Linux-libre 4.6.2-gnu

331 files changed, 23811 insertions, 2757 deletions

diff --git a/tools/Makefile b/tools/Makefile
index 6339f6ac3..60c7e6c8f 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -13,6 +13,7 @@ help:
 	@echo '  cpupower               - a tool for all things x86 CPU power'
 	@echo '  firewire               - the userspace part of nosy, an IEEE-1394 traffic sniffer'
 	@echo '  freefall               - laptop accelerometer program for disk protection'
+	@echo '  gpio                   - GPIO tools'
 	@echo '  hv                     - tools used when in Hyper-V clients'
 	@echo '  iio                    - IIO tools'
 	@echo '  lguest                 - a minimal 32-bit x86 hypervisor'
@@ -20,6 +21,7 @@ help:
 	@echo '  perf                   - Linux performance measurement and analysis tool'
 	@echo '  selftests              - various kernel selftests'
 	@echo '  spi                    - spi tools'
+	@echo '  objtool                - an ELF object analysis tool'
 	@echo '  tmon                   - thermal monitoring and tuning tool'
 	@echo '  turbostat              - Intel CPU idle stats and freq reporting tool'
 	@echo '  usb                    - USB testing tools'
@@ -53,7 +55,7 @@ acpi: FORCE
 cpupower: FORCE
 	$(call descend,power/$@)
 
-cgroup firewire hv guest spi usb virtio vm net iio: FORCE
+cgroup firewire hv guest spi usb virtio vm net iio gpio objtool: FORCE
 	$(call descend,$@)
 
 liblockdep: FORCE
@@ -85,7 +87,7 @@ freefall: FORCE
 all: acpi cgroup cpupower hv firewire lguest \
 		perf selftests turbostat usb \
 		virtio vm net x86_energy_perf_policy \
-		tmon freefall
+		tmon freefall objtool
 
 acpi_install:
 	$(call descend,power/$(@:_install=),install)
@@ -93,7 +95,7 @@ acpi_install:
 cpupower_install:
 	$(call descend,power/$(@:_install=),install)
 
-cgroup_install firewire_install hv_install lguest_install perf_install usb_install virtio_install vm_install net_install:
+cgroup_install firewire_install hv_install lguest_install perf_install usb_install virtio_install vm_install net_install objtool_install:
 	$(call descend,$(@:_install=),install)
 
 selftests_install:
@@ -111,7 +113,7 @@ freefall_install:
 install: acpi_install cgroup_install cpupower_install hv_install firewire_install lguest_install \
 		perf_install selftests_install turbostat_install usb_install \
 		virtio_install vm_install net_install x86_energy_perf_policy_install \
-		tmon_install freefall_install
+		tmon_install freefall_install objtool_install
 
 acpi_clean:
 	$(call descend,power/acpi,clean)
@@ -119,7 +121,7 @@ acpi_clean:
 cpupower_clean:
 	$(call descend,power/cpupower,clean)
 
-cgroup_clean hv_clean firewire_clean lguest_clean spi_clean usb_clean virtio_clean vm_clean net_clean iio_clean:
+cgroup_clean hv_clean firewire_clean lguest_clean spi_clean usb_clean virtio_clean vm_clean net_clean iio_clean gpio_clean objtool_clean:
 	$(call descend,$(@:_clean=),clean)
 
 liblockdep_clean:
@@ -155,6 +157,7 @@ build_clean:
 clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean lguest_clean \
 		perf_clean selftests_clean turbostat_clean spi_clean usb_clean virtio_clean \
 		vm_clean net_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
-		freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean
+		freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean \
+		gpio_clean objtool_clean
 
 .PHONY: FORCE
diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index 4a96473b1..ee566e8bd 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -85,7 +85,7 @@ $(OUTPUT)%.i: %.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_i_c)
 
-$(OUTPUT)%.i: %.S FORCE
+$(OUTPUT)%.s: %.S FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_i_c)
 
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 02db3cdff..9f8786190 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -27,9 +27,10 @@ endef
 #   the rule that uses them - an example for that is the 'bionic'
 #   feature check. ]
 #
-FEATURE_TESTS ?=			\
+FEATURE_TESTS_BASIC :=			\
 	backtrace			\
 	dwarf				\
+	dwarf_getlocations		\
 	fortify-source			\
 	sync-compare-and-swap		\
 	glibc				\
@@ -46,6 +47,7 @@ FEATURE_TESTS ?=			\
 	libpython			\
 	libpython-version		\
 	libslang			\
+	libcrypto			\
 	libunwind			\
 	pthread-attr-setaffinity-np	\
 	stackprotector-all		\
@@ -56,8 +58,28 @@ FEATURE_TESTS ?=			\
 	get_cpuid			\
 	bpf
 
+# FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
+# of all feature tests
+FEATURE_TESTS_EXTRA :=			\
+	bionic				\
+	compile-32			\
+	compile-x32			\
+	cplus-demangle			\
+	hello				\
+	libbabeltrace			\
+	liberty				\
+	liberty-z			\
+	libunwind-debug-frame
+
+FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC)
+
+ifeq ($(FEATURE_TESTS),all)
+  FEATURE_TESTS := $(FEATURE_TESTS_BASIC) $(FEATURE_TESTS_EXTRA)
+endif
+
 FEATURE_DISPLAY ?=			\
 	dwarf				\
+	dwarf_getlocations		\
 	glibc				\
 	gtk2				\
 	libaudit			\
@@ -68,6 +90,7 @@ FEATURE_DISPLAY ?=			\
 	libperl				\
 	libpython			\
 	libslang			\
+	libcrypto			\
 	libunwind			\
 	libdw-dwarf-unwind		\
 	zlib				\
@@ -100,6 +123,14 @@ ifeq ($(feature-all), 1)
   # test-all.c passed - just set all the core feature flags to 1:
   #
   $(foreach feat,$(FEATURE_TESTS),$(call feature_set,$(feat)))
+  #
+  # test-all.c does not comprise these tests, so we need to
+  # for this case to get features proper values
+  #
+  $(call feature_check,compile-32)
+  $(call feature_check,compile-x32)
+  $(call feature_check,bionic)
+  $(call feature_check,libbabeltrace)
 else
   $(foreach feat,$(FEATURE_TESTS),$(call feature_check,$(feat)))
 endif
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index bf8f03522..4ae94dbfd 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -3,6 +3,7 @@ FILES=					\
 	test-backtrace.bin		\
 	test-bionic.bin			\
 	test-dwarf.bin			\
+	test-dwarf_getlocations.bin	\
 	test-fortify-source.bin		\
 	test-sync-compare-and-swap.bin	\
 	test-glibc.bin			\
@@ -23,6 +24,7 @@ FILES=					\
 	test-libpython.bin		\
 	test-libpython-version.bin	\
 	test-libslang.bin		\
+	test-libcrypto.bin		\
 	test-libunwind.bin		\
 	test-libunwind-debug-frame.bin	\
 	test-pthread-attr-setaffinity-np.bin	\
@@ -81,6 +83,9 @@ endif
 $(OUTPUT)test-dwarf.bin:
 	$(BUILD) $(DWARFLIBS)
 
+$(OUTPUT)test-dwarf_getlocations.bin:
+	$(BUILD) $(DWARFLIBS)
+
 $(OUTPUT)test-libelf-mmap.bin:
 	$(BUILD) -lelf
 
@@ -105,6 +110,9 @@ $(OUTPUT)test-libaudit.bin:
 $(OUTPUT)test-libslang.bin:
 	$(BUILD) -I/usr/include/slang -lslang
 
+$(OUTPUT)test-libcrypto.bin:
+	$(BUILD) -lcrypto
+
 $(OUTPUT)test-gtk2.bin:
 	$(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null)
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 81025cade..a282e8cb8 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -41,6 +41,10 @@
 # include "test-dwarf.c"
 #undef main
 
+#define main main_test_dwarf_getlocations
+# include "test-dwarf_getlocations.c"
+#undef main
+
 #define main main_test_libelf_getphdrnum
 # include "test-libelf-getphdrnum.c"
 #undef main
@@ -129,6 +133,10 @@
 # include "test-bpf.c"
 #undef main
 
+#define main main_test_libcrypto
+# include "test-libcrypto.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
@@ -139,6 +147,7 @@ int main(int argc, char *argv[])
 	main_test_libelf_mmap();
 	main_test_glibc();
 	main_test_dwarf();
+	main_test_dwarf_getlocations();
 	main_test_libelf_getphdrnum();
 	main_test_libunwind();
 	main_test_libaudit();
@@ -158,6 +167,7 @@ int main(int argc, char *argv[])
 	main_test_lzma();
 	main_test_get_cpuid();
 	main_test_bpf();
+	main_test_libcrypto();
 
 	return 0;
 }
diff --git a/tools/build/feature/test-compile.c b/tools/build/feature/test-compile.c
index 31dbf45bf..c54e6551a 100644
--- a/tools/build/feature/test-compile.c
+++ b/tools/build/feature/test-compile.c
@@ -1,4 +1,6 @@
+#include <stdio.h>
 int main(void)
 {
+	printf("Hello World!\n");
 	return 0;
 }
diff --git a/tools/build/feature/test-dwarf_getlocations.c b/tools/build/feature/test-dwarf_getlocations.c
new file mode 100644
index 000000000..70162699d
--- /dev/null
+++ b/tools/build/feature/test-dwarf_getlocations.c
@@ -0,0 +1,12 @@
+#include <stdlib.h>
+#include <elfutils/libdw.h>
+
+int main(void)
+{
+	Dwarf_Addr base, start, end;
+	Dwarf_Attribute attr;
+	Dwarf_Op *op;
+        size_t nops;
+	ptrdiff_t offset = 0;
+        return (int)dwarf_getlocations(&attr, offset, &base, &start, &end, &op, &nops);
+}
diff --git a/tools/build/feature/test-libcrypto.c b/tools/build/feature/test-libcrypto.c
new file mode 100644
index 000000000..bd79dc7f2
--- /dev/null
+++ b/tools/build/feature/test-libcrypto.c
@@ -0,0 +1,17 @@
+#include <openssl/sha.h>
+#include <openssl/md5.h>
+
+int main(void)
+{
+	MD5_CTX context;
+	unsigned char md[MD5_DIGEST_LENGTH + SHA_DIGEST_LENGTH];
+	unsigned char dat[] = "12345";
+
+	MD5_Init(&context);
+	MD5_Update(&context, &dat[0], sizeof(dat));
+	MD5_Final(&md[0], &context);
+
+	SHA1(&dat[0], sizeof(dat), &md[0]);
+
+	return 0;
+}
diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile
new file mode 100644
index 000000000..4d198d5c4
--- /dev/null
+++ b/tools/gpio/Makefile
@@ -0,0 +1,12 @@
+CC = $(CROSS_COMPILE)gcc
+CFLAGS += -Wall -g -D_GNU_SOURCE
+
+all: lsgpio
+
+lsgpio: lsgpio.o gpio-utils.o
+
+%.o: %.c gpio-utils.h
+
+.PHONY: clean
+clean:
+	rm -f *.o lsgpio
diff --git a/tools/gpio/gpio-utils.c b/tools/gpio/gpio-utils.c
new file mode 100644
index 000000000..8208718f2
--- /dev/null
+++ b/tools/gpio/gpio-utils.c
@@ -0,0 +1,11 @@
+/*
+ * GPIO tools - helpers library for the GPIO tools
+ *
+ * Copyright (C) 2015 Linus Walleij
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ */
+
+#include "gpio-utils.h"
diff --git a/tools/gpio/gpio-utils.h b/tools/gpio/gpio-utils.h
new file mode 100644
index 000000000..5f57133b8
--- /dev/null
+++ b/tools/gpio/gpio-utils.h
@@ -0,0 +1,27 @@
+/*
+ * GPIO tools - utility helpers library for the GPIO tools
+ *
+ * Copyright (C) 2015 Linus Walleij
+ *
+ * Portions copied from iio_utils and lssio:
+ * Copyright (c) 2010 Manuel Stahl <manuel.stahl@iis.fraunhofer.de>
+ * Copyright (c) 2008 Jonathan Cameron
+ * *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ */
+#ifndef _GPIO_UTILS_H_
+#define _GPIO_UTILS_H_
+
+#include <string.h>
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+static inline int check_prefix(const char *str, const char *prefix)
+{
+	return strlen(str) > strlen(prefix) &&
+		strncmp(str, prefix, strlen(prefix)) == 0;
+}
+
+#endif /* _GPIO_UTILS_H_ */
diff --git a/tools/gpio/lsgpio.c b/tools/gpio/lsgpio.c
new file mode 100644
index 000000000..1124da375
--- /dev/null
+++ b/tools/gpio/lsgpio.c
@@ -0,0 +1,195 @@
+/*
+ * lsgpio - example on how to list the GPIO lines on a system
+ *
+ * Copyright (C) 2015 Linus Walleij
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * Usage:
+ *	lsgpio <-n device-name>
+ */
+
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <dirent.h>
+#include <errno.h>
+#include <string.h>
+#include <poll.h>
+#include <fcntl.h>
+#include <getopt.h>
+#include <sys/ioctl.h>
+#include <linux/gpio.h>
+
+#include "gpio-utils.h"
+
+struct gpio_flag {
+	char *name;
+	unsigned long mask;
+};
+
+struct gpio_flag flagnames[] = {
+	{
+		.name = "kernel",
+		.mask = GPIOLINE_FLAG_KERNEL,
+	},
+	{
+		.name = "output",
+		.mask = GPIOLINE_FLAG_IS_OUT,
+	},
+	{
+		.name = "active-low",
+		.mask = GPIOLINE_FLAG_ACTIVE_LOW,
+	},
+	{
+		.name = "open-drain",
+		.mask = GPIOLINE_FLAG_OPEN_DRAIN,
+	},
+	{
+		.name = "open-source",
+		.mask = GPIOLINE_FLAG_OPEN_SOURCE,
+	},
+};
+
+void print_flags(unsigned long flags)
+{
+	int i;
+	int printed = 0;
+
+	for (i = 0; i < ARRAY_SIZE(flagnames); i++) {
+		if (flags & flagnames[i].mask) {
+			if (printed)
+				fprintf(stdout, " ");
+			fprintf(stdout, "%s", flagnames[i].name);
+			printed++;
+		}
+	}
+}
+
+int list_device(const char *device_name)
+{
+	struct gpiochip_info cinfo;
+	char *chrdev_name;
+	int fd;
+	int ret;
+	int i;
+
+	ret = asprintf(&chrdev_name, "/dev/%s", device_name);
+	if (ret < 0)
+		return -ENOMEM;
+
+	fd = open(chrdev_name, 0);
+	if (fd == -1) {
+		ret = -errno;
+		fprintf(stderr, "Failed to open %s\n", chrdev_name);
+		goto exit_close_error;
+	}
+
+	/* Inspect this GPIO chip */
+	ret = ioctl(fd, GPIO_GET_CHIPINFO_IOCTL, &cinfo);
+	if (ret == -1) {
+		ret = -errno;
+		perror("Failed to issue CHIPINFO IOCTL\n");
+		goto exit_close_error;
+	}
+	fprintf(stdout, "GPIO chip: %s, \"%s\", %u GPIO lines\n",
+		cinfo.name, cinfo.label, cinfo.lines);
+
+	/* Loop over the lines and print info */
+	for (i = 0; i < cinfo.lines; i++) {
+		struct gpioline_info linfo;
+
+		memset(&linfo, 0, sizeof(linfo));
+		linfo.line_offset = i;
+
+		ret = ioctl(fd, GPIO_GET_LINEINFO_IOCTL, &linfo);
+		if (ret == -1) {
+			ret = -errno;
+			perror("Failed to issue LINEINFO IOCTL\n");
+			goto exit_close_error;
+		}
+		fprintf(stdout, "\tline %2d:", linfo.line_offset);
+		if (linfo.name[0])
+			fprintf(stdout, " \"%s\"", linfo.name);
+		else
+			fprintf(stdout, " unnamed");
+		if (linfo.consumer[0])
+			fprintf(stdout, " \"%s\"", linfo.consumer);
+		else
+			fprintf(stdout, " unused");
+		if (linfo.flags) {
+			fprintf(stdout, " [");
+			print_flags(linfo.flags);
+			fprintf(stdout, "]");
+		}
+		fprintf(stdout, "\n");
+
+	}
+
+exit_close_error:
+	if (close(fd) == -1)
+		perror("Failed to close GPIO character device file");
+	free(chrdev_name);
+	return ret;
+}
+
+void print_usage(void)
+{
+	fprintf(stderr, "Usage: lsgpio [options]...\n"
+		"List GPIO chips, lines and states\n"
+		"  -n <name>  List GPIOs on a named device\n"
+		"  -?         This helptext\n"
+	);
+}
+
+int main(int argc, char **argv)
+{
+	const char *device_name;
+	int ret;
+	int c;
+
+	while ((c = getopt(argc, argv, "n:")) != -1) {
+		switch (c) {
+		case 'n':
+			device_name = optarg;
+			break;
+		case '?':
+			print_usage();
+			return -1;
+		}
+	}
+
+	if (device_name)
+		ret = list_device(device_name);
+	else {
+		const struct dirent *ent;
+		DIR *dp;
+
+		/* List all GPIO devices one at a time */
+		dp = opendir("/dev");
+		if (!dp) {
+			ret = -errno;
+			goto error_out;
+		}
+
+		ret = -ENOENT;
+		while (ent = readdir(dp), ent) {
+			if (check_prefix(ent->d_name, "gpiochip")) {
+				ret = list_device(ent->d_name);
+				if (ret)
+					break;
+			}
+		}
+
+		ret = 0;
+		if (closedir(dp) == -1) {
+			perror("scanning devices: Failed to close directory");
+			ret = -errno;
+		}
+	}
+error_out:
+	return ret;
+}
diff --git a/tools/include/asm-generic/bitops/__fls.h b/tools/include/asm-generic/bitops/__fls.h
index 2218b9add..494c9c615 100644
--- a/tools/include/asm-generic/bitops/__fls.h
+++ b/tools/include/asm-generic/bitops/__fls.h
@@ -1 +1 @@
-#include <../../../../include/asm-generic/bitops/__fls.h>
+#include "../../../../include/asm-generic/bitops/__fls.h"
diff --git a/tools/include/asm-generic/bitops/fls.h b/tools/include/asm-generic/bitops/fls.h
index dbf711a28..0e4995fa0 100644
--- a/tools/include/asm-generic/bitops/fls.h
+++ b/tools/include/asm-generic/bitops/fls.h
@@ -1 +1 @@
-#include <../../../../include/asm-generic/bitops/fls.h>
+#include "../../../../include/asm-generic/bitops/fls.h"
diff --git a/tools/include/asm-generic/bitops/fls64.h b/tools/include/asm-generic/bitops/fls64.h
index 980b1f63c..35bee0071 100644
--- a/tools/include/asm-generic/bitops/fls64.h
+++ b/tools/include/asm-generic/bitops/fls64.h
@@ -1 +1 @@
-#include <../../../../include/asm-generic/bitops/fls64.h>
+#include "../../../../include/asm-generic/bitops/fls64.h"
diff --git a/tools/include/linux/hashtable.h b/tools/include/linux/hashtable.h
new file mode 100644
index 000000000..c65cc0aa2
--- /dev/null
+++ b/tools/include/linux/hashtable.h
@@ -0,0 +1,152 @@
+/*
+ * Statically sized hash table implementation
+ * (C) 2012  Sasha Levin <levinsasha928@gmail.com>
+ */
+
+#ifndef _LINUX_HASHTABLE_H
+#define _LINUX_HASHTABLE_H
+
+#include <linux/list.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/hash.h>
+#include <linux/log2.h>
+
+#ifndef ARRAY_SIZE
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
+
+#define DEFINE_HASHTABLE(name, bits)						\
+	struct hlist_head name[1 << (bits)] =					\
+			{ [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT }
+
+#define DECLARE_HASHTABLE(name, bits)                                   	\
+	struct hlist_head name[1 << (bits)]
+
+#define HASH_SIZE(name) (ARRAY_SIZE(name))
+#define HASH_BITS(name) ilog2(HASH_SIZE(name))
+
+/* Use hash_32 when possible to allow for fast 32bit hashing in 64bit kernels. */
+#define hash_min(val, bits)							\
+	(sizeof(val) <= 4 ? hash_32(val, bits) : hash_long(val, bits))
+
+static inline void __hash_init(struct hlist_head *ht, unsigned int sz)
+{
+	unsigned int i;
+
+	for (i = 0; i < sz; i++)
+		INIT_HLIST_HEAD(&ht[i]);
+}
+
+/**
+ * hash_init - initialize a hash table
+ * @hashtable: hashtable to be initialized
+ *
+ * Calculates the size of the hashtable from the given parameter, otherwise
+ * same as hash_init_size.
+ *
+ * This has to be a macro since HASH_BITS() will not work on pointers since
+ * it calculates the size during preprocessing.
+ */
+#define hash_init(hashtable) __hash_init(hashtable, HASH_SIZE(hashtable))
+
+/**
+ * hash_add - add an object to a hashtable
+ * @hashtable: hashtable to add to
+ * @node: the &struct hlist_node of the object to be added
+ * @key: the key of the object to be added
+ */
+#define hash_add(hashtable, node, key)						\
+	hlist_add_head(node, &hashtable[hash_min(key, HASH_BITS(hashtable))])
+
+/**
+ * hash_hashed - check whether an object is in any hashtable
+ * @node: the &struct hlist_node of the object to be checked
+ */
+static inline bool hash_hashed(struct hlist_node *node)
+{
+	return !hlist_unhashed(node);
+}
+
+static inline bool __hash_empty(struct hlist_head *ht, unsigned int sz)
+{
+	unsigned int i;
+
+	for (i = 0; i < sz; i++)
+		if (!hlist_empty(&ht[i]))
+			return false;
+
+	return true;
+}
+
+/**
+ * hash_empty - check whether a hashtable is empty
+ * @hashtable: hashtable to check
+ *
+ * This has to be a macro since HASH_BITS() will not work on pointers since
+ * it calculates the size during preprocessing.
+ */
+#define hash_empty(hashtable) __hash_empty(hashtable, HASH_SIZE(hashtable))
+
+/**
+ * hash_del - remove an object from a hashtable
+ * @node: &struct hlist_node of the object to remove
+ */
+static inline void hash_del(struct hlist_node *node)
+{
+	hlist_del_init(node);
+}
+
+/**
+ * hash_for_each - iterate over a hashtable
+ * @name: hashtable to iterate
+ * @bkt: integer to use as bucket loop cursor
+ * @obj: the type * to use as a loop cursor for each entry
+ * @member: the name of the hlist_node within the struct
+ */
+#define hash_for_each(name, bkt, obj, member)				\
+	for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\
+			(bkt)++)\
+		hlist_for_each_entry(obj, &name[bkt], member)
+
+/**
+ * hash_for_each_safe - iterate over a hashtable safe against removal of
+ * hash entry
+ * @name: hashtable to iterate
+ * @bkt: integer to use as bucket loop cursor
+ * @tmp: a &struct used for temporary storage
+ * @obj: the type * to use as a loop cursor for each entry
+ * @member: the name of the hlist_node within the struct
+ */
+#define hash_for_each_safe(name, bkt, tmp, obj, member)			\
+	for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\
+			(bkt)++)\
+		hlist_for_each_entry_safe(obj, tmp, &name[bkt], member)
+
+/**
+ * hash_for_each_possible - iterate over all possible objects hashing to the
+ * same bucket
+ * @name: hashtable to iterate
+ * @obj: the type * to use as a loop cursor for each entry
+ * @member: the name of the hlist_node within the struct
+ * @key: the key of the objects to iterate over
+ */
+#define hash_for_each_possible(name, obj, member, key)			\
+	hlist_for_each_entry(obj, &name[hash_min(key, HASH_BITS(name))], member)
+
+/**
+ * hash_for_each_possible_safe - iterate over all possible objects hashing to the
+ * same bucket safe against removals
+ * @name: hashtable to iterate
+ * @obj: the type * to use as a loop cursor for each entry
+ * @tmp: a &struct used for temporary storage
+ * @member: the name of the hlist_node within the struct
+ * @key: the key of the objects to iterate over
+ */
+#define hash_for_each_possible_safe(name, obj, tmp, member, key)	\
+	hlist_for_each_entry_safe(obj, tmp,\
+		&name[hash_min(key, HASH_BITS(name))], member)
+
+
+#endif
diff --git a/tools/include/linux/stringify.h b/tools/include/linux/stringify.h
new file mode 100644
index 000000000..841cec8ed
--- /dev/null
+++ b/tools/include/linux/stringify.h
@@ -0,0 +1,12 @@
+#ifndef __LINUX_STRINGIFY_H
+#define __LINUX_STRINGIFY_H
+
+/* Indirect stringification.  Doing two levels allows the parameter to be a
+ * macro itself.  For example, compile with -DFOO=bar, __stringify(FOO)
+ * converts to "bar".
+ */
+
+#define __stringify_1(x...)	#x
+#define __stringify(x...)	__stringify_1(x)
+
+#endif	/* !__LINUX_STRINGIFY_H */
diff --git a/tools/lib/api/Build b/tools/lib/api/Build
index e8b8a23b9..954c644f7 100644
--- a/tools/lib/api/Build
+++ b/tools/lib/api/Build
@@ -1,3 +1,4 @@
 libapi-y += fd/
 libapi-y += fs/
 libapi-y += cpu.o
+libapi-y += debug.o
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index d85904dc9..316f308a6 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -1,5 +1,5 @@
 include ../../scripts/Makefile.include
-include ../../perf/config/utilities.mak		# QUIET_CLEAN
+include ../../scripts/utilities.mak		# QUIET_CLEAN
 
 ifeq ($(srctree),)
 srctree := $(patsubst %/,%,$(dir $(shell pwd)))
@@ -18,6 +18,7 @@ LIBFILE = $(OUTPUT)libapi.a
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
 CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
 CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
+CFLAGS += -I$(srctree)/tools/lib/api
 
 RM = rm -f
 
diff --git a/tools/lib/api/debug-internal.h b/tools/lib/api/debug-internal.h
new file mode 100644
index 000000000..188f7880e
--- /dev/null
+++ b/tools/lib/api/debug-internal.h
@@ -0,0 +1,20 @@
+#ifndef __API_DEBUG_INTERNAL_H__
+#define __API_DEBUG_INTERNAL_H__
+
+#include "debug.h"
+
+#define __pr(func, fmt, ...)	\
+do {				\
+	if ((func))		\
+		(func)("libapi: " fmt, ##__VA_ARGS__); \
+} while (0)
+
+extern libapi_print_fn_t __pr_warning;
+extern libapi_print_fn_t __pr_info;
+extern libapi_print_fn_t __pr_debug;
+
+#define pr_warning(fmt, ...)	__pr(__pr_warning, fmt, ##__VA_ARGS__)
+#define pr_info(fmt, ...)	__pr(__pr_info, fmt, ##__VA_ARGS__)
+#define pr_debug(fmt, ...)	__pr(__pr_debug, fmt, ##__VA_ARGS__)
+
+#endif /* __API_DEBUG_INTERNAL_H__ */
diff --git a/tools/lib/api/debug.c b/tools/lib/api/debug.c
new file mode 100644
index 000000000..5fa5cf500
--- /dev/null
+++ b/tools/lib/api/debug.c
@@ -0,0 +1,28 @@
+#include <stdio.h>
+#include <stdarg.h>
+#include "debug.h"
+#include "debug-internal.h"
+
+static int __base_pr(const char *format, ...)
+{
+	va_list args;
+	int err;
+
+	va_start(args, format);
+	err = vfprintf(stderr, format, args);
+	va_end(args);
+	return err;
+}
+
+libapi_print_fn_t __pr_warning = __base_pr;
+libapi_print_fn_t __pr_info    = __base_pr;
+libapi_print_fn_t __pr_debug;
+
+void libapi_set_print(libapi_print_fn_t warn,
+		      libapi_print_fn_t info,
+		      libapi_print_fn_t debug)
+{
+	__pr_warning = warn;
+	__pr_info    = info;
+	__pr_debug   = debug;
+}
diff --git a/tools/lib/api/debug.h b/tools/lib/api/debug.h
new file mode 100644
index 000000000..a0872f68f
--- /dev/null
+++ b/tools/lib/api/debug.h
@@ -0,0 +1,10 @@
+#ifndef __API_DEBUG_H__
+#define __API_DEBUG_H__
+
+typedef int (*libapi_print_fn_t)(const char *, ...);
+
+void libapi_set_print(libapi_print_fn_t warn,
+		      libapi_print_fn_t info,
+		      libapi_print_fn_t debug);
+
+#endif /* __API_DEBUG_H__ */
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 459599d1b..ef78c22ff 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -13,6 +13,7 @@
 #include <sys/mount.h>
 
 #include "fs.h"
+#include "debug-internal.h"
 
 #define _STR(x) #x
 #define STR(x) _STR(x)
@@ -300,6 +301,56 @@ int filename__read_ull(const char *filename, unsigned long long *value)
 	return err;
 }
 
+#define STRERR_BUFSIZE  128     /* For the buffer size of strerror_r */
+
+int filename__read_str(const char *filename, char **buf, size_t *sizep)
+{
+	size_t size = 0, alloc_size = 0;
+	void *bf = NULL, *nbf;
+	int fd, n, err = 0;
+	char sbuf[STRERR_BUFSIZE];
+
+	fd = open(filename, O_RDONLY);
+	if (fd < 0)
+		return -errno;
+
+	do {
+		if (size == alloc_size) {
+			alloc_size += BUFSIZ;
+			nbf = realloc(bf, alloc_size);
+			if (!nbf) {
+				err = -ENOMEM;
+				break;
+			}
+
+			bf = nbf;
+		}
+
+		n = read(fd, bf + size, alloc_size - size);
+		if (n < 0) {
+			if (size) {
+				pr_warning("read failed %d: %s\n", errno,
+					 strerror_r(errno, sbuf, sizeof(sbuf)));
+				err = 0;
+			} else
+				err = -errno;
+
+			break;
+		}
+
+		size += n;
+	} while (n > 0);
+
+	if (!err) {
+		*sizep = size;
+		*buf   = bf;
+	} else
+		free(bf);
+
+	close(fd);
+	return err;
+}
+
 int sysfs__read_ull(const char *entry, unsigned long long *value)
 {
 	char path[PATH_MAX];
@@ -326,6 +377,19 @@ int sysfs__read_int(const char *entry, int *value)
 	return filename__read_int(path, value);
 }
 
+int sysfs__read_str(const char *entry, char **buf, size_t *sizep)
+{
+	char path[PATH_MAX];
+	const char *sysfs = sysfs__mountpoint();
+
+	if (!sysfs)
+		return -1;
+
+	snprintf(path, sizeof(path), "%s/%s", sysfs, entry);
+
+	return filename__read_str(path, buf, sizep);
+}
+
 int sysctl__read_int(const char *sysctl, int *value)
 {
 	char path[PATH_MAX];
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
index d024a7f68..9f6598098 100644
--- a/tools/lib/api/fs/fs.h
+++ b/tools/lib/api/fs/fs.h
@@ -2,6 +2,7 @@
 #define __API_FS__
 
 #include <stdbool.h>
+#include <unistd.h>
 
 /*
  * On most systems <limits.h> would have given us this, but  not on some systems
@@ -26,8 +27,10 @@ FS(tracefs)
 
 int filename__read_int(const char *filename, int *value);
 int filename__read_ull(const char *filename, unsigned long long *value);
+int filename__read_str(const char *filename, char **buf, size_t *sizep);
 
 int sysctl__read_int(const char *sysctl, int *value);
 int sysfs__read_int(const char *entry, int *value);
 int sysfs__read_ull(const char *entry, unsigned long long *value);
+int sysfs__read_str(const char *entry, char **buf, size_t *sizep);
 #endif /* __API_FS__ */
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 8334a5a9d..7e543c310 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -201,6 +201,7 @@ struct bpf_object {
 			Elf_Data *data;
 		} *reloc;
 		int nr_reloc;
+		int maps_shndx;
 	} efile;
 	/*
 	 * All loaded bpf_object is linked in a list, which is
@@ -350,6 +351,7 @@ static struct bpf_object *bpf_object__new(const char *path,
 	 */
 	obj->efile.obj_buf = obj_buf;
 	obj->efile.obj_buf_sz = obj_buf_sz;
+	obj->efile.maps_shndx = -1;
 
 	obj->loaded = false;
 
@@ -529,12 +531,12 @@ bpf_object__init_maps(struct bpf_object *obj, void *data,
 }
 
 static int
-bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx)
+bpf_object__init_maps_name(struct bpf_object *obj)
 {
 	int i;
 	Elf_Data *symbols = obj->efile.symbols;
 
-	if (!symbols || maps_shndx < 0)
+	if (!symbols || obj->efile.maps_shndx < 0)
 		return -EINVAL;
 
 	for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
@@ -544,7 +546,7 @@ bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx)
 
 		if (!gelf_getsym(symbols, i, &sym))
 			continue;
-		if (sym.st_shndx != maps_shndx)
+		if (sym.st_shndx != obj->efile.maps_shndx)
 			continue;
 
 		map_name = elf_strptr(obj->efile.elf,
@@ -572,7 +574,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 	Elf *elf = obj->efile.elf;
 	GElf_Ehdr *ep = &obj->efile.ehdr;
 	Elf_Scn *scn = NULL;
-	int idx = 0, err = 0, maps_shndx = -1;
+	int idx = 0, err = 0;
 
 	/* Elf is corrupted/truncated, avoid calling elf_strptr. */
 	if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) {
@@ -625,7 +627,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 		else if (strcmp(name, "maps") == 0) {
 			err = bpf_object__init_maps(obj, data->d_buf,
 						    data->d_size);
-			maps_shndx = idx;
+			obj->efile.maps_shndx = idx;
 		} else if (sh.sh_type == SHT_SYMTAB) {
 			if (obj->efile.symbols) {
 				pr_warning("bpf: multiple SYMTAB in %s\n",
@@ -674,8 +676,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 		pr_warning("Corrupted ELF file: index of strtab invalid\n");
 		return LIBBPF_ERRNO__FORMAT;
 	}
-	if (maps_shndx >= 0)
-		err = bpf_object__init_maps_name(obj, maps_shndx);
+	if (obj->efile.maps_shndx >= 0)
+		err = bpf_object__init_maps_name(obj);
 out:
 	return err;
 }
@@ -697,7 +699,8 @@ bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx)
 static int
 bpf_program__collect_reloc(struct bpf_program *prog,
 			   size_t nr_maps, GElf_Shdr *shdr,
-			   Elf_Data *data, Elf_Data *symbols)
+			   Elf_Data *data, Elf_Data *symbols,
+			   int maps_shndx)
 {
 	int i, nrels;
 
@@ -724,9 +727,6 @@ bpf_program__collect_reloc(struct bpf_program *prog,
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
-		insn_idx = rel.r_offset / sizeof(struct bpf_insn);
-		pr_debug("relocation: insn_idx=%u\n", insn_idx);
-
 		if (!gelf_getsym(symbols,
 				 GELF_R_SYM(rel.r_info),
 				 &sym)) {
@@ -735,6 +735,15 @@ bpf_program__collect_reloc(struct bpf_program *prog,
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
+		if (sym.st_shndx != maps_shndx) {
+			pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n",
+				   prog->section_name, sym.st_shndx);
+			return -LIBBPF_ERRNO__RELOC;
+		}
+
+		insn_idx = rel.r_offset / sizeof(struct bpf_insn);
+		pr_debug("relocation: insn_idx=%u\n", insn_idx);
+
 		if (insns[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) {
 			pr_warning("bpf: relocation: invalid relo for insns[%d].code 0x%x\n",
 				   insn_idx, insns[insn_idx].code);
@@ -863,7 +872,8 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 
 		err = bpf_program__collect_reloc(prog, nr_maps,
 						 shdr, data,
-						 obj->efile.symbols);
+						 obj->efile.symbols,
+						 obj->efile.maps_shndx);
 		if (err)
 			return err;
 	}
diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile
index 90d2baeb6..1d57af568 100644
--- a/tools/lib/lockdep/Makefile
+++ b/tools/lib/lockdep/Makefile
@@ -100,7 +100,7 @@ include $(srctree)/tools/build/Makefile.include
 
 do_compile_shared_library =			\
 	($(print_shared_lib_compile)		\
-	$(CC) --shared $^ -o $@ -lpthread -ldl -Wl,-soname='"$@"';$(shell ln -s $@ liblockdep.so))
+	$(CC) --shared $^ -o $@ -lpthread -ldl -Wl,-soname='"$@"';$(shell ln -sf $@ liblockdep.so))
 
 do_build_static_lib =				\
 	($(print_static_lib_build)		\
diff --git a/tools/lib/lockdep/common.c b/tools/lib/lockdep/common.c
index 9be663340..d1c89cc06 100644
--- a/tools/lib/lockdep/common.c
+++ b/tools/lib/lockdep/common.c
@@ -11,11 +11,6 @@ static __thread struct task_struct current_obj;
 bool debug_locks = true;
 bool debug_locks_silent;
 
-__attribute__((constructor)) static void liblockdep_init(void)
-{
-	lockdep_init();
-}
-
 __attribute__((destructor)) static void liblockdep_exit(void)
 {
 	debug_check_no_locks_held();
diff --git a/tools/lib/lockdep/include/liblockdep/common.h b/tools/lib/lockdep/include/liblockdep/common.h
index a60c14b96..6e66277ec 100644
--- a/tools/lib/lockdep/include/liblockdep/common.h
+++ b/tools/lib/lockdep/include/liblockdep/common.h
@@ -44,7 +44,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 void lock_release(struct lockdep_map *lock, int nested,
 			unsigned long ip);
 extern void debug_check_no_locks_freed(const void *from, unsigned long len);
-extern void lockdep_init(void);
 
 #define STATIC_LOCKDEP_MAP_INIT(_name, _key) \
 	{ .name = (_name), .key = (void *)(_key), }
diff --git a/tools/lib/lockdep/lockdep.c b/tools/lib/lockdep/lockdep.c
index f42b7e9aa..a0a2e3a26 100644
--- a/tools/lib/lockdep/lockdep.c
+++ b/tools/lib/lockdep/lockdep.c
@@ -1,2 +1,8 @@
 #include <linux/lockdep.h>
+
+/* Trivial API wrappers, we don't (yet) have RCU in user-space: */
+#define hlist_for_each_entry_rcu	hlist_for_each_entry
+#define hlist_add_head_rcu		hlist_add_head
+#define hlist_del_rcu			hlist_del
+
 #include "../../../kernel/locking/lockdep.c"
diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c
index 21cdf869a..528448475 100644
--- a/tools/lib/lockdep/preload.c
+++ b/tools/lib/lockdep/preload.c
@@ -439,7 +439,5 @@ __attribute__((constructor)) static void init_preload(void)
 	ll_pthread_rwlock_unlock = dlsym(RTLD_NEXT, "pthread_rwlock_unlock");
 #endif
 
-	lockdep_init();
-
 	__init_state = done;
 }
diff --git a/tools/lib/lockdep/run_tests.sh b/tools/lib/lockdep/run_tests.sh
index 5334ad9d3..1069d9624 100755
--- a/tools/lib/lockdep/run_tests.sh
+++ b/tools/lib/lockdep/run_tests.sh
@@ -3,7 +3,7 @@
 make &> /dev/null
 
 for i in `ls tests/*.c`; do
-	testname=$(basename -s .c "$i")
+	testname=$(basename "$i" .c)
 	gcc -o tests/$testname -pthread -lpthread $i liblockdep.a -Iinclude -D__USE_LIBLOCKDEP &> /dev/null
 	echo -ne "$testname... "
 	if [ $(timeout 1 ./tests/$testname | wc -l) -gt 0 ]; then
@@ -11,11 +11,13 @@ for i in `ls tests/*.c`; do
 	else
 		echo "FAILED!"
 	fi
-	rm tests/$testname
+	if [ -f "tests/$testname" ]; then
+		rm tests/$testname
+	fi
 done
 
 for i in `ls tests/*.c`; do
-	testname=$(basename -s .c "$i")
+	testname=$(basename "$i" .c)
 	gcc -o tests/$testname -pthread -lpthread -Iinclude $i &> /dev/null
 	echo -ne "(PRELOAD) $testname... "
 	if [ $(timeout 1 ./lockdep ./tests/$testname | wc -l) -gt 0 ]; then
@@ -23,5 +25,7 @@ for i in `ls tests/*.c`; do
 	else
 		echo "FAILED!"
 	fi
-	rm tests/$testname
+	if [ -f "tests/$testname" ]; then
+		rm tests/$testname
+	fi
 done
diff --git a/tools/lib/lockdep/tests/AA.c b/tools/lib/lockdep/tests/AA.c
index 0f782ff40..18211a5f3 100644
--- a/tools/lib/lockdep/tests/AA.c
+++ b/tools/lib/lockdep/tests/AA.c
@@ -1,13 +1,13 @@
 #include <liblockdep/mutex.h>
 
-void main(void)
+int main(void)
 {
-	pthread_mutex_t a, b;
+	pthread_mutex_t a;
 
 	pthread_mutex_init(&a, NULL);
-	pthread_mutex_init(&b, NULL);
 
 	pthread_mutex_lock(&a);
-	pthread_mutex_lock(&b);
 	pthread_mutex_lock(&a);
+
+	return 0;
 }
diff --git a/tools/lib/lockdep/tests/ABA.c b/tools/lib/lockdep/tests/ABA.c
new file mode 100644
index 000000000..0f782ff40
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABA.c
@@ -0,0 +1,13 @@
+#include <liblockdep/mutex.h>
+
+void main(void)
+{
+	pthread_mutex_t a, b;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+
+	pthread_mutex_lock(&a);
+	pthread_mutex_lock(&b);
+	pthread_mutex_lock(&a);
+}
diff --git a/tools/lib/lockdep/tests/ABBA_2threads.c b/tools/lib/lockdep/tests/ABBA_2threads.c
new file mode 100644
index 000000000..cd807d736
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABBA_2threads.c
@@ -0,0 +1,46 @@
+#include <stdio.h>
+#include <pthread.h>
+
+pthread_mutex_t a = PTHREAD_MUTEX_INITIALIZER;
+pthread_mutex_t b = PTHREAD_MUTEX_INITIALIZER;
+pthread_barrier_t bar;
+
+void *ba_lock(void *arg)
+{
+	int ret, i;
+
+	pthread_mutex_lock(&b);
+
+	if (pthread_barrier_wait(&bar) == PTHREAD_BARRIER_SERIAL_THREAD)
+		pthread_barrier_destroy(&bar);
+
+	pthread_mutex_lock(&a);
+
+	pthread_mutex_unlock(&a);
+	pthread_mutex_unlock(&b);
+}
+
+int main(void)
+{
+	pthread_t t;
+
+	pthread_barrier_init(&bar, NULL, 2);
+
+	if (pthread_create(&t, NULL, ba_lock, NULL)) {
+		fprintf(stderr, "pthread_create() failed\n");
+		return 1;
+	}
+	pthread_mutex_lock(&a);
+
+	if (pthread_barrier_wait(&bar) == PTHREAD_BARRIER_SERIAL_THREAD)
+		pthread_barrier_destroy(&bar);
+
+	pthread_mutex_lock(&b);
+
+	pthread_mutex_unlock(&b);
+	pthread_mutex_unlock(&a);
+
+	pthread_join(t, NULL);
+
+	return 0;
+}
diff --git a/tools/lib/lockdep/uinclude/linux/compiler.h b/tools/lib/lockdep/uinclude/linux/compiler.h
index 6386dc318..fd3e56a83 100644
--- a/tools/lib/lockdep/uinclude/linux/compiler.h
+++ b/tools/lib/lockdep/uinclude/linux/compiler.h
@@ -3,6 +3,7 @@
 
 #define __used		__attribute__((__unused__))
 #define unlikely
+#define READ_ONCE(x) (x)
 #define WRITE_ONCE(x, val) x=(val)
 #define RCU_INIT_POINTER(p, v) p=(v)
 
diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile
index 629cf8c14..a8103700c 100644
--- a/tools/lib/subcmd/Makefile
+++ b/tools/lib/subcmd/Makefile
@@ -1,5 +1,5 @@
 include ../../scripts/Makefile.include
-include ../../perf/config/utilities.mak		# QUIET_CLEAN
+include ../../scripts/utilities.mak		# QUIET_CLEAN
 
 ifeq ($(srctree),)
 srctree := $(patsubst %/,%,$(dir $(shell pwd)))
@@ -8,8 +8,10 @@ srctree := $(patsubst %/,%,$(dir $(srctree)))
 #$(info Determined 'srctree' to be $(srctree))
 endif
 
-CC = $(CROSS_COMPILE)gcc
-AR = $(CROSS_COMPILE)ar
+CC ?= $(CROSS_COMPILE)gcc
+LD ?= $(CROSS_COMPILE)ld
+AR ?= $(CROSS_COMPILE)ar
+
 RM = rm -f
 
 MAKEFLAGS += --no-print-directory
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index c3bd294a6..a8b6357d1 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -1951,6 +1951,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 		   strcmp(token, "*") == 0 ||
 		   strcmp(token, "^") == 0 ||
 		   strcmp(token, "/") == 0 ||
+		   strcmp(token, "%") == 0 ||
 		   strcmp(token, "<") == 0 ||
 		   strcmp(token, ">") == 0 ||
 		   strcmp(token, "<=") == 0 ||
@@ -2397,6 +2398,12 @@ static int arg_num_eval(struct print_arg *arg, long long *val)
 				break;
 			*val = left + right;
 			break;
+		case '~':
+			ret = arg_num_eval(arg->op.right, &right);
+			if (!ret)
+				break;
+			*val = ~right;
+			break;
 		default:
 			do_warning("unknown op '%s'", arg->op.op);
 			ret = 0;
@@ -2634,6 +2641,7 @@ process_hex(struct event_format *event, struct print_arg *arg, char **tok)
 
 free_field:
 	free_arg(arg->hex.field);
+	arg->hex.field = NULL;
 out:
 	*tok = NULL;
 	return EVENT_ERROR;
@@ -2658,8 +2666,10 @@ process_int_array(struct event_format *event, struct print_arg *arg, char **tok)
 
 free_size:
 	free_arg(arg->int_array.count);
+	arg->int_array.count = NULL;
 free_field:
 	free_arg(arg->int_array.field);
+	arg->int_array.field = NULL;
 out:
 	*tok = NULL;
 	return EVENT_ERROR;
@@ -3689,6 +3699,9 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 		case '/':
 			val = left / right;
 			break;
+		case '%':
+			val = left % right;
+			break;
 		case '*':
 			val = left * right;
 			break;
@@ -4971,7 +4984,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 						break;
 					}
 				}
-				if (pevent->long_size == 8 && ls &&
+				if (pevent->long_size == 8 && ls == 1 &&
 				    sizeof(long) != 8) {
 					char *p;
 
@@ -5335,41 +5348,45 @@ static bool is_timestamp_in_us(char *trace_clock, bool use_trace_clock)
 	return false;
 }
 
-void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
-			struct pevent_record *record, bool use_trace_clock)
+/**
+ * pevent_find_event_by_record - return the event from a given record
+ * @pevent: a handle to the pevent
+ * @record: The record to get the event from
+ *
+ * Returns the associated event for a given record, or NULL if non is
+ * is found.
+ */
+struct event_format *
+pevent_find_event_by_record(struct pevent *pevent, struct pevent_record *record)
 {
-	static const char *spaces = "                    "; /* 20 spaces */
-	struct event_format *event;
-	unsigned long secs;
-	unsigned long usecs;
-	unsigned long nsecs;
-	const char *comm;
-	void *data = record->data;
 	int type;
-	int pid;
-	int len;
-	int p;
-	bool use_usec_format;
-
-	use_usec_format = is_timestamp_in_us(pevent->trace_clock,
-							use_trace_clock);
-	if (use_usec_format) {
-		secs = record->ts / NSECS_PER_SEC;
-		nsecs = record->ts - secs * NSECS_PER_SEC;
-	}
 
 	if (record->size < 0) {
 		do_warning("ug! negative record size %d", record->size);
-		return;
+		return NULL;
 	}
 
-	type = trace_parse_common_type(pevent, data);
+	type = trace_parse_common_type(pevent, record->data);
 
-	event = pevent_find_event(pevent, type);
-	if (!event) {
-		do_warning("ug! no event found for type %d", type);
-		return;
-	}
+	return pevent_find_event(pevent, type);
+}
+
+/**
+ * pevent_print_event_task - Write the event task comm, pid and CPU
+ * @pevent: a handle to the pevent
+ * @s: the trace_seq to write to
+ * @event: the handle to the record's event
+ * @record: The record to get the event from
+ *
+ * Writes the tasks comm, pid and CPU to @s.
+ */
+void pevent_print_event_task(struct pevent *pevent, struct trace_seq *s,
+			     struct event_format *event,
+			     struct pevent_record *record)
+{
+	void *data = record->data;
+	const char *comm;
+	int pid;
 
 	pid = parse_common_pid(pevent, data);
 	comm = find_cmdline(pevent, pid);
@@ -5377,9 +5394,41 @@ void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
 	if (pevent->latency_format) {
 		trace_seq_printf(s, "%8.8s-%-5d %3d",
 		       comm, pid, record->cpu);
-		pevent_data_lat_fmt(pevent, s, record);
 	} else
 		trace_seq_printf(s, "%16s-%-5d [%03d]", comm, pid, record->cpu);
+}
+
+/**
+ * pevent_print_event_time - Write the event timestamp
+ * @pevent: a handle to the pevent
+ * @s: the trace_seq to write to
+ * @event: the handle to the record's event
+ * @record: The record to get the event from
+ * @use_trace_clock: Set to parse according to the @pevent->trace_clock
+ *
+ * Writes the timestamp of the record into @s.
+ */
+void pevent_print_event_time(struct pevent *pevent, struct trace_seq *s,
+			     struct event_format *event,
+			     struct pevent_record *record,
+			     bool use_trace_clock)
+{
+	unsigned long secs;
+	unsigned long usecs;
+	unsigned long nsecs;
+	int p;
+	bool use_usec_format;
+
+	use_usec_format = is_timestamp_in_us(pevent->trace_clock,
+							use_trace_clock);
+	if (use_usec_format) {
+		secs = record->ts / NSECS_PER_SEC;
+		nsecs = record->ts - secs * NSECS_PER_SEC;
+	}
+
+	if (pevent->latency_format) {
+		pevent_data_lat_fmt(pevent, s, record);
+	}
 
 	if (use_usec_format) {
 		if (pevent->flags & PEVENT_NSEC_OUTPUT) {
@@ -5387,14 +5436,36 @@ void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
 			p = 9;
 		} else {
 			usecs = (nsecs + 500) / NSECS_PER_USEC;
+			/* To avoid usecs larger than 1 sec */
+			if (usecs >= 1000000) {
+				usecs -= 1000000;
+				secs++;
+			}
 			p = 6;
 		}
 
-		trace_seq_printf(s, " %5lu.%0*lu: %s: ",
-					secs, p, usecs, event->name);
+		trace_seq_printf(s, " %5lu.%0*lu:", secs, p, usecs);
 	} else
-		trace_seq_printf(s, " %12llu: %s: ",
-					record->ts, event->name);
+		trace_seq_printf(s, " %12llu:", record->ts);
+}
+
+/**
+ * pevent_print_event_data - Write the event data section
+ * @pevent: a handle to the pevent
+ * @s: the trace_seq to write to
+ * @event: the handle to the record's event
+ * @record: The record to get the event from
+ *
+ * Writes the parsing of the record's data to @s.
+ */
+void pevent_print_event_data(struct pevent *pevent, struct trace_seq *s,
+			     struct event_format *event,
+			     struct pevent_record *record)
+{
+	static const char *spaces = "                    "; /* 20 spaces */
+	int len;
+
+	trace_seq_printf(s, " %s: ", event->name);
 
 	/* Space out the event names evenly. */
 	len = strlen(event->name);
@@ -5404,6 +5475,23 @@ void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
 	pevent_event_info(s, event, record);
 }
 
+void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
+			struct pevent_record *record, bool use_trace_clock)
+{
+	struct event_format *event;
+
+	event = pevent_find_event_by_record(pevent, record);
+	if (!event) {
+		do_warning("ug! no event found for type %d",
+			   trace_parse_common_type(pevent, record->data));
+		return;
+	}
+
+	pevent_print_event_task(pevent, s, event, record);
+	pevent_print_event_time(pevent, s, event, record, use_trace_clock);
+	pevent_print_event_data(pevent, s, event, record);
+}
+
 static int events_id_cmp(const void *a, const void *b)
 {
 	struct event_format * const * ea = a;
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 706d9bc24..9ffde377e 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -628,6 +628,16 @@ int pevent_register_print_string(struct pevent *pevent, const char *fmt,
 				 unsigned long long addr);
 int pevent_pid_is_registered(struct pevent *pevent, int pid);
 
+void pevent_print_event_task(struct pevent *pevent, struct trace_seq *s,
+			     struct event_format *event,
+			     struct pevent_record *record);
+void pevent_print_event_time(struct pevent *pevent, struct trace_seq *s,
+			     struct event_format *event,
+			     struct pevent_record *record,
+			     bool use_trace_clock);
+void pevent_print_event_data(struct pevent *pevent, struct trace_seq *s,
+			     struct event_format *event,
+			     struct pevent_record *record);
 void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
 			struct pevent_record *record, bool use_trace_clock);
 
@@ -694,6 +704,9 @@ struct event_format *pevent_find_event(struct pevent *pevent, int id);
 struct event_format *
 pevent_find_event_by_name(struct pevent *pevent, const char *sys, const char *name);
 
+struct event_format *
+pevent_find_event_by_record(struct pevent *pevent, struct pevent_record *record);
+
 void pevent_data_lat_fmt(struct pevent *pevent,
 			 struct trace_seq *s, struct pevent_record *record);
 int pevent_data_type(struct pevent *pevent, struct pevent_record *rec);
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 0144b3d1b..88cccea3c 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -1164,11 +1164,11 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 		current_op = current_exp;
 
 	ret = collapse_tree(current_op, parg, error_str);
+	/* collapse_tree() may free current_op, and updates parg accordingly */
+	current_op = NULL;
 	if (ret < 0)
 		goto fail;
 
-	*parg = current_op;
-
 	free(token);
 	return 0;
 
diff --git a/tools/net/bpf_dbg.c b/tools/net/bpf_dbg.c
index 9a287bec6..4f254bcc4 100644
--- a/tools/net/bpf_dbg.c
+++ b/tools/net/bpf_dbg.c
@@ -129,16 +129,16 @@ struct bpf_regs {
 };
 
 static struct sock_filter bpf_image[BPF_MAXINSNS + 1];
-static unsigned int bpf_prog_len = 0;
+static unsigned int bpf_prog_len;
 
 static int bpf_breakpoints[64];
 static struct bpf_regs bpf_regs[BPF_MAXINSNS + 1];
 static struct bpf_regs bpf_curr;
-static unsigned int bpf_regs_len = 0;
+static unsigned int bpf_regs_len;
 
 static int pcap_fd = -1;
-static unsigned int pcap_packet = 0;
-static size_t pcap_map_size = 0;
+static unsigned int pcap_packet;
+static size_t pcap_map_size;
 static char *pcap_ptr_va_start, *pcap_ptr_va_curr;
 
 static const char * const op_table[] = {
@@ -1172,7 +1172,7 @@ static int cmd_breakpoint(char *subcmd)
 
 static int cmd_run(char *num)
 {
-	static uint32_t pass = 0, fail = 0;
+	static uint32_t pass, fail;
 	bool has_limit = true;
 	int pkts = 0, i = 0;
 
diff --git a/tools/net/bpf_exp.l b/tools/net/bpf_exp.l
index 7cc72a336..bd83149e7 100644
--- a/tools/net/bpf_exp.l
+++ b/tools/net/bpf_exp.l
@@ -23,6 +23,9 @@
 #include <stdio.h>
 #include <stdint.h>
 #include <stdlib.h>
+#include <string.h>
+
+#include <linux/filter.h>
 
 #include "bpf_exp.yacc.h"
 
@@ -79,22 +82,71 @@ extern void yyerror(const char *str);
 "txa"		{ return OP_TXA; }
 
 "#"?("len")	{ return K_PKT_LEN; }
-"#"?("proto")	{ return K_PROTO; }
-"#"?("type")	{ return K_TYPE; }
-"#"?("poff")	{ return K_POFF; }
-"#"?("ifidx")	{ return K_IFIDX; }
-"#"?("nla")	{ return K_NLATTR; }
-"#"?("nlan")	{ return K_NLATTR_NEST; }
-"#"?("mark")	{ return K_MARK; }
-"#"?("queue")	{ return K_QUEUE; }
-"#"?("hatype")	{ return K_HATYPE; }
-"#"?("rxhash")	{ return K_RXHASH; }
-"#"?("cpu")	{ return K_CPU; }
-"#"?("vlan_tci")	{ return K_VLAN_TCI; }
-"#"?("vlan_pr")		{ return K_VLAN_AVAIL; }
-"#"?("vlan_avail")	{ return K_VLAN_AVAIL; }
-"#"?("vlan_tpid")	{ return K_VLAN_TPID; }
-"#"?("rand")	{ return K_RAND; }
+
+"#"?("proto")	{
+		yylval.number = SKF_AD_PROTOCOL;
+		return extension;
+	}
+"#"?("type")	{
+		yylval.number = SKF_AD_PKTTYPE;
+		return extension;
+	}
+"#"?("poff")	{
+		yylval.number = SKF_AD_PAY_OFFSET;
+		return extension;
+	}
+"#"?("ifidx")	{
+		yylval.number = SKF_AD_IFINDEX;
+		return extension;
+	}
+"#"?("nla")	{
+		yylval.number = SKF_AD_NLATTR;
+		return extension;
+	}
+"#"?("nlan")	{
+		yylval.number = SKF_AD_NLATTR_NEST;
+		return extension;
+	}
+"#"?("mark")	{
+		yylval.number = SKF_AD_MARK;
+		return extension;
+	}
+"#"?("queue")	{
+		yylval.number = SKF_AD_QUEUE;
+		return extension;
+	}
+"#"?("hatype")	{
+		yylval.number = SKF_AD_HATYPE;
+		return extension;
+	}
+"#"?("rxhash")	{
+		yylval.number = SKF_AD_RXHASH;
+		return extension;
+	}
+"#"?("cpu")	{
+		yylval.number = SKF_AD_CPU;
+		return extension;
+	}
+"#"?("vlan_tci") {
+		yylval.number = SKF_AD_VLAN_TAG;
+		return extension;
+	}
+"#"?("vlan_pr")	{
+		yylval.number = SKF_AD_VLAN_TAG_PRESENT;
+		return extension;
+	}
+"#"?("vlan_avail") {
+		yylval.number = SKF_AD_VLAN_TAG_PRESENT;
+		return extension;
+	}
+"#"?("vlan_tpid") {
+		yylval.number = SKF_AD_VLAN_TPID;
+		return extension;
+	}
+"#"?("rand")	{
+		yylval.number = SKF_AD_RANDOM;
+		return extension;
+	}
 
 ":"		{ return ':'; }
 ","		{ return ','; }
diff --git a/tools/net/bpf_exp.y b/tools/net/bpf_exp.y
index e24eea1b0..56ba1de50 100644
--- a/tools/net/bpf_exp.y
+++ b/tools/net/bpf_exp.y
@@ -35,6 +35,7 @@
 enum jmp_type { JTL, JFL, JKL };
 
 extern FILE *yyin;
+extern int yylineno;
 extern int yylex(void);
 extern void yyerror(const char *str);
 
@@ -55,14 +56,14 @@ static void bpf_set_jmp_label(char *label, enum jmp_type type);
 %token OP_RET OP_TAX OP_TXA OP_LDXB OP_MOD OP_NEG OP_JNEQ OP_JLT OP_JLE OP_LDI
 %token OP_LDXI
 
-%token K_PKT_LEN K_PROTO K_TYPE K_NLATTR K_NLATTR_NEST K_MARK K_QUEUE K_HATYPE
-%token K_RXHASH K_CPU K_IFIDX K_VLAN_TCI K_VLAN_AVAIL K_VLAN_TPID K_POFF K_RAND
+%token K_PKT_LEN
 
 %token ':' ',' '[' ']' '(' ')' 'x' 'a' '+' 'M' '*' '&' '#' '%'
 
-%token number label
+%token extension number label
 
 %type <label> label
+%type <number> extension
 %type <number> number
 
 %%
@@ -125,51 +126,9 @@ ldb
 		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_IND, 0, 0, $6); }
 	| OP_LDB '[' number ']' {
 		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0, $3); }
-	| OP_LDB K_PROTO {
+	| OP_LDB extension {
 		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_PROTOCOL); }
-	| OP_LDB K_TYPE {
-		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_PKTTYPE); }
-	| OP_LDB K_IFIDX {
-		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_IFINDEX); }
-	| OP_LDB K_NLATTR {
-		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_NLATTR); }
-	| OP_LDB K_NLATTR_NEST {
-		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_NLATTR_NEST); }
-	| OP_LDB K_MARK {
-		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_MARK); }
-	| OP_LDB K_QUEUE {
-		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_QUEUE); }
-	| OP_LDB K_HATYPE {
-		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_HATYPE); }
-	| OP_LDB K_RXHASH {
-		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_RXHASH); }
-	| OP_LDB K_CPU {
-		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_CPU); }
-	| OP_LDB K_VLAN_TCI {
-		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_VLAN_TAG); }
-	| OP_LDB K_VLAN_AVAIL {
-		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT); }
-	| OP_LDB K_POFF {
-		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_PAY_OFFSET); }
-	| OP_LDB K_RAND {
-		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_RANDOM); }
-	| OP_LDB K_VLAN_TPID {
-		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_VLAN_TPID); }
+				   SKF_AD_OFF + $2); }
 	;
 
 ldh
@@ -179,51 +138,9 @@ ldh
 		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_IND, 0, 0, $6); }
 	| OP_LDH '[' number ']' {
 		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0, $3); }
-	| OP_LDH K_PROTO {
-		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_PROTOCOL); }
-	| OP_LDH K_TYPE {
-		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_PKTTYPE); }
-	| OP_LDH K_IFIDX {
-		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_IFINDEX); }
-	| OP_LDH K_NLATTR {
-		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_NLATTR); }
-	| OP_LDH K_NLATTR_NEST {
-		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_NLATTR_NEST); }
-	| OP_LDH K_MARK {
-		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_MARK); }
-	| OP_LDH K_QUEUE {
-		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_QUEUE); }
-	| OP_LDH K_HATYPE {
+	| OP_LDH extension {
 		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_HATYPE); }
-	| OP_LDH K_RXHASH {
-		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_RXHASH); }
-	| OP_LDH K_CPU {
-		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_CPU); }
-	| OP_LDH K_VLAN_TCI {
-		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_VLAN_TAG); }
-	| OP_LDH K_VLAN_AVAIL {
-		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT); }
-	| OP_LDH K_POFF {
-		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_PAY_OFFSET); }
-	| OP_LDH K_RAND {
-		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_RANDOM); }
-	| OP_LDH K_VLAN_TPID {
-		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_VLAN_TPID); }
+				   SKF_AD_OFF + $2); }
 	;
 
 ldi
@@ -238,51 +155,9 @@ ld
 		bpf_set_curr_instr(BPF_LD | BPF_IMM, 0, 0, $3); }
 	| OP_LD K_PKT_LEN {
 		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_LEN, 0, 0, 0); }
-	| OP_LD K_PROTO {
-		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_PROTOCOL); }
-	| OP_LD K_TYPE {
-		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_PKTTYPE); }
-	| OP_LD K_IFIDX {
-		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_IFINDEX); }
-	| OP_LD K_NLATTR {
-		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_NLATTR); }
-	| OP_LD K_NLATTR_NEST {
-		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_NLATTR_NEST); }
-	| OP_LD K_MARK {
-		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_MARK); }
-	| OP_LD K_QUEUE {
-		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_QUEUE); }
-	| OP_LD K_HATYPE {
-		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_HATYPE); }
-	| OP_LD K_RXHASH {
-		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_RXHASH); }
-	| OP_LD K_CPU {
-		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_CPU); }
-	| OP_LD K_VLAN_TCI {
-		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_VLAN_TAG); }
-	| OP_LD K_VLAN_AVAIL {
-		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT); }
-	| OP_LD K_POFF {
-		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_PAY_OFFSET); }
-	| OP_LD K_RAND {
-		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_RANDOM); }
-	| OP_LD K_VLAN_TPID {
+	| OP_LD extension {
 		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
-				   SKF_AD_OFF + SKF_AD_VLAN_TPID); }
+				   SKF_AD_OFF + $2); }
 	| OP_LD 'M' '[' number ']' {
 		bpf_set_curr_instr(BPF_LD | BPF_MEM, 0, 0, $4); }
 	| OP_LD '[' 'x' '+' number ']' {
@@ -776,5 +651,6 @@ void bpf_asm_compile(FILE *fp, bool cstyle)
 
 void yyerror(const char *str)
 {
+	fprintf(stderr, "error: %s at line %d\n", str, yylineno);
 	exit(1);
 }
diff --git a/tools/net/bpf_jit_disasm.c b/tools/net/bpf_jit_disasm.c
index 5b3241340..544b05a53 100644
--- a/tools/net/bpf_jit_disasm.c
+++ b/tools/net/bpf_jit_disasm.c
@@ -98,6 +98,9 @@ static char *get_klog_buff(unsigned int *klen)
 	char *buff;
 
