Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

author: David S. Miller <davem@davemloft.net> 2012-04-10 14:30:45 -0400
committer: David S. Miller <davem@davemloft.net> 2012-04-10 14:30:45 -0400
commit: 06eb4eafbdc0796d741d139a44f1253278da8611 (patch)
tree: fbdb44317130c371928154c9e6903e699fe2b995 /tools
parent: 32ed53b83ea5ec26a4dba90e18f5e0ff6c71eb48 (diff)
parent: f68e556e23d1a4176b563bcb25d8baf2c5313f91 (diff)
60 files changed, 4103 insertions, 700 deletions
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 87feeee8b90..2d89f02719b 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -48,6 +48,9 @@ OPTIONS
 	Only consider these symbols. CSV that understands
 	file://filename entries.
 
+--symbol-filter=::
+	Only show symbols that match (partially) with this filter.
+
 -U::
 --hide-unresolved::
         Only display entries resolved to a symbol.
@@ -110,6 +113,8 @@ OPTIONS
 	requires a tty, if one is not present, as when piping to other
 	commands, the stdio interface is used.
 
+--gtk:: Use the GTK2 interface.
+
 -k::
 --vmlinux=<file>::
         vmlinux pathname
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 74fd7f89208..820371f10d1 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -182,7 +182,7 @@ endif
 
 ### --- END CONFIGURATION SECTION ---
 
-BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
+BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)/util -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 BASIC_LDFLAGS =
 
 # Guard against environment variables
@@ -234,6 +234,25 @@ endif
 
 export PERL_PATH
 
+FLEX = $(CROSS_COMPILE)flex
+BISON= $(CROSS_COMPILE)bison
+
+event-parser:
+	$(QUIET_BISON)$(BISON) -v util/parse-events.y -d -o $(OUTPUT)util/parse-events-bison.c
+	$(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/parse-events-flex.h -t util/parse-events.l > $(OUTPUT)util/parse-events-flex.c
+
+$(OUTPUT)util/parse-events-flex.c: event-parser
+$(OUTPUT)util/parse-events-bison.c: event-parser
+
+pmu-parser:
+	$(QUIET_BISON)$(BISON) -v util/pmu.y -d -o $(OUTPUT)util/pmu-bison.c
+	$(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/pmu-flex.h -t util/pmu.l > $(OUTPUT)util/pmu-flex.c
+
+$(OUTPUT)util/pmu-flex.c: pmu-parser
+$(OUTPUT)util/pmu-bison.c: pmu-parser
+
+$(OUTPUT)util/parse-events.o: event-parser pmu-parser
+
 LIB_FILE=$(OUTPUT)libperf.a
 
 LIB_H += ../../include/linux/perf_event.h
@@ -249,7 +268,7 @@ LIB_H += util/include/linux/const.h
 LIB_H += util/include/linux/ctype.h
 LIB_H += util/include/linux/kernel.h
 LIB_H += util/include/linux/list.h
-LIB_H += util/include/linux/module.h
+LIB_H += util/include/linux/export.h
 LIB_H += util/include/linux/poison.h
 LIB_H += util/include/linux/prefetch.h
 LIB_H += util/include/linux/rbtree.h
@@ -276,6 +295,7 @@ LIB_H += util/build-id.h
 LIB_H += util/debug.h
 LIB_H += util/debugfs.h
 LIB_H += util/sysfs.h
+LIB_H += util/pmu.h
 LIB_H += util/event.h
 LIB_H += util/evsel.h
 LIB_H += util/evlist.h
@@ -323,6 +343,7 @@ LIB_OBJS += $(OUTPUT)util/config.o
 LIB_OBJS += $(OUTPUT)util/ctype.o
 LIB_OBJS += $(OUTPUT)util/debugfs.o
 LIB_OBJS += $(OUTPUT)util/sysfs.o
+LIB_OBJS += $(OUTPUT)util/pmu.o
 LIB_OBJS += $(OUTPUT)util/environment.o
 LIB_OBJS += $(OUTPUT)util/event.o
 LIB_OBJS += $(OUTPUT)util/evlist.o
@@ -359,6 +380,10 @@ LIB_OBJS += $(OUTPUT)util/session.o
 LIB_OBJS += $(OUTPUT)util/thread.o
 LIB_OBJS += $(OUTPUT)util/thread_map.o
 LIB_OBJS += $(OUTPUT)util/trace-event-parse.o
+LIB_OBJS += $(OUTPUT)util/parse-events-flex.o
+LIB_OBJS += $(OUTPUT)util/parse-events-bison.o
+LIB_OBJS += $(OUTPUT)util/pmu-flex.o
+LIB_OBJS += $(OUTPUT)util/pmu-bison.o
 LIB_OBJS += $(OUTPUT)util/trace-event-read.o
 LIB_OBJS += $(OUTPUT)util/trace-event-info.o
 LIB_OBJS += $(OUTPUT)util/trace-event-scripting.o
@@ -501,6 +526,20 @@ else
 	endif
 endif
 
+ifdef NO_GTK2
+	BASIC_CFLAGS += -DNO_GTK2
+else
+	FLAGS_GTK2=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(shell pkg-config --libs --cflags gtk+-2.0)
+	ifneq ($(call try-cc,$(SOURCE_GTK2),$(FLAGS_GTK2)),y)
+		msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev);
+		BASIC_CFLAGS += -DNO_GTK2_SUPPORT
+	else
+		BASIC_CFLAGS += $(shell pkg-config --cflags gtk+-2.0)
+		EXTLIBS += $(shell pkg-config --libs gtk+-2.0)
+		LIB_OBJS += $(OUTPUT)util/gtk/browser.o
+	endif
+endif
+
 ifdef NO_LIBPERL
 	BASIC_CFLAGS += -DNO_LIBPERL
 else
@@ -647,6 +686,8 @@ ifndef V
 	QUIET_LINK     = @echo '   ' LINK $@;
 	QUIET_MKDIR    = @echo '   ' MKDIR $@;
 	QUIET_GEN      = @echo '   ' GEN $@;
+	QUIET_FLEX     = @echo '   ' FLEX $@;
+	QUIET_BISON    = @echo '   ' BISON $@;
 endif
 endif
 
@@ -727,12 +768,28 @@ $(OUTPUT)perf.o perf.spec \
 	$(SCRIPTS) \
 	: $(OUTPUT)PERF-VERSION-FILE
 
+.SUFFIXES:
+.SUFFIXES: .o .c .S .s
+
+# These two need to be here so that when O= is not used they take precedence
+# over the general rule for .o
+
+$(OUTPUT)util/%-flex.o: $(OUTPUT)util/%-flex.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -Iutil/ -Wno-redundant-decls -Wno-switch-default -Wno-unused-function $<
+
+$(OUTPUT)util/%-bison.o: $(OUTPUT)util/%-bison.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -Iutil/ -Wno-redundant-decls -Wno-switch-default -Wno-unused-function $<
+
 $(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
+$(OUTPUT)%.i: %.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -E $(ALL_CFLAGS) $<
 $(OUTPUT)%.s: %.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -S $(ALL_CFLAGS) $<
+	$(QUIET_CC)$(CC) -o $@ -S $(ALL_CFLAGS) $<
 $(OUTPUT)%.o: %.S
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
+$(OUTPUT)%.s: %.S
+	$(QUIET_CC)$(CC) -o $@ -E $(ALL_CFLAGS) $<
 
 $(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
@@ -795,6 +852,8 @@ help:
 	@echo '  html		- make html documentation'
 	@echo '  info		- make GNU info documentation (access with info <foo>)'
 	@echo '  pdf		- make pdf documentation'
+	@echo '  event-parser	- make event parser code'
+	@echo '  pmu-parser	- make pmu format parser code'
 	@echo '  TAGS		- use etags to make tag information for source browsing'
 	@echo '  tags		- use ctags to make tag information for source browsing'
 	@echo '  cscope	- use cscope to make interactive browsing database'
@@ -931,6 +990,7 @@ clean:
 	$(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope*
 	$(MAKE) -C Documentation/ clean
 	$(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS
+	$(RM) $(OUTPUT)util/*-{bison,flex}*
 	$(python-clean)
 
 .PHONY: all install clean strip
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 4f19513d7dd..d29d350fb2b 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -24,6 +24,11 @@ static char	  diff__default_sort_order[] = "dso,symbol";
 static bool  force;
 static bool show_displacement;
 
+struct perf_diff {
+	struct perf_tool tool;
+	struct perf_session *session;
+};
+
 static int hists__add_entry(struct hists *self,
 			    struct addr_location *al, u64 period)
 {
@@ -32,12 +37,14 @@ static int hists__add_entry(struct hists *self,
 	return -ENOMEM;
 }
 
-static int diff__process_sample_event(struct perf_tool *tool __used,
+static int diff__process_sample_event(struct perf_tool *tool,
 				      union perf_event *event,
 				      struct perf_sample *sample,
 				      struct perf_evsel *evsel __used,
 				      struct machine *machine)
 {
+	struct perf_diff *_diff = container_of(tool, struct perf_diff, tool);
+	struct perf_session *session = _diff->session;
 	struct addr_location al;
 
 	if (perf_event__preprocess_sample(event, machine, &al, sample, NULL) < 0) {
@@ -49,24 +56,26 @@ static int diff__process_sample_event(struct perf_tool *tool __used,
 	if (al.filtered || al.sym == NULL)
 		return 0;
 
-	if (hists__add_entry(&evsel->hists, &al, sample->period)) {
+	if (hists__add_entry(&session->hists, &al, sample->period)) {
 		pr_warning("problem incrementing symbol period, skipping event\n");
 		return -1;
 	}
 
-	evsel->hists.stats.total_period += sample->period;
+	session->hists.stats.total_period += sample->period;
 	return 0;
 }
 
-static struct perf_tool perf_diff = {
-	.sample	= diff__process_sample_event,
-	.mmap	= perf_event__process_mmap,
-	.comm	= perf_event__process_comm,
-	.exit	= perf_event__process_task,
-	.fork	= perf_event__process_task,
-	.lost	= perf_event__process_lost,
-	.ordered_samples = true,
-	.ordering_requires_timestamps = true,
+static struct perf_diff diff = {
+	.tool = {
+		.sample	= diff__process_sample_event,
+		.mmap	= perf_event__process_mmap,
+		.comm	= perf_event__process_comm,
+		.exit	= perf_event__process_task,
+		.fork	= perf_event__process_task,
+		.lost	= perf_event__process_lost,
+		.ordered_samples = true,
+		.ordering_requires_timestamps = true,
+	},
 };
 
 static void perf_session__insert_hist_entry_by_name(struct rb_root *root,
@@ -107,12 +116,6 @@ static void hists__resort_entries(struct hists *self)
 	self->entries = tmp;
 }
 
-static void hists__set_positions(struct hists *self)
-{
-	hists__output_resort(self);
-	hists__resort_entries(self);
-}
-
 static struct hist_entry *hists__find_entry(struct hists *self,
 					    struct hist_entry *he)
 {
@@ -146,30 +149,37 @@ static void hists__match(struct hists *older, struct hists *newer)
 static int __cmd_diff(void)
 {
 	int ret, i;
+#define older (session[0])
+#define newer (session[1])
 	struct perf_session *session[2];
 
-	session[0] = perf_session__new(input_old, O_RDONLY, force, false, &perf_diff);
-	session[1] = perf_session__new(input_new, O_RDONLY, force, false, &perf_diff);
+	older = perf_session__new(input_old, O_RDONLY, force, false,
+				  &diff.tool);
+	newer = perf_session__new(input_new, O_RDONLY, force, false,
+				  &diff.tool);
 	if (session[0] == NULL || session[1] == NULL)
 		return -ENOMEM;
 
 	for (i = 0; i < 2; ++i) {
-		ret = perf_session__process_events(session[i], &perf_diff);
+		diff.session = session[i];
+		ret = perf_session__process_events(session[i], &diff.tool);
 		if (ret)
 			goto out_delete;
+		hists__output_resort(&session[i]->hists);
 	}
 
-	hists__output_resort(&session[1]->hists);
 	if (show_displacement)
-		hists__set_positions(&session[0]->hists);
+		hists__resort_entries(&older->hists);
 
-	hists__match(&session[0]->hists, &session[1]->hists);
-	hists__fprintf(&session[1]->hists, &session[0]->hists,
+	hists__match(&older->hists, &newer->hists);
+	hists__fprintf(&newer->hists, &older->hists,
 		       show_displacement, true, 0, 0, stdout);
 out_delete:
 	for (i = 0; i < 2; ++i)
 		perf_session__delete(session[i]);
 	return ret;
+#undef older
+#undef newer
 }
 
 static const char * const diff_usage[] = {
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8e91c6eba18..2e317438980 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -40,7 +40,7 @@ struct perf_report {
 	struct perf_tool	tool;
 	struct perf_session	*session;
 	char const		*input_name;
-	bool			force, use_tui, use_stdio;
+	bool			force, use_tui, use_gtk, use_stdio;
 	bool			hide_unresolved;
 	bool			dont_use_callchains;
 	bool			show_full_info;
@@ -50,6 +50,7 @@ struct perf_report {
 	const char		*pretty_printing_style;
 	symbol_filter_t		annotate_init;
 	const char		*cpu_list;
+	const char		*symbol_filter_str;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
@@ -400,6 +401,9 @@ static int __cmd_report(struct perf_report *rep)
 	list_for_each_entry(pos, &session->evlist->entries, node) {
 		struct hists *hists = &pos->hists;
 
+		if (pos->idx == 0)
+			hists->symbol_filter_str = rep->symbol_filter_str;
+
 		hists__collapse_resort(hists);
 		hists__output_resort(hists);
 		nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE];
@@ -411,8 +415,13 @@ static int __cmd_report(struct perf_report *rep)
 	}
 
 	if (use_browser > 0) {
-		perf_evlist__tui_browse_hists(session->evlist, help,
-					      NULL, NULL, 0);
+		if (use_browser == 1) {
+			perf_evlist__tui_browse_hists(session->evlist, help,
+						      NULL, NULL, 0);
+		} else if (use_browser == 2) {
+			perf_evlist__gtk_browse_hists(session->evlist, help,
+						      NULL, NULL, 0);
+		}
 	} else
 		perf_evlist__tty_browse_hists(session->evlist, rep, help);
 
@@ -569,6 +578,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 	OPT_STRING(0, "pretty", &report.pretty_printing_style, "key",
 		   "pretty printing style key: normal raw"),
 	OPT_BOOLEAN(0, "tui", &report.use_tui, "Use the TUI interface"),
+	OPT_BOOLEAN(0, "gtk", &report.use_gtk, "Use the GTK2 interface"),
 	OPT_BOOLEAN(0, "stdio", &report.use_stdio,
 		    "Use the stdio interface"),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
@@ -591,6 +601,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 		   "only consider symbols in these comms"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
 		   "only consider these symbols"),
+	OPT_STRING(0, "symbol-filter", &report.symbol_filter_str, "filter",
+		   "only show symbols that (partially) match with this filter"),
 	OPT_STRING('w', "column-widths", &symbol_conf.col_width_list_str,
 		   "width[,width...]",
 		   "don't try to adjust column width, use these fixed values"),
@@ -624,6 +636,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 		use_browser = 0;
 	else if (report.use_tui)
 		use_browser = 1;
+	else if (report.use_gtk)
+		use_browser = 2;
 
 	if (report.inverted_callchain)
 		callchain_param.order = ORDER_CALLER;
@@ -660,7 +674,10 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 	}
 
 	if (strcmp(report.input_name, "-") != 0) {
-		setup_browser(true);
+		if (report.use_gtk)
+			perf_gtk_setup_browser(argc, argv, true);
+		else
+			setup_browser(true);
 	} else {
 		use_browser = 0;
 	}
@@ -709,11 +726,16 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 	} else
 		symbol_conf.exclude_other = false;
 
-	/*
-	 * Any (unrecognized) arguments left?
-	 */
-	if (argc)
-		usage_with_options(report_usage, options);
+	if (argc) {
+		/*
+		 * Special case: if there's an argument left then assume that
+		 * it's a symbol filter:
+		 */
+		if (argc > 1)
+			usage_with_options(report_usage, options);
+
+		report.symbol_filter_str = argv[0];
+	}
 
 	sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", stdout);
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index ea40e4e8b22..c941bb640f4 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -296,7 +296,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel,
 	if (system_wide)
 		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus,
 						group, group_fd);
-	if (!target_pid && !target_tid) {
+	if (!target_pid && !target_tid && (!group || evsel == first)) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 3e087ce8daa..1c5b9801ac6 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -13,6 +13,7 @@
 #include "util/parse-events.h"
 #include "util/symbol.h"
 #include "util/thread_map.h"
+#include "util/pmu.h"
 #include "../../include/linux/hw_breakpoint.h"
 
 #include <sys/mman.h>
@@ -650,7 +651,7 @@ static int test__checkevent_raw(struct perf_evlist *evlist)
 
 	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
-	TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong config", 0x1a == evsel->attr.config);
 	return 0;
 }
 
@@ -677,6 +678,24 @@ static int test__checkevent_symbolic_name(struct perf_evlist *evlist)
 	return 0;
 }
 
+static int test__checkevent_symbolic_name_config(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = list_entry(evlist->entries.next,
+					      struct perf_evsel, node);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong period",
+			100000 == evsel->attr.sample_period);
+	TEST_ASSERT_VAL("wrong config1",
+			0 == evsel->attr.config1);
+	TEST_ASSERT_VAL("wrong config2",
+			1 == evsel->attr.config2);
+	return 0;
+}
+
 static int test__checkevent_symbolic_alias(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel = list_entry(evlist->entries.next,
@@ -858,6 +877,115 @@ static int test__checkevent_genhw_modifier(struct perf_evlist *evlist)
 	return test__checkevent_genhw(evlist);
 }
 
+static int test__checkevent_breakpoint_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = list_entry(evlist->entries.next,
+					      struct perf_evsel, node);
+
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	return test__checkevent_breakpoint(evlist);
+}
+
+static int test__checkevent_breakpoint_x_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = list_entry(evlist->entries.next,
+					      struct perf_evsel, node);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	return test__checkevent_breakpoint_x(evlist);
+}
+
+static int test__checkevent_breakpoint_r_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = list_entry(evlist->entries.next,
+					      struct perf_evsel, node);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+
+	return test__checkevent_breakpoint_r(evlist);
+}
+
+static int test__checkevent_breakpoint_w_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = list_entry(evlist->entries.next,
+					      struct perf_evsel, node);
+
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+
+	return test__checkevent_breakpoint_w(evlist);
+}
+
+static int test__checkevent_pmu(struct perf_evlist *evlist)
+{
+
+	struct perf_evsel *evsel = list_entry(evlist->entries.next,
+					      struct perf_evsel, node);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",    10 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong config1",    1 == evsel->attr.config1);
+	TEST_ASSERT_VAL("wrong config2",    3 == evsel->attr.config2);
+	TEST_ASSERT_VAL("wrong period",  1000 == evsel->attr.sample_period);
+
+	return 0;
+}
+
+static int test__checkevent_list(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries);
+
+	/* r1 */
+	evsel = list_entry(evlist->entries.next, struct perf_evsel, node);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong config1", 0 == evsel->attr.config1);
+	TEST_ASSERT_VAL("wrong config2", 0 == evsel->attr.config2);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	/* syscalls:sys_enter_open:k */
+	evsel = list_entry(evsel->node.next, struct perf_evsel, node);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong sample_type",
+		(PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | PERF_SAMPLE_CPU) ==
+		evsel->attr.sample_type);
+	TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->attr.sample_period);
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	/* 1:1:hp */
+	evsel = list_entry(evsel->node.next, struct perf_evsel, node);
+	TEST_ASSERT_VAL("wrong type", 1 == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+
+	return 0;
+}
+
 static struct test__event_st {
 	const char *name;
 	__u32 type;
@@ -872,7 +1000,7 @@ static struct test__event_st {
 		.check = test__checkevent_tracepoint_multi,
 	},
 	{
-		.name  = "r1",
+		.name  = "r1a",
 		.check = test__checkevent_raw,
 	},
 	{
@@ -884,6 +1012,10 @@ static struct test__event_st {
 		.check = test__checkevent_symbolic_name,
 	},
 	{
+		.name  = "cycles/period=100000,config2/",
+		.check = test__checkevent_symbolic_name_config,
+	},
+	{
 		.name  = "faults",
 		.check = test__checkevent_symbolic_alias,
 	},
@@ -916,7 +1048,7 @@ static struct test__event_st {
 		.check = test__checkevent_tracepoint_multi_modifier,
 	},
 	{
-		.name  = "r1:kp",
+		.name  = "r1a:kp",
 		.check = test__checkevent_raw_modifier,
 	},
 	{
@@ -935,6 +1067,30 @@ static struct test__event_st {
 		.name  = "L1-dcache-load-miss:kp",
 		.check = test__checkevent_genhw_modifier,
 	},
+	{
+		.name  = "mem:0:u",
+		.check = test__checkevent_breakpoint_modifier,
+	},
+	{
+		.name  = "mem:0:x:k",
+		.check = test__checkevent_breakpoint_x_modifier,
+	},
+	{
+		.name  = "mem:0:r:hp",
+		.check = test__checkevent_breakpoint_r_modifier,
+	},
+	{
+		.name  = "mem:0:w:up",
+		.check = test__checkevent_breakpoint_w_modifier,
+	},
+	{
+		.name  = "cpu/config=10,config1,config2=3,period=1000/u",
+		.check = test__checkevent_pmu,
+	},
+	{
+		.name  = "r1,syscalls:sys_enter_open:k,1:1:hp",
+		.check = test__checkevent_list,
+	},
 };
 
 #define TEST__EVENTS_CNT (sizeof(test__events) / sizeof(struct test__event_st))
@@ -960,10 +1116,9 @@ static int test__parse_events(void)
 		}
 
 		ret = e->check(evlist);
+		perf_evlist__delete(evlist);
 		if (ret)
 			break;
-
-		perf_evlist__delete(evlist);
 	}
 
 	return ret;
@@ -1462,6 +1617,11 @@ static int test__rdpmc(void)
 
 #endif
 
+static int test__perf_pmu(void)
+{
+	return perf_pmu__test();
+}
+
 static struct test {
 	const char *desc;
 	int (*func)(void);
@@ -1497,6 +1657,10 @@ static struct test {
 		.func = test__PERF_RECORD,
 	},
 	{
+		.desc = "Test perf pmu format parsing",
+		.func = test__perf_pmu,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak
index 6170fd2531b..d9084e03ce5 100644
--- a/tools/perf/config/feature-tests.mak
+++ b/tools/perf/config/feature-tests.mak
@@ -65,6 +65,21 @@ int main(void)
 endef
 endif
 
+ifndef NO_GTK2
+define SOURCE_GTK2
+#pragma GCC diagnostic ignored \"-Wstrict-prototypes\"
+#include <gtk/gtk.h>
+#pragma GCC diagnostic error \"-Wstrict-prototypes\"
+
+int main(int argc, char *argv[])
+{
+        gtk_init(&argc, &argv);
+
+        return 0;
+}
+endef
+endif
+
 ifndef NO_LIBPERL
 define SOURCE_PERL_EMBED
 #include <EXTERN.h>
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index e5a462f1d07..199f69ec656 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -28,8 +28,8 @@ int symbol__annotate_init(struct map *map __used, struct symbol *sym)
 int symbol__alloc_hist(struct symbol *sym)
 {
 	struct annotation *notes = symbol__annotation(sym);
-	size_t sizeof_sym_hist = (sizeof(struct sym_hist) +
-				  (sym->end - sym->start) * sizeof(u64));
+	const size_t size = sym->end - sym->start + 1;
+	size_t sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(u64));
 
 	notes->src = zalloc(sizeof(*notes->src) + symbol_conf.nr_events * sizeof_sym_hist);
 	if (notes->src == NULL)
@@ -64,7 +64,7 @@ int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 
 	pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr));
 
-	if (addr >= sym->end)
+	if (addr > sym->end)
 		return 0;
 
 	offset = addr - sym->start;
@@ -408,7 +408,7 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
 	if (!notes->src->lines)
 		return -1;
 
-	start = map->unmap_ip(map, sym->start);
+	start = map__rip_2objdump(map, sym->start);
 
 	for (i = 0; i < len; i++) {
 		char *path = NULL;
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index fc5e5a09d5b..8dd224df3e5 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -45,6 +45,18 @@ void setup_browser(bool fallback_to_pager);
 void exit_browser(bool wait_for_ok);
 #endif
 
+#ifdef NO_GTK2_SUPPORT
+static inline void perf_gtk_setup_browser(int argc __used, const char *argv[] __used, bool fallback_to_pager)
+{
+	if (fallback_to_pager)
+		setup_pager();
+}
+static inline void perf_gtk_exit_browser(bool wait_for_ok __used) {}
+#else
+void perf_gtk_setup_browser(int argc, const char *argv[], bool fallback_to_pager);
+void perf_gtk_exit_browser(bool wait_for_ok);
+#endif
+
 char *alias_lookup(const char *alias);
 int split_cmdline(char *cmdline, const char ***argv);
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 159263d17c2..1986d8051bd 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -51,13 +51,15 @@ struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
 void perf_evlist__config_attrs(struct perf_evlist *evlist,
 			       struct perf_record_opts *opts)
 {
-	struct perf_evsel *evsel;
+	struct perf_evsel *evsel, *first;
 
 	if (evlist->cpus->map[0] < 0)
 		opts->no_inherit = true;
 
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
 	list_for_each_entry(evsel, &evlist->entries, node) {
-		perf_evsel__config(evsel, opts);
+		perf_evsel__config(evsel, opts, first);
 
 		if (evlist->nr_entries > 1)
 			evsel->attr.sample_type |= PERF_SAMPLE_ID;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f421f7cbc0d..8c13dbcb84b 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -34,7 +34,7 @@ int __perf_evsel__sample_size(u64 sample_type)
 	return size;
 }
 
-static void hists__init(struct hists *hists)
+void hists__init(struct hists *hists)
 {
 	memset(hists, 0, sizeof(*hists));
 	hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
@@ -63,7 +63,8 @@ struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
 	return evsel;
 }
 
-void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts)
+void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts,
+			struct perf_evsel *first)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	int track = !evsel->idx; /* only the first counter needs these */
@@ -134,7 +135,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts)
 	attr->mmap = track;
 	attr->comm = track;
 
-	if (!opts->target_pid && !opts->target_tid && !opts->system_wide) {
+	if (!opts->target_pid && !opts->target_tid && !opts->system_wide &&
+	    (!opts->group || evsel == first)) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
@@ -578,6 +580,8 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 			return -EFAULT;
 
 		data->raw_data = (void *) pdata;
+
+		array = (void *)array + data->raw_size + sizeof(u32);
 	}
 
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 326b8e4d503..3d6b3e4cb66 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -80,7 +80,8 @@ void perf_evsel__exit(struct perf_evsel *evsel);
 void perf_evsel__delete(struct perf_evsel *evsel);
 
 void perf_evsel__config(struct perf_evsel *evsel,
-			struct perf_record_opts *opts);
+			struct perf_record_opts *opts,
+			struct perf_evsel *first);
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
@@ -169,4 +170,6 @@ static inline int perf_evsel__sample_size(struct perf_evsel *evsel)
 	return __perf_evsel__sample_size(evsel->attr.sample_type);
 }
 
