In the perf annotate view for LoongArch, there is no arrowed line pointing to the target from the branch instruction. This issue is caused by incorrect instruction association and parsing. $ perf record alloc-6276705c94ad1398 # rust benchmark $ perf report 0.28 │ ori $a1, $zero, 0x63 │ move $a2, $zero 10.55 │ addi.d $a3, $a2, 1(0x1) │ sltu $a4, $a3, $s7 9.53 │ masknez $a4, $s7, $a4 │ sub.d $a3, $a3, $a4 12.12 │ st.d $a1, $fp, 24(0x18) │ st.d $a3, $fp, 16(0x10) 16.29 │ slli.d $a2, $a2, 0x2 │ ldx.w $a2, $s8, $a2 12.77 │ st.w $a2, $sp, 724(0x2d4) │ st.w $s0, $sp, 720(0x2d0) 7.03 │ addi.d $a2, $sp, 720(0x2d0) │ addi.d $a1, $a1, -1(0xfff) 12.03 │ move $a2, $a3 │ → bne $a1, $s3, -52(0x3ffcc) # 82ce8 <test::bench::Bencher::iter+0x3f4> 2.50 │ addi.d $a0, $a0, 1(0x1) This patch fixes instruction association issues, such as associating branch instructions with jump_ops instead of call_ops, and corrects false instruction matches. It also implements branch instruction parsing specifically for LoongArch. With this patch, we will be able to see the arrowed line. 0.79 │3ec: ori $a1, $zero, 0x63 │ move $a2, $zero 10.32 │3f4:┌─→addi.d $a3, $a2, 1(0x1) │ │ sltu $a4, $a3, $s7 10.44 │ │ masknez $a4, $s7, $a4 │ │ sub.d $a3, $a3, $a4 14.17 │ │ st.d $a1, $fp, 24(0x18) │ │ st.d $a3, $fp, 16(0x10) 13.15 │ │ slli.d $a2, $a2, 0x2 │ │ ldx.w $a2, $s8, $a2 11.00 │ │ st.w $a2, $sp, 724(0x2d4) │ │ st.w $s0, $sp, 720(0x2d0) 8.00 │ │ addi.d $a2, $sp, 720(0x2d0) │ │ addi.d $a1, $a1, -1(0xfff) 11.99 │ │ move $a2, $a3 │ └──bne $a1, $s3, 3f4 3.17 │ addi.d $a0, $a0, 1(0x1) Signed-off-by: WANG Rui <wangrui@loongson.cn> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: loongarch@lists.linux.dev Cc: loongson-kernel@lists.loongnix.cn Cc: Huacai Chen <chenhuacai@loongson.cn> Cc: Tiezhu Yang <yangtiezhu@loongson.cn> Cc: Ingo Molnar <mingo@redhat.com> Cc: WANG Xuerui <kernel@xen0n.name> Link: https://lore.kernel.org/r/20230620132025.105563-1-wangrui@loongson.cn Signed-off-by: Namhyung Kim <namhyung@kernel.org>
171 lines
3.6 KiB
C
171 lines
3.6 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <linux/compiler.h>
|
|
|
|
static int s390_call__parse(struct arch *arch, struct ins_operands *ops,
|
|
struct map_symbol *ms)
|
|
{
|
|
char *endptr, *tok, *name;
|
|
struct map *map = ms->map;
|
|
struct addr_map_symbol target = {
|
|
.ms = { .map = map, },
|
|
};
|
|
|
|
tok = strchr(ops->raw, ',');
|
|
if (!tok)
|
|
return -1;
|
|
|
|
ops->target.addr = strtoull(tok + 1, &endptr, 16);
|
|
|
|
name = strchr(endptr, '<');
|
|
if (name == NULL)
|
|
return -1;
|
|
|
|
name++;
|
|
|
|
if (arch->objdump.skip_functions_char &&
|
|
strchr(name, arch->objdump.skip_functions_char))
|
|
return -1;
|
|
|
|
tok = strchr(name, '>');
|
|
if (tok == NULL)
|
|
return -1;
|
|
|
|
*tok = '\0';
|
|
ops->target.name = strdup(name);
|
|
*tok = '>';
|
|
|
|
if (ops->target.name == NULL)
|
|
return -1;
|
|
target.addr = map__objdump_2mem(map, ops->target.addr);
|
|
|
|
if (maps__find_ams(ms->maps, &target) == 0 &&
|
|
map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr)
