Merge branch 'linus' into perf/urgent

Merge reason: Include most of the merge window trees, to do fixes on top.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

34 files changed, 1816 insertions, 1029 deletions

diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 6f5a498608b..85c5f026930 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -66,6 +66,12 @@ OPTIONS
 	used. This interfaces starts by centering on the line with more
 	samples, TAB/UNTAB cycles through the lines with more samples.
 
+-c::
+--cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
+	be provided as a comma-separated list with no space: 0,1. Ranges of
+	CPUs are specified with -: 0-2. Default is to report samples on all
+	CPUs.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 02bafce4b34..2780d9ce48b 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -34,9 +34,11 @@ OPTIONS
 	Specify vmlinux path which has debuginfo (Dwarf binary).
 
 -m::
---module=MODNAME::
+--module=MODNAME|PATH::
 	Specify module name in which perf-probe searches probe points
-	or lines.
+	or lines. If a path of module file is passed, perf-probe
+	treat it as an offline module (this means you can add a probe on
+        a module which has not been loaded yet).
 
 -s::
 --source=PATH::
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 8ba03d6e539..04253c07d19 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -80,15 +80,24 @@ OPTIONS
 --dump-raw-trace::
         Dump raw trace in ASCII.
 
--g [type,min]::
+-g [type,min,order]::
 --call-graph::
-        Display call chains using type and min percent threshold.
+        Display call chains using type, min percent threshold and order.
 	type can be either:
 	- flat: single column, linear exposure of call chains.
 	- graph: use a graph tree, displaying absolute overhead rates.
 	- fractal: like graph, but displays relative rates. Each branch of
 		 the tree is considered as a new profiled object. +
-	Default: fractal,0.5.
+
+	order can be either:
+	- callee: callee based call graph.
+	- caller: inverted caller based call graph.
+
+	Default: fractal,0.5,callee.
+
+-G::
+--inverted::
+        alias for inverted caller based call graph.
 
 --pretty=<key>::
         Pretty printing style.  key: normal, raw
@@ -119,6 +128,12 @@ OPTIONS
 --symfs=<directory>::
         Look for files with symbols relative to this directory.
 
+-c::
+--cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
+	be provided as a comma-separated list with no space: 0,1. Ranges of
+	CPUs are specified with -: 0-2. Default is to report samples on all
+	CPUs.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1]
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 86c87e214b1..db017867d9e 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -115,10 +115,10 @@ OPTIONS
 -f::
 --fields::
         Comma separated list of fields to print. Options are:
-        comm, tid, pid, time, cpu, event, trace, sym. Field
-        list can be prepended with the type, trace, sw or hw,
+        comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr.
+        Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
-        e.g., -f sw:comm,tid,time,sym  and -f trace:time,cpu,trace
+        e.g., -f sw:comm,tid,time,ip,sym  and -f trace:time,cpu,trace
 
 		perf script -f <fields>
 
@@ -132,17 +132,17 @@ OPTIONS
 	The arguments are processed in the order received. A later usage can
 	reset a prior request. e.g.:
     
-		-f trace: -f comm,tid,time,sym
+		-f trace: -f comm,tid,time,ip,sym
     
 	The first -f suppresses trace events (field list is ""), but then the
-	second invocation sets the fields to comm,tid,time,sym. In this case a
+	second invocation sets the fields to comm,tid,time,ip,sym. In this case a
 	warning is given to the user:
     
 		"Overriding previous field request for all events."
     
 	Alternativey, consider the order:
     
-		-f comm,tid,time,sym -f trace:
+		-f comm,tid,time,ip,sym -f trace:
     
 	The first -f sets the fields for all events and the second -f
 	suppresses trace events. The user is given a warning message about
@@ -182,6 +182,12 @@ OPTIONS
 --hide-call-graph::
         When printing symbols do not display call chain.
 
