Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

 * Remove die()/exit() calls from several tools.

 * Add missing perf_regs.h file to MANIFEST

 * Clean up and improve 'perf sched' performance by elliminating lots of
   needless calls to libtraceevent.

 * More patches to make perf build on Android, from Irina Tirdea

 * Resolve vdso callchains, from Jiri Olsa

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

92 files changed, 1518 insertions, 1231 deletions

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index f4190b5764de..2c54cdd8ae1b 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -1824,7 +1824,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 }
 
 static enum event_type
-process_entry(struct event_format *event __unused, struct print_arg *arg,
+process_entry(struct event_format *event __maybe_unused, struct print_arg *arg,
 	      char **tok)
 {
 	enum event_type type;
@@ -2458,7 +2458,8 @@ process_paren(struct event_format *event, struct print_arg *arg, char **tok)
 
 
 static enum event_type
-process_str(struct event_format *event __unused, struct print_arg *arg, char **tok)
+process_str(struct event_format *event __maybe_unused, struct print_arg *arg,
+	    char **tok)
 {
 	enum event_type type;
 	char *token;
@@ -3653,7 +3654,8 @@ static void free_args(struct print_arg *args)
 }
 
 static char *
-get_bprint_format(void *data, int size __unused, struct event_format *event)
+get_bprint_format(void *data, int size __maybe_unused,
+		  struct event_format *event)
 {
 	struct pevent *pevent = event->pevent;
 	unsigned long long addr;
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 3318963f1c98..a4bbe2437925 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -24,8 +24,8 @@
 #include <stdarg.h>
 #include <regex.h>
 
-#ifndef __unused
-#define __unused __attribute__ ((unused))
+#ifndef __maybe_unused
+#define __maybe_unused __attribute__((unused))
 #endif
 
 /* ----------------------- trace_seq ----------------------- */
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index b4b572e8c100..051807990938 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -10,6 +10,7 @@ include/linux/stringify.h
 lib/rbtree.c
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
+arch/*/include/asm/perf_regs.h
 arch/*/lib/memcpy*.S
 arch/*/lib/memset*.S
 include/linux/poison.h
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index e4b2e8f2606c..209774bcee2e 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -264,6 +264,7 @@ LIB_H += util/include/linux/ctype.h
 LIB_H += util/include/linux/kernel.h
 LIB_H += util/include/linux/list.h
 LIB_H += util/include/linux/export.h
+LIB_H += util/include/linux/magic.h
 LIB_H += util/include/linux/poison.h
 LIB_H += util/include/linux/prefetch.h
 LIB_H += util/include/linux/rbtree.h
@@ -336,6 +337,7 @@ LIB_H += util/intlist.h
 LIB_H += util/perf_regs.h
 LIB_H += util/unwind.h
 LIB_H += ui/helpline.h
+LIB_H += util/vdso.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -403,6 +405,7 @@ LIB_OBJS += $(OUTPUT)util/cgroup.o
 LIB_OBJS += $(OUTPUT)util/target.o
 LIB_OBJS += $(OUTPUT)util/rblist.o
 LIB_OBJS += $(OUTPUT)util/intlist.o
+LIB_OBJS += $(OUTPUT)util/vdso.o
 
 LIB_OBJS += $(OUTPUT)ui/helpline.o
 LIB_OBJS += $(OUTPUT)ui/hist.o
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index a09bece6dad2..8f89998eeaf4 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -3,7 +3,8 @@
 
 extern int bench_sched_messaging(int argc, const char **argv, const char *prefix);
 extern int bench_sched_pipe(int argc, const char **argv, const char *prefix);
-extern int bench_mem_memcpy(int argc, const char **argv, const char *prefix __used);
+extern int bench_mem_memcpy(int argc, const char **argv,
+			    const char *prefix __maybe_unused);
 extern int bench_mem_memset(int argc, const char **argv, const char *prefix);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 02dad5d3359b..93c83e3cb4a7 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -177,7 +177,7 @@ static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
 	} while (0)
 
 int bench_mem_memcpy(int argc, const char **argv,
-		     const char *prefix __used)
+		     const char *prefix __maybe_unused)
 {
 	int i;
 	size_t len;
diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c
index 350cc9557265..c6e4bc523492 100644
--- a/tools/perf/bench/mem-memset.c
+++ b/tools/perf/bench/mem-memset.c
@@ -171,7 +171,7 @@ static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault)
 	} while (0)
 
 int bench_mem_memset(int argc, const char **argv,
-		     const char *prefix __used)
+		     const char *prefix __maybe_unused)
 {
 	int i;
 	size_t len;
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index d1d1b30f99c1..cc1190a0849b 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -267,7 +267,7 @@ static const char * const bench_sched_message_usage[] = {
 };
 
 int bench_sched_messaging(int argc, const char **argv,
-		    const char *prefix __used)
+		    const char *prefix __maybe_unused)
 {
 	unsigned int i, total_children;
 	struct timeval start, stop, diff;
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 15911e9c587a..69cfba8d4c6c 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -43,7 +43,7 @@ static const char * const bench_sched_pipe_usage[] = {
 };
 
 int bench_sched_pipe(int argc, const char **argv,
-		     const char *prefix __used)
+		     const char *prefix __maybe_unused)
 {
 	int pipe_1[2], pipe_2[2];
 	int m = 0, i;
@@ -55,8 +55,8 @@ int bench_sched_pipe(int argc, const char **argv,
 	 * discarding returned value of read(), write()
 	 * causes error in building environment for perf
 	 */
-	int __used ret, wait_stat;
-	pid_t pid, retpid __used;
+	int __maybe_unused ret, wait_stat;
+	pid_t pid, retpid __maybe_unused;
 
 	argc = parse_options(argc, argv, options,
 			     bench_sched_pipe_usage, 0);
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 2f3f0029c0f7..9ea38540b873 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -239,7 +239,7 @@ static const char * const annotate_usage[] = {
 	NULL
 };
 
-int cmd_annotate(int argc, const char **argv, const char *prefix __used)
+int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	struct perf_annotate annotate = {
 		.tool = {
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index 1f3100216448..cae9a5fd2ecf 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -173,7 +173,7 @@ static void all_subsystem(void)
 		all_suite(&subsystems[i]);
 }
 
-int cmd_bench(int argc, const char **argv, const char *prefix __used)
+int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	int i, j, status = 0;
 
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 29ad20e67919..83654557e108 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -43,15 +43,16 @@ static int build_id_cache__add_file(const char *filename, const char *debugdir)
 	}
 
 	build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
-	err = build_id_cache__add_s(sbuild_id, debugdir, filename, false);
+	err = build_id_cache__add_s(sbuild_id, debugdir, filename,
+				    false, false);
 	if (verbose)
 		pr_info("Adding %s %s: %s\n", sbuild_id, filename,
 			err ? "FAIL" : "Ok");
 	return err;
 }
 
-static int build_id_cache__remove_file(const char *filename __used,
-				       const char *debugdir __used)
+static int build_id_cache__remove_file(const char *filename __maybe_unused,
+				       const char *debugdir __maybe_unused)
 {
 	u8 build_id[BUILD_ID_SIZE];
 	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
@@ -119,7 +120,8 @@ static int __cmd_buildid_cache(void)
 	return 0;
 }
 
-int cmd_buildid_cache(int argc, const char **argv, const char *prefix __used)
+int cmd_buildid_cache(int argc, const char **argv,
+		      const char *prefix __maybe_unused)
 {
 	argc = parse_options(argc, argv, buildid_cache_options,
 			     buildid_cache_usage, 0);
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index 7d6842826a0c..1159feeebb19 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -103,7 +103,8 @@ static int __cmd_buildid_list(void)
 	return perf_session__list_build_ids();
 }
 
-int cmd_buildid_list(int argc, const char **argv, const char *prefix __used)
+int cmd_buildid_list(int argc, const char **argv,
+		     const char *prefix __maybe_unused)
 {
 	argc = parse_options(argc, argv, options, buildid_list_usage, 0);
 	setup_pager();
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index c4c6d76b70ea..761f4197a9e2 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -33,7 +33,7 @@ static int hists__add_entry(struct hists *self,
 	return -ENOMEM;
 }
 
-static int diff__process_sample_event(struct perf_tool *tool __used,
+static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 				      union perf_event *event,
 				      struct perf_sample *sample,
 				      struct perf_evsel *evsel,
@@ -242,7 +242,7 @@ static const struct option options[] = {
 	OPT_END()
 };
 
-int cmd_diff(int argc, const char **argv, const char *prefix __used)
+int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	sort_order = diff__default_sort_order;
 	argc = parse_options(argc, argv, options, diff_usage, 0);
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index 0dd5a058f766..1fb164164fd0 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -113,7 +113,7 @@ static const char * const evlist_usage[] = {
 	NULL
 };
 
-int cmd_evlist(int argc, const char **argv, const char *prefix __used)
+int cmd_evlist(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	struct perf_attr_details details = { .verbose = false, };
 	const char *input_name = NULL;
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index f9daae5ac47a..25c8b942ff85 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -426,7 +426,7 @@ static int show_html_page(const char *perf_cmd)
 	return 0;
 }
 
-int cmd_help(int argc, const char **argv, const char *prefix __used)
+int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	const char *alias;
 	int rc = 0;
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 64d8ba2fb7bc..1eaa6617c814 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -17,9 +17,9 @@
 static char		const *input_name = "-";
 static bool		inject_build_ids;
 
-static int perf_event__repipe_synth(struct perf_tool *tool __used,
+static int perf_event__repipe_synth(struct perf_tool *tool __maybe_unused,
 				    union perf_event *event,
-				    struct machine *machine __used)
+				    struct machine *machine __maybe_unused)
 {
 	uint32_t size;
 	void *buf = event;
@@ -40,7 +40,8 @@ static int perf_event__repipe_synth(struct perf_tool *tool __used,
 
 static int perf_event__repipe_op2_synth(struct perf_tool *tool,
 					union perf_event *event,
-					struct perf_session *session __used)
+					struct perf_session *session
+					__maybe_unused)
 {
 	return perf_event__repipe_synth(tool, event, NULL);
 }
@@ -52,13 +53,14 @@ static int perf_event__repipe_event_type_synth(struct perf_tool *tool,
 }
 
 static int perf_event__repipe_tracing_data_synth(union perf_event *event,
-						 struct perf_session *session __used)
+						 struct perf_session *session
+						 __maybe_unused)
 {
 	return perf_event__repipe_synth(NULL, event, NULL);
 }
 
 static int perf_event__repipe_attr(union perf_event *event,
-				   struct perf_evlist **pevlist __used)
+				   struct perf_evlist **pevlist __maybe_unused)
 {
 	int ret;
 	ret = perf_event__process_attr(event, pevlist);
@@ -70,7 +72,7 @@ static int perf_event__repipe_attr(union perf_event *event,
 
 static int perf_event__repipe(struct perf_tool *tool,
 			      union perf_event *event,
-			      struct perf_sample *sample __used,
+			      struct perf_sample *sample __maybe_unused,
 			      struct machine *machine)
 {
 	return perf_event__repipe_synth(tool, event, machine);
@@ -78,8 +80,8 @@ static int perf_event__repipe(struct perf_tool *tool,
 
 static int perf_event__repipe_sample(struct perf_tool *tool,
 				     union perf_event *event,
-			      struct perf_sample *sample __used,
-			      struct perf_evsel *evsel __used,
+			      struct perf_sample *sample __maybe_unused,
+			      struct perf_evsel *evsel __maybe_unused,
 			      struct machine *machine)
 {
 	return perf_event__repipe_synth(tool, event, machine);
@@ -163,7 +165,7 @@ static int dso__inject_build_id(struct dso *self, struct perf_tool *tool,
 static int perf_event__inject_buildid(struct perf_tool *tool,
 				      union perf_event *event,
 				      struct perf_sample *sample,
-				      struct perf_evsel *evsel __used,
+				      struct perf_evsel *evsel __maybe_unused,
 				      struct machine *machine)
 {
 	struct addr_location al;
@@ -224,7 +226,7 @@ struct perf_tool perf_inject = {
 
 extern volatile int session_done;
 
-static void sig_handler(int sig __attribute__((__unused__)))
+static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
 }
@@ -267,7 +269,7 @@ static const struct option options[] = {
 	OPT_END()
 };
 
-int cmd_inject(int argc, const char **argv, const char *prefix __used)
+int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	argc = parse_options(argc, argv, options, report_usage, 0);
 
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index fc6607b383f2..f5f8a6b745a3 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -58,41 +58,52 @@ static unsigned long nr_allocs, nr_cross_allocs;
 
 #define PATH_SYS_NODE	"/sys/devices/system/node"
 
-static void init_cpunode_map(void)
+static int init_cpunode_map(void)
 {
 	FILE *fp;
-	int i;
+	int i, err = -1;
 
 	fp = fopen("/sys/devices/system/cpu/kernel_max", "r");
 	if (!fp) {
 		max_cpu_num = 4096;
-		return;
+		return 0;
+	}
+
+	if (fscanf(fp, "%d", &max_cpu_num) < 1) {
+		pr_err("Failed to read 'kernel_max' from sysfs");
+		goto out_close;
 	}
 
-	if (fscanf(fp, "%d", &max_cpu_num) < 1)
-		die("Failed to read 'kernel_max' from sysfs");
 	max_cpu_num++;
 
 	cpunode_map = calloc(max_cpu_num, sizeof(int));
-	if (!cpunode_map)
-		die("calloc");
+	if (!cpunode_map) {
+		pr_err("%s: calloc failed\n", __func__);
+		goto out_close;
+	}
+
 	for (i = 0; i < max_cpu_num; i++)
 		cpunode_map[i] = -1;
+
+	err = 0;
+out_close:
 	fclose(fp);
+	return err;
 }
 
-static void setup_cpunode_map(void)
+static int setup_cpunode_map(void)
 {
 	struct dirent *dent1, *dent2;
 	DIR *dir1, *dir2;
 	unsigned int cpu, mem;
 	char buf[PATH_MAX];
 
-	init_cpunode_map();
+	if (init_cpunode_map())
+		return -1;
 
 	dir1 = opendir(PATH_SYS_NODE);
 	if (!dir1)
-		return;
+		return -1;
 
 	while ((dent1 = readdir(dir1)) != NULL) {
 		if (dent1->d_type != DT_DIR ||
@@ -112,10 +123,11 @@ static void setup_cpunode_map(void)
 		closedir(dir2);
 	}
 	closedir(dir1);
+	return 0;
 }
 
-static void insert_alloc_stat(unsigned long call_site, unsigned long ptr,
-			      int bytes_req, int bytes_alloc, int cpu)
+static int insert_alloc_stat(unsigned long call_site, unsigned long ptr,
+			     int bytes_req, int bytes_alloc, int cpu)
 {
 	struct rb_node **node = &root_alloc_stat.rb_node;
 	struct rb_node *parent = NULL;
@@ -139,8 +151,10 @@ static void insert_alloc_stat(unsigned long call_site, unsigned long ptr,
 		data->bytes_alloc += bytes_alloc;
 	} else {
 		data = malloc(sizeof(*data));
-		if (!data)
-			die("malloc");
+		if (!data) {
+			pr_err("%s: malloc failed\n", __func__);
+			return -1;
+		}
 		data->ptr = ptr;
 		data->pingpong = 0;
 		data->hit = 1;
@@ -152,9 +166,10 @@ static void insert_alloc_stat(unsigned long call_site, unsigned long ptr,
 	}
 	data->call_site = call_site;
 	data->alloc_cpu = cpu;
+	return 0;
 }
 
-static void insert_caller_stat(unsigned long call_site,
+static int insert_caller_stat(unsigned long call_site,
 			      int bytes_req, int bytes_alloc)
 {
 	struct rb_node **node = &root_caller_stat.rb_node;
@@ -179,8 +194,10 @@ static void insert_caller_stat(unsigned long call_site,
 		data->bytes_alloc += bytes_alloc;
 	} else {
 		data = malloc(sizeof(*data));
-		if (!data)
-			die("malloc");
+		if (!data) {
+			pr_err("%s: malloc failed\n", __func__);
+			return -1;
+		}
 		data->call_site = call_site;
 		data->pingpong = 0;
 		data->hit = 1;
@@ -190,11 +207,12 @@ static void insert_caller_stat(unsigned long call_site,
 		rb_link_node(&data->node, parent, node);
 		rb_insert_color(&data->node, &root_caller_stat);
 	}
+
+	return 0;
 }
 
-static void perf_evsel__process_alloc_event(struct perf_evsel *evsel,
-					    struct perf_sample *sample,
-					    int node)
+static int perf_evsel__process_alloc_event(struct perf_evsel *evsel,
+					   struct perf_sample *sample, int node)
 {
 	struct event_format *event = evsel->tp_format;
 	void *data = sample->raw_data;
@@ -209,8 +227,9 @@ static void perf_evsel__process_alloc_event(struct perf_evsel *evsel,
 	bytes_req = raw_field_value(event, "bytes_req", data);
 	bytes_alloc = raw_field_value(event, "bytes_alloc", data);
 
-	insert_alloc_stat(call_site, ptr, bytes_req, bytes_alloc, cpu);
-	insert_caller_stat(call_site, bytes_req, bytes_alloc);
+	if (insert_alloc_stat(call_site, ptr, bytes_req, bytes_alloc, cpu) ||
+	    insert_caller_stat(call_site, bytes_req, bytes_alloc))
+		return -1;
 
 	total_requested += bytes_req;
 	total_allocated += bytes_alloc;
@@ -222,6 +241,7 @@ static void perf_evsel__process_alloc_event(struct perf_evsel *evsel,
 			nr_cross_allocs++;
 	}
 	nr_allocs++;
+	return 0;
 }
 
 static int ptr_cmp(struct alloc_stat *, struct alloc_stat *);
@@ -252,8 +272,8 @@ static struct alloc_stat *search_alloc_stat(unsigned long ptr,
 	return NULL;
 }
 
-static void perf_evsel__process_free_event(struct perf_evsel *evsel,
-					   struct perf_sample *sample)
+static int perf_evsel__process_free_event(struct perf_evsel *evsel,
+					  struct perf_sample *sample)
 {
 	unsigned long ptr = raw_field_value(evsel->tp_format, "ptr",
 					    sample->raw_data);
@@ -261,44 +281,46 @@ static void perf_evsel__process_free_event(struct perf_evsel *evsel,
 
 	s_alloc = search_alloc_stat(ptr, 0, &root_alloc_stat, ptr_cmp);
 	if (!s_alloc)
-		return;
+		return 0;
 
 	if ((short)sample->cpu != s_alloc->alloc_cpu) {
 		s_alloc->pingpong++;
 
 		s_caller = search_alloc_stat(0, s_alloc->call_site,
 					     &root_caller_stat, callsite_cmp);
-		assert(s_caller);
+		if (!s_caller)
+			return -1;
 		s_caller->pingpong++;
 	}
 	s_alloc->alloc_cpu = -1;
+
+	return 0;
 }
 
-static void perf_evsel__process_kmem_event(struct perf_evsel *evsel,
-					   struct perf_sample *sample)
+static int perf_evsel__process_kmem_event(struct perf_evsel *evsel,
+					  struct perf_sample *sample)
 {
 	struct event_format *event = evsel->tp_format;
 
 	if (!strcmp(event->name, "kmalloc") ||
 	    !strcmp(event->name, "kmem_cache_alloc")) {
-		perf_evsel__process_alloc_event(evsel, sample, 0);
-		return;
+		return perf_evsel__process_alloc_event(evsel, sample, 0);
 	}
 
 	if (!strcmp(event->name, "kmalloc_node") ||
 	    !strcmp(event->name, "kmem_cache_alloc_node")) {
-		perf_evsel__process_alloc_event(evsel, sample, 1);
-		return;
+		return perf_evsel__process_alloc_event(evsel, sample, 1);
 	}
 
 	if (!strcmp(event->name, "kfree") ||
 	    !strcmp(event->name, "kmem_cache_free")) {
-		perf_evsel__process_free_event(evsel, sample);
-		return;
+		return perf_evsel__process_free_event(evsel, sample);
 	}
+
+	return 0;
 }
 
-static int process_sample_event(struct perf_tool *tool __used,
+static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				union perf_event *event,
 				struct perf_sample *sample,
 				struct perf_evsel *evsel,
@@ -314,8 +336,7 @@ static int process_sample_event(struct perf_tool *tool __used,
 
 	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
 
-	perf_evsel__process_kmem_event(evsel, sample);
-	return 0;
+	return perf_evsel__process_kmem_event(evsel, sample);
 }
 
 static struct perf_tool perf_kmem = {
@@ -613,8 +634,10 @@ static int sort_dimension__add(const char *tok, struct list_head *list)
 	for (i = 0; i < NUM_AVAIL_SORTS; i++) {
 		if (!strcmp(avail_sorts[i]->name, tok)) {
 			sort = malloc(sizeof(*sort));
-			if (!sort)
-				die("malloc");
+			if (!sort) {
+				pr_err("%s: malloc failed\n", __func__);
+				return -1;
+			}
 			memcpy(sort, avail_sorts[i], sizeof(*sort));
 			list_add_tail(&sort->list, list);
 			return 0;
@@ -629,8 +652,10 @@ static int setup_sorting(struct list_head *sort_list, const char *arg)
 	char *tok;
 	char *str = strdup(arg);
 
-	if (!str)
-		die("strdup");
+	if (!str) {
+		pr_err("%s: strdup failed\n", __func__);
+		return -1;
+	}
 
 	while (true) {
 		tok = strsep(&str, ",");
@@ -647,8 +672,8 @@ static int setup_sorting(struct list_head *sort_list, const char *arg)
 	return 0;
 }
 
-static int parse_sort_opt(const struct option *opt __used,
-			  const char *arg, int unset __used)
+static int parse_sort_opt(const struct option *opt __maybe_unused,
+			  const char *arg, int unset __maybe_unused)
 {
 	if (!arg)
 		return -1;
@@ -661,22 +686,24 @@ static int parse_sort_opt(const struct option *opt __used,
 	return 0;
 }
 
-static int parse_caller_opt(const struct option *opt __used,
-			  const char *arg __used, int unset __used)
+static int parse_caller_opt(const struct option *opt __maybe_unused,
+			    const char *arg __maybe_unused,
+			    int unset __maybe_unused)
 {
 	caller_flag = (alloc_flag + 1);
 	return 0;
 }
 
-static int parse_alloc_opt(const struct option *opt __used,
-			  const char *arg __used, int unset __used)
+static int parse_alloc_opt(const struct option *opt __maybe_unused,
+			   const char *arg __maybe_unused,
+			   int unset __maybe_unused)
 {
 	alloc_flag = (caller_flag + 1);
 	return 0;
 }
 
-static int parse_line_opt(const struct option *opt __used,
-			  const char *arg, int unset __used)
+static int parse_line_opt(const struct option *opt __maybe_unused,
+			  const char *arg, int unset __maybe_unused)
 {
 	int lines;
 
@@ -746,7 +773,7 @@ static int __cmd_record(int argc, const char **argv)
 	return cmd_record(i, rec_argv, NULL);
 }
 
-int cmd_kmem(int argc, const char **argv, const char *prefix __used)
+int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	argc = parse_options(argc, argv, kmem_options, kmem_usage, 0);
 
@@ -758,7 +785,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __used)
 	if (!strncmp(argv[0], "rec", 3)) {
 		return __cmd_record(argc, argv);
 	} else if (!strcmp(argv[0], "stat")) {
-		setup_cpunode_map();
+		if (setup_cpunode_map())
+			return -1;
 
 		if (list_empty(&caller_sort))
 			setup_sorting(&caller_sort, default_sort_order);
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 9fc6e0fa3dce..4d2aa2cbeca8 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -102,7 +102,7 @@ static int __cmd_buildid_list(int argc, const char **argv)
 	return cmd_buildid_list(i, rec_argv, NULL);
 }
 
-int cmd_kvm(int argc, const char **argv, const char *prefix __used)
+int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	perf_host  = 0;
 	perf_guest = 1;
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index bdcff81b532a..1948eceb517a 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -14,7 +14,7 @@
 #include "util/parse-events.h"
 #include "util/cache.h"
 
-int cmd_list(int argc, const char **argv, const char *prefix __used)
+int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	setup_pager();
 
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 75153c87e650..a8035207a3dd 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -870,7 +870,7 @@ static int dump_info(void)
 	return rc;
 }
 
-static int process_sample_event(struct perf_tool *tool __used,
+static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				union perf_event *event,
 				struct perf_sample *sample,
 				struct perf_evsel *evsel,
@@ -1020,7 +1020,7 @@ static int __cmd_record(int argc, const char **argv)
 	return cmd_record(i, rec_argv, NULL);
 }
 
-int cmd_lock(int argc, const char **argv, const char *prefix __used)
+int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	unsigned int i;
 	int rc = 0;
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index e215ae61b2ae..118aa8946573 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -143,8 +143,8 @@ static int parse_probe_event_argv(int argc, const char **argv)
 	return ret;
 }
 
-static int opt_add_probe_event(const struct option *opt __used,
-			      const char *str, int unset __used)
+static int opt_add_probe_event(const struct option *opt __maybe_unused,
+			      const char *str, int unset __maybe_unused)
 {
 	if (str) {
 		params.mod_events = true;
@@ -153,8 +153,8 @@ static int opt_add_probe_event(const struct option *opt __used,
 		return 0;
 }
 
-static int opt_del_probe_event(const struct option *opt __used,
-			       const char *str, int unset __used)
+static int opt_del_probe_event(const struct option *opt __maybe_unused,
+			       const char *str, int unset __maybe_unused)
 {
 	if (str) {
 		params.mod_events = true;
@@ -166,7 +166,7 @@ static int opt_del_probe_event(const struct option *opt __used,
 }
 
 static int opt_set_target(const struct option *opt, const char *str,
-			int unset __used)
+			int unset __maybe_unused)
 {
 	int ret = -ENOENT;
 
