Merge tag 'perf-core-for-mingo-4.13-20170719' 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:

User visible changes:

- Allow adding and removing fields to the default 'perf script' columns,
  using + or - as field prefixes to do so (Andi Kleen)

- Display titles in left frame in the annotate browser (Jin Yao)

- Allow resolving the DSO name with 'perf script -F brstack{sym,off},dso'
  (Mark Santaniello)

- Support function filtering in 'perf ftrace' (Namhyung Kim)

- Allow specifying function call depth in 'perf ftrace' (Namhyumg Kim)

Infrastructure changes:

- Adopt __noreturn, __printf, __scanf, noinline, __packed and __aligned
  __alignment__(()) markers, to make the tools/ source code base to be
  more compact and look more like kernel code (Arnaldo Carvalho de Melo)

- Remove unnecessary check in annotate_browser_write() (Jin Yao)

- Return arch from symbol__disassemble() so that callers, such as
  the annotate TUI browser to use arch specific formattings, such
  as the upcoming instruction micro-op fusion on Intel Core (Jin Yao)

- Remove superfluous check before use in the coresight code base (Kim
  Phillips)

- Remove unused SAMPLE_SIZE defines and BTS priv array (Kim Phillips)

- Error handling fix/tidy ups in 'perf config' (Taeung Song)

- Avoid error in the BPF proggie built with clang in 'perf test llvm'
  when PROFILE_ALL_BRANCHES is set (Wang Nan)

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

35 files changed, 482 insertions, 161 deletions

diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt
index 6e6a8b22c859..721a447f046e 100644
--- a/tools/perf/Documentation/perf-ftrace.txt
+++ b/tools/perf/Documentation/perf-ftrace.txt
@@ -48,6 +48,39 @@ OPTIONS
 	Ranges of CPUs are specified with -: 0-2.
 	Default is to trace on all online CPUs.
 
+-T::
+--trace-funcs=::
+	Only trace functions given by the argument.  Multiple functions
+	can be given by using this option more than once.  The function
+	argument also can be a glob pattern.  It will be passed to
+	'set_ftrace_filter' in tracefs.
+
+-N::
+--notrace-funcs=::
+	Do not trace functions given by the argument.  Like -T option,
+	this can be used more than once to specify multiple functions
+	(or glob patterns).  It will be passed to 'set_ftrace_notrace'
+	in tracefs.
+
+-G::
+--graph-funcs=::
+	Set graph filter on the given function (or a glob pattern).
+	This is useful for the function_graph tracer only and enables
+	tracing for functions executed from the given function.
+	This can be used more than once to specify multiple functions.
+	It will be passed to 'set_graph_function' in tracefs.
+
+-g::
+--nograph-funcs=::
+	Set graph notrace filter on the given function (or a glob pattern).
+	Like -G option, this is useful for the function_graph tracer only
+	and disables tracing for function executed from the given function.
+	This can be used more than once to specify multiple functions.
+	It will be passed to 'set_graph_notrace' in tracefs.
+
+-D::
+--graph-depth=::
+	Set max depth for function graph tracer to follow
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 3517e204a2b3..e2468ed6a307 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -116,7 +116,7 @@ OPTIONS
 --fields::
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
-        srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn,
+        srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn, brstackoff,
         callindent, insn, insnlen. Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace
@@ -130,6 +130,14 @@ OPTIONS
 	i.e., the specified fields apply to all event types if the type string
 	is not given.
 
+	In addition to overriding fields, it is also possible to add or remove
+	fields from the defaults. For example
+
+		-F -cpu,+insn
+
+	removes the cpu field and adds the insn field. Adding/removing fields
+	cannot be mixed with normal overriding.
+
 	The arguments are processed in the order received. A later usage can
 	reset a prior request. e.g.:
 
@@ -203,6 +211,8 @@ OPTIONS
 	is printed. This is the full execution path leading to the sample. This is only supported when the
 	sample was recorded with perf record -b or -j any.
 
+	The brstackoff field will print an offset into a specific dso/binary.
+
 -k::
 --vmlinux=<file>::
         vmlinux pathname
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 29361d9b635a..7ce3d1a25133 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -17,6 +17,7 @@
 
 #include <api/fs/fs.h>
 #include <linux/bitops.h>
+#include <linux/compiler.h>
 #include <linux/coresight-pmu.h>
 #include <linux/kernel.h>
 #include <linux/log2.h>
@@ -202,19 +203,18 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 		pr_debug2("%s snapshot size: %zu\n", CORESIGHT_ETM_PMU_NAME,
 			  opts->auxtrace_snapshot_size);
 
-	if (cs_etm_evsel) {
-		/*
-		 * To obtain the auxtrace buffer file descriptor, the auxtrace
-		 * event must come first.
-		 */
-		perf_evlist__to_front(evlist, cs_etm_evsel);
-		/*
-		 * In the case of per-cpu mmaps, we need the CPU on the
-		 * AUX event.
-		 */
-		if (!cpu_map__empty(cpus))
-			perf_evsel__set_sample_bit(cs_etm_evsel, CPU);
-	}
+	/*
+	 * To obtain the auxtrace buffer file descriptor, the auxtrace
+	 * event must come first.
+	 */
+	perf_evlist__to_front(evlist, cs_etm_evsel);
+
+	/*
+	 * In the case of per-cpu mmaps, we need the CPU on the
+	 * AUX event.
+	 */
+	if (!cpu_map__empty(cpus))
+		perf_evsel__set_sample_bit(cs_etm_evsel, CPU);
 
 	/* Add dummy event to keep tracking */
 	if (opts->full_auxtrace) {
@@ -583,8 +583,7 @@ static FILE *cs_device__open_file(const char *name)
 
 }
 
-static __attribute__((format(printf, 2, 3)))
-int cs_device__print_file(const char *name, const char *fmt, ...)
+static int __printf(2, 3) cs_device__print_file(const char *name, const char *fmt, ...)
 {
 	va_list args;
 	FILE *file;
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index af2bce7a2cd6..781df40b2966 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -35,10 +35,6 @@
 #define KiB_MASK(x) (KiB(x) - 1)
 #define MiB_MASK(x) (MiB(x) - 1)
 
