Merge tag 'perf-core-for-mingo-4.17-20180403' 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:

- Show only failing syscalls with 'perf trace --failure' (Arnaldo Carvalho de Melo)

	e.g: See what 'openat' syscalls are failing:

  # perf trace --failure -e openat
   762.323 ( 0.007 ms): VideoCapture/4566 openat(dfd: CWD, filename: /dev/video2) = -1 ENOENT No such file or directory
   <SNIP N /dev/videoN open attempts... sigh, where is that improvised camera lid?!? >
   790.228 ( 0.008 ms): VideoCapture/4566 openat(dfd: CWD, filename: /dev/video63) = -1 ENOENT No such file or directory
  ^C#

- Show information about the event (freq, nr_samples, total period/nr_events) in
  the annotate --tui and --stdio2 'perf annotate' output, similar to the
  first line in the 'perf report --tui', but just for the samples for a
  the annotated symbol (Arnaldo Carvalho de Melo)

- Introduce 'perf version --build-options' to show what features were
  linked, aliased as well as a shorter 'perf -vv' (Jin Yao)

- Add a "dso_size" sort order (Kim Phillips)

- Remove redundant ')' in the tracepoint output in 'perf trace' (Changbin Du)

- Synchronize x86's cpufeatures.h, no effect on toolss (Arnaldo Carvalho de Melo)

Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>

tools/arch/x86/include/asm/cpufeatures.h

@@ -316,6 +316,7 @@
 #define X86_FEATURE_VPCLMULQDQ		(16*32+10) /* Carry-Less Multiplication Double Quadword */
 #define X86_FEATURE_AVX512_VNNI		(16*32+11) /* Vector Neural Network Instructions */
 #define X86_FEATURE_AVX512_BITALG	(16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */
+#define X86_FEATURE_TME			(16*32+13) /* Intel Total Memory Encryption */
 #define X86_FEATURE_AVX512_VPOPCNTDQ	(16*32+14) /* POPCNT for vectors of DW/QW */
 #define X86_FEATURE_LA57		(16*32+16) /* 5-level page tables */
 #define X86_FEATURE_RDPID		(16*32+22) /* RDPID instruction */
@@ -328,6 +329,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */

tools/include/tools/config.h

@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_CONFIG_H
+#define _TOOLS_CONFIG_H
+
+/* Subset of include/linux/kconfig.h */
+
+#define __ARG_PLACEHOLDER_1 0,
+#define __take_second_arg(__ignored, val, ...) val
+
+/*
+ * Helper macros to use CONFIG_ options in C/CPP expressions. Note that
+ * these only work with boolean and tristate options.
+ */
+
+/*
+ * Getting something that works in C and CPP for an arg that may or may
+ * not be defined is tricky.  Here, if we have "#define CONFIG_BOOGER 1"
+ * we match on the placeholder define, insert the "0," for arg1 and generate
+ * the triplet (0, 1, 0).  Then the last step cherry picks the 2nd arg (a one).
+ * When CONFIG_BOOGER is not defined, we generate a (... 1, 0) pair, and when
+ * the last step cherry picks the 2nd arg, we get a zero.
+ */
+#define __is_defined(x)			___is_defined(x)
+#define ___is_defined(val)		____is_defined(__ARG_PLACEHOLDER_##val)
+#define ____is_defined(arg1_or_junk)	__take_second_arg(arg1_or_junk 1, 0)
+
+/*
+ * IS_BUILTIN(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y', 0
+ * otherwise. For boolean options, this is equivalent to
+ * IS_ENABLED(CONFIG_FOO).
+ */
+#define IS_BUILTIN(option) __is_defined(option)
+
+#endif /* _TOOLS_CONFIG_H */

tools/perf/Documentation/perf-report.txt

@@ -80,6 +80,7 @@ OPTIONS
 	- comm: command (name) of the task which can be read via /proc/<pid>/comm
 	- pid: command and tid of the task
 	- dso: name of library or module executed at the time of sample
+	- dso_size: size of library or module executed at the time of sample
 	- symbol: name of function executed at the time of sample
 	- symbol_size: size of function executed at the time of sample
 	- parent: name of function matched to the parent regex filter. Unmatched

tools/perf/Documentation/perf-trace.txt

@@ -117,6 +117,9 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 --sched::
 	Accrue thread runtime and provide a summary at the end of the session.
 
