Merge branch 'linus' into x86/apic

Pull in update changes so we can apply conflicting patches

138 files changed, 3211 insertions, 590 deletions

diff --git a/tools/Makefile b/tools/Makefile
index d6f307dfb1a3..7dc820a8c1f1 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -32,6 +32,10 @@ help:
 	@echo '  from the kernel command line to build and install one of'
 	@echo '  the tools above'
 	@echo ''
+	@echo '  $$ make tools/all'
+	@echo ''
+	@echo '  builds all tools.'
+	@echo ''
 	@echo '  $$ make tools/install'
 	@echo ''
 	@echo '  installs all tools.'
@@ -77,6 +81,11 @@ tmon: FORCE
 freefall: FORCE
 	$(call descend,laptop/$@)
 
+all: acpi cgroup cpupower hv firewire lguest \
+		perf selftests turbostat usb \
+		virtio vm net x86_energy_perf_policy \
+		tmon freefall
+
 acpi_install:
 	$(call descend,power/$(@:_install=),install)
 
@@ -101,7 +110,7 @@ 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 freefall_install
+		tmon_install freefall_install
 
 acpi_clean:
 	$(call descend,power/acpi,clean)
diff --git a/tools/iio/generic_buffer.c b/tools/iio/generic_buffer.c
index 9f7b85bf6ada..01c4f67801e0 100644
--- a/tools/iio/generic_buffer.c
+++ b/tools/iio/generic_buffer.c
@@ -328,6 +328,15 @@ int main(int argc, char **argv)
 			"diag %s\n", dev_dir_name);
 		goto error_free_triggername;
 	}
+	if (!num_channels) {
+		fprintf(stderr,
+			"No channels are enabled, we have nothing to scan.\n");
+		fprintf(stderr, "Enable channels manually in "
+			FORMAT_SCAN_ELEMENTS_DIR
+			"/*_en and try again.\n", dev_dir_name);
+		ret = -ENOENT;
+		goto error_free_triggername;
+	}
 
 	/*
 	 * Construct the directory name for the associated buffer.
diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c
index cd3fd41b481d..d51eb04202e9 100644
--- a/tools/iio/iio_event_monitor.c
+++ b/tools/iio/iio_event_monitor.c
@@ -284,7 +284,11 @@ int main(int argc, char **argv)
 	ret = ioctl(fd, IIO_GET_EVENT_FD_IOCTL, &event_fd);
 	if (ret == -1 || event_fd == -1) {
 		ret = -errno;
-		fprintf(stderr, "Failed to retrieve event fd\n");
+		if (ret == -ENODEV)
+			fprintf(stderr,
+				"This device does not support events\n");
+		else
+			fprintf(stderr, "Failed to retrieve event fd\n");
 		if (close(fd) == -1)
 			perror("Failed to close character device file");
 
diff --git a/tools/include/linux/list.h b/tools/include/linux/list.h
index 76b014c96893..a017f1595676 100644
--- a/tools/include/linux/list.h
+++ b/tools/include/linux/list.h
@@ -1,3 +1,4 @@
+#include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 
diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore
index 812aeedaea38..f81e549ddfdb 100644
--- a/tools/lib/bpf/.gitignore
+++ b/tools/lib/bpf/.gitignore
@@ -1,2 +1,2 @@
 libbpf_version.h
-FEATURE-DUMP
+FEATURE-DUMP.libbpf
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index fc9af57b666e..a3caaf3eafbd 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -180,7 +180,7 @@ config-clean:
 clean:
 	$(call QUIET_CLEAN, libbpf) $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d \
 		$(RM) LIBBPF-CFLAGS
-	$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP
+	$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
 
 
 
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 4252fc22f78f..e176bad19bcb 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -61,6 +61,60 @@ void libbpf_set_print(libbpf_print_fn_t warn,
 	__pr_debug = debug;
 }
 
+#define STRERR_BUFSIZE  128
+
+#define ERRNO_OFFSET(e)		((e) - __LIBBPF_ERRNO__START)
+#define ERRCODE_OFFSET(c)	ERRNO_OFFSET(LIBBPF_ERRNO__##c)
+#define NR_ERRNO	(__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)
+
+static const char *libbpf_strerror_table[NR_ERRNO] = {
+	[ERRCODE_OFFSET(LIBELF)]	= "Something wrong in libelf",
+	[ERRCODE_OFFSET(FORMAT)]	= "BPF object format invalid",
+	[ERRCODE_OFFSET(KVERSION)]	= "'version' section incorrect or lost",
+	[ERRCODE_OFFSET(ENDIAN)]	= "Endian missmatch",
+	[ERRCODE_OFFSET(INTERNAL)]	= "Internal error in libbpf",
+	[ERRCODE_OFFSET(RELOC)]		= "Relocation failed",
+	[ERRCODE_OFFSET(VERIFY)]	= "Kernel verifier blocks program loading",
+	[ERRCODE_OFFSET(PROG2BIG)]	= "Program too big",
+	[ERRCODE_OFFSET(KVER)]		= "Incorrect kernel version",
+};
+
+int libbpf_strerror(int err, char *buf, size_t size)
+{
+	if (!buf || !size)
+		return -1;
+
+	err = err > 0 ? err : -err;
+
+	if (err < __LIBBPF_ERRNO__START) {
+		int ret;
+
+		ret = strerror_r(err, buf, size);
+		buf[size - 1] = '\0';
+		return ret;
+	}
+
+	if (err < __LIBBPF_ERRNO__END) {
+		const char *msg;
+
+		msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
+		snprintf(buf, size, "%s", msg);
+		buf[size - 1] = '\0';
+		return 0;
+	}
+
+	snprintf(buf, size, "Unknown libbpf error %d", err);
+	buf[size - 1] = '\0';
+	return -1;
+}
+
+#define CHECK_ERR(action, err, out) do {	\
+	err = action;			\
+	if (err)			\
+		goto out;		\
+} while(0)
+
+
 /* Copied from tools/perf/util/util.h */
 #ifndef zfree
 # define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
@@ -258,7 +312,7 @@ static struct bpf_object *bpf_object__new(const char *path,
 	obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1);
 	if (!obj) {
 		pr_warning("alloc memory failed for %s\n", path);
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	strcpy(obj->path, path);
@@ -305,7 +359,7 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 
 	if (obj_elf_valid(obj)) {
 		pr_warning("elf init: internal error\n");
-		return -EEXIST;
+		return -LIBBPF_ERRNO__LIBELF;
 	}
 
 	if (obj->efile.obj_buf_sz > 0) {
@@ -331,14 +385,14 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 	if (!obj->efile.elf) {
 		pr_warning("failed to open %s as ELF file\n",
 				obj->path);
-		err = -EINVAL;
+		err = -LIBBPF_ERRNO__LIBELF;
 		goto errout;
 	}
 
 	if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) {
 		pr_warning("failed to get EHDR from %s\n",
 				obj->path);
-		err = -EINVAL;
+		err = -LIBBPF_ERRNO__FORMAT;
 		goto errout;
 	}
 	ep = &obj->efile.ehdr;
@@ -346,7 +400,7 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 	if ((ep->e_type != ET_REL) || (ep->e_machine != 0)) {
 		pr_warning("%s is not an eBPF object file\n",
 			obj->path);
-		err = -EINVAL;
+		err = -LIBBPF_ERRNO__FORMAT;
 		goto errout;
 	}
 
@@ -374,14 +428,14 @@ bpf_object__check_endianness(struct bpf_object *obj)
 			goto mismatch;
 		break;
 	default:
-		return -EINVAL;
+		return -LIBBPF_ERRNO__ENDIAN;
 	}
 
 	return 0;
 
 mismatch:
 	pr_warning("Error: endianness mismatch.\n");
-	return -EINVAL;
+	return -LIBBPF_ERRNO__ENDIAN;
 }
 
 static int
@@ -402,7 +456,7 @@ bpf_object__init_kversion(struct bpf_object *obj,
 
 	if (size != sizeof(kver)) {
 		pr_warning("invalid kver section in %s\n", obj->path);
-		return -EINVAL;
+		return -LIBBPF_ERRNO__FORMAT;
 	}
 	memcpy(&kver, data, sizeof(kver));
 	obj->kern_version = kver;
@@ -444,7 +498,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 	if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) {
 		pr_warning("failed to get e_shstrndx from %s\n",
 			   obj->path);
-		return -EINVAL;
+		return -LIBBPF_ERRNO__FORMAT;
 	}
 
 	while ((scn = elf_nextscn(elf, scn)) != NULL) {
@@ -456,7 +510,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 		if (gelf_getshdr(scn, &sh) != &sh) {
 			pr_warning("failed to get section header from %s\n",
 				   obj->path);
-			err = -EINVAL;
+			err = -LIBBPF_ERRNO__FORMAT;
 			goto out;
 		}
 
@@ -464,7 +518,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 		if (!name) {
 			pr_warning("failed to get section name from %s\n",
 				   obj->path);
-			err = -EINVAL;
+			err = -LIBBPF_ERRNO__FORMAT;
 			goto out;
 		}
 
@@ -472,7 +526,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 		if (!data) {
 			pr_warning("failed to get section data from %s(%s)\n",
 				   name, obj->path);
-			err = -EINVAL;
+			err = -LIBBPF_ERRNO__FORMAT;
 			goto out;
 		}
 		pr_debug("section %s, size %ld, link %d, flags %lx, type=%d\n",
@@ -495,7 +549,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 			if (obj->efile.symbols) {
 				pr_warning("bpf: multiple SYMTAB in %s\n",
 					   obj->path);
-				err = -EEXIST;
+				err = -LIBBPF_ERRNO__FORMAT;
 			} else
 				obj->efile.symbols = data;
 		} else if ((sh.sh_type == SHT_PROGBITS) &&
@@ -504,7 +558,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 			err = bpf_object__add_program(obj, data->d_buf,
 						      data->d_size, name, idx);
 			if (err) {
-				char errmsg[128];
+				char errmsg[STRERR_BUFSIZE];
+
 				strerror_r(-err, errmsg, sizeof(errmsg));
 				pr_warning("failed to alloc program %s (%s): %s",
 					   name, obj->path, errmsg);
@@ -576,7 +631,7 @@ bpf_program__collect_reloc(struct bpf_program *prog,
 
 		if (!gelf_getrel(data, i, &rel)) {
 			pr_warning("relocation: failed to get %d reloc\n", i);
-			return -EINVAL;
+			return -LIBBPF_ERRNO__FORMAT;
 		}
 
 		insn_idx = rel.r_offset / sizeof(struct bpf_insn);
@@ -587,20 +642,20 @@ bpf_program__collect_reloc(struct bpf_program *prog,
 				 &sym)) {
 			pr_warning("relocation: symbol %"PRIx64" not found\n",
 				   GELF_R_SYM(rel.r_info));
-			return -EINVAL;
+			return -LIBBPF_ERRNO__FORMAT;
 		}
 
 		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);
-			return -EINVAL;
+			return -LIBBPF_ERRNO__RELOC;
 		}
 
 		map_idx = sym.st_value / sizeof(struct bpf_map_def);
 		if (map_idx >= nr_maps) {
 			pr_warning("bpf relocation: map_idx %d large than %d\n",
 				   (int)map_idx, (int)nr_maps - 1);
-			return -EINVAL;
+			return -LIBBPF_ERRNO__RELOC;
 		}
 
 		prog->reloc_desc[i].insn_idx = insn_idx;
@@ -683,7 +738,7 @@ bpf_program__relocate(struct bpf_program *prog, int *map_fds)
 		if (insn_idx >= (int)prog->insns_cnt) {
 			pr_warning("relocation out of range: '%s'\n",
 				   prog->section_name);
-			return -ERANGE;
+			return -LIBBPF_ERRNO__RELOC;
 		}
 		insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
 		insns[insn_idx].imm = map_fds[map_idx];
@@ -721,7 +776,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 
 	if (!obj_elf_valid(obj)) {
 		pr_warning("Internal error: elf object is closed\n");
-		return -EINVAL;
+		return -LIBBPF_ERRNO__INTERNAL;
 	}
 
 	for (i = 0; i < obj->efile.nr_reloc; i++) {
@@ -734,21 +789,21 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 
 		if (shdr->sh_type != SHT_REL) {
 			pr_warning("internal error at %d\n", __LINE__);
-			return -EINVAL;
+			return -LIBBPF_ERRNO__INTERNAL;
 		}
 
 		prog = bpf_object__find_prog_by_idx(obj, idx);
 		if (!prog) {
 			pr_warning("relocation failed: no %d section\n",
 				   idx);
-			return -ENOENT;
+			return -LIBBPF_ERRNO__RELOC;
 		}
 
 		err = bpf_program__collect_reloc(prog, nr_maps,
 						 shdr, data,
 						 obj->efile.symbols);
 		if (err)
-			return -EINVAL;
+			return err;
 	}
 	return 0;
 }
@@ -777,13 +832,23 @@ load_program(struct bpf_insn *insns, int insns_cnt,
 		goto out;
 	}
 
-	ret = -EINVAL;
+	ret = -LIBBPF_ERRNO__LOAD;
 	pr_warning("load bpf program failed: %s\n", strerror(errno));
 
-	if (log_buf) {
+	if (log_buf && log_buf[0] != '\0') {
+		ret = -LIBBPF_ERRNO__VERIFY;
 		pr_warning("-- BEGIN DUMP LOG ---\n");
 		pr_warning("\n%s\n", log_buf);
 		pr_warning("-- END LOG --\n");
+	} else {
+		if (insns_cnt >= BPF_MAXINSNS) {
+			pr_warning("Program too large (%d insns), at most %d insns\n",
+				   insns_cnt, BPF_MAXINSNS);
+			ret = -LIBBPF_ERRNO__PROG2BIG;
+		} else if (log_buf) {
+			pr_warning("log buffer is empty\n");
+			ret = -LIBBPF_ERRNO__KVER;
+		}
 	}
 
 out:
@@ -831,7 +896,7 @@ static int bpf_object__validate(struct bpf_object *obj)
 	if (obj->kern_version == 0) {
 		pr_warning("%s doesn't provide kernel version\n",
 			   obj->path);
-		return -EINVAL;
+		return -LIBBPF_ERRNO__KVERSION;
 	}
 	return 0;
 }
@@ -840,32 +905,28 @@ static struct bpf_object *
 __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz)
 {
 	struct bpf_object *obj;
+	int err;
 
 	if (elf_version(EV_CURRENT) == EV_NONE) {
 		pr_warning("failed to init libelf for %s\n", path);
-		return NULL;
+		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
 	}
 
 	obj = bpf_object__new(path, obj_buf, obj_buf_sz);
-	if (!obj)
-		return NULL;
+	if (IS_ERR(obj))
+		return obj;
 
-	if (bpf_object__elf_init(obj))
-		goto out;
-	if (bpf_object__check_endianness(obj))
-		goto out;
-	if (bpf_object__elf_collect(obj))
-		goto out;
-	if (bpf_object__collect_reloc(obj))
-		goto out;
-	if (bpf_object__validate(obj))
-		goto out;
+	CHECK_ERR(bpf_object__elf_init(obj), err, out);
+	CHECK_ERR(bpf_object__check_endianness(obj), err, out);
+	CHECK_ERR(bpf_object__elf_collect(obj), err, out);
+	CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
+	CHECK_ERR(bpf_object__validate(obj), err, out);
 
 	bpf_object__elf_finish(obj);
 	return obj;
 out:
 	bpf_object__close(obj);
-	return NULL;
+	return ERR_PTR(err);
 }
 
 struct bpf_object *bpf_object__open(const char *path)
@@ -922,6 +983,8 @@ int bpf_object__unload(struct bpf_object *obj)
 
 int bpf_object__load(struct bpf_object *obj)
 {
+	int err;
+
 	if (!obj)
 		return -EINVAL;
 
@@ -931,18 +994,16 @@ int bpf_object__load(struct bpf_object *obj)
 	}
 
 	obj->loaded = true;
-	if (bpf_object__create_maps(obj))
-		goto out;
-	if (bpf_object__relocate(obj))
-		goto out;
-	if (bpf_object__load_progs(obj))
-		goto out;
+
+	CHECK_ERR(bpf_object__create_maps(obj), err, out);
+	CHECK_ERR(bpf_object__relocate(obj), err, out);
+	CHECK_ERR(bpf_object__load_progs(obj), err, out);
 
 	return 0;
 out:
 	bpf_object__unload(obj);
 	pr_warning("failed to load object '%s'\n", obj->path);
-	return -EINVAL;
+	return err;
 }
 
 void bpf_object__close(struct bpf_object *obj)
@@ -990,10 +1051,18 @@ const char *
 bpf_object__get_name(struct bpf_object *obj)
 {
 	if (!obj)
-		return NULL;
+		return ERR_PTR(-EINVAL);
 	return obj->path;
 }
 
+unsigned int
+bpf_object__get_kversion(struct bpf_object *obj)
+{
+	if (!obj)
+		return 0;
+	return obj->kern_version;
+}
+
 struct bpf_program *
 bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
 {
@@ -1034,16 +1103,16 @@ int bpf_program__get_private(struct bpf_program *prog, void **ppriv)
 	return 0;
 }
 
-const char *bpf_program__title(struct bpf_program *prog, bool dup)
+const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
 {
 	const char *title;
 
 	title = prog->section_name;
-	if (dup) {
+	if (needs_copy) {
 		title = strdup(title);
 		if (!title) {
 			pr_warning("failed to strdup program title\n");
-			return NULL;
+			return ERR_PTR(-ENOMEM);
 		}
 	}
 
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index f16170c95ffd..c9a9aef2806c 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -10,6 +10,26 @@
 
 #include <stdio.h>
 #include <stdbool.h>
+#include <linux/err.h>
+
+enum libbpf_errno {
+	__LIBBPF_ERRNO__START = 4000,
+
+	/* Something wrong in libelf */
+	LIBBPF_ERRNO__LIBELF = __LIBBPF_ERRNO__START,
+	LIBBPF_ERRNO__FORMAT,	/* BPF object format invalid */
+	LIBBPF_ERRNO__KVERSION,	/* Incorrect or no 'version' section */
+	LIBBPF_ERRNO__ENDIAN,	/* Endian missmatch */
+	LIBBPF_ERRNO__INTERNAL,	/* Internal error in libbpf */
+	LIBBPF_ERRNO__RELOC,	/* Relocation failed */
+	LIBBPF_ERRNO__LOAD,	/* Load program failure for unknown reason */
+	LIBBPF_ERRNO__VERIFY,	/* Kernel verifier blocks program loading */
+	LIBBPF_ERRNO__PROG2BIG,	/* Program too big */
+	LIBBPF_ERRNO__KVER,	/* Incorrect kernel version */
+	__LIBBPF_ERRNO__END,
+};
+
+int libbpf_strerror(int err, char *buf, size_t size);
 
 /*
  * In include/linux/compiler-gcc.h, __printf is defined. However
@@ -36,6 +56,7 @@ void bpf_object__close(struct bpf_object *object);
 int bpf_object__load(struct bpf_object *obj);
 int bpf_object__unload(struct bpf_object *obj);
 const char *bpf_object__get_name(struct bpf_object *obj);
+unsigned int bpf_object__get_kversion(struct bpf_object *obj);
 
 struct bpf_object *bpf_object__next(struct bpf_object *prev);
 #define bpf_object__for_each_safe(pos, tmp)			\
@@ -63,7 +84,7 @@ int bpf_program__set_private(struct bpf_program *prog, void *priv,
 int bpf_program__get_private(struct bpf_program *prog,
 			     void **ppriv);
 
-const char *bpf_program__title(struct bpf_program *prog, bool dup);
+const char *bpf_program__title(struct bpf_program *prog, bool needs_copy);
 
 int bpf_program__fd(struct bpf_program *prog);
 
diff --git a/tools/lib/lockdep/common.c b/tools/lib/lockdep/common.c
index 8ef602f18a32..9be663340f0a 100644
--- a/tools/lib/lockdep/common.c
+++ b/tools/lib/lockdep/common.c
@@ -18,7 +18,7 @@ __attribute__((constructor)) static void liblockdep_init(void)
 
 __attribute__((destructor)) static void liblockdep_exit(void)
 {
-	debug_check_no_locks_held(&current_obj);
+	debug_check_no_locks_held();
 }
 
 struct task_struct *__curr(void)
diff --git a/tools/lib/lockdep/include/liblockdep/common.h b/tools/lib/lockdep/include/liblockdep/common.h
index 0bda630027c3..a60c14b9662a 100644
--- a/tools/lib/lockdep/include/liblockdep/common.h
+++ b/tools/lib/lockdep/include/liblockdep/common.h
@@ -43,6 +43,8 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 			struct lockdep_map *nest_lock, unsigned long ip);
 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/uinclude/linux/compiler.h b/tools/lib/lockdep/uinclude/linux/compiler.h
index 7ac838a1f196..6386dc3182a0 100644
--- a/tools/lib/lockdep/uinclude/linux/compiler.h
+++ b/tools/lib/lockdep/uinclude/linux/compiler.h
@@ -3,5 +3,7 @@
 
 #define __used		__attribute__((__unused__))
 #define unlikely
+#define WRITE_ONCE(x, val) x=(val)
+#define RCU_INIT_POINTER(p, v) p=(v)
 
 #endif
diff --git a/tools/lib/lockdep/uinclude/linux/lockdep.h b/tools/lib/lockdep/uinclude/linux/lockdep.h
index c1552c28507e..c808c7d02d21 100644
--- a/tools/lib/lockdep/uinclude/linux/lockdep.h
+++ b/tools/lib/lockdep/uinclude/linux/lockdep.h
@@ -6,7 +6,7 @@
 #include <string.h>
 #include <limits.h>
 #include <linux/utsname.h>
-
+#include <linux/compiler.h>
 
 #define MAX_LOCK_DEPTH 2000UL
 
@@ -54,5 +54,6 @@ static struct new_utsname *init_utsname(void)
 #define static_obj(x) 1
 
 #define debug_show_all_locks()
+extern void debug_check_no_locks_held(void);
 
 #endif
diff --git a/tools/net/Makefile b/tools/net/Makefile
index ee577ea03ba5..ddf888010652 100644
--- a/tools/net/Makefile
+++ b/tools/net/Makefile
@@ -4,6 +4,9 @@ CC = gcc
 LEX = flex
 YACC = bison
 
+CFLAGS += -Wall -O2
+CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
+
 %.yacc.c: %.y
 	$(YACC) -o $@ -d $<
 
@@ -12,15 +15,13 @@ YACC = bison
 
 all : bpf_jit_disasm bpf_dbg bpf_asm
 
-bpf_jit_disasm : CFLAGS = -Wall -O2 -DPACKAGE='bpf_jit_disasm'
+bpf_jit_disasm : CFLAGS += -DPACKAGE='bpf_jit_disasm'
 bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl
 bpf_jit_disasm : bpf_jit_disasm.o
 
-bpf_dbg : CFLAGS = -Wall -O2
 bpf_dbg : LDLIBS = -lreadline
 bpf_dbg : bpf_dbg.o
 
-bpf_asm : CFLAGS = -Wall -O2 -I.
 bpf_asm : LDLIBS =
 bpf_asm : bpf_asm.o bpf_exp.yacc.o bpf_exp.lex.o
 bpf_exp.lex.o : bpf_exp.yacc.c
diff --git a/tools/net/bpf_jit_disasm.c b/tools/net/bpf_jit_disasm.c
index 2cd3d4c99738..5b3241340945 100644
--- a/tools/net/bpf_jit_disasm.c
+++ b/tools/net/bpf_jit_disasm.c
@@ -156,8 +156,8 @@ static void put_log_buff(char *buff)
 	free(buff);
 }
 
-static int get_last_jit_image(char *haystack, size_t hlen,
-			      uint8_t *image, size_t ilen)
+static unsigned int get_last_jit_image(char *haystack, size_t hlen,
+				       uint8_t *image, size_t ilen)
 {
 	char *ptr, *pptr, *tmp;
 	off_t off = 0;
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 7ea078658a87..13293de8869f 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -62,7 +62,6 @@ OPTIONS
 --verbose=::
         Verbosity level.
 
--i::
 --no-inherit::
 	Child tasks do not inherit counters.
 
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 480546d5f13b..dcd9a70c7193 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -78,7 +78,7 @@ clean:
 # The build-test target is not really parallel, don't print the jobs info:
 #
 build-test:
-	@$(MAKE) -f tests/make --no-print-directory
+	@$(MAKE) SHUF=1 -f tests/make --no-print-directory
 
 #
 # All other targets get passed through:
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 0a945d2e8ca5..99d127fe9c35 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -675,6 +675,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			.fork		= perf_event__repipe,
 			.exit		= perf_event__repipe,
 			.lost		= perf_event__repipe,
+			.lost_samples	= perf_event__repipe,
 			.aux		= perf_event__repipe,
 			.itrace_start	= perf_event__repipe,
 			.context_switch	= perf_event__repipe,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 2853ad2bd435..f256fac1e722 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -44,7 +44,7 @@
 struct report {
 	struct perf_tool	tool;
 	struct perf_session	*session;
-	bool			force, use_tui, use_gtk, use_stdio;
+	bool			use_tui, use_gtk, use_stdio;
 	bool			hide_unresolved;
 	bool			dont_use_callchains;
 	bool			show_full_info;
@@ -678,7 +678,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "file", "vmlinux pathname"),
 	OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name,
 		   "file", "kallsyms pathname"),
-	OPT_BOOLEAN('f', "force", &report.force, "don't complain, do it"),
+	OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
 	OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
 		    "load module symbols - WARNING: use only with -k and LIVE kernel"),
 	OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
@@ -832,7 +832,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	}
 
 	file.path  = input_name;
-	file.force = report.force;
+	file.force = symbol_conf.force;
 
 repeat:
 	session = perf_session__new(&file, false, &report.tool);
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 0ee6d900e100..e3d3e32c0a93 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1203,12 +1203,13 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_
 
 static int pid_cmp(struct work_atoms *l, struct work_atoms *r)
 {
+	if (l->thread == r->thread)
+		return 0;
 	if (l->thread->tid < r->thread->tid)
 		return -1;
 	if (l->thread->tid > r->thread->tid)
 		return 1;
-
-	return 0;
+	return (int)(l->thread - r->thread);
 }
 
 static int avg_cmp(struct work_atoms *l, struct work_atoms *r)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 2f438f76cceb..e77880b5094d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -122,6 +122,9 @@ static bool			forever				= false;
 static struct timespec		ref_time;
 static struct cpu_map		*aggr_map;
 static aggr_get_id_t		aggr_get_id;
+static bool			append_file;
+static const char		*output_name;
+static int			output_fd;
 
 static volatile int done = 0;
 
@@ -513,15 +516,6 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
-
-	if (csv_output || stat_config.interval)
-		return;
-
-	if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
-		fprintf(output, " # %8.3f CPUs utilized          ",
-			avg / avg_stats(&walltime_nsecs_stats));
-	else
-		fprintf(output, "                                   ");
 }
 
 static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
@@ -529,7 +523,6 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 	FILE *output = stat_config.output;
 	double sc =  evsel->scale;
 	const char *fmt;
-	int cpu = cpu_map__id_to_cpu(id);
 
 	if (csv_output) {
 		fmt = sc != 1.0 ?  "%.2f%s" : "%.0f%s";
@@ -542,9 +535,6 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 
 	aggr_printout(evsel, id, nr);
 
-	if (stat_config.aggr_mode == AGGR_GLOBAL)
-		cpu = 0;
-
 	fprintf(output, fmt, avg, csv_sep);
 
 	if (evsel->unit)
@@ -556,12 +546,24 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
+}
 
-	if (csv_output || stat_config.interval)
-		return;
+static void printout(int id, int nr, struct perf_evsel *counter, double uval)
+{
+	int cpu = cpu_map__id_to_cpu(id);
+
+	if (stat_config.aggr_mode == AGGR_GLOBAL)
+		cpu = 0;
 
-	perf_stat__print_shadow_stats(output, evsel, avg, cpu,
-				      stat_config.aggr_mode);
+	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);
 }
 
 static void print_aggr(char *prefix)
@@ -617,12 +619,7 @@ static void print_aggr(char *prefix)
 				continue;
 			}
 			uval = val * counter->scale;
-
-			if (nsec_counter(counter))
-				nsec_printout(id, nr, counter, uval);
-			else
-				abs_printout(id, nr, counter, uval);
-
+			printout(id, nr, counter, uval);
 			if (!csv_output)
 				print_noise(counter, 1.0);
 
@@ -653,11 +650,7 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
 			fprintf(output, "%s", prefix);
 
 		uval = val * counter->scale;
-
-		if (nsec_counter(counter))
-			nsec_printout(thread, 0, counter, uval);
-		else
-			abs_printout(thread, 0, counter, uval);
+		printout(thread, 0, counter, uval);
 
 		if (!csv_output)
 			print_noise(counter, 1.0);
@@ -707,11 +700,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 	}
 
 	uval = avg * counter->scale;
-
-	if (nsec_counter(counter))
-		nsec_printout(-1, 0, counter, uval);
-	else
-		abs_printout(-1, 0, counter, uval);
+	printout(-1, 0, counter, uval);
 
 	print_noise(counter, avg);
 
