Merge branch 'perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux-2.6 into perf/core

30 files changed, 328 insertions, 96 deletions

diff --git a/Makefile b/Makefile
index 6e39ec701cbf..6e186a1bb1ea 100644
--- a/Makefile
+++ b/Makefile
@@ -411,7 +411,7 @@ endif
 no-dot-config-targets := clean mrproper distclean \
                          cscope TAGS tags help %docs check% \
                          include/linux/version.h headers_% \
-                         kernelrelease kernelversion
+                         kernelrelease kernelversion %src-pkg
 
 config-targets := 0
 mixed-targets  := 0
@@ -1215,6 +1215,8 @@ distclean: mrproper
 # rpm target kept for backward compatibility
 package-dir     := $(srctree)/scripts/package
 
+%src-pkg: FORCE
+        $(Q)$(MAKE) $(build)=$(package-dir) $@
 %pkg: include/config/kernel.release FORCE
         $(Q)$(MAKE) $(build)=$(package-dir) $@
 rpm: include/config/kernel.release FORCE
diff --git a/scripts/package/Makefile b/scripts/package/Makefile
index 62fcc3a7f4d3..18513b0191db 100644
--- a/scripts/package/Makefile
+++ b/scripts/package/Makefile
@@ -111,13 +111,38 @@ tar%pkg: FORCE
 clean-dirs += $(objtree)/tar-install/
 
 
+# perf-pkg - generate a source tarball with perf source
+# ---------------------------------------------------------------------------
+
+perf-tar=perf-$(KERNELVERSION)
+
+quiet_cmd_perf_tar = TAR
+      cmd_perf_tar = \
+git archive --prefix=$(perf-tar)/ HEAD^{tree}                       \
+        $$(cat $(srctree)/tools/perf/MANIFEST) -o $(perf-tar).tar;  \
+mkdir -p $(perf-tar);                                               \
+git rev-parse HEAD > $(perf-tar)/HEAD;                              \
+tar rf $(perf-tar).tar $(perf-tar)/HEAD;                            \
+rm -r $(perf-tar);                                                  \
+$(if $(findstring tar-src,$@),,                                     \
+$(if $(findstring bz2,$@),bzip2,                                    \
+$(if $(findstring gz,$@),gzip,                                      \
+$(error unknown target $@)))                                       \
+        -f -9 $(perf-tar).tar)
+
+perf-%pkg: FORCE
+        $(call cmd,perf_tar)
+
 # Help text displayed when executing 'make help'
 # ---------------------------------------------------------------------------
 help: FORCE
-        @echo '  rpm-pkg         - Build both source and binary RPM kernel packages'
-        @echo '  binrpm-pkg      - Build only the binary kernel package'
-        @echo '  deb-pkg         - Build the kernel as an deb package'
-        @echo '  tar-pkg         - Build the kernel as an uncompressed tarball'
-        @echo '  targz-pkg       - Build the kernel as a gzip compressed tarball'
-        @echo '  tarbz2-pkg      - Build the kernel as a bzip2 compressed tarball'
+        @echo '  rpm-pkg             - Build both source and binary RPM kernel packages'
+        @echo '  binrpm-pkg          - Build only the binary kernel package'
+        @echo '  deb-pkg             - Build the kernel as an deb package'
+        @echo '  tar-pkg             - Build the kernel as an uncompressed tarball'
+        @echo '  targz-pkg           - Build the kernel as a gzip compressed tarball'
+        @echo '  tarbz2-pkg          - Build the kernel as a bzip2 compressed tarball'
+        @echo '  perf-tar-src-pkg    - Build $(perf-tar).tar source tarball'
+        @echo '  perf-targz-src-pkg  - Build $(perf-tar).tar.gz source tarball'
+        @echo '  perf-tarbz2-src-pkg - Build $(perf-tar).tar.bz2 source tarball'
 
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 34e255fc3e2f..25576b477c83 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -103,6 +103,13 @@ OPTIONS
 --raw-samples::
 Collect raw sample records from all opened counters (default for tracepoint counters).
 
+-C::
+--cpu::
+Collect samples only on the list of cpus provided. Multiple CPUs can be provided as a
+comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+In per-thread mode with inheritance mode on (default), samples are captured only when
+the thread executes on the designated CPUs. Default is to monitor all CPUs.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 909fa766fa1c..4b3a2d46b437 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -46,6 +46,13 @@ OPTIONS
 -B::
         print large numbers with thousands' separators according to locale
 
+-C::
+--cpu=::
+Count only on the list of cpus provided. Multiple CPUs can be provided as a
+comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+In per-thread mode, this option is ignored. The -a option is still necessary
+to activate system-wide monitoring. Default is to count on all CPUs.
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 785b9fc32a46..1f9687663f2a 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -25,9 +25,11 @@ OPTIONS
 --count=<count>::
         Event period to sample.
 
