Merge branch 'github.com/Freescale/linux-fslc/4.14-2.0.x-imx' into toradex_4.14-2.0.x-imx-next

Conflicts:
	sound/soc/codecs/sgtl5000.c

79 files changed, 1232 insertions, 133 deletions

diff --git a/tools/gpio/Build b/tools/gpio/Build
index 620c1937d957..4141f35837db 100644
--- a/tools/gpio/Build
+++ b/tools/gpio/Build
@@ -1,3 +1,4 @@
+gpio-utils-y += gpio-utils.o
 lsgpio-y += lsgpio.o gpio-utils.o
 gpio-hammer-y += gpio-hammer.o gpio-utils.o
 gpio-event-mon-y += gpio-event-mon.o gpio-utils.o
diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile
index 240eda014b37..6a73c06e069c 100644
--- a/tools/gpio/Makefile
+++ b/tools/gpio/Makefile
@@ -3,7 +3,11 @@ include ../scripts/Makefile.include
 
 bindir ?= /usr/bin
 
-ifeq ($(srctree),)
+# This will work when gpio is built in tools env. where srctree
+# isn't set and when invoked from selftests build, where srctree
+# is set to ".". building_out_of_srctree is undefined for in srctree
+# builds
+ifndef building_out_of_srctree
 srctree := $(patsubst %/,%,$(dir $(CURDIR)))
 srctree := $(patsubst %/,%,$(dir $(srctree)))
 endif
@@ -31,11 +35,15 @@ $(OUTPUT)include/linux/gpio.h: ../../include/uapi/linux/gpio.h
 
 prepare: $(OUTPUT)include/linux/gpio.h
 
+GPIO_UTILS_IN := $(output)gpio-utils-in.o
+$(GPIO_UTILS_IN): prepare FORCE
+	$(Q)$(MAKE) $(build)=gpio-utils
+
 #
 # lsgpio
 #
 LSGPIO_IN := $(OUTPUT)lsgpio-in.o
-$(LSGPIO_IN): prepare FORCE
+$(LSGPIO_IN): prepare FORCE $(OUTPUT)gpio-utils-in.o
 	$(Q)$(MAKE) $(build)=lsgpio
 $(OUTPUT)lsgpio: $(LSGPIO_IN)
 	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
@@ -44,7 +52,7 @@ $(OUTPUT)lsgpio: $(LSGPIO_IN)
 # gpio-hammer
 #
 GPIO_HAMMER_IN := $(OUTPUT)gpio-hammer-in.o
-$(GPIO_HAMMER_IN): prepare FORCE
+$(GPIO_HAMMER_IN): prepare FORCE $(OUTPUT)gpio-utils-in.o
 	$(Q)$(MAKE) $(build)=gpio-hammer
 $(OUTPUT)gpio-hammer: $(GPIO_HAMMER_IN)
 	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
@@ -53,7 +61,7 @@ $(OUTPUT)gpio-hammer: $(GPIO_HAMMER_IN)
 # gpio-event-mon
 #
 GPIO_EVENT_MON_IN := $(OUTPUT)gpio-event-mon-in.o
-$(GPIO_EVENT_MON_IN): prepare FORCE
+$(GPIO_EVENT_MON_IN): prepare FORCE $(OUTPUT)gpio-utils-in.o
 	$(Q)$(MAKE) $(build)=gpio-event-mon
 $(OUTPUT)gpio-event-mon: $(GPIO_EVENT_MON_IN)
 	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index 62c9a503ae05..1b917eaffad8 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -867,7 +867,7 @@ kvp_get_ip_info(int family, char *if_name, int op,
 	int sn_offset = 0;
 	int error = 0;
 	char *buffer;
-	struct hv_kvp_ipaddr_value *ip_buffer;
+	struct hv_kvp_ipaddr_value *ip_buffer = NULL;
 	char cidr_mask[5]; /* /xyz */
 	int weight;
 	int i;
@@ -1380,6 +1380,8 @@ int main(int argc, char *argv[])
 			daemonize = 0;
 			break;
 		case 'h':
+			print_usage(argv);
+			exit(0);
 		default:
 			print_usage(argv);
 			exit(EXIT_FAILURE);
diff --git a/tools/hv/hv_vss_daemon.c b/tools/hv/hv_vss_daemon.c
index 34031a297f02..514d29966ac6 100644
--- a/tools/hv/hv_vss_daemon.c
+++ b/tools/hv/hv_vss_daemon.c
@@ -172,6 +172,8 @@ int main(int argc, char *argv[])
 			daemonize = 0;
 			break;
 		case 'h':
+			print_usage(argv);
+			exit(0);
 		default:
 			print_usage(argv);
 			exit(EXIT_FAILURE);
diff --git a/tools/iio/iio_utils.c b/tools/iio/iio_utils.c
index 7a6d61c6c012..55272fef3b50 100644
--- a/tools/iio/iio_utils.c
+++ b/tools/iio/iio_utils.c
@@ -159,9 +159,9 @@ int iioutils_get_type(unsigned *is_signed, unsigned *bytes, unsigned *bits_used,
 			*be = (endianchar == 'b');
 			*bytes = padint / 8;
 			if (*bits_used == 64)
-				*mask = ~0;
+				*mask = ~(0ULL);
 			else
-				*mask = (1ULL << *bits_used) - 1;
+				*mask = (1ULL << *bits_used) - 1ULL;
 
 			*is_signed = (signchar == 's');
 			if (fclose(sysfsfp)) {
diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile
index ed61fb3a46c0..5b2cd5e58df0 100644
--- a/tools/lib/subcmd/Makefile
+++ b/tools/lib/subcmd/Makefile
@@ -20,7 +20,13 @@ MAKEFLAGS += --no-print-directory
 LIBFILE = $(OUTPUT)libsubcmd.a
 
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
-CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -fPIC
+
+ifeq ($(DEBUG),0)
+  ifeq ($(feature-fortify-source), 1)
+    CFLAGS += -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2
+  endif
+endif
 
 ifeq ($(CC_NO_CLANG), 0)
   CFLAGS += -O3
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 46cd5f871ad7..8107f060fa84 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -55,15 +55,15 @@ set_plugin_dir := 1
 
 # Set plugin_dir to preffered global plugin location
 # If we install under $HOME directory we go under
-# $(HOME)/.traceevent/plugins
+# $(HOME)/.local/lib/traceevent/plugins
 #
 # We dont set PLUGIN_DIR in case we install under $HOME
 # directory, because by default the code looks under:
-# $(HOME)/.traceevent/plugins by default.
+# $(HOME)/.local/lib/traceevent/plugins by default.
 #
 ifeq ($(plugin_dir),)
 ifeq ($(prefix),$(HOME))
-override plugin_dir = $(HOME)/.traceevent/plugins
+override plugin_dir = $(HOME)/.local/lib/traceevent/plugins
 set_plugin_dir := 0
 else
 override plugin_dir = $(libdir)/traceevent/plugins
@@ -259,8 +259,8 @@ endef
 
 define do_generate_dynamic_list_file
 	symbol_type=`$(NM) -u -D $1 | awk 'NF>1 {print $$1}' | \
-	xargs echo "U W w" | tr ' ' '\n' | sort -u | xargs echo`;\
-	if [ "$$symbol_type" = "U W w" ];then				\
+	xargs echo "U w W" | tr 'w ' 'W\n' | sort -u | xargs echo`;\
+	if [ "$$symbol_type" = "U W" ];then				\
 		(echo '{';						\
 		$(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\
 		echo '};';						\
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 7989dd6289e7..8211e8010e09 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -268,10 +268,10 @@ static int add_new_comm(struct pevent *pevent, const char *comm, int pid)
 		errno = ENOMEM;
 		return -1;
 	}
+	pevent->cmdlines = cmdlines;
 
 	cmdlines[pevent->cmdline_count].comm = strdup(comm);
 	if (!cmdlines[pevent->cmdline_count].comm) {
-		free(cmdlines);
 		errno = ENOMEM;
 		return -1;
 	}
@@ -282,7 +282,6 @@ static int add_new_comm(struct pevent *pevent, const char *comm, int pid)
 		pevent->cmdline_count++;
 
 	qsort(cmdlines, pevent->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
-	pevent->cmdlines = cmdlines;
 
 	return 0;
 }
diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c
index a16756ae3526..5fe7889606a2 100644
--- a/tools/lib/traceevent/event-plugin.c
+++ b/tools/lib/traceevent/event-plugin.c
@@ -30,7 +30,7 @@
 #include "event-parse.h"
 #include "event-utils.h"
 
-#define LOCAL_PLUGIN_DIR ".traceevent/plugins"
+#define LOCAL_PLUGIN_DIR ".local/lib/traceevent/plugins/"
 
 static struct registered_plugin_options {
 	struct registered_plugin_options	*next;
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 884d4f1ed0c1..7786bce816c9 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -26,14 +26,17 @@ LIBSUBCMD		= $(LIBSUBCMD_OUTPUT)libsubcmd.a
 OBJTOOL    := $(OUTPUT)objtool
 OBJTOOL_IN := $(OBJTOOL)-in.o
 
+LIBELF_FLAGS := $(shell pkg-config libelf --cflags 2>/dev/null)
+LIBELF_LIBS  := $(shell pkg-config libelf --libs 2>/dev/null || echo -lelf)
+
 all: $(OBJTOOL)
 
 INCLUDES := -I$(srctree)/tools/include \
 	    -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \
 	    -I$(srctree)/tools/objtool/arch/$(ARCH)/include
 WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
-CFLAGS   += -Wall -Werror $(WARNINGS) -fomit-frame-pointer -O2 -g $(INCLUDES)
-LDFLAGS  += -lelf $(LIBSUBCMD)
+CFLAGS   := -Wall -Werror $(WARNINGS) -fomit-frame-pointer -O2 -g $(INCLUDES) $(LIBELF_FLAGS)
+LDFLAGS  += $(LIBELF_LIBS) $(LIBSUBCMD)
 
 # Allow old libelf to be used:
 elfshdr := $(shell echo '$(pound)include <libelf.h>' | $(CC) $(CFLAGS) -x c -E - | grep elf_getshdr)
diff --git a/tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk b/tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk
index b02a36b2c14f..a42015b305f4 100644
--- a/tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk
@@ -69,7 +69,7 @@ BEGIN {
 
 	lprefix1_expr = "\\((66|!F3)\\)"
 	lprefix2_expr = "\\(F3\\)"
-	lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)"
+	lprefix3_expr = "\\((F2|!F3|66&F2)\\)"
 	lprefix_expr = "\\((66|F2|F3)\\)"
 	max_lprefix = 4
 
@@ -257,7 +257,7 @@ function convert_operands(count,opnd,       i,j,imm,mod)
 	return add_flags(imm, mod)
 }
 
-/^[0-9a-f]+\:/ {
+/^[0-9a-f]+:/ {
 	if (NR == 1)
 		next
 	# get index
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 95326c6a7a24..5422543faff8 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -165,6 +165,8 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func,
 		"__reiserfs_panic",
 		"lbug_with_loc",
 		"fortify_panic",
+		"machine_real_restart",
+		"rewind_stack_do_exit",
 	};
 
 	if (func->bind == STB_WEAK)
@@ -814,7 +816,7 @@ static int add_switch_table(struct objtool_file *file, struct instruction *insn,
 	struct symbol *pfunc = insn->func->pfunc;
 	unsigned int prev_offset = 0;
 
-	list_for_each_entry_from(rela, &file->rodata->rela->rela_list, list) {
+	list_for_each_entry_from(rela, &table->rela_sec->rela_list, list) {
 		if (rela == next_table)
 			break;
 
@@ -904,6 +906,7 @@ static struct rela *find_switch_table(struct objtool_file *file,
 {
 	struct rela *text_rela, *rodata_rela;
 	struct instruction *orig_insn = insn;
+	struct section *rodata_sec;
 	unsigned long table_offset;
 
 	/*
@@ -931,10 +934,13 @@ static struct rela *find_switch_table(struct objtool_file *file,
 		/* look for a relocation which references .rodata */
 		text_rela = find_rela_by_dest_range(insn->sec, insn->offset,
 						    insn->len);
-		if (!text_rela || text_rela->sym != file->rodata->sym)
+		if (!text_rela || text_rela->sym->type != STT_SECTION ||
+		    !text_rela->sym->sec->rodata)
 			continue;
 
 		table_offset = text_rela->addend;
+		rodata_sec = text_rela->sym->sec;
+
 		if (text_rela->type == R_X86_64_PC32)
 			table_offset += 4;
 