+void hists__init(struct hists *hists);
+
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/gtk/browser.c b/tools/perf/util/gtk/browser.c
new file mode 100644
index 00000000000..258352a2356
--- /dev/null
+++ b/tools/perf/util/gtk/browser.c
@@ -0,0 +1,189 @@
+#include "../evlist.h"
+#include "../cache.h"
+#include "../evsel.h"
+#include "../sort.h"
+#include "../hist.h"
+#include "gtk.h"
+
+#include <signal.h>
+
+#define MAX_COLUMNS			32
+
+void perf_gtk_setup_browser(int argc, const char *argv[],
+			    bool fallback_to_pager __used)
+{
+	gtk_init(&argc, (char ***)&argv);
+}
+
+void perf_gtk_exit_browser(bool wait_for_ok __used)
+{
+	gtk_main_quit();
+}
+
+static void perf_gtk_signal(int sig)
+{
+	psignal(sig, "perf");
+	gtk_main_quit();
+}
+
+static void perf_gtk_resize_window(GtkWidget *window)
+{
+	GdkRectangle rect;
+	GdkScreen *screen;
+	int monitor;
+	int height;
+	int width;
+
+	screen = gtk_widget_get_screen(window);
+
+	monitor = gdk_screen_get_monitor_at_window(screen, window->window);
+
+	gdk_screen_get_monitor_geometry(screen, monitor, &rect);
+
+	width	= rect.width * 3 / 4;
+	height	= rect.height * 3 / 4;
+
+	gtk_window_resize(GTK_WINDOW(window), width, height);
+}
+
+static void perf_gtk_show_hists(GtkWidget *window, struct hists *hists)
+{
+	GType col_types[MAX_COLUMNS];
+	GtkCellRenderer *renderer;
+	struct sort_entry *se;
+	GtkListStore *store;
+	struct rb_node *nd;
+	u64 total_period;
+	GtkWidget *view;
+	int col_idx;
+	int nr_cols;
+
+	nr_cols = 0;
+
+	/* The percentage column */
+	col_types[nr_cols++] = G_TYPE_STRING;
+
+	list_for_each_entry(se, &hist_entry__sort_list, list) {
+		if (se->elide)
+			continue;
+
+		col_types[nr_cols++] = G_TYPE_STRING;
+	}
+
+	store = gtk_list_store_newv(nr_cols, col_types);
+
+	view = gtk_tree_view_new();
+
+	renderer = gtk_cell_renderer_text_new();
+
+	col_idx = 0;
+
+	/* The percentage column */
+	gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
+						    -1, "Overhead (%)",
+						    renderer, "text",
+						    col_idx++, NULL);
+
+	list_for_each_entry(se, &hist_entry__sort_list, list) {
+		if (se->elide)
+			continue;
+
+		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
+							    -1, se->se_header,
+							    renderer, "text",
+							    col_idx++, NULL);
+	}
+
+	gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store));
+
+	g_object_unref(GTK_TREE_MODEL(store));
+
+	total_period = hists->stats.total_period;
+
+	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+		GtkTreeIter iter;
+		double percent;
+		char s[512];
+
+		if (h->filtered)
+			continue;
+
+		gtk_list_store_append(store, &iter);
+
+		col_idx = 0;
+
+		percent = (h->period * 100.0) / total_period;
+
+		snprintf(s, ARRAY_SIZE(s), "%.2f", percent);
+
+		gtk_list_store_set(store, &iter, col_idx++, s, -1);
+
+		list_for_each_entry(se, &hist_entry__sort_list, list) {
+			if (se->elide)
+				continue;
+
+			se->se_snprintf(h, s, ARRAY_SIZE(s),
+					hists__col_len(hists, se->se_width_idx));
+
+			gtk_list_store_set(store, &iter, col_idx++, s, -1);
+		}
+	}
+
+	gtk_container_add(GTK_CONTAINER(window), view);
+}
+
+int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
+				  const char *help __used,
+				  void (*timer) (void *arg)__used,
+				  void *arg __used, int delay_secs __used)
+{
+	struct perf_evsel *pos;
+	GtkWidget *notebook;
+	GtkWidget *window;
+
+	signal(SIGSEGV, perf_gtk_signal);
+	signal(SIGFPE,  perf_gtk_signal);
+	signal(SIGINT,  perf_gtk_signal);
+	signal(SIGQUIT, perf_gtk_signal);
+	signal(SIGTERM, perf_gtk_signal);
+
+	window = gtk_window_new(GTK_WINDOW_TOPLEVEL);
+
+	gtk_window_set_title(GTK_WINDOW(window), "perf report");
+
+	g_signal_connect(window, "delete_event", gtk_main_quit, NULL);
+
+	notebook = gtk_notebook_new();
+
+	list_for_each_entry(pos, &evlist->entries, node) {
+		struct hists *hists = &pos->hists;
+		const char *evname = event_name(pos);
+		GtkWidget *scrolled_window;
+		GtkWidget *tab_label;
+
+		scrolled_window = gtk_scrolled_window_new(NULL, NULL);
+
+		gtk_scrolled_window_set_policy(GTK_SCROLLED_WINDOW(scrolled_window),
+							GTK_POLICY_AUTOMATIC,
+							GTK_POLICY_AUTOMATIC);
+
+		perf_gtk_show_hists(scrolled_window, hists);
+
+		tab_label = gtk_label_new(evname);
+
+		gtk_notebook_append_page(GTK_NOTEBOOK(notebook), scrolled_window, tab_label);
+	}
+
+	gtk_container_add(GTK_CONTAINER(window), notebook);
+
+	gtk_widget_show_all(window);
+
+	perf_gtk_resize_window(window);
+
+	gtk_window_set_position(GTK_WINDOW(window), GTK_WIN_POS_CENTER);
+
+	gtk_main();
+
+	return 0;
+}
diff --git a/tools/perf/util/gtk/gtk.h b/tools/perf/util/gtk/gtk.h
new file mode 100644
index 00000000000..75177ee0403
--- /dev/null
+++ b/tools/perf/util/gtk/gtk.h
@@ -0,0 +1,8 @@
+#ifndef _PERF_GTK_H_
+#define _PERF_GTK_H_ 1
+
+#pragma GCC diagnostic ignored "-Wstrict-prototypes"
+#include <gtk/gtk.h>
+#pragma GCC diagnostic error "-Wstrict-prototypes"
+
+#endif /* _PERF_GTK_H_ */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index fcd9cf3ea63..4c7c2d73251 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1177,7 +1177,7 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
 		goto error;
 
 	msz = sizeof(attr);
-	if (sz < (ssize_t)msz)
+	if (sz < msz)
 		msz = sz;
 
 	for (i = 0 ; i < nre; i++) {
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 3dc99a9b71f..2ec4b60aff6 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -10,11 +10,14 @@ static bool hists__filter_entry_by_dso(struct hists *hists,
 				       struct hist_entry *he);
 static bool hists__filter_entry_by_thread(struct hists *hists,
 					  struct hist_entry *he);
+static bool hists__filter_entry_by_symbol(struct hists *hists,
+					  struct hist_entry *he);
 
 enum hist_filter {
 	HIST_FILTER__DSO,
 	HIST_FILTER__THREAD,
 	HIST_FILTER__PARENT,
+	HIST_FILTER__SYMBOL,
 };
 
 struct callchain_param	callchain_param = {
@@ -420,6 +423,7 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he)
 {
 	hists__filter_entry_by_dso(hists, he);
 	hists__filter_entry_by_thread(hists, he);
+	hists__filter_entry_by_symbol(hists, he);
 }
 
 static void __hists__collapse_resort(struct hists *hists, bool threaded)
@@ -603,7 +607,7 @@ static void init_rem_hits(void)
 	rem_hits.ms.sym = rem_sq_bracket;
 }
 
-static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
+static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 					 u64 total_samples, int depth,
 					 int depth_mask, int left_margin)
 {
@@ -611,21 +615,16 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 	struct callchain_node *child;
 	struct callchain_list *chain;
 	int new_depth_mask = depth_mask;
-	u64 new_total;
 	u64 remaining;
 	size_t ret = 0;
 	int i;
 	uint entries_printed = 0;
 
-	if (callchain_param.mode == CHAIN_GRAPH_REL)
-		new_total = self->children_hit;
-	else
-		new_total = total_samples;
-
-	remaining = new_total;
+	remaining = total_samples;
 
-	node = rb_first(&self->rb_root);
+	node = rb_first(root);
 	while (node) {
+		u64 new_total;
 		u64 cumul;
 
 		child = rb_entry(node, struct callchain_node, rb_node);
@@ -653,11 +652,17 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 		list_for_each_entry(chain, &child->val, list) {
 			ret += ipchain__fprintf_graph(fp, chain, depth,
 						      new_depth_mask, i++,
-						      new_total,
+						      total_samples,
 						      cumul,
 						      left_margin);
 		}
-		ret += __callchain__fprintf_graph(fp, child, new_total,
+
+		if (callchain_param.mode == CHAIN_GRAPH_REL)
+			new_total = child->children_hit;
+		else
+			new_total = total_samples;
+
+		ret += __callchain__fprintf_graph(fp, &child->rb_root, new_total,
 						  depth + 1,
 						  new_depth_mask | (1 << depth),
 						  left_margin);
@@ -667,61 +672,75 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 	}
 
 	if (callchain_param.mode == CHAIN_GRAPH_REL &&
-		remaining && remaining != new_total) {
+		remaining && remaining != total_samples) {
 
 		if (!rem_sq_bracket)
 			return ret;
 
 		new_depth_mask &= ~(1 << (depth - 1));
-
 		ret += ipchain__fprintf_graph(fp, &rem_hits, depth,
-					      new_depth_mask, 0, new_total,
+					      new_depth_mask, 0, total_samples,
 					      remaining, left_margin);
 	}
 
 	return ret;
 }
 
-static size_t callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
+static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 				       u64 total_samples, int left_margin)
 {
+	struct callchain_node *cnode;
 	struct callchain_list *chain;
+	u32 entries_printed = 0;
 	bool printed = false;
+	struct rb_node *node;
 	int i = 0;
-	int ret = 0;
-	u32 entries_printed = 0;
-
-	list_for_each_entry(chain, &self->val, list) {
-		if (!i++ && sort__first_dimension == SORT_SYM)
-			continue;
-
-		if (!printed) {
-			ret += callchain__fprintf_left_margin(fp, left_margin);
-			ret += fprintf(fp, "|\n");
-			ret += callchain__fprintf_left_margin(fp, left_margin);
-			ret += fprintf(fp, "---");
-
-			left_margin += 3;
-			printed = true;
-		} else
-			ret += callchain__fprintf_left_margin(fp, left_margin);
+	int ret;
 
-		if (chain->ms.sym)
-			ret += fprintf(fp, " %s\n", chain->ms.sym->name);
-		else
-			ret += fprintf(fp, " %p\n", (void *)(long)chain->ip);
+	/*
+	 * If have one single callchain root, don't bother printing
+	 * its percentage (100 % in fractal mode and the same percentage
+	 * than the hist in graph mode). This also avoid one level of column.
+	 */
+	node = rb_first(root);
+	if (node && !rb_next(node)) {
+		cnode = rb_entry(node, struct callchain_node, rb_node);
+		list_for_each_entry(chain, &cnode->val, list) {
+			/*
+			 * If we sort by symbol, the first entry is the same than
+			 * the symbol. No need to print it otherwise it appears as
+			 * displayed twice.
+			 */
+			if (!i++ && sort__first_dimension == SORT_SYM)
+				continue;
+			if (!printed) {
+				ret += callchain__fprintf_left_margin(fp, left_margin);
+				ret += fprintf(fp, "|\n");
+				ret += callchain__fprintf_left_margin(fp, left_margin);
+				ret += fprintf(fp, "---");
+				left_margin += 3;
+				printed = true;
+			} else
+				ret += callchain__fprintf_left_margin(fp, left_margin);
+
+			if (chain->ms.sym)
+				ret += fprintf(fp, " %s\n", chain->ms.sym->name);
+			else
+				ret += fprintf(fp, " %p\n", (void *)(long)chain->ip);
 
-		if (++entries_printed == callchain_param.print_limit)
-			break;
+			if (++entries_printed == callchain_param.print_limit)
+				break;
+		}
+		root = &cnode->rb_root;
 	}
 
-	ret += __callchain__fprintf_graph(fp, self, total_samples, 1, 1, left_margin);
-
-	return ret;
+	return __callchain__fprintf_graph(fp, root, total_samples,
+					  1, 1, left_margin);
 }
 
-static size_t callchain__fprintf_flat(FILE *fp, struct callchain_node *self,
-				      u64 total_samples)
+static size_t __callchain__fprintf_flat(FILE *fp,
+					struct callchain_node *self,
+					u64 total_samples)
 {
 	struct callchain_list *chain;
 	size_t ret = 0;
@@ -729,7 +748,7 @@ static size_t callchain__fprintf_flat(FILE *fp, struct callchain_node *self,
 	if (!self)
 		return 0;
 
-	ret += callchain__fprintf_flat(fp, self->parent, total_samples);
+	ret += __callchain__fprintf_flat(fp, self->parent, total_samples);
 
 
 	list_for_each_entry(chain, &self->val, list) {
@@ -745,44 +764,58 @@ static size_t callchain__fprintf_flat(FILE *fp, struct callchain_node *self,
 	return ret;
 }
 
-static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
-					    u64 total_samples, int left_margin,
-					    FILE *fp)
+static size_t callchain__fprintf_flat(FILE *fp, struct rb_root *self,
+				      u64 total_samples)
 {
-	struct rb_node *rb_node;
-	struct callchain_node *chain;
 	size_t ret = 0;
 	u32 entries_printed = 0;
+	struct rb_node *rb_node;
+	struct callchain_node *chain;
 
-	rb_node = rb_first(&he->sorted_chain);
+	rb_node = rb_first(self);
 	while (rb_node) {
 		double percent;
 
 		chain = rb_entry(rb_node, struct callchain_node, rb_node);
 		percent = chain->hit * 100.0 / total_samples;
-		switch (callchain_param.mode) {
-		case CHAIN_FLAT:
-			ret += percent_color_fprintf(fp, "           %6.2f%%\n",
-						     percent);
-			ret += callchain__fprintf_flat(fp, chain, total_samples);
-			break;
-		case CHAIN_GRAPH_ABS: /* Falldown */
-		case CHAIN_GRAPH_REL:
-			ret += callchain__fprintf_graph(fp, chain, total_samples,
-							left_margin);
-		case CHAIN_NONE:
-		default:
-			break;
-		}
+
+		ret = percent_color_fprintf(fp, "           %6.2f%%\n", percent);
+		ret += __callchain__fprintf_flat(fp, chain, total_samples);
 		ret += fprintf(fp, "\n");
 		if (++entries_printed == callchain_param.print_limit)
 			break;
+
 		rb_node = rb_next(rb_node);
 	}
 
 	return ret;
 }
 
+static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
+					    u64 total_samples, int left_margin,
+					    FILE *fp)
+{
+	switch (callchain_param.mode) {
+	case CHAIN_GRAPH_REL:
+		return callchain__fprintf_graph(fp, &he->sorted_chain, he->period,
+						left_margin);
+		break;
+	case CHAIN_GRAPH_ABS:
+		return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples,
+						left_margin);
+		break;
+	case CHAIN_FLAT:
+		return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples);
+		break;
+	case CHAIN_NONE:
+		break;
+	default:
+		pr_err("Bad callchain mode\n");
+	}
+
+	return 0;
+}
+
 void hists__output_recalc_col_len(struct hists *hists, int max_rows)
 {
 	struct rb_node *next = rb_first(&hists->entries);
@@ -887,9 +920,9 @@ static int hist_entry__pcnt_snprintf(struct hist_entry *he, char *s,
 		diff = new_percent - old_percent;
 
 		if (fabs(diff) >= 0.01)
-			ret += scnprintf(bf, sizeof(bf), "%+4.2F%%", diff);
+			scnprintf(bf, sizeof(bf), "%+4.2F%%", diff);
 		else
-			ret += scnprintf(bf, sizeof(bf), " ");
+			scnprintf(bf, sizeof(bf), " ");
 
 		if (sep)
 			ret += scnprintf(s + ret, size - ret, "%c%s", *sep, bf);
@@ -898,9 +931,9 @@ static int hist_entry__pcnt_snprintf(struct hist_entry *he, char *s,
 
 		if (show_displacement) {
 			if (displacement)
-				ret += scnprintf(bf, sizeof(bf), "%+4ld", displacement);
+				scnprintf(bf, sizeof(bf), "%+4ld", displacement);
 			else
-				ret += scnprintf(bf, sizeof(bf), " ");
+				scnprintf(bf, sizeof(bf), " ");
 
 			if (sep)
 				ret += scnprintf(s + ret, size - ret, "%c%s", *sep, bf);
@@ -1247,6 +1280,37 @@ void hists__filter_by_thread(struct hists *hists)
 	}
 }
 
+static bool hists__filter_entry_by_symbol(struct hists *hists,
+					  struct hist_entry *he)
+{
+	if (hists->symbol_filter_str != NULL &&
+	    (!he->ms.sym || strstr(he->ms.sym->name,
+				   hists->symbol_filter_str) == NULL)) {
+		he->filtered |= (1 << HIST_FILTER__SYMBOL);
+		return true;
+	}
+
+	return false;
+}
+
+void hists__filter_by_symbol(struct hists *hists)
+{
+	struct rb_node *nd;
+
+	hists->nr_entries = hists->stats.total_period = 0;
+	hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+	hists__reset_col_len(hists);
+
+	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		if (hists__filter_entry_by_symbol(hists, h))
+			continue;
+
+		hists__remove_entry_filter(hists, h, HIST_FILTER__SYMBOL);
+	}
+}
+
 int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip)
 {
 	return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 9413f3e31fe..2cae9df40e0 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -62,6 +62,7 @@ struct hists {
 	const struct thread	*thread_filter;
 	const struct dso	*dso_filter;
 	const char		*uid_filter_str;
+	const char		*symbol_filter_str;
 	pthread_mutex_t		lock;
 	struct events_stats	stats;
 	u64			event_stream;
@@ -107,6 +108,7 @@ int hist_entry__annotate(struct hist_entry *self, size_t privsize);
 
 void hists__filter_by_dso(struct hists *hists);
 void hists__filter_by_thread(struct hists *hists);
+void hists__filter_by_symbol(struct hists *hists);
 
 u16 hists__col_len(struct hists *self, enum hist_column col);
 void hists__set_col_len(struct hists *self, enum hist_column col, u16 len);
@@ -145,6 +147,23 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
 				  int refresh);
 #endif
 
+#ifdef NO_GTK2_SUPPORT
+static inline
+int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __used,
+				  const char *help __used,
+				  void(*timer)(void *arg) __used,
+				  void *arg __used,
+				  int refresh __used)
+{
+	return 0;
+}
+
+#else
+int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help,
+				  void(*timer)(void *arg), void *arg,
+				  int refresh);
+#endif
+
 unsigned int hists__sort_list_width(struct hists *self);
 
 #endif	/* __PERF_HIST_H */
diff --git a/tools/perf/util/include/linux/module.h b/tools/perf/util/include/linux/export.h
index b43e2dc21e0..b43e2dc21e0 100644
--- a/tools/perf/util/include/linux/module.h
+++ b/tools/perf/util/include/linux/export.h
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c7a6f6faf91..5b3a0ef4e23 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -11,6 +11,10 @@
 #include "cache.h"
 #include "header.h"
 #include "debugfs.h"
+#include "parse-events-flex.h"
+#include "pmu.h"
+
+#define MAX_NAME_LEN 100
 
 struct event_symbol {
 	u8		type;
@@ -19,11 +23,8 @@ struct event_symbol {
 	const char	*alias;
 };
 
-enum event_result {
-	EVT_FAILED,
-	EVT_HANDLED,
-	EVT_HANDLED_ALL
-};
+int parse_events_parse(struct list_head *list, struct list_head *list_tmp,
+		       int *idx);
 
 #define CHW(x) .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_##x
 #define CSW(x) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_##x
@@ -354,7 +355,24 @@ const char *__event_name(int type, u64 config)
 	return "unknown";
 }
 
-static int parse_aliases(const char **str, const char *names[][MAX_ALIASES], int size)
+static int add_event(struct list_head *list, int *idx,
+		     struct perf_event_attr *attr, char *name)
+{
+	struct perf_evsel *evsel;
+
+	event_attr_init(attr);
+
+	evsel = perf_evsel__new(attr, (*idx)++);
+	if (!evsel)
+		return -ENOMEM;
+
+	list_add_tail(&evsel->node, list);
+
+	evsel->name = strdup(name);
+	return 0;
+}
+
+static int parse_aliases(char *str, const char *names[][MAX_ALIASES], int size)
 {
 	int i, j;
 	int n, longest = -1;
@@ -362,58 +380,57 @@ static int parse_aliases(const char **str, const char *names[][MAX_ALIASES], int
 	for (i = 0; i < size; i++) {
 		for (j = 0; j < MAX_ALIASES && names[i][j]; j++) {
 			n = strlen(names[i][j]);
-			if (n > longest && !strncasecmp(*str, names[i][j], n))
+			if (n > longest && !strncasecmp(str, names[i][j], n))
 				longest = n;
 		}
-		if (longest > 0) {
-			*str += longest;
+		if (longest > 0)
 			return i;
-		}
 	}
 
 	return -1;
 }
 
-static enum event_result
-parse_generic_hw_event(const char **str, struct perf_event_attr *attr)
+int parse_events_add_cache(struct list_head *list, int *idx,
+			   char *type, char *op_result1, char *op_result2)
 {
-	const char *s = *str;
+	struct perf_event_attr attr;
+	char name[MAX_NAME_LEN];
 	int cache_type = -1, cache_op = -1, cache_result = -1;
+	char *op_result[2] = { op_result1, op_result2 };
+	int i, n;
 
-	cache_type = parse_aliases(&s, hw_cache, PERF_COUNT_HW_CACHE_MAX);
 	/*
 	 * No fallback - if we cannot get a clear cache type
 	 * then bail out:
 	 */
+	cache_type = parse_aliases(type, hw_cache,
+				   PERF_COUNT_HW_CACHE_MAX);
 	if (cache_type == -1)
-		return EVT_FAILED;
+		return -EINVAL;
 
-	while ((cache_op == -1 || cache_result == -1) && *s == '-') {
-		++s;
+	n = snprintf(name, MAX_NAME_LEN, "%s", type);
+
+	for (i = 0; (i < 2) && (op_result[i]); i++) {
+		char *str = op_result[i];
+
+		snprintf(name + n, MAX_NAME_LEN - n, "-%s\n", str);
 
 		if (cache_op == -1) {
-			cache_op = parse_aliases(&s, hw_cache_op,
-						PERF_COUNT_HW_CACHE_OP_MAX);
+			cache_op = parse_aliases(str, hw_cache_op,
+						 PERF_COUNT_HW_CACHE_OP_MAX);
 			if (cache_op >= 0) {
 				if (!is_cache_op_valid(cache_type, cache_op))
-					return EVT_FAILED;
+					return -EINVAL;
 				continue;
 			}
 		}
 
 		if (cache_result == -1) {
-			cache_result = parse_aliases(&s, hw_cache_result,
+			cache_result = parse_aliases(str, hw_cache_result,
 						PERF_COUNT_HW_CACHE_RESULT_MAX);
 			if (cache_result >= 0)
 				continue;
 		}
-
-		/*
-		 * Can't parse this as a cache op or result, so back up
-		 * to the '-'.
-		 */
-		--s;
-		break;
 	}
 
 	/*
@@ -428,20 +445,17 @@ parse_generic_hw_event(const char **str, struct perf_event_attr *attr)
 	if (cache_result == -1)
 		cache_result = PERF_COUNT_HW_CACHE_RESULT_ACCESS;
 
-	attr->config = cache_type | (cache_op << 8) | (cache_result << 16);
-	attr->type = PERF_TYPE_HW_CACHE;
-
-	*str = s;
-	return EVT_HANDLED;
+	memset(&attr, 0, sizeof(attr));
+	attr.config = cache_type | (cache_op << 8) | (cache_result << 16);
+	attr.type = PERF_TYPE_HW_CACHE;
+	return add_event(list, idx, &attr, name);
 }
 
-static enum event_result
-parse_single_tracepoint_event(char *sys_name,
-			      const char *evt_name,
-			      unsigned int evt_length,
-			      struct perf_event_attr *attr,
-			      const char **strp)
+static int add_tracepoint(struct list_head *list, int *idx,
+			  char *sys_name, char *evt_name)
 {
+	struct perf_event_attr attr;
+	char name[MAX_NAME_LEN];
 	char evt_path[MAXPATHLEN];
 	char id_buf[4];
 	u64 id;
@@ -452,130 +466,80 @@ parse_single_tracepoint_event(char *sys_name,
 
 	fd = open(evt_path, O_RDONLY);
 	if (fd < 0)
-		return EVT_FAILED;
+		return -1;
 
 	if (read(fd, id_buf, sizeof(id_buf)) < 0) {
 		close(fd);
-		return EVT_FAILED;
+		return -1;
 	}
 
 	close(fd);
 	id = atoll(id_buf);
-	attr->config = id;
-	attr->type = PERF_TYPE_TRACEPOINT;
-	*strp += strlen(sys_name) + evt_length + 1; /* + 1 for the ':' */
-
-	attr->sample_type |= PERF_SAMPLE_RAW;
-	attr->sample_type |= PERF_SAMPLE_TIME;
-	attr->sample_type |= PERF_SAMPLE_CPU;
-
-	attr->sample_period = 1;
 
+	memset(&attr, 0, sizeof(attr));
+	attr.config = id;
+	attr.type = PERF_TYPE_TRACEPOINT;
+	attr.sample_type |= PERF_SAMPLE_RAW;
+	attr.sample_type |= PERF_SAMPLE_TIME;
+	attr.sample_type |= PERF_SAMPLE_CPU;
+	attr.sample_period = 1;
 
-	return EVT_HANDLED;
+	snprintf(name, MAX_NAME_LEN, "%s:%s", sys_name, evt_name);
+	return add_event(list, idx, &attr, name);
 }
 
-/* sys + ':' + event + ':' + flags*/
-#define MAX_EVOPT_LEN	(MAX_EVENT_LENGTH * 2 + 2 + 128)
-static enum event_result
-parse_multiple_tracepoint_event(struct perf_evlist *evlist, char *sys_name,
-				const char *evt_exp, char *flags)
+static int add_tracepoint_multi(struct list_head *list, int *idx,
+				char *sys_name, char *evt_name)
 {
 	char evt_path[MAXPATHLEN];
 	struct dirent *evt_ent;
 	DIR *evt_dir;
+	int ret = 0;
 
 	snprintf(evt_path, MAXPATHLEN, "%s/%s", tracing_events_path, sys_name);
 	evt_dir = opendir(evt_path);
-
 	if (!evt_dir) {
 		perror("Can't open event dir");
-		return EVT_FAILED;
+		return -1;
 	}
 
-	while ((evt_ent = readdir(evt_dir))) {
-		char event_opt[MAX_EVOPT_LEN + 1];
-		int len;
-
+	while (!ret && (evt_ent = readdir(evt_dir))) {
 		if (!strcmp(evt_ent->d_name, ".")
 		    || !strcmp(evt_ent->d_name, "..")
 		    || !strcmp(evt_ent->d_name, "enable")
 		    || !strcmp(evt_ent->d_name, "filter"))
 			continue;
 
