korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-11-29 07:04:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

perf/core improvements and fixes:

Browse Source 
User visible:
 
 - 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/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>
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQEcBAABAgAGBQJUigtHAAoJEBpxZoYYoA71rXYIAJQK1etzZiUsgnCaYnSggx40
 TWXfSF9EJABO3qi1PrzmAcwzRTss0LA/YTTZ8h/9WqGyaro2meOu3IBIAFUKHFIl
 Sq4DK+GhatdqLCmiT+LHuXvaOO5hbtEKmphREnz3OprKUVa2uWP6S/3nQKe/dlY1
 wArOjcjfGTh+gRzkAUFySKIG0IHMsMBLJzqtx2YwKeDcDBcOpXO+BP50QuE/Crdn
 SwkCk/WKkQh1DYrVZUNMTaHAurVFudpjjYCksqaJ7CUV9CGTXuAoITJmwpn3thwg
 8EIpfcoF9ZCCbZl6X7F7tRfucc1DtbAZXSap9CsQCgnhEIvxFe3OHUU+rczQgWU=
 =rF9+
 -----END PGP SIGNATURE-----

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>
This commit is contained in:
Ingo Molnar 2014-12-12 09:09:52 +01:00
commit 41e950c033
25 changed files with 417 additions and 568 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
scripts/kconfig/mconf.c
View File

@ -330,10 +330,10 @@ static void set_subtitle(void)
list_for_each_entry(sp, &trail, entries) {
if (sp->text) {
if (pos) {
pos->next = xcalloc(sizeof(*pos), 1);
pos->next = xcalloc(1, sizeof(*pos));
pos = pos->next;
} else {
subtitles = pos = xcalloc(sizeof(*pos), 1);
subtitles = pos = xcalloc(1, sizeof(*pos));
}
pos->text = sp->text;
}

34
tools/lib/api/fs/fs.c
View File

@ -7,6 +7,10 @@
#include <stdlib.h>
#include <string.h>
#include <sys/vfs.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <unistd.h>
#include "debugfs.h"
#include "fs.h"
@ -163,3 +167,33 @@ const char *name##__mountpoint(void) \
FS__MOUNTPOINT(sysfs, FS__SYSFS);
FS__MOUNTPOINT(procfs, FS__PROCFS);
int filename__read_int(const char *filename, int *value)
{
char line[64];
int fd = open(filename, O_RDONLY), err = -1;
if (fd < 0)
return -1;
if (read(fd, line, sizeof(line)) > 0) {
*value = atoi(line);
err = 0;
}
close(fd);
return err;
}
int sysctl__read_int(const char *sysctl, int *value)
{
char path[PATH_MAX];
const char *procfs = procfs__mountpoint();
if (!procfs)
return -1;
snprintf(path, sizeof(path), "%s/sys/%s", procfs, sysctl);
return filename__read_int(path, value);
}

3
tools/lib/api/fs/fs.h
View File

@ -11,4 +11,7 @@
const char *sysfs__mountpoint(void);
const char *procfs__mountpoint(void);
int filename__read_int(const char *filename, int *value);
int sysctl__read_int(const char *sysctl, int *value);
#endif /* __API_FS__ */