--C <cpu>::
---CPU=<cpu>::
-        CPU to profile.
+-C <cpu-list>::
+--cpu=<cpu>::
+Monitor only on the list of cpus provided. Multiple CPUs can be provided as a
+comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+Default is to monitor all CPUS.
 
 -d <seconds>::
 --delay=<seconds>::
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
new file mode 100644
index 000000000000..8c7fc0c8f0b8
--- /dev/null
+++ b/tools/perf/MANIFEST
@@ -0,0 +1,12 @@
+tools/perf
+include/linux/perf_event.h
+include/linux/rbtree.h
+include/linux/list.h
+include/linux/hash.h
+include/linux/stringify.h
+lib/rbtree.c
+include/linux/swab.h
+arch/*/include/asm/unistd*.h
+include/linux/poison.h
+include/linux/magic.h
+include/linux/hw_breakpoint.h
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 96db5248e995..fd20670ce986 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -61,11 +61,9 @@ static int hists__add_entry(struct hists *self, struct addr_location *al)
 static int process_sample_event(event_t *event, struct perf_session *session)
 {
         struct addr_location al;
+        struct sample_data data;
 
-        dump_printf("(IP, %d): %d: %#Lx\n", event->header.misc,
-                    event->ip.pid, event->ip.ip);
-
-        if (event__preprocess_sample(event, session, &al, NULL) < 0) {
+        if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) {
                 pr_warning("problem processing %d event, skipping it.\n",
                            event->header.type);
                 return -1;
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index f8e3d1852029..29ad20e67919 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -78,8 +78,7 @@ static int __cmd_buildid_cache(void)
         struct str_node *pos;
         char debugdir[PATH_MAX];
 
-        snprintf(debugdir, sizeof(debugdir), "%s/%s", getenv("HOME"),
-                 DEBUG_CACHE_DIR);
+        snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir);
 
         if (add_name_list_str) {
                 list = strlist__new(true, add_name_list_str);
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index a6e2fdc7a04e..39e6627ebb96 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -35,10 +35,7 @@ static int diff__process_sample_event(event_t *event, struct perf_session *sessi
         struct addr_location al;
         struct sample_data data = { .period = 1, };
 
-        dump_printf("(IP, %d): %d: %#Lx\n", event->header.misc,
-                    event->ip.pid, event->ip.ip);
-
-        if (event__preprocess_sample(event, session, &al, NULL) < 0) {
+        if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) {
                 pr_warning("problem processing %d event, skipping it.\n",
                            event->header.type);
                 return -1;
@@ -47,8 +44,6 @@ static int diff__process_sample_event(event_t *event, struct perf_session *sessi
         if (al.filtered || al.sym == NULL)
                 return 0;
 
-        event__parse_sample(event, session->sample_type, &data);
-
         if (hists__add_entry(&session->hists, &al, data.period)) {
                 pr_warning("problem incrementing symbol period, skipping event\n");
                 return -1;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index dc3435e18bde..5e5c6403a315 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -49,7 +49,6 @@ static int			group				=      0;
 static int                      realtime_prio                   =      0;
 static bool                     raw_samples                     =  false;
 static bool                     system_wide                     =  false;
-static int                      profile_cpu                     =     -1;
 static pid_t                    target_pid                      =     -1;
 static pid_t                    target_tid                      =     -1;
 static pid_t                    *all_tids                       =      NULL;
@@ -74,6 +73,7 @@ static int			file_new			=      1;
 static off_t                    post_processing_offset;
 
 static struct perf_session      *session;
+static const char               *cpu_list;
 
 struct mmap_data {
         int                     counter;
@@ -274,6 +274,9 @@ static void create_counter(int counter, int cpu)
         if (call_graph)
                 attr->sample_type       |= PERF_SAMPLE_CALLCHAIN;
 
+        if (system_wide)
+                attr->sample_type       |= PERF_SAMPLE_CPU;
+
         if (raw_samples) {
                 attr->sample_type       |= PERF_SAMPLE_TIME;
                 attr->sample_type       |= PERF_SAMPLE_RAW;
@@ -300,7 +303,7 @@ try_again:
                                 die("Permission error - are you root?\n"
                                         "\t Consider tweaking"
                                         " /proc/sys/kernel/perf_event_paranoid.\n");
-                        else if (err ==  ENODEV && profile_cpu != -1) {
+                        else if (err ==  ENODEV && cpu_list) {
                                 die("No such device - did you specify"
                                         " an out-of-range profile CPU?\n");
                         }
@@ -622,10 +625,15 @@ static int __cmd_record(int argc, const char **argv)
                 close(child_ready_pipe[0]);
         }
 
