20 files changed, 140 insertions, 449 deletions

diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index a7c6aa8..891bc77 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -169,7 +169,35 @@ endif
 
 ### --- END CONFIGURATION SECTION ---
 
-BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)util -Iutil -I. -I$(TRACE_EVENT_DIR) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
+endif
+
+ifneq ($(objtree),)
+#$(info Determined 'objtree' to be $(objtree))
+endif
+
+ifneq ($(OUTPUT),)
+#$(info Determined 'OUTPUT' to be $(OUTPUT))
+endif
+
+BASIC_CFLAGS = \
+	-Iutil/include \
+	-Iarch/$(ARCH)/include \
+	$(if $(objtree),-I$(objtree)/arch/$(ARCH)/include/generated/uapi) \
+	-I$(srctree)/arch/$(ARCH)/include/uapi \
+	-I$(srctree)/arch/$(ARCH)/include \
+	$(if $(objtree),-I$(objtree)/include/generated/uapi) \
+	-I$(srctree)/include/uapi \
+	-I$(srctree)/include \
+	-I$(OUTPUT)util \
+	-Iutil \
+	-I. \
+	-I$(TRACE_EVENT_DIR) \
+	-D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
+
 BASIC_LDFLAGS =
 
 ifeq ($(call try-cc,$(SOURCE_BIONIC),$(CFLAGS),bionic),y)
diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h
index 46fc9f1..7fcdcdb 100644
--- a/tools/perf/arch/x86/include/perf_regs.h
+++ b/tools/perf/arch/x86/include/perf_regs.h
@@ -3,7 +3,7 @@
 
 #include <stdlib.h>
 #include "../../util/types.h"
-#include "../../../../../arch/x86/include/asm/perf_regs.h"
+#include <asm/perf_regs.h>
 
 #ifndef ARCH_X86_64
 #define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1)
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 836c82f..ca3f80e 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -22,9 +22,10 @@
 #include <pthread.h>
 #include <math.h>
 
-#include "../../arch/x86/include/asm/svm.h"
-#include "../../arch/x86/include/asm/vmx.h"
-#include "../../arch/x86/include/asm/kvm.h"
+#if defined(__i386__) || defined(__x86_64__)
+#include <asm/svm.h>
+#include <asm/vmx.h>
+#include <asm/kvm.h>
 
 struct event_key {
 	#define INVALID_KEY     (~0ULL)
@@ -58,7 +59,7 @@ struct kvm_event_key {
 };
 
 
-struct perf_kvm;
+struct perf_kvm_stat;
 
 struct kvm_events_ops {
 	bool (*is_begin_event)(struct perf_evsel *evsel,
@@ -66,7 +67,7 @@ struct kvm_events_ops {
 			       struct event_key *key);
 	bool (*is_end_event)(struct perf_evsel *evsel,
 			     struct perf_sample *sample, struct event_key *key);
-	void (*decode_key)(struct perf_kvm *kvm, struct event_key *key,
+	void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key,
 			   char decode[20]);
 	const char *name;
 };
@@ -79,7 +80,7 @@ struct exit_reasons_table {
 #define EVENTS_BITS		12
 #define EVENTS_CACHE_SIZE	(1UL << EVENTS_BITS)
 
-struct perf_kvm {
+struct perf_kvm_stat {
 	struct perf_tool    tool;
 	struct perf_session *session;
 
@@ -146,7 +147,7 @@ static struct exit_reasons_table svm_exit_reasons[] = {
 	SVM_EXIT_REASONS
 };
 
-static const char *get_exit_reason(struct perf_kvm *kvm, u64 exit_code)
+static const char *get_exit_reason(struct perf_kvm_stat *kvm, u64 exit_code)
 {
 	int i = kvm->exit_reasons_size;
 	struct exit_reasons_table *tbl = kvm->exit_reasons;
@@ -162,7 +163,7 @@ static const char *get_exit_reason(struct perf_kvm *kvm, u64 exit_code)
 	return "UNKNOWN";
 }
 
-static void exit_event_decode_key(struct perf_kvm *kvm,
+static void exit_event_decode_key(struct perf_kvm_stat *kvm,
 				  struct event_key *key,
 				  char decode[20])
 {
@@ -228,7 +229,7 @@ static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample,
 	return false;
 }
 
-static void mmio_event_decode_key(struct perf_kvm *kvm __maybe_unused,
+static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
 				  struct event_key *key,
 				  char decode[20])
 {
@@ -271,7 +272,7 @@ static bool ioport_event_end(struct perf_evsel *evsel,
 	return kvm_entry_event(evsel);
 }
 
-static void ioport_event_decode_key(struct perf_kvm *kvm __maybe_unused,
+static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
 				    struct event_key *key,
 				    char decode[20])
 {
@@ -286,7 +287,7 @@ static struct kvm_events_ops ioport_events = {
 	.name = "IO Port Access"
 };
 
-static bool register_kvm_events_ops(struct perf_kvm *kvm)
+static bool register_kvm_events_ops(struct perf_kvm_stat *kvm)
 {
 	bool ret = true;
 
@@ -311,7 +312,7 @@ struct vcpu_event_record {
 };
 