@@ -942,10 +948,10 @@ static struct rela *find_switch_table(struct objtool_file *file,
 		 * Make sure the .rodata address isn't associated with a
 		 * symbol.  gcc jump tables are anonymous data.
 		 */
-		if (find_symbol_containing(file->rodata, table_offset))
+		if (find_symbol_containing(rodata_sec, table_offset))
 			continue;
 
-		rodata_rela = find_rela_by_dest(file->rodata, table_offset);
+		rodata_rela = find_rela_by_dest(rodata_sec, table_offset);
 		if (rodata_rela) {
 			/*
 			 * Use of RIP-relative switch jumps is quite rare, and
@@ -1030,7 +1036,7 @@ static int add_switch_table_alts(struct objtool_file *file)
 	struct symbol *func;
 	int ret;
 
-	if (!file->rodata || !file->rodata->rela)
+	if (!file->rodata)
 		return 0;
 
 	for_each_sec(file, sec) {
@@ -1175,10 +1181,33 @@ static int read_retpoline_hints(struct objtool_file *file)
 	return 0;
 }
 
+static void mark_rodata(struct objtool_file *file)
+{
+	struct section *sec;
+	bool found = false;
+
+	/*
+	 * This searches for the .rodata section or multiple .rodata.func_name
+	 * sections if -fdata-sections is being used. The .str.1.1 and .str.1.8
+	 * rodata sections are ignored as they don't contain jump tables.
+	 */
+	for_each_sec(file, sec) {
+		if (!strncmp(sec->name, ".rodata", 7) &&
+		    !strstr(sec->name, ".str1.")) {
+			sec->rodata = true;
+			found = true;
+		}
+	}
+
+	file->rodata = found;
+}
+
 static int decode_sections(struct objtool_file *file)
 {
 	int ret;
 
+	mark_rodata(file);
+
 	ret = decode_instructions(file);
 	if (ret)
 		return ret;
@@ -2150,7 +2179,6 @@ int check(const char *_objname, bool orc)
 	INIT_LIST_HEAD(&file.insn_list);
 	hash_init(file.insn_hash);
 	file.whitelist = find_section_by_name(file.elf, ".discard.func_stack_frame_non_standard");
-	file.rodata = find_section_by_name(file.elf, ".rodata");
 	file.c_file = find_section_by_name(file.elf, ".comment");
 	file.ignore_unreachables = no_unreachable;
 	file.hints = false;
diff --git a/tools/objtool/check.h b/tools/objtool/check.h
index c6b68fcb926f..a039521b6753 100644
--- a/tools/objtool/check.h
+++ b/tools/objtool/check.h
@@ -60,8 +60,8 @@ struct objtool_file {
 	struct elf *elf;
 	struct list_head insn_list;
 	DECLARE_HASHTABLE(insn_hash, 16);
-	struct section *rodata, *whitelist;
-	bool ignore_unreachables, c_file, hints;
+	struct section *whitelist;
+	bool ignore_unreachables, c_file, hints, rodata;
 };
 
 int check(const char *objname, bool orc);
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index dd4ed7c3c062..d089c711355a 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -305,7 +305,7 @@ static int read_symbols(struct elf *elf)
 			if (sym->type != STT_FUNC)
 				continue;
 			sym->pfunc = sym->cfunc = sym;
-			coldstr = strstr(sym->name, ".cold.");
+			coldstr = strstr(sym->name, ".cold");
 			if (!coldstr)
 				continue;
 
@@ -390,6 +390,7 @@ static int read_relas(struct elf *elf)
 			rela->offset = rela->rela.r_offset;
 			symndx = GELF_R_SYM(rela->rela.r_info);
 			rela->sym = find_symbol_by_index(elf, symndx);
+			rela->rela_sec = sec;
 			if (!rela->sym) {
 				WARN("can't find rela entry symbol %d for %s",
 				     symndx, sec->name);
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index de5cd2ddded9..bc97ed86b9cd 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -48,7 +48,7 @@ struct section {
 	char *name;
 	int idx;
 	unsigned int len;
-	bool changed, text;
+	bool changed, text, rodata;
 };
 
 struct symbol {
@@ -68,6 +68,7 @@ struct rela {
 	struct list_head list;
 	struct hlist_node hash;
 	GElf_Rela rela;
+	struct section *rela_sec;
 	struct symbol *sym;
 	unsigned int type;
 	unsigned long offset;
diff --git a/tools/pci/pcitest.c b/tools/pci/pcitest.c
index 9074b477bff0..7002df55826f 100644
--- a/tools/pci/pcitest.c
+++ b/tools/pci/pcitest.c
@@ -23,7 +23,6 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <sys/ioctl.h>
-#include <time.h>
 #include <unistd.h>
 
 #include <linux/pcitest.h>
@@ -45,15 +44,13 @@ struct pci_test {
 
 static int run_test(struct pci_test *test)
 {
-	long ret;
+	int ret = -EINVAL;
 	int fd;
-	struct timespec start, end;
-	double time;
 
 	fd = open(test->device, O_RDWR);
 	if (fd < 0) {
 		perror("can't open PCI Endpoint Test device");
-		return fd;
+		return -ENODEV;
 	}
 
 	if (test->barnum >= 0 && test->barnum <= 5) {
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index ecdc3770d899..b8f301ea30af 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -780,7 +780,7 @@ ifndef NO_JVMTI
     JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | awk '{print $$3}')
   else
     ifneq (,$(wildcard /usr/sbin/alternatives))
-      JDIR=$(shell /usr/sbin/alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
+      JDIR=$(shell /usr/sbin/alternatives --display java | tail -1 | cut -d' ' -f 5 | sed -e 's%/jre/bin/java.%%g' -e 's%/bin/java.%%g')
     endif
   endif
   ifndef JDIR
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index fbfc055d3f4d..aec62e822bab 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -43,6 +43,8 @@ struct cs_etm_recording {
 	struct auxtrace_record	itr;
 	struct perf_pmu		*cs_etm_pmu;
 	struct perf_evlist	*evlist;
+	int			wrapped_cnt;
+	bool			*wrapped;
 	bool			snapshot_mode;
 	size_t			snapshot_size;
 };
@@ -485,16 +487,131 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 	return 0;
 }
 
-static int cs_etm_find_snapshot(struct auxtrace_record *itr __maybe_unused,
+static int cs_etm_alloc_wrapped_array(struct cs_etm_recording *ptr, int idx)
+{
+	bool *wrapped;
+	int cnt = ptr->wrapped_cnt;
+
+	/* Make @ptr->wrapped as big as @idx */
+	while (cnt <= idx)
+		cnt++;
+
+	/*
+	 * Free'ed in cs_etm_recording_free().  Using realloc() to avoid
+	 * cross compilation problems where the host's system supports
+	 * reallocarray() but not the target.
+	 */
+	wrapped = realloc(ptr->wrapped, cnt * sizeof(bool));
+	if (!wrapped)
+		return -ENOMEM;
+
+	wrapped[cnt - 1] = false;
+	ptr->wrapped_cnt = cnt;
+	ptr->wrapped = wrapped;
+
+	return 0;
+}
+
+static bool cs_etm_buffer_has_wrapped(unsigned char *buffer,
+				      size_t buffer_size, u64 head)
+{
+	u64 i, watermark;
+	u64 *buf = (u64 *)buffer;
+	size_t buf_size = buffer_size;
+
+	/*
+	 * We want to look the very last 512 byte (chosen arbitrarily) in
+	 * the ring buffer.
+	 */
+	watermark = buf_size - 512;
+
+	/*
+	 * @head is continuously increasing - if its value is equal or greater
+	 * than the size of the ring buffer, it has wrapped around.
+	 */
+	if (head >= buffer_size)
+		return true;
+
+	/*
+	 * The value of @head is somewhere within the size of the ring buffer.
+	 * This can be that there hasn't been enough data to fill the ring
+	 * buffer yet or the trace time was so long that @head has numerically
+	 * wrapped around.  To find we need to check if we have data at the very
+	 * end of the ring buffer.  We can reliably do this because mmap'ed
+	 * pages are zeroed out and there is a fresh mapping with every new
+	 * session.
+	 */
+
+	/* @head is less than 512 byte from the end of the ring buffer */
+	if (head > watermark)
+		watermark = head;
+
+	/*
+	 * Speed things up by using 64 bit transactions (see "u64 *buf" above)
+	 */
+	watermark >>= 3;
+	buf_size >>= 3;
+
+	/*
+	 * If we find trace data at the end of the ring buffer, @head has
+	 * been there and has numerically wrapped around at least once.
+	 */
+	for (i = watermark; i < buf_size; i++)
+		if (buf[i])
+			return true;
+
+	return false;
+}
+
+static int cs_etm_find_snapshot(struct auxtrace_record *itr,
 				int idx, struct auxtrace_mmap *mm,
-				unsigned char *data __maybe_unused,
+				unsigned char *data,
 				u64 *head, u64 *old)
 {
+	int err;
+	bool wrapped;
+	struct cs_etm_recording *ptr =
+			container_of(itr, struct cs_etm_recording, itr);
+
+	/*
+	 * Allocate memory to keep track of wrapping if this is the first
+	 * time we deal with this *mm.
+	 */
+	if (idx >= ptr->wrapped_cnt) {
+		err = cs_etm_alloc_wrapped_array(ptr, idx);
+		if (err)
+			return err;
+	}
+
+	/*
+	 * Check to see if *head has wrapped around.  If it hasn't only the
+	 * amount of data between *head and *old is snapshot'ed to avoid
+	 * bloating the perf.data file with zeros.  But as soon as *head has
+	 * wrapped around the entire size of the AUX ring buffer it taken.
+	 */
+	wrapped = ptr->wrapped[idx];
+	if (!wrapped && cs_etm_buffer_has_wrapped(data, mm->len, *head)) {
+		wrapped = true;
+		ptr->wrapped[idx] = true;
+	}
+
 	pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n",
 		  __func__, idx, (size_t)*old, (size_t)*head, mm->len);
 
-	*old = *head;
-	*head += mm->len;
+	/* No wrap has occurred, we can just use *head and *old. */
+	if (!wrapped)
+		return 0;
+
+	/*
+	 * *head has wrapped around - adjust *head and *old to pickup the
+	 * entire content of the AUX buffer.
+	 */
+	if (*head >= mm->len) {
+		*old = *head - mm->len;
+	} else {
+		*head += mm->len;
+		*old = *head - mm->len;
+	}
 
 	return 0;
 }
@@ -535,6 +652,8 @@ static void cs_etm_recording_free(struct auxtrace_record *itr)
 {
 	struct cs_etm_recording *ptr =
 			container_of(itr, struct cs_etm_recording, itr);
+
+	zfree(&ptr->wrapped);
 	free(ptr);
 }
 
diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c
index 0b2054007314..c8c86a0c9b79 100644
--- a/tools/perf/arch/s390/util/machine.c
+++ b/tools/perf/arch/s390/util/machine.c
@@ -5,16 +5,48 @@
 #include "util.h"
 #include "machine.h"
 #include "api/fs/fs.h"
+#include "debug.h"
+#include "symbol.h"
 
