diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 0a5571080e7453bc9d602061ffbe2c6ad81647a2..62ec3e6af7ea2eb43916ee2a49a83bf10e297a95 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -2341,6 +2341,27 @@ int uncore_pmu_event_init(struct perf_event *event)
 	return ret;
 }
 
+static ssize_t uncore_get_attr_cpumask(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &uncore_cpu_mask);
+
+	buf[n++] = '\n';
+	buf[n] = '\0';
+	return n;
+}
+
+static DEVICE_ATTR(cpumask, S_IRUGO, uncore_get_attr_cpumask, NULL);
+
+static struct attribute *uncore_pmu_attrs[] = {
+	&dev_attr_cpumask.attr,
+	NULL,
+};
+
+static struct attribute_group uncore_pmu_attr_group = {
+	.attrs = uncore_pmu_attrs,
+};
+
 static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu)
 {
 	int ret;
@@ -2378,8 +2399,8 @@ static void __init uncore_type_exit(struct intel_uncore_type *type)
 		free_percpu(type->pmus[i].box);
 	kfree(type->pmus);
 	type->pmus = NULL;
-	kfree(type->attr_groups[1]);
-	type->attr_groups[1] = NULL;
+	kfree(type->events_group);
+	type->events_group = NULL;
 }
 
 static void __init uncore_types_exit(struct intel_uncore_type **types)
@@ -2431,9 +2452,10 @@ static int __init uncore_type_init(struct intel_uncore_type *type)
 		for (j = 0; j < i; j++)
 			attrs[j] = &type->event_descs[j].attr.attr;
 
-		type->attr_groups[1] = events_group;
+		type->events_group = events_group;
 	}
 
+	type->pmu_group = &uncore_pmu_attr_group;
 	type->pmus = pmus;
 	return 0;
 fail:
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 5b81c1856aacadb95da71cdf7474bc1633ac7ecc..e68a4550e9529ffd1aa0fe5631397ed3360d03c8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -369,10 +369,12 @@ struct intel_uncore_type {
 	struct intel_uncore_pmu *pmus;
 	struct intel_uncore_ops *ops;
 	struct uncore_event_desc *event_descs;
-	const struct attribute_group *attr_groups[3];
+	const struct attribute_group *attr_groups[4];
 };
 
-#define format_group attr_groups[0]
+#define pmu_group attr_groups[0]
+#define format_group attr_groups[1]
+#define events_group attr_groups[2]
 
 struct intel_uncore_ops {
 	void (*init_box)(struct intel_uncore_box *);
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 14131cb0522d3e7983fc4efc730bb5f30e6ee8ef..04d959fa022667af25b1f9f685c2204c7c778acd 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -129,7 +129,7 @@ CFLAGS ?= -g -Wall
 
 # Append required CFLAGS
 override CFLAGS += $(CONFIG_FLAGS) $(INCLUDES) $(PLUGIN_DIR_SQ)
-override CFLAGS += $(udis86-flags)
+override CFLAGS += $(udis86-flags) -D_GNU_SOURCE
 
 ifeq ($(VERBOSE),1)
   Q =
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 2c54cdd8ae1b0dd5e22599991ce158fc219b0aec..77ebeb8266f4b429394d881f371c69e2399348fd 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -24,7 +24,6 @@
  *  Frederic Weisbecker gave his permission to relicense the code to
  *  the Lesser General Public License.
  */
-#define _GNU_SOURCE
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 209774bcee2e17c3aad2a6e0a429c72a430df779..5077f8e2ef72159fd2dd81c1634e864cca2e6c88 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -406,6 +406,7 @@ LIB_OBJS += $(OUTPUT)util/target.o
 LIB_OBJS += $(OUTPUT)util/rblist.o
 LIB_OBJS += $(OUTPUT)util/intlist.o
 LIB_OBJS += $(OUTPUT)util/vdso.o
+LIB_OBJS += $(OUTPUT)util/stat.o
 
 LIB_OBJS += $(OUTPUT)ui/helpline.o
 LIB_OBJS += $(OUTPUT)ui/hist.o
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 97b2e6300f4c80a09efd1ce8f50dda5a51453f3e..1da243dfbc3e7005ea9a64c195571f7ef1504c19 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -93,7 +93,7 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
 			struct annotation *notes;
 			err = -ENOMEM;
 			bx = he->branch_info;
-			if (bx->from.sym && use_browser > 0) {
+			if (bx->from.sym && use_browser == 1 && sort__has_sym) {
 				notes = symbol__annotation(bx->from.sym);
 				if (!notes->src
 				    && symbol__alloc_hist(bx->from.sym) < 0)
@@ -107,7 +107,7 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
 					goto out;
 			}
 
