Merge commit 'v3.0-rc1' into kbuild/kbuild

45 files changed, 2510 insertions, 845 deletions

diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt
index 5bb41e55a3ac..3152cca15501 100644
--- a/tools/perf/Documentation/perf-script-perl.txt
+++ b/tools/perf/Documentation/perf-script-perl.txt
@@ -63,7 +63,6 @@ The format file for the sched_wakep event defines the following fields
         field:unsigned char common_flags;
         field:unsigned char common_preempt_count;
         field:int common_pid;
-        field:int common_lock_depth;
 
         field:char comm[TASK_COMM_LEN];
         field:pid_t pid;
diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt
index 36b38277422c..471022069119 100644
--- a/tools/perf/Documentation/perf-script-python.txt
+++ b/tools/perf/Documentation/perf-script-python.txt
@@ -463,7 +463,6 @@ The format file for the sched_wakep event defines the following fields
         field:unsigned char common_flags;
         field:unsigned char common_preempt_count;
         field:int common_pid;
-        field:int common_lock_depth;
 
         field:char comm[TASK_COMM_LEN];
         field:pid_t pid;
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 158c30e8210c..032ba6398a5c 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.
@@ -35,15 +43,21 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
 				  -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
 				  -e s/sh[234].*/sh/ )
 
+CC = $(CROSS_COMPILE)gcc
+AR = $(CROSS_COMPILE)ar
+
 # Additional ARCH settings for x86
 ifeq ($(ARCH),i386)
         ARCH := x86
 endif
 ifeq ($(ARCH),x86_64)
-	RAW_ARCH := x86_64
-        ARCH := x86
-	ARCH_CFLAGS := -DARCH_X86_64
-	ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S
+	ARCH := x86
+	IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -xc - | tail -n 1)
+	ifeq (${IS_X86_64}, 1)
+		RAW_ARCH := x86_64
+		ARCH_CFLAGS := -DARCH_X86_64
+		ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S
+	endif
 endif
 
 #
@@ -119,8 +133,6 @@ lib = lib
 
 export prefix bindir sharedir sysconfdir
 
-CC = $(CROSS_COMPILE)gcc
-AR = $(CROSS_COMPILE)ar
 RM = rm -f
 MKDIR = mkdir
 FIND = find
@@ -130,7 +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
@@ -165,8 +177,10 @@ grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
 
 $(OUTPUT)python/perf.so: $(PYRF_OBJS)
-	$(QUIET_GEN)python util/setup.py --quiet  build_ext --build-lib='$(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='$(OUTPUT)python/temp'
 #
 # No Perl scripts right now:
 #
@@ -201,11 +215,13 @@ LIB_FILE=$(OUTPUT)libperf.a
 LIB_H += ../../include/linux/perf_event.h
 LIB_H += ../../include/linux/rbtree.h
 LIB_H += ../../include/linux/list.h
+LIB_H += ../../include/linux/const.h
 LIB_H += ../../include/linux/hash.h
 LIB_H += ../../include/linux/stringify.h
 LIB_H += util/include/linux/bitmap.h
 LIB_H += util/include/linux/bitops.h
 LIB_H += util/include/linux/compiler.h
+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
@@ -471,24 +487,74 @@ 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
@@ -829,8 +895,7 @@ 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-annotate.c b/tools/perf/builtin-annotate.c
index e18eb7ed30ae..7b139e1e7e86 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -8,8 +8,6 @@
 #include "builtin.h"
 
 #include "util/util.h"
-
-#include "util/util.h"
 #include "util/color.h"
 #include <linux/list.h>
 #include "util/cache.h"
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 6febcc168a8c..8e2c85798185 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -41,7 +41,7 @@ static u64			user_interval			= ULLONG_MAX;
 static u64			default_interval		=      0;
 
 static unsigned int		page_size;
-static unsigned int		mmap_pages			=    128;
+static unsigned int		mmap_pages			= UINT_MAX;
 static unsigned int		user_freq 			= UINT_MAX;
 static int			freq				=   1000;
 static int			output;
@@ -163,6 +163,7 @@ static void config_attr(struct perf_evsel *evsel, struct perf_evlist *evlist)
 	struct perf_event_attr *attr = &evsel->attr;
 	int track = !evsel->idx; /* only the first counter needs these */
 
+	attr->inherit		= !no_inherit;
 	attr->read_format	= PERF_FORMAT_TOTAL_TIME_ENABLED |
 				  PERF_FORMAT_TOTAL_TIME_RUNNING |
 				  PERF_FORMAT_ID;
@@ -251,6 +252,9 @@ static void open_counters(struct perf_evlist *evlist)
 {
 	struct perf_evsel *pos;
 
+	if (evlist->cpus->map[0] < 0)
+		no_inherit = true;
+
 	list_for_each_entry(pos, &evlist->entries, node) {
 		struct perf_event_attr *attr = &pos->attr;
 		/*
@@ -271,15 +275,13 @@ static void open_counters(struct perf_evlist *evlist)
 retry_sample_id:
 		attr->sample_id_all = sample_id_all_avail ? 1 : 0;
 try_again:
-		if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group,
-				     !no_inherit) < 0) {
+		if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group) < 0) {
 			int err = errno;
 
-			if (err == EPERM || err == EACCES)
-				die("Permission error - are you root?\n"
-					"\t Consider tweaking"
-					" /proc/sys/kernel/perf_event_paranoid.\n");
-			else if (err ==  ENODEV && cpu_list) {
+			if (err == EPERM || err == EACCES) {
+				ui__warning_paranoid();
+				exit(EXIT_FAILURE);
+			} else if (err ==  ENODEV && cpu_list) {
 				die("No such device - did you specify"
 					" an out-of-range profile CPU?\n");
 			} else if (err == EINVAL && sample_id_all_avail) {
@@ -302,11 +304,19 @@ try_again:
 					&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
 
 				if (verbose)
-					warning(" ... trying to fall back to cpu-clock-ticks\n");
+					ui__warning("The cycles event is not supported, "
+						    "trying to fall back to cpu-clock-ticks\n");
 				attr->type = PERF_TYPE_SOFTWARE;
 				attr->config = PERF_COUNT_SW_CPU_CLOCK;
 				goto try_again;
 			}
+
+			if (err == ENOENT) {
+				ui__warning("The %s event is not supported.\n",
+					    event_name(pos));
+				exit(EXIT_FAILURE);
+			}
+
 			printf("\n");
 			error("sys_perf_event_open() syscall returned with %d (%s).  /bin/dmesg may provide additional information.\n",
 			      err, strerror(err));
@@ -417,7 +427,7 @@ static void mmap_read_all(void)
 {
 	int i;
 
-	for (i = 0; i < evsel_list->cpus->nr; i++) {
+	for (i = 0; i < evsel_list->nr_mmaps; i++) {
 		if (evsel_list->mmap[i].base)
 			mmap_read(&evsel_list->mmap[i]);
 	}
@@ -506,6 +516,10 @@ static int __cmd_record(int argc, const char **argv)
 	if (have_tracepoints(&evsel_list->entries))
 		perf_header__set_feat(&session->header, HEADER_TRACE_INFO);
 
+	/* 512 kiB: default amount of unprivileged mlocked memory */
+	if (mmap_pages == UINT_MAX)
+		mmap_pages = (512 * 1024) / page_size;
+
 	if (forks) {
 		child_pid = fork();
 		if (child_pid < 0) {
@@ -809,6 +823,16 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 
 	symbol__init();
 
+	if (symbol_conf.kptr_restrict)
+		pr_warning(
+"WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
+"check /proc/sys/kernel/kptr_restrict.\n\n"
+"Samples in kernel functions may not be resolved if a suitable vmlinux\n"
+"file is not found in the buildid cache or in the vmlinux path.\n\n"
+"Samples in kernel modules won't be resolved at all.\n\n"
+"If some relocation was applied (e.g. kexec) symbols may be misresolved\n"
+"even with a suitable vmlinux or kallsyms file.\n\n");
+
 	if (no_buildid_cache || no_buildid)
 		disable_buildid_cache();
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 498c6f70a747..287a173523a7 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -116,6 +116,9 @@ static int process_sample_event(union perf_event *event,
 	if (al.filtered || (hide_unresolved && al.sym == NULL))
 		return 0;
 
+	if (al.map != NULL)
+		al.map->dso->hit = 1;
+
 	if (perf_session__add_hist_entry(session, &al, sample, evsel)) {
 		pr_debug("problem incrementing symbol period, skipping event\n");
 		return -1;
@@ -249,6 +252,8 @@ static int __cmd_report(void)
 	u64 nr_samples;
 	struct perf_session *session;
 	struct perf_evsel *pos;
+	struct map *kernel_map;
+	struct kmap *kernel_kmap;
 	const char *help = "For a higher level overview, try: perf report --sort comm,dso";
 
 	signal(SIGINT, sig_handler);
@@ -268,6 +273,24 @@ static int __cmd_report(void)
 	if (ret)
 		goto out_delete;
 
+	kernel_map = session->host_machine.vmlinux_maps[MAP__FUNCTION];
+	kernel_kmap = map__kmap(kernel_map);
+	if (kernel_map == NULL ||
+	    (kernel_map->dso->hit &&
+	     (kernel_kmap->ref_reloc_sym == NULL ||
+	      kernel_kmap->ref_reloc_sym->addr == 0))) {
+		const struct dso *kdso = kernel_map->dso;
+
+		ui__warning(
+"Kernel address maps (/proc/{kallsyms,modules}) were restricted.\n\n"
+"Check /proc/sys/kernel/kptr_restrict before running 'perf record'.\n\n%s\n\n"
+"Samples in kernel modules can't be resolved as well.\n\n",
+			    RB_EMPTY_ROOT(&kdso->symbols[MAP__FUNCTION]) ?
+"As no suitable kallsyms nor vmlinux was found, kernel samples\n"
+"can't be resolved." :
+"If some relocation was applied (e.g. kexec) symbols may be misresolved.");
+	}
+
 	if (dump_trace) {
 		perf_session__fprintf_nr_events(session, stdout);
 		goto out_delete;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index ac574ea23917..22747de7234b 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -10,7 +10,6 @@
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/trace-event.h"
-#include "util/parse-options.h"
 #include "util/util.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
@@ -49,57 +48,169 @@ 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[attr->type].fields & PERF_OUTPUT_##x)
+
+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;
 
-#define PRINT_FIELD(x)  (output_fields[attr->type] & PERF_OUTPUT_##x)
+	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_session__check_attr(struct perf_session *session,
-				    struct perf_event_attr *attr)
+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 +279,7 @@ 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 +559,7 @@ 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 +567,99 @@ 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 +985,7 @@ 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 +1176,7 @@ 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 +1216,11 @@ 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 e2109f9b43eb..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)
@@ -167,16 +275,17 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
 				    PERF_FORMAT_TOTAL_TIME_RUNNING;
 
+	attr->inherit = !no_inherit;
+
 	if (system_wide)
-		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, false, false);
+		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, false);
 
-	attr->inherit = !no_inherit;
 	if (target_pid == -1 && target_tid == -1) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
 
-	return perf_evsel__open_per_thread(evsel, evsel_list->threads, false, false);
+	return perf_evsel__open_per_thread(evsel, evsel_list->threads, false);
 }
 
 /*
@@ -192,6 +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
  */
@@ -216,12 +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;
 }
@@ -241,12 +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;
@@ -314,13 +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",
@@ -371,6 +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;
@@ -379,15 +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",
@@ -403,8 +547,191 @@ static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg)
 		return;
 
 	if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
-		fprintf(stderr, " # %10.3f CPUs ",
-				avg / avg_stats(&walltime_nsecs_stats));
+		fprintf(stderr, " # %8.3f CPUs utilized          ", avg / avg_stats(&walltime_nsecs_stats));
+}
+
+static void print_stalled_cycles_frontend(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_cycles_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = PERF_COLOR_NORMAL;
+	if (ratio > 50.0)
+		color = PERF_COLOR_RED;
+	else if (ratio > 30.0)
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > 10.0)
+		color = PERF_COLOR_YELLOW;
+
+	fprintf(stderr, " #  ");
+	color_fprintf(stderr, color, "%6.2f%%", ratio);
+	fprintf(stderr, " frontend cycles idle   ");
+}
+
+static void print_stalled_cycles_backend(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_cycles_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = PERF_COLOR_NORMAL;
+	if (ratio > 75.0)
+		color = PERF_COLOR_RED;
+	else if (ratio > 50.0)
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > 20.0)
+		color = PERF_COLOR_YELLOW;
+
+	fprintf(stderr, " #  ");
+	color_fprintf(stderr, color, "%6.2f%%", ratio);
+	fprintf(stderr, " backend  cycles idle   ");
+}
+
+static void print_branch_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_branches_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = PERF_COLOR_NORMAL;
+	if (ratio > 20.0)
+		color = PERF_COLOR_RED;
+	else if (ratio > 10.0)
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > 5.0)
+		color = PERF_COLOR_YELLOW;
+
+	fprintf(stderr, " #  ");
+	color_fprintf(stderr, color, "%6.2f%%", ratio);
+	fprintf(stderr, " of all branches        ");
+}
+
+static void print_l1_dcache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_l1_dcache_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = PERF_COLOR_NORMAL;
+	if (ratio > 20.0)
+		color = PERF_COLOR_RED;
+	else if (ratio > 10.0)
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > 5.0)
+		color = PERF_COLOR_YELLOW;
+
+	fprintf(stderr, " #  ");
+	color_fprintf(stderr, color, "%6.2f%%", ratio);
+	fprintf(stderr, " of all L1-dcache hits  ");
+}
+
+static void print_l1_icache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_l1_icache_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = PERF_COLOR_NORMAL;
+	if (ratio > 20.0)
+		color = PERF_COLOR_RED;
+	else if (ratio > 10.0)
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > 5.0)
+		color = PERF_COLOR_YELLOW;
+
+	fprintf(stderr, " #  ");
+	color_fprintf(stderr, color, "%6.2f%%", ratio);
+	fprintf(stderr, " of all L1-icache hits  ");
+}
+
+static void print_dtlb_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_dtlb_cache_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = PERF_COLOR_NORMAL;
+	if (ratio > 20.0)
+		color = PERF_COLOR_RED;
+	else if (ratio > 10.0)
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > 5.0)
+		color = PERF_COLOR_YELLOW;
+
+	fprintf(stderr, " #  ");
+	color_fprintf(stderr, color, "%6.2f%%", ratio);
+	fprintf(stderr, " of all dTLB cache hits ");
+}
+
+static void print_itlb_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_itlb_cache_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = PERF_COLOR_NORMAL;
+	if (ratio > 20.0)
+		color = PERF_COLOR_RED;
+	else if (ratio > 10.0)
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > 5.0)
+		color = PERF_COLOR_YELLOW;
+
+	fprintf(stderr, " #  ");
+	color_fprintf(stderr, color, "%6.2f%%", ratio);
+	fprintf(stderr, " of all iTLB cache hits ");
+}
+
+static void print_ll_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+
+	total = avg_stats(&runtime_ll_cache_stats[cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = PERF_COLOR_NORMAL;
+	if (ratio > 20.0)
+		color = PERF_COLOR_RED;
+	else if (ratio > 10.0)
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > 5.0)
+		color = PERF_COLOR_YELLOW;
+
+	fprintf(stderr, " #  ");
+	color_fprintf(stderr, color, "%6.2f%%", ratio);
+	fprintf(stderr, " of all LL-cache hits   ");
 }
 
 static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
@@ -416,9 +743,9 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 	if (csv_output)
 		fmt = "%s%.0f%s%s";
 	else if (big_num)
-		fmt = "%s%'18.0f%s%-24s";
+		fmt = "%s%'18.0f%s%-25s";
 	else
-		fmt = "%s%18.0f%s%-24s";
+		fmt = "%s%18.0f%s%-25s";
 
 	if (no_aggr)
 		sprintf(cpustr, "CPU%*d%s",
@@ -441,23 +768,83 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 		if (total)
 			ratio = avg / total;
 
-		fprintf(stderr, " # %10.3f IPC  ", ratio);
+		fprintf(stderr, " #   %5.2f  insns per cycle        ", ratio);
+
+		total = avg_stats(&runtime_stalled_cycles_front_stats[cpu]);
+		total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[cpu]));
+
+		if (total && avg) {
+			ratio = total / avg;
+			fprintf(stderr, "\n                                             #   %5.2f  stalled cycles per insn", ratio);
+		}
+
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
 			runtime_branches_stats[cpu].n != 0) {
-		total = avg_stats(&runtime_branches_stats[cpu]);
+		print_branch_misses(cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_l1_dcache_stats[cpu].n != 0) {
+		print_l1_dcache_misses(cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_l1_icache_stats[cpu].n != 0) {
+		print_l1_icache_misses(cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_dtlb_cache_stats[cpu].n != 0) {
+		print_dtlb_cache_misses(cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_itlb_cache_stats[cpu].n != 0) {
+		print_itlb_cache_misses(cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_ll_cache_stats[cpu].n != 0) {
+		print_ll_cache_misses(cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
+			runtime_cacherefs_stats[cpu].n != 0) {
+		total = avg_stats(&runtime_cacherefs_stats[cpu]);
 
 		if (total)
 			ratio = avg * 100 / total;
 
-		fprintf(stderr, " # %10.3f %%    ", ratio);
+		fprintf(stderr, " # %8.3f %% of all cache refs    ", ratio);
 
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
+		print_stalled_cycles_frontend(cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
+		print_stalled_cycles_backend(cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
+		total = avg_stats(&runtime_nsecs_stats[cpu]);
+
+		if (total)
+			ratio = 1.0 * avg / total;
+
+		fprintf(stderr, " # %8.3f GHz                    ", ratio);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
 		if (total)
 			ratio = 1000.0 * avg / total;
 
-		fprintf(stderr, " # %10.3f M/sec", ratio);
+		fprintf(stderr, " # %8.3f M/sec                  ", ratio);
+	} else {
+		fprintf(stderr, "                                   ");
 	}
 }
 
@@ -504,8 +891,7 @@ static void print_counter_aggr(struct perf_evsel *counter)
 		avg_enabled = avg_stats(&ps->res_stats[1]);
 		avg_running = avg_stats(&ps->res_stats[2]);
 
-		fprintf(stderr, "  (scaled from %.2f%%)",
-				100 * avg_running / avg_enabled);
+		fprintf(stderr, " [%5.2f%%]", 100 * avg_running / avg_enabled);
 	}
 	fprintf(stderr, "\n");
 }
@@ -547,10 +933,8 @@ static void print_counter(struct perf_evsel *counter)
 		if (!csv_output) {
 			print_noise(counter, 1.0);
 
-			if (run != ena) {
-				fprintf(stderr, "  (scaled from %.2f%%)",
-					100.0 * run / ena);
-			}
+			if (run != ena)
+				fprintf(stderr, "  (%.2f%%)", 100.0 * run / ena);
 		}
 		fputc('\n', stderr);
 	}
@@ -590,13 +974,14 @@ static void print_stat(int argc, const char **argv)
 	}
 
 	if (!csv_output) {
-		fprintf(stderr, "\n");
-		fprintf(stderr, " %18.9f  seconds time elapsed",
+		if (!null_run)
+			fprintf(stderr, "\n");
+		fprintf(stderr, " %17.9f seconds time elapsed",
 				avg_stats(&walltime_nsecs_stats)/1e9);
 		if (run_count > 1) {
-			fprintf(stderr, "   ( +- %7.3f%% )",
-				100*stddev_stats(&walltime_nsecs_stats) /
-				avg_stats(&walltime_nsecs_stats));
+			fprintf(stderr, "                                        ");
+			print_noise_pct(stddev_stats(&walltime_nsecs_stats),
+					avg_stats(&walltime_nsecs_stats));
 		}
 		fprintf(stderr, "\n\n");
 	}
@@ -658,6 +1043,10 @@ static const struct option options[] = {
 		    "repeat command and print average + stddev (max: 100)"),
 	OPT_BOOLEAN('n', "null", &null_run,
 		    "null run - dont start any counters"),
+	OPT_INCR('d', "detailed", &detailed_run,
+		    "detailed run - start a lot of events"),
+	OPT_BOOLEAN('S', "sync", &sync_run,
+		    "call sync() before starting a run"),
 	OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL, 
 			   "print large numbers with thousands\' separators",
 			   stat__set_big_num),
@@ -673,6 +1062,70 @@ static const struct option options[] = {
 	OPT_END()
 };
 
+/*
+ * Add default attributes, if there were no attributes specified or
+ * if -d/--detailed, -d -d or -d -d -d is used:
+ */
+static int add_default_attributes(void)
+{
+	struct perf_evsel *pos;
+	size_t attr_nr = 0;
+	size_t c;
+
+	/* Set attrs if no event is selected and !null_run: */
+	if (null_run)
+		return 0;
+
+	if (!evsel_list->nr_entries) {
+		for (c = 0; c < ARRAY_SIZE(default_attrs); c++) {
+			pos = perf_evsel__new(default_attrs + c, c + attr_nr);
+			if (pos == NULL)
+				return -1;
+			perf_evlist__add(evsel_list, pos);
+		}
+		attr_nr += c;
+	}
+
+	/* Detailed events get appended to the event list: */
+
+	if (detailed_run <  1)
+		return 0;
+
+	/* Append detailed run extra attributes: */
+	for (c = 0; c < ARRAY_SIZE(detailed_attrs); c++) {
+		pos = perf_evsel__new(detailed_attrs + c, c + attr_nr);
+		if (pos == NULL)
+			return -1;
+		perf_evlist__add(evsel_list, pos);
+	}
+	attr_nr += c;
+
+	if (detailed_run < 2)
+		return 0;
+
+	/* Append very detailed run extra attributes: */
+	for (c = 0; c < ARRAY_SIZE(very_detailed_attrs); c++) {
+		pos = perf_evsel__new(very_detailed_attrs + c, c + attr_nr);
+		if (pos == NULL)
+			return -1;
+		perf_evlist__add(evsel_list, pos);
+	}
+
+	if (detailed_run < 3)
+		return 0;
+
+	/* Append very, very detailed run extra attributes: */
+	for (c = 0; c < ARRAY_SIZE(very_very_detailed_attrs); c++) {
+		pos = perf_evsel__new(very_very_detailed_attrs + c, c + attr_nr);
+		if (pos == NULL)
+			return -1;
+		perf_evlist__add(evsel_list, pos);
+	}
+
+
+	return 0;
+}
+
 int cmd_stat(int argc, const char **argv, const char *prefix __used)
 {
 	struct perf_evsel *pos;
@@ -718,17 +1171,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 		usage_with_options(stat_usage, options);
 	}
 