-		if (!strglobmatch(evt_ent->d_name, evt_exp))
+		if (!strglobmatch(evt_ent->d_name, evt_name))
 			continue;
 
-		len = snprintf(event_opt, MAX_EVOPT_LEN, "%s:%s%s%s", sys_name,
-			       evt_ent->d_name, flags ? ":" : "",
-			       flags ?: "");
-		if (len < 0)
-			return EVT_FAILED;
-
-		if (parse_events(evlist, event_opt, 0))
-			return EVT_FAILED;
+		ret = add_tracepoint(list, idx, sys_name, evt_ent->d_name);
 	}
 
-	return EVT_HANDLED_ALL;
+	return ret;
 }
 
-static enum event_result
-parse_tracepoint_event(struct perf_evlist *evlist, const char **strp,
-		       struct perf_event_attr *attr)
+int parse_events_add_tracepoint(struct list_head *list, int *idx,
+				char *sys, char *event)
 {
-	const char *evt_name;
-	char *flags = NULL, *comma_loc;
-	char sys_name[MAX_EVENT_LENGTH];
-	unsigned int sys_length, evt_length;
-
-	if (debugfs_valid_mountpoint(tracing_events_path))
-		return 0;
-
-	evt_name = strchr(*strp, ':');
-	if (!evt_name)
-		return EVT_FAILED;
-
-	sys_length = evt_name - *strp;
-	if (sys_length >= MAX_EVENT_LENGTH)
-		return 0;
+	int ret;
 
-	strncpy(sys_name, *strp, sys_length);
-	sys_name[sys_length] = '\0';
-	evt_name = evt_name + 1;
+	ret = debugfs_valid_mountpoint(tracing_events_path);
+	if (ret)
+		return ret;
 
-	comma_loc = strchr(evt_name, ',');
-	if (comma_loc) {
-		/* take the event name up to the comma */
-		evt_name = strndup(evt_name, comma_loc - evt_name);
-	}
-	flags = strchr(evt_name, ':');
-	if (flags) {
-		/* split it out: */
-		evt_name = strndup(evt_name, flags - evt_name);
-		flags++;
-	}
-
-	evt_length = strlen(evt_name);
-	if (evt_length >= MAX_EVENT_LENGTH)
-		return EVT_FAILED;
-	if (strpbrk(evt_name, "*?")) {
-		*strp += strlen(sys_name) + evt_length + 1; /* 1 == the ':' */
-		return parse_multiple_tracepoint_event(evlist, sys_name,
-						       evt_name, flags);
-	} else {
-		return parse_single_tracepoint_event(sys_name, evt_name,
-						     evt_length, attr, strp);
-	}
+	return strpbrk(event, "*?") ?
+	       add_tracepoint_multi(list, idx, sys, event) :
+	       add_tracepoint(list, idx, sys, event);
 }
 
-static enum event_result
-parse_breakpoint_type(const char *type, const char **strp,
-		      struct perf_event_attr *attr)
+static int
+parse_breakpoint_type(const char *type, struct perf_event_attr *attr)
 {
 	int i;
 
 	for (i = 0; i < 3; i++) {
-		if (!type[i])
+		if (!type || !type[i])
 			break;
 
 		switch (type[i]) {
@@ -589,164 +553,146 @@ parse_breakpoint_type(const char *type, const char **strp,
 			attr->bp_type |= HW_BREAKPOINT_X;
 			break;
 		default:
-			return EVT_FAILED;
+			return -EINVAL;
 		}
 	}
+
 	if (!attr->bp_type) /* Default */
 		attr->bp_type = HW_BREAKPOINT_R | HW_BREAKPOINT_W;
 
-	*strp = type + i;
-
-	return EVT_HANDLED;
+	return 0;
 }
 
-static enum event_result
-parse_breakpoint_event(const char **strp, struct perf_event_attr *attr)
+int parse_events_add_breakpoint(struct list_head *list, int *idx,
+				void *ptr, char *type)
 {
-	const char *target;
-	const char *type;
-	char *endaddr;
-	u64 addr;
-	enum event_result err;
-
-	target = strchr(*strp, ':');
-	if (!target)
-		return EVT_FAILED;
-
-	if (strncmp(*strp, "mem", target - *strp) != 0)
-		return EVT_FAILED;
-
-	target++;
-
-	addr = strtoull(target, &endaddr, 0);
-	if (target == endaddr)
-		return EVT_FAILED;
-
-	attr->bp_addr = addr;
-	*strp = endaddr;
+	struct perf_event_attr attr;
+	char name[MAX_NAME_LEN];
 
-	type = strchr(target, ':');
+	memset(&attr, 0, sizeof(attr));
+	attr.bp_addr = (unsigned long) ptr;
 
-	/* If no type is defined, just rw as default */
-	if (!type) {
-		attr->bp_type = HW_BREAKPOINT_R | HW_BREAKPOINT_W;
-	} else {
-		err = parse_breakpoint_type(++type, strp, attr);
-		if (err == EVT_FAILED)
-			return EVT_FAILED;
-	}
+	if (parse_breakpoint_type(type, &attr))
+		return -EINVAL;
 
 	/*
 	 * We should find a nice way to override the access length
 	 * Provide some defaults for now
 	 */
-	if (attr->bp_type == HW_BREAKPOINT_X)
-		attr->bp_len = sizeof(long);
+	if (attr.bp_type == HW_BREAKPOINT_X)
+		attr.bp_len = sizeof(long);
 	else
-		attr->bp_len = HW_BREAKPOINT_LEN_4;
+		attr.bp_len = HW_BREAKPOINT_LEN_4;
 
-	attr->type = PERF_TYPE_BREAKPOINT;
+	attr.type = PERF_TYPE_BREAKPOINT;
 
-	return EVT_HANDLED;
+	snprintf(name, MAX_NAME_LEN, "mem:%p:%s", ptr, type ? type : "rw");
+	return add_event(list, idx, &attr, name);
 }
 
-static int check_events(const char *str, unsigned int i)
+static int config_term(struct perf_event_attr *attr,
+		       struct parse_events__term *term)
 {
-	int n;
+	switch (term->type) {
+	case PARSE_EVENTS__TERM_TYPE_CONFIG:
+		attr->config = term->val.num;
+		break;
+	case PARSE_EVENTS__TERM_TYPE_CONFIG1:
+		attr->config1 = term->val.num;
+		break;
+	case PARSE_EVENTS__TERM_TYPE_CONFIG2:
+		attr->config2 = term->val.num;
+		break;
+	case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
+		attr->sample_period = term->val.num;
+		break;
+	case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE:
+		/*
+		 * TODO uncomment when the field is available
+		 * attr->branch_sample_type = term->val.num;
+		 */
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
 
-	n = strlen(event_symbols[i].symbol);
-	if (!strncasecmp(str, event_symbols[i].symbol, n))
-		return n;
+static int config_attr(struct perf_event_attr *attr,
+		       struct list_head *head, int fail)
+{
+	struct parse_events__term *term;
 
-	n = strlen(event_symbols[i].alias);
-	if (n) {
-		if (!strncasecmp(str, event_symbols[i].alias, n))
-			return n;
-	}
+	list_for_each_entry(term, head, list)
+		if (config_term(attr, term) && fail)
+			return -EINVAL;
 
 	return 0;
 }
 
-static enum event_result
-parse_symbolic_event(const char **strp, struct perf_event_attr *attr)
+int parse_events_add_numeric(struct list_head *list, int *idx,
+			     unsigned long type, unsigned long config,
+			     struct list_head *head_config)
 {
-	const char *str = *strp;
-	unsigned int i;
-	int n;
-
-	for (i = 0; i < ARRAY_SIZE(event_symbols); i++) {
-		n = check_events(str, i);
-		if (n > 0) {
-			attr->type = event_symbols[i].type;
-			attr->config = event_symbols[i].config;
-			*strp = str + n;
-			return EVT_HANDLED;
-		}
-	}
-	return EVT_FAILED;
+	struct perf_event_attr attr;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.type = type;
+	attr.config = config;
+
+	if (head_config &&
+	    config_attr(&attr, head_config, 1))
+		return -EINVAL;
+
+	return add_event(list, idx, &attr,
+			 (char *) __event_name(type, config));
 }
 
-static enum event_result
-parse_raw_event(const char **strp, struct perf_event_attr *attr)
+int parse_events_add_pmu(struct list_head *list, int *idx,
+			 char *name, struct list_head *head_config)
 {
-	const char *str = *strp;
-	u64 config;
-	int n;
-
-	if (*str != 'r')
-		return EVT_FAILED;
-	n = hex2u64(str + 1, &config);
-	if (n > 0) {
-		const char *end = str + n + 1;
-		if (*end != '\0' && *end != ',' && *end != ':')
-			return EVT_FAILED;
-
-		*strp = end;
-		attr->type = PERF_TYPE_RAW;
-		attr->config = config;
-		return EVT_HANDLED;
-	}
-	return EVT_FAILED;
+	struct perf_event_attr attr;
+	struct perf_pmu *pmu;
+
+	pmu = perf_pmu__find(name);
+	if (!pmu)
+		return -EINVAL;
+
+	memset(&attr, 0, sizeof(attr));
+
+	/*
+	 * Configure hardcoded terms first, no need to check
+	 * return value when called with fail == 0 ;)
+	 */
+	config_attr(&attr, head_config, 0);
+
+	if (perf_pmu__config(pmu, &attr, head_config))
+		return -EINVAL;
+
+	return add_event(list, idx, &attr, (char *) "pmu");
 }
 
-static enum event_result
-parse_numeric_event(const char **strp, struct perf_event_attr *attr)
+void parse_events_update_lists(struct list_head *list_event,
+			       struct list_head *list_all)
 {
-	const char *str = *strp;
-	char *endp;
-	unsigned long type;
-	u64 config;
-
-	type = strtoul(str, &endp, 0);
-	if (endp > str && type < PERF_TYPE_MAX && *endp == ':') {
-		str = endp + 1;
-		config = strtoul(str, &endp, 0);
-		if (endp > str) {
-			attr->type = type;
-			attr->config = config;
-			*strp = endp;
-			return EVT_HANDLED;
-		}
-	}
-	return EVT_FAILED;
+	/*
+	 * Called for single event definition. Update the
+	 * 'all event' list, and reinit the 'signle event'
+	 * list, for next event definition.
+	 */
+	list_splice_tail(list_event, list_all);
+	INIT_LIST_HEAD(list_event);
 }
 
-static int
-parse_event_modifier(const char **strp, struct perf_event_attr *attr)
+int parse_events_modifier(struct list_head *list, char *str)
 {
-	const char *str = *strp;
+	struct perf_evsel *evsel;
 	int exclude = 0, exclude_GH = 0;
 	int eu = 0, ek = 0, eh = 0, eH = 0, eG = 0, precise = 0;
 
-	if (!*str)
+	if (str == NULL)
 		return 0;
 
-	if (*str == ',')
-		return 0;
-
-	if (*str++ != ':')
-		return -1;
-
 	while (*str) {
 		if (*str == 'u') {
 			if (!exclude)
@@ -775,111 +721,62 @@ parse_event_modifier(const char **strp, struct perf_event_attr *attr)
 
 		++str;
 	}
-	if (str < *strp + 2)
-		return -1;
 
-	*strp = str;
+	/*
+	 * precise ip:
+	 *
+	 *  0 - SAMPLE_IP can have arbitrary skid
+	 *  1 - SAMPLE_IP must have constant skid
+	 *  2 - SAMPLE_IP requested to have 0 skid
+	 *  3 - SAMPLE_IP must have 0 skid
+	 *
+	 *  See also PERF_RECORD_MISC_EXACT_IP
+	 */
+	if (precise > 3)
+		return -EINVAL;
 
-	attr->exclude_user   = eu;
-	attr->exclude_kernel = ek;
-	attr->exclude_hv     = eh;
-	attr->precise_ip     = precise;
-	attr->exclude_host   = eH;
-	attr->exclude_guest  = eG;
+	list_for_each_entry(evsel, list, node) {
+		evsel->attr.exclude_user   = eu;
+		evsel->attr.exclude_kernel = ek;
+		evsel->attr.exclude_hv     = eh;
+		evsel->attr.precise_ip     = precise;
+		evsel->attr.exclude_host   = eH;
+		evsel->attr.exclude_guest  = eG;
+	}
 
 	return 0;
 }
 
-/*
- * Each event can have multiple symbolic names.
- * Symbolic names are (almost) exactly matched.
- */
-static enum event_result
-parse_event_symbols(struct perf_evlist *evlist, const char **str,
-		    struct perf_event_attr *attr)
+int parse_events(struct perf_evlist *evlist, const char *str, int unset __used)
 {
-	enum event_result ret;
-
-	ret = parse_tracepoint_event(evlist, str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
-
-	ret = parse_raw_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
+	LIST_HEAD(list);
+	LIST_HEAD(list_tmp);
+	YY_BUFFER_STATE buffer;
+	int ret, idx = evlist->nr_entries;
 
-	ret = parse_numeric_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
+	buffer = parse_events__scan_string(str);
 
-	ret = parse_symbolic_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
+	ret = parse_events_parse(&list, &list_tmp, &idx);
 
-	ret = parse_generic_hw_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
+	parse_events__flush_buffer(buffer);
+	parse_events__delete_buffer(buffer);
 
-	ret = parse_breakpoint_event(str, attr);
-	if (ret != EVT_FAILED)
-		goto modifier;
-
-	fprintf(stderr, "invalid or unsupported event: '%s'\n", *str);
-	fprintf(stderr, "Run 'perf list' for a list of valid events\n");
-	return EVT_FAILED;
-
-modifier:
-	if (parse_event_modifier(str, attr) < 0) {
-		fprintf(stderr, "invalid event modifier: '%s'\n", *str);
-		fprintf(stderr, "Run 'perf list' for a list of valid events and modifiers\n");
-
-		return EVT_FAILED;
+	if (!ret) {
+		int entries = idx - evlist->nr_entries;
+		perf_evlist__splice_list_tail(evlist, &list, entries);
+		return 0;
 	}
 
+	/*
+	 * There are 2 users - builtin-record and builtin-test objects.
+	 * Both call perf_evlist__delete in case of error, so we dont
+	 * need to bother.
+	 */
+	fprintf(stderr, "invalid or unsupported event: '%s'\n", str);
+	fprintf(stderr, "Run 'perf list' for a list of valid events\n");
 	return ret;
 }
 
-int parse_events(struct perf_evlist *evlist , const char *str, int unset __used)
-{
-	struct perf_event_attr attr;
-	enum event_result ret;
-	const char *ostr;
-
-	for (;;) {
-		ostr = str;
-		memset(&attr, 0, sizeof(attr));
-		event_attr_init(&attr);
-		ret = parse_event_symbols(evlist, &str, &attr);
-		if (ret == EVT_FAILED)
-			return -1;
-
-		if (!(*str == 0 || *str == ',' || isspace(*str)))
-			return -1;
-
-		if (ret != EVT_HANDLED_ALL) {
-			struct perf_evsel *evsel;
-			evsel = perf_evsel__new(&attr, evlist->nr_entries);
-			if (evsel == NULL)
-				return -1;
-			perf_evlist__add(evlist, evsel);
-
-			evsel->name = calloc(str - ostr + 1, 1);
-			if (!evsel->name)
-				return -1;
-			strncpy(evsel->name, ostr, str - ostr);
-		}
-
-		if (*str == 0)
-			break;
-		if (*str == ',')
-			++str;
-		while (isspace(*str))
-			++str;
-	}
-
-	return 0;
-}
-
 int parse_events_option(const struct option *opt, const char *str,
 			int unset __used)
 {
@@ -1052,8 +949,6 @@ int print_hwcache_events(const char *event_glob)
 	return printed;
 }
 
-#define MAX_NAME_LEN 100
-
 /*
  * Print the help text for the event symbols:
  */
@@ -1102,8 +997,12 @@ void print_events(const char *event_glob)
 
 	printf("\n");
 	printf("  %-50s [%s]\n",
-		"rNNN (see 'perf list --help' on how to encode it)",
+	       "rNNN",
 	       event_type_descriptors[PERF_TYPE_RAW]);
+	printf("  %-50s [%s]\n",
+	       "cpu/t1=v1[,t2=v2,t3 ...]/modifier",
+	       event_type_descriptors[PERF_TYPE_RAW]);
+	printf("   (see 'perf list --help' on how to encode it)\n");
 	printf("\n");
 
 	printf("  %-50s [%s]\n",
@@ -1113,3 +1012,51 @@ void print_events(const char *event_glob)
 
 	print_tracepoint_events(NULL, NULL);
 }
+
+int parse_events__is_hardcoded_term(struct parse_events__term *term)
+{
+	return term->type <= PARSE_EVENTS__TERM_TYPE_HARDCODED_MAX;
+}
+
+int parse_events__new_term(struct parse_events__term **_term, int type,
+			   char *config, char *str, long num)
+{
+	struct parse_events__term *term;
+
+	term = zalloc(sizeof(*term));
+	if (!term)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&term->list);
+	term->type = type;
+	term->config = config;
+
+	switch (type) {
+	case PARSE_EVENTS__TERM_TYPE_CONFIG:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG1:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG2:
+	case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
+	case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE:
+	case PARSE_EVENTS__TERM_TYPE_NUM:
+		term->val.num = num;
+		break;
+	case PARSE_EVENTS__TERM_TYPE_STR:
+		term->val.str = str;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*_term = term;
+	return 0;
+}
+
+void parse_events__free_terms(struct list_head *terms)
+{
+	struct parse_events__term *term, *h;
+
+	list_for_each_entry_safe(term, h, terms, list)
+		free(term);
+
+	free(terms);
+}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 7e0cbe75d5f..ca069f89338 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -33,6 +33,55 @@ extern int parse_filter(const struct option *opt, const char *str, int unset);
 
 #define EVENTS_HELP_MAX (128*1024)
 