@@ -764,12 +753,7 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 		}
 
 		uval = val * counter->scale;
-
-		if (nsec_counter(counter))
-			nsec_printout(cpu, 0, counter, uval);
-		else
-			abs_printout(cpu, 0, counter, uval);
-
+		printout(cpu, 0, counter, uval);
 		if (!csv_output)
 			print_noise(counter, 1.0);
 		print_running(run, ena);
@@ -946,6 +930,67 @@ static int stat__set_big_num(const struct option *opt __maybe_unused,
 	return 0;
 }
 
+static const struct option stat_options[] = {
+	OPT_BOOLEAN('T', "transaction", &transaction_run,
+		    "hardware transaction statistics"),
+	OPT_CALLBACK('e', "event", &evsel_list, "event",
+		     "event selector. use 'perf list' to list available events",
+		     parse_events_option),
+	OPT_CALLBACK(0, "filter", &evsel_list, "filter",
+		     "event filter", parse_filter),
+	OPT_BOOLEAN('i', "no-inherit", &no_inherit,
+		    "child tasks do not inherit counters"),
+	OPT_STRING('p', "pid", &target.pid, "pid",
+		   "stat events on existing process id"),
+	OPT_STRING('t', "tid", &target.tid, "tid",
+		   "stat events on existing thread id"),
+	OPT_BOOLEAN('a', "all-cpus", &target.system_wide,
+		    "system-wide collection from all CPUs"),
+	OPT_BOOLEAN('g', "group", &group,
+		    "put the counters into a counter group"),
+	OPT_BOOLEAN('c', "scale", &stat_config.scale, "scale/normalize counters"),
+	OPT_INCR('v', "verbose", &verbose,
+		    "be more verbose (show counter open errors, etc)"),
+	OPT_INTEGER('r', "repeat", &run_count,
+		    "repeat command and print average + stddev (max: 100, forever: 0)"),
+	OPT_BOOLEAN('n', "null", &null_run,
+		    "null run - dont start any counters"),
+	OPT_INCR('d', "detailed", &detailed_run,
+		    "detailed run - start a lot of events"),
+	OPT_BOOLEAN('S', "sync", &sync_run,
+		    "call sync() before starting a run"),
+	OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL,
+			   "print large numbers with thousands\' separators",
+			   stat__set_big_num),
+	OPT_STRING('C', "cpu", &target.cpu_list, "cpu",
+		    "list of cpus to monitor in system-wide"),
+	OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode,
+		    "disable CPU count aggregation", AGGR_NONE),
+	OPT_STRING('x', "field-separator", &csv_sep, "separator",
+		   "print counts with custom separator"),
+	OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
+		     "monitor event in cgroup name only", parse_cgroups),
+	OPT_STRING('o', "output", &output_name, "file", "output file name"),
+	OPT_BOOLEAN(0, "append", &append_file, "append to the output file"),
+	OPT_INTEGER(0, "log-fd", &output_fd,
+		    "log output to fd, instead of stderr"),
+	OPT_STRING(0, "pre", &pre_cmd, "command",
+			"command to run prior to the measured command"),
+	OPT_STRING(0, "post", &post_cmd, "command",
+			"command to run after to the measured command"),
+	OPT_UINTEGER('I', "interval-print", &stat_config.interval,
+		    "print counts at regular interval in ms (>= 10)"),
+	OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode,
+		     "aggregate counts per processor socket", AGGR_SOCKET),
+	OPT_SET_UINT(0, "per-core", &stat_config.aggr_mode,
+		     "aggregate counts per physical processor core", AGGR_CORE),
+	OPT_SET_UINT(0, "per-thread", &stat_config.aggr_mode,
+		     "aggregate counts per thread", AGGR_THREAD),
+	OPT_UINTEGER('D', "delay", &initial_delay,
+		     "ms to wait before starting measurement after program start"),
+	OPT_END()
+};
+
 static int perf_stat__get_socket(struct cpu_map *map, int cpu)
 {
 	return cpu_map__get_socket(map, cpu, NULL);
@@ -1193,69 +1238,6 @@ static int add_default_attributes(void)
 
 int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	bool append_file = false;
-	int output_fd = 0;
-	const char *output_name	= NULL;
-	const struct option options[] = {
-	OPT_BOOLEAN('T', "transaction", &transaction_run,
-		    "hardware transaction statistics"),
-	OPT_CALLBACK('e', "event", &evsel_list, "event",
-		     "event selector. use 'perf list' to list available events",
-		     parse_events_option),
-	OPT_CALLBACK(0, "filter", &evsel_list, "filter",
-		     "event filter", parse_filter),
-	OPT_BOOLEAN('i', "no-inherit", &no_inherit,
-		    "child tasks do not inherit counters"),
-	OPT_STRING('p', "pid", &target.pid, "pid",
-		   "stat events on existing process id"),
-	OPT_STRING('t', "tid", &target.tid, "tid",
-		   "stat events on existing thread id"),
-	OPT_BOOLEAN('a', "all-cpus", &target.system_wide,
-		    "system-wide collection from all CPUs"),
-	OPT_BOOLEAN('g', "group", &group,
-		    "put the counters into a counter group"),
-	OPT_BOOLEAN('c', "scale", &stat_config.scale, "scale/normalize counters"),
-	OPT_INCR('v', "verbose", &verbose,
-		    "be more verbose (show counter open errors, etc)"),
-	OPT_INTEGER('r', "repeat", &run_count,
-		    "repeat command and print average + stddev (max: 100, forever: 0)"),
-	OPT_BOOLEAN('n', "null", &null_run,
-		    "null run - dont start any counters"),
-	OPT_INCR('d', "detailed", &detailed_run,
-		    "detailed run - start a lot of events"),
-	OPT_BOOLEAN('S', "sync", &sync_run,
-		    "call sync() before starting a run"),
-	OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL,
-			   "print large numbers with thousands\' separators",
-			   stat__set_big_num),
-	OPT_STRING('C', "cpu", &target.cpu_list, "cpu",
-		    "list of cpus to monitor in system-wide"),
-	OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode,
-		    "disable CPU count aggregation", AGGR_NONE),
-	OPT_STRING('x', "field-separator", &csv_sep, "separator",
-		   "print counts with custom separator"),
-	OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
-		     "monitor event in cgroup name only", parse_cgroups),
-	OPT_STRING('o', "output", &output_name, "file", "output file name"),
-	OPT_BOOLEAN(0, "append", &append_file, "append to the output file"),
-	OPT_INTEGER(0, "log-fd", &output_fd,
-		    "log output to fd, instead of stderr"),
-	OPT_STRING(0, "pre", &pre_cmd, "command",
-			"command to run prior to the measured command"),
-	OPT_STRING(0, "post", &post_cmd, "command",
-			"command to run after to the measured command"),
-	OPT_UINTEGER('I', "interval-print", &stat_config.interval,
-		    "print counts at regular interval in ms (>= 10)"),
-	OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode,
-		     "aggregate counts per processor socket", AGGR_SOCKET),
-	OPT_SET_UINT(0, "per-core", &stat_config.aggr_mode,
-		     "aggregate counts per physical processor core", AGGR_CORE),
-	OPT_SET_UINT(0, "per-thread", &stat_config.aggr_mode,
-		     "aggregate counts per thread", AGGR_THREAD),
-	OPT_UINTEGER('D', "delay", &initial_delay,
-		     "ms to wait before starting measurement after program start"),
-	OPT_END()
-	};
 	const char * const stat_usage[] = {
 		"perf stat [<options>] [<command>]",
 		NULL
@@ -1271,7 +1253,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (evsel_list == NULL)
 		return -ENOMEM;
 
-	argc = parse_options(argc, argv, options, stat_usage,
+	argc = parse_options(argc, argv, stat_options, stat_usage,
 		PARSE_OPT_STOP_AT_NON_OPTION);
 
 	interval = stat_config.interval;
@@ -1281,14 +1263,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	if (output_name && output_fd) {
 		fprintf(stderr, "cannot use both --output and --log-fd\n");
-		parse_options_usage(stat_usage, options, "o", 1);
-		parse_options_usage(NULL, options, "log-fd", 0);
+		parse_options_usage(stat_usage, stat_options, "o", 1);
+		parse_options_usage(NULL, stat_options, "log-fd", 0);
 		goto out;
 	}
 
 	if (output_fd < 0) {
 		fprintf(stderr, "argument to --log-fd must be a > 0\n");
-		parse_options_usage(stat_usage, options, "log-fd", 0);
+		parse_options_usage(stat_usage, stat_options, "log-fd", 0);
 		goto out;
 	}
 
@@ -1328,8 +1310,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		/* User explicitly passed -B? */
 		if (big_num_opt == 1) {
 			fprintf(stderr, "-B option not supported with -x\n");
-			parse_options_usage(stat_usage, options, "B", 1);
-			parse_options_usage(NULL, options, "x", 1);
+			parse_options_usage(stat_usage, stat_options, "B", 1);
+			parse_options_usage(NULL, stat_options, "x", 1);
 			goto out;
 		} else /* Nope, so disable big number formatting */
 			big_num = false;
@@ -1337,11 +1319,11 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		big_num = false;
 
 	if (!argc && target__none(&target))
-		usage_with_options(stat_usage, options);
+		usage_with_options(stat_usage, stat_options);
 
 	if (run_count < 0) {
 		pr_err("Run count must be a positive number\n");
-		parse_options_usage(stat_usage, options, "r", 1);
+		parse_options_usage(stat_usage, stat_options, "r", 1);
 		goto out;
 	} else if (run_count == 0) {
 		forever = true;
@@ -1351,8 +1333,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	if ((stat_config.aggr_mode == AGGR_THREAD) && !target__has_task(&target)) {
 		fprintf(stderr, "The --per-thread option is only available "
 			"when monitoring via -p -t options.\n");
-		parse_options_usage(NULL, options, "p", 1);
-		parse_options_usage(NULL, options, "t", 1);
+		parse_options_usage(NULL, stat_options, "p", 1);
+		parse_options_usage(NULL, stat_options, "t", 1);
 		goto out;
 	}
 
@@ -1366,9 +1348,9 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		fprintf(stderr, "both cgroup and no-aggregation "
 			"modes only available in system-wide mode\n");
 
-		parse_options_usage(stat_usage, options, "G", 1);
-		parse_options_usage(NULL, options, "A", 1);
-		parse_options_usage(NULL, options, "a", 1);
+		parse_options_usage(stat_usage, stat_options, "G", 1);
+		parse_options_usage(NULL, stat_options, "A", 1);
+		parse_options_usage(NULL, stat_options, "a", 1);
 		goto out;
 	}
 
@@ -1380,12 +1362,12 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (perf_evlist__create_maps(evsel_list, &target) < 0) {
 		if (target__has_task(&target)) {
 			pr_err("Problems finding threads of monitor\n");
-			parse_options_usage(stat_usage, options, "p", 1);
-			parse_options_usage(NULL, options, "t", 1);
+			parse_options_usage(stat_usage, stat_options, "p", 1);
+			parse_options_usage(NULL, stat_options, "t", 1);
 		} else if (target__has_cpu(&target)) {
 			perror("failed to parse CPUs map");
-			parse_options_usage(stat_usage, options, "C", 1);
-			parse_options_usage(NULL, options, "a", 1);
+			parse_options_usage(stat_usage, stat_options, "C", 1);
+			parse_options_usage(NULL, stat_options, "a", 1);
 		}
 		goto out;
 	}
@@ -1400,7 +1382,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (interval && interval < 100) {
 		if (interval < 10) {
 			pr_err("print interval must be >= 10ms\n");
-			parse_options_usage(stat_usage, options, "I", 1);
+			parse_options_usage(stat_usage, stat_options, "I", 1);
 			goto out;
 		} else
 			pr_warning("print interval < 100ms. "
diff --git a/tools/perf/tests/.gitignore b/tools/perf/tests/.gitignore
new file mode 100644
index 000000000000..489fc9ffbcb0
--- /dev/null
+++ b/tools/perf/tests/.gitignore
@@ -0,0 +1,2 @@
+llvm-src-base.c
+llvm-src-kbuild.c
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 50de2253cff6..f41ebf8849fe 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -31,9 +31,24 @@ 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
+perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o
+perf-y += bpf.o
 perf-y += topology.o
 
+$(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c
+	$(call rule_mkdir)
+	$(Q)echo '#include <tests/llvm.h>' > $@
+	$(Q)echo 'const char test_llvm__bpf_base_prog[] =' >> $@
+	$(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
+	$(Q)echo ';' >> $@
+
+$(OUTPUT)tests/llvm-src-kbuild.c: tests/bpf-script-test-kbuild.c
+	$(call rule_mkdir)
+	$(Q)echo '#include <tests/llvm.h>' > $@
+	$(Q)echo 'const char test_llvm__bpf_test_kbuild_prog[] =' >> $@
+	$(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/attr.c b/tools/perf/tests/attr.c
index 2dfc9ad0e6f2..638875a0960a 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -171,6 +171,5 @@ int test__attr(void)
 	    !lstat(path_perf, &st))
 		return run_dir(path_dir, path_perf);
 
-	fprintf(stderr, " (omitted)");
-	return 0;
+	return TEST_SKIP;
 }
diff --git a/tools/perf/tests/bpf-script-example.c b/tools/perf/tests/bpf-script-example.c
index 410a70b93b93..0ec9c2c03164 100644
--- a/tools/perf/tests/bpf-script-example.c
+++ b/tools/perf/tests/bpf-script-example.c
@@ -1,3 +1,7 @@
+/*
+ * bpf-script-example.c
+ * Test basic LLVM building
+ */
 #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'
diff --git a/tools/perf/tests/bpf-script-test-kbuild.c b/tools/perf/tests/bpf-script-test-kbuild.c
new file mode 100644
index 000000000000..3626924740d8
--- /dev/null
+++ b/tools/perf/tests/bpf-script-test-kbuild.c
@@ -0,0 +1,21 @@
+/*
+ * bpf-script-test-kbuild.c
+ * Test include from kernel header
+ */
+#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 SEC(NAME) __attribute__((section(NAME), used))
+
+#include <uapi/linux/fs.h>
+#include <uapi/asm/ptrace.h>
+
+SEC("func=vfs_llseek")
+int bpf_func__vfs_llseek(void *ctx)
+{
+	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
new file mode 100644
index 000000000000..ec16f7812c8b
--- /dev/null
+++ b/tools/perf/tests/bpf.c
@@ -0,0 +1,209 @@
+#include <stdio.h>
+#include <sys/epoll.h>
+#include <util/bpf-loader.h>
+#include <util/evlist.h>
+#include "tests.h"
+#include "llvm.h"
+#include "debug.h"
+#define NR_ITERS       111
+
+#ifdef HAVE_LIBBPF_SUPPORT
+
+static int epoll_pwait_loop(void)
+{
+	int i;
+
+	/* Should fail NR_ITERS times */
+	for (i = 0; i < NR_ITERS; i++)
+		epoll_pwait(-(i + 1), NULL, 0, 0, NULL);
+	return 0;
+}
+
+static struct {
+	enum test_llvm__testcase prog_id;
+	const char *desc;
+	const char *name;
+	const char *msg_compile_fail;
+	const char *msg_load_fail;
+	int (*target_func)(void);
+	int expect_result;
+} bpf_testcase_table[] = {
+	{
+		LLVM_TESTCASE_BASE,
+		"Test basic BPF filtering",
+		"[basic_bpf_test]",
+		"fix 'perf test LLVM' first",
+		"load bpf object failed",
+		&epoll_pwait_loop,
+		(NR_ITERS + 1) / 2,
+	},
+};
+
+static int do_test(struct bpf_object *obj, int (*func)(void),
+		   int expect)
+{
+	struct record_opts opts = {
+		.target = {
+			.uid = UINT_MAX,
+			.uses_mmap = true,
+		},
+		.freq	      = 0,
+		.mmap_pages   = 256,
+		.default_interval = 1,
+	};
+
+	char pid[16];
+	char sbuf[STRERR_BUFSIZE];
+	struct perf_evlist *evlist;
+	int i, ret = TEST_FAIL, err = 0, count = 0;
+
+	struct parse_events_evlist parse_evlist;
+	struct parse_events_error parse_error;
+
+	bzero(&parse_error, sizeof(parse_error));
+	bzero(&parse_evlist, sizeof(parse_evlist));
+	parse_evlist.error = &parse_error;
+	INIT_LIST_HEAD(&parse_evlist.list);
+
+	err = parse_events_load_bpf_obj(&parse_evlist, &parse_evlist.list, obj);
+	if (err || list_empty(&parse_evlist.list)) {
+		pr_debug("Failed to add events selected by BPF\n");
+		if (!err)
+			return TEST_FAIL;
+	}
+
+	snprintf(pid, sizeof(pid), "%d", getpid());
+	pid[sizeof(pid) - 1] = '\0';
+	opts.target.tid = opts.target.pid = pid;
+
+	/* Instead of perf_evlist__new_default, don't add default events */
+	evlist = perf_evlist__new();
+	if (!evlist) {
+		pr_debug("No ehough memory to create evlist\n");
+		return TEST_FAIL;
+	}
+
+	err = perf_evlist__create_maps(evlist, &opts.target);
+	if (err < 0) {
+		pr_debug("Not enough memory to create thread/cpu maps\n");
+		goto out_delete_evlist;
+	}
+
+	perf_evlist__splice_list_tail(evlist, &parse_evlist.list);
+	evlist->nr_groups = parse_evlist.nr_groups;
+
+	perf_evlist__config(evlist, &opts);
+
+	err = perf_evlist__open(evlist);
+	if (err < 0) {
+		pr_debug("perf_evlist__open: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
+		goto out_delete_evlist;
+	}
+
+	err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
+	if (err < 0) {
+		pr_debug("perf_evlist__mmap: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
+		goto out_delete_evlist;
+	}
+
+	perf_evlist__enable(evlist);
+	(*func)();
+	perf_evlist__disable(evlist);
+
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		union perf_event *event;
+
+		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+			const u32 type = event->header.type;
+
+			if (type == PERF_RECORD_SAMPLE)
+				count ++;
+		}
+	}
+
+	if (count != expect)
+		pr_debug("BPF filter result incorrect\n");
+
+	ret = TEST_OK;
+
+out_delete_evlist:
+	perf_evlist__delete(evlist);
+	return ret;
+}
+
+static struct bpf_object *
+prepare_bpf(void *obj_buf, size_t obj_buf_sz, const char *name)
+{
+	struct bpf_object *obj;
+
+	obj = bpf__prepare_load_buffer(obj_buf, obj_buf_sz, name);
+	if (IS_ERR(obj)) {
+		pr_debug("Compile BPF program failed.\n");
+		return NULL;
+	}
+	return obj;
+}
+
+static int __test__bpf(int index)
+{
+	int ret;
+	void *obj_buf;
+	size_t obj_buf_sz;
+	struct bpf_object *obj;
+
+	ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
+				       bpf_testcase_table[index].prog_id,
+				       true);
+	if (ret != TEST_OK || !obj_buf || !obj_buf_sz) {
+		pr_debug("Unable to get BPF object, %s\n",
+			 bpf_testcase_table[index].msg_compile_fail);
+		if (index == 0)
+			return TEST_SKIP;
+		else
+			return TEST_FAIL;
+	}
+
+	obj = prepare_bpf(obj_buf, obj_buf_sz,
+			  bpf_testcase_table[index].name);
+	if (!obj) {
+		ret = TEST_FAIL;
+		goto out;
+	}
+
+	ret = do_test(obj,
+		      bpf_testcase_table[index].target_func,
+		      bpf_testcase_table[index].expect_result);
+out:
+	bpf__clear();
+	return ret;
+}
+
+int test__bpf(void)
+{
+	unsigned int i;
+	int err;
+
+	if (geteuid() != 0) {
+		pr_debug("Only root can run BPF test\n");
+		return TEST_SKIP;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(bpf_testcase_table); i++) {
+		err = __test__bpf(i);
+
+		if (err != TEST_OK)
+			return err;
+	}
+
+	return TEST_OK;
+}
+
+#else
+int test__bpf(void)
+{
+	pr_debug("Skip BPF test because BPF support is not compiled\n");
+	return TEST_SKIP;
+}
+#endif
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 66f72d3d6677..80c442eab767 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -166,6 +166,10 @@ static struct test generic_tests[] = {
 		.func = test_session_topology,
 	},
 	{
+		.desc = "Test BPF filter",
+		.func = test__bpf,
+	},
+	{
 		.func = NULL,
 	},
 };
@@ -192,7 +196,7 @@ static bool perf_test__matches(struct test *test, int curr, int argc, const char
 			continue;
 		}
 
-		if (strstr(test->desc, argv[i]))
+		if (strcasestr(test->desc, argv[i]))
 			return true;
 	}
 
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 49b1959dda41..a767a6400c5c 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -613,16 +613,16 @@ int test__code_reading(void)
 	case TEST_CODE_READING_OK:
 		return 0;
 	case TEST_CODE_READING_NO_VMLINUX:
-		fprintf(stderr, " (no vmlinux)");
+		pr_debug("no vmlinux\n");
 		return 0;
 	case TEST_CODE_READING_NO_KCORE:
-		fprintf(stderr, " (no kcore)");
+		pr_debug("no kcore\n");
 		return 0;
 	case TEST_CODE_READING_NO_ACCESS:
-		fprintf(stderr, " (no access)");
+		pr_debug("no access\n");
 		return 0;
 	case TEST_CODE_READING_NO_KERNEL_OBJ:
-		fprintf(stderr, " (no kernel obj)");
+		pr_debug("no kernel obj\n");
 		return 0;
 	default:
 		return -1;
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 4d4b9837b630..a2e2269aa093 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -90,8 +90,8 @@ int test__keep_tracking(void)
 	evsel->attr.enable_on_exec = 0;
 
 	if (perf_evlist__open(evlist) < 0) {
-		fprintf(stderr, " (not supported)");
-		err = 0;
+		pr_debug("Unable to open dummy and cycles event\n");
+		err = TEST_SKIP;
 		goto out_err;
 	}
 
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index 52d55971f66f..bc4cf507cde5 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -2,6 +2,7 @@
 #include <bpf/libbpf.h>
 #include <util/llvm-utils.h>
 #include <util/cache.h>
+#include "llvm.h"
 #include "tests.h"
 #include "debug.h"
 
@@ -11,42 +12,58 @@ static int perf_config_cb(const char *var, const char *val,
 	return perf_default_config(var, val, arg);
 }
 
-/*
- * Randomly give it a "version" section since we don't really load it
- * into kernel
- */
-static const char test_bpf_prog[] =
-	"__attribute__((section(\"do_fork\"), used)) "
-	"int fork(void *ctx) {return 0;} "
-	"char _license[] __attribute__((section(\"license\"), used)) = \"GPL\";"
-	"int _version __attribute__((section(\"version\"), used)) = 0x40100;";
-
 #ifdef HAVE_LIBBPF_SUPPORT
 static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz)
 {
 	struct bpf_object *obj;
 
 	obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, NULL);
-	if (!obj)
-		return -1;
+	if (IS_ERR(obj))
+		return TEST_FAIL;
 	bpf_object__close(obj);
-	return 0;
+	return TEST_OK;
 }
 #else
 static int test__bpf_parsing(void *obj_buf __maybe_unused,
 			     size_t obj_buf_sz __maybe_unused)
 {
-	fprintf(stderr, " (skip bpf parsing)");
-	return 0;
+	pr_debug("Skip bpf parsing\n");
+	return TEST_OK;
 }
 #endif
 
-int test__llvm(void)
+static struct {
+	const char *source;
+	const char *desc;
+} bpf_source_table[__LLVM_TESTCASE_MAX] = {
+	[LLVM_TESTCASE_BASE] = {
+		.source = test_llvm__bpf_base_prog,
+		.desc = "Basic BPF llvm compiling test",
+	},
+	[LLVM_TESTCASE_KBUILD] = {
+		.source = test_llvm__bpf_test_kbuild_prog,
+		.desc = "Test kbuild searching",
+	},
+};
+
+
+int
+test_llvm__fetch_bpf_obj(void **p_obj_buf,
+			 size_t *p_obj_buf_sz,
+			 enum test_llvm__testcase index,
+			 bool force)
 {
-	char *tmpl_new, *clang_opt_new;
-	void *obj_buf;
-	size_t obj_buf_sz;
-	int err, old_verbose;
+	const char *source;
+	const char *desc;
+	const char *tmpl_old, *clang_opt_old;
+	char *tmpl_new = NULL, *clang_opt_new = NULL;
+	int err, old_verbose, ret = TEST_FAIL;
+
+	if (index >= __LLVM_TESTCASE_MAX)
+		return TEST_FAIL;
+
+	source = bpf_source_table[index].source;
+	desc = bpf_source_table[index].desc;
 
 	perf_config(perf_config_cb, NULL);
 
@@ -54,45 +71,100 @@ int test__llvm(void)
 	 * Skip this test if user's .perfconfig doesn't set [llvm] section
 	 * and clang is not found in $PATH, and this is not perf test -v
 	 */
-	if (verbose == 0 && !llvm_param.user_set_param && llvm__search_clang()) {
-		fprintf(stderr, " (no clang, try 'perf test -v LLVM')");
+	if (!force && (verbose == 0 &&
+		       !llvm_param.user_set_param &&
+		       llvm__search_clang())) {
+		pr_debug("No clang and no verbosive, skip this test\n");
 		return TEST_SKIP;
 	}
 
-	old_verbose = verbose;
 	/*
 	 * llvm is verbosity when error. Suppress all error output if
 	 * not 'perf test -v'.
 	 */
+	old_verbose = verbose;
 	if (verbose == 0)
 		verbose = -1;
 
+	*p_obj_buf = NULL;
+	*p_obj_buf_sz = 0;
+
 	if (!llvm_param.clang_bpf_cmd_template)
-		return -1;
+		goto out;
 
 	if (!llvm_param.clang_opt)
 		llvm_param.clang_opt = strdup("");
 
-	err = asprintf(&tmpl_new, "echo '%s' | %s", test_bpf_prog,
-		       llvm_param.clang_bpf_cmd_template);
+	err = asprintf(&tmpl_new, "echo '%s' | %s%s", source,
+		       llvm_param.clang_bpf_cmd_template,
+		       old_verbose ? "" : " 2>/dev/null");
 	if (err < 0)
-		return -1;
+		goto out;
 	err = asprintf(&clang_opt_new, "-xc %s", llvm_param.clang_opt);
 	if (err < 0)
-		return -1;
+		goto out;
 
+	tmpl_old = llvm_param.clang_bpf_cmd_template;
 	llvm_param.clang_bpf_cmd_template = tmpl_new;
+	clang_opt_old = llvm_param.clang_opt;
 	llvm_param.clang_opt = clang_opt_new;
-	err = llvm__compile_bpf("-", &obj_buf, &obj_buf_sz);
+
+	err = llvm__compile_bpf("-", p_obj_buf, p_obj_buf_sz);
+
+	llvm_param.clang_bpf_cmd_template = tmpl_old;
+	llvm_param.clang_opt = clang_opt_old;
 
 	verbose = old_verbose;
-	if (err) {
-		if (!verbose)
-			fprintf(stderr, " (use -v to see error message)");
-		return -1;
-	}
+	if (err)
+		goto out;
+
+	ret = TEST_OK;
+out:
+	free(tmpl_new);
+	free(clang_opt_new);
+	if (ret != TEST_OK)
+		pr_debug("Failed to compile test case: '%s'\n", desc);
+	return ret;
+}
+
+int test__llvm(void)
+{
+	enum test_llvm__testcase i;
+
+	for (i = 0; i < __LLVM_TESTCASE_MAX; i++) {
+		int ret;
+		void *obj_buf = NULL;
+		size_t obj_buf_sz = 0;
+
+		ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
+					       i, false);
 
