 0)
-                        die("Probe point is not found in subprograms.");
+
+                show_probe_point(sp_die, pf);
                 /* Continuing, because target line might be inlined. */
         }
-        dwarf_srclines_dealloc(__dw_debug, lines, cnt);
+        /* TODO: deallocate lines, but how? */
+}
+
+static int probe_point_inline_cb(Dwarf_Die *in_die, void *data)
+{
+        struct probe_finder *pf = (struct probe_finder *)data;
+        struct probe_point *pp = pf->pp;
+
+        if (pp->lazy_line)
+                find_probe_point_lazy(in_die, pf);
+        else {
+                /* Get probe address */
+                pf->addr = die_get_entrypc(in_die);
+                pf->addr += pp->offset;
+                pr_debug("found inline addr: 0x%jx\n",
+                         (uintmax_t)pf->addr);
+
+                show_probe_point(in_die, pf);
+        }
+
+        return DWARF_CB_OK;
 }
 
 /* Search function from function name */
-static int probefunc_callback(struct die_link *dlink, void *data)
+static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 {
         struct probe_finder *pf = (struct probe_finder *)data;
         struct probe_point *pp = pf->pp;
-        struct die_link *lk;
-        Dwarf_Signed offs;
-        Dwarf_Half tag;
-        int ret;
 
-        ret = dwarf_tag(dlink->die, &tag, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        if (tag == DW_TAG_subprogram) {
-                if (die_compare_name(dlink->die, pp->function) == 0) {
-                        if (pp->line) { /* Function relative line */
-                                pf->fno = die_get_decl_file(dlink->die);
-                                pf->lno = die_get_decl_line(dlink->die)
-                                         + pp->line;
-                                find_probe_point_by_line(pf);
-                                return 1;
-                        }
-                        if (die_inlined_subprogram(dlink->die)) {
-                                /* Inlined function, save it. */
-                                ret = dwarf_die_CU_offset(dlink->die,
-                                                          &pf->inl_offs,
-                                                          &__dw_error);
-                                DIE_IF(ret != DW_DLV_OK);
-                                pr_debug("inline definition offset %lld\n",
-                                         pf->inl_offs);
-                                return 0;       /* Continue to search */
-                        }
-                        /* Get probe address */
-                        pf->addr = die_get_entrypc(dlink->die);
+        /* Check tag and diename */
+        if (dwarf_tag(sp_die) != DW_TAG_subprogram ||
+            die_compare_name(sp_die, pp->function) != 0)
+                return 0;
+
+        pf->fname = dwarf_decl_file(sp_die);
+        if (pp->line) { /* Function relative line */
+                dwarf_decl_line(sp_die, &pf->lno);
+                pf->lno += pp->line;
+                find_probe_point_by_line(pf);
+        } else if (!dwarf_func_inline(sp_die)) {
+                /* Real function */
+                if (pp->lazy_line)
+                        find_probe_point_lazy(sp_die, pf);
+                else {
+                        pf->addr = die_get_entrypc(sp_die);
                         pf->addr += pp->offset;
                         /* TODO: Check the address in this function */
-                        show_probepoint(dlink->die, pp->offset, pf);
-                        return 1; /* Exit; no same symbol in this CU. */
+                        show_probe_point(sp_die, pf);
                 }
-        } else if (tag == DW_TAG_inlined_subroutine && pf->inl_offs) {
-                if (die_get_abstract_origin(dlink->die) == pf->inl_offs) {
-                        /* Get probe address */
-                        pf->addr = die_get_entrypc(dlink->die);
-                        pf->addr += pp->offset;
-                        pr_debug("found inline addr: 0x%llx\n", pf->addr);
-                        /* Inlined function. Get a real subprogram */
-                        for (lk = dlink->parent; lk != NULL; lk = lk->parent) {
-                                tag = 0;
-                                dwarf_tag(lk->die, &tag, &__dw_error);
-                                DIE_IF(ret == DW_DLV_ERROR);
-                                if (tag == DW_TAG_subprogram &&
-                                    !die_inlined_subprogram(lk->die))
-                                        goto found;
-                        }
-                        die("Failed to find real subprogram.");
-found:
-                        /* Get offset from subprogram */
-                        ret = die_within_subprogram(lk->die, pf->addr, &offs);
-                        DIE_IF(!ret);
-                        show_probepoint(lk->die, offs, pf);
-                        /* Continue to search */
-                }
-        }
-        return 0;
+        } else
+                /* Inlined function: search instances */
+                dwarf_func_inline_instances(sp_die, probe_point_inline_cb, pf);
+
+        return 1; /* Exit; no same symbol in this CU. */
 }
 