|
|
ops->target.sym = target.ms.sym;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static struct ins_ops s390_call_ops = {
|
|
.parse = s390_call__parse,
|
|
.scnprintf = call__scnprintf,
|
|
};
|
|
|
|
static int s390_mov__parse(struct arch *arch __maybe_unused,
|
|
struct ins_operands *ops,
|
|
struct map_symbol *ms __maybe_unused)
|
|
{
|
|
char *s = strchr(ops->raw, ','), *target, *endptr;
|
|
|
|
if (s == NULL)
|
|
return -1;
|
|
|
|
*s = '\0';
|
|
ops->source.raw = strdup(ops->raw);
|
|
*s = ',';
|
|
|
|
if (ops->source.raw == NULL)
|
|
return -1;
|
|
|
|
target = ++s;
|
|
ops->target.raw = strdup(target);
|
|
if (ops->target.raw == NULL)
|
|
goto out_free_source;
|
|
|
|
ops->target.addr = strtoull(target, &endptr, 16);
|
|
if (endptr == target)
|
|
goto out_free_target;
|
|
|
|
s = strchr(endptr, '<');
|
|
if (s == NULL)
|
|
goto out_free_target;
|
|
endptr = strchr(s + 1, '>');
|
|
if (endptr == NULL)
|
|
goto out_free_target;
|
|
|
|
*endptr = '\0';
|
|
ops->target.name = strdup(s + 1);
|
|
*endptr = '>';
|
|
if (ops->target.name == NULL)
|
|
goto out_free_target;
|
|
|
|
return 0;
|
|
|
|
out_free_target:
|
|
zfree(&ops->target.raw);
|
|
out_free_source:
|
|
zfree(&ops->source.raw);
|
|
return -1;
|
|
}
|
|
|
|
|
|
static struct ins_ops s390_mov_ops = {
|
|
.parse = s390_mov__parse,
|
|
.scnprintf = mov__scnprintf,
|
|
};
|
|
|
|
static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *name)
|
|
{
|
|
struct ins_ops *ops = NULL;
|
|
|
|
/* catch all kind of jumps */
|
|
if (strchr(name, 'j') ||
|
|
!strncmp(name, "bct", 3) ||
|
|
!strncmp(name, "br", 2))
|
|
ops = &jump_ops;
|
|
/* override call/returns */
|
|
if (!strcmp(name, "bras") ||
|
|
!strcmp(name, "brasl") ||
|
|
!strcmp(name, "basr"))
|
|
ops = &s390_call_ops;
|
|
if (!strcmp(name, "br"))
|
|
ops = &ret_ops;
|
|
/* override load/store relative to PC */
|
|
if (!strcmp(name, "lrl") ||
|
|
!strcmp(name, "lgrl") ||
|
|
!strcmp(name, "lgfrl") ||
|
|
!strcmp(name, "llgfrl") ||
|
|
!strcmp(name, "strl") ||
|
|
!strcmp(name, "stgrl"))
|
|
ops = &s390_mov_ops;
|
|
|
|
if (ops)
|
|
arch__associate_ins_ops(arch, name, ops);
|
|
return ops;
|
|
}
|
|
|
|
static int s390__cpuid_parse(struct arch *arch, char *cpuid)
|
|
{
|
|
unsigned int family;
|
|
char model[16], model_c[16], cpumf_v[16], cpumf_a[16];
|
|
int ret;
|
|
|
|
/*
|
|
* cpuid string format:
|
|
* "IBM,family,model-capacity,model[,cpum_cf-version,cpum_cf-authorization]"
|
|
*/
|
|
ret = sscanf(cpuid, "%*[^,],%u,%[^,],%[^,],%[^,],%s", &family, model_c,
|
|
model, cpumf_v, cpumf_a);
|
|
if (ret >= 2) {
|
|
arch->family = family;
|
|
arch->model = 0;
|
|
return 0;
|
|
}
|
|
|
|
return -1;
|
|
}
|
|
|
|
static int s390__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
|
|
{
|
|
int err = 0;
|
|
|
|
if (!arch->initialized) {
|
|
arch->initialized = true;
|
|
arch->associate_instruction_ops = s390__associate_ins_ops;
|
|
if (cpuid) {
|
|
if (s390__cpuid_parse(arch, cpuid))
|
|
err = SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING;
|
|
}
|
|
}
|
|
|
|
return err;
|
|
}
|