2024-03-28 23:21:31

by Namhyung Kim

Subject: [PATCH 0/4] perf annotate: Use libcapstone as a disasssembler

Hello,

As we've added libcapstone support, it's natural to use it for perf annotate
as well. This change added the capstone support on x86 first. Other archs
can be added later (by someone who can verify it doesn't break things).

For now it tries to use capstone (if available) before objdump. But it
doesn't support source file and line number info. So users should use the
objdump (by passing --objdump=PATH option) if they need them. For example,
this command line will keep the existing behavior (i.e. using objdump).

# not to use capstone for disassembly
$ perf annotate --objdump=objdump

The capstone uses LLVM objdump style output which is slightly different than
the GNU objdump. But it should not have differences besides that. I've
verified the result of data type profiling and it produced the same output
but gave me ~3x speedups.

Thanks,
Namhyung


Cc: Changbin Du <[email protected]>


Namhyung Kim (4):
perf annotate: Use ins__is_xxx() if possible
perf annotate: Add and use ins__is_nop()
perf annotate: Split out util/disasm.c
perf annotate: Use libcapstone to disassemble

tools/perf/util/Build | 1 +
tools/perf/util/annotate.c | 1711 ++---------------------------------
tools/perf/util/annotate.h | 59 +-
tools/perf/util/disasm.c | 1739 ++++++++++++++++++++++++++++++++++++
tools/perf/util/disasm.h | 112 +++
5 files changed, 1914 insertions(+), 1708 deletions(-)
create mode 100644 tools/perf/util/disasm.c
create mode 100644 tools/perf/util/disasm.h

--
2.44.0.478.gd926399ef9-goog

2024-03-28 23:23:10

by Namhyung Kim

Subject: [PATCH 3/4] perf annotate: Split out util/disasm.c

The util/annotate.c code has both disassembly and sample annotation
related codes. Factor out the disasm part so that it can be handled
more easily.

Signed-off-by: Namhyung Kim <[email protected]>
---
tools/perf/util/Build | 1 +
tools/perf/util/annotate.c | 1708 ++----------------------------------
tools/perf/util/annotate.h | 60 +-
tools/perf/util/disasm.c | 1586 +++++++++++++++++++++++++++++++++
tools/perf/util/disasm.h | 112 +++
5 files changed, 1757 insertions(+), 1710 deletions(-)
create mode 100644 tools/perf/util/disasm.c
create mode 100644 tools/perf/util/disasm.h

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index e0a723e24503..aec5a590e349 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -12,6 +12,7 @@ perf-y += config.o
perf-y += copyfile.o
perf-y += ctype.o
perf-y += db-export.o
+perf-y += disasm.o
perf-y += env.o
perf-y += event.o
perf-y += evlist.o
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 5d0ca004dcfb..b795f27f2602 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -16,6 +16,7 @@
#include "build-id.h"
#include "color.h"
#include "config.h"
+#include "disasm.h"
#include "dso.h"
#include "env.h"
#include "map.h"
@@ -64,48 +65,6 @@
/* global annotation options */
struct annotation_options annotate_opts;

-static regex_t file_lineno;
-
-static struct ins_ops *ins__find(struct arch *arch, const char *name);
-static void ins__sort(struct arch *arch);
-static int disasm_line__parse(char *line, const char **namep, char **rawp);
-static int call__scnprintf(struct ins *ins, char *bf, size_t size,
- struct ins_operands *ops, int max_ins_name);
-static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
- struct ins_operands *ops, int max_ins_name);
-
-struct arch {
- const char *name;
- struct ins *instructions;
- size_t nr_instructions;
- size_t nr_instructions_allocated;
- struct ins_ops *(*associate_instruction_ops)(struct arch *arch, const char *name);
- bool sorted_instructions;
- bool initialized;
- const char *insn_suffix;
- void *priv;
- unsigned int model;
- unsigned int family;
- int (*init)(struct arch *arch, char *cpuid);
- bool (*ins_is_fused)(struct arch *arch, const char *ins1,
- const char *ins2);
- struct {
- char comment_char;
- char skip_functions_char;
- char register_char;
- char memory_ref_char;
- char imm_char;
- } objdump;
-};
-
-static struct ins_ops call_ops;
-static struct ins_ops dec_ops;
-static struct ins_ops jump_ops;
-static struct ins_ops mov_ops;
-static struct ins_ops nop_ops;
-static struct ins_ops lock_ops;
-static struct ins_ops ret_ops;
-
/* Data type collection debug statistics */
struct annotated_data_stat ann_data_stat;
LIST_HEAD(ann_insn_stat);
@@ -125,759 +84,6 @@ struct annotated_data_type canary_type = {
},
};