+-c::
+--cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
+	be provided as a comma-separated list with no space: 0,1. Ranges of
+	CPUs are specified with -: 0-2. Default is to report samples on all
+	CPUs.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index c16836611d2..56d62d3fb16 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -282,6 +282,7 @@ LIB_H += util/thread.h
 LIB_H += util/thread_map.h
 LIB_H += util/trace-event.h
 LIB_H += util/probe-finder.h
+LIB_H += util/dwarf-aux.h
 LIB_H += util/probe-event.h
 LIB_H += util/pstack.h
 LIB_H += util/cpumap.h
@@ -438,6 +439,7 @@ else
 	BASIC_CFLAGS += -DDWARF_SUPPORT
 	EXTLIBS += -lelf -ldw
 	LIB_OBJS += $(OUTPUT)util/probe-finder.o
+	LIB_OBJS += $(OUTPUT)util/dwarf-aux.o
 endif # PERF_HAVE_DWARF_REGS
 endif # NO_DWARF
 
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 7b139e1e7e8..555aefd7fe0 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -28,6 +28,8 @@
 #include "util/hist.h"
 #include "util/session.h"
 
+#include <linux/bitmap.h>
+
 static char		const *input_name = "perf.data";
 
 static bool		force, use_tui, use_stdio;
@@ -38,6 +40,9 @@ static bool		print_line;
 
 static const char *sym_hist_filter;
 
+static const char	*cpu_list;
+static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+
 static int perf_evlist__add_sample(struct perf_evlist *evlist,
 				   struct perf_sample *sample,
 				   struct perf_evsel *evsel,
@@ -90,6 +95,9 @@ static int process_sample_event(union perf_event *event,
 		return -1;
 	}
 
+	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
+		return 0;
+
 	if (!al.filtered &&
 	    perf_evlist__add_sample(session->evlist, sample, evsel, &al)) {
 		pr_warning("problem incrementing symbol count, "
@@ -177,6 +185,12 @@ static int __cmd_annotate(void)
 	if (session == NULL)
 		return -ENOMEM;
 
+	if (cpu_list) {
+		ret = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap);
+		if (ret)
+			goto out_delete;
+	}
+
 	ret = perf_session__process_events(session, &event_ops);
 	if (ret)
 		goto out_delete;
@@ -252,6 +266,7 @@ static const struct option options[] = {
 		    "print matching source lines (may be slow)"),
 	OPT_BOOLEAN('P', "full-paths", &full_paths,
 		    "Don't shorten the displayed pathnames"),
+	OPT_STRING('c', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
 	OPT_END()
 };
 
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 2c0e64d0b4a..5f2a5c7046d 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -242,7 +242,8 @@ static const struct option options[] = {
 	OPT_STRING('s', "source", &symbol_conf.source_prefix,
 		   "directory", "path to kernel source"),
 	OPT_STRING('m', "module", &params.target_module,
-		   "modname", "target module name"),
+		   "modname|path",
+		   "target module name (for online) or path (for offline)"),
 #endif
 	OPT__DRY_RUN(&probe_event_dry_run),
 	OPT_INTEGER('\0', "max-probes", &params.max_probe_points,
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 8e2c8579818..80dc5b790e4 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -740,7 +740,7 @@ static bool force, append_file;
 const struct option record_options[] = {
 	OPT_CALLBACK('e', "event", &evsel_list, "event",
 		     "event selector. use 'perf list' to list available events",
-		     parse_events),
+		     parse_events_option),
 	OPT_CALLBACK(0, "filter", &evsel_list, "filter",
 		     "event filter", parse_filter),
 	OPT_INTEGER('p', "pid", &target_pid,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 287a173523a..f854efda768 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -33,6 +33,8 @@
 #include "util/sort.h"
 #include "util/hist.h"
 
+#include <linux/bitmap.h>
+
 static char		const *input_name = "perf.data";
 
 static bool		force, use_tui, use_stdio;
@@ -45,9 +47,13 @@ static struct perf_read_values	show_threads_values;
 static const char	default_pretty_printing_style[] = "normal";
 static const char	*pretty_printing_style = default_pretty_printing_style;
 
-static char		callchain_default_opt[] = "fractal,0.5";
+static char		callchain_default_opt[] = "fractal,0.5,callee";
+static bool		inverted_callchain;
 static symbol_filter_t	annotate_init;
 