@@ -188,8 +188,8 @@ static int opt_set_target(const struct option *opt, const char *str,
 }
 
 #ifdef DWARF_SUPPORT
-static int opt_show_lines(const struct option *opt __used,
-			  const char *str, int unset __used)
+static int opt_show_lines(const struct option *opt __maybe_unused,
+			  const char *str, int unset __maybe_unused)
 {
 	int ret = 0;
 
@@ -209,8 +209,8 @@ static int opt_show_lines(const struct option *opt __used,
 	return ret;
 }
 
-static int opt_show_vars(const struct option *opt __used,
-			 const char *str, int unset __used)
+static int opt_show_vars(const struct option *opt __maybe_unused,
+			 const char *str, int unset __maybe_unused)
 {
 	struct perf_probe_event *pev = &params.events[params.nevents];
 	int ret;
@@ -229,8 +229,8 @@ static int opt_show_vars(const struct option *opt __used,
 }
 #endif
 
-static int opt_set_filter(const struct option *opt __used,
-			  const char *str, int unset __used)
+static int opt_set_filter(const struct option *opt __maybe_unused,
+			  const char *str, int unset __maybe_unused)
 {
 	const char *err;
 
@@ -327,7 +327,7 @@ static const struct option options[] = {
 	OPT_END()
 };
 
-int cmd_probe(int argc, const char **argv, const char *prefix __used)
+int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	int ret;
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 7b8b891d4d56..c643ed669ef9 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -92,8 +92,8 @@ static int write_output(struct perf_record *rec, void *buf, size_t size)
 
 static int process_synthesized_event(struct perf_tool *tool,
 				     union perf_event *event,
-				     struct perf_sample *sample __used,
-				     struct machine *machine __used)
+				     struct perf_sample *sample __maybe_unused,
+				     struct machine *machine __maybe_unused)
 {
 	struct perf_record *rec = container_of(tool, struct perf_record, tool);
 	if (write_output(rec, event, event->header.size) < 0)
@@ -159,7 +159,7 @@ static void sig_handler(int sig)
 	signr = sig;
 }
 
-static void perf_record__sig_exit(int exit_status __used, void *arg)
+static void perf_record__sig_exit(int exit_status __maybe_unused, void *arg)
 {
 	struct perf_record *rec = arg;
 	int status;
@@ -827,7 +827,7 @@ static int get_stack_size(char *str, unsigned long *_size)
 #endif /* !NO_LIBUNWIND_SUPPORT */
 
 static int
-parse_callchain_opt(const struct option *opt __used, const char *arg,
+parse_callchain_opt(const struct option *opt __maybe_unused, const char *arg,
 		    int unset)
 {
 	struct perf_record *rec = (struct perf_record *)opt->value;
@@ -1003,7 +1003,7 @@ const struct option record_options[] = {
 	OPT_END()
 };
 
-int cmd_record(int argc, const char **argv, const char *prefix __used)
+int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	int err = -ENOMEM;
 	struct perf_evsel *pos;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 1f8d11b4f7ff..97b2e6300f4c 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -223,9 +223,9 @@ static int process_sample_event(struct perf_tool *tool,
 
 static int process_read_event(struct perf_tool *tool,
 			      union perf_event *event,
-			      struct perf_sample *sample __used,
+			      struct perf_sample *sample __maybe_unused,
 			      struct perf_evsel *evsel,
-			      struct machine *machine __used)
+			      struct machine *machine __maybe_unused)
 {
 	struct perf_report *rep = container_of(tool, struct perf_report, tool);
 
@@ -287,7 +287,7 @@ static int perf_report__setup_sample_type(struct perf_report *rep)
 
 extern volatile int session_done;
 
-static void sig_handler(int sig __used)
+static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
 }
@@ -533,13 +533,14 @@ setup:
 }
 
 static int
-parse_branch_mode(const struct option *opt __used, const char *str __used, int unset)
+parse_branch_mode(const struct option *opt __maybe_unused,
+		  const char *str __maybe_unused, int unset)
 {
 	sort__branch_mode = !unset;
 	return 0;
 }
 
-int cmd_report(int argc, const char **argv, const char *prefix __used)
+int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	struct perf_session *session;
 	struct stat st;
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index a25a023965bb..af305f57bd22 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -23,26 +23,12 @@
 #include <pthread.h>
 #include <math.h>
 
-static const char		*input_name;
-
-static char			default_sort_order[] = "avg, max, switch, runtime";
-static const char		*sort_order = default_sort_order;
-
-static int			profile_cpu = -1;
-
 #define PR_SET_NAME		15               /* Set process name */
 #define MAX_CPUS		4096
-
-static u64			run_measurement_overhead;
-static u64			sleep_measurement_overhead;
-
 #define COMM_LEN		20
 #define SYM_LEN			129
-
 #define MAX_PID			65536
 
-static unsigned long		nr_tasks;
-
 struct sched_atom;
 
 struct task_desc {
@@ -80,44 +66,6 @@ struct sched_atom {
 	struct task_desc	*wakee;
 };
 
-static struct task_desc		*pid_to_task[MAX_PID];
-
-static struct task_desc		**tasks;
-
-static pthread_mutex_t		start_work_mutex = PTHREAD_MUTEX_INITIALIZER;
-static u64			start_time;
-
-static pthread_mutex_t		work_done_wait_mutex = PTHREAD_MUTEX_INITIALIZER;
-
-static unsigned long		nr_run_events;
-static unsigned long		nr_sleep_events;
-static unsigned long		nr_wakeup_events;
-
-static unsigned long		nr_sleep_corrections;
-static unsigned long		nr_run_events_optimized;
-
-static unsigned long		targetless_wakeups;
-static unsigned long		multitarget_wakeups;
-
-static u64			cpu_usage;
-static u64			runavg_cpu_usage;
-static u64			parent_cpu_usage;
-static u64			runavg_parent_cpu_usage;
-
-static unsigned long		nr_runs;
-static u64			sum_runtime;
-static u64			sum_fluct;
-static u64			run_avg;
-
-static unsigned int		replay_repeat = 10;
-static unsigned long		nr_timestamps;
-static unsigned long		nr_unordered_timestamps;
-static unsigned long		nr_state_machine_bugs;
-static unsigned long		nr_context_switch_bugs;
-static unsigned long		nr_events;
-static unsigned long		nr_lost_chunks;
-static unsigned long		nr_lost_events;
-
 #define TASK_STATE_TO_CHAR_STR "RSDTtZX"
 
 enum thread_state {
@@ -149,11 +97,79 @@ struct work_atoms {
 
 typedef int (*sort_fn_t)(struct work_atoms *, struct work_atoms *);
 
-static struct rb_root		atom_root, sorted_atom_root;
+struct perf_sched;
 
-static u64			all_runtime;
-static u64			all_count;
+struct trace_sched_handler {
+	int (*switch_event)(struct perf_sched *sched, struct perf_evsel *evsel,
+			    struct perf_sample *sample, struct machine *machine);
+
+	int (*runtime_event)(struct perf_sched *sched, struct perf_evsel *evsel,
+			     struct perf_sample *sample, struct machine *machine);
+
+	int (*wakeup_event)(struct perf_sched *sched, struct perf_evsel *evsel,
+			    struct perf_sample *sample, struct machine *machine);
+
+	int (*fork_event)(struct perf_sched *sched, struct perf_evsel *evsel,
+			  struct perf_sample *sample);
 
+	int (*migrate_task_event)(struct perf_sched *sched,
+				  struct perf_evsel *evsel,
+				  struct perf_sample *sample,
+				  struct machine *machine);
+};
+
+struct perf_sched {
+	struct perf_tool tool;
+	const char	 *input_name;
+	const char	 *sort_order;
+	unsigned long	 nr_tasks;
+	struct task_desc *pid_to_task[MAX_PID];
+	struct task_desc **tasks;
+	const struct trace_sched_handler *tp_handler;
+	pthread_mutex_t	 start_work_mutex;
+	pthread_mutex_t	 work_done_wait_mutex;
+	int		 profile_cpu;
+/*
+ * Track the current task - that way we can know whether there's any
+ * weird events, such as a task being switched away that is not current.
+ */
+	int		 max_cpu;
+	u32		 curr_pid[MAX_CPUS];
+	struct thread	 *curr_thread[MAX_CPUS];
+	char		 next_shortname1;
+	char		 next_shortname2;
+	unsigned int	 replay_repeat;
+	unsigned long	 nr_run_events;
+	unsigned long	 nr_sleep_events;
+	unsigned long	 nr_wakeup_events;
+	unsigned long	 nr_sleep_corrections;
+	unsigned long	 nr_run_events_optimized;
+	unsigned long	 targetless_wakeups;
+	unsigned long	 multitarget_wakeups;
+	unsigned long	 nr_runs;
+	unsigned long	 nr_timestamps;
+	unsigned long	 nr_unordered_timestamps;
+	unsigned long	 nr_state_machine_bugs;
+	unsigned long	 nr_context_switch_bugs;
+	unsigned long	 nr_events;
+	unsigned long	 nr_lost_chunks;
+	unsigned long	 nr_lost_events;
+	u64		 run_measurement_overhead;
+	u64		 sleep_measurement_overhead;
+	u64		 start_time;
+	u64		 cpu_usage;
+	u64		 runavg_cpu_usage;
+	u64		 parent_cpu_usage;
+	u64		 runavg_parent_cpu_usage;
+	u64		 sum_runtime;
+	u64		 sum_fluct;
+	u64		 run_avg;
+	u64		 all_runtime;
+	u64		 all_count;
+	u64		 cpu_last_switched[MAX_CPUS];
+	struct rb_root	 atom_root, sorted_atom_root;
+	struct list_head sort_list, cmp_pid;
+};
 
 static u64 get_nsecs(void)
 {
@@ -164,13 +180,13 @@ static u64 get_nsecs(void)
 	return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
 }
 
-static void burn_nsecs(u64 nsecs)
+static void burn_nsecs(struct perf_sched *sched, u64 nsecs)
 {
 	u64 T0 = get_nsecs(), T1;
 
 	do {
 		T1 = get_nsecs();
-	} while (T1 + run_measurement_overhead < T0 + nsecs);
+	} while (T1 + sched->run_measurement_overhead < T0 + nsecs);
 }
 
 static void sleep_nsecs(u64 nsecs)
@@ -183,24 +199,24 @@ static void sleep_nsecs(u64 nsecs)
 	nanosleep(&ts, NULL);
 }
 
-static void calibrate_run_measurement_overhead(void)
+static void calibrate_run_measurement_overhead(struct perf_sched *sched)
 {
 	u64 T0, T1, delta, min_delta = 1000000000ULL;
 	int i;
 
 	for (i = 0; i < 10; i++) {
 		T0 = get_nsecs();
-		burn_nsecs(0);
+		burn_nsecs(sched, 0);
 		T1 = get_nsecs();
 		delta = T1-T0;
 		min_delta = min(min_delta, delta);
 	}
-	run_measurement_overhead = min_delta;
+	sched->run_measurement_overhead = min_delta;
 
 	printf("run measurement overhead: %" PRIu64 " nsecs\n", min_delta);
 }
 
-static void calibrate_sleep_measurement_overhead(void)
+static void calibrate_sleep_measurement_overhead(struct perf_sched *sched)
 {
 	u64 T0, T1, delta, min_delta = 1000000000ULL;
 	int i;
@@ -213,7 +229,7 @@ static void calibrate_sleep_measurement_overhead(void)
 		min_delta = min(min_delta, delta);
 	}
 	min_delta -= 10000;
-	sleep_measurement_overhead = min_delta;
+	sched->sleep_measurement_overhead = min_delta;
 
 	printf("sleep measurement overhead: %" PRIu64 " nsecs\n", min_delta);
 }
@@ -246,8 +262,8 @@ static struct sched_atom *last_event(struct task_desc *task)
 	return task->atoms[task->nr_events - 1];
 }
 
-static void
-add_sched_event_run(struct task_desc *task, u64 timestamp, u64 duration)
+static void add_sched_event_run(struct perf_sched *sched, struct task_desc *task,
+				u64 timestamp, u64 duration)
 {
 	struct sched_atom *event, *curr_event = last_event(task);
 
@@ -256,7 +272,7 @@ add_sched_event_run(struct task_desc *task, u64 timestamp, u64 duration)
 	 * to it:
 	 */
 	if (curr_event && curr_event->type == SCHED_EVENT_RUN) {
-		nr_run_events_optimized++;
+		sched->nr_run_events_optimized++;
 		curr_event->duration += duration;
 		return;
 	}
@@ -266,12 +282,11 @@ add_sched_event_run(struct task_desc *task, u64 timestamp, u64 duration)
 	event->type = SCHED_EVENT_RUN;
 	event->duration = duration;
 
-	nr_run_events++;
+	sched->nr_run_events++;
 }
 
-static void
-add_sched_event_wakeup(struct task_desc *task, u64 timestamp,
-		       struct task_desc *wakee)
+static void add_sched_event_wakeup(struct perf_sched *sched, struct task_desc *task,
+				   u64 timestamp, struct task_desc *wakee)
 {
 	struct sched_atom *event, *wakee_event;
 
@@ -281,11 +296,11 @@ add_sched_event_wakeup(struct task_desc *task, u64 timestamp,
 
 	wakee_event = last_event(wakee);
 	if (!wakee_event || wakee_event->type != SCHED_EVENT_SLEEP) {
-		targetless_wakeups++;
+		sched->targetless_wakeups++;
 		return;
 	}
 	if (wakee_event->wait_sem) {
-		multitarget_wakeups++;
+		sched->multitarget_wakeups++;
 		return;
 	}
 
@@ -294,89 +309,89 @@ add_sched_event_wakeup(struct task_desc *task, u64 timestamp,
 	wakee_event->specific_wait = 1;
 	event->wait_sem = wakee_event->wait_sem;
 
-	nr_wakeup_events++;
+	sched->nr_wakeup_events++;
 }
 
-static void
-add_sched_event_sleep(struct task_desc *task, u64 timestamp,
-		      u64 task_state __used)
+static void add_sched_event_sleep(struct perf_sched *sched, struct task_desc *task,
+				  u64 timestamp, u64 task_state __maybe_unused)
 {
 	struct sched_atom *event = get_new_event(task, timestamp);
 
 	event->type = SCHED_EVENT_SLEEP;
 
-	nr_sleep_events++;
+	sched->nr_sleep_events++;
 }
 
-static struct task_desc *register_pid(unsigned long pid, const char *comm)
+static struct task_desc *register_pid(struct perf_sched *sched,
+				      unsigned long pid, const char *comm)
 {
 	struct task_desc *task;
 
 	BUG_ON(pid >= MAX_PID);
 
-	task = pid_to_task[pid];
+	task = sched->pid_to_task[pid];
 
 	if (task)
 		return task;
 
 	task = zalloc(sizeof(*task));
 	task->pid = pid;
-	task->nr = nr_tasks;
+	task->nr = sched->nr_tasks;
 	strcpy(task->comm, comm);
 	/*
 	 * every task starts in sleeping state - this gets ignored
 	 * if there's no wakeup pointing to this sleep state:
 	 */
-	add_sched_event_sleep(task, 0, 0);
+	add_sched_event_sleep(sched, task, 0, 0);
 
-	pid_to_task[pid] = task;
-	nr_tasks++;
-	tasks = realloc(tasks, nr_tasks*sizeof(struct task_task *));
-	BUG_ON(!tasks);
-	tasks[task->nr] = task;
+	sched->pid_to_task[pid] = task;
+	sched->nr_tasks++;
+	sched->tasks = realloc(sched->tasks, sched->nr_tasks * sizeof(struct task_task *));
+	BUG_ON(!sched->tasks);
+	sched->tasks[task->nr] = task;
 
 	if (verbose)
-		printf("registered task #%ld, PID %ld (%s)\n", nr_tasks, pid, comm);
+		printf("registered task #%ld, PID %ld (%s)\n", sched->nr_tasks, pid, comm);
 
 	return task;
 }
 
 
-static void print_task_traces(void)
+static void print_task_traces(struct perf_sched *sched)
 {
 	struct task_desc *task;
 	unsigned long i;
 
-	for (i = 0; i < nr_tasks; i++) {
-		task = tasks[i];
+	for (i = 0; i < sched->nr_tasks; i++) {
+		task = sched->tasks[i];
 		printf("task %6ld (%20s:%10ld), nr_events: %ld\n",
 			task->nr, task->comm, task->pid, task->nr_events);
 	}
 }
 
-static void add_cross_task_wakeups(void)
+static void add_cross_task_wakeups(struct perf_sched *sched)
 {
 	struct task_desc *task1, *task2;
 	unsigned long i, j;
 
-	for (i = 0; i < nr_tasks; i++) {
-		task1 = tasks[i];
+	for (i = 0; i < sched->nr_tasks; i++) {
+		task1 = sched->tasks[i];
 		j = i + 1;
-		if (j == nr_tasks)
+		if (j == sched->nr_tasks)
 			j = 0;
-		task2 = tasks[j];
-		add_sched_event_wakeup(task1, 0, task2);
+		task2 = sched->tasks[j];
+		add_sched_event_wakeup(sched, task1, 0, task2);
 	}
 }
 
-static void
-process_sched_event(struct task_desc *this_task __used, struct sched_atom *atom)
+static void perf_sched__process_event(struct perf_sched *sched,
+				      struct sched_atom *atom)
 {
 	int ret = 0;
 
 	switch (atom->type) {
 		case SCHED_EVENT_RUN:
-			burn_nsecs(atom->duration);
+			burn_nsecs(sched, atom->duration);
 			break;
 		case SCHED_EVENT_SLEEP:
 			if (atom->wait_sem)
@@ -423,8 +438,8 @@ static int self_open_counters(void)
 	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
 
 	if (fd < 0)
-		die("Error: sys_perf_event_open() syscall returned"
-		    "with %d (%s)\n", fd, strerror(errno));
+		pr_debug("Error: sys_perf_event_open() syscall returned"
+			 "with %d (%s)\n", fd, strerror(errno));
 	return fd;
 }
 
@@ -439,31 +454,41 @@ static u64 get_cpu_usage_nsec_self(int fd)
 	return runtime;
 }
 
+struct sched_thread_parms {
+	struct task_desc  *task;
+	struct perf_sched *sched;
+};
+
 static void *thread_func(void *ctx)
 {
-	struct task_desc *this_task = ctx;
+	struct sched_thread_parms *parms = ctx;
+	struct task_desc *this_task = parms->task;
+	struct perf_sched *sched = parms->sched;
 	u64 cpu_usage_0, cpu_usage_1;
 	unsigned long i, ret;
 	char comm2[22];
 	int fd;
 
+	free(parms);
+
 	sprintf(comm2, ":%s", this_task->comm);
 	prctl(PR_SET_NAME, comm2);
 	fd = self_open_counters();
-
+	if (fd < 0)
+		return NULL;
 again:
 	ret = sem_post(&this_task->ready_for_work);
 	BUG_ON(ret);
-	ret = pthread_mutex_lock(&start_work_mutex);
+	ret = pthread_mutex_lock(&sched->start_work_mutex);
 	BUG_ON(ret);
-	ret = pthread_mutex_unlock(&start_work_mutex);
+	ret = pthread_mutex_unlock(&sched->start_work_mutex);
 	BUG_ON(ret);
 
 	cpu_usage_0 = get_cpu_usage_nsec_self(fd);
 
 	for (i = 0; i < this_task->nr_events; i++) {
 		this_task->curr_event = i;
-		process_sched_event(this_task, this_task->atoms[i]);
+		perf_sched__process_event(sched, this_task->atoms[i]);
 	}
 
 	cpu_usage_1 = get_cpu_usage_nsec_self(fd);
@@ -471,15 +496,15 @@ again:
 	ret = sem_post(&this_task->work_done_sem);
 	BUG_ON(ret);
 
-	ret = pthread_mutex_lock(&work_done_wait_mutex);
+	ret = pthread_mutex_lock(&sched->work_done_wait_mutex);
 	BUG_ON(ret);
-	ret = pthread_mutex_unlock(&work_done_wait_mutex);
+	ret = pthread_mutex_unlock(&sched->work_done_wait_mutex);
 	BUG_ON(ret);
 
 	goto again;
 }
 
-static void create_tasks(void)
+static void create_tasks(struct perf_sched *sched)
 {
 	struct task_desc *task;
 	pthread_attr_t attr;
@@ -491,128 +516,129 @@ static void create_tasks(void)
 	err = pthread_attr_setstacksize(&attr,
 			(size_t) max(16 * 1024, PTHREAD_STACK_MIN));
 	BUG_ON(err);
-	err = pthread_mutex_lock(&start_work_mutex);
+	err = pthread_mutex_lock(&sched->start_work_mutex);
 	BUG_ON(err);
-	err = pthread_mutex_lock(&work_done_wait_mutex);
+	err = pthread_mutex_lock(&sched->work_done_wait_mutex);
 	BUG_ON(err);
-	for (i = 0; i < nr_tasks; i++) {
-		task = tasks[i];
+	for (i = 0; i < sched->nr_tasks; i++) {
+		struct sched_thread_parms *parms = malloc(sizeof(*parms));
+		BUG_ON(parms == NULL);
+		parms->task = task = sched->tasks[i];
+		parms->sched = sched;
 		sem_init(&task->sleep_sem, 0, 0);
 		sem_init(&task->ready_for_work, 0, 0);
 		sem_init(&task->work_done_sem, 0, 0);
 		task->curr_event = 0;
-		err = pthread_create(&task->thread, &attr, thread_func, task);
+		err = pthread_create(&task->thread, &attr, thread_func, parms);
 		BUG_ON(err);
 	}
 }
 
-static void wait_for_tasks(void)
+static void wait_for_tasks(struct perf_sched *sched)
 {
 	u64 cpu_usage_0, cpu_usage_1;
 	struct task_desc *task;
 	unsigned long i, ret;
 
-	start_time = get_nsecs();
-	cpu_usage = 0;
-	pthread_mutex_unlock(&work_done_wait_mutex);
+	sched->start_time = get_nsecs();
+	sched->cpu_usage = 0;
+	pthread_mutex_unlock(&sched->work_done_wait_mutex);
 
-	for (i = 0; i < nr_tasks; i++) {
-		task = tasks[i];
+	for (i = 0; i < sched->nr_tasks; i++) {
+		task = sched->tasks[i];
 		ret = sem_wait(&task->ready_for_work);
 		BUG_ON(ret);
 		sem_init(&task->ready_for_work, 0, 0);
 	}
-	ret = pthread_mutex_lock(&work_done_wait_mutex);
+	ret = pthread_mutex_lock(&sched->work_done_wait_mutex);
 	BUG_ON(ret);
 
 	cpu_usage_0 = get_cpu_usage_nsec_parent();
 
-	pthread_mutex_unlock(&start_work_mutex);
+	pthread_mutex_unlock(&sched->start_work_mutex);
 
-	for (i = 0; i < nr_tasks; i++) {
-		task = tasks[i];
+	for (i = 0; i < sched->nr_tasks; i++) {
+		task = sched->tasks[i];
 		ret = sem_wait(&task->work_done_sem);
 		BUG_ON(ret);
 		sem_init(&task->work_done_sem, 0, 0);
-		cpu_usage += task->cpu_usage;
+		sched->cpu_usage += task->cpu_usage;
 		task->cpu_usage = 0;
 	}
 
 	cpu_usage_1 = get_cpu_usage_nsec_parent();
-	if (!runavg_cpu_usage)
-		runavg_cpu_usage = cpu_usage;
-	runavg_cpu_usage = (runavg_cpu_usage*9 + cpu_usage)/10;
+	if (!sched->runavg_cpu_usage)
+		sched->runavg_cpu_usage = sched->cpu_usage;
+	sched->runavg_cpu_usage = (sched->runavg_cpu_usage * 9 + sched->cpu_usage) / 10;
 
-	parent_cpu_usage = cpu_usage_1 - cpu_usage_0;
-	if (!runavg_parent_cpu_usage)
-		runavg_parent_cpu_usage = parent_cpu_usage;
-	runavg_parent_cpu_usage = (runavg_parent_cpu_usage*9 +
-				   parent_cpu_usage)/10;
+	sched->parent_cpu_usage = cpu_usage_1 - cpu_usage_0;
+	if (!sched->runavg_parent_cpu_usage)
+		sched->runavg_parent_cpu_usage = sched->parent_cpu_usage;
+	sched->runavg_parent_cpu_usage = (sched->runavg_parent_cpu_usage * 9 +
+					 sched->parent_cpu_usage)/10;
 
-	ret = pthread_mutex_lock(&start_work_mutex);
+	ret = pthread_mutex_lock(&sched->start_work_mutex);
 	BUG_ON(ret);
 
-	for (i = 0; i < nr_tasks; i++) {
-		task = tasks[i];
+	for (i = 0; i < sched->nr_tasks; i++) {
+		task = sched->tasks[i];
 		sem_init(&task->sleep_sem, 0, 0);
 		task->curr_event = 0;
 	}
 }
 
-static void run_one_test(void)
+static void run_one_test(struct perf_sched *sched)
 {
 	u64 T0, T1, delta, avg_delta, fluct;
 
 	T0 = get_nsecs();
-	wait_for_tasks();
+	wait_for_tasks(sched);
 	T1 = get_nsecs();
 
 	delta = T1 - T0;
-	sum_runtime += delta;
-	nr_runs++;
+	sched->sum_runtime += delta;
+	sched->nr_runs++;
 
-	avg_delta = sum_runtime / nr_runs;
+	avg_delta = sched->sum_runtime / sched->nr_runs;
 	if (delta < avg_delta)
 		fluct = avg_delta - delta;
 	else
 		fluct = delta - avg_delta;
-	sum_fluct += fluct;
-	if (!run_avg)
-		run_avg = delta;
-	run_avg = (run_avg*9 + delta)/10;
+	sched->sum_fluct += fluct;
+	if (!sched->run_avg)
+		sched->run_avg = delta;
+	sched->run_avg = (sched->run_avg * 9 + delta) / 10;
 