 static void find_probe_point_by_func(struct probe_finder *pf)
 {
-        search_die_from_children(pf->cu_die, probefunc_callback, pf);
+        dwarf_getfuncs(&pf->cu_die, probe_point_search_cb, pf, 0);
 }
 
 /* Find a probe point */
-int find_probepoint(int fd, struct probe_point *pp)
+int find_probe_point(int fd, struct probe_point *pp)
 {
-        Dwarf_Half addr_size = 0;
-        Dwarf_Unsigned next_cuh = 0;
-        int cu_number = 0, ret;
         struct probe_finder pf = {.pp = pp};
+        Dwarf_Off off, noff;
+        size_t cuhl;
+        Dwarf_Die *diep;
+        Dwarf *dbg;
 
-        ret = dwarf_init(fd, DW_DLC_READ, 0, 0, &__dw_debug, &__dw_error);
-        if (ret != DW_DLV_OK)
+        dbg = dwarf_begin(fd, DWARF_C_READ);
+        if (!dbg)
                 return -ENOENT;
 
         pp->found = 0;
-        while (++cu_number) {
-                /* Search CU (Compilation Unit) */
-                ret = dwarf_next_cu_header(__dw_debug, NULL, NULL, NULL,
-                        &addr_size, &next_cuh, &__dw_error);
-                DIE_IF(ret == DW_DLV_ERROR);
-                if (ret == DW_DLV_NO_ENTRY)
-                        break;
-
+        off = 0;
+        line_list__init(&pf.lcache);
+        /* Loop on CUs (Compilation Unit) */
+        while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL)) {
                 /* Get the DIE(Debugging Information Entry) of this CU */
-                ret = dwarf_siblingof(__dw_debug, 0, &pf.cu_die, &__dw_error);
-                DIE_IF(ret != DW_DLV_OK);
+                diep = dwarf_offdie(dbg, off + cuhl, &pf.cu_die);
+                if (!diep)
+                        continue;
 
                 /* Check if target file is included. */
                 if (pp->file)
-                        pf.fno = cu_find_fileno(pf.cu_die, pp->file);
-
-                if (!pp->file || pf.fno) {
-                        /* Save CU base address (for frame_base) */
-                        ret = dwarf_lowpc(pf.cu_die, &pf.cu_base, &__dw_error);
-                        DIE_IF(ret == DW_DLV_ERROR);
-                        if (ret == DW_DLV_NO_ENTRY)
-                                pf.cu_base = 0;
+                        pf.fname = cu_find_realpath(&pf.cu_die, pp->file);
+                else
+                        pf.fname = NULL;
+
+                if (!pp->file || pf.fname) {
                         if (pp->function)
                                 find_probe_point_by_func(&pf);
+                        else if (pp->lazy_line)
+                                find_probe_point_lazy(NULL, &pf);
                         else {
                                 pf.lno = pp->line;
                                 find_probe_point_by_line(&pf);
                         }
                 }
-                dwarf_dealloc(__dw_debug, pf.cu_die, DW_DLA_DIE);
+                off = noff;
         }
-        ret = dwarf_finish(__dw_debug, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
+        line_list__free(&pf.lcache);
+        dwarf_end(dbg);
 