+static const char	*cpu_list;
+static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+
 static int perf_session__add_hist_entry(struct perf_session *session,
 					struct addr_location *al,
 					struct perf_sample *sample,
@@ -116,6 +122,9 @@ static int process_sample_event(union perf_event *event,
 	if (al.filtered || (hide_unresolved && al.sym == NULL))
 		return 0;
 
+	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
+		return 0;
+
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
 
@@ -262,6 +271,12 @@ static int __cmd_report(void)
 	if (session == NULL)
 		return -ENOMEM;
 
+	if (cpu_list) {
+		ret = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap);
+		if (ret)
+			goto out_delete;
+	}
+
 	if (show_threads)
 		perf_read_values_init(&show_threads_values);
 
@@ -386,13 +401,29 @@ parse_callchain_opt(const struct option *opt __used, const char *arg,
 	if (!tok)
 		goto setup;
 
-	tok2 = strtok(NULL, ",");
 	callchain_param.min_percent = strtod(tok, &endptr);
 	if (tok == endptr)
 		return -1;
 
-	if (tok2)
+	/* get the print limit */
+	tok2 = strtok(NULL, ",");
+	if (!tok2)
+		goto setup;
+
+	if (tok2[0] != 'c') {
 		callchain_param.print_limit = strtod(tok2, &endptr);
+		tok2 = strtok(NULL, ",");
+		if (!tok2)
+			goto setup;
+	}
+
+	/* get the call chain order */
+	if (!strcmp(tok2, "caller"))
+		callchain_param.order = ORDER_CALLER;
+	else if (!strcmp(tok2, "callee"))
+		callchain_param.order = ORDER_CALLEE;
+	else
+		return -1;
 setup:
 	if (callchain_register_param(&callchain_param) < 0) {
 		fprintf(stderr, "Can't register callchain params\n");
@@ -436,9 +467,10 @@ static const struct option options[] = {
 		   "regex filter to identify parent, see: '--sort parent'"),
 	OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,
 		    "Only display entries with parent-match"),
-	OPT_CALLBACK_DEFAULT('g', "call-graph", NULL, "output_type,min_percent",
-		     "Display callchains using output_type (graph, flat, fractal, or none) and min percent threshold. "
-		     "Default: fractal,0.5", &parse_callchain_opt, callchain_default_opt),
+	OPT_CALLBACK_DEFAULT('g', "call-graph", NULL, "output_type,min_percent, call_order",
+		     "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold and callchain order. "
+		     "Default: fractal,0.5,callee", &parse_callchain_opt, callchain_default_opt),
+	OPT_BOOLEAN('G', "inverted", &inverted_callchain, "alias for inverted call graph"),
 	OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
 		   "only consider symbols in these dsos"),
 	OPT_STRING('C', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
@@ -455,6 +487,7 @@ static const struct option options[] = {
 		    "Only display entries resolved to a symbol"),
 	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
 		    "Look for files with symbols relative to this directory"),
+	OPT_STRING('c', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
 	OPT_END()
 };
 
@@ -467,6 +500,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 	else if (use_tui)
 		use_browser = 1;
 
+	if (inverted_callchain)
+		callchain_param.order = ORDER_CALLER;
+
 	if (strcmp(input_name, "-") != 0)
 		setup_browser(true);
 	else
@@ -504,7 +540,14 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 	if (parent_pattern != default_parent_pattern) {
 		if (sort_dimension__add("parent") < 0)
 			return -1;
-		sort_parent.elide = 1;
+
+		/*
+		 * Only show the parent fields if we explicitly
+		 * sort that way. If we only use parent machinery
+		 * for filtering, we don't want it.
+		 */
+		if (!strstr(sort_order, "parent"))
+			sort_parent.elide = 1;
 	} else
 		symbol_conf.exclude_other = false;
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 22747de7234..09024ec2ab2 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -13,6 +13,7 @@
 #include "util/util.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
+#include <linux/bitmap.h>
 
