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

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

User visible changes:

- Mark events as (x86 only) in help output for 'perf kvm stat live" (Alexander Yarygin)

- Provide a better explanation when mmap fails in 'trace' (Arnaldo Carvalho de Melo)

- Add --buildid-dir option to set cache directory, i.e. use:

      $ perf --buildid-dir /path/to/dir tool --tool-options

  (Jiri Olsa)

- Fix memcpy/memset 'perf bench' output (Rabin Vicent)

- Fix 'perf test' attr tests size values to cope with machine state on
  interrupt ABI changes (Jiri Olsa)

- Fixup callchain type parameter handling error message (Kan Liang)

Infrastructure changes and cleanups:

- calloc/xcalloc: Fix argument order (Arjun Sreedharan)

- Move filename__read_int from tools/perf/ to tools/lib, add sysctl__read_int
  there and use it in place of ad-hoc copies (Arnaldo Carvalho de Melo)

- Use single strcmp call instead of two (Jiri Olsa)

- Remove extra debugdir variables in 'perf buildid-cache' (Jiri Olsa)

- Fix -a segfault related to kcore handling in 'perf buildid-cache' (Jiri Olsa)

- Move cpumode resolve code to add_callchain_ip (Kan Liang)

- Merge memset into memcpy 'perf bench' (Rabin Vincent)

- Change print format from %lu to %PRIu64 in the hists browser (Tom Huynh)

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

21 files changed, 308 insertions, 496 deletions

diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt
index d240bb2e5b22..1e8e400b4493 100644
--- a/tools/perf/Documentation/perf.txt
+++ b/tools/perf/Documentation/perf.txt
@@ -18,6 +18,10 @@ OPTIONS
 	  --debug verbose   # sets verbose = 1
 	  --debug verbose=2 # sets verbose = 2
 
+--buildid-dir::
+	Setup buildid cache directory. It has higher priority than
+	buildid.dir config file option.
+
 DESCRIPTION
 -----------
 Performance counters for Linux are a new kernel-based subsystem
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 478efa9b2364..763e68fb5767 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -458,7 +458,6 @@ BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o
 endif
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
-BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.o
 BUILTIN_OBJS += $(OUTPUT)bench/futex-hash.o
 BUILTIN_OBJS += $(OUTPUT)bench/futex-wake.o
 BUILTIN_OBJS += $(OUTPUT)bench/futex-requeue.o
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 2465141b554b..6c14afe8c1b1 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -13,6 +13,7 @@
 #include "../util/cloexec.h"
 #include "bench.h"
 #include "mem-memcpy-arch.h"
+#include "mem-memset-arch.h"
 
 #include <stdio.h>
 #include <stdlib.h>
@@ -48,20 +49,24 @@ static const struct option options[] = {
 };
 
 typedef void *(*memcpy_t)(void *, const void *, size_t);
+typedef void *(*memset_t)(void *, int, size_t);
 
 struct routine {
 	const char *name;
 	const char *desc;
-	memcpy_t fn;
+	union {
+		memcpy_t memcpy;
+		memset_t memset;
+	} fn;
 };
 
-struct routine routines[] = {
-	{ "default",
-	  "Default memcpy() provided by glibc",
-	  memcpy },
+struct routine memcpy_routines[] = {
+	{ .name = "default",
+	  .desc = "Default memcpy() provided by glibc",
+	  .fn.memcpy = memcpy },
 #ifdef HAVE_ARCH_X86_64_SUPPORT
 
-#define MEMCPY_FN(fn, name, desc) { name, desc, fn },
+#define MEMCPY_FN(_fn, _name, _desc) {.name = _name, .desc = _desc, .fn.memcpy = _fn},
 #include "mem-memcpy-x86-64-asm-def.h"
 #undef MEMCPY_FN
 