-        if ((!system_wide && no_inherit) || profile_cpu != -1) {
-                open_counters(profile_cpu);
+        nr_cpus = read_cpu_map(cpu_list);
+        if (nr_cpus < 1) {
+                perror("failed to collect number of CPUs\n");
+                return -1;
+        }
+
+        if (!system_wide && no_inherit && !cpu_list) {
+                open_counters(-1);
         } else {
-                nr_cpus = read_cpu_map();
                 for (i = 0; i < nr_cpus; i++)
                         open_counters(cpumap[i]);
         }
@@ -704,7 +712,7 @@ static int __cmd_record(int argc, const char **argv)
         if (perf_guest)
                 perf_session__process_machines(session, event__synthesize_guest_os);
 
-        if (!system_wide && profile_cpu == -1)
+        if (!system_wide && cpu_list)
                 event__synthesize_thread(target_tid, process_synthesized_event,
                                          session);
         else
@@ -794,8 +802,8 @@ static const struct option options[] = {
                             "system-wide collection from all CPUs"),
         OPT_BOOLEAN('A', "append", &append_file,
                             "append to the output file to do incremental profiling"),
-        OPT_INTEGER('C', "profile_cpu", &profile_cpu,
-                            "CPU to profile on"),
+        OPT_STRING('C', "cpu", &cpu_list, "cpu",
+                    "list of cpus to monitor"),
         OPT_BOOLEAN('f', "force", &force,
                         "overwrite existing data file (deprecated)"),
         OPT_U64('c', "count", &user_interval, "event period to sample"),
@@ -825,7 +833,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
         argc = parse_options(argc, argv, options, record_usage,
                             PARSE_OPT_STOP_AT_NON_OPTION);
         if (!argc && target_pid == -1 && target_tid == -1 &&
-                !system_wide && profile_cpu == -1)
+                !system_wide && !cpu_list)
                 usage_with_options(record_usage, options);
 
         if (force && append_file) {
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 359205782964..371a3c995806 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -155,30 +155,7 @@ static int process_sample_event(event_t *event, struct perf_session *session)
         struct addr_location al;
         struct perf_event_attr *attr;
 
-        event__parse_sample(event, session->sample_type, &data);
-
-        dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc,
-                    data.pid, data.tid, data.ip, data.period);
-
-        if (session->sample_type & PERF_SAMPLE_CALLCHAIN) {
-                unsigned int i;
-
-                dump_printf("... chain: nr:%Lu\n", data.callchain->nr);
-
-                if (!ip_callchain__valid(data.callchain, event)) {
-                        pr_debug("call-chain problem with event, "
-                                 "skipping it.\n");
-                        return 0;
-                }
-
-                if (dump_trace) {
-                        for (i = 0; i < data.callchain->nr; i++)
-                                dump_printf("..... %2d: %016Lx\n",
-                                            i, data.callchain->ips[i]);
-                }
-        }
-
-        if (event__preprocess_sample(event, session, &al, NULL) < 0) {
+        if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) {
                 fprintf(stderr, "problem processing %d event, skipping it.\n",
                         event->header.type);
                 return -1;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 9a39ca3c3ac4..a6b4d44f9502 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -69,7 +69,7 @@ static struct perf_event_attr default_attrs[] = {
 };
 
 static bool                     system_wide                     =  false;
-static unsigned int             nr_cpus                         =  0;
+static int                      nr_cpus                         =  0;
 static int                      run_idx                         =  0;
 
 static int                      run_count                       =  1;
@@ -82,6 +82,7 @@ static int			thread_num			=  0;
 static pid_t                    child_pid                       = -1;
 static bool                     null_run                        =  false;
 static bool                     big_num                         =  false;
+static const char               *cpu_list;
 
 
 static int                      *fd[MAX_NR_CPUS][MAX_COUNTERS];
@@ -158,7 +159,7 @@ static int create_perf_stat_counter(int counter)
                                     PERF_FORMAT_TOTAL_TIME_RUNNING;
 
         if (system_wide) {
-                unsigned int cpu;
+                int cpu;
 
                 for (cpu = 0; cpu < nr_cpus; cpu++) {
                         fd[cpu][counter][0] = sys_perf_event_open(attr,
@@ -208,7 +209,7 @@ static inline int nsec_counter(int counter)
 static void read_counter(int counter)
 {
         u64 count[3], single_count[3];
-        unsigned int cpu;
+        int cpu;
         size_t res, nv;
         int scaled;
         int i, thread;
@@ -542,6 +543,8 @@ static const struct option options[] = {
                     "null run - dont start any counters"),
         OPT_BOOLEAN('B', "big-num", &big_num,
                     "print large numbers with thousands\' separators"),
+        OPT_STRING('C', "cpu", &cpu_list, "cpu",
+                    "list of cpus to monitor in system-wide"),
         OPT_END()
 };
 