-	/* Set attrs and nr_counters if no event is selected and !null_run */
-	if (!null_run && !evsel_list->nr_entries) {
-		size_t c;
-
-		for (c = 0; c < ARRAY_SIZE(default_attrs); ++c) {
-			pos = perf_evsel__new(&default_attrs[c], c);
-			if (pos == NULL)
-				goto out;
-			perf_evlist__add(evsel_list, pos);
-		}
-	}
+	if (add_default_attributes())
+		goto out;
 
 	if (target_pid != -1)
 		target_tid = target_pid;
@@ -772,6 +1216,10 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 	for (run_idx = 0; run_idx < run_count; run_idx++) {
 		if (run_count != 1 && verbose)
 			fprintf(stderr, "[ perf stat: executing run #%d ... ]\n", run_idx + 1);
+
+		if (sync_run)
+			sync();
+
 		status = run_perf_stat(argc, argv);
 	}
 
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 1b2106c58f66..b67186228c89 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -290,7 +290,7 @@ static int test__open_syscall_event(void)
 		goto out_thread_map_delete;
 	}
 
-	if (perf_evsel__open_per_thread(evsel, threads, false, false) < 0) {
+	if (perf_evsel__open_per_thread(evsel, threads, false) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 			 strerror(errno));
@@ -303,7 +303,7 @@ static int test__open_syscall_event(void)
 	}
 
 	if (perf_evsel__read_on_cpu(evsel, 0, 0) < 0) {
-		pr_debug("perf_evsel__open_read_on_cpu\n");
+		pr_debug("perf_evsel__read_on_cpu\n");
 		goto out_close_fd;
 	}
 
@@ -365,7 +365,7 @@ static int test__open_syscall_event_on_all_cpus(void)
 		goto out_thread_map_delete;
 	}
 
-	if (perf_evsel__open(evsel, cpus, threads, false, false) < 0) {
+	if (perf_evsel__open(evsel, cpus, threads, false) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 			 strerror(errno));
@@ -418,7 +418,7 @@ static int test__open_syscall_event_on_all_cpus(void)
 			continue;
 
 		if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) {
-			pr_debug("perf_evsel__open_read_on_cpu\n");
+			pr_debug("perf_evsel__read_on_cpu\n");
 			err = -1;
 			break;
 		}
@@ -474,6 +474,7 @@ static int test__basic_mmap(void)
 	unsigned int nr_events[nsyscalls],
 		     expected_nr_events[nsyscalls], i, j;
 	struct perf_evsel *evsels[nsyscalls], *evsel;
+	int sample_size = perf_sample_size(attr.sample_type);
 
 	for (i = 0; i < nsyscalls; ++i) {
 		char name[64];
@@ -529,7 +530,7 @@ static int test__basic_mmap(void)
 
 		perf_evlist__add(evlist, evsels[i]);
 
-		if (perf_evsel__open(evsels[i], cpus, threads, false, false) < 0) {
+		if (perf_evsel__open(evsels[i], cpus, threads, false) < 0) {
 			pr_debug("failed to open counter: %s, "
 				 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 				 strerror(errno));
@@ -549,7 +550,7 @@ static int test__basic_mmap(void)
 			++foo;
 		}
 
-	while ((event = perf_evlist__read_on_cpu(evlist, 0)) != NULL) {
+	while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
 		struct perf_sample sample;
 
 		if (event->header.type != PERF_RECORD_SAMPLE) {
@@ -558,7 +559,13 @@ static int test__basic_mmap(void)
 			goto out_munmap;
 		}
 
-		perf_event__parse_sample(event, attr.sample_type, false, &sample);
+		err = perf_event__parse_sample(event, attr.sample_type, sample_size,
+					       false, &sample);
+		if (err) {
+			pr_err("Can't parse sample, err = %d\n", err);
+			goto out_munmap;
+		}
+
 		evsel = perf_evlist__id2evsel(evlist, sample.id);
 		if (evsel == NULL) {
 			pr_debug("event with id %" PRIu64
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 676b4fb0070f..f2f3f4937aa2 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -62,8 +62,6 @@
 #include <linux/unistd.h>
 #include <linux/types.h>
 
-#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
-
 static struct perf_top top = {
 	.count_filter		= 5,
 	.delay_secs		= 2,
@@ -82,6 +80,8 @@ static bool			use_tui, use_stdio;
 
 static int			default_interval		=      0;
 
+static bool			kptr_restrict_warned;
+static bool			vmlinux_warned;
 static bool			inherit				=  false;
 static int			realtime_prio			=      0;
 static bool			group				=  false;
@@ -740,7 +740,22 @@ static void perf_event__process_sample(const union perf_event *event,
 	    al.filtered)
 		return;
 
+	if (!kptr_restrict_warned &&
+	    symbol_conf.kptr_restrict &&
+	    al.cpumode == PERF_RECORD_MISC_KERNEL) {
+		ui__warning(
+"Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
+"Check /proc/sys/kernel/kptr_restrict.\n\n"
+"Kernel%s samples will not be resolved.\n",
+			  !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
+			  " modules" : "");
+		if (use_browser <= 0)
+			sleep(5);
+		kptr_restrict_warned = true;
+	}
+
 	if (al.sym == NULL) {
+		const char *msg = "Kernel samples will not be resolved.\n";
 		/*
 		 * As we do lazy loading of symtabs we only will know if the
 		 * specified vmlinux file is invalid when we actually have a
@@ -752,12 +767,20 @@ static void perf_event__process_sample(const union perf_event *event,
 		 * --hide-kernel-symbols, even if the user specifies an
 		 * invalid --vmlinux ;-)
 		 */
-		if (al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
+		if (!kptr_restrict_warned && !vmlinux_warned &&
+		    al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
 		    RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) {
-			ui__warning("The %s file can't be used\n",
-				    symbol_conf.vmlinux_name);
-			exit_browser(0);
-			exit(1);
+			if (symbol_conf.vmlinux_name) {
+				ui__warning("The %s file can't be used.\n%s",
+					    symbol_conf.vmlinux_name, msg);
+			} else {
+				ui__warning("A vmlinux file was not found.\n%s",
+					    msg);
+			}
+
+			if (use_browser <= 0)
+				sleep(5);
+			vmlinux_warned = true;
 		}
 
 		return;
@@ -801,13 +824,18 @@ static void perf_event__process_sample(const union perf_event *event,
 	}
 }
 
-static void perf_session__mmap_read_cpu(struct perf_session *self, int cpu)
+static void perf_session__mmap_read_idx(struct perf_session *self, int idx)
 {
 	struct perf_sample sample;
 	union perf_event *event;
+	int ret;
 
-	while ((event = perf_evlist__read_on_cpu(top.evlist, cpu)) != NULL) {
-		perf_session__parse_sample(self, event, &sample);
+	while ((event = perf_evlist__mmap_read(top.evlist, idx)) != NULL) {
+		ret = perf_session__parse_sample(self, event, &sample);
+		if (ret) {
+			pr_err("Can't parse sample, err = %d\n", ret);
+			continue;
+		}
 
 		if (event->header.type == PERF_RECORD_SAMPLE)
 			perf_event__process_sample(event, &sample, self);
@@ -820,8 +848,8 @@ static void perf_session__mmap_read(struct perf_session *self)
 {
 	int i;
 
-	for (i = 0; i < top.evlist->cpus->nr; i++)
-		perf_session__mmap_read_cpu(self, i);
+	for (i = 0; i < top.evlist->nr_mmaps; i++)
+		perf_session__mmap_read_idx(self, i);
 }
 
 static void start_counters(struct perf_evlist *evlist)
@@ -845,15 +873,16 @@ static void start_counters(struct perf_evlist *evlist)
 		}
 
 		attr->mmap = 1;
+		attr->inherit = inherit;
 try_again:
 		if (perf_evsel__open(counter, top.evlist->cpus,
-				     top.evlist->threads, group, inherit) < 0) {
+				     top.evlist->threads, group) < 0) {
 			int err = errno;
 
-			if (err == EPERM || err == EACCES)
-				die("Permission error - are you root?\n"
-					"\t Consider tweaking"
-					" /proc/sys/kernel/perf_event_paranoid.\n");
+			if (err == EPERM || err == EACCES) {
+				ui__warning_paranoid();
+				goto out_err;
+			}
 			/*
 			 * If it's cycles then fall back to hrtimer
 			 * based cpu-clock-tick sw counter, which
@@ -861,25 +890,41 @@ try_again:
 			 */
 			if (attr->type == PERF_TYPE_HARDWARE &&
 			    attr->config == PERF_COUNT_HW_CPU_CYCLES) {
-
 				if (verbose)
-					warning(" ... trying to fall back to cpu-clock-ticks\n");
+					ui__warning("Cycles event not supported,\n"
+						    "trying to fall back to cpu-clock-ticks\n");
 
 				attr->type = PERF_TYPE_SOFTWARE;
 				attr->config = PERF_COUNT_SW_CPU_CLOCK;
 				goto try_again;
 			}
-			printf("\n");
-			error("sys_perf_event_open() syscall returned with %d "
-			      "(%s).  /bin/dmesg may provide additional information.\n",
-			      err, strerror(err));
-			die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
-			exit(-1);
+
+			if (err == ENOENT) {
+				ui__warning("The %s event is not supported.\n",
+					    event_name(counter));
+				goto out_err;
+			}
+
+			ui__warning("The sys_perf_event_open() syscall "
+				    "returned with %d (%s).  /bin/dmesg "
+				    "may provide additional information.\n"
+				    "No CONFIG_PERF_EVENTS=y kernel support "
+				    "configured?\n", err, strerror(err));
+			goto out_err;
 		}
 	}
 
-	if (perf_evlist__mmap(evlist, mmap_pages, false) < 0)
-		die("failed to mmap with %d (%s)\n", errno, strerror(errno));
+	if (perf_evlist__mmap(evlist, mmap_pages, false) < 0) {
+		ui__warning("Failed to mmap with %d (%s)\n",
+			    errno, strerror(errno));
+		goto out_err;
+	}
+
+	return;
+
+out_err:
+	exit_browser(0);
+	exit(0);
 }
 
 static int __cmd_top(void)
diff --git a/tools/perf/feature-tests.mak b/tools/perf/config/feature-tests.mak
index b041ca67a2cb..6170fd2531b5 100644
--- a/tools/perf/feature-tests.mak
+++ b/tools/perf/config/feature-tests.mak
@@ -79,9 +79,15 @@ endef
 endif
 
 ifndef NO_LIBPYTHON
+define SOURCE_PYTHON_VERSION
+#include <Python.h>
+#if PY_VERSION_HEX >= 0x03000000
+	#error
+#endif
+int main(void){}
+endef
 define SOURCE_PYTHON_EMBED
 #include <Python.h>
-
 int main(void)
 {
 	Py_Initialize();
@@ -120,11 +126,3 @@ int main(void)
 	return 0;
 }
 endef
-
-# try-cc
-# Usage: option = $(call try-cc, source-to-build, cc-options)
-try-cc = $(shell sh -c						  \
-	'TMP="$(OUTPUT)$(TMPOUT).$$$$";				  \
-	 echo "$(1)" |						  \
-	 $(CC) -x c - $(2) -o "$$TMP" > /dev/null 2>&1 && echo y; \
-	 rm -f "$$TMP"')
diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak
new file mode 100644
index 000000000000..8046182a19eb
--- /dev/null
+++ b/tools/perf/config/utilities.mak
@@ -0,0 +1,188 @@
+# This allows us to work with the newline character:
+define newline
+
+
+endef
+newline := $(newline)
+
+# nl-escape
+#
+# Usage: escape = $(call nl-escape[,escape])
+#
+# This is used as the common way to specify
+# what should replace a newline when escaping
+# newlines; the default is a bizarre string.
+#
+nl-escape = $(or $(1),m822df3020w6a44id34bt574ctac44eb9f4n)
+
+# escape-nl
+#
+# Usage: escaped-text = $(call escape-nl,text[,escape])
+#
+# GNU make's $(shell ...) function converts to a
+# single space each newline character in the output
+# produced during the expansion; this may not be
+# desirable.
+#
+# The only solution is to change each newline into
+# something that won't be converted, so that the
+# information can be recovered later with
+# $(call unescape-nl...)
+#
+escape-nl = $(subst $(newline),$(call nl-escape,$(2)),$(1))
+
+# unescape-nl
+#
+# Usage: text = $(call unescape-nl,escaped-text[,escape])
+#
+# See escape-nl.
+#
+unescape-nl = $(subst $(call nl-escape,$(2)),$(newline),$(1))
+
+# shell-escape-nl
+#
+# Usage: $(shell some-command | $(call shell-escape-nl[,escape]))
+#
+# Use this to escape newlines from within a shell call;
+# the default escape is a bizarre string.
+#
+# NOTE: The escape is used directly as a string constant
+#       in an `awk' program that is delimited by shell
+#       single-quotes, so be wary of the characters
+#       that are chosen.
+#
+define shell-escape-nl
+awk 'NR==1 {t=$$0} NR>1 {t=t "$(nl-escape)" $$0} END {printf t}'
+endef
+
+# shell-unescape-nl
+#
+# Usage: $(shell some-command | $(call shell-unescape-nl[,escape]))
+#
+# Use this to unescape newlines from within a shell call;
+# the default escape is a bizarre string.
+#
+# NOTE: The escape is used directly as an extended regular
+#       expression constant in an `awk' program that is
+#       delimited by shell single-quotes, so be wary
+#       of the characters that are chosen.
+#
+# (The bash shell has a bug where `{gsub(...),...}' is
+#  misinterpreted as a brace expansion; this can be
+#  overcome by putting a space between `{' and `gsub').
+#
+define shell-unescape-nl
+awk 'NR==1 {t=$$0} NR>1 {t=t "\n" $$0} END { gsub(/$(nl-escape)/,"\n",t); printf t }'
+endef
+
+# escape-for-shell-sq
+#
+# Usage: embeddable-text = $(call escape-for-shell-sq,text)
+#
+# This function produces text that is suitable for
+# embedding in a shell string that is delimited by
+# single-quotes.
+#
+escape-for-shell-sq =  $(subst ','\'',$(1))
+
+# shell-sq
+#
+# Usage: single-quoted-and-escaped-text = $(call shell-sq,text)
+#
+shell-sq = '$(escape-for-shell-sq)'
+
+# shell-wordify
+#
+# Usage: wordified-text = $(call shell-wordify,text)
+#
+# For instance:
+#
+#  |define text
+#  |hello
+#  |world
+#  |endef
+#  |
+#  |target:
+#  |	echo $(call shell-wordify,$(text))
+#
+# At least GNU make gets confused by expanding a newline
+# within the context of a command line of a makefile rule
+# (this is in constrast to a `$(shell ...)' function call,
+# which can handle it just fine).
+#
+# This function avoids the problem by producing a string
+# that works as a shell word, regardless of whether or
+# not it contains a newline.
+#
+# If the text to be wordified contains a newline, then
+# an intrictate shell command substitution is constructed
+# to render the text as a single line; when the shell
+# processes the resulting escaped text, it transforms
+# it into the original unescaped text.
+#
+# If the text does not contain a newline, then this function
+# produces the same results as the `$(shell-sq)' function.
+#
+shell-wordify = $(if $(findstring $(newline),$(1)),$(_sw-esc-nl),$(shell-sq))
+define _sw-esc-nl
+"$$(echo $(call escape-nl,$(shell-sq),$(2)) | $(call shell-unescape-nl,$(2)))"
+endef
+
+# is-absolute
+#
+# Usage: bool-value = $(call is-absolute,path)
+#
+is-absolute = $(shell echo $(shell-sq) | grep ^/ -q && echo y)
+
+# lookup
+#
+# Usage: absolute-executable-path-or-empty = $(call lookup,path)
+#
+# (It's necessary to use `sh -c' because GNU make messes up by
+#  trying too hard and getting things wrong).
+#
+lookup = $(call unescape-nl,$(shell sh -c $(_l-sh)))
+_l-sh = $(call shell-sq,command -v $(shell-sq) | $(call shell-escape-nl,))
+
+# is-executable
+#
+# Usage: bool-value = $(call is-executable,path)
+#
+# (It's necessary to use `sh -c' because GNU make messes up by
+#  trying too hard and getting things wrong).
+#
+is-executable = $(call _is-executable-helper,$(shell-sq))
+_is-executable-helper = $(shell sh -c $(_is-executable-sh))
+_is-executable-sh = $(call shell-sq,test -f $(1) -a -x $(1) && echo y)
+
+# get-executable
+#
+# Usage: absolute-executable-path-or-empty = $(call get-executable,path)
+#
+# The goal is to get an absolute path for an executable;
+# the `command -v' is defined by POSIX, but it's not
+# necessarily very portable, so it's only used if
+# relative path resolution is requested, as determined
+# by the presence of a leading `/'.
+#
+get-executable = $(if $(1),$(if $(is-absolute),$(_ge-abspath),$(lookup)))
+_ge-abspath = $(if $(is-executable),$(1))
+
+# get-supplied-or-default-executable
+#
+# Usage: absolute-executable-path-or-empty = $(call get-executable-or-default,variable,default)
+#
+define get-executable-or-default
+$(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2)))
+endef
+_ge_attempt = $(or $(get-executable),$(_gea_warn),$(call _gea_err,$(2)))
+_gea_warn = $(warning The path '$(1)' is not executable.)
+_gea_err  = $(if $(1),$(error Please set '$(1)' appropriately))
+
+# try-cc
+# Usage: option = $(call try-cc, source-to-build, cc-options)
+try-cc = $(shell sh -c						  \
+	'TMP="$(OUTPUT)$(TMPOUT).$$$$";				  \
+	 echo "$(1)" |						  \
+	 $(CC) -x c - $(2) -o "$$TMP" > /dev/null 2>&1 && echo y; \
+	 rm -f "$$TMP"')
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 9fea75535221..96bee5c46008 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -13,7 +13,7 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen)
 {
 	FILE *fp;
 	char mountpoint[MAX_PATH+1], tokens[MAX_PATH+1], type[MAX_PATH+1];
-	char *token, *saved_ptr;
+	char *token, *saved_ptr = NULL;
 	int found = 0;
 
 	fp = fopen("/proc/mounts", "r");
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index d4536a9e0d8c..155749d74350 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -57,6 +57,16 @@ void ui__warning(const char *format, ...)
 }
 #endif
 
+void ui__warning_paranoid(void)
+{
+	ui__warning("Permission error - are you root?\n"
+		    "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n"
+		    " -1 - Not paranoid at all\n"
+		    "  0 - Disallow raw tracepoint access for unpriv\n"
+		    "  1 - Disallow cpu events for unpriv\n"
+		    "  2 - Disallow kernel profiling for unpriv\n");
+}
+
 void trace_event(union perf_event *event)
 {
 	unsigned char *raw_event = (void *)event;
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 93516cf4682c..fd53db47e3de 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -36,5 +36,6 @@ int ui_helpline__show_help(const char *format, va_list ap);
 #endif
 
 void ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
+void ui__warning_paranoid(void);
 
 #endif	/* __PERF_DEBUG_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 2b15c362ef56..0fe9adf76379 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -9,21 +9,21 @@
 #include "thread_map.h"
 
 static const char *perf_event__names[] = {
-	[0]			 = "TOTAL",
-	[PERF_RECORD_MMAP]	 = "MMAP",
-	[PERF_RECORD_LOST]	 = "LOST",
-	[PERF_RECORD_COMM]	 = "COMM",
-	[PERF_RECORD_EXIT]	 = "EXIT",
-	[PERF_RECORD_THROTTLE]	 = "THROTTLE",
-	[PERF_RECORD_UNTHROTTLE] = "UNTHROTTLE",
-	[PERF_RECORD_FORK]	 = "FORK",
-	[PERF_RECORD_READ]	 = "READ",
-	[PERF_RECORD_SAMPLE]	 = "SAMPLE",
-	[PERF_RECORD_HEADER_ATTR]	 = "ATTR",
-	[PERF_RECORD_HEADER_EVENT_TYPE]	 = "EVENT_TYPE",
-	[PERF_RECORD_HEADER_TRACING_DATA]	 = "TRACING_DATA",
-	[PERF_RECORD_HEADER_BUILD_ID]	 = "BUILD_ID",
-	[PERF_RECORD_FINISHED_ROUND]	 = "FINISHED_ROUND",
+	[0]					= "TOTAL",
+	[PERF_RECORD_MMAP]			= "MMAP",
+	[PERF_RECORD_LOST]			= "LOST",
+	[PERF_RECORD_COMM]			= "COMM",
+	[PERF_RECORD_EXIT]			= "EXIT",
+	[PERF_RECORD_THROTTLE]			= "THROTTLE",
+	[PERF_RECORD_UNTHROTTLE]		= "UNTHROTTLE",
+	[PERF_RECORD_FORK]			= "FORK",
+	[PERF_RECORD_READ]			= "READ",
+	[PERF_RECORD_SAMPLE]			= "SAMPLE",
+	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
+	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
+	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
+	[PERF_RECORD_HEADER_BUILD_ID]		= "BUILD_ID",
+	[PERF_RECORD_FINISHED_ROUND]		= "FINISHED_ROUND",
 };
 
 const char *perf_event__name(unsigned int id)
@@ -35,6 +35,22 @@ const char *perf_event__name(unsigned int id)
 	return perf_event__names[id];
 }
 