         return pp->found;
 }
 
-
-static void line_range_add_line(struct line_range *lr, unsigned int line)
-{
-        struct line_node *ln;
-        struct list_head *p;
-
-        /* Reverse search, because new line will be the last one */
-        list_for_each_entry_reverse(ln, &lr->line_list, list) {
-                if (ln->line < line) {
-                        p = &ln->list;
-                        goto found;
-                } else if (ln->line == line)    /* Already exist */
-                        return ;
-        }
-        /* List is empty, or the smallest entry */
-        p = &lr->line_list;
-found:
-        pr_debug("Debug: add a line %u\n", line);
-        ln = zalloc(sizeof(struct line_node));
-        DIE_IF(ln == NULL);
-        ln->line = line;
-        INIT_LIST_HEAD(&ln->list);
-        list_add(&ln->list, p);
-}
-
 /* Find line range from its line number */
-static void find_line_range_by_line(struct line_finder *lf)
+static void find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
 {
-        Dwarf_Signed cnt, i;
-        Dwarf_Line *lines;
-        Dwarf_Unsigned lineno = 0;
-        Dwarf_Unsigned fno;
+        Dwarf_Lines *lines;
+        Dwarf_Line *line;
+        size_t nlines, i;
         Dwarf_Addr addr;
+        int lineno;
         int ret;
+        const char *src;
+        Dwarf_Die die_mem;
 
-        ret = dwarf_srclines(lf->cu_die, &lines, &cnt, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
+        line_list__init(&lf->lr->line_list);
+        ret = dwarf_getsrclines(&lf->cu_die, &lines, &nlines);
+        DIE_IF(ret != 0);
 
-        for (i = 0; i < cnt; i++) {
-                ret = dwarf_line_srcfileno(lines[i], &fno, &__dw_error);
-                DIE_IF(ret != DW_DLV_OK);
-                if (fno != lf->fno)
-                        continue;
-
-                ret = dwarf_lineno(lines[i], &lineno, &__dw_error);
-                DIE_IF(ret != DW_DLV_OK);
+        for (i = 0; i < nlines; i++) {
+                line = dwarf_onesrcline(lines, i);
+                ret = dwarf_lineno(line, &lineno);
+                DIE_IF(ret != 0);
                 if (lf->lno_s > lineno || lf->lno_e < lineno)
                         continue;
 
-                /* Filter line in the function address range */
-                if (lf->addr_s && lf->addr_e) {
-                        ret = dwarf_lineaddr(lines[i], &addr, &__dw_error);
-                        DIE_IF(ret != DW_DLV_OK);
-                        if (lf->addr_s > addr || lf->addr_e <= addr)
+                if (sp_die) {
+                        /* Address filtering 1: does sp_die include addr? */
+                        ret = dwarf_lineaddr(line, &addr);
+                        DIE_IF(ret != 0);
+                        if (!dwarf_haspc(sp_die, addr))
+                                continue;
+
+                        /* Address filtering 2: No child include addr? */
+                        if (die_get_inlinefunc(sp_die, addr, &die_mem))
                                 continue;
                 }
-                line_range_add_line(lf->lr, (unsigned int)lineno);
+
+                /* TODO: Get fileno from line, but how? */
+                src = dwarf_linesrc(line, NULL, NULL);
+                if (strtailcmp(src, lf->fname) != 0)
+                        continue;
+
+                /* Copy real path */
+                if (!lf->lr->path)
+                        lf->lr->path = strdup(src);
+                line_list__add_line(&lf->lr->line_list, (unsigned int)lineno);
         }
-        dwarf_srclines_dealloc(__dw_debug, lines, cnt);
+        /* Update status */
         if (!list_empty(&lf->lr->line_list))
                 lf->found = 1;
+        else {
+                free(lf->lr->path);
+                lf->lr->path = NULL;
+        }
+}
+
+static int line_range_inline_cb(Dwarf_Die *in_die, void *data)
+{
+        find_line_range_by_line(in_die, (struct line_finder *)data);
+        return DWARF_CB_ABORT;  /* No need to find other instances */
 }
 