+--failure::
+	Show only syscalls that failed, i.e. that returned < 0.
+
 -i::
 --input::
 	Process events from a given perf data file.

tools/perf/Documentation/perf-version.txt

@@ -0,0 +1,24 @@
+perf-version(1)
+===============
+
+NAME
+----
+perf-version - display the version of perf binary
+
+SYNOPSIS
+--------
+'perf version' [--build-options]
+
+DESCRIPTION
+-----------
+With no options given, the 'perf version' prints the perf version
+on the standard output.
+
+If the option '--build-options' is given, then the status of
+compiled-in libraries are printed on the standard output.
+
+OPTIONS
+-------
+--build-options::
+        Prints the status of compiled-in libraries on the
+        standard output.

tools/perf/Makefile.config

@@ -346,12 +346,16 @@ else
       ifneq ($(feature-dwarf_getlocations), 1)
         msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157);
       else
-        CFLAGS += -DHAVE_DWARF_GETLOCATIONS
+        CFLAGS += -DHAVE_DWARF_GETLOCATIONS_SUPPORT
       endif # dwarf_getlocations
     endif # Dwarf support
   endif # libelf support
 endif # NO_LIBELF
 
+ifeq ($(feature-glibc), 1)
+  CFLAGS += -DHAVE_GLIBC_SUPPORT
+endif
+
 ifdef NO_DWARF
   NO_LIBDW_DWARF_UNWIND := 1
 endif
@@ -635,6 +639,7 @@ else
   else
     LDFLAGS += $(PERL_EMBED_LDFLAGS)
     EXTLIBS += $(PERL_EMBED_LIBADD)
+    CFLAGS += -DHAVE_LIBPERL_SUPPORT
     $(call detected,CONFIG_LIBPERL)
   endif
 endif
@@ -671,6 +676,7 @@ else
          LDFLAGS += $(PYTHON_EMBED_LDFLAGS)
          EXTLIBS += $(PYTHON_EMBED_LIBADD)
          LANG_BINDINGS += $(obj-perf)python/perf.so
+         CFLAGS += -DHAVE_LIBPYTHON_SUPPORT
          $(call detected,CONFIG_LIBPYTHON)
       endif
     endif

tools/perf/builtin-trace.c

@@ -112,6 +112,7 @@ struct trace {
 	bool			multiple_threads;
 	bool			summary;
 	bool			summary_only;
+	bool			failure_only;
 	bool			show_comm;
 	bool			print_sample;
 	bool			show_tool_stats;
@@ -1565,7 +1566,7 @@ static int trace__printf_interrupted_entry(struct trace *trace)
 	struct thread_trace *ttrace;
 	size_t printed;
 
-	if (trace->current == NULL)
+	if (trace->failure_only || trace->current == NULL)
 		return 0;
 
 	ttrace = thread__priv(trace->current);
@@ -1638,7 +1639,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 					   args, trace, thread);
 
 	if (sc->is_exit) {
-		if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) {
+		if (!(trace->duration_filter || trace->summary_only || trace->failure_only || trace->min_stack)) {
 			trace__fprintf_entry_head(trace, thread, 0, false, ttrace->entry_time, trace->output);
 			fprintf(trace->output, "%-70s)\n", ttrace->entry_str);
 		}
@@ -1742,7 +1743,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 		}
 	}
 
-	if (trace->summary_only)
+	if (trace->summary_only || (ret >= 0 && trace->failure_only))
 		goto out;
 
 	trace__fprintf_entry_head(trace, thread, duration, duration_calculated, ttrace->entry_time, trace->output);
@@ -1961,7 +1962,7 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 				      trace->output);
 	}
 
-	fprintf(trace->output, ")\n");
+	fprintf(trace->output, "\n");
 
 	if (callchain_ret > 0)
 		trace__fprintf_callchain(trace, sample);
@@ -3087,6 +3088,8 @@ int cmd_trace(int argc, const char **argv)
 	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
 	OPT_BOOLEAN('T', "time", &trace.full_time,
 		    "Show full timestamp, not time relative to first start"),
+	OPT_BOOLEAN(0, "failure", &trace.failure_only,
+		    "Show only syscalls that failed"),
 	OPT_BOOLEAN('s', "summary", &trace.summary_only,
 		    "Show only syscall summary with statistics"),
 	OPT_BOOLEAN('S', "with-summary", &trace.summary,

tools/perf/builtin-version.c

@@ -1,11 +1,91 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "builtin.h"
 #include "perf.h"
+#include "color.h"
 #include <linux/compiler.h>
+#include <tools/config.h>
 #include <stdio.h>
+#include <string.h>
+#include <subcmd/parse-options.h>
 