@@ -566,10 +569,13 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
         }
 
         if (system_wide)
-                nr_cpus = read_cpu_map();
+                nr_cpus = read_cpu_map(cpu_list);
         else
                 nr_cpus = 1;
 
+        if (nr_cpus < 1)
+                usage_with_options(stat_usage, options);
+
         if (target_pid != -1) {
                 target_tid = target_pid;
                 thread_num = find_all_tid(target_pid, &all_tids);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index a66f4272b994..1e8e92e317b9 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -102,6 +102,7 @@ struct sym_entry		*sym_filter_entry_sched		=   NULL;
 static int                      sym_pcnt_filter                 =      5;
 static int                      sym_counter                     =      0;
 static int                      display_weighted                =     -1;
+static const char               *cpu_list;
 
 /*
  * Symbols
@@ -982,6 +983,7 @@ static void event__process_sample(const event_t *self,
         u64 ip = self->ip.ip;
         struct sym_entry *syme;
         struct addr_location al;
+        struct sample_data data;
         struct machine *machine;
         u8 origin = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
@@ -1024,7 +1026,8 @@ static void event__process_sample(const event_t *self,
         if (self->header.misc & PERF_RECORD_MISC_EXACT_IP)
                 exact_samples++;
 
-        if (event__preprocess_sample(self, session, &al, symbol_filter) < 0 ||
+        if (event__preprocess_sample(self, session, &al, &data,
+                                     symbol_filter) < 0 ||
             al.filtered)
                 return;
 
@@ -1351,8 +1354,8 @@ static const struct option options[] = {
                     "profile events on existing thread id"),
         OPT_BOOLEAN('a', "all-cpus", &system_wide,
                             "system-wide collection from all CPUs"),
-        OPT_INTEGER('C', "CPU", &profile_cpu,
-                    "CPU to profile on"),
+        OPT_STRING('C', "cpu", &cpu_list, "cpu",
+                    "list of cpus to monitor"),
         OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
                    "file", "vmlinux pathname"),
         OPT_BOOLEAN('K', "hide_kernel_symbols", &hide_kernel_symbols,
@@ -1428,10 +1431,10 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
                 return -ENOMEM;
 
         /* CPU and PID are mutually exclusive */
-        if (target_tid > 0 && profile_cpu != -1) {
+        if (target_tid > 0 && cpu_list) {
                 printf("WARNING: PID switch overriding CPU\n");
                 sleep(1);
-                profile_cpu = -1;
+                cpu_list = NULL;
         }
 
         if (!nr_counters)
@@ -1469,10 +1472,13 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
                 attrs[counter].sample_period = default_interval;
         }
 
-        if (target_tid != -1 || profile_cpu != -1)
+        if (target_tid != -1)
                 nr_cpus = 1;
         else
-                nr_cpus = read_cpu_map();
+                nr_cpus = read_cpu_map(cpu_list);
+
+        if (nr_cpus < 1)
+                usage_with_options(top_usage, options);
 
         get_term_dimensions(&winsize);
         if (print_entries == 0) {
diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh
index 2e7a4f417e20..677e59d62a8d 100644
--- a/tools/perf/perf-archive.sh
+++ b/tools/perf/perf-archive.sh
@@ -7,7 +7,17 @@ if [ $# -ne 0 ] ; then
         PERF_DATA=$1
 fi
 
-DEBUGDIR=~/.debug/
+#
+# PERF_BUILDID_DIR environment variable set by perf
+# path to buildid directory, default to $HOME/.debug
+#
+if [ -z $PERF_BUILDID_DIR ]; then
+        PERF_BUILDID_DIR=~/.debug/
+else
+        # append / to make substitutions work
+        PERF_BUILDID_DIR=$PERF_BUILDID_DIR/
+fi
+
 BUILDIDS=$(mktemp /tmp/perf-archive-buildids.XXXXXX)
 NOBUILDID=0000000000000000000000000000000000000000
 