 
-static void init_kvm_event_record(struct perf_kvm *kvm)
+static void init_kvm_event_record(struct perf_kvm_stat *kvm)
 {
 	unsigned int i;
 
@@ -360,7 +361,7 @@ static struct kvm_event *kvm_alloc_init_event(struct event_key *key)
 	return event;
 }
 
-static struct kvm_event *find_create_kvm_event(struct perf_kvm *kvm,
+static struct kvm_event *find_create_kvm_event(struct perf_kvm_stat *kvm,
 					       struct event_key *key)
 {
 	struct kvm_event *event;
@@ -382,7 +383,7 @@ static struct kvm_event *find_create_kvm_event(struct perf_kvm *kvm,
 	return event;
 }
 
-static bool handle_begin_event(struct perf_kvm *kvm,
+static bool handle_begin_event(struct perf_kvm_stat *kvm,
 			       struct vcpu_event_record *vcpu_record,
 			       struct event_key *key, u64 timestamp)
 {
@@ -429,7 +430,7 @@ static bool update_kvm_event(struct kvm_event *event, int vcpu_id,
 	return true;
 }
 
-static bool handle_end_event(struct perf_kvm *kvm,
+static bool handle_end_event(struct perf_kvm_stat *kvm,
 			     struct vcpu_event_record *vcpu_record,
 			     struct event_key *key,
 			     u64 timestamp)
@@ -496,7 +497,7 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread,
 	return thread->priv;
 }
 
-static bool handle_kvm_event(struct perf_kvm *kvm,
+static bool handle_kvm_event(struct perf_kvm_stat *kvm,
 			     struct thread *thread,
 			     struct perf_evsel *evsel,
 			     struct perf_sample *sample)
@@ -556,7 +557,7 @@ static struct kvm_event_key keys[] = {
 	{ NULL, NULL }
 };
 
-static bool select_key(struct perf_kvm *kvm)
+static bool select_key(struct perf_kvm_stat *kvm)
 {
 	int i;
 
@@ -592,7 +593,8 @@ static void insert_to_result(struct rb_root *result, struct kvm_event *event,
 	rb_insert_color(&event->rb, result);
 }
 
-static void update_total_count(struct perf_kvm *kvm, struct kvm_event *event)
+static void
+update_total_count(struct perf_kvm_stat *kvm, struct kvm_event *event)
 {
 	int vcpu = kvm->trace_vcpu;
 
@@ -605,7 +607,7 @@ static bool event_is_valid(struct kvm_event *event, int vcpu)
 	return !!get_event_count(event, vcpu);
 }
 
-static void sort_result(struct perf_kvm *kvm)
+static void sort_result(struct perf_kvm_stat *kvm)
 {
 	unsigned int i;
 	int vcpu = kvm->trace_vcpu;
@@ -644,7 +646,7 @@ static void print_vcpu_info(int vcpu)
 		pr_info("VCPU %d:\n\n", vcpu);
 }
 
-static void print_result(struct perf_kvm *kvm)
+static void print_result(struct perf_kvm_stat *kvm)
 {
 	char decode[20];
 	struct kvm_event *event;
@@ -687,7 +689,8 @@ static int process_sample_event(struct perf_tool *tool,
 				struct machine *machine)
 {
 	struct thread *thread = machine__findnew_thread(machine, sample->tid);
-	struct perf_kvm *kvm = container_of(tool, struct perf_kvm, tool);
+	struct perf_kvm_stat *kvm = container_of(tool, struct perf_kvm_stat,
+						 tool);
 
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",
@@ -718,7 +721,7 @@ static int get_cpu_isa(struct perf_session *session)
 	return isa;
 }
 
-static int read_events(struct perf_kvm *kvm)
+static int read_events(struct perf_kvm_stat *kvm)
 {
 	int ret;
 
@@ -767,7 +770,7 @@ static bool verify_vcpu(int vcpu)
 	return true;
 }
 
-static int kvm_events_report_vcpu(struct perf_kvm *kvm)
+static int kvm_events_report_vcpu(struct perf_kvm_stat *kvm)
 {
 	int ret = -EINVAL;
 	int vcpu = kvm->trace_vcpu;
@@ -815,7 +818,8 @@ static const char * const record_args[] = {
 		_p;			\
 	})
 
-static int kvm_events_record(struct perf_kvm *kvm, int argc, const char **argv)
+static int
+kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
 {
 	unsigned int rec_argc, i, j;
 	const char **rec_argv;
@@ -838,7 +842,8 @@ static int kvm_events_record(struct perf_kvm *kvm, int argc, const char **argv)
 	return cmd_record(i, rec_argv, NULL);
 }
 
-static int kvm_events_report(struct perf_kvm *kvm, int argc, const char **argv)
+static int
+kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
 {
 	const struct option kvm_events_report_options[] = {
 		OPT_STRING(0, "event", &kvm->report_event, "report event",
@@ -881,24 +886,37 @@ static void print_kvm_stat_usage(void)
 	printf("\nOtherwise, it is the alias of 'perf stat':\n");
 }
 