-#define INTEL_BTS_DFLT_SAMPLE_SIZE	KiB(4)
-
-#define INTEL_BTS_MAX_SAMPLE_SIZE	KiB(60)
-
 struct intel_bts_snapshot_ref {
 	void	*ref_buf;
 	size_t	ref_offset;
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index f630de0206a1..6fe667b3269e 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -40,10 +40,6 @@
 #define KiB_MASK(x) (KiB(x) - 1)
 #define MiB_MASK(x) (MiB(x) - 1)
 
-#define INTEL_PT_DEFAULT_SAMPLE_SIZE	KiB(4)
-
-#define INTEL_PT_MAX_SAMPLE_SIZE	KiB(60)
-
 #define INTEL_PT_PSB_PERIOD_NEAR	256
 
 struct intel_pt_snapshot_ref {
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 27de0c8c5c19..469d65b21122 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -700,7 +700,7 @@ static inline uint32_t lfsr_32(uint32_t lfsr)
  * kernel (KSM, zero page, etc.) cannot optimize away RAM
  * accesses:
  */
-static inline u64 access_data(u64 *data __attribute__((unused)), u64 val)
+static inline u64 access_data(u64 *data, u64 val)
 {
 	if (g->p.data_reads)
 		val += *data;
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
index 80668fa7556e..ece45582a48d 100644
--- a/tools/perf/builtin-config.c
+++ b/tools/perf/builtin-config.c
@@ -156,7 +156,7 @@ static int parse_config_arg(char *arg, char **var, char **value)
 
 int cmd_config(int argc, const char **argv)
 {
-	int i, ret = 0;
+	int i, ret = -1;
 	struct perf_config_set *set;
 	char *user_config = mkpath("%s/.perfconfig", getenv("HOME"));
 	const char *config_filename;
@@ -186,10 +186,8 @@ int cmd_config(int argc, const char **argv)
 	 * because of reinitializing with options config file location.
 	 */
 	set = perf_config_set__new();
-	if (!set) {
-		ret = -1;
+	if (!set)
 		goto out_err;
-	}
 
 	switch (actions) {
 	case ACTION_LIST:
@@ -197,41 +195,54 @@ int cmd_config(int argc, const char **argv)
 			pr_err("Error: takes no arguments\n");
 			parse_options_usage(config_usage, config_options, "l", 1);
 		} else {
-			ret = show_config(set);
-			if (ret < 0)
+			if (show_config(set) < 0) {
 				pr_err("Nothing configured, "
 				       "please check your %s \n", config_filename);
+				goto out_err;
+			}
 		}
 		break;
 	default:
-		if (argc) {
-			for (i = 0; argv[i]; i++) {
-				char *var, *value;
-				char *arg = strdup(argv[i]);
-
-				if (!arg) {
-					pr_err("%s: strdup failed\n", __func__);
-					ret = -1;
-					break;
-				}
+		if (!argc) {
+			usage_with_options(config_usage, config_options);
+			break;
+		}
 
-				if (parse_config_arg(arg, &var, &value) < 0) {
-					free(arg);
-					ret = -1;
-					break;
-				}
+		for (i = 0; argv[i]; i++) {
+			char *var, *value;
+			char *arg = strdup(argv[i]);
+
+			if (!arg) {
+				pr_err("%s: strdup failed\n", __func__);
+				goto out_err;
+			}
 
-				if (value == NULL)
-					ret = show_spec_config(set, var);
-				else
-					ret = set_config(set, config_filename, var, value);
+			if (parse_config_arg(arg, &var, &value) < 0) {
 				free(arg);
+				goto out_err;
 			}
-		} else
-			usage_with_options(config_usage, config_options);
+
+			if (value == NULL) {
+				if (show_spec_config(set, var) < 0) {
+					pr_err("%s is not configured: %s\n",
+					       var, config_filename);
+					free(arg);
+					goto out_err;
+				}
+			} else {
+				if (set_config(set, config_filename, var, value) < 0) {
+					pr_err("Failed to set '%s=%s' on %s\n",
+					       var, value, config_filename);
+					free(arg);
+					goto out_err;
+				}
+			}
+			free(arg);
+		}
 	}
 
-	perf_config_set__delete(set);
+	ret = 0;
 out_err:
+	perf_config_set__delete(set);
 	return ret;
 }
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 9e0b35cd0eea..dd26c62c9893 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -28,9 +28,19 @@
 #define DEFAULT_TRACER  "function_graph"
 
 struct perf_ftrace {
-	struct perf_evlist *evlist;
-	struct target target;
-	const char *tracer;
+	struct perf_evlist	*evlist;
+	struct target		target;
+	const char		*tracer;
+	struct list_head	filters;
+	struct list_head	notrace;
+	struct list_head	graph_funcs;
+	struct list_head	nograph_funcs;
+	int			graph_depth;
+};
+
+struct filter_entry {
+	struct list_head	list;
+	char			name[];
 };
 
 static bool done;
@@ -61,6 +71,7 @@ static int __write_tracing_file(const char *name, const char *val, bool append)
 	int fd, ret = -1;
 	ssize_t size = strlen(val);
 	int flags = O_WRONLY;
+	char errbuf[512];
 
 	file = get_tracing_file(name);
 	if (!file) {
@@ -75,14 +86,16 @@ static int __write_tracing_file(const char *name, const char *val, bool append)
 
 	fd = open(file, flags);
 	if (fd < 0) {
-		pr_debug("cannot open tracing file: %s\n", name);
+		pr_debug("cannot open tracing file: %s: %s\n",
+			 name, str_error_r(errno, errbuf, sizeof(errbuf)));
 		goto out;
 	}
 
 	if (write(fd, val, size) == size)
 		ret = 0;
 	else
-		pr_debug("write '%s' to tracing/%s failed\n", val, name);
+		pr_debug("write '%s' to tracing/%s failed: %s\n",
+			 val, name, str_error_r(errno, errbuf, sizeof(errbuf)));
 
 	close(fd);
 out:
@@ -101,6 +114,7 @@ static int append_tracing_file(const char *name, const char *val)
 }
 
 static int reset_tracing_cpu(void);
+static void reset_tracing_filters(void);
 
 static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused)
 {
@@ -116,6 +130,10 @@ static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused)
 	if (reset_tracing_cpu() < 0)
 		return -1;
 
+	if (write_tracing_file("max_graph_depth", "0") < 0)
+		return -1;
+
+	reset_tracing_filters();
 	return 0;
 }
 