-	err = test__bpf_parsing(obj_buf, obj_buf_sz);
-	free(obj_buf);
-	return err;
+		if (ret == TEST_OK) {
+			ret = test__bpf_parsing(obj_buf, obj_buf_sz);
+			if (ret != TEST_OK)
+				pr_debug("Failed to parse test case '%s'\n",
+					 bpf_source_table[i].desc);
+		}
+		free(obj_buf);
+
+		switch (ret) {
+		case TEST_SKIP:
+			return TEST_SKIP;
+		case TEST_OK:
+			break;
+		default:
+			/*
+			 * Test 0 is the basic LLVM test. If test 0
+			 * fail, the basic LLVM support not functional
+			 * so the whole test should fail. If other test
+			 * case fail, it can be fixed by adjusting
+			 * config so don't report error.
+			 */
+			if (i == 0)
+				return TEST_FAIL;
+			else
+				return TEST_SKIP;
+		}
+	}
+	return TEST_OK;
 }
diff --git a/tools/perf/tests/llvm.h b/tools/perf/tests/llvm.h
new file mode 100644
index 000000000000..d91d8f44efee
--- /dev/null
+++ b/tools/perf/tests/llvm.h
@@ -0,0 +1,18 @@
+#ifndef PERF_TEST_LLVM_H
+#define PERF_TEST_LLVM_H
+
+#include <stddef.h> /* for size_t */
+#include <stdbool.h> /* for bool */
+
+extern const char test_llvm__bpf_base_prog[];
+extern const char test_llvm__bpf_test_kbuild_prog[];
+
+enum test_llvm__testcase {
+	LLVM_TESTCASE_BASE,
+	LLVM_TESTCASE_KBUILD,
+	__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);
+#endif
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 2cbd0c6901e3..8ea3dffc5065 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -221,6 +221,11 @@ test_O = $(if $(test_$1),$(test_$1),$(test_default_O))
 
 all:
 
+ifdef SHUF
+run := $(shell shuf -e $(run))
+run_O := $(shell shuf -e $(run_O))
+endif
+
 ifdef DEBUG
 d := $(info run   $(run))
 d := $(info run_O $(run_O))
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index e698742d4fec..a02af503100c 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -366,7 +366,7 @@ int test__switch_tracking(void)
 
 	/* Third event */
 	if (!perf_evlist__can_select_event(evlist, sched_switch)) {
-		fprintf(stderr, " (no sched_switch)");
+		pr_debug("No sched_switch\n");
 		err = 0;
 		goto out;
 	}
@@ -442,7 +442,7 @@ int test__switch_tracking(void)
 	}
 
 	if (perf_evlist__open(evlist) < 0) {
-		fprintf(stderr, " (not supported)");
+		pr_debug("Not supported\n");
 		err = 0;
 		goto out;
 	}
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index c80486969f83..3c8734a3abbc 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -66,6 +66,7 @@ int test__fdarray__add(void);
 int test__kmod_path__parse(void);
 int test__thread_map(void);
 int test__llvm(void);
+int test__bpf(void);
 int test_session_topology(void);
 
 #if defined(__arm__) || defined(__aarch64__)
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index e5afb8936040..fa9eb92c9e24 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1430,7 +1430,6 @@ close_file_and_continue:
 
 struct popup_action {
 	struct thread 		*thread;
-	struct dso		*dso;
 	struct map_symbol 	ms;
 	int			socket;
 
@@ -1565,7 +1564,6 @@ add_dso_opt(struct hist_browser *browser, struct popup_action *act,
 		return 0;
 
 	act->ms.map = map;
-	act->dso = map->dso;
 	act->fn = do_zoom_dso;
 	return 1;
 }
@@ -1827,7 +1825,6 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 
 	while (1) {
 		struct thread *thread = NULL;
-		struct dso *dso = NULL;
 		struct map *map = NULL;
 		int choice = 0;
 		int socked_id = -1;
@@ -1839,8 +1836,6 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 		if (browser->he_selection != NULL) {
 			thread = hist_browser__selected_thread(browser);
 			map = browser->selection->map;
-			if (map)
-				dso = map->dso;
 			socked_id = browser->he_selection->socket;
 		}
 		switch (key) {
@@ -1874,7 +1869,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			hist_browser__dump(browser);
 			continue;
 		case 'd':
-			actions->dso = dso;
+			actions->ms.map = map;
 			do_zoom_dso(browser, actions);
 			continue;
 		case 'V':
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 0fc8d7a2fea5..1dd1949b0e79 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1084,6 +1084,7 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
 	struct kcore_extract kce;
 	bool delete_extract = false;
 	int lineno = 0;
+	int nline;
 
 	if (filename)
 		symbol__join_symfs(symfs_filename, filename);
@@ -1179,6 +1180,9 @@ fallback:
 
 		ret = decompress_to_file(m.ext, symfs_filename, fd);
 
+		if (ret)
+			pr_err("Cannot decompress %s %s\n", m.ext, symfs_filename);
+
 		free(m.ext);
 		close(fd);
 
@@ -1204,13 +1208,25 @@ fallback:
 	pr_debug("Executing: %s\n", command);
 
 	file = popen(command, "r");
-	if (!file)
+	if (!file) {
+		pr_err("Failure running %s\n", command);
+		/*
+		 * If we were using debug info should retry with
+		 * original binary.
+		 */
 		goto out_remove_tmp;
+	}
 
-	while (!feof(file))
+	nline = 0;
+	while (!feof(file)) {
 		if (symbol__parse_objdump_line(sym, map, file, privsize,
 			    &lineno) < 0)
 			break;
+		nline++;
+	}
+
+	if (nline == 0)
+		pr_err("No output from %s\n", command);
 
 	/*
 	 * kallsyms does not have symbol sizes so there may a nop at the end.
@@ -1604,6 +1620,7 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map,
 	len = symbol__size(sym);
 
 	if (print_lines) {
+		srcline_full_filename = full_paths;
 		symbol__get_source_line(sym, map, evsel, &source_line, len);
 		print_summary(&source_line, dso->long_name);
 	}
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index ba6f7526b282..4c50411371db 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -26,18 +26,40 @@ static int libbpf_##name(const char *fmt, ...)	\
 	return ret;				\
 }
 
-DEFINE_PRINT_FN(warning, 0)
-DEFINE_PRINT_FN(info, 0)
+DEFINE_PRINT_FN(warning, 1)
+DEFINE_PRINT_FN(info, 1)
 DEFINE_PRINT_FN(debug, 1)
 
 struct bpf_prog_priv {
 	struct perf_probe_event pev;
 };
 
+static bool libbpf_initialized;
+
+struct bpf_object *
+bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name)
+{
+	struct bpf_object *obj;
+
+	if (!libbpf_initialized) {
+		libbpf_set_print(libbpf_warning,
+				 libbpf_info,
+				 libbpf_debug);
+		libbpf_initialized = true;
+	}
+
+	obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, name);
+	if (IS_ERR(obj)) {
+		pr_debug("bpf: failed to load buffer\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	return obj;
+}
+
 struct bpf_object *bpf__prepare_load(const char *filename, bool source)
 {
 	struct bpf_object *obj;
-	static bool libbpf_initialized;
 
 	if (!libbpf_initialized) {
 		libbpf_set_print(libbpf_warning,
@@ -53,15 +75,15 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source)
 
 		err = llvm__compile_bpf(filename, &obj_buf, &obj_buf_sz);
 		if (err)
-			return ERR_PTR(err);
+			return ERR_PTR(-BPF_LOADER_ERRNO__COMPILE);
 		obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, filename);
 		free(obj_buf);
 	} else
 		obj = bpf_object__open(filename);
 
-	if (!obj) {
+	if (IS_ERR(obj)) {
 		pr_debug("bpf: failed to load %s\n", filename);
-		return ERR_PTR(-EINVAL);
+		return obj;
 	}
 
 	return obj;
@@ -96,9 +118,9 @@ config_bpf_program(struct bpf_program *prog)
 	int err;
 
 	config_str = bpf_program__title(prog, false);
-	if (!config_str) {
+	if (IS_ERR(config_str)) {
 		pr_debug("bpf: unable to get title for program\n");
-		return -EINVAL;
+		return PTR_ERR(config_str);
 	}
 
 	priv = calloc(sizeof(*priv), 1);
@@ -113,14 +135,14 @@ config_bpf_program(struct bpf_program *prog)
 	if (err < 0) {
 		pr_debug("bpf: '%s' is not a valid config string\n",
 			 config_str);
-		err = -EINVAL;
+		err = -BPF_LOADER_ERRNO__CONFIG;
 		goto errout;
 	}
 
 	if (pev->group && strcmp(pev->group, PERF_BPF_PROBE_GROUP)) {
 		pr_debug("bpf: '%s': group for event is set and not '%s'.\n",
 			 config_str, PERF_BPF_PROBE_GROUP);
-		err = -EINVAL;
+		err = -BPF_LOADER_ERRNO__GROUP;
 		goto errout;
 	} else if (!pev->group)
 		pev->group = strdup(PERF_BPF_PROBE_GROUP);
@@ -132,9 +154,9 @@ config_bpf_program(struct bpf_program *prog)
 	}
 
 	if (!pev->event) {
-		pr_debug("bpf: '%s': event name is missing\n",
+		pr_debug("bpf: '%s': event name is missing. Section name should be 'key=value'\n",
 			 config_str);
-		err = -EINVAL;
+		err = -BPF_LOADER_ERRNO__EVENTNAME;
 		goto errout;
 	}
 	pr_debug("bpf: config '%s' is ok\n", config_str);
@@ -285,7 +307,7 @@ int bpf__foreach_tev(struct bpf_object *obj,
 				(void **)&priv);
 		if (err || !priv) {
 			pr_debug("bpf: failed to get private field\n");
-			return -EINVAL;
+			return -BPF_LOADER_ERRNO__INTERNAL;
 		}
 
 		pev = &priv->pev;
@@ -308,13 +330,57 @@ int bpf__foreach_tev(struct bpf_object *obj,
 	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)
+
+static const char *bpf_loader_strerror_table[NR_ERRNO] = {
+	[ERRCODE_OFFSET(CONFIG)]	= "Invalid config string",
+	[ERRCODE_OFFSET(GROUP)]		= "Invalid group name",
+	[ERRCODE_OFFSET(EVENTNAME)]	= "No event name found in config string",
+	[ERRCODE_OFFSET(INTERNAL)]	= "BPF loader internal error",
+	[ERRCODE_OFFSET(COMPILE)]	= "Error when compiling BPF scriptlet",
+};
+
+static int
+bpf_loader_strerror(int err, char *buf, size_t size)
+{
+	char sbuf[STRERR_BUFSIZE];
+	const char *msg;
+
+	if (!buf || !size)
+		return -1;
+
+	err = err > 0 ? err : -err;
+
+	if (err >= __LIBBPF_ERRNO__START)
+		return libbpf_strerror(err, buf, size);
+
+	if (err >= __BPF_LOADER_ERRNO__START && err < __BPF_LOADER_ERRNO__END) {
+		msg = bpf_loader_strerror_table[ERRNO_OFFSET(err)];
+		snprintf(buf, size, "%s", msg);
+		buf[size - 1] = '\0';
+		return 0;
+	}
+
+	if (err >= __BPF_LOADER_ERRNO__END)
+		snprintf(buf, size, "Unknown bpf loader error %d", err);
+	else
+		snprintf(buf, size, "%s",
+			 strerror_r(err, sbuf, sizeof(sbuf)));
+
+	buf[size - 1] = '\0';
+	return -1;
+}
+
 #define bpf__strerror_head(err, buf, size) \
 	char sbuf[STRERR_BUFSIZE], *emsg;\
 	if (!size)\
 		return 0;\
 	if (err < 0)\
 		err = -err;\
-	emsg = strerror_r(err, sbuf, sizeof(sbuf));\
+	bpf_loader_strerror(err, sbuf, sizeof(sbuf));\
+	emsg = sbuf;\
 	switch (err) {\
 	default:\
 		scnprintf(buf, size, "%s", emsg);\
@@ -330,23 +396,62 @@ int bpf__foreach_tev(struct bpf_object *obj,
 	}\
 	buf[size - 1] = '\0';
 
+int bpf__strerror_prepare_load(const char *filename, bool source,
+			       int err, char *buf, size_t size)
+{
+	size_t n;
+	int ret;
+
+	n = snprintf(buf, size, "Failed to load %s%s: ",
+			 filename, source ? " from source" : "");
+	if (n >= size) {
+		buf[size - 1] = '\0';
+		return 0;
+	}
+	buf += n;
+	size -= n;
+
+	ret = bpf_loader_strerror(err, buf, size);
+	buf[size - 1] = '\0';
+	return ret;
+}
+
 int bpf__strerror_probe(struct bpf_object *obj __maybe_unused,
 			int err, char *buf, size_t size)
 {
 	bpf__strerror_head(err, buf, size);
 	bpf__strerror_entry(EEXIST, "Probe point exist. Try use 'perf probe -d \"*\"'");
-	bpf__strerror_entry(EPERM, "You need to be root, and /proc/sys/kernel/kptr_restrict should be 0\n");
-	bpf__strerror_entry(ENOENT, "You need to check probing points in BPF file\n");
+	bpf__strerror_entry(EACCES, "You need to be root");
+	bpf__strerror_entry(EPERM, "You need to be root, and /proc/sys/kernel/kptr_restrict should be 0");
+	bpf__strerror_entry(ENOENT, "You need to check probing points in BPF file");
 	bpf__strerror_end(buf, size);
 	return 0;
 }
 
-int bpf__strerror_load(struct bpf_object *obj __maybe_unused,
+int bpf__strerror_load(struct bpf_object *obj,
 		       int err, char *buf, size_t size)
 {
 	bpf__strerror_head(err, buf, size);
-	bpf__strerror_entry(EINVAL, "%s: Are you root and runing a CONFIG_BPF_SYSCALL kernel?",
-			    emsg)
+	case LIBBPF_ERRNO__KVER: {
+		unsigned int obj_kver = bpf_object__get_kversion(obj);
+		unsigned int real_kver;
+
+		if (fetch_kernel_version(&real_kver, NULL, 0)) {
+			scnprintf(buf, size, "Unable to fetch kernel version");
+			break;
+		}
+
+		if (obj_kver != real_kver) {
+			scnprintf(buf, size,
+				  "'version' ("KVER_FMT") doesn't match running kernel ("KVER_FMT")",
+				  KVER_PARAM(obj_kver),
+				  KVER_PARAM(real_kver));
+			break;
+		}
+
+		scnprintf(buf, size, "Failed to load program for unknown reason");
+		break;
+	}
 	bpf__strerror_end(buf, size);
 	return 0;
 }
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index ccd8d7fd79d3..9caf3ae4acf3 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -8,9 +8,21 @@
 #include <linux/compiler.h>
 #include <linux/err.h>
 #include <string.h>
+#include <bpf/libbpf.h>
 #include "probe-event.h"
 #include "debug.h"
 
+enum bpf_loader_errno {
+	__BPF_LOADER_ERRNO__START = __LIBBPF_ERRNO__START - 100,
+	/* Invalid config string */
+	BPF_LOADER_ERRNO__CONFIG = __BPF_LOADER_ERRNO__START,
+	BPF_LOADER_ERRNO__GROUP,	/* Invalid group name */
+	BPF_LOADER_ERRNO__EVENTNAME,	/* Event name is missing */
+	BPF_LOADER_ERRNO__INTERNAL,	/* BPF loader internal error */
+	BPF_LOADER_ERRNO__COMPILE,	/* Error when compiling BPF scriptlet */
+	__BPF_LOADER_ERRNO__END,
+};
+
 struct bpf_object;
 #define PERF_BPF_PROBE_GROUP "perf_bpf_probe"
 
@@ -19,6 +31,11 @@ typedef int (*bpf_prog_iter_callback_t)(struct probe_trace_event *tev,
 
 #ifdef HAVE_LIBBPF_SUPPORT
 struct bpf_object *bpf__prepare_load(const char *filename, bool source);
+int bpf__strerror_prepare_load(const char *filename, bool source,
+			       int err, char *buf, size_t size);
+
+struct bpf_object *bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz,
+					    const char *name);
 
 void bpf__clear(void);
 
@@ -41,6 +58,13 @@ bpf__prepare_load(const char *filename __maybe_unused,
 	return ERR_PTR(-ENOTSUP);
 }
 
+static inline struct bpf_object *
+bpf__prepare_load_buffer(void *obj_buf __maybe_unused,
+					   size_t obj_buf_sz __maybe_unused)
+{
+	return ERR_PTR(-ENOTSUP);
+}
+
 static inline void bpf__clear(void) { }
 
 static inline int bpf__probe(struct bpf_object *obj __maybe_unused) { return 0;}
@@ -67,6 +91,15 @@ __bpf_strerror(char *buf, size_t size)
 	return 0;
 }
 
+static inline
+int bpf__strerror_prepare_load(const char *filename __maybe_unused,
+			       bool source __maybe_unused,
+			       int err __maybe_unused,
+			       char *buf, size_t size)
+{
+	return __bpf_strerror(buf, size);
+}
+
 static inline int
 bpf__strerror_probe(struct bpf_object *obj __maybe_unused,
 		    int err __maybe_unused,
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index d909459fb54c..217b5a60e2ab 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -76,6 +76,7 @@ struct perf_tool build_id__mark_dso_hit_ops = {
 	.exit	= perf_event__exit_del_thread,
 	.attr		 = perf_event__process_attr,
 	.build_id	 = perf_event__process_build_id,
+	.ordered_events	 = true,
 };
 
 int build_id__sprintf(const u8 *build_id, int len, char *bf)
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 7c0c08386a1d..425df5c86c9c 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -933,6 +933,7 @@ static struct dso *__dso__findlink_by_longname(struct rb_root *root,
 		/* Add new node and rebalance tree */
 		rb_link_node(&dso->rb_node, parent, p);
 		rb_insert_color(&dso->rb_node, root);
+		dso->root = root;
 	}
 	return NULL;
 }
@@ -945,15 +946,30 @@ static inline struct dso *__dso__find_by_longname(struct rb_root *root,
 
 void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
 {
+	struct rb_root *root = dso->root;
+
 	if (name == NULL)
 		return;
 
 	if (dso->long_name_allocated)
 		free((char *)dso->long_name);
 
+	if (root) {
+		rb_erase(&dso->rb_node, root);
+		/*
+		 * __dso__findlink_by_longname() isn't guaranteed to add it
+		 * back, so a clean removal is required here.
+		 */
+		RB_CLEAR_NODE(&dso->rb_node);
+		dso->root = NULL;
+	}
+
 	dso->long_name		 = name;
 	dso->long_name_len	 = strlen(name);
 	dso->long_name_allocated = name_allocated;
+
+	if (root)
+		__dso__findlink_by_longname(root, dso, NULL);
 }
 
 void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated)
@@ -1046,6 +1062,7 @@ struct dso *dso__new(const char *name)
 		dso->kernel = DSO_TYPE_USER;
 		dso->needs_swap = DSO_SWAP__UNSET;
 		RB_CLEAR_NODE(&dso->rb_node);
+		dso->root = NULL;
 		INIT_LIST_HEAD(&dso->node);
 		INIT_LIST_HEAD(&dso->data.open_entry);
 		pthread_mutex_init(&dso->lock, NULL);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index fc8db9c764ac..45ec4d0a50ed 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -135,6 +135,7 @@ struct dso {
 	pthread_mutex_t	 lock;
 	struct list_head node;
 	struct rb_node	 rb_node;	/* rbtree node sorted by long name */
+	struct rb_root	 *root;		/* root of rbtree that rb_node is in */
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
 	struct {
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 4f6a4780bd5f..00724d496d38 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -4,17 +4,18 @@
  */
 
 #include <stdio.h>
-#include <sys/utsname.h>
 #include "util.h"
 #include "debug.h"
 #include "llvm-utils.h"
 #include "cache.h"
 
 #define CLANG_BPF_CMD_DEFAULT_TEMPLATE				\
-		"$CLANG_EXEC -D__KERNEL__ $CLANG_OPTIONS "	\
-		"$KERNEL_INC_OPTIONS -Wno-unused-value "	\
-		"-Wno-pointer-sign -working-directory "		\
-		"$WORKING_DIR -c \"$CLANG_SOURCE\" -target bpf -O2 -o -"
+		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
+		"-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE "	\
+		"$CLANG_OPTIONS $KERNEL_INC_OPTIONS "		\
+		"-Wno-unused-value -Wno-pointer-sign "		\
+		"-working-directory $WORKING_DIR "		\
+		"-c \"$CLANG_SOURCE\" -target bpf -O2 -o -"
 
 struct llvm_param llvm_param = {
 	.clang_path = "clang",
@@ -214,18 +215,19 @@ static int detect_kbuild_dir(char **kbuild_dir)
 	const char *suffix_dir = "";
 
 	char *autoconf_path;
-	struct utsname utsname;
 
 	int err;
 
 	if (!test_dir) {
-		err = uname(&utsname);
-		if (err) {
-			pr_warning("uname failed: %s\n", strerror(errno));
+		/* _UTSNAME_LENGTH is 65 */
+		char release[128];
+
+		err = fetch_kernel_version(NULL, release,
+					   sizeof(release));
+		if (err)
 			return -EINVAL;
-		}
 
-		test_dir = utsname.release;
+		test_dir = release;
 		prefix_dir = "/lib/modules/";
 		suffix_dir = "/build";
 	}
@@ -326,13 +328,15 @@ get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts)
 int llvm__compile_bpf(const char *path, void **p_obj_buf,
 		      size_t *p_obj_buf_sz)
 {
-	int err;
-	char clang_path[PATH_MAX];
+	size_t obj_buf_sz;
+	void *obj_buf = NULL;
+	int err, nr_cpus_avail;
+	unsigned int kernel_version;
+	char linux_version_code_str[64];
 	const char *clang_opt = llvm_param.clang_opt;
-	const char *template = llvm_param.clang_bpf_cmd_template;
+	char clang_path[PATH_MAX], nr_cpus_avail_str[64];
 	char *kbuild_dir = NULL, *kbuild_include_opts = NULL;
-	void *obj_buf = NULL;
-	size_t obj_buf_sz;
+	const char *template = llvm_param.clang_bpf_cmd_template;
 
 	if (!template)
 		template = CLANG_BPF_CMD_DEFAULT_TEMPLATE;
@@ -354,6 +358,24 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	 */
 	get_kbuild_opts(&kbuild_dir, &kbuild_include_opts);
 
+	nr_cpus_avail = sysconf(_SC_NPROCESSORS_CONF);
+	if (nr_cpus_avail <= 0) {
+		pr_err(
+"WARNING:\tunable to get available CPUs in this system: %s\n"
+"        \tUse 128 instead.\n", strerror(errno));
+		nr_cpus_avail = 128;
+	}
+	snprintf(nr_cpus_avail_str, sizeof(nr_cpus_avail_str), "%d",
+		 nr_cpus_avail);
+
+	if (fetch_kernel_version(&kernel_version, NULL, 0))
+		kernel_version = 0;
+
+	snprintf(linux_version_code_str, sizeof(linux_version_code_str),
+		 "0x%x", kernel_version);
+
+	force_set_env("NR_CPUS", nr_cpus_avail_str);
+	force_set_env("LINUX_VERSION_CODE", linux_version_code_str);
 	force_set_env("CLANG_EXEC", clang_path);
 	force_set_env("CLANG_OPTIONS", clang_opt);
 	force_set_env("KERNEL_INC_OPTIONS", kbuild_include_opts);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 5ef90be2a249..8b303ff20289 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -91,6 +91,7 @@ static void dsos__purge(struct dsos *dsos)
 
 	list_for_each_entry_safe(pos, n, &dsos->head, node) {
 		RB_CLEAR_NODE(&pos->rb_node);
+		pos->root = NULL;
 		list_del_init(&pos->node);
 		dso__put(pos);
 	}
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 4e38c396a897..afc6b56cf749 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -644,6 +644,12 @@ size_t map_groups__fprintf(struct map_groups *mg, FILE *fp)
 	return printed;
 }
 
+static void __map_groups__insert(struct map_groups *mg, struct map *map)
+{
+	__maps__insert(&mg->maps[map->type], map);
+	map->groups = mg;
+}
+
 static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
 {
 	struct rb_root *root;
@@ -682,7 +688,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
 			}
 
 			before->end = map->start;
-			__maps__insert(maps, before);
+			__map_groups__insert(pos->groups, before);
 			if (verbose >= 2)
 				map__fprintf(before, fp);
 		}
@@ -696,7 +702,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
 			}
 
 			after->start = map->end;
-			__maps__insert(maps, after);
+			__map_groups__insert(pos->groups, after);
 			if (verbose >= 2)
 				map__fprintf(after, fp);
 		}
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index bee60583839a..e48d9da75707 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -632,19 +632,20 @@ int parse_events_load_bpf(struct parse_events_evlist *data,
 	struct bpf_object *obj;
 
 	obj = bpf__prepare_load(bpf_file_name, source);
-	if (IS_ERR(obj) || !obj) {
+	if (IS_ERR(obj)) {
 		char errbuf[BUFSIZ];
 		int err;
 
-		err = obj ? PTR_ERR(obj) : -EINVAL;
+		err = PTR_ERR(obj);
 
 		if (err == -ENOTSUP)
 			snprintf(errbuf, sizeof(errbuf),
 				 "BPF support is not compiled");
 		else
-			snprintf(errbuf, sizeof(errbuf),
-				 "BPF object file '%s' is invalid",
-				 bpf_file_name);
+			bpf__strerror_prepare_load(bpf_file_name,
+						   source,
+						   -err, errbuf,
+						   sizeof(errbuf));
 
 		data->error->help = strdup("(add -v to see detail)");
 		data->error->str = strdup(errbuf);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index b51a8bfb40f9..03875f9154e7 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1895,9 +1895,8 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
 		sym = map__find_symbol(map, addr, NULL);
 	} else {
 		if (tp->symbol && !addr) {
-			ret = kernel_get_symbol_address_by_name(tp->symbol,
-							&addr, true, false);
-			if (ret < 0)
+			if (kernel_get_symbol_address_by_name(tp->symbol,
+						&addr, true, false) < 0)
 				goto out;
 		}
 		if (addr) {
@@ -1905,6 +1904,7 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
 			sym = __find_kernel_function(addr, &map);
 		}
 	}
+
 	if (!sym)
 		goto out;
 
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 89dbeb92c68e..e3b3b92e4458 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -138,6 +138,9 @@ struct strlist *probe_file__get_rawlist(int fd)
 	char *p;
 	struct strlist *sl;
 
+	if (fd < 0)
+		return NULL;
+
 	sl = strlist__new(NULL, NULL);
 
 	fp = fdopen(dup(fd), "r");
@@ -271,6 +274,9 @@ int probe_file__get_events(int fd, struct strfilter *filter,
 	const char *p;
 	int ret = -ENOENT;
 
+	if (!plist)
+		return -EINVAL;
+
 	namelist = __probe_file__get_namelist(fd, true);
 	if (!namelist)
 		return -ENOENT;
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index bd8f03de5e40..05012bb178d7 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1183,7 +1183,7 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf)
 			container_of(pf, struct trace_event_finder, pf);
 	struct perf_probe_point *pp = &pf->pev->point;
 	struct probe_trace_event *tev;
-	struct perf_probe_arg *args;
+	struct perf_probe_arg *args = NULL;
 	int ret, i;
 
 	/* Check number of tevs */
@@ -1198,19 +1198,23 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf)
 	ret = convert_to_trace_point(&pf->sp_die, tf->mod, pf->addr,
 				     pp->retprobe, pp->function, &tev->point);
 	if (ret < 0)
-		return ret;
+		goto end;
 
 	tev->point.realname = strdup(dwarf_diename(sc_die));
-	if (!tev->point.realname)
-		return -ENOMEM;
+	if (!tev->point.realname) {
+		ret = -ENOMEM;
+		goto end;
+	}
 
 	pr_debug("Probe point found: %s+%lu\n", tev->point.symbol,
 		 tev->point.offset);
 
 	/* Expand special probe argument if exist */
 	args = zalloc(sizeof(struct perf_probe_arg) * MAX_PROBE_ARGS);
-	if (args == NULL)
-		return -ENOMEM;
+	if (args == NULL) {
+		ret = -ENOMEM;
+		goto end;
+	}
 
 	ret = expand_probe_args(sc_die, pf, args);
 	if (ret < 0)
@@ -1234,6 +1238,10 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf)
 	}
 
 end:
+	if (ret) {
+		clear_probe_trace_event(tev);
+		tf->ntevs--;
+	}
 	free(args);
 	return ret;
 }
@@ -1246,7 +1254,7 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 	struct trace_event_finder tf = {
 			.pf = {.pev = pev, .callback = add_probe_trace_event},
 			.max_tevs = probe_conf.max_probes, .mod = dbg->mod};
-	int ret;
+	int ret, i;
 
 	/* Allocate result tevs array */
 	*tevs = zalloc(sizeof(struct probe_trace_event) * tf.max_tevs);
@@ -1258,6 +1266,8 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 
 	ret = debuginfo__find_probes(dbg, &tf.pf);
 	if (ret < 0) {
+		for (i = 0; i < tf.ntevs; i++)
+			clear_probe_trace_event(&tf.tevs[i]);
 		zfree(tevs);
 		return ret;
 	}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 428149bc64d2..c35ffdd360fe 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -29,7 +29,7 @@ static int perf_session__open(struct perf_session *session)
 	struct perf_data_file *file = session->file;
 
 	if (perf_session__read_header(session) < 0) {
-		pr_err("incompatible file format (rerun with -v to learn more)");
+		pr_err("incompatible file format (rerun with -v to learn more)\n");
 		return -1;
 	}
 