 static char const		*script_name;
 static char const		*generate_script_lang;
@@ -21,6 +22,8 @@ static u64			last_timestamp;
 static u64			nr_unordered;
 extern const struct option	record_options[];
 static bool			no_callchain;
+static const char		*cpu_list;
+static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 
 enum perf_output_field {
 	PERF_OUTPUT_COMM            = 1U << 0,
@@ -30,7 +33,10 @@ enum perf_output_field {
 	PERF_OUTPUT_CPU             = 1U << 4,
 	PERF_OUTPUT_EVNAME          = 1U << 5,
 	PERF_OUTPUT_TRACE           = 1U << 6,
-	PERF_OUTPUT_SYM             = 1U << 7,
+	PERF_OUTPUT_IP              = 1U << 7,
+	PERF_OUTPUT_SYM             = 1U << 8,
+	PERF_OUTPUT_DSO             = 1U << 9,
+	PERF_OUTPUT_ADDR            = 1U << 10,
 };
 
 struct output_option {
@@ -44,7 +50,10 @@ struct output_option {
 	{.str = "cpu",   .field = PERF_OUTPUT_CPU},
 	{.str = "event", .field = PERF_OUTPUT_EVNAME},
 	{.str = "trace", .field = PERF_OUTPUT_TRACE},
+	{.str = "ip",    .field = PERF_OUTPUT_IP},
 	{.str = "sym",   .field = PERF_OUTPUT_SYM},
+	{.str = "dso",   .field = PERF_OUTPUT_DSO},
+	{.str = "addr",  .field = PERF_OUTPUT_ADDR},
 };
 
 /* default set to maintain compatibility with current format */
@@ -60,7 +69,8 @@ static struct {
 
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
-			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_SYM,
+			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
+				  PERF_OUTPUT_SYM | PERF_OUTPUT_DSO,
 
 		.invalid_fields = PERF_OUTPUT_TRACE,
 	},
@@ -70,7 +80,8 @@ static struct {
 
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
-			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_SYM,
+			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
+				  PERF_OUTPUT_SYM | PERF_OUTPUT_DSO,
 
 		.invalid_fields = PERF_OUTPUT_TRACE,
 	},
@@ -88,7 +99,8 @@ static struct {
 
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
-			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_SYM,
+			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
+				  PERF_OUTPUT_SYM | PERF_OUTPUT_DSO,
 
 		.invalid_fields = PERF_OUTPUT_TRACE,
 	},
@@ -157,9 +169,9 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		!perf_session__has_traces(session, "record -R"))
 		return -EINVAL;
 
-	if (PRINT_FIELD(SYM)) {
+	if (PRINT_FIELD(IP)) {
 		if (perf_event_attr__check_stype(attr, PERF_SAMPLE_IP, "IP",
-					   PERF_OUTPUT_SYM))
+					   PERF_OUTPUT_IP))
 			return -EINVAL;
 
 		if (!no_callchain &&
@@ -167,6 +179,24 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 			symbol_conf.use_callchain = false;
 	}
 
+	if (PRINT_FIELD(ADDR) &&
+		perf_event_attr__check_stype(attr, PERF_SAMPLE_ADDR, "ADDR",
+				       PERF_OUTPUT_ADDR))
+		return -EINVAL;
+
+	if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
+		pr_err("Display of symbols requested but neither sample IP nor "
+			   "sample address\nis selected. Hence, no addresses to convert "
+		       "to symbols.\n");
+		return -EINVAL;
+	}
+	if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
+		pr_err("Display of DSO requested but neither sample IP nor "
+			   "sample address\nis selected. Hence, no addresses to convert "
+		       "to DSO.\n");
+		return -EINVAL;
+	}
+
 	if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
 		perf_event_attr__check_stype(attr, PERF_SAMPLE_TID, "TID",
 				       PERF_OUTPUT_TID|PERF_OUTPUT_PID))
@@ -230,7 +260,7 @@ static void print_sample_start(struct perf_sample *sample,
 	if (PRINT_FIELD(COMM)) {
 		if (latency_format)
 			printf("%8.8s ", thread->comm);
-		else if (PRINT_FIELD(SYM) && symbol_conf.use_callchain)
+		else if (PRINT_FIELD(IP) && symbol_conf.use_callchain)
 			printf("%s ", thread->comm);
 		else
 			printf("%16s ", thread->comm);
@@ -271,6 +301,63 @@ static void print_sample_start(struct perf_sample *sample,
 	}
 }
 