@@ -181,6 +199,68 @@ static int reset_tracing_cpu(void)
 	return ret;
 }
 
+static int __set_tracing_filter(const char *filter_file, struct list_head *funcs)
+{
+	struct filter_entry *pos;
+
+	list_for_each_entry(pos, funcs, list) {
+		if (append_tracing_file(filter_file, pos->name) < 0)
+			return -1;
+	}
+
+	return 0;
+}
+
+static int set_tracing_filters(struct perf_ftrace *ftrace)
+{
+	int ret;
+
+	ret = __set_tracing_filter("set_ftrace_filter", &ftrace->filters);
+	if (ret < 0)
+		return ret;
+
+	ret = __set_tracing_filter("set_ftrace_notrace", &ftrace->notrace);
+	if (ret < 0)
+		return ret;
+
+	ret = __set_tracing_filter("set_graph_function", &ftrace->graph_funcs);
+	if (ret < 0)
+		return ret;
+
+	/* old kernels do not have this filter */
+	__set_tracing_filter("set_graph_notrace", &ftrace->nograph_funcs);
+
+	return ret;
+}
+
+static void reset_tracing_filters(void)
+{
+	write_tracing_file("set_ftrace_filter", " ");
+	write_tracing_file("set_ftrace_notrace", " ");
+	write_tracing_file("set_graph_function", " ");
+	write_tracing_file("set_graph_notrace", " ");
+}
+
+static int set_tracing_depth(struct perf_ftrace *ftrace)
+{
+	char buf[16];
+
+	if (ftrace->graph_depth == 0)
+		return 0;
+
+	if (ftrace->graph_depth < 0) {
+		pr_err("invalid graph depth: %d\n", ftrace->graph_depth);
+		return -1;
+	}
+
+	snprintf(buf, sizeof(buf), "%d", ftrace->graph_depth);
+
+	if (write_tracing_file("max_graph_depth", buf) < 0)
+		return -1;
+
+	return 0;
+}
+
 static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
 {
 	char *trace_file;
@@ -223,11 +303,23 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
 		goto out_reset;
 	}
 
+	if (set_tracing_filters(ftrace) < 0) {
+		pr_err("failed to set tracing filters\n");
+		goto out_reset;
+	}
+
+	if (set_tracing_depth(ftrace) < 0) {
+		pr_err("failed to set graph depth\n");
+		goto out_reset;
+	}
+
 	if (write_tracing_file("current_tracer", ftrace->tracer) < 0) {
 		pr_err("failed to set current_tracer to %s\n", ftrace->tracer);
 		goto out_reset;
 	}
 
+	setup_pager();
+
 	trace_file = get_tracing_file("trace_pipe");
 	if (!trace_file) {
 		pr_err("failed to open trace_pipe\n");
@@ -251,8 +343,6 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
 		goto out_close_fd;
 	}
 
-	setup_pager();
-
 	perf_evlist__start_workload(ftrace->evlist);
 
 	while (!done) {
@@ -307,6 +397,32 @@ static int perf_ftrace_config(const char *var, const char *value, void *cb)
 	return -1;
 }
 
+static int parse_filter_func(const struct option *opt, const char *str,
+			     int unset __maybe_unused)
+{
+	struct list_head *head = opt->value;
+	struct filter_entry *entry;
+
+	entry = malloc(sizeof(*entry) + strlen(str) + 1);
+	if (entry == NULL)
+		return -ENOMEM;
+
+	strcpy(entry->name, str);
+	list_add_tail(&entry->list, head);
+
+	return 0;
+}
+
+static void delete_filter_func(struct list_head *head)
+{
+	struct filter_entry *pos, *tmp;
+
+	list_for_each_entry_safe(pos, tmp, head, list) {
+		list_del(&pos->list);
+		free(pos);
+	}
+}
+
 int cmd_ftrace(int argc, const char **argv)
 {
 	int ret;
@@ -330,9 +446,24 @@ int cmd_ftrace(int argc, const char **argv)
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('C', "cpu", &ftrace.target.cpu_list, "cpu",
 		    "list of cpus to monitor"),
+	OPT_CALLBACK('T', "trace-funcs", &ftrace.filters, "func",
+		     "trace given functions only", parse_filter_func),
+	OPT_CALLBACK('N', "notrace-funcs", &ftrace.notrace, "func",
+		     "do not trace given functions", parse_filter_func),
+	OPT_CALLBACK('G', "graph-funcs", &ftrace.graph_funcs, "func",
+		     "Set graph filter on given functions", parse_filter_func),
+	OPT_CALLBACK('g', "nograph-funcs", &ftrace.nograph_funcs, "func",
+		     "Set nograph filter on given functions", parse_filter_func),
+	OPT_INTEGER('D', "graph-depth", &ftrace.graph_depth,
+		    "Max depth for function graph tracer"),
 	OPT_END()
 	};
 
+	INIT_LIST_HEAD(&ftrace.filters);
+	INIT_LIST_HEAD(&ftrace.notrace);
+	INIT_LIST_HEAD(&ftrace.graph_funcs);
+	INIT_LIST_HEAD(&ftrace.nograph_funcs);
+
 	ret = perf_config(perf_ftrace_config, &ftrace);
 	if (ret < 0)
 		return -1;
@@ -348,12 +479,14 @@ int cmd_ftrace(int argc, const char **argv)
 
 		target__strerror(&ftrace.target, ret, errbuf, 512);
 		pr_err("%s\n", errbuf);
-		return -EINVAL;
+		goto out_delete_filters;
 	}
 
 	ftrace.evlist = perf_evlist__new();
-	if (ftrace.evlist == NULL)
-		return -ENOMEM;
+	if (ftrace.evlist == NULL) {
+		ret = -ENOMEM;
+		goto out_delete_filters;
+	}
 
 	ret = perf_evlist__create_maps(ftrace.evlist, &ftrace.target);
 	if (ret < 0)
@@ -364,5 +497,11 @@ int cmd_ftrace(int argc, const char **argv)
 out_delete_evlist:
 	perf_evlist__delete(ftrace.evlist);
 