 	len = klogctl(CMD_ACTION_SIZE_BUFFER, NULL, 0);
+	if (len < 0)
+		return NULL;
+
 	buff = malloc(len);
 	if (!buff)
 		return NULL;
diff --git a/tools/objtool/.gitignore b/tools/objtool/.gitignore
new file mode 100644
index 000000000..a0b3128bb
--- /dev/null
+++ b/tools/objtool/.gitignore
@@ -0,0 +1,2 @@
+arch/x86/insn/inat-tables.c
+objtool
diff --git a/tools/objtool/Build b/tools/objtool/Build
new file mode 100644
index 000000000..0e89258a3
--- /dev/null
+++ b/tools/objtool/Build
@@ -0,0 +1,13 @@
+objtool-y += arch/$(ARCH)/
+objtool-y += builtin-check.o
+objtool-y += elf.o
+objtool-y += special.o
+objtool-y += objtool.o
+
+objtool-y += libstring.o
+
+CFLAGS += -I$(srctree)/tools/lib
+
+$(OUTPUT)libstring.o: ../lib/string.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)
diff --git a/tools/objtool/Documentation/stack-validation.txt b/tools/objtool/Documentation/stack-validation.txt
new file mode 100644
index 000000000..55a60d331
--- /dev/null
+++ b/tools/objtool/Documentation/stack-validation.txt
@@ -0,0 +1,362 @@
+Compile-time stack metadata validation
+======================================
+
+
+Overview
+--------
+
+The kernel CONFIG_STACK_VALIDATION option enables a host tool named
+objtool which runs at compile time.  It has a "check" subcommand which
+analyzes every .o file and ensures the validity of its stack metadata.
+It enforces a set of rules on asm code and C inline assembly code so
+that stack traces can be reliable.
+
+Currently it only checks frame pointer usage, but there are plans to add
+CFI validation for C files and CFI generation for asm files.
+
+For each function, it recursively follows all possible code paths and
+validates the correct frame pointer state at each instruction.
+
+It also follows code paths involving special sections, like
+.altinstructions, __jump_table, and __ex_table, which can add
+alternative execution paths to a given instruction (or set of
+instructions).  Similarly, it knows how to follow switch statements, for
+which gcc sometimes uses jump tables.
+
+
+Why do we need stack metadata validation?
+-----------------------------------------
+
+Here are some of the benefits of validating stack metadata:
+
+a) More reliable stack traces for frame pointer enabled kernels
+
+   Frame pointers are used for debugging purposes.  They allow runtime
+   code and debug tools to be able to walk the stack to determine the
+   chain of function call sites that led to the currently executing
+   code.
+
+   For some architectures, frame pointers are enabled by
+   CONFIG_FRAME_POINTER.  For some other architectures they may be
+   required by the ABI (sometimes referred to as "backchain pointers").
+
+   For C code, gcc automatically generates instructions for setting up
+   frame pointers when the -fno-omit-frame-pointer option is used.
+
+   But for asm code, the frame setup instructions have to be written by
+   hand, which most people don't do.  So the end result is that
+   CONFIG_FRAME_POINTER is honored for C code but not for most asm code.
+
+   For stack traces based on frame pointers to be reliable, all
+   functions which call other functions must first create a stack frame
+   and update the frame pointer.  If a first function doesn't properly
+   create a stack frame before calling a second function, the *caller*
+   of the first function will be skipped on the stack trace.
+
+   For example, consider the following example backtrace with frame
+   pointers enabled:
+
+     [<ffffffff81812584>] dump_stack+0x4b/0x63
+     [<ffffffff812d6dc2>] cmdline_proc_show+0x12/0x30
+     [<ffffffff8127f568>] seq_read+0x108/0x3e0
+     [<ffffffff812cce62>] proc_reg_read+0x42/0x70
+     [<ffffffff81256197>] __vfs_read+0x37/0x100
+     [<ffffffff81256b16>] vfs_read+0x86/0x130
+     [<ffffffff81257898>] SyS_read+0x58/0xd0
+     [<ffffffff8181c1f2>] entry_SYSCALL_64_fastpath+0x12/0x76
+
+   It correctly shows that the caller of cmdline_proc_show() is
+   seq_read().
+
+   If we remove the frame pointer logic from cmdline_proc_show() by
+   replacing the frame pointer related instructions with nops, here's
+   what it looks like instead:
+
+     [<ffffffff81812584>] dump_stack+0x4b/0x63
+     [<ffffffff812d6dc2>] cmdline_proc_show+0x12/0x30
+     [<ffffffff812cce62>] proc_reg_read+0x42/0x70
+     [<ffffffff81256197>] __vfs_read+0x37/0x100
+     [<ffffffff81256b16>] vfs_read+0x86/0x130
+     [<ffffffff81257898>] SyS_read+0x58/0xd0
+     [<ffffffff8181c1f2>] entry_SYSCALL_64_fastpath+0x12/0x76
+
+   Notice that cmdline_proc_show()'s caller, seq_read(), has been
+   skipped.  Instead the stack trace seems to show that
+   cmdline_proc_show() was called by proc_reg_read().
+
+   The benefit of objtool here is that because it ensures that *all*
+   functions honor CONFIG_FRAME_POINTER, no functions will ever[*] be
+   skipped on a stack trace.
+
+   [*] unless an interrupt or exception has occurred at the very
+       beginning of a function before the stack frame has been created,
+       or at the very end of the function after the stack frame has been
+       destroyed.  This is an inherent limitation of frame pointers.
+
+b) 100% reliable stack traces for DWARF enabled kernels
+
+   (NOTE: This is not yet implemented)
+
+   As an alternative to frame pointers, DWARF Call Frame Information
+   (CFI) metadata can be used to walk the stack.  Unlike frame pointers,
+   CFI metadata is out of band.  So it doesn't affect runtime
+   performance and it can be reliable even when interrupts or exceptions
+   are involved.
+
+   For C code, gcc automatically generates DWARF CFI metadata.  But for
+   asm code, generating CFI is a tedious manual approach which requires
+   manually placed .cfi assembler macros to be scattered throughout the
+   code.  It's clumsy and very easy to get wrong, and it makes the real
+   code harder to read.
+
+   Stacktool will improve this situation in several ways.  For code
+   which already has CFI annotations, it will validate them.  For code
+   which doesn't have CFI annotations, it will generate them.  So an
+   architecture can opt to strip out all the manual .cfi annotations
+   from their asm code and have objtool generate them instead.
+
+   We might also add a runtime stack validation debug option where we
+   periodically walk the stack from schedule() and/or an NMI to ensure
+   that the stack metadata is sane and that we reach the bottom of the
+   stack.
+
+   So the benefit of objtool here will be that external tooling should
+   always show perfect stack traces.  And the same will be true for
+   kernel warning/oops traces if the architecture has a runtime DWARF
+   unwinder.
+
+c) Higher live patching compatibility rate
+
+   (NOTE: This is not yet implemented)
+
+   Currently with CONFIG_LIVEPATCH there's a basic live patching
+   framework which is safe for roughly 85-90% of "security" fixes.  But
+   patches can't have complex features like function dependency or
+   prototype changes, or data structure changes.
+
+   There's a strong need to support patches which have the more complex
+   features so that the patch compatibility rate for security fixes can
+   eventually approach something resembling 100%.  To achieve that, a
+   "consistency model" is needed, which allows tasks to be safely
+   transitioned from an unpatched state to a patched state.
+
+   One of the key requirements of the currently proposed livepatch
+   consistency model [*] is that it needs to walk the stack of each
+   sleeping task to determine if it can be transitioned to the patched
+   state.  If objtool can ensure that stack traces are reliable, this
+   consistency model can be used and the live patching compatibility
+   rate can be improved significantly.
+
+   [*] https://lkml.kernel.org/r/cover.1423499826.git.jpoimboe@redhat.com
+
+
+Rules
+-----
+
+To achieve the validation, objtool enforces the following rules:
+
+1. Each callable function must be annotated as such with the ELF
+   function type.  In asm code, this is typically done using the
+   ENTRY/ENDPROC macros.  If objtool finds a return instruction
+   outside of a function, it flags an error since that usually indicates
+   callable code which should be annotated accordingly.
+
+   This rule is needed so that objtool can properly identify each
+   callable function in order to analyze its stack metadata.
+
+2. Conversely, each section of code which is *not* callable should *not*
+   be annotated as an ELF function.  The ENDPROC macro shouldn't be used
+   in this case.
+
+   This rule is needed so that objtool can ignore non-callable code.
+   Such code doesn't have to follow any of the other rules.
+
+3. Each callable function which calls another function must have the
+   correct frame pointer logic, if required by CONFIG_FRAME_POINTER or
+   the architecture's back chain rules.  This can by done in asm code
+   with the FRAME_BEGIN/FRAME_END macros.
+
+   This rule ensures that frame pointer based stack traces will work as
+   designed.  If function A doesn't create a stack frame before calling
+   function B, the _caller_ of function A will be skipped on the stack
+   trace.
+
+4. Dynamic jumps and jumps to undefined symbols are only allowed if:
+
+   a) the jump is part of a switch statement; or
+
+   b) the jump matches sibling call semantics and the frame pointer has
+      the same value it had on function entry.
+
+   This rule is needed so that objtool can reliably analyze all of a
+   function's code paths.  If a function jumps to code in another file,
+   and it's not a sibling call, objtool has no way to follow the jump
+   because it only analyzes a single file at a time.
+
+5. A callable function may not execute kernel entry/exit instructions.
+   The only code which needs such instructions is kernel entry code,
+   which shouldn't be be in callable functions anyway.
+
+   This rule is just a sanity check to ensure that callable functions
+   return normally.
+
+
+Errors in .S files
+------------------
+
+If you're getting an error in a compiled .S file which you don't
+understand, first make sure that the affected code follows the above
+rules.
+
+Here are some examples of common warnings reported by objtool, what
+they mean, and suggestions for how to fix them.
+
+
+1. asm_file.o: warning: objtool: func()+0x128: call without frame pointer save/setup
+
+   The func() function made a function call without first saving and/or
+   updating the frame pointer.
+
+   If func() is indeed a callable function, add proper frame pointer
+   logic using the FRAME_BEGIN and FRAME_END macros.  Otherwise, remove
+   its ELF function annotation by changing ENDPROC to END.
+
+   If you're getting this error in a .c file, see the "Errors in .c
+   files" section.
+
+
+2. asm_file.o: warning: objtool: .text+0x53: return instruction outside of a callable function
+
+   A return instruction was detected, but objtool couldn't find a way
+   for a callable function to reach the instruction.
+
+   If the return instruction is inside (or reachable from) a callable
+   function, the function needs to be annotated with the ENTRY/ENDPROC
+   macros.
+
+   If you _really_ need a return instruction outside of a function, and
+   are 100% sure that it won't affect stack traces, you can tell
+   objtool to ignore it.  See the "Adding exceptions" section below.
+
+
+3. asm_file.o: warning: objtool: func()+0x9: function has unreachable instruction
+
+   The instruction lives inside of a callable function, but there's no
+   possible control flow path from the beginning of the function to the
+   instruction.
+
+   If the instruction is actually needed, and it's actually in a
+   callable function, ensure that its function is properly annotated
+   with ENTRY/ENDPROC.
+
+   If it's not actually in a callable function (e.g. kernel entry code),
+   change ENDPROC to END.
+
+
+4. asm_file.o: warning: objtool: func(): can't find starting instruction
+   or
+   asm_file.o: warning: objtool: func()+0x11dd: can't decode instruction
+
+   Did you put data in a text section?  If so, that can confuse
+   objtool's instruction decoder.  Move the data to a more appropriate
+   section like .data or .rodata.
+
+
+5. asm_file.o: warning: objtool: func()+0x6: kernel entry/exit from callable instruction
+
+   This is a kernel entry/exit instruction like sysenter or sysret.
+   Such instructions aren't allowed in a callable function, and are most
+   likely part of the kernel entry code.
+
+   If the instruction isn't actually in a callable function, change
+   ENDPROC to END.
+
+
+6. asm_file.o: warning: objtool: func()+0x26: sibling call from callable instruction with changed frame pointer
+
+   This is a dynamic jump or a jump to an undefined symbol.  Stacktool
+   assumed it's a sibling call and detected that the frame pointer
+   wasn't first restored to its original state.
+
+   If it's not really a sibling call, you may need to move the
+   destination code to the local file.
+
+   If the instruction is not actually in a callable function (e.g.
+   kernel entry code), change ENDPROC to END.
+
+
+7. asm_file: warning: objtool: func()+0x5c: frame pointer state mismatch
+
+   The instruction's frame pointer state is inconsistent, depending on
+   which execution path was taken to reach the instruction.
+
+   Make sure the function pushes and sets up the frame pointer (for
+   x86_64, this means rbp) at the beginning of the function and pops it
+   at the end of the function.  Also make sure that no other code in the
+   function touches the frame pointer.
+
+
+Errors in .c files
+------------------
+
+1. c_file.o: warning: objtool: funcA() falls through to next function funcB()
+
+   This means that funcA() doesn't end with a return instruction or an
+   unconditional jump, and that objtool has determined that the function
+   can fall through into the next function.  There could be different
+   reasons for this:
+
+   1) funcA()'s last instruction is a call to a "noreturn" function like
+      panic().  In this case the noreturn function needs to be added to
+      objtool's hard-coded global_noreturns array.  Feel free to bug the
+      objtool maintainer, or you can submit a patch.
+
+   2) funcA() uses the unreachable() annotation in a section of code
+      that is actually reachable.
+
+   3) If funcA() calls an inline function, the object code for funcA()
+      might be corrupt due to a gcc bug.  For more details, see:
+      https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70646
+
+2. If you're getting any other objtool error in a compiled .c file, it
+   may be because the file uses an asm() statement which has a "call"
+   instruction.  An asm() statement with a call instruction must declare
+   the use of the stack pointer in its output operand.  For example, on
+   x86_64:
+
+     register void *__sp asm("rsp");
+     asm volatile("call func" : "+r" (__sp));
+
+   Otherwise the stack frame may not get created before the call.
+
+3. Another possible cause for errors in C code is if the Makefile removes
+   -fno-omit-frame-pointer or adds -fomit-frame-pointer to the gcc options.
+
+Also see the above section for .S file errors for more information what
+the individual error messages mean.
+
+If the error doesn't seem to make sense, it could be a bug in objtool.
+Feel free to ask the objtool maintainer for help.
+
+
+Adding exceptions
+-----------------
+
+If you _really_ need objtool to ignore something, and are 100% sure
+that it won't affect kernel stack traces, you can tell objtool to
+ignore it:
+
+- To skip validation of a function, use the STACK_FRAME_NON_STANDARD
+  macro.
+
+- To skip validation of a file, add
+
+    OBJECT_FILES_NON_STANDARD_filename.o := n
+
+  to the Makefile.
+
+- To skip validation of a directory, add
+
+    OBJECT_FILES_NON_STANDARD := y
+
+  to the Makefile.
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
new file mode 100644
index 000000000..f094f3c4e
--- /dev/null
+++ b/tools/objtool/Makefile
@@ -0,0 +1,67 @@
+include ../scripts/Makefile.include
+
+ifndef ($(ARCH))
+ARCH ?= $(shell uname -m)
+ifeq ($(ARCH),x86_64)
+ARCH := x86
+endif
+endif
+
+# always use the host compiler
+CC = gcc
+LD = ld
+AR = ar
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+endif
+
+SUBCMD_SRCDIR		= $(srctree)/tools/lib/subcmd/
+LIBSUBCMD_OUTPUT	= $(if $(OUTPUT),$(OUTPUT),$(PWD)/)
+LIBSUBCMD		= $(LIBSUBCMD_OUTPUT)libsubcmd.a
+
+OBJTOOL    := $(OUTPUT)objtool
+OBJTOOL_IN := $(OBJTOOL)-in.o
+
+all: $(OBJTOOL)
+
+INCLUDES := -I$(srctree)/tools/include
+CFLAGS   += -Wall -Werror $(EXTRA_WARNINGS) -fomit-frame-pointer -O2 -g $(INCLUDES)
+LDFLAGS  += -lelf $(LIBSUBCMD)
+
+# Allow old libelf to be used:
+elfshdr := $(shell echo '\#include <libelf.h>' | $(CC) $(CFLAGS) -x c -E - | grep elf_getshdr)
+CFLAGS += $(if $(elfshdr),,-DLIBELF_USE_DEPRECATED)
+
+AWK = awk
+export srctree OUTPUT CFLAGS ARCH AWK
+include $(srctree)/tools/build/Makefile.include
+
+$(OBJTOOL_IN): fixdep FORCE
+	@$(MAKE) $(build)=objtool
+
+$(OBJTOOL): $(LIBSUBCMD) $(OBJTOOL_IN)
+	@(test -d ../../kernel -a -d ../../tools -a -d ../objtool && (( \
+	diff -I'^#include' arch/x86/insn/insn.c ../../arch/x86/lib/insn.c >/dev/null && \
+	diff -I'^#include' arch/x86/insn/inat.c ../../arch/x86/lib/inat.c >/dev/null && \
+	diff arch/x86/insn/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null && \
+	diff arch/x86/insn/gen-insn-attr-x86.awk ../../arch/x86/tools/gen-insn-attr-x86.awk >/dev/null && \
+	diff -I'^#include' arch/x86/insn/insn.h ../../arch/x86/include/asm/insn.h >/dev/null && \
+	diff -I'^#include' arch/x86/insn/inat.h ../../arch/x86/include/asm/inat.h >/dev/null && \
+	diff -I'^#include' arch/x86/insn/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) \
+	|| echo "Warning: objtool: x86 instruction decoder differs from kernel" >&2 )) || true
+	$(QUIET_LINK)$(CC) $(OBJTOOL_IN) $(LDFLAGS) -o $@
+
+
+$(LIBSUBCMD): fixdep FORCE
+	$(Q)$(MAKE) -C $(SUBCMD_SRCDIR) OUTPUT=$(LIBSUBCMD_OUTPUT)
+
+clean:
+	$(call QUIET_CLEAN, objtool) $(RM) $(OBJTOOL)
+	$(Q)find $(OUTPUT) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
+	$(Q)$(RM) $(OUTPUT)arch/x86/insn/inat-tables.c $(OUTPUT)fixdep
+
+FORCE:
+
+.PHONY: clean FORCE
diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h
new file mode 100644
index 000000000..f7350fced
--- /dev/null
+++ b/tools/objtool/arch.h
@@ -0,0 +1,44 @@
+/*
+ * Copyright (C) 2015 Josh Poimboeuf <jpoimboe@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _ARCH_H
+#define _ARCH_H
+
+#include <stdbool.h>
+#include "elf.h"
+
+#define INSN_FP_SAVE		1
+#define INSN_FP_SETUP		2
+#define INSN_FP_RESTORE		3
+#define INSN_JUMP_CONDITIONAL	4
+#define INSN_JUMP_UNCONDITIONAL	5
+#define INSN_JUMP_DYNAMIC	6
+#define INSN_CALL		7
+#define INSN_CALL_DYNAMIC	8
+#define INSN_RETURN		9
+#define INSN_CONTEXT_SWITCH	10
+#define INSN_BUG		11
+#define INSN_NOP		12
+#define INSN_OTHER		13
+#define INSN_LAST		INSN_OTHER
+
+int arch_decode_instruction(struct elf *elf, struct section *sec,
+			    unsigned long offset, unsigned int maxlen,
+			    unsigned int *len, unsigned char *type,
+			    unsigned long *displacement);
+
+#endif /* _ARCH_H */
diff --git a/tools/objtool/arch/x86/Build b/tools/objtool/arch/x86/Build
new file mode 100644
index 000000000..debbdb0b5
--- /dev/null
+++ b/tools/objtool/arch/x86/Build
@@ -0,0 +1,12 @@
+objtool-y += decode.o
+
+inat_tables_script = arch/x86/insn/gen-insn-attr-x86.awk
+inat_tables_maps = arch/x86/insn/x86-opcode-map.txt
+
+$(OUTPUT)arch/x86/insn/inat-tables.c: $(inat_tables_script) $(inat_tables_maps)
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,gen)$(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@
+
+$(OUTPUT)arch/x86/decode.o: $(OUTPUT)arch/x86/insn/inat-tables.c
+
+CFLAGS_decode.o += -I$(OUTPUT)arch/x86/insn
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
new file mode 100644
index 000000000..c0c0b265e
--- /dev/null
+++ b/tools/objtool/arch/x86/decode.c
@@ -0,0 +1,172 @@
+/*
+ * Copyright (C) 2015 Josh Poimboeuf <jpoimboe@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+
+#define unlikely(cond) (cond)
+#include "insn/insn.h"
+#include "insn/inat.c"
+#include "insn/insn.c"
+
+#include "../../elf.h"
+#include "../../arch.h"
+#include "../../warn.h"
+
+static int is_x86_64(struct elf *elf)
+{
+	switch (elf->ehdr.e_machine) {
+	case EM_X86_64:
+		return 1;
+	case EM_386:
+		return 0;
+	default:
+		WARN("unexpected ELF machine type %d", elf->ehdr.e_machine);
+		return -1;
+	}
+}
+
+int arch_decode_instruction(struct elf *elf, struct section *sec,
+			    unsigned long offset, unsigned int maxlen,
+			    unsigned int *len, unsigned char *type,
+			    unsigned long *immediate)
+{
+	struct insn insn;
+	int x86_64;
+	unsigned char op1, op2, ext;
+
+	x86_64 = is_x86_64(elf);
+	if (x86_64 == -1)
+		return -1;
+
+	insn_init(&insn, (void *)(sec->data + offset), maxlen, x86_64);
+	insn_get_length(&insn);
+	insn_get_opcode(&insn);
+	insn_get_modrm(&insn);
+	insn_get_immediate(&insn);
+
+	if (!insn_complete(&insn)) {
+		WARN_FUNC("can't decode instruction", sec, offset);
+		return -1;
+	}
+
+	*len = insn.length;
+	*type = INSN_OTHER;
+
+	if (insn.vex_prefix.nbytes)
+		return 0;
+
+	op1 = insn.opcode.bytes[0];
+	op2 = insn.opcode.bytes[1];
+
+	switch (op1) {
+	case 0x55:
+		if (!insn.rex_prefix.nbytes)
+			/* push rbp */
+			*type = INSN_FP_SAVE;
+		break;
+
+	case 0x5d:
+		if (!insn.rex_prefix.nbytes)
+			/* pop rbp */
+			*type = INSN_FP_RESTORE;
+		break;
+
+	case 0x70 ... 0x7f:
+		*type = INSN_JUMP_CONDITIONAL;
+		break;
+
+	case 0x89:
+		if (insn.rex_prefix.nbytes == 1 &&
+		    insn.rex_prefix.bytes[0] == 0x48 &&
+		    insn.modrm.nbytes && insn.modrm.bytes[0] == 0xe5)
+			/* mov rsp, rbp */
+			*type = INSN_FP_SETUP;
+		break;
+
+	case 0x90:
+		*type = INSN_NOP;
+		break;
+
+	case 0x0f:
+		if (op2 >= 0x80 && op2 <= 0x8f)
+			*type = INSN_JUMP_CONDITIONAL;
+		else if (op2 == 0x05 || op2 == 0x07 || op2 == 0x34 ||
+			 op2 == 0x35)
+			/* sysenter, sysret */
+			*type = INSN_CONTEXT_SWITCH;
+		else if (op2 == 0x0b || op2 == 0xb9)
+			/* ud2 */
+			*type = INSN_BUG;
+		else if (op2 == 0x0d || op2 == 0x1f)
+			/* nopl/nopw */
+			*type = INSN_NOP;
+		else if (op2 == 0x01 && insn.modrm.nbytes &&
+			 (insn.modrm.bytes[0] == 0xc2 ||
+			  insn.modrm.bytes[0] == 0xd8))
+			/* vmlaunch, vmrun */
+			*type = INSN_CONTEXT_SWITCH;
+
+		break;
+
+	case 0xc9: /* leave */
+		*type = INSN_FP_RESTORE;
+		break;
+
+	case 0xe3: /* jecxz/jrcxz */
+		*type = INSN_JUMP_CONDITIONAL;
+		break;
+
+	case 0xe9:
+	case 0xeb:
+		*type = INSN_JUMP_UNCONDITIONAL;
+		break;
+
+	case 0xc2:
+	case 0xc3:
+		*type = INSN_RETURN;
+		break;
+
+	case 0xc5: /* iret */
+	case 0xca: /* retf */
+	case 0xcb: /* retf */
+		*type = INSN_CONTEXT_SWITCH;
+		break;
+
+	case 0xe8:
+		*type = INSN_CALL;
+		break;
+
+	case 0xff:
+		ext = X86_MODRM_REG(insn.modrm.bytes[0]);
+		if (ext == 2 || ext == 3)
+			*type = INSN_CALL_DYNAMIC;
+		else if (ext == 4)
+			*type = INSN_JUMP_DYNAMIC;
+		else if (ext == 5) /*jmpf */
+			*type = INSN_CONTEXT_SWITCH;
+
+		break;
+
+	default:
+		break;
+	}
+
+	*immediate = insn.immediate.nbytes ? insn.immediate.value : 0;
+
+	return 0;
+}
diff --git a/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk b/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk
new file mode 100644
index 000000000..093a89202
--- /dev/null
+++ b/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk
@@ -0,0 +1,387 @@
+#!/bin/awk -f
+# gen-insn-attr-x86.awk: Instruction attribute table generator
+# Written by Masami Hiramatsu <mhiramat@redhat.com>
+#
+# Usage: awk -f gen-insn-attr-x86.awk x86-opcode-map.txt > inat-tables.c
+
+# Awk implementation sanity check
+function check_awk_implement() {
+	if (sprintf("%x", 0) != "0")
+		return "Your awk has a printf-format problem."
+	return ""
+}
+
+# Clear working vars
+function clear_vars() {
+	delete table
+	delete lptable2
+	delete lptable1
+	delete lptable3
+	eid = -1 # escape id
+	gid = -1 # group id
+	aid = -1 # AVX id
+	tname = ""
+}
+
+BEGIN {
+	# Implementation error checking
+	awkchecked = check_awk_implement()
+	if (awkchecked != "") {
+		print "Error: " awkchecked > "/dev/stderr"
+		print "Please try to use gawk." > "/dev/stderr"
+		exit 1
+	}
+
+	# Setup generating tables
+	print "/* x86 opcode map generated from x86-opcode-map.txt */"
+	print "/* Do not change this code. */\n"
+	ggid = 1
+	geid = 1
+	gaid = 0
+	delete etable
+	delete gtable
+	delete atable
+
+	opnd_expr = "^[A-Za-z/]"
+	ext_expr = "^\\("
+	sep_expr = "^\\|$"
+	group_expr = "^Grp[0-9A-Za-z]+"
+
+	imm_expr = "^[IJAOL][a-z]"
+	imm_flag["Ib"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
+	imm_flag["Jb"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
+	imm_flag["Iw"] = "INAT_MAKE_IMM(INAT_IMM_WORD)"
+	imm_flag["Id"] = "INAT_MAKE_IMM(INAT_IMM_DWORD)"
+	imm_flag["Iq"] = "INAT_MAKE_IMM(INAT_IMM_QWORD)"
+	imm_flag["Ap"] = "INAT_MAKE_IMM(INAT_IMM_PTR)"
+	imm_flag["Iz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)"
+	imm_flag["Jz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)"
+	imm_flag["Iv"] = "INAT_MAKE_IMM(INAT_IMM_VWORD)"
+	imm_flag["Ob"] = "INAT_MOFFSET"
+	imm_flag["Ov"] = "INAT_MOFFSET"
+	imm_flag["Lx"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
+
+	modrm_expr = "^([CDEGMNPQRSUVW/][a-z]+|NTA|T[012])"
+	force64_expr = "\\([df]64\\)"
+	rex_expr = "^REX(\\.[XRWB]+)*"
+	fpu_expr = "^ESC" # TODO
+
+	lprefix1_expr = "\\((66|!F3)\\)"
+	lprefix2_expr = "\\(F3\\)"
+	lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)"
+	lprefix_expr = "\\((66|F2|F3)\\)"
+	max_lprefix = 4
+
+	# All opcodes starting with lower-case 'v' or with (v1) superscript
+	# accepts VEX prefix
+	vexok_opcode_expr = "^v.*"
+	vexok_expr = "\\(v1\\)"
+	# All opcodes with (v) superscript supports *only* VEX prefix
+	vexonly_expr = "\\(v\\)"
+
+	prefix_expr = "\\(Prefix\\)"
+	prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
+	prefix_num["REPNE"] = "INAT_PFX_REPNE"
+	prefix_num["REP/REPE"] = "INAT_PFX_REPE"
+	prefix_num["XACQUIRE"] = "INAT_PFX_REPNE"
+	prefix_num["XRELEASE"] = "INAT_PFX_REPE"
+	prefix_num["LOCK"] = "INAT_PFX_LOCK"
+	prefix_num["SEG=CS"] = "INAT_PFX_CS"
+	prefix_num["SEG=DS"] = "INAT_PFX_DS"
+	prefix_num["SEG=ES"] = "INAT_PFX_ES"
+	prefix_num["SEG=FS"] = "INAT_PFX_FS"
+	prefix_num["SEG=GS"] = "INAT_PFX_GS"
+	prefix_num["SEG=SS"] = "INAT_PFX_SS"
+	prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
+	prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
+	prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
+
+	clear_vars()
+}
+
+function semantic_error(msg) {
+	print "Semantic error at " NR ": " msg > "/dev/stderr"
+	exit 1
+}
+
+function debug(msg) {
+	print "DEBUG: " msg
+}
+
+function array_size(arr,   i,c) {
+	c = 0
+	for (i in arr)
+		c++
+	return c
+}
+
+/^Table:/ {
+	print "/* " $0 " */"
+	if (tname != "")
+		semantic_error("Hit Table: before EndTable:.");
+}
+
+/^Referrer:/ {
+	if (NF != 1) {
+		# escape opcode table
+		ref = ""
+		for (i = 2; i <= NF; i++)
+			ref = ref $i
+		eid = escape[ref]
+		tname = sprintf("inat_escape_table_%d", eid)
+	}
+}
+
+/^AVXcode:/ {
+	if (NF != 1) {
+		# AVX/escape opcode table
+		aid = $2
+		if (gaid <= aid)
+			gaid = aid + 1
+		if (tname == "")	# AVX only opcode table
+			tname = sprintf("inat_avx_table_%d", $2)
+	}
+	if (aid == -1 && eid == -1)	# primary opcode table
+		tname = "inat_primary_table"
+}
+
+/^GrpTable:/ {
+	print "/* " $0 " */"
+	if (!($2 in group))
+		semantic_error("No group: " $2 )
+	gid = group[$2]
+	tname = "inat_group_table_" gid
+}
+
+function print_table(tbl,name,fmt,n)
+{
+	print "const insn_attr_t " name " = {"
+	for (i = 0; i < n; i++) {
+		id = sprintf(fmt, i)
+		if (tbl[id])
+			print "	[" id "] = " tbl[id] ","
+	}
+	print "};"
+}
+
+/^EndTable/ {
+	if (gid != -1) {
+		# print group tables
+		if (array_size(table) != 0) {
+			print_table(table, tname "[INAT_GROUP_TABLE_SIZE]",
+				    "0x%x", 8)
+			gtable[gid,0] = tname
+		}
+		if (array_size(lptable1) != 0) {
+			print_table(lptable1, tname "_1[INAT_GROUP_TABLE_SIZE]",
+				    "0x%x", 8)
+			gtable[gid,1] = tname "_1"
+		}
+		if (array_size(lptable2) != 0) {
+			print_table(lptable2, tname "_2[INAT_GROUP_TABLE_SIZE]",
+				    "0x%x", 8)
+			gtable[gid,2] = tname "_2"
+		}
+		if (array_size(lptable3) != 0) {
+			print_table(lptable3, tname "_3[INAT_GROUP_TABLE_SIZE]",
+				    "0x%x", 8)
+			gtable[gid,3] = tname "_3"
+		}
+	} else {
+		# print primary/escaped tables
+		if (array_size(table) != 0) {
+			print_table(table, tname "[INAT_OPCODE_TABLE_SIZE]",
+				    "0x%02x", 256)
+			etable[eid,0] = tname
+			if (aid >= 0)
+				atable[aid,0] = tname
+		}
+		if (array_size(lptable1) != 0) {
+			print_table(lptable1,tname "_1[INAT_OPCODE_TABLE_SIZE]",
+				    "0x%02x", 256)
+			etable[eid,1] = tname "_1"
+			if (aid >= 0)
+				atable[aid,1] = tname "_1"
+		}
+		if (array_size(lptable2) != 0) {
+			print_table(lptable2,tname "_2[INAT_OPCODE_TABLE_SIZE]",
+				    "0x%02x", 256)
+			etable[eid,2] = tname "_2"
+			if (aid >= 0)
+				atable[aid,2] = tname "_2"
+		}
+		if (array_size(lptable3) != 0) {
+			print_table(lptable3,tname "_3[INAT_OPCODE_TABLE_SIZE]",
+				    "0x%02x", 256)
+			etable[eid,3] = tname "_3"
+			if (aid >= 0)
+				atable[aid,3] = tname "_3"
+		}
+	}
+	print ""
+	clear_vars()
+}
+
+function add_flags(old,new) {
+	if (old && new)
+		return old " | " new
+	else if (old)
+		return old
+	else
+		return new
+}
+
+# convert operands to flags.
+function convert_operands(count,opnd,       i,j,imm,mod)
+{
+	imm = null
+	mod = null
+	for (j = 1; j <= count; j++) {
+		i = opnd[j]
+		if (match(i, imm_expr) == 1) {
+			if (!imm_flag[i])
+				semantic_error("Unknown imm opnd: " i)
+			if (imm) {
+				if (i != "Ib")
+					semantic_error("Second IMM error")
+				imm = add_flags(imm, "INAT_SCNDIMM")
+			} else
+				imm = imm_flag[i]
+		} else if (match(i, modrm_expr))
+			mod = "INAT_MODRM"
+	}
+	return add_flags(imm, mod)
+}
+
+/^[0-9a-f]+\:/ {
+	if (NR == 1)
+		next
+	# get index
+	idx = "0x" substr($1, 1, index($1,":") - 1)
+	if (idx in table)
+		semantic_error("Redefine " idx " in " tname)
+
+	# check if escaped opcode
+	if ("escape" == $2) {
+		if ($3 != "#")
+			semantic_error("No escaped name")
+		ref = ""
+		for (i = 4; i <= NF; i++)
+			ref = ref $i
+		if (ref in escape)
+			semantic_error("Redefine escape (" ref ")")
+		escape[ref] = geid
+		geid++
+		table[idx] = "INAT_MAKE_ESCAPE(" escape[ref] ")"
+		next
+	}
+
+	variant = null
+	# converts
+	i = 2
+	while (i <= NF) {
+		opcode = $(i++)
+		delete opnds
+		ext = null
+		flags = null
+		opnd = null
+		# parse one opcode
+		if (match($i, opnd_expr)) {
+			opnd = $i
+			count = split($(i++), opnds, ",")
+			flags = convert_operands(count, opnds)
+		}
+		if (match($i, ext_expr))
+			ext = $(i++)
+		if (match($i, sep_expr))
+			i++
+		else if (i < NF)
+			semantic_error($i " is not a separator")
+
+		# check if group opcode
+		if (match(opcode, group_expr)) {
+			if (!(opcode in group)) {
+				group[opcode] = ggid
+				ggid++
+			}
+			flags = add_flags(flags, "INAT_MAKE_GROUP(" group[opcode] ")")
+		}
+		# check force(or default) 64bit
+		if (match(ext, force64_expr))
+			flags = add_flags(flags, "INAT_FORCE64")
+
+		# check REX prefix
+		if (match(opcode, rex_expr))
+			flags = add_flags(flags, "INAT_MAKE_PREFIX(INAT_PFX_REX)")
+
+		# check coprocessor escape : TODO
+		if (match(opcode, fpu_expr))
+			flags = add_flags(flags, "INAT_MODRM")
+
+		# check VEX codes
+		if (match(ext, vexonly_expr))
+			flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
+		else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr))
+			flags = add_flags(flags, "INAT_VEXOK")
+
+		# check prefixes
+		if (match(ext, prefix_expr)) {
+			if (!prefix_num[opcode])
+				semantic_error("Unknown prefix: " opcode)
+			flags = add_flags(flags, "INAT_MAKE_PREFIX(" prefix_num[opcode] ")")
+		}
+		if (length(flags) == 0)
+			continue
+		# check if last prefix
+		if (match(ext, lprefix1_expr)) {
+			lptable1[idx] = add_flags(lptable1[idx],flags)
+			variant = "INAT_VARIANT"
+		}
+		if (match(ext, lprefix2_expr)) {
+			lptable2[idx] = add_flags(lptable2[idx],flags)
+			variant = "INAT_VARIANT"
+		}
+		if (match(ext, lprefix3_expr)) {
+			lptable3[idx] = add_flags(lptable3[idx],flags)
+			variant = "INAT_VARIANT"
+		}
+		if (!match(ext, lprefix_expr)){
+			table[idx] = add_flags(table[idx],flags)
+		}
+	}
+	if (variant)
+		table[idx] = add_flags(table[idx],variant)
+}
+
+END {
+	if (awkchecked != "")
+		exit 1
+	# print escape opcode map's array
+	print "/* Escape opcode map array */"
+	print "const insn_attr_t * const inat_escape_tables[INAT_ESC_MAX + 1]" \
+	      "[INAT_LSTPFX_MAX + 1] = {"
+	for (i = 0; i < geid; i++)
+		for (j = 0; j < max_lprefix; j++)
+			if (etable[i,j])
+				print "	["i"]["j"] = "etable[i,j]","
+	print "};\n"
+	# print group opcode map's array
+	print "/* Group opcode map array */"
+	print "const insn_attr_t * const inat_group_tables[INAT_GRP_MAX + 1]"\
+	      "[INAT_LSTPFX_MAX + 1] = {"
+	for (i = 0; i < ggid; i++)
+		for (j = 0; j < max_lprefix; j++)
+			if (gtable[i,j])
+				print "	["i"]["j"] = "gtable[i,j]","
+	print "};\n"
+	# print AVX opcode map's array
+	print "/* AVX opcode map array */"
+	print "const insn_attr_t * const inat_avx_tables[X86_VEX_M_MAX + 1]"\
+	      "[INAT_LSTPFX_MAX + 1] = {"
+	for (i = 0; i < gaid; i++)
+		for (j = 0; j < max_lprefix; j++)
+			if (atable[i,j])
+				print "	["i"]["j"] = "atable[i,j]","
+	print "};"
+}
+
diff --git a/tools/objtool/arch/x86/insn/inat.c b/tools/objtool/arch/x86/insn/inat.c
new file mode 100644
index 000000000..e4bf28e6f
--- /dev/null
+++ b/tools/objtool/arch/x86/insn/inat.c
@@ -0,0 +1,97 @@
+/*
+ * x86 instruction attribute tables
+ *
+ * Written by Masami Hiramatsu <mhiramat@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+#include "insn.h"
+
+/* Attribute tables are generated from opcode map */
+#include "inat-tables.c"
+
+/* Attribute search APIs */
+insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode)
+{
+	return inat_primary_table[opcode];
+}
+
+int inat_get_last_prefix_id(insn_byte_t last_pfx)
+{
+	insn_attr_t lpfx_attr;
+
+	lpfx_attr = inat_get_opcode_attribute(last_pfx);
+	return inat_last_prefix_id(lpfx_attr);
+}
+
+insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, int lpfx_id,
+				      insn_attr_t esc_attr)
+{
+	const insn_attr_t *table;
+	int n;
+
+	n = inat_escape_id(esc_attr);
+
+	table = inat_escape_tables[n][0];
+	if (!table)
+		return 0;
+	if (inat_has_variant(table[opcode]) && lpfx_id) {
+		table = inat_escape_tables[n][lpfx_id];
+		if (!table)
+			return 0;
+	}
+	return table[opcode];
+}
+
+insn_attr_t inat_get_group_attribute(insn_byte_t modrm, int lpfx_id,
+				     insn_attr_t grp_attr)
+{
+	const insn_attr_t *table;
+	int n;
+
+	n = inat_group_id(grp_attr);
+
+	table = inat_group_tables[n][0];
+	if (!table)
+		return inat_group_common_attribute(grp_attr);
+	if (inat_has_variant(table[X86_MODRM_REG(modrm)]) && lpfx_id) {
+		table = inat_group_tables[n][lpfx_id];
+		if (!table)
+			return inat_group_common_attribute(grp_attr);
+	}
+	return table[X86_MODRM_REG(modrm)] |
+	       inat_group_common_attribute(grp_attr);
+}
+
+insn_attr_t inat_get_avx_attribute(insn_byte_t opcode, insn_byte_t vex_m,
+				   insn_byte_t vex_p)
+{
+	const insn_attr_t *table;
+	if (vex_m > X86_VEX_M_MAX || vex_p > INAT_LSTPFX_MAX)
+		return 0;
+	/* At first, this checks the master table */
+	table = inat_avx_tables[vex_m][0];
+	if (!table)
+		return 0;
+	if (!inat_is_group(table[opcode]) && vex_p) {
+		/* If this is not a group, get attribute directly */
+		table = inat_avx_tables[vex_m][vex_p];
+		if (!table)
+			return 0;
+	}
+	return table[opcode];
+}
+
diff --git a/tools/objtool/arch/x86/insn/inat.h b/tools/objtool/arch/x86/insn/inat.h
new file mode 100644
index 000000000..611645e90
--- /dev/null
+++ b/tools/objtool/arch/x86/insn/inat.h
@@ -0,0 +1,221 @@
+#ifndef _ASM_X86_INAT_H
+#define _ASM_X86_INAT_H
+/*
+ * x86 instruction attributes
+ *
+ * Written by Masami Hiramatsu <mhiramat@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+#include "inat_types.h"
+
+/*
+ * Internal bits. Don't use bitmasks directly, because these bits are
+ * unstable. You should use checking functions.
+ */
+
+#define INAT_OPCODE_TABLE_SIZE 256
+#define INAT_GROUP_TABLE_SIZE 8
+
+/* Legacy last prefixes */
+#define INAT_PFX_OPNDSZ	1	/* 0x66 */ /* LPFX1 */
+#define INAT_PFX_REPE	2	/* 0xF3 */ /* LPFX2 */
+#define INAT_PFX_REPNE	3	/* 0xF2 */ /* LPFX3 */
+/* Other Legacy prefixes */
+#define INAT_PFX_LOCK	4	/* 0xF0 */
+#define INAT_PFX_CS	5	/* 0x2E */
+#define INAT_PFX_DS	6	/* 0x3E */
+#define INAT_PFX_ES	7	/* 0x26 */
+#define INAT_PFX_FS	8	/* 0x64 */
+#define INAT_PFX_GS	9	/* 0x65 */
+#define INAT_PFX_SS	10	/* 0x36 */
+#define INAT_PFX_ADDRSZ	11	/* 0x67 */
+/* x86-64 REX prefix */
+#define INAT_PFX_REX	12	/* 0x4X */
+/* AVX VEX prefixes */
+#define INAT_PFX_VEX2	13	/* 2-bytes VEX prefix */
+#define INAT_PFX_VEX3	14	/* 3-bytes VEX prefix */
+
+#define INAT_LSTPFX_MAX	3
+#define INAT_LGCPFX_MAX	11
+
+/* Immediate size */
+#define INAT_IMM_BYTE		1
+#define INAT_IMM_WORD		2
+#define INAT_IMM_DWORD		3
+#define INAT_IMM_QWORD		4
+#define INAT_IMM_PTR		5
+#define INAT_IMM_VWORD32	6
+#define INAT_IMM_VWORD		7
+
+/* Legacy prefix */
+#define INAT_PFX_OFFS	0
+#define INAT_PFX_BITS	4
+#define INAT_PFX_MAX    ((1 << INAT_PFX_BITS) - 1)
+#define INAT_PFX_MASK	(INAT_PFX_MAX << INAT_PFX_OFFS)
+/* Escape opcodes */
+#define INAT_ESC_OFFS	(INAT_PFX_OFFS + INAT_PFX_BITS)
+#define INAT_ESC_BITS	2
+#define INAT_ESC_MAX	((1 << INAT_ESC_BITS) - 1)
+#define INAT_ESC_MASK	(INAT_ESC_MAX << INAT_ESC_OFFS)
+/* Group opcodes (1-16) */
+#define INAT_GRP_OFFS	(INAT_ESC_OFFS + INAT_ESC_BITS)
+#define INAT_GRP_BITS	5
+#define INAT_GRP_MAX	((1 << INAT_GRP_BITS) - 1)
+#define INAT_GRP_MASK	(INAT_GRP_MAX << INAT_GRP_OFFS)
+/* Immediates */
+#define INAT_IMM_OFFS	(INAT_GRP_OFFS + INAT_GRP_BITS)
+#define INAT_IMM_BITS	3
+#define INAT_IMM_MASK	(((1 << INAT_IMM_BITS) - 1) << INAT_IMM_OFFS)
+/* Flags */
+#define INAT_FLAG_OFFS	(INAT_IMM_OFFS + INAT_IMM_BITS)
+#define INAT_MODRM	(1 << (INAT_FLAG_OFFS))
+#define INAT_FORCE64	(1 << (INAT_FLAG_OFFS + 1))
+#define INAT_SCNDIMM	(1 << (INAT_FLAG_OFFS + 2))
+#define INAT_MOFFSET	(1 << (INAT_FLAG_OFFS + 3))
+#define INAT_VARIANT	(1 << (INAT_FLAG_OFFS + 4))
+#define INAT_VEXOK	(1 << (INAT_FLAG_OFFS + 5))
+#define INAT_VEXONLY	(1 << (INAT_FLAG_OFFS + 6))
+/* Attribute making macros for attribute tables */
+#define INAT_MAKE_PREFIX(pfx)	(pfx << INAT_PFX_OFFS)
+#define INAT_MAKE_ESCAPE(esc)	(esc << INAT_ESC_OFFS)
+#define INAT_MAKE_GROUP(grp)	((grp << INAT_GRP_OFFS) | INAT_MODRM)
+#define INAT_MAKE_IMM(imm)	(imm << INAT_IMM_OFFS)
+
+/* Attribute search APIs */
+extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
+extern int inat_get_last_prefix_id(insn_byte_t last_pfx);
+extern insn_attr_t inat_get_escape_attribute(insn_byte_t opcode,
+					     int lpfx_id,
+					     insn_attr_t esc_attr);
+extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm,
+					    int lpfx_id,
+					    insn_attr_t esc_attr);
+extern insn_attr_t inat_get_avx_attribute(insn_byte_t opcode,
+					  insn_byte_t vex_m,
+					  insn_byte_t vex_pp);
+
+/* Attribute checking functions */
+static inline int inat_is_legacy_prefix(insn_attr_t attr)
+{
+	attr &= INAT_PFX_MASK;
+	return attr && attr <= INAT_LGCPFX_MAX;
+}
+
+static inline int inat_is_address_size_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_ADDRSZ;
+}
+
+static inline int inat_is_operand_size_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_OPNDSZ;
+}
+
+static inline int inat_is_rex_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_REX;
+}
+
+static inline int inat_last_prefix_id(insn_attr_t attr)
+{
+	if ((attr & INAT_PFX_MASK) > INAT_LSTPFX_MAX)
+		return 0;
+	else
+		return attr & INAT_PFX_MASK;
+}
+
+static inline int inat_is_vex_prefix(insn_attr_t attr)
+{
+	attr &= INAT_PFX_MASK;
+	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3;
+}
+
+static inline int inat_is_vex3_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_VEX3;
+}
+
+static inline int inat_is_escape(insn_attr_t attr)
+{
+	return attr & INAT_ESC_MASK;
+}
+
+static inline int inat_escape_id(insn_attr_t attr)
+{
+	return (attr & INAT_ESC_MASK) >> INAT_ESC_OFFS;
+}
+
+static inline int inat_is_group(insn_attr_t attr)
+{
+	return attr & INAT_GRP_MASK;
+}
+
+static inline int inat_group_id(insn_attr_t attr)
+{
+	return (attr & INAT_GRP_MASK) >> INAT_GRP_OFFS;
+}
+
+static inline int inat_group_common_attribute(insn_attr_t attr)
+{
+	return attr & ~INAT_GRP_MASK;
+}
+
+static inline int inat_has_immediate(insn_attr_t attr)
+{
+	return attr & INAT_IMM_MASK;
+}
+
+static inline int inat_immediate_size(insn_attr_t attr)
+{
+	return (attr & INAT_IMM_MASK) >> INAT_IMM_OFFS;
+}
+
+static inline int inat_has_modrm(insn_attr_t attr)
+{
+	return attr & INAT_MODRM;
+}
+
+static inline int inat_is_force64(insn_attr_t attr)
+{
+	return attr & INAT_FORCE64;
+}
+
+static inline int inat_has_second_immediate(insn_attr_t attr)
+{
+	return attr & INAT_SCNDIMM;
+}
+
+static inline int inat_has_moffset(insn_attr_t attr)
+{
+	return attr & INAT_MOFFSET;
+}
+
+static inline int inat_has_variant(insn_attr_t attr)
+{
+	return attr & INAT_VARIANT;
+}
+
+static inline int inat_accept_vex(insn_attr_t attr)
+{
+	return attr & INAT_VEXOK;
+}
+
+static inline int inat_must_vex(insn_attr_t attr)
+{
+	return attr & INAT_VEXONLY;
+}
+#endif
diff --git a/tools/objtool/arch/x86/insn/inat_types.h b/tools/objtool/arch/x86/insn/inat_types.h
new file mode 100644
index 000000000..cb3c20ce3
--- /dev/null
+++ b/tools/objtool/arch/x86/insn/inat_types.h
@@ -0,0 +1,29 @@
+#ifndef _ASM_X86_INAT_TYPES_H
+#define _ASM_X86_INAT_TYPES_H
+/*
+ * x86 instruction attributes
+ *
+ * Written by Masami Hiramatsu <mhiramat@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+
+/* Instruction attributes */
+typedef unsigned int insn_attr_t;
+typedef unsigned char insn_byte_t;
+typedef signed int insn_value_t;
+
+#endif
diff --git a/tools/objtool/arch/x86/insn/insn.c b/tools/objtool/arch/x86/insn/insn.c
new file mode 100644
index 000000000..9f26eae6c
--- /dev/null
+++ b/tools/objtool/arch/x86/insn/insn.c
@@ -0,0 +1,594 @@
+/*
+ * x86 instruction analysis
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2002, 2004, 2009
+ */
+
+#ifdef __KERNEL__
+#include <linux/string.h>
+#else
+#include <string.h>
+#endif
+#include "inat.h"
+#include "insn.h"
+
+/* Verify next sizeof(t) bytes can be on the same instruction */
+#define validate_next(t, insn, n)	\
+	((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr)
+
+#define __get_next(t, insn)	\
+	({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; })
+
+#define __peek_nbyte_next(t, insn, n)	\
+	({ t r = *(t*)((insn)->next_byte + n); r; })
+
+#define get_next(t, insn)	\
+	({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); })
+
+#define peek_nbyte_next(t, insn, n)	\
+	({ if (unlikely(!validate_next(t, insn, n))) goto err_out; __peek_nbyte_next(t, insn, n); })
+
+#define peek_next(t, insn)	peek_nbyte_next(t, insn, 0)
+
+/**
+ * insn_init() - initialize struct insn
+ * @insn:	&struct insn to be initialized
+ * @kaddr:	address (in kernel memory) of instruction (or copy thereof)
+ * @x86_64:	!0 for 64-bit kernel or 64-bit app
+ */
+void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
+{
+	/*
+	 * Instructions longer than MAX_INSN_SIZE (15 bytes) are invalid
+	 * even if the input buffer is long enough to hold them.
+	 */
+	if (buf_len > MAX_INSN_SIZE)
+		buf_len = MAX_INSN_SIZE;
+
+	memset(insn, 0, sizeof(*insn));
+	insn->kaddr = kaddr;
+	insn->end_kaddr = kaddr + buf_len;
+	insn->next_byte = kaddr;
+	insn->x86_64 = x86_64 ? 1 : 0;
+	insn->opnd_bytes = 4;
+	if (x86_64)
+		insn->addr_bytes = 8;
+	else
+		insn->addr_bytes = 4;
+}
+
+/**
+ * insn_get_prefixes - scan x86 instruction prefix bytes
+ * @insn:	&struct insn containing instruction
+ *
+ * Populates the @insn->prefixes bitmap, and updates @insn->next_byte
+ * to point to the (first) opcode.  No effect if @insn->prefixes.got
+ * is already set.
+ */
+void insn_get_prefixes(struct insn *insn)
+{
+	struct insn_field *prefixes = &insn->prefixes;
+	insn_attr_t attr;
+	insn_byte_t b, lb;
+	int i, nb;
+
+	if (prefixes->got)
+		return;
+
+	nb = 0;
+	lb = 0;
+	b = peek_next(insn_byte_t, insn);
+	attr = inat_get_opcode_attribute(b);
+	while (inat_is_legacy_prefix(attr)) {
+		/* Skip if same prefix */
+		for (i = 0; i < nb; i++)
+			if (prefixes->bytes[i] == b)
+				goto found;
+		if (nb == 4)
+			/* Invalid instruction */
+			break;
+		prefixes->bytes[nb++] = b;
+		if (inat_is_address_size_prefix(attr)) {
+			/* address size switches 2/4 or 4/8 */
+			if (insn->x86_64)
+				insn->addr_bytes ^= 12;
+			else
+				insn->addr_bytes ^= 6;
+		} else if (inat_is_operand_size_prefix(attr)) {
+			/* oprand size switches 2/4 */
+			insn->opnd_bytes ^= 6;
+		}
+found:
+		prefixes->nbytes++;
+		insn->next_byte++;
+		lb = b;
+		b = peek_next(insn_byte_t, insn);
+		attr = inat_get_opcode_attribute(b);
+	}
+	/* Set the last prefix */
+	if (lb && lb != insn->prefixes.bytes[3]) {
+		if (unlikely(insn->prefixes.bytes[3])) {
+			/* Swap the last prefix */
+			b = insn->prefixes.bytes[3];
+			for (i = 0; i < nb; i++)
+				if (prefixes->bytes[i] == lb)
+					prefixes->bytes[i] = b;
+		}
+		insn->prefixes.bytes[3] = lb;
+	}
+
+	/* Decode REX prefix */
+	if (insn->x86_64) {
+		b = peek_next(insn_byte_t, insn);
+		attr = inat_get_opcode_attribute(b);
+		if (inat_is_rex_prefix(attr)) {
+			insn->rex_prefix.value = b;
+			insn->rex_prefix.nbytes = 1;
+			insn->next_byte++;
+			if (X86_REX_W(b))
+				/* REX.W overrides opnd_size */
+				insn->opnd_bytes = 8;
+		}
+	}
+	insn->rex_prefix.got = 1;
+
+	/* Decode VEX prefix */
+	b = peek_next(insn_byte_t, insn);
+	attr = inat_get_opcode_attribute(b);
+	if (inat_is_vex_prefix(attr)) {
+		insn_byte_t b2 = peek_nbyte_next(insn_byte_t, insn, 1);
+		if (!insn->x86_64) {
+			/*
+			 * In 32-bits mode, if the [7:6] bits (mod bits of
+			 * ModRM) on the second byte are not 11b, it is
+			 * LDS or LES.
+			 */
+			if (X86_MODRM_MOD(b2) != 3)
+				goto vex_end;
+		}
+		insn->vex_prefix.bytes[0] = b;
+		insn->vex_prefix.bytes[1] = b2;
+		if (inat_is_vex3_prefix(attr)) {
+			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
+			insn->vex_prefix.bytes[2] = b2;
+			insn->vex_prefix.nbytes = 3;
+			insn->next_byte += 3;
+			if (insn->x86_64 && X86_VEX_W(b2))
+				/* VEX.W overrides opnd_size */
+				insn->opnd_bytes = 8;
+		} else {
+			/*
+			 * For VEX2, fake VEX3-like byte#2.
+			 * Makes it easier to decode vex.W, vex.vvvv,
+			 * vex.L and vex.pp. Masking with 0x7f sets vex.W == 0.
+			 */
+			insn->vex_prefix.bytes[2] = b2 & 0x7f;
+			insn->vex_prefix.nbytes = 2;
+			insn->next_byte += 2;
+		}
+	}
+vex_end:
+	insn->vex_prefix.got = 1;
+
+	prefixes->got = 1;
+
+err_out:
+	return;
+}
+
+/**
+ * insn_get_opcode - collect opcode(s)
+ * @insn:	&struct insn containing instruction
+ *
+ * Populates @insn->opcode, updates @insn->next_byte to point past the
+ * opcode byte(s), and set @insn->attr (except for groups).
+ * If necessary, first collects any preceding (prefix) bytes.
+ * Sets @insn->opcode.value = opcode1.  No effect if @insn->opcode.got
+ * is already 1.
+ */
+void insn_get_opcode(struct insn *insn)
+{
+	struct insn_field *opcode = &insn->opcode;
+	insn_byte_t op;
+	int pfx_id;
+	if (opcode->got)
+		return;
+	if (!insn->prefixes.got)
+		insn_get_prefixes(insn);
+
+	/* Get first opcode */
+	op = get_next(insn_byte_t, insn);
+	opcode->bytes[0] = op;
+	opcode->nbytes = 1;
+
+	/* Check if there is VEX prefix or not */
+	if (insn_is_avx(insn)) {
+		insn_byte_t m, p;
+		m = insn_vex_m_bits(insn);
+		p = insn_vex_p_bits(insn);
+		insn->attr = inat_get_avx_attribute(op, m, p);
+		if (!inat_accept_vex(insn->attr) && !inat_is_group(insn->attr))
+			insn->attr = 0;	/* This instruction is bad */
+		goto end;	/* VEX has only 1 byte for opcode */
+	}
+
+	insn->attr = inat_get_opcode_attribute(op);
+	while (inat_is_escape(insn->attr)) {
+		/* Get escaped opcode */
+		op = get_next(insn_byte_t, insn);
+		opcode->bytes[opcode->nbytes++] = op;
+		pfx_id = insn_last_prefix_id(insn);
+		insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr);
+	}
+	if (inat_must_vex(insn->attr))
+		insn->attr = 0;	/* This instruction is bad */
+end:
+	opcode->got = 1;
+
+err_out:
+	return;
+}
+
+/**
+ * insn_get_modrm - collect ModRM byte, if any
+ * @insn:	&struct insn containing instruction
+ *
+ * Populates @insn->modrm and updates @insn->next_byte to point past the
+ * ModRM byte, if any.  If necessary, first collects the preceding bytes
+ * (prefixes and opcode(s)).  No effect if @insn->modrm.got is already 1.
+ */
+void insn_get_modrm(struct insn *insn)
+{
+	struct insn_field *modrm = &insn->modrm;
+	insn_byte_t pfx_id, mod;
+	if (modrm->got)
+		return;
+	if (!insn->opcode.got)
+		insn_get_opcode(insn);
+
+	if (inat_has_modrm(insn->attr)) {
+		mod = get_next(insn_byte_t, insn);
+		modrm->value = mod;
+		modrm->nbytes = 1;
+		if (inat_is_group(insn->attr)) {
+			pfx_id = insn_last_prefix_id(insn);
+			insn->attr = inat_get_group_attribute(mod, pfx_id,
+							      insn->attr);
+			if (insn_is_avx(insn) && !inat_accept_vex(insn->attr))
+				insn->attr = 0;	/* This is bad */
+		}
+	}
+
+	if (insn->x86_64 && inat_is_force64(insn->attr))
+		insn->opnd_bytes = 8;
+	modrm->got = 1;
+
+err_out:
+	return;
+}
+
+
+/**
+ * insn_rip_relative() - Does instruction use RIP-relative addressing mode?
+ * @insn:	&struct insn containing instruction
+ *
+ * If necessary, first collects the instruction up to and including the
+ * ModRM byte.  No effect if @insn->x86_64 is 0.
+ */
+int insn_rip_relative(struct insn *insn)
+{
+	struct insn_field *modrm = &insn->modrm;
+
+	if (!insn->x86_64)
+		return 0;
+	if (!modrm->got)
+		insn_get_modrm(insn);
+	/*
+	 * For rip-relative instructions, the mod field (top 2 bits)
+	 * is zero and the r/m field (bottom 3 bits) is 0x5.
+	 */
+	return (modrm->nbytes && (modrm->value & 0xc7) == 0x5);
+}
+
+/**
+ * insn_get_sib() - Get the SIB byte of instruction
+ * @insn:	&struct insn containing instruction
+ *
+ * If necessary, first collects the instruction up to and including the
+ * ModRM byte.
+ */
+void insn_get_sib(struct insn *insn)
+{
+	insn_byte_t modrm;
+
+	if (insn->sib.got)
+		return;
+	if (!insn->modrm.got)
+		insn_get_modrm(insn);
+	if (insn->modrm.nbytes) {
+		modrm = (insn_byte_t)insn->modrm.value;
+		if (insn->addr_bytes != 2 &&
+		    X86_MODRM_MOD(modrm) != 3 && X86_MODRM_RM(modrm) == 4) {
+			insn->sib.value = get_next(insn_byte_t, insn);
+			insn->sib.nbytes = 1;
+		}
+	}
+	insn->sib.got = 1;
+
+err_out:
+	return;
+}
+
+
+/**
+ * insn_get_displacement() - Get the displacement of instruction
+ * @insn:	&struct insn containing instruction
+ *
+ * If necessary, first collects the instruction up to and including the
+ * SIB byte.
+ * Displacement value is sign-expanded.
+ */
+void insn_get_displacement(struct insn *insn)
+{
+	insn_byte_t mod, rm, base;
+
+	if (insn->displacement.got)
+		return;
+	if (!insn->sib.got)
+		insn_get_sib(insn);
+	if (insn->modrm.nbytes) {
+		/*
+		 * Interpreting the modrm byte:
+		 * mod = 00 - no displacement fields (exceptions below)
+		 * mod = 01 - 1-byte displacement field
+		 * mod = 10 - displacement field is 4 bytes, or 2 bytes if
+		 * 	address size = 2 (0x67 prefix in 32-bit mode)
+		 * mod = 11 - no memory operand
+		 *
+		 * If address size = 2...
+		 * mod = 00, r/m = 110 - displacement field is 2 bytes
+		 *
+		 * If address size != 2...
+		 * mod != 11, r/m = 100 - SIB byte exists
+		 * mod = 00, SIB base = 101 - displacement field is 4 bytes
+		 * mod = 00, r/m = 101 - rip-relative addressing, displacement
+		 * 	field is 4 bytes
+		 */
+		mod = X86_MODRM_MOD(insn->modrm.value);
+		rm = X86_MODRM_RM(insn->modrm.value);
+		base = X86_SIB_BASE(insn->sib.value);
+		if (mod == 3)
+			goto out;
+		if (mod == 1) {
+			insn->displacement.value = get_next(signed char, insn);
+			insn->displacement.nbytes = 1;
+		} else if (insn->addr_bytes == 2) {
+			if ((mod == 0 && rm == 6) || mod == 2) {
+				insn->displacement.value =
+					 get_next(short, insn);
+				insn->displacement.nbytes = 2;
+			}
+		} else {
+			if ((mod == 0 && rm == 5) || mod == 2 ||
+			    (mod == 0 && base == 5)) {
+				insn->displacement.value = get_next(int, insn);
+				insn->displacement.nbytes = 4;
+			}
+		}
+	}
+out:
+	insn->displacement.got = 1;
+
+err_out:
+	return;
+}
+
+/* Decode moffset16/32/64. Return 0 if failed */
+static int __get_moffset(struct insn *insn)
+{
+	switch (insn->addr_bytes) {
+	case 2:
+		insn->moffset1.value = get_next(short, insn);
+		insn->moffset1.nbytes = 2;
+		break;
+	case 4:
+		insn->moffset1.value = get_next(int, insn);
+		insn->moffset1.nbytes = 4;
+		break;
+	case 8:
+		insn->moffset1.value = get_next(int, insn);
+		insn->moffset1.nbytes = 4;
+		insn->moffset2.value = get_next(int, insn);
+		insn->moffset2.nbytes = 4;
+		break;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
+	}
+	insn->moffset1.got = insn->moffset2.got = 1;
+
+	return 1;
+
+err_out:
+	return 0;
+}
+
+/* Decode imm v32(Iz). Return 0 if failed */
+static int __get_immv32(struct insn *insn)
+{
+	switch (insn->opnd_bytes) {
+	case 2:
+		insn->immediate.value = get_next(short, insn);
+		insn->immediate.nbytes = 2;
+		break;
+	case 4:
+	case 8:
+		insn->immediate.value = get_next(int, insn);
+		insn->immediate.nbytes = 4;
+		break;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
+	}
+
+	return 1;
+
+err_out:
+	return 0;
+}
+
+/* Decode imm v64(Iv/Ov), Return 0 if failed */
+static int __get_immv(struct insn *insn)
+{
+	switch (insn->opnd_bytes) {
+	case 2:
+		insn->immediate1.value = get_next(short, insn);
+		insn->immediate1.nbytes = 2;
+		break;
+	case 4:
+		insn->immediate1.value = get_next(int, insn);
+		insn->immediate1.nbytes = 4;
+		break;
+	case 8:
+		insn->immediate1.value = get_next(int, insn);
+		insn->immediate1.nbytes = 4;
+		insn->immediate2.value = get_next(int, insn);
+		insn->immediate2.nbytes = 4;
+		break;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
+	}
+	insn->immediate1.got = insn->immediate2.got = 1;
+
+	return 1;
+err_out:
+	return 0;
+}
+
+/* Decode ptr16:16/32(Ap) */
+static int __get_immptr(struct insn *insn)
+{
+	switch (insn->opnd_bytes) {
+	case 2:
+		insn->immediate1.value = get_next(short, insn);
+		insn->immediate1.nbytes = 2;
+		break;
+	case 4:
+		insn->immediate1.value = get_next(int, insn);
+		insn->immediate1.nbytes = 4;
+		break;
+	case 8:
+		/* ptr16:64 is not exist (no segment) */
+		return 0;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
+	}
+	insn->immediate2.value = get_next(unsigned short, insn);
+	insn->immediate2.nbytes = 2;
+	insn->immediate1.got = insn->immediate2.got = 1;
+
+	return 1;
+err_out:
+	return 0;
+}
+
+/**
+ * insn_get_immediate() - Get the immediates of instruction
+ * @insn:	&struct insn containing instruction
+ *
+ * If necessary, first collects the instruction up to and including the
+ * displacement bytes.
+ * Basically, most of immediates are sign-expanded. Unsigned-value can be
+ * get by bit masking with ((1 << (nbytes * 8)) - 1)
+ */
+void insn_get_immediate(struct insn *insn)
+{
+	if (insn->immediate.got)
+		return;
+	if (!insn->displacement.got)
+		insn_get_displacement(insn);
+
+	if (inat_has_moffset(insn->attr)) {
+		if (!__get_moffset(insn))
+			goto err_out;
+		goto done;
+	}
+
+	if (!inat_has_immediate(insn->attr))
+		/* no immediates */
+		goto done;
+
+	switch (inat_immediate_size(insn->attr)) {
+	case INAT_IMM_BYTE:
+		insn->immediate.value = get_next(signed char, insn);
+		insn->immediate.nbytes = 1;
+		break;
+	case INAT_IMM_WORD:
+		insn->immediate.value = get_next(short, insn);
+		insn->immediate.nbytes = 2;
+		break;
+	case INAT_IMM_DWORD:
+		insn->immediate.value = get_next(int, insn);
+		insn->immediate.nbytes = 4;
+		break;
+	case INAT_IMM_QWORD:
+		insn->immediate1.value = get_next(int, insn);
+		insn->immediate1.nbytes = 4;
+		insn->immediate2.value = get_next(int, insn);
+		insn->immediate2.nbytes = 4;
+		break;
+	case INAT_IMM_PTR:
+		if (!__get_immptr(insn))
+			goto err_out;
+		break;
+	case INAT_IMM_VWORD32:
+		if (!__get_immv32(insn))
+			goto err_out;
+		break;
+	case INAT_IMM_VWORD:
+		if (!__get_immv(insn))
+			goto err_out;
+		break;
+	default:
+		/* Here, insn must have an immediate, but failed */
+		goto err_out;
+	}
+	if (inat_has_second_immediate(insn->attr)) {
+		insn->immediate2.value = get_next(signed char, insn);
+		insn->immediate2.nbytes = 1;
+	}
+done:
+	insn->immediate.got = 1;
+
+err_out:
+	return;
+}
+
+/**
+ * insn_get_length() - Get the length of instruction
+ * @insn:	&struct insn containing instruction
+ *
+ * If necessary, first collects the instruction up to and including the
+ * immediates bytes.
+ */
+void insn_get_length(struct insn *insn)
+{
+	if (insn->length)
+		return;
+	if (!insn->immediate.got)
+		insn_get_immediate(insn);
+	insn->length = (unsigned char)((unsigned long)insn->next_byte
+				     - (unsigned long)insn->kaddr);
+}
diff --git a/tools/objtool/arch/x86/insn/insn.h b/tools/objtool/arch/x86/insn/insn.h
new file mode 100644
index 000000000..dd12da0f4
--- /dev/null
+++ b/tools/objtool/arch/x86/insn/insn.h
@@ -0,0 +1,201 @@
+#ifndef _ASM_X86_INSN_H
+#define _ASM_X86_INSN_H
+/*
+ * x86 instruction analysis
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2009
+ */
+
+/* insn_attr_t is defined in inat.h */
+#include "inat.h"
+
+struct insn_field {
+	union {
+		insn_value_t value;
+		insn_byte_t bytes[4];
+	};
+	/* !0 if we've run insn_get_xxx() for this field */
+	unsigned char got;
+	unsigned char nbytes;
+};
+
+struct insn {
+	struct insn_field prefixes;	/*
+					 * Prefixes
+					 * prefixes.bytes[3]: last prefix
+					 */
+	struct insn_field rex_prefix;	/* REX prefix */
+	struct insn_field vex_prefix;	/* VEX prefix */
+	struct insn_field opcode;	/*
+					 * opcode.bytes[0]: opcode1
+					 * opcode.bytes[1]: opcode2
+					 * opcode.bytes[2]: opcode3
+					 */
+	struct insn_field modrm;
+	struct insn_field sib;
+	struct insn_field displacement;
+	union {
+		struct insn_field immediate;
+		struct insn_field moffset1;	/* for 64bit MOV */
+		struct insn_field immediate1;	/* for 64bit imm or off16/32 */
+	};
+	union {
+		struct insn_field moffset2;	/* for 64bit MOV */
+		struct insn_field immediate2;	/* for 64bit imm or seg16 */
+	};
+
+	insn_attr_t attr;
+	unsigned char opnd_bytes;
+	unsigned char addr_bytes;
+	unsigned char length;
+	unsigned char x86_64;
+
+	const insn_byte_t *kaddr;	/* kernel address of insn to analyze */
+	const insn_byte_t *end_kaddr;	/* kernel address of last insn in buffer */
+	const insn_byte_t *next_byte;
+};
+
+#define MAX_INSN_SIZE	15
+
+#define X86_MODRM_MOD(modrm) (((modrm) & 0xc0) >> 6)
+#define X86_MODRM_REG(modrm) (((modrm) & 0x38) >> 3)
+#define X86_MODRM_RM(modrm) ((modrm) & 0x07)
+
+#define X86_SIB_SCALE(sib) (((sib) & 0xc0) >> 6)
+#define X86_SIB_INDEX(sib) (((sib) & 0x38) >> 3)
+#define X86_SIB_BASE(sib) ((sib) & 0x07)
+
+#define X86_REX_W(rex) ((rex) & 8)
+#define X86_REX_R(rex) ((rex) & 4)
+#define X86_REX_X(rex) ((rex) & 2)
+#define X86_REX_B(rex) ((rex) & 1)
+
+/* VEX bit flags  */
+#define X86_VEX_W(vex)	((vex) & 0x80)	/* VEX3 Byte2 */
+#define X86_VEX_R(vex)	((vex) & 0x80)	/* VEX2/3 Byte1 */
+#define X86_VEX_X(vex)	((vex) & 0x40)	/* VEX3 Byte1 */
+#define X86_VEX_B(vex)	((vex) & 0x20)	/* VEX3 Byte1 */
+#define X86_VEX_L(vex)	((vex) & 0x04)	/* VEX3 Byte2, VEX2 Byte1 */
+/* VEX bit fields */
+#define X86_VEX3_M(vex)	((vex) & 0x1f)		/* VEX3 Byte1 */
+#define X86_VEX2_M	1			/* VEX2.M always 1 */
+#define X86_VEX_V(vex)	(((vex) & 0x78) >> 3)	/* VEX3 Byte2, VEX2 Byte1 */
+#define X86_VEX_P(vex)	((vex) & 0x03)		/* VEX3 Byte2, VEX2 Byte1 */
+#define X86_VEX_M_MAX	0x1f			/* VEX3.M Maximum value */
+
+extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64);
+extern void insn_get_prefixes(struct insn *insn);
+extern void insn_get_opcode(struct insn *insn);
+extern void insn_get_modrm(struct insn *insn);
+extern void insn_get_sib(struct insn *insn);
+extern void insn_get_displacement(struct insn *insn);
+extern void insn_get_immediate(struct insn *insn);
+extern void insn_get_length(struct insn *insn);
+
+/* Attribute will be determined after getting ModRM (for opcode groups) */
+static inline void insn_get_attribute(struct insn *insn)
+{
+	insn_get_modrm(insn);
+}
+
+/* Instruction uses RIP-relative addressing */
+extern int insn_rip_relative(struct insn *insn);
+
+/* Init insn for kernel text */
+static inline void kernel_insn_init(struct insn *insn,
+				    const void *kaddr, int buf_len)
+{
+#ifdef CONFIG_X86_64
+	insn_init(insn, kaddr, buf_len, 1);
+#else /* CONFIG_X86_32 */
+	insn_init(insn, kaddr, buf_len, 0);
+#endif
+}
+
+static inline int insn_is_avx(struct insn *insn)
+{
+	if (!insn->prefixes.got)
+		insn_get_prefixes(insn);
+	return (insn->vex_prefix.value != 0);
+}
+
+/* Ensure this instruction is decoded completely */
+static inline int insn_complete(struct insn *insn)
+{
+	return insn->opcode.got && insn->modrm.got && insn->sib.got &&
+		insn->displacement.got && insn->immediate.got;
+}
+
+static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
+{
+	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
+		return X86_VEX2_M;
+	else
+		return X86_VEX3_M(insn->vex_prefix.bytes[1]);
+}
+
+static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
+{
+	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
+		return X86_VEX_P(insn->vex_prefix.bytes[1]);
+	else
+		return X86_VEX_P(insn->vex_prefix.bytes[2]);
+}
+
+/* Get the last prefix id from last prefix or VEX prefix */
+static inline int insn_last_prefix_id(struct insn *insn)
+{
+	if (insn_is_avx(insn))
+		return insn_vex_p_bits(insn);	/* VEX_p is a SIMD prefix id */
+
+	if (insn->prefixes.bytes[3])
+		return inat_get_last_prefix_id(insn->prefixes.bytes[3]);
+
+	return 0;
+}
+
+/* Offset of each field from kaddr */
+static inline int insn_offset_rex_prefix(struct insn *insn)
+{
+	return insn->prefixes.nbytes;
+}
+static inline int insn_offset_vex_prefix(struct insn *insn)
+{
+	return insn_offset_rex_prefix(insn) + insn->rex_prefix.nbytes;
+}
+static inline int insn_offset_opcode(struct insn *insn)
+{
+	return insn_offset_vex_prefix(insn) + insn->vex_prefix.nbytes;
+}
+static inline int insn_offset_modrm(struct insn *insn)
+{
+	return insn_offset_opcode(insn) + insn->opcode.nbytes;
+}
+static inline int insn_offset_sib(struct insn *insn)
+{
+	return insn_offset_modrm(insn) + insn->modrm.nbytes;
+}
+static inline int insn_offset_displacement(struct insn *insn)
+{
+	return insn_offset_sib(insn) + insn->sib.nbytes;
+}
+static inline int insn_offset_immediate(struct insn *insn)
+{
+	return insn_offset_displacement(insn) + insn->displacement.nbytes;
+}
+
+#endif /* _ASM_X86_INSN_H */
diff --git a/tools/objtool/arch/x86/insn/x86-opcode-map.txt b/tools/objtool/arch/x86/insn/x86-opcode-map.txt
new file mode 100644
index 000000000..d388de72e
--- /dev/null
+++ b/tools/objtool/arch/x86/insn/x86-opcode-map.txt
@@ -0,0 +1,984 @@
+# x86 Opcode Maps
+#
+# This is (mostly) based on following documentations.
+# - Intel(R) 64 and IA-32 Architectures Software Developer's Manual Vol.2C
+#   (#326018-047US, June 2013)
+#
+#<Opcode maps>
+# Table: table-name
+# Referrer: escaped-name
+# AVXcode: avx-code
+# opcode: mnemonic|GrpXXX [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
+# (or)
+# opcode: escape # escaped-name
+# EndTable
+#
+#<group maps>
+# GrpTable: GrpXXX
+# reg:  mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
+# EndTable
+#
+# AVX Superscripts
+#  (v): this opcode requires VEX prefix.
+#  (v1): this opcode only supports 128bit VEX.
+#
+# Last Prefix Superscripts
+#  - (66): the last prefix is 0x66
+#  - (F3): the last prefix is 0xF3
+#  - (F2): the last prefix is 0xF2
+#  - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
+#  - (66&F2): Both 0x66 and 0xF2 prefixes are specified.
+
+Table: one byte opcode
+Referrer:
+AVXcode:
+# 0x00 - 0x0f
+00: ADD Eb,Gb
+01: ADD Ev,Gv
+02: ADD Gb,Eb
+03: ADD Gv,Ev
+04: ADD AL,Ib
+05: ADD rAX,Iz
+06: PUSH ES (i64)
+07: POP ES (i64)
+08: OR Eb,Gb
+09: OR Ev,Gv
+0a: OR Gb,Eb
+0b: OR Gv,Ev
+0c: OR AL,Ib
+0d: OR rAX,Iz
+0e: PUSH CS (i64)
+0f: escape # 2-byte escape
+# 0x10 - 0x1f
+10: ADC Eb,Gb
+11: ADC Ev,Gv
+12: ADC Gb,Eb
+13: ADC Gv,Ev
+14: ADC AL,Ib
+15: ADC rAX,Iz
+16: PUSH SS (i64)
+17: POP SS (i64)
+18: SBB Eb,Gb
+19: SBB Ev,Gv
+1a: SBB Gb,Eb
+1b: SBB Gv,Ev
+1c: SBB AL,Ib
+1d: SBB rAX,Iz
+1e: PUSH DS (i64)
+1f: POP DS (i64)
+# 0x20 - 0x2f
+20: AND Eb,Gb
+21: AND Ev,Gv
+22: AND Gb,Eb
+23: AND Gv,Ev
+24: AND AL,Ib
+25: AND rAx,Iz
+26: SEG=ES (Prefix)
+27: DAA (i64)
+28: SUB Eb,Gb
+29: SUB Ev,Gv
+2a: SUB Gb,Eb
+2b: SUB Gv,Ev
+2c: SUB AL,Ib
+2d: SUB rAX,Iz
+2e: SEG=CS (Prefix)
+2f: DAS (i64)
+# 0x30 - 0x3f
+30: XOR Eb,Gb
+31: XOR Ev,Gv
+32: XOR Gb,Eb
+33: XOR Gv,Ev
+34: XOR AL,Ib
+35: XOR rAX,Iz
+36: SEG=SS (Prefix)
+37: AAA (i64)
+38: CMP Eb,Gb
+39: CMP Ev,Gv
+3a: CMP Gb,Eb
+3b: CMP Gv,Ev
+3c: CMP AL,Ib
+3d: CMP rAX,Iz
+3e: SEG=DS (Prefix)
+3f: AAS (i64)
+# 0x40 - 0x4f
+40: INC eAX (i64) | REX (o64)
+41: INC eCX (i64) | REX.B (o64)
+42: INC eDX (i64) | REX.X (o64)
+43: INC eBX (i64) | REX.XB (o64)
+44: INC eSP (i64) | REX.R (o64)
+45: INC eBP (i64) | REX.RB (o64)
+46: INC eSI (i64) | REX.RX (o64)
+47: INC eDI (i64) | REX.RXB (o64)
+48: DEC eAX (i64) | REX.W (o64)
+49: DEC eCX (i64) | REX.WB (o64)
+4a: DEC eDX (i64) | REX.WX (o64)
+4b: DEC eBX (i64) | REX.WXB (o64)
+4c: DEC eSP (i64) | REX.WR (o64)
+4d: DEC eBP (i64) | REX.WRB (o64)
+4e: DEC eSI (i64) | REX.WRX (o64)
+4f: DEC eDI (i64) | REX.WRXB (o64)
+# 0x50 - 0x5f
+50: PUSH rAX/r8 (d64)
+51: PUSH rCX/r9 (d64)
+52: PUSH rDX/r10 (d64)
+53: PUSH rBX/r11 (d64)
+54: PUSH rSP/r12 (d64)
+55: PUSH rBP/r13 (d64)
+56: PUSH rSI/r14 (d64)
+57: PUSH rDI/r15 (d64)
+58: POP rAX/r8 (d64)
+59: POP rCX/r9 (d64)
+5a: POP rDX/r10 (d64)
+5b: POP rBX/r11 (d64)
+5c: POP rSP/r12 (d64)
+5d: POP rBP/r13 (d64)
+5e: POP rSI/r14 (d64)
+5f: POP rDI/r15 (d64)
+# 0x60 - 0x6f
+60: PUSHA/PUSHAD (i64)
+61: POPA/POPAD (i64)
+62: BOUND Gv,Ma (i64)
+63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64)
+64: SEG=FS (Prefix)
+65: SEG=GS (Prefix)
+66: Operand-Size (Prefix)
+67: Address-Size (Prefix)
+68: PUSH Iz (d64)
+69: IMUL Gv,Ev,Iz
+6a: PUSH Ib (d64)
+6b: IMUL Gv,Ev,Ib
+6c: INS/INSB Yb,DX
+6d: INS/INSW/INSD Yz,DX
+6e: OUTS/OUTSB DX,Xb
+6f: OUTS/OUTSW/OUTSD DX,Xz
+# 0x70 - 0x7f
+70: JO Jb
+71: JNO Jb
+72: JB/JNAE/JC Jb
+73: JNB/JAE/JNC Jb
+74: JZ/JE Jb
+75: JNZ/JNE Jb
+76: JBE/JNA Jb
+77: JNBE/JA Jb
+78: JS Jb
+79: JNS Jb
+7a: JP/JPE Jb
+7b: JNP/JPO Jb
+7c: JL/JNGE Jb
+7d: JNL/JGE Jb
+7e: JLE/JNG Jb
+7f: JNLE/JG Jb
+# 0x80 - 0x8f
+80: Grp1 Eb,Ib (1A)
+81: Grp1 Ev,Iz (1A)
+82: Grp1 Eb,Ib (1A),(i64)
+83: Grp1 Ev,Ib (1A)
+84: TEST Eb,Gb
+85: TEST Ev,Gv
+86: XCHG Eb,Gb
+87: XCHG Ev,Gv
+88: MOV Eb,Gb
+89: MOV Ev,Gv
+8a: MOV Gb,Eb
+8b: MOV Gv,Ev
+8c: MOV Ev,Sw
+8d: LEA Gv,M
+8e: MOV Sw,Ew
+8f: Grp1A (1A) | POP Ev (d64)
+# 0x90 - 0x9f
+90: NOP | PAUSE (F3) | XCHG r8,rAX
+91: XCHG rCX/r9,rAX
+92: XCHG rDX/r10,rAX
+93: XCHG rBX/r11,rAX
+94: XCHG rSP/r12,rAX
+95: XCHG rBP/r13,rAX
+96: XCHG rSI/r14,rAX
+97: XCHG rDI/r15,rAX
+98: CBW/CWDE/CDQE
+99: CWD/CDQ/CQO
+9a: CALLF Ap (i64)
+9b: FWAIT/WAIT
+9c: PUSHF/D/Q Fv (d64)
+9d: POPF/D/Q Fv (d64)
+9e: SAHF
+9f: LAHF
+# 0xa0 - 0xaf
+a0: MOV AL,Ob
+a1: MOV rAX,Ov
+a2: MOV Ob,AL
+a3: MOV Ov,rAX
+a4: MOVS/B Yb,Xb
+a5: MOVS/W/D/Q Yv,Xv
+a6: CMPS/B Xb,Yb
+a7: CMPS/W/D Xv,Yv
+a8: TEST AL,Ib
+a9: TEST rAX,Iz
+aa: STOS/B Yb,AL
+ab: STOS/W/D/Q Yv,rAX
+ac: LODS/B AL,Xb
+ad: LODS/W/D/Q rAX,Xv
+ae: SCAS/B AL,Yb
+# Note: The May 2011 Intel manual shows Xv for the second parameter of the
+# next instruction but Yv is correct
+af: SCAS/W/D/Q rAX,Yv
+# 0xb0 - 0xbf
+b0: MOV AL/R8L,Ib
+b1: MOV CL/R9L,Ib
+b2: MOV DL/R10L,Ib
+b3: MOV BL/R11L,Ib
+b4: MOV AH/R12L,Ib
+b5: MOV CH/R13L,Ib
+b6: MOV DH/R14L,Ib
+b7: MOV BH/R15L,Ib
+b8: MOV rAX/r8,Iv
+b9: MOV rCX/r9,Iv
+ba: MOV rDX/r10,Iv
+bb: MOV rBX/r11,Iv
+bc: MOV rSP/r12,Iv
+bd: MOV rBP/r13,Iv
+be: MOV rSI/r14,Iv
+bf: MOV rDI/r15,Iv
+# 0xc0 - 0xcf
+c0: Grp2 Eb,Ib (1A)
+c1: Grp2 Ev,Ib (1A)
+c2: RETN Iw (f64)
+c3: RETN
+c4: LES Gz,Mp (i64) | VEX+2byte (Prefix)
+c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix)
+c6: Grp11A Eb,Ib (1A)
+c7: Grp11B Ev,Iz (1A)
+c8: ENTER Iw,Ib
+c9: LEAVE (d64)
+ca: RETF Iw
+cb: RETF
+cc: INT3
+cd: INT Ib
+ce: INTO (i64)
+cf: IRET/D/Q
+# 0xd0 - 0xdf
+d0: Grp2 Eb,1 (1A)
+d1: Grp2 Ev,1 (1A)
+d2: Grp2 Eb,CL (1A)
+d3: Grp2 Ev,CL (1A)
+d4: AAM Ib (i64)
+d5: AAD Ib (i64)
+d6:
+d7: XLAT/XLATB
+d8: ESC
+d9: ESC
+da: ESC
+db: ESC
+dc: ESC
+dd: ESC
+de: ESC
+df: ESC
+# 0xe0 - 0xef
+# Note: "forced64" is Intel CPU behavior: they ignore 0x66 prefix
+# in 64-bit mode. AMD CPUs accept 0x66 prefix, it causes RIP truncation
+# to 16 bits. In 32-bit mode, 0x66 is accepted by both Intel and AMD.
+e0: LOOPNE/LOOPNZ Jb (f64)
+e1: LOOPE/LOOPZ Jb (f64)
+e2: LOOP Jb (f64)
+e3: JrCXZ Jb (f64)
+e4: IN AL,Ib
+e5: IN eAX,Ib
+e6: OUT Ib,AL
+e7: OUT Ib,eAX
+# With 0x66 prefix in 64-bit mode, for AMD CPUs immediate offset
+# in "near" jumps and calls is 16-bit. For CALL,
+# push of return address is 16-bit wide, RSP is decremented by 2
+# but is not truncated to 16 bits, unlike RIP.
+e8: CALL Jz (f64)
+e9: JMP-near Jz (f64)
+ea: JMP-far Ap (i64)
+eb: JMP-short Jb (f64)
+ec: IN AL,DX
+ed: IN eAX,DX
+ee: OUT DX,AL
+ef: OUT DX,eAX
+# 0xf0 - 0xff
+f0: LOCK (Prefix)
+f1:
+f2: REPNE (Prefix) | XACQUIRE (Prefix)
+f3: REP/REPE (Prefix) | XRELEASE (Prefix)
+f4: HLT
+f5: CMC
+f6: Grp3_1 Eb (1A)
+f7: Grp3_2 Ev (1A)
+f8: CLC
+f9: STC
+fa: CLI
+fb: STI
+fc: CLD
+fd: STD
+fe: Grp4 (1A)
+ff: Grp5 (1A)
+EndTable
+
+Table: 2-byte opcode (0x0f)
+Referrer: 2-byte escape
+AVXcode: 1
+# 0x0f 0x00-0x0f
+00: Grp6 (1A)
+01: Grp7 (1A)
+02: LAR Gv,Ew
+03: LSL Gv,Ew
+04:
+05: SYSCALL (o64)
+06: CLTS
+07: SYSRET (o64)
+08: INVD
+09: WBINVD
+0a:
+0b: UD2 (1B)
+0c:
+# AMD's prefetch group. Intel supports prefetchw(/1) only.
+0d: GrpP
+0e: FEMMS
+# 3DNow! uses the last imm byte as opcode extension.
+0f: 3DNow! Pq,Qq,Ib
+# 0x0f 0x10-0x1f
+# NOTE: According to Intel SDM opcode map, vmovups and vmovupd has no operands
+# but it actually has operands. And also, vmovss and vmovsd only accept 128bit.
+# MOVSS/MOVSD has too many forms(3) on SDM. This map just shows a typical form.
+# Many AVX instructions lack v1 superscript, according to Intel AVX-Prgramming
+# Reference A.1
+10: vmovups Vps,Wps | vmovupd Vpd,Wpd (66) | vmovss Vx,Hx,Wss (F3),(v1) | vmovsd Vx,Hx,Wsd (F2),(v1)
+11: vmovups Wps,Vps | vmovupd Wpd,Vpd (66) | vmovss Wss,Hx,Vss (F3),(v1) | vmovsd Wsd,Hx,Vsd (F2),(v1)
+12: vmovlps Vq,Hq,Mq (v1) | vmovhlps Vq,Hq,Uq (v1) | vmovlpd Vq,Hq,Mq (66),(v1) | vmovsldup Vx,Wx (F3) | vmovddup Vx,Wx (F2)
+13: vmovlps Mq,Vq (v1) | vmovlpd Mq,Vq (66),(v1)
+14: vunpcklps Vx,Hx,Wx | vunpcklpd Vx,Hx,Wx (66)
+15: vunpckhps Vx,Hx,Wx | vunpckhpd Vx,Hx,Wx (66)
+16: vmovhps Vdq,Hq,Mq (v1) | vmovlhps Vdq,Hq,Uq (v1) | vmovhpd Vdq,Hq,Mq (66),(v1) | vmovshdup Vx,Wx (F3)
+17: vmovhps Mq,Vq (v1) | vmovhpd Mq,Vq (66),(v1)
+18: Grp16 (1A)
+19:
+# Intel SDM opcode map does not list MPX instructions. For now using Gv for
+# bnd registers and Ev for everything else is OK because the instruction
+# decoder does not use the information except as an indication that there is
+# a ModR/M byte.
+1a: BNDCL Gv,Ev (F3) | BNDCU Gv,Ev (F2) | BNDMOV Gv,Ev (66) | BNDLDX Gv,Ev
+1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv
+1c:
+1d:
+1e:
+1f: NOP Ev
+# 0x0f 0x20-0x2f
+20: MOV Rd,Cd
+21: MOV Rd,Dd
+22: MOV Cd,Rd
+23: MOV Dd,Rd
+24:
+25:
+26:
+27:
+28: vmovaps Vps,Wps | vmovapd Vpd,Wpd (66)
+29: vmovaps Wps,Vps | vmovapd Wpd,Vpd (66)
+2a: cvtpi2ps Vps,Qpi | cvtpi2pd Vpd,Qpi (66) | vcvtsi2ss Vss,Hss,Ey (F3),(v1) | vcvtsi2sd Vsd,Hsd,Ey (F2),(v1)
+2b: vmovntps Mps,Vps | vmovntpd Mpd,Vpd (66)
+2c: cvttps2pi Ppi,Wps | cvttpd2pi Ppi,Wpd (66) | vcvttss2si Gy,Wss (F3),(v1) | vcvttsd2si Gy,Wsd (F2),(v1)
+2d: cvtps2pi Ppi,Wps | cvtpd2pi Qpi,Wpd (66) | vcvtss2si Gy,Wss (F3),(v1) | vcvtsd2si Gy,Wsd (F2),(v1)
+2e: vucomiss Vss,Wss (v1) | vucomisd  Vsd,Wsd (66),(v1)
+2f: vcomiss Vss,Wss (v1) | vcomisd  Vsd,Wsd (66),(v1)
+# 0x0f 0x30-0x3f
+30: WRMSR
+31: RDTSC
+32: RDMSR
+33: RDPMC
+34: SYSENTER
+35: SYSEXIT
+36:
+37: GETSEC
+38: escape # 3-byte escape 1
+39:
+3a: escape # 3-byte escape 2
+3b:
+3c:
+3d:
+3e:
+3f:
+# 0x0f 0x40-0x4f
+40: CMOVO Gv,Ev
+41: CMOVNO Gv,Ev
+42: CMOVB/C/NAE Gv,Ev
+43: CMOVAE/NB/NC Gv,Ev
+44: CMOVE/Z Gv,Ev
+45: CMOVNE/NZ Gv,Ev
+46: CMOVBE/NA Gv,Ev
+47: CMOVA/NBE Gv,Ev
+48: CMOVS Gv,Ev
+49: CMOVNS Gv,Ev
+4a: CMOVP/PE Gv,Ev
+4b: CMOVNP/PO Gv,Ev
+4c: CMOVL/NGE Gv,Ev
+4d: CMOVNL/GE Gv,Ev
+4e: CMOVLE/NG Gv,Ev
+4f: CMOVNLE/G Gv,Ev
+# 0x0f 0x50-0x5f
+50: vmovmskps Gy,Ups | vmovmskpd Gy,Upd (66)
+51: vsqrtps Vps,Wps | vsqrtpd Vpd,Wpd (66) | vsqrtss Vss,Hss,Wss (F3),(v1) | vsqrtsd Vsd,Hsd,Wsd (F2),(v1)
+52: vrsqrtps Vps,Wps | vrsqrtss Vss,Hss,Wss (F3),(v1)
+53: vrcpps Vps,Wps | vrcpss Vss,Hss,Wss (F3),(v1)
+54: vandps Vps,Hps,Wps | vandpd Vpd,Hpd,Wpd (66)
+55: vandnps Vps,Hps,Wps | vandnpd Vpd,Hpd,Wpd (66)
+56: vorps Vps,Hps,Wps | vorpd Vpd,Hpd,Wpd (66)
+57: vxorps Vps,Hps,Wps | vxorpd Vpd,Hpd,Wpd (66)
+58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1)
+59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1)
+5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1)
+5b: vcvtdq2ps Vps,Wdq | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
+5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1)
+5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1)
+5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1)
+5f: vmaxps Vps,Hps,Wps | vmaxpd Vpd,Hpd,Wpd (66) | vmaxss Vss,Hss,Wss (F3),(v1) | vmaxsd Vsd,Hsd,Wsd (F2),(v1)
+# 0x0f 0x60-0x6f
+60: punpcklbw Pq,Qd | vpunpcklbw Vx,Hx,Wx (66),(v1)
+61: punpcklwd Pq,Qd | vpunpcklwd Vx,Hx,Wx (66),(v1)
+62: punpckldq Pq,Qd | vpunpckldq Vx,Hx,Wx (66),(v1)
+63: packsswb Pq,Qq | vpacksswb Vx,Hx,Wx (66),(v1)
+64: pcmpgtb Pq,Qq | vpcmpgtb Vx,Hx,Wx (66),(v1)
+65: pcmpgtw Pq,Qq | vpcmpgtw Vx,Hx,Wx (66),(v1)
+66: pcmpgtd Pq,Qq | vpcmpgtd Vx,Hx,Wx (66),(v1)
+67: packuswb Pq,Qq | vpackuswb Vx,Hx,Wx (66),(v1)
+68: punpckhbw Pq,Qd | vpunpckhbw Vx,Hx,Wx (66),(v1)
+69: punpckhwd Pq,Qd | vpunpckhwd Vx,Hx,Wx (66),(v1)
+6a: punpckhdq Pq,Qd | vpunpckhdq Vx,Hx,Wx (66),(v1)
+6b: packssdw Pq,Qd | vpackssdw Vx,Hx,Wx (66),(v1)
+6c: vpunpcklqdq Vx,Hx,Wx (66),(v1)
+6d: vpunpckhqdq Vx,Hx,Wx (66),(v1)
+6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1)
+6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqu Vx,Wx (F3)
+# 0x0f 0x70-0x7f
+70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1)
+71: Grp12 (1A)
+72: Grp13 (1A)
+73: Grp14 (1A)
+74: pcmpeqb Pq,Qq | vpcmpeqb Vx,Hx,Wx (66),(v1)
+75: pcmpeqw Pq,Qq | vpcmpeqw Vx,Hx,Wx (66),(v1)
+76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1)
+# Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX.
+77: emms | vzeroupper | vzeroall
+78: VMREAD Ey,Gy
+79: VMWRITE Gy,Ey
+7a:
+7b:
+7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2)
+7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2)
+7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1)
+7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqu Wx,Vx (F3)
+# 0x0f 0x80-0x8f
+# Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
+80: JO Jz (f64)
+81: JNO Jz (f64)
+82: JB/JC/JNAE Jz (f64)
+83: JAE/JNB/JNC Jz (f64)
+84: JE/JZ Jz (f64)
+85: JNE/JNZ Jz (f64)
+86: JBE/JNA Jz (f64)
+87: JA/JNBE Jz (f64)
+88: JS Jz (f64)
+89: JNS Jz (f64)
+8a: JP/JPE Jz (f64)
+8b: JNP/JPO Jz (f64)
+8c: JL/JNGE Jz (f64)
+8d: JNL/JGE Jz (f64)
+8e: JLE/JNG Jz (f64)
+8f: JNLE/JG Jz (f64)
+# 0x0f 0x90-0x9f
+90: SETO Eb
+91: SETNO Eb
+92: SETB/C/NAE Eb
+93: SETAE/NB/NC Eb
+94: SETE/Z Eb
+95: SETNE/NZ Eb
+96: SETBE/NA Eb
+97: SETA/NBE Eb
+98: SETS Eb
+99: SETNS Eb
+9a: SETP/PE Eb
+9b: SETNP/PO Eb
+9c: SETL/NGE Eb
+9d: SETNL/GE Eb
+9e: SETLE/NG Eb
+9f: SETNLE/G Eb
+# 0x0f 0xa0-0xaf
+a0: PUSH FS (d64)
+a1: POP FS (d64)
+a2: CPUID
+a3: BT Ev,Gv
+a4: SHLD Ev,Gv,Ib
+a5: SHLD Ev,Gv,CL
+a6: GrpPDLK
+a7: GrpRNG
+a8: PUSH GS (d64)
+a9: POP GS (d64)
+aa: RSM
+ab: BTS Ev,Gv
+ac: SHRD Ev,Gv,Ib
+ad: SHRD Ev,Gv,CL
+ae: Grp15 (1A),(1C)
+af: IMUL Gv,Ev
+# 0x0f 0xb0-0xbf
+b0: CMPXCHG Eb,Gb
+b1: CMPXCHG Ev,Gv
+b2: LSS Gv,Mp
+b3: BTR Ev,Gv
+b4: LFS Gv,Mp
+b5: LGS Gv,Mp
+b6: MOVZX Gv,Eb
+b7: MOVZX Gv,Ew
+b8: JMPE (!F3) | POPCNT Gv,Ev (F3)
+b9: Grp10 (1A)
+ba: Grp8 Ev,Ib (1A)
+bb: BTC Ev,Gv
+bc: BSF Gv,Ev (!F3) | TZCNT Gv,Ev (F3)
+bd: BSR Gv,Ev (!F3) | LZCNT Gv,Ev (F3)
+be: MOVSX Gv,Eb
+bf: MOVSX Gv,Ew
+# 0x0f 0xc0-0xcf
+c0: XADD Eb,Gb
+c1: XADD Ev,Gv
+c2: vcmpps Vps,Hps,Wps,Ib | vcmppd Vpd,Hpd,Wpd,Ib (66) | vcmpss Vss,Hss,Wss,Ib (F3),(v1) | vcmpsd Vsd,Hsd,Wsd,Ib (F2),(v1)
+c3: movnti My,Gy
+c4: pinsrw Pq,Ry/Mw,Ib | vpinsrw Vdq,Hdq,Ry/Mw,Ib (66),(v1)
+c5: pextrw Gd,Nq,Ib | vpextrw Gd,Udq,Ib (66),(v1)
+c6: vshufps Vps,Hps,Wps,Ib | vshufpd Vpd,Hpd,Wpd,Ib (66)
+c7: Grp9 (1A)
+c8: BSWAP RAX/EAX/R8/R8D
+c9: BSWAP RCX/ECX/R9/R9D
+ca: BSWAP RDX/EDX/R10/R10D
+cb: BSWAP RBX/EBX/R11/R11D
+cc: BSWAP RSP/ESP/R12/R12D
+cd: BSWAP RBP/EBP/R13/R13D
+ce: BSWAP RSI/ESI/R14/R14D
+cf: BSWAP RDI/EDI/R15/R15D
+# 0x0f 0xd0-0xdf
+d0: vaddsubpd Vpd,Hpd,Wpd (66) | vaddsubps Vps,Hps,Wps (F2)
+d1: psrlw Pq,Qq | vpsrlw Vx,Hx,Wx (66),(v1)
+d2: psrld Pq,Qq | vpsrld Vx,Hx,Wx (66),(v1)
+d3: psrlq Pq,Qq | vpsrlq Vx,Hx,Wx (66),(v1)
+d4: paddq Pq,Qq | vpaddq Vx,Hx,Wx (66),(v1)
+d5: pmullw Pq,Qq | vpmullw Vx,Hx,Wx (66),(v1)
+d6: vmovq Wq,Vq (66),(v1) | movq2dq Vdq,Nq (F3) | movdq2q Pq,Uq (F2)
+d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1)
+d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1)
+d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1)
+da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1)
+db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1)
+dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1)
+dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1)
+de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1)
+df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1)
+# 0x0f 0xe0-0xef
+e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1)
+e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1)
+e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1)
+e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1)
+e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1)
+e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1)
+e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtpd2dq Vx,Wpd (F2)
+e7: movntq Mq,Pq | vmovntdq Mx,Vx (66)
+e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1)
+e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1)
+ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1)
+eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1)
+ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1)
+ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1)
+ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1)
+ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1)
+# 0x0f 0xf0-0xff
+f0: vlddqu Vx,Mx (F2)
+f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1)
+f2: pslld Pq,Qq | vpslld Vx,Hx,Wx (66),(v1)
+f3: psllq Pq,Qq | vpsllq Vx,Hx,Wx (66),(v1)
+f4: pmuludq Pq,Qq | vpmuludq Vx,Hx,Wx (66),(v1)
+f5: pmaddwd Pq,Qq | vpmaddwd Vx,Hx,Wx (66),(v1)
+f6: psadbw Pq,Qq | vpsadbw Vx,Hx,Wx (66),(v1)
+f7: maskmovq Pq,Nq | vmaskmovdqu Vx,Ux (66),(v1)
+f8: psubb Pq,Qq | vpsubb Vx,Hx,Wx (66),(v1)
+f9: psubw Pq,Qq | vpsubw Vx,Hx,Wx (66),(v1)
+fa: psubd Pq,Qq | vpsubd Vx,Hx,Wx (66),(v1)
+fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1)
+fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1)
+fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1)
+fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1)
+ff:
+EndTable
+
+Table: 3-byte opcode 1 (0x0f 0x38)
+Referrer: 3-byte escape 1
+AVXcode: 2
+# 0x0f 0x38 0x00-0x0f
+00: pshufb Pq,Qq | vpshufb Vx,Hx,Wx (66),(v1)
+01: phaddw Pq,Qq | vphaddw Vx,Hx,Wx (66),(v1)
+02: phaddd Pq,Qq | vphaddd Vx,Hx,Wx (66),(v1)
+03: phaddsw Pq,Qq | vphaddsw Vx,Hx,Wx (66),(v1)
+04: pmaddubsw Pq,Qq | vpmaddubsw Vx,Hx,Wx (66),(v1)
+05: phsubw Pq,Qq | vphsubw Vx,Hx,Wx (66),(v1)
+06: phsubd Pq,Qq | vphsubd Vx,Hx,Wx (66),(v1)
+07: phsubsw Pq,Qq | vphsubsw Vx,Hx,Wx (66),(v1)
+08: psignb Pq,Qq | vpsignb Vx,Hx,Wx (66),(v1)
+09: psignw Pq,Qq | vpsignw Vx,Hx,Wx (66),(v1)
+0a: psignd Pq,Qq | vpsignd Vx,Hx,Wx (66),(v1)
+0b: pmulhrsw Pq,Qq | vpmulhrsw Vx,Hx,Wx (66),(v1)
+0c: vpermilps Vx,Hx,Wx (66),(v)
+0d: vpermilpd Vx,Hx,Wx (66),(v)
+0e: vtestps Vx,Wx (66),(v)
+0f: vtestpd Vx,Wx (66),(v)
+# 0x0f 0x38 0x10-0x1f
+10: pblendvb Vdq,Wdq (66)
+11:
+12:
+13: vcvtph2ps Vx,Wx,Ib (66),(v)
+14: blendvps Vdq,Wdq (66)
+15: blendvpd Vdq,Wdq (66)
+16: vpermps Vqq,Hqq,Wqq (66),(v)
+17: vptest Vx,Wx (66)
+18: vbroadcastss Vx,Wd (66),(v)
+19: vbroadcastsd Vqq,Wq (66),(v)
+1a: vbroadcastf128 Vqq,Mdq (66),(v)
+1b:
+1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1)
+1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1)
+1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1)
+1f:
+# 0x0f 0x38 0x20-0x2f
+20: vpmovsxbw Vx,Ux/Mq (66),(v1)
+21: vpmovsxbd Vx,Ux/Md (66),(v1)
+22: vpmovsxbq Vx,Ux/Mw (66),(v1)
+23: vpmovsxwd Vx,Ux/Mq (66),(v1)
+24: vpmovsxwq Vx,Ux/Md (66),(v1)
+25: vpmovsxdq Vx,Ux/Mq (66),(v1)
+26:
+27:
+28: vpmuldq Vx,Hx,Wx (66),(v1)
+29: vpcmpeqq Vx,Hx,Wx (66),(v1)
+2a: vmovntdqa Vx,Mx (66),(v1)
+2b: vpackusdw Vx,Hx,Wx (66),(v1)
+2c: vmaskmovps Vx,Hx,Mx (66),(v)
+2d: vmaskmovpd Vx,Hx,Mx (66),(v)
+2e: vmaskmovps Mx,Hx,Vx (66),(v)
+2f: vmaskmovpd Mx,Hx,Vx (66),(v)
+# 0x0f 0x38 0x30-0x3f
+30: vpmovzxbw Vx,Ux/Mq (66),(v1)
+31: vpmovzxbd Vx,Ux/Md (66),(v1)
+32: vpmovzxbq Vx,Ux/Mw (66),(v1)
+33: vpmovzxwd Vx,Ux/Mq (66),(v1)
+34: vpmovzxwq Vx,Ux/Md (66),(v1)
+35: vpmovzxdq Vx,Ux/Mq (66),(v1)
+36: vpermd Vqq,Hqq,Wqq (66),(v)
+37: vpcmpgtq Vx,Hx,Wx (66),(v1)
+38: vpminsb Vx,Hx,Wx (66),(v1)
+39: vpminsd Vx,Hx,Wx (66),(v1)
+3a: vpminuw Vx,Hx,Wx (66),(v1)
+3b: vpminud Vx,Hx,Wx (66),(v1)
+3c: vpmaxsb Vx,Hx,Wx (66),(v1)
+3d: vpmaxsd Vx,Hx,Wx (66),(v1)
+3e: vpmaxuw Vx,Hx,Wx (66),(v1)
+3f: vpmaxud Vx,Hx,Wx (66),(v1)
+# 0x0f 0x38 0x40-0x8f
+40: vpmulld Vx,Hx,Wx (66),(v1)
+41: vphminposuw Vdq,Wdq (66),(v1)
+42:
+43:
+44:
+45: vpsrlvd/q Vx,Hx,Wx (66),(v)
+46: vpsravd Vx,Hx,Wx (66),(v)
+47: vpsllvd/q Vx,Hx,Wx (66),(v)
+# Skip 0x48-0x57
+58: vpbroadcastd Vx,Wx (66),(v)
+59: vpbroadcastq Vx,Wx (66),(v)
+5a: vbroadcasti128 Vqq,Mdq (66),(v)
+# Skip 0x5b-0x77
+78: vpbroadcastb Vx,Wx (66),(v)
+79: vpbroadcastw Vx,Wx (66),(v)
+# Skip 0x7a-0x7f
+80: INVEPT Gy,Mdq (66)
+81: INVPID Gy,Mdq (66)
+82: INVPCID Gy,Mdq (66)
+8c: vpmaskmovd/q Vx,Hx,Mx (66),(v)
+8e: vpmaskmovd/q Mx,Vx,Hx (66),(v)
+# 0x0f 0x38 0x90-0xbf (FMA)
+90: vgatherdd/q Vx,Hx,Wx (66),(v)
+91: vgatherqd/q Vx,Hx,Wx (66),(v)
+92: vgatherdps/d Vx,Hx,Wx (66),(v)
+93: vgatherqps/d Vx,Hx,Wx (66),(v)
+94:
+95:
+96: vfmaddsub132ps/d Vx,Hx,Wx (66),(v)
+97: vfmsubadd132ps/d Vx,Hx,Wx (66),(v)
+98: vfmadd132ps/d Vx,Hx,Wx (66),(v)
+99: vfmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
+9a: vfmsub132ps/d Vx,Hx,Wx (66),(v)
+9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
+9c: vfnmadd132ps/d Vx,Hx,Wx (66),(v)
+9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
+9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v)
+9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
+a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v)
+a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v)
+a8: vfmadd213ps/d Vx,Hx,Wx (66),(v)
+a9: vfmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
+aa: vfmsub213ps/d Vx,Hx,Wx (66),(v)
+ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
+ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)
+ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
+ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
+af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
+b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v)
+b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v)
+b8: vfmadd231ps/d Vx,Hx,Wx (66),(v)
+b9: vfmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
+ba: vfmsub231ps/d Vx,Hx,Wx (66),(v)
+bb: vfmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
+bc: vfnmadd231ps/d Vx,Hx,Wx (66),(v)
+bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
+be: vfnmsub231ps/d Vx,Hx,Wx (66),(v)
+bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
+# 0x0f 0x38 0xc0-0xff
+c8: sha1nexte Vdq,Wdq
+c9: sha1msg1 Vdq,Wdq
+ca: sha1msg2 Vdq,Wdq
+cb: sha256rnds2 Vdq,Wdq
+cc: sha256msg1 Vdq,Wdq
+cd: sha256msg2 Vdq,Wdq
+db: VAESIMC Vdq,Wdq (66),(v1)
+dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
+dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
+de: VAESDEC Vdq,Hdq,Wdq (66),(v1)
+df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1)
+f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2)
+f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2)
+f2: ANDN Gy,By,Ey (v)
+f3: Grp17 (1A)
+f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v)
+f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v)
+f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v)
+EndTable
+
+Table: 3-byte opcode 2 (0x0f 0x3a)
+Referrer: 3-byte escape 2
+AVXcode: 3
+# 0x0f 0x3a 0x00-0xff
+00: vpermq Vqq,Wqq,Ib (66),(v)
+01: vpermpd Vqq,Wqq,Ib (66),(v)
+02: vpblendd Vx,Hx,Wx,Ib (66),(v)
+03:
+04: vpermilps Vx,Wx,Ib (66),(v)
+05: vpermilpd Vx,Wx,Ib (66),(v)
+06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v)
+07:
+08: vroundps Vx,Wx,Ib (66)
+09: vroundpd Vx,Wx,Ib (66)
+0a: vroundss Vss,Wss,Ib (66),(v1)
+0b: vroundsd Vsd,Wsd,Ib (66),(v1)
+0c: vblendps Vx,Hx,Wx,Ib (66)
+0d: vblendpd Vx,Hx,Wx,Ib (66)
+0e: vpblendw Vx,Hx,Wx,Ib (66),(v1)
+0f: palignr Pq,Qq,Ib | vpalignr Vx,Hx,Wx,Ib (66),(v1)
+14: vpextrb Rd/Mb,Vdq,Ib (66),(v1)
+15: vpextrw Rd/Mw,Vdq,Ib (66),(v1)
+16: vpextrd/q Ey,Vdq,Ib (66),(v1)
+17: vextractps Ed,Vdq,Ib (66),(v1)
+18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v)
+19: vextractf128 Wdq,Vqq,Ib (66),(v)
+1d: vcvtps2ph Wx,Vx,Ib (66),(v)
+20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1)
+21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1)
+22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1)
+38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v)
+39: vextracti128 Wdq,Vqq,Ib (66),(v)
+40: vdpps Vx,Hx,Wx,Ib (66)
+41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1)
+42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1)
+44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1)
+46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v)
+4a: vblendvps Vx,Hx,Wx,Lx (66),(v)
+4b: vblendvpd Vx,Hx,Wx,Lx (66),(v)
+4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1)
+60: vpcmpestrm Vdq,Wdq,Ib (66),(v1)
+61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
+62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
+63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
+cc: sha1rnds4 Vdq,Wdq,Ib
+df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
+f0: RORX Gy,Ey,Ib (F2),(v)
+EndTable
+
+GrpTable: Grp1
+0: ADD
+1: OR
+2: ADC
+3: SBB
+4: AND
+5: SUB
+6: XOR
+7: CMP
+EndTable
+
+GrpTable: Grp1A
+0: POP
+EndTable
+
+GrpTable: Grp2
+0: ROL
+1: ROR
+2: RCL
+3: RCR
+4: SHL/SAL
+5: SHR
+6:
+7: SAR
+EndTable
+
+GrpTable: Grp3_1
+0: TEST Eb,Ib
+1:
+2: NOT Eb
+3: NEG Eb
+4: MUL AL,Eb
+5: IMUL AL,Eb
+6: DIV AL,Eb
+7: IDIV AL,Eb
+EndTable
+
+GrpTable: Grp3_2
+0: TEST Ev,Iz
+1:
+2: NOT Ev
+3: NEG Ev
+4: MUL rAX,Ev
+5: IMUL rAX,Ev
+6: DIV rAX,Ev
+7: IDIV rAX,Ev
+EndTable
+
+GrpTable: Grp4
+0: INC Eb
+1: DEC Eb
+EndTable
+
+GrpTable: Grp5
+0: INC Ev
+1: DEC Ev
+# Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
+2: CALLN Ev (f64)
+3: CALLF Ep
+4: JMPN Ev (f64)
+5: JMPF Mp
+6: PUSH Ev (d64)
+7:
+EndTable
+
+GrpTable: Grp6
+0: SLDT Rv/Mw
+1: STR Rv/Mw
+2: LLDT Ew
+3: LTR Ew
+4: VERR Ew
+5: VERW Ew
+EndTable
+
+GrpTable: Grp7
+0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B)
+1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B)
+2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B)
+3: LIDT Ms
+4: SMSW Mw/Rv
+5: rdpkru (110),(11B) | wrpkru (111),(11B)
+6: LMSW Ew
+7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B)
+EndTable
+
+GrpTable: Grp8
+4: BT
+5: BTS
+6: BTR
+7: BTC
+EndTable
+
+GrpTable: Grp9
+1: CMPXCHG8B/16B Mq/Mdq
+3: xrstors
+4: xsavec
+5: xsaves
+6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B)
+7: VMPTRST Mq | VMPTRST Mq (F3) | RDSEED Rv (11B)
+EndTable
+
+GrpTable: Grp10
+EndTable
+
+# Grp11A and Grp11B are expressed as Grp11 in Intel SDM
+GrpTable: Grp11A
+0: MOV Eb,Ib
+7: XABORT Ib (000),(11B)
+EndTable
+
+GrpTable: Grp11B
+0: MOV Eb,Iz
+7: XBEGIN Jz (000),(11B)
+EndTable
+
+GrpTable: Grp12
+2: psrlw Nq,Ib (11B) | vpsrlw Hx,Ux,Ib (66),(11B),(v1)
+4: psraw Nq,Ib (11B) | vpsraw Hx,Ux,Ib (66),(11B),(v1)
+6: psllw Nq,Ib (11B) | vpsllw Hx,Ux,Ib (66),(11B),(v1)
+EndTable
+
+GrpTable: Grp13
+2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1)
+4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1)
+6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1)
+EndTable
+
+GrpTable: Grp14
+2: psrlq Nq,Ib (11B) | vpsrlq Hx,Ux,Ib (66),(11B),(v1)
+3: vpsrldq Hx,Ux,Ib (66),(11B),(v1)
+6: psllq Nq,Ib (11B) | vpsllq Hx,Ux,Ib (66),(11B),(v1)
+7: vpslldq Hx,Ux,Ib (66),(11B),(v1)
+EndTable
+
+GrpTable: Grp15
+0: fxsave | RDFSBASE Ry (F3),(11B)
+1: fxstor | RDGSBASE Ry (F3),(11B)
+2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B)
+3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B)
+4: XSAVE
+5: XRSTOR | lfence (11B)
+6: XSAVEOPT | clwb (66) | mfence (11B)
+7: clflush | clflushopt (66) | sfence (11B) | pcommit (66),(11B)
+EndTable
+
+GrpTable: Grp16
+0: prefetch NTA
+1: prefetch T0
+2: prefetch T1
+3: prefetch T2
+EndTable
+
+GrpTable: Grp17
+1: BLSR By,Ey (v)
+2: BLSMSK By,Ey (v)
+3: BLSI By,Ey (v)
+EndTable
+
+# AMD's Prefetch Group
+GrpTable: GrpP
+0: PREFETCH
+1: PREFETCHW
+EndTable
+
+GrpTable: GrpPDLK
+0: MONTMUL
+1: XSHA1
+2: XSHA2
+EndTable
+
+GrpTable: GrpRNG
+0: xstore-rng
+1: xcrypt-ecb
+2: xcrypt-cbc
+4: xcrypt-cfb
+5: xcrypt-ofb
+EndTable
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
new file mode 100644
index 000000000..e8a1e69eb
--- /dev/null
+++ b/tools/objtool/builtin-check.c
@@ -0,0 +1,1206 @@
+/*
+ * Copyright (C) 2015 Josh Poimboeuf <jpoimboe@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * objtool check:
+ *
+ * This command analyzes every .o file and ensures the validity of its stack
+ * trace metadata.  It enforces a set of rules on asm code and C inline
+ * assembly code so that stack traces can be reliable.
+ *
+ * For more information, see tools/objtool/Documentation/stack-validation.txt.
+ */
+
+#include <string.h>
+#include <subcmd/parse-options.h>
+
+#include "builtin.h"
+#include "elf.h"
+#include "special.h"
+#include "arch.h"
+#include "warn.h"
+
+#include <linux/hashtable.h>
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+
+#define STATE_FP_SAVED		0x1
+#define STATE_FP_SETUP		0x2
+#define STATE_FENTRY		0x4
+
+struct instruction {
+	struct list_head list;
+	struct hlist_node hash;
+	struct section *sec;
+	unsigned long offset;
+	unsigned int len, state;
+	unsigned char type;
+	unsigned long immediate;
+	bool alt_group, visited;
+	struct symbol *call_dest;
+	struct instruction *jump_dest;
+	struct list_head alts;
+	struct symbol *func;
+};
+
+struct alternative {
+	struct list_head list;
+	struct instruction *insn;
+};
+
+struct objtool_file {
+	struct elf *elf;
+	struct list_head insn_list;
+	DECLARE_HASHTABLE(insn_hash, 16);
+	struct section *rodata, *whitelist;
+	bool ignore_unreachables, c_file;
+};
+
+const char *objname;
+static bool nofp;
+
+static struct instruction *find_insn(struct objtool_file *file,
+				     struct section *sec, unsigned long offset)
+{
+	struct instruction *insn;
+
+	hash_for_each_possible(file->insn_hash, insn, hash, offset)
+		if (insn->sec == sec && insn->offset == offset)
+			return insn;
+
+	return NULL;
+}
+
+static struct instruction *next_insn_same_sec(struct objtool_file *file,
+					      struct instruction *insn)
+{
+	struct instruction *next = list_next_entry(insn, list);
+
+	if (&next->list == &file->insn_list || next->sec != insn->sec)
+		return NULL;
+
+	return next;
+}
+
+#define for_each_insn(file, insn)					\
+	list_for_each_entry(insn, &file->insn_list, list)
+
+#define func_for_each_insn(file, func, insn)				\
+	for (insn = find_insn(file, func->sec, func->offset);		\
+	     insn && &insn->list != &file->insn_list &&			\
+		insn->sec == func->sec &&				\
+		insn->offset < func->offset + func->len;		\
+	     insn = list_next_entry(insn, list))
+
+#define sec_for_each_insn_from(file, insn)				\
+	for (; insn; insn = next_insn_same_sec(file, insn))
+
+
+/*
+ * Check if the function has been manually whitelisted with the
+ * STACK_FRAME_NON_STANDARD macro, or if it should be automatically whitelisted
+ * due to its use of a context switching instruction.
+ */
+static bool ignore_func(struct objtool_file *file, struct symbol *func)
+{
+	struct rela *rela;
+	struct instruction *insn;
+
+	/* check for STACK_FRAME_NON_STANDARD */
+	if (file->whitelist && file->whitelist->rela)
+		list_for_each_entry(rela, &file->whitelist->rela->rela_list, list)
+			if (rela->sym->sec == func->sec &&
+			    rela->addend == func->offset)
+				return true;
+
+	/* check if it has a context switching instruction */
+	func_for_each_insn(file, func, insn)
+		if (insn->type == INSN_CONTEXT_SWITCH)
+			return true;
+
+	return false;
+}
+
+/*
+ * This checks to see if the given function is a "noreturn" function.
+ *
+ * For global functions which are outside the scope of this object file, we
+ * have to keep a manual list of them.
+ *
+ * For local functions, we have to detect them manually by simply looking for
+ * the lack of a return instruction.
+ *
+ * Returns:
+ *  -1: error
+ *   0: no dead end
+ *   1: dead end
+ */
+static int __dead_end_function(struct objtool_file *file, struct symbol *func,
+			       int recursion)
+{
+	int i;
+	struct instruction *insn;
+	bool empty = true;
+
+	/*
+	 * Unfortunately these have to be hard coded because the noreturn
+	 * attribute isn't provided in ELF data.
+	 */
+	static const char * const global_noreturns[] = {
+		"__stack_chk_fail",
+		"panic",
+		"do_exit",
+		"__module_put_and_exit",
+		"complete_and_exit",
+		"kvm_spurious_fault",
+		"__reiserfs_panic",
+		"lbug_with_loc"
+	};
+
+	if (func->bind == STB_WEAK)
+		return 0;
+
+	if (func->bind == STB_GLOBAL)
+		for (i = 0; i < ARRAY_SIZE(global_noreturns); i++)
+			if (!strcmp(func->name, global_noreturns[i]))
+				return 1;
+
+	if (!func->sec)
+		return 0;
+
+	func_for_each_insn(file, func, insn) {
+		empty = false;
+
+		if (insn->type == INSN_RETURN)
+			return 0;
+	}
+
+	if (empty)
+		return 0;
+
+	/*
+	 * A function can have a sibling call instead of a return.  In that
+	 * case, the function's dead-end status depends on whether the target
+	 * of the sibling call returns.
+	 */
+	func_for_each_insn(file, func, insn) {
+		if (insn->sec != func->sec ||
+		    insn->offset >= func->offset + func->len)
+			break;
+
+		if (insn->type == INSN_JUMP_UNCONDITIONAL) {
+			struct instruction *dest = insn->jump_dest;
+			struct symbol *dest_func;
+
+			if (!dest)
+				/* sibling call to another file */
+				return 0;
+
+			if (dest->sec != func->sec ||
+			    dest->offset < func->offset ||
+			    dest->offset >= func->offset + func->len) {
+				/* local sibling call */
+				dest_func = find_symbol_by_offset(dest->sec,
+								  dest->offset);
+				if (!dest_func)
+					continue;
+
+				if (recursion == 5) {
+					WARN_FUNC("infinite recursion (objtool bug!)",
+						  dest->sec, dest->offset);
+					return -1;
+				}
+
+				return __dead_end_function(file, dest_func,
+							   recursion + 1);
+			}
+		}
+
+		if (insn->type == INSN_JUMP_DYNAMIC && list_empty(&insn->alts))
+			/* sibling call */
+			return 0;
+	}
+
+	return 1;
+}
+
+static int dead_end_function(struct objtool_file *file, struct symbol *func)
+{
+	return __dead_end_function(file, func, 0);
+}
+
+/*
+ * Call the arch-specific instruction decoder for all the instructions and add
+ * them to the global instruction list.
+ */
+static int decode_instructions(struct objtool_file *file)
+{
+	struct section *sec;
+	struct symbol *func;
+	unsigned long offset;
+	struct instruction *insn;
+	int ret;
+
+	list_for_each_entry(sec, &file->elf->sections, list) {
+
+		if (!(sec->sh.sh_flags & SHF_EXECINSTR))
+			continue;
+
+		for (offset = 0; offset < sec->len; offset += insn->len) {
+			insn = malloc(sizeof(*insn));
+			memset(insn, 0, sizeof(*insn));
+
+			INIT_LIST_HEAD(&insn->alts);
+			insn->sec = sec;
+			insn->offset = offset;
+
+			ret = arch_decode_instruction(file->elf, sec, offset,
+						      sec->len - offset,
+						      &insn->len, &insn->type,
+						      &insn->immediate);
+			if (ret)
+				return ret;
+
+			if (!insn->type || insn->type > INSN_LAST) {
+				WARN_FUNC("invalid instruction type %d",
+					  insn->sec, insn->offset, insn->type);
+				return -1;
+			}
+
+			hash_add(file->insn_hash, &insn->hash, insn->offset);
+			list_add_tail(&insn->list, &file->insn_list);
+		}
+
+		list_for_each_entry(func, &sec->symbol_list, list) {
+			if (func->type != STT_FUNC)
+				continue;
+
+			if (!find_insn(file, sec, func->offset)) {
+				WARN("%s(): can't find starting instruction",
+				     func->name);
+				return -1;
+			}
+
+			func_for_each_insn(file, func, insn)
+				if (!insn->func)
+					insn->func = func;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Warnings shouldn't be reported for ignored functions.
+ */
+static void add_ignores(struct objtool_file *file)
+{
+	struct instruction *insn;
+	struct section *sec;
+	struct symbol *func;
+
+	list_for_each_entry(sec, &file->elf->sections, list) {
+		list_for_each_entry(func, &sec->symbol_list, list) {
+			if (func->type != STT_FUNC)
+				continue;
+
+			if (!ignore_func(file, func))
+				continue;
+
+			func_for_each_insn(file, func, insn)
+				insn->visited = true;
+		}
+	}
+}
+
+/*
+ * Find the destination instructions for all jumps.
+ */
+static int add_jump_destinations(struct objtool_file *file)
+{
+	struct instruction *insn;
+	struct rela *rela;
+	struct section *dest_sec;
+	unsigned long dest_off;
+
+	for_each_insn(file, insn) {
+		if (insn->type != INSN_JUMP_CONDITIONAL &&
+		    insn->type != INSN_JUMP_UNCONDITIONAL)
+			continue;
+
+		/* skip ignores */
+		if (insn->visited)
+			continue;
+
+		rela = find_rela_by_dest_range(insn->sec, insn->offset,
+					       insn->len);
+		if (!rela) {
+			dest_sec = insn->sec;
+			dest_off = insn->offset + insn->len + insn->immediate;
+		} else if (rela->sym->type == STT_SECTION) {
+			dest_sec = rela->sym->sec;
+			dest_off = rela->addend + 4;
+		} else if (rela->sym->sec->idx) {
+			dest_sec = rela->sym->sec;
+			dest_off = rela->sym->sym.st_value + rela->addend + 4;
+		} else {
+			/* sibling call */
+			insn->jump_dest = 0;
+			continue;
+		}
+
+		insn->jump_dest = find_insn(file, dest_sec, dest_off);
+		if (!insn->jump_dest) {
+
+			/*
+			 * This is a special case where an alt instruction
+			 * jumps past the end of the section.  These are
+			 * handled later in handle_group_alt().
+			 */
+			if (!strcmp(insn->sec->name, ".altinstr_replacement"))
+				continue;
+
+			WARN_FUNC("can't find jump dest instruction at %s+0x%lx",
+				  insn->sec, insn->offset, dest_sec->name,
+				  dest_off);
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Find the destination instructions for all calls.
+ */
+static int add_call_destinations(struct objtool_file *file)
+{
+	struct instruction *insn;
+	unsigned long dest_off;
+	struct rela *rela;
+
+	for_each_insn(file, insn) {
+		if (insn->type != INSN_CALL)
+			continue;
+
+		rela = find_rela_by_dest_range(insn->sec, insn->offset,
+					       insn->len);
+		if (!rela) {
+			dest_off = insn->offset + insn->len + insn->immediate;
+			insn->call_dest = find_symbol_by_offset(insn->sec,
+								dest_off);
+			if (!insn->call_dest) {
+				WARN_FUNC("can't find call dest symbol at offset 0x%lx",
+					  insn->sec, insn->offset, dest_off);
+				return -1;
+			}
+		} else if (rela->sym->type == STT_SECTION) {
+			insn->call_dest = find_symbol_by_offset(rela->sym->sec,
+								rela->addend+4);
+			if (!insn->call_dest ||
+			    insn->call_dest->type != STT_FUNC) {
+				WARN_FUNC("can't find call dest symbol at %s+0x%x",
+					  insn->sec, insn->offset,
+					  rela->sym->sec->name,
+					  rela->addend + 4);
+				return -1;
+			}
+		} else
+			insn->call_dest = rela->sym;
+	}
+
+	return 0;
+}
+
+/*
+ * The .alternatives section requires some extra special care, over and above
+ * what other special sections require:
+ *
+ * 1. Because alternatives are patched in-place, we need to insert a fake jump
+ *    instruction at the end so that validate_branch() skips all the original
+ *    replaced instructions when validating the new instruction path.
+ *
+ * 2. An added wrinkle is that the new instruction length might be zero.  In
+ *    that case the old instructions are replaced with noops.  We simulate that
+ *    by creating a fake jump as the only new instruction.
+ *
+ * 3. In some cases, the alternative section includes an instruction which
+ *    conditionally jumps to the _end_ of the entry.  We have to modify these
+ *    jumps' destinations to point back to .text rather than the end of the
+ *    entry in .altinstr_replacement.
+ *
+ * 4. It has been requested that we don't validate the !POPCNT feature path
+ *    which is a "very very small percentage of machines".
+ */
+static int handle_group_alt(struct objtool_file *file,
+			    struct special_alt *special_alt,
+			    struct instruction *orig_insn,
+			    struct instruction **new_insn)
+{
+	struct instruction *last_orig_insn, *last_new_insn, *insn, *fake_jump;
+	unsigned long dest_off;
+
+	last_orig_insn = NULL;
+	insn = orig_insn;
+	sec_for_each_insn_from(file, insn) {
+		if (insn->offset >= special_alt->orig_off + special_alt->orig_len)
+			break;
+
+		if (special_alt->skip_orig)
+			insn->type = INSN_NOP;
+
+		insn->alt_group = true;
+		last_orig_insn = insn;
+	}
+
+	if (!next_insn_same_sec(file, last_orig_insn)) {
+		WARN("%s: don't know how to handle alternatives at end of section",
+		     special_alt->orig_sec->name);
+		return -1;
+	}
+
+	fake_jump = malloc(sizeof(*fake_jump));
+	if (!fake_jump) {
+		WARN("malloc failed");
+		return -1;
+	}
+	memset(fake_jump, 0, sizeof(*fake_jump));
+	INIT_LIST_HEAD(&fake_jump->alts);
+	fake_jump->sec = special_alt->new_sec;
+	fake_jump->offset = -1;
+	fake_jump->type = INSN_JUMP_UNCONDITIONAL;
+	fake_jump->jump_dest = list_next_entry(last_orig_insn, list);
+
+	if (!special_alt->new_len) {
+		*new_insn = fake_jump;
+		return 0;
+	}
+
+	last_new_insn = NULL;
+	insn = *new_insn;
+	sec_for_each_insn_from(file, insn) {
+		if (insn->offset >= special_alt->new_off + special_alt->new_len)
+			break;
+
+		last_new_insn = insn;
+
+		if (insn->type != INSN_JUMP_CONDITIONAL &&
+		    insn->type != INSN_JUMP_UNCONDITIONAL)
+			continue;
+
+		if (!insn->immediate)
+			continue;
+
+		dest_off = insn->offset + insn->len + insn->immediate;
+		if (dest_off == special_alt->new_off + special_alt->new_len)
+			insn->jump_dest = fake_jump;
+
+		if (!insn->jump_dest) {
+			WARN_FUNC("can't find alternative jump destination",
+				  insn->sec, insn->offset);
+			return -1;
+		}
+	}
+
+	if (!last_new_insn) {
+		WARN_FUNC("can't find last new alternative instruction",
+			  special_alt->new_sec, special_alt->new_off);
+		return -1;
+	}
+
+	list_add(&fake_jump->list, &last_new_insn->list);
+
+	return 0;
+}
+
+/*
+ * A jump table entry can either convert a nop to a jump or a jump to a nop.
+ * If the original instruction is a jump, make the alt entry an effective nop
+ * by just skipping the original instruction.
+ */
+static int handle_jump_alt(struct objtool_file *file,
+			   struct special_alt *special_alt,
+			   struct instruction *orig_insn,
+			   struct instruction **new_insn)
+{
+	if (orig_insn->type == INSN_NOP)
+		return 0;
+
+	if (orig_insn->type != INSN_JUMP_UNCONDITIONAL) {
+		WARN_FUNC("unsupported instruction at jump label",
+			  orig_insn->sec, orig_insn->offset);
+		return -1;
+	}
+
+	*new_insn = list_next_entry(orig_insn, list);
+	return 0;
+}
+
+/*
+ * Read all the special sections which have alternate instructions which can be
+ * patched in or redirected to at runtime.  Each instruction having alternate
+ * instruction(s) has them added to its insn->alts list, which will be
+ * traversed in validate_branch().
+ */
+static int add_special_section_alts(struct objtool_file *file)
+{
+	struct list_head special_alts;
+	struct instruction *orig_insn, *new_insn;
+	struct special_alt *special_alt, *tmp;
+	struct alternative *alt;
+	int ret;
+
+	ret = special_get_alts(file->elf, &special_alts);
+	if (ret)
+		return ret;
+
+	list_for_each_entry_safe(special_alt, tmp, &special_alts, list) {
+		alt = malloc(sizeof(*alt));
+		if (!alt) {
+			WARN("malloc failed");
+			ret = -1;
+			goto out;
+		}
+
+		orig_insn = find_insn(file, special_alt->orig_sec,
+				      special_alt->orig_off);
+		if (!orig_insn) {
+			WARN_FUNC("special: can't find orig instruction",
+				  special_alt->orig_sec, special_alt->orig_off);
+			ret = -1;
+			goto out;
+		}
+
+		new_insn = NULL;
+		if (!special_alt->group || special_alt->new_len) {
+			new_insn = find_insn(file, special_alt->new_sec,
+					     special_alt->new_off);
+			if (!new_insn) {
+				WARN_FUNC("special: can't find new instruction",
+					  special_alt->new_sec,
+					  special_alt->new_off);
+				ret = -1;
+				goto out;
+			}
+		}
+
+		if (special_alt->group) {
+			ret = handle_group_alt(file, special_alt, orig_insn,
+					       &new_insn);
+			if (ret)
+				goto out;
+		} else if (special_alt->jump_or_nop) {
+			ret = handle_jump_alt(file, special_alt, orig_insn,
+					      &new_insn);
+			if (ret)
+				goto out;
+		}
+
+		alt->insn = new_insn;
+		list_add_tail(&alt->list, &orig_insn->alts);
+
+		list_del(&special_alt->list);
+		free(special_alt);
+	}
+
+out:
+	return ret;
+}
+
+static int add_switch_table(struct objtool_file *file, struct symbol *func,
+			    struct instruction *insn, struct rela *table,
+			    struct rela *next_table)
+{
+	struct rela *rela = table;
+	struct instruction *alt_insn;
+	struct alternative *alt;
+
+	list_for_each_entry_from(rela, &file->rodata->rela->rela_list, list) {
+		if (rela == next_table)
+			break;
+
+		if (rela->sym->sec != insn->sec ||
+		    rela->addend <= func->offset ||
+		    rela->addend >= func->offset + func->len)
+			break;
+
+		alt_insn = find_insn(file, insn->sec, rela->addend);
+		if (!alt_insn) {
+			WARN("%s: can't find instruction at %s+0x%x",
+			     file->rodata->rela->name, insn->sec->name,
+			     rela->addend);
+			return -1;
+		}
+
+		alt = malloc(sizeof(*alt));
+		if (!alt) {
+			WARN("malloc failed");
+			return -1;
+		}
+
+		alt->insn = alt_insn;
+		list_add_tail(&alt->list, &insn->alts);
+	}
+
+	return 0;
+}
+
+static int add_func_switch_tables(struct objtool_file *file,
+				  struct symbol *func)
+{
+	struct instruction *insn, *prev_jump;
+	struct rela *text_rela, *rodata_rela, *prev_rela;
+	int ret;
+
+	prev_jump = NULL;
+
+	func_for_each_insn(file, func, insn) {
+		if (insn->type != INSN_JUMP_DYNAMIC)
+			continue;
+
+		text_rela = find_rela_by_dest_range(insn->sec, insn->offset,
+						    insn->len);
+		if (!text_rela || text_rela->sym != file->rodata->sym)
+			continue;
+
+		/* common case: jmpq *[addr](,%rax,8) */
+		rodata_rela = find_rela_by_dest(file->rodata,
+						text_rela->addend);
+
+		/*
+		 * rare case:   jmpq *[addr](%rip)
+		 *
+		 * This check is for a rare gcc quirk, currently only seen in
+		 * three driver functions in the kernel, only with certain
+		 * obscure non-distro configs.
+		 *
+		 * As part of an optimization, gcc makes a copy of an existing
+		 * switch jump table, modifies it, and then hard-codes the jump
+		 * (albeit with an indirect jump) to use a single entry in the
+		 * table.  The rest of the jump table and some of its jump
+		 * targets remain as dead code.
+		 *
+		 * In such a case we can just crudely ignore all unreachable
+		 * instruction warnings for the entire object file.  Ideally we
+		 * would just ignore them for the function, but that would
+		 * require redesigning the code quite a bit.  And honestly
+		 * that's just not worth doing: unreachable instruction
+		 * warnings are of questionable value anyway, and this is such
+		 * a rare issue.
+		 *
+		 * kbuild reports:
+		 * - https://lkml.kernel.org/r/201603231906.LWcVUpxm%25fengguang.wu@intel.com
+		 * - https://lkml.kernel.org/r/201603271114.K9i45biy%25fengguang.wu@intel.com
+		 * - https://lkml.kernel.org/r/201603291058.zuJ6ben1%25fengguang.wu@intel.com
+		 *
+		 * gcc bug:
+		 * - https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70604
+		 */
+		if (!rodata_rela) {
+			rodata_rela = find_rela_by_dest(file->rodata,
+							text_rela->addend + 4);
+			if (rodata_rela)
+				file->ignore_unreachables = true;
+		}
+
+		if (!rodata_rela)
+			continue;
+
+		/*
+		 * We found a switch table, but we don't know yet how big it
+		 * is.  Don't add it until we reach the end of the function or
+		 * the beginning of another switch table in the same function.
+		 */
+		if (prev_jump) {
+			ret = add_switch_table(file, func, prev_jump, prev_rela,
+					       rodata_rela);
+			if (ret)
+				return ret;
+		}
+
+		prev_jump = insn;
+		prev_rela = rodata_rela;
+	}
+
+	if (prev_jump) {
+		ret = add_switch_table(file, func, prev_jump, prev_rela, NULL);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * For some switch statements, gcc generates a jump table in the .rodata
+ * section which contains a list of addresses within the function to jump to.
+ * This finds these jump tables and adds them to the insn->alts lists.
+ */
+static int add_switch_table_alts(struct objtool_file *file)
+{
+	struct section *sec;
+	struct symbol *func;
+	int ret;
+
+	if (!file->rodata || !file->rodata->rela)
+		return 0;
+
+	list_for_each_entry(sec, &file->elf->sections, list) {
+		list_for_each_entry(func, &sec->symbol_list, list) {
+			if (func->type != STT_FUNC)
+				continue;
+
+			ret = add_func_switch_tables(file, func);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int decode_sections(struct objtool_file *file)
+{
+	int ret;
+
+	ret = decode_instructions(file);
+	if (ret)
+		return ret;
+
+	add_ignores(file);
+
+	ret = add_jump_destinations(file);
+	if (ret)
+		return ret;
+
+	ret = add_call_destinations(file);
+	if (ret)
+		return ret;
+
+	ret = add_special_section_alts(file);
+	if (ret)
+		return ret;
+
+	ret = add_switch_table_alts(file);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static bool is_fentry_call(struct instruction *insn)
+{
+	if (insn->type == INSN_CALL &&
+	    insn->call_dest->type == STT_NOTYPE &&
+	    !strcmp(insn->call_dest->name, "__fentry__"))
+		return true;
+
+	return false;
+}
+
+static bool has_modified_stack_frame(struct instruction *insn)
+{
+	return (insn->state & STATE_FP_SAVED) ||
+	       (insn->state & STATE_FP_SETUP);
+}
+
+static bool has_valid_stack_frame(struct instruction *insn)
+{
+	return (insn->state & STATE_FP_SAVED) &&
+	       (insn->state & STATE_FP_SETUP);
+}
+
+static unsigned int frame_state(unsigned long state)
+{
+	return (state & (STATE_FP_SAVED | STATE_FP_SETUP));
+}
+
+/*
+ * Follow the branch starting at the given instruction, and recursively follow
+ * any other branches (jumps).  Meanwhile, track the frame pointer state at
+ * each instruction and validate all the rules described in
+ * tools/objtool/Documentation/stack-validation.txt.
+ */
+static int validate_branch(struct objtool_file *file,
+			   struct instruction *first, unsigned char first_state)
+{
+	struct alternative *alt;
+	struct instruction *insn;
+	struct section *sec;
+	struct symbol *func = NULL;
+	unsigned char state;
+	int ret;
+
+	insn = first;
+	sec = insn->sec;
+	state = first_state;
+
+	if (insn->alt_group && list_empty(&insn->alts)) {
+		WARN_FUNC("don't know how to handle branch to middle of alternative instruction group",
+			  sec, insn->offset);
+		return 1;
+	}
+
+	while (1) {
+		if (file->c_file && insn->func) {
+			if (func && func != insn->func) {
+				WARN("%s() falls through to next function %s()",
+				     func->name, insn->func->name);
+				return 1;
+			}
+
+			func = insn->func;
+		}
+
+		if (insn->visited) {
+			if (frame_state(insn->state) != frame_state(state)) {
+				WARN_FUNC("frame pointer state mismatch",
+					  sec, insn->offset);
+				return 1;
+			}
+
+			return 0;
+		}
+
+		insn->visited = true;
+		insn->state = state;
+
+		list_for_each_entry(alt, &insn->alts, list) {
+			ret = validate_branch(file, alt->insn, state);
+			if (ret)
+				return 1;
+		}
+
+		switch (insn->type) {
+
+		case INSN_FP_SAVE:
+			if (!nofp) {
+				if (state & STATE_FP_SAVED) {
+					WARN_FUNC("duplicate frame pointer save",
+						  sec, insn->offset);
+					return 1;
+				}
+				state |= STATE_FP_SAVED;
+			}
+			break;
+
+		case INSN_FP_SETUP:
+			if (!nofp) {
+				if (state & STATE_FP_SETUP) {
+					WARN_FUNC("duplicate frame pointer setup",
+						  sec, insn->offset);
+					return 1;
+				}
+				state |= STATE_FP_SETUP;
+			}
+			break;
+
+		case INSN_FP_RESTORE:
+			if (!nofp) {
+				if (has_valid_stack_frame(insn))
+					state &= ~STATE_FP_SETUP;
+
+				state &= ~STATE_FP_SAVED;
+			}
+			break;
+
+		case INSN_RETURN:
+			if (!nofp && has_modified_stack_frame(insn)) {
+				WARN_FUNC("return without frame pointer restore",
+					  sec, insn->offset);
+				return 1;
+			}
+			return 0;
+
+		case INSN_CALL:
+			if (is_fentry_call(insn)) {
+				state |= STATE_FENTRY;
+				break;
+			}
+
+			ret = dead_end_function(file, insn->call_dest);
+			if (ret == 1)
+				return 0;
+			if (ret == -1)
+				return 1;
+
+			/* fallthrough */
+		case INSN_CALL_DYNAMIC:
+			if (!nofp && !has_valid_stack_frame(insn)) {
+				WARN_FUNC("call without frame pointer save/setup",
+					  sec, insn->offset);
+				return 1;
+			}
+			break;
+
+		case INSN_JUMP_CONDITIONAL:
+		case INSN_JUMP_UNCONDITIONAL:
+			if (insn->jump_dest) {
+				ret = validate_branch(file, insn->jump_dest,
+						      state);
+				if (ret)
+					return 1;
+			} else if (has_modified_stack_frame(insn)) {
+				WARN_FUNC("sibling call from callable instruction with changed frame pointer",
+					  sec, insn->offset);
+				return 1;
+			} /* else it's a sibling call */
+
+			if (insn->type == INSN_JUMP_UNCONDITIONAL)
+				return 0;
+
+			break;
+
+		case INSN_JUMP_DYNAMIC:
+			if (list_empty(&insn->alts) &&
+			    has_modified_stack_frame(insn)) {
+				WARN_FUNC("sibling call from callable instruction with changed frame pointer",
+					  sec, insn->offset);
+				return 1;
+			}
+
+			return 0;
+
+		case INSN_BUG:
+			return 0;
+
+		default:
+			break;
+		}
+
+		insn = next_insn_same_sec(file, insn);
+		if (!insn) {
+			WARN("%s: unexpected end of section", sec->name);
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+static bool is_gcov_insn(struct instruction *insn)
+{
+	struct rela *rela;
+	struct section *sec;
+	struct symbol *sym;
+	unsigned long offset;
+
+	rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len);
+	if (!rela)
+		return false;
+
+	if (rela->sym->type != STT_SECTION)
+		return false;
+
+	sec = rela->sym->sec;
+	offset = rela->addend + insn->offset + insn->len - rela->offset;
+
+	list_for_each_entry(sym, &sec->symbol_list, list) {
+		if (sym->type != STT_OBJECT)
+			continue;
+
+		if (offset >= sym->offset && offset < sym->offset + sym->len)
+			return (!memcmp(sym->name, "__gcov0.", 8));
+	}
+
+	return false;
+}
+
+static bool is_kasan_insn(struct instruction *insn)
+{
+	return (insn->type == INSN_CALL &&
+		!strcmp(insn->call_dest->name, "__asan_handle_no_return"));
+}
+
+static bool is_ubsan_insn(struct instruction *insn)
+{
+	return (insn->type == INSN_CALL &&
+		!strcmp(insn->call_dest->name,
+			"__ubsan_handle_builtin_unreachable"));
+}
+
+static bool ignore_unreachable_insn(struct symbol *func,
+				    struct instruction *insn)
+{
+	int i;
+
+	if (insn->type == INSN_NOP)
+		return true;
+
+	if (is_gcov_insn(insn))
+		return true;
+
+	/*
+	 * Check if this (or a subsequent) instruction is related to
+	 * CONFIG_UBSAN or CONFIG_KASAN.
+	 *
+	 * End the search at 5 instructions to avoid going into the weeds.
+	 */
+	for (i = 0; i < 5; i++) {
+
+		if (is_kasan_insn(insn) || is_ubsan_insn(insn))
+			return true;
+
+		if (insn->type == INSN_JUMP_UNCONDITIONAL && insn->jump_dest) {
+			insn = insn->jump_dest;
+			continue;
+		}
+
+		if (insn->offset + insn->len >= func->offset + func->len)
+			break;
+		insn = list_next_entry(insn, list);
+	}
+
+	return false;
+}
+
+static int validate_functions(struct objtool_file *file)
+{
+	struct section *sec;
+	struct symbol *func;
+	struct instruction *insn;
+	int ret, warnings = 0;
+
+	list_for_each_entry(sec, &file->elf->sections, list) {
+		list_for_each_entry(func, &sec->symbol_list, list) {
+			if (func->type != STT_FUNC)
+				continue;
+
+			insn = find_insn(file, sec, func->offset);
+			if (!insn)
+				continue;
+
+			ret = validate_branch(file, insn, 0);
+			warnings += ret;
+		}
+	}
+
+	list_for_each_entry(sec, &file->elf->sections, list) {
+		list_for_each_entry(func, &sec->symbol_list, list) {
+			if (func->type != STT_FUNC)
+				continue;
+
+			func_for_each_insn(file, func, insn) {
+				if (insn->visited)
+					continue;
+
+				insn->visited = true;
+
+				if (file->ignore_unreachables || warnings ||
+				    ignore_unreachable_insn(func, insn))
+					continue;
+
+				WARN_FUNC("function has unreachable instruction", insn->sec, insn->offset);
+				warnings++;
+			}
+		}
+	}
+
+	return warnings;
+}
+
+static int validate_uncallable_instructions(struct objtool_file *file)
+{
+	struct instruction *insn;
+	int warnings = 0;
+
+	for_each_insn(file, insn) {
+		if (!insn->visited && insn->type == INSN_RETURN) {
+			WARN_FUNC("return instruction outside of a callable function",
+				  insn->sec, insn->offset);
+			warnings++;
+		}
+	}
+
+	return warnings;
+}
+
+static void cleanup(struct objtool_file *file)
+{
+	struct instruction *insn, *tmpinsn;
+	struct alternative *alt, *tmpalt;
+
+	list_for_each_entry_safe(insn, tmpinsn, &file->insn_list, list) {
+		list_for_each_entry_safe(alt, tmpalt, &insn->alts, list) {
+			list_del(&alt->list);
+			free(alt);
+		}
+		list_del(&insn->list);
+		hash_del(&insn->hash);
+		free(insn);
+	}
+	elf_close(file->elf);
+}
+
+const char * const check_usage[] = {
+	"objtool check [<options>] file.o",
+	NULL,
+};
+
+int cmd_check(int argc, const char **argv)
+{
+	struct objtool_file file;
+	int ret, warnings = 0;
+
+	const struct option options[] = {
+		OPT_BOOLEAN('f', "no-fp", &nofp, "Skip frame pointer validation"),
+		OPT_END(),
+	};
+
+	argc = parse_options(argc, argv, options, check_usage, 0);
+
+	if (argc != 1)
+		usage_with_options(check_usage, options);
+
+	objname = argv[0];
+
+	file.elf = elf_open(objname);
+	if (!file.elf) {
+		fprintf(stderr, "error reading elf file %s\n", objname);
+		return 1;
+	}
+
+	INIT_LIST_HEAD(&file.insn_list);
+	hash_init(file.insn_hash);
+	file.whitelist = find_section_by_name(file.elf, "__func_stack_frame_non_standard");
+	file.rodata = find_section_by_name(file.elf, ".rodata");
+	file.ignore_unreachables = false;
+	file.c_file = find_section_by_name(file.elf, ".comment");
+
+	ret = decode_sections(&file);
+	if (ret < 0)
+		goto out;
+	warnings += ret;
+
+	ret = validate_functions(&file);
+	if (ret < 0)
+		goto out;
+	warnings += ret;
+
+	ret = validate_uncallable_instructions(&file);
+	if (ret < 0)
+		goto out;
+	warnings += ret;
+
+out:
+	cleanup(&file);
+
+	/* ignore warnings for now until we get all the code cleaned up */
+	if (ret || warnings)
+		return 0;
+	return 0;
+}
diff --git a/tools/objtool/builtin.h b/tools/objtool/builtin.h
new file mode 100644
index 000000000..34d2ba78a
--- /dev/null
+++ b/tools/objtool/builtin.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2015 Josh Poimboeuf <jpoimboe@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef _BUILTIN_H
+#define _BUILTIN_H
+
+extern int cmd_check(int argc, const char **argv);
+
+#endif /* _BUILTIN_H */
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
new file mode 100644
index 000000000..e11f6b69c
--- /dev/null
+++ b/tools/objtool/elf.c
@@ -0,0 +1,412 @@
+/*
+ * elf.c - ELF access library
+ *
+ * Adapted from kpatch (https://github.com/dynup/kpatch):
+ * Copyright (C) 2013-2015 Josh Poimboeuf <jpoimboe@redhat.com>
+ * Copyright (C) 2014 Seth Jennings <sjenning@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "elf.h"
+#include "warn.h"
+
+struct section *find_section_by_name(struct elf *elf, const char *name)
+{
+	struct section *sec;
+
+	list_for_each_entry(sec, &elf->sections, list)
+		if (!strcmp(sec->name, name))
+			return sec;
+
+	return NULL;
+}
+
+static struct section *find_section_by_index(struct elf *elf,
+					     unsigned int idx)
+{
+	struct section *sec;
+
+	list_for_each_entry(sec, &elf->sections, list)
+		if (sec->idx == idx)
+			return sec;
+
+	return NULL;
+}
+
+static struct symbol *find_symbol_by_index(struct elf *elf, unsigned int idx)
+{
+	struct section *sec;
+	struct symbol *sym;
+
+	list_for_each_entry(sec, &elf->sections, list)
+		hash_for_each_possible(sec->symbol_hash, sym, hash, idx)
+			if (sym->idx == idx)
+				return sym;
+
+	return NULL;
+}
+
+struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset)
+{
+	struct symbol *sym;
+
+	list_for_each_entry(sym, &sec->symbol_list, list)
+		if (sym->type != STT_SECTION &&
+		    sym->offset == offset)
+			return sym;
+
+	return NULL;
+}
+
+struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
+				     unsigned int len)
+{
+	struct rela *rela;
+	unsigned long o;
+
+	if (!sec->rela)
+		return NULL;
+
+	for (o = offset; o < offset + len; o++)
+		hash_for_each_possible(sec->rela->rela_hash, rela, hash, o)
+			if (rela->offset == o)
+				return rela;
+
+	return NULL;
+}
+
+struct rela *find_rela_by_dest(struct section *sec, unsigned long offset)
+{
+	return find_rela_by_dest_range(sec, offset, 1);
+}
+
+struct symbol *find_containing_func(struct section *sec, unsigned long offset)
+{
+	struct symbol *func;
+
+	list_for_each_entry(func, &sec->symbol_list, list)
+		if (func->type == STT_FUNC && offset >= func->offset &&
+		    offset < func->offset + func->len)
+			return func;
+
+	return NULL;
+}
+
+static int read_sections(struct elf *elf)
+{
+	Elf_Scn *s = NULL;
+	struct section *sec;
+	size_t shstrndx, sections_nr;
+	int i;
+
+	if (elf_getshdrnum(elf->elf, &sections_nr)) {
+		perror("elf_getshdrnum");
+		return -1;
+	}
+
+	if (elf_getshdrstrndx(elf->elf, &shstrndx)) {
+		perror("elf_getshdrstrndx");
+		return -1;
+	}
+
+	for (i = 0; i < sections_nr; i++) {
+		sec = malloc(sizeof(*sec));
+		if (!sec) {
+			perror("malloc");
+			return -1;
+		}
+		memset(sec, 0, sizeof(*sec));
+
+		INIT_LIST_HEAD(&sec->symbol_list);
+		INIT_LIST_HEAD(&sec->rela_list);
+		hash_init(sec->rela_hash);
+		hash_init(sec->symbol_hash);
+
+		list_add_tail(&sec->list, &elf->sections);
+
+		s = elf_getscn(elf->elf, i);
+		if (!s) {
+			perror("elf_getscn");
+			return -1;
+		}
+
+		sec->idx = elf_ndxscn(s);
+
+		if (!gelf_getshdr(s, &sec->sh)) {
+			perror("gelf_getshdr");
+			return -1;
+		}
+
+		sec->name = elf_strptr(elf->elf, shstrndx, sec->sh.sh_name);
+		if (!sec->name) {
+			perror("elf_strptr");
+			return -1;
+		}
+
+		sec->elf_data = elf_getdata(s, NULL);
+		if (!sec->elf_data) {
+			perror("elf_getdata");
+			return -1;
+		}
+
+		if (sec->elf_data->d_off != 0 ||
+		    sec->elf_data->d_size != sec->sh.sh_size) {
+			WARN("unexpected data attributes for %s", sec->name);
+			return -1;
+		}
+
+		sec->data = (unsigned long)sec->elf_data->d_buf;
+		sec->len = sec->elf_data->d_size;
+	}
+
+	/* sanity check, one more call to elf_nextscn() should return NULL */
+	if (elf_nextscn(elf->elf, s)) {
+		WARN("section entry mismatch");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int read_symbols(struct elf *elf)
+{
+	struct section *symtab;
+	struct symbol *sym;
+	struct list_head *entry, *tmp;
+	int symbols_nr, i;
+
+	symtab = find_section_by_name(elf, ".symtab");
+	if (!symtab) {
+		WARN("missing symbol table");
+		return -1;
+	}
+
+	symbols_nr = symtab->sh.sh_size / symtab->sh.sh_entsize;
+
+	for (i = 0; i < symbols_nr; i++) {
+		sym = malloc(sizeof(*sym));
+		if (!sym) {
+			perror("malloc");
+			return -1;
+		}
+		memset(sym, 0, sizeof(*sym));
+
+		sym->idx = i;
+
+		if (!gelf_getsym(symtab->elf_data, i, &sym->sym)) {
+			perror("gelf_getsym");
+			goto err;
+		}
+
+		sym->name = elf_strptr(elf->elf, symtab->sh.sh_link,
+				       sym->sym.st_name);
+		if (!sym->name) {
+			perror("elf_strptr");
+			goto err;
+		}
+
+		sym->type = GELF_ST_TYPE(sym->sym.st_info);
+		sym->bind = GELF_ST_BIND(sym->sym.st_info);
+
+		if (sym->sym.st_shndx > SHN_UNDEF &&
+		    sym->sym.st_shndx < SHN_LORESERVE) {
+			sym->sec = find_section_by_index(elf,
+							 sym->sym.st_shndx);
+			if (!sym->sec) {
+				WARN("couldn't find section for symbol %s",
+				     sym->name);
+				goto err;
+			}
+			if (sym->type == STT_SECTION) {
+				sym->name = sym->sec->name;
+				sym->sec->sym = sym;
+			}
+		} else
+			sym->sec = find_section_by_index(elf, 0);
+
+		sym->offset = sym->sym.st_value;
+		sym->len = sym->sym.st_size;
+
+		/* sorted insert into a per-section list */
+		entry = &sym->sec->symbol_list;
+		list_for_each_prev(tmp, &sym->sec->symbol_list) {
+			struct symbol *s;
+
+			s = list_entry(tmp, struct symbol, list);
+
+			if (sym->offset > s->offset) {
+				entry = tmp;
+				break;
+			}
+
+			if (sym->offset == s->offset && sym->len >= s->len) {
+				entry = tmp;
+				break;
+			}
+		}
+		list_add(&sym->list, entry);
+		hash_add(sym->sec->symbol_hash, &sym->hash, sym->idx);
+	}
+
+	return 0;
+
+err:
+	free(sym);
+	return -1;
+}
+
+static int read_relas(struct elf *elf)
+{
+	struct section *sec;
+	struct rela *rela;
+	int i;
+	unsigned int symndx;
+
+	list_for_each_entry(sec, &elf->sections, list) {
+		if (sec->sh.sh_type != SHT_RELA)
+			continue;
+
+		sec->base = find_section_by_name(elf, sec->name + 5);
+		if (!sec->base) {
+			WARN("can't find base section for rela section %s",
+			     sec->name);
+			return -1;
+		}
+
+		sec->base->rela = sec;
+
+		for (i = 0; i < sec->sh.sh_size / sec->sh.sh_entsize; i++) {
+			rela = malloc(sizeof(*rela));
+			if (!rela) {
+				perror("malloc");
+				return -1;
+			}
+			memset(rela, 0, sizeof(*rela));
+
+			if (!gelf_getrela(sec->elf_data, i, &rela->rela)) {
+				perror("gelf_getrela");
+				return -1;
+			}
+
+			rela->type = GELF_R_TYPE(rela->rela.r_info);
+			rela->addend = rela->rela.r_addend;
+			rela->offset = rela->rela.r_offset;
+			symndx = GELF_R_SYM(rela->rela.r_info);
+			rela->sym = find_symbol_by_index(elf, symndx);
+			if (!rela->sym) {
+				WARN("can't find rela entry symbol %d for %s",
+				     symndx, sec->name);
+				return -1;
+			}
+
+			list_add_tail(&rela->list, &sec->rela_list);
+			hash_add(sec->rela_hash, &rela->hash, rela->offset);
+
+		}
+	}
+
+	return 0;
+}
+
+struct elf *elf_open(const char *name)
+{
+	struct elf *elf;
+
+	elf_version(EV_CURRENT);
+
+	elf = malloc(sizeof(*elf));
+	if (!elf) {
+		perror("malloc");
+		return NULL;
+	}
+	memset(elf, 0, sizeof(*elf));
+
+	INIT_LIST_HEAD(&elf->sections);
+
+	elf->name = strdup(name);
+	if (!elf->name) {
+		perror("strdup");
+		goto err;
+	}
+
+	elf->fd = open(name, O_RDONLY);
+	if (elf->fd == -1) {
+		perror("open");
+		goto err;
+	}
+
+	elf->elf = elf_begin(elf->fd, ELF_C_READ_MMAP, NULL);
+	if (!elf->elf) {
+		perror("elf_begin");
+		goto err;
+	}
+
+	if (!gelf_getehdr(elf->elf, &elf->ehdr)) {
+		perror("gelf_getehdr");
+		goto err;
+	}
+
+	if (read_sections(elf))
+		goto err;
+
+	if (read_symbols(elf))
+		goto err;
+
+	if (read_relas(elf))
+		goto err;
+
+	return elf;
+
+err:
+	elf_close(elf);
+	return NULL;
+}
+
+void elf_close(struct elf *elf)
+{
+	struct section *sec, *tmpsec;
+	struct symbol *sym, *tmpsym;
+	struct rela *rela, *tmprela;
+
+	list_for_each_entry_safe(sec, tmpsec, &elf->sections, list) {
+		list_for_each_entry_safe(sym, tmpsym, &sec->symbol_list, list) {
+			list_del(&sym->list);
+			hash_del(&sym->hash);
+			free(sym);
+		}
+		list_for_each_entry_safe(rela, tmprela, &sec->rela_list, list) {
+			list_del(&rela->list);
+			hash_del(&rela->hash);
+			free(rela);
+		}
+		list_del(&sec->list);
+		free(sec);
+	}
+	if (elf->name)
+		free(elf->name);
+	if (elf->fd > 0)
+		close(elf->fd);
+	if (elf->elf)
+		elf_end(elf->elf);
+	free(elf);
+}
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
new file mode 100644
index 000000000..aa1ff6596
--- /dev/null
+++ b/tools/objtool/elf.h
@@ -0,0 +1,90 @@
+/*
+ * Copyright (C) 2015 Josh Poimboeuf <jpoimboe@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _OBJTOOL_ELF_H
+#define _OBJTOOL_ELF_H
+
+#include <stdio.h>
+#include <gelf.h>
+#include <linux/list.h>
+#include <linux/hashtable.h>
+
+#ifdef LIBELF_USE_DEPRECATED
+# define elf_getshdrnum    elf_getshnum
+# define elf_getshdrstrndx elf_getshstrndx
+#endif
+
+struct section {
+	struct list_head list;
+	GElf_Shdr sh;
+	struct list_head symbol_list;
+	DECLARE_HASHTABLE(symbol_hash, 8);
+	struct list_head rela_list;
+	DECLARE_HASHTABLE(rela_hash, 16);
+	struct section *base, *rela;
+	struct symbol *sym;
+	Elf_Data *elf_data;
+	char *name;
+	int idx;
+	unsigned long data;
+	unsigned int len;
+};
+
+struct symbol {
+	struct list_head list;
+	struct hlist_node hash;
+	GElf_Sym sym;
+	struct section *sec;
+	char *name;
+	unsigned int idx;
+	unsigned char bind, type;
+	unsigned long offset;
+	unsigned int len;
+};
+
+struct rela {
+	struct list_head list;
+	struct hlist_node hash;
+	GElf_Rela rela;
+	struct symbol *sym;
+	unsigned int type;
+	unsigned long offset;
+	int addend;
+};
+
+struct elf {
+	Elf *elf;
+	GElf_Ehdr ehdr;
+	int fd;
+	char *name;
+	struct list_head sections;
+	DECLARE_HASHTABLE(rela_hash, 16);
+};
+
+
+struct elf *elf_open(const char *name);
+struct section *find_section_by_name(struct elf *elf, const char *name);
+struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset);
+struct rela *find_rela_by_dest(struct section *sec, unsigned long offset);
+struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
+				     unsigned int len);
+struct symbol *find_containing_func(struct section *sec, unsigned long offset);
+void elf_close(struct elf *elf);
+
+
+
+#endif /* _OBJTOOL_ELF_H */
diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c
new file mode 100644
index 000000000..46c326db4
--- /dev/null
+++ b/tools/objtool/objtool.c
@@ -0,0 +1,136 @@
+/*
+ * Copyright (C) 2015 Josh Poimboeuf <jpoimboe@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * objtool:
+ *
+ * The 'check' subcmd analyzes every .o file and ensures the validity of its
+ * stack trace metadata.  It enforces a set of rules on asm code and C inline
+ * assembly code so that stack traces can be reliable.
+ *
+ * For more information, see tools/objtool/Documentation/stack-validation.txt.
+ */
+
+#include <stdio.h>
+#include <stdbool.h>
+#include <string.h>
+#include <stdlib.h>
+#include <subcmd/exec-cmd.h>
+#include <subcmd/pager.h>
+
+#include "builtin.h"
+
+#define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0]))
+
+struct cmd_struct {
+	const char *name;
+	int (*fn)(int, const char **);
+	const char *help;
+};
+
+static const char objtool_usage_string[] =
+	"objtool [OPTIONS] COMMAND [ARGS]";
+
+static struct cmd_struct objtool_cmds[] = {
+	{"check",	cmd_check,	"Perform stack metadata validation on an object file" },
+};
+
+bool help;
+
+static void cmd_usage(void)
+{
+	unsigned int i, longest = 0;
+
+	printf("\n usage: %s\n\n", objtool_usage_string);
+
+	for (i = 0; i < ARRAY_SIZE(objtool_cmds); i++) {
+		if (longest < strlen(objtool_cmds[i].name))
+			longest = strlen(objtool_cmds[i].name);
+	}
+
+	puts(" Commands:");
+	for (i = 0; i < ARRAY_SIZE(objtool_cmds); i++) {
+		printf("   %-*s   ", longest, objtool_cmds[i].name);
+		puts(objtool_cmds[i].help);
+	}
+
+	printf("\n");
+
+	exit(1);
+}
+
+static void handle_options(int *argc, const char ***argv)
+{
+	while (*argc > 0) {
+		const char *cmd = (*argv)[0];
+
+		if (cmd[0] != '-')
+			break;
+
+		if (!strcmp(cmd, "--help") || !strcmp(cmd, "-h")) {
+			help = true;
+			break;
+		} else {
+			fprintf(stderr, "Unknown option: %s\n", cmd);
+			fprintf(stderr, "\n Usage: %s\n",
+				objtool_usage_string);
+			exit(1);
+		}
+
+		(*argv)++;
+		(*argc)--;
+	}
+}
+
+static void handle_internal_command(int argc, const char **argv)
+{
+	const char *cmd = argv[0];
+	unsigned int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(objtool_cmds); i++) {
+		struct cmd_struct *p = objtool_cmds+i;
+
+		if (strcmp(p->name, cmd))
+			continue;
+
+		ret = p->fn(argc, argv);
+
+		exit(ret);
+	}
+
+	cmd_usage();
+}
+
+int main(int argc, const char **argv)
+{
+	static const char *UNUSED = "OBJTOOL_NOT_IMPLEMENTED";
+
+	/* libsubcmd init */
+	exec_cmd_init("objtool", UNUSED, UNUSED, UNUSED);
+	pager_init(UNUSED);
+
+	argv++;
+	argc--;
+	handle_options(&argc, &argv);
+
+	if (!argc || help)
+		cmd_usage();
+
+	handle_internal_command(argc, argv);
+
+	return 0;
+}
diff --git a/tools/objtool/special.c b/tools/objtool/special.c
new file mode 100644
index 000000000..bff8abb3a
--- /dev/null
+++ b/tools/objtool/special.c
@@ -0,0 +1,193 @@
+/*
+ * Copyright (C) 2015 Josh Poimboeuf <jpoimboe@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * This file reads all the special sections which have alternate instructions
+ * which can be patched in or redirected to at runtime.
+ */
+
+#include <stdlib.h>
+#include <string.h>
+
+#include "special.h"
+#include "warn.h"
+
+#define EX_ENTRY_SIZE		12
+#define EX_ORIG_OFFSET		0
+#define EX_NEW_OFFSET		4
+
+#define JUMP_ENTRY_SIZE		24
+#define JUMP_ORIG_OFFSET	0
+#define JUMP_NEW_OFFSET		8
+
+#define ALT_ENTRY_SIZE		13
+#define ALT_ORIG_OFFSET		0
+#define ALT_NEW_OFFSET		4
+#define ALT_FEATURE_OFFSET	8
+#define ALT_ORIG_LEN_OFFSET	10
+#define ALT_NEW_LEN_OFFSET	11
+
+#define X86_FEATURE_POPCNT (4*32+23)
+
+struct special_entry {
+	const char *sec;
+	bool group, jump_or_nop;
+	unsigned char size, orig, new;
+	unsigned char orig_len, new_len; /* group only */
+	unsigned char feature; /* ALTERNATIVE macro CPU feature */
+};
+
+struct special_entry entries[] = {
+	{
+		.sec = ".altinstructions",
+		.group = true,
+		.size = ALT_ENTRY_SIZE,
+		.orig = ALT_ORIG_OFFSET,
+		.orig_len = ALT_ORIG_LEN_OFFSET,
+		.new = ALT_NEW_OFFSET,
+		.new_len = ALT_NEW_LEN_OFFSET,
+		.feature = ALT_FEATURE_OFFSET,
+	},
+	{
+		.sec = "__jump_table",
+		.jump_or_nop = true,
+		.size = JUMP_ENTRY_SIZE,
+		.orig = JUMP_ORIG_OFFSET,
+		.new = JUMP_NEW_OFFSET,
+	},
+	{
+		.sec = "__ex_table",
+		.size = EX_ENTRY_SIZE,
+		.orig = EX_ORIG_OFFSET,
+		.new = EX_NEW_OFFSET,
+	},
+	{},
+};
+
+static int get_alt_entry(struct elf *elf, struct special_entry *entry,
+			 struct section *sec, int idx,
+			 struct special_alt *alt)
+{
+	struct rela *orig_rela, *new_rela;
+	unsigned long offset;
+
+	offset = idx * entry->size;
+
+	alt->group = entry->group;
+	alt->jump_or_nop = entry->jump_or_nop;
+
+	if (alt->group) {
+		alt->orig_len = *(unsigned char *)(sec->data + offset +
+						   entry->orig_len);
+		alt->new_len = *(unsigned char *)(sec->data + offset +
+						  entry->new_len);
+	}
+
+	if (entry->feature) {
+		unsigned short feature;
+
+		feature = *(unsigned short *)(sec->data + offset +
+					      entry->feature);
+
+		/*
+		 * It has been requested that we don't validate the !POPCNT
+		 * feature path which is a "very very small percentage of
+		 * machines".
+		 */
+		if (feature == X86_FEATURE_POPCNT)
+			alt->skip_orig = true;
+	}
+
+	orig_rela = find_rela_by_dest(sec, offset + entry->orig);
+	if (!orig_rela) {
+		WARN_FUNC("can't find orig rela", sec, offset + entry->orig);
+		return -1;
+	}
+	if (orig_rela->sym->type != STT_SECTION) {
+		WARN_FUNC("don't know how to handle non-section rela symbol %s",
+			   sec, offset + entry->orig, orig_rela->sym->name);
+		return -1;
+	}
+
+	alt->orig_sec = orig_rela->sym->sec;
+	alt->orig_off = orig_rela->addend;
+
+	if (!entry->group || alt->new_len) {
+		new_rela = find_rela_by_dest(sec, offset + entry->new);
+		if (!new_rela) {
+			WARN_FUNC("can't find new rela",
+				  sec, offset + entry->new);
+			return -1;
+		}
+
+		alt->new_sec = new_rela->sym->sec;
+		alt->new_off = (unsigned int)new_rela->addend;
+
+		/* _ASM_EXTABLE_EX hack */
+		if (alt->new_off >= 0x7ffffff0)
+			alt->new_off -= 0x7ffffff0;
+	}
+
+	return 0;
+}
+
+/*
+ * Read all the special sections and create a list of special_alt structs which
+ * describe all the alternate instructions which can be patched in or
+ * redirected to at runtime.
+ */
+int special_get_alts(struct elf *elf, struct list_head *alts)
+{
+	struct special_entry *entry;
+	struct section *sec;
+	unsigned int nr_entries;
+	struct special_alt *alt;
+	int idx, ret;
+
+	INIT_LIST_HEAD(alts);
+
+	for (entry = entries; entry->sec; entry++) {
+		sec = find_section_by_name(elf, entry->sec);
+		if (!sec)
+			continue;
+
+		if (sec->len % entry->size != 0) {
+			WARN("%s size not a multiple of %d",
+			     sec->name, entry->size);
+			return -1;
+		}
+
+		nr_entries = sec->len / entry->size;
+
+		for (idx = 0; idx < nr_entries; idx++) {
+			alt = malloc(sizeof(*alt));
+			if (!alt) {
+				WARN("malloc failed");
+				return -1;
+			}
+			memset(alt, 0, sizeof(*alt));
+
+			ret = get_alt_entry(elf, entry, sec, idx, alt);
+			if (ret)
+				return ret;
+
+			list_add_tail(&alt->list, alts);
+		}
+	}
+
+	return 0;
+}
diff --git a/tools/objtool/special.h b/tools/objtool/special.h
new file mode 100644
index 000000000..fad1d092f
--- /dev/null
+++ b/tools/objtool/special.h
@@ -0,0 +1,42 @@
+/*
+ * Copyright (C) 2015 Josh Poimboeuf <jpoimboe@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _SPECIAL_H
+#define _SPECIAL_H
+
+#include <stdbool.h>
+#include "elf.h"
+
+struct special_alt {
+	struct list_head list;
+
+	bool group;
+	bool skip_orig;
+	bool jump_or_nop;
+
+	struct section *orig_sec;
+	unsigned long orig_off;
+
+	struct section *new_sec;
+	unsigned long new_off;
+
+	unsigned int orig_len, new_len; /* group only */
+};
+
+int special_get_alts(struct elf *elf, struct list_head *alts);
+
+#endif /* _SPECIAL_H */
diff --git a/tools/objtool/warn.h b/tools/objtool/warn.h
new file mode 100644
index 000000000..ac7e07523
--- /dev/null
+++ b/tools/objtool/warn.h
@@ -0,0 +1,60 @@
+/*
+ * Copyright (C) 2015 Josh Poimboeuf <jpoimboe@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _WARN_H
+#define _WARN_H
+
+extern const char *objname;
+
+static inline char *offstr(struct section *sec, unsigned long offset)
+{
+	struct symbol *func;
+	char *name, *str;
+	unsigned long name_off;
+
+	func = find_containing_func(sec, offset);
+	if (func) {
+		name = func->name;
+		name_off = offset - func->offset;
+	} else {
+		name = sec->name;
+		name_off = offset;
+	}
+
+	str = malloc(strlen(name) + 20);
+
+	if (func)
+		sprintf(str, "%s()+0x%lx", name, name_off);
+	else
+		sprintf(str, "%s+0x%lx", name, name_off);
+
+	return str;
+}
+
+#define WARN(format, ...)				\
+	fprintf(stderr,					\
+		"%s: warning: objtool: " format "\n",	\
+		objname, ##__VA_ARGS__)
+
+#define WARN_FUNC(format, sec, offset, ...)		\
+({							\
+	char *_str = offstr(sec, offset);		\
+	WARN("%s: " format, _str, ##__VA_ARGS__);	\
+	free(_str);					\
+})
+
+#endif /* _WARN_H */
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index 3ba1c0b09..098cfb9ca 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -1,5 +1,5 @@
 include ../../scripts/Makefile.include
-include ../config/utilities.mak
+include ../../scripts/utilities.mak
 
 MAN1_TXT= \
 	$(filter-out $(addsuffix .txt, $(ARTICLES) $(SP_ARTICLES)), \
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index b9ca1e304..15949e2a7 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -8,7 +8,7 @@ perf-config - Get and set variables in a configuration file.
 SYNOPSIS
 --------
 [verse]
-'perf config' -l | --list
+'perf config' [<file-option>] -l | --list
 
 DESCRIPTION
 -----------
@@ -21,6 +21,14 @@ OPTIONS
 --list::
 	Show current config variables, name and value, for all sections.
 
+--user::
+	For writing and reading options: write to user
+	'$HOME/.perfconfig' file or read it.
+
+--system::
+	For writing and reading options: write to system-wide
+	'$(sysconfdir)/perfconfig' or read it.
+
 CONFIGURATION FILE
 ------------------
 
@@ -30,6 +38,10 @@ The '$HOME/.perfconfig' file is used to store a per-user configuration.
 The file '$(sysconfdir)/perfconfig' can be used to
 store a system-wide default configuration.
 