-static int arch__grow_instructions(struct arch *arch)
-{
- struct ins *new_instructions;
- size_t new_nr_allocated;
-
- if (arch->nr_instructions_allocated == 0 && arch->instructions)
- goto grow_from_non_allocated_table;
-
- new_nr_allocated = arch->nr_instructions_allocated + 128;
- new_instructions = realloc(arch->instructions, new_nr_allocated * sizeof(struct ins));
- if (new_instructions == NULL)
- return -1;
-
-out_update_instructions:
- arch->instructions = new_instructions;
- arch->nr_instructions_allocated = new_nr_allocated;
- return 0;
-
-grow_from_non_allocated_table:
- new_nr_allocated = arch->nr_instructions + 128;
- new_instructions = calloc(new_nr_allocated, sizeof(struct ins));
- if (new_instructions == NULL)
- return -1;
-
- memcpy(new_instructions, arch->instructions, arch->nr_instructions);
- goto out_update_instructions;
-}
-
-static int arch__associate_ins_ops(struct arch* arch, const char *name, struct ins_ops *ops)
-{
- struct ins *ins;
-
- if (arch->nr_instructions == arch->nr_instructions_allocated &&
- arch__grow_instructions(arch))
- return -1;
-
- ins = &arch->instructions[arch->nr_instructions];
- ins->name = strdup(name);
- if (!ins->name)
- return -1;
-
- ins->ops = ops;
- arch->nr_instructions++;
-
- ins__sort(arch);
- return 0;
-}
-
-#include "arch/arc/annotate/instructions.c"
-#include "arch/arm/annotate/instructions.c"
-#include "arch/arm64/annotate/instructions.c"
-#include "arch/csky/annotate/instructions.c"
-#include "arch/loongarch/annotate/instructions.c"
-#include "arch/mips/annotate/instructions.c"
-#include "arch/x86/annotate/instructions.c"
-#include "arch/powerpc/annotate/instructions.c"
-#include "arch/riscv64/annotate/instructions.c"
-#include "arch/s390/annotate/instructions.c"
-#include "arch/sparc/annotate/instructions.c"
-
-static struct arch architectures[] = {
- {
- .name = "arc",
- .init = arc__annotate_init,
- },
- {
- .name = "arm",
- .init = arm__annotate_init,
- },
- {
- .name = "arm64",
- .init = arm64__annotate_init,
- },
- {
- .name = "csky",
- .init = csky__annotate_init,
- },
- {
- .name = "mips",
- .init = mips__annotate_init,
- .objdump = {
- .comment_char = '#',
- },
- },
- {
- .name = "x86",
- .init = x86__annotate_init,
- .instructions = x86__instructions,
- .nr_instructions = ARRAY_SIZE(x86__instructions),
- .insn_suffix = "bwlq",
- .objdump = {
- .comment_char = '#',
- .register_char = '%',
- .memory_ref_char = '(',
- .imm_char = '$',
- },
- },
- {
- .name = "powerpc",
- .init = powerpc__annotate_init,
- },
- {
- .name = "riscv64",
- .init = riscv64__annotate_init,
- },
- {
- .name = "s390",
- .init = s390__annotate_init,
- .objdump = {
- .comment_char = '#',
- },
- },
- {
- .name = "sparc",
- .init = sparc__annotate_init,
- .objdump = {
- .comment_char = '#',
- },
- },
- {
- .name = "loongarch",
- .init = loongarch__annotate_init,
- .objdump = {
- .comment_char = '#',
- },
- },
-};
-
-static void ins__delete(struct ins_operands *ops)
-{
- if (ops == NULL)
- return;
- zfree(&ops->source.raw);
- zfree(&ops->source.name);
- zfree(&ops->target.raw);
- zfree(&ops->target.name);
-}
-
-static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size,
- struct ins_operands *ops, int max_ins_name)
-{
- return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->raw);
-}
-
-int ins__scnprintf(struct ins *ins, char *bf, size_t size,
- struct ins_operands *ops, int max_ins_name)
-{
- if (ins->ops->scnprintf)
- return ins->ops->scnprintf(ins, bf, size, ops, max_ins_name);
-
- return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
-}
-
-bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2)
-{
- if (!arch || !arch->ins_is_fused)
- return false;
-
- return arch->ins_is_fused(arch, ins1, ins2);
-}
-
-static int 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, },
- };
-
- ops->target.addr = strtoull(ops->raw, &endptr, 16);
-
- name = strchr(endptr, '<');
- if (name == NULL)
- goto indirect_call;
-
- 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;
-find_target:
- 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;
-
-indirect_call:
- tok = strchr(endptr, '*');
- if (tok != NULL) {
- endptr++;
-
- /* Indirect call can use a non-rip register and offset: callq *0x8(%rbx).
- * Do not parse such instruction. */
- if (strstr(endptr, "(%r") == NULL)
- ops->target.addr = strtoull(endptr, NULL, 16);
- }
- goto find_target;
-}
-
-static int call__scnprintf(struct ins *ins, char *bf, size_t size,
- struct ins_operands *ops, int max_ins_name)
-{
- if (ops->target.sym)
- return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.sym->name);
-
- if (ops->target.addr == 0)
- return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
-
- if (ops->target.name)
- return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.name);
-
- return scnprintf(bf, size, "%-*s *%" PRIx64, max_ins_name, ins->name, ops->target.addr);
-}
-
-static struct ins_ops call_ops = {
- .parse = call__parse,
- .scnprintf = call__scnprintf,
-};
-
-bool ins__is_call(const struct ins *ins)
-{
- return ins->ops == &call_ops || ins->ops == &s390_call_ops || ins->ops == &loongarch_call_ops;
-}
-
-/*
- * Prevents from matching commas in the comment section, e.g.:
- * ffff200008446e70: b.cs ffff2000084470f4 <generic_exec_single+0x314> // b.hs, b.nlast
- *
- * and skip comma as part of function arguments, e.g.:
- * 1d8b4ac <linemap_lookup(line_maps const*, unsigned int)+0xcc>
- */
-static inline const char *validate_comma(const char *c, struct ins_operands *ops)
-{
- if (ops->jump.raw_comment && c > ops->jump.raw_comment)
- return NULL;
-
- if (ops->jump.raw_func_start && c > ops->jump.raw_func_start)
- return NULL;
-
- return c;
-}
-
-static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
-{
- struct map *map = ms->map;
- struct symbol *sym = ms->sym;
- struct addr_map_symbol target = {
- .ms = { .map = map, },
- };
- const char *c = strchr(ops->raw, ',');
- u64 start, end;
-
- ops->jump.raw_comment = strchr(ops->raw, arch->objdump.comment_char);
- ops->jump.raw_func_start = strchr(ops->raw, '<');
-
- c = validate_comma(c, ops);
-
- /*
- * Examples of lines to parse for the _cpp_lex_token@@Base
- * function:
- *
- * 1159e6c: jne 115aa32 <_cpp_lex_token@@Base+0xf92>
- * 1159e8b: jne c469be <cpp_named_operator2name@@Base+0xa72>
- *
- * The first is a jump to an offset inside the same function,
- * the second is to another function, i.e. that 0xa72 is an
- * offset in the cpp_named_operator2name@@base function.
- */
- /*
- * skip over possible up to 2 operands to get to address, e.g.:
- * tbnz w0, #26, ffff0000083cd190 <security_file_permission+0xd0>
- */
- if (c++ != NULL) {
- ops->target.addr = strtoull(c, NULL, 16);
- if (!ops->target.addr) {
- c = strchr(c, ',');
- c = validate_comma(c, ops);
- if (c++ != NULL)
- ops->target.addr = strtoull(c, NULL, 16);
- }
- } else {
- ops->target.addr = strtoull(ops->raw, NULL, 16);
- }
-
- target.addr = map__objdump_2mem(map, ops->target.addr);
- start = map__unmap_ip(map, sym->start);
- end = map__unmap_ip(map, sym->end);
-