+out_delete_filters:
+	delete_filter_func(&ftrace.filters);
+	delete_filter_func(&ftrace.notrace);
+	delete_filter_func(&ftrace.graph_funcs);
+	delete_filter_func(&ftrace.nograph_funcs);
+
 	return ret;
 }
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 4761b0d7fcb5..db5261c3f719 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -85,6 +85,7 @@ enum perf_output_field {
 	PERF_OUTPUT_INSN	    = 1U << 21,
 	PERF_OUTPUT_INSNLEN	    = 1U << 22,
 	PERF_OUTPUT_BRSTACKINSN	    = 1U << 23,
+	PERF_OUTPUT_BRSTACKOFF	    = 1U << 24,
 };
 
 struct output_option {
@@ -115,6 +116,7 @@ struct output_option {
 	{.str = "insn", .field = PERF_OUTPUT_INSN},
 	{.str = "insnlen", .field = PERF_OUTPUT_INSNLEN},
 	{.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN},
+	{.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF},
 };
 
 /* default set to maintain compatibility with current format */
@@ -298,10 +300,10 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		       "selected.\n");
 		return -EINVAL;
 	}
-	if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
-		pr_err("Display of DSO requested but neither sample IP nor "
-			   "sample address\nis selected. Hence, no addresses to convert "
-		       "to DSO.\n");
+	if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR) &&
+	    !PRINT_FIELD(BRSTACK) && !PRINT_FIELD(BRSTACKSYM) && !PRINT_FIELD(BRSTACKOFF)) {
+		pr_err("Display of DSO requested but no address to convert.  Select\n"
+		       "sample IP, sample address, brstack, brstacksym, or brstackoff.\n");
 		return -EINVAL;
 	}
 	if (PRINT_FIELD(SRCLINE) && !PRINT_FIELD(IP)) {
@@ -514,18 +516,43 @@ mispred_str(struct branch_entry *br)
 	return br->flags.predicted ? 'P' : 'M';
 }
 
-static void print_sample_brstack(struct perf_sample *sample)
+static void print_sample_brstack(struct perf_sample *sample,
+				 struct thread *thread,
+				 struct perf_event_attr *attr)
 {
 	struct branch_stack *br = sample->branch_stack;
-	u64 i;
+	struct addr_location alf, alt;
+	u64 i, from, to;
 
 	if (!(br && br->nr))
 		return;
 
 	for (i = 0; i < br->nr; i++) {
-		printf(" 0x%"PRIx64"/0x%"PRIx64"/%c/%c/%c/%d ",
-			br->entries[i].from,
-			br->entries[i].to,
+		from = br->entries[i].from;
+		to   = br->entries[i].to;
+
+		if (PRINT_FIELD(DSO)) {
+			memset(&alf, 0, sizeof(alf));
+			memset(&alt, 0, sizeof(alt));
+			thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf);
+			thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
+		}
+
+		printf("0x%"PRIx64, from);
+		if (PRINT_FIELD(DSO)) {
+			printf("(");
+			map__fprintf_dsoname(alf.map, stdout);
+			printf(")");
+		}
+
+		printf("/0x%"PRIx64, to);
+		if (PRINT_FIELD(DSO)) {
+			printf("(");
+			map__fprintf_dsoname(alt.map, stdout);
+			printf(")");
+		}
+
+		printf("/%c/%c/%c/%d ",
 			mispred_str( br->entries + i),
 			br->entries[i].flags.in_tx? 'X' : '-',
 			br->entries[i].flags.abort? 'A' : '-',
@@ -534,7 +561,8 @@ static void print_sample_brstack(struct perf_sample *sample)
 }
 
 static void print_sample_brstacksym(struct perf_sample *sample,
-				    struct thread *thread)
+				    struct thread *thread,
+				    struct perf_event_attr *attr)
 {
 	struct branch_stack *br = sample->branch_stack;
 	struct addr_location alf, alt;
@@ -559,8 +587,18 @@ static void print_sample_brstacksym(struct perf_sample *sample,
 			alt.sym = map__find_symbol(alt.map, alt.addr);
 
 		symbol__fprintf_symname_offs(alf.sym, &alf, stdout);
+		if (PRINT_FIELD(DSO)) {
+			printf("(");
+			map__fprintf_dsoname(alf.map, stdout);
+			printf(")");
+		}
 		putchar('/');
 		symbol__fprintf_symname_offs(alt.sym, &alt, stdout);
+		if (PRINT_FIELD(DSO)) {
+			printf("(");
+			map__fprintf_dsoname(alt.map, stdout);
+			printf(")");
+		}
 		printf("/%c/%c/%c/%d ",
 			mispred_str( br->entries + i),
 			br->entries[i].flags.in_tx? 'X' : '-',
@@ -569,6 +607,51 @@ static void print_sample_brstacksym(struct perf_sample *sample,
 	}
 }
 
+static void print_sample_brstackoff(struct perf_sample *sample,
+				    struct thread *thread,
+				    struct perf_event_attr *attr)
+{
+	struct branch_stack *br = sample->branch_stack;
+	struct addr_location alf, alt;
+	u64 i, from, to;
+
+	if (!(br && br->nr))
+		return;
+
+	for (i = 0; i < br->nr; i++) {
+
+		memset(&alf, 0, sizeof(alf));
+		memset(&alt, 0, sizeof(alt));
+		from = br->entries[i].from;
+		to   = br->entries[i].to;
+
+		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf);
+		if (alf.map && !alf.map->dso->adjust_symbols)
+			from = map__map_ip(alf.map, from);
+
+		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
+		if (alt.map && !alt.map->dso->adjust_symbols)
+			to = map__map_ip(alt.map, to);
+
+		printf("0x%"PRIx64, from);
+		if (PRINT_FIELD(DSO)) {
+			printf("(");
+			map__fprintf_dsoname(alf.map, stdout);
+			printf(")");
+		}
+		printf("/0x%"PRIx64, to);
+		if (PRINT_FIELD(DSO)) {
+			printf("(");
+			map__fprintf_dsoname(alt.map, stdout);
+			printf(")");
+		}
+		printf("/%c/%c/%c/%d ",
+			mispred_str(br->entries + i),
+			br->entries[i].flags.in_tx ? 'X' : '-',
+			br->entries[i].flags.abort ? 'A' : '-',
+			br->entries[i].flags.cycles);
+	}
+}
 #define MAXBB 16384UL
 
 static int grab_bb(u8 *buffer, u64 start, u64 end,
@@ -1187,9 +1270,11 @@ static void process_event(struct perf_script *script,
 		print_sample_iregs(sample, attr);
 
 	if (PRINT_FIELD(BRSTACK))
-		print_sample_brstack(sample);
+		print_sample_brstack(sample, thread, attr);
 	else if (PRINT_FIELD(BRSTACKSYM))
-		print_sample_brstacksym(sample, thread);
+		print_sample_brstacksym(sample, thread, attr);
+	else if (PRINT_FIELD(BRSTACKOFF))
+		print_sample_brstackoff(sample, thread, attr);
 
 	if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
 		print_sample_bpf_output(sample);
@@ -1727,6 +1812,7 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
 	int rc = 0;
 	char *str = strdup(arg);
 	int type = -1;
+	enum { DEFAULT, SET, ADD, REMOVE } change = DEFAULT;
 
 	if (!str)
 		return -ENOMEM;
@@ -1772,6 +1858,10 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
 			goto out;
 		}
 