-static int kvm_cmd_stat(struct perf_kvm *kvm, int argc, const char **argv)
+static int kvm_cmd_stat(const char *file_name, int argc, const char **argv)
 {
+	struct perf_kvm_stat kvm = {
+		.file_name = file_name,
+
+		.trace_vcpu	= -1,
+		.report_event	= "vmexit",
+		.sort_key	= "sample",
+
+		.exit_reasons = svm_exit_reasons,
+		.exit_reasons_size = ARRAY_SIZE(svm_exit_reasons),
+		.exit_reasons_isa = "SVM",
+	};
+
 	if (argc == 1) {
 		print_kvm_stat_usage();
 		goto perf_stat;
 	}
 
 	if (!strncmp(argv[1], "rec", 3))
-		return kvm_events_record(kvm, argc - 1, argv + 1);
+		return kvm_events_record(&kvm, argc - 1, argv + 1);
 
 	if (!strncmp(argv[1], "rep", 3))
-		return kvm_events_report(kvm, argc - 1 , argv + 1);
+		return kvm_events_report(&kvm, argc - 1 , argv + 1);
 
 perf_stat:
 	return cmd_stat(argc, argv, NULL);
 }
+#endif
 
-static int __cmd_record(struct perf_kvm *kvm, int argc, const char **argv)
+static int __cmd_record(const char *file_name, int argc, const char **argv)
 {
 	int rec_argc, i = 0, j;
 	const char **rec_argv;
@@ -907,7 +925,7 @@ static int __cmd_record(struct perf_kvm *kvm, int argc, const char **argv)
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 	rec_argv[i++] = strdup("record");
 	rec_argv[i++] = strdup("-o");
-	rec_argv[i++] = strdup(kvm->file_name);
+	rec_argv[i++] = strdup(file_name);
 	for (j = 1; j < argc; j++, i++)
 		rec_argv[i] = argv[j];
 
@@ -916,7 +934,7 @@ static int __cmd_record(struct perf_kvm *kvm, int argc, const char **argv)
 	return cmd_record(i, rec_argv, NULL);
 }
 
-static int __cmd_report(struct perf_kvm *kvm, int argc, const char **argv)
+static int __cmd_report(const char *file_name, int argc, const char **argv)
 {
 	int rec_argc, i = 0, j;
 	const char **rec_argv;
@@ -925,7 +943,7 @@ static int __cmd_report(struct perf_kvm *kvm, int argc, const char **argv)
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 	rec_argv[i++] = strdup("report");
 	rec_argv[i++] = strdup("-i");
-	rec_argv[i++] = strdup(kvm->file_name);
+	rec_argv[i++] = strdup(file_name);
 	for (j = 1; j < argc; j++, i++)
 		rec_argv[i] = argv[j];
 
@@ -934,7 +952,8 @@ static int __cmd_report(struct perf_kvm *kvm, int argc, const char **argv)
 	return cmd_report(i, rec_argv, NULL);
 }
 
-static int __cmd_buildid_list(struct perf_kvm *kvm, int argc, const char **argv)
+static int
+__cmd_buildid_list(const char *file_name, int argc, const char **argv)
 {
 	int rec_argc, i = 0, j;
 	const char **rec_argv;
@@ -943,7 +962,7 @@ static int __cmd_buildid_list(struct perf_kvm *kvm, int argc, const char **argv)
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 	rec_argv[i++] = strdup("buildid-list");
 	rec_argv[i++] = strdup("-i");
-	rec_argv[i++] = strdup(kvm->file_name);
+	rec_argv[i++] = strdup(file_name);
 	for (j = 1; j < argc; j++, i++)
 		rec_argv[i] = argv[j];
 
@@ -954,20 +973,12 @@ static int __cmd_buildid_list(struct perf_kvm *kvm, int argc, const char **argv)
 
 int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	struct perf_kvm kvm = {
-		.trace_vcpu	= -1,
-		.report_event	= "vmexit",
-		.sort_key	= "sample",
-
-		.exit_reasons = svm_exit_reasons,
-		.exit_reasons_size = ARRAY_SIZE(svm_exit_reasons),
-		.exit_reasons_isa = "SVM",
-	};
+	const char *file_name;
 
 	const struct option kvm_options[] = {
-		OPT_STRING('i', "input", &kvm.file_name, "file",
+		OPT_STRING('i', "input", &file_name, "file",
 			   "Input file name"),
-		OPT_STRING('o', "output", &kvm.file_name, "file",
+		OPT_STRING('o', "output", &file_name, "file",
 			   "Output file name"),
 		OPT_BOOLEAN(0, "guest", &perf_guest,
 			    "Collect guest os data"),
@@ -1002,32 +1013,34 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (!perf_host)
 		perf_guest = 1;
 
-	if (!kvm.file_name) {
+	if (!file_name) {
 		if (perf_host && !perf_guest)
-			kvm.file_name = strdup("perf.data.host");
+			file_name = strdup("perf.data.host");
 		else if (!perf_host && perf_guest)
-			kvm.file_name = strdup("perf.data.guest");
+			file_name = strdup("perf.data.guest");
 		else
-			kvm.file_name = strdup("perf.data.kvm");
+			file_name = strdup("perf.data.kvm");
 
