Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (107 commits)
  perf stat: Add more cache-miss percentage printouts
  perf stat: Add -d -d and -d -d -d options to show more CPU events
  ftrace/kbuild: Add recordmcount files to force full build
  ftrace: Add self-tests for multiple function trace users
  ftrace: Modify ftrace_set_filter/notrace to take ops
  ftrace: Allow dynamically allocated function tracers
  ftrace: Implement separate user function filtering
  ftrace: Free hash with call_rcu_sched()
  ftrace: Have global_ops store the functions that are to be traced
  ftrace: Add ops parameter to ftrace_startup/shutdown functions
  ftrace: Add enabled_functions file
  ftrace: Use counters to enable functions to trace
  ftrace: Separate hash allocation and assignment
  ftrace: Create a global_ops to hold the filter and notrace hashes
  ftrace: Use hash instead for FTRACE_FL_FILTER
  ftrace: Replace FTRACE_FL_NOTRACE flag with a hash of ignored functions
  perf bench, x86: Add alternatives-asm.h wrapper
  x86, 64-bit: Fix copy_[to/from]_user() checks for the userspace address limit
  x86, mem: memset_64.S: Optimize memset by enhanced REP MOVSB/STOSB
  x86, mem: memmove_64.S: Optimize memmove by enhanced REP MOVSB/STOSB
  ...

15 files changed, 1599 insertions, 564 deletions

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 66f040b30729..86c87e214b11 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -113,13 +113,61 @@ OPTIONS
         Do various checks like samples ordering and lost events.
 
 -f::
---fields
+--fields::
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, sym. Field
-        list must be prepended with the type, trace, sw or hw,
+        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
 
+		perf script -f <fields>
+
+	is equivalent to:
+
+		perf script -f trace:<fields> -f sw:<fields> -f hw:<fields>
+    
+	i.e., the specified fields apply to all event types if the type string
+	is not given.
+    
+	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
+    
+	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
+	warning is given to the user:
+    
+		"Overriding previous field request for all events."
+    
+	Alternativey, consider the order:
+    
+		-f comm,tid,time,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
+	the override, and the result of the above is that only S/W and H/W
+	events are displayed with the given fields.
+    
+	For the 'wildcard' option if a user selected field is invalid for an
+	event type, a message is displayed to the user that the option is
+	ignored for that type. For example:
+    
+		$ perf script -f comm,tid,trace
+		'trace' not valid for hardware events. Ignoring.
+		'trace' not valid for software events. Ignoring.
+    
+	Alternatively, if the type is given an invalid field is specified it
+	is an error. For example:
+    
+        perf script -v -f sw:comm,tid,trace
+        'trace' not valid for software events.
+    
+	At this point usage is displayed, and perf-script exits.
+    
+	Finally, a user may not set fields to none for all event types.
+	i.e., -f "" is not allowed.
+
 -k::
 --vmlinux=<file>::
         vmlinux pathname
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 0c542563ea6c..1455413ec7a7 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -5,6 +5,8 @@ endif
 # The default target of this Makefile is...
 all:
 
+include config/utilities.mak
+
 ifneq ($(OUTPUT),)
 # check that the output directory actually exists
 OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
@@ -13,6 +15,12 @@ endif
 
 # Define V to have a more verbose compile.
 #
+# Define PYTHON to point to the python binary if the default
+# `python' is not correct; for example: PYTHON=python2
+#
+# Define PYTHON_CONFIG to point to the python-config binary if
+# the default `$(PYTHON)-config' is not correct.
+#
 # Define ASCIIDOC8 if you want to format documentation with AsciiDoc 8
 #
 # Define DOCBOOK_XSL_172 if you want to format man pages with DocBook XSL v1.72.
@@ -134,7 +142,7 @@ INSTALL = install
 # explicitly what architecture to check for. Fix this up for yours..
 SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
 
--include feature-tests.mak
+-include config/feature-tests.mak
 
 ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -fstack-protector-all),y)
 	CFLAGS := $(CFLAGS) -fstack-protector-all
@@ -169,12 +177,10 @@ grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
 