+When reading or writing, the values are read from the system and user
+configuration files by default, and options '--system' and '--user'
+can be used to tell the command to read from or write to only that location.
+
 Syntax
 ~~~~~~
 
@@ -62,7 +74,7 @@ Given a $HOME/.perfconfig like this:
 		medium = green, default
 		normal = lightgray, default
 		selected = white, lightgray
-		code = blue, default
+		jump_arrows = blue, default
 		addr = magenta, default
 		root = white, blue
 
@@ -98,6 +110,347 @@ Given a $HOME/.perfconfig like this:
 		order = caller
 		sort-key = function
 
+Variables
+~~~~~~~~~
+
+colors.*::
+	The variables for customizing the colors used in the output for the
+	'report', 'top' and 'annotate' in the TUI. They should specify the
+	foreground and background colors, separated by a comma, for example:
+
+		medium = green, lightgray
+
+	If you want to use the color configured for you terminal, just leave it
+	as 'default', for example:
+
+		medium = default, lightgray
+
+	Available colors:
+	red, yellow, green, cyan, gray, black, blue,
+	white, default, magenta, lightgray
+
+	colors.top::
+		'top' means a overhead percentage which is more than 5%.
+		And values of this variable specify percentage colors.
+		Basic key values are foreground-color 'red' and
+		background-color 'default'.
+	colors.medium::
+		'medium' means a overhead percentage which has more than 0.5%.
+		Default values are 'green' and 'default'.
+	colors.normal::
+		'normal' means the rest of overhead percentages
+		except 'top', 'medium', 'selected'.
+		Default values are 'lightgray' and 'default'.
+	colors.selected::
+		This selects the colors for the current entry in a list of entries
+		from sub-commands (top, report, annotate).
+		Default values are 'black' and 'lightgray'.
+	colors.jump_arrows::
+		Colors for jump arrows on assembly code listings
+		such as 'jns', 'jmp', 'jane', etc.
+		Default values are 'blue', 'default'.
+	colors.addr::
+		This selects colors for addresses from 'annotate'.
+		Default values are 'magenta', 'default'.
+	colors.root::
+		Colors for headers in the output of a sub-commands (top, report).
+		Default values are 'white', 'blue'.
+
+tui.*, gtk.*::
+	Subcommands that can be configured here are 'top', 'report' and 'annotate'.
+	These values are booleans, for example:
+
+	[tui]
+		top = true
+
+	will make the TUI be the default for the 'top' subcommand. Those will be
+	available if the required libs were detected at tool build time.
+
+buildid.*::
+	buildid.dir::
+		Each executable and shared library in modern distributions comes with a
+		content based identifier that, if available, will be inserted in a
+		'perf.data' file header to, at analysis time find what is needed to do
+		symbol resolution, code annotation, etc.
+
+		The recording tools also stores a hard link or copy in a per-user
+		directory, $HOME/.debug/, of binaries, shared libraries, /proc/kallsyms
+		and /proc/kcore files to be used at analysis time.
+
+		The buildid.dir variable can be used to either change this directory
+		cache location, or to disable it altogether. If you want to disable it,
+		set buildid.dir to /dev/null. The default is $HOME/.debug
+
+annotate.*::
+	These options work only for TUI.
+	These are in control of addresses, jump function, source code
+	in lines of assembly code from a specific program.
+
+	annotate.hide_src_code::
+		If a program which is analyzed has source code,
+		this option lets 'annotate' print a list of assembly code with the source code.
+		For example, let's see a part of a program. There're four lines.
+		If this option is 'true', they can be printed
+		without source code from a program as below.
+
+		│        push   %rbp
+		│        mov    %rsp,%rbp
+		│        sub    $0x10,%rsp
+		│        mov    (%rdi),%rdx
+
+		But if this option is 'false', source code of the part
+		can be also printed as below. Default is 'false'.
+
+		│      struct rb_node *rb_next(const struct rb_node *node)
+		│      {
+		│        push   %rbp
+		│        mov    %rsp,%rbp
+		│        sub    $0x10,%rsp
+		│              struct rb_node *parent;
+		│
+		│              if (RB_EMPTY_NODE(node))
+		│        mov    (%rdi),%rdx
+		│              return n;
+
+        annotate.use_offset::
+		Basing on a first address of a loaded function, offset can be used.
+		Instead of using original addresses of assembly code,
+		addresses subtracted from a base address can be printed.
+		Let's illustrate an example.
+		If a base address is 0XFFFFFFFF81624d50 as below,
+
+		ffffffff81624d50 <load0>
+
+		an address on assembly code has a specific absolute address as below
+
+		ffffffff816250b8:│  mov    0x8(%r14),%rdi
+
+		but if use_offset is 'true', an address subtracted from a base address is printed.
+		Default is true. This option is only applied to TUI.
+
+		             368:│  mov    0x8(%r14),%rdi
+
+	annotate.jump_arrows::
+		There can be jump instruction among assembly code.
+		Depending on a boolean value of jump_arrows,
+		arrows can be printed or not which represent
+		where do the instruction jump into as below.
+
+		│     ┌──jmp    1333
+		│     │  xchg   %ax,%ax
+		│1330:│  mov    %r15,%r10
+		│1333:└─→cmp    %r15,%r14
+
+		If jump_arrow is 'false', the arrows isn't printed as below.
+		Default is 'false'.
+
+		│      ↓ jmp    1333
+		│        xchg   %ax,%ax
+		│1330:   mov    %r15,%r10
+		│1333:   cmp    %r15,%r14
+
+        annotate.show_linenr::
+		When showing source code if this option is 'true',
+		line numbers are printed as below.
+
+		│1628         if (type & PERF_SAMPLE_IDENTIFIER) {
+		│     ↓ jne    508
+		│1628                 data->id = *array;
+		│1629                 array++;
+		│1630         }
+
+		However if this option is 'false', they aren't printed as below.
+		Default is 'false'.
+
+		│             if (type & PERF_SAMPLE_IDENTIFIER) {
+		│     ↓ jne    508
+		│                     data->id = *array;
+		│                     array++;
+		│             }
+
+        annotate.show_nr_jumps::
+		Let's see a part of assembly code.
+
+		│1382:   movb   $0x1,-0x270(%rbp)
+
+		If use this, the number of branches jumping to that address can be printed as below.
+		Default is 'false'.
+
+		│1 1382:   movb   $0x1,-0x270(%rbp)
+
+        annotate.show_total_period::
+		To compare two records on an instruction base, with this option
+		provided, display total number of samples that belong to a line
+		in assembly code. If this option is 'true', total periods are printed
+		instead of percent values as below.
+
+		  302 │      mov    %eax,%eax
+
+		But if this option is 'false', percent values for overhead are printed i.e.
+		Default is 'false'.
+
+		99.93 │      mov    %eax,%eax
+
+hist.*::
+	hist.percentage::
+		This option control the way to calculate overhead of filtered entries -
+		that means the value of this option is effective only if there's a
+		filter (by comm, dso or symbol name). Suppose a following example:
+
+		       Overhead  Symbols
+		       ........  .......
+		        33.33%     foo
+		        33.33%     bar
+		        33.33%     baz
+
+	       This is an original overhead and we'll filter out the first 'foo'
+	       entry. The value of 'relative' would increase the overhead of 'bar'
+	       and 'baz' to 50.00% for each, while 'absolute' would show their
+	       current overhead (33.33%).
+
+ui.*::
+	ui.show-headers::
+		This option controls display of column headers (like 'Overhead' and 'Symbol')
+		in 'report' and 'top'. If this option is false, they are hidden.
+		This option is only applied to TUI.
+
+call-graph.*::
+	When sub-commands 'top' and 'report' work with -g/—-children
+	there're options in control of call-graph.
+
+	call-graph.record-mode::
+		The record-mode can be 'fp' (frame pointer), 'dwarf' and 'lbr'.
+		The value of 'dwarf' is effective only if perf detect needed library
+		(libunwind or a recent version of libdw).
+		'lbr' only work for cpus that support it.
+
+	call-graph.dump-size::
+		The size of stack to dump in order to do post-unwinding. Default is 8192 (byte).
+		When using dwarf into record-mode, the default size will be used if omitted.
+
+	call-graph.print-type::
+		The print-types can be graph (graph absolute), fractal (graph relative),
+		flat and folded. This option controls a way to show overhead for each callchain
+		entry. Suppose a following example.
+
+                Overhead  Symbols
+                ........  .......
+                  40.00%  foo
+                          |
+                          ---foo
+                             |
+                             |--50.00%--bar
+                             |          main
+                             |
+                              --50.00%--baz
+                                        main
+
+		This output is a 'fractal' format. The 'foo' came from 'bar' and 'baz' exactly
+		half and half so 'fractal' shows 50.00% for each
+		(meaning that it assumes 100% total overhead of 'foo').
+
+		The 'graph' uses absolute overhead value of 'foo' as total so each of
+		'bar' and 'baz' callchain will have 20.00% of overhead.
+		If 'flat' is used, single column and linear exposure of call chains.
+		'folded' mean call chains are displayed in a line, separated by semicolons.
+
+	call-graph.order::
+		This option controls print order of callchains. The default is
+		'callee' which means callee is printed at top and then followed by its
+		caller and so on. The 'caller' prints it in reverse order.
+
+		If this option is not set and report.children or top.children is
+		set to true (or the equivalent command line option is given),
+		the default value of this option is changed to 'caller' for the
+		execution of 'perf report' or 'perf top'. Other commands will
+		still default to 'callee'.
+
+	call-graph.sort-key::
+		The callchains are merged if they contain same information.
+		The sort-key option determines a way to compare the callchains.
+		A value of 'sort-key' can be 'function' or 'address'.
+		The default is 'function'.
+
+	call-graph.threshold::
+		When there're many callchains it'd print tons of lines. So perf omits
+		small callchains under a certain overhead (threshold) and this option
+		control the threshold. Default is 0.5 (%). The overhead is calculated
+		by value depends on call-graph.print-type.
+
+	call-graph.print-limit::
+		This is a maximum number of lines of callchain printed for a single
+		histogram entry. Default is 0 which means no limitation.
+
+report.*::
+	report.percent-limit::
+		This one is mostly the same as call-graph.threshold but works for
+		histogram entries. Entries having an overhead lower than this
+		percentage will not be printed. Default is '0'. If percent-limit
+		is '10', only entries which have more than 10% of overhead will be
+		printed.
+
+	report.queue-size::
+		This option sets up the maximum allocation size of the internal
+		event queue for ordering events. Default is 0, meaning no limit.
+
+	report.children::
+		'Children' means functions called from another function.
+		If this option is true, 'perf report' cumulates callchains of children
+		and show (accumulated) total overhead as well as 'Self' overhead.
+		Please refer to the 'perf report' manual. The default is 'true'.
+
+	report.group::
+		This option is to show event group information together.
+		Example output with this turned on, notice that there is one column
+		per event in the group, ref-cycles and cycles:
+
+		# group: {ref-cycles,cycles}
+		# ========
+		#
+		# Samples: 7K of event 'anon group { ref-cycles, cycles }'
+		# Event count (approx.): 6876107743
+		#
+		#         Overhead  Command      Shared Object               Symbol
+		# ................  .......  .................  ...................
+		#
+		    99.84%  99.76%  noploop  noploop            [.] main
+		     0.07%   0.00%  noploop  ld-2.15.so         [.] strcmp
+		     0.03%   0.00%  noploop  [kernel.kallsyms]  [k] timerqueue_del
+
+top.*::
+	top.children::
+		Same as 'report.children'. So if it is enabled, the output of 'top'
+		command will have 'Children' overhead column as well as 'Self' overhead
+		column by default.
+		The default is 'true'.
+
+man.*::
+	man.viewer::
+		This option can assign a tool to view manual pages when 'help'
+		subcommand was invoked. Supported tools are 'man', 'woman'
+		(with emacs client) and 'konqueror'. Default is 'man'.
+
+		New man viewer tool can be also added using 'man.<tool>.cmd'
+		or use different path using 'man.<tool>.path' config option.
+
+pager.*::
+	pager.<subcommand>::
+		When the subcommand is run on stdio, determine whether it uses
+		pager or not based on this value. Default is 'unspecified'.
+
+kmem.*::
+	kmem.default::
+		This option decides which allocator is to be analyzed if neither
+		'--slab' nor '--page' option is used. Default is 'slab'.
+
+record.*::
+	record.build-id::
+		This option can be 'cache', 'no-cache' or 'skip'.
+		'cache' is to post-process data and save/update the binaries into
+		the build-id cache (in ~/.debug). This is the default.
+		But if this option is 'no-cache', it will not update the build-id cache.
+		'skip' skips post-processing and does not update the cache.
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt
index 0b1cedeef..87b2588d1 100644
--- a/tools/perf/Documentation/perf-inject.txt
+++ b/tools/perf/Documentation/perf-inject.txt
@@ -53,6 +53,13 @@ include::itrace.txt[]
 --strip::
 	Use with --itrace to strip out non-synthesized events.
 
+-j::
+--jit::
+	Process jitdump files by injecting the mmap records corresponding to jitted
+	functions. This option also generates the ELF images for each jitted function
+	found in the jitdumps files captured in the input perf.data file. Use this option
+	if you are monitoring environment using JIT runtimes, such as Java, DART or V8.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 79483f40e..ec723d0a5 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -40,10 +40,12 @@ address should be. The 'p' modifier can be specified multiple times:
  0 - SAMPLE_IP can have arbitrary skid
  1 - SAMPLE_IP must have constant skid
  2 - SAMPLE_IP requested to have 0 skid
- 3 - SAMPLE_IP must have 0 skid
+ 3 - SAMPLE_IP must have 0 skid, or uses randomization to avoid
+     sample shadowing effects.
 
 For Intel systems precise event sampling is implemented with PEBS
-which supports up to precise-level 2.
+which supports up to precise-level 2, and precise level 3 for
+some special cases
 
 On AMD systems it is implemented using IBS (up to precise-level 2).
 The precise modifier works with event types 0x76 (cpu-cycles, CPU
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index fbceb6313..19aa17532 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -341,6 +341,12 @@ Specify vmlinux path which has debuginfo.
 --buildid-all::
 Record build-id of all DSOs regardless whether it's actually hit or not.
 
+--all-kernel::
+Configure all used events to run in kernel space.
+
+--all-user::
+Configure all used events to run in user space.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 8a301f6af..12113992a 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -117,6 +117,22 @@ OPTIONS
 	And default sort keys are changed to comm, dso_from, symbol_from, dso_to
 	and symbol_to, see '--branch-stack'.
 
+	If the --mem-mode option is used, the following sort keys are also available
+	(incompatible with --branch-stack):
+	symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline.
+
+	- symbol_daddr: name of data symbol being executed on at the time of sample
+	- dso_daddr: name of library or module containing the data being executed
+	on at the time of the sample
+	- locked: whether the bus was locked at the time of the sample
+	- tlb: type of tlb access for the data at the time of the sample
+	- mem: type of memory access for the data at the time of the sample
+	- snoop: type of snoop (if any) for the data at the time of the sample
+	- dcacheline: the cacheline the data address is on at the time of the sample
+
+	And the default sort keys are changed to local_weight, mem, sym, dso,
+	symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'.
+
 	If the data file has tracepoint event(s), following (dynamic) sort keys
 	are also available:
 	trace, trace_fields, [<event>.]<field>[/raw]
@@ -151,22 +167,6 @@ OPTIONS
 	By default, every sort keys not specified in -F will be appended
 	automatically.
 
-	If --mem-mode option is used, following sort keys are also available
-	(incompatible with --branch-stack):
-	symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline.
-
-	- symbol_daddr: name of data symbol being executed on at the time of sample
-	- dso_daddr: name of library or module containing the data being executed
-	on at the time of sample
-	- locked: whether the bus was locked at the time of sample
-	- tlb: type of tlb access for the data at the time of sample
-	- mem: type of memory access for the data at the time of sample
-	- snoop: type of snoop (if any) for the data at the time of sample
-	- dcacheline: the cacheline the data address is on at the time of sample
-
-	And default sort keys are changed to local_weight, mem, sym, dso,
-	symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'.
-
 -p::
 --parent=<regex>::
         A regex filter to identify parent. The parent is a caller of this
@@ -351,7 +351,10 @@ OPTIONS
 
 --percent-limit::
 	Do not show entries which have an overhead under that percent.
-	(Default: 0).
+	(Default: 0).  Note that this option also sets the percent limit (threshold)
+	of callchains.  However the default value of callchain threshold is
+	different than the default value of hist entries.  Please see the
+	--call-graph option for details.
 
 --percentage::
 	Determine how to display the overhead percentage of filtered entries.
@@ -398,6 +401,9 @@ include::itrace.txt[]
 --raw-trace::
 	When displaying traceevent output, do not use print fmt or plugins.
 
+--hierarchy::
+	Enable hierarchical output.
+
 include::callchain-overhead-calculation.txt[]
 
 SEE ALSO
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 14d9e8ffa..04f23b404 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -147,6 +147,10 @@ Print count deltas every N milliseconds (minimum: 10ms)
 The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals.  Use with caution.
 	example: 'perf stat -I 1000 -e cycles -a sleep 5'
 
+--metric-only::
+Only print computed metrics. Print them in a single line.
+Don't show any raw values. Not supported with --per-thread.
+
 --per-socket::
 Aggregate counts per processor socket for system-wide mode measurements.  This
 is a useful mode to detect imbalance between sockets.  To enable this mode,
@@ -219,6 +223,29 @@ $ perf stat -- make -j
 
  Wall-clock time elapsed:   719.554352 msecs
 
+CSV FORMAT
+----------
+
+With -x, perf stat is able to output a not-quite-CSV format output
+Commas in the output are not put into "". To make it easy to parse
+it is recommended to use a different character like -x \;
+
+The fields are in this order:
+
+	- optional usec time stamp in fractions of second (with -I xxx)
+	- optional CPU, core, or socket identifier
+	- optional number of logical CPUs aggregated
+	- counter value
+	- unit of the counter value or empty
+	- event name
+	- run time of counter
+	- percentage of measurement time the counter was running
+	- optional variance if multiple values are collected with -r
+	- optional metric value
+	- optional unit of metric
+
+Additional metrics may be printed with all earlier fields being empty.
+
 SEE ALSO
 --------
 linkperf:perf-top[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index b0e60e17d..19f046f02 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -233,6 +233,9 @@ Default is to monitor all CPUS.
 --raw-trace::
 	When displaying traceevent output, do not use print fmt or plugins.
 
+--hierarchy::
+	Enable hierarchy output.
+
 INTERACTIVE PROMPTING KEYS
 --------------------------
 
diff --git a/tools/perf/Documentation/perfconfig.example b/tools/perf/Documentation/perfconfig.example
index 767ea2436..1d8d5bc4c 100644
--- a/tools/perf/Documentation/perfconfig.example
+++ b/tools/perf/Documentation/perfconfig.example
@@ -5,7 +5,7 @@
 	medium = green, lightgray
 	normal = black, lightgray
 	selected = lightgray, magenta
-	code = blue, lightgray
+	jump_arrows = blue, lightgray
 	addr = magenta, lightgray
 
 [tui]
diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt
index e0ce9573b..5950b5a24 100644
--- a/tools/perf/Documentation/tips.txt
+++ b/tools/perf/Documentation/tips.txt
@@ -27,3 +27,4 @@ Skip collecing build-id when recording: perf record -B
 To change sampling frequency to 100 Hz: perf record -F 100
 See assembly instructions with percentage: perf annotate <symbol>
 If you prefer Intel style assembly, try: perf annotate -M intel
+For hierarchical output, try: perf report --hierarchy
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 2e1fa2357..8c8c6b9ce 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -74,6 +74,7 @@ arch/*/include/uapi/asm/unistd*.h
 arch/*/include/uapi/asm/perf_regs.h
 arch/*/lib/memcpy*.S
 arch/*/lib/memset*.S
+arch/*/include/asm/*features.h
 include/linux/poison.h
 include/linux/hw_breakpoint.h
 include/uapi/linux/perf_event.h
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index dcd9a70c7..32a64e619 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -68,6 +68,20 @@ all tags TAGS:
 	$(print_msg)
 	$(make)
 
+ifdef MAKECMDGOALS
+has_clean := 0
+ifneq ($(filter clean,$(MAKECMDGOALS)),)
+  has_clean := 1
+endif # clean
+
+ifeq ($(has_clean),1)
+  rest := $(filter-out clean,$(MAKECMDGOALS))
+  ifneq ($(rest),)
+$(rest): clean
+  endif # rest
+endif # has_clean
+endif # MAKECMDGOALS
+
 #
 # The clean target is not really parallel, don't print the jobs info:
 #
@@ -75,10 +89,17 @@ clean:
 	$(make)
 
 #
-# The build-test target is not really parallel, don't print the jobs info:
+# The build-test target is not really parallel, don't print the jobs info,
+# it also uses only the tests/make targets that don't pollute the source
+# repository, i.e. that uses O= or builds the tarpkg outside the source
+# repo directories.
+#
+# For a full test, use:
+#
+# make -C tools/perf -f tests/make
 #
 build-test:
-	@$(MAKE) SHUF=1 -f tests/make --no-print-directory
+	@$(MAKE) SHUF=1 -f tests/make REUSE_FEATURES_DUMP=1 MK=Makefile SET_PARALLEL=1 --no-print-directory tarpkg out
 
 #
 # All other targets get passed through:
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 5d34815c7..000ea2103 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -3,7 +3,7 @@ include ../scripts/Makefile.include
 # The default target of this Makefile is...
 all:
 
-include config/utilities.mak
+include ../scripts/utilities.mak
 
 # Define V to have a more verbose compile.
 #
@@ -58,6 +58,9 @@ include config/utilities.mak
 #
 # Define NO_LIBBIONIC if you do not want bionic support
 #
+# Define NO_LIBCRYPTO if you do not want libcrypto (openssl) support
+# used for generating build-ids for ELFs generated by jitdump.
+#
 # Define NO_LIBDW_DWARF_UNWIND if you do not want libdw support
 # for dwarf backtrace post unwind.
 #
@@ -136,6 +139,8 @@ $(call allow-override,CC,$(CROSS_COMPILE)gcc)
 $(call allow-override,AR,$(CROSS_COMPILE)ar)
 $(call allow-override,LD,$(CROSS_COMPILE)ld)
 
+LD += $(EXTRA_LDFLAGS)
+
 PKG_CONFIG = $(CROSS_COMPILE)pkg-config
 
 RM      = rm -f
@@ -165,7 +170,16 @@ ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
 endif
 endif
 
+# Set FEATURE_TESTS to 'all' so all possible feature checkers are executed.
+# Without this setting the output feature dump file misses some features, for
+# example, liberty. Select all checkers so we won't get an incomplete feature
+# dump file.
 ifeq ($(config),1)
+ifdef MAKECMDGOALS
+ifeq ($(filter feature-dump,$(MAKECMDGOALS)),feature-dump)
+FEATURE_TESTS := all
+endif
+endif
 include config/Makefile
 endif
 
@@ -618,7 +632,7 @@ clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32
 	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \
 		$(OUTPUT)util/intel-pt-decoder/inat-tables.c $(OUTPUT)fixdep \
-		$(OUTPUT)tests/llvm-src-{base,kbuild,prologue}.c
+		$(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
 	$(python-clean)
 
diff --git a/tools/perf/arch/arm/Makefile b/tools/perf/arch/arm/Makefile
index 7fbca1750..18b13518d 100644
--- a/tools/perf/arch/arm/Makefile
+++ b/tools/perf/arch/arm/Makefile
@@ -1,3 +1,4 @@
 ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
+PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index 7fbca1750..18b13518d 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -1,3 +1,4 @@
 ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
+PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index 7fbca1750..56e05f126 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -1,3 +1,6 @@
 ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
+
+HAVE_KVM_STAT_SUPPORT := 1
+PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
index 7b8b0d1a1..c8fe2074d 100644
--- a/tools/perf/arch/powerpc/util/Build
+++ b/tools/perf/arch/powerpc/util/Build
@@ -1,5 +1,6 @@
 libperf-y += header.o
 libperf-y += sym-handling.o
+libperf-y += kvm-stat.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 libperf-$(CONFIG_DWARF) += skip-callchain-idx.o
diff --git a/tools/perf/arch/powerpc/util/book3s_hcalls.h b/tools/perf/arch/powerpc/util/book3s_hcalls.h
new file mode 100644
index 000000000..0dd6b7f2d
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/book3s_hcalls.h
@@ -0,0 +1,123 @@
+#ifndef ARCH_PERF_BOOK3S_HV_HCALLS_H
+#define ARCH_PERF_BOOK3S_HV_HCALLS_H
+
+/*
+ * PowerPC HCALL codes : hcall code to name mapping
+ */
+#define kvm_trace_symbol_hcall \
+	{0x4, "H_REMOVE"},					\
+	{0x8, "H_ENTER"},					\
+	{0xc, "H_READ"},					\
+	{0x10, "H_CLEAR_MOD"},					\
+	{0x14, "H_CLEAR_REF"},					\
+	{0x18, "H_PROTECT"},					\
+	{0x1c, "H_GET_TCE"},					\
+	{0x20, "H_PUT_TCE"},					\
+	{0x24, "H_SET_SPRG0"},					\
+	{0x28, "H_SET_DABR"},					\
+	{0x2c, "H_PAGE_INIT"},					\
+	{0x30, "H_SET_ASR"},					\
+	{0x34, "H_ASR_ON"},					\
+	{0x38, "H_ASR_OFF"},					\
+	{0x3c, "H_LOGICAL_CI_LOAD"},				\
+	{0x40, "H_LOGICAL_CI_STORE"},				\
+	{0x44, "H_LOGICAL_CACHE_LOAD"},				\
+	{0x48, "H_LOGICAL_CACHE_STORE"},			\
+	{0x4c, "H_LOGICAL_ICBI"},				\
+	{0x50, "H_LOGICAL_DCBF"},				\
+	{0x54, "H_GET_TERM_CHAR"},				\
+	{0x58, "H_PUT_TERM_CHAR"},				\
+	{0x5c, "H_REAL_TO_LOGICAL"},				\
+	{0x60, "H_HYPERVISOR_DATA"},				\
+	{0x64, "H_EOI"},					\
+	{0x68, "H_CPPR"},					\
+	{0x6c, "H_IPI"},					\
+	{0x70, "H_IPOLL"},					\
+	{0x74, "H_XIRR"},					\
+	{0x78, "H_MIGRATE_DMA"},				\
+	{0x7c, "H_PERFMON"},					\
+	{0xdc, "H_REGISTER_VPA"},				\
+	{0xe0, "H_CEDE"},					\
+	{0xe4, "H_CONFER"},					\
+	{0xe8, "H_PROD"},					\
+	{0xec, "H_GET_PPP"},					\
+	{0xf0, "H_SET_PPP"},					\
+	{0xf4, "H_PURR"},					\
+	{0xf8, "H_PIC"},					\
+	{0xfc, "H_REG_CRQ"},					\
+	{0x100, "H_FREE_CRQ"},					\
+	{0x104, "H_VIO_SIGNAL"},				\
+	{0x108, "H_SEND_CRQ"},					\
+	{0x110, "H_COPY_RDMA"},					\
+	{0x114, "H_REGISTER_LOGICAL_LAN"},			\
+	{0x118, "H_FREE_LOGICAL_LAN"},				\
+	{0x11c, "H_ADD_LOGICAL_LAN_BUFFER"},			\
+	{0x120, "H_SEND_LOGICAL_LAN"},				\
+	{0x124, "H_BULK_REMOVE"},				\
+	{0x130, "H_MULTICAST_CTRL"},				\
+	{0x134, "H_SET_XDABR"},					\
+	{0x138, "H_STUFF_TCE"},					\
+	{0x13c, "H_PUT_TCE_INDIRECT"},				\
+	{0x14c, "H_CHANGE_LOGICAL_LAN_MAC"},			\
+	{0x150, "H_VTERM_PARTNER_INFO"},			\
+	{0x154, "H_REGISTER_VTERM"},				\
+	{0x158, "H_FREE_VTERM"},				\
+	{0x15c, "H_RESET_EVENTS"},				\
+	{0x160, "H_ALLOC_RESOURCE"},				\
+	{0x164, "H_FREE_RESOURCE"},				\
+	{0x168, "H_MODIFY_QP"},					\
+	{0x16c, "H_QUERY_QP"},					\
+	{0x170, "H_REREGISTER_PMR"},				\
+	{0x174, "H_REGISTER_SMR"},				\
+	{0x178, "H_QUERY_MR"},					\
+	{0x17c, "H_QUERY_MW"},					\
+	{0x180, "H_QUERY_HCA"},					\
+	{0x184, "H_QUERY_PORT"},				\
+	{0x188, "H_MODIFY_PORT"},				\
+	{0x18c, "H_DEFINE_AQP1"},				\
+	{0x190, "H_GET_TRACE_BUFFER"},				\
+	{0x194, "H_DEFINE_AQP0"},				\
+	{0x198, "H_RESIZE_MR"},					\
+	{0x19c, "H_ATTACH_MCQP"},				\
+	{0x1a0, "H_DETACH_MCQP"},				\
+	{0x1a4, "H_CREATE_RPT"},				\
+	{0x1a8, "H_REMOVE_RPT"},				\
+	{0x1ac, "H_REGISTER_RPAGES"},				\
+	{0x1b0, "H_DISABLE_AND_GETC"},				\
+	{0x1b4, "H_ERROR_DATA"},				\
+	{0x1b8, "H_GET_HCA_INFO"},				\
+	{0x1bc, "H_GET_PERF_COUNT"},				\
+	{0x1c0, "H_MANAGE_TRACE"},				\
+	{0x1d4, "H_FREE_LOGICAL_LAN_BUFFER"},			\
+	{0x1d8, "H_POLL_PENDING"},				\
+	{0x1e4, "H_QUERY_INT_STATE"},				\
+	{0x244, "H_ILLAN_ATTRIBUTES"},				\
+	{0x250, "H_MODIFY_HEA_QP"},				\
+	{0x254, "H_QUERY_HEA_QP"},				\
+	{0x258, "H_QUERY_HEA"},					\
+	{0x25c, "H_QUERY_HEA_PORT"},				\
+	{0x260, "H_MODIFY_HEA_PORT"},				\
+	{0x264, "H_REG_BCMC"},					\
+	{0x268, "H_DEREG_BCMC"},				\
+	{0x26c, "H_REGISTER_HEA_RPAGES"},			\
+	{0x270, "H_DISABLE_AND_GET_HEA"},			\
+	{0x274, "H_GET_HEA_INFO"},				\
+	{0x278, "H_ALLOC_HEA_RESOURCE"},			\
+	{0x284, "H_ADD_CONN"},					\
+	{0x288, "H_DEL_CONN"},					\
+	{0x298, "H_JOIN"},					\
+	{0x2a4, "H_VASI_STATE"},				\
+	{0x2b0, "H_ENABLE_CRQ"},				\
+	{0x2b8, "H_GET_EM_PARMS"},				\
+	{0x2d0, "H_SET_MPP"},					\
+	{0x2d4, "H_GET_MPP"},					\
+	{0x2ec, "H_HOME_NODE_ASSOCIATIVITY"},			\
+	{0x2f4, "H_BEST_ENERGY"},				\
+	{0x2fc, "H_XIRR_X"},					\
+	{0x300, "H_RANDOM"},					\
+	{0x304, "H_COP"},					\
+	{0x314, "H_GET_MPP_X"},					\
+	{0x31c, "H_SET_MODE"},					\
+	{0xf000, "H_RTAS"}					\
+
+#endif
diff --git a/tools/perf/arch/powerpc/util/book3s_hv_exits.h b/tools/perf/arch/powerpc/util/book3s_hv_exits.h
new file mode 100644
index 000000000..e68ba2da8
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/book3s_hv_exits.h
@@ -0,0 +1,33 @@
+#ifndef ARCH_PERF_BOOK3S_HV_EXITS_H
+#define ARCH_PERF_BOOK3S_HV_EXITS_H
+
+/*
+ * PowerPC Interrupt vectors : exit code to name mapping
+ */
+
+#define kvm_trace_symbol_exit \
+	{0x0,	"RETURN_TO_HOST"}, \
+	{0x100, "SYSTEM_RESET"}, \
+	{0x200, "MACHINE_CHECK"}, \
+	{0x300, "DATA_STORAGE"}, \
+	{0x380, "DATA_SEGMENT"}, \
+	{0x400, "INST_STORAGE"}, \
+	{0x480, "INST_SEGMENT"}, \
+	{0x500, "EXTERNAL"}, \
+	{0x501, "EXTERNAL_LEVEL"}, \
+	{0x502, "EXTERNAL_HV"}, \
+	{0x600, "ALIGNMENT"}, \
+	{0x700, "PROGRAM"}, \
+	{0x800, "FP_UNAVAIL"}, \
+	{0x900, "DECREMENTER"}, \
+	{0x980, "HV_DECREMENTER"}, \
+	{0xc00, "SYSCALL"}, \
+	{0xd00, "TRACE"}, \
+	{0xe00, "H_DATA_STORAGE"}, \
+	{0xe20, "H_INST_STORAGE"}, \
+	{0xe40, "H_EMUL_ASSIST"}, \
+	{0xf00, "PERFMON"}, \
+	{0xf20, "ALTIVEC"}, \
+	{0xf40, "VSX"}
+
+#endif
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index 6c1b8a75d..f8ccee132 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -3,9 +3,9 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-
-#include "../../util/header.h"
-#include "../../util/util.h"
+#include <linux/stringify.h>
+#include "header.h"
+#include "util.h"
 
 #define mfspr(rn)       ({unsigned long rval; \
 			 asm volatile("mfspr %0," __stringify(rn) \
diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c
new file mode 100644
index 000000000..74eee3039
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/kvm-stat.c
@@ -0,0 +1,170 @@
+#include "util/kvm-stat.h"
+#include "util/parse-events.h"
+#include "util/debug.h"
+
+#include "book3s_hv_exits.h"
+#include "book3s_hcalls.h"
+
+#define NR_TPS 4
+
+const char *vcpu_id_str = "vcpu_id";
+const int decode_str_len = 40;
+const char *kvm_entry_trace = "kvm_hv:kvm_guest_enter";
+const char *kvm_exit_trace = "kvm_hv:kvm_guest_exit";
+
+define_exit_reasons_table(hv_exit_reasons, kvm_trace_symbol_exit);
+define_exit_reasons_table(hcall_reasons, kvm_trace_symbol_hcall);
+
+/* Tracepoints specific to ppc_book3s_hv */
+const char *ppc_book3s_hv_kvm_tp[] = {
+	"kvm_hv:kvm_guest_enter",
+	"kvm_hv:kvm_guest_exit",
+	"kvm_hv:kvm_hcall_enter",
+	"kvm_hv:kvm_hcall_exit",
+	NULL,
+};
+
+/* 1 extra placeholder for NULL */
+const char *kvm_events_tp[NR_TPS + 1];
+const char *kvm_exit_reason;
+
+static void hcall_event_get_key(struct perf_evsel *evsel,
+				struct perf_sample *sample,
+				struct event_key *key)
+{
+	key->info = 0;
+	key->key = perf_evsel__intval(evsel, sample, "req");
+}
+
+static const char *get_hcall_exit_reason(u64 exit_code)
+{
+	struct exit_reasons_table *tbl = hcall_reasons;
+
+	while (tbl->reason != NULL) {
+		if (tbl->exit_code == exit_code)
+			return tbl->reason;
+		tbl++;
+	}
+
+	pr_debug("Unknown hcall code: %lld\n",
+	       (unsigned long long)exit_code);
+	return "UNKNOWN";
+}
+
+static bool hcall_event_end(struct perf_evsel *evsel,
+			    struct perf_sample *sample __maybe_unused,
+			    struct event_key *key __maybe_unused)
+{
+	return (!strcmp(evsel->name, kvm_events_tp[3]));
+}
+
+static bool hcall_event_begin(struct perf_evsel *evsel,
+			      struct perf_sample *sample, struct event_key *key)
+{
+	if (!strcmp(evsel->name, kvm_events_tp[2])) {
+		hcall_event_get_key(evsel, sample, key);
+		return true;
+	}
+
+	return false;
+}
+static void hcall_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
+				   struct event_key *key,
+				   char *decode)
+{
+	const char *hcall_reason = get_hcall_exit_reason(key->key);
+
+	scnprintf(decode, decode_str_len, "%s", hcall_reason);
+}
+
+static struct kvm_events_ops hcall_events = {
+	.is_begin_event = hcall_event_begin,
+	.is_end_event = hcall_event_end,
+	.decode_key = hcall_event_decode_key,
+	.name = "HCALL-EVENT",
+};
+
+static struct kvm_events_ops exit_events = {
+	.is_begin_event = exit_event_begin,
+	.is_end_event = exit_event_end,
+	.decode_key = exit_event_decode_key,
+	.name = "VM-EXIT"
+};
+
+struct kvm_reg_events_ops kvm_reg_events_ops[] = {
+	{ .name = "vmexit", .ops = &exit_events },
+	{ .name = "hcall", .ops = &hcall_events },
+	{ NULL, NULL },
+};
+
+const char * const kvm_skip_events[] = {
+	NULL,
+};
+
+
+static int is_tracepoint_available(const char *str, struct perf_evlist *evlist)
+{
+	struct parse_events_error err;
+	int ret;
+
+	err.str = NULL;
+	ret = parse_events(evlist, str, &err);
+	if (err.str)
+		pr_err("%s : %s\n", str, err.str);
+	return ret;
+}
+
+static int ppc__setup_book3s_hv(struct perf_kvm_stat *kvm,
+				struct perf_evlist *evlist)
+{
+	const char **events_ptr;
+	int i, nr_tp = 0, err = -1;
+
+	/* Check for book3s_hv tracepoints */
+	for (events_ptr = ppc_book3s_hv_kvm_tp; *events_ptr; events_ptr++) {
+		err = is_tracepoint_available(*events_ptr, evlist);
+		if (err)
+			return -1;
+		nr_tp++;
+	}
+
+	for (i = 0; i < nr_tp; i++)
+		kvm_events_tp[i] = ppc_book3s_hv_kvm_tp[i];
+
+	kvm_events_tp[i] = NULL;
+	kvm_exit_reason = "trap";
+	kvm->exit_reasons = hv_exit_reasons;
+	kvm->exit_reasons_isa = "HV";
+
+	return 0;
+}
+
+/* Wrapper to setup kvm tracepoints */
+static int ppc__setup_kvm_tp(struct perf_kvm_stat *kvm)
+{
+	struct perf_evlist *evlist = perf_evlist__new();
+
+	if (evlist == NULL)
+		return -ENOMEM;
+
+	/* Right now, only supported on book3s_hv */
+	return ppc__setup_book3s_hv(kvm, evlist);
+}
+
+int setup_kvm_events_tp(struct perf_kvm_stat *kvm)
+{
+	return ppc__setup_kvm_tp(kvm);
+}
+
+int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused)
+{
+	int ret;
+
+	ret = ppc__setup_kvm_tp(kvm);
+	if (ret) {
+		kvm->exit_reasons = NULL;
+		kvm->exit_reasons_isa = NULL;
+	}
+
+	return ret;
+}
diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c
index a5dbc07ec..ed57df2e6 100644
--- a/tools/perf/arch/s390/util/kvm-stat.c
+++ b/tools/perf/arch/s390/util/kvm-stat.c
@@ -10,7 +10,7 @@
  */
 
 #include "../../util/kvm-stat.h"
-#include <asm/kvm_perf.h>
+#include <asm/sie.h>
 
 define_exit_reasons_table(sie_exit_reasons, sie_intercept_code);
 define_exit_reasons_table(sie_icpt_insn_codes, icpt_insn_codes);
@@ -18,6 +18,12 @@ define_exit_reasons_table(sie_sigp_order_codes, sigp_order_codes);
 define_exit_reasons_table(sie_diagnose_codes, diagnose_codes);
 define_exit_reasons_table(sie_icpt_prog_codes, icpt_prog_codes);
 
+const char *vcpu_id_str = "id";
+const int decode_str_len = 40;
+const char *kvm_exit_reason = "icptcode";
+const char *kvm_entry_trace = "kvm:kvm_s390_sie_enter";
+const char *kvm_exit_trace = "kvm:kvm_s390_sie_exit";
+
 static void event_icpt_insn_get_key(struct perf_evsel *evsel,
 				    struct perf_sample *sample,
 				    struct event_key *key)
@@ -73,7 +79,7 @@ static struct kvm_events_ops exit_events = {
 	.name = "VM-EXIT"
 };
 
-const char * const kvm_events_tp[] = {
+const char *kvm_events_tp[] = {
 	"kvm:kvm_s390_sie_enter",
 	"kvm:kvm_s390_sie_exit",
 	"kvm:kvm_s390_intercept_instruction",
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 09ba923de..269af2143 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -3,3 +3,4 @@ PERF_HAVE_DWARF_REGS := 1
 endif
 HAVE_KVM_STAT_SUPPORT := 1
 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
+PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c
index 7bb0d13c2..72193f19d 100644
--- a/tools/perf/arch/x86/tests/rdpmc.c
+++ b/tools/perf/arch/x86/tests/rdpmc.c
@@ -59,7 +59,7 @@ static u64 mmap_read_self(void *addr)
 		u64 quot, rem;
 
 		quot = (cyc >> time_shift);
-		rem = cyc & ((1 << time_shift) - 1);
+		rem = cyc & (((u64)1 << time_shift) - 1);
 		delta = time_offset + quot * time_mult +
 			((rem * time_mult) >> time_shift);
 
@@ -103,6 +103,7 @@ static int __test__rdpmc(void)
 
 	sigfillset(&sa.sa_mask);
 	sa.sa_sigaction = segfault_handler;
+	sa.sa_flags = 0;
 	sigaction(SIGSEGV, &sa, NULL);
 
 	fd = sys_perf_event_open(&attr, 0, -1, -1,
diff --git a/tools/perf/arch/x86/util/dwarf-regs.c b/tools/perf/arch/x86/util/dwarf-regs.c
index 9223c164e..1f86ee8fb 100644
--- a/tools/perf/arch/x86/util/dwarf-regs.c
+++ b/tools/perf/arch/x86/util/dwarf-regs.c
@@ -63,6 +63,8 @@ struct pt_regs_offset {
 # define REG_OFFSET_NAME_32(n, r) {.name = n, .offset = offsetof(struct pt_regs, r)}
 #endif
 
+/* TODO: switching by dwarf address size */
+#ifndef __x86_64__
 static const struct pt_regs_offset x86_32_regoffset_table[] = {
 	REG_OFFSET_NAME_32("%ax",	eax),
 	REG_OFFSET_NAME_32("%cx",	ecx),
@@ -75,6 +77,8 @@ static const struct pt_regs_offset x86_32_regoffset_table[] = {
 	REG_OFFSET_END,
 };
 
+#define regoffset_table x86_32_regoffset_table
+#else
 static const struct pt_regs_offset x86_64_regoffset_table[] = {
 	REG_OFFSET_NAME_64("%ax",	rax),
 	REG_OFFSET_NAME_64("%dx",	rdx),
@@ -95,11 +99,7 @@ static const struct pt_regs_offset x86_64_regoffset_table[] = {
 	REG_OFFSET_END,
 };
 
-/* TODO: switching by dwarf address size */
-#ifdef __x86_64__
 #define regoffset_table x86_64_regoffset_table
-#else
-#define regoffset_table x86_32_regoffset_table
 #endif
 
 /* Minus 1 for the ending REG_OFFSET_END */
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 8d8150f1c..d66f9ad4d 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -60,7 +60,9 @@ struct branch {
 	u64 misc;
 };
 
-static size_t intel_bts_info_priv_size(struct auxtrace_record *itr __maybe_unused)
+static size_t
+intel_bts_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+			 struct perf_evlist *evlist __maybe_unused)
 {
 	return INTEL_BTS_AUXTRACE_PRIV_SIZE;
 }
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index f05daacc9..a3395179c 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -89,7 +89,7 @@ static int intel_pt_parse_terms_with_default(struct list_head *formats,
 
 	*config = attr.config;
 out_free:
-	parse_events__free_terms(terms);
+	parse_events_terms__delete(terms);
 	return err;
 }
 
@@ -273,7 +273,9 @@ intel_pt_pmu_default_config(struct perf_pmu *intel_pt_pmu)
 	return attr;
 }
 
-static size_t intel_pt_info_priv_size(struct auxtrace_record *itr __maybe_unused)
+static size_t
+intel_pt_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+			struct perf_evlist *evlist __maybe_unused)
 {
 	return INTEL_PT_AUXTRACE_PRIV_SIZE;
 }
diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c
index 14e4e668f..b63d4be65 100644
--- a/tools/perf/arch/x86/util/kvm-stat.c
+++ b/tools/perf/arch/x86/util/kvm-stat.c
@@ -1,5 +1,7 @@
 #include "../../util/kvm-stat.h"
-#include <asm/kvm_perf.h>
+#include <asm/svm.h>
+#include <asm/vmx.h>
+#include <asm/kvm.h>
 
 define_exit_reasons_table(vmx_exit_reasons, VMX_EXIT_REASONS);
 define_exit_reasons_table(svm_exit_reasons, SVM_EXIT_REASONS);
@@ -11,6 +13,12 @@ static struct kvm_events_ops exit_events = {
 	.name = "VM-EXIT"
 };
 
+const char *vcpu_id_str = "vcpu_id";
+const int decode_str_len = 20;
+const char *kvm_exit_reason = "exit_reason";
+const char *kvm_entry_trace = "kvm:kvm_entry";
+const char *kvm_exit_trace = "kvm:kvm_exit";
+
 /*
  * For the mmio events, we treat:
  * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry
@@ -65,7 +73,7 @@ static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
 				  struct event_key *key,
 				  char *decode)
 {
-	scnprintf(decode, DECODE_STR_LEN, "%#lx:%s",
+	scnprintf(decode, decode_str_len, "%#lx:%s",
 		  (unsigned long)key->key,
 		  key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R");
 }
@@ -109,7 +117,7 @@ static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
 				    struct event_key *key,
 				    char *decode)
 {
-	scnprintf(decode, DECODE_STR_LEN, "%#llx:%s",
+	scnprintf(decode, decode_str_len, "%#llx:%s",
 		  (unsigned long long)key->key,
 		  key->info ? "POUT" : "PIN");
 }
@@ -121,7 +129,7 @@ static struct kvm_events_ops ioport_events = {
 	.name = "IO Port Access"
 };
 
-const char * const kvm_events_tp[] = {
+const char *kvm_events_tp[] = {
 	"kvm:kvm_entry",
 	"kvm:kvm_exit",
 	"kvm:kvm_mmio",
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index a50df86f2..579a59299 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -25,19 +25,17 @@
 # endif
 #endif
 
-extern int bench_numa(int argc, const char **argv, const char *prefix);
-extern int bench_sched_messaging(int argc, const char **argv, const char *prefix);
-extern int bench_sched_pipe(int argc, const char **argv, const char *prefix);
-extern int bench_mem_memcpy(int argc, const char **argv,
-			    const char *prefix __maybe_unused);
-extern int bench_mem_memset(int argc, const char **argv, const char *prefix);
-extern int bench_futex_hash(int argc, const char **argv, const char *prefix);
-extern int bench_futex_wake(int argc, const char **argv, const char *prefix);
-extern int bench_futex_wake_parallel(int argc, const char **argv,
-				     const char *prefix);
-extern int bench_futex_requeue(int argc, const char **argv, const char *prefix);
+int bench_numa(int argc, const char **argv, const char *prefix);
+int bench_sched_messaging(int argc, const char **argv, const char *prefix);
+int bench_sched_pipe(int argc, const char **argv, const char *prefix);
+int bench_mem_memcpy(int argc, const char **argv, const char *prefix);
+int bench_mem_memset(int argc, const char **argv, const char *prefix);
+int bench_futex_hash(int argc, const char **argv, const char *prefix);
+int bench_futex_wake(int argc, const char **argv, const char *prefix);
+int bench_futex_wake_parallel(int argc, const char **argv, const char *prefix);
+int bench_futex_requeue(int argc, const char **argv, const char *prefix);
 /* pi futexes */
-extern int bench_futex_lock_pi(int argc, const char **argv, const char *prefix);
+int bench_futex_lock_pi(int argc, const char **argv, const char *prefix);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
 #define BENCH_FORMAT_DEFAULT		0
diff --git a/tools/perf/bench/mem-memcpy-arch.h b/tools/perf/bench/mem-memcpy-arch.h
index 57b4ed871..5aad2a940 100644
--- a/tools/perf/bench/mem-memcpy-arch.h
+++ b/tools/perf/bench/mem-memcpy-arch.h
@@ -2,7 +2,7 @@
 #ifdef HAVE_ARCH_X86_64_SUPPORT
 
 #define MEMCPY_FN(fn, name, desc)		\
-	extern void *fn(void *, const void *, size_t);
+	void *fn(void *, const void *, size_t);
 
 #include "mem-memcpy-x86-64-asm-def.h"
 
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index e4c2c3014..5c3cce082 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -1,6 +1,11 @@
+
+/* Various wrappers to make the kernel .S file build in user-space: */
+
 #define memcpy MEMCPY /* don't hide glibc's memcpy() */
 #define altinstr_replacement text
 #define globl p2align 4; .globl
+#define _ASM_EXTABLE_FAULT(x, y)
+
 #include "../../../arch/x86/lib/memcpy_64.S"
 /*
  * We need to provide note.GNU-stack section, saying that we want
diff --git a/tools/perf/bench/mem-memset-arch.h b/tools/perf/bench/mem-memset-arch.h
index 633800cb0..0d15786d9 100644
--- a/tools/perf/bench/mem-memset-arch.h
+++ b/tools/perf/bench/mem-memset-arch.h
@@ -2,7 +2,7 @@
 #ifdef HAVE_ARCH_X86_64_SUPPORT
 
 #define MEMSET_FN(fn, name, desc)		\
-	extern void *fn(void *, int, size_t);
+	void *fn(void *, int, size_t);
 
 #include "mem-memset-x86-64-asm-def.h"
 
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 5049d6357..7500d959d 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -293,7 +293,7 @@ static void bind_to_memnode(int node)
 	if (node == -1)
 		return;
 
-	BUG_ON(g->p.nr_nodes > (int)sizeof(nodemask));
+	BUG_ON(g->p.nr_nodes > (int)sizeof(nodemask)*8);
 	nodemask = 1L << node;
 
 	ret = set_mempolicy(MPOL_BIND, &nodemask, sizeof(nodemask)*8);
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index cc5c1267c..814158393 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -94,7 +94,7 @@ static int process_sample_event(struct perf_tool *tool,
 	struct addr_location al;
 	int ret = 0;
 
-	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
+	if (machine__resolve(machine, &al, sample) < 0) {
 		pr_warning("problem processing %d event, skipping it.\n",
 			   event->header.type);
 		return -1;
@@ -245,7 +245,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
 			hists__collapse_resort(hists, NULL);
 			/* Don't sort callchain */
 			perf_evsel__reset_sample_bit(pos, CALLCHAIN);
-			hists__output_resort(hists, NULL);
+			perf_evsel__output_resort(pos, NULL);
 
 			if (symbol_conf.event_group &&
 			    !perf_evsel__is_group_leader(pos))
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index d93bff7fc..632efc6b7 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -38,19 +38,7 @@ static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid)
 
 static int build_id_cache__kcore_dir(char *dir, size_t sz)
 {
-	struct timeval tv;
-	struct tm tm;
-	char dt[32];
-
-	if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm))
-		return -1;
-
-	if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm))
-		return -1;
-
-	scnprintf(dir, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000);
-
-	return 0;
+	return fetch_current_timestamp(dir, sz);
 }
 
 static bool same_kallsyms_reloc(const char *from_dir, char *to_dir)
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
index f04e804a9..c42448ed5 100644
--- a/tools/perf/builtin-config.c
+++ b/tools/perf/builtin-config.c
@@ -13,8 +13,10 @@
 #include "util/util.h"
 #include "util/debug.h"
 
+static bool use_system_config, use_user_config;
+
 static const char * const config_usage[] = {
-	"perf config [options]",
+	"perf config [<file-option>] [options]",
 	NULL
 };
 
@@ -25,6 +27,8 @@ enum actions {
 static struct option config_options[] = {
 	OPT_SET_UINT('l', "list", &actions,
 		     "show current config variables", ACTION_LIST),
+	OPT_BOOLEAN(0, "system", &use_system_config, "use system config file"),
+	OPT_BOOLEAN(0, "user", &use_user_config, "use user config file"),
 	OPT_END()
 };
 
@@ -42,10 +46,23 @@ static int show_config(const char *key, const char *value,
 int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	int ret = 0;
+	char *user_config = mkpath("%s/.perfconfig", getenv("HOME"));
 
 	argc = parse_options(argc, argv, config_options, config_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 
+	if (use_system_config && use_user_config) {
+		pr_err("Error: only one config file at a time\n");
+		parse_options_usage(config_usage, config_options, "user", 0);
+		parse_options_usage(NULL, config_options, "system", 0);
+		return -1;
+	}
+
+	if (use_system_config)
+		config_exclusive_filename = perf_etc_perfconfig();
+	else if (use_user_config)
+		config_exclusive_filename = user_config;
+
 	switch (actions) {
 	case ACTION_LIST:
 		if (argc) {
@@ -53,9 +70,13 @@ int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused)
 			parse_options_usage(config_usage, config_options, "l", 1);
 		} else {
 			ret = perf_config(show_config, NULL);
-			if (ret < 0)
+			if (ret < 0) {
+				const char * config_filename = config_exclusive_filename;
+				if (!config_exclusive_filename)
+					config_filename = user_config;
 				pr_err("Nothing configured, "
-				       "please check your ~/.perfconfig file\n");
+				       "please check your %s \n", config_filename);
+			}
 		}
 		break;
 	default:
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 36ccc2b88..8053a8cee 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -330,7 +330,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 	struct hists *hists = evsel__hists(evsel);
 	int ret = -1;
 
-	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
+	if (machine__resolve(machine, &al, sample) < 0) {
 		pr_warning("problem processing %d event, skipping it.\n",
 			   event->header.type);
 		return -1;
@@ -1264,8 +1264,6 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (ret < 0)
 		return ret;
 
-	perf_config(perf_default_config, NULL);
-
 	argc = parse_options(argc, argv, options, diff_usage, 0);
 
 	if (symbol__init(NULL) < 0)
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 96c1a4cfb..bc1de9b8f 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -86,8 +86,7 @@ static int check_emacsclient_version(void)
 		return -1;
 	}
 
-	strbuf_remove(&buffer, 0, strlen("emacsclient"));
-	version = atoi(buffer.buf);
+	version = atoi(buffer.buf + strlen("emacsclient"));
 
 	if (version < 22) {
 		fprintf(stderr,
@@ -107,12 +106,14 @@ static void exec_woman_emacs(const char *path, const char *page)
 
 	if (!check_emacsclient_version()) {
 		/* This works only with emacsclient version >= 22. */
-		struct strbuf man_page = STRBUF_INIT;
+		char *man_page;
 
 		if (!path)
 			path = "emacsclient";
-		strbuf_addf(&man_page, "(woman \"%s\")", page);
-		execlp(path, "emacsclient", "-e", man_page.buf, NULL);
+		if (asprintf(&man_page, "(woman \"%s\")", page) > 0) {
+			execlp(path, "emacsclient", "-e", man_page, NULL);
+			free(man_page);
+		}
 		warning("failed to exec '%s': %s", path,
 			strerror_r(errno, sbuf, sizeof(sbuf)));
 	}
@@ -123,7 +124,7 @@ static void exec_man_konqueror(const char *path, const char *page)
 	const char *display = getenv("DISPLAY");
 
 	if (display && *display) {
-		struct strbuf man_page = STRBUF_INIT;
+		char *man_page;
 		const char *filename = "kfmclient";
 		char sbuf[STRERR_BUFSIZE];
 
@@ -142,8 +143,10 @@ static void exec_man_konqueror(const char *path, const char *page)
 				filename = file;
 		} else
 			path = "kfmclient";
-		strbuf_addf(&man_page, "man:%s(1)", page);
-		execlp(path, filename, "newTab", man_page.buf, NULL);
+		if (asprintf(&man_page, "man:%s(1)", page) > 0) {
+			execlp(path, filename, "newTab", man_page, NULL);
+			free(man_page);
+		}
 		warning("failed to exec '%s': %s", path,
 			strerror_r(errno, sbuf, sizeof(sbuf)));
 	}
@@ -162,11 +165,13 @@ static void exec_man_man(const char *path, const char *page)
 
 static void exec_man_cmd(const char *cmd, const char *page)
 {
-	struct strbuf shell_cmd = STRBUF_INIT;
 	char sbuf[STRERR_BUFSIZE];
+	char *shell_cmd;
 
-	strbuf_addf(&shell_cmd, "%s %s", cmd, page);
-	execl("/bin/sh", "sh", "-c", shell_cmd.buf, NULL);
+	if (asprintf(&shell_cmd, "%s %s", cmd, page) > 0) {
+		execl("/bin/sh", "sh", "-c", shell_cmd, NULL);
+		free(shell_cmd);
+	}
 	warning("failed to exec '%s': %s", cmd,
 		strerror_r(errno, sbuf, sizeof(sbuf)));
 }
@@ -273,7 +278,7 @@ static int perf_help_config(const char *var, const char *value, void *cb)
 	if (!prefixcmp(var, "man."))
 		return add_man_viewer_info(var, value);
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 static struct cmdnames main_cmds, other_cmds;
@@ -300,43 +305,33 @@ static int is_perf_command(const char *s)
 		is_in_cmdlist(&other_cmds, s);
 }
 
-static const char *prepend(const char *prefix, const char *cmd)
-{
-	size_t pre_len = strlen(prefix);
-	size_t cmd_len = strlen(cmd);
-	char *p = malloc(pre_len + cmd_len + 1);
-	memcpy(p, prefix, pre_len);
-	strcpy(p + pre_len, cmd);
-	return p;
-}
-
 static const char *cmd_to_page(const char *perf_cmd)
 {
+	char *s;
+
 	if (!perf_cmd)
 		return "perf";
 	else if (!prefixcmp(perf_cmd, "perf"))
 		return perf_cmd;
-	else
-		return prepend("perf-", perf_cmd);
+
+	return asprintf(&s, "perf-%s", perf_cmd) < 0 ? NULL : s;
 }
 
 static void setup_man_path(void)
 {
-	struct strbuf new_path = STRBUF_INIT;
+	char *new_path;
 	const char *old_path = getenv("MANPATH");
 
 	/* We should always put ':' after our path. If there is no
 	 * old_path, the ':' at the end will let 'man' to try
 	 * system-wide paths after ours to find the manual page. If
 	 * there is old_path, we need ':' as delimiter. */
-	strbuf_addstr(&new_path, system_path(PERF_MAN_PATH));
-	strbuf_addch(&new_path, ':');
-	if (old_path)
-		strbuf_addstr(&new_path, old_path);
-
-	setenv("MANPATH", new_path.buf, 1);
-
-	strbuf_release(&new_path);
+	if (asprintf(&new_path, "%s:%s", system_path(PERF_MAN_PATH), old_path ?: "") > 0) {
+		setenv("MANPATH", new_path, 1);
+		free(new_path);
+	} else {
+		error("Unable to setup man path");
+	}
 }
 
 static void exec_viewer(const char *name, const char *page)
@@ -381,7 +376,7 @@ static int show_info_page(const char *perf_cmd)
 	return -1;
 }
 
-static int get_html_page_path(struct strbuf *page_path, const char *page)
+static int get_html_page_path(char **page_path, const char *page)
 {
 	struct stat st;
 	const char *html_path = system_path(PERF_HTML_PATH);
@@ -393,10 +388,7 @@ static int get_html_page_path(struct strbuf *page_path, const char *page)
 		return -1;
 	}
 
-	strbuf_init(page_path, 0);
-	strbuf_addf(page_path, "%s/%s.html", html_path, page);
-
-	return 0;
+	return asprintf(page_path, "%s/%s.html", html_path, page);
 }
 
 /*
@@ -414,12 +406,12 @@ static void open_html(const char *path)
 static int show_html_page(const char *perf_cmd)
 {
 	const char *page = cmd_to_page(perf_cmd);
-	struct strbuf page_path; /* it leaks but we exec bellow */
+	char *page_path; /* it leaks but we exec bellow */
 
-	if (get_html_page_path(&page_path, page) != 0)
+	if (get_html_page_path(&page_path, page) < 0)
 		return -1;
 
-	open_html(page_path.buf);
+	open_html(page_path);
 
 	return 0;
 }
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 0022e02ed..d1a2d104f 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -17,6 +17,7 @@
 #include "util/build-id.h"
 #include "util/data.h"
 #include "util/auxtrace.h"
+#include "util/jit.h"
 
 #include <subcmd/parse-options.h>
 
@@ -29,6 +30,7 @@ struct perf_inject {
 	bool			sched_stat;
 	bool			have_auxtrace;
 	bool			strip;
+	bool			jit_mode;
 	const char		*input_name;
 	struct perf_data_file	output;
 	u64			bytes_written;
@@ -71,6 +73,15 @@ static int perf_event__repipe_oe_synth(struct perf_tool *tool,
 	return perf_event__repipe_synth(tool, event);
 }
 
+#ifdef HAVE_JITDUMP
+static int perf_event__drop_oe(struct perf_tool *tool __maybe_unused,
+			       union perf_event *event __maybe_unused,
+			       struct ordered_events *oe __maybe_unused)
+{
+	return 0;
+}
+#endif
+
 static int perf_event__repipe_op2_synth(struct perf_tool *tool,
 					union perf_event *event,
 					struct perf_session *session
@@ -120,8 +131,7 @@ static int copy_bytes(struct perf_inject *inject, int fd, off_t size)
 
 static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
 				       union perf_event *event,
-				       struct perf_session *session
-				       __maybe_unused)
+				       struct perf_session *session)
 {
 	struct perf_inject *inject = container_of(tool, struct perf_inject,
 						  tool);
@@ -234,6 +244,31 @@ static int perf_event__repipe_mmap(struct perf_tool *tool,
 	return err;
 }
 
+#ifdef HAVE_JITDUMP
+static int perf_event__jit_repipe_mmap(struct perf_tool *tool,
+				       union perf_event *event,
+				       struct perf_sample *sample,
+				       struct machine *machine)
+{
+	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
+	u64 n = 0;
+	int ret;
+
+	/*
+	 * if jit marker, then inject jit mmaps and generate ELF images
+	 */
+	ret = jit_process(inject->session, &inject->output, machine,
+			  event->mmap.filename, sample->pid, &n);
+	if (ret < 0)
+		return ret;
+	if (ret) {
+		inject->bytes_written += n;
+		return 0;
+	}
+	return perf_event__repipe_mmap(tool, event, sample, machine);
+}
+#endif
+
 static int perf_event__repipe_mmap2(struct perf_tool *tool,
 				   union perf_event *event,
 				   struct perf_sample *sample,
@@ -247,6 +282,31 @@ static int perf_event__repipe_mmap2(struct perf_tool *tool,
 	return err;
 }
 
+#ifdef HAVE_JITDUMP
+static int perf_event__jit_repipe_mmap2(struct perf_tool *tool,
+					union perf_event *event,
+					struct perf_sample *sample,
+					struct machine *machine)
+{
+	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
+	u64 n = 0;
+	int ret;
+
+	/*
+	 * if jit marker, then inject jit mmaps and generate ELF images
+	 */
+	ret = jit_process(inject->session, &inject->output, machine,
+			  event->mmap2.filename, sample->pid, &n);
+	if (ret < 0)
+		return ret;
+	if (ret) {
+		inject->bytes_written += n;
+		return 0;
+	}
+	return perf_event__repipe_mmap2(tool, event, sample, machine);
+}
+#endif
+
 static int perf_event__repipe_fork(struct perf_tool *tool,
 				   union perf_event *event,
 				   struct perf_sample *sample,
@@ -356,9 +416,6 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
 {
 	struct addr_location al;
 	struct thread *thread;
-	u8 cpumode;
-
-	cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
 	thread = machine__findnew_thread(machine, sample->pid, sample->tid);
 	if (thread == NULL) {
@@ -367,7 +424,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
 		goto repipe;
 	}
 
-	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, &al);
+	thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, &al);
 
 	if (al.map != NULL) {
 		if (!al.map->dso->hit) {
@@ -626,12 +683,16 @@ static int __cmd_inject(struct perf_inject *inject)
 	ret = perf_session__process_events(session);
 
 	if (!file_out->is_pipe) {
-		if (inject->build_ids) {
+		if (inject->build_ids)
 			perf_header__set_feat(&session->header,
 					      HEADER_BUILD_ID);
-			if (inject->have_auxtrace)
-				dsos__hit_all(session);
-		}
+		/*
+		 * Keep all buildids when there is unprocessed AUX data because
+		 * it is not known which ones the AUX trace hits.
+		 */
+		if (perf_header__has_feat(&session->header, HEADER_BUILD_ID) &&
+		    inject->have_auxtrace && !inject->itrace_synth_opts.set)
+			dsos__hit_all(session);
 		/*
 		 * The AUX areas have been removed and replaced with
 		 * synthesized hardware events, so clear the feature flag and
@@ -703,7 +764,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 	};
 	int ret;
 
-	const struct option options[] = {
+	struct option options[] = {
 		OPT_BOOLEAN('b', "build-ids", &inject.build_ids,
 			    "Inject build-ids into the output stream"),
 		OPT_STRING('i', "input", &inject.input_name, "file",
@@ -713,6 +774,9 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 		OPT_BOOLEAN('s', "sched-stat", &inject.sched_stat,
 			    "Merge sched-stat and sched-switch for getting events "
 			    "where and how long tasks slept"),
+#ifdef HAVE_JITDUMP
+		OPT_BOOLEAN('j', "jit", &inject.jit_mode, "merge jitdump files into perf.data file"),
+#endif
 		OPT_INCR('v', "verbose", &verbose,
 			 "be more verbose (show build ids, etc)"),
 		OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file",
@@ -729,7 +793,9 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 		"perf inject [<options>]",
 		NULL
 	};
-
+#ifndef HAVE_JITDUMP
+	set_option_nobuild(options, 'j', "jit", "NO_LIBELF=1", true);
+#endif
 	argc = parse_options(argc, argv, options, inject_usage, 0);
 
 	/*
@@ -755,6 +821,29 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (inject.session == NULL)
 		return -1;
 
+	if (inject.build_ids) {
+		/*
+		 * to make sure the mmap records are ordered correctly
+		 * and so that the correct especially due to jitted code
+		 * mmaps. We cannot generate the buildid hit list and
+		 * inject the jit mmaps at the same time for now.
+		 */
+		inject.tool.ordered_events = true;
+		inject.tool.ordering_requires_timestamps = true;
+	}
+#ifdef HAVE_JITDUMP
+	if (inject.jit_mode) {
+		inject.tool.mmap2	   = perf_event__jit_repipe_mmap2;
+		inject.tool.mmap	   = perf_event__jit_repipe_mmap;
+		inject.tool.ordered_events = true;
+		inject.tool.ordering_requires_timestamps = true;
+		/*
+		 * JIT MMAP injection injects all MMAP events in one go, so it
+		 * does not obey finished_round semantics.
+		 */
+		inject.tool.finished_round = perf_event__drop_oe;
+	}
+#endif
 	ret = symbol__init(&inject.session->header.env);
 	if (ret < 0)
 		goto out_delete;
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 118010553..c9cb3be47 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -602,7 +602,7 @@ static int gfpcmp(const void *a, const void *b)
 	return fa->flags - fb->flags;
 }
 
-/* see include/trace/events/gfpflags.h */
+/* see include/trace/events/mmflags.h */
 static const struct {
 	const char *original;
 	const char *compact;
@@ -612,30 +612,39 @@ static const struct {
 	{ "GFP_HIGHUSER",		"HU" },
 	{ "GFP_USER",			"U" },
 	{ "GFP_TEMPORARY",		"TMP" },
+	{ "GFP_KERNEL_ACCOUNT",		"KAC" },
 	{ "GFP_KERNEL",			"K" },
 	{ "GFP_NOFS",			"NF" },
 	{ "GFP_ATOMIC",			"A" },
 	{ "GFP_NOIO",			"NI" },
-	{ "GFP_HIGH",			"H" },
-	{ "GFP_WAIT",			"W" },
-	{ "GFP_IO",			"I" },
-	{ "GFP_COLD",			"CO" },
-	{ "GFP_NOWARN",			"NWR" },
-	{ "GFP_REPEAT",			"R" },
-	{ "GFP_NOFAIL",			"NF" },
-	{ "GFP_NORETRY",		"NR" },
-	{ "GFP_COMP",			"C" },
-	{ "GFP_ZERO",			"Z" },
-	{ "GFP_NOMEMALLOC",		"NMA" },
-	{ "GFP_MEMALLOC",		"MA" },
-	{ "GFP_HARDWALL",		"HW" },
-	{ "GFP_THISNODE",		"TN" },
-	{ "GFP_RECLAIMABLE",		"RC" },
-	{ "GFP_MOVABLE",		"M" },
-	{ "GFP_NOTRACK",		"NT" },
-	{ "GFP_NO_KSWAPD",		"NK" },
-	{ "GFP_OTHER_NODE",		"ON" },
 	{ "GFP_NOWAIT",			"NW" },
+	{ "GFP_DMA",			"D" },
+	{ "__GFP_HIGHMEM",		"HM" },
+	{ "GFP_DMA32",			"D32" },
+	{ "__GFP_HIGH",			"H" },
+	{ "__GFP_ATOMIC",		"_A" },
+	{ "__GFP_IO",			"I" },
+	{ "__GFP_FS",			"F" },
+	{ "__GFP_COLD",			"CO" },
+	{ "__GFP_NOWARN",		"NWR" },
+	{ "__GFP_REPEAT",		"R" },
+	{ "__GFP_NOFAIL",		"NF" },
+	{ "__GFP_NORETRY",		"NR" },
+	{ "__GFP_COMP",			"C" },
+	{ "__GFP_ZERO",			"Z" },
+	{ "__GFP_NOMEMALLOC",		"NMA" },
+	{ "__GFP_MEMALLOC",		"MA" },
+	{ "__GFP_HARDWALL",		"HW" },
+	{ "__GFP_THISNODE",		"TN" },
+	{ "__GFP_RECLAIMABLE",		"RC" },
+	{ "__GFP_MOVABLE",		"M" },
+	{ "__GFP_ACCOUNT",		"AC" },
+	{ "__GFP_NOTRACK",		"NT" },
+	{ "__GFP_WRITE",		"WR" },
+	{ "__GFP_RECLAIM",		"R" },
+	{ "__GFP_DIRECT_RECLAIM",	"DR" },
+	{ "__GFP_KSWAPD_RECLAIM",	"KR" },
+	{ "__GFP_OTHER_NODE",		"ON" },
 };
 
 static size_t max_gfp_len;
@@ -1834,7 +1843,7 @@ static int __cmd_record(int argc, const char **argv)
 	return cmd_record(i, rec_argv, NULL);
 }
 
-static int kmem_config(const char *var, const char *value, void *cb)
+static int kmem_config(const char *var, const char *value, void *cb __maybe_unused)
 {
 	if (!strcmp(var, "kmem.default")) {
 		if (!strcmp(value, "slab"))
@@ -1847,7 +1856,7 @@ static int kmem_config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 4418d9214..bff666458 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -30,7 +30,6 @@
 #include <math.h>
 
 #ifdef HAVE_KVM_STAT_SUPPORT
-#include <asm/kvm_perf.h>
 #include "util/kvm-stat.h"
 
 void exit_event_get_key(struct perf_evsel *evsel,
@@ -38,12 +37,12 @@ void exit_event_get_key(struct perf_evsel *evsel,
 			struct event_key *key)
 {
 	key->info = 0;
-	key->key = perf_evsel__intval(evsel, sample, KVM_EXIT_REASON);
+	key->key = perf_evsel__intval(evsel, sample, kvm_exit_reason);
 }
 
 bool kvm_exit_event(struct perf_evsel *evsel)
 {
-	return !strcmp(evsel->name, KVM_EXIT_TRACE);
+	return !strcmp(evsel->name, kvm_exit_trace);
 }
 
 bool exit_event_begin(struct perf_evsel *evsel,
@@ -59,7 +58,7 @@ bool exit_event_begin(struct perf_evsel *evsel,
 
 bool kvm_entry_event(struct perf_evsel *evsel)
 {
-	return !strcmp(evsel->name, KVM_ENTRY_TRACE);
+	return !strcmp(evsel->name, kvm_entry_trace);
 }
 
 bool exit_event_end(struct perf_evsel *evsel,
@@ -91,7 +90,7 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm,
 	const char *exit_reason = get_exit_reason(kvm, key->exit_reasons,
 						  key->key);
 
-	scnprintf(decode, DECODE_STR_LEN, "%s", exit_reason);
+	scnprintf(decode, decode_str_len, "%s", exit_reason);
 }
 
 static bool register_kvm_events_ops(struct perf_kvm_stat *kvm)
@@ -357,7 +356,7 @@ static bool handle_end_event(struct perf_kvm_stat *kvm,
 	time_diff = sample->time - time_begin;
 
 	if (kvm->duration && time_diff > kvm->duration) {
-		char decode[DECODE_STR_LEN];
+		char decode[decode_str_len];
 
 		kvm->events_ops->decode_key(kvm, &event->key, decode);
 		if (!skip_event(decode)) {
@@ -385,7 +384,8 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread,
 			return NULL;
 		}
 
-		vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, VCPU_ID);
+		vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample,
+							  vcpu_id_str);
 		thread__set_priv(thread, vcpu_record);
 	}
 
@@ -574,7 +574,7 @@ static void show_timeofday(void)
 
 static void print_result(struct perf_kvm_stat *kvm)
 {
-	char decode[DECODE_STR_LEN];
+	char decode[decode_str_len];
 	struct kvm_event *event;
 	int vcpu = kvm->trace_vcpu;
 
@@ -585,7 +585,7 @@ static void print_result(struct perf_kvm_stat *kvm)
 
 	pr_info("\n\n");
 	print_vcpu_info(kvm);
-	pr_info("%*s ", DECODE_STR_LEN, kvm->events_ops->name);
+	pr_info("%*s ", decode_str_len, kvm->events_ops->name);
 	pr_info("%10s ", "Samples");
 	pr_info("%9s ", "Samples%");
 
@@ -604,7 +604,7 @@ static void print_result(struct perf_kvm_stat *kvm)
 		min = get_event_min(event, vcpu);
 
 		kvm->events_ops->decode_key(kvm, &event->key, decode);
-		pr_info("%*s ", DECODE_STR_LEN, decode);
+		pr_info("%*s ", decode_str_len, decode);
 		pr_info("%10llu ", (unsigned long long)ecount);
 		pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100);
 		pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100);
@@ -1132,6 +1132,11 @@ exit:
 		_p;			\
 	})
 
+int __weak setup_kvm_events_tp(struct perf_kvm_stat *kvm __maybe_unused)
+{
+	return 0;
+}
+
 static int
 kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
 {
@@ -1148,7 +1153,14 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
 		NULL
 	};
 	const char * const *events_tp;
+	int ret;
+
 	events_tp_size = 0;
+	ret = setup_kvm_events_tp(kvm);
+	if (ret < 0) {
+		pr_err("Unable to setup the kvm tracepoints\n");
+		return ret;
+	}
 
 	for (events_tp = kvm_events_tp; *events_tp; events_tp++)
 		events_tp_size++;
@@ -1377,6 +1389,12 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	/*
 	 * generate the event list
 	 */
+	err = setup_kvm_events_tp(kvm);
+	if (err < 0) {
+		pr_err("Unable to setup the kvm tracepoints\n");
+		return err;
+	}
+
 	kvm->evlist = kvm_live_event_list();
 	if (kvm->evlist == NULL) {
 		err = -1;
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 390170041..85db3be4b 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -6,6 +6,8 @@
 #include "util/tool.h"
 #include "util/session.h"
 #include "util/data.h"
+#include "util/mem-events.h"
+#include "util/debug.h"
 
 #define MEM_OPERATION_LOAD	0x1
 #define MEM_OPERATION_STORE	0x2
@@ -21,11 +23,56 @@ struct perf_mem {
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
+static int parse_record_events(const struct option *opt,
+			       const char *str, int unset __maybe_unused)
+{
+	struct perf_mem *mem = *(struct perf_mem **)opt->value;
+	int j;
+
+	if (strcmp(str, "list")) {
+		if (!perf_mem_events__parse(str)) {
+			mem->operation = 0;
+			return 0;
+		}
+		exit(-1);
+	}
+
+	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+		struct perf_mem_event *e = &perf_mem_events[j];
+
+		fprintf(stderr, "%-13s%-*s%s\n",
+			e->tag,
+			verbose ? 25 : 0,
+			verbose ? perf_mem_events__name(j) : "",
+			e->supported ? ": available" : "");
+	}
+	exit(0);
+}
+
+static const char * const __usage[] = {
+	"perf mem record [<options>] [<command>]",
+	"perf mem record [<options>] -- <command> [<options>]",
+	NULL
+};
+
+static const char * const *record_mem_usage = __usage;
+
 static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 {
 	int rec_argc, i = 0, j;
 	const char **rec_argv;
 	int ret;
+	struct option options[] = {
+	OPT_CALLBACK('e', "event", &mem, "event",
+		     "event selector. use 'perf mem record -e list' to list available events",
+		     parse_record_events),
+	OPT_INCR('v', "verbose", &verbose,
+		 "be more verbose (show counter open errors, etc)"),
+	OPT_END()
+	};
+
+	argc = parse_options(argc, argv, options, record_mem_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
 
 	rec_argc = argc + 7; /* max number of arguments */
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
@@ -35,23 +82,40 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	rec_argv[i++] = "record";
 
 	if (mem->operation & MEM_OPERATION_LOAD)
+		perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true;
+
+	if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record)
 		rec_argv[i++] = "-W";
 
 	rec_argv[i++] = "-d";
 
-	if (mem->operation & MEM_OPERATION_LOAD) {
-		rec_argv[i++] = "-e";
-		rec_argv[i++] = "cpu/mem-loads/pp";
-	}
+	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+		if (!perf_mem_events[j].record)
+			continue;
+
+		if (!perf_mem_events[j].supported) {
+			pr_err("failed: event '%s' not supported\n",
+			       perf_mem_events__name(j));
+			return -1;
+		}
 
-	if (mem->operation & MEM_OPERATION_STORE) {
 		rec_argv[i++] = "-e";
-		rec_argv[i++] = "cpu/mem-stores/pp";
-	}
+		rec_argv[i++] = perf_mem_events__name(j);
+	};
 
-	for (j = 1; j < argc; j++, i++)
+	for (j = 0; j < argc; j++, i++)
 		rec_argv[i] = argv[j];
 
+	if (verbose > 0) {
+		pr_debug("calling: record ");
+
+		while (rec_argv[j]) {
+			pr_debug("%s ", rec_argv[j]);
+			j++;
+		}
+		pr_debug("\n");
+	}
+
 	ret = cmd_record(i, rec_argv, NULL);
 	free(rec_argv);
 	return ret;
@@ -67,7 +131,7 @@ dump_raw_samples(struct perf_tool *tool,
 	struct addr_location al;
 	const char *fmt;
 
-	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
+	if (machine__resolve(machine, &al, sample) < 0) {
 		fprintf(stderr, "problem processing %d event, skipping it.\n",
 				event->header.type);
 		return -1;
@@ -298,6 +362,10 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
 		NULL
 	};
 
+	if (perf_mem_events__init()) {
+		pr_err("failed: memory events not supported\n");
+		return -1;
+	}
 
 	argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands,
 					mem_usage, PARSE_OPT_STOP_AT_NON_OPTION);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 319712a4e..515510ecc 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -32,6 +32,8 @@
 #include "util/parse-branch-options.h"
 #include "util/parse-regs-options.h"
 #include "util/llvm-utils.h"
+#include "util/bpf-loader.h"
+#include "asm/bug.h"
 
 #include <unistd.h>
 #include <sched.h>
@@ -49,7 +51,9 @@ struct record {
 	const char		*progname;
 	int			realtime_prio;
 	bool			no_buildid;
+	bool			no_buildid_set;
 	bool			no_buildid_cache;
+	bool			no_buildid_cache_set;
 	bool			buildid_all;
 	unsigned long long	samples;
 };
@@ -320,7 +324,10 @@ try_again:
 		} else {
 			pr_err("failed to mmap with %d (%s)\n", errno,
 				strerror_r(errno, msg, sizeof(msg)));
-			rc = -errno;
+			if (errno)
+				rc = -errno;
+			else
+				rc = -EINVAL;
 		}
 		goto out;
 	}
@@ -464,6 +471,29 @@ static void record__init_features(struct record *rec)
 	perf_header__clear_feat(&session->header, HEADER_STAT);
 }
 
+static void
+record__finish_output(struct record *rec)
+{
+	struct perf_data_file *file = &rec->file;
+	int fd = perf_data_file__fd(file);
+
+	if (file->is_pipe)
+		return;
+
+	rec->session->header.data_size += rec->bytes_written;
+	file->size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);
+
+	if (!rec->no_buildid) {
+		process_buildids(rec);
+
+		if (rec->buildid_all)
+			dsos__hit_all(rec->session);
+	}
+	perf_session__write_header(rec->session, rec->evlist, fd, true);
+
+	return;
+}
+
 static volatile int workload_exec_errno;
 
 /*
@@ -482,6 +512,74 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
 
 static void snapshot_sig_handler(int sig);
 
+static int record__synthesize(struct record *rec)
+{
+	struct perf_session *session = rec->session;
+	struct machine *machine = &session->machines.host;
+	struct perf_data_file *file = &rec->file;
+	struct record_opts *opts = &rec->opts;
+	struct perf_tool *tool = &rec->tool;
+	int fd = perf_data_file__fd(file);
+	int err = 0;
+
+	if (file->is_pipe) {
+		err = perf_event__synthesize_attrs(tool, session,
+						   process_synthesized_event);
+		if (err < 0) {
+			pr_err("Couldn't synthesize attrs.\n");
+			goto out;
+		}
+
+		if (have_tracepoints(&rec->evlist->entries)) {
+			/*
+			 * FIXME err <= 0 here actually means that
+			 * there were no tracepoints so its not really
+			 * an error, just that we don't need to
+			 * synthesize anything.  We really have to
+			 * return this more properly and also
+			 * propagate errors that now are calling die()
+			 */
+			err = perf_event__synthesize_tracing_data(tool,	fd, rec->evlist,
+								  process_synthesized_event);
+			if (err <= 0) {
+				pr_err("Couldn't record tracing data.\n");
+				goto out;
+			}
+			rec->bytes_written += err;
+		}
+	}
+
+	if (rec->opts.full_auxtrace) {
+		err = perf_event__synthesize_auxtrace_info(rec->itr, tool,
+					session, process_synthesized_event);
+		if (err)
+			goto out;
+	}
+
+	err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
+						 machine);
+	WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n"
+			   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+			   "Check /proc/kallsyms permission or run as root.\n");
+
+	err = perf_event__synthesize_modules(tool, process_synthesized_event,
+					     machine);
+	WARN_ONCE(err < 0, "Couldn't record kernel module information.\n"
+			   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+			   "Check /proc/modules permission or run as root.\n");
+
+	if (perf_guest) {
+		machines__process_guests(&session->machines,
+					 perf_event__synthesize_guest_os, tool);
+	}
+
+	err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
+					    process_synthesized_event, opts->sample_address,
+					    opts->proc_map_timeout);
+out:
+	return err;
+}
+
 static int __cmd_record(struct record *rec, int argc, const char **argv)
 {
 	int err;
@@ -534,6 +632,16 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		goto out_child;
 	}
 
+	err = bpf__apply_obj_config();
+	if (err) {
+		char errbuf[BUFSIZ];
+
+		bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf));
+		pr_err("ERROR: Apply config to BPF failed: %s\n",
+			 errbuf);
+		goto out_child;
+	}
+
 	/*
 	 * Normally perf_session__new would do this, but it doesn't have the
 	 * evlist.
@@ -566,63 +674,8 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
 	machine = &session->machines.host;
 
-	if (file->is_pipe) {
-		err = perf_event__synthesize_attrs(tool, session,
-						   process_synthesized_event);
-		if (err < 0) {
-			pr_err("Couldn't synthesize attrs.\n");
-			goto out_child;
-		}
-
-		if (have_tracepoints(&rec->evlist->entries)) {
-			/*
-			 * FIXME err <= 0 here actually means that
-			 * there were no tracepoints so its not really
-			 * an error, just that we don't need to
-			 * synthesize anything.  We really have to
-			 * return this more properly and also
-			 * propagate errors that now are calling die()
-			 */
-			err = perf_event__synthesize_tracing_data(tool,	fd, rec->evlist,
-								  process_synthesized_event);
-			if (err <= 0) {
-				pr_err("Couldn't record tracing data.\n");
-				goto out_child;
-			}
-			rec->bytes_written += err;
-		}
-	}
-
-	if (rec->opts.full_auxtrace) {
-		err = perf_event__synthesize_auxtrace_info(rec->itr, tool,
-					session, process_synthesized_event);
-		if (err)
-			goto out_delete_session;
-	}
-
-	err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-						 machine);
-	if (err < 0)
-		pr_err("Couldn't record kernel reference relocation symbol\n"
-		       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
-		       "Check /proc/kallsyms permission or run as root.\n");
-
-	err = perf_event__synthesize_modules(tool, process_synthesized_event,
-					     machine);
+	err = record__synthesize(rec);
 	if (err < 0)
-		pr_err("Couldn't record kernel module information.\n"
-		       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
-		       "Check /proc/modules permission or run as root.\n");
-
-	if (perf_guest) {
-		machines__process_guests(&session->machines,
-					 perf_event__synthesize_guest_os, tool);
-	}
-
-	err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
-					    process_synthesized_event, opts->sample_address,
-					    opts->proc_map_timeout);
-	if (err != 0)
 		goto out_child;
 
 	if (rec->realtime_prio) {
@@ -758,18 +811,8 @@ out_child:
 	/* this will be recalculated during process_buildids() */
 	rec->samples = 0;
 
-	if (!err && !file->is_pipe) {
-		rec->session->header.data_size += rec->bytes_written;
-		file->size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);
-
-		if (!rec->no_buildid) {
-			process_buildids(rec);
-
-			if (rec->buildid_all)
-				dsos__hit_all(rec->session);
-		}
-		perf_session__write_header(rec->session, rec->evlist, fd, true);
-	}
+	if (!err)
+		record__finish_output(rec);
 
 	if (!err && !quiet) {
 		char samples[128];
@@ -1097,10 +1140,12 @@ struct option __record_options[] = {
 	OPT_BOOLEAN('P', "period", &record.opts.period, "Record the sample period"),
 	OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples,
 		    "don't sample"),
-	OPT_BOOLEAN('N', "no-buildid-cache", &record.no_buildid_cache,
-		    "do not update the buildid cache"),
-	OPT_BOOLEAN('B', "no-buildid", &record.no_buildid,
-		    "do not collect buildids in perf.data"),
+	OPT_BOOLEAN_SET('N', "no-buildid-cache", &record.no_buildid_cache,
+			&record.no_buildid_cache_set,
+			"do not update the buildid cache"),
+	OPT_BOOLEAN_SET('B', "no-buildid", &record.no_buildid,
+			&record.no_buildid_set,
+			"do not collect buildids in perf.data"),
 	OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
 		     "monitor event in cgroup name only",
 		     parse_cgroups),
@@ -1136,6 +1181,12 @@ struct option __record_options[] = {
 			"per thread proc mmap processing timeout in ms"),
 	OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events,
 		    "Record context switch events"),
+	OPT_BOOLEAN_FLAG(0, "all-kernel", &record.opts.all_kernel,
+			 "Configure all used events to run in kernel space.",
+			 PARSE_OPT_EXCLUSIVE),
+	OPT_BOOLEAN_FLAG(0, "all-user", &record.opts.all_user,
+			 "Configure all used events to run in user space.",
+			 PARSE_OPT_EXCLUSIVE),
 	OPT_STRING(0, "clang-path", &llvm_param.clang_path, "clang path",
 		   "clang binary to use for compiling BPF scriptlets"),
 	OPT_STRING(0, "clang-opt", &llvm_param.clang_opt, "clang options",
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 2bf537f19..160ea23b4 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -41,6 +41,7 @@
 
 #include <dlfcn.h>
 #include <linux/bitmap.h>
+#include <linux/stringify.h>
 
 struct report {
 	struct perf_tool	tool;
@@ -75,7 +76,10 @@ static int report__config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 	if (!strcmp(var, "report.percent-limit")) {
-		rep->min_percent = strtof(value, NULL);
+		double pcnt = strtof(value, NULL);
+
+		rep->min_percent = pcnt;
+		callchain_param.min_percent = pcnt;
 		return 0;
 	}
 	if (!strcmp(var, "report.children")) {
@@ -87,7 +91,7 @@ static int report__config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 static int hist_iter__report_callback(struct hist_entry_iter *iter,
@@ -151,7 +155,7 @@ static int process_sample_event(struct perf_tool *tool,
 	};
 	int ret = 0;
 
-	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
+	if (machine__resolve(machine, &al, sample) < 0) {
 		pr_debug("problem processing %d event, skipping it.\n",
 			 event->header.type);
 		return -1;
@@ -466,10 +470,11 @@ static int report__browse_hists(struct report *rep)
 	return ret;
 }
 
-static void report__collapse_hists(struct report *rep)
+static int report__collapse_hists(struct report *rep)
 {
 	struct ui_progress prog;
 	struct perf_evsel *pos;
+	int ret = 0;
 
 	ui_progress__init(&prog, rep->nr_entries, "Merging related events...");
 
@@ -481,7 +486,9 @@ static void report__collapse_hists(struct report *rep)
 
 		hists->socket_filter = rep->socket_filter;
 
-		hists__collapse_resort(hists, &prog);
+		ret = hists__collapse_resort(hists, &prog);
+		if (ret < 0)
+			break;
 
 		/* Non-group events are considered as leader */
 		if (symbol_conf.event_group &&
@@ -494,6 +501,7 @@ static void report__collapse_hists(struct report *rep)
 	}
 
 	ui_progress__finish();
+	return ret;
 }
 
 static void report__output_resort(struct report *rep)
@@ -504,7 +512,7 @@ static void report__output_resort(struct report *rep)
 	ui_progress__init(&prog, rep->nr_entries, "Sorting events for output...");
 
 	evlist__for_each(rep->session->evlist, pos)
-		hists__output_resort(evsel__hists(pos), &prog);
+		perf_evsel__output_resort(pos, &prog);
 
 	ui_progress__finish();
 }
@@ -561,7 +569,11 @@ static int __cmd_report(struct report *rep)
 		}
 	}
 
-	report__collapse_hists(rep);
+	ret = report__collapse_hists(rep);
+	if (ret) {
+		ui__error("failed to process hist entry\n");
+		return ret;
+	}
 
 	if (session_done())
 		return 0;
@@ -633,8 +645,10 @@ parse_percent_limit(const struct option *opt, const char *str,
 		    int unset __maybe_unused)
 {
 	struct report *rep = opt->value;
+	double pcnt = strtof(str, NULL);
 
-	rep->min_percent = strtof(str, NULL);
+	rep->min_percent = pcnt;
+	callchain_param.min_percent = pcnt;
 	return 0;
 }
 
@@ -798,6 +812,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "only show processor socket that match with this filter"),
 	OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace,
 		    "Show raw trace event output (do not use print fmt or plugins)"),
+	OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
+		    "Show entries in a hierarchy"),
 	OPT_END()
 	};
 	struct perf_data_file file = {
@@ -907,13 +923,19 @@ repeat:
 		symbol_conf.cumulate_callchain = false;
 	}
 
-	if (setup_sorting(session->evlist) < 0) {
-		if (sort_order)
-			parse_options_usage(report_usage, options, "s", 1);
-		if (field_order)
-			parse_options_usage(sort_order ? NULL : report_usage,
-					    options, "F", 1);
-		goto error;
+	if (symbol_conf.report_hierarchy) {
+		/* disable incompatible options */
+		symbol_conf.event_group = false;
+		symbol_conf.cumulate_callchain = false;
+
+		if (field_order) {
+			pr_err("Error: --hierarchy and --fields options cannot be used together\n");
+			parse_options_usage(report_usage, options, "F", 1);
+			parse_options_usage(NULL, options, "hierarchy", 0);
+			goto error;
+		}
+
+		sort__need_collapse = true;
 	}
 
 	/* Force tty output for header output and per-thread stat. */
@@ -925,6 +947,15 @@ repeat:
 	else
 		use_browser = 0;
 
+	if (setup_sorting(session->evlist) < 0) {
+		if (sort_order)
+			parse_options_usage(report_usage, options, "s", 1);
+		if (field_order)
+			parse_options_usage(sort_order ? NULL : report_usage,
+					    options, "F", 1);
+		goto error;
+	}
+
 	if (report.header || report.header_only) {
 		perf_session__fprintf_info(session, stdout,
 					   report.show_full_info);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c691214d8..52826696c 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -23,6 +23,7 @@
 #include "util/stat.h"
 #include <linux/bitmap.h>
 #include "asm/bug.h"
+#include "util/mem-events.h"
 
 static char const		*script_name;
 static char const		*generate_script_lang;
@@ -58,6 +59,9 @@ enum perf_output_field {
 	PERF_OUTPUT_IREGS	    = 1U << 14,
 	PERF_OUTPUT_BRSTACK	    = 1U << 15,
 	PERF_OUTPUT_BRSTACKSYM	    = 1U << 16,
+	PERF_OUTPUT_DATA_SRC	    = 1U << 17,
+	PERF_OUTPUT_WEIGHT	    = 1U << 18,
+	PERF_OUTPUT_BPF_OUTPUT	    = 1U << 19,
 };
 
 struct output_option {
@@ -81,6 +85,9 @@ struct output_option {
 	{.str = "iregs", .field = PERF_OUTPUT_IREGS},
 	{.str = "brstack", .field = PERF_OUTPUT_BRSTACK},
 	{.str = "brstacksym", .field = PERF_OUTPUT_BRSTACKSYM},
+	{.str = "data_src", .field = PERF_OUTPUT_DATA_SRC},
+	{.str = "weight",   .field = PERF_OUTPUT_WEIGHT},
+	{.str = "bpf-output",   .field = PERF_OUTPUT_BPF_OUTPUT},
 };
 
 /* default set to maintain compatibility with current format */
@@ -101,7 +108,7 @@ static struct {
 			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
 			      PERF_OUTPUT_PERIOD,
 
-		.invalid_fields = PERF_OUTPUT_TRACE,
+		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
 
 	[PERF_TYPE_SOFTWARE] = {
@@ -111,7 +118,7 @@ static struct {
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
 			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_PERIOD,
+			      PERF_OUTPUT_PERIOD | PERF_OUTPUT_BPF_OUTPUT,
 
 		.invalid_fields = PERF_OUTPUT_TRACE,
 	},
@@ -121,7 +128,7 @@ static struct {
 
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 				  PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
-				  PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE,
+				  PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE
 	},
 
 	[PERF_TYPE_RAW] = {
@@ -131,9 +138,10 @@ static struct {
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
 			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_PERIOD,
+			      PERF_OUTPUT_PERIOD |  PERF_OUTPUT_ADDR |
+			      PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT,
 
-		.invalid_fields = PERF_OUTPUT_TRACE,
+		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
 
 	[PERF_TYPE_BREAKPOINT] = {
@@ -145,7 +153,7 @@ static struct {
 			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
 			      PERF_OUTPUT_PERIOD,
 
-		.invalid_fields = PERF_OUTPUT_TRACE,
+		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
 };
 
@@ -242,6 +250,16 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 					   PERF_OUTPUT_ADDR, allow_user_set))
 		return -EINVAL;
 
+	if (PRINT_FIELD(DATA_SRC) &&
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC",
+					PERF_OUTPUT_DATA_SRC))
+		return -EINVAL;
+
+	if (PRINT_FIELD(WEIGHT) &&
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT, "WEIGHT",
+					PERF_OUTPUT_WEIGHT))
+		return -EINVAL;
+
 	if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
 		pr_err("Display of symbols requested but neither sample IP nor "
 			   "sample address\nis selected. Hence, no addresses to convert "
@@ -387,9 +405,7 @@ out:
 	return 0;
 }
 
-static void print_sample_iregs(union perf_event *event __maybe_unused,
-			  struct perf_sample *sample,
-			  struct thread *thread __maybe_unused,
+static void print_sample_iregs(struct perf_sample *sample,
 			  struct perf_event_attr *attr)
 {
 	struct regs_dump *regs = &sample->intr_regs;
@@ -458,10 +474,7 @@ mispred_str(struct branch_entry *br)
 	return br->flags.predicted ? 'P' : 'M';
 }
 
-static void print_sample_brstack(union perf_event *event __maybe_unused,
-			  struct perf_sample *sample,
-			  struct thread *thread __maybe_unused,
-			  struct perf_event_attr *attr __maybe_unused)
+static void print_sample_brstack(struct perf_sample *sample)
 {
 	struct branch_stack *br = sample->branch_stack;
 	u64 i;
@@ -480,14 +493,11 @@ static void print_sample_brstack(union perf_event *event __maybe_unused,
 	}
 }
 
-static void print_sample_brstacksym(union perf_event *event __maybe_unused,
-			  struct perf_sample *sample,
-			  struct thread *thread __maybe_unused,
-			  struct perf_event_attr *attr __maybe_unused)
+static void print_sample_brstacksym(struct perf_sample *sample,
+				    struct thread *thread)
 {
 	struct branch_stack *br = sample->branch_stack;
 	struct addr_location alf, alt;
-	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	u64 i, from, to;
 
 	if (!(br && br->nr))
@@ -500,11 +510,11 @@ static void print_sample_brstacksym(union perf_event *event __maybe_unused,
 		from = br->entries[i].from;
 		to   = br->entries[i].to;
 
-		thread__find_addr_map(thread, cpumode, MAP__FUNCTION, from, &alf);
+		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf);
 		if (alf.map)
 			alf.sym = map__find_symbol(alf.map, alf.addr, NULL);
 
-		thread__find_addr_map(thread, cpumode, MAP__FUNCTION, to, &alt);
+		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
 		if (alt.map)
 			alt.sym = map__find_symbol(alt.map, alt.addr, NULL);
 
@@ -520,8 +530,7 @@ static void print_sample_brstacksym(union perf_event *event __maybe_unused,
 }
 
 
-static void print_sample_addr(union perf_event *event,
-			  struct perf_sample *sample,
+static void print_sample_addr(struct perf_sample *sample,
 			  struct thread *thread,
 			  struct perf_event_attr *attr)
 {
@@ -532,7 +541,7 @@ static void print_sample_addr(union perf_event *event,
 	if (!sample_addr_correlates_sym(attr))
 		return;
 
-	perf_event__preprocess_sample_addr(event, sample, thread, &al);
+	thread__resolve(thread, &al, sample);
 
 	if (PRINT_FIELD(SYM)) {
 		printf(" ");
@@ -549,8 +558,7 @@ static void print_sample_addr(union perf_event *event,
 	}
 }
 
-static void print_sample_bts(union perf_event *event,
-			     struct perf_sample *sample,
+static void print_sample_bts(struct perf_sample *sample,
 			     struct perf_evsel *evsel,
 			     struct thread *thread,
 			     struct addr_location *al)
@@ -580,7 +588,7 @@ static void print_sample_bts(union perf_event *event,
 	    ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
 	     !output[attr->type].user_set)) {
 		printf(" => ");
-		print_sample_addr(event, sample, thread, attr);
+		print_sample_addr(sample, thread, attr);
 	}
 
 	if (print_srcline_last)
@@ -608,6 +616,84 @@ static void print_sample_flags(u32 flags)
 	printf("  %-4s ", str);
 }
 
+struct printer_data {
+	int line_no;
+	bool hit_nul;
+	bool is_printable;
+};
+
+static void
+print_sample_bpf_output_printer(enum binary_printer_ops op,
+				unsigned int val,
+				void *extra)
+{
+	unsigned char ch = (unsigned char)val;
+	struct printer_data *printer_data = extra;
+
+	switch (op) {
+	case BINARY_PRINT_DATA_BEGIN:
+		printf("\n");
+		break;
+	case BINARY_PRINT_LINE_BEGIN:
+		printf("%17s", !printer_data->line_no ? "BPF output:" :
+						        "           ");
+		break;
+	case BINARY_PRINT_ADDR:
+		printf(" %04x:", val);
+		break;
+	case BINARY_PRINT_NUM_DATA:
+		printf(" %02x", val);
+		break;
+	case BINARY_PRINT_NUM_PAD:
+		printf("   ");
+		break;
+	case BINARY_PRINT_SEP:
+		printf("  ");
+		break;
+	case BINARY_PRINT_CHAR_DATA:
+		if (printer_data->hit_nul && ch)
+			printer_data->is_printable = false;
+
+		if (!isprint(ch)) {
+			printf("%c", '.');
+
+			if (!printer_data->is_printable)
+				break;
+
+			if (ch == '\0')
+				printer_data->hit_nul = true;
+			else
+				printer_data->is_printable = false;
+		} else {
+			printf("%c", ch);
+		}
+		break;
+	case BINARY_PRINT_CHAR_PAD:
+		printf(" ");
+		break;
+	case BINARY_PRINT_LINE_END:
+		printf("\n");
+		printer_data->line_no++;
+		break;
+	case BINARY_PRINT_DATA_END:
+	default:
+		break;
+	}
+}
+
+static void print_sample_bpf_output(struct perf_sample *sample)
+{
+	unsigned int nr_bytes = sample->raw_size;
+	struct printer_data printer_data = {0, false, true};
+
+	print_binary(sample->raw_data, nr_bytes, 8,
+		     print_sample_bpf_output_printer, &printer_data);
+
+	if (printer_data.is_printable && printer_data.hit_nul)
+		printf("%17s \"%s\"\n", "BPF string:",
+		       (char *)(sample->raw_data));
+}
+
 struct perf_script {
 	struct perf_tool	tool;
 	struct perf_session	*session;
@@ -634,7 +720,24 @@ static int perf_evlist__max_name_len(struct perf_evlist *evlist)
 	return max;
 }
 
-static void process_event(struct perf_script *script, union perf_event *event,
+static size_t data_src__printf(u64 data_src)
+{
+	struct mem_info mi = { .data_src.val = data_src };
+	char decode[100];
+	char out[100];
+	static int maxlen;
+	int len;
+
+	perf_script__meminfo_scnprintf(decode, 100, &mi);
+
+	len = scnprintf(out, 100, "%16" PRIx64 " %s", data_src, decode);
+	if (maxlen < len)
+		maxlen = len;
+
+	return printf("%-*s", maxlen, out);
+}
+
+static void process_event(struct perf_script *script,
 			  struct perf_sample *sample, struct perf_evsel *evsel,
 			  struct addr_location *al)
 {
@@ -663,7 +766,7 @@ static void process_event(struct perf_script *script, union perf_event *event,
 		print_sample_flags(sample->flags);
 
 	if (is_bts_event(attr)) {
-		print_sample_bts(event, sample, evsel, thread, al);
+		print_sample_bts(sample, evsel, thread, al);
 		return;
 	}
 
@@ -671,7 +774,13 @@ static void process_event(struct perf_script *script, union perf_event *event,
 		event_format__print(evsel->tp_format, sample->cpu,
 				    sample->raw_data, sample->raw_size);
 	if (PRINT_FIELD(ADDR))
-		print_sample_addr(event, sample, thread, attr);
+		print_sample_addr(sample, thread, attr);
+
+	if (PRINT_FIELD(DATA_SRC))
+		data_src__printf(sample->data_src);
+
+	if (PRINT_FIELD(WEIGHT))
+		printf("%16" PRIu64, sample->weight);
 
 	if (PRINT_FIELD(IP)) {
 		if (!symbol_conf.use_callchain)
@@ -685,12 +794,15 @@ static void process_event(struct perf_script *script, union perf_event *event,
 	}
 
 	if (PRINT_FIELD(IREGS))
-		print_sample_iregs(event, sample, thread, attr);
+		print_sample_iregs(sample, attr);
 
 	if (PRINT_FIELD(BRSTACK))
-		print_sample_brstack(event, sample, thread, attr);
+		print_sample_brstack(sample);
 	else if (PRINT_FIELD(BRSTACKSYM))
-		print_sample_brstacksym(event, sample, thread, attr);
+		print_sample_brstacksym(sample, thread);
+
+	if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
+		print_sample_bpf_output(sample);
 
 	printf("\n");
 }
@@ -783,7 +895,7 @@ static int process_sample_event(struct perf_tool *tool,
 		return 0;
 	}
 
-	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
+	if (machine__resolve(machine, &al, sample) < 0) {
 		pr_err("problem processing %d event, skipping it.\n",
 		       event->header.type);
 		return -1;
@@ -798,7 +910,7 @@ static int process_sample_event(struct perf_tool *tool,
 	if (scripting_ops)
 		scripting_ops->process_event(event, sample, evsel, &al);
 	else
-		process_event(scr, event, sample, evsel, &al);
+		process_event(scr, sample, evsel, &al);
 
 out_put:
 	addr_location__put(&al);
@@ -1090,23 +1202,6 @@ static struct script_spec *script_spec__find(const char *spec)
 	return NULL;
 }
 
-static struct script_spec *script_spec__findnew(const char *spec,
-						struct scripting_ops *ops)
-{
-	struct script_spec *s = script_spec__find(spec);
-
-	if (s)
-		return s;
-
-	s = script_spec__new(spec, ops);
-	if (!s)
-		return NULL;
-
-	script_spec__add(s);
-
-	return s;
-}
-
 int script_spec_register(const char *spec, struct scripting_ops *ops)
 {
 	struct script_spec *s;
@@ -1115,9 +1210,11 @@ int script_spec_register(const char *spec, struct scripting_ops *ops)
 	if (s)
 		return -1;
 
-	s = script_spec__findnew(spec, ops);
+	s = script_spec__new(spec, ops);
 	if (!s)
 		return -1;
+	else
+		script_spec__add(s);
 
 	return 0;
 }
@@ -1318,21 +1415,19 @@ static int is_directory(const char *base_path, const struct dirent *dent)
 	return S_ISDIR(st.st_mode);
 }
 
-#define for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next)\
-	while (!readdir_r(scripts_dir, &lang_dirent, &lang_next) &&	\
-	       lang_next)						\
-		if ((lang_dirent.d_type == DT_DIR ||			\
-		     (lang_dirent.d_type == DT_UNKNOWN &&		\
-		      is_directory(scripts_path, &lang_dirent))) &&	\
-		    (strcmp(lang_dirent.d_name, ".")) &&		\
-		    (strcmp(lang_dirent.d_name, "..")))
+#define for_each_lang(scripts_path, scripts_dir, lang_dirent)		\
+	while ((lang_dirent = readdir(scripts_dir)) != NULL)		\
+		if ((lang_dirent->d_type == DT_DIR ||			\
+		     (lang_dirent->d_type == DT_UNKNOWN &&		\
+		      is_directory(scripts_path, lang_dirent))) &&	\
+		    (strcmp(lang_dirent->d_name, ".")) &&		\
+		    (strcmp(lang_dirent->d_name, "..")))
 
-#define for_each_script(lang_path, lang_dir, script_dirent, script_next)\
-	while (!readdir_r(lang_dir, &script_dirent, &script_next) &&	\
-	       script_next)						\
-		if (script_dirent.d_type != DT_DIR &&			\
-		    (script_dirent.d_type != DT_UNKNOWN ||		\
-		     !is_directory(lang_path, &script_dirent)))
+#define for_each_script(lang_path, lang_dir, script_dirent)		\
+	while ((script_dirent = readdir(lang_dir)) != NULL)		\
+		if (script_dirent->d_type != DT_DIR &&			\
+		    (script_dirent->d_type != DT_UNKNOWN ||		\
+		     !is_directory(lang_path, script_dirent)))
 
 
 #define RECORD_SUFFIX			"-record"
@@ -1478,7 +1573,7 @@ static int list_available_scripts(const struct option *opt __maybe_unused,
 				  const char *s __maybe_unused,
 				  int unset __maybe_unused)
 {
-	struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
+	struct dirent *script_dirent, *lang_dirent;
 	char scripts_path[MAXPATHLEN];
 	DIR *scripts_dir, *lang_dir;
 	char script_path[MAXPATHLEN];
@@ -1493,19 +1588,19 @@ static int list_available_scripts(const struct option *opt __maybe_unused,
 	if (!scripts_dir)
 		return -1;
 
-	for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) {
+	for_each_lang(scripts_path, scripts_dir, lang_dirent) {
 		snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
-			 lang_dirent.d_name);
+			 lang_dirent->d_name);
 		lang_dir = opendir(lang_path);
 		if (!lang_dir)
 			continue;
 
-		for_each_script(lang_path, lang_dir, script_dirent, script_next) {
-			script_root = get_script_root(&script_dirent, REPORT_SUFFIX);
+		for_each_script(lang_path, lang_dir, script_dirent) {
+			script_root = get_script_root(script_dirent, REPORT_SUFFIX);
 			if (script_root) {
 				desc = script_desc__findnew(script_root);
 				snprintf(script_path, MAXPATHLEN, "%s/%s",
-					 lang_path, script_dirent.d_name);
+					 lang_path, script_dirent->d_name);
 				read_script_info(desc, script_path);
 				free(script_root);
 			}
@@ -1593,7 +1688,7 @@ static int check_ev_match(char *dir_name, char *scriptname,
  */
 int find_scripts(char **scripts_array, char **scripts_path_array)
 {
-	struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
+	struct dirent *script_dirent, *lang_dirent;
 	char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN];
 	DIR *scripts_dir, *lang_dir;
 	struct perf_session *session;
@@ -1616,9 +1711,9 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
 		return -1;
 	}
 
-	for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) {
+	for_each_lang(scripts_path, scripts_dir, lang_dirent) {
 		snprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path,
-			 lang_dirent.d_name);
+			 lang_dirent->d_name);
 #ifdef NO_LIBPERL
 		if (strstr(lang_path, "perl"))
 			continue;
@@ -1632,16 +1727,16 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
 		if (!lang_dir)
 			continue;
 
-		for_each_script(lang_path, lang_dir, script_dirent, script_next) {
+		for_each_script(lang_path, lang_dir, script_dirent) {
 			/* Skip those real time scripts: xxxtop.p[yl] */
-			if (strstr(script_dirent.d_name, "top."))
+			if (strstr(script_dirent->d_name, "top."))
 				continue;
 			sprintf(scripts_path_array[i], "%s/%s", lang_path,
-				script_dirent.d_name);
-			temp = strchr(script_dirent.d_name, '.');
+				script_dirent->d_name);
+			temp = strchr(script_dirent->d_name, '.');
 			snprintf(scripts_array[i],
-				(temp - script_dirent.d_name) + 1,
-				"%s", script_dirent.d_name);
+				(temp - script_dirent->d_name) + 1,
+				"%s", script_dirent->d_name);
 
 			if (check_ev_match(lang_path,
 					scripts_array[i], session))
@@ -1659,7 +1754,7 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
 
 static char *get_script_path(const char *script_root, const char *suffix)
 {
-	struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
+	struct dirent *script_dirent, *lang_dirent;
 	char scripts_path[MAXPATHLEN];
 	char script_path[MAXPATHLEN];
 	DIR *scripts_dir, *lang_dir;
@@ -1672,21 +1767,21 @@ static char *get_script_path(const char *script_root, const char *suffix)
 	if (!scripts_dir)
 		return NULL;
 
-	for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) {
+	for_each_lang(scripts_path, scripts_dir, lang_dirent) {
 		snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
-			 lang_dirent.d_name);
+			 lang_dirent->d_name);
 		lang_dir = opendir(lang_path);
 		if (!lang_dir)
 			continue;
 
-		for_each_script(lang_path, lang_dir, script_dirent, script_next) {
-			__script_root = get_script_root(&script_dirent, suffix);
+		for_each_script(lang_path, lang_dir, script_dirent) {
+			__script_root = get_script_root(script_dirent, suffix);
 			if (__script_root && !strcmp(script_root, __script_root)) {
 				free(__script_root);
 				closedir(lang_dir);
 				closedir(scripts_dir);
 				snprintf(script_path, MAXPATHLEN, "%s/%s",
-					 lang_path, script_dirent.d_name);
+					 lang_path, script_dirent->d_name);
 				return strdup(script_path);
 			}
 			free(__script_root);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 038e87708..307e8a1a0 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -122,6 +122,7 @@ static bool			sync_run			= false;
 static unsigned int		initial_delay			= 0;
 static unsigned int		unit_width			= 4; /* strlen("unit") */
 static bool			forever				= false;
+static bool			metric_only			= false;
 static struct timespec		ref_time;
 static struct cpu_map		*aggr_map;
 static aggr_get_id_t		aggr_get_id;
@@ -527,6 +528,7 @@ static int __run_perf_stat(int argc, const char **argv)
 		perf_evlist__set_leader(evsel_list);
 
 	evlist__for_each(evsel_list, counter) {
+try_again:
 		if (create_perf_stat_counter(counter) < 0) {
 			/*
 			 * PPC returns ENXIO for HW counters until 2.6.37
@@ -543,7 +545,11 @@ static int __run_perf_stat(int argc, const char **argv)
 				if ((counter->leader != counter) ||
 				    !(counter->leader->nr_members > 1))
 					continue;
-			}
+			} else if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
+                                if (verbose)
+                                        ui__warning("%s\n", msg);
+                                goto try_again;
+                        }
 
 			perf_evsel__open_strerror(counter, &target,
 						  errno, msg, sizeof(msg));
@@ -735,6 +741,191 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 	}
 }
 
+struct outstate {
+	FILE *fh;
+	bool newline;
+	const char *prefix;
+	int  nfields;
+	int  id, nr;
+	struct perf_evsel *evsel;
+};
+
+#define METRIC_LEN  35
+
+static void new_line_std(void *ctx)
+{
+	struct outstate *os = ctx;
+
+	os->newline = true;
+}
+
+static void do_new_line_std(struct outstate *os)
+{
+	fputc('\n', os->fh);
+	fputs(os->prefix, os->fh);
+	aggr_printout(os->evsel, os->id, os->nr);
+	if (stat_config.aggr_mode == AGGR_NONE)
+		fprintf(os->fh, "        ");
+	fprintf(os->fh, "                                                 ");
+}
+
+static void print_metric_std(void *ctx, const char *color, const char *fmt,
+			     const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	int n;
+	bool newline = os->newline;
+
+	os->newline = false;
+
+	if (unit == NULL || fmt == NULL) {
+		fprintf(out, "%-*s", METRIC_LEN, "");
+		return;
+	}
+
+	if (newline)
+		do_new_line_std(os);
+
+	n = fprintf(out, " # ");
+	if (color)
+		n += color_fprintf(out, color, fmt, val);
+	else
+		n += fprintf(out, fmt, val);
+	fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
+}
+
+static void new_line_csv(void *ctx)
+{
+	struct outstate *os = ctx;
+	int i;
+
+	fputc('\n', os->fh);
+	if (os->prefix)
+		fprintf(os->fh, "%s%s", os->prefix, csv_sep);
+	aggr_printout(os->evsel, os->id, os->nr);
+	for (i = 0; i < os->nfields; i++)
+		fputs(csv_sep, os->fh);
+}
+
+static void print_metric_csv(void *ctx,
+			     const char *color __maybe_unused,
+			     const char *fmt, const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[64], *vals, *ends;
+
+	if (unit == NULL || fmt == NULL) {
+		fprintf(out, "%s%s%s%s", csv_sep, csv_sep, csv_sep, csv_sep);
+		return;
+	}
+	snprintf(buf, sizeof(buf), fmt, val);
+	vals = buf;
+	while (isspace(*vals))
+		vals++;
+	ends = vals;
+	while (isdigit(*ends) || *ends == '.')
+		ends++;
+	*ends = 0;
+	while (isspace(*unit))
+		unit++;
+	fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit);
+}
+
+#define METRIC_ONLY_LEN 20
+
+/* Filter out some columns that don't work well in metrics only mode */
+
+static bool valid_only_metric(const char *unit)
+{
+	if (!unit)
+		return false;
+	if (strstr(unit, "/sec") ||
+	    strstr(unit, "hz") ||
+	    strstr(unit, "Hz") ||
+	    strstr(unit, "CPUs utilized"))
+		return false;
+	return true;
+}
+
+static const char *fixunit(char *buf, struct perf_evsel *evsel,
+			   const char *unit)
+{
+	if (!strncmp(unit, "of all", 6)) {
+		snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel),
+			 unit);
+		return buf;
+	}
+	return unit;
+}
+
+static void print_metric_only(void *ctx, const char *color, const char *fmt,
+			      const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	int n;
+	char buf[1024];
+	unsigned mlen = METRIC_ONLY_LEN;
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(buf, os->evsel, unit);
+	if (color)
+		n = color_fprintf(out, color, fmt, val);
+	else
+		n = fprintf(out, fmt, val);
+	if (n > METRIC_ONLY_LEN)
+		n = METRIC_ONLY_LEN;
+	if (mlen < strlen(unit))
+		mlen = strlen(unit) + 1;
+	fprintf(out, "%*s", mlen - n, "");
+}
+
+static void print_metric_only_csv(void *ctx, const char *color __maybe_unused,
+				  const char *fmt,
+				  const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[64], *vals, *ends;
+	char tbuf[1024];
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(tbuf, os->evsel, unit);
+	snprintf(buf, sizeof buf, fmt, val);
+	vals = buf;
+	while (isspace(*vals))
+		vals++;
+	ends = vals;
+	while (isdigit(*ends) || *ends == '.')
+		ends++;
+	*ends = 0;
+	fprintf(out, "%s%s", vals, csv_sep);
+}
+
+static void new_line_metric(void *ctx __maybe_unused)
+{
+}
+
+static void print_metric_header(void *ctx, const char *color __maybe_unused,
+				const char *fmt __maybe_unused,
+				const char *unit, double val __maybe_unused)
+{
+	struct outstate *os = ctx;
+	char tbuf[1024];
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(tbuf, os->evsel, unit);
+	if (csv_output)
+		fprintf(os->fh, "%s%s", unit, csv_sep);
+	else
+		fprintf(os->fh, "%-*s ", METRIC_ONLY_LEN, unit);
+}
+
 static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	FILE *output = stat_config.output;
@@ -763,6 +954,28 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
 }
 
+static int first_shadow_cpu(struct perf_evsel *evsel, int id)
+{
+	int i;
+
+	if (!aggr_get_id)
+		return 0;
+
+	if (stat_config.aggr_mode == AGGR_NONE)
+		return id;
+
+	if (stat_config.aggr_mode == AGGR_GLOBAL)
+		return 0;
+
+	for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
+		int cpu2 = perf_evsel__cpus(evsel)->map[i];
+
+		if (aggr_get_id(evsel_list->cpus, cpu2) == id)
+			return cpu2;
+	}
+	return 0;
+}
+
 static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	FILE *output = stat_config.output;
@@ -793,22 +1006,124 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
 }
 
-static void printout(int id, int nr, struct perf_evsel *counter, double uval)
+static void printout(int id, int nr, struct perf_evsel *counter, double uval,
+		     char *prefix, u64 run, u64 ena, double noise)
 {
-	int cpu = cpu_map__id_to_cpu(id);
+	struct perf_stat_output_ctx out;
+	struct outstate os = {
+		.fh = stat_config.output,
+		.prefix = prefix ? prefix : "",
+		.id = id,
+		.nr = nr,
+		.evsel = counter,
+	};
+	print_metric_t pm = print_metric_std;
+	void (*nl)(void *);
 
-	if (stat_config.aggr_mode == AGGR_GLOBAL)
-		cpu = 0;
+	if (metric_only) {
+		nl = new_line_metric;
+		if (csv_output)
+			pm = print_metric_only_csv;
+		else
+			pm = print_metric_only;
+	} else
+		nl = new_line_std;
+
+	if (csv_output && !metric_only) {
+		static int aggr_fields[] = {
+			[AGGR_GLOBAL] = 0,
+			[AGGR_THREAD] = 1,
+			[AGGR_NONE] = 1,
+			[AGGR_SOCKET] = 2,
+			[AGGR_CORE] = 2,
+		};
+
+		pm = print_metric_csv;
+		nl = new_line_csv;
+		os.nfields = 3;
+		os.nfields += aggr_fields[stat_config.aggr_mode];
+		if (counter->cgrp)
+			os.nfields++;
+	}
+	if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
+		if (metric_only) {
+			pm(&os, NULL, "", "", 0);
+			return;
+		}
+		aggr_printout(counter, id, nr);
+
+		fprintf(stat_config.output, "%*s%s",
+			csv_output ? 0 : 18,
+			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
+			csv_sep);
+
+		fprintf(stat_config.output, "%-*s%s",
+			csv_output ? 0 : unit_width,
+			counter->unit, csv_sep);
+
+		fprintf(stat_config.output, "%*s",
+			csv_output ? 0 : -25,
+			perf_evsel__name(counter));
+
+		if (counter->cgrp)
+			fprintf(stat_config.output, "%s%s",
+				csv_sep, counter->cgrp->name);
 
-	if (nsec_counter(counter))
+		if (!csv_output)
+			pm(&os, NULL, NULL, "", 0);
+		print_noise(counter, noise);
+		print_running(run, ena);
+		if (csv_output)
+			pm(&os, NULL, NULL, "", 0);
+		return;
+	}
+
+	if (metric_only)
+		/* nothing */;
+	else if (nsec_counter(counter))
 		nsec_printout(id, nr, counter, uval);
 	else
 		abs_printout(id, nr, counter, uval);
 
-	if (!csv_output && !stat_config.interval)
-		perf_stat__print_shadow_stats(stat_config.output, counter,
-					      uval, cpu,
-					      stat_config.aggr_mode);
+	out.print_metric = pm;
+	out.new_line = nl;
+	out.ctx = &os;
+
+	if (csv_output && !metric_only) {
+		print_noise(counter, noise);
+		print_running(run, ena);
+	}
+
+	perf_stat__print_shadow_stats(counter, uval,
+				first_shadow_cpu(counter, id),
+				&out);
+	if (!csv_output && !metric_only) {
+		print_noise(counter, noise);
+		print_running(run, ena);
+	}
+}
+
+static void aggr_update_shadow(void)
+{
+	int cpu, s2, id, s;
+	u64 val;
+	struct perf_evsel *counter;
+
+	for (s = 0; s < aggr_map->nr; s++) {
+		id = aggr_map->map[s];
+		evlist__for_each(evsel_list, counter) {
+			val = 0;
+			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+				s2 = aggr_get_id(evsel_list->cpus, cpu);
+				if (s2 != id)
+					continue;
+				val += perf_counts(counter->counts, cpu, 0)->val;
+			}
+			val = val * counter->scale;
+			perf_stat__update_shadow_stats(counter, &val,
+						       first_shadow_cpu(counter, id));
+		}
+	}
 }
 
 static void print_aggr(char *prefix)
@@ -818,12 +1133,23 @@ static void print_aggr(char *prefix)
 	int cpu, s, s2, id, nr;
 	double uval;
 	u64 ena, run, val;
+	bool first;
 
 	if (!(aggr_map || aggr_get_id))
 		return;
 
+	aggr_update_shadow();
+
+	/*
+	 * With metric_only everything is on a single line.
+	 * Without each counter has its own line.
+	 */
 	for (s = 0; s < aggr_map->nr; s++) {
+		if (prefix && metric_only)
+			fprintf(output, "%s", prefix);
+
 		id = aggr_map->map[s];
+		first = true;
 		evlist__for_each(evsel_list, counter) {
 			val = ena = run = 0;
 			nr = 0;
@@ -836,41 +1162,20 @@ static void print_aggr(char *prefix)
 				run += perf_counts(counter->counts, cpu, 0)->run;
 				nr++;
 			}
-			if (prefix)
-				fprintf(output, "%s", prefix);
-
-			if (run == 0 || ena == 0) {
+			if (first && metric_only) {
+				first = false;
 				aggr_printout(counter, id, nr);
-
-				fprintf(output, "%*s%s",
-					csv_output ? 0 : 18,
-					counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-					csv_sep);
-
-				fprintf(output, "%-*s%s",
-					csv_output ? 0 : unit_width,
-					counter->unit, csv_sep);
-
-				fprintf(output, "%*s",
-					csv_output ? 0 : -25,
-					perf_evsel__name(counter));
-
-				if (counter->cgrp)
-					fprintf(output, "%s%s",
-						csv_sep, counter->cgrp->name);
-
-				print_running(run, ena);
-				fputc('\n', output);
-				continue;
 			}
-			uval = val * counter->scale;
-			printout(id, nr, counter, uval);
-			if (!csv_output)
-				print_noise(counter, 1.0);
+			if (prefix && !metric_only)
+				fprintf(output, "%s", prefix);
 
-			print_running(run, ena);
-			fputc('\n', output);
+			uval = val * counter->scale;
+			printout(id, nr, counter, uval, prefix, run, ena, 1.0);
+			if (!metric_only)
+				fputc('\n', output);
 		}
+		if (metric_only)
+			fputc('\n', output);
 	}
 }
 
@@ -895,12 +1200,7 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
 			fprintf(output, "%s", prefix);
 
 		uval = val * counter->scale;
-		printout(thread, 0, counter, uval);
-
-		if (!csv_output)
-			print_noise(counter, 1.0);
-
-		print_running(run, ena);
+		printout(thread, 0, counter, uval, prefix, run, ena, 1.0);
 		fputc('\n', output);
 	}
 }
@@ -914,43 +1214,19 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 	FILE *output = stat_config.output;
 	struct perf_stat_evsel *ps = counter->priv;
 	double avg = avg_stats(&ps->res_stats[0]);
-	int scaled = counter->counts->scaled;
 	double uval;
 	double avg_enabled, avg_running;
 
 	avg_enabled = avg_stats(&ps->res_stats[1]);
 	avg_running = avg_stats(&ps->res_stats[2]);
 
-	if (prefix)
+	if (prefix && !metric_only)
 		fprintf(output, "%s", prefix);
 
-	if (scaled == -1 || !counter->supported) {
-		fprintf(output, "%*s%s",
-			csv_output ? 0 : 18,
-			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-			csv_sep);
-		fprintf(output, "%-*s%s",
-			csv_output ? 0 : unit_width,
-			counter->unit, csv_sep);
-		fprintf(output, "%*s",
-			csv_output ? 0 : -25,
-			perf_evsel__name(counter));
-
-		if (counter->cgrp)
-			fprintf(output, "%s%s", csv_sep, counter->cgrp->name);
-
-		print_running(avg_running, avg_enabled);
-		fputc('\n', output);
-		return;
-	}
-
 	uval = avg * counter->scale;
-	printout(-1, 0, counter, uval);
-
-	print_noise(counter, avg);
-
-	print_running(avg_running, avg_enabled);
-	fprintf(output, "\n");
+	printout(-1, 0, counter, uval, prefix, avg_running, avg_enabled, avg);
+	if (!metric_only)
+		fprintf(output, "\n");
 }
 
 /*
@@ -972,39 +1248,78 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 		if (prefix)
 			fprintf(output, "%s", prefix);
 
-		if (run == 0 || ena == 0) {
-			fprintf(output, "CPU%*d%s%*s%s",
-				csv_output ? 0 : -4,
-				perf_evsel__cpus(counter)->map[cpu], csv_sep,
-				csv_output ? 0 : 18,
-				counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-				csv_sep);
+		uval = val * counter->scale;
+		printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
 
-				fprintf(output, "%-*s%s",
-					csv_output ? 0 : unit_width,
-					counter->unit, csv_sep);
+		fputc('\n', output);
+	}
+}
 
-				fprintf(output, "%*s",
-					csv_output ? 0 : -25,
-					perf_evsel__name(counter));
+static void print_no_aggr_metric(char *prefix)
+{
+	int cpu;
+	int nrcpus = 0;
+	struct perf_evsel *counter;
+	u64 ena, run, val;
+	double uval;
 
-			if (counter->cgrp)
-				fprintf(output, "%s%s",
-					csv_sep, counter->cgrp->name);
+	nrcpus = evsel_list->cpus->nr;
+	for (cpu = 0; cpu < nrcpus; cpu++) {
+		bool first = true;
 
-			print_running(run, ena);
-			fputc('\n', output);
-			continue;
+		if (prefix)
+			fputs(prefix, stat_config.output);
+		evlist__for_each(evsel_list, counter) {
+			if (first) {
+				aggr_printout(counter, cpu, 0);
+				first = false;
+			}
+			val = perf_counts(counter->counts, cpu, 0)->val;
+			ena = perf_counts(counter->counts, cpu, 0)->ena;
+			run = perf_counts(counter->counts, cpu, 0)->run;
+
+			uval = val * counter->scale;
+			printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
 		}
+		fputc('\n', stat_config.output);
+	}
+}
 
-		uval = val * counter->scale;
-		printout(cpu, 0, counter, uval);
-		if (!csv_output)
-			print_noise(counter, 1.0);
-		print_running(run, ena);
+static int aggr_header_lens[] = {
+	[AGGR_CORE] = 18,
+	[AGGR_SOCKET] = 12,
+	[AGGR_NONE] = 6,
+	[AGGR_THREAD] = 24,
+	[AGGR_GLOBAL] = 0,
+};
 
-		fputc('\n', output);
+static void print_metric_headers(char *prefix)
+{
+	struct perf_stat_output_ctx out;
+	struct perf_evsel *counter;
+	struct outstate os = {
+		.fh = stat_config.output
+	};
+
+	if (prefix)
+		fprintf(stat_config.output, "%s", prefix);
+
+	if (!csv_output)
+		fprintf(stat_config.output, "%*s",
+			aggr_header_lens[stat_config.aggr_mode], "");
+
+	/* Print metrics headers only */
+	evlist__for_each(evsel_list, counter) {
+		os.evsel = counter;
+		out.ctx = &os;
+		out.print_metric = print_metric_header;
+		out.new_line = new_line_metric;
+		os.evsel = counter;
+		perf_stat__print_shadow_stats(counter, 0,
+					      0,
+					      &out);
 	}
+	fputc('\n', stat_config.output);
 }
 
 static void print_interval(char *prefix, struct timespec *ts)
@@ -1014,7 +1329,7 @@ static void print_interval(char *prefix, struct timespec *ts)
 
 	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
 
-	if (num_print_interval == 0 && !csv_output) {
+	if (num_print_interval == 0 && !csv_output && !metric_only) {
 		switch (stat_config.aggr_mode) {
 		case AGGR_SOCKET:
 			fprintf(output, "#           time socket cpus             counts %*s events\n", unit_width, "unit");
@@ -1101,6 +1416,17 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 	else
 		print_header(argc, argv);
 
+	if (metric_only) {
+		static int num_print_iv;
+
+		if (num_print_iv == 0)
+			print_metric_headers(prefix);
+		if (num_print_iv++ == 25)
+			num_print_iv = 0;
+		if (stat_config.aggr_mode == AGGR_GLOBAL && prefix)
+			fprintf(stat_config.output, "%s", prefix);
+	}
+
 	switch (stat_config.aggr_mode) {
 	case AGGR_CORE:
 	case AGGR_SOCKET:
@@ -1113,10 +1439,16 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 	case AGGR_GLOBAL:
 		evlist__for_each(evsel_list, counter)
 			print_counter_aggr(counter, prefix);
+		if (metric_only)
+			fputc('\n', stat_config.output);
 		break;
 	case AGGR_NONE:
-		evlist__for_each(evsel_list, counter)
-			print_counter(counter, prefix);
+		if (metric_only)
+			print_no_aggr_metric(prefix);
+		else {
+			evlist__for_each(evsel_list, counter)
+				print_counter(counter, prefix);
+		}
 		break;
 	case AGGR_UNSET:
 	default:
@@ -1237,6 +1569,8 @@ static const struct option stat_options[] = {
 		     "aggregate counts per thread", AGGR_THREAD),
 	OPT_UINTEGER('D', "delay", &initial_delay,
 		     "ms to wait before starting measurement after program start"),
+	OPT_BOOLEAN(0, "metric-only", &metric_only,
+			"Only print computed metrics. No raw values"),
 	OPT_END()
 };
 
@@ -1435,7 +1769,7 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
  */
 static int add_default_attributes(void)
 {
-	struct perf_event_attr default_attrs[] = {
+	struct perf_event_attr default_attrs0[] = {
 
   { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK		},
   { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES	},
@@ -1443,8 +1777,14 @@ static int add_default_attributes(void)
   { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS		},
 
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES		},
+};
+	struct perf_event_attr frontend_attrs[] = {
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND	},
+};
+	struct perf_event_attr backend_attrs[] = {
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_BACKEND	},
+};
+	struct perf_event_attr default_attrs1[] = {
   { .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		},
@@ -1561,7 +1901,19 @@ static int add_default_attributes(void)
 	}
 
 	if (!evsel_list->nr_entries) {
-		if (perf_evlist__add_default_attrs(evsel_list, default_attrs) < 0)
+		if (perf_evlist__add_default_attrs(evsel_list, default_attrs0) < 0)
+			return -1;
+		if (pmu_have_event("cpu", "stalled-cycles-frontend")) {
+			if (perf_evlist__add_default_attrs(evsel_list,
+						frontend_attrs) < 0)
+				return -1;
+		}
+		if (pmu_have_event("cpu", "stalled-cycles-backend")) {
+			if (perf_evlist__add_default_attrs(evsel_list,
+						backend_attrs) < 0)
+				return -1;
+		}
+		if (perf_evlist__add_default_attrs(evsel_list, default_attrs1) < 0)
 			return -1;
 	}
 
@@ -1825,9 +2177,11 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (evsel_list == NULL)
 		return -ENOMEM;
 
+	parse_events__shrink_config_terms();
 	argc = parse_options_subcommand(argc, argv, stat_options, stat_subcommands,
 					(const char **) stat_usage,
 					PARSE_OPT_STOP_AT_NON_OPTION);
+	perf_stat__init_shadow_stats();
 
 	if (csv_sep) {
 		csv_output = true;
@@ -1858,6 +2212,16 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out;
 	}
 
+	if (metric_only && stat_config.aggr_mode == AGGR_THREAD) {
+		fprintf(stderr, "--metric-only is not supported with --per-thread\n");
+		goto out;
+	}
+
+	if (metric_only && run_count > 1) {
+		fprintf(stderr, "--metric-only is not supported with -r\n");
+		goto out;
+	}
+
 	if (output_fd < 0) {
 		fprintf(stderr, "argument to --log-fd must be a > 0\n");
 		parse_options_usage(stat_usage, stat_options, "log-fd", 0);
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index bd7a77571..40cc9bb35 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -489,7 +489,7 @@ static const char *cat_backtrace(union perf_event *event,
 	if (!chain)
 		goto exit;
 
-	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
+	if (machine__resolve(machine, &al, sample) < 0) {
 		fprintf(stderr, "problem processing %d event, skipping it.\n",
 			event->header.type);
 		goto exit;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index bf01cbb0e..833214979 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -67,6 +67,7 @@
 #include <sys/utsname.h>
 #include <sys/mman.h>
 
+#include <linux/stringify.h>
 #include <linux/types.h>
 
 static volatile int done;
@@ -252,7 +253,8 @@ static void perf_top__print_sym_table(struct perf_top *top)
 	char bf[160];
 	int printed = 0;
 	const int win_width = top->winsize.ws_col - 1;
-	struct hists *hists = evsel__hists(top->sym_evsel);
+	struct perf_evsel *evsel = top->sym_evsel;
+	struct hists *hists = evsel__hists(evsel);
 
 	puts(CONSOLE_CLEAR);
 
@@ -288,7 +290,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
 	}
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists, NULL);
+	perf_evsel__output_resort(evsel, NULL);
 
 	hists__output_recalc_col_len(hists, top->print_entries - printed);
 	putchar('\n');
@@ -540,6 +542,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 static void perf_top__sort_new_samples(void *arg)
 {
 	struct perf_top *t = arg;
+	struct perf_evsel *evsel = t->sym_evsel;
 	struct hists *hists;
 
 	perf_top__reset_sample_counters(t);
@@ -547,7 +550,7 @@ static void perf_top__sort_new_samples(void *arg)
 	if (t->evlist->selected != NULL)
 		t->sym_evsel = t->evlist->selected;
 
-	hists = evsel__hists(t->sym_evsel);
+	hists = evsel__hists(evsel);
 
 	if (t->evlist->enabled) {
 		if (t->zero) {
@@ -559,7 +562,7 @@ static void perf_top__sort_new_samples(void *arg)
 	}
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists, NULL);
+	perf_evsel__output_resort(evsel, NULL);
 }
 
 static void *display_thread_tui(void *arg)
@@ -726,7 +729,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	if (event->header.misc & PERF_RECORD_MISC_EXACT_IP)
 		top->exact_samples++;
 
-	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0)
+	if (machine__resolve(machine, &al, sample) < 0)
 		return;
 
 	if (!top->kptr_restrict_warned &&
@@ -807,7 +810,6 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 	struct perf_session *session = top->session;
 	union perf_event *event;
 	struct machine *machine;
-	u8 origin;
 	int ret;
 
 	while ((event = perf_evlist__mmap_read(top->evlist, idx)) != NULL) {
@@ -820,12 +822,10 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 		evsel = perf_evlist__id2evsel(session->evlist, sample.id);
 		assert(evsel != NULL);
 
-		origin = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-
 		if (event->header.type == PERF_RECORD_SAMPLE)
 			++top->samples;
 
-		switch (origin) {
+		switch (sample.cpumode) {
 		case PERF_RECORD_MISC_USER:
 			++top->us_samples;
 			if (top->hide_user_symbols)
@@ -1063,7 +1063,7 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 	return parse_callchain_top_opt(arg);
 }
 
-static int perf_top_config(const char *var, const char *value, void *cb)
+static int perf_top_config(const char *var, const char *value, void *cb __maybe_unused)
 {
 	if (!strcmp(var, "top.call-graph"))
 		var = "call-graph.record-mode"; /* fall-through */
@@ -1072,7 +1072,7 @@ static int perf_top_config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 static int
@@ -1212,6 +1212,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		     parse_branch_stack),
 	OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace,
 		    "Show raw trace event output (do not use print fmt or plugins)"),
+	OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
+		    "Show entries in a hierarchy"),
 	OPT_END()
 	};
 	const char * const top_usage[] = {
@@ -1239,10 +1241,30 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out_delete_evlist;
 	}
 
+	if (symbol_conf.report_hierarchy) {
+		/* disable incompatible options */
+		symbol_conf.event_group = false;
+		symbol_conf.cumulate_callchain = false;
+
+		if (field_order) {
+			pr_err("Error: --hierarchy and --fields options cannot be used together\n");
+			parse_options_usage(top_usage, options, "fields", 0);
+			parse_options_usage(NULL, options, "hierarchy", 0);
+			goto out_delete_evlist;
+		}
+	}
+
 	sort__mode = SORT_MODE__TOP;
 	/* display thread wants entries to be collapsed in a different tree */
 	sort__need_collapse = 1;
 
+	if (top.use_stdio)
+		use_browser = 0;
+	else if (top.use_tui)
+		use_browser = 1;
+
+	setup_browser(false);
+
 	if (setup_sorting(top.evlist) < 0) {
 		if (sort_order)
 			parse_options_usage(top_usage, options, "s", 1);
@@ -1252,13 +1274,6 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out_delete_evlist;
 	}
 
-	if (top.use_stdio)
-		use_browser = 0;
-	else if (top.use_tui)
-		use_browser = 1;
-
-	setup_browser(false);
-
 	status = target__validate(target);
 	if (status) {
 		target__strerror(target, status, errbuf, BUFSIZ);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 20916dd77..93ac724fb 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -33,6 +33,7 @@
 #include "util/stat.h"
 #include "trace-event.h"
 #include "util/parse-events.h"
+#include "util/bpf-loader.h"
 
 #include <libaudit.h>
 #include <stdlib.h>
@@ -1724,8 +1725,12 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 
 	sc->args = sc->tp_format->format.fields;
 	sc->nr_args = sc->tp_format->format.nr_fields;
-	/* drop nr field - not relevant here; does not exist on older kernels */
-	if (sc->args && strcmp(sc->args->name, "nr") == 0) {
+	/*
+	 * We need to check and discard the first variable '__syscall_nr'
+	 * or 'nr' that mean the syscall number. It is needless here.
+	 * So drop '__syscall_nr' or 'nr' field but does not exist on older kernels.
+	 */
+	if (sc->args && (!strcmp(sc->args->name, "__syscall_nr") || !strcmp(sc->args->name, "nr"))) {
 		sc->args = sc->args->next;
 		--sc->nr_args;
 	}
@@ -2177,6 +2182,37 @@ out_dump:
 	return 0;
 }
 
+static void bpf_output__printer(enum binary_printer_ops op,
+				unsigned int val, void *extra)
+{
+	FILE *output = extra;
+	unsigned char ch = (unsigned char)val;
+
+	switch (op) {
+	case BINARY_PRINT_CHAR_DATA:
+		fprintf(output, "%c", isprint(ch) ? ch : '.');
+		break;
+	case BINARY_PRINT_DATA_BEGIN:
+	case BINARY_PRINT_LINE_BEGIN:
+	case BINARY_PRINT_ADDR:
+	case BINARY_PRINT_NUM_DATA:
+	case BINARY_PRINT_NUM_PAD:
+	case BINARY_PRINT_SEP:
+	case BINARY_PRINT_CHAR_PAD:
+	case BINARY_PRINT_LINE_END:
+	case BINARY_PRINT_DATA_END:
+	default:
+		break;
+	}
+}
+
+static void bpf_output__fprintf(struct trace *trace,
+				struct perf_sample *sample)
+{
+	print_binary(sample->raw_data, sample->raw_size, 8,
+		     bpf_output__printer, trace->output);
+}
+
 static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 				union perf_event *event __maybe_unused,
 				struct perf_sample *sample)
@@ -2189,7 +2225,9 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 
 	fprintf(trace->output, "%s:", evsel->name);
 
-	if (evsel->tp_format) {
+	if (perf_evsel__is_bpf_output(evsel)) {
+		bpf_output__fprintf(trace, sample);
+	} else if (evsel->tp_format) {
 		event_format__fprintf(evsel->tp_format, sample->cpu,
 				      sample->raw_data, sample->raw_size,
 				      trace->output);
@@ -2218,11 +2256,10 @@ static void print_location(FILE *f, struct perf_sample *sample,
 
 static int trace__pgfault(struct trace *trace,
 			  struct perf_evsel *evsel,
-			  union perf_event *event,
+			  union perf_event *event __maybe_unused,
 			  struct perf_sample *sample)
 {
 	struct thread *thread;
-	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	struct addr_location al;
 	char map_type = 'd';
 	struct thread_trace *ttrace;
@@ -2241,7 +2278,7 @@ static int trace__pgfault(struct trace *trace,
 	if (trace->summary_only)
 		goto out;
 
-	thread__find_addr_location(thread, cpumode, MAP__FUNCTION,
+	thread__find_addr_location(thread, sample->cpumode, MAP__FUNCTION,
 			      sample->ip, &al);
 
 	trace__fprintf_entry_head(trace, thread, 0, sample->time, trace->output);
@@ -2254,11 +2291,11 @@ static int trace__pgfault(struct trace *trace,
 
 	fprintf(trace->output, "] => ");
 
-	thread__find_addr_location(thread, cpumode, MAP__VARIABLE,
+	thread__find_addr_location(thread, sample->cpumode, MAP__VARIABLE,
 				   sample->addr, &al);
 
 	if (!al.map) {
-		thread__find_addr_location(thread, cpumode,
+		thread__find_addr_location(thread, sample->cpumode,
 					   MAP__FUNCTION, sample->addr, &al);
 
 		if (al.map)
@@ -2586,6 +2623,16 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (err < 0)
 		goto out_error_open;
 
+	err = bpf__apply_obj_config();
+	if (err) {
+		char errbuf[BUFSIZ];
+
+		bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf));
+		pr_err("ERROR: Apply config to BPF failed: %s\n",
+			 errbuf);
+		goto out_error_open;
+	}
+
 	/*
 	 * Better not use !target__has_task() here because we need to cover the
 	 * case where no threads were specified in the command line, but a
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 3f871b54e..41c24010a 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -7,38 +7,38 @@
 extern const char perf_usage_string[];
 extern const char perf_more_info_string[];
 
-extern void list_common_cmds_help(void);
-extern const char *help_unknown_cmd(const char *cmd);
-extern void prune_packed_objects(int);
-extern int read_line_with_nul(char *buf, int size, FILE *file);
-extern int check_pager_config(const char *cmd);
+void list_common_cmds_help(void);
+const char *help_unknown_cmd(const char *cmd);
+void prune_packed_objects(int);
+int read_line_with_nul(char *buf, int size, FILE *file);
+int check_pager_config(const char *cmd);
 
-extern int cmd_annotate(int argc, const char **argv, const char *prefix);
-extern int cmd_bench(int argc, const char **argv, const char *prefix);
-extern int cmd_buildid_cache(int argc, const char **argv, const char *prefix);
-extern int cmd_buildid_list(int argc, const char **argv, const char *prefix);
-extern int cmd_config(int argc, const char **argv, const char *prefix);
-extern int cmd_diff(int argc, const char **argv, const char *prefix);
-extern int cmd_evlist(int argc, const char **argv, const char *prefix);
-extern int cmd_help(int argc, const char **argv, const char *prefix);
-extern int cmd_sched(int argc, const char **argv, const char *prefix);
-extern int cmd_list(int argc, const char **argv, const char *prefix);
-extern int cmd_record(int argc, const char **argv, const char *prefix);
-extern int cmd_report(int argc, const char **argv, const char *prefix);
-extern int cmd_stat(int argc, const char **argv, const char *prefix);
-extern int cmd_timechart(int argc, const char **argv, const char *prefix);
-extern int cmd_top(int argc, const char **argv, const char *prefix);
-extern int cmd_script(int argc, const char **argv, const char *prefix);
-extern int cmd_version(int argc, const char **argv, const char *prefix);
-extern int cmd_probe(int argc, const char **argv, const char *prefix);
-extern int cmd_kmem(int argc, const char **argv, const char *prefix);
-extern int cmd_lock(int argc, const char **argv, const char *prefix);
-extern int cmd_kvm(int argc, const char **argv, const char *prefix);
-extern int cmd_test(int argc, const char **argv, const char *prefix);
-extern int cmd_trace(int argc, const char **argv, const char *prefix);
-extern int cmd_inject(int argc, const char **argv, const char *prefix);
-extern int cmd_mem(int argc, const char **argv, const char *prefix);
-extern int cmd_data(int argc, const char **argv, const char *prefix);
+int cmd_annotate(int argc, const char **argv, const char *prefix);
+int cmd_bench(int argc, const char **argv, const char *prefix);
+int cmd_buildid_cache(int argc, const char **argv, const char *prefix);
+int cmd_buildid_list(int argc, const char **argv, const char *prefix);
+int cmd_config(int argc, const char **argv, const char *prefix);
+int cmd_diff(int argc, const char **argv, const char *prefix);
+int cmd_evlist(int argc, const char **argv, const char *prefix);
+int cmd_help(int argc, const char **argv, const char *prefix);
+int cmd_sched(int argc, const char **argv, const char *prefix);
+int cmd_list(int argc, const char **argv, const char *prefix);
+int cmd_record(int argc, const char **argv, const char *prefix);
+int cmd_report(int argc, const char **argv, const char *prefix);
+int cmd_stat(int argc, const char **argv, const char *prefix);
+int cmd_timechart(int argc, const char **argv, const char *prefix);
+int cmd_top(int argc, const char **argv, const char *prefix);
+int cmd_script(int argc, const char **argv, const char *prefix);
+int cmd_version(int argc, const char **argv, const char *prefix);
+int cmd_probe(int argc, const char **argv, const char *prefix);
+int cmd_kmem(int argc, const char **argv, const char *prefix);
+int cmd_lock(int argc, const char **argv, const char *prefix);
+int cmd_kvm(int argc, const char **argv, const char *prefix);
+int cmd_test(int argc, const char **argv, const char *prefix);
+int cmd_trace(int argc, const char **argv, const char *prefix);
+int cmd_inject(int argc, const char **argv, const char *prefix);
+int cmd_mem(int argc, const char **argv, const char *prefix);
+int cmd_data(int argc, const char **argv, const char *prefix);
 
-extern int find_scripts(char **scripts_array, char **scripts_path_array);
+int find_scripts(char **scripts_array, char **scripts_path_array);
 #endif
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 511141b10..6f8f6430f 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -61,50 +61,45 @@ endif
 
 ifeq ($(LIBUNWIND_LIBS),)
   NO_LIBUNWIND := 1
-else
-  #
-  # For linking with debug library, run like:
-  #
-  #   make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
-  #
-  ifdef LIBUNWIND_DIR
-    LIBUNWIND_CFLAGS  = -I$(LIBUNWIND_DIR)/include
-    LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib
-  endif
-  LIBUNWIND_LDFLAGS += $(LIBUNWIND_LIBS)
-
-  # Set per-feature check compilation flags
-  FEATURE_CHECK_CFLAGS-libunwind = $(LIBUNWIND_CFLAGS)
-  FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS)
-  FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS)
-  FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS)
 endif
+#
+# For linking with debug library, run like:
+#
+#   make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
+#
+ifdef LIBUNWIND_DIR
+  LIBUNWIND_CFLAGS  = -I$(LIBUNWIND_DIR)/include
+  LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib
+endif
+LIBUNWIND_LDFLAGS += $(LIBUNWIND_LIBS)
+
+# Set per-feature check compilation flags
+FEATURE_CHECK_CFLAGS-libunwind = $(LIBUNWIND_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS)
+FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS)
 
 ifeq ($(NO_PERF_REGS),0)
   CFLAGS += -DHAVE_PERF_REGS_SUPPORT
 endif
 
-ifndef NO_LIBELF
-  # for linking with debug library, run like:
-  # make DEBUG=1 LIBDW_DIR=/opt/libdw/
-  ifdef LIBDW_DIR
-    LIBDW_CFLAGS  := -I$(LIBDW_DIR)/include
-    LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
-  endif
-  FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS)
-  FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw
+# for linking with debug library, run like:
+# make DEBUG=1 LIBDW_DIR=/opt/libdw/
+ifdef LIBDW_DIR
+  LIBDW_CFLAGS  := -I$(LIBDW_DIR)/include
+  LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
 endif
+FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw
 
-ifdef LIBBABELTRACE
-  # for linking with debug library, run like:
-  # make DEBUG=1 LIBBABELTRACE_DIR=/opt/libbabeltrace/
-  ifdef LIBBABELTRACE_DIR
-    LIBBABELTRACE_CFLAGS  := -I$(LIBBABELTRACE_DIR)/include
-    LIBBABELTRACE_LDFLAGS := -L$(LIBBABELTRACE_DIR)/lib
-  endif
-  FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS)
-  FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf
+# for linking with debug library, run like:
+# make DEBUG=1 LIBBABELTRACE_DIR=/opt/libbabeltrace/
+ifdef LIBBABELTRACE_DIR
+  LIBBABELTRACE_CFLAGS  := -I$(LIBBABELTRACE_DIR)/include
+  LIBBABELTRACE_LDFLAGS := -L$(LIBBABELTRACE_DIR)/lib
 endif
+FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf
 
 FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/arch/$(ARCH)/include/uapi -I$(srctree)/include/uapi
 # include ARCH specific config
@@ -114,7 +109,7 @@ ifdef PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
   CFLAGS += -DHAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
 endif
 
-include $(src-perf)/config/utilities.mak
+include $(srctree)/tools/scripts/utilities.mak
 
 ifeq ($(call get-executable,$(FLEX)),)
   dummy := $(error Error: $(FLEX) is missing on this system, please install it)
@@ -145,28 +140,26 @@ ifdef PARSER_DEBUG
   $(call detected_var,PARSER_DEBUG_FLEX)
 endif
 
-ifndef NO_LIBPYTHON
-  # Try different combinations to accommodate systems that only have
-  # python[2][-config] in weird combinations but always preferring
-  # python2 and python2-config as per pep-0394. If we catch a
-  # python[-config] in version 3, the version check will kill it.
-  PYTHON2 := $(if $(call get-executable,python2),python2,python)
-  override PYTHON := $(call get-executable-or-default,PYTHON,$(PYTHON2))
-  PYTHON2_CONFIG := \
-    $(if $(call get-executable,$(PYTHON)-config),$(PYTHON)-config,python-config)
-  override PYTHON_CONFIG := \