@@ -37,17 +37,17 @@ static int perf_session__open(struct perf_session *session)
 		return 0;
 
 	if (!perf_evlist__valid_sample_type(session->evlist)) {
-		pr_err("non matching sample_type");
+		pr_err("non matching sample_type\n");
 		return -1;
 	}
 
 	if (!perf_evlist__valid_sample_id_all(session->evlist)) {
-		pr_err("non matching sample_id_all");
+		pr_err("non matching sample_id_all\n");
 		return -1;
 	}
 
 	if (!perf_evlist__valid_read_format(session->evlist)) {
-		pr_err("non matching read_format");
+		pr_err("non matching read_format\n");
 		return -1;
 	}
 
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 2a5d8d7698ae..6ac03146889d 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -413,6 +413,11 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 			ratio = total / avg;
 
 		fprintf(out, " # %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);
+		else
+			fprintf(out, "                                   ");
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index b4cc7662677e..cd08027a6d2c 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -654,19 +654,24 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map,
 	struct map_groups *kmaps = map__kmaps(map);
 	struct map *curr_map;
 	struct symbol *pos;
-	int count = 0, moved = 0;
+	int count = 0;
+	struct rb_root old_root = dso->symbols[map->type];
 	struct rb_root *root = &dso->symbols[map->type];
 	struct rb_node *next = rb_first(root);
 
 	if (!kmaps)
 		return -1;
 
+	*root = RB_ROOT;
+
 	while (next) {
 		char *module;
 
 		pos = rb_entry(next, struct symbol, rb_node);
 		next = rb_next(&pos->rb_node);
 
+		rb_erase_init(&pos->rb_node, &old_root);
+
 		module = strchr(pos->name, '\t');
 		if (module)
 			*module = '\0';
@@ -674,28 +679,21 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map,
 		curr_map = map_groups__find(kmaps, map->type, pos->start);
 
 		if (!curr_map || (filter && filter(curr_map, pos))) {
-			rb_erase_init(&pos->rb_node, root);
 			symbol__delete(pos);
-		} else {
-			pos->start -= curr_map->start - curr_map->pgoff;
-			if (pos->end)
-				pos->end -= curr_map->start - curr_map->pgoff;
-			if (curr_map->dso != map->dso) {
-				rb_erase_init(&pos->rb_node, root);
-				symbols__insert(
-					&curr_map->dso->symbols[curr_map->type],
-					pos);
-				++moved;
-			} else {
-				++count;
-			}
+			continue;
 		}
+
+		pos->start -= curr_map->start - curr_map->pgoff;
+		if (pos->end)
+			pos->end -= curr_map->start - curr_map->pgoff;
+		symbols__insert(&curr_map->dso->symbols[curr_map->type], pos);
+		++count;
 	}
 
 	/* Symbols have been adjusted */
 	dso->adjust_symbols = 1;
 
-	return count + moved;
+	return count;
 }
 
 /*
@@ -1438,9 +1436,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 		if (lstat(dso->name, &st) < 0)
 			goto out;
 
-		if (st.st_uid && (st.st_uid != geteuid())) {
+		if (!symbol_conf.force && st.st_uid && (st.st_uid != geteuid())) {
 			pr_warning("File %s not owned by current user or root, "
-				"ignoring it.\n", dso->name);
+				   "ignoring it (use -f to override).\n", dso->name);
 			goto out;
 		}
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 40073c60b83d..dcd786e364f2 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -84,6 +84,7 @@ struct symbol_conf {
 	unsigned short	priv_size;
 	unsigned short	nr_events;
 	bool		try_vmlinux_path,
+			force,
 			ignore_vmlinux,
 			ignore_vmlinux_buildid,
 			show_kernel_path,
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index cd12c25e4ea4..47b1e36c7ea0 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -3,6 +3,7 @@
 #include "debug.h"
 #include <api/fs/fs.h>
 #include <sys/mman.h>
+#include <sys/utsname.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
 #include <execinfo.h>
 #endif
@@ -665,3 +666,32 @@ bool find_process(const char *name)
 	closedir(dir);
 	return ret ? false : true;
 }
+
+int
+fetch_kernel_version(unsigned int *puint, char *str,
+		     size_t str_size)
+{
+	struct utsname utsname;
+	int version, patchlevel, sublevel, err;
+
+	if (uname(&utsname))
+		return -1;
+
+	if (str && str_size) {
+		strncpy(str, utsname.release, str_size);
+		str[str_size - 1] = '\0';
+	}
+
+	err = sscanf(utsname.release, "%d.%d.%d",
+		     &version, &patchlevel, &sublevel);
+
+	if (err != 3) {
+		pr_debug("Unablt to get kernel version from uname '%s'\n",
+			 utsname.release);
+		return -1;
+	}
+
+	if (puint)
+		*puint = (version << 16) + (patchlevel << 8) + sublevel;
+	return 0;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 4cfb913aa9e0..dcc659017976 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -350,4 +350,12 @@ static inline char *asprintf_expr_not_in_ints(const char *var, size_t nints, int
 
 int get_stack_size(const char *str, unsigned long *_size);
 
+int fetch_kernel_version(unsigned int *puint,
+			 char *str, size_t str_sz);
+#define KVER_VERSION(x)		(((x) >> 16) & 0xff)
+#define KVER_PATCHLEVEL(x)	(((x) >> 8) & 0xff)
+#define KVER_SUBLEVEL(x)	((x) & 0xff)
+#define KVER_FMT	"%d.%d.%d"
+#define KVER_PARAM(x)	KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x)
+
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/power/acpi/tools/acpidump/apfiles.c b/tools/power/acpi/tools/acpidump/apfiles.c
index a37f9702b2a9..a1c62de42a3b 100644
--- a/tools/power/acpi/tools/acpidump/apfiles.c
+++ b/tools/power/acpi/tools/acpidump/apfiles.c
@@ -150,7 +150,7 @@ int ap_write_to_binary_file(struct acpi_table_header *table, u32 instance)
 		strcat(filename, instance_str);
 	}
 
-	strcat(filename, ACPI_TABLE_FILE_SUFFIX);
+	strcat(filename, FILE_SUFFIX_BINARY_TABLE);
 
 	if (gbl_verbose_mode) {
 		acpi_log_error
diff --git a/tools/power/cpupower/debug/i386/dump_psb.c b/tools/power/cpupower/debug/i386/dump_psb.c
index 8d6a47514253..2c768cf70128 100644
--- a/tools/power/cpupower/debug/i386/dump_psb.c
+++ b/tools/power/cpupower/debug/i386/dump_psb.c
@@ -134,7 +134,7 @@ next_one:
 }
 
 static struct option info_opts[] = {
-	{.name = "numpst",	.has_arg=no_argument,	.flag=NULL, .val='n'},
+     {"numpst", no_argument, NULL, 'n'},
 };
 
 void print_help(void)
diff --git a/tools/power/cpupower/man/cpupower-idle-set.1 b/tools/power/cpupower/man/cpupower-idle-set.1
index 3e6799d7a79f..580c4e3ea92a 100644
--- a/tools/power/cpupower/man/cpupower-idle-set.1
+++ b/tools/power/cpupower/man/cpupower-idle-set.1
@@ -20,7 +20,9 @@ Disable a specific processor sleep state.
 Enable a specific processor sleep state.
 .TP
 \fB\-D\fR \fB\-\-disable-by-latency\fR <LATENCY>
-Disable all idle states with a equal or higher latency than <LATENCY>
+Disable all idle states with a equal or higher latency than <LATENCY>.
+
+Enable all idle states with a latency lower than <LATENCY>.
 .TP
 \fB\-E\fR \fB\-\-enable-all\fR
 Enable all idle states if not enabled already.
diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c
index b4b90a97662c..0e6764330241 100644
--- a/tools/power/cpupower/utils/cpufreq-info.c
+++ b/tools/power/cpupower/utils/cpufreq-info.c
@@ -536,21 +536,21 @@ static int get_latency(unsigned int cpu, unsigned int human)
 }
 
 static struct option info_opts[] = {
-	{ .name = "debug",	.has_arg = no_argument,		.flag = NULL,	.val = 'e'},
-	{ .name = "boost",	.has_arg = no_argument,		.flag = NULL,	.val = 'b'},
-	{ .name = "freq",	.has_arg = no_argument,		.flag = NULL,	.val = 'f'},
-	{ .name = "hwfreq",	.has_arg = no_argument,		.flag = NULL,	.val = 'w'},
-	{ .name = "hwlimits",	.has_arg = no_argument,		.flag = NULL,	.val = 'l'},
-	{ .name = "driver",	.has_arg = no_argument,		.flag = NULL,	.val = 'd'},
-	{ .name = "policy",	.has_arg = no_argument,		.flag = NULL,	.val = 'p'},
-	{ .name = "governors",	.has_arg = no_argument,		.flag = NULL,	.val = 'g'},
-	{ .name = "related-cpus", .has_arg = no_argument,	.flag = NULL,	.val = 'r'},
-	{ .name = "affected-cpus",.has_arg = no_argument,	.flag = NULL,	.val = 'a'},
-	{ .name = "stats",	.has_arg = no_argument,		.flag = NULL,	.val = 's'},
-	{ .name = "latency",	.has_arg = no_argument,		.flag = NULL,	.val = 'y'},
-	{ .name = "proc",	.has_arg = no_argument,		.flag = NULL,	.val = 'o'},
-	{ .name = "human",	.has_arg = no_argument,		.flag = NULL,	.val = 'm'},
-	{ .name = "no-rounding", .has_arg = no_argument,	.flag = NULL,	.val = 'n'},
+	{"debug",	 no_argument,		 NULL,	 'e'},
+	{"boost",	 no_argument,		 NULL,	 'b'},
+	{"freq",	 no_argument,		 NULL,	 'f'},
+	{"hwfreq",	 no_argument,		 NULL,	 'w'},
+	{"hwlimits",	 no_argument,		 NULL,	 'l'},
+	{"driver",	 no_argument,		 NULL,	 'd'},
+	{"policy",	 no_argument,		 NULL,	 'p'},
+	{"governors",	 no_argument,		 NULL,	 'g'},
+	{"related-cpus",  no_argument,	 NULL,	 'r'},
+	{"affected-cpus", no_argument,	 NULL,	 'a'},
+	{"stats",	 no_argument,		 NULL,	 's'},
+	{"latency",	 no_argument,		 NULL,	 'y'},
+	{"proc",	 no_argument,		 NULL,	 'o'},
+	{"human",	 no_argument,		 NULL,	 'm'},
+	{"no-rounding", no_argument,	 NULL,	 'n'},
 	{ },
 };
 
diff --git a/tools/power/cpupower/utils/cpufreq-set.c b/tools/power/cpupower/utils/cpufreq-set.c
index 4e213576381e..0fbd1a22c0a9 100644
--- a/tools/power/cpupower/utils/cpufreq-set.c
+++ b/tools/power/cpupower/utils/cpufreq-set.c
@@ -22,11 +22,11 @@
 #define NORM_FREQ_LEN 32
 
 static struct option set_opts[] = {
-	{ .name = "min",	.has_arg = required_argument,	.flag = NULL,	.val = 'd'},
-	{ .name = "max",	.has_arg = required_argument,	.flag = NULL,	.val = 'u'},
-	{ .name = "governor",	.has_arg = required_argument,	.flag = NULL,	.val = 'g'},
-	{ .name = "freq",	.has_arg = required_argument,	.flag = NULL,	.val = 'f'},
-	{ .name = "related",	.has_arg = no_argument,		.flag = NULL,	.val='r'},
+	{"min",		required_argument,	NULL, 'd'},
+	{"max",		required_argument,	NULL, 'u'},
+	{"governor",	required_argument,	NULL, 'g'},
+	{"freq",	required_argument,	NULL, 'f'},
+	{"related",	no_argument,		NULL, 'r'},
 	{ },
 };
 
diff --git a/tools/power/cpupower/utils/cpuidle-info.c b/tools/power/cpupower/utils/cpuidle-info.c
index 75e66de7e7a7..750c1d82c3f7 100644
--- a/tools/power/cpupower/utils/cpuidle-info.c
+++ b/tools/power/cpupower/utils/cpuidle-info.c
@@ -126,8 +126,8 @@ static void proc_cpuidle_cpu_output(unsigned int cpu)
 }
 
 static struct option info_opts[] = {
-	{ .name = "silent",	.has_arg = no_argument,	.flag = NULL,	.val = 's'},
-	{ .name = "proc",	.has_arg = no_argument,	.flag = NULL,	.val = 'o'},
+	{"silent", no_argument, NULL, 's'},
+	{"proc", no_argument, NULL, 'o'},
 	{ },
 };
 
diff --git a/tools/power/cpupower/utils/cpuidle-set.c b/tools/power/cpupower/utils/cpuidle-set.c
index d45d8d775c02..d6b6ae44b8c2 100644
--- a/tools/power/cpupower/utils/cpuidle-set.c
+++ b/tools/power/cpupower/utils/cpuidle-set.c
@@ -13,15 +13,11 @@
 #include "helpers/sysfs.h"
 
 static struct option info_opts[] = {
-	{ .name = "disable",
-	  .has_arg = required_argument,	.flag = NULL,	.val = 'd'},
-	{ .name = "enable",
-	  .has_arg = required_argument,	.flag = NULL,	.val = 'e'},
-	{ .name = "disable-by-latency",
-	  .has_arg = required_argument,	.flag = NULL,	.val = 'D'},
-	{ .name = "enable-all",
-	  .has_arg = no_argument,	.flag = NULL,	.val = 'E'},
-	{ },
+     {"disable",	required_argument,		NULL, 'd'},
+     {"enable",		required_argument,		NULL, 'e'},
+     {"disable-by-latency", required_argument,		NULL, 'D'},
+     {"enable-all",	no_argument,			NULL, 'E'},
+     { },
 };
 
 
@@ -148,14 +144,21 @@ int cmd_idle_set(int argc, char **argv)
 					(cpu, idlestate);
 				state_latency = sysfs_get_idlestate_latency
 					(cpu, idlestate);
-				printf("CPU: %u - idlestate %u - state_latency: %llu - latency: %llu\n",
-				       cpu, idlestate, state_latency, latency);
-				if (disabled == 1 || latency > state_latency)
+				if (disabled == 1) {
+					if (latency > state_latency){
+						ret = sysfs_idlestate_disable
+							(cpu, idlestate, 0);
+						if (ret == 0)
+		printf(_("Idlestate %u enabled on CPU %u\n"),  idlestate, cpu);
+					}
 					continue;
-				ret = sysfs_idlestate_disable
-					(cpu, idlestate, 1);
-				if (ret == 0)
+				}
+				if (latency <= state_latency){
+					ret = sysfs_idlestate_disable
+						(cpu, idlestate, 1);
+					if (ret == 0)
 		printf(_("Idlestate %u disabled on CPU %u\n"), idlestate, cpu);
+				}
 			}
 			break;
 		case 'E':
diff --git a/tools/power/cpupower/utils/cpupower-info.c b/tools/power/cpupower/utils/cpupower-info.c
index 136d979e9586..10299f2e9d2a 100644
--- a/tools/power/cpupower/utils/cpupower-info.c
+++ b/tools/power/cpupower/utils/cpupower-info.c
@@ -17,8 +17,8 @@
 #include "helpers/sysfs.h"
 
 static struct option set_opts[] = {
-	{ .name = "perf-bias",	.has_arg = optional_argument,	.flag = NULL,	.val = 'b'},
-	{ },
+     {"perf-bias", optional_argument, NULL, 'b'},
+     { },
 };
 
 static void print_wrong_arg_exit(void)
diff --git a/tools/power/cpupower/utils/cpupower-set.c b/tools/power/cpupower/utils/cpupower-set.c
index 573c75f8e3f5..3e6f374f8dd7 100644
--- a/tools/power/cpupower/utils/cpupower-set.c
+++ b/tools/power/cpupower/utils/cpupower-set.c
@@ -18,7 +18,7 @@
 #include "helpers/bitmask.h"
 
 static struct option set_opts[] = {
-	{ .name = "perf-bias",	.has_arg = required_argument,	.flag = NULL,	.val = 'b'},
+	{"perf-bias", required_argument, NULL, 'b'},
 	{ },
 };
 
diff --git a/tools/power/cpupower/utils/helpers/topology.c b/tools/power/cpupower/utils/helpers/topology.c
index cea398c176e7..9cbb7fd75171 100644
--- a/tools/power/cpupower/utils/helpers/topology.c
+++ b/tools/power/cpupower/utils/helpers/topology.c
@@ -73,18 +73,22 @@ int get_cpu_topology(struct cpupower_topology *cpu_top)
 	for (cpu = 0; cpu < cpus; cpu++) {
 		cpu_top->core_info[cpu].cpu = cpu;
 		cpu_top->core_info[cpu].is_online = sysfs_is_cpu_online(cpu);
-		if (!cpu_top->core_info[cpu].is_online)
-			continue;
 		if(sysfs_topology_read_file(
 			cpu,
 			"physical_package_id",
-			&(cpu_top->core_info[cpu].pkg)) < 0)
-			return -1;
+			&(cpu_top->core_info[cpu].pkg)) < 0) {
+			cpu_top->core_info[cpu].pkg = -1;
+			cpu_top->core_info[cpu].core = -1;
+			continue;
+		}
 		if(sysfs_topology_read_file(
 			cpu,
 			"core_id",
-			&(cpu_top->core_info[cpu].core)) < 0)
-			return -1;
+			&(cpu_top->core_info[cpu].core)) < 0) {
+			cpu_top->core_info[cpu].pkg = -1;
+			cpu_top->core_info[cpu].core = -1;
+			continue;
+		}
 	}
 
 	qsort(cpu_top->core_info, cpus, sizeof(struct cpuid_core_info),
@@ -95,12 +99,15 @@ int get_cpu_topology(struct cpupower_topology *cpu_top)
 	   done by pkg value. */
 	last_pkg = cpu_top->core_info[0].pkg;
 	for(cpu = 1; cpu < cpus; cpu++) {
-		if(cpu_top->core_info[cpu].pkg != last_pkg) {
+		if (cpu_top->core_info[cpu].pkg != last_pkg &&
+				cpu_top->core_info[cpu].pkg != -1) {
+
 			last_pkg = cpu_top->core_info[cpu].pkg;
 			cpu_top->pkgs++;
 		}
 	}
-	cpu_top->pkgs++;
+	if (!cpu_top->core_info[0].pkg == -1)
+		cpu_top->pkgs++;
 
 	/* Intel's cores count is not consecutively numbered, there may
 	 * be a core_id of 3, but none of 2. Assume there always is 0
diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
index c4bae9203a69..05f953f0f0a0 100644
--- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
+++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
@@ -143,6 +143,9 @@ void print_results(int topology_depth, int cpu)
 	/* Be careful CPUs may got resorted for pkg value do not just use cpu */
 	if (!bitmask_isbitset(cpus_chosen, cpu_top.core_info[cpu].cpu))
 		return;
+	if (!cpu_top.core_info[cpu].is_online &&
+	    cpu_top.core_info[cpu].pkg == -1)
+		return;
 
 	if (topology_depth > 2)
 		printf("%4d|", cpu_top.core_info[cpu].pkg);
@@ -191,7 +194,8 @@ void print_results(int topology_depth, int cpu)
 	 * It's up to the monitor plug-in to check .is_online, this one
 	 * is just for additional info.
 	 */
-	if (!cpu_top.core_info[cpu].is_online) {
+	if (!cpu_top.core_info[cpu].is_online &&
+	    cpu_top.core_info[cpu].pkg != -1) {
 		printf(_(" *is offline\n"));
 		return;
 	} else
@@ -388,6 +392,9 @@ int cmd_monitor(int argc, char **argv)
 		return EXIT_FAILURE;
 	}
 
+	if (!cpu_top.core_info[0].is_online)
+		printf("WARNING: at least one cpu is offline\n");
+
 	/* Default is: monitor all CPUs */
 	if (bitmask_isallclear(cpus_chosen))
 		bitmask_setall(cpus_chosen);
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index bde0ef1a63df..0dac7e05a6ac 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -75,6 +75,7 @@ unsigned int aperf_mperf_multiplier = 1;
 int do_smi;
 double bclk;
 double base_hz;
+unsigned int has_base_hz;
 double tsc_tweak = 1.0;
 unsigned int show_pkg;
 unsigned int show_core;
@@ -96,6 +97,7 @@ unsigned int do_ring_perf_limit_reasons;
 unsigned int crystal_hz;
 unsigned long long tsc_hz;
 int base_cpu;
+double discover_bclk(unsigned int family, unsigned int model);
 
 #define RAPL_PKG		(1 << 0)
 					/* 0x610 MSR_PKG_POWER_LIMIT */
@@ -511,9 +513,13 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	}
 
 	/* Bzy_MHz */
-	if (has_aperf)
-		outp += sprintf(outp, "%8.0f",
-			1.0 * t->tsc * tsc_tweak / units * t->aperf / t->mperf / interval_float);
+	if (has_aperf) {
+		if (has_base_hz)
+			outp += sprintf(outp, "%8.0f", base_hz / units * t->aperf / t->mperf);
+		else
+			outp += sprintf(outp, "%8.0f",
+				1.0 * t->tsc / units * t->aperf / t->mperf / interval_float);
+	}
 
 	/* TSC_MHz */
 	outp += sprintf(outp, "%8.0f", 1.0 * t->tsc/units/interval_float);
@@ -1158,12 +1164,6 @@ int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV,
 static void
 calculate_tsc_tweak()
 {
-	unsigned long long msr;
-	unsigned int base_ratio;
-
-	get_msr(base_cpu, MSR_NHM_PLATFORM_INFO, &msr);
-	base_ratio = (msr >> 8) & 0xFF;
-	base_hz = base_ratio * bclk * 1000000;
 	tsc_tweak = base_hz / tsc_hz;
 }
 
@@ -1173,9 +1173,9 @@ dump_nhm_platform_info(void)
 	unsigned long long msr;
 	unsigned int ratio;
 
-	get_msr(base_cpu, MSR_NHM_PLATFORM_INFO, &msr);
+	get_msr(base_cpu, MSR_PLATFORM_INFO, &msr);
 
-	fprintf(stderr, "cpu%d: MSR_NHM_PLATFORM_INFO: 0x%08llx\n", base_cpu, msr);
+	fprintf(stderr, "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",
@@ -1440,7 +1440,7 @@ dump_config_tdp(void)
 	
 	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) & 0xEF);
+	fprintf(stderr, "MAX_NON_TURBO_RATIO=%d", (unsigned int)(msr) & 0x7F);
 	fprintf(stderr, " lock=%d", (unsigned int)(msr >> 31) & 1);
 	fprintf(stderr, ")\n");
 }
@@ -1807,7 +1807,7 @@ void check_permissions()
  *
  * MSR_SMI_COUNT                   0x00000034
  *
- * MSR_NHM_PLATFORM_INFO           0x000000ce
+ * MSR_PLATFORM_INFO               0x000000ce
  * MSR_NHM_SNB_PKG_CST_CFG_CTL     0x000000e2
  *
  * MSR_PKG_C3_RESIDENCY            0x000003f8
@@ -1821,6 +1821,7 @@ void check_permissions()
 int probe_nhm_msrs(unsigned int family, unsigned int model)
 {
 	unsigned long long msr;
+	unsigned int base_ratio;
 	int *pkg_cstate_limits;
 
 	if (!genuine_intel)
@@ -1829,6 +1830,8 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 	if (family != 6)
 		return 0;
 
+	bclk = discover_bclk(family, model);
+
 	switch (model) {
 	case 0x1A:	/* Core i7, Xeon 5500 series - Bloomfield, Gainstown NHM-EP */
 	case 0x1E:	/* Core i7 and i5 Processor - Clarksfield, Lynnfield, Jasper Forest */
@@ -1871,9 +1874,13 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 		return 0;
 	}
 	get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
-
 	pkg_cstate_limit = pkg_cstate_limits[msr & 0xF];
 
+	get_msr(base_cpu, MSR_PLATFORM_INFO, &msr);
+	base_ratio = (msr >> 8) & 0xFF;
+
+	base_hz = base_ratio * bclk * 1000000;
+	has_base_hz = 1;
 	return 1;
 }
 int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model)
@@ -2780,7 +2787,6 @@ void process_cpuid()
 	do_skl_residency = has_skl_msrs(family, model);
 	do_slm_cstates = is_slm(family, model);
 	do_knl_cstates  = is_knl(family, model);
-	bclk = discover_bclk(family, model);
 
 	rapl_probe(family, model);
 	perf_limit_reasons_probe(family, model);
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 021e6f97f33e..51cf8256c6cd 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -17,8 +17,10 @@
 #include <linux/vmalloc.h>
 #include <linux/device.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/ndctl.h>
 #include <linux/sizes.h>
+#include <linux/list.h>
 #include <linux/slab.h>
 #include <nfit.h>
 #include <nd.h>
@@ -44,6 +46,15 @@
  * +------+  |                 blk5.0             |  pm1.0  |    3      region5
  *           +-------------------------+----------+-+-------+
  *
+ * +--+---+
+ * | cpu1 |
+ * +--+---+                   (Hotplug DIMM)
+ *    |      +----------------------------------------------+
+ * +--+---+  |                 blk6.0/pm7.0                 |    4      region6/7
+ * | imc0 +--+----------------------------------------------+
+ * +------+
+ *
+ *
  * *) In this layout we have four dimms and two memory controllers in one
  *    socket.  Each unique interface (BLK or PMEM) to DPA space
  *    is identified by a region device with a dynamically assigned id.
@@ -85,8 +96,8 @@
  *    reference an NVDIMM.
  */
 enum {
-	NUM_PM  = 2,
-	NUM_DCR = 4,
+	NUM_PM  = 3,
+	NUM_DCR = 5,
 	NUM_BDW = NUM_DCR,
 	NUM_SPA = NUM_PM + NUM_DCR + NUM_BDW,
 	NUM_MEM = NUM_DCR + NUM_BDW + 2 /* spa0 iset */ + 4 /* spa1 iset */,
@@ -115,6 +126,7 @@ static u32 handle[NUM_DCR] = {
 	[1] = NFIT_DIMM_HANDLE(0, 0, 0, 0, 1),
 	[2] = NFIT_DIMM_HANDLE(0, 0, 1, 0, 0),
 	[3] = NFIT_DIMM_HANDLE(0, 0, 1, 0, 1),
+	[4] = NFIT_DIMM_HANDLE(0, 1, 0, 0, 0),
 };
 
 struct nfit_test {
@@ -138,6 +150,7 @@ struct nfit_test {
 	dma_addr_t *dcr_dma;
 	int (*alloc)(struct nfit_test *t);
 	void (*setup)(struct nfit_test *t);
+	int setup_hotplug;
 };
 
 static struct nfit_test *to_nfit_test(struct device *dev)
@@ -407,8 +420,7 @@ static struct nfit_test_resource *nfit_test_lookup(resource_size_t addr)
 
 static int nfit_test0_alloc(struct nfit_test *t)
 {
-	size_t nfit_size = sizeof(struct acpi_table_nfit)
-			+ sizeof(struct acpi_nfit_system_address) * NUM_SPA
+	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
 			+ sizeof(struct acpi_nfit_data_region) * NUM_BDW
@@ -428,6 +440,10 @@ static int nfit_test0_alloc(struct nfit_test *t)
 	if (!t->spa_set[1])
 		return -ENOMEM;
 
+	t->spa_set[2] = test_alloc_coherent(t, SPA0_SIZE, &t->spa_set_dma[2]);
+	if (!t->spa_set[2])
+		return -ENOMEM;
+
 	for (i = 0; i < NUM_DCR; i++) {
 		t->dimm[i] = test_alloc(t, DIMM_SIZE, &t->dimm_dma[i]);
 		if (!t->dimm[i])
@@ -454,8 +470,7 @@ static int nfit_test0_alloc(struct nfit_test *t)
 
 static int nfit_test1_alloc(struct nfit_test *t)
 {
-	size_t nfit_size = sizeof(struct acpi_table_nfit)
-		+ sizeof(struct acpi_nfit_system_address)
+	size_t nfit_size = sizeof(struct acpi_nfit_system_address)
 		+ sizeof(struct acpi_nfit_memory_map)
 		+ sizeof(struct acpi_nfit_control_region);
 
@@ -471,39 +486,24 @@ static int nfit_test1_alloc(struct nfit_test *t)
 	return 0;
 }
 