-	printf("#%-3ld: %0.3f, ",
-		nr_runs, (double)delta/1000000.0);
+	printf("#%-3ld: %0.3f, ", sched->nr_runs, (double)delta / 1000000.0);
 
-	printf("ravg: %0.2f, ",
-		(double)run_avg/1e6);
+	printf("ravg: %0.2f, ", (double)sched->run_avg / 1e6);
 
 	printf("cpu: %0.2f / %0.2f",
-		(double)cpu_usage/1e6, (double)runavg_cpu_usage/1e6);
+		(double)sched->cpu_usage / 1e6, (double)sched->runavg_cpu_usage / 1e6);
 
 #if 0
 	/*
 	 * rusage statistics done by the parent, these are less
-	 * accurate than the sum_exec_runtime based statistics:
+	 * accurate than the sched->sum_exec_runtime based statistics:
 	 */
 	printf(" [%0.2f / %0.2f]",
-		(double)parent_cpu_usage/1e6,
-		(double)runavg_parent_cpu_usage/1e6);
+		(double)sched->parent_cpu_usage/1e6,
+		(double)sched->runavg_parent_cpu_usage/1e6);
 #endif
 
 	printf("\n");
 
-	if (nr_sleep_corrections)
-		printf(" (%ld sleep corrections)\n", nr_sleep_corrections);
-	nr_sleep_corrections = 0;
+	if (sched->nr_sleep_corrections)
+		printf(" (%ld sleep corrections)\n", sched->nr_sleep_corrections);
+	sched->nr_sleep_corrections = 0;
 }
 
-static void test_calibrations(void)
+static void test_calibrations(struct perf_sched *sched)
 {
 	u64 T0, T1;
 
 	T0 = get_nsecs();
-	burn_nsecs(1e6);
+	burn_nsecs(sched, 1e6);
 	T1 = get_nsecs();
 
 	printf("the run test took %" PRIu64 " nsecs\n", T1 - T0);
@@ -624,216 +650,92 @@ static void test_calibrations(void)
 	printf("the sleep test took %" PRIu64 " nsecs\n", T1 - T0);
 }
 
-#define FILL_FIELD(ptr, field, event, data)	\
-	ptr.field = (typeof(ptr.field)) raw_field_value(event, #field, data)
-
-#define FILL_ARRAY(ptr, array, event, data)			\
-do {								\
-	void *__array = raw_field_ptr(event, #array, data);	\
-	memcpy(ptr.array, __array, sizeof(ptr.array));	\
-} while(0)
-
-#define FILL_COMMON_FIELDS(ptr, event, data)			\
-do {								\
-	FILL_FIELD(ptr, common_type, event, data);		\
-	FILL_FIELD(ptr, common_flags, event, data);		\
-	FILL_FIELD(ptr, common_preempt_count, event, data);	\
-	FILL_FIELD(ptr, common_pid, event, data);		\
-	FILL_FIELD(ptr, common_tgid, event, data);		\
-} while (0)
-
-
-
-struct trace_switch_event {
-	u32 size;
-
-	u16 common_type;
-	u8 common_flags;
-	u8 common_preempt_count;
-	u32 common_pid;
-	u32 common_tgid;
-
-	char prev_comm[16];
-	u32 prev_pid;
-	u32 prev_prio;
-	u64 prev_state;
-	char next_comm[16];
-	u32 next_pid;
-	u32 next_prio;
-};
-
-struct trace_runtime_event {
-	u32 size;
-
-	u16 common_type;
-	u8 common_flags;
-	u8 common_preempt_count;
-	u32 common_pid;
-	u32 common_tgid;
-
-	char comm[16];
-	u32 pid;
-	u64 runtime;
-	u64 vruntime;
-};
-
-struct trace_wakeup_event {
-	u32 size;
-
-	u16 common_type;
-	u8 common_flags;
-	u8 common_preempt_count;
-	u32 common_pid;
-	u32 common_tgid;
-
-	char comm[16];
-	u32 pid;
-
-	u32 prio;
-	u32 success;
-	u32 cpu;
-};
-
-struct trace_fork_event {
-	u32 size;
-
-	u16 common_type;
-	u8 common_flags;
-	u8 common_preempt_count;
-	u32 common_pid;
-	u32 common_tgid;
-
-	char parent_comm[16];
-	u32 parent_pid;
-	char child_comm[16];
-	u32 child_pid;
-};
-
-struct trace_migrate_task_event {
-	u32 size;
-
-	u16 common_type;
-	u8 common_flags;
-	u8 common_preempt_count;
-	u32 common_pid;
-	u32 common_tgid;
-
-	char comm[16];
-	u32 pid;
-
-	u32 prio;
-	u32 cpu;
-};
-
-struct trace_sched_handler {
-	void (*switch_event)(struct trace_switch_event *,
-			     struct machine *,
-			     struct event_format *,
-			     struct perf_sample *sample);
-
-	void (*runtime_event)(struct trace_runtime_event *,
-			      struct machine *,
-			      struct perf_sample *sample);
-
-	void (*wakeup_event)(struct trace_wakeup_event *,
-			     struct machine *,
-			     struct event_format *,
-			     struct perf_sample *sample);
-
-	void (*fork_event)(struct trace_fork_event *,
-			   struct event_format *event);
-
-	void (*migrate_task_event)(struct trace_migrate_task_event *,
-				   struct machine *machine,
-				   struct perf_sample *sample);
-};
-
-
-static void
-replay_wakeup_event(struct trace_wakeup_event *wakeup_event,
-		    struct machine *machine __used,
-		    struct event_format *event, struct perf_sample *sample)
+static int
+replay_wakeup_event(struct perf_sched *sched,
+		    struct perf_evsel *evsel, struct perf_sample *sample,
+		    struct machine *machine __maybe_unused)
 {
+	const char *comm = perf_evsel__strval(evsel, sample, "comm");
+	const u32 pid	 = perf_evsel__intval(evsel, sample, "pid");
 	struct task_desc *waker, *wakee;
 
 	if (verbose) {
-		printf("sched_wakeup event %p\n", event);
+		printf("sched_wakeup event %p\n", evsel);
 
-		printf(" ... pid %d woke up %s/%d\n",
-			wakeup_event->common_pid,
-			wakeup_event->comm,
-			wakeup_event->pid);
+		printf(" ... pid %d woke up %s/%d\n", sample->tid, comm, pid);
 	}
 
-	waker = register_pid(wakeup_event->common_pid, "<unknown>");
-	wakee = register_pid(wakeup_event->pid, wakeup_event->comm);
+	waker = register_pid(sched, sample->tid, "<unknown>");
+	wakee = register_pid(sched, pid, comm);
 
-	add_sched_event_wakeup(waker, sample->time, wakee);
+	add_sched_event_wakeup(sched, waker, sample->time, wakee);
+	return 0;
 }
 
-static u64 cpu_last_switched[MAX_CPUS];
-
-static void
-replay_switch_event(struct trace_switch_event *switch_event,
-		    struct machine *machine __used,
-		    struct event_format *event,
-		    struct perf_sample *sample)
+static int replay_switch_event(struct perf_sched *sched,
+			       struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       struct machine *machine __maybe_unused)
 {
-	struct task_desc *prev, __used *next;
+	const char *prev_comm  = perf_evsel__strval(evsel, sample, "prev_comm"),
+		   *next_comm  = perf_evsel__strval(evsel, sample, "next_comm");
+	const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"),
+		  next_pid = perf_evsel__intval(evsel, sample, "next_pid");
+	const u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state");
+	struct task_desc *prev, __maybe_unused *next;
 	u64 timestamp0, timestamp = sample->time;
 	int cpu = sample->cpu;
 	s64 delta;
 
 	if (verbose)
-		printf("sched_switch event %p\n", event);
+		printf("sched_switch event %p\n", evsel);
 
 	if (cpu >= MAX_CPUS || cpu < 0)
-		return;
+		return 0;
 
-	timestamp0 = cpu_last_switched[cpu];
+	timestamp0 = sched->cpu_last_switched[cpu];
 	if (timestamp0)
 		delta = timestamp - timestamp0;
 	else
 		delta = 0;
 
-	if (delta < 0)
-		die("hm, delta: %" PRIu64 " < 0 ?\n", delta);
-
-	if (verbose) {
-		printf(" ... switch from %s/%d to %s/%d [ran %" PRIu64 " nsecs]\n",
-			switch_event->prev_comm, switch_event->prev_pid,
-			switch_event->next_comm, switch_event->next_pid,
-			delta);
+	if (delta < 0) {
+		pr_debug("hm, delta: %" PRIu64 " < 0 ?\n", delta);
+		return -1;
 	}
 
-	prev = register_pid(switch_event->prev_pid, switch_event->prev_comm);
-	next = register_pid(switch_event->next_pid, switch_event->next_comm);
+	pr_debug(" ... switch from %s/%d to %s/%d [ran %" PRIu64 " nsecs]\n",
+		 prev_comm, prev_pid, next_comm, next_pid, delta);
 
-	cpu_last_switched[cpu] = timestamp;
+	prev = register_pid(sched, prev_pid, prev_comm);
+	next = register_pid(sched, next_pid, next_comm);
 
-	add_sched_event_run(prev, timestamp, delta);
-	add_sched_event_sleep(prev, timestamp, switch_event->prev_state);
-}
+	sched->cpu_last_switched[cpu] = timestamp;
 
+	add_sched_event_run(sched, prev, timestamp, delta);
+	add_sched_event_sleep(sched, prev, timestamp, prev_state);
 
-static void
-replay_fork_event(struct trace_fork_event *fork_event,
-		  struct event_format *event)
+	return 0;
+}
+
+static int replay_fork_event(struct perf_sched *sched, struct perf_evsel *evsel,
+			     struct perf_sample *sample)
 {
+	const char *parent_comm = perf_evsel__strval(evsel, sample, "parent_comm"),
+		   *child_comm  = perf_evsel__strval(evsel, sample, "child_comm");
+	const u32 parent_pid  = perf_evsel__intval(evsel, sample, "parent_pid"),
+		  child_pid  = perf_evsel__intval(evsel, sample, "child_pid");
+
 	if (verbose) {
-		printf("sched_fork event %p\n", event);
-		printf("... parent: %s/%d\n", fork_event->parent_comm, fork_event->parent_pid);
-		printf("...  child: %s/%d\n", fork_event->child_comm, fork_event->child_pid);
+		printf("sched_fork event %p\n", evsel);
+		printf("... parent: %s/%d\n", parent_comm, parent_pid);
+		printf("...  child: %s/%d\n", child_comm, child_pid);
 	}
-	register_pid(fork_event->parent_pid, fork_event->parent_comm);
-	register_pid(fork_event->child_pid, fork_event->child_comm);
-}
 
-static struct trace_sched_handler replay_ops  = {
-	.wakeup_event		= replay_wakeup_event,
-	.switch_event		= replay_switch_event,
-	.fork_event		= replay_fork_event,
-};
+	register_pid(sched, parent_pid, parent_comm);
+	register_pid(sched, child_pid, child_comm);
+	return 0;
+}
 
 struct sort_dimension {
 	const char		*name;
@@ -841,8 +743,6 @@ struct sort_dimension {
 	struct list_head	list;
 };
 
-static LIST_HEAD(cmp_pid);
-
 static int
 thread_lat_cmp(struct list_head *list, struct work_atoms *l, struct work_atoms *r)
 {
@@ -911,40 +811,45 @@ __thread_latency_insert(struct rb_root *root, struct work_atoms *data,
 	rb_insert_color(&data->node, root);
 }
 
-static void thread_atoms_insert(struct thread *thread)
+static int thread_atoms_insert(struct perf_sched *sched, struct thread *thread)
 {
 	struct work_atoms *atoms = zalloc(sizeof(*atoms));
-	if (!atoms)
-		die("No memory");
+	if (!atoms) {
+		pr_err("No memory at %s\n", __func__);
+		return -1;
+	}
 
 	atoms->thread = thread;
 	INIT_LIST_HEAD(&atoms->work_list);
-	__thread_latency_insert(&atom_root, atoms, &cmp_pid);
+	__thread_latency_insert(&sched->atom_root, atoms, &sched->cmp_pid);
+	return 0;
 }
 
-static void
-latency_fork_event(struct trace_fork_event *fork_event __used,
-		   struct event_format *event __used)
+static int latency_fork_event(struct perf_sched *sched __maybe_unused,
+			      struct perf_evsel *evsel __maybe_unused,
+			      struct perf_sample *sample __maybe_unused)
 {
 	/* should insert the newcomer */
+	return 0;
 }
 
-__used
-static char sched_out_state(struct trace_switch_event *switch_event)
+static char sched_out_state(u64 prev_state)
 {
 	const char *str = TASK_STATE_TO_CHAR_STR;
 
-	return str[switch_event->prev_state];
+	return str[prev_state];
 }
 
-static void
+static int
 add_sched_out_event(struct work_atoms *atoms,
 		    char run_state,
 		    u64 timestamp)
 {
 	struct work_atom *atom = zalloc(sizeof(*atom));
-	if (!atom)
-		die("Non memory");
+	if (!atom) {
+		pr_err("Non memory at %s", __func__);
+		return -1;
+	}
 
 	atom->sched_out_time = timestamp;
 
@@ -954,10 +859,12 @@ add_sched_out_event(struct work_atoms *atoms,
 	}
 
 	list_add_tail(&atom->list, &atoms->work_list);
+	return 0;
 }
 
 static void
-add_runtime_event(struct work_atoms *atoms, u64 delta, u64 timestamp __used)
+add_runtime_event(struct work_atoms *atoms, u64 delta,
+		  u64 timestamp __maybe_unused)
 {
 	struct work_atom *atom;
 
@@ -1000,12 +907,14 @@ add_sched_in_event(struct work_atoms *atoms, u64 timestamp)
 	atoms->nb_atoms++;
 }
 
-static void
-latency_switch_event(struct trace_switch_event *switch_event,
-		     struct machine *machine,
-		     struct event_format *event __used,
-		     struct perf_sample *sample)
+static int latency_switch_event(struct perf_sched *sched,
+				struct perf_evsel *evsel,
+				struct perf_sample *sample,
+				struct machine *machine)
 {
+	const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"),
+		  next_pid = perf_evsel__intval(evsel, sample, "next_pid");
+	const u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state");
 	struct work_atoms *out_events, *in_events;
 	struct thread *sched_out, *sched_in;
 	u64 timestamp0, timestamp = sample->time;
@@ -1014,87 +923,112 @@ latency_switch_event(struct trace_switch_event *switch_event,
 
 	BUG_ON(cpu >= MAX_CPUS || cpu < 0);
 
-	timestamp0 = cpu_last_switched[cpu];
-	cpu_last_switched[cpu] = timestamp;
+	timestamp0 = sched->cpu_last_switched[cpu];
+	sched->cpu_last_switched[cpu] = timestamp;
 	if (timestamp0)
 		delta = timestamp - timestamp0;
 	else
 		delta = 0;
 
-	if (delta < 0)
-		die("hm, delta: %" PRIu64 " < 0 ?\n", delta);
-
+	if (delta < 0) {
+		pr_err("hm, delta: %" PRIu64 " < 0 ?\n", delta);
+		return -1;
+	}
 
-	sched_out = machine__findnew_thread(machine, switch_event->prev_pid);
-	sched_in = machine__findnew_thread(machine, switch_event->next_pid);
+	sched_out = machine__findnew_thread(machine, prev_pid);
+	sched_in = machine__findnew_thread(machine, next_pid);
 
-	out_events = thread_atoms_search(&atom_root, sched_out, &cmp_pid);
+	out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid);
 	if (!out_events) {
-		thread_atoms_insert(sched_out);
-		out_events = thread_atoms_search(&atom_root, sched_out, &cmp_pid);
-		if (!out_events)
-			die("out-event: Internal tree error");
+		if (thread_atoms_insert(sched, sched_out))
+			return -1;
+		out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid);
+		if (!out_events) {
+			pr_err("out-event: Internal tree error");
+			return -1;
+		}
 	}
-	add_sched_out_event(out_events, sched_out_state(switch_event), timestamp);
+	if (add_sched_out_event(out_events, sched_out_state(prev_state), timestamp))
+		return -1;
 
-	in_events = thread_atoms_search(&atom_root, sched_in, &cmp_pid);
+	in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid);
 	if (!in_events) {
-		thread_atoms_insert(sched_in);
-		in_events = thread_atoms_search(&atom_root, sched_in, &cmp_pid);
-		if (!in_events)
-			die("in-event: Internal tree error");
+		if (thread_atoms_insert(sched, sched_in))
+			return -1;
+		in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid);
+		if (!in_events) {
+			pr_err("in-event: Internal tree error");
+			return -1;
+		}
 		/*
 		 * Take came in we have not heard about yet,
 		 * add in an initial atom in runnable state:
 		 */
-		add_sched_out_event(in_events, 'R', timestamp);
+		if (add_sched_out_event(in_events, 'R', timestamp))
+			return -1;
 	}
 	add_sched_in_event(in_events, timestamp);
+
+	return 0;
 }
 
-static void
-latency_runtime_event(struct trace_runtime_event *runtime_event,
-		      struct machine *machine, struct perf_sample *sample)
+static int latency_runtime_event(struct perf_sched *sched,
+				 struct perf_evsel *evsel,
+				 struct perf_sample *sample,
+				 struct machine *machine)
 {
-	struct thread *thread = machine__findnew_thread(machine, runtime_event->pid);
-	struct work_atoms *atoms = thread_atoms_search(&atom_root, thread, &cmp_pid);
+	const u32 pid	   = perf_evsel__intval(evsel, sample, "pid");
+	const u64 runtime  = perf_evsel__intval(evsel, sample, "runtime");
+	struct thread *thread = machine__findnew_thread(machine, pid);
+	struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
 	u64 timestamp = sample->time;
 	int cpu = sample->cpu;
 
 	BUG_ON(cpu >= MAX_CPUS || cpu < 0);
 	if (!atoms) {
-		thread_atoms_insert(thread);
-		atoms = thread_atoms_search(&atom_root, thread, &cmp_pid);
-		if (!atoms)
-			die("in-event: Internal tree error");
-		add_sched_out_event(atoms, 'R', timestamp);
+		if (thread_atoms_insert(sched, thread))
+			return -1;
+		atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
+		if (!atoms) {
+			pr_debug("in-event: Internal tree error");
+			return -1;
+		}
+		if (add_sched_out_event(atoms, 'R', timestamp))
+			return -1;
 	}
 
-	add_runtime_event(atoms, runtime_event->runtime, timestamp);
+	add_runtime_event(atoms, runtime, timestamp);
+	return 0;
 }
 
-static void
-latency_wakeup_event(struct trace_wakeup_event *wakeup_event,
-		     struct machine *machine, struct event_format *event __used,
-		     struct perf_sample *sample)
+static int latency_wakeup_event(struct perf_sched *sched,
+				struct perf_evsel *evsel,
+				struct perf_sample *sample,
+				struct machine *machine)
 {
+	const u32 pid	  = perf_evsel__intval(evsel, sample, "pid"),
+		  success = perf_evsel__intval(evsel, sample, "success");
 	struct work_atoms *atoms;
 	struct work_atom *atom;
 	struct thread *wakee;
 	u64 timestamp = sample->time;
 
 	/* Note for later, it may be interesting to observe the failing cases */
-	if (!wakeup_event->success)
-		return;
+	if (!success)
+		return 0;
 
-	wakee = machine__findnew_thread(machine, wakeup_event->pid);
-	atoms = thread_atoms_search(&atom_root, wakee, &cmp_pid);
+	wakee = machine__findnew_thread(machine, pid);
+	atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
 	if (!atoms) {
-		thread_atoms_insert(wakee);
-		atoms = thread_atoms_search(&atom_root, wakee, &cmp_pid);
-		if (!atoms)
-			die("wakeup-event: Internal tree error");
-		add_sched_out_event(atoms, 'S', timestamp);
+		if (thread_atoms_insert(sched, wakee))
+			return -1;
+		atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
+		if (!atoms) {
+			pr_debug("wakeup-event: Internal tree error");
+			return -1;
+		}
+		if (add_sched_out_event(atoms, 'S', timestamp))
+			return -1;
 	}
 
 	BUG_ON(list_empty(&atoms->work_list));
@@ -1106,23 +1040,26 @@ latency_wakeup_event(struct trace_wakeup_event *wakeup_event,
 	 * one CPU, or are only looking at only one, so don't
 	 * make useless noise.
 	 */
-	if (profile_cpu == -1 && atom->state != THREAD_SLEEPING)
-		nr_state_machine_bugs++;
+	if (sched->profile_cpu == -1 && atom->state != THREAD_SLEEPING)
+		sched->nr_state_machine_bugs++;
 
-	nr_timestamps++;
+	sched->nr_timestamps++;
 	if (atom->sched_out_time > timestamp) {
-		nr_unordered_timestamps++;
-		return;
+		sched->nr_unordered_timestamps++;
+		return 0;
 	}
 
 	atom->state = THREAD_WAIT_CPU;
 	atom->wake_up_time = timestamp;
+	return 0;
 }
 
-static void
-latency_migrate_task_event(struct trace_migrate_task_event *migrate_task_event,
-			   struct machine *machine, struct perf_sample *sample)
+static int latency_migrate_task_event(struct perf_sched *sched,
+				      struct perf_evsel *evsel,
+				      struct perf_sample *sample,
+				      struct machine *machine)
 {
+	const u32 pid = perf_evsel__intval(evsel, sample, "pid");
 	u64 timestamp = sample->time;
 	struct work_atoms *atoms;
 	struct work_atom *atom;
@@ -1131,18 +1068,22 @@ latency_migrate_task_event(struct trace_migrate_task_event *migrate_task_event,
 	/*
 	 * Only need to worry about migration when profiling one CPU.
 	 */
-	if (profile_cpu == -1)
-		return;
+	if (sched->profile_cpu == -1)
+		return 0;
 
-	migrant = machine__findnew_thread(machine, migrate_task_event->pid);
-	atoms = thread_atoms_search(&atom_root, migrant, &cmp_pid);
+	migrant = machine__findnew_thread(machine, pid);
+	atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
 	if (!atoms) {
-		thread_atoms_insert(migrant);
-		register_pid(migrant->pid, migrant->comm);
-		atoms = thread_atoms_search(&atom_root, migrant, &cmp_pid);
-		if (!atoms)
-			die("migration-event: Internal tree error");
-		add_sched_out_event(atoms, 'R', timestamp);
+		if (thread_atoms_insert(sched, migrant))
+			return -1;
+		register_pid(sched, migrant->pid, migrant->comm);
+		atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
+		if (!atoms) {
+			pr_debug("migration-event: Internal tree error");
+			return -1;
+		}
+		if (add_sched_out_event(atoms, 'R', timestamp))
+			return -1;
 	}
 
 	BUG_ON(list_empty(&atoms->work_list));
@@ -1150,21 +1091,15 @@ latency_migrate_task_event(struct trace_migrate_task_event *migrate_task_event,
 	atom = list_entry(atoms->work_list.prev, struct work_atom, list);
 	atom->sched_in_time = atom->sched_out_time = atom->wake_up_time = timestamp;
 
-	nr_timestamps++;
+	sched->nr_timestamps++;
 
 	if (atom->sched_out_time > timestamp)
-		nr_unordered_timestamps++;
-}
+		sched->nr_unordered_timestamps++;
 
-static struct trace_sched_handler lat_ops  = {
-	.wakeup_event		= latency_wakeup_event,
-	.switch_event		= latency_switch_event,
-	.runtime_event		= latency_runtime_event,
-	.fork_event		= latency_fork_event,
-	.migrate_task_event	= latency_migrate_task_event,
-};
+	return 0;
+}
 
-static void output_lat_thread(struct work_atoms *work_list)
+static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_list)
 {
 	int i;
 	int ret;
@@ -1178,8 +1113,8 @@ static void output_lat_thread(struct work_atoms *work_list)
 	if (!strcmp(work_list->thread->comm, "swapper"))
 		return;
 
-	all_runtime += work_list->total_runtime;
-	all_count += work_list->nb_atoms;
+	sched->all_runtime += work_list->total_runtime;
+	sched->all_count   += work_list->nb_atoms;
 
 	ret = printf("  %s:%d ", work_list->thread->comm, work_list->thread->pid);
 
@@ -1205,11 +1140,6 @@ static int pid_cmp(struct work_atoms *l, struct work_atoms *r)
 	return 0;
 }
 
-static struct sort_dimension pid_sort_dimension = {
-	.name			= "pid",
-	.cmp			= pid_cmp,
-};
-
 static int avg_cmp(struct work_atoms *l, struct work_atoms *r)
 {
 	u64 avgl, avgr;
@@ -1231,11 +1161,6 @@ static int avg_cmp(struct work_atoms *l, struct work_atoms *r)
 	return 0;
 }
 
-static struct sort_dimension avg_sort_dimension = {
-	.name			= "avg",
-	.cmp			= avg_cmp,
-};
-
 static int max_cmp(struct work_atoms *l, struct work_atoms *r)
 {
 	if (l->max_lat < r->max_lat)
@@ -1246,11 +1171,6 @@ static int max_cmp(struct work_atoms *l, struct work_atoms *r)
 	return 0;
 }
 
-static struct sort_dimension max_sort_dimension = {
-	.name			= "max",
-	.cmp			= max_cmp,
-};
-
 static int switch_cmp(struct work_atoms *l, struct work_atoms *r)
 {
 	if (l->nb_atoms < r->nb_atoms)
@@ -1261,11 +1181,6 @@ static int switch_cmp(struct work_atoms *l, struct work_atoms *r)
 	return 0;
 }
 
