diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index e5342a344c43bee9140d9127f1fe907b21149e8d..b7df302a02046e2b9404d8267a66a6300ffd831a 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1035,7 +1035,7 @@ int __kprobes register_kretprobe(struct kretprobe *rp)
 	/* Pre-allocate memory for max kretprobe instances */
 	if (rp->maxactive <= 0) {
 #ifdef CONFIG_PREEMPT
-		rp->maxactive = max(10, 2 * num_possible_cpus());
+		rp->maxactive = max_t(unsigned int, 10, 2*num_possible_cpus());
 #else
 		rp->maxactive = num_possible_cpus();
 #endif
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 4390d225686d63360cf9c5e8bbc87b9bebdec8af..652a470b5f749aeadc05e33f617bf18a588b3162 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -343,13 +343,18 @@ LIB_H += util/include/linux/string.h
 LIB_H += util/include/linux/types.h
 LIB_H += util/include/asm/asm-offsets.h
 LIB_H += util/include/asm/bitops.h
+LIB_H += util/include/asm/bug.h
 LIB_H += util/include/asm/byteorder.h
 LIB_H += util/include/asm/swab.h
 LIB_H += util/include/asm/system.h
 LIB_H += util/include/asm/uaccess.h
 LIB_H += perf.h
+LIB_H += util/cache.h
+LIB_H += util/callchain.h
+LIB_H += util/debug.h
 LIB_H += util/debugfs.h
 LIB_H += util/event.h
+LIB_H += util/exec_cmd.h
 LIB_H += util/types.h
 LIB_H += util/levenshtein.h
 LIB_H += util/parse-options.h
@@ -362,6 +367,7 @@ LIB_H += util/session.h
 LIB_H += util/strbuf.h
 LIB_H += util/string.h
 LIB_H += util/strlist.h
+LIB_H += util/svghelper.h
 LIB_H += util/run-command.h
 LIB_H += util/sigchain.h
 LIB_H += util/symbol.h
@@ -370,6 +376,8 @@ LIB_H += util/values.h
 LIB_H += util/sort.h
 LIB_H += util/hist.h
 LIB_H += util/thread.h
+LIB_H += util/trace-event.h
+LIB_H += util/trace-event-perl.h
 LIB_H += util/probe-finder.h
 LIB_H += util/probe-event.h
 
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index e693e6777af5a3418d3f0b542a4197b2383aa741..1e99ac806913679d963ae8043f6035f844ea2bc2 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -17,7 +17,7 @@
 static char const *input_name = "perf.data";
 static int force;
 
-static const char *const buildid_list_usage[] = {
+static const char * const buildid_list_usage[] = {
 	"perf buildid-list [<options>]",
 	NULL
 };
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 4d33b55d55846c9c46fe8854824e4eb8da5c3873..bd71b8ceafb78d0c0e6f05e2daa266b2d4758d88 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -189,8 +189,9 @@ static int __cmd_diff(void)
 	return ret;
 }
 
-static const char *const diff_usage[] = {
+static const char * const diff_usage[] = {
 	"perf diff [<options>] [old_file] [new_file]",
+	NULL,
 };
 
 static const struct option options[] = {
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index fc21ad79dd83e25a7520f00e6d3611587650ee79..7ceb7416c3169dadb71fbf44de7246a4e25c5f2a 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -137,7 +137,7 @@ static void insert_alloc_stat(unsigned long call_site, unsigned long ptr,
 	if (data && data->ptr == ptr) {
 		data->hit++;
 		data->bytes_req += bytes_req;
-		data->bytes_alloc += bytes_req;
+		data->bytes_alloc += bytes_alloc;
 	} else {
 		data = malloc(sizeof(*data));
 		if (!data)
@@ -177,7 +177,7 @@ static void insert_caller_stat(unsigned long call_site,
 	if (data && data->call_site == call_site) {
 		data->hit++;
 		data->bytes_req += bytes_req;
-		data->bytes_alloc += bytes_req;
+		data->bytes_alloc += bytes_alloc;
 	} else {
 		data = malloc(sizeof(*data));
 		if (!data)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 63136d0534d450ef18a6bf65ee1d78275f41333b..265425322734eecfc3087a7be42a60960c89f2b0 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -402,7 +402,7 @@ static void atexit_header(void)
 	perf_header__write(&session->header, output, true);
 }
 