- ops->target.outside = target.addr < start || target.addr > end;
-
- /*
- * FIXME: things like this in _cpp_lex_token (gcc's cc1 program):
-
- cpp_named_operator2name@@Base+0xa72
-
- * Point to a place that is after the cpp_named_operator2name
- * boundaries, i.e. in the ELF symbol table for cc1
- * cpp_named_operator2name is marked as being 32-bytes long, but it in
- * fact is much larger than that, so we seem to need a symbols__find()
- * routine that looks for >= current->start and < next_symbol->start,
- * possibly just for C++ objects?
- *
- * For now lets just make some progress by marking jumps to outside the
- * current function as call like.
- *
- * Actual navigation will come next, with further understanding of how
- * the symbol searching and disassembly should be done.
- */
- 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;
-
- if (!ops->target.outside) {
- ops->target.offset = target.addr - start;
- ops->target.offset_avail = true;
- } else {
- ops->target.offset_avail = false;
- }
-
- return 0;
-}
-
-static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
- struct ins_operands *ops, int max_ins_name)
-{
- const char *c;
-
- if (!ops->target.addr || ops->target.offset < 0)
- return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
-
- if (ops->target.outside && ops->target.sym != NULL)
- return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.sym->name);
-
- c = strchr(ops->raw, ',');
- c = validate_comma(c, ops);
-
- if (c != NULL) {
- const char *c2 = strchr(c + 1, ',');
-
- c2 = validate_comma(c2, ops);
- /* check for 3-op insn */
- if (c2 != NULL)
- c = c2;
- c++;
-
- /* mirror arch objdump's space-after-comma style */
- if (*c == ' ')
- c++;
- }
-
- return scnprintf(bf, size, "%-*s %.*s%" PRIx64, max_ins_name,
- ins->name, c ? c - ops->raw : 0, ops->raw,
- ops->target.offset);
-}
-
-static void jump__delete(struct ins_operands *ops __maybe_unused)
-{
- /*
- * The ops->jump.raw_comment and ops->jump.raw_func_start belong to the
- * raw string, don't free them.
- */
-}
-
-static struct ins_ops jump_ops = {
- .free = jump__delete,
- .parse = jump__parse,
- .scnprintf = jump__scnprintf,
-};
-
-bool ins__is_jump(const struct ins *ins)
-{
- return ins->ops == &jump_ops || ins->ops == &loongarch_jump_ops;
-}
-
-static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep)
-{
- char *endptr, *name, *t;
-
- if (strstr(raw, "(%rip)") == NULL)
- return 0;
-
- *addrp = strtoull(comment, &endptr, 16);
- if (endptr == comment)
- return 0;
- name = strchr(endptr, '<');
- if (name == NULL)
- return -1;
-
- name++;
-
- t = strchr(name, '>');
- if (t == NULL)
- return 0;
-
- *t = '\0';
- *namep = strdup(name);
- *t = '>';
-
- return 0;
-}
-
-static int lock__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
-{
- ops->locked.ops = zalloc(sizeof(*ops->locked.ops));
- if (ops->locked.ops == NULL)
- return 0;
-
- if (disasm_line__parse(ops->raw, &ops->locked.ins.name, &ops->locked.ops->raw) < 0)
- goto out_free_ops;
-
- ops->locked.ins.ops = ins__find(arch, ops->locked.ins.name);
-
- if (ops->locked.ins.ops == NULL)
- goto out_free_ops;
-
- if (ops->locked.ins.ops->parse &&
- ops->locked.ins.ops->parse(arch, ops->locked.ops, ms) < 0)
- goto out_free_ops;
-
- return 0;
-
-out_free_ops:
- zfree(&ops->locked.ops);
- return 0;
-}
-
-static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
- struct ins_operands *ops, int max_ins_name)
-{
- int printed;
-
- if (ops->locked.ins.ops == NULL)
- return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
-
- printed = scnprintf(bf, size, "%-*s ", max_ins_name, ins->name);
- return printed + ins__scnprintf(&ops->locked.ins, bf + printed,
- size - printed, ops->locked.ops, max_ins_name);
-}
-
-static void lock__delete(struct ins_operands *ops)
-{
- struct ins *ins = &ops->locked.ins;
-
- if (ins->ops && ins->ops->free)
- ins->ops->free(ops->locked.ops);
- else
- ins__delete(ops->locked.ops);
-
- zfree(&ops->locked.ops);
- zfree(&ops->target.raw);
- zfree(&ops->target.name);
-}
-
-static struct ins_ops lock_ops = {
- .free = lock__delete,
- .parse = lock__parse,
- .scnprintf = lock__scnprintf,
-};
-
-/*
- * Check if the operand has more than one registers like x86 SIB addressing:
- * 0x1234(%rax, %rbx, 8)
- *
- * But it doesn't care segment selectors like %gs:0x5678(%rcx), so just check
- * the input string after 'memory_ref_char' if exists.
- */
-static bool check_multi_regs(struct arch *arch, const char *op)
-{
- int count = 0;
-
- if (arch->objdump.register_char == 0)
- return false;
-
- if (arch->objdump.memory_ref_char) {
- op = strchr(op, arch->objdump.memory_ref_char);
- if (op == NULL)
- return false;
- }
-
- while ((op = strchr(op, arch->objdump.register_char)) != NULL) {
- count++;
- op++;
- }
-
- return count > 1;
-}
-
-static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms __maybe_unused)
-{
- char *s = strchr(ops->raw, ','), *target, *comment, prev;
-
- if (s == NULL)
- return -1;
-
- *s = '\0';
-
- /*
- * x86 SIB addressing has something like 0x8(%rax, %rcx, 1)
- * then it needs to have the closing parenthesis.
- */
- if (strchr(ops->raw, '(')) {
- *s = ',';
- s = strchr(ops->raw, ')');
- if (s == NULL || s[1] != ',')
- return -1;
- *++s = '\0';
- }
-
- ops->source.raw = strdup(ops->raw);
- *s = ',';
-
- if (ops->source.raw == NULL)
- return -1;
-
- ops->source.multi_regs = check_multi_regs(arch, ops->source.raw);
-
- target = skip_spaces(++s);
- comment = strchr(s, arch->objdump.comment_char);
-
- if (comment != NULL)
- s = comment - 1;
- else
- s = strchr(s, '\0') - 1;
-
- while (s > target && isspace(s[0]))
- --s;
- s++;
- prev = *s;
- *s = '\0';
-
- ops->target.raw = strdup(target);
- *s = prev;
-
- if (ops->target.raw == NULL)
- goto out_free_source;
-
- ops->target.multi_regs = check_multi_regs(arch, ops->target.raw);
-
- if (comment == NULL)
- return 0;
-
- comment = skip_spaces(comment);
- comment__symbol(ops->source.raw, comment + 1, &ops->source.addr, &ops->source.name);
- comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
-
- return 0;
-
-out_free_source:
- zfree(&ops->source.raw);
- return -1;
-}
-
-static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
- struct ins_operands *ops, int max_ins_name)
-{
- return scnprintf(bf, size, "%-*s %s,%s", max_ins_name, ins->name,
- ops->source.name ?: ops->source.raw,
- ops->target.name ?: ops->target.raw);
-}
-
-static struct ins_ops mov_ops = {
- .parse = mov__parse,
- .scnprintf = mov__scnprintf,
-};
-
-static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms __maybe_unused)
-{
- char *target, *comment, *s, prev;
-
- target = s = ops->raw;
-
- while (s[0] != '\0' && !isspace(s[0]))
- ++s;
- prev = *s;
- *s = '\0';
-
- ops->target.raw = strdup(target);
- *s = prev;
-
- if (ops->target.raw == NULL)
- return -1;
-
- comment = strchr(s, arch->objdump.comment_char);
- if (comment == NULL)
- return 0;
-
- comment = skip_spaces(comment);
- comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
-
- return 0;
-}
-
-static int dec__scnprintf(struct ins *ins, char *bf, size_t size,