@@ -69,7 +74,7 @@ struct routine routines[] = {
 
 	{ NULL,
 	  NULL,
-	  NULL   }
+	  {NULL}   }
 };
 
 static const char * const bench_mem_memcpy_usage[] = {
@@ -110,63 +115,6 @@ static double timeval2double(struct timeval *ts)
 		(double)ts->tv_usec / (double)1000000;
 }
 
-static void alloc_mem(void **dst, void **src, size_t length)
-{
-	*dst = zalloc(length);
-	if (!*dst)
-		die("memory allocation failed - maybe length is too large?\n");
-
-	*src = zalloc(length);
-	if (!*src)
-		die("memory allocation failed - maybe length is too large?\n");
-	/* Make sure to always replace the zero pages even if MMAP_THRESH is crossed */
-	memset(*src, 0, length);
-}
-
-static u64 do_memcpy_cycle(memcpy_t fn, size_t len, bool prefault)
-{
-	u64 cycle_start = 0ULL, cycle_end = 0ULL;
-	void *src = NULL, *dst = NULL;
-	int i;
-
-	alloc_mem(&src, &dst, len);
-
-	if (prefault)
-		fn(dst, src, len);
-
-	cycle_start = get_cycle();
-	for (i = 0; i < iterations; ++i)
-		fn(dst, src, len);
-	cycle_end = get_cycle();
-
-	free(src);
-	free(dst);
-	return cycle_end - cycle_start;
-}
-
-static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
-{
-	struct timeval tv_start, tv_end, tv_diff;
-	void *src = NULL, *dst = NULL;
-	int i;
-
-	alloc_mem(&src, &dst, len);
-
-	if (prefault)
-		fn(dst, src, len);
-
-	BUG_ON(gettimeofday(&tv_start, NULL));
-	for (i = 0; i < iterations; ++i)
-		fn(dst, src, len);
-	BUG_ON(gettimeofday(&tv_end, NULL));
-
-	timersub(&tv_end, &tv_start, &tv_diff);
-
-	free(src);
-	free(dst);
-	return (double)((double)len / timeval2double(&tv_diff));
-}
-
 #define pf (no_prefault ? 0 : 1)
 
 #define print_bps(x) do {					\
@@ -180,16 +128,25 @@ static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
 			printf(" %14lf GB/Sec", x / K / K / K); \
 	} while (0)
 
-int bench_mem_memcpy(int argc, const char **argv,
-		     const char *prefix __maybe_unused)
+struct bench_mem_info {
+	const struct routine *routines;
+	u64 (*do_cycle)(const struct routine *r, size_t len, bool prefault);
+	double (*do_gettimeofday)(const struct routine *r, size_t len, bool prefault);
+	const char *const *usage;
+};
+
+static int bench_mem_common(int argc, const char **argv,
+		     const char *prefix __maybe_unused,
+		     struct bench_mem_info *info)
 {
 	int i;
 	size_t len;
+	double totallen;
 	double result_bps[2];
 	u64 result_cycle[2];
 
 	argc = parse_options(argc, argv, options,
-			     bench_mem_memcpy_usage, 0);
+			     info->usage, 0);
 
 	if (no_prefault && only_prefault) {
 		fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n");
@@ -200,6 +157,7 @@ int bench_mem_memcpy(int argc, const char **argv,
 		init_cycle();
 
 	len = (size_t)perf_atoll((char *)length_str);
+	totallen = (double)len * iterations;
 
 	result_cycle[0] = result_cycle[1] = 0ULL;
 	result_bps[0] = result_bps[1] = 0.0;
@@ -213,16 +171,16 @@ int bench_mem_memcpy(int argc, const char **argv,
 	if (only_prefault && no_prefault)
 		only_prefault = no_prefault = false;
 