+int perf_sample_size(u64 sample_type)
+{
+	u64 mask = sample_type & PERF_SAMPLE_MASK;
+	int size = 0;
+	int i;
+
+	for (i = 0; i < 64; i++) {
+		if (mask & (1ULL << i))
+			size++;
+	}
+
+	size *= sizeof(u64);
+
+	return size;
+}
+
 static struct perf_sample synth_sample = {
 	.pid	   = -1,
 	.tid	   = -1,
@@ -537,9 +553,18 @@ static int perf_event__process_kernel_mmap(union perf_event *event,
 			goto out_problem;
 
 		perf_event__set_kernel_mmap_len(event, machine->vmlinux_maps);
-		perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
-							 symbol_name,
-							 event->mmap.pgoff);
+
+		/*
+		 * Avoid using a zero address (kptr_restrict) for the ref reloc
+		 * symbol. Effectively having zero here means that at record
+		 * time /proc/sys/kernel/kptr_restrict was non zero.
+		 */
+		if (event->mmap.pgoff != 0) {
+			perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
+								 symbol_name,
+								 event->mmap.pgoff);
+		}
+
 		if (machine__is_default_guest(machine)) {
 			/*
 			 * preload dso of guest kernel and modules
@@ -710,7 +735,7 @@ try_again:
 		 * in the whole kernel symbol list.
 		 */
 		if ((long long)al->addr < 0 &&
-		    cpumode == PERF_RECORD_MISC_KERNEL &&
+		    cpumode == PERF_RECORD_MISC_USER &&
 		    machine && mg != &machine->kmaps) {
 			mg = &machine->kmaps;
 			goto try_again;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 9c35170fb379..c08332871408 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -56,6 +56,13 @@ struct read_event {
 	u64 id;
 };
 
+
+#define PERF_SAMPLE_MASK				\
+	(PERF_SAMPLE_IP | PERF_SAMPLE_TID |		\
+	 PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR |		\
+	PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID |	\
+	 PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
+
 struct sample_event {
 	struct perf_event_header        header;
 	u64 array[];
@@ -75,6 +82,8 @@ struct perf_sample {
 	struct ip_callchain *callchain;
 };
 
+int perf_sample_size(u64 sample_type);
+
 #define BUILD_ID_SIZE 20
 
 struct build_id_event {
@@ -178,6 +187,7 @@ int perf_event__preprocess_sample(const union perf_event *self,
 const char *perf_event__name(unsigned int id);
 
 int perf_event__parse_sample(const union perf_event *event, u64 type,
-			     bool sample_id_all, struct perf_sample *sample);
+			     int sample_size, bool sample_id_all,
+			     struct perf_sample *sample);
 
 #endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d852cefa20de..50aa34879c33 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -12,6 +12,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "util.h"
+#include "debug.h"
 
 #include <sys/mman.h>
 
@@ -165,11 +166,11 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
 	return NULL;
 }
 
-union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *evlist, int cpu)
+union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 {
 	/* XXX Move this to perf.c, making it generally available */
 	unsigned int page_size = sysconf(_SC_PAGE_SIZE);
-	struct perf_mmap *md = &evlist->mmap[cpu];
+	struct perf_mmap *md = &evlist->mmap[idx];
 	unsigned int head = perf_mmap__read_head(md);
 	unsigned int old = md->prev;
 	unsigned char *data = md->base + page_size;
@@ -234,36 +235,126 @@ union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *evlist, int cpu)
 
 void perf_evlist__munmap(struct perf_evlist *evlist)
 {
-	int cpu;
+	int i;
 
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
-		if (evlist->mmap[cpu].base != NULL) {
-			munmap(evlist->mmap[cpu].base, evlist->mmap_len);
-			evlist->mmap[cpu].base = NULL;
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		if (evlist->mmap[i].base != NULL) {
+			munmap(evlist->mmap[i].base, evlist->mmap_len);
+			evlist->mmap[i].base = NULL;
 		}
 	}
+
+	free(evlist->mmap);
+	evlist->mmap = NULL;
 }
 
 int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 {
-	evlist->mmap = zalloc(evlist->cpus->nr * sizeof(struct perf_mmap));
+	evlist->nr_mmaps = evlist->cpus->nr;
+	if (evlist->cpus->map[0] == -1)
+		evlist->nr_mmaps = evlist->threads->nr;
+	evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
 	return evlist->mmap != NULL ? 0 : -ENOMEM;
 }
 
-static int __perf_evlist__mmap(struct perf_evlist *evlist, int cpu, int prot,
-			       int mask, int fd)
+static int __perf_evlist__mmap(struct perf_evlist *evlist, struct perf_evsel *evsel,
+			       int idx, int prot, int mask, int fd)
 {
-	evlist->mmap[cpu].prev = 0;
-	evlist->mmap[cpu].mask = mask;
-	evlist->mmap[cpu].base = mmap(NULL, evlist->mmap_len, prot,
+	evlist->mmap[idx].prev = 0;
+	evlist->mmap[idx].mask = mask;
+	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot,
 				      MAP_SHARED, fd, 0);
-	if (evlist->mmap[cpu].base == MAP_FAILED)
+	if (evlist->mmap[idx].base == MAP_FAILED) {
+		if (evlist->cpus->map[idx] == -1 && evsel->attr.inherit)
+			ui__warning("Inherit is not allowed on per-task "
+				    "events using mmap.\n");
 		return -1;
+	}
 
 	perf_evlist__add_pollfd(evlist, fd);
 	return 0;
 }
 
+static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int mask)
+{
+	struct perf_evsel *evsel;
+	int cpu, thread;
+
+	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+		int output = -1;
+
+		for (thread = 0; thread < evlist->threads->nr; thread++) {
+			list_for_each_entry(evsel, &evlist->entries, node) {
+				int fd = FD(evsel, cpu, thread);
+
+				if (output == -1) {
+					output = fd;
+					if (__perf_evlist__mmap(evlist, evsel, cpu,
+								prot, mask, output) < 0)
+						goto out_unmap;
+				} else {
+					if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0)
+						goto out_unmap;
+				}
+
+				if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+				    perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
+					goto out_unmap;
+			}
+		}
+	}
+
+	return 0;
+
+out_unmap:
+	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+		if (evlist->mmap[cpu].base != NULL) {
+			munmap(evlist->mmap[cpu].base, evlist->mmap_len);
+			evlist->mmap[cpu].base = NULL;
+		}
+	}
+	return -1;
+}
+
+static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, int mask)
+{
+	struct perf_evsel *evsel;
+	int thread;
+
+	for (thread = 0; thread < evlist->threads->nr; thread++) {
+		int output = -1;
+
+		list_for_each_entry(evsel, &evlist->entries, node) {
+			int fd = FD(evsel, 0, thread);
+
+			if (output == -1) {
+				output = fd;
+				if (__perf_evlist__mmap(evlist, evsel, thread,
+							prot, mask, output) < 0)
+					goto out_unmap;
+			} else {
+				if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0)
+					goto out_unmap;
+			}
+
+			if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+			    perf_evlist__id_add_fd(evlist, evsel, 0, thread, fd) < 0)
+				goto out_unmap;
+		}
+	}
+
+	return 0;
+
+out_unmap:
+	for (thread = 0; thread < evlist->threads->nr; thread++) {
+		if (evlist->mmap[thread].base != NULL) {
+			munmap(evlist->mmap[thread].base, evlist->mmap_len);
+			evlist->mmap[thread].base = NULL;
+		}
+	}
+	return -1;
+}
+
 /** perf_evlist__mmap - Create per cpu maps to receive events
  *
  * @evlist - list of events
@@ -282,11 +373,11 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int cpu, int prot,
 int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite)
 {
 	unsigned int page_size = sysconf(_SC_PAGE_SIZE);
-	int mask = pages * page_size - 1, cpu;
-	struct perf_evsel *first_evsel, *evsel;
+	int mask = pages * page_size - 1;
+	struct perf_evsel *evsel;
 	const struct cpu_map *cpus = evlist->cpus;
 	const struct thread_map *threads = evlist->threads;
-	int thread, prot = PROT_READ | (overwrite ? 0 : PROT_WRITE);
+	int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE);
 
 	if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
 		return -ENOMEM;
@@ -296,42 +387,18 @@ int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite)
 
 	evlist->overwrite = overwrite;
 	evlist->mmap_len = (pages + 1) * page_size;
-	first_evsel = list_entry(evlist->entries.next, struct perf_evsel, node);
 
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
 		    evsel->sample_id == NULL &&
 		    perf_evsel__alloc_id(evsel, cpus->nr, threads->nr) < 0)
 			return -ENOMEM;
-
-		for (cpu = 0; cpu < cpus->nr; cpu++) {
-			for (thread = 0; thread < threads->nr; thread++) {
-				int fd = FD(evsel, cpu, thread);
-
-				if (evsel->idx || thread) {
-					if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT,
-						  FD(first_evsel, cpu, 0)) != 0)
-						goto out_unmap;
-				} else if (__perf_evlist__mmap(evlist, cpu, prot, mask, fd) < 0)
-					goto out_unmap;
-
-				if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
-				    perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
-					goto out_unmap;
-			}
-		}
 	}
 
-	return 0;
+	if (evlist->cpus->map[0] == -1)
+		return perf_evlist__mmap_per_thread(evlist, prot, mask);
 
-out_unmap:
-	for (cpu = 0; cpu < cpus->nr; cpu++) {
-		if (evlist->mmap[cpu].base != NULL) {
-			munmap(evlist->mmap[cpu].base, evlist->mmap_len);
-			evlist->mmap[cpu].base = NULL;
-		}
-	}
-	return -1;
+	return perf_evlist__mmap_per_cpu(evlist, prot, mask);
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
@@ -342,7 +409,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
 	if (evlist->threads == NULL)
 		return -1;
 
-	if (target_tid != -1)
+	if (cpu_list == NULL && target_tid != -1)
 		evlist->cpus = cpu_map__dummy_new();
 	else
 		evlist->cpus = cpu_map__new(cpu_list);
@@ -392,3 +459,34 @@ int perf_evlist__set_filters(struct perf_evlist *evlist)
 
 	return 0;
 }
+
+u64 perf_evlist__sample_type(struct perf_evlist *evlist)
+{
+	struct perf_evsel *pos;
+	u64 type = 0;
+
+	list_for_each_entry(pos, &evlist->entries, node) {
+		if (!type)
+			type = pos->attr.sample_type;
+		else if (type != pos->attr.sample_type)
+			die("non matching sample_type");
+	}
+
+	return type;
+}
+
+bool perf_evlist__sample_id_all(const struct perf_evlist *evlist)
+{
+	bool value = false, first = true;
+	struct perf_evsel *pos;
+
+	list_for_each_entry(pos, &evlist->entries, node) {
+		if (first) {
+			value = pos->attr.sample_id_all;
+			first = false;
+		} else if (value != pos->attr.sample_id_all)
+			die("non matching sample_id_all");
+	}
+
+	return value;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 8b1cb7a4c5f1..0a1ef1f051f0 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -17,6 +17,7 @@ struct perf_evlist {
 	struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
 	int		 nr_entries;
 	int		 nr_fds;
+	int		 nr_mmaps;
 	int		 mmap_len;
 	bool		 overwrite;
 	union perf_event event_copy;
@@ -46,7 +47,7 @@ void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
 
 struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
 
-union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *self, int cpu);
+union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
 
 int perf_evlist__alloc_mmap(struct perf_evlist *evlist);
 int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite);
@@ -65,4 +66,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
 void perf_evlist__delete_maps(struct perf_evlist *evlist);
 int perf_evlist__set_filters(struct perf_evlist *evlist);
 
+u64 perf_evlist__sample_type(struct perf_evlist *evlist);
+bool perf_evlist__sample_id_all(const struct perf_evlist *evlist);
+
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 662596afd7f1..cca29ededb5b 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -35,7 +35,17 @@ struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
+	int cpu, thread;
 	evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
+
+	if (evsel->fd) {
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			for (thread = 0; thread < nthreads; thread++) {
+				FD(evsel, cpu, thread) = -1;
+			}
+		}
+	}
+
 	return evsel->fd != NULL ? 0 : -ENOMEM;
 }
 
@@ -175,7 +185,7 @@ int __perf_evsel__read(struct perf_evsel *evsel,
 }
 
 static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-			      struct thread_map *threads, bool group, bool inherit)
+			      struct thread_map *threads, bool group)
 {
 	int cpu, thread;
 	unsigned long flags = 0;
@@ -192,19 +202,6 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 		int group_fd = -1;
-		/*
-		 * Don't allow mmap() of inherited per-task counters. This
-		 * would create a performance issue due to all children writing
-		 * to the same buffer.
-		 *
-		 * FIXME:
-		 * Proper fix is not to pass 'inherit' to perf_evsel__open*,
-		 * but a 'flags' parameter, with 'group' folded there as well,
-		 * then introduce a PERF_O_{MMAP,GROUP,INHERIT} enum, and if
-		 * O_MMAP is set, emit a warning if cpu < 0 and O_INHERIT is
-		 * set. Lets go for the minimal fix first tho.
-		 */
-		evsel->attr.inherit = (cpus->map[cpu] >= 0) && inherit;
 
 		for (thread = 0; thread < threads->nr; thread++) {
 
@@ -253,7 +250,7 @@ static struct {
 };
 
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-		     struct thread_map *threads, bool group, bool inherit)
+		     struct thread_map *threads, bool group)
 {
 	if (cpus == NULL) {
 		/* Work around old compiler warnings about strict aliasing */
@@ -263,19 +260,19 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 	if (threads == NULL)
 		threads = &empty_thread_map.map;
 
-	return __perf_evsel__open(evsel, cpus, threads, group, inherit);
+	return __perf_evsel__open(evsel, cpus, threads, group);
 }
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
-			     struct cpu_map *cpus, bool group, bool inherit)
+			     struct cpu_map *cpus, bool group)
 {
-	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group, inherit);
+	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group);
 }
 
 int perf_evsel__open_per_thread(struct perf_evsel *evsel,
-				struct thread_map *threads, bool group, bool inherit)
+				struct thread_map *threads, bool group)
 {
-	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group, inherit);
+	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group);
 }
 
 static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
@@ -316,8 +313,20 @@ static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
 	return 0;
 }
 
+static bool sample_overlap(const union perf_event *event,
+			   const void *offset, u64 size)
+{
+	const void *base = event;
+
+	if (offset + size > base + event->header.size)
+		return true;
+
+	return false;
+}
+
 int perf_event__parse_sample(const union perf_event *event, u64 type,
-			     bool sample_id_all, struct perf_sample *data)
+			     int sample_size, bool sample_id_all,
+			     struct perf_sample *data)
 {
 	const u64 *array;
 
@@ -332,6 +341,9 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 
 	array = event->sample.array;
 
+	if (sample_size + sizeof(event->header) > event->header.size)
+		return -EFAULT;
+
 	if (type & PERF_SAMPLE_IP) {
 		data->ip = event->ip.ip;
 		array++;
@@ -382,14 +394,29 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	}
 
 	if (type & PERF_SAMPLE_CALLCHAIN) {
+		if (sample_overlap(event, array, sizeof(data->callchain->nr)))
+			return -EFAULT;
+
 		data->callchain = (struct ip_callchain *)array;
+
+		if (sample_overlap(event, array, data->callchain->nr))
+			return -EFAULT;
+
 		array += 1 + data->callchain->nr;
 	}
 
 	if (type & PERF_SAMPLE_RAW) {
 		u32 *p = (u32 *)array;
+
+		if (sample_overlap(event, array, sizeof(u32)))
+			return -EFAULT;
+
 		data->raw_size = *p;
 		p++;
+
+		if (sample_overlap(event, p, data->raw_size))
+			return -EFAULT;
+
 		data->raw_data = p;
 	}
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 6710ab538342..f79bb2c09a6c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -81,11 +81,11 @@ void perf_evsel__free_id(struct perf_evsel *evsel);
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
-			     struct cpu_map *cpus, bool group, bool inherit);
+			     struct cpu_map *cpus, bool group);
 int perf_evsel__open_per_thread(struct perf_evsel *evsel,
-				struct thread_map *threads, bool group, bool inherit);
+				struct thread_map *threads, bool group);
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-		     struct thread_map *threads, bool group, bool inherit);
+		     struct thread_map *threads, bool group);
 
 #define perf_evsel__match(evsel, t, c)		\
 	(evsel->attr.type == PERF_TYPE_##t &&	\
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 93862a8027ea..afb0849fe530 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -193,9 +193,13 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 	     *linkname = malloc(size), *targetname;
 	int len, err = -1;
 
-	if (is_kallsyms)
+	if (is_kallsyms) {
+		if (symbol_conf.kptr_restrict) {
+			pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
+			return 0;
+		}
 		realname = (char *)name;
-	else
+	} else
 		realname = realpath(name, NULL);
 
 	if (realname == NULL || filename == NULL || linkname == NULL)
@@ -934,37 +938,6 @@ out_delete_evlist:
 	return -ENOMEM;
 }
 
-u64 perf_evlist__sample_type(struct perf_evlist *evlist)
-{
-	struct perf_evsel *pos;
-	u64 type = 0;
-
-	list_for_each_entry(pos, &evlist->entries, node) {
-		if (!type)
-			type = pos->attr.sample_type;
-		else if (type != pos->attr.sample_type)
-			die("non matching sample_type");
-	}
-
-	return type;
-}
-
-bool perf_evlist__sample_id_all(const struct perf_evlist *evlist)
-{
-	bool value = false, first = true;
-	struct perf_evsel *pos;
-
-	list_for_each_entry(pos, &evlist->entries, node) {
-		if (first) {
-			value = pos->attr.sample_id_all;
-			first = false;
-		} else if (value != pos->attr.sample_id_all)
-			die("non matching sample_id_all");
-	}
-
-	return value;
-}
-
 int perf_event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
 				perf_event__handler_t process,
 				struct perf_session *session)
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 456661d7f10e..1886256768a1 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -64,8 +64,6 @@ int perf_header__write_pipe(int fd);
 int perf_header__push_event(u64 id, const char *name);
 char *perf_header__find_event(u64 id);
 
-u64 perf_evlist__sample_type(struct perf_evlist *evlist);
-bool perf_evlist__sample_id_all(const struct perf_evlist *evlist);
 void perf_header__set_feat(struct perf_header *header, int feat);
 void perf_header__clear_feat(struct perf_header *header, int feat);
 bool perf_header__has_feat(const struct perf_header *header, int feat);
diff --git a/tools/perf/util/include/asm/alternative-asm.h b/tools/perf/util/include/asm/alternative-asm.h
new file mode 100644
index 000000000000..6789d788d494
--- /dev/null
+++ b/tools/perf/util/include/asm/alternative-asm.h
@@ -0,0 +1,8 @@
+#ifndef _PERF_ASM_ALTERNATIVE_ASM_H
+#define _PERF_ASM_ALTERNATIVE_ASM_H
+
+/* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */
+
+#define altinstruction_entry #
+
+#endif
diff --git a/tools/perf/util/include/linux/const.h b/tools/perf/util/include/linux/const.h
new file mode 100644
index 000000000000..1b476c9ae649
--- /dev/null
+++ b/tools/perf/util/include/linux/const.h
@@ -0,0 +1 @@
+#include "../../../../include/linux/const.h"
diff --git a/tools/perf/util/include/linux/list.h b/tools/perf/util/include/linux/list.h
index 356c7e467b83..1d928a0ce997 100644
--- a/tools/perf/util/include/linux/list.h
+++ b/tools/perf/util/include/linux/list.h
@@ -1,4 +1,6 @@
 #include <linux/kernel.h>
+#include <linux/prefetch.h>
+
 #include "../../../../include/linux/list.h"
 
 #ifndef PERF_LIST_H
@@ -23,5 +25,5 @@ static inline void list_del_range(struct list_head *begin,
  * @head: the head for your list.
  */
 #define list_for_each_from(pos, head) \
-	for (; prefetch(pos->next), pos != (head); pos = pos->next)
+	for (; pos != (head); pos = pos->next)
 #endif
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 952b4ae3d954..41982c373faf 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -31,34 +31,36 @@ char debugfs_path[MAXPATHLEN];
 #define CSW(x) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_##x
 
 static struct event_symbol event_symbols[] = {
-  { CHW(CPU_CYCLES),		"cpu-cycles",		"cycles"	},
-  { CHW(INSTRUCTIONS),		"instructions",		""		},
-  { CHW(CACHE_REFERENCES),	"cache-references",	""		},
-  { CHW(CACHE_MISSES),		"cache-misses",		""		},
-  { CHW(BRANCH_INSTRUCTIONS),	"branch-instructions",	"branches"	},
-  { CHW(BRANCH_MISSES),		"branch-misses",	""		},
-  { CHW(BUS_CYCLES),		"bus-cycles",		""		},
-
-  { CSW(CPU_CLOCK),		"cpu-clock",		""		},
-  { CSW(TASK_CLOCK),		"task-clock",		""		},
-  { CSW(PAGE_FAULTS),		"page-faults",		"faults"	},
-  { CSW(PAGE_FAULTS_MIN),	"minor-faults",		""		},
-  { CSW(PAGE_FAULTS_MAJ),	"major-faults",		""		},
-  { CSW(CONTEXT_SWITCHES),	"context-switches",	"cs"		},
-  { CSW(CPU_MIGRATIONS),	"cpu-migrations",	"migrations"	},
-  { CSW(ALIGNMENT_FAULTS),	"alignment-faults",	""		},
-  { CSW(EMULATION_FAULTS),	"emulation-faults",	""		},
+  { CHW(CPU_CYCLES),			"cpu-cycles",			"cycles"		},
+  { CHW(STALLED_CYCLES_FRONTEND),	"stalled-cycles-frontend",	"idle-cycles-frontend"	},
+  { CHW(STALLED_CYCLES_BACKEND),	"stalled-cycles-backend",	"idle-cycles-backend"	},
+  { CHW(INSTRUCTIONS),			"instructions",			""			},
+  { CHW(CACHE_REFERENCES),		"cache-references",		""			},
+  { CHW(CACHE_MISSES),			"cache-misses",			""			},
+  { CHW(BRANCH_INSTRUCTIONS),		"branch-instructions",		"branches"		},
+  { CHW(BRANCH_MISSES),			"branch-misses",		""			},
+  { CHW(BUS_CYCLES),			"bus-cycles",			""			},
+
+  { CSW(CPU_CLOCK),			"cpu-clock",			""			},
+  { CSW(TASK_CLOCK),			"task-clock",			""			},
+  { CSW(PAGE_FAULTS),			"page-faults",			"faults"		},
+  { CSW(PAGE_FAULTS_MIN),		"minor-faults",			""			},
+  { CSW(PAGE_FAULTS_MAJ),		"major-faults",			""			},
+  { CSW(CONTEXT_SWITCHES),		"context-switches",		"cs"			},
+  { CSW(CPU_MIGRATIONS),		"cpu-migrations",		"migrations"		},
+  { CSW(ALIGNMENT_FAULTS),		"alignment-faults",		""			},
+  { CSW(EMULATION_FAULTS),		"emulation-faults",		""			},
 };
 