@@ -22,13 +32,13 @@ MANIFEST=$(mktemp /tmp/perf-archive-manifest.XXXXXX)
 
 cut -d ' ' -f 1 $BUILDIDS | \
 while read build_id ; do
-        linkname=$DEBUGDIR.build-id/${build_id:0:2}/${build_id:2}
+        linkname=$PERF_BUILDID_DIR.build-id/${build_id:0:2}/${build_id:2}
         filename=$(readlink -f $linkname)
-        echo ${linkname#$DEBUGDIR} >> $MANIFEST
-        echo ${filename#$DEBUGDIR} >> $MANIFEST
+        echo ${linkname#$PERF_BUILDID_DIR} >> $MANIFEST
+        echo ${filename#$PERF_BUILDID_DIR} >> $MANIFEST
 done
 
-tar cfj $PERF_DATA.tar.bz2 -C $DEBUGDIR -T $MANIFEST
+tar cfj $PERF_DATA.tar.bz2 -C $PERF_BUILDID_DIR -T $MANIFEST
 rm -f $MANIFEST $BUILDIDS
 echo -e "Now please run:\n"
 echo -e "$ tar xvf $PERF_DATA.tar.bz2 -C ~/.debug\n"
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 6e4871191138..cdd6c03f1e14 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -458,6 +458,8 @@ int main(int argc, const char **argv)
         handle_options(&argv, &argc, NULL);
         commit_pager_choice();
         set_debugfs_path();
+        set_buildid_dir();
+
         if (argc > 0) {
                 if (!prefixcmp(argv[0], "--"))
                         argv[0] += 2;
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 70c5cf87d020..5c26e2d314af 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -43,19 +43,17 @@ struct perf_event_ops build_id__mark_dso_hit_ops = {
 char *dso__build_id_filename(struct dso *self, char *bf, size_t size)
 {
         char build_id_hex[BUILD_ID_SIZE * 2 + 1];
-        const char *home;
 
         if (!self->has_build_id)
                 return NULL;
 
         build_id__sprintf(self->build_id, sizeof(self->build_id), build_id_hex);
-        home = getenv("HOME");
         if (bf == NULL) {
-                if (asprintf(&bf, "%s/%s/.build-id/%.2s/%s", home,
-                             DEBUG_CACHE_DIR, build_id_hex, build_id_hex + 2) < 0)
+                if (asprintf(&bf, "%s/.build-id/%.2s/%s", buildid_dir,
+                             build_id_hex, build_id_hex + 2) < 0)
                         return NULL;
         } else
-                snprintf(bf, size, "%s/%s/.build-id/%.2s/%s", home,
-                         DEBUG_CACHE_DIR, build_id_hex, build_id_hex + 2);
+                snprintf(bf, size, "%s/.build-id/%.2s/%s", buildid_dir,
+                         build_id_hex, build_id_hex + 2);
         return bf;
 }
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 65fe664fddf6..27e9ebe4076e 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -23,6 +23,7 @@ extern int perf_config(config_fn_t fn, void *);
 extern int perf_config_int(const char *, const char *);
 extern int perf_config_bool(const char *, const char *);
 extern int config_error_nonbool(const char *);
+extern const char *perf_config_dirname(const char *, const char *);
 
 /* pager.c */
 extern void setup_pager(void);
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 62b69ad4aa73..e63c997d6c1b 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -18,7 +18,7 @@
 #include "util.h"
 #include "callchain.h"
 
-bool ip_callchain__valid(struct ip_callchain *chain, event_t *event)
+bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event)
 {
         unsigned int chain_size = event->header.size;
         chain_size -= (unsigned long)&event->ip.__more_data - (unsigned long)event;
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 1ca73e4a2723..809850fb75fb 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -60,5 +60,5 @@ int register_callchain_param(struct callchain_param *param);
 int append_chain(struct callchain_node *root, struct ip_callchain *chain,
                  struct map_symbol *syms);
 
-bool ip_callchain__valid(struct ip_callchain *chain, event_t *event);
+bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event);
 #endif  /* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index dabe892d0e53..e02d78cae70f 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -11,6 +11,11 @@
 
 #define MAXNAME (256)
 
+#define DEBUG_CACHE_DIR ".debug"
+
+
+char buildid_dir[MAXPATHLEN]; /* root dir for buildid, binary cache */
+
 static FILE *config_file;
 static const char *config_file_name;
 static int config_linenr;
@@ -127,7 +132,7 @@ static int get_value(config_fn_t fn, void *data, char *name, unsigned int len)
                         break;
                 if (!iskeychar(c))
                         break;
-                name[len++] = tolower(c);
+                name[len++] = c;
                 if (len >= MAXNAME)
                         return -1;
         }
@@ -327,6 +332,13 @@ int perf_config_bool(const char *name, const char *value)
         return !!perf_config_bool_or_int(name, value, &discard);
 }
 
