30 files changed, 520 insertions, 112 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/Makefile b/tools/perf/Makefile
index 2d537382c686..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
 
@@ -488,19 +492,19 @@ 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 '\#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) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -I/usr/include/elfutils -ldw -lelf -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
+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
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 c30a33592340..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 {
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.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 44408c2621cf..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)
@@ -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 c971e81e9cbf..7c004b6ef24f 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -242,7 +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 */
@@ -508,8 +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);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index e77dc886760e..c171a243d05b 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -169,7 +169,7 @@ static const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname)
 {
         Dwarf_Files *files;
         size_t nfiles, i;
-        const char *src;
+        const char *src = NULL;
         int ret;
 
         if (!fname)
@@ -333,8 +333,8 @@ static void show_location(Dwarf_Op *op, struct probe_finder *pf)
                 die("%u exceeds max register number.", regn);
 
         if (deref)
-                ret = snprintf(pf->buf, pf->len, " %s=+%ju(%s)",
-                               pf->var, (uintmax_t)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);
@@ -352,8 +352,7 @@ static void show_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
         if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL)
                 goto error;
         /* TODO: handle more than 1 exprs */
-        ret = dwarf_getlocation_addr(&attr, (pf->addr - pf->cu_base),
-                                     &expr, &nexpr, 1);
+        ret = dwarf_getlocation_addr(&attr, pf->addr, &expr, &nexpr, 1);
         if (ret <= 0 || nexpr == 0)
                 goto error;
 
@@ -437,8 +436,7 @@ static void show_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf)
 
         /* 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->cu_base),
-                                     &pf->fb_ops, &nops, 1);
+        ret = dwarf_getlocation_addr(&fb_attr, pf->addr, &pf->fb_ops, &nops, 1);
         if (ret <= 0 || nops == 0)
                 pf->fb_ops = NULL;
 
@@ -455,6 +453,9 @@ static void show_probe_point(Dwarf_Die *sp_die, struct probe_finder *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++;
 }
@@ -641,7 +642,6 @@ static void find_probe_point_by_func(struct probe_finder *pf)
 int find_probe_point(int fd, struct probe_point *pp)
 {
         struct probe_finder pf = {.pp = pp};
-        int ret;
         Dwarf_Off off, noff;
         size_t cuhl;
         Dwarf_Die *diep;
@@ -668,10 +668,6 @@ int find_probe_point(int fd, struct probe_point *pp)
                         pf.fname = NULL;
 
                 if (!pp->file || pf.fname) {
-                        /* Save CU base address (for frame_base) */
-                        ret = dwarf_lowpc(&pf.cu_die, &pf.cu_base);
-                        if (ret != 0)
-                                pf.cu_base = 0;
                         if (pp->function)
                                 find_probe_point_by_func(&pf);
                         else if (pp->lazy_line)
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index d1a651793ba6..21f7354397b4 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -71,7 +71,6 @@ struct probe_finder {
 
         /* For variable searching */
         Dwarf_Op                *fb_ops;        /* Frame base attribute */
-        Dwarf_Addr              cu_base;        /* Current CU base address */
         const char              *var;           /* Current variable name */
         char                    *buf;           /* Current output buffer */
         int                     len;            /* Length of output buffer */
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/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;