-			if (bx->to.sym && use_browser > 0) {
+			if (bx->to.sym && use_browser == 1 && sort__has_sym) {
 				notes = symbol__annotation(bx->to.sym);
 				if (!notes->src
 				    && symbol__alloc_hist(bx->to.sym) < 0)
@@ -162,7 +162,7 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
 	 * so we don't allocated the extra space needed because the stdio
 	 * code will not use it.
 	 */
-	if (he->ms.sym != NULL && use_browser > 0) {
+	if (he->ms.sym != NULL && use_browser == 1 && sort__has_sym) {
 		struct annotation *notes = symbol__annotation(he->ms.sym);
 
 		assert(evsel != NULL);
@@ -689,15 +689,19 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	if (strcmp(report.input_name, "-") != 0)
 		setup_browser(true);
-	else
+	else {
 		use_browser = 0;
+		perf_hpp__init(false, false);
+	}
+
+	setup_sorting(report_usage, options);
 
 	/*
 	 * Only in the newt browser we are doing integrated annotation,
 	 * so don't allocate extra space that won't be used in the stdio
 	 * implementation.
 	 */
-	if (use_browser > 0) {
+	if (use_browser == 1 && sort__has_sym) {
 		symbol_conf.priv_size = sizeof(struct annotation);
 		report.annotate_init  = symbol__annotate_init;
 		/*
@@ -720,8 +724,6 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (symbol__init() < 0)
 		goto error;
 
-	setup_sorting(report_usage, options);
-
 	if (parent_pattern != default_parent_pattern) {
 		if (sort_dimension__add("parent") < 0)
 			goto error;
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index af305f57bd22ed59b4ad75f200e9f394ab3952a5..9b9e32eaa8051da3a5cf562e38abe372a1afb6ee 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -438,8 +438,8 @@ static int self_open_counters(void)
 	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
 
 	if (fd < 0)
-		pr_debug("Error: sys_perf_event_open() syscall returned"
-			 "with %d (%s)\n", fd, strerror(errno));
+		pr_err("Error: sys_perf_event_open() syscall returned "
+		       "with %d (%s)\n", fd, strerror(errno));
 	return fd;
 }
 
@@ -700,7 +700,7 @@ static int replay_switch_event(struct perf_sched *sched,
 		delta = 0;
 
 	if (delta < 0) {
-		pr_debug("hm, delta: %" PRIu64 " < 0 ?\n", delta);
+		pr_err("hm, delta: %" PRIu64 " < 0 ?\n", delta);
 		return -1;
 	}
 
@@ -990,7 +990,7 @@ static int latency_runtime_event(struct perf_sched *sched,
 			return -1;
 		atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
 		if (!atoms) {
-			pr_debug("in-event: Internal tree error");
+			pr_err("in-event: Internal tree error");
 			return -1;
 		}
 		if (add_sched_out_event(atoms, 'R', timestamp))
@@ -1024,7 +1024,7 @@ static int latency_wakeup_event(struct perf_sched *sched,
 			return -1;
 		atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
 		if (!atoms) {
-			pr_debug("wakeup-event: Internal tree error");
+			pr_err("wakeup-event: Internal tree error");
 			return -1;
 		}
 		if (add_sched_out_event(atoms, 'S', timestamp))
@@ -1079,7 +1079,7 @@ static int latency_migrate_task_event(struct perf_sched *sched,
 		register_pid(sched, migrant->pid, migrant->comm);
 		atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
 		if (!atoms) {
-			pr_debug("migration-event: Internal tree error");
+			pr_err("migration-event: Internal tree error");
 			return -1;
 		}
 		if (add_sched_out_event(atoms, 'R', timestamp))
@@ -1286,7 +1286,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 		delta = 0;
 
 	if (delta < 0) {
-		pr_debug("hm, delta: %" PRIu64 " < 0 ?\n", delta);
+		pr_err("hm, delta: %" PRIu64 " < 0 ?\n", delta);
 		return -1;
 	}
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 6d98a83d5a60a76b676ac60ad1e3069576b842a9..1be843aa1546ed1df603119e3cec193d04cf0673 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -14,6 +14,7 @@
 #include "util/util.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
+#include "util/sort.h"
 #include <linux/bitmap.h>
 
 static char const		*script_name;
@@ -1031,6 +1032,61 @@ static int list_available_scripts(const struct option *opt __maybe_unused,
 	exit(0);
 }
 