-static struct sort_dimension switch_sort_dimension = {
-	.name			= "switch",
-	.cmp			= switch_cmp,
-};
-
 static int runtime_cmp(struct work_atoms *l, struct work_atoms *r)
 {
 	if (l->total_runtime < r->total_runtime)
@@ -1276,28 +1191,38 @@ static int runtime_cmp(struct work_atoms *l, struct work_atoms *r)
 	return 0;
 }
 
-static struct sort_dimension runtime_sort_dimension = {
-	.name			= "runtime",
-	.cmp			= runtime_cmp,
-};
-
-static struct sort_dimension *available_sorts[] = {
-	&pid_sort_dimension,
-	&avg_sort_dimension,
-	&max_sort_dimension,
-	&switch_sort_dimension,
-	&runtime_sort_dimension,
-};
-
-#define NB_AVAILABLE_SORTS	(int)(sizeof(available_sorts) / sizeof(struct sort_dimension *))
-
-static LIST_HEAD(sort_list);
-
 static int sort_dimension__add(const char *tok, struct list_head *list)
 {
-	int i;
+	size_t i;
+	static struct sort_dimension avg_sort_dimension = {
+		.name = "avg",
+		.cmp  = avg_cmp,
+	};
+	static struct sort_dimension max_sort_dimension = {
+		.name = "max",
+		.cmp  = max_cmp,
+	};
+	static struct sort_dimension pid_sort_dimension = {
+		.name = "pid",
+		.cmp  = pid_cmp,
+	};
+	static struct sort_dimension runtime_sort_dimension = {
+		.name = "runtime",
+		.cmp  = runtime_cmp,
+	};
+	static struct sort_dimension switch_sort_dimension = {
+		.name = "switch",
+		.cmp  = switch_cmp,
+	};
+	struct sort_dimension *available_sorts[] = {
+		&pid_sort_dimension,
+		&avg_sort_dimension,
+		&max_sort_dimension,
+		&switch_sort_dimension,
+		&runtime_sort_dimension,
+	};
 
-	for (i = 0; i < NB_AVAILABLE_SORTS; i++) {
+	for (i = 0; i < ARRAY_SIZE(available_sorts); i++) {
 		if (!strcmp(available_sorts[i]->name, tok)) {
 			list_add_tail(&available_sorts[i]->list, list);
 
@@ -1308,68 +1233,41 @@ static int sort_dimension__add(const char *tok, struct list_head *list)
 	return -1;
 }
 
-static void setup_sorting(void);
-
-static void sort_lat(void)
+static void perf_sched__sort_lat(struct perf_sched *sched)
 {
 	struct rb_node *node;
 
 	for (;;) {
 		struct work_atoms *data;
-		node = rb_first(&atom_root);
+		node = rb_first(&sched->atom_root);
 		if (!node)
 			break;
 
-		rb_erase(node, &atom_root);
+		rb_erase(node, &sched->atom_root);
 		data = rb_entry(node, struct work_atoms, node);
-		__thread_latency_insert(&sorted_atom_root, data, &sort_list);
+		__thread_latency_insert(&sched->sorted_atom_root, data, &sched->sort_list);
 	}
 }
 
-static struct trace_sched_handler *trace_handler;
-
-static void
-process_sched_wakeup_event(struct perf_tool *tool __used,
-			   struct event_format *event,
-			   struct perf_sample *sample,
-			   struct machine *machine,
-			   struct thread *thread __used)
+static int process_sched_wakeup_event(struct perf_tool *tool,
+				      struct perf_evsel *evsel,
+				      struct perf_sample *sample,
+				      struct machine *machine)
 {
-	void *data = sample->raw_data;
-	struct trace_wakeup_event wakeup_event;
+	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
 
-	FILL_COMMON_FIELDS(wakeup_event, event, data);
+	if (sched->tp_handler->wakeup_event)
+		return sched->tp_handler->wakeup_event(sched, evsel, sample, machine);
 
-	FILL_ARRAY(wakeup_event, comm, event, data);
-	FILL_FIELD(wakeup_event, pid, event, data);
-	FILL_FIELD(wakeup_event, prio, event, data);
-	FILL_FIELD(wakeup_event, success, event, data);
-	FILL_FIELD(wakeup_event, cpu, event, data);
-
-	if (trace_handler->wakeup_event)
-		trace_handler->wakeup_event(&wakeup_event, machine, event, sample);
+	return 0;
 }
 
-/*
- * Track the current task - that way we can know whether there's any
- * weird events, such as a task being switched away that is not current.
- */
-static int max_cpu;
-
-static u32 curr_pid[MAX_CPUS] = { [0 ... MAX_CPUS-1] = -1 };
-
-static struct thread *curr_thread[MAX_CPUS];
-
-static char next_shortname1 = 'A';
-static char next_shortname2 = '0';
-
-static void
-map_switch_event(struct trace_switch_event *switch_event,
-		 struct machine *machine,
-		 struct event_format *event __used,
-		 struct perf_sample *sample)
+static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
+			    struct perf_sample *sample, struct machine *machine)
 {
-	struct thread *sched_out __used, *sched_in;
+	const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"),
+		  next_pid = perf_evsel__intval(evsel, sample, "next_pid");
+	struct thread *sched_out __maybe_unused, *sched_in;
 	int new_shortname;
 	u64 timestamp0, timestamp = sample->time;
 	s64 delta;
@@ -1377,54 +1275,55 @@ map_switch_event(struct trace_switch_event *switch_event,
 
 	BUG_ON(this_cpu >= MAX_CPUS || this_cpu < 0);
 
-	if (this_cpu > max_cpu)
-		max_cpu = this_cpu;
+	if (this_cpu > sched->max_cpu)
+		sched->max_cpu = this_cpu;
 
-	timestamp0 = cpu_last_switched[this_cpu];
-	cpu_last_switched[this_cpu] = timestamp;
+	timestamp0 = sched->cpu_last_switched[this_cpu];
+	sched->cpu_last_switched[this_cpu] = timestamp;
 	if (timestamp0)
 		delta = timestamp - timestamp0;
 	else
 		delta = 0;
 
-	if (delta < 0)
-		die("hm, delta: %" PRIu64 " < 0 ?\n", delta);
-
+	if (delta < 0) {
+		pr_debug("hm, delta: %" PRIu64 " < 0 ?\n", delta);
+		return -1;
+	}
 
-	sched_out = machine__findnew_thread(machine, switch_event->prev_pid);
-	sched_in = machine__findnew_thread(machine, switch_event->next_pid);
+	sched_out = machine__findnew_thread(machine, prev_pid);
+	sched_in = machine__findnew_thread(machine, next_pid);
 
-	curr_thread[this_cpu] = sched_in;
+	sched->curr_thread[this_cpu] = sched_in;
 
 	printf("  ");
 
 	new_shortname = 0;
 	if (!sched_in->shortname[0]) {
-		sched_in->shortname[0] = next_shortname1;
-		sched_in->shortname[1] = next_shortname2;
+		sched_in->shortname[0] = sched->next_shortname1;
+		sched_in->shortname[1] = sched->next_shortname2;
 
-		if (next_shortname1 < 'Z') {
-			next_shortname1++;
+		if (sched->next_shortname1 < 'Z') {
+			sched->next_shortname1++;
 		} else {
-			next_shortname1='A';
-			if (next_shortname2 < '9') {
-				next_shortname2++;
+			sched->next_shortname1='A';
+			if (sched->next_shortname2 < '9') {
+				sched->next_shortname2++;
 			} else {
-				next_shortname2='0';
+				sched->next_shortname2='0';
 			}
 		}
 		new_shortname = 1;
 	}
 
-	for (cpu = 0; cpu <= max_cpu; cpu++) {
+	for (cpu = 0; cpu <= sched->max_cpu; cpu++) {
 		if (cpu != this_cpu)
 			printf(" ");
 		else
 			printf("*");
 
-		if (curr_thread[cpu]) {
-			if (curr_thread[cpu]->pid)
-				printf("%2s ", curr_thread[cpu]->shortname);
+		if (sched->curr_thread[cpu]) {
+			if (sched->curr_thread[cpu]->pid)
+				printf("%2s ", sched->curr_thread[cpu]->shortname);
 			else
 				printf(".  ");
 		} else
@@ -1438,127 +1337,97 @@ map_switch_event(struct trace_switch_event *switch_event,
 	} else {
 		printf("\n");
 	}
+
+	return 0;
 }
 
-static void
-process_sched_switch_event(struct perf_tool *tool __used,
-			   struct event_format *event,
-			   struct perf_sample *sample,
-			   struct machine *machine,
-			   struct thread *thread __used)
+static int process_sched_switch_event(struct perf_tool *tool,
+				      struct perf_evsel *evsel,
+				      struct perf_sample *sample,
+				      struct machine *machine)
 {
-	int this_cpu = sample->cpu;
-	void *data = sample->raw_data;
-	struct trace_switch_event switch_event;
-
-	FILL_COMMON_FIELDS(switch_event, event, data);
+	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
+	int this_cpu = sample->cpu, err = 0;
+	u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"),
+	    next_pid = perf_evsel__intval(evsel, sample, "next_pid");
 
-	FILL_ARRAY(switch_event, prev_comm, event, data);
-	FILL_FIELD(switch_event, prev_pid, event, data);
-	FILL_FIELD(switch_event, prev_prio, event, data);
-	FILL_FIELD(switch_event, prev_state, event, data);
-	FILL_ARRAY(switch_event, next_comm, event, data);
-	FILL_FIELD(switch_event, next_pid, event, data);
-	FILL_FIELD(switch_event, next_prio, event, data);
-
-	if (curr_pid[this_cpu] != (u32)-1) {
+	if (sched->curr_pid[this_cpu] != (u32)-1) {
 		/*
 		 * Are we trying to switch away a PID that is
 		 * not current?
 		 */
-		if (curr_pid[this_cpu] != switch_event.prev_pid)
-			nr_context_switch_bugs++;
+		if (sched->curr_pid[this_cpu] != prev_pid)
+			sched->nr_context_switch_bugs++;
 	}
-	if (trace_handler->switch_event)
-		trace_handler->switch_event(&switch_event, machine, event, sample);
 
-	curr_pid[this_cpu] = switch_event.next_pid;
+	if (sched->tp_handler->switch_event)
+		err = sched->tp_handler->switch_event(sched, evsel, sample, machine);
+
+	sched->curr_pid[this_cpu] = next_pid;
+	return err;
 }
 
-static void
-process_sched_runtime_event(struct perf_tool *tool __used,
-			    struct event_format *event,
-			    struct perf_sample *sample,
-			    struct machine *machine,
-			    struct thread *thread __used)
+static int process_sched_runtime_event(struct perf_tool *tool,
+				       struct perf_evsel *evsel,
+				       struct perf_sample *sample,
+				       struct machine *machine)
 {
-	void *data = sample->raw_data;
-	struct trace_runtime_event runtime_event;
+	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
 
-	FILL_ARRAY(runtime_event, comm, event, data);
-	FILL_FIELD(runtime_event, pid, event, data);
-	FILL_FIELD(runtime_event, runtime, event, data);
-	FILL_FIELD(runtime_event, vruntime, event, data);
+	if (sched->tp_handler->runtime_event)
+		return sched->tp_handler->runtime_event(sched, evsel, sample, machine);
 
-	if (trace_handler->runtime_event)
-		trace_handler->runtime_event(&runtime_event, machine, sample);
+	return 0;
 }
 
-static void
-process_sched_fork_event(struct perf_tool *tool __used,
-			 struct event_format *event,
-			 struct perf_sample *sample,
-			 struct machine *machine __used,
-			 struct thread *thread __used)
+static int process_sched_fork_event(struct perf_tool *tool,
+				    struct perf_evsel *evsel,
+				    struct perf_sample *sample,
+				    struct machine *machine __maybe_unused)
 {
-	void *data = sample->raw_data;
-	struct trace_fork_event fork_event;
-
-	FILL_COMMON_FIELDS(fork_event, event, data);
+	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
 
-	FILL_ARRAY(fork_event, parent_comm, event, data);
-	FILL_FIELD(fork_event, parent_pid, event, data);
-	FILL_ARRAY(fork_event, child_comm, event, data);
-	FILL_FIELD(fork_event, child_pid, event, data);
+	if (sched->tp_handler->fork_event)
+		return sched->tp_handler->fork_event(sched, evsel, sample);
 
-	if (trace_handler->fork_event)
-		trace_handler->fork_event(&fork_event, event);
+	return 0;
 }
 
-static void
-process_sched_exit_event(struct perf_tool *tool __used,
-			 struct event_format *event,
-			 struct perf_sample *sample __used,
-			 struct machine *machine __used,
-			 struct thread *thread __used)
+static int process_sched_exit_event(struct perf_tool *tool __maybe_unused,
+				    struct perf_evsel *evsel,
+				    struct perf_sample *sample __maybe_unused,
+				    struct machine *machine __maybe_unused)
 {
-	if (verbose)
-		printf("sched_exit event %p\n", event);
+	pr_debug("sched_exit event %p\n", evsel);
+	return 0;
 }
 
-static void
-process_sched_migrate_task_event(struct perf_tool *tool __used,
-				 struct event_format *event,
-				 struct perf_sample *sample,
-				 struct machine *machine,
-				 struct thread *thread __used)
+static int process_sched_migrate_task_event(struct perf_tool *tool,
+					    struct perf_evsel *evsel,
+					    struct perf_sample *sample,
+					    struct machine *machine)
 {
-	void *data = sample->raw_data;
-	struct trace_migrate_task_event migrate_task_event;
+	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
 
-	FILL_COMMON_FIELDS(migrate_task_event, event, data);
+	if (sched->tp_handler->migrate_task_event)
+		return sched->tp_handler->migrate_task_event(sched, evsel, sample, machine);
 
-	FILL_ARRAY(migrate_task_event, comm, event, data);
-	FILL_FIELD(migrate_task_event, pid, event, data);
-	FILL_FIELD(migrate_task_event, prio, event, data);
-	FILL_FIELD(migrate_task_event, cpu, event, data);
-
-	if (trace_handler->migrate_task_event)
-		trace_handler->migrate_task_event(&migrate_task_event, machine, sample);
+	return 0;
 }
 
-typedef void (*tracepoint_handler)(struct perf_tool *tool, struct event_format *event,
-				   struct perf_sample *sample,
-				   struct machine *machine,
-				   struct thread *thread);
+typedef int (*tracepoint_handler)(struct perf_tool *tool,
+				  struct perf_evsel *evsel,
+				  struct perf_sample *sample,
+				  struct machine *machine);
 
-static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __used,
-						 union perf_event *event __used,
+static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_unused,
+						 union perf_event *event __maybe_unused,
 						 struct perf_sample *sample,
 						 struct perf_evsel *evsel,
 						 struct machine *machine)
 {
 	struct thread *thread = machine__findnew_thread(machine, sample->pid);
+	int err = 0;
 
 	if (thread == NULL) {
 		pr_debug("problem processing %s event, skipping it.\n",
@@ -1571,23 +1440,15 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __used,
 
 	if (evsel->handler.func != NULL) {
 		tracepoint_handler f = evsel->handler.func;
-		f(tool, evsel->tp_format, sample, machine, thread);
+		err = f(tool, evsel, sample, machine);
 	}
 
-	return 0;
+	return err;
 }
 
-static struct perf_tool perf_sched = {
-	.sample		 = perf_sched__process_tracepoint_sample,
-	.comm		 = perf_event__process_comm,
-	.lost		 = perf_event__process_lost,
-	.fork		 = perf_event__process_task,
-	.ordered_samples = true,
-};
-
-static void read_events(bool destroy, struct perf_session **psession)
+static int perf_sched__read_events(struct perf_sched *sched, bool destroy,
+				   struct perf_session **psession)
 {
-	int err = -EINVAL;
 	const struct perf_evsel_str_handler handlers[] = {
 		{ "sched:sched_switch",	      process_sched_switch_event, },
 		{ "sched:sched_stat_runtime", process_sched_runtime_event, },
@@ -1599,21 +1460,25 @@ static void read_events(bool destroy, struct perf_session **psession)
 	};
 	struct perf_session *session;
 
-	session = perf_session__new(input_name, O_RDONLY, 0, false, &perf_sched);
-	if (session == NULL)
-		die("No Memory");
+	session = perf_session__new(sched->input_name, O_RDONLY, 0, false, &sched->tool);
+	if (session == NULL) {
+		pr_debug("No Memory for session\n");
+		return -1;
+	}
 
-	err = perf_session__set_tracepoints_handlers(session, handlers);
-	assert(err == 0);
+	if (perf_session__set_tracepoints_handlers(session, handlers))
+		goto out_delete;
 
 	if (perf_session__has_traces(session, "record -R")) {
-		err = perf_session__process_events(session, &perf_sched);
-		if (err)
-			die("Failed to process events, error %d", err);
+		int err = perf_session__process_events(session, &sched->tool);
+		if (err) {
+			pr_err("Failed to process events, error %d", err);
+			goto out_delete;
+		}
 
-		nr_events      = session->hists.stats.nr_events[0];
-		nr_lost_events = session->hists.stats.total_lost;
-		nr_lost_chunks = session->hists.stats.nr_events[PERF_RECORD_LOST];
+		sched->nr_events      = session->hists.stats.nr_events[0];
+		sched->nr_lost_events = session->hists.stats.total_lost;
+		sched->nr_lost_chunks = session->hists.stats.nr_events[PERF_RECORD_LOST];
 	}
 
 	if (destroy)
@@ -1621,208 +1486,166 @@ static void read_events(bool destroy, struct perf_session **psession)
 
 	if (psession)
 		*psession = session;
+
+	return 0;
+
+out_delete:
+	perf_session__delete(session);
+	return -1;
 }
 
-static void print_bad_events(void)
+static void print_bad_events(struct perf_sched *sched)
 {
-	if (nr_unordered_timestamps && nr_timestamps) {
+	if (sched->nr_unordered_timestamps && sched->nr_timestamps) {
 		printf("  INFO: %.3f%% unordered timestamps (%ld out of %ld)\n",
-			(double)nr_unordered_timestamps/(double)nr_timestamps*100.0,
-			nr_unordered_timestamps, nr_timestamps);
+			(double)sched->nr_unordered_timestamps/(double)sched->nr_timestamps*100.0,
+			sched->nr_unordered_timestamps, sched->nr_timestamps);
 	}
-	if (nr_lost_events && nr_events) {
+	if (sched->nr_lost_events && sched->nr_events) {
 		printf("  INFO: %.3f%% lost events (%ld out of %ld, in %ld chunks)\n",
-			(double)nr_lost_events/(double)nr_events*100.0,
-			nr_lost_events, nr_events, nr_lost_chunks);
+			(double)sched->nr_lost_events/(double)sched->nr_events * 100.0,
+			sched->nr_lost_events, sched->nr_events, sched->nr_lost_chunks);
 	}
-	if (nr_state_machine_bugs && nr_timestamps) {
+	if (sched->nr_state_machine_bugs && sched->nr_timestamps) {
 		printf("  INFO: %.3f%% state machine bugs (%ld out of %ld)",
-			(double)nr_state_machine_bugs/(double)nr_timestamps*100.0,
-			nr_state_machine_bugs, nr_timestamps);
-		if (nr_lost_events)
+			(double)sched->nr_state_machine_bugs/(double)sched->nr_timestamps*100.0,
+			sched->nr_state_machine_bugs, sched->nr_timestamps);
+		if (sched->nr_lost_events)
 			printf(" (due to lost events?)");
 		printf("\n");
 	}
-	if (nr_context_switch_bugs && nr_timestamps) {
+	if (sched->nr_context_switch_bugs && sched->nr_timestamps) {
 		printf("  INFO: %.3f%% context switch bugs (%ld out of %ld)",
-			(double)nr_context_switch_bugs/(double)nr_timestamps*100.0,
-			nr_context_switch_bugs, nr_timestamps);
-		if (nr_lost_events)
+			(double)sched->nr_context_switch_bugs/(double)sched->nr_timestamps*100.0,
+			sched->nr_context_switch_bugs, sched->nr_timestamps);
+		if (sched->nr_lost_events)
 			printf(" (due to lost events?)");
 		printf("\n");
 	}
 }
 
-static void __cmd_lat(void)
+static int perf_sched__lat(struct perf_sched *sched)
 {
 	struct rb_node *next;
 	struct perf_session *session;
 
 	setup_pager();
-	read_events(false, &session);
-	sort_lat();
+	if (perf_sched__read_events(sched, false, &session))
+		return -1;
+	perf_sched__sort_lat(sched);
 
 	printf("\n ---------------------------------------------------------------------------------------------------------------\n");
 	printf("  Task                  |   Runtime ms  | Switches | Average delay ms | Maximum delay ms | Maximum delay at     |\n");
 	printf(" ---------------------------------------------------------------------------------------------------------------\n");
 
-	next = rb_first(&sorted_atom_root);
+	next = rb_first(&sched->sorted_atom_root);
 
 	while (next) {
 		struct work_atoms *work_list;
 
 		work_list = rb_entry(next, struct work_atoms, node);
-		output_lat_thread(work_list);
+		output_lat_thread(sched, work_list);
 		next = rb_next(next);
 	}
 
 	printf(" -----------------------------------------------------------------------------------------\n");
 	printf("  TOTAL:                |%11.3f ms |%9" PRIu64 " |\n",
-		(double)all_runtime/1e6, all_count);
+		(double)sched->all_runtime / 1e6, sched->all_count);
 
 	printf(" ---------------------------------------------------\n");
 
-	print_bad_events();
+	print_bad_events(sched);
 	printf("\n");
 
 	perf_session__delete(session);
+	return 0;
 }
 
-static struct trace_sched_handler map_ops  = {
-	.wakeup_event		= NULL,
-	.switch_event		= map_switch_event,
-	.runtime_event		= NULL,
-	.fork_event		= NULL,
-};
-
-static void __cmd_map(void)
+static int perf_sched__map(struct perf_sched *sched)
 {
-	max_cpu = sysconf(_SC_NPROCESSORS_CONF);
+	sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF);
 
 	setup_pager();
-	read_events(true, NULL);
-	print_bad_events();
+	if (perf_sched__read_events(sched, true, NULL))
+		return -1;
+	print_bad_events(sched);
+	return 0;
 }
 
-static void __cmd_replay(void)
+static int perf_sched__replay(struct perf_sched *sched)
 {
 	unsigned long i;
 
-	calibrate_run_measurement_overhead();
-	calibrate_sleep_measurement_overhead();
+	calibrate_run_measurement_overhead(sched);
+	calibrate_sleep_measurement_overhead(sched);
 
-	test_calibrations();
+	test_calibrations(sched);
 
-	read_events(true, NULL);
+	if (perf_sched__read_events(sched, true, NULL))
+		return -1;
 
-	printf("nr_run_events:        %ld\n", nr_run_events);
-	printf("nr_sleep_events:      %ld\n", nr_sleep_events);
-	printf("nr_wakeup_events:     %ld\n", nr_wakeup_events);
+	printf("nr_run_events:        %ld\n", sched->nr_run_events);
+	printf("nr_sleep_events:      %ld\n", sched->nr_sleep_events);
+	printf("nr_wakeup_events:     %ld\n", sched->nr_wakeup_events);
 
-	if (targetless_wakeups)
-		printf("target-less wakeups:  %ld\n", targetless_wakeups);
-	if (multitarget_wakeups)
-		printf("multi-target wakeups: %ld\n", multitarget_wakeups);
-	if (nr_run_events_optimized)
+	if (sched->targetless_wakeups)
+		printf("target-less wakeups:  %ld\n", sched->targetless_wakeups);
+	if (sched->multitarget_wakeups)
+		printf("multi-target wakeups: %ld\n", sched->multitarget_wakeups);
+	if (sched->nr_run_events_optimized)
 		printf("run atoms optimized: %ld\n",
-			nr_run_events_optimized);
+			sched->nr_run_events_optimized);
 
-	print_task_traces();
-	add_cross_task_wakeups();
+	print_task_traces(sched);
+	add_cross_task_wakeups(sched);
 
-	create_tasks();
+	create_tasks(sched);
 	printf("------------------------------------------------------------\n");
-	for (i = 0; i < replay_repeat; i++)
-		run_one_test();
-}
-
+	for (i = 0; i < sched->replay_repeat; i++)
+		run_one_test(sched);
 
-static const char * const sched_usage[] = {
-	"perf sched [<options>] {record|latency|map|replay|script}",
-	NULL
-};
-
-static const struct option sched_options[] = {
-	OPT_STRING('i', "input", &input_name, "file",
-		    "input file name"),
-	OPT_INCR('v', "verbose", &verbose,
-		    "be more verbose (show symbol address, etc)"),
-	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
-		    "dump raw trace in ASCII"),
-	OPT_END()
-};
-
-static const char * const latency_usage[] = {
-	"perf sched latency [<options>]",
-	NULL
-};
-
-static const struct option latency_options[] = {
-	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
-		   "sort by key(s): runtime, switch, avg, max"),
-	OPT_INCR('v', "verbose", &verbose,
-		    "be more verbose (show symbol address, etc)"),
-	OPT_INTEGER('C', "CPU", &profile_cpu,
-		    "CPU to profile on"),
-	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
-		    "dump raw trace in ASCII"),
-	OPT_END()
-};
-
-static const char * const replay_usage[] = {
-	"perf sched replay [<options>]",
-	NULL
-};
-
-static const struct option replay_options[] = {
-	OPT_UINTEGER('r', "repeat", &replay_repeat,
-		     "repeat the workload replay N times (-1: infinite)"),
-	OPT_INCR('v', "verbose", &verbose,
-		    "be more verbose (show symbol address, etc)"),
-	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
-		    "dump raw trace in ASCII"),
-	OPT_END()
-};
+	return 0;
+}
 