 #define __PERF_EVENT_FIELD(config, name) \
 	((config & PERF_EVENT_##name##_MASK) >> PERF_EVENT_##name##_SHIFT)
 
-#define PERF_EVENT_RAW(config)	__PERF_EVENT_FIELD(config, RAW)
+#define PERF_EVENT_RAW(config)		__PERF_EVENT_FIELD(config, RAW)
 #define PERF_EVENT_CONFIG(config)	__PERF_EVENT_FIELD(config, CONFIG)
-#define PERF_EVENT_TYPE(config)	__PERF_EVENT_FIELD(config, TYPE)
+#define PERF_EVENT_TYPE(config)		__PERF_EVENT_FIELD(config, TYPE)
 #define PERF_EVENT_ID(config)		__PERF_EVENT_FIELD(config, EVENT)
 
-static const char *hw_event_names[] = {
+static const char *hw_event_names[PERF_COUNT_HW_MAX] = {
 	"cycles",
 	"instructions",
 	"cache-references",
@@ -66,11 +68,13 @@ static const char *hw_event_names[] = {
 	"branches",
 	"branch-misses",
 	"bus-cycles",
+	"stalled-cycles-frontend",
+	"stalled-cycles-backend",
 };
 
-static const char *sw_event_names[] = {
-	"cpu-clock-msecs",
-	"task-clock-msecs",
+static const char *sw_event_names[PERF_COUNT_SW_MAX] = {
+	"cpu-clock",
+	"task-clock",
 	"page-faults",
 	"context-switches",
 	"CPU-migrations",
@@ -307,7 +311,7 @@ const char *__event_name(int type, u64 config)
 
 	switch (type) {
 	case PERF_TYPE_HARDWARE:
-		if (config < PERF_COUNT_HW_MAX)
+		if (config < PERF_COUNT_HW_MAX && hw_event_names[config])
 			return hw_event_names[config];
 		return "unknown-hardware";
 
@@ -333,7 +337,7 @@ const char *__event_name(int type, u64 config)
 	}
 
 	case PERF_TYPE_SOFTWARE:
-		if (config < PERF_COUNT_SW_MAX)
+		if (config < PERF_COUNT_SW_MAX && sw_event_names[config])
 			return sw_event_names[config];
 		return "unknown-software";
 
@@ -648,13 +652,15 @@ static int check_events(const char *str, unsigned int i)
 	int n;
 
 	n = strlen(event_symbols[i].symbol);
-	if (!strncmp(str, event_symbols[i].symbol, n))
+	if (!strncasecmp(str, event_symbols[i].symbol, n))
 		return n;
 
 	n = strlen(event_symbols[i].alias);
-	if (n)
-		if (!strncmp(str, event_symbols[i].alias, n))
+	if (n) {
+		if (!strncasecmp(str, event_symbols[i].alias, n))
 			return n;
+	}
+
 	return 0;
 }
 
@@ -718,15 +724,22 @@ parse_numeric_event(const char **strp, struct perf_event_attr *attr)
 	return EVT_FAILED;
 }
 
-static enum event_result
+static int
 parse_event_modifier(const char **strp, struct perf_event_attr *attr)
 {
 	const char *str = *strp;
 	int exclude = 0;
 	int eu = 0, ek = 0, eh = 0, precise = 0;
 
-	if (*str++ != ':')
+	if (!*str)
+		return 0;
+
+	if (*str == ',')
 		return 0;
+
+	if (*str++ != ':')
+		return -1;
+
 	while (*str) {
 		if (*str == 'u') {
 			if (!exclude)
@@ -747,14 +760,16 @@ parse_event_modifier(const char **strp, struct perf_event_attr *attr)
 
 		++str;
 	}
-	if (str >= *strp + 2) {
-		*strp = str;
-		attr->exclude_user   = eu;
-		attr->exclude_kernel = ek;
-		attr->exclude_hv     = eh;
-		attr->precise_ip     = precise;
-		return 1;
-	}
+	if (str < *strp + 2)
+		return -1;
+
+	*strp = str;
+
+	attr->exclude_user   = eu;
+	attr->exclude_kernel = ek;
+	attr->exclude_hv     = eh;
+	attr->precise_ip     = precise;
+
 	return 0;
 }
 
@@ -797,7 +812,12 @@ parse_event_symbols(const struct option *opt, const char **str,
 	return EVT_FAILED;
 
 modifier:
-	parse_event_modifier(str, attr);
+	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;
+	}
 
 	return ret;
 }
@@ -912,7 +932,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob)
 
 			snprintf(evt_path, MAXPATHLEN, "%s:%s",
 				 sys_dirent.d_name, evt_dirent.d_name);
-			printf("  %-42s [%s]\n", evt_path,
+			printf("  %-50s [%s]\n", evt_path,
 				event_type_descriptors[PERF_TYPE_TRACEPOINT]);
 		}
 		closedir(evt_dir);
@@ -977,7 +997,7 @@ void print_events_type(u8 type)
 		else
 			snprintf(name, sizeof(name), "%s", syms->symbol);
 
-		printf("  %-42s [%s]\n", name,
+		printf("  %-50s [%s]\n", name,
 			event_type_descriptors[type]);
 	}
 }
@@ -995,11 +1015,10 @@ int print_hwcache_events(const char *event_glob)
 			for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
 				char *name = event_cache_name(type, op, i);
 
-				if (event_glob != NULL && 
-				    !strglobmatch(name, event_glob))
+				if (event_glob != NULL && !strglobmatch(name, event_glob))
 					continue;
 
-				printf("  %-42s [%s]\n", name,
+				printf("  %-50s [%s]\n", name,
 					event_type_descriptors[PERF_TYPE_HW_CACHE]);
 				++printed;
 			}
@@ -1009,14 +1028,16 @@ int print_hwcache_events(const char *event_glob)
 	return printed;
 }
 
+#define MAX_NAME_LEN 100
+
 /*
  * Print the help text for the event symbols:
  */
 void print_events(const char *event_glob)
 {
-	struct event_symbol *syms = event_symbols;
 	unsigned int i, type, prev_type = -1, printed = 0, ntypes_printed = 0;
-	char name[40];
+	struct event_symbol *syms = event_symbols;
+	char name[MAX_NAME_LEN];
 
 	printf("\n");
 	printf("List of pre-defined events (to be used in -e):\n");
@@ -1036,10 +1057,10 @@ void print_events(const char *event_glob)
 			continue;
 
 		if (strlen(syms->alias))
-			sprintf(name, "%s OR %s", syms->symbol, syms->alias);
+			snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias);
 		else
-			strcpy(name, syms->symbol);
-		printf("  %-42s [%s]\n", name,
+			strncpy(name, syms->symbol, MAX_NAME_LEN);
+		printf("  %-50s [%s]\n", name,
 			event_type_descriptors[type]);
 
 		prev_type = type;
@@ -1056,12 +1077,12 @@ void print_events(const char *event_glob)
 		return;
 
 	printf("\n");
-	printf("  %-42s [%s]\n",
+	printf("  %-50s [%s]\n",
 		"rNNN (see 'perf list --help' on how to encode it)",
 	       event_type_descriptors[PERF_TYPE_RAW]);
 	printf("\n");
 
-	printf("  %-42s [%s]\n",
+	printf("  %-50s [%s]\n",
 			"mem:<addr>[:access]",
 			event_type_descriptors[PERF_TYPE_BREAKPOINT]);
 	printf("\n");
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 5ddee66020a7..f0223166e761 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -234,7 +234,6 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 
 	/* Searching trace events corresponding to probe event */
 	ntevs = find_probe_trace_events(fd, pev, tevs, max_tevs);
-	close(fd);
 
 	if (ntevs > 0) {	/* Succeeded to find trace events */
 		pr_debug("find %d probe_trace_events.\n", ntevs);
@@ -388,7 +387,6 @@ int show_line_range(struct line_range *lr, const char *module)
 	}
 
 	ret = find_line_range(fd, lr);
-	close(fd);
 	if (ret == 0) {
 		pr_warning("Specified source line is not found.\n");
 		return -ENOENT;
@@ -512,19 +510,18 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 	if (ret < 0)
 		return ret;
 
-	fd = open_vmlinux(module);
-	if (fd < 0) {
-		pr_warning("Failed to open debug information file.\n");
-		return fd;
-	}
-
 	setup_pager();
 
-	for (i = 0; i < npevs && ret >= 0; i++)
+	for (i = 0; i < npevs && ret >= 0; i++) {
+		fd = open_vmlinux(module);
+		if (fd < 0) {
+			pr_warning("Failed to open debug information file.\n");
+			ret = fd;
+			break;
+		}
 		ret = show_available_vars_at(fd, &pevs[i], max_vls, _filter,
 					     externs);
-
-	close(fd);
+	}
 	return ret;
 }
 
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 194f9e2a3285..3b9d0b800d5c 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -273,6 +273,25 @@ static const char *cu_get_comp_dir(Dwarf_Die *cu_die)
 	return dwarf_formstring(&attr);
 }
 
+/* Get a line number and file name for given address */
+static int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr,
+			    const char **fname, int *lineno)
+{
+	Dwarf_Line *line;
+	Dwarf_Addr laddr;
+
+	line = dwarf_getsrc_die(cudie, (Dwarf_Addr)addr);
+	if (line && dwarf_lineaddr(line, &laddr) == 0 &&
+	    addr == (unsigned long)laddr && dwarf_lineno(line, lineno) == 0) {
+		*fname = dwarf_linesrc(line, NULL, NULL);
+		if (!*fname)
+			/* line number is useless without filename */
+			*lineno = 0;
+	}
+
+	return *lineno ?: -ENOENT;
+}
+
 /* Compare diename and tname */
 static bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
 {
@@ -497,7 +516,20 @@ static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data)
 static Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
 				      Dwarf_Die *die_mem)
 {
-	return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem);
+	Dwarf_Die tmp_die;
+
+	sp_die = die_find_child(sp_die, __die_find_inline_cb, &addr, &tmp_die);
+	if (!sp_die)
+		return NULL;
+
+	/* Inlined function could be recursive. Trace it until fail */
+	while (sp_die) {
+		memcpy(die_mem, sp_die, sizeof(Dwarf_Die));
+		sp_die = die_find_child(sp_die, __die_find_inline_cb, &addr,
+					&tmp_die);
+	}
+
+	return die_mem;
 }
 
 /* Walker on lines (Note: line number will not be sorted) */
@@ -1395,6 +1427,10 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 	    !die_compare_name(sp_die, pp->function))
 		return DWARF_CB_OK;
 
+	/* Check declared file */
+	if (pp->file && strtailcmp(pp->file, dwarf_decl_file(sp_die)))
+		return DWARF_CB_OK;
+
 	pf->fname = dwarf_decl_file(sp_die);
 	if (pp->line) { /* Function relative line */
 		dwarf_decl_line(sp_die, &pf->lno);
@@ -1435,6 +1471,38 @@ static int find_probe_point_by_func(struct probe_finder *pf)
 	return _param.retval;
 }
 
+struct pubname_callback_param {
+	char *function;
+	char *file;
+	Dwarf_Die *cu_die;
+	Dwarf_Die *sp_die;
+	int found;
+};
+
+static int pubname_search_cb(Dwarf *dbg, Dwarf_Global *gl, void *data)
+{
+	struct pubname_callback_param *param = data;
+
+	if (dwarf_offdie(dbg, gl->die_offset, param->sp_die)) {
+		if (dwarf_tag(param->sp_die) != DW_TAG_subprogram)
+			return DWARF_CB_OK;
+
+		if (die_compare_name(param->sp_die, param->function)) {
+			if (!dwarf_offdie(dbg, gl->cu_offset, param->cu_die))
+				return DWARF_CB_OK;
+
+			if (param->file &&
+			    strtailcmp(param->file, dwarf_decl_file(param->sp_die)))
+				return DWARF_CB_OK;
+
+			param->found = 1;
+			return DWARF_CB_ABORT;
+		}
+	}
+
+	return DWARF_CB_OK;
+}
+
 /* Find probe points from debuginfo */
 static int find_probes(int fd, struct probe_finder *pf)
 {
@@ -1451,6 +1519,7 @@ static int find_probes(int fd, struct probe_finder *pf)
 	if (!dbg) {
 		pr_warning("No debug information found in the vmlinux - "
 			"please rebuild with CONFIG_DEBUG_INFO=y.\n");
+		close(fd);	/* Without dwfl_end(), fd isn't closed. */
 		return -EBADF;
 	}
 
@@ -1461,6 +1530,28 @@ static int find_probes(int fd, struct probe_finder *pf)
 
 	off = 0;
 	line_list__init(&pf->lcache);
+
+	/* Fastpath: lookup by function name from .debug_pubnames section */
+	if (pp->function) {
+		struct pubname_callback_param pubname_param = {
+			.function = pp->function,
+			.file	  = pp->file,
+			.cu_die	  = &pf->cu_die,
+			.sp_die	  = &pf->sp_die,
+			.found	  = 0,
+		};
+		struct dwarf_callback_param probe_param = {
+			.data = pf,
+		};
+
+		dwarf_getpubnames(dbg, pubname_search_cb, &pubname_param, 0);
+		if (pubname_param.found) {
+			ret = probe_point_search_cb(&pf->sp_die, &probe_param);
+			if (ret)
+				goto found;
+		}
+	}
+
 	/* Loop on CUs (Compilation Unit) */
 	while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL)) {
 		/* Get the DIE(Debugging Information Entry) of this CU */
@@ -1488,6 +1579,8 @@ static int find_probes(int fd, struct probe_finder *pf)
 		}
 		off = noff;
 	}
+
+found:
 	line_list__free(&pf->lcache);
 	if (dwfl)
 		dwfl_end(dwfl);
@@ -1686,11 +1779,9 @@ int find_perf_probe_point(unsigned long addr, struct perf_probe_point *ppt)
 	Dwarf_Die cudie, spdie, indie;
 	Dwarf *dbg = NULL;
 	Dwfl *dwfl = NULL;
-	Dwarf_Line *line;
-	Dwarf_Addr laddr, eaddr, bias = 0;
-	const char *tmp;
-	int lineno, ret = 0;
-	bool found = false;
+	Dwarf_Addr _addr, baseaddr, bias = 0;
+	const char *fname = NULL, *func = NULL, *tmp;
+	int baseline = 0, lineno = 0, ret = 0;
 
 	/* Open the live linux kernel */
 	dbg = dwfl_init_live_kernel_dwarf(addr, &dwfl, &bias);
@@ -1711,68 +1802,79 @@ int find_perf_probe_point(unsigned long addr, struct perf_probe_point *ppt)
 		goto end;
 	}
 
-	/* Find a corresponding line */
-	line = dwarf_getsrc_die(&cudie, (Dwarf_Addr)addr);
-	if (line) {
-		if (dwarf_lineaddr(line, &laddr) == 0 &&
-		    (Dwarf_Addr)addr == laddr &&
-		    dwarf_lineno(line, &lineno) == 0) {
-			tmp = dwarf_linesrc(line, NULL, NULL);
-			if (tmp) {
-				ppt->line = lineno;
-				ppt->file = strdup(tmp);
-				if (ppt->file == NULL) {
-					ret = -ENOMEM;
-					goto end;
-				}
-				found = true;
-			}
-		}
-	}
+	/* Find a corresponding line (filename and lineno) */
+	cu_find_lineinfo(&cudie, addr, &fname, &lineno);
+	/* Don't care whether it failed or not */
 
-	/* Find a corresponding function */
+	/* Find a corresponding function (name, baseline and baseaddr) */
 	if (die_find_real_subprogram(&cudie, (Dwarf_Addr)addr, &spdie)) {
+		/* Get function entry information */
 		tmp = dwarf_diename(&spdie);
-		if (!tmp || dwarf_entrypc(&spdie, &eaddr) != 0)
-			goto end;
-
-		if (ppt->line) {
-			if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr,
-						&indie)) {
-				/* addr in an inline function */
+		if (!tmp ||
+		    dwarf_entrypc(&spdie, &baseaddr) != 0 ||
+		    dwarf_decl_line(&spdie, &baseline) != 0)
+			goto post;
+		func = tmp;
+
+		if (addr == (unsigned long)baseaddr)
+			/* Function entry - Relative line number is 0 */
+			lineno = baseline;
+		else if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr,
+					     &indie)) {
+			if (dwarf_entrypc(&indie, &_addr) == 0 &&
+			    _addr == addr)
+				/*
+				 * addr is at an inline function entry.
+				 * In this case, lineno should be the call-site
+				 * line number.
+				 */
+				lineno = die_get_call_lineno(&indie);
+			else {
+				/*
+				 * addr is in an inline function body.
+				 * Since lineno points one of the lines
+				 * of the inline function, baseline should
+				 * be the entry line of the inline function.
+				 */
 				tmp = dwarf_diename(&indie);
-				if (!tmp)
-					goto end;
-				ret = dwarf_decl_line(&indie, &lineno);
-			} else {
-				if (eaddr == addr) {	/* Function entry */
-					lineno = ppt->line;
-					ret = 0;
-				} else
-					ret = dwarf_decl_line(&spdie, &lineno);
-			}
-			if (ret == 0) {
-				/* Make a relative line number */
-				ppt->line -= lineno;
-				goto found;
+				if (tmp &&
+				    dwarf_decl_line(&spdie, &baseline) == 0)
+					func = tmp;
 			}
 		}
-		/* We don't have a line number, let's use offset */
-		ppt->offset = addr - (unsigned long)eaddr;
-found:
-		ppt->function = strdup(tmp);
+	}
+
+post:
+	/* Make a relative line number or an offset */
+	if (lineno)
+		ppt->line = lineno - baseline;
+	else if (func)
+		ppt->offset = addr - (unsigned long)baseaddr;
+
+	/* Duplicate strings */
+	if (func) {
+		ppt->function = strdup(func);
 		if (ppt->function == NULL) {
 			ret = -ENOMEM;
 			goto end;
 		}
-		found = true;
 	}
-
+	if (fname) {
+		ppt->file = strdup(fname);
+		if (ppt->file == NULL) {
+			if (ppt->function) {
+				free(ppt->function);
+				ppt->function = NULL;
+			}
+			ret = -ENOMEM;
+			goto end;
+		}
+	}
 end:
 	if (dwfl)
 		dwfl_end(dwfl);
-	if (ret >= 0)
-		ret = found ? 1 : 0;
+	if (ret == 0 && (fname || func))
+		ret = 1;	/* Found a point */
 	return ret;
 }
 
@@ -1840,6 +1942,10 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 	struct line_finder *lf = param->data;
 	struct line_range *lr = lf->lr;
 
+	/* Check declared file */
+	if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die)))
+		return DWARF_CB_OK;
+
 	if (dwarf_tag(sp_die) == DW_TAG_subprogram &&
 	    die_compare_name(sp_die, lr->function)) {
 		lf->fname = dwarf_decl_file(sp_die);
@@ -1892,9 +1998,26 @@ int find_line_range(int fd, struct line_range *lr)
 	if (!dbg) {
 		pr_warning("No debug information found in the vmlinux - "
 			"please rebuild with CONFIG_DEBUG_INFO=y.\n");
+		close(fd);	/* Without dwfl_end(), fd isn't closed. */
 		return -EBADF;
 	}
 
+	/* Fastpath: lookup by function name from .debug_pubnames section */
+	if (lr->function) {
+		struct pubname_callback_param pubname_param = {
+			.function = lr->function, .file = lr->file,
+			.cu_die = &lf.cu_die, .sp_die = &lf.sp_die, .found = 0};
+		struct dwarf_callback_param line_range_param = {
+			.data = (void *)&lf, .retval = 0};
+
+		dwarf_getpubnames(dbg, pubname_search_cb, &pubname_param, 0);
+		if (pubname_param.found) {
+			line_range_search_cb(&lf.sp_die, &line_range_param);
+			if (lf.found)
+				goto found;
+		}
+	}
+
 	/* Loop on CUs (Compilation Unit) */
 	while (!lf.found && ret >= 0) {
 		if (dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL) != 0)
@@ -1923,6 +2046,7 @@ int find_line_range(int fd, struct line_range *lr)
 		off = noff;
 	}
 
+found:
 	/* Store comp_dir */
 	if (lf.found) {
 		comp_dir = cu_get_comp_dir(&lf.cu_die);
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index beaefc3c1223..605730a366db 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -49,6 +49,7 @@ struct probe_finder {
 	Dwarf_Addr		addr;		/* Address */
 	const char		*fname;		/* Real file name */
 	Dwarf_Die		cu_die;		/* Current CU */
+	Dwarf_Die		sp_die;
 	struct list_head	lcache;		/* Line cache for lazy match */
 
 	/* For variable searching */
@@ -83,6 +84,7 @@ struct line_finder {
 	int			lno_s;		/* Start line number */
 	int			lno_e;		/* End line number */
 	Dwarf_Die		cu_die;		/* Current CU */
+	Dwarf_Die		sp_die;
 	int			found;
 };
 
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index a9f2d7e1204d..69436b3200a4 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -498,11 +498,11 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
 	struct cpu_map *cpus = NULL;
 	struct thread_map *threads = NULL;
 	PyObject *pcpus = NULL, *pthreads = NULL;
-	int group = 0, overwrite = 0;
-	static char *kwlist[] = {"cpus", "threads", "group", "overwrite", NULL, NULL};
+	int group = 0, inherit = 0;
+	static char *kwlist[] = {"cpus", "threads", "group", "inherit", NULL, NULL};
 
 	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist,
-					 &pcpus, &pthreads, &group, &overwrite))
+					 &pcpus, &pthreads, &group, &inherit))
 		return NULL;
 
 	if (pthreads != NULL)
@@ -511,7 +511,8 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
 	if (pcpus != NULL)
 		cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;
 
-	if (perf_evsel__open(evsel, cpus, threads, group, overwrite) < 0) {
+	evsel->attr.inherit = inherit;
+	if (perf_evsel__open(evsel, cpus, threads, group) < 0) {
 		PyErr_SetFromErrno(PyExc_OSError);
 		return NULL;
 	}
@@ -674,12 +675,13 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 	union perf_event *event;
 	int sample_id_all = 1, cpu;
 	static char *kwlist[] = {"sample_id_all", NULL, NULL};
+	int err;
 
 	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist,
 					 &cpu, &sample_id_all))
 		return NULL;
 