+static bool sample_addr_correlates_sym(struct perf_event_attr *attr)
+{
+	if ((attr->type == PERF_TYPE_SOFTWARE) &&
+	    ((attr->config == PERF_COUNT_SW_PAGE_FAULTS) ||
+	     (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MIN) ||
+	     (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)))
+		return true;
+
+	return false;
+}
+
+static void print_sample_addr(union perf_event *event,
+			  struct perf_sample *sample,
+			  struct perf_session *session,
+			  struct thread *thread,
+			  struct perf_event_attr *attr)
+{
+	struct addr_location al;
+	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	const char *symname, *dsoname;
+
+	printf("%16" PRIx64, sample->addr);
+
+	if (!sample_addr_correlates_sym(attr))
+		return;
+
+	thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
+			      event->ip.pid, sample->addr, &al);
+	if (!al.map)
+		thread__find_addr_map(thread, session, cpumode, MAP__VARIABLE,
+				      event->ip.pid, sample->addr, &al);
+
+	al.cpu = sample->cpu;
+	al.sym = NULL;
+
+	if (al.map)
+		al.sym = map__find_symbol(al.map, al.addr, NULL);
+
+	if (PRINT_FIELD(SYM)) {
+		if (al.sym && al.sym->name)
+			symname = al.sym->name;
+		else
+			symname = "";
+
+		printf(" %16s", symname);
+	}
+
+	if (PRINT_FIELD(DSO)) {
+		if (al.map && al.map->dso && al.map->dso->name)
+			dsoname = al.map->dso->name;
+		else
+			dsoname = "";
+
+		printf(" (%s)", dsoname);
+	}
+}
+
 static void process_event(union perf_event *event __unused,
 			  struct perf_sample *sample,
 			  struct perf_evsel *evsel,
@@ -288,12 +375,16 @@ static void process_event(union perf_event *event __unused,
 		print_trace_event(sample->cpu, sample->raw_data,
 				  sample->raw_size);
 
-	if (PRINT_FIELD(SYM)) {
+	if (PRINT_FIELD(ADDR))
+		print_sample_addr(event, sample, session, thread, attr);
+
+	if (PRINT_FIELD(IP)) {
 		if (!symbol_conf.use_callchain)
 			printf(" ");
 		else
 			printf("\n");
-		perf_session__print_symbols(event, sample, session);
+		perf_session__print_ip(event, sample, session,
+					      PRINT_FIELD(SYM), PRINT_FIELD(DSO));
 	}
 
 	printf("\n");
@@ -365,6 +456,10 @@ static int process_sample_event(union perf_event *event,
 		last_timestamp = sample->time;
 		return 0;
 	}
+
+	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
+		return 0;
+
 	scripting_ops->process_event(event, sample, evsel, session, thread);
 
 	session->hists.stats.total_period += sample->period;
@@ -985,8 +1080,9 @@ static const struct option options[] = {
 	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
 		    "Look for files with symbols relative to this directory"),
 	OPT_CALLBACK('f', "fields", NULL, "str",
-		     "comma separated output fields prepend with 'type:'. Valid types: hw,sw,trace,raw. Fields: comm,tid,pid,time,cpu,event,trace,sym",
+		     "comma separated output fields prepend with 'type:'. Valid types: hw,sw,trace,raw. Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,addr",
 		     parse_output_fields),
+	OPT_STRING('c', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
 
 	OPT_END()
 };
@@ -1167,6 +1263,11 @@ int cmd_script(int argc, const char **argv, const char *prefix __used)
 	if (session == NULL)
 		return -ENOMEM;
 
+	if (cpu_list) {
+		if (perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap))
+			return -1;
+	}
+
 	if (!no_callchain)
 		symbol_conf.use_callchain = true;
 	else
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a9f06715e44..1ad04ce29c3 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -61,6 +61,8 @@
 #include <locale.h>
 