+enum {
+	PARSE_EVENTS__TERM_TYPE_CONFIG,
+	PARSE_EVENTS__TERM_TYPE_CONFIG1,
+	PARSE_EVENTS__TERM_TYPE_CONFIG2,
+	PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD,
+	PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE,
+	PARSE_EVENTS__TERM_TYPE_NUM,
+	PARSE_EVENTS__TERM_TYPE_STR,
+
+	PARSE_EVENTS__TERM_TYPE_HARDCODED_MAX =
+		PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE,
+};
+
+struct parse_events__term {
+	char *config;
+	union {
+		char *str;
+		long  num;
+	} val;
+	int type;
+
+	struct list_head list;
+};
+
+int parse_events__is_hardcoded_term(struct parse_events__term *term);
+int parse_events__new_term(struct parse_events__term **term, int type,
+			   char *config, char *str, long num);
+void parse_events__free_terms(struct list_head *terms);
+int parse_events_modifier(struct list_head *list __used, char *str __used);
+int parse_events_add_tracepoint(struct list_head *list, int *idx,
+				char *sys, char *event);
+int parse_events_add_raw(struct perf_evlist *evlist, unsigned long config,
+			 unsigned long config1, unsigned long config2,
+			 char *mod);
+int parse_events_add_numeric(struct list_head *list, int *idx,
+			     unsigned long type, unsigned long config,
+			     struct list_head *head_config);
+int parse_events_add_cache(struct list_head *list, int *idx,
+			   char *type, char *op_result1, char *op_result2);
+int parse_events_add_breakpoint(struct list_head *list, int *idx,
+				void *ptr, char *type);
+int parse_events_add_pmu(struct list_head *list, int *idx,
+			 char *pmu , struct list_head *head_config);
+void parse_events_update_lists(struct list_head *list_event,
+			       struct list_head *list_all);
+void parse_events_error(struct list_head *list_all,
+			struct list_head *list_event,
+			int *idx, char const *msg);
+
 void print_events(const char *event_glob);
 void print_events_type(u8 type);
 void print_tracepoint_events(const char *subsys_glob, const char *event_glob);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
new file mode 100644
index 00000000000..05d766e3ecb
--- /dev/null
+++ b/tools/perf/util/parse-events.l
@@ -0,0 +1,127 @@
+
+%option prefix="parse_events_"
+
+%{
+#include <errno.h>
+#include "../perf.h"
+#include "parse-events-bison.h"
+#include "parse-events.h"
+
+static int __value(char *str, int base, int token)
+{
+	long num;
+
+	errno = 0;
+	num = strtoul(str, NULL, base);
+	if (errno)
+		return PE_ERROR;
+
+	parse_events_lval.num = num;
+	return token;
+}
+
+static int value(int base)
+{
+	return __value(parse_events_text, base, PE_VALUE);
+}
+
+static int raw(void)
+{
+	return __value(parse_events_text + 1, 16, PE_RAW);
+}
+
+static int str(int token)
+{
+	parse_events_lval.str = strdup(parse_events_text);
+	return token;
+}
+
+static int sym(int type, int config)
+{
+	parse_events_lval.num = (type << 16) + config;
+	return PE_VALUE_SYM;
+}
+
+static int term(int type)
+{
+	parse_events_lval.num = type;
+	return PE_TERM;
+}
+
+%}
+
+num_dec		[0-9]+
+num_hex		0x[a-fA-F0-9]+
+num_raw_hex	[a-fA-F0-9]+
+name		[a-zA-Z_*?][a-zA-Z0-9_*?]*
+modifier_event	[ukhp]{1,5}
+modifier_bp	[rwx]
+
+%%
+cpu-cycles|cycles				{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); }
+stalled-cycles-frontend|idle-cycles-frontend	{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
+stalled-cycles-backend|idle-cycles-backend	{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
+instructions					{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS); }
+cache-references				{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_REFERENCES); }
+cache-misses					{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_MISSES); }
+branch-instructions|branches			{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
+branch-misses					{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_MISSES); }
+bus-cycles					{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BUS_CYCLES); }
+ref-cycles					{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_REF_CPU_CYCLES); }
+cpu-clock					{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK); }
+task-clock					{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_TASK_CLOCK); }
+page-faults|faults				{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS); }
+minor-faults					{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MIN); }
+major-faults					{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MAJ); }
+context-switches|cs				{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CONTEXT_SWITCHES); }
+cpu-migrations|migrations			{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); }
+alignment-faults				{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
+emulation-faults				{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
+
+L1-dcache|l1-d|l1d|L1-data		|
+L1-icache|l1-i|l1i|L1-instruction	|
+LLC|L2					|
+dTLB|d-tlb|Data-TLB			|
+iTLB|i-tlb|Instruction-TLB		|
+branch|branches|bpu|btb|bpc		|
+node					{ return str(PE_NAME_CACHE_TYPE); }
+
+load|loads|read				|
+store|stores|write			|
+prefetch|prefetches			|
+speculative-read|speculative-load	|
+refs|Reference|ops|access		|
+misses|miss				{ return str(PE_NAME_CACHE_OP_RESULT); }
+
+	/*
+	 * These are event config hardcoded term names to be specified
+	 * within xxx/.../ syntax. So far we dont clash with other names,
+	 * so we can put them here directly. In case the we have a conflict
+	 * in future, this needs to go into '//' condition block.
+	 */
+config			{ return term(PARSE_EVENTS__TERM_TYPE_CONFIG); }
+config1			{ return term(PARSE_EVENTS__TERM_TYPE_CONFIG1); }
+config2			{ return term(PARSE_EVENTS__TERM_TYPE_CONFIG2); }
+period			{ return term(PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); }
+branch_type		{ return term(PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); }
+
+mem:			{ return PE_PREFIX_MEM; }
+r{num_raw_hex}		{ return raw(); }
+{num_dec}		{ return value(10); }
+{num_hex}		{ return value(16); }
+
+{modifier_event}	{ return str(PE_MODIFIER_EVENT); }
+{modifier_bp}		{ return str(PE_MODIFIER_BP); }
+{name}			{ return str(PE_NAME); }
+"/"			{ return '/'; }
+-			{ return '-'; }
+,			{ return ','; }
+:			{ return ':'; }
+=			{ return '='; }
+
+%%
+
+int parse_events_wrap(void)
+{
+	return 1;
+}
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
new file mode 100644
index 00000000000..d9637da7333
--- /dev/null
+++ b/tools/perf/util/parse-events.y
@@ -0,0 +1,229 @@
+
+%name-prefix "parse_events_"
+%parse-param {struct list_head *list_all}
+%parse-param {struct list_head *list_event}
+%parse-param {int *idx}
+
+%{
+
+#define YYDEBUG 1
+
+#include <linux/compiler.h>
+#include <linux/list.h>
+#include "types.h"
+#include "util.h"
+#include "parse-events.h"
+
+extern int parse_events_lex (void);
+
+#define ABORT_ON(val) \
+do { \
+	if (val) \
+		YYABORT; \
+} while (0)
+
+%}
+
+%token PE_VALUE PE_VALUE_SYM PE_RAW PE_TERM
+%token PE_NAME
+%token PE_MODIFIER_EVENT PE_MODIFIER_BP
+%token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT
+%token PE_PREFIX_MEM PE_PREFIX_RAW
+%token PE_ERROR
+%type <num> PE_VALUE
+%type <num> PE_VALUE_SYM
+%type <num> PE_RAW
+%type <num> PE_TERM
+%type <str> PE_NAME
+%type <str> PE_NAME_CACHE_TYPE
+%type <str> PE_NAME_CACHE_OP_RESULT
+%type <str> PE_MODIFIER_EVENT
+%type <str> PE_MODIFIER_BP
+%type <head> event_config
+%type <term> event_term
+
+%union
+{
+	char *str;
+	unsigned long num;
+	struct list_head *head;
+	struct parse_events__term *term;
+}
+%%
+
+events:
+events ',' event | event
+
+event:
+event_def PE_MODIFIER_EVENT
+{
+	/*
+	 * Apply modifier on all events added by single event definition
+	 * (there could be more events added for multiple tracepoint
+	 * definitions via '*?'.
+	 */
+	ABORT_ON(parse_events_modifier(list_event, $2));
+	parse_events_update_lists(list_event, list_all);
+}
+|
+event_def
+{
+	parse_events_update_lists(list_event, list_all);
+}
+
+event_def: event_pmu |
+	   event_legacy_symbol |
+	   event_legacy_cache sep_dc |
+	   event_legacy_mem |
+	   event_legacy_tracepoint sep_dc |
+	   event_legacy_numeric sep_dc |
+	   event_legacy_raw sep_dc
+
+event_pmu:
+PE_NAME '/' event_config '/'
+{
+	ABORT_ON(parse_events_add_pmu(list_event, idx, $1, $3));
+	parse_events__free_terms($3);
+}
+
+event_legacy_symbol:
+PE_VALUE_SYM '/' event_config '/'
+{
+	int type = $1 >> 16;
+	int config = $1 & 255;
+
+	ABORT_ON(parse_events_add_numeric(list_event, idx, type, config, $3));
+	parse_events__free_terms($3);
+}
+|
+PE_VALUE_SYM sep_slash_dc
+{
+	int type = $1 >> 16;
+	int config = $1 & 255;
+
+	ABORT_ON(parse_events_add_numeric(list_event, idx, type, config, NULL));
+}
+
+event_legacy_cache:
+PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT
+{
+	ABORT_ON(parse_events_add_cache(list_event, idx, $1, $3, $5));
+}
+|
+PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT
+{
+	ABORT_ON(parse_events_add_cache(list_event, idx, $1, $3, NULL));
+}
+|
+PE_NAME_CACHE_TYPE
+{
+	ABORT_ON(parse_events_add_cache(list_event, idx, $1, NULL, NULL));
+}
+
+event_legacy_mem:
+PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
+{
+	ABORT_ON(parse_events_add_breakpoint(list_event, idx, (void *) $2, $4));
+}
+|
+PE_PREFIX_MEM PE_VALUE sep_dc
+{
+	ABORT_ON(parse_events_add_breakpoint(list_event, idx, (void *) $2, NULL));
+}
+
+event_legacy_tracepoint:
+PE_NAME ':' PE_NAME
+{
+	ABORT_ON(parse_events_add_tracepoint(list_event, idx, $1, $3));
+}
+
+event_legacy_numeric:
+PE_VALUE ':' PE_VALUE
+{
+	ABORT_ON(parse_events_add_numeric(list_event, idx, $1, $3, NULL));
+}
+
+event_legacy_raw:
+PE_RAW
+{
+	ABORT_ON(parse_events_add_numeric(list_event, idx, PERF_TYPE_RAW, $1, NULL));
+}
+
+event_config:
+event_config ',' event_term
+{
+	struct list_head *head = $1;
+	struct parse_events__term *term = $3;
+
+	ABORT_ON(!head);
+	list_add_tail(&term->list, head);
+	$$ = $1;
+}
+|
+event_term
+{
+	struct list_head *head = malloc(sizeof(*head));
+	struct parse_events__term *term = $1;
+
+	ABORT_ON(!head);
+	INIT_LIST_HEAD(head);
+	list_add_tail(&term->list, head);
+	$$ = head;
+}
+
+event_term:
+PE_NAME '=' PE_NAME
+{
+	struct parse_events__term *term;
+
+	ABORT_ON(parse_events__new_term(&term, PARSE_EVENTS__TERM_TYPE_STR,
+		 $1, $3, 0));
+	$$ = term;
+}
+|
+PE_NAME '=' PE_VALUE
+{
+	struct parse_events__term *term;
+
+	ABORT_ON(parse_events__new_term(&term, PARSE_EVENTS__TERM_TYPE_NUM,
+		 $1, NULL, $3));
+	$$ = term;
+}
+|
+PE_NAME
+{
+	struct parse_events__term *term;
+
+	ABORT_ON(parse_events__new_term(&term, PARSE_EVENTS__TERM_TYPE_NUM,
+		 $1, NULL, 1));
+	$$ = term;
+}
+|
+PE_TERM '=' PE_VALUE
+{
+	struct parse_events__term *term;
+
+	ABORT_ON(parse_events__new_term(&term, $1, NULL, NULL, $3));
+	$$ = term;
+}
+|
+PE_TERM
+{
+	struct parse_events__term *term;
+
+	ABORT_ON(parse_events__new_term(&term, $1, NULL, NULL, 1));
+	$$ = term;
+}
+
+sep_dc: ':' |
+
+sep_slash_dc: '/' | ':' |
+
+%%
+
+void parse_events_error(struct list_head *list_all __used,
+			struct list_head *list_event __used,
+			int *idx __used,
+			char const *msg __used)
+{
+}
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
new file mode 100644
index 00000000000..cb08a118e81
--- /dev/null
+++ b/tools/perf/util/pmu.c
@@ -0,0 +1,469 @@
+
+#include <linux/list.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <dirent.h>
+#include "sysfs.h"
+#include "util.h"
+#include "pmu.h"
+#include "parse-events.h"
+
+int perf_pmu_parse(struct list_head *list, char *name);
+extern FILE *perf_pmu_in;
+
+static LIST_HEAD(pmus);
+
+/*
+ * Parse & process all the sysfs attributes located under
+ * the directory specified in 'dir' parameter.
+ */
+static int pmu_format_parse(char *dir, struct list_head *head)
+{
+	struct dirent *evt_ent;
+	DIR *format_dir;
+	int ret = 0;
+
+	format_dir = opendir(dir);
+	if (!format_dir)
+		return -EINVAL;
+
+	while (!ret && (evt_ent = readdir(format_dir))) {
+		char path[PATH_MAX];
+		char *name = evt_ent->d_name;
+		FILE *file;
+
+		if (!strcmp(name, ".") || !strcmp(name, ".."))
+			continue;
+
+		snprintf(path, PATH_MAX, "%s/%s", dir, name);
+
+		ret = -EINVAL;
+		file = fopen(path, "r");
+		if (!file)
+			break;
+
+		perf_pmu_in = file;
+		ret = perf_pmu_parse(head, name);
+		fclose(file);
+	}
+
+	closedir(format_dir);
+	return ret;
+}
+
+/*
+ * Reading/parsing the default pmu format definition, which should be
+ * located at:
+ * /sys/bus/event_source/devices/<dev>/format as sysfs group attributes.
+ */
+static int pmu_format(char *name, struct list_head *format)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	const char *sysfs;
+
+	sysfs = sysfs_find_mountpoint();
+	if (!sysfs)
+		return -1;
+
+	snprintf(path, PATH_MAX,
+		 "%s/bus/event_source/devices/%s/format", sysfs, name);
+
+	if (stat(path, &st) < 0)
+		return -1;
+
+	if (pmu_format_parse(path, format))
+		return -1;
+
+	return 0;
+}
+
+/*
+ * Reading/parsing the default pmu type value, which should be
+ * located at:
+ * /sys/bus/event_source/devices/<dev>/type as sysfs attribute.
+ */
+static int pmu_type(char *name, __u32 *type)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	const char *sysfs;
+	FILE *file;
+	int ret = 0;
+
+	sysfs = sysfs_find_mountpoint();
+	if (!sysfs)
+		return -1;
+
+	snprintf(path, PATH_MAX,
+		 "%s/bus/event_source/devices/%s/type", sysfs, name);
+
+	if (stat(path, &st) < 0)
+		return -1;
+
+	file = fopen(path, "r");
+	if (!file)
+		return -EINVAL;
+
+	if (1 != fscanf(file, "%u", type))
+		ret = -1;
+
+	fclose(file);
+	return ret;
+}
+
+static struct perf_pmu *pmu_lookup(char *name)
+{
+	struct perf_pmu *pmu;
+	LIST_HEAD(format);
+	__u32 type;
+
+	/*
+	 * The pmu data we store & need consists of the pmu
+	 * type value and format definitions. Load both right
+	 * now.
+	 */
+	if (pmu_format(name, &format))
+		return NULL;
+
+	if (pmu_type(name, &type))
+		return NULL;
+
+	pmu = zalloc(sizeof(*pmu));
+	if (!pmu)
+		return NULL;
+
+	INIT_LIST_HEAD(&pmu->format);
+	list_splice(&format, &pmu->format);
+	pmu->name = strdup(name);
+	pmu->type = type;
+	return pmu;
+}
+
+static struct perf_pmu *pmu_find(char *name)
+{
+	struct perf_pmu *pmu;
+
+	list_for_each_entry(pmu, &pmus, list)
+		if (!strcmp(pmu->name, name))
+			return pmu;
+
+	return NULL;
+}
+
+struct perf_pmu *perf_pmu__find(char *name)
+{
+	struct perf_pmu *pmu;
+
+	/*
+	 * Once PMU is loaded it stays in the list,
+	 * so we keep us from multiple reading/parsing
+	 * the pmu format definitions.
+	 */
+	pmu = pmu_find(name);
+	if (pmu)
+		return pmu;
+
+	return pmu_lookup(name);
+}
+
+static struct perf_pmu__format*
+pmu_find_format(struct list_head *formats, char *name)
+{
+	struct perf_pmu__format *format;
+
+	list_for_each_entry(format, formats, list)
+		if (!strcmp(format->name, name))
+			return format;
+
+	return NULL;
+}
+
+/*
+ * Returns value based on the format definition (format parameter)
+ * and unformated value (value parameter).
+ *
+ * TODO maybe optimize a little ;)
+ */
+static __u64 pmu_format_value(unsigned long *format, __u64 value)
+{
+	unsigned long fbit, vbit;
+	__u64 v = 0;
+
+	for (fbit = 0, vbit = 0; fbit < PERF_PMU_FORMAT_BITS; fbit++) {
+
+		if (!test_bit(fbit, format))
+			continue;
+
+		if (!(value & (1llu << vbit++)))
+			continue;
+
+		v |= (1llu << fbit);
+	}
+
+	return v;
+}
+
+/*
+ * Setup one of config[12] attr members based on the
+ * user input data - temr parameter.
+ */
+static int pmu_config_term(struct list_head *formats,
+			   struct perf_event_attr *attr,
+			   struct parse_events__term *term)
+{
+	struct perf_pmu__format *format;
+	__u64 *vp;
+
+	/*
+	 * Support only for hardcoded and numnerial terms.
+	 * Hardcoded terms should be already in, so nothing
+	 * to be done for them.
+	 */
+	if (parse_events__is_hardcoded_term(term))
+		return 0;
+
+	if (term->type != PARSE_EVENTS__TERM_TYPE_NUM)
+		return -EINVAL;
+
+	format = pmu_find_format(formats, term->config);
+	if (!format)
+		return -EINVAL;
+
+	switch (format->value) {
+	case PERF_PMU_FORMAT_VALUE_CONFIG:
+		vp = &attr->config;
+		break;
+	case PERF_PMU_FORMAT_VALUE_CONFIG1:
+		vp = &attr->config1;
+		break;
+	case PERF_PMU_FORMAT_VALUE_CONFIG2:
+		vp = &attr->config2;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*vp |= pmu_format_value(format->bits, term->val.num);
+	return 0;
+}
+
+static int pmu_config(struct list_head *formats, struct perf_event_attr *attr,
+		      struct list_head *head_terms)
+{
+	struct parse_events__term *term, *h;
+
+	list_for_each_entry_safe(term, h, head_terms, list)
+		if (pmu_config_term(formats, attr, term))
+			return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * Configures event's 'attr' parameter based on the:
+ * 1) users input - specified in terms parameter
+ * 2) pmu format definitions - specified by pmu parameter
+ */
+int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
+		     struct list_head *head_terms)
+{
+	attr->type = pmu->type;
+	return pmu_config(&pmu->format, attr, head_terms);
+}
+
+int perf_pmu__new_format(struct list_head *list, char *name,
+			 int config, unsigned long *bits)
+{
+	struct perf_pmu__format *format;
+
+	format = zalloc(sizeof(*format));
+	if (!format)
+		return -ENOMEM;
+
+	format->name = strdup(name);
+	format->value = config;
+	memcpy(format->bits, bits, sizeof(format->bits));
+
+	list_add_tail(&format->list, list);
+	return 0;
+}
+
+void perf_pmu__set_format(unsigned long *bits, long from, long to)
+{
+	long b;
+
+	if (!to)
+		to = from;
+
+	memset(bits, 0, BITS_TO_LONGS(PERF_PMU_FORMAT_BITS));
+	for (b = from; b <= to; b++)
+		set_bit(b, bits);
+}
+
+/* Simulated format definitions. */
+static struct test_format {
+	const char *name;
+	const char *value;
+} test_formats[] = {
+	{ "krava01", "config:0-1,62-63\n", },
+	{ "krava02", "config:10-17\n", },
+	{ "krava03", "config:5\n", },
+	{ "krava11", "config1:0,2,4,6,8,20-28\n", },
+	{ "krava12", "config1:63\n", },
+	{ "krava13", "config1:45-47\n", },
+	{ "krava21", "config2:0-3,10-13,20-23,30-33,40-43,50-53,60-63\n", },
+	{ "krava22", "config2:8,18,48,58\n", },
+	{ "krava23", "config2:28-29,38\n", },
+};
+
+#define TEST_FORMATS_CNT (sizeof(test_formats) / sizeof(struct test_format))
+
+/* Simulated users input. */
+static struct parse_events__term test_terms[] = {
+	{
+		.config  = (char *) "krava01",
+		.val.num = 15,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava02",
+		.val.num = 170,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava03",
+		.val.num = 1,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava11",
+		.val.num = 27,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava12",
+		.val.num = 1,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava13",
+		.val.num = 2,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava21",
+		.val.num = 119,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava22",
+		.val.num = 11,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+	{
+		.config  = (char *) "krava23",
+		.val.num = 2,
+		.type    = PARSE_EVENTS__TERM_TYPE_NUM,
+	},
+};
+#define TERMS_CNT (sizeof(test_terms) / sizeof(struct parse_events__term))
+
+/*
+ * Prepare format directory data, exported by kernel
+ * at /sys/bus/event_source/devices/<dev>/format.
+ */
+static char *test_format_dir_get(void)
+{
+	static char dir[PATH_MAX];
+	unsigned int i;
+
+	snprintf(dir, PATH_MAX, "/tmp/perf-pmu-test-format-XXXXXX");
+	if (!mkdtemp(dir))
+		return NULL;
+
+	for (i = 0; i < TEST_FORMATS_CNT; i++) {
+		static char name[PATH_MAX];
+		struct test_format *format = &test_formats[i];
+		FILE *file;
+
+		snprintf(name, PATH_MAX, "%s/%s", dir, format->name);
+
+		file = fopen(name, "w");
+		if (!file)
+			return NULL;
+
+		if (1 != fwrite(format->value, strlen(format->value), 1, file))
+			break;
+
+		fclose(file);
+	}
+
+	return dir;
+}
+
+/* Cleanup format directory. */
+static int test_format_dir_put(char *dir)
+{
+	char buf[PATH_MAX];
+	snprintf(buf, PATH_MAX, "rm -f %s/*\n", dir);
+	if (system(buf))
+		return -1;
+
+	snprintf(buf, PATH_MAX, "rmdir %s\n", dir);
+	return system(buf);
+}
+
+static struct list_head *test_terms_list(void)
+{
+	static LIST_HEAD(terms);
+	unsigned int i;
+
+	for (i = 0; i < TERMS_CNT; i++)
+		list_add_tail(&test_terms[i].list, &terms);
+
+	return &terms;
+}
+
+#undef TERMS_CNT
+
+int perf_pmu__test(void)
+{
+	char *format = test_format_dir_get();
+	LIST_HEAD(formats);
+	struct list_head *terms = test_terms_list();
+	int ret;
+
+	if (!format)
+		return -EINVAL;
+
+	do {
+		struct perf_event_attr attr;
+
+		memset(&attr, 0, sizeof(attr));
+
+		ret = pmu_format_parse(format, &formats);
+		if (ret)
+			break;
+
+		ret = pmu_config(&formats, &attr, terms);
+		if (ret)
+			break;
+
+		ret = -EINVAL;
+
+		if (attr.config  != 0xc00000000002a823)
+			break;
+		if (attr.config1 != 0x8000400000000145)
+			break;
+		if (attr.config2 != 0x0400000020041d07)
+			break;
+
+		ret = 0;
+	} while (0);
+
+	test_format_dir_put(format);
+	return ret;
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
new file mode 100644
index 00000000000..68c0db965e1
--- /dev/null
+++ b/tools/perf/util/pmu.h
@@ -0,0 +1,41 @@
+#ifndef __PMU_H
+#define __PMU_H
+
+#include <linux/bitops.h>
+#include "../../../include/linux/perf_event.h"
+
+enum {
+	PERF_PMU_FORMAT_VALUE_CONFIG,
+	PERF_PMU_FORMAT_VALUE_CONFIG1,
+	PERF_PMU_FORMAT_VALUE_CONFIG2,
+};
+
+#define PERF_PMU_FORMAT_BITS 64
+
+struct perf_pmu__format {
+	char *name;
+	int value;
+	DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS);
+	struct list_head list;
+};
+
+struct perf_pmu {
+	char *name;
+	__u32 type;
+	struct list_head format;
+	struct list_head list;
+};
+
+struct perf_pmu *perf_pmu__find(char *name);
+int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
+		     struct list_head *head_terms);
+
+int perf_pmu_wrap(void);
+void perf_pmu_error(struct list_head *list, char *name, char const *msg);
+
+int perf_pmu__new_format(struct list_head *list, char *name,
+			 int config, unsigned long *bits);
+void perf_pmu__set_format(unsigned long *bits, long from, long to);
+
+int perf_pmu__test(void);
+#endif /* __PMU_H */
diff --git a/tools/perf/util/pmu.l b/tools/perf/util/pmu.l
new file mode 100644
index 00000000000..a15d9fbd7c0
--- /dev/null
+++ b/tools/perf/util/pmu.l
@@ -0,0 +1,43 @@
+%option prefix="perf_pmu_"
+
+%{
+#include <stdlib.h>
+#include <linux/bitops.h>
+#include "pmu.h"
+#include "pmu-bison.h"
+
+static int value(int base)
+{
+	long num;
+
+	errno = 0;
+	num = strtoul(perf_pmu_text, NULL, base);
+	if (errno)
+		return PP_ERROR;
+
+	perf_pmu_lval.num = num;
+	return PP_VALUE;
+}
+
+%}
+
+num_dec         [0-9]+
+
+%%
+
+{num_dec}	{ return value(10); }
+config		{ return PP_CONFIG; }
+config1		{ return PP_CONFIG1; }
+config2		{ return PP_CONFIG2; }
+-		{ return '-'; }
+:		{ return ':'; }
+,		{ return ','; }
+.		{ ; }
+\n		{ ; }
+
+%%
+
+int perf_pmu_wrap(void)
+{
+	return 1;
+}
diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y
new file mode 100644
index 00000000000..20ea77e9316
--- /dev/null
+++ b/tools/perf/util/pmu.y
@@ -0,0 +1,93 @@
+
+%name-prefix "perf_pmu_"
+%parse-param {struct list_head *format}
+%parse-param {char *name}
+
+%{
+
+#include <linux/compiler.h>
+#include <linux/list.h>
+#include <linux/bitmap.h>
+#include <string.h>
+#include "pmu.h"
+
+extern int perf_pmu_lex (void);
+
+#define ABORT_ON(val) \
+do { \
+        if (val) \
+                YYABORT; \
+} while (0)
+
+%}
+
+%token PP_CONFIG PP_CONFIG1 PP_CONFIG2
+%token PP_VALUE PP_ERROR
+%type <num> PP_VALUE
+%type <bits> bit_term
+%type <bits> bits
+
+%union
+{
+	unsigned long num;
+	DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS);
+}
+
+%%
+
+format:
+format format_term
+|
+format_term
+
+format_term:
+PP_CONFIG ':' bits
+{
+	ABORT_ON(perf_pmu__new_format(format, name,
+				      PERF_PMU_FORMAT_VALUE_CONFIG,
+				      $3));
+}
+|
+PP_CONFIG1 ':' bits
+{
+	ABORT_ON(perf_pmu__new_format(format, name,
+				      PERF_PMU_FORMAT_VALUE_CONFIG1,
+				      $3));
+}
+|
+PP_CONFIG2 ':' bits
+{
+	ABORT_ON(perf_pmu__new_format(format, name,
+				      PERF_PMU_FORMAT_VALUE_CONFIG2,
+				      $3));
+}
+
+bits:
+bits ',' bit_term
+{
+	bitmap_or($$, $1, $3, 64);
+}
+|
+bit_term
+{
+	memcpy($$, $1, sizeof($1));
+}
+
+bit_term:
+PP_VALUE '-' PP_VALUE
+{
+	perf_pmu__set_format($$, $1, $3);
+}
+|
+PP_VALUE
+{
+	perf_pmu__set_format($$, $1, 0);
+}
+
+%%
+
+void perf_pmu_error(struct list_head *list __used,
+		    char *name __used,
+		    char const *msg __used)
+{
+}
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 2cc162d3b78..d448984ed78 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -972,10 +972,12 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 	struct dwarf_callback_param *param = data;
 	struct probe_finder *pf = param->data;
 	struct perf_probe_point *pp = &pf->pev->point;
+	Dwarf_Attribute attr;
 
 	/* Check tag and diename */
 	if (dwarf_tag(sp_die) != DW_TAG_subprogram ||
-	    !die_compare_name(sp_die, pp->function))
+	    !die_compare_name(sp_die, pp->function) ||
+	    dwarf_attr(sp_die, DW_AT_declaration, &attr))
 		return DWARF_CB_OK;
 
 	/* Check declared file */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 002ebbf59f4..9412e3b05f6 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -140,6 +140,7 @@ struct perf_session *perf_session__new(const char *filename, int mode,
 	INIT_LIST_HEAD(&self->ordered_samples.sample_cache);
 	INIT_LIST_HEAD(&self->ordered_samples.to_free);
 	machine__init(&self->host_machine, "", HOST_KERNEL_ID);
+	hists__init(&self->hists);
 
 	if (mode == O_RDONLY) {
 		if (perf_session__open(self, force) < 0)
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 5dd83c3e2c0..c0a028c3eba 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1,6 +1,5 @@
 #include <dirent.h>
 #include <errno.h>
-#include <libgen.h>
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
@@ -51,6 +50,8 @@ struct symbol_conf symbol_conf = {
 
 int dso__name_len(const struct dso *dso)
 {
+	if (!dso)
+		return strlen("[unknown]");
 	if (verbose)
 		return dso->long_name_len;
 
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index a4088ced1e6..dfd1bd8371a 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -722,7 +722,7 @@ static char *event_read_name(void)
 static int event_read_id(void)
 {
 	char *token;
-	int id;
+	int id = -1;
 
 	if (read_expected_item(EVENT_ITEM, "ID") < 0)
 		return -1;
@@ -731,15 +731,13 @@ static int event_read_id(void)
 		return -1;
 
 	if (read_expect_type(EVENT_ITEM, &token) < 0)
-		goto fail;
+		goto free;
 
 	id = strtoul(token, NULL, 0);
-	free_token(token);
-	return id;
 
- fail:
+ free:
 	free_token(token);
-	return -1;
+	return id;
 }
 
 static int field_is_string(struct format_field *field)
diff --git a/tools/perf/util/ui/browser.h b/tools/perf/util/ui/browser.h
index 84d761b730c..6ee82f60fea 100644
--- a/tools/perf/util/ui/browser.h
+++ b/tools/perf/util/ui/browser.h
@@ -49,6 +49,8 @@ int ui_browser__warning(struct ui_browser *browser, int timeout,
 			const char *format, ...);
 int ui_browser__help_window(struct ui_browser *browser, const char *text);
 bool ui_browser__dialog_yesno(struct ui_browser *browser, const char *text);
+int ui_browser__input_window(const char *title, const char *text, char *input,
+			     const char *exit_msg, int delay_sec);
 
 void ui_browser__argv_seek(struct ui_browser *browser, off_t offset, int whence);
 unsigned int ui_browser__argv_refresh(struct ui_browser *browser);
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index fa530fcc764..d7a1c4afe28 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -879,6 +879,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	char *options[16];
 	int nr_options = 0;
 	int key = -1;
+	char buf[64];
 
 	if (browser == NULL)
 		return -1;
@@ -933,6 +934,16 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			goto zoom_dso;
 		case 't':
 			goto zoom_thread;
+		case 's':
+			if (ui_browser__input_window("Symbol to show",
+					"Please enter the name of symbol you want to see",
+					buf, "ENTER: OK, ESC: Cancel",
+					delay_secs * 2) == K_ENTER) {
+				self->symbol_filter_str = *buf ? buf : NULL;
+				hists__filter_by_symbol(self);
+				hist_browser__reset(browser);
+			}
+			continue;
 		case K_F1:
 		case 'h':
 		case '?':
@@ -950,7 +961,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 					"C             Collapse all callchains\n"
 					"E             Expand all callchains\n"
 					"d             Zoom into current DSO\n"
-					"t             Zoom into current Thread");
+					"t             Zoom into current Thread\n"
+					"s             Filter symbol by name");
 			continue;
 		case K_ENTER:
 		case K_RIGHT:
diff --git a/tools/perf/util/ui/keysyms.h b/tools/perf/util/ui/keysyms.h
index 3458b198576..809eca5707f 100644
--- a/tools/perf/util/ui/keysyms.h
+++ b/tools/perf/util/ui/keysyms.h
@@ -16,6 +16,8 @@
 #define K_TAB	'\t'
 #define K_UNTAB	SL_KEY_UNTAB
 #define K_UP	SL_KEY_UP
+#define K_BKSPC 0x7f
+#define K_DEL	SL_KEY_DELETE
 
 /* Not really keys */
 #define K_TIMER	 -1
diff --git a/tools/perf/util/ui/util.c b/tools/perf/util/ui/util.c
index 45daa7c41da..ad4374a16bb 100644
--- a/tools/perf/util/ui/util.c
+++ b/tools/perf/util/ui/util.c
@@ -69,6 +69,88 @@ int ui__popup_menu(int argc, char * const argv[])
 	return popup_menu__run(&menu);
 }
 
+int ui_browser__input_window(const char *title, const char *text, char *input,
+			     const char *exit_msg, int delay_secs)
+{
+	int x, y, len, key;
+	int max_len = 60, nr_lines = 0;
+	static char buf[50];
+	const char *t;
+
+	t = text;
+	while (1) {
+		const char *sep = strchr(t, '\n');
+
+		if (sep == NULL)
+			sep = strchr(t, '\0');
+		len = sep - t;
+		if (max_len < len)
+			max_len = len;
+		++nr_lines;
+		if (*sep == '\0')
+			break;
+		t = sep + 1;
+	}
+
+	max_len += 2;
+	nr_lines += 8;
+	y = SLtt_Screen_Rows / 2 - nr_lines / 2;
+	x = SLtt_Screen_Cols / 2 - max_len / 2;
+
+	SLsmg_set_color(0);
+	SLsmg_draw_box(y, x++, nr_lines, max_len);
+	if (title) {
+		SLsmg_gotorc(y, x + 1);
+		SLsmg_write_string((char *)title);
+	}
+	SLsmg_gotorc(++y, x);
+	nr_lines -= 7;
+	max_len -= 2;
+	SLsmg_write_wrapped_string((unsigned char *)text, y, x,
+				   nr_lines, max_len, 1);
+	y += nr_lines;
+	len = 5;
+	while (len--) {
+		SLsmg_gotorc(y + len - 1, x);
+		SLsmg_write_nstring((char *)" ", max_len);
+	}
+	SLsmg_draw_box(y++, x + 1, 3, max_len - 2);
+
+	SLsmg_gotorc(y + 3, x);
+	SLsmg_write_nstring((char *)exit_msg, max_len);
+	SLsmg_refresh();
+
+	x += 2;
+	len = 0;
+	key = ui__getch(delay_secs);
+	while (key != K_TIMER && key != K_ENTER && key != K_ESC) {
+		if (key == K_BKSPC) {
+			if (len == 0)
+				goto next_key;
+			SLsmg_gotorc(y, x + --len);
+			SLsmg_write_char(' ');
+		} else {
+			buf[len] = key;
+			SLsmg_gotorc(y, x + len++);
+			SLsmg_write_char(key);
+		}
+		SLsmg_refresh();
+
+		/* XXX more graceful overflow handling needed */
+		if (len == sizeof(buf) - 1) {
+			ui_helpline__push("maximum size of symbol name reached!");
+			key = K_ENTER;
+			break;
+		}
+next_key:
+		key = ui__getch(delay_secs);
+	}
+
+	buf[len] = '\0';
+	strncpy(input, buf, len+1);
+	return key;
+}
+
 int ui__question_window(const char *title, const char *text,
 			const char *exit_msg, int delay_secs)
 {
diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile
index e8a03aceceb..a93e06cfcc2 100644
--- a/tools/power/cpupower/Makefile
+++ b/tools/power/cpupower/Makefile
@@ -19,6 +19,16 @@
 # along with this program; if not, write to the Free Software
 # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
 #
+OUTPUT=./
+ifeq ("$(origin O)", "command line")
+	OUTPUT := $(O)/
+endif
+
+ifneq ($(OUTPUT),)
+# check that the output directory actually exists
+OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
+$(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
+endif
 