-int arch__fix_module_text_start(u64 *start, const char *name)
+int arch__fix_module_text_start(u64 *start, u64 *size, const char *name)
 {
+	u64 m_start = *start;
 	char path[PATH_MAX];
 
 	snprintf(path, PATH_MAX, "module/%.*s/sections/.text",
 				(int)strlen(name) - 2, name + 1);
-
-	if (sysfs__read_ull(path, (unsigned long long *)start) < 0)
-		return -1;
+	if (sysfs__read_ull(path, (unsigned long long *)start) < 0) {
+		pr_debug2("Using module %s start:%#lx\n", path, m_start);
+		*start = m_start;
+	} else {
+		/* Successful read of the modules segment text start address.
+		 * Calculate difference between module start address
+		 * in memory and module text segment start address.
+		 * For example module load address is 0x3ff8011b000
+		 * (from /proc/modules) and module text segment start
+		 * address is 0x3ff8011b870 (from file above).
+		 *
+		 * Adjust the module size and subtract the GOT table
+		 * size located at the beginning of the module.
+		 */
+		*size -= (*start - m_start);
+	}
 
 	return 0;
 }
+
+/* On s390 kernel text segment start is located at very low memory addresses,
+ * for example 0x10000. Modules are located at very high memory addresses,
+ * for example 0x3ff xxxx xxxx. The gap between end of kernel text segment
+ * and beginning of first module's text segment is very big.
+ * Therefore do not fill this gap and do not assign it to the kernel dso map.
+ */
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+	if (strchr(p->name, '[') == NULL && strchr(c->name, '['))
+		/* Last kernel symbol mapped to end of page */
+		p->end = roundup(p->end, page_size);
+	else
+		p->end = c->start;
+	pr_debug4("%s sym:%s end:%#lx\n", __func__, p->name, p->end);
+}
diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c
index 05920e3edf7a..47357973b55b 100644
--- a/tools/perf/arch/x86/util/unwind-libunwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -1,11 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <errno.h>
+#include "../../util/debug.h"
 #ifndef REMOTE_UNWIND_LIBUNWIND
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
-#include "../../util/debug.h"
 #endif
 
 #ifdef HAVE_ARCH_X86_64_SUPPORT
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 997875c770b1..275f1c3c73b6 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -378,8 +378,10 @@ static u8 *alloc_data(ssize_t bytes0, int map_flags,
 
 	/* Allocate and initialize all memory on CPU#0: */
 	if (init_cpu0) {
-		orig_mask = bind_to_node(0);
-		bind_to_memnode(0);
+		int node = numa_node_of_cpu(0);
+
+		orig_mask = bind_to_node(node);
+		bind_to_memnode(node);
 	}
 
 	bytes = bytes0 + HPSIZE;
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 32e64a8a6443..bec7a2f1fb4d 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2454,6 +2454,7 @@ static int build_cl_output(char *cl_sort, bool no_source)
 	bool add_sym   = false;
 	bool add_dso   = false;
 	bool add_src   = false;
+	int ret = 0;
 
 	if (!buf)
 		return -ENOMEM;
@@ -2472,7 +2473,8 @@ static int build_cl_output(char *cl_sort, bool no_source)
 			add_dso = true;
 		} else if (strcmp(tok, "offset")) {
 			pr_err("unrecognized sort token: %s\n", tok);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto err;
 		}
 	}
 
@@ -2495,13 +2497,15 @@ static int build_cl_output(char *cl_sort, bool no_source)
 		add_sym ? "symbol," : "",
 		add_dso ? "dso," : "",
 		add_src ? "cl_srcline," : "",
-		"node") < 0)
-		return -ENOMEM;
+		"node") < 0) {
+		ret = -ENOMEM;
+		goto err;
+	}
 
 	c2c.show_src = add_src;
-
+err:
 	free(buf);
-	return 0;
+	return ret;
 }
 
 static int setup_coalesce(const char *coalesce, bool no_source)
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 25a42acabee1..13a33fb71a6d 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -162,7 +162,7 @@ static int set_tracing_cpumask(struct cpu_map *cpumap)
 	int last_cpu;
 
 	last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1);
-	mask_size = (last_cpu + 3) / 4 + 1;
+	mask_size = last_cpu / 4 + 2; /* one more byte for EOS */
 	mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */
 
 	cpumask = malloc(mask_size);
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index a0f7ed2b869b..3c364798093b 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -189,7 +189,7 @@ static void add_man_viewer(const char *name)
 	while (*p)
 		p = &((*p)->next);
 	*p = zalloc(sizeof(**p) + len + 1);
-	strncpy((*p)->name, name, len);
+	strcpy((*p)->name, name);
 }
 
 static int supported_man_viewer(const char *name, size_t len)
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 9e693ce4b73b..ce786f363476 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -687,6 +687,7 @@ static char *compact_gfp_flags(char *gfp_flags)
 			new = realloc(new_flags, len + strlen(cpt) + 2);
 			if (new == NULL) {
 				free(new_flags);
+				free(orig_flags);
 				return NULL;
 			}
 
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index c0065923a525..e1ac51aaedcf 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -712,6 +712,16 @@ __cmd_probe(int argc, const char **argv)
 
 		ret = perf_add_probe_events(params.events, params.nevents);
 		if (ret < 0) {
+
+			/*
+			 * When perf_add_probe_events() fails it calls
+			 * cleanup_perf_probe_events(pevs, npevs), i.e.
+			 * cleanup_perf_probe_events(params.events, params.nevents), which
+			 * will call clear_perf_probe_event(), so set nevents to zero
+			 * to avoid cleanup_params() to call clear_perf_probe_event() again
+			 * on the same pevs.
+			 */
+			params.nevents = 0;
 			pr_err_with_code("  Error: Failed to add events.", ret);
 			return ret;
 		}
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 52486c90ab93..0801e0ffba4a 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2769,8 +2769,11 @@ int cmd_stat(int argc, const char **argv)
 			fprintf(output, "[ perf stat: executing run #%d ... ]\n",
 				run_idx + 1);
 
+		if (run_idx != 0)
+			perf_evlist__reset_prev_raw_counts(evsel_list);
+
 		status = run_perf_stat(argc, argv);
-		if (forever && status != -1) {
+		if (forever && status != -1 && !interval) {
 			print_counters(NULL, argc, argv);
 			perf_stat__reset_stats();
 		}
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 96f62dd7e3ed..d4ebd0956114 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -25,7 +25,7 @@ static inline unsigned long long rdclock(void)
 }
 
 #ifndef MAX_NR_CPUS
-#define MAX_NR_CPUS			1024
+#define MAX_NR_CPUS			2048
 #endif
 
 extern const char *input_name;
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index d51dc9ca8861..6f9f247b4516 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -342,11 +342,12 @@ static struct fixed {
 	const char *name;
 	const char *event;
 } fixed[] = {
-	{ "inst_retired.any", "event=0xc0" },
-	{ "inst_retired.any_p", "event=0xc0" },
-	{ "cpu_clk_unhalted.ref", "event=0x0,umask=0x03" },
-	{ "cpu_clk_unhalted.thread", "event=0x3c" },
-	{ "cpu_clk_unhalted.thread_any", "event=0x3c,any=1" },
+	{ "inst_retired.any", "event=0xc0,period=2000003" },
+	{ "inst_retired.any_p", "event=0xc0,period=2000003" },
+	{ "cpu_clk_unhalted.ref", "event=0x0,umask=0x03,period=2000003" },
+	{ "cpu_clk_unhalted.thread", "event=0x3c,period=2000003" },
+	{ "cpu_clk_unhalted.core", "event=0x3c,period=2000003" },
+	{ "cpu_clk_unhalted.thread_any", "event=0x3c,any=1,period=2000003" },
 	{ NULL, NULL},
 };
 
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 3c3f3e029e33..2ecb86876f10 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -52,7 +52,7 @@ static void *thread_fn(void *arg)
 {
 	struct thread_data *td = arg;
 	ssize_t ret;
-	int go;
+	int go = 0;
 
 	if (thread_init(td))
 		return NULL;
diff --git a/tools/perf/tests/perf-hooks.c b/tools/perf/tests/perf-hooks.c
index a693bcf017ea..44c16fd11bf6 100644
--- a/tools/perf/tests/perf-hooks.c
+++ b/tools/perf/tests/perf-hooks.c
@@ -20,12 +20,11 @@ static void sigsegv_handler(int sig __maybe_unused)
 static void the_hook(void *_hook_flags)
 {
 	int *hook_flags = _hook_flags;
-	int *p = NULL;
 
 	*hook_flags = 1234;
 
 	/* Generate a segfault, test perf_hooks__recover */
-	*p = 0;
+	raise(SIGSEGV);
 }
 
 int test__perf_hooks(struct test *test __maybe_unused, int subtest __maybe_unused)
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index 2a9ef080efd0..a8a516dec4ed 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -30,6 +30,10 @@ if [ $err -ne 0 ] ; then
 	exit $err
 fi
 
+# Do not use whatever ~/.perfconfig file, it may change the output
+# via trace.{show_timestamp,show_prefix,etc}
+export PERF_CONFIG=/dev/null
+
 trace_open_vfs_getname
 err=$?
 rm -f ${file}
diff --git a/tools/perf/trace/beauty/ioctl.c b/tools/perf/trace/beauty/ioctl.c
index 1be3b4cf0827..82346ca06f17 100644
--- a/tools/perf/trace/beauty/ioctl.c
+++ b/tools/perf/trace/beauty/ioctl.c
@@ -22,7 +22,7 @@
 static size_t ioctl__scnprintf_tty_cmd(int nr, int dir, char *bf, size_t size)
 {
 	static const char *ioctl_tty_cmd[] = {
-	"TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW",
+	[_IOC_NR(TCGETS)] = "TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW",
 	"TCSETAF", "TCSBRK", "TCXONC", "TCFLSH", "TIOCEXCL", "TIOCNXCL", "TIOCSCTTY",
 	"TIOCGPGRP", "TIOCSPGRP", "TIOCOUTQ", "TIOCSTI", "TIOCGWINSZ", "TIOCSWINSZ",
 	"TIOCMGET", "TIOCMBIS", "TIOCMBIC", "TIOCMSET", "TIOCGSOFTCAR", "TIOCSSOFTCAR",
diff --git a/tools/perf/ui/tui/helpline.c b/tools/perf/ui/tui/helpline.c
index 4ca799aadb4e..93d6b7240285 100644
--- a/tools/perf/ui/tui/helpline.c
+++ b/tools/perf/ui/tui/helpline.c
@@ -24,7 +24,7 @@ static void tui_helpline__push(const char *msg)
 	SLsmg_set_color(0);
 	SLsmg_write_nstring((char *)msg, SLtt_Screen_Cols);
 	SLsmg_refresh();
-	strncpy(ui_helpline__current, msg, sz)[sz - 1] = '\0';
+	strlcpy(ui_helpline__current, msg, sz);
 }
 
 static int tui_helpline__show(const char *format, va_list ap)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 398d4cc2f0e4..2a8d2a6723f6 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -868,16 +868,14 @@ static int disasm_line__parse(char *line, const char **namep, char **rawp)
 	*namep = strdup(name);
 
 	if (*namep == NULL)
-		goto out_free_name;
+		goto out;
 
 	(*rawp)[0] = tmp;
 	*rawp = ltrim(*rawp);
 
 	return 0;
 
-out_free_name:
-	free((void *)namep);
-	*namep = NULL;
+out:
 	return -1;
 }
 
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 383674f448fc..f93846edc1e0 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -701,7 +701,10 @@ size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size)
 	unsigned char *bitmap;
 	int last_cpu = cpu_map__cpu(map, map->nr - 1);
 
-	bitmap = zalloc((last_cpu + 7) / 8);
+	if (buf == NULL)
+		return 0;
+
+	bitmap = zalloc(last_cpu / 8 + 1);
 	if (bitmap == NULL) {
 		buf[0] = '\0';
 		return 0;
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 2346cecb8ea2..5131304ea3a8 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -271,7 +271,7 @@ static int string_set_value(struct bt_ctf_field *field, const char *string)
 				if (i > 0)
 					strncpy(buffer, string, i);
 			}
-			strncat(buffer + p, numstr, 4);
+			memcpy(buffer + p, numstr, 4);
 			p += 3;
 		}
 	}
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 0cf6f537f980..3ab81e8e079e 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -587,6 +587,9 @@ const char *perf_evsel__name(struct perf_evsel *evsel)
 {
 	char bf[128];
 
+	if (!evsel)
+		goto out_unknown;
+
 	if (evsel->name)
 		return evsel->name;
 
@@ -623,7 +626,10 @@ const char *perf_evsel__name(struct perf_evsel *evsel)
 
 	evsel->name = strdup(bf);
 