-static void nfit_test_init_header(struct acpi_table_nfit *nfit, size_t size)
-{
-	memcpy(nfit->header.signature, ACPI_SIG_NFIT, 4);
-	nfit->header.length = size;
-	nfit->header.revision = 1;
-	memcpy(nfit->header.oem_id, "LIBND", 6);
-	memcpy(nfit->header.oem_table_id, "TEST", 5);
-	nfit->header.oem_revision = 1;
-	memcpy(nfit->header.asl_compiler_id, "TST", 4);
-	nfit->header.asl_compiler_revision = 1;
-}
-
 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;
-	size_t size = t->nfit_size;
 	struct acpi_nfit_system_address *spa;
 	struct acpi_nfit_control_region *dcr;
 	struct acpi_nfit_data_region *bdw;
 	struct acpi_nfit_flush_address *flush;
 	unsigned int offset;
 
-	nfit_test_init_header(nfit_buf, size);
-
 	/*
 	 * spa0 (interleave first half of dimm0 and dimm1, note storage
 	 * does not actually alias the related block-data-window
 	 * regions)
 	 */
-	spa = nfit_buf + sizeof(struct acpi_table_nfit);
+	spa = nfit_buf;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
 	spa->header.length = sizeof(*spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16);
@@ -516,7 +516,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	 * does not actually alias the related block-data-window
 	 * regions)
 	 */
-	spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa);
+	spa = nfit_buf + sizeof(*spa);
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
 	spa->header.length = sizeof(*spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16);
@@ -525,7 +525,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	spa->length = SPA1_SIZE;
 
 	/* spa2 (dcr0) dimm0 */
-	spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 2;
+	spa = nfit_buf + sizeof(*spa) * 2;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
 	spa->header.length = sizeof(*spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16);
@@ -534,7 +534,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	spa->length = DCR_SIZE;
 
 	/* spa3 (dcr1) dimm1 */
-	spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 3;
+	spa = nfit_buf + sizeof(*spa) * 3;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
 	spa->header.length = sizeof(*spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16);
@@ -543,7 +543,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	spa->length = DCR_SIZE;
 
 	/* spa4 (dcr2) dimm2 */
-	spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 4;
+	spa = nfit_buf + sizeof(*spa) * 4;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
 	spa->header.length = sizeof(*spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16);
@@ -552,7 +552,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	spa->length = DCR_SIZE;
 
 	/* spa5 (dcr3) dimm3 */
-	spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 5;
+	spa = nfit_buf + sizeof(*spa) * 5;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
 	spa->header.length = sizeof(*spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16);
@@ -561,7 +561,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	spa->length = DCR_SIZE;
 
 	/* spa6 (bdw for dcr0) dimm0 */
-	spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 6;
+	spa = nfit_buf + sizeof(*spa) * 6;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
 	spa->header.length = sizeof(*spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16);
@@ -570,7 +570,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	spa->length = DIMM_SIZE;
 
 	/* spa7 (bdw for dcr1) dimm1 */
-	spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 7;
+	spa = nfit_buf + sizeof(*spa) * 7;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
 	spa->header.length = sizeof(*spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16);
@@ -579,7 +579,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	spa->length = DIMM_SIZE;
 
 	/* spa8 (bdw for dcr2) dimm2 */
-	spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 8;
+	spa = nfit_buf + sizeof(*spa) * 8;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
 	spa->header.length = sizeof(*spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16);
@@ -588,7 +588,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	spa->length = DIMM_SIZE;
 
 	/* spa9 (bdw for dcr3) dimm3 */
-	spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 9;
+	spa = nfit_buf + sizeof(*spa) * 9;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
 	spa->header.length = sizeof(*spa);
 	memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16);
@@ -596,7 +596,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	spa->address = t->dimm_dma[3];
 	spa->length = DIMM_SIZE;
 
-	offset = sizeof(struct acpi_table_nfit) + sizeof(*spa) * 10;
+	offset = sizeof(*spa) * 10;
 	/* mem-region0 (spa0, dimm0) */
 	memdev = nfit_buf + offset;
 	memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
@@ -950,6 +950,126 @@ static void nfit_test0_setup(struct nfit_test *t)
 	flush->hint_count = 1;
 	flush->hint_address[0] = t->flush_dma[3];
 
+	if (t->setup_hotplug) {
+		offset = offset + sizeof(struct acpi_nfit_flush_address) * 4;
+		/* dcr-descriptor4 */
+		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->vendor_id = 0xabcd;
+		dcr->device_id = 0;
+		dcr->revision_id = 1;
+		dcr->serial_number = ~handle[4];
+		dcr->windows = 1;
+		dcr->window_size = DCR_SIZE;
+		dcr->command_offset = 0;
+		dcr->command_size = 8;
+		dcr->status_offset = 8;
+		dcr->status_size = 4;
+
+		offset = offset + sizeof(struct acpi_nfit_control_region);
+		/* 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->windows = 1;
+		bdw->offset = 0;
+		bdw->size = BDW_SIZE;
+		bdw->capacity = DIMM_SIZE;
+		bdw->start_address = 0;
+
+		offset = offset + sizeof(struct acpi_nfit_data_region);
+		/* spa10 (dcr4) dimm4 */
+		spa = nfit_buf + offset;
+		spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
+		spa->header.length = sizeof(*spa);
+		memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16);
+		spa->range_index = 10+1;
+		spa->address = t->dcr_dma[4];
+		spa->length = DCR_SIZE;
+
+		/*
+		 * spa11 (single-dimm interleave for hotplug, note storage
+		 * does not actually alias the related block-data-window
+		 * regions)
+		 */
+		spa = nfit_buf + offset + sizeof(*spa);
+		spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
+		spa->header.length = sizeof(*spa);
+		memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16);
+		spa->range_index = 11+1;
+		spa->address = t->spa_set_dma[2];
+		spa->length = SPA0_SIZE;
+
+		/* spa12 (bdw for dcr4) dimm4 */
+		spa = nfit_buf + offset + sizeof(*spa) * 2;
+		spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
+		spa->header.length = sizeof(*spa);
+		memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16);
+		spa->range_index = 12+1;
+		spa->address = t->dimm_dma[4];
+		spa->length = DIMM_SIZE;
+
+		offset = offset + sizeof(*spa) * 3;
+		/* mem-region14 (spa/dcr4, dimm4) */
+		memdev = nfit_buf + offset;
+		memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
+		memdev->header.length = sizeof(*memdev);
+		memdev->device_handle = handle[4];
+		memdev->physical_id = 4;
+		memdev->region_id = 0;
+		memdev->range_index = 10+1;
+		memdev->region_index = 4+1;
+		memdev->region_size = 0;
+		memdev->region_offset = 0;
+		memdev->address = 0;
+		memdev->interleave_index = 0;
+		memdev->interleave_ways = 1;
+
+		/* mem-region15 (spa0, dimm4) */
+		memdev = nfit_buf + offset +
+				sizeof(struct acpi_nfit_memory_map);
+		memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
+		memdev->header.length = sizeof(*memdev);
+		memdev->device_handle = handle[4];
+		memdev->physical_id = 4;
+		memdev->region_id = 0;
+		memdev->range_index = 11+1;
+		memdev->region_index = 4+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) */
+		memdev = nfit_buf + offset +
+				sizeof(struct acpi_nfit_memory_map) * 2;
+		memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
+		memdev->header.length = sizeof(*memdev);
+		memdev->device_handle = handle[4];
+		memdev->physical_id = 4;
+		memdev->region_id = 0;
+		memdev->range_index = 12+1;
+		memdev->region_index = 4+1;
+		memdev->region_size = 0;
+		memdev->region_offset = 0;
+		memdev->address = 0;
+		memdev->interleave_index = 0;
+		memdev->interleave_ways = 1;
+
+		offset = offset + sizeof(struct acpi_nfit_memory_map) * 3;
+		/* flush3 (dimm4) */
+		flush = nfit_buf + offset;
+		flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS;
+		flush->header.length = sizeof(struct acpi_nfit_flush_address);
+		flush->device_handle = handle[4];
+		flush->hint_count = 1;
+		flush->hint_address[0] = t->flush_dma[4];
+	}
+
 	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);
@@ -963,15 +1083,13 @@ static void nfit_test0_setup(struct nfit_test *t)
 
 static void nfit_test1_setup(struct nfit_test *t)
 {
-	size_t size = t->nfit_size, offset;
+	size_t offset;
 	void *nfit_buf = t->nfit_buf;
 	struct acpi_nfit_memory_map *memdev;
 	struct acpi_nfit_control_region *dcr;
 	struct acpi_nfit_system_address *spa;
 
-	nfit_test_init_header(nfit_buf, size);
-
-	offset = sizeof(struct acpi_table_nfit);
+	offset = 0;
 	/* spa0 (flat range with no bdw aliasing) */
 	spa = nfit_buf + offset;
 	spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
@@ -998,7 +1116,7 @@ static void nfit_test1_setup(struct nfit_test *t)
 	memdev->interleave_ways = 1;
 	memdev->flags = ACPI_NFIT_MEM_SAVE_FAILED | ACPI_NFIT_MEM_RESTORE_FAILED
 		| ACPI_NFIT_MEM_FLUSH_FAILED | ACPI_NFIT_MEM_HEALTH_OBSERVED
-		| ACPI_NFIT_MEM_ARMED;
+		| ACPI_NFIT_MEM_NOT_ARMED;
 
 	offset += sizeof(*memdev);
 	/* dcr-descriptor0 */
@@ -1108,6 +1226,29 @@ static int nfit_test_probe(struct platform_device *pdev)
 	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);
+		return rc;
+	}
+
+	if (nfit_test->setup != nfit_test0_setup)
+		return 0;
+
+	nfit_test->setup_hotplug = 1;
+	nfit_test->setup(nfit_test);
+
 	rc = acpi_nfit_init(acpi_desc, nfit_test->nfit_size);
 	if (rc) {
 		nvdimm_bus_unregister(acpi_desc->nvdimm_bus);
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index cfe121353eec..c8edff6803d1 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -6,6 +6,7 @@ TARGETS += firmware
 TARGETS += ftrace
 TARGETS += futex
 TARGETS += kcmp
+TARGETS += lib
 TARGETS += membarrier
 TARGETS += memfd
 TARGETS += memory-hotplug
@@ -13,6 +14,7 @@ TARGETS += mount
 TARGETS += mqueue
 TARGETS += net
 TARGETS += powerpc
+TARGETS += pstore
 TARGETS += ptrace
 TARGETS += seccomp
 TARGETS += size
@@ -65,6 +67,9 @@ clean_hotplug:
 		make -C $$TARGET clean; \
 	done;
 
+run_pstore_crash:
+	make -C pstore run_crash
+
 INSTALL_PATH ?= install
 INSTALL_PATH := $(abspath $(INSTALL_PATH))
 ALL_SCRIPT := $(INSTALL_PATH)/run_kselftest.sh
diff --git a/tools/testing/selftests/breakpoints/Makefile b/tools/testing/selftests/breakpoints/Makefile
index d27108b4f208..c0d957015f52 100644
--- a/tools/testing/selftests/breakpoints/Makefile
+++ b/tools/testing/selftests/breakpoints/Makefile
@@ -6,7 +6,7 @@ ifeq ($(ARCH),x86)
 TEST_PROGS := breakpoint_test
 endif
 
-all:
+all: $(TEST_PROGS)
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/efivarfs/.gitignore b/tools/testing/selftests/efivarfs/.gitignore
new file mode 100644
index 000000000000..33618493562b
--- /dev/null
+++ b/tools/testing/selftests/efivarfs/.gitignore
@@ -0,0 +1,2 @@
+create-read
+open-unlink
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
index a5a426211129..c3843ed49bf6 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
@@ -5,7 +5,7 @@
 
 echo 0 > events/enable
 echo > kprobe_events
-echo p:myevent do_fork > kprobe_events
+echo p:myevent _do_fork > kprobe_events
 grep myevent kprobe_events
 test -d events/kprobes/myevent
 echo > kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
index d8c7bb6581fe..74507db8bbc8 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
@@ -5,7 +5,7 @@
 
 echo 0 > events/enable
 echo > kprobe_events
-echo p:myevent do_fork > kprobe_events
+echo p:myevent _do_fork > kprobe_events
 test -d events/kprobes/myevent
 echo 1 > events/kprobes/myevent/enable
 echo > kprobe_events && exit 1 # this must fail
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
index c45ee2761354..64949d4eda69 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
@@ -5,7 +5,7 @@
 
 echo 0 > events/enable
 echo > kprobe_events
-echo 'p:testprobe do_fork $stack $stack0 +0($stack)' > kprobe_events
+echo 'p:testprobe _do_fork $stack $stack0 +0($stack)' > kprobe_events
 grep testprobe kprobe_events
 test -d events/kprobes/testprobe
 echo 1 > events/kprobes/testprobe/enable
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
index ab41d2b29841..d6f2f4965697 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
@@ -6,31 +6,31 @@ grep function available_tracers || exit_unsupported # this is configurable
 
 # prepare
 echo nop > current_tracer
-echo do_fork > set_ftrace_filter
+echo _do_fork > set_ftrace_filter
 echo 0 > events/enable
 echo > kprobe_events
-echo 'p:testprobe do_fork' > kprobe_events
+echo 'p:testprobe _do_fork' > kprobe_events
 
 # kprobe on / ftrace off
 echo 1 > events/kprobes/testprobe/enable
 echo > trace
 ( echo "forked")
 grep testprobe trace
-! grep 'do_fork <-' trace
+! grep '_do_fork <-' trace
 
 # kprobe on / ftrace on
 echo function > current_tracer
 echo > trace
 ( echo "forked")
 grep testprobe trace
-grep 'do_fork <-' trace
+grep '_do_fork <-' trace
 
 # kprobe off / ftrace on
 echo 0 > events/kprobes/testprobe/enable
 echo > trace
 ( echo "forked")
 ! grep testprobe trace
-grep 'do_fork <-' trace
+grep '_do_fork <-' trace
 
 # kprobe on / ftrace on
 echo 1 > events/kprobes/testprobe/enable
@@ -38,14 +38,14 @@ echo function > current_tracer
 echo > trace
 ( echo "forked")
 grep testprobe trace
-grep 'do_fork <-' trace
+grep '_do_fork <-' trace
 
 # kprobe on / ftrace off
 echo nop > current_tracer
 echo > trace
 ( echo "forked")
 grep testprobe trace
-! grep 'do_fork <-' trace
+! grep '_do_fork <-' trace
 
 # cleanup
 echo nop > current_tracer
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
index 31717985acc7..0d09546258fd 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
@@ -5,7 +5,7 @@
 
 echo 0 > events/enable
 echo > kprobe_events
-echo 'r:testprobe2 do_fork $retval' > kprobe_events
+echo 'r:testprobe2 _do_fork $retval' > kprobe_events
 grep testprobe2 kprobe_events
 test -d events/kprobes/testprobe2
 echo 1 > events/kprobes/testprobe2/enable
diff --git a/tools/testing/selftests/futex/README b/tools/testing/selftests/futex/README
index 3224a049b196..0558bb9ce0a6 100644
--- a/tools/testing/selftests/futex/README
+++ b/tools/testing/selftests/futex/README
@@ -27,7 +27,7 @@ o The build system shall remain as simple as possible, avoiding any archive or
 o Where possible, any helper functions or other package-wide code shall be
   implemented in header files, avoiding the need to compile intermediate object
   files.
-o External dependendencies shall remain as minimal as possible. Currently gcc
+o External dependencies shall remain as minimal as possible. Currently gcc
   and glibc are the only dependencies.
 o Tests return 0 for success and < 0 for failure.
 
diff --git a/tools/testing/selftests/lib/Makefile b/tools/testing/selftests/lib/Makefile
new file mode 100644
index 000000000000..47147b968514
--- /dev/null
+++ b/tools/testing/selftests/lib/Makefile
@@ -0,0 +1,8 @@
+# Makefile for lib/ function selftests
+
+# No binaries, but make sure arg-less "make" doesn't trigger "run_tests"
+all:
+
+TEST_PROGS := printf.sh
+
+include ../lib.mk
diff --git a/tools/testing/selftests/lib/printf.sh b/tools/testing/selftests/lib/printf.sh
new file mode 100644
index 000000000000..4fdc70fe6980
--- /dev/null
+++ b/tools/testing/selftests/lib/printf.sh
@@ -0,0 +1,10 @@
+#!/bin/sh
+# Runs printf infrastructure using test_printf kernel module
+
+if /sbin/modprobe -q test_printf; then
+	/sbin/modprobe -q -r test_printf
+	echo "printf: ok"
+else
+	echo "printf: [FAIL]"
+	exit 1
+fi
diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile
index 3e7eb7972511..fd396ac811b6 100644
--- a/tools/testing/selftests/memfd/Makefile
+++ b/tools/testing/selftests/memfd/Makefile
@@ -4,16 +4,16 @@ CFLAGS += -I../../../../include/uapi/
 CFLAGS += -I../../../../include/
 CFLAGS += -I../../../../usr/include/
 
-all:
-	$(CC) $(CFLAGS) memfd_test.c -o memfd_test
-
 TEST_PROGS := memfd_test
 
+all: $(TEST_PROGS)
+
 include ../lib.mk
 
-build_fuse:
-	$(CC) $(CFLAGS) fuse_mnt.c `pkg-config fuse --cflags --libs` -o fuse_mnt
-	$(CC) $(CFLAGS) fuse_test.c -o fuse_test
+build_fuse: fuse_mnt fuse_test
+
+fuse_mnt.o: CFLAGS += $(shell pkg-config fuse --cflags)
+fuse_mnt: LDFLAGS += $(shell pkg-config fuse --libs)
 
 run_fuse: build_fuse
 	@./run_fuse_test.sh || echo "fuse_test: [FAIL]"
diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c
index 0b9eafb7ab7b..26546892cd54 100644
--- a/tools/testing/selftests/memfd/memfd_test.c
+++ b/tools/testing/selftests/memfd/memfd_test.c
@@ -15,10 +15,11 @@
 #include <sys/mman.h>
 #include <sys/stat.h>
 #include <sys/syscall.h>
+#include <sys/wait.h>
 #include <unistd.h>
 
 #define MFD_DEF_SIZE 8192
-#define STACK_SIZE 65535
+#define STACK_SIZE 65536
 
 static int sys_memfd_create(const char *name,
 			    unsigned int flags)
diff --git a/tools/testing/selftests/memfd/run_fuse_test.sh b/tools/testing/selftests/memfd/run_fuse_test.sh
index 69b930e1e041..69b930e1e041 100644..100755
--- a/tools/testing/selftests/memfd/run_fuse_test.sh
+++ b/tools/testing/selftests/memfd/run_fuse_test.sh
diff --git a/tools/testing/selftests/mqueue/mq_open_tests.c b/tools/testing/selftests/mqueue/mq_open_tests.c
index 9c1a5d359055..e0a74bd207a5 100644
--- a/tools/testing/selftests/mqueue/mq_open_tests.c
+++ b/tools/testing/selftests/mqueue/mq_open_tests.c
@@ -31,6 +31,7 @@
 #include <sys/resource.h>
 #include <sys/stat.h>
 #include <mqueue.h>
+#include <error.h>
 
 static char *usage =
 "Usage:\n"
diff --git a/tools/testing/selftests/mqueue/mq_perf_tests.c b/tools/testing/selftests/mqueue/mq_perf_tests.c
index 8519e9ee97e3..8188f72de93c 100644
--- a/tools/testing/selftests/mqueue/mq_perf_tests.c
+++ b/tools/testing/selftests/mqueue/mq_perf_tests.c
@@ -37,6 +37,7 @@
 #include <sys/stat.h>
 #include <mqueue.h>
 #include <popt.h>
+#include <error.h>
 
 static char *usage =
 "Usage:\n"
diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile
index 03ca2e64b3fc..0c2706bda330 100644
--- a/tools/testing/selftests/powerpc/Makefile
+++ b/tools/testing/selftests/powerpc/Makefile
@@ -12,7 +12,17 @@ CFLAGS := -Wall -O2 -flto -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CUR
 
 export CFLAGS
 
-SUB_DIRS = pmu copyloops mm tm primitives stringloops vphn switch_endian dscr
+SUB_DIRS = benchmarks 		\
+	   copyloops		\
+	   dscr			\
+	   mm			\
+	   pmu			\
+	   primitives		\
+	   stringloops		\
+	   switch_endian	\
+	   syscalls		\
+	   tm			\
+	   vphn
 
 endif
 
diff --git a/tools/testing/selftests/powerpc/benchmarks/.gitignore b/tools/testing/selftests/powerpc/benchmarks/.gitignore
new file mode 100644
index 000000000000..b4709ea588c1
--- /dev/null
+++ b/tools/testing/selftests/powerpc/benchmarks/.gitignore
@@ -0,0 +1 @@
+gettimeofday
diff --git a/tools/testing/selftests/powerpc/benchmarks/Makefile b/tools/testing/selftests/powerpc/benchmarks/Makefile
new file mode 100644
index 000000000000..5fa48702070d
--- /dev/null
+++ b/tools/testing/selftests/powerpc/benchmarks/Makefile
@@ -0,0 +1,12 @@
+TEST_PROGS := gettimeofday
+
+CFLAGS += -O2
+
+all: $(TEST_PROGS)
+
+$(TEST_PROGS): ../harness.c
+
+include ../../lib.mk
+
+clean:
+	rm -f $(TEST_PROGS) *.o
diff --git a/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c b/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c
new file mode 100644
index 000000000000..3af3c21e8036
--- /dev/null
+++ b/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c
@@ -0,0 +1,31 @@
+/*
+ * Copyright 2015, Anton Blanchard, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <sys/time.h>
+#include <stdio.h>
+
+#include "utils.h"
+
+static int test_gettimeofday(void)
+{
+	int i;
+
+	struct timeval tv_start, tv_end;
+
+	gettimeofday(&tv_start, NULL);
+
+	for(i = 0; i < 100000000; i++) {
+		gettimeofday(&tv_end, NULL);
+	}
+
+	printf("time = %.6f\n", tv_end.tv_sec - tv_start.tv_sec + (tv_end.tv_usec - tv_start.tv_usec) * 1e-6);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(test_gettimeofday, "gettimeofday");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
index 66ea765c0e72..94110b1dcd3d 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
@@ -63,6 +63,8 @@ int back_to_back_ebbs(void)
 {
 	struct event event;
 
+	SKIP_IF(!ebb_is_supported());
+
 	event_init_named(&event, 0x1001e, "cycles");
 	event_leader_ebb_init(&event);
 
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/close_clears_pmcc_test.c b/tools/testing/selftests/powerpc/pmu/ebb/close_clears_pmcc_test.c
index 0f0423dba18b..ac18cf617dd6 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/close_clears_pmcc_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/close_clears_pmcc_test.c
@@ -20,6 +20,8 @@ int close_clears_pmcc(void)
 {
 	struct event event;
 
+	SKIP_IF(!ebb_is_supported());
+
 	event_init_named(&event, 0x1001e, "cycles");
 	event_leader_ebb_init(&event);
 
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_pinned_vs_ebb_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_pinned_vs_ebb_test.c
index d3ed64d5d6c0..f0632e7fdf29 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_pinned_vs_ebb_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_pinned_vs_ebb_test.c
@@ -43,6 +43,8 @@ int cpu_event_pinned_vs_ebb(void)
 	int cpu, rc;
 	pid_t pid;
 
+	SKIP_IF(!ebb_is_supported());
+
 	cpu = pick_online_cpu();
 	FAIL_IF(cpu < 0);
 	FAIL_IF(bind_to_cpu(cpu));
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_vs_ebb_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_vs_ebb_test.c
index 8b972c2aa392..33e56a2342e5 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_vs_ebb_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_vs_ebb_test.c
@@ -41,6 +41,8 @@ int cpu_event_vs_ebb(void)
 	int cpu, rc;
 	pid_t pid;
 
+	SKIP_IF(!ebb_is_supported());
+
 	cpu = pick_online_cpu();
 	FAIL_IF(cpu < 0);
 	FAIL_IF(bind_to_cpu(cpu));
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
index 8590fc1bfc0d..7c57a8d79535 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
@@ -16,6 +16,8 @@ int cycles(void)
 {
 	struct event event;
 
+	SKIP_IF(!ebb_is_supported());
+
 	event_init_named(&event, 0x1001e, "cycles");
 	event_leader_ebb_init(&event);
 
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
index 754b3f2008d3..ecf5ee3283a3 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
@@ -56,6 +56,8 @@ int cycles_with_freeze(void)
 	uint64_t val;
 	bool fc_cleared;
 
+	SKIP_IF(!ebb_is_supported());
+
 	event_init_named(&event, 0x1001e, "cycles");
 	event_leader_ebb_init(&event);
 
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
index d43029b0800c..c0faba520b35 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
@@ -26,6 +26,8 @@ int cycles_with_mmcr2(void)
 	int i;
 	bool bad_mmcr2;
 
+	SKIP_IF(!ebb_is_supported());
+
 	event_init_named(&event, 0x1001e, "cycles");
 	event_leader_ebb_init(&event);
 
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
index d7a72ce696b5..9729d9f90218 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
@@ -13,6 +13,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/ioctl.h>
+#include <linux/auxvec.h>
 
 #include "trace.h"
 #include "reg.h"
@@ -319,6 +320,16 @@ void ebb_global_disable(void)
 	mb();
 }
 
+bool ebb_is_supported(void)
+{
+#ifdef PPC_FEATURE2_EBB
+	/* EBB requires at least POWER8 */
+	return ((long)get_auxv_entry(AT_HWCAP2) & PPC_FEATURE2_EBB);
+#else
+	return false;
+#endif
+}
+
 void event_ebb_init(struct event *e)
 {
 	e->attr.config |= (1ull << 63);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.h b/tools/testing/selftests/powerpc/pmu/ebb/ebb.h
index e44eee5d97ca..f87e761f82d0 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.h
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.h
@@ -52,6 +52,7 @@ void standard_ebb_callee(void);
 int ebb_event_enable(struct event *e);
 void ebb_global_enable(void);
 void ebb_global_disable(void);
+bool ebb_is_supported(void);
 void ebb_freeze_pmcs(void);
 void ebb_unfreeze_pmcs(void);
 void event_ebb_init(struct event *e);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_child_test.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_child_test.c
index c45f948148e1..1e7b7fe2396b 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_child_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_child_test.c
@@ -47,6 +47,8 @@ int ebb_on_child(void)
 	struct event event;
 	pid_t pid;
 
+	SKIP_IF(!ebb_is_supported());
+
 	FAIL_IF(pipe(read_pipe.fds) == -1);
 	FAIL_IF(pipe(write_pipe.fds) == -1);
 
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
index 11acf1d55f8d..a991d2ea8d0a 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
@@ -54,6 +54,8 @@ int ebb_on_willing_child(void)
 	struct event event;
 	pid_t pid;
 
+	SKIP_IF(!ebb_is_supported());
+
 	FAIL_IF(pipe(read_pipe.fds) == -1);
 	FAIL_IF(pipe(write_pipe.fds) == -1);
 
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_vs_cpu_event_test.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_vs_cpu_event_test.c
index be4dd5a4e98e..af20a2b363aa 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb_vs_cpu_event_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_vs_cpu_event_test.c
@@ -41,6 +41,8 @@ int ebb_vs_cpu_event(void)
 	int cpu, rc;
 	pid_t pid;
 
+	SKIP_IF(!ebb_is_supported());
+
 	cpu = pick_online_cpu();
 	FAIL_IF(cpu < 0);
 	FAIL_IF(bind_to_cpu(cpu));
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/event_attributes_test.c b/tools/testing/selftests/powerpc/pmu/ebb/event_attributes_test.c
index 7e78153f08eb..7762ab26e5ac 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/event_attributes_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/event_attributes_test.c
@@ -16,6 +16,8 @@ int event_attributes(void)
 {
 	struct event event, leader;
 
+	SKIP_IF(!ebb_is_supported());
+
 	event_init(&event, 0x1001e);
 	event_leader_ebb_init(&event);
 	/* Expected to succeed */
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/fork_cleanup_test.c b/tools/testing/selftests/powerpc/pmu/ebb/fork_cleanup_test.c
index 9e7af6e76622..167135bd92a8 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/fork_cleanup_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/fork_cleanup_test.c
@@ -44,6 +44,8 @@ int fork_cleanup(void)
 {
 	pid_t pid;
 
+	SKIP_IF(!ebb_is_supported());
+
 	event_init_named(&event, 0x1001e, "cycles");
 	event_leader_ebb_init(&event);
 
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/instruction_count_test.c b/tools/testing/selftests/powerpc/pmu/ebb/instruction_count_test.c
index f8190fa29592..5da355135df2 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/instruction_count_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/instruction_count_test.c
@@ -111,6 +111,8 @@ int instruction_count(void)
 	struct event event;
 	uint64_t overhead;
 
+	SKIP_IF(!ebb_is_supported());
+
 	event_init_named(&event, 0x400FA, "PM_RUN_INST_CMPL");
 	event_leader_ebb_init(&event);
 	event.attr.exclude_kernel = 1;
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
index 0c9dd9b2e39d..eb8acb78bc6c 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
@@ -23,6 +23,8 @@ static int test_body(void)
 	int i, orig_period, max_period;
 	struct event event;
 