-static int __cmd_record(int argc __used, const char **argv)
+static int __cmd_record(int argc, const char **argv)
 {
 	int i, counter;
 	struct stat st;
@@ -411,6 +411,7 @@ static int __cmd_record(int argc __used, const char **argv)
 	int err;
 	unsigned long waking = 0;
 	int child_ready_pipe[2], go_pipe[2];
+	const bool forks = target_pid == -1 && argc > 0;
 	char buf;
 
 	page_size = sysconf(_SC_PAGE_SIZE);
@@ -422,7 +423,7 @@ static int __cmd_record(int argc __used, const char **argv)
 	signal(SIGCHLD, sig_handler);
 	signal(SIGINT, sig_handler);
 
-	if (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0) {
+	if (forks && (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0)) {
 		perror("failed to create pipes");
 		exit(-1);
 	}
@@ -483,7 +484,7 @@ static int __cmd_record(int argc __used, const char **argv)
 
 	atexit(atexit_header);
 
-	if (target_pid == -1) {
+	if (forks) {
 		pid = fork();
 		if (pid < 0) {
 			perror("failed to fork");
@@ -550,7 +551,7 @@ static int __cmd_record(int argc __used, const char **argv)
 			return err;
 	}
 
-	if (!system_wide)
+	if (!system_wide && profile_cpu == -1)
 		event__synthesize_thread(pid, process_synthesized_event,
 					 session);
 	else
@@ -569,7 +570,8 @@ static int __cmd_record(int argc __used, const char **argv)
 	/*
 	 * Let the child rip
 	 */
-	close(go_pipe[1]);
+	if (forks)
+		close(go_pipe[1]);
 
 	for (;;) {
 		int hits = samples;
@@ -667,7 +669,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 
 	argc = parse_options(argc, argv, options, record_usage,
 			    PARSE_OPT_STOP_AT_NON_OPTION);
-	if (!argc && target_pid == -1 && (!system_wide || profile_cpu == -1))
+	if (!argc && target_pid == -1 && !system_wide && profile_cpu == -1)
 		usage_with_options(record_usage, options);
 
 	symbol__init();
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 5c2ab5357ec689b4047689fa6281a1d1a99f78fb..db10c0e8ecae7ee18f4ce352256bed5516fd4024 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -294,8 +294,7 @@ parse_callchain_opt(const struct option *opt __used, const char *arg,
 	return 0;
 }
 
-//static const char * const report_usage[] = {
-const char * const report_usage[] = {
+static const char * const report_usage[] = {
 	"perf report [<options>] <command>",
 	NULL
 };
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index e2285e28720fe2cb076240edc53fdd90913ee748..574a215e800b502abeb05fa9e874421db8e3f79a 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -512,7 +512,7 @@ static char *get_script_path(const char *script_root, const char *suffix)
 	return path;
 }
 
-static const char * const annotate_usage[] = {
+static const char * const trace_usage[] = {
 	"perf trace [<options>] <command>",
 	NULL
 };
@@ -581,7 +581,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
 
 	setup_scripting();
 
-	argc = parse_options(argc, argv, options, annotate_usage,
+	argc = parse_options(argc, argv, options, trace_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 
 	if (symbol__init() < 0)
diff --git a/tools/perf/design.txt b/tools/perf/design.txt
index f000c30877acf3eb153c8a499b61d51660fde917..8d0de5130db3a2d006e1e04497ba41fcf09e7247 100644
--- a/tools/perf/design.txt
+++ b/tools/perf/design.txt
@@ -21,7 +21,7 @@ There's one file descriptor per virtual counter used.
 The special file descriptor is opened via the perf_event_open()
 system call:
 
-   int sys_perf_event_open(struct perf_event_hw_event *hw_event_uptr,
+   int sys_perf_event_open(struct perf_event_attr *hw_event_uptr,
 			     pid_t pid, int cpu, int group_fd,
 			     unsigned long flags);
 
@@ -32,9 +32,9 @@ can be used to set the blocking mode, etc.
 Multiple counters can be kept open at a time, and the counters
 can be poll()ed.
 
-When creating a new counter fd, 'perf_event_hw_event' is:
+When creating a new counter fd, 'perf_event_attr' is:
 
-struct perf_event_hw_event {
+struct perf_event_attr {
         /*
          * The MSB of the config word signifies if the rest contains cpu
          * specific (raw) counter configuration data, if unset, the next
@@ -399,7 +399,7 @@ Notification of new events is possible through poll()/select()/epoll() and
 fcntl() managing signals.
 
 Normally a notification is generated for every page filled, however one can
-additionally set perf_event_hw_event.wakeup_events to generate one every
+additionally set perf_event_attr.wakeup_events to generate one every
 so many counter overflow events.
 
 Future work will include a splice() interface to the ring-buffer.