-		if (!kvm.file_name) {
+		if (!file_name) {
 			pr_err("Failed to allocate memory for filename\n");
 			return -ENOMEM;
 		}
 	}
 
 	if (!strncmp(argv[0], "rec", 3))
-		return __cmd_record(&kvm, argc, argv);
+		return __cmd_record(file_name, argc, argv);
 	else if (!strncmp(argv[0], "rep", 3))
-		return __cmd_report(&kvm, argc, argv);
+		return __cmd_report(file_name, argc, argv);
 	else if (!strncmp(argv[0], "diff", 4))
 		return cmd_diff(argc, argv, NULL);
 	else if (!strncmp(argv[0], "top", 3))
 		return cmd_top(argc, argv, NULL);
 	else if (!strncmp(argv[0], "buildid-list", 12))
-		return __cmd_buildid_list(&kvm, argc, argv);
+		return __cmd_buildid_list(file_name, argc, argv);
+#if defined(__i386__) || defined(__x86_64__)
 	else if (!strncmp(argv[0], "stat", 4))
-		return kvm_cmd_stat(&kvm, argc, argv);
+		return kvm_cmd_stat(file_name, argc, argv);
+#endif
 	else
 		usage_with_options(kvm_usage, kvm_options);
 
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index f53ee0b..2c340e7 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -5,8 +5,9 @@ struct winsize;
 
 void get_term_dimensions(struct winsize *ws);
 
+#include <asm/unistd.h>
+
 #if defined(__i386__)
-#include "../../arch/x86/include/asm/unistd.h"
 #define rmb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
 #define cpu_relax()	asm volatile("rep; nop" ::: "memory");
 #define CPUINFO_PROC	"model name"
@@ -16,7 +17,6 @@ void get_term_dimensions(struct winsize *ws);
 #endif
 
 #if defined(__x86_64__)
-#include "../../arch/x86/include/asm/unistd.h"
 #define rmb()		asm volatile("lfence" ::: "memory")
 #define cpu_relax()	asm volatile("rep; nop" ::: "memory");
 #define CPUINFO_PROC	"model name"
@@ -33,13 +33,11 @@ void get_term_dimensions(struct winsize *ws);
 #endif
 
 #ifdef __s390__
-#include "../../arch/s390/include/asm/unistd.h"
 #define rmb()		asm volatile("bcr 15,0" ::: "memory")
 #define cpu_relax()	asm volatile("" ::: "memory");
 #endif
 
 #ifdef __sh__
-#include "../../arch/sh/include/asm/unistd.h"
 #if defined(__SH4A__) || defined(__SH5__)
 # define rmb()		asm volatile("synco" ::: "memory")
 #else
@@ -50,35 +48,30 @@ void get_term_dimensions(struct winsize *ws);
 #endif
 
 #ifdef __hppa__
-#include "../../arch/parisc/include/asm/unistd.h"
 #define rmb()		asm volatile("" ::: "memory")
 #define cpu_relax()	asm volatile("" ::: "memory");
 #define CPUINFO_PROC	"cpu"
 #endif
 
 #ifdef __sparc__
-#include "../../arch/sparc/include/uapi/asm/unistd.h"
 #define rmb()		asm volatile("":::"memory")
 #define cpu_relax()	asm volatile("":::"memory")
 #define CPUINFO_PROC	"cpu"
 #endif
 
 #ifdef __alpha__
-#include "../../arch/alpha/include/asm/unistd.h"
 #define rmb()		asm volatile("mb" ::: "memory")
 #define cpu_relax()	asm volatile("" ::: "memory")
 #define CPUINFO_PROC	"cpu model"
 #endif
 
 #ifdef __ia64__
-#include "../../arch/ia64/include/asm/unistd.h"
 #define rmb()		asm volatile ("mf" ::: "memory")
 #define cpu_relax()	asm volatile ("hint @pause" ::: "memory")
 #define CPUINFO_PROC	"model name"
 #endif
 
 #ifdef __arm__
-#include "../../arch/arm/include/asm/unistd.h"
 /*
  * Use the __kuser_memory_barrier helper in the CPU helper page. See
  * arch/arm/kernel/entry-armv.S in the kernel source for details.
@@ -89,13 +82,11 @@ void get_term_dimensions(struct winsize *ws);
 #endif
 
 #ifdef __aarch64__
-#include "../../arch/arm64/include/asm/unistd.h"
 #define rmb()		asm volatile("dmb ld" ::: "memory")
 #define cpu_relax()	asm volatile("yield" ::: "memory")
 #endif
 
 #ifdef __mips__
-#include "../../arch/mips/include/asm/unistd.h"
 #define rmb()		asm volatile(					\
 				".set	mips2\n\t"			\
 				"sync\n\t"				\
@@ -112,7 +103,7 @@ void get_term_dimensions(struct winsize *ws);
 #include <sys/types.h>
 #include <sys/syscall.h>
 
-#include "../../include/uapi/linux/perf_event.h"
+#include <linux/perf_event.h>
 #include "util/types.h"
 #include <stdbool.h>
 
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 42a0c8c..32ee478 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -3,8 +3,8 @@
 #include "evsel.h"
 #include "evlist.h"
 #include "sysfs.h"
-#include "../../../include/linux/hw_breakpoint.h"
 #include "tests.h"
+#include <linux/hw_breakpoint.h>
 