- struct ins_operands *ops, int max_ins_name)
-{
- return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name,
- ops->target.name ?: ops->target.raw);
-}
-
-static struct ins_ops dec_ops = {
- .parse = dec__parse,
- .scnprintf = dec__scnprintf,
-};
-
-static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size,
- struct ins_operands *ops __maybe_unused, int max_ins_name)
-{
- return scnprintf(bf, size, "%-*s", max_ins_name, "nop");
-}
-
-static struct ins_ops nop_ops = {
- .scnprintf = nop__scnprintf,
-};
-
-static struct ins_ops ret_ops = {
- .scnprintf = ins__raw_scnprintf,
-};
-
-bool ins__is_nop(const struct ins *ins)
-{
- return ins->ops == &nop_ops;
-}
-
-bool ins__is_ret(const struct ins *ins)
-{
- return ins->ops == &ret_ops;
-}
-
-bool ins__is_lock(const struct ins *ins)
-{
- return ins->ops == &lock_ops;
-}
-
-static int ins__key_cmp(const void *name, const void *insp)
-{
- const struct ins *ins = insp;
-
- return strcmp(name, ins->name);
-}
-
-static int ins__cmp(const void *a, const void *b)
-{
- const struct ins *ia = a;
- const struct ins *ib = b;
-
- return strcmp(ia->name, ib->name);
-}
-
-static void ins__sort(struct arch *arch)
-{
- const int nmemb = arch->nr_instructions;
-
- qsort(arch->instructions, nmemb, sizeof(struct ins), ins__cmp);
-}
-
-static struct ins_ops *__ins__find(struct arch *arch, const char *name)
-{
- struct ins *ins;
- const int nmemb = arch->nr_instructions;
-
- if (!arch->sorted_instructions) {
- ins__sort(arch);
- arch->sorted_instructions = true;
- }
-
- ins = bsearch(name, arch->instructions, nmemb, sizeof(struct ins), ins__key_cmp);
- if (ins)
- return ins->ops;
-
- if (arch->insn_suffix) {
- char tmp[32];
- char suffix;
- size_t len = strlen(name);
-
- if (len == 0 || len >= sizeof(tmp))
- return NULL;
-
- suffix = name[len - 1];
- if (strchr(arch->insn_suffix, suffix) == NULL)
- return NULL;
-
- strcpy(tmp, name);
- tmp[len - 1] = '\0'; /* remove the suffix and check again */
-
- ins = bsearch(tmp, arch->instructions, nmemb, sizeof(struct ins), ins__key_cmp);
- }
- return ins ? ins->ops : NULL;
-}
-
-static struct ins_ops *ins__find(struct arch *arch, const char *name)
-{
- struct ins_ops *ops = __ins__find(arch, name);
-
- if (!ops && arch->associate_instruction_ops)
- ops = arch->associate_instruction_ops(arch, name);
-
- return ops;
-}
-
-static int arch__key_cmp(const void *name, const void *archp)
-{
- const struct arch *arch = archp;
-
- return strcmp(name, arch->name);
-}
-
-static int arch__cmp(const void *a, const void *b)
-{
- const struct arch *aa = a;
- const struct arch *ab = b;
-
- return strcmp(aa->name, ab->name);
-}
-
-static void arch__sort(void)
-{
- const int nmemb = ARRAY_SIZE(architectures);
-
- qsort(architectures, nmemb, sizeof(struct arch), arch__cmp);
-}
-
-static struct arch *arch__find(const char *name)
-{
- const int nmemb = ARRAY_SIZE(architectures);
- static bool sorted;
-
- if (!sorted) {
- arch__sort();
- sorted = true;
- }
-
- return bsearch(name, architectures, nmemb, sizeof(struct arch), arch__key_cmp);
-}
-
-bool arch__is(struct arch *arch, const char *name)
-{
- return !strcmp(arch->name, name);
-}
-
/* symbol histogram: key = offset << 16 | evsel->core.idx */
static size_t sym_hist_hash(long key, void *ctx __maybe_unused)
{
@@ -1214,212 +420,76 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64
branch->cover_insn += cover_insn;
}
}
-}
-
-static int annotation__compute_ipc(struct annotation *notes, size_t size)
-{
- int err = 0;
- s64 offset;
-
- if (!notes->branch || !notes->branch->cycles_hist)
- return 0;
-
- notes->branch->total_insn = annotation__count_insn(notes, 0, size - 1);
- notes->branch->hit_cycles = 0;
- notes->branch->hit_insn = 0;
- notes->branch->cover_insn = 0;
-
- annotation__lock(notes);
- for (offset = size - 1; offset >= 0; --offset) {
- struct cyc_hist *ch;
-
- ch = &notes->branch->cycles_hist[offset];
- if (ch && ch->cycles) {
- struct annotation_line *al;
-
- al = notes->src->offsets[offset];
- if (al && al->cycles == NULL) {
- al->cycles = zalloc(sizeof(*al->cycles));
- if (al->cycles == NULL) {
- err = ENOMEM;
- break;
- }
- }
- if (ch->have_start)
- annotation__count_and_fill(notes, ch->start, offset, ch);
- if (al && ch->num_aggr) {
- al->cycles->avg = ch->cycles_aggr / ch->num_aggr;
- al->cycles->max = ch->cycles_max;
- al->cycles->min = ch->cycles_min;
- }
- }
- }
-
- if (err) {
- while (++offset < (s64)size) {
- struct cyc_hist *ch = &notes->branch->cycles_hist[offset];
-
- if (ch && ch->cycles) {
- struct annotation_line *al = notes->src->offsets[offset];
- if (al)
- zfree(&al->cycles);
- }
- }
- }
-
- annotation__unlock(notes);
- return 0;
-}
-
-int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample,
- struct evsel *evsel)
-{
- return symbol__inc_addr_samples(&ams->ms, evsel, ams->al_addr, sample);
-}
-
-int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample,
- struct evsel *evsel, u64 ip)
-{
- return symbol__inc_addr_samples(&he->ms, evsel, ip, sample);
-}
-
-static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map_symbol *ms)
-{
- dl->ins.ops = ins__find(arch, dl->ins.name);
-
- if (!dl->ins.ops)
- return;
-
- if (dl->ins.ops->parse && dl->ins.ops->parse(arch, &dl->ops, ms) < 0)
- dl->ins.ops = NULL;
-}
-
-static int disasm_line__parse(char *line, const char **namep, char **rawp)
-{
- char tmp, *name = skip_spaces(line);
-
- if (name[0] == '\0')
- return -1;
-
- *rawp = name + 1;
-
- while ((*rawp)[0] != '\0' && !isspace((*rawp)[0]))
- ++*rawp;
-
- tmp = (*rawp)[0];
- (*rawp)[0] = '\0';
- *namep = strdup(name);
-
- if (*namep == NULL)
- goto out;
-
- (*rawp)[0] = tmp;
- *rawp = strim(*rawp);
-
- return 0;
-
-out:
- return -1;
-}
-
-struct annotate_args {
- struct arch *arch;
- struct map_symbol ms;
- struct evsel *evsel;
- struct annotation_options *options;
- s64 offset;
- char *line;
- int line_nr;
- char *fileloc;
-};
-
-static void annotation_line__init(struct annotation_line *al,
- struct annotate_args *args,
- int nr)
-{
- al->offset = args->offset;
- al->line = strdup(args->line);
- al->line_nr = args->line_nr;
- al->fileloc = args->fileloc;
- al->data_nr = nr;
-}
-
-static void annotation_line__exit(struct annotation_line *al)
-{
- zfree_srcline(&al->path);
- zfree(&al->line);
- zfree(&al->cycles);
-}
-
-static size_t disasm_line_size(int nr)
-{
- struct annotation_line *al;
-
- return (sizeof(struct disasm_line) + (sizeof(al->data[0]) * nr));
-}
-
-/*
- * Allocating the disasm annotation line data with
- * following structure:
- *
- * -------------------------------------------
- * struct disasm_line | struct annotation_line
- * -------------------------------------------
- *
- * We have 'struct annotation_line' member as last member
- * of 'struct disasm_line' to have an easy access.
- */
-static struct disasm_line *disasm_line__new(struct annotate_args *args)
+}
+
+static int annotation__compute_ipc(struct annotation *notes, size_t size)
{
- struct disasm_line *dl = NULL;
- int nr = 1;
+ int err = 0;
+ s64 offset;