-	for (i = 0; routines[i].name; i++) {
-		if (!strcmp(routines[i].name, routine))
+	for (i = 0; info->routines[i].name; i++) {
+		if (!strcmp(info->routines[i].name, routine))
 			break;
 	}
-	if (!routines[i].name) {
+	if (!info->routines[i].name) {
 		printf("Unknown routine:%s\n", routine);
 		printf("Available routines...\n");
-		for (i = 0; routines[i].name; i++) {
+		for (i = 0; info->routines[i].name; i++) {
 			printf("\t%s ... %s\n",
-			       routines[i].name, routines[i].desc);
+			       info->routines[i].name, info->routines[i].desc);
 		}
 		return 1;
 	}
@@ -234,25 +192,25 @@ int bench_mem_memcpy(int argc, const char **argv,
 		/* show both of results */
 		if (use_cycle) {
 			result_cycle[0] =
-				do_memcpy_cycle(routines[i].fn, len, false);
+				info->do_cycle(&info->routines[i], len, false);
 			result_cycle[1] =
-				do_memcpy_cycle(routines[i].fn, len, true);
+				info->do_cycle(&info->routines[i], len, true);
 		} else {
 			result_bps[0] =
-				do_memcpy_gettimeofday(routines[i].fn,
+				info->do_gettimeofday(&info->routines[i],
 						len, false);
 			result_bps[1] =
-				do_memcpy_gettimeofday(routines[i].fn,
+				info->do_gettimeofday(&info->routines[i],
 						len, true);
 		}
 	} else {
 		if (use_cycle) {
 			result_cycle[pf] =
-				do_memcpy_cycle(routines[i].fn,
+				info->do_cycle(&info->routines[i],
 						len, only_prefault);
 		} else {
 			result_bps[pf] =
-				do_memcpy_gettimeofday(routines[i].fn,
+				info->do_gettimeofday(&info->routines[i],
 						len, only_prefault);
 		}
 	}
@@ -263,10 +221,10 @@ int bench_mem_memcpy(int argc, const char **argv,
 			if (use_cycle) {
 				printf(" %14lf Cycle/Byte\n",
 					(double)result_cycle[0]
-					/ (double)len);
+					/ totallen);
 				printf(" %14lf Cycle/Byte (with prefault)\n",
 					(double)result_cycle[1]
-					/ (double)len);
+					/ totallen);
 			} else {
 				print_bps(result_bps[0]);
 				printf("\n");
@@ -277,7 +235,7 @@ int bench_mem_memcpy(int argc, const char **argv,
 			if (use_cycle) {
 				printf(" %14lf Cycle/Byte",
 					(double)result_cycle[pf]
-					/ (double)len);
+					/ totallen);
 			} else
 				print_bps(result_bps[pf]);
 
@@ -288,8 +246,8 @@ int bench_mem_memcpy(int argc, const char **argv,
 		if (!only_prefault && !no_prefault) {
 			if (use_cycle) {
 				printf("%lf %lf\n",
-					(double)result_cycle[0] / (double)len,
-					(double)result_cycle[1] / (double)len);
+					(double)result_cycle[0] / totallen,
+					(double)result_cycle[1] / totallen);
 			} else {
 				printf("%lf %lf\n",
 					result_bps[0], result_bps[1]);
@@ -297,7 +255,7 @@ int bench_mem_memcpy(int argc, const char **argv,
 		} else {
 			if (use_cycle) {
 				printf("%lf\n", (double)result_cycle[pf]
-					/ (double)len);
+					/ totallen);
 			} else
 				printf("%lf\n", result_bps[pf]);
 		}
@@ -310,3 +268,163 @@ int bench_mem_memcpy(int argc, const char **argv,
 
