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>

tools/include/linux/compiler-gcc.h

@@ -19,3 +19,13 @@
 
 /* &a[0] degrades to a pointer: a different type from an array */
 #define __must_be_array(a)	BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
+
+#define  noinline	__attribute__((noinline))
+
+#define __packed	__attribute__((packed))
+
+#define __noreturn	__attribute__((noreturn))
+
+#define __aligned(x)	__attribute__((aligned(x)))
+#define __printf(a, b)	__attribute__((format(printf, a, b)))
+#define __scanf(a, b)	__attribute__((format(scanf, a, b)))

tools/include/linux/compiler.h

@@ -17,6 +17,10 @@
 # define __always_inline	inline __attribute__((always_inline))
 #endif
 
+#ifndef noinline
+#define noinline
+#endif
+
 /* Are two types/vars the same type (ignoring qualifiers)? */
 #ifndef __same_type
 # define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(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
 --------

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

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;

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;

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 {

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;

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;
@@ -186,52 +186,63 @@ 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:
 		if (argc) {
 			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;
 }