-static void setup_sorting(void)
+static void setup_sorting(struct perf_sched *sched, const struct option *options,
+			  const char * const usage_msg[])
 {
-	char *tmp, *tok, *str = strdup(sort_order);
+	char *tmp, *tok, *str = strdup(sched->sort_order);
 
 	for (tok = strtok_r(str, ", ", &tmp);
 			tok; tok = strtok_r(NULL, ", ", &tmp)) {
-		if (sort_dimension__add(tok, &sort_list) < 0) {
+		if (sort_dimension__add(tok, &sched->sort_list) < 0) {
 			error("Unknown --sort key: `%s'", tok);
-			usage_with_options(latency_usage, latency_options);
+			usage_with_options(usage_msg, options);
 		}
 	}
 
 	free(str);
 
-	sort_dimension__add("pid", &cmp_pid);
+	sort_dimension__add("pid", &sched->cmp_pid);
 }
 
-static const char *record_args[] = {
-	"record",
-	"-a",
-	"-R",
-	"-f",
-	"-m", "1024",
-	"-c", "1",
-	"-e", "sched:sched_switch",
-	"-e", "sched:sched_stat_wait",
-	"-e", "sched:sched_stat_sleep",
-	"-e", "sched:sched_stat_iowait",
-	"-e", "sched:sched_stat_runtime",
-	"-e", "sched:sched_process_exit",
-	"-e", "sched:sched_process_fork",
-	"-e", "sched:sched_wakeup",
-	"-e", "sched:sched_migrate_task",
-};
-
 static int __cmd_record(int argc, const char **argv)
 {
 	unsigned int rec_argc, i, j;
 	const char **rec_argv;
+	const char * const record_args[] = {
+		"record",
+		"-a",
+		"-R",
+		"-f",
+		"-m", "1024",
+		"-c", "1",
+		"-e", "sched:sched_switch",
+		"-e", "sched:sched_stat_wait",
+		"-e", "sched:sched_stat_sleep",
+		"-e", "sched:sched_stat_iowait",
+		"-e", "sched:sched_stat_runtime",
+		"-e", "sched:sched_process_exit",
+		"-e", "sched:sched_process_fork",
+		"-e", "sched:sched_wakeup",
+		"-e", "sched:sched_migrate_task",
+	};
 
 	rec_argc = ARRAY_SIZE(record_args) + argc - 1;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
@@ -1841,8 +1664,85 @@ static int __cmd_record(int argc, const char **argv)
 	return cmd_record(i, rec_argv, NULL);
 }
 
-int cmd_sched(int argc, const char **argv, const char *prefix __used)
+int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 {
+	const char default_sort_order[] = "avg, max, switch, runtime";
+	struct perf_sched sched = {
+		.tool = {
+			.sample		 = perf_sched__process_tracepoint_sample,
+			.comm		 = perf_event__process_comm,
+			.lost		 = perf_event__process_lost,
+			.fork		 = perf_event__process_task,
+			.ordered_samples = true,
+		},
+		.cmp_pid	      = LIST_HEAD_INIT(sched.cmp_pid),
+		.sort_list	      = LIST_HEAD_INIT(sched.sort_list),
+		.start_work_mutex     = PTHREAD_MUTEX_INITIALIZER,
+		.work_done_wait_mutex = PTHREAD_MUTEX_INITIALIZER,
+		.curr_pid	      = { [0 ... MAX_CPUS - 1] = -1 },
+		.sort_order	      = default_sort_order,
+		.replay_repeat	      = 10,
+		.profile_cpu	      = -1,
+		.next_shortname1      = 'A',
+		.next_shortname2      = '0',
+	};
+	const struct option latency_options[] = {
+	OPT_STRING('s', "sort", &sched.sort_order, "key[,key2...]",
+		   "sort by key(s): runtime, switch, avg, max"),
+	OPT_INCR('v', "verbose", &verbose,
+		    "be more verbose (show symbol address, etc)"),
+	OPT_INTEGER('C', "CPU", &sched.profile_cpu,
+		    "CPU to profile on"),
+	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
+		    "dump raw trace in ASCII"),
+	OPT_END()
+	};
+	const struct option replay_options[] = {
+	OPT_UINTEGER('r', "repeat", &sched.replay_repeat,
+		     "repeat the workload replay N times (-1: infinite)"),
+	OPT_INCR('v', "verbose", &verbose,
+		    "be more verbose (show symbol address, etc)"),
+	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
+		    "dump raw trace in ASCII"),
+	OPT_END()
+	};
+	const struct option sched_options[] = {
+	OPT_STRING('i', "input", &sched.input_name, "file",
+		    "input file name"),
+	OPT_INCR('v', "verbose", &verbose,
+		    "be more verbose (show symbol address, etc)"),
+	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
+		    "dump raw trace in ASCII"),
+	OPT_END()
+	};
+	const char * const latency_usage[] = {
+		"perf sched latency [<options>]",
+		NULL
+	};
+	const char * const replay_usage[] = {
+		"perf sched replay [<options>]",
+		NULL
+	};
+	const char * const sched_usage[] = {
+		"perf sched [<options>] {record|latency|map|replay|script}",
+		NULL
+	};
+	struct trace_sched_handler lat_ops  = {
+		.wakeup_event	    = latency_wakeup_event,
+		.switch_event	    = latency_switch_event,
+		.runtime_event	    = latency_runtime_event,
+		.fork_event	    = latency_fork_event,
+		.migrate_task_event = latency_migrate_task_event,
+	};
+	struct trace_sched_handler map_ops  = {
+		.switch_event	    = map_switch_event,
+	};
+	struct trace_sched_handler replay_ops  = {
+		.wakeup_event	    = replay_wakeup_event,
+		.switch_event	    = replay_switch_event,
+		.fork_event	    = replay_fork_event,
+	};
+
 	argc = parse_options(argc, argv, sched_options, sched_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 	if (!argc)
@@ -1858,26 +1758,26 @@ int cmd_sched(int argc, const char **argv, const char *prefix __used)
 	if (!strncmp(argv[0], "rec", 3)) {
 		return __cmd_record(argc, argv);
 	} else if (!strncmp(argv[0], "lat", 3)) {
-		trace_handler = &lat_ops;
+		sched.tp_handler = &lat_ops;
 		if (argc > 1) {
 			argc = parse_options(argc, argv, latency_options, latency_usage, 0);
 			if (argc)
 				usage_with_options(latency_usage, latency_options);
 		}
-		setup_sorting();
-		__cmd_lat();
+		setup_sorting(&sched, latency_options, latency_usage);
+		return perf_sched__lat(&sched);
 	} else if (!strcmp(argv[0], "map")) {
-		trace_handler = &map_ops;
-		setup_sorting();
-		__cmd_map();
+		sched.tp_handler = &map_ops;
+		setup_sorting(&sched, latency_options, latency_usage);
+		return perf_sched__map(&sched);
 	} else if (!strncmp(argv[0], "rep", 3)) {
-		trace_handler = &replay_ops;
+		sched.tp_handler = &replay_ops;
 		if (argc) {
 			argc = parse_options(argc, argv, replay_options, replay_usage, 0);
 			if (argc)
 				usage_with_options(replay_usage, replay_options);
 		}
-		__cmd_replay();
+		return perf_sched__replay(&sched);
 	} else {
 		usage_with_options(sched_usage, sched_options);
 	}
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c350cfee3157..6d98a83d5a60 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -430,9 +430,9 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 	printf("\n");
 }
 
-static int default_start_script(const char *script __unused,
-				int argc __unused,
-				const char **argv __unused)
+static int default_start_script(const char *script __maybe_unused,
+				int argc __maybe_unused,
+				const char **argv __maybe_unused)
 {
 	return 0;
 }
@@ -442,8 +442,8 @@ static int default_stop_script(void)
 	return 0;
 }
 
-static int default_generate_script(struct pevent *pevent __unused,
-				   const char *outfile __unused)
+static int default_generate_script(struct pevent *pevent __maybe_unused,
+				   const char *outfile __maybe_unused)
 {
 	return 0;
 }
@@ -474,7 +474,7 @@ static int cleanup_scripting(void)
 
 static const char *input_name;
 
-static int process_sample_event(struct perf_tool *tool __used,
+static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				union perf_event *event,
 				struct perf_sample *sample,
 				struct perf_evsel *evsel,
@@ -534,7 +534,7 @@ static struct perf_tool perf_script = {
 
 extern volatile int session_done;
 
-static void sig_handler(int sig __unused)
+static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
 }
@@ -644,8 +644,8 @@ static void list_available_languages(void)
 	fprintf(stderr, "\n");
 }
 
-static int parse_scriptname(const struct option *opt __used,
-			    const char *str, int unset __used)
+static int parse_scriptname(const struct option *opt __maybe_unused,
+			    const char *str, int unset __maybe_unused)
 {
 	char spec[PATH_MAX];
 	const char *script, *ext;
@@ -690,8 +690,8 @@ static int parse_scriptname(const struct option *opt __used,
 	return 0;
 }
 
-static int parse_output_fields(const struct option *opt __used,
-			    const char *arg, int unset __used)
+static int parse_output_fields(const struct option *opt __maybe_unused,
+			    const char *arg, int unset __maybe_unused)
 {
 	char *tok;
 	int i, imax = sizeof(all_output_options) / sizeof(struct output_option);
@@ -982,8 +982,9 @@ static char *get_script_root(struct dirent *script_dirent, const char *suffix)
 	return script_root;
 }
 
-static int list_available_scripts(const struct option *opt __used,
-				  const char *s __used, int unset __used)
+static int list_available_scripts(const struct option *opt __maybe_unused,
+				  const char *s __maybe_unused,
+				  int unset __maybe_unused)
 {
 	struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
 	char scripts_path[MAXPATHLEN];
@@ -1172,7 +1173,7 @@ static int have_cmd(int argc, const char **argv)
 	return 0;
 }
 
-int cmd_script(int argc, const char **argv, const char *prefix __used)
+int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	char *rec_script_path = NULL;
 	char *rep_script_path = NULL;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 02f49eba677f..dab347d7b010 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -417,7 +417,7 @@ static int read_counter(struct perf_evsel *counter)
 	return 0;
 }
 
-static int run_perf_stat(int argc __used, const char **argv)
+static int run_perf_stat(int argc __maybe_unused, const char **argv)
 {
 	unsigned long long t0, t1;
 	struct perf_evsel *counter, *first;
@@ -634,7 +634,9 @@ static const char *get_ratio_color(enum grc_type type, double ratio)
 	return color;
 }
 
-static void print_stalled_cycles_frontend(int cpu, struct perf_evsel *evsel __used, double avg)
+static void print_stalled_cycles_frontend(int cpu,
+					  struct perf_evsel *evsel
+					  __maybe_unused, double avg)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -651,7 +653,9 @@ static void print_stalled_cycles_frontend(int cpu, struct perf_evsel *evsel __us
 	fprintf(output, " frontend cycles idle   ");
 }
 
-static void print_stalled_cycles_backend(int cpu, struct perf_evsel *evsel __used, double avg)
+static void print_stalled_cycles_backend(int cpu,
+					 struct perf_evsel *evsel
+					 __maybe_unused, double avg)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -668,7 +672,9 @@ static void print_stalled_cycles_backend(int cpu, struct perf_evsel *evsel __use
 	fprintf(output, " backend  cycles idle   ");
 }
 
-static void print_branch_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+static void print_branch_misses(int cpu,
+				struct perf_evsel *evsel __maybe_unused,
+				double avg)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -685,7 +691,9 @@ static void print_branch_misses(int cpu, struct perf_evsel *evsel __used, double
 	fprintf(output, " of all branches        ");
 }
 
-static void print_l1_dcache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+static void print_l1_dcache_misses(int cpu,
+				   struct perf_evsel *evsel __maybe_unused,
+				   double avg)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -702,7 +710,9 @@ static void print_l1_dcache_misses(int cpu, struct perf_evsel *evsel __used, dou
 	fprintf(output, " of all L1-dcache hits  ");
 }
 
-static void print_l1_icache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+static void print_l1_icache_misses(int cpu,
+				   struct perf_evsel *evsel __maybe_unused,
+				   double avg)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -719,7 +729,9 @@ static void print_l1_icache_misses(int cpu, struct perf_evsel *evsel __used, dou
 	fprintf(output, " of all L1-icache hits  ");
 }
 
-static void print_dtlb_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+static void print_dtlb_cache_misses(int cpu,
+				    struct perf_evsel *evsel __maybe_unused,
+				    double avg)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -736,7 +748,9 @@ static void print_dtlb_cache_misses(int cpu, struct perf_evsel *evsel __used, do
 	fprintf(output, " of all dTLB cache hits ");
 }
 
-static void print_itlb_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+static void print_itlb_cache_misses(int cpu,
+				    struct perf_evsel *evsel __maybe_unused,
+				    double avg)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -753,7 +767,9 @@ static void print_itlb_cache_misses(int cpu, struct perf_evsel *evsel __used, do
 	fprintf(output, " of all iTLB cache hits ");
 }
 
-static void print_ll_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+static void print_ll_cache_misses(int cpu,
+				  struct perf_evsel *evsel __maybe_unused,
+				  double avg)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -1059,8 +1075,8 @@ static const char * const stat_usage[] = {
 	NULL
 };
 
-static int stat__set_big_num(const struct option *opt __used,
-			     const char *s __used, int unset)
+static int stat__set_big_num(const struct option *opt __maybe_unused,
+			     const char *s __maybe_unused, int unset)
 {
 	big_num_opt = unset ? 0 : 1;
 	return 0;
@@ -1154,7 +1170,7 @@ static int add_default_attributes(void)
 	return perf_evlist__add_default_attrs(evsel_list, very_very_detailed_attrs);
 }
 
-int cmd_stat(int argc, const char **argv, const char *prefix __used)
+int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	struct perf_evsel *pos;
 	int status = -ENOMEM;
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index cf33e5081c36..d33143efefce 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -18,7 +18,8 @@
 
 #include <sys/mman.h>
 
-static int vmlinux_matches_kallsyms_filter(struct map *map __used, struct symbol *sym)
+static int vmlinux_matches_kallsyms_filter(struct map *map __maybe_unused,
+					   struct symbol *sym)
 {
 	bool *visited = symbol__priv(sym);
 	*visited = true;
@@ -996,7 +997,9 @@ static u64 mmap_read_self(void *addr)
 /*
  * If the RDPMC instruction faults then signal this back to the test parent task:
  */
-static void segfault_handler(int sig __used, siginfo_t *info __used, void *uc __used)
+static void segfault_handler(int sig __maybe_unused,
+			     siginfo_t *info __maybe_unused,
+			     void *uc __maybe_unused)
 {
 	exit(-1);
 }
@@ -1023,14 +1026,16 @@ static int __test__rdpmc(void)
 
 	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
 	if (fd < 0) {
-		die("Error: sys_perf_event_open() syscall returned "
-		    "with %d (%s)\n", fd, strerror(errno));
+		pr_debug("Error: sys_perf_event_open() syscall returned "
+			 "with %d (%s)\n", fd, strerror(errno));
+		return -1;
 	}
 
 	addr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0);
 	if (addr == (void *)(-1)) {
-		die("Error: mmap() syscall returned "
-		    "with (%s)\n", strerror(errno));
+		pr_debug("Error: mmap() syscall returned with (%s)\n",
+			 strerror(errno));
+		goto out_close;
 	}
 
 	for (n = 0; n < 6; n++) {
@@ -1051,9 +1056,9 @@ static int __test__rdpmc(void)
 	}
 
 	munmap(addr, page_size);
-	close(fd);
-
 	pr_debug("   ");
+out_close:
+	close(fd);
 
 	if (!delta_sum)
 		return -1;
@@ -1313,7 +1318,7 @@ static int perf_test__list(int argc, const char **argv)
 	return 0;
 }
 
-int cmd_test(int argc, const char **argv, const char *prefix __used)
+int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	const char * const test_usage[] = {
 	"perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]",
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 3b75b2e21ea5..55a3a6c6b9e7 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -275,28 +275,28 @@ static int cpus_cstate_state[MAX_CPUS];
 static u64 cpus_pstate_start_times[MAX_CPUS];
 static u64 cpus_pstate_state[MAX_CPUS];
 
-static int process_comm_event(struct perf_tool *tool __used,
+static int process_comm_event(struct perf_tool *tool __maybe_unused,
 			      union perf_event *event,
-			      struct perf_sample *sample __used,
-			      struct machine *machine __used)
+			      struct perf_sample *sample __maybe_unused,
+			      struct machine *machine __maybe_unused)
 {
 	pid_set_comm(event->comm.tid, event->comm.comm);
 	return 0;
 }
 
-static int process_fork_event(struct perf_tool *tool __used,
+static int process_fork_event(struct perf_tool *tool __maybe_unused,
 			      union perf_event *event,
-			      struct perf_sample *sample __used,
-			      struct machine *machine __used)
+			      struct perf_sample *sample __maybe_unused,
+			      struct machine *machine __maybe_unused)
 {
 	pid_fork(event->fork.pid, event->fork.ppid, event->fork.time);
 	return 0;
 }
 
-static int process_exit_event(struct perf_tool *tool __used,
+static int process_exit_event(struct perf_tool *tool __maybe_unused,
 			      union perf_event *event,
-			      struct perf_sample *sample __used,
-			      struct machine *machine __used)
+			      struct perf_sample *sample __maybe_unused,
+			      struct machine *machine __maybe_unused)
 {
 	pid_exit(event->fork.pid, event->fork.time);
 	return 0;
@@ -491,11 +491,11 @@ static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te)
 }
 
 
-static int process_sample_event(struct perf_tool *tool __used,
-				union perf_event *event __used,
+static int process_sample_event(struct perf_tool *tool __maybe_unused,
+				union perf_event *event __maybe_unused,
 				struct perf_sample *sample,
 				struct perf_evsel *evsel,
-				struct machine *machine __used)
+				struct machine *machine __maybe_unused)
 {
 	struct trace_entry *te;
 
@@ -1081,7 +1081,8 @@ static int __cmd_record(int argc, const char **argv)
 }
 
 static int
-parse_process(const struct option *opt __used, const char *arg, int __used unset)
+parse_process(const struct option *opt __maybe_unused, const char *arg,
+	      int __maybe_unused unset)
 {
 	if (arg)
 		add_process_filter(arg);
@@ -1106,7 +1107,8 @@ static const struct option options[] = {
 };
 
 
-int cmd_timechart(int argc, const char **argv, const char *prefix __used)
+int cmd_timechart(int argc, const char **argv,
+		  const char *prefix __maybe_unused)
 {
 	argc = parse_options(argc, argv, options, timechart_usage,
 			PARSE_OPT_STOP_AT_NON_OPTION);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 0513aaa659f9..5550754c05f2 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -95,7 +95,8 @@ static void perf_top__update_print_entries(struct perf_top *top)
 		top->print_entries -= 9;
 }
 
-static void perf_top__sig_winch(int sig __used, siginfo_t *info __used, void *arg)
+static void perf_top__sig_winch(int sig __maybe_unused,
+				siginfo_t *info __maybe_unused, void *arg)
 {
 	struct perf_top *top = arg;
 
@@ -663,7 +664,7 @@ static const char *skip_symbols[] = {
 	NULL
 };
 
-static int symbol_filter(struct map *map __used, struct symbol *sym)
+static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
 {
 	const char *name = sym->name;
 	int i;
@@ -1163,7 +1164,7 @@ static const char * const top_usage[] = {
 	NULL
 };
 
-int cmd_top(int argc, const char **argv, const char *prefix __used)
+int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	struct perf_evsel *pos;
 	int status;
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 1818a531f1d3..4aeb7d5df939 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -269,7 +269,7 @@ int ui_browser__show(struct ui_browser *browser, const char *title,
 	return err ? 0 : -1;
 }
 
-void ui_browser__hide(struct ui_browser *browser __used)
+void ui_browser__hide(struct ui_browser *browser __maybe_unused)
 {
 	pthread_mutex_lock(&ui__lock);
 	ui_helpline__pop();
@@ -518,7 +518,7 @@ static struct ui_browser__colorset {
 
 
 static int ui_browser__color_config(const char *var, const char *value,
-				    void *data __used)
+				    void *data __maybe_unused)
 {
 	char *fg = NULL, *bg;
 	int i;
@@ -602,7 +602,8 @@ void __ui_browser__vline(struct ui_browser *browser, unsigned int column,
 	SLsmg_set_char_set(0);
 }
 
-void ui_browser__write_graph(struct ui_browser *browser __used, int graph)
+void ui_browser__write_graph(struct ui_browser *browser __maybe_unused,
+			     int graph)
 {
 	SLsmg_set_char_set(1);
 	SLsmg_write_char(graph);
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 67a2703e666a..8f8cd2d73b3b 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -54,7 +54,8 @@ static inline struct browser_disasm_line *disasm_line__browser(struct disasm_lin
 	return (struct browser_disasm_line *)(dl + 1);
 }
 
-static bool disasm_line__filter(struct ui_browser *browser __used, void *entry)
+static bool disasm_line__filter(struct ui_browser *browser __maybe_unused,
+				void *entry)
 {
 	if (annotate_browser__opts.hide_src_code) {
 		struct disasm_line *dl = list_entry(entry, struct disasm_line, node);
@@ -928,7 +929,8 @@ static int annotate_config__cmp(const void *name, const void *cfgp)
 	return strcmp(name, cfg->name);
 }
 
-static int annotate__config(const char *var, const char *value, void *data __used)
+static int annotate__config(const char *var, const char *value,
+			    void *data __maybe_unused)
 {
 	struct annotate__config *cfg;
 	const char *name;
diff --git a/tools/perf/ui/gtk/browser.c b/tools/perf/ui/gtk/browser.c
index 3c16ab50e0f8..55acba6e0df4 100644
--- a/tools/perf/ui/gtk/browser.c
+++ b/tools/perf/ui/gtk/browser.c
@@ -237,8 +237,9 @@ static GtkWidget *perf_gtk__setup_statusbar(void)
 
 int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 				  const char *help,
-				  void (*timer) (void *arg)__used,
-				  void *arg __used, int delay_secs __used)
+				  void (*timer) (void *arg)__maybe_unused,
+				  void *arg __maybe_unused,
+				  int delay_secs __maybe_unused)
 {
 	struct perf_evsel *pos;
 	GtkWidget *vbox;
diff --git a/tools/perf/ui/gtk/setup.c b/tools/perf/ui/gtk/setup.c
index 26429437e19e..3c4c6ef78283 100644
--- a/tools/perf/ui/gtk/setup.c
+++ b/tools/perf/ui/gtk/setup.c
@@ -12,7 +12,7 @@ int perf_gtk__init(void)
 	return gtk_init_check(NULL, NULL) ? 0 : -1;
 }
 
-void perf_gtk__exit(bool wait_for_ok __used)
+void perf_gtk__exit(bool wait_for_ok __maybe_unused)
 {
 	if (!perf_gtk__is_active_context(pgctx))
 		return;
diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c
index b8efb966f94c..8aada5b3c04c 100644
--- a/tools/perf/ui/gtk/util.c
+++ b/tools/perf/ui/gtk/util.c
@@ -117,8 +117,8 @@ struct perf_error_ops perf_gtk_eops = {
  *        For now, just add stubs for NO_NEWT=1 build.
  */
 #ifdef NO_NEWT_SUPPORT
-void ui_progress__update(u64 curr __used, u64 total __used,
-			 const char *title __used)
+void ui_progress__update(u64 curr __maybe_unused, u64 total __maybe_unused,
+			 const char *title __maybe_unused)
 {
 }
 #endif
diff --git a/tools/perf/ui/helpline.c b/tools/perf/ui/helpline.c
index 78ba28ac7a2c..a49bcf3c190b 100644
--- a/tools/perf/ui/helpline.c
+++ b/tools/perf/ui/helpline.c
@@ -12,7 +12,7 @@ static void nop_helpline__pop(void)
 {
 }
 
-static void nop_helpline__push(const char *msg __used)
+static void nop_helpline__push(const char *msg __maybe_unused)
 {
 }
 
diff --git a/tools/perf/ui/helpline.h b/tools/perf/ui/helpline.h
index a2487f93aa48..2b667ee454c3 100644
--- a/tools/perf/ui/helpline.h
+++ b/tools/perf/ui/helpline.h
@@ -24,8 +24,8 @@ void ui_helpline__puts(const char *msg);
 extern char ui_helpline__current[512];
 
 #ifdef NO_NEWT_SUPPORT
-static inline int ui_helpline__show_help(const char *format __used,
-					 va_list ap __used)
+static inline int ui_helpline__show_help(const char *format __maybe_unused,
+					 va_list ap __maybe_unused)
 {
 	return 0;
 }
@@ -35,8 +35,8 @@ int ui_helpline__show_help(const char *format, va_list ap);
 #endif /* NO_NEWT_SUPPORT */
 
 #ifdef NO_GTK2_SUPPORT
-static inline int perf_gtk__show_helpline(const char *format __used,
-					  va_list ap __used)
+static inline int perf_gtk__show_helpline(const char *format __maybe_unused,
+					  va_list ap __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 031b349a3f84..407e855cccb8 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -13,7 +13,7 @@ static int hpp__header_overhead(struct perf_hpp *hpp)
 	return scnprintf(hpp->buf, hpp->size, fmt);
 }
 
-static int hpp__width_overhead(struct perf_hpp *hpp __used)
+static int hpp__width_overhead(struct perf_hpp *hpp __maybe_unused)
 {
 	return 8;
 }
@@ -62,7 +62,7 @@ static int hpp__header_overhead_sys(struct perf_hpp *hpp)
 	return scnprintf(hpp->buf, hpp->size, fmt, "sys");
 }
 
-static int hpp__width_overhead_sys(struct perf_hpp *hpp __used)
+static int hpp__width_overhead_sys(struct perf_hpp *hpp __maybe_unused)
 {
 	return 6;
 }
@@ -88,7 +88,7 @@ static int hpp__header_overhead_us(struct perf_hpp *hpp)
 	return scnprintf(hpp->buf, hpp->size, fmt, "user");
 }
 