 	return 0;
 }
+
+static void memcpy_alloc_mem(void **dst, void **src, size_t length)
+{
+	*dst = zalloc(length);
+	if (!*dst)
+		die("memory allocation failed - maybe length is too large?\n");
+
+	*src = zalloc(length);
+	if (!*src)
+		die("memory allocation failed - maybe length is too large?\n");
+	/* Make sure to always replace the zero pages even if MMAP_THRESH is crossed */
+	memset(*src, 0, length);
+}
+
+static u64 do_memcpy_cycle(const struct routine *r, size_t len, bool prefault)
+{
+	u64 cycle_start = 0ULL, cycle_end = 0ULL;
+	void *src = NULL, *dst = NULL;
+	memcpy_t fn = r->fn.memcpy;
+	int i;
+
+	memcpy_alloc_mem(&src, &dst, len);
+
+	if (prefault)
+		fn(dst, src, len);
+
+	cycle_start = get_cycle();
+	for (i = 0; i < iterations; ++i)
+		fn(dst, src, len);
+	cycle_end = get_cycle();
+
+	free(src);
+	free(dst);
+	return cycle_end - cycle_start;
+}
+
+static double do_memcpy_gettimeofday(const struct routine *r, size_t len,
+				     bool prefault)
+{
+	struct timeval tv_start, tv_end, tv_diff;
+	memcpy_t fn = r->fn.memcpy;
+	void *src = NULL, *dst = NULL;
+	int i;
+
+	memcpy_alloc_mem(&src, &dst, len);
+
+	if (prefault)
+		fn(dst, src, len);
+
+	BUG_ON(gettimeofday(&tv_start, NULL));
+	for (i = 0; i < iterations; ++i)
+		fn(dst, src, len);
+	BUG_ON(gettimeofday(&tv_end, NULL));
+
+	timersub(&tv_end, &tv_start, &tv_diff);
+
+	free(src);
+	free(dst);
+	return (double)(((double)len * iterations) / timeval2double(&tv_diff));
+}
+
+int bench_mem_memcpy(int argc, const char **argv,
+		     const char *prefix __maybe_unused)
+{
+	struct bench_mem_info info = {
+		.routines = memcpy_routines,
+		.do_cycle = do_memcpy_cycle,
+		.do_gettimeofday = do_memcpy_gettimeofday,
+		.usage = bench_mem_memcpy_usage,
+	};
+
+	return bench_mem_common(argc, argv, prefix, &info);
+}
+
+static void memset_alloc_mem(void **dst, size_t length)
+{
+	*dst = zalloc(length);
+	if (!*dst)
+		die("memory allocation failed - maybe length is too large?\n");
+}
+
+static u64 do_memset_cycle(const struct routine *r, size_t len, bool prefault)
+{
+	u64 cycle_start = 0ULL, cycle_end = 0ULL;
+	memset_t fn = r->fn.memset;
+	void *dst = NULL;
+	int i;
+
+	memset_alloc_mem(&dst, len);
+
+	if (prefault)
+		fn(dst, -1, len);
+
+	cycle_start = get_cycle();
+	for (i = 0; i < iterations; ++i)
+		fn(dst, i, len);
+	cycle_end = get_cycle();
+
+	free(dst);
+	return cycle_end - cycle_start;
+}
+
+static double do_memset_gettimeofday(const struct routine *r, size_t len,
+				     bool prefault)
+{
+	struct timeval tv_start, tv_end, tv_diff;
+	memset_t fn = r->fn.memset;
+	void *dst = NULL;
+	int i;
+
+	memset_alloc_mem(&dst, len);
+
+	if (prefault)
+		fn(dst, -1, len);
+
+	BUG_ON(gettimeofday(&tv_start, NULL));
+	for (i = 0; i < iterations; ++i)
+		fn(dst, i, len);
+	BUG_ON(gettimeofday(&tv_end, NULL));
+
+	timersub(&tv_end, &tv_start, &tv_diff);
+
+	free(dst);
+	return (double)(((double)len * iterations) / timeval2double(&tv_diff));
+}
+
+static const char * const bench_mem_memset_usage[] = {
+	"perf bench mem memset <options>",
+	NULL
+};
+
+static const struct routine memset_routines[] = {
+	{ .name ="default",
+	  .desc = "Default memset() provided by glibc",
+	  .fn.memset = memset },
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+
+#define MEMSET_FN(_fn, _name, _desc) { .name = _name, .desc = _desc, .fn.memset = _fn },
+#include "mem-memset-x86-64-asm-def.h"
+#undef MEMSET_FN
+
+#endif
+
+	{ .name = NULL,
+	  .desc = NULL,
+	  .fn.memset = NULL   }
+};
+
+int bench_mem_memset(int argc, const char **argv,
+		     const char *prefix __maybe_unused)
+{
+	struct bench_mem_info info = {
+		.routines = memset_routines,
+		.do_cycle = do_memset_cycle,
+		.do_gettimeofday = do_memset_gettimeofday,
+		.usage = bench_mem_memset_usage,
+	};
+
+	return bench_mem_common(argc, argv, prefix, &info);
+}
diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c