-    $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG))
+# Try different combinations to accommodate systems that only have
+# python[2][-config] in weird combinations but always preferring
+# python2 and python2-config as per pep-0394. If we catch a
+# python[-config] in version 3, the version check will kill it.
+PYTHON2 := $(if $(call get-executable,python2),python2,python)
+override PYTHON := $(call get-executable-or-default,PYTHON,$(PYTHON2))
+PYTHON2_CONFIG := \
+  $(if $(call get-executable,$(PYTHON)-config),$(PYTHON)-config,python-config)
+override PYTHON_CONFIG := \
+  $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG))
 
-  PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
+PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
 
-  PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
-  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
+PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
 
-  FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
-  FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
-  FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
-  FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
-endif
+FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
+FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
+FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
+FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
 
 CFLAGS += -fno-omit-frame-pointer
 CFLAGS += -ggdb3
@@ -275,6 +268,12 @@ else
     ifneq ($(feature-dwarf), 1)
       msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
       NO_DWARF := 1
+    else
+      ifneq ($(feature-dwarf_getlocations), 1)
+        msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157);
+      else
+        CFLAGS += -DHAVE_DWARF_GETLOCATIONS
+      endif # dwarf_getlocations
     endif # Dwarf support
   endif # libelf support
 endif # NO_LIBELF
@@ -335,6 +334,13 @@ ifndef NO_LIBELF
   endif # NO_LIBBPF
 endif # NO_LIBELF
 
+ifdef PERF_HAVE_JITDUMP
+  ifndef NO_DWARF
+    $(call detected,CONFIG_JITDUMP)
+    CFLAGS += -DHAVE_JITDUMP
+  endif
+endif
+
 ifeq ($(ARCH),powerpc)
   ifndef NO_DWARF
     CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX
@@ -411,6 +417,17 @@ ifndef NO_LIBAUDIT
   endif
 endif
 
+ifndef NO_LIBCRYPTO
+  ifneq ($(feature-libcrypto), 1)
+    msg := $(warning No libcrypto.h found, disables jitted code injection, please install libssl-devel or libssl-dev);
+    NO_LIBCRYPTO := 1
+  else
+    CFLAGS += -DHAVE_LIBCRYPTO_SUPPORT
+    EXTLIBS += -lcrypto
+    $(call detected,CONFIG_CRYPTO)
+  endif
+endif
+
 ifdef NO_NEWT
   NO_SLANG=1
 endif
diff --git a/tools/perf/jvmti/Makefile b/tools/perf/jvmti/Makefile
new file mode 100644
index 000000000..5ce61a1bd
--- /dev/null
+++ b/tools/perf/jvmti/Makefile
@@ -0,0 +1,89 @@
+ARCH=$(shell uname -m)
+
+ifeq ($(ARCH), x86_64)
+JARCH=amd64
+endif
+ifeq ($(ARCH), armv7l)
+JARCH=armhf
+endif
+ifeq ($(ARCH), armv6l)
+JARCH=armhf
+endif
+ifeq ($(ARCH), aarch64)
+JARCH=aarch64
+endif
+ifeq ($(ARCH), ppc64)
+JARCH=powerpc
+endif
+ifeq ($(ARCH), ppc64le)
+JARCH=powerpc
+endif
+
+DESTDIR=/usr/local
+
+VERSION=1
+REVISION=0
+AGE=0
+
+LN=ln -sf
+RM=rm
+
+SLIBJVMTI=libjvmti.so.$(VERSION).$(REVISION).$(AGE)
+VLIBJVMTI=libjvmti.so.$(VERSION)
+SLDFLAGS=-shared -Wl,-soname -Wl,$(VLIBJVMTI)
+SOLIBEXT=so
+
+# The following works at least on fedora 23, you may need the next
+# line for other distros.
+ifneq (,$(wildcard /usr/sbin/update-java-alternatives))
+JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | cut -d ' ' -f 3)
+else
+  ifneq (,$(wildcard /usr/sbin/alternatives))
+    JDIR=$(shell alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
+  endif
+endif
+ifndef JDIR
+$(error Could not find alternatives command, you need to set JDIR= to point to the root of your Java directory)
+else
+  ifeq (,$(wildcard $(JDIR)/include/jvmti.h))
+  $(error the openjdk development package appears to me missing, install and try again)
+  endif
+endif
+$(info Using Java from $(JDIR))
+# -lrt required in 32-bit mode for clock_gettime()
+LIBS=-lelf -lrt
+INCDIR=-I $(JDIR)/include -I $(JDIR)/include/linux
+
+TARGETS=$(SLIBJVMTI)
+
+SRCS=libjvmti.c jvmti_agent.c
+OBJS=$(SRCS:.c=.o)
+SOBJS=$(OBJS:.o=.lo)
+OPT=-O2 -g -Werror -Wall
+
+CFLAGS=$(INCDIR) $(OPT)
+
+all: $(TARGETS)
+
+.c.o:
+	$(CC) $(CFLAGS) -c $*.c
+.c.lo:
+	$(CC) -fPIC -DPIC $(CFLAGS) -c $*.c -o $*.lo
+
+$(OBJS) $(SOBJS): Makefile jvmti_agent.h ../util/jitdump.h
+
+$(SLIBJVMTI):  $(SOBJS)
+	$(CC) $(CFLAGS) $(SLDFLAGS)  -o $@ $(SOBJS) $(LIBS)
+	$(LN) $@ libjvmti.$(SOLIBEXT)
+
+clean:
+	$(RM) -f *.o *.so.* *.so *.lo
+
+install:
+	-mkdir -p $(DESTDIR)/lib
+	install -m 755 $(SLIBJVMTI) $(DESTDIR)/lib/
+	(cd $(DESTDIR)/lib; $(LN) $(SLIBJVMTI) $(VLIBJVMTI))
+	(cd $(DESTDIR)/lib; $(LN) $(SLIBJVMTI) libjvmti.$(SOLIBEXT))
+	ldconfig
+
+.SUFFIXES: .c .S .o .lo
diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c
new file mode 100644
index 000000000..6461e02ab
--- /dev/null
+++ b/tools/perf/jvmti/jvmti_agent.c
@@ -0,0 +1,465 @@
+/*
+ * jvmti_agent.c: JVMTI agent interface
+ *
+ * Adapted from the Oprofile code in opagent.c:
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ * Copyright 2007 OProfile authors
+ * Jens Wilke
+ * Daniel Hansel
+ * Copyright IBM Corporation 2007
+ */
+#include <sys/types.h>
+#include <sys/stat.h> /* for mkdir() */
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <limits.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <time.h>
+#include <sys/mman.h>
+#include <syscall.h> /* for gettid() */
+#include <err.h>
+
+#include "jvmti_agent.h"
+#include "../util/jitdump.h"
+
+#define JIT_LANG "java"
+
+static char jit_path[PATH_MAX];
+static void *marker_addr;
+
+/*
+ * padding buffer
+ */
+static const char pad_bytes[7];
+
+static inline pid_t gettid(void)
+{
+	return (pid_t)syscall(__NR_gettid);
+}
+
+static int get_e_machine(struct jitheader *hdr)
+{
+	ssize_t sret;
+	char id[16];
+	int fd, ret = -1;
+	int m = -1;
+	struct {
+		uint16_t e_type;
+		uint16_t e_machine;
+	} info;
+
+	fd = open("/proc/self/exe", O_RDONLY);
+	if (fd == -1)
+		return -1;
+
+	sret = read(fd, id, sizeof(id));
+	if (sret != sizeof(id))
+		goto error;
+
+	/* check ELF signature */
+	if (id[0] != 0x7f || id[1] != 'E' || id[2] != 'L' || id[3] != 'F')
+		goto error;
+
+	sret = read(fd, &info, sizeof(info));
+	if (sret != sizeof(info))
+		goto error;
+
+	m = info.e_machine;
+	if (m < 0)
+		m = 0; /* ELF EM_NONE */
+
+	hdr->elf_mach = m;
+	ret = 0;
+error:
+	close(fd);
+	return ret;
+}
+
+#define NSEC_PER_SEC	1000000000
+static int perf_clk_id = CLOCK_MONOTONIC;
+
+static inline uint64_t
+timespec_to_ns(const struct timespec *ts)
+{
+        return ((uint64_t) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec;
+}
+
+static inline uint64_t
+perf_get_timestamp(void)
+{
+	struct timespec ts;
+	int ret;
+
+	ret = clock_gettime(perf_clk_id, &ts);
+	if (ret)
+		return 0;
+
+	return timespec_to_ns(&ts);
+}
+
+static int
+debug_cache_init(void)
+{
+	char str[32];
+	char *base, *p;
+	struct tm tm;
+	time_t t;
+	int ret;
+
+	time(&t);
+	localtime_r(&t, &tm);
+
+	base = getenv("JITDUMPDIR");
+	if (!base)
+		base = getenv("HOME");
+	if (!base)
+		base = ".";
+
+	strftime(str, sizeof(str), JIT_LANG"-jit-%Y%m%d", &tm);
+
+	snprintf(jit_path, PATH_MAX - 1, "%s/.debug/", base);
+
+	ret = mkdir(jit_path, 0755);
+	if (ret == -1) {
+		if (errno != EEXIST) {
+			warn("jvmti: cannot create jit cache dir %s", jit_path);
+			return -1;
+		}
+	}
+
+	snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit", base);
+	ret = mkdir(jit_path, 0755);
+	if (ret == -1) {
+		if (errno != EEXIST) {
+			warn("cannot create jit cache dir %s", jit_path);
+			return -1;
+		}
+	}
+
+	snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit/%s.XXXXXXXX", base, str);
+
+	p = mkdtemp(jit_path);
+	if (p != jit_path) {
+		warn("cannot create jit cache dir %s", jit_path);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int
+perf_open_marker_file(int fd)
+{
+	long pgsz;
+
+	pgsz = sysconf(_SC_PAGESIZE);
+	if (pgsz == -1)
+		return -1;
+
+	/*
+	 * we mmap the jitdump to create an MMAP RECORD in perf.data file.
+	 * The mmap is captured either live (perf record running when we mmap)
+	 * or  in deferred mode, via /proc/PID/maps
+	 * the MMAP record is used as a marker of a jitdump file for more meta
+	 * data info about the jitted code. Perf report/annotate detect this
+	 * special filename and process the jitdump file.
+	 *
+	 * mapping must be PROT_EXEC to ensure it is captured by perf record
+	 * even when not using -d option
+	 */
+	marker_addr = mmap(NULL, pgsz, PROT_READ|PROT_EXEC, MAP_PRIVATE, fd, 0);
+	return (marker_addr == MAP_FAILED) ? -1 : 0;
+}
+
+static void
+perf_close_marker_file(void)
+{
+	long pgsz;
+
+	if (!marker_addr)
+		return;
+
+	pgsz = sysconf(_SC_PAGESIZE);
+	if (pgsz == -1)
+		return;
+
+	munmap(marker_addr, pgsz);
+}
+
+void *jvmti_open(void)
+{
+	int pad_cnt;
+	char dump_path[PATH_MAX];
+	struct jitheader header;
+	int fd;
+	FILE *fp;
+
+	/*
+	 * check if clockid is supported
+	 */
+	if (!perf_get_timestamp())
+		warnx("jvmti: kernel does not support %d clock id", perf_clk_id);
+
+	memset(&header, 0, sizeof(header));
+
+	debug_cache_init();
+
+	/*
+	 * jitdump file name
+	 */
+	snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
+
+	fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666);
+	if (fd == -1)
+		return NULL;
+
+	/*
+	 * create perf.data maker for the jitdump file
+	 */
+	if (perf_open_marker_file(fd)) {
+		warnx("jvmti: failed to create marker file");
+		return NULL;
+	}
+
+	fp = fdopen(fd, "w+");
+	if (!fp) {
+		warn("jvmti: cannot create %s", dump_path);
+		close(fd);
+		goto error;
+	}
+
+	warnx("jvmti: jitdump in %s", dump_path);
+
+	if (get_e_machine(&header)) {
+		warn("get_e_machine failed\n");
+		goto error;
+	}
+
+	header.magic      = JITHEADER_MAGIC;
+	header.version    = JITHEADER_VERSION;
+	header.total_size = sizeof(header);
+	header.pid        = getpid();
+
+	/* calculate amount of padding '\0' */
+	pad_cnt = PADDING_8ALIGNED(header.total_size);
+	header.total_size += pad_cnt;
+
+	header.timestamp = perf_get_timestamp();
+
+	if (!fwrite(&header, sizeof(header), 1, fp)) {
+		warn("jvmti: cannot write dumpfile header");
+		goto error;
+	}
+
+	/* write padding '\0' if necessary */
+	if (pad_cnt && !fwrite(pad_bytes, pad_cnt, 1, fp)) {
+		warn("jvmti: cannot write dumpfile header padding");
+		goto error;
+	}
+
+	return fp;
+error:
+	fclose(fp);
+	return NULL;
+}
+
+int
+jvmti_close(void *agent)
+{
+	struct jr_code_close rec;
+	FILE *fp = agent;
+
+	if (!fp) {
+		warnx("jvmti: incalid fd in close_agent");
+		return -1;
+	}
+
+	rec.p.id = JIT_CODE_CLOSE;
+	rec.p.total_size = sizeof(rec);
+
+	rec.p.timestamp = perf_get_timestamp();
+
+	if (!fwrite(&rec, sizeof(rec), 1, fp))
+		return -1;
+
+	fclose(fp);
+
+	fp = NULL;
+
+	perf_close_marker_file();
+
+	return 0;
+}
+
+int
+jvmti_write_code(void *agent, char const *sym,
+	uint64_t vma, void const *code, unsigned int const size)
+{
+	static int code_generation = 1;
+	struct jr_code_load rec;
+	size_t sym_len;
+	size_t padding_count;
+	FILE *fp = agent;
+	int ret = -1;
+
+	/* don't care about 0 length function, no samples */
+	if (size == 0)
+		return 0;
+
+	if (!fp) {
+		warnx("jvmti: invalid fd in write_native_code");
+		return -1;
+	}
+
+	sym_len = strlen(sym) + 1;
+
+	rec.p.id           = JIT_CODE_LOAD;
+	rec.p.total_size   = sizeof(rec) + sym_len;
+	padding_count      = PADDING_8ALIGNED(rec.p.total_size);
+	rec.p. total_size += padding_count;
+	rec.p.timestamp    = perf_get_timestamp();
+
+	rec.code_size  = size;
+	rec.vma        = vma;
+	rec.code_addr  = vma;
+	rec.pid	       = getpid();
+	rec.tid	       = gettid();
+
+	if (code)
+		rec.p.total_size += size;
+
+	/*
+	 * If JVM is multi-threaded, nultiple concurrent calls to agent
+	 * may be possible, so protect file writes
+	 */
+	flockfile(fp);
+
+	/*
+	 * get code index inside lock to avoid race condition
+	 */
+	rec.code_index = code_generation++;
+
+	ret = fwrite_unlocked(&rec, sizeof(rec), 1, fp);
+	fwrite_unlocked(sym, sym_len, 1, fp);
+
+	if (padding_count)
+		fwrite_unlocked(pad_bytes, padding_count, 1, fp);
+
+	if (code)
+		fwrite_unlocked(code, size, 1, fp);
+
+	funlockfile(fp);
+
+	ret = 0;
+
+	return ret;
+}
+
+int
+jvmti_write_debug_info(void *agent, uint64_t code, const char *file,
+		       jvmti_line_info_t *li, int nr_lines)
+{
+	struct jr_code_debug_info rec;
+	size_t sret, len, size, flen;
+	size_t padding_count;
+	uint64_t addr;
+	const char *fn = file;
+	FILE *fp = agent;
+	int i;
+
+	/*
+	 * no entry to write
+	 */
+	if (!nr_lines)
+		return 0;
+
+	if (!fp) {
+		warnx("jvmti: invalid fd in write_debug_info");
+		return -1;
+	}
+
+	flen = strlen(file) + 1;
+
+	rec.p.id        = JIT_CODE_DEBUG_INFO;
+	size            = sizeof(rec);
+	rec.p.timestamp = perf_get_timestamp();
+	rec.code_addr   = (uint64_t)(uintptr_t)code;
+	rec.nr_entry    = nr_lines;
+
+	/*
+	 * on disk source line info layout:
+	 * uint64_t : addr
+	 * int      : line number
+	 * int      : column discriminator
+	 * file[]   : source file name
+	 * padding  : pad to multiple of 8 bytes
+	 */
+	size += nr_lines * sizeof(struct debug_entry);
+	size += flen * nr_lines;
+	/*
+	 * pad to 8 bytes
+	 */
+	padding_count = PADDING_8ALIGNED(size);
+
+	rec.p.total_size = size + padding_count;
+
+	/*
+	 * If JVM is multi-threaded, nultiple concurrent calls to agent
+	 * may be possible, so protect file writes
+	 */
+	flockfile(fp);
+
+	sret = fwrite_unlocked(&rec, sizeof(rec), 1, fp);
+	if (sret != 1)
+		goto error;
+
+	for (i = 0; i < nr_lines; i++) {
+
+		addr = (uint64_t)li[i].pc;
+		len  = sizeof(addr);
+		sret = fwrite_unlocked(&addr, len, 1, fp);
+		if (sret != 1)
+			goto error;
+
+		len  = sizeof(li[0].line_number);
+		sret = fwrite_unlocked(&li[i].line_number, len, 1, fp);
+		if (sret != 1)
+			goto error;
+
+		len  = sizeof(li[0].discrim);
+		sret = fwrite_unlocked(&li[i].discrim, len, 1, fp);
+		if (sret != 1)
+			goto error;
+
+		sret = fwrite_unlocked(fn, flen, 1, fp);
+		if (sret != 1)
+			goto error;
+	}
+	if (padding_count)
+		sret = fwrite_unlocked(pad_bytes, padding_count, 1, fp);
+		if (sret != 1)
+			goto error;
+
+	funlockfile(fp);
+	return 0;
+error:
+	funlockfile(fp);
+	return -1;
+}
diff --git a/tools/perf/jvmti/jvmti_agent.h b/tools/perf/jvmti/jvmti_agent.h
new file mode 100644
index 000000000..bedf5d0ba
--- /dev/null
+++ b/tools/perf/jvmti/jvmti_agent.h
@@ -0,0 +1,36 @@
+#ifndef __JVMTI_AGENT_H__
+#define __JVMTI_AGENT_H__
+
+#include <sys/types.h>
+#include <stdint.h>
+#include <jvmti.h>
+
+#define __unused __attribute__((unused))
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+typedef struct {
+	unsigned long	pc;
+	int		line_number;
+	int		discrim; /* discriminator -- 0 for now */
+} jvmti_line_info_t;
+
+void *jvmti_open(void);
+int   jvmti_close(void *agent);
+int   jvmti_write_code(void *agent, char const *symbol_name,
+		       uint64_t vma, void const *code,
+		       const unsigned int code_size);
+
+int   jvmti_write_debug_info(void *agent,
+		             uint64_t code,
+			     const char *file,
+			     jvmti_line_info_t *li,
+			     int nr_lines);
+
+#if defined(__cplusplus)
+}
+
+#endif
+#endif /* __JVMTI_H__ */
diff --git a/tools/perf/jvmti/libjvmti.c b/tools/perf/jvmti/libjvmti.c
new file mode 100644
index 000000000..ac12e4b91
--- /dev/null
+++ b/tools/perf/jvmti/libjvmti.c
@@ -0,0 +1,304 @@
+#include <sys/types.h>
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+#include <err.h>
+#include <jvmti.h>
+#include <jvmticmlr.h>
+#include <limits.h>
+
+#include "jvmti_agent.h"
+
+static int has_line_numbers;
+void *jvmti_agent;
+
+static jvmtiError
+do_get_line_numbers(jvmtiEnv *jvmti, void *pc, jmethodID m, jint bci,
+		    jvmti_line_info_t *tab, jint *nr)
+{
+	jint i, lines = 0;
+	jint nr_lines = 0;
+	jvmtiLineNumberEntry *loc_tab = NULL;
+	jvmtiError ret;
+
+	ret = (*jvmti)->GetLineNumberTable(jvmti, m, &nr_lines, &loc_tab);
+	if (ret != JVMTI_ERROR_NONE)
+		return ret;
+
+	for (i = 0; i < nr_lines; i++) {
+		if (loc_tab[i].start_location < bci) {
+			tab[lines].pc = (unsigned long)pc;
+			tab[lines].line_number = loc_tab[i].line_number;
+			tab[lines].discrim = 0; /* not yet used */
+			lines++;
+		} else {
+			break;
+		}
+	}
+	(*jvmti)->Deallocate(jvmti, (unsigned char *)loc_tab);
+	*nr = lines;
+	return JVMTI_ERROR_NONE;
+}
+
+static jvmtiError
+get_line_numbers(jvmtiEnv *jvmti, const void *compile_info, jvmti_line_info_t **tab, int *nr_lines)
+{
+	const jvmtiCompiledMethodLoadRecordHeader *hdr;
+	jvmtiCompiledMethodLoadInlineRecord *rec;
+	jvmtiLineNumberEntry *lne = NULL;
+	PCStackInfo *c;
+	jint nr, ret;
+	int nr_total = 0;
+	int i, lines_total = 0;
+
+	if (!(tab && nr_lines))
+		return JVMTI_ERROR_NULL_POINTER;
+
+	/*
+	 * Phase 1 -- get the number of lines necessary
+	 */
+	for (hdr = compile_info; hdr != NULL; hdr = hdr->next) {
+		if (hdr->kind == JVMTI_CMLR_INLINE_INFO) {
+			rec = (jvmtiCompiledMethodLoadInlineRecord *)hdr;
+			for (i = 0; i < rec->numpcs; i++) {
+				c = rec->pcinfo + i;
+				nr = 0;
+				/*
+				 * unfortunately, need a tab to get the number of lines!
+				 */
+				ret = (*jvmti)->GetLineNumberTable(jvmti, c->methods[0], &nr, &lne);
+				if (ret == JVMTI_ERROR_NONE) {
+					/* free what was allocated for nothing */
+					(*jvmti)->Deallocate(jvmti, (unsigned char *)lne);
+					nr_total += (int)nr;
+				}
+			}
+		}
+	}
+
+	if (nr_total == 0)
+		return JVMTI_ERROR_NOT_FOUND;
+
+	/*
+	 * Phase 2 -- allocate big enough line table
+	 */
+	*tab = malloc(nr_total * sizeof(**tab));
+	if (!*tab)
+		return JVMTI_ERROR_OUT_OF_MEMORY;
+
+	for (hdr = compile_info; hdr != NULL; hdr = hdr->next) {
+		if (hdr->kind == JVMTI_CMLR_INLINE_INFO) {
+			rec = (jvmtiCompiledMethodLoadInlineRecord *)hdr;
+			for (i = 0; i < rec->numpcs; i++) {
+				c = rec->pcinfo + i;
+				nr = 0;
+				ret = do_get_line_numbers(jvmti, c->pc,
+							  c->methods[0],
+							  c->bcis[0],
+							  *tab + lines_total,
+							  &nr);
+				if (ret == JVMTI_ERROR_NONE)
+					lines_total += nr;
+			}
+		}
+	}
+	*nr_lines = lines_total;
+	return JVMTI_ERROR_NONE;
+}
+
+static void JNICALL
+compiled_method_load_cb(jvmtiEnv *jvmti,
+			jmethodID method,
+			jint code_size,
+			void const *code_addr,
+			jint map_length,
+			jvmtiAddrLocationMap const *map,
+			const void *compile_info)
+{
+	jvmti_line_info_t *line_tab = NULL;
+	jclass decl_class;
+	char *class_sign = NULL;
+	char *func_name = NULL;
+	char *func_sign = NULL;
+	char *file_name= NULL;
+	char fn[PATH_MAX];
+	uint64_t addr = (uint64_t)(uintptr_t)code_addr;
+	jvmtiError ret;
+	int nr_lines = 0; /* in line_tab[] */
+	size_t len;
+
+	ret = (*jvmti)->GetMethodDeclaringClass(jvmti, method,
+						&decl_class);
+	if (ret != JVMTI_ERROR_NONE) {
+		warnx("jvmti: cannot get declaring class");
+		return;
+	}
+
+	if (has_line_numbers && map && map_length) {
+		ret = get_line_numbers(jvmti, compile_info, &line_tab, &nr_lines);
+		if (ret != JVMTI_ERROR_NONE) {
+			warnx("jvmti: cannot get line table for method");
+			nr_lines = 0;
+		}
+	}
+
+	ret = (*jvmti)->GetSourceFileName(jvmti, decl_class, &file_name);
+	if (ret != JVMTI_ERROR_NONE) {
+		warnx("jvmti: cannot get source filename ret=%d", ret);
+		goto error;
+	}
+
+	ret = (*jvmti)->GetClassSignature(jvmti, decl_class,
+					  &class_sign, NULL);
+	if (ret != JVMTI_ERROR_NONE) {
+		warnx("jvmti: getclassignature failed");
+		goto error;
+	}
+
+	ret = (*jvmti)->GetMethodName(jvmti, method, &func_name,
+				      &func_sign, NULL);
+	if (ret != JVMTI_ERROR_NONE) {
+		warnx("jvmti: failed getmethodname");
+		goto error;
+	}
+
+	/*
+	 * Assume path name is class hierarchy, this is a common practice with Java programs
+	 */
+	if (*class_sign == 'L') {
+		int j, i = 0;
+		char *p = strrchr(class_sign, '/');
+		if (p) {
+			/* drop the 'L' prefix and copy up to the final '/' */
+			for (i = 0; i < (p - class_sign); i++)
+				fn[i] = class_sign[i+1];
+		}
+		/*
+		 * append file name, we use loops and not string ops to avoid modifying
+		 * class_sign which is used later for the symbol name
+		 */
+		for (j = 0; i < (PATH_MAX - 1) && file_name && j < strlen(file_name); j++, i++)
+			fn[i] = file_name[j];
+		fn[i] = '\0';
+	} else {
+		/* fallback case */
+		strcpy(fn, file_name);
+	}
+	/*
+	 * write source line info record if we have it
+	 */
+	if (jvmti_write_debug_info(jvmti_agent, addr, fn, line_tab, nr_lines))
+		warnx("jvmti: write_debug_info() failed");
+
+	len = strlen(func_name) + strlen(class_sign) + strlen(func_sign) + 2;
+	{
+		char str[len];
+		snprintf(str, len, "%s%s%s", class_sign, func_name, func_sign);
+
+		if (jvmti_write_code(jvmti_agent, str, addr, code_addr, code_size))
+			warnx("jvmti: write_code() failed");
+	}
+error:
+	(*jvmti)->Deallocate(jvmti, (unsigned char *)func_name);
+	(*jvmti)->Deallocate(jvmti, (unsigned char *)func_sign);
+	(*jvmti)->Deallocate(jvmti, (unsigned char *)class_sign);
+	(*jvmti)->Deallocate(jvmti, (unsigned char *)file_name);
+	free(line_tab);
+}
+
+static void JNICALL
+code_generated_cb(jvmtiEnv *jvmti,
+		  char const *name,
+		  void const *code_addr,
+		  jint code_size)
+{
+	uint64_t addr = (uint64_t)(unsigned long)code_addr;
+	int ret;
+
+	ret = jvmti_write_code(jvmti_agent, name, addr, code_addr, code_size);
+	if (ret)
+		warnx("jvmti: write_code() failed for code_generated");
+}
+
+JNIEXPORT jint JNICALL
+Agent_OnLoad(JavaVM *jvm, char *options, void *reserved __unused)
+{
+	jvmtiEventCallbacks cb;
+	jvmtiCapabilities caps1;
+	jvmtiJlocationFormat format;
+	jvmtiEnv *jvmti = NULL;
+	jint ret;
+
+	jvmti_agent = jvmti_open();
+	if (!jvmti_agent) {
+		warnx("jvmti: open_agent failed");
+		return -1;
+	}
+
+	/*
+	 * Request a JVMTI interface version 1 environment
+	 */
+	ret = (*jvm)->GetEnv(jvm, (void *)&jvmti, JVMTI_VERSION_1);
+	if (ret != JNI_OK) {
+		warnx("jvmti: jvmti version 1 not supported");
+		return -1;
+	}
+
+	/*
+	 * acquire method_load capability, we require it
+	 * request line numbers (optional)
+	 */
+	memset(&caps1, 0, sizeof(caps1));
+	caps1.can_generate_compiled_method_load_events = 1;
+
+	ret = (*jvmti)->AddCapabilities(jvmti, &caps1);
+	if (ret != JVMTI_ERROR_NONE) {
+		warnx("jvmti: acquire compiled_method capability failed");
+		return -1;
+	}
+	ret = (*jvmti)->GetJLocationFormat(jvmti, &format);
+        if (ret == JVMTI_ERROR_NONE && format == JVMTI_JLOCATION_JVMBCI) {
+                memset(&caps1, 0, sizeof(caps1));
+                caps1.can_get_line_numbers = 1;
+                caps1.can_get_source_file_name = 1;
+		ret = (*jvmti)->AddCapabilities(jvmti, &caps1);
+                if (ret == JVMTI_ERROR_NONE)
+                        has_line_numbers = 1;
+        }
+
+	memset(&cb, 0, sizeof(cb));
+
+	cb.CompiledMethodLoad   = compiled_method_load_cb;
+	cb.DynamicCodeGenerated = code_generated_cb;
+
+	ret = (*jvmti)->SetEventCallbacks(jvmti, &cb, sizeof(cb));
+	if (ret != JVMTI_ERROR_NONE) {
+		warnx("jvmti: cannot set event callbacks");
+		return -1;
+	}
+
+	ret = (*jvmti)->SetEventNotificationMode(jvmti, JVMTI_ENABLE,
+			JVMTI_EVENT_COMPILED_METHOD_LOAD, NULL);
+	if (ret != JVMTI_ERROR_NONE) {
+		warnx("jvmti: setnotification failed for method_load");
+		return -1;
+	}
+
+	ret = (*jvmti)->SetEventNotificationMode(jvmti, JVMTI_ENABLE,
+			JVMTI_EVENT_DYNAMIC_CODE_GENERATED, NULL);
+	if (ret != JVMTI_ERROR_NONE) {
+		warnx("jvmti: setnotification failed on code_generated");
+		return -1;
+	}
+	return 0;
+}
+
+JNIEXPORT void JNICALL
+Agent_OnUnload(JavaVM *jvm __unused)
+{
+	int ret;
+
+	ret = jvmti_close(jvmti_agent);
+	if (ret)
+		errx(1, "Error: op_close_agent()");
+}
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index a929618b8..aaee0a782 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -454,11 +454,12 @@ static void handle_internal_command(int argc, const char **argv)
 
 static void execv_dashed_external(const char **argv)
 {
-	struct strbuf cmd = STRBUF_INIT;
+	char *cmd;
 	const char *tmp;
 	int status;
 
-	strbuf_addf(&cmd, "perf-%s", argv[0]);
+	if (asprintf(&cmd, "perf-%s", argv[0]) < 0)
+		goto do_die;
 
 	/*
 	 * argv[0] must be the perf command, but the argv array
@@ -467,7 +468,7 @@ static void execv_dashed_external(const char **argv)
 	 * restore it on error.
 	 */
 	tmp = argv[0];
-	argv[0] = cmd.buf;
+	argv[0] = cmd;
 
 	/*
 	 * if we fail because the command is not found, it is
@@ -475,15 +476,16 @@ static void execv_dashed_external(const char **argv)
 	 */
 	status = run_command_v_opt(argv, 0);
 	if (status != -ERR_RUN_COMMAND_EXEC) {
-		if (IS_RUN_COMMAND_ERR(status))
+		if (IS_RUN_COMMAND_ERR(status)) {
+do_die:
 			die("unable to run '%s'", argv[0]);
+		}
 		exit(-status);
 	}
 	errno = ENOENT; /* as if we called execvp */
 
 	argv[0] = tmp;
-
-	strbuf_release(&cmd);
+	zfree(&cmd);
 }
 
 static int run_argv(int *argcp, const char ***argv)
@@ -546,6 +548,8 @@ int main(int argc, const char **argv)
 
 	srandom(time(NULL));
 
+	perf_config(perf_default_config, NULL);
+
 	/* get debugfs/tracefs mount point from /proc/mounts */
 	tracing_path_mount();
 
@@ -613,6 +617,8 @@ int main(int argc, const char **argv)
 	 */
 	pthread__block_sigwinch();
 
+	perf_debug_setup();
+
 	while (1) {
 		static int done_help;
 		int was_alias = run_argv(&argc, &argv);
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 90129accf..5381a01c0 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -58,6 +58,8 @@ struct record_opts {
 	bool	     full_auxtrace;
 	bool	     auxtrace_snapshot_mode;
 	bool	     record_switch_events;
+	bool	     all_kernel;
+	bool	     all_user;
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int auxtrace_mmap_pages;
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
index 15c840024..1d9500959 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
@@ -71,7 +71,10 @@ try:
 except:
 	if not audit_package_warned:
 		audit_package_warned = True
-		print "Install the audit-libs-python package to get syscall names"
+		print "Install the audit-libs-python package to get syscall names.\n" \
+                    "For example:\n  # apt-get install python-audit (Ubuntu)" \
+                    "\n  # yum install audit-libs-python (Fedora)" \
+                    "\n  etc.\n"
 
 def syscall_name(id):
 	try:
diff --git a/tools/perf/tests/.gitignore b/tools/perf/tests/.gitignore
index bf016c439..8cc30e731 100644
--- a/tools/perf/tests/.gitignore
+++ b/tools/perf/tests/.gitignore
@@ -1,3 +1,4 @@
 llvm-src-base.c
 llvm-src-kbuild.c
 llvm-src-prologue.c
+llvm-src-relocation.c
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 614899b88..1ba628ed0 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -31,7 +31,7 @@ perf-y += sample-parsing.o
 perf-y += parse-no-sample-id-all.o
 perf-y += kmod-path.o
 perf-y += thread-map.o
-perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o
+perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o llvm-src-relocation.o
 perf-y += bpf.o
 perf-y += topology.o
 perf-y += cpumap.o
@@ -59,6 +59,13 @@ $(OUTPUT)tests/llvm-src-prologue.c: tests/bpf-script-test-prologue.c tests/Build
 	$(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
 	$(Q)echo ';' >> $@
 
+$(OUTPUT)tests/llvm-src-relocation.c: tests/bpf-script-test-relocation.c tests/Build
+	$(call rule_mkdir)
+	$(Q)echo '#include <tests/llvm.h>' > $@
+	$(Q)echo 'const char test_llvm__bpf_test_relocation[] =' >> $@
+	$(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
+	$(Q)echo ';' >> $@
+
 ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64))
 perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 endif
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index fb80c9eb6..e7664fe3b 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -29,14 +29,59 @@
 
 static int fd1;
 static int fd2;
+static int fd3;
 static int overflows;
+static int overflows_2;
+
+volatile long the_var;
+
+
+/*
+ * Use ASM to ensure watchpoint and breakpoint can be triggered
+ * at one instruction.
+ */
+#if defined (__x86_64__)
+extern void __test_function(volatile long *ptr);
+asm (
+	".globl __test_function\n"
+	"__test_function:\n"
+	"incq (%rdi)\n"
+	"ret\n");
+#elif defined (__aarch64__)
+extern void __test_function(volatile long *ptr);
+asm (
+	".globl __test_function\n"
+	"__test_function:\n"
+	"str x30, [x0]\n"
+	"ret\n");
+
+#else
+static void __test_function(volatile long *ptr)
+{
+	*ptr = 0x1234;
+}
+#endif
 
 __attribute__ ((noinline))
 static int test_function(void)
 {
+	__test_function(&the_var);
+	the_var++;
 	return time(NULL);
 }
 
+static void sig_handler_2(int signum __maybe_unused,
+			  siginfo_t *oh __maybe_unused,
+			  void *uc __maybe_unused)
+{
+	overflows_2++;
+	if (overflows_2 > 10) {
+		ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0);
+		ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0);
+		ioctl(fd3, PERF_EVENT_IOC_DISABLE, 0);
+	}
+}
+
 static void sig_handler(int signum __maybe_unused,
 			siginfo_t *oh __maybe_unused,
 			void *uc __maybe_unused)
@@ -54,10 +99,11 @@ static void sig_handler(int signum __maybe_unused,
 		 */
 		ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0);
 		ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0);
+		ioctl(fd3, PERF_EVENT_IOC_DISABLE, 0);
 	}
 }
 
-static int bp_event(void *fn, int setup_signal)
+static int __event(bool is_x, void *addr, int sig)
 {
 	struct perf_event_attr pe;
 	int fd;
@@ -67,8 +113,8 @@ static int bp_event(void *fn, int setup_signal)
 	pe.size = sizeof(struct perf_event_attr);
 
 	pe.config = 0;
-	pe.bp_type = HW_BREAKPOINT_X;
-	pe.bp_addr = (unsigned long) fn;
+	pe.bp_type = is_x ? HW_BREAKPOINT_X : HW_BREAKPOINT_W;
+	pe.bp_addr = (unsigned long) addr;
 	pe.bp_len = sizeof(long);
 
 	pe.sample_period = 1;
@@ -86,17 +132,25 @@ static int bp_event(void *fn, int setup_signal)
 		return TEST_FAIL;
 	}
 
-	if (setup_signal) {
-		fcntl(fd, F_SETFL, O_RDWR|O_NONBLOCK|O_ASYNC);
-		fcntl(fd, F_SETSIG, SIGIO);
-		fcntl(fd, F_SETOWN, getpid());
-	}
+	fcntl(fd, F_SETFL, O_RDWR|O_NONBLOCK|O_ASYNC);
+	fcntl(fd, F_SETSIG, sig);
+	fcntl(fd, F_SETOWN, getpid());
 
 	ioctl(fd, PERF_EVENT_IOC_RESET, 0);
 
 	return fd;
 }
 
+static int bp_event(void *addr, int sig)
+{
+	return __event(true, addr, sig);
+}
+
+static int wp_event(void *addr, int sig)
+{
+	return __event(false, addr, sig);
+}
+
 static long long bp_count(int fd)
 {
 	long long count;
@@ -114,7 +168,7 @@ static long long bp_count(int fd)
 int test__bp_signal(int subtest __maybe_unused)
 {
 	struct sigaction sa;
-	long long count1, count2;
+	long long count1, count2, count3;
 
 	/* setup SIGIO signal handler */
 	memset(&sa, 0, sizeof(struct sigaction));
@@ -126,21 +180,52 @@ int test__bp_signal(int subtest __maybe_unused)
 		return TEST_FAIL;
 	}
 
+	sa.sa_sigaction = (void *) sig_handler_2;
+	if (sigaction(SIGUSR1, &sa, NULL) < 0) {
+		pr_debug("failed setting up signal handler 2\n");
+		return TEST_FAIL;
+	}
+
 	/*
 	 * We create following events:
 	 *
-	 * fd1 - breakpoint event on test_function with SIGIO
+	 * fd1 - breakpoint event on __test_function with SIGIO
 	 *       signal configured. We should get signal
 	 *       notification each time the breakpoint is hit
 	 *
-	 * fd2 - breakpoint event on sig_handler without SIGIO
+	 * fd2 - breakpoint event on sig_handler with SIGUSR1
+	 *       configured. We should get SIGUSR1 each time when
+	 *       breakpoint is hit
+	 *
+	 * fd3 - watchpoint event on __test_function with SIGIO
 	 *       configured.
 	 *
 	 * Following processing should happen:
-	 *   - execute test_function
-	 *   - fd1 event breakpoint hit -> count1 == 1
-	 *   - SIGIO is delivered       -> overflows == 1
-	 *   - fd2 event breakpoint hit -> count2 == 1
+	 *   Exec:               Action:                       Result:
+	 *   incq (%rdi)       - fd1 event breakpoint hit   -> count1 == 1
+	 *                     - SIGIO is delivered
+	 *   sig_handler       - fd2 event breakpoint hit   -> count2 == 1
+	 *                     - SIGUSR1 is delivered
+	 *   sig_handler_2                                  -> overflows_2 == 1  (nested signal)
+	 *   sys_rt_sigreturn  - return from sig_handler_2
+	 *   overflows++                                    -> overflows = 1
+	 *   sys_rt_sigreturn  - return from sig_handler
+	 *   incq (%rdi)       - fd3 event watchpoint hit   -> count3 == 1       (wp and bp in one insn)
+	 *                     - SIGIO is delivered
+	 *   sig_handler       - fd2 event breakpoint hit   -> count2 == 2
+	 *                     - SIGUSR1 is delivered
+	 *   sig_handler_2                                  -> overflows_2 == 2  (nested signal)
+	 *   sys_rt_sigreturn  - return from sig_handler_2
+	 *   overflows++                                    -> overflows = 2
+	 *   sys_rt_sigreturn  - return from sig_handler
+	 *   the_var++         - fd3 event watchpoint hit   -> count3 == 2       (standalone watchpoint)
+	 *                     - SIGIO is delivered
+	 *   sig_handler       - fd2 event breakpoint hit   -> count2 == 3
+	 *                     - SIGUSR1 is delivered
+	 *   sig_handler_2                                  -> overflows_2 == 3  (nested signal)
+	 *   sys_rt_sigreturn  - return from sig_handler_2
+	 *   overflows++                                    -> overflows == 3
+	 *   sys_rt_sigreturn  - return from sig_handler
 	 *
 	 * The test case check following error conditions:
 	 * - we get stuck in signal handler because of debug
@@ -152,11 +237,13 @@ int test__bp_signal(int subtest __maybe_unused)
 	 *
 	 */
 
-	fd1 = bp_event(test_function, 1);
-	fd2 = bp_event(sig_handler, 0);
+	fd1 = bp_event(__test_function, SIGIO);
+	fd2 = bp_event(sig_handler, SIGUSR1);
+	fd3 = wp_event((void *)&the_var, SIGIO);
 
 	ioctl(fd1, PERF_EVENT_IOC_ENABLE, 0);
 	ioctl(fd2, PERF_EVENT_IOC_ENABLE, 0);
+	ioctl(fd3, PERF_EVENT_IOC_ENABLE, 0);
 
 	/*
 	 * Kick off the test by trigering 'fd1'
@@ -166,15 +253,18 @@ int test__bp_signal(int subtest __maybe_unused)
 
 	ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0);
 	ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0);
+	ioctl(fd3, PERF_EVENT_IOC_DISABLE, 0);
 
 	count1 = bp_count(fd1);
 	count2 = bp_count(fd2);
+	count3 = bp_count(fd3);
 
 	close(fd1);
 	close(fd2);
+	close(fd3);
 
-	pr_debug("count1 %lld, count2 %lld, overflow %d\n",
-		 count1, count2, overflows);
+	pr_debug("count1 %lld, count2 %lld, count3 %lld, overflow %d, overflows_2 %d\n",
+		 count1, count2, count3, overflows, overflows_2);
 
 	if (count1 != 1) {
 		if (count1 == 11)
@@ -183,12 +273,18 @@ int test__bp_signal(int subtest __maybe_unused)
 			pr_debug("failed: wrong count for bp1%lld\n", count1);
 	}
 
-	if (overflows != 1)
+	if (overflows != 3)
 		pr_debug("failed: wrong overflow hit\n");
 
-	if (count2 != 1)
+	if (overflows_2 != 3)
+		pr_debug("failed: wrong overflow_2 hit\n");
+
+	if (count2 != 3)
 		pr_debug("failed: wrong count for bp2\n");
 
-	return count1 == 1 && overflows == 1 && count2 == 1 ?
+	if (count3 != 2)
+		pr_debug("failed: wrong count for bp3\n");
+
+	return count1 == 1 && overflows == 3 && count2 == 3 && overflows_2 == 3 && count3 == 2 ?
 		TEST_OK : TEST_FAIL;
 }
diff --git a/tools/perf/tests/bpf-script-test-relocation.c b/tools/perf/tests/bpf-script-test-relocation.c
new file mode 100644
index 000000000..93af77421
--- /dev/null
+++ b/tools/perf/tests/bpf-script-test-relocation.c
@@ -0,0 +1,50 @@
+/*
+ * bpf-script-test-relocation.c
+ * Test BPF loader checking relocation
+ */
+#ifndef LINUX_VERSION_CODE
+# error Need LINUX_VERSION_CODE
+# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig'
+#endif
+#define BPF_ANY 0
+#define BPF_MAP_TYPE_ARRAY 2
+#define BPF_FUNC_map_lookup_elem 1
+#define BPF_FUNC_map_update_elem 2
+
+static void *(*bpf_map_lookup_elem)(void *map, void *key) =
+	(void *) BPF_FUNC_map_lookup_elem;
+static void *(*bpf_map_update_elem)(void *map, void *key, void *value, int flags) =
+	(void *) BPF_FUNC_map_update_elem;
+
+struct bpf_map_def {
+	unsigned int type;
+	unsigned int key_size;
+	unsigned int value_size;
+	unsigned int max_entries;
+};
+
+#define SEC(NAME) __attribute__((section(NAME), used))
+struct bpf_map_def SEC("maps") my_table = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.max_entries = 1,
+};
+
+int this_is_a_global_val;
+
+SEC("func=sys_write")
+int bpf_func__sys_write(void *ctx)
+{
+	int key = 0;
+	int value = 0;
+
+	/*
+	 * Incorrect relocation. Should not allow this program be
+	 * loaded into kernel.
+	 */
+	bpf_map_update_elem(&this_is_a_global_val, &key, &value, 0);
+	return 0;
+}
+char _license[] SEC("license") = "GPL";
+int _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 33689a0cf..199501c71 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -1,7 +1,11 @@
 #include <stdio.h>
 #include <sys/epoll.h>
+#include <util/util.h>
 #include <util/bpf-loader.h>
 #include <util/evlist.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <bpf/bpf.h>
 #include "tests.h"
 #include "llvm.h"
 #include "debug.h"
@@ -71,6 +75,15 @@ static struct {
 		(NR_ITERS + 1) / 4,
 	},
 #endif
+	{
+		LLVM_TESTCASE_BPF_RELOCATION,
+		"Test BPF relocation checker",
+		"[bpf_relocation_test]",
+		"fix 'perf test LLVM' first",
+		"libbpf error when dealing with relocation",
+		NULL,
+		0,
+	},
 };
 
 static int do_test(struct bpf_object *obj, int (*func)(void),
@@ -99,7 +112,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
 	parse_evlist.error = &parse_error;
 	INIT_LIST_HEAD(&parse_evlist.list);
 
-	err = parse_events_load_bpf_obj(&parse_evlist, &parse_evlist.list, obj);
+	err = parse_events_load_bpf_obj(&parse_evlist, &parse_evlist.list, obj, NULL);
 	if (err || list_empty(&parse_evlist.list)) {
 		pr_debug("Failed to add events selected by BPF\n");
 		return TEST_FAIL;
@@ -190,7 +203,7 @@ static int __test__bpf(int idx)
 
 	ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
 				       bpf_testcase_table[idx].prog_id,
-				       true);
+				       true, NULL);
 	if (ret != TEST_OK || !obj_buf || !obj_buf_sz) {
 		pr_debug("Unable to get BPF object, %s\n",
 			 bpf_testcase_table[idx].msg_compile_fail);
@@ -202,14 +215,21 @@ static int __test__bpf(int idx)
 
 	obj = prepare_bpf(obj_buf, obj_buf_sz,
 			  bpf_testcase_table[idx].name);
-	if (!obj) {
+	if ((!!bpf_testcase_table[idx].target_func) != (!!obj)) {
+		if (!obj)
+			pr_debug("Fail to load BPF object: %s\n",
+				 bpf_testcase_table[idx].msg_load_fail);
+		else
+			pr_debug("Success unexpectedly: %s\n",
+				 bpf_testcase_table[idx].msg_load_fail);
 		ret = TEST_FAIL;
 		goto out;
 	}
 
-	ret = do_test(obj,
-		      bpf_testcase_table[idx].target_func,
-		      bpf_testcase_table[idx].expect_result);
+	if (obj)
+		ret = do_test(obj,
+			      bpf_testcase_table[idx].target_func,
+			      bpf_testcase_table[idx].expect_result);
 out:
 	bpf__clear();
 	return ret;
@@ -227,6 +247,36 @@ const char *test__bpf_subtest_get_desc(int i)
 	return bpf_testcase_table[i].desc;
 }
 
+static int check_env(void)
+{
+	int err;
+	unsigned int kver_int;
+	char license[] = "GPL";
+
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+	};
+
+	err = fetch_kernel_version(&kver_int, NULL, 0);
+	if (err) {
+		pr_debug("Unable to get kernel version\n");
+		return err;
+	}
+
+	err = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns,
+			       sizeof(insns) / sizeof(insns[0]),
+			       license, kver_int, NULL, 0);
+	if (err < 0) {
+		pr_err("Missing basic BPF support, skip this test: %s\n",
+		       strerror(errno));
+		return err;
+	}
+	close(err);
+
+	return 0;
+}
+
 int test__bpf(int i)
 {
 	int err;
@@ -239,6 +289,9 @@ int test__bpf(int i)
 		return TEST_SKIP;
 	}
 
+	if (check_env())
+		return TEST_SKIP;
+
 	err = __test__bpf(i);
 	return err;
 }
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 313a48c6b..abd3f0ec0 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -293,7 +293,6 @@ static int process_sample_event(struct machine *machine,
 {
 	struct perf_sample sample;
 	struct thread *thread;
-	u8 cpumode;
 	int ret;
 
 	if (perf_evlist__parse_sample(evlist, event, &sample)) {
@@ -307,9 +306,7 @@ static int process_sample_event(struct machine *machine,
 		return -1;
 	}
 
-	cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-
-	ret = read_object_code(sample.ip, READLEN, cpumode, thread, state);
+	ret = read_object_code(sample.ip, READLEN, sample.cpumode, thread, state);
 	thread__put(thread);
 	return ret;
 }
@@ -439,7 +436,7 @@ static int do_test_code_reading(bool try_kcore)
 		.mmap_pages	     = UINT_MAX,
 		.user_freq	     = UINT_MAX,
 		.user_interval	     = ULLONG_MAX,
-		.freq		     = 4000,
+		.freq		     = 500,
 		.target		     = {
 			.uses_mmap   = true,
 		},
@@ -559,7 +556,13 @@ static int do_test_code_reading(bool try_kcore)
 				evlist = NULL;
 				continue;
 			}
-			pr_debug("perf_evlist__open failed\n");
+
+			if (verbose) {
+				char errbuf[512];
+				perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));
+				pr_debug("perf_evlist__open() failed!\n%s\n", errbuf);
+			}
+
 			goto out_put;
 		}
 		break;
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 1c5c0221c..8f6eb853a 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -20,10 +20,10 @@
 
 static int mmap_handler(struct perf_tool *tool __maybe_unused,
 			union perf_event *event,
-			struct perf_sample *sample __maybe_unused,
+			struct perf_sample *sample,
 			struct machine *machine)
 {
-	return machine__process_mmap2_event(machine, event, NULL);
+	return machine__process_mmap2_event(machine, event, sample);
 }
 
 static int init_live_machine(struct machine *machine)
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index 071a8b5f5..f55f4bd47 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -100,9 +100,11 @@ struct machine *setup_fake_machine(struct machines *machines)
 	}
 
 	for (i = 0; i < ARRAY_SIZE(fake_mmap_info); i++) {
+		struct perf_sample sample = {
+			.cpumode = PERF_RECORD_MISC_USER,
+		};
 		union perf_event fake_mmap_event = {
 			.mmap = {
-				.header = { .misc = PERF_RECORD_MISC_USER, },
 				.pid = fake_mmap_info[i].pid,
 				.tid = fake_mmap_info[i].pid,
 				.start = fake_mmap_info[i].start,
@@ -114,7 +116,7 @@ struct machine *setup_fake_machine(struct machines *machines)
 		strcpy(fake_mmap_event.mmap.filename,
 		       fake_mmap_info[i].filename);
 
-		machine__process_mmap_event(machine, &fake_mmap_event, NULL);
+		machine__process_mmap_event(machine, &fake_mmap_event, &sample);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(fake_symbols); i++) {
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 5e6a86e50..ed5aa9eae 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -81,11 +81,6 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 	size_t i;
 
 	for (i = 0; i < ARRAY_SIZE(fake_samples); i++) {
-		const union perf_event event = {
-			.header = {
-				.misc = PERF_RECORD_MISC_USER,
-			},
-		};
 		struct hist_entry_iter iter = {
 			.evsel = evsel,
 			.sample	= &sample,
@@ -97,13 +92,13 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 		else
 			iter.ops = &hist_iter_normal;
 
+		sample.cpumode = PERF_RECORD_MISC_USER;
 		sample.pid = fake_samples[i].pid;
 		sample.tid = fake_samples[i].pid;
 		sample.ip = fake_samples[i].ip;
 		sample.callchain = (struct ip_callchain *)fake_callchains[i];
 
-		if (perf_event__preprocess_sample(&event, machine, &al,
-						  &sample) < 0)
+		if (machine__resolve(machine, &al, &sample) < 0)
 			goto out;
 
 		if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH,
@@ -191,7 +186,7 @@ static int do_test(struct hists *hists, struct result *expected, size_t nr_expec
 	 * function since TEST_ASSERT_VAL() returns in case of failure.
 	 */
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists, NULL);
+	perf_evsel__output_resort(hists_to_evsel(hists), NULL);
 
 	if (verbose > 2) {
 		pr_info("use callchain: %d, cumulate callchain: %d\n",
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 351a42463..b825d24f8 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -58,11 +58,6 @@ static int add_hist_entries(struct perf_evlist *evlist,
 	 */
 	evlist__for_each(evlist, evsel) {
 		for (i = 0; i < ARRAY_SIZE(fake_samples); i++) {
-			const union perf_event event = {
-				.header = {
-					.misc = PERF_RECORD_MISC_USER,
-				},
-			};
 			struct hist_entry_iter iter = {
 				.evsel = evsel,
 				.sample = &sample,
@@ -76,12 +71,12 @@ static int add_hist_entries(struct perf_evlist *evlist,
 			hists->dso_filter = NULL;
 			hists->symbol_filter_str = NULL;
 
+			sample.cpumode = PERF_RECORD_MISC_USER;
 			sample.pid = fake_samples[i].pid;
 			sample.tid = fake_samples[i].pid;
 			sample.ip = fake_samples[i].ip;
 
-			if (perf_event__preprocess_sample(&event, machine, &al,
-							  &sample) < 0)
+			if (machine__resolve(machine, &al, &sample) < 0)
 				goto out;
 
 			al.socket = fake_samples[i].socket;
@@ -145,7 +140,7 @@ int test__hists_filter(int subtest __maybe_unused)
 		struct hists *hists = evsel__hists(evsel);
 
 		hists__collapse_resort(hists, NULL);
-		hists__output_resort(hists, NULL);
+		perf_evsel__output_resort(evsel, NULL);
 
 		if (verbose > 2) {
 			pr_info("Normal histogram\n");
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 64b257d8d..358324e47 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -76,17 +76,12 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 		struct hists *hists = evsel__hists(evsel);
 
 		for (k = 0; k < ARRAY_SIZE(fake_common_samples); k++) {
-			const union perf_event event = {
-				.header = {
-					.misc = PERF_RECORD_MISC_USER,
-				},
-			};
-
+			sample.cpumode = PERF_RECORD_MISC_USER;
 			sample.pid = fake_common_samples[k].pid;
 			sample.tid = fake_common_samples[k].pid;
 			sample.ip = fake_common_samples[k].ip;
-			if (perf_event__preprocess_sample(&event, machine, &al,
-							  &sample) < 0)
+
+			if (machine__resolve(machine, &al, &sample) < 0)
 				goto out;
 
 			he = __hists__add_entry(hists, &al, NULL,
@@ -102,17 +97,10 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 		}
 
 		for (k = 0; k < ARRAY_SIZE(fake_samples[i]); k++) {
-			const union perf_event event = {
-				.header = {
-					.misc = PERF_RECORD_MISC_USER,
-				},
-			};
-
 			sample.pid = fake_samples[i][k].pid;
 			sample.tid = fake_samples[i][k].pid;
 			sample.ip = fake_samples[i][k].ip;
-			if (perf_event__preprocess_sample(&event, machine, &al,
-							  &sample) < 0)
+			if (machine__resolve(machine, &al, &sample) < 0)
 				goto out;
 
 			he = __hists__add_entry(hists, &al, NULL,
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index b23126514..d3556fbe8 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -51,11 +51,6 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 	size_t i;
 
 	for (i = 0; i < ARRAY_SIZE(fake_samples); i++) {
-		const union perf_event event = {
-			.header = {
-				.misc = PERF_RECORD_MISC_USER,
-			},
-		};
 		struct hist_entry_iter iter = {
 			.evsel = evsel,
 			.sample = &sample,
@@ -63,13 +58,13 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 			.hide_unresolved = false,
 		};
 
+		sample.cpumode = PERF_RECORD_MISC_USER;
 		sample.cpu = fake_samples[i].cpu;
 		sample.pid = fake_samples[i].pid;
 		sample.tid = fake_samples[i].pid;
 		sample.ip = fake_samples[i].ip;
 
-		if (perf_event__preprocess_sample(&event, machine, &al,
-						  &sample) < 0)
+		if (machine__resolve(machine, &al, &sample) < 0)
 			goto out;
 
 		if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH,
@@ -156,7 +151,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine)
 		goto out;
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists, NULL);
+	perf_evsel__output_resort(evsel, NULL);
 
 	if (verbose > 2) {
 		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -256,7 +251,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine)
 		goto out;
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists, NULL);
+	perf_evsel__output_resort(evsel, NULL);
 
 	if (verbose > 2) {
 		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -310,7 +305,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
 		goto out;
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists, NULL);
+	perf_evsel__output_resort(evsel, NULL);
 
 	if (verbose > 2) {
 		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -388,7 +383,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 		goto out;
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists, NULL);
+	perf_evsel__output_resort(evsel, NULL);
 
 	if (verbose > 2) {
 		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -491,7 +486,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine)
 		goto out;
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists, NULL);
+	perf_evsel__output_resort(evsel, NULL);
 
 	if (verbose > 2) {
 		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index 06f45c1d4..cff564fb4 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -6,12 +6,6 @@
 #include "tests.h"
 #include "debug.h"
 
-static int perf_config_cb(const char *var, const char *val,
-			  void *arg __maybe_unused)
-{
-	return perf_default_config(var, val, arg);
-}
-
 #ifdef HAVE_LIBBPF_SUPPORT
 static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz)
 {
@@ -35,6 +29,7 @@ static int test__bpf_parsing(void *obj_buf __maybe_unused,
 static struct {
 	const char *source;
 	const char *desc;
+	bool should_load_fail;
 } bpf_source_table[__LLVM_TESTCASE_MAX] = {
 	[LLVM_TESTCASE_BASE] = {
 		.source = test_llvm__bpf_base_prog,
@@ -48,14 +43,19 @@ static struct {
 		.source = test_llvm__bpf_test_prologue_prog,
 		.desc = "Compile source for BPF prologue generation test",
 	},
+	[LLVM_TESTCASE_BPF_RELOCATION] = {
+		.source = test_llvm__bpf_test_relocation,
+		.desc = "Compile source for BPF relocation test",
+		.should_load_fail = true,
+	},
 };
 
-
 int
 test_llvm__fetch_bpf_obj(void **p_obj_buf,
 			 size_t *p_obj_buf_sz,
 			 enum test_llvm__testcase idx,
-			 bool force)
+			 bool force,
+			 bool *should_load_fail)
 {
 	const char *source;
 	const char *desc;
@@ -68,8 +68,8 @@ test_llvm__fetch_bpf_obj(void **p_obj_buf,
 
 	source = bpf_source_table[idx].source;
 	desc = bpf_source_table[idx].desc;
-
-	perf_config(perf_config_cb, NULL);
+	if (should_load_fail)
+		*should_load_fail = bpf_source_table[idx].should_load_fail;
 
 	/*
 	 * Skip this test if user's .perfconfig doesn't set [llvm] section
@@ -136,14 +136,15 @@ int test__llvm(int subtest)
 	int ret;
 	void *obj_buf = NULL;
 	size_t obj_buf_sz = 0;
+	bool should_load_fail = false;
 
 	if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX))
 		return TEST_FAIL;
 
 	ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
-				       subtest, false);
+				       subtest, false, &should_load_fail);
 
-	if (ret == TEST_OK) {
+	if (ret == TEST_OK && !should_load_fail) {
 		ret = test__bpf_parsing(obj_buf, obj_buf_sz);
 		if (ret != TEST_OK) {
 			pr_debug("Failed to parse test case '%s'\n",
diff --git a/tools/perf/tests/llvm.h b/tools/perf/tests/llvm.h
index 5150b4d6e..0eaa604be 100644
--- a/tools/perf/tests/llvm.h
+++ b/tools/perf/tests/llvm.h
@@ -7,14 +7,17 @@
 extern const char test_llvm__bpf_base_prog[];
 extern const char test_llvm__bpf_test_kbuild_prog[];
 extern const char test_llvm__bpf_test_prologue_prog[];
+extern const char test_llvm__bpf_test_relocation[];
 
 enum test_llvm__testcase {
 	LLVM_TESTCASE_BASE,
 	LLVM_TESTCASE_KBUILD,
 	LLVM_TESTCASE_BPF_PROLOGUE,
+	LLVM_TESTCASE_BPF_RELOCATION,
 	__LLVM_TESTCASE_MAX,
 };
 
 int test_llvm__fetch_bpf_obj(void **p_obj_buf, size_t *p_obj_buf_sz,
-			     enum test_llvm__testcase index, bool force);
+			     enum test_llvm__testcase index, bool force,
+			     bool *should_load_fail);
 #endif
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index f91801551..cac15d93a 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -15,6 +15,7 @@ else
 PERF := .
 PERF_O := $(PERF)
 O_OPT :=
+FULL_O := $(shell readlink -f $(PERF_O) || echo $(PERF_O))
 
 ifneq ($(O),)
   FULL_O := $(shell readlink -f $(O) || echo $(O))
@@ -79,6 +80,7 @@ make_no_libaudit    := NO_LIBAUDIT=1
 make_no_libbionic   := NO_LIBBIONIC=1
 make_no_auxtrace    := NO_AUXTRACE=1
 make_no_libbpf	    := NO_LIBBPF=1
+make_no_libcrypto   := NO_LIBCRYPTO=1
 make_tags           := tags
 make_cscope         := cscope
 make_help           := help
@@ -102,6 +104,7 @@ make_minimal        := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1
 make_minimal        += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1
 make_minimal        += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1
 make_minimal        += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1
+make_minimal        += NO_LIBCRYPTO=1
 
 # $(run) contains all available tests
 run := make_pure
@@ -110,6 +113,9 @@ run := make_pure
 # disable features detection
 ifeq ($(MK),Makefile)
 run += make_clean_all
+MAKE_F := $(MAKE)
+else
+MAKE_F := $(MAKE) -f $(MK)
 endif
 run += make_python_perf_so
 run += make_debug
@@ -260,6 +266,8 @@ run := $(shell shuf -e $(run))
 run_O := $(shell shuf -e $(run_O))
 endif
 
+max_width := $(shell echo $(run_O) | sed 's/ /\n/g' | wc -L)
+
 ifdef DEBUG
 d := $(info run   $(run))
 d := $(info run_O $(run_O))
@@ -267,13 +275,13 @@ endif
 
 MAKEFLAGS := --no-print-directory
 
-clean := @(cd $(PERF); make -s -f $(MK) $(O_OPT) clean >/dev/null)
+clean := @(cd $(PERF); $(MAKE_F) -s $(O_OPT) clean >/dev/null)
 
 $(run):
 	$(call clean)
 	@TMP_DEST=$$(mktemp -d); \
-	cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) $(O_OPT) DESTDIR=$$TMP_DEST $($@)"; \
-	echo "- $@: $$cmd" && echo $$cmd > $@ && \
+	cmd="cd $(PERF) && $(MAKE_F) $($@) $(PARALLEL_OPT) $(O_OPT) DESTDIR=$$TMP_DEST"; \
+	printf "%*.*s: %s\n" $(max_width) $(max_width) "$@" "$$cmd" && echo $$cmd > $@ && \
 	( eval $$cmd ) >> $@ 2>&1; \
 	echo "  test: $(call test,$@)" >> $@ 2>&1; \
 	$(call test,$@) && \
@@ -283,8 +291,8 @@ $(run_O):
 	$(call clean)
 	@TMP_O=$$(mktemp -d); \
 	TMP_DEST=$$(mktemp -d); \
-	cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \
-	echo "- $@: $$cmd" && echo $$cmd > $@ && \
+	cmd="cd $(PERF) && $(MAKE_F) $($(patsubst %_O,%,$@)) $(PARALLEL_OPT) O=$$TMP_O DESTDIR=$$TMP_DEST"; \
+	printf "%*.*s: %s\n" $(max_width) $(max_width) "$@" "$$cmd" && echo $$cmd > $@ && \
 	( eval $$cmd ) >> $@ 2>&1 && \
 	echo "  test: $(call test_O,$@)" >> $@ 2>&1; \
 	$(call test_O,$@) && \
@@ -313,11 +321,43 @@ make_kernelsrc_tools:
 	(make -C ../../tools $(PARALLEL_OPT) $(K_O_OPT) perf) > $@ 2>&1 && \
 	test -x $(KERNEL_O)/tools/perf/perf && rm -f $@ || (cat $@ ; false)
 
+FEATURES_DUMP_FILE := $(FULL_O)/BUILD_TEST_FEATURE_DUMP
+FEATURES_DUMP_FILE_STATIC := $(FULL_O)/BUILD_TEST_FEATURE_DUMP_STATIC
+
 all: $(run) $(run_O) tarpkg make_kernelsrc make_kernelsrc_tools
 	@echo OK
+	@rm -f $(FEATURES_DUMP_FILE) $(FEATURES_DUMP_FILE_STATIC)
 
 out: $(run_O)
 	@echo OK
+	@rm -f $(FEATURES_DUMP_FILE) $(FEATURES_DUMP_FILE_STATIC)
+
+ifeq ($(REUSE_FEATURES_DUMP),1)
+$(FEATURES_DUMP_FILE):
+	$(call clean)
+	@cmd="cd $(PERF) && make FEATURE_DUMP_COPY=$@ $(O_OPT) feature-dump"; \
+	echo "- $@: $$cmd" && echo $$cmd && \
+	( eval $$cmd ) > /dev/null 2>&1
+
+$(FEATURES_DUMP_FILE_STATIC):
+	$(call clean)
+	@cmd="cd $(PERF) && make FEATURE_DUMP_COPY=$@ $(O_OPT) LDFLAGS='-static' feature-dump"; \
+	echo "- $@: $$cmd" && echo $$cmd && \
+	( eval $$cmd ) > /dev/null 2>&1
+
+# Add feature dump dependency for run/run_O targets
+$(foreach t,$(run) $(run_O),$(eval \
+	$(t): $(if $(findstring make_static,$(t)),\
+		$(FEATURES_DUMP_FILE_STATIC),\
+		$(FEATURES_DUMP_FILE))))
+
+# Append 'FEATURES_DUMP=' option to all test cases. For example:
+# make_no_libbpf: NO_LIBBPF=1  --> NO_LIBBPF=1 FEATURES_DUMP=/a/b/BUILD_TEST_FEATURE_DUMP
+# make_static: LDFLAGS=-static --> LDFLAGS=-static FEATURES_DUMP=/a/b/BUILD_TEST_FEATURE_DUMP_STATIC
+$(foreach t,$(run),$(if $(findstring make_static,$(t)),\
+			$(eval $(t) := $($(t)) FEATURES_DUMP=$(FEATURES_DUMP_FILE_STATIC)),\
+			$(eval $(t) := $($(t)) FEATURES_DUMP=$(FEATURES_DUMP_FILE))))
+endif
 
 .PHONY: all $(run) $(run_O) tarpkg clean make_kernelsrc make_kernelsrc_tools
 endif # ifndef MK
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index abe8849d1..7865f68dc 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1271,6 +1271,38 @@ static int test__checkevent_precise_max_modifier(struct perf_evlist *evlist)
 	return 0;
 }
 
+static int test__checkevent_config_symbol(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "insn") == 0);
+	return 0;
+}
+
+static int test__checkevent_config_raw(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "rawpmu") == 0);
+	return 0;
+}
+
+static int test__checkevent_config_num(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "numpmu") == 0);
+	return 0;
+}
+
+static int test__checkevent_config_cache(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "cachepmu") == 0);
+	return 0;
+}
+
 static int count_tracepoints(void)
 {
 	struct dirent *events_ent;
@@ -1579,6 +1611,26 @@ static struct evlist_test test__events[] = {
 		.check = test__checkevent_precise_max_modifier,
 		.id    = 47,
 	},
+	{
+		.name  = "instructions/name=insn/",
+		.check = test__checkevent_config_symbol,
+		.id    = 48,
+	},
+	{
+		.name  = "r1234/name=rawpmu/",
+		.check = test__checkevent_config_raw,
+		.id    = 49,
+	},
+	{
+		.name  = "4:0x6530160/name=numpmu/",
+		.check = test__checkevent_config_num,
+		.id    = 50,
+	},
+	{
+		.name  = "L1-dcache-misses/name=cachepmu/",
+		.check = test__checkevent_config_cache,
+		.id    = 51,
+	},
 };
 
 static struct evlist_test test__events_pmu[] = {
@@ -1666,7 +1718,7 @@ static int test_term(struct terms_test *t)
 	}
 
 	ret = t->check(&terms);
-	parse_events__free_terms(&terms);
+	parse_events_terms__purge(&terms);
 
 	return ret;
 }
diff --git a/tools/perf/tests/perf-targz-src-pkg b/tools/perf/tests/perf-targz-src-pkg
index 238aa3927..f2d9c5fe5 100755
--- a/tools/perf/tests/perf-targz-src-pkg
+++ b/tools/perf/tests/perf-targz-src-pkg
@@ -15,7 +15,7 @@ TMP_DEST=$(mktemp -d)
 tar xf ${TARBALL} -C $TMP_DEST
 rm -f ${TARBALL}
 cd - > /dev/null
-make -C $TMP_DEST/perf*/tools/perf > /dev/null 2>&1
+make -C $TMP_DEST/perf*/tools/perf > /dev/null
 RC=$?
 rm -rf ${TMP_DEST}
 exit $RC
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index f0bfc9e8f..630b0b409 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -110,7 +110,6 @@ int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
 	 */
 	for (nd = rb_first(&vmlinux_map->dso->symbols[type]); nd; nd = rb_next(nd)) {
 		struct symbol *pair, *first_pair;
-		bool backwards = true;
 
 		sym  = rb_entry(nd, struct symbol, rb_node);
 
@@ -151,27 +150,14 @@ next_pair:
 				continue;
 
 			} else {
-				struct rb_node *nnd;
-detour:
-				nnd = backwards ? rb_prev(&pair->rb_node) :
-						  rb_next(&pair->rb_node);
-				if (nnd) {
-					struct symbol *next = rb_entry(nnd, struct symbol, rb_node);
-
-					if (UM(next->start) == mem_start) {
-						pair = next;
+				pair = machine__find_kernel_symbol_by_name(&kallsyms, type, sym->name, NULL, NULL);
+				if (pair) {
+					if (UM(pair->start) == mem_start)
 						goto next_pair;
-					}
-				}
 
-				if (backwards) {
-					backwards = false;
-					pair = first_pair;
-					goto detour;
+					pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n",
+						 mem_start, sym->name, pair->name);
 				}
-
-				pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n",
-					 mem_start, sym->name, pair->name);
 			}
 		} else
 			pr_debug("%#" PRIx64 ": %s not on kallsyms\n",
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index d37202121..af68a9d48 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -531,8 +531,8 @@ static struct ui_browser_colorset {
 		.bg	  = "yellow",
 	},
 	{
-		.colorset = HE_COLORSET_CODE,
-		.name	  = "code",
+		.colorset = HE_COLORSET_JUMP_ARROWS,
+		.name	  = "jump_arrows",
 		.fg	  = "blue",
 		.bg	  = "default",
 	},
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index 01781de59..be3b70eb5 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -7,7 +7,7 @@
 #define HE_COLORSET_MEDIUM	51
 #define HE_COLORSET_NORMAL	52
 #define HE_COLORSET_SELECTED	53
-#define HE_COLORSET_CODE	54
+#define HE_COLORSET_JUMP_ARROWS	54
 #define HE_COLORSET_ADDR	55
 #define HE_COLORSET_ROOT	56
 
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 718bd46d4..4fc208e82 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -284,7 +284,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 		to = (u64)btarget->idx;
 	}
 
-	ui_browser__set_color(browser, HE_COLORSET_CODE);
+	ui_browser__set_color(browser, HE_COLORSET_JUMP_ARROWS);
 	__ui_browser__line_arrow(browser, pcnt_width + 2 + ab->addr_width,
 				 from, to);
 }
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 7bb47424b..2a8341415 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -32,6 +32,7 @@ struct hist_browser {
 	bool		     show_headers;
 	float		     min_pcnt;
 	u64		     nr_non_filtered_entries;
+	u64		     nr_hierarchy_entries;
 	u64		     nr_callchain_rows;
 };
 
@@ -58,11 +59,11 @@ static int hist_browser__get_folding(struct hist_browser *browser)
 
 	for (nd = rb_first(&hists->entries);
 	     (nd = hists__filter_entries(nd, browser->min_pcnt)) != NULL;
-	     nd = rb_next(nd)) {
+	     nd = rb_hierarchy_next(nd)) {
 		struct hist_entry *he =
 			rb_entry(nd, struct hist_entry, rb_node);
 
-		if (he->unfolded)
+		if (he->leaf && he->unfolded)
 			unfolded_rows += he->nr_rows;
 	}
 	return unfolded_rows;
@@ -72,7 +73,9 @@ static u32 hist_browser__nr_entries(struct hist_browser *hb)
 {
 	u32 nr_entries;
 
-	if (hist_browser__has_filter(hb))
+	if (symbol_conf.report_hierarchy)
+		nr_entries = hb->nr_hierarchy_entries;
+	else if (hist_browser__has_filter(hb))
 		nr_entries = hb->nr_non_filtered_entries;
 	else
 		nr_entries = hb->hists->nr_entries;
@@ -247,6 +250,38 @@ static int callchain__count_rows(struct rb_root *chain)
 	return n;
 }
 
+static int hierarchy_count_rows(struct hist_browser *hb, struct hist_entry *he,
+				bool include_children)
+{
+	int count = 0;
+	struct rb_node *node;
+	struct hist_entry *child;
+
+	if (he->leaf)
+		return callchain__count_rows(&he->sorted_chain);
+
+	if (he->has_no_entry)
+		return 1;
+
+	node = rb_first(&he->hroot_out);
+	while (node) {
+		float percent;
+
+		child = rb_entry(node, struct hist_entry, rb_node);
+		percent = hist_entry__get_percent_limit(child);
+
+		if (!child->filtered && percent >= hb->min_pcnt) {
+			count++;
+
+			if (include_children && child->unfolded)
+				count += hierarchy_count_rows(hb, child, true);
+		}
+
+		node = rb_next(node);
+	}
+	return count;
+}
+
 static bool hist_entry__toggle_fold(struct hist_entry *he)
 {
 	if (!he)
@@ -326,11 +361,17 @@ static void callchain__init_have_children(struct rb_root *root)
 
 static void hist_entry__init_have_children(struct hist_entry *he)
 {
-	if (!he->init_have_children) {
+	if (he->init_have_children)
+		return;
+
+	if (he->leaf) {
 		he->has_children = !RB_EMPTY_ROOT(&he->sorted_chain);
 		callchain__init_have_children(&he->sorted_chain);
-		he->init_have_children = true;
+	} else {
+		he->has_children = !RB_EMPTY_ROOT(&he->hroot_out);
 	}
+
+	he->init_have_children = true;
 }
 
 static bool hist_browser__toggle_fold(struct hist_browser *browser)
@@ -349,17 +390,49 @@ static bool hist_browser__toggle_fold(struct hist_browser *browser)
 		has_children = callchain_list__toggle_fold(cl);
 
 	if (has_children) {
+		int child_rows = 0;
+
 		hist_entry__init_have_children(he);
 		browser->b.nr_entries -= he->nr_rows;
-		browser->nr_callchain_rows -= he->nr_rows;
 
-		if (he->unfolded)
-			he->nr_rows = callchain__count_rows(&he->sorted_chain);
+		if (he->leaf)
+			browser->nr_callchain_rows -= he->nr_rows;
 		else
+			browser->nr_hierarchy_entries -= he->nr_rows;
+
+		if (symbol_conf.report_hierarchy)
+			child_rows = hierarchy_count_rows(browser, he, true);
+
+		if (he->unfolded) {
+			if (he->leaf)
+				he->nr_rows = callchain__count_rows(&he->sorted_chain);
+			else
+				he->nr_rows = hierarchy_count_rows(browser, he, false);
+
+			/* account grand children */
+			if (symbol_conf.report_hierarchy)
+				browser->b.nr_entries += child_rows - he->nr_rows;
+
+			if (!he->leaf && he->nr_rows == 0) {
+				he->has_no_entry = true;
+				he->nr_rows = 1;
+			}
+		} else {
+			if (symbol_conf.report_hierarchy)
+				browser->b.nr_entries -= child_rows - he->nr_rows;
+
+			if (he->has_no_entry)
+				he->has_no_entry = false;
+
 			he->nr_rows = 0;
+		}
 
 		browser->b.nr_entries += he->nr_rows;
-		browser->nr_callchain_rows += he->nr_rows;
+
+		if (he->leaf)
+			browser->nr_callchain_rows += he->nr_rows;
+		else
+			browser->nr_hierarchy_entries += he->nr_rows;
 
 		return true;
 	}
@@ -422,13 +495,38 @@ static int callchain__set_folding(struct rb_root *chain, bool unfold)
 	return n;
 }
 
-static void hist_entry__set_folding(struct hist_entry *he, bool unfold)
+static int hierarchy_set_folding(struct hist_browser *hb, struct hist_entry *he,
+				 bool unfold __maybe_unused)
+{
+	float percent;
+	struct rb_node *nd;
+	struct hist_entry *child;
+	int n = 0;
+
+	for (nd = rb_first(&he->hroot_out); nd; nd = rb_next(nd)) {
+		child = rb_entry(nd, struct hist_entry, rb_node);
+		percent = hist_entry__get_percent_limit(child);
+		if (!child->filtered && percent >= hb->min_pcnt)
+			n++;
+	}
+
+	return n;
+}
+
+static void hist_entry__set_folding(struct hist_entry *he,
+				    struct hist_browser *hb, bool unfold)
 {
 	hist_entry__init_have_children(he);
 	he->unfolded = unfold ? he->has_children : false;
 
 	if (he->has_children) {
-		int n = callchain__set_folding(&he->sorted_chain, unfold);
+		int n;
+
+		if (he->leaf)
+			n = callchain__set_folding(&he->sorted_chain, unfold);
+		else
+			n = hierarchy_set_folding(hb, he, unfold);
+
 		he->nr_rows = unfold ? n : 0;
 	} else
 		he->nr_rows = 0;
@@ -438,19 +536,38 @@ static void
 __hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 {
 	struct rb_node *nd;
-	struct hists *hists = browser->hists;
+	struct hist_entry *he;
+	double percent;
 
-	for (nd = rb_first(&hists->entries);
-	     (nd = hists__filter_entries(nd, browser->min_pcnt)) != NULL;
-	     nd = rb_next(nd)) {
-		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
-		hist_entry__set_folding(he, unfold);
-		browser->nr_callchain_rows += he->nr_rows;
+	nd = rb_first(&browser->hists->entries);
+	while (nd) {
+		he = rb_entry(nd, struct hist_entry, rb_node);
+
+		/* set folding state even if it's currently folded */
+		nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD);
+
+		hist_entry__set_folding(he, browser, unfold);
+
+		percent = hist_entry__get_percent_limit(he);
+		if (he->filtered || percent < browser->min_pcnt)
+			continue;
+
+		if (!he->depth || unfold)
+			browser->nr_hierarchy_entries++;
+		if (he->leaf)
+			browser->nr_callchain_rows += he->nr_rows;
+		else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
+			browser->nr_hierarchy_entries++;
+			he->has_no_entry = true;
+			he->nr_rows = 1;
+		} else
+			he->has_no_entry = false;
 	}
 }
 
 static void hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 {
+	browser->nr_hierarchy_entries = 0;
 	browser->nr_callchain_rows = 0;
 	__hist_browser__set_folding(browser, unfold);
 
@@ -657,9 +774,24 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
 	return 1;
 }
 
+static bool check_percent_display(struct rb_node *node, u64 parent_total)
+{
+	struct callchain_node *child;
+
+	if (node == NULL)
+		return false;
+
+	if (rb_next(node))
+		return true;
+
+	child = rb_entry(node, struct callchain_node, rb_node);
+	return callchain_cumul_hits(child) != parent_total;
+}
+
 static int hist_browser__show_callchain_flat(struct hist_browser *browser,
 					     struct rb_root *root,
 					     unsigned short row, u64 total,
+					     u64 parent_total,
 					     print_callchain_entry_fn print,
 					     struct callchain_print_arg *arg,
 					     check_output_full_fn is_output_full)
@@ -669,7 +801,7 @@ static int hist_browser__show_callchain_flat(struct hist_browser *browser,
 	bool need_percent;
 
 	node = rb_first(root);
-	need_percent = node && rb_next(node);
+	need_percent = check_percent_display(node, parent_total);
 
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
@@ -763,6 +895,7 @@ static char *hist_browser__folded_callchain_str(struct hist_browser *browser,
 static int hist_browser__show_callchain_folded(struct hist_browser *browser,
 					       struct rb_root *root,
 					       unsigned short row, u64 total,
+					       u64 parent_total,
 					       print_callchain_entry_fn print,
 					       struct callchain_print_arg *arg,
 					       check_output_full_fn is_output_full)
@@ -772,7 +905,7 @@ static int hist_browser__show_callchain_folded(struct hist_browser *browser,
 	bool need_percent;
 
 	node = rb_first(root);
-	need_percent = node && rb_next(node);
+	need_percent = check_percent_display(node, parent_total);
 
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
@@ -847,17 +980,21 @@ next:
 static int hist_browser__show_callchain_graph(struct hist_browser *browser,
 					struct rb_root *root, int level,
 					unsigned short row, u64 total,
+					u64 parent_total,
 					print_callchain_entry_fn print,
 					struct callchain_print_arg *arg,
 					check_output_full_fn is_output_full)
 {
 	struct rb_node *node;
 	int first_row = row, offset = level * LEVEL_OFFSET_STEP;
-	u64 new_total;
 	bool need_percent;
+	u64 percent_total = total;
+
+	if (callchain_param.mode == CHAIN_GRAPH_REL)
+		percent_total = parent_total;
 
 	node = rb_first(root);
-	need_percent = node && rb_next(node);
+	need_percent = check_percent_display(node, parent_total);
 
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
@@ -878,7 +1015,7 @@ static int hist_browser__show_callchain_graph(struct hist_browser *browser,
 			folded_sign = callchain_list__folded(chain);
 
 			row += hist_browser__show_callchain_list(browser, child,
-							chain, row, total,
+							chain, row, percent_total,
 							was_first && need_percent,
 							offset + extra_offset,
 							print, arg);
@@ -893,13 +1030,9 @@ static int hist_browser__show_callchain_graph(struct hist_browser *browser,
 		if (folded_sign == '-') {
 			const int new_level = level + (extra_offset ? 2 : 1);
 
-			if (callchain_param.mode == CHAIN_GRAPH_REL)
-				new_total = child->children_hit;
-			else
-				new_total = total;
-
 			row += hist_browser__show_callchain_graph(browser, &child->rb_root,
-							    new_level, row, new_total,
+							    new_level, row, total,
+							    child->children_hit,
 							    print, arg, is_output_full);
 		}
 		if (is_output_full(browser, row))
@@ -918,27 +1051,29 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 					check_output_full_fn is_output_full)
 {
 	u64 total = hists__total_period(entry->hists);
+	u64 parent_total;
 	int printed;
 
-	if (callchain_param.mode == CHAIN_GRAPH_REL) {
-		if (symbol_conf.cumulate_callchain)
-			total = entry->stat_acc->period;
-		else
-			total = entry->stat.period;
-	}
+	if (symbol_conf.cumulate_callchain)
+		parent_total = entry->stat_acc->period;
+	else
+		parent_total = entry->stat.period;
 
 	if (callchain_param.mode == CHAIN_FLAT) {
 		printed = hist_browser__show_callchain_flat(browser,
-						&entry->sorted_chain, row, total,
-						print, arg, is_output_full);
+						&entry->sorted_chain, row,
+						total, parent_total, print, arg,
+						is_output_full);
 	} else if (callchain_param.mode == CHAIN_FOLDED) {
 		printed = hist_browser__show_callchain_folded(browser,
-						&entry->sorted_chain, row, total,
-						print, arg, is_output_full);
+						&entry->sorted_chain, row,
+						total, parent_total, print, arg,
+						is_output_full);
 	} else {
 		printed = hist_browser__show_callchain_graph(browser,
-						&entry->sorted_chain, level, row, total,
-						print, arg, is_output_full);
+						&entry->sorted_chain, level, row,
+						total, parent_total, print, arg,
+						is_output_full);
 	}
 
 	if (arg->is_current_entry)
@@ -1043,7 +1178,6 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 				    struct hist_entry *entry,
 				    unsigned short row)
 {
-	char s[256];
 	int printed = 0;
 	int width = browser->b.width;
 	char folded_sign = ' ';
@@ -1068,16 +1202,18 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			.folded_sign	= folded_sign,
 			.current_entry	= current_entry,
 		};
-		struct perf_hpp hpp = {
-			.buf		= s,
-			.size		= sizeof(s),
-			.ptr		= &arg,
-		};
 		int column = 0;
 
 		hist_browser__gotorc(browser, row, 0);
 
-		perf_hpp__for_each_format(fmt) {
+		hists__for_each_format(browser->hists, fmt) {
+			char s[2048];
+			struct perf_hpp hpp = {
+				.buf	= s,
+				.size	= sizeof(s),
+				.ptr	= &arg,
+			};
+
 			if (perf_hpp__should_skip(fmt, entry->hists) ||
 			    column++ < browser->b.horiz_scroll)
 				continue;
@@ -1102,11 +1238,18 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			}
 
 			if (fmt->color) {
-				width -= fmt->color(fmt, &hpp, entry);
+				int ret = fmt->color(fmt, &hpp, entry);
+				hist_entry__snprintf_alignment(entry, &hpp, fmt, ret);
+				/*
+				 * fmt->color() already used ui_browser to
+				 * print the non alignment bits, skip it (+ret):
+				 */
+				ui_browser__printf(&browser->b, "%s", s + ret);
 			} else {
-				width -= fmt->entry(fmt, &hpp, entry);
+				hist_entry__snprintf_alignment(entry, &hpp, fmt, fmt->entry(fmt, &hpp, entry));
 				ui_browser__printf(&browser->b, "%s", s);
 			}
+			width -= hpp.buf - s;
 		}
 
 		/* The scroll bar isn't being used */
@@ -1134,6 +1277,233 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 	return printed;
 }
 
+static int hist_browser__show_hierarchy_entry(struct hist_browser *browser,
+					      struct hist_entry *entry,
+					      unsigned short row,
+					      int level)
+{
+	int printed = 0;
+	int width = browser->b.width;
+	char folded_sign = ' ';
+	bool current_entry = ui_browser__is_current_entry(&browser->b, row);
+	off_t row_offset = entry->row_offset;
+	bool first = true;
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+	struct hpp_arg arg = {
+		.b		= &browser->b,
+		.current_entry	= current_entry,
+	};
+	int column = 0;
+	int hierarchy_indent = (entry->hists->nr_hpp_node - 2) * HIERARCHY_INDENT;
+
+	if (current_entry) {
+		browser->he_selection = entry;
+		browser->selection = &entry->ms;
+	}
+
+	hist_entry__init_have_children(entry);
+	folded_sign = hist_entry__folded(entry);
+	arg.folded_sign = folded_sign;
+
+	if (entry->leaf && row_offset) {
+		row_offset--;
+		goto show_callchain;
+	}
+
+	hist_browser__gotorc(browser, row, 0);
+
+	if (current_entry && browser->b.navkeypressed)
+		ui_browser__set_color(&browser->b, HE_COLORSET_SELECTED);
+	else
+		ui_browser__set_color(&browser->b, HE_COLORSET_NORMAL);
+
+	ui_browser__write_nstring(&browser->b, "", level * HIERARCHY_INDENT);
+	width -= level * HIERARCHY_INDENT;
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&entry->hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		char s[2048];
+		struct perf_hpp hpp = {
+			.buf		= s,
+			.size		= sizeof(s),
+			.ptr		= &arg,
+		};
+
+		if (perf_hpp__should_skip(fmt, entry->hists) ||
+		    column++ < browser->b.horiz_scroll)
+			continue;
+
+		if (current_entry && browser->b.navkeypressed) {
+			ui_browser__set_color(&browser->b,
+					      HE_COLORSET_SELECTED);
+		} else {
+			ui_browser__set_color(&browser->b,
+					      HE_COLORSET_NORMAL);
+		}
+
+		if (first) {
+			ui_browser__printf(&browser->b, "%c", folded_sign);
+			width--;
+			first = false;
+		} else {
+			ui_browser__printf(&browser->b, "  ");
+			width -= 2;
+		}
+
+		if (fmt->color) {
+			int ret = fmt->color(fmt, &hpp, entry);
+			hist_entry__snprintf_alignment(entry, &hpp, fmt, ret);
+			/*
+			 * fmt->color() already used ui_browser to
+			 * print the non alignment bits, skip it (+ret):
+			 */
+			ui_browser__printf(&browser->b, "%s", s + ret);
+		} else {
+			int ret = fmt->entry(fmt, &hpp, entry);
+			hist_entry__snprintf_alignment(entry, &hpp, fmt, ret);
+			ui_browser__printf(&browser->b, "%s", s);
+		}
+		width -= hpp.buf - s;
+	}
+
+	ui_browser__write_nstring(&browser->b, "", hierarchy_indent);
+	width -= hierarchy_indent;
+
+	if (column >= browser->b.horiz_scroll) {
+		char s[2048];
+		struct perf_hpp hpp = {
+			.buf		= s,
+			.size		= sizeof(s),
+			.ptr		= &arg,
+		};
+
+		if (current_entry && browser->b.navkeypressed) {
+			ui_browser__set_color(&browser->b,
+					      HE_COLORSET_SELECTED);
+		} else {
+			ui_browser__set_color(&browser->b,
+					      HE_COLORSET_NORMAL);
+		}
+
+		perf_hpp_list__for_each_format(entry->hpp_list, fmt) {
+			ui_browser__write_nstring(&browser->b, "", 2);
+			width -= 2;
+
+			/*
+			 * No need to call hist_entry__snprintf_alignment()
+			 * since this fmt is always the last column in the
+			 * hierarchy mode.
+			 */
+			if (fmt->color) {
+				width -= fmt->color(fmt, &hpp, entry);
+			} else {
+				int i = 0;
+
+				width -= fmt->entry(fmt, &hpp, entry);
+				ui_browser__printf(&browser->b, "%s", ltrim(s));
+
+				while (isspace(s[i++]))
+					width++;
+			}
+		}
+	}
+
+	/* The scroll bar isn't being used */
+	if (!browser->b.navkeypressed)
+		width += 1;
+
+	ui_browser__write_nstring(&browser->b, "", width);
+
+	++row;
+	++printed;
+
+show_callchain:
+	if (entry->leaf && folded_sign == '-' && row != browser->b.rows) {
+		struct callchain_print_arg carg = {
+			.row_offset = row_offset,
+		};
+
+		printed += hist_browser__show_callchain(browser, entry,
+					level + 1, row,
+					hist_browser__show_callchain_entry, &carg,
+					hist_browser__check_output_full);
+	}
+
+	return printed;
+}
+
+static int hist_browser__show_no_entry(struct hist_browser *browser,
+				       unsigned short row, int level)
+{
+	int width = browser->b.width;
+	bool current_entry = ui_browser__is_current_entry(&browser->b, row);
+	bool first = true;
+	int column = 0;
+	int ret;
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+	int indent = browser->hists->nr_hpp_node - 2;
+
+	if (current_entry) {
+		browser->he_selection = NULL;
+		browser->selection = NULL;
+	}
+
+	hist_browser__gotorc(browser, row, 0);
+
+	if (current_entry && browser->b.navkeypressed)
+		ui_browser__set_color(&browser->b, HE_COLORSET_SELECTED);
+	else
+		ui_browser__set_color(&browser->b, HE_COLORSET_NORMAL);
+
+	ui_browser__write_nstring(&browser->b, "", level * HIERARCHY_INDENT);
+	width -= level * HIERARCHY_INDENT;
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&browser->hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		if (perf_hpp__should_skip(fmt, browser->hists) ||
+		    column++ < browser->b.horiz_scroll)
+			continue;
+
+		ret = fmt->width(fmt, NULL, hists_to_evsel(browser->hists));
+
+		if (first) {
+			/* for folded sign */
+			first = false;
+			ret++;
+		} else {
+			/* space between columns */
+			ret += 2;
+		}
+
+		ui_browser__write_nstring(&browser->b, "", ret);
+		width -= ret;
+	}
+
+	ui_browser__write_nstring(&browser->b, "", indent * HIERARCHY_INDENT);
+	width -= indent * HIERARCHY_INDENT;
+
+	if (column >= browser->b.horiz_scroll) {
+		char buf[32];
+
+		ret = snprintf(buf, sizeof(buf), "no entry >= %.2f%%", browser->min_pcnt);
+		ui_browser__printf(&browser->b, "  %s", buf);
+		width -= ret + 2;
+	}
+
+	/* The scroll bar isn't being used */
+	if (!browser->b.navkeypressed)
+		width += 1;
+
+	ui_browser__write_nstring(&browser->b, "", width);
+	return 1;
+}
+
 static int advance_hpp_check(struct perf_hpp *hpp, int inc)
 {
 	advance_hpp(hpp, inc);
@@ -1157,7 +1527,7 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char *
 			return ret;
 	}
 
-	perf_hpp__for_each_format(fmt) {
+	hists__for_each_format(browser->hists, fmt) {
 		if (perf_hpp__should_skip(fmt, hists)  || column++ < browser->b.horiz_scroll)
 			continue;
 
@@ -1173,11 +1543,96 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char *
 	return ret;
 }
 
+static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *browser, char *buf, size_t size)
+{
+	struct hists *hists = browser->hists;
+	struct perf_hpp dummy_hpp = {
+		.buf    = buf,
+		.size   = size,
+	};
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+	size_t ret = 0;
+	int column = 0;
+	int indent = hists->nr_hpp_node - 2;
+	bool first_node, first_col;
+
+	ret = scnprintf(buf, size, " ");
+	if (advance_hpp_check(&dummy_hpp, ret))
+		return ret;
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		if (column++ < browser->b.horiz_scroll)
+			continue;
+
+		ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+		if (advance_hpp_check(&dummy_hpp, ret))
+			break;
+
+		ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "  ");
+		if (advance_hpp_check(&dummy_hpp, ret))
+			break;
+	}
+
+	ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "%*s",
+			indent * HIERARCHY_INDENT, "");
+	if (advance_hpp_check(&dummy_hpp, ret))
+		return ret;
+
+	first_node = true;
+	list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
+		if (!first_node) {
+			ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, " / ");
+			if (advance_hpp_check(&dummy_hpp, ret))
+				break;
+		}
+		first_node = false;
+
+		first_col = true;
+		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+			char *start;
+
+			if (perf_hpp__should_skip(fmt, hists))
+				continue;
+
+			if (!first_col) {
+				ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "+");
+				if (advance_hpp_check(&dummy_hpp, ret))
+					break;
+			}
+			first_col = false;
+
+			ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+			dummy_hpp.buf[ret] = '\0';
+			rtrim(dummy_hpp.buf);
+
+			start = ltrim(dummy_hpp.buf);
+			ret = strlen(start);
+
+			if (start != dummy_hpp.buf)
+				memmove(dummy_hpp.buf, start, ret + 1);
+
+			if (advance_hpp_check(&dummy_hpp, ret))
+				break;
+		}
+	}
+
+	return ret;
+}
+
 static void hist_browser__show_headers(struct hist_browser *browser)
 {
 	char headers[1024];
 
-	hists_browser__scnprintf_headers(browser, headers, sizeof(headers));
+	if (symbol_conf.report_hierarchy)
+		hists_browser__scnprintf_hierarchy_headers(browser, headers,
+							   sizeof(headers));
+	else
+		hists_browser__scnprintf_headers(browser, headers,
+						 sizeof(headers));
 	ui_browser__gotorc(&browser->b, 0, 0);
 	ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
 	ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1);
@@ -1209,18 +1664,34 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser)
 	hb->he_selection = NULL;
 	hb->selection = NULL;
 
-	for (nd = browser->top; nd; nd = rb_next(nd)) {
+	for (nd = browser->top; nd; nd = rb_hierarchy_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 		float percent;
 
-		if (h->filtered)
+		if (h->filtered) {
+			/* let it move to sibling */
+			h->unfolded = false;
 			continue;
+		}
 
 		percent = hist_entry__get_percent_limit(h);
 		if (percent < hb->min_pcnt)
 			continue;
 
-		row += hist_browser__show_entry(hb, h, row);
+		if (symbol_conf.report_hierarchy) {
+			row += hist_browser__show_hierarchy_entry(hb, h, row,
+								  h->depth);
+			if (row == browser->rows)
+				break;
+
+			if (h->has_no_entry) {
+				hist_browser__show_no_entry(hb, row, h->depth + 1);
+				row++;
+			}
+		} else {
+			row += hist_browser__show_entry(hb, h, row);
+		}
+
 		if (row == browser->rows)
 			break;
 	}
@@ -1238,7 +1709,14 @@ static struct rb_node *hists__filter_entries(struct rb_node *nd,
 		if (!h->filtered && percent >= min_pcnt)
 			return nd;
 
-		nd = rb_next(nd);
+		/*
+		 * If it's filtered, its all children also were filtered.
+		 * So move to sibling node.
+		 */
+		if (rb_next(nd))
+			nd = rb_next(nd);
+		else
+			nd = rb_hierarchy_next(nd);
 	}
 
 	return NULL;
@@ -1254,7 +1732,7 @@ static struct rb_node *hists__filter_prev_entries(struct rb_node *nd,
 		if (!h->filtered && percent >= min_pcnt)
 			return nd;
 
-		nd = rb_prev(nd);
+		nd = rb_hierarchy_prev(nd);
 	}
 
 	return NULL;
@@ -1284,8 +1762,8 @@ static void ui_browser__hists_seek(struct ui_browser *browser,
 		nd = browser->top;
 		goto do_offset;
 	case SEEK_END:
-		nd = hists__filter_prev_entries(rb_last(browser->entries),
-						hb->min_pcnt);
+		nd = rb_hierarchy_last(rb_last(browser->entries));
+		nd = hists__filter_prev_entries(nd, hb->min_pcnt);
 		first = false;
 		break;
 	default:
@@ -1319,7 +1797,7 @@ do_offset:
 	if (offset > 0) {
 		do {
 			h = rb_entry(nd, struct hist_entry, rb_node);
-			if (h->unfolded) {
+			if (h->unfolded && h->leaf) {
 				u16 remaining = h->nr_rows - h->row_offset;
 				if (offset > remaining) {
 					offset -= remaining;
@@ -1331,7 +1809,8 @@ do_offset:
 					break;
 				}
 			}
-			nd = hists__filter_entries(rb_next(nd), hb->min_pcnt);
+			nd = hists__filter_entries(rb_hierarchy_next(nd),
+						   hb->min_pcnt);
 			if (nd == NULL)
 				break;
 			--offset;
@@ -1340,7 +1819,7 @@ do_offset:
 	} else if (offset < 0) {
 		while (1) {
 			h = rb_entry(nd, struct hist_entry, rb_node);
-			if (h->unfolded) {
+			if (h->unfolded && h->leaf) {
 				if (first) {
 					if (-offset > h->row_offset) {
 						offset += h->row_offset;
@@ -1364,7 +1843,7 @@ do_offset:
 				}
 			}
 
-			nd = hists__filter_prev_entries(rb_prev(nd),
+			nd = hists__filter_prev_entries(rb_hierarchy_prev(nd),
 							hb->min_pcnt);
 			if (nd == NULL)
 				break;
@@ -1377,7 +1856,7 @@ do_offset:
 				 * row_offset at its last entry.
 				 */
 				h = rb_entry(nd, struct hist_entry, rb_node);
-				if (h->unfolded)
+				if (h->unfolded && h->leaf)
 					h->row_offset = h->nr_rows;
 				break;
 			}
@@ -1391,13 +1870,14 @@ do_offset:
 }
 
 static int hist_browser__fprintf_callchain(struct hist_browser *browser,
-					   struct hist_entry *he, FILE *fp)
+					   struct hist_entry *he, FILE *fp,
+					   int level)
 {
 	struct callchain_print_arg arg  = {
 		.fp = fp,
 	};
 
-	hist_browser__show_callchain(browser, he, 1, 0,
+	hist_browser__show_callchain(browser, he, level, 0,
 				     hist_browser__fprintf_callchain_entry, &arg,
 				     hist_browser__check_dump_full);
 	return arg.printed;
@@ -1423,7 +1903,7 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser,
 	if (symbol_conf.use_callchain)
 		printed += fprintf(fp, "%c ", folded_sign);
 
-	perf_hpp__for_each_format(fmt) {
+	hists__for_each_format(browser->hists, fmt) {
 		if (perf_hpp__should_skip(fmt, he->hists))
 			continue;
 
@@ -1434,12 +1914,71 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser,
 			first = false;
 
 		ret = fmt->entry(fmt, &hpp, he);
+		ret = hist_entry__snprintf_alignment(he, &hpp, fmt, ret);
 		advance_hpp(&hpp, ret);
 	}
-	printed += fprintf(fp, "%s\n", rtrim(s));
+	printed += fprintf(fp, "%s\n", s);
 
 	if (folded_sign == '-')
-		printed += hist_browser__fprintf_callchain(browser, he, fp);
+		printed += hist_browser__fprintf_callchain(browser, he, fp, 1);
+
+	return printed;
+}
+
+
+static int hist_browser__fprintf_hierarchy_entry(struct hist_browser *browser,
+						 struct hist_entry *he,
+						 FILE *fp, int level)
+{
+	char s[8192];
+	int printed = 0;
+	char folded_sign = ' ';
+	struct perf_hpp hpp = {
+		.buf = s,
+		.size = sizeof(s),
+	};
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+	bool first = true;
+	int ret;
+	int hierarchy_indent = (he->hists->nr_hpp_node - 2) * HIERARCHY_INDENT;
+
+	printed = fprintf(fp, "%*s", level * HIERARCHY_INDENT, "");
+
+	folded_sign = hist_entry__folded(he);
+	printed += fprintf(fp, "%c", folded_sign);
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&he->hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		if (!first) {
+			ret = scnprintf(hpp.buf, hpp.size, "  ");
+			advance_hpp(&hpp, ret);
+		} else
+			first = false;
+
+		ret = fmt->entry(fmt, &hpp, he);
+		advance_hpp(&hpp, ret);
+	}
+
+	ret = scnprintf(hpp.buf, hpp.size, "%*s", hierarchy_indent, "");
+	advance_hpp(&hpp, ret);
+
+	perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+		ret = scnprintf(hpp.buf, hpp.size, "  ");
+		advance_hpp(&hpp, ret);
+
+		ret = fmt->entry(fmt, &hpp, he);
+		advance_hpp(&hpp, ret);
+	}
+
+	printed += fprintf(fp, "%s\n", rtrim(s));
+
+	if (he->leaf && folded_sign == '-') {
+		printed += hist_browser__fprintf_callchain(browser, he, fp,
+							   he->depth + 1);
+	}
 
 	return printed;
 }
@@ -1453,8 +1992,16 @@ static int hist_browser__fprintf(struct hist_browser *browser, FILE *fp)
 	while (nd) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
-		printed += hist_browser__fprintf_entry(browser, h, fp);
-		nd = hists__filter_entries(rb_next(nd), browser->min_pcnt);
+		if (symbol_conf.report_hierarchy) {
+			printed += hist_browser__fprintf_hierarchy_entry(browser,
+									 h, fp,
+									 h->depth);
+		} else {
+			printed += hist_browser__fprintf_entry(browser, h, fp);
+		}
+
+		nd = hists__filter_entries(rb_hierarchy_next(nd),
+					   browser->min_pcnt);
 	}
 
 	return printed;
@@ -1589,11 +2136,18 @@ static int hists__browser_title(struct hists *hists,
 	if (hists->uid_filter_str)
 		printed += snprintf(bf + printed, size - printed,
 				    ", UID: %s", hists->uid_filter_str);
-	if (thread)
-		printed += scnprintf(bf + printed, size - printed,
+	if (thread) {
+		if (sort__has_thread) {
+			printed += scnprintf(bf + printed, size - printed,
 				    ", Thread: %s(%d)",
 				     (thread->comm_set ? thread__comm_str(thread) : ""),
 				    thread->tid);
+		} else {
+			printed += scnprintf(bf + printed, size - printed,
+				    ", Thread: %s",
+				     (thread->comm_set ? thread__comm_str(thread) : ""));
+		}
+	}
 	if (dso)
 		printed += scnprintf(bf + printed, size - printed,
 				    ", DSO: %s", dso->short_name);
@@ -1768,15 +2322,24 @@ do_zoom_thread(struct hist_browser *browser, struct popup_action *act)
 {
 	struct thread *thread = act->thread;
 
+	if ((!sort__has_thread && !sort__has_comm) || thread == NULL)
+		return 0;
+
 	if (browser->hists->thread_filter) {
 		pstack__remove(browser->pstack, &browser->hists->thread_filter);
 		perf_hpp__set_elide(HISTC_THREAD, false);
 		thread__zput(browser->hists->thread_filter);
 		ui_helpline__pop();
 	} else {
-		ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s(%d) thread\"",
-				   thread->comm_set ? thread__comm_str(thread) : "",
-				   thread->tid);
+		if (sort__has_thread) {
+			ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s(%d) thread\"",
+					   thread->comm_set ? thread__comm_str(thread) : "",
+					   thread->tid);
+		} else {
+			ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s thread\"",
+					   thread->comm_set ? thread__comm_str(thread) : "");
+		}
+
 		browser->hists->thread_filter = thread__get(thread);
 		perf_hpp__set_elide(HISTC_THREAD, false);
 		pstack__push(browser->pstack, &browser->hists->thread_filter);
@@ -1791,13 +2354,22 @@ static int
 add_thread_opt(struct hist_browser *browser, struct popup_action *act,
 	       char **optstr, struct thread *thread)
 {
-	if (thread == NULL)
+	int ret;
+
+	if ((!sort__has_thread && !sort__has_comm) || thread == NULL)
 		return 0;
 
-	if (asprintf(optstr, "Zoom %s %s(%d) thread",
-		     browser->hists->thread_filter ? "out of" : "into",
-		     thread->comm_set ? thread__comm_str(thread) : "",
-		     thread->tid) < 0)
+	if (sort__has_thread) {
+		ret = asprintf(optstr, "Zoom %s %s(%d) thread",
+			       browser->hists->thread_filter ? "out of" : "into",
+			       thread->comm_set ? thread__comm_str(thread) : "",
+			       thread->tid);
+	} else {
+		ret = asprintf(optstr, "Zoom %s %s thread",
+			       browser->hists->thread_filter ? "out of" : "into",
+			       thread->comm_set ? thread__comm_str(thread) : "");
+	}
+	if (ret < 0)
 		return 0;
 
 	act->thread = thread;
@@ -1810,6 +2382,9 @@ do_zoom_dso(struct hist_browser *browser, struct popup_action *act)
 {
 	struct map *map = act->ms.map;
 
+	if (!sort__has_dso || map == NULL)
+		return 0;
+
 	if (browser->hists->dso_filter) {
 		pstack__remove(browser->pstack, &browser->hists->dso_filter);
 		perf_hpp__set_elide(HISTC_DSO, false);
@@ -1834,7 +2409,7 @@ static int
 add_dso_opt(struct hist_browser *browser, struct popup_action *act,
 	    char **optstr, struct map *map)
 {
-	if (map == NULL)
+	if (!sort__has_dso || map == NULL)
 		return 0;
 
 	if (asprintf(optstr, "Zoom %s %s DSO",
@@ -1859,7 +2434,7 @@ static int
 add_map_opt(struct hist_browser *browser __maybe_unused,
 	    struct popup_action *act, char **optstr, struct map *map)
 {
-	if (map == NULL)
+	if (!sort__has_dso || map == NULL)
 		return 0;
 
 	if (asprintf(optstr, "Browse map details") < 0)
@@ -1961,6 +2536,9 @@ add_exit_opt(struct hist_browser *browser __maybe_unused,
 static int
 do_zoom_socket(struct hist_browser *browser, struct popup_action *act)
 {
+	if (!sort__has_socket || act->socket < 0)
+		return 0;
+
 	if (browser->hists->socket_filter > -1) {
 		pstack__remove(browser->pstack, &browser->hists->socket_filter);
 		browser->hists->socket_filter = -1;
@@ -1980,7 +2558,7 @@ static int
 add_socket_opt(struct hist_browser *browser, struct popup_action *act,
 	       char **optstr, int socket_id)
 {
-	if (socket_id < 0)
+	if (!sort__has_socket || socket_id < 0)
 		return 0;
 
 	if (asprintf(optstr, "Zoom %s Processor Socket %d",
@@ -1998,17 +2576,60 @@ static void hist_browser__update_nr_entries(struct hist_browser *hb)
 	u64 nr_entries = 0;
 	struct rb_node *nd = rb_first(&hb->hists->entries);
 
-	if (hb->min_pcnt == 0) {
+	if (hb->min_pcnt == 0 && !symbol_conf.report_hierarchy) {
 		hb->nr_non_filtered_entries = hb->hists->nr_non_filtered_entries;
 		return;
 	}
 
 	while ((nd = hists__filter_entries(nd, hb->min_pcnt)) != NULL) {
 		nr_entries++;
-		nd = rb_next(nd);
+		nd = rb_hierarchy_next(nd);
 	}
 
 	hb->nr_non_filtered_entries = nr_entries;
+	hb->nr_hierarchy_entries = nr_entries;
+}
+
+static void hist_browser__update_percent_limit(struct hist_browser *hb,
+					       double percent)
+{
+	struct hist_entry *he;
+	struct rb_node *nd = rb_first(&hb->hists->entries);
+	u64 total = hists__total_period(hb->hists);
+	u64 min_callchain_hits = total * (percent / 100);
+
+	hb->min_pcnt = callchain_param.min_percent = percent;
+
+	while ((nd = hists__filter_entries(nd, hb->min_pcnt)) != NULL) {
+		he = rb_entry(nd, struct hist_entry, rb_node);
+
+		if (he->has_no_entry) {
+			he->has_no_entry = false;
+			he->nr_rows = 0;
+		}
+
+		if (!he->leaf || !symbol_conf.use_callchain)
+			goto next;
+
+		if (callchain_param.mode == CHAIN_GRAPH_REL) {
+			total = he->stat.period;
+
+			if (symbol_conf.cumulate_callchain)
+				total = he->stat_acc->period;
+
+			min_callchain_hits = total * (percent / 100);
+		}
+
+		callchain_param.sort(&he->sorted_chain, he->callchain,
+				     min_callchain_hits, &callchain_param);
+
+next:
+		nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD);
+
+		/* force to re-evaluate folding state of callchains */
+		he->init_have_children = false;
+		hist_entry__set_folding(he, hb, false);
+	}
 }
 
 static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
@@ -2046,6 +2667,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	"E             Expand all callchains\n"				\
 	"F             Toggle percentage of filtered entries\n"		\
 	"H             Display column headers\n"			\
+	"L             Change percent limit\n"				\
 	"m             Display context menu\n"				\
 	"S             Zoom into current Processor Socket\n"		\
 
@@ -2086,7 +2708,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	memset(options, 0, sizeof(options));
 	memset(actions, 0, sizeof(actions));
 
-	perf_hpp__for_each_format(fmt) {
+	hists__for_each_format(browser->hists, fmt) {
 		perf_hpp__reset_width(fmt, hists);
 		/*
 		 * This is done just once, and activates the horizontal scrolling
@@ -2201,6 +2823,24 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 				top->zero = !top->zero;
 			}
 			continue;
+		case 'L':
+			if (ui_browser__input_window("Percent Limit",
+					"Please enter the value you want to hide entries under that percent.",
+					buf, "ENTER: OK, ESC: Cancel",
+					delay_secs * 2) == K_ENTER) {
+				char *end;
+				double new_percent = strtod(buf, &end);
+
+				if (new_percent < 0 || new_percent > 100) {
+					ui_browser__warning(&browser->b, delay_secs * 2,
+						"Invalid percent: %.2f", new_percent);
+					continue;
+				}
+
+				hist_browser__update_percent_limit(browser, new_percent);
+				hist_browser__reset(browser);
+			}
+			continue;
 		case K_F1:
 		case 'h':
 		case '?':
@@ -2272,10 +2912,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			continue;
 		}
 
-		if (!sort__has_sym)
-			goto add_exit_option;
-
-		if (browser->selection == NULL)
+		if (!sort__has_sym || browser->selection == NULL)
 			goto skip_annotation;
 
 		if (sort__mode == SORT_MODE__BRANCH) {
@@ -2315,11 +2952,16 @@ skip_annotation:
 					     &options[nr_options],
 					     socked_id);
 		/* perf script support */
+		if (!is_report_browser(hbt))
+			goto skip_scripting;
+
 		if (browser->he_selection) {
-			nr_options += add_script_opt(browser,
-						     &actions[nr_options],
-						     &options[nr_options],
-						     thread, NULL);
+			if (sort__has_thread && thread) {
+				nr_options += add_script_opt(browser,
+							     &actions[nr_options],
+							     &options[nr_options],
+							     thread, NULL);
+			}
 			/*
 			 * Note that browser->selection != NULL
 			 * when browser->he_selection is not NULL,
@@ -2340,7 +2982,7 @@ skip_annotation:
 					     &options[nr_options], NULL, NULL);
 		nr_options += add_switch_opt(browser, &actions[nr_options],
 					     &options[nr_options]);
-add_exit_option:
+skip_scripting:
 		nr_options += add_exit_opt(browser, &actions[nr_options],
 					   &options[nr_options]);
 
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 0f8dcfdfb..2aa45b606 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -55,7 +55,7 @@ static u64 he_get_acc_##_field(struct hist_entry *he)				\
 	return he->stat_acc->_field;						\
 }										\
 										\
-static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
+static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt,		\
 				       struct perf_hpp *hpp,			\
 				       struct hist_entry *he)			\
 {										\
@@ -306,7 +306,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 
 	nr_cols = 0;
 
-	perf_hpp__for_each_format(fmt)
+	hists__for_each_format(hists, fmt)
 		col_types[nr_cols++] = G_TYPE_STRING;
 
 	store = gtk_tree_store_newv(nr_cols, col_types);
@@ -317,7 +317,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 
 	col_idx = 0;
 
-	perf_hpp__for_each_format(fmt) {
+	hists__for_each_format(hists, fmt) {
 		if (perf_hpp__should_skip(fmt, hists))
 			continue;
 
@@ -367,7 +367,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 
 		col_idx = 0;
 
-		perf_hpp__for_each_format(fmt) {
+		hists__for_each_format(hists, fmt) {
 			if (perf_hpp__should_skip(fmt, h->hists))
 				continue;
 
@@ -396,6 +396,194 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 	gtk_container_add(GTK_CONTAINER(window), view);
 }
 
+static void perf_gtk__add_hierarchy_entries(struct hists *hists,
+					    struct rb_root *root,
+					    GtkTreeStore *store,
+					    GtkTreeIter *parent,
+					    struct perf_hpp *hpp,
+					    float min_pcnt)
+{
+	int col_idx = 0;
+	struct rb_node *node;
+	struct hist_entry *he;
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+	u64 total = hists__total_period(hists);
+	int size;
+
+	for (node = rb_first(root); node; node = rb_next(node)) {
+		GtkTreeIter iter;
+		float percent;
+		char *bf;
+
+		he = rb_entry(node, struct hist_entry, rb_node);
+		if (he->filtered)
+			continue;
+
+		percent = hist_entry__get_percent_limit(he);
+		if (percent < min_pcnt)
+			continue;
+
+		gtk_tree_store_append(store, &iter, parent);
+
+		col_idx = 0;
+
+		/* the first hpp_list_node is for overhead columns */
+		fmt_node = list_first_entry(&hists->hpp_formats,
+					    struct perf_hpp_list_node, list);
+		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+			if (fmt->color)
+				fmt->color(fmt, hpp, he);
+			else
+				fmt->entry(fmt, hpp, he);
+
+			gtk_tree_store_set(store, &iter, col_idx++, hpp->buf, -1);
+		}
+
+		bf = hpp->buf;
+		size = hpp->size;
+		perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+			int ret;
+
+			if (fmt->color)
+				ret = fmt->color(fmt, hpp, he);
+			else
+				ret = fmt->entry(fmt, hpp, he);
+
+			snprintf(hpp->buf + ret, hpp->size - ret, "  ");
+			advance_hpp(hpp, ret + 2);
+		}
+
+		gtk_tree_store_set(store, &iter, col_idx, ltrim(rtrim(bf)), -1);
+
+		if (!he->leaf) {
+			hpp->buf = bf;
+			hpp->size = size;
+
+			perf_gtk__add_hierarchy_entries(hists, &he->hroot_out,
+							store, &iter, hpp,
+							min_pcnt);
+
+			if (!hist_entry__has_hierarchy_children(he, min_pcnt)) {
+				char buf[32];
+				GtkTreeIter child;
+
+				snprintf(buf, sizeof(buf), "no entry >= %.2f%%",
+					 min_pcnt);
+
+				gtk_tree_store_append(store, &child, &iter);
+				gtk_tree_store_set(store, &child, col_idx, buf, -1);
+			}
+		}
+
+		if (symbol_conf.use_callchain && he->leaf) {
+			if (callchain_param.mode == CHAIN_GRAPH_REL)
+				total = symbol_conf.cumulate_callchain ?
+					he->stat_acc->period : he->stat.period;
+
+			perf_gtk__add_callchain(&he->sorted_chain, store, &iter,
+						col_idx, total);
+		}
+	}
+
+}
+
+static void perf_gtk__show_hierarchy(GtkWidget *window, struct hists *hists,
+				     float min_pcnt)
+{
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+	GType col_types[MAX_COLUMNS];
+	GtkCellRenderer *renderer;
+	GtkTreeStore *store;
+	GtkWidget *view;
+	int col_idx;
+	int nr_cols = 0;
+	char s[512];
+	char buf[512];
+	bool first_node, first_col;
+	struct perf_hpp hpp = {
+		.buf		= s,
+		.size		= sizeof(s),
+	};
+
+	hists__for_each_format(hists, fmt) {
+		if (perf_hpp__is_sort_entry(fmt) ||
+		    perf_hpp__is_dynamic_entry(fmt))
+			break;
+
+		col_types[nr_cols++] = G_TYPE_STRING;
+	}
+	col_types[nr_cols++] = G_TYPE_STRING;
+
+	store = gtk_tree_store_newv(nr_cols, col_types);
+	view = gtk_tree_view_new();
+	renderer = gtk_cell_renderer_text_new();
+
+	col_idx = 0;
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
+							    -1, fmt->name,
+							    renderer, "markup",
+							    col_idx++, NULL);
+	}
+
+	/* construct merged column header since sort keys share single column */
+	buf[0] = '\0';
+	first_node = true;
+	list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
+		if (!first_node)
+			strcat(buf, " / ");
+		first_node = false;
+
+		first_col = true;
+		perf_hpp_list__for_each_format(&fmt_node->hpp ,fmt) {
+			if (perf_hpp__should_skip(fmt, hists))
+				continue;
+
+			if (!first_col)
+				strcat(buf, "+");
+			first_col = false;
+
+			fmt->header(fmt, &hpp, hists_to_evsel(hists));
+			strcat(buf, ltrim(rtrim(hpp.buf)));
+		}
+	}
+
+	gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
+						    -1, buf,
+						    renderer, "markup",
+						    col_idx++, NULL);
+
+	for (col_idx = 0; col_idx < nr_cols; col_idx++) {
+		GtkTreeViewColumn *column;
+
+		column = gtk_tree_view_get_column(GTK_TREE_VIEW(view), col_idx);
+		gtk_tree_view_column_set_resizable(column, TRUE);
+
+		if (col_idx == 0) {
+			gtk_tree_view_set_expander_column(GTK_TREE_VIEW(view),
+							  column);
+		}
+	}
+
+	gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store));
+	g_object_unref(GTK_TREE_MODEL(store));
+
+	perf_gtk__add_hierarchy_entries(hists, &hists->entries, store,
+					NULL, &hpp, min_pcnt);
+
+	gtk_tree_view_set_rules_hint(GTK_TREE_VIEW(view), TRUE);
+
+	g_signal_connect(view, "row-activated",
+			 G_CALLBACK(on_row_activated), NULL);
+	gtk_container_add(GTK_CONTAINER(window), view);
+}
+
 int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 				  const char *help,
 				  struct hist_browser_timer *hbt __maybe_unused,
@@ -463,7 +651,10 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 							GTK_POLICY_AUTOMATIC,
 							GTK_POLICY_AUTOMATIC);
 
-		perf_gtk__show_hists(scrolled_window, hists, min_pcnt);
+		if (symbol_conf.report_hierarchy)
+			perf_gtk__show_hierarchy(scrolled_window, hists, min_pcnt);
+		else
+			perf_gtk__show_hists(scrolled_window, hists, min_pcnt);
 
 		tab_label = gtk_label_new(evname);
 
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index bf2a66e25..3baeaa6e7 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -5,6 +5,7 @@
 #include "../util/util.h"
 #include "../util/sort.h"
 #include "../util/evsel.h"
+#include "../util/evlist.h"
 
 /* hist period print (hpp) functions */
 
@@ -371,7 +372,20 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 	return 0;
 }
 
-#define HPP__COLOR_PRINT_FNS(_name, _fn)		\
+static bool perf_hpp__is_hpp_entry(struct perf_hpp_fmt *a)
+{
+	return a->header == hpp__header_fn;
+}
+
+static bool hpp__equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+	if (!perf_hpp__is_hpp_entry(a) || !perf_hpp__is_hpp_entry(b))
+		return false;
+
+	return a->idx == b->idx;
+}
+
+#define HPP__COLOR_PRINT_FNS(_name, _fn, _idx)		\
 	{						\
 		.name   = _name,			\
 		.header	= hpp__header_fn,		\
@@ -381,9 +395,11 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 		.cmp	= hpp__nop_cmp,			\
 		.collapse = hpp__nop_cmp,		\
 		.sort	= hpp__sort_ ## _fn,		\
+		.idx	= PERF_HPP__ ## _idx,		\
+		.equal	= hpp__equal,			\
 	}
 
-#define HPP__COLOR_ACC_PRINT_FNS(_name, _fn)		\
+#define HPP__COLOR_ACC_PRINT_FNS(_name, _fn, _idx)	\
 	{						\
 		.name   = _name,			\
 		.header	= hpp__header_fn,		\
@@ -393,9 +409,11 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 		.cmp	= hpp__nop_cmp,			\
 		.collapse = hpp__nop_cmp,		\
 		.sort	= hpp__sort_ ## _fn,		\
+		.idx	= PERF_HPP__ ## _idx,		\
+		.equal	= hpp__equal,			\
 	}
 
-#define HPP__PRINT_FNS(_name, _fn)			\
+#define HPP__PRINT_FNS(_name, _fn, _idx)		\
 	{						\
 		.name   = _name,			\
 		.header	= hpp__header_fn,		\
@@ -404,22 +422,25 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 		.cmp	= hpp__nop_cmp,			\
 		.collapse = hpp__nop_cmp,		\
 		.sort	= hpp__sort_ ## _fn,		\
+		.idx	= PERF_HPP__ ## _idx,		\
+		.equal	= hpp__equal,			\
 	}
 
 struct perf_hpp_fmt perf_hpp__format[] = {
-	HPP__COLOR_PRINT_FNS("Overhead", overhead),
-	HPP__COLOR_PRINT_FNS("sys", overhead_sys),
-	HPP__COLOR_PRINT_FNS("usr", overhead_us),
-	HPP__COLOR_PRINT_FNS("guest sys", overhead_guest_sys),
-	HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us),
-	HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc),
-	HPP__PRINT_FNS("Samples", samples),
-	HPP__PRINT_FNS("Period", period)
+	HPP__COLOR_PRINT_FNS("Overhead", overhead, OVERHEAD),
+	HPP__COLOR_PRINT_FNS("sys", overhead_sys, OVERHEAD_SYS),
+	HPP__COLOR_PRINT_FNS("usr", overhead_us, OVERHEAD_US),
+	HPP__COLOR_PRINT_FNS("guest sys", overhead_guest_sys, OVERHEAD_GUEST_SYS),
+	HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us, OVERHEAD_GUEST_US),
+	HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc, OVERHEAD_ACC),
+	HPP__PRINT_FNS("Samples", samples, SAMPLES),
+	HPP__PRINT_FNS("Period", period, PERIOD)
 };
 
-LIST_HEAD(perf_hpp__list);
-LIST_HEAD(perf_hpp__sort_list);
-
+struct perf_hpp_list perf_hpp_list = {
+	.fields	= LIST_HEAD_INIT(perf_hpp_list.fields),
+	.sorts	= LIST_HEAD_INIT(perf_hpp_list.sorts),
+};
 
 #undef HPP__COLOR_PRINT_FNS
 #undef HPP__COLOR_ACC_PRINT_FNS
@@ -485,63 +506,60 @@ void perf_hpp__init(void)
 		hpp_dimension__add_output(PERF_HPP__PERIOD);
 }
 
-void perf_hpp__column_register(struct perf_hpp_fmt *format)
+void perf_hpp_list__column_register(struct perf_hpp_list *list,
+				    struct perf_hpp_fmt *format)
 {
-	list_add_tail(&format->list, &perf_hpp__list);
+	list_add_tail(&format->list, &list->fields);
 }
 
-void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
+void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
+					struct perf_hpp_fmt *format)
 {
-	list_del(&format->list);
+	list_add_tail(&format->sort_list, &list->sorts);
 }
 
-void perf_hpp__register_sort_field(struct perf_hpp_fmt *format)
-{
-	list_add_tail(&format->sort_list, &perf_hpp__sort_list);
-}
-
-void perf_hpp__column_enable(unsigned col)
-{
-	BUG_ON(col >= PERF_HPP__MAX_INDEX);
-	perf_hpp__column_register(&perf_hpp__format[col]);
-}
-
-void perf_hpp__column_disable(unsigned col)
+void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 {
-	BUG_ON(col >= PERF_HPP__MAX_INDEX);
-	perf_hpp__column_unregister(&perf_hpp__format[col]);
+	list_del(&format->list);
 }
 
 void perf_hpp__cancel_cumulate(void)
 {
+	struct perf_hpp_fmt *fmt, *acc, *ovh, *tmp;
+
 	if (is_strict_order(field_order))
 		return;
 
-	perf_hpp__column_disable(PERF_HPP__OVERHEAD_ACC);
-	perf_hpp__format[PERF_HPP__OVERHEAD].name = "Overhead";
+	ovh = &perf_hpp__format[PERF_HPP__OVERHEAD];
+	acc = &perf_hpp__format[PERF_HPP__OVERHEAD_ACC];
+
+	perf_hpp_list__for_each_format_safe(&perf_hpp_list, fmt, tmp) {
+		if (acc->equal(acc, fmt)) {
+			perf_hpp__column_unregister(fmt);
+			continue;
+		}
+
+		if (ovh->equal(ovh, fmt))
+			fmt->name = "Overhead";
+	}
 }
 
-void perf_hpp__setup_output_field(void)
+static bool fmt_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+	return a->equal && a->equal(a, b);
+}
+
+void perf_hpp__setup_output_field(struct perf_hpp_list *list)
 {
 	struct perf_hpp_fmt *fmt;
 
 	/* append sort keys to output field */
-	perf_hpp__for_each_sort_list(fmt) {
-		if (!list_empty(&fmt->list))
-			continue;
-
-		/*
-		 * sort entry fields are dynamically created,
-		 * so they can share a same sort key even though
-		 * the list is empty.
-		 */
-		if (perf_hpp__is_sort_entry(fmt)) {
-			struct perf_hpp_fmt *pos;
+	perf_hpp_list__for_each_sort_list(list, fmt) {
+		struct perf_hpp_fmt *pos;
 
-			perf_hpp__for_each_format(pos) {
-				if (perf_hpp__same_sort_entry(pos, fmt))
-					goto next;
-			}
+		perf_hpp_list__for_each_format(list, pos) {
+			if (fmt_equal(fmt, pos))
+				goto next;
 		}
 
 		perf_hpp__column_register(fmt);
@@ -550,27 +568,17 @@ next:
 	}
 }
 
-void perf_hpp__append_sort_keys(void)
+void perf_hpp__append_sort_keys(struct perf_hpp_list *list)
 {
 	struct perf_hpp_fmt *fmt;
 
 	/* append output fields to sort keys */
-	perf_hpp__for_each_format(fmt) {
-		if (!list_empty(&fmt->sort_list))
-			continue;
-
-		/*
-		 * sort entry fields are dynamically created,
-		 * so they can share a same sort key even though
-		 * the list is empty.
-		 */
-		if (perf_hpp__is_sort_entry(fmt)) {
-			struct perf_hpp_fmt *pos;
+	perf_hpp_list__for_each_format(list, fmt) {
+		struct perf_hpp_fmt *pos;
 
-			perf_hpp__for_each_sort_list(pos) {
-				if (perf_hpp__same_sort_entry(pos, fmt))
-					goto next;
-			}
+		perf_hpp_list__for_each_sort_list(list, pos) {
+			if (fmt_equal(fmt, pos))
+				goto next;
 		}
 
 		perf_hpp__register_sort_field(fmt);
@@ -579,20 +587,29 @@ next:
 	}
 }
 
-void perf_hpp__reset_output_field(void)
+
+static void fmt_free(struct perf_hpp_fmt *fmt)
+{
+	if (fmt->free)
+		fmt->free(fmt);
+}
+
+void perf_hpp__reset_output_field(struct perf_hpp_list *list)
 {
 	struct perf_hpp_fmt *fmt, *tmp;
 
 	/* reset output fields */
-	perf_hpp__for_each_format_safe(fmt, tmp) {
+	perf_hpp_list__for_each_format_safe(list, fmt, tmp) {
 		list_del_init(&fmt->list);
 		list_del_init(&fmt->sort_list);
+		fmt_free(fmt);
 	}
 
 	/* reset sort keys */
-	perf_hpp__for_each_sort_list_safe(fmt, tmp) {
+	perf_hpp_list__for_each_sort_list_safe(list, fmt, tmp) {
 		list_del_init(&fmt->list);
 		list_del_init(&fmt->sort_list);
+		fmt_free(fmt);
 	}
 }
 
@@ -606,7 +623,7 @@ unsigned int hists__sort_list_width(struct hists *hists)
 	bool first = true;
 	struct perf_hpp dummy_hpp;
 
-	perf_hpp__for_each_format(fmt) {
+	hists__for_each_format(hists, fmt) {
 		if (perf_hpp__should_skip(fmt, hists))
 			continue;
 
@@ -624,22 +641,39 @@ unsigned int hists__sort_list_width(struct hists *hists)
 	return ret;
 }
 
-void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
+unsigned int hists__overhead_width(struct hists *hists)
 {
-	int idx;
-
-	if (perf_hpp__is_sort_entry(fmt))
-		return perf_hpp__reset_sort_width(fmt, hists);
+	struct perf_hpp_fmt *fmt;
+	int ret = 0;
+	bool first = true;
+	struct perf_hpp dummy_hpp;
 
-	for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) {
-		if (fmt == &perf_hpp__format[idx])
+	hists__for_each_format(hists, fmt) {
+		if (perf_hpp__is_sort_entry(fmt) || perf_hpp__is_dynamic_entry(fmt))
 			break;
+
+		if (first)
+			first = false;
+		else
+			ret += 2;
+
+		ret += fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists));
 	}
 
-	if (idx == PERF_HPP__MAX_INDEX)
+	return ret;
+}
+
+void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
+{
+	if (perf_hpp__is_sort_entry(fmt))
+		return perf_hpp__reset_sort_width(fmt, hists);
+
+	if (perf_hpp__is_dynamic_entry(fmt))
 		return;
 
-	switch (idx) {
+	BUG_ON(fmt->idx >= PERF_HPP__MAX_INDEX);
+
+	switch (fmt->idx) {
 	case PERF_HPP__OVERHEAD:
 	case PERF_HPP__OVERHEAD_SYS:
 	case PERF_HPP__OVERHEAD_US:
@@ -667,7 +701,7 @@ void perf_hpp__set_user_width(const char *width_list_str)
 	struct perf_hpp_fmt *fmt;
 	const char *ptr = width_list_str;
 
-	perf_hpp__for_each_format(fmt) {
+	perf_hpp_list__for_each_format(&perf_hpp_list, fmt) {
 		char *p;
 
 		int len = strtol(ptr, &p, 10);
@@ -679,3 +713,71 @@ void perf_hpp__set_user_width(const char *width_list_str)
 			break;
 	}
 }
+
+static int add_hierarchy_fmt(struct hists *hists, struct perf_hpp_fmt *fmt)
+{
+	struct perf_hpp_list_node *node = NULL;
+	struct perf_hpp_fmt *fmt_copy;
+	bool found = false;
+	bool skip = perf_hpp__should_skip(fmt, hists);
+
+	list_for_each_entry(node, &hists->hpp_formats, list) {
+		if (node->level == fmt->level) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		node = malloc(sizeof(*node));
+		if (node == NULL)
+			return -1;
+
+		node->skip = skip;
+		node->level = fmt->level;
+		perf_hpp_list__init(&node->hpp);
+
+		hists->nr_hpp_node++;
+		list_add_tail(&node->list, &hists->hpp_formats);
+	}
+
+	fmt_copy = perf_hpp_fmt__dup(fmt);
+	if (fmt_copy == NULL)
+		return -1;
+
+	if (!skip)
+		node->skip = false;
+
+	list_add_tail(&fmt_copy->list, &node->hpp.fields);
+	list_add_tail(&fmt_copy->sort_list, &node->hpp.sorts);
+
+	return 0;
+}
+
+int perf_hpp__setup_hists_formats(struct perf_hpp_list *list,
+				  struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	struct perf_hpp_fmt *fmt;
+	struct hists *hists;
+	int ret;
+
+	if (!symbol_conf.report_hierarchy)
+		return 0;
+
+	evlist__for_each(evlist, evsel) {
+		hists = evsel__hists(evsel);
+
+		perf_hpp_list__for_each_sort_list(list, fmt) {
+			if (perf_hpp__is_dynamic_entry(fmt) &&
+			    !perf_hpp__defined_dynamic_entry(fmt, hists))
+				continue;
+
+			ret = add_hierarchy_fmt(hists, fmt);
+			if (ret < 0)
+				return ret;
+		}
+	}
+
+	return 0;
+}
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 387110d50..7aff5acf3 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -165,8 +165,28 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 	return ret;
 }
 
+/*
+ * If have one single callchain root, don't bother printing
+ * its percentage (100 % in fractal mode and the same percentage
+ * than the hist in graph mode). This also avoid one level of column.
+ *
+ * However when percent-limit applied, it's possible that single callchain
+ * node have different (non-100% in fractal mode) percentage.
+ */
+static bool need_percent_display(struct rb_node *node, u64 parent_samples)
+{
+	struct callchain_node *cnode;
+
+	if (rb_next(node))
+		return true;
+
+	cnode = rb_entry(node, struct callchain_node, rb_node);
+	return callchain_cumul_hits(cnode) != parent_samples;
+}
+
 static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
-				       u64 total_samples, int left_margin)
+				       u64 total_samples, u64 parent_samples,
+				       int left_margin)
 {
 	struct callchain_node *cnode;
 	struct callchain_list *chain;
@@ -177,13 +197,8 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 	int ret = 0;
 	char bf[1024];
 
-	/*
-	 * If have one single callchain root, don't bother printing
-	 * its percentage (100 % in fractal mode and the same percentage
-	 * than the hist in graph mode). This also avoid one level of column.
-	 */
 	node = rb_first(root);
-	if (node && !rb_next(node)) {
+	if (node && !need_percent_display(node, parent_samples)) {
 		cnode = rb_entry(node, struct callchain_node, rb_node);
 		list_for_each_entry(chain, &cnode->val, list) {
 			/*
@@ -213,9 +228,15 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 		root = &cnode->rb_root;
 	}
 
+	if (callchain_param.mode == CHAIN_GRAPH_REL)
+		total_samples = parent_samples;
+
 	ret += __callchain__fprintf_graph(fp, root, total_samples,
 					  1, 1, left_margin);
-	ret += fprintf(fp, "\n");
+	if (ret) {
+		/* do not add a blank line if it printed nothing */
+		ret += fprintf(fp, "\n");
+	}
 
 	return ret;
 }
@@ -323,16 +344,19 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
 					    u64 total_samples, int left_margin,
 					    FILE *fp)
 {
+	u64 parent_samples = he->stat.period;
+
+	if (symbol_conf.cumulate_callchain)
+		parent_samples = he->stat_acc->period;
+
 	switch (callchain_param.mode) {
 	case CHAIN_GRAPH_REL:
-		return callchain__fprintf_graph(fp, &he->sorted_chain,
-						symbol_conf.cumulate_callchain ?
-						he->stat_acc->period : he->stat.period,
-						left_margin);
+		return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples,
+						parent_samples, left_margin);
 		break;
 	case CHAIN_GRAPH_ABS:
 		return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples,
-						left_margin);
+						parent_samples, left_margin);
 		break;
 	case CHAIN_FLAT:
 		return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples);
@@ -349,45 +373,66 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
 	return 0;
 }
 
-static size_t hist_entry__callchain_fprintf(struct hist_entry *he,
-					    struct hists *hists,
-					    FILE *fp)
+static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
 {
-	int left_margin = 0;
-	u64 total_period = hists->stats.total_period;
+	const char *sep = symbol_conf.field_sep;
+	struct perf_hpp_fmt *fmt;
+	char *start = hpp->buf;
+	int ret;
+	bool first = true;
 
-	if (field_order == NULL && (sort_order == NULL ||
-				    !prefixcmp(sort_order, "comm"))) {
-		struct perf_hpp_fmt *fmt;
+	if (symbol_conf.exclude_other && !he->parent)
+		return 0;
 
-		perf_hpp__for_each_format(fmt) {
-			if (!perf_hpp__is_sort_entry(fmt))
-				continue;
+	hists__for_each_format(he->hists, fmt) {
+		if (perf_hpp__should_skip(fmt, he->hists))
+			continue;
 
-			/* must be 'comm' sort entry */
-			left_margin = fmt->width(fmt, NULL, hists_to_evsel(hists));
-			left_margin -= thread__comm_len(he->thread);
-			break;
-		}
+		/*
+		 * If there's no field_sep, we still need
+		 * to display initial '  '.
+		 */
+		if (!sep || !first) {
+			ret = scnprintf(hpp->buf, hpp->size, "%s", sep ?: "  ");
+			advance_hpp(hpp, ret);
+		} else
+			first = false;
+
+		if (perf_hpp__use_color() && fmt->color)
+			ret = fmt->color(fmt, hpp, he);
+		else
+			ret = fmt->entry(fmt, hpp, he);
+
+		ret = hist_entry__snprintf_alignment(he, hpp, fmt, ret);
+		advance_hpp(hpp, ret);
 	}
-	return hist_entry_callchain__fprintf(he, total_period, left_margin, fp);
+
+	return hpp->buf - start;
 }
 
-static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
+static int hist_entry__hierarchy_fprintf(struct hist_entry *he,
+					 struct perf_hpp *hpp,
+					 struct hists *hists,
+					 FILE *fp)
 {
 	const char *sep = symbol_conf.field_sep;
 	struct perf_hpp_fmt *fmt;
-	char *start = hpp->buf;
-	int ret;
+	struct perf_hpp_list_node *fmt_node;
+	char *buf = hpp->buf;
+	size_t size = hpp->size;
+	int ret, printed = 0;
 	bool first = true;
 
 	if (symbol_conf.exclude_other && !he->parent)
 		return 0;
 
-	perf_hpp__for_each_format(fmt) {
-		if (perf_hpp__should_skip(fmt, he->hists))
-			continue;
+	ret = scnprintf(hpp->buf, hpp->size, "%*s", he->depth * HIERARCHY_INDENT, "");
+	advance_hpp(hpp, ret);
 
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
 		/*
 		 * If there's no field_sep, we still need
 		 * to display initial '  '.
@@ -403,10 +448,47 @@ static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
 		else
 			ret = fmt->entry(fmt, hpp, he);
 
+		ret = hist_entry__snprintf_alignment(he, hpp, fmt, ret);
 		advance_hpp(hpp, ret);
 	}
 
-	return hpp->buf - start;
+	if (!sep)
+		ret = scnprintf(hpp->buf, hpp->size, "%*s",
+				(hists->nr_hpp_node - 2) * HIERARCHY_INDENT, "");
+	advance_hpp(hpp, ret);
+
+	printed += fprintf(fp, "%s", buf);
+
+	perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+		hpp->buf  = buf;
+		hpp->size = size;
+
+		/*
+		 * No need to call hist_entry__snprintf_alignment() since this
+		 * fmt is always the last column in the hierarchy mode.
+		 */
+		if (perf_hpp__use_color() && fmt->color)
+			fmt->color(fmt, hpp, he);
+		else
+			fmt->entry(fmt, hpp, he);
+
+		/*
+		 * dynamic entries are right-aligned but we want left-aligned
+		 * in the hierarchy mode
+		 */
+		printed += fprintf(fp, "%s%s", sep ?: "  ", ltrim(buf));
+	}
+	printed += putc('\n', fp);
+
+	if (symbol_conf.use_callchain && he->leaf) {
+		u64 total = hists__total_period(hists);
+
+		printed += hist_entry_callchain__fprintf(he, total, 0, fp);
+		goto out;
+	}
+
+out:
+	return printed;
 }
 
 static int hist_entry__fprintf(struct hist_entry *he, size_t size,
@@ -418,24 +500,134 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 		.buf		= bf,
 		.size		= size,
 	};
+	u64 total_period = hists->stats.total_period;
 
 	if (size == 0 || size > bfsz)
 		size = hpp.size = bfsz;
 
+	if (symbol_conf.report_hierarchy)
+		return hist_entry__hierarchy_fprintf(he, &hpp, hists, fp);
+
 	hist_entry__snprintf(he, &hpp);
 
 	ret = fprintf(fp, "%s\n", bf);
 
 	if (symbol_conf.use_callchain)
-		ret += hist_entry__callchain_fprintf(he, hists, fp);
+		ret += hist_entry_callchain__fprintf(he, total_period, 0, fp);
 
 	return ret;
 }
 
+static int print_hierarchy_indent(const char *sep, int indent,
+				  const char *line, FILE *fp)
+{
+	if (sep != NULL || indent < 2)
+		return 0;
+
+	return fprintf(fp, "%-.*s", (indent - 2) * HIERARCHY_INDENT, line);
+}
+
+static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
+				  const char *sep, FILE *fp)
+{
+	bool first_node, first_col;
+	int indent;
+	int depth;
+	unsigned width = 0;
+	unsigned header_width = 0;
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+
+	indent = hists->nr_hpp_node;
+
+	/* preserve max indent depth for column headers */
+	print_hierarchy_indent(sep, indent, spaces, fp);
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		fmt->header(fmt, hpp, hists_to_evsel(hists));
+		fprintf(fp, "%s%s", hpp->buf, sep ?: "  ");
+	}
+
+	/* combine sort headers with ' / ' */
+	first_node = true;
+	list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
+		if (!first_node)
+			header_width += fprintf(fp, " / ");
+		first_node = false;
+
+		first_col = true;
+		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+			if (perf_hpp__should_skip(fmt, hists))
+				continue;
+
+			if (!first_col)
+				header_width += fprintf(fp, "+");
+			first_col = false;
+
+			fmt->header(fmt, hpp, hists_to_evsel(hists));
+			rtrim(hpp->buf);
+
+			header_width += fprintf(fp, "%s", ltrim(hpp->buf));
+		}
+	}
+
+	fprintf(fp, "\n# ");
+
+	/* preserve max indent depth for initial dots */
+	print_hierarchy_indent(sep, indent, dots, fp);
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+
+	first_col = true;
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		if (!first_col)
+			fprintf(fp, "%s", sep ?: "..");
+		first_col = false;
+
+		width = fmt->width(fmt, hpp, hists_to_evsel(hists));
+		fprintf(fp, "%.*s", width, dots);
+	}
+
+	depth = 0;
+	list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
+		first_col = true;
+		width = depth * HIERARCHY_INDENT;
+
+		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+			if (perf_hpp__should_skip(fmt, hists))
+				continue;
+
+			if (!first_col)
+				width++;  /* for '+' sign between column header */
+			first_col = false;
+
+			width += fmt->width(fmt, hpp, hists_to_evsel(hists));
+		}
+
+		if (width > header_width)
+			header_width = width;
+
+		depth++;
+	}
+
+	fprintf(fp, "%s%-.*s", sep ?: "  ", header_width, dots);
+
+	fprintf(fp, "\n#\n");
+
+	return 2;
+}
+
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp)
 {
 	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
 	struct rb_node *nd;
 	size_t ret = 0;
 	unsigned int width;
@@ -449,10 +641,11 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 	bool first = true;
 	size_t linesz;
 	char *line = NULL;
+	unsigned indent;
 
 	init_rem_hits();
 
-	perf_hpp__for_each_format(fmt)
+	hists__for_each_format(hists, fmt)
 		perf_hpp__reset_width(fmt, hists);
 
 	if (symbol_conf.col_width_list_str)
@@ -463,7 +656,16 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 
 	fprintf(fp, "# ");
 
-	perf_hpp__for_each_format(fmt) {
+	if (symbol_conf.report_hierarchy) {
+		list_for_each_entry(fmt_node, &hists->hpp_formats, list) {
+			perf_hpp_list__for_each_format(&fmt_node->hpp, fmt)
+				perf_hpp__reset_width(fmt, hists);
+		}
+		nr_rows += print_hierarchy_header(hists, &dummy_hpp, sep, fp);
+		goto print_entries;
+	}
+
+	hists__for_each_format(hists, fmt) {
 		if (perf_hpp__should_skip(fmt, hists))
 			continue;
 
@@ -487,7 +689,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 
 	fprintf(fp, "# ");
 
-	perf_hpp__for_each_format(fmt) {
+	hists__for_each_format(hists, fmt) {
 		unsigned int i;
 
 		if (perf_hpp__should_skip(fmt, hists))
@@ -520,7 +722,9 @@ print_entries:
 		goto out;
 	}
 
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+	indent = hists__overhead_width(hists) + 4;
+
+	for (nd = rb_first(&hists->entries); nd; nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 		float percent;
 
@@ -536,6 +740,20 @@ print_entries:
 		if (max_rows && ++nr_rows >= max_rows)
 			break;
 
+		/*
+		 * If all children are filtered out or percent-limited,
+		 * display "no entry >= x.xx%" message.
+		 */
+		if (!h->leaf && !hist_entry__has_hierarchy_children(h, min_pcnt)) {
+			int depth = hists->nr_hpp_node + h->depth + 1;
+
+			print_hierarchy_indent(sep, depth, spaces, fp);
+			fprintf(fp, "%*sno entry >= %.2f%%\n", indent, "", min_pcnt);
+
+			if (max_rows && ++nr_rows >= max_rows)
+				break;
+		}
+
 		if (h->ms.map == NULL && verbose > 1) {
 			__map_groups__fprintf_maps(h->thread->mg,
 						   MAP__FUNCTION, fp);
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 5eec53a3f..da48fd843 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -1,4 +1,3 @@
-libperf-y += abspath.o
 libperf-y += alias.o
 libperf-y += annotate.o
 libperf-y += build-id.o
@@ -82,6 +81,7 @@ libperf-y += parse-branch-options.o
 libperf-y += parse-regs-options.o
 libperf-y += term.o
 libperf-y += help-unknown-cmd.o
+libperf-y += mem-events.o
 
 libperf-$(CONFIG_LIBBPF) += bpf-loader.o
 libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
@@ -105,8 +105,17 @@ libperf-y += scripting-engines/
 
 libperf-$(CONFIG_ZLIB) += zlib.o
 libperf-$(CONFIG_LZMA) += lzma.o
+libperf-y += demangle-java.o
+
+ifdef CONFIG_JITDUMP
+libperf-$(CONFIG_LIBELF) += jitdump.o
+libperf-$(CONFIG_LIBELF) += genelf.o
+libperf-$(CONFIG_LIBELF) += genelf_debug.o
+endif
 
 CFLAGS_config.o   += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
+# avoid compiler warnings in 32-bit mode
+CFLAGS_genelf_debug.o  += -Wno-packed
 
 $(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
 	$(call rule_mkdir)
diff --git a/tools/perf/util/abspath.c b/tools/perf/util/abspath.c
deleted file mode 100644
index 0e76affe9..000000000
--- a/tools/perf/util/abspath.c
+++ /dev/null
@@ -1,37 +0,0 @@
-#include "cache.h"
-
-static const char *get_pwd_cwd(void)
-{
-	static char cwd[PATH_MAX + 1];
-	char *pwd;
-	struct stat cwd_stat, pwd_stat;
-	if (getcwd(cwd, PATH_MAX) == NULL)
-		return NULL;
-	pwd = getenv("PWD");
-	if (pwd && strcmp(pwd, cwd)) {
-		stat(cwd, &cwd_stat);
-		if (!stat(pwd, &pwd_stat) &&
-		    pwd_stat.st_dev == cwd_stat.st_dev &&
-		    pwd_stat.st_ino == cwd_stat.st_ino) {
-			strlcpy(cwd, pwd, PATH_MAX);
-		}
-	}
-	return cwd;
-}
-
-const char *make_nonrelative_path(const char *path)
-{
-	static char buf[PATH_MAX + 1];
-
-	if (is_absolute_path(path)) {
-		if (strlcpy(buf, path, PATH_MAX) >= PATH_MAX)
-			die("Too long path: %.*s", 60, path);
-	} else {
-		const char *cwd = get_pwd_cwd();
-		if (!cwd)
-			die("Cannot determine the current working directory");
-		if (snprintf(buf, PATH_MAX, "%s/%s", cwd, path) >= PATH_MAX)
-			die("Too long path: %.*s", 60, path);
-	}
-	return buf;
-}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index cea323d9e..9241f8c2b 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -158,7 +158,7 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize);
 
 int hist_entry__annotate(struct hist_entry *he, size_t privsize);
 
-int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym);
+int symbol__annotate_init(struct map *map, struct symbol *sym);
 int symbol__annotate_printf(struct symbol *sym, struct map *map,
 			    struct perf_evsel *evsel, bool full_paths,
 			    int min_pcnt, int max_lines, int context);
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 360fda01f..ec164fe70 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -478,10 +478,11 @@ void auxtrace_heap__pop(struct auxtrace_heap *heap)
 			 heap_array[last].ordinal);
 }
 
-size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr)
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr,
+				       struct perf_evlist *evlist)
 {
 	if (itr)
-		return itr->info_priv_size(itr);
+		return itr->info_priv_size(itr, evlist);
 	return 0;
 }
 
@@ -852,7 +853,7 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
 	int err;
 
 	pr_debug2("Synthesizing auxtrace information\n");
-	priv_size = auxtrace_record__info_priv_size(itr);
+	priv_size = auxtrace_record__info_priv_size(itr, session->evlist);
 	ev = zalloc(sizeof(struct auxtrace_info_event) + priv_size);
 	if (!ev)
 		return -ENOMEM;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index b86f90db1..57ff31ecb 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -293,7 +293,8 @@ struct auxtrace_record {
 	int (*recording_options)(struct auxtrace_record *itr,
 				 struct perf_evlist *evlist,
 				 struct record_opts *opts);
-	size_t (*info_priv_size)(struct auxtrace_record *itr);
+	size_t (*info_priv_size)(struct auxtrace_record *itr,
+				 struct perf_evlist *evlist);
 	int (*info_fill)(struct auxtrace_record *itr,
 			 struct perf_session *session,
 			 struct auxtrace_info_event *auxtrace_info,
@@ -429,7 +430,8 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
 int auxtrace_record__options(struct auxtrace_record *itr,
 			     struct perf_evlist *evlist,
 			     struct record_opts *opts);
-size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr);
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr,
+				       struct perf_evlist *evlist);
 int auxtrace_record__info_fill(struct auxtrace_record *itr,
 			       struct perf_session *session,
 			       struct auxtrace_info_event *auxtrace_info,
@@ -515,7 +517,7 @@ static inline void auxtrace__free(struct perf_session *session)
 
 static inline struct auxtrace_record *
 auxtrace_record__init(struct perf_evlist *evlist __maybe_unused,
-		      int *err __maybe_unused)
+		      int *err)
 {
 	*err = 0;
 	return NULL;
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 540a7efa6..0967ce601 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -7,6 +7,7 @@
 
 #include <linux/bpf.h>
 #include <bpf/libbpf.h>
+#include <bpf/bpf.h>
 #include <linux/err.h>
 #include <linux/string.h>
 #include "perf.h"
@@ -16,6 +17,7 @@
 #include "llvm-utils.h"
 #include "probe-event.h"
 #include "probe-finder.h" // for MAX_PROBES
+#include "parse-events.h"
 #include "llvm-utils.h"
 
 #define DEFINE_PRINT_FN(name, level) \
@@ -108,8 +110,8 @@ void bpf__clear(void)
 }
 
 static void
-bpf_prog_priv__clear(struct bpf_program *prog __maybe_unused,
-		     void *_priv)
+clear_prog_priv(struct bpf_program *prog __maybe_unused,
+		void *_priv)
 {
 	struct bpf_prog_priv *priv = _priv;
 
@@ -337,7 +339,7 @@ config_bpf_program(struct bpf_program *prog)
 	}
 	pr_debug("bpf: config '%s' is ok\n", config_str);
 
-	err = bpf_program__set_private(prog, priv, bpf_prog_priv__clear);
+	err = bpf_program__set_private(prog, priv, clear_prog_priv);
 	if (err) {
 		pr_debug("Failed to set priv for program '%s'\n", config_str);
 		goto errout;
@@ -739,6 +741,682 @@ int bpf__foreach_tev(struct bpf_object *obj,
 	return 0;
 }
 
+enum bpf_map_op_type {
+	BPF_MAP_OP_SET_VALUE,
+	BPF_MAP_OP_SET_EVSEL,
+};
+
+enum bpf_map_key_type {
+	BPF_MAP_KEY_ALL,
+	BPF_MAP_KEY_RANGES,
+};
+
+struct bpf_map_op {
+	struct list_head list;
+	enum bpf_map_op_type op_type;
+	enum bpf_map_key_type key_type;
+	union {
+		struct parse_events_array array;
+	} k;
+	union {
+		u64 value;
+		struct perf_evsel *evsel;
+	} v;
+};
+
+struct bpf_map_priv {
+	struct list_head ops_list;
+};
+
+static void
+bpf_map_op__delete(struct bpf_map_op *op)
+{
+	if (!list_empty(&op->list))
+		list_del(&op->list);
+	if (op->key_type == BPF_MAP_KEY_RANGES)
+		parse_events__clear_array(&op->k.array);
+	free(op);
+}
+
+static void
+bpf_map_priv__purge(struct bpf_map_priv *priv)
+{
+	struct bpf_map_op *pos, *n;
+
+	list_for_each_entry_safe(pos, n, &priv->ops_list, list) {
+		list_del_init(&pos->list);
+		bpf_map_op__delete(pos);
+	}
+}
+
+static void
+bpf_map_priv__clear(struct bpf_map *map __maybe_unused,
+		    void *_priv)
+{
+	struct bpf_map_priv *priv = _priv;
+
+	bpf_map_priv__purge(priv);
+	free(priv);
+}
+
+static int
+bpf_map_op_setkey(struct bpf_map_op *op, struct parse_events_term *term)
+{
+	op->key_type = BPF_MAP_KEY_ALL;
+	if (!term)
+		return 0;
+
+	if (term->array.nr_ranges) {
+		size_t memsz = term->array.nr_ranges *
+				sizeof(op->k.array.ranges[0]);
+
+		op->k.array.ranges = memdup(term->array.ranges, memsz);
+		if (!op->k.array.ranges) {
+			pr_debug("No enough memory to alloc indices for map\n");
+			return -ENOMEM;
+		}
+		op->key_type = BPF_MAP_KEY_RANGES;
+		op->k.array.nr_ranges = term->array.nr_ranges;
+	}
+	return 0;
+}
+
+static struct bpf_map_op *
+bpf_map_op__new(struct parse_events_term *term)
+{
+	struct bpf_map_op *op;
+	int err;
+
+	op = zalloc(sizeof(*op));
+	if (!op) {
+		pr_debug("Failed to alloc bpf_map_op\n");
+		return ERR_PTR(-ENOMEM);
+	}
+	INIT_LIST_HEAD(&op->list);
+
+	err = bpf_map_op_setkey(op, term);
+	if (err) {
+		free(op);
+		return ERR_PTR(err);
+	}
+	return op;
+}
+
+static int
+bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op)
+{
+	struct bpf_map_priv *priv;
+	const char *map_name;
+	int err;
+
+	map_name = bpf_map__get_name(map);
+	err = bpf_map__get_private(map, (void **)&priv);
+	if (err) {
+		pr_debug("Failed to get private from map %s\n", map_name);
+		return err;
+	}
+
+	if (!priv) {
+		priv = zalloc(sizeof(*priv));
+		if (!priv) {
+			pr_debug("No enough memory to alloc map private\n");
+			return -ENOMEM;
+		}
+		INIT_LIST_HEAD(&priv->ops_list);
+
+		if (bpf_map__set_private(map, priv, bpf_map_priv__clear)) {
+			free(priv);
+			return -BPF_LOADER_ERRNO__INTERNAL;
+		}
+	}
+
+	list_add_tail(&op->list, &priv->ops_list);
+	return 0;
+}
+
+static struct bpf_map_op *
+bpf_map__add_newop(struct bpf_map *map, struct parse_events_term *term)
+{
+	struct bpf_map_op *op;
+	int err;
+
+	op = bpf_map_op__new(term);
+	if (IS_ERR(op))
+		return op;
+
+	err = bpf_map__add_op(map, op);
+	if (err) {
+		bpf_map_op__delete(op);
+		return ERR_PTR(err);
+	}
+	return op;
+}
+
+static int
+__bpf_map__config_value(struct bpf_map *map,
+			struct parse_events_term *term)
+{
+	struct bpf_map_def def;
+	struct bpf_map_op *op;
+	const char *map_name;
+	int err;
+
+	map_name = bpf_map__get_name(map);
+
+	err = bpf_map__get_def(map, &def);
+	if (err) {
+		pr_debug("Unable to get map definition from '%s'\n",
+			 map_name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	if (def.type != BPF_MAP_TYPE_ARRAY) {
+		pr_debug("Map %s type is not BPF_MAP_TYPE_ARRAY\n",
+			 map_name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
+	}
+	if (def.key_size < sizeof(unsigned int)) {
+		pr_debug("Map %s has incorrect key size\n", map_name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE;
+	}
+	switch (def.value_size) {
+	case 1:
+	case 2:
+	case 4:
+	case 8:
+		break;
+	default:
+		pr_debug("Map %s has incorrect value size\n", map_name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE;
+	}
+
+	op = bpf_map__add_newop(map, term);
+	if (IS_ERR(op))
+		return PTR_ERR(op);
+	op->op_type = BPF_MAP_OP_SET_VALUE;
+	op->v.value = term->val.num;
+	return 0;
+}
+
+static int
+bpf_map__config_value(struct bpf_map *map,
+		      struct parse_events_term *term,
+		      struct perf_evlist *evlist __maybe_unused)
+{
+	if (!term->err_val) {
+		pr_debug("Config value not set\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_CONF;
+	}
+
+	if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM) {
+		pr_debug("ERROR: wrong value type for 'value'\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE;
+	}
+
+	return __bpf_map__config_value(map, term);
+}
+
+static int
+__bpf_map__config_event(struct bpf_map *map,
+			struct parse_events_term *term,
+			struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	struct bpf_map_def def;
+	struct bpf_map_op *op;
+	const char *map_name;
+	int err;
+
+	map_name = bpf_map__get_name(map);
+	evsel = perf_evlist__find_evsel_by_str(evlist, term->val.str);
+	if (!evsel) {
+		pr_debug("Event (for '%s') '%s' doesn't exist\n",
+			 map_name, term->val.str);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT;
+	}
+
+	err = bpf_map__get_def(map, &def);
+	if (err) {
+		pr_debug("Unable to get map definition from '%s'\n",
+			 map_name);
+		return err;
+	}
+
+	/*
+	 * No need to check key_size and value_size:
+	 * kernel has already checked them.
+	 */
+	if (def.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
+		pr_debug("Map %s type is not BPF_MAP_TYPE_PERF_EVENT_ARRAY\n",
+			 map_name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
+	}
+
+	op = bpf_map__add_newop(map, term);
+	if (IS_ERR(op))
+		return PTR_ERR(op);
+	op->op_type = BPF_MAP_OP_SET_EVSEL;
+	op->v.evsel = evsel;
+	return 0;
+}
+
+static int
+bpf_map__config_event(struct bpf_map *map,
+		      struct parse_events_term *term,
+		      struct perf_evlist *evlist)
+{
+	if (!term->err_val) {
+		pr_debug("Config value not set\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_CONF;
+	}
+
+	if (term->type_val != PARSE_EVENTS__TERM_TYPE_STR) {
+		pr_debug("ERROR: wrong value type for 'event'\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE;
+	}
+
+	return __bpf_map__config_event(map, term, evlist);
+}
+
+struct bpf_obj_config__map_func {
+	const char *config_opt;