- if (evsel__is_group_event(args->evsel))
- nr = args->evsel->core.nr_members;
+ if (!notes->branch || !notes->branch->cycles_hist)
+ return 0;

- dl = zalloc(disasm_line_size(nr));
- if (!dl)
- return NULL;
+ notes->branch->total_insn = annotation__count_insn(notes, 0, size - 1);
+ notes->branch->hit_cycles = 0;
+ notes->branch->hit_insn = 0;
+ notes->branch->cover_insn = 0;

- annotation_line__init(&dl->al, args, nr);
- if (dl->al.line == NULL)
- goto out_delete;
+ annotation__lock(notes);
+ for (offset = size - 1; offset >= 0; --offset) {
+ struct cyc_hist *ch;

- if (args->offset != -1) {
- if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
- goto out_free_line;
+ ch = &notes->branch->cycles_hist[offset];
+ if (ch && ch->cycles) {
+ struct annotation_line *al;

- disasm_line__init_ins(dl, args->arch, &args->ms);
+ al = notes->src->offsets[offset];
+ if (al && al->cycles == NULL) {
+ al->cycles = zalloc(sizeof(*al->cycles));
+ if (al->cycles == NULL) {
+ err = ENOMEM;
+ break;
+ }
+ }
+ if (ch->have_start)
+ annotation__count_and_fill(notes, ch->start, offset, ch);
+ if (al && ch->num_aggr) {
+ al->cycles->avg = ch->cycles_aggr / ch->num_aggr;
+ al->cycles->max = ch->cycles_max;
+ al->cycles->min = ch->cycles_min;
+ }
+ }
}

- return dl;
+ if (err) {
+ while (++offset < (s64)size) {
+ struct cyc_hist *ch = &notes->branch->cycles_hist[offset];

-out_free_line:
- zfree(&dl->al.line);
-out_delete:
- free(dl);
- return NULL;
+ if (ch && ch->cycles) {
+ struct annotation_line *al = notes->src->offsets[offset];
+ if (al)
+ zfree(&al->cycles);
+ }
+ }
+ }
+
+ annotation__unlock(notes);
+ return 0;
}

-void disasm_line__free(struct disasm_line *dl)
+int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample,
+ struct evsel *evsel)
{
- if (dl->ins.ops && dl->ins.ops->free)
- dl->ins.ops->free(&dl->ops);
- else
- ins__delete(&dl->ops);
- zfree(&dl->ins.name);
- annotation_line__exit(&dl->al);
- free(dl);
+ return symbol__inc_addr_samples(&ams->ms, evsel, ams->al_addr, sample);
}

-int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name)
+int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample,
+ struct evsel *evsel, u64 ip)
{
- if (raw || !dl->ins.ops)
- return scnprintf(bf, size, "%-*s %s", max_ins_name, dl->ins.name, dl->ops.raw);
-
- return ins__scnprintf(&dl->ins, bf, size, &dl->ops, max_ins_name);
+ return symbol__inc_addr_samples(&he->ms, evsel, ip, sample);
}

+
void annotation__exit(struct annotation *notes)
{
annotated_source__delete(notes->src);
@@ -1478,8 +548,7 @@ bool annotation__trylock(struct annotation *notes)
return mutex_trylock(mutex);
}

-
-static void annotation_line__add(struct annotation_line *al, struct list_head *head)
+void annotation_line__add(struct annotation_line *al, struct list_head *head)
{
list_add_tail(&al->node, head);
}
@@ -1689,673 +758,6 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start
return 0;
}