 /* Search function from function name */
-static int linefunc_callback(struct die_link *dlink, void *data)
+static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 {
         struct line_finder *lf = (struct line_finder *)data;
         struct line_range *lr = lf->lr;
-        Dwarf_Half tag;
-        int ret;
 
-        ret = dwarf_tag(dlink->die, &tag, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        if (tag == DW_TAG_subprogram &&
-            die_compare_name(dlink->die, lr->function) == 0) {
-                /* Get the address range of this function */
-                ret = dwarf_highpc(dlink->die, &lf->addr_e, &__dw_error);
-                if (ret == DW_DLV_OK)
-                        ret = dwarf_lowpc(dlink->die, &lf->addr_s, &__dw_error);
-                DIE_IF(ret == DW_DLV_ERROR);
-                if (ret == DW_DLV_NO_ENTRY) {
-                        lf->addr_s = 0;
-                        lf->addr_e = 0;
-                }
-
-                lf->fno = die_get_decl_file(dlink->die);
-                lr->offset = die_get_decl_line(dlink->die);;
+        if (dwarf_tag(sp_die) == DW_TAG_subprogram &&
+            die_compare_name(sp_die, lr->function) == 0) {
+                lf->fname = dwarf_decl_file(sp_die);
+                dwarf_decl_line(sp_die, &lr->offset);
+                pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset);
                 lf->lno_s = lr->offset + lr->start;
                 if (!lr->end)
-                        lf->lno_e = (Dwarf_Unsigned)-1;
+                        lf->lno_e = INT_MAX;
                 else
                         lf->lno_e = lr->offset + lr->end;
                 lr->start = lf->lno_s;
                 lr->end = lf->lno_e;
-                find_line_range_by_line(lf);
-                /* If we find a target function, this should be end. */
-                lf->found = 1;
+                if (dwarf_func_inline(sp_die))
+                        dwarf_func_inline_instances(sp_die,
+                                                    line_range_inline_cb, lf);
+                else
+                        find_line_range_by_line(sp_die, lf);
                 return 1;
         }
         return 0;
@@ -857,55 +775,55 @@ static int linefunc_callback(struct die_link *dlink, void *data)
 
 static void find_line_range_by_func(struct line_finder *lf)
 {
-        search_die_from_children(lf->cu_die, linefunc_callback, lf);
+        dwarf_getfuncs(&lf->cu_die, line_range_search_cb, lf, 0);
 }
 
 int find_line_range(int fd, struct line_range *lr)
 {
-        Dwarf_Half addr_size = 0;
-        Dwarf_Unsigned next_cuh = 0;
+        struct line_finder lf = {.lr = lr, .found = 0};
         int ret;
-        struct line_finder lf = {.lr = lr};
+        Dwarf_Off off = 0, noff;
+        size_t cuhl;
+        Dwarf_Die *diep;
+        Dwarf *dbg;
 
-        ret = dwarf_init(fd, DW_DLC_READ, 0, 0, &__dw_debug, &__dw_error);
-        if (ret != DW_DLV_OK)
+        dbg = dwarf_begin(fd, DWARF_C_READ);
+        if (!dbg)
                 return -ENOENT;
 
+        /* Loop on CUs (Compilation Unit) */
         while (!lf.found) {
-                /* Search CU (Compilation Unit) */
-                ret = dwarf_next_cu_header(__dw_debug, NULL, NULL, NULL,
-                        &addr_size, &next_cuh, &__dw_error);
-                DIE_IF(ret == DW_DLV_ERROR);
-                if (ret == DW_DLV_NO_ENTRY)
+                ret = dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL);
+                if (ret != 0)
                         break;
 
                 /* Get the DIE(Debugging Information Entry) of this CU */
-                ret = dwarf_siblingof(__dw_debug, 0, &lf.cu_die, &__dw_error);
-                DIE_IF(ret != DW_DLV_OK);
+                diep = dwarf_offdie(dbg, off + cuhl, &lf.cu_die);
+                if (!diep)
+                        continue;
 