 $(OUTPUT)python/perf.so: $(PYRF_OBJS)
-	$(QUIET_GEN)( \
-		export CFLAGS="$(BASIC_CFLAGS)"; \
-		python util/setup.py --quiet  build_ext --build-lib='$(OUTPUT)python' \
-			--build-temp='$(OUTPUT)python/temp' \
-	)
-
+	$(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \
+	  --quiet build_ext \
+	  --build-lib='$(OUTPUT)python' \
+	  --build-temp='$(OUTPUT)python/temp'
 #
 # No Perl scripts right now:
 #
@@ -479,24 +485,74 @@ else
 	endif
 endif
 
-ifdef NO_LIBPYTHON
-	BASIC_CFLAGS += -DNO_LIBPYTHON
+disable-python = $(eval $(disable-python_code))
+define disable-python_code
+  BASIC_CFLAGS += -DNO_LIBPYTHON
+  $(if $(1),$(warning No $(1) was found))
+  $(warning Python support won't be built)
+endef
+
+override PYTHON := \
+  $(call get-executable-or-default,PYTHON,python)
+
+ifndef PYTHON
+  $(call disable-python,python interpreter)
+  python-clean :=
 else
-       PYTHON_EMBED_LDOPTS = $(shell python-config --ldflags 2>/dev/null)
-       PYTHON_EMBED_LDFLAGS = $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
-       PYTHON_EMBED_LIBADD = $(call grep-libs,$(PYTHON_EMBED_LDOPTS))
-	PYTHON_EMBED_CCOPTS = `python-config --cflags 2>/dev/null`
-	FLAGS_PYTHON_EMBED=$(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
-	ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED)),y)
-		msg := $(warning No Python.h found, install python-dev[el] to have python support in 'perf script' and to build the python bindings)
-		BASIC_CFLAGS += -DNO_LIBPYTHON
-	else
-               ALL_LDFLAGS += $(PYTHON_EMBED_LDFLAGS)
-               EXTLIBS += $(PYTHON_EMBED_LIBADD)
-		LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
-		LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
-		LANG_BINDINGS += $(OUTPUT)python/perf.so
-	endif
+
+  PYTHON_WORD := $(call shell-wordify,$(PYTHON))
+
+  python-clean := $(PYTHON_WORD) util/setup.py clean \
+    --build-lib='$(OUTPUT)python' \
+    --build-temp='$(OUTPUT)python/temp'
+
+  ifdef NO_LIBPYTHON
+    $(call disable-python)
+  else
+
+    override PYTHON_CONFIG := \
+      $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON)-config)
+
+    ifndef PYTHON_CONFIG
+      $(call disable-python,python-config tool)
+    else
+
+      PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
+
+      PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
+      PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
+      PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS))
+      PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+      FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
+
+      ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED)),y)
+        $(call disable-python,Python.h (for Python 2.x))
+      else
+
+        ifneq ($(call try-cc,$(SOURCE_PYTHON_VERSION),$(FLAGS_PYTHON_EMBED)),y)
+          $(warning Python 3 is not yet supported; please set)
+          $(warning PYTHON and/or PYTHON_CONFIG appropriately.)
+          $(warning If you also have Python 2 installed, then)
+          $(warning try something like:)
+          $(warning $(and ,))
+          $(warning $(and ,)  make PYTHON=python2)
+          $(warning $(and ,))
+          $(warning Otherwise, disable Python support entirely:)
+          $(warning $(and ,))
+          $(warning $(and ,)  make NO_LIBPYTHON=1)
+          $(warning $(and ,))
+          $(error   $(and ,))
+        else
+          ALL_LDFLAGS += $(PYTHON_EMBED_LDFLAGS)
+          EXTLIBS += $(PYTHON_EMBED_LIBADD)
+          LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
+          LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
+          LANG_BINDINGS += $(OUTPUT)python/perf.so
+        endif
+
+      endif
+    endif
+  endif
 endif
 
 ifdef NO_DEMANGLE
@@ -837,8 +893,7 @@ clean:
 	$(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope*
 	$(MAKE) -C Documentation/ clean
 	$(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS
-	@python util/setup.py clean --build-lib='$(OUTPUT)python' \
-				   --build-temp='$(OUTPUT)python/temp'
+	$(python-clean)
 
 .PHONY: all install clean strip
 .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index ac574ea23917..974f6d3f4e53 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -49,57 +49,169 @@ struct output_option {
 };
 