-	event = perf_evlist__read_on_cpu(evlist, cpu);
+	event = perf_evlist__mmap_read(evlist, cpu);
 	if (event != NULL) {
 		struct perf_evsel *first;
 		PyObject *pyevent = pyrf_event__new(event);
@@ -689,11 +691,17 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 			return PyErr_NoMemory();
 
 		first = list_entry(evlist->entries.next, struct perf_evsel, node);
-		perf_event__parse_sample(event, first->attr.sample_type, sample_id_all,
-					 &pevent->sample);
+		err = perf_event__parse_sample(event, first->attr.sample_type,
+					       perf_sample_size(first->attr.sample_type),
+					       sample_id_all, &pevent->sample);
+		if (err) {
+			pr_err("Can't parse sample, err = %d\n", err);
+			goto end;
+		}
+
 		return pyevent;
 	}
-
+end:
 	Py_INCREF(Py_None);
 	return Py_None;
 }
@@ -809,6 +817,9 @@ static struct {
 	{ "COUNT_HW_CACHE_RESULT_ACCESS", PERF_COUNT_HW_CACHE_RESULT_ACCESS },
 	{ "COUNT_HW_CACHE_RESULT_MISS",   PERF_COUNT_HW_CACHE_RESULT_MISS },
 
+	{ "COUNT_HW_STALLED_CYCLES_FRONTEND",	  PERF_COUNT_HW_STALLED_CYCLES_FRONTEND },
+	{ "COUNT_HW_STALLED_CYCLES_BACKEND",	  PERF_COUNT_HW_STALLED_CYCLES_BACKEND },
+
 	{ "COUNT_SW_CPU_CLOCK",	       PERF_COUNT_SW_CPU_CLOCK },
 	{ "COUNT_SW_TASK_CLOCK",       PERF_COUNT_SW_TASK_CLOCK },
 	{ "COUNT_SW_PAGE_FAULTS",      PERF_COUNT_SW_PAGE_FAULTS },
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index caa224522fea..64500fc78799 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -97,6 +97,7 @@ out:
 void perf_session__update_sample_type(struct perf_session *self)
 {
 	self->sample_type = perf_evlist__sample_type(self->evlist);
+	self->sample_size = perf_sample_size(self->sample_type);
 	self->sample_id_all = perf_evlist__sample_id_all(self->evlist);
 	perf_session__id_header_size(self);
 }
@@ -479,6 +480,7 @@ static void flush_sample_queue(struct perf_session *s,
 	struct perf_sample sample;
 	u64 limit = os->next_flush;
 	u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
+	int ret;
 
 	if (!ops->ordered_samples || !limit)
 		return;
@@ -487,9 +489,12 @@ static void flush_sample_queue(struct perf_session *s,
 		if (iter->timestamp > limit)
 			break;
 
-		perf_session__parse_sample(s, iter->event, &sample);
-		perf_session_deliver_event(s, iter->event, &sample, ops,
-					   iter->file_offset);
+		ret = perf_session__parse_sample(s, iter->event, &sample);
+		if (ret)
+			pr_err("Can't parse sample, err = %d\n", ret);
+		else
+			perf_session_deliver_event(s, iter->event, &sample, ops,
+						   iter->file_offset);
 
 		os->last_flush = iter->timestamp;
 		list_del(&iter->list);
@@ -805,7 +810,9 @@ static int perf_session__process_event(struct perf_session *session,
 	/*
 	 * For all kernel events we get the sample data
 	 */
-	perf_session__parse_sample(session, event, &sample);
+	ret = perf_session__parse_sample(session, event, &sample);
+	if (ret)
+		return ret;
 
 	/* Preprocess sample records - precheck callchains */
 	if (perf_session__preprocess_sample(session, event, &sample))
@@ -953,6 +960,30 @@ out_err:
 	return err;
 }
 
+static union perf_event *
+fetch_mmaped_event(struct perf_session *session,
+		   u64 head, size_t mmap_size, char *buf)
+{
+	union perf_event *event;
+
+	/*
+	 * Ensure we have enough space remaining to read
+	 * the size of the event in the headers.
+	 */
+	if (head + sizeof(event->header) > mmap_size)
+		return NULL;
+
+	event = (union perf_event *)(buf + head);
+
+	if (session->header.needs_swap)
+		perf_event_header__bswap(&event->header);
+
+	if (head + event->header.size > mmap_size)
+		return NULL;
+
+	return event;
+}
+
 int __perf_session__process_events(struct perf_session *session,
 				   u64 data_offset, u64 data_size,
 				   u64 file_size, struct perf_event_ops *ops)
@@ -1007,15 +1038,8 @@ remap:
 	file_pos = file_offset + head;
 
 more:
-	event = (union perf_event *)(buf + head);
-
-	if (session->header.needs_swap)
-		perf_event_header__bswap(&event->header);
-	size = event->header.size;
-	if (size == 0)
-		size = 8;
-
-	if (head + event->header.size > mmap_size) {
+	event = fetch_mmaped_event(session, head, mmap_size, buf);
+	if (!event) {
 		if (mmaps[map_idx]) {
 			munmap(mmaps[map_idx], mmap_size);
 			mmaps[map_idx] = NULL;
@@ -1156,6 +1180,18 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
 	return ret;
 }
 
+struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
+					      unsigned int type)
+{
+	struct perf_evsel *pos;
+
+	list_for_each_entry(pos, &session->evlist->entries, node) {
+		if (pos->attr.type == type)
+			return pos;
+	}
+	return NULL;
+}
+
 void perf_session__print_symbols(union perf_event *event,
 				struct perf_sample *sample,
 				struct perf_session *session)
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 1ac481fc1100..66d4e1490879 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -43,6 +43,7 @@ struct perf_session {
 	 */
 	struct hists		hists;
 	u64			sample_type;
+	int			sample_size;
 	int			fd;
 	bool			fd_pipe;
 	bool			repipe;
@@ -159,9 +160,13 @@ static inline int perf_session__parse_sample(struct perf_session *session,
 					     struct perf_sample *sample)
 {
 	return perf_event__parse_sample(event, session->sample_type,
+					session->sample_size,
 					session->sample_id_all, sample);
 }
 
+struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
+					    unsigned int type);
+
 void perf_session__print_symbols(union perf_event *event,
 				 struct perf_sample *sample,
 				 struct perf_session *session);
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index e24ffadb20b2..bbc982f5dd8b 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -1,13 +1,18 @@
 #!/usr/bin/python2
 
 from distutils.core import setup, Extension
+from os import getenv
+
+cflags = ['-fno-strict-aliasing', '-Wno-write-strings']
+cflags += getenv('CFLAGS', '').split()
 
 perf = Extension('perf',
 		  sources = ['util/python.c', 'util/ctype.c', 'util/evlist.c',
 			     'util/evsel.c', 'util/cpumap.c', 'util/thread_map.c',
 			     'util/util.c', 'util/xyarray.c', 'util/cgroup.c'],
 		  include_dirs = ['util/include'],
-		  extra_compile_args = ['-fno-strict-aliasing', '-Wno-write-strings'])
+		  extra_compile_args = cflags,
+                 )
 
 setup(name='perf',
       version='0.1',
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index 8fc0bd3a3a4a..b9a985dadd08 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -85,7 +85,7 @@ out:
 
 /*
  * Helper function for splitting a string into an argv-like array.
- * originaly copied from lib/argv_split.c
+ * originally copied from lib/argv_split.c
  */
 static const char *skip_sep(const char *cp)
 {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 17df793c8924..eec196329fd9 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -31,13 +31,13 @@
 #define NT_GNU_BUILD_ID 3
 #endif
 
-static bool dso__build_id_equal(const struct dso *self, u8 *build_id);
+static bool dso__build_id_equal(const struct dso *dso, u8 *build_id);
 static int elf_read_build_id(Elf *elf, void *bf, size_t size);
 static void dsos__add(struct list_head *head, struct dso *dso);
 static struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
-static int dso__load_kernel_sym(struct dso *self, struct map *map,
+static int dso__load_kernel_sym(struct dso *dso, struct map *map,
 				symbol_filter_t filter);
-static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
+static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
 			symbol_filter_t filter);
 static int vmlinux_path__nr_entries;
 static char **vmlinux_path;
@@ -49,27 +49,27 @@ struct symbol_conf symbol_conf = {
 	.symfs            = "",
 };
 
-int dso__name_len(const struct dso *self)
+int dso__name_len(const struct dso *dso)
 {
 	if (verbose)
-		return self->long_name_len;
+		return dso->long_name_len;
 
-	return self->short_name_len;
+	return dso->short_name_len;
 }
 
-bool dso__loaded(const struct dso *self, enum map_type type)
+bool dso__loaded(const struct dso *dso, enum map_type type)
 {
-	return self->loaded & (1 << type);
+	return dso->loaded & (1 << type);
 }
 
-bool dso__sorted_by_name(const struct dso *self, enum map_type type)
+bool dso__sorted_by_name(const struct dso *dso, enum map_type type)
 {
-	return self->sorted_by_name & (1 << type);
+	return dso->sorted_by_name & (1 << type);
 }
 
-static void dso__set_sorted_by_name(struct dso *self, enum map_type type)
+static void dso__set_sorted_by_name(struct dso *dso, enum map_type type)
 {
-	self->sorted_by_name |= (1 << type);
+	dso->sorted_by_name |= (1 << type);
 }
 
 bool symbol_type__is_a(char symbol_type, enum map_type map_type)
@@ -84,9 +84,9 @@ bool symbol_type__is_a(char symbol_type, enum map_type map_type)
 	}
 }
 
-static void symbols__fixup_end(struct rb_root *self)
+static void symbols__fixup_end(struct rb_root *symbols)
 {
-	struct rb_node *nd, *prevnd = rb_first(self);
+	struct rb_node *nd, *prevnd = rb_first(symbols);
 	struct symbol *curr, *prev;
 
 	if (prevnd == NULL)
@@ -107,10 +107,10 @@ static void symbols__fixup_end(struct rb_root *self)
 		curr->end = roundup(curr->start, 4096);
 }
 
-static void __map_groups__fixup_end(struct map_groups *self, enum map_type type)
+static void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
 {
 	struct map *prev, *curr;
-	struct rb_node *nd, *prevnd = rb_first(&self->maps[type]);
+	struct rb_node *nd, *prevnd = rb_first(&mg->maps[type]);
 
 	if (prevnd == NULL)
 		return;
@@ -130,128 +130,128 @@ static void __map_groups__fixup_end(struct map_groups *self, enum map_type type)
 	curr->end = ~0ULL;
 }
 
-static void map_groups__fixup_end(struct map_groups *self)
+static void map_groups__fixup_end(struct map_groups *mg)
 {
 	int i;
 	for (i = 0; i < MAP__NR_TYPES; ++i)
-		__map_groups__fixup_end(self, i);
+		__map_groups__fixup_end(mg, i);
 }
 
 static struct symbol *symbol__new(u64 start, u64 len, u8 binding,
 				  const char *name)
 {
 	size_t namelen = strlen(name) + 1;
-	struct symbol *self = calloc(1, (symbol_conf.priv_size +
-					 sizeof(*self) + namelen));
-	if (self == NULL)
+	struct symbol *sym = calloc(1, (symbol_conf.priv_size +
+					sizeof(*sym) + namelen));
+	if (sym == NULL)
 		return NULL;
 
 	if (symbol_conf.priv_size)
-		self = ((void *)self) + symbol_conf.priv_size;
-
-	self->start   = start;
-	self->end     = len ? start + len - 1 : start;
-	self->binding = binding;
-	self->namelen = namelen - 1;
+		sym = ((void *)sym) + symbol_conf.priv_size;
 
-	pr_debug4("%s: %s %#" PRIx64 "-%#" PRIx64 "\n", __func__, name, start, self->end);
+	sym->start   = start;
+	sym->end     = len ? start + len - 1 : start;
+	sym->binding = binding;
+	sym->namelen = namelen - 1;
 
-	memcpy(self->name, name, namelen);
+	pr_debug4("%s: %s %#" PRIx64 "-%#" PRIx64 "\n",
+		  __func__, name, start, sym->end);
+	memcpy(sym->name, name, namelen);
 
-	return self;
+	return sym;
 }
 
-void symbol__delete(struct symbol *self)
+void symbol__delete(struct symbol *sym)
 {
-	free(((void *)self) - symbol_conf.priv_size);
+	free(((void *)sym) - symbol_conf.priv_size);
 }
 
-static size_t symbol__fprintf(struct symbol *self, FILE *fp)
+static size_t symbol__fprintf(struct symbol *sym, FILE *fp)
 {
 	return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %c %s\n",
-		       self->start, self->end,
-		       self->binding == STB_GLOBAL ? 'g' :
-		       self->binding == STB_LOCAL  ? 'l' : 'w',
-		       self->name);
+		       sym->start, sym->end,
+		       sym->binding == STB_GLOBAL ? 'g' :
+		       sym->binding == STB_LOCAL  ? 'l' : 'w',
+		       sym->name);
 }
 
-void dso__set_long_name(struct dso *self, char *name)
+void dso__set_long_name(struct dso *dso, char *name)
 {
 	if (name == NULL)
 		return;
-	self->long_name = name;
-	self->long_name_len = strlen(name);
+	dso->long_name = name;
+	dso->long_name_len = strlen(name);
 }
 
-static void dso__set_short_name(struct dso *self, const char *name)
+static void dso__set_short_name(struct dso *dso, const char *name)
 {
 	if (name == NULL)
 		return;
-	self->short_name = name;
-	self->short_name_len = strlen(name);
+	dso->short_name = name;
+	dso->short_name_len = strlen(name);
 }
 
-static void dso__set_basename(struct dso *self)
+static void dso__set_basename(struct dso *dso)
 {
-	dso__set_short_name(self, basename(self->long_name));
+	dso__set_short_name(dso, basename(dso->long_name));
 }
 
 struct dso *dso__new(const char *name)
 {
-	struct dso *self = calloc(1, sizeof(*self) + strlen(name) + 1);
+	struct dso *dso = calloc(1, sizeof(*dso) + strlen(name) + 1);
 
-	if (self != NULL) {
+	if (dso != NULL) {
 		int i;
-		strcpy(self->name, name);
-		dso__set_long_name(self, self->name);
-		dso__set_short_name(self, self->name);
+		strcpy(dso->name, name);
+		dso__set_long_name(dso, dso->name);
+		dso__set_short_name(dso, dso->name);
 		for (i = 0; i < MAP__NR_TYPES; ++i)
-			self->symbols[i] = self->symbol_names[i] = RB_ROOT;
-		self->symtab_type = SYMTAB__NOT_FOUND;
-		self->loaded = 0;
-		self->sorted_by_name = 0;
-		self->has_build_id = 0;
-		self->kernel = DSO_TYPE_USER;
-		INIT_LIST_HEAD(&self->node);
+			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
+		dso->symtab_type = SYMTAB__NOT_FOUND;
+		dso->loaded = 0;
+		dso->sorted_by_name = 0;
+		dso->has_build_id = 0;
+		dso->kernel = DSO_TYPE_USER;
+		INIT_LIST_HEAD(&dso->node);
 	}
 
-	return self;
+	return dso;
 }
 
-static void symbols__delete(struct rb_root *self)
+static void symbols__delete(struct rb_root *symbols)
 {
 	struct symbol *pos;
-	struct rb_node *next = rb_first(self);
+	struct rb_node *next = rb_first(symbols);
 
 	while (next) {
 		pos = rb_entry(next, struct symbol, rb_node);
 		next = rb_next(&pos->rb_node);
-		rb_erase(&pos->rb_node, self);
+		rb_erase(&pos->rb_node, symbols);
 		symbol__delete(pos);
 	}
 }
 
-void dso__delete(struct dso *self)
+void dso__delete(struct dso *dso)
 {
 	int i;
 	for (i = 0; i < MAP__NR_TYPES; ++i)
-		symbols__delete(&self->symbols[i]);
-	if (self->sname_alloc)
-		free((char *)self->short_name);
-	if (self->lname_alloc)
-		free(self->long_name);
-	free(self);
+		symbols__delete(&dso->symbols[i]);
+	if (dso->sname_alloc)
+		free((char *)dso->short_name);
+	if (dso->lname_alloc)
+		free(dso->long_name);
+	free(dso);
 }
 
-void dso__set_build_id(struct dso *self, void *build_id)
+void dso__set_build_id(struct dso *dso, void *build_id)
 {
-	memcpy(self->build_id, build_id, sizeof(self->build_id));
-	self->has_build_id = 1;
+	memcpy(dso->build_id, build_id, sizeof(dso->build_id));
+	dso->has_build_id = 1;
 }
 
-static void symbols__insert(struct rb_root *self, struct symbol *sym)
+static void symbols__insert(struct rb_root *symbols, struct symbol *sym)
 {
-	struct rb_node **p = &self->rb_node;
+	struct rb_node **p = &symbols->rb_node;
 	struct rb_node *parent = NULL;
 	const u64 ip = sym->start;
 	struct symbol *s;
@@ -265,17 +265,17 @@ static void symbols__insert(struct rb_root *self, struct symbol *sym)
 			p = &(*p)->rb_right;
 	}
 	rb_link_node(&sym->rb_node, parent, p);
-	rb_insert_color(&sym->rb_node, self);
+	rb_insert_color(&sym->rb_node, symbols);
 }
 
-static struct symbol *symbols__find(struct rb_root *self, u64 ip)
+static struct symbol *symbols__find(struct rb_root *symbols, u64 ip)
 {
 	struct rb_node *n;
 
-	if (self == NULL)
+	if (symbols == NULL)
 		return NULL;
 
-	n = self->rb_node;
+	n = symbols->rb_node;
 
 	while (n) {
 		struct symbol *s = rb_entry(n, struct symbol, rb_node);
@@ -296,9 +296,9 @@ struct symbol_name_rb_node {
 	struct symbol	sym;
 };
 
-static void symbols__insert_by_name(struct rb_root *self, struct symbol *sym)
+static void symbols__insert_by_name(struct rb_root *symbols, struct symbol *sym)
 {
-	struct rb_node **p = &self->rb_node;
+	struct rb_node **p = &symbols->rb_node;
 	struct rb_node *parent = NULL;
 	struct symbol_name_rb_node *symn, *s;
 
@@ -313,27 +313,29 @@ static void symbols__insert_by_name(struct rb_root *self, struct symbol *sym)
 			p = &(*p)->rb_right;
 	}
 	rb_link_node(&symn->rb_node, parent, p);
-	rb_insert_color(&symn->rb_node, self);
+	rb_insert_color(&symn->rb_node, symbols);
 }
 
-static void symbols__sort_by_name(struct rb_root *self, struct rb_root *source)
+static void symbols__sort_by_name(struct rb_root *symbols,
+				  struct rb_root *source)
 {
 	struct rb_node *nd;
 
 	for (nd = rb_first(source); nd; nd = rb_next(nd)) {
 		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
-		symbols__insert_by_name(self, pos);
+		symbols__insert_by_name(symbols, pos);
 	}
 }
 
-static struct symbol *symbols__find_by_name(struct rb_root *self, const char *name)
+static struct symbol *symbols__find_by_name(struct rb_root *symbols,
+					    const char *name)
 {
 	struct rb_node *n;
 
-	if (self == NULL)
+	if (symbols == NULL)
 		return NULL;
 
-	n = self->rb_node;
+	n = symbols->rb_node;
 
 	while (n) {
 		struct symbol_name_rb_node *s;
@@ -353,29 +355,29 @@ static struct symbol *symbols__find_by_name(struct rb_root *self, const char *na
 	return NULL;
 }
 
-struct symbol *dso__find_symbol(struct dso *self,
+struct symbol *dso__find_symbol(struct dso *dso,
 				enum map_type type, u64 addr)
 {
-	return symbols__find(&self->symbols[type], addr);
+	return symbols__find(&dso->symbols[type], addr);
 }
 
-struct symbol *dso__find_symbol_by_name(struct dso *self, enum map_type type,
+struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
 					const char *name)
 {
-	return symbols__find_by_name(&self->symbol_names[type], name);
+	return symbols__find_by_name(&dso->symbol_names[type], name);
 }
 
-void dso__sort_by_name(struct dso *self, enum map_type type)
+void dso__sort_by_name(struct dso *dso, enum map_type type)
 {
-	dso__set_sorted_by_name(self, type);
-	return symbols__sort_by_name(&self->symbol_names[type],
-				     &self->symbols[type]);
+	dso__set_sorted_by_name(dso, type);
+	return symbols__sort_by_name(&dso->symbol_names[type],
+				     &dso->symbols[type]);
 }
 
-int build_id__sprintf(const u8 *self, int len, char *bf)
+int build_id__sprintf(const u8 *build_id, int len, char *bf)
 {
 	char *bid = bf;
-	const u8 *raw = self;
+	const u8 *raw = build_id;
 	int i;
 
 	for (i = 0; i < len; ++i) {
@@ -384,24 +386,25 @@ int build_id__sprintf(const u8 *self, int len, char *bf)
 		bid += 2;
 	}
 
-	return raw - self;
+	return raw - build_id;
 }
 
-size_t dso__fprintf_buildid(struct dso *self, FILE *fp)
+size_t dso__fprintf_buildid(struct dso *dso, FILE *fp)
 {
 	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
 
-	build_id__sprintf(self->build_id, sizeof(self->build_id), sbuild_id);
+	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
 	return fprintf(fp, "%s", sbuild_id);
 }
 
-size_t dso__fprintf_symbols_by_name(struct dso *self, enum map_type type, FILE *fp)
+size_t dso__fprintf_symbols_by_name(struct dso *dso,
+				    enum map_type type, FILE *fp)
 {
 	size_t ret = 0;
 	struct rb_node *nd;
 	struct symbol_name_rb_node *pos;
 
-	for (nd = rb_first(&self->symbol_names[type]); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&dso->symbol_names[type]); nd; nd = rb_next(nd)) {
 		pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
 		fprintf(fp, "%s\n", pos->sym.name);
 	}
@@ -409,18 +412,18 @@ size_t dso__fprintf_symbols_by_name(struct dso *self, enum map_type type, FILE *
 	return ret;
 }
 
-size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp)
+size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp)
 {
 	struct rb_node *nd;
-	size_t ret = fprintf(fp, "dso: %s (", self->short_name);
+	size_t ret = fprintf(fp, "dso: %s (", dso->short_name);
 