                 /* Check if target file is included. */
                 if (lr->file)
-                        lf.fno = cu_find_fileno(lf.cu_die, lr->file);
+                        lf.fname = cu_find_realpath(&lf.cu_die, lr->file);
+                else
+                        lf.fname = 0;
 
-                if (!lr->file || lf.fno) {
+                if (!lr->file || lf.fname) {
                         if (lr->function)
                                 find_line_range_by_func(&lf);
                         else {
                                 lf.lno_s = lr->start;
                                 if (!lr->end)
-                                        lf.lno_e = (Dwarf_Unsigned)-1;
+                                        lf.lno_e = INT_MAX;
                                 else
                                         lf.lno_e = lr->end;
-                                find_line_range_by_line(&lf);
+                                find_line_range_by_line(NULL, &lf);
                         }
-                        /* Get the real file path */
-                        if (lf.found)
-                                cu_get_filename(lf.cu_die, lf.fno, &lr->path);
                 }
-                dwarf_dealloc(__dw_debug, lf.cu_die, DW_DLA_DIE);
+                off = noff;
         }
-        ret = dwarf_finish(__dw_debug, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
+        pr_debug("path: %lx\n", (unsigned long)lr->path);
+        dwarf_end(dbg);
         return lf.found;
 }
 
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 972b386116f1..21f7354397b4 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -1,6 +1,7 @@
 #ifndef _PROBE_FINDER_H
 #define _PROBE_FINDER_H
 
+#include <stdbool.h>
 #include "util.h"
 
 #define MAX_PATH_LEN             256
@@ -20,6 +21,7 @@ struct probe_point {
         /* Inputs */
         char                    *file;                  /* File name */
         int                     line;                   /* Line number */
+        char                    *lazy_line;             /* Lazy line pattern */
 
         char                    *function;              /* Function name */
         int                     offset;                 /* Offset bytes */
@@ -46,53 +48,45 @@ struct line_range {
         char                    *function;              /* Function name */
         unsigned int            start;                  /* Start line number */
         unsigned int            end;                    /* End line number */
-        unsigned int            offset;                 /* Start line offset */
+        int                     offset;                 /* Start line offset */
         char                    *path;                  /* Real path name */
         struct list_head        line_list;              /* Visible lines */
 };
 
-#ifndef NO_LIBDWARF
-extern int find_probepoint(int fd, struct probe_point *pp);
+#ifndef NO_DWARF_SUPPORT
+extern int find_probe_point(int fd, struct probe_point *pp);
 extern int find_line_range(int fd, struct line_range *lr);
 
-/* Workaround for undefined _MIPS_SZLONG bug in libdwarf.h: */
-#ifndef _MIPS_SZLONG
-# define _MIPS_SZLONG           0
-#endif
-
 #include <dwarf.h>
-#include <libdwarf.h>
+#include <libdw.h>
 
 struct probe_finder {
-        struct probe_point      *pp;                    /* Target probe point */
+        struct probe_point      *pp;            /* Target probe point */
 
         /* For function searching */
-        Dwarf_Addr              addr;                   /* Address */
-        Dwarf_Unsigned          fno;                    /* File number */
-        Dwarf_Unsigned          lno;                    /* Line number */
-        Dwarf_Off               inl_offs;               /* Inline offset */
-        Dwarf_Die               cu_die;                 /* Current CU */
+        Dwarf_Addr              addr;           /* Address */
+        const char              *fname;         /* File name */
+        int                     lno;            /* Line number */
+        Dwarf_Die               cu_die;         /* Current CU */
 