 # --- CONFIGURATION BEGIN ---
 
@@ -87,6 +97,7 @@ AR = $(CROSS)ar
 STRIP = $(CROSS)strip
 RANLIB = $(CROSS)ranlib
 HOSTCC = gcc
+MKDIR = mkdir
 
 
 # Now we set up the build system
@@ -95,7 +106,7 @@ HOSTCC = gcc
 # set up PWD so that older versions of make will work with our build.
 PWD = $(shell pwd)
 
-GMO_FILES = ${shell for HLANG in ${LANGUAGES}; do echo po/$$HLANG.gmo; done;}
+GMO_FILES = ${shell for HLANG in ${LANGUAGES}; do echo $(OUTPUT)po/$$HLANG.gmo; done;}
 
 export CROSS CC AR STRIP RANLIB CFLAGS LDFLAGS LIB_OBJS
 
@@ -122,15 +133,18 @@ UTIL_OBJS =  utils/helpers/amd.o utils/helpers/topology.o utils/helpers/msr.o \
 	utils/cpupower.o utils/cpufreq-info.o utils/cpufreq-set.o \
 	utils/cpupower-set.o utils/cpupower-info.o utils/cpuidle-info.o
 
+UTIL_SRC := $(UTIL_OBJS:.o=.c)
+
+UTIL_OBJS := $(addprefix $(OUTPUT),$(UTIL_OBJS))
+
 UTIL_HEADERS = utils/helpers/helpers.h utils/idle_monitor/cpupower-monitor.h \
 	utils/helpers/bitmask.h \
 	utils/idle_monitor/idle_monitors.h utils/idle_monitor/idle_monitors.def
 
-UTIL_SRC := $(UTIL_OBJS:.o=.c)
-
 LIB_HEADERS = 	lib/cpufreq.h lib/sysfs.h
 LIB_SRC = 	lib/cpufreq.c lib/sysfs.c
 LIB_OBJS = 	lib/cpufreq.o lib/sysfs.o
+LIB_OBJS :=	$(addprefix $(OUTPUT),$(LIB_OBJS))
 
 CFLAGS +=	-pipe
 
@@ -168,83 +182,90 @@ endif
 
 # the actual make rules
 
-all: libcpupower cpupower $(COMPILE_NLS) $(COMPILE_BENCH)
+all: libcpupower $(OUTPUT)cpupower $(COMPILE_NLS) $(COMPILE_BENCH)
 
-lib/%.o: $(LIB_SRC) $(LIB_HEADERS)
+$(OUTPUT)lib/%.o: $(LIB_SRC) $(LIB_HEADERS)
 	$(ECHO) "  CC      " $@
 	$(QUIET) $(CC) $(CFLAGS) -fPIC -o $@ -c lib/$*.c
 
-libcpupower.so.$(LIB_MAJ): $(LIB_OBJS)
+$(OUTPUT)libcpupower.so.$(LIB_MAJ): $(LIB_OBJS)
 	$(ECHO) "  LD      " $@
 	$(QUIET) $(CC) -shared $(CFLAGS) $(LDFLAGS) -o $@ \
 		-Wl,-soname,libcpupower.so.$(LIB_MIN) $(LIB_OBJS)
-	@ln -sf $@ libcpupower.so
-	@ln -sf $@ libcpupower.so.$(LIB_MIN)
+	@ln -sf $(@F) $(OUTPUT)libcpupower.so
+	@ln -sf $(@F) $(OUTPUT)libcpupower.so.$(LIB_MIN)
 
-libcpupower: libcpupower.so.$(LIB_MAJ)
+libcpupower: $(OUTPUT)libcpupower.so.$(LIB_MAJ)
 
 # Let all .o files depend on its .c file and all headers
 # Might be worth to put this into utils/Makefile at some point of time
 $(UTIL_OBJS): $(UTIL_HEADERS)
 
-.c.o:
+$(OUTPUT)%.o: %.c
 	$(ECHO) "  CC      " $@
 	$(QUIET) $(CC) $(CFLAGS) -I./lib -I ./utils -o $@ -c $*.c
 
-cpupower: $(UTIL_OBJS) libcpupower.so.$(LIB_MAJ)
+$(OUTPUT)cpupower: $(UTIL_OBJS) $(OUTPUT)libcpupower.so.$(LIB_MAJ)
 	$(ECHO) "  CC      " $@
-	$(QUIET) $(CC) $(CFLAGS) $(LDFLAGS) -lcpupower -lrt -lpci -L. -o $@ $(UTIL_OBJS)
+	$(QUIET) $(CC) $(CFLAGS) $(LDFLAGS) $(UTIL_OBJS) -lcpupower -lrt -lpci -L$(OUTPUT) -o $@
 	$(QUIET) $(STRIPCMD) $@
 
-po/$(PACKAGE).pot: $(UTIL_SRC)
+$(OUTPUT)po/$(PACKAGE).pot: $(UTIL_SRC)
 	$(ECHO) "  GETTEXT " $@
 	$(QUIET) xgettext --default-domain=$(PACKAGE) --add-comments \
-		--keyword=_ --keyword=N_ $(UTIL_SRC) && \
-	test -f $(PACKAGE).po && \
-	mv -f $(PACKAGE).po po/$(PACKAGE).pot
+		--keyword=_ --keyword=N_ $(UTIL_SRC) -p $(@D) -o $(@F)
 
-po/%.gmo: po/%.po
+$(OUTPUT)po/%.gmo: po/%.po
 	$(ECHO) "  MSGFMT  " $@
 	$(QUIET) msgfmt -o $@ po/$*.po
 
 create-gmo: ${GMO_FILES}
 
-update-po: po/$(PACKAGE).pot
+update-po: $(OUTPUT)po/$(PACKAGE).pot
 	$(ECHO) "  MSGMRG  " $@
 	$(QUIET) @for HLANG in $(LANGUAGES); do \
 		echo -n "Updating $$HLANG "; \
-		if msgmerge po/$$HLANG.po po/$(PACKAGE).pot -o \
-		   po/$$HLANG.new.po; then \
-			mv -f po/$$HLANG.new.po po/$$HLANG.po; \
+		if msgmerge po/$$HLANG.po $< -o \
+		   $(OUTPUT)po/$$HLANG.new.po; then \
+			mv -f $(OUTPUT)po/$$HLANG.new.po $(OUTPUT)po/$$HLANG.po; \
 		else \
 			echo "msgmerge for $$HLANG failed!"; \
-			rm -f po/$$HLANG.new.po; \
+			rm -f $(OUTPUT)po/$$HLANG.new.po; \
 		fi; \
 	done;
 
-compile-bench: libcpupower.so.$(LIB_MAJ)
-	@V=$(V) confdir=$(confdir) $(MAKE) -C bench
+compile-bench: $(OUTPUT)libcpupower.so.$(LIB_MAJ)
+	@V=$(V) confdir=$(confdir) $(MAKE) -C bench O=$(OUTPUT)
+
+# we compile into subdirectories. if the target directory is not the
+# source directory, they might not exists. So we depend the various
+# files onto their directories.
+DIRECTORY_DEPS = $(LIB_OBJS) $(UTIL_OBJS) $(GMO_FILES)
+$(DIRECTORY_DEPS): | $(sort $(dir $(DIRECTORY_DEPS)))
+
+# In the second step, we make a rule to actually create these directories
+$(sort $(dir $(DIRECTORY_DEPS))):
+	$(ECHO) "  MKDIR      " $@
+	$(QUIET) $(MKDIR) -p $@ 2>/dev/null
 
 clean:
-	-find . \( -not -type d \) -and \( -name '*~' -o -name '*.[oas]' \) -type f -print \
+	-find $(OUTPUT) \( -not -type d \) -and \( -name '*~' -o -name '*.[oas]' \) -type f -print \
 	 | xargs rm -f
-	-rm -f $(UTIL_BINS)
-	-rm -f $(IDLE_OBJS)
-	-rm -f cpupower
-	-rm -f libcpupower.so*
-	-rm -rf po/*.gmo po/*.pot
-	$(MAKE) -C bench clean
+	-rm -f $(OUTPUT)cpupower
+	-rm -f $(OUTPUT)libcpupower.so*
+	-rm -rf $(OUTPUT)po/*.{gmo,pot}
+	$(MAKE) -C bench O=$(OUTPUT) clean
 
 
 install-lib:
 	$(INSTALL) -d $(DESTDIR)${libdir}
-	$(CP) libcpupower.so* $(DESTDIR)${libdir}/
+	$(CP) $(OUTPUT)libcpupower.so* $(DESTDIR)${libdir}/
 	$(INSTALL) -d $(DESTDIR)${includedir}
 	$(INSTALL_DATA) lib/cpufreq.h $(DESTDIR)${includedir}/cpufreq.h
 
 install-tools:
 	$(INSTALL) -d $(DESTDIR)${bindir}
-	$(INSTALL_PROGRAM) cpupower $(DESTDIR)${bindir}
+	$(INSTALL_PROGRAM) $(OUTPUT)cpupower $(DESTDIR)${bindir}
 
 install-man:
 	$(INSTALL_DATA) -D man/cpupower.1 $(DESTDIR)${mandir}/man1/cpupower.1
@@ -257,13 +278,13 @@ install-man:
 install-gmo:
 	$(INSTALL) -d $(DESTDIR)${localedir}
 	for HLANG in $(LANGUAGES); do \
-		echo '$(INSTALL_DATA) -D po/$$HLANG.gmo $(DESTDIR)${localedir}/$$HLANG/LC_MESSAGES/cpupower.mo'; \
-		$(INSTALL_DATA) -D po/$$HLANG.gmo $(DESTDIR)${localedir}/$$HLANG/LC_MESSAGES/cpupower.mo; \
+		echo '$(INSTALL_DATA) -D $(OUTPUT)po/$$HLANG.gmo $(DESTDIR)${localedir}/$$HLANG/LC_MESSAGES/cpupower.mo'; \
+		$(INSTALL_DATA) -D $(OUTPUT)po/$$HLANG.gmo $(DESTDIR)${localedir}/$$HLANG/LC_MESSAGES/cpupower.mo; \
 	done;
 
 install-bench:
 	@#DESTDIR must be set from outside to survive
-	@sbindir=$(sbindir) bindir=$(bindir) docdir=$(docdir) confdir=$(confdir) $(MAKE) -C bench install
+	@sbindir=$(sbindir) bindir=$(bindir) docdir=$(docdir) confdir=$(confdir) $(MAKE) -C bench O=$(OUTPUT) install
 
 install: all install-lib install-tools install-man $(INSTALL_NLS) $(INSTALL_BENCH)
 
diff --git a/tools/power/cpupower/bench/Makefile b/tools/power/cpupower/bench/Makefile
index 2b67606fc3e..7ec7021a29c 100644
--- a/tools/power/cpupower/bench/Makefile
+++ b/tools/power/cpupower/bench/Makefile
@@ -1,29 +1,36 @@
-LIBS = -L../ -lm -lcpupower
+OUTPUT := ./
+ifeq ("$(origin O)", "command line")
+ifneq ($(O),)
+	OUTPUT := $(O)/
+endif
+endif
 
-OBJS = main.o parse.o system.o benchmark.o
+LIBS = -L../ -L$(OUTPUT) -lm -lcpupower
+
+OBJS = $(OUTPUT)main.o $(OUTPUT)parse.o $(OUTPUT)system.o $(OUTPUT)benchmark.o
 CFLAGS += -D_GNU_SOURCE -I../lib -DDEFAULT_CONFIG_FILE=\"$(confdir)/cpufreq-bench.conf\"
 
-%.o : %.c
+$(OUTPUT)%.o : %.c
 	$(ECHO) "  CC      " $@
 	$(QUIET) $(CC) -c $(CFLAGS) $< -o $@
 
-cpufreq-bench: $(OBJS)
+$(OUTPUT)cpufreq-bench: $(OBJS)
 	$(ECHO) "  CC      " $@
 	$(QUIET) $(CC) -o $@ $(CFLAGS) $(OBJS) $(LIBS)
 
-all: cpufreq-bench
+all: $(OUTPUT)cpufreq-bench
 
 install:
 	mkdir -p $(DESTDIR)/$(sbindir)
 	mkdir -p $(DESTDIR)/$(bindir)
 	mkdir -p $(DESTDIR)/$(docdir)
 	mkdir -p $(DESTDIR)/$(confdir)
-	install -m 755 cpufreq-bench $(DESTDIR)/$(sbindir)/cpufreq-bench
+	install -m 755 $(OUTPUT)cpufreq-bench $(DESTDIR)/$(sbindir)/cpufreq-bench
 	install -m 755 cpufreq-bench_plot.sh $(DESTDIR)/$(bindir)/cpufreq-bench_plot.sh
 	install -m 644 README-BENCH $(DESTDIR)/$(docdir)/README-BENCH
 	install -m 755 cpufreq-bench_script.sh $(DESTDIR)/$(docdir)/cpufreq-bench_script.sh
 	install -m 644 example.cfg $(DESTDIR)/$(confdir)/cpufreq-bench.conf
 
 clean:
-	rm -f *.o
-	rm -f cpufreq-bench
+	rm -f $(OUTPUT)*.o
+	rm -f $(OUTPUT)cpufreq-bench
diff --git a/tools/power/cpupower/debug/i386/Makefile b/tools/power/cpupower/debug/i386/Makefile
index d08cc1ead9b..3ba158f0e28 100644
--- a/tools/power/cpupower/debug/i386/Makefile
+++ b/tools/power/cpupower/debug/i386/Makefile
@@ -1,20 +1,38 @@
+OUTPUT=./
+ifeq ("$(origin O)", "command line")
+	OUTPUT := $(O)/
+endif
+
+DESTDIR =
+bindir  = /usr/bin
+
+INSTALL = /usr/bin/install
+
+
 default: all
 
-centrino-decode: centrino-decode.c
-	$(CC) $(CFLAGS) -o centrino-decode centrino-decode.c
+$(OUTPUT)centrino-decode: centrino-decode.c
+	$(CC) $(CFLAGS) -o $@ centrino-decode.c
 
-dump_psb: dump_psb.c
-	$(CC) $(CFLAGS) -o dump_psb dump_psb.c
+$(OUTPUT)dump_psb: dump_psb.c
+	$(CC) $(CFLAGS) -o $@ dump_psb.c
 
-intel_gsic: intel_gsic.c
-	$(CC) $(CFLAGS) -o intel_gsic -llrmi intel_gsic.c
+$(OUTPUT)intel_gsic: intel_gsic.c
+	$(CC) $(CFLAGS) -o $@ -llrmi intel_gsic.c
 
-powernow-k8-decode: powernow-k8-decode.c
-	$(CC) $(CFLAGS) -o powernow-k8-decode powernow-k8-decode.c
+$(OUTPUT)powernow-k8-decode: powernow-k8-decode.c
+	$(CC) $(CFLAGS) -o $@ powernow-k8-decode.c
 
-all: centrino-decode dump_psb intel_gsic powernow-k8-decode
+all: $(OUTPUT)centrino-decode $(OUTPUT)dump_psb $(OUTPUT)intel_gsic $(OUTPUT)powernow-k8-decode
 
 clean:
-	rm -rf centrino-decode dump_psb intel_gsic powernow-k8-decode
+	rm -rf $(OUTPUT){centrino-decode,dump_psb,intel_gsic,powernow-k8-decode}
+
+install:
+	$(INSTALL) -d $(DESTDIR)${bindir}
+	$(INSTALL) $(OUTPUT)centrino-decode $(DESTDIR)${bindir}
+	$(INSTALL) $(OUTPUT)powernow-k8-decode $(DESTDIR)${bindir}
+	$(INSTALL) $(OUTPUT)dump_psb $(DESTDIR)${bindir}
+	$(INSTALL) $(OUTPUT)intel_gsic $(DESTDIR)${bindir}
 
-.PHONY: all default clean
+.PHONY: all default clean install
diff --git a/tools/power/cpupower/debug/x86_64/Makefile b/tools/power/cpupower/debug/x86_64/Makefile
index 3326217dd31..1c521452671 100644
--- a/tools/power/cpupower/debug/x86_64/Makefile
+++ b/tools/power/cpupower/debug/x86_64/Makefile
@@ -1,14 +1,30 @@
+OUTPUT=./
+ifeq ("$(origin O)", "command line")
+	OUTPUT := $(O)/
+endif
+
+DESTDIR =
+bindir  = /usr/bin
+
+INSTALL = /usr/bin/install
+
+
 default: all
 
-centrino-decode: ../i386/centrino-decode.c
+$(OUTPUT)centrino-decode: ../i386/centrino-decode.c
 	$(CC) $(CFLAGS) -o $@ $<
 
-powernow-k8-decode: ../i386/powernow-k8-decode.c
+$(OUTPUT)powernow-k8-decode: ../i386/powernow-k8-decode.c
 	$(CC) $(CFLAGS) -o $@ $<
 
-all: centrino-decode powernow-k8-decode
+all: $(OUTPUT)centrino-decode $(OUTPUT)powernow-k8-decode
 
 clean:
-	rm -rf centrino-decode powernow-k8-decode
+	rm -rf $(OUTPUT)centrino-decode $(OUTPUT)powernow-k8-decode
+
+install:
+	$(INSTALL) -d $(DESTDIR)${bindir}
+	$(INSTALL) $(OUTPUT)centrino-decode $(DESTDIR)${bindir}
+	$(INSTALL) $(OUTPUT)powernow-k8-decode $(DESTDIR)${bindir}
 
-.PHONY: all default clean
+.PHONY: all default clean install
diff --git a/tools/power/cpupower/man/cpupower-frequency-info.1 b/tools/power/cpupower/man/cpupower-frequency-info.1
index bb60a8d1e45..4a1918ea8f9 100644
--- a/tools/power/cpupower/man/cpupower-frequency-info.1
+++ b/tools/power/cpupower/man/cpupower-frequency-info.1
@@ -1,4 +1,4 @@
-.TH "cpupower-frequency-info" "1" "0.1" "Mattia Dongili" ""
+.TH "CPUPOWER\-FREQUENCY\-INFO" "1" "0.1" "" "cpupower Manual"
 .SH "NAME"
 .LP 
 cpupower frequency\-info \- Utility to retrieve cpufreq kernel information
@@ -50,8 +50,6 @@ Prints out information like provided by the /proc/cpufreq interface in 2.4. and
 \fB\-m\fR \fB\-\-human\fR
 human\-readable output for the \-f, \-w, \-s and \-y parameters.
 .TP  
-\fB\-h\fR \fB\-\-help\fR
-Prints out the help screen.
 .SH "REMARKS"
 .LP 
 By default only values of core zero are displayed. How to display settings of
diff --git a/tools/power/cpupower/man/cpupower-frequency-set.1 b/tools/power/cpupower/man/cpupower-frequency-set.1
index 685f469093a..3eacc8d03d1 100644
--- a/tools/power/cpupower/man/cpupower-frequency-set.1
+++ b/tools/power/cpupower/man/cpupower-frequency-set.1
@@ -1,4 +1,4 @@
-.TH "cpupower-freqency-set" "1" "0.1" "Mattia Dongili" ""
+.TH "CPUPOWER\-FREQUENCY\-SET" "1" "0.1" "" "cpupower Manual"
 .SH "NAME"
 .LP 
 cpupower frequency\-set \- A small tool which allows to modify cpufreq settings.
@@ -26,8 +26,6 @@ specific frequency to be set. Requires userspace governor to be available and lo
 \fB\-r\fR \fB\-\-related\fR
 modify all hardware-related CPUs at the same time
 .TP 
-\fB\-h\fR \fB\-\-help\fR
-Prints out the help screen.
 .SH "REMARKS"
 .LP 
 By default values are applied on all cores. How to modify single core
diff --git a/tools/power/cpupower/man/cpupower-idle-info.1 b/tools/power/cpupower/man/cpupower-idle-info.1
new file mode 100644
index 00000000000..4178effd9e9
--- /dev/null
+++ b/tools/power/cpupower/man/cpupower-idle-info.1
@@ -0,0 +1,90 @@
+.TH "CPUPOWER-IDLE-INFO" "1" "0.1" "" "cpupower Manual"
+.SH "NAME"
+.LP
+cpupower idle\-info \- Utility to retrieve cpu idle kernel information
+.SH "SYNTAX"
+.LP
+cpupower [ \-c cpulist ] idle\-info [\fIoptions\fP]
+.SH "DESCRIPTION"
+.LP
+A tool which prints out per cpu idle information helpful to developers and interested users.
+.SH "OPTIONS"
+.LP
+.TP
+\fB\-f\fR \fB\-\-silent\fR
+Only print a summary of all available C-states in the system.
+.TP
+\fB\-e\fR \fB\-\-proc\fR
+deprecated.
+Prints out idle information in old /proc/acpi/processor/*/power format. This
+interface has been removed from the kernel for quite some time, do not let
+further code depend on this option, best do not use it.
+
+.SH IDLE\-INFO DESCRIPTIONS
+CPU sleep state statistics and descriptions are retrieved from sysfs files,
+exported by the cpuidle kernel subsystem. The kernel only updates these
+statistics when it enters or leaves an idle state, therefore on a very idle or
+a very busy system, these statistics may not be accurate. They still provide a
+good overview about the usage and availability of processor sleep states on
+the platform.
+
+Be aware that the sleep states as exported by the hardware or BIOS and used by
+the Linux kernel may not exactly reflect the capabilities of the
+processor. This often is the case on the X86 architecture when the acpi_idle
+driver is used. It is also possible that the hardware overrules the kernel
+requests, due to internal activity monitors or other reasons.
+On recent X86 platforms it is often possible to read out hardware registers
+which monitor the duration of sleep states the processor resided in. The
+cpupower monitor tool (cpupower\-monitor(1)) can be used to show real sleep
+state residencies. Please refer to the architecture specific description
+section below.
+
+.SH IDLE\-INFO ARCHITECTURE SPECIFIC DESCRIPTIONS
+.SS "X86"
+POLL idle state
+
+If cpuidle is active, X86 platforms have one special idle state.
+The POLL idle state is not a real idle state, it does not save any
+power. Instead, a busy\-loop is executed doing nothing for a short period of
+time. This state is used if the kernel knows that work has to be processed
+very soon and entering any real hardware idle state may result in a slight
+performance penalty.
+
+There exist two different cpuidle drivers on the X86 architecture platform:
+
+"acpi_idle" cpuidle driver
+
+The acpi_idle cpuidle driver retrieves available sleep states (C\-states) from
+the ACPI BIOS tables (from the _CST ACPI function on recent platforms or from
+the FADT BIOS table on older ones).
+The C1 state is not retrieved from ACPI tables. If the C1 state is entered,
+the kernel will call the hlt instruction (or mwait on Intel).
+
+"intel_idle" cpuidle driver
+
+In kernel 2.6.36 the intel_idle driver was introduced.
+It only serves recent Intel CPUs (Nehalem, Westmere, Sandybridge, Atoms or
+newer). On older Intel CPUs the acpi_idle driver is still used (if the BIOS
+provides C\-state ACPI tables).
+The intel_idle driver knows the sleep state capabilities of the processor and
+ignores ACPI BIOS exported processor sleep states tables.
+
+.SH "REMARKS"
+.LP
+By default only values of core zero are displayed. How to display settings of
+other cores is described in the cpupower(1) manpage in the \-\-cpu option
+section.
+.SH REFERENCES
+http://www.acpi.info/spec.htm
+.SH "FILES"
+.nf
+\fI/sys/devices/system/cpu/cpu*/cpuidle/state*\fP
+\fI/sys/devices/system/cpu/cpuidle/*\fP
+.fi
+.SH "AUTHORS"
+.nf
+Thomas Renninger <trenn@suse.de>
+.fi
+.SH "SEE ALSO"
+.LP
+cpupower(1), cpupower\-monitor(1), cpupower\-info(1), cpupower\-set(1)
diff --git a/tools/power/cpupower/man/cpupower-monitor.1 b/tools/power/cpupower/man/cpupower-monitor.1
index d5cfa265c3d..1141c207371 100644
--- a/tools/power/cpupower/man/cpupower-monitor.1
+++ b/tools/power/cpupower/man/cpupower-monitor.1
@@ -107,7 +107,7 @@ Deepest package sleep states may in reality show up as machine/platform wide
 sleep states and can only be entered if all cores are idle. Look up Intel
 manuals (some are provided in the References section) for further details.
 