+/*
+ * Return -1 if none is found, otherwise the actual scripts number.
+ *
+ * Currently the only user of this function is the script browser, which
+ * will list all statically runnable scripts, select one, execute it and
+ * show the output in a perf browser.
+ */
+int find_scripts(char **scripts_array, char **scripts_path_array)
+{
+	struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
+	char scripts_path[MAXPATHLEN];
+	DIR *scripts_dir, *lang_dir;
+	char lang_path[MAXPATHLEN];
+	char *temp;
+	int i = 0;
+
+	snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
+
+	scripts_dir = opendir(scripts_path);
+	if (!scripts_dir)
+		return -1;
+
+	for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) {
+		snprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path,
+			 lang_dirent.d_name);
+#ifdef NO_LIBPERL
+		if (strstr(lang_path, "perl"))
+			continue;
+#endif
+#ifdef NO_LIBPYTHON
+		if (strstr(lang_path, "python"))
+			continue;
+#endif
+
+		lang_dir = opendir(lang_path);
+		if (!lang_dir)
+			continue;
+
+		for_each_script(lang_path, lang_dir, script_dirent, script_next) {
+			/* Skip those real time scripts: xxxtop.p[yl] */
+			if (strstr(script_dirent.d_name, "top."))
+				continue;
+			sprintf(scripts_path_array[i], "%s/%s", lang_path,
+				script_dirent.d_name);
+			temp = strchr(script_dirent.d_name, '.');
+			snprintf(scripts_array[i],
+				(temp - script_dirent.d_name) + 1,
+				"%s", script_dirent.d_name);
+			i++;
+		}
+	}
+
+	return i;
+}
+
 static char *get_script_path(const char *script_root, const char *suffix)
 {
 	struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
@@ -1143,6 +1199,8 @@ static const struct option options[] = {
 		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		     "system-wide collection from all CPUs"),
+	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
+		   "only consider these symbols"),
 	OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
 	OPT_STRING('c', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
 		   "only display events for these comms"),
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index dab347d7b010a8c048287f273077d67e8760cb0f..e0f65fe65944cb5717ed015450df50991e8f2078 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -51,13 +51,13 @@
 #include "util/evsel.h"
 #include "util/debug.h"
 #include "util/color.h"
+#include "util/stat.h"
 #include "util/header.h"
 #include "util/cpumap.h"
 #include "util/thread.h"
 #include "util/thread_map.h"
 
 #include <sys/prctl.h>
-#include <math.h>
 #include <locale.h>
 
 #define DEFAULT_SEPARATOR	" "
@@ -199,11 +199,6 @@ static int			output_fd;
 
 static volatile int done = 0;
 
-struct stats
-{
-	double n, mean, M2;
-};
-
 struct perf_stat {
 	struct stats	  res_stats[3];
 };
@@ -220,48 +215,14 @@ static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
 	evsel->priv = NULL;
 }
 
-static void update_stats(struct stats *stats, u64 val)
+static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
 {
-	double delta;
-
-	stats->n++;
-	delta = val - stats->mean;
-	stats->mean += delta / stats->n;
-	stats->M2 += delta*(val - stats->mean);
+	return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus;
 }
 
-static double avg_stats(struct stats *stats)
-{
-	return stats->mean;
-}
-
-/*
- * http://en.wikipedia.org/wiki/Algorithms_for_calculating_variance
- *
- *       (\Sum n_i^2) - ((\Sum n_i)^2)/n
- * s^2 = -------------------------------
- *                  n - 1
- *
- * http://en.wikipedia.org/wiki/Stddev
- *
- * The std dev of the mean is related to the std dev by:
- *
- *             s
- * s_mean = -------
- *          sqrt(n)
- *
- */
-static double stddev_stats(struct stats *stats)
+static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
 {
-	double variance, variance_mean;
-
-	if (!stats->n)
-		return 0.0;
-
-	variance = stats->M2 / (stats->n - 1);
-	variance_mean = variance / stats->n;
-
-	return sqrt(variance_mean);
+	return perf_evsel__cpus(evsel)->nr;
 }
 
 static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
@@ -295,7 +256,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel,
 		evsel->attr.exclude_guest = evsel->attr.exclude_host = 0;
 
 	if (perf_target__has_cpu(&target)) {
-		ret = perf_evsel__open_per_cpu(evsel, evsel_list->cpus);
+		ret = perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
 		if (ret)
 			goto check_ret;
 		return 0;
@@ -376,7 +337,7 @@ static int read_counter_aggr(struct perf_evsel *counter)
 	u64 *count = counter->counts->aggr.values;
 	int i;
 
-	if (__perf_evsel__read(counter, evsel_list->cpus->nr,
+	if (__perf_evsel__read(counter, perf_evsel__nr_cpus(counter),
 			       evsel_list->threads->nr, scale) < 0)
 		return -1;
 
@@ -405,7 +366,7 @@ static int read_counter(struct perf_evsel *counter)
 	u64 *count;
 	int cpu;
 
-	for (cpu = 0; cpu < evsel_list->cpus->nr; cpu++) {
+	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
 		if (__perf_evsel__read_on_cpu(counter, cpu, 0, scale) < 0)
 			return -1;
 
@@ -544,12 +505,12 @@ static int run_perf_stat(int argc __maybe_unused, const char **argv)
 	if (no_aggr) {
 		list_for_each_entry(counter, &evsel_list->entries, node) {
 			read_counter(counter);
-			perf_evsel__close_fd(counter, evsel_list->cpus->nr, 1);
+			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), 1);
 		}
 	} else {
 		list_for_each_entry(counter, &evsel_list->entries, node) {
 			read_counter_aggr(counter);
-			perf_evsel__close_fd(counter, evsel_list->cpus->nr,
+			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
 					     evsel_list->threads->nr);
 		}
 	}
@@ -559,10 +520,7 @@ static int run_perf_stat(int argc __maybe_unused, const char **argv)
 
 static void print_noise_pct(double total, double avg)
 {
-	double pct = 0.0;
-
-	if (avg)
-		pct = 100.0*total/avg;
+	double pct = rel_stddev_stats(total, avg);
 
 	if (csv_output)
 		fprintf(output, "%s%.2f%%", csv_sep, pct);
@@ -590,7 +548,7 @@ static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg)
 	if (no_aggr)
 		sprintf(cpustr, "CPU%*d%s",
 			csv_output ? 0 : -4,
-			evsel_list->cpus->map[cpu], csv_sep);
+			perf_evsel__cpus(evsel)->map[cpu], csv_sep);
 
 	fprintf(output, fmt, cpustr, msecs, csv_sep, perf_evsel__name(evsel));
 