+		/* Don't override defaults for +- */
+		if (strchr(str, '+') || strchr(str, '-'))
+			goto parse;
+
 		if (output_set_by_user())
 			pr_warning("Overriding previous field request for all events.\n");
 
@@ -1782,13 +1872,30 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
 		}
 	}
 
+parse:
 	for (tok = strtok_r(tok, ",", &strtok_saveptr); tok; tok = strtok_r(NULL, ",", &strtok_saveptr)) {
+		if (*tok == '+') {
+			if (change == SET)
+				goto out_badmix;
+			change = ADD;
+			tok++;
+		} else if (*tok == '-') {
+			if (change == SET)
+				goto out_badmix;
+			change = REMOVE;
+			tok++;
+		} else {
+			if (change != SET && change != DEFAULT)
+				goto out_badmix;
+			change = SET;
+		}
+
 		for (i = 0; i < imax; ++i) {
 			if (strcmp(tok, all_output_options[i].str) == 0)
 				break;
 		}
 		if (i == imax && strcmp(tok, "flags") == 0) {
-			print_flags = true;
+			print_flags = change == REMOVE ? false : true;
 			continue;
 		}
 		if (i == imax) {
@@ -1805,8 +1912,12 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
 				if (output[j].invalid_fields & all_output_options[i].field) {
 					pr_warning("\'%s\' not valid for %s events. Ignoring.\n",
 						   all_output_options[i].str, event_type(j));
-				} else
-					output[j].fields |= all_output_options[i].field;
+				} else {
+					if (change == REMOVE)
+						output[j].fields &= ~all_output_options[i].field;
+					else
+						output[j].fields |= all_output_options[i].field;
+				}
 			}
 		} else {
 			if (output[type].invalid_fields & all_output_options[i].field) {
@@ -1826,7 +1937,11 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
 				 "Events will not be displayed.\n", event_type(type));
 		}
 	}
+	goto out;
 
+out_badmix:
+	fprintf(stderr, "Cannot mix +-field with overridden fields\n");
+	rc = -EINVAL;
 out:
 	free(str);
 	return rc;
@@ -2444,6 +2559,7 @@ int cmd_script(int argc, const char **argv)
 		     symbol__config_symfs),
 	OPT_CALLBACK('F', "fields", NULL, "str",
 		     "comma separated output fields prepend with 'type:'. "
+		     "+field to add and -field to remove."
 		     "Valid types: hw,sw,trace,raw. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
 		     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 10b6362ca0bf..2bcfa46913c8 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -134,7 +134,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 		return err;
 	}
 
-	err = symbol__disassemble(sym, map, NULL, 0);
+	err = symbol__disassemble(sym, map, NULL, 0, NULL);
 	if (err == 0) {
 out_assign:
 		top->sym_filter_entry = he;
diff --git a/tools/perf/jvmti/jvmti_agent.h b/tools/perf/jvmti/jvmti_agent.h
index bedf5d0ba9ff..c53a41f48b63 100644
--- a/tools/perf/jvmti/jvmti_agent.h
+++ b/tools/perf/jvmti/jvmti_agent.h
@@ -5,8 +5,6 @@
 #include <stdint.h>
 #include <jvmti.h>
 
-#define __unused __attribute__((unused))
-
 #if defined(__cplusplus)
 extern "C" {
 #endif
diff --git a/tools/perf/jvmti/libjvmti.c b/tools/perf/jvmti/libjvmti.c
index 5612641c69b4..6d710904c837 100644
--- a/tools/perf/jvmti/libjvmti.c
+++ b/tools/perf/jvmti/libjvmti.c
@@ -1,3 +1,4 @@
+#include <linux/compiler.h>
 #include <sys/types.h>
 #include <stdio.h>
 #include <string.h>
@@ -238,7 +239,7 @@ code_generated_cb(jvmtiEnv *jvmti,
 }
 
 JNIEXPORT jint JNICALL
-Agent_OnLoad(JavaVM *jvm, char *options, void *reserved __unused)
+Agent_OnLoad(JavaVM *jvm, char *options, void *reserved __maybe_unused)
 {
 	jvmtiEventCallbacks cb;
 	jvmtiCapabilities caps1;
@@ -313,7 +314,7 @@ Agent_OnLoad(JavaVM *jvm, char *options, void *reserved __unused)
 }
 
 JNIEXPORT void JNICALL
-Agent_OnUnload(JavaVM *jvm __unused)
+Agent_OnUnload(JavaVM *jvm __maybe_unused)
 {
 	int ret;
 
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index baa073f38334..bd0aabb2bd0f 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -48,10 +48,6 @@
 #include "json.h"
 #include "jevents.h"
 
-#ifndef __maybe_unused
-#define __maybe_unused                  __attribute__((unused))
-#endif
-
 int verbose;
 char *prog;
 
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index 8ba2c4618fe9..39bbb97cd30a 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -62,8 +62,7 @@ static void __test_function(volatile long *ptr)
 }
 #endif
 
-__attribute__ ((noinline))
-static int test_function(void)
+static noinline int test_function(void)
 {
 	__test_function(&the_var);
 	the_var++;
diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c
index 89f92fa67cc4..3b1ac6f31b15 100644
--- a/tools/perf/tests/bp_signal_overflow.c
+++ b/tools/perf/tests/bp_signal_overflow.c
@@ -28,8 +28,7 @@
 
 static int overflows;
 