         /* For variable searching */
-        Dwarf_Addr              cu_base;                /* Current CU base address */
-        Dwarf_Locdesc           fbloc;                  /* Location of Current Frame Base */
-        const char              *var;                   /* Current variable name */
-        char                    *buf;                   /* Current output buffer */
-        int                     len;                    /* Length of output buffer */
+        Dwarf_Op                *fb_ops;        /* Frame base attribute */
+        const char              *var;           /* Current variable name */
+        char                    *buf;           /* Current output buffer */
+        int                     len;            /* Length of output buffer */
+        struct list_head        lcache;         /* Line cache for lazy match */
 };
 
 struct line_finder {
-        struct line_range       *lr;                    /* Target line range */
-
-        Dwarf_Unsigned          fno;                    /* File number */
-        Dwarf_Unsigned          lno_s;                  /* Start line number */
-        Dwarf_Unsigned          lno_e;                  /* End line number */
-        Dwarf_Addr              addr_s;                 /* Start address */
-        Dwarf_Addr              addr_e;                 /* End address */
-        Dwarf_Die               cu_die;                 /* Current CU */
+        struct line_range       *lr;            /* Target line range */
+
+        const char              *fname;         /* File name */
+        int                     lno_s;          /* Start line number */
+        int                     lno_e;          /* End line number */
+        Dwarf_Die               cu_die;         /* Current CU */
         int                     found;
 };
 
-#endif /* NO_LIBDWARF */
+#endif /* NO_DWARF_SUPPORT */
 
 #endif /*_PROBE_FINDER_H */
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 33a414bbba3e..6a72f14c5986 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -208,7 +208,7 @@ static void python_process_event(int cpu, void *data,
                                  int size __unused,
                                  unsigned long long nsecs, char *comm)
 {
-        PyObject *handler, *retval, *context, *t;
+        PyObject *handler, *retval, *context, *t, *obj;
         static char handler_name[256];
         struct format_field *field;
         unsigned long long val;
@@ -256,16 +256,23 @@ static void python_process_event(int cpu, void *data,
                                 offset &= 0xffff;
                         } else
                                 offset = field->offset;
-                        PyTuple_SetItem(t, n++,
-                                PyString_FromString((char *)data + offset));
+                        obj = PyString_FromString((char *)data + offset);
                 } else { /* FIELD_IS_NUMERIC */
                         val = read_size(data + field->offset, field->size);
                         if (field->flags & FIELD_IS_SIGNED) {
-                                PyTuple_SetItem(t, n++, PyInt_FromLong(val));
+                                if ((long long)val >= LONG_MIN &&
+                                    (long long)val <= LONG_MAX)
+                                        obj = PyInt_FromLong(val);
+                                else
+                                        obj = PyLong_FromLongLong(val);
                         } else {
-                                PyTuple_SetItem(t, n++, PyInt_FromLong(val));
+                                if (val <= LONG_MAX)
+                                        obj = PyInt_FromLong(val);
+                                else
+                                        obj = PyLong_FromUnsignedLongLong(val);
                         }
                 }
+                PyTuple_SetItem(t, n++, obj);
         }
 
         if (_PyTuple_Resize(&t, n) == -1)
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0de7258e70a5..eed1cb889008 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -70,6 +70,7 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc
 
         memcpy(self->filename, filename, len);
         self->threads = RB_ROOT;
+        self->stats_by_id = RB_ROOT;
         self->last_match = NULL;
         self->mmap_window = 32;
         self->cwd = NULL;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 31950fcd8a4d..5c33417eebb3 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -20,6 +20,7 @@ struct perf_session {
         struct thread           *last_match;
         struct map              *vmlinux_maps[MAP__NR_TYPES];
         struct events_stats     events_stats;
+        struct rb_root          stats_by_id;
         unsigned long           event_total[PERF_RECORD_MAX];
         unsigned long           unknown_events;
         struct rb_root          hists;
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index c397d4f6f748..a175949ed216 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -265,21 +265,21 @@ error:
         return false;
 }
 