@@ -802,7 +760,7 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 	if (no_aggr)
 		sprintf(cpustr, "CPU%*d%s",
 			csv_output ? 0 : -4,
-			evsel_list->cpus->map[cpu], csv_sep);
+			perf_evsel__cpus(evsel)->map[cpu], csv_sep);
 	else
 		cpu = 0;
 
@@ -963,14 +921,14 @@ static void print_counter(struct perf_evsel *counter)
 	u64 ena, run, val;
 	int cpu;
 
-	for (cpu = 0; cpu < evsel_list->cpus->nr; cpu++) {
+	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
 		val = counter->counts->cpu[cpu].val;
 		ena = counter->counts->cpu[cpu].ena;
 		run = counter->counts->cpu[cpu].run;
 		if (run == 0 || ena == 0) {
 			fprintf(output, "CPU%*d%s%*s%s%*s",
 				csv_output ? 0 : -4,
-				evsel_list->cpus->map[cpu], csv_sep,
+				perf_evsel__cpus(counter)->map[cpu], csv_sep,
 				csv_output ? 0 : 18,
 				counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
 				csv_sep,
@@ -1269,7 +1227,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	list_for_each_entry(pos, &evsel_list->entries, node) {
 		if (perf_evsel__alloc_stat_priv(pos) < 0 ||
-		    perf_evsel__alloc_counts(pos, evsel_list->cpus->nr) < 0)
+		    perf_evsel__alloc_counts(pos, perf_evsel__nr_cpus(pos)) < 0)
 			goto out_free_fd;
 	}
 
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index d33143efefcec91bea798642bfb1563ee556774e..4aed1553db56a30309574d7edbf863f12b17a4dc 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -1026,15 +1026,15 @@ static int __test__rdpmc(void)
 
 	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
 	if (fd < 0) {
-		pr_debug("Error: sys_perf_event_open() syscall returned "
-			 "with %d (%s)\n", fd, strerror(errno));
+		pr_err("Error: sys_perf_event_open() syscall returned "
+		       "with %d (%s)\n", fd, strerror(errno));
 		return -1;
 	}
 
 	addr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0);
 	if (addr == (void *)(-1)) {
-		pr_debug("Error: mmap() syscall returned with (%s)\n",
-			 strerror(errno));
+		pr_err("Error: mmap() syscall returned with (%s)\n",
+		       strerror(errno));
 		goto out_close;
 	}
 
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index b382bd551aacd3d427522400fe11be1cbeb9f435..3ea74ed1b26b799620e53484dcf4e60c3bad6019 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -36,4 +36,5 @@ extern int cmd_kvm(int argc, const char **argv, const char *prefix);
 extern int cmd_test(int argc, const char **argv, const char *prefix);
 extern int cmd_inject(int argc, const char **argv, const char *prefix);
 
+extern int find_scripts(char **scripts_array, char **scripts_path_array);
 #endif
diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh
index 95b6f8b6177a98e45bc295bf4096b753aab70696..e919306202699cce814589562a4c91ff6bc32983 100644
--- a/tools/perf/perf-archive.sh
+++ b/tools/perf/perf-archive.sh
@@ -24,7 +24,7 @@ NOBUILDID=0000000000000000000000000000000000000000
 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
+	rm $BUILDIDS || true
 	exit 1
 fi
 
@@ -39,8 +39,8 @@ while read build_id ; do
 	echo ${filename#$PERF_BUILDID_LINKDIR} >> $MANIFEST
 done
 