4
tools/perf/Documentation/perf.txt
View File

@ -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

1
tools/perf/Makefile.perf
View File

@ -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

420
tools/perf/bench/mem-memcpy.c
View File

@ -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[] = {
@ -110,7 +115,161 @@ static double timeval2double(struct timeval *ts)
(double)ts->tv_usec / (double)1000000;
}
static void alloc_mem(void **dst, void **src, size_t length)
#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)
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,
info->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);
totallen = (double)len * iterations;
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; info->routines[i].name; i++) {
if (!strcmp(info->routines[i].name, routine))
break;
}
if (!info->routines[i].name) {
printf("Unknown routine:%s\n", routine);
printf("Available routines...\n");
for (i = 0; info->routines[i].name; i++) {
printf("\t%s ... %s\n",
info->routines[i].name, info->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] =
info->do_cycle(&info->routines[i], len, false);
result_cycle[1] =
info->do_cycle(&info->routines[i], len, true);
} else {
result_bps[0] =
info->do_gettimeofday(&info->routines[i],
len, false);
result_bps[1] =
info->do_gettimeofday(&info->routines[i],
len, true);
}
} else {
if (use_cycle) {
result_cycle[pf] =
info->do_cycle(&info->routines[i],
len, only_prefault);
} else {
result_bps[pf] =
info->do_gettimeofday(&info->routines[i],
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]
/ totallen);
printf(" %14lf Cycle/Byte (with prefault)\n",
(double)result_cycle[1]
/ totallen);
} 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]
/ totallen);
} 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] / totallen,
(double)result_cycle[1] / totallen);
} else {
printf("%lf %lf\n",
result_bps[0], result_bps[1]);
}
} else {
if (use_cycle) {
printf("%lf\n", (double)result_cycle[pf]
/ totallen);
} 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;
}
static void memcpy_alloc_mem(void **dst, void **src, size_t length)
{
*dst = zalloc(length);
if (!*dst)
@ -123,13 +282,14 @@ static void alloc_mem(void **dst, void **src, size_t length)
memset(*src, 0, length);
}
static u64 do_memcpy_cycle(memcpy_t fn, size_t len, bool prefault)
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;
alloc_mem(&src, &dst, len);
memcpy_alloc_mem(&src, &dst, len);
if (prefault)
fn(dst, src, len);
@ -144,13 +304,15 @@ static u64 do_memcpy_cycle(memcpy_t fn, size_t len, bool prefault)
return cycle_end - cycle_start;
}
static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
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;
alloc_mem(&src, &dst, len);
memcpy_alloc_mem(&src, &dst, len);
if (prefault)
fn(dst, src, len);
@ -164,149 +326,105 @@ static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
free(src);
free(dst);
return (double)((double)len / timeval2double(&tv_diff));
return (double)(((double)len * iterations) / 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_memcpy(int argc, const char **argv,
const char *prefix __maybe_unused)
{
int i;
size_t len;
double result_bps[2];
u64 result_cycle[2];
struct bench_mem_info info = {
.routines = memcpy_routines,
.do_cycle = do_memcpy_cycle,
.do_gettimeofday = do_memcpy_gettimeofday,
.usage = bench_mem_memcpy_usage,
};
argc = parse_options(argc, argv, options,
bench_mem_memcpy_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_memcpy_cycle(routines[i].fn, len, false);
result_cycle[1] =
do_memcpy_cycle(routines[i].fn, len, true);
} else {
result_bps[0] =
do_memcpy_gettimeofday(routines[i].fn,
len, false);
result_bps[1] =
do_memcpy_gettimeofday(routines[i].fn,
len, true);
}
} else {
if (use_cycle) {
result_cycle[pf] =
do_memcpy_cycle(routines[i].fn,
len, only_prefault);
} else {
result_bps[pf] =
do_memcpy_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;
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);
}

304
tools/perf/bench/mem-memset.c
View File

@ -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;
}

13
tools/perf/builtin-buildid-cache.c
View File

@ -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:

3
tools/perf/builtin-kvm.c
View File

@ -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",

12
tools/perf/builtin-trace.c
View File

@ -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));

14
tools/perf/perf.c
View File

@ -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], "--"))

2
tools/perf/tests/attr/base-record
View File

@ -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

2
tools/perf/tests/attr/base-stat
View File

@ -5,7 +5,7 @@ group_fd=-1
flags=0|8
cpu=*
type=0
size=96
size=104
config=0
sample_period=0
sample_type=0

2
tools/perf/ui/browsers/hists.c
View File

@ -1252,7 +1252,7 @@ static int hists__browser_title(struct hists *hists,
nr_samples = convert_unit(nr_samples, &unit);
printed = scnprintf(bf, size,
"Samples: %lu%c of event '%s', Event count (approx.): %lu",
"Samples: %lu%c of event '%s', Event count (approx.): %" PRIu64,
nr_samples, unit, ev_name, nr_events);

4
tools/perf/ui/hist.c
View File

@ -162,8 +162,8 @@ static int __hpp__sort(struct hist_entry *a, struct hist_entry *b,
return ret;
nr_members = evsel->nr_members;
fields_a = calloc(sizeof(*fields_a), nr_members);
fields_b = calloc(sizeof(*fields_b), nr_members);
fields_a = calloc(nr_members, sizeof(*fields_a));
fields_b = calloc(nr_members, sizeof(*fields_b));
if (!fields_a || !fields_b)
goto out;

9
tools/perf/util/build-id.c
View File

@ -410,21 +410,18 @@ int perf_session__cache_build_ids(struct perf_session *session)
{
struct rb_node *nd;
int ret;
char debugdir[PATH_MAX];
if (no_buildid_cache)
return 0;
snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir);
if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
if (mkdir(buildid_dir, 0755) != 0 && errno != EEXIST)
return -1;
ret = machine__cache_build_ids(&session->machines.host, debugdir);
ret = machine__cache_build_ids(&session->machines.host, buildid_dir);
for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
struct machine *pos = rb_entry(nd, struct machine, rb_node);
ret |= machine__cache_build_ids(pos, debugdir);
ret |= machine__cache_build_ids(pos, buildid_dir);
}
return ret ? -1 : 0;
}