-/*
- * symbol__parse_objdump_line() parses objdump output (with -d --no-show-raw)
- * which looks like following
- *
- * 0000000000415500 <_init>:
- * 415500: sub $0x8,%rsp
- * 415504: mov 0x2f5ad5(%rip),%rax # 70afe0 <_DYNAMIC+0x2f8>
- * 41550b: test %rax,%rax
- * 41550e: je 415515 <_init+0x15>
- * 415510: callq 416e70 <__gmon_start__@plt>
- * 415515: add $0x8,%rsp
- * 415519: retq
- *
- * it will be parsed and saved into struct disasm_line as
- * <offset> <name> <ops.raw>
- *
- * The offset will be a relative offset from the start of the symbol and -1
- * means that it's not a disassembly line so should be treated differently.
- * The ops.raw part will be parsed further according to type of the instruction.
- */
-static int symbol__parse_objdump_line(struct symbol *sym,
- struct annotate_args *args,
- char *parsed_line, int *line_nr, char **fileloc)
-{
- struct map *map = args->ms.map;
- struct annotation *notes = symbol__annotation(sym);
- struct disasm_line *dl;
- char *tmp;
- s64 line_ip, offset = -1;
- regmatch_t match[2];
-
- /* /filename:linenr ? Save line number and ignore. */
- if (regexec(&file_lineno, parsed_line, 2, match, 0) == 0) {
- *line_nr = atoi(parsed_line + match[1].rm_so);
- free(*fileloc);
- *fileloc = strdup(parsed_line);
- return 0;
- }
-
- /* Process hex address followed by ':'. */
- line_ip = strtoull(parsed_line, &tmp, 16);
- if (parsed_line != tmp && tmp[0] == ':' && tmp[1] != '\0') {
- u64 start = map__rip_2objdump(map, sym->start),
- end = map__rip_2objdump(map, sym->end);
-
- offset = line_ip - start;
- if ((u64)line_ip < start || (u64)line_ip >= end)
- offset = -1;
- else
- parsed_line = tmp + 1;
- }
-
- args->offset = offset;
- args->line = parsed_line;
- args->line_nr = *line_nr;
- args->fileloc = *fileloc;
- args->ms.sym = sym;
-
- dl = disasm_line__new(args);
- (*line_nr)++;
-
- if (dl == NULL)
- return -1;
-
- if (!disasm_line__has_local_offset(dl)) {
- dl->ops.target.offset = dl->ops.target.addr -
- map__rip_2objdump(map, sym->start);
- dl->ops.target.offset_avail = true;
- }
-
- /* kcore has no symbols, so add the call target symbol */
- if (dl->ins.ops && ins__is_call(&dl->ins) && !dl->ops.target.sym) {
- struct addr_map_symbol target = {
- .addr = dl->ops.target.addr,
- .ms = { .map = map, },
- };
-
- if (!maps__find_ams(args->ms.maps, &target) &&
- target.ms.sym->start == target.al_addr)
- dl->ops.target.sym = target.ms.sym;
- }
-
- annotation_line__add(&dl->al, &notes->src->source);
- return 0;
-}
-
-static __attribute__((constructor)) void symbol__init_regexpr(void)
-{
- regcomp(&file_lineno, "^/[^:]+:([0-9]+)", REG_EXTENDED);
-}
-
-static void delete_last_nop(struct symbol *sym)
-{
- struct annotation *notes = symbol__annotation(sym);
- struct list_head *list = &notes->src->source;
- struct disasm_line *dl;
-
- while (!list_empty(list)) {
- dl = list_entry(list->prev, struct disasm_line, al.node);
-
- if (dl->ins.ops) {
- if (!ins__is_nop(&dl->ins))
- return;
- } else {
- if (!strstr(dl->al.line, " nop ") &&
- !strstr(dl->al.line, " nopl ") &&
- !strstr(dl->al.line, " nopw "))
- return;
- }
-
- list_del_init(&dl->al.node);
- disasm_line__free(dl);
- }
-}
-
-int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, size_t buflen)
-{
- struct dso *dso = map__dso(ms->map);
-
- BUG_ON(buflen == 0);
-
- if (errnum >= 0) {
- str_error_r(errnum, buf, buflen);
- return 0;
- }
-
- switch (errnum) {
- case SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX: {
- char bf[SBUILD_ID_SIZE + 15] = " with build id ";
- char *build_id_msg = NULL;
-
- if (dso->has_build_id) {
- build_id__sprintf(&dso->bid, bf + 15);
- build_id_msg = bf;
- }
- scnprintf(buf, buflen,
- "No vmlinux file%s\nwas found in the path.\n\n"
- "Note that annotation using /proc/kcore requires CAP_SYS_RAWIO capability.\n\n"
- "Please use:\n\n"
- " perf buildid-cache -vu vmlinux\n\n"
- "or:\n\n"
- " --vmlinux vmlinux\n", build_id_msg ?: "");
- }
- break;
- case SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF:
- scnprintf(buf, buflen, "Please link with binutils's libopcode to enable BPF annotation");
- break;
- case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP:
- scnprintf(buf, buflen, "Problems with arch specific instruction name regular expressions.");
- break;
- case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING:
- scnprintf(buf, buflen, "Problems while parsing the CPUID in the arch specific initialization.");
- break;
- case SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE:
- scnprintf(buf, buflen, "Invalid BPF file: %s.", dso->long_name);
- break;
- case SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF:
- scnprintf(buf, buflen, "The %s BPF file has no BTF section, compile with -g or use pahole -J.",
- dso->long_name);
- break;
- default:
- scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum);
- break;
- }
-
- return 0;
-}
-
-static int dso__disassemble_filename(struct dso *dso, char *filename, size_t filename_size)
-{
- char linkname[PATH_MAX];
- char *build_id_filename;
- char *build_id_path = NULL;
- char *pos;
- int len;
-
- if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
- !dso__is_kcore(dso))
- return SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX;
-
- build_id_filename = dso__build_id_filename(dso, NULL, 0, false);
- if (build_id_filename) {
- __symbol__join_symfs(filename, filename_size, build_id_filename);
- free(build_id_filename);
- } else {
- if (dso->has_build_id)
- return ENOMEM;
- goto fallback;
- }
-
- build_id_path = strdup(filename);
- if (!build_id_path)
- return ENOMEM;
-
- /*
- * old style build-id cache has name of XX/XXXXXXX.. while