-/**
- * strglobmatch - glob expression pattern matching
- * @str: the target string to match
- * @pat: the pattern string to match
- *
- * This returns true if the @str matches @pat. @pat can includes wildcards
- * ('*','?') and character classes ([CHARS], complementation and ranges are
- * also supported). Also, this supports escape character ('\') to use special
- * characters as normal character.
- *
- * Note: if @pat syntax is broken, this always returns false.
- */
-bool strglobmatch(const char *str, const char *pat)
+/* Glob/lazy pattern matching */
+static bool __match_glob(const char *str, const char *pat, bool ignore_space)
 {
         while (*str && *pat && *pat != '*') {
+                if (ignore_space) {
+                        /* Ignore spaces for lazy matching */
+                        if (isspace(*str)) {
+                                str++;
+                                continue;
+                        }
+                        if (isspace(*pat)) {
+                                pat++;
+                                continue;
+                        }
+                }
                 if (*pat == '?') {      /* Matches any single character */
                         str++;
                         pat++;
@@ -308,3 +308,32 @@ bool strglobmatch(const char *str, const char *pat)
         return !*str && !*pat;
 }
 
+/**
+ * strglobmatch - glob expression pattern matching
+ * @str: the target string to match
+ * @pat: the pattern string to match
+ *
+ * This returns true if the @str matches @pat. @pat can includes wildcards
+ * ('*','?') and character classes ([CHARS], complementation and ranges are
+ * also supported). Also, this supports escape character ('\') to use special
+ * characters as normal character.
+ *
+ * Note: if @pat syntax is broken, this always returns false.
+ */
+bool strglobmatch(const char *str, const char *pat)
+{
+        return __match_glob(str, pat, false);
+}
+
+/**
+ * strlazymatch - matching pattern strings lazily with glob pattern
+ * @str: the target string to match
+ * @pat: the pattern string to match
+ *
+ * This is similar to strglobmatch, except this ignores spaces in
+ * the target string.
+ */
+bool strlazymatch(const char *str, const char *pat)
+{
+        return __match_glob(str, pat, true);
+}
diff --git a/tools/perf/util/string.h b/tools/perf/util/string.h
index 02ede58c54b4..542e44de3719 100644
--- a/tools/perf/util/string.h
+++ b/tools/perf/util/string.h
@@ -10,6 +10,7 @@ s64 perf_atoll(const char *str);
 char **argv_split(const char *str, int *argcp);
 void argv_free(char **argv);
 bool strglobmatch(const char *str, const char *pat);
+bool strlazymatch(const char *str, const char *pat);
 
 #define _STR(x) #x
 #define STR(x) _STR(x)
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 323c0aea0a91..c458c4a371d1 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -163,9 +163,17 @@ void dso__set_long_name(struct dso *self, char *name)
         self->long_name_len = strlen(name);
 }
 
+static void dso__set_short_name(struct dso *self, const char *name)
+{
+        if (name == NULL)
+                return;
+        self->short_name = name;
+        self->short_name_len = strlen(name);
+}
+
 static void dso__set_basename(struct dso *self)
 {
-        self->short_name = basename(self->long_name);
+        dso__set_short_name(self, basename(self->long_name));
 }
 
 struct dso *dso__new(const char *name)
@@ -176,7 +184,7 @@ struct dso *dso__new(const char *name)
                 int i;
                 strcpy(self->name, name);
                 dso__set_long_name(self, self->name);
-                self->short_name = self->name;
+                dso__set_short_name(self, self->name);
                 for (i = 0; i < MAP__NR_TYPES; ++i)
                         self->symbols[i] = self->symbol_names[i] = RB_ROOT;
                 self->slen_calculated = 0;
@@ -897,7 +905,6 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
         struct kmap *kmap = self->kernel ? map__kmap(map) : NULL;
         struct map *curr_map = map;
         struct dso *curr_dso = self;
-        size_t dso_name_len = strlen(self->short_name);
         Elf_Data *symstrs, *secstrs;
         uint32_t nr_syms;
         int err = -1;
@@ -987,7 +994,8 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
                         char dso_name[PATH_MAX];
 
                         if (strcmp(section_name,
-                                   curr_dso->short_name + dso_name_len) == 0)
+                                   (curr_dso->short_name +
+                                    self->short_name_len)) == 0)
                                 goto new_symbol;
 