-	return evsel->name ?: "unknown";
+	if (evsel->name)
+		return evsel->name;
+out_unknown:
+	return "unknown";
 }
 
 const char *perf_evsel__group_name(struct perf_evsel *evsel)
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 696f2654826b..c892bb4f26c3 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1063,7 +1063,7 @@ static int cpu_cache_level__read(struct cpu_cache_level *cache, u32 cpu, u16 lev
 
 	scnprintf(file, PATH_MAX, "%s/shared_cpu_list", path);
 	if (sysfs__read_str(file, &cache->map, &len)) {
-		free(cache->map);
+		free(cache->size);
 		free(cache->type);
 		return -1;
 	}
@@ -1122,7 +1122,7 @@ static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp)
 	return 0;
 }
 
-#define MAX_CACHES 2000
+#define MAX_CACHES (MAX_NR_CPUS * 4)
 
 static int write_cache(struct feat_fd *ff,
 		       struct perf_evlist *evlist __maybe_unused)
@@ -1882,8 +1882,10 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 	/* On s390 the socket_id number is not related to the numbers of cpus.
 	 * The socket_id number might be higher than the numbers of cpus.
 	 * This depends on the configuration.
+	 * AArch64 is the same.
 	 */
-	if (ph->env.arch && !strncmp(ph->env.arch, "s390", 4))
+	if (ph->env.arch && (!strncmp(ph->env.arch, "s390", 4)
+			  || !strncmp(ph->env.arch, "aarch64", 7)))
 		do_core_id_test = false;
 
 	for (i = 0; i < (u32)cpu_nr; i++) {
@@ -2901,6 +2903,13 @@ int perf_session__read_header(struct perf_session *session)
 			   file->path);
 	}
 
+	if (f_header.attr_size == 0) {
+		pr_err("ERROR: The %s file's attr size field is 0 which is unexpected.\n"
+		       "Was the 'perf record' command properly terminated?\n",
+		       file->path);
+		return -EINVAL;
+	}
+
 	nr_attrs = f_header.attrs.size / f_header.attr_size;
 	lseek(fd, f_header.attrs.offset, SEEK_SET);
 
@@ -2983,7 +2992,7 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
 	size += sizeof(struct perf_event_header);
 	size += ids * sizeof(u64);
 
-	ev = malloc(size);
+	ev = zalloc(size);
 
 	if (ev == NULL)
 		return -ENOMEM;
@@ -3081,7 +3090,7 @@ int perf_event__process_feature(struct perf_tool *tool,
 		return 0;
 
 	ff.buf  = (void *)fe->data;
-	ff.size = event->header.size - sizeof(event->header);
+	ff.size = event->header.size - sizeof(*fe);
 	ff.ph = &session->header;
 
 	if (feat_ops[feat].process(&ff, NULL))
@@ -3171,7 +3180,7 @@ perf_event__synthesize_event_update_name(struct perf_tool *tool,
 	if (ev == NULL)
 		return -ENOMEM;
 
-	strncpy(ev->data, evsel->name, len);
+	strlcpy(ev->data, evsel->name, len + 1);
 	err = process(tool, (union perf_event*) ev, NULL, NULL);
 	free(ev);
 	return err;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 5b8bc1fd943d..c1f9615b02f7 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1504,7 +1504,7 @@ int hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 	return 0;
 }
 
-static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
+static int64_t hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
 {
 	struct hists *hists = a->hists;
 	struct perf_hpp_fmt *fmt;
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index 36483db032e8..3f02a5e284b2 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -394,7 +394,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
 	size_t size;
 	u16 idr_size;
 	const char *sym;
-	uint32_t count;
+	uint64_t count;
 	int ret, csize, usize;
 	pid_t pid, tid;
 	struct {
@@ -417,7 +417,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
 		return -1;
 
 	filename = event->mmap2.filename;
-	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%u.so",
+	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%" PRIu64 ".so",
 			jd->dir,
 			pid,
 			count);
@@ -530,7 +530,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr)
 		return -1;
 
 	filename = event->mmap2.filename;
-	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%"PRIu64,
+	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%" PRIu64 ".so",
 	         jd->dir,
 	         pid,
 		 jr->move.code_index);
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 2bdaac048a0a..da59a9e9543b 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -225,14 +225,14 @@ static int detect_kbuild_dir(char **kbuild_dir)
 	const char *prefix_dir = "";
 	const char *suffix_dir = "";
 
+	/* _UTSNAME_LENGTH is 65 */
+	char release[128];
+
 	char *autoconf_path;
 
 	int err;
 
 	if (!test_dir) {
-		/* _UTSNAME_LENGTH is 65 */
-		char release[128];
-
 		err = fetch_kernel_version(NULL, release,
 					   sizeof(release));
 		if (err)
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 968fd0454e6b..5145c6a84c47 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -156,6 +156,9 @@ void machine__delete_threads(struct machine *machine)
 
 void machine__exit(struct machine *machine)
 {
+	if (machine == NULL)
+		return;
+
 	machine__destroy_kernel_maps(machine);
 	map_groups__exit(&machine->kmaps);
 	dsos__exit(&machine->dsos);
@@ -1230,6 +1233,7 @@ static int machine__set_modules_path(struct machine *machine)
 	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0);
 }
 int __weak arch__fix_module_text_start(u64 *start __maybe_unused,
+				u64 *size __maybe_unused,
 				const char *name __maybe_unused)
 {
 	return 0;
@@ -1241,7 +1245,7 @@ static int machine__create_module(void *arg, const char *name, u64 start,
 	struct machine *machine = arg;
 	struct map *map;
 
-	if (arch__fix_module_text_start(&start, name) < 0)
+	if (arch__fix_module_text_start(&start, &size, name) < 0)
 		return -1;
 
 	map = machine__findnew_module_map(machine, start, name);
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 13041b036a5b..ec339cdf854c 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -213,7 +213,7 @@ struct symbol *machine__find_kernel_function_by_name(struct machine *machine,
 
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 					const char *filename);
-int arch__fix_module_text_start(u64 *start, const char *name);
+int arch__fix_module_text_start(u64 *start, u64 *size, const char *name);
 
 int __machine__load_kallsyms(struct machine *machine, const char *filename,
 			     enum map_type type, bool no_kcore);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 4e7bd2750122..63db9872c880 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "symbol.h"
+#include <assert.h>
 #include <errno.h>
 #include <inttypes.h>
 #include <limits.h>
@@ -737,6 +738,8 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
 			}
 
 			after->start = map->end;
+			after->pgoff += map->end - pos->start;
+			assert(pos->map_ip(pos, map->end) == after->map_ip(after, map->end));
 			__map_groups__insert(pos->groups, after);
 			if (verbose >= 2 && !use_browser)
 				map__fprintf(after, fp);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index da55081aefc6..c49e8ea1a42c 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1145,6 +1145,9 @@ static void dump_read(struct perf_evsel *evsel, union perf_event *event)
 	       evsel ? perf_evsel__name(evsel) : "FAIL",
 	       event->read.value);
 
+	if (!evsel)
+		return;
+
 	read_format = evsel->attr.read_format;
 
 	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 37363869c9a1..eadc9a2aef16 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -271,7 +271,7 @@ static struct perf_evsel *perf_stat__find_event(struct perf_evlist *evsel_list,
 	struct perf_evsel *c2;
 
 	evlist__for_each_entry (evsel_list, c2) {
-		if (!strcasecmp(c2->name, name))
+		if (!strcasecmp(c2->name, name) && !c2->collect_stat)
 			return c2;
 	}
 	return NULL;
@@ -310,7 +310,8 @@ void perf_stat__collect_metric_expr(struct perf_evlist *evsel_list)
 			if (leader) {
 				/* Search in group */
 				for_each_group_member (oc, leader) {
-					if (!strcasecmp(oc->name, metric_names[i])) {
+					if (!strcasecmp(oc->name, metric_names[i]) &&
+						!oc->collect_stat) {
 						found = true;
 						break;
 					}
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index c9bae5fb8b47..d028c2786802 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -154,6 +154,15 @@ static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
 	evsel->prev_raw_counts = NULL;
 }
 
+static void perf_evsel__reset_prev_raw_counts(struct perf_evsel *evsel)
+{
+	if (evsel->prev_raw_counts) {
+		evsel->prev_raw_counts->aggr.val = 0;
+		evsel->prev_raw_counts->aggr.ena = 0;
+		evsel->prev_raw_counts->aggr.run = 0;
+       }
+}
+
 static int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
 {
 	int ncpus = perf_evsel__nr_cpus(evsel);
@@ -204,6 +213,14 @@ void perf_evlist__reset_stats(struct perf_evlist *evlist)
 	}
 }
 
+void perf_evlist__reset_prev_raw_counts(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel)
+		perf_evsel__reset_prev_raw_counts(evsel);
+}
+
 static void zero_per_pkg(struct perf_evsel *counter)
 {
 	if (counter->per_pkg_mask)
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 96326b1f9443..bdfbed8e2df2 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -100,6 +100,7 @@ void perf_stat__collect_metric_expr(struct perf_evlist *);
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
 void perf_evlist__free_stats(struct perf_evlist *evlist);
 void perf_evlist__reset_stats(struct perf_evlist *evlist);
+void perf_evlist__reset_prev_raw_counts(struct perf_evlist *evlist);
 
 int perf_stat_process_counter(struct perf_stat_config *config,
 			      struct perf_evsel *counter);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 3936f69f385c..27bffcb213eb 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -93,6 +93,11 @@ static int prefix_underscores_count(const char *str)
 	return tail - str;
 }
 
+void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+	p->end = c->start;
+}
+
 const char * __weak arch__normalize_symbol_name(const char *name)
 {
 	return name;
@@ -219,7 +224,7 @@ void symbols__fixup_end(struct rb_root *symbols)
 		curr = rb_entry(nd, struct symbol, rb_node);
 
 		if (prev->end == prev->start && prev->end != curr->start)
-			prev->end = curr->start;
+			arch__symbols__fixup_end(prev, curr);
 	}
 
 	/* Last entry */
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 698c65e603a8..95ac21be8481 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -351,6 +351,7 @@ const char *arch__normalize_symbol_name(const char *name);
 #define SYMBOL_A 0
 #define SYMBOL_B 1
 
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c);
 int arch__compare_symbol_names(const char *namea, const char *nameb);
 int arch__compare_symbol_names_n(const char *namea, const char *nameb,
 				 unsigned int n);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 1dbcd3c8dee0..177436c8e026 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -160,14 +160,24 @@ struct comm *thread__comm(const struct thread *thread)
 
 struct comm *thread__exec_comm(const struct thread *thread)
 {
-	struct comm *comm, *last = NULL;
+	struct comm *comm, *last = NULL, *second_last = NULL;
 
 	list_for_each_entry(comm, &thread->comm_list, list) {
 		if (comm->exec)
 			return comm;
+		second_last = last;
 		last = comm;
 	}
 
+	/*
+	 * 'last' with no start time might be the parent's comm of a synthesized
+	 * thread (created by processing a synthesized fork event). For a main
+	 * thread, that is very probably wrong. Prefer a later comm to avoid
+	 * that case.
+	 */
+	if (second_last && !last->start && thread->pid_ == thread->tid)
+		return second_last;
+
 	return last;
 }
 
diff --git a/tools/perf/util/xyarray.h b/tools/perf/util/xyarray.h
index 7ffe562e7ae7..2627b038b6f2 100644
--- a/tools/perf/util/xyarray.h
+++ b/tools/perf/util/xyarray.h
@@ -2,6 +2,7 @@
 #ifndef _PERF_XYARRAY_H_
 #define _PERF_XYARRAY_H_ 1
 