- * new style has XX/XXXXXXX../{elf,kallsyms,vdso}.
- * extract the build-id part of dirname in the new style only.
- */
- pos = strrchr(build_id_path, '/');
- if (pos && strlen(pos) < SBUILD_ID_SIZE - 2)
- dirname(build_id_path);
-
- if (dso__is_kcore(dso))
- goto fallback;
-
- len = readlink(build_id_path, linkname, sizeof(linkname) - 1);
- if (len < 0)
- goto fallback;
-
- linkname[len] = '\0';
- if (strstr(linkname, DSO__NAME_KALLSYMS) ||
- access(filename, R_OK)) {
-fallback:
- /*
- * If we don't have build-ids or the build-id file isn't in the
- * cache, or is just a kallsyms file, well, lets hope that this
- * DSO is the same as when 'perf record' ran.
- */
- if (dso->kernel && dso->long_name[0] == '/')
- snprintf(filename, filename_size, "%s", dso->long_name);
- else
- __symbol__join_symfs(filename, filename_size, dso->long_name);
-
- mutex_lock(&dso->lock);
- if (access(filename, R_OK) && errno == ENOENT && dso->nsinfo) {
- char *new_name = dso__filename_with_chroot(dso, filename);
- if (new_name) {
- strlcpy(filename, new_name, filename_size);
- free(new_name);
- }
- }
- mutex_unlock(&dso->lock);
- }
-
- free(build_id_path);
- return 0;
-}
-
-#if defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
-#define PACKAGE "perf"
-#include <bfd.h>
-#include <dis-asm.h>
-#include <bpf/bpf.h>
-#include <bpf/btf.h>
-#include <bpf/libbpf.h>
-#include <linux/btf.h>
-#include <tools/dis-asm-compat.h>
-
-static int symbol__disassemble_bpf(struct symbol *sym,
- struct annotate_args *args)
-{
- struct annotation *notes = symbol__annotation(sym);
- struct bpf_prog_linfo *prog_linfo = NULL;
- struct bpf_prog_info_node *info_node;
- int len = sym->end - sym->start;
- disassembler_ftype disassemble;
- struct map *map = args->ms.map;
- struct perf_bpil *info_linear;
- struct disassemble_info info;
- struct dso *dso = map__dso(map);
- int pc = 0, count, sub_id;
- struct btf *btf = NULL;
- char tpath[PATH_MAX];
- size_t buf_size;
- int nr_skip = 0;
- char *buf;
- bfd *bfdf;
- int ret;
- FILE *s;
-
- if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO)
- return SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE;
-
- pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__,
- sym->name, sym->start, sym->end - sym->start);
-
- memset(tpath, 0, sizeof(tpath));
- perf_exe(tpath, sizeof(tpath));
-
- bfdf = bfd_openr(tpath, NULL);
- if (bfdf == NULL)
- abort();
-
- if (!bfd_check_format(bfdf, bfd_object))
- abort();
-
- s = open_memstream(&buf, &buf_size);
- if (!s) {
- ret = errno;
- goto out;
- }
- init_disassemble_info_compat(&info, s,
- (fprintf_ftype) fprintf,
- fprintf_styled);
- info.arch = bfd_get_arch(bfdf);
- info.mach = bfd_get_mach(bfdf);
-
- info_node = perf_env__find_bpf_prog_info(dso->bpf_prog.env,
- dso->bpf_prog.id);
- if (!info_node) {
- ret = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF;
- goto out;
- }
- info_linear = info_node->info_linear;
- sub_id = dso->bpf_prog.sub_id;
-
- info.buffer = (void *)(uintptr_t)(info_linear->info.jited_prog_insns);
- info.buffer_length = info_linear->info.jited_prog_len;
-
- if (info_linear->info.nr_line_info)
- prog_linfo = bpf_prog_linfo__new(&info_linear->info);
-
- if (info_linear->info.btf_id) {
- struct btf_node *node;
-
- node = perf_env__find_btf(dso->bpf_prog.env,
- info_linear->info.btf_id);
- if (node)
- btf = btf__new((__u8 *)(node->data),
- node->data_size);
- }
-
- disassemble_init_for_target(&info);
-
-#ifdef DISASM_FOUR_ARGS_SIGNATURE
- disassemble = disassembler(info.arch,
- bfd_big_endian(bfdf),
- info.mach,
- bfdf);
-#else
- disassemble = disassembler(bfdf);
-#endif
- if (disassemble == NULL)
- abort();
-
- fflush(s);
- do {
- const struct bpf_line_info *linfo = NULL;
- struct disasm_line *dl;
- size_t prev_buf_size;
- const char *srcline;
- u64 addr;
-
- addr = pc + ((u64 *)(uintptr_t)(info_linear->info.jited_ksyms))[sub_id];
- count = disassemble(pc, &info);
-
- if (prog_linfo)
- linfo = bpf_prog_linfo__lfind_addr_func(prog_linfo,
- addr, sub_id,
- nr_skip);
-
- if (linfo && btf) {
- srcline = btf__name_by_offset(btf, linfo->line_off);
- nr_skip++;
- } else
- srcline = NULL;
-
- fprintf(s, "\n");
- prev_buf_size = buf_size;
- fflush(s);
-
- if (!annotate_opts.hide_src_code && srcline) {
- args->offset = -1;
- args->line = strdup(srcline);
- args->line_nr = 0;
- args->fileloc = NULL;
- args->ms.sym = sym;
- dl = disasm_line__new(args);
- if (dl) {
- annotation_line__add(&dl->al,
- &notes->src->source);
- }
- }
-
- args->offset = pc;
- args->line = buf + prev_buf_size;
- args->line_nr = 0;
- args->fileloc = NULL;
- args->ms.sym = sym;
- dl = disasm_line__new(args);
- if (dl)
- annotation_line__add(&dl->al, &notes->src->source);
-
- pc += count;
- } while (count > 0 && pc < len);
-
- ret = 0;
-out:
- free(prog_linfo);
- btf__free(btf);
- fclose(s);
- bfd_close(bfdf);
- return ret;
-}
-#else // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
-static int symbol__disassemble_bpf(struct symbol *sym __maybe_unused,
- struct annotate_args *args __maybe_unused)
-{
- return SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF;
-}
-#endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
-
-static int
-symbol__disassemble_bpf_image(struct symbol *sym,
- struct annotate_args *args)
-{
- struct annotation *notes = symbol__annotation(sym);
- struct disasm_line *dl;
-
- args->offset = -1;
- args->line = strdup("to be implemented");
- args->line_nr = 0;
- args->fileloc = NULL;
- dl = disasm_line__new(args);
- if (dl)
- annotation_line__add(&dl->al, &notes->src->source);
-
- zfree(&args->line);
- return 0;
-}
-
-/*