-.SS "Ontario" "Liano"
+.SS "Fam_12h" "Fam_14h"
 AMD laptop and desktop processor (family 12h and 14h) sleep state counters.
 The registers are accessed via PCI and therefore can still be read out while
 cores have been offlined.
diff --git a/tools/power/cpupower/utils/cpuidle-info.c b/tools/power/cpupower/utils/cpuidle-info.c
index b028267c137..8145af5f93a 100644
--- a/tools/power/cpupower/utils/cpuidle-info.c
+++ b/tools/power/cpupower/utils/cpuidle-info.c
@@ -35,17 +35,9 @@ static void cpuidle_cpu_output(unsigned int cpu, int verbose)
 		printf(_("CPU %u: Can't read idle state info\n"), cpu);
 		return;
 	}
-	tmp = sysfs_get_idlestate_name(cpu, idlestates - 1);
-	if (!tmp) {
-		printf(_("Could not determine max idle state %u\n"),
-		       idlestates - 1);
-		return;
-	}
-
 	printf(_("Number of idle states: %d\n"), idlestates);
-
 	printf(_("Available idle states:"));
-	for (idlestate = 1; idlestate < idlestates; idlestate++) {
+	for (idlestate = 0; idlestate < idlestates; idlestate++) {
 		tmp = sysfs_get_idlestate_name(cpu, idlestate);
 		if (!tmp)
 			continue;
@@ -57,7 +49,7 @@ static void cpuidle_cpu_output(unsigned int cpu, int verbose)
 	if (!verbose)
 		return;
 
-	for (idlestate = 1; idlestate < idlestates; idlestate++) {
+	for (idlestate = 0; idlestate < idlestates; idlestate++) {
 		tmp = sysfs_get_idlestate_name(cpu, idlestate);
 		if (!tmp)
 			continue;
diff --git a/tools/power/cpupower/utils/helpers/amd.c b/tools/power/cpupower/utils/helpers/amd.c
index 87d5605bdda..6437ef39aee 100644
--- a/tools/power/cpupower/utils/helpers/amd.c
+++ b/tools/power/cpupower/utils/helpers/amd.c
@@ -112,14 +112,12 @@ int decode_pstates(unsigned int cpu, unsigned int cpu_family,
 int amd_pci_get_num_boost_states(int *active, int *states)
 {
 	struct pci_access *pci_acc;
-	int vendor_id = 0x1022;
-	int boost_dev_ids[4] = {0x1204, 0x1604, 0x1704, 0};
 	struct pci_dev *device;
 	uint8_t val = 0;
 
 	*active = *states = 0;
 
-	device = pci_acc_init(&pci_acc, vendor_id, boost_dev_ids);
+	device = pci_slot_func_init(&pci_acc, 0x18, 4);
 
 	if (device == NULL)
 		return -ENODEV;
diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h
index 2747e738efb..2eb584cf2f5 100644
--- a/tools/power/cpupower/utils/helpers/helpers.h
+++ b/tools/power/cpupower/utils/helpers/helpers.h
@@ -66,8 +66,8 @@ enum cpupower_cpu_vendor {X86_VENDOR_UNKNOWN = 0, X86_VENDOR_INTEL,
 #define CPUPOWER_CAP_AMD_CBP		0x00000004
 #define CPUPOWER_CAP_PERF_BIAS		0x00000008
 #define CPUPOWER_CAP_HAS_TURBO_RATIO	0x00000010
-#define CPUPOWER_CAP_IS_SNB		0x00000011
-#define CPUPOWER_CAP_INTEL_IDA		0x00000012
+#define CPUPOWER_CAP_IS_SNB		0x00000020
+#define CPUPOWER_CAP_INTEL_IDA		0x00000040
 
 #define MAX_HW_PSTATES 10
 
@@ -132,8 +132,11 @@ extern unsigned long long msr_intel_get_turbo_ratio(unsigned int cpu);
 
 /* PCI stuff ****************************/
 extern int amd_pci_get_num_boost_states(int *active, int *states);
-extern struct pci_dev *pci_acc_init(struct pci_access **pacc, int vendor_id,
-				    int *dev_ids);
+extern struct pci_dev *pci_acc_init(struct pci_access **pacc, int domain,
+				    int bus, int slot, int func, int vendor,
+				    int dev);
+extern struct pci_dev *pci_slot_func_init(struct pci_access **pacc,
+					      int slot, int func);
 
 /* PCI stuff ****************************/
 
diff --git a/tools/power/cpupower/utils/helpers/pci.c b/tools/power/cpupower/utils/helpers/pci.c
index cd2eb6fe41c..9690798e644 100644
--- a/tools/power/cpupower/utils/helpers/pci.c
+++ b/tools/power/cpupower/utils/helpers/pci.c
@@ -10,19 +10,24 @@
  * **pacc : if a valid pci_dev is returned
  *         *pacc must be passed to pci_acc_cleanup to free it
  *
- * vendor_id : the pci vendor id matching the pci device to access
- * dev_ids :   device ids matching the pci device to access
+ * domain: domain
+ * bus:    bus
+ * slot:   slot
+ * func:   func
+ * vendor: vendor
+ * device: device
+ * Pass -1 for one of the six above to match any
  *
  * Returns :
  * struct pci_dev which can be used with pci_{read,write}_* functions
  *                to access the PCI config space of matching pci devices
  */
-struct pci_dev *pci_acc_init(struct pci_access **pacc, int vendor_id,
-				    int *dev_ids)
+struct pci_dev *pci_acc_init(struct pci_access **pacc, int domain, int bus,
+			     int slot, int func, int vendor, int dev)
 {
-	struct pci_filter filter_nb_link = { -1, -1, -1, -1, vendor_id, 0};
+	struct pci_filter filter_nb_link = { domain, bus, slot, func,
+					     vendor, dev };
 	struct pci_dev *device;
-	unsigned int i;
 
 	*pacc = pci_alloc();
 	if (*pacc == NULL)
@@ -31,14 +36,20 @@ struct pci_dev *pci_acc_init(struct pci_access **pacc, int vendor_id,
 	pci_init(*pacc);
 	pci_scan_bus(*pacc);
 
-	for (i = 0; dev_ids[i] != 0; i++) {
-		filter_nb_link.device = dev_ids[i];
-		for (device = (*pacc)->devices; device; device = device->next) {
-			if (pci_filter_match(&filter_nb_link, device))
-				return device;
-		}
+	for (device = (*pacc)->devices; device; device = device->next) {
+		if (pci_filter_match(&filter_nb_link, device))
+			return device;
 	}
 	pci_cleanup(*pacc);
 	return NULL;
 }
+
+/* Typically one wants to get a specific slot(device)/func of the root domain
+   and bus */
+struct pci_dev *pci_slot_func_init(struct pci_access **pacc, int slot,
+				       int func)
+{
+	return pci_acc_init(pacc, 0, 0, slot, func, -1, -1);
+}
+
 #endif /* defined(__i386__) || defined(__x86_64__) */
diff --git a/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c b/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
index 202e555988b..2116df9ad83 100644
--- a/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
+++ b/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
@@ -20,8 +20,6 @@
 #include "idle_monitor/cpupower-monitor.h"
 #include "helpers/helpers.h"
 
-/******** PCI parts could go into own file and get shared ***************/
-
 #define PCI_NON_PC0_OFFSET	0xb0
 #define PCI_PC1_OFFSET		0xb4
 #define PCI_PC6_OFFSET		0xb8
@@ -82,10 +80,7 @@ static cstate_t amd_fam14h_cstates[AMD_FAM14H_STATE_NUM] = {
 };
 
 static struct pci_access *pci_acc;
-static int pci_vendor_id = 0x1022;
-static int pci_dev_ids[2] = {0x1716, 0};
 static struct pci_dev *amd_fam14h_pci_dev;
-
 static int nbp1_entered;
 
 struct timespec start_time;
@@ -286,13 +281,13 @@ struct cpuidle_monitor *amd_fam14h_register(void)
 	if (cpupower_cpu_info.vendor != X86_VENDOR_AMD)
 		return NULL;
 
-	if (cpupower_cpu_info.family == 0x14) {
-		if (cpu_count <= 0 || cpu_count > 2) {
-			fprintf(stderr, "AMD fam14h: Invalid cpu count: %d\n",
-				cpu_count);
-			return NULL;
-		}
-	} else
+	if (cpupower_cpu_info.family == 0x14)
+		strncpy(amd_fam14h_monitor.name, "Fam_14h",
+			MONITOR_NAME_LEN - 1);
+	else if (cpupower_cpu_info.family == 0x12)
+		strncpy(amd_fam14h_monitor.name, "Fam_12h",
+			MONITOR_NAME_LEN - 1);
+	else
 		return NULL;
 
 	/* We do not alloc for nbp1 machine wide counter */
@@ -303,7 +298,9 @@ struct cpuidle_monitor *amd_fam14h_register(void)
 					      sizeof(unsigned long long));
 	}
 
-	amd_fam14h_pci_dev = pci_acc_init(&pci_acc, pci_vendor_id, pci_dev_ids);
+	/* We need PCI device: Slot 18, Func 6, compare with BKDG
+	   for fam 12h/14h */
+	amd_fam14h_pci_dev = pci_slot_func_init(&pci_acc, 0x18, 6);
 	if (amd_fam14h_pci_dev == NULL || pci_acc == NULL)
 		return NULL;
 
@@ -325,7 +322,7 @@ static void amd_fam14h_unregister(void)
 }
 
 struct cpuidle_monitor amd_fam14h_monitor = {
-	.name			= "Ontario",
+	.name			= "",
 	.hw_states		= amd_fam14h_cstates,
 	.hw_states_num		= AMD_FAM14H_STATE_NUM,
 	.start			= amd_fam14h_start,
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index 555c69a5592..adf175f6149 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -4,11 +4,13 @@ turbostat \- Report processor frequency and idle statistics
 .SH SYNOPSIS
 .ft B
 .B turbostat
+.RB [ "\-s" ]
 .RB [ "\-v" ]
 .RB [ "\-M MSR#" ]
 .RB command
 .br
 .B turbostat
+.RB [ "\-s" ]
 .RB [ "\-v" ]
 .RB [ "\-M MSR#" ]
 .RB [ "\-i interval_sec" ]
@@ -25,6 +27,8 @@ supports an "invariant" TSC, plus the APERF and MPERF MSRs.
 on processors that additionally support C-state residency counters.
 
 .SS Options
+The \fB-s\fP option prints only a 1-line summary for each sample interval.
+.PP
 The \fB-v\fP option increases verbosity.
 .PP
 The \fB-M MSR#\fP option dumps the specified MSR,
@@ -39,13 +43,14 @@ displays the statistics gathered since it was forked.
 .SH FIELD DESCRIPTIONS
 .nf
 \fBpk\fP processor package number.
-\fBcr\fP processor core number.
+\fBcor\fP processor core number.
 \fBCPU\fP Linux CPU (logical processor) number.
+Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology.
 \fB%c0\fP percent of the interval that the CPU retired instructions.
 \fBGHz\fP average clock rate while the CPU was in c0 state.
 \fBTSC\fP average GHz that the TSC ran during the entire interval.
-\fB%c1, %c3, %c6\fP show the percentage residency in hardware core idle states.
-\fB%pc3, %pc6\fP percentage residency in hardware package idle states.
+\fB%c1, %c3, %c6, %c7\fP show the percentage residency in hardware core idle states.
+\fB%pc2, %pc3, %pc6, %pc7\fP percentage residency in hardware package idle states.
 .fi
 .PP
 .SH EXAMPLE
@@ -53,25 +58,37 @@ Without any parameters, turbostat prints out counters ever 5 seconds.
 (override interval with "-i sec" option, or specify a command
 for turbostat to fork).
 
-The first row of statistics reflect the average for the entire system.
+The first row of statistics is a summary for the entire system.
+Note that the summary is a weighted average.
 Subsequent rows show per-CPU statistics.
 
 .nf
 [root@x980]# ./turbostat
-cr   CPU   %c0   GHz  TSC   %c1    %c3    %c6   %pc3   %pc6
-          0.04 1.62 3.38   0.11   0.00  99.85   0.00  95.07
-  0   0   0.04 1.62 3.38   0.06   0.00  99.90   0.00  95.07
-  0   6   0.02 1.62 3.38   0.08   0.00  99.90   0.00  95.07
-  1   2   0.10 1.62 3.38   0.29   0.00  99.61   0.00  95.07
-  1   8   0.11 1.62 3.38   0.28   0.00  99.61   0.00  95.07
-  2   4   0.01 1.62 3.38   0.01   0.00  99.98   0.00  95.07
-  2  10   0.01 1.61 3.38   0.02   0.00  99.98   0.00  95.07
-  8   1   0.07 1.62 3.38   0.15   0.00  99.78   0.00  95.07
-  8   7   0.03 1.62 3.38   0.19   0.00  99.78   0.00  95.07
-  9   3   0.01 1.62 3.38   0.02   0.00  99.98   0.00  95.07
-  9   9   0.01 1.62 3.38   0.02   0.00  99.98   0.00  95.07
- 10   5   0.01 1.62 3.38   0.13   0.00  99.86   0.00  95.07
- 10  11   0.08 1.62 3.38   0.05   0.00  99.86   0.00  95.07
+cor CPU    %c0  GHz  TSC    %c1    %c3    %c6   %pc3   %pc6
+          0.60 1.63 3.38   2.91   0.00  96.49   0.00  76.64
+  0   0   0.59 1.62 3.38   4.51   0.00  94.90   0.00  76.64
+  0   6   1.13 1.64 3.38   3.97   0.00  94.90   0.00  76.64
+  1   2   0.08 1.62 3.38   0.07   0.00  99.85   0.00  76.64
+  1   8   0.03 1.62 3.38   0.12   0.00  99.85   0.00  76.64
+  2   4   0.01 1.62 3.38   0.06   0.00  99.93   0.00  76.64
+  2  10   0.04 1.62 3.38   0.02   0.00  99.93   0.00  76.64
+  8   1   2.85 1.62 3.38  11.71   0.00  85.44   0.00  76.64
+  8   7   1.98 1.62 3.38  12.58   0.00  85.44   0.00  76.64
+  9   3   0.36 1.62 3.38   0.71   0.00  98.93   0.00  76.64
+  9   9   0.09 1.62 3.38   0.98   0.00  98.93   0.00  76.64
+ 10   5   0.03 1.62 3.38   0.09   0.00  99.87   0.00  76.64
+ 10  11   0.07 1.62 3.38   0.06   0.00  99.87   0.00  76.64
+.fi
+.SH SUMMARY EXAMPLE
+The "-s" option prints the column headers just once,
+and then the one line system summary for each sample interval.
+
+.nf
+[root@x980]# ./turbostat -s
+   %c0  GHz  TSC    %c1    %c3    %c6   %pc3   %pc6
+  0.61 1.89 3.38   5.95   0.00  93.44   0.00  66.33
+  0.52 1.62 3.38   6.83   0.00  92.65   0.00  61.11
+  0.62 1.92 3.38   5.47   0.00  93.91   0.00  67.31
 .fi
 .SH VERBOSE EXAMPLE
 The "-v" option adds verbosity to the output:
@@ -101,33 +118,33 @@ until ^C while the other CPUs are mostly idle:
 
 .nf
 [root@x980 lenb]# ./turbostat cat /dev/zero > /dev/null
-
-^Ccr   CPU   %c0   GHz  TSC   %c1    %c3    %c6   %pc3   %pc6
-           8.49 3.63 3.38  16.23   0.66  74.63   0.00   0.00
-   0   0   1.22 3.62 3.38  32.18   0.00  66.60   0.00   0.00
-   0   6   0.40 3.61 3.38  33.00   0.00  66.60   0.00   0.00
-   1   2   0.11 3.14 3.38   0.19   3.95  95.75   0.00   0.00
-   1   8   0.05 2.88 3.38   0.25   3.95  95.75   0.00   0.00
-   2   4   0.00 3.13 3.38   0.02   0.00  99.98   0.00   0.00
-   2  10   0.00 3.09 3.38   0.02   0.00  99.98   0.00   0.00
-   8   1   0.04 3.50 3.38  14.43   0.00  85.54   0.00   0.00
-   8   7   0.03 2.98 3.38  14.43   0.00  85.54   0.00   0.00
-   9   3   0.00 3.16 3.38 100.00   0.00   0.00   0.00   0.00
-   9   9  99.93 3.63 3.38   0.06   0.00   0.00   0.00   0.00
-  10   5   0.01 2.82 3.38   0.08   0.00  99.91   0.00   0.00
-  10  11   0.02 3.36 3.38   0.06   0.00  99.91   0.00   0.00
-6.950866 sec
+^C
+cor CPU    %c0  GHz  TSC    %c1    %c3    %c6   %pc3   %pc6
+          8.63 3.64 3.38  14.46   0.49  76.42   0.00   0.00
+  0   0   0.34 3.36 3.38  99.66   0.00   0.00   0.00   0.00
+  0   6  99.96 3.64 3.38   0.04   0.00   0.00   0.00   0.00
+  1   2   0.14 3.50 3.38   1.75   2.04  96.07   0.00   0.00
+  1   8   0.38 3.57 3.38   1.51   2.04  96.07   0.00   0.00
+  2   4   0.01 2.65 3.38   0.06   0.00  99.93   0.00   0.00
+  2  10   0.03 2.12 3.38   0.04   0.00  99.93   0.00   0.00
+  8   1   0.91 3.59 3.38  35.27   0.92  62.90   0.00   0.00
+  8   7   1.61 3.63 3.38  34.57   0.92  62.90   0.00   0.00
+  9   3   0.04 3.38 3.38   0.20   0.00  99.76   0.00   0.00
+  9   9   0.04 3.29 3.38   0.20   0.00  99.76   0.00   0.00
+ 10   5   0.03 3.08 3.38   0.12   0.00  99.85   0.00   0.00
+ 10  11   0.05 3.07 3.38   0.10   0.00  99.85   0.00   0.00
+4.907015 sec
 
 .fi
-Above the cycle soaker drives cpu9 up 3.6 Ghz turbo limit
+Above the cycle soaker drives cpu6 up 3.6 Ghz turbo limit
 while the other processors are generally in various states of idle.
 
-Note that cpu3 is an HT sibling sharing core9
-with cpu9, and thus it is unable to get to an idle state
-deeper than c1 while cpu9 is busy.
+Note that cpu0 is an HT sibling sharing core0
+with cpu6, and thus it is unable to get to an idle state
+deeper than c1 while cpu6 is busy.
 
-Note that turbostat reports average GHz of 3.61, while
-the arithmetic average of the GHz column above is 3.24.
+Note that turbostat reports average GHz of 3.64, while
+the arithmetic average of the GHz column above is lower.
 This is a weighted average, where the weight is %c0.  ie. it is the total number of
 un-halted cycles elapsed per time divided by the number of CPUs.
 .SH NOTES
@@ -167,6 +184,6 @@ http://www.intel.com/products/processor/manuals/
 .SH "SEE ALSO"
 msr(4), vmstat(8)
 .PP
-.SH AUTHORS
+.SH AUTHOR
 .nf
 Written by Len Brown <len.brown@intel.com>
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 310d3dd5e54..ab2f682fd44 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -2,7 +2,7 @@
  * turbostat -- show CPU frequency and C-state residency
  * on modern Intel turbo-capable processors.
  *
- * Copyright (c) 2010, Intel Corporation.
+ * Copyright (c) 2012 Intel Corporation.
  * Len Brown <len.brown@intel.com>
  *
  * This program is free software; you can redistribute it and/or modify it
@@ -19,6 +19,7 @@
  * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
+#define _GNU_SOURCE
 #include <stdio.h>
 #include <unistd.h>
 #include <sys/types.h>
@@ -32,6 +33,7 @@
 #include <dirent.h>
 #include <string.h>
 #include <ctype.h>
+#include <sched.h>
 
 #define MSR_TSC	0x10
 #define MSR_NEHALEM_PLATFORM_INFO	0xCE
@@ -49,6 +51,7 @@
 char *proc_stat = "/proc/stat";
 unsigned int interval_sec = 5;	/* set with -i interval_sec */
 unsigned int verbose;		/* set with -v */
+unsigned int summary_only;	/* set with -s */
 unsigned int skip_c0;
 unsigned int skip_c1;
 unsigned int do_nhm_cstates;
@@ -68,9 +71,10 @@ unsigned int show_cpu;
 int aperf_mperf_unstable;
 int backwards_count;
 char *progname;
-int need_reinitialize;
 
 int num_cpus;
+cpu_set_t *cpu_mask;
+size_t cpu_mask_size;
 
 struct counters {
 	unsigned long long tsc;		/* per thread */
@@ -99,44 +103,76 @@ struct timeval tv_even;
 struct timeval tv_odd;
 struct timeval tv_delta;
 
-unsigned long long get_msr(int cpu, off_t offset)
+/*
+ * cpu_mask_init(ncpus)
+ *
+ * allocate and clear cpu_mask
+ * set cpu_mask_size
+ */
+void cpu_mask_init(int ncpus)
+{
+	cpu_mask = CPU_ALLOC(ncpus);
+	if (cpu_mask == NULL) {
+		perror("CPU_ALLOC");
+		exit(3);
+	}
+	cpu_mask_size = CPU_ALLOC_SIZE(ncpus);
+	CPU_ZERO_S(cpu_mask_size, cpu_mask);
+}
+
+void cpu_mask_uninit()
+{
+	CPU_FREE(cpu_mask);
+	cpu_mask = NULL;
+	cpu_mask_size = 0;
+}
+
+int cpu_migrate(int cpu)
+{
+	CPU_ZERO_S(cpu_mask_size, cpu_mask);
+	CPU_SET_S(cpu, cpu_mask_size, cpu_mask);
+	if (sched_setaffinity(0, cpu_mask_size, cpu_mask) == -1)
+		return -1;
+	else
+		return 0;
+}
+
+int get_msr(int cpu, off_t offset, unsigned long long *msr)
 {
 	ssize_t retval;
-	unsigned long long msr;
 	char pathname[32];
 	int fd;
 
 	sprintf(pathname, "/dev/cpu/%d/msr", cpu);
 	fd = open(pathname, O_RDONLY);
-	if (fd < 0) {
-		perror(pathname);
-		need_reinitialize = 1;
-		return 0;
-	}
-
-	retval = pread(fd, &msr, sizeof msr, offset);
-	if (retval != sizeof msr) {
-		fprintf(stderr, "cpu%d pread(..., 0x%zx) = %jd\n",
-			cpu, offset, retval);
-		exit(-2);
-	}
+	if (fd < 0)
+		return -1;
 
+	retval = pread(fd, msr, sizeof *msr, offset);
 	close(fd);
-	return msr;
+
+	if (retval != sizeof *msr)
+		return -1;
+
+	return 0;
 }
 
 void print_header(void)
 {
 	if (show_pkg)
 		fprintf(stderr, "pk");
+	if (show_pkg)
+		fprintf(stderr, " ");
 	if (show_core)
-		fprintf(stderr, " cr");
+		fprintf(stderr, "cor");
 	if (show_cpu)
 		fprintf(stderr, " CPU");
+	if (show_pkg || show_core || show_cpu)
+		fprintf(stderr, " ");
 	if (do_nhm_cstates)
-		fprintf(stderr, "    %%c0 ");
+		fprintf(stderr, "   %%c0");
 	if (has_aperf)
-		fprintf(stderr, " GHz");
+		fprintf(stderr, "  GHz");
 	fprintf(stderr, "  TSC");
 	if (do_nhm_cstates)
 		fprintf(stderr, "    %%c1");
@@ -147,13 +183,13 @@ void print_header(void)
 	if (do_snb_cstates)
 		fprintf(stderr, "    %%c7");
 	if (do_snb_cstates)
-		fprintf(stderr, "  %%pc2");
+		fprintf(stderr, "   %%pc2");
 	if (do_nhm_cstates)
-		fprintf(stderr, "  %%pc3");
+		fprintf(stderr, "   %%pc3");
 	if (do_nhm_cstates)
-		fprintf(stderr, "  %%pc6");
+		fprintf(stderr, "   %%pc6");
 	if (do_snb_cstates)
-		fprintf(stderr, "  %%pc7");
+		fprintf(stderr, "   %%pc7");
 	if (extra_msr_offset)
 		fprintf(stderr, "        MSR 0x%x ", extra_msr_offset);
 
@@ -187,6 +223,15 @@ void dump_list(struct counters *cnt)
 		dump_cnt(cnt);
 }
 
+/*
+ * column formatting convention & formats
+ * package: "pk" 2 columns %2d
+ * core: "cor" 3 columns %3d
+ * CPU: "CPU" 3 columns %3d
+ * GHz: "GHz" 3 columns %3.2
+ * TSC: "TSC" 3 columns %3.2
+ * percentage " %pc3" %6.2
+ */
 void print_cnt(struct counters *p)
 {
 	double interval_float;
@@ -196,39 +241,45 @@ void print_cnt(struct counters *p)
 	/* topology columns, print blanks on 1st (average) line */
 	if (p == cnt_average) {
 		if (show_pkg)
+			fprintf(stderr, "  ");
+		if (show_pkg && show_core)
 			fprintf(stderr, " ");
 		if (show_core)
-			fprintf(stderr, "    ");
+			fprintf(stderr, "   ");
 		if (show_cpu)
-			fprintf(stderr, "    ");
+			fprintf(stderr, " " "   ");
 	} else {
 		if (show_pkg)
-			fprintf(stderr, "%d", p->pkg);
+			fprintf(stderr, "%2d", p->pkg);
+		if (show_pkg && show_core)
+			fprintf(stderr, " ");
 		if (show_core)
-			fprintf(stderr, "%4d", p->core);
+			fprintf(stderr, "%3d", p->core);
 		if (show_cpu)
-			fprintf(stderr, "%4d", p->cpu);
+			fprintf(stderr, " %3d", p->cpu);
 	}
 
 	/* %c0 */
 	if (do_nhm_cstates) {
+		if (show_pkg || show_core || show_cpu)
+			fprintf(stderr, " ");
 		if (!skip_c0)
-			fprintf(stderr, "%7.2f", 100.0 * p->mperf/p->tsc);
+			fprintf(stderr, "%6.2f", 100.0 * p->mperf/p->tsc);
 		else
-			fprintf(stderr, "   ****");
+			fprintf(stderr, "  ****");
 	}
 
 	/* GHz */
 	if (has_aperf) {
 		if (!aperf_mperf_unstable) {
-			fprintf(stderr, "%5.2f",
+			fprintf(stderr, " %3.2f",
 				1.0 * p->tsc / units * p->aperf /
 				p->mperf / interval_float);
 		} else {
 			if (p->aperf > p->tsc || p->mperf > p->tsc) {
-				fprintf(stderr, " ****");
+				fprintf(stderr, " ***");
 			} else {
-				fprintf(stderr, "%4.1f*",
+				fprintf(stderr, "%3.1f*",
 					1.0 * p->tsc /
 					units * p->aperf /
 					p->mperf / interval_float);
@@ -241,7 +292,7 @@ void print_cnt(struct counters *p)
 
 	if (do_nhm_cstates) {
 		if (!skip_c1)
-			fprintf(stderr, "%7.2f", 100.0 * p->c1/p->tsc);
+			fprintf(stderr, " %6.2f", 100.0 * p->c1/p->tsc);
 		else
 			fprintf(stderr, "  ****");
 	}
@@ -252,13 +303,13 @@ void print_cnt(struct counters *p)
 	if (do_snb_cstates)
 		fprintf(stderr, " %6.2f", 100.0 * p->c7/p->tsc);
 	if (do_snb_cstates)
-		fprintf(stderr, " %5.2f", 100.0 * p->pc2/p->tsc);
+		fprintf(stderr, " %6.2f", 100.0 * p->pc2/p->tsc);
 	if (do_nhm_cstates)
-		fprintf(stderr, " %5.2f", 100.0 * p->pc3/p->tsc);
+		fprintf(stderr, " %6.2f", 100.0 * p->pc3/p->tsc);
 	if (do_nhm_cstates)
-		fprintf(stderr, " %5.2f", 100.0 * p->pc6/p->tsc);
+		fprintf(stderr, " %6.2f", 100.0 * p->pc6/p->tsc);
 	if (do_snb_cstates)
-		fprintf(stderr, " %5.2f", 100.0 * p->pc7/p->tsc);
+		fprintf(stderr, " %6.2f", 100.0 * p->pc7/p->tsc);
 	if (extra_msr_offset)
 		fprintf(stderr, "  0x%016llx", p->extra_msr);
 	putc('\n', stderr);
@@ -267,12 +318,20 @@ void print_cnt(struct counters *p)
 void print_counters(struct counters *counters)
 {
 	struct counters *cnt;
+	static int printed;
+
 
-	print_header();
+	if (!printed || !summary_only)
+		print_header();
 
 	if (num_cpus > 1)
 		print_cnt(cnt_average);
 
+	printed = 1;
+
+	if (summary_only)
+		return;
+
 	for (cnt = counters; cnt != NULL; cnt = cnt->next)
 		print_cnt(cnt);
 
@@ -440,31 +499,51 @@ void compute_average(struct counters *delta, struct counters *avg)
 	free(sum);
 }
 