                         if (strcmp(section_name, ".text") == 0) {
@@ -1782,7 +1790,7 @@ struct dso *dso__new_kernel(const char *name)
         struct dso *self = dso__new(name ?: "[kernel.kallsyms]");
 
         if (self != NULL) {
-                self->short_name = "[kernel]";
+                dso__set_short_name(self, "[kernel]");
                 self->kernel     = 1;
         }
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 280dadd32a08..f30a37428919 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -110,9 +110,10 @@ struct dso {
         u8               sorted_by_name;
         u8               loaded;
         u8               build_id[BUILD_ID_SIZE];
-        u16              long_name_len;
         const char       *short_name;
         char             *long_name;
+        u16              long_name_len;
+        u16              short_name_len;
         char             name[0];
 };
 
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 21b92162282b..fa968312ee7d 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -79,8 +79,8 @@ int thread__comm_len(struct thread *self)
         return self->comm_len;
 }
 
-static size_t __map_groups__fprintf_maps(struct map_groups *self,
-                                         enum map_type type, FILE *fp)
+size_t __map_groups__fprintf_maps(struct map_groups *self,
+                                  enum map_type type, FILE *fp)
 {
         size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
         struct rb_node *nd;
@@ -89,7 +89,7 @@ static size_t __map_groups__fprintf_maps(struct map_groups *self,
                 struct map *pos = rb_entry(nd, struct map, rb_node);
                 printed += fprintf(fp, "Map:");
                 printed += map__fprintf(pos, fp);
-                if (verbose > 1) {
+                if (verbose > 2) {
                         printed += dso__fprintf(pos->dso, type, fp);
                         printed += fprintf(fp, "--\n");
                 }
@@ -183,8 +183,8 @@ struct thread *perf_session__findnew(struct perf_session *self, pid_t pid)
         return th;
 }
 
-static void map_groups__remove_overlappings(struct map_groups *self,
-                                            struct map *map)
+static int map_groups__fixup_overlappings(struct map_groups *self,
+                                          struct map *map)
 {
         struct rb_root *root = &self->maps[map->type];
         struct rb_node *next = rb_first(root);
@@ -209,7 +209,36 @@ static void map_groups__remove_overlappings(struct map_groups *self,
                  * list.
                  */
                 list_add_tail(&pos->node, &self->removed_maps[map->type]);
+                /*
+                 * Now check if we need to create new maps for areas not
+                 * overlapped by the new map:
+                 */
+                if (map->start > pos->start) {
+                        struct map *before = map__clone(pos);
+
+                        if (before == NULL)
+                                return -ENOMEM;
+
+                        before->end = map->start - 1;
+                        map_groups__insert(self, before);
+                        if (verbose >= 2)
+                                map__fprintf(before, stderr);
+                }
+
+                if (map->end < pos->end) {
+                        struct map *after = map__clone(pos);
+
+                        if (after == NULL)
+                                return -ENOMEM;
+
+                        after->start = map->end + 1;
+                        map_groups__insert(self, after);
+                        if (verbose >= 2)
+                                map__fprintf(after, stderr);
+                }
         }
+
+        return 0;
 }
 
 void maps__insert(struct rb_root *maps, struct map *map)
@@ -254,7 +283,7 @@ struct map *maps__find(struct rb_root *maps, u64 ip)
 
 void thread__insert_map(struct thread *self, struct map *map)
 {
-        map_groups__remove_overlappings(&self->mg, map);
+        map_groups__fixup_overlappings(&self->mg, map);
         map_groups__insert(&self->mg, map);
 }
 
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 0a28f39de545..dcf70303e58e 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -10,6 +10,9 @@ struct map_groups {
         struct list_head        removed_maps[MAP__NR_TYPES];
 };
 
+size_t __map_groups__fprintf_maps(struct map_groups *self,
+                                  enum map_type type, FILE *fp);
+
 struct thread {
         struct rb_node          rb_node;
         struct map_groups       mg;