deleted file mode 100644
index 75fc3e65fb2a..000000000000
--- a/tools/perf/bench/mem-memset.c
+++ /dev/null
@@ -1,304 +0,0 @@
-/*
- * mem-memset.c
- *
- * memset: Simple memory set in various ways
- *
- * Trivial clone of mem-memcpy.c.
- */
-
-#include "../perf.h"
-#include "../util/util.h"
-#include "../util/parse-options.h"
-#include "../util/header.h"
-#include "../util/cloexec.h"
-#include "bench.h"
-#include "mem-memset-arch.h"
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <sys/time.h>
-#include <errno.h>
-
-#define K 1024
-
-static const char	*length_str	= "1MB";
-static const char	*routine	= "default";
-static int		iterations	= 1;
-static bool		use_cycle;
-static int		cycle_fd;
-static bool		only_prefault;
-static bool		no_prefault;
-
-static const struct option options[] = {
-	OPT_STRING('l', "length", &length_str, "1MB",
-		    "Specify length of memory to set. "
-		    "Available units: B, KB, MB, GB and TB (upper and lower)"),
-	OPT_STRING('r', "routine", &routine, "default",
-		    "Specify routine to set"),
-	OPT_INTEGER('i', "iterations", &iterations,
-		    "repeat memset() invocation this number of times"),
-	OPT_BOOLEAN('c', "cycle", &use_cycle,
-		    "Use cycles event instead of gettimeofday() for measuring"),
-	OPT_BOOLEAN('o', "only-prefault", &only_prefault,
-		    "Show only the result with page faults before memset()"),
-	OPT_BOOLEAN('n', "no-prefault", &no_prefault,
-		    "Show only the result without page faults before memset()"),
-	OPT_END()
-};
-
-typedef void *(*memset_t)(void *, int, size_t);
-
-struct routine {
-	const char *name;
-	const char *desc;
-	memset_t fn;
-};
-
-static const struct routine routines[] = {
-	{ "default",
-	  "Default memset() provided by glibc",
-	  memset },
-#ifdef HAVE_ARCH_X86_64_SUPPORT
-
-#define MEMSET_FN(fn, name, desc) { name, desc, fn },
-#include "mem-memset-x86-64-asm-def.h"
-#undef MEMSET_FN
-
-#endif
-
-	{ NULL,
-	  NULL,
-	  NULL   }
-};
-
-static const char * const bench_mem_memset_usage[] = {
-	"perf bench mem memset <options>",
-	NULL
-};
-
-static struct perf_event_attr cycle_attr = {
-	.type		= PERF_TYPE_HARDWARE,
-	.config		= PERF_COUNT_HW_CPU_CYCLES
-};
-
-static void init_cycle(void)
-{
-	cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1,
-				       perf_event_open_cloexec_flag());
-
-	if (cycle_fd < 0 && errno == ENOSYS)
-		die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
-	else
-		BUG_ON(cycle_fd < 0);
-}
-
-static u64 get_cycle(void)
-{
-	int ret;
-	u64 clk;
-
-	ret = read(cycle_fd, &clk, sizeof(u64));
-	BUG_ON(ret != sizeof(u64));
-
-	return clk;
-}
-
-static double timeval2double(struct timeval *ts)
-{
-	return (double)ts->tv_sec +
-		(double)ts->tv_usec / (double)1000000;
-}
-
-static void alloc_mem(void **dst, size_t length)
-{
-	*dst = zalloc(length);
-	if (!*dst)
-		die("memory allocation failed - maybe length is too large?\n");
-}
-
-static u64 do_memset_cycle(memset_t fn, size_t len, bool prefault)
-{
-	u64 cycle_start = 0ULL, cycle_end = 0ULL;
-	void *dst = NULL;
-	int i;
-
-	alloc_mem(&dst, len);
-
-	if (prefault)
-		fn(dst, -1, len);
-
-	cycle_start = get_cycle();
-	for (i = 0; i < iterations; ++i)
-		fn(dst, i, len);
-	cycle_end = get_cycle();
-
-	free(dst);
-	return cycle_end - cycle_start;
-}
-
-static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault)
-{
-	struct timeval tv_start, tv_end, tv_diff;
-	void *dst = NULL;
-	int i;
-
-	alloc_mem(&dst, len);
-
-	if (prefault)
-		fn(dst, -1, len);
-
-	BUG_ON(gettimeofday(&tv_start, NULL));
-	for (i = 0; i < iterations; ++i)
-		fn(dst, i, len);
-	BUG_ON(gettimeofday(&tv_end, NULL));
-
-	timersub(&tv_end, &tv_start, &tv_diff);
-
-	free(dst);
-	return (double)((double)len / timeval2double(&tv_diff));
-}
-
-#define pf (no_prefault ? 0 : 1)
-
-#define print_bps(x) do {					\
-		if (x < K)					\
-			printf(" %14lf B/Sec", x);		\
-		else if (x < K * K)				\