-int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused)
+int version_verbose;
+
+struct version {
+	bool	build_options;
+};
+
+static struct version version;
+
+static struct option version_options[] = {
+	OPT_BOOLEAN(0, "build-options", &version.build_options,
+		    "display the build options"),
+};
+
+static const char * const version_usage[] = {
+	"perf version [<options>]",
+	NULL
+};
+
+static void on_off_print(const char *status)
+{
+	printf("[ ");
+
+	if (!strcmp(status, "OFF"))
+		color_fprintf(stdout, PERF_COLOR_RED, "%-3s", status);
+	else
+		color_fprintf(stdout, PERF_COLOR_GREEN, "%-3s", status);
+
+	printf(" ]");
+}
+
+static void status_print(const char *name, const char *macro,
+			 const char *status)
 {
+	printf("%22s: ", name);
+	on_off_print(status);
+	printf("  # %s\n", macro);
+}
+
+#define STATUS(__d, __m)				\
+do {							\
+	if (IS_BUILTIN(__d))				\
+		status_print(#__m, #__d, "on");		\
+	else						\
+		status_print(#__m, #__d, "OFF");	\
+} while (0)
+
+static void library_status(void)
+{
+	STATUS(HAVE_DWARF_SUPPORT, dwarf);
+	STATUS(HAVE_DWARF_GETLOCATIONS_SUPPORT, dwarf_getlocations);
+	STATUS(HAVE_GLIBC_SUPPORT, glibc);
+	STATUS(HAVE_GTK2_SUPPORT, gtk2);
+	STATUS(HAVE_LIBAUDIT_SUPPORT, libaudit);
+	STATUS(HAVE_LIBBFD_SUPPORT, libbfd);
+	STATUS(HAVE_LIBELF_SUPPORT, libelf);
+	STATUS(HAVE_LIBNUMA_SUPPORT, libnuma);
+	STATUS(HAVE_LIBNUMA_SUPPORT, numa_num_possible_cpus);
+	STATUS(HAVE_LIBPERL_SUPPORT, libperl);
+	STATUS(HAVE_LIBPYTHON_SUPPORT, libpython);
+	STATUS(HAVE_SLANG_SUPPORT, libslang);
+	STATUS(HAVE_LIBCRYPTO_SUPPORT, libcrypto);
+	STATUS(HAVE_LIBUNWIND_SUPPORT, libunwind);
+	STATUS(HAVE_DWARF_SUPPORT, libdw-dwarf-unwind);
+	STATUS(HAVE_ZLIB_SUPPORT, zlib);
+	STATUS(HAVE_LZMA_SUPPORT, lzma);
+	STATUS(HAVE_AUXTRACE_SUPPORT, get_cpuid);
+	STATUS(HAVE_LIBBPF_SUPPORT, bpf);
+}
+
+int cmd_version(int argc, const char **argv)
+{
+	argc = parse_options(argc, argv, version_options, version_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
+
 	printf("perf version %s\n", perf_version_string);
+
+	if (version.build_options || version_verbose == 1)
+		library_status();
+
 	return 0;
 }

tools/perf/perf.c

@@ -190,6 +190,12 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
 			break;
 		}
 
+		if (!strcmp(cmd, "-vv")) {
+			(*argv)[0] = "version";
+			version_verbose = 1;
+			break;
+		}
+
 		/*
 		 * Check remaining flags.
 		 */

tools/perf/perf.h

@@ -84,6 +84,7 @@ struct record_opts {
 struct option;
 extern const char * const *record_usage;
 extern struct option *record_options;
+extern int version_verbose;
 
 int record__parse_freq(const struct option *opt, const char *str, int unset);
 #endif

tools/perf/ui/browser.c

@@ -45,11 +45,16 @@ void ui_browser__set_percent_color(struct ui_browser *browser,
 	 ui_browser__set_color(browser, color);
 }
 
-void ui_browser__gotorc(struct ui_browser *browser, int y, int x)
+void ui_browser__gotorc_title(struct ui_browser *browser, int y, int x)
 {
 	SLsmg_gotorc(browser->y + y, browser->x + x);
 }
 
+void ui_browser__gotorc(struct ui_browser *browser, int y, int x)
+{
+	SLsmg_gotorc(browser->y + y + browser->extra_title_lines, browser->x + x);
+}
+
 void ui_browser__write_nstring(struct ui_browser *browser __maybe_unused, const char *msg,
 			       unsigned int width)
 {
@@ -191,6 +196,7 @@ void ui_browser__refresh_dimensions(struct ui_browser *browser)
 {
 	browser->width = SLtt_Screen_Cols - 1;
 	browser->height = browser->rows = SLtt_Screen_Rows - 2;
+	browser->rows -= browser->extra_title_lines;
 	browser->y = 1;
 	browser->x = 0;
 }

tools/perf/ui/browser.h

@@ -17,6 +17,7 @@ struct ui_browser {
 	u64	      index, top_idx;
 	void	      *top, *entries;
 	u16	      y, x, width, height, rows, columns, horiz_scroll;
+	u8	      extra_title_lines;
 	int	      current_color;
 	void	      *priv;
 	const char    *title;
@@ -38,6 +39,7 @@ bool ui_browser__is_current_entry(struct ui_browser *browser, unsigned row);
 void ui_browser__refresh_dimensions(struct ui_browser *browser);
 void ui_browser__reset_index(struct ui_browser *browser);
 
+void ui_browser__gotorc_title(struct ui_browser *browser, int y, int x);
 void ui_browser__gotorc(struct ui_browser *browser, int y, int x);
 void ui_browser__write_nstring(struct ui_browser *browser, const char *msg,
 			       unsigned int width);