 /* default set to maintain compatibility with current format */
-static u64 output_fields[PERF_TYPE_MAX] = {
-	[PERF_TYPE_HARDWARE] = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | \
-			       PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | \
-			       PERF_OUTPUT_EVNAME | PERF_OUTPUT_SYM,
-
-	[PERF_TYPE_SOFTWARE] = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | \
-			       PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | \
-			       PERF_OUTPUT_EVNAME | PERF_OUTPUT_SYM,
-
-	[PERF_TYPE_TRACEPOINT] = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | \
-				 PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | \
-				 PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE,
+static struct {
+	bool user_set;
+	bool wildcard_set;
+	u64 fields;
+	u64 invalid_fields;
+} output[PERF_TYPE_MAX] = {
+
+	[PERF_TYPE_HARDWARE] = {
+		.user_set = false,
+
+		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_SYM,
+
+		.invalid_fields = PERF_OUTPUT_TRACE,
+	},
+
+	[PERF_TYPE_SOFTWARE] = {
+		.user_set = false,
+
+		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_SYM,
+
+		.invalid_fields = PERF_OUTPUT_TRACE,
+	},
+
+	[PERF_TYPE_TRACEPOINT] = {
+		.user_set = false,
+
+		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+				  PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+				  PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE,
+	},
+
+	[PERF_TYPE_RAW] = {
+		.user_set = false,
+
+		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_SYM,
+
+		.invalid_fields = PERF_OUTPUT_TRACE,
+	},
 };
 
-static bool output_set_by_user;
+static bool output_set_by_user(void)
+{
+	int j;
+	for (j = 0; j < PERF_TYPE_MAX; ++j) {
+		if (output[j].user_set)
+			return true;
+	}
+	return false;
+}
+
+static const char *output_field2str(enum perf_output_field field)
+{
+	int i, imax = ARRAY_SIZE(all_output_options);
+	const char *str = "";
+
+	for (i = 0; i < imax; ++i) {
+		if (all_output_options[i].field == field) {
+			str = all_output_options[i].str;
+			break;
+		}
+	}
+	return str;
+}
 
-#define PRINT_FIELD(x)  (output_fields[attr->type] & PERF_OUTPUT_##x)
+#define PRINT_FIELD(x)  (output[attr->type].fields & PERF_OUTPUT_##x)
 
-static int perf_session__check_attr(struct perf_session *session,
-				    struct perf_event_attr *attr)
+static int perf_event_attr__check_stype(struct perf_event_attr *attr,
+				  u64 sample_type, const char *sample_msg,
+				  enum perf_output_field field)
 {
+	int type = attr->type;
+	const char *evname;
+
+	if (attr->sample_type & sample_type)
+		return 0;
+
+	if (output[type].user_set) {
+		evname = __event_name(attr->type, attr->config);
+		pr_err("Samples for '%s' event do not have %s attribute set. "
+		       "Cannot print '%s' field.\n",
+		       evname, sample_msg, output_field2str(field));
+		return -1;
+	}
+
+	/* user did not ask for it explicitly so remove from the default list */
+	output[type].fields &= ~field;
+	evname = __event_name(attr->type, attr->config);
+	pr_debug("Samples for '%s' event do not have %s attribute set. "
+		 "Skipping '%s' field.\n",
+		 evname, sample_msg, output_field2str(field));
+
+	return 0;
+}
+
+static int perf_evsel__check_attr(struct perf_evsel *evsel,
+				  struct perf_session *session)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+
 	if (PRINT_FIELD(TRACE) &&
 		!perf_session__has_traces(session, "record -R"))
 		return -EINVAL;
 
 	if (PRINT_FIELD(SYM)) {
-		if (!(session->sample_type & PERF_SAMPLE_IP)) {
-			pr_err("Samples do not contain IP data.\n");
+		if (perf_event_attr__check_stype(attr, PERF_SAMPLE_IP, "IP",
+					   PERF_OUTPUT_SYM))
 			return -EINVAL;
-		}
+
 		if (!no_callchain &&
-		    !(session->sample_type & PERF_SAMPLE_CALLCHAIN))
+		    !(attr->sample_type & PERF_SAMPLE_CALLCHAIN))
 			symbol_conf.use_callchain = false;
 	}
 