-	if (self->short_name != self->long_name)
-		ret += fprintf(fp, "%s, ", self->long_name);
+	if (dso->short_name != dso->long_name)
+		ret += fprintf(fp, "%s, ", dso->long_name);
 	ret += fprintf(fp, "%s, %sloaded, ", map_type__name[type],
-		       self->loaded ? "" : "NOT ");
-	ret += dso__fprintf_buildid(self, fp);
+		       dso->loaded ? "" : "NOT ");
+	ret += dso__fprintf_buildid(dso, fp);
 	ret += fprintf(fp, ")\n");
-	for (nd = rb_first(&self->symbols[type]); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&dso->symbols[type]); nd; nd = rb_next(nd)) {
 		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
 		ret += symbol__fprintf(pos, fp);
 	}
@@ -543,10 +546,10 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
  * so that we can in the next step set the symbol ->end address and then
  * call kernel_maps__split_kallsyms.
  */
-static int dso__load_all_kallsyms(struct dso *self, const char *filename,
+static int dso__load_all_kallsyms(struct dso *dso, const char *filename,
 				  struct map *map)
 {
-	struct process_kallsyms_args args = { .map = map, .dso = self, };
+	struct process_kallsyms_args args = { .map = map, .dso = dso, };
 	return kallsyms__parse(filename, &args, map__process_kallsym_symbol);
 }
 
@@ -555,7 +558,7 @@ static int dso__load_all_kallsyms(struct dso *self, const char *filename,
  * kernel range is broken in several maps, named [kernel].N, as we don't have
  * the original ELF section names vmlinux have.
  */
-static int dso__split_kallsyms(struct dso *self, struct map *map,
+static int dso__split_kallsyms(struct dso *dso, struct map *map,
 			       symbol_filter_t filter)
 {
 	struct map_groups *kmaps = map__kmap(map)->kmaps;
@@ -563,7 +566,7 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 	struct map *curr_map = map;
 	struct symbol *pos;
 	int count = 0, moved = 0;	
-	struct rb_root *root = &self->symbols[map->type];
+	struct rb_root *root = &dso->symbols[map->type];
 	struct rb_node *next = rb_first(root);
 	int kernel_range = 0;
 
@@ -582,7 +585,7 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 
 			if (strcmp(curr_map->dso->short_name, module)) {
 				if (curr_map != map &&
-				    self->kernel == DSO_TYPE_GUEST_KERNEL &&
+				    dso->kernel == DSO_TYPE_GUEST_KERNEL &&
 				    machine__is_default_guest(machine)) {
 					/*
 					 * We assume all symbols of a module are
@@ -618,14 +621,14 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 			pos->end   = curr_map->map_ip(curr_map, pos->end);
 		} else if (curr_map != map) {
 			char dso_name[PATH_MAX];
-			struct dso *dso;
+			struct dso *ndso;
 
 			if (count == 0) {
 				curr_map = map;
 				goto filter_symbol;
 			}
 
-			if (self->kernel == DSO_TYPE_GUEST_KERNEL)
+			if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
 				snprintf(dso_name, sizeof(dso_name),
 					"[guest.kernel].%d",
 					kernel_range++);
@@ -634,15 +637,15 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 					"[kernel].%d",
 					kernel_range++);
 
-			dso = dso__new(dso_name);
-			if (dso == NULL)
+			ndso = dso__new(dso_name);
+			if (ndso == NULL)
 				return -1;
 
-			dso->kernel = self->kernel;
+			ndso->kernel = dso->kernel;
 
-			curr_map = map__new2(pos->start, dso, map->type);
+			curr_map = map__new2(pos->start, ndso, map->type);
 			if (curr_map == NULL) {
-				dso__delete(dso);
+				dso__delete(ndso);
 				return -1;
 			}
 
@@ -665,7 +668,7 @@ discard_symbol:		rb_erase(&pos->rb_node, root);
 	}
 
 	if (curr_map != map &&
-	    self->kernel == DSO_TYPE_GUEST_KERNEL &&
+	    dso->kernel == DSO_TYPE_GUEST_KERNEL &&
 	    machine__is_default_guest(kmaps->machine)) {
 		dso__set_loaded(curr_map->dso, curr_map->type);
 	}
@@ -673,21 +676,42 @@ discard_symbol:		rb_erase(&pos->rb_node, root);
 	return count + moved;
 }
 
-int dso__load_kallsyms(struct dso *self, const char *filename,
+static bool symbol__restricted_filename(const char *filename,
+					const char *restricted_filename)
+{
+	bool restricted = false;
+
+	if (symbol_conf.kptr_restrict) {
+		char *r = realpath(filename, NULL);
+
+		if (r != NULL) {
+			restricted = strcmp(r, restricted_filename) == 0;
+			free(r);
+			return restricted;
+		}
+	}
+
+	return restricted;
+}
+
+int dso__load_kallsyms(struct dso *dso, const char *filename,
 		       struct map *map, symbol_filter_t filter)
 {
-	if (dso__load_all_kallsyms(self, filename, map) < 0)
+	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+		return -1;
+
+	if (dso__load_all_kallsyms(dso, filename, map) < 0)
 		return -1;
 
-	if (self->kernel == DSO_TYPE_GUEST_KERNEL)
-		self->symtab_type = SYMTAB__GUEST_KALLSYMS;
+	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+		dso->symtab_type = SYMTAB__GUEST_KALLSYMS;
 	else
-		self->symtab_type = SYMTAB__KALLSYMS;
+		dso->symtab_type = SYMTAB__KALLSYMS;
 
-	return dso__split_kallsyms(self, map, filter);
+	return dso__split_kallsyms(dso, map, filter);
 }
 
-static int dso__load_perf_map(struct dso *self, struct map *map,
+static int dso__load_perf_map(struct dso *dso, struct map *map,
 			      symbol_filter_t filter)
 {
 	char *line = NULL;
@@ -695,7 +719,7 @@ static int dso__load_perf_map(struct dso *self, struct map *map,
 	FILE *file;
 	int nr_syms = 0;
 
-	file = fopen(self->long_name, "r");
+	file = fopen(dso->long_name, "r");
 	if (file == NULL)
 		goto out_failure;
 
@@ -733,7 +757,7 @@ static int dso__load_perf_map(struct dso *self, struct map *map,
 		if (filter && filter(map, sym))
 			symbol__delete(sym);
 		else {
-			symbols__insert(&self->symbols[map->type], sym);
+			symbols__insert(&dso->symbols[map->type], sym);
 			nr_syms++;
 		}
 	}
@@ -752,7 +776,7 @@ out_failure:
 /**
  * elf_symtab__for_each_symbol - iterate thru all the symbols
  *
- * @self: struct elf_symtab instance to iterate
+ * @syms: struct elf_symtab instance to iterate
  * @idx: uint32_t idx
  * @sym: GElf_Sym iterator
  */
@@ -852,7 +876,7 @@ static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
  * And always look at the original dso, not at debuginfo packages, that
  * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS).
  */
-static int dso__synthesize_plt_symbols(struct  dso *self, struct map *map,
+static int dso__synthesize_plt_symbols(struct  dso *dso, struct map *map,
 				       symbol_filter_t filter)
 {
 	uint32_t nr_rel_entries, idx;
@@ -871,7 +895,7 @@ static int dso__synthesize_plt_symbols(struct  dso *self, struct map *map,
 	char name[PATH_MAX];
 
 	snprintf(name, sizeof(name), "%s%s",
-		 symbol_conf.symfs, self->long_name);
+		 symbol_conf.symfs, dso->long_name);
 	fd = open(name, O_RDONLY);
 	if (fd < 0)
 		goto out;
@@ -947,7 +971,7 @@ static int dso__synthesize_plt_symbols(struct  dso *self, struct map *map,
 			if (filter && filter(map, f))
 				symbol__delete(f);
 			else {
-				symbols__insert(&self->symbols[map->type], f);
+				symbols__insert(&dso->symbols[map->type], f);
 				++nr;
 			}
 		}
@@ -969,7 +993,7 @@ static int dso__synthesize_plt_symbols(struct  dso *self, struct map *map,
 			if (filter && filter(map, f))
 				symbol__delete(f);
 			else {
-				symbols__insert(&self->symbols[map->type], f);
+				symbols__insert(&dso->symbols[map->type], f);
 				++nr;
 			}
 		}
@@ -985,29 +1009,30 @@ out_close:
 		return nr;
 out:
 	pr_debug("%s: problems reading %s PLT info.\n",
-		 __func__, self->long_name);
+		 __func__, dso->long_name);
 	return 0;
 }
 
-static bool elf_sym__is_a(GElf_Sym *self, enum map_type type)
+static bool elf_sym__is_a(GElf_Sym *sym, enum map_type type)
 {
 	switch (type) {
 	case MAP__FUNCTION:
-		return elf_sym__is_function(self);
+		return elf_sym__is_function(sym);
 	case MAP__VARIABLE:
-		return elf_sym__is_object(self);
+		return elf_sym__is_object(sym);
 	default:
 		return false;
 	}
 }
 
-static bool elf_sec__is_a(GElf_Shdr *self, Elf_Data *secstrs, enum map_type type)
+static bool elf_sec__is_a(GElf_Shdr *shdr, Elf_Data *secstrs,
+			  enum map_type type)
 {
 	switch (type) {
 	case MAP__FUNCTION:
-		return elf_sec__is_text(self, secstrs);
+		return elf_sec__is_text(shdr, secstrs);
 	case MAP__VARIABLE:
-		return elf_sec__is_data(self, secstrs);
+		return elf_sec__is_data(shdr, secstrs);
 	default:
 		return false;
 	}
@@ -1032,13 +1057,13 @@ static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr)
 	return -1;
 }
 
-static int dso__load_sym(struct dso *self, struct map *map, const char *name,
+static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
 			 int fd, symbol_filter_t filter, int kmodule,
 			 int want_symtab)
 {
-	struct kmap *kmap = self->kernel ? map__kmap(map) : NULL;
+	struct kmap *kmap = dso->kernel ? map__kmap(map) : NULL;
 	struct map *curr_map = map;
-	struct dso *curr_dso = self;
+	struct dso *curr_dso = dso;
 	Elf_Data *symstrs, *secstrs;
 	uint32_t nr_syms;
 	int err = -1;
@@ -1064,14 +1089,14 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 	}
 
 	/* Always reject images with a mismatched build-id: */
-	if (self->has_build_id) {
+	if (dso->has_build_id) {
 		u8 build_id[BUILD_ID_SIZE];
 
 		if (elf_read_build_id(elf, build_id,
 				      BUILD_ID_SIZE) != BUILD_ID_SIZE)
 			goto out_elf_end;
 
-		if (!dso__build_id_equal(self, build_id))
+		if (!dso__build_id_equal(dso, build_id))
 			goto out_elf_end;
 	}
 
@@ -1112,13 +1137,14 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 	nr_syms = shdr.sh_size / shdr.sh_entsize;
 
 	memset(&sym, 0, sizeof(sym));
-	if (self->kernel == DSO_TYPE_USER) {
-		self->adjust_symbols = (ehdr.e_type == ET_EXEC ||
+	if (dso->kernel == DSO_TYPE_USER) {
+		dso->adjust_symbols = (ehdr.e_type == ET_EXEC ||
 				elf_section_by_name(elf, &ehdr, &shdr,
 						     ".gnu.prelink_undo",
 						     NULL) != NULL);
-	} else self->adjust_symbols = 0;
-
+	} else {
+		dso->adjust_symbols = 0;
+	}
 	elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) {
 		struct symbol *f;
 		const char *elf_name = elf_sym__name(&sym, symstrs);
@@ -1168,22 +1194,22 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 		    (sym.st_value & 1))
 			--sym.st_value;
 
-		if (self->kernel != DSO_TYPE_USER || kmodule) {
+		if (dso->kernel != DSO_TYPE_USER || kmodule) {
 			char dso_name[PATH_MAX];
 
 			if (strcmp(section_name,
 				   (curr_dso->short_name +
-				    self->short_name_len)) == 0)
+				    dso->short_name_len)) == 0)
 				goto new_symbol;
 
 			if (strcmp(section_name, ".text") == 0) {
 				curr_map = map;
-				curr_dso = self;
+				curr_dso = dso;
 				goto new_symbol;
 			}
 
 			snprintf(dso_name, sizeof(dso_name),
-				 "%s%s", self->short_name, section_name);
+				 "%s%s", dso->short_name, section_name);
 
 			curr_map = map_groups__find_by_name(kmap->kmaps, map->type, dso_name);
 			if (curr_map == NULL) {
@@ -1195,7 +1221,9 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 				curr_dso = dso__new(dso_name);
 				if (curr_dso == NULL)
 					goto out_elf_end;
-				curr_dso->kernel = self->kernel;
+				curr_dso->kernel = dso->kernel;
+				curr_dso->long_name = dso->long_name;
+				curr_dso->long_name_len = dso->long_name_len;
 				curr_map = map__new2(start, curr_dso,
 						     map->type);
 				if (curr_map == NULL) {
@@ -1204,9 +1232,9 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 				}
 				curr_map->map_ip = identity__map_ip;
 				curr_map->unmap_ip = identity__map_ip;
-				curr_dso->symtab_type = self->symtab_type;
+				curr_dso->symtab_type = dso->symtab_type;
 				map_groups__insert(kmap->kmaps, curr_map);
-				dsos__add(&self->node, curr_dso);
+				dsos__add(&dso->node, curr_dso);
 				dso__set_loaded(curr_dso, map->type);
 			} else
 				curr_dso = curr_map->dso;
@@ -1248,7 +1276,7 @@ new_symbol:
 	 * For misannotated, zeroed, ASM function sizes.
 	 */
 	if (nr > 0) {
-		symbols__fixup_end(&self->symbols[map->type]);
+		symbols__fixup_end(&dso->symbols[map->type]);
 		if (kmap) {
 			/*
 			 * We need to fixup this here too because we create new
@@ -1264,9 +1292,9 @@ out_close:
 	return err;
 }
 
-static bool dso__build_id_equal(const struct dso *self, u8 *build_id)
+static bool dso__build_id_equal(const struct dso *dso, u8 *build_id)
 {
-	return memcmp(self->build_id, build_id, sizeof(self->build_id)) == 0;
+	return memcmp(dso->build_id, build_id, sizeof(dso->build_id)) == 0;
 }
 
 bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
@@ -1427,7 +1455,7 @@ out:
 	return err;
 }
 
-char dso__symtab_origin(const struct dso *self)
+char dso__symtab_origin(const struct dso *dso)
 {
 	static const char origin[] = {
 		[SYMTAB__KALLSYMS]	      = 'k',
@@ -1442,12 +1470,12 @@ char dso__symtab_origin(const struct dso *self)
 		[SYMTAB__GUEST_KMODULE]	      =  'G',
 	};
 
-	if (self == NULL || self->symtab_type == SYMTAB__NOT_FOUND)
+	if (dso == NULL || dso->symtab_type == SYMTAB__NOT_FOUND)
 		return '!';
-	return origin[self->symtab_type];
+	return origin[dso->symtab_type];
 }
 
-int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
+int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 {
 	int size = PATH_MAX;
 	char *name;
@@ -1457,12 +1485,12 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 	const char *root_dir;
 	int want_symtab;
 
-	dso__set_loaded(self, map->type);
+	dso__set_loaded(dso, map->type);
 
-	if (self->kernel == DSO_TYPE_KERNEL)
-		return dso__load_kernel_sym(self, map, filter);
-	else if (self->kernel == DSO_TYPE_GUEST_KERNEL)
-		return dso__load_guest_kernel_sym(self, map, filter);
+	if (dso->kernel == DSO_TYPE_KERNEL)
+		return dso__load_kernel_sym(dso, map, filter);
+	else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+		return dso__load_guest_kernel_sym(dso, map, filter);
 
 	if (map->groups && map->groups->machine)
 		machine = map->groups->machine;
@@ -1473,11 +1501,11 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 	if (!name)
 		return -1;
 
-	self->adjust_symbols = 0;
+	dso->adjust_symbols = 0;
 
-	if (strncmp(self->name, "/tmp/perf-", 10) == 0) {
-		ret = dso__load_perf_map(self, map, filter);
-		self->symtab_type = ret > 0 ? SYMTAB__JAVA_JIT :
+	if (strncmp(dso->name, "/tmp/perf-", 10) == 0) {
+		ret = dso__load_perf_map(dso, map, filter);
+		dso->symtab_type = ret > 0 ? SYMTAB__JAVA_JIT :
 					      SYMTAB__NOT_FOUND;
 		return ret;
 	}
@@ -1488,33 +1516,33 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 	 */
 	want_symtab = 1;
 restart:
-	for (self->symtab_type = SYMTAB__BUILD_ID_CACHE;
-	     self->symtab_type != SYMTAB__NOT_FOUND;
-	     self->symtab_type++) {
-		switch (self->symtab_type) {
+	for (dso->symtab_type = SYMTAB__BUILD_ID_CACHE;
+	     dso->symtab_type != SYMTAB__NOT_FOUND;
+	     dso->symtab_type++) {
+		switch (dso->symtab_type) {
 		case SYMTAB__BUILD_ID_CACHE:
 			/* skip the locally configured cache if a symfs is given */
 			if (symbol_conf.symfs[0] ||
-			    (dso__build_id_filename(self, name, size) == NULL)) {
+			    (dso__build_id_filename(dso, name, size) == NULL)) {
 				continue;
 			}
 			break;
 		case SYMTAB__FEDORA_DEBUGINFO:
 			snprintf(name, size, "%s/usr/lib/debug%s.debug",
-				 symbol_conf.symfs, self->long_name);
+				 symbol_conf.symfs, dso->long_name);
 			break;
 		case SYMTAB__UBUNTU_DEBUGINFO:
 			snprintf(name, size, "%s/usr/lib/debug%s",
-				 symbol_conf.symfs, self->long_name);
+				 symbol_conf.symfs, dso->long_name);
 			break;
 		case SYMTAB__BUILDID_DEBUGINFO: {
 			char build_id_hex[BUILD_ID_SIZE * 2 + 1];
 
-			if (!self->has_build_id)
+			if (!dso->has_build_id)
 				continue;
 
-			build_id__sprintf(self->build_id,
-					  sizeof(self->build_id),
+			build_id__sprintf(dso->build_id,
+					  sizeof(dso->build_id),
 					  build_id_hex);
 			snprintf(name, size,
 				 "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
@@ -1523,7 +1551,7 @@ restart:
 			break;
 		case SYMTAB__SYSTEM_PATH_DSO:
 			snprintf(name, size, "%s%s",
-			     symbol_conf.symfs, self->long_name);
+			     symbol_conf.symfs, dso->long_name);
 			break;
 		case SYMTAB__GUEST_KMODULE:
 			if (map->groups && machine)
@@ -1531,12 +1559,12 @@ restart:
 			else
 				root_dir = "";
 			snprintf(name, size, "%s%s%s", symbol_conf.symfs,
-				 root_dir, self->long_name);
+				 root_dir, dso->long_name);
 			break;
 
 		case SYMTAB__SYSTEM_PATH_KMODULE:
 			snprintf(name, size, "%s%s", symbol_conf.symfs,
-				 self->long_name);
+				 dso->long_name);
 			break;
 		default:;
 		}
@@ -1546,7 +1574,7 @@ restart:
 		if (fd < 0)
 			continue;
 
-		ret = dso__load_sym(self, map, name, fd, filter, 0,
+		ret = dso__load_sym(dso, map, name, fd, filter, 0,
 				    want_symtab);
 		close(fd);
 
@@ -1558,7 +1586,8 @@ restart:
 			continue;
 
 		if (ret > 0) {
-			int nr_plt = dso__synthesize_plt_symbols(self, map, filter);
+			int nr_plt = dso__synthesize_plt_symbols(dso, map,
+								 filter);
 			if (nr_plt > 0)
 				ret += nr_plt;
 			break;
@@ -1575,17 +1604,17 @@ restart:
 	}
 
 	free(name);
-	if (ret < 0 && strstr(self->name, " (deleted)") != NULL)
+	if (ret < 0 && strstr(dso->name, " (deleted)") != NULL)
 		return 0;
 	return ret;
 }
 
-struct map *map_groups__find_by_name(struct map_groups *self,
+struct map *map_groups__find_by_name(struct map_groups *mg,
 				     enum map_type type, const char *name)
 {
 	struct rb_node *nd;
 
-	for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
 		struct map *map = rb_entry(nd, struct map, rb_node);
 
 		if (map->dso && strcmp(map->dso->short_name, name) == 0)
@@ -1595,28 +1624,28 @@ struct map *map_groups__find_by_name(struct map_groups *self,
 	return NULL;
 }
 
-static int dso__kernel_module_get_build_id(struct dso *self,
-				const char *root_dir)
+static int dso__kernel_module_get_build_id(struct dso *dso,
+					   const char *root_dir)
 {
 	char filename[PATH_MAX];
 	/*
 	 * kernel module short names are of the form "[module]" and
 	 * we need just "module" here.
 	 */
-	const char *name = self->short_name + 1;
+	const char *name = dso->short_name + 1;
 
 	snprintf(filename, sizeof(filename),
 		 "%s/sys/module/%.*s/notes/.note.gnu.build-id",
 		 root_dir, (int)strlen(name) - 1, name);
 
-	if (sysfs__read_build_id(filename, self->build_id,
-				 sizeof(self->build_id)) == 0)
-		self->has_build_id = true;
+	if (sysfs__read_build_id(filename, dso->build_id,
+				 sizeof(dso->build_id)) == 0)
+		dso->has_build_id = true;
 
 	return 0;
 }
 
-static int map_groups__set_modules_path_dir(struct map_groups *self,
+static int map_groups__set_modules_path_dir(struct map_groups *mg,
 				const char *dir_name)
 {
 	struct dirent *dent;
@@ -1644,7 +1673,7 @@ static int map_groups__set_modules_path_dir(struct map_groups *self,
 
 			snprintf(path, sizeof(path), "%s/%s",
 				 dir_name, dent->d_name);
-			ret = map_groups__set_modules_path_dir(self, path);
+			ret = map_groups__set_modules_path_dir(mg, path);
 			if (ret < 0)
 				goto out;
 		} else {
@@ -1659,7 +1688,8 @@ static int map_groups__set_modules_path_dir(struct map_groups *self,
 				 (int)(dot - dent->d_name), dent->d_name);
 
 			strxfrchar(dso_name, '-', '_');
-			map = map_groups__find_by_name(self, MAP__FUNCTION, dso_name);
+			map = map_groups__find_by_name(mg, MAP__FUNCTION,
+						       dso_name);
 			if (map == NULL)
 				continue;
 