 #define TEST_ASSERT_VAL(text, cond) \
 do { \
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1fb636c..1b16dd1 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -18,8 +18,8 @@
 #include "cpumap.h"
 #include "thread_map.h"
 #include "target.h"
-#include "../../../include/linux/hw_breakpoint.h"
-#include "../../../include/uapi/linux/perf_event.h"
+#include <linux/hw_breakpoint.h>
+#include <linux/perf_event.h>
 #include "perf_regs.h"
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index a4c1dd4..3d2b801 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -4,7 +4,7 @@
 #include <linux/list.h>
 #include <stdbool.h>
 #include <stddef.h>
-#include "../../../include/uapi/linux/perf_event.h"
+#include <linux/perf_event.h>
 #include "types.h"
 #include "xyarray.h"
 #include "cgroup.h"
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 195a47a..b7da463 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1379,6 +1379,8 @@ static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused,
 
 		str = tmp + 1;
 		fprintf(fp, "# node%u cpu list : %s\n", c, str);
+
+		str += strlen(str) + 1;
 	}
 	return;
 error:
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 5f1cd68..20f0344 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -1,7 +1,7 @@
 #ifndef __PERF_HEADER_H
 #define __PERF_HEADER_H
 
-#include "../../../include/uapi/linux/perf_event.h"
+#include <linux/perf_event.h>
 #include <sys/types.h>
 #include <stdbool.h>
 #include "types.h"
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 020323a..2d8d53be 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1,4 +1,4 @@
-#include "../../../include/linux/hw_breakpoint.h"
+#include <linux/hw_breakpoint.h>
 #include "util.h"
 #include "../perf.h"
 #include "evlist.h"
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index f639937..b7af80b 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -7,7 +7,7 @@
 #include <linux/list.h>
 #include <stdbool.h>
 #include "types.h"
-#include "../../../include/uapi/linux/perf_event.h"
+#include <linux/perf_event.h>
 #include "types.h"
 
 struct list_head;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 07d553f..a313ed7 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -2,7 +2,7 @@
 #define __PMU_H
 
 #include <linux/bitops.h>
-#include "../../../include/uapi/linux/perf_event.h"
+#include <linux/perf_event.h>
 
 enum {
 	PERF_PMU_FORMAT_VALUE_CONFIG,
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 18d1222b..cea133a 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -8,7 +8,7 @@
 #include "symbol.h"
 #include "thread.h"
 #include <linux/rbtree.h>
-#include "../../../include/uapi/linux/perf_event.h"
+#include <linux/perf_event.h>
 
 struct sample_queue;
 struct ip_callchain;
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 2eeb51b..cfa9068 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -90,17 +90,17 @@ void strbuf_addf(struct strbuf *sb, const char *fmt, ...)
 	if (!strbuf_avail(sb))
 		strbuf_grow(sb, 64);
 	va_start(ap, fmt);
-	len = vscnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap);
+	len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap);
 	va_end(ap);
 	if (len < 0)
-		die("your vscnprintf is broken");
+		die("your vsnprintf is broken");
 	if (len > strbuf_avail(sb)) {
 		strbuf_grow(sb, len);
 		va_start(ap, fmt);
-		len = vscnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap);
+		len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap);
 		va_end(ap);
 		if (len > strbuf_avail(sb)) {
-			die("this should not happen, your snprintf is broken");
+			die("this should not happen, your vsnprintf is broken");
 		}
 	}
 	strbuf_setlen(sb, sb->len + len);
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 2655ae9..ea095ab 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -206,8 +206,10 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
 	retval = pread(fd, msr, sizeof *msr, offset);
 	close(fd);
 
-	if (retval != sizeof *msr)
+	if (retval != sizeof *msr) {
+		fprintf(stderr, "%s offset 0x%zx read failed\n", pathname, offset);
 		return -1;
+	}
 
 	return 0;
 }
@@ -1101,7 +1103,9 @@ void turbostat_loop()
 
 restart:
 	retval = for_all_cpus(get_counters, EVEN_COUNTERS);
-	if (retval) {
+	if (retval < -1) {
+		exit(retval);
+	} else if (retval == -1) {
 		re_initialize();
 		goto restart;
 	}
@@ -1114,7 +1118,9 @@ restart:
 		}
 		sleep(interval_sec);
 		retval = for_all_cpus(get_counters, ODD_COUNTERS);
-		if (retval) {
+		if (retval < -1) {
+			exit(retval);
+		} else if (retval == -1) {
 			re_initialize();
 			goto restart;
 		}
@@ -1126,7 +1132,9 @@ restart:
 		flush_stdout();
 		sleep(interval_sec);
 		retval = for_all_cpus(get_counters, EVEN_COUNTERS);
-		if (retval) {
+		if (retval < -1) {
+			exit(retval);
+		} else if (retval == -1) {
 			re_initialize();
 			goto restart;
 		}
@@ -1545,8 +1553,11 @@ void turbostat_init()
 int fork_it(char **argv)
 {
 	pid_t child_pid;
+	int status;
 