+	int (*config_func)(struct bpf_map *, struct parse_events_term *,
+			   struct perf_evlist *);
+};
+
+struct bpf_obj_config__map_func bpf_obj_config__map_funcs[] = {
+	{"value", bpf_map__config_value},
+	{"event", bpf_map__config_event},
+};
+
+static int
+config_map_indices_range_check(struct parse_events_term *term,
+			       struct bpf_map *map,
+			       const char *map_name)
+{
+	struct parse_events_array *array = &term->array;
+	struct bpf_map_def def;
+	unsigned int i;
+	int err;
+
+	if (!array->nr_ranges)
+		return 0;
+	if (!array->ranges) {
+		pr_debug("ERROR: map %s: array->nr_ranges is %d but range array is NULL\n",
+			 map_name, (int)array->nr_ranges);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	err = bpf_map__get_def(map, &def);
+	if (err) {
+		pr_debug("ERROR: Unable to get map definition from '%s'\n",
+			 map_name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	for (i = 0; i < array->nr_ranges; i++) {
+		unsigned int start = array->ranges[i].start;
+		size_t length = array->ranges[i].length;
+		unsigned int idx = start + length - 1;
+
+		if (idx >= def.max_entries) {
+			pr_debug("ERROR: index %d too large\n", idx);
+			return -BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG;
+		}
+	}
+	return 0;
+}
+
+static int
+bpf__obj_config_map(struct bpf_object *obj,
+		    struct parse_events_term *term,
+		    struct perf_evlist *evlist,
+		    int *key_scan_pos)
+{
+	/* key is "map:<mapname>.<config opt>" */
+	char *map_name = strdup(term->config + sizeof("map:") - 1);
+	struct bpf_map *map;
+	int err = -BPF_LOADER_ERRNO__OBJCONF_OPT;
+	char *map_opt;
+	size_t i;
+
+	if (!map_name)
+		return -ENOMEM;
+
+	map_opt = strchr(map_name, '.');
+	if (!map_opt) {
+		pr_debug("ERROR: Invalid map config: %s\n", map_name);
+		goto out;
+	}
+
+	*map_opt++ = '\0';
+	if (*map_opt == '\0') {
+		pr_debug("ERROR: Invalid map option: %s\n", term->config);
+		goto out;
+	}
+
+	map = bpf_object__get_map_by_name(obj, map_name);
+	if (!map) {
+		pr_debug("ERROR: Map %s doesn't exist\n", map_name);
+		err = -BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST;
+		goto out;
+	}
+
+	*key_scan_pos += strlen(map_opt);
+	err = config_map_indices_range_check(term, map, map_name);
+	if (err)
+		goto out;
+	*key_scan_pos -= strlen(map_opt);
+
+	for (i = 0; i < ARRAY_SIZE(bpf_obj_config__map_funcs); i++) {
+		struct bpf_obj_config__map_func *func =
+				&bpf_obj_config__map_funcs[i];
+
+		if (strcmp(map_opt, func->config_opt) == 0) {
+			err = func->config_func(map, term, evlist);
+			goto out;
+		}
+	}
+
+	pr_debug("ERROR: Invalid map config option '%s'\n", map_opt);
+	err = -BPF_LOADER_ERRNO__OBJCONF_MAP_OPT;
+out:
+	free(map_name);
+	if (!err)
+		key_scan_pos += strlen(map_opt);
+	return err;
+}
+
+int bpf__config_obj(struct bpf_object *obj,
+		    struct parse_events_term *term,
+		    struct perf_evlist *evlist,
+		    int *error_pos)
+{
+	int key_scan_pos = 0;
+	int err;
+
+	if (!obj || !term || !term->config)
+		return -EINVAL;
+
+	if (!prefixcmp(term->config, "map:")) {
+		key_scan_pos = sizeof("map:") - 1;
+		err = bpf__obj_config_map(obj, term, evlist, &key_scan_pos);
+		goto out;
+	}
+	err = -BPF_LOADER_ERRNO__OBJCONF_OPT;
+out:
+	if (error_pos)
+		*error_pos = key_scan_pos;
+	return err;
+
+}
+
+typedef int (*map_config_func_t)(const char *name, int map_fd,
+				 struct bpf_map_def *pdef,
+				 struct bpf_map_op *op,
+				 void *pkey, void *arg);
+
+static int
+foreach_key_array_all(map_config_func_t func,
+		      void *arg, const char *name,
+		      int map_fd, struct bpf_map_def *pdef,
+		      struct bpf_map_op *op)
+{
+	unsigned int i;
+	int err;
+
+	for (i = 0; i < pdef->max_entries; i++) {
+		err = func(name, map_fd, pdef, op, &i, arg);
+		if (err) {
+			pr_debug("ERROR: failed to insert value to %s[%u]\n",
+				 name, i);
+			return err;
+		}
+	}
+	return 0;
+}
+
+static int
+foreach_key_array_ranges(map_config_func_t func, void *arg,
+			 const char *name, int map_fd,
+			 struct bpf_map_def *pdef,
+			 struct bpf_map_op *op)
+{
+	unsigned int i, j;
+	int err;
+
+	for (i = 0; i < op->k.array.nr_ranges; i++) {
+		unsigned int start = op->k.array.ranges[i].start;
+		size_t length = op->k.array.ranges[i].length;
+
+		for (j = 0; j < length; j++) {
+			unsigned int idx = start + j;
+
+			err = func(name, map_fd, pdef, op, &idx, arg);
+			if (err) {
+				pr_debug("ERROR: failed to insert value to %s[%u]\n",
+					 name, idx);
+				return err;
+			}
+		}
+	}
+	return 0;
+}
+
+static int
+bpf_map_config_foreach_key(struct bpf_map *map,
+			   map_config_func_t func,
+			   void *arg)
+{
+	int err, map_fd;
+	const char *name;
+	struct bpf_map_op *op;
+	struct bpf_map_def def;
+	struct bpf_map_priv *priv;
+
+	name = bpf_map__get_name(map);
+
+	err = bpf_map__get_private(map, (void **)&priv);
+	if (err) {
+		pr_debug("ERROR: failed to get private from map %s\n", name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+	if (!priv || list_empty(&priv->ops_list)) {
+		pr_debug("INFO: nothing to config for map %s\n", name);
+		return 0;
+	}
+
+	err = bpf_map__get_def(map, &def);
+	if (err) {
+		pr_debug("ERROR: failed to get definition from map %s\n", name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+	map_fd = bpf_map__get_fd(map);
+	if (map_fd < 0) {
+		pr_debug("ERROR: failed to get fd from map %s\n", name);
+		return map_fd;
+	}
+
+	list_for_each_entry(op, &priv->ops_list, list) {
+		switch (def.type) {
+		case BPF_MAP_TYPE_ARRAY:
+		case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
+			switch (op->key_type) {
+			case BPF_MAP_KEY_ALL:
+				err = foreach_key_array_all(func, arg, name,
+							    map_fd, &def, op);
+				break;
+			case BPF_MAP_KEY_RANGES:
+				err = foreach_key_array_ranges(func, arg, name,
+							       map_fd, &def,
+							       op);
+				break;
+			default:
+				pr_debug("ERROR: keytype for map '%s' invalid\n",
+					 name);
+				return -BPF_LOADER_ERRNO__INTERNAL;
+			}
+			if (err)
+				return err;
+			break;
+		default:
+			pr_debug("ERROR: type of '%s' incorrect\n", name);
+			return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
+		}
+	}
+
+	return 0;
+}
+
+static int
+apply_config_value_for_key(int map_fd, void *pkey,
+			   size_t val_size, u64 val)
+{
+	int err = 0;
+
+	switch (val_size) {
+	case 1: {
+		u8 _val = (u8)(val);
+		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
+		break;
+	}
+	case 2: {
+		u16 _val = (u16)(val);
+		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
+		break;
+	}
+	case 4: {
+		u32 _val = (u32)(val);
+		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
+		break;
+	}
+	case 8: {
+		err = bpf_map_update_elem(map_fd, pkey, &val, BPF_ANY);
+		break;
+	}
+	default:
+		pr_debug("ERROR: invalid value size\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE;
+	}
+	if (err && errno)
+		err = -errno;
+	return err;
+}
+
+static int
+apply_config_evsel_for_key(const char *name, int map_fd, void *pkey,
+			   struct perf_evsel *evsel)
+{
+	struct xyarray *xy = evsel->fd;
+	struct perf_event_attr *attr;
+	unsigned int key, events;
+	bool check_pass = false;
+	int *evt_fd;
+	int err;
+
+	if (!xy) {
+		pr_debug("ERROR: evsel not ready for map %s\n", name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	if (xy->row_size / xy->entry_size != 1) {
+		pr_debug("ERROR: Dimension of target event is incorrect for map %s\n",
+			 name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM;
+	}
+
+	attr = &evsel->attr;
+	if (attr->inherit) {
+		pr_debug("ERROR: Can't put inherit event into map %s\n", name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH;
+	}
+
+	if (perf_evsel__is_bpf_output(evsel))
+		check_pass = true;
+	if (attr->type == PERF_TYPE_RAW)
+		check_pass = true;
+	if (attr->type == PERF_TYPE_HARDWARE)
+		check_pass = true;
+	if (!check_pass) {
+		pr_debug("ERROR: Event type is wrong for map %s\n", name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE;
+	}
+
+	events = xy->entries / (xy->row_size / xy->entry_size);
+	key = *((unsigned int *)pkey);
+	if (key >= events) {
+		pr_debug("ERROR: there is no event %d for map %s\n",
+			 key, name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_MAPSIZE;
+	}
+	evt_fd = xyarray__entry(xy, key, 0);
+	err = bpf_map_update_elem(map_fd, pkey, evt_fd, BPF_ANY);
+	if (err && errno)
+		err = -errno;
+	return err;
+}
+
+static int
+apply_obj_config_map_for_key(const char *name, int map_fd,
+			     struct bpf_map_def *pdef __maybe_unused,
+			     struct bpf_map_op *op,
+			     void *pkey, void *arg __maybe_unused)
+{
+	int err;
+
+	switch (op->op_type) {
+	case BPF_MAP_OP_SET_VALUE:
+		err = apply_config_value_for_key(map_fd, pkey,
+						 pdef->value_size,
+						 op->v.value);
+		break;
+	case BPF_MAP_OP_SET_EVSEL:
+		err = apply_config_evsel_for_key(name, map_fd, pkey,
+						 op->v.evsel);
+		break;
+	default:
+		pr_debug("ERROR: unknown value type for '%s'\n", name);
+		err = -BPF_LOADER_ERRNO__INTERNAL;
+	}
+	return err;
+}
+
+static int
+apply_obj_config_map(struct bpf_map *map)
+{
+	return bpf_map_config_foreach_key(map,
+					  apply_obj_config_map_for_key,
+					  NULL);
+}
+
+static int
+apply_obj_config_object(struct bpf_object *obj)
+{
+	struct bpf_map *map;
+	int err;
+
+	bpf_map__for_each(map, obj) {
+		err = apply_obj_config_map(map);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+int bpf__apply_obj_config(void)
+{
+	struct bpf_object *obj, *tmp;
+	int err;
+
+	bpf_object__for_each_safe(obj, tmp) {
+		err = apply_obj_config_object(obj);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 #define ERRNO_OFFSET(e)		((e) - __BPF_LOADER_ERRNO__START)
 #define ERRCODE_OFFSET(c)	ERRNO_OFFSET(BPF_LOADER_ERRNO__##c)
 #define NR_ERRNO	(__BPF_LOADER_ERRNO__END - __BPF_LOADER_ERRNO__START)
@@ -753,6 +1431,20 @@ static const char *bpf_loader_strerror_table[NR_ERRNO] = {
 	[ERRCODE_OFFSET(PROLOGUE)]	= "Failed to generate prologue",
 	[ERRCODE_OFFSET(PROLOGUE2BIG)]	= "Prologue too big for program",
 	[ERRCODE_OFFSET(PROLOGUEOOB)]	= "Offset out of bound for prologue",
+	[ERRCODE_OFFSET(OBJCONF_OPT)]	= "Invalid object config option",
+	[ERRCODE_OFFSET(OBJCONF_CONF)]	= "Config value not set (missing '=')",
+	[ERRCODE_OFFSET(OBJCONF_MAP_OPT)]	= "Invalid object map config option",
+	[ERRCODE_OFFSET(OBJCONF_MAP_NOTEXIST)]	= "Target map doesn't exist",
+	[ERRCODE_OFFSET(OBJCONF_MAP_VALUE)]	= "Incorrect value type for map",
+	[ERRCODE_OFFSET(OBJCONF_MAP_TYPE)]	= "Incorrect map type",
+	[ERRCODE_OFFSET(OBJCONF_MAP_KEYSIZE)]	= "Incorrect map key size",
+	[ERRCODE_OFFSET(OBJCONF_MAP_VALUESIZE)]	= "Incorrect map value size",
+	[ERRCODE_OFFSET(OBJCONF_MAP_NOEVT)]	= "Event not found for map setting",
+	[ERRCODE_OFFSET(OBJCONF_MAP_MAPSIZE)]	= "Invalid map size for event setting",
+	[ERRCODE_OFFSET(OBJCONF_MAP_EVTDIM)]	= "Event dimension too large",
+	[ERRCODE_OFFSET(OBJCONF_MAP_EVTINH)]	= "Doesn't support inherit event",
+	[ERRCODE_OFFSET(OBJCONF_MAP_EVTTYPE)]	= "Wrong event type for map",
+	[ERRCODE_OFFSET(OBJCONF_MAP_IDX2BIG)]	= "Index too large",
 };
 
 static int
@@ -872,3 +1564,29 @@ int bpf__strerror_load(struct bpf_object *obj,
 	bpf__strerror_end(buf, size);
 	return 0;
 }
+
+int bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
+			     struct parse_events_term *term __maybe_unused,
+			     struct perf_evlist *evlist __maybe_unused,
+			     int *error_pos __maybe_unused, int err,
+			     char *buf, size_t size)
+{
+	bpf__strerror_head(err, buf, size);
+	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE,
+			    "Can't use this config term with this map type");
+	bpf__strerror_end(buf, size);
+	return 0;
+}
+
+int bpf__strerror_apply_obj_config(int err, char *buf, size_t size)
+{
+	bpf__strerror_head(err, buf, size);
+	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM,
+			    "Cannot set event to BPF map in multi-thread tracing");
+	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH,
+			    "%s (Hint: use -i to turn off inherit)", emsg);
+	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE,
+			    "Can only put raw, hardware and BPF output event into a BPF map");
+	bpf__strerror_end(buf, size);
+	return 0;
+}
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 6fdc0457e..be4311944 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -10,6 +10,7 @@
 #include <string.h>
 #include <bpf/libbpf.h>
 #include "probe-event.h"
+#include "evlist.h"
 #include "debug.h"
 
 enum bpf_loader_errno {
@@ -24,10 +25,25 @@ enum bpf_loader_errno {
 	BPF_LOADER_ERRNO__PROLOGUE,	/* Failed to generate prologue */
 	BPF_LOADER_ERRNO__PROLOGUE2BIG,	/* Prologue too big for program */
 	BPF_LOADER_ERRNO__PROLOGUEOOB,	/* Offset out of bound for prologue */
+	BPF_LOADER_ERRNO__OBJCONF_OPT,	/* Invalid object config option */
+	BPF_LOADER_ERRNO__OBJCONF_CONF,	/* Config value not set (lost '=')) */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_OPT,	/* Invalid object map config option */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST,	/* Target map not exist */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE,	/* Incorrect value type for map */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE,	/* Incorrect map type */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE,	/* Incorrect map key size */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE,/* Incorrect map value size */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT,	/* Event not found for map setting */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_MAPSIZE,	/* Invalid map size for event setting */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM,	/* Event dimension too large */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH,	/* Doesn't support inherit event */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE,	/* Wrong event type for map */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG,	/* Index too large */
 	__BPF_LOADER_ERRNO__END,
 };
 
 struct bpf_object;
+struct parse_events_term;
 #define PERF_BPF_PROBE_GROUP "perf_bpf_probe"
 
 typedef int (*bpf_prog_iter_callback_t)(struct probe_trace_event *tev,
@@ -53,6 +69,16 @@ int bpf__strerror_load(struct bpf_object *obj, int err,
 		       char *buf, size_t size);
 int bpf__foreach_tev(struct bpf_object *obj,
 		     bpf_prog_iter_callback_t func, void *arg);
+
+int bpf__config_obj(struct bpf_object *obj, struct parse_events_term *term,
+		    struct perf_evlist *evlist, int *error_pos);
+int bpf__strerror_config_obj(struct bpf_object *obj,
+			     struct parse_events_term *term,
+			     struct perf_evlist *evlist,
+			     int *error_pos, int err, char *buf,
+			     size_t size);
+int bpf__apply_obj_config(void);
+int bpf__strerror_apply_obj_config(int err, char *buf, size_t size);
 #else
 static inline struct bpf_object *
 bpf__prepare_load(const char *filename __maybe_unused,
@@ -84,6 +110,21 @@ bpf__foreach_tev(struct bpf_object *obj __maybe_unused,
 }
 
 static inline int
+bpf__config_obj(struct bpf_object *obj __maybe_unused,
+		struct parse_events_term *term __maybe_unused,
+		struct perf_evlist *evlist __maybe_unused,
+		int *error_pos __maybe_unused)
+{
+	return 0;
+}
+
+static inline int
+bpf__apply_obj_config(void)
+{
+	return 0;
+}
+
+static inline int
 __bpf_strerror(char *buf, size_t size)
 {
 	if (!size)
@@ -118,5 +159,23 @@ static inline int bpf__strerror_load(struct bpf_object *obj __maybe_unused,
 {
 	return __bpf_strerror(buf, size);
 }
+
+static inline int
+bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
+			 struct parse_events_term *term __maybe_unused,
+			 struct perf_evlist *evlist __maybe_unused,
+			 int *error_pos __maybe_unused,
+			 int err __maybe_unused,
+			 char *buf, size_t size)
+{
+	return __bpf_strerror(buf, size);
+}
+
+static inline int
+bpf__strerror_apply_obj_config(int err __maybe_unused,
+			       char *buf, size_t size)
+{
+	return __bpf_strerror(buf, size);
+}
 #endif
 #endif
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 6a7e273a5..0573c2ec8 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -28,7 +28,6 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 			   struct machine *machine)
 {
 	struct addr_location al;
-	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	struct thread *thread = machine__findnew_thread(machine, sample->pid,
 							sample->tid);
 
@@ -38,7 +37,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 		return -1;
 	}
 
-	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, &al);
+	thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, &al);
 
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
@@ -166,6 +165,50 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
 	return build_id__filename(build_id_hex, bf, size);
 }
 
+bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size)
+{
+	char *id_name, *ch;
+	struct stat sb;
+
+	id_name = dso__build_id_filename(dso, bf, size);
+	if (!id_name)
+		goto err;
+	if (access(id_name, F_OK))
+		goto err;
+	if (lstat(id_name, &sb) == -1)
+		goto err;
+	if ((size_t)sb.st_size > size - 1)
+		goto err;
+	if (readlink(id_name, bf, size - 1) < 0)
+		goto err;
+
+	bf[sb.st_size] = '\0';
+
+	/*
+	 * link should be:
+	 * ../../lib/modules/4.4.0-rc4/kernel/net/ipv4/netfilter/nf_nat_ipv4.ko/a09fe3eb3147dafa4e3b31dbd6257e4d696bdc92
+	 */
+	ch = strrchr(bf, '/');
+	if (!ch)
+		goto err;
+	if (ch - 3 < bf)
+		goto err;
+
+	return strncmp(".ko", ch - 3, 3) == 0;
+err:
+	/*
+	 * If dso__build_id_filename work, get id_name again,
+	 * because id_name points to bf and is broken.
+	 */
+	if (id_name)
+		id_name = dso__build_id_filename(dso, bf, size);
+	pr_err("Invalid build id: %s\n", id_name ? :
+					 dso->long_name ? :
+					 dso->short_name ? :
+					 "[unknown]");
+	return false;
+}
+
 #define dsos__for_each_with_build_id(pos, head)	\
 	list_for_each_entry(pos, head, node)	\
 		if (!pos->has_build_id)		\
@@ -211,6 +254,7 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
 	dsos__for_each_with_build_id(pos, &machine->dsos.head) {
 		const char *name;
 		size_t name_len;
+		bool in_kernel = false;
 
 		if (!pos->hit)
 			continue;
@@ -227,8 +271,11 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
 			name_len = pos->long_name_len + 1;
 		}
 
+		in_kernel = pos->kernel ||
+				is_kernel_module(name,
+					PERF_RECORD_MISC_CPUMODE_UNKNOWN);
 		err = write_buildid(name, name_len, pos->build_id, machine->pid,
-				    pos->kernel ? kmisc : umisc, fd);
+				    in_kernel ? kmisc : umisc, fd);
 		if (err)
 			break;
 	}
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 27a14a8a9..64af3e206 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -16,6 +16,7 @@ int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id);
 int filename__sprintf_build_id(const char *pathname, char *sbuild_id);
 
 char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
+bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size);
 
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
 			   struct perf_sample *sample, struct perf_evsel *evsel,
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 07b5d6394..1f5a93c2c 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -23,14 +23,17 @@
 #define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR"
 #define PERF_PAGER_ENVIRONMENT "PERF_PAGER"
 
+extern const char *config_exclusive_filename;
+
 typedef int (*config_fn_t)(const char *, const char *, void *);
-extern int perf_default_config(const char *, const char *, void *);
-extern int perf_config(config_fn_t fn, void *);
-extern int perf_config_int(const char *, const char *);
-extern u64 perf_config_u64(const char *, const char *);
-extern int perf_config_bool(const char *, const char *);
-extern int config_error_nonbool(const char *);
-extern const char *perf_config_dirname(const char *, const char *);
+int perf_default_config(const char *, const char *, void *);
+int perf_config(config_fn_t fn, void *);
+int perf_config_int(const char *, const char *);
+u64 perf_config_u64(const char *, const char *);
+int perf_config_bool(const char *, const char *);
+int config_error_nonbool(const char *);
+const char *perf_config_dirname(const char *, const char *);
+const char *perf_etc_perfconfig(void);
 
 char *alias_lookup(const char *alias);
 int split_cmdline(char *cmdline, const char ***argv);
@@ -61,13 +64,9 @@ static inline int is_absolute_path(const char *path)
 	return path[0] == '/';
 }
 
-const char *make_nonrelative_path(const char *path);
 char *strip_path_suffix(const char *path, const char *suffix);
 
-extern char *mkpath(const char *fmt, ...) __attribute__((format (printf, 1, 2)));
-extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2)));
-
-extern char *perf_pathdup(const char *fmt, ...)
-	__attribute__((format (printf, 1, 2)));
+char *mkpath(const char *fmt, ...) __attribute__((format (printf, 1, 2)));
+char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2)));
 
 #endif /* __PERF_CACHE_H */
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 53c43eb94..24b4bd0d7 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -416,7 +416,7 @@ create_child(struct callchain_node *parent, bool inherit_children)
 /*
  * Fill the node with callchain values
  */
-static void
+static int
 fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 {
 	struct callchain_cursor_node *cursor_node;
@@ -433,7 +433,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 		call = zalloc(sizeof(*call));
 		if (!call) {
 			perror("not enough memory for the code path tree");
-			return;
+			return -1;
 		}
 		call->ip = cursor_node->ip;
 		call->ms.sym = cursor_node->sym;
@@ -443,6 +443,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 		callchain_cursor_advance(cursor);
 		cursor_node = callchain_cursor_current(cursor);
 	}
+	return 0;
 }
 
 static struct callchain_node *
@@ -453,7 +454,19 @@ add_child(struct callchain_node *parent,
 	struct callchain_node *new;
 
 	new = create_child(parent, false);
-	fill_node(new, cursor);
+	if (new == NULL)
+		return NULL;
+
+	if (fill_node(new, cursor) < 0) {
+		struct callchain_list *call, *tmp;
+
+		list_for_each_entry_safe(call, tmp, &new->val, list) {
+			list_del(&call->list);
+			free(call);
+		}
+		free(new);
+		return NULL;
+	}
 
 	new->children_hit = 0;
 	new->hit = period;
@@ -462,16 +475,32 @@ add_child(struct callchain_node *parent,
 	return new;
 }
 
-static s64 match_chain(struct callchain_cursor_node *node,
-		      struct callchain_list *cnode)
+enum match_result {
+	MATCH_ERROR  = -1,
+	MATCH_EQ,
+	MATCH_LT,
+	MATCH_GT,
+};
+
+static enum match_result match_chain(struct callchain_cursor_node *node,
+				     struct callchain_list *cnode)
 {
 	struct symbol *sym = node->sym;
+	u64 left, right;
 
 	if (cnode->ms.sym && sym &&
-	    callchain_param.key == CCKEY_FUNCTION)
-		return cnode->ms.sym->start - sym->start;
-	else
-		return cnode->ip - node->ip;
+	    callchain_param.key == CCKEY_FUNCTION) {
+		left = cnode->ms.sym->start;
+		right = sym->start;
+	} else {
+		left = cnode->ip;
+		right = node->ip;
+	}
+
+	if (left == right)
+		return MATCH_EQ;
+
+	return left > right ? MATCH_GT : MATCH_LT;
 }
 
 /*
@@ -479,7 +508,7 @@ static s64 match_chain(struct callchain_cursor_node *node,
  * give a part of its callchain to the created child.
  * Then create another child to host the given callchain of new branch
  */
-static void
+static int
 split_add_child(struct callchain_node *parent,
 		struct callchain_cursor *cursor,
 		struct callchain_list *to_split,
@@ -491,6 +520,8 @@ split_add_child(struct callchain_node *parent,
 
 	/* split */
 	new = create_child(parent, true);
+	if (new == NULL)
+		return -1;
 
 	/* split the callchain and move a part to the new child */
 	old_tail = parent->val.prev;
@@ -524,6 +555,8 @@ split_add_child(struct callchain_node *parent,
 
 		node = callchain_cursor_current(cursor);
 		new = add_child(parent, cursor, period);
+		if (new == NULL)
+			return -1;
 
 		/*
 		 * This is second child since we moved parent's children
@@ -534,7 +567,7 @@ split_add_child(struct callchain_node *parent,
 		cnode = list_first_entry(&first->val, struct callchain_list,
 					 list);
 
-		if (match_chain(node, cnode) < 0)
+		if (match_chain(node, cnode) == MATCH_LT)
 			pp = &p->rb_left;
 		else
 			pp = &p->rb_right;
@@ -545,14 +578,15 @@ split_add_child(struct callchain_node *parent,
 		parent->hit = period;
 		parent->count = 1;
 	}
+	return 0;
 }
 
-static int
+static enum match_result
 append_chain(struct callchain_node *root,
 	     struct callchain_cursor *cursor,
 	     u64 period);
 
-static void
+static int
 append_chain_children(struct callchain_node *root,
 		      struct callchain_cursor *cursor,
 		      u64 period)
@@ -564,36 +598,42 @@ append_chain_children(struct callchain_node *root,
 
 	node = callchain_cursor_current(cursor);
 	if (!node)
-		return;
+		return -1;
 
 	/* lookup in childrens */
 	while (*p) {
-		s64 ret;
+		enum match_result ret;
 
 		parent = *p;
 		rnode = rb_entry(parent, struct callchain_node, rb_node_in);
 
 		/* If at least first entry matches, rely to children */
 		ret = append_chain(rnode, cursor, period);
-		if (ret == 0)
+		if (ret == MATCH_EQ)
 			goto inc_children_hit;
+		if (ret == MATCH_ERROR)
+			return -1;
 
-		if (ret < 0)
+		if (ret == MATCH_LT)
 			p = &parent->rb_left;
 		else
 			p = &parent->rb_right;
 	}
 	/* nothing in children, add to the current node */
 	rnode = add_child(root, cursor, period);
+	if (rnode == NULL)
+		return -1;
+
 	rb_link_node(&rnode->rb_node_in, parent, p);
 	rb_insert_color(&rnode->rb_node_in, &root->rb_root_in);
 
 inc_children_hit:
 	root->children_hit += period;
 	root->children_count++;
+	return 0;
 }
 
-static int
+static enum match_result
 append_chain(struct callchain_node *root,
 	     struct callchain_cursor *cursor,
 	     u64 period)
@@ -602,7 +642,7 @@ append_chain(struct callchain_node *root,
 	u64 start = cursor->pos;
 	bool found = false;
 	u64 matches;
-	int cmp = 0;
+	enum match_result cmp = MATCH_ERROR;
 
 	/*
 	 * Lookup in the current node
@@ -618,7 +658,7 @@ append_chain(struct callchain_node *root,
 			break;
 
 		cmp = match_chain(node, cnode);
-		if (cmp)
+		if (cmp != MATCH_EQ)
 			break;
 
 		found = true;
@@ -628,7 +668,7 @@ append_chain(struct callchain_node *root,
 
 	/* matches not, relay no the parent */
 	if (!found) {
-		WARN_ONCE(!cmp, "Chain comparison error\n");
+		WARN_ONCE(cmp == MATCH_ERROR, "Chain comparison error\n");
 		return cmp;
 	}
 
@@ -636,21 +676,25 @@ append_chain(struct callchain_node *root,
 
 	/* we match only a part of the node. Split it and add the new chain */
 	if (matches < root->val_nr) {
-		split_add_child(root, cursor, cnode, start, matches, period);
-		return 0;
+		if (split_add_child(root, cursor, cnode, start, matches,
+				    period) < 0)
+			return MATCH_ERROR;
+
+		return MATCH_EQ;
 	}
 
 	/* we match 100% of the path, increment the hit */
 	if (matches == root->val_nr && cursor->pos == cursor->nr) {
 		root->hit += period;
 		root->count++;
-		return 0;
+		return MATCH_EQ;
 	}
 
 	/* We match the node and still have a part remaining */
-	append_chain_children(root, cursor, period);
+	if (append_chain_children(root, cursor, period) < 0)
+		return MATCH_ERROR;
 
-	return 0;
+	return MATCH_EQ;
 }
 
 int callchain_append(struct callchain_root *root,
@@ -662,7 +706,8 @@ int callchain_append(struct callchain_root *root,
 
 	callchain_cursor_commit(cursor);
 
-	append_chain_children(&root->node, cursor, period);
+	if (append_chain_children(&root->node, cursor, period) < 0)
+		return -1;
 
 	if (cursor->nr > root->max_depth)
 		root->max_depth = cursor->nr;
@@ -690,7 +735,8 @@ merge_chain_branch(struct callchain_cursor *cursor,
 
 	if (src->hit) {
 		callchain_cursor_commit(cursor);
-		append_chain_children(dst, cursor, src->hit);
+		if (append_chain_children(dst, cursor, src->hit) < 0)
+			return -1;
 	}
 
 	n = rb_first(&src->rb_root_in);
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 18dd22269..d2a9e6948 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -220,7 +220,7 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *
 			bool hide_unresolved);
 
 extern const char record_callchain_help[];
-extern int parse_callchain_record(const char *arg, struct callchain_param *param);
+int parse_callchain_record(const char *arg, struct callchain_param *param);
 int parse_callchain_record_opt(const char *arg, struct callchain_param *param);
 int parse_callchain_report_opt(const char *arg);
 int parse_callchain_top_opt(const char *arg);
@@ -236,7 +236,7 @@ static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
 }
 
 #ifdef HAVE_SKIP_CALLCHAIN_IDX
-extern int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain);
+int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain);
 #else
 static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
 			struct ip_callchain *chain __maybe_unused)
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index b4b8cb42f..31f8dcdbd 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -13,7 +13,7 @@ struct cgroup_sel {
 
 
 extern int nr_cgroups; /* number of explicit cgroups defined */
-extern void close_cgroup(struct cgroup_sel *cgrp);
-extern int parse_cgroups(const struct option *opt, const char *str, int unset);
+void close_cgroup(struct cgroup_sel *cgrp);
+int parse_cgroups(const struct option *opt, const char *str, int unset);
 
 #endif /* __CGROUP_H__ */
diff --git a/tools/perf/util/cloexec.h b/tools/perf/util/cloexec.h
index 3bee6773d..d0d465953 100644
--- a/tools/perf/util/cloexec.h
+++ b/tools/perf/util/cloexec.h
@@ -5,7 +5,7 @@ unsigned long perf_event_open_cloexec_flag(void);
 
 #ifdef __GLIBC_PREREQ
 #if !__GLIBC_PREREQ(2, 6) && !defined(__UCLIBC__)
-extern int sched_getcpu(void) __THROW;
+int sched_getcpu(void) __THROW;
 #endif
 #endif
 
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index e5fb88bab..43e84aa27 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -32,14 +32,15 @@ int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty)
 	return 0;
 }
 
-int perf_color_default_config(const char *var, const char *value, void *cb)
+int perf_color_default_config(const char *var, const char *value,
+			      void *cb __maybe_unused)
 {
 	if (!strcmp(var, "color.ui")) {
 		perf_use_color_default = perf_config_colorbool(var, value, -1);
 		return 0;
 	}
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 static int __color_vsnprintf(char *bf, size_t size, const char *color,
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index d3e12e30e..4e7276354 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -26,7 +26,7 @@ static const char *config_file_name;
 static int config_linenr;
 static int config_file_eof;
 
-static const char *config_exclusive_filename;
+const char *config_exclusive_filename;
 
 static int get_next_char(void)
 {
@@ -434,7 +434,7 @@ static int perf_config_from_file(config_fn_t fn, const char *filename, void *dat
 	return ret;
 }
 
-static const char *perf_etc_perfconfig(void)
+const char *perf_etc_perfconfig(void)
 {
 	static const char *system_wide;
 	if (!system_wide)
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index fa935093a..9bcf2bed3 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -8,6 +8,10 @@
 #include <linux/bitmap.h>
 #include "asm/bug.h"
 
+static int max_cpu_num;
+static int max_node_num;
+static int *cpunode_map;
+
 static struct cpu_map *cpu_map__default_new(void)
 {
 	struct cpu_map *cpus;
@@ -486,6 +490,32 @@ out:
 		pr_err("Failed to read max nodes, using default of %d\n", max_node_num);
 }
 
+int cpu__max_node(void)
+{
+	if (unlikely(!max_node_num))
+		set_max_node_num();
+
+	return max_node_num;
+}
+
+int cpu__max_cpu(void)
+{
+	if (unlikely(!max_cpu_num))
+		set_max_cpu_num();
+
+	return max_cpu_num;
+}
+
+int cpu__get_node(int cpu)
+{
+	if (unlikely(cpunode_map == NULL)) {
+		pr_debug("cpu_map not initialized\n");
+		return -1;
+	}
+
+	return cpunode_map[cpu];
+}
+
 static int init_cpunode_map(void)
 {
 	int i;
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 71c41b9ef..81a2562aa 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -57,37 +57,11 @@ static inline bool cpu_map__empty(const struct cpu_map *map)
 	return map ? map->map[0] == -1 : true;
 }
 
-int max_cpu_num;
-int max_node_num;
-int *cpunode_map;
-
 int cpu__setup_cpunode_map(void);
 
-static inline int cpu__max_node(void)
-{
-	if (unlikely(!max_node_num))
-		pr_debug("cpu_map not initialized\n");
-
-	return max_node_num;
-}
-
-static inline int cpu__max_cpu(void)
-{
-	if (unlikely(!max_cpu_num))
-		pr_debug("cpu_map not initialized\n");
-
-	return max_cpu_num;
-}
-
-static inline int cpu__get_node(int cpu)
-{
-	if (unlikely(cpunode_map == NULL)) {
-		pr_debug("cpu_map not initialized\n");
-		return -1;
-	}
-
-	return cpunode_map[cpu];
-}
+int cpu__max_node(void);
+int cpu__max_cpu(void);
+int cpu__get_node(int cpu);
 
 int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
 		       int (*f)(struct cpu_map *map, int cpu, void *data),
diff --git a/tools/perf/util/ctype.c b/tools/perf/util/ctype.c
index aada3ac5e..d4a5a21c2 100644
--- a/tools/perf/util/ctype.c
+++ b/tools/perf/util/ctype.c
@@ -32,8 +32,17 @@ unsigned char sane_ctype[256] = {
 
 const char *graph_line =
 	"_____________________________________________________________________"
+	"_____________________________________________________________________"
 	"_____________________________________________________________________";
 const char *graph_dotted_line =
 	"---------------------------------------------------------------------"
 	"---------------------------------------------------------------------"
 	"---------------------------------------------------------------------";
+const char *spaces =
+	"                                                                     "
+	"                                                                     "
+	"                                                                     ";
+const char *dots =
+	"....................................................................."
+	"....................................................................."
+	".....................................................................";
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 34cd1e403..bbf69d248 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -352,6 +352,84 @@ static int add_tracepoint_values(struct ctf_writer *cw,
 	return ret;
 }
 
+static int
+add_bpf_output_values(struct bt_ctf_event_class *event_class,
+		      struct bt_ctf_event *event,
+		      struct perf_sample *sample)
+{
+	struct bt_ctf_field_type *len_type, *seq_type;
+	struct bt_ctf_field *len_field, *seq_field;
+	unsigned int raw_size = sample->raw_size;
+	unsigned int nr_elements = raw_size / sizeof(u32);
+	unsigned int i;
+	int ret;
+
+	if (nr_elements * sizeof(u32) != raw_size)
+		pr_warning("Incorrect raw_size (%u) in bpf output event, skip %lu bytes\n",
+			   raw_size, nr_elements * sizeof(u32) - raw_size);
+
+	len_type = bt_ctf_event_class_get_field_by_name(event_class, "raw_len");
+	len_field = bt_ctf_field_create(len_type);
+	if (!len_field) {
+		pr_err("failed to create 'raw_len' for bpf output event\n");
+		ret = -1;
+		goto put_len_type;
+	}
+
+	ret = bt_ctf_field_unsigned_integer_set_value(len_field, nr_elements);
+	if (ret) {
+		pr_err("failed to set field value for raw_len\n");
+		goto put_len_field;
+	}
+	ret = bt_ctf_event_set_payload(event, "raw_len", len_field);
+	if (ret) {
+		pr_err("failed to set payload to raw_len\n");
+		goto put_len_field;
+	}
+
+	seq_type = bt_ctf_event_class_get_field_by_name(event_class, "raw_data");
+	seq_field = bt_ctf_field_create(seq_type);
+	if (!seq_field) {
+		pr_err("failed to create 'raw_data' for bpf output event\n");
+		ret = -1;
+		goto put_seq_type;
+	}
+
+	ret = bt_ctf_field_sequence_set_length(seq_field, len_field);
+	if (ret) {
+		pr_err("failed to set length of 'raw_data'\n");
+		goto put_seq_field;
+	}
+
+	for (i = 0; i < nr_elements; i++) {
+		struct bt_ctf_field *elem_field =
+			bt_ctf_field_sequence_get_field(seq_field, i);
+
+		ret = bt_ctf_field_unsigned_integer_set_value(elem_field,
+				((u32 *)(sample->raw_data))[i]);
+
+		bt_ctf_field_put(elem_field);
+		if (ret) {
+			pr_err("failed to set raw_data[%d]\n", i);
+			goto put_seq_field;
+		}
+	}
+
+	ret = bt_ctf_event_set_payload(event, "raw_data", seq_field);
+	if (ret)
+		pr_err("failed to set payload for raw_data\n");
+
+put_seq_field:
+	bt_ctf_field_put(seq_field);
+put_seq_type:
+	bt_ctf_field_type_put(seq_type);
+put_len_field:
+	bt_ctf_field_put(len_field);
+put_len_type:
+	bt_ctf_field_type_put(len_type);
+	return ret;
+}
+
 static int add_generic_values(struct ctf_writer *cw,
 			      struct bt_ctf_event *event,
 			      struct perf_evsel *evsel,
@@ -554,7 +632,7 @@ static bool is_flush_needed(struct ctf_stream *cs)
 }
 
 static int process_sample_event(struct perf_tool *tool,
-				union perf_event *_event __maybe_unused,
+				union perf_event *_event,
 				struct perf_sample *sample,
 				struct perf_evsel *evsel,
 				struct machine *machine __maybe_unused)
@@ -597,6 +675,12 @@ static int process_sample_event(struct perf_tool *tool,
 			return -1;
 	}
 
+	if (perf_evsel__is_bpf_output(evsel)) {
+		ret = add_bpf_output_values(event_class, event, sample);
+		if (ret)
+			return -1;
+	}
+
 	cs = ctf_stream(cw, get_sample_cpu(cw, sample, evsel));
 	if (cs) {
 		if (is_flush_needed(cs))
@@ -744,6 +828,25 @@ static int add_tracepoint_types(struct ctf_writer *cw,
 	return ret;
 }
 
+static int add_bpf_output_types(struct ctf_writer *cw,
+				struct bt_ctf_event_class *class)
+{
+	struct bt_ctf_field_type *len_type = cw->data.u32;
+	struct bt_ctf_field_type *seq_base_type = cw->data.u32_hex;
+	struct bt_ctf_field_type *seq_type;
+	int ret;
+
+	ret = bt_ctf_event_class_add_field(class, len_type, "raw_len");
+	if (ret)
+		return ret;
+
+	seq_type = bt_ctf_field_type_sequence_create(seq_base_type, "raw_len");
+	if (!seq_type)
+		return -1;
+
+	return bt_ctf_event_class_add_field(class, seq_type, "raw_data");
+}
+
 static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
 			     struct bt_ctf_event_class *event_class)
 {
@@ -755,7 +858,8 @@ static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
 	 *                              ctf event header
 	 *   PERF_SAMPLE_READ         - TODO
 	 *   PERF_SAMPLE_CALLCHAIN    - TODO
-	 *   PERF_SAMPLE_RAW          - tracepoint fields are handled separately
+	 *   PERF_SAMPLE_RAW          - tracepoint fields and BPF output
+	 *                              are handled separately
 	 *   PERF_SAMPLE_BRANCH_STACK - TODO
 	 *   PERF_SAMPLE_REGS_USER    - TODO
 	 *   PERF_SAMPLE_STACK_USER   - TODO
@@ -824,6 +928,12 @@ static int add_event(struct ctf_writer *cw, struct perf_evsel *evsel)
 			goto err;
 	}
 
+	if (perf_evsel__is_bpf_output(evsel)) {
+		ret = add_bpf_output_types(cw, event_class);
+		if (ret)
+			goto err;
+	}
+
 	ret = bt_ctf_stream_class_add_event_class(cw->stream_class, event_class);
 	if (ret) {
 		pr("Failed to add event class into stream.\n");
@@ -858,6 +968,23 @@ static int setup_events(struct ctf_writer *cw, struct perf_session *session)
 	return 0;
 }
 
+static void cleanup_events(struct perf_session *session)
+{
+	struct perf_evlist *evlist = session->evlist;
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		struct evsel_priv *priv;
+
+		priv = evsel->priv;
+		bt_ctf_event_class_put(priv->event_class);
+		zfree(&evsel->priv);
+	}
+
+	perf_evlist__delete(evlist);
+	session->evlist = NULL;
+}
+
 static int setup_streams(struct ctf_writer *cw, struct perf_session *session)
 {
 	struct ctf_stream **stream;
@@ -953,6 +1080,12 @@ static struct bt_ctf_field_type *create_int_type(int size, bool sign, bool hex)
 	    bt_ctf_field_type_integer_set_base(type, BT_CTF_INTEGER_BASE_HEXADECIMAL))
 		goto err;
 
+#if __BYTE_ORDER == __BIG_ENDIAN
+	bt_ctf_field_type_set_byte_order(type, BT_CTF_BYTE_ORDER_BIG_ENDIAN);
+#else
+	bt_ctf_field_type_set_byte_order(type, BT_CTF_BYTE_ORDER_LITTLE_ENDIAN);
+#endif
+
 	pr2("Created type: INTEGER %d-bit %ssigned %s\n",
 	    size, sign ? "un" : "", hex ? "hex" : "");
 	return type;
@@ -1100,7 +1233,7 @@ static int convert__config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 int bt_convert__perf2ctf(const char *input, const char *path, bool force)
@@ -1171,6 +1304,7 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 		(double) c.events_size / 1024.0 / 1024.0,
 		c.events_count);
 
+	cleanup_events(session);
 	perf_session__delete(session);
 	ctf_writer__cleanup(cw);
 
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 1c9689e4c..049438d51 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -333,7 +333,7 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 	    sample_addr_correlates_sym(&evsel->attr)) {
 		struct addr_location addr_al;
 
-		perf_event__preprocess_sample_addr(event, sample, thread, &addr_al);
+		thread__resolve(thread, &addr_al, sample);
 		err = db_ids_from_al(dbe, &addr_al, &es.addr_dso_db_id,
 				     &es.addr_sym_db_id, &es.addr_offset);
 		if (err)
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 86d9c7302..8c4212abd 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -5,6 +5,7 @@
 #include <string.h>
 #include <stdarg.h>
 #include <stdio.h>
+#include <api/debug.h>
 
 #include "cache.h"
 #include "color.h"
@@ -22,7 +23,7 @@ int debug_ordered_events;
 static int redirect_to_stderr;
 int debug_data_convert;
 
-static int _eprintf(int level, int var, const char *fmt, va_list args)
+int veprintf(int level, int var, const char *fmt, va_list args)
 {
 	int ret = 0;
 
@@ -36,24 +37,19 @@ static int _eprintf(int level, int var, const char *fmt, va_list args)
 	return ret;
 }
 
-int veprintf(int level, int var, const char *fmt, va_list args)
-{
-	return _eprintf(level, var, fmt, args);
-}
-
 int eprintf(int level, int var, const char *fmt, ...)
 {
 	va_list args;
 	int ret;
 
 	va_start(args, fmt);
-	ret = _eprintf(level, var, fmt, args);
+	ret = veprintf(level, var, fmt, args);
 	va_end(args);
 
 	return ret;
 }
 
-static int __eprintf_time(u64 t, const char *fmt, va_list args)
+static int veprintf_time(u64 t, const char *fmt, va_list args)
 {
 	int ret = 0;
 	u64 secs, usecs, nsecs = t;
@@ -75,7 +71,7 @@ int eprintf_time(int level, int var, u64 t, const char *fmt, ...)
 
 	if (var >= level) {
 		va_start(args, fmt);
-		ret = __eprintf_time(t, fmt, args);
+		ret = veprintf_time(t, fmt, args);
 		va_end(args);
 	}
 
@@ -91,7 +87,7 @@ void pr_stat(const char *fmt, ...)
 	va_list args;
 
 	va_start(args, fmt);
-	_eprintf(1, verbose, fmt, args);
+	veprintf(1, verbose, fmt, args);
 	va_end(args);
 	eprintf(1, verbose, "\n");
 }
@@ -110,40 +106,61 @@ int dump_printf(const char *fmt, ...)
 	return ret;
 }
 
+static void trace_event_printer(enum binary_printer_ops op,
+				unsigned int val, void *extra)
+{
+	const char *color = PERF_COLOR_BLUE;
+	union perf_event *event = (union perf_event *)extra;
+	unsigned char ch = (unsigned char)val;
+
+	switch (op) {
+	case BINARY_PRINT_DATA_BEGIN:
+		printf(".");
+		color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n",
+				event->header.size);
+		break;
+	case BINARY_PRINT_LINE_BEGIN:
+		printf(".");
+		break;
+	case BINARY_PRINT_ADDR:
+		color_fprintf(stdout, color, "  %04x: ", val);
+		break;
+	case BINARY_PRINT_NUM_DATA:
+		color_fprintf(stdout, color, " %02x", val);
+		break;
+	case BINARY_PRINT_NUM_PAD:
+		color_fprintf(stdout, color, "   ");
+		break;
+	case BINARY_PRINT_SEP:
+		color_fprintf(stdout, color, "  ");
+		break;
+	case BINARY_PRINT_CHAR_DATA:
+		color_fprintf(stdout, color, "%c",
+			      isprint(ch) ? ch : '.');
+		break;
+	case BINARY_PRINT_CHAR_PAD:
+		color_fprintf(stdout, color, " ");
+		break;
+	case BINARY_PRINT_LINE_END:
+		color_fprintf(stdout, color, "\n");
+		break;
+	case BINARY_PRINT_DATA_END:
+		printf("\n");
+		break;
+	default:
+		break;
+	}
+}
+
 void trace_event(union perf_event *event)
 {
 	unsigned char *raw_event = (void *)event;
-	const char *color = PERF_COLOR_BLUE;
-	int i, j;
 
 	if (!dump_trace)
 		return;
 
-	printf(".");
-	color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n",
-		      event->header.size);
-
-	for (i = 0; i < event->header.size; i++) {
-		if ((i & 15) == 0) {
-			printf(".");
-			color_fprintf(stdout, color, "  %04x: ", i);
-		}
-
-		color_fprintf(stdout, color, " %02x", raw_event[i]);
-
-		if (((i & 15) == 15) || i == event->header.size-1) {
-			color_fprintf(stdout, color, "  ");
-			for (j = 0; j < 15-(i & 15); j++)
-				color_fprintf(stdout, color, "   ");
-			for (j = i & ~15; j <= i; j++) {
-				color_fprintf(stdout, color, "%c",
-					      isprint(raw_event[j]) ?
-					      raw_event[j] : '.');
-			}
-			color_fprintf(stdout, color, "\n");
-		}
-	}
-	printf(".\n");
+	print_binary(raw_event, event->header.size, 16,
+		     trace_event_printer, event);
 }
 
 static struct debug_variable {
@@ -192,3 +209,23 @@ int perf_debug_option(const char *str)
 	free(s);
 	return 0;
 }
+
+#define DEBUG_WRAPPER(__n, __l)				\
+static int pr_ ## __n ## _wrapper(const char *fmt, ...)	\
+{							\
+	va_list args;					\
+	int ret;					\
+							\
+	va_start(args, fmt);				\
+	ret = veprintf(__l, verbose, fmt, args);	\
+	va_end(args);					\
+	return ret;					\
+}
+
+DEBUG_WRAPPER(warning, 0);
+DEBUG_WRAPPER(debug, 1);
+
+void perf_debug_setup(void)
+{
+	libapi_set_print(pr_warning_wrapper, pr_warning_wrapper, pr_debug_wrapper);
+}
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 8b9a088c3..14bafda79 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -53,5 +53,6 @@ int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __attribute__(
 int veprintf(int level, int var, const char *fmt, va_list args);
 
 int perf_debug_option(const char *str);
+void perf_debug_setup(void);
 
 #endif	/* __PERF_DEBUG_H */
diff --git a/tools/perf/util/demangle-java.c b/tools/perf/util/demangle-java.c
new file mode 100644
index 000000000..3e6062ab2
--- /dev/null
+++ b/tools/perf/util/demangle-java.c
@@ -0,0 +1,199 @@
+#include <sys/types.h>
+#include <stdio.h>
+#include <string.h>
+#include "util.h"
+#include "debug.h"
+#include "symbol.h"
+
+#include "demangle-java.h"
+
+enum {
+	MODE_PREFIX = 0,
+	MODE_CLASS  = 1,
+	MODE_FUNC   = 2,
+	MODE_TYPE   = 3,
+	MODE_CTYPE  = 3, /* class arg */
+};
+
+#define BASE_ENT(c, n)	[c - 'A']=n
+static const char *base_types['Z' - 'A' + 1] = {
+	BASE_ENT('B', "byte" ),
+	BASE_ENT('C', "char" ),
+	BASE_ENT('D', "double" ),
+	BASE_ENT('F', "float" ),
+	BASE_ENT('I', "int" ),
+	BASE_ENT('J', "long" ),
+	BASE_ENT('S', "short" ),
+	BASE_ENT('Z', "bool" ),
+};
+
+/*
+ * demangle Java symbol between str and end positions and stores
+ * up to maxlen characters into buf. The parser starts in mode.
+ *
+ * Use MODE_PREFIX to process entire prototype till end position
+ * Use MODE_TYPE to process return type if str starts on return type char
+ *
+ *  Return:
+ *	success: buf
+ *	error  : NULL
+ */
+static char *
+__demangle_java_sym(const char *str, const char *end, char *buf, int maxlen, int mode)
+{
+	int rlen = 0;
+	int array = 0;
+	int narg = 0;
+	const char *q;
+
+	if (!end)
+		end = str + strlen(str);
+
+	for (q = str; q != end; q++) {
+
+		if (rlen == (maxlen - 1))
+			break;
+
+		switch (*q) {
+		case 'L':
+			if (mode == MODE_PREFIX || mode == MODE_CTYPE) {
+				if (mode == MODE_CTYPE) {
+					if (narg)
+						rlen += scnprintf(buf + rlen, maxlen - rlen, ", ");
+					narg++;
+				}
+				rlen += scnprintf(buf + rlen, maxlen - rlen, "class ");
+				if (mode == MODE_PREFIX)
+					mode = MODE_CLASS;
+			} else
+				buf[rlen++] = *q;
+			break;
+		case 'B':
+		case 'C':
+		case 'D':
+		case 'F':
+		case 'I':
+		case 'J':
+		case 'S':
+		case 'Z':
+			if (mode == MODE_TYPE) {
+				if (narg)
+					rlen += scnprintf(buf + rlen, maxlen - rlen, ", ");
+				rlen += scnprintf(buf + rlen, maxlen - rlen, "%s", base_types[*q - 'A']);
+				while (array--)
+					rlen += scnprintf(buf + rlen, maxlen - rlen, "[]");
+				array = 0;
+				narg++;
+			} else
+				buf[rlen++] = *q;
+			break;
+		case 'V':
+			if (mode == MODE_TYPE) {
+				rlen += scnprintf(buf + rlen, maxlen - rlen, "void");
+				while (array--)
+					rlen += scnprintf(buf + rlen, maxlen - rlen, "[]");
+				array = 0;
+			} else
+				buf[rlen++] = *q;
+			break;
+		case '[':
+			if (mode != MODE_TYPE)
+				goto error;
+			array++;
+			break;
+		case '(':
+			if (mode != MODE_FUNC)
+				goto error;
+			buf[rlen++] = *q;
+			mode = MODE_TYPE;
+			break;
+		case ')':
+			if (mode != MODE_TYPE)
+				goto error;
+			buf[rlen++] = *q;
+			narg = 0;
+			break;
+		case ';':
+			if (mode != MODE_CLASS && mode != MODE_CTYPE)
+				goto error;
+			/* safe because at least one other char to process */
+			if (isalpha(*(q + 1)))
+				rlen += scnprintf(buf + rlen, maxlen - rlen, ".");
+			if (mode == MODE_CLASS)
+				mode = MODE_FUNC;
+			else if (mode == MODE_CTYPE)
+				mode = MODE_TYPE;
+			break;
+		case '/':
+			if (mode != MODE_CLASS && mode != MODE_CTYPE)
+				goto error;
+			rlen += scnprintf(buf + rlen, maxlen - rlen, ".");
+			break;
+		default :
+			buf[rlen++] = *q;
+		}
+	}
+	buf[rlen] = '\0';
+	return buf;
+error:
+	return NULL;
+}
+
+/*
+ * Demangle Java function signature (openJDK, not GCJ)
+ * input:
+ * 	str: string to parse. String is not modified
+ *    flags: comobination of JAVA_DEMANGLE_* flags to modify demangling
+ * return:
+ *	if input can be demangled, then a newly allocated string is returned.
+ *	if input cannot be demangled, then NULL is returned
+ *
+ * Note: caller is responsible for freeing demangled string
+ */
+char *
+java_demangle_sym(const char *str, int flags)
+{
+	char *buf, *ptr;
+	char *p;
+	size_t len, l1 = 0;
+
+	if (!str)
+		return NULL;
+
+	/* find start of retunr type */
+	p = strrchr(str, ')');
+	if (!p)
+		return NULL;
+
+	/*
+	 * expansion factor estimated to 3x
+	 */
+	len = strlen(str) * 3 + 1;
+	buf = malloc(len);
+	if (!buf)
+		return NULL;
+
+	buf[0] = '\0';
+	if (!(flags & JAVA_DEMANGLE_NORET)) {
+		/*
+		 * get return type first
+		 */
+		ptr = __demangle_java_sym(p + 1, NULL, buf, len, MODE_TYPE);
+		if (!ptr)
+			goto error;
+
+		/* add space between return type and function prototype */
+		l1 = strlen(buf);
+		buf[l1++] = ' ';
+	}
+
+	/* process function up to return type */
+	ptr = __demangle_java_sym(str, p + 1, buf + l1, len - l1, MODE_PREFIX);
+	if (!ptr)
+		goto error;
+
+	return buf;
+error:
+	free(buf);
+	return NULL;
+}
diff --git a/tools/perf/util/demangle-java.h b/tools/perf/util/demangle-java.h
new file mode 100644
index 000000000..a981c1f96
--- /dev/null
+++ b/tools/perf/util/demangle-java.h
@@ -0,0 +1,10 @@
+#ifndef __PERF_DEMANGLE_JAVA
+#define __PERF_DEMANGLE_JAVA 1
+/*
+ * demangle function flags
+ */
+#define JAVA_DEMANGLE_NORET	0x1 /* do not process return type */
+
+char * java_demangle_sym(const char *str, int flags);
+
+#endif /* __PERF_DEMANGLE_JAVA */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index e8e9a9dbf..8e6395439 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -52,6 +52,11 @@ int dso__read_binary_type_filename(const struct dso *dso,
 			debuglink--;
 		if (*debuglink == '/')
 			debuglink++;
+
+		ret = -1;
+		if (!is_regular_file(filename))
+			break;
+
 		ret = filename__read_debuglink(filename, debuglink,
 					       size - (debuglink - filename));
 		}
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 45ec4d0a5..095328062 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -162,6 +162,7 @@ struct dso {
 	u8		 loaded;
 	u8		 rel;
 	u8		 build_id[BUILD_ID_SIZE];
+	u64		 text_offset;
 	const char	 *short_name;
 	const char	 *long_name;
 	u16		 long_name_len;
@@ -301,7 +302,7 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
  * TODO
 */
 int dso__data_get_fd(struct dso *dso, struct machine *machine);
-void dso__data_put_fd(struct dso *dso __maybe_unused);
+void dso__data_put_fd(struct dso *dso);
 void dso__data_close(struct dso *dso);
 
 off_t dso__data_size(struct dso *dso, struct machine *machine);
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index a509aa843..aea189b41 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -915,7 +915,7 @@ int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
 		tmp = "*";
 	else if (tag == DW_TAG_subroutine_type) {
 		/* Function pointer */
-		strbuf_addf(buf, "(function_type)");
+		strbuf_add(buf, "(function_type)", 15);
 		return 0;
 	} else {
 		if (!dwarf_diename(&type))
@@ -932,7 +932,7 @@ int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
 	}
 	ret = die_get_typename(&type, buf);
 	if (ret == 0)
-		strbuf_addf(buf, "%s", tmp);
+		strbuf_addstr(buf, tmp);
 
 	return ret;
 }
@@ -951,7 +951,7 @@ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf)
 	ret = die_get_typename(vr_die, buf);
 	if (ret < 0) {
 		pr_debug("Failed to get type, make it unknown.\n");
-		strbuf_addf(buf, "(unknown_type)");
+		strbuf_add(buf, " (unknown_type)", 14);
 	}
 
 	strbuf_addf(buf, "\t%s", dwarf_diename(vr_die));
@@ -959,6 +959,7 @@ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf)
 	return 0;
 }
 
+#ifdef HAVE_DWARF_GETLOCATIONS
 /**
  * die_get_var_innermost_scope - Get innermost scope range of given variable DIE
  * @sp_die: a subprogram DIE
@@ -1013,7 +1014,7 @@ static int die_get_var_innermost_scope(Dwarf_Die *sp_die, Dwarf_Die *vr_die,
 	}
 
 	if (!first)
-		strbuf_addf(buf, "]>");
+		strbuf_add(buf, "]>", 2);
 
 out:
 	free(scopes);
@@ -1076,7 +1077,15 @@ int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf)
 	}
 
 	if (!first)
-		strbuf_addf(buf, "]>");
+		strbuf_add(buf, "]>", 2);
 
 	return ret;
 }
+#else
+int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
+		      Dwarf_Die *vr_die __maybe_unused,
+		      struct strbuf *buf __maybe_unused)
+{
+	return -ENOTSUP;
+}
+#endif
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index c42ec366f..dc0ce1adb 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -25,48 +25,48 @@
 #include <elfutils/version.h>
 
 /* Find the realpath of the target file */
-extern const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname);
+const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname);
 
 /* Get DW_AT_comp_dir (should be NULL with older gcc) */
-extern const char *cu_get_comp_dir(Dwarf_Die *cu_die);
+const char *cu_get_comp_dir(Dwarf_Die *cu_die);
 
 /* Get a line number and file name for given address */
-extern int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr,
-			    const char **fname, int *lineno);
+int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr,
+		     const char **fname, int *lineno);
 
 /* Walk on funcitons at given address */
-extern int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr,
-			int (*callback)(Dwarf_Die *, void *), void *data);
+int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr,
+			 int (*callback)(Dwarf_Die *, void *), void *data);
 
 /* Ensure that this DIE is a subprogram and definition (not declaration) */
-extern bool die_is_func_def(Dwarf_Die *dw_die);
+bool die_is_func_def(Dwarf_Die *dw_die);
 
 /* Ensure that this DIE is an instance of a subprogram */
-extern bool die_is_func_instance(Dwarf_Die *dw_die);
+bool die_is_func_instance(Dwarf_Die *dw_die);
 
 /* Compare diename and tname */
-extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname);
+bool die_compare_name(Dwarf_Die *dw_die, const char *tname);
 
 /* Matching diename with glob pattern */
-extern bool die_match_name(Dwarf_Die *dw_die, const char *glob);
+bool die_match_name(Dwarf_Die *dw_die, const char *glob);
 
 /* Get callsite line number of inline-function instance */
-extern int die_get_call_lineno(Dwarf_Die *in_die);
+int die_get_call_lineno(Dwarf_Die *in_die);
 
 /* Get callsite file name of inlined function instance */
-extern const char *die_get_call_file(Dwarf_Die *in_die);
+const char *die_get_call_file(Dwarf_Die *in_die);
 
 /* Get type die */
-extern Dwarf_Die *die_get_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem);
+Dwarf_Die *die_get_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem);
 
 /* Get a type die, but skip qualifiers and typedef */
-extern Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem);
+Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem);
 
 /* Check whether the DIE is signed or not */
-extern bool die_is_signed_type(Dwarf_Die *tp_die);
+bool die_is_signed_type(Dwarf_Die *tp_die);
 
 /* Get data_member_location offset */
-extern int die_get_data_member_location(Dwarf_Die *mb_die, Dwarf_Word *offs);
+int die_get_data_member_location(Dwarf_Die *mb_die, Dwarf_Word *offs);
 
 /* Return values for die_find_child() callbacks */
 enum {
@@ -77,29 +77,29 @@ enum {
 };
 
 /* Search child DIEs */
-extern Dwarf_Die *die_find_child(Dwarf_Die *rt_die,
-				 int (*callback)(Dwarf_Die *, void *),
-				 void *data, Dwarf_Die *die_mem);
+Dwarf_Die *die_find_child(Dwarf_Die *rt_die,
+			 int (*callback)(Dwarf_Die *, void *),
+			 void *data, Dwarf_Die *die_mem);
 
 /* Search a non-inlined function including given address */
-extern Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
-				    Dwarf_Die *die_mem);
+Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
+			     Dwarf_Die *die_mem);
 
 /* Search a non-inlined function with tail call at given address */
 Dwarf_Die *die_find_tailfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
 				    Dwarf_Die *die_mem);
 
 /* Search the top inlined function including given address */
-extern Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
-					  Dwarf_Die *die_mem);
+Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
+				   Dwarf_Die *die_mem);
 
 /* Search the deepest inlined function including given address */
-extern Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
-				      Dwarf_Die *die_mem);
+Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
+			       Dwarf_Die *die_mem);
 
 /* Walk on the instances of given DIE */
-extern int die_walk_instances(Dwarf_Die *in_die,
-			      int (*callback)(Dwarf_Die *, void *), void *data);
+int die_walk_instances(Dwarf_Die *in_die,
+		       int (*callback)(Dwarf_Die *, void *), void *data);
 
 /* Walker on lines (Note: line number will not be sorted) */
 typedef int (* line_walk_callback_t) (const char *fname, int lineno,
@@ -109,22 +109,20 @@ typedef int (* line_walk_callback_t) (const char *fname, int lineno,
  * Walk on lines inside given DIE. If the DIE is a subprogram, walk only on
  * the lines inside the subprogram, otherwise the DIE must be a CU DIE.
  */
-extern int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback,
-			  void *data);
+int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data);
 
 /* Find a variable called 'name' at given address */
-extern Dwarf_Die *die_find_variable_at(Dwarf_Die *sp_die, const char *name,
-				       Dwarf_Addr addr, Dwarf_Die *die_mem);
+Dwarf_Die *die_find_variable_at(Dwarf_Die *sp_die, const char *name,
+				Dwarf_Addr addr, Dwarf_Die *die_mem);
 
 /* Find a member called 'name' */
-extern Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
-				  Dwarf_Die *die_mem);
+Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
+			   Dwarf_Die *die_mem);
 
 /* Get the name of given variable DIE */
-extern int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf);
+int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf);
 
 /* Get the name and type of given variable DIE, stored as "type\tname" */
-extern int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf);
-extern int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die,
-			struct strbuf *buf);
+int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf);
+int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf);
 #endif
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 7dd5939de..49a11d9d8 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -6,6 +6,8 @@ struct perf_env perf_env;
 
 void perf_env__exit(struct perf_env *env)
 {
+	int i;
+
 	zfree(&env->hostname);
 	zfree(&env->os_release);
 	zfree(&env->version);
@@ -19,6 +21,10 @@ void perf_env__exit(struct perf_env *env)
 	zfree(&env->numa_nodes);
 	zfree(&env->pmu_mappings);
 	zfree(&env->cpu);
+
+	for (i = 0; i < env->caches_cnt; i++)
+		cpu_cache_level__free(&env->caches[i]);
+	zfree(&env->caches);
 }
 
 int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[])
@@ -75,3 +81,10 @@ int perf_env__read_cpu_topology_map(struct perf_env *env)
 	env->nr_cpus_avail = nr_cpus;
 	return 0;
 }
+
+void cpu_cache_level__free(struct cpu_cache_level *cache)
+{
+	free(cache->type);
+	free(cache->map);
+	free(cache->size);
+}
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 0132b9557..56cffb60a 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -1,11 +1,23 @@
 #ifndef __PERF_ENV_H
 #define __PERF_ENV_H
 
+#include <linux/types.h>
+
 struct cpu_topology_map {
 	int	socket_id;
 	int	core_id;
 };
 
+struct cpu_cache_level {
+	u32	level;
+	u32	line_size;
+	u32	sets;
+	u32	ways;
+	char	*type;
+	char	*size;
+	char	*map;
+};
+
 struct perf_env {
 	char			*hostname;
 	char			*os_release;
@@ -31,6 +43,8 @@ struct perf_env {
 	char			*numa_nodes;
 	char			*pmu_mappings;
 	struct cpu_topology_map	*cpu;
+	struct cpu_cache_level	*caches;
+	int			 caches_cnt;
 };
 
 extern struct perf_env perf_env;
@@ -41,4 +55,5 @@ int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]);
 
 int perf_env__read_cpu_topology_map(struct perf_env *env);
 
+void cpu_cache_level__free(struct cpu_cache_level *cache);
 #endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 7bad5c3fa..edcf4ed4e 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -56,13 +56,22 @@ const char *perf_event__name(unsigned int id)
 	return perf_event__names[id];
 }
 
-static struct perf_sample synth_sample = {
+static int perf_tool__process_synth_event(struct perf_tool *tool,
+					  union perf_event *event,
+					  struct machine *machine,
+					  perf_event__handler_t process)
+{
+	struct perf_sample synth_sample = {
 	.pid	   = -1,
 	.tid	   = -1,
 	.time	   = -1,
 	.stream_id = -1,
 	.cpu	   = -1,
 	.period	   = 1,
+	.cpumode   = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK,
+	};
+
+	return process(tool, event, &synth_sample, machine);
 };
 
 /*
@@ -186,7 +195,7 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 	if (perf_event__prepare_comm(event, pid, machine, &tgid, &ppid) != 0)
 		return -1;
 
-	if (process(tool, event, &synth_sample, machine) != 0)
+	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
 		return -1;
 
 	return tgid;
@@ -218,7 +227,7 @@ static int perf_event__synthesize_fork(struct perf_tool *tool,
 
 	event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size);
 
-	if (process(tool, event, &synth_sample, machine) != 0)
+	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
 		return -1;
 
 	return 0;
@@ -344,7 +353,7 @@ out:
 		event->mmap2.pid = tgid;
 		event->mmap2.tid = pid;
 
-		if (process(tool, event, &synth_sample, machine) != 0) {
+		if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
 			rc = -1;
 			break;
 		}
@@ -402,7 +411,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 
 		memcpy(event->mmap.filename, pos->dso->long_name,
 		       pos->dso->long_name_len + 1);
-		if (process(tool, event, &synth_sample, machine) != 0) {
+		if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
 			rc = -1;
 			break;
 		}
@@ -424,7 +433,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 {
 	char filename[PATH_MAX];
 	DIR *tasks;
-	struct dirent dirent, *next;
+	struct dirent *dirent;
 	pid_t tgid, ppid;
 	int rc = 0;
 
@@ -453,11 +462,11 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		return 0;
 	}
 
-	while (!readdir_r(tasks, &dirent, &next) && next) {
+	while ((dirent = readdir(tasks)) != NULL) {
 		char *end;
 		pid_t _pid;
 
-		_pid = strtol(dirent.d_name, &end, 10);
+		_pid = strtol(dirent->d_name, &end, 10);
 		if (*end)
 			continue;
 
@@ -472,7 +481,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		/*
 		 * Send the prepared comm event
 		 */
-		if (process(tool, comm_event, &synth_sample, machine) != 0)
+		if (perf_tool__process_synth_event(tool, comm_event, machine, process) != 0)
 			break;
 
 		rc = 0;
@@ -566,7 +575,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 {
 	DIR *proc;
 	char proc_path[PATH_MAX];
-	struct dirent dirent, *next;
+	struct dirent *dirent;
 	union perf_event *comm_event, *mmap_event, *fork_event;
 	int err = -1;
 
@@ -591,9 +600,9 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	if (proc == NULL)
 		goto out_free_fork;
 
-	while (!readdir_r(proc, &dirent, &next) && next) {
+	while ((dirent = readdir(proc)) != NULL) {
 		char *end;
-		pid_t pid = strtol(dirent.d_name, &end, 10);
+		pid_t pid = strtol(dirent->d_name, &end, 10);
 
 		if (*end) /* only interested in proper numerical dirents */
 			continue;
@@ -701,7 +710,7 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 	event->mmap.len   = map->end - event->mmap.start;
 	event->mmap.pid   = machine->pid;
 
-	err = process(tool, event, &synth_sample, machine);
+	err = perf_tool__process_synth_event(tool, event, machine, process);
 	free(event);
 
 	return err;
@@ -1295,12 +1304,9 @@ void thread__find_addr_location(struct thread *thread,
  * Callers need to drop the reference to al->thread, obtained in
  * machine__findnew_thread()
  */
-int perf_event__preprocess_sample(const union perf_event *event,
-				  struct machine *machine,
-				  struct addr_location *al,
-				  struct perf_sample *sample)
+int machine__resolve(struct machine *machine, struct addr_location *al,
+		     struct perf_sample *sample)
 {
-	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	struct thread *thread = machine__findnew_thread(machine, sample->pid,
 							sample->tid);
 
@@ -1315,11 +1321,11 @@ int perf_event__preprocess_sample(const union perf_event *event,
 	 * events, but for older perf.data files there was no such thing, so do
 	 * it now.
 	 */
-	if (cpumode == PERF_RECORD_MISC_KERNEL &&
+	if (sample->cpumode == PERF_RECORD_MISC_KERNEL &&
 	    machine__kernel_map(machine) == NULL)
 		machine__create_kernel_maps(machine);
 
-	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, al);
+	thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, al);
 	dump_printf(" ...... dso: %s\n",
 		    al->map ? al->map->dso->long_name :
 			al->level == 'H' ? "[hypervisor]" : "<not found>");
@@ -1395,16 +1401,12 @@ bool sample_addr_correlates_sym(struct perf_event_attr *attr)
 	return false;
 }
 
-void perf_event__preprocess_sample_addr(union perf_event *event,
-					struct perf_sample *sample,
-					struct thread *thread,
-					struct addr_location *al)
+void thread__resolve(struct thread *thread, struct addr_location *al,
+		     struct perf_sample *sample)
 {
-	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-
-	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->addr, al);
+	thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->addr, al);
 	if (!al->map)
-		thread__find_addr_map(thread, cpumode, MAP__VARIABLE,
+		thread__find_addr_map(thread, sample->cpumode, MAP__VARIABLE,
 				      sample->addr, al);
 
 	al->cpu = sample->cpu;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index b7ffb7ee9..6bb1c9283 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -192,6 +192,7 @@ struct perf_sample {
 	u64 data_src;
 	u32 flags;
 	u16 insn_len;
+	u8  cpumode;
 	void *raw_data;
 	struct ip_callchain *callchain;
 	struct branch_stack *branch_stack;
@@ -597,10 +598,8 @@ int perf_event__process(struct perf_tool *tool,
 
 struct addr_location;
 
-int perf_event__preprocess_sample(const union perf_event *event,
-				  struct machine *machine,
-				  struct addr_location *al,
-				  struct perf_sample *sample);
+int machine__resolve(struct machine *machine, struct addr_location *al,
+		     struct perf_sample *sample);
 
 void addr_location__put(struct addr_location *al);
 
@@ -608,10 +607,8 @@ struct thread;
 
 bool is_bts_event(struct perf_event_attr *attr);
 bool sample_addr_correlates_sym(struct perf_event_attr *attr);
-void perf_event__preprocess_sample_addr(union perf_event *event,
-					struct perf_sample *sample,
-					struct thread *thread,
-					struct addr_location *al);
+void thread__resolve(struct thread *thread, struct addr_location *al,
+		     struct perf_sample *sample);
 
 const char *perf_event__name(unsigned int id);
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index a7eb0eae9..86a03836a 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1223,6 +1223,9 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
 	int err = 0;
 
 	evlist__for_each(evlist, evsel) {
+		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+			continue;
+
 		err = perf_evsel__set_filter(evsel, filter);
 		if (err)
 			break;
@@ -1624,7 +1627,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp)
 	return printed + fprintf(fp, "\n");
 }
 
-int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
+int perf_evlist__strerror_open(struct perf_evlist *evlist,
 			       int err, char *buf, size_t size)
 {
 	int printed, value;
@@ -1652,7 +1655,25 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
 				    "Hint:\tTry: 'sudo sh -c \"echo -1 > /proc/sys/kernel/perf_event_paranoid\"'\n"
 				    "Hint:\tThe current value is %d.", value);
 		break;
+	case EINVAL: {
+		struct perf_evsel *first = perf_evlist__first(evlist);
+		int max_freq;
+
+		if (sysctl__read_int("kernel/perf_event_max_sample_rate", &max_freq) < 0)
+			goto out_default;
+
+		if (first->attr.sample_freq < (u64)max_freq)
+			goto out_default;
+
+		printed = scnprintf(buf, size,
+				    "Error:\t%s.\n"
+				    "Hint:\tCheck /proc/sys/kernel/perf_event_max_sample_rate.\n"
+				    "Hint:\tThe current value is %d and %" PRIu64 " is being requested.",
+				    emsg, max_freq, first->attr.sample_freq);
+		break;
+	}
 	default:
+out_default:
 		scnprintf(buf, size, "%s", emsg);
 		break;
 	}
@@ -1723,3 +1744,19 @@ void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 
 	tracking_evsel->tracking = true;
 }
+
+struct perf_evsel *
+perf_evlist__find_evsel_by_str(struct perf_evlist *evlist,
+			       const char *str)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		if (!evsel->name)
+			continue;
+		if (strcmp(str, evsel->name) == 0)
+			return evsel;
+	}
+
+	return NULL;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 7c4d9a206..a0d15221d 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -294,4 +294,7 @@ void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 				     struct perf_evsel *tracking_evsel);
 
 void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr);
+
+struct perf_evsel *
+perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index cdbaf9b51..645dc1828 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -225,6 +225,11 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 	if (evsel != NULL)
 		perf_evsel__init(evsel, attr, idx);
 
+	if (perf_evsel__is_bpf_output(evsel)) {
+		evsel->attr.sample_type |= PERF_SAMPLE_RAW;
+		evsel->attr.sample_period = 1;
+	}
+
 	return evsel;
 }
 
@@ -898,6 +903,16 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	if (evsel->precise_max)
 		perf_event_attr__set_max_precise_ip(attr);
 
+	if (opts->all_user) {
+		attr->exclude_kernel = 1;
+		attr->exclude_user   = 0;
+	}
+
+	if (opts->all_kernel) {
+		attr->exclude_kernel = 0;
+		attr->exclude_user   = 1;
+	}
+
 	/*
 	 * Apply event specific term settings,
 	 * it overloads any global configuration.
@@ -1628,6 +1643,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 	data->stream_id = data->id = data->time = -1ULL;
 	data->period = evsel->attr.sample_period;
 	data->weight = 0;
+	data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
 	if (event->header.type != PERF_RECORD_SAMPLE) {
 		if (!evsel->attr.sample_id_all)
@@ -2329,6 +2345,8 @@ out:
 bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 			  char *msg, size_t msgsize)
 {
+	int paranoid;
+
 	if ((err == ENOENT || err == ENXIO || err == ENODEV) &&
 	    evsel->attr.type   == PERF_TYPE_HARDWARE &&
 	    evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES) {
@@ -2348,6 +2366,22 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 
 		zfree(&evsel->name);
 		return true;
+	} else if (err == EACCES && !evsel->attr.exclude_kernel &&
+		   (paranoid = perf_event_paranoid()) > 1) {
+		const char *name = perf_evsel__name(evsel);
+		char *new_name;
+
+		if (asprintf(&new_name, "%s%su", name, strchr(name, ':') ? "" : ":") < 0)
+			return false;
+
+		if (evsel->name)
+			free(evsel->name);
+		evsel->name = new_name;
+		scnprintf(msg, msgsize,
+"kernel.perf_event_paranoid=%d, trying to fall back to excluding kernel samples", paranoid);
+		evsel->attr.exclude_kernel = 1;
+
+		return true;
 	}
 
 	return false;
@@ -2362,13 +2396,17 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 	case EPERM:
 	case EACCES:
 		return scnprintf(msg, size,
-		 "You may not have permission to collect %sstats.\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",
-				 target->system_wide ? "system-wide " : "");
+		 "You may not have permission to collect %sstats.\n\n"
+		 "Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n"
+		 "which controls use of the performance events system by\n"
+		 "unprivileged users (without CAP_SYS_ADMIN).\n\n"
+		 "The current value is %d:\n\n"
+		 "  -1: Allow use of (almost) all events by all users\n"
+		 ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n"
+		 ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n"
+		 ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN",
+				 target->system_wide ? "system-wide " : "",
+				 perf_event_paranoid());
 	case ENOENT:
 		return scnprintf(msg, size, "The %s event is not supported.",
 				 perf_evsel__name(evsel));
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 4d8037a3d..501ea6e56 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -362,6 +362,14 @@ static inline bool perf_evsel__is_function_event(struct perf_evsel *evsel)
 #undef FUNCTION_EVENT
 }
 
+static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+
+	return (attr->config == PERF_COUNT_SW_BPF_OUTPUT) &&
+		(attr->type == PERF_TYPE_SOFTWARE);
+}
+
 struct perf_attr_details {
 	bool freq;
 	bool verbose;
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
new file mode 100644
index 000000000..c1ef805c6
--- /dev/null
+++ b/tools/perf/util/genelf.c
@@ -0,0 +1,449 @@
+/*
+ * genelf.c
+ * Copyright (C) 2014, Google, Inc
+ *
+ * Contributed by:
+ * 	Stephane Eranian <eranian@gmail.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include <sys/types.h>
+#include <stdio.h>
+#include <getopt.h>
+#include <stddef.h>
+#include <libelf.h>
+#include <string.h>
+#include <stdlib.h>
+#include <inttypes.h>
+#include <limits.h>
+#include <fcntl.h>
+#include <err.h>
+#include <dwarf.h>
+
+#include "perf.h"
+#include "genelf.h"
+#include "../util/jitdump.h"
+
+#define JVMTI
+
+#define BUILD_ID_URANDOM /* different uuid for each run */
+
+#ifdef HAVE_LIBCRYPTO
+
+#define BUILD_ID_MD5
+#undef BUILD_ID_SHA	/* does not seem to work well when linked with Java */
+#undef BUILD_ID_URANDOM /* different uuid for each run */
+
+#ifdef BUILD_ID_SHA
+#include <openssl/sha.h>
+#endif
+
+#ifdef BUILD_ID_MD5
+#include <openssl/md5.h>
+#endif
+#endif
+
+
+typedef struct {
+  unsigned int namesz;  /* Size of entry's owner string */
+  unsigned int descsz;  /* Size of the note descriptor */
+  unsigned int type;    /* Interpretation of the descriptor */
+  char         name[0]; /* Start of the name+desc data */
+} Elf_Note;
+
+struct options {
+	char *output;
+	int fd;
+};
+
+static char shd_string_table[] = {
+	0,
+	'.', 't', 'e', 'x', 't', 0,			/*  1 */
+	'.', 's', 'h', 's', 't', 'r', 't', 'a', 'b', 0, /*  7 */
+	'.', 's', 'y', 'm', 't', 'a', 'b', 0,		/* 17 */
+	'.', 's', 't', 'r', 't', 'a', 'b', 0,		/* 25 */
+	'.', 'n', 'o', 't', 'e', '.', 'g', 'n', 'u', '.', 'b', 'u', 'i', 'l', 'd', '-', 'i', 'd', 0, /* 33 */
+	'.', 'd', 'e', 'b', 'u', 'g', '_', 'l', 'i', 'n', 'e', 0, /* 52 */
+	'.', 'd', 'e', 'b', 'u', 'g', '_', 'i', 'n', 'f', 'o', 0, /* 64 */
+	'.', 'd', 'e', 'b', 'u', 'g', '_', 'a', 'b', 'b', 'r', 'e', 'v', 0, /* 76 */
+};
+
+static struct buildid_note {
+	Elf_Note desc;		/* descsz: size of build-id, must be multiple of 4 */
+	char	 name[4];	/* GNU\0 */
+	char	 build_id[20];
+} bnote;
+
+static Elf_Sym symtab[]={
+	/* symbol 0 MUST be the undefined symbol */
+	{ .st_name  = 0, /* index in sym_string table */
+	  .st_info  = ELF_ST_TYPE(STT_NOTYPE),
+	  .st_shndx = 0, /* for now */
+	  .st_value = 0x0,
+	  .st_other = ELF_ST_VIS(STV_DEFAULT),
+	  .st_size  = 0,
+	},
+	{ .st_name  = 1, /* index in sym_string table */
+	  .st_info  = ELF_ST_BIND(STB_LOCAL) | ELF_ST_TYPE(STT_FUNC),
+	  .st_shndx = 1,
+	  .st_value = 0, /* for now */
+	  .st_other = ELF_ST_VIS(STV_DEFAULT),
+	  .st_size  = 0, /* for now */
+	}
+};
+
+#ifdef BUILD_ID_URANDOM
+static void
+gen_build_id(struct buildid_note *note,
+	     unsigned long load_addr __maybe_unused,
+	     const void *code __maybe_unused,
+	     size_t csize __maybe_unused)
+{
+	int fd;
+	size_t sz = sizeof(note->build_id);
+	ssize_t sret;
+
+	fd = open("/dev/urandom", O_RDONLY);
+	if (fd == -1)
+		err(1, "cannot access /dev/urandom for builid");
+
+	sret = read(fd, note->build_id, sz);
+
+	close(fd);
+
+	if (sret != (ssize_t)sz)
+		memset(note->build_id, 0, sz);
+}
+#endif
+
+#ifdef BUILD_ID_SHA
+static void
+gen_build_id(struct buildid_note *note,
+	     unsigned long load_addr __maybe_unused,
+	     const void *code,
+	     size_t csize)
+{
+	if (sizeof(note->build_id) < SHA_DIGEST_LENGTH)
+		errx(1, "build_id too small for SHA1");
+
+	SHA1(code, csize, (unsigned char *)note->build_id);
+}
+#endif
+
+#ifdef BUILD_ID_MD5
+static void
+gen_build_id(struct buildid_note *note, unsigned long load_addr, const void *code, size_t csize)
+{
+	MD5_CTX context;
+
+	if (sizeof(note->build_id) < 16)
+		errx(1, "build_id too small for MD5");
+
+	MD5_Init(&context);
+	MD5_Update(&context, &load_addr, sizeof(load_addr));
+	MD5_Update(&context, code, csize);
+	MD5_Final((unsigned char *)note->build_id, &context);
+}
+#endif
+
+/*
+ * fd: file descriptor open for writing for the output file
+ * load_addr: code load address (could be zero, just used for buildid)
+ * sym: function name (for native code - used as the symbol)
+ * code: the native code
+ * csize: the code size in bytes
+ */
+int
+jit_write_elf(int fd, uint64_t load_addr, const char *sym,
+	      const void *code, int csize,
+	      void *debug, int nr_debug_entries)
+{
+	Elf *e;
+	Elf_Data *d;
+	Elf_Scn *scn;
+	Elf_Ehdr *ehdr;
+	Elf_Shdr *shdr;
+	char *strsym = NULL;
+	int symlen;
+	int retval = -1;
+
+	if (elf_version(EV_CURRENT) == EV_NONE) {
+		warnx("ELF initialization failed");
+		return -1;
+	}
+
+	e = elf_begin(fd, ELF_C_WRITE, NULL);
+	if (!e) {
+		warnx("elf_begin failed");
+		goto error;
+	}
+
+	/*
+	 * setup ELF header
+	 */
+	ehdr = elf_newehdr(e);
+	if (!ehdr) {
+		warnx("cannot get ehdr");
+		goto error;
+	}
+
+	ehdr->e_ident[EI_DATA] = GEN_ELF_ENDIAN;
+	ehdr->e_ident[EI_CLASS] = GEN_ELF_CLASS;
+	ehdr->e_machine = GEN_ELF_ARCH;
+	ehdr->e_type = ET_DYN;
+	ehdr->e_entry = GEN_ELF_TEXT_OFFSET;
+	ehdr->e_version = EV_CURRENT;
+	ehdr->e_shstrndx= 2; /* shdr index for section name */
+
+	/*
+	 * setup text section
+	 */
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		goto error;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		goto error;
+	}
+
+	d->d_align = 16;
+	d->d_off = 0LL;
+	d->d_buf = (void *)code;
+	d->d_type = ELF_T_BYTE;
+	d->d_size = csize;
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		goto error;
+	}
+
+	shdr->sh_name = 1;
+	shdr->sh_type = SHT_PROGBITS;
+	shdr->sh_addr = GEN_ELF_TEXT_OFFSET;
+	shdr->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+	shdr->sh_entsize = 0;
+
+	/*
+	 * setup section headers string table
+	 */
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		goto error;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		goto error;
+	}
+
+	d->d_align = 1;
+	d->d_off = 0LL;
+	d->d_buf = shd_string_table;
+	d->d_type = ELF_T_BYTE;
+	d->d_size = sizeof(shd_string_table);
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		goto error;
+	}
+
+	shdr->sh_name = 7; /* offset of '.shstrtab' in shd_string_table */
+	shdr->sh_type = SHT_STRTAB;
+	shdr->sh_flags = 0;
+	shdr->sh_entsize = 0;
+
+	/*
+	 * setup symtab section
+	 */
+	symtab[1].st_size  = csize;
+	symtab[1].st_value = GEN_ELF_TEXT_OFFSET;
+
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		goto error;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		goto error;
+	}
+
+	d->d_align = 8;
+	d->d_off = 0LL;
+	d->d_buf = symtab;
+	d->d_type = ELF_T_SYM;
+	d->d_size = sizeof(symtab);
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		goto error;
+	}
+
+	shdr->sh_name = 17; /* offset of '.symtab' in shd_string_table */
+	shdr->sh_type = SHT_SYMTAB;
+	shdr->sh_flags = 0;
+	shdr->sh_entsize = sizeof(Elf_Sym);
+	shdr->sh_link = 4; /* index of .strtab section */
+
+	/*
+	 * setup symbols string table
+	 * 2 = 1 for 0 in 1st entry, 1 for the 0 at end of symbol for 2nd entry
+	 */
+	symlen = 2 + strlen(sym);
+	strsym = calloc(1, symlen);
+	if (!strsym) {
+		warnx("cannot allocate strsym");
+		goto error;
+	}
+	strcpy(strsym + 1, sym);
+
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		goto error;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		goto error;
+	}
+
+	d->d_align = 1;
+	d->d_off = 0LL;
+	d->d_buf = strsym;
+	d->d_type = ELF_T_BYTE;
+	d->d_size = symlen;
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		goto error;
+	}
+
+	shdr->sh_name = 25; /* offset in shd_string_table */
+	shdr->sh_type = SHT_STRTAB;
+	shdr->sh_flags = 0;
+	shdr->sh_entsize = 0;
+
+	/*
+	 * setup build-id section
+	 */
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		goto error;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		goto error;
+	}
+
+	/*
+	 * build-id generation
+	 */
+	gen_build_id(&bnote, load_addr, code, csize);
+	bnote.desc.namesz = sizeof(bnote.name); /* must include 0 termination */
+	bnote.desc.descsz = sizeof(bnote.build_id);
+	bnote.desc.type   = NT_GNU_BUILD_ID;
+	strcpy(bnote.name, "GNU");
+
+	d->d_align = 4;
+	d->d_off = 0LL;
+	d->d_buf = &bnote;
+	d->d_type = ELF_T_BYTE;
+	d->d_size = sizeof(bnote);
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		goto error;
+	}
+
+	shdr->sh_name = 33; /* offset in shd_string_table */
+	shdr->sh_type = SHT_NOTE;
+	shdr->sh_addr = 0x0;
+	shdr->sh_flags = SHF_ALLOC;
+	shdr->sh_size = sizeof(bnote);
+	shdr->sh_entsize = 0;
+
+	if (debug && nr_debug_entries) {
+		retval = jit_add_debug_info(e, load_addr, debug, nr_debug_entries);
+		if (retval)
+			goto error;
+	} else {
+		if (elf_update(e, ELF_C_WRITE) < 0) {
+			warnx("elf_update 4 failed");
+			goto error;
+		}
+	}
+
+	retval = 0;
+error:
+	(void)elf_end(e);
+
+	free(strsym);
+
+
+	return retval;
+}
+
+#ifndef JVMTI
+
+static unsigned char x86_code[] = {
+    0xBB, 0x2A, 0x00, 0x00, 0x00, /* movl $42, %ebx */
+    0xB8, 0x01, 0x00, 0x00, 0x00, /* movl $1, %eax */
+    0xCD, 0x80            /* int $0x80 */
+};
+
+static struct options options;
+
+int main(int argc, char **argv)
+{
+	int c, fd, ret;
+
+	while ((c = getopt(argc, argv, "o:h")) != -1) {
+		switch (c) {
+		case 'o':
+			options.output = optarg;
+			break;
+		case 'h':
+			printf("Usage: genelf -o output_file [-h]\n");
+			return 0;
+		default:
+			errx(1, "unknown option");
+		}
+	}
+
+	fd = open(options.output, O_CREAT|O_TRUNC|O_RDWR, 0666);
+	if (fd == -1)
+		err(1, "cannot create file %s", options.output);
+
+	ret = jit_write_elf(fd, "main", x86_code, sizeof(x86_code));
+	close(fd);
+
+	if (ret != 0)
+		unlink(options.output);
+
+	return ret;
+}
+#endif
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
new file mode 100644
index 000000000..2fbeb59c4
--- /dev/null
+++ b/tools/perf/util/genelf.h
@@ -0,0 +1,61 @@
+#ifndef __GENELF_H__
+#define __GENELF_H__
+
+/* genelf.c */
+int jit_write_elf(int fd, uint64_t code_addr, const char *sym,
+		  const void *code, int csize, void *debug, int nr_debug_entries);
+/* genelf_debug.c */
+int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_entries);
+
+#if   defined(__arm__)
+#define GEN_ELF_ARCH	EM_ARM
+#define GEN_ELF_CLASS	ELFCLASS32
+#elif defined(__aarch64__)
+#define GEN_ELF_ARCH	EM_AARCH64
+#define GEN_ELF_CLASS	ELFCLASS64
+#elif defined(__x86_64__)
+#define GEN_ELF_ARCH	EM_X86_64
+#define GEN_ELF_CLASS	ELFCLASS64
+#elif defined(__i386__)
+#define GEN_ELF_ARCH	EM_386
+#define GEN_ELF_CLASS	ELFCLASS32
+#elif defined(__powerpc64__)
+#define GEN_ELF_ARCH	EM_PPC64
+#define GEN_ELF_CLASS	ELFCLASS64
+#elif defined(__powerpc__)
+#define GEN_ELF_ARCH	EM_PPC
+#define GEN_ELF_CLASS	ELFCLASS32
+#else
+#error "unsupported architecture"
+#endif
+
+#if __BYTE_ORDER == __BIG_ENDIAN
+#define GEN_ELF_ENDIAN	ELFDATA2MSB
+#else
+#define GEN_ELF_ENDIAN	ELFDATA2LSB
+#endif
+
+#if GEN_ELF_CLASS == ELFCLASS64
+#define elf_newehdr	elf64_newehdr
+#define elf_getshdr	elf64_getshdr
+#define Elf_Ehdr	Elf64_Ehdr
+#define Elf_Shdr	Elf64_Shdr
+#define Elf_Sym		Elf64_Sym
+#define ELF_ST_TYPE(a)	ELF64_ST_TYPE(a)
+#define ELF_ST_BIND(a)	ELF64_ST_BIND(a)
+#define ELF_ST_VIS(a)	ELF64_ST_VISIBILITY(a)
+#else
+#define elf_newehdr	elf32_newehdr
+#define elf_getshdr	elf32_getshdr
+#define Elf_Ehdr	Elf32_Ehdr
+#define Elf_Shdr	Elf32_Shdr
+#define Elf_Sym		Elf32_Sym
+#define ELF_ST_TYPE(a)	ELF32_ST_TYPE(a)
+#define ELF_ST_BIND(a)	ELF32_ST_BIND(a)
+#define ELF_ST_VIS(a)	ELF32_ST_VISIBILITY(a)
+#endif
+
+/* The .text section is directly after the ELF header */
+#define GEN_ELF_TEXT_OFFSET sizeof(Elf_Ehdr)
+
+#endif
diff --git a/tools/perf/util/genelf_debug.c b/tools/perf/util/genelf_debug.c
new file mode 100644
index 000000000..5980f7d25
--- /dev/null
+++ b/tools/perf/util/genelf_debug.c
@@ -0,0 +1,610 @@
+/*
+ * genelf_debug.c
+ * Copyright (C) 2015, Google, Inc
+ *
+ * Contributed by:
+ * 	Stephane Eranian <eranian@google.com>
+ *
+ * Released under the GPL v2.
+ *
+ * based on GPLv2 source code from Oprofile
+ * @remark Copyright 2007 OProfile authors
+ * @author Philippe Elie
+ */
+#include <sys/types.h>
+#include <stdio.h>
+#include <getopt.h>
+#include <stddef.h>
+#include <libelf.h>
+#include <string.h>
+#include <stdlib.h>
+#include <inttypes.h>
+#include <limits.h>
+#include <fcntl.h>
+#include <err.h>
+#include <dwarf.h>
+
+#include "perf.h"
+#include "genelf.h"
+#include "../util/jitdump.h"
+
+#define BUFFER_EXT_DFL_SIZE	(4 * 1024)
+
+typedef uint32_t uword;
+typedef uint16_t uhalf;
+typedef int32_t  sword;
+typedef int16_t  shalf;
+typedef uint8_t  ubyte;
+typedef int8_t   sbyte;
+
+struct buffer_ext {
+	size_t cur_pos;
+	size_t max_sz;
+	void *data;
+};
+
+static void
+buffer_ext_dump(struct buffer_ext *be, const char *msg)
+{
+	size_t i;
+	warnx("DUMP for %s", msg);
+	for (i = 0 ; i < be->cur_pos; i++)
+		warnx("%4zu 0x%02x", i, (((char *)be->data)[i]) & 0xff);
+}
+
+static inline int
+buffer_ext_add(struct buffer_ext *be, void *addr, size_t sz)
+{
+	void *tmp;
+	size_t be_sz = be->max_sz;
+
+retry:
+	if ((be->cur_pos + sz) < be_sz) {
+		memcpy(be->data + be->cur_pos, addr, sz);
+		be->cur_pos += sz;
+		return 0;
+	}
+
+	if (!be_sz)
+		be_sz = BUFFER_EXT_DFL_SIZE;
+	else
+		be_sz <<= 1;
+
+	tmp = realloc(be->data, be_sz);
+	if (!tmp)
+		return -1;
+
+	be->data   = tmp;
+	be->max_sz = be_sz;
+
+	goto retry;
+}
+
+static void
+buffer_ext_init(struct buffer_ext *be)
+{
+	be->data = NULL;
+	be->cur_pos = 0;
+	be->max_sz = 0;
+}
+
+static inline size_t
+buffer_ext_size(struct buffer_ext *be)
+{
+	return be->cur_pos;
+}
+
+static inline void *
+buffer_ext_addr(struct buffer_ext *be)
+{
+	return be->data;
+}
+
+struct debug_line_header {
+	// Not counting this field
+	uword total_length;
+	// version number (2 currently)
+	uhalf version;
+	// relative offset from next field to
+	// program statement
+	uword prolog_length;
+	ubyte minimum_instruction_length;
+	ubyte default_is_stmt;
+	// line_base - see DWARF 2 specs
+	sbyte line_base;
+	// line_range - see DWARF 2 specs
+	ubyte line_range;
+	// number of opcode + 1
+	ubyte opcode_base;
+	/* follow the array of opcode args nr: ubytes [nr_opcode_base] */
+	/* follow the search directories index, zero terminated string
+	 * terminated by an empty string.
+	 */
+	/* follow an array of { filename, LEB128, LEB128, LEB128 }, first is
+	 * the directory index entry, 0 means current directory, then mtime
+	 * and filesize, last entry is followed by en empty string.
+	 */
+	/* follow the first program statement */
+} __attribute__((packed));
+
+/* DWARF 2 spec talk only about one possible compilation unit header while
+ * binutils can handle two flavours of dwarf 2, 32 and 64 bits, this is not
+ * related to the used arch, an ELF 32 can hold more than 4 Go of debug
+ * information. For now we handle only DWARF 2 32 bits comp unit. It'll only
+ * become a problem if we generate more than 4GB of debug information.
+ */
+struct compilation_unit_header {
+	uword total_length;
+	uhalf version;
+	uword debug_abbrev_offset;
+	ubyte pointer_size;
+} __attribute__((packed));
+
+#define DW_LNS_num_opcode (DW_LNS_set_isa + 1)
+
+/* field filled at run time are marked with -1 */
+static struct debug_line_header const default_debug_line_header = {
+	.total_length = -1,
+	.version = 2,
+	.prolog_length = -1,
+	.minimum_instruction_length = 1,	/* could be better when min instruction size != 1 */
+	.default_is_stmt = 1,	/* we don't take care about basic block */
+	.line_base = -5,	/* sensible value for line base ... */
+	.line_range = -14,     /* ... and line range are guessed statically */
+	.opcode_base = DW_LNS_num_opcode
+};
+
+static ubyte standard_opcode_length[] =
+{
+	0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1
+};
+#if 0
+{
+	[DW_LNS_advance_pc]   = 1,
+	[DW_LNS_advance_line] = 1,
+	[DW_LNS_set_file] =  1,
+	[DW_LNS_set_column] = 1,
+	[DW_LNS_fixed_advance_pc] = 1,
+	[DW_LNS_set_isa] = 1,
+};
+#endif
+
+/* field filled at run time are marked with -1 */
+static struct compilation_unit_header default_comp_unit_header = {
+	.total_length = -1,
+	.version = 2,
+	.debug_abbrev_offset = 0,     /* we reuse the same abbrev entries for all comp unit */
+	.pointer_size = sizeof(void *)
+};
+
+static void emit_uword(struct buffer_ext *be, uword data)
+{
+	buffer_ext_add(be, &data, sizeof(uword));
+}
+
+static void emit_string(struct buffer_ext *be, const char *s)
+{
+	buffer_ext_add(be, (void *)s, strlen(s) + 1);
+}
+
+static void emit_unsigned_LEB128(struct buffer_ext *be,
+				 unsigned long data)
+{
+	do {
+		ubyte cur = data & 0x7F;
+		data >>= 7;
+		if (data)
+			cur |= 0x80;
+		buffer_ext_add(be, &cur, 1);
+	} while (data);
+}
+
+static void emit_signed_LEB128(struct buffer_ext *be, long data)
+{
+	int more = 1;
+	int negative = data < 0;
+	int size = sizeof(long) * CHAR_BIT;
+	while (more) {
+		ubyte cur = data & 0x7F;
+		data >>= 7;
+		if (negative)
+			data |= - (1 << (size - 7));
+		if ((data == 0 && !(cur & 0x40)) ||
+		    (data == -1l && (cur & 0x40)))
+			more = 0;
+		else
+			cur |= 0x80;
+		buffer_ext_add(be, &cur, 1);
+	}
+}
+
+static void emit_extended_opcode(struct buffer_ext *be, ubyte opcode,
+				 void *data, size_t data_len)
+{
+	buffer_ext_add(be, (char *)"", 1);
+
+	emit_unsigned_LEB128(be, data_len + 1);
+
+	buffer_ext_add(be, &opcode, 1);
+	buffer_ext_add(be, data, data_len);
+}
+
+static void emit_opcode(struct buffer_ext *be, ubyte opcode)
+{
+	buffer_ext_add(be, &opcode, 1);
+}
+
+static void emit_opcode_signed(struct buffer_ext  *be,
+			       ubyte opcode, long data)
+{
+	buffer_ext_add(be, &opcode, 1);
+	emit_signed_LEB128(be, data);
+}
+
+static void emit_opcode_unsigned(struct buffer_ext *be, ubyte opcode,
+				 unsigned long data)
+{
+	buffer_ext_add(be, &opcode, 1);
+	emit_unsigned_LEB128(be, data);
+}
+
+static void emit_advance_pc(struct buffer_ext *be, unsigned long delta_pc)
+{
+	emit_opcode_unsigned(be, DW_LNS_advance_pc, delta_pc);
+}
+
+static void emit_advance_lineno(struct buffer_ext  *be, long delta_lineno)
+{
+	emit_opcode_signed(be, DW_LNS_advance_line, delta_lineno);
+}
+
+static void emit_lne_end_of_sequence(struct buffer_ext *be)
+{
+	emit_extended_opcode(be, DW_LNE_end_sequence, NULL, 0);
+}
+
+static void emit_set_file(struct buffer_ext *be, unsigned long idx)
+{
+	emit_opcode_unsigned(be, DW_LNS_set_file, idx);
+}
+
+static void emit_lne_define_filename(struct buffer_ext *be,
+				     const char *filename)
+{
+	buffer_ext_add(be, (void *)"", 1);
+
+	/* LNE field, strlen(filename) + zero termination, 3 bytes for: the dir entry, timestamp, filesize */
+	emit_unsigned_LEB128(be, strlen(filename) + 5);
+	emit_opcode(be, DW_LNE_define_file);
+	emit_string(be, filename);
+	/* directory index 0=do not know */
+        emit_unsigned_LEB128(be, 0);
+	/* last modification date on file 0=do not know */
+        emit_unsigned_LEB128(be, 0);
+	/* filesize 0=do not know */
+        emit_unsigned_LEB128(be, 0);
+}
+
+static void emit_lne_set_address(struct buffer_ext *be,
+				 void *address)
+{
+	emit_extended_opcode(be, DW_LNE_set_address, &address, sizeof(unsigned long));
+}
+
+static ubyte get_special_opcode(struct debug_entry *ent,
+				unsigned int last_line,
+				unsigned long last_vma)
+{
+	unsigned int temp;
+	unsigned long delta_addr;
+
+	/*
+	 * delta from line_base
+	 */
+	temp = (ent->lineno - last_line) - default_debug_line_header.line_base;
+
+	if (temp >= default_debug_line_header.line_range)
+		return 0;
+
+	/*
+	 * delta of addresses
+	 */
+	delta_addr = (ent->addr - last_vma) / default_debug_line_header.minimum_instruction_length;
+
+	/* This is not sufficient to ensure opcode will be in [0-256] but
+	 * sufficient to ensure when summing with the delta lineno we will
+	 * not overflow the unsigned long opcode */
+
+	if (delta_addr <= 256 / default_debug_line_header.line_range) {
+		unsigned long opcode = temp +
+			(delta_addr * default_debug_line_header.line_range) +
+			default_debug_line_header.opcode_base;
+
+		return opcode <= 255 ? opcode : 0;
+	}
+	return 0;
+}
+
+static void emit_lineno_info(struct buffer_ext *be,
+			     struct debug_entry *ent, size_t nr_entry,
+			     unsigned long code_addr)
+{
+	size_t i;
+
+	/*
+	 * Machine state at start of a statement program
+	 * address = 0
+	 * file    = 1
+	 * line    = 1
+	 * column  = 0
+	 * is_stmt = default_is_stmt as given in the debug_line_header
+	 * basic block = 0
+	 * end sequence = 0
+	 */
+
+	/* start state of the state machine we take care of */
+	unsigned long last_vma = code_addr;
+	char const  *cur_filename = NULL;
+	unsigned long cur_file_idx = 0;
+	int last_line = 1;
+
+	emit_lne_set_address(be, (void *)code_addr);
+
+	for (i = 0; i < nr_entry; i++, ent = debug_entry_next(ent)) {
+		int need_copy = 0;
+		ubyte special_opcode;
+
+		/*
+		 * check if filename changed, if so add it
+		 */
+		if (!cur_filename || strcmp(cur_filename, ent->name)) {
+			emit_lne_define_filename(be, ent->name);
+			cur_filename = ent->name;
+			emit_set_file(be, ++cur_file_idx);
+			need_copy = 1;
+		}
+
+		special_opcode = get_special_opcode(ent, last_line, last_vma);
+		if (special_opcode != 0) {
+			last_line = ent->lineno;
+			last_vma  = ent->addr;
+			emit_opcode(be, special_opcode);
+		} else {
+			/*
+			 * lines differ, emit line delta
+			 */
+			if (last_line != ent->lineno) {
+				emit_advance_lineno(be, ent->lineno - last_line);
+				last_line = ent->lineno;
+				need_copy = 1;
+			}
+			/*
+			 * addresses differ, emit address delta
+			 */
+			if (last_vma != ent->addr) {
+				emit_advance_pc(be, ent->addr - last_vma);
+				last_vma = ent->addr;
+				need_copy = 1;
+			}
+			/*
+			 * add new row to matrix
+			 */
+			if (need_copy)
+				emit_opcode(be, DW_LNS_copy);
+		}
+	}
+}
+
+static void add_debug_line(struct buffer_ext *be,
+	struct debug_entry *ent, size_t nr_entry,
+	unsigned long code_addr)
+{
+	struct debug_line_header * dbg_header;
+	size_t old_size;
+
+	old_size = buffer_ext_size(be);
+
+	buffer_ext_add(be, (void *)&default_debug_line_header,
+		 sizeof(default_debug_line_header));
+
+	buffer_ext_add(be, &standard_opcode_length,  sizeof(standard_opcode_length));
+
+	// empty directory entry
+	buffer_ext_add(be, (void *)"", 1);
+
+	// empty filename directory
+	buffer_ext_add(be, (void *)"", 1);
+
+	dbg_header = buffer_ext_addr(be) + old_size;
+	dbg_header->prolog_length = (buffer_ext_size(be) - old_size) -
+		offsetof(struct debug_line_header, minimum_instruction_length);
+
+	emit_lineno_info(be, ent, nr_entry, code_addr);
+
+	emit_lne_end_of_sequence(be);
+
+	dbg_header = buffer_ext_addr(be) + old_size;
+	dbg_header->total_length = (buffer_ext_size(be) - old_size) -
+		offsetof(struct debug_line_header, version);
+}
+
+static void
+add_debug_abbrev(struct buffer_ext *be)
+{
+        emit_unsigned_LEB128(be, 1);
+        emit_unsigned_LEB128(be, DW_TAG_compile_unit);
+        emit_unsigned_LEB128(be, DW_CHILDREN_yes);
+        emit_unsigned_LEB128(be, DW_AT_stmt_list);
+        emit_unsigned_LEB128(be, DW_FORM_data4);
+        emit_unsigned_LEB128(be, 0);
+        emit_unsigned_LEB128(be, 0);
+        emit_unsigned_LEB128(be, 0);
+}
+
+static void
+add_compilation_unit(struct buffer_ext *be,
+		     size_t offset_debug_line)
+{
+	struct compilation_unit_header *comp_unit_header;
+	size_t old_size = buffer_ext_size(be);
+
+	buffer_ext_add(be, &default_comp_unit_header,
+		       sizeof(default_comp_unit_header));
+
+	emit_unsigned_LEB128(be, 1);
+	emit_uword(be, offset_debug_line);
+
+	comp_unit_header = buffer_ext_addr(be) + old_size;
+	comp_unit_header->total_length = (buffer_ext_size(be) - old_size) -
+		offsetof(struct compilation_unit_header, version);
+}
+
+static int
+jit_process_debug_info(uint64_t code_addr,
+		       void *debug, int nr_debug_entries,
+		       struct buffer_ext *dl,
+		       struct buffer_ext *da,
+		       struct buffer_ext *di)
+{
+	struct debug_entry *ent = debug;
+	int i;
+
+	for (i = 0; i < nr_debug_entries; i++) {
+		ent->addr = ent->addr - code_addr;
+		ent = debug_entry_next(ent);
+	}
+	add_compilation_unit(di, buffer_ext_size(dl));
+	add_debug_line(dl, debug, nr_debug_entries, 0);
+	add_debug_abbrev(da);
+	if (0) buffer_ext_dump(da, "abbrev");
+
+	return 0;
+}
+
+int
+jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_entries)
+{
+	Elf_Data *d;
+	Elf_Scn *scn;
+	Elf_Shdr *shdr;
+	struct buffer_ext dl, di, da;
+	int ret;
+
+	buffer_ext_init(&dl);
+	buffer_ext_init(&di);
+	buffer_ext_init(&da);
+
+	ret = jit_process_debug_info(code_addr, debug, nr_debug_entries, &dl, &da, &di);
+	if (ret)
+		return -1;
+	/*
+	 * setup .debug_line section
+	 */
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		return -1;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		return -1;
+	}
+
+	d->d_align = 1;
+	d->d_off = 0LL;
+	d->d_buf = buffer_ext_addr(&dl);
+	d->d_type = ELF_T_BYTE;
+	d->d_size = buffer_ext_size(&dl);
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		return -1;
+	}
+
+	shdr->sh_name = 52; /* .debug_line */
+	shdr->sh_type = SHT_PROGBITS;
+	shdr->sh_addr = 0; /* must be zero or == sh_offset -> dynamic object */
+	shdr->sh_flags = 0;
+	shdr->sh_entsize = 0;
+
+	/*
+	 * setup .debug_info section
+	 */
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		return -1;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		return -1;
+	}
+
+	d->d_align = 1;
+	d->d_off = 0LL;
+	d->d_buf = buffer_ext_addr(&di);
+	d->d_type = ELF_T_BYTE;
+	d->d_size = buffer_ext_size(&di);
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		return -1;
+	}
+
+	shdr->sh_name = 64; /* .debug_info */
+	shdr->sh_type = SHT_PROGBITS;
+	shdr->sh_addr = 0; /* must be zero or == sh_offset -> dynamic object */
+	shdr->sh_flags = 0;
+	shdr->sh_entsize = 0;
+
+	/*
+	 * setup .debug_abbrev section
+	 */
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		return -1;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		return -1;
+	}
+
+	d->d_align = 1;
+	d->d_off = 0LL;
+	d->d_buf = buffer_ext_addr(&da);
+	d->d_type = ELF_T_BYTE;
+	d->d_size = buffer_ext_size(&da);
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		return -1;
+	}
+
+	shdr->sh_name = 76; /* .debug_info */
+	shdr->sh_type = SHT_PROGBITS;
+	shdr->sh_addr = 0; /* must be zero or == sh_offset -> dynamic object */
+	shdr->sh_flags = 0;
+	shdr->sh_entsize = 0;
+
+	/*
+	 * now we update the ELF image with all the sections
+	 */
+	if (elf_update(e, ELF_C_WRITE) < 0) {
+		warnx("elf_update debug failed");
+		return -1;
+	}
+	return 0;
+}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index f50b7235e..90680ec9f 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -23,6 +23,8 @@
 #include "strbuf.h"
 #include "build-id.h"
 #include "data.h"
+#include <api/fs/fs.h>
+#include "asm/bug.h"
 
 /*
  * magic2 = "PERFILE2"
@@ -868,6 +870,199 @@ static int write_auxtrace(int fd, struct perf_header *h,
 	return err;
 }
 
+static int cpu_cache_level__sort(const void *a, const void *b)
+{
+	struct cpu_cache_level *cache_a = (struct cpu_cache_level *)a;
+	struct cpu_cache_level *cache_b = (struct cpu_cache_level *)b;
+
+	return cache_a->level - cache_b->level;
+}
+
+static bool cpu_cache_level__cmp(struct cpu_cache_level *a, struct cpu_cache_level *b)
+{
+	if (a->level != b->level)
+		return false;
+
+	if (a->line_size != b->line_size)
+		return false;
+
+	if (a->sets != b->sets)
+		return false;
+
+	if (a->ways != b->ways)
+		return false;
+
+	if (strcmp(a->type, b->type))
+		return false;
+
+	if (strcmp(a->size, b->size))
+		return false;
+
+	if (strcmp(a->map, b->map))
+		return false;
+
+	return true;
+}
+
+static int cpu_cache_level__read(struct cpu_cache_level *cache, u32 cpu, u16 level)
+{
+	char path[PATH_MAX], file[PATH_MAX];
+	struct stat st;
+	size_t len;
+
+	scnprintf(path, PATH_MAX, "devices/system/cpu/cpu%d/cache/index%d/", cpu, level);
+	scnprintf(file, PATH_MAX, "%s/%s", sysfs__mountpoint(), path);
+
+	if (stat(file, &st))
+		return 1;
+
+	scnprintf(file, PATH_MAX, "%s/level", path);
+	if (sysfs__read_int(file, (int *) &cache->level))
+		return -1;
+
+	scnprintf(file, PATH_MAX, "%s/coherency_line_size", path);
+	if (sysfs__read_int(file, (int *) &cache->line_size))
+		return -1;
+
+	scnprintf(file, PATH_MAX, "%s/number_of_sets", path);
+	if (sysfs__read_int(file, (int *) &cache->sets))
+		return -1;
+
+	scnprintf(file, PATH_MAX, "%s/ways_of_associativity", path);
+	if (sysfs__read_int(file, (int *) &cache->ways))
+		return -1;
+
+	scnprintf(file, PATH_MAX, "%s/type", path);
+	if (sysfs__read_str(file, &cache->type, &len))
+		return -1;
+
+	cache->type[len] = 0;
+	cache->type = rtrim(cache->type);
+
+	scnprintf(file, PATH_MAX, "%s/size", path);
+	if (sysfs__read_str(file, &cache->size, &len)) {
+		free(cache->type);
+		return -1;
+	}
+
+	cache->size[len] = 0;
+	cache->size = rtrim(cache->size);
+
+	scnprintf(file, PATH_MAX, "%s/shared_cpu_list", path);
+	if (sysfs__read_str(file, &cache->map, &len)) {
+		free(cache->map);
+		free(cache->type);
+		return -1;
+	}
+
+	cache->map[len] = 0;
+	cache->map = rtrim(cache->map);
+	return 0;
+}
+
+static void cpu_cache_level__fprintf(FILE *out, struct cpu_cache_level *c)
+{
+	fprintf(out, "L%d %-15s %8s [%s]\n", c->level, c->type, c->size, c->map);
+}
+
+static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp)
+{
+	u32 i, cnt = 0;
+	long ncpus;
+	u32 nr, cpu;
+	u16 level;
+
+	ncpus = sysconf(_SC_NPROCESSORS_CONF);
+	if (ncpus < 0)
+		return -1;
+
+	nr = (u32)(ncpus & UINT_MAX);
+
+	for (cpu = 0; cpu < nr; cpu++) {
+		for (level = 0; level < 10; level++) {
+			struct cpu_cache_level c;
+			int err;
+
+			err = cpu_cache_level__read(&c, cpu, level);
+			if (err < 0)
+				return err;
+
+			if (err == 1)
+				break;
+
+			for (i = 0; i < cnt; i++) {
+				if (cpu_cache_level__cmp(&c, &caches[i]))
+					break;
+			}
+
+			if (i == cnt)
+				caches[cnt++] = c;
+			else
+				cpu_cache_level__free(&c);
+
+			if (WARN_ONCE(cnt == size, "way too many cpu caches.."))
+				goto out;
+		}
+	}
+ out:
+	*cntp = cnt;
+	return 0;
+}
+
+#define MAX_CACHES 2000
+
+static int write_cache(int fd, struct perf_header *h __maybe_unused,
+			  struct perf_evlist *evlist __maybe_unused)
+{
+	struct cpu_cache_level caches[MAX_CACHES];
+	u32 cnt = 0, i, version = 1;
+	int ret;
+
+	ret = build_caches(caches, MAX_CACHES, &cnt);
+	if (ret)
+		goto out;
+
+	qsort(&caches, cnt, sizeof(struct cpu_cache_level), cpu_cache_level__sort);
+
+	ret = do_write(fd, &version, sizeof(u32));
+	if (ret < 0)
+		goto out;
+
+	ret = do_write(fd, &cnt, sizeof(u32));
+	if (ret < 0)
+		goto out;
+
+	for (i = 0; i < cnt; i++) {
+		struct cpu_cache_level *c = &caches[i];
+
+		#define _W(v)					\
+			ret = do_write(fd, &c->v, sizeof(u32));	\
+			if (ret < 0)				\
+				goto out;
+
+		_W(level)
+		_W(line_size)
+		_W(sets)
+		_W(ways)
+		#undef _W
+
+		#define _W(v)						\
+			ret = do_write_string(fd, (const char *) c->v);	\
+			if (ret < 0)					\
+				goto out;
+
+		_W(type)
+		_W(size)
+		_W(map)
+		#undef _W
+	}
+
+out:
+	for (i = 0; i < cnt; i++)
+		cpu_cache_level__free(&caches[i]);
+	return ret;
+}
+
 static int write_stat(int fd __maybe_unused,
 		      struct perf_header *h __maybe_unused,
 		      struct perf_evlist *evlist __maybe_unused)
@@ -1172,6 +1367,18 @@ static void print_stat(struct perf_header *ph __maybe_unused,
 	fprintf(fp, "# contains stat data\n");
 }
 
+static void print_cache(struct perf_header *ph __maybe_unused,
+			int fd __maybe_unused, FILE *fp __maybe_unused)
+{
+	int i;
+
+	fprintf(fp, "# CPU cache info:\n");
+	for (i = 0; i < ph->env.caches_cnt; i++) {
+		fprintf(fp, "#  ");
+		cpu_cache_level__fprintf(fp, &ph->env.caches[i]);
+	}
+}
+
 static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
 			       FILE *fp)
 {
@@ -1665,11 +1872,6 @@ static int process_cpu_topology(struct perf_file_section *section,
 		if (ph->needs_swap)
 			nr = bswap_32(nr);
 
-		if (nr > (u32)cpu_nr) {
-			pr_debug("core_id number is too big."
-				 "You may need to upgrade the perf tool.\n");
-			goto free_cpu;
-		}
 		ph->env.cpu[i].core_id = nr;
 
 		ret = readn(fd, &nr, sizeof(nr));
@@ -1920,6 +2122,68 @@ static int process_auxtrace(struct perf_file_section *section,
 	return err;
 }
 
+static int process_cache(struct perf_file_section *section __maybe_unused,
+			 struct perf_header *ph __maybe_unused, int fd __maybe_unused,
+			 void *data __maybe_unused)
+{
+	struct cpu_cache_level *caches;
+	u32 cnt, i, version;
+
+	if (readn(fd, &version, sizeof(version)) != sizeof(version))
+		return -1;
+
+	if (ph->needs_swap)
+		version = bswap_32(version);
+
+	if (version != 1)
+		return -1;
+
+	if (readn(fd, &cnt, sizeof(cnt)) != sizeof(cnt))
+		return -1;
+
+	if (ph->needs_swap)
+		cnt = bswap_32(cnt);
+
+	caches = zalloc(sizeof(*caches) * cnt);
+	if (!caches)
+		return -1;
+
+	for (i = 0; i < cnt; i++) {
+		struct cpu_cache_level c;
+
+		#define _R(v)						\
+			if (readn(fd, &c.v, sizeof(u32)) != sizeof(u32))\
+				goto out_free_caches;			\
+			if (ph->needs_swap)				\
+				c.v = bswap_32(c.v);			\
+
+		_R(level)
+		_R(line_size)
+		_R(sets)
+		_R(ways)
+		#undef _R
+
+		#define _R(v)				\
+			c.v = do_read_string(fd, ph);	\
+			if (!c.v)			\
+				goto out_free_caches;
+
+		_R(type)
+		_R(size)
+		_R(map)
+		#undef _R
+
+		caches[i] = c;
+	}
+
+	ph->env.caches = caches;
+	ph->env.caches_cnt = cnt;
+	return 0;
+out_free_caches:
+	free(caches);
+	return -1;
+}
+
 struct feature_ops {
 	int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
 	void (*print)(struct perf_header *h, int fd, FILE *fp);
@@ -1962,6 +2226,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPP(HEADER_GROUP_DESC,	group_desc),
 	FEAT_OPP(HEADER_AUXTRACE,	auxtrace),
 	FEAT_OPA(HEADER_STAT,		stat),
+	FEAT_OPF(HEADER_CACHE,		cache),
 };
 
 struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index cff989245..d306ca118 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -32,6 +32,7 @@ enum {
 	HEADER_GROUP_DESC,
 	HEADER_AUXTRACE,
 	HEADER_STAT,
+	HEADER_CACHE,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
@@ -120,7 +121,7 @@ int perf_event__synthesize_event_update_cpus(struct perf_tool *tool,
 					     perf_event__handler_t process);
 int perf_event__process_attr(struct perf_tool *tool, union perf_event *event,
 			     struct perf_evlist **pevlist);
-int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
+int perf_event__process_event_update(struct perf_tool *tool,
 				     union perf_event *event,
 				     struct perf_evlist **pevlist);
 size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp);
diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c
index dc1e41c9b..43a98a4dc 100644
--- a/tools/perf/util/help-unknown-cmd.c
+++ b/tools/perf/util/help-unknown-cmd.c
@@ -6,7 +6,8 @@
 static int autocorrect;
 static struct cmdnames aliases;
 
-static int perf_unknown_cmd_config(const char *var, const char *value, void *cb)
+static int perf_unknown_cmd_config(const char *var, const char *value,
+				   void *cb __maybe_unused)
 {
 	if (!strcmp(var, "help.autocorrect"))
 		autocorrect = perf_config_int(var,value);
@@ -14,7 +15,7 @@ static int perf_unknown_cmd_config(const char *var, const char *value, void *cb)
 	if (!prefixcmp(var, "alias."))
 		add_cmdname(&aliases, var + 6, strlen(var + 6));
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 static int levenshtein_compare(const void *p1, const void *p2)
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 68a761201..31c4641fe 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -179,6 +179,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	if (h->transaction)
 		hists__new_col_len(hists, HISTC_TRANSACTION,
 				   hist_entry__transaction_len());
+
+	if (h->trace_output)
+		hists__new_col_len(hists, HISTC_TRACE, strlen(h->trace_output));
 }
 
 void hists__output_recalc_col_len(struct hists *hists, int max_rows)
@@ -245,6 +248,8 @@ static void he_stat__decay(struct he_stat *he_stat)
 	/* XXX need decay for weight too? */
 }
 
+static void hists__delete_entry(struct hists *hists, struct hist_entry *he);
+
 static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 {
 	u64 prev_period = he->stat.period;
@@ -260,21 +265,45 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 
 	diff = prev_period - he->stat.period;
 
-	hists->stats.total_period -= diff;
-	if (!he->filtered)
-		hists->stats.total_non_filtered_period -= diff;
+	if (!he->depth) {
+		hists->stats.total_period -= diff;
+		if (!he->filtered)
+			hists->stats.total_non_filtered_period -= diff;
+	}
+
+	if (!he->leaf) {
+		struct hist_entry *child;
+		struct rb_node *node = rb_first(&he->hroot_out);
+		while (node) {
+			child = rb_entry(node, struct hist_entry, rb_node);
+			node = rb_next(node);
+
+			if (hists__decay_entry(hists, child))
+				hists__delete_entry(hists, child);
+		}
+	}
 
 	return he->stat.period == 0;
 }
 
 static void hists__delete_entry(struct hists *hists, struct hist_entry *he)
 {
-	rb_erase(&he->rb_node, &hists->entries);
+	struct rb_root *root_in;
+	struct rb_root *root_out;
 
-	if (sort__need_collapse)
-		rb_erase(&he->rb_node_in, &hists->entries_collapsed);
-	else
-		rb_erase(&he->rb_node_in, hists->entries_in);
+	if (he->parent_he) {
+		root_in  = &he->parent_he->hroot_in;
+		root_out = &he->parent_he->hroot_out;
+	} else {
+		if (sort__need_collapse)
+			root_in = &hists->entries_collapsed;
+		else
+			root_in = hists->entries_in;
+		root_out = &hists->entries;
+	}
+
+	rb_erase(&he->rb_node_in, root_in);
+	rb_erase(&he->rb_node, root_out);
 
 	--hists->nr_entries;
 	if (!he->filtered)
@@ -393,6 +422,9 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
 		}
 		INIT_LIST_HEAD(&he->pairs.node);
 		thread__get(he->thread);
+
+		if (!symbol_conf.report_hierarchy)
+			he->leaf = true;
 	}
 
 	return he;
@@ -405,6 +437,16 @@ static u8 symbol__parent_filter(const struct symbol *parent)
 	return 0;
 }
 
+static void hist_entry__add_callchain_period(struct hist_entry *he, u64 period)
+{
+	if (!symbol_conf.use_callchain)
+		return;
+
+	he->hists->callchain_period += period;
+	if (!he->filtered)
+		he->hists->callchain_non_filtered_period += period;
+}
+
 static struct hist_entry *hists__findnew_entry(struct hists *hists,
 					       struct hist_entry *entry,
 					       struct addr_location *al,
@@ -432,8 +474,10 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 		cmp = hist_entry__cmp(he, entry);
 
 		if (!cmp) {
-			if (sample_self)
+			if (sample_self) {
 				he_stat__add_period(&he->stat, period, weight);
+				hist_entry__add_callchain_period(he, period);
+			}
 			if (symbol_conf.cumulate_callchain)
 				he_stat__add_period(he->stat_acc, period, weight);
 
@@ -466,6 +510,8 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 	if (!he)
 		return NULL;
 
+	if (sample_self)
+		hist_entry__add_callchain_period(he, period);
 	hists->nr_entries++;
 
 	rb_link_node(&he->rb_node_in, parent, p);
@@ -624,7 +670,7 @@ iter_prepare_branch_entry(struct hist_entry_iter *iter, struct addr_location *al
 }
 
 static int
-iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused,
+iter_add_single_branch_entry(struct hist_entry_iter *iter,
 			     struct addr_location *al __maybe_unused)
 {
 	/* to avoid calling callback function */
@@ -951,10 +997,15 @@ out:
 int64_t
 hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
 {
+	struct hists *hists = left->hists;
 	struct perf_hpp_fmt *fmt;
 	int64_t cmp = 0;
 
-	perf_hpp__for_each_sort_list(fmt) {
+	hists__for_each_sort_list(hists, fmt) {
+		if (perf_hpp__is_dynamic_entry(fmt) &&
+		    !perf_hpp__defined_dynamic_entry(fmt, hists))
+			continue;
+
 		cmp = fmt->cmp(fmt, left, right);
 		if (cmp)
 			break;
@@ -966,10 +1017,15 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
 int64_t
 hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 {
+	struct hists *hists = left->hists;
 	struct perf_hpp_fmt *fmt;
 	int64_t cmp = 0;
 
-	perf_hpp__for_each_sort_list(fmt) {
+	hists__for_each_sort_list(hists, fmt) {
+		if (perf_hpp__is_dynamic_entry(fmt) &&
+		    !perf_hpp__defined_dynamic_entry(fmt, hists))
+			continue;
+
 		cmp = fmt->collapse(fmt, left, right);
 		if (cmp)
 			break;
@@ -1006,17 +1062,250 @@ void hist_entry__delete(struct hist_entry *he)
 }
 
 /*
+ * If this is not the last column, then we need to pad it according to the
+ * pre-calculated max lenght for this column, otherwise don't bother adding
+ * spaces because that would break viewing this with, for instance, 'less',
+ * that would show tons of trailing spaces when a long C++ demangled method
+ * names is sampled.
+*/
+int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
+				   struct perf_hpp_fmt *fmt, int printed)
+{
+	if (!list_is_last(&fmt->list, &he->hists->hpp_list->fields)) {
+		const int width = fmt->width(fmt, hpp, hists_to_evsel(he->hists));
+		if (printed < width) {
+			advance_hpp(hpp, printed);
+			printed = scnprintf(hpp->buf, hpp->size, "%-*s", width - printed, " ");
+		}
+	}
+
+	return printed;
+}
+
+/*
  * collapse the histogram
  */
 
-bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
-				  struct rb_root *root, struct hist_entry *he)
+static void hists__apply_filters(struct hists *hists, struct hist_entry *he);
+static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *he,
+				       enum hist_filter type);
+
+typedef bool (*fmt_chk_fn)(struct perf_hpp_fmt *fmt);
+
+static bool check_thread_entry(struct perf_hpp_fmt *fmt)
+{
+	return perf_hpp__is_thread_entry(fmt) || perf_hpp__is_comm_entry(fmt);
+}
+
+static void hist_entry__check_and_remove_filter(struct hist_entry *he,
+						enum hist_filter type,
+						fmt_chk_fn check)
+{
+	struct perf_hpp_fmt *fmt;
+	bool type_match = false;
+	struct hist_entry *parent = he->parent_he;
+
+	switch (type) {
+	case HIST_FILTER__THREAD:
+		if (symbol_conf.comm_list == NULL &&
+		    symbol_conf.pid_list == NULL &&
+		    symbol_conf.tid_list == NULL)
+			return;
+		break;
+	case HIST_FILTER__DSO:
+		if (symbol_conf.dso_list == NULL)
+			return;
+		break;
+	case HIST_FILTER__SYMBOL:
+		if (symbol_conf.sym_list == NULL)
+			return;
+		break;
+	case HIST_FILTER__PARENT:
+	case HIST_FILTER__GUEST:
+	case HIST_FILTER__HOST:
+	case HIST_FILTER__SOCKET:
+	default:
+		return;
+	}
+
+	/* if it's filtered by own fmt, it has to have filter bits */
+	perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+		if (check(fmt)) {
+			type_match = true;
+			break;
+		}
+	}
+
+	if (type_match) {
+		/*
+		 * If the filter is for current level entry, propagate
+		 * filter marker to parents.  The marker bit was
+		 * already set by default so it only needs to clear
+		 * non-filtered entries.
+		 */
+		if (!(he->filtered & (1 << type))) {
+			while (parent) {
+				parent->filtered &= ~(1 << type);
+				parent = parent->parent_he;
+			}
+		}
+	} else {
+		/*
+		 * If current entry doesn't have matching formats, set
+		 * filter marker for upper level entries.  it will be
+		 * cleared if its lower level entries is not filtered.
+		 *
+		 * For lower-level entries, it inherits parent's
+		 * filter bit so that lower level entries of a
+		 * non-filtered entry won't set the filter marker.
+		 */
+		if (parent == NULL)
+			he->filtered |= (1 << type);
+		else
+			he->filtered |= (parent->filtered & (1 << type));
+	}
+}
+
+static void hist_entry__apply_hierarchy_filters(struct hist_entry *he)
+{
+	hist_entry__check_and_remove_filter(he, HIST_FILTER__THREAD,
+					    check_thread_entry);
+
+	hist_entry__check_and_remove_filter(he, HIST_FILTER__DSO,
+					    perf_hpp__is_dso_entry);
+
+	hist_entry__check_and_remove_filter(he, HIST_FILTER__SYMBOL,
+					    perf_hpp__is_sym_entry);
+
+	hists__apply_filters(he->hists, he);
+}
+
+static struct hist_entry *hierarchy_insert_entry(struct hists *hists,
+						 struct rb_root *root,
+						 struct hist_entry *he,
+						 struct hist_entry *parent_he,
+						 struct perf_hpp_list *hpp_list)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *iter, *new;
+	struct perf_hpp_fmt *fmt;
+	int64_t cmp;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct hist_entry, rb_node_in);
+
+		cmp = 0;
+		perf_hpp_list__for_each_sort_list(hpp_list, fmt) {
+			cmp = fmt->collapse(fmt, iter, he);
+			if (cmp)
+				break;
+		}
+
+		if (!cmp) {
+			he_stat__add_stat(&iter->stat, &he->stat);
+			return iter;
+		}
+
+		if (cmp < 0)
+			p = &parent->rb_left;
+		else
+			p = &parent->rb_right;
+	}
+
+	new = hist_entry__new(he, true);
+	if (new == NULL)
+		return NULL;
+
+	hists->nr_entries++;
+
+	/* save related format list for output */
+	new->hpp_list = hpp_list;
+	new->parent_he = parent_he;
+
+	hist_entry__apply_hierarchy_filters(new);
+
+	/* some fields are now passed to 'new' */
+	perf_hpp_list__for_each_sort_list(hpp_list, fmt) {
+		if (perf_hpp__is_trace_entry(fmt) || perf_hpp__is_dynamic_entry(fmt))
+			he->trace_output = NULL;
+		else
+			new->trace_output = NULL;
+
+		if (perf_hpp__is_srcline_entry(fmt))
+			he->srcline = NULL;
+		else
+			new->srcline = NULL;
+
+		if (perf_hpp__is_srcfile_entry(fmt))
+			he->srcfile = NULL;
+		else
+			new->srcfile = NULL;
+	}
+
+	rb_link_node(&new->rb_node_in, parent, p);
+	rb_insert_color(&new->rb_node_in, root);
+	return new;
+}
+
+static int hists__hierarchy_insert_entry(struct hists *hists,
+					 struct rb_root *root,
+					 struct hist_entry *he)
+{
+	struct perf_hpp_list_node *node;
+	struct hist_entry *new_he = NULL;
+	struct hist_entry *parent = NULL;
+	int depth = 0;
+	int ret = 0;
+
+	list_for_each_entry(node, &hists->hpp_formats, list) {
+		/* skip period (overhead) and elided columns */
+		if (node->level == 0 || node->skip)
+			continue;
+
+		/* insert copy of 'he' for each fmt into the hierarchy */
+		new_he = hierarchy_insert_entry(hists, root, he, parent, &node->hpp);
+		if (new_he == NULL) {
+			ret = -1;
+			break;
+		}
+
+		root = &new_he->hroot_in;
+		new_he->depth = depth++;
+		parent = new_he;
+	}
+
+	if (new_he) {
+		new_he->leaf = true;
+
+		if (symbol_conf.use_callchain) {
+			callchain_cursor_reset(&callchain_cursor);
+			if (callchain_merge(&callchain_cursor,
+					    new_he->callchain,
+					    he->callchain) < 0)
+				ret = -1;
+		}
+	}
+
+	/* 'he' is no longer used */
+	hist_entry__delete(he);
+
+	/* return 0 (or -1) since it already applied filters */
+	return ret;
+}
+
+int hists__collapse_insert_entry(struct hists *hists, struct rb_root *root,
+				 struct hist_entry *he)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
 	int64_t cmp;
 
+	if (symbol_conf.report_hierarchy)
+		return hists__hierarchy_insert_entry(hists, root, he);
+
 	while (*p != NULL) {
 		parent = *p;
 		iter = rb_entry(parent, struct hist_entry, rb_node_in);
@@ -1024,18 +1313,21 @@ bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
 		cmp = hist_entry__collapse(iter, he);
 
 		if (!cmp) {
+			int ret = 0;
+
 			he_stat__add_stat(&iter->stat, &he->stat);
 			if (symbol_conf.cumulate_callchain)
 				he_stat__add_stat(iter->stat_acc, he->stat_acc);
 
 			if (symbol_conf.use_callchain) {
 				callchain_cursor_reset(&callchain_cursor);
-				callchain_merge(&callchain_cursor,
-						iter->callchain,
-						he->callchain);
+				if (callchain_merge(&callchain_cursor,
+						    iter->callchain,
+						    he->callchain) < 0)
+					ret = -1;
 			}
 			hist_entry__delete(he);
-			return false;
+			return ret;
 		}
 
 		if (cmp < 0)
@@ -1047,7 +1339,7 @@ bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
 
 	rb_link_node(&he->rb_node_in, parent, p);
 	rb_insert_color(&he->rb_node_in, root);
-	return true;
+	return 1;
 }
 
 struct rb_root *hists__get_rotate_entries_in(struct hists *hists)
@@ -1073,14 +1365,15 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he)
 	hists__filter_entry_by_socket(hists, he);
 }
 
-void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
+int hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 {
 	struct rb_root *root;
 	struct rb_node *next;
 	struct hist_entry *n;
+	int ret;
 
 	if (!sort__need_collapse)
-		return;
+		return 0;
 
 	hists->nr_entries = 0;
 
@@ -1095,7 +1388,11 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 		next = rb_next(&n->rb_node_in);
 
 		rb_erase(&n->rb_node_in, root);
-		if (hists__collapse_insert_entry(hists, &hists->entries_collapsed, n)) {
+		ret = hists__collapse_insert_entry(hists, &hists->entries_collapsed, n);
+		if (ret < 0)
+			return -1;
+
+		if (ret) {
 			/*
 			 * If it wasn't combined with one of the entries already
 			 * collapsed, we need to apply the filters that may have
@@ -1106,14 +1403,16 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 		if (prog)
 			ui_progress__update(prog, 1);
 	}
+	return 0;
 }
 
 static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
 {
+	struct hists *hists = a->hists;
 	struct perf_hpp_fmt *fmt;
 	int64_t cmp = 0;
 
-	perf_hpp__for_each_sort_list(fmt) {
+	hists__for_each_sort_list(hists, fmt) {
 		if (perf_hpp__should_skip(fmt, a->hists))
 			continue;
 
@@ -1154,6 +1453,113 @@ void hists__inc_stats(struct hists *hists, struct hist_entry *h)
 	hists->stats.total_period += h->stat.period;
 }
 
+static void hierarchy_recalc_total_periods(struct hists *hists)
+{
+	struct rb_node *node;
+	struct hist_entry *he;
+
+	node = rb_first(&hists->entries);
+
+	hists->stats.total_period = 0;
+	hists->stats.total_non_filtered_period = 0;
+
+	/*
+	 * recalculate total period using top-level entries only
+	 * since lower level entries only see non-filtered entries
+	 * but upper level entries have sum of both entries.
+	 */
+	while (node) {
+		he = rb_entry(node, struct hist_entry, rb_node);
+		node = rb_next(node);
+
+		hists->stats.total_period += he->stat.period;
+		if (!he->filtered)
+			hists->stats.total_non_filtered_period += he->stat.period;
+	}
+}
+
+static void hierarchy_insert_output_entry(struct rb_root *root,
+					  struct hist_entry *he)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *iter;
+	struct perf_hpp_fmt *fmt;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct hist_entry, rb_node);
+
+		if (hist_entry__sort(he, iter) > 0)
+			p = &parent->rb_left;
+		else
+			p = &parent->rb_right;
+	}
+
+	rb_link_node(&he->rb_node, parent, p);
+	rb_insert_color(&he->rb_node, root);
+
+	/* update column width of dynamic entry */
+	perf_hpp_list__for_each_sort_list(he->hpp_list, fmt) {
+		if (perf_hpp__is_dynamic_entry(fmt))
+			fmt->sort(fmt, he, NULL);
+	}
+}
+
+static void hists__hierarchy_output_resort(struct hists *hists,
+					   struct ui_progress *prog,
+					   struct rb_root *root_in,
+					   struct rb_root *root_out,
+					   u64 min_callchain_hits,
+					   bool use_callchain)
+{
+	struct rb_node *node;
+	struct hist_entry *he;
+
+	*root_out = RB_ROOT;
+	node = rb_first(root_in);
+
+	while (node) {
+		he = rb_entry(node, struct hist_entry, rb_node_in);
+		node = rb_next(node);
+
+		hierarchy_insert_output_entry(root_out, he);
+
+		if (prog)
+			ui_progress__update(prog, 1);
+
+		if (!he->leaf) {
+			hists__hierarchy_output_resort(hists, prog,
+						       &he->hroot_in,
+						       &he->hroot_out,
+						       min_callchain_hits,
+						       use_callchain);
+			hists->nr_entries++;
+			if (!he->filtered) {
+				hists->nr_non_filtered_entries++;
+				hists__calc_col_len(hists, he);
+			}
+
+			continue;
+		}
+
+		if (!use_callchain)
+			continue;
+
+		if (callchain_param.mode == CHAIN_GRAPH_REL) {
+			u64 total = he->stat.period;
+
+			if (symbol_conf.cumulate_callchain)
+				total = he->stat_acc->period;
+
+			min_callchain_hits = total * (callchain_param.min_percent / 100);
+		}
+
+		callchain_param.sort(&he->sorted_chain, he->callchain,
+				     min_callchain_hits, &callchain_param);
+	}
+}
+
 static void __hists__insert_output_entry(struct rb_root *entries,
 					 struct hist_entry *he,
 					 u64 min_callchain_hits,
@@ -1162,10 +1568,20 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 	struct rb_node **p = &entries->rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
+	struct perf_hpp_fmt *fmt;
+
+	if (use_callchain) {
+		if (callchain_param.mode == CHAIN_GRAPH_REL) {
+			u64 total = he->stat.period;
+
+			if (symbol_conf.cumulate_callchain)
+				total = he->stat_acc->period;
 
-	if (use_callchain)
+			min_callchain_hits = total * (callchain_param.min_percent / 100);
+		}
 		callchain_param.sort(&he->sorted_chain, he->callchain,
 				      min_callchain_hits, &callchain_param);
+	}
 
 	while (*p != NULL) {
 		parent = *p;
@@ -1179,23 +1595,41 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 
 	rb_link_node(&he->rb_node, parent, p);
 	rb_insert_color(&he->rb_node, entries);
+
+	perf_hpp_list__for_each_sort_list(&perf_hpp_list, fmt) {
+		if (perf_hpp__is_dynamic_entry(fmt) &&
+		    perf_hpp__defined_dynamic_entry(fmt, he->hists))
+			fmt->sort(fmt, he, NULL);  /* update column width */
+	}
 }
 
-void hists__output_resort(struct hists *hists, struct ui_progress *prog)
+static void output_resort(struct hists *hists, struct ui_progress *prog,
+			  bool use_callchain)
 {
 	struct rb_root *root;
 	struct rb_node *next;
 	struct hist_entry *n;
+	u64 callchain_total;
 	u64 min_callchain_hits;
-	struct perf_evsel *evsel = hists_to_evsel(hists);
-	bool use_callchain;
 
-	if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph)
-		use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN;
-	else
-		use_callchain = symbol_conf.use_callchain;
+	callchain_total = hists->callchain_period;
+	if (symbol_conf.filter_relative)
+		callchain_total = hists->callchain_non_filtered_period;
 
-	min_callchain_hits = hists->stats.total_period * (callchain_param.min_percent / 100);
+	min_callchain_hits = callchain_total * (callchain_param.min_percent / 100);
+
+	hists__reset_stats(hists);
+	hists__reset_col_len(hists);
+
+	if (symbol_conf.report_hierarchy) {
+		hists__hierarchy_output_resort(hists, prog,
+					       &hists->entries_collapsed,
+					       &hists->entries,
+					       min_callchain_hits,
+					       use_callchain);
+		hierarchy_recalc_total_periods(hists);
+		return;
+	}
 
 	if (sort__need_collapse)
 		root = &hists->entries_collapsed;
@@ -1205,9 +1639,6 @@ void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 	next = rb_first(root);
 	hists->entries = RB_ROOT;
 
-	hists__reset_stats(hists);
-	hists__reset_col_len(hists);
-
 	while (next) {
 		n = rb_entry(next, struct hist_entry, rb_node_in);
 		next = rb_next(&n->rb_node_in);
@@ -1223,15 +1654,136 @@ void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 	}
 }
 
+void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog)
+{
+	bool use_callchain;
+
+	if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph)
+		use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN;
+	else
+		use_callchain = symbol_conf.use_callchain;
+
+	output_resort(evsel__hists(evsel), prog, use_callchain);
+}
+
+void hists__output_resort(struct hists *hists, struct ui_progress *prog)
+{
+	output_resort(hists, prog, symbol_conf.use_callchain);
+}
+
+static bool can_goto_child(struct hist_entry *he, enum hierarchy_move_dir hmd)
+{
+	if (he->leaf || hmd == HMD_FORCE_SIBLING)
+		return false;
+
+	if (he->unfolded || hmd == HMD_FORCE_CHILD)
+		return true;
+
+	return false;
+}
+
+struct rb_node *rb_hierarchy_last(struct rb_node *node)
+{
+	struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node);
+
+	while (can_goto_child(he, HMD_NORMAL)) {
+		node = rb_last(&he->hroot_out);
+		he = rb_entry(node, struct hist_entry, rb_node);
+	}
+	return node;
+}
+
+struct rb_node *__rb_hierarchy_next(struct rb_node *node, enum hierarchy_move_dir hmd)
+{
+	struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node);
+
+	if (can_goto_child(he, hmd))
+		node = rb_first(&he->hroot_out);
+	else
+		node = rb_next(node);
+
+	while (node == NULL) {
+		he = he->parent_he;
+		if (he == NULL)
+			break;
+
+		node = rb_next(&he->rb_node);
+	}
+	return node;
+}
+
+struct rb_node *rb_hierarchy_prev(struct rb_node *node)
+{
+	struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node);
+
+	node = rb_prev(node);
+	if (node)
+		return rb_hierarchy_last(node);
+
+	he = he->parent_he;
+	if (he == NULL)
+		return NULL;
+
+	return &he->rb_node;
+}
+
+bool hist_entry__has_hierarchy_children(struct hist_entry *he, float limit)
+{
+	struct rb_node *node;
+	struct hist_entry *child;
+	float percent;
+
+	if (he->leaf)
+		return false;
+
+	node = rb_first(&he->hroot_out);
+	child = rb_entry(node, struct hist_entry, rb_node);
+
+	while (node && child->filtered) {
+		node = rb_next(node);
+		child = rb_entry(node, struct hist_entry, rb_node);
+	}
+
+	if (node)
+		percent = hist_entry__get_percent_limit(child);
+	else
+		percent = 0;
+
+	return node && percent >= limit;
+}
+
 static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h,
 				       enum hist_filter filter)
 {
 	h->filtered &= ~(1 << filter);
+
+	if (symbol_conf.report_hierarchy) {
+		struct hist_entry *parent = h->parent_he;
+
+		while (parent) {
+			he_stat__add_stat(&parent->stat, &h->stat);
+
+			parent->filtered &= ~(1 << filter);
+
+			if (parent->filtered)
+				goto next;
+
+			/* force fold unfiltered entry for simplicity */
+			parent->unfolded = false;
+			parent->has_no_entry = false;
+			parent->row_offset = 0;
+			parent->nr_rows = 0;
+next:
+			parent = parent->parent_he;
+		}
+	}
+
 	if (h->filtered)
 		return;
 
 	/* force fold unfiltered entry for simplicity */
 	h->unfolded = false;
+	h->has_no_entry = false;
 	h->row_offset = 0;
 	h->nr_rows = 0;
 
@@ -1254,28 +1806,6 @@ static bool hists__filter_entry_by_dso(struct hists *hists,
 	return false;
 }
 
-void hists__filter_by_dso(struct hists *hists)
-{
-	struct rb_node *nd;
-
-	hists->stats.nr_non_filtered_samples = 0;
-
-	hists__reset_filter_stats(hists);
-	hists__reset_col_len(hists);
-
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
-		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-
-		if (symbol_conf.exclude_other && !h->parent)
-			continue;
-
-		if (hists__filter_entry_by_dso(hists, h))
-			continue;
-
-		hists__remove_entry_filter(hists, h, HIST_FILTER__DSO);
-	}
-}
-
 static bool hists__filter_entry_by_thread(struct hists *hists,
 					  struct hist_entry *he)
 {
@@ -1288,25 +1818,6 @@ static bool hists__filter_entry_by_thread(struct hists *hists,
 	return false;
 }
 
-void hists__filter_by_thread(struct hists *hists)
-{
-	struct rb_node *nd;
-
-	hists->stats.nr_non_filtered_samples = 0;
-
-	hists__reset_filter_stats(hists);
-	hists__reset_col_len(hists);
-
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
-		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-
-		if (hists__filter_entry_by_thread(hists, h))
-			continue;
-
-		hists__remove_entry_filter(hists, h, HIST_FILTER__THREAD);
-	}
-}
-
 static bool hists__filter_entry_by_symbol(struct hists *hists,
 					  struct hist_entry *he)
 {
@@ -1320,7 +1831,21 @@ static bool hists__filter_entry_by_symbol(struct hists *hists,
 	return false;
 }
 
-void hists__filter_by_symbol(struct hists *hists)
+static bool hists__filter_entry_by_socket(struct hists *hists,
+					  struct hist_entry *he)
+{
+	if ((hists->socket_filter > -1) &&
+	    (he->socket != hists->socket_filter)) {
+		he->filtered |= (1 << HIST_FILTER__SOCKET);
+		return true;
+	}
+
+	return false;
+}
+
+typedef bool (*filter_fn_t)(struct hists *hists, struct hist_entry *he);
+
+static void hists__filter_by_type(struct hists *hists, int type, filter_fn_t filter)
 {
 	struct rb_node *nd;
 
@@ -1332,42 +1857,155 @@ void hists__filter_by_symbol(struct hists *hists)
 	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
-		if (hists__filter_entry_by_symbol(hists, h))
+		if (filter(hists, h))
 			continue;
 
-		hists__remove_entry_filter(hists, h, HIST_FILTER__SYMBOL);
+		hists__remove_entry_filter(hists, h, type);
 	}
 }
 
-static bool hists__filter_entry_by_socket(struct hists *hists,
-					  struct hist_entry *he)
+static void resort_filtered_entry(struct rb_root *root, struct hist_entry *he)
 {
-	if ((hists->socket_filter > -1) &&
-	    (he->socket != hists->socket_filter)) {
-		he->filtered |= (1 << HIST_FILTER__SOCKET);
-		return true;
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *iter;
+	struct rb_root new_root = RB_ROOT;
+	struct rb_node *nd;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct hist_entry, rb_node);
+
+		if (hist_entry__sort(he, iter) > 0)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
 	}
 
-	return false;
+	rb_link_node(&he->rb_node, parent, p);
+	rb_insert_color(&he->rb_node, root);
+
+	if (he->leaf || he->filtered)
+		return;
+
+	nd = rb_first(&he->hroot_out);
+	while (nd) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		nd = rb_next(nd);
+		rb_erase(&h->rb_node, &he->hroot_out);
+
+		resort_filtered_entry(&new_root, h);
+	}
+
+	he->hroot_out = new_root;
 }
 
-void hists__filter_by_socket(struct hists *hists)
+static void hists__filter_hierarchy(struct hists *hists, int type, const void *arg)
 {
 	struct rb_node *nd;
+	struct rb_root new_root = RB_ROOT;
 
 	hists->stats.nr_non_filtered_samples = 0;
 
 	hists__reset_filter_stats(hists);
 	hists__reset_col_len(hists);
 
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+	nd = rb_first(&hists->entries);
+	while (nd) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+		int ret;
 
-		if (hists__filter_entry_by_socket(hists, h))
-			continue;
+		ret = hist_entry__filter(h, type, arg);
 
-		hists__remove_entry_filter(hists, h, HIST_FILTER__SOCKET);
+		/*
+		 * case 1. non-matching type
+		 * zero out the period, set filter marker and move to child
+		 */
+		if (ret < 0) {
+			memset(&h->stat, 0, sizeof(h->stat));
+			h->filtered |= (1 << type);
+
+			nd = __rb_hierarchy_next(&h->rb_node, HMD_FORCE_CHILD);
+		}
+		/*
+		 * case 2. matched type (filter out)
+		 * set filter marker and move to next
+		 */
+		else if (ret == 1) {
+			h->filtered |= (1 << type);
+
+			nd = __rb_hierarchy_next(&h->rb_node, HMD_FORCE_SIBLING);
+		}
+		/*
+		 * case 3. ok (not filtered)
+		 * add period to hists and parents, erase the filter marker
+		 * and move to next sibling
+		 */
+		else {
+			hists__remove_entry_filter(hists, h, type);
+
+			nd = __rb_hierarchy_next(&h->rb_node, HMD_FORCE_SIBLING);
+		}
+	}
+
+	hierarchy_recalc_total_periods(hists);
+
+	/*
+	 * resort output after applying a new filter since filter in a lower
+	 * hierarchy can change periods in a upper hierarchy.
+	 */
+	nd = rb_first(&hists->entries);
+	while (nd) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		nd = rb_next(nd);
+		rb_erase(&h->rb_node, &hists->entries);
+
+		resort_filtered_entry(&new_root, h);
 	}
+
+	hists->entries = new_root;
+}
+
+void hists__filter_by_thread(struct hists *hists)
+{
+	if (symbol_conf.report_hierarchy)
+		hists__filter_hierarchy(hists, HIST_FILTER__THREAD,
+					hists->thread_filter);
+	else
+		hists__filter_by_type(hists, HIST_FILTER__THREAD,
+				      hists__filter_entry_by_thread);
+}
+
+void hists__filter_by_dso(struct hists *hists)
+{
+	if (symbol_conf.report_hierarchy)
+		hists__filter_hierarchy(hists, HIST_FILTER__DSO,
+					hists->dso_filter);
+	else
+		hists__filter_by_type(hists, HIST_FILTER__DSO,
+				      hists__filter_entry_by_dso);
+}
+
+void hists__filter_by_symbol(struct hists *hists)
+{
+	if (symbol_conf.report_hierarchy)
+		hists__filter_hierarchy(hists, HIST_FILTER__SYMBOL,
+					hists->symbol_filter_str);
+	else
+		hists__filter_by_type(hists, HIST_FILTER__SYMBOL,
+				      hists__filter_entry_by_symbol);
+}
+
+void hists__filter_by_socket(struct hists *hists)
+{
+	if (symbol_conf.report_hierarchy)
+		hists__filter_hierarchy(hists, HIST_FILTER__SOCKET,
+					&hists->socket_filter);
+	else
+		hists__filter_by_type(hists, HIST_FILTER__SOCKET,
+				      hists__filter_entry_by_socket);
 }
 
 void events_stats__inc(struct events_stats *stats, u32 type)
@@ -1585,7 +2223,7 @@ int perf_hist_config(const char *var, const char *value)
 	return 0;
 }
 
-int __hists__init(struct hists *hists)
+int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list)
 {
 	memset(hists, 0, sizeof(*hists));
 	hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
@@ -1594,6 +2232,8 @@ int __hists__init(struct hists *hists)
 	hists->entries = RB_ROOT;
 	pthread_mutex_init(&hists->lock, NULL);
 	hists->socket_filter = -1;
+	hists->hpp_list = hpp_list;
+	INIT_LIST_HEAD(&hists->hpp_formats);
 	return 0;
 }
 
@@ -1622,15 +2262,26 @@ static void hists__delete_all_entries(struct hists *hists)
 static void hists_evsel__exit(struct perf_evsel *evsel)
 {
 	struct hists *hists = evsel__hists(evsel);
+	struct perf_hpp_fmt *fmt, *pos;
+	struct perf_hpp_list_node *node, *tmp;
 
 	hists__delete_all_entries(hists);
+
+	list_for_each_entry_safe(node, tmp, &hists->hpp_formats, list) {
+		perf_hpp_list__for_each_format_safe(&node->hpp, fmt, pos) {