-__attribute__ ((noinline))
-static int test_function(void)
+static noinline int test_function(void)
 {
 	return time(NULL);
 }
diff --git a/tools/perf/tests/bpf-script-test-prologue.c b/tools/perf/tests/bpf-script-test-prologue.c
index 7230e62c70fc..b4ebc75e25ae 100644
--- a/tools/perf/tests/bpf-script-test-prologue.c
+++ b/tools/perf/tests/bpf-script-test-prologue.c
@@ -10,6 +10,15 @@
 
 #include <uapi/linux/fs.h>
 
+/*
+ * If CONFIG_PROFILE_ALL_BRANCHES is selected,
+ * 'if' is redefined after include kernel header.
+ * Recover 'if' for BPF object code.
+ */
+#ifdef if
+# undef if
+#endif
+
 #define FMODE_READ		0x1
 #define FMODE_WRITE		0x2
 
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index dfe5c89e2049..3e56d08f7995 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -76,8 +76,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	return strcmp((const char *) symbol, funcs[idx]);
 }
 
-__attribute__ ((noinline))
-static int unwind_thread(struct thread *thread)
+static noinline int unwind_thread(struct thread *thread)
 {
 	struct perf_sample sample;
 	unsigned long cnt = 0;
@@ -108,8 +107,7 @@ static int unwind_thread(struct thread *thread)
 
 static int global_unwind_retval = -INT_MAX;
 
-__attribute__ ((noinline))
-static int compare(void *p1, void *p2)
+static noinline int compare(void *p1, void *p2)
 {
 	/* Any possible value should be 'thread' */
 	struct thread *thread = *(struct thread **)p1;
@@ -128,8 +126,7 @@ static int compare(void *p1, void *p2)
 	return p1 - p2;
 }
 
-__attribute__ ((noinline))
-static int krava_3(struct thread *thread)
+static noinline int krava_3(struct thread *thread)
 {
 	struct thread *array[2] = {thread, thread};
 	void *fp = &bsearch;
@@ -147,14 +144,12 @@ static int krava_3(struct thread *thread)
 	return global_unwind_retval;
 }
 
-__attribute__ ((noinline))
-static int krava_2(struct thread *thread)
+static noinline int krava_2(struct thread *thread)
 {
 	return krava_3(thread);
 }
 
-__attribute__ ((noinline))
-static int krava_1(struct thread *thread)
+static noinline int krava_1(struct thread *thread)
 {
 	return krava_2(thread);
 }
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index d990ad08a3c6..27f41f28dcb4 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -46,12 +46,15 @@ static struct annotate_browser_opt {
 	.jump_arrows	= true,
 };
 
+struct arch;
+
 struct annotate_browser {
 	struct ui_browser b;
 	struct rb_root	  entries;
 	struct rb_node	  *curr_hot;
 	struct disasm_line  *selection;
 	struct disasm_line  **offsets;
+	struct arch	    *arch;
 	int		    nr_events;
 	u64		    start;
 	int		    nr_asm_entries;
@@ -125,43 +128,57 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 	int i, pcnt_width = annotate_browser__pcnt_width(ab);
 	double percent_max = 0.0;
 	char bf[256];
+	bool show_title = false;
 
 	for (i = 0; i < ab->nr_events; i++) {
 		if (bdl->samples[i].percent > percent_max)
 			percent_max = bdl->samples[i].percent;
 	}
 
+	if ((row == 0) && (dl->offset == -1 || percent_max == 0.0)) {
+		if (ab->have_cycles) {
+			if (dl->ipc == 0.0 && dl->cycles == 0)
+				show_title = true;
+		} else
+			show_title = true;
+	}
+
 	if (dl->offset != -1 && percent_max != 0.0) {
-		if (percent_max != 0.0) {
-			for (i = 0; i < ab->nr_events; i++) {
-				ui_browser__set_percent_color(browser,
-							bdl->samples[i].percent,
-							current_entry);
-				if (annotate_browser__opts.show_total_period) {
-					ui_browser__printf(browser, "%6" PRIu64 " ",
-							   bdl->samples[i].nr);
-				} else {
-					ui_browser__printf(browser, "%6.2f ",
-							   bdl->samples[i].percent);
-				}
+		for (i = 0; i < ab->nr_events; i++) {
+			ui_browser__set_percent_color(browser,
+						bdl->samples[i].percent,
+						current_entry);
+			if (annotate_browser__opts.show_total_period) {
+				ui_browser__printf(browser, "%6" PRIu64 " ",
+						   bdl->samples[i].nr);
+			} else {
+				ui_browser__printf(browser, "%6.2f ",
+						   bdl->samples[i].percent);
 			}
-		} else {
-			ui_browser__write_nstring(browser, " ", 7 * ab->nr_events);
 		}
 	} else {
 		ui_browser__set_percent_color(browser, 0, current_entry);
-		ui_browser__write_nstring(browser, " ", 7 * ab->nr_events);
+
+		if (!show_title)
+			ui_browser__write_nstring(browser, " ", 7 * ab->nr_events);
+		else
+			ui_browser__printf(browser, "%*s", 7, "Percent");
 	}
 	if (ab->have_cycles) {
 		if (dl->ipc)
 			ui_browser__printf(browser, "%*.2f ", IPC_WIDTH - 1, dl->ipc);
-		else
+		else if (!show_title)
 			ui_browser__write_nstring(browser, " ", IPC_WIDTH);
+		else
+			ui_browser__printf(browser, "%*s ", IPC_WIDTH - 1, "IPC");
+
 		if (dl->cycles)
 			ui_browser__printf(browser, "%*" PRIu64 " ",
 					   CYCLES_WIDTH - 1, dl->cycles);
-		else
+		else if (!show_title)
 			ui_browser__write_nstring(browser, " ", CYCLES_WIDTH);
+		else
+			ui_browser__printf(browser, "%*s ", CYCLES_WIDTH - 1, "Cycle");
 	}
 
 	SLsmg_write_char(' ');
@@ -1056,7 +1073,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 		  (nr_pcnt - 1);
 	}
 
-	err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), sizeof_bdl);
+	err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel),
+				  sizeof_bdl, &browser.arch);
 	if (err) {
 		char msg[BUFSIZ];
 		symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index e99ba86158d2..d903fd493416 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -168,7 +168,8 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map,
 	if (map->dso->annotate_warned)
 		return -1;
 