+	SKIP_IF(!ebb_is_supported());
+
 	/* We use PMC4 to make sure the kernel switches all counters correctly */
 	event_init_named(&event, 0x40002, "instructions");
 	event_leader_ebb_init(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
index 67d78af3284c..6ff8c8ff27d6 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
@@ -18,6 +18,8 @@ int multi_counter(void)
 	struct event events[6];
 	int i, group_fd;
 
+	SKIP_IF(!ebb_is_supported());
+
 	event_init_named(&events[0], 0x1001C, "PM_CMPLU_STALL_THRD");
 	event_init_named(&events[1], 0x2D016, "PM_CMPLU_STALL_FXU");
 	event_init_named(&events[2], 0x30006, "PM_CMPLU_STALL_OTHER_CMPL");
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
index b8dc371f9338..037cb6154f36 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
@@ -79,6 +79,8 @@ int multi_ebb_procs(void)
 	pid_t pids[NR_CHILDREN];
 	int cpu, rc, i;
 
+	SKIP_IF(!ebb_is_supported());
+
 	cpu = pick_online_cpu();
 	FAIL_IF(cpu < 0);
 	FAIL_IF(bind_to_cpu(cpu));
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/no_handler_test.c b/tools/testing/selftests/powerpc/pmu/ebb/no_handler_test.c
index 2f9bf8edfa60..8341d7778d5e 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/no_handler_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/no_handler_test.c
@@ -19,6 +19,8 @@ static int no_handler_test(void)
 	u64 val;
 	int i;
 
+	SKIP_IF(!ebb_is_supported());
+
 	event_init_named(&event, 0x1001e, "cycles");
 	event_leader_ebb_init(&event);
 
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
index 986500fd2131..c5fa64790c22 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
@@ -58,6 +58,8 @@ static int test_body(void)
 {
 	struct event event;
 
+	SKIP_IF(!ebb_is_supported());
+
 	event_init_named(&event, 0x1001e, "cycles");
 	event_leader_ebb_init(&event);
 
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
index a503fa70c950..c22860ab9733 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
@@ -49,6 +49,8 @@ int pmc56_overflow(void)
 {
 	struct event event;
 
+	SKIP_IF(!ebb_is_supported());
+
 	/* Use PMC2 so we set PMCjCE, which enables PMC5/6 */
 	event_init(&event, 0x2001e);
 	event_leader_ebb_init(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/reg_access_test.c b/tools/testing/selftests/powerpc/pmu/ebb/reg_access_test.c
index 0cae66f659a3..5b1188f10c15 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/reg_access_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/reg_access_test.c
@@ -18,6 +18,8 @@ int reg_access(void)
 {
 	uint64_t val, expected;
 
+	SKIP_IF(!ebb_is_supported());
+
 	expected = 0x8000000100000000ull;
 	mtspr(SPRN_BESCR, expected);
 	val = mfspr(SPRN_BESCR);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/task_event_pinned_vs_ebb_test.c b/tools/testing/selftests/powerpc/pmu/ebb/task_event_pinned_vs_ebb_test.c
index d56607e4ffab..1846f4e84635 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/task_event_pinned_vs_ebb_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/task_event_pinned_vs_ebb_test.c
@@ -42,6 +42,8 @@ int task_event_pinned_vs_ebb(void)
 	pid_t pid;
 	int rc;
 
+	SKIP_IF(!ebb_is_supported());
+
 	FAIL_IF(pipe(read_pipe.fds) == -1);
 	FAIL_IF(pipe(write_pipe.fds) == -1);
 
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/task_event_vs_ebb_test.c b/tools/testing/selftests/powerpc/pmu/ebb/task_event_vs_ebb_test.c
index eba32196dbbf..e3bc6e92a6a5 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/task_event_vs_ebb_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/task_event_vs_ebb_test.c
@@ -40,6 +40,8 @@ int task_event_vs_ebb(void)
 	pid_t pid;
 	int rc;
 
+	SKIP_IF(!ebb_is_supported());
+
 	FAIL_IF(pipe(read_pipe.fds) == -1);
 	FAIL_IF(pipe(write_pipe.fds) == -1);
 
diff --git a/tools/testing/selftests/powerpc/syscalls/.gitignore b/tools/testing/selftests/powerpc/syscalls/.gitignore
new file mode 100644
index 000000000000..f0f3fcc9d802
--- /dev/null
+++ b/tools/testing/selftests/powerpc/syscalls/.gitignore
@@ -0,0 +1 @@
+ipc_unmuxed
diff --git a/tools/testing/selftests/powerpc/syscalls/Makefile b/tools/testing/selftests/powerpc/syscalls/Makefile
new file mode 100644
index 000000000000..b35c7945bec5
--- /dev/null
+++ b/tools/testing/selftests/powerpc/syscalls/Makefile
@@ -0,0 +1,12 @@
+TEST_PROGS := ipc_unmuxed
+
+CFLAGS += -I../../../../../usr/include
+
+all: $(TEST_PROGS)
+
+$(TEST_PROGS): ../harness.c
+
+include ../../lib.mk
+
+clean:
+	rm -f $(TEST_PROGS) *.o
diff --git a/tools/testing/selftests/powerpc/syscalls/ipc.h b/tools/testing/selftests/powerpc/syscalls/ipc.h
new file mode 100644
index 000000000000..fbebc022edf6
--- /dev/null
+++ b/tools/testing/selftests/powerpc/syscalls/ipc.h
@@ -0,0 +1,47 @@
+#ifdef __NR_semop
+DO_TEST(semop, __NR_semop)
+#endif
+
+#ifdef __NR_semget
+DO_TEST(semget, __NR_semget)
+#endif
+
+#ifdef __NR_semctl
+DO_TEST(semctl, __NR_semctl)
+#endif
+
+#ifdef __NR_semtimedop
+DO_TEST(semtimedop, __NR_semtimedop)
+#endif
+
+#ifdef __NR_msgsnd
+DO_TEST(msgsnd, __NR_msgsnd)
+#endif
+
+#ifdef __NR_msgrcv
+DO_TEST(msgrcv, __NR_msgrcv)
+#endif
+
+#ifdef __NR_msgget
+DO_TEST(msgget, __NR_msgget)
+#endif
+
+#ifdef __NR_msgctl
+DO_TEST(msgctl, __NR_msgctl)
+#endif
+
+#ifdef __NR_shmat
+DO_TEST(shmat, __NR_shmat)
+#endif
+
+#ifdef __NR_shmdt
+DO_TEST(shmdt, __NR_shmdt)
+#endif
+
+#ifdef __NR_shmget
+DO_TEST(shmget, __NR_shmget)
+#endif
+
+#ifdef __NR_shmctl
+DO_TEST(shmctl, __NR_shmctl)
+#endif
diff --git a/tools/testing/selftests/powerpc/syscalls/ipc_unmuxed.c b/tools/testing/selftests/powerpc/syscalls/ipc_unmuxed.c
new file mode 100644
index 000000000000..2ac02706f8c8
--- /dev/null
+++ b/tools/testing/selftests/powerpc/syscalls/ipc_unmuxed.c
@@ -0,0 +1,61 @@
+/*
+ * Copyright 2015, Michael Ellerman, 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 simply tests that certain syscalls are implemented. It doesn't
+ * actually exercise their logic in any way.
+ */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+
+#include "utils.h"
+
+
+#define DO_TEST(_name, _num)	\
+static int test_##_name(void)			\
+{						\
+	int rc;					\
+	printf("Testing " #_name);		\
+	errno = 0;				\
+	rc = syscall(_num, -1, 0, 0, 0, 0, 0);	\
+	printf("\treturned %d, errno %d\n", rc, errno); \
+	return errno == ENOSYS;			\
+}
+
+#include "ipc.h"
+#undef DO_TEST
+
+static int ipc_unmuxed(void)
+{
+	int tests_done = 0;
+
+#define DO_TEST(_name, _num)		\
+	FAIL_IF(test_##_name());	\
+	tests_done++;
+
+#include "ipc.h"
+#undef DO_TEST
+
+	/*
+	 * If we ran no tests then it means none of the syscall numbers were
+	 * defined, possibly because we were built against old headers. But it
+	 * means we didn't really test anything, so instead of passing mark it
+	 * as a skip to give the user a clue.
+	 */
+	SKIP_IF(tests_done == 0);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(ipc_unmuxed, "ipc_unmuxed");
+}
diff --git a/tools/testing/selftests/powerpc/tm/tm-syscall.c b/tools/testing/selftests/powerpc/tm/tm-syscall.c
index 1276e23da63b..e835bf7ec7ae 100644
--- a/tools/testing/selftests/powerpc/tm/tm-syscall.c
+++ b/tools/testing/selftests/powerpc/tm/tm-syscall.c
@@ -77,13 +77,23 @@ pid_t getppid_tm(bool suspend)
 	exit(-1);
 }
 
+static inline bool have_htm_nosc(void)
+{
+#ifdef PPC_FEATURE2_HTM_NOSC
+	return ((long)get_auxv_entry(AT_HWCAP2) & PPC_FEATURE2_HTM_NOSC);
+#else
+	printf("PPC_FEATURE2_HTM_NOSC not defined, can't check AT_HWCAP2\n");
+	return false;
+#endif
+}
+
 int tm_syscall(void)
 {
 	unsigned count = 0;
 	struct timeval end, now;
 
-	SKIP_IF(!((long)get_auxv_entry(AT_HWCAP2)
-		  & PPC_FEATURE2_HTM_NOSC));
+	SKIP_IF(!have_htm_nosc());
+
 	setbuf(stdout, NULL);
 
 	printf("Testing transactional syscalls for %d seconds...\n", TEST_DURATION);
diff --git a/tools/testing/selftests/pstore/Makefile b/tools/testing/selftests/pstore/Makefile
new file mode 100644
index 000000000000..bd7abe24ea08
--- /dev/null
+++ b/tools/testing/selftests/pstore/Makefile
@@ -0,0 +1,15 @@
+# Makefile for pstore selftests.
+# Expects pstore backend is registered.
+
+all:
+
+TEST_PROGS := pstore_tests pstore_post_reboot_tests
+TEST_FILES := common_tests pstore_crash_test
+
+include ../lib.mk
+
+run_crash:
+	@sh pstore_crash_test || { echo "pstore_crash_test: [FAIL]"; exit 1; }
+
+clean:
+	rm -rf logs/* *uuid
diff --git a/tools/testing/selftests/pstore/common_tests b/tools/testing/selftests/pstore/common_tests
new file mode 100755
index 000000000000..3ea64d7cf1cd
--- /dev/null
+++ b/tools/testing/selftests/pstore/common_tests
@@ -0,0 +1,83 @@
+#!/bin/sh
+
+# common_tests - Shell script commonly used by pstore test scripts
+#
+# Copyright (C) Hitachi Ltd., 2015
+#  Written by Hiraku Toyooka <hiraku.toyooka.gu@hitachi.com>
+#
+# Released under the terms of the GPL v2.
+
+# Utilities
+errexit() { # message
+    echo "Error: $1" 1>&2
+    exit 1
+}
+
+absdir() { # file_path
+    (cd `dirname $1`; pwd)
+}
+
+show_result() { # result_value
+    if [ $1 -eq 0 ]; then
+	prlog "ok"
+    else
+	prlog "FAIL"
+	rc=1
+    fi
+}
+
+check_files_exist() { # type of pstorefs file
+    if [ -e ${1}-${backend}-0 ]; then
+	prlog "ok"
+	for f in `ls ${1}-${backend}-*`; do
+            prlog -e "\t${f}"
+	done
+    else
+	prlog "FAIL"
+	rc=1
+    fi
+}
+
+operate_files() { # tested value, files, operation
+    if [ $1 -eq 0 ]; then
+	prlog
+	for f in $2; do
+	    prlog -ne "\t${f} ... "
+	    # execute operation
+	    $3 $f
+	    show_result $?
+	done
+    else
+	prlog " ... FAIL"
+	rc=1
+    fi
+}
+
+# Parameters
+TEST_STRING_PATTERN="Testing pstore: uuid="
+UUID=`cat /proc/sys/kernel/random/uuid`
+TOP_DIR=`absdir $0`
+LOG_DIR=$TOP_DIR/logs/`date +%Y%m%d-%H%M%S`_${UUID}/
+REBOOT_FLAG=$TOP_DIR/reboot_flag
+
+# Preparing logs
+LOG_FILE=$LOG_DIR/`basename $0`.log
+mkdir -p $LOG_DIR || errexit "Failed to make a log directory: $LOG_DIR"
+date > $LOG_FILE
+prlog() { # messages
+    /bin/echo "$@" | tee -a $LOG_FILE
+}
+
+# Starting tests
+rc=0
+prlog "=== Pstore unit tests (`basename $0`) ==="
+prlog "UUID="$UUID
+
+prlog -n "Checking pstore backend is registered ... "
+backend=`cat /sys/module/pstore/parameters/backend`
+show_result $?
+prlog -e "\tbackend=${backend}"
+prlog -e "\tcmdline=`cat /proc/cmdline`"
+if [ $rc -ne 0 ]; then
+    exit 1
+fi
diff --git a/tools/testing/selftests/pstore/pstore_crash_test b/tools/testing/selftests/pstore/pstore_crash_test
new file mode 100755
index 000000000000..1a4afe5c12b6
--- /dev/null
+++ b/tools/testing/selftests/pstore/pstore_crash_test
@@ -0,0 +1,30 @@
+#!/bin/sh
+
+# pstore_crash_test - Pstore test shell script which causes crash and reboot
+#
+# Copyright (C) Hitachi Ltd., 2015
+#  Written by Hiraku Toyooka <hiraku.toyooka.gu@hitachi.com>
+#
+# Released under the terms of the GPL v2.
+
+# exit if pstore backend is not registered
+. ./common_tests
+
+prlog "Causing kernel crash ..."
+
+# enable all functions triggered by sysrq
+echo 1 > /proc/sys/kernel/sysrq
+# setting to reboot in 3 seconds after panic
+echo 3 > /proc/sys/kernel/panic
+
+# save uuid file by different name because next test execution will replace it.
+mv $TOP_DIR/uuid $TOP_DIR/prev_uuid
+
+# create a file as reboot flag
+touch $REBOOT_FLAG
+sync
+
+# cause crash
+# Note: If you use kdump and want to see kmesg-* files after reboot, you should
+#       specify 'crash_kexec_post_notifiers' in 1st kernel's cmdline.
+echo c > /proc/sysrq-trigger
diff --git a/tools/testing/selftests/pstore/pstore_post_reboot_tests b/tools/testing/selftests/pstore/pstore_post_reboot_tests
new file mode 100755
index 000000000000..6ccb154cb4aa
--- /dev/null
+++ b/tools/testing/selftests/pstore/pstore_post_reboot_tests
@@ -0,0 +1,77 @@
+#!/bin/sh
+
+# pstore_post_reboot_tests - Check pstore's behavior after crash/reboot
+#
+# Copyright (C) Hitachi Ltd., 2015
+#  Written by Hiraku Toyooka <hiraku.toyooka.gu@hitachi.com>
+#
+# Released under the terms of the GPL v2.
+
+. ./common_tests
+
+if [ -e $REBOOT_FLAG  ]; then
+    rm $REBOOT_FLAG
+else
+    prlog "pstore_crash_test has not been executed yet. we skip further tests."
+    exit 0
+fi
+
+prlog -n "Mounting pstore filesystem ... "
+mount_info=`grep pstore /proc/mounts`
+if [ $? -eq 0 ]; then
+    mount_point=`echo ${mount_info} | cut -d' ' -f2 | head -n1`
+    prlog "ok"
+else
+    mount none /sys/fs/pstore -t pstore
+    if [ $? -eq 0 ]; then
+	mount_point=`grep pstore /proc/mounts | cut -d' ' -f2 | head -n1`
+	prlog "ok"
+    else
+	prlog "FAIL"
+	exit 1
+    fi
+fi
+
+cd ${mount_point}
+
+prlog -n "Checking dmesg files exist in pstore filesystem ... "
+check_files_exist dmesg
+
+prlog -n "Checking console files exist in pstore filesystem ... "
+check_files_exist console
+
+prlog -n "Checking pmsg files exist in pstore filesystem ... "
+check_files_exist pmsg
+
+prlog -n "Checking dmesg files contain oops end marker"
+grep_end_trace() {
+    grep -q "\---\[ end trace" $1
+}
+files=`ls dmesg-${backend}-*`
+operate_files $? "$files" grep_end_trace
+
+prlog -n "Checking console file contains oops end marker ... "
+grep -q "\---\[ end trace" console-${backend}-0
+show_result $?
+
+prlog -n "Checking pmsg file properly keeps the content written before crash ... "
+prev_uuid=`cat $TOP_DIR/prev_uuid`
+if [ $? -eq 0 ]; then
+    nr_matched=`grep -c "$TEST_STRING_PATTERN" pmsg-${backend}-0`
+    if [ $nr_matched -eq 1 ]; then
+	grep -q "$TEST_STRING_PATTERN"$prev_uuid pmsg-${backend}-0
+	show_result $?
+    else
+	prlog "FAIL"
+	rc=1
+    fi
+else
+    prlog "FAIL"
+    rc=1
+fi
+
+prlog -n "Removing all files in pstore filesystem "
+files=`ls *-${backend}-*`
+operate_files $? "$files" rm
+
+exit $rc
diff --git a/tools/testing/selftests/pstore/pstore_tests b/tools/testing/selftests/pstore/pstore_tests
new file mode 100755
index 000000000000..f25d2a349a60
--- /dev/null
+++ b/tools/testing/selftests/pstore/pstore_tests
@@ -0,0 +1,30 @@
+#!/bin/sh
+
+# pstore_tests - Check pstore's behavior before crash/reboot
+#
+# Copyright (C) Hitachi Ltd., 2015
+#  Written by Hiraku Toyooka <hiraku.toyooka.gu@hitachi.com>
+#
+# Released under the terms of the GPL v2.
+
+. ./common_tests
+
+prlog -n "Checking pstore console is registered ... "
+dmesg | grep -q "console \[pstore"
+show_result $?
+
+prlog -n "Checking /dev/pmsg0 exists ... "
+test -e /dev/pmsg0
+show_result $?
+
+prlog -n "Writing unique string to /dev/pmsg0 ... "
+if [ -e "/dev/pmsg0" ]; then
+    echo "${TEST_STRING_PATTERN}""$UUID" > /dev/pmsg0
+    show_result $?
+    echo "$UUID" > $TOP_DIR/uuid
+else
+    prlog "FAIL"
+    rc=1
+fi
+
+exit $rc
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 770f47adf295..882fe83a3554 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -19,15 +19,19 @@
 #include <linux/prctl.h>
 #include <linux/ptrace.h>
 #include <linux/seccomp.h>
-#include <poll.h>
 #include <pthread.h>
 #include <semaphore.h>
 #include <signal.h>
 #include <stddef.h>
 #include <stdbool.h>
 #include <string.h>
+#include <time.h>
 #include <linux/elf.h>
 #include <sys/uio.h>
+#include <sys/utsname.h>
+#include <sys/fcntl.h>
+#include <sys/mman.h>
+#include <sys/times.h>
 
 #define _GNU_SOURCE
 #include <unistd.h>
@@ -428,14 +432,16 @@ TEST_SIGNAL(KILL_one, SIGSYS)
 
 TEST_SIGNAL(KILL_one_arg_one, SIGSYS)
 {
+	void *fatal_address;
 	struct sock_filter filter[] = {
 		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
 			offsetof(struct seccomp_data, nr)),
-		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 1, 0),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_times, 1, 0),
 		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
 		/* Only both with lower 32-bit for now. */
 		BPF_STMT(BPF_LD|BPF_W|BPF_ABS, syscall_arg(0)),
-		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, 0x0C0FFEE, 0, 1),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K,
+			(unsigned long)&fatal_address, 0, 1),
 		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL),
 		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
 	};
@@ -445,7 +451,8 @@ TEST_SIGNAL(KILL_one_arg_one, SIGSYS)
 	};
 	long ret;
 	pid_t parent = getppid();
-	pid_t pid = getpid();
+	struct tms timebuf;
+	clock_t clock = times(&timebuf);
 
 	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
 	ASSERT_EQ(0, ret);
@@ -454,17 +461,22 @@ TEST_SIGNAL(KILL_one_arg_one, SIGSYS)
 	ASSERT_EQ(0, ret);
 
 	EXPECT_EQ(parent, syscall(__NR_getppid));
-	EXPECT_EQ(pid, syscall(__NR_getpid));
-	/* getpid() should never return. */
-	EXPECT_EQ(0, syscall(__NR_getpid, 0x0C0FFEE));
+	EXPECT_LE(clock, syscall(__NR_times, &timebuf));
+	/* times() should never return. */
+	EXPECT_EQ(0, syscall(__NR_times, &fatal_address));
 }
 
 TEST_SIGNAL(KILL_one_arg_six, SIGSYS)
 {
+#ifndef __NR_mmap2
+	int sysno = __NR_mmap;
+#else
+	int sysno = __NR_mmap2;
+#endif
 	struct sock_filter filter[] = {
 		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
 			offsetof(struct seccomp_data, nr)),
-		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 1, 0),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, sysno, 1, 0),
 		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
 		/* Only both with lower 32-bit for now. */
 		BPF_STMT(BPF_LD|BPF_W|BPF_ABS, syscall_arg(5)),
@@ -478,7 +490,11 @@ TEST_SIGNAL(KILL_one_arg_six, SIGSYS)
 	};
 	long ret;
 	pid_t parent = getppid();
-	pid_t pid = getpid();
+	int fd;
+	void *map1, *map2;
+	int page_size = sysconf(_SC_PAGESIZE);
+
+	ASSERT_LT(0, page_size);
 
 	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
 	ASSERT_EQ(0, ret);
@@ -486,10 +502,22 @@ TEST_SIGNAL(KILL_one_arg_six, SIGSYS)
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
 	ASSERT_EQ(0, ret);
 
+	fd = open("/dev/zero", O_RDONLY);
+	ASSERT_NE(-1, fd);
+
 	EXPECT_EQ(parent, syscall(__NR_getppid));
-	EXPECT_EQ(pid, syscall(__NR_getpid));
-	/* getpid() should never return. */
-	EXPECT_EQ(0, syscall(__NR_getpid, 1, 2, 3, 4, 5, 0x0C0FFEE));
+	map1 = (void *)syscall(sysno,
+		NULL, page_size, PROT_READ, MAP_PRIVATE, fd, page_size);
+	EXPECT_NE(MAP_FAILED, map1);
+	/* mmap2() should never return. */
+	map2 = (void *)syscall(sysno,
+		 NULL, page_size, PROT_READ, MAP_PRIVATE, fd, 0x0C0FFEE);
+	EXPECT_EQ(MAP_FAILED, map2);
+
+	/* The test failed, so clean up the resources. */
+	munmap(map1, page_size);
+	munmap(map2, page_size);
+	close(fd);
 }
 
 /* TODO(wad) add 64-bit versus 32-bit arg tests. */
@@ -1247,8 +1275,8 @@ void change_syscall(struct __test_metadata *_metadata,
 	ret = ptrace(PTRACE_GETREGSET, tracee, NT_PRSTATUS, &iov);
 	EXPECT_EQ(0, ret);
 
-#if defined(__x86_64__) || defined(__i386__) || defined(__aarch64__) || \
-    defined(__powerpc__) || defined(__s390__)
+#if defined(__x86_64__) || defined(__i386__) || defined(__powerpc__) || \
+    defined(__s390__)
 	{
 		regs.SYSCALL_NUM = syscall;
 	}
@@ -1262,6 +1290,18 @@ void change_syscall(struct __test_metadata *_metadata,
 		EXPECT_EQ(0, ret);
 	}
 
+#elif defined(__aarch64__)
+# ifndef NT_ARM_SYSTEM_CALL
+#  define NT_ARM_SYSTEM_CALL 0x404
+# endif
+	{
+		iov.iov_base = &syscall;
+		iov.iov_len = sizeof(syscall);
+		ret = ptrace(PTRACE_SETREGSET, tracee, NT_ARM_SYSTEM_CALL,
+			     &iov);
+		EXPECT_EQ(0, ret);
+	}
+
 #else
 	ASSERT_EQ(1, 0) {
 		TH_LOG("How is the syscall changed on this architecture?");
@@ -1272,6 +1312,8 @@ void change_syscall(struct __test_metadata *_metadata,
 	if (syscall == -1)
 		regs.SYSCALL_RET = 1;
 
+	iov.iov_base = &regs;
+	iov.iov_len = sizeof(regs);
 	ret = ptrace(PTRACE_SETREGSET, tracee, NT_PRSTATUS, &iov);
 	EXPECT_EQ(0, ret);
 }
@@ -2005,20 +2047,25 @@ TEST(syscall_restart)
 		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 5, 0),
 		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_exit, 4, 0),
 		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_rt_sigreturn, 3, 0),
-		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_poll, 4, 0),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_nanosleep, 4, 0),
 		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_restart_syscall, 4, 0),
 
 		/* Allow __NR_write for easy logging. */
 		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_write, 0, 1),
 		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
 		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL),
-		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE|0x100), /* poll */
-		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE|0x200), /* restart */
+		/* The nanosleep jump target. */
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE|0x100),
+		/* The restart_syscall jump target. */
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE|0x200),
 	};
 	struct sock_fprog prog = {
 		.len = (unsigned short)ARRAY_SIZE(filter),
 		.filter = filter,
 	};
+#if defined(__arm__)
+	struct utsname utsbuf;
+#endif
 
 	ASSERT_EQ(0, pipe(pipefd));
 
@@ -2027,10 +2074,7 @@ TEST(syscall_restart)
 	if (child_pid == 0) {
 		/* Child uses EXPECT not ASSERT to deliver status correctly. */
 		char buf = ' ';
-		struct pollfd fds = {
-			.fd = pipefd[0],
-			.events = POLLIN,
-		};
+		struct timespec timeout = { };
 
 		/* Attach parent as tracer and stop. */
 		EXPECT_EQ(0, ptrace(PTRACE_TRACEME));
@@ -2054,10 +2098,11 @@ TEST(syscall_restart)
 			TH_LOG("Failed to get sync data from read()");
 		}
 
-		/* Start poll to be interrupted. */
+		/* Start nanosleep to be interrupted. */
+		timeout.tv_sec = 1;
 		errno = 0;
-		EXPECT_EQ(1, poll(&fds, 1, -1)) {
-			TH_LOG("Call to poll() failed (errno %d)", errno);
+		EXPECT_EQ(0, nanosleep(&timeout, NULL)) {
+			TH_LOG("Call to nanosleep() failed (errno %d)", errno);
 		}
 
 		/* Read final sync from parent. */
@@ -2082,14 +2127,14 @@ TEST(syscall_restart)
 	ASSERT_EQ(0, ptrace(PTRACE_CONT, child_pid, NULL, 0));
 	ASSERT_EQ(1, write(pipefd[1], ".", 1));
 
-	/* Wait for poll() to start. */
+	/* Wait for nanosleep() to start. */
 	ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0));
 	ASSERT_EQ(true, WIFSTOPPED(status));
 	ASSERT_EQ(SIGTRAP, WSTOPSIG(status));
 	ASSERT_EQ(PTRACE_EVENT_SECCOMP, (status >> 16));
 	ASSERT_EQ(0, ptrace(PTRACE_GETEVENTMSG, child_pid, NULL, &msg));
 	ASSERT_EQ(0x100, msg);
-	EXPECT_EQ(__NR_poll, get_syscall(_metadata, child_pid));
+	EXPECT_EQ(__NR_nanosleep, get_syscall(_metadata, child_pid));
 
 	/* Might as well check siginfo for sanity while we're here. */
 	ASSERT_EQ(0, ptrace(PTRACE_GETSIGINFO, child_pid, NULL, &info));
@@ -2100,7 +2145,7 @@ TEST(syscall_restart)
 	/* Verify signal delivery came from child (seccomp-triggered). */
 	EXPECT_EQ(child_pid, info.si_pid);
 
-	/* Interrupt poll with SIGSTOP (which we'll need to handle). */
+	/* Interrupt nanosleep with SIGSTOP (which we'll need to handle). */
 	ASSERT_EQ(0, kill(child_pid, SIGSTOP));
 	ASSERT_EQ(0, ptrace(PTRACE_CONT, child_pid, NULL, 0));
 	ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0));
@@ -2110,7 +2155,7 @@ TEST(syscall_restart)
 	ASSERT_EQ(0, ptrace(PTRACE_GETSIGINFO, child_pid, NULL, &info));
 	EXPECT_EQ(getpid(), info.si_pid);
 