+const char *perf_config_dirname(const char *name, const char *value)
+{
+        if (!name)
+                return NULL;
+        return value;
+}
+
 static int perf_default_core_config(const char *var __used, const char *value __used)
 {
         /* Add other config variables here and to Documentation/config.txt. */
@@ -428,3 +440,53 @@ int config_error_nonbool(const char *var)
 {
         return error("Missing value for '%s'", var);
 }
+
+struct buildid_dir_config {
+        char *dir;
+};
+
+static int buildid_dir_command_config(const char *var, const char *value,
+                                      void *data)
+{
+        struct buildid_dir_config *c = data;
+        const char *v;
+
+        /* same dir for all commands */
+        if (!prefixcmp(var, "buildid.") && !strcmp(var + 8, "dir")) {
+                v = perf_config_dirname(var, value);
+                if (!v)
+                        return -1;
+                strncpy(c->dir, v, MAXPATHLEN-1);
+                c->dir[MAXPATHLEN-1] = '\0';
+        }
+        return 0;
+}
+
+static void check_buildid_dir_config(void)
+{
+        struct buildid_dir_config c;
+        c.dir = buildid_dir;
+        perf_config(buildid_dir_command_config, &c);
+}
+
+void set_buildid_dir(void)
+{
+        buildid_dir[0] = '\0';
+
+        /* try config file */
+        check_buildid_dir_config();
+
+        /* default to $HOME/.debug */
+        if (buildid_dir[0] == '\0') {
+                char *v = getenv("HOME");
+                if (v) {
+                        snprintf(buildid_dir, MAXPATHLEN-1, "%s/%s",
+                                 v, DEBUG_CACHE_DIR);
+                } else {
+                        strncpy(buildid_dir, DEBUG_CACHE_DIR, MAXPATHLEN-1);
+                }
+                buildid_dir[MAXPATHLEN-1] = '\0';
+        }
+        /* for communicating with external commands */
+        setenv("PERF_BUILDID_DIR", buildid_dir, 1);
+}
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 4e01490e51e5..0f9b8d7a7d7e 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -20,7 +20,7 @@ static int default_cpu_map(void)
         return nr_cpus;
 }
 
-int read_cpu_map(void)
+static int read_all_cpu_map(void)
 {
         FILE *onlnf;
         int nr_cpus = 0;
@@ -57,3 +57,58 @@ int read_cpu_map(void)
 
         return default_cpu_map();
 }
+
+int read_cpu_map(const char *cpu_list)
+{
+        unsigned long start_cpu, end_cpu = 0;
+        char *p = NULL;
+        int i, nr_cpus = 0;
+
+        if (!cpu_list)
+                return read_all_cpu_map();
+
+        if (!isdigit(*cpu_list))
+                goto invalid;
+
+        while (isdigit(*cpu_list)) {
+                p = NULL;
+                start_cpu = strtoul(cpu_list, &p, 0);
+                if (start_cpu >= INT_MAX
+                    || (*p != '\0' && *p != ',' && *p != '-'))
+                        goto invalid;
+
+                if (*p == '-') {
+                        cpu_list = ++p;
+                        p = NULL;
+                        end_cpu = strtoul(cpu_list, &p, 0);
+
+                        if (end_cpu >= INT_MAX || (*p != '\0' && *p != ','))
+                                goto invalid;
+
+                        if (end_cpu < start_cpu)
+                                goto invalid;
+                } else {
+                        end_cpu = start_cpu;
+                }
+
+                for (; start_cpu <= end_cpu; start_cpu++) {
+                        /* check for duplicates */
+                        for (i = 0; i < nr_cpus; i++)
+                                if (cpumap[i] == (int)start_cpu)
+                                        goto invalid;
+
+                        assert(nr_cpus < MAX_NR_CPUS);
+                        cpumap[nr_cpus++] = (int)start_cpu;
+                }
+                if (*p)
+                        ++p;
+
+                cpu_list = p;
+        }
+        if (nr_cpus > 0)
+                return nr_cpus;
+
+        return default_cpu_map();
+invalid:
+        return -1;
+}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 86c78bb33098..3e60f56e490e 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -1,7 +1,7 @@
 #ifndef __PERF_CPUMAP_H
 #define __PERF_CPUMAP_H
 
-extern int read_cpu_map(void);
+extern int read_cpu_map(const char *cpu_list);
 extern int cpumap[];
 