-	for_all_cpus(get_counters, EVEN_COUNTERS);
+	status = for_all_cpus(get_counters, EVEN_COUNTERS);
+	if (status)
+		exit(status);
 	/* clear affinity side-effect of get_counters() */
 	sched_setaffinity(0, cpu_present_setsize, cpu_present_set);
 	gettimeofday(&tv_even, (struct timezone *)NULL);
@@ -1556,7 +1567,6 @@ int fork_it(char **argv)
 		/* child */
 		execvp(argv[0], argv);
 	} else {
-		int status;
 
 		/* parent */
 		if (child_pid == -1) {
@@ -1568,7 +1578,7 @@ int fork_it(char **argv)
 		signal(SIGQUIT, SIG_IGN);
 		if (waitpid(child_pid, &status, 0) == -1) {
 			perror("wait");
-			exit(1);
+			exit(status);
 		}
 	}
 	/*
@@ -1585,7 +1595,7 @@ int fork_it(char **argv)
 
 	fprintf(stderr, "%.6f sec\n", tv_delta.tv_sec + tv_delta.tv_usec/1000000.0);
 
-	return 0;
+	return status;
 }
 
 void cmdline(int argc, char **argv)
@@ -1594,7 +1604,7 @@ void cmdline(int argc, char **argv)
 
 	progname = argv[0];
 
-	while ((opt = getopt(argc, argv, "+pPSvisc:sC:m:M:")) != -1) {
+	while ((opt = getopt(argc, argv, "+pPSvi:sc:sC:m:M:")) != -1) {
 		switch (opt) {
 		case 'p':
 			show_core_only++;
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index b51d787..c7ba761 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -1740,8 +1740,10 @@ sub install {
     open(IN, "$output_config") or dodie("Can't read config file");
     while (<IN>) {
 	if (/CONFIG_MODULES(=y)?/) {
-	    $install_mods = 1 if (defined($1));
-	    last;
+	    if (defined($1)) {
+		$install_mods = 1;
+		last;
+	    }
 	}
     }
     close(IN);
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 4348014..85baf11 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -1,4 +1,4 @@
-TARGETS = breakpoints kcmp mqueue vm cpu-hotplug memory-hotplug epoll
+TARGETS = breakpoints kcmp mqueue vm cpu-hotplug memory-hotplug
 