-void get_counters(struct counters *cnt)
+int get_counters(struct counters *cnt)
 {
 	for ( ; cnt; cnt = cnt->next) {
-		cnt->tsc = get_msr(cnt->cpu, MSR_TSC);
-		if (do_nhm_cstates)
-			cnt->c3 = get_msr(cnt->cpu, MSR_CORE_C3_RESIDENCY);
-		if (do_nhm_cstates)
-			cnt->c6 = get_msr(cnt->cpu, MSR_CORE_C6_RESIDENCY);
-		if (do_snb_cstates)
-			cnt->c7 = get_msr(cnt->cpu, MSR_CORE_C7_RESIDENCY);
-		if (has_aperf)
-			cnt->aperf = get_msr(cnt->cpu, MSR_APERF);
-		if (has_aperf)
-			cnt->mperf = get_msr(cnt->cpu, MSR_MPERF);
-		if (do_snb_cstates)
-			cnt->pc2 = get_msr(cnt->cpu, MSR_PKG_C2_RESIDENCY);
-		if (do_nhm_cstates)
-			cnt->pc3 = get_msr(cnt->cpu, MSR_PKG_C3_RESIDENCY);
-		if (do_nhm_cstates)
-			cnt->pc6 = get_msr(cnt->cpu, MSR_PKG_C6_RESIDENCY);
+
+		if (cpu_migrate(cnt->cpu))
+			return -1;
+
+		if (get_msr(cnt->cpu, MSR_TSC, &cnt->tsc))
+			return -1;
+
+		if (has_aperf) {
+			if (get_msr(cnt->cpu, MSR_APERF, &cnt->aperf))
+				return -1;
+			if (get_msr(cnt->cpu, MSR_MPERF, &cnt->mperf))
+				return -1;
+		}
+
+		if (do_nhm_cstates) {
+			if (get_msr(cnt->cpu, MSR_CORE_C3_RESIDENCY, &cnt->c3))
+				return -1;
+			if (get_msr(cnt->cpu, MSR_CORE_C6_RESIDENCY, &cnt->c6))
+				return -1;
+		}
+
 		if (do_snb_cstates)
-			cnt->pc7 = get_msr(cnt->cpu, MSR_PKG_C7_RESIDENCY);
+			if (get_msr(cnt->cpu, MSR_CORE_C7_RESIDENCY, &cnt->c7))
+				return -1;
+
+		if (do_nhm_cstates) {
+			if (get_msr(cnt->cpu, MSR_PKG_C3_RESIDENCY, &cnt->pc3))
+				return -1;
+			if (get_msr(cnt->cpu, MSR_PKG_C6_RESIDENCY, &cnt->pc6))
+				return -1;
+		}
+		if (do_snb_cstates) {
+			if (get_msr(cnt->cpu, MSR_PKG_C2_RESIDENCY, &cnt->pc2))
+				return -1;
+			if (get_msr(cnt->cpu, MSR_PKG_C7_RESIDENCY, &cnt->pc7))
+				return -1;
+		}
 		if (extra_msr_offset)
-			cnt->extra_msr = get_msr(cnt->cpu, extra_msr_offset);
+			if (get_msr(cnt->cpu, extra_msr_offset, &cnt->extra_msr))
+				return -1;
 	}
+	return 0;
 }
 
 void print_nehalem_info(void)
@@ -475,7 +554,7 @@ void print_nehalem_info(void)
 	if (!do_nehalem_platform_info)
 		return;
 
-	msr = get_msr(0, MSR_NEHALEM_PLATFORM_INFO);
+	get_msr(0, MSR_NEHALEM_PLATFORM_INFO, &msr);
 
 	ratio = (msr >> 40) & 0xFF;
 	fprintf(stderr, "%d * %.0f = %.0f MHz max efficiency\n",
@@ -491,7 +570,7 @@ void print_nehalem_info(void)
 	if (!do_nehalem_turbo_ratio_limit)
 		return;
 
-	msr = get_msr(0, MSR_NEHALEM_TURBO_RATIO_LIMIT);
+	get_msr(0, MSR_NEHALEM_TURBO_RATIO_LIMIT, &msr);
 
 	ratio = (msr >> 24) & 0xFF;
 	if (ratio)
@@ -557,7 +636,8 @@ void insert_counters(struct counters **list,
 		return;
 	}
 
-	show_cpu = 1;	/* there is more than one CPU */
+	if (!summary_only)
+		show_cpu = 1;	/* there is more than one CPU */
 
 	/*
 	 * insert on front of list.
@@ -575,13 +655,15 @@ void insert_counters(struct counters **list,
 
 	while (prev->next && (prev->next->pkg < new->pkg)) {
 		prev = prev->next;
-		show_pkg = 1;	/* there is more than 1 package */
+		if (!summary_only)
+			show_pkg = 1;	/* there is more than 1 package */
 	}
 
 	while (prev->next && (prev->next->pkg == new->pkg)
 		&& (prev->next->core < new->core)) {
 		prev = prev->next;
-		show_core = 1;	/* there is more than 1 core */
+		if (!summary_only)
+			show_core = 1;	/* there is more than 1 core */
 	}
 
 	while (prev->next && (prev->next->pkg == new->pkg)
@@ -681,7 +763,7 @@ int get_core_id(int cpu)
 }
 
 /*
- * run func(index, cpu) on every cpu in /proc/stat
+ * run func(pkg, core, cpu) on every cpu in /proc/stat
  */
 
 int for_all_cpus(void (func)(int, int, int))
@@ -717,18 +799,18 @@ int for_all_cpus(void (func)(int, int, int))
 
 void re_initialize(void)
 {
-	printf("turbostat: topology changed, re-initializing.\n");
 	free_all_counters();
 	num_cpus = for_all_cpus(alloc_new_counters);
-	need_reinitialize = 0;
-	printf("num_cpus is now %d\n", num_cpus);
+	cpu_mask_uninit();
+	cpu_mask_init(num_cpus);
+	printf("turbostat: re-initialized with num_cpus %d\n", num_cpus);
 }
 
 void dummy(int pkg, int core, int cpu) { return; }
 /*
  * check to see if a cpu came on-line
  */
-void verify_num_cpus(void)
+int verify_num_cpus(void)
 {
 	int new_num_cpus;
 
@@ -738,8 +820,9 @@ void verify_num_cpus(void)
 		if (verbose)
 			printf("num_cpus was %d, is now  %d\n",
 				num_cpus, new_num_cpus);
-		need_reinitialize = 1;
+		return -1;
 	}
+	return 0;
 }
 
 void turbostat_loop()
@@ -749,25 +832,25 @@ restart:
 	gettimeofday(&tv_even, (struct timezone *)NULL);
 
 	while (1) {
-		verify_num_cpus();
-		if (need_reinitialize) {
+		if (verify_num_cpus()) {
 			re_initialize();
 			goto restart;
 		}
 		sleep(interval_sec);
-		get_counters(cnt_odd);
+		if (get_counters(cnt_odd)) {
+			re_initialize();
+			goto restart;
+		}
 		gettimeofday(&tv_odd, (struct timezone *)NULL);
-
 		compute_delta(cnt_odd, cnt_even, cnt_delta);
 		timersub(&tv_odd, &tv_even, &tv_delta);
 		compute_average(cnt_delta, cnt_average);
 		print_counters(cnt_delta);
-		if (need_reinitialize) {
+		sleep(interval_sec);
+		if (get_counters(cnt_even)) {
 			re_initialize();
 			goto restart;
 		}
-		sleep(interval_sec);
-		get_counters(cnt_even);
 		gettimeofday(&tv_even, (struct timezone *)NULL);
 		compute_delta(cnt_even, cnt_odd, cnt_delta);
 		timersub(&tv_even, &tv_odd, &tv_delta);
@@ -953,6 +1036,7 @@ void turbostat_init()
 	check_super_user();
 
 	num_cpus = for_all_cpus(alloc_new_counters);
+	cpu_mask_init(num_cpus);
 
 	if (verbose)
 		print_nehalem_info();
@@ -1005,8 +1089,11 @@ void cmdline(int argc, char **argv)
 
 	progname = argv[0];
 
-	while ((opt = getopt(argc, argv, "+vi:M:")) != -1) {
+	while ((opt = getopt(argc, argv, "+svi:M:")) != -1) {
 		switch (opt) {
+		case 's':
+			summary_only++;
+			break;
 		case 'v':
 			verbose++;
 			break;
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 4ec84018cc1..28bc57ee757 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -1,10 +1,15 @@
-TARGETS = breakpoints
+TARGETS = breakpoints vm
 
 all:
 	for TARGET in $(TARGETS); do \
 		make -C $$TARGET; \
 	done;
 
+run_tests: all
+	for TARGET in $(TARGETS); do \
+		make -C $$TARGET run_tests; \
+	done;
+
 clean:
 	for TARGET in $(TARGETS); do \
 		make -C $$TARGET clean; \
diff --git a/tools/testing/selftests/breakpoints/Makefile b/tools/testing/selftests/breakpoints/Makefile
index f362722cdce..931278035f5 100644
--- a/tools/testing/selftests/breakpoints/Makefile
+++ b/tools/testing/selftests/breakpoints/Makefile
@@ -11,10 +11,13 @@ endif
 
 all:
 ifeq ($(ARCH),x86)
-	gcc breakpoint_test.c -o run_test
+	gcc breakpoint_test.c -o breakpoint_test
 else
 	echo "Not an x86 target, can't build breakpoints selftests"
 endif
 