-tar cfj $PERF_DATA.tar.bz2 -C $PERF_BUILDID_DIR -T $MANIFEST
-rm -f $MANIFEST $BUILDIDS
+tar cjf $PERF_DATA.tar.bz2 -C $PERF_BUILDID_DIR -T $MANIFEST
+rm $MANIFEST $BUILDIDS || true
 echo -e "Now please run:\n"
 echo -e "$ tar xvf $PERF_DATA.tar.bz2 -C ~/.debug\n"
 echo "wherever you need to run 'perf report' on."
diff --git a/tools/perf/scripts/python/bin/event_analyzing_sample-record b/tools/perf/scripts/python/bin/event_analyzing_sample-record
new file mode 100644
index 0000000000000000000000000000000000000000..5ce652dabd02f6245df130b908ee9dc9626b921d
--- /dev/null
+++ b/tools/perf/scripts/python/bin/event_analyzing_sample-record
@@ -0,0 +1,8 @@
+#!/bin/bash
+
+#
+# event_analyzing_sample.py can cover all type of perf samples including
+# the tracepoints, so no special record requirements, just record what
+# you want to analyze.
+#
+perf record $@
diff --git a/tools/perf/scripts/python/bin/event_analyzing_sample-report b/tools/perf/scripts/python/bin/event_analyzing_sample-report
new file mode 100644
index 0000000000000000000000000000000000000000..0941fc94e15842c2ed08274c44622e8ba39f2f94
--- /dev/null
+++ b/tools/perf/scripts/python/bin/event_analyzing_sample-report
@@ -0,0 +1,3 @@
+#!/bin/bash
+# description: analyze all perf samples
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/event_analyzing_sample.py
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 5a5739bbe6ac31ba949b6139a1709ac4536a8e97..a21f40bebbaced57a7862fb67dec5753f6249497 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -571,7 +571,7 @@ static int hist_browser__hpp_color_ ## _name(struct perf_hpp *hpp,	\
 {									\
 	double percent = 100.0 * he->_field / hpp->total_period;	\
 	*(double *)hpp->ptr = percent;					\
-	return scnprintf(hpp->buf, hpp->size, "%5.2f%%", percent);	\
+	return scnprintf(hpp->buf, hpp->size, "%6.2f%%", percent);	\
 }
 
 HPP__COLOR_FN(overhead, period)
@@ -605,7 +605,7 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 	char s[256];
 	double percent;
 	int i, printed = 0;
-	int width = browser->b.width - 1;
+	int width = browser->b.width;
 	char folded_sign = ' ';
 	bool current_entry = ui_browser__is_current_entry(&browser->b, row);
 	off_t row_offset = entry->row_offset;
@@ -627,7 +627,7 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			.total_period	= browser->hists->stats.total_period,
 		};
 
-		ui_browser__gotorc(&browser->b, row, 1);
+		ui_browser__gotorc(&browser->b, row, 0);
 
 		for (i = 0; i < PERF_HPP__MAX_INDEX; i++) {
 			if (!perf_hpp__format[i].cond)
diff --git a/tools/perf/ui/gtk/browser.c b/tools/perf/ui/gtk/browser.c
index 55acba6e0df4592e0117053a86447d97291db3e7..7ff99ec1d95e9e15dccd4d787192d1a23cb3dc97 100644
--- a/tools/perf/ui/gtk/browser.c
+++ b/tools/perf/ui/gtk/browser.c
@@ -56,7 +56,7 @@ static int perf_gtk__hpp_color_ ## _name(struct perf_hpp *hpp,			\
 	markup = perf_gtk__get_percent_color(percent);				\
 	if (markup)								\
 		ret += scnprintf(hpp->buf, hpp->size, "%s", markup);		\
-	ret += scnprintf(hpp->buf + ret, hpp->size - ret, "%5.2f%%", percent); 	\
+	ret += scnprintf(hpp->buf + ret, hpp->size - ret, "%6.2f%%", percent); 	\
 	if (markup)								\
 		ret += scnprintf(hpp->buf + ret, hpp->size - ret, "</span>"); 	\
 										\
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 407e855cccb83996c4b0c631d870d90b929294de..e3f8cd46e7d753258b4044635c5f030a31ab5632 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -33,13 +33,13 @@ static int hpp__color_overhead(struct perf_hpp *hpp, struct hist_entry *he)
 			percent = 0.0;
 	}
 
-	return percent_color_snprintf(hpp->buf, hpp->size, "  %5.2f%%", percent);
+	return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%%", percent);
 }
 
 static int hpp__entry_overhead(struct perf_hpp *hpp, struct hist_entry *he)
 {
 	double percent = 100.0 * he->period / hpp->total_period;
-	const char *fmt = symbol_conf.field_sep ? "%.2f" : "  %5.2f%%";
+	const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%%";
 
 	if (hpp->ptr) {
 		struct hists *old_hists = hpp->ptr;
@@ -57,52 +57,52 @@ static int hpp__entry_overhead(struct perf_hpp *hpp, struct hist_entry *he)
 
 static int hpp__header_overhead_sys(struct perf_hpp *hpp)
 {
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%6s";
+	const char *fmt = symbol_conf.field_sep ? "%s" : "%7s";
 
 	return scnprintf(hpp->buf, hpp->size, fmt, "sys");
 }
 
 static int hpp__width_overhead_sys(struct perf_hpp *hpp __maybe_unused)
 {
-	return 6;
+	return 7;
 }
 
 static int hpp__color_overhead_sys(struct perf_hpp *hpp, struct hist_entry *he)
 {
 	double percent = 100.0 * he->period_sys / hpp->total_period;
-	return percent_color_snprintf(hpp->buf, hpp->size, "%5.2f%%", percent);
+	return percent_color_snprintf(hpp->buf, hpp->size, "%6.2f%%", percent);
 }
 