-			printf(" %14lfd KB/Sec", x / K);	\
-		else if (x < K * K * K)				\
-			printf(" %14lf MB/Sec", x / K / K);	\
-		else						\
-			printf(" %14lf GB/Sec", x / K / K / K); \
-	} while (0)
-
-int bench_mem_memset(int argc, const char **argv,
-		     const char *prefix __maybe_unused)
-{
-	int i;
-	size_t len;
-	double result_bps[2];
-	u64 result_cycle[2];
-
-	argc = parse_options(argc, argv, options,
-			     bench_mem_memset_usage, 0);
-
-	if (no_prefault && only_prefault) {
-		fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n");
-		return 1;
-	}
-
-	if (use_cycle)
-		init_cycle();
-
-	len = (size_t)perf_atoll((char *)length_str);
-
-	result_cycle[0] = result_cycle[1] = 0ULL;
-	result_bps[0] = result_bps[1] = 0.0;
-
-	if ((s64)len <= 0) {
-		fprintf(stderr, "Invalid length:%s\n", length_str);
-		return 1;
-	}
-
-	/* same to without specifying either of prefault and no-prefault */
-	if (only_prefault && no_prefault)
-		only_prefault = no_prefault = false;
-
-	for (i = 0; routines[i].name; i++) {
-		if (!strcmp(routines[i].name, routine))
-			break;
-	}
-	if (!routines[i].name) {
-		printf("Unknown routine:%s\n", routine);
-		printf("Available routines...\n");
-		for (i = 0; routines[i].name; i++) {
-			printf("\t%s ... %s\n",
-			       routines[i].name, routines[i].desc);
-		}
-		return 1;
-	}
-
-	if (bench_format == BENCH_FORMAT_DEFAULT)
-		printf("# Copying %s Bytes ...\n\n", length_str);
-
-	if (!only_prefault && !no_prefault) {
-		/* show both of results */
-		if (use_cycle) {
-			result_cycle[0] =
-				do_memset_cycle(routines[i].fn, len, false);
-			result_cycle[1] =
-				do_memset_cycle(routines[i].fn, len, true);
-		} else {
-			result_bps[0] =
-				do_memset_gettimeofday(routines[i].fn,
-						len, false);
-			result_bps[1] =
-				do_memset_gettimeofday(routines[i].fn,
-						len, true);
-		}
-	} else {
-		if (use_cycle) {
-			result_cycle[pf] =
-				do_memset_cycle(routines[i].fn,
-						len, only_prefault);
-		} else {
-			result_bps[pf] =
-				do_memset_gettimeofday(routines[i].fn,
-						len, only_prefault);
-		}
-	}
-
-	switch (bench_format) {
-	case BENCH_FORMAT_DEFAULT:
-		if (!only_prefault && !no_prefault) {
-			if (use_cycle) {
-				printf(" %14lf Cycle/Byte\n",
-					(double)result_cycle[0]
-					/ (double)len);
-				printf(" %14lf Cycle/Byte (with prefault)\n ",
-					(double)result_cycle[1]
-					/ (double)len);
-			} else {
-				print_bps(result_bps[0]);
-				printf("\n");
-				print_bps(result_bps[1]);
-				printf(" (with prefault)\n");
-			}
-		} else {
-			if (use_cycle) {
-				printf(" %14lf Cycle/Byte",
-					(double)result_cycle[pf]
-					/ (double)len);
-			} else
-				print_bps(result_bps[pf]);
-
-			printf("%s\n", only_prefault ? " (with prefault)" : "");
-		}
-		break;
-	case BENCH_FORMAT_SIMPLE:
-		if (!only_prefault && !no_prefault) {
-			if (use_cycle) {
-				printf("%lf %lf\n",
-					(double)result_cycle[0] / (double)len,
-					(double)result_cycle[1] / (double)len);
-			} else {
-				printf("%lf %lf\n",
-					result_bps[0], result_bps[1]);
-			}
-		} else {
-			if (use_cycle) {
-				printf("%lf\n", (double)result_cycle[pf]
-					/ (double)len);
-			} else
-				printf("%lf\n", result_bps[pf]);
-		}
-		break;
-	default:
-		/* reaching this means there's some disaster: */
-		die("unknown format: %d\n", bench_format);
-		break;
-	}
-
-	return 0;
-}
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 70385756da63..77d5cae54c6a 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -285,12 +285,11 @@ int cmd_buildid_cache(int argc, const char **argv,
 	struct str_node *pos;
 	int ret = 0;
 	bool force = false;
-	char debugdir[PATH_MAX];
 	char const *add_name_list_str = NULL,
 		   *remove_name_list_str = NULL,
 		   *missing_filename = NULL,
 		   *update_name_list_str = NULL,
-		   *kcore_filename;
+		   *kcore_filename = NULL;
 	char sbuf[STRERR_BUFSIZE];
 