 all:
 	for TARGET in $(TARGETS); do \
diff --git a/tools/testing/selftests/epoll/Makefile b/tools/testing/selftests/epoll/Makefile
deleted file mode 100644
index 19806ed..0000000
--- a/tools/testing/selftests/epoll/Makefile
+++ /dev/null
@@ -1,11 +0,0 @@
-# Makefile for epoll selftests
-
-all: test_epoll
-%: %.c
-	gcc -pthread -g -o $@ $^
-
-run_tests: all
-	./test_epoll
-
-clean:
-	$(RM) test_epoll
diff --git a/tools/testing/selftests/epoll/test_epoll.c b/tools/testing/selftests/epoll/test_epoll.c
deleted file mode 100644
index e0fcff1e..0000000
--- a/tools/testing/selftests/epoll/test_epoll.c
+++ /dev/null
@@ -1,344 +0,0 @@
-/*
- *  tools/testing/selftests/epoll/test_epoll.c
- *
- *  Copyright 2012 Adobe Systems Incorporated
- *
- *  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.
- *
- *  Paton J. Lewis <palewis@adobe.com>
- *
- */
-
-#include <errno.h>
-#include <fcntl.h>
-#include <pthread.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <sys/epoll.h>
-#include <sys/socket.h>
-
-/*
- * A pointer to an epoll_item_private structure will be stored in the epoll
- * item's event structure so that we can get access to the epoll_item_private
- * data after calling epoll_wait:
- */
-struct epoll_item_private {
-	int index;  /* Position of this struct within the epoll_items array. */
-	int fd;
-	uint32_t events;
-	pthread_mutex_t mutex;  /* Guards the following variables... */
-	int stop;
-	int status;  /* Stores any error encountered while handling item. */
-	/* The following variable allows us to test whether we have encountered
-	   a problem while attempting to cancel and delete the associated
-	   event. When the test program exits, 'deleted' should be exactly
-	   one. If it is greater than one, then the failed test reflects a real
-	   world situation where we would have tried to access the epoll item's
-	   private data after deleting it: */
-	int deleted;
-};
-
-struct epoll_item_private *epoll_items;
-
-/*
- * Delete the specified item from the epoll set. In a real-world secneario this
- * is where we would free the associated data structure, but in this testing
- * environment we retain the structure so that we can test for double-deletion:
- */
-void delete_item(int index)
-{
-	__sync_fetch_and_add(&epoll_items[index].deleted, 1);
-}
-
-/*
- * A pointer to a read_thread_data structure will be passed as the argument to
- * each read thread:
- */
-struct read_thread_data {
-	int stop;
-	int status;  /* Indicates any error encountered by the read thread. */
-	int epoll_set;
-};
-
-/*
- * The function executed by the read threads:
- */
-void *read_thread_function(void *function_data)
-{
-	struct read_thread_data *thread_data =
-		(struct read_thread_data *)function_data;
-	struct epoll_event event_data;
-	struct epoll_item_private *item_data;
-	char socket_data;
-
-	/* Handle events until we encounter an error or this thread's 'stop'
-	   condition is set: */
-	while (1) {
-		int result = epoll_wait(thread_data->epoll_set,
-					&event_data,
-					1,	/* Number of desired events */
-					1000);  /* Timeout in ms */
-		if (result < 0) {
-			/* Breakpoints signal all threads. Ignore that while
-			   debugging: */
-			if (errno == EINTR)
-				continue;
-			thread_data->status = errno;
-			return 0;
-		} else if (thread_data->stop)
-			return 0;
-		else if (result == 0)  /* Timeout */
-			continue;
-
-		/* We need the mutex here because checking for the stop
-		   condition and re-enabling the epoll item need to be done
-		   together as one atomic operation when EPOLL_CTL_DISABLE is
-		   available: */
-		item_data = (struct epoll_item_private *)event_data.data.ptr;
-		pthread_mutex_lock(&item_data->mutex);
-
-		/* Remove the item from the epoll set if we want to stop
-		   handling that event: */
-		if (item_data->stop)
-			delete_item(item_data->index);
-		else {
-			/* Clear the data that was written to the other end of
-			   our non-blocking socket: */
-			do {
-				if (read(item_data->fd, &socket_data, 1) < 1) {
-					if ((errno == EAGAIN) ||
-					    (errno == EWOULDBLOCK))
-						break;
-					else
-						goto error_unlock;
-				}
-			} while (item_data->events & EPOLLET);
-
-			/* The item was one-shot, so re-enable it: */
-			event_data.events = item_data->events;
-			if (epoll_ctl(thread_data->epoll_set,
-						  EPOLL_CTL_MOD,
-						  item_data->fd,
-						  &event_data) < 0)
-				goto error_unlock;
-		}
-
-		pthread_mutex_unlock(&item_data->mutex);
-	}
-
-error_unlock:
-	thread_data->status = item_data->status = errno;
-	pthread_mutex_unlock(&item_data->mutex);
-	return 0;
-}
-
-/*
- * A pointer to a write_thread_data structure will be passed as the argument to
- * the write thread:
- */
-struct write_thread_data {
-	int stop;
-	int status;  /* Indicates any error encountered by the write thread. */
-	int n_fds;
-	int *fds;
-};
-
-/*
- * The function executed by the write thread. It writes a single byte to each
- * socket in turn until the stop condition for this thread is set. If writing to
- * a socket would block (i.e. errno was EAGAIN), we leave that socket alone for
- * the moment and just move on to the next socket in the list. We don't care
- * about the order in which we deliver events to the epoll set. In fact we don't
- * care about the data we're writing to the pipes at all; we just want to
- * trigger epoll events:
- */
-void *write_thread_function(void *function_data)
-{
-	const char data = 'X';
-	int index;
-	struct write_thread_data *thread_data =
-		(struct write_thread_data *)function_data;
-	while (!write_thread_data->stop)
-		for (index = 0;
-		     !thread_data->stop && (index < thread_data->n_fds);
-		     ++index)
-			if ((write(thread_data->fds[index], &data, 1) < 1) &&
-				(errno != EAGAIN) &&
-				(errno != EWOULDBLOCK)) {
-				write_thread_data->status = errno;
-				return;
-			}
-}
-
-/*
- * Arguments are currently ignored:
- */
-int main(int argc, char **argv)
-{
-	const int n_read_threads = 100;
-	const int n_epoll_items = 500;