-	err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), 0);
+	err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel),
+				  0, NULL);
 	if (err) {
 		char msg[BUFSIZ];
 		symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ddbd56df9187..be1caabb9290 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1379,7 +1379,9 @@ static const char *annotate__norm_arch(const char *arch_name)
 	return normalize_arch((char *)arch_name);
 }
 
-int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_name, size_t privsize)
+int symbol__disassemble(struct symbol *sym, struct map *map,
+			const char *arch_name, size_t privsize,
+			struct arch **parch)
 {
 	struct dso *dso = map->dso;
 	char command[PATH_MAX * 2];
@@ -1405,6 +1407,9 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na
 	if (arch == NULL)
 		return -ENOTSUP;
 
+	if (parch)
+		*parch = arch;
+
 	if (arch->init) {
 		err = arch->init(arch);
 		if (err) {
@@ -1901,7 +1906,8 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map,
 	struct rb_root source_line = RB_ROOT;
 	u64 len;
 
-	if (symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), 0) < 0)
+	if (symbol__disassemble(sym, map, perf_evsel__env_arch(evsel),
+				0, NULL) < 0)
 		return -1;
 
 	len = symbol__size(sym);
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 948aa8e6fd39..21055034aedd 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -158,7 +158,9 @@ int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr);
 int symbol__alloc_hist(struct symbol *sym);
 void symbol__annotate_zero_histograms(struct symbol *sym);
 
-int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_name, size_t privsize);
+int symbol__disassemble(struct symbol *sym, struct map *map,
+			const char *arch_name, size_t privsize,
+			struct arch **parch);
 
 enum symbol_disassemble_errno {
 	SYMBOL_ANNOTATE_ERRNO__SUCCESS		= 0,
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 0328f297a748..0175765c05b9 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -5,6 +5,7 @@
 #include <subcmd/pager.h>
 #include "../ui/ui.h"
 
+#include <linux/compiler.h>
 #include <linux/string.h>
 
 #define CMD_EXEC_PATH "--exec-path"
@@ -24,6 +25,6 @@ static inline int is_absolute_path(const char *path)
 	return path[0] == '/';
 }
 
-char *mkpath(const char *fmt, ...) __attribute__((format (printf, 1, 2)));
+char *mkpath(const char *fmt, ...) __printf(1, 2);
 
 #endif /* __PERF_CACHE_H */
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 8a23ea1a71c7..c818bdb1c1ab 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -4,6 +4,7 @@
 
 #include <stdbool.h>
 #include <string.h>
+#include <linux/compiler.h>
 #include "event.h"
 #include "../ui/helpline.h"
 #include "../ui/progress.h"
@@ -40,16 +41,16 @@ extern int debug_data_convert;
 
 #define STRERR_BUFSIZE	128	/* For the buffer size of str_error_r */
 
-int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
+int dump_printf(const char *fmt, ...) __printf(1, 2);
 void trace_event(union perf_event *event);
 
-int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2)));
-int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
+int ui__error(const char *format, ...) __printf(1, 2);
+int ui__warning(const char *format, ...) __printf(1, 2);
 
 void pr_stat(const char *fmt, ...);
 
-int eprintf(int level, int var, const char *fmt, ...) __attribute__((format(printf, 3, 4)));
-int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __attribute__((format(printf, 4, 5)));
+int eprintf(int level, int var, const char *fmt, ...) __printf(3, 4);
+int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __printf(4, 5);
 int veprintf(int level, int var, const char *fmt, va_list args);
 
 int perf_debug_option(const char *str);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 94cea4398a13..8d601fbdd8d6 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -1,6 +1,7 @@
 #ifndef __PERF_EVLIST_H
 #define __PERF_EVLIST_H 1
 
+#include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/refcount.h>
 #include <linux/list.h>
@@ -34,7 +35,7 @@ struct perf_mmap {
 	refcount_t	 refcnt;
 	u64		 prev;
 	struct auxtrace_mmap auxtrace_mmap;
-	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8)));
+	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);
 };
 
 static inline size_t
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index cda44b0e821c..7f78f27f5382 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -15,6 +15,7 @@
 #include <traceevent/event-parse.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/perf_event.h>
+#include <linux/compiler.h>
 #include <linux/err.h>
 #include <sys/ioctl.h>
 #include <sys/resource.h>
@@ -1441,7 +1442,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 }
 
 static int __open_attr__fprintf(FILE *fp, const char *name, const char *val,
-				void *priv __attribute__((unused)))
+				void *priv __maybe_unused)
 {
 	return fprintf(fp, "  %-32s %s\n", name, val);
 }
diff --git a/tools/perf/util/genelf_debug.c b/tools/perf/util/genelf_debug.c
index 5980f7d256b1..40789d8603d0 100644
--- a/tools/perf/util/genelf_debug.c
+++ b/tools/perf/util/genelf_debug.c
@@ -11,6 +11,7 @@
  * @remark Copyright 2007 OProfile authors
  * @author Philippe Elie
  */
+#include <linux/compiler.h>
 #include <sys/types.h>
 #include <stdio.h>
 #include <getopt.h>
@@ -125,7 +126,7 @@ struct debug_line_header {
 	 * and filesize, last entry is followed by en empty string.
 	 */
 	/* follow the first program statement */
-} __attribute__((packed));
+} __packed;
 
 /* DWARF 2 spec talk only about one possible compilation unit header while
  * binutils can handle two flavours of dwarf 2, 32 and 64 bits, this is not
@@ -138,7 +139,7 @@ struct compilation_unit_header {
 	uhalf version;
 	uword debug_abbrev_offset;
 	ubyte pointer_size;
-} __attribute__((packed));
+} __packed;
 
 #define DW_LNS_num_opcode (DW_LNS_set_isa + 1)
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index b5baff3007bb..76ed7d03e500 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -8,6 +8,7 @@
 #include <unistd.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/kernel.h>
 #include <linux/bitops.h>
@@ -1274,7 +1275,7 @@ error:
 }
 
 static int __desc_attr__fprintf(FILE *fp, const char *name, const char *val,
-				void *priv __attribute__((unused)))
+				void *priv __maybe_unused)
 {
 	return fprintf(fp, ", %s = %s", name, val);
 }
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index b2834ac7b1f5..218ee2bac9a5 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -866,8 +866,6 @@ static void intel_bts_print_info(u64 *arr, int start, int finish)
 		fprintf(stdout, intel_bts_info_fmts[i], arr[i]);
 }
 