 #define DEFAULT_SEPARATOR	" "
+#define CNTR_NOT_SUPPORTED	"<not supported>"
+#define CNTR_NOT_COUNTED	"<not counted>"
 
 static struct perf_event_attr default_attrs[] = {
 
@@ -448,6 +450,7 @@ static int run_perf_stat(int argc __used, const char **argv)
 				if (verbose)
 					ui__warning("%s event is not supported by the kernel.\n",
 						    event_name(counter));
+				counter->supported = false;
 				continue;
 			}
 
@@ -466,6 +469,7 @@ static int run_perf_stat(int argc __used, const char **argv)
 			die("Not all events could be opened.\n");
 			return -1;
 		}
+		counter->supported = true;
 	}
 
 	if (perf_evlist__set_filters(evsel_list)) {
@@ -513,7 +517,10 @@ static void print_noise_pct(double total, double avg)
 	if (avg)
 		pct = 100.0*total/avg;
 
-	fprintf(stderr, "  ( +-%6.2f%% )", pct);
+	if (csv_output)
+		fprintf(stderr, "%s%.2f%%", csv_sep, pct);
+	else
+		fprintf(stderr, "  ( +-%6.2f%% )", pct);
 }
 
 static void print_noise(struct perf_evsel *evsel, double avg)
@@ -861,7 +868,7 @@ static void print_counter_aggr(struct perf_evsel *counter)
 	if (scaled == -1) {
 		fprintf(stderr, "%*s%s%*s",
 			csv_output ? 0 : 18,
-			"<not counted>",
+			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
 			csv_sep,
 			csv_output ? 0 : -24,
 			event_name(counter));
@@ -878,13 +885,13 @@ static void print_counter_aggr(struct perf_evsel *counter)
 	else
 		abs_printout(-1, counter, avg);
 
+	print_noise(counter, avg);
+
 	if (csv_output) {
 		fputc('\n', stderr);
 		return;
 	}
 
-	print_noise(counter, avg);
-
 	if (scaled) {
 		double avg_enabled, avg_running;
 
@@ -914,7 +921,8 @@ static void print_counter(struct perf_evsel *counter)
 				csv_output ? 0 : -4,
 				evsel_list->cpus->map[cpu], csv_sep,
 				csv_output ? 0 : 18,
-				"<not counted>", csv_sep,
+				counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
+				csv_sep,
 				csv_output ? 0 : -24,
 				event_name(counter));
 
@@ -1024,7 +1032,7 @@ static int stat__set_big_num(const struct option *opt __used,
 static const struct option options[] = {
 	OPT_CALLBACK('e', "event", &evsel_list, "event",
 		     "event selector. use 'perf list' to list available events",
-		     parse_events),
+		     parse_events_option),
 	OPT_CALLBACK(0, "filter", &evsel_list, "filter",
 		     "event filter", parse_filter),
 	OPT_BOOLEAN('i', "no-inherit", &no_inherit,
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 2da9162262b..55f4c76f282 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -12,6 +12,7 @@
 #include "util/parse-events.h"
 #include "util/symbol.h"
 #include "util/thread_map.h"
+#include "../../include/linux/hw_breakpoint.h"
 
 static long page_size;
 
@@ -245,8 +246,8 @@ static int trace_event__id(const char *evname)
 	int err = -1, fd;
 
 	if (asprintf(&filename,
-		     "/sys/kernel/debug/tracing/events/syscalls/%s/id",
-		     evname) < 0)
+		     "%s/syscalls/%s/id",
+		     debugfs_path, evname) < 0)
 		return -1;
 
 	fd = open(filename, O_RDONLY);
@@ -600,6 +601,246 @@ out_free_threads:
 #undef nsyscalls
 }
 
+#define TEST_ASSERT_VAL(text, cond) \
+do { \
+	if (!cond) { \
+		pr_debug("FAILED %s:%d %s\n", __FILE__, __LINE__, text); \
+		return -1; \
+	} \
+} while (0)
+
+static int test__checkevent_tracepoint(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_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);
+	return 0;
+}
+
+static int test__checkevent_tracepoint_multi(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1);
+
+	list_for_each_entry(evsel, &evlist->entries, 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);
+	}
+	return 0;
+}
+
+static int test__checkevent_raw(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 conf