 	if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
-		!(session->sample_type & PERF_SAMPLE_TID)) {
-		pr_err("Samples do not contain TID/PID data.\n");
+		perf_event_attr__check_stype(attr, PERF_SAMPLE_TID, "TID",
+				       PERF_OUTPUT_TID|PERF_OUTPUT_PID))
 		return -EINVAL;
-	}
 
 	if (PRINT_FIELD(TIME) &&
-		!(session->sample_type & PERF_SAMPLE_TIME)) {
-		pr_err("Samples do not contain timestamps.\n");
+		perf_event_attr__check_stype(attr, PERF_SAMPLE_TIME, "TIME",
+				       PERF_OUTPUT_TIME))
 		return -EINVAL;
-	}
 
 	if (PRINT_FIELD(CPU) &&
-		!(session->sample_type & PERF_SAMPLE_CPU)) {
-		pr_err("Samples do not contain cpu.\n");
+		perf_event_attr__check_stype(attr, PERF_SAMPLE_CPU, "CPU",
+				       PERF_OUTPUT_CPU))
 		return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * verify all user requested events exist and the samples
+ * have the expected data
+ */
+static int perf_session__check_output_opt(struct perf_session *session)
+{
+	int j;
+	struct perf_evsel *evsel;
+
+	for (j = 0; j < PERF_TYPE_MAX; ++j) {
+		evsel = perf_session__find_first_evtype(session, j);
+
+		/*
+		 * even if fields is set to 0 (ie., show nothing) event must
+		 * exist if user explicitly includes it on the command line
+		 */
+		if (!evsel && output[j].user_set && !output[j].wildcard_set) {
+			pr_err("%s events do not exist. "
+			       "Remove corresponding -f option to proceed.\n",
+			       event_type(j));
+			return -1;
+		}
+
+		if (evsel && output[j].fields &&
+			perf_evsel__check_attr(evsel, session))
+			return -1;
 	}
 
 	return 0;
@@ -168,10 +280,7 @@ static void process_event(union perf_event *event __unused,
 {
 	struct perf_event_attr *attr = &evsel->attr;
 
-	if (output_fields[attr->type] == 0)
-		return;
-
-	if (perf_session__check_attr(session, attr) < 0)
+	if (output[attr->type].fields == 0)
 		return;
 
 	print_sample_start(sample, thread, attr);
@@ -451,6 +560,7 @@ static int parse_output_fields(const struct option *opt __used,
 {
 	char *tok;
 	int i, imax = sizeof(all_output_options) / sizeof(struct output_option);
+	int j;
 	int rc = 0;
 	char *str = strdup(arg);
 	int type = -1;
@@ -458,52 +568,99 @@ static int parse_output_fields(const struct option *opt __used,
 	if (!str)
 		return -ENOMEM;
 
-	tok = strtok(str, ":");
-	if (!tok) {
-		fprintf(stderr,
-			"Invalid field string - not prepended with type.");
-		return -EINVAL;
-	}
-
-	/* first word should state which event type user
-	 * is specifying the fields
+	/* first word can state for which event type the user is specifying
+	 * the fields. If no type exists, the specified fields apply to all
+	 * event types found in the file minus the invalid fields for a type.
 	 */
-	if (!strcmp(tok, "hw"))
-		type = PERF_TYPE_HARDWARE;
-	else if (!strcmp(tok, "sw"))
-		type = PERF_TYPE_SOFTWARE;
-	else if (!strcmp(tok, "trace"))
-		type = PERF_TYPE_TRACEPOINT;
-	else {
-		fprintf(stderr, "Invalid event type in field string.");
-		return -EINVAL;
+	tok = strchr(str, ':');
+	if (tok) {
+		*tok = '\0';
+		tok++;
+		if (!strcmp(str, "hw"))
+			type = PERF_TYPE_HARDWARE;
+		else if (!strcmp(str, "sw"))
+			type = PERF_TYPE_SOFTWARE;
+		else if (!strcmp(str, "trace"))
+			type = PERF_TYPE_TRACEPOINT;
+		else if (!strcmp(str, "raw"))
+			type = PERF_TYPE_RAW;
+		else {
+			fprintf(stderr, "Invalid event type in field string.\n");
+			return -EINVAL;
+		}
+
+		if (output[type].user_set)
+			pr_warning("Overriding previous field request for %s events.\n",
+				   event_type(type));
+
+		output[type].fields = 0;
+		output[type].user_set = true;
+		output[type].wildcard_set = false;
+
+	} else {
+		tok = str;
+		if (strlen(str) == 0) {
+			fprintf(stderr,
+				"Cannot set fields to 'none' for all event types.\n");
+			rc = -EINVAL;
+			goto out;
+		}
+
+		if (output_set_by_user())
+			pr_warning("Overriding previous field request for all events.\n");
+
+		for (j = 0; j < PERF_TYPE_MAX; ++j) {
+			output[j].fields = 0;
+			output[j].user_set = true;
+			output[j].wildcard_set = true;
+		}
 	}
 