@@ -1709,20 +1739,20 @@ static char *get_kernel_version(const char *root_dir)
 	return strdup(name);
 }
 
-static int machine__set_modules_path(struct machine *self)
+static int machine__set_modules_path(struct machine *machine)
 {
 	char *version;
 	char modules_path[PATH_MAX];
 
-	version = get_kernel_version(self->root_dir);
+	version = get_kernel_version(machine->root_dir);
 	if (!version)
 		return -1;
 
 	snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel",
-		 self->root_dir, version);
+		 machine->root_dir, version);
 	free(version);
 
-	return map_groups__set_modules_path_dir(&self->kmaps, modules_path);
+	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path);
 }
 
 /*
@@ -1732,23 +1762,23 @@ static int machine__set_modules_path(struct machine *self)
  */
 static struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
 {
-	struct map *self = calloc(1, (sizeof(*self) +
-				      (dso->kernel ? sizeof(struct kmap) : 0)));
-	if (self != NULL) {
+	struct map *map = calloc(1, (sizeof(*map) +
+				     (dso->kernel ? sizeof(struct kmap) : 0)));
+	if (map != NULL) {
 		/*
 		 * ->end will be filled after we load all the symbols
 		 */
-		map__init(self, type, start, 0, 0, dso);
+		map__init(map, type, start, 0, 0, dso);
 	}
 
-	return self;
+	return map;
 }
 
-struct map *machine__new_module(struct machine *self, u64 start,
+struct map *machine__new_module(struct machine *machine, u64 start,
 				const char *filename)
 {
 	struct map *map;
-	struct dso *dso = __dsos__findnew(&self->kernel_dsos, filename);
+	struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename);
 
 	if (dso == NULL)
 		return NULL;
@@ -1757,15 +1787,15 @@ struct map *machine__new_module(struct machine *self, u64 start,
 	if (map == NULL)
 		return NULL;
 
-	if (machine__is_host(self))
+	if (machine__is_host(machine))
 		dso->symtab_type = SYMTAB__SYSTEM_PATH_KMODULE;
 	else
 		dso->symtab_type = SYMTAB__GUEST_KMODULE;
-	map_groups__insert(&self->kmaps, map);
+	map_groups__insert(&machine->kmaps, map);
 	return map;
 }
 
-static int machine__create_modules(struct machine *self)
+static int machine__create_modules(struct machine *machine)
 {
 	char *line = NULL;
 	size_t n;
@@ -1774,13 +1804,16 @@ static int machine__create_modules(struct machine *self)
 	const char *modules;
 	char path[PATH_MAX];
 
-	if (machine__is_default_guest(self))
+	if (machine__is_default_guest(machine))
 		modules = symbol_conf.default_guest_modules;
 	else {
-		sprintf(path, "%s/proc/modules", self->root_dir);
+		sprintf(path, "%s/proc/modules", machine->root_dir);
 		modules = path;
 	}
 
+	if (symbol__restricted_filename(path, "/proc/modules"))
+		return -1;
+
 	file = fopen(modules, "r");
 	if (file == NULL)
 		return -1;
@@ -1813,16 +1846,16 @@ static int machine__create_modules(struct machine *self)
 		*sep = '\0';
 
 		snprintf(name, sizeof(name), "[%s]", line);
-		map = machine__new_module(self, start, name);
+		map = machine__new_module(machine, start, name);
 		if (map == NULL)
 			goto out_delete_line;
-		dso__kernel_module_get_build_id(map->dso, self->root_dir);
+		dso__kernel_module_get_build_id(map->dso, machine->root_dir);
 	}
 
 	free(line);
 	fclose(file);
 
-	return machine__set_modules_path(self);
+	return machine__set_modules_path(machine);
 
 out_delete_line:
 	free(line);
@@ -1830,7 +1863,7 @@ out_failure:
 	return -1;
 }
 
-int dso__load_vmlinux(struct dso *self, struct map *map,
+int dso__load_vmlinux(struct dso *dso, struct map *map,
 		      const char *vmlinux, symbol_filter_t filter)
 {
 	int err = -1, fd;
@@ -1842,8 +1875,9 @@ int dso__load_vmlinux(struct dso *self, struct map *map,
 	if (fd < 0)
 		return -1;
 
-	dso__set_loaded(self, map->type);
-	err = dso__load_sym(self, map, symfs_vmlinux, fd, filter, 0, 0);
+	dso__set_long_name(dso, (char *)vmlinux);
+	dso__set_loaded(dso, map->type);
+	err = dso__load_sym(dso, map, symfs_vmlinux, fd, filter, 0, 0);
 	close(fd);
 
 	if (err > 0)
@@ -1852,7 +1886,7 @@ int dso__load_vmlinux(struct dso *self, struct map *map,
 	return err;
 }
 
-int dso__load_vmlinux_path(struct dso *self, struct map *map,
+int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 			   symbol_filter_t filter)
 {
 	int i, err = 0;
@@ -1861,20 +1895,20 @@ int dso__load_vmlinux_path(struct dso *self, struct map *map,
 	pr_debug("Looking at the vmlinux_path (%d entries long)\n",
 		 vmlinux_path__nr_entries + 1);
 
-	filename = dso__build_id_filename(self, NULL, 0);
+	filename = dso__build_id_filename(dso, NULL, 0);
 	if (filename != NULL) {
-		err = dso__load_vmlinux(self, map, filename, filter);
+		err = dso__load_vmlinux(dso, map, filename, filter);
 		if (err > 0) {
-			dso__set_long_name(self, filename);
+			dso__set_long_name(dso, filename);
 			goto out;
 		}
 		free(filename);
 	}
 
 	for (i = 0; i < vmlinux_path__nr_entries; ++i) {
-		err = dso__load_vmlinux(self, map, vmlinux_path[i], filter);
+		err = dso__load_vmlinux(dso, map, vmlinux_path[i], filter);
 		if (err > 0) {
-			dso__set_long_name(self, strdup(vmlinux_path[i]));
+			dso__set_long_name(dso, strdup(vmlinux_path[i]));
 			break;
 		}
 	}
@@ -1882,7 +1916,7 @@ out:
 	return err;
 }
 
-static int dso__load_kernel_sym(struct dso *self, struct map *map,
+static int dso__load_kernel_sym(struct dso *dso, struct map *map,
 				symbol_filter_t filter)
 {
 	int err;
@@ -1909,10 +1943,10 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
 	}
 
 	if (symbol_conf.vmlinux_name != NULL) {
-		err = dso__load_vmlinux(self, map,
+		err = dso__load_vmlinux(dso, map,
 					symbol_conf.vmlinux_name, filter);
 		if (err > 0) {
-			dso__set_long_name(self,
+			dso__set_long_name(dso,
 					   strdup(symbol_conf.vmlinux_name));
 			goto out_fixup;
 		}
@@ -1920,7 +1954,7 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
 	}
 
 	if (vmlinux_path != NULL) {
-		err = dso__load_vmlinux_path(self, map, filter);
+		err = dso__load_vmlinux_path(dso, map, filter);
 		if (err > 0)
 			goto out_fixup;
 	}
@@ -1934,13 +1968,13 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
 	 * we have a build-id, so check if it is the same as the running kernel,
 	 * using it if it is.
 	 */
-	if (self->has_build_id) {
+	if (dso->has_build_id) {
 		u8 kallsyms_build_id[BUILD_ID_SIZE];
 		char sbuild_id[BUILD_ID_SIZE * 2 + 1];
 
 		if (sysfs__read_build_id("/sys/kernel/notes", kallsyms_build_id,
 					 sizeof(kallsyms_build_id)) == 0) {
-			if (dso__build_id_equal(self, kallsyms_build_id)) {
+			if (dso__build_id_equal(dso, kallsyms_build_id)) {
 				kallsyms_filename = "/proc/kallsyms";
 				goto do_kallsyms;
 			}
@@ -1949,7 +1983,7 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
 		 * Now look if we have it on the build-id cache in
 		 * $HOME/.debug/[kernel.kallsyms].
 		 */
-		build_id__sprintf(self->build_id, sizeof(self->build_id),
+		build_id__sprintf(dso->build_id, sizeof(dso->build_id),
 				  sbuild_id);
 
 		if (asprintf(&kallsyms_allocated_filename,
@@ -1976,7 +2010,7 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
 	}
 
 do_kallsyms:
-	err = dso__load_kallsyms(self, kallsyms_filename, map, filter);
+	err = dso__load_kallsyms(dso, kallsyms_filename, map, filter);
 	if (err > 0)
 		pr_debug("Using %s for symbols\n", kallsyms_filename);
 	free(kallsyms_allocated_filename);
@@ -1984,7 +2018,7 @@ do_kallsyms:
 	if (err > 0) {
 out_fixup:
 		if (kallsyms_filename != NULL)
-			dso__set_long_name(self, strdup("[kernel.kallsyms]"));
+			dso__set_long_name(dso, strdup("[kernel.kallsyms]"));
 		map__fixup_start(map);
 		map__fixup_end(map);
 	}
@@ -1992,8 +2026,8 @@ out_fixup:
 	return err;
 }
 
-static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
-				symbol_filter_t filter)
+static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
+				      symbol_filter_t filter)
 {
 	int err;
 	const char *kallsyms_filename = NULL;
@@ -2013,7 +2047,7 @@ static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
 		 * Or use file guest_kallsyms inputted by user on commandline
 		 */
 		if (symbol_conf.default_guest_vmlinux_name != NULL) {
-			err = dso__load_vmlinux(self, map,
+			err = dso__load_vmlinux(dso, map,
 				symbol_conf.default_guest_vmlinux_name, filter);
 			goto out_try_fixup;
 		}
@@ -2026,7 +2060,7 @@ static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
 		kallsyms_filename = path;
 	}
 
-	err = dso__load_kallsyms(self, kallsyms_filename, map, filter);
+	err = dso__load_kallsyms(dso, kallsyms_filename, map, filter);
 	if (err > 0)
 		pr_debug("Using %s for symbols\n", kallsyms_filename);
 
@@ -2034,7 +2068,7 @@ out_try_fixup:
 	if (err > 0) {
 		if (kallsyms_filename != NULL) {
 			machine__mmap_name(machine, path, sizeof(path));
-			dso__set_long_name(self, strdup(path));
+			dso__set_long_name(dso, strdup(path));
 		}
 		map__fixup_start(map);
 		map__fixup_end(map);
@@ -2087,12 +2121,12 @@ size_t __dsos__fprintf(struct list_head *head, FILE *fp)
 	return ret;
 }
 
-size_t machines__fprintf_dsos(struct rb_root *self, FILE *fp)
+size_t machines__fprintf_dsos(struct rb_root *machines, FILE *fp)
 {
 	struct rb_node *nd;
 	size_t ret = 0;
 
-	for (nd = rb_first(self); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(machines); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		ret += __dsos__fprintf(&pos->kernel_dsos, fp);
 		ret += __dsos__fprintf(&pos->user_dsos, fp);
@@ -2116,18 +2150,20 @@ static size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
 	return ret;
 }
 
-size_t machine__fprintf_dsos_buildid(struct machine *self, FILE *fp, bool with_hits)
+size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
+				     bool with_hits)
 {
-	return __dsos__fprintf_buildid(&self->kernel_dsos, fp, with_hits) +
-	       __dsos__fprintf_buildid(&self->user_dsos, fp, with_hits);
+	return __dsos__fprintf_buildid(&machine->kernel_dsos, fp, with_hits) +
+	       __dsos__fprintf_buildid(&machine->user_dsos, fp, with_hits);
 }
 
-size_t machines__fprintf_dsos_buildid(struct rb_root *self, FILE *fp, bool with_hits)
+size_t machines__fprintf_dsos_buildid(struct rb_root *machines,
+				      FILE *fp, bool with_hits)
 {
 	struct rb_node *nd;
 	size_t ret = 0;
 
-	for (nd = rb_first(self); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(machines); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		ret += machine__fprintf_dsos_buildid(pos, fp, with_hits);
 	}
@@ -2136,59 +2172,59 @@ size_t machines__fprintf_dsos_buildid(struct rb_root *self, FILE *fp, bool with_
 
 struct dso *dso__new_kernel(const char *name)
 {
-	struct dso *self = dso__new(name ?: "[kernel.kallsyms]");
+	struct dso *dso = dso__new(name ?: "[kernel.kallsyms]");
 
-	if (self != NULL) {
-		dso__set_short_name(self, "[kernel]");
-		self->kernel = DSO_TYPE_KERNEL;
+	if (dso != NULL) {
+		dso__set_short_name(dso, "[kernel]");
+		dso->kernel = DSO_TYPE_KERNEL;
 	}
 
-	return self;
+	return dso;
 }
 
 static struct dso *dso__new_guest_kernel(struct machine *machine,
 					const char *name)
 {
 	char bf[PATH_MAX];
-	struct dso *self = dso__new(name ?: machine__mmap_name(machine, bf, sizeof(bf)));
-
-	if (self != NULL) {
-		dso__set_short_name(self, "[guest.kernel]");
-		self->kernel = DSO_TYPE_GUEST_KERNEL;
+	struct dso *dso = dso__new(name ?: machine__mmap_name(machine, bf,
+							      sizeof(bf)));
+	if (dso != NULL) {
+		dso__set_short_name(dso, "[guest.kernel]");
+		dso->kernel = DSO_TYPE_GUEST_KERNEL;
 	}
 
-	return self;
+	return dso;
 }
 
-void dso__read_running_kernel_build_id(struct dso *self, struct machine *machine)
+void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine)
 {
 	char path[PATH_MAX];
 
 	if (machine__is_default_guest(machine))
 		return;
 	sprintf(path, "%s/sys/kernel/notes", machine->root_dir);
-	if (sysfs__read_build_id(path, self->build_id,
-				 sizeof(self->build_id)) == 0)
-		self->has_build_id = true;
+	if (sysfs__read_build_id(path, dso->build_id,
+				 sizeof(dso->build_id)) == 0)
+		dso->has_build_id = true;
 }
 
-static struct dso *machine__create_kernel(struct machine *self)
+static struct dso *machine__create_kernel(struct machine *machine)
 {
 	const char *vmlinux_name = NULL;
 	struct dso *kernel;
 
-	if (machine__is_host(self)) {
+	if (machine__is_host(machine)) {
 		vmlinux_name = symbol_conf.vmlinux_name;
 		kernel = dso__new_kernel(vmlinux_name);
 	} else {
-		if (machine__is_default_guest(self))
+		if (machine__is_default_guest(machine))
 			vmlinux_name = symbol_conf.default_guest_vmlinux_name;
-		kernel = dso__new_guest_kernel(self, vmlinux_name);
+		kernel = dso__new_guest_kernel(machine, vmlinux_name);
 	}
 
 	if (kernel != NULL) {
-		dso__read_running_kernel_build_id(kernel, self);
-		dsos__add(&self->kernel_dsos, kernel);
+		dso__read_running_kernel_build_id(kernel, machine);
+		dsos__add(&machine->kernel_dsos, kernel);
 	}
 	return kernel;
 }
@@ -2227,47 +2263,52 @@ static u64 machine__get_kernel_start_addr(struct machine *machine)
 		}
 	}
 
+	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+		return 0;
+
 	if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0)
 		return 0;
 
 	return args.start;
 }
 
-int __machine__create_kernel_maps(struct machine *self, struct dso *kernel)
+int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {
 	enum map_type type;
-	u64 start = machine__get_kernel_start_addr(self);
+	u64 start = machine__get_kernel_start_addr(machine);
 
 	for (type = 0; type < MAP__NR_TYPES; ++type) {
 		struct kmap *kmap;
 
-		self->vmlinux_maps[type] = map__new2(start, kernel, type);
-		if (self->vmlinux_maps[type] == NULL)
+		machine->vmlinux_maps[type] = map__new2(start, kernel, type);
+		if (machine->vmlinux_maps[type] == NULL)
 			return -1;
 
-		self->vmlinux_maps[type]->map_ip =
-			self->vmlinux_maps[type]->unmap_ip = identity__map_ip;
-
-		kmap = map__kmap(self->vmlinux_maps[type]);
-		kmap->kmaps = &self->kmaps;
-		map_groups__insert(&self->kmaps, self->vmlinux_maps[type]);
+		machine->vmlinux_maps[type]->map_ip =
+			machine->vmlinux_maps[type]->unmap_ip =
+				identity__map_ip;
+		kmap = map__kmap(machine->vmlinux_maps[type]);
+		kmap->kmaps = &machine->kmaps;
+		map_groups__insert(&machine->kmaps,
+				   machine->vmlinux_maps[type]);
 	}
 
 	return 0;
 }
 
-void machine__destroy_kernel_maps(struct machine *self)
+void machine__destroy_kernel_maps(struct machine *machine)
 {
 	enum map_type type;
 
 	for (type = 0; type < MAP__NR_TYPES; ++type) {
 		struct kmap *kmap;
 
-		if (self->vmlinux_maps[type] == NULL)
+		if (machine->vmlinux_maps[type] == NULL)
 			continue;
 
-		kmap = map__kmap(self->vmlinux_maps[type]);
-		map_groups__remove(&self->kmaps, self->vmlinux_maps[type]);
+		kmap = map__kmap(machine->vmlinux_maps[type]);
+		map_groups__remove(&machine->kmaps,
+				   machine->vmlinux_maps[type]);
 		if (kmap->ref_reloc_sym) {
 			/*
 			 * ref_reloc_sym is shared among all maps, so free just
@@ -2281,25 +2322,25 @@ void machine__destroy_kernel_maps(struct machine *self)
 			kmap->ref_reloc_sym = NULL;
 		}
 
-		map__delete(self->vmlinux_maps[type]);
-		self->vmlinux_maps[type] = NULL;
+		map__delete(machine->vmlinux_maps[type]);
+		machine->vmlinux_maps[type] = NULL;
 	}
 }
 
-int machine__create_kernel_maps(struct machine *self)
+int machine__create_kernel_maps(struct machine *machine)
 {
-	struct dso *kernel = machine__create_kernel(self);
+	struct dso *kernel = machine__create_kernel(machine);
 
 	if (kernel == NULL ||
-	    __machine__create_kernel_maps(self, kernel) < 0)
+	    __machine__create_kernel_maps(machine, kernel) < 0)
 		return -1;
 
-	if (symbol_conf.use_modules && machine__create_modules(self) < 0)
+	if (symbol_conf.use_modules && machine__create_modules(machine) < 0)
 		pr_debug("Problems creating module maps, continuing anyway...\n");
 	/*
 	 * Now that we have all the maps created, just set the ->end of them:
 	 */
-	map_groups__fixup_end(&self->kmaps);
+	map_groups__fixup_end(&machine->kmaps);
 	return 0;
 }
 
@@ -2363,11 +2404,11 @@ out_fail:
 	return -1;
 }
 
-size_t machine__fprintf_vmlinux_path(struct machine *self, FILE *fp)
+size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
 {
 	int i;
 	size_t printed = 0;
-	struct dso *kdso = self->vmlinux_maps[MAP__FUNCTION]->dso;
+	struct dso *kdso = machine->vmlinux_maps[MAP__FUNCTION]->dso;
 
 	if (kdso->has_build_id) {
 		char filename[PATH_MAX];
@@ -2396,6 +2437,25 @@ static int setup_list(struct strlist **list, const char *list_str,
 	return 0;
 }
 
+static bool symbol__read_kptr_restrict(void)
+{
+	bool value = false;
+
+	if (geteuid() != 0) {
+		FILE *fp = fopen("/proc/sys/kernel/kptr_restrict", "r");
+		if (fp != NULL) {
+			char line[8];
+
+			if (fgets(line, sizeof(line), fp) != NULL)
+				value = atoi(line) != 0;
+
+			fclose(fp);
+		}
+	}
+
+	return value;
+}
+
 int symbol__init(void)
 {
 	const char *symfs;
@@ -2403,6 +2463,8 @@ int symbol__init(void)
 	if (symbol_conf.initialized)
 		return 0;
 
+	symbol_conf.priv_size = ALIGN(symbol_conf.priv_size, sizeof(u64));
+
 	elf_version(EV_CURRENT);
 	if (symbol_conf.sort_by_name)
 		symbol_conf.priv_size += (sizeof(struct symbol_name_rb_node) -
@@ -2440,6 +2502,8 @@ int symbol__init(void)
 	if (symfs != symbol_conf.symfs)
 		free((void *)symfs);
 
+	symbol_conf.kptr_restrict = symbol__read_kptr_restrict();
+
 	symbol_conf.initialized = true;
 	return 0;
 
@@ -2462,9 +2526,9 @@ void symbol__exit(void)
 	symbol_conf.initialized = false;
 }
 
-int machines__create_kernel_maps(struct rb_root *self, pid_t pid)
+int machines__create_kernel_maps(struct rb_root *machines, pid_t pid)
 {
-	struct machine *machine = machines__findnew(self, pid);
+	struct machine *machine = machines__findnew(machines, pid);
 
 	if (machine == NULL)
 		return -1;
@@ -2515,7 +2579,7 @@ char *strxfrchar(char *s, char from, char to)
 	return s;
 }
 
-int machines__create_guest_kernel_maps(struct rb_root *self)
+int machines__create_guest_kernel_maps(struct rb_root *machines)
 {
 	int ret = 0;
 	struct dirent **namelist = NULL;
@@ -2526,7 +2590,7 @@ int machines__create_guest_kernel_maps(struct rb_root *self)
 	if (symbol_conf.default_guest_vmlinux_name ||
 	    symbol_conf.default_guest_modules ||
 	    symbol_conf.default_guest_kallsyms) {
-		machines__create_kernel_maps(self, DEFAULT_GUEST_KERNEL_ID);
+		machines__create_kernel_maps(machines, DEFAULT_GUEST_KERNEL_ID);
 	}
 
 	if (symbol_conf.guestmount) {
@@ -2547,7 +2611,7 @@ int machines__create_guest_kernel_maps(struct rb_root *self)
 				pr_debug("Can't access file %s\n", path);
 				goto failure;
 			}
-			machines__create_kernel_maps(self, pid);
+			machines__create_kernel_maps(machines, pid);
 		}
 failure:
 		free(namelist);
@@ -2556,23 +2620,23 @@ failure:
 	return ret;
 }
 