 	struct perf_data_file file = {
@@ -335,13 +334,11 @@ int cmd_buildid_cache(int argc, const char **argv,
 
 	setup_pager();
 
-	snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir);
-
 	if (add_name_list_str) {
 		list = strlist__new(true, add_name_list_str);
 		if (list) {
 			strlist__for_each(pos, list)
-				if (build_id_cache__add_file(pos->s, debugdir)) {
+				if (build_id_cache__add_file(pos->s, buildid_dir)) {
 					if (errno == EEXIST) {
 						pr_debug("%s already in the cache\n",
 							 pos->s);
@@ -359,7 +356,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 		list = strlist__new(true, remove_name_list_str);
 		if (list) {
 			strlist__for_each(pos, list)
-				if (build_id_cache__remove_file(pos->s, debugdir)) {
+				if (build_id_cache__remove_file(pos->s, buildid_dir)) {
 					if (errno == ENOENT) {
 						pr_debug("%s wasn't in the cache\n",
 							 pos->s);
@@ -380,7 +377,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 		list = strlist__new(true, update_name_list_str);
 		if (list) {
 			strlist__for_each(pos, list)
-				if (build_id_cache__update_file(pos->s, debugdir)) {
+				if (build_id_cache__update_file(pos->s, buildid_dir)) {
 					if (errno == ENOENT) {
 						pr_debug("%s wasn't in the cache\n",
 							 pos->s);
@@ -395,7 +392,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 	}
 
 	if (kcore_filename &&
-	    build_id_cache__add_kcore(kcore_filename, debugdir, force))
+	    build_id_cache__add_kcore(kcore_filename, buildid_dir, force))
 		pr_warning("Couldn't add %s\n", kcore_filename);
 