-u64 intel_bts_auxtrace_info_priv[INTEL_BTS_AUXTRACE_PRIV_SIZE];
-
 int intel_bts_process_auxtrace_info(union perf_event *event,
 				    struct perf_session *session)
 {
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.h b/tools/perf/util/intel-pt-decoder/intel-pt-log.h
index debe751dc3d6..45b64f93f358 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-log.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.h
@@ -16,6 +16,7 @@
 #ifndef INCLUDE__INTEL_PT_LOG_H__
 #define INCLUDE__INTEL_PT_LOG_H__
 
+#include <linux/compiler.h>
 #include <stdint.h>
 #include <inttypes.h>
 
@@ -34,8 +35,7 @@ void __intel_pt_log_insn(struct intel_pt_insn *intel_pt_insn, uint64_t ip);
 void __intel_pt_log_insn_no_data(struct intel_pt_insn *intel_pt_insn,
 				 uint64_t ip);
 
-__attribute__((format(printf, 1, 2)))
-void __intel_pt_log(const char *fmt, ...);
+void __intel_pt_log(const char *fmt, ...) __printf(1, 2);
 
 #define intel_pt_log(fmt, ...) \
 	do { \
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index ea7f450dc609..389e9729331f 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -2,6 +2,7 @@
 #define __PMU_H
 
 #include <linux/bitmap.h>
+#include <linux/compiler.h>
 #include <linux/perf_event.h>
 #include <stdbool.h>
 #include "evsel.h"
@@ -83,8 +84,7 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet,
 		      bool long_desc, bool details_flag);
 bool pmu_have_event(const char *pname, const char *name);
 
-int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
-			...) __attribute__((format(scanf, 3, 4)));
+int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, ...) __scanf(3, 4);
 
 int perf_pmu__test(void);
 
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 373842656fb6..5812947418dd 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -1,6 +1,7 @@
 #ifndef _PROBE_EVENT_H
 #define _PROBE_EVENT_H
 
+#include <linux/compiler.h>
 #include <stdbool.h>
 #include "intlist.h"
 
@@ -171,8 +172,7 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev,
 			     struct symbol *sym);
 
 /* If there is no space to write, returns -E2BIG. */
-int e_snprintf(char *str, size_t size, const char *format, ...)
-	__attribute__((format(printf, 3, 4)));
+int e_snprintf(char *str, size_t size, const char *format, ...) __printf(3, 4);
 
 /* Maximum index number of event-name postfix */
 #define MAX_EVENT_INDEX	1024
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 40de3cb40d21..57b7a00e6f16 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -28,6 +28,7 @@
 #include <stdbool.h>
 #include <errno.h>
 #include <linux/bitmap.h>
+#include <linux/compiler.h>
 #include <linux/time64.h>
 
 #include "../../perf.h"
@@ -84,7 +85,7 @@ struct tables {
 
 static struct tables tables_global;
 
-static void handler_call_die(const char *handler_name) NORETURN;
+static void handler_call_die(const char *handler_name) __noreturn;
 static void handler_call_die(const char *handler_name)
 {
 	PyErr_Print();
diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h
index 318424ea561d..802d743378af 100644
--- a/tools/perf/util/strbuf.h
+++ b/tools/perf/util/strbuf.h
@@ -42,6 +42,7 @@
 #include <stdarg.h>
 #include <stddef.h>
 #include <string.h>
+#include <linux/compiler.h>
 #include <sys/types.h>
 
 extern char strbuf_slopbuf[];
@@ -85,8 +86,7 @@ static inline int strbuf_addstr(struct strbuf *sb, const char *s) {
 	return strbuf_add(sb, s, strlen(s));
 }
 
-__attribute__((format(printf,2,3)))
-int strbuf_addf(struct strbuf *sb, const char *fmt, ...);
+int strbuf_addf(struct strbuf *sb, const char *fmt, ...) __printf(2, 3);
 
 /* XXX: if read fails, any partial read is undone */
 ssize_t strbuf_read(struct strbuf *, int fd, ssize_t hint);
diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c
index 996046a66fe5..aacb65e079aa 100644
--- a/tools/perf/util/usage.c
+++ b/tools/perf/util/usage.c
@@ -16,13 +16,13 @@ static void report(const char *prefix, const char *err, va_list params)
 	fprintf(stderr, " %s%s\n", prefix, msg);
 }
 
-static NORETURN void usage_builtin(const char *err)
+static __noreturn void usage_builtin(const char *err)
 {
 	fprintf(stderr, "\n Usage: %s\n", err);
 	exit(129);
 }
 
-static NORETURN void die_builtin(const char *err, va_list params)
+static __noreturn void die_builtin(const char *err, va_list params)
 {
 	report(" Fatal: ", err, params);
 	exit(128);
@@ -40,7 +40,7 @@ static void warn_builtin(const char *warn, va_list params)
 
 /* If we are in a dlopen()ed .so write to a global variable would segfault
  * (ugh), so keep things static. */
-static void (*usage_routine)(const char *err) NORETURN = usage_builtin;
+static void (*usage_routine)(const char *err) __noreturn = usage_builtin;
 static void (*error_routine)(const char *err, va_list params) = error_builtin;
 static void (*warn_routine)(const char *err, va_list params) = warn_builtin;
 
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 5dfb9bb6482d..21c6db173bcc 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -11,22 +11,14 @@
 #include <stddef.h>
 #include <stdlib.h>
 #include <stdarg.h>
+#include <linux/compiler.h>
 #include <linux/types.h>
 
-#ifdef __GNUC__
-#define NORETURN __attribute__((__noreturn__))
-#else
-#define NORETURN
-#ifndef __attribute__
-#define __attribute__(x)
-#endif
-#endif
-
 /* General helper functions */
-void usage(const char *err) NORETURN;
-void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2)));
-int error(const char *err, ...) __attribute__((format (printf, 1, 2)));
-void warning(const char *err, ...) __attribute__((format (printf, 1, 2)));
+void usage(const char *err) __noreturn;
+void die(const char *err, ...) __noreturn __printf(1, 2);
+int error(const char *err, ...) __printf(1, 2);
+void warning(const char *err, ...) __printf(1, 2);
 
 void set_warning_routine(void (*routine)(const char *err, va_list params));