+			list_del(&fmt->list);
+			free(fmt);
+		}
+		list_del(&node->list);
+		free(node);
+	}
 }
 
 static int hists_evsel__init(struct perf_evsel *evsel)
 {
 	struct hists *hists = evsel__hists(evsel);
 
-	__hists__init(hists);
+	__hists__init(hists, &perf_hpp_list);
 	return 0;
 }
 
@@ -1649,3 +2300,9 @@ int hists__init(void)
 
 	return err;
 }
+
+void perf_hpp_list__init(struct perf_hpp_list *list)
+{
+	INIT_LIST_HEAD(&list->fields);
+	INIT_LIST_HEAD(&list->sorts);
+}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index d4ec4822a..bec0cd660 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -66,6 +66,8 @@ struct hists {
 	struct rb_root		entries_collapsed;
 	u64			nr_entries;
 	u64			nr_non_filtered_entries;
+	u64			callchain_period;
+	u64			callchain_non_filtered_period;
 	struct thread		*thread_filter;
 	const struct dso	*dso_filter;
 	const char		*uid_filter_str;
@@ -75,6 +77,9 @@ struct hists {
 	u64			event_stream;
 	u16			col_len[HISTC_NR_COLS];
 	int			socket_filter;
+	struct perf_hpp_list	*hpp_list;
+	struct list_head	hpp_formats;
+	int			nr_hpp_node;
 };
 
 struct hist_entry_iter;
@@ -121,15 +126,21 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 			 int max_stack_depth, void *arg);
 
+struct perf_hpp;
+struct perf_hpp_fmt;
+
 int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
 int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right);
 int hist_entry__transaction_len(void);
 int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size,
 			      struct hists *hists);
+int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
+				   struct perf_hpp_fmt *fmt, int printed);
 void hist_entry__delete(struct hist_entry *he);
 
+void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog);
 void hists__output_resort(struct hists *hists, struct ui_progress *prog);
-void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
+int hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
 
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
 void hists__delete_entries(struct hists *hists);
@@ -185,10 +196,10 @@ static inline struct hists *evsel__hists(struct perf_evsel *evsel)
 }
 
 int hists__init(void);
-int __hists__init(struct hists *hists);
+int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list);
 
 struct rb_root *hists__get_rotate_entries_in(struct hists *hists);
-bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
+int hists__collapse_insert_entry(struct hists *hists,
 				  struct rb_root *root, struct hist_entry *he);
 
 struct perf_hpp {
@@ -214,28 +225,64 @@ struct perf_hpp_fmt {
 			    struct hist_entry *a, struct hist_entry *b);
 	int64_t (*sort)(struct perf_hpp_fmt *fmt,
 			struct hist_entry *a, struct hist_entry *b);
+	bool (*equal)(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b);
+	void (*free)(struct perf_hpp_fmt *fmt);
 
 	struct list_head list;
 	struct list_head sort_list;
 	bool elide;
 	int len;
 	int user_len;
+	int idx;
+	int level;
+};
+
+struct perf_hpp_list {
+	struct list_head fields;
+	struct list_head sorts;
 };
 
-extern struct list_head perf_hpp__list;
-extern struct list_head perf_hpp__sort_list;
+extern struct perf_hpp_list perf_hpp_list;
+
+struct perf_hpp_list_node {
+	struct list_head	list;
+	struct perf_hpp_list	hpp;
+	int			level;
+	bool			skip;
+};
+
+void perf_hpp_list__column_register(struct perf_hpp_list *list,
+				    struct perf_hpp_fmt *format);
+void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
+					struct perf_hpp_fmt *format);
+
+static inline void perf_hpp__column_register(struct perf_hpp_fmt *format)
+{
+	perf_hpp_list__column_register(&perf_hpp_list, format);
+}
+
+static inline void perf_hpp__register_sort_field(struct perf_hpp_fmt *format)
+{
+	perf_hpp_list__register_sort_field(&perf_hpp_list, format);
+}
+
+#define perf_hpp_list__for_each_format(_list, format) \
+	list_for_each_entry(format, &(_list)->fields, list)
 
-#define perf_hpp__for_each_format(format) \
-	list_for_each_entry(format, &perf_hpp__list, list)
+#define perf_hpp_list__for_each_format_safe(_list, format, tmp)	\
+	list_for_each_entry_safe(format, tmp, &(_list)->fields, list)
 
-#define perf_hpp__for_each_format_safe(format, tmp)	\
-	list_for_each_entry_safe(format, tmp, &perf_hpp__list, list)
+#define perf_hpp_list__for_each_sort_list(_list, format) \
+	list_for_each_entry(format, &(_list)->sorts, sort_list)
 
-#define perf_hpp__for_each_sort_list(format) \
-	list_for_each_entry(format, &perf_hpp__sort_list, sort_list)
+#define perf_hpp_list__for_each_sort_list_safe(_list, format, tmp)	\
+	list_for_each_entry_safe(format, tmp, &(_list)->sorts, sort_list)
 
-#define perf_hpp__for_each_sort_list_safe(format, tmp)	\
-	list_for_each_entry_safe(format, tmp, &perf_hpp__sort_list, sort_list)
+#define hists__for_each_format(hists, format) \
+	perf_hpp_list__for_each_format((hists)->hpp_list, fmt)
+
+#define hists__for_each_sort_list(hists, format) \
+	perf_hpp_list__for_each_sort_list((hists)->hpp_list, fmt)
 
 extern struct perf_hpp_fmt perf_hpp__format[];
 
@@ -254,21 +301,29 @@ enum {
 };
 
 void perf_hpp__init(void);
-void perf_hpp__column_register(struct perf_hpp_fmt *format);
 void perf_hpp__column_unregister(struct perf_hpp_fmt *format);
-void perf_hpp__column_enable(unsigned col);
-void perf_hpp__column_disable(unsigned col);
 void perf_hpp__cancel_cumulate(void);
+void perf_hpp__setup_output_field(struct perf_hpp_list *list);
+void perf_hpp__reset_output_field(struct perf_hpp_list *list);
+void perf_hpp__append_sort_keys(struct perf_hpp_list *list);
+int perf_hpp__setup_hists_formats(struct perf_hpp_list *list,
+				  struct perf_evlist *evlist);
 
-void perf_hpp__register_sort_field(struct perf_hpp_fmt *format);
-void perf_hpp__setup_output_field(void);
-void perf_hpp__reset_output_field(void);
-void perf_hpp__append_sort_keys(void);
 
 bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format);
-bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b);
 bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *format);
 bool perf_hpp__defined_dynamic_entry(struct perf_hpp_fmt *fmt, struct hists *hists);
+bool perf_hpp__is_trace_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_srcline_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_srcfile_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_thread_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_comm_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_dso_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_sym_entry(struct perf_hpp_fmt *fmt);
+
+struct perf_hpp_fmt *perf_hpp_fmt__dup(struct perf_hpp_fmt *fmt);
+
+int hist_entry__filter(struct hist_entry *he, int type, const void *arg);
 
 static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format,
 					 struct hists *hists)
@@ -372,13 +427,35 @@ static inline int script_browse(const char *script_opt __maybe_unused)
 #endif
 
 unsigned int hists__sort_list_width(struct hists *hists);
+unsigned int hists__overhead_width(struct hists *hists);
 
 void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
 			  struct perf_sample *sample, bool nonany_branch_mode);
 
 struct option;
-int parse_filter_percentage(const struct option *opt __maybe_unused,
-			    const char *arg, int unset __maybe_unused);
+int parse_filter_percentage(const struct option *opt, const char *arg, int unset);
 int perf_hist_config(const char *var, const char *value);
 
+void perf_hpp_list__init(struct perf_hpp_list *list);
+
+enum hierarchy_move_dir {
+	HMD_NORMAL,
+	HMD_FORCE_SIBLING,
+	HMD_FORCE_CHILD,
+};
+
+struct rb_node *rb_hierarchy_last(struct rb_node *node);
+struct rb_node *__rb_hierarchy_next(struct rb_node *node,
+				    enum hierarchy_move_dir hmd);
+struct rb_node *rb_hierarchy_prev(struct rb_node *node);
+
+static inline struct rb_node *rb_hierarchy_next(struct rb_node *node)
+{
+	return __rb_hierarchy_next(node, HMD_NORMAL);
+}
+
+#define HIERARCHY_INDENT  3
+
+bool hist_entry__has_hierarchy_children(struct hist_entry *he, float limit);
+
 #endif	/* __PERF_HIST_H */
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index eb0e7f8bf..abf1366e2 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -279,6 +279,7 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 	event.sample.header.misc = PERF_RECORD_MISC_USER;
 	event.sample.header.size = sizeof(struct perf_event_header);
 
+	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.ip = le64_to_cpu(branch->from);
 	sample.pid = btsq->pid;
 	sample.tid = btsq->tid;
@@ -678,7 +679,7 @@ static int intel_bts_process_auxtrace_event(struct perf_session *session,
 	return 0;
 }
 
-static int intel_bts_flush(struct perf_session *session __maybe_unused,
+static int intel_bts_flush(struct perf_session *session,
 			   struct perf_tool *tool __maybe_unused)
 {
 	struct intel_bts *bts = container_of(session->auxtrace, struct intel_bts,
diff --git a/tools/perf/util/intel-pt-decoder/insn.c b/tools/perf/util/intel-pt-decoder/insn.c
index 47314a643..9f26eae6c 100644
--- a/tools/perf/util/intel-pt-decoder/insn.c
+++ b/tools/perf/util/intel-pt-decoder/insn.c
@@ -374,7 +374,7 @@ void insn_get_displacement(struct insn *insn)
 		if (mod == 3)
 			goto out;
 		if (mod == 1) {
-			insn->displacement.value = get_next(char, insn);
+			insn->displacement.value = get_next(signed char, insn);
 			insn->displacement.nbytes = 1;
 		} else if (insn->addr_bytes == 2) {
 			if ((mod == 0 && rm == 6) || mod == 2) {
@@ -532,7 +532,7 @@ void insn_get_immediate(struct insn *insn)
 
 	switch (inat_immediate_size(insn->attr)) {
 	case INAT_IMM_BYTE:
-		insn->immediate.value = get_next(char, insn);
+		insn->immediate.value = get_next(signed char, insn);
 		insn->immediate.nbytes = 1;
 		break;
 	case INAT_IMM_WORD:
@@ -566,7 +566,7 @@ void insn_get_immediate(struct insn *insn)
 		goto err_out;
 	}
 	if (inat_has_second_immediate(insn->attr)) {
-		insn->immediate2.value = get_next(char, insn);
+		insn->immediate2.value = get_next(signed char, insn);
 		insn->immediate2.nbytes = 1;
 	}
 done:
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 4e1590ba8..617578440 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -979,6 +979,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 	if (!pt->timeless_decoding)
 		sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
 
+	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.ip = ptq->state->from_ip;
 	sample.pid = ptq->pid;
 	sample.tid = ptq->tid;
@@ -1035,6 +1036,7 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
 	if (!pt->timeless_decoding)
 		sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
 
+	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.ip = ptq->state->from_ip;
 	sample.pid = ptq->pid;
 	sample.tid = ptq->tid;
@@ -1092,6 +1094,7 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
 	if (!pt->timeless_decoding)
 		sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
 
+	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.ip = ptq->state->from_ip;
 	sample.pid = ptq->pid;
 	sample.tid = ptq->tid;
diff --git a/tools/perf/util/jit.h b/tools/perf/util/jit.h
new file mode 100644
index 000000000..3f42ee4d2
--- /dev/null
+++ b/tools/perf/util/jit.h
@@ -0,0 +1,11 @@
+#ifndef __JIT_H__
+#define __JIT_H__
+
+#include <data.h>
+
+int jit_process(struct perf_session *session, struct perf_data_file *output,
+		struct machine *machine, char *filename, pid_t pid, u64 *nbytes);
+
+int jit_inject_record(const char *filename);
+
+#endif /* __JIT_H__ */
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
new file mode 100644
index 000000000..ad0c0bb1f
--- /dev/null
+++ b/tools/perf/util/jitdump.c
@@ -0,0 +1,699 @@
+#include <sys/types.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <inttypes.h>
+#include <byteswap.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+
+#include "util.h"
+#include "event.h"
+#include "debug.h"
+#include "evlist.h"
+#include "symbol.h"
+#include "strlist.h"
+#include <elf.h>
+
+#include "session.h"
+#include "jit.h"
+#include "jitdump.h"
+#include "genelf.h"
+#include "../builtin.h"
+
+struct jit_buf_desc {
+	struct perf_data_file *output;
+	struct perf_session *session;
+	struct machine *machine;
+	union jr_entry   *entry;
+	void             *buf;
+	uint64_t	 sample_type;
+	size_t           bufsize;
+	FILE             *in;
+	bool		 needs_bswap; /* handles cross-endianess */
+	void		 *debug_data;
+	size_t		 nr_debug_entries;
+	uint32_t         code_load_count;
+	u64		 bytes_written;
+	struct rb_root   code_root;
+	char		 dir[PATH_MAX];
+};
+
+struct debug_line_info {
+	unsigned long vma;
+	unsigned int lineno;
+	/* The filename format is unspecified, absolute path, relative etc. */
+	char const filename[0];
+};
+
+struct jit_tool {
+	struct perf_tool tool;
+	struct perf_data_file	output;
+	struct perf_data_file	input;
+	u64 bytes_written;
+};
+
+#define hmax(a, b) ((a) > (b) ? (a) : (b))
+#define get_jit_tool(t) (container_of(tool, struct jit_tool, tool))
+
+static int
+jit_emit_elf(char *filename,
+	     const char *sym,
+	     uint64_t code_addr,
+	     const void *code,
+	     int csize,
+	     void *debug,
+	     int nr_debug_entries)
+{
+	int ret, fd;
+
+	if (verbose > 0)
+		fprintf(stderr, "write ELF image %s\n", filename);
+
+	fd = open(filename, O_CREAT|O_TRUNC|O_WRONLY, 0644);
+	if (fd == -1) {
+		pr_warning("cannot create jit ELF %s: %s\n", filename, strerror(errno));
+		return -1;
+	}
+
+        ret = jit_write_elf(fd, code_addr, sym, (const void *)code, csize, debug, nr_debug_entries);
+
+        close(fd);
+
+        if (ret)
+                unlink(filename);
+
+	return ret;
+}
+
+static void
+jit_close(struct jit_buf_desc *jd)
+{
+	if (!(jd && jd->in))
+		return;
+	funlockfile(jd->in);
+	fclose(jd->in);
+	jd->in = NULL;
+}
+
+static int
+jit_validate_events(struct perf_session *session)
+{
+	struct perf_evsel *evsel;
+
+	/*
+	 * check that all events use CLOCK_MONOTONIC
+	 */
+	evlist__for_each(session->evlist, evsel) {
+		if (evsel->attr.use_clockid == 0 || evsel->attr.clockid != CLOCK_MONOTONIC)
+			return -1;
+	}
+	return 0;
+}
+
+static int
+jit_open(struct jit_buf_desc *jd, const char *name)
+{
+	struct jitheader header;
+	struct jr_prefix *prefix;
+	ssize_t bs, bsz = 0;
+	void *n, *buf = NULL;
+	int ret, retval = -1;
+
+	jd->in = fopen(name, "r");
+	if (!jd->in)
+		return -1;
+
+	bsz = hmax(sizeof(header), sizeof(*prefix));
+
+	buf = malloc(bsz);
+	if (!buf)
+		goto error;
+
+	/*
+	 * protect from writer modifying the file while we are reading it
+	 */
+	flockfile(jd->in);
+
+	ret = fread(buf, sizeof(header), 1, jd->in);
+	if (ret != 1)
+		goto error;
+
+	memcpy(&header, buf, sizeof(header));
+
+	if (header.magic != JITHEADER_MAGIC) {
+		if (header.magic != JITHEADER_MAGIC_SW)
+			goto error;
+		jd->needs_bswap = true;
+	}
+
+	if (jd->needs_bswap) {
+		header.version    = bswap_32(header.version);
+		header.total_size = bswap_32(header.total_size);
+		header.pid	  = bswap_32(header.pid);
+		header.elf_mach   = bswap_32(header.elf_mach);
+		header.timestamp  = bswap_64(header.timestamp);
+		header.flags      = bswap_64(header.flags);
+	}
+
+	if (verbose > 2)
+		pr_debug("version=%u\nhdr.size=%u\nts=0x%llx\npid=%d\nelf_mach=%d\n",
+			header.version,
+			header.total_size,
+			(unsigned long long)header.timestamp,
+			header.pid,
+			header.elf_mach);
+
+	if (header.flags & JITDUMP_FLAGS_RESERVED) {
+		pr_err("jitdump file contains invalid or unsupported flags 0x%llx\n",
+		       (unsigned long long)header.flags & JITDUMP_FLAGS_RESERVED);
+		goto error;
+	}
+
+	/*
+	 * validate event is using the correct clockid
+	 */
+	if (jit_validate_events(jd->session)) {
+		pr_err("error, jitted code must be sampled with perf record -k 1\n");
+		goto error;
+	}
+
+	bs = header.total_size - sizeof(header);
+
+	if (bs > bsz) {
+		n = realloc(buf, bs);
+		if (!n)
+			goto error;
+		bsz = bs;
+		buf = n;
+		/* read extra we do not know about */
+		ret = fread(buf, bs - bsz, 1, jd->in);
+		if (ret != 1)
+			goto error;
+	}
+	/*
+	 * keep dirname for generating files and mmap records
+	 */
+	strcpy(jd->dir, name);
+	dirname(jd->dir);
+
+	return 0;
+error:
+	funlockfile(jd->in);
+	fclose(jd->in);
+	return retval;
+}
+
+static union jr_entry *
+jit_get_next_entry(struct jit_buf_desc *jd)
+{
+	struct jr_prefix *prefix;
+	union jr_entry *jr;
+	void *addr;
+	size_t bs, size;
+	int id, ret;
+
+	if (!(jd && jd->in))
+		return NULL;
+
+	if (jd->buf == NULL) {
+		size_t sz = getpagesize();
+		if (sz < sizeof(*prefix))
+			sz = sizeof(*prefix);
+
+		jd->buf = malloc(sz);
+		if (jd->buf == NULL)
+			return NULL;
+
+		jd->bufsize = sz;
+	}
+
+	prefix = jd->buf;
+
+	/*
+	 * file is still locked at this point
+	 */
+	ret = fread(prefix, sizeof(*prefix), 1, jd->in);
+	if (ret  != 1)
+		return NULL;
+
+	if (jd->needs_bswap) {
+		prefix->id   	   = bswap_32(prefix->id);
+		prefix->total_size = bswap_32(prefix->total_size);
+		prefix->timestamp  = bswap_64(prefix->timestamp);
+	}
+	id   = prefix->id;
+	size = prefix->total_size;
+
+	bs = (size_t)size;
+	if (bs < sizeof(*prefix))
+		return NULL;
+
+	if (id >= JIT_CODE_MAX) {
+		pr_warning("next_entry: unknown prefix %d, skipping\n", id);
+		return NULL;
+	}
+	if (bs > jd->bufsize) {
+		void *n;
+		n = realloc(jd->buf, bs);
+		if (!n)
+			return NULL;
+		jd->buf = n;
+		jd->bufsize = bs;
+	}
+
+	addr = ((void *)jd->buf) + sizeof(*prefix);
+
+	ret = fread(addr, bs - sizeof(*prefix), 1, jd->in);
+	if (ret != 1)
+		return NULL;
+
+	jr = (union jr_entry *)jd->buf;
+
+	switch(id) {
+	case JIT_CODE_DEBUG_INFO:
+		if (jd->needs_bswap) {
+			uint64_t n;
+			jr->info.code_addr = bswap_64(jr->info.code_addr);
+			jr->info.nr_entry  = bswap_64(jr->info.nr_entry);
+			for (n = 0 ; n < jr->info.nr_entry; n++) {
+				jr->info.entries[n].addr    = bswap_64(jr->info.entries[n].addr);
+				jr->info.entries[n].lineno  = bswap_32(jr->info.entries[n].lineno);
+				jr->info.entries[n].discrim = bswap_32(jr->info.entries[n].discrim);
+			}
+		}
+		break;
+	case JIT_CODE_CLOSE:
+		break;
+	case JIT_CODE_LOAD:
+		if (jd->needs_bswap) {
+			jr->load.pid       = bswap_32(jr->load.pid);
+			jr->load.tid       = bswap_32(jr->load.tid);
+			jr->load.vma       = bswap_64(jr->load.vma);
+			jr->load.code_addr = bswap_64(jr->load.code_addr);
+			jr->load.code_size = bswap_64(jr->load.code_size);
+			jr->load.code_index= bswap_64(jr->load.code_index);
+		}
+		jd->code_load_count++;
+		break;
+	case JIT_CODE_MOVE:
+		if (jd->needs_bswap) {
+			jr->move.pid           = bswap_32(jr->move.pid);
+			jr->move.tid           = bswap_32(jr->move.tid);
+			jr->move.vma           = bswap_64(jr->move.vma);
+			jr->move.old_code_addr = bswap_64(jr->move.old_code_addr);
+			jr->move.new_code_addr = bswap_64(jr->move.new_code_addr);
+			jr->move.code_size     = bswap_64(jr->move.code_size);
+			jr->move.code_index    = bswap_64(jr->move.code_index);
+		}
+		break;
+	case JIT_CODE_MAX:
+	default:
+		return NULL;
+	}
+	return jr;
+}
+
+static int
+jit_inject_event(struct jit_buf_desc *jd, union perf_event *event)
+{
+	ssize_t size;
+
+	size = perf_data_file__write(jd->output, event, event->header.size);
+	if (size < 0)
+		return -1;
+
+	jd->bytes_written += size;
+	return 0;
+}
+
+static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
+{
+	struct perf_sample sample;
+	union perf_event *event;
+	struct perf_tool *tool = jd->session->tool;
+	uint64_t code, addr;
+	uintptr_t uaddr;
+	char *filename;
+	struct stat st;
+	size_t size;
+	u16 idr_size;
+	const char *sym;
+	uint32_t count;
+	int ret, csize;
+	pid_t pid, tid;
+	struct {
+		u32 pid, tid;
+		u64 time;
+	} *id;
+
+	pid   = jr->load.pid;
+	tid   = jr->load.tid;
+	csize = jr->load.code_size;
+	addr  = jr->load.code_addr;
+	sym   = (void *)((unsigned long)jr + sizeof(jr->load));
+	code  = (unsigned long)jr + jr->load.p.total_size - csize;
+	count = jr->load.code_index;
+	idr_size = jd->machine->id_hdr_size;
+
+	event = calloc(1, sizeof(*event) + idr_size);
+	if (!event)
+		return -1;
+
+	filename = event->mmap2.filename;
+	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%u.so",
+			jd->dir,
+			pid,
+			count);
+
+	size++; /* for \0 */
+
+	size = PERF_ALIGN(size, sizeof(u64));
+	uaddr = (uintptr_t)code;
+	ret = jit_emit_elf(filename, sym, addr, (const void *)uaddr, csize, jd->debug_data, jd->nr_debug_entries);
+
+	if (jd->debug_data && jd->nr_debug_entries) {
+		free(jd->debug_data);
+		jd->debug_data = NULL;
+		jd->nr_debug_entries = 0;
+	}
+
+	if (ret) {
+		free(event);
+		return -1;
+	}
+	if (stat(filename, &st))
+		memset(&st, 0, sizeof(stat));
+
+	event->mmap2.header.type = PERF_RECORD_MMAP2;
+	event->mmap2.header.misc = PERF_RECORD_MISC_USER;
+	event->mmap2.header.size = (sizeof(event->mmap2) -
+			(sizeof(event->mmap2.filename) - size) + idr_size);
+
+	event->mmap2.pgoff = GEN_ELF_TEXT_OFFSET;
+	event->mmap2.start = addr;
+	event->mmap2.len   = csize;
+	event->mmap2.pid   = pid;
+	event->mmap2.tid   = tid;
+	event->mmap2.ino   = st.st_ino;
+	event->mmap2.maj   = major(st.st_dev);
+	event->mmap2.min   = minor(st.st_dev);
+	event->mmap2.prot  = st.st_mode;
+	event->mmap2.flags = MAP_SHARED;
+	event->mmap2.ino_generation = 1;
+
+	id = (void *)((unsigned long)event + event->mmap.header.size - idr_size);
+	if (jd->sample_type & PERF_SAMPLE_TID) {
+		id->pid  = pid;
+		id->tid  = tid;
+	}
+	if (jd->sample_type & PERF_SAMPLE_TIME)
+		id->time = jr->load.p.timestamp;
+
+	/*
+	 * create pseudo sample to induce dso hit increment
+	 * use first address as sample address
+	 */
+	memset(&sample, 0, sizeof(sample));
+	sample.cpumode = PERF_RECORD_MISC_USER;
+	sample.pid  = pid;
+	sample.tid  = tid;
+	sample.time = id->time;
+	sample.ip   = addr;
+
+	ret = perf_event__process_mmap2(tool, event, &sample, jd->machine);
+	if (ret)
+		return ret;
+
+	ret = jit_inject_event(jd, event);
+	/*
+	 * mark dso as use to generate buildid in the header
+	 */
+	if (!ret)
+		build_id__mark_dso_hit(tool, event, &sample, NULL, jd->machine);
+
+	return ret;
+}
+
+static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr)
+{
+	struct perf_sample sample;
+	union perf_event *event;
+	struct perf_tool *tool = jd->session->tool;
+	char *filename;
+	size_t size;
+	struct stat st;
+	u16 idr_size;
+	int ret;
+	pid_t pid, tid;
+	struct {
+		u32 pid, tid;
+		u64 time;
+	} *id;
+
+	pid = jr->move.pid;
+	tid =  jr->move.tid;
+	idr_size = jd->machine->id_hdr_size;
+
+	/*
+	 * +16 to account for sample_id_all (hack)
+	 */
+	event = calloc(1, sizeof(*event) + 16);
+	if (!event)
+		return -1;
+
+	filename = event->mmap2.filename;
+	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%"PRIu64,
+	         jd->dir,
+	         pid,
+		 jr->move.code_index);
+
+	size++; /* for \0 */
+
+	if (stat(filename, &st))
+		memset(&st, 0, sizeof(stat));
+
+	size = PERF_ALIGN(size, sizeof(u64));
+
+	event->mmap2.header.type = PERF_RECORD_MMAP2;
+	event->mmap2.header.misc = PERF_RECORD_MISC_USER;
+	event->mmap2.header.size = (sizeof(event->mmap2) -
+			(sizeof(event->mmap2.filename) - size) + idr_size);
+	event->mmap2.pgoff = GEN_ELF_TEXT_OFFSET;
+	event->mmap2.start = jr->move.new_code_addr;
+	event->mmap2.len   = jr->move.code_size;
+	event->mmap2.pid   = pid;
+	event->mmap2.tid   = tid;
+	event->mmap2.ino   = st.st_ino;
+	event->mmap2.maj   = major(st.st_dev);
+	event->mmap2.min   = minor(st.st_dev);
+	event->mmap2.prot  = st.st_mode;
+	event->mmap2.flags = MAP_SHARED;
+	event->mmap2.ino_generation = 1;
+
+	id = (void *)((unsigned long)event + event->mmap.header.size - idr_size);
+	if (jd->sample_type & PERF_SAMPLE_TID) {
+		id->pid  = pid;
+		id->tid  = tid;
+	}
+	if (jd->sample_type & PERF_SAMPLE_TIME)
+		id->time = jr->load.p.timestamp;
+
+	/*
+	 * create pseudo sample to induce dso hit increment
+	 * use first address as sample address
+	 */
+	memset(&sample, 0, sizeof(sample));
+	sample.cpumode = PERF_RECORD_MISC_USER;
+	sample.pid  = pid;
+	sample.tid  = tid;
+	sample.time = id->time;
+	sample.ip   = jr->move.new_code_addr;
+
+	ret = perf_event__process_mmap2(tool, event, &sample, jd->machine);
+	if (ret)
+		return ret;
+
+	ret = jit_inject_event(jd, event);
+	if (!ret)
+		build_id__mark_dso_hit(tool, event, &sample, NULL, jd->machine);
+
+	return ret;
+}
+
+static int jit_repipe_debug_info(struct jit_buf_desc *jd, union jr_entry *jr)
+{
+	void *data;
+	size_t sz;
+
+	if (!(jd && jr))
+		return -1;
+
+	sz  = jr->prefix.total_size - sizeof(jr->info);
+	data = malloc(sz);
+	if (!data)
+		return -1;
+
+	memcpy(data, &jr->info.entries, sz);
+
+	jd->debug_data       = data;
+
+	/*
+	 * we must use nr_entry instead of size here because
+	 * we cannot distinguish actual entry from padding otherwise
+	 */
+	jd->nr_debug_entries = jr->info.nr_entry;
+
+	return 0;
+}
+
+static int
+jit_process_dump(struct jit_buf_desc *jd)
+{
+	union jr_entry *jr;
+	int ret;
+
+	while ((jr = jit_get_next_entry(jd))) {
+		switch(jr->prefix.id) {
+		case JIT_CODE_LOAD:
+			ret = jit_repipe_code_load(jd, jr);
+			break;
+		case JIT_CODE_MOVE:
+			ret = jit_repipe_code_move(jd, jr);
+			break;
+		case JIT_CODE_DEBUG_INFO:
+			ret = jit_repipe_debug_info(jd, jr);
+			break;
+		default:
+			ret = 0;
+			continue;
+		}
+	}
+	return ret;
+}
+
+static int
+jit_inject(struct jit_buf_desc *jd, char *path)
+{
+	int ret;
+
+	if (verbose > 0)
+		fprintf(stderr, "injecting: %s\n", path);
+
+	ret = jit_open(jd, path);
+	if (ret)
+		return -1;
+
+	ret = jit_process_dump(jd);
+
+	jit_close(jd);
+
+	if (verbose > 0)
+		fprintf(stderr, "injected: %s (%d)\n", path, ret);
+
+	return 0;
+}
+
+/*
+ * File must be with pattern .../jit-XXXX.dump
+ * where XXXX is the PID of the process which did the mmap()
+ * as captured in the RECORD_MMAP record
+ */
+static int
+jit_detect(char *mmap_name, pid_t pid)
+ {
+	char *p;
+	char *end = NULL;
+	pid_t pid2;
+
+	if (verbose > 2)
+		fprintf(stderr, "jit marker trying : %s\n", mmap_name);
+	/*
+	 * get file name
+	 */
+	p = strrchr(mmap_name, '/');
+	if (!p)
+		return -1;
+
+	/*
+	 * match prefix
+	 */
+	if (strncmp(p, "/jit-", 5))
+		return -1;
+
+	/*
+	 * skip prefix
+	 */
+	p += 5;
+
+	/*
+	 * must be followed by a pid
+	 */
+	if (!isdigit(*p))
+		return -1;
+
+	pid2 = (int)strtol(p, &end, 10);
+	if (!end)
+		return -1;
+
+	/*
+	 * pid does not match mmap pid
+	 * pid==0 in system-wide mode (synthesized)
+	 */
+	if (pid && pid2 != pid)
+		return -1;
+	/*
+	 * validate suffix
+	 */
+	if (strcmp(end, ".dump"))
+		return -1;
+
+	if (verbose > 0)
+		fprintf(stderr, "jit marker found: %s\n", mmap_name);
+
+	return 0;
+}
+
+int
+jit_process(struct perf_session *session,
+	    struct perf_data_file *output,
+	    struct machine *machine,
+	    char *filename,
+	    pid_t pid,
+	    u64 *nbytes)
+{
+	struct perf_evsel *first;
+	struct jit_buf_desc jd;
+	int ret;
+
+	/*
+	 * first, detect marker mmap (i.e., the jitdump mmap)
+	 */
+	if (jit_detect(filename, pid))
+		return 0;
+
+	memset(&jd, 0, sizeof(jd));
+
+	jd.session = session;
+	jd.output  = output;
+	jd.machine = machine;
+
+	/*
+	 * track sample_type to compute id_all layout
+	 * perf sets the same sample type to all events as of now
+	 */
+	first = perf_evlist__first(session->evlist);
+	jd.sample_type = first->attr.sample_type;
+
+	*nbytes = 0;
+
+	ret = jit_inject(&jd, filename);
+	if (!ret) {
+		*nbytes = jd.bytes_written;
+		ret = 1;
+	}
+
+	return ret;
+}
diff --git a/tools/perf/util/jitdump.h b/tools/perf/util/jitdump.h
new file mode 100644
index 000000000..b66c1f503
--- /dev/null
+++ b/tools/perf/util/jitdump.h
@@ -0,0 +1,124 @@
+/*
+ * jitdump.h: jitted code info encapsulation file format
+ *
+ * Adapted from OProfile GPLv2 support jidump.h:
+ * Copyright 2007 OProfile authors
+ * Jens Wilke
+ * Daniel Hansel
+ * Copyright IBM Corporation 2007
+ */
+#ifndef JITDUMP_H
+#define JITDUMP_H
+
+#include <sys/time.h>
+#include <time.h>
+#include <stdint.h>
+
+/* JiTD */
+#define JITHEADER_MAGIC		0x4A695444
+#define JITHEADER_MAGIC_SW	0x4454694A
+
+#define PADDING_8ALIGNED(x) ((((x) + 7) & 7) ^ 7)
+
+#define JITHEADER_VERSION 1
+
+enum jitdump_flags_bits {
+	JITDUMP_FLAGS_MAX_BIT,
+};
+
+#define JITDUMP_FLAGS_RESERVED (JITDUMP_FLAGS_MAX_BIT < 64 ? \
+				(~((1ULL << JITDUMP_FLAGS_MAX_BIT) - 1)) : 0)
+
+struct jitheader {
+	uint32_t magic;		/* characters "jItD" */
+	uint32_t version;	/* header version */
+	uint32_t total_size;	/* total size of header */
+	uint32_t elf_mach;	/* elf mach target */
+	uint32_t pad1;		/* reserved */
+	uint32_t pid;		/* JIT process id */
+	uint64_t timestamp;	/* timestamp */
+	uint64_t flags;		/* flags */
+};
+
+enum jit_record_type {
+	JIT_CODE_LOAD		= 0,
+        JIT_CODE_MOVE           = 1,
+	JIT_CODE_DEBUG_INFO	= 2,
+	JIT_CODE_CLOSE		= 3,
+
+	JIT_CODE_MAX,
+};
+
+/* record prefix (mandatory in each record) */
+struct jr_prefix {
+	uint32_t id;
+	uint32_t total_size;
+	uint64_t timestamp;
+};
+
+struct jr_code_load {
+	struct jr_prefix p;
+
+	uint32_t pid;
+	uint32_t tid;
+	uint64_t vma;
+	uint64_t code_addr;
+	uint64_t code_size;
+	uint64_t code_index;
+};
+
+struct jr_code_close {
+	struct jr_prefix p;
+};
+
+struct jr_code_move {
+	struct jr_prefix p;
+
+	uint32_t pid;
+	uint32_t tid;
+	uint64_t vma;
+	uint64_t old_code_addr;
+	uint64_t new_code_addr;
+	uint64_t code_size;
+	uint64_t code_index;
+};
+
+struct debug_entry {
+	uint64_t addr;
+	int lineno;	    /* source line number starting at 1 */
+	int discrim;	    /* column discriminator, 0 is default */
+	const char name[0]; /* null terminated filename, \xff\0 if same as previous entry */
+};
+
+struct jr_code_debug_info {
+	struct jr_prefix p;
+
+	uint64_t code_addr;
+	uint64_t nr_entry;
+	struct debug_entry entries[0];
+};
+
+union jr_entry {
+        struct jr_code_debug_info info;
+        struct jr_code_close close;
+        struct jr_code_load load;
+        struct jr_code_move move;
+        struct jr_prefix prefix;
+};
+
+static inline struct debug_entry *
+debug_entry_next(struct debug_entry *ent)
+{
+	void *a = ent + 1;
+	size_t l = strlen(ent->name) + 1;
+	return a + l;
+}
+
+static inline char *
+debug_entry_file(struct debug_entry *ent)
+{
+	void *a = ent + 1;
+	return a;
+}
+
+#endif /* !JITDUMP_H */
diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h
index ae825d4ec..d01e73592 100644
--- a/tools/perf/util/kvm-stat.h
+++ b/tools/perf/util/kvm-stat.h
@@ -122,6 +122,7 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm,
 
 bool kvm_exit_event(struct perf_evsel *evsel);
 bool kvm_entry_event(struct perf_evsel *evsel);
+int setup_kvm_events_tp(struct perf_kvm_stat *kvm);
 
 #define define_exit_reasons_table(name, symbols)	\
 	static struct exit_reasons_table name[] = {	\
@@ -133,8 +134,13 @@ bool kvm_entry_event(struct perf_evsel *evsel);
  */
 int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid);
 
-extern const char * const kvm_events_tp[];
+extern const char *kvm_events_tp[];
 extern struct kvm_reg_events_ops kvm_reg_events_ops[];
 extern const char * const kvm_skip_events[];
+extern const char *vcpu_id_str;
+extern const int decode_str_len;
+extern const char *kvm_exit_reason;
+extern const char *kvm_entry_trace;
+extern const char *kvm_exit_trace;
 
 #endif /* __PERF_KVM_STAT_H */
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 00724d496..33071d615 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -3,11 +3,11 @@
  * Copyright (C) 2015, Huawei Inc.
  */
 
+#include <limits.h>
 #include <stdio.h>
-#include "util.h"
+#include <stdlib.h>
 #include "debug.h"
 #include "llvm-utils.h"
-#include "cache.h"
 
 #define CLANG_BPF_CMD_DEFAULT_TEMPLATE				\
 		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
@@ -98,11 +98,12 @@ read_from_pipe(const char *cmd, void **p_buf, size_t *p_read_sz)
 	void *buf = NULL;
 	FILE *file = NULL;
 	size_t read_sz = 0, buf_sz = 0;
+	char serr[STRERR_BUFSIZE];
 
 	file = popen(cmd, "r");
 	if (!file) {
 		pr_err("ERROR: unable to popen cmd: %s\n",
-		       strerror(errno));
+		       strerror_r(errno, serr, sizeof(serr)));
 		return -EINVAL;
 	}
 
@@ -136,7 +137,7 @@ read_from_pipe(const char *cmd, void **p_buf, size_t *p_read_sz)
 
 	if (ferror(file)) {
 		pr_err("ERROR: error occurred when reading from pipe: %s\n",
-		       strerror(errno));
+		       strerror_r(errno, serr, sizeof(serr)));
 		err = -EIO;
 		goto errout;
 	}
@@ -334,10 +335,18 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	unsigned int kernel_version;
 	char linux_version_code_str[64];
 	const char *clang_opt = llvm_param.clang_opt;
-	char clang_path[PATH_MAX], nr_cpus_avail_str[64];
+	char clang_path[PATH_MAX], abspath[PATH_MAX], nr_cpus_avail_str[64];
+	char serr[STRERR_BUFSIZE];
 	char *kbuild_dir = NULL, *kbuild_include_opts = NULL;
 	const char *template = llvm_param.clang_bpf_cmd_template;
 
+	if (path[0] != '-' && realpath(path, abspath) == NULL) {
+		err = errno;
+		pr_err("ERROR: problems with path %s: %s\n",
+		       path, strerror_r(err, serr, sizeof(serr)));
+		return -err;
+	}
+
 	if (!template)
 		template = CLANG_BPF_CMD_DEFAULT_TEMPLATE;
 
@@ -362,7 +371,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	if (nr_cpus_avail <= 0) {
 		pr_err(
 "WARNING:\tunable to get available CPUs in this system: %s\n"
-"        \tUse 128 instead.\n", strerror(errno));
+"        \tUse 128 instead.\n", strerror_r(errno, serr, sizeof(serr)));
 		nr_cpus_avail = 128;
 	}
 	snprintf(nr_cpus_avail_str, sizeof(nr_cpus_avail_str), "%d",
@@ -387,8 +396,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	 * stdin to be source file (testing).
 	 */
 	force_set_env("CLANG_SOURCE",
-		      (path[0] == '-') ? path :
-		      make_nonrelative_path(path));
+		      (path[0] == '-') ? path : abspath);
 
 	pr_debug("llvm compiling command template: %s\n", template);
 	err = read_from_pipe(template, &obj_buf, &obj_buf_sz);
diff --git a/tools/perf/util/llvm-utils.h b/tools/perf/util/llvm-utils.h
index 5b3cf1c22..23b9a743f 100644
--- a/tools/perf/util/llvm-utils.h
+++ b/tools/perf/util/llvm-utils.h
@@ -39,11 +39,10 @@ struct llvm_param {
 };
 
 extern struct llvm_param llvm_param;
-extern int perf_llvm_config(const char *var, const char *value);
+int perf_llvm_config(const char *var, const char *value);
 
-extern int llvm__compile_bpf(const char *path, void **p_obj_buf,
-			     size_t *p_obj_buf_sz);
+int llvm__compile_bpf(const char *path, void **p_obj_buf, size_t *p_obj_buf_sz);
 
 /* This function is for test__llvm() use only */
-extern int llvm__search_clang(void);
+int llvm__search_clang(void);
 #endif
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index ad79297c7..80b9b6a87 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1301,9 +1301,8 @@ out_problem:
 
 int machine__process_mmap2_event(struct machine *machine,
 				 union perf_event *event,
-				 struct perf_sample *sample __maybe_unused)
+				 struct perf_sample *sample)
 {
-	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	struct thread *thread;
 	struct map *map;
 	enum map_type type;
@@ -1312,8 +1311,8 @@ int machine__process_mmap2_event(struct machine *machine,
 	if (dump_trace)
 		perf_event__fprintf_mmap2(event, stdout);
 
-	if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
-	    cpumode == PERF_RECORD_MISC_KERNEL) {
+	if (sample->cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
+	    sample->cpumode == PERF_RECORD_MISC_KERNEL) {
 		ret = machine__process_kernel_mmap_event(machine, event);
 		if (ret < 0)
 			goto out_problem;
@@ -1355,9 +1354,8 @@ out_problem:
 }
 
 int machine__process_mmap_event(struct machine *machine, union perf_event *event,
-				struct perf_sample *sample __maybe_unused)
+				struct perf_sample *sample)
 {
-	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	struct thread *thread;
 	struct map *map;
 	enum map_type type;
@@ -1366,8 +1364,8 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 	if (dump_trace)
 		perf_event__fprintf_mmap(event, stdout);
 
-	if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
-	    cpumode == PERF_RECORD_MISC_KERNEL) {
+	if (sample->cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
+	    sample->cpumode == PERF_RECORD_MISC_KERNEL) {
 		ret = machine__process_kernel_mmap_event(machine, event);
 		if (ret < 0)
 			goto out_problem;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 2c2b443df..8499db281 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -94,7 +94,7 @@ int machine__process_aux_event(struct machine *machine,
 			       union perf_event *event);
 int machine__process_itrace_start_event(struct machine *machine,
 					union perf_event *event);
-int machine__process_switch_event(struct machine *machine __maybe_unused,
+int machine__process_switch_event(struct machine *machine,
 				  union perf_event *event);
 int machine__process_mmap_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
@@ -180,6 +180,16 @@ struct symbol *machine__find_kernel_symbol(struct machine *machine,
 }
 
 static inline
+struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine,
+						   enum map_type type, const char *name,
+						   struct map **mapp,
+						   symbol_filter_t filter)
+{
+	return map_groups__find_symbol_by_name(&machine->kmaps, type, name,
+					       mapp, filter);
+}
+
+static inline
 struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr,
 					     struct map **mapp,
 					     symbol_filter_t filter)
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
new file mode 100644
index 000000000..75465f89a
--- /dev/null
+++ b/tools/perf/util/mem-events.c
@@ -0,0 +1,255 @@
+#include <stddef.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <api/fs/fs.h>
+#include "mem-events.h"
+#include "debug.h"
+#include "symbol.h"
+
+#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
+
+struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
+	E("ldlat-loads",	"cpu/mem-loads,ldlat=30/P",	"mem-loads"),
+	E("ldlat-stores",	"cpu/mem-stores/P",		"mem-stores"),
+};
+#undef E
+
+#undef E
+
+char *perf_mem_events__name(int i)
+{
+	return (char *)perf_mem_events[i].name;
+}
+
+int perf_mem_events__parse(const char *str)
+{
+	char *tok, *saveptr = NULL;
+	bool found = false;
+	char *buf;
+	int j;
+
+	/* We need buffer that we know we can write to. */
+	buf = malloc(strlen(str) + 1);
+	if (!buf)
+		return -ENOMEM;
+
+	strcpy(buf, str);
+
+	tok = strtok_r((char *)buf, ",", &saveptr);
+
+	while (tok) {
+		for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+			struct perf_mem_event *e = &perf_mem_events[j];
+
+			if (strstr(e->tag, tok))
+				e->record = found = true;
+		}
+
+		tok = strtok_r(NULL, ",", &saveptr);
+	}
+
+	free(buf);
+
+	if (found)
+		return 0;
+
+	pr_err("failed: event '%s' not found, use '-e list' to get list of available events\n", str);
+	return -1;
+}
+
+int perf_mem_events__init(void)
+{
+	const char *mnt = sysfs__mount();
+	bool found = false;
+	int j;
+
+	if (!mnt)
+		return -ENOENT;
+
+	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+		char path[PATH_MAX];
+		struct perf_mem_event *e = &perf_mem_events[j];
+		struct stat st;
+
+		scnprintf(path, PATH_MAX, "%s/devices/cpu/events/%s",
+			  mnt, e->sysfs_name);
+
+		if (!stat(path, &st))
+			e->supported = found = true;
+	}
+
+	return found ? 0 : -ENOENT;
+}
+
+static const char * const tlb_access[] = {
+	"N/A",
+	"HIT",
+	"MISS",
+	"L1",
+	"L2",
+	"Walker",
+	"Fault",
+};
+
+int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	size_t l = 0, i;
+	u64 m = PERF_MEM_TLB_NA;
+	u64 hit, miss;
+
+	sz -= 1; /* -1 for null termination */
+	out[0] = '\0';
+
+	if (mem_info)
+		m = mem_info->data_src.mem_dtlb;
+
+	hit = m & PERF_MEM_TLB_HIT;
+	miss = m & PERF_MEM_TLB_MISS;
+
+	/* already taken care of */
+	m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS);
+
+	for (i = 0; m && i < ARRAY_SIZE(tlb_access); i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		l += scnprintf(out + l, sz - l, tlb_access[i]);
+	}
+	if (*out == '\0')
+		l += scnprintf(out, sz - l, "N/A");
+	if (hit)
+		l += scnprintf(out + l, sz - l, " hit");
+	if (miss)
+		l += scnprintf(out + l, sz - l, " miss");
+
+	return l;
+}
+
+static const char * const mem_lvl[] = {
+	"N/A",
+	"HIT",
+	"MISS",
+	"L1",
+	"LFB",
+	"L2",
+	"L3",
+	"Local RAM",
+	"Remote RAM (1 hop)",
+	"Remote RAM (2 hops)",
+	"Remote Cache (1 hop)",
+	"Remote Cache (2 hops)",
+	"I/O",
+	"Uncached",
+};
+
+int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	size_t i, l = 0;
+	u64 m =  PERF_MEM_LVL_NA;
+	u64 hit, miss;
+
+	if (mem_info)
+		m  = mem_info->data_src.mem_lvl;
+
+	sz -= 1; /* -1 for null termination */
+	out[0] = '\0';
+
+	hit = m & PERF_MEM_LVL_HIT;
+	miss = m & PERF_MEM_LVL_MISS;
+
+	/* already taken care of */
+	m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
+
+	for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		l += scnprintf(out + l, sz - l, mem_lvl[i]);
+	}
+	if (*out == '\0')
+		l += scnprintf(out, sz - l, "N/A");
+	if (hit)
+		l += scnprintf(out + l, sz - l, " hit");
+	if (miss)
+		l += scnprintf(out + l, sz - l, " miss");
+
+	return l;
+}
+
+static const char * const snoop_access[] = {
+	"N/A",
+	"None",
+	"Miss",
+	"Hit",
+	"HitM",
+};
+
+int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	size_t i, l = 0;
+	u64 m = PERF_MEM_SNOOP_NA;
+
+	sz -= 1; /* -1 for null termination */
+	out[0] = '\0';
+
+	if (mem_info)
+		m = mem_info->data_src.mem_snoop;
+
+	for (i = 0; m && i < ARRAY_SIZE(snoop_access); i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		l += scnprintf(out + l, sz - l, snoop_access[i]);
+	}
+
+	if (*out == '\0')
+		l += scnprintf(out, sz - l, "N/A");
+
+	return l;
+}
+
+int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	u64 mask = PERF_MEM_LOCK_NA;
+	int l;
+
+	if (mem_info)
+		mask = mem_info->data_src.mem_lock;
+
+	if (mask & PERF_MEM_LOCK_NA)
+		l = scnprintf(out, sz, "N/A");
+	else if (mask & PERF_MEM_LOCK_LOCKED)
+		l = scnprintf(out, sz, "Yes");
+	else
+		l = scnprintf(out, sz, "No");
+
+	return l;
+}
+
+int perf_script__meminfo_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	int i = 0;
+
+	i += perf_mem__lvl_scnprintf(out, sz, mem_info);
+	i += scnprintf(out + i, sz - i, "|SNP ");
+	i += perf_mem__snp_scnprintf(out + i, sz - i, mem_info);
+	i += scnprintf(out + i, sz - i, "|TLB ");
+	i += perf_mem__tlb_scnprintf(out + i, sz - i, mem_info);
+	i += scnprintf(out + i, sz - i, "|LCK ");
+	i += perf_mem__lck_scnprintf(out + i, sz - i, mem_info);
+
+	return i;
+}
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
new file mode 100644
index 000000000..5d6d93066
--- /dev/null
+++ b/tools/perf/util/mem-events.h
@@ -0,0 +1,35 @@
+#ifndef __PERF_MEM_EVENTS_H
+#define __PERF_MEM_EVENTS_H
+
+#include <stdbool.h>
+
+struct perf_mem_event {
+	bool		record;
+	bool		supported;
+	const char	*tag;
+	const char	*name;
+	const char	*sysfs_name;
+};
+
+enum {
+	PERF_MEM_EVENTS__LOAD,
+	PERF_MEM_EVENTS__STORE,
+	PERF_MEM_EVENTS__MAX,
+};
+
+extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
+
+int perf_mem_events__parse(const char *str);
+int perf_mem_events__init(void);
+
+char *perf_mem_events__name(int i);
+
+struct mem_info;
+int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+
+int perf_script__meminfo_scnprintf(char *bf, size_t size, struct mem_info *mem_info);
+
+#endif /* __PERF_MEM_EVENTS_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 48a1c5e7d..bcbc983d4 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -138,11 +138,11 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
 #define PERF_EVENT_TYPE(config)		__PERF_EVENT_FIELD(config, TYPE)
 #define PERF_EVENT_ID(config)		__PERF_EVENT_FIELD(config, EVENT)
 
-#define for_each_subsystem(sys_dir, sys_dirent, sys_next)	       \
-	while (!readdir_r(sys_dir, &sys_dirent, &sys_next) && sys_next)	       \
-	if (sys_dirent.d_type == DT_DIR &&				       \
-	   (strcmp(sys_dirent.d_name, ".")) &&				       \
-	   (strcmp(sys_dirent.d_name, "..")))
+#define for_each_subsystem(sys_dir, sys_dirent)			\
+	while ((sys_dirent = readdir(sys_dir)) != NULL)		\
+		if (sys_dirent->d_type == DT_DIR &&		\
+		    (strcmp(sys_dirent->d_name, ".")) &&	\
+		    (strcmp(sys_dirent->d_name, "..")))
 
 static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir)
 {
@@ -159,12 +159,12 @@ static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir)
 	return 0;
 }
 
-#define for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next)	       \
-	while (!readdir_r(evt_dir, &evt_dirent, &evt_next) && evt_next)        \
-	if (evt_dirent.d_type == DT_DIR &&				       \
-	   (strcmp(evt_dirent.d_name, ".")) &&				       \
-	   (strcmp(evt_dirent.d_name, "..")) &&				       \
-	   (!tp_event_has_id(&sys_dirent, &evt_dirent)))
+#define for_each_event(sys_dirent, evt_dir, evt_dirent)		\
+	while ((evt_dirent = readdir(evt_dir)) != NULL)		\
+		if (evt_dirent->d_type == DT_DIR &&		\
+		    (strcmp(evt_dirent->d_name, ".")) &&	\
+		    (strcmp(evt_dirent->d_name, "..")) &&	\
+		    (!tp_event_has_id(sys_dirent, evt_dirent)))
 
 #define MAX_EVENT_LENGTH 512
 
@@ -173,7 +173,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 {
 	struct tracepoint_path *path = NULL;
 	DIR *sys_dir, *evt_dir;
-	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
+	struct dirent *sys_dirent, *evt_dirent;
 	char id_buf[24];
 	int fd;
 	u64 id;
@@ -184,18 +184,18 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 	if (!sys_dir)
 		return NULL;
 
-	for_each_subsystem(sys_dir, sys_dirent, sys_next) {
+	for_each_subsystem(sys_dir, sys_dirent) {
 
 		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent.d_name);
+			 sys_dirent->d_name);
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
 			continue;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
+		for_each_event(sys_dirent, evt_dir, evt_dirent) {
 
 			snprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path,
-				 evt_dirent.d_name);
+				 evt_dirent->d_name);
 			fd = open(evt_path, O_RDONLY);
 			if (fd < 0)
 				continue;
@@ -220,9 +220,9 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 					free(path);
 					return NULL;
 				}
-				strncpy(path->system, sys_dirent.d_name,
+				strncpy(path->system, sys_dirent->d_name,
 					MAX_EVENT_LENGTH);
-				strncpy(path->name, evt_dirent.d_name,
+				strncpy(path->name, evt_dirent->d_name,
 					MAX_EVENT_LENGTH);
 				return path;
 			}
@@ -279,7 +279,24 @@ const char *event_type(int type)
 	return "unknown";
 }
 
+static int parse_events__is_name_term(struct parse_events_term *term)
+{
+	return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME;
+}
 
+static char *get_config_name(struct list_head *head_terms)
+{
+	struct parse_events_term *term;
+
+	if (!head_terms)
+		return NULL;
+
+	list_for_each_entry(term, head_terms, list)
+		if (parse_events__is_name_term(term))
+			return term->val.str;
+
+	return NULL;
+}
 
 static struct perf_evsel *
 __add_event(struct list_head *list, int *idx,
@@ -333,11 +350,25 @@ static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES]
 	return -1;
 }
 
+typedef int config_term_func_t(struct perf_event_attr *attr,
+			       struct parse_events_term *term,
+			       struct parse_events_error *err);
+static int config_term_common(struct perf_event_attr *attr,
+			      struct parse_events_term *term,
+			      struct parse_events_error *err);
+static int config_attr(struct perf_event_attr *attr,
+		       struct list_head *head,
+		       struct parse_events_error *err,
+		       config_term_func_t config_term);
+
 int parse_events_add_cache(struct list_head *list, int *idx,
-			   char *type, char *op_result1, char *op_result2)
+			   char *type, char *op_result1, char *op_result2,
+			   struct parse_events_error *err,
+			   struct list_head *head_config)
 {
 	struct perf_event_attr attr;
-	char name[MAX_NAME_LEN];
+	LIST_HEAD(config_terms);
+	char name[MAX_NAME_LEN], *config_name;
 	int cache_type = -1, cache_op = -1, cache_result = -1;
 	char *op_result[2] = { op_result1, op_result2 };
 	int i, n;
@@ -351,6 +382,7 @@ int parse_events_add_cache(struct list_head *list, int *idx,
 	if (cache_type == -1)
 		return -EINVAL;
 
+	config_name = get_config_name(head_config);
 	n = snprintf(name, MAX_NAME_LEN, "%s", type);
 
 	for (i = 0; (i < 2) && (op_result[i]); i++) {
@@ -391,7 +423,16 @@ int parse_events_add_cache(struct list_head *list, int *idx,
 	memset(&attr, 0, sizeof(attr));
 	attr.config = cache_type | (cache_op << 8) | (cache_result << 16);
 	attr.type = PERF_TYPE_HW_CACHE;
-	return add_event(list, idx, &attr, name, NULL);
+
+	if (head_config) {
+		if (config_attr(&attr, head_config, err,
+				config_term_common))
+			return -EINVAL;
+
+		if (get_config_terms(head_config, &config_terms))
+			return -ENOMEM;
+	}
+	return add_event(list, idx, &attr, config_name ? : name, &config_terms);
 }
 
 static void tracepoint_error(struct parse_events_error *e, int err,
@@ -540,6 +581,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 struct __add_bpf_event_param {
 	struct parse_events_evlist *data;
 	struct list_head *list;
+	struct list_head *head_config;
 };
 
 static int add_bpf_event(struct probe_trace_event *tev, int fd,
@@ -556,7 +598,8 @@ static int add_bpf_event(struct probe_trace_event *tev, int fd,
 		 tev->group, tev->event, fd);
 
 	err = parse_events_add_tracepoint(&new_evsels, &evlist->idx, tev->group,
-					  tev->event, evlist->error, NULL);
+					  tev->event, evlist->error,
+					  param->head_config);
 	if (err) {
 		struct perf_evsel *evsel, *tmp;
 
@@ -581,11 +624,12 @@ static int add_bpf_event(struct probe_trace_event *tev, int fd,
 
 int parse_events_load_bpf_obj(struct parse_events_evlist *data,
 			      struct list_head *list,
-			      struct bpf_object *obj)
+			      struct bpf_object *obj,
+			      struct list_head *head_config)
 {
 	int err;
 	char errbuf[BUFSIZ];
-	struct __add_bpf_event_param param = {data, list};
+	struct __add_bpf_event_param param = {data, list, head_config};
 	static bool registered_unprobe_atexit = false;
 
 	if (IS_ERR(obj) || !obj) {
@@ -631,17 +675,99 @@ errout:
 	return err;
 }
 
+static int
+parse_events_config_bpf(struct parse_events_evlist *data,
+			struct bpf_object *obj,
+			struct list_head *head_config)
+{
+	struct parse_events_term *term;
+	int error_pos;
+
+	if (!head_config || list_empty(head_config))
+		return 0;
+
+	list_for_each_entry(term, head_config, list) {
+		char errbuf[BUFSIZ];
+		int err;
+
+		if (term->type_term != PARSE_EVENTS__TERM_TYPE_USER) {
+			snprintf(errbuf, sizeof(errbuf),
+				 "Invalid config term for BPF object");
+			errbuf[BUFSIZ - 1] = '\0';
+
+			data->error->idx = term->err_term;
+			data->error->str = strdup(errbuf);
+			return -EINVAL;
+		}
+
+		err = bpf__config_obj(obj, term, data->evlist, &error_pos);
+		if (err) {
+			bpf__strerror_config_obj(obj, term, data->evlist,
+						 &error_pos, err, errbuf,
+						 sizeof(errbuf));
+			data->error->help = strdup(
+"Hint:\tValid config terms:\n"
+"     \tmap:[<arraymap>].value<indices>=[value]\n"
+"     \tmap:[<eventmap>].event<indices>=[event]\n"
+"\n"
+"     \twhere <indices> is something like [0,3...5] or [all]\n"
+"     \t(add -v to see detail)");
+			data->error->str = strdup(errbuf);
+			if (err == -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE)
+				data->error->idx = term->err_val;
+			else
+				data->error->idx = term->err_term + error_pos;
+			return err;
+		}
+	}
+	return 0;
+}
+
+/*
+ * Split config terms:
+ * perf record -e bpf.c/call-graph=fp,map:array.value[0]=1/ ...
+ *  'call-graph=fp' is 'evt config', should be applied to each
+ *  events in bpf.c.
+ * 'map:array.value[0]=1' is 'obj config', should be processed
+ * with parse_events_config_bpf.
+ *
+ * Move object config terms from the first list to obj_head_config.
+ */
+static void
+split_bpf_config_terms(struct list_head *evt_head_config,
+		       struct list_head *obj_head_config)
+{
+	struct parse_events_term *term, *temp;
+
+	/*
+	 * Currectly, all possible user config term
+	 * belong to bpf object. parse_events__is_hardcoded_term()
+	 * happends to be a good flag.
+	 *
+	 * See parse_events_config_bpf() and
+	 * config_term_tracepoint().
+	 */
+	list_for_each_entry_safe(term, temp, evt_head_config, list)
+		if (!parse_events__is_hardcoded_term(term))
+			list_move_tail(&term->list, obj_head_config);
+}
+
 int parse_events_load_bpf(struct parse_events_evlist *data,
 			  struct list_head *list,
 			  char *bpf_file_name,
-			  bool source)
+			  bool source,
+			  struct list_head *head_config)
 {
+	int err;
 	struct bpf_object *obj;
+	LIST_HEAD(obj_head_config);
+
+	if (head_config)
+		split_bpf_config_terms(head_config, &obj_head_config);
 
 	obj = bpf__prepare_load(bpf_file_name, source);
 	if (IS_ERR(obj)) {
 		char errbuf[BUFSIZ];
-		int err;
 
 		err = PTR_ERR(obj);
 
@@ -659,7 +785,18 @@ int parse_events_load_bpf(struct parse_events_evlist *data,
 		return err;
 	}
 
-	return parse_events_load_bpf_obj(data, list, obj);
+	err = parse_events_load_bpf_obj(data, list, obj, head_config);
+	if (err)
+		return err;
+	err = parse_events_config_bpf(data, obj, &obj_head_config);
+
+	/*
+	 * Caller doesn't know anything about obj_head_config,
+	 * so combine them together again before returnning.
+	 */
+	if (head_config)
+		list_splice_tail(&obj_head_config, head_config);
+	return err;
 }
 
 static int
@@ -746,9 +883,59 @@ static int check_type_val(struct parse_events_term *term,
 	return -EINVAL;
 }
 
-typedef int config_term_func_t(struct perf_event_attr *attr,
-			       struct parse_events_term *term,
-			       struct parse_events_error *err);
+/*
+ * Update according to parse-events.l
+ */
+static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
+	[PARSE_EVENTS__TERM_TYPE_USER]			= "<sysfs term>",
+	[PARSE_EVENTS__TERM_TYPE_CONFIG]		= "config",
+	[PARSE_EVENTS__TERM_TYPE_CONFIG1]		= "config1",
+	[PARSE_EVENTS__TERM_TYPE_CONFIG2]		= "config2",
+	[PARSE_EVENTS__TERM_TYPE_NAME]			= "name",
+	[PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD]		= "period",
+	[PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ]		= "freq",
+	[PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE]	= "branch_type",
+	[PARSE_EVENTS__TERM_TYPE_TIME]			= "time",
+	[PARSE_EVENTS__TERM_TYPE_CALLGRAPH]		= "call-graph",
+	[PARSE_EVENTS__TERM_TYPE_STACKSIZE]		= "stack-size",
+	[PARSE_EVENTS__TERM_TYPE_NOINHERIT]		= "no-inherit",
+	[PARSE_EVENTS__TERM_TYPE_INHERIT]		= "inherit",
+};
+
+static bool config_term_shrinked;
+
+static bool
+config_term_avail(int term_type, struct parse_events_error *err)
+{
+	if (term_type < 0 || term_type >= __PARSE_EVENTS__TERM_TYPE_NR) {
+		err->str = strdup("Invalid term_type");
+		return false;
+	}
+	if (!config_term_shrinked)
+		return true;
+
+	switch (term_type) {
+	case PARSE_EVENTS__TERM_TYPE_CONFIG:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG1:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG2:
+	case PARSE_EVENTS__TERM_TYPE_NAME:
+		return true;
+	default:
+		if (!err)
+			return false;
+
+		/* term_type is validated so indexing is safe */
+		if (asprintf(&err->str, "'%s' is not usable in 'perf stat'",
+			     config_term_names[term_type]) < 0)
+			err->str = NULL;
+		return false;
+	}
+}
+
+void parse_events__shrink_config_terms(void)
+{
+	config_term_shrinked = true;
+}
 
 static int config_term_common(struct perf_event_attr *attr,
 			      struct parse_events_term *term,
@@ -815,6 +1002,17 @@ do {									   \
 		return -EINVAL;
 	}
 
+	/*
+	 * Check term availbility after basic checking so
+	 * PARSE_EVENTS__TERM_TYPE_USER can be found and filtered.
+	 *
+	 * If check availbility at the entry of this function,
+	 * user will see "'<sysfs term>' is not usable in 'perf stat'"
+	 * if an invalid config term is provided for legacy events
+	 * (for example, instructions/badterm/...), which is confusing.
+	 */
+	if (!config_term_avail(term->type_term, err))
+		return -EINVAL;
 	return 0;
 #undef CHECK_TYPE_VAL
 }
@@ -961,23 +1159,8 @@ int parse_events_add_numeric(struct parse_events_evlist *data,
 			return -ENOMEM;
 	}
 
-	return add_event(list, &data->idx, &attr, NULL, &config_terms);
-}
-
-static int parse_events__is_name_term(struct parse_events_term *term)
-{
-	return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME;
-}
-
-static char *pmu_event_name(struct list_head *head_terms)
-{
-	struct parse_events_term *term;
-
-	list_for_each_entry(term, head_terms, list)
-		if (parse_events__is_name_term(term))
-			return term->val.str;
-
-	return NULL;
+	return add_event(list, &data->idx, &attr,
+			 get_config_name(head_config), &config_terms);
 }
 
 int parse_events_add_pmu(struct parse_events_evlist *data,
@@ -1024,7 +1207,7 @@ int parse_events_add_pmu(struct parse_events_evlist *data,
 		return -EINVAL;
 
 	evsel = __add_event(list, &data->idx, &attr,
-			    pmu_event_name(head_config), pmu->cpus,
+			    get_config_name(head_config), pmu->cpus,
 			    &config_terms);
 	if (evsel) {
 		evsel->unit = info.unit;
@@ -1386,8 +1569,7 @@ int parse_events_terms(struct list_head *terms, const char *str)
 		return 0;
 	}
 
-	if (data.terms)
-		parse_events__free_terms(data.terms);
+	parse_events_terms__delete(data.terms);
 	return ret;
 }
 
@@ -1395,9 +1577,10 @@ int parse_events(struct perf_evlist *evlist, const char *str,
 		 struct parse_events_error *err)
 {
 	struct parse_events_evlist data = {
-		.list  = LIST_HEAD_INIT(data.list),
-		.idx   = evlist->nr_entries,
-		.error = err,
+		.list   = LIST_HEAD_INIT(data.list),
+		.idx    = evlist->nr_entries,
+		.error  = err,
+		.evlist = evlist,
 	};
 	int ret;
 
@@ -1629,7 +1812,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 			     bool name_only)
 {
 	DIR *sys_dir, *evt_dir;
-	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
+	struct dirent *sys_dirent, *evt_dirent;
 	char evt_path[MAXPATHLEN];
 	char dir_path[MAXPATHLEN];
 	char **evt_list = NULL;
@@ -1647,20 +1830,20 @@ restart:
 			goto out_close_sys_dir;
 	}
 
-	for_each_subsystem(sys_dir, sys_dirent, sys_next) {
+	for_each_subsystem(sys_dir, sys_dirent) {
 		if (subsys_glob != NULL &&
-		    !strglobmatch(sys_dirent.d_name, subsys_glob))
+		    !strglobmatch(sys_dirent->d_name, subsys_glob))
 			continue;
 
 		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent.d_name);
+			 sys_dirent->d_name);
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
 			continue;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
+		for_each_event(sys_dirent, evt_dir, evt_dirent) {
 			if (event_glob != NULL &&
-			    !strglobmatch(evt_dirent.d_name, event_glob))
+			    !strglobmatch(evt_dirent->d_name, event_glob))
 				continue;
 
 			if (!evt_num_known) {
@@ -1669,7 +1852,7 @@ restart:
 			}
 
 			snprintf(evt_path, MAXPATHLEN, "%s:%s",
-				 sys_dirent.d_name, evt_dirent.d_name);
+				 sys_dirent->d_name, evt_dirent->d_name);
 
 			evt_list[evt_i] = strdup(evt_path);
 			if (evt_list[evt_i] == NULL)
@@ -1722,7 +1905,7 @@ out_close_sys_dir:
 int is_valid_tracepoint(const char *event_string)
 {
 	DIR *sys_dir, *evt_dir;
-	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
+	struct dirent *sys_dirent, *evt_dirent;
 	char evt_path[MAXPATHLEN];
 	char dir_path[MAXPATHLEN];
 
@@ -1730,17 +1913,17 @@ int is_valid_tracepoint(const char *event_string)
 	if (!sys_dir)
 		return 0;
 
-	for_each_subsystem(sys_dir, sys_dirent, sys_next) {
+	for_each_subsystem(sys_dir, sys_dirent) {
 
 		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent.d_name);
+			 sys_dirent->d_name);
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
 			continue;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
+		for_each_event(sys_dirent, evt_dir, evt_dirent) {
 			snprintf(evt_path, MAXPATHLEN, "%s:%s",
-				 sys_dirent.d_name, evt_dirent.d_name);
+				 sys_dirent->d_name, evt_dirent->d_name);
 			if (!strcmp(evt_path, event_string)) {
 				closedir(evt_dir);
 				closedir(sys_dir);
@@ -2068,12 +2251,29 @@ int parse_events_term__clone(struct parse_events_term **new,
 			term->err_term, term->err_val);
 }
 
-void parse_events__free_terms(struct list_head *terms)
+void parse_events_terms__purge(struct list_head *terms)
 {
 	struct parse_events_term *term, *h;
 
-	list_for_each_entry_safe(term, h, terms, list)
+	list_for_each_entry_safe(term, h, terms, list) {
+		if (term->array.nr_ranges)
+			free(term->array.ranges);
+		list_del_init(&term->list);
 		free(term);
+	}
+}
+
+void parse_events_terms__delete(struct list_head *terms)
+{
+	if (!terms)
+		return;
+	parse_events_terms__purge(terms);
+	free(terms);
+}
+
+void parse_events__clear_array(struct parse_events_array *a)
+{
+	free(a->ranges);
 }
 
 void parse_events_evlist_error(struct parse_events_evlist *data,
@@ -2088,6 +2288,33 @@ void parse_events_evlist_error(struct parse_events_evlist *data,
 	WARN_ONCE(!err->str, "WARNING: failed to allocate error string");
 }
 
+static void config_terms_list(char *buf, size_t buf_sz)
+{
+	int i;
+	bool first = true;
+
+	buf[0] = '\0';
+	for (i = 0; i < __PARSE_EVENTS__TERM_TYPE_NR; i++) {
+		const char *name = config_term_names[i];
+
+		if (!config_term_avail(i, NULL))
+			continue;
+		if (!name)
+			continue;
+		if (name[0] == '<')
+			continue;
+
+		if (strlen(buf) + strlen(name) + 2 >= buf_sz)
+			return;
+
+		if (!first)
+			strcat(buf, ",");
+		else
+			first = false;
+		strcat(buf, name);
+	}
+}
+
 /*
  * Return string contains valid config terms of an event.
  * @additional_terms: For terms such as PMU sysfs terms.
@@ -2095,10 +2322,11 @@ void parse_events_evlist_error(struct parse_events_evlist *data,
 char *parse_events_formats_error_string(char *additional_terms)
 {
 	char *str;
-	static const char *static_terms = "config,config1,config2,name,"
-					  "period,freq,branch_type,time,"
-					  "call-graph,stack-size\n";
+	/* "branch_type" is the longest name */
+	char static_terms[__PARSE_EVENTS__TERM_TYPE_NR *
+			  (sizeof("branch_type") - 1)];
 
+	config_terms_list(static_terms, sizeof(static_terms));
 	/* valid terms */
 	if (additional_terms) {
 		if (asprintf(&str, "valid terms: %s,%s",
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index f1a6db107..d740c3ca9 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -22,19 +22,18 @@ struct tracepoint_path {
 	struct tracepoint_path *next;
 };
 
-extern struct tracepoint_path *tracepoint_id_to_path(u64 config);
-extern struct tracepoint_path *tracepoint_name_to_path(const char *name);
-extern bool have_tracepoints(struct list_head *evlist);
+struct tracepoint_path *tracepoint_id_to_path(u64 config);
+struct tracepoint_path *tracepoint_name_to_path(const char *name);
+bool have_tracepoints(struct list_head *evlist);
 
 const char *event_type(int type);
 
-extern int parse_events_option(const struct option *opt, const char *str,
-			       int unset);
-extern int parse_events(struct perf_evlist *evlist, const char *str,
-			struct parse_events_error *error);
-extern int parse_events_terms(struct list_head *terms, const char *str);
-extern int parse_filter(const struct option *opt, const char *str, int unset);
-extern int exclude_perf(const struct option *opt, const char *arg, int unset);
+int parse_events_option(const struct option *opt, const char *str, int unset);
+int parse_events(struct perf_evlist *evlist, const char *str,
+		 struct parse_events_error *error);
+int parse_events_terms(struct list_head *terms, const char *str);
+int parse_filter(const struct option *opt, const char *str, int unset);
+int exclude_perf(const struct option *opt, const char *arg, int unset);
 
 #define EVENTS_HELP_MAX (128*1024)
 
@@ -68,11 +67,21 @@ enum {
 	PARSE_EVENTS__TERM_TYPE_CALLGRAPH,
 	PARSE_EVENTS__TERM_TYPE_STACKSIZE,
 	PARSE_EVENTS__TERM_TYPE_NOINHERIT,
-	PARSE_EVENTS__TERM_TYPE_INHERIT
+	PARSE_EVENTS__TERM_TYPE_INHERIT,
+	__PARSE_EVENTS__TERM_TYPE_NR,
+};
+
+struct parse_events_array {
+	size_t nr_ranges;
+	struct {
+		unsigned int start;
+		size_t length;
+	} *ranges;
 };
 
 struct parse_events_term {
 	char *config;
+	struct parse_events_array array;
 	union {
 		char *str;
 		u64  num;
@@ -98,12 +107,14 @@ struct parse_events_evlist {
 	int			   idx;
 	int			   nr_groups;
 	struct parse_events_error *error;
+	struct perf_evlist	  *evlist;
 };
 
 struct parse_events_terms {
 	struct list_head *terms;
 };
 
+void parse_events__shrink_config_terms(void);
 int parse_events__is_hardcoded_term(struct parse_events_term *term);
 int parse_events_term__num(struct parse_events_term **term,
 			   int type_term, char *config, u64 num,
@@ -115,7 +126,9 @@ int parse_events_term__sym_hw(struct parse_events_term **term,
 			      char *config, unsigned idx);
 int parse_events_term__clone(struct parse_events_term **new,
 			     struct parse_events_term *term);
-void parse_events__free_terms(struct list_head *terms);
+void parse_events_terms__delete(struct list_head *terms);
+void parse_events_terms__purge(struct list_head *terms);
+void parse_events__clear_array(struct parse_events_array *a);
 int parse_events__modifier_event(struct list_head *list, char *str, bool add);
 int parse_events__modifier_group(struct list_head *list, char *event_mod);
 int parse_events_name(struct list_head *list, char *name);
@@ -126,18 +139,22 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,
 int parse_events_load_bpf(struct parse_events_evlist *data,
 			  struct list_head *list,
 			  char *bpf_file_name,
-			  bool source);
+			  bool source,
+			  struct list_head *head_config);
 /* Provide this function for perf test */
 struct bpf_object;
 int parse_events_load_bpf_obj(struct parse_events_evlist *data,
 			      struct list_head *list,
-			      struct bpf_object *obj);
+			      struct bpf_object *obj,
+			      struct list_head *head_config);
 int parse_events_add_numeric(struct parse_events_evlist *data,
 			     struct list_head *list,
 			     u32 type, u64 config,
 			     struct list_head *head_config);
 int parse_events_add_cache(struct list_head *list, int *idx,
-			   char *type, char *op_result1, char *op_result2);
+			   char *type, char *op_result1, char *op_result2,
+			   struct parse_events_error *error,
+			   struct list_head *head_config);
 int parse_events_add_breakpoint(struct list_head *list, int *idx,
 				void *ptr, char *type, u64 len);
 int parse_events_add_pmu(struct parse_events_evlist *data,
@@ -165,7 +182,7 @@ void print_symbol_events(const char *event_glob, unsigned type,
 void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 			     bool name_only);
 int print_hwcache_events(const char *event_glob, bool name_only);
-extern int is_valid_tracepoint(const char *event_string);
+int is_valid_tracepoint(const char *event_string);
 
 int valid_event_mount(const char *eventfs);
 char *parse_events_formats_error_string(char *additional_terms);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 58c5831ff..1477fbc78 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -9,8 +9,8 @@
 %{
 #include <errno.h>
 #include "../perf.h"
-#include "parse-events-bison.h"
 #include "parse-events.h"
+#include "parse-events-bison.h"
 
 char *parse_events_get_text(yyscan_t yyscanner);
 YYSTYPE *parse_events_get_lval(yyscan_t yyscanner);
@@ -111,6 +111,7 @@ do {							\
 %x mem
 %s config
 %x event
+%x array
 
 group		[^,{}/]*[{][^}]*[}][^,{}/]*
 event_pmu	[^,{}/]+[/][^/]*[/][^,{}/]*
@@ -122,7 +123,7 @@ num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]+
 num_raw_hex	[a-fA-F0-9]+
 name		[a-zA-Z_*?][a-zA-Z0-9_*?.]*
-name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.]*
+name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
 /* If you add a modifier you need to update check_modifier() */
 modifier_event	[ukhpPGHSDI]+
 modifier_bp	[rwx]{1,3}
@@ -176,10 +177,17 @@ modifier_bp	[rwx]{1,3}
 
 }
 
+<array>{
+"]"			{ BEGIN(config); return ']'; }
+{num_dec}		{ return value(yyscanner, 10); }
+{num_hex}		{ return value(yyscanner, 16); }
+,			{ return ','; }
+"\.\.\."		{ return PE_ARRAY_RANGE; }
+}
+
 <config>{
 	/*
-	 * Please update parse_events_formats_error_string any time
-	 * new static term is added.
+	 * Please update config_term_names when new static term is added.
 	 */
 config			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
 config1			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); }
@@ -196,6 +204,8 @@ no-inherit		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
 ,			{ return ','; }
 "/"			{ BEGIN(INITIAL); return '/'; }
 {name_minus}		{ return str(yyscanner, PE_NAME); }
+\[all\]			{ return PE_ARRAY_ALL; }
+"["			{ BEGIN(array); return '['; }
 }
 
 <mem>{
@@ -238,6 +248,7 @@ cpu-migrations|migrations			{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COU
 alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
 emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
 dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
+bpf-output					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
 
 	/*
 	 * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately.
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index ad379968d..5be4a5f21 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -28,7 +28,7 @@ do { \
 	INIT_LIST_HEAD(list);         \
 } while (0)
 
-static inc_group_count(struct list_head *list,
+static void inc_group_count(struct list_head *list,
 		       struct parse_events_evlist *data)
 {
 	/* Count groups only have more than 1 members */
@@ -48,6 +48,7 @@ static inc_group_count(struct list_head *list,
 %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP
 %token PE_ERROR
 %token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
+%token PE_ARRAY_ALL PE_ARRAY_RANGE
 %type <num> PE_VALUE
 %type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
@@ -64,6 +65,7 @@ static inc_group_count(struct list_head *list,
 %type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
 %type <num> value_sym
 %type <head> event_config
+%type <head> opt_event_config
 %type <term> event_term
 %type <head> event_pmu
 %type <head> event_legacy_symbol
@@ -82,6 +84,9 @@ static inc_group_count(struct list_head *list,
 %type <head> group_def
 %type <head> group
 %type <head> groups
+%type <array> array
+%type <array> array_term
+%type <array> array_terms
 
 %union
 {
@@ -93,6 +98,7 @@ static inc_group_count(struct list_head *list,
 		char *sys;
 		char *event;
 	} tracepoint_name;
+	struct parse_events_array array;
 }
 %%
 
@@ -211,24 +217,14 @@ event_def: event_pmu |
 	   event_bpf_file
 
 event_pmu:
-PE_NAME '/' event_config '/'
+PE_NAME opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(data, list, $1, $3));
-	parse_events__free_terms($3);
-	$$ = list;
-}
-|
-PE_NAME '/' '/'
-{
-	struct parse_events_evlist *data = _data;
-	struct list_head *list;
-
-	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(data, list, $1, NULL));
+	ABORT_ON(parse_events_add_pmu(data, list, $1, $2));
+	parse_events_terms__delete($2);
 	$$ = list;
 }
 |
@@ -246,7 +242,7 @@ PE_KERNEL_PMU_EVENT sep_dc
 
 	ALLOC_LIST(list);
 	ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
-	parse_events__free_terms(head);
+	parse_events_terms__delete(head);
 	$$ = list;
 }
 |
@@ -266,7 +262,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
 
 	ALLOC_LIST(list);
 	ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
-	parse_events__free_terms(head);
+	parse_events_terms__delete(head);
 	$$ = list;
 }
 
@@ -285,7 +281,7 @@ value_sym '/' event_config '/'
 
 	ALLOC_LIST(list);
 	ABORT_ON(parse_events_add_numeric(data, list, type, config, $3));
-	parse_events__free_terms($3);
+	parse_events_terms__delete($3);
 	$$ = list;
 }
 |
@@ -302,33 +298,39 @@ value_sym sep_slash_dc
 }
 
 event_legacy_cache:
-PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT
+PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT opt_event_config
 {
 	struct parse_events_evlist *data = _data;
+	struct parse_events_error *error = data->error;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5));
+	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5, error, $6));
+	parse_events_terms__delete($6);
 	$$ = list;
 }
 |
-PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT
+PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT opt_event_config
 {
 	struct parse_events_evlist *data = _data;
+	struct parse_events_error *error = data->error;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL));
+	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL, error, $4));
+	parse_events_terms__delete($4);
 	$$ = list;
 }
 |
-PE_NAME_CACHE_TYPE
+PE_NAME_CACHE_TYPE opt_event_config
 {
 	struct parse_events_evlist *data = _data;
+	struct parse_events_error *error = data->error;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL));
+	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL, error, $2));
+	parse_events_terms__delete($2);
 	$$ = list;
 }
 
@@ -378,24 +380,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc
 }
 
 event_legacy_tracepoint:
-tracepoint_name
-{
-	struct parse_events_evlist *data = _data;
-	struct parse_events_error *error = data->error;
-	struct list_head *list;
-
-	ALLOC_LIST(list);
-	if (error)
-		error->idx = @1.first_column;
-
-	if (parse_events_add_tracepoint(list, &data->idx, $1.sys, $1.event,
-					error, NULL))
-		return -1;
-
-	$$ = list;
-}
-|
-tracepoint_name '/' event_config '/'
+tracepoint_name opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct parse_events_error *error = data->error;
@@ -406,7 +391,7 @@ tracepoint_name '/' event_config '/'
 		error->idx = @1.first_column;
 
 	if (parse_events_add_tracepoint(list, &data->idx, $1.sys, $1.event,
-					error, $3))
+					error, $2))
 		return -1;
 
 	$$ = list;
@@ -433,49 +418,68 @@ PE_NAME ':' PE_NAME
 }
 
 event_legacy_numeric:
-PE_VALUE ':' PE_VALUE
+PE_VALUE ':' PE_VALUE opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, NULL));
+	ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, $4));
+	parse_events_terms__delete($4);
 	$$ = list;
 }
 
 event_legacy_raw:
-PE_RAW
+PE_RAW opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, NULL));
+	ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, $2));
+	parse_events_terms__delete($2);
 	$$ = list;
 }
 
 event_bpf_file:
-PE_BPF_OBJECT
+PE_BPF_OBJECT opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct parse_events_error *error = data->error;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_load_bpf(data, list, $1, false));
+	ABORT_ON(parse_events_load_bpf(data, list, $1, false, $2));
+	parse_events_terms__delete($2);
 	$$ = list;
 }
 |
-PE_BPF_SOURCE
+PE_BPF_SOURCE opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_load_bpf(data, list, $1, true));
+	ABORT_ON(parse_events_load_bpf(data, list, $1, true, $2));
+	parse_events_terms__delete($2);
 	$$ = list;
 }
 
+opt_event_config:
+'/' event_config '/'
+{
+	$$ = $2;
+}
+|
+'/' '/'
+{
+	$$ = NULL;
+}
+|
+{
+	$$ = NULL;
+}
+
 start_terms: event_config
 {
 	struct parse_events_terms *data = _data;
@@ -573,6 +577,86 @@ PE_TERM
 	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, &@1, NULL));
 	$$ = term;
 }
+|
+PE_NAME array '=' PE_NAME
+{
+	struct parse_events_term *term;
+	int i;
+
+	ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					$1, $4, &@1, &@4));
+
+	term->array = $2;
+	$$ = term;
+}
+|
+PE_NAME array '=' PE_VALUE
+{
+	struct parse_events_term *term;
+
+	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					$1, $4, &@1, &@4));
+	term->array = $2;
+	$$ = term;
+}
+
+array:
+'[' array_terms ']'
+{
+	$$ = $2;
+}
+|
+PE_ARRAY_ALL
+{
+	$$.nr_ranges = 0;
+	$$.ranges = NULL;
+}
+
+array_terms:
+array_terms ',' array_term
+{
+	struct parse_events_array new_array;
+
+	new_array.nr_ranges = $1.nr_ranges + $3.nr_ranges;
+	new_array.ranges = malloc(sizeof(new_array.ranges[0]) *
+				  new_array.nr_ranges);
+	ABORT_ON(!new_array.ranges);
+	memcpy(&new_array.ranges[0], $1.ranges,
+	       $1.nr_ranges * sizeof(new_array.ranges[0]));
+	memcpy(&new_array.ranges[$1.nr_ranges], $3.ranges,
+	       $3.nr_ranges * sizeof(new_array.ranges[0]));
+	free($1.ranges);
+	free($3.ranges);
+	$$ = new_array;
+}
+|
+array_term
+
+array_term:
+PE_VALUE
+{
+	struct parse_events_array array;
+
+	array.nr_ranges = 1;
+	array.ranges = malloc(sizeof(array.ranges[0]));
+	ABORT_ON(!array.ranges);
+	array.ranges[0].start = $1;
+	array.ranges[0].length = 1;
+	$$ = array;
+}
+|
+PE_VALUE PE_ARRAY_RANGE PE_VALUE
+{
+	struct parse_events_array array;
+
+	ABORT_ON($3 < $1);
+	array.nr_ranges = 1;
+	array.ranges = malloc(sizeof(array.ranges[0]));
+	ABORT_ON(!array.ranges);
+	array.ranges[0].start = $1;
+	array.ranges[0].length = $3 - $1 + 1;
+	$$ = array;
+}
 
 sep_dc: ':' |
 
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
index 3654d964e..3bf6bf82f 100644
--- a/tools/perf/util/path.c
+++ b/tools/perf/util/path.c
@@ -41,36 +41,6 @@ static char *cleanup_path(char *path)
 	return path;
 }
 
-static char *perf_vsnpath(char *buf, size_t n, const char *fmt, va_list args)
-{
-	const char *perf_dir = get_perf_dir();
-	size_t len;
-
-	len = strlen(perf_dir);
-	if (n < len + 1)
-		goto bad;
-	memcpy(buf, perf_dir, len);
-	if (len && !is_dir_sep(perf_dir[len-1]))
-		buf[len++] = '/';
-	len += vsnprintf(buf + len, n - len, fmt, args);
-	if (len >= n)
-		goto bad;
-	return cleanup_path(buf);
-bad:
-	strlcpy(buf, bad_path, n);
-	return buf;
-}
-
-char *perf_pathdup(const char *fmt, ...)
-{
-	char path[PATH_MAX];
-	va_list args;
-	va_start(args, fmt);
-	(void)perf_vsnpath(path, sizeof(path), fmt, args);
-	va_end(args);
-	return xstrdup(path);
-}
-
 char *mkpath(const char *fmt, ...)
 {
 	va_list args;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 37b4f5070..adef23b13 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -98,7 +98,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	char scale[128];
 	int fd, ret = -1;
 	char path[PATH_MAX];
-	const char *lc;
+	char *lc;
 
 	snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
 
@@ -124,6 +124,17 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	lc = setlocale(LC_NUMERIC, NULL);
 
 	/*
+	 * The lc string may be allocated in static storage,
+	 * so get a dynamic copy to make it survive setlocale
+	 * call below.
+	 */
+	lc = strdup(lc);
+	if (!lc) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	/*
 	 * force to C locale to ensure kernel
 	 * scale string is converted correctly.
 	 * kernel uses default C locale.
@@ -135,6 +146,8 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	/* restore locale */
 	setlocale(LC_NUMERIC, lc);
 
+	free(lc);
+
 	ret = 0;
 error:
 	close(fd);
@@ -153,7 +166,7 @@ static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *n
 	if (fd == -1)
 		return -1;
 
-		sret = read(fd, alias->unit, UNIT_MAX_LEN);
+	sret = read(fd, alias->unit, UNIT_MAX_LEN);
 	if (sret < 0)
 		goto error;
 
@@ -355,7 +368,7 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias,
 	list_for_each_entry(term, &alias->terms, list) {
 		ret = parse_events_term__clone(&cloned, term);
 		if (ret) {
-			parse_events__free_terms(&list);
+			parse_events_terms__purge(&list);
 			return ret;
 		}
 		list_add_tail(&cloned->list, &list);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 93996ec4b..8319fbb08 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2179,7 +2179,7 @@ static int perf_probe_event__sprintf(const char *group, const char *event,
 		strbuf_addf(result, " in %s", module);
 
 	if (pev->nargs > 0) {
-		strbuf_addstr(result, " with");
+		strbuf_add(result, " with", 5);
 		for (i = 0; i < pev->nargs; i++) {
 			ret = synthesize_perf_probe_arg(&pev->args[i],
 							buf, 128);
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index ba926c30f..e54e7b011 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -114,49 +114,44 @@ int init_probe_symbol_maps(bool user_only);
 void exit_probe_symbol_maps(void);
 
 /* Command string to events */
-extern int parse_perf_probe_command(const char *cmd,
-				    struct perf_probe_event *pev);
-extern int parse_probe_trace_command(const char *cmd,
-				     struct probe_trace_event *tev);
+int parse_perf_probe_command(const char *cmd, struct perf_probe_event *pev);
+int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev);
 
 /* Events to command string */
-extern char *synthesize_perf_probe_command(struct perf_probe_event *pev);
-extern char *synthesize_probe_trace_command(struct probe_trace_event *tev);
-extern int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf,
-				     size_t len);
+char *synthesize_perf_probe_command(struct perf_probe_event *pev);
+char *synthesize_probe_trace_command(struct probe_trace_event *tev);
+int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len);
 
 /* Check the perf_probe_event needs debuginfo */
-extern bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
+bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
 
 /* Release event contents */
-extern void clear_perf_probe_event(struct perf_probe_event *pev);
-extern void clear_probe_trace_event(struct probe_trace_event *tev);
+void clear_perf_probe_event(struct perf_probe_event *pev);
+void clear_probe_trace_event(struct probe_trace_event *tev);
 
 /* Command string to line-range */
-extern int parse_line_range_desc(const char *cmd, struct line_range *lr);
+int parse_line_range_desc(const char *cmd, struct line_range *lr);
 
 /* Release line range members */
-extern void line_range__clear(struct line_range *lr);
+void line_range__clear(struct line_range *lr);
 
 /* Initialize line range */
-extern int line_range__init(struct line_range *lr);
-
-extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs);
-extern int convert_perf_probe_events(struct perf_probe_event *pevs, int npevs);
-extern int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs);
-extern void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs);
-extern int del_perf_probe_events(struct strfilter *filter);
-
-extern int show_perf_probe_event(const char *group, const char *event,
-				 struct perf_probe_event *pev,
-				 const char *module, bool use_stdout);
-extern int show_perf_probe_events(struct strfilter *filter);
-extern int show_line_range(struct line_range *lr, const char *module,
-			   bool user);
-extern int show_available_vars(struct perf_probe_event *pevs, int npevs,
-			       struct strfilter *filter);
-extern int show_available_funcs(const char *module, struct strfilter *filter,
-				bool user);
+int line_range__init(struct line_range *lr);
+
+int add_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+int convert_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+int del_perf_probe_events(struct strfilter *filter);
+
+int show_perf_probe_event(const char *group, const char *event,
+			  struct perf_probe_event *pev,
+			  const char *module, bool use_stdout);
+int show_perf_probe_events(struct strfilter *filter);
+int show_line_range(struct line_range *lr, const char *module, bool user);
+int show_available_vars(struct perf_probe_event *pevs, int npevs,
+			struct strfilter *filter);
+int show_available_funcs(const char *module, struct strfilter *filter, bool user);
 bool arch__prefers_symtab(void);
 void arch__fix_tev_from_maps(struct perf_probe_event *pev,
 			     struct probe_trace_event *tev, struct map *map);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 4ce5c5e18..b3bd0fba0 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1314,18 +1314,18 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
 			if (probe_conf.show_location_range) {
 				if (!externs) {
 					if (ret)
-						strbuf_addf(&buf, "[INV]\t");
+						strbuf_add(&buf, "[INV]\t", 6);
 					else
-						strbuf_addf(&buf, "[VAL]\t");
+						strbuf_add(&buf, "[VAL]\t", 6);
 				} else
-					strbuf_addf(&buf, "[EXT]\t");
+					strbuf_add(&buf, "[EXT]\t", 6);
 			}
 
 			ret2 = die_get_varname(die_mem, &buf);
 
 			if (!ret2 && probe_conf.show_location_range &&
 				!externs) {
-				strbuf_addf(&buf, "\t");
+				strbuf_addch(&buf, '\t');
 				ret2 = die_get_var_range(&af->pf.sp_die,
 							die_mem, &buf);
 			}
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 0aec7704e..51137fccb 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -34,27 +34,25 @@ struct debuginfo {
 };
 
 /* This also tries to open distro debuginfo */
-extern struct debuginfo *debuginfo__new(const char *path);
-extern void debuginfo__delete(struct debuginfo *dbg);
+struct debuginfo *debuginfo__new(const char *path);
+void debuginfo__delete(struct debuginfo *dbg);
 
 /* Find probe_trace_events specified by perf_probe_event from debuginfo */
-extern int debuginfo__find_trace_events(struct debuginfo *dbg,
-					struct perf_probe_event *pev,
-					struct probe_trace_event **tevs);
+int debuginfo__find_trace_events(struct debuginfo *dbg,
+				 struct perf_probe_event *pev,
+				 struct probe_trace_event **tevs);
 
 /* Find a perf_probe_point from debuginfo */
-extern int debuginfo__find_probe_point(struct debuginfo *dbg,
-				       unsigned long addr,
-				       struct perf_probe_point *ppt);
+int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
+				struct perf_probe_point *ppt);
 
 /* Find a line range */
-extern int debuginfo__find_line_range(struct debuginfo *dbg,
-				      struct line_range *lr);
+int debuginfo__find_line_range(struct debuginfo *dbg, struct line_range *lr);
 
 /* Find available variables */
-extern int debuginfo__find_available_vars_at(struct debuginfo *dbg,
-					     struct perf_probe_event *pev,
-					     struct variable_list **vls);
+int debuginfo__find_available_vars_at(struct debuginfo *dbg,
+				      struct perf_probe_event *pev,
+				      struct variable_list **vls);
 
 /* Find a src file from a DWARF tag path */
 int get_real_path(const char *raw_path, const char *comp_dir,
diff --git a/tools/perf/util/quote.h b/tools/perf/util/quote.h
index 172889ea2..3340c9c4a 100644
--- a/tools/perf/util/quote.h
+++ b/tools/perf/util/quote.h
@@ -24,6 +24,6 @@
  * sq_quote() in a real application.
  */
 
-extern void sq_quote_argv(struct strbuf *, const char **argv, size_t maxlen);
+void sq_quote_argv(struct strbuf *, const char **argv, size_t maxlen);
 
 #endif /* __PERF_QUOTE_H */
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 544509c15..b3aabc0d4 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -187,6 +187,9 @@ static void define_event_symbols(struct event_format *event,
 				 const char *ev_name,
 				 struct print_arg *args)
 {
+	if (args == NULL)
+		return;
+
 	switch (args->type) {
 	case PRINT_NULL:
 		break;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index d72fafc1c..fbd05242b 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -205,6 +205,9 @@ static void define_event_symbols(struct event_format *event,
 				 const char *ev_name,
 				 struct print_arg *args)
 {
+	if (args == NULL)
+		return;
+
 	switch (args->type) {
 	case PRINT_NULL:
 		break;
@@ -1091,8 +1094,6 @@ static int python_start_script(const char *script, int argc, const char **argv)
 		goto error;
 	}
 
-	free(command_line);
-
 	set_table_handlers(tables);
 
 	if (tables->db_export_mode) {
@@ -1101,6 +1102,8 @@ static int python_start_script(const char *script, int argc, const char **argv)
 			goto error;
 	}
 
+	free(command_line);
+
 	return err;
 error:
 	Py_Finalize();
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 40b7a0d09..4abd85c63 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -240,14 +240,6 @@ static int process_event_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int process_build_id_stub(struct perf_tool *tool __maybe_unused,
-				 union perf_event *event __maybe_unused,
-				 struct perf_session *session __maybe_unused)
-{
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
 static int process_finished_round_stub(struct perf_tool *tool __maybe_unused,
 				       union perf_event *event __maybe_unused,
 				       struct ordered_events *oe __maybe_unused)
@@ -260,23 +252,6 @@ static int process_finished_round(struct perf_tool *tool,
 				  union perf_event *event,
 				  struct ordered_events *oe);
 
-static int process_id_index_stub(struct perf_tool *tool __maybe_unused,
-				 union perf_event *event __maybe_unused,
-				 struct perf_session *perf_session
-				 __maybe_unused)
-{
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
-static int process_event_auxtrace_info_stub(struct perf_tool *tool __maybe_unused,
-				union perf_event *event __maybe_unused,
-				struct perf_session *session __maybe_unused)
-{
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
 static int skipn(int fd, off_t n)
 {
 	char buf[4096];
@@ -303,10 +278,9 @@ static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
 	return event->auxtrace.size;
 }
 
-static
-int process_event_auxtrace_error_stub(struct perf_tool *tool __maybe_unused,
-				      union perf_event *event __maybe_unused,
-				      struct perf_session *session __maybe_unused)
+static int process_event_op2_stub(struct perf_tool *tool __maybe_unused,
+				  union perf_event *event __maybe_unused,
+				  struct perf_session *session __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
@@ -410,7 +384,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 	if (tool->tracing_data == NULL)
 		tool->tracing_data = process_event_synth_tracing_data_stub;
 	if (tool->build_id == NULL)
-		tool->build_id = process_build_id_stub;
+		tool->build_id = process_event_op2_stub;
 	if (tool->finished_round == NULL) {
 		if (tool->ordered_events)
 			tool->finished_round = process_finished_round;
@@ -418,13 +392,13 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 			tool->finished_round = process_finished_round_stub;
 	}
 	if (tool->id_index == NULL)
-		tool->id_index = process_id_index_stub;
+		tool->id_index = process_event_op2_stub;
 	if (tool->auxtrace_info == NULL)
-		tool->auxtrace_info = process_event_auxtrace_info_stub;
+		tool->auxtrace_info = process_event_op2_stub;
 	if (tool->auxtrace == NULL)
 		tool->auxtrace = process_event_auxtrace_stub;
 	if (tool->auxtrace_error == NULL)
-		tool->auxtrace_error = process_event_auxtrace_error_stub;
+		tool->auxtrace_error = process_event_op2_stub;
 	if (tool->thread_map == NULL)
 		tool->thread_map = process_event_thread_map_stub;
 	if (tool->cpu_map == NULL)
@@ -1133,12 +1107,11 @@ static struct machine *machines__find_for_cpumode(struct machines *machines,
 					       union perf_event *event,
 					       struct perf_sample *sample)
 {
-	const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	struct machine *machine;
 
 	if (perf_guest &&
-	    ((cpumode == PERF_RECORD_MISC_GUEST_KERNEL) ||
-	     (cpumode == PERF_RECORD_MISC_GUEST_USER))) {
+	    ((sample->cpumode == PERF_RECORD_MISC_GUEST_KERNEL) ||
+	     (sample->cpumode == PERF_RECORD_MISC_GUEST_USER))) {
 		u32 pid;
 
 		if (event->header.type == PERF_RECORD_MMAP
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index ec722346e..f5ba111cd 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -6,6 +6,7 @@
 #include "evsel.h"
 #include "evlist.h"
 #include <traceevent/event-parse.h>
+#include "mem-events.h"
 
 regex_t		parent_regex;
 const char	default_parent_pattern[] = "^sys_|^do_page_fault";
@@ -25,9 +26,19 @@ int		sort__has_parent = 0;
 int		sort__has_sym = 0;
 int		sort__has_dso = 0;
 int		sort__has_socket = 0;
+int		sort__has_thread = 0;
+int		sort__has_comm = 0;
 enum sort_mode	sort__mode = SORT_MODE__NORMAL;
 
-
+/*
+ * Replaces all occurrences of a char used with the:
+ *
+ * -t, --field-separator
+ *
+ * option, that uses a special separator character and don't pad with spaces,
+ * replacing all occurances of this separator in symbol names (and other
+ * output) with a '.' character, that thus it's the only non valid separator.
+*/
 static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...)
 {
 	int n;
@@ -80,10 +91,21 @@ static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf,
 			       width, width, comm ?: "");
 }
 
+static int hist_entry__thread_filter(struct hist_entry *he, int type, const void *arg)
+{
+	const struct thread *th = arg;
+
+	if (type != HIST_FILTER__THREAD)
+		return -1;
+
+	return th && he->thread != th;
+}
+
 struct sort_entry sort_thread = {
 	.se_header	= "  Pid:Command",
 	.se_cmp		= sort__thread_cmp,
 	.se_snprintf	= hist_entry__thread_snprintf,
+	.se_filter	= hist_entry__thread_filter,
 	.se_width_idx	= HISTC_THREAD,
 };
 
@@ -121,6 +143,7 @@ struct sort_entry sort_comm = {
 	.se_collapse	= sort__comm_collapse,
 	.se_sort	= sort__comm_sort,
 	.se_snprintf	= hist_entry__comm_snprintf,
+	.se_filter	= hist_entry__thread_filter,
 	.se_width_idx	= HISTC_COMM,
 };
 
@@ -170,10 +193,21 @@ static int hist_entry__dso_snprintf(struct hist_entry *he, char *bf,
 	return _hist_entry__dso_snprintf(he->ms.map, bf, size, width);
 }
 
+static int hist_entry__dso_filter(struct hist_entry *he, int type, const void *arg)
+{
+	const struct dso *dso = arg;
+
+	if (type != HIST_FILTER__DSO)
+		return -1;
+
+	return dso && (!he->ms.map || he->ms.map->dso != dso);
+}
+
 struct sort_entry sort_dso = {
 	.se_header	= "Shared Object",
 	.se_cmp		= sort__dso_cmp,
 	.se_snprintf	= hist_entry__dso_snprintf,
+	.se_filter	= hist_entry__dso_filter,
 	.se_width_idx	= HISTC_DSO,
 };
 
@@ -246,10 +280,8 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
 			ret += repsep_snprintf(bf + ret, size - ret, "%s", sym->name);
 			ret += repsep_snprintf(bf + ret, size - ret, "+0x%llx",
 					ip - map->unmap_ip(map, sym->start));
-			ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
-				       width - ret, "");
 		} else {
-			ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
+			ret += repsep_snprintf(bf + ret, size - ret, "%.*s",
 					       width - ret,
 					       sym->name);
 		}
@@ -257,14 +289,9 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
 		size_t len = BITS_PER_LONG / 4;
 		ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx",
 				       len, ip);
-		ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
-				       width - ret, "");
 	}
 
-	if (ret > width)
-		bf[width] = '\0';
-
-	return width;
+	return ret;
 }
 
 static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf,
@@ -274,46 +301,56 @@ static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf,
 					 he->level, bf, size, width);
 }
 
+static int hist_entry__sym_filter(struct hist_entry *he, int type, const void *arg)
+{
+	const char *sym = arg;
+
+	if (type != HIST_FILTER__SYMBOL)
+		return -1;
+
+	return sym && (!he->ms.sym || !strstr(he->ms.sym->name, sym));
+}
+
 struct sort_entry sort_sym = {
 	.se_header	= "Symbol",
 	.se_cmp		= sort__sym_cmp,
 	.se_sort	= sort__sym_sort,
 	.se_snprintf	= hist_entry__sym_snprintf,
+	.se_filter	= hist_entry__sym_filter,
 	.se_width_idx	= HISTC_SYMBOL,
 };
 
 /* --sort srcline */
 
+static char *hist_entry__get_srcline(struct hist_entry *he)
+{
+	struct map *map = he->ms.map;
+
+	if (!map)
+		return SRCLINE_UNKNOWN;
+
+	return get_srcline(map->dso, map__rip_2objdump(map, he->ip),
+			   he->ms.sym, true);
+}
+
 static int64_t
 sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	if (!left->srcline) {
-		if (!left->ms.map)
-			left->srcline = SRCLINE_UNKNOWN;
-		else {
-			struct map *map = left->ms.map;
-			left->srcline = get_srcline(map->dso,
-					   map__rip_2objdump(map, left->ip),
-						    left->ms.sym, true);
-		}
-	}
-	if (!right->srcline) {
-		if (!right->ms.map)
-			right->srcline = SRCLINE_UNKNOWN;
-		else {
-			struct map *map = right->ms.map;
-			right->srcline = get_srcline(map->dso,
-					     map__rip_2objdump(map, right->ip),
-						     right->ms.sym, true);
-		}
-	}
+	if (!left->srcline)
+		left->srcline = hist_entry__get_srcline(left);
+	if (!right->srcline)
+		right->srcline = hist_entry__get_srcline(right);
+
 	return strcmp(right->srcline, left->srcline);
 }
 
 static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf,
 					size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*.*s", width, width, he->srcline);
+	if (!he->srcline)
+		he->srcline = hist_entry__get_srcline(he);
+
+	return repsep_snprintf(bf, size, "%-.*s", width, he->srcline);
 }
 
 struct sort_entry sort_srcline = {
@@ -327,11 +364,14 @@ struct sort_entry sort_srcline = {
 
 static char no_srcfile[1];
 
-static char *get_srcfile(struct hist_entry *e)
+static char *hist_entry__get_srcfile(struct hist_entry *e)
 {
 	char *sf, *p;
 	struct map *map = e->ms.map;
 
+	if (!map)
+		return no_srcfile;
+
 	sf = __get_srcline(map->dso, map__rip_2objdump(map, e->ip),
 			 e->ms.sym, false, true);
 	if (!strcmp(sf, SRCLINE_UNKNOWN))
@@ -348,25 +388,21 @@ static char *get_srcfile(struct hist_entry *e)
 static int64_t
 sort__srcfile_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	if (!left->srcfile) {
-		if (!left->ms.map)
-			left->srcfile = no_srcfile;
-		else
-			left->srcfile = get_srcfile(left);
-	}
-	if (!right->srcfile) {
-		if (!right->ms.map)
-			right->srcfile = no_srcfile;
-		else
-			right->srcfile = get_srcfile(right);
-	}
+	if (!left->srcfile)
+		left->srcfile = hist_entry__get_srcfile(left);
+	if (!right->srcfile)
+		right->srcfile = hist_entry__get_srcfile(right);
+
 	return strcmp(right->srcfile, left->srcfile);
 }
 
 static int hist_entry__srcfile_snprintf(struct hist_entry *he, char *bf,
 					size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*.*s", width, width, he->srcfile);
+	if (!he->srcfile)
+		he->srcfile = hist_entry__get_srcfile(he);
+
+	return repsep_snprintf(bf, size, "%-.*s", width, he->srcfile);
 }
 
 struct sort_entry sort_srcfile = {
@@ -439,10 +475,21 @@ static int hist_entry__socket_snprintf(struct hist_entry *he, char *bf,
 	return repsep_snprintf(bf, size, "%*.*d", width, width-3, he->socket);
 }
 
+static int hist_entry__socket_filter(struct hist_entry *he, int type, const void *arg)
+{
+	int sk = *(const int *)arg;
+
+	if (type != HIST_FILTER__SOCKET)
+		return -1;
+
+	return sk >= 0 && he->socket != sk;
+}
+
 struct sort_entry sort_socket = {
 	.se_header      = "Socket",
 	.se_cmp	        = sort__socket_cmp,
 	.se_snprintf    = hist_entry__socket_snprintf,
+	.se_filter      = hist_entry__socket_filter,
 	.se_width_idx	= HISTC_SOCKET,
 };
 
@@ -483,9 +530,6 @@ sort__trace_cmp(struct hist_entry *left, struct hist_entry *right)
 	if (right->trace_output == NULL)
 		right->trace_output = get_trace_output(right);
 
-	hists__new_col_len(left->hists, HISTC_TRACE, strlen(left->trace_output));
-	hists__new_col_len(right->hists, HISTC_TRACE, strlen(right->trace_output));
-
 	return strcmp(right->trace_output, left->trace_output);
 }
 
@@ -496,11 +540,11 @@ static int hist_entry__trace_snprintf(struct hist_entry *he, char *bf,
 
 	evsel = hists_to_evsel(he->hists);
 	if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
-		return scnprintf(bf, size, "%-*.*s", width, width, "N/A");
+		return scnprintf(bf, size, "%-.*s", width, "N/A");
 
 	if (he->trace_output == NULL)
 		he->trace_output = get_trace_output(he);
-	return repsep_snprintf(bf, size, "%-*.*s", width, width, he->trace_output);
+	return repsep_snprintf(bf, size, "%-.*s", width, he->trace_output);
 }
 
 struct sort_entry sort_trace = {
@@ -532,6 +576,18 @@ static int hist_entry__dso_from_snprintf(struct hist_entry *he, char *bf,
 		return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
+static int hist_entry__dso_from_filter(struct hist_entry *he, int type,
+				       const void *arg)
+{
+	const struct dso *dso = arg;
+
+	if (type != HIST_FILTER__DSO)
+		return -1;
+
+	return dso && (!he->branch_info || !he->branch_info->from.map ||
+		       he->branch_info->from.map->dso != dso);
+}
+
 static int64_t
 sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -552,6 +608,18 @@ static int hist_entry__dso_to_snprintf(struct hist_entry *he, char *bf,
 		return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
+static int hist_entry__dso_to_filter(struct hist_entry *he, int type,
+				     const void *arg)
+{
+	const struct dso *dso = arg;
+
+	if (type != HIST_FILTER__DSO)
+		return -1;
+
+	return dso && (!he->branch_info || !he->branch_info->to.map ||
+		       he->branch_info->to.map->dso != dso);
+}
+
 static int64_t
 sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -613,10 +681,35 @@ static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf,
 	return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
+static int hist_entry__sym_from_filter(struct hist_entry *he, int type,
+				       const void *arg)
+{
+	const char *sym = arg;
+
+	if (type != HIST_FILTER__SYMBOL)
+		return -1;
+
+	return sym && !(he->branch_info && he->branch_info->from.sym &&
+			strstr(he->branch_info->from.sym->name, sym));
+}
+
+static int hist_entry__sym_to_filter(struct hist_entry *he, int type,
+				       const void *arg)
+{
+	const char *sym = arg;
+
+	if (type != HIST_FILTER__SYMBOL)
+		return -1;
+
+	return sym && !(he->branch_info && he->branch_info->to.sym &&
+		        strstr(he->branch_info->to.sym->name, sym));
+}
+
 struct sort_entry sort_dso_from = {
 	.se_header	= "Source Shared Object",
 	.se_cmp		= sort__dso_from_cmp,
 	.se_snprintf	= hist_entry__dso_from_snprintf,
+	.se_filter	= hist_entry__dso_from_filter,
 	.se_width_idx	= HISTC_DSO_FROM,
 };
 
@@ -624,6 +717,7 @@ struct sort_entry sort_dso_to = {
 	.se_header	= "Target Shared Object",
 	.se_cmp		= sort__dso_to_cmp,
 	.se_snprintf	= hist_entry__dso_to_snprintf,
+	.se_filter	= hist_entry__dso_to_filter,
 	.se_width_idx	= HISTC_DSO_TO,
 };
 
@@ -631,6 +725,7 @@ struct sort_entry sort_sym_from = {
 	.se_header	= "Source Symbol",
 	.se_cmp		= sort__sym_from_cmp,
 	.se_snprintf	= hist_entry__sym_from_snprintf,
+	.se_filter	= hist_entry__sym_from_filter,
 	.se_width_idx	= HISTC_SYMBOL_FROM,
 };
 
@@ -638,6 +733,7 @@ struct sort_entry sort_sym_to = {
 	.se_header	= "Target Symbol",
 	.se_cmp		= sort__sym_to_cmp,
 	.se_snprintf	= hist_entry__sym_to_snprintf,
+	.se_filter	= hist_entry__sym_to_filter,
 	.se_width_idx	= HISTC_SYMBOL_TO,
 };
 
@@ -797,20 +893,10 @@ sort__locked_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__locked_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	const char *out;
-	u64 mask = PERF_MEM_LOCK_NA;
+	char out[10];
 
-	if (he->mem_info)
-		mask = he->mem_info->data_src.mem_lock;
-
-	if (mask & PERF_MEM_LOCK_NA)
-		out = "N/A";
-	else if (mask & PERF_MEM_LOCK_LOCKED)
-		out = "Yes";
-	else
-		out = "No";
-
-	return repsep_snprintf(bf, size, "%-*s", width, out);
+	perf_mem__lck_scnprintf(out, sizeof(out), he->mem_info);
+	return repsep_snprintf(bf, size, "%.*s", width, out);
 }
 
 static int64_t
@@ -832,54 +918,12 @@ sort__tlb_cmp(struct hist_entry *left, struct hist_entry *right)
 	return (int64_t)(data_src_r.mem_dtlb - data_src_l.mem_dtlb);
 }
 
-static const char * const tlb_access[] = {
-	"N/A",
-	"HIT",
-	"MISS",
-	"L1",
-	"L2",
-	"Walker",
-	"Fault",
-};
-#define NUM_TLB_ACCESS (sizeof(tlb_access)/sizeof(const char *))
-
 static int hist_entry__tlb_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
 	char out[64];
-	size_t sz = sizeof(out) - 1; /* -1 for null termination */
-	size_t l = 0, i;
-	u64 m = PERF_MEM_TLB_NA;
-	u64 hit, miss;
-
-	out[0] = '\0';
-
-	if (he->mem_info)
-		m = he->mem_info->data_src.mem_dtlb;
-
-	hit = m & PERF_MEM_TLB_HIT;
-	miss = m & PERF_MEM_TLB_MISS;
-
-	/* already taken care of */
-	m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS);
-
-	for (i = 0; m && i < NUM_TLB_ACCESS; i++, m >>= 1) {
-		if (!(m & 0x1))
-			continue;
-		if (l) {
-			strcat(out, " or ");
-			l += 4;
-		}
-		strncat(out, tlb_access[i], sz - l);
-		l += strlen(tlb_access[i]);
-	}
-	if (*out == '\0')
-		strcpy(out, "N/A");
-	if (hit)
-		strncat(out, " hit", sz - l);
-	if (miss)
-		strncat(out, " miss", sz - l);
 
+	perf_mem__tlb_scnprintf(out, sizeof(out), he->mem_info);
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
@@ -902,61 +946,12 @@ sort__lvl_cmp(struct hist_entry *left, struct hist_entry *right)
 	return (int64_t)(data_src_r.mem_lvl - data_src_l.mem_lvl);
 }
 
-static const char * const mem_lvl[] = {
-	"N/A",
-	"HIT",
-	"MISS",
-	"L1",
-	"LFB",
-	"L2",
-	"L3",
-	"Local RAM",
-	"Remote RAM (1 hop)",
-	"Remote RAM (2 hops)",
-	"Remote Cache (1 hop)",
-	"Remote Cache (2 hops)",
-	"I/O",
-	"Uncached",
-};
-#define NUM_MEM_LVL (sizeof(mem_lvl)/sizeof(const char *))
-
 static int hist_entry__lvl_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
 	char out[64];
-	size_t sz = sizeof(out) - 1; /* -1 for null termination */
-	size_t i, l = 0;
-	u64 m =  PERF_MEM_LVL_NA;
-	u64 hit, miss;
-
-	if (he->mem_info)
-		m  = he->mem_info->data_src.mem_lvl;
-
-	out[0] = '\0';
-
-	hit = m & PERF_MEM_LVL_HIT;
-	miss = m & PERF_MEM_LVL_MISS;
-
-	/* already taken care of */
-	m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
-
-	for (i = 0; m && i < NUM_MEM_LVL; i++, m >>= 1) {
-		if (!(m & 0x1))
-			continue;
-		if (l) {
-			strcat(out, " or ");
-			l += 4;
-		}
-		strncat(out, mem_lvl[i], sz - l);
-		l += strlen(mem_lvl[i]);
-	}
-	if (*out == '\0')
-		strcpy(out, "N/A");
-	if (hit)
-		strncat(out, " hit", sz - l);
-	if (miss)
-		strncat(out, " miss", sz - l);
 
+	perf_mem__lvl_scnprintf(out, sizeof(out), he->mem_info);
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
@@ -979,51 +974,15 @@ sort__snoop_cmp(struct hist_entry *left, struct hist_entry *right)
 	return (int64_t)(data_src_r.mem_snoop - data_src_l.mem_snoop);
 }
 
-static const char * const snoop_access[] = {
-	"N/A",
-	"None",
-	"Miss",
-	"Hit",
-	"HitM",
-};
-#define NUM_SNOOP_ACCESS (sizeof(snoop_access)/sizeof(const char *))
-
 static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
 	char out[64];
-	size_t sz = sizeof(out) - 1; /* -1 for null termination */
-	size_t i, l = 0;
-	u64 m = PERF_MEM_SNOOP_NA;
-
-	out[0] = '\0';
-
-	if (he->mem_info)
-		m = he->mem_info->data_src.mem_snoop;
-
-	for (i = 0; m && i < NUM_SNOOP_ACCESS; i++, m >>= 1) {
-		if (!(m & 0x1))
-			continue;
-		if (l) {
-			strcat(out, " or ");
-			l += 4;
-		}
-		strncat(out, snoop_access[i], sz - l);
-		l += strlen(snoop_access[i]);
-	}
-
-	if (*out == '\0')
-		strcpy(out, "N/A");
 
+	perf_mem__snp_scnprintf(out, sizeof(out), he->mem_info);
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
-static inline  u64 cl_address(u64 address)
-{
-	/* return the cacheline of the address */
-	return (address & ~(cacheline_size - 1));
-}
-
 static int64_t
 sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -1440,20 +1399,6 @@ struct hpp_sort_entry {
 	struct sort_entry *se;
 };
 
-bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
-{
-	struct hpp_sort_entry *hse_a;
-	struct hpp_sort_entry *hse_b;
-
-	if (!perf_hpp__is_sort_entry(a) || !perf_hpp__is_sort_entry(b))
-		return false;
-
-	hse_a = container_of(a, struct hpp_sort_entry, hpp);
-	hse_b = container_of(b, struct hpp_sort_entry, hpp);
-
-	return hse_a->se == hse_b->se;
-}
-
 void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 {
 	struct hpp_sort_entry *hse;
@@ -1539,8 +1484,56 @@ static int64_t __sort__hpp_sort(struct perf_hpp_fmt *fmt,
 	return sort_fn(a, b);
 }
 
+bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format)
+{
+	return format->header == __sort__hpp_header;
+}
+
+#define MK_SORT_ENTRY_CHK(key)					\
+bool perf_hpp__is_ ## key ## _entry(struct perf_hpp_fmt *fmt)	\
+{								\
+	struct hpp_sort_entry *hse;				\
+								\
+	if (!perf_hpp__is_sort_entry(fmt))			\
+		return false;					\
+								\
+	hse = container_of(fmt, struct hpp_sort_entry, hpp);	\
+	return hse->se == &sort_ ## key ;			\
+}
+
+MK_SORT_ENTRY_CHK(trace)
+MK_SORT_ENTRY_CHK(srcline)
+MK_SORT_ENTRY_CHK(srcfile)
+MK_SORT_ENTRY_CHK(thread)
+MK_SORT_ENTRY_CHK(comm)
+MK_SORT_ENTRY_CHK(dso)
+MK_SORT_ENTRY_CHK(sym)
+
+
+static bool __sort__hpp_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+	struct hpp_sort_entry *hse_a;
+	struct hpp_sort_entry *hse_b;
+
+	if (!perf_hpp__is_sort_entry(a) || !perf_hpp__is_sort_entry(b))
+		return false;
+
+	hse_a = container_of(a, struct hpp_sort_entry, hpp);
+	hse_b = container_of(b, struct hpp_sort_entry, hpp);
+
+	return hse_a->se == hse_b->se;
+}
+
+static void hse_free(struct perf_hpp_fmt *fmt)
+{
+	struct hpp_sort_entry *hse;
+
+	hse = container_of(fmt, struct hpp_sort_entry, hpp);
+	free(hse);
+}
+
 static struct hpp_sort_entry *
-__sort_dimension__alloc_hpp(struct sort_dimension *sd)
+__sort_dimension__alloc_hpp(struct sort_dimension *sd, int level)
 {
 	struct hpp_sort_entry *hse;
 
@@ -1560,40 +1553,92 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd)
 	hse->hpp.cmp = __sort__hpp_cmp;
 	hse->hpp.collapse = __sort__hpp_collapse;
 	hse->hpp.sort = __sort__hpp_sort;
+	hse->hpp.equal = __sort__hpp_equal;
+	hse->hpp.free = hse_free;
 
 	INIT_LIST_HEAD(&hse->hpp.list);
 	INIT_LIST_HEAD(&hse->hpp.sort_list);
 	hse->hpp.elide = false;
 	hse->hpp.len = 0;
 	hse->hpp.user_len = 0;
+	hse->hpp.level = level;
 
 	return hse;
 }
 
-bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format)
+static void hpp_free(struct perf_hpp_fmt *fmt)
 {
-	return format->header == __sort__hpp_header;
+	free(fmt);
+}
+
+static struct perf_hpp_fmt *__hpp_dimension__alloc_hpp(struct hpp_dimension *hd,
+						       int level)
+{
+	struct perf_hpp_fmt *fmt;
+
+	fmt = memdup(hd->fmt, sizeof(*fmt));
+	if (fmt) {
+		INIT_LIST_HEAD(&fmt->list);
+		INIT_LIST_HEAD(&fmt->sort_list);
+		fmt->free = hpp_free;
+		fmt->level = level;
+	}
+
+	return fmt;
+}
+
+int hist_entry__filter(struct hist_entry *he, int type, const void *arg)
+{
+	struct perf_hpp_fmt *fmt;
+	struct hpp_sort_entry *hse;
+	int ret = -1;
+	int r;
+
+	perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+		if (!perf_hpp__is_sort_entry(fmt))
+			continue;
+
+		hse = container_of(fmt, struct hpp_sort_entry, hpp);
+		if (hse->se->se_filter == NULL)
+			continue;
+
+		/*
+		 * hist entry is filtered if any of sort key in the hpp list
+		 * is applied.  But it should skip non-matched filter types.
+		 */
+		r = hse->se->se_filter(he, type, arg);
+		if (r >= 0) {
+			if (ret < 0)
+				ret = 0;
+			ret |= r;
+		}
+	}
+
+	return ret;
 }
 
-static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd)
+static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd,
+					  struct perf_hpp_list *list,
+					  int level)
 {
-	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd);
+	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd, level);
 
 	if (hse == NULL)
 		return -1;
 
-	perf_hpp__register_sort_field(&hse->hpp);
+	perf_hpp_list__register_sort_field(list, &hse->hpp);
 	return 0;
 }
 
-static int __sort_dimension__add_hpp_output(struct sort_dimension *sd)
+static int __sort_dimension__add_hpp_output(struct sort_dimension *sd,
+					    struct perf_hpp_list *list)
 {
-	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd);
+	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd, 0);
 
 	if (hse == NULL)
 		return -1;
 
-	perf_hpp__column_register(&hse->hpp);
+	perf_hpp_list__column_register(list, &hse->hpp);
 	return 0;
 }
 
@@ -1727,6 +1772,9 @@ static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	if (hde->raw_trace)
 		goto raw_field;
 
+	if (!he->trace_output)
+		he->trace_output = get_trace_output(he);
+
 	field = hde->field;
 	namelen = strlen(field->name);
 	str = he->trace_output;
@@ -1776,6 +1824,11 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
 
 	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
 
+	if (b == NULL) {
+		update_dynamic_len(hde, a);
+		return 0;
+	}
+
 	field = hde->field;
 	if (field->flags & FIELD_IS_DYNAMIC) {
 		unsigned long long dyn;
@@ -1790,9 +1843,6 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
 	} else {
 		offset = field->offset;
 		size = field->size;
-
-		update_dynamic_len(hde, a);
-		update_dynamic_len(hde, b);
 	}
 
 	return memcmp(a->raw_data + offset, b->raw_data + offset, size);
@@ -1803,8 +1853,31 @@ bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *fmt)
 	return fmt->cmp == __sort__hde_cmp;
 }
 
+static bool __sort__hde_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+	struct hpp_dynamic_entry *hde_a;
+	struct hpp_dynamic_entry *hde_b;
+
+	if (!perf_hpp__is_dynamic_entry(a) || !perf_hpp__is_dynamic_entry(b))
+		return false;
+
+	hde_a = container_of(a, struct hpp_dynamic_entry, hpp);
+	hde_b = container_of(b, struct hpp_dynamic_entry, hpp);
+
+	return hde_a->field == hde_b->field;
+}
+
+static void hde_free(struct perf_hpp_fmt *fmt)
+{
+	struct hpp_dynamic_entry *hde;
+
+	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+	free(hde);
+}
+
 static struct hpp_dynamic_entry *
-__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field)
+__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field,
+		      int level)
 {
 	struct hpp_dynamic_entry *hde;
 
@@ -1827,16 +1900,47 @@ __alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field)
 	hde->hpp.cmp = __sort__hde_cmp;
 	hde->hpp.collapse = __sort__hde_cmp;
 	hde->hpp.sort = __sort__hde_cmp;
+	hde->hpp.equal = __sort__hde_equal;
+	hde->hpp.free = hde_free;
 
 	INIT_LIST_HEAD(&hde->hpp.list);
 	INIT_LIST_HEAD(&hde->hpp.sort_list);
 	hde->hpp.elide = false;
 	hde->hpp.len = 0;
 	hde->hpp.user_len = 0;
+	hde->hpp.level = level;
 
 	return hde;
 }
 
+struct perf_hpp_fmt *perf_hpp_fmt__dup(struct perf_hpp_fmt *fmt)
+{
+	struct perf_hpp_fmt *new_fmt = NULL;
+
+	if (perf_hpp__is_sort_entry(fmt)) {
+		struct hpp_sort_entry *hse, *new_hse;
+
+		hse = container_of(fmt, struct hpp_sort_entry, hpp);
+		new_hse = memdup(hse, sizeof(*hse));
+		if (new_hse)
+			new_fmt = &new_hse->hpp;
+	} else if (perf_hpp__is_dynamic_entry(fmt)) {
+		struct hpp_dynamic_entry *hde, *new_hde;
+
+		hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+		new_hde = memdup(hde, sizeof(*hde));
+		if (new_hde)
+			new_fmt = &new_hde->hpp;
+	} else {
+		new_fmt = memdup(fmt, sizeof(*fmt));
+	}
+
+	INIT_LIST_HEAD(&new_fmt->list);
+	INIT_LIST_HEAD(&new_fmt->sort_list);
+
+	return new_fmt;
+}
+
 static int parse_field_name(char *str, char **event, char **field, char **opt)
 {
 	char *event_name, *field_name, *opt_name;
@@ -1908,11 +2012,11 @@ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_nam
 
 static int __dynamic_dimension__add(struct perf_evsel *evsel,
 				    struct format_field *field,
-				    bool raw_trace)
+				    bool raw_trace, int level)
 {
 	struct hpp_dynamic_entry *hde;
 
-	hde = __alloc_dynamic_entry(evsel, field);
+	hde = __alloc_dynamic_entry(evsel, field, level);
 	if (hde == NULL)
 		return -ENOMEM;
 
@@ -1922,14 +2026,14 @@ static int __dynamic_dimension__add(struct perf_evsel *evsel,
 	return 0;
 }
 
-static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace)
+static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace, int level)
 {
 	int ret;
 	struct format_field *field;
 
 	field = evsel->tp_format->format.fields;
 	while (field) {
-		ret = __dynamic_dimension__add(evsel, field, raw_trace);
+		ret = __dynamic_dimension__add(evsel, field, raw_trace, level);
 		if (ret < 0)
 			return ret;
 
@@ -1938,7 +2042,8 @@ static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace)
 	return 0;
 }
 
-static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace)
+static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace,
+				  int level)
 {
 	int ret;
 	struct perf_evsel *evsel;
@@ -1947,7 +2052,7 @@ static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace)
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
 			continue;
 
-		ret = add_evsel_fields(evsel, raw_trace);
+		ret = add_evsel_fields(evsel, raw_trace, level);
 		if (ret < 0)
 			return ret;
 	}
@@ -1955,7 +2060,7 @@ static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace)
 }
 
 static int add_all_matching_fields(struct perf_evlist *evlist,
-				   char *field_name, bool raw_trace)
+				   char *field_name, bool raw_trace, int level)
 {
 	int ret = -ESRCH;
 	struct perf_evsel *evsel;
@@ -1969,14 +2074,15 @@ static int add_all_matching_fields(struct perf_evlist *evlist,
 		if (field == NULL)
 			continue;
 
-		ret = __dynamic_dimension__add(evsel, field, raw_trace);
+		ret = __dynamic_dimension__add(evsel, field, raw_trace, level);
 		if (ret < 0)
 			break;
 	}
 	return ret;
 }
 
-static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
+static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok,
+			     int level)
 {
 	char *str, *event_name, *field_name, *opt_name;
 	struct perf_evsel *evsel;
@@ -2006,12 +2112,12 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
 	}
 
 	if (!strcmp(field_name, "trace_fields")) {
-		ret = add_all_dynamic_fields(evlist, raw_trace);
+		ret = add_all_dynamic_fields(evlist, raw_trace, level);
 		goto out;
 	}
 
 	if (event_name == NULL) {
-		ret = add_all_matching_fields(evlist, field_name, raw_trace);
+		ret = add_all_matching_fields(evlist, field_name, raw_trace, level);
 		goto out;
 	}
 
@@ -2029,7 +2135,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
 	}
 
 	if (!strcmp(field_name, "*")) {
-		ret = add_evsel_fields(evsel, raw_trace);
+		ret = add_evsel_fields(evsel, raw_trace, level);
 	} else {
 		field = pevent_find_any_field(evsel->tp_format, field_name);
 		if (field == NULL) {
@@ -2038,7 +2144,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
 			return -ENOENT;
 		}
 
-		ret = __dynamic_dimension__add(evsel, field, raw_trace);
+		ret = __dynamic_dimension__add(evsel, field, raw_trace, level);
 	}
 
 out:
@@ -2046,12 +2152,14 @@ out:
 	return ret;
 }
 
-static int __sort_dimension__add(struct sort_dimension *sd)
+static int __sort_dimension__add(struct sort_dimension *sd,
+				 struct perf_hpp_list *list,
+				 int level)
 {
 	if (sd->taken)
 		return 0;
 
-	if (__sort_dimension__add_hpp_sort(sd) < 0)
+	if (__sort_dimension__add_hpp_sort(sd, list, level) < 0)
 		return -1;
 
 	if (sd->entry->se_collapse)
@@ -2062,46 +2170,63 @@ static int __sort_dimension__add(struct sort_dimension *sd)
 	return 0;
 }
 
-static int __hpp_dimension__add(struct hpp_dimension *hd)
+static int __hpp_dimension__add(struct hpp_dimension *hd,
+				struct perf_hpp_list *list,
+				int level)
 {
-	if (!hd->taken) {
-		hd->taken = 1;
+	struct perf_hpp_fmt *fmt;
 
-		perf_hpp__register_sort_field(hd->fmt);
-	}
+	if (hd->taken)
+		return 0;
+
+	fmt = __hpp_dimension__alloc_hpp(hd, level);
+	if (!fmt)
+		return -1;
+
+	hd->taken = 1;
+	perf_hpp_list__register_sort_field(list, fmt);
 	return 0;
 }
 
-static int __sort_dimension__add_output(struct sort_dimension *sd)
+static int __sort_dimension__add_output(struct perf_hpp_list *list,
+					struct sort_dimension *sd)
 {
 	if (sd->taken)
 		return 0;
 
-	if (__sort_dimension__add_hpp_output(sd) < 0)
+	if (__sort_dimension__add_hpp_output(sd, list) < 0)
 		return -1;
 
 	sd->taken = 1;
 	return 0;
 }
 
-static int __hpp_dimension__add_output(struct hpp_dimension *hd)
+static int __hpp_dimension__add_output(struct perf_hpp_list *list,
+				       struct hpp_dimension *hd)
 {
-	if (!hd->taken) {
-		hd->taken = 1;
+	struct perf_hpp_fmt *fmt;
 
-		perf_hpp__column_register(hd->fmt);
-	}
+	if (hd->taken)
+		return 0;
+
+	fmt = __hpp_dimension__alloc_hpp(hd, 0);
+	if (!fmt)
+		return -1;
+
+	hd->taken = 1;
+	perf_hpp_list__column_register(list, fmt);
 	return 0;
 }
 
 int hpp_dimension__add_output(unsigned col)
 {
 	BUG_ON(col >= PERF_HPP__MAX_INDEX);
-	return __hpp_dimension__add_output(&hpp_sort_dimensions[col]);
+	return __hpp_dimension__add_output(&perf_hpp_list, &hpp_sort_dimensions[col]);
 }
 
-static int sort_dimension__add(const char *tok,
-			       struct perf_evlist *evlist __maybe_unused)
+static int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
+			       struct perf_evlist *evlist,
+			       int level)
 {
 	unsigned int i;
 
@@ -2136,9 +2261,13 @@ static int sort_dimension__add(const char *tok,
 			sort__has_dso = 1;
 		} else if (sd->entry == &sort_socket) {
 			sort__has_socket = 1;
+		} else if (sd->entry == &sort_thread) {
+			sort__has_thread = 1;
+		} else if (sd->entry == &sort_comm) {
+			sort__has_comm = 1;
 		}
 
-		return __sort_dimension__add(sd);
+		return __sort_dimension__add(sd, list, level);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
@@ -2147,7 +2276,7 @@ static int sort_dimension__add(const char *tok,
 		if (strncasecmp(tok, hd->name, strlen(tok)))
 			continue;
 
-		return __hpp_dimension__add(hd);
+		return __hpp_dimension__add(hd, list, level);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
@@ -2162,7 +2291,7 @@ static int sort_dimension__add(const char *tok,
 		if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to)
 			sort__has_sym = 1;
 
-		__sort_dimension__add(sd);
+		__sort_dimension__add(sd, list, level);
 		return 0;
 	}
 
@@ -2178,16 +2307,60 @@ static int sort_dimension__add(const char *tok,
 		if (sd->entry == &sort_mem_daddr_sym)
 			sort__has_sym = 1;
 
-		__sort_dimension__add(sd);
+		__sort_dimension__add(sd, list, level);
 		return 0;
 	}
 
-	if (!add_dynamic_entry(evlist, tok))
+	if (!add_dynamic_entry(evlist, tok, level))
 		return 0;
 
 	return -ESRCH;
 }
 
+static int setup_sort_list(struct perf_hpp_list *list, char *str,
+			   struct perf_evlist *evlist)
+{
+	char *tmp, *tok;
+	int ret = 0;
+	int level = 0;
+	int next_level = 1;
+	bool in_group = false;
+
+	do {
+		tok = str;
+		tmp = strpbrk(str, "{}, ");
+		if (tmp) {
+			if (in_group)
+				next_level = level;
+			else
+				next_level = level + 1;
+
+			if (*tmp == '{')
+				in_group = true;
+			else if (*tmp == '}')
+				in_group = false;
+
+			*tmp = '\0';
+			str = tmp + 1;
+		}
+
+		if (*tok) {
+			ret = sort_dimension__add(list, tok, evlist, level);
+			if (ret == -EINVAL) {
+				error("Invalid --sort key: `%s'", tok);
+				break;
+			} else if (ret == -ESRCH) {
+				error("Unknown --sort key: `%s'", tok);
+				break;
+			}
+		}
+
+		level = next_level;
+	} while (tmp);
+
+	return ret;
+}
+
 static const char *get_default_sort_order(struct perf_evlist *evlist)
 {
 	const char *default_sort_orders[] = {
@@ -2272,6 +2445,9 @@ static char *prefix_if_not_in(const char *pre, char *str)
 
 static char *setup_overhead(char *keys)
 {
+	if (sort__mode == SORT_MODE__DIFF)
+		return keys;
+
 	keys = prefix_if_not_in("overhead", keys);
 
 	if (symbol_conf.cumulate_callchain)
@@ -2282,7 +2458,7 @@ static char *setup_overhead(char *keys)
 
 static int __setup_sorting(struct perf_evlist *evlist)
 {
-	char *tmp, *tok, *str;
+	char *str;
 	const char *sort_keys;
 	int ret = 0;
 
@@ -2320,17 +2496,7 @@ static int __setup_sorting(struct perf_evlist *evlist)
 		}
 	}
 
-	for (tok = strtok_r(str, ", ", &tmp);
-			tok; tok = strtok_r(NULL, ", ", &tmp)) {
-		ret = sort_dimension__add(tok, evlist);
-		if (ret == -EINVAL) {
-			error("Invalid --sort key: `%s'", tok);
-			break;
-		} else if (ret == -ESRCH) {
-			error("Unknown --sort key: `%s'", tok);
-			break;
-		}
-	}
+	ret = setup_sort_list(&perf_hpp_list, str, evlist);
 
 	free(str);
 	return ret;
@@ -2341,7 +2507,7 @@ void perf_hpp__set_elide(int idx, bool elide)
 	struct perf_hpp_fmt *fmt;
 	struct hpp_sort_entry *hse;
 
-	perf_hpp__for_each_format(fmt) {
+	perf_hpp_list__for_each_format(&perf_hpp_list, fmt) {
 		if (!perf_hpp__is_sort_entry(fmt))
 			continue;
 
@@ -2401,7 +2567,7 @@ void sort__setup_elide(FILE *output)
 	struct perf_hpp_fmt *fmt;
 	struct hpp_sort_entry *hse;
 
-	perf_hpp__for_each_format(fmt) {
+	perf_hpp_list__for_each_format(&perf_hpp_list, fmt) {
 		if (!perf_hpp__is_sort_entry(fmt))
 			continue;
 
@@ -2413,7 +2579,7 @@ void sort__setup_elide(FILE *output)
 	 * It makes no sense to elide all of sort entries.
 	 * Just revert them to show up again.
 	 */
-	perf_hpp__for_each_format(fmt) {
+	perf_hpp_list__for_each_format(&perf_hpp_list, fmt) {
 		if (!perf_hpp__is_sort_entry(fmt))
 			continue;
 
@@ -2421,7 +2587,7 @@ void sort__setup_elide(FILE *output)
 			return;
 	}
 
-	perf_hpp__for_each_format(fmt) {
+	perf_hpp_list__for_each_format(&perf_hpp_list, fmt) {
 		if (!perf_hpp__is_sort_entry(fmt))
 			continue;
 
@@ -2429,7 +2595,7 @@ void sort__setup_elide(FILE *output)
 	}
 }
 
-static int output_field_add(char *tok)
+static int output_field_add(struct perf_hpp_list *list, char *tok)
 {
 	unsigned int i;
 
@@ -2439,7 +2605,7 @@ static int output_field_add(char *tok)
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		return __sort_dimension__add_output(sd);
+		return __sort_dimension__add_output(list, sd);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
@@ -2448,7 +2614,7 @@ static int output_field_add(char *tok)
 		if (strncasecmp(tok, hd->name, strlen(tok)))
 			continue;
 
-		return __hpp_dimension__add_output(hd);
+		return __hpp_dimension__add_output(list, hd);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
@@ -2457,7 +2623,7 @@ static int output_field_add(char *tok)
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		return __sort_dimension__add_output(sd);
+		return __sort_dimension__add_output(list, sd);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) {
@@ -2466,12 +2632,32 @@ static int output_field_add(char *tok)
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		return __sort_dimension__add_output(sd);
+		return __sort_dimension__add_output(list, sd);
 	}
 
 	return -ESRCH;
 }
 
+static int setup_output_list(struct perf_hpp_list *list, char *str)
+{
+	char *tmp, *tok;
+	int ret = 0;
+
+	for (tok = strtok_r(str, ", ", &tmp);
+			tok; tok = strtok_r(NULL, ", ", &tmp)) {
+		ret = output_field_add(list, tok);
+		if (ret == -EINVAL) {
+			error("Invalid --fields key: `%s'", tok);
+			break;
+		} else if (ret == -ESRCH) {
+			error("Unknown --fields key: `%s'", tok);
+			break;
+		}
+	}
+
+	return ret;
+}
+
 static void reset_dimensions(void)
 {
 	unsigned int i;
@@ -2496,7 +2682,7 @@ bool is_strict_order(const char *order)
 
 static int __setup_output_field(void)
 {
-	char *tmp, *tok, *str, *strp;
+	char *str, *strp;
 	int ret = -EINVAL;
 
 	if (field_order == NULL)
@@ -2516,17 +2702,7 @@ static int __setup_output_field(void)
 		goto out;
 	}
 
-	for (tok = strtok_r(strp, ", ", &tmp);
-			tok; tok = strtok_r(NULL, ", ", &tmp)) {
-		ret = output_field_add(tok);
-		if (ret == -EINVAL) {
-			error("Invalid --fields key: `%s'", tok);
-			break;
-		} else if (ret == -ESRCH) {
-			error("Unknown --fields key: `%s'", tok);
-			break;
-		}
-	}
+	ret = setup_output_list(&perf_hpp_list, strp);
 
 out:
 	free(str);
@@ -2542,7 +2718,7 @@ int setup_sorting(struct perf_evlist *evlist)
 		return err;
 
 	if (parent_pattern != default_parent_pattern) {
-		err = sort_dimension__add("parent", evlist);
+		err = sort_dimension__add(&perf_hpp_list, "parent", evlist, -1);
 		if (err < 0)
 			return err;
 	}
@@ -2560,9 +2736,13 @@ int setup_sorting(struct perf_evlist *evlist)
 		return err;
 
 	/* copy sort keys to output fields */
-	perf_hpp__setup_output_field();
+	perf_hpp__setup_output_field(&perf_hpp_list);
 	/* and then copy output fields to sort keys */
-	perf_hpp__append_sort_keys();
+	perf_hpp__append_sort_keys(&perf_hpp_list);
+
+	/* setup hists-specific output fields */
+	if (perf_hpp__setup_hists_formats(&perf_hpp_list, evlist) < 0)
+		return -1;
 
 	return 0;
 }
@@ -2578,5 +2758,5 @@ void reset_output_field(void)
 	sort_order = NULL;
 
 	reset_dimensions();
-	perf_hpp__reset_output_field();
+	perf_hpp__reset_output_field(&perf_hpp_list);
 }
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 687bbb124..3f4e35998 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -32,9 +32,12 @@ extern const char default_sort_order[];
 extern regex_t ignore_callees_regex;
 extern int have_ignore_callees;
 extern int sort__need_collapse;
+extern int sort__has_dso;
 extern int sort__has_parent;
 extern int sort__has_sym;
 extern int sort__has_socket;
+extern int sort__has_thread;
+extern int sort__has_comm;
 extern enum sort_mode sort__mode;
 extern struct sort_entry sort_comm;
 extern struct sort_entry sort_dso;
@@ -94,9 +97,11 @@ struct hist_entry {
 	s32			socket;
 	s32			cpu;
 	u8			cpumode;
+	u8			depth;
 
 	/* We are added by hists__add_dummy_entry. */
 	bool			dummy;
+	bool			leaf;
 
 	char			level;
 	u8			filtered;
@@ -113,18 +118,28 @@ struct hist_entry {
 			bool	init_have_children;
 			bool	unfolded;
 			bool	has_children;
+			bool	has_no_entry;
 		};
 	};
 	char			*srcline;
 	char			*srcfile;
 	struct symbol		*parent;
-	struct rb_root		sorted_chain;
 	struct branch_info	*branch_info;
 	struct hists		*hists;
 	struct mem_info		*mem_info;
 	void			*raw_data;
 	u32			raw_size;
 	void			*trace_output;
+	struct perf_hpp_list	*hpp_list;
+	struct hist_entry	*parent_he;
+	union {
+		/* this is for hierarchical entry structure */
+		struct {
+			struct rb_root	hroot_in;
+			struct rb_root  hroot_out;
+		};				/* non-leaf entries */
+		struct rb_root	sorted_chain;	/* leaf entry has callchains */
+	};
 	struct callchain_root	callchain[0]; /* must be last member */
 };
 
@@ -160,6 +175,17 @@ static inline float hist_entry__get_percent_limit(struct hist_entry *he)
 	return period * 100.0 / total_period;
 }
 
+static inline u64 cl_address(u64 address)
+{
+	/* return the cacheline of the address */
+	return (address & ~(cacheline_size - 1));
+}
+
+static inline u64 cl_offset(u64 address)
+{
+	/* return the cacheline of the address */
+	return (address & (cacheline_size - 1));
+}
 
 enum sort_mode {
 	SORT_MODE__NORMAL,
@@ -221,6 +247,7 @@ struct sort_entry {
 	int64_t	(*se_sort)(struct hist_entry *, struct hist_entry *);
 	int	(*se_snprintf)(struct hist_entry *he, char *bf, size_t size,
 			       unsigned int width);
+	int	(*se_filter)(struct hist_entry *he, int type, const void *arg);
 	u8	se_width_idx;
 };
 
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 6ac031468..fdb719611 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -2,6 +2,7 @@
 #include "evsel.h"
 #include "stat.h"
 #include "color.h"
+#include "pmu.h"
 
 enum {
 	CTX_BIT_USER	= 1 << 0,
@@ -14,6 +15,13 @@ enum {
 
 #define NUM_CTX CTX_BIT_MAX
 
+/*
+ * AGGR_GLOBAL: Use CPU 0
+ * AGGR_SOCKET: Use first CPU of socket
+ * AGGR_CORE: Use first CPU of core
+ * AGGR_NONE: Use matching CPU
+ * AGGR_THREAD: Not supported?
+ */
 static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
 static struct stats runtime_cycles_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_stalled_cycles_front_stats[NUM_CTX][MAX_NR_CPUS];
@@ -28,9 +36,15 @@ static struct stats runtime_dtlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_cycles_in_tx_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_transaction_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_elision_stats[NUM_CTX][MAX_NR_CPUS];
+static bool have_frontend_stalled;
 
 struct stats walltime_nsecs_stats;
 
+void perf_stat__init_shadow_stats(void)
+{
+	have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend");
+}
+
 static int evsel_context(struct perf_evsel *evsel)
 {
 	int ctx = 0;
@@ -137,9 +151,9 @@ static const char *get_ratio_color(enum grc_type type, double ratio)
 	return color;
 }
 
-static void print_stalled_cycles_frontend(FILE *out, int cpu,
-					  struct perf_evsel *evsel
-					  __maybe_unused, double avg)
+static void print_stalled_cycles_frontend(int cpu,
+					  struct perf_evsel *evsel, double avg,
+					  struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -152,14 +166,16 @@ static void print_stalled_cycles_frontend(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " frontend cycles idle   ");
+	if (ratio)
+		out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle",
+				  ratio);
+	else
+		out->print_metric(out->ctx, NULL, NULL, "frontend cycles idle", 0);
 }
 
-static void print_stalled_cycles_backend(FILE *out, int cpu,
-					 struct perf_evsel *evsel
-					 __maybe_unused, double avg)
+static void print_stalled_cycles_backend(int cpu,
+					 struct perf_evsel *evsel, double avg,
+					 struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -172,14 +188,13 @@ static void print_stalled_cycles_backend(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " backend  cycles idle   ");
+	out->print_metric(out->ctx, color, "%6.2f%%", "backend cycles idle", ratio);
 }
 
-static void print_branch_misses(FILE *out, int cpu,
-				struct perf_evsel *evsel __maybe_unused,
-				double avg)
+static void print_branch_misses(int cpu,
+				struct perf_evsel *evsel,
+				double avg,
+				struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -192,14 +207,13 @@ static void print_branch_misses(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all branches        ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all branches", ratio);
 }
 
-static void print_l1_dcache_misses(FILE *out, int cpu,
-				   struct perf_evsel *evsel __maybe_unused,
-				   double avg)
+static void print_l1_dcache_misses(int cpu,
+				   struct perf_evsel *evsel,
+				   double avg,
+				   struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -212,14 +226,13 @@ static void print_l1_dcache_misses(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all L1-dcache hits  ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
 }
 
-static void print_l1_icache_misses(FILE *out, int cpu,
-				   struct perf_evsel *evsel __maybe_unused,
-				   double avg)
+static void print_l1_icache_misses(int cpu,
+				   struct perf_evsel *evsel,
+				   double avg,
+				   struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -231,15 +244,13 @@ static void print_l1_icache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all L1-icache hits  ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
 }
 
-static void print_dtlb_cache_misses(FILE *out, int cpu,
-				    struct perf_evsel *evsel __maybe_unused,
-				    double avg)
+static void print_dtlb_cache_misses(int cpu,
+				    struct perf_evsel *evsel,
+				    double avg,
+				    struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -251,15 +262,13 @@ static void print_dtlb_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all dTLB cache hits ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
 }
 
-static void print_itlb_cache_misses(FILE *out, int cpu,
-				    struct perf_evsel *evsel __maybe_unused,
-				    double avg)
+static void print_itlb_cache_misses(int cpu,
+				    struct perf_evsel *evsel,
+				    double avg,
+				    struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -271,15 +280,13 @@ static void print_itlb_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all iTLB cache hits ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
 }
 
-static void print_ll_cache_misses(FILE *out, int cpu,
-				  struct perf_evsel *evsel __maybe_unused,
-				  double avg)
+static void print_ll_cache_misses(int cpu,
+				  struct perf_evsel *evsel,
+				  double avg,
+				  struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -291,15 +298,15 @@ static void print_ll_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all LL-cache hits   ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
 }
 
-void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
-				   double avg, int cpu, enum aggr_mode aggr)
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+				   double avg, int cpu,
+				   struct perf_stat_output_ctx *out)
 {
+	void *ctxp = out->ctx;
+	print_metric_t print_metric = out->print_metric;
 	double total, ratio = 0.0, total2;
 	int ctx = evsel_context(evsel);
 
@@ -307,119 +314,145 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		if (total) {
 			ratio = avg / total;
-			fprintf(out, " #   %5.2f  insns per cycle        ", ratio);
+			print_metric(ctxp, NULL, "%7.2f ",
+					"insn per cycle", ratio);
 		} else {
-			fprintf(out, "                                   ");
+			print_metric(ctxp, NULL, NULL, "insn per cycle", 0);
 		}
 		total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
 		total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));
 
 		if (total && avg) {
+			out->new_line(ctxp);
 			ratio = total / avg;
-			fprintf(out, "\n");
-			if (aggr == AGGR_NONE)
-				fprintf(out, "        ");
-			fprintf(out, "                                                  #   %5.2f  stalled cycles per insn", ratio);
+			print_metric(ctxp, NULL, "%7.2f ",
+					"stalled cycles per insn",
+					ratio);
+		} else if (have_frontend_stalled) {
+			print_metric(ctxp, NULL, NULL,
+				     "stalled cycles per insn", 0);
 		}
-
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
-			runtime_branches_stats[ctx][cpu].n != 0) {
-		print_branch_misses(out, cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
+		if (runtime_branches_stats[ctx][cpu].n != 0)
+			print_branch_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all branches", 0);
 	} 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[ctx][cpu].n != 0) {
-		print_l1_dcache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_l1_dcache_stats[ctx][cpu].n != 0)
+			print_l1_dcache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
 	} 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[ctx][cpu].n != 0) {
-		print_l1_icache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_l1_icache_stats[ctx][cpu].n != 0)
+			print_l1_icache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
 	} 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[ctx][cpu].n != 0) {
-		print_dtlb_cache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_dtlb_cache_stats[ctx][cpu].n != 0)
+			print_dtlb_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
 	} 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[ctx][cpu].n != 0) {
-		print_itlb_cache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_itlb_cache_stats[ctx][cpu].n != 0)
+			print_itlb_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
 	} 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[ctx][cpu].n != 0) {
-		print_ll_cache_misses(out, cpu, evsel, avg);
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
-			runtime_cacherefs_stats[ctx][cpu].n != 0) {
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_ll_cache_stats[ctx][cpu].n != 0)
+			print_ll_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all LL-cache hits", 0);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
 		total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);
 
 		if (total)
 			ratio = avg * 100 / total;
 
-		fprintf(out, " # %8.3f %% of all cache refs    ", ratio);
-
+		if (runtime_cacherefs_stats[ctx][cpu].n != 0)
+			print_metric(ctxp, NULL, "%8.3f %%",
+				     "of all cache refs", ratio);
+		else
+			print_metric(ctxp, NULL, NULL, "of all cache refs", 0);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
-		print_stalled_cycles_frontend(out, cpu, evsel, avg);
+		print_stalled_cycles_frontend(cpu, evsel, avg, out);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
-		print_stalled_cycles_backend(out, cpu, evsel, avg);
+		print_stalled_cycles_backend(cpu, evsel, avg, out);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
 		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
 		if (total) {
 			ratio = avg / total;
-			fprintf(out, " # %8.3f GHz                    ", ratio);
+			print_metric(ctxp, NULL, "%8.3f", "GHz", ratio);
 		} else {
-			fprintf(out, "                                   ");
+			print_metric(ctxp, NULL, NULL, "Ghz", 0);
 		}