 static int hpp__entry_overhead_sys(struct perf_hpp *hpp, struct hist_entry *he)
 {
 	double percent = 100.0 * he->period_sys / hpp->total_period;
-	const char *fmt = symbol_conf.field_sep ? "%.2f" : "%5.2f%%";
+	const char *fmt = symbol_conf.field_sep ? "%.2f" : "%6.2f%%";
 
 	return scnprintf(hpp->buf, hpp->size, fmt, percent);
 }
 
 static int hpp__header_overhead_us(struct perf_hpp *hpp)
 {
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%6s";
+	const char *fmt = symbol_conf.field_sep ? "%s" : "%7s";
 
 	return scnprintf(hpp->buf, hpp->size, fmt, "user");
 }
 
 static int hpp__width_overhead_us(struct perf_hpp *hpp __maybe_unused)
 {
-	return 6;
+	return 7;
 }
 
 static int hpp__color_overhead_us(struct perf_hpp *hpp, struct hist_entry *he)
 {
 	double percent = 100.0 * he->period_us / hpp->total_period;
-	return percent_color_snprintf(hpp->buf, hpp->size, "%5.2f%%", percent);
+	return percent_color_snprintf(hpp->buf, hpp->size, "%6.2f%%", percent);
 }
 
 static int hpp__entry_overhead_us(struct perf_hpp *hpp, struct hist_entry *he)
 {
 	double percent = 100.0 * he->period_us / hpp->total_period;
-	const char *fmt = symbol_conf.field_sep ? "%.2f" : "%5.2f%%";
+	const char *fmt = symbol_conf.field_sep ? "%.2f" : "%6.2f%%";
 
 	return scnprintf(hpp->buf, hpp->size, fmt, percent);
 }
@@ -121,14 +121,14 @@ static int hpp__color_overhead_guest_sys(struct perf_hpp *hpp,
 					 struct hist_entry *he)
 {
 	double percent = 100.0 * he->period_guest_sys / hpp->total_period;
-	return percent_color_snprintf(hpp->buf, hpp->size, "  %5.2f%% ", percent);
+	return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%% ", percent);
 }
 
 static int hpp__entry_overhead_guest_sys(struct perf_hpp *hpp,
 					 struct hist_entry *he)
 {
 	double percent = 100.0 * he->period_guest_sys / hpp->total_period;
-	const char *fmt = symbol_conf.field_sep ? "%.2f" : "  %5.2f%% ";
+	const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%% ";
 
 	return scnprintf(hpp->buf, hpp->size, fmt, percent);
 }
@@ -147,14 +147,14 @@ static int hpp__color_overhead_guest_us(struct perf_hpp *hpp,
 					struct hist_entry *he)
 {
 	double percent = 100.0 * he->period_guest_us / hpp->total_period;
-	return percent_color_snprintf(hpp->buf, hpp->size, "  %5.2f%% ", percent);
+	return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%% ", percent);
 }
 
 static int hpp__entry_overhead_guest_us(struct perf_hpp *hpp,
 					struct hist_entry *he)
 {
 	double percent = 100.0 * he->period_guest_us / hpp->total_period;
-	const char *fmt = symbol_conf.field_sep ? "%.2f" : "  %5.2f%% ";
+	const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%% ";
 
 	return scnprintf(hpp->buf, hpp->size, fmt, percent);
 }
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index adc72f09914d0c8089bd104784284928da3cd1f9..2b32ffa9ebdb188e8edeb31fc4176380d99b2337 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -38,24 +38,19 @@ static struct cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus)
 	return cpus;
 }
 
-static struct cpu_map *cpu_map__read_all_cpu_map(void)
+struct cpu_map *cpu_map__read(FILE *file)
 {
 	struct cpu_map *cpus = NULL;
-	FILE *onlnf;
 	int nr_cpus = 0;
 	int *tmp_cpus = NULL, *tmp;
 	int max_entries = 0;
 	int n, cpu, prev;
 	char sep;
 
-	onlnf = fopen("/sys/devices/system/cpu/online", "r");
-	if (!onlnf)
-		return cpu_map__default_new();
-
 	sep = 0;
 	prev = -1;
 	for (;;) {
-		n = fscanf(onlnf, "%u%c", &cpu, &sep);
+		n = fscanf(file, "%u%c", &cpu, &sep);
 		if (n <= 0)
 			break;
 		if (prev >= 0) {
@@ -95,6 +90,19 @@ static struct cpu_map *cpu_map__read_all_cpu_map(void)
 		cpus = cpu_map__default_new();
 out_free_tmp:
 	free(tmp_cpus);
+	return cpus;
+}
+
+static struct cpu_map *cpu_map__read_all_cpu_map(void)
+{
+	struct cpu_map *cpus = NULL;
+	FILE *onlnf;
+
+	onlnf = fopen("/sys/devices/system/cpu/online", "r");
+	if (!onlnf)
+		return cpu_map__default_new();
+
+	cpus = cpu_map__read(onlnf);
 	fclose(onlnf);
 	return cpus;
 }
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index c41518573c6af013e5de3c16d916bfac84e92897..17b5264f6436f69393199a21913941a40ea65e3f 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -11,7 +11,7 @@ struct cpu_map {
 struct cpu_map *cpu_map__new(const char *cpu_list);
 struct cpu_map *cpu_map__dummy_new(void);
 void cpu_map__delete(struct cpu_map *map);
-
+struct cpu_map *cpu_map__read(FILE *file);
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
 