 out:
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 3c0f3d4fb021..0894a817f67e 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1293,7 +1293,8 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 		OPT_UINTEGER('d', "display", &kvm->display_time,
 			"time in seconds between display updates"),
 		OPT_STRING(0, "event", &kvm->report_event, "report event",
-			"event for reporting: vmexit, mmio, ioport"),
+			"event for reporting: "
+			"vmexit, mmio (x86 only), ioport (x86 only)"),
 		OPT_INTEGER(0, "vcpu", &kvm->trace_vcpu,
 			"vcpu id to report"),
 		OPT_STRING('k', "key", &kvm->sort_key, "sort-key",
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 83a4835c8118..327541e43c7f 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2045,7 +2045,6 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	unsigned long before;
 	const bool forks = argc > 0;
 	bool draining = false;
-	char sbuf[STRERR_BUFSIZE];
 
 	trace->live = true;
 
@@ -2106,11 +2105,8 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		goto out_error_open;
 
 	err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
-	if (err < 0) {
-		fprintf(trace->output, "Couldn't mmap the events: %s\n",
-			strerror_r(errno, sbuf, sizeof(sbuf)));
-		goto out_delete_evlist;
-	}
+	if (err < 0)
+		goto out_error_mmap;
 
 	perf_evlist__enable(evlist);
 
@@ -2210,6 +2206,10 @@ out_error_tp:
 	perf_evlist__strerror_tp(evlist, errno, errbuf, sizeof(errbuf));
 	goto out_error;
 
+out_error_mmap:
+	perf_evlist__strerror_mmap(evlist, errno, errbuf, sizeof(errbuf));
+	goto out_error;
+
 out_error_open:
 	perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));
 
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 452a8474d29d..3700a7faca6c 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -200,6 +200,16 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
 				*envchanged = 1;
 			(*argv)++;
 			(*argc)--;
+		} else if (!strcmp(cmd, "--buildid-dir")) {
+			if (*argc < 2) {
+				fprintf(stderr, "No directory given for --buildid-dir.\n");
+				usage(perf_usage_string);
+			}
+			set_buildid_dir((*argv)[1]);
+			if (envchanged)
+				*envchanged = 1;
+			(*argv)++;
+			(*argc)--;
 		} else if (!prefixcmp(cmd, CMD_DEBUGFS_DIR)) {
 			perf_debugfs_set_path(cmd + strlen(CMD_DEBUGFS_DIR));
 			fprintf(stderr, "dir: %s\n", debugfs_mountpoint);
@@ -499,7 +509,7 @@ int main(int argc, const char **argv)
 	}
 	if (!prefixcmp(cmd, "trace")) {
 #ifdef HAVE_LIBAUDIT_SUPPORT
-		set_buildid_dir();
+		set_buildid_dir(NULL);
 		setup_path();
 		argv[0] = "trace";
 		return cmd_trace(argc, argv, NULL);
@@ -514,7 +524,7 @@ int main(int argc, const char **argv)
 	argc--;
 	handle_options(&argv, &argc, NULL);
 	commit_pager_choice();
-	set_buildid_dir();
+	set_buildid_dir(NULL);
 
 	if (argc > 0) {
 		if (!prefixcmp(argv[0], "--"))
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
index f710b92ccff6..d3095dafed36 100644
--- a/tools/perf/tests/attr/base-record
+++ b/tools/perf/tests/attr/base-record
@@ -5,7 +5,7 @@ group_fd=-1
 flags=0|8
 cpu=*
 type=0|1
-size=96
+size=104
 config=0
 sample_period=4000
 sample_type=263
diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat
index dc3ada2470c0..872ed7e24c7c 100644
--- a/tools/perf/tests/attr/base-stat
+++ b/tools/perf/tests/attr/base-stat
@@ -5,7 +5,7 @@ group_fd=-1
 flags=0|8
 cpu=*