summaryrefslogtreecommitdiff
path: root/tools/perf
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf')
-rw-r--r--tools/perf/bench/mem-memcpy-x86-64-asm-def.h6
-rw-r--r--tools/perf/bench/mem-memcpy-x86-64-asm.S2
-rw-r--r--tools/perf/bench/mem-memcpy.c132
-rw-r--r--tools/perf/bench/mem-memset-x86-64-asm-def.h6
-rw-r--r--tools/perf/bench/mem-memset-x86-64-asm.S2
-rw-r--r--tools/perf/config/Makefile.arch4
-rw-r--r--tools/perf/config/feature-checks/Makefile2
-rw-r--r--tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c3
-rw-r--r--tools/perf/util/annotate.c2
-rw-r--r--tools/perf/util/cloexec.c18
-rw-r--r--tools/perf/util/evlist.h2
-rw-r--r--tools/perf/util/include/asm/alternative-asm.h1
-rw-r--r--tools/perf/util/symbol-elf.c5
13 files changed, 105 insertions, 80 deletions
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
index d66ab799b35f..8c0c1a2770c8 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
@@ -1,12 +1,12 @@
-MEMCPY_FN(__memcpy,
+MEMCPY_FN(memcpy_orig,
"x86-64-unrolled",
"unrolled memcpy() in arch/x86/lib/memcpy_64.S")
-MEMCPY_FN(memcpy_c,
+MEMCPY_FN(__memcpy,
"x86-64-movsq",
"movsq-based memcpy() in arch/x86/lib/memcpy_64.S")
-MEMCPY_FN(memcpy_c_e,
+MEMCPY_FN(memcpy_erms,
"x86-64-movsb",
"movsb-based memcpy() in arch/x86/lib/memcpy_64.S")
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index fcd9cf00600a..e4c2c30143b9 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -1,8 +1,6 @@
#define memcpy MEMCPY /* don't hide glibc's memcpy() */
#define altinstr_replacement text
#define globl p2align 4; .globl
-#define Lmemcpy_c globl memcpy_c; memcpy_c
-#define Lmemcpy_c_e globl memcpy_c_e; memcpy_c_e
#include "../../../arch/x86/lib/memcpy_64.S"
/*
* We need to provide note.GNU-stack section, saying that we want
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 6c14afe8c1b1..d3dfb7936dcd 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -36,7 +36,7 @@ static const struct option options[] = {
"Specify length of memory to copy. "
"Available units: B, KB, MB, GB and TB (upper and lower)"),
OPT_STRING('r', "routine", &routine, "default",
- "Specify routine to copy"),
+ "Specify routine to copy, \"all\" runs all available routines"),
OPT_INTEGER('i', "iterations", &iterations,
"repeat memcpy() invocation this number of times"),
OPT_BOOLEAN('c', "cycle", &use_cycle,
@@ -135,55 +135,16 @@ struct bench_mem_info {
const char *const *usage;
};
-static int bench_mem_common(int argc, const char **argv,
- const char *prefix __maybe_unused,
- struct bench_mem_info *info)
+static void __bench_mem_routine(struct bench_mem_info *info, int r_idx, size_t len, double totallen)
{
- int i;
- size_t len;
- double totallen;
+ const struct routine *r = &info->routines[r_idx];
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;
- }
+ printf("Routine %s (%s)\n", r->name, r->desc);
if (bench_format == BENCH_FORMAT_DEFAULT)
printf("# Copying %s Bytes ...\n\n", length_str);
@@ -191,28 +152,17 @@ static int bench_mem_common(int argc, const char **argv,
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);
+ result_cycle[0] = info->do_cycle(r, len, false);
+ result_cycle[1] = info->do_cycle(r, 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);
+ result_bps[0] = info->do_gettimeofday(r, len, false);
+ result_bps[1] = info->do_gettimeofday(r, 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);
- }
+ if (use_cycle)
+ result_cycle[pf] = info->do_cycle(r, len, only_prefault);
+ else
+ result_bps[pf] = info->do_gettimeofday(r, len, only_prefault);
}
switch (bench_format) {
@@ -265,6 +215,60 @@ static int bench_mem_common(int argc, const char **argv,
die("unknown format: %d\n", bench_format);
break;
}
+}
+
+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;
+
+ 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;
+
+ 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;
+
+ if (!strncmp(routine, "all", 3)) {
+ for (i = 0; info->routines[i].name; i++)
+ __bench_mem_routine(info, i, len, totallen);
+ return 0;
+ }
+
+ 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;
+ }
+
+ __bench_mem_routine(info, i, len, totallen);
return 0;
}
@@ -289,7 +293,7 @@ static u64 do_memcpy_cycle(const struct routine *r, size_t len, bool prefault)
memcpy_t fn = r->fn.memcpy;
int i;
- memcpy_alloc_mem(&src, &dst, len);
+ memcpy_alloc_mem(&dst, &src, len);
if (prefault)
fn(dst, src, len);
@@ -312,7 +316,7 @@ static double do_memcpy_gettimeofday(const struct routine *r, size_t len,
void *src = NULL, *dst = NULL;
int i;
- memcpy_alloc_mem(&src, &dst, len);
+ memcpy_alloc_mem(&dst, &src, len);
if (prefault)
fn(dst, src, len);
diff --git a/tools/perf/bench/mem-memset-x86-64-asm-def.h b/tools/perf/bench/mem-memset-x86-64-asm-def.h
index a71dff97c1f5..f02d028771d9 100644