+run_tests:
+	./breakpoint_test
+
 clean:
-	rm -fr run_test
+	rm -fr breakpoint_test
diff --git a/tools/testing/selftests/run_tests b/tools/testing/selftests/run_tests
deleted file mode 100644
index 320718a4e6b..00000000000
--- a/tools/testing/selftests/run_tests
+++ /dev/null
@@ -1,8 +0,0 @@
-#!/bin/bash
-
-TARGETS=breakpoints
-
-for TARGET in $TARGETS
-do
-	$TARGET/run_test
-done
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
new file mode 100644
index 00000000000..b336b24aa6c
--- /dev/null
+++ b/tools/testing/selftests/vm/Makefile
@@ -0,0 +1,14 @@
+# Makefile for vm selftests
+
+CC = $(CROSS_COMPILE)gcc
+CFLAGS = -Wall -Wextra
+
+all: hugepage-mmap hugepage-shm  map_hugetlb
+%: %.c
+	$(CC) $(CFLAGS) -o $@ $^
+
+run_tests: all
+	/bin/sh ./run_vmtests
+
+clean:
+	$(RM) hugepage-mmap hugepage-shm  map_hugetlb
diff --git a/tools/testing/selftests/vm/hugepage-mmap.c b/tools/testing/selftests/vm/hugepage-mmap.c
new file mode 100644
index 00000000000..a10f310d236
--- /dev/null
+++ b/tools/testing/selftests/vm/hugepage-mmap.c
@@ -0,0 +1,92 @@
+/*
+ * hugepage-mmap:
+ *
+ * Example of using huge page memory in a user application using the mmap
+ * system call.  Before running this application, make sure that the
+ * administrator has mounted the hugetlbfs filesystem (on some directory
+ * like /mnt) using the command mount -t hugetlbfs nodev /mnt. In this
+ * example, the app is requesting memory of size 256MB that is backed by
+ * huge pages.
+ *
+ * For the ia64 architecture, the Linux kernel reserves Region number 4 for
+ * huge pages.  That means that if one requires a fixed address, a huge page
+ * aligned address starting with 0x800000... will be required.  If a fixed
+ * address is not required, the kernel will select an address in the proper
+ * range.
+ * Other architectures, such as ppc64, i386 or x86_64 are not so constrained.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+
+#define FILE_NAME "huge/hugepagefile"
+#define LENGTH (256UL*1024*1024)
+#define PROTECTION (PROT_READ | PROT_WRITE)
+
+/* Only ia64 requires this */
+#ifdef __ia64__
+#define ADDR (void *)(0x8000000000000000UL)
+#define FLAGS (MAP_SHARED | MAP_FIXED)
+#else
+#define ADDR (void *)(0x0UL)
+#define FLAGS (MAP_SHARED)
+#endif
+
+static void check_bytes(char *addr)
+{
+	printf("First hex is %x\n", *((unsigned int *)addr));
+}
+
+static void write_bytes(char *addr)
+{
+	unsigned long i;
+
+	for (i = 0; i < LENGTH; i++)
+		*(addr + i) = (char)i;
+}
+
+static int read_bytes(char *addr)
+{
+	unsigned long i;
+
+	check_bytes(addr);
+	for (i = 0; i < LENGTH; i++)
+		if (*(addr + i) != (char)i) {
+			printf("Mismatch at %lu\n", i);
+			return 1;
+		}
+	return 0;
+}
+
+int main(void)
+{
+	void *addr;
+	int fd, ret;
+
+	fd = open(FILE_NAME, O_CREAT | O_RDWR, 0755);
+	if (fd < 0) {
+		perror("Open failed");
+		exit(1);
+	}
+
+	addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, fd, 0);
+	if (addr == MAP_FAILED) {
+		perror("mmap");
+		unlink(FILE_NAME);
+		exit(1);
+	}
+
+	printf("Returned address is %p\n", addr);
+	check_bytes(addr);
+	write_bytes(addr);
+	ret = read_bytes(addr);
+
+	munmap(addr, LENGTH);
+	close(fd);
+	unlink(FILE_NAME);
+
+	return ret;
+}
diff --git a/tools/testing/selftests/vm/hugepage-shm.c b/tools/testing/selftests/vm/hugepage-shm.c
new file mode 100644
index 00000000000..0d0ef4fc0c0
--- /dev/null
+++ b/tools/testing/selftests/vm/hugepage-shm.c
@@ -0,0 +1,100 @@
+/*
+ * hugepage-shm:
+ *
+ * Example of using huge page memory in a user application using Sys V shared
+ * memory system calls.  In this example the app is requesting 256MB of
+ * memory that is backed by huge pages.  The application uses the flag
+ * SHM_HUGETLB in the shmget system call to inform the kernel that it is
+ * requesting huge pages.
+ *
+ * For the ia64 architecture, the Linux kernel reserves Region number 4 for
+ * huge pages.  That means that if one requires a fixed address, a huge page
+ * aligned address starting with 0x800000... will be required.  If a fixed
+ * address is not required, the kernel will select an address in the proper
+ * range.
+ * Other architectures, such as ppc64, i386 or x86_64 are not so constrained.
+ *
+ * Note: The default shared memory limit is quite low on many kernels,
+ * you may need to increase it via:
+ *
+ * echo 268435456 > /proc/sys/kernel/shmmax
+ *
+ * This will increase the maximum size per shared memory segment to 256MB.
+ * The other limit that you will hit eventually is shmall which is the
+ * total amount of shared memory in pages. To set it to 16GB on a system
+ * with a 4kB pagesize do:
+ *
+ * echo 4194304 > /proc/sys/kernel/shmall
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <sys/types.h>
+#include <sys/ipc.h>
+#include <sys/shm.h>
+#include <sys/mman.h>
+
+#ifndef SHM_HUGETLB
+#define SHM_HUGETLB 04000
+#endif
+
+#define LENGTH (256UL*1024*1024)
+
+#define dprintf(x)  printf(x)
+
+/* Only ia64 requires this */
+#ifdef __ia64__
+#define ADDR (void *)(0x8000000000000000UL)
+#define SHMAT_FLAGS (SHM_RND)
+#else
+#define ADDR (void *)(0x0UL)
+#define SHMAT_FLAGS (0)
+#endif
+
+int main(void)
+{
+	int shmid;
+	unsigned long i;
+	char *shmaddr;
+
+	shmid = shmget(2, LENGTH, SHM_HUGETLB | IPC_CREAT | SHM_R | SHM_W);
+	if (shmid < 0) {
+		perror("shmget");
+		exit(1);
+	}
+	printf("shmid: 0x%x\n", shmid);
+
+	shmaddr = shmat(shmid, ADDR, SHMAT_FLAGS);
+	if (shmaddr == (char *)-1) {
+		perror("Shared memory attach failure");
+		shmctl(shmid, IPC_RMID, NULL);
+		exit(2);
+	}
+	printf("shmaddr: %p\n", shmaddr);
+
+	dprintf("Starting the writes:\n");
+	for (i = 0; i < LENGTH; i++) {
+		shmaddr[i] = (char)(i);
+		if (!(i % (1024 * 1024)))
+			dprintf(".");
+	}
+	dprintf("\n");
+
+	dprintf("Starting the Check...");
+	for (i = 0; i < LENGTH; i++)
+		if (shmaddr[i] != (char)i) {
+			printf("\nIndex %lu mismatched\n", i);
+			exit(3);
+		}
+	dprintf("Done.\n");
+
+	if (shmdt((const void *)shmaddr) != 0) {
+		perror("Detach failure");
+		shmctl(shmid, IPC_RMID, NULL);
+		exit(4);
+	}
+
+	shmctl(shmid, IPC_RMID, NULL);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/vm/map_hugetlb.c b/tools/testing/selftests/vm/map_hugetlb.c
new file mode 100644
index 00000000000..ac56639dd4a
--- /dev/null
+++ b/tools/testing/selftests/vm/map_hugetlb.c
@@ -0,0 +1,79 @@
+/*
+ * Example of using hugepage memory in a user application using the mmap
+ * system call with MAP_HUGETLB flag.  Before running this program make
+ * sure the administrator has allocated enough default sized huge pages
+ * to cover the 256 MB allocation.
+ *
+ * For ia64 architecture, Linux kernel reserves Region number 4 for hugepages.
+ * That means the addresses starting with 0x800000... will need to be
+ * specified.  Specifying a fixed address is not required on ppc64, i386
+ * or x86_64.
+ */
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+
+#define LENGTH (256UL*1024*1024)
+#define PROTECTION (PROT_READ | PROT_WRITE)
+
+#ifndef MAP_HUGETLB
+#define MAP_HUGETLB 0x40000 /* arch specific */
+#endif
+
+/* Only ia64 requires this */
+#ifdef __ia64__
+#define ADDR (void *)(0x8000000000000000UL)
+#define FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB | MAP_FIXED)
+#else
+#define ADDR (void *)(0x0UL)
+#define FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB)
+#endif
+
+static void check_bytes(char *addr)
+{
+	printf("First hex is %x\n", *((unsigned int *)addr));
+}
+
+static void write_bytes(char *addr)
+{
+	unsigned long i;
+
+	for (i = 0; i < LENGTH; i++)
+		*(addr + i) = (char)i;
+}
+
+static int read_bytes(char *addr)
+{
+	unsigned long i;
+
+	check_bytes(addr);
+	for (i = 0; i < LENGTH; i++)
+		if (*(addr + i) != (char)i) {
+			printf("Mismatch at %lu\n", i);
+			return 1;
+		}
+	return 0;
+}
+
+int main(void)
+{
+	void *addr;
+	int ret;
+
+	addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, 0, 0);
+	if (addr == MAP_FAILED) {
+		perror("mmap");
+		exit(1);
+	}
+
+	printf("Returned address is %p\n", addr);
+	check_bytes(addr);
+	write_bytes(addr);
+	ret = read_bytes(addr);
+
+	munmap(addr, LENGTH);
+
+	return ret;
+}
diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests
new file mode 100644
index 00000000000..8b40bd5e5cc
--- /dev/null
+++ b/tools/testing/selftests/vm/run_vmtests
@@ -0,0 +1,77 @@
+#!/bin/bash
+#please run as root
+
+#we need 256M, below is the size in kB
+needmem=262144
+mnt=./huge
+
+#get pagesize and freepages from /proc/meminfo
+while read name size unit; do
+	if [ "$name" = "HugePages_Free:" ]; then
+		freepgs=$size
+	fi
+	if [ "$name" = "Hugepagesize:" ]; then
+		pgsize=$size
+	fi
+done < /proc/meminfo
+
+#set proper nr_hugepages
+if [ -n "$freepgs" ] && [ -n "$pgsize" ]; then
+	nr_hugepgs=`cat /proc/sys/vm/nr_hugepages`
+	needpgs=`expr $needmem / $pgsize`
+	if [ $freepgs -lt $needpgs ]; then
+		lackpgs=$(( $needpgs - $freepgs ))
+		echo $(( $lackpgs + $nr_hugepgs )) > /proc/sys/vm/nr_hugepages
+		if [ $? -ne 0 ]; then
+			echo "Please run this test as root"
+			exit 1
+		fi
+	fi
+else
+	echo "no hugetlbfs support in kernel?"
+	exit 1
+fi
+
+mkdir $mnt
+mount -t hugetlbfs none $mnt
+
+echo "--------------------"
+echo "runing hugepage-mmap"
+echo "--------------------"
+./hugepage-mmap
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+else
+	echo "[PASS]"
+fi
+
+shmmax=`cat /proc/sys/kernel/shmmax`
+shmall=`cat /proc/sys/kernel/shmall`
+echo 268435456 > /proc/sys/kernel/shmmax
+echo 4194304 > /proc/sys/kernel/shmall
+echo "--------------------"
+echo "runing hugepage-shm"
+echo "--------------------"
+./hugepage-shm
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+else
+	echo "[PASS]"
+fi
+echo $shmmax > /proc/sys/kernel/shmmax
+echo $shmall > /proc/sys/kernel/shmall
+
+echo "--------------------"
+echo "runing map_hugetlb"
+echo "--------------------"
+./map_hugetlb
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+else
+	echo "[PASS]"
+fi
+
+#cleanup
+umount $mnt
+rm -rf $mnt
+echo $nr_hugepgs > /proc/sys/vm/nr_hugepages
diff --git a/tools/vm/Makefile b/tools/vm/Makefile
new file mode 100644
index 00000000000..8e30e5c40f8
--- /dev/null
+++ b/tools/vm/Makefile
@@ -0,0 +1,11 @@
+# Makefile for vm tools
+
+CC = $(CROSS_COMPILE)gcc
+CFLAGS = -Wall -Wextra
+
+all: page-types slabinfo
+%: %.c
+	$(CC) $(CFLAGS) -o $@ $^
+
+clean:
+	$(RM) page-types slabinfo
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
new file mode 100644
index 00000000000..7dab7b25b5c
--- /dev/null
+++ b/tools/vm/page-types.c
@@ -0,0 +1,1102 @@
+/*
+ * page-types: Tool for querying page flags
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; version 2.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should find a copy of v2 of the GNU General Public License somewhere on
+ * your Linux system; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * Copyright (C) 2009 Intel corporation
+ *
+ * Authors: Wu Fengguang <fengguang.wu@intel.com>
+ */
+
+#define _LARGEFILE64_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdint.h>
+#include <stdarg.h>
+#include <string.h>
+#include <getopt.h>
+#include <limits.h>
+#include <assert.h>
+#include <sys/types.h>
+#include <sys/errno.h>
+#include <sys/fcntl.h>
+#include <sys/mount.h>
+#include <sys/statfs.h>
+#include "../../include/linux/magic.h"
+
+
+#ifndef MAX_PATH
+# define MAX_PATH 256
+#endif
+
+#ifndef STR
+# define _STR(x) #x
+# define STR(x) _STR(x)
+#endif
+
+/*
+ * pagemap kernel ABI bits
+ */
+
+#define PM_ENTRY_BYTES      sizeof(uint64_t)
+#define PM_STATUS_BITS      3
+#define PM_STATUS_OFFSET    (64 - PM_STATUS_BITS)
+#define PM_STATUS_MASK      (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET)
+#define PM_STATUS(nr)       (((nr) << PM_STATUS_OFFSET) & PM_STATUS_MASK)
+#define PM_PSHIFT_BITS      6
+#define PM_PSHIFT_OFFSET    (PM_STATUS_OFFSET - PM_PSHIFT_BITS)
+#define PM_PSHIFT_MASK      (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET)
+#define PM_PSHIFT(x)        (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
+#define PM_PFRAME_MASK      ((1LL << PM_PSHIFT_OFFSET) - 1)
+#define PM_PFRAME(x)        ((x) & PM_PFRAME_MASK)
+
+#define PM_PRESENT          PM_STATUS(4LL)
+#define PM_SWAP             PM_STATUS(2LL)
+
+
+/*
+ * kernel page flags
+ */
+
+#define KPF_BYTES		8
+#define PROC_KPAGEFLAGS		"/proc/kpageflags"
+
+/* copied from kpageflags_read() */
+#define KPF_LOCKED		0
+#define KPF_ERROR		1
+#define KPF_REFERENCED		2
+#define KPF_UPTODATE		3
+#define KPF_DIRTY		4
+#define KPF_LRU			5
+#define KPF_ACTIVE		6
+#define KPF_SLAB		7
+#define KPF_WRITEBACK		8
+#define KPF_RECLAIM		9
+#define KPF_BUDDY		10
+
+/* [11-20] new additions in 2.6.31 */
+#define KPF_MMAP		11
+#define KPF_ANON		12
+#define KPF_SWAPCACHE		13
+#define KPF_SWAPBACKED		14
+#define KPF_COMPOUND_HEAD	15
+#define KPF_COMPOUND_TAIL	16
+#define KPF_HUGE		17
+#define KPF_UNEVICTABLE		18
+#define KPF_HWPOISON		19
+#define KPF_NOPAGE		20
+#define KPF_KSM			21
+#define KPF_THP			22
+
+/* [32-] kernel hacking assistances */
+#define KPF_RESERVED		32
+#define KPF_MLOCKED		33
+#define KPF_MAPPEDTODISK	34
+#define KPF_PRIVATE		35
+#define KPF_PRIVATE_2		36
+#define KPF_OWNER_PRIVATE	37
+#define KPF_ARCH		38
+#define KPF_UNCACHED		39
+
+/* [48-] take some arbitrary free slots for expanding overloaded flags
+ * not part of kernel API
+ */
+#define KPF_READAHEAD		48
+#define KPF_SLOB_FREE		49
+#define KPF_SLUB_FROZEN		50
+#define KPF_SLUB_DEBUG		51
+
+#define KPF_ALL_BITS		((uint64_t)~0ULL)
+#define KPF_HACKERS_BITS	(0xffffULL << 32)
+#define KPF_OVERLOADED_BITS	(0xffffULL << 48)
+#define BIT(name)		(1ULL << KPF_##name)
+#define BITS_COMPOUND		(BIT(COMPOUND_HEAD) | BIT(COMPOUND_TAIL))
+
+static const char * const page_flag_names[] = {
+	[KPF_LOCKED]		= "L:locked",
+	[KPF_ERROR]		= "E:error",
+	[KPF_REFERENCED]	= "R:referenced",
+	[KPF_UPTODATE]		= "U:uptodate",
+	[KPF_DIRTY]		= "D:dirty",
+	[KPF_LRU]		= "l:lru",
+	[KPF_ACTIVE]		= "A:active",
+	[KPF_SLAB]		= "S:slab",
+	[KPF_WRITEBACK]		= "W:writeback",
+	[KPF_RECLAIM]		= "I:reclaim",
+	[KPF_BUDDY]		= "B:buddy",
+
+	[KPF_MMAP]		= "M:mmap",
+	[KPF_ANON]		= "a:anonymous",
+	[KPF_SWAPCACHE]		= "s:swapcache",
+	[KPF_SWAPBACKED]	= "b:swapbacked",
+	[KPF_COMPOUND_HEAD]	= "H:compound_head",
+	[KPF_COMPOUND_TAIL]	= "T:compound_tail",
+	[KPF_HUGE]		= "G:huge",
+	[KPF_UNEVICTABLE]	= "u:unevictable",
+	[KPF_HWPOISON]		= "X:hwpoison",
+	[KPF_NOPAGE]		= "n:nopage",
+	[KPF_KSM]		= "x:ksm",
+	[KPF_THP]		= "t:thp",
+
+	[KPF_RESERVED]		= "r:reserved",
+	[KPF_MLOCKED]		= "m:mlocked",
+	[KPF_MAPPEDTODISK]	= "d:mappedtodisk",
+	[KPF_PRIVATE]		= "P:private",
+	[KPF_PRIVATE_2]		= "p:private_2",
+	[KPF_OWNER_PRIVATE]	= "O:owner_private",
+	[KPF_ARCH]		= "h:arch",
+	[KPF_UNCACHED]		= "c:uncached",
+
+	[KPF_READAHEAD]		= "I:readahead",
+	[KPF_SLOB_FREE]		= "P:slob_free",
+	[KPF_SLUB_FROZEN]	= "A:slub_frozen",
+	[KPF_SLUB_DEBUG]	= "E:slub_debug",
+};
+
+
+static const char * const debugfs_known_mountpoints[] = {
+	"/sys/kernel/debug",
+	"/debug",
+	0,
+};
+
+/*
+ * data structures
+ */
+
+static int		opt_raw;	/* for kernel developers */
+static int		opt_list;	/* list pages (in ranges) */
+static int		opt_no_summary;	/* don't show summary */
+static pid_t		opt_pid;	/* process to walk */
+
+#define MAX_ADDR_RANGES	1024
+static int		nr_addr_ranges;
+static unsigned long	opt_offset[MAX_ADDR_RANGES];
+static unsigned long	opt_size[MAX_ADDR_RANGES];
+
+#define MAX_VMAS	10240
+static int		nr_vmas;
+static unsigned long	pg_start[MAX_VMAS];
+static unsigned long	pg_end[MAX_VMAS];
+
+#define MAX_BIT_FILTERS	64
+static int		nr_bit_filters;
+static uint64_t		opt_mask[MAX_BIT_FILTERS];
+static uint64_t		opt_bits[MAX_BIT_FILTERS];
+
+static int		page_size;
+
+static int		pagemap_fd;
+static int		kpageflags_fd;
+
+static int		opt_hwpoison;
+static int		opt_unpoison;
+
+static char		hwpoison_debug_fs[MAX_PATH+1];
+static int		hwpoison_inject_fd;
+static int		hwpoison_forget_fd;
+
+#define HASH_SHIFT	13
+#define HASH_SIZE	(1 << HASH_SHIFT)
+#define HASH_MASK	(HASH_SIZE - 1)
+#define HASH_KEY(flags)	(flags & HASH_MASK)
+
+static unsigned long	total_pages;
+static unsigned long	nr_pages[HASH_SIZE];
+static uint64_t		page_flags[HASH_SIZE];
+
+
+/*
+ * helper functions
+ */
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+
+#define min_t(type, x, y) ({			\
+	type __min1 = (x);			\
+	type __min2 = (y);			\
+	__min1 < __min2 ? __min1 : __min2; })
+
+#define max_t(type, x, y) ({			\
+	type __max1 = (x);			\
+	type __max2 = (y);			\
+	__max1 > __max2 ? __max1 : __max2; })
+
+static unsigned long pages2mb(unsigned long pages)
+{
+	return (pages * page_size) >> 20;
+}
+
+static void fatal(const char *x, ...)
+{
+	va_list ap;
+
+	va_start(ap, x);
+	vfprintf(stderr, x, ap);
+	va_end(ap);
+	exit(EXIT_FAILURE);
+}
+
+static int checked_open(const char *pathname, int flags)
+{
+	int fd = open(pathname, flags);
+
+	if (fd < 0) {
+		perror(pathname);
+		exit(EXIT_FAILURE);
+	}
+
+	return fd;
+}
+
+/*
+ * pagemap/kpageflags routines
+ */
+
+static unsigned long do_u64_read(int fd, char *name,
+				 uint64_t *buf,
+				 unsigned long index,
+				 unsigned long count)
+{
+	long bytes;
+
+	if (index > ULONG_MAX / 8)
+		fatal("index overflow: %lu\n", index);
+
+	if (lseek(fd, index * 8, SEEK_SET) < 0) {
+		perror(name);
+		exit(EXIT_FAILURE);
+	}
+
+	bytes = read(fd, buf, count * 8);
+	if (bytes < 0) {
+		perror(name);
+		exit(EXIT_FAILURE);
+	}
+	if (bytes % 8)
+		fatal("partial read: %lu bytes\n", bytes);
+
+	return bytes / 8;
+}
+
+static unsigned long kpageflags_read(uint64_t *buf,
+				     unsigned long index,
+				     unsigned long pages)
+{
+	return do_u64_read(kpageflags_fd, PROC_KPAGEFLAGS, buf, index, pages);
+}
+
+static unsigned long pagemap_read(uint64_t *buf,
+				  unsigned long index,
+				  unsigned long pages)
+{
+	return do_u64_read(pagemap_fd, "/proc/pid/pagemap", buf, index, pages);
+}
+
+static unsigned long pagemap_pfn(uint64_t val)
+{
+	unsigned long pfn;
+
+	if (val & PM_PRESENT)
+		pfn = PM_PFRAME(val);
+	else
+		pfn = 0;
+
+	return pfn;
+}
+
+
+/*
+ * page flag names
+ */
+
+static char *page_flag_name(uint64_t flags)
+{
+	static char buf[65];
+	int present;
+	int i, j;
+
+	for (i = 0, j = 0; i < ARRAY_SIZE(page_flag_names); i++) {
+		present = (flags >> i) & 1;
+		if (!page_flag_names[i]) {
+			if (present)
+				fatal("unknown flag bit %d\n", i);
+			continue;
+		}
+		buf[j++] = present ? page_flag_names[i][0] : '_';
+	}
+
+	return buf;
+}
+
+static char *page_flag_longname(uint64_t flags)
+{
+	static char buf[1024];
+	int i, n;
+
+	for (i = 0, n = 0; i < ARRAY_SIZE(page_flag_names); i++) {
+		if (!page_flag_names[i])
+			continue;
+		if ((flags >> i) & 1)
+			n += snprintf(buf + n, sizeof(buf) - n, "%s,",
+					page_flag_names[i] + 2);
+	}
+	if (n)
+		n--;
+	buf[n] = '\0';
+
+	return buf;
+}
+
+
+/*
+ * page list and summary
+ */
+
+static void show_page_range(unsigned long voffset,
+			    unsigned long offset, uint64_t flags)
+{
+	static uint64_t      flags0;
+	static unsigned long voff;
+	static unsigned long index;
+	static unsigned long count;
+
+	if (flags == flags0 && offset == index + count &&
+	    (!opt_pid || voffset == voff + count)) {
+		count++;
+		return;
+	}
+
+	if (count) {
+		if (opt_pid)
+			printf("%lx\t", voff);
+		printf("%lx\t%lx\t%s\n",
+				index, count, page_flag_name(flags0));
+	}
+
+	flags0 = flags;
+	index  = offset;
+	voff   = voffset;
+	count  = 1;
+}
+
+static void show_page(unsigned long voffset,
+		      unsigned long offset, uint64_t flags)
+{
+	if (opt_pid)
+		printf("%lx\t", voffset);
+	printf("%lx\t%s\n", offset, page_flag_name(flags));
+}
+
+static void show_summary(void)
+{
+	int i;
+
+	printf("             flags\tpage-count       MB"
+		"  symbolic-flags\t\t\tlong-symbolic-flags\n");
+
+	for (i = 0; i < ARRAY_SIZE(nr_pages); i++) {
+		if (nr_pages[i])
+			printf("0x%016llx\t%10lu %8lu  %s\t%s\n",
+				(unsigned long long)page_flags[i],
+				nr_pages[i],
+				pages2mb(nr_pages[i]),
+				page_flag_name(page_flags[i]),
+				page_flag_longname(page_flags[i]));
+	}
+
+	printf("             total\t%10lu %8lu\n",
+			total_pages, pages2mb(total_pages));
+}
+
+
+/*
+ * page flag filters
+ */
+
+static int bit_mask_ok(uint64_t flags)
+{
+	int i;
+
+	for (i = 0; i < nr_bit_filters; i++) {
+		if (opt_bits[i] == KPF_ALL_BITS) {
+			if ((flags & opt_mask[i]) == 0)
+				return 0;
+		} else {
+			if ((flags & opt_mask[i]) != opt_bits[i])
+				return 0;
+		}
+	}
+
+	return 1;
+}
+
+static uint64_t expand_overloaded_flags(uint64_t flags)
+{
+	/* SLOB/SLUB overload several page flags */
+	if (flags & BIT(SLAB)) {
+		if (flags & BIT(PRIVATE))
+			flags ^= BIT(PRIVATE) | BIT(SLOB_FREE);
+		if (flags & BIT(ACTIVE))
+			flags ^= BIT(ACTIVE) | BIT(SLUB_FROZEN);
+		if (flags & BIT(ERROR))
+			flags ^= BIT(ERROR) | BIT(SLUB_DEBUG);
+	}
+
+	/* PG_reclaim is overloaded as PG_readahead in the read path */
+	if ((flags & (BIT(RECLAIM) | BIT(WRITEBACK))) == BIT(RECLAIM))
+		flags ^= BIT(RECLAIM) | BIT(READAHEAD);
+
+	return flags;
+}
+
+static uint64_t well_known_flags(uint64_t flags)
+{
+	/* hide flags intended only for kernel hacker */
+	flags &= ~KPF_HACKERS_BITS;
+
+	/* hide non-hugeTLB compound pages */
+	if ((flags & BITS_COMPOUND) && !(flags & BIT(HUGE)))
+		flags &= ~BITS_COMPOUND;
+
+	return flags;
+}
+
+static uint64_t kpageflags_flags(uint64_t flags)
+{
+	flags = expand_overloaded_flags(flags);
+
+	if (!opt_raw)
+		flags = well_known_flags(flags);
+
+	return flags;
+}
+
+/* verify that a mountpoint is actually a debugfs instance */
+static int debugfs_valid_mountpoint(const char *debugfs)
+{
+	struct statfs st_fs;
+
+	if (statfs(debugfs, &st_fs) < 0)
+		return -ENOENT;
+	else if (st_fs.f_type != (long) DEBUGFS_MAGIC)
+		return -ENOENT;
+
+	return 0;
+}
+
+/* find the path to the mounted debugfs */
+static const char *debugfs_find_mountpoint(void)
+{
+	const char **ptr;
+	char type[100];
+	FILE *fp;
+
+	ptr = debugfs_known_mountpoints;
+	while (*ptr) {
+		if (debugfs_valid_mountpoint(*ptr) == 0) {
+			strcpy(hwpoison_debug_fs, *ptr);
+			return hwpoison_debug_fs;
+		}
+		ptr++;
+	}
+
+	/* give up and parse /proc/mounts */
+	fp = fopen("/proc/mounts", "r");
+	if (fp == NULL)
+		perror("Can't open /proc/mounts for read");
+
+	while (fscanf(fp, "%*s %"
+		      STR(MAX_PATH)
+		      "s %99s %*s %*d %*d\n",
+		      hwpoison_debug_fs, type) == 2) {
+		if (strcmp(type, "debugfs") == 0)
+			break;
+	}
+	fclose(fp);
+
+	if (strcmp(type, "debugfs") != 0)
+		return NULL;
+
+	return hwpoison_debug_fs;
+}
+
+/* mount the debugfs somewhere if it's not mounted */
+
+static void debugfs_mount(void)
+{
+	const char **ptr;
+
+	/* see if it's already mounted */
+	if (debugfs_find_mountpoint())
+		return;
+
+	ptr = debugfs_known_mountpoints;
+	while (*ptr) {
+		if (mount(NULL, *ptr, "debugfs", 0, NULL) == 0) {
+			/* save the mountpoint */
+			strcpy(hwpoison_debug_fs, *ptr);
+			break;
+		}
+		ptr++;
+	}
+
+	if (*ptr == NULL) {
+		perror("mount debugfs");
+		exit(EXIT_FAILURE);
+	}
+}
+
+/*
+ * page actions
+ */
+
+static void prepare_hwpoison_fd(void)
+{
+	char buf[MAX_PATH + 1];
+
+	debugfs_mount();
+
+	if (opt_hwpoison && !hwpoison_inject_fd) {
+		snprintf(buf, MAX_PATH, "%s/hwpoison/corrupt-pfn",
+			hwpoison_debug_fs);
+		hwpoison_inject_fd = checked_open(buf, O_WRONLY);
+	}
+
+	if (opt_unpoison && !hwpoison_forget_fd) {
+		snprintf(buf, MAX_PATH, "%s/hwpoison/unpoison-pfn",
+			hwpoison_debug_fs);
+		hwpoison_forget_fd = checked_open(buf, O_WRONLY);
+	}
+}
+
+static int hwpoison_page(unsigned long offset)
+{
+	char buf[100];
+	int len;
+
+	len = sprintf(buf, "0x%lx\n", offset);
+	len = write(hwpoison_inject_fd, buf, len);
+	if (len < 0) {
+		perror("hwpoison inject");
+		return len;
+	}
+	return 0;
+}
+
+static int unpoison_page(unsigned long offset)
+{
+	char buf[100];
+	int len;
+
+	len = sprintf(buf, "0x%lx\n", offset);
+	len = write(hwpoison_forget_fd, buf, len);
+	if (len < 0) {
+		perror("hwpoison forget");
+		return len;
+	}
+	return 0;
+}
+
+/*
+ * page frame walker
+ */
+
+static int hash_slot(uint64_t flags)
+{
+	int k = HASH_KEY(flags);
+	int i;
+
+	/* Explicitly reserve slot 0 for flags 0: the following logic
+	 * cannot distinguish an unoccupied slot from slot (flags==0).
+	 */
+	if (flags == 0)
+		return 0;
+
+	/* search through the remaining (HASH_SIZE-1) slots */
+	for (i = 1; i < ARRAY_SIZE(page_flags); i++, k++) {
+		if (!k || k >= ARRAY_SIZE(page_flags))
+			k = 1;
+		if (page_flags[k] == 0) {
+			page_flags[k] = flags;
+			return k;
+		}
+		if (page_flags[k] == flags)
+			return k;
+	}
+
+	fatal("hash table full: bump up HASH_SHIFT?\n");
+	exit(EXIT_FAILURE);
+}
+
+static void add_page(unsigned long voffset,
+		     unsigned long offset, uint64_t flags)
+{
+	flags = kpageflags_flags(flags);
+
+	if (!bit_mask_ok(flags))
+		return;
+
+	if (opt_hwpoison)
+		hwpoison_page(offset);
+	if (opt_unpoison)
+		unpoison_page(offset);
+
+	if (opt_list == 1)
+		show_page_range(voffset, offset, flags);
+	else if (opt_list == 2)
+		show_page(voffset, offset, flags);
+
+	nr_pages[hash_slot(flags)]++;
+	total_pages++;
+}
+
+#define KPAGEFLAGS_BATCH	(64 << 10)	/* 64k pages */
+static void walk_pfn(unsigned long voffset,
+		     unsigned long index,
+		     unsigned long count)
+{
+	uint64_t buf[KPAGEFLAGS_BATCH];
+	unsigned long batch;
+	long pages;
+	unsigned long i;
+
+	while (count) {
+		batch = min_t(unsigned long, count, KPAGEFLAGS_BATCH);
+		pages = kpageflags_read(buf, index, batch);
+		if (pages == 0)
+			break;
+
+		for (i = 0; i < pages; i++)
+			add_page(voffset + i, index + i, buf[i]);
+
+		index += pages;
+		count -= pages;
+	}
+}
+
+#define PAGEMAP_BATCH	(64 << 10)
+static void walk_vma(unsigned long index, unsigned long count)
+{
+	uint64_t buf[PAGEMAP_BATCH];
+	unsigned long batch;
+	unsigned long pages;
+	unsigned long pfn;
+	unsigned long i;
+
+	while (count) {
+		batch = min_t(unsigned long, count, PAGEMAP_BATCH);
+		pages = pagemap_read(buf, index, batch);
+		if (pages == 0)
+			break;
+
+		for (i = 0; i < pages; i++) {
+			pfn = pagemap_pfn(buf[i]);
+			if (pfn)
+				walk_pfn(index + i, pfn, 1);
+		}
+
+		index += pages;
+		count -= pages;
+	}
+}
+
+static void walk_task(unsigned long index, unsigned long count)
+{
+	const unsigned long end = index + count;
+	unsigned long start;
+	int i = 0;
+
+	while (index < end) {
+
+		while (pg_end[i] <= index)
+			if (++i >= nr_vmas)
+				return;
+		if (pg_start[i] >= end)
+			return;
+
+		start = max_t(unsigned long, pg_start[i], index);
+		index = min_t(unsigned long, pg_end[i], end);
+
+		assert(start < index);
+		walk_vma(start, index - start);
+	}
+}
+
+static void add_addr_range(unsigned long offset, unsigned long size)
+{
+	if (nr_addr_ranges >= MAX_ADDR_RANGES)
+		fatal("too many addr ranges\n");
+
+	opt_offset[nr_addr_ranges] = offset;
+	opt_size[nr_addr_ranges] = min_t(unsigned long, size, ULONG_MAX-offset);
+	nr_addr_ranges++;
+}
+
+static void walk_addr_ranges(void)
+{
+	int i;
+
+	kpageflags_fd = checked_open(PROC_KPAGEFLAGS, O_RDONLY);
+
+	if (!nr_addr_ranges)
+		add_addr_range(0, ULONG_MAX);
+
+	for (i = 0; i < nr_addr_ranges; i++)
+		if (!opt_pid)
+			walk_pfn(0, opt_offset[i], opt_size[i]);
+		else
+			walk_task(opt_offset[i], opt_size[i]);
+
+	close(kpageflags_fd);
+}
+
+
+/*
+ * user interface
+ */
+
+static const char *page_flag_type(uint64_t flag)
+{
+	if (flag & KPF_HACKERS_BITS)
+		return "(r)";
+	if (flag & KPF_OVERLOADED_BITS)
+		return "(o)";
+	return "   ";
+}
+
+static void usage(void)
+{
+	int i, j;
+
+	printf(
+"page-types [options]\n"
+"            -r|--raw                   Raw mode, for kernel developers\n"
+"            -d|--describe flags        Describe flags\n"
+"            -a|--addr    addr-spec     Walk a range of pages\n"
+"            -b|--bits    bits-spec     Walk pages with specified bits\n"
+"            -p|--pid     pid           Walk process address space\n"
+#if 0 /* planned features */
+"            -f|--file    filename      Walk file address space\n"
+#endif
+"            -l|--list                  Show page details in ranges\n"
+"            -L|--list-each             Show page details one by one\n"
+"            -N|--no-summary            Don't show summary info\n"
+"            -X|--hwpoison              hwpoison pages\n"
+"            -x|--unpoison              unpoison pages\n"
+"            -h|--help                  Show this usage message\n"
+"flags:\n"
+"            0x10                       bitfield format, e.g.\n"
+"            anon                       bit-name, e.g.\n"
+"            0x10,anon                  comma-separated list, e.g.\n"
+"addr-spec:\n"
+"            N                          one page at offset N (unit: pages)\n"
+"            N+M                        pages range from N to N+M-1\n"
+"            N,M                        pages range from N to M-1\n"
+"            N,                         pages range from N to end\n"
+"            ,M                         pages range from 0 to M-1\n"
+"bits-spec:\n"
+"            bit1,bit2                  (flags & (bit1|bit2)) != 0\n"
+"            bit1,bit2=bit1             (flags & (bit1|bit2)) == bit1\n"
+"            bit1,~bit2                 (flags & (bit1|bit2)) == bit1\n"
+"            =bit1,bit2                 flags == (bit1|bit2)\n"
+"bit-names:\n"
+	);
+
+	for (i = 0, j = 0; i < ARRAY_SIZE(page_flag_names); i++) {
+		if (!page_flag_names[i])
+			continue;
+		printf("%16s%s", page_flag_names[i] + 2,
+				 page_flag_type(1ULL << i));
+		if (++j > 3) {
+			j = 0;
+			putchar('\n');
+		}
+	}
+	printf("\n                                   "
+		"(r) raw mode bits  (o) overloaded bits\n");
+}
+
+static unsigned long long parse_number(const char *str)
+{
+	unsigned long long n;
+
+	n = strtoll(str, NULL, 0);
+
+	if (n == 0 && str[0] != '0')
+		fatal("invalid name or number: %s\n", str);
+
+	return n;
+}
+
+static void parse_pid(const char *str)
+{
+	FILE *file;
+	char buf[5000];
+
+	opt_pid = parse_number(str);
+
+	sprintf(buf, "/proc/%d/pagemap", opt_pid);
+	pagemap_fd = checked_open(buf, O_RDONLY);
+
+	sprintf(buf, "/proc/%d/maps", opt_pid);
+	file = fopen(buf, "r");
+	if (!file) {
+		perror(buf);
+		exit(EXIT_FAILURE);
+	}
+
+	while (fgets(buf, sizeof(buf), file) != NULL) {
+		unsigned long vm_start;
+		unsigned long vm_end;
+		unsigned long long pgoff;
+		int major, minor;
+		char r, w, x, s;
+		unsigned long ino;
+		int n;
+
+		n = sscanf(buf, "%lx-%lx %c%c%c%c %llx %x:%x %lu",
+			   &vm_start,
+			   &vm_end,
+			   &r, &w, &x, &s,
+			   &pgoff,
+			   &major, &minor,
+			   &ino);
+		if (n < 10) {
+			fprintf(stderr, "unexpected line: %s\n", buf);
+			continue;
+		}
+		pg_start[nr_vmas] = vm_start / page_size;
+		pg_end[nr_vmas] = vm_end / page_size;
+		if (++nr_vmas >= MAX_VMAS) {
+			fprintf(stderr, "too many VMAs\n");
+			break;
+		}
+	}
+	fclose(file);
+}
+
+static void parse_file(const char *name)
+{
+}
+
+static void parse_addr_range(const char *optarg)
+{
+	unsigned long offset;
+	unsigned long size;
+	char *p;
+
+	p = strchr(optarg, ',');
+	if (!p)
+		p = strchr(optarg, '+');
+
+	if (p == optarg) {
+		offset = 0;
+		size   = parse_number(p + 1);
+	} else if (p) {
+		offset = parse_number(optarg);
+		if (p[1] == '\0')
+			size = ULONG_MAX;
+		else {
+			size = parse_number(p + 1);
+			if (*p == ',') {
+				if (size < offset)
+					fatal("invalid range: %lu,%lu\n",
+							offset, size);
+				size -= offset;
+			}
+		}
+	} else {
+		offset = parse_number(optarg);
+		size   = 1;
+	}
+
+	add_addr_range(offset, size);
+}
+
+static void add_bits_filter(uint64_t mask, uint64_t bits)
+{
+	if (nr_bit_filters >= MAX_BIT_FILTERS)
+		fatal("too much bit filters\n");
+
+	opt_mask[nr_bit_filters] = mask;
+	opt_bits[nr_bit_filters] = bits;
+	nr_bit_filters++;
+}
+
+static uint64_t parse_flag_name(const char *str, int len)
+{
+	int i;
+
+	if (!*str || !len)
+		return 0;
+
+	if (len <= 8 && !strncmp(str, "compound", len))
+		return BITS_COMPOUND;
+
+	for (i = 0; i < ARRAY_SIZE(page_flag_names); i++) {
+		if (!page_flag_names[i])
+			continue;
+		if (!strncmp(str, page_flag_names[i] + 2, len))
+			return 1ULL << i;
+	}
+
+	return parse_number(str);
+}
+
+static uint64_t parse_flag_names(const char *str, int all)
+{
+	const char *p    = str;
+	uint64_t   flags = 0;
+
+	while (1) {
+		if (*p == ',' || *p == '=' || *p == '\0') {
+			if ((*str != '~') || (*str == '~' && all && *++str))
+				flags |= parse_flag_name(str, p - str);
+			if (*p != ',')
+				break;
+			str = p + 1;
+		}
+		p++;
+	}
+
+	return flags;
+}
+
+static void parse_bits_mask(const char *optarg)
+{
+	uint64_t mask;
+	uint64_t bits;
+	const char *p;
+
+	p = strchr(optarg, '=');
+	if (p == optarg) {
+		mask = KPF_ALL_BITS;
+		bits = parse_flag_names(p + 1, 0);
+	} else if (p) {
+		mask = parse_flag_names(optarg, 0);
+		bits = parse_flag_names(p + 1, 0);
+	} else if (strchr(optarg, '~')) {
+		mask = parse_flag_names(optarg, 1);
+		bits = parse_flag_names(optarg, 0);
+	} else {
+		mask = parse_flag_names(optarg, 0);
+		bits = KPF_ALL_BITS;
+	}
+
+	add_bits_filter(mask, bits);
+}
+
+static void describe_flags(const char *optarg)
+{
+	uint64_t flags = parse_flag_names(optarg, 0);
+
+	printf("0x%016llx\t%s\t%s\n",
+		(unsigned long long)flags,
+		page_flag_name(flags),
+		page_flag_longname(flags));
+}
+
+static const struct option opts[] = {
+	{ "raw"       , 0, NULL, 'r' },
+	{ "pid"       , 1, NULL, 'p' },
+	{ "file"      , 1, NULL, 'f' },
+	{ "addr"      , 1, NULL, 'a' },
+	{ "bits"      , 1, NULL, 'b' },
+	{ "describe"  , 1, NULL, 'd' },
+	{ "list"      , 0, NULL, 'l' },
+	{ "list-each" , 0, NULL, 'L' },
+	{ "no-summary", 0, NULL, 'N' },
+	{ "hwpoison"  , 0, NULL, 'X' },
+	{ "unpoison"  , 0, NULL, 'x' },
+	{ "help"      , 0, NULL, 'h' },
+	{ NULL        , 0, NULL, 0 }
+};
+
+int main(int argc, char *argv[])
+{
+	int c;
+
+	page_size = getpagesize();
+
+	while ((c = getopt_long(argc, argv,
+				"rp:f:a:b:d:lLNXxh", opts, NULL)) != -1) {
+		switch (c) {
+		case 'r':
+			opt_raw = 1;
+			break;
+		case 'p':
+			parse_pid(optarg);
+			break;
+		case 'f':
+			parse_file(optarg);
+			break;
+		case 'a':
+			parse_addr_range(optarg);
+			break;
+		case 'b':
+			parse_bits_mask(optarg);
+			break;
+		case 'd':
+			describe_flags(optarg);
+			exit(0);
+		case 'l':
+			opt_list = 1;
+			break;
+		case 'L':
+			opt_list = 2;
+			break;
+		case 'N':
+			opt_no_summary = 1;
+			break;
+		case 'X':
+			opt_hwpoison = 1;
+			prepare_hwpoison_fd();
+			break;
+		case 'x':
+			opt_unpoison = 1;
+			prepare_hwpoison_fd();
+			break;
+		case 'h':
+			usage();
+			exit(0);
+		default:
+			usage();
+			exit(1);
+		}
+	}
+
+	if (opt_list && opt_pid)
+		printf("voffset\t");
+	if (opt_list == 1)
+		printf("offset\tlen\tflags\n");
+	if (opt_list == 2)
+		printf("offset\tflags\n");
+
+	walk_addr_ranges();
+
+	if (opt_list == 1)
+		show_page_range(0, 0, 0);  /* drain the buffer */
+
+	if (opt_no_summary)
+		return 0;
+
+	if (opt_list)
+		printf("\n\n");
+
+	show_summary();
+
+	return 0;
+}
diff --git a/tools/slub/slabinfo.c b/tools/vm/slabinfo.c
index 164cbcf6110..164cbcf6110 100644
--- a/tools/slub/slabinfo.c
+++ b/tools/vm/slabinfo.c
author	David S. Miller <davem@davemloft.net>	2012-04-10 14:30:45 -0400
committer	David S. Miller <davem@davemloft.net>	2012-04-10 14:30:45 -0400
commit	06eb4eafbdc0796d741d139a44f1253278da8611 (patch)
tree	fbdb44317130c371928154c9e6903e699fe2b995 /tools
parent	32ed53b83ea5ec26a4dba90e18f5e0ff6c71eb48 (diff)
parent	f68e556e23d1a4176b563bcb25d8baf2c5313f91 (diff)