+#include <linux/compiler.h>
 #include <sys/types.h>
 
 struct xyarray {
@@ -10,7 +11,7 @@ struct xyarray {
 	size_t entries;
 	size_t max_x;
 	size_t max_y;
-	char contents[];
+	char contents[] __aligned(8);
 };
 
 struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size);
diff --git a/tools/power/acpi/tools/acpidump/apmain.c b/tools/power/acpi/tools/acpidump/apmain.c
index 943b6b614683..bed0794e3295 100644
--- a/tools/power/acpi/tools/acpidump/apmain.c
+++ b/tools/power/acpi/tools/acpidump/apmain.c
@@ -139,7 +139,7 @@ static int ap_insert_action(char *argument, u32 to_be_done)
 
 	current_action++;
 	if (current_action > AP_MAX_ACTIONS) {
-		fprintf(stderr, "Too many table options (max %u)\n",
+		fprintf(stderr, "Too many table options (max %d)\n",
 			AP_MAX_ACTIONS);
 		return (-1);
 	}
diff --git a/tools/power/cpupower/utils/cpufreq-set.c b/tools/power/cpupower/utils/cpufreq-set.c
index 1eef0aed6423..08a405593a79 100644
--- a/tools/power/cpupower/utils/cpufreq-set.c
+++ b/tools/power/cpupower/utils/cpufreq-set.c
@@ -306,6 +306,8 @@ int cmd_freq_set(int argc, char **argv)
 				bitmask_setbit(cpus_chosen, cpus->cpu);
 				cpus = cpus->next;
 			}
+			/* Set the last cpu in related cpus list */
+			bitmask_setbit(cpus_chosen, cpus->cpu);
 			cpufreq_put_related_cpus(cpus);
 		}
 	}
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 3e5f8b3db272..19e345cf8193 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -4488,7 +4488,7 @@ int initialize_counters(int cpu_id)
 
 void allocate_output_buffer()
 {
-	output_buffer = calloc(1, (1 + topo.num_cpus) * 1024);
+	output_buffer = calloc(1, (1 + topo.num_cpus) * 2048);
 	outp = output_buffer;
 	if (outp == NULL)
 		err(-1, "calloc output buffer");
diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
index 65bbe627a425..2aba622d1c5a 100644
--- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
+++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
@@ -546,7 +546,7 @@ void cmdline(int argc, char **argv)
 
 	progname = argv[0];
 
-	while ((opt = getopt_long_only(argc, argv, "+a:c:dD:E:e:f:m:M:rt:u:vw",
+	while ((opt = getopt_long_only(argc, argv, "+a:c:dD:E:e:f:m:M:rt:u:vw:",
 				long_options, &option_index)) != -1) {
 		switch (opt) {
 		case 'a':
@@ -1260,6 +1260,15 @@ void probe_dev_msr(void)
 		if (system("/sbin/modprobe msr > /dev/null 2>&1"))
 			err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" ");
 }
+
+static void get_cpuid_or_exit(unsigned int leaf,
+			     unsigned int *eax, unsigned int *ebx,
+			     unsigned int *ecx, unsigned int *edx)
+{
+	if (!__get_cpuid(leaf, eax, ebx, ecx, edx))
+		errx(1, "Processor not supported\n");
+}
+
 /*
  * early_cpuid()
  * initialize turbo_is_enabled, has_hwp, has_epb
@@ -1267,15 +1276,10 @@ void probe_dev_msr(void)
  */
 void early_cpuid(void)
 {
-	unsigned int eax, ebx, ecx, edx, max_level;
+	unsigned int eax, ebx, ecx, edx;
 	unsigned int fms, family, model;
 
-	__get_cpuid(0, &max_level, &ebx, &ecx, &edx);
-
-	if (max_level < 6)
-		errx(1, "Processor not supported\n");
-
-	__get_cpuid(1, &fms, &ebx, &ecx, &edx);
+	get_cpuid_or_exit(1, &fms, &ebx, &ecx, &edx);
 	family = (fms >> 8) & 0xf;
 	model = (fms >> 4) & 0xf;
 	if (family == 6 || family == 0xf)
@@ -1289,7 +1293,7 @@ void early_cpuid(void)
 		bdx_highest_ratio = msr & 0xFF;
 	}
 
-	__get_cpuid(0x6, &eax, &ebx, &ecx, &edx);
+	get_cpuid_or_exit(0x6, &eax, &ebx, &ecx, &edx);
 	turbo_is_enabled = (eax >> 1) & 1;
 	has_hwp = (eax >> 7) & 1;
 	has_epb = (ecx >> 3) & 1;
@@ -1307,7 +1311,7 @@ void parse_cpuid(void)
 
 	eax = ebx = ecx = edx = 0;
 
-	__get_cpuid(0, &max_level, &ebx, &ecx, &edx);
+	get_cpuid_or_exit(0, &max_level, &ebx, &ecx, &edx);
 
 	if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e)
 		genuine_intel = 1;
@@ -1316,7 +1320,7 @@ void parse_cpuid(void)
 		fprintf(stderr, "CPUID(0): %.4s%.4s%.4s ",
 			(char *)&ebx, (char *)&edx, (char *)&ecx);
 
-	__get_cpuid(1, &fms, &ebx, &ecx, &edx);
+	get_cpuid_or_exit(1, &fms, &ebx, &ecx, &edx);
 	family = (fms >> 8) & 0xf;
 	model = (fms >> 4) & 0xf;
 	stepping = fms & 0xf;
@@ -1341,7 +1345,7 @@ void parse_cpuid(void)
 		errx(1, "CPUID: no MSR");
 
 
-	__get_cpuid(0x6, &eax, &ebx, &ecx, &edx);
+	get_cpuid_or_exit(0x6, &eax, &ebx, &ecx, &edx);
 	/* turbo_is_enabled already set */
 	/* has_hwp already set */
 	has_hwp_notify = eax & (1 << 8);
diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index 8e61aad0ca3f..07cec1b5a0d8 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -177,6 +177,57 @@ void idr_get_next_test(void)
 	idr_destroy(&idr);
 }
 
+static inline void *idr_mk_value(unsigned long v)
+{
+	BUG_ON((long)v < 0);
+	return (void *)((v & 1) | 2 | (v << 1));
+}
+
+DEFINE_IDR(find_idr);
+
+static void *idr_throbber(void *arg)
+{
+	time_t start = time(NULL);
+	int id = *(int *)arg;
+
+	rcu_register_thread();
+	do {
+		idr_alloc(&find_idr, idr_mk_value(id), id, id + 1, GFP_KERNEL);
+		idr_remove(&find_idr, id);
+	} while (time(NULL) < start + 10);
+	rcu_unregister_thread();
+
+	return NULL;
+}
+
+void idr_find_test_1(int anchor_id, int throbber_id)
+{
+	pthread_t throbber;
+	time_t start = time(NULL);
+
+	pthread_create(&throbber, NULL, idr_throbber, &throbber_id);
+
+	BUG_ON(idr_alloc(&find_idr, idr_mk_value(anchor_id), anchor_id,
+				anchor_id + 1, GFP_KERNEL) != anchor_id);
+
+	do {
+		int id = 0;
+		void *entry = idr_get_next(&find_idr, &id);
+		BUG_ON(entry != idr_mk_value(id));
+	} while (time(NULL) < start + 11);
+
+	pthread_join(throbber, NULL);
+
+	idr_remove(&find_idr, anchor_id);
+	BUG_ON(!idr_is_empty(&find_idr));
+}
+
+void idr_find_test(void)
+{
+	idr_find_test_1(100000, 0);
+	idr_find_test_1(0, 100000);
+}
+
 void idr_checks(void)
 {
 	unsigned long i;
@@ -234,6 +285,7 @@ void idr_checks(void)
 	idr_null_test();
 	idr_nowait_test();
 	idr_get_next_test();
+	idr_find_test();
 }
 
 /*
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc
index 231bcd2c4eb5..1e7ac6f3362f 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc
@@ -71,8 +71,11 @@ test_badarg "\$stackp" "\$stack0+10" "\$stack1-10"
 echo "r ${PROBEFUNC} \$retval" > kprobe_events
 ! echo "p ${PROBEFUNC} \$retval" > kprobe_events
 
+# $comm was introduced in 4.8, older kernels reject it.
+if grep -A1 "fetcharg:" README | grep -q '\$comm' ; then
 : "Comm access"
 test_goodarg "\$comm"
+fi
 
 : "Indirect memory access"
 test_goodarg "+0(${GOODREG})" "-0(${GOODREG})" "+10(\$stack)" \
diff --git a/tools/testing/selftests/kvm/config b/tools/testing/selftests/kvm/config
new file mode 100644
index 000000000000..63ed533f73d6
--- /dev/null
+++ b/tools/testing/selftests/kvm/config
@@ -0,0 +1,3 @@
+CONFIG_KVM=y
+CONFIG_KVM_INTEL=y
+CONFIG_KVM_AMD=y
diff --git a/tools/testing/selftests/net/reuseport_dualstack.c b/tools/testing/selftests/net/reuseport_dualstack.c
index fe3230c55986..fb7a59ed759e 100644
--- a/tools/testing/selftests/net/reuseport_dualstack.c
+++ b/tools/testing/selftests/net/reuseport_dualstack.c
@@ -129,7 +129,7 @@ static void test(int *rcv_fds, int count, int proto)
 {
 	struct epoll_event ev;
 	int epfd, i, test_fd;
-	uint16_t test_family;
+	int test_family;
 	socklen_t len;
 
 	epfd = epoll_create(1);
@@ -146,6 +146,7 @@ static void test(int *rcv_fds, int count, int proto)
 	send_from_v4(proto);
 
 	test_fd = receive_once(epfd, proto);
+	len = sizeof(test_family);
 	if (getsockopt(test_fd, SOL_SOCKET, SO_DOMAIN, &test_family, &len))
 		error(1, errno, "failed to read socket domain");
 	if (test_family != AF_INET)
diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh
index 8ec76681605c..f25f72a75cf3 100755
--- a/tools/testing/selftests/netfilter/nft_nat.sh
+++ b/tools/testing/selftests/netfilter/nft_nat.sh
@@ -23,7 +23,11 @@ ip netns add ns0
 ip netns add ns1
 ip netns add ns2
 
-ip link add veth0 netns ns0 type veth peer name eth0 netns ns1
+ip link add veth0 netns ns0 type veth peer name eth0 netns ns1 > /dev/null 2>&1
+if [ $? -ne 0 ];then
+    echo "SKIP: No virtual ethernet pair device support in kernel"
+    exit $ksft_skip
+fi
 ip link add veth1 netns ns0 type veth peer name eth0 netns ns2
 
 ip -net ns0 link set lo up
diff --git a/tools/testing/selftests/powerpc/cache_shape/Makefile b/tools/testing/selftests/powerpc/cache_shape/Makefile
index 1be547434a49..7e0c175b8297 100644
--- a/tools/testing/selftests/powerpc/cache_shape/Makefile
+++ b/tools/testing/selftests/powerpc/cache_shape/Makefile
@@ -1,11 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
-TEST_PROGS := cache_shape
-
-all: $(TEST_PROGS)
-
-$(TEST_PROGS): ../harness.c ../utils.c
+TEST_GEN_PROGS := cache_shape
 
 include ../../lib.mk
 
-clean:
-	rm -f $(TEST_PROGS) *.o
+$(TEST_GEN_PROGS): ../harness.c ../utils.c
diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile
index bf315bcbe663..fae8c52cf8f0 100644
--- a/tools/testing/selftests/powerpc/mm/Makefile
+++ b/tools/testing/selftests/powerpc/mm/Makefile
@@ -3,6 +3,7 @@ noarg:
 	$(MAKE) -C ../
 
 TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao
+TEST_GEN_PROGS_EXTENDED := tlbie_test
 TEST_GEN_FILES := tempfile
 
 include ../../lib.mk
@@ -14,3 +15,4 @@ $(OUTPUT)/prot_sao: ../utils.c
 $(OUTPUT)/tempfile:
 	dd if=/dev/zero of=$@ bs=64k count=1
 