-	/* Restart poll with SIGCONT, which triggers restart_syscall. */
+	/* Restart nanosleep with SIGCONT, which triggers restart_syscall. */
 	ASSERT_EQ(0, kill(child_pid, SIGCONT));
 	ASSERT_EQ(0, ptrace(PTRACE_CONT, child_pid, NULL, 0));
 	ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0));
@@ -2124,16 +2169,25 @@ TEST(syscall_restart)
 	ASSERT_EQ(SIGTRAP, WSTOPSIG(status));
 	ASSERT_EQ(PTRACE_EVENT_SECCOMP, (status >> 16));
 	ASSERT_EQ(0, ptrace(PTRACE_GETEVENTMSG, child_pid, NULL, &msg));
+
 	ASSERT_EQ(0x200, msg);
 	ret = get_syscall(_metadata, child_pid);
 #if defined(__arm__)
-	/* FIXME: ARM does not expose true syscall in registers. */
-	EXPECT_EQ(__NR_poll, ret);
-#else
-	EXPECT_EQ(__NR_restart_syscall, ret);
+	/*
+	 * FIXME:
+	 * - native ARM registers do NOT expose true syscall.
+	 * - compat ARM registers on ARM64 DO expose true syscall.
+	 */
+	ASSERT_EQ(0, uname(&utsbuf));
+	if (strncmp(utsbuf.machine, "arm", 3) == 0) {
+		EXPECT_EQ(__NR_nanosleep, ret);
+	} else
 #endif
+	{
+		EXPECT_EQ(__NR_restart_syscall, ret);
+	}
 
-	/* Write again to end poll. */
+	/* Write again to end test. */
 	ASSERT_EQ(0, ptrace(PTRACE_CONT, child_pid, NULL, 0));
 	ASSERT_EQ(1, write(pipefd[1], "!", 1));
 	EXPECT_EQ(0, close(pipefd[1]));
diff --git a/tools/testing/selftests/static_keys/test_static_keys.sh b/tools/testing/selftests/static_keys/test_static_keys.sh
index 1261e3fa1e3a..1261e3fa1e3a 100644..100755
--- a/tools/testing/selftests/static_keys/test_static_keys.sh
+++ b/tools/testing/selftests/static_keys/test_static_keys.sh
diff --git a/tools/testing/selftests/timers/nanosleep.c b/tools/testing/selftests/timers/nanosleep.c
index 8a3c29de7d49..ff942ff7c9b3 100644
--- a/tools/testing/selftests/timers/nanosleep.c
+++ b/tools/testing/selftests/timers/nanosleep.c
@@ -19,6 +19,7 @@
  *   GNU General Public License for more details.
  */
 
+#include <errno.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <time.h>
diff --git a/tools/testing/selftests/timers/rtctest.c b/tools/testing/selftests/timers/rtctest.c
index d80ae852334d..624bce51b27d 100644
--- a/tools/testing/selftests/timers/rtctest.c
+++ b/tools/testing/selftests/timers/rtctest.c
@@ -61,7 +61,7 @@ int main(int argc, char **argv)
 	/* Turn on update interrupts (one per second) */
 	retval = ioctl(fd, RTC_UIE_ON, 0);
 	if (retval == -1) {
-		if (errno == ENOTTY) {
+		if (errno == EINVAL) {
 			fprintf(stderr,
 				"\n...Update IRQs not supported.\n");
 			goto test_READ;
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 3c53cac15de1..e4bb1de1d526 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -5,6 +5,8 @@ BINARIES = compaction_test
 BINARIES += hugepage-mmap
 BINARIES += hugepage-shm
 BINARIES += map_hugetlb
+BINARIES += mlock2-tests
+BINARIES += on-fault-limit
 BINARIES += thuge-gen
 BINARIES += transhuge-stress
 BINARIES += userfaultfd
diff --git a/tools/testing/selftests/vm/mlock2-tests.c b/tools/testing/selftests/vm/mlock2-tests.c
new file mode 100644
index 000000000000..02ca5e0177c5
--- /dev/null
+++ b/tools/testing/selftests/vm/mlock2-tests.c
@@ -0,0 +1,737 @@
+#define _GNU_SOURCE
+#include <sys/mman.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <syscall.h>
+#include <errno.h>
+#include <stdbool.h>
+
+#ifndef MLOCK_ONFAULT
+#define MLOCK_ONFAULT 1
+#endif
+
+#ifndef MCL_ONFAULT
+#define MCL_ONFAULT (MCL_FUTURE << 1)
+#endif
+
+static int mlock2_(void *start, size_t len, int flags)
+{
+#ifdef __NR_mlock2
+	return syscall(__NR_mlock2, start, len, flags);
+#else
+	errno = ENOSYS;
+	return -1;
+#endif
+}
+
+struct vm_boundaries {
+	unsigned long start;
+	unsigned long end;
+};
+
+static int get_vm_area(unsigned long addr, struct vm_boundaries *area)
+{
+	FILE *file;
+	int ret = 1;
+	char line[1024] = {0};
+	char *end_addr;
+	char *stop;
+	unsigned long start;
+	unsigned long end;
+
+	if (!area)
+		return ret;
+
+	file = fopen("/proc/self/maps", "r");
+	if (!file) {
+		perror("fopen");
+		return ret;
+	}
+
+	memset(area, 0, sizeof(struct vm_boundaries));
+
+	while(fgets(line, 1024, file)) {
+		end_addr = strchr(line, '-');
+		if (!end_addr) {
+			printf("cannot parse /proc/self/maps\n");
+			goto out;
+		}
+		*end_addr = '\0';
+		end_addr++;
+		stop = strchr(end_addr, ' ');
+		if (!stop) {
+			printf("cannot parse /proc/self/maps\n");
+			goto out;
+		}
+		stop = '\0';
+
+		sscanf(line, "%lx", &start);
+		sscanf(end_addr, "%lx", &end);
+
+		if (start <= addr && end > addr) {
+			area->start = start;
+			area->end = end;
+			ret = 0;
+			goto out;
+		}
+	}
+out:
+	fclose(file);
+	return ret;
+}
+
+static uint64_t get_pageflags(unsigned long addr)
+{
+	FILE *file;
+	uint64_t pfn;
+	unsigned long offset;
+
+	file = fopen("/proc/self/pagemap", "r");
+	if (!file) {
+		perror("fopen pagemap");
+		_exit(1);
+	}
+
+	offset = addr / getpagesize() * sizeof(pfn);
+
+	if (fseek(file, offset, SEEK_SET)) {
+		perror("fseek pagemap");
+		_exit(1);
+	}
+
+	if (fread(&pfn, sizeof(pfn), 1, file) != 1) {
+		perror("fread pagemap");
+		_exit(1);
+	}
+
+	fclose(file);
+	return pfn;
+}
+
+static uint64_t get_kpageflags(unsigned long pfn)
+{
+	uint64_t flags;
+	FILE *file;
+
+	file = fopen("/proc/kpageflags", "r");
+	if (!file) {
+		perror("fopen kpageflags");
+		_exit(1);
+	}
+
+	if (fseek(file, pfn * sizeof(flags), SEEK_SET)) {
+		perror("fseek kpageflags");
+		_exit(1);
+	}
+
+	if (fread(&flags, sizeof(flags), 1, file) != 1) {
+		perror("fread kpageflags");
+		_exit(1);
+	}
+
+	fclose(file);
+	return flags;
+}
+
+static FILE *seek_to_smaps_entry(unsigned long addr)
+{
+	FILE *file;
+	char *line = NULL;
+	size_t size = 0;
+	unsigned long start, end;
+	char perms[5];
+	unsigned long offset;
+	char dev[32];
+	unsigned long inode;
+	char path[BUFSIZ];
+
+	file = fopen("/proc/self/smaps", "r");
+	if (!file) {
+		perror("fopen smaps");
+		_exit(1);
+	}
+
+	while (getline(&line, &size, file) > 0) {
+		if (sscanf(line, "%lx-%lx %s %lx %s %lu %s\n",
+			   &start, &end, perms, &offset, dev, &inode, path) < 6)
+			goto next;
+
+		if (start <= addr && addr < end)
+			goto out;
+
+next:
+		free(line);
+		line = NULL;
+		size = 0;
+	}
+
+	fclose(file);
+	file = NULL;
+
+out:
+	free(line);
+	return file;
+}
+
+#define VMFLAGS "VmFlags:"
+
+static bool is_vmflag_set(unsigned long addr, const char *vmflag)
+{
+	char *line = NULL;
+	char *flags;
+	size_t size = 0;
+	bool ret = false;
+	FILE *smaps;
+
+	smaps = seek_to_smaps_entry(addr);
+	if (!smaps) {
+		printf("Unable to parse /proc/self/smaps\n");
+		goto out;
+	}
+
+	while (getline(&line, &size, smaps) > 0) {
+		if (!strstr(line, VMFLAGS)) {
+			free(line);
+			line = NULL;
+			size = 0;
+			continue;
+		}
+
+		flags = line + strlen(VMFLAGS);
+		ret = (strstr(flags, vmflag) != NULL);
+		goto out;
+	}
+
+out:
+	free(line);
+	fclose(smaps);
+	return ret;
+}
+
+#define SIZE "Size:"
+#define RSS  "Rss:"
+#define LOCKED "lo"
+
+static bool is_vma_lock_on_fault(unsigned long addr)
+{
+	bool ret = false;
+	bool locked;
+	FILE *smaps = NULL;
+	unsigned long vma_size, vma_rss;
+	char *line = NULL;
+	char *value;
+	size_t size = 0;
+
+	locked = is_vmflag_set(addr, LOCKED);
+	if (!locked)
+		goto out;
+
+	smaps = seek_to_smaps_entry(addr);
+	if (!smaps) {
+		printf("Unable to parse /proc/self/smaps\n");
+		goto out;
+	}
+
+	while (getline(&line, &size, smaps) > 0) {
+		if (!strstr(line, SIZE)) {
+			free(line);
+			line = NULL;
+			size = 0;
+			continue;
+		}
+
+		value = line + strlen(SIZE);
+		if (sscanf(value, "%lu kB", &vma_size) < 1) {
+			printf("Unable to parse smaps entry for Size\n");
+			goto out;
+		}
+		break;
+	}
+
+	while (getline(&line, &size, smaps) > 0) {
+		if (!strstr(line, RSS)) {
+			free(line);
+			line = NULL;
+			size = 0;
+			continue;
+		}
+
+		value = line + strlen(RSS);
+		if (sscanf(value, "%lu kB", &vma_rss) < 1) {
+			printf("Unable to parse smaps entry for Rss\n");
+			goto out;
+		}
+		break;
+	}
+
+	ret = locked && (vma_rss < vma_size);
+out:
+	free(line);
+	if (smaps)
+		fclose(smaps);
+	return ret;
+}
+
+#define PRESENT_BIT     0x8000000000000000ULL
+#define PFN_MASK        0x007FFFFFFFFFFFFFULL
+#define UNEVICTABLE_BIT (1UL << 18)
+
+static int lock_check(char *map)
+{
+	unsigned long page_size = getpagesize();
+	uint64_t page1_flags, page2_flags;
+
+	page1_flags = get_pageflags((unsigned long)map);
+	page2_flags = get_pageflags((unsigned long)map + page_size);
+
+	/* Both pages should be present */
+	if (((page1_flags & PRESENT_BIT) == 0) ||
+	    ((page2_flags & PRESENT_BIT) == 0)) {
+		printf("Failed to make both pages present\n");
+		return 1;
+	}
+
+	page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+	page2_flags = get_kpageflags(page2_flags & PFN_MASK);
+
+	/* Both pages should be unevictable */
+	if (((page1_flags & UNEVICTABLE_BIT) == 0) ||
+	    ((page2_flags & UNEVICTABLE_BIT) == 0)) {
+		printf("Failed to make both pages unevictable\n");
+		return 1;
+	}
+
+	if (!is_vmflag_set((unsigned long)map, LOCKED)) {
+		printf("VMA flag %s is missing on page 1\n", LOCKED);
+		return 1;
+	}
+
+	if (!is_vmflag_set((unsigned long)map + page_size, LOCKED)) {
+		printf("VMA flag %s is missing on page 2\n", LOCKED);
+		return 1;
+	}
+
+	return 0;
+}
+
+static int unlock_lock_check(char *map)
+{
+	unsigned long page_size = getpagesize();
+	uint64_t page1_flags, page2_flags;
+
+	page1_flags = get_pageflags((unsigned long)map);
+	page2_flags = get_pageflags((unsigned long)map + page_size);
+	page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+	page2_flags = get_kpageflags(page2_flags & PFN_MASK);
+
+	if ((page1_flags & UNEVICTABLE_BIT) || (page2_flags & UNEVICTABLE_BIT)) {
+		printf("A page is still marked unevictable after unlock\n");
+		return 1;
+	}
+
+	if (is_vmflag_set((unsigned long)map, LOCKED)) {
+		printf("VMA flag %s is present on page 1 after unlock\n", LOCKED);
+		return 1;
+	}
+
+	if (is_vmflag_set((unsigned long)map + page_size, LOCKED)) {
+		printf("VMA flag %s is present on page 2 after unlock\n", LOCKED);
+		return 1;
+	}
+
+	return 0;
+}
+
+static int test_mlock_lock()
+{
+	char *map;
+	int ret = 1;
+	unsigned long page_size = getpagesize();
+
+	map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+		   MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+	if (map == MAP_FAILED) {
+		perror("test_mlock_locked mmap");
+		goto out;
+	}
+
+	if (mlock2_(map, 2 * page_size, 0)) {
+		if (errno == ENOSYS) {
+			printf("Cannot call new mlock family, skipping test\n");
+			_exit(0);
+		}
+		perror("mlock2(0)");
+		goto unmap;
+	}
+
+	if (lock_check(map))
+		goto unmap;
+
+	/* Now unlock and recheck attributes */
+	if (munlock(map, 2 * page_size)) {
+		perror("munlock()");
+		goto unmap;
+	}
+
+	ret = unlock_lock_check(map);
+
+unmap:
+	munmap(map, 2 * page_size);
+out:
+	return ret;
+}
+
+static int onfault_check(char *map)
+{
+	unsigned long page_size = getpagesize();
+	uint64_t page1_flags, page2_flags;
+
+	page1_flags = get_pageflags((unsigned long)map);
+	page2_flags = get_pageflags((unsigned long)map + page_size);
+
+	/* Neither page should be present */
+	if ((page1_flags & PRESENT_BIT) || (page2_flags & PRESENT_BIT)) {
+		printf("Pages were made present by MLOCK_ONFAULT\n");
+		return 1;
+	}
+
+	*map = 'a';
+	page1_flags = get_pageflags((unsigned long)map);
+	page2_flags = get_pageflags((unsigned long)map + page_size);
+
+	/* Only page 1 should be present */
+	if ((page1_flags & PRESENT_BIT) == 0) {
+		printf("Page 1 is not present after fault\n");
+		return 1;
+	} else if (page2_flags & PRESENT_BIT) {
+		printf("Page 2 was made present\n");
+		return 1;
+	}
+
+	page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+
+	/* Page 1 should be unevictable */
+	if ((page1_flags & UNEVICTABLE_BIT) == 0) {
+		printf("Failed to make faulted page unevictable\n");
+		return 1;
+	}
+
+	if (!is_vma_lock_on_fault((unsigned long)map)) {
+		printf("VMA is not marked for lock on fault\n");
+		return 1;
+	}
+
+	if (!is_vma_lock_on_fault((unsigned long)map + page_size)) {
+		printf("VMA is not marked for lock on fault\n");
+		return 1;
+	}
+
+	return 0;
+}
+
+static int unlock_onfault_check(char *map)
+{
+	unsigned long page_size = getpagesize();
+	uint64_t page1_flags;
+
+	page1_flags = get_pageflags((unsigned long)map);
+	page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+
+	if (page1_flags & UNEVICTABLE_BIT) {
+		printf("Page 1 is still marked unevictable after unlock\n");
+		return 1;
+	}
+
+	if (is_vma_lock_on_fault((unsigned long)map) ||
+	    is_vma_lock_on_fault((unsigned long)map + page_size)) {
+		printf("VMA is still lock on fault after unlock\n");
+		return 1;
+	}
+
+	return 0;
+}
+
+static int test_mlock_onfault()
+{
+	char *map;
+	int ret = 1;
+	unsigned long page_size = getpagesize();
+
+	map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+		   MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+	if (map == MAP_FAILED) {
+		perror("test_mlock_locked mmap");
+		goto out;
+	}
+
+	if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) {
+		if (errno == ENOSYS) {
+			printf("Cannot call new mlock family, skipping test\n");
+			_exit(0);
+		}
+		perror("mlock2(MLOCK_ONFAULT)");
+		goto unmap;
+	}
+
+	if (onfault_check(map))
+		goto unmap;
+
+	/* Now unlock and recheck attributes */
+	if (munlock(map, 2 * page_size)) {
+		if (errno == ENOSYS) {
+			printf("Cannot call new mlock family, skipping test\n");
+			_exit(0);
+		}
+		perror("munlock()");
+		goto unmap;
+	}
+
+	ret = unlock_onfault_check(map);
+unmap:
+	munmap(map, 2 * page_size);
+out:
+	return ret;
+}
+
+static int test_lock_onfault_of_present()
+{
+	char *map;
+	int ret = 1;
+	unsigned long page_size = getpagesize();
+	uint64_t page1_flags, page2_flags;
+
+	map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+		   MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+	if (map == MAP_FAILED) {
+		perror("test_mlock_locked mmap");
+		goto out;
+	}
+
+	*map = 'a';
+
+	if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) {
+		if (errno == ENOSYS) {
+			printf("Cannot call new mlock family, skipping test\n");
+			_exit(0);
+		}
+		perror("mlock2(MLOCK_ONFAULT)");
+		goto unmap;
+	}
+
+	page1_flags = get_pageflags((unsigned long)map);
+	page2_flags = get_pageflags((unsigned long)map + page_size);
+	page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+	page2_flags = get_kpageflags(page2_flags & PFN_MASK);
+
+	/* Page 1 should be unevictable */
+	if ((page1_flags & UNEVICTABLE_BIT) == 0) {
+		printf("Failed to make present page unevictable\n");
+		goto unmap;
+	}
+
+	if (!is_vma_lock_on_fault((unsigned long)map) ||
+	    !is_vma_lock_on_fault((unsigned long)map + page_size)) {
+		printf("VMA with present pages is not marked lock on fault\n");
+		goto unmap;
+	}
+	ret = 0;
+unmap:
+	munmap(map, 2 * page_size);
+out:
+	return ret;
+}
+
+static int test_munlockall()
+{
+	char *map;
+	int ret = 1;
+	unsigned long page_size = getpagesize();
+
+	map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+		   MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+
+	if (map == MAP_FAILED) {
+		perror("test_munlockall mmap");
+		goto out;
+	}
+
+	if (mlockall(MCL_CURRENT)) {
+		perror("mlockall(MCL_CURRENT)");
+		goto out;
+	}
+
+	if (lock_check(map))
+		goto unmap;
+
+	if (munlockall()) {
+		perror("munlockall()");
+		goto unmap;
+	}
+
+	if (unlock_lock_check(map))
+		goto unmap;
+
+	munmap(map, 2 * page_size);
+
+	map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+		   MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+
+	if (map == MAP_FAILED) {
+		perror("test_munlockall second mmap");
+		goto out;
+	}
+
+	if (mlockall(MCL_CURRENT | MCL_ONFAULT)) {
+		perror("mlockall(MCL_CURRENT | MCL_ONFAULT)");
+		goto unmap;
+	}
+
+	if (onfault_check(map))
+		goto unmap;
+
+	if (munlockall()) {
+		perror("munlockall()");
+		goto unmap;
+	}
+
+	if (unlock_onfault_check(map))
+		goto unmap;
+
+	if (mlockall(MCL_CURRENT | MCL_FUTURE)) {
+		perror("mlockall(MCL_CURRENT | MCL_FUTURE)");
+		goto out;
+	}
+
+	if (lock_check(map))
+		goto unmap;
+
+	if (munlockall()) {
+		perror("munlockall()");
+		goto unmap;
+	}
+
+	ret = unlock_lock_check(map);
+
+unmap:
+	munmap(map, 2 * page_size);
+out:
+	munlockall();
+	return ret;
+}
+
+static int test_vma_management(bool call_mlock)
+{
+	int ret = 1;
+	void *map;
+	unsigned long page_size = getpagesize();
+	struct vm_boundaries page1;
+	struct vm_boundaries page2;
+	struct vm_boundaries page3;
+
+	map = mmap(NULL, 3 * page_size, PROT_READ | PROT_WRITE,
+		   MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+	if (map == MAP_FAILED) {
+		perror("mmap()");
+		return ret;
+	}
+
+	if (call_mlock && mlock2_(map, 3 * page_size, MLOCK_ONFAULT)) {
+		if (errno == ENOSYS) {
+			printf("Cannot call new mlock family, skipping test\n");
+			_exit(0);
+		}
+		perror("mlock(ONFAULT)\n");
+		goto out;
+	}
+
+	if (get_vm_area((unsigned long)map, &page1) ||
+	    get_vm_area((unsigned long)map + page_size, &page2) ||
+	    get_vm_area((unsigned long)map + page_size * 2, &page3)) {
+		printf("couldn't find mapping in /proc/self/maps\n");
+		goto out;
+	}
+
+	/*
+	 * Before we unlock a portion, we need to that all three pages are in
+	 * the same VMA.  If they are not we abort this test (Note that this is
+	 * not a failure)
+	 */
+	if (page1.start != page2.start || page2.start != page3.start) {
+		printf("VMAs are not merged to start, aborting test\n");
+		ret = 0;
+		goto out;
+	}
+
+	if (munlock(map + page_size, page_size)) {
+		perror("munlock()");
+		goto out;
+	}
+
+	if (get_vm_area((unsigned long)map, &page1) ||
+	    get_vm_area((unsigned long)map + page_size, &page2) ||
+	    get_vm_area((unsigned long)map + page_size * 2, &page3)) {
+		printf("couldn't find mapping in /proc/self/maps\n");
+		goto out;
+	}
+
+	/* All three VMAs should be different */
+	if (page1.start == page2.start || page2.start == page3.start) {
+		printf("failed to split VMA for munlock\n");
+		goto out;
+	}
+
+	/* Now unlock the first and third page and check the VMAs again */
+	if (munlock(map, page_size * 3)) {
+		perror("munlock()");
+		goto out;
+	}
+
+	if (get_vm_area((unsigned long)map, &page1) ||
+	    get_vm_area((unsigned long)map + page_size, &page2) ||
+	    get_vm_area((unsigned long)map + page_size * 2, &page3)) {
+		printf("couldn't find mapping in /proc/self/maps\n");
+		goto out;
+	}
+
+	/* Now all three VMAs should be the same */
+	if (page1.start != page2.start || page2.start != page3.start) {
+		printf("failed to merge VMAs after munlock\n");
+		goto out;
+	}
+
+	ret = 0;
+out:
+	munmap(map, 3 * page_size);
+	return ret;
+}
+
+static int test_mlockall(int (test_function)(bool call_mlock))
+{
+	int ret = 1;
+
+	if (mlockall(MCL_CURRENT | MCL_ONFAULT | MCL_FUTURE)) {
+		perror("mlockall");
+		return ret;
+	}
+
+	ret = test_function(false);
+	munlockall();
+	return ret;
+}
+
+int main(int argc, char **argv)
+{
+	int ret = 0;
+	ret += test_mlock_lock();
+	ret += test_mlock_onfault();
+	ret += test_munlockall();
+	ret += test_lock_onfault_of_present();
+	ret += test_vma_management(true);
+	ret += test_mlockall(test_vma_management);
+	return ret;
+}
diff --git a/tools/testing/selftests/vm/on-fault-limit.c b/tools/testing/selftests/vm/on-fault-limit.c
new file mode 100644
index 000000000000..245acccce42d
--- /dev/null
+++ b/tools/testing/selftests/vm/on-fault-limit.c
@@ -0,0 +1,47 @@
+#include <sys/mman.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <string.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+
+#ifndef MCL_ONFAULT
+#define MCL_ONFAULT (MCL_FUTURE << 1)
+#endif
+
+static int test_limit(void)
+{
+	int ret = 1;
+	struct rlimit lims;
+	void *map;
+
+	if (getrlimit(RLIMIT_MEMLOCK, &lims)) {
+		perror("getrlimit");
+		return ret;
+	}
+
+	if (mlockall(MCL_CURRENT | MCL_ONFAULT | MCL_FUTURE)) {
+		perror("mlockall");
+		return ret;
+	}
+
+	map = mmap(NULL, 2 * lims.rlim_max, PROT_READ | PROT_WRITE,
+		   MAP_PRIVATE | MAP_ANONYMOUS | MAP_POPULATE, 0, 0);
+	if (map != MAP_FAILED)
+		printf("mmap should have failed, but didn't\n");
+	else {
+		ret = 0;
+		munmap(map, 2 * lims.rlim_max);
+	}
+
+	munlockall();
+	return ret;
+}
+
+int main(int argc, char **argv)
+{
+	int ret = 0;
+
+	ret += test_limit();
+	return ret;
+}
diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests
index 9179ce8df485..e11968b3677e 100755
--- a/tools/testing/selftests/vm/run_vmtests
+++ b/tools/testing/selftests/vm/run_vmtests
@@ -20,13 +20,26 @@ done < /proc/meminfo
 if [ -n "$freepgs" ] && [ -n "$pgsize" ]; then
 	nr_hugepgs=`cat /proc/sys/vm/nr_hugepages`
 	needpgs=`expr $needmem / $pgsize`
-	if [ $freepgs -lt $needpgs ]; then
+	tries=2
+	while [ $tries -gt 0 ] && [ $freepgs -lt $needpgs ]; do
 		lackpgs=$(( $needpgs - $freepgs ))
+		echo 3 > /proc/sys/vm/drop_caches
 		echo $(( $lackpgs + $nr_hugepgs )) > /proc/sys/vm/nr_hugepages
 		if [ $? -ne 0 ]; then
 			echo "Please run this test as root"
 			exit 1
 		fi
+		while read name size unit; do
+			if [ "$name" = "HugePages_Free:" ]; then
+				freepgs=$size
+			fi
+		done < /proc/meminfo
+		tries=$((tries - 1))
+	done
+	if [ $freepgs -lt $needpgs ]; then
+		printf "Not enough huge pages available (%d < %d)\n" \
+		       $freepgs $needpgs
+		exit 1
 	fi
 else
 	echo "no hugetlbfs support in kernel?"
@@ -106,4 +119,26 @@ else
 	echo "[PASS]"
 fi
 
+echo "--------------------"
+echo "running on-fault-limit"
+echo "--------------------"
+sudo -u nobody ./on-fault-limit
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+	exitcode=1
+else
+	echo "[PASS]"
+fi
+
+echo "--------------------"
+echo "running mlock2-tests"
+echo "--------------------"
+./mlock2-tests
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+	exitcode=1
+else
+	echo "[PASS]"
+fi
+
 exit $exitcode
diff --git a/tools/thermal/tmon/Makefile b/tools/thermal/tmon/Makefile
index 2e83dd3655a2..3a961e998281 100644
--- a/tools/thermal/tmon/Makefile
+++ b/tools/thermal/tmon/Makefile
@@ -22,6 +22,9 @@ TMON_LIBS += $(shell pkg-config --libs $(STATIC) panelw ncursesw 2> /dev/null ||
 		     pkg-config --libs $(STATIC) panel ncurses 2> /dev/null || \
 		     echo -lpanel -lncurses)
 
+CFLAGS    += $(shell pkg-config --cflags $(STATIC) panelw ncursesw 2> /dev/null || \
+		     pkg-config --cflags $(STATIC) panel ncurses 2> /dev/null)
+
 OBJS = tmon.o tui.o sysfs.o pid.o
 OBJS +=
 
diff --git a/tools/usb/testusb.c b/tools/usb/testusb.c
index 879f9870a6bc..0692d99b6d8f 100644
--- a/tools/usb/testusb.c
+++ b/tools/usb/testusb.c
@@ -394,7 +394,7 @@ int main (int argc, char **argv)
 	 *      low speed, interrupt    8 *  1     =     8
 	 */
 	param.iterations = 1000;
-	param.length = 512;
+	param.length = 1024;
 	param.vary = 512;
 	param.sglen = 32;
 
@@ -454,10 +454,10 @@ usage:
 			"\t-t testnum	only run specified case\n"
 			"\t-n		no test running, show devices to be tested\n"
 			"Case arguments:\n"
-			"\t-c iterations	default 1000\n"
-			"\t-s packetsize	default 512\n"
-			"\t-g sglen	default 32\n"
-			"\t-v vary		default 512\n",
+			"\t-c iterations		default 1000\n"
+			"\t-s transfer length	default 1024\n"
+			"\t-g sglen		default 32\n"
+			"\t-v vary			default 512\n",
 			argv[0]);
 		return 1;
 	}
diff --git a/tools/usb/usbip/src/usbip_detach.c b/tools/usb/usbip/src/usbip_detach.c
index 05c6d15856eb..9db9d21bb2ec 100644
--- a/tools/usb/usbip/src/usbip_detach.c
+++ b/tools/usb/usbip/src/usbip_detach.c
@@ -47,7 +47,9 @@ static int detach_port(char *port)
 	uint8_t portnum;
 	char path[PATH_MAX+1];
 