--- a/tools/perf/bench/mem-memset-x86-64-asm-def.h
+++ b/tools/perf/bench/mem-memset-x86-64-asm-def.h
@@ -1,12 +1,12 @@
-MEMSET_FN(__memset,
+MEMSET_FN(memset_orig,
"x86-64-unrolled",
"unrolled memset() in arch/x86/lib/memset_64.S")
-MEMSET_FN(memset_c,
+MEMSET_FN(__memset,
"x86-64-stosq",
"movsq-based memset() in arch/x86/lib/memset_64.S")
-MEMSET_FN(memset_c_e,
+MEMSET_FN(memset_erms,
"x86-64-stosb",
"movsb-based memset() in arch/x86/lib/memset_64.S")
diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S
index 9e5af89ed13a..de278784c866 100644
--- a/tools/perf/bench/mem-memset-x86-64-asm.S
+++ b/tools/perf/bench/mem-memset-x86-64-asm.S
@@ -1,8 +1,6 @@
#define memset MEMSET /* don't hide glibc's memset() */
#define altinstr_replacement text
#define globl p2align 4; .globl
-#define Lmemset_c globl memset_c; memset_c
-#define Lmemset_c_e globl memset_c_e; memset_c_e
#include "../../../arch/x86/lib/memset_64.S"
/*
diff --git a/tools/perf/config/Makefile.arch b/tools/perf/config/Makefile.arch
index ff95a68741d1..ac8721ffa6c8 100644
--- a/tools/perf/config/Makefile.arch
+++ b/tools/perf/config/Makefile.arch
@@ -21,6 +21,10 @@ ifeq ($(RAW_ARCH),x86_64)
endif
endif
+ifeq ($(RAW_ARCH),sparc64)
+ ARCH ?= sparc
+endif
+
ARCH ?= $(RAW_ARCH)
LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 42ac05aaf8ac..b32ff3372514 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -49,7 +49,7 @@ test-hello.bin:
$(BUILD)
test-pthread-attr-setaffinity-np.bin:
- $(BUILD) -Werror -lpthread
+ $(BUILD) -D_GNU_SOURCE -Werror -lpthread
test-stackprotector-all.bin:
$(BUILD) -Werror -fstack-protector-all
diff --git a/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c b/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c
index 0a0d3ecb4e8a..2b81b72eca23 100644
--- a/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c
+++ b/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c
@@ -5,10 +5,11 @@ int main(void)
{
int ret = 0;
pthread_attr_t thread_attr;
+ cpu_set_t cs;
pthread_attr_init(&thread_attr);
/* don't care abt exact args, just the API itself in libpthread */
- ret = pthread_attr_setaffinity_np(&thread_attr, 0, NULL);
+ ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cs), &cs);
return ret;
}
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 61bf9128e1f2..9d9db3b296dd 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -30,6 +30,8 @@ static int disasm_line__parse(char *line, char **namep, char **rawp);
static void ins__delete(struct ins_operands *ops)
{
+ if (ops == NULL)
+ return;
zfree(&ops->source.raw);
zfree(&ops->source.name);
zfree(&ops->target.raw);
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index 47b78b3f0325..6da965bdbc2c 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -25,6 +25,10 @@ static int perf_flag_probe(void)
if (cpu < 0)
cpu = 0;
+ /*
+ * Using -1 for the pid is a workaround to avoid gratuitous jump label
+ * changes.
+ */
while (1) {
/* check cloexec flag */
fd = sys_perf_event_open(&attr, pid, cpu, -1,
@@ -47,16 +51,24 @@ static int perf_flag_probe(void)
err, strerror_r(err, sbuf, sizeof(sbuf)));
/* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */
- fd = sys_perf_event_open(&attr, pid, cpu, -1, 0);
+ while (1) {
+ fd = sys_perf_event_open(&attr, pid, cpu, -1, 0);
+ if (fd < 0 && pid == -1 && errno == EACCES) {
+ pid = 0;
+ continue;
+ }
+ break;
+ }
err = errno;
+ if (fd >= 0)
+ close(fd);
+
if (WARN_ONCE(fd < 0 && err != EBUSY,
"perf_event_open(..., 0) failed unexpectedly with error %d (%s)\n",
err, strerror_r(err, sbuf, sizeof(sbuf))))
return -1;
- close(fd);
-
return 0;
}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index c94a9e03ecf1..e99a67632831 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -28,7 +28,7 @@ struct perf_mmap {
int mask;
int refcnt;
unsigned int prev;
- char event_copy[PERF_SAMPLE_MAX_SIZE];
+ char event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8)));
};
struct perf_evlist {
diff --git a/tools/perf/util/include/asm/alternative-asm.h b/tools/perf/util/include/asm/alternative-asm.h
index 6789d788d494..3a3a0f16456a 100644
--- a/tools/perf/util/include/asm/alternative-asm.h
+++ b/tools/perf/util/include/asm/alternative-asm.h
@@ -4,5 +4,6 @@
/* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */
#define altinstruction_entry #
+#define ALTERNATIVE_2 #
#endif
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index b24f9d8727a8..33b7a2aef713 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -11,6 +11,11 @@
#include <symbol/kallsyms.h>
#include "debug.h"
+#ifndef EM_AARCH64
+#define EM_AARCH64 183 /* ARM 64 bit */
+#endif
+
+
#ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
extern char *cplus_demangle(const char *, int);
generated by cgit (git 2.34.1) at 2025-07-24 13:25:42 +0000