+$(OUTPUT)/tlbie_test: LDLIBS += -lpthread
diff --git a/tools/testing/selftests/powerpc/mm/tlbie_test.c b/tools/testing/selftests/powerpc/mm/tlbie_test.c
new file mode 100644
index 000000000000..f85a0938ab25
--- /dev/null
+++ b/tools/testing/selftests/powerpc/mm/tlbie_test.c
@@ -0,0 +1,734 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2019, Nick Piggin, Gautham R. Shenoy, Aneesh Kumar K.V, IBM Corp.
+ */
+
+/*
+ *
+ * Test tlbie/mtpidr race. We have 4 threads doing flush/load/compare/store
+ * sequence in a loop. The same threads also rung a context switch task
+ * that does sched_yield() in loop.
+ *
+ * The snapshot thread mark the mmap area PROT_READ in between, make a copy
+ * and copy it back to the original area. This helps us to detect if any
+ * store continued to happen after we marked the memory PROT_READ.
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/ipc.h>
+#include <sys/shm.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <linux/futex.h>
+#include <unistd.h>
+#include <asm/unistd.h>
+#include <string.h>
+#include <stdlib.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <time.h>
+#include <stdarg.h>
+#include <sched.h>
+#include <pthread.h>
+#include <signal.h>
+#include <sys/prctl.h>
+
+static inline void dcbf(volatile unsigned int *addr)
+{
+	__asm__ __volatile__ ("dcbf %y0; sync" : : "Z"(*(unsigned char *)addr) : "memory");
+}
+
+static void err_msg(char *msg)
+{
+
+	time_t now;
+	time(&now);
+	printf("=================================\n");
+	printf("    Error: %s\n", msg);
+	printf("    %s", ctime(&now));
+	printf("=================================\n");
+	exit(1);
+}
+
+static char *map1;
+static char *map2;
+static pid_t rim_process_pid;
+
+/*
+ * A "rim-sequence" is defined to be the sequence of the following
+ * operations performed on a memory word:
+ *	1) FLUSH the contents of that word.
+ *	2) LOAD the contents of that word.
+ *	3) COMPARE the contents of that word with the content that was
+ *	           previously stored at that word
+ *	4) STORE new content into that word.
+ *
+ * The threads in this test that perform the rim-sequence are termed
+ * as rim_threads.
+ */
+
+/*
+ * A "corruption" is defined to be the failed COMPARE operation in a
+ * rim-sequence.
+ *
+ * A rim_thread that detects a corruption informs about it to all the
+ * other rim_threads, and the mem_snapshot thread.
+ */
+static volatile unsigned int corruption_found;
+
+/*
+ * This defines the maximum number of rim_threads in this test.
+ *
+ * The THREAD_ID_BITS denote the number of bits required
+ * to represent the thread_ids [0..MAX_THREADS - 1].
+ * We are being a bit paranoid here and set it to 8 bits,
+ * though 6 bits suffice.
+ *
+ */
+#define MAX_THREADS 		64
+#define THREAD_ID_BITS		8
+#define THREAD_ID_MASK		((1 << THREAD_ID_BITS) - 1)
+static unsigned int rim_thread_ids[MAX_THREADS];
+static pthread_t rim_threads[MAX_THREADS];
+
+
+/*
+ * Each rim_thread works on an exclusive "chunk" of size
+ * RIM_CHUNK_SIZE.
+ *
+ * The ith rim_thread works on the ith chunk.
+ *
+ * The ith chunk begins at
+ * map1 + (i * RIM_CHUNK_SIZE)
+ */
+#define RIM_CHUNK_SIZE  	1024
+#define BITS_PER_BYTE 		8
+#define WORD_SIZE     		(sizeof(unsigned int))
+#define WORD_BITS		(WORD_SIZE * BITS_PER_BYTE)
+#define WORDS_PER_CHUNK		(RIM_CHUNK_SIZE/WORD_SIZE)
+
+static inline char *compute_chunk_start_addr(unsigned int thread_id)
+{
+	char *chunk_start;
+
+	chunk_start = (char *)((unsigned long)map1 +
+			       (thread_id * RIM_CHUNK_SIZE));
+
+	return chunk_start;
+}
+
+/*
+ * The "word-offset" of a word-aligned address inside a chunk, is
+ * defined to be the number of words that precede the address in that
+ * chunk.
+ *
+ * WORD_OFFSET_BITS denote the number of bits required to represent
+ * the word-offsets of all the word-aligned addresses of a chunk.
+ */
+#define WORD_OFFSET_BITS	(__builtin_ctz(WORDS_PER_CHUNK))
+#define WORD_OFFSET_MASK	((1 << WORD_OFFSET_BITS) - 1)
+
+static inline unsigned int compute_word_offset(char *start, unsigned int *addr)
+{
+	unsigned int delta_bytes, ret;
+	delta_bytes = (unsigned long)addr - (unsigned long)start;
+
+	ret = delta_bytes/WORD_SIZE;
+
+	return ret;
+}
+
+/*
+ * A "sweep" is defined to be the sequential execution of the
+ * rim-sequence by a rim_thread on its chunk one word at a time,
+ * starting from the first word of its chunk and ending with the last
+ * word of its chunk.
+ *
+ * Each sweep of a rim_thread is uniquely identified by a sweep_id.
+ * SWEEP_ID_BITS denote the number of bits required to represent
+ * the sweep_ids of rim_threads.
+ *
+ * As to why SWEEP_ID_BITS are computed as a function of THREAD_ID_BITS,
+ * WORD_OFFSET_BITS, and WORD_BITS, see the "store-pattern" below.
+ */
+#define SWEEP_ID_BITS		(WORD_BITS - (THREAD_ID_BITS + WORD_OFFSET_BITS))
+#define SWEEP_ID_MASK		((1 << SWEEP_ID_BITS) - 1)
+
+/*
+ * A "store-pattern" is the word-pattern that is stored into a word
+ * location in the 4)STORE step of the rim-sequence.
+ *
+ * In the store-pattern, we shall encode:
+ *
+ *      - The thread-id of the rim_thread performing the store
+ *        (The most significant THREAD_ID_BITS)
+ *
+ *      - The word-offset of the address into which the store is being
+ *        performed (The next WORD_OFFSET_BITS)
+ *
+ *      - The sweep_id of the current sweep in which the store is
+ *        being performed. (The lower SWEEP_ID_BITS)
+ *
+ * Store Pattern: 32 bits
+ * |------------------|--------------------|---------------------------------|
+ * |    Thread id     |  Word offset       |         sweep_id                |
+ * |------------------|--------------------|---------------------------------|
+ *    THREAD_ID_BITS     WORD_OFFSET_BITS          SWEEP_ID_BITS
+ *
+ * In the store pattern, the (Thread-id + Word-offset) uniquely identify the
+ * address to which the store is being performed i.e,
+ *    address == map1 +
+ *              (Thread-id * RIM_CHUNK_SIZE) + (Word-offset * WORD_SIZE)
+ *
+ * And the sweep_id in the store pattern identifies the time when the
+ * store was performed by the rim_thread.
+ *
+ * We shall use this property in the 3)COMPARE step of the
+ * rim-sequence.
+ */
+#define SWEEP_ID_SHIFT	0
+#define WORD_OFFSET_SHIFT	(SWEEP_ID_BITS)
+#define THREAD_ID_SHIFT		(WORD_OFFSET_BITS + SWEEP_ID_BITS)
+
+/*
+ * Compute the store pattern for a given thread with id @tid, at
+ * location @addr in the sweep identified by @sweep_id
+ */
+static inline unsigned int compute_store_pattern(unsigned int tid,
+						 unsigned int *addr,
+						 unsigned int sweep_id)
+{
+	unsigned int ret = 0;
+	char *start = compute_chunk_start_addr(tid);
+	unsigned int word_offset = compute_word_offset(start, addr);
+
+	ret += (tid & THREAD_ID_MASK) << THREAD_ID_SHIFT;
+	ret += (word_offset & WORD_OFFSET_MASK) << WORD_OFFSET_SHIFT;
+	ret += (sweep_id & SWEEP_ID_MASK) << SWEEP_ID_SHIFT;
+	return ret;
+}
+
+/* Extract the thread-id from the given store-pattern */
+static inline unsigned int extract_tid(unsigned int pattern)
+{
+	unsigned int ret;
+
+	ret = (pattern >> THREAD_ID_SHIFT) & THREAD_ID_MASK;
+	return ret;
+}
+
+/* Extract the word-offset from the given store-pattern */
+static inline unsigned int extract_word_offset(unsigned int pattern)
+{
+	unsigned int ret;
+
+	ret = (pattern >> WORD_OFFSET_SHIFT) & WORD_OFFSET_MASK;
+
+	return ret;
+}
+
+/* Extract the sweep-id from the given store-pattern */
+static inline unsigned int extract_sweep_id(unsigned int pattern)
+
+{
+	unsigned int ret;
+
+	ret = (pattern >> SWEEP_ID_SHIFT) & SWEEP_ID_MASK;
+
+	return ret;
+}
+
+/************************************************************
+ *                                                          *
+ *          Logging the output of the verification          *
+ *                                                          *
+ ************************************************************/
+#define LOGDIR_NAME_SIZE 100
+static char logdir[LOGDIR_NAME_SIZE];
+
+static FILE *fp[MAX_THREADS];
+static const char logfilename[] ="Thread-%02d-Chunk";
+
+static inline void start_verification_log(unsigned int tid,
+					  unsigned int *addr,
+					  unsigned int cur_sweep_id,
+					  unsigned int prev_sweep_id)
+{
+	FILE *f;
+	char logfile[30];
+	char path[LOGDIR_NAME_SIZE + 30];
+	char separator[2] = "/";
+	char *chunk_start = compute_chunk_start_addr(tid);
+	unsigned int size = RIM_CHUNK_SIZE;
+
+	sprintf(logfile, logfilename, tid);
+	strcpy(path, logdir);
+	strcat(path, separator);
+	strcat(path, logfile);
+	f = fopen(path, "w");
+
+	if (!f) {
+		err_msg("Unable to create logfile\n");
+	}
+
+	fp[tid] = f;
+
+	fprintf(f, "----------------------------------------------------------\n");
+	fprintf(f, "PID                = %d\n", rim_process_pid);
+	fprintf(f, "Thread id          = %02d\n", tid);
+	fprintf(f, "Chunk Start Addr   = 0x%016lx\n", (unsigned long)chunk_start);
+	fprintf(f, "Chunk Size         = %d\n", size);
+	fprintf(f, "Next Store Addr    = 0x%016lx\n", (unsigned long)addr);
+	fprintf(f, "Current sweep-id   = 0x%08x\n", cur_sweep_id);
+	fprintf(f, "Previous sweep-id  = 0x%08x\n", prev_sweep_id);
+	fprintf(f, "----------------------------------------------------------\n");
+}
+
+static inline void log_anamoly(unsigned int tid, unsigned int *addr,
+			       unsigned int expected, unsigned int observed)
+{
+	FILE *f = fp[tid];
+
+	fprintf(f, "Thread %02d: Addr 0x%lx: Expected 0x%x, Observed 0x%x\n",
+	        tid, (unsigned long)addr, expected, observed);
+	fprintf(f, "Thread %02d: Expected Thread id   = %02d\n", tid, extract_tid(expected));
+	fprintf(f, "Thread %02d: Observed Thread id   = %02d\n", tid, extract_tid(observed));
+	fprintf(f, "Thread %02d: Expected Word offset = %03d\n", tid, extract_word_offset(expected));
+	fprintf(f, "Thread %02d: Observed Word offset = %03d\n", tid, extract_word_offset(observed));
+	fprintf(f, "Thread %02d: Expected sweep-id    = 0x%x\n", tid, extract_sweep_id(expected));
+	fprintf(f, "Thread %02d: Observed sweep-id    = 0x%x\n", tid, extract_sweep_id(observed));
+	fprintf(f, "----------------------------------------------------------\n");
+}
+
+static inline void end_verification_log(unsigned int tid, unsigned nr_anamolies)
+{
+	FILE *f = fp[tid];
+	char logfile[30];
+	char path[LOGDIR_NAME_SIZE + 30];
+	char separator[] = "/";
+
+	fclose(f);
+
+	if (nr_anamolies == 0) {
+		remove(path);
+		return;
+	}
+
+	sprintf(logfile, logfilename, tid);
+	strcpy(path, logdir);
+	strcat(path, separator);
+	strcat(path, logfile);
+
+	printf("Thread %02d chunk has %d corrupted words. For details check %s\n",
+		tid, nr_anamolies, path);
+}
+
+/*
+ * When a COMPARE step of a rim-sequence fails, the rim_thread informs
+ * everyone else via the shared_memory pointed to by
+ * corruption_found variable. On seeing this, every thread verifies the