-	for (unsigned int i = 0; i < strlen(port); i++)
+	unsigned int port_len = strlen(port);
+
+	for (unsigned int i = 0; i < port_len; i++)
 		if (!isdigit(port[i])) {
 			err("invalid port %s", port);
 			return -1;
diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h
index 0a3da64638ce..4db7d5691ba7 100644
--- a/tools/virtio/linux/kernel.h
+++ b/tools/virtio/linux/kernel.h
@@ -110,4 +110,10 @@ static inline void free_page(unsigned long addr)
 	(void) (&_min1 == &_min2);		\
 	_min1 < _min2 ? _min1 : _min2; })
 
+/* TODO: empty stubs for now. Broken but enough for virtio_ring.c */
+#define list_add_tail(a, b) do {} while (0)
+#define list_del(a) do {} while (0)
+#define list_for_each_entry(a, b, c) while (0)
+/* end of stubs */
+
 #endif /* KERNEL_H */
diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h
index a3e07016a440..ee125e714053 100644
--- a/tools/virtio/linux/virtio.h
+++ b/tools/virtio/linux/virtio.h
@@ -3,12 +3,6 @@
 #include <linux/scatterlist.h>
 #include <linux/kernel.h>
 
-/* TODO: empty stubs for now. Broken but enough for virtio_ring.c */
-#define list_add_tail(a, b) do {} while (0)
-#define list_del(a) do {} while (0)
-#define list_for_each_entry(a, b, c) while (0)
-/* end of stubs */
-
 struct virtio_device {
 	void *dev;
 	u64 features;
diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h
index 806d683ab107..57a6964a1e35 100644
--- a/tools/virtio/linux/virtio_config.h
+++ b/tools/virtio/linux/virtio_config.h
@@ -40,33 +40,39 @@ static inline void __virtio_clear_bit(struct virtio_device *vdev,
 #define virtio_has_feature(dev, feature) \
 	(__virtio_test_bit((dev), feature))
 
+static inline bool virtio_is_little_endian(struct virtio_device *vdev)
+{
+	return virtio_has_feature(vdev, VIRTIO_F_VERSION_1) ||
+		virtio_legacy_is_little_endian();
+}
+
+/* Memory accessors */
 static inline u16 virtio16_to_cpu(struct virtio_device *vdev, __virtio16 val)
 {
-	return __virtio16_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+	return __virtio16_to_cpu(virtio_is_little_endian(vdev), val);
 }
 
 static inline __virtio16 cpu_to_virtio16(struct virtio_device *vdev, u16 val)
 {
-	return __cpu_to_virtio16(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+	return __cpu_to_virtio16(virtio_is_little_endian(vdev), val);
 }
 
 static inline u32 virtio32_to_cpu(struct virtio_device *vdev, __virtio32 val)
 {
-	return __virtio32_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+	return __virtio32_to_cpu(virtio_is_little_endian(vdev), val);
 }
 
 static inline __virtio32 cpu_to_virtio32(struct virtio_device *vdev, u32 val)
 {
-	return __cpu_to_virtio32(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+	return __cpu_to_virtio32(virtio_is_little_endian(vdev), val);
 }
 
 static inline u64 virtio64_to_cpu(struct virtio_device *vdev, __virtio64 val)
 {
-	return __virtio64_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+	return __virtio64_to_cpu(virtio_is_little_endian(vdev), val);
 }
 
 static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
 {
-	return __cpu_to_virtio64(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+	return __cpu_to_virtio64(virtio_is_little_endian(vdev), val);
 }
-
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index bcf5ec760eb9..5a6016224bb9 100644
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -128,6 +128,7 @@ static const char * const page_flag_names[] = {
 	[KPF_THP]		= "t:thp",
 	[KPF_BALLOON]		= "o:balloon",
 	[KPF_ZERO_PAGE]		= "z:zero_page",
+	[KPF_IDLE]              = "i:idle_page",
 
 	[KPF_RESERVED]		= "r:reserved",
 	[KPF_MLOCKED]		= "m:mlocked",
diff --git a/tools/vm/slabinfo-gnuplot.sh b/tools/vm/slabinfo-gnuplot.sh
new file mode 100644
index 000000000000..35b039864b77
--- /dev/null
+++ b/tools/vm/slabinfo-gnuplot.sh
@@ -0,0 +1,275 @@
+#!/bin/sh
+
+# Sergey Senozhatsky, 2015
+# sergey.senozhatsky.work@gmail.com
+#
+# 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.
+
+
+# This program is intended to plot a `slabinfo -X' stats, collected,
+# for example, using the following command:
+#   while [ 1 ]; do slabinfo -X >> stats; sleep 1; done
+#
+# Use `slabinfo-gnuplot.sh stats' to pre-process collected records
+# and generate graphs (totals, slabs sorted by size, slabs sorted
+# by size).
+#
+# Graphs can be [individually] regenerate with different ranges and
+# size (-r %d,%d and -s %d,%d options).
+#
+# To visually compare N `totals' graphs, do
+# slabinfo-gnuplot.sh -t FILE1-totals FILE2-totals ... FILEN-totals
+#
+
+min_slab_name_size=11
+xmin=0
+xmax=0
+width=1500
+height=700
+mode=preprocess
+
+usage()
+{
+	echo "Usage: [-s W,H] [-r MIN,MAX] [-t|-l] FILE1 [FILE2 ..]"
+	echo "FILEs must contain 'slabinfo -X' samples"
+	echo "-t 			- plot totals for FILE(s)"
+	echo "-l 			- plot slabs stats for FILE(s)"
+	echo "-s %d,%d		- set image width and height"
+	echo "-r %d,%d		- use data samples from a given range"
+}
+
+check_file_exist()
+{
+	if [ ! -f "$1" ]; then
+		echo "File '$1' does not exist"
+		exit 1
+	fi
+}
+
+do_slabs_plotting()
+{
+	local file=$1
+	local out_file
+	local range="every ::$xmin"
+	local xtic=""
+	local xtic_rotate="norotate"
+	local lines=2000000
+	local wc_lines
+
+	check_file_exist "$file"
+
+	out_file=`basename "$file"`
+	if [ $xmax -ne 0 ]; then
+		range="$range::$xmax"
+		lines=$((xmax-xmin))
+	fi
+
+	wc_lines=`cat "$file" | wc -l`
+	if [ $? -ne 0 ] || [ "$wc_lines" -eq 0 ] ; then
+		wc_lines=$lines
+	fi
+
+	if [ "$wc_lines" -lt "$lines" ]; then
+		lines=$wc_lines
+	fi
+
+	if [ $((width / lines)) -gt $min_slab_name_size ]; then
+		xtic=":xtic(1)"
+		xtic_rotate=90
+	fi
+
+gnuplot -p << EOF
+#!/usr/bin/env gnuplot
+
+set terminal png enhanced size $width,$height large
+set output '$out_file.png'
+set autoscale xy
+set xlabel 'samples'
+set ylabel 'bytes'
+set style histogram columnstacked title textcolor lt -1
+set style fill solid 0.15
+set xtics rotate $xtic_rotate
+set key left above Left title reverse
+
+plot "$file" $range u 2$xtic title 'SIZE' with boxes,\
+	'' $range u 3 title 'LOSS' with boxes
+EOF
+
+	if [ $? -eq 0 ]; then
+		echo "$out_file.png"
+	fi
+}
+
+do_totals_plotting()
+{
+	local gnuplot_cmd=""
+	local range="every ::$xmin"
+	local file=""
+
+	if [ $xmax -ne 0 ]; then
+		range="$range::$xmax"
+	fi
+
+	for i in "${t_files[@]}"; do
+		check_file_exist "$i"
+
+		file="$file"`basename "$i"`
+		gnuplot_cmd="$gnuplot_cmd '$i' $range using 1 title\
+			'$i Memory usage' with lines,"
+		gnuplot_cmd="$gnuplot_cmd '' $range using 2 title \
+			'$i Loss' with lines,"
+	done
+
+gnuplot -p << EOF
+#!/usr/bin/env gnuplot
+
+set terminal png enhanced size $width,$height large
+set autoscale xy
+set output '$file.png'
+set xlabel 'samples'
+set ylabel 'bytes'
+set key left above Left title reverse
+
+plot $gnuplot_cmd
+EOF
+
+	if [ $? -eq 0 ]; then
+		echo "$file.png"
+	fi
+}
+
+do_preprocess()
+{
+	local out
+	local lines
+	local in=$1
+
+	check_file_exist "$in"
+
+	# use only 'TOP' slab (biggest memory usage or loss)
+	let lines=3
+	out=`basename "$in"`"-slabs-by-loss"
+	`cat "$in" | grep -A "$lines" 'Slabs sorted by loss' |\
+		egrep -iv '\-\-|Name|Slabs'\
+		| awk '{print $1" "$4+$2*$3" "$4}' > "$out"`
+	if [ $? -eq 0 ]; then
+		do_slabs_plotting "$out"
+	fi
+
+	let lines=3
+	out=`basename "$in"`"-slabs-by-size"
+	`cat "$in" | grep -A "$lines" 'Slabs sorted by size' |\
+		egrep -iv '\-\-|Name|Slabs'\
+		| awk '{print $1" "$4" "$4-$2*$3}' > "$out"`
+	if [ $? -eq 0 ]; then
+		do_slabs_plotting "$out"
+	fi
+
+	out=`basename "$in"`"-totals"
+	`cat "$in" | grep "Memory used" |\
+		awk '{print $3" "$7}' > "$out"`
+	if [ $? -eq 0 ]; then
+		t_files[0]=$out
+		do_totals_plotting
+	fi
+}
+
+parse_opts()
+{
+	local opt
+
+	while getopts "tlr::s::h" opt; do
+		case $opt in
+			t)
+				mode=totals
+				;;
+			l)
+				mode=slabs
+				;;
+			s)
+				array=(${OPTARG//,/ })
+				width=${array[0]}
+				height=${array[1]}
+				;;
+			r)
+				array=(${OPTARG//,/ })
+				xmin=${array[0]}
+				xmax=${array[1]}
+				;;
+			h)
+				usage
+				exit 0
+				;;
+			\?)
+				echo "Invalid option: -$OPTARG" >&2
+				exit 1
+				;;
+			:)
+				echo "-$OPTARG requires an argument." >&2
+				exit 1
+				;;
+		esac
+	done
+
+	return $OPTIND
+}
+
+parse_args()
+{
+	local idx=0
+	local p
+
+	for p in "$@"; do
+		case $mode in
+			preprocess)
+				files[$idx]=$p
+				idx=$idx+1
+				;;
+			totals)
+				t_files[$idx]=$p
+				idx=$idx+1
+				;;
+			slabs)
+				files[$idx]=$p
+				idx=$idx+1
+				;;
+		esac
+	done
+}
+
+parse_opts "$@"
+argstart=$?
+parse_args "${@:$argstart}"
+
+if [ ${#files[@]} -eq 0 ] && [ ${#t_files[@]} -eq 0 ]; then
+	usage
+	exit 1
+fi
+
+case $mode in
+	preprocess)
+		for i in "${files[@]}"; do
+			do_preprocess "$i"
+		done
+		;;
+	totals)
+		do_totals_plotting
+		;;
+	slabs)
+		for i in "${files[@]}"; do
+			do_slabs_plotting "$i"
+		done
+		;;
+	*)
+		echo "Unknown mode $mode" >&2
+		usage
+		exit 1
+	;;
+esac
diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c
index 808d5a9d5dcf..86e698d07e20 100644
--- a/tools/vm/slabinfo.c
+++ b/tools/vm/slabinfo.c
@@ -53,39 +53,43 @@ struct aliasinfo {
 	struct slabinfo *slab;
 } aliasinfo[MAX_ALIASES];
 
-int slabs = 0;
-int actual_slabs = 0;
-int aliases = 0;
-int alias_targets = 0;
-int highest_node = 0;
+int slabs;
+int actual_slabs;
+int aliases;
+int alias_targets;
+int highest_node;
 
 char buffer[4096];
 
-int show_empty = 0;
-int show_report = 0;
-int show_alias = 0;
-int show_slab = 0;
+int show_empty;
+int show_report;
+int show_alias;
+int show_slab;
 int skip_zero = 1;
-int show_numa = 0;
-int show_track = 0;
-int show_first_alias = 0;
-int validate = 0;
-int shrink = 0;
-int show_inverted = 0;
-int show_single_ref = 0;
-int show_totals = 0;
-int sort_size = 0;
-int sort_active = 0;
-int set_debug = 0;
-int show_ops = 0;
-int show_activity = 0;
+int show_numa;
+int show_track;
+int show_first_alias;
+int validate;
+int shrink;
+int show_inverted;
+int show_single_ref;
+int show_totals;
+int sort_size;
+int sort_active;
+int set_debug;
+int show_ops;
+int show_activity;
+int output_lines = -1;
+int sort_loss;
+int extended_totals;
+int show_bytes;
 
 /* Debug options */
-int sanity = 0;
-int redzone = 0;
-int poison = 0;
-int tracking = 0;
-int tracing = 0;
+int sanity;
+int redzone;
+int poison;
+int tracking;
+int tracing;
 
 int page_size;
 
@@ -124,6 +128,10 @@ static void usage(void)
 		"-v|--validate          Validate slabs\n"
 		"-z|--zero              Include empty slabs\n"
 		"-1|--1ref              Single reference\n"
+		"-N|--lines=K           Show the first K slabs\n"
+		"-L|--Loss              Sort by loss\n"
+		"-X|--Xtotals           Show extended summary information\n"
+		"-B|--Bytes             Show size in bytes\n"
 		"\nValid debug options (FZPUT may be combined)\n"
 		"a / A          Switch on all debug options (=FZUP)\n"
 		"-              Switch off all debug options\n"
@@ -225,15 +233,17 @@ static int store_size(char *buffer, unsigned long value)
 	char trailer = 0;
 	int n;
 
-	if (value > 1000000000UL) {
-		divisor = 100000000UL;
-		trailer = 'G';
-	} else if (value > 1000000UL) {
-		divisor = 100000UL;
-		trailer = 'M';
-	} else if (value > 1000UL) {
-		divisor = 100;
-		trailer = 'K';
+	if (!show_bytes) {
+		if (value > 1000000000UL) {
+			divisor = 100000000UL;
+			trailer = 'G';
+		} else if (value > 1000000UL) {
+			divisor = 100000UL;
+			trailer = 'M';
+		} else if (value > 1000UL) {
+			divisor = 100;
+			trailer = 'K';
+		}
 	}
 
 	value /= divisor;
@@ -297,10 +307,12 @@ int line = 0;
 static void first_line(void)
 {
 	if (show_activity)
-		printf("Name                   Objects      Alloc       Free   %%Fast Fallb O CmpX   UL\n");
+		printf("Name                   Objects      Alloc       Free"
+			"   %%Fast Fallb O CmpX   UL\n");
 	else
-		printf("Name                   Objects Objsize    Space "
-			"Slabs/Part/Cpu  O/S O %%Fr %%Ef Flg\n");
+		printf("Name                   Objects Objsize           %s "
+			"Slabs/Part/Cpu  O/S O %%Fr %%Ef Flg\n",
+			sort_loss ? " Loss" : "Space");
 }
 
 /*
@@ -333,6 +345,11 @@ static unsigned long slab_activity(struct slabinfo *s)
 		s->alloc_slowpath + s->free_slowpath;
 }
 
+static unsigned long slab_waste(struct slabinfo *s)
+{
+	return	slab_size(s) - s->objects * s->object_size;
+}
+
 static void slab_numa(struct slabinfo *s, int mode)
 {
 	int node;
@@ -504,7 +521,7 @@ static void report(struct slabinfo *s)
 	if (strcmp(s->name, "*") == 0)
 		return;
 
-	printf("\nSlabcache: %-20s  Aliases: %2d Order : %2d Objects: %lu\n",
+	printf("\nSlabcache: %-15s  Aliases: %2d Order : %2d Objects: %lu\n",
 		s->name, s->aliases, s->order, s->objects);
 	if (s->hwcache_align)
 		printf("** Hardware cacheline aligned\n");
@@ -561,7 +578,10 @@ static void slabcache(struct slabinfo *s)
 	if (show_empty && s->slabs)
 		return;
 
-	store_size(size_str, slab_size(s));
+	if (sort_loss == 0)
+		store_size(size_str, slab_size(s));
+	else
+		store_size(size_str, slab_waste(s));
 	snprintf(dist_str, 40, "%lu/%lu/%d", s->slabs - s->cpu_slabs,
 						s->partial, s->cpu_slabs);
 
@@ -602,15 +622,15 @@ static void slabcache(struct slabinfo *s)
 			total_free ? (s->free_fastpath * 100 / total_free) : 0,
 			s->order_fallback, s->order, s->cmpxchg_double_fail,
 			s->cmpxchg_double_cpu_fail);
-	}
-	else
-		printf("%-21s %8ld %7d %8s %14s %4d %1d %3ld %3ld %s\n",
+	} else {
+		printf("%-21s %8ld %7d %15s %14s %4d %1d %3ld %3ld %s\n",
 			s->name, s->objects, s->object_size, size_str, dist_str,
 			s->objs_per_slab, s->order,
 			s->slabs ? (s->partial * 100) / s->slabs : 100,
 			s->slabs ? (s->objects * s->object_size * 100) /
 				(s->slabs * (page_size << s->order)) : 100,
 			flags);
+	}
 }
 
 /*
@@ -918,84 +938,88 @@ static void totals(void)
 
 	printf("Slabcache Totals\n");
 	printf("----------------\n");
-	printf("Slabcaches : %3d      Aliases  : %3d->%-3d Active: %3d\n",
+	printf("Slabcaches : %15d   Aliases  : %11d->%-3d  Active:    %3d\n",
 			slabs, aliases, alias_targets, used_slabs);
 
 	store_size(b1, total_size);store_size(b2, total_waste);
 	store_size(b3, total_waste * 100 / total_used);
-	printf("Memory used: %6s   # Loss   : %6s   MRatio:%6s%%\n", b1, b2, b3);
+	printf("Memory used: %15s   # Loss   : %15s   MRatio:%6s%%\n", b1, b2, b3);
 
 	store_size(b1, total_objects);store_size(b2, total_partobj);
 	store_size(b3, total_partobj * 100 / total_objects);
-	printf("# Objects  : %6s   # PartObj: %6s   ORatio:%6s%%\n", b1, b2, b3);
+	printf("# Objects  : %15s   # PartObj: %15s   ORatio:%6s%%\n", b1, b2, b3);
 
 	printf("\n");
-	printf("Per Cache    Average         Min         Max       Total\n");
-	printf("---------------------------------------------------------\n");
+	printf("Per Cache         Average              "
+		"Min              Max            Total\n");
+	printf("---------------------------------------"
+		"-------------------------------------\n");
 
 	store_size(b1, avg_objects);store_size(b2, min_objects);
 	store_size(b3, max_objects);store_size(b4, total_objects);
-	printf("#Objects  %10s  %10s  %10s  %10s\n",
+	printf("#Objects  %15s  %15s  %15s  %15s\n",
 			b1,	b2,	b3,	b4);
 
 	store_size(b1, avg_slabs);store_size(b2, min_slabs);
 	store_size(b3, max_slabs);store_size(b4, total_slabs);
-	printf("#Slabs    %10s  %10s  %10s  %10s\n",
+	printf("#Slabs    %15s  %15s  %15s  %15s\n",
 			b1,	b2,	b3,	b4);
 
 	store_size(b1, avg_partial);store_size(b2, min_partial);
 	store_size(b3, max_partial);store_size(b4, total_partial);
-	printf("#PartSlab %10s  %10s  %10s  %10s\n",
+	printf("#PartSlab %15s  %15s  %15s  %15s\n",
 			b1,	b2,	b3,	b4);
 	store_size(b1, avg_ppart);store_size(b2, min_ppart);
 	store_size(b3, max_ppart);
 	store_size(b4, total_partial * 100  / total_slabs);
-	printf("%%PartSlab%10s%% %10s%% %10s%% %10s%%\n",
+	printf("%%PartSlab%15s%% %15s%% %15s%% %15s%%\n",
 			b1,	b2,	b3,	b4);
 
 	store_size(b1, avg_partobj);store_size(b2, min_partobj);
 	store_size(b3, max_partobj);
 	store_size(b4, total_partobj);
-	printf("PartObjs  %10s  %10s  %10s  %10s\n",
+	printf("PartObjs  %15s  %15s  %15s  %15s\n",
 			b1,	b2,	b3,	b4);
 
 	store_size(b1, avg_ppartobj);store_size(b2, min_ppartobj);
 	store_size(b3, max_ppartobj);
 	store_size(b4, total_partobj * 100 / total_objects);
-	printf("%% PartObj%10s%% %10s%% %10s%% %10s%%\n",
+	printf("%% PartObj%15s%% %15s%% %15s%% %15s%%\n",
 			b1,	b2,	b3,	b4);
 
 	store_size(b1, avg_size);store_size(b2, min_size);
 	store_size(b3, max_size);store_size(b4, total_size);
-	printf("Memory    %10s  %10s  %10s  %10s\n",
+	printf("Memory    %15s  %15s  %15s  %15s\n",
 			b1,	b2,	b3,	b4);
 
 	store_size(b1, avg_used);store_size(b2, min_used);
 	store_size(b3, max_used);store_size(b4, total_used);
-	printf("Used      %10s  %10s  %10s  %10s\n",
+	printf("Used      %15s  %15s  %15s  %15s\n",
 			b1,	b2,	b3,	b4);
 
 	store_size(b1, avg_waste);store_size(b2, min_waste);
 	store_size(b3, max_waste);store_size(b4, total_waste);
-	printf("Loss      %10s  %10s  %10s  %10s\n",
+	printf("Loss      %15s  %15s  %15s  %15s\n",
 			b1,	b2,	b3,	b4);
 
 	printf("\n");
-	printf("Per Object   Average         Min         Max\n");
-	printf("---------------------------------------------\n");
+	printf("Per Object        Average              "
+		"Min              Max\n");
+	printf("---------------------------------------"
+		"--------------------\n");
 
 	store_size(b1, avg_memobj);store_size(b2, min_memobj);
 	store_size(b3, max_memobj);
-	printf("Memory    %10s  %10s  %10s\n",
+	printf("Memory    %15s  %15s  %15s\n",
 			b1,	b2,	b3);
 	store_size(b1, avg_objsize);store_size(b2, min_objsize);
 	store_size(b3, max_objsize);
-	printf("User      %10s  %10s  %10s\n",
+	printf("User      %15s  %15s  %15s\n",
 			b1,	b2,	b3);
 
 	store_size(b1, avg_objwaste);store_size(b2, min_objwaste);
 	store_size(b3, max_objwaste);
-	printf("Loss      %10s  %10s  %10s\n",
+	printf("Loss      %15s  %15s  %15s\n",
 			b1,	b2,	b3);
 }
 
@@ -1011,6 +1035,8 @@ static void sort_slabs(void)
 				result = slab_size(s1) < slab_size(s2);
 			else if (sort_active)
 				result = slab_activity(s1) < slab_activity(s2);
+			else if (sort_loss)
+				result = slab_waste(s1) < slab_waste(s2);
 			else
 				result = strcasecmp(s1->name, s2->name);
 
@@ -1095,7 +1121,7 @@ static void alias(void)
 			active = a->slab->name;
 		}
 		else
-			printf("%-20s -> %s\n", a->name, a->slab->name);
+			printf("%-15s -> %s\n", a->name, a->slab->name);
 	}
 	if (active)
 		printf("\n");
@@ -1241,12 +1267,16 @@ static void read_slab_dir(void)
 static void output_slabs(void)
 {
 	struct slabinfo *slab;
+	int lines = output_lines;
 
-	for (slab = slabinfo; slab < slabinfo + slabs; slab++) {
+	for (slab = slabinfo; (slab < slabinfo + slabs) &&
+			lines != 0; slab++) {
 
 		if (slab->alias)
 			continue;
 
+		if (lines != -1)
+			lines--;
 
 		if (show_numa)
 			slab_numa(slab, 0);
@@ -1267,24 +1297,54 @@ static void output_slabs(void)
 	}
 }
 
+static void xtotals(void)
+{
+	totals();
+
+	link_slabs();
+	rename_slabs();
+
+	printf("\nSlabs sorted by size\n");
+	printf("--------------------\n");
+	sort_loss = 0;
+	sort_size = 1;
+	sort_slabs();
+	output_slabs();
+
+	printf("\nSlabs sorted by loss\n");
+	printf("--------------------\n");
+	line = 0;
+	sort_loss = 1;
+	sort_size = 0;
+	sort_slabs();
+	output_slabs();
+	printf("\n");
+}
+
 struct option opts[] = {
-	{ "aliases", 0, NULL, 'a' },
-	{ "activity", 0, NULL, 'A' },
-	{ "debug", 2, NULL, 'd' },
-	{ "display-activity", 0, NULL, 'D' },
-	{ "empty", 0, NULL, 'e' },
-	{ "first-alias", 0, NULL, 'f' },
-	{ "help", 0, NULL, 'h' },
-	{ "inverted", 0, NULL, 'i'},
-	{ "numa", 0, NULL, 'n' },
-	{ "ops", 0, NULL, 'o' },
-	{ "report", 0, NULL, 'r' },
-	{ "shrink", 0, NULL, 's' },
-	{ "slabs", 0, NULL, 'l' },
-	{ "track", 0, NULL, 't'},
-	{ "validate", 0, NULL, 'v' },
-	{ "zero", 0, NULL, 'z' },
-	{ "1ref", 0, NULL, '1'},
+	{ "aliases", no_argument, NULL, 'a' },
+	{ "activity", no_argument, NULL, 'A' },
+	{ "debug", optional_argument, NULL, 'd' },
+	{ "display-activity", no_argument, NULL, 'D' },
+	{ "empty", no_argument, NULL, 'e' },
+	{ "first-alias", no_argument, NULL, 'f' },
+	{ "help", no_argument, NULL, 'h' },
+	{ "inverted", no_argument, NULL, 'i'},
+	{ "slabs", no_argument, NULL, 'l' },
+	{ "numa", no_argument, NULL, 'n' },
+	{ "ops", no_argument, NULL, 'o' },
+	{ "shrink", no_argument, NULL, 's' },
+	{ "report", no_argument, NULL, 'r' },
+	{ "Size", no_argument, NULL, 'S'},
+	{ "tracking", no_argument, NULL, 't'},
+	{ "Totals", no_argument, NULL, 'T'},
+	{ "validate", no_argument, NULL, 'v' },
+	{ "zero", no_argument, NULL, 'z' },
+	{ "1ref", no_argument, NULL, '1'},
+	{ "lines", required_argument, NULL, 'N'},
+	{ "Loss", no_argument, NULL, 'L'},
+	{ "Xtotals", no_argument, NULL, 'X'},
+	{ "Bytes", no_argument, NULL, 'B'},
 	{ NULL, 0, NULL, 0 }
 };
 
@@ -1296,7 +1356,7 @@ int main(int argc, char *argv[])
 
 	page_size = getpagesize();
 
-	while ((c = getopt_long(argc, argv, "aAd::Defhil1noprstvzTS",
+	while ((c = getopt_long(argc, argv, "aAd::Defhil1noprstvzTSN:LXB",
 						opts, NULL)) != -1)
 		switch (c) {
 		case '1':
@@ -1358,7 +1418,25 @@ int main(int argc, char *argv[])
 		case 'S':
 			sort_size = 1;
 			break;
-
+		case 'N':
+			if (optarg) {
+				output_lines = atoi(optarg);
+				if (output_lines < 1)
+					output_lines = 1;
+			}
+			break;
+		case 'L':
+			sort_loss = 1;
+			break;
+		case 'X':
+			if (output_lines == -1)
+				output_lines = 1;
+			extended_totals = 1;
+			show_bytes = 1;
+			break;
+		case 'B':
+			show_bytes = 1;
+			break;
 		default:
 			fatal("%s: Invalid option '%c'\n", argv[0], optopt);
 
@@ -1378,12 +1456,13 @@ int main(int argc, char *argv[])
 		fatal("%s: Invalid pattern '%s' code %d\n",
 			argv[0], pattern_source, err);
 	read_slab_dir();
-	if (show_alias)
+	if (show_alias) {
 		alias();
-	else
-	if (show_totals)
+	} else if (extended_totals) {
+		xtotals();
+	} else if (show_totals) {
 		totals();
-	else {
+	} else {
 		link_slabs();
 		rename_slabs();
 		sort_slabs();