-void machines__destroy_guest_kernel_maps(struct rb_root *self)
+void machines__destroy_guest_kernel_maps(struct rb_root *machines)
 {
-	struct rb_node *next = rb_first(self);
+	struct rb_node *next = rb_first(machines);
 
 	while (next) {
 		struct machine *pos = rb_entry(next, struct machine, rb_node);
 
 		next = rb_next(&pos->rb_node);
-		rb_erase(&pos->rb_node, self);
+		rb_erase(&pos->rb_node, machines);
 		machine__delete(pos);
 	}
 }
 
-int machine__load_kallsyms(struct machine *self, const char *filename,
+int machine__load_kallsyms(struct machine *machine, const char *filename,
 			   enum map_type type, symbol_filter_t filter)
 {
-	struct map *map = self->vmlinux_maps[type];
+	struct map *map = machine->vmlinux_maps[type];
 	int ret = dso__load_kallsyms(map->dso, filename, map, filter);
 
 	if (ret > 0) {
@@ -2582,16 +2646,16 @@ int machine__load_kallsyms(struct machine *self, const char *filename,
 		 * kernel, with modules between them, fixup the end of all
 		 * sections.
 		 */
-		__map_groups__fixup_end(&self->kmaps, type);
+		__map_groups__fixup_end(&machine->kmaps, type);
 	}
 
 	return ret;
 }
 
-int machine__load_vmlinux_path(struct machine *self, enum map_type type,
+int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
 			       symbol_filter_t filter)
 {
-	struct map *map = self->vmlinux_maps[type];
+	struct map *map = machine->vmlinux_maps[type];
 	int ret = dso__load_vmlinux_path(map->dso, map, filter);
 
 	if (ret > 0) {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 713b0b40cc4a..325ee36a9d29 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -62,7 +62,7 @@ struct symbol {
 	char		name[0];
 };
 
-void symbol__delete(struct symbol *self);
+void symbol__delete(struct symbol *sym);
 
 struct strlist;
 
@@ -75,7 +75,8 @@ struct symbol_conf {
 			use_callchain,
 			exclude_other,
 			show_cpu_utilization,
-			initialized;
+			initialized,
+			kptr_restrict;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
@@ -96,9 +97,9 @@ struct symbol_conf {
 
 extern struct symbol_conf symbol_conf;
 
-static inline void *symbol__priv(struct symbol *self)
+static inline void *symbol__priv(struct symbol *sym)
 {
-	return ((void *)self) - symbol_conf.priv_size;
+	return ((void *)sym) - symbol_conf.priv_size;
 }
 
 struct ref_reloc_sym {
@@ -155,43 +156,45 @@ struct dso {
 
 struct dso *dso__new(const char *name);
 struct dso *dso__new_kernel(const char *name);
-void dso__delete(struct dso *self);
+void dso__delete(struct dso *dso);
 
-int dso__name_len(const struct dso *self);
+int dso__name_len(const struct dso *dso);
 
-bool dso__loaded(const struct dso *self, enum map_type type);
-bool dso__sorted_by_name(const struct dso *self, enum map_type type);
+bool dso__loaded(const struct dso *dso, enum map_type type);
+bool dso__sorted_by_name(const struct dso *dso, enum map_type type);
 
-static inline void dso__set_loaded(struct dso *self, enum map_type type)
+static inline void dso__set_loaded(struct dso *dso, enum map_type type)
 {
-	self->loaded |= (1 << type);
+	dso->loaded |= (1 << type);
 }
 
-void dso__sort_by_name(struct dso *self, enum map_type type);
+void dso__sort_by_name(struct dso *dso, enum map_type type);
 
 struct dso *__dsos__findnew(struct list_head *head, const char *name);
 
-int dso__load(struct dso *self, struct map *map, symbol_filter_t filter);
-int dso__load_vmlinux(struct dso *self, struct map *map,
+int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter);
+int dso__load_vmlinux(struct dso *dso, struct map *map,
 		      const char *vmlinux, symbol_filter_t filter);
-int dso__load_vmlinux_path(struct dso *self, struct map *map,
+int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 			   symbol_filter_t filter);
-int dso__load_kallsyms(struct dso *self, const char *filename, struct map *map,
+int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
 		       symbol_filter_t filter);
-int machine__load_kallsyms(struct machine *self, const char *filename,
+int machine__load_kallsyms(struct machine *machine, const char *filename,
 			   enum map_type type, symbol_filter_t filter);
-int machine__load_vmlinux_path(struct machine *self, enum map_type type,
+int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
 			       symbol_filter_t filter);
 
 size_t __dsos__fprintf(struct list_head *head, FILE *fp);
 
-size_t machine__fprintf_dsos_buildid(struct machine *self, FILE *fp, bool with_hits);
-size_t machines__fprintf_dsos(struct rb_root *self, FILE *fp);
-size_t machines__fprintf_dsos_buildid(struct rb_root *self, FILE *fp, bool with_hits);
-
-size_t dso__fprintf_buildid(struct dso *self, FILE *fp);
-size_t dso__fprintf_symbols_by_name(struct dso *self, enum map_type type, FILE *fp);
-size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp);
+size_t machine__fprintf_dsos_buildid(struct machine *machine,
+				     FILE *fp, bool with_hits);
+size_t machines__fprintf_dsos(struct rb_root *machines, FILE *fp);
+size_t machines__fprintf_dsos_buildid(struct rb_root *machines,
+				      FILE *fp, bool with_hits);
+size_t dso__fprintf_buildid(struct dso *dso, FILE *fp);
+size_t dso__fprintf_symbols_by_name(struct dso *dso,
+				    enum map_type type, FILE *fp);
+size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp);
 
 enum symtab_type {
 	SYMTAB__KALLSYMS = 0,
@@ -207,34 +210,36 @@ enum symtab_type {
 	SYMTAB__NOT_FOUND,
 };
 
-char dso__symtab_origin(const struct dso *self);
-void dso__set_long_name(struct dso *self, char *name);
-void dso__set_build_id(struct dso *self, void *build_id);
-void dso__read_running_kernel_build_id(struct dso *self, struct machine *machine);
-struct symbol *dso__find_symbol(struct dso *self, enum map_type type, u64 addr);
-struct symbol *dso__find_symbol_by_name(struct dso *self, enum map_type type,
+char dso__symtab_origin(const struct dso *dso);
+void dso__set_long_name(struct dso *dso, char *name);
+void dso__set_build_id(struct dso *dso, void *build_id);
+void dso__read_running_kernel_build_id(struct dso *dso,
+				       struct machine *machine);
+struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
+				u64 addr);
+struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
 					const char *name);
 
 int filename__read_build_id(const char *filename, void *bf, size_t size);
 int sysfs__read_build_id(const char *filename, void *bf, size_t size);
 bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
-int build_id__sprintf(const u8 *self, int len, char *bf);
+int build_id__sprintf(const u8 *build_id, int len, char *bf);
 int kallsyms__parse(const char *filename, void *arg,
 		    int (*process_symbol)(void *arg, const char *name,
 					  char type, u64 start, u64 end));
 
-void machine__destroy_kernel_maps(struct machine *self);
-int __machine__create_kernel_maps(struct machine *self, struct dso *kernel);
-int machine__create_kernel_maps(struct machine *self);
+void machine__destroy_kernel_maps(struct machine *machine);
+int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel);
+int machine__create_kernel_maps(struct machine *machine);
 
-int machines__create_kernel_maps(struct rb_root *self, pid_t pid);
-int machines__create_guest_kernel_maps(struct rb_root *self);
-void machines__destroy_guest_kernel_maps(struct rb_root *self);
+int machines__create_kernel_maps(struct rb_root *machines, pid_t pid);
+int machines__create_guest_kernel_maps(struct rb_root *machines);
+void machines__destroy_guest_kernel_maps(struct rb_root *machines);
 
 int symbol__init(void);
 void symbol__exit(void);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 
-size_t machine__fprintf_vmlinux_path(struct machine *self, FILE *fp);
+size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
 
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 0a7ed5b5e281..1e88485c16a0 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -2187,7 +2187,6 @@ static const struct flag flags[] = {
 	{ "TASKLET_SOFTIRQ", 6 },
 	{ "SCHED_SOFTIRQ", 7 },
 	{ "HRTIMER_SOFTIRQ", 8 },
-	{ "RCU_SOFTIRQ", 9 },
 
 	{ "HRTIMER_NORESTART", 0 },
 	{ "HRTIMER_RESTART", 1 },
diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c
index 8c17a8730e4a..0229723aceb3 100644
--- a/tools/perf/util/ui/browsers/annotate.c
+++ b/tools/perf/util/ui/browsers/annotate.c
@@ -5,7 +5,6 @@
 #include "../../hist.h"
 #include "../../sort.h"
 #include "../../symbol.h"
-#include "../../annotate.h"
 #include <pthread.h>
 
 static void ui__error_window(const char *fmt, ...)
@@ -256,10 +255,9 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 			 int refresh)
 {
 	struct objdump_line *pos, *n;
-	struct annotation *notes = symbol__annotation(sym);
+	struct annotation *notes;
 	struct annotate_browser browser = {
 		.b = {
-			.entries = &notes->src->source,
 			.refresh = ui_browser__list_head_refresh,
 			.seek	 = ui_browser__list_head_seek,
 			.write	 = annotate_browser__write,
@@ -281,6 +279,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 
 	ui_helpline__push("Press <- or ESC to exit");
 
+	notes = symbol__annotation(sym);
+
 	list_for_each_entry(pos, &notes->src->source, node) {
 		struct objdump_line_rb_node *rbpos;
 		size_t line_len = strlen(pos->line);
@@ -291,6 +291,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 		rbpos->idx = browser.b.nr_entries++;
 	}
 
+	browser.b.entries = &notes->src->source,
 	browser.b.width += 18; /* Percentage */
 	ret = annotate_browser__run(&browser, evidx, refresh);
 	list_for_each_entry_safe(pos, n, &notes->src->source, node) {
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index 798efdca3ead..5d767c622dfc 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -851,7 +851,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel,
 			goto out_free_stack;
 		case 'a':
 			if (browser->selection == NULL ||
-			    browser->selection->map == NULL ||
+			    browser->selection->sym == NULL ||
 			    browser->selection->map->dso->annotate_warned)
 				continue;
 			goto do_annotate;
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 362a0cb448db..6d8ef4a3a9b5 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -990,7 +990,7 @@ int fork_it(char **argv)
 	if (!retval)
 		print_counters(cnt_delta);
 
-	fprintf(stderr, "%.6f sec\n", tv_delta.tv_sec + tv_delta.tv_usec/1000000.0);;
+	fprintf(stderr, "%.6f sec\n", tv_delta.tv_sec + tv_delta.tv_usec/1000000.0);
 
 	return 0;
 }
diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
index d9678a34dd70..2618ef2ba31f 100644
--- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
+++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
@@ -46,7 +46,7 @@ int cpu = -1;
  *
  *  performance
  *	Performance is paramount.
- *	Unwilling to sacrafice any performance
+ *	Unwilling to sacrifice any performance
  *	for the sake of energy saving. (hardware default)
  *
  *  normal
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 8ce792ea08e9..1fd29b2daa92 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -36,6 +36,7 @@ $default{"REBOOT_ON_SUCCESS"}	= 1;
 $default{"POWEROFF_ON_SUCCESS"}	= 0;
 $default{"BUILD_OPTIONS"}	= "";
 $default{"BISECT_SLEEP_TIME"}	= 60;   # sleep time between bisects
+$default{"PATCHCHECK_SLEEP_TIME"} = 60; # sleep time between patch checks
 $default{"CLEAR_LOG"}		= 0;
 $default{"BISECT_MANUAL"}	= 0;
 $default{"BISECT_SKIP"}		= 1;
@@ -96,6 +97,7 @@ my $monitor_pid;
 my $monitor_cnt = 0;
 my $sleep_time;
 my $bisect_sleep_time;
+my $patchcheck_sleep_time;
 my $store_failures;
 my $timeout;
 my $booted_timeout;
@@ -112,6 +114,7 @@ my $successes = 0;
 
 my %entered_configs;
 my %config_help;
+my %variable;
 
 $config_help{"MACHINE"} = << "EOF"
  The machine hostname that you will test.
@@ -260,6 +263,39 @@ sub get_ktest_configs {
     }
 }
 
+sub process_variables {
+    my ($value) = @_;
+    my $retval = "";
+
+    # We want to check for '\', and it is just easier
+    # to check the previous characet of '$' and not need
+    # to worry if '$' is the first character. By adding
+    # a space to $value, we can just check [^\\]\$ and
+    # it will still work.
+    $value = " $value";
+
+    while ($value =~ /(.*?[^\\])\$\{(.*?)\}(.*)/) {
+	my $begin = $1;
+	my $var = $2;
+	my $end = $3;
+	# append beginning of value to retval
+	$retval = "$retval$begin";
+	if (defined($variable{$var})) {
+	    $retval = "$retval$variable{$var}";
+	} else {
+	    # put back the origin piece.
+	    $retval = "$retval\$\{$var\}";
+	}
+	$value = $end;
+    }
+    $retval = "$retval$value";
+
+    # remove the space added in the beginning
+    $retval =~ s/ //;
+
+    return "$retval"
+}
+
 sub set_value {
     my ($lvalue, $rvalue) = @_;
 
@@ -269,10 +305,22 @@ sub set_value {
     if ($rvalue =~ /^\s*$/) {
 	delete $opt{$lvalue};
     } else {
+	$rvalue = process_variables($rvalue);
 	$opt{$lvalue} = $rvalue;
     }
 }
 
+sub set_variable {
+    my ($lvalue, $rvalue) = @_;
+
+    if ($rvalue =~ /^\s*$/) {
+	delete $variable{$lvalue};
+    } else {
+	$rvalue = process_variables($rvalue);
+	$variable{$lvalue} = $rvalue;
+    }
+}
+
 sub read_config {
     my ($config) = @_;
 
@@ -385,6 +433,22 @@ sub read_config {
 		    $repeats{$val} = $repeat;
 		}
 	    }
+	} elsif (/^\s*([A-Z_\[\]\d]+)\s*:=\s*(.*?)\s*$/) {
+	    next if ($skip);
+
+	    my $lvalue = $1;
+	    my $rvalue = $2;
+
+	    # process config variables.
+	    # Config variables are only active while reading the
+	    # config and can be defined anywhere. They also ignore
+	    # TEST_START and DEFAULTS, but are skipped if they are in
+	    # on of these sections that have SKIP defined.
+	    # The save variable can be
+	    # defined multiple times and the new one simply overrides
+	    # the prevous one.
+	    set_variable($lvalue, $rvalue);
+
 	} else {
 	    die "$name: $.: Garbage found in config\n$_";
 	}
@@ -838,6 +902,7 @@ sub monitor {
 
 	if ($stop_test_after > 0 && !$booted && !$bug) {
 	    if (time - $monitor_start > $stop_test_after) {
+		doprint "STOP_TEST_AFTER ($stop_test_after seconds) timed out\n";
 		$done = 1;
 	    }
 	}
@@ -907,7 +972,7 @@ sub install {
     return if (!defined($post_install));
 
     my $cp_post_install = $post_install;
-    $cp_post_install = s/\$KERNEL_VERSION/$version/g;
+    $cp_post_install =~ s/\$KERNEL_VERSION/$version/g;
     run_command "$cp_post_install" or
 	dodie "Failed to run post install";
 }
@@ -1247,14 +1312,14 @@ sub run_bisect_test {
 
     if ($failed) {
 	$result = 0;
-
-	# reboot the box to a good kernel
-	if ($type ne "build") {
-	    bisect_reboot;
-	}
     } else {
 	$result = 1;
     }
+
+    # reboot the box to a kernel we can ssh to
+    if ($type ne "build") {
+	bisect_reboot;
+    }
     $in_bisect = 0;
 
     return $result;
@@ -1763,6 +1828,14 @@ sub config_bisect {
     success $i;
 }
 
+sub patchcheck_reboot {
+    doprint "Reboot and sleep $patchcheck_sleep_time seconds\n";
+    reboot;
+    start_monitor;
+    wait_for_monitor $patchcheck_sleep_time;
+    end_monitor;
+}
+
 sub patchcheck {
     my ($i) = @_;
 
@@ -1854,6 +1927,8 @@ sub patchcheck {
 	end_monitor;
 	return 0 if ($failed);
 
+	patchcheck_reboot;
+
     }
     $in_patchcheck = 0;
     success $i;
@@ -1944,7 +2019,7 @@ for (my $i = 0, my $repeat = 1; $i <= $opt{"NUM_TESTS"}; $i += $repeat) {
     }
 }
 
-sub set_test_option {
+sub __set_test_option {
     my ($name, $i) = @_;
 
     my $option = "$name\[$i\]";
@@ -1970,6 +2045,72 @@ sub set_test_option {
     return undef;
 }
 
+sub eval_option {
+    my ($option, $i) = @_;
+
+    # Add space to evaluate the character before $
+    $option = " $option";
+    my $retval = "";
+
+    while ($option =~ /(.*?[^\\])\$\{(.*?)\}(.*)/) {
+	my $start = $1;
+	my $var = $2;
+	my $end = $3;
+
+	# Append beginning of line
+	$retval = "$retval$start";
+
+	# If the iteration option OPT[$i] exists, then use that.
+	# otherwise see if the default OPT (without [$i]) exists.
+
+	my $o = "$var\[$i\]";
+
+	if (defined($opt{$o})) {
+	    $o = $opt{$o};
+	    $retval = "$retval$o";
+	} elsif (defined($opt{$var})) {
+	    $o = $opt{$var};
+	    $retval = "$retval$o";
+	} else {
+	    $retval = "$retval\$\{$var\}";
+	}
+
+	$option = $end;
+    }
+
+    $retval = "$retval$option";
+
+    $retval =~ s/^ //;
+
+    return $retval;
+}
+
+sub set_test_option {
+    my ($name, $i) = @_;
+
+    my $option = __set_test_option($name, $i);
+    return $option if (!defined($option));
+
+    my $prev = "";
+
+    # Since an option can evaluate to another option,
+    # keep iterating until we do not evaluate any more
+    # options.
+    my $r = 0;
+    while ($prev ne $option) {
+	# Check for recursive evaluations.
+	# 100 deep should be more than enough.
+	if ($r++ > 100) {
+	    die "Over 100 evaluations accurred with $name\n" .
+		"Check for recursive variables\n";
+	}
+	$prev = $option;
+	$option = eval_option($option, $i);
+    }
+
+    return $option;
+}
+
 # First we need to do is the builds
 for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
 
@@ -2003,6 +2144,7 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
     $poweroff_after_halt = set_test_option("POWEROFF_AFTER_HALT", $i);
     $sleep_time = set_test_option("SLEEP_TIME", $i);
     $bisect_sleep_time = set_test_option("BISECT_SLEEP_TIME", $i);
+    $patchcheck_sleep_time = set_test_option("PATCHCHECK_SLEEP_TIME", $i);
     $bisect_manual = set_test_option("BISECT_MANUAL", $i);
     $bisect_skip = set_test_option("BISECT_SKIP", $i);
     $store_failures = set_test_option("STORE_FAILURES", $i);
diff --git a/tools/testing/ktest/sample.conf b/tools/testing/ktest/sample.conf
index 4c5d6bd74a02..48cbcc80602a 100644
--- a/tools/testing/ktest/sample.conf
+++ b/tools/testing/ktest/sample.conf
@@ -73,6 +73,95 @@
 # ktest will fail to execute, and no tests will run.
 #
 
+#### Config variables ####
+#
+# This config file can also contain "config variables".
+# These are assigned with ":=" instead of the ktest option
+# assigment "=".
+#
+# The difference between ktest options and config variables
+# is that config variables can be used multiple times,
+# where each instance will override the previous instance.
+# And that they only live at time of processing this config.
+#
+# The advantage to config variables are that they can be used
+# by any option or any other config variables to define thing
+# that you may use over and over again in the options.
+#
+# For example:
+#
+# USER      := root
+# TARGET    := mybox
+# TEST_CASE := ssh ${USER}@${TARGET} /path/to/my/test
+#
+# TEST_START
+# MIN_CONFIG = config1
+# TEST = ${TEST_CASE}
+#
+# TEST_START
+# MIN_CONFIG = config2
+# TEST = ${TEST_CASE}
+#
+# TEST_CASE := ssh ${USER}@${TARGET} /path/to/my/test2
+#
+# TEST_START
+# MIN_CONFIG = config1
+# TEST = ${TEST_CASE}
+#
+# TEST_START
+# MIN_CONFIG = config2
+# TEST = ${TEST_CASE}
+#
+# TEST_DIR := /home/me/test
+#
+# BUILD_DIR = ${TEST_DIR}/linux.git
+# OUTPUT_DIR = ${TEST_DIR}/test
+#
+# Note, the config variables are evaluated immediately, thus
+# updating TARGET after TEST_CASE has been assigned does nothing
+# to TEST_CASE.
+#
+# As shown in the example, to evaluate a config variable, you
+# use the ${X} convention. Simple $X will not work.
+#
+# If the config variable does not exist, the ${X} will not
+# be evaluated. Thus:
+#
+# MAKE_CMD = PATH=/mypath:${PATH} make
+#
+# If PATH is not a config variable, then the ${PATH} in
+# the MAKE_CMD option will be evaluated by the shell when
+# the MAKE_CMD option is passed into shell processing.
+
+#### Using options in other options ####
+#
+# Options that are defined in the config file may also be used
+# by other options. All options are evaulated at time of
+# use (except that config variables are evaluated at config
+# processing time).
+#
+# If an ktest option is used within another option, instead of
+# typing it again in that option you can simply use the option
+# just like you can config variables.
+#
+# MACHINE = mybox
+#
+# TEST = ssh root@${MACHINE} /path/to/test
+#
+# The option will be used per test case. Thus:
+#
+# TEST_TYPE = test
+# TEST = ssh root@{MACHINE}
+#
+# TEST_START
+# MACHINE = box1
+#
+# TEST_START
+# MACHINE = box2
+#
+# For both test cases, MACHINE will be evaluated at the time
+# of the test case. The first test will run ssh root@box1
+# and the second will run ssh root@box2.
 
 #### Mandatory Default Options ####
 
@@ -366,6 +455,10 @@
 # (default 60)
 #BISECT_SLEEP_TIME = 60
 
+# The time in between patch checks to sleep (in seconds)
+# (default 60)
+#PATCHCHECK_SLEEP_TIME = 60
+
 # Reboot the target box on error (default 0)
 #REBOOT_ON_ERROR = 0