 #endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 8202f5ca04830dd391e1c946ed638dba6e98bba6..6715b19387258cd184bba45d88a00e76eaebbeba 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -904,8 +904,9 @@ int perf_event__preprocess_sample(const union perf_event *event,
 		al->sym = map__find_symbol(al->map, al->addr, filter);
 	}
 
-	if (symbol_conf.sym_list && al->sym &&
-	    !strlist__has_entry(symbol_conf.sym_list, al->sym->name))
+	if (symbol_conf.sym_list &&
+		(!al->sym || !strlist__has_entry(symbol_conf.sym_list,
+						al->sym->name)))
 		goto out_filtered;
 
 	return 0;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index dc40fe32210b606f229aa2de4ab354b50fde79f7..93876bad2e52c12acb4604dbce1ffe9be2d4d645 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -66,6 +66,7 @@ struct perf_evsel {
 		void		*func;
 		void		*data;
 	} handler;
+	struct cpu_map		*cpus;
 	unsigned int		sample_size;
 	bool 			supported;
 	/* parse modifier helper */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 44afcf40f7963237414b4587b30009ef16c8ac9e..bf5d033ee1b4d0c4b493b3e68c9a91af9cee2a6d 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -239,8 +239,11 @@ const char *event_type(int type)
 	return "unknown";
 }
 
-static int add_event(struct list_head **_list, int *idx,
-		     struct perf_event_attr *attr, char *name)
+
+
+static int __add_event(struct list_head **_list, int *idx,
+		       struct perf_event_attr *attr,
+		       char *name, struct cpu_map *cpus)
 {
 	struct perf_evsel *evsel;
 	struct list_head *list = *_list;
@@ -260,6 +263,7 @@ static int add_event(struct list_head **_list, int *idx,
 		return -ENOMEM;
 	}
 
+	evsel->cpus = cpus;
 	if (name)
 		evsel->name = strdup(name);
 	list_add_tail(&evsel->node, list);
@@ -267,6 +271,12 @@ static int add_event(struct list_head **_list, int *idx,
 	return 0;
 }
 
+static int add_event(struct list_head **_list, int *idx,
+		     struct perf_event_attr *attr, char *name)
+{
+	return __add_event(_list, idx, attr, name, NULL);
+}
+
 static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size)
 {
 	int i, j;
@@ -607,8 +617,8 @@ int parse_events_add_pmu(struct list_head **list, int *idx,
 	if (perf_pmu__config(pmu, &attr, head_config))
 		return -EINVAL;
 
-	return add_event(list, idx, &attr,
-			 pmu_event_name(head_config));
+	return __add_event(list, idx, &attr, pmu_event_name(head_config),
+			   pmu->cpus);
 }
 
 int parse_events__modifier_group(struct list_head *list,
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 6631d828db3dc131dad22c02489bf47efe039070..8a2229da594fca292d6d0672bb40b4a10a0a52f2 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -9,6 +9,7 @@
 #include "util.h"
 #include "pmu.h"
 #include "parse-events.h"
+#include "cpumap.h"
 
 #define EVENT_SOURCE_DEVICE_PATH "/bus/event_source/devices/"
 
@@ -253,6 +254,33 @@ static void pmu_read_sysfs(void)
 	closedir(dir);
 }
 
+static struct cpu_map *pmu_cpumask(char *name)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	const char *sysfs;
+	FILE *file;
+	struct cpu_map *cpus;
+
+	sysfs = sysfs_find_mountpoint();
+	if (!sysfs)
+		return NULL;
+
+	snprintf(path, PATH_MAX,
+		 "%s/bus/event_source/devices/%s/cpumask", sysfs, name);
+
+	if (stat(path, &st) < 0)
+		return NULL;
+
+	file = fopen(path, "r");
+	if (!file)
+		return NULL;
+
+	cpus = cpu_map__read(file);
+	fclose(file);
+	return cpus;
+}
+
 static struct perf_pmu *pmu_lookup(char *name)
 {
 	struct perf_pmu *pmu;
@@ -275,6 +303,8 @@ static struct perf_pmu *pmu_lookup(char *name)
 	if (!pmu)
 		return NULL;
 
+	pmu->cpus = pmu_cpumask(name);
+
 	pmu_aliases(name, &aliases);
 
 	INIT_LIST_HEAD(&pmu->format);
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 47f68d3cc5d1e51354ae7f2df5f06cfa50372b2c..53c7794fc4be3b409c72dee5687abce438111707 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -28,6 +28,7 @@ struct perf_pmu__alias {
 struct perf_pmu {
 	char *name;
 	__u32 type;
+	struct cpu_map *cpus;
 	struct list_head format;
 	struct list_head aliases;
 	struct list_head list;
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 526ba56e720b39bc0817e011914bc3a8fac63c29..1daf5c14e751bf954e5665e1caa179b191cbd361 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -525,8 +525,10 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 			return -ENOENT;
 		}
 		/* Verify it is a data structure  */
-		if (dwarf_tag(&type) != DW_TAG_structure_type) {
-			pr_warning("%s is not a data structure.\n", varname);
+		tag = dwarf_tag(&type);
+		if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) {
+			pr_warning("%s is not a data structure nor an union.\n",
+				   varname);
 			return -EINVAL;
 		}
 