-static int hpp__width_overhead_us(struct perf_hpp *hpp __used)
+static int hpp__width_overhead_us(struct perf_hpp *hpp __maybe_unused)
 {
 	return 6;
 }
@@ -112,7 +112,7 @@ static int hpp__header_overhead_guest_sys(struct perf_hpp *hpp)
 	return scnprintf(hpp->buf, hpp->size, "guest sys");
 }
 
-static int hpp__width_overhead_guest_sys(struct perf_hpp *hpp __used)
+static int hpp__width_overhead_guest_sys(struct perf_hpp *hpp __maybe_unused)
 {
 	return 9;
 }
@@ -138,7 +138,7 @@ static int hpp__header_overhead_guest_us(struct perf_hpp *hpp)
 	return scnprintf(hpp->buf, hpp->size, "guest usr");
 }
 
-static int hpp__width_overhead_guest_us(struct perf_hpp *hpp __used)
+static int hpp__width_overhead_guest_us(struct perf_hpp *hpp __maybe_unused)
 {
 	return 9;
 }
@@ -166,7 +166,7 @@ static int hpp__header_samples(struct perf_hpp *hpp)
 	return scnprintf(hpp->buf, hpp->size, fmt, "Samples");
 }
 
-static int hpp__width_samples(struct perf_hpp *hpp __used)
+static int hpp__width_samples(struct perf_hpp *hpp __maybe_unused)
 {
 	return 11;
 }
@@ -185,7 +185,7 @@ static int hpp__header_period(struct perf_hpp *hpp)
 	return scnprintf(hpp->buf, hpp->size, fmt, "Period");
 }
 
-static int hpp__width_period(struct perf_hpp *hpp __used)
+static int hpp__width_period(struct perf_hpp *hpp __maybe_unused)
 {
 	return 12;
 }
@@ -204,7 +204,7 @@ static int hpp__header_delta(struct perf_hpp *hpp)
 	return scnprintf(hpp->buf, hpp->size, fmt, "Delta");
 }
 
-static int hpp__width_delta(struct perf_hpp *hpp __used)
+static int hpp__width_delta(struct perf_hpp *hpp __maybe_unused)
 {
 	return 7;
 }
@@ -238,12 +238,13 @@ static int hpp__header_displ(struct perf_hpp *hpp)
 	return scnprintf(hpp->buf, hpp->size, "Displ.");
 }
 
-static int hpp__width_displ(struct perf_hpp *hpp __used)
+static int hpp__width_displ(struct perf_hpp *hpp __maybe_unused)
 {
 	return 6;
 }
 
-static int hpp__entry_displ(struct perf_hpp *hpp, struct hist_entry *he __used)
+static int hpp__entry_displ(struct perf_hpp *hpp,
+			    struct hist_entry *he __maybe_unused)
 {
 	const char *fmt = symbol_conf.field_sep ? "%s" : "%6.6s";
 	char buf[32] = " ";
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index 4dc0887c04f1..60debb81537a 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -28,7 +28,7 @@ void ui__refresh_dimensions(bool force)
 	}
 }
 
-static void ui__sigwinch(int sig __used)
+static void ui__sigwinch(int sig __maybe_unused)
 {
 	ui__need_resize = 1;
 }
@@ -88,7 +88,7 @@ int ui__getch(int delay_secs)
 	return SLkp_getkey();
 }
 
-static void newt_suspend(void *d __used)
+static void newt_suspend(void *d __maybe_unused)
 {
 	newtSuspend();
 	raise(SIGTSTP);
diff --git a/tools/perf/util/alias.c b/tools/perf/util/alias.c
index b8144e80bb1e..e6d134773d0a 100644
--- a/tools/perf/util/alias.c
+++ b/tools/perf/util/alias.c
@@ -3,7 +3,8 @@
 static const char *alias_key;
 static char *alias_val;
 
-static int alias_lookup_cb(const char *k, const char *v, void *cb __used)
+static int alias_lookup_cb(const char *k, const char *v,
+			   void *cb __maybe_unused)
 {
 	if (!prefixcmp(k, "alias.") && !strcmp(k+6, alias_key)) {
 		if (!v)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 04eafd3939df..f0a910371377 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -313,8 +313,8 @@ static struct ins_ops dec_ops = {
 	.scnprintf = dec__scnprintf,
 };
 
-static int nop__scnprintf(struct ins *ins __used, char *bf, size_t size,
-			  struct ins_operands *ops __used)
+static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size,
+			  struct ins_operands *ops __maybe_unused)
 {
 	return scnprintf(bf, size, "%-6.6s", "nop");
 }
@@ -416,7 +416,7 @@ static struct ins *ins__find(const char *name)
 	return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__cmp);
 }
 
-int symbol__annotate_init(struct map *map __used, struct symbol *sym)
+int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym)
 {
 	struct annotation *notes = symbol__annotation(sym);
 	pthread_mutex_init(&notes->lock, NULL);
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 62a6e7a7365d..9b5b21e7b032 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -126,7 +126,7 @@ int symbol__alloc_hist(struct symbol *sym);
 void symbol__annotate_zero_histograms(struct symbol *sym);
 
 int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize);
-int symbol__annotate_init(struct map *map __used, struct symbol *sym);
+int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym);
 int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx,
 			    bool full_paths, int min_pcnt, int max_lines,
 			    int context);
@@ -139,11 +139,12 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx,
 			 int max_lines);
 
 #ifdef NO_NEWT_SUPPORT
-static inline int symbol__tui_annotate(struct symbol *sym __used,
-				       struct map *map __used,
-				       int evidx __used,
-				       void(*timer)(void *arg) __used,
-				       void *arg __used, int delay_secs __used)
+static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused,
+				       struct map *map __maybe_unused,
+				       int evidx __maybe_unused,
+				       void(*timer)(void *arg) __maybe_unused,
+				       void *arg __maybe_unused,
+				       int delay_secs __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index fd9a5944b627..8e3a740ddbd4 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -16,10 +16,10 @@
 #include "session.h"
 #include "tool.h"
 
-static int build_id__mark_dso_hit(struct perf_tool *tool __used,
+static int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 				  union perf_event *event,
-				  struct perf_sample *sample __used,
-				  struct perf_evsel *evsel __used,
+				  struct perf_sample *sample __maybe_unused,
+				  struct perf_evsel *evsel __maybe_unused,
 				  struct machine *machine)
 {
 	struct addr_location al;
@@ -41,9 +41,10 @@ static int build_id__mark_dso_hit(struct perf_tool *tool __used,
 	return 0;
 }
 
-static int perf_event__exit_del_thread(struct perf_tool *tool __used,
+static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused,
 				       union perf_event *event,
-				       struct perf_sample *sample __used,
+				       struct perf_sample *sample
+				       __maybe_unused,
 				       struct machine *machine)
 {
 	struct thread *thread = machine__findnew_thread(machine, event->fork.tid);
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index cff18c617d13..ab1769426541 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -39,7 +39,7 @@ static inline void setup_browser(bool fallback_to_pager)
 	if (fallback_to_pager)
 		setup_pager();
 }
-static inline void exit_browser(bool wait_for_ok __used) {}
+static inline void exit_browser(bool wait_for_ok __maybe_unused) {}
 #else
 void setup_browser(bool fallback_to_pager);
 void exit_browser(bool wait_for_ok);
@@ -49,7 +49,7 @@ static inline int ui__init(void)
 {
 	return -1;
 }
-static inline void ui__exit(bool wait_for_ok __used) {}
+static inline void ui__exit(bool wait_for_ok __maybe_unused) {}
 #else
 int ui__init(void);
 void ui__exit(bool wait_for_ok);
@@ -60,7 +60,7 @@ static inline int perf_gtk__init(void)
 {
 	return -1;
 }
-static inline void perf_gtk__exit(bool wait_for_ok __used) {}
+static inline void perf_gtk__exit(bool wait_for_ok __maybe_unused) {}
 #else
 int perf_gtk__init(void);
 void perf_gtk__exit(bool wait_for_ok);
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 3a6bff47614f..d3b3f5d82137 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -93,7 +93,7 @@ __sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node,
  */
 static void
 sort_chain_flat(struct rb_root *rb_root, struct callchain_root *root,
-		u64 min_hit, struct callchain_param *param __used)
+		u64 min_hit, struct callchain_param *param __maybe_unused)
 {
 	__sort_chain_flat(rb_root, &root->node, min_hit);
 }
@@ -115,7 +115,7 @@ static void __sort_chain_graph_abs(struct callchain_node *node,
 
 static void
 sort_chain_graph_abs(struct rb_root *rb_root, struct callchain_root *chain_root,
-		     u64 min_hit, struct callchain_param *param __used)
+		     u64 min_hit, struct callchain_param *param __maybe_unused)
 {
 	__sort_chain_graph_abs(&chain_root->node, min_hit);
 	rb_root->rb_node = chain_root->node.rb_root.rb_node;
@@ -140,7 +140,7 @@ static void __sort_chain_graph_rel(struct callchain_node *node,
 
 static void
 sort_chain_graph_rel(struct rb_root *rb_root, struct callchain_root *chain_root,
-		     u64 min_hit __used, struct callchain_param *param)
+		     u64 min_hit __maybe_unused, struct callchain_param *param)
 {
 	__sort_chain_graph_rel(&chain_root->node, param->min_percent / 100.0);
 	rb_root->rb_node = chain_root->node.rb_root.rb_node;
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index dbe2f16b1a1a..96bbda1ddb83 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -138,8 +138,8 @@ void close_cgroup(struct cgroup_sel *cgrp)
 	}
 }
 
-int parse_cgroups(const struct option *opt __used, const char *str,
-		  int unset __used)
+int parse_cgroups(const struct option *opt __maybe_unused, const char *str,
+		  int unset __maybe_unused)
 {
 	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
 	const char *p, *e, *eos = str + strlen(str);
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 6faa3a18bfbd..3e0fdd369ccb 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -342,13 +342,15 @@ const char *perf_config_dirname(const char *name, const char *value)
 	return value;
 }
 
-static int perf_default_core_config(const char *var __used, const char *value __used)
+static int perf_default_core_config(const char *var __maybe_unused,
+				    const char *value __maybe_unused)
 {
 	/* Add other config variables here. */
 	return 0;
 }
 
-int perf_default_config(const char *var, const char *value, void *dummy __used)
+int perf_default_config(const char *var, const char *value,
+			void *dummy __maybe_unused)
 {
 	if (!prefixcmp(var, "core."))
 		return perf_default_core_config(var, value);
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 05e660cbf7e2..bb2e7d1007ab 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -16,19 +16,20 @@ struct ui_progress;
 struct perf_error_ops;
 
 #if defined(NO_NEWT_SUPPORT) && defined(NO_GTK2_SUPPORT)
-static inline void ui_progress__update(u64 curr __used, u64 total __used,
-				       const char *title __used) {}
+static inline void ui_progress__update(u64 curr __maybe_unused,
+				       u64 total __maybe_unused,
+				       const char *title __maybe_unused) {}
 
 #define ui__error(format, arg...) ui__warning(format, ##arg)
 
 static inline int
-perf_error__register(struct perf_error_ops *eops __used)
+perf_error__register(struct perf_error_ops *eops __maybe_unused)
 {
 	return 0;
 }
 
 static inline int
-perf_error__unregister(struct perf_error_ops *eops __used)
+perf_error__unregister(struct perf_error_ops *eops __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 84ff6f160cd0..8202f5ca0483 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -112,7 +112,7 @@ static pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 	event->comm.header.type = PERF_RECORD_COMM;
 
 	size = strlen(event->comm.comm) + 1;
-	size = ALIGN(size, sizeof(u64));
+	size = PERF_ALIGN(size, sizeof(u64));
 	memset(event->comm.comm + size, 0, machine->id_hdr_size);
 	event->comm.header.size = (sizeof(event->comm) -
 				(sizeof(event->comm.comm) - size) +
@@ -145,7 +145,7 @@ static pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 					 sizeof(event->comm.comm));
 
 		size = strlen(event->comm.comm) + 1;
-		size = ALIGN(size, sizeof(u64));
+		size = PERF_ALIGN(size, sizeof(u64));
 		memset(event->comm.comm + size, 0, machine->id_hdr_size);
 		event->comm.header.size = (sizeof(event->comm) -
 					  (sizeof(event->comm.comm) - size) +
@@ -228,7 +228,7 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			size = strlen(execname);
 			execname[size - 1] = '\0'; /* Remove \n */
 			memcpy(event->mmap.filename, execname, size);
-			size = ALIGN(size, sizeof(u64));
+			size = PERF_ALIGN(size, sizeof(u64));
 			event->mmap.len -= event->mmap.start;
 			event->mmap.header.size = (sizeof(event->mmap) -
 					        (sizeof(event->mmap.filename) - size));
@@ -282,7 +282,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 		if (pos->dso->kernel)
 			continue;
 
-		size = ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
+		size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
 		event->mmap.header.type = PERF_RECORD_MMAP;
 		event->mmap.header.size = (sizeof(event->mmap) -
 				        (sizeof(event->mmap.filename) - size));
@@ -494,7 +494,7 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 	map = machine->vmlinux_maps[MAP__FUNCTION];
 	size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
 			"%s%s", mmap_name, symbol_name) + 1;
-	size = ALIGN(size, sizeof(u64));
+	size = PERF_ALIGN(size, sizeof(u64));
 	event->mmap.header.type = PERF_RECORD_MMAP;
 	event->mmap.header.size = (sizeof(event->mmap) -
 			(sizeof(event->mmap.filename) - size) + machine->id_hdr_size);
@@ -514,9 +514,9 @@ size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
 	return fprintf(fp, ": %s:%d\n", event->comm.comm, event->comm.tid);
 }
 
-int perf_event__process_comm(struct perf_tool *tool __used,
+int perf_event__process_comm(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
-			     struct perf_sample *sample __used,
+			     struct perf_sample *sample __maybe_unused,
 			     struct machine *machine)
 {
 	struct thread *thread = machine__findnew_thread(machine, event->comm.tid);
@@ -532,10 +532,10 @@ int perf_event__process_comm(struct perf_tool *tool __used,
 	return 0;
 }
 
-int perf_event__process_lost(struct perf_tool *tool __used,
+int perf_event__process_lost(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
-			     struct perf_sample *sample __used,
-			     struct machine *machine __used)
+			     struct perf_sample *sample __maybe_unused,
+			     struct machine *machine __maybe_unused)
 {
 	dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n",
 		    event->lost.id, event->lost.lost);
@@ -555,7 +555,8 @@ static void perf_event__set_kernel_mmap_len(union perf_event *event,
 		maps[MAP__FUNCTION]->end = ~0ULL;
 }
 
-static int perf_event__process_kernel_mmap(struct perf_tool *tool __used,
+static int perf_event__process_kernel_mmap(struct perf_tool *tool
+					   __maybe_unused,
 					   union perf_event *event,
 					   struct machine *machine)
 {
@@ -657,7 +658,7 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 
 int perf_event__process_mmap(struct perf_tool *tool,
 			     union perf_event *event,
-			     struct perf_sample *sample __used,
+			     struct perf_sample *sample __maybe_unused,
 			     struct machine *machine)
 {
 	struct thread *thread;
@@ -701,9 +702,9 @@ size_t perf_event__fprintf_task(union perf_event *event, FILE *fp)
 		       event->fork.ppid, event->fork.ptid);
 }
 
-int perf_event__process_task(struct perf_tool *tool __used,
+int perf_event__process_task(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
-			     struct perf_sample *sample __used,
+			     struct perf_sample *sample __maybe_unused,
 			      struct machine *machine)
 {
 	struct thread *thread = machine__findnew_thread(machine, event->fork.tid);
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 0e088d046e56..21b99e741a87 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -101,7 +101,7 @@ struct perf_sample {
 struct build_id_event {
 	struct perf_event_header header;
 	pid_t			 pid;
-	u8			 build_id[ALIGN(BUILD_ID_SIZE, sizeof(u64))];
+	u8			 build_id[PERF_ALIGN(BUILD_ID_SIZE, sizeof(u64))];
 	char			 filename[];
 };
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 06f76441547a..1506ba0453f1 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -10,6 +10,7 @@
 #include <byteswap.h>
 #include <linux/bitops.h>
 #include "asm/bug.h"
+#include "event-parse.h"
 #include "evsel.h"
 #include "evlist.h"
 #include "util.h"
@@ -1000,3 +1001,37 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 
 	return 0;
 }
+
+char *perf_evsel__strval(struct perf_evsel *evsel, struct perf_sample *sample,
+			 const char *name)
+{
+	struct format_field *field = pevent_find_field(evsel->tp_format, name);
+	int offset;
+
+        if (!field)
+                return NULL;
+
+	offset = field->offset;
+
+	if (field->flags & FIELD_IS_DYNAMIC) {
+		offset = *(int *)(sample->raw_data + field->offset);
+		offset &= 0xffff;
+	}
+
+	return sample->raw_data + offset;
+}
+
+u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
+		       const char *name)
+{
+	struct format_field *field = pevent_find_field(evsel->tp_format, name);
+	u64 val;
+
+        if (!field)
+                return 0;
+
+	val = pevent_read_number(evsel->tp_format->pevent,
+				 sample->raw_data + field->offset, field->size);
+	return val;
+
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 390690eb8781..dc40fe32210b 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -120,6 +120,13 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 		     struct thread_map *threads);
 void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads);
 
+struct perf_sample;
+
+char *perf_evsel__strval(struct perf_evsel *evsel, struct perf_sample *sample,
+			 const char *name);
+u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
+		       const char *name);
+
 #define perf_evsel__match(evsel, t, c)		\
 	(evsel->attr.type == PERF_TYPE_##t &&	\
 	 evsel->attr.config == PERF_COUNT_##c)
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index d07bc134e562..acbf6336199e 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -21,6 +21,7 @@
 #include "debug.h"
 #include "cpumap.h"
 #include "pmu.h"
+#include "vdso.h"
 
 static bool no_buildid_cache = false;
 
@@ -129,7 +130,7 @@ static int do_write_string(int fd, const char *str)
 	int ret;
 
 	olen = strlen(str) + 1;
-	len = ALIGN(olen, NAME_ALIGN);
+	len = PERF_ALIGN(olen, NAME_ALIGN);
 
 	/* write len, incl. \0 */
 	ret = do_write(fd, &len, sizeof(len));
@@ -207,6 +208,29 @@ perf_header__set_cmdline(int argc, const char **argv)
 			continue;		\
 		else
 
+static int write_buildid(char *name, size_t name_len, u8 *build_id,
+			 pid_t pid, u16 misc, int fd)
+{
+	int err;
+	struct build_id_event b;
+	size_t len;
+
+	len = name_len + 1;
+	len = PERF_ALIGN(len, NAME_ALIGN);
+
+	memset(&b, 0, sizeof(b));
+	memcpy(&b.build_id, build_id, BUILD_ID_SIZE);
+	b.pid = pid;
+	b.header.misc = misc;
+	b.header.size = sizeof(b) + len;
+
+	err = do_write(fd, &b, sizeof(b));
+	if (err < 0)
+		return err;
+
+	return write_padded(fd, name, name_len + 1, len);
+}
+
 static int __dsos__write_buildid_table(struct list_head *head, pid_t pid,
 				u16 misc, int fd)
 {
@@ -214,24 +238,23 @@ static int __dsos__write_buildid_table(struct list_head *head, pid_t pid,
 
 	dsos__for_each_with_build_id(pos, head) {
 		int err;
-		struct build_id_event b;
-		size_t len;
+		char  *name;
+		size_t name_len;
 
 		if (!pos->hit)
 			continue;
-		len = pos->long_name_len + 1;
-		len = ALIGN(len, NAME_ALIGN);
-		memset(&b, 0, sizeof(b));
-		memcpy(&b.build_id, pos->build_id, sizeof(pos->build_id));
-		b.pid = pid;
-		b.header.misc = misc;
-		b.header.size = sizeof(b) + len;
-		err = do_write(fd, &b, sizeof(b));
-		if (err < 0)
-			return err;
-		err = write_padded(fd, pos->long_name,
-				   pos->long_name_len + 1, len);
-		if (err < 0)
+
+		if (is_vdso_map(pos->short_name)) {
+			name = (char *) VDSO__MAP_NAME;
+			name_len = sizeof(VDSO__MAP_NAME) + 1;
+		} else {
+			name = pos->long_name;
+			name_len = pos->long_name_len + 1;
+		}
+
+		err = write_buildid(name, name_len, pos->build_id,
+				    pid, misc, fd);
+		if (err)
 			return err;
 	}
 
@@ -277,19 +300,20 @@ static int dsos__write_buildid_table(struct perf_header *header, int fd)
 }
 
 int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
-			  const char *name, bool is_kallsyms)
+			  const char *name, bool is_kallsyms, bool is_vdso)
 {
 	const size_t size = PATH_MAX;
 	char *realname, *filename = zalloc(size),
 	     *linkname = zalloc(size), *targetname;
 	int len, err = -1;
+	bool slash = is_kallsyms || is_vdso;
 
 	if (is_kallsyms) {
 		if (symbol_conf.kptr_restrict) {
 			pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
 			return 0;
 		}
-		realname = (char *)name;
+		realname = (char *) name;
 	} else
 		realname = realpath(name, NULL);
 
@@ -297,7 +321,8 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 		goto out_free;
 
 	len = scnprintf(filename, size, "%s%s%s",
-		       debugdir, is_kallsyms ? "/" : "", realname);
+		       debugdir, slash ? "/" : "",
+		       is_vdso ? VDSO__MAP_NAME : realname);
 	if (mkdir_p(filename, 0755))
 		goto out_free;
 
@@ -333,13 +358,14 @@ out_free:
 
 static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
 				 const char *name, const char *debugdir,
-				 bool is_kallsyms)
+				 bool is_kallsyms, bool is_vdso)
 {
 	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
 
 	build_id__sprintf(build_id, build_id_size, sbuild_id);
 
-	return build_id_cache__add_s(sbuild_id, debugdir, name, is_kallsyms);
+	return build_id_cache__add_s(sbuild_id, debugdir, name,
+				     is_kallsyms, is_vdso);
 }
 
 int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir)
@@ -383,9 +409,11 @@ out_free:
 static int dso__cache_build_id(struct dso *dso, const char *debugdir)
 {
 	bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
+	bool is_vdso = is_vdso_map(dso->short_name);
 
 	return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id),
-				     dso->long_name, debugdir, is_kallsyms);
+				     dso->long_name, debugdir,
+				     is_kallsyms, is_vdso);
 }
 
 static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir)
@@ -447,7 +475,7 @@ static bool perf_session__read_build_ids(struct perf_session *session, bool with
 	return ret;
 }
 
-static int write_tracing_data(int fd, struct perf_header *h __used,
+static int write_tracing_data(int fd, struct perf_header *h __maybe_unused,
 			    struct perf_evlist *evlist)
 {
 	return read_tracing_data(fd, &evlist->entries);
@@ -455,7 +483,7 @@ static int write_tracing_data(int fd, struct perf_header *h __used,
 
 
 static int write_build_id(int fd, struct perf_header *h,
-			  struct perf_evlist *evlist __used)
+			  struct perf_evlist *evlist __maybe_unused)
 {
 	struct perf_session *session;
 	int err;
@@ -476,8 +504,8 @@ static int write_build_id(int fd, struct perf_header *h,
 	return 0;
 }
 
-static int write_hostname(int fd, struct perf_header *h __used,
-			  struct perf_evlist *evlist __used)
+static int write_hostname(int fd, struct perf_header *h __maybe_unused,
+			  struct perf_evlist *evlist __maybe_unused)
 {
 	struct utsname uts;
 	int ret;
@@ -489,8 +517,8 @@ static int write_hostname(int fd, struct perf_header *h __used,
 	return do_write_string(fd, uts.nodename);
 }
 
-static int write_osrelease(int fd, struct perf_header *h __used,
-			   struct perf_evlist *evlist __used)
+static int write_osrelease(int fd, struct perf_header *h __maybe_unused,
+			   struct perf_evlist *evlist __maybe_unused)
 {
 	struct utsname uts;
 	int ret;
@@ -502,8 +530,8 @@ static int write_osrelease(int fd, struct perf_header *h __used,
 	return do_write_string(fd, uts.release);
 }
 
-static int write_arch(int fd, struct perf_header *h __used,
-		      struct perf_evlist *evlist __used)
+static int write_arch(int fd, struct perf_header *h __maybe_unused,
+		      struct perf_evlist *evlist __maybe_unused)
 {
 	struct utsname uts;
 	int ret;
@@ -515,14 +543,14 @@ static int write_arch(int fd, struct perf_header *h __used,
 	return do_write_string(fd, uts.machine);
 }
 
-static int write_version(int fd, struct perf_header *h __used,
-			 struct perf_evlist *evlist __used)
+static int write_version(int fd, struct perf_header *h __maybe_unused,
+			 struct perf_evlist *evlist __maybe_unused)
 {
 	return do_write_string(fd, perf_version_string);
 }
 
-static int write_cpudesc(int fd, struct perf_header *h __used,
-		       struct perf_evlist *evlist __used)
+static int write_cpudesc(int fd, struct perf_header *h __maybe_unused,
+		       struct perf_evlist *evlist __maybe_unused)
 {
 #ifndef CPUINFO_PROC
 #define CPUINFO_PROC NULL
@@ -580,8 +608,8 @@ done:
 	return ret;
 }
 
-static int write_nrcpus(int fd, struct perf_header *h __used,
-			struct perf_evlist *evlist __used)
+static int write_nrcpus(int fd, struct perf_header *h __maybe_unused,
+			struct perf_evlist *evlist __maybe_unused)
 {
 	long nr;
 	u32 nrc, nra;
@@ -606,7 +634,7 @@ static int write_nrcpus(int fd, struct perf_header *h __used,
 	return do_write(fd, &nra, sizeof(nra));
 }
 