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		if (total)
-			fprintf(out,
-				" #   %5.2f%% transactional cycles   ",
-				100.0 * (avg / total));
+			print_metric(ctxp, NULL,
+					"%7.2f%%", "transactional cycles",
+					100.0 * (avg / total));
+		else
+			print_metric(ctxp, NULL, NULL, "transactional cycles",
+				     0);
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		total2 = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 		if (total2 < avg)
 			total2 = avg;
 		if (total)
-			fprintf(out,
-				" #   %5.2f%% aborted cycles         ",
+			print_metric(ctxp, NULL, "%7.2f%%", "aborted cycles",
 				100.0 * ((total2-avg) / total));
-	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
-		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+		else
+			print_metric(ctxp, NULL, NULL, "aborted cycles", 0);
+	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
 		if (avg)
 			ratio = total / avg;
 
-		fprintf(out, " # %8.0f cycles / transaction   ", ratio);
-	} else if (perf_stat_evsel__is(evsel, ELISION_START) &&
-		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+		if (runtime_cycles_in_tx_stats[ctx][cpu].n != 0)
+			print_metric(ctxp, NULL, "%8.0f",
+				     "cycles / transaction", ratio);
+		else
+			print_metric(ctxp, NULL, NULL, "cycles / transaction",
+				     0);
+	} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
 		if (avg)
 			ratio = total / avg;
 
-		fprintf(out, " # %8.0f cycles / elision       ", ratio);
+		print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
 	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) {
 		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
-			fprintf(out, " # %8.3f CPUs utilized          ", avg / ratio);
+			print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
+				     avg / ratio);
 		else
-			fprintf(out, "                                   ");
+			print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
+		char unit_buf[10];
 
 		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
@@ -429,9 +462,9 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 			ratio *= 1000;
 			unit = 'K';
 		}
-
-		fprintf(out, " # %8.3f %c/sec                  ", ratio, unit);
+		snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
+		print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio);
 	} else {
-		fprintf(out, "                                   ");
+		print_metric(ctxp, NULL, NULL, NULL, 0);
 	}
 }
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index afb0c45eb..4d9b481cf 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -97,7 +97,7 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel)
 	}
 }
 
-void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
+static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 {
 	int i;
 	struct perf_stat_evsel *ps = evsel->priv;
@@ -108,7 +108,7 @@ void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 	perf_stat_evsel_id_init(evsel);
 }
 
-int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
+static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 {
 	evsel->priv = zalloc(sizeof(struct perf_stat_evsel));
 	if (evsel->priv == NULL)
@@ -117,13 +117,13 @@ int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 	return 0;
 }
 
-void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
+static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
 {
 	zfree(&evsel->priv);
 }
 
-int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
-				      int ncpus, int nthreads)
+static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
+					     int ncpus, int nthreads)
 {
 	struct perf_counts *counts;
 
@@ -134,13 +134,13 @@ int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
 	return counts ? 0 : -ENOMEM;
 }
 
-void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
+static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
 {
 	perf_counts__delete(evsel->prev_raw_counts);
 	evsel->prev_raw_counts = NULL;
 }
 
-int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
+static int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
 {
 	int ncpus = perf_evsel__nr_cpus(evsel);
 	int nthreads = thread_map__nr(evsel->threads);
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 086f4e128..0150e786c 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -68,21 +68,23 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel);
 
 extern struct stats walltime_nsecs_stats;
 
+typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit,
+			       const char *fmt, double val);
+typedef void (*new_line_t )(void *ctx);
+
+void perf_stat__init_shadow_stats(void);
 void perf_stat__reset_shadow_stats(void);
 void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 				    int cpu);
-void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
-				   double avg, int cpu, enum aggr_mode aggr);
-
-void perf_evsel__reset_stat_priv(struct perf_evsel *evsel);
-int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel);
-void perf_evsel__free_stat_priv(struct perf_evsel *evsel);
-
-int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
-				      int ncpus, int nthreads);
-void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel);
+struct perf_stat_output_ctx {
+	void *ctx;
+	print_metric_t print_metric;
+	new_line_t new_line;
+};
 
-int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw);
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+				   double avg, int cpu,
+				   struct perf_stat_output_ctx *out);
 
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
 void perf_evlist__free_stats(struct perf_evlist *evlist);
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 25671fa16..8fb73295e 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -51,28 +51,11 @@ void strbuf_grow(struct strbuf *sb, size_t extra)
 	ALLOC_GROW(sb->buf, sb->len + extra + 1, sb->alloc);
 }
 
-static void strbuf_splice(struct strbuf *sb, size_t pos, size_t len,
-				   const void *data, size_t dlen)
+void strbuf_addch(struct strbuf *sb, int c)
 {
-	if (pos + len < pos)
-		die("you want to use way too much memory");
-	if (pos > sb->len)
-		die("`pos' is too far after the end of the buffer");
-	if (pos + len > sb->len)
-		die("`pos + len' is too far after the end of the buffer");
-
-	if (dlen >= len)
-		strbuf_grow(sb, dlen - len);
-	memmove(sb->buf + pos + dlen,
-			sb->buf + pos + len,
-			sb->len - pos - len);
-	memcpy(sb->buf + pos, data, dlen);
-	strbuf_setlen(sb, sb->len + dlen - len);
-}
-
-void strbuf_remove(struct strbuf *sb, size_t pos, size_t len)
-{
-	strbuf_splice(sb, pos, len, NULL, 0);
+	strbuf_grow(sb, 1);
+	sb->buf[sb->len++] = c;
+	sb->buf[sb->len] = '\0';
 }
 
 void strbuf_add(struct strbuf *sb, const void *data, size_t len)
@@ -82,7 +65,7 @@ void strbuf_add(struct strbuf *sb, const void *data, size_t len)
 	strbuf_setlen(sb, sb->len + len);
 }
 
-void strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap)
+static void strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap)
 {
 	int len;
 	va_list ap_saved;
diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h
index 529f2f035..ab9be0fbb 100644
--- a/tools/perf/util/strbuf.h
+++ b/tools/perf/util/strbuf.h
@@ -51,16 +51,16 @@ struct strbuf {
 #define STRBUF_INIT  { 0, 0, strbuf_slopbuf }
 
 /*----- strbuf life cycle -----*/
-extern void strbuf_init(struct strbuf *buf, ssize_t hint);
-extern void strbuf_release(struct strbuf *);
-extern char *strbuf_detach(struct strbuf *, size_t *);
+void strbuf_init(struct strbuf *buf, ssize_t hint);
+void strbuf_release(struct strbuf *buf);
+char *strbuf_detach(struct strbuf *buf, size_t *);
 
 /*----- strbuf size related -----*/
 static inline ssize_t strbuf_avail(const struct strbuf *sb) {
 	return sb->alloc ? sb->alloc - sb->len - 1 : 0;
 }
 
-extern void strbuf_grow(struct strbuf *, size_t);
+void strbuf_grow(struct strbuf *buf, size_t);
 
 static inline void strbuf_setlen(struct strbuf *sb, size_t len) {
 	if (!sb->alloc)
@@ -71,24 +71,17 @@ static inline void strbuf_setlen(struct strbuf *sb, size_t len) {
 }
 
 /*----- add data in your buffer -----*/
-static inline void strbuf_addch(struct strbuf *sb, int c) {
-	strbuf_grow(sb, 1);
-	sb->buf[sb->len++] = c;
-	sb->buf[sb->len] = '\0';
-}
-
-extern void strbuf_remove(struct strbuf *, size_t pos, size_t len);
+void strbuf_addch(struct strbuf *sb, int c);
 
-extern void strbuf_add(struct strbuf *, const void *, size_t);
+void strbuf_add(struct strbuf *buf, const void *, size_t);
 static inline void strbuf_addstr(struct strbuf *sb, const char *s) {
 	strbuf_add(sb, s, strlen(s));
 }
 
 __attribute__((format(printf,2,3)))
-extern void strbuf_addf(struct strbuf *sb, const char *fmt, ...);
-extern void strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap);
+void strbuf_addf(struct strbuf *sb, const char *fmt, ...);
 
 /* XXX: if read fails, any partial read is undone */
-extern ssize_t strbuf_read(struct strbuf *, int fd, ssize_t hint);
+ssize_t strbuf_read(struct strbuf *, int fd, ssize_t hint);
 
 #endif /* __PERF_STRBUF_H */
diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h
index 9292a5291..946fdf2db 100644
--- a/tools/perf/util/svghelper.h
+++ b/tools/perf/util/svghelper.h
@@ -3,32 +3,31 @@
 
 #include <linux/types.h>
 
-extern void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end);
-extern void svg_ubox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
-extern void svg_lbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
-extern void svg_fbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
-extern void svg_box(int Yslot, u64 start, u64 end, const char *type);
-extern void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
-extern void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
-extern void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
-extern void svg_cpu_box(int cpu, u64 max_frequency, u64 turbo_frequency);
-
-
-extern void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const char *backtrace);
-extern void svg_cstate(int cpu, u64 start, u64 end, int type);
-extern void svg_pstate(int cpu, u64 start, u64 end, u64 freq);
-
-
-extern void svg_time_grid(double min_thickness);
-extern void svg_io_legenda(void);
-extern void svg_legenda(void);
-extern void svg_wakeline(u64 start, int row1, int row2, const char *backtrace);
-extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace);
-extern void svg_interrupt(u64 start, int row, const char *backtrace);
-extern void svg_text(int Yslot, u64 start, const char *text);
-extern void svg_close(void);
-extern int svg_build_topology_map(char *sib_core, int sib_core_nr,
-				  char *sib_thr, int sib_thr_nr);
+void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end);
+void svg_ubox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
+void svg_lbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
+void svg_fbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
+void svg_box(int Yslot, u64 start, u64 end, const char *type);
+void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
+void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
+void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
+void svg_cpu_box(int cpu, u64 max_frequency, u64 turbo_frequency);
+
+
+void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const char *backtrace);
+void svg_cstate(int cpu, u64 start, u64 end, int type);
+void svg_pstate(int cpu, u64 start, u64 end, u64 freq);
+
+
+void svg_time_grid(double min_thickness);
+void svg_io_legenda(void);
+void svg_legenda(void);
+void svg_wakeline(u64 start, int row1, int row2, const char *backtrace);
+void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace);
+void svg_interrupt(u64 start, int row, const char *backtrace);
+void svg_text(int Yslot, u64 start, const char *text);
+void svg_close(void);
+int svg_build_topology_map(char *sib_core, int sib_core_nr, char *sib_thr, int sib_thr_nr);
 
 extern int svg_page_width;
 extern u64 svg_highlight;
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 562b8ebea..bc229a74c 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -6,6 +6,7 @@
 #include <inttypes.h>
 
 #include "symbol.h"
+#include "demangle-java.h"
 #include "machine.h"
 #include "vdso.h"
 #include <symbol/kallsyms.h>
@@ -792,6 +793,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
 	uint32_t idx;
 	GElf_Ehdr ehdr;
 	GElf_Shdr shdr;
+	GElf_Shdr tshdr;
 	Elf_Data *syms, *opddata = NULL;
 	GElf_Sym sym;
 	Elf_Scn *sec, *sec_strndx;
@@ -831,6 +833,9 @@ int dso__load_sym(struct dso *dso, struct map *map,
 	sec = syms_ss->symtab;
 	shdr = syms_ss->symshdr;
 
+	if (elf_section_by_name(elf, &ehdr, &tshdr, ".text", NULL))
+		dso->text_offset = tshdr.sh_addr - tshdr.sh_offset;
+
 	if (runtime_ss->opdsec)
 		opddata = elf_rawdata(runtime_ss->opdsec, NULL);
 
@@ -879,12 +884,8 @@ int dso__load_sym(struct dso *dso, struct map *map,
 	 * Handle any relocation of vdso necessary because older kernels
 	 * attempted to prelink vdso to its virtual address.
 	 */
-	if (dso__is_vdso(dso)) {
-		GElf_Shdr tshdr;
-
-		if (elf_section_by_name(elf, &ehdr, &tshdr, ".text", NULL))
-			map->reloc = map->start - tshdr.sh_addr + tshdr.sh_offset;
-	}
+	if (dso__is_vdso(dso))
+		map->reloc = map->start - dso->text_offset;
 
 	dso->adjust_symbols = runtime_ss->adjust_symbols || ref_reloc(kmap);
 	/*
@@ -1077,6 +1078,8 @@ new_symbol:
 				demangle_flags = DMGL_PARAMS | DMGL_ANSI;
 
 			demangled = bfd_demangle(NULL, elf_name, demangle_flags);
+			if (demangled == NULL)
+				demangled = java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET);
 			if (demangled != NULL)
 				elf_name = demangled;
 		}
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index ab02209a7..e7588dc91 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1466,7 +1466,8 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	 * Read the build id if possible. This is required for
 	 * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
 	 */
-	if (filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
+	if (is_regular_file(name) &&
+	    filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
 		dso__set_build_id(dso, build_id);
 
 	/*
@@ -1487,6 +1488,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 						   root_dir, name, PATH_MAX))
 			continue;
 
+		if (!is_regular_file(name))
+			continue;
+
 		/* Name is now the name of the next image to try */
 		if (symsrc__init(ss, dso, name, symtab_type) < 0)
 			continue;
@@ -1525,6 +1529,10 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	if (!runtime_ss && syms_ss)
 		runtime_ss = syms_ss;
 
+	if (syms_ss && syms_ss->type == DSO_BINARY_TYPE__BUILD_ID_CACHE)
+		if (dso__build_id_is_kmod(dso, name, PATH_MAX))
+			kmod = true;
+
 	if (syms_ss)
 		ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, kmod);
 	else
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index ccd1caa40..c8b7544d9 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -34,8 +34,8 @@
 #endif
 
 #ifdef HAVE_LIBELF_SUPPORT
-extern Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
-				GElf_Shdr *shp, const char *name, size_t *idx);
+Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
+			     GElf_Shdr *shp, const char *name, size_t *idx);
 #endif
 
 #ifndef DMGL_PARAMS
@@ -110,7 +110,8 @@ struct symbol_conf {
 			has_filter,
 			show_ref_callgraph,
 			hide_unresolved,
-			raw_trace;
+			raw_trace,
+			report_hierarchy;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 08afc6909..267112b4e 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -94,7 +94,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 	DIR *proc;
 	int max_threads = 32, items, i;
 	char path[256];
-	struct dirent dirent, *next, **namelist = NULL;
+	struct dirent *dirent, **namelist = NULL;
 	struct thread_map *threads = thread_map__alloc(max_threads);
 
 	if (threads == NULL)
@@ -107,16 +107,16 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 	threads->nr = 0;
 	atomic_set(&threads->refcnt, 1);
 
-	while (!readdir_r(proc, &dirent, &next) && next) {
+	while ((dirent = readdir(proc)) != NULL) {
 		char *end;
 		bool grow = false;
 		struct stat st;
-		pid_t pid = strtol(dirent.d_name, &end, 10);
+		pid_t pid = strtol(dirent->d_name, &end, 10);
 
 		if (*end) /* only interested in proper numerical dirents */
 			continue;
 
-		snprintf(path, sizeof(path), "/proc/%s", dirent.d_name);
+		snprintf(path, sizeof(path), "/proc/%s", dirent->d_name);
 
 		if (stat(path, &st) != 0)
 			continue;
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 802bb868d..8ae051e0e 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -10,6 +10,7 @@
 #include <linux/err.h>
 #include <traceevent/event-parse.h>
 #include <api/fs/tracing_path.h>
+#include <api/fs/fs.h>
 #include "trace-event.h"
 #include "machine.h"
 #include "util.h"
diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c
index 4d4210d4e..1b741646e 100644
--- a/tools/perf/util/tsc.c
+++ b/tools/perf/util/tsc.c
@@ -19,7 +19,7 @@ u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc)
 	u64 quot, rem;
 
 	quot = cyc >> tc->time_shift;
-	rem  = cyc & ((1 << tc->time_shift) - 1);
+	rem  = cyc & (((u64)1 << tc->time_shift) - 1);
 	return tc->time_zero + quot * tc->time_mult +
 	       ((rem * tc->time_mult) >> tc->time_shift);
 }
diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c
index 6adfa18cd..996046a66 100644
--- a/tools/perf/util/usage.c
+++ b/tools/perf/util/usage.c
@@ -41,15 +41,9 @@ static void warn_builtin(const char *warn, va_list params)
 /* If we are in a dlopen()ed .so write to a global variable would segfault
  * (ugh), so keep things static. */
 static void (*usage_routine)(const char *err) NORETURN = usage_builtin;
-static void (*die_routine)(const char *err, va_list params) NORETURN = die_builtin;
 static void (*error_routine)(const char *err, va_list params) = error_builtin;
 static void (*warn_routine)(const char *err, va_list params) = warn_builtin;
 
-void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN)
-{
-	die_routine = routine;
-}
-
 void set_warning_routine(void (*routine)(const char *err, va_list params))
 {
 	warn_routine = routine;
@@ -65,7 +59,7 @@ void die(const char *err, ...)
 	va_list params;
 
 	va_start(params, err);
-	die_routine(err, params);
+	die_builtin(err, params);
 	va_end(params);
 }
 
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index ead950983..b7766c577 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -14,6 +14,7 @@
 #include <limits.h>
 #include <byteswap.h>
 #include <linux/kernel.h>
+#include <linux/log2.h>
 #include <unistd.h>
 #include "callchain.h"
 #include "strlist.h"
@@ -507,54 +508,6 @@ int parse_callchain_record(const char *arg, struct callchain_param *param)
 	return ret;
 }
 
-int filename__read_str(const char *filename, char **buf, size_t *sizep)
-{
-	size_t size = 0, alloc_size = 0;
-	void *bf = NULL, *nbf;
-	int fd, n, err = 0;
-	char sbuf[STRERR_BUFSIZE];
-
-	fd = open(filename, O_RDONLY);
-	if (fd < 0)
-		return -errno;
-
-	do {
-		if (size == alloc_size) {
-			alloc_size += BUFSIZ;
-			nbf = realloc(bf, alloc_size);
-			if (!nbf) {
-				err = -ENOMEM;
-				break;
-			}
-
-			bf = nbf;
-		}
-
-		n = read(fd, bf + size, alloc_size - size);
-		if (n < 0) {
-			if (size) {
-				pr_warning("read failed %d: %s\n", errno,
-					 strerror_r(errno, sbuf, sizeof(sbuf)));
-				err = 0;
-			} else
-				err = -errno;
-
-			break;
-		}
-
-		size += n;
-	} while (n > 0);
-
-	if (!err) {
-		*sizep = size;
-		*buf   = bf;
-	} else
-		free(bf);
-
-	close(fd);
-	return err;
-}
-
 const char *get_filename_for_perf_kvm(void)
 {
 	const char *filename;
@@ -691,3 +644,66 @@ out:
 
 	return tip;
 }
+
+bool is_regular_file(const char *file)
+{
+	struct stat st;
+
+	if (stat(file, &st))
+		return false;
+
+	return S_ISREG(st.st_mode);
+}
+
+int fetch_current_timestamp(char *buf, size_t sz)
+{
+	struct timeval tv;
+	struct tm tm;
+	char dt[32];
+
+	if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm))
+		return -1;
+
+	if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm))
+		return -1;
+
+	scnprintf(buf, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000);
+
+	return 0;
+}
+
+void print_binary(unsigned char *data, size_t len,
+		  size_t bytes_per_line, print_binary_t printer,
+		  void *extra)
+{
+	size_t i, j, mask;
+
+	if (!printer)
+		return;
+
+	bytes_per_line = roundup_pow_of_two(bytes_per_line);
+	mask = bytes_per_line - 1;
+
+	printer(BINARY_PRINT_DATA_BEGIN, 0, extra);
+	for (i = 0; i < len; i++) {
+		if ((i & mask) == 0) {
+			printer(BINARY_PRINT_LINE_BEGIN, -1, extra);
+			printer(BINARY_PRINT_ADDR, i, extra);
+		}
+
+		printer(BINARY_PRINT_NUM_DATA, data[i], extra);
+
+		if (((i & mask) == mask) || i == len - 1) {
+			for (j = 0; j < mask-(i & mask); j++)
+				printer(BINARY_PRINT_NUM_PAD, -1, extra);
+
+			printer(BINARY_PRINT_SEP, i, extra);
+			for (j = i & ~mask; j <= i; j++)
+				printer(BINARY_PRINT_CHAR_DATA, data[j], extra);
+			for (j = 0; j < mask-(i & mask); j++)
+				printer(BINARY_PRINT_CHAR_PAD, i, extra);
+			printer(BINARY_PRINT_LINE_END, -1, extra);
+		}
+	}
+	printer(BINARY_PRINT_DATA_END, -1, extra);
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index fe915e616..8298d607c 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -82,6 +82,8 @@
 
 extern const char *graph_line;
 extern const char *graph_dotted_line;
+extern const char *spaces;
+extern const char *dots;
 extern char buildid_dir[];
 
 /* On most systems <limits.h> would have given us this, but
@@ -131,25 +133,15 @@ extern char buildid_dir[];
 #define PERF_GTK_DSO  "libperf-gtk.so"
 
 /* General helper functions */
-extern void usage(const char *err) NORETURN;
-extern void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2)));
-extern int error(const char *err, ...) __attribute__((format (printf, 1, 2)));
-extern void warning(const char *err, ...) __attribute__((format (printf, 1, 2)));
+void usage(const char *err) NORETURN;
+void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2)));
+int error(const char *err, ...) __attribute__((format (printf, 1, 2)));
+void warning(const char *err, ...) __attribute__((format (printf, 1, 2)));
 
-#include "../../../include/linux/stringify.h"
+void set_warning_routine(void (*routine)(const char *err, va_list params));
 
-#define DIE_IF(cnd)	\
-	do { if (cnd)	\
-		die(" at (" __FILE__ ":" __stringify(__LINE__) "): "	\
-		    __stringify(cnd) "\n");				\
-	} while (0)
-
-
-extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN);
-extern void set_warning_routine(void (*routine)(const char *err, va_list params));
-
-extern int prefixcmp(const char *str, const char *prefix);
-extern void set_buildid_dir(const char *dir);
+int prefixcmp(const char *str, const char *prefix);
+void set_buildid_dir(const char *dir);
 
 #ifdef __GLIBC_PREREQ
 #if __GLIBC_PREREQ(2, 1)
@@ -170,8 +162,7 @@ static inline char *gitstrchrnul(const char *s, int c)
 /*
  * Wrappers:
  */
-extern char *xstrdup(const char *str);
-extern void *xrealloc(void *ptr, size_t size) __attribute__((weak));
+void *xrealloc(void *ptr, size_t size) __attribute__((weak));
 
 
 static inline void *zalloc(size_t size)
@@ -303,7 +294,6 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 		  bool show_sym, bool unwind_inlines);
 void free_srcline(char *srcline);
 
-int filename__read_str(const char *filename, char **buf, size_t *sizep);
 int perf_event_paranoid(void);
 
 void mem_bswap_64(void *src, int byte_size);
@@ -343,5 +333,27 @@ int fetch_kernel_version(unsigned int *puint,
 #define KVER_PARAM(x)	KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x)
 
 const char *perf_tip(const char *dirpath);
+bool is_regular_file(const char *file);
+int fetch_current_timestamp(char *buf, size_t sz);
+
+enum binary_printer_ops {
+	BINARY_PRINT_DATA_BEGIN,
+	BINARY_PRINT_LINE_BEGIN,
+	BINARY_PRINT_ADDR,
+	BINARY_PRINT_NUM_DATA,
+	BINARY_PRINT_NUM_PAD,
+	BINARY_PRINT_SEP,
+	BINARY_PRINT_CHAR_DATA,
+	BINARY_PRINT_CHAR_PAD,
+	BINARY_PRINT_LINE_END,
+	BINARY_PRINT_DATA_END,
+};
+
+typedef void (*print_binary_t)(enum binary_printer_ops,
+			       unsigned int val,
+			       void *extra);
 
+void print_binary(unsigned char *data, size_t len,
+		  size_t bytes_per_line, print_binary_t printer,
+		  void *extra);
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/perf/util/wrapper.c b/tools/perf/util/wrapper.c
index 19f15b650..5f1a07c4b 100644
--- a/tools/perf/util/wrapper.c
+++ b/tools/perf/util/wrapper.c
@@ -12,18 +12,6 @@ static inline void release_pack_memory(size_t size __maybe_unused,
 {
 }
 
-char *xstrdup(const char *str)
-{
-	char *ret = strdup(str);
-	if (!ret) {
-		release_pack_memory(strlen(str) + 1, -1);
-		ret = strdup(str);
-		if (!ret)
-			die("Out of memory, strdup failed");
-	}
-	return ret;
-}
-
 void *xrealloc(void *ptr, size_t size)
 {
 	void *ret = realloc(ptr, size);
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index 622db685b..89a55d5e3 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -34,7 +34,10 @@ name as necessary to disambiguate it from others is necessary.  Note that option
 \fB--debug\fP displays additional system configuration information.  Invoking this parameter
 more than once may also enable internal turbostat debug information.
 .PP
-\fB--interval seconds\fP overrides the default 5-second measurement interval.
+\fB--interval seconds\fP overrides the default 5.0 second measurement interval.
+.PP
+\fB--out output_file\fP turbostat output is written to the specified output_file.
+The file is truncated if it already exists, and it is created if it does not exist.
 .PP
 \fB--help\fP displays usage for the most common parameters.
 .PP
@@ -61,7 +64,7 @@ displays the statistics gathered since it was forked.
 .nf
 \fBCPU\fP Linux CPU (logical processor) number.  Yes, it is okay that on many systems the CPUs are not listed in numerical order -- for efficiency reasons, turbostat runs in topology order, so HT siblings appear together.
 \fBAVG_MHz\fP number of cycles executed divided by time elapsed.
-\fB%Busy\fP percent of the interval that the CPU retired instructions, aka. % of time in "C0" state.
+\fBBusy%\fP percent of the interval that the CPU retired instructions, aka. % of time in "C0" state.
 \fBBzy_MHz\fP average clock rate while the CPU was busy (in "c0" state).
 \fBTSC_MHz\fP average MHz that the TSC ran during the entire interval.
 .fi
@@ -83,13 +86,14 @@ Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading T
 \fBRAM_%\fP percent of the interval that RAPL throttling was active on DRAM.
 .fi
 .PP
-.SH EXAMPLE
+.SH PERIODIC EXAMPLE
 Without any parameters, turbostat displays statistics ever 5 seconds.
-(override interval with "-i sec" option, or specify a command
-for turbostat to fork).
+Periodic output goes to stdout, by default, unless --out is used to specify an output file.
+The 5-second interval can be changed with th "-i sec" option.
+Or a command may be specified as in "FORK EXAMPLE" below.
 .nf
 [root@hsw]# ./turbostat
-     CPU Avg_MHz   %Busy Bzy_MHz TSC_MHz
+     CPU Avg_MHz   Busy% Bzy_MHz TSC_MHz
        -     488   12.51    3898    3498
        0       0    0.01    3885    3498
        4    3897   99.99    3898    3498
@@ -145,7 +149,7 @@ cpu0: MSR_IA32_THERM_STATUS: 0x88340000 (48 C +/- 1)
 cpu1: MSR_IA32_THERM_STATUS: 0x88440000 (32 C +/- 1)
 cpu2: MSR_IA32_THERM_STATUS: 0x88450000 (31 C +/- 1)
 cpu3: MSR_IA32_THERM_STATUS: 0x88490000 (27 C +/- 1)
-    Core     CPU Avg_MHz   %Busy Bzy_MHz TSC_MHz     SMI  CPU%c1  CPU%c3  CPU%c6  CPU%c7 CoreTmp  PkgTmp PkgWatt CorWatt GFXWatt
+    Core     CPU Avg_MHz   Busy% Bzy_MHz TSC_MHz     SMI  CPU%c1  CPU%c3  CPU%c6  CPU%c7 CoreTmp  PkgTmp PkgWatt CorWatt GFXWatt
        -       -     493   12.64    3898    3498       0   12.64    0.00    0.00   74.72      47      47   21.62   13.74    0.00
        0       0       4    0.11    3894    3498       0   99.89    0.00    0.00    0.00      47      47   21.62   13.74    0.00
        0       4    3897   99.98    3898    3498       0    0.02
@@ -171,14 +175,16 @@ The --debug option adds additional columns to the measurement ouput, including C
 See the field definitions above.
 .SH FORK EXAMPLE
 If turbostat is invoked with a command, it will fork that command
-and output the statistics gathered when the command exits.
+and output the statistics gathered after the command exits.
+In this case, turbostat output goes to stderr, by default.
+Output can instead be saved to a file using the --out option.
 eg. Here a cycle soaker is run on 1 CPU (see %c0) for a few seconds
 until ^C while the other CPUs are mostly idle:
 
 .nf
 root@hsw: turbostat cat /dev/zero > /dev/null
 ^C
-     CPU Avg_MHz   %Busy Bzy_MHz TSC_MHz
+     CPU Avg_MHz   Busy% Bzy_MHz TSC_MHz
        -     482   12.51    3854    3498
        0       0    0.01    1960    3498
        4       0    0.00    2128    3498
@@ -192,12 +198,12 @@ root@hsw: turbostat cat /dev/zero > /dev/null
 
 .fi
 Above the cycle soaker drives cpu5 up its 3.9 GHz turbo limit.
-The first row shows the average MHz and %Busy across all the processors in the system.
+The first row shows the average MHz and Busy% across all the processors in the system.
 
 Note that the Avg_MHz column reflects the total number of cycles executed
-divided by the measurement interval.  If the %Busy column is 100%,
+divided by the measurement interval.  If the Busy% column is 100%,
 then the processor was running at that speed the entire interval.
-The Avg_MHz multiplied by the %Busy results in the Bzy_MHz --
+The Avg_MHz multiplied by the Busy% results in the Bzy_MHz --
 which is the average frequency while the processor was executing --
 not including any non-busy idle time.
 
@@ -233,7 +239,7 @@ in the brand string in /proc/cpuinfo.  On a system where
 the TSC stops in idle, TSC_MHz will drop
 below the processor's base frequency.
 
-%Busy = MPERF_delta/TSC_delta
+Busy% = MPERF_delta/TSC_delta
 
 Bzy_MHz = TSC_delta/APERF_delta/MPERF_delta/measurement_interval
 
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 0dac7e05a..acbf7ff2e 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -38,12 +38,15 @@
 #include <string.h>
 #include <ctype.h>
 #include <sched.h>
+#include <time.h>
 #include <cpuid.h>
 #include <linux/capability.h>
 #include <errno.h>
 
 char *proc_stat = "/proc/stat";
-unsigned int interval_sec = 5;
+FILE *outf;
+int *fd_percpu;
+struct timespec interval_ts = {5, 0};
 unsigned int debug;
 unsigned int rapl_joules;
 unsigned int summary_only;
@@ -63,6 +66,8 @@ unsigned int do_slm_cstates;
 unsigned int use_c1_residency_msr;
 unsigned int has_aperf;
 unsigned int has_epb;
+unsigned int do_irtl_snb;
+unsigned int do_irtl_hsw;
 unsigned int units = 1000000;	/* MHz etc */
 unsigned int genuine_intel;
 unsigned int has_invariant_tsc;
@@ -72,6 +77,7 @@ unsigned int extra_msr_offset64;
 unsigned int extra_delta_offset32;
 unsigned int extra_delta_offset64;
 unsigned int aperf_mperf_multiplier = 1;
+int do_irq = 1;
 int do_smi;
 double bclk;
 double base_hz;
@@ -86,6 +92,10 @@ char *output_buffer, *outp;
 unsigned int do_rapl;
 unsigned int do_dts;
 unsigned int do_ptm;
+unsigned int do_gfx_rc6_ms;
+unsigned long long  gfx_cur_rc6_ms;
+unsigned int do_gfx_mhz;
+unsigned int gfx_cur_mhz;
 unsigned int tcc_activation_temp;
 unsigned int tcc_activation_temp_override;
 double rapl_power_units, rapl_time_units;
@@ -98,6 +108,12 @@ unsigned int crystal_hz;
 unsigned long long tsc_hz;
 int base_cpu;
 double discover_bclk(unsigned int family, unsigned int model);
+unsigned int has_hwp;	/* IA32_PM_ENABLE, IA32_HWP_CAPABILITIES */
+			/* IA32_HWP_REQUEST, IA32_HWP_STATUS */
+unsigned int has_hwp_notify;		/* IA32_HWP_INTERRUPT */
+unsigned int has_hwp_activity_window;	/* IA32_HWP_REQUEST[bits 41:32] */
+unsigned int has_hwp_epp;		/* IA32_HWP_REQUEST[bits 31:24] */
+unsigned int has_hwp_pkg;		/* IA32_HWP_REQUEST_PKG */
 
 #define RAPL_PKG		(1 << 0)
 					/* 0x610 MSR_PKG_POWER_LIMIT */
@@ -145,6 +161,7 @@ struct thread_data {
 	unsigned long long extra_delta64;
 	unsigned long long extra_msr32;
 	unsigned long long extra_delta32;
+	unsigned int irq_count;
 	unsigned int smi_count;
 	unsigned int cpu_id;
 	unsigned int flags;
@@ -172,6 +189,8 @@ struct pkg_data {
 	unsigned long long pkg_any_core_c0;
 	unsigned long long pkg_any_gfxe_c0;
 	unsigned long long pkg_both_core_gfxe_c0;
+	long long gfx_rc6_ms;
+	unsigned int gfx_mhz;
 	unsigned int package_id;
 	unsigned int energy_pkg;	/* MSR_PKG_ENERGY_STATUS */
 	unsigned int energy_dram;	/* MSR_DRAM_ENERGY_STATUS */
@@ -212,6 +231,9 @@ struct topo_params {
 
 struct timeval tv_even, tv_odd, tv_delta;
 
+int *irq_column_2_cpu;	/* /proc/interrupts column numbers */
+int *irqs_per_cpu;		/* indexed by cpu_num */
+
 void setup_all_buffers(void);
 
 int cpu_is_not_present(int cpu)
@@ -262,23 +284,34 @@ int cpu_migrate(int cpu)
 	else
 		return 0;
 }
-
-int get_msr(int cpu, off_t offset, unsigned long long *msr)
+int get_msr_fd(int cpu)
 {
-	ssize_t retval;
 	char pathname[32];
 	int fd;
 
+	fd = fd_percpu[cpu];
+
+	if (fd)
+		return fd;
+
 	sprintf(pathname, "/dev/cpu/%d/msr", cpu);
 	fd = open(pathname, O_RDONLY);
 	if (fd < 0)
 		err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, or run as root", pathname);
 
-	retval = pread(fd, msr, sizeof *msr, offset);
-	close(fd);
+	fd_percpu[cpu] = fd;
+
+	return fd;
+}
+
+int get_msr(int cpu, off_t offset, unsigned long long *msr)
+{
+	ssize_t retval;
+
+	retval = pread(get_msr_fd(cpu), msr, sizeof(*msr), offset);
 
 	if (retval != sizeof *msr)
-		err(-1, "%s offset 0x%llx read failed", pathname, (unsigned long long)offset);
+		err(-1, "msr %d offset 0x%llx read failed", cpu, (unsigned long long)offset);
 
 	return 0;
 }
@@ -286,8 +319,8 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
 /*
  * Example Format w/ field column widths:
  *
- *  Package    Core     CPU Avg_MHz Bzy_MHz TSC_MHz     SMI   %Busy CPU_%c1 CPU_%c3 CPU_%c6 CPU_%c7 CoreTmp  PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt
- * 123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678
+ *  Package    Core     CPU Avg_MHz Bzy_MHz TSC_MHz     IRQ   SMI   Busy% CPU_%c1 CPU_%c3 CPU_%c6 CPU_%c7 CoreTmp  PkgTmp  GFXMHz Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt
+ * 12345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678
  */
 
 void print_header(void)
@@ -301,7 +334,7 @@ void print_header(void)
 	if (has_aperf)
 		outp += sprintf(outp, " Avg_MHz");
 	if (has_aperf)
-		outp += sprintf(outp, "   %%Busy");
+		outp += sprintf(outp, "   Busy%%");
 	if (has_aperf)
 		outp += sprintf(outp, " Bzy_MHz");
 	outp += sprintf(outp, " TSC_MHz");
@@ -318,6 +351,8 @@ void print_header(void)
 	if (!debug)
 		goto done;
 
+	if (do_irq)
+		outp += sprintf(outp, "     IRQ");
 	if (do_smi)
 		outp += sprintf(outp, "     SMI");
 
@@ -335,6 +370,12 @@ void print_header(void)
 	if (do_ptm)
 		outp += sprintf(outp, "  PkgTmp");
 
+	if (do_gfx_rc6_ms)
+		outp += sprintf(outp, " GFX%%rc6");
+
+	if (do_gfx_mhz)
+		outp += sprintf(outp, "  GFXMHz");
+
 	if (do_skl_residency) {
 		outp += sprintf(outp, " Totl%%C0");
 		outp += sprintf(outp, "  Any%%C0");
@@ -409,6 +450,8 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 			extra_msr_offset32, t->extra_msr32);
 		outp += sprintf(outp, "msr0x%x: %016llX\n",
 			extra_msr_offset64, t->extra_msr64);
+		if (do_irq)
+			outp += sprintf(outp, "IRQ: %08X\n", t->irq_count);
 		if (do_smi)
 			outp += sprintf(outp, "SMI: %08X\n", t->smi_count);
 	}
@@ -504,7 +547,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "%8.0f",
 			1.0 / units * t->aperf / interval_float);
 
-	/* %Busy */
+	/* Busy% */
 	if (has_aperf) {
 		if (!skip_c0)
 			outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc/tsc_tweak);
@@ -542,6 +585,10 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (!debug)
 		goto done;
 
+	/* IRQ */
+	if (do_irq)
+		outp += sprintf(outp, "%8d", t->irq_count);
+
 	/* SMI */
 	if (do_smi)
 		outp += sprintf(outp, "%8d", t->smi_count);
@@ -575,6 +622,20 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (do_ptm)
 		outp += sprintf(outp, "%8d", p->pkg_temp_c);
 
+	/* GFXrc6 */
+	if (do_gfx_rc6_ms) {
+		if (p->gfx_rc6_ms == -1) {	/* detect counter reset */
+			outp += sprintf(outp, "  ***.**");
+		} else {
+			outp += sprintf(outp, "%8.2f",
+				p->gfx_rc6_ms / 10.0 / interval_float);
+		}
+	}
+
+	/* GFXMHz */
+	if (do_gfx_mhz)
+		outp += sprintf(outp, "%8d", p->gfx_mhz);
+
 	/* Totl%C0, Any%C0 GFX%C0 CPUGFX% */
 	if (do_skl_residency) {
 		outp += sprintf(outp, "%8.2f", 100.0 * p->pkg_wtd_core_c0/t->tsc);
@@ -645,15 +706,24 @@ done:
 	return 0;
 }
 
-void flush_stdout()
+void flush_output_stdout(void)
 {
-	fputs(output_buffer, stdout);
-	fflush(stdout);
+	FILE *filep;
+
+	if (outf == stderr)
+		filep = stdout;
+	else
+		filep = outf;
+
+	fputs(output_buffer, filep);
+	fflush(filep);
+
 	outp = output_buffer;
 }
-void flush_stderr()
+void flush_output_stderr(void)
 {
-	fputs(output_buffer, stderr);
+	fputs(output_buffer, outf);
+	fflush(outf);
 	outp = output_buffer;
 }
 void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
@@ -704,6 +774,14 @@ delta_package(struct pkg_data *new, struct pkg_data *old)
 	old->pc10 = new->pc10 - old->pc10;
 	old->pkg_temp_c = new->pkg_temp_c;
 
+	/* flag an error when rc6 counter resets/wraps */
+	if (old->gfx_rc6_ms >  new->gfx_rc6_ms)
+		old->gfx_rc6_ms = -1;
+	else
+		old->gfx_rc6_ms = new->gfx_rc6_ms - old->gfx_rc6_ms;
+
+	old->gfx_mhz = new->gfx_mhz;
+
 	DELTA_WRAP32(new->energy_pkg, old->energy_pkg);
 	DELTA_WRAP32(new->energy_cores, old->energy_cores);
 	DELTA_WRAP32(new->energy_gfx, old->energy_gfx);
@@ -745,9 +823,9 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 		} else {
 
 			if (!aperf_mperf_unstable) {
-				fprintf(stderr, "%s: APERF or MPERF went backwards *\n", progname);
-				fprintf(stderr, "* Frequency results do not cover entire interval *\n");
-				fprintf(stderr, "* fix this by running Linux-2.6.30 or later *\n");
+				fprintf(outf, "%s: APERF or MPERF went backwards *\n", progname);
+				fprintf(outf, "* Frequency results do not cover entire interval *\n");
+				fprintf(outf, "* fix this by running Linux-2.6.30 or later *\n");
 
 				aperf_mperf_unstable = 1;
 			}
@@ -782,7 +860,8 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 	}
 
 	if (old->mperf == 0) {
-		if (debug > 1) fprintf(stderr, "cpu%d MPERF 0!\n", old->cpu_id);
+		if (debug > 1)
+			fprintf(outf, "cpu%d MPERF 0!\n", old->cpu_id);
 		old->mperf = 1;	/* divide by 0 protection */
 	}
 
@@ -797,6 +876,9 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 	old->extra_msr32 = new->extra_msr32;
 	old->extra_msr64 = new->extra_msr64;
 
+	if (do_irq)
+		old->irq_count = new->irq_count - old->irq_count;
+
 	if (do_smi)
 		old->smi_count = new->smi_count - old->smi_count;
 }
@@ -826,10 +908,12 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	t->mperf = 0;
 	t->c1 = 0;
 
-	t->smi_count = 0;
 	t->extra_delta32 = 0;
 	t->extra_delta64 = 0;
 
+	t->irq_count = 0;
+	t->smi_count = 0;
+
 	/* tells format_counters to dump all fields from this set */
 	t->flags = CPU_IS_FIRST_THREAD_IN_CORE | CPU_IS_FIRST_CORE_IN_PACKAGE;
 
@@ -861,6 +945,9 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	p->rapl_pkg_perf_status = 0;
 	p->rapl_dram_perf_status = 0;
 	p->pkg_temp_c = 0;
+
+	p->gfx_rc6_ms = 0;
+	p->gfx_mhz = 0;
 }
 int sum_counters(struct thread_data *t, struct core_data *c,
 	struct pkg_data *p)
@@ -873,6 +960,9 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 	average.threads.extra_delta32 += t->extra_delta32;
 	average.threads.extra_delta64 += t->extra_delta64;
 
+	average.threads.irq_count += t->irq_count;
+	average.threads.smi_count += t->smi_count;
+
 	/* sum per-core values only for 1st thread in core */
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		return 0;
@@ -910,6 +1000,9 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 	average.packages.energy_cores += p->energy_cores;
 	average.packages.energy_gfx += p->energy_gfx;
 
+	average.packages.gfx_rc6_ms = p->gfx_rc6_ms;
+	average.packages.gfx_mhz = p->gfx_mhz;
+
 	average.packages.pkg_temp_c = MAX(average.packages.pkg_temp_c, p->pkg_temp_c);
 
 	average.packages.rapl_pkg_perf_status += p->rapl_pkg_perf_status;
@@ -970,7 +1063,6 @@ static unsigned long long rdtsc(void)
 	return low | ((unsigned long long)high) << 32;
 }
 
-
 /*
  * get_counters(...)
  * migrate to cpu
@@ -980,23 +1072,74 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 {
 	int cpu = t->cpu_id;
 	unsigned long long msr;
+	int aperf_mperf_retry_count = 0;
 
 	if (cpu_migrate(cpu)) {
-		fprintf(stderr, "Could not migrate to CPU %d\n", cpu);
+		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
 		return -1;
 	}
 
+retry:
 	t->tsc = rdtsc();	/* we are running on local CPU of interest */
 
 	if (has_aperf) {
+		unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time;
+
+		/*
+		 * The TSC, APERF and MPERF must be read together for
+		 * APERF/MPERF and MPERF/TSC to give accurate results.
+		 *
+		 * Unfortunately, APERF and MPERF are read by
+		 * individual system call, so delays may occur
+		 * between them.  If the time to read them
+		 * varies by a large amount, we re-read them.
+		 */
+
+		/*
+		 * This initial dummy APERF read has been seen to
+		 * reduce jitter in the subsequent reads.
+		 */
+
+		if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
+			return -3;
+
+		t->tsc = rdtsc();	/* re-read close to APERF */
+
+		tsc_before = t->tsc;
+
 		if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
 			return -3;
+
+		tsc_between = rdtsc();
+
 		if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf))
 			return -4;
+
+		tsc_after = rdtsc();
+
+		aperf_time = tsc_between - tsc_before;
+		mperf_time = tsc_after - tsc_between;
+
+		/*
+		 * If the system call latency to read APERF and MPERF
+		 * differ by more than 2x, then try again.
+		 */
+		if ((aperf_time > (2 * mperf_time)) || (mperf_time > (2 * aperf_time))) {
+			aperf_mperf_retry_count++;
+			if (aperf_mperf_retry_count < 5)
+				goto retry;
+			else
+				warnx("cpu%d jitter %lld %lld",
+					cpu, aperf_time, mperf_time);
+		}
+		aperf_mperf_retry_count = 0;
+
 		t->aperf = t->aperf * aperf_mperf_multiplier;
 		t->mperf = t->mperf * aperf_mperf_multiplier;
 	}
 
+	if (do_irq)
+		t->irq_count = irqs_per_cpu[cpu];
 	if (do_smi) {
 		if (get_msr(cpu, MSR_SMI_COUNT, &msr))
 			return -5;
@@ -1124,6 +1267,13 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			return -17;
 		p->pkg_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F);
 	}
+
+	if (do_gfx_rc6_ms)
+		p->gfx_rc6_ms = gfx_cur_rc6_ms;
+
+	if (do_gfx_mhz)
+		p->gfx_mhz = gfx_cur_mhz;
+
 	return 0;
 }
 
@@ -1159,6 +1309,7 @@ int hsw_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL__3, PCL__6, PCL__7, PCL_7S,
 int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int amt_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
+int bxt_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 
 
 static void
@@ -1175,18 +1326,18 @@ dump_nhm_platform_info(void)
 
 	get_msr(base_cpu, MSR_PLATFORM_INFO, &msr);
 
-	fprintf(stderr, "cpu%d: MSR_PLATFORM_INFO: 0x%08llx\n", base_cpu, msr);
+	fprintf(outf, "cpu%d: MSR_PLATFORM_INFO: 0x%08llx\n", base_cpu, msr);
 
 	ratio = (msr >> 40) & 0xFF;
-	fprintf(stderr, "%d * %.0f = %.0f MHz max efficiency frequency\n",
+	fprintf(outf, "%d * %.0f = %.0f MHz max efficiency frequency\n",
 		ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 8) & 0xFF;
-	fprintf(stderr, "%d * %.0f = %.0f MHz base frequency\n",
+	fprintf(outf, "%d * %.0f = %.0f MHz base frequency\n",
 		ratio, bclk, ratio * bclk);
 
 	get_msr(base_cpu, MSR_IA32_POWER_CTL, &msr);
-	fprintf(stderr, "cpu%d: MSR_IA32_POWER_CTL: 0x%08llx (C1E auto-promotion: %sabled)\n",
+	fprintf(outf, "cpu%d: MSR_IA32_POWER_CTL: 0x%08llx (C1E auto-promotion: %sabled)\n",
 		base_cpu, msr, msr & 0x2 ? "EN" : "DIS");
 
 	return;
@@ -1200,16 +1351,16 @@ dump_hsw_turbo_ratio_limits(void)
 
 	get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT2, &msr);
 
-	fprintf(stderr, "cpu%d: MSR_TURBO_RATIO_LIMIT2: 0x%08llx\n", base_cpu, msr);
+	fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT2: 0x%08llx\n", base_cpu, msr);
 
 	ratio = (msr >> 8) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 18 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 18 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 0) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 17 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 17 active cores\n",
 			ratio, bclk, ratio * bclk);
 	return;
 }
@@ -1222,46 +1373,46 @@ dump_ivt_turbo_ratio_limits(void)
 
 	get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT1, &msr);
 
-	fprintf(stderr, "cpu%d: MSR_TURBO_RATIO_LIMIT1: 0x%08llx\n", base_cpu, msr);
+	fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT1: 0x%08llx\n", base_cpu, msr);
 
 	ratio = (msr >> 56) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 16 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 16 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 48) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 15 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 15 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 40) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 14 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 14 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 32) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 13 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 13 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 24) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 12 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 12 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 16) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 11 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 11 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 8) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 10 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 10 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 0) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 9 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 9 active cores\n",
 			ratio, bclk, ratio * bclk);
 	return;
 }
@@ -1274,46 +1425,46 @@ dump_nhm_turbo_ratio_limits(void)
 
 	get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT, &msr);
 
-	fprintf(stderr, "cpu%d: MSR_TURBO_RATIO_LIMIT: 0x%08llx\n", base_cpu, msr);
+	fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT: 0x%08llx\n", base_cpu, msr);
 
 	ratio = (msr >> 56) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 8 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 8 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 48) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 7 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 7 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 40) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 6 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 6 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 32) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 5 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 5 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 24) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 4 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 4 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 16) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 3 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 3 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 8) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 2 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 2 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 0) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 1 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 1 active cores\n",
 			ratio, bclk, ratio * bclk);
 	return;
 }
@@ -1321,21 +1472,23 @@ dump_nhm_turbo_ratio_limits(void)
 static void
 dump_knl_turbo_ratio_limits(void)
 {
-	int cores;
-	unsigned int ratio;
+	const unsigned int buckets_no = 7;
+
 	unsigned long long msr;
-	int delta_cores;
-	int delta_ratio;
-	int i;
+	int delta_cores, delta_ratio;
+	int i, b_nr;
+	unsigned int cores[buckets_no];
+	unsigned int ratio[buckets_no];
 
 	get_msr(base_cpu, MSR_NHM_TURBO_RATIO_LIMIT, &msr);
 
-	fprintf(stderr, "cpu%d: MSR_NHM_TURBO_RATIO_LIMIT: 0x%08llx\n",
+	fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT: 0x%08llx\n",
 		base_cpu, msr);
 
 	/**
 	 * Turbo encoding in KNL is as follows:
-	 * [7:0] -- Base value of number of active cores of bucket 1.
+	 * [0] -- Reserved
+	 * [7:1] -- Base value of number of active cores of bucket 1.
 	 * [15:8] -- Base value of freq ratio of bucket 1.
 	 * [20:16] -- +ve delta of number of active cores of bucket 2.
 	 * i.e. active cores of bucket 2 =
@@ -1354,29 +1507,25 @@ dump_knl_turbo_ratio_limits(void)
 	 * [60:56]-- +ve delta of number of active cores of bucket 7.
 	 * [63:61]-- -ve delta of freq ratio of bucket 7.
 	 */
-	cores = msr & 0xFF;
-	ratio = (msr >> 8) && 0xFF;
-	if (ratio > 0)
-		fprintf(stderr,
-			"%d * %.0f = %.0f MHz max turbo %d active cores\n",
-			ratio, bclk, ratio * bclk, cores);
-
-	for (i = 16; i < 64; i = i + 8) {
+
+	b_nr = 0;
+	cores[b_nr] = (msr & 0xFF) >> 1;
+	ratio[b_nr] = (msr >> 8) & 0xFF;
+
+	for (i = 16; i < 64; i += 8) {
 		delta_cores = (msr >> i) & 0x1F;
-		delta_ratio = (msr >> (i + 5)) && 0x7;
-		if (!delta_cores || !delta_ratio)
-			return;
-		cores = cores + delta_cores;
-		ratio = ratio - delta_ratio;
-
-		/** -ve ratios will make successive ratio calculations
-		 * negative. Hence return instead of carrying on.
-		 */
-		if (ratio > 0)
-			fprintf(stderr,
-				"%d * %.0f = %.0f MHz max turbo %d active cores\n",
-				ratio, bclk, ratio * bclk, cores);
+		delta_ratio = (msr >> (i + 5)) & 0x7;
+
+		cores[b_nr + 1] = cores[b_nr] + delta_cores;
+		ratio[b_nr + 1] = ratio[b_nr] - delta_ratio;
+		b_nr++;
 	}
+
+	for (i = buckets_no - 1; i >= 0; i--)
+		if (i > 0 ? ratio[i] != ratio[i - 1] : 1)
+			fprintf(outf,
+				"%d * %.0f = %.0f MHz max turbo %d active cores\n",
+				ratio[i], bclk, ratio[i] * bclk, cores[i]);
 }
 
 static void
@@ -1389,15 +1538,15 @@ dump_nhm_cst_cfg(void)
 #define SNB_C1_AUTO_UNDEMOTE              (1UL << 27)
 #define SNB_C3_AUTO_UNDEMOTE              (1UL << 28)
 
-	fprintf(stderr, "cpu%d: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x%08llx", base_cpu, msr);
+	fprintf(outf, "cpu%d: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x%08llx", base_cpu, msr);
 
-	fprintf(stderr, " (%s%s%s%s%slocked: pkg-cstate-limit=%d: %s)\n",
+	fprintf(outf, " (%s%s%s%s%slocked: pkg-cstate-limit=%d: %s)\n",
 		(msr & SNB_C3_AUTO_UNDEMOTE) ? "UNdemote-C3, " : "",
 		(msr & SNB_C1_AUTO_UNDEMOTE) ? "UNdemote-C1, " : "",
 		(msr & NHM_C3_AUTO_DEMOTE) ? "demote-C3, " : "",
 		(msr & NHM_C1_AUTO_DEMOTE) ? "demote-C1, " : "",
 		(msr & (1 << 15)) ? "" : "UN",
-		(unsigned int)msr & 7,
+		(unsigned int)msr & 0xF,
 		pkg_cstate_limit_strings[pkg_cstate_limit]);
 	return;
 }
@@ -1408,48 +1557,100 @@ dump_config_tdp(void)
 	unsigned long long msr;
 
 	get_msr(base_cpu, MSR_CONFIG_TDP_NOMINAL, &msr);
-	fprintf(stderr, "cpu%d: MSR_CONFIG_TDP_NOMINAL: 0x%08llx", base_cpu, msr);
-	fprintf(stderr, " (base_ratio=%d)\n", (unsigned int)msr & 0xEF);
+	fprintf(outf, "cpu%d: MSR_CONFIG_TDP_NOMINAL: 0x%08llx", base_cpu, msr);
+	fprintf(outf, " (base_ratio=%d)\n", (unsigned int)msr & 0xFF);
 
 	get_msr(base_cpu, MSR_CONFIG_TDP_LEVEL_1, &msr);
-	fprintf(stderr, "cpu%d: MSR_CONFIG_TDP_LEVEL_1: 0x%08llx (", base_cpu, msr);
+	fprintf(outf, "cpu%d: MSR_CONFIG_TDP_LEVEL_1: 0x%08llx (", base_cpu, msr);
 	if (msr) {
-		fprintf(stderr, "PKG_MIN_PWR_LVL1=%d ", (unsigned int)(msr >> 48) & 0xEFFF);
-		fprintf(stderr, "PKG_MAX_PWR_LVL1=%d ", (unsigned int)(msr >> 32) & 0xEFFF);
-		fprintf(stderr, "LVL1_RATIO=%d ", (unsigned int)(msr >> 16) & 0xEF);
-		fprintf(stderr, "PKG_TDP_LVL1=%d", (unsigned int)(msr) & 0xEFFF);
+		fprintf(outf, "PKG_MIN_PWR_LVL1=%d ", (unsigned int)(msr >> 48) & 0x7FFF);
+		fprintf(outf, "PKG_MAX_PWR_LVL1=%d ", (unsigned int)(msr >> 32) & 0x7FFF);
+		fprintf(outf, "LVL1_RATIO=%d ", (unsigned int)(msr >> 16) & 0xFF);
+		fprintf(outf, "PKG_TDP_LVL1=%d", (unsigned int)(msr) & 0x7FFF);
 	}
-	fprintf(stderr, ")\n");
+	fprintf(outf, ")\n");
 
 	get_msr(base_cpu, MSR_CONFIG_TDP_LEVEL_2, &msr);
-	fprintf(stderr, "cpu%d: MSR_CONFIG_TDP_LEVEL_2: 0x%08llx (", base_cpu, msr);
+	fprintf(outf, "cpu%d: MSR_CONFIG_TDP_LEVEL_2: 0x%08llx (", base_cpu, msr);
 	if (msr) {
-		fprintf(stderr, "PKG_MIN_PWR_LVL2=%d ", (unsigned int)(msr >> 48) & 0xEFFF);
-		fprintf(stderr, "PKG_MAX_PWR_LVL2=%d ", (unsigned int)(msr >> 32) & 0xEFFF);
-		fprintf(stderr, "LVL2_RATIO=%d ", (unsigned int)(msr >> 16) & 0xEF);
-		fprintf(stderr, "PKG_TDP_LVL2=%d", (unsigned int)(msr) & 0xEFFF);
+		fprintf(outf, "PKG_MIN_PWR_LVL2=%d ", (unsigned int)(msr >> 48) & 0x7FFF);
+		fprintf(outf, "PKG_MAX_PWR_LVL2=%d ", (unsigned int)(msr >> 32) & 0x7FFF);
+		fprintf(outf, "LVL2_RATIO=%d ", (unsigned int)(msr >> 16) & 0xFF);
+		fprintf(outf, "PKG_TDP_LVL2=%d", (unsigned int)(msr) & 0x7FFF);
 	}
-	fprintf(stderr, ")\n");
+	fprintf(outf, ")\n");
 
 	get_msr(base_cpu, MSR_CONFIG_TDP_CONTROL, &msr);
-	fprintf(stderr, "cpu%d: MSR_CONFIG_TDP_CONTROL: 0x%08llx (", base_cpu, msr);
+	fprintf(outf, "cpu%d: MSR_CONFIG_TDP_CONTROL: 0x%08llx (", base_cpu, msr);
 	if ((msr) & 0x3)
-		fprintf(stderr, "TDP_LEVEL=%d ", (unsigned int)(msr) & 0x3);
-	fprintf(stderr, " lock=%d", (unsigned int)(msr >> 31) & 1);
-	fprintf(stderr, ")\n");
-	
+		fprintf(outf, "TDP_LEVEL=%d ", (unsigned int)(msr) & 0x3);
+	fprintf(outf, " lock=%d", (unsigned int)(msr >> 31) & 1);
+	fprintf(outf, ")\n");
+
 	get_msr(base_cpu, MSR_TURBO_ACTIVATION_RATIO, &msr);
-	fprintf(stderr, "cpu%d: MSR_TURBO_ACTIVATION_RATIO: 0x%08llx (", base_cpu, msr);
-	fprintf(stderr, "MAX_NON_TURBO_RATIO=%d", (unsigned int)(msr) & 0x7F);
-	fprintf(stderr, " lock=%d", (unsigned int)(msr >> 31) & 1);
-	fprintf(stderr, ")\n");
+	fprintf(outf, "cpu%d: MSR_TURBO_ACTIVATION_RATIO: 0x%08llx (", base_cpu, msr);
+	fprintf(outf, "MAX_NON_TURBO_RATIO=%d", (unsigned int)(msr) & 0xFF);
+	fprintf(outf, " lock=%d", (unsigned int)(msr >> 31) & 1);
+	fprintf(outf, ")\n");
+}
+
+unsigned int irtl_time_units[] = {1, 32, 1024, 32768, 1048576, 33554432, 0, 0 };
+
+void print_irtl(void)
+{
+	unsigned long long msr;
+
+	get_msr(base_cpu, MSR_PKGC3_IRTL, &msr);
+	fprintf(outf, "cpu%d: MSR_PKGC3_IRTL: 0x%08llx (", base_cpu, msr);
+	fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+		(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+
+	get_msr(base_cpu, MSR_PKGC6_IRTL, &msr);
+	fprintf(outf, "cpu%d: MSR_PKGC6_IRTL: 0x%08llx (", base_cpu, msr);
+	fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+		(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+
+	get_msr(base_cpu, MSR_PKGC7_IRTL, &msr);
+	fprintf(outf, "cpu%d: MSR_PKGC7_IRTL: 0x%08llx (", base_cpu, msr);
+	fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+		(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+
+	if (!do_irtl_hsw)
+		return;
+
+	get_msr(base_cpu, MSR_PKGC8_IRTL, &msr);
+	fprintf(outf, "cpu%d: MSR_PKGC8_IRTL: 0x%08llx (", base_cpu, msr);
+	fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+		(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+
+	get_msr(base_cpu, MSR_PKGC9_IRTL, &msr);
+	fprintf(outf, "cpu%d: MSR_PKGC9_IRTL: 0x%08llx (", base_cpu, msr);
+	fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+		(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+
+	get_msr(base_cpu, MSR_PKGC10_IRTL, &msr);
+	fprintf(outf, "cpu%d: MSR_PKGC10_IRTL: 0x%08llx (", base_cpu, msr);
+	fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+		(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+
+}
+void free_fd_percpu(void)
+{
+	int i;
+
+	for (i = 0; i < topo.max_cpu_num; ++i) {
+		if (fd_percpu[i] != 0)
+			close(fd_percpu[i]);
+	}
+
+	free(fd_percpu);
 }
 
 void free_all_buffers(void)
 {
 	CPU_FREE(cpu_present_set);
 	cpu_present_set = NULL;
-	cpu_present_set = 0;
+	cpu_present_setsize = 0;
 
 	CPU_FREE(cpu_affinity_set);
 	cpu_affinity_set = NULL;
@@ -1474,6 +1675,11 @@ void free_all_buffers(void)
 	free(output_buffer);
 	output_buffer = NULL;
 	outp = NULL;
+
+	free_fd_percpu();
+
+	free(irq_column_2_cpu);
+	free(irqs_per_cpu);
 }
 
 /*
@@ -1481,7 +1687,7 @@ void free_all_buffers(void)
  */
 FILE *fopen_or_die(const char *path, const char *mode)
 {
-	FILE *filep = fopen(path, "r");
+	FILE *filep = fopen(path, mode);
 	if (!filep)
 		err(1, "%s: open failed", path);
 	return filep;
@@ -1696,6 +1902,136 @@ int mark_cpu_present(int cpu)
 	return 0;
 }
 
+/*
+ * snapshot_proc_interrupts()
+ *
+ * read and record summary of /proc/interrupts
+ *
+ * return 1 if config change requires a restart, else return 0
+ */
+int snapshot_proc_interrupts(void)
+{
+	static FILE *fp;
+	int column, retval;
+
+	if (fp == NULL)
+		fp = fopen_or_die("/proc/interrupts", "r");
+	else
+		rewind(fp);
+
+	/* read 1st line of /proc/interrupts to get cpu* name for each column */
+	for (column = 0; column < topo.num_cpus; ++column) {
+		int cpu_number;
+
+		retval = fscanf(fp, " CPU%d", &cpu_number);
+		if (retval != 1)
+			break;
+
+		if (cpu_number > topo.max_cpu_num) {
+			warn("/proc/interrupts: cpu%d: > %d", cpu_number, topo.max_cpu_num);
+			return 1;
+		}
+
+		irq_column_2_cpu[column] = cpu_number;
+		irqs_per_cpu[cpu_number] = 0;
+	}
+
+	/* read /proc/interrupt count lines and sum up irqs per cpu */
+	while (1) {
+		int column;
+		char buf[64];
+
+		retval = fscanf(fp, " %s:", buf);	/* flush irq# "N:" */
+		if (retval != 1)
+			break;
+
+		/* read the count per cpu */
+		for (column = 0; column < topo.num_cpus; ++column) {
+
+			int cpu_number, irq_count;
+
+			retval = fscanf(fp, " %d", &irq_count);
+			if (retval != 1)
+				break;
+
+			cpu_number = irq_column_2_cpu[column];
+			irqs_per_cpu[cpu_number] += irq_count;
+
+		}
+
+		while (getc(fp) != '\n')
+			;	/* flush interrupt description */
+
+	}
+	return 0;
+}
+/*
+ * snapshot_gfx_rc6_ms()
+ *
+ * record snapshot of
+ * /sys/class/drm/card0/power/rc6_residency_ms
+ *
+ * return 1 if config change requires a restart, else return 0
+ */
+int snapshot_gfx_rc6_ms(void)
+{
+	FILE *fp;
+	int retval;
+
+	fp = fopen_or_die("/sys/class/drm/card0/power/rc6_residency_ms", "r");
+
+	retval = fscanf(fp, "%lld", &gfx_cur_rc6_ms);
+	if (retval != 1)
+		err(1, "GFX rc6");
+
+	fclose(fp);
+
+	return 0;
+}
+/*
+ * snapshot_gfx_mhz()
+ *
+ * record snapshot of
+ * /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz
+ *
+ * return 1 if config change requires a restart, else return 0
+ */
+int snapshot_gfx_mhz(void)
+{
+	static FILE *fp;
+	int retval;
+
+	if (fp == NULL)
+		fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", "r");
+	else
+		rewind(fp);
+
+	retval = fscanf(fp, "%d", &gfx_cur_mhz);
+	if (retval != 1)
+		err(1, "GFX MHz");
+
+	return 0;
+}
+
+/*
+ * snapshot /proc and /sys files
+ *
+ * return 1 if configuration restart needed, else return 0
+ */
+int snapshot_proc_sysfs_files(void)
+{
+	if (snapshot_proc_interrupts())
+		return 1;
+
+	if (do_gfx_rc6_ms)
+		snapshot_gfx_rc6_ms();
+
+	if (do_gfx_mhz)
+		snapshot_gfx_mhz();
+
+	return 0;
+}
+
 void turbostat_loop()
 {
 	int retval;
@@ -1704,6 +2040,7 @@ void turbostat_loop()
 restart:
 	restarted++;
 
+	snapshot_proc_sysfs_files();
 	retval = for_all_cpus(get_counters, EVEN_COUNTERS);
 	if (retval < -1) {
 		exit(retval);
@@ -1722,7 +2059,9 @@ restart:
 			re_initialize();
 			goto restart;
 		}
-		sleep(interval_sec);
+		nanosleep(&interval_ts, NULL);
+		if (snapshot_proc_sysfs_files())
+			goto restart;
 		retval = for_all_cpus(get_counters, ODD_COUNTERS);
 		if (retval < -1) {
 			exit(retval);
@@ -1735,8 +2074,10 @@ restart:
 		for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS);
 		compute_average(EVEN_COUNTERS);
 		format_all_counters(EVEN_COUNTERS);
-		flush_stdout();
-		sleep(interval_sec);
+		flush_output_stdout();
+		nanosleep(&interval_ts, NULL);
+		if (snapshot_proc_sysfs_files())
+			goto restart;
 		retval = for_all_cpus(get_counters, EVEN_COUNTERS);
 		if (retval < -1) {
 			exit(retval);
@@ -1749,7 +2090,7 @@ restart:
 		for_all_cpus_2(delta_cpu, EVEN_COUNTERS, ODD_COUNTERS);
 		compute_average(ODD_COUNTERS);
 		format_all_counters(ODD_COUNTERS);
-		flush_stdout();
+		flush_output_stdout();
 	}
 }
 
@@ -1858,6 +2199,9 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 	case 0x56:	/* BDX-DE */
 	case 0x4E:	/* SKL */
 	case 0x5E:	/* SKL */
+	case 0x8E:	/* KBL */
+	case 0x9E:	/* KBL */
+	case 0x55:	/* SKX */
 		pkg_cstate_limits = hsw_pkg_cstate_limits;
 		break;
 	case 0x37:	/* BYT */
@@ -1870,6 +2214,9 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 	case 0x57:	/* PHI */
 		pkg_cstate_limits = phi_pkg_cstate_limits;
 		break;
+	case 0x5C:	/* BXT */
+		pkg_cstate_limits = bxt_pkg_cstate_limits;
+		break;
 	default:
 		return 0;
 	}
@@ -1889,6 +2236,7 @@ int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model)
 	/* Nehalem compatible, but do not include turbo-ratio limit support */
 	case 0x2E:	/* Nehalem-EX Xeon - Beckton */
 	case 0x2F:	/* Westmere-EX Xeon - Eagleton */
+	case 0x57:	/* PHI - Knights Landing (different MSR definition) */
 		return 0;
 	default:
 		return 1;
@@ -1961,6 +2309,9 @@ int has_config_tdp(unsigned int family, unsigned int model)
 	case 0x56:	/* BDX-DE */
 	case 0x4E:	/* SKL */
 	case 0x5E:	/* SKL */
+	case 0x8E:	/* KBL */
+	case 0x9E:	/* KBL */
+	case 0x55:	/* SKX */
 
 	case 0x57:	/* Knights Landing */
 		return 1;
@@ -1970,7 +2321,7 @@ int has_config_tdp(unsigned int family, unsigned int model)
 }
 
 static void
-dump_cstate_pstate_config_info(family, model)
+dump_cstate_pstate_config_info(unsigned int family, unsigned int model)
 {
 	if (!do_nhm_platform_info)
 		return;
@@ -2016,7 +2367,7 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		return 0;
 
 	if (cpu_migrate(cpu)) {
-		fprintf(stderr, "Could not migrate to CPU %d\n", cpu);
+		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
 		return -1;
 	}
 
@@ -2037,7 +2388,98 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		epb_string = "custom";
 		break;
 	}
-	fprintf(stderr, "cpu%d: MSR_IA32_ENERGY_PERF_BIAS: 0x%08llx (%s)\n", cpu, msr, epb_string);
+	fprintf(outf, "cpu%d: MSR_IA32_ENERGY_PERF_BIAS: 0x%08llx (%s)\n", cpu, msr, epb_string);
+
+	return 0;
+}
+/*
+ * print_hwp()
+ * Decode the MSR_HWP_CAPABILITIES
+ */
+int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+	unsigned long long msr;
+	int cpu;
+
+	if (!has_hwp)
+		return 0;
+
+	cpu = t->cpu_id;
+
+	/* MSR_HWP_CAPABILITIES is per-package */
+	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+		return 0;
+
+	if (cpu_migrate(cpu)) {
+		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
+		return -1;
+	}
+
+	if (get_msr(cpu, MSR_PM_ENABLE, &msr))
+		return 0;
+
+	fprintf(outf, "cpu%d: MSR_PM_ENABLE: 0x%08llx (%sHWP)\n",
+		cpu, msr, (msr & (1 << 0)) ? "" : "No-");
+
+	/* MSR_PM_ENABLE[1] == 1 if HWP is enabled and MSRs visible */
+	if ((msr & (1 << 0)) == 0)
+		return 0;
+
+	if (get_msr(cpu, MSR_HWP_CAPABILITIES, &msr))
+		return 0;
+
+	fprintf(outf, "cpu%d: MSR_HWP_CAPABILITIES: 0x%08llx "
+			"(high 0x%x guar 0x%x eff 0x%x low 0x%x)\n",
+			cpu, msr,
+			(unsigned int)HWP_HIGHEST_PERF(msr),
+			(unsigned int)HWP_GUARANTEED_PERF(msr),
+			(unsigned int)HWP_MOSTEFFICIENT_PERF(msr),
+			(unsigned int)HWP_LOWEST_PERF(msr));
+
+	if (get_msr(cpu, MSR_HWP_REQUEST, &msr))
+		return 0;
+
+	fprintf(outf, "cpu%d: MSR_HWP_REQUEST: 0x%08llx "
+			"(min 0x%x max 0x%x des 0x%x epp 0x%x window 0x%x pkg 0x%x)\n",
+			cpu, msr,
+			(unsigned int)(((msr) >> 0) & 0xff),
+			(unsigned int)(((msr) >> 8) & 0xff),
+			(unsigned int)(((msr) >> 16) & 0xff),
+			(unsigned int)(((msr) >> 24) & 0xff),
+			(unsigned int)(((msr) >> 32) & 0xff3),
+			(unsigned int)(((msr) >> 42) & 0x1));
+
+	if (has_hwp_pkg) {
+		if (get_msr(cpu, MSR_HWP_REQUEST_PKG, &msr))
+			return 0;
+
+		fprintf(outf, "cpu%d: MSR_HWP_REQUEST_PKG: 0x%08llx "
+			"(min 0x%x max 0x%x des 0x%x epp 0x%x window 0x%x)\n",
+			cpu, msr,
+			(unsigned int)(((msr) >> 0) & 0xff),
+			(unsigned int)(((msr) >> 8) & 0xff),
+			(unsigned int)(((msr) >> 16) & 0xff),
+			(unsigned int)(((msr) >> 24) & 0xff),
+			(unsigned int)(((msr) >> 32) & 0xff3));
+	}
+	if (has_hwp_notify) {
+		if (get_msr(cpu, MSR_HWP_INTERRUPT, &msr))
+			return 0;
+
+		fprintf(outf, "cpu%d: MSR_HWP_INTERRUPT: 0x%08llx "
+			"(%s_Guaranteed_Perf_Change, %s_Excursion_Min)\n",
+			cpu, msr,
+			((msr) & 0x1) ? "EN" : "Dis",
+			((msr) & 0x2) ? "EN" : "Dis");
+	}
+	if (get_msr(cpu, MSR_HWP_STATUS, &msr))
+		return 0;
+
+	fprintf(outf, "cpu%d: MSR_HWP_STATUS: 0x%08llx "
+			"(%sGuaranteed_Perf_Change, %sExcursion_Min)\n",
+			cpu, msr,
+			((msr) & 0x1) ? "" : "No-",
+			((msr) & 0x2) ? "" : "No-");
 
 	return 0;
 }
@@ -2057,14 +2499,14 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 		return 0;
 
 	if (cpu_migrate(cpu)) {
-		fprintf(stderr, "Could not migrate to CPU %d\n", cpu);
+		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
 		return -1;
 	}
 
 	if (do_core_perf_limit_reasons) {
 		get_msr(cpu, MSR_CORE_PERF_LIMIT_REASONS, &msr);
-		fprintf(stderr, "cpu%d: MSR_CORE_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
-		fprintf(stderr, " (Active: %s%s%s%s%s%s%s%s%s%s%s%s%s%s)",
+		fprintf(outf, "cpu%d: MSR_CORE_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
+		fprintf(outf, " (Active: %s%s%s%s%s%s%s%s%s%s%s%s%s%s)",
 			(msr & 1 << 15) ? "bit15, " : "",
 			(msr & 1 << 14) ? "bit14, " : "",
 			(msr & 1 << 13) ? "Transitions, " : "",
@@ -2079,7 +2521,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 			(msr & 1 << 2) ? "bit2, " : "",
 			(msr & 1 << 1) ? "ThermStatus, " : "",
 			(msr & 1 << 0) ? "PROCHOT, " : "");
-		fprintf(stderr, " (Logged: %s%s%s%s%s%s%s%s%s%s%s%s%s%s)\n",
+		fprintf(outf, " (Logged: %s%s%s%s%s%s%s%s%s%s%s%s%s%s)\n",
 			(msr & 1 << 31) ? "bit31, " : "",
 			(msr & 1 << 30) ? "bit30, " : "",
 			(msr & 1 << 29) ? "Transitions, " : "",
@@ -2098,8 +2540,8 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 	}
 	if (do_gfx_perf_limit_reasons) {
 		get_msr(cpu, MSR_GFX_PERF_LIMIT_REASONS, &msr);
-		fprintf(stderr, "cpu%d: MSR_GFX_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
-		fprintf(stderr, " (Active: %s%s%s%s%s%s%s%s)",
+		fprintf(outf, "cpu%d: MSR_GFX_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
+		fprintf(outf, " (Active: %s%s%s%s%s%s%s%s)",
 			(msr & 1 << 0) ? "PROCHOT, " : "",
 			(msr & 1 << 1) ? "ThermStatus, " : "",
 			(msr & 1 << 4) ? "Graphics, " : "",
@@ -2108,7 +2550,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 			(msr & 1 << 9) ? "GFXPwr, " : "",
 			(msr & 1 << 10) ? "PkgPwrL1, " : "",
 			(msr & 1 << 11) ? "PkgPwrL2, " : "");
-		fprintf(stderr, " (Logged: %s%s%s%s%s%s%s%s)\n",
+		fprintf(outf, " (Logged: %s%s%s%s%s%s%s%s)\n",
 			(msr & 1 << 16) ? "PROCHOT, " : "",
 			(msr & 1 << 17) ? "ThermStatus, " : "",
 			(msr & 1 << 20) ? "Graphics, " : "",
@@ -2120,15 +2562,15 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 	}
 	if (do_ring_perf_limit_reasons) {
 		get_msr(cpu, MSR_RING_PERF_LIMIT_REASONS, &msr);
-		fprintf(stderr, "cpu%d: MSR_RING_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
-		fprintf(stderr, " (Active: %s%s%s%s%s%s)",
+		fprintf(outf, "cpu%d: MSR_RING_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
+		fprintf(outf, " (Active: %s%s%s%s%s%s)",
 			(msr & 1 << 0) ? "PROCHOT, " : "",
 			(msr & 1 << 1) ? "ThermStatus, " : "",
 			(msr & 1 << 6) ? "VR-Therm, " : "",
 			(msr & 1 << 8) ? "Amps, " : "",
 			(msr & 1 << 10) ? "PkgPwrL1, " : "",
 			(msr & 1 << 11) ? "PkgPwrL2, " : "");
-		fprintf(stderr, " (Logged: %s%s%s%s%s%s)\n",
+		fprintf(outf, " (Logged: %s%s%s%s%s%s)\n",
 			(msr & 1 << 16) ? "PROCHOT, " : "",
 			(msr & 1 << 17) ? "ThermStatus, " : "",
 			(msr & 1 << 22) ? "VR-Therm, " : "",
@@ -2142,7 +2584,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 #define	RAPL_POWER_GRANULARITY	0x7FFF	/* 15 bit power granularity */
 #define	RAPL_TIME_GRANULARITY	0x3F /* 6 bit time granularity */
 
-double get_tdp(model)
+double get_tdp(unsigned int model)
 {
 	unsigned long long msr;
 
@@ -2207,13 +2649,19 @@ void rapl_probe(unsigned int family, unsigned int model)
 	case 0x47:	/* BDW */
 		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_GFX | RAPL_PKG_POWER_INFO;
 		break;
+	case 0x5C:	/* BXT */
+		do_rapl = RAPL_PKG | RAPL_PKG_POWER_INFO;
+		break;
 	case 0x4E:	/* SKL */
 	case 0x5E:	/* SKL */
+	case 0x8E:	/* KBL */
+	case 0x9E:	/* KBL */
 		do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
 		break;
 	case 0x3F:	/* HSX */
 	case 0x4F:	/* BDX */
 	case 0x56:	/* BDX-DE */
+	case 0x55:	/* SKX */
 	case 0x57:	/* KNL */
 		do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
 		break;
@@ -2251,12 +2699,12 @@ void rapl_probe(unsigned int family, unsigned int model)
 
 	rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
 	if (debug)
-		fprintf(stderr, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
+		fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
 
 	return;
 }
 
-void perf_limit_reasons_probe(family, model)
+void perf_limit_reasons_probe(unsigned int family, unsigned int model)
 {
 	if (!genuine_intel)
 		return;
@@ -2293,7 +2741,7 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
 		return 0;
 
 	if (cpu_migrate(cpu)) {
-		fprintf(stderr, "Could not migrate to CPU %d\n", cpu);
+		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
 		return -1;
 	}
 
@@ -2302,7 +2750,7 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
 			return 0;
 
 		dts = (msr >> 16) & 0x7F;
-		fprintf(stderr, "cpu%d: MSR_IA32_PACKAGE_THERM_STATUS: 0x%08llx (%d C)\n",
+		fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_STATUS: 0x%08llx (%d C)\n",
 			cpu, msr, tcc_activation_temp - dts);
 
 #ifdef	THERM_DEBUG
@@ -2311,7 +2759,7 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
 
 		dts = (msr >> 16) & 0x7F;
 		dts2 = (msr >> 8) & 0x7F;
-		fprintf(stderr, "cpu%d: MSR_IA32_PACKAGE_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
+		fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
 			cpu, msr, tcc_activation_temp - dts, tcc_activation_temp - dts2);
 #endif
 	}
@@ -2325,7 +2773,7 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
 
 		dts = (msr >> 16) & 0x7F;
 		resolution = (msr >> 27) & 0xF;
-		fprintf(stderr, "cpu%d: MSR_IA32_THERM_STATUS: 0x%08llx (%d C +/- %d)\n",
+		fprintf(outf, "cpu%d: MSR_IA32_THERM_STATUS: 0x%08llx (%d C +/- %d)\n",
 			cpu, msr, tcc_activation_temp - dts, resolution);
 
 #ifdef THERM_DEBUG
@@ -2334,17 +2782,17 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
 
 		dts = (msr >> 16) & 0x7F;
 		dts2 = (msr >> 8) & 0x7F;
-		fprintf(stderr, "cpu%d: MSR_IA32_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
+		fprintf(outf, "cpu%d: MSR_IA32_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
 			cpu, msr, tcc_activation_temp - dts, tcc_activation_temp - dts2);
 #endif
 	}
 
 	return 0;
 }
-	
+
 void print_power_limit_msr(int cpu, unsigned long long msr, char *label)
 {
-	fprintf(stderr, "cpu%d: %s: %sabled (%f Watts, %f sec, clamp %sabled)\n",
+	fprintf(outf, "cpu%d: %s: %sabled (%f Watts, %f sec, clamp %sabled)\n",
 		cpu, label,
 		((msr >> 15) & 1) ? "EN" : "DIS",
 		((msr >> 0) & 0x7FFF) * rapl_power_units,
@@ -2368,7 +2816,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 
 	cpu = t->cpu_id;
 	if (cpu_migrate(cpu)) {
-		fprintf(stderr, "Could not migrate to CPU %d\n", cpu);
+		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
 		return -1;
 	}
 
@@ -2376,7 +2824,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		return -1;
 
 	if (debug) {
-		fprintf(stderr, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx "
+		fprintf(outf, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx "
 			"(%f Watts, %f Joules, %f sec.)\n", cpu, msr,
 			rapl_power_units, rapl_energy_units, rapl_time_units);
 	}
@@ -2386,7 +2834,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
                 	return -5;
 
 
-		fprintf(stderr, "cpu%d: MSR_PKG_POWER_INFO: 0x%08llx (%.0f W TDP, RAPL %.0f - %.0f W, %f sec.)\n",
+		fprintf(outf, "cpu%d: MSR_PKG_POWER_INFO: 0x%08llx (%.0f W TDP, RAPL %.0f - %.0f W, %f sec.)\n",
 			cpu, msr,
 			((msr >>  0) & RAPL_POWER_GRANULARITY) * rapl_power_units,
 			((msr >> 16) & RAPL_POWER_GRANULARITY) * rapl_power_units,
@@ -2399,11 +2847,11 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		if (get_msr(cpu, MSR_PKG_POWER_LIMIT, &msr))
 			return -9;
 
-		fprintf(stderr, "cpu%d: MSR_PKG_POWER_LIMIT: 0x%08llx (%slocked)\n",
+		fprintf(outf, "cpu%d: MSR_PKG_POWER_LIMIT: 0x%08llx (%slocked)\n",
 			cpu, msr, (msr >> 63) & 1 ? "": "UN");
 
 		print_power_limit_msr(cpu, msr, "PKG Limit #1");
-		fprintf(stderr, "cpu%d: PKG Limit #2: %sabled (%f Watts, %f* sec, clamp %sabled)\n",
+		fprintf(outf, "cpu%d: PKG Limit #2: %sabled (%f Watts, %f* sec, clamp %sabled)\n",
 			cpu,
 			((msr >> 47) & 1) ? "EN" : "DIS",
 			((msr >> 32) & 0x7FFF) * rapl_power_units,
@@ -2415,7 +2863,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		if (get_msr(cpu, MSR_DRAM_POWER_INFO, &msr))
                 	return -6;
 
-		fprintf(stderr, "cpu%d: MSR_DRAM_POWER_INFO,: 0x%08llx (%.0f W TDP, RAPL %.0f - %.0f W, %f sec.)\n",
+		fprintf(outf, "cpu%d: MSR_DRAM_POWER_INFO,: 0x%08llx (%.0f W TDP, RAPL %.0f - %.0f W, %f sec.)\n",
 			cpu, msr,
 			((msr >>  0) & RAPL_POWER_GRANULARITY) * rapl_power_units,
 			((msr >> 16) & RAPL_POWER_GRANULARITY) * rapl_power_units,
@@ -2425,7 +2873,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	if (do_rapl & RAPL_DRAM) {
 		if (get_msr(cpu, MSR_DRAM_POWER_LIMIT, &msr))
 			return -9;
-		fprintf(stderr, "cpu%d: MSR_DRAM_POWER_LIMIT: 0x%08llx (%slocked)\n",
+		fprintf(outf, "cpu%d: MSR_DRAM_POWER_LIMIT: 0x%08llx (%slocked)\n",
 				cpu, msr, (msr >> 31) & 1 ? "": "UN");
 
 		print_power_limit_msr(cpu, msr, "DRAM Limit");
@@ -2435,7 +2883,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			if (get_msr(cpu, MSR_PP0_POLICY, &msr))
 				return -7;
 
-			fprintf(stderr, "cpu%d: MSR_PP0_POLICY: %lld\n", cpu, msr & 0xF);
+			fprintf(outf, "cpu%d: MSR_PP0_POLICY: %lld\n", cpu, msr & 0xF);
 		}
 	}
 	if (do_rapl & RAPL_CORES) {
@@ -2443,7 +2891,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 
 			if (get_msr(cpu, MSR_PP0_POWER_LIMIT, &msr))
 				return -9;
-			fprintf(stderr, "cpu%d: MSR_PP0_POWER_LIMIT: 0x%08llx (%slocked)\n",
+			fprintf(outf, "cpu%d: MSR_PP0_POWER_LIMIT: 0x%08llx (%slocked)\n",
 					cpu, msr, (msr >> 31) & 1 ? "": "UN");
 			print_power_limit_msr(cpu, msr, "Cores Limit");
 		}
@@ -2453,11 +2901,11 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			if (get_msr(cpu, MSR_PP1_POLICY, &msr))
 				return -8;
 
-			fprintf(stderr, "cpu%d: MSR_PP1_POLICY: %lld\n", cpu, msr & 0xF);
+			fprintf(outf, "cpu%d: MSR_PP1_POLICY: %lld\n", cpu, msr & 0xF);
 
 			if (get_msr(cpu, MSR_PP1_POWER_LIMIT, &msr))
 				return -9;
-			fprintf(stderr, "cpu%d: MSR_PP1_POWER_LIMIT: 0x%08llx (%slocked)\n",
+			fprintf(outf, "cpu%d: MSR_PP1_POWER_LIMIT: 0x%08llx (%slocked)\n",
 					cpu, msr, (msr >> 31) & 1 ? "": "UN");
 			print_power_limit_msr(cpu, msr, "GFX Limit");
 		}
@@ -2493,6 +2941,10 @@ int has_snb_msrs(unsigned int family, unsigned int model)
 	case 0x56:	/* BDX-DE */
 	case 0x4E:	/* SKL */
 	case 0x5E:	/* SKL */
+	case 0x8E:	/* KBL */
+	case 0x9E:	/* KBL */
+	case 0x55:	/* SKX */
+	case 0x5C:	/* BXT */
 		return 1;
 	}
 	return 0;
@@ -2501,9 +2953,14 @@ int has_snb_msrs(unsigned int family, unsigned int model)
 /*
  * HSW adds support for additional MSRs:
  *
- * MSR_PKG_C8_RESIDENCY            0x00000630
- * MSR_PKG_C9_RESIDENCY            0x00000631
- * MSR_PKG_C10_RESIDENCY           0x00000632
+ * MSR_PKG_C8_RESIDENCY		0x00000630
+ * MSR_PKG_C9_RESIDENCY		0x00000631
+ * MSR_PKG_C10_RESIDENCY	0x00000632
+ *
+ * MSR_PKGC8_IRTL		0x00000633
+ * MSR_PKGC9_IRTL		0x00000634
+ * MSR_PKGC10_IRTL		0x00000635
+ *
  */
 int has_hsw_msrs(unsigned int family, unsigned int model)
 {
@@ -2515,6 +2972,9 @@ int has_hsw_msrs(unsigned int family, unsigned int model)
 	case 0x3D:	/* BDW */
 	case 0x4E:	/* SKL */
 	case 0x5E:	/* SKL */
+	case 0x8E:	/* KBL */
+	case 0x9E:	/* KBL */
+	case 0x5C:	/* BXT */
 		return 1;
 	}
 	return 0;
@@ -2536,6 +2996,8 @@ int has_skl_msrs(unsigned int family, unsigned int model)
 	switch (model) {
 	case 0x4E:	/* SKL */
 	case 0x5E:	/* SKL */
+	case 0x8E:	/* KBL */
+	case 0x9E:	/* KBL */
 		return 1;
 	}
 	return 0;
@@ -2583,23 +3045,23 @@ double slm_bclk(void)
 	double freq;
 
 	if (get_msr(base_cpu, MSR_FSB_FREQ, &msr))
-		fprintf(stderr, "SLM BCLK: unknown\n");
+		fprintf(outf, "SLM BCLK: unknown\n");
 
 	i = msr & 0xf;
 	if (i >= SLM_BCLK_FREQS) {
-		fprintf(stderr, "SLM BCLK[%d] invalid\n", i);
+		fprintf(outf, "SLM BCLK[%d] invalid\n", i);
 		msr = 3;
 	}
 	freq = slm_freq_table[i];
 
-	fprintf(stderr, "SLM BCLK: %.1f Mhz\n", freq);
+	fprintf(outf, "SLM BCLK: %.1f Mhz\n", freq);
 
 	return freq;
 }
 
 double discover_bclk(unsigned int family, unsigned int model)
 {
-	if (has_snb_msrs(family, model))
+	if (has_snb_msrs(family, model) || is_knl(family, model))
 		return 100.00;
 	else if (is_slm(family, model))
 		return slm_bclk();
@@ -2635,13 +3097,13 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk
 
 	cpu = t->cpu_id;
 	if (cpu_migrate(cpu)) {
-		fprintf(stderr, "Could not migrate to CPU %d\n", cpu);
+		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
 		return -1;
 	}
 
 	if (tcc_activation_temp_override != 0) {
 		tcc_activation_temp = tcc_activation_temp_override;
-		fprintf(stderr, "cpu%d: Using cmdline TCC Target (%d C)\n",
+		fprintf(outf, "cpu%d: Using cmdline TCC Target (%d C)\n",
 			cpu, tcc_activation_temp);
 		return 0;
 	}
@@ -2656,7 +3118,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk
 	target_c_local = (msr >> 16) & 0xFF;
 
 	if (debug)
-		fprintf(stderr, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n",
+		fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n",
 			cpu, msr, target_c_local);
 
 	if (!target_c_local)
@@ -2668,37 +3130,93 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk
 
 guess:
 	tcc_activation_temp = TJMAX_DEFAULT;
-	fprintf(stderr, "cpu%d: Guessing tjMax %d C, Please use -T to specify\n",
+	fprintf(outf, "cpu%d: Guessing tjMax %d C, Please use -T to specify\n",
 		cpu, tcc_activation_temp);
 
 	return 0;
 }
+
+void decode_feature_control_msr(void)
+{
+	unsigned long long msr;
+
+	if (!get_msr(base_cpu, MSR_IA32_FEATURE_CONTROL, &msr))
+		fprintf(outf, "cpu%d: MSR_IA32_FEATURE_CONTROL: 0x%08llx (%sLocked %s)\n",
+			base_cpu, msr,
+			msr & FEATURE_CONTROL_LOCKED ? "" : "UN-",
+			msr & (1 << 18) ? "SGX" : "");
+}
+
+void decode_misc_enable_msr(void)
+{
+	unsigned long long msr;
+
+	if (!get_msr(base_cpu, MSR_IA32_MISC_ENABLE, &msr))
+		fprintf(outf, "cpu%d: MSR_IA32_MISC_ENABLE: 0x%08llx (%s %s %s)\n",
+			base_cpu, msr,
+			msr & (1 << 3) ? "TCC" : "",
+			msr & (1 << 16) ? "EIST" : "",
+			msr & (1 << 18) ? "MONITOR" : "");
+}
+
+/*
+ * Decode MSR_MISC_PWR_MGMT
+ *
+ * Decode the bits according to the Nehalem documentation
+ * bit[0] seems to continue to have same meaning going forward
+ * bit[1] less so...
+ */
+void decode_misc_pwr_mgmt_msr(void)
+{
+	unsigned long long msr;
+
+	if (!do_nhm_platform_info)
+		return;
+
+	if (!get_msr(base_cpu, MSR_MISC_PWR_MGMT, &msr))
+		fprintf(outf, "cpu%d: MSR_MISC_PWR_MGMT: 0x%08llx (%sable-EIST_Coordination %sable-EPB)\n",
+			base_cpu, msr,
+			msr & (1 << 0) ? "DIS" : "EN",
+			msr & (1 << 1) ? "EN" : "DIS");
+}
+
 void process_cpuid()
 {
-	unsigned int eax, ebx, ecx, edx, max_level;
+	unsigned int eax, ebx, ecx, edx, max_level, max_extended_level;
 	unsigned int fms, family, model, stepping;
 
 	eax = ebx = ecx = edx = 0;
 
-	__get_cpuid(0, &max_level, &ebx, &ecx, &edx);
+	__cpuid(0, max_level, ebx, ecx, edx);
 
 	if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e)
 		genuine_intel = 1;
 
 	if (debug)
-		fprintf(stderr, "CPUID(0): %.4s%.4s%.4s ",
+		fprintf(outf, "CPUID(0): %.4s%.4s%.4s ",
 			(char *)&ebx, (char *)&edx, (char *)&ecx);
 
-	__get_cpuid(1, &fms, &ebx, &ecx, &edx);
+	__cpuid(1, fms, ebx, ecx, edx);
 	family = (fms >> 8) & 0xf;
 	model = (fms >> 4) & 0xf;
 	stepping = fms & 0xf;
 	if (family == 6 || family == 0xf)
 		model += ((fms >> 16) & 0xf) << 4;
 
-	if (debug)
-		fprintf(stderr, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n",
+	if (debug) {
+		fprintf(outf, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n",
 			max_level, family, model, stepping, family, model, stepping);
+		fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s\n",
+			ecx & (1 << 0) ? "SSE3" : "-",
+			ecx & (1 << 3) ? "MONITOR" : "-",
+			ecx & (1 << 6) ? "SMX" : "-",
+			ecx & (1 << 7) ? "EIST" : "-",
+			ecx & (1 << 8) ? "TM2" : "-",
+			edx & (1 << 4) ? "TSC" : "-",
+			edx & (1 << 5) ? "MSR" : "-",
+			edx & (1 << 22) ? "ACPI-TM" : "-",
+			edx & (1 << 29) ? "TM" : "-");
+	}
 
 	if (!(edx & (1 << 5)))
 		errx(1, "CPUID: no MSR");
@@ -2709,15 +3227,15 @@ void process_cpuid()
 	 * This check is valid for both Intel and AMD.
 	 */
 	ebx = ecx = edx = 0;
-	__get_cpuid(0x80000000, &max_level, &ebx, &ecx, &edx);
+	__cpuid(0x80000000, max_extended_level, ebx, ecx, edx);
 
-	if (max_level >= 0x80000007) {
+	if (max_extended_level >= 0x80000007) {
 
 		/*
 		 * Non-Stop TSC is advertised by CPUID.EAX=0x80000007: EDX.bit8
 		 * this check is valid for both Intel and AMD
 		 */
-		__get_cpuid(0x80000007, &eax, &ebx, &ecx, &edx);
+		__cpuid(0x80000007, eax, ebx, ecx, edx);
 		has_invariant_tsc = edx & (1 << 8);
 	}
 
@@ -2726,20 +3244,48 @@ void process_cpuid()
 	 * this check is valid for both Intel and AMD
 	 */
 
-	__get_cpuid(0x6, &eax, &ebx, &ecx, &edx);
+	__cpuid(0x6, eax, ebx, ecx, edx);
 	has_aperf = ecx & (1 << 0);
 	do_dts = eax & (1 << 0);
 	do_ptm = eax & (1 << 6);
+	has_hwp = eax & (1 << 7);
+	has_hwp_notify = eax & (1 << 8);
+	has_hwp_activity_window = eax & (1 << 9);
+	has_hwp_epp = eax & (1 << 10);
+	has_hwp_pkg = eax & (1 << 11);
 	has_epb = ecx & (1 << 3);
 
 	if (debug)
-		fprintf(stderr, "CPUID(6): %sAPERF, %sDTS, %sPTM, %sEPB\n",
-			has_aperf ? "" : "No ",
-			do_dts ? "" : "No ",
-			do_ptm ? "" : "No ",
-			has_epb ? "" : "No ");
+		fprintf(outf, "CPUID(6): %sAPERF, %sDTS, %sPTM, %sHWP, "
+			"%sHWPnotify, %sHWPwindow, %sHWPepp, %sHWPpkg, %sEPB\n",
+			has_aperf ? "" : "No-",
+			do_dts ? "" : "No-",
+			do_ptm ? "" : "No-",
+			has_hwp ? "" : "No-",
+			has_hwp_notify ? "" : "No-",
+			has_hwp_activity_window ? "" : "No-",
+			has_hwp_epp ? "" : "No-",
+			has_hwp_pkg ? "" : "No-",
+			has_epb ? "" : "No-");
+
+	if (debug)
+		decode_misc_enable_msr();
+
+	if (max_level >= 0x7 && debug) {
+		int has_sgx;
+
+		ecx = 0;
+
+		__cpuid_count(0x7, 0, eax, ebx, ecx, edx);
+
+		has_sgx = ebx & (1 << 2);
+		fprintf(outf, "CPUID(7): %sSGX\n", has_sgx ? "" : "No-");
+
+		if (has_sgx)
+			decode_feature_control_msr();
+	}
 
-	if (max_level > 0x15) {
+	if (max_level >= 0x15) {
 		unsigned int eax_crystal;
 		unsigned int ebx_tsc;
 
@@ -2747,19 +3293,27 @@ void process_cpuid()
 		 * CPUID 15H TSC/Crystal ratio, possibly Crystal Hz
 		 */
 		eax_crystal = ebx_tsc = crystal_hz = edx = 0;
-		__get_cpuid(0x15, &eax_crystal, &ebx_tsc, &crystal_hz, &edx);
+		__cpuid(0x15, eax_crystal, ebx_tsc, crystal_hz, edx);
 
 		if (ebx_tsc != 0) {
 
 			if (debug && (ebx != 0))
-				fprintf(stderr, "CPUID(0x15): eax_crystal: %d ebx_tsc: %d ecx_crystal_hz: %d\n",
+				fprintf(outf, "CPUID(0x15): eax_crystal: %d ebx_tsc: %d ecx_crystal_hz: %d\n",
 					eax_crystal, ebx_tsc, crystal_hz);
 
 			if (crystal_hz == 0)
 				switch(model) {
 				case 0x4E:	/* SKL */
 				case 0x5E:	/* SKL */
-					crystal_hz = 24000000;	/* 24 MHz */
+				case 0x8E:	/* KBL */
+				case 0x9E:	/* KBL */
+					crystal_hz = 24000000;	/* 24.0 MHz */
+					break;
+				case 0x55:	/* SKX */
+					crystal_hz = 25000000;	/* 25.0 MHz */
+					break;
+				case 0x5C:	/* BXT */
+					crystal_hz = 19200000;	/* 19.2 MHz */
 					break;
 				default:
 					crystal_hz = 0;
@@ -2768,41 +3322,63 @@ void process_cpuid()
 			if (crystal_hz) {
 				tsc_hz =  (unsigned long long) crystal_hz * ebx_tsc / eax_crystal;
 				if (debug)
-					fprintf(stderr, "TSC: %lld MHz (%d Hz * %d / %d / 1000000)\n",
+					fprintf(outf, "TSC: %lld MHz (%d Hz * %d / %d / 1000000)\n",
 						tsc_hz / 1000000, crystal_hz, ebx_tsc,  eax_crystal);
 			}
 		}
 	}
+	if (max_level >= 0x16) {
+		unsigned int base_mhz, max_mhz, bus_mhz, edx;
+
+		/*
+		 * CPUID 16H Base MHz, Max MHz, Bus MHz
+		 */
+		base_mhz = max_mhz = bus_mhz = edx = 0;
+
+		__cpuid(0x16, base_mhz, max_mhz, bus_mhz, edx);
+		if (debug)
+			fprintf(outf, "CPUID(0x16): base_mhz: %d max_mhz: %d bus_mhz: %d\n",
+				base_mhz, max_mhz, bus_mhz);
+	}
 
 	if (has_aperf)
 		aperf_mperf_multiplier = get_aperf_mperf_multiplier(family, model);
 
 	do_nhm_platform_info = do_nhm_cstates = do_smi = probe_nhm_msrs(family, model);
 	do_snb_cstates = has_snb_msrs(family, model);
+	do_irtl_snb = has_snb_msrs(family, model);
 	do_pc2 = do_snb_cstates && (pkg_cstate_limit >= PCL__2);
 	do_pc3 = (pkg_cstate_limit >= PCL__3);
 	do_pc6 = (pkg_cstate_limit >= PCL__6);
 	do_pc7 = do_snb_cstates && (pkg_cstate_limit >= PCL__7);
 	do_c8_c9_c10 = has_hsw_msrs(family, model);
+	do_irtl_hsw = has_hsw_msrs(family, model);
 	do_skl_residency = has_skl_msrs(family, model);
 	do_slm_cstates = is_slm(family, model);
 	do_knl_cstates  = is_knl(family, model);
 
+	if (debug)
+		decode_misc_pwr_mgmt_msr();
+
 	rapl_probe(family, model);
 	perf_limit_reasons_probe(family, model);
 
 	if (debug)
-		dump_cstate_pstate_config_info();
+		dump_cstate_pstate_config_info(family, model);
 
 	if (has_skl_msrs(family, model))
 		calculate_tsc_tweak();
 
+	do_gfx_rc6_ms = !access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK);
+
+	do_gfx_mhz = !access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK);
+
 	return;
 }
 
 void help()
 {
-	fprintf(stderr,
+	fprintf(outf,
 	"Usage: turbostat [OPTIONS][(--interval seconds) | COMMAND ...]\n"
 	"\n"
 	"Turbostat forks the specified COMMAND and prints statistics\n"
@@ -2814,6 +3390,7 @@ void help()
 	"--help		print this help message\n"
 	"--counter msr	print 32-bit counter at address \"msr\"\n"
 	"--Counter msr	print 64-bit Counter at address \"msr\"\n"
+	"--out file	create or truncate \"file\" for all output\n"
 	"--msr msr	print 32-bit value at address \"msr\"\n"
 	"--MSR msr	print 64-bit Value at address \"msr\"\n"
 	"--version	print version information\n"
@@ -2858,7 +3435,7 @@ void topology_probe()
 		show_cpu = 1;
 
 	if (debug > 1)
-		fprintf(stderr, "num_cpus %d max_cpu_num %d\n", topo.num_cpus, topo.max_cpu_num);
+		fprintf(outf, "num_cpus %d max_cpu_num %d\n", topo.num_cpus, topo.max_cpu_num);
 
 	cpus = calloc(1, (topo.max_cpu_num  + 1) * sizeof(struct cpu_topology));
 	if (cpus == NULL)
@@ -2893,7 +3470,7 @@ void topology_probe()
 
 		if (cpu_is_not_present(i)) {
 			if (debug > 1)
-				fprintf(stderr, "cpu%d NOT PRESENT\n", i);
+				fprintf(outf, "cpu%d NOT PRESENT\n", i);
 			continue;
 		}
 		cpus[i].core_id = get_core_id(i);
@@ -2908,26 +3485,26 @@ void topology_probe()
 		if (siblings > max_siblings)
 			max_siblings = siblings;
 		if (debug > 1)
-			fprintf(stderr, "cpu %d pkg %d core %d\n",
+			fprintf(outf, "cpu %d pkg %d core %d\n",
 				i, cpus[i].physical_package_id, cpus[i].core_id);
 	}
 	topo.num_cores_per_pkg = max_core_id + 1;
 	if (debug > 1)
-		fprintf(stderr, "max_core_id %d, sizing for %d cores per package\n",
+		fprintf(outf, "max_core_id %d, sizing for %d cores per package\n",
 			max_core_id, topo.num_cores_per_pkg);
 	if (debug && !summary_only && topo.num_cores_per_pkg > 1)
 		show_core = 1;
 
 	topo.num_packages = max_package_id + 1;
 	if (debug > 1)
-		fprintf(stderr, "max_package_id %d, sizing for %d packages\n",
+		fprintf(outf, "max_package_id %d, sizing for %d packages\n",
 			max_package_id, topo.num_packages);
 	if (debug && !summary_only && topo.num_packages > 1)
 		show_pkg = 1;
 
 	topo.num_threads_per_core = max_siblings;
 	if (debug > 1)
-		fprintf(stderr, "max_siblings %d\n", max_siblings);
+		fprintf(outf, "max_siblings %d\n", max_siblings);
 
 	free(cpus);
 }
@@ -3019,10 +3596,27 @@ void allocate_output_buffer()
 	if (outp == NULL)
 		err(-1, "calloc output buffer");
 }
+void allocate_fd_percpu(void)
+{
+	fd_percpu = calloc(topo.max_cpu_num, sizeof(int));
+	if (fd_percpu == NULL)
+		err(-1, "calloc fd_percpu");
+}
+void allocate_irq_buffers(void)
+{
+	irq_column_2_cpu = calloc(topo.num_cpus, sizeof(int));
+	if (irq_column_2_cpu == NULL)
+		err(-1, "calloc %d", topo.num_cpus);
 
+	irqs_per_cpu = calloc(topo.max_cpu_num, sizeof(int));
+	if (irqs_per_cpu == NULL)
+		err(-1, "calloc %d", topo.max_cpu_num);
+}
 void setup_all_buffers(void)
 {
 	topology_probe();
+	allocate_irq_buffers();
+	allocate_fd_percpu();
 	allocate_counters(&thread_even, &core_even, &package_even);
 	allocate_counters(&thread_odd, &core_odd, &package_odd);
 	allocate_output_buffer();
@@ -3036,7 +3630,7 @@ void set_base_cpu(void)
 		err(-ENODEV, "No valid cpus found");
 
 	if (debug > 1)
-		fprintf(stderr, "base_cpu = %d\n", base_cpu);
+		fprintf(outf, "base_cpu = %d\n", base_cpu);
 }
 
 void turbostat_init()
@@ -3049,6 +3643,9 @@ void turbostat_init()
 
 
 	if (debug)
+		for_all_cpus(print_hwp, ODD_COUNTERS);
+
+	if (debug)
 		for_all_cpus(print_epb, ODD_COUNTERS);
 
 	if (debug)
@@ -3061,6 +3658,9 @@ void turbostat_init()
 
 	if (debug)
 		for_all_cpus(print_thermal, ODD_COUNTERS);
+
+	if (debug && do_irtl_snb)
+		print_irtl();
 }
 
 int fork_it(char **argv)
@@ -3100,9 +3700,10 @@ int fork_it(char **argv)
 	for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS);
 	compute_average(EVEN_COUNTERS);
 	format_all_counters(EVEN_COUNTERS);
-	flush_stderr();
 
-	fprintf(stderr, "%.6f sec\n", tv_delta.tv_sec + tv_delta.tv_usec/1000000.0);
+	fprintf(outf, "%.6f sec\n", tv_delta.tv_sec + tv_delta.tv_usec/1000000.0);
+
+	flush_output_stderr();
 
 	return status;
 }
@@ -3119,13 +3720,13 @@ int get_and_dump_counters(void)
 	if (status)
 		return status;
 
-	flush_stdout();
+	flush_output_stdout();
 
 	return status;
 }
 
 void print_version() {
-	fprintf(stderr, "turbostat version 4.8 26-Sep, 2015"
+	fprintf(outf, "turbostat version 4.12 5 Apr 2016"
 		" - Len Brown <lenb@kernel.org>\n");
 }
 
@@ -3143,6 +3744,7 @@ void cmdline(int argc, char **argv)
 		{"Joules",	no_argument,		0, 'J'},
 		{"MSR",		required_argument,	0, 'M'},
 		{"msr",		required_argument,	0, 'm'},
+		{"out",		required_argument,	0, 'o'},
 		{"Package",	no_argument,		0, 'p'},
 		{"processor",	no_argument,		0, 'p'},
 		{"Summary",	no_argument,		0, 'S'},
@@ -3153,7 +3755,7 @@ void cmdline(int argc, char **argv)
 
 	progname = argv[0];
 
-	while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:PpST:v",
+	while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:PpST:v",
 				long_options, &option_index)) != -1) {
 		switch (opt) {
 		case 'C':
@@ -3173,7 +3775,18 @@ void cmdline(int argc, char **argv)
 			help();
 			exit(1);
 		case 'i':
-			interval_sec = atoi(optarg);
+			{
+				double interval = strtod(optarg, NULL);
+
+				if (interval < 0.001) {
+					fprintf(outf, "interval %f seconds is too small\n",
+						interval);
+					exit(2);
+				}
+
+				interval_ts.tv_sec = interval;
+				interval_ts.tv_nsec = (interval - interval_ts.tv_sec) * 1000000000;
+			}
 			break;
 		case 'J':
 			rapl_joules++;
@@ -3184,6 +3797,9 @@ void cmdline(int argc, char **argv)
 		case 'm':
 			sscanf(optarg, "%x", &extra_msr_offset32);
 			break;
+		case 'o':
+			outf = fopen_or_die(optarg, "w");
+			break;
 		case 'P':
 			show_pkg_only++;
 			break;
@@ -3206,6 +3822,8 @@ void cmdline(int argc, char **argv)
 
 int main(int argc, char **argv)
 {
+	outf = stderr;
+
 	cmdline(argc, argv);
 
 	if (debug)
diff --git a/tools/perf/config/utilities.mak b/tools/scripts/utilities.mak
index c16ce8330..c16ce8330 100644
--- a/tools/perf/config/utilities.mak
+++ b/tools/scripts/utilities.mak
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index b3281dcd4..3187322ee 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -151,6 +151,11 @@ struct nfit_test {
 	int (*alloc)(struct nfit_test *t);
 	void (*setup)(struct nfit_test *t);
 	int setup_hotplug;
+	struct ars_state {
+		struct nd_cmd_ars_status *ars_status;
+		unsigned long deadline;
+		spinlock_t lock;
+	} ars_state;
 };
 
 static struct nfit_test *to_nfit_test(struct device *dev)
@@ -218,6 +223,7 @@ static int nfit_test_cmd_set_config_data(struct nd_cmd_set_config_hdr *nd_cmd,
 }
 
 #define NFIT_TEST_ARS_RECORDS 4
+#define NFIT_TEST_CLEAR_ERR_UNIT 256
 
 static int nfit_test_cmd_ars_cap(struct nd_cmd_ars_cap *nd_cmd,
 		unsigned int buf_len)
@@ -228,44 +234,113 @@ static int nfit_test_cmd_ars_cap(struct nd_cmd_ars_cap *nd_cmd,
 	nd_cmd->max_ars_out = sizeof(struct nd_cmd_ars_status)
 		+ NFIT_TEST_ARS_RECORDS * sizeof(struct nd_ars_record);
 	nd_cmd->status = (ND_ARS_PERSISTENT | ND_ARS_VOLATILE) << 16;
+	nd_cmd->clear_err_unit = NFIT_TEST_CLEAR_ERR_UNIT;
 
 	return 0;
 }
 
-static int nfit_test_cmd_ars_start(struct nd_cmd_ars_start *nd_cmd,
-		unsigned int buf_len)
+/*
+ * Initialize the ars_state to return an ars_result 1 second in the future with
+ * a 4K error range in the middle of the requested address range.
+ */
+static void post_ars_status(struct ars_state *ars_state, u64 addr, u64 len)
 {
-	if (buf_len < sizeof(*nd_cmd))
+	struct nd_cmd_ars_status *ars_status;
+	struct nd_ars_record *ars_record;
+
+	ars_state->deadline = jiffies + 1*HZ;
+	ars_status = ars_state->ars_status;
+	ars_status->status = 0;
+	ars_status->out_length = sizeof(struct nd_cmd_ars_status)
+		+ sizeof(struct nd_ars_record);
+	ars_status->address = addr;
+	ars_status->length = len;
+	ars_status->type = ND_ARS_PERSISTENT;
+	ars_status->num_records = 1;
+	ars_record = &ars_status->records[0];
+	ars_record->handle = 0;
+	ars_record->err_address = addr + len / 2;
+	ars_record->length = SZ_4K;
+}
+
+static int nfit_test_cmd_ars_start(struct ars_state *ars_state,
+		struct nd_cmd_ars_start *ars_start, unsigned int buf_len,
+		int *cmd_rc)
+{
+	if (buf_len < sizeof(*ars_start))
 		return -EINVAL;
 
-	nd_cmd->status = 0;
+	spin_lock(&ars_state->lock);
+	if (time_before(jiffies, ars_state->deadline)) {
+		ars_start->status = NFIT_ARS_START_BUSY;
+		*cmd_rc = -EBUSY;
+	} else {
+		ars_start->status = 0;
+		ars_start->scrub_time = 1;
+		post_ars_status(ars_state, ars_start->address,
+				ars_start->length);
+		*cmd_rc = 0;
+	}
+	spin_unlock(&ars_state->lock);
 
 	return 0;
 }
 
-static int nfit_test_cmd_ars_status(struct nd_cmd_ars_status *nd_cmd,
-		unsigned int buf_len)
+static int nfit_test_cmd_ars_status(struct ars_state *ars_state,
+		struct nd_cmd_ars_status *ars_status, unsigned int buf_len,
+		int *cmd_rc)
 {
-	if (buf_len < sizeof(*nd_cmd))
+	if (buf_len < ars_state->ars_status->out_length)
 		return -EINVAL;
 
-	nd_cmd->out_length = sizeof(struct nd_cmd_ars_status);
-	/* TODO: emit error records */
-	nd_cmd->num_records = 0;
-	nd_cmd->address = 0;
-	nd_cmd->length = -1ULL;
-	nd_cmd->status = 0;
+	spin_lock(&ars_state->lock);
+	if (time_before(jiffies, ars_state->deadline)) {
+		memset(ars_status, 0, buf_len);
+		ars_status->status = NFIT_ARS_STATUS_BUSY;
+		ars_status->out_length = sizeof(*ars_status);
+		*cmd_rc = -EBUSY;
+	} else {
+		memcpy(ars_status, ars_state->ars_status,
+				ars_state->ars_status->out_length);
+		*cmd_rc = 0;
+	}
+	spin_unlock(&ars_state->lock);
+	return 0;
+}
 
+static int nfit_test_cmd_clear_error(struct nd_cmd_clear_error *clear_err,
+		unsigned int buf_len, int *cmd_rc)
+{
+	const u64 mask = NFIT_TEST_CLEAR_ERR_UNIT - 1;
+	if (buf_len < sizeof(*clear_err))
+		return -EINVAL;
+
+	if ((clear_err->address & mask) || (clear_err->length & mask))
+		return -EINVAL;
+
+	/*
+	 * Report 'all clear' success for all commands even though a new
+	 * scrub will find errors again.  This is enough to have the
+	 * error removed from the 'badblocks' tracking in the pmem
+	 * driver.
+	 */
+	clear_err->status = 0;
+	clear_err->cleared = clear_err->length;
+	*cmd_rc = 0;
 	return 0;
 }
 
 static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
 		struct nvdimm *nvdimm, unsigned int cmd, void *buf,
-		unsigned int buf_len)
+		unsigned int buf_len, int *cmd_rc)
 {
 	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
 	struct nfit_test *t = container_of(acpi_desc, typeof(*t), acpi_desc);
-	int i, rc = 0;
+	int i, rc = 0, __cmd_rc;
+
+	if (!cmd_rc)
+		cmd_rc = &__cmd_rc;
+	*cmd_rc = 0;
 
 	if (nvdimm) {
 		struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
@@ -297,6 +372,8 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
 			return -ENOTTY;
 		}
 	} else {
+		struct ars_state *ars_state = &t->ars_state;
+
 		if (!nd_desc || !test_bit(cmd, &nd_desc->dsm_mask))
 			return -ENOTTY;
 
@@ -305,10 +382,15 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
 			rc = nfit_test_cmd_ars_cap(buf, buf_len);
 			break;
 		case ND_CMD_ARS_START:
-			rc = nfit_test_cmd_ars_start(buf, buf_len);
+			rc = nfit_test_cmd_ars_start(ars_state, buf, buf_len,
+					cmd_rc);
 			break;
 		case ND_CMD_ARS_STATUS:
-			rc = nfit_test_cmd_ars_status(buf, buf_len);
+			rc = nfit_test_cmd_ars_status(ars_state, buf, buf_len,
+					cmd_rc);
+			break;
+		case ND_CMD_CLEAR_ERROR:
+			rc = nfit_test_cmd_clear_error(buf, buf_len, cmd_rc);
 			break;
 		default:
 			return -ENOTTY;
@@ -424,11 +506,25 @@ static struct nfit_test_resource *nfit_test_lookup(resource_size_t addr)
 	return NULL;
 }
 
+static int ars_state_init(struct device *dev, struct ars_state *ars_state)
+{
+	ars_state->ars_status = devm_kzalloc(dev,
+			sizeof(struct nd_cmd_ars_status)
+			+ sizeof(struct nd_ars_record) * NFIT_TEST_ARS_RECORDS,
+			GFP_KERNEL);
+	if (!ars_state->ars_status)
+		return -ENOMEM;
+	spin_lock_init(&ars_state->lock);
+	return 0;
+}
+
 static int nfit_test0_alloc(struct nfit_test *t)
 {
 	size_t nfit_size = sizeof(struct acpi_nfit_system_address) * NUM_SPA
 			+ sizeof(struct acpi_nfit_memory_map) * NUM_MEM
 			+ sizeof(struct acpi_nfit_control_region) * NUM_DCR
+			+ offsetof(struct acpi_nfit_control_region,
+					window_size) * NUM_DCR
 			+ sizeof(struct acpi_nfit_data_region) * NUM_BDW
 			+ sizeof(struct acpi_nfit_flush_address) * NUM_DCR;
 	int i;
@@ -471,14 +567,14 @@ static int nfit_test0_alloc(struct nfit_test *t)
 			return -ENOMEM;
 	}
 
-	return 0;
+	return ars_state_init(&t->pdev.dev, &t->ars_state);
 }
 
 static int nfit_test1_alloc(struct nfit_test *t)
 {
 	size_t nfit_size = sizeof(struct acpi_nfit_system_address)
 		+ sizeof(struct acpi_nfit_memory_map)
-		+ sizeof(struct acpi_nfit_control_region);
+		+ offsetof(struct acpi_nfit_control_region, window_size);
 
 	t->nfit_buf = test_alloc(t, nfit_size, &t->nfit_dma);
 	if (!t->nfit_buf)
@@ -489,12 +585,11 @@ static int nfit_test1_alloc(struct nfit_test *t)
 	if (!t->spa_set[0])
 		return -ENOMEM;
 
-	return 0;
+	return ars_state_init(&t->pdev.dev, &t->ars_state);
 }
 
 static void nfit_test0_setup(struct nfit_test *t)
 {
-	struct nvdimm_bus_descriptor *nd_desc;
 	struct acpi_nfit_desc *acpi_desc;
 	struct acpi_nfit_memory_map *memdev;
 	void *nfit_buf = t->nfit_buf;
@@ -611,7 +706,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	memdev->physical_id = 0;
 	memdev->region_id = 0;
 	memdev->range_index = 0+1;
-	memdev->region_index = 0+1;
+	memdev->region_index = 4+1;
 	memdev->region_size = SPA0_SIZE/2;
 	memdev->region_offset = t->spa_set_dma[0];
 	memdev->address = 0;
@@ -626,7 +721,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	memdev->physical_id = 1;
 	memdev->region_id = 0;
 	memdev->range_index = 0+1;
-	memdev->region_index = 1+1;
+	memdev->region_index = 5+1;
 	memdev->region_size = SPA0_SIZE/2;
 	memdev->region_offset = t->spa_set_dma[0] + SPA0_SIZE/2;
 	memdev->address = 0;
@@ -641,7 +736,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	memdev->physical_id = 0;
 	memdev->region_id = 1;
 	memdev->range_index = 1+1;
-	memdev->region_index = 0+1;
+	memdev->region_index = 4+1;
 	memdev->region_size = SPA1_SIZE/4;
 	memdev->region_offset = t->spa_set_dma[1];
 	memdev->address = SPA0_SIZE/2;
@@ -656,7 +751,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	memdev->physical_id = 1;
 	memdev->region_id = 1;
 	memdev->range_index = 1+1;
-	memdev->region_index = 1+1;
+	memdev->region_index = 5+1;
 	memdev->region_size = SPA1_SIZE/4;
 	memdev->region_offset = t->spa_set_dma[1] + SPA1_SIZE/4;
 	memdev->address = SPA0_SIZE/2;
@@ -671,7 +766,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	memdev->physical_id = 2;
 	memdev->region_id = 0;
 	memdev->range_index = 1+1;
-	memdev->region_index = 2+1;
+	memdev->region_index = 6+1;
 	memdev->region_size = SPA1_SIZE/4;
 	memdev->region_offset = t->spa_set_dma[1] + 2*SPA1_SIZE/4;
 	memdev->address = SPA0_SIZE/2;
@@ -686,7 +781,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	memdev->physical_id = 3;
 	memdev->region_id = 0;
 	memdev->range_index = 1+1;
-	memdev->region_index = 3+1;
+	memdev->region_index = 7+1;
 	memdev->region_size = SPA1_SIZE/4;
 	memdev->region_offset = t->spa_set_dma[1] + 3*SPA1_SIZE/4;
 	memdev->address = SPA0_SIZE/2;
@@ -814,7 +909,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	memdev->interleave_ways = 1;
 
 	offset = offset + sizeof(struct acpi_nfit_memory_map) * 14;
-	/* dcr-descriptor0 */
+	/* dcr-descriptor0: blk */
 	dcr = nfit_buf + offset;
 	dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
 	dcr->header.length = sizeof(struct acpi_nfit_control_region);
@@ -823,6 +918,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	dcr->device_id = 0;
 	dcr->revision_id = 1;
 	dcr->serial_number = ~handle[0];
+	dcr->code = NFIT_FIC_BLK;
 	dcr->windows = 1;
 	dcr->window_size = DCR_SIZE;
 	dcr->command_offset = 0;
@@ -830,7 +926,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	dcr->status_offset = 8;
 	dcr->status_size = 4;
 
-	/* dcr-descriptor1 */
+	/* dcr-descriptor1: blk */
 	dcr = nfit_buf + offset + sizeof(struct acpi_nfit_control_region);
 	dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
 	dcr->header.length = sizeof(struct acpi_nfit_control_region);
@@ -839,6 +935,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	dcr->device_id = 0;
 	dcr->revision_id = 1;
 	dcr->serial_number = ~handle[1];
+	dcr->code = NFIT_FIC_BLK;
 	dcr->windows = 1;
 	dcr->window_size = DCR_SIZE;
 	dcr->command_offset = 0;
@@ -846,7 +943,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	dcr->status_offset = 8;
 	dcr->status_size = 4;
 
-	/* dcr-descriptor2 */
+	/* dcr-descriptor2: blk */
 	dcr = nfit_buf + offset + sizeof(struct acpi_nfit_control_region) * 2;
 	dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
 	dcr->header.length = sizeof(struct acpi_nfit_control_region);
@@ -855,6 +952,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	dcr->device_id = 0;
 	dcr->revision_id = 1;
 	dcr->serial_number = ~handle[2];
+	dcr->code = NFIT_FIC_BLK;
 	dcr->windows = 1;
 	dcr->window_size = DCR_SIZE;
 	dcr->command_offset = 0;
@@ -862,7 +960,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	dcr->status_offset = 8;
 	dcr->status_size = 4;
 
-	/* dcr-descriptor3 */
+	/* dcr-descriptor3: blk */
 	dcr = nfit_buf + offset + sizeof(struct acpi_nfit_control_region) * 3;
 	dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
 	dcr->header.length = sizeof(struct acpi_nfit_control_region);
@@ -871,6 +969,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	dcr->device_id = 0;
 	dcr->revision_id = 1;
 	dcr->serial_number = ~handle[3];
+	dcr->code = NFIT_FIC_BLK;
 	dcr->windows = 1;
 	dcr->window_size = DCR_SIZE;
 	dcr->command_offset = 0;
@@ -879,6 +978,63 @@ static void nfit_test0_setup(struct nfit_test *t)
 	dcr->status_size = 4;
 
 	offset = offset + sizeof(struct acpi_nfit_control_region) * 4;
+	/* dcr-descriptor0: pmem */
+	dcr = nfit_buf + offset;
+	dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
+	dcr->header.length = offsetof(struct acpi_nfit_control_region,
+			window_size);
+	dcr->region_index = 4+1;
+	dcr->vendor_id = 0xabcd;
+	dcr->device_id = 0;
+	dcr->revision_id = 1;
+	dcr->serial_number = ~handle[0];
+	dcr->code = NFIT_FIC_BYTEN;
+	dcr->windows = 0;
+
+	/* dcr-descriptor1: pmem */
+	dcr = nfit_buf + offset + offsetof(struct acpi_nfit_control_region,
+			window_size);
+	dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
+	dcr->header.length = offsetof(struct acpi_nfit_control_region,
+			window_size);
+	dcr->region_index = 5+1;
+	dcr->vendor_id = 0xabcd;
+	dcr->device_id = 0;
+	dcr->revision_id = 1;
+	dcr->serial_number = ~handle[1];
+	dcr->code = NFIT_FIC_BYTEN;
+	dcr->windows = 0;
+
+	/* dcr-descriptor2: pmem */
+	dcr = nfit_buf + offset + offsetof(struct acpi_nfit_control_region,
+			window_size) * 2;
+	dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
+	dcr->header.length = offsetof(struct acpi_nfit_control_region,
+			window_size);
+	dcr->region_index = 6+1;
+	dcr->vendor_id = 0xabcd;
+	dcr->device_id = 0;
+	dcr->revision_id = 1;
+	dcr->serial_number = ~handle[2];
+	dcr->code = NFIT_FIC_BYTEN;
+	dcr->windows = 0;
+
+	/* dcr-descriptor3: pmem */
+	dcr = nfit_buf + offset + offsetof(struct acpi_nfit_control_region,
+			window_size) * 3;
+	dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
+	dcr->header.length = offsetof(struct acpi_nfit_control_region,
+			window_size);
+	dcr->region_index = 7+1;
+	dcr->vendor_id = 0xabcd;
+	dcr->device_id = 0;
+	dcr->revision_id = 1;
+	dcr->serial_number = ~handle[3];
+	dcr->code = NFIT_FIC_BYTEN;
+	dcr->windows = 0;
+
+	offset = offset + offsetof(struct acpi_nfit_control_region,
+			window_size) * 4;
 	/* bdw0 (spa/dcr0, dimm0) */
 	bdw = nfit_buf + offset;
 	bdw->header.type = ACPI_NFIT_TYPE_DATA_REGION;
@@ -958,15 +1114,16 @@ static void nfit_test0_setup(struct nfit_test *t)
 
 	if (t->setup_hotplug) {
 		offset = offset + sizeof(struct acpi_nfit_flush_address) * 4;
-		/* dcr-descriptor4 */
+		/* dcr-descriptor4: blk */
 		dcr = nfit_buf + offset;
 		dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
 		dcr->header.length = sizeof(struct acpi_nfit_control_region);
-		dcr->region_index = 4+1;
+		dcr->region_index = 8+1;
 		dcr->vendor_id = 0xabcd;
 		dcr->device_id = 0;
 		dcr->revision_id = 1;
 		dcr->serial_number = ~handle[4];
+		dcr->code = NFIT_FIC_BLK;
 		dcr->windows = 1;
 		dcr->window_size = DCR_SIZE;
 		dcr->command_offset = 0;
@@ -975,11 +1132,26 @@ static void nfit_test0_setup(struct nfit_test *t)
 		dcr->status_size = 4;
 
 		offset = offset + sizeof(struct acpi_nfit_control_region);
+		/* dcr-descriptor4: pmem */
+		dcr = nfit_buf + offset;
+		dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
+		dcr->header.length = offsetof(struct acpi_nfit_control_region,
+				window_size);
+		dcr->region_index = 9+1;
+		dcr->vendor_id = 0xabcd;
+		dcr->device_id = 0;
+		dcr->revision_id = 1;
+		dcr->serial_number = ~handle[4];
+		dcr->code = NFIT_FIC_BYTEN;
+		dcr->windows = 0;
+
+		offset = offset + offsetof(struct acpi_nfit_control_region,
+				window_size);
 		/* bdw4 (spa/dcr4, dimm4) */
 		bdw = nfit_buf + offset;
 		bdw->header.type = ACPI_NFIT_TYPE_DATA_REGION;
 		bdw->header.length = sizeof(struct acpi_nfit_data_region);
-		bdw->region_index = 4+1;
+		bdw->region_index = 8+1;
 		bdw->windows = 1;
 		bdw->offset = 0;
 		bdw->size = BDW_SIZE;
@@ -1027,7 +1199,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 		memdev->physical_id = 4;
 		memdev->region_id = 0;
 		memdev->range_index = 10+1;
-		memdev->region_index = 4+1;
+		memdev->region_index = 8+1;
 		memdev->region_size = 0;
 		memdev->region_offset = 0;
 		memdev->address = 0;
@@ -1043,14 +1215,14 @@ static void nfit_test0_setup(struct nfit_test *t)
 		memdev->physical_id = 4;
 		memdev->region_id = 0;
 		memdev->range_index = 11+1;
-		memdev->region_index = 4+1;
+		memdev->region_index = 9+1;
 		memdev->region_size = SPA0_SIZE;
 		memdev->region_offset = t->spa_set_dma[2];
 		memdev->address = 0;
 		memdev->interleave_index = 0;
 		memdev->interleave_ways = 1;
 
-		/* mem-region16 (spa/dcr4, dimm4) */
+		/* mem-region16 (spa/bdw4, dimm4) */
 		memdev = nfit_buf + offset +
 				sizeof(struct acpi_nfit_memory_map) * 2;
 		memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
@@ -1059,7 +1231,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 		memdev->physical_id = 4;
 		memdev->region_id = 0;
 		memdev->range_index = 12+1;
-		memdev->region_index = 4+1;
+		memdev->region_index = 8+1;
 		memdev->region_size = 0;
 		memdev->region_offset = 0;
 		memdev->address = 0;
@@ -1076,6 +1248,8 @@ static void nfit_test0_setup(struct nfit_test *t)
 		flush->hint_address[0] = t->flush_dma[4];
 	}
 
+	post_ars_status(&t->ars_state, t->spa_set_dma[0], SPA0_SIZE);
+
 	acpi_desc = &t->acpi_desc;
 	set_bit(ND_CMD_GET_CONFIG_SIZE, &acpi_desc->dimm_dsm_force_en);
 	set_bit(ND_CMD_GET_CONFIG_DATA, &acpi_desc->dimm_dsm_force_en);
@@ -1083,8 +1257,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	set_bit(ND_CMD_ARS_CAP, &acpi_desc->bus_dsm_force_en);
 	set_bit(ND_CMD_ARS_START, &acpi_desc->bus_dsm_force_en);
 	set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_dsm_force_en);
-	nd_desc = &acpi_desc->nd_desc;
-	nd_desc->ndctl = nfit_test_ctl;
+	set_bit(ND_CMD_CLEAR_ERROR, &acpi_desc->bus_dsm_force_en);
 }
 
 static void nfit_test1_setup(struct nfit_test *t)
@@ -1094,7 +1267,6 @@ static void nfit_test1_setup(struct nfit_test *t)
 	struct acpi_nfit_memory_map *memdev;
 	struct acpi_nfit_control_region *dcr;
 	struct acpi_nfit_system_address *spa;
-	struct nvdimm_bus_descriptor *nd_desc;
 	struct acpi_nfit_desc *acpi_desc;
 
 	offset = 0;
@@ -1130,26 +1302,23 @@ static void nfit_test1_setup(struct nfit_test *t)
 	/* dcr-descriptor0 */
 	dcr = nfit_buf + offset;
 	dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
-	dcr->header.length = sizeof(struct acpi_nfit_control_region);
+	dcr->header.length = offsetof(struct acpi_nfit_control_region,
+			window_size);
 	dcr->region_index = 0+1;
 	dcr->vendor_id = 0xabcd;
 	dcr->device_id = 0;
 	dcr->revision_id = 1;
 	dcr->serial_number = ~0;
-	dcr->code = 0x201;
+	dcr->code = NFIT_FIC_BYTE;
 	dcr->windows = 0;
-	dcr->window_size = 0;
-	dcr->command_offset = 0;
-	dcr->command_size = 0;
-	dcr->status_offset = 0;
-	dcr->status_size = 0;
+
+	post_ars_status(&t->ars_state, t->spa_set_dma[0], SPA2_SIZE);
 
 	acpi_desc = &t->acpi_desc;
 	set_bit(ND_CMD_ARS_CAP, &acpi_desc->bus_dsm_force_en);
 	set_bit(ND_CMD_ARS_START, &acpi_desc->bus_dsm_force_en);
 	set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_dsm_force_en);
-	nd_desc = &acpi_desc->nd_desc;
-	nd_desc->ndctl = nfit_test_ctl;
+	set_bit(ND_CMD_CLEAR_ERROR, &acpi_desc->bus_dsm_force_en);
 }
 
 static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa,
@@ -1232,26 +1401,16 @@ static int nfit_test_probe(struct platform_device *pdev)
 
 	nfit_test->setup(nfit_test);
 	acpi_desc = &nfit_test->acpi_desc;
-	acpi_desc->dev = &pdev->dev;
+	acpi_nfit_desc_init(acpi_desc, &pdev->dev);
 	acpi_desc->nfit = nfit_test->nfit_buf;
 	acpi_desc->blk_do_io = nfit_test_blk_do_io;
 	nd_desc = &acpi_desc->nd_desc;
-	nd_desc->attr_groups = acpi_nfit_attribute_groups;
+	nd_desc->provider_name = NULL;
+	nd_desc->ndctl = nfit_test_ctl;
 	acpi_desc->nvdimm_bus = nvdimm_bus_register(&pdev->dev, nd_desc);
 	if (!acpi_desc->nvdimm_bus)
 		return -ENXIO;
 
-	INIT_LIST_HEAD(&acpi_desc->spa_maps);
-	INIT_LIST_HEAD(&acpi_desc->spas);
-	INIT_LIST_HEAD(&acpi_desc->dcrs);
-	INIT_LIST_HEAD(&acpi_desc->bdws);
-	INIT_LIST_HEAD(&acpi_desc->idts);
-	INIT_LIST_HEAD(&acpi_desc->flushes);
-	INIT_LIST_HEAD(&acpi_desc->memdevs);
-	INIT_LIST_HEAD(&acpi_desc->dimms);
-	mutex_init(&acpi_desc->spa_map_mutex);
-	mutex_init(&acpi_desc->init_mutex);
-
 	rc = acpi_nfit_init(acpi_desc, nfit_test->nfit_size);
 	if (rc) {
 		nvdimm_bus_unregister(acpi_desc->nvdimm_bus);
diff --git a/tools/testing/radix-tree/.gitignore b/tools/testing/radix-tree/.gitignore
new file mode 100644
index 000000000..11d888ca6
--- /dev/null
+++ b/tools/testing/radix-tree/.gitignore
@@ -0,0 +1,2 @@
+main
+radix-tree.c
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
new file mode 100644
index 000000000..604212db9
--- /dev/null
+++ b/tools/testing/radix-tree/Makefile
@@ -0,0 +1,19 @@
+
+CFLAGS += -I. -g -Wall -D_LGPL_SOURCE
+LDFLAGS += -lpthread -lurcu
+TARGETS = main
+OFILES = main.o radix-tree.o linux.o test.o tag_check.o find_next_bit.o \
+	 regression1.o regression2.o regression3.o
+
+targets: $(TARGETS)
+
+main:	$(OFILES)
+	$(CC) $(CFLAGS) $(LDFLAGS) $(OFILES) -o main
+
+clean:
+	$(RM) -f $(TARGETS) *.o radix-tree.c
+
+$(OFILES): *.h */*.h
+
+radix-tree.c: ../../../lib/radix-tree.c
+	sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@
diff --git a/tools/testing/radix-tree/find_next_bit.c b/tools/testing/radix-tree/find_next_bit.c
new file mode 100644
index 000000000..d1c2178bb
--- /dev/null
+++ b/tools/testing/radix-tree/find_next_bit.c
@@ -0,0 +1,57 @@
+/* find_next_bit.c: fallback find next bit implementation
+ *
+ * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/types.h>
+#include <linux/bitops.h>
+
+#define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)
+
+/*
+ * Find the next set bit in a memory region.
+ */
+unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
+			    unsigned long offset)
+{
+	const unsigned long *p = addr + BITOP_WORD(offset);
+	unsigned long result = offset & ~(BITS_PER_LONG-1);
+	unsigned long tmp;
+
+	if (offset >= size)
+		return size;
+	size -= result;
+	offset %= BITS_PER_LONG;
+	if (offset) {
+		tmp = *(p++);
+		tmp &= (~0UL << offset);
+		if (size < BITS_PER_LONG)
+			goto found_first;
+		if (tmp)
+			goto found_middle;
+		size -= BITS_PER_LONG;
+		result += BITS_PER_LONG;
+	}
+	while (size & ~(BITS_PER_LONG-1)) {
+		if ((tmp = *(p++)))
+			goto found_middle;
+		result += BITS_PER_LONG;
+		size -= BITS_PER_LONG;
+	}
+	if (!size)
+		return result;
+	tmp = *p;
+
+found_first:
+	tmp &= (~0UL >> (BITS_PER_LONG - size));
+	if (tmp == 0UL)		/* Are any bits set? */
+		return result + size;	/* Nope. */
+found_middle:
+	return result + __ffs(tmp);
+}
diff --git a/tools/testing/radix-tree/linux.c b/tools/testing/radix-tree/linux.c
new file mode 100644
index 000000000..154823737
--- /dev/null
+++ b/tools/testing/radix-tree/linux.c
@@ -0,0 +1,60 @@
+#include <stdlib.h>
+#include <string.h>
+#include <malloc.h>
+#include <unistd.h>
+#include <assert.h>
+
+#include <linux/mempool.h>
+#include <linux/slab.h>
+#include <urcu/uatomic.h>
+
+int nr_allocated;
+
+void *mempool_alloc(mempool_t *pool, int gfp_mask)
+{
+	return pool->alloc(gfp_mask, pool->data);
+}
+
+void mempool_free(void *element, mempool_t *pool)
+{
+	pool->free(element, pool->data);
+}
+
+mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn,
+			mempool_free_t *free_fn, void *pool_data)
+{
+	mempool_t *ret = malloc(sizeof(*ret));
+
+	ret->alloc = alloc_fn;
+	ret->free = free_fn;
+	ret->data = pool_data;
+	return ret;
+}
+
+void *kmem_cache_alloc(struct kmem_cache *cachep, int flags)
+{
+	void *ret = malloc(cachep->size);
+	if (cachep->ctor)
+		cachep->ctor(ret);
+	uatomic_inc(&nr_allocated);
+	return ret;
+}
+
+void kmem_cache_free(struct kmem_cache *cachep, void *objp)
+{
+	assert(objp);
+	uatomic_dec(&nr_allocated);
+	memset(objp, 0, cachep->size);
+	free(objp);
+}
+
+struct kmem_cache *
+kmem_cache_create(const char *name, size_t size, size_t offset,
+	unsigned long flags, void (*ctor)(void *))
+{
+	struct kmem_cache *ret = malloc(sizeof(*ret));
+
+	ret->size = size;
+	ret->ctor = ctor;
+	return ret;
+}
diff --git a/tools/testing/radix-tree/linux/bitops.h b/tools/testing/radix-tree/linux/bitops.h
new file mode 100644
index 000000000..71d58427a
--- /dev/null
+++ b/tools/testing/radix-tree/linux/bitops.h
@@ -0,0 +1,150 @@
+#ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
+#define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
+
+#include <linux/types.h>
+
+#define BITOP_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
+#define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)
+
+/**
+ * __set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike set_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static inline void __set_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BITOP_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
+
+	*p  |= mask;
+}
+
+static inline void __clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BITOP_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
+
+	*p &= ~mask;
+}
+
+/**
+ * __change_bit - Toggle a bit in memory
+ * @nr: the bit to change
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static inline void __change_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BITOP_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
+
+	*p ^= mask;
+}
+
+/**
+ * __test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BITOP_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old | mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * __test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BITOP_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old & ~mask;
+	return (old & mask) != 0;
+}
+
+/* WARNING: non atomic and it can be reordered! */
+static inline int __test_and_change_bit(int nr,
+					    volatile unsigned long *addr)
+{
+	unsigned long mask = BITOP_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old ^ mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static inline int test_bit(int nr, const volatile unsigned long *addr)
+{
+	return 1UL & (addr[BITOP_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
+}
+
+/**
+ * __ffs - find first bit in word.
+ * @word: The word to search
+ *
+ * Undefined if no bit exists, so code should check against 0 first.
+ */
+static inline unsigned long __ffs(unsigned long word)
+{
+	int num = 0;
+
+	if ((word & 0xffffffff) == 0) {
+		num += 32;
+		word >>= 32;
+	}
+	if ((word & 0xffff) == 0) {
+		num += 16;
+		word >>= 16;
+	}
+	if ((word & 0xff) == 0) {
+		num += 8;
+		word >>= 8;
+	}
+	if ((word & 0xf) == 0) {
+		num += 4;
+		word >>= 4;
+	}
+	if ((word & 0x3) == 0) {
+		num += 2;
+		word >>= 2;
+	}
+	if ((word & 0x1) == 0)
+		num += 1;
+	return num;
+}
+
+unsigned long find_next_bit(const unsigned long *addr,
+			    unsigned long size,
+			    unsigned long offset);
+
+#endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
diff --git a/tools/testing/radix-tree/linux/bitops/__ffs.h b/tools/testing/radix-tree/linux/bitops/__ffs.h
new file mode 100644
index 000000000..9a3274aec
--- /dev/null
+++ b/tools/testing/radix-tree/linux/bitops/__ffs.h
@@ -0,0 +1,43 @@
+#ifndef _ASM_GENERIC_BITOPS___FFS_H_
+#define _ASM_GENERIC_BITOPS___FFS_H_
+
+#include <asm/types.h>
+
+/**
+ * __ffs - find first bit in word.
+ * @word: The word to search
+ *
+ * Undefined if no bit exists, so code should check against 0 first.
+ */
+static inline unsigned long __ffs(unsigned long word)
+{
+	int num = 0;
+
+#if BITS_PER_LONG == 64
+	if ((word & 0xffffffff) == 0) {
+		num += 32;
+		word >>= 32;
+	}
+#endif
+	if ((word & 0xffff) == 0) {
+		num += 16;
+		word >>= 16;
+	}
+	if ((word & 0xff) == 0) {
+		num += 8;
+		word >>= 8;
+	}
+	if ((word & 0xf) == 0) {
+		num += 4;
+		word >>= 4;
+	}
+	if ((word & 0x3) == 0) {
+		num += 2;
+		word >>= 2;
+	}
+	if ((word & 0x1) == 0)
+		num += 1;
+	return num;
+}
+
+#endif /* _ASM_GENERIC_BITOPS___FFS_H_ */
diff --git a/tools/testing/radix-tree/linux/bitops/ffs.h b/tools/testing/radix-tree/linux/bitops/ffs.h
new file mode 100644
index 000000000..fbbb43af7
--- /dev/null
+++ b/tools/testing/radix-tree/linux/bitops/ffs.h
@@ -0,0 +1,41 @@
+#ifndef _ASM_GENERIC_BITOPS_FFS_H_
+#define _ASM_GENERIC_BITOPS_FFS_H_
+
+/**
+ * ffs - find first bit set
+ * @x: the word to search
+ *
+ * This is defined the same way as
+ * the libc and compiler builtin ffs routines, therefore
+ * differs in spirit from the above ffz (man ffs).
+ */
+static inline int ffs(int x)
+{
+	int r = 1;
+
+	if (!x)
+		return 0;
+	if (!(x & 0xffff)) {
+		x >>= 16;
+		r += 16;
+	}
+	if (!(x & 0xff)) {
+		x >>= 8;
+		r += 8;
+	}
+	if (!(x & 0xf)) {
+		x >>= 4;
+		r += 4;
+	}
+	if (!(x & 3)) {
+		x >>= 2;
+		r += 2;
+	}
+	if (!(x & 1)) {
+		x >>= 1;
+		r += 1;
+	}
+	return r;
+}
+
+#endif /* _ASM_GENERIC_BITOPS_FFS_H_ */
diff --git a/tools/testing/radix-tree/linux/bitops/ffz.h b/tools/testing/radix-tree/linux/bitops/ffz.h
new file mode 100644
index 000000000..6744bd4cd
--- /dev/null
+++ b/tools/testing/radix-tree/linux/bitops/ffz.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_GENERIC_BITOPS_FFZ_H_
+#define _ASM_GENERIC_BITOPS_FFZ_H_
+
+/*
+ * ffz - find first zero in word.
+ * @word: The word to search
+ *
+ * Undefined if no zero exists, so code should check against ~0UL first.
+ */
+#define ffz(x)  __ffs(~(x))
+
+#endif /* _ASM_GENERIC_BITOPS_FFZ_H_ */
diff --git a/tools/testing/radix-tree/linux/bitops/find.h b/tools/testing/radix-tree/linux/bitops/find.h
new file mode 100644
index 000000000..72a51e5a1
--- /dev/null
+++ b/tools/testing/radix-tree/linux/bitops/find.h
@@ -0,0 +1,13 @@
+#ifndef _ASM_GENERIC_BITOPS_FIND_H_
+#define _ASM_GENERIC_BITOPS_FIND_H_
+
+extern unsigned long find_next_bit(const unsigned long *addr, unsigned long
+		size, unsigned long offset);
+
+extern unsigned long find_next_zero_bit(const unsigned long *addr, unsigned
+		long size, unsigned long offset);
+
+#define find_first_bit(addr, size) find_next_bit((addr), (size), 0)
+#define find_first_zero_bit(addr, size) find_next_zero_bit((addr), (size), 0)
+
+#endif /*_ASM_GENERIC_BITOPS_FIND_H_ */
diff --git a/tools/testing/radix-tree/linux/bitops/fls.h b/tools/testing/radix-tree/linux/bitops/fls.h
new file mode 100644
index 000000000..850859bc5
--- /dev/null
+++ b/tools/testing/radix-tree/linux/bitops/fls.h
@@ -0,0 +1,41 @@
+#ifndef _ASM_GENERIC_BITOPS_FLS_H_
+#define _ASM_GENERIC_BITOPS_FLS_H_
+
+/**
+ * fls - find last (most-significant) bit set
+ * @x: the word to search
+ *
+ * This is defined the same way as ffs.
+ * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
+ */
+
+static inline int fls(int x)
+{
+	int r = 32;
+
+	if (!x)
+		return 0;
+	if (!(x & 0xffff0000u)) {
+		x <<= 16;
+		r -= 16;
+	}
+	if (!(x & 0xff000000u)) {
+		x <<= 8;
+		r -= 8;
+	}
+	if (!(x & 0xf0000000u)) {
+		x <<= 4;
+		r -= 4;
+	}
+	if (!(x & 0xc0000000u)) {
+		x <<= 2;
+		r -= 2;
+	}
+	if (!(x & 0x80000000u)) {
+		x <<= 1;
+		r -= 1;
+	}
+	return r;
+}
+
+#endif /* _ASM_GENERIC_BITOPS_FLS_H_ */
diff --git a/tools/testing/radix-tree/linux/bitops/fls64.h b/tools/testing/radix-tree/linux/bitops/fls64.h
new file mode 100644
index 000000000..1b6b17ce2
--- /dev/null
+++ b/tools/testing/radix-tree/linux/bitops/fls64.h
@@ -0,0 +1,14 @@
+#ifndef _ASM_GENERIC_BITOPS_FLS64_H_
+#define _ASM_GENERIC_BITOPS_FLS64_H_
+
+#include <asm/types.h>
+
+static inline int fls64(__u64 x)
+{
+	__u32 h = x >> 32;
+	if (h)
+		return fls(h) + 32;
+	return fls(x);
+}
+
+#endif /* _ASM_GENERIC_BITOPS_FLS64_H_ */
diff --git a/tools/testing/radix-tree/linux/bitops/hweight.h b/tools/testing/radix-tree/linux/bitops/hweight.h
new file mode 100644
index 000000000..fbbc38377
--- /dev/null
+++ b/tools/testing/radix-tree/linux/bitops/hweight.h
@@ -0,0 +1,11 @@
+#ifndef _ASM_GENERIC_BITOPS_HWEIGHT_H_
+#define _ASM_GENERIC_BITOPS_HWEIGHT_H_
+
+#include <asm/types.h>
+
+extern unsigned int hweight32(unsigned int w);
+extern unsigned int hweight16(unsigned int w);
+extern unsigned int hweight8(unsigned int w);
+extern unsigned long hweight64(__u64 w);
+
+#endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/tools/testing/radix-tree/linux/bitops/le.h b/tools/testing/radix-tree/linux/bitops/le.h
new file mode 100644
index 000000000..b9c7e5d2d
--- /dev/null
+++ b/tools/testing/radix-tree/linux/bitops/le.h
@@ -0,0 +1,53 @@
+#ifndef _ASM_GENERIC_BITOPS_LE_H_
+#define _ASM_GENERIC_BITOPS_LE_H_
+
+#include <asm/types.h>
+#include <asm/byteorder.h>
+
+#define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)
+#define BITOP_LE_SWIZZLE	((BITS_PER_LONG-1) & ~0x7)
+
+#if defined(__LITTLE_ENDIAN)
+
+#define generic_test_le_bit(nr, addr) test_bit(nr, addr)
+#define generic___set_le_bit(nr, addr) __set_bit(nr, addr)
+#define generic___clear_le_bit(nr, addr) __clear_bit(nr, addr)
+
+#define generic_test_and_set_le_bit(nr, addr) test_and_set_bit(nr, addr)
+#define generic_test_and_clear_le_bit(nr, addr) test_and_clear_bit(nr, addr)
+
+#define generic___test_and_set_le_bit(nr, addr) __test_and_set_bit(nr, addr)
+#define generic___test_and_clear_le_bit(nr, addr) __test_and_clear_bit(nr, addr)
+
+#define generic_find_next_zero_le_bit(addr, size, offset) find_next_zero_bit(addr, size, offset)
+
+#elif defined(__BIG_ENDIAN)
+
+#define generic_test_le_bit(nr, addr) \
+	test_bit((nr) ^ BITOP_LE_SWIZZLE, (addr))
+#define generic___set_le_bit(nr, addr) \
+	__set_bit((nr) ^ BITOP_LE_SWIZZLE, (addr))
+#define generic___clear_le_bit(nr, addr) \
+	__clear_bit((nr) ^ BITOP_LE_SWIZZLE, (addr))
+
+#define generic_test_and_set_le_bit(nr, addr) \
+	test_and_set_bit((nr) ^ BITOP_LE_SWIZZLE, (addr))
+#define generic_test_and_clear_le_bit(nr, addr) \
+	test_and_clear_bit((nr) ^ BITOP_LE_SWIZZLE, (addr))
+
+#define generic___test_and_set_le_bit(nr, addr) \
+	__test_and_set_bit((nr) ^ BITOP_LE_SWIZZLE, (addr))
+#define generic___test_and_clear_le_bit(nr, addr) \
+	__test_and_clear_bit((nr) ^ BITOP_LE_SWIZZLE, (addr))
+
+extern unsigned long generic_find_next_zero_le_bit(const unsigned long *addr,
+		unsigned long size, unsigned long offset);
+
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+
+#define generic_find_first_zero_le_bit(addr, size) \
+        generic_find_next_zero_le_bit((addr), (size), 0)
+
+#endif /* _ASM_GENERIC_BITOPS_LE_H_ */
diff --git a/tools/testing/radix-tree/linux/bitops/non-atomic.h b/tools/testing/radix-tree/linux/bitops/non-atomic.h
new file mode 100644
index 000000000..46a825cf2
--- /dev/null
+++ b/tools/testing/radix-tree/linux/bitops/non-atomic.h
@@ -0,0 +1,111 @@
+#ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
+#define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
+
+#include <asm/types.h>
+
+#define BITOP_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
+#define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)
+
+/**
+ * __set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike set_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static inline void __set_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BITOP_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
+
+	*p  |= mask;
+}
+
+static inline void __clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BITOP_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
+
+	*p &= ~mask;
+}
+
+/**
+ * __change_bit - Toggle a bit in memory
+ * @nr: the bit to change
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static inline void __change_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BITOP_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
+
+	*p ^= mask;
+}
+
+/**
+ * __test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BITOP_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old | mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * __test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BITOP_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old & ~mask;
+	return (old & mask) != 0;
+}
+
+/* WARNING: non atomic and it can be reordered! */
+static inline int __test_and_change_bit(int nr,
+					    volatile unsigned long *addr)
+{
+	unsigned long mask = BITOP_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old ^ mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static inline int test_bit(int nr, const volatile unsigned long *addr)
+{
+	return 1UL & (addr[BITOP_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
+}
+
+#endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
diff --git a/tools/testing/radix-tree/linux/bug.h b/tools/testing/radix-tree/linux/bug.h
new file mode 100644
index 000000000..ccbe44497
--- /dev/null
+++ b/tools/testing/radix-tree/linux/bug.h
@@ -0,0 +1 @@
+#define WARN_ON_ONCE(x)		assert(x)
diff --git a/tools/testing/radix-tree/linux/cpu.h b/tools/testing/radix-tree/linux/cpu.h
new file mode 100644
index 000000000..60a40459f
--- /dev/null
+++ b/tools/testing/radix-tree/linux/cpu.h
@@ -0,0 +1,34 @@
+
+#define hotcpu_notifier(a, b)
+
+#define CPU_ONLINE		0x0002 /* CPU (unsigned)v is up */
+#define CPU_UP_PREPARE		0x0003 /* CPU (unsigned)v coming up */
+#define CPU_UP_CANCELED		0x0004 /* CPU (unsigned)v NOT coming up */
+#define CPU_DOWN_PREPARE	0x0005 /* CPU (unsigned)v going down */
+#define CPU_DOWN_FAILED		0x0006 /* CPU (unsigned)v NOT going down */
+#define CPU_DEAD		0x0007 /* CPU (unsigned)v dead */
+#define CPU_DYING		0x0008 /* CPU (unsigned)v not running any task,
+					* not handling interrupts, soon dead.
+					* Called on the dying cpu, interrupts
+					* are already disabled. Must not
+					* sleep, must not fail */
+#define CPU_POST_DEAD		0x0009 /* CPU (unsigned)v dead, cpu_hotplug
+					* lock is dropped */
+#define CPU_STARTING		0x000A /* CPU (unsigned)v soon running.
+					* Called on the new cpu, just before
+					* enabling interrupts. Must not sleep,
+					* must not fail */
+#define CPU_DYING_IDLE		0x000B /* CPU (unsigned)v dying, reached
+					* idle loop. */
+#define CPU_BROKEN		0x000C /* CPU (unsigned)v did not die properly,
+					* perhaps due to preemption. */
+#define CPU_TASKS_FROZEN	0x0010
+
+#define CPU_ONLINE_FROZEN	(CPU_ONLINE | CPU_TASKS_FROZEN)
+#define CPU_UP_PREPARE_FROZEN	(CPU_UP_PREPARE | CPU_TASKS_FROZEN)
+#define CPU_UP_CANCELED_FROZEN  (CPU_UP_CANCELED | CPU_TASKS_FROZEN)
+#define CPU_DOWN_PREPARE_FROZEN (CPU_DOWN_PREPARE | CPU_TASKS_FROZEN)
+#define CPU_DOWN_FAILED_FROZEN  (CPU_DOWN_FAILED | CPU_TASKS_FROZEN)
+#define CPU_DEAD_FROZEN		(CPU_DEAD | CPU_TASKS_FROZEN)
+#define CPU_DYING_FROZEN	(CPU_DYING | CPU_TASKS_FROZEN)
+#define CPU_STARTING_FROZEN	(CPU_STARTING | CPU_TASKS_FROZEN)
diff --git a/tools/testing/radix-tree/linux/export.h b/tools/testing/radix-tree/linux/export.h
new file mode 100644
index 000000000..b6afd1319
--- /dev/null
+++ b/tools/testing/radix-tree/linux/export.h
@@ -0,0 +1,2 @@
+
+#define EXPORT_SYMBOL(sym)
diff --git a/tools/testing/radix-tree/linux/gfp.h b/tools/testing/radix-tree/linux/gfp.h
new file mode 100644
index 000000000..0e37f7a76
--- /dev/null
+++ b/tools/testing/radix-tree/linux/gfp.h
@@ -0,0 +1,10 @@
+#ifndef _GFP_H
+#define _GFP_H
+
+#define __GFP_BITS_SHIFT 22
+#define __GFP_BITS_MASK ((gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
+#define __GFP_WAIT 1
+#define __GFP_ACCOUNT 0
+#define __GFP_NOWARN 0
+
+#endif
diff --git a/tools/testing/radix-tree/linux/kernel.h b/tools/testing/radix-tree/linux/kernel.h
new file mode 100644
index 000000000..ae013b016
--- /dev/null
+++ b/tools/testing/radix-tree/linux/kernel.h
@@ -0,0 +1,35 @@
+#ifndef _KERNEL_H
+#define _KERNEL_H
+
+#include <assert.h>
+#include <string.h>
+#include <stdio.h>
+#include <stddef.h>
+#include <limits.h>
+
+#ifndef NULL
+#define NULL	0
+#endif
+
+#define BUG_ON(expr)	assert(!(expr))
+#define __init
+#define __must_check
+#define panic(expr)
+#define printk printf
+#define __force
+#define likely(c) (c)
+#define unlikely(c) (c)
+#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+#define container_of(ptr, type, member) ({                      \
+	const typeof( ((type *)0)->member ) *__mptr = (ptr);    \
+	(type *)( (char *)__mptr - offsetof(type, member) );})
+#define min(a, b) ((a) < (b) ? (a) : (b))
+
+static inline int in_interrupt(void)
+{
+	return 0;
+}
+#endif /* _KERNEL_H */
diff --git a/tools/testing/radix-tree/linux/kmemleak.h b/tools/testing/radix-tree/linux/kmemleak.h
new file mode 100644
index 000000000..155f11278
--- /dev/null
+++ b/tools/testing/radix-tree/linux/kmemleak.h
@@ -0,0 +1 @@
+static inline void kmemleak_update_trace(const void *ptr) { }
diff --git a/tools/testing/radix-tree/linux/mempool.h b/tools/testing/radix-tree/linux/mempool.h
new file mode 100644
index 000000000..6a2dc55b4
--- /dev/null
+++ b/tools/testing/radix-tree/linux/mempool.h
@@ -0,0 +1,16 @@
+
+#include <linux/slab.h>
+
+typedef void *(mempool_alloc_t)(int gfp_mask, void *pool_data);
+typedef void (mempool_free_t)(void *element, void *pool_data);
+
+typedef struct {
+	mempool_alloc_t *alloc;
+	mempool_free_t *free;
+	void *data;
+} mempool_t;
+
+void *mempool_alloc(mempool_t *pool, int gfp_mask);
+void mempool_free(void *element, mempool_t *pool);
+mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn,
+			mempool_free_t *free_fn, void *pool_data);
diff --git a/tools/testing/radix-tree/linux/notifier.h b/tools/testing/radix-tree/linux/notifier.h
new file mode 100644
index 000000000..70e4797d5
--- /dev/null
+++ b/tools/testing/radix-tree/linux/notifier.h
@@ -0,0 +1,8 @@
+#ifndef _NOTIFIER_H
+#define _NOTIFIER_H
+
+struct notifier_block;
+
+#define NOTIFY_OK              0x0001          /* Suits me */
+
+#endif
diff --git a/tools/testing/radix-tree/linux/percpu.h b/tools/testing/radix-tree/linux/percpu.h
new file mode 100644
index 000000000..5837f1d56
--- /dev/null
+++ b/tools/testing/radix-tree/linux/percpu.h
@@ -0,0 +1,7 @@
+
+#define DEFINE_PER_CPU(type, val) type val
+
+#define __get_cpu_var(var)	var
+#define this_cpu_ptr(var)	var
+#define per_cpu_ptr(ptr, cpu)   ({ (void)(cpu); (ptr); })
+#define per_cpu(var, cpu)	(*per_cpu_ptr(&(var), cpu))
diff --git a/tools/testing/radix-tree/linux/preempt.h b/tools/testing/radix-tree/linux/preempt.h
new file mode 100644
index 000000000..6210672e3
--- /dev/null
+++ b/tools/testing/radix-tree/linux/preempt.h
@@ -0,0 +1,4 @@
+/* */
+
+#define preempt_disable() do { } while (0)
+#define preempt_enable() do { } while (0)
diff --git a/tools/testing/radix-tree/linux/radix-tree.h b/tools/testing/radix-tree/linux/radix-tree.h
new file mode 100644
index 000000000..ce694ddd4
--- /dev/null
+++ b/tools/testing/radix-tree/linux/radix-tree.h
@@ -0,0 +1 @@
+#include "../../../../include/linux/radix-tree.h"
diff --git a/tools/testing/radix-tree/linux/rcupdate.h b/tools/testing/radix-tree/linux/rcupdate.h
new file mode 100644
index 000000000..f7129ea2a
--- /dev/null
+++ b/tools/testing/radix-tree/linux/rcupdate.h
@@ -0,0 +1,9 @@
+#ifndef _RCUPDATE_H
+#define _RCUPDATE_H
+
+#include <urcu.h>
+
+#define rcu_dereference_raw(p) rcu_dereference(p)
+#define rcu_dereference_protected(p, cond) rcu_dereference(p)
+
+#endif
diff --git a/tools/testing/radix-tree/linux/slab.h b/tools/testing/radix-tree/linux/slab.h
new file mode 100644
index 000000000..57282506c
--- /dev/null
+++ b/tools/testing/radix-tree/linux/slab.h
@@ -0,0 +1,28 @@
+#ifndef SLAB_H
+#define SLAB_H
+
+#include <linux/types.h>
+
+#define GFP_KERNEL 1
+#define SLAB_HWCACHE_ALIGN 1
+#define SLAB_PANIC 2
+#define SLAB_RECLAIM_ACCOUNT    0x00020000UL            /* Objects are reclaimable */
+
+static inline int gfpflags_allow_blocking(gfp_t mask)
+{
+	return 1;
+}
+
+struct kmem_cache {
+	int size;
+	void (*ctor)(void *);
+};
+
+void *kmem_cache_alloc(struct kmem_cache *cachep, int flags);
+void kmem_cache_free(struct kmem_cache *cachep, void *objp);
+
+struct kmem_cache *
+kmem_cache_create(const char *name, size_t size, size_t offset,
+	unsigned long flags, void (*ctor)(void *));
+
+#endif		/* SLAB_H */
diff --git a/tools/testing/radix-tree/linux/types.h b/tools/testing/radix-tree/linux/types.h
new file mode 100644
index 000000000..72a9d85f6
--- /dev/null
+++ b/tools/testing/radix-tree/linux/types.h
@@ -0,0 +1,28 @@
+#ifndef _TYPES_H
+#define _TYPES_H
+
+#define __rcu
+#define __read_mostly
+
+#define BITS_PER_LONG (sizeof(long) * 8)
+
+struct list_head {
+	struct list_head *next, *prev;
+};
+
+static inline void INIT_LIST_HEAD(struct list_head *list)
+{
+	list->next = list;
+	list->prev = list;
+}
+
+typedef struct {
+	unsigned int x;
+} spinlock_t;
+
+#define uninitialized_var(x) x = x
+
+typedef unsigned gfp_t;
+#include <linux/gfp.h>
+
+#endif
diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c
new file mode 100644
index 000000000..0e83cad27
--- /dev/null
+++ b/tools/testing/radix-tree/main.c
@@ -0,0 +1,272 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <time.h>
+#include <assert.h>
+
+#include <linux/slab.h>
+#include <linux/radix-tree.h>
+
+#include "test.h"
+#include "regression.h"
+
+void __gang_check(unsigned long middle, long down, long up, int chunk, int hop)
+{
+	long idx;
+	RADIX_TREE(tree, GFP_KERNEL);
+
+	middle = 1 << 30;
+
+	for (idx = -down; idx < up; idx++)
+		item_insert(&tree, middle + idx);
+
+	item_check_absent(&tree, middle - down - 1);
+	for (idx = -down; idx < up; idx++)
+		item_check_present(&tree, middle + idx);
+	item_check_absent(&tree, middle + up);
+
+	item_gang_check_present(&tree, middle - down,
+			up + down, chunk, hop);
+	item_full_scan(&tree, middle - down, down + up, chunk);
+	item_kill_tree(&tree);
+}
+
+void gang_check(void)
+{
+	__gang_check(1 << 30, 128, 128, 35, 2);
+	__gang_check(1 << 31, 128, 128, 32, 32);
+	__gang_check(1 << 31, 128, 128, 32, 100);
+	__gang_check(1 << 31, 128, 128, 17, 7);
+	__gang_check(0xffff0000, 0, 65536, 17, 7);
+	__gang_check(0xfffffffe, 1, 1, 17, 7);
+}
+
+void __big_gang_check(void)
+{
+	unsigned long start;
+	int wrapped = 0;
+
+	start = 0;
+	do {
+		unsigned long old_start;
+
+//		printf("0x%08lx\n", start);
+		__gang_check(start, rand() % 113 + 1, rand() % 71,
+				rand() % 157, rand() % 91 + 1);
+		old_start = start;
+		start += rand() % 1000000;
+		start %= 1ULL << 33;
+		if (start < old_start)
+			wrapped = 1;
+	} while (!wrapped);
+}
+
+void big_gang_check(void)
+{
+	int i;
+
+	for (i = 0; i < 1000; i++) {
+		__big_gang_check();
+		srand(time(0));
+		printf("%d ", i);
+		fflush(stdout);
+	}
+}
+
+void add_and_check(void)
+{
+	RADIX_TREE(tree, GFP_KERNEL);
+
+	item_insert(&tree, 44);
+	item_check_present(&tree, 44);
+	item_check_absent(&tree, 43);
+	item_kill_tree(&tree);
+}
+
+void dynamic_height_check(void)
+{
+	int i;
+	RADIX_TREE(tree, GFP_KERNEL);
+	tree_verify_min_height(&tree, 0);
+
+	item_insert(&tree, 42);
+	tree_verify_min_height(&tree, 42);
+
+	item_insert(&tree, 1000000);
+	tree_verify_min_height(&tree, 1000000);
+
+	assert(item_delete(&tree, 1000000));
+	tree_verify_min_height(&tree, 42);
+
+	assert(item_delete(&tree, 42));
+	tree_verify_min_height(&tree, 0);
+
+	for (i = 0; i < 1000; i++) {
+		item_insert(&tree, i);
+		tree_verify_min_height(&tree, i);
+	}
+
+	i--;
+	for (;;) {
+		assert(item_delete(&tree, i));
+		if (i == 0) {
+			tree_verify_min_height(&tree, 0);