-	output_fields[type] = 0;
-	while (1) {
-		tok = strtok(NULL, ",");
-		if (!tok)
-			break;
+	tok = strtok(tok, ",");
+	while (tok) {
 		for (i = 0; i < imax; ++i) {
-			if (strcmp(tok, all_output_options[i].str) == 0) {
-				output_fields[type] |= all_output_options[i].field;
+			if (strcmp(tok, all_output_options[i].str) == 0)
 				break;
-			}
 		}
 		if (i == imax) {
-			fprintf(stderr, "Invalid field requested.");
+			fprintf(stderr, "Invalid field requested.\n");
 			rc = -EINVAL;
-			break;
+			goto out;
 		}
-	}
 
-	if (output_fields[type] == 0) {
-		pr_debug("No fields requested for %s type. "
-			 "Events will not be displayed\n", event_type(type));
+		if (type == -1) {
+			/* add user option to all events types for
+			 * which it is valid
+			 */
+			for (j = 0; j < PERF_TYPE_MAX; ++j) {
+				if (output[j].invalid_fields & all_output_options[i].field) {
+					pr_warning("\'%s\' not valid for %s events. Ignoring.\n",
+						   all_output_options[i].str, event_type(j));
+				} else
+					output[j].fields |= all_output_options[i].field;
+			}
+		} else {
+			if (output[type].invalid_fields & all_output_options[i].field) {
+				fprintf(stderr, "\'%s\' not valid for %s events.\n",
+					 all_output_options[i].str, event_type(type));
+
+				rc = -EINVAL;
+				goto out;
+			}
+			output[type].fields |= all_output_options[i].field;
+		}
+
+		tok = strtok(NULL, ",");
 	}
 
-	output_set_by_user = true;
+	if (type >= 0) {
+		if (output[type].fields == 0) {
+			pr_debug("No fields requested for %s type. "
+				 "Events will not be displayed.\n", event_type(type));
+		}
+	}
 
+out:
 	free(str);
 	return rc;
 }
@@ -829,7 +986,7 @@ 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. 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,sym",
 		     parse_output_fields),
 
 	OPT_END()
@@ -1020,7 +1177,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __used)
 		struct stat perf_stat;
 		int input;
 
-		if (output_set_by_user) {
+		if (output_set_by_user()) {
 			fprintf(stderr,
 				"custom fields not supported for generated scripts");
 			return -1;
@@ -1060,6 +1217,11 @@ int cmd_script(int argc, const char **argv, const char *prefix __used)
 		pr_debug("perf script started with script %s\n\n", script_name);
 	}
 
+
+	err = perf_session__check_output_opt(session);
+	if (err < 0)
+		goto out;
+
 	err = __cmd_script(session);
 
 	perf_session__delete(session);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 03f0e45f1479..a9f06715e44d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -6,24 +6,28 @@
  *
  * Sample output:
 
-   $ perf stat ~/hackbench 10
-   Time: 0.104
+   $ perf stat ./hackbench 10
 
-    Performance counter stats for '/home/mingo/hackbench':
+  Time: 0.118
 
-       1255.538611  task clock ticks     #      10.143 CPU utilization factor
-             54011  context switches     #       0.043 M/sec
-               385  CPU migrations       #       0.000 M/sec
-             17755  pagefaults           #       0.014 M/sec
-        3808323185  CPU cycles           #    3033.219 M/sec
-        1575111190  instructions         #    1254.530 M/sec
-          17367895  cache references     #      13.833 M/sec
-           7674421  cache misses         #       6.112 M/sec
+  Performance counter stats for './hackbench 10':
 