-static int write_event_desc(int fd, struct perf_header *h __used,
+static int write_event_desc(int fd, struct perf_header *h __maybe_unused,
 			    struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
@@ -663,8 +691,8 @@ static int write_event_desc(int fd, struct perf_header *h __used,
 	return 0;
 }
 
-static int write_cmdline(int fd, struct perf_header *h __used,
-			 struct perf_evlist *evlist __used)
+static int write_cmdline(int fd, struct perf_header *h __maybe_unused,
+			 struct perf_evlist *evlist __maybe_unused)
 {
 	char buf[MAXPATHLEN];
 	char proc[32];
@@ -832,8 +860,8 @@ static struct cpu_topo *build_cpu_topology(void)
 	return tp;
 }
 
-static int write_cpu_topology(int fd, struct perf_header *h __used,
-			  struct perf_evlist *evlist __used)
+static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused,
+			  struct perf_evlist *evlist __maybe_unused)
 {
 	struct cpu_topo *tp;
 	u32 i;
@@ -868,8 +896,8 @@ done:
 
 
 
-static int write_total_mem(int fd, struct perf_header *h __used,
-			  struct perf_evlist *evlist __used)
+static int write_total_mem(int fd, struct perf_header *h __maybe_unused,
+			  struct perf_evlist *evlist __maybe_unused)
 {
 	char *buf = NULL;
 	FILE *fp;
@@ -954,8 +982,8 @@ done:
 	return ret;
 }
 
-static int write_numa_topology(int fd, struct perf_header *h __used,
-			  struct perf_evlist *evlist __used)
+static int write_numa_topology(int fd, struct perf_header *h __maybe_unused,
+			  struct perf_evlist *evlist __maybe_unused)
 {
 	char *buf = NULL;
 	size_t len = 0;
@@ -1015,8 +1043,8 @@ done:
  * };
  */
 
-static int write_pmu_mappings(int fd, struct perf_header *h __used,
-			      struct perf_evlist *evlist __used)
+static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused,
+			      struct perf_evlist *evlist __maybe_unused)
 {
 	struct perf_pmu *pmu = NULL;
 	off_t offset = lseek(fd, 0, SEEK_CUR);
@@ -1046,13 +1074,14 @@ static int write_pmu_mappings(int fd, struct perf_header *h __used,
  * default get_cpuid(): nothing gets recorded
  * actual implementation must be in arch/$(ARCH)/util/header.c
  */
-int __attribute__((weak)) get_cpuid(char *buffer __used, size_t sz __used)
+int __attribute__ ((weak)) get_cpuid(char *buffer __maybe_unused,
+				     size_t sz __maybe_unused)
 {
 	return -1;
 }
 
-static int write_cpuid(int fd, struct perf_header *h __used,
-		       struct perf_evlist *evlist __used)
+static int write_cpuid(int fd, struct perf_header *h __maybe_unused,
+		       struct perf_evlist *evlist __maybe_unused)
 {
 	char buffer[64];
 	int ret;
@@ -1066,8 +1095,9 @@ write_it:
 	return do_write_string(fd, buffer);
 }
 
-static int write_branch_stack(int fd __used, struct perf_header *h __used,
-		       struct perf_evlist *evlist __used)
+static int write_branch_stack(int fd __maybe_unused,
+			      struct perf_header *h __maybe_unused,
+		       struct perf_evlist *evlist __maybe_unused)
 {
 	return 0;
 }
@@ -1344,7 +1374,8 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
 	free_event_desc(events);
 }
 
-static void print_total_mem(struct perf_header *h __used, int fd, FILE *fp)
+static void print_total_mem(struct perf_header *h __maybe_unused, int fd,
+			    FILE *fp)
 {
 	uint64_t mem;
 	ssize_t ret;
@@ -1362,7 +1393,8 @@ error:
 	fprintf(fp, "# total memory : unknown\n");
 }
 
-static void print_numa_topology(struct perf_header *h __used, int fd, FILE *fp)
+static void print_numa_topology(struct perf_header *h __maybe_unused, int fd,
+				FILE *fp)
 {
 	ssize_t ret;
 	u32 nr, c, i;
@@ -1422,7 +1454,8 @@ static void print_cpuid(struct perf_header *ph, int fd, FILE *fp)
 	free(str);
 }
 
-static void print_branch_stack(struct perf_header *ph __used, int fd __used,
+static void print_branch_stack(struct perf_header *ph __maybe_unused,
+			       int fd __maybe_unused,
 			       FILE *fp)
 {
 	fprintf(fp, "# contains samples with branch stack\n");
@@ -1532,7 +1565,7 @@ static int perf_header__read_build_ids_abi_quirk(struct perf_header *header,
 	struct perf_session *session = container_of(header, struct perf_session, header);
 	struct {
 		struct perf_event_header   header;
-		u8			   build_id[ALIGN(BUILD_ID_SIZE, sizeof(u64))];
+		u8			   build_id[PERF_ALIGN(BUILD_ID_SIZE, sizeof(u64))];
 		char			   filename[0];
 	} old_bev;
 	struct build_id_event bev;
@@ -1621,9 +1654,10 @@ out:
 	return err;
 }
 
-static int process_tracing_data(struct perf_file_section *section __unused,
-			      struct perf_header *ph __unused,
-			      int feat __unused, int fd, void *data)
+static int process_tracing_data(struct perf_file_section *section
+				__maybe_unused,
+			      struct perf_header *ph __maybe_unused,
+			      int feat __maybe_unused, int fd, void *data)
 {
 	trace_report(fd, data, false);
 	return 0;
@@ -1631,7 +1665,8 @@ static int process_tracing_data(struct perf_file_section *section __unused,
 
 static int process_build_id(struct perf_file_section *section,
 			    struct perf_header *ph,
-			    int feat __unused, int fd, void *data __used)
+			    int feat __maybe_unused, int fd,
+			    void *data __maybe_unused)
 {
 	if (perf_header__read_build_ids(ph, fd, section->offset, section->size))
 		pr_debug("Failed to read buildids, continuing...\n");
@@ -1670,9 +1705,9 @@ perf_evlist__set_event_name(struct perf_evlist *evlist, struct perf_evsel *event
 }
 
 static int
-process_event_desc(struct perf_file_section *section __unused,
-		   struct perf_header *header, int feat __unused, int fd,
-		   void *data __used)
+process_event_desc(struct perf_file_section *section __maybe_unused,
+		   struct perf_header *header, int feat __maybe_unused, int fd,
+		   void *data __maybe_unused)
 {
 	struct perf_session *session = container_of(header, struct perf_session, header);
 	struct perf_evsel *evsel, *events = read_event_desc(header, fd);
@@ -2439,7 +2474,7 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
 	int err;
 
 	size = sizeof(struct perf_event_attr);
-	size = ALIGN(size, sizeof(u64));
+	size = PERF_ALIGN(size, sizeof(u64));
 	size += sizeof(struct perf_event_header);
 	size += ids * sizeof(u64);
 
@@ -2537,7 +2572,7 @@ int perf_event__synthesize_event_type(struct perf_tool *tool,
 
 	ev.event_type.header.type = PERF_RECORD_HEADER_EVENT_TYPE;
 	size = strlen(ev.event_type.event_type.name);
-	size = ALIGN(size, sizeof(u64));
+	size = PERF_ALIGN(size, sizeof(u64));
 	ev.event_type.header.size = sizeof(ev.event_type) -
 		(sizeof(ev.event_type.event_type.name) - size);
 
@@ -2568,7 +2603,7 @@ int perf_event__synthesize_event_types(struct perf_tool *tool,
 	return err;
 }
 
-int perf_event__process_event_type(struct perf_tool *tool __unused,
+int perf_event__process_event_type(struct perf_tool *tool __maybe_unused,
 				   union perf_event *event)
 {
 	if (perf_header__push_event(event->event_type.event_type.event_id,
@@ -2585,7 +2620,7 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
 	union perf_event ev;
 	struct tracing_data *tdata;
 	ssize_t size = 0, aligned_size = 0, padding;
-	int err __used = 0;
+	int err __maybe_unused = 0;
 
 	/*
 	 * We are going to store the size of the data followed
@@ -2606,7 +2641,7 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
 
 	ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA;
 	size = tdata->size;
-	aligned_size = ALIGN(size, sizeof(u64));
+	aligned_size = PERF_ALIGN(size, sizeof(u64));
 	padding = aligned_size - size;
 	ev.tracing_data.header.size = sizeof(ev.tracing_data);
 	ev.tracing_data.size = aligned_size;
@@ -2637,7 +2672,7 @@ int perf_event__process_tracing_data(union perf_event *event,
 
 	size_read = trace_report(session->fd, &session->pevent,
 				 session->repipe);
-	padding = ALIGN(size_read, sizeof(u64)) - size_read;
+	padding = PERF_ALIGN(size_read, sizeof(u64)) - size_read;
 
 	if (read(session->fd, buf, padding) < 0)
 		die("reading input file");
@@ -2671,7 +2706,7 @@ int perf_event__synthesize_build_id(struct perf_tool *tool,
 	memset(&ev, 0, sizeof(ev));
 
 	len = pos->long_name_len + 1;
-	len = ALIGN(len, NAME_ALIGN);
+	len = PERF_ALIGN(len, NAME_ALIGN);
 	memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id));
 	ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID;
 	ev.build_id.header.misc = misc;
@@ -2684,7 +2719,7 @@ int perf_event__synthesize_build_id(struct perf_tool *tool,
 	return err;
 }
 
-int perf_event__process_build_id(struct perf_tool *tool __used,
+int perf_event__process_build_id(struct perf_tool *tool __maybe_unused,
 				 union perf_event *event,
 				 struct perf_session *session)
 {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 9d5eedceda72..209dad4fee2b 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -96,7 +96,7 @@ int perf_header__process_sections(struct perf_header *header, int fd,
 int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full);
 
 int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
-			  const char *name, bool is_kallsyms);
+			  const char *name, bool is_kallsyms, bool is_vdso);
 int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);
 
 int perf_event__synthesize_attr(struct perf_tool *tool,
diff --git a/tools/perf/util/help.c b/tools/perf/util/help.c
index 4fa764d8f7d7..8b1f6e891b8a 100644
--- a/tools/perf/util/help.c
+++ b/tools/perf/util/help.c
@@ -332,7 +332,8 @@ const char *help_unknown_cmd(const char *cmd)
 	exit(1);
 }
 
-int cmd_version(int argc __used, const char **argv __used, const char *prefix __used)
+int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused,
+		const char *prefix __maybe_unused)
 {
 	printf("perf version %s\n", perf_version_string);
 	return 0;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 0ba65ad07cd1..6ec5398de89d 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -394,7 +394,7 @@ void hist_entry__free(struct hist_entry *he)
  * collapse the histogram
  */
 
-static bool hists__collapse_insert_entry(struct hists *hists __used,
+static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
 					 struct rb_root *root,
 					 struct hist_entry *he)
 {
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 4146f51124f0..f011ad4756e8 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -156,20 +156,22 @@ struct perf_evlist;
 
 #ifdef NO_NEWT_SUPPORT
 static inline
-int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __used,
-				  const char *help __used,
-				  void(*timer)(void *arg) __used,
-				  void *arg __used,
-				  int refresh __used)
+int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused,
+				  const char *help __maybe_unused,
+				  void(*timer)(void *arg) __maybe_unused,
+				  void *arg __maybe_unused,
+				  int refresh __maybe_unused)
 {
 	return 0;
 }
 
-static inline int hist_entry__tui_annotate(struct hist_entry *self __used,
-					   int evidx __used,
-					   void(*timer)(void *arg) __used,
-					   void *arg __used,
-					   int delay_secs __used)
+static inline int hist_entry__tui_annotate(struct hist_entry *self
+					   __maybe_unused,
+					   int evidx __maybe_unused,
+					   void(*timer)(void *arg)
+					   __maybe_unused,
+					   void *arg __maybe_unused,
+					   int delay_secs __maybe_unused)
 {
 	return 0;
 }
@@ -187,11 +189,11 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
 
 #ifdef NO_GTK2_SUPPORT
 static inline
-int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __used,
-				  const char *help __used,
-				  void(*timer)(void *arg) __used,
-				  void *arg __used,
-				  int refresh __used)
+int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __maybe_unused,
+				  const char *help __maybe_unused,
+				  void(*timer)(void *arg) __maybe_unused,
+				  void *arg __maybe_unused,
+				  int refresh __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
index 587a230d2075..a55d8cf083c9 100644
--- a/tools/perf/util/include/linux/bitops.h
+++ b/tools/perf/util/include/linux/bitops.h
@@ -5,6 +5,10 @@
 #include <linux/compiler.h>
 #include <asm/hweight.h>
 
+#ifndef __WORDSIZE
+#define __WORDSIZE (__SIZEOF_LONG__ * 8)
+#endif
+
 #define BITS_PER_LONG __WORDSIZE
 #define BITS_PER_BYTE           8
 #define BITS_TO_LONGS(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
diff --git a/tools/perf/util/include/linux/compiler.h b/tools/perf/util/include/linux/compiler.h
index 2dc867128e46..96b919dae11c 100644
--- a/tools/perf/util/include/linux/compiler.h
+++ b/tools/perf/util/include/linux/compiler.h
@@ -9,7 +9,13 @@
 #define __attribute_const__
 #endif
 
-#define __used		__attribute__((__unused__))
+#ifndef __maybe_unused
+#define __maybe_unused		__attribute__((unused))
+#endif
 #define __packed	__attribute__((__packed__))
 
+#ifndef __force
+#define __force
+#endif
+
 #endif
diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h
index 4af9a10cc2d2..d8c927c868ee 100644
--- a/tools/perf/util/include/linux/kernel.h
+++ b/tools/perf/util/include/linux/kernel.h
@@ -8,8 +8,8 @@
 
 #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
 
-#define ALIGN(x,a)		__ALIGN_MASK(x,(typeof(x))(a)-1)
-#define __ALIGN_MASK(x,mask)	(((x)+(mask))&~(mask))
+#define PERF_ALIGN(x, a)	__PERF_ALIGN_MASK(x, (typeof(x))(a)-1)
+#define __PERF_ALIGN_MASK(x, mask)	(((x)+(mask))&~(mask))
 
 #ifndef offsetof
 #define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)
@@ -46,6 +46,15 @@
 	_min1 < _min2 ? _min1 : _min2; })
 #endif
 
+#ifndef roundup
+#define roundup(x, y) (                                \
+{                                                      \
+	const typeof(y) __y = y;		       \
+	(((x) + (__y - 1)) / __y) * __y;	       \
+}                                                      \
+)
+#endif
+
 #ifndef BUG_ON
 #ifdef NDEBUG
 #define BUG_ON(cond) do { if (cond) {} } while (0)
diff --git a/tools/perf/util/include/linux/magic.h b/tools/perf/util/include/linux/magic.h
new file mode 100644
index 000000000000..58b64ed4da12
--- /dev/null
+++ b/tools/perf/util/include/linux/magic.h
@@ -0,0 +1,12 @@
+#ifndef _PERF_LINUX_MAGIC_H_
+#define _PERF_LINUX_MAGIC_H_
+
+#ifndef DEBUGFS_MAGIC
+#define DEBUGFS_MAGIC          0x64626720
+#endif
+
+#ifndef SYSFS_MAGIC
+#define SYSFS_MAGIC            0x62656572
+#endif
+
+#endif
diff --git a/tools/perf/util/include/linux/string.h b/tools/perf/util/include/linux/string.h
index 3b2f5900276f..6f19c548ecc0 100644
--- a/tools/perf/util/include/linux/string.h
+++ b/tools/perf/util/include/linux/string.h
@@ -1 +1,3 @@
 #include <string.h>
+
+void *memdup(const void *src, size_t len);
diff --git a/tools/perf/util/include/linux/types.h b/tools/perf/util/include/linux/types.h
index 12de3b8112f9..eb464786c084 100644
--- a/tools/perf/util/include/linux/types.h
+++ b/tools/perf/util/include/linux/types.h
@@ -3,6 +3,14 @@
 
 #include <asm/types.h>
 
+#ifndef __bitwise
+#define __bitwise
+#endif
+
+#ifndef __le32
+typedef __u32 __bitwise __le32;
+#endif
+
 #define DECLARE_BITMAP(name,bits) \
 	unsigned long name[BITS_TO_LONGS(bits)]
 
diff --git a/tools/perf/util/intlist.c b/tools/perf/util/intlist.c
index 77c504ff0088..9d0740024ba8 100644
--- a/tools/perf/util/intlist.c
+++ b/tools/perf/util/intlist.c
@@ -11,7 +11,7 @@
 
 #include "intlist.h"
 
-static struct rb_node *intlist__node_new(struct rblist *rblist __used,
+static struct rb_node *intlist__node_new(struct rblist *rblist __maybe_unused,
 					 const void *entry)
 {
 	int i = (int)((long)entry);
@@ -31,7 +31,7 @@ static void int_node__delete(struct int_node *ilist)
 	free(ilist);
 }
 
-static void intlist__node_delete(struct rblist *rblist __used,
+static void intlist__node_delete(struct rblist *rblist __maybe_unused,
 				 struct rb_node *rb_node)
 {
 	struct int_node *node = container_of(rb_node, struct int_node, rb_node);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 7d37159c1e99..b442ee49452b 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -9,6 +9,7 @@
 #include "map.h"
 #include "thread.h"
 #include "strlist.h"
+#include "vdso.h"
 
 const char *map_type__name[MAP__NR_TYPES] = {
 	[MAP__FUNCTION] = "Functions",
@@ -23,7 +24,6 @@ static inline int is_anon_memory(const char *filename)
 static inline int is_no_dso_memory(const char *filename)
 {
 	return !strcmp(filename, "[stack]") ||
-	       !strcmp(filename, "[vdso]")  ||
 	       !strcmp(filename, "[heap]");
 }
 
@@ -52,9 +52,10 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 	if (self != NULL) {
 		char newfilename[PATH_MAX];
 		struct dso *dso;
-		int anon, no_dso;
+		int anon, no_dso, vdso;
 
 		anon = is_anon_memory(filename);
+		vdso = is_vdso_map(filename);
 		no_dso = is_no_dso_memory(filename);
 
 		if (anon) {
@@ -62,7 +63,12 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 			filename = newfilename;
 		}
 
-		dso = __dsos__findnew(dsos__list, filename);
+		if (vdso) {
+			pgoff = 0;
+			dso = vdso__dso_findnew(dsos__list);
+		} else
+			dso = __dsos__findnew(dsos__list, filename);
+
 		if (dso == NULL)
 			goto out_delete;
 
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 25ab4cdbc446..d2250fc97e25 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -96,7 +96,7 @@ static inline u64 map__unmap_ip(struct map *map, u64 ip)
 	return ip + map->start - map->pgoff;
 }
 
-static inline u64 identity__map_ip(struct map *map __used, u64 ip)
+static inline u64 identity__map_ip(struct map *map __maybe_unused, u64 ip)
 {
 	return ip;
 }
diff --git a/tools/perf/util/parse-events-test.c b/tools/perf/util/parse-events-test.c
index bc8b65130ae0..d7244e553670 100644
--- a/tools/perf/util/parse-events-test.c
+++ b/tools/perf/util/parse-events-test.c
@@ -569,7 +569,7 @@ static int test__group2(struct perf_evlist *evlist)
 	return 0;
 }
 
-static int test__group3(struct perf_evlist *evlist __used)
+static int test__group3(struct perf_evlist *evlist __maybe_unused)
 {
 	struct perf_evsel *evsel, *leader;
 
@@ -648,7 +648,7 @@ static int test__group3(struct perf_evlist *evlist __used)
 	return 0;
 }
 
-static int test__group4(struct perf_evlist *evlist __used)
+static int test__group4(struct perf_evlist *evlist __maybe_unused)
 {
 	struct perf_evsel *evsel, *leader;
 
@@ -684,7 +684,7 @@ static int test__group4(struct perf_evlist *evlist __used)
 	return 0;
 }
 
-static int test__group5(struct perf_evlist *evlist __used)
+static int test__group5(struct perf_evlist *evlist __maybe_unused)
 {
 	struct perf_evsel *evsel, *leader;
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index a031ee1f54f6..44afcf40f796 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -807,7 +807,8 @@ int parse_events_terms(struct list_head *terms, const char *str)
 	return ret;
 }
 
-int parse_events(struct perf_evlist *evlist, const char *str, int unset __used)
+int parse_events(struct perf_evlist *evlist, const char *str,
+		 int unset __maybe_unused)
 {
 	struct parse_events_data__events data = {
 		.list = LIST_HEAD_INIT(data.list),
@@ -833,14 +834,14 @@ int parse_events(struct perf_evlist *evlist, const char *str, int unset __used)
 }
 
 int parse_events_option(const struct option *opt, const char *str,
-			int unset __used)
+			int unset __maybe_unused)
 {
 	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
 	return parse_events(evlist, str, unset);
 }
 
 int parse_filter(const struct option *opt, const char *str,
-		 int unset __used)
+		 int unset __maybe_unused)
 {
 	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
 	struct perf_evsel *last = NULL;
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index f5e28dc68270..c87efc12579d 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -207,7 +207,7 @@ r{num_raw_hex}		{ return raw(yyscanner); }
 
 %%
 
-int parse_events_wrap(void *scanner __used)
+int parse_events_wrap(void *scanner __maybe_unused)
 {
 	return 1;
 }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 42d9a17b83b1..cd88209e3c58 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -391,7 +391,7 @@ sep_slash_dc: '/' | ':' |
 
 %%
 
-void parse_events_error(void *data __used, void *scanner __used,
-			char const *msg __used)
+void parse_events_error(void *data __maybe_unused, void *scanner __maybe_unused,
+			char const *msg __maybe_unused)
 {
 }
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index 594f8fad5ecd..443fc116512b 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -557,7 +557,8 @@ int parse_options_usage(const char * const *usagestr,
 }
 
 
-int parse_opt_verbosity_cb(const struct option *opt, const char *arg __used,
+int parse_opt_verbosity_cb(const struct option *opt,
+			   const char *arg __maybe_unused,
 			   int unset)
 {
 	int *target = opt->value;
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index 9bd6c4e069c8..316dbe7f86ed 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -6,7 +6,7 @@
 #else
 #define PERF_REGS_MASK	0
 
-static inline const char *perf_reg_name(int id __used)
+static inline const char *perf_reg_name(int id __maybe_unused)
 {
 	return NULL;
 }
diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y
index 20ea77e93169..ec898047ebb9 100644
--- a/tools/perf/util/pmu.y
+++ b/tools/perf/util/pmu.y
@@ -86,8 +86,8 @@ PP_VALUE
 
 %%
 
-void perf_pmu_error(struct list_head *list __used,
-		    char *name __used,
-		    char const *msg __used)
+void perf_pmu_error(struct list_head *list __maybe_unused,
+		    char *name __maybe_unused,
+		    char const *msg __maybe_unused)
 {
 }
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index e8c72de0f70c..4ce04c2281d3 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -41,7 +41,7 @@
 #include "symbol.h"
 #include "thread.h"
 #include "debugfs.h"
-#include "trace-event.h"	/* For __unused */
+#include "trace-event.h"	/* For __maybe_unused */
 #include "probe-event.h"
 #include "probe-finder.h"
 #include "session.h"
@@ -647,8 +647,8 @@ static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
 }
 
 static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
-				struct probe_trace_event **tevs __unused,
-				int max_tevs __unused, const char *target)
+				struct probe_trace_event **tevs __maybe_unused,
+				int max_tevs __maybe_unused, const char *target)
 {
 	if (perf_probe_event_need_dwarf(pev)) {
 		pr_warning("Debuginfo-analysis is not supported.\n");
@@ -661,17 +661,18 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 	return 0;
 }
 
-int show_line_range(struct line_range *lr __unused, const char *module __unused)
+int show_line_range(struct line_range *lr __maybe_unused,
+		    const char *module __maybe_unused)
 {
 	pr_warning("Debuginfo-analysis is not supported.\n");
 	return -ENOSYS;
 }
 
-int show_available_vars(struct perf_probe_event *pevs __unused,
-			int npevs __unused, int max_vls __unused,
-			const char *module __unused,
-			struct strfilter *filter __unused,
-			bool externs __unused)
+int show_available_vars(struct perf_probe_event *pevs __maybe_unused,
+			int npevs __maybe_unused, int max_vls __maybe_unused,
+			const char *module __maybe_unused,
+			struct strfilter *filter __maybe_unused,
+			bool externs __maybe_unused)
 {
 	pr_warning("Debuginfo-analysis is not supported.\n");
 	return -ENOSYS;
@@ -2183,7 +2184,7 @@ static struct strfilter *available_func_filter;
  * If a symbol corresponds to a function with global binding and
  * matches filter return 0. For all others return 1.
  */
-static int filter_available_functions(struct map *map __unused,
+static int filter_available_functions(struct map *map __maybe_unused,
 				      struct symbol *sym)
 {
 	if (sym->binding == STB_GLOBAL &&
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index d448984ed789..526ba56e720b 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -207,7 +207,7 @@ static int debuginfo__init_online_kernel_dwarf(struct debuginfo *self,
 #else
 /* With older elfutils, this just support kernel module... */
 static int debuginfo__init_online_kernel_dwarf(struct debuginfo *self,
-					       Dwarf_Addr addr __used)
+					       Dwarf_Addr addr __maybe_unused)
 {
 	const char *path = kernel_get_module_path("kernel");
 