 #endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 1f08f008d289..a7460868124b 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -655,11 +655,36 @@ static void dso__calc_col_width(struct dso *self)
 }
 
 int event__preprocess_sample(const event_t *self, struct perf_session *session,
-                             struct addr_location *al, symbol_filter_t filter)
+                             struct addr_location *al, struct sample_data *data,
+                             symbol_filter_t filter)
 {
         u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-        struct thread *thread = perf_session__findnew(session, self->ip.pid);
+        struct thread *thread;
+
+        event__parse_sample(self, session->sample_type, data);
+
+        dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld cpu:%d\n",
+                    self->header.misc, data->pid, data->tid, data->ip,
+                    data->period, data->cpu);
+
+        if (session->sample_type & PERF_SAMPLE_CALLCHAIN) {
+                unsigned int i;
+
+                dump_printf("... chain: nr:%Lu\n", data->callchain->nr);
+
+                if (!ip_callchain__valid(data->callchain, self)) {
+                        pr_debug("call-chain problem with event, "
+                                 "skipping it.\n");
+                        goto out_filtered;
+                }
 
+                if (dump_trace) {
+                        for (i = 0; i < data->callchain->nr; i++)
+                                dump_printf("..... %2d: %016Lx\n",
+                                            i, data->callchain->ips[i]);
+                }
+        }
+        thread = perf_session__findnew(session, self->ip.pid);
         if (thread == NULL)
                 return -1;
 
@@ -685,6 +710,7 @@ int event__preprocess_sample(const event_t *self, struct perf_session *session,
                     al->map ? al->map->dso->long_name :
                         al->level == 'H' ? "[hypervisor]" : "<not found>");
         al->sym = NULL;
+        al->cpu = data->cpu;
 
         if (al->map) {
                 if (symbol_conf.dso_list &&
@@ -724,9 +750,9 @@ out_filtered:
         return 0;
 }
 
-int event__parse_sample(event_t *event, u64 type, struct sample_data *data)
+int event__parse_sample(const event_t *event, u64 type, struct sample_data *data)
 {
-        u64 *array = event->sample.array;
+        const u64 *array = event->sample.array;
 
         if (type & PERF_SAMPLE_IP) {
                 data->ip = event->ip.ip;
@@ -765,7 +791,8 @@ int event__parse_sample(event_t *event, u64 type, struct sample_data *data)
                 u32 *p = (u32 *)array;
                 data->cpu = *p;
                 array++;
-        }
+        } else
+                data->cpu = -1;
 
         if (type & PERF_SAMPLE_PERIOD) {
                 data->period = *array;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 8577085db067..887ee63bbb62 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -157,8 +157,9 @@ int event__process_task(event_t *self, struct perf_session *session);
 
 struct addr_location;
 int event__preprocess_sample(const event_t *self, struct perf_session *session,
-                             struct addr_location *al, symbol_filter_t filter);
-int event__parse_sample(event_t *event, u64 type, struct sample_data *data);
+                             struct addr_location *al, struct sample_data *data,
+                             symbol_filter_t filter);
+int event__parse_sample(const event_t *event, u64 type, struct sample_data *data);
 
 extern const char *event__name[];
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 1f62435f96c2..4a6a4b3a4ab7 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -385,8 +385,7 @@ static int perf_session__cache_build_ids(struct perf_session *self)
         int ret;
         char debugdir[PATH_MAX];
 
-        snprintf(debugdir, sizeof(debugdir), "%s/%s", getenv("HOME"),
-                 DEBUG_CACHE_DIR);
+        snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir);
 
         if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
                 return -1;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 07f89b66b318..68d288c975de 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -70,6 +70,7 @@ struct hist_entry *__hists__add_entry(struct hists *self,
                         .map    = al->map,
                         .sym    = al->sym,
                 },
+                .cpu    = al->cpu,
                 .ip     = al->addr,
                 .level  = al->level,
                 .period = period,
@@ -1037,7 +1038,7 @@ fallback:
                  dso, dso->long_name, sym, sym->name);
 
         snprintf(command, sizeof(command),
-                 "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS %s|grep -v %s|expand",
+                 "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS -C %s|grep -v %s|expand",
                  map__rip_2objdump(map, sym->start),
                  map__rip_2objdump(map, sym->end),
                  filename, filename);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 2316cb5a4116..c27b4b03fbc1 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -13,6 +13,7 @@ enum sort_type	sort__first_dimension;
 unsigned int dsos__col_width;
 unsigned int comms__col_width;
 unsigned int threads__col_width;
+unsigned int cpus__col_width;
 static unsigned int parent_symbol__col_width;
 char * field_sep;
 