2
tools/perf/util/callchain.c
View File

@ -77,7 +77,7 @@ int parse_callchain_record_opt(const char *arg)
ret = 0;
} else
pr_err("callchain: No more arguments "
"needed for -g fp\n");
"needed for --call-graph fp\n");
break;
#ifdef HAVE_DWARF_UNWIND_SUPPORT

10
tools/perf/util/config.c
View File

@ -522,7 +522,7 @@ static int buildid_dir_command_config(const char *var, const char *value,
const char *v;
/* same dir for all commands */
if (!prefixcmp(var, "buildid.") && !strcmp(var + 8, "dir")) {
if (!strcmp(var, "buildid.dir")) {
v = perf_config_dirname(var, value);
if (!v)
return -1;
@ -539,12 +539,14 @@ static void check_buildid_dir_config(void)
perf_config(buildid_dir_command_config, &c);
}
void set_buildid_dir(void)
void set_buildid_dir(const char *dir)
{
buildid_dir[0] = '\0';
if (dir)
scnprintf(buildid_dir, MAXPATHLEN-1, "%s", dir);
/* try config file */
check_buildid_dir_config();
if (buildid_dir[0] == '\0')
check_buildid_dir_config();
/* default to $HOME/.debug */
if (buildid_dir[0] == '\0') {

23
tools/perf/util/evlist.c
View File

@ -8,6 +8,7 @@
*/
#include "util.h"
#include <api/fs/debugfs.h>
#include <api/fs/fs.h>
#include <poll.h>
#include "cpumap.h"
#include "thread_map.h"
@ -1483,6 +1484,28 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
return 0;
}
int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size)
{
char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
int value;
switch (err) {
case EPERM:
sysctl__read_int("kernel/perf_event_mlock_kb", &value);
scnprintf(buf, size, "Error:\t%s.\n"
"Hint:\tCheck /proc/sys/kernel/perf_event_mlock_kb (%d kB) setting.\n"
"Hint:\tTried using %zd kB.\n"
"Hint:\tTry using a bigger -m/--mmap-pages value.",
emsg, value, evlist->mmap_len / 1024);
break;
default:
scnprintf(buf, size, "%s", emsg);
break;
}
return 0;
}
void perf_evlist__to_front(struct perf_evlist *evlist,
struct perf_evsel *move_evsel)
{

1
tools/perf/util/evlist.h
View File

@ -185,6 +185,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp);
int perf_evlist__strerror_tp(struct perf_evlist *evlist, int err, char *buf, size_t size);
int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size);
int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size);
static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm)
{

72
tools/perf/util/machine.c
View File

@ -1385,19 +1385,46 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
static int add_callchain_ip(struct thread *thread,
struct symbol **parent,
struct addr_location *root_al,
int cpumode,
bool branch_history,
u64 ip)
{
struct addr_location al;
al.filtered = 0;
al.sym = NULL;
if (cpumode == -1)
if (branch_history)
thread__find_cpumode_addr_location(thread, MAP__FUNCTION,
ip, &al);
else
else {
u8 cpumode = PERF_RECORD_MISC_USER;
if (ip >= PERF_CONTEXT_MAX) {
switch (ip) {
case PERF_CONTEXT_HV:
cpumode = PERF_RECORD_MISC_HYPERVISOR;
break;
case PERF_CONTEXT_KERNEL:
cpumode = PERF_RECORD_MISC_KERNEL;
break;
case PERF_CONTEXT_USER:
cpumode = PERF_RECORD_MISC_USER;
break;
default:
pr_debug("invalid callchain context: "
"%"PRId64"\n", (s64) ip);
/*
* It seems the callchain is corrupted.
* Discard all.
*/
callchain_cursor_reset(&callchain_cursor);
return 1;
}
return 0;
}
thread__find_addr_location(thread, cpumode, MAP__FUNCTION,
ip, &al);
}
if (al.sym != NULL) {
if (sort__has_parent && !*parent &&
symbol__match_regex(al.sym, &parent_regex))
@ -1480,11 +1507,8 @@ static int thread__resolve_callchain_sample(struct thread *thread,
struct addr_location *root_al,
int max_stack)
{
u8 cpumode = PERF_RECORD_MISC_USER;
int chain_nr = min(max_stack, (int)chain->nr);
int i;
int j;
int err;
int i, j, err;
int skip_idx = -1;
int first_call = 0;
@ -1542,10 +1566,10 @@ static int thread__resolve_callchain_sample(struct thread *thread,
for (i = 0; i < nr; i++) {
err = add_callchain_ip(thread, parent, root_al,
-1, be[i].to);
true, be[i].to);
if (!err)
err = add_callchain_ip(thread, parent, root_al,
-1, be[i].from);
true, be[i].from);
if (err == -EINVAL)
break;
if (err)
@ -1574,36 +1598,10 @@ check_calls:
#endif
ip = chain->ips[j];
if (ip >= PERF_CONTEXT_MAX) {
switch (ip) {
case PERF_CONTEXT_HV:
cpumode = PERF_RECORD_MISC_HYPERVISOR;
break;
case PERF_CONTEXT_KERNEL:
cpumode = PERF_RECORD_MISC_KERNEL;
break;
case PERF_CONTEXT_USER:
cpumode = PERF_RECORD_MISC_USER;
break;
default:
pr_debug("invalid callchain context: "
"%"PRId64"\n", (s64) ip);
/*
* It seems the callchain is corrupted.
* Discard all.
*/
callchain_cursor_reset(&callchain_cursor);
return 0;
}
continue;
}
err = add_callchain_ip(thread, parent, root_al, false, ip);
err = add_callchain_ip(thread, parent, root_al,
cpumode, ip);
if (err == -EINVAL)
break;
if (err)
return err;
return (err < 0) ? err : 0;
}
return 0;