@@ -1419,7 +1419,7 @@ static int line_range_add_line(const char *src, unsigned int lineno,
 }
 
 static int line_range_walk_cb(const char *fname, int lineno,
-			      Dwarf_Addr addr __used,
+			      Dwarf_Addr addr __maybe_unused,
 			      void *data)
 {
 	struct line_finder *lf = data;
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 27187f0b71f0..ca85444bcfbf 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -672,7 +672,7 @@ struct pyrf_evlist {
 };
 
 static int pyrf_evlist__init(struct pyrf_evlist *pevlist,
-			     PyObject *args, PyObject *kwargs __used)
+			     PyObject *args, PyObject *kwargs __maybe_unused)
 {
 	PyObject *pcpus = NULL, *pthreads = NULL;
 	struct cpu_map *cpus;
@@ -733,7 +733,8 @@ static PyObject *pyrf_evlist__poll(struct pyrf_evlist *pevlist,
 }
 
 static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist,
-					 PyObject *args __used, PyObject *kwargs __used)
+					 PyObject *args __maybe_unused,
+					 PyObject *kwargs __maybe_unused)
 {
 	struct perf_evlist *evlist = &pevlist->evlist;
         PyObject *list = PyList_New(0);
@@ -765,7 +766,8 @@ free_list:
 
 
 static PyObject *pyrf_evlist__add(struct pyrf_evlist *pevlist,
-				  PyObject *args, PyObject *kwargs __used)
+				  PyObject *args,
+				  PyObject *kwargs __maybe_unused)
 {
 	struct perf_evlist *evlist = &pevlist->evlist;
 	PyObject *pevsel;
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 94e673643bcb..ffde3e4e34aa 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -257,10 +257,10 @@ static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
 	return event;
 }
 
-static void perl_process_tracepoint(union perf_event *perf_event __unused,
+static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused,
 				    struct perf_sample *sample,
 				    struct perf_evsel *evsel,
-				    struct machine *machine __unused,
+				    struct machine *machine __maybe_unused,
 				    struct addr_location *al)
 {
 	struct format_field *field;
@@ -349,8 +349,8 @@ static void perl_process_tracepoint(union perf_event *perf_event __unused,
 static void perl_process_event_generic(union perf_event *event,
 				       struct perf_sample *sample,
 				       struct perf_evsel *evsel,
-				       struct machine *machine __unused,
-				       struct addr_location *al __unused)
+				       struct machine *machine __maybe_unused,
+				       struct addr_location *al __maybe_unused)
 {
 	dSP;
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index afba09729183..730c6630cba5 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -221,10 +221,11 @@ static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
 	return event;
 }
 
-static void python_process_tracepoint(union perf_event *perf_event __unused,
+static void python_process_tracepoint(union perf_event *perf_event
+				      __maybe_unused,
 				 struct perf_sample *sample,
 				 struct perf_evsel *evsel,
-				 struct machine *machine __unused,
+				 struct machine *machine __maybe_unused,
 				 struct addr_location *al)
 {
 	PyObject *handler, *retval, *context, *t, *obj, *dict = NULL;
@@ -339,10 +340,11 @@ static void python_process_tracepoint(union perf_event *perf_event __unused,
 	Py_DECREF(t);
 }
 
-static void python_process_general_event(union perf_event *perf_event __unused,
+static void python_process_general_event(union perf_event *perf_event
+					 __maybe_unused,
 					 struct perf_sample *sample,
 					 struct perf_evsel *evsel,
-					 struct machine *machine __unused,
+					 struct machine *machine __maybe_unused,
 					 struct addr_location *al)
 {
 	PyObject *handler, *retval, *t, *dict;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 945375897c2a..3049b0ae7003 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -17,6 +17,7 @@
 #include "event-parse.h"
 #include "perf_regs.h"
 #include "unwind.h"
+#include "vdso.h"
 
 static int perf_session__open(struct perf_session *self, bool force)
 {
@@ -211,6 +212,7 @@ void perf_session__delete(struct perf_session *self)
 	machine__exit(&self->host_machine);
 	close(self->fd);
 	free(self);
+	vdso__exit();
 }
 
 void machine__remove_thread(struct machine *self, struct thread *th)
@@ -388,55 +390,64 @@ int machine__resolve_callchain(struct machine *machine,
 	      (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER)))
 		return 0;
 
+	/* Bail out if nothing was captured. */
+	if ((!sample->user_regs.regs) ||
+	    (!sample->user_stack.size))
+		return 0;
+
 	return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
 				   thread, evsel->attr.sample_regs_user,
 				   sample);
 
 }
 
-static int process_event_synth_tracing_data_stub(union perf_event *event __used,
-						 struct perf_session *session __used)
+static int process_event_synth_tracing_data_stub(union perf_event *event
+						 __maybe_unused,
+						 struct perf_session *session
+						__maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
 }
 
-static int process_event_synth_attr_stub(union perf_event *event __used,
-					 struct perf_evlist **pevlist __used)
+static int process_event_synth_attr_stub(union perf_event *event __maybe_unused,
+					 struct perf_evlist **pevlist
+					 __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
 }
 
-static int process_event_sample_stub(struct perf_tool *tool __used,
-				     union perf_event *event __used,
-				     struct perf_sample *sample __used,
-				     struct perf_evsel *evsel __used,
-				     struct machine *machine __used)
+static int process_event_sample_stub(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event __maybe_unused,
+				     struct perf_sample *sample __maybe_unused,
+				     struct perf_evsel *evsel __maybe_unused,
+				     struct machine *machine __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
 }
 
-static int process_event_stub(struct perf_tool *tool __used,
-			      union perf_event *event __used,
-			      struct perf_sample *sample __used,
-			      struct machine *machine __used)
+static int process_event_stub(struct perf_tool *tool __maybe_unused,
+			      union perf_event *event __maybe_unused,
+			      struct perf_sample *sample __maybe_unused,
+			      struct machine *machine __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
 }
 
-static int process_finished_round_stub(struct perf_tool *tool __used,
-				       union perf_event *event __used,
-				       struct perf_session *perf_session __used)
+static int process_finished_round_stub(struct perf_tool *tool __maybe_unused,
+				       union perf_event *event __maybe_unused,
+				       struct perf_session *perf_session
+				       __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
 }
 
-static int process_event_type_stub(struct perf_tool *tool __used,
-				   union perf_event *event __used)
+static int process_event_type_stub(struct perf_tool *tool __maybe_unused,
+				   union perf_event *event __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
@@ -513,7 +524,7 @@ static void swap_sample_id_all(union perf_event *event, void *data)
 }
 
 static void perf_event__all64_swap(union perf_event *event,
-				   bool sample_id_all __used)
+				   bool sample_id_all __maybe_unused)
 {
 	struct perf_event_header *hdr = &event->header;
 	mem_bswap_64(hdr + 1, event->header.size - sizeof(*hdr));
@@ -527,7 +538,7 @@ static void perf_event__comm_swap(union perf_event *event, bool sample_id_all)
 	if (sample_id_all) {
 		void *data = &event->comm.comm;
 
-		data += ALIGN(strlen(data) + 1, sizeof(u64));
+		data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
 		swap_sample_id_all(event, data);
 	}
 }
@@ -544,7 +555,7 @@ static void perf_event__mmap_swap(union perf_event *event,
 	if (sample_id_all) {
 		void *data = &event->mmap.filename;
 
-		data += ALIGN(strlen(data) + 1, sizeof(u64));
+		data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
 		swap_sample_id_all(event, data);
 	}
 }
@@ -624,7 +635,7 @@ void perf_event__attr_swap(struct perf_event_attr *attr)
 }
 
 static void perf_event__hdr_attr_swap(union perf_event *event,
-				      bool sample_id_all __used)
+				      bool sample_id_all __maybe_unused)
 {
 	size_t size;
 
@@ -636,14 +647,14 @@ static void perf_event__hdr_attr_swap(union perf_event *event,
 }
 
 static void perf_event__event_type_swap(union perf_event *event,
-					bool sample_id_all __used)
+					bool sample_id_all __maybe_unused)
 {
 	event->event_type.event_type.event_id =
 		bswap_64(event->event_type.event_type.event_id);
 }
 
 static void perf_event__tracing_data_swap(union perf_event *event,
-					  bool sample_id_all __used)
+					  bool sample_id_all __maybe_unused)
 {
 	event->tracing_data.size = bswap_32(event->tracing_data.size);
 }
@@ -784,7 +795,7 @@ static int flush_sample_queue(struct perf_session *s,
  *      etc...
  */
 static int process_finished_round(struct perf_tool *tool,
-				  union perf_event *event __used,
+				  union perf_event *event __maybe_unused,
 				  struct perf_session *session)
 {
 	int ret = flush_sample_queue(session, tool);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 7a2fbd8855b7..0981bc7a2917 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -170,7 +170,7 @@ static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
 
 static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
 				     u64 ip, char level, char *bf, size_t size,
-				     unsigned int width __used)
+				     unsigned int width __maybe_unused)
 {
 	size_t ret = 0;
 
@@ -205,7 +205,8 @@ struct sort_entry sort_dso = {
 };
 
 static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
-				    size_t size, unsigned int width __used)
+				    size_t size,
+				    unsigned int width __maybe_unused)
 {
 	return _hist_entry__sym_snprintf(self->ms.map, self->ms.sym, self->ip,
 					 self->level, bf, size, width);
@@ -248,7 +249,8 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
 }
 
 static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf,
-				   size_t size, unsigned int width __used)
+					size_t size,
+					unsigned int width __maybe_unused)
 {
 	FILE *fp;
 	char cmd[PATH_MAX + 2], *path = self->srcline, *nl;
@@ -397,7 +399,8 @@ sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right)
 }
 
 static int hist_entry__sym_from_snprintf(struct hist_entry *self, char *bf,
-				    size_t size, unsigned int width __used)
+					size_t size,
+					unsigned int width __maybe_unused)
 {
 	struct addr_map_symbol *from = &self->branch_info->from;
 	return _hist_entry__sym_snprintf(from->map, from->sym, from->addr,
@@ -406,7 +409,8 @@ static int hist_entry__sym_from_snprintf(struct hist_entry *self, char *bf,
 }
 
 static int hist_entry__sym_to_snprintf(struct hist_entry *self, char *bf,
-				    size_t size, unsigned int width __used)
+				       size_t size,
+				       unsigned int width __maybe_unused)
 {
 	struct addr_map_symbol *to = &self->branch_info->to;
 	return _hist_entry__sym_snprintf(to->map, to->sym, to->addr,
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index 199bc4d8905d..32170590892d 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -1,5 +1,5 @@
 #include "util.h"
-#include "string.h"
+#include "linux/string.h"
 
 #define K 1024LL
 /*
@@ -335,3 +335,19 @@ char *rtrim(char *s)
 
 	return s;
 }
+
+/**
+ * memdup - duplicate region of memory
+ * @src: memory region to duplicate
+ * @len: memory region length
+ */
+void *memdup(const void *src, size_t len)
+{
+	void *p;
+
+	p = malloc(len);
+	if (p)
+		memcpy(p, src, len);
+
+	return p;
+}
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 6738ea128c90..259f8f2ea9c9 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -69,8 +69,9 @@ static int read_build_id(void *note_data, size_t note_len, void *bf,
 	return -1;
 }
 
-int filename__read_debuglink(const char *filename __used,
-			     char *debuglink __used, size_t size __used)
+int filename__read_debuglink(const char *filename __maybe_unused,
+			     char *debuglink __maybe_unused,
+			     size_t size __maybe_unused)
 {
 	return -1;
 }
@@ -241,7 +242,8 @@ out:
 	return ret;
 }
 
-int symsrc__init(struct symsrc *ss, struct dso *dso __used, const char *name,
+int symsrc__init(struct symsrc *ss, struct dso *dso __maybe_unused,
+		 const char *name,
 	         enum dso_binary_type type)
 {
 	int fd = open(name, O_RDONLY);
@@ -260,13 +262,13 @@ out_close:
 	return -1;
 }
 
-bool symsrc__possibly_runtime(struct symsrc *ss __used)
+bool symsrc__possibly_runtime(struct symsrc *ss __maybe_unused)
 {
 	/* Assume all sym sources could be a runtime image. */
 	return true;
 }
 
-bool symsrc__has_symtab(struct symsrc *ss __used)
+bool symsrc__has_symtab(struct symsrc *ss __maybe_unused)
 {
 	return false;
 }
@@ -277,17 +279,19 @@ void symsrc__destroy(struct symsrc *ss)
 	close(ss->fd);
 }
 
-int dso__synthesize_plt_symbols(struct dso *dso __used,
-				struct symsrc *ss __used,
-				struct map *map __used,
-				symbol_filter_t filter __used)
+int dso__synthesize_plt_symbols(struct dso *dso __maybe_unused,
+				struct symsrc *ss __maybe_unused,
+				struct map *map __maybe_unused,
+				symbol_filter_t filter __maybe_unused)
 {
 	return 0;
 }
 
-int dso__load_sym(struct dso *dso, struct map *map __used, struct symsrc *ss,
-		  struct symsrc *runtime_ss __used,
-		  symbol_filter_t filter __used, int kmodule __used)
+int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
+		  struct symsrc *ss,
+		  struct symsrc *runtime_ss __maybe_unused,
+		  symbol_filter_t filter __maybe_unused,
+		  int kmodule __maybe_unused)
 {
 	unsigned char *build_id[BUILD_ID_SIZE];
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 753699a20bc8..e2e8c697cffe 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1596,7 +1596,7 @@ void dsos__add(struct list_head *head, struct dso *dso)
 	list_add_tail(&dso->node, head);
 }
 
-static struct dso *dsos__find(struct list_head *head, const char *name)
+struct dso *dsos__find(struct list_head *head, const char *name)
 {
 	struct dso *pos;
 
@@ -1755,7 +1755,7 @@ struct process_args {
 };
 
 static int symbol__in_kernel(void *arg, const char *name,
-			     char type __used, u64 start)
+			     char type __maybe_unused, u64 start)
 {
 	struct process_args *args = arg;
 
@@ -1991,7 +1991,7 @@ int symbol__init(void)
 	if (symbol_conf.initialized)
 		return 0;
 
-	symbol_conf.priv_size = ALIGN(symbol_conf.priv_size, sizeof(u64));
+	symbol_conf.priv_size = PERF_ALIGN(symbol_conf.priv_size, sizeof(u64));
 
 	symbol__elf_init();
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 41a15dac4120..4ff45e30c726 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -21,14 +21,15 @@
 #ifdef HAVE_CPLUS_DEMANGLE
 extern char *cplus_demangle(const char *, int);
 
-static inline char *bfd_demangle(void __used *v, const char *c, int i)
+static inline char *bfd_demangle(void __maybe_unused *v, const char *c, int i)
 {
 	return cplus_demangle(c, i);
 }
 #else
 #ifdef NO_DEMANGLE
-static inline char *bfd_demangle(void __used *v, const char __used *c,
-				 int __used i)
+static inline char *bfd_demangle(void __maybe_unused *v,
+				 const char __maybe_unused *c,
+				 int __maybe_unused i)
 {
 	return NULL;
 }
@@ -294,6 +295,7 @@ static inline void dso__set_loaded(struct dso *dso, enum map_type type)
 void dso__sort_by_name(struct dso *dso, enum map_type type);
 
 void dsos__add(struct list_head *head, struct dso *dso);
+struct dso *dsos__find(struct list_head *head, const char *name);
 struct dso *__dsos__findnew(struct list_head *head, const char *name);
 
 int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter);
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index a5a554efeb50..aa4c860a21d1 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -221,7 +221,7 @@ void print_event(struct pevent *pevent, int cpu, void *data, int size,
 }
 
 void parse_proc_kallsyms(struct pevent *pevent,
-			 char *file, unsigned int size __unused)
+			 char *file, unsigned int size __maybe_unused)
 {
 	unsigned long long addr;
 	char *func;
@@ -253,7 +253,7 @@ void parse_proc_kallsyms(struct pevent *pevent,
 }
 
 void parse_ftrace_printk(struct pevent *pevent,
-			 char *file, unsigned int size __unused)
+			 char *file, unsigned int size __maybe_unused)
 {
 	unsigned long long addr;
 	char *printk;
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 302ff262494c..8715a1006d00 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -35,11 +35,11 @@ static int stop_script_unsupported(void)
 	return 0;
 }
 
-static void process_event_unsupported(union perf_event *event __unused,
-				      struct perf_sample *sample __unused,
-				      struct perf_evsel *evsel __unused,
-				      struct machine *machine __unused,
-				      struct addr_location *al __unused)
+static void process_event_unsupported(union perf_event *event __maybe_unused,
+				      struct perf_sample *sample __maybe_unused,
+				      struct perf_evsel *evsel __maybe_unused,
+				      struct machine *machine __maybe_unused,
+				      struct addr_location *al __maybe_unused)
 {
 }
 
@@ -52,17 +52,19 @@ static void print_python_unsupported_msg(void)
 		"\n  etc.\n");
 }
 
-static int python_start_script_unsupported(const char *script __unused,
-					   int argc __unused,
-					   const char **argv __unused)
+static int python_start_script_unsupported(const char *script __maybe_unused,
+					   int argc __maybe_unused,
+					   const char **argv __maybe_unused)
 {
 	print_python_unsupported_msg();
 
 	return -1;
 }
 
-static int python_generate_script_unsupported(struct pevent *pevent __unused,
-					      const char *outfile __unused)
+static int python_generate_script_unsupported(struct pevent *pevent
+					      __maybe_unused,
+					      const char *outfile
+					      __maybe_unused)
 {
 	print_python_unsupported_msg();
 
@@ -114,17 +116,18 @@ static void print_perl_unsupported_msg(void)
 		"\n  etc.\n");
 }
 
-static int perl_start_script_unsupported(const char *script __unused,
-					 int argc __unused,
-					 const char **argv __unused)
+static int perl_start_script_unsupported(const char *script __maybe_unused,
+					 int argc __maybe_unused,
+					 const char **argv __maybe_unused)
 {
 	print_perl_unsupported_msg();
 
 	return -1;
 }
 
-static int perl_generate_script_unsupported(struct pevent *pevent __unused,
-					    const char *outfile __unused)
+static int perl_generate_script_unsupported(struct pevent *pevent
+					    __maybe_unused,
+					    const char *outfile __maybe_unused)
 {
 	print_perl_unsupported_msg();
 
diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind.c
index 00a42aa8d5c1..958723ba3d2e 100644
--- a/tools/perf/util/unwind.c
+++ b/tools/perf/util/unwind.c
@@ -307,32 +307,36 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
 					 need_unwind_info, arg);
 }
 
-static int access_fpreg(unw_addr_space_t __used as, unw_regnum_t __used num,
-			unw_fpreg_t __used *val, int __used __write,
-			void __used *arg)
+static int access_fpreg(unw_addr_space_t __maybe_unused as,
+			unw_regnum_t __maybe_unused num,
+			unw_fpreg_t __maybe_unused *val,
+			int __maybe_unused __write,
+			void __maybe_unused *arg)
 {
 	pr_err("unwind: access_fpreg unsupported\n");
 	return -UNW_EINVAL;
 }
 
-static int get_dyn_info_list_addr(unw_addr_space_t __used as,
-				  unw_word_t __used *dil_addr,
-				  void __used *arg)
+static int get_dyn_info_list_addr(unw_addr_space_t __maybe_unused as,
+				  unw_word_t __maybe_unused *dil_addr,
+				  void __maybe_unused *arg)
 {
 	return -UNW_ENOINFO;
 }
 
-static int resume(unw_addr_space_t __used as, unw_cursor_t __used *cu,
-		  void __used *arg)
+static int resume(unw_addr_space_t __maybe_unused as,
+		  unw_cursor_t __maybe_unused *cu,
+		  void __maybe_unused *arg)
 {
 	pr_err("unwind: resume unsupported\n");
 	return -UNW_EINVAL;
 }
 
 static int
-get_proc_name(unw_addr_space_t __used as, unw_word_t __used addr,
-		char __used *bufp, size_t __used buf_len,
-		unw_word_t __used *offp, void __used *arg)
+get_proc_name(unw_addr_space_t __maybe_unused as,
+	      unw_word_t __maybe_unused addr,
+		char __maybe_unused *bufp, size_t __maybe_unused buf_len,
+		unw_word_t __maybe_unused *offp, void __maybe_unused *arg)
 {
 	pr_err("unwind: get_proc_name unsupported\n");
 	return -UNW_EINVAL;
@@ -377,7 +381,7 @@ static int reg_value(unw_word_t *valp, struct regs_dump *regs, int id,
 	return 0;
 }
 
-static int access_mem(unw_addr_space_t __used as,
+static int access_mem(unw_addr_space_t __maybe_unused as,
 		      unw_word_t addr, unw_word_t *valp,
 		      int __write, void *arg)
 {
@@ -422,7 +426,7 @@ static int access_mem(unw_addr_space_t __used as,
 	return 0;
 }
 
-static int access_reg(unw_addr_space_t __used as,
+static int access_reg(unw_addr_space_t __maybe_unused as,
 		      unw_regnum_t regnum, unw_word_t *valp,
 		      int __write, void *arg)
 {
@@ -454,9 +458,9 @@ static int access_reg(unw_addr_space_t __used as,
 	return 0;
 }
 
-static void put_unwind_info(unw_addr_space_t __used as,
-			    unw_proc_info_t *pi __used,
-			    void *arg __used)
+static void put_unwind_info(unw_addr_space_t __maybe_unused as,
+			    unw_proc_info_t *pi __maybe_unused,
+			    void *arg __maybe_unused)
 {
 	pr_debug("unwind: put_unwind_info called\n");
 }
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index 919bd6ad8501..a78c8b303bb5 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -22,11 +22,12 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 int unwind__arch_reg_id(int regnum);
 #else
 static inline int
-unwind__get_entries(unwind_entry_cb_t cb __used, void *arg __used,
-		    struct machine *machine __used,
-		    struct thread *thread __used,
-		    u64 sample_uregs __used,
-		    struct perf_sample *data __used)
+unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
+		    void *arg __maybe_unused,
+		    struct machine *machine __maybe_unused,
+		    struct thread *thread __maybe_unused,
+		    u64 sample_uregs __maybe_unused,
+		    struct perf_sample *data __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 67a371355c75..70fa70b535b2 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -70,7 +70,7 @@
 #include <sys/socket.h>
 #include <sys/ioctl.h>
 #include <inttypes.h>
-#include "../../../include/linux/magic.h"
+#include <linux/magic.h>
 #include "types.h"
 #include <sys/ttydefaults.h>
 
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
new file mode 100644
index 000000000000..e60951fcdb12
--- /dev/null
+++ b/tools/perf/util/vdso.c
@@ -0,0 +1,111 @@
+
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <linux/kernel.h>
+
+#include "vdso.h"
+#include "util.h"
+#include "symbol.h"
+#include "linux/string.h"
+
+static bool vdso_found;
+static char vdso_file[] = "/tmp/perf-vdso.so-XXXXXX";
+
+static int find_vdso_map(void **start, void **end)
+{
+	FILE *maps;
+	char line[128];
+	int found = 0;
+
+	maps = fopen("/proc/self/maps", "r");
+	if (!maps) {
+		pr_err("vdso: cannot open maps\n");
+		return -1;
+	}
+
+	while (!found && fgets(line, sizeof(line), maps)) {
+		int m = -1;
+
+		/* We care only about private r-x mappings. */
+		if (2 != sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n",
+				start, end, &m))
+			continue;
+		if (m < 0)
+			continue;
+
+		if (!strncmp(&line[m], VDSO__MAP_NAME,
+			     sizeof(VDSO__MAP_NAME) - 1))
+			found = 1;
+	}
+
+	fclose(maps);
+	return !found;
+}
+
+static char *get_file(void)
+{
+	char *vdso = NULL;
+	char *buf = NULL;
+	void *start, *end;
+	size_t size;
+	int fd;
+
+	if (vdso_found)
+		return vdso_file;
+
+	if (find_vdso_map(&start, &end))
+		return NULL;
+
+	size = end - start;
+
+	buf = memdup(start, size);
+	if (!buf)
+		return NULL;
+
+	fd = mkstemp(vdso_file);
+	if (fd < 0)
+		goto out;
+
+	if (size == (size_t) write(fd, buf, size))
+		vdso = vdso_file;
+
+	close(fd);
+
+ out:
+	free(buf);
+
+	vdso_found = (vdso != NULL);
+	return vdso;
+}
+
+void vdso__exit(void)
+{
+	if (vdso_found)
+		unlink(vdso_file);
+}
+
+struct dso *vdso__dso_findnew(struct list_head *head)
+{
+	struct dso *dso = dsos__find(head, VDSO__MAP_NAME);
+
+	if (!dso) {
+		char *file;
+
+		file = get_file();
+		if (!file)
+			return NULL;
+
+		dso = dso__new(VDSO__MAP_NAME);
+		if (dso != NULL) {
+			dsos__add(head, dso);
+			dso__set_long_name(dso, file);
+		}
+	}
+
+	return dso;
+}
diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h
new file mode 100644
index 000000000000..0f76e7caf6f8
--- /dev/null
+++ b/tools/perf/util/vdso.h
@@ -0,0 +1,18 @@
+#ifndef __PERF_VDSO__
+#define __PERF_VDSO__
+
+#include <linux/types.h>
+#include <string.h>
+#include <stdbool.h>
+
+#define VDSO__MAP_NAME "[vdso]"
+
+static inline bool is_vdso_map(const char *filename)
+{
+	return !strcmp(filename, VDSO__MAP_NAME);
+}
+
+struct dso *vdso__dso_findnew(struct list_head *head);
+void vdso__exit(void);
+
+#endif /* __PERF_VDSO__ */
diff --git a/tools/perf/util/wrapper.c b/tools/perf/util/wrapper.c
index 73e900edb5a2..19f15b650703 100644
--- a/tools/perf/util/wrapper.c
+++ b/tools/perf/util/wrapper.c
@@ -7,7 +7,8 @@
  * There's no pack memory to release - but stay close to the Git
  * version so wrap this away:
  */
-static inline void release_pack_memory(size_t size __used, int flag __used)
+static inline void release_pack_memory(size_t size __maybe_unused,
+				       int flag __maybe_unused)
 {
 }