-    Wall-clock time elapsed:   123.786620 msecs
+       1708.761321 task-clock                #   11.037 CPUs utilized
+            41,190 context-switches          #    0.024 M/sec
+             6,735 CPU-migrations            #    0.004 M/sec
+            17,318 page-faults               #    0.010 M/sec
+     5,205,202,243 cycles                    #    3.046 GHz
+     3,856,436,920 stalled-cycles-frontend   #   74.09% frontend cycles idle
+     1,600,790,871 stalled-cycles-backend    #   30.75% backend  cycles idle
+     2,603,501,247 instructions              #    0.50  insns per cycle
+                                             #    1.48  stalled cycles per insn
+       484,357,498 branches                  #  283.455 M/sec
+         6,388,934 branch-misses             #    1.32% of all branches
+
+        0.154822978  seconds time elapsed
 
  *
- * Copyright (C) 2008, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
+ * Copyright (C) 2008-2011, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
  *
  * Improvements and fixes by:
  *
@@ -46,6 +50,7 @@
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/debug.h"
+#include "util/color.h"
 #include "util/header.h"
 #include "util/cpumap.h"
 #include "util/thread.h"
@@ -65,14 +70,107 @@ static struct perf_event_attr default_attrs[] = {
   { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS		},
 
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES		},
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND	},
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_BACKEND	},
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS		},
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS	},
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES		},
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES	},
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES		},
 
 };
 
+/*
+ * Detailed stats (-d), covering the L1 and last level data caches:
+ */
+static struct perf_event_attr detailed_attrs[] = {
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_LL			<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_LL			<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+};
+
+/*
+ * Very detailed stats (-d -d), covering the instruction cache and the TLB caches:
+ */
+static struct perf_event_attr very_detailed_attrs[] = {
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1I		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1I		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_DTLB		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_DTLB		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_ITLB		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_ITLB		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+
+};
+
+/*
+ * Very, very detailed stats (-d -d -d), adding prefetch events:
+ */
+static struct perf_event_attr very_very_detailed_attrs[] = {
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_PREFETCH	<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
+	(PERF_COUNT_HW_CACHE_OP_PREFETCH	<<  8) |
+	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
+};
+
+
+
 struct perf_evlist		*evsel_list;
 
 static bool			system_wide			=  false;
@@ -86,6 +184,8 @@ static pid_t			target_pid			= -1;
 static pid_t			target_tid			= -1;
 static pid_t			child_pid			= -1;
 static bool			null_run			=  false;
+static int			detailed_run			=  0;
+static bool			sync_run			=  false;
 static bool			big_num				=  true;
 static int			big_num_opt			=  -1;
 static const char		*cpu_list;
@@ -156,7 +256,15 @@ static double stddev_stats(struct stats *stats)
 
 struct stats			runtime_nsecs_stats[MAX_NR_CPUS];
 struct stats			runtime_cycles_stats[MAX_NR_CPUS];
+struct stats			runtime_stalled_cycles_front_stats[MAX_NR_CPUS];
+struct stats			runtime_stalled_cycles_back_stats[MAX_NR_CPUS];
 struct stats			runtime_branches_stats[MAX_NR_CPUS];
+struct stats			runtime_cacherefs_stats[MAX_NR_CPUS];
+struct stats			runtime_l1_dcache_stats[MAX_NR_CPUS];
+struct stats			runtime_l1_icache_stats[MAX_NR_CPUS];
+struct stats			runtime_ll_cache_stats[MAX_NR_CPUS];
+struct stats			runtime_itlb_cache_stats[MAX_NR_CPUS];
+struct stats			runtime_dtlb_cache_stats[MAX_NR_CPUS];
 struct stats			walltime_nsecs_stats;
 
 static int create_perf_stat_counter(struct perf_evsel *evsel)
@@ -193,6 +301,37 @@ static inline int nsec_counter(struct perf_evsel *evsel)
 }
 