11
tools/perf/util/record.c
View File

@ -137,16 +137,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
static int get_max_rate(unsigned int *rate)
{
char path[PATH_MAX];
const char *procfs = procfs__mountpoint();
if (!procfs)
return -1;
snprintf(path, PATH_MAX,
"%s/sys/kernel/perf_event_max_sample_rate", procfs);
return filename__read_int(path, (int *) rate);
return sysctl__read_int("kernel/perf_event_max_sample_rate", (int *)rate);
}
static int record_opts__config_freq(struct record_opts *opts)

26
tools/perf/util/util.c
View File

@ -442,23 +442,6 @@ unsigned long parse_tag_value(const char *str, struct parse_tag *tags)
return (unsigned long) -1;
}
int filename__read_int(const char *filename, int *value)
{
char line[64];
int fd = open(filename, O_RDONLY), err = -1;
if (fd < 0)
return -1;
if (read(fd, line, sizeof(line)) > 0) {
*value = atoi(line);
err = 0;
}
close(fd);
return err;
}
int filename__read_str(const char *filename, char **buf, size_t *sizep)
{
size_t size = 0, alloc_size = 0;
@ -523,16 +506,9 @@ const char *get_filename_for_perf_kvm(void)
int perf_event_paranoid(void)
{
char path[PATH_MAX];
const char *procfs = procfs__mountpoint();
int value;
if (!procfs)
return INT_MAX;
scnprintf(path, PATH_MAX, "%s/sys/kernel/perf_event_paranoid", procfs);
if (filename__read_int(path, &value))
if (sysctl__read_int("kernel/perf_event_paranoid", &value))
return INT_MAX;
return value;

3
tools/perf/util/util.h
View File

@ -153,7 +153,7 @@ extern void warning(const char *err, ...) __attribute__((format (printf, 1, 2)))
extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN);
extern int prefixcmp(const char *str, const char *prefix);
extern void set_buildid_dir(void);
extern void set_buildid_dir(const char *dir);
static inline const char *skip_prefix(const char *str, const char *prefix)
{
@ -343,7 +343,6 @@ char *get_srcline(struct dso *dso, unsigned long addr, struct symbol *sym,
bool show_sym);
void free_srcline(char *srcline);
int filename__read_int(const char *filename, int *value);
int filename__read_str(const char *filename, char **buf, size_t *sizep);
int perf_event_paranoid(void);

6
tools/thermal/tmon/sysfs.c
View File

@ -446,7 +446,7 @@ int probe_thermal_sysfs(void)
return -1;
}
ptdata.tzi = calloc(sizeof(struct tz_info), ptdata.max_tz_instance+1);
ptdata.tzi = calloc(ptdata.max_tz_instance+1, sizeof(struct tz_info));
if (!ptdata.tzi) {
fprintf(stderr, "Err: allocate tz_info\n");
return -1;
@ -454,8 +454,8 @@ int probe_thermal_sysfs(void)
/* we still show thermal zone information if there is no cdev */
if (ptdata.nr_cooling_dev) {
ptdata.cdi = calloc(sizeof(struct cdev_info),
ptdata.max_cdev_instance + 1);
ptdata.cdi = calloc(ptdata.max_cdev_instance + 1,
sizeof(struct cdev_info));
if (!ptdata.cdi) {
free(ptdata.tzi);
fprintf(stderr, "Err: allocate cdev_info\n");