+ * content of its chunk as follows.
+ *
+ * Suppose a thread identified with @tid was about to store (but not
+ * yet stored) to @next_store_addr in its current sweep identified
+ * @cur_sweep_id. Let @prev_sweep_id indicate the previous sweep_id.
+ *
+ * This implies that for all the addresses @addr < @next_store_addr,
+ * Thread @tid has already performed a store as part of its current
+ * sweep. Hence we expect the content of such @addr to be:
+ *    |-------------------------------------------------|
+ *    | tid   | word_offset(addr) |    cur_sweep_id     |
+ *    |-------------------------------------------------|
+ *
+ * Since Thread @tid is yet to perform stores on address
+ * @next_store_addr and above, we expect the content of such an
+ * address @addr to be:
+ *    |-------------------------------------------------|
+ *    | tid   | word_offset(addr) |    prev_sweep_id    |
+ *    |-------------------------------------------------|
+ *
+ * The verifier function @verify_chunk does this verification and logs
+ * any anamolies that it finds.
+ */
+static void verify_chunk(unsigned int tid, unsigned int *next_store_addr,
+		  unsigned int cur_sweep_id,
+		  unsigned int prev_sweep_id)
+{
+	unsigned int *iter_ptr;
+	unsigned int size = RIM_CHUNK_SIZE;
+	unsigned int expected;
+	unsigned int observed;
+	char *chunk_start = compute_chunk_start_addr(tid);
+
+	int nr_anamolies = 0;
+
+	start_verification_log(tid, next_store_addr,
+			       cur_sweep_id, prev_sweep_id);
+
+	for (iter_ptr = (unsigned int *)chunk_start;
+	     (unsigned long)iter_ptr < (unsigned long)chunk_start + size;
+	     iter_ptr++) {
+		unsigned int expected_sweep_id;
+
+		if (iter_ptr < next_store_addr) {
+			expected_sweep_id = cur_sweep_id;
+		} else {
+			expected_sweep_id = prev_sweep_id;
+		}
+
+		expected = compute_store_pattern(tid, iter_ptr, expected_sweep_id);
+
+		dcbf((volatile unsigned int*)iter_ptr); //Flush before reading
+		observed = *iter_ptr;
+
+	        if (observed != expected) {
+			nr_anamolies++;
+			log_anamoly(tid, iter_ptr, expected, observed);
+		}
+	}
+
+	end_verification_log(tid, nr_anamolies);
+}
+
+static void set_pthread_cpu(pthread_t th, int cpu)
+{
+	cpu_set_t run_cpu_mask;
+	struct sched_param param;
+
+	CPU_ZERO(&run_cpu_mask);
+	CPU_SET(cpu, &run_cpu_mask);
+	pthread_setaffinity_np(th, sizeof(cpu_set_t), &run_cpu_mask);
+
+	param.sched_priority = 1;
+	if (0 && sched_setscheduler(0, SCHED_FIFO, &param) == -1) {
+		/* haven't reproduced with this setting, it kills random preemption which may be a factor */
+		fprintf(stderr, "could not set SCHED_FIFO, run as root?\n");
+	}
+}
+
+static void set_mycpu(int cpu)
+{
+	cpu_set_t run_cpu_mask;
+	struct sched_param param;
+
+	CPU_ZERO(&run_cpu_mask);
+	CPU_SET(cpu, &run_cpu_mask);
+	sched_setaffinity(0, sizeof(cpu_set_t), &run_cpu_mask);
+
+	param.sched_priority = 1;
+	if (0 && sched_setscheduler(0, SCHED_FIFO, &param) == -1) {
+		fprintf(stderr, "could not set SCHED_FIFO, run as root?\n");
+	}
+}
+
+static volatile int segv_wait;
+
+static void segv_handler(int signo, siginfo_t *info, void *extra)
+{
+	while (segv_wait) {
+		sched_yield();
+	}
+
+}
+
+static void set_segv_handler(void)
+{
+	struct sigaction sa;
+
+	sa.sa_flags = SA_SIGINFO;
+	sa.sa_sigaction = segv_handler;
+
+	if (sigaction(SIGSEGV, &sa, NULL) == -1) {
+		perror("sigaction");
+		exit(EXIT_FAILURE);
+	}
+}
+
+int timeout = 0;
+/*
+ * This function is executed by every rim_thread.
+ *
+ * This function performs sweeps over the exclusive chunks of the
+ * rim_threads executing the rim-sequence one word at a time.
+ */
+static void *rim_fn(void *arg)
+{
+	unsigned int tid = *((unsigned int *)arg);
+
+	int size = RIM_CHUNK_SIZE;
+	char *chunk_start = compute_chunk_start_addr(tid);
+
+	unsigned int prev_sweep_id;
+	unsigned int cur_sweep_id = 0;
+
+	/* word access */
+	unsigned int pattern = cur_sweep_id;
+	unsigned int *pattern_ptr = &pattern;
+	unsigned int *w_ptr, read_data;
+
+	set_segv_handler();
+
+	/*
+	 * Let us initialize the chunk:
+	 *
+	 * Each word-aligned address addr in the chunk,
+	 * is initialized to :
+	 *    |-------------------------------------------------|
+	 *    | tid   | word_offset(addr) |         0           |
+	 *    |-------------------------------------------------|
+	 */
+	for (w_ptr = (unsigned int *)chunk_start;
+	     (unsigned long)w_ptr < (unsigned long)(chunk_start) + size;
+	     w_ptr++) {
+
+		*pattern_ptr = compute_store_pattern(tid, w_ptr, cur_sweep_id);
+		*w_ptr = *pattern_ptr;
+	}
+
+	while (!corruption_found && !timeout) {
+		prev_sweep_id = cur_sweep_id;
+		cur_sweep_id = cur_sweep_id + 1;
+
+		for (w_ptr = (unsigned int *)chunk_start;
+		     (unsigned long)w_ptr < (unsigned long)(chunk_start) + size;
+		     w_ptr++)  {
+			unsigned int old_pattern;
+
+			/*
+			 * Compute the pattern that we would have
+			 * stored at this location in the previous
+			 * sweep.
+			 */
+			old_pattern = compute_store_pattern(tid, w_ptr, prev_sweep_id);
+
+			/*
+			 * FLUSH:Ensure that we flush the contents of
+			 *       the cache before loading
+			 */
+			dcbf((volatile unsigned int*)w_ptr); //Flush
+
+			/* LOAD: Read the value */
+			read_data = *w_ptr; //Load
+
+			/*
+			 * COMPARE: Is it the same as what we had stored
+			 *          in the previous sweep ? It better be!
+			 */
+			if (read_data != old_pattern) {
+				/* No it isn't! Tell everyone */
+				corruption_found = 1;
+			}
+
+			/*
+			 * Before performing a store, let us check if
+			 * any rim_thread has found a corruption.
+			 */
+			if (corruption_found || timeout) {
+				/*
+				 * Yes. Someone (including us!) has found
+				 * a corruption :(
+				 *
+				 * Let us verify that our chunk is
+				 * correct.
+				 */
+				/* But first, let us allow the dust to settle down! */
+				verify_chunk(tid, w_ptr, cur_sweep_id, prev_sweep_id);
+
+				return 0;
+			}
+
+			/*
+			 * Compute the new pattern that we are going
+			 * to write to this location
+			 */
+			*pattern_ptr = compute_store_pattern(tid, w_ptr, cur_sweep_id);
+
+			/*
+			 * STORE: Now let us write this pattern into
+			 *        the location
+			 */
+			*w_ptr = *pattern_ptr;
+		}
+	}
+
+	return NULL;
+}
+
+
+static unsigned long start_cpu = 0;
+static unsigned long nrthreads = 4;
+
+static pthread_t mem_snapshot_thread;
+
+static void *mem_snapshot_fn(void *arg)
+{
+	int page_size = getpagesize();
+	size_t size = page_size;
+	void *tmp = malloc(size);
+
+	while (!corruption_found && !timeout) {
+		/* Stop memory migration once corruption is found */
+		segv_wait = 1;
+
+		mprotect(map1, size, PROT_READ);
+
+		/*
+		 * Load from the working alias (map1). Loading from map2
+		 * also fails.
+		 */
+		memcpy(tmp, map1, size);
+
+		/*
+		 * Stores must go via map2 which has write permissions, but
+		 * the corrupted data tends to be seen in the snapshot buffer,
+		 * so corruption does not appear to be introduced at the
+		 * copy-back via map2 alias here.
+		 */
+		memcpy(map2, tmp, size);
+		/*
+		 * Before releasing other threads, must ensure the copy
+		 * back to
+		 */
+		asm volatile("sync" ::: "memory");
+		mprotect(map1, size, PROT_READ|PROT_WRITE);
+		asm volatile("sync" ::: "memory");
+		segv_wait = 0;
+
+		usleep(1); /* This value makes a big difference */
+	}
+
+	return 0;
+}
+
+void alrm_sighandler(int sig)
+{
+	timeout = 1;
+}
+
+int main(int argc, char *argv[])
+{
+	int c;
+	int page_size = getpagesize();
+	time_t now;
+	int i, dir_error;
+	pthread_attr_t attr;
+	key_t shm_key = (key_t) getpid();
+	int shmid, run_time = 20 * 60;
+	struct sigaction sa_alrm;
+
+	snprintf(logdir, LOGDIR_NAME_SIZE,
+		 "/tmp/logdir-%u", (unsigned int)getpid());
+	while ((c = getopt(argc, argv, "r:hn:l:t:")) != -1) {
+		switch(c) {
+		case 'r':
+			start_cpu = strtoul(optarg, NULL, 10);
+			break;
+		case 'h':
+			printf("%s [-r <start_cpu>] [-n <nrthreads>] [-l <logdir>] [-t <timeout>]\n", argv[0]);
+			exit(0);
+			break;
+		case 'n':
+			nrthreads = strtoul(optarg, NULL, 10);
+			break;
+		case 'l':
+			strncpy(logdir, optarg, LOGDIR_NAME_SIZE - 1);
+			break;
+		case 't':
+			run_time = strtoul(optarg, NULL, 10);
+			break;
+		default:
+			printf("invalid option\n");
+			exit(0);
+			break;
+		}
+	}
+
+	if (nrthreads > MAX_THREADS)
+		nrthreads = MAX_THREADS;
+
+	shmid = shmget(shm_key, page_size, IPC_CREAT|0666);
+	if (shmid < 0) {
+		err_msg("Failed shmget\n");
+	}
+
+	map1 = shmat(shmid, NULL, 0);
+	if (map1 == (void *) -1) {
+		err_msg("Failed shmat");
+	}
+
+	map2 = shmat(shmid, NULL, 0);
+	if (map2 == (void *) -1) {
+		err_msg("Failed shmat");
+	}
+
+	dir_error = mkdir(logdir, 0755);
+
+	if (dir_error) {
+		err_msg("Failed mkdir");
+	}
+
+	printf("start_cpu list:%lu\n", start_cpu);
+	printf("number of worker threads:%lu + 1 snapshot thread\n", nrthreads);
+	printf("Allocated address:0x%016lx + secondary map:0x%016lx\n", (unsigned long)map1, (unsigned long)map2);
+	printf("logdir at : %s\n", logdir);
+	printf("Timeout: %d seconds\n", run_time);
+
+	time(&now);
+	printf("=================================\n");
+	printf("     Starting Test\n");
+	printf("     %s", ctime(&now));
+	printf("=================================\n");
+
+	for (i = 0; i < nrthreads; i++) {
+		if (1 && !fork()) {
+			prctl(PR_SET_PDEATHSIG, SIGKILL);
+			set_mycpu(start_cpu + i);
+			for (;;)
+				sched_yield();
+			exit(0);
+		}
+	}
+
+
+	sa_alrm.sa_handler = &alrm_sighandler;
+	sigemptyset(&sa_alrm.sa_mask);
+	sa_alrm.sa_flags = 0;
+
+	if (sigaction(SIGALRM, &sa_alrm, 0) == -1) {
+		err_msg("Failed signal handler registration\n");
+	}
+
+	alarm(run_time);
+
+	pthread_attr_init(&attr);
+	for (i = 0; i < nrthreads; i++) {
+		rim_thread_ids[i] = i;
+		pthread_create(&rim_threads[i], &attr, rim_fn, &rim_thread_ids[i]);
+		set_pthread_cpu(rim_threads[i], start_cpu + i);
+	}
+
+	pthread_create(&mem_snapshot_thread, &attr, mem_snapshot_fn, map1);
+	set_pthread_cpu(mem_snapshot_thread, start_cpu + i);
+
+
+	pthread_join(mem_snapshot_thread, NULL);
+	for (i = 0; i < nrthreads; i++) {
+		pthread_join(rim_threads[i], NULL);
+	}
+
+	if (!timeout) {
+		time(&now);
+		printf("=================================\n");
+		printf("      Data Corruption Detected\n");
+		printf("      %s", ctime(&now));
+		printf("      See logfiles in %s\n", logdir);
+		printf("=================================\n");
+		return 1;
+	}
+	return 0;
+}
diff --git a/tools/testing/selftests/powerpc/signal/Makefile b/tools/testing/selftests/powerpc/signal/Makefile
index a7cbd5082e27..4213978f3ee2 100644
--- a/tools/testing/selftests/powerpc/signal/Makefile
+++ b/tools/testing/selftests/powerpc/signal/Makefile
@@ -1,14 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
-TEST_PROGS := signal signal_tm
-
-all: $(TEST_PROGS)
-
-$(TEST_PROGS): ../harness.c ../utils.c signal.S
+TEST_GEN_PROGS := signal signal_tm
 