 /*
+ * Update various tracking values we maintain to print
+ * more semantic information such as miss/hit ratios,
+ * instruction rates, etc:
+ */
+static void update_shadow_stats(struct perf_evsel *counter, u64 *count)
+{
+	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
+		update_stats(&runtime_nsecs_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
+		update_stats(&runtime_cycles_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
+		update_stats(&runtime_stalled_cycles_front_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
+		update_stats(&runtime_stalled_cycles_back_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
+		update_stats(&runtime_branches_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
+		update_stats(&runtime_cacherefs_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
+		update_stats(&runtime_l1_dcache_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
+		update_stats(&runtime_l1_icache_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
+		update_stats(&runtime_ll_cache_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
+		update_stats(&runtime_dtlb_cache_stats[0], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
+		update_stats(&runtime_itlb_cache_stats[0], count[0]);
+}
+
+/*
  * Read out the results of a single counter:
  * aggregate counts across CPUs in system-wide mode
  */
@@ -217,12 +356,7 @@ static int read_counter_aggr(struct perf_evsel *counter)
 	/*
 	 * Save the full runtime - to allow normalization during printout:
 	 */
-	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
-		update_stats(&runtime_nsecs_stats[0], count[0]);
-	if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
-		update_stats(&runtime_cycles_stats[0], count[0]);
-	if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
-		update_stats(&runtime_branches_stats[0], count[0]);
+	update_shadow_stats(counter, count);
 
 	return 0;
 }
@@ -242,12 +376,7 @@ static int read_counter(struct perf_evsel *counter)
 
 		count = counter->counts->cpu[cpu].values;
 
-		if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
-			update_stats(&runtime_nsecs_stats[cpu], count[0]);
-		if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
-			update_stats(&runtime_cycles_stats[cpu], count[0]);
-		if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
-			update_stats(&runtime_branches_stats[cpu], count[0]);
+		update_shadow_stats(counter, count);
 	}
 
 	return 0;
@@ -315,13 +444,18 @@ static int run_perf_stat(int argc __used, const char **argv)
 
 	list_for_each_entry(counter, &evsel_list->entries, node) {
 		if (create_perf_stat_counter(counter) < 0) {
-			if (errno == -EPERM || errno == -EACCES) {
+			if (errno == EINVAL || errno == ENOSYS || errno == ENOENT) {
+				if (verbose)
+					ui__warning("%s event is not supported by the kernel.\n",
+						    event_name(counter));
+				continue;
+			}
+
+			if (errno == EPERM || errno == EACCES) {
 				error("You may not have permission to collect %sstats.\n"
 				      "\t Consider tweaking"
 				      " /proc/sys/kernel/perf_event_paranoid or running as root.",
 				      system_wide ? "system-wide " : "");
-			} else if (errno == ENOENT) {
-				error("%s event is not supported. ", event_name(counter));
 			} else {
 				error("open_counter returned with %d (%s). "
 				      "/bin/dmesg may provide additional information.\n",
@@ -372,6 +506,16 @@ static int run_perf_stat(int argc __used, const char **argv)
 	return WEXITSTATUS(status);
 }
 
+static void print_noise_pct(double total, double avg)
+{
+	double pct = 0.0;
+
+	if (avg)
+		pct = 100.0*total/avg;
+
+	fprintf(stderr, "  ( +-%6.2f%% )", pct);
+}
+
 static void print_noise(struct perf_evsel *evsel, double avg)
 {
 	struct perf_stat *ps;
@@ -380,15 +524,14 @@ static void print_noise(struct perf_evsel *evsel, double avg)
 		return;
 
 	ps = evsel->priv;
-	fprintf(stderr, "   ( +- %7.3f%% )",
-			100 * stddev_stats(&ps->res_stats[0]) / avg);
+	print_noise_pct(stddev_stats(&ps->res_stats[0]), avg);
 }
 
 static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg)
 {
 	double msecs = avg / 1e6;
 	char cpustr[16] = { '\0', };
-	const char *fmt = csv_output ? "%s%.6f%s%s" : "%s%18.6f%s%-24s";
+	const char *fmt = csv_output ? "%s%.6f%s%s" : "%s%18.6f%s%-25s";
 
 	if (no_aggr)
 		sprintf(cpustr, "CPU%*d%s",
@@ -404,8 +547,191 @@