+			break;
+		}
+		i--;
+		tree_verify_min_height(&tree, i);
+	}
+
+	item_kill_tree(&tree);
+}
+
+void check_copied_tags(struct radix_tree_root *tree, unsigned long start, unsigned long end, unsigned long *idx, int count, int fromtag, int totag)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+/*		if (i % 1000 == 0)
+			putchar('.'); */
+		if (idx[i] < start || idx[i] > end) {
+			if (item_tag_get(tree, idx[i], totag)) {
+				printf("%lu-%lu: %lu, tags %d-%d\n", start, end, idx[i], item_tag_get(tree, idx[i], fromtag), item_tag_get(tree, idx[i], totag));
+			}
+			assert(!item_tag_get(tree, idx[i], totag));
+			continue;
+		}
+		if (item_tag_get(tree, idx[i], fromtag) ^
+			item_tag_get(tree, idx[i], totag)) {
+			printf("%lu-%lu: %lu, tags %d-%d\n", start, end, idx[i], item_tag_get(tree, idx[i], fromtag), item_tag_get(tree, idx[i], totag));
+		}
+		assert(!(item_tag_get(tree, idx[i], fromtag) ^
+			 item_tag_get(tree, idx[i], totag)));
+	}
+}
+
+#define ITEMS 50000
+
+void copy_tag_check(void)
+{
+	RADIX_TREE(tree, GFP_KERNEL);
+	unsigned long idx[ITEMS];
+	unsigned long start, end, count = 0, tagged, cur, tmp;
+	int i;
+
+//	printf("generating radix tree indices...\n");
+	start = rand();
+	end = rand();
+	if (start > end && (rand() % 10)) {
+		cur = start;
+		start = end;
+		end = cur;
+	}
+	/* Specifically create items around the start and the end of the range
+	 * with high probability to check for off by one errors */
+	cur = rand();
+	if (cur & 1) {
+		item_insert(&tree, start);
+		if (cur & 2) {
+			if (start <= end)
+				count++;
+			item_tag_set(&tree, start, 0);
+		}
+	}
+	if (cur & 4) {
+		item_insert(&tree, start-1);
+		if (cur & 8)
+			item_tag_set(&tree, start-1, 0);
+	}
+	if (cur & 16) {
+		item_insert(&tree, end);
+		if (cur & 32) {
+			if (start <= end)
+				count++;
+			item_tag_set(&tree, end, 0);
+		}
+	}
+	if (cur & 64) {
+		item_insert(&tree, end+1);
+		if (cur & 128)
+			item_tag_set(&tree, end+1, 0);
+	}
+
+	for (i = 0; i < ITEMS; i++) {
+		do {
+			idx[i] = rand();
+		} while (item_lookup(&tree, idx[i]));
+
+		item_insert(&tree, idx[i]);
+		if (rand() & 1) {
+			item_tag_set(&tree, idx[i], 0);
+			if (idx[i] >= start && idx[i] <= end)
+				count++;
+		}
+/*		if (i % 1000 == 0)
+			putchar('.'); */
+	}
+
+//	printf("\ncopying tags...\n");
+	cur = start;
+	tagged = radix_tree_range_tag_if_tagged(&tree, &cur, end, ITEMS, 0, 1);
+
+//	printf("checking copied tags\n");
+	assert(tagged == count);
+	check_copied_tags(&tree, start, end, idx, ITEMS, 0, 1);
+
+	/* Copy tags in several rounds */
+//	printf("\ncopying tags...\n");
+	cur = start;
+	do {
+		tmp = rand() % (count/10+2);
+		tagged = radix_tree_range_tag_if_tagged(&tree, &cur, end, tmp, 0, 2);
+	} while (tmp == tagged);
+
+//	printf("%lu %lu %lu\n", tagged, tmp, count);
+//	printf("checking copied tags\n");
+	check_copied_tags(&tree, start, end, idx, ITEMS, 0, 2);
+	assert(tagged < tmp);
+	verify_tag_consistency(&tree, 0);
+	verify_tag_consistency(&tree, 1);
+	verify_tag_consistency(&tree, 2);
+//	printf("\n");
+	item_kill_tree(&tree);
+}
+
+static void single_thread_tests(void)
+{
+	int i;
+
+	tag_check();
+	printf("after tag_check: %d allocated\n", nr_allocated);
+	gang_check();
+	printf("after gang_check: %d allocated\n", nr_allocated);
+	add_and_check();
+	printf("after add_and_check: %d allocated\n", nr_allocated);
+	dynamic_height_check();
+	printf("after dynamic_height_check: %d allocated\n", nr_allocated);
+	big_gang_check();
+	printf("after big_gang_check: %d allocated\n", nr_allocated);
+	for (i = 0; i < 2000; i++) {
+		copy_tag_check();
+		printf("%d ", i);
+		fflush(stdout);
+	}
+	printf("after copy_tag_check: %d allocated\n", nr_allocated);
+}
+
+int main(void)
+{
+	rcu_register_thread();
+	radix_tree_init();
+
+	regression1_test();
+	regression2_test();
+	regression3_test();
+	single_thread_tests();
+
+	sleep(1);
+	printf("after sleep(1): %d allocated\n", nr_allocated);
+	rcu_unregister_thread();
+
+	exit(0);
+}
diff --git a/tools/testing/radix-tree/rcupdate.c b/tools/testing/radix-tree/rcupdate.c
new file mode 100644
index 000000000..31a2d1422
--- /dev/null
+++ b/tools/testing/radix-tree/rcupdate.c
@@ -0,0 +1,86 @@
+#include <linux/rcupdate.h>
+#include <pthread.h>
+#include <stdio.h>
+#include <assert.h>
+
+static pthread_mutex_t rculock = PTHREAD_MUTEX_INITIALIZER;
+static struct rcu_head *rcuhead_global = NULL;
+static __thread int nr_rcuhead = 0;
+static __thread struct rcu_head *rcuhead = NULL;
+static __thread struct rcu_head *rcutail = NULL;
+
+static pthread_cond_t rcu_worker_cond = PTHREAD_COND_INITIALIZER;
+
+/* switch to urcu implementation when it is merged. */
+void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *head))
+{
+	head->func = func;
+	head->next = rcuhead;
+	rcuhead = head;
+	if (!rcutail)
+		rcutail = head;
+	nr_rcuhead++;
+	if (nr_rcuhead >= 1000) {
+		int signal = 0;
+
+		pthread_mutex_lock(&rculock);
+		if (!rcuhead_global)
+			signal = 1;
+		rcutail->next = rcuhead_global;
+		rcuhead_global = head;
+		pthread_mutex_unlock(&rculock);
+
+		nr_rcuhead = 0;
+		rcuhead = NULL;
+		rcutail = NULL;
+
+		if (signal) {
+			pthread_cond_signal(&rcu_worker_cond);
+		}
+	}
+}
+
+static void *rcu_worker(void *arg)
+{
+	struct rcu_head *r;
+
+	rcupdate_thread_init();
+
+	while (1) {
+		pthread_mutex_lock(&rculock);
+		while (!rcuhead_global) {
+			pthread_cond_wait(&rcu_worker_cond, &rculock);
+		}
+		r = rcuhead_global;
+		rcuhead_global = NULL;
+
+		pthread_mutex_unlock(&rculock);
+
+		synchronize_rcu();
+
+		while (r) {
+			struct rcu_head *tmp = r->next;
+			r->func(r);
+			r = tmp;
+		}
+	}
+
+	rcupdate_thread_exit();
+
+	return NULL;
+}
+
+static pthread_t worker_thread;
+void rcupdate_init(void)
+{
+	pthread_create(&worker_thread, NULL, rcu_worker, NULL);
+}
+
+void rcupdate_thread_init(void)
+{
+	rcu_register_thread();
+}
+void rcupdate_thread_exit(void)
+{
+	rcu_unregister_thread();
+}
diff --git a/tools/testing/radix-tree/regression.h b/tools/testing/radix-tree/regression.h
new file mode 100644
index 000000000..e018c4816
--- /dev/null
+++ b/tools/testing/radix-tree/regression.h
@@ -0,0 +1,8 @@
+#ifndef __REGRESSION_H__
+#define __REGRESSION_H__
+
+void regression1_test(void);
+void regression2_test(void);
+void regression3_test(void);
+
+#endif
diff --git a/tools/testing/radix-tree/regression1.c b/tools/testing/radix-tree/regression1.c
new file mode 100644
index 000000000..2d03a63bb
--- /dev/null
+++ b/tools/testing/radix-tree/regression1.c
@@ -0,0 +1,220 @@
+/*
+ * Regression1
+ * Description:
+ * Salman Qazi describes the following radix-tree bug:
+ *
+ * In the following case, we get can get a deadlock:
+ *
+ * 0.  The radix tree contains two items, one has the index 0.
+ * 1.  The reader (in this case find_get_pages) takes the rcu_read_lock.
+ * 2.  The reader acquires slot(s) for item(s) including the index 0 item.
+ * 3.  The non-zero index item is deleted, and as a consequence the other item
+ *     is moved to the root of the tree. The place where it used to be is queued
+ *     for deletion after the readers finish.
+ * 3b. The zero item is deleted, removing it from the direct slot, it remains in
+ *     the rcu-delayed indirect node.
+ * 4.  The reader looks at the index 0 slot, and finds that the page has 0 ref
+ *     count
+ * 5.  The reader looks at it again, hoping that the item will either be freed
+ *     or the ref count will increase. This never happens, as the slot it is
+ *     looking at will never be updated. Also, this slot can never be reclaimed
+ *     because the reader is holding rcu_read_lock and is in an infinite loop.
+ *
+ * The fix is to re-use the same "indirect" pointer case that requires a slot
+ * lookup retry into a general "retry the lookup" bit.
+ *
+ * Running:
+ * This test should run to completion in a few seconds. The above bug would
+ * cause it to hang indefinitely.
+ *
+ * Upstream commit:
+ * Not yet
+ */
+#include <linux/kernel.h>
+#include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/radix-tree.h>
+#include <linux/rcupdate.h>
+#include <stdlib.h>
+#include <pthread.h>
+#include <stdio.h>
+#include <assert.h>
+
+#include "regression.h"
+
+static RADIX_TREE(mt_tree, GFP_KERNEL);
+static pthread_mutex_t mt_lock;
+
+struct page {
+	pthread_mutex_t lock;
+	struct rcu_head rcu;
+	int count;
+	unsigned long index;
+};
+
+static struct page *page_alloc(void)
+{
+	struct page *p;
+	p = malloc(sizeof(struct page));
+	p->count = 1;
+	p->index = 1;
+	pthread_mutex_init(&p->lock, NULL);
+
+	return p;
+}
+
+static void page_rcu_free(struct rcu_head *rcu)
+{
+	struct page *p = container_of(rcu, struct page, rcu);
+	assert(!p->count);
+	pthread_mutex_destroy(&p->lock);
+	free(p);
+}
+
+static void page_free(struct page *p)
+{
+	call_rcu(&p->rcu, page_rcu_free);
+}
+
+static unsigned find_get_pages(unsigned long start,
+			    unsigned int nr_pages, struct page **pages)
+{
+	unsigned int i;
+	unsigned int ret;
+	unsigned int nr_found;
+
+	rcu_read_lock();
+restart:
+	nr_found = radix_tree_gang_lookup_slot(&mt_tree,
+				(void ***)pages, NULL, start, nr_pages);
+	ret = 0;
+	for (i = 0; i < nr_found; i++) {
+		struct page *page;
+repeat:
+		page = radix_tree_deref_slot((void **)pages[i]);
+		if (unlikely(!page))
+			continue;
+
+		if (radix_tree_exception(page)) {
+			if (radix_tree_deref_retry(page)) {
+				/*
+				 * Transient condition which can only trigger
+				 * when entry at index 0 moves out of or back
+				 * to root: none yet gotten, safe to restart.
+				 */
+				assert((start | i) == 0);
+				goto restart;
+			}
+			/*
+			 * No exceptional entries are inserted in this test.
+			 */
+			assert(0);
+		}
+
+		pthread_mutex_lock(&page->lock);
+		if (!page->count) {
+			pthread_mutex_unlock(&page->lock);
+			goto repeat;
+		}
+		/* don't actually update page refcount */
+		pthread_mutex_unlock(&page->lock);
+
+		/* Has the page moved? */
+		if (unlikely(page != *((void **)pages[i]))) {
+			goto repeat;
+		}
+
+		pages[ret] = page;
+		ret++;
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+static pthread_barrier_t worker_barrier;
+
+static void *regression1_fn(void *arg)
+{
+	rcu_register_thread();
+
+	if (pthread_barrier_wait(&worker_barrier) ==
+			PTHREAD_BARRIER_SERIAL_THREAD) {
+		int j;
+
+		for (j = 0; j < 1000000; j++) {
+			struct page *p;
+
+			p = page_alloc();
+			pthread_mutex_lock(&mt_lock);
+			radix_tree_insert(&mt_tree, 0, p);
+			pthread_mutex_unlock(&mt_lock);
+
+			p = page_alloc();
+			pthread_mutex_lock(&mt_lock);
+			radix_tree_insert(&mt_tree, 1, p);
+			pthread_mutex_unlock(&mt_lock);
+
+			pthread_mutex_lock(&mt_lock);
+			p = radix_tree_delete(&mt_tree, 1);
+			pthread_mutex_lock(&p->lock);
+			p->count--;
+			pthread_mutex_unlock(&p->lock);
+			pthread_mutex_unlock(&mt_lock);
+			page_free(p);
+
+			pthread_mutex_lock(&mt_lock);
+			p = radix_tree_delete(&mt_tree, 0);
+			pthread_mutex_lock(&p->lock);
+			p->count--;
+			pthread_mutex_unlock(&p->lock);
+			pthread_mutex_unlock(&mt_lock);
+			page_free(p);
+		}
+	} else {
+		int j;
+
+		for (j = 0; j < 100000000; j++) {
+			struct page *pages[10];
+
+			find_get_pages(0, 10, pages);
+		}
+	}
+
+	rcu_unregister_thread();
+
+	return NULL;
+}
+
+static pthread_t *threads;
+void regression1_test(void)
+{
+	int nr_threads;
+	int i;
+	long arg;
+
+	/* Regression #1 */
+	printf("running regression test 1, should finish in under a minute\n");
+	nr_threads = 2;
+	pthread_barrier_init(&worker_barrier, NULL, nr_threads);
+
+	threads = malloc(nr_threads * sizeof(pthread_t *));
+
+	for (i = 0; i < nr_threads; i++) {
+		arg = i;
+		if (pthread_create(&threads[i], NULL, regression1_fn, (void *)arg)) {
+			perror("pthread_create");
+			exit(1);
+		}
+	}
+
+	for (i = 0; i < nr_threads; i++) {
+		if (pthread_join(threads[i], NULL)) {
+			perror("pthread_join");
+			exit(1);
+		}
+	}
+
+	free(threads);
+
+	printf("regression test 1, done\n");
+}
diff --git a/tools/testing/radix-tree/regression2.c b/tools/testing/radix-tree/regression2.c
new file mode 100644
index 000000000..5d2fa28cd
--- /dev/null
+++ b/tools/testing/radix-tree/regression2.c
@@ -0,0 +1,126 @@
+/*
+ * Regression2
+ * Description:
+ * Toshiyuki Okajima describes the following radix-tree bug:
+ *
+ * In the following case, we can get a hangup on
+ *   radix_radix_tree_gang_lookup_tag_slot.
+ *
+ * 0.  The radix tree contains RADIX_TREE_MAP_SIZE items. And the tag of
+ *     a certain item has PAGECACHE_TAG_DIRTY.
+ * 1.  radix_tree_range_tag_if_tagged(, start, end, , PAGECACHE_TAG_DIRTY,
+ *     PAGECACHE_TAG_TOWRITE) is called to add PAGECACHE_TAG_TOWRITE tag
+ *     for the tag which has PAGECACHE_TAG_DIRTY. However, there is no tag with
+ *     PAGECACHE_TAG_DIRTY within the range from start to end. As the result,
+ *     There is no tag with PAGECACHE_TAG_TOWRITE but the root tag has
+ *     PAGECACHE_TAG_TOWRITE.
+ * 2.  An item is added into the radix tree and then the level of it is
+ *     extended into 2 from 1. At that time, the new radix tree node succeeds
+ *     the tag status of the root tag. Therefore the tag of the new radix tree
+ *     node has PAGECACHE_TAG_TOWRITE but there is not slot with
+ *     PAGECACHE_TAG_TOWRITE tag in the child node of the new radix tree node.
+ * 3.  The tag of a certain item is cleared with PAGECACHE_TAG_DIRTY.
+ * 4.  All items within the index range from 0 to RADIX_TREE_MAP_SIZE - 1 are
+ *     released. (Only the item which index is RADIX_TREE_MAP_SIZE exist in the
+ *     radix tree.) As the result, the slot of the radix tree node is NULL but
+ *     the tag which corresponds to the slot has PAGECACHE_TAG_TOWRITE.
+ * 5.  radix_tree_gang_lookup_tag_slot(PAGECACHE_TAG_TOWRITE) calls
+ *     __lookup_tag. __lookup_tag returns with 0. And __lookup_tag doesn't
+ *     change the index that is the input and output parameter. Because the 1st
+ *     slot of the radix tree node is NULL, but the tag which corresponds to
+ *     the slot has PAGECACHE_TAG_TOWRITE.
+ *     Therefore radix_tree_gang_lookup_tag_slot tries to get some items by
+ *     calling __lookup_tag, but it cannot get any items forever.
+ *
+ * The fix is to change that radix_tree_tag_if_tagged doesn't tag the root tag
+ * if it doesn't set any tags within the specified range.
+ *
+ * Running:
+ * This test should run to completion immediately. The above bug would cause it
+ * to hang indefinitely.
+ *
+ * Upstream commit:
+ * Not yet
+ */
+#include <linux/kernel.h>
+#include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/radix-tree.h>
+#include <stdlib.h>
+#include <stdio.h>
+
+#include "regression.h"
+
+#ifdef __KERNEL__
+#define RADIX_TREE_MAP_SHIFT    (CONFIG_BASE_SMALL ? 4 : 6)
+#else
+#define RADIX_TREE_MAP_SHIFT    3       /* For more stressful testing */
+#endif
+
+#define RADIX_TREE_MAP_SIZE     (1UL << RADIX_TREE_MAP_SHIFT)
+#define PAGECACHE_TAG_DIRTY     0
+#define PAGECACHE_TAG_WRITEBACK 1
+#define PAGECACHE_TAG_TOWRITE   2
+
+static RADIX_TREE(mt_tree, GFP_KERNEL);
+unsigned long page_count = 0;
+
+struct page {
+	unsigned long index;
+};
+
+static struct page *page_alloc(void)
+{
+	struct page *p;
+	p = malloc(sizeof(struct page));
+	p->index = page_count++;
+
+	return p;
+}
+
+void regression2_test(void)
+{
+	int i;
+	struct page *p;
+	int max_slots = RADIX_TREE_MAP_SIZE;
+	unsigned long int start, end;
+	struct page *pages[1];
+
+	printf("running regression test 2 (should take milliseconds)\n");
+	/* 0. */
+	for (i = 0; i <= max_slots - 1; i++) {
+		p = page_alloc();
+		radix_tree_insert(&mt_tree, i, p);
+	}
+	radix_tree_tag_set(&mt_tree, max_slots - 1, PAGECACHE_TAG_DIRTY);
+
+	/* 1. */
+	start = 0;
+	end = max_slots - 2;
+	radix_tree_range_tag_if_tagged(&mt_tree, &start, end, 1,
+				PAGECACHE_TAG_DIRTY, PAGECACHE_TAG_TOWRITE);
+
+	/* 2. */
+	p = page_alloc();
+	radix_tree_insert(&mt_tree, max_slots, p);
+
+	/* 3. */
+	radix_tree_tag_clear(&mt_tree, max_slots - 1, PAGECACHE_TAG_DIRTY);
+
+	/* 4. */
+	for (i = max_slots - 1; i >= 0; i--)
+		radix_tree_delete(&mt_tree, i);
+
+	/* 5. */
+	// NOTE: start should not be 0 because radix_tree_gang_lookup_tag_slot
+	//       can return.
+	start = 1;
+	end = max_slots - 2;
+	radix_tree_gang_lookup_tag_slot(&mt_tree, (void ***)pages, start, end,
+		PAGECACHE_TAG_TOWRITE);
+
+	/* We remove all the remained nodes */
+	radix_tree_delete(&mt_tree, max_slots);
+
+	printf("regression test 2, done\n");
+}
diff --git a/tools/testing/radix-tree/regression3.c b/tools/testing/radix-tree/regression3.c
new file mode 100644
index 000000000..1f06ed73d
--- /dev/null
+++ b/tools/testing/radix-tree/regression3.c
@@ -0,0 +1,117 @@
+/*
+ * Regression3
+ * Description:
+ * Helper radix_tree_iter_retry resets next_index to the current index.
+ * In following radix_tree_next_slot current chunk size becomes zero.
+ * This isn't checked and it tries to dereference null pointer in slot.
+ *
+ * Helper radix_tree_iter_next reset slot to NULL and next_index to index + 1,
+ * for tagger iteraction it also must reset cached tags in iterator to abort
+ * next radix_tree_next_slot and go to slow-path into radix_tree_next_chunk.
+ *
+ * Running:
+ * This test should run to completion immediately. The above bug would
+ * cause it to segfault.
+ *
+ * Upstream commit:
+ * Not yet
+ */
+#include <linux/kernel.h>
+#include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/radix-tree.h>
+#include <stdlib.h>
+#include <stdio.h>
+
+#include "regression.h"
+
+void regression3_test(void)
+{
+	RADIX_TREE(root, GFP_KERNEL);
+	void *ptr0 = (void *)4ul;
+	void *ptr = (void *)8ul;
+	struct radix_tree_iter iter;
+	void **slot;
+	bool first;
+
+	printf("running regression test 3 (should take milliseconds)\n");
+
+	radix_tree_insert(&root, 0, ptr0);
+	radix_tree_tag_set(&root, 0, 0);
+
+	first = true;
+	radix_tree_for_each_tagged(slot, &root, &iter, 0, 0) {
+		printf("tagged %ld %p\n", iter.index, *slot);
+		if (first) {
+			radix_tree_insert(&root, 1, ptr);
+			radix_tree_tag_set(&root, 1, 0);
+			first = false;
+		}
+		if (radix_tree_deref_retry(*slot)) {
+			printf("retry at %ld\n", iter.index);
+			slot = radix_tree_iter_retry(&iter);
+			continue;
+		}
+	}
+	radix_tree_delete(&root, 1);
+
+	first = true;
+	radix_tree_for_each_slot(slot, &root, &iter, 0) {
+		printf("slot %ld %p\n", iter.index, *slot);
+		if (first) {
+			radix_tree_insert(&root, 1, ptr);
+			first = false;
+		}
+		if (radix_tree_deref_retry(*slot)) {
+			printk("retry at %ld\n", iter.index);
+			slot = radix_tree_iter_retry(&iter);
+			continue;
+		}
+	}
+	radix_tree_delete(&root, 1);
+
+	first = true;
+	radix_tree_for_each_contig(slot, &root, &iter, 0) {
+		printk("contig %ld %p\n", iter.index, *slot);
+		if (first) {
+			radix_tree_insert(&root, 1, ptr);
+			first = false;
+		}
+		if (radix_tree_deref_retry(*slot)) {
+			printk("retry at %ld\n", iter.index);
+			slot = radix_tree_iter_retry(&iter);
+			continue;
+		}
+	}
+
+	radix_tree_for_each_slot(slot, &root, &iter, 0) {
+		printf("slot %ld %p\n", iter.index, *slot);
+		if (!iter.index) {
+			printf("next at %ld\n", iter.index);
+			slot = radix_tree_iter_next(&iter);
+		}
+	}
+
+	radix_tree_for_each_contig(slot, &root, &iter, 0) {
+		printf("contig %ld %p\n", iter.index, *slot);
+		if (!iter.index) {
+			printf("next at %ld\n", iter.index);
+			slot = radix_tree_iter_next(&iter);
+		}
+	}
+
+	radix_tree_tag_set(&root, 0, 0);
+	radix_tree_tag_set(&root, 1, 0);
+	radix_tree_for_each_tagged(slot, &root, &iter, 0, 0) {
+		printf("tagged %ld %p\n", iter.index, *slot);
+		if (!iter.index) {
+			printf("next at %ld\n", iter.index);
+			slot = radix_tree_iter_next(&iter);
+		}
+	}
+
+	radix_tree_delete(&root, 0);
+	radix_tree_delete(&root, 1);
+
+	printf("regression test 3 passed\n");
+}
diff --git a/tools/testing/radix-tree/tag_check.c b/tools/testing/radix-tree/tag_check.c
new file mode 100644
index 000000000..83136be55
--- /dev/null
+++ b/tools/testing/radix-tree/tag_check.c
@@ -0,0 +1,332 @@
+#include <stdlib.h>
+#include <assert.h>
+#include <stdio.h>
+#include <string.h>
+
+#include <linux/slab.h>
+#include <linux/radix-tree.h>
+
+#include "test.h"
+
+
+static void
+__simple_checks(struct radix_tree_root *tree, unsigned long index, int tag)
+{
+	int ret;
+
+	item_check_absent(tree, index);
+	assert(item_tag_get(tree, index, tag) == 0);
+
+	item_insert(tree, index);
+	assert(item_tag_get(tree, index, tag) == 0);
+	item_tag_set(tree, index, tag);
+	ret = item_tag_get(tree, index, tag);
+	assert(ret != 0);
+	ret = item_delete(tree, index);
+	assert(ret != 0);
+	item_insert(tree, index);
+	ret = item_tag_get(tree, index, tag);
+	assert(ret == 0);
+	ret = item_delete(tree, index);
+	assert(ret != 0);
+	ret = item_delete(tree, index);
+	assert(ret == 0);
+}
+
+void simple_checks(void)
+{
+	unsigned long index;
+	RADIX_TREE(tree, GFP_KERNEL);
+
+	for (index = 0; index < 10000; index++) {
+		__simple_checks(&tree, index, 0);
+		__simple_checks(&tree, index, 1);
+	}
+	verify_tag_consistency(&tree, 0);
+	verify_tag_consistency(&tree, 1);
+	printf("before item_kill_tree: %d allocated\n", nr_allocated);
+	item_kill_tree(&tree);
+	printf("after item_kill_tree: %d allocated\n", nr_allocated);
+}
+
+/*
+ * Check that tags propagate correctly when extending a tree.
+ */
+static void extend_checks(void)
+{
+	RADIX_TREE(tree, GFP_KERNEL);
+
+	item_insert(&tree, 43);
+	assert(item_tag_get(&tree, 43, 0) == 0);
+	item_tag_set(&tree, 43, 0);
+	assert(item_tag_get(&tree, 43, 0) == 1);
+	item_insert(&tree, 1000000);
+	assert(item_tag_get(&tree, 43, 0) == 1);
+
+	item_insert(&tree, 0);
+	item_tag_set(&tree, 0, 0);
+	item_delete(&tree, 1000000);
+	assert(item_tag_get(&tree, 43, 0) != 0);
+	item_delete(&tree, 43);
+	assert(item_tag_get(&tree, 43, 0) == 0);	/* crash */
+	assert(item_tag_get(&tree, 0, 0) == 1);
+
+	verify_tag_consistency(&tree, 0);
+
+	item_kill_tree(&tree);
+}
+
+/*
+ * Check that tags propagate correctly when contracting a tree.
+ */
+static void contract_checks(void)
+{
+	struct item *item;
+	int tmp;
+	RADIX_TREE(tree, GFP_KERNEL);
+
+	tmp = 1<<RADIX_TREE_MAP_SHIFT;
+	item_insert(&tree, tmp);
+	item_insert(&tree, tmp+1);
+	item_tag_set(&tree, tmp, 0);
+	item_tag_set(&tree, tmp, 1);
+	item_tag_set(&tree, tmp+1, 0);
+	item_delete(&tree, tmp+1);
+	item_tag_clear(&tree, tmp, 1);
+
+	assert(radix_tree_gang_lookup_tag(&tree, (void **)&item, 0, 1, 0) == 1);
+	assert(radix_tree_gang_lookup_tag(&tree, (void **)&item, 0, 1, 1) == 0);
+
+	assert(item_tag_get(&tree, tmp, 0) == 1);
+	assert(item_tag_get(&tree, tmp, 1) == 0);
+
+	verify_tag_consistency(&tree, 0);
+	item_kill_tree(&tree);
+}
+
+/*
+ * Stupid tag thrasher
+ *
+ * Create a large linear array corresponding to the tree.   Each element in
+ * the array is coherent with each node in the tree
+ */
+
+enum {
+	NODE_ABSENT = 0,
+	NODE_PRESENT = 1,
+	NODE_TAGGED = 2,
+};
+
+#define THRASH_SIZE		1000 * 1000
+#define N 127
+#define BATCH	33
+
+static void gang_check(struct radix_tree_root *tree,
+			char *thrash_state, int tag)
+{
+	struct item *items[BATCH];
+	int nr_found;
+	unsigned long index = 0;
+	unsigned long last_index = 0;
+
+	while ((nr_found = radix_tree_gang_lookup_tag(tree, (void **)items,
+					index, BATCH, tag))) {
+		int i;
+
+		for (i = 0; i < nr_found; i++) {
+			struct item *item = items[i];
+
+			while (last_index < item->index) {
+				assert(thrash_state[last_index] != NODE_TAGGED);
+				last_index++;
+			}
+			assert(thrash_state[last_index] == NODE_TAGGED);
+			last_index++;
+		}
+		index = items[nr_found - 1]->index + 1;
+	}
+}
+
+static void do_thrash(struct radix_tree_root *tree, char *thrash_state, int tag)
+{
+	int insert_chunk;
+	int delete_chunk;
+	int tag_chunk;
+	int untag_chunk;
+	int total_tagged = 0;
+	int total_present = 0;
+
+	for (insert_chunk = 1; insert_chunk < THRASH_SIZE; insert_chunk *= N)
+	for (delete_chunk = 1; delete_chunk < THRASH_SIZE; delete_chunk *= N)
+	for (tag_chunk = 1; tag_chunk < THRASH_SIZE; tag_chunk *= N)
+	for (untag_chunk = 1; untag_chunk < THRASH_SIZE; untag_chunk *= N) {
+		int i;
+		unsigned long index;
+		int nr_inserted = 0;
+		int nr_deleted = 0;
+		int nr_tagged = 0;
+		int nr_untagged = 0;
+		int actual_total_tagged;
+		int actual_total_present;
+
+		for (i = 0; i < insert_chunk; i++) {
+			index = rand() % THRASH_SIZE;
+			if (thrash_state[index] != NODE_ABSENT)
+				continue;
+			item_check_absent(tree, index);
+			item_insert(tree, index);
+			assert(thrash_state[index] != NODE_PRESENT);
+			thrash_state[index] = NODE_PRESENT;
+			nr_inserted++;
+			total_present++;
+		}
+
+		for (i = 0; i < delete_chunk; i++) {
+			index = rand() % THRASH_SIZE;
+			if (thrash_state[index] == NODE_ABSENT)
+				continue;
+			item_check_present(tree, index);
+			if (item_tag_get(tree, index, tag)) {
+				assert(thrash_state[index] == NODE_TAGGED);
+				total_tagged--;
+			} else {
+				assert(thrash_state[index] == NODE_PRESENT);
+			}
+			item_delete(tree, index);
+			assert(thrash_state[index] != NODE_ABSENT);
+			thrash_state[index] = NODE_ABSENT;
+			nr_deleted++;
+			total_present--;
+		}
+
+		for (i = 0; i < tag_chunk; i++) {
+			index = rand() % THRASH_SIZE;
+			if (thrash_state[index] != NODE_PRESENT) {
+				if (item_lookup(tree, index))
+					assert(item_tag_get(tree, index, tag));
+				continue;
+			}
+			item_tag_set(tree, index, tag);
+			item_tag_set(tree, index, tag);
+			assert(thrash_state[index] != NODE_TAGGED);
+			thrash_state[index] = NODE_TAGGED;
+			nr_tagged++;
+			total_tagged++;
+		}
+
+		for (i = 0; i < untag_chunk; i++) {
+			index = rand() % THRASH_SIZE;
+			if (thrash_state[index] != NODE_TAGGED)
+				continue;
+			item_check_present(tree, index);
+			assert(item_tag_get(tree, index, tag));
+			item_tag_clear(tree, index, tag);
+			item_tag_clear(tree, index, tag);
+			assert(thrash_state[index] != NODE_PRESENT);
+			thrash_state[index] = NODE_PRESENT;
+			nr_untagged++;
+			total_tagged--;
+		}
+
+		actual_total_tagged = 0;
+		actual_total_present = 0;
+		for (index = 0; index < THRASH_SIZE; index++) {
+			switch (thrash_state[index]) {
+			case NODE_ABSENT:
+				item_check_absent(tree, index);
+				break;
+			case NODE_PRESENT:
+				item_check_present(tree, index);
+				assert(!item_tag_get(tree, index, tag));
+				actual_total_present++;
+				break;
+			case NODE_TAGGED:
+				item_check_present(tree, index);
+				assert(item_tag_get(tree, index, tag));
+				actual_total_present++;
+				actual_total_tagged++;
+				break;
+			}
+		}
+
+		gang_check(tree, thrash_state, tag);
+
+		printf("%d(%d) %d(%d) %d(%d) %d(%d) / "
+				"%d(%d) present, %d(%d) tagged\n",
+			insert_chunk, nr_inserted,
+			delete_chunk, nr_deleted,
+			tag_chunk, nr_tagged,
+			untag_chunk, nr_untagged,
+			total_present, actual_total_present,
+			total_tagged, actual_total_tagged);
+	}
+}
+
+static void thrash_tags(void)
+{
+	RADIX_TREE(tree, GFP_KERNEL);
+	char *thrash_state;
+
+	thrash_state = malloc(THRASH_SIZE);
+	memset(thrash_state, 0, THRASH_SIZE);
+
+	do_thrash(&tree, thrash_state, 0);
+
+	verify_tag_consistency(&tree, 0);
+	item_kill_tree(&tree);
+	free(thrash_state);
+}
+
+static void leak_check(void)
+{
+	RADIX_TREE(tree, GFP_KERNEL);
+
+	item_insert(&tree, 1000000);
+	item_delete(&tree, 1000000);
+	item_kill_tree(&tree);
+}
+
+static void __leak_check(void)
+{
+	RADIX_TREE(tree, GFP_KERNEL);
+
+	printf("%d: nr_allocated=%d\n", __LINE__, nr_allocated);
+	item_insert(&tree, 1000000);
+	printf("%d: nr_allocated=%d\n", __LINE__, nr_allocated);
+	item_delete(&tree, 1000000);
+	printf("%d: nr_allocated=%d\n", __LINE__, nr_allocated);
+	item_kill_tree(&tree);
+	printf("%d: nr_allocated=%d\n", __LINE__, nr_allocated);
+}
+
+static void single_check(void)
+{
+	struct item *items[BATCH];
+	RADIX_TREE(tree, GFP_KERNEL);
+	int ret;
+
+	item_insert(&tree, 0);
+	item_tag_set(&tree, 0, 0);
+	ret = radix_tree_gang_lookup_tag(&tree, (void **)items, 0, BATCH, 0);
+	assert(ret == 1);
+	ret = radix_tree_gang_lookup_tag(&tree, (void **)items, 1, BATCH, 0);
+	assert(ret == 0);
+	verify_tag_consistency(&tree, 0);
+	verify_tag_consistency(&tree, 1);
+	item_kill_tree(&tree);
+}
+
+void tag_check(void)
+{
+	single_check();
+	extend_checks();
+	contract_checks();
+	printf("after extend_checks: %d allocated\n", nr_allocated);
+	__leak_check();
+	leak_check();
+	printf("after leak_check: %d allocated\n", nr_allocated);
+	simple_checks();
+	printf("after simple_checks: %d allocated\n", nr_allocated);
+	thrash_tags();
+	printf("after thrash_tags: %d allocated\n", nr_allocated);
+}
diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
new file mode 100644
index 000000000..2bebf34cd
--- /dev/null
+++ b/tools/testing/radix-tree/test.c
@@ -0,0 +1,219 @@
+#include <stdlib.h>
+#include <assert.h>
+#include <stdio.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+
+#include "test.h"
+
+struct item *
+item_tag_set(struct radix_tree_root *root, unsigned long index, int tag)
+{
+	return radix_tree_tag_set(root, index, tag);
+}
+
+struct item *
+item_tag_clear(struct radix_tree_root *root, unsigned long index, int tag)
+{
+	return radix_tree_tag_clear(root, index, tag);
+}
+
+int item_tag_get(struct radix_tree_root *root, unsigned long index, int tag)
+{
+	return radix_tree_tag_get(root, index, tag);
+}
+
+int __item_insert(struct radix_tree_root *root, struct item *item)
+{
+	return radix_tree_insert(root, item->index, item);
+}
+
+int item_insert(struct radix_tree_root *root, unsigned long index)
+{
+	return __item_insert(root, item_create(index));
+}
+
+int item_delete(struct radix_tree_root *root, unsigned long index)
+{
+	struct item *item = radix_tree_delete(root, index);
+
+	if (item) {
+		assert(item->index == index);
+		free(item);
+		return 1;
+	}
+	return 0;
+}
+
+struct item *item_create(unsigned long index)
+{
+	struct item *ret = malloc(sizeof(*ret));
+
+	ret->index = index;
+	return ret;
+}
+
+void item_check_present(struct radix_tree_root *root, unsigned long index)
+{
+	struct item *item;
+
+	item = radix_tree_lookup(root, index);
+	assert(item != 0);
+	assert(item->index == index);
+}
+
+struct item *item_lookup(struct radix_tree_root *root, unsigned long index)
+{
+	return radix_tree_lookup(root, index);
+}
+
+void item_check_absent(struct radix_tree_root *root, unsigned long index)
+{
+	struct item *item;
+
+	item = radix_tree_lookup(root, index);
+	assert(item == 0);
+}
+
+/*
+ * Scan only the passed (start, start+nr] for present items
+ */
+void item_gang_check_present(struct radix_tree_root *root,
+			unsigned long start, unsigned long nr,
+			int chunk, int hop)
+{
+	struct item *items[chunk];
+	unsigned long into;
+
+	for (into = 0; into < nr; ) {
+		int nfound;
+		int nr_to_find = chunk;
+		int i;
+
+		if (nr_to_find > (nr - into))
+			nr_to_find = nr - into;
+
+		nfound = radix_tree_gang_lookup(root, (void **)items,
+						start + into, nr_to_find);
+		assert(nfound == nr_to_find);
+		for (i = 0; i < nfound; i++)
+			assert(items[i]->index == start + into + i);
+		into += hop;
+	}
+}
+
+/*
+ * Scan the entire tree, only expecting present items (start, start+nr]
+ */
+void item_full_scan(struct radix_tree_root *root, unsigned long start,
+			unsigned long nr, int chunk)
+{
+	struct item *items[chunk];
+	unsigned long into = 0;
+	unsigned long this_index = start;
+	int nfound;
+	int i;
+
+//	printf("%s(0x%08lx, 0x%08lx, %d)\n", __FUNCTION__, start, nr, chunk);
+
+	while ((nfound = radix_tree_gang_lookup(root, (void **)items, into,
+					chunk))) {
+//		printf("At 0x%08lx, nfound=%d\n", into, nfound);
+		for (i = 0; i < nfound; i++) {
+			assert(items[i]->index == this_index);
+			this_index++;
+		}
+//		printf("Found 0x%08lx->0x%08lx\n",
+//			items[0]->index, items[nfound-1]->index);
+		into = this_index;
+	}
+	if (chunk)
+		assert(this_index == start + nr);
+	nfound = radix_tree_gang_lookup(root, (void **)items,
+					this_index, chunk);
+	assert(nfound == 0);
+}
+
+static int verify_node(struct radix_tree_node *slot, unsigned int tag,
+			unsigned int height, int tagged)
+{
+	int anyset = 0;
+	int i;
+	int j;
+
+	slot = indirect_to_ptr(slot);
+
+	/* Verify consistency at this level */
+	for (i = 0; i < RADIX_TREE_TAG_LONGS; i++) {
+		if (slot->tags[tag][i]) {
+			anyset = 1;
+			break;
+		}
+	}
+	if (tagged != anyset) {
+		printf("tag: %u, height %u, tagged: %d, anyset: %d\n", tag, height, tagged, anyset);
+		for (j = 0; j < RADIX_TREE_MAX_TAGS; j++) {
+			printf("tag %d: ", j);
+			for (i = 0; i < RADIX_TREE_TAG_LONGS; i++)
+				printf("%016lx ", slot->tags[j][i]);
+			printf("\n");
+		}
+		return 1;
+	}
+	assert(tagged == anyset);
+
+	/* Go for next level */
+	if (height > 1) {
+		for (i = 0; i < RADIX_TREE_MAP_SIZE; i++)
+			if (slot->slots[i])
+				if (verify_node(slot->slots[i], tag, height - 1,
+					    !!test_bit(i, slot->tags[tag]))) {
+					printf("Failure at off %d\n", i);
+					for (j = 0; j < RADIX_TREE_MAX_TAGS; j++) {
+						printf("tag %d: ", j);
+						for (i = 0; i < RADIX_TREE_TAG_LONGS; i++)
+							printf("%016lx ", slot->tags[j][i]);
+						printf("\n");
+					}
+					return 1;
+				}
+	}
+	return 0;
+}
+
+void verify_tag_consistency(struct radix_tree_root *root, unsigned int tag)
+{
+	if (!root->height)
+		return;
+	verify_node(root->rnode, tag, root->height, !!root_tag_get(root, tag));
+}
+
+void item_kill_tree(struct radix_tree_root *root)
+{
+	struct item *items[32];
+	int nfound;
+
+	while ((nfound = radix_tree_gang_lookup(root, (void **)items, 0, 32))) {
+		int i;
+
+		for (i = 0; i < nfound; i++) {
+			void *ret;
+
+			ret = radix_tree_delete(root, items[i]->index);
+			assert(ret == items[i]);
+			free(items[i]);
+		}
+	}
+	assert(radix_tree_gang_lookup(root, (void **)items, 0, 32) == 0);
+	assert(root->rnode == NULL);
+}
+
+void tree_verify_min_height(struct radix_tree_root *root, int maxindex)
+{
+	assert(radix_tree_maxindex(root->height) >= maxindex);
+	if (root->height > 1)
+		assert(radix_tree_maxindex(root->height-1) < maxindex);
+	else if (root->height == 1)
+		assert(radix_tree_maxindex(root->height-1) <= maxindex);
+}
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
new file mode 100644
index 000000000..4e1d95faa
--- /dev/null
+++ b/tools/testing/radix-tree/test.h
@@ -0,0 +1,40 @@
+#include <linux/gfp.h>
+#include <linux/types.h>
+#include <linux/radix-tree.h>
+#include <linux/rcupdate.h>
+
+struct item {
+	unsigned long index;
+};
+
+struct item *item_create(unsigned long index);
+int __item_insert(struct radix_tree_root *root, struct item *item);
+int item_insert(struct radix_tree_root *root, unsigned long index);
+int item_delete(struct radix_tree_root *root, unsigned long index);
+struct item *item_lookup(struct radix_tree_root *root, unsigned long index);
+
+void item_check_present(struct radix_tree_root *root, unsigned long index);
+void item_check_absent(struct radix_tree_root *root, unsigned long index);
+void item_gang_check_present(struct radix_tree_root *root,
+			unsigned long start, unsigned long nr,
+			int chunk, int hop);
+void item_full_scan(struct radix_tree_root *root, unsigned long start,
+			unsigned long nr, int chunk);
+void item_kill_tree(struct radix_tree_root *root);
+
+void tag_check(void);
+
+struct item *
+item_tag_set(struct radix_tree_root *root, unsigned long index, int tag);
+struct item *
+item_tag_clear(struct radix_tree_root *root, unsigned long index, int tag);
+int item_tag_get(struct radix_tree_root *root, unsigned long index, int tag);
+void tree_verify_min_height(struct radix_tree_root *root, int maxindex);
+void verify_tag_consistency(struct radix_tree_root *root, unsigned int tag);
+
+extern int nr_allocated;
+
+/* Normally private parts of lib/radix-tree.c */
+void *indirect_to_ptr(void *ptr);
+int root_tag_get(struct radix_tree_root *root, unsigned int tag);
+unsigned long radix_tree_maxindex(unsigned int height);
diff --git a/tools/testing/selftests/breakpoints/.gitignore b/tools/testing/selftests/breakpoints/.gitignore
index 9b3193d06..a23bb4a6f 100644
--- a/tools/testing/selftests/breakpoints/.gitignore
+++ b/tools/testing/selftests/breakpoints/.gitignore
@@ -1 +1,2 @@
 breakpoint_test
+step_after_suspend_test
diff --git a/tools/testing/selftests/breakpoints/Makefile b/tools/testing/selftests/breakpoints/Makefile
index c0d957015..74e533fd4 100644
--- a/tools/testing/selftests/breakpoints/Makefile
+++ b/tools/testing/selftests/breakpoints/Makefile
@@ -6,9 +6,11 @@ ifeq ($(ARCH),x86)
 TEST_PROGS := breakpoint_test
 endif
 
+TEST_PROGS += step_after_suspend_test
+
 all: $(TEST_PROGS)
 
 include ../lib.mk
 
 clean:
-	rm -fr breakpoint_test
+	rm -fr breakpoint_test step_after_suspend_test
diff --git a/tools/testing/selftests/breakpoints/step_after_suspend_test.c b/tools/testing/selftests/breakpoints/step_after_suspend_test.c
new file mode 100644
index 000000000..60b8a95da
--- /dev/null
+++ b/tools/testing/selftests/breakpoints/step_after_suspend_test.c
@@ -0,0 +1,218 @@
+/*
+ * Copyright (C) 2016 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/ptrace.h>
+#include <sys/stat.h>
+#include <sys/timerfd.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+
+#include "../kselftest.h"
+
+void child(int cpu)
+{
+	cpu_set_t set;
+
+	CPU_ZERO(&set);
+	CPU_SET(cpu, &set);
+	if (sched_setaffinity(0, sizeof(set), &set) != 0) {
+		perror("sched_setaffinity() failed");
+		_exit(1);
+	}
+
+	if (ptrace(PTRACE_TRACEME, 0, NULL, NULL) != 0) {
+		perror("ptrace(PTRACE_TRACEME) failed");
+		_exit(1);
+	}
+
+	if (raise(SIGSTOP) != 0) {
+		perror("raise(SIGSTOP) failed");
+		_exit(1);
+	}
+
+	_exit(0);
+}
+
+bool run_test(int cpu)
+{
+	int status;
+	pid_t pid = fork();
+	pid_t wpid;
+
+	if (pid < 0) {
+		perror("fork() failed");
+		return false;
+	}
+	if (pid == 0)
+		child(cpu);
+
+	wpid = waitpid(pid, &status, __WALL);
+	if (wpid != pid) {
+		perror("waitpid() failed");
+		return false;
+	}
+	if (!WIFSTOPPED(status)) {
+		printf("child did not stop\n");
+		return false;
+	}
+	if (WSTOPSIG(status) != SIGSTOP) {
+		printf("child did not stop with SIGSTOP\n");
+		return false;
+	}
+
+	if (ptrace(PTRACE_SINGLESTEP, pid, NULL, NULL) < 0) {
+		if (errno == EIO) {
+			printf("ptrace(PTRACE_SINGLESTEP) not supported on this architecture\n");
+			ksft_exit_skip();
+		}
+		perror("ptrace(PTRACE_SINGLESTEP) failed");
+		return false;
+	}
+
+	wpid = waitpid(pid, &status, __WALL);
+	if (wpid != pid) {
+		perror("waitpid() failed");
+		return false;
+	}
+	if (WIFEXITED(status)) {
+		printf("child did not single-step\n");
+		return false;
+	}
+	if (!WIFSTOPPED(status)) {
+		printf("child did not stop\n");
+		return false;
+	}
+	if (WSTOPSIG(status) != SIGTRAP) {
+		printf("child did not stop with SIGTRAP\n");
+		return false;
+	}
+
+	if (ptrace(PTRACE_CONT, pid, NULL, NULL) < 0) {
+		perror("ptrace(PTRACE_CONT) failed");
+		return false;
+	}
+
+	wpid = waitpid(pid, &status, __WALL);
+	if (wpid != pid) {
+		perror("waitpid() failed");
+		return false;
+	}
+	if (!WIFEXITED(status)) {
+		printf("child did not exit after PTRACE_CONT\n");
+		return false;
+	}
+
+	return true;
+}
+
+void suspend(void)
+{
+	int power_state_fd;
+	struct sigevent event = {};
+	int timerfd;
+	int err;
+	struct itimerspec spec = {};
+
+	power_state_fd = open("/sys/power/state", O_RDWR);
+	if (power_state_fd < 0) {
+		perror("open(\"/sys/power/state\") failed (is this test running as root?)");
+		ksft_exit_fail();
+	}
+
+	timerfd = timerfd_create(CLOCK_BOOTTIME_ALARM, 0);
+	if (timerfd < 0) {
+		perror("timerfd_create() failed");
+		ksft_exit_fail();
+	}
+
+	spec.it_value.tv_sec = 5;
+	err = timerfd_settime(timerfd, 0, &spec, NULL);
+	if (err < 0) {
+		perror("timerfd_settime() failed");
+		ksft_exit_fail();
+	}
+
+	if (write(power_state_fd, "mem", strlen("mem")) != strlen("mem")) {
+		perror("entering suspend failed");
+		ksft_exit_fail();
+	}
+
+	close(timerfd);
+	close(power_state_fd);
+}
+
+int main(int argc, char **argv)
+{
+	int opt;
+	bool do_suspend = true;
+	bool succeeded = true;
+	cpu_set_t available_cpus;
+	int err;
+	int cpu;
+
+	while ((opt = getopt(argc, argv, "n")) != -1) {
+		switch (opt) {
+		case 'n':
+			do_suspend = false;
+			break;
+		default:
+			printf("Usage: %s [-n]\n", argv[0]);
+			printf("        -n: do not trigger a suspend/resume cycle before the test\n");
+			return -1;
+		}
+	}
+
+	if (do_suspend)
+		suspend();
+
+	err = sched_getaffinity(0, sizeof(available_cpus), &available_cpus);
+	if (err < 0) {
+		perror("sched_getaffinity() failed");
+		ksft_exit_fail();
+	}
+
+	for (cpu = 0; cpu < CPU_SETSIZE; cpu++) {
+		bool test_success;
+
+		if (!CPU_ISSET(cpu, &available_cpus))
+			continue;
+
+		test_success = run_test(cpu);
+		printf("CPU %d: ", cpu);
+		if (test_success) {
+			printf("[OK]\n");
+			ksft_inc_pass_cnt();
+		} else {
+			printf("[FAILED]\n");
+			ksft_inc_fail_cnt();
+			succeeded = false;
+		}
+	}
+
+	ksft_print_cnts();
+	if (succeeded)
+		ksft_exit_pass();
+	else
+		ksft_exit_fail();
+}
diff --git a/tools/testing/selftests/cpu-hotplug/config b/tools/testing/selftests/cpu-hotplug/config
new file mode 100644
index 000000000..e6ab090cf
--- /dev/null
+++ b/tools/testing/selftests/cpu-hotplug/config
@@ -0,0 +1,2 @@
+CONFIG_NOTIFIER_ERROR_INJECTION=y
+CONFIG_CPU_NOTIFIER_ERROR_INJECT=m
diff --git a/tools/testing/selftests/firmware/config b/tools/testing/selftests/firmware/config
new file mode 100644
index 000000000..c8137f70e
--- /dev/null
+++ b/tools/testing/selftests/firmware/config
@@ -0,0 +1 @@
+CONFIG_TEST_FIRMWARE=y
diff --git a/tools/testing/selftests/ftrace/config b/tools/testing/selftests/ftrace/config
new file mode 100644
index 000000000..ef8214661
--- /dev/null
+++ b/tools/testing/selftests/ftrace/config
@@ -0,0 +1 @@
+CONFIG_FTRACE=y
diff --git a/tools/testing/selftests/ipc/.gitignore b/tools/testing/selftests/ipc/.gitignore
new file mode 100644
index 000000000..84b66a3c1
--- /dev/null
+++ b/tools/testing/selftests/ipc/.gitignore
@@ -0,0 +1 @@
+msgque_test
diff --git a/tools/testing/selftests/ipc/config b/tools/testing/selftests/ipc/config
new file mode 100644
index 000000000..070244710
--- /dev/null
+++ b/tools/testing/selftests/ipc/config
@@ -0,0 +1,2 @@
+CONFIG_EXPERT=y
+CONFIG_CHECKPOINT_RESTORE=y
diff --git a/tools/testing/selftests/lib/Makefile b/tools/testing/selftests/lib/Makefile
index 47147b968..08360060a 100644
--- a/tools/testing/selftests/lib/Makefile
+++ b/tools/testing/selftests/lib/Makefile
@@ -3,6 +3,6 @@
 # No binaries, but make sure arg-less "make" doesn't trigger "run_tests"
 all:
 
-TEST_PROGS := printf.sh
+TEST_PROGS := printf.sh bitmap.sh
 
 include ../lib.mk
diff --git a/tools/testing/selftests/lib/bitmap.sh b/tools/testing/selftests/lib/bitmap.sh
new file mode 100755
index 000000000..2da187b6d
--- /dev/null
+++ b/tools/testing/selftests/lib/bitmap.sh
@@ -0,0 +1,10 @@
+#!/bin/sh
+# Runs bitmap infrastructure tests using test_bitmap kernel module
+
+if /sbin/modprobe -q test_bitmap; then
+	/sbin/modprobe -q -r test_bitmap
+	echo "bitmap: ok"
+else
+	echo "bitmap: [FAIL]"
+	exit 1
+fi
diff --git a/tools/testing/selftests/media_tests/.gitignore b/tools/testing/selftests/media_tests/.gitignore
new file mode 100644
index 000000000..1c0711708
--- /dev/null
+++ b/tools/testing/selftests/media_tests/.gitignore
@@ -0,0 +1 @@
+media_device_test
diff --git a/tools/testing/selftests/media_tests/Makefile b/tools/testing/selftests/media_tests/Makefile
new file mode 100644
index 000000000..7071bcc1d
--- /dev/null
+++ b/tools/testing/selftests/media_tests/Makefile
@@ -0,0 +1,7 @@
+TEST_PROGS := media_device_test
+all: $(TEST_PROGS)
+
+include ../lib.mk
+
+clean:
+	rm -fr media_device_test
diff --git a/tools/testing/selftests/media_tests/media_device_test.c b/tools/testing/selftests/media_tests/media_device_test.c
new file mode 100644
index 000000000..cbf53a032
--- /dev/null
+++ b/tools/testing/selftests/media_tests/media_device_test.c
@@ -0,0 +1,95 @@
+/*
+ * media_devkref_test.c - Media Controller Device Kref API Test
+ *
+ * Copyright (c) 2016 Shuah Khan <shuahkh@osg.samsung.com>
+ * Copyright (c) 2016 Samsung Electronics Co., Ltd.
+ *
+ * This file is released under the GPLv2.
+ */
+
+/*
+ * This file adds a test for Media Controller API.
+ * This test should be run as root and should not be
+ * included in the Kselftest run. This test should be
+ * run when hardware and driver that makes use Media
+ * Controller API are present in the system.
+ *
+ * This test opens user specified Media Device and calls
+ * MEDIA_IOC_DEVICE_INFO ioctl in a loop once every 10
+ * seconds.
+ *
+ * Usage:
+ *	sudo ./media_device_test -d /dev/mediaX
+ *
+ *	While test is running, remove the device and
+ *	ensure there are no use after free errors and
+ *	other Oops in the dmesg. Enable KaSan kernel
+ *	config option for use-after-free error detection.
+*/
+
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <string.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <sys/stat.h>
+#include <linux/media.h>
+
+int main(int argc, char **argv)
+{
+	int opt;
+	char media_device[256];
+	int count = 0;
+	struct media_device_info mdi;
+	int ret;
+	int fd;
+
+	if (argc < 2) {
+		printf("Usage: %s [-d </dev/mediaX>]\n", argv[0]);
+		exit(-1);
+	}
+
+	/* Process arguments */
+	while ((opt = getopt(argc, argv, "d:")) != -1) {
+		switch (opt) {
+		case 'd':
+			strncpy(media_device, optarg, sizeof(media_device) - 1);
+			media_device[sizeof(media_device)-1] = '\0';
+			break;
+		default:
+			printf("Usage: %s [-d </dev/mediaX>]\n", argv[0]);
+			exit(-1);
+		}
+	}
+
+	if (getuid() != 0) {
+		printf("Please run the test as root - Exiting.\n");
+		exit(-1);
+	}
+
+	/* Open Media device and keep it open */
+	fd = open(media_device, O_RDWR);
+	if (fd == -1) {
+		printf("Media Device open errno %s\n", strerror(errno));
+		exit(-1);
+	}
+
+	printf("\nNote:\n"
+	       "While test is running, remove the device and\n"
+	       "ensure there are no use after free errors and\n"
+	       "other Oops in the dmesg. Enable KaSan kernel\n"
+	       "config option for use-after-free error detection.\n\n");
+
+	while (count < 100) {
+		ret = ioctl(fd, MEDIA_IOC_DEVICE_INFO, &mdi);
+		if (ret < 0)
+			printf("Media Device Info errno %s\n", strerror(errno));
+		else
+			printf("Media device model %s driver %s\n",
+				mdi.model, mdi.driver);
+		sleep(10);
+		count++;
+	}
+}
diff --git a/tools/testing/selftests/memory-hotplug/config b/tools/testing/selftests/memory-hotplug/config
new file mode 100644
index 000000000..2fde30191
--- /dev/null
+++ b/tools/testing/selftests/memory-hotplug/config
@@ -0,0 +1,4 @@
+CONFIG_MEMORY_HOTPLUG=y
+CONFIG_MEMORY_HOTPLUG_SPARSE=y
+CONFIG_NOTIFIER_ERROR_INJECTION=y
+CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m
diff --git a/tools/testing/selftests/mount/config b/tools/testing/selftests/mount/config
new file mode 100644
index 000000000..b5d881e48
--- /dev/null
+++ b/tools/testing/selftests/mount/config
@@ -0,0 +1,2 @@
+CONFIG_USER_NS=y
+CONFIG_DEVPTS_MULTIPLE_INSTANCES=y
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 6fb23366b..0840684de 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -2,3 +2,5 @@ socket
 psock_fanout
 psock_tpacket
 reuseport_bpf
+reuseport_bpf_cpu
+reuseport_dualstack
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 41449b5ad..0e5340742 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -4,7 +4,7 @@ CFLAGS = -Wall -O2 -g
 
 CFLAGS += -I../../../../usr/include/
 
-NET_PROGS = socket psock_fanout psock_tpacket reuseport_bpf
+NET_PROGS = socket psock_fanout psock_tpacket reuseport_bpf reuseport_bpf_cpu reuseport_dualstack
 
 all: $(NET_PROGS)
 %: %.c
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
new file mode 100644
index 000000000..e57b4ac40
--- /dev/null
+++ b/tools/testing/selftests/net/config
@@ -0,0 +1,3 @@
+CONFIG_USER_NS=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_TEST_BPF=m
diff --git a/tools/testing/selftests/net/reuseport_bpf.c b/tools/testing/selftests/net/reuseport_bpf.c
index bec1b5dd2..96ba386b1 100644
--- a/tools/testing/selftests/net/reuseport_bpf.c
+++ b/tools/testing/selftests/net/reuseport_bpf.c
@@ -9,10 +9,12 @@
 
 #include <errno.h>
 #include <error.h>
+#include <fcntl.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
 #include <linux/unistd.h>
 #include <netinet/in.h>
+#include <netinet/tcp.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -169,9 +171,15 @@ static void build_recv_group(const struct test_params p, int fd[], uint16_t mod,
 		if (bind(fd[i], addr, sockaddr_size()))
 			error(1, errno, "failed to bind recv socket %d", i);
 
-		if (p.protocol == SOCK_STREAM)
+		if (p.protocol == SOCK_STREAM) {
+			opt = 4;
+			if (setsockopt(fd[i], SOL_TCP, TCP_FASTOPEN, &opt,
+				       sizeof(opt)))
+				error(1, errno,
+				      "failed to set TCP_FASTOPEN on %d", i);
 			if (listen(fd[i], p.recv_socks * 10))
 				error(1, errno, "failed to listen on socket");
+		}
 	}
 	free(addr);
 }
@@ -189,10 +197,8 @@ static void send_from(struct test_params p, uint16_t sport, char *buf,
 
 	if (bind(fd, saddr, sockaddr_size()))
 		error(1, errno, "failed to bind send socket");
-	if (connect(fd, daddr, sockaddr_size()))
-		error(1, errno, "failed to connect");
 
-	if (send(fd, buf, len, 0) < 0)
+	if (sendto(fd, buf, len, MSG_FASTOPEN, daddr, sockaddr_size()) < 0)
 		error(1, errno, "failed to send message");
 
 	close(fd);
@@ -260,7 +266,7 @@ static void test_recv_order(const struct test_params p, int fd[], int mod)
 	}
 }
 
-static void test_reuseport_ebpf(const struct test_params p)
+static void test_reuseport_ebpf(struct test_params p)
 {
 	int i, fd[p.recv_socks];
 
@@ -268,6 +274,7 @@ static void test_reuseport_ebpf(const struct test_params p)
 	build_recv_group(p, fd, p.recv_socks, attach_ebpf);
 	test_recv_order(p, fd, p.recv_socks);
 
+	p.send_port_min += p.recv_socks * 2;
 	fprintf(stderr, "Reprograming, testing mod %zd...\n", p.recv_socks / 2);
 	attach_ebpf(fd[0], p.recv_socks / 2);
 	test_recv_order(p, fd, p.recv_socks / 2);
@@ -276,7 +283,7 @@ static void test_reuseport_ebpf(const struct test_params p)
 		close(fd[i]);
 }
 
-static void test_reuseport_cbpf(const struct test_params p)
+static void test_reuseport_cbpf(struct test_params p)
 {
 	int i, fd[p.recv_socks];
 
@@ -284,6 +291,7 @@ static void test_reuseport_cbpf(const struct test_params p)
 	build_recv_group(p, fd, p.recv_socks, attach_cbpf);
 	test_recv_order(p, fd, p.recv_socks);
 
+	p.send_port_min += p.recv_socks * 2;
 	fprintf(stderr, "Reprograming, testing mod %zd...\n", p.recv_socks / 2);
 	attach_cbpf(fd[0], p.recv_socks / 2);
 	test_recv_order(p, fd, p.recv_socks / 2);
@@ -377,7 +385,7 @@ static void test_filter_no_reuseport(const struct test_params p)
 
 static void test_filter_without_bind(void)
 {
-	int fd1, fd2;
+	int fd1, fd2, opt = 1;
 
 	fprintf(stderr, "Testing filter add without bind...\n");
 	fd1 = socket(AF_INET, SOCK_DGRAM, 0);
@@ -386,6 +394,10 @@ static void test_filter_without_bind(void)
 	fd2 = socket(AF_INET, SOCK_DGRAM, 0);
 	if (fd2 < 0)
 		error(1, errno, "failed to create socket 2");
+	if (setsockopt(fd1, SOL_SOCKET, SO_REUSEPORT, &opt, sizeof(opt)))
+		error(1, errno, "failed to set SO_REUSEPORT on socket 1");
+	if (setsockopt(fd2, SOL_SOCKET, SO_REUSEPORT, &opt, sizeof(opt)))
+		error(1, errno, "failed to set SO_REUSEPORT on socket 2");
 
 	attach_ebpf(fd1, 10);
 	attach_cbpf(fd2, 10);
@@ -394,6 +406,32 @@ static void test_filter_without_bind(void)
 	close(fd2);
 }
 
+void enable_fastopen(void)
+{
+	int fd = open("/proc/sys/net/ipv4/tcp_fastopen", 0);
+	int rw_mask = 3;  /* bit 1: client side; bit-2 server side */
+	int val, size;
+	char buf[16];
+
+	if (fd < 0)
+		error(1, errno, "Unable to open tcp_fastopen sysctl");
+	if (read(fd, buf, sizeof(buf)) <= 0)
+		error(1, errno, "Unable to read tcp_fastopen sysctl");
+	val = atoi(buf);
+	close(fd);
+
+	if ((val & rw_mask) != rw_mask) {
+		fd = open("/proc/sys/net/ipv4/tcp_fastopen", O_RDWR);
+		if (fd < 0)
+			error(1, errno,
+			      "Unable to open tcp_fastopen sysctl for writing");
+		val |= rw_mask;
+		size = snprintf(buf, 16, "%d", val);
+		if (write(fd, buf, size) <= 0)
+			error(1, errno, "Unable to write tcp_fastopen sysctl");
+		close(fd);
+	}
+}
 
 int main(void)
 {
@@ -506,6 +544,71 @@ int main(void)
 		.recv_port = 8007,
 		.send_port_min = 9100});
 
+	/* TCP fastopen is required for the TCP tests */
+	enable_fastopen();
+	fprintf(stderr, "---- IPv4 TCP ----\n");
+	test_reuseport_ebpf((struct test_params) {
+		.recv_family = AF_INET,
+		.send_family = AF_INET,
+		.protocol = SOCK_STREAM,
+		.recv_socks = 10,
+		.recv_port = 8008,
+		.send_port_min = 9120});
+	test_reuseport_cbpf((struct test_params) {
+		.recv_family = AF_INET,
+		.send_family = AF_INET,
+		.protocol = SOCK_STREAM,
+		.recv_socks = 10,
+		.recv_port = 8009,
+		.send_port_min = 9160});
+	test_extra_filter((struct test_params) {
+		.recv_family = AF_INET,
+		.protocol = SOCK_STREAM,
+		.recv_port = 8010});
+	test_filter_no_reuseport((struct test_params) {
+		.recv_family = AF_INET,
+		.protocol = SOCK_STREAM,
+		.recv_port = 8011});
+
+	fprintf(stderr, "---- IPv6 TCP ----\n");
+	test_reuseport_ebpf((struct test_params) {
+		.recv_family = AF_INET6,
+		.send_family = AF_INET6,
+		.protocol = SOCK_STREAM,
+		.recv_socks = 10,
+		.recv_port = 8012,
+		.send_port_min = 9200});
+	test_reuseport_cbpf((struct test_params) {
+		.recv_family = AF_INET6,
+		.send_family = AF_INET6,
+		.protocol = SOCK_STREAM,
+		.recv_socks = 10,
+		.recv_port = 8013,
+		.send_port_min = 9240});
+	test_extra_filter((struct test_params) {
+		.recv_family = AF_INET6,
+		.protocol = SOCK_STREAM,
+		.recv_port = 8014});
+	test_filter_no_reuseport((struct test_params) {
+		.recv_family = AF_INET6,
+		.protocol = SOCK_STREAM,
+		.recv_port = 8015});
+
+	fprintf(stderr, "---- IPv6 TCP w/ mapped IPv4 ----\n");
+	test_reuseport_ebpf((struct test_params) {
+		.recv_family = AF_INET6,
+		.send_family = AF_INET,
+		.protocol = SOCK_STREAM,
+		.recv_socks = 10,
+		.recv_port = 8016,
+		.send_port_min = 9320});
+	test_reuseport_cbpf((struct test_params) {
+		.recv_family = AF_INET6,
+		.send_family = AF_INET,
+		.protocol = SOCK_STREAM,
+		.recv_socks = 10,
+		.recv_port = 8017,
+		.send_port_min = 9360});
 
 	test_filter_without_bind();
 
diff --git a/tools/testing/selftests/net/reuseport_bpf_cpu.c b/tools/testing/selftests/net/reuseport_bpf_cpu.c
new file mode 100644
index 000000000..b23d6f54d
--- /dev/null
+++ b/tools/testing/selftests/net/reuseport_bpf_cpu.c
@@ -0,0 +1,258 @@
+/*
+ * Test functionality of BPF filters with SO_REUSEPORT.  This program creates
+ * an SO_REUSEPORT receiver group containing one socket per CPU core. It then
+ * creates a BPF program that will select a socket from this group based
+ * on the core id that receives the packet.  The sending code artificially
+ * moves itself to run on different core ids and sends one message from
+ * each core.  Since these packets are delivered over loopback, they should
+ * arrive on the same core that sent them.  The receiving code then ensures
+ * that the packet was received on the socket for the corresponding core id.
+ * This entire process is done for several different core id permutations
+ * and for each IPv4/IPv6 and TCP/UDP combination.
+ */
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <linux/filter.h>
+#include <linux/in.h>
+#include <linux/unistd.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/epoll.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <unistd.h>
+
+static const int PORT = 8888;
+
+static void build_rcv_group(int *rcv_fd, size_t len, int family, int proto)
+{
+	struct sockaddr_storage addr;
+	struct sockaddr_in  *addr4;
+	struct sockaddr_in6 *addr6;
+	size_t i;
+	int opt;
+
+	switch (family) {
+	case AF_INET:
+		addr4 = (struct sockaddr_in *)&addr;
+		addr4->sin_family = AF_INET;
+		addr4->sin_addr.s_addr = htonl(INADDR_ANY);
+		addr4->sin_port = htons(PORT);
+		break;
+	case AF_INET6:
+		addr6 = (struct sockaddr_in6 *)&addr;
+		addr6->sin6_family = AF_INET6;
+		addr6->sin6_addr = in6addr_any;
+		addr6->sin6_port = htons(PORT);
+		break;
+	default:
+		error(1, 0, "Unsupported family %d", family);
+	}
+
+	for (i = 0; i < len; ++i) {
+		rcv_fd[i] = socket(family, proto, 0);
+		if (rcv_fd[i] < 0)
+			error(1, errno, "failed to create receive socket");
+
+		opt = 1;
+		if (setsockopt(rcv_fd[i], SOL_SOCKET, SO_REUSEPORT, &opt,
+			       sizeof(opt)))
+			error(1, errno, "failed to set SO_REUSEPORT");
+
+		if (bind(rcv_fd[i], (struct sockaddr *)&addr, sizeof(addr)))
+			error(1, errno, "failed to bind receive socket");
+
+		if (proto == SOCK_STREAM && listen(rcv_fd[i], len * 10))
+			error(1, errno, "failed to listen on receive port");
+	}
+}
+
+static void attach_bpf(int fd)
+{
+	struct sock_filter code[] = {
+		/* A = raw_smp_processor_id() */
+		{ BPF_LD  | BPF_W | BPF_ABS, 0, 0, SKF_AD_OFF + SKF_AD_CPU },
+		/* return A */
+		{ BPF_RET | BPF_A, 0, 0, 0 },
+	};
+	struct sock_fprog p = {
+		.len = 2,
+		.filter = code,
+	};
+
+	if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_REUSEPORT_CBPF, &p, sizeof(p)))
+		error(1, errno, "failed to set SO_ATTACH_REUSEPORT_CBPF");
+}
+
+static void send_from_cpu(int cpu_id, int family, int proto)
+{
+	struct sockaddr_storage saddr, daddr;
+	struct sockaddr_in  *saddr4, *daddr4;
+	struct sockaddr_in6 *saddr6, *daddr6;
+	cpu_set_t cpu_set;
+	int fd;
+
+	switch (family) {
+	case AF_INET:
+		saddr4 = (struct sockaddr_in *)&saddr;
+		saddr4->sin_family = AF_INET;
+		saddr4->sin_addr.s_addr = htonl(INADDR_ANY);
+		saddr4->sin_port = 0;
+
+		daddr4 = (struct sockaddr_in *)&daddr;
+		daddr4->sin_family = AF_INET;
+		daddr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+		daddr4->sin_port = htons(PORT);
+		break;
+	case AF_INET6:
+		saddr6 = (struct sockaddr_in6 *)&saddr;
+		saddr6->sin6_family = AF_INET6;
+		saddr6->sin6_addr = in6addr_any;
+		saddr6->sin6_port = 0;
+
+		daddr6 = (struct sockaddr_in6 *)&daddr;
+		daddr6->sin6_family = AF_INET6;
+		daddr6->sin6_addr = in6addr_loopback;
+		daddr6->sin6_port = htons(PORT);
+		break;
+	default:
+		error(1, 0, "Unsupported family %d", family);
+	}
+
+	memset(&cpu_set, 0, sizeof(cpu_set));
+	CPU_SET(cpu_id, &cpu_set);
+	if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0)
+		error(1, errno, "failed to pin to cpu");
+
+	fd = socket(family, proto, 0);
+	if (fd < 0)
+		error(1, errno, "failed to create send socket");
+
+	if (bind(fd, (struct sockaddr *)&saddr, sizeof(saddr)))
+		error(1, errno, "failed to bind send socket");
+
+	if (connect(fd, (struct sockaddr *)&daddr, sizeof(daddr)))
+		error(1, errno, "failed to connect send socket");
+
+	if (send(fd, "a", 1, 0) < 0)
+		error(1, errno, "failed to send message");
+
+	close(fd);
+}
+
+static
+void receive_on_cpu(int *rcv_fd, int len, int epfd, int cpu_id, int proto)
+{
+	struct epoll_event ev;
+	int i, fd;
+	char buf[8];
+
+	i = epoll_wait(epfd, &ev, 1, -1);
+	if (i < 0)
+		error(1, errno, "epoll_wait failed");
+
+	if (proto == SOCK_STREAM) {
+		fd = accept(ev.data.fd, NULL, NULL);
+		if (fd < 0)
+			error(1, errno, "failed to accept");
+		i = recv(fd, buf, sizeof(buf), 0);
+		close(fd);
+	} else {
+		i = recv(ev.data.fd, buf, sizeof(buf), 0);
+	}
+
+	if (i < 0)
+		error(1, errno, "failed to recv");
+
+	for (i = 0; i < len; ++i)
+		if (ev.data.fd == rcv_fd[i])
+			break;
+	if (i == len)
+		error(1, 0, "failed to find socket");
+	fprintf(stderr, "send cpu %d, receive socket %d\n", cpu_id, i);
+	if (cpu_id != i)
+		error(1, 0, "cpu id/receive socket mismatch");
+}
+
+static void test(int *rcv_fd, int len, int family, int proto)
+{
+	struct epoll_event ev;
+	int epfd, cpu;
+
+	build_rcv_group(rcv_fd, len, family, proto);
+	attach_bpf(rcv_fd[0]);
+
+	epfd = epoll_create(1);
+	if (epfd < 0)
+		error(1, errno, "failed to create epoll");
+	for (cpu = 0; cpu < len; ++cpu) {
+		ev.events = EPOLLIN;
+		ev.data.fd = rcv_fd[cpu];
+		if (epoll_ctl(epfd, EPOLL_CTL_ADD, rcv_fd[cpu], &ev))
+			error(1, errno, "failed to register sock epoll");
+	}
+
+	/* Forward iterate */
+	for (cpu = 0; cpu < len; ++cpu) {
+		send_from_cpu(cpu, family, proto);
+		receive_on_cpu(rcv_fd, len, epfd, cpu, proto);
+	}
+
+	/* Reverse iterate */
+	for (cpu = len - 1; cpu >= 0; --cpu) {
+		send_from_cpu(cpu, family, proto);
+		receive_on_cpu(rcv_fd, len, epfd, cpu, proto);
+	}
+
+	/* Even cores */
+	for (cpu = 0; cpu < len; cpu += 2) {
+		send_from_cpu(cpu, family, proto);
+		receive_on_cpu(rcv_fd, len, epfd, cpu, proto);
+	}
+
+	/* Odd cores */
+	for (cpu = 1; cpu < len; cpu += 2) {
+		send_from_cpu(cpu, family, proto);
+		receive_on_cpu(rcv_fd, len, epfd, cpu, proto);
+	}
+
+	close(epfd);
+	for (cpu = 0; cpu < len; ++cpu)
+		close(rcv_fd[cpu]);
+}
+
+int main(void)
+{
+	int *rcv_fd, cpus;
+
+	cpus = sysconf(_SC_NPROCESSORS_ONLN);
+	if (cpus <= 0)
+		error(1, errno, "failed counting cpus");
+
+	rcv_fd = calloc(cpus, sizeof(int));
+	if (!rcv_fd)
+		error(1, 0, "failed to allocate array");
+
+	fprintf(stderr, "---- IPv4 UDP ----\n");
+	test(rcv_fd, cpus, AF_INET, SOCK_DGRAM);
+
+	fprintf(stderr, "---- IPv6 UDP ----\n");
+	test(rcv_fd, cpus, AF_INET6, SOCK_DGRAM);
+
+	fprintf(stderr, "---- IPv4 TCP ----\n");
+	test(rcv_fd, cpus, AF_INET, SOCK_STREAM);
+
+	fprintf(stderr, "---- IPv6 TCP ----\n");
+	test(rcv_fd, cpus, AF_INET6, SOCK_STREAM);
+
+	free(rcv_fd);
+
+	fprintf(stderr, "SUCCESS\n");
+	return 0;
+}
diff --git a/tools/testing/selftests/net/reuseport_dualstack.c b/tools/testing/selftests/net/reuseport_dualstack.c
new file mode 100644
index 000000000..90958aaaa
--- /dev/null
+++ b/tools/testing/selftests/net/reuseport_dualstack.c
@@ -0,0 +1,208 @@
+/*
+ * It is possible to use SO_REUSEPORT to open multiple sockets bound to
+ * equivalent local addresses using AF_INET and AF_INET6 at the same time.  If
+ * the AF_INET6 socket has IPV6_V6ONLY set, it's clear which socket should
+ * receive a given incoming packet.  However, when it is not set, incoming v4
+ * packets should prefer the AF_INET socket(s).  This behavior was defined with
+ * the original SO_REUSEPORT implementation, but broke with
+ * e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection")
+ * This test creates these mixed AF_INET/AF_INET6 sockets and asserts the
+ * AF_INET preference for v4 packets.
+ */
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <linux/in.h>
+#include <linux/unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/epoll.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <unistd.h>
+
+static const int PORT = 8888;
+
+static void build_rcv_fd(int family, int proto, int *rcv_fds, int count)
+{
+	struct sockaddr_storage addr;
+	struct sockaddr_in  *addr4;
+	struct sockaddr_in6 *addr6;
+	int opt, i;
+
+	switch (family) {
+	case AF_INET:
+		addr4 = (struct sockaddr_in *)&addr;
+		addr4->sin_family = AF_INET;
+		addr4->sin_addr.s_addr = htonl(INADDR_ANY);
+		addr4->sin_port = htons(PORT);
+		break;
+	case AF_INET6:
+		addr6 = (struct sockaddr_in6 *)&addr;
+		addr6->sin6_family = AF_INET6;
+		addr6->sin6_addr = in6addr_any;
+		addr6->sin6_port = htons(PORT);
+		break;
+	default:
+		error(1, 0, "Unsupported family %d", family);
+	}
+
+	for (i = 0; i < count; ++i) {
+		rcv_fds[i] = socket(family, proto, 0);
+		if (rcv_fds[i] < 0)
+			error(1, errno, "failed to create receive socket");
+
+		opt = 1;
+		if (setsockopt(rcv_fds[i], SOL_SOCKET, SO_REUSEPORT, &opt,
+			       sizeof(opt)))
+			error(1, errno, "failed to set SO_REUSEPORT");
+
+		if (bind(rcv_fds[i], (struct sockaddr *)&addr, sizeof(addr)))
+			error(1, errno, "failed to bind receive socket");
+
+		if (proto == SOCK_STREAM && listen(rcv_fds[i], 10))
+			error(1, errno, "failed to listen on receive port");
+	}
+}
+
+static void send_from_v4(int proto)
+{
+	struct sockaddr_in  saddr, daddr;
+	int fd;
+
+	saddr.sin_family = AF_INET;
+	saddr.sin_addr.s_addr = htonl(INADDR_ANY);
+	saddr.sin_port = 0;
+
+	daddr.sin_family = AF_INET;
+	daddr.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+	daddr.sin_port = htons(PORT);
+
+	fd = socket(AF_INET, proto, 0);
+	if (fd < 0)
+		error(1, errno, "failed to create send socket");
+
+	if (bind(fd, (struct sockaddr *)&saddr, sizeof(saddr)))
+		error(1, errno, "failed to bind send socket");
+
+	if (connect(fd, (struct sockaddr *)&daddr, sizeof(daddr)))
+		error(1, errno, "failed to connect send socket");
+
+	if (send(fd, "a", 1, 0) < 0)
+		error(1, errno, "failed to send message");
+
+	close(fd);
+}
+
+static int receive_once(int epfd, int proto)
+{
+	struct epoll_event ev;
+	int i, fd;
+	char buf[8];
+
+	i = epoll_wait(epfd, &ev, 1, -1);
+	if (i < 0)
+		error(1, errno, "epoll_wait failed");
+
+	if (proto == SOCK_STREAM) {
+		fd = accept(ev.data.fd, NULL, NULL);
+		if (fd < 0)
+			error(1, errno, "failed to accept");
+		i = recv(fd, buf, sizeof(buf), 0);
+		close(fd);
+	} else {
+		i = recv(ev.data.fd, buf, sizeof(buf), 0);
+	}
+
+	if (i < 0)
+		error(1, errno, "failed to recv");
+
+	return ev.data.fd;
+}
+
+static void test(int *rcv_fds, int count, int proto)
+{
+	struct epoll_event ev;
+	int epfd, i, test_fd;
+	uint16_t test_family;
+	socklen_t len;
+
+	epfd = epoll_create(1);
+	if (epfd < 0)
+		error(1, errno, "failed to create epoll");
+
+	ev.events = EPOLLIN;
+	for (i = 0; i < count; ++i) {
+		ev.data.fd = rcv_fds[i];
+		if (epoll_ctl(epfd, EPOLL_CTL_ADD, rcv_fds[i], &ev))
+			error(1, errno, "failed to register sock epoll");
+	}
+
+	send_from_v4(proto);
+
+	test_fd = receive_once(epfd, proto);
+	if (getsockopt(test_fd, SOL_SOCKET, SO_DOMAIN, &test_family, &len))
+		error(1, errno, "failed to read socket domain");
+	if (test_family != AF_INET)
+		error(1, 0, "expected to receive on v4 socket but got v6 (%d)",
+		      test_family);
+
+	close(epfd);
+}
+
+int main(void)
+{
+	int rcv_fds[32], i;
+
+	fprintf(stderr, "---- UDP IPv4 created before IPv6 ----\n");
+	build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds, 5);
+	build_rcv_fd(AF_INET6, SOCK_DGRAM, &(rcv_fds[5]), 5);
+	test(rcv_fds, 10, SOCK_DGRAM);
+	for (i = 0; i < 10; ++i)
+		close(rcv_fds[i]);
+
+	fprintf(stderr, "---- UDP IPv6 created before IPv4 ----\n");
+	build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds, 5);
+	build_rcv_fd(AF_INET, SOCK_DGRAM, &(rcv_fds[5]), 5);
+	test(rcv_fds, 10, SOCK_DGRAM);
+	for (i = 0; i < 10; ++i)
+		close(rcv_fds[i]);
+
+	/* NOTE: UDP socket lookups traverse a different code path when there
+	 * are > 10 sockets in a group.
+	 */
+	fprintf(stderr, "---- UDP IPv4 created before IPv6 (large) ----\n");
+	build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds, 16);
+	build_rcv_fd(AF_INET6, SOCK_DGRAM, &(rcv_fds[16]), 16);
+	test(rcv_fds, 32, SOCK_DGRAM);
+	for (i = 0; i < 32; ++i)
+		close(rcv_fds[i]);
+
+	fprintf(stderr, "---- UDP IPv6 created before IPv4 (large) ----\n");
+	build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds, 16);
+	build_rcv_fd(AF_INET, SOCK_DGRAM, &(rcv_fds[16]), 16);
+	test(rcv_fds, 32, SOCK_DGRAM);
+	for (i = 0; i < 32; ++i)
+		close(rcv_fds[i]);
+
+	fprintf(stderr, "---- TCP IPv4 created before IPv6 ----\n");
+	build_rcv_fd(AF_INET, SOCK_STREAM, rcv_fds, 5);
+	build_rcv_fd(AF_INET6, SOCK_STREAM, &(rcv_fds[5]), 5);
+	test(rcv_fds, 10, SOCK_STREAM);
+	for (i = 0; i < 10; ++i)
+		close(rcv_fds[i]);
+
+	fprintf(stderr, "---- TCP IPv6 created before IPv4 ----\n");
+	build_rcv_fd(AF_INET6, SOCK_STREAM, rcv_fds, 5);
+	build_rcv_fd(AF_INET, SOCK_STREAM, &(rcv_fds[5]), 5);
+	test(rcv_fds, 10, SOCK_STREAM);
+	for (i = 0; i < 10; ++i)
+		close(rcv_fds[i]);
+
+	fprintf(stderr, "SUCCESS\n");
+	return 0;
+}
diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile
index 0c2706bda..b08f77cbe 100644
--- a/tools/testing/selftests/powerpc/Makefile
+++ b/tools/testing/selftests/powerpc/Makefile
@@ -8,7 +8,7 @@ ifeq ($(ARCH),powerpc)
 
 GIT_VERSION = $(shell git describe --always --long --dirty || echo "unknown")
 
-CFLAGS := -Wall -O2 -flto -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) $(CFLAGS)
+CFLAGS := -Wall -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) $(CFLAGS)
 
 export CFLAGS
 
@@ -22,7 +22,8 @@ SUB_DIRS = benchmarks 		\
 	   switch_endian	\
 	   syscalls		\
 	   tm			\
-	   vphn
+	   vphn         \
+	   math
 
 endif
 
diff --git a/tools/testing/selftests/powerpc/basic_asm.h b/tools/testing/selftests/powerpc/basic_asm.h
new file mode 100644
index 000000000..3349a0704
--- /dev/null
+++ b/tools/testing/selftests/powerpc/basic_asm.h
@@ -0,0 +1,70 @@
+#ifndef _SELFTESTS_POWERPC_BASIC_ASM_H
+#define _SELFTESTS_POWERPC_BASIC_ASM_H
+
+#include <ppc-asm.h>
+#include <asm/unistd.h>
+
+#define LOAD_REG_IMMEDIATE(reg,expr) \
+	lis	reg,(expr)@highest;	\
+	ori	reg,reg,(expr)@higher;	\
+	rldicr	reg,reg,32,31;	\
+	oris	reg,reg,(expr)@high;	\
+	ori	reg,reg,(expr)@l;
+
+/*
+ * Note: These macros assume that variables being stored on the stack are
+ * doublewords, while this is usually the case it may not always be the
+ * case for each use case.
+ */
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define STACK_FRAME_MIN_SIZE 32
+#define STACK_FRAME_TOC_POS  24
+#define __STACK_FRAME_PARAM(_param)  (32 + ((_param)*8))
+#define __STACK_FRAME_LOCAL(_num_params,_var_num)  ((STACK_FRAME_PARAM(_num_params)) + ((_var_num)*8))
+#else
+#define STACK_FRAME_MIN_SIZE 112
+#define STACK_FRAME_TOC_POS  40
+#define __STACK_FRAME_PARAM(i)  (48 + ((i)*8))
+
+/*
+ * Caveat: if a function passed more than 8 doublewords, the caller will have
+ * made more space... which would render the 112 incorrect.
+ */
+#define __STACK_FRAME_LOCAL(_num_params,_var_num)  (112 + ((_var_num)*8))
+#endif
+
+/* Parameter x saved to the stack */
+#define STACK_FRAME_PARAM(var)    __STACK_FRAME_PARAM(var)
+
+/* Local variable x saved to the stack after x parameters */
+#define STACK_FRAME_LOCAL(num_params,var)    __STACK_FRAME_LOCAL(num_params,var)
+#define STACK_FRAME_LR_POS   16
+#define STACK_FRAME_CR_POS   8
+
+/*
+ * It is very important to note here that _extra is the extra amount of
+ * stack space needed. This space can be accessed using STACK_FRAME_PARAM()
+ * or STACK_FRAME_LOCAL() macros.
+ *
+ * r1 and r2 are not defined in ppc-asm.h (instead they are defined as sp
+ * and toc). Kernel programmers tend to prefer rX even for r1 and r2, hence
+ * %1 and %r2. r0 is defined in ppc-asm.h and therefore %r0 gets
+ * preprocessed incorrectly, hence r0.
+ */
+#define PUSH_BASIC_STACK(_extra) \
+	mflr	r0; \
+	std	r0,STACK_FRAME_LR_POS(%r1); \
+	stdu	%r1,-(_extra + STACK_FRAME_MIN_SIZE)(%r1); \
+	mfcr	r0; \
+	stw	r0,STACK_FRAME_CR_POS(%r1); \
+	std	%r2,STACK_FRAME_TOC_POS(%r1);
+
+#define POP_BASIC_STACK(_extra) \
+	ld	%r2,STACK_FRAME_TOC_POS(%r1); \
+	lwz	r0,STACK_FRAME_CR_POS(%r1); \
+	mtcr	r0; \
+	addi	%r1,%r1,(_extra + STACK_FRAME_MIN_SIZE); \
+	ld	r0,STACK_FRAME_LR_POS(%r1); \
+	mtlr	r0;
+
+#endif /* _SELFTESTS_POWERPC_BASIC_ASM_H */
diff --git a/tools/testing/selftests/powerpc/math/.gitignore b/tools/testing/selftests/powerpc/math/.gitignore
new file mode 100644
index 000000000..4fe13a439
--- /dev/null
+++ b/tools/testing/selftests/powerpc/math/.gitignore
@@ -0,0 +1,6 @@
+fpu_syscall
+vmx_syscall
+fpu_preempt
+vmx_preempt
+fpu_signal
+vmx_signal
diff --git a/tools/testing/selftests/powerpc/math/Makefile b/tools/testing/selftests/powerpc/math/Makefile
new file mode 100644
index 000000000..5b88875d5
--- /dev/null
+++ b/tools/testing/selftests/powerpc/math/Makefile
@@ -0,0 +1,19 @@
+TEST_PROGS := fpu_syscall fpu_preempt fpu_signal vmx_syscall vmx_preempt vmx_signal
+
+all: $(TEST_PROGS)
+
+$(TEST_PROGS): ../harness.c
+$(TEST_PROGS): CFLAGS += -O2 -g -pthread -m64 -maltivec
+
+fpu_syscall: fpu_asm.S
+fpu_preempt: fpu_asm.S
+fpu_signal:  fpu_asm.S
+
+vmx_syscall: vmx_asm.S
+vmx_preempt: vmx_asm.S
+vmx_signal: vmx_asm.S
+
+include ../../lib.mk
+
+clean:
+	rm -f $(TEST_PROGS) *.o
diff --git a/tools/testing/selftests/powerpc/math/fpu_asm.S b/tools/testing/selftests/powerpc/math/fpu_asm.S
new file mode 100644
index 000000000..f3711d80e
--- /dev/null
+++ b/tools/testing/selftests/powerpc/math/fpu_asm.S
@@ -0,0 +1,198 @@
+/*
+ * Copyright 2015, Cyril Bur, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include "../basic_asm.h"
+
+#define PUSH_FPU(pos) \
+	stfd	f14,pos(sp); \
+	stfd	f15,pos+8(sp); \
+	stfd	f16,pos+16(sp); \
+	stfd	f17,pos+24(sp); \
+	stfd	f18,pos+32(sp); \
+	stfd	f19,pos+40(sp); \
+	stfd	f20,pos+48(sp); \
+	stfd	f21,pos+56(sp); \
+	stfd	f22,pos+64(sp); \
+	stfd	f23,pos+72(sp); \
+	stfd	f24,pos+80(sp); \
+	stfd	f25,pos+88(sp); \
+	stfd	f26,pos+96(sp); \
+	stfd	f27,pos+104(sp); \
+	stfd	f28,pos+112(sp); \
+	stfd	f29,pos+120(sp); \
+	stfd	f30,pos+128(sp); \
+	stfd	f31,pos+136(sp);
+
+#define POP_FPU(pos) \
+	lfd	f14,pos(sp); \
+	lfd	f15,pos+8(sp); \
+	lfd	f16,pos+16(sp); \
+	lfd	f17,pos+24(sp); \
+	lfd	f18,pos+32(sp); \
+	lfd	f19,pos+40(sp); \
+	lfd	f20,pos+48(sp); \
+	lfd	f21,pos+56(sp); \
+	lfd	f22,pos+64(sp); \
+	lfd	f23,pos+72(sp); \
+	lfd	f24,pos+80(sp); \
+	lfd	f25,pos+88(sp); \
+	lfd	f26,pos+96(sp); \
+	lfd	f27,pos+104(sp); \
+	lfd	f28,pos+112(sp); \
+	lfd	f29,pos+120(sp); \
+	lfd	f30,pos+128(sp); \
+	lfd	f31,pos+136(sp);
+
+# Careful calling this, it will 'clobber' fpu (by design)
+# Don't call this from C
+FUNC_START(load_fpu)
+	lfd	f14,0(r3)
+	lfd	f15,8(r3)
+	lfd	f16,16(r3)
+	lfd	f17,24(r3)
+	lfd	f18,32(r3)
+	lfd	f19,40(r3)
+	lfd	f20,48(r3)
+	lfd	f21,56(r3)
+	lfd	f22,64(r3)
+	lfd	f23,72(r3)
+	lfd	f24,80(r3)
+	lfd	f25,88(r3)
+	lfd	f26,96(r3)
+	lfd	f27,104(r3)
+	lfd	f28,112(r3)
+	lfd	f29,120(r3)
+	lfd	f30,128(r3)
+	lfd	f31,136(r3)
+	blr
+FUNC_END(load_fpu)
+
+FUNC_START(check_fpu)
+	mr r4,r3
+	li	r3,1 # assume a bad result
+	lfd	f0,0(r4)
+	fcmpu	cr1,f0,f14
+	bne	cr1,1f
+	lfd	f0,8(r4)
+	fcmpu	cr1,f0,f15
+	bne	cr1,1f
+	lfd	f0,16(r4)
+	fcmpu	cr1,f0,f16
+	bne	cr1,1f
+	lfd	f0,24(r4)
+	fcmpu	cr1,f0,f17
+	bne	cr1,1f
+	lfd	f0,32(r4)
+	fcmpu	cr1,f0,f18
+	bne	cr1,1f
+	lfd	f0,40(r4)
+	fcmpu	cr1,f0,f19
+	bne	cr1,1f
+	lfd	f0,48(r4)
+	fcmpu	cr1,f0,f20
+	bne	cr1,1f
+	lfd	f0,56(r4)
+	fcmpu	cr1,f0,f21
+	bne	cr1,1f
+	lfd	f0,64(r4)
+	fcmpu	cr1,f0,f22
+	bne	cr1,1f
+	lfd	f0,72(r4)
+	fcmpu	cr1,f0,f23
+	bne	cr1,1f
+	lfd	f0,80(r4)
+	fcmpu	cr1,f0,f24
+	bne	cr1,1f
+	lfd	f0,88(r4)
+	fcmpu	cr1,f0,f25
+	bne	cr1,1f
+	lfd	f0,96(r4)
+	fcmpu	cr1,f0,f26
+	bne	cr1,1f
+	lfd	f0,104(r4)
+	fcmpu	cr1,f0,f27
+	bne	cr1,1f
+	lfd	f0,112(r4)
+	fcmpu	cr1,f0,f28
+	bne	cr1,1f
+	lfd	f0,120(r4)
+	fcmpu	cr1,f0,f29
+	bne	cr1,1f
+	lfd	f0,128(r4)
+	fcmpu	cr1,f0,f30
+	bne	cr1,1f
+	lfd	f0,136(r4)
+	fcmpu	cr1,f0,f31
+	bne	cr1,1f
+	li	r3,0 # Success!!!
+1:	blr
+
+FUNC_START(test_fpu)
+	# r3 holds pointer to where to put the result of fork
+	# r4 holds pointer to the pid
+	# f14-f31 are non volatiles
+	PUSH_BASIC_STACK(256)
+	std	r3,STACK_FRAME_PARAM(0)(sp) # Address of darray
+	std r4,STACK_FRAME_PARAM(1)(sp) # Address of pid
+	PUSH_FPU(STACK_FRAME_LOCAL(2,0))
+
+	bl load_fpu
+	nop
+	li	r0,__NR_fork
+	sc
+
+	# pass the result of the fork to the caller
+	ld	r9,STACK_FRAME_PARAM(1)(sp)
+	std	r3,0(r9)
+
+	ld r3,STACK_FRAME_PARAM(0)(sp)
+	bl check_fpu
+	nop
+
+	POP_FPU(STACK_FRAME_LOCAL(2,0))
+	POP_BASIC_STACK(256)
+	blr
+FUNC_END(test_fpu)
+
+# int preempt_fpu(double *darray, int *threads_running, int *running)
+# On starting will (atomically) decrement not_ready as a signal that the FPU
+# has been loaded with darray. Will proceed to check the validity of the FPU
+# registers while running is not zero.
+FUNC_START(preempt_fpu)
+	PUSH_BASIC_STACK(256)
+	std r3,STACK_FRAME_PARAM(0)(sp) # double *darray
+	std r4,STACK_FRAME_PARAM(1)(sp) # int *threads_starting
+	std r5,STACK_FRAME_PARAM(2)(sp) # int *running
+	PUSH_FPU(STACK_FRAME_LOCAL(3,0))
+
+	bl load_fpu
+	nop
+
+	sync
+	# Atomic DEC
+	ld r3,STACK_FRAME_PARAM(1)(sp)
+1:	lwarx r4,0,r3
+	addi r4,r4,-1
+	stwcx. r4,0,r3
+	bne- 1b
+
+2:	ld r3,STACK_FRAME_PARAM(0)(sp)
+	bl check_fpu
+	nop
+	cmpdi r3,0
+	bne 3f
+	ld r4,STACK_FRAME_PARAM(2)(sp)
+	ld r5,0(r4)
+	cmpwi r5,0
+	bne 2b
+
+3:	POP_FPU(STACK_FRAME_LOCAL(3,0))
+	POP_BASIC_STACK(256)
+	blr
+FUNC_END(preempt_fpu)
diff --git a/tools/testing/selftests/powerpc/math/fpu_preempt.c b/tools/testing/selftests/powerpc/math/fpu_preempt.c
new file mode 100644
index 000000000..0f85b79d8
--- /dev/null
+++ b/tools/testing/selftests/powerpc/math/fpu_preempt.c
@@ -0,0 +1,113 @@
+/*
+ * Copyright 2015, Cyril Bur, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * This test attempts to see if the FPU registers change across preemption.
+ * Two things should be noted here a) The check_fpu function in asm only checks
+ * the non volatile registers as it is reused from the syscall test b) There is
+ * no way to be sure preemption happened so this test just uses many threads
+ * and a long wait. As such, a successful test doesn't mean much but a failure
+ * is bad.
+ */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <stdlib.h>
+#include <pthread.h>
+
+#include "utils.h"
+
+/* Time to wait for workers to get preempted (seconds) */
+#define PREEMPT_TIME 20
+/*
+ * Factor by which to multiply number of online CPUs for total number of
+ * worker threads
+ */
+#define THREAD_FACTOR 8
+
+
+__thread double darray[] = {0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0,
+		     1.1, 1.2, 1.3, 1.4, 1.5, 1.6, 1.7, 1.8, 1.9, 2.0,
+		     2.1};
+
+int threads_starting;
+int running;
+
+extern void preempt_fpu(double *darray, int *threads_starting, int *running);
+
+void *preempt_fpu_c(void *p)
+{
+	int i;
+	srand(pthread_self());
+	for (i = 0; i < 21; i++)
+		darray[i] = rand();
+
+	/* Test failed if it ever returns */
+	preempt_fpu(darray, &threads_starting, &running);
+
+	return p;
+}
+
+int test_preempt_fpu(void)
+{
+	int i, rc, threads;
+	pthread_t *tids;
+
+	threads = sysconf(_SC_NPROCESSORS_ONLN) * THREAD_FACTOR;
+	tids = malloc((threads) * sizeof(pthread_t));
+	FAIL_IF(!tids);
+
+	running = true;
+	threads_starting = threads;
+	for (i = 0; i < threads; i++) {
+		rc = pthread_create(&tids[i], NULL, preempt_fpu_c, NULL);
+		FAIL_IF(rc);
+	}
+
+	setbuf(stdout, NULL);
+	/* Not really necessary but nice to wait for every thread to start */
+	printf("\tWaiting for all workers to start...");
+	while(threads_starting)
+		asm volatile("": : :"memory");
+	printf("done\n");
+
+	printf("\tWaiting for %d seconds to let some workers get preempted...", PREEMPT_TIME);
+	sleep(PREEMPT_TIME);
+	printf("done\n");
+
+	printf("\tStopping workers...");
+	/*
+	 * Working are checking this value every loop. In preempt_fpu 'cmpwi r5,0; bne 2b'.
+	 * r5 will have loaded the value of running.
+	 */
+	running = 0;
+	for (i = 0; i < threads; i++) {
+		void *rc_p;
+		pthread_join(tids[i], &rc_p);
+
+		/*
+		 * Harness will say the fail was here, look at why preempt_fpu
+		 * returned
+		 */
+		if ((long) rc_p)
+			printf("oops\n");
+		FAIL_IF((long) rc_p);
+	}
+	printf("done\n");
+
+	free(tids);
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	return test_harness(test_preempt_fpu, "fpu_preempt");
+}
diff --git a/tools/testing/selftests/powerpc/math/fpu_signal.c b/tools/testing/selftests/powerpc/math/fpu_signal.c
new file mode 100644
index 000000000..888aa51b4
--- /dev/null
+++ b/tools/testing/selftests/powerpc/math/fpu_signal.c
@@ -0,0 +1,135 @@
+/*
+ * Copyright 2015, Cyril Bur, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * This test attempts to see if the FPU registers are correctly reported in a
+ * signal context. Each worker just spins checking its FPU registers, at some
+ * point a signal will interrupt it and C code will check the signal context
+ * ensuring it is also the same.
+ */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <stdlib.h>
+#include <pthread.h>
+
+#include "utils.h"
+
+/* Number of times each thread should receive the signal */
+#define ITERATIONS 10
+/*
+ * Factor by which to multiply number of online CPUs for total number of
+ * worker threads
+ */
+#define THREAD_FACTOR 8
+
+__thread double darray[] = {0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0,
+		     1.1, 1.2, 1.3, 1.4, 1.5, 1.6, 1.7, 1.8, 1.9, 2.0,
+		     2.1};
+
+bool bad_context;
+int threads_starting;
+int running;
+
+extern long preempt_fpu(double *darray, int *threads_starting, int *running);
+
+void signal_fpu_sig(int sig, siginfo_t *info, void *context)
+{
+	int i;
+	ucontext_t *uc = context;
+	mcontext_t *mc = &uc->uc_mcontext;
+
+	/* Only the non volatiles were loaded up */
+	for (i = 14; i < 32; i++) {
+		if (mc->fp_regs[i] != darray[i - 14]) {
+			bad_context = true;
+			break;
+		}
+	}
+}
+
+void *signal_fpu_c(void *p)
+{
+	int i;
+	long rc;
+	struct sigaction act;
+	act.sa_sigaction = signal_fpu_sig;
+	act.sa_flags = SA_SIGINFO;
+	rc = sigaction(SIGUSR1, &act, NULL);
+	if (rc)
+		return p;
+
+	srand(pthread_self());
+	for (i = 0; i < 21; i++)
+		darray[i] = rand();
+
+	rc = preempt_fpu(darray, &threads_starting, &running);
+
+	return (void *) rc;
+}
+
+int test_signal_fpu(void)
+{
+	int i, j, rc, threads;
+	void *rc_p;
+	pthread_t *tids;
+
+	threads = sysconf(_SC_NPROCESSORS_ONLN) * THREAD_FACTOR;
+	tids = malloc(threads * sizeof(pthread_t));
+	FAIL_IF(!tids);
+
+	running = true;
+	threads_starting = threads;
+	for (i = 0; i < threads; i++) {
+		rc = pthread_create(&tids[i], NULL, signal_fpu_c, NULL);
+		FAIL_IF(rc);
+	}
+
+	setbuf(stdout, NULL);
+	printf("\tWaiting for all workers to start...");
+	while (threads_starting)
+		asm volatile("": : :"memory");
+	printf("done\n");
+
+	printf("\tSending signals to all threads %d times...", ITERATIONS);
+	for (i = 0; i < ITERATIONS; i++) {
+		for (j = 0; j < threads; j++) {
+			pthread_kill(tids[j], SIGUSR1);
+		}
+		sleep(1);
+	}
+	printf("done\n");
+
+	printf("\tStopping workers...");
+	running = 0;
+	for (i = 0; i < threads; i++) {
+		pthread_join(tids[i], &rc_p);
+
+		/*
+		 * Harness will say the fail was here, look at why signal_fpu
+		 * returned
+		 */
+		if ((long) rc_p || bad_context)
+			printf("oops\n");
+		if (bad_context)
+			fprintf(stderr, "\t!! bad_context is true\n");
+		FAIL_IF((long) rc_p || bad_context);
+	}
+	printf("done\n");
+
+	free(tids);
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	return test_harness(test_signal_fpu, "fpu_signal");
+}
diff --git a/tools/testing/selftests/powerpc/math/fpu_syscall.c b/tools/testing/selftests/powerpc/math/fpu_syscall.c
new file mode 100644
index 000000000..949e67212
--- /dev/null
+++ b/tools/testing/selftests/powerpc/math/fpu_syscall.c
@@ -0,0 +1,90 @@
+/*
+ * Copyright 2015, Cyril Bur, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * This test attempts to see if the FPU registers change across a syscall (fork).
+ */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <stdlib.h>
+
+#include "utils.h"
+
+extern int test_fpu(double *darray, pid_t *pid);
+
+double darray[] = {0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0,
+		     1.1, 1.2, 1.3, 1.4, 1.5, 1.6, 1.7, 1.8, 1.9, 2.0,
+		     2.1};
+
+int syscall_fpu(void)
+{
+	pid_t fork_pid;
+	int i;
+	int ret;
+	int child_ret;
+	for (i = 0; i < 1000; i++) {
+		/* test_fpu will fork() */
+		ret = test_fpu(darray, &fork_pid);
+		if (fork_pid == -1)
+			return -1;
+		if (fork_pid == 0)
+			exit(ret);
+		waitpid(fork_pid, &child_ret, 0);
+		if (ret || child_ret)
+			return 1;
+	}
+
+	return 0;
+}
+
+int test_syscall_fpu(void)
+{
+	/*
+	 * Setup an environment with much context switching
+	 */
+	pid_t pid2;
+	pid_t pid = fork();
+	int ret;
+	int child_ret;
+	FAIL_IF(pid == -1);
+
+	pid2 = fork();
+	/* Can't FAIL_IF(pid2 == -1); because already forked once */
+	if (pid2 == -1) {
+		/*
+		 * Couldn't fork, ensure test is a fail
+		 */
+		child_ret = ret = 1;
+	} else {
+		ret = syscall_fpu();
+		if (pid2)
+			waitpid(pid2, &child_ret, 0);
+		else
+			exit(ret);
+	}
+
+	ret |= child_ret;
+
+	if (pid)
+		waitpid(pid, &child_ret, 0);
+	else
+		exit(ret);
+
+	FAIL_IF(ret || child_ret);
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	return test_harness(test_syscall_fpu, "syscall_fpu");
+
+}
diff --git a/tools/testing/selftests/powerpc/math/vmx_asm.S b/tools/testing/selftests/powerpc/math/vmx_asm.S
new file mode 100644
index 000000000..1b8c248b3
--- /dev/null
+++ b/tools/testing/selftests/powerpc/math/vmx_asm.S
@@ -0,0 +1,235 @@
+/*
+ * Copyright 2015, Cyril Bur, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include "../basic_asm.h"
+
+# POS MUST BE 16 ALIGNED!
+#define PUSH_VMX(pos,reg) \
+	li	reg,pos; \
+	stvx	v20,reg,sp; \
+	addi	reg,reg,16; \
+	stvx	v21,reg,sp; \
+	addi	reg,reg,16; \
+	stvx	v22,reg,sp; \
+	addi	reg,reg,16; \
+	stvx	v23,reg,sp; \
+	addi	reg,reg,16; \
+	stvx	v24,reg,sp; \
+	addi	reg,reg,16; \
+	stvx	v25,reg,sp; \
+	addi	reg,reg,16; \
+	stvx	v26,reg,sp; \
+	addi	reg,reg,16; \
+	stvx	v27,reg,sp; \
+	addi	reg,reg,16; \
+	stvx	v28,reg,sp; \
+	addi	reg,reg,16; \
+	stvx	v29,reg,sp; \
+	addi	reg,reg,16; \
+	stvx	v30,reg,sp; \
+	addi	reg,reg,16; \
+	stvx	v31,reg,sp;
+
+# POS MUST BE 16 ALIGNED!
+#define POP_VMX(pos,reg) \
+	li	reg,pos; \
+	lvx	v20,reg,sp; \
+	addi	reg,reg,16; \
+	lvx	v21,reg,sp; \
+	addi	reg,reg,16; \
+	lvx	v22,reg,sp; \
+	addi	reg,reg,16; \
+	lvx	v23,reg,sp; \
+	addi	reg,reg,16; \
+	lvx	v24,reg,sp; \
+	addi	reg,reg,16; \
+	lvx	v25,reg,sp; \
+	addi	reg,reg,16; \
+	lvx	v26,reg,sp; \
+	addi	reg,reg,16; \
+	lvx	v27,reg,sp; \
+	addi	reg,reg,16; \
+	lvx	v28,reg,sp; \
+	addi	reg,reg,16; \
+	lvx	v29,reg,sp; \
+	addi	reg,reg,16; \
+	lvx	v30,reg,sp; \
+	addi	reg,reg,16; \
+	lvx	v31,reg,sp;
+
+# Carefull this will 'clobber' vmx (by design)
+# Don't call this from C
+FUNC_START(load_vmx)
+	li	r5,0
+	lvx	v20,r5,r3
+	addi	r5,r5,16
+	lvx	v21,r5,r3
+	addi	r5,r5,16
+	lvx	v22,r5,r3
+	addi	r5,r5,16
+	lvx	v23,r5,r3
+	addi	r5,r5,16
+	lvx	v24,r5,r3
+	addi	r5,r5,16
+	lvx	v25,r5,r3
+	addi	r5,r5,16
+	lvx	v26,r5,r3
+	addi	r5,r5,16
+	lvx	v27,r5,r3
+	addi	r5,r5,16
+	lvx	v28,r5,r3
+	addi	r5,r5,16
+	lvx	v29,r5,r3
+	addi	r5,r5,16
+	lvx	v30,r5,r3
+	addi	r5,r5,16
+	lvx	v31,r5,r3
+	blr
+FUNC_END(load_vmx)
+
+# Should be safe from C, only touches r4, r5 and v0,v1,v2
+FUNC_START(check_vmx)
+	PUSH_BASIC_STACK(32)
+	mr r4,r3
+	li	r3,1 # assume a bad result
+	li	r5,0
+	lvx	v0,r5,r4
+	vcmpequd.	v1,v0,v20
+	vmr	v2,v1
+
+	addi	r5,r5,16
+	lvx	v0,r5,r4
+	vcmpequd.	v1,v0,v21
+	vand	v2,v2,v1
+
+	addi	r5,r5,16
+	lvx	v0,r5,r4
+	vcmpequd.	v1,v0,v22
+	vand	v2,v2,v1
+
+	addi	r5,r5,16
+	lvx	v0,r5,r4
+	vcmpequd.	v1,v0,v23
+	vand	v2,v2,v1
+
+	addi	r5,r5,16
+	lvx	v0,r5,r4
+	vcmpequd.	v1,v0,v24
+	vand	v2,v2,v1
+
+	addi	r5,r5,16
+	lvx	v0,r5,r4
+	vcmpequd.	v1,v0,v25
+	vand	v2,v2,v1
+
+	addi	r5,r5,16
+	lvx	v0,r5,r4
+	vcmpequd.	v1,v0,v26
+	vand	v2,v2,v1
+
+	addi	r5,r5,16
+	lvx	v0,r5,r4
+	vcmpequd.	v1,v0,v27
+	vand	v2,v2,v1
+
+	addi	r5,r5,16
+	lvx	v0,r5,r4
+	vcmpequd.	v1,v0,v28
+	vand	v2,v2,v1
+
+	addi	r5,r5,16
+	lvx	v0,r5,r4
+	vcmpequd.	v1,v0,v29
+	vand	v2,v2,v1
+
+	addi	r5,r5,16
+	lvx	v0,r5,r4
+	vcmpequd.	v1,v0,v30
+	vand	v2,v2,v1
+
+	addi	r5,r5,16
+	lvx	v0,r5,r4
+	vcmpequd.	v1,v0,v31
+	vand	v2,v2,v1
+
+	li	r5,STACK_FRAME_LOCAL(0,0)
+	stvx	v2,r5,sp
+	ldx	r0,r5,sp
+	cmpdi	r0,0xffffffffffffffff
+	bne	1f
+	li	r3,0
+1:	POP_BASIC_STACK(32)
+	blr
+FUNC_END(check_vmx)
+
+# Safe from C
+FUNC_START(test_vmx)
+	# r3 holds pointer to where to put the result of fork
+	# r4 holds pointer to the pid
+	# v20-v31 are non-volatile
+	PUSH_BASIC_STACK(512)
+	std	r3,STACK_FRAME_PARAM(0)(sp) # Address of varray
+	std r4,STACK_FRAME_PARAM(1)(sp) # address of pid
+	PUSH_VMX(STACK_FRAME_LOCAL(2,0),r4)
+
+	bl load_vmx
+	nop
+
+	li	r0,__NR_fork
+	sc
+	# Pass the result of fork back to the caller
+	ld	r9,STACK_FRAME_PARAM(1)(sp)
+	std	r3,0(r9)
+
+	ld r3,STACK_FRAME_PARAM(0)(sp)
+	bl check_vmx
+	nop
+
+	POP_VMX(STACK_FRAME_LOCAL(2,0),r4)
+	POP_BASIC_STACK(512)
+	blr
+FUNC_END(test_vmx)
+
+# int preempt_vmx(vector int *varray, int *threads_starting, int *running)
+# On starting will (atomically) decrement threads_starting as a signal that
+# the VMX have been loaded with varray. Will proceed to check the validity of
+# the VMX registers while running is not zero.
+FUNC_START(preempt_vmx)
+	PUSH_BASIC_STACK(512)
+	std r3,STACK_FRAME_PARAM(0)(sp) # vector int *varray
+	std r4,STACK_FRAME_PARAM(1)(sp) # int *threads_starting
+	std r5,STACK_FRAME_PARAM(2)(sp) # int *running
+	# VMX need to write to 16 byte aligned addresses, skip STACK_FRAME_LOCAL(3,0)
+	PUSH_VMX(STACK_FRAME_LOCAL(4,0),r4)
+
+	bl load_vmx
+	nop
+
+	sync
+	# Atomic DEC
+	ld r3,STACK_FRAME_PARAM(1)(sp)
+1:	lwarx r4,0,r3
+	addi r4,r4,-1
+	stwcx. r4,0,r3
+	bne- 1b
+
+2:	ld r3,STACK_FRAME_PARAM(0)(sp)
+	bl check_vmx
+	nop
+	cmpdi r3,0
+	bne 3f
+	ld r4,STACK_FRAME_PARAM(2)(sp)
+	ld r5,0(r4)
+	cmpwi r5,0
+	bne 2b
+
+3:	POP_VMX(STACK_FRAME_LOCAL(4,0),r4)
+	POP_BASIC_STACK(512)
+	blr
+FUNC_END(preempt_vmx)
diff --git a/tools/testing/selftests/powerpc/math/vmx_preempt.c b/tools/testing/selftests/powerpc/math/vmx_preempt.c
new file mode 100644
index 000000000..9ef376c55
--- /dev/null
+++ b/tools/testing/selftests/powerpc/math/vmx_preempt.c
@@ -0,0 +1,112 @@
+/*
+ * Copyright 2015, Cyril Bur, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * This test attempts to see if the VMX registers change across preemption.
+ * Two things should be noted here a) The check_vmx function in asm only checks
+ * the non volatile registers as it is reused from the syscall test b) There is
+ * no way to be sure preemption happened so this test just uses many threads
+ * and a long wait. As such, a successful test doesn't mean much but a failure
+ * is bad.
+ */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <stdlib.h>
+#include <pthread.h>
+
+#include "utils.h"
+
+/* Time to wait for workers to get preempted (seconds) */
+#define PREEMPT_TIME 20
+/*
+ * Factor by which to multiply number of online CPUs for total number of
+ * worker threads
+ */
+#define THREAD_FACTOR 8
+
+__thread vector int varray[] = {{1, 2, 3, 4}, {5, 6, 7, 8}, {9, 10,11,12},
+	{13,14,15,16},{17,18,19,20},{21,22,23,24},
+	{25,26,27,28},{29,30,31,32},{33,34,35,36},
+	{37,38,39,40},{41,42,43,44},{45,46,47,48}};
+
+int threads_starting;
+int running;
+
+extern void preempt_vmx(vector int *varray, int *threads_starting, int *running);
+
+void *preempt_vmx_c(void *p)
+{
+	int i, j;
+	srand(pthread_self());
+	for (i = 0; i < 12; i++)
+		for (j = 0; j < 4; j++)
+			varray[i][j] = rand();
+
+	/* Test fails if it ever returns */
+	preempt_vmx(varray, &threads_starting, &running);
+	return p;
+}
+
+int test_preempt_vmx(void)
+{
+	int i, rc, threads;
+	pthread_t *tids;
+
+	threads = sysconf(_SC_NPROCESSORS_ONLN) * THREAD_FACTOR;
+	tids = malloc(threads * sizeof(pthread_t));
+	FAIL_IF(!tids);
+
+	running = true;
+	threads_starting = threads;
+	for (i = 0; i < threads; i++) {
+		rc = pthread_create(&tids[i], NULL, preempt_vmx_c, NULL);
+		FAIL_IF(rc);
+	}
+
+	setbuf(stdout, NULL);
+	/* Not really nessesary but nice to wait for every thread to start */
+	printf("\tWaiting for all workers to start...");
+	while(threads_starting)
+		asm volatile("": : :"memory");
+	printf("done\n");
+
+	printf("\tWaiting for %d seconds to let some workers get preempted...", PREEMPT_TIME);
+	sleep(PREEMPT_TIME);
+	printf("done\n");
+
+	printf("\tStopping workers...");
+	/*
+	 * Working are checking this value every loop. In preempt_vmx 'cmpwi r5,0; bne 2b'.
+	 * r5 will have loaded the value of running.
+	 */
+	running = 0;
+	for (i = 0; i < threads; i++) {
+		void *rc_p;
+		pthread_join(tids[i], &rc_p);
+
+		/*
+		 * Harness will say the fail was here, look at why preempt_vmx
+		 * returned
+		 */
+		if ((long) rc_p)
+			printf("oops\n");
+		FAIL_IF((long) rc_p);
+	}
+	printf("done\n");
+
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	return test_harness(test_preempt_vmx, "vmx_preempt");
+}
diff --git a/tools/testing/selftests/powerpc/math/vmx_signal.c b/tools/testing/selftests/powerpc/math/vmx_signal.c
new file mode 100644
index 000000000..671d7533a
--- /dev/null
+++ b/tools/testing/selftests/powerpc/math/vmx_signal.c
@@ -0,0 +1,156 @@
+/*
+ * Copyright 2015, Cyril Bur, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * This test attempts to see if the VMX registers are correctly reported in a
+ * signal context. Each worker just spins checking its VMX registers, at some
+ * point a signal will interrupt it and C code will check the signal context
+ * ensuring it is also the same.
+ */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <stdlib.h>
+#include <string.h>
+#include <pthread.h>
+#include <altivec.h>
+
+#include "utils.h"
+
+/* Number of times each thread should receive the signal */
+#define ITERATIONS 10
+/*
+ * Factor by which to multiply number of online CPUs for total number of
+ * worker threads
+ */
+#define THREAD_FACTOR 8
+
+__thread vector int varray[] = {{1, 2, 3, 4}, {5, 6, 7, 8}, {9, 10,11,12},
+	{13,14,15,16},{17,18,19,20},{21,22,23,24},
+	{25,26,27,28},{29,30,31,32},{33,34,35,36},
+	{37,38,39,40},{41,42,43,44},{45,46,47,48}};
+
+bool bad_context;
+int running;
+int threads_starting;
+
+extern int preempt_vmx(vector int *varray, int *threads_starting, int *sentinal);
+
+void signal_vmx_sig(int sig, siginfo_t *info, void *context)
+{
+	int i;
+	ucontext_t *uc = context;
+	mcontext_t *mc = &uc->uc_mcontext;
+
+	/* Only the non volatiles were loaded up */
+	for (i = 20; i < 32; i++) {
+		if (memcmp(mc->v_regs->vrregs[i], &varray[i - 20], 16)) {
+			int j;
+			/*
+			 * Shouldn't printf() in a signal handler, however, this is a
+			 * test and we've detected failure. Understanding what failed
+			 * is paramount. All that happens after this is tests exit with
+			 * failure.
+			 */
+			printf("VMX mismatch at reg %d!\n", i);
+			printf("Reg | Actual                  | Expected\n");
+			for (j = 20; j < 32; j++) {
+				printf("%d  | 0x%04x%04x%04x%04x      | 0x%04x%04x%04x%04x\n", j, mc->v_regs->vrregs[j][0],
+					   mc->v_regs->vrregs[j][1], mc->v_regs->vrregs[j][2], mc->v_regs->vrregs[j][3],
+					   varray[j - 20][0], varray[j - 20][1], varray[j - 20][2], varray[j - 20][3]);
+			}
+			bad_context = true;
+			break;
+		}
+	}
+}
+
+void *signal_vmx_c(void *p)
+{
+	int i, j;
+	long rc;
+	struct sigaction act;
+	act.sa_sigaction = signal_vmx_sig;
+	act.sa_flags = SA_SIGINFO;
+	rc = sigaction(SIGUSR1, &act, NULL);
+	if (rc)
+		return p;
+
+	srand(pthread_self());
+	for (i = 0; i < 12; i++)
+		for (j = 0; j < 4; j++)
+			varray[i][j] = rand();
+
+	rc = preempt_vmx(varray, &threads_starting, &running);
+
+	return (void *) rc;
+}
+
+int test_signal_vmx(void)
+{
+	int i, j, rc, threads;
+	void *rc_p;
+	pthread_t *tids;
+
+	threads = sysconf(_SC_NPROCESSORS_ONLN) * THREAD_FACTOR;
+	tids = malloc(threads * sizeof(pthread_t));
+	FAIL_IF(!tids);
+
+	running = true;
+	threads_starting = threads;
+	for (i = 0; i < threads; i++) {
+		rc = pthread_create(&tids[i], NULL, signal_vmx_c, NULL);
+		FAIL_IF(rc);
+	}
+
+	setbuf(stdout, NULL);
+	printf("\tWaiting for %d workers to start... %d", threads, threads_starting);
+	while (threads_starting) {
+		asm volatile("": : :"memory");
+		usleep(1000);
+		printf(", %d", threads_starting);
+	}
+	printf(" ...done\n");
+
+	printf("\tSending signals to all threads %d times...", ITERATIONS);
+	for (i = 0; i < ITERATIONS; i++) {
+		for (j = 0; j < threads; j++) {
+			pthread_kill(tids[j], SIGUSR1);
+		}
+		sleep(1);
+	}
+	printf("done\n");
+
+	printf("\tKilling workers...");
+	running = 0;
+	for (i = 0; i < threads; i++) {
+		pthread_join(tids[i], &rc_p);
+
+		/*
+		 * Harness will say the fail was here, look at why signal_vmx
+		 * returned
+		 */
+		if ((long) rc_p || bad_context)
+			printf("oops\n");
+		if (bad_context)
+			fprintf(stderr, "\t!! bad_context is true\n");
+		FAIL_IF((long) rc_p || bad_context);
+	}
+	printf("done\n");
+
+	free(tids);
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	return test_harness(test_signal_vmx, "vmx_signal");
+}
diff --git a/tools/testing/selftests/powerpc/math/vmx_syscall.c b/tools/testing/selftests/powerpc/math/vmx_syscall.c
new file mode 100644
index 000000000..a017918ee
--- /dev/null
+++ b/tools/testing/selftests/powerpc/math/vmx_syscall.c
@@ -0,0 +1,91 @@
+/*
+ * Copyright 2015, Cyril Bur, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * This test attempts to see if the VMX registers change across a syscall (fork).
+ */
+
+#include <altivec.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/time.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include "utils.h"
+
+vector int varray[] = {{1, 2, 3, 4}, {5, 6, 7, 8}, {9, 10,11,12},
+	{13,14,15,16},{17,18,19,20},{21,22,23,24},
+	{25,26,27,28},{29,30,31,32},{33,34,35,36},
+	{37,38,39,40},{41,42,43,44},{45,46,47,48}};
+
+extern int test_vmx(vector int *varray, pid_t *pid);
+
+int vmx_syscall(void)
+{
+	pid_t fork_pid;
+	int i;
+	int ret;
+	int child_ret;
+	for (i = 0; i < 1000; i++) {
+		/* test_vmx will fork() */
+		ret = test_vmx(varray, &fork_pid);
+		if (fork_pid == -1)
+			return -1;
+		if (fork_pid == 0)
+			exit(ret);
+		waitpid(fork_pid, &child_ret, 0);
+		if (ret || child_ret)
+			return 1;
+	}
+
+	return 0;
+}
+
+int test_vmx_syscall(void)
+{
+	/*
+	 * Setup an environment with much context switching
+	 */
+	pid_t pid2;
+	pid_t pid = fork();
+	int ret;
+	int child_ret;
+	FAIL_IF(pid == -1);
+
+	pid2 = fork();
+	ret = vmx_syscall();
+	/* Can't FAIL_IF(pid2 == -1); because we've already forked */
+	if (pid2 == -1) {
+		/*
+		 * Couldn't fork, ensure child_ret is set and is a fail
+		 */
+		ret = child_ret = 1;
+	} else {
+		if (pid2)
+			waitpid(pid2, &child_ret, 0);
+		else
+			exit(ret);
+	}
+
+	ret |= child_ret;
+
+	if (pid)
+		waitpid(pid, &child_ret, 0);
+	else
+		exit(ret);
+
+	FAIL_IF(ret || child_ret);
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	return test_harness(test_vmx_syscall, "vmx_syscall");
+
+}
diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-msr-resv.c b/tools/testing/selftests/powerpc/tm/tm-signal-msr-resv.c
index d86653f28..8c54d18b3 100644
--- a/tools/testing/selftests/powerpc/tm/tm-signal-msr-resv.c
+++ b/tools/testing/selftests/powerpc/tm/tm-signal-msr-resv.c
@@ -40,7 +40,7 @@ void signal_usr1(int signum, siginfo_t *info, void *uc)
 #ifdef __powerpc64__
 	ucp->uc_mcontext.gp_regs[PT_MSR] |= (7ULL << 32);
 #else
-	ucp->uc_mcontext.regs->gpr[PT_MSR] |= (7ULL);
+	ucp->uc_mcontext.uc_regs->gregs[PT_MSR] |= (7ULL);
 #endif
 	/* Should segv on return becuase of invalid context */
 	segv_expected = 1;
diff --git a/tools/testing/selftests/pstore/config b/tools/testing/selftests/pstore/config
new file mode 100644
index 000000000..6a8e5a9bf
--- /dev/null
+++ b/tools/testing/selftests/pstore/config
@@ -0,0 +1,4 @@
+CONFIG_MISC_FILESYSTEMS=y
+CONFIG_PSTORE=y
+CONFIG_PSTORE_PMSG=y
+CONFIG_PSTORE_CONSOLE=y
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index 844787a0d..5eb49b7f8 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -33,7 +33,7 @@ if grep -Pq '\x00' < $file
 then
 	print_warning Console output contains nul bytes, old qemu still running?
 fi
-egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|Stall ended before state dump start' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $1.diags
+egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $1.diags
 if test -s $1.diags
 then
 	print_warning Assertion failure in $file $title
@@ -64,10 +64,12 @@ then
 	then
 		summary="$summary  lockdep: $n_badness"
 	fi
-	n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|Stall ended before state dump start' $1`
+	n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state' $1`
 	if test "$n_stalls" -ne 0
 	then
 		summary="$summary  Stalls: $n_stalls"
 	fi
 	print_warning Summary: $summary
+else
+	rm $1.diags
 fi
diff --git a/tools/testing/selftests/seccomp/config b/tools/testing/selftests/seccomp/config
new file mode 100644
index 000000000..db1e11b08
--- /dev/null
+++ b/tools/testing/selftests/seccomp/config
@@ -0,0 +1,2 @@
+CONFIG_SECCOMP=y
+CONFIG_SECCOMP_FILTER=y
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index b9453b838..150829dd7 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -1497,15 +1497,15 @@ TEST_F(TRACE_syscall, syscall_dropped)
 #define SECCOMP_SET_MODE_FILTER 1
 #endif
 
-#ifndef SECCOMP_FLAG_FILTER_TSYNC
-#define SECCOMP_FLAG_FILTER_TSYNC 1
+#ifndef SECCOMP_FILTER_FLAG_TSYNC
+#define SECCOMP_FILTER_FLAG_TSYNC 1
 #endif
 
 #ifndef seccomp
-int seccomp(unsigned int op, unsigned int flags, struct sock_fprog *filter)
+int seccomp(unsigned int op, unsigned int flags, void *args)
 {
 	errno = 0;
-	return syscall(__NR_seccomp, op, flags, filter);
+	return syscall(__NR_seccomp, op, flags, args);
 }
 #endif
 
@@ -1613,7 +1613,7 @@ TEST(TSYNC_first)
 		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
 	}
 
-	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
 		      &prog);
 	ASSERT_NE(ENOSYS, errno) {
 		TH_LOG("Kernel does not support seccomp syscall!");
@@ -1831,7 +1831,7 @@ TEST_F(TSYNC, two_siblings_with_ancestor)
 		self->sibling_count++;
 	}
 
-	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
 		      &self->apply_prog);
 	ASSERT_EQ(0, ret) {
 		TH_LOG("Could install filter on all threads!");
@@ -1892,7 +1892,7 @@ TEST_F(TSYNC, two_siblings_with_no_filter)
 		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
 	}
 
-	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
 		      &self->apply_prog);
 	ASSERT_NE(ENOSYS, errno) {
 		TH_LOG("Kernel does not support seccomp syscall!");
@@ -1940,7 +1940,7 @@ TEST_F(TSYNC, two_siblings_with_one_divergence)
 		self->sibling_count++;
 	}
 
-	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
 		      &self->apply_prog);
 	ASSERT_EQ(self->sibling[0].system_tid, ret) {
 		TH_LOG("Did not fail on diverged sibling.");
@@ -1992,7 +1992,7 @@ TEST_F(TSYNC, two_siblings_not_under_filter)
 		TH_LOG("Kernel does not support SECCOMP_SET_MODE_FILTER!");
 	}
 
-	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
 		      &self->apply_prog);
 	ASSERT_EQ(ret, self->sibling[0].system_tid) {
 		TH_LOG("Did not fail on diverged sibling.");
@@ -2021,7 +2021,7 @@ TEST_F(TSYNC, two_siblings_not_under_filter)
 	/* Switch to the remaining sibling */
 	sib = !sib;
 
-	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
 		      &self->apply_prog);
 	ASSERT_EQ(0, ret) {
 		TH_LOG("Expected the remaining sibling to sync");
@@ -2044,7 +2044,7 @@ TEST_F(TSYNC, two_siblings_not_under_filter)
 	while (!kill(self->sibling[sib].system_tid, 0))
 		sleep(0.1);
 
-	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
 		      &self->apply_prog);
 	ASSERT_EQ(0, ret);  /* just us chickens */
 }
diff --git a/tools/testing/selftests/static_keys/config b/tools/testing/selftests/static_keys/config
new file mode 100644
index 000000000..d538fb774
--- /dev/null
+++ b/tools/testing/selftests/static_keys/config
@@ -0,0 +1 @@
+CONFIG_TEST_STATIC_KEYS=m
diff --git a/tools/testing/selftests/timers/alarmtimer-suspend.c b/tools/testing/selftests/timers/alarmtimer-suspend.c
index 72cacf538..2b361b830 100644
--- a/tools/testing/selftests/timers/alarmtimer-suspend.c
+++ b/tools/testing/selftests/timers/alarmtimer-suspend.c
@@ -153,7 +153,7 @@ int main(void)
 
 		alarmcount = 0;
 		if (timer_create(alarm_clock_id, &se, &tm1) == -1) {
-			printf("timer_create failled, %s unspported?\n",
+			printf("timer_create failed, %s unsupported?\n",
 					clockstring(alarm_clock_id));
 			break;
 		}
diff --git a/tools/testing/selftests/user/config b/tools/testing/selftests/user/config
new file mode 100644
index 000000000..784ed8416
--- /dev/null
+++ b/tools/testing/selftests/user/config
@@ -0,0 +1 @@
+CONFIG_TEST_USER_COPY=m
diff --git a/tools/testing/selftests/vm/config b/tools/testing/selftests/vm/config
new file mode 100644
index 000000000..698c7ed28
--- /dev/null
+++ b/tools/testing/selftests/vm/config
@@ -0,0 +1 @@
+CONFIG_USERFAULTFD=y
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index d0c473f65..b47ebd170 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -4,15 +4,16 @@ include ../lib.mk
 
 .PHONY: all all_32 all_64 warn_32bit_failure clean
 
-TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall
-TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault sigreturn test_syscall_vdso unwind_vdso \
+TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall \
+			check_initial_reg_state sigreturn ldt_gdt iopl
+TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
 			test_FCMOV test_FCOMI test_FISTTP \
-			ldt_gdt \
 			vdso_restorer
 
 TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY)
+TARGETS_C_64BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_64BIT_ONLY)
 BINARIES_32 := $(TARGETS_C_32BIT_ALL:%=%_32)
-BINARIES_64 := $(TARGETS_C_BOTHBITS:%=%_64)
+BINARIES_64 := $(TARGETS_C_64BIT_ALL:%=%_64)
 
 CFLAGS := -O2 -g -std=gnu99 -pthread -Wall
 
@@ -40,7 +41,7 @@ clean:
 $(TARGETS_C_32BIT_ALL:%=%_32): %_32: %.c
 	$(CC) -m32 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl -lm
 
-$(TARGETS_C_BOTHBITS:%=%_64): %_64: %.c
+$(TARGETS_C_64BIT_ALL:%=%_64): %_64: %.c
 	$(CC) -m64 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl
 
 # x86_64 users should be encouraged to install 32-bit libraries
@@ -65,3 +66,9 @@ endif
 sysret_ss_attrs_64: thunks.S
 ptrace_syscall_32: raw_syscall_helper_32.S
 test_syscall_vdso_32: thunks_32.S
+
+# check_initial_reg_state is special: it needs a custom entry, and it
+# needs to be static so that its interpreter doesn't destroy its initial
+# state.
+check_initial_reg_state_32: CFLAGS += -Wl,-ereal_start -static
+check_initial_reg_state_64: CFLAGS += -Wl,-ereal_start -static
diff --git a/tools/testing/selftests/x86/check_initial_reg_state.c b/tools/testing/selftests/x86/check_initial_reg_state.c
new file mode 100644
index 000000000..6aaed9b85
--- /dev/null
+++ b/tools/testing/selftests/x86/check_initial_reg_state.c
@@ -0,0 +1,109 @@
+/*
+ * check_initial_reg_state.c - check that execve sets the correct state
+ * Copyright (c) 2014-2016 Andrew Lutomirski
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+
+unsigned long ax, bx, cx, dx, si, di, bp, sp, flags;
+unsigned long r8, r9, r10, r11, r12, r13, r14, r15;
+
+asm (
+	".pushsection .text\n\t"
+	".type real_start, @function\n\t"
+	".global real_start\n\t"
+	"real_start:\n\t"
+#ifdef __x86_64__
+	"mov %rax, ax\n\t"
+	"mov %rbx, bx\n\t"
+	"mov %rcx, cx\n\t"
+	"mov %rdx, dx\n\t"
+	"mov %rsi, si\n\t"
+	"mov %rdi, di\n\t"
+	"mov %rbp, bp\n\t"
+	"mov %rsp, sp\n\t"
+	"mov %r8, r8\n\t"
+	"mov %r9, r9\n\t"
+	"mov %r10, r10\n\t"
+	"mov %r11, r11\n\t"
+	"mov %r12, r12\n\t"
+	"mov %r13, r13\n\t"
+	"mov %r14, r14\n\t"
+	"mov %r15, r15\n\t"
+	"pushfq\n\t"
+	"popq flags\n\t"
+#else
+	"mov %eax, ax\n\t"
+	"mov %ebx, bx\n\t"
+	"mov %ecx, cx\n\t"
+	"mov %edx, dx\n\t"
+	"mov %esi, si\n\t"
+	"mov %edi, di\n\t"
+	"mov %ebp, bp\n\t"
+	"mov %esp, sp\n\t"
+	"pushfl\n\t"
+	"popl flags\n\t"
+#endif
+	"jmp _start\n\t"
+	".size real_start, . - real_start\n\t"
+	".popsection");
+
+int main()
+{
+	int nerrs = 0;
+
+	if (sp == 0) {
+		printf("[FAIL]\tTest was built incorrectly\n");
+		return 1;
+	}
+
+	if (ax || bx || cx || dx || si || di || bp
+#ifdef __x86_64__
+	    || r8 || r9 || r10 || r11 || r12 || r13 || r14 || r15
+#endif
+		) {
+		printf("[FAIL]\tAll GPRs except SP should be 0\n");
+#define SHOW(x) printf("\t" #x " = 0x%lx\n", x);
+		SHOW(ax);
+		SHOW(bx);
+		SHOW(cx);
+		SHOW(dx);
+		SHOW(si);
+		SHOW(di);
+		SHOW(bp);
+		SHOW(sp);
+#ifdef __x86_64__
+		SHOW(r8);
+		SHOW(r9);
+		SHOW(r10);
+		SHOW(r11);
+		SHOW(r12);
+		SHOW(r13);
+		SHOW(r14);
+		SHOW(r15);
+#endif
+		nerrs++;
+	} else {
+		printf("[OK]\tAll GPRs except SP are 0\n");
+	}
+
+	if (flags != 0x202) {
+		printf("[FAIL]\tFLAGS is 0x%lx, but it should be 0x202\n", flags);
+		nerrs++;
+	} else {
+		printf("[OK]\tFLAGS is 0x202\n");
+	}
+
+	return nerrs ? 1 : 0;
+}
diff --git a/tools/testing/selftests/x86/iopl.c b/tools/testing/selftests/x86/iopl.c
new file mode 100644
index 000000000..c496ca97b
--- /dev/null
+++ b/tools/testing/selftests/x86/iopl.c
@@ -0,0 +1,135 @@
+/*
+ * iopl.c - Test case for a Linux on Xen 64-bit bug
+ * Copyright (c) 2015 Andrew Lutomirski
+ */
+
+#define _GNU_SOURCE
+#include <err.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <signal.h>
+#include <setjmp.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <stdbool.h>
+#include <sched.h>
+#include <sys/io.h>
+
+static int nerrs = 0;
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+		       int flags)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handler;
+	sa.sa_flags = SA_SIGINFO | flags;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+
+}
+
+static jmp_buf jmpbuf;
+
+static void sigsegv(int sig, siginfo_t *si, void *ctx_void)
+{
+	siglongjmp(jmpbuf, 1);
+}
+
+int main(void)
+{
+	cpu_set_t cpuset;
+	CPU_ZERO(&cpuset);
+	CPU_SET(0, &cpuset);
+	if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0)
+		err(1, "sched_setaffinity to CPU 0");
+
+	/* Probe for iopl support.  Note that iopl(0) works even as nonroot. */
+	if (iopl(3) != 0) {
+		printf("[OK]\tiopl(3) failed (%d) -- try running as root\n",
+		       errno);
+		return 0;
+	}
+
+	/* Restore our original state prior to starting the test. */
+	if (iopl(0) != 0)
+		err(1, "iopl(0)");
+
+	pid_t child = fork();
+	if (child == -1)
+		err(1, "fork");
+
+	if (child == 0) {
+		printf("\tchild: set IOPL to 3\n");
+		if (iopl(3) != 0)
+			err(1, "iopl");
+
+		printf("[RUN]\tchild: write to 0x80\n");
+		asm volatile ("outb %%al, $0x80" : : "a" (0));
+
+		return 0;
+	} else {
+		int status;
+		if (waitpid(child, &status, 0) != child ||
+		    !WIFEXITED(status)) {
+			printf("[FAIL]\tChild died\n");
+			nerrs++;
+		} else if (WEXITSTATUS(status) != 0) {
+			printf("[FAIL]\tChild failed\n");
+			nerrs++;
+		} else {
+			printf("[OK]\tChild succeeded\n");
+		}
+	}
+
+	printf("[RUN]\tparent: write to 0x80 (should fail)\n");
+
+	sethandler(SIGSEGV, sigsegv, 0);
+	if (sigsetjmp(jmpbuf, 1) != 0) {
+		printf("[OK]\twrite was denied\n");
+	} else {
+		asm volatile ("outb %%al, $0x80" : : "a" (0));
+		printf("[FAIL]\twrite was allowed\n");
+		nerrs++;
+	}
+
+	/* Test the capability checks. */
+	printf("\tiopl(3)\n");
+	if (iopl(3) != 0)
+		err(1, "iopl(3)");
+
+	printf("\tDrop privileges\n");
+	if (setresuid(1, 1, 1) != 0) {
+		printf("[WARN]\tDropping privileges failed\n");
+		goto done;
+	}
+
+	printf("[RUN]\tiopl(3) unprivileged but with IOPL==3\n");
+	if (iopl(3) != 0) {
+		printf("[FAIL]\tiopl(3) should work if iopl is already 3 even if unprivileged\n");
+		nerrs++;
+	}
+
+	printf("[RUN]\tiopl(0) unprivileged\n");
+	if (iopl(0) != 0) {
+		printf("[FAIL]\tiopl(0) should work if iopl is already 3 even if unprivileged\n");
+		nerrs++;
+	}
+
+	printf("[RUN]\tiopl(3) unprivileged\n");
+	if (iopl(3) == 0) {
+		printf("[FAIL]\tiopl(3) should fail if when unprivileged if iopl==0\n");
+		nerrs++;
+	} else {
+		printf("[OK]\tFailed as expected\n");
+	}
+
+done:
+	return nerrs ? 1 : 0;
+}
+
diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c
index 5105b49cd..421456784 100644
--- a/tools/testing/selftests/x86/ptrace_syscall.c
+++ b/tools/testing/selftests/x86/ptrace_syscall.c
@@ -103,6 +103,17 @@ static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
 		err(1, "sigaction");
 }
 
+static void setsigign(int sig, int flags)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = (void *)SIG_IGN;
+	sa.sa_flags = flags;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
 static void clearhandler(int sig)
 {
 	struct sigaction sa;
@@ -187,7 +198,7 @@ static void test_ptrace_syscall_restart(void)
 
 	printf("[RUN]\tSYSEMU\n");
 	if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0)
-		err(1, "PTRACE_SYSCALL");
+		err(1, "PTRACE_SYSEMU");
 	wait_trap(chld);
 
 	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
@@ -218,7 +229,7 @@ static void test_ptrace_syscall_restart(void)
 		err(1, "PTRACE_SETREGS");
 
 	if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0)
-		err(1, "PTRACE_SYSCALL");
+		err(1, "PTRACE_SYSEMU");
 	wait_trap(chld);
 
 	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
@@ -250,7 +261,7 @@ static void test_ptrace_syscall_restart(void)
 		err(1, "PTRACE_SETREGS");
 
 	if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0)
-		err(1, "PTRACE_SYSCALL");
+		err(1, "PTRACE_SYSEMU");
 	wait_trap(chld);
 
 	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
@@ -277,6 +288,119 @@ static void test_ptrace_syscall_restart(void)
 	}
 }
 
+static void test_restart_under_ptrace(void)
+{
+	printf("[RUN]\tkernel syscall restart under ptrace\n");
+	pid_t chld = fork();
+	if (chld < 0)
+		err(1, "fork");
+
+	if (chld == 0) {
+		if (ptrace(PTRACE_TRACEME, 0, 0, 0) != 0)
+			err(1, "PTRACE_TRACEME");
+
+		printf("\tChild will take a nap until signaled\n");
+		setsigign(SIGUSR1, SA_RESTART);
+		raise(SIGSTOP);
+
+		syscall(SYS_pause, 0, 0, 0, 0, 0, 0);
+		_exit(0);
+	}
+
+	int status;
+
+	/* Wait for SIGSTOP. */
+	if (waitpid(chld, &status, 0) != chld || !WIFSTOPPED(status))
+		err(1, "waitpid");
+
+	struct user_regs_struct regs;
+
+	printf("[RUN]\tSYSCALL\n");
+	if (ptrace(PTRACE_SYSCALL, chld, 0, 0) != 0)
+		err(1, "PTRACE_SYSCALL");
+	wait_trap(chld);
+
+	/* We should be stopped at pause(2) entry. */
+
+	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_GETREGS");
+
+	if (regs.user_syscall_nr != SYS_pause ||
+	    regs.user_arg0 != 0 || regs.user_arg1 != 0 ||
+	    regs.user_arg2 != 0 || regs.user_arg3 != 0 ||
+	    regs.user_arg4 != 0 || regs.user_arg5 != 0) {
+		printf("[FAIL]\tInitial args are wrong (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n", (unsigned long)regs.user_syscall_nr, (unsigned long)regs.user_arg0, (unsigned long)regs.user_arg1, (unsigned long)regs.user_arg2, (unsigned long)regs.user_arg3, (unsigned long)regs.user_arg4, (unsigned long)regs.user_arg5);
+		nerrs++;
+	} else {
+		printf("[OK]\tInitial nr and args are correct\n");
+	}
+
+	/* Interrupt it. */
+	kill(chld, SIGUSR1);
+
+	/* Advance.  We should be stopped at exit. */
+	printf("[RUN]\tSYSCALL\n");
+	if (ptrace(PTRACE_SYSCALL, chld, 0, 0) != 0)
+		err(1, "PTRACE_SYSCALL");
+	wait_trap(chld);
+
+	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_GETREGS");
+
+	if (regs.user_syscall_nr != SYS_pause ||
+	    regs.user_arg0 != 0 || regs.user_arg1 != 0 ||
+	    regs.user_arg2 != 0 || regs.user_arg3 != 0 ||
+	    regs.user_arg4 != 0 || regs.user_arg5 != 0) {
+		printf("[FAIL]\tArgs after SIGUSR1 are wrong (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n", (unsigned long)regs.user_syscall_nr, (unsigned long)regs.user_arg0, (unsigned long)regs.user_arg1, (unsigned long)regs.user_arg2, (unsigned long)regs.user_arg3, (unsigned long)regs.user_arg4, (unsigned long)regs.user_arg5);
+		nerrs++;
+	} else {
+		printf("[OK]\tArgs after SIGUSR1 are correct (ax = %ld)\n",
+		       (long)regs.user_ax);
+	}
+
+	/* Poke the regs back in.  This must not break anything. */
+	if (ptrace(PTRACE_SETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_SETREGS");
+
+	/* Catch the (ignored) SIGUSR1. */
+	if (ptrace(PTRACE_CONT, chld, 0, 0) != 0)
+		err(1, "PTRACE_CONT");
+	if (waitpid(chld, &status, 0) != chld)
+		err(1, "waitpid");
+	if (!WIFSTOPPED(status)) {
+		printf("[FAIL]\tChild was stopped for SIGUSR1 (status = 0x%x)\n", status);
+		nerrs++;
+	} else {
+		printf("[OK]\tChild got SIGUSR1\n");
+	}
+
+	/* The next event should be pause(2) again. */
+	printf("[RUN]\tStep again\n");
+	if (ptrace(PTRACE_SYSCALL, chld, 0, 0) != 0)
+		err(1, "PTRACE_SYSCALL");
+	wait_trap(chld);
+
+	/* We should be stopped at pause(2) entry. */
+
+	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_GETREGS");
+
+	if (regs.user_syscall_nr != SYS_pause ||
+	    regs.user_arg0 != 0 || regs.user_arg1 != 0 ||
+	    regs.user_arg2 != 0 || regs.user_arg3 != 0 ||
+	    regs.user_arg4 != 0 || regs.user_arg5 != 0) {
+		printf("[FAIL]\tpause did not restart (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n", (unsigned long)regs.user_syscall_nr, (unsigned long)regs.user_arg0, (unsigned long)regs.user_arg1, (unsigned long)regs.user_arg2, (unsigned long)regs.user_arg3, (unsigned long)regs.user_arg4, (unsigned long)regs.user_arg5);
+		nerrs++;
+	} else {
+		printf("[OK]\tpause(2) restarted correctly\n");
+	}
+
+	/* Kill it. */
+	kill(chld, SIGKILL);
+	if (waitpid(chld, &status, 0) != chld)
+		err(1, "waitpid");
+}
+
 int main()
 {
 	printf("[RUN]\tCheck int80 return regs\n");
@@ -290,5 +414,7 @@ int main()
 
 	test_ptrace_syscall_restart();
 
+	test_restart_under_ptrace();
+
 	return 0;
 }
diff --git a/tools/testing/selftests/x86/sigreturn.c b/tools/testing/selftests/x86/sigreturn.c
index b5aa1bab7..8a577e707 100644
--- a/tools/testing/selftests/x86/sigreturn.c
+++ b/tools/testing/selftests/x86/sigreturn.c
@@ -54,6 +54,37 @@
 #include <sys/ptrace.h>
 #include <sys/user.h>
 
+/* Pull in AR_xyz defines. */
+typedef unsigned int u32;
+typedef unsigned short u16;
+#include "../../../../arch/x86/include/asm/desc_defs.h"
+
+/*
+ * Copied from asm/ucontext.h, as asm/ucontext.h conflicts badly with the glibc
+ * headers.
+ */
+#ifdef __x86_64__
+/*
+ * UC_SIGCONTEXT_SS will be set when delivering 64-bit or x32 signals on
+ * kernels that save SS in the sigcontext.  All kernels that set
+ * UC_SIGCONTEXT_SS will correctly restore at least the low 32 bits of esp
+ * regardless of SS (i.e. they implement espfix).
+ *
+ * Kernels that set UC_SIGCONTEXT_SS will also set UC_STRICT_RESTORE_SS
+ * when delivering a signal that came from 64-bit code.
+ *
+ * Sigreturn restores SS as follows:
+ *
+ * if (saved SS is valid || UC_STRICT_RESTORE_SS is set ||
+ *     saved CS is not 64-bit)
+ *         new SS = saved SS  (will fail IRET and signal if invalid)
+ * else
+ *         new SS = a flat 32-bit data segment
+ */
+#define UC_SIGCONTEXT_SS       0x2
+#define UC_STRICT_RESTORE_SS   0x4
+#endif
+
 /*
  * In principle, this test can run on Linux emulation layers (e.g.
  * Illumos "LX branded zones").  Solaris-based kernels reserve LDT
@@ -267,6 +298,9 @@ static gregset_t initial_regs, requested_regs, resulting_regs;
 /* Instructions for the SIGUSR1 handler. */
 static volatile unsigned short sig_cs, sig_ss;
 static volatile sig_atomic_t sig_trapped, sig_err, sig_trapno;
+#ifdef __x86_64__
+static volatile sig_atomic_t sig_corrupt_final_ss;
+#endif
 
 /* Abstractions for some 32-bit vs 64-bit differences. */
 #ifdef __x86_64__
@@ -305,9 +339,105 @@ static greg_t *csptr(ucontext_t *ctx)
 }
 #endif
 
+/*
+ * Checks a given selector for its code bitness or returns -1 if it's not
+ * a usable code segment selector.
+ */
+int cs_bitness(unsigned short cs)
+{
+	uint32_t valid = 0, ar;
+	asm ("lar %[cs], %[ar]\n\t"
+	     "jnz 1f\n\t"
+	     "mov $1, %[valid]\n\t"
+	     "1:"
+	     : [ar] "=r" (ar), [valid] "+rm" (valid)
+	     : [cs] "r" (cs));
+
+	if (!valid)
+		return -1;
+
+	bool db = (ar & (1 << 22));
+	bool l = (ar & (1 << 21));
+
+	if (!(ar & (1<<11)))
+	    return -1;	/* Not code. */
+
+	if (l && !db)
+		return 64;
+	else if (!l && db)
+		return 32;
+	else if (!l && !db)
+		return 16;
+	else
+		return -1;	/* Unknown bitness. */
+}
+
+/*
+ * Checks a given selector for its code bitness or returns -1 if it's not
+ * a usable code segment selector.
+ */
+bool is_valid_ss(unsigned short cs)
+{
+	uint32_t valid = 0, ar;
+	asm ("lar %[cs], %[ar]\n\t"
+	     "jnz 1f\n\t"
+	     "mov $1, %[valid]\n\t"
+	     "1:"
+	     : [ar] "=r" (ar), [valid] "+rm" (valid)
+	     : [cs] "r" (cs));
+
+	if (!valid)
+		return false;
+
+	if ((ar & AR_TYPE_MASK) != AR_TYPE_RWDATA &&
+	    (ar & AR_TYPE_MASK) != AR_TYPE_RWDATA_EXPDOWN)
+		return false;
+
+	return (ar & AR_P);
+}
+
 /* Number of errors in the current test case. */
 static volatile sig_atomic_t nerrs;
 
+static void validate_signal_ss(int sig, ucontext_t *ctx)
+{
+#ifdef __x86_64__
+	bool was_64bit = (cs_bitness(*csptr(ctx)) == 64);
+
+	if (!(ctx->uc_flags & UC_SIGCONTEXT_SS)) {
+		printf("[FAIL]\tUC_SIGCONTEXT_SS was not set\n");
+		nerrs++;
+
+		/*
+		 * This happens on Linux 4.1.  The rest will fail, too, so
+		 * return now to reduce the noise.
+		 */
+		return;
+	}
+
+	/* UC_STRICT_RESTORE_SS is set iff we came from 64-bit mode. */
+	if (!!(ctx->uc_flags & UC_STRICT_RESTORE_SS) != was_64bit) {
+		printf("[FAIL]\tUC_STRICT_RESTORE_SS was wrong in signal %d\n",
+		       sig);
+		nerrs++;
+	}
+
+	if (is_valid_ss(*ssptr(ctx))) {
+		/*
+		 * DOSEMU was written before 64-bit sigcontext had SS, and
+		 * it tries to figure out the signal source SS by looking at
+		 * the physical register.  Make sure that keeps working.
+		 */
+		unsigned short hw_ss;
+		asm ("mov %%ss, %0" : "=rm" (hw_ss));
+		if (hw_ss != *ssptr(ctx)) {
+			printf("[FAIL]\tHW SS didn't match saved SS\n");
+			nerrs++;
+		}
+	}
+#endif
+}
+
 /*
  * SIGUSR1 handler.  Sets CS and SS as requested and points IP to the
  * int3 trampoline.  Sets SP to a large known value so that we can see
@@ -317,6 +447,8 @@ static void sigusr1(int sig, siginfo_t *info, void *ctx_void)
 {
 	ucontext_t *ctx = (ucontext_t*)ctx_void;
 
+	validate_signal_ss(sig, ctx);
+
 	memcpy(&initial_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t));
 
 	*csptr(ctx) = sig_cs;
@@ -334,13 +466,16 @@ static void sigusr1(int sig, siginfo_t *info, void *ctx_void)
 }
 
 /*
- * Called after a successful sigreturn.  Restores our state so that
- * the original raise(SIGUSR1) returns.
+ * Called after a successful sigreturn (via int3) or from a failed
+ * sigreturn (directly by kernel).  Restores our state so that the
+ * original raise(SIGUSR1) returns.
  */
 static void sigtrap(int sig, siginfo_t *info, void *ctx_void)
 {
 	ucontext_t *ctx = (ucontext_t*)ctx_void;
 
+	validate_signal_ss(sig, ctx);
+
 	sig_err = ctx->uc_mcontext.gregs[REG_ERR];
 	sig_trapno = ctx->uc_mcontext.gregs[REG_TRAPNO];
 
@@ -358,41 +493,62 @@ static void sigtrap(int sig, siginfo_t *info, void *ctx_void)
 	memcpy(&resulting_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t));
 	memcpy(&ctx->uc_mcontext.gregs, &initial_regs, sizeof(gregset_t));
 
+#ifdef __x86_64__
+	if (sig_corrupt_final_ss) {
+		if (ctx->uc_flags & UC_STRICT_RESTORE_SS) {
+			printf("[FAIL]\tUC_STRICT_RESTORE_SS was set inappropriately\n");
+			nerrs++;
+		} else {
+			/*
+			 * DOSEMU transitions from 32-bit to 64-bit mode by
+			 * adjusting sigcontext, and it requires that this work
+			 * even if the saved SS is bogus.
+			 */
+			printf("\tCorrupting SS on return to 64-bit mode\n");
+			*ssptr(ctx) = 0;
+		}
+	}
+#endif
+
 	sig_trapped = sig;
 }
 
-/*
- * Checks a given selector for its code bitness or returns -1 if it's not
- * a usable code segment selector.
- */
-int cs_bitness(unsigned short cs)
+#ifdef __x86_64__
+/* Tests recovery if !UC_STRICT_RESTORE_SS */
+static void sigusr2(int sig, siginfo_t *info, void *ctx_void)
 {
-	uint32_t valid = 0, ar;
-	asm ("lar %[cs], %[ar]\n\t"
-	     "jnz 1f\n\t"
-	     "mov $1, %[valid]\n\t"
-	     "1:"
-	     : [ar] "=r" (ar), [valid] "+rm" (valid)
-	     : [cs] "r" (cs));
+	ucontext_t *ctx = (ucontext_t*)ctx_void;
 
-	if (!valid)
-		return -1;
+	if (!(ctx->uc_flags & UC_STRICT_RESTORE_SS)) {
+		printf("[FAIL]\traise(2) didn't set UC_STRICT_RESTORE_SS\n");
+		nerrs++;
+		return;  /* We can't do the rest. */
+	}
 
-	bool db = (ar & (1 << 22));
-	bool l = (ar & (1 << 21));
+	ctx->uc_flags &= ~UC_STRICT_RESTORE_SS;
+	*ssptr(ctx) = 0;
 
-	if (!(ar & (1<<11)))
-	    return -1;	/* Not code. */
+	/* Return.  The kernel should recover without sending another signal. */
+}
 
-	if (l && !db)
-		return 64;
-	else if (!l && db)
-		return 32;
-	else if (!l && !db)
-		return 16;
-	else
-		return -1;	/* Unknown bitness. */
+static int test_nonstrict_ss(void)
+{
+	clearhandler(SIGUSR1);
+	clearhandler(SIGTRAP);
+	clearhandler(SIGSEGV);
+	clearhandler(SIGILL);
+	sethandler(SIGUSR2, sigusr2, 0);
+
+	nerrs = 0;
+
+	printf("[RUN]\tClear UC_STRICT_RESTORE_SS and corrupt SS\n");
+	raise(SIGUSR2);
+	if (!nerrs)
+		printf("[OK]\tIt worked\n");
+
+	return nerrs;
 }
+#endif
 
 /* Finds a usable code segment of the requested bitness. */
 int find_cs(int bitness)
@@ -576,6 +732,12 @@ static int test_bad_iret(int cs_bits, unsigned short ss, int force_cs)
 		       errdesc, strsignal(sig_trapped));
 		return 0;
 	} else {
+		/*
+		 * This also implicitly tests UC_STRICT_RESTORE_SS:
+		 * We check that these signals set UC_STRICT_RESTORE_SS and,
+		 * if UC_STRICT_RESTORE_SS doesn't cause strict behavior,
+		 * then we won't get SIGSEGV.
+		 */
 		printf("[FAIL]\tDid not get SIGSEGV\n");
 		return 1;
 	}
@@ -632,6 +794,14 @@ int main()
 						    GDT3(gdt_data16_idx));
 	}
 
+#ifdef __x86_64__
+	/* Nasty ABI case: check SS corruption handling. */
+	sig_corrupt_final_ss = 1;
+	total_nerrs += test_valid_sigreturn(32, false, -1);
+	total_nerrs += test_valid_sigreturn(32, true, -1);
+	sig_corrupt_final_ss = 0;
+#endif
+
 	/*
 	 * We're done testing valid sigreturn cases.  Now we test states
 	 * for which sigreturn itself will succeed but the subsequent
@@ -680,5 +850,9 @@ int main()
 	if (gdt_npdata32_idx)
 		test_bad_iret(32, GDT3(gdt_npdata32_idx), -1);
 
+#ifdef __x86_64__
+	total_nerrs += test_nonstrict_ss();
+#endif
+
 	return total_nerrs ? 1 : 0;
 }
diff --git a/tools/testing/selftests/x86/syscall_nt.c b/tools/testing/selftests/x86/syscall_nt.c
index 60c06af46..43fcab367 100644
--- a/tools/testing/selftests/x86/syscall_nt.c
+++ b/tools/testing/selftests/x86/syscall_nt.c
@@ -17,6 +17,9 @@
 
 #include <stdio.h>
 #include <unistd.h>
+#include <string.h>
+#include <signal.h>
+#include <err.h>
 #include <sys/syscall.h>
 #include <asm/processor-flags.h>
 
@@ -26,6 +29,8 @@
 # define WIDTH "l"
 #endif
 
+static unsigned int nerrs;
+
 static unsigned long get_eflags(void)
 {
 	unsigned long eflags;
@@ -39,16 +44,52 @@ static void set_eflags(unsigned long eflags)
 		      : : "rm" (eflags) : "flags");
 }
 
-int main()
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+		       int flags)
 {
-	printf("[RUN]\tSet NT and issue a syscall\n");
-	set_eflags(get_eflags() | X86_EFLAGS_NT);
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handler;
+	sa.sa_flags = SA_SIGINFO | flags;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
+static void sigtrap(int sig, siginfo_t *si, void *ctx_void)
+{
+}
+
+static void do_it(unsigned long extraflags)
+{
+	unsigned long flags;
+
+	set_eflags(get_eflags() | extraflags);
 	syscall(SYS_getpid);
-	if (get_eflags() & X86_EFLAGS_NT) {
-		printf("[OK]\tThe syscall worked and NT is still set\n");
-		return 0;
+	flags = get_eflags();
+	if ((flags & extraflags) == extraflags) {
+		printf("[OK]\tThe syscall worked and flags are still set\n");
 	} else {
-		printf("[FAIL]\tThe syscall worked but NT was cleared\n");
-		return 1;
+		printf("[FAIL]\tThe syscall worked but flags were cleared (flags = 0x%lx but expected 0x%lx set)\n",
+		       flags, extraflags);
+		nerrs++;
 	}
 }
+
+int main(void)
+{
+	printf("[RUN]\tSet NT and issue a syscall\n");
+	do_it(X86_EFLAGS_NT);
+
+	/*
+	 * Now try it again with TF set -- TF forces returns via IRET in all
+	 * cases except non-ptregs-using 64-bit full fast path syscalls.
+	 */
+
+	sethandler(SIGTRAP, sigtrap, 0);
+
+	printf("[RUN]\tSet NT|TF and issue a syscall\n");
+	do_it(X86_EFLAGS_NT | X86_EFLAGS_TF);
+
+	return nerrs == 0 ? 0 : 1;
+}
diff --git a/tools/testing/selftests/zram/config b/tools/testing/selftests/zram/config
new file mode 100644
index 000000000..e0cc47e2c
--- /dev/null
+++ b/tools/testing/selftests/zram/config
@@ -0,0 +1,2 @@
+CONFIG_ZSMALLOC=y
+CONFIG_ZRAM=m
diff --git a/tools/virtio/linux/dma-mapping.h b/tools/virtio/linux/dma-mapping.h
new file mode 100644
index 000000000..4f93af89a
--- /dev/null
+++ b/tools/virtio/linux/dma-mapping.h
@@ -0,0 +1,17 @@
+#ifndef _LINUX_DMA_MAPPING_H
+#define _LINUX_DMA_MAPPING_H
+
+#ifdef CONFIG_HAS_DMA
+# error Virtio userspace code does not support CONFIG_HAS_DMA
+#endif
+
+#define PCI_DMA_BUS_IS_PHYS 1
+
+enum dma_data_direction {
+	DMA_BIDIRECTIONAL = 0,
+	DMA_TO_DEVICE = 1,
+	DMA_FROM_DEVICE = 2,
+	DMA_NONE = 3,
+};
+
+#endif
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index 5a6016224..e92903fc7 100644
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -61,6 +61,8 @@
 #define PM_PFRAME_BITS		55
 #define PM_PFRAME_MASK		((1LL << PM_PFRAME_BITS) - 1)
 #define PM_PFRAME(x)		((x) & PM_PFRAME_MASK)
+#define MAX_SWAPFILES_SHIFT	5
+#define PM_SWAP_OFFSET(x)	(((x) & PM_PFRAME_MASK) >> MAX_SWAPFILES_SHIFT)
 #define PM_SOFT_DIRTY		(1ULL << 55)
 #define PM_MMAP_EXCLUSIVE	(1ULL << 56)
 #define PM_FILE			(1ULL << 61)
@@ -73,6 +75,7 @@
 
 #define KPF_BYTES		8
 #define PROC_KPAGEFLAGS		"/proc/kpageflags"
+#define PROC_KPAGECGROUP	"/proc/kpagecgroup"
 
 /* [32-] kernel hacking assistances */
 #define KPF_RESERVED		32
@@ -92,7 +95,8 @@
 #define KPF_SLOB_FREE		49
 #define KPF_SLUB_FROZEN		50
 #define KPF_SLUB_DEBUG		51
-#define KPF_FILE		62
+#define KPF_FILE		61
+#define KPF_SWAP		62
 #define KPF_MMAP_EXCLUSIVE	63
 
 #define KPF_ALL_BITS		((uint64_t)~0ULL)
@@ -146,6 +150,7 @@ static const char * const page_flag_names[] = {
 	[KPF_SLUB_DEBUG]	= "E:slub_debug",
 
 	[KPF_FILE]		= "F:file",
+	[KPF_SWAP]		= "w:swap",
 	[KPF_MMAP_EXCLUSIVE]	= "1:mmap_exclusive",
 };
 
@@ -164,7 +169,9 @@ static int		opt_raw;	/* for kernel developers */
 static int		opt_list;	/* list pages (in ranges) */
 static int		opt_no_summary;	/* don't show summary */
 static pid_t		opt_pid;	/* process to walk */
-const char *		opt_file;
+const char *		opt_file;	/* file or directory path */
+static uint64_t		opt_cgroup;	/* cgroup inode */
+static int		opt_list_cgroup;/* list page cgroup */
 
 #define MAX_ADDR_RANGES	1024
 static int		nr_addr_ranges;
@@ -185,6 +192,7 @@ static int		page_size;
 
 static int		pagemap_fd;
 static int		kpageflags_fd;
+static int		kpagecgroup_fd = -1;
 
 static int		opt_hwpoison;
 static int		opt_unpoison;
@@ -278,6 +286,16 @@ static unsigned long kpageflags_read(uint64_t *buf,
 	return do_u64_read(kpageflags_fd, PROC_KPAGEFLAGS, buf, index, pages);
 }
 
+static unsigned long kpagecgroup_read(uint64_t *buf,
+				      unsigned long index,
+				      unsigned long pages)
+{
+	if (kpagecgroup_fd < 0)
+		return pages;
+
+	return do_u64_read(kpagecgroup_fd, PROC_KPAGEFLAGS, buf, index, pages);
+}
+
 static unsigned long pagemap_read(uint64_t *buf,
 				  unsigned long index,
 				  unsigned long pages)
@@ -297,6 +315,10 @@ static unsigned long pagemap_pfn(uint64_t val)
 	return pfn;
 }
 
+static unsigned long pagemap_swap_offset(uint64_t val)
+{
+	return val & PM_SWAP ? PM_SWAP_OFFSET(val) : 0;
+}
 
 /*
  * page flag names
@@ -346,14 +368,15 @@ static char *page_flag_longname(uint64_t flags)
  */
 
 static void show_page_range(unsigned long voffset, unsigned long offset,
-			    unsigned long size, uint64_t flags)
+			    unsigned long size, uint64_t flags, uint64_t cgroup)
 {
 	static uint64_t      flags0;
+	static uint64_t	     cgroup0;
 	static unsigned long voff;
 	static unsigned long index;
 	static unsigned long count;
 
-	if (flags == flags0 && offset == index + count &&
+	if (flags == flags0 && cgroup == cgroup0 && offset == index + count &&
 	    size && voffset == voff + count) {
 		count += size;
 		return;
@@ -364,11 +387,14 @@ static void show_page_range(unsigned long voffset, unsigned long offset,
 			printf("%lx\t", voff);
 		if (opt_file)
 			printf("%lu\t", voff);
+		if (opt_list_cgroup)
+			printf("@%llu\t", (unsigned long long)cgroup0);
 		printf("%lx\t%lx\t%s\n",
 				index, count, page_flag_name(flags0));
 	}
 
 	flags0 = flags;
+	cgroup0= cgroup;
 	index  = offset;
 	voff   = voffset;
 	count  = size;
@@ -376,16 +402,18 @@ static void show_page_range(unsigned long voffset, unsigned long offset,
 
 static void flush_page_range(void)
 {
-	show_page_range(0, 0, 0, 0);
+	show_page_range(0, 0, 0, 0, 0);
 }
 
-static void show_page(unsigned long voffset,
-		      unsigned long offset, uint64_t flags)
+static void show_page(unsigned long voffset, unsigned long offset,
+		      uint64_t flags, uint64_t cgroup)
 {
 	if (opt_pid)
 		printf("%lx\t", voffset);
 	if (opt_file)
 		printf("%lu\t", voffset);
+	if (opt_list_cgroup)
+		printf("@%llu\t", (unsigned long long)cgroup);
 	printf("%lx\t%s\n", offset, page_flag_name(flags));
 }
 
@@ -452,6 +480,8 @@ static uint64_t expand_overloaded_flags(uint64_t flags, uint64_t pme)
 		flags |= BIT(SOFTDIRTY);
 	if (pme & PM_FILE)
 		flags |= BIT(FILE);
+	if (pme & PM_SWAP)
+		flags |= BIT(SWAP);
 	if (pme & PM_MMAP_EXCLUSIVE)
 		flags |= BIT(MMAP_EXCLUSIVE);
 
@@ -566,23 +596,26 @@ static size_t hash_slot(uint64_t flags)
 	exit(EXIT_FAILURE);
 }
 
-static void add_page(unsigned long voffset,
-		     unsigned long offset, uint64_t flags, uint64_t pme)
+static void add_page(unsigned long voffset, unsigned long offset,
+		     uint64_t flags, uint64_t cgroup, uint64_t pme)
 {
 	flags = kpageflags_flags(flags, pme);
 
 	if (!bit_mask_ok(flags))
 		return;
 
+	if (opt_cgroup && cgroup != (uint64_t)opt_cgroup)
+		return;
+
 	if (opt_hwpoison)
 		hwpoison_page(offset);
 	if (opt_unpoison)
 		unpoison_page(offset);
 
 	if (opt_list == 1)
-		show_page_range(voffset, offset, 1, flags);
+		show_page_range(voffset, offset, 1, flags, cgroup);
 	else if (opt_list == 2)
-		show_page(voffset, offset, flags);
+		show_page(voffset, offset, flags, cgroup);
 
 	nr_pages[hash_slot(flags)]++;
 	total_pages++;
@@ -595,24 +628,57 @@ static void walk_pfn(unsigned long voffset,
 		     uint64_t pme)
 {
 	uint64_t buf[KPAGEFLAGS_BATCH];
+	uint64_t cgi[KPAGEFLAGS_BATCH];
 	unsigned long batch;
 	unsigned long pages;
 	unsigned long i;
 
+	/*
+	 * kpagecgroup_read() reads only if kpagecgroup were opened, but
+	 * /proc/kpagecgroup might even not exist, so it's better to fill
+	 * them with zeros here.
+	 */
+	if (count == 1)
+		cgi[0] = 0;
+	else
+		memset(cgi, 0, sizeof cgi);
+
 	while (count) {
 		batch = min_t(unsigned long, count, KPAGEFLAGS_BATCH);
 		pages = kpageflags_read(buf, index, batch);
 		if (pages == 0)
 			break;
 
+		if (kpagecgroup_read(cgi, index, pages) != pages)
+			fatal("kpagecgroup returned fewer pages than expected");
+
 		for (i = 0; i < pages; i++)
-			add_page(voffset + i, index + i, buf[i], pme);
+			add_page(voffset + i, index + i, buf[i], cgi[i], pme);
 
 		index += pages;
 		count -= pages;
 	}
 }
 
+static void walk_swap(unsigned long voffset, uint64_t pme)
+{
+	uint64_t flags = kpageflags_flags(0, pme);
+
+	if (!bit_mask_ok(flags))
+		return;
+
+	if (opt_cgroup)
+		return;
+
+	if (opt_list == 1)
+		show_page_range(voffset, pagemap_swap_offset(pme), 1, flags, 0);
+	else if (opt_list == 2)
+		show_page(voffset, pagemap_swap_offset(pme), flags, 0);
+
+	nr_pages[hash_slot(flags)]++;
+	total_pages++;
+}
+
 #define PAGEMAP_BATCH	(64 << 10)
 static void walk_vma(unsigned long index, unsigned long count)
 {
@@ -632,6 +698,8 @@ static void walk_vma(unsigned long index, unsigned long count)
 			pfn = pagemap_pfn(buf[i]);
 			if (pfn)
 				walk_pfn(index + i, pfn, 1, buf[i]);
+			if (buf[i] & PM_SWAP)
+				walk_swap(index + i, buf[i]);
 		}
 
 		index += pages;
@@ -713,10 +781,12 @@ static void usage(void)
 "            -d|--describe flags        Describe flags\n"
 "            -a|--addr    addr-spec     Walk a range of pages\n"
 "            -b|--bits    bits-spec     Walk pages with specified bits\n"
+"            -c|--cgroup  path|@inode   Walk pages within memory cgroup\n"
 "            -p|--pid     pid           Walk process address space\n"
 "            -f|--file    filename      Walk file address space\n"
 "            -l|--list                  Show page details in ranges\n"
 "            -L|--list-each             Show page details one by one\n"
+"            -C|--list-cgroup           Show cgroup inode for pages\n"
 "            -N|--no-summary            Don't show summary info\n"
 "            -X|--hwpoison              hwpoison pages\n"
 "            -x|--unpoison              unpoison pages\n"
@@ -851,6 +921,7 @@ static void walk_file(const char *name, const struct stat *st)
 {
 	uint8_t vec[PAGEMAP_BATCH];
 	uint64_t buf[PAGEMAP_BATCH], flags;
+	uint64_t cgroup = 0;
 	unsigned long nr_pages, pfn, i;
 	off_t off, end = st->st_size;
 	int fd;
@@ -908,12 +979,15 @@ got_sigbus:
 				continue;
 			if (!kpageflags_read(&flags, pfn, 1))
 				continue;
+			if (!kpagecgroup_read(&cgroup, pfn, 1))
+				fatal("kpagecgroup_read failed");
 			if (first && opt_list) {
 				first = 0;
 				flush_page_range();
 				show_file(name, st);
 			}
-			add_page(off / page_size + i, pfn, flags, buf[i]);
+			add_page(off / page_size + i, pfn,
+				 flags, cgroup, buf[i]);
 		}
 	}
 
@@ -965,6 +1039,24 @@ static void parse_file(const char *name)
 	opt_file = name;
 }
 
+static void parse_cgroup(const char *path)
+{
+	if (path[0] == '@') {
+		opt_cgroup = parse_number(path + 1);
+		return;
+	}
+
+	struct stat st;
+
+	if (stat(path, &st))
+		fatal("stat failed: %s: %m\n", path);
+
+	if (!S_ISDIR(st.st_mode))
+		fatal("cgroup supposed to be a directory: %s\n", path);
+
+	opt_cgroup = st.st_ino;
+}
+
 static void parse_addr_range(const char *optarg)
 {
 	unsigned long offset;
@@ -1088,9 +1180,11 @@ static const struct option opts[] = {
 	{ "file"      , 1, NULL, 'f' },
 	{ "addr"      , 1, NULL, 'a' },
 	{ "bits"      , 1, NULL, 'b' },
+	{ "cgroup"    , 1, NULL, 'c' },
 	{ "describe"  , 1, NULL, 'd' },
 	{ "list"      , 0, NULL, 'l' },
 	{ "list-each" , 0, NULL, 'L' },
+	{ "list-cgroup", 0, NULL, 'C' },
 	{ "no-summary", 0, NULL, 'N' },
 	{ "hwpoison"  , 0, NULL, 'X' },
 	{ "unpoison"  , 0, NULL, 'x' },
@@ -1105,7 +1199,7 @@ int main(int argc, char *argv[])
 	page_size = getpagesize();
 
 	while ((c = getopt_long(argc, argv,
-				"rp:f:a:b:d:lLNXxh", opts, NULL)) != -1) {
+				"rp:f:a:b:d:c:ClLNXxh", opts, NULL)) != -1) {
 		switch (c) {
 		case 'r':
 			opt_raw = 1;
@@ -1122,6 +1216,12 @@ int main(int argc, char *argv[])
 		case 'b':
 			parse_bits_mask(optarg);
 			break;
+		case 'c':
+			parse_cgroup(optarg);
+			break;
+		case 'C':
+			opt_list_cgroup = 1;
+			break;
 		case 'd':
 			describe_flags(optarg);
 			exit(0);
@@ -1151,10 +1251,15 @@ int main(int argc, char *argv[])
 		}
 	}
 
+	if (opt_cgroup || opt_list_cgroup)
+		kpagecgroup_fd = checked_open(PROC_KPAGECGROUP, O_RDONLY);
+
 	if (opt_list && opt_pid)
 		printf("voffset\t");
 	if (opt_list && opt_file)
 		printf("foffset\t");
+	if (opt_list && opt_list_cgroup)
+		printf("cgroup\t");
 	if (opt_list == 1)
 		printf("offset\tlen\tflags\n");
 	if (opt_list == 2)
diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c
index 86e698d07..1889163f2 100644
--- a/tools/vm/slabinfo.c
+++ b/tools/vm/slabinfo.c
@@ -135,7 +135,7 @@ static void usage(void)
 		"\nValid debug options (FZPUT may be combined)\n"
 		"a / A          Switch on all debug options (=FZUP)\n"
 		"-              Switch off all debug options\n"
-		"f / F          Sanity Checks (SLAB_DEBUG_FREE)\n"
+		"f / F          Sanity Checks (SLAB_CONSISTENCY_CHECKS)\n"
 		"z / Z          Redzoning\n"
 		"p / P          Poisoning\n"
 		"u / U          Tracking\n"