 CFLAGS += -maltivec
-signal_tm: CFLAGS += -mhtm
+$(OUTPUT)/signal_tm: CFLAGS += -mhtm
 
 include ../../lib.mk
 
-clean:
-	rm -f $(TEST_PROGS) *.o
+$(TEST_GEN_PROGS): ../harness.c ../utils.c signal.S
diff --git a/tools/testing/selftests/powerpc/switch_endian/Makefile b/tools/testing/selftests/powerpc/switch_endian/Makefile
index 30b8ff8fb82e..e4cedfe9753d 100644
--- a/tools/testing/selftests/powerpc/switch_endian/Makefile
+++ b/tools/testing/selftests/powerpc/switch_endian/Makefile
@@ -7,6 +7,7 @@ EXTRA_CLEAN = $(OUTPUT)/*.o $(OUTPUT)/check-reversed.S
 
 include ../../lib.mk
 
+$(OUTPUT)/switch_endian_test: ASFLAGS += -I $(OUTPUT)
 $(OUTPUT)/switch_endian_test: $(OUTPUT)/check-reversed.S
 
 $(OUTPUT)/check-reversed.o: $(OUTPUT)/check.o
diff --git a/tools/testing/selftests/timers/adjtick.c b/tools/testing/selftests/timers/adjtick.c
index 0caca3a06bd2..54d8d87f36b3 100644
--- a/tools/testing/selftests/timers/adjtick.c
+++ b/tools/testing/selftests/timers/adjtick.c
@@ -136,6 +136,7 @@ int check_tick_adj(long tickval)
 
 	eppm = get_ppm_drift();
 	printf("%lld usec, %lld ppm", systick + (systick * eppm / MILLION), eppm);
+	fflush(stdout);
 
 	tx1.modes = 0;
 	adjtimex(&tx1);
diff --git a/tools/testing/selftests/timers/leapcrash.c b/tools/testing/selftests/timers/leapcrash.c
index 830c462f605d..dc80728ed191 100644
--- a/tools/testing/selftests/timers/leapcrash.c
+++ b/tools/testing/selftests/timers/leapcrash.c
@@ -101,6 +101,7 @@ int main(void)
 		}
 		clear_time_state();
 		printf(".");
+		fflush(stdout);
 	}
 	printf("[OK]\n");
 	return ksft_exit_pass();
diff --git a/tools/testing/selftests/timers/mqueue-lat.c b/tools/testing/selftests/timers/mqueue-lat.c
index 1867db5d6f5e..7916cf5cc6ff 100644
--- a/tools/testing/selftests/timers/mqueue-lat.c
+++ b/tools/testing/selftests/timers/mqueue-lat.c
@@ -102,6 +102,7 @@ int main(int argc, char **argv)
 	int ret;
 
 	printf("Mqueue latency :                          ");
+	fflush(stdout);
 
 	ret = mqueue_lat_test();
 	if (ret < 0) {
diff --git a/tools/testing/selftests/timers/nanosleep.c b/tools/testing/selftests/timers/nanosleep.c
index 8adb0bb51d4d..71b5441c2fd9 100644
--- a/tools/testing/selftests/timers/nanosleep.c
+++ b/tools/testing/selftests/timers/nanosleep.c
@@ -142,6 +142,7 @@ int main(int argc, char **argv)
 			continue;
 
 		printf("Nanosleep %-31s ", clockstring(clockid));
+		fflush(stdout);
 
 		length = 10;
 		while (length <= (NSEC_PER_SEC * 10)) {
diff --git a/tools/testing/selftests/timers/nsleep-lat.c b/tools/testing/selftests/timers/nsleep-lat.c
index c3c3dc10db17..eb3e79ed7b4a 100644
--- a/tools/testing/selftests/timers/nsleep-lat.c
+++ b/tools/testing/selftests/timers/nsleep-lat.c
@@ -155,6 +155,7 @@ int main(int argc, char **argv)
 			continue;
 
 		printf("nsleep latency %-26s ", clockstring(clockid));
+		fflush(stdout);
 
 		length = 10;
 		while (length <= (NSEC_PER_SEC * 10)) {
diff --git a/tools/testing/selftests/timers/raw_skew.c b/tools/testing/selftests/timers/raw_skew.c
index dcf73c5dab6e..b41d8dd0c40c 100644
--- a/tools/testing/selftests/timers/raw_skew.c
+++ b/tools/testing/selftests/timers/raw_skew.c
@@ -112,6 +112,7 @@ int main(int argv, char **argc)
 		printf("WARNING: ADJ_OFFSET in progress, this will cause inaccurate results\n");
 
 	printf("Estimating clock drift: ");
+	fflush(stdout);
 	sleep(120);
 
 	get_monotonic_and_raw(&mon, &raw);
diff --git a/tools/testing/selftests/timers/set-tai.c b/tools/testing/selftests/timers/set-tai.c
index 70fed27d8fd3..8c4179ee2ca2 100644
--- a/tools/testing/selftests/timers/set-tai.c
+++ b/tools/testing/selftests/timers/set-tai.c
@@ -55,6 +55,7 @@ int main(int argc, char **argv)
 	printf("tai offset started at %i\n", ret);
 
 	printf("Checking tai offsets can be properly set: ");
+	fflush(stdout);
 	for (i = 1; i <= 60; i++) {
 		ret = set_tai(i);
 		ret = get_tai();
diff --git a/tools/testing/selftests/timers/set-tz.c b/tools/testing/selftests/timers/set-tz.c
index 877fd5532fee..62bd33eb16f0 100644
--- a/tools/testing/selftests/timers/set-tz.c
+++ b/tools/testing/selftests/timers/set-tz.c
@@ -65,6 +65,7 @@ int main(int argc, char **argv)
 	printf("tz_minuteswest started at %i, dst at %i\n", min, dst);
 
 	printf("Checking tz_minuteswest can be properly set: ");
+	fflush(stdout);
 	for (i = -15*60; i < 15*60; i += 30) {
 		ret = set_tz(i, dst);
 		ret = get_tz_min();
@@ -76,6 +77,7 @@ int main(int argc, char **argv)
 	printf("[OK]\n");
 
 	printf("Checking invalid tz_minuteswest values are caught: ");
+	fflush(stdout);
 
 	if (!set_tz(-15*60-1, dst)) {
 		printf("[FAILED] %i didn't return failure!\n", -15*60-1);
diff --git a/tools/testing/selftests/timers/threadtest.c b/tools/testing/selftests/timers/threadtest.c
index 759c9c06f1a0..cf3e48919874 100644
--- a/tools/testing/selftests/timers/threadtest.c
+++ b/tools/testing/selftests/timers/threadtest.c
@@ -163,6 +163,7 @@ int main(int argc, char **argv)
 	strftime(buf, 255, "%a, %d %b %Y %T %z", localtime(&start));
 	printf("%s\n", buf);
 	printf("Testing consistency with %i threads for %ld seconds: ", thread_count, runtime);
+	fflush(stdout);
 
 	/* spawn */
 	for (i = 0; i < thread_count; i++)
diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c
index d9d3ab93b31a..5397de708d3c 100644
--- a/tools/testing/selftests/timers/valid-adjtimex.c
+++ b/tools/testing/selftests/timers/valid-adjtimex.c
@@ -123,6 +123,7 @@ int validate_freq(void)
 	/* Set the leap second insert flag */
 
 	printf("Testing ADJ_FREQ... ");
+	fflush(stdout);
 	for (i = 0; i < NUM_FREQ_VALID; i++) {
 		tx.modes = ADJ_FREQUENCY;
 		tx.freq = valid_freq[i];
@@ -250,6 +251,7 @@ int set_bad_offset(long sec, long usec, int use_nano)
 int validate_set_offset(void)
 {
 	printf("Testing ADJ_SETOFFSET... ");
+	fflush(stdout);
 
 	/* Test valid values */
 	if (set_offset(NSEC_PER_SEC - 1, 1))
diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c
index 6e290874b70e..f1c6e025cbe5 100644
--- a/tools/testing/selftests/watchdog/watchdog-test.c
+++ b/tools/testing/selftests/watchdog/watchdog-test.c
@@ -89,7 +89,13 @@ int main(int argc, char *argv[])
 	fd = open("/dev/watchdog", O_WRONLY);
 
 	if (fd == -1) {
-		printf("Watchdog device not enabled.\n");
+		if (errno == ENOENT)
+			printf("Watchdog device not enabled.\n");
+		else if (errno == EACCES)
+			printf("Run watchdog as root.\n");
+		else
+			printf("Watchdog device open failed %s\n",
+				strerror(errno));
 		exit(-1);
 	}
 
@@ -103,7 +109,7 @@ int main(int argc, char *argv[])
 				printf("Last boot is caused by: %s.\n", (flags != 0) ?
 					"Watchdog" : "Power-On-Reset");
 			else
-				printf("WDIOC_GETBOOTSTATUS errno '%s'\n", strerror(errno));
+				printf("WDIOC_GETBOOTSTATUS error '%s'\n", strerror(errno));
 			break;
 		case 'd':
 			flags = WDIOS_DISABLECARD;
@@ -111,7 +117,7 @@ int main(int argc, char *argv[])
 			if (!ret)
 				printf("Watchdog card disabled.\n");
 			else
-				printf("WDIOS_DISABLECARD errno '%s'\n", strerror(errno));
+				printf("WDIOS_DISABLECARD error '%s'\n", strerror(errno));
 			break;
 		case 'e':
 			flags = WDIOS_ENABLECARD;
@@ -119,7 +125,7 @@ int main(int argc, char *argv[])
 			if (!ret)
 				printf("Watchdog card enabled.\n");
 			else
-				printf("WDIOS_ENABLECARD errno '%s'\n", strerror(errno));
+				printf("WDIOS_ENABLECARD error '%s'\n", strerror(errno));
 			break;
 		case 'p':
 			ping_rate = strtoul(optarg, NULL, 0);
@@ -133,7 +139,7 @@ int main(int argc, char *argv[])
 			if (!ret)
 				printf("Watchdog timeout set to %u seconds.\n", flags);
 			else
-				printf("WDIOC_SETTIMEOUT errno '%s'\n", strerror(errno));
+				printf("WDIOC_SETTIMEOUT error '%s'\n", strerror(errno));
 			break;
 		default:
 			usage(argv[0]);
diff --git a/tools/usb/usbip/libsrc/usbip_host_common.c b/tools/usb/usbip/libsrc/usbip_host_common.c
index 6ff7b601f854..4bb905925b0e 100644
--- a/tools/usb/usbip/libsrc/usbip_host_common.c
+++ b/tools/usb/usbip/libsrc/usbip_host_common.c
@@ -43,7 +43,7 @@ static int32_t read_attr_usbip_status(struct usbip_usb_device *udev)
 	int size;
 	int fd;
 	int length;
-	char status;
+	char status[2] = { 0 };
 	int value = 0;
 
 	size = snprintf(status_attr_path, sizeof(status_attr_path),
@@ -61,15 +61,15 @@ static int32_t read_attr_usbip_status(struct usbip_usb_device *udev)
 		return -1;
 	}
 
-	length = read(fd, &status, 1);
+	length = read(fd, status, 1);
 	if (length < 0) {
 		err("error reading attribute %s", status_attr_path);
 		close(fd);
 		return -1;
 	}
 
-	value = atoi(&status);
-
+	value = atoi(status);
+	close(fd);
 	return value;
 }