@@ -539,8 +541,9 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 			*ref_ptr = ref;
 	} else {
 		/* Verify it is a data structure  */
-		if (tag != DW_TAG_structure_type) {
-			pr_warning("%s is not a data structure.\n", varname);
+		if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) {
+			pr_warning("%s is not a data structure nor an union.\n",
+				   varname);
 			return -EINVAL;
 		}
 		if (field->name[0] == '[') {
@@ -567,10 +570,15 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 	}
 
 	/* Get the offset of the field */
-	ret = die_get_data_member_location(die_mem, &offs);
-	if (ret < 0) {
-		pr_warning("Failed to get the offset of %s.\n", field->name);
-		return ret;
+	if (tag == DW_TAG_union_type) {
+		offs = 0;
+	} else {
+		ret = die_get_data_member_location(die_mem, &offs);
+		if (ret < 0) {
+			pr_warning("Failed to get the offset of %s.\n",
+				   field->name);
+			return ret;
+		}
 	}
 	ref->offset += (long)offs;
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 0981bc7a29172a1d950236b0bbff7a76e6b2276c..b5b1b9211960884efd1a4c707fa8c56910db01f1 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -8,6 +8,7 @@ const char	default_sort_order[] = "comm,dso,symbol";
 const char	*sort_order = default_sort_order;
 int		sort__need_collapse = 0;
 int		sort__has_parent = 0;
+int		sort__has_sym = 0;
 int		sort__branch_mode = -1; /* -1 = means not set */
 
 enum sort_type	sort__first_dimension;
@@ -511,6 +512,10 @@ int sort_dimension__add(const char *tok)
 				return -EINVAL;
 			}
 			sort__has_parent = 1;
+		} else if (sd->entry == &sort_sym ||
+			   sd->entry == &sort_sym_from ||
+			   sd->entry == &sort_sym_to) {
+			sort__has_sym = 1;
 		}
 
 		if (sd->taken)
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index e459c981b039fa8d9ec96c7ab48e75be4745da08..12d634792de511051decb3cfa7caf6458d60560c 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -31,6 +31,7 @@ extern const char *parent_pattern;
 extern const char default_sort_order[];
 extern int sort__need_collapse;
 extern int sort__has_parent;
+extern int sort__has_sym;
 extern int sort__branch_mode;
 extern struct sort_entry sort_comm;
 extern struct sort_entry sort_dso;
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
new file mode 100644
index 0000000000000000000000000000000000000000..23742126f47c848b81f38a15af23f30593230354
--- /dev/null
+++ b/tools/perf/util/stat.c
@@ -0,0 +1,57 @@
+#include <math.h>
+
+#include "stat.h"
+
+void update_stats(struct stats *stats, u64 val)
+{
+	double delta;
+
+	stats->n++;
+	delta = val - stats->mean;
+	stats->mean += delta / stats->n;
+	stats->M2 += delta*(val - stats->mean);
+}
+
+double avg_stats(struct stats *stats)
+{
+	return stats->mean;
+}
+
+/*
+ * http://en.wikipedia.org/wiki/Algorithms_for_calculating_variance
+ *
+ *       (\Sum n_i^2) - ((\Sum n_i)^2)/n
+ * s^2 = -------------------------------
+ *                  n - 1
+ *
+ * http://en.wikipedia.org/wiki/Stddev
+ *
+ * The std dev of the mean is related to the std dev by:
+ *
+ *             s
+ * s_mean = -------
+ *          sqrt(n)
+ *
+ */
+double stddev_stats(struct stats *stats)
+{
+	double variance, variance_mean;
+
+	if (!stats->n)
+		return 0.0;
+
+	variance = stats->M2 / (stats->n - 1);
+	variance_mean = variance / stats->n;
+
+	return sqrt(variance_mean);
+}
+
+double rel_stddev_stats(double stddev, double avg)
+{
+	double pct = 0.0;
+
+	if (avg)
+		pct = 100.0 * stddev/avg;
+
+	return pct;
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
new file mode 100644
index 0000000000000000000000000000000000000000..588367c3c767f2fd6ff7f3f317986756174a2b3c
--- /dev/null
+++ b/tools/perf/util/stat.h
@@ -0,0 +1,16 @@
+#ifndef __PERF_STATS_H
+#define __PERF_STATS_H
+
+#include "types.h"
+
+struct stats
+{
+	double n, mean, M2;
+};
+
+void update_stats(struct stats *stats, u64 val);
+double avg_stats(struct stats *stats);
+double stddev_stats(struct stats *stats);
+double rel_stddev_stats(double stddev, double avg);
+
+#endif