@@ -28,6 +29,8 @@ static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
                                     size_t size, unsigned int width);
 static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf,
                                        size_t size, unsigned int width);
+static int hist_entry__cpu_snprintf(struct hist_entry *self, char *bf,
+                                    size_t size, unsigned int width);
 
 struct sort_entry sort_thread = {
         .se_header      = "Command:  Pid",
@@ -63,6 +66,13 @@ struct sort_entry sort_parent = {
         .se_snprintf    = hist_entry__parent_snprintf,
         .se_width       = &parent_symbol__col_width,
 };
+ 
+struct sort_entry sort_cpu = {
+        .se_header      = "CPU",
+        .se_cmp         = sort__cpu_cmp,
+        .se_snprintf    = hist_entry__cpu_snprintf,
+        .se_width       = &cpus__col_width,
+};
 
 struct sort_dimension {
         const char              *name;
@@ -76,6 +86,7 @@ static struct sort_dimension sort_dimensions[] = {
         { .name = "dso",        .entry = &sort_dso,     },
         { .name = "symbol",     .entry = &sort_sym,     },
         { .name = "parent",     .entry = &sort_parent,  },
+        { .name = "cpu",        .entry = &sort_cpu,     },
 };
 
 int64_t cmp_null(void *l, void *r)
@@ -242,6 +253,20 @@ static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf,
                               self->parent ? self->parent->name : "[other]");
 }
 
+/* --sort cpu */
+
+int64_t
+sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+        return right->cpu - left->cpu;
+}
+
+static int hist_entry__cpu_snprintf(struct hist_entry *self, char *bf,
+                                       size_t size, unsigned int width)
+{
+        return repsep_snprintf(bf, size, "%-*d", width, self->cpu);
+}
+
 int sort_dimension__add(const char *tok)
 {
         unsigned int i;
@@ -281,6 +306,8 @@ int sort_dimension__add(const char *tok)
                                 sort__first_dimension = SORT_SYM;
                         else if (!strcmp(sd->name, "parent"))
                                 sort__first_dimension = SORT_PARENT;
+                        else if (!strcmp(sd->name, "cpu"))
+                                sort__first_dimension = SORT_CPU;
                 }
 
                 list_add_tail(&sd->entry->list, &hist_entry__sort_list);
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 0d61c4082f43..560c855417e4 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -39,6 +39,7 @@ extern struct sort_entry sort_parent;
 extern unsigned int dsos__col_width;
 extern unsigned int comms__col_width;
 extern unsigned int threads__col_width;
+extern unsigned int cpus__col_width;
 extern enum sort_type sort__first_dimension;
 
 struct hist_entry {
@@ -51,6 +52,7 @@ struct hist_entry {
         struct map_symbol       ms;
         struct thread           *thread;
         u64                     ip;
+        s32                     cpu;
         u32                     nr_events;
         char                    level;
         u8                      filtered;
@@ -68,7 +70,8 @@ enum sort_type {
         SORT_COMM,
         SORT_DSO,
         SORT_SYM,
-        SORT_PARENT
+        SORT_PARENT,
+        SORT_CPU,
 };
 
 /*
@@ -104,6 +107,7 @@ extern int64_t sort__comm_collapse(struct hist_entry *, struct hist_entry *);
 extern int64_t sort__dso_cmp(struct hist_entry *, struct hist_entry *);
 extern int64_t sort__sym_cmp(struct hist_entry *, struct hist_entry *);
 extern int64_t sort__parent_cmp(struct hist_entry *, struct hist_entry *);
+int64_t sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right);
 extern size_t sort__parent_print(FILE *, struct hist_entry *, unsigned int);
 extern int sort_dimension__add(const char *);
 void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list,
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 5e02d2c17154..10b7ff859ce0 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -9,8 +9,6 @@
 #include <linux/rbtree.h>
 #include <stdio.h>
 
-#define DEBUG_CACHE_DIR ".debug"
-
 #ifdef HAVE_CPLUS_DEMANGLE
 extern char *cplus_demangle(const char *, int);
 
@@ -112,7 +110,8 @@ struct addr_location {
         u64           addr;
         char          level;
         bool          filtered;
-        unsigned int  cpumode;
+        u8            cpumode;
+        s32           cpu;
 };
 
 enum dso_kernel_type {
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 4e8b6b0c551c..de61441b6dd7 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -89,6 +89,7 @@
 
 extern const char *graph_line;
 extern const char *graph_dotted_line;
+extern char buildid_dir[];
 
 /* On most systems <limits.h> would have given us this, but
  * not on some systems (e.g. GNU/Hurd).
@@ -152,6 +153,7 @@ extern void warning(const char *err, ...) __attribute__((format (printf, 1, 2)))
 extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN);
 
 extern int prefixcmp(const char *str, const char *prefix);
+extern void set_buildid_dir(void);
 
 static inline const char *skip_prefix(const char *str, const char *prefix)
 {