-	int index;
-	int epoll_set = epoll_create1(0);
-	struct write_thread_data write_thread_data = {
-		0, 0, n_epoll_items, malloc(n_epoll_items * sizeof(int))
-	};
-	struct read_thread_data *read_thread_data =
-		malloc(n_read_threads * sizeof(struct read_thread_data));
-	pthread_t *read_threads = malloc(n_read_threads * sizeof(pthread_t));
-	pthread_t write_thread;
-
-	printf("-----------------\n");
-	printf("Runing test_epoll\n");
-	printf("-----------------\n");
-
-	epoll_items = malloc(n_epoll_items * sizeof(struct epoll_item_private));
-
-	if (epoll_set < 0 || epoll_items == 0 || write_thread_data.fds == 0 ||
-		read_thread_data == 0 || read_threads == 0)
-		goto error;
-
-	if (sysconf(_SC_NPROCESSORS_ONLN) < 2) {
-		printf("Error: please run this test on a multi-core system.\n");
-		goto error;
-	}
-
-	/* Create the socket pairs and epoll items: */
-	for (index = 0; index < n_epoll_items; ++index) {
-		int socket_pair[2];
-		struct epoll_event event_data;
-		if (socketpair(AF_UNIX,
-			       SOCK_STREAM | SOCK_NONBLOCK,
-			       0,
-			       socket_pair) < 0)
-			goto error;
-		write_thread_data.fds[index] = socket_pair[0];
-		epoll_items[index].index = index;
-		epoll_items[index].fd = socket_pair[1];
-		if (pthread_mutex_init(&epoll_items[index].mutex, NULL) != 0)
-			goto error;
-		/* We always use EPOLLONESHOT because this test is currently
-		   structured to demonstrate the need for EPOLL_CTL_DISABLE,
-		   which only produces useful information in the EPOLLONESHOT
-		   case (without EPOLLONESHOT, calling epoll_ctl with
-		   EPOLL_CTL_DISABLE will never return EBUSY). If support for
-		   testing events without EPOLLONESHOT is desired, it should
-		   probably be implemented in a separate unit test. */
-		epoll_items[index].events = EPOLLIN | EPOLLONESHOT;
-		if (index < n_epoll_items / 2)
-			epoll_items[index].events |= EPOLLET;
-		epoll_items[index].stop = 0;
-		epoll_items[index].status = 0;
-		epoll_items[index].deleted = 0;
-		event_data.events = epoll_items[index].events;
-		event_data.data.ptr = &epoll_items[index];
-		if (epoll_ctl(epoll_set,
-			      EPOLL_CTL_ADD,
-			      epoll_items[index].fd,
-			      &event_data) < 0)
-			goto error;
-	}
-
-	/* Create and start the read threads: */
-	for (index = 0; index < n_read_threads; ++index) {
-		read_thread_data[index].stop = 0;
-		read_thread_data[index].status = 0;
-		read_thread_data[index].epoll_set = epoll_set;
-		if (pthread_create(&read_threads[index],
-				   NULL,
-				   read_thread_function,
-				   &read_thread_data[index]) != 0)
-			goto error;
-	}
-
-	if (pthread_create(&write_thread,
-			   NULL,
-			   write_thread_function,
-			   &write_thread_data) != 0)
-		goto error;
-
-	/* Cancel all event pollers: */
-#ifdef EPOLL_CTL_DISABLE
-	for (index = 0; index < n_epoll_items; ++index) {
-		pthread_mutex_lock(&epoll_items[index].mutex);
-		++epoll_items[index].stop;
-		if (epoll_ctl(epoll_set,
-			      EPOLL_CTL_DISABLE,
-			      epoll_items[index].fd,
-			      NULL) == 0)
-			delete_item(index);
-		else if (errno != EBUSY) {
-			pthread_mutex_unlock(&epoll_items[index].mutex);
-			goto error;
-		}
-		/* EBUSY means events were being handled; allow the other thread
-		   to delete the item. */
-		pthread_mutex_unlock(&epoll_items[index].mutex);
-	}
-#else
-	for (index = 0; index < n_epoll_items; ++index) {
-		pthread_mutex_lock(&epoll_items[index].mutex);
-		++epoll_items[index].stop;
-		pthread_mutex_unlock(&epoll_items[index].mutex);
-		/* Wait in case a thread running read_thread_function is
-		   currently executing code between epoll_wait and
-		   pthread_mutex_lock with this item. Note that a longer delay
-		   would make double-deletion less likely (at the expense of
-		   performance), but there is no guarantee that any delay would
-		   ever be sufficient. Note also that we delete all event
-		   pollers at once for testing purposes, but in a real-world
-		   environment we are likely to want to be able to cancel event
-		   pollers at arbitrary times. Therefore we can't improve this
-		   situation by just splitting this loop into two loops
-		   (i.e. signal 'stop' for all items, sleep, and then delete all
-		   items). We also can't fix the problem via EPOLL_CTL_DEL
-		   because that command can't prevent the case where some other
-		   thread is executing read_thread_function within the region
-		   mentioned above: */
-		usleep(1);
-		pthread_mutex_lock(&epoll_items[index].mutex);
-		if (!epoll_items[index].deleted)
-			delete_item(index);
-		pthread_mutex_unlock(&epoll_items[index].mutex);
-	}
-#endif
-
-	/* Shut down the read threads: */
-	for (index = 0; index < n_read_threads; ++index)
-		__sync_fetch_and_add(&read_thread_data[index].stop, 1);
-	for (index = 0; index < n_read_threads; ++index) {
-		if (pthread_join(read_threads[index], NULL) != 0)
-			goto error;
-		if (read_thread_data[index].status)
-			goto error;
-	}
-
-	/* Shut down the write thread: */
-	__sync_fetch_and_add(&write_thread_data.stop, 1);
-	if ((pthread_join(write_thread, NULL) != 0) || write_thread_data.status)
-		goto error;
-
-	/* Check for final error conditions: */
-	for (index = 0; index < n_epoll_items; ++index) {
-		if (epoll_items[index].status != 0)
-			goto error;
-		if (pthread_mutex_destroy(&epoll_items[index].mutex) < 0)
-			goto error;
-	}
-	for (index = 0; index < n_epoll_items; ++index)
-		if (epoll_items[index].deleted != 1) {
-			printf("Error: item data deleted %1d times.\n",
-				   epoll_items[index].deleted);
-			goto error;
-		}
-
-	printf("[PASS]\n");
-	return 0;
-
- error:
-	printf("[FAIL]\n");
-	return errno;
-}
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index cd1b03e..b76edf2 100644
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -35,7 +35,7 @@
 #include <sys/mount.h>
 #include <sys/statfs.h>
 #include "../../include/uapi/linux/magic.h"
-#include "../../include/linux/kernel-page-flags.h"
+#include "../../include/uapi/linux/kernel-page-flags.h"
 
 
 #ifndef MAX_PATH