- * Possibly create a new version of line with tabs expanded. Returns the
- * existing or new line, storage is updated if a new line is allocated. If
- * allocation fails then NULL is returned.
- */
-static char *expand_tabs(char *line, char **storage, size_t *storage_len)
-{
- size_t i, src, dst, len, new_storage_len, num_tabs;
- char *new_line;
- size_t line_len = strlen(line);
-
- for (num_tabs = 0, i = 0; i < line_len; i++)
- if (line[i] == '\t')
- num_tabs++;
-
- if (num_tabs == 0)
- return line;
-
- /*
- * Space for the line and '\0', less the leading and trailing
- * spaces. Each tab may introduce 7 additional spaces.
- */
- new_storage_len = line_len + 1 + (num_tabs * 7);
-
- new_line = malloc(new_storage_len);
- if (new_line == NULL) {
- pr_err("Failure allocating memory for tab expansion\n");
- return NULL;
- }
-
- /*
- * Copy regions starting at src and expand tabs. If there are two
- * adjacent tabs then 'src == i', the memcpy is of size 0 and the spaces
- * are inserted.
- */
- for (i = 0, src = 0, dst = 0; i < line_len && num_tabs; i++) {
- if (line[i] == '\t') {
- len = i - src;
- memcpy(&new_line[dst], &line[src], len);
- dst += len;
- new_line[dst++] = ' ';
- while (dst % 8 != 0)
- new_line[dst++] = ' ';
- src = i + 1;
- num_tabs--;
- }
- }
-
- /* Expand the last region. */
- len = line_len - src;
- memcpy(&new_line[dst], &line[src], len);
- dst += len;
- new_line[dst] = '\0';
-
- free(*storage);
- *storage = new_line;
- *storage_len = new_storage_len;
- return new_line;
-
-}
-
-static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
-{
- struct annotation_options *opts = &annotate_opts;
- struct map *map = args->ms.map;
- struct dso *dso = map__dso(map);
- char *command;
- FILE *file;
- char symfs_filename[PATH_MAX];
- struct kcore_extract kce;
- bool delete_extract = false;
- bool decomp = false;
- int lineno = 0;
- char *fileloc = NULL;
- int nline;
- char *line;
- size_t line_len;
- const char *objdump_argv[] = {
- "/bin/sh",
- "-c",
- NULL, /* Will be the objdump command to run. */
- "--",
- NULL, /* Will be the symfs path. */
- NULL,
- };
- struct child_process objdump_process;
- int err = dso__disassemble_filename(dso, symfs_filename, sizeof(symfs_filename));
-
- if (err)
- return err;
-
- pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
- symfs_filename, sym->name, map__unmap_ip(map, sym->start),
- map__unmap_ip(map, sym->end));
-
- pr_debug("annotating [%p] %30s : [%p] %30s\n",
- dso, dso->long_name, sym, sym->name);
-
- if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) {
- return symbol__disassemble_bpf(sym, args);
- } else if (dso->binary_type == DSO_BINARY_TYPE__BPF_IMAGE) {
- return symbol__disassemble_bpf_image(sym, args);
- } else if (dso__is_kcore(dso)) {
- kce.kcore_filename = symfs_filename;
- kce.addr = map__rip_2objdump(map, sym->start);
- kce.offs = sym->start;
- kce.len = sym->end - sym->start;
- if (!kcore_extract__create(&kce)) {
- delete_extract = true;
- strlcpy(symfs_filename, kce.extract_filename,
- sizeof(symfs_filename));
- }
- } else if (dso__needs_decompress(dso)) {
- char tmp[KMOD_DECOMP_LEN];
-
- if (dso__decompress_kmodule_path(dso, symfs_filename,
- tmp, sizeof(tmp)) < 0)
- return -1;
-
- decomp = true;
- strcpy(symfs_filename, tmp);
- }
-
- err = asprintf(&command,
- "%s %s%s --start-address=0x%016" PRIx64
- " --stop-address=0x%016" PRIx64
- " %s -d %s %s %s %c%s%c %s%s -C \"$1\"",
- opts->objdump_path ?: "objdump",
- opts->disassembler_style ? "-M " : "",
- opts->disassembler_style ?: "",
- map__rip_2objdump(map, sym->start),
- map__rip_2objdump(map, sym->end),
- opts->show_linenr ? "-l" : "",
- opts->show_asm_raw ? "" : "--no-show-raw-insn",
- opts->annotate_src ? "-S" : "",
- opts->prefix ? "--prefix " : "",
- opts->prefix ? '"' : ' ',
- opts->prefix ?: "",
- opts->prefix ? '"' : ' ',
- opts->prefix_strip ? "--prefix-strip=" : "",
- opts->prefix_strip ?: "");
-
- if (err < 0) {
- pr_err("Failure allocating memory for the command to run\n");
- goto out_remove_tmp;
- }
-
- pr_debug("Executing: %s\n", command);
-
- objdump_argv[2] = command;
- objdump_argv[4] = symfs_filename;
-
- /* Create a pipe to read from for stdout */
- memset(&objdump_process, 0, sizeof(objdump_process));
- objdump_process.argv = objdump_argv;
- objdump_process.out = -1;
- objdump_process.err = -1;
- objdump_process.no_stderr = 1;
- if (start_command(&objdump_process)) {
- pr_err("Failure starting to run %s\n", command);
- err = -1;
- goto out_free_command;
- }
-
- file = fdopen(objdump_process.out, "r");
- if (!file) {
- pr_err("Failure creating FILE stream for %s\n", command);
- /*
- * If we were using debug info should retry with
- * original binary.
- */
- err = -1;
- goto out_close_stdout;
- }
-
- /* Storage for getline. */
- line = NULL;
- line_len = 0;
-
- nline = 0;
- while (!feof(file)) {
- const char *match;
- char *expanded_line;
-
- if (getline(&line, &line_len, file) < 0 || !line)
- break;
-
- /* Skip lines containing "filename:" */
- match = strstr(line, symfs_filename);
- if (match && match[strlen(symfs_filename)] == ':')
- continue;
-
- expanded_line = strim(line);
- expanded_line = expand_tabs(expanded_line, &line, &line_len);
- if (!expanded_line)
- break;
-
- /*
- * The source code line number (lineno) needs to be kept in
- * across calls to symbol__parse_objdump_line(), so that it
- * can associate it with the instructions till the next one.
- * See disasm_line__new() and struct disasm_line::line_nr.
- */
- if (symbol__parse_objdump_line(sym, args, expanded_line,
- &lineno, &fileloc) < 0)
- break;
- nline++;
- }
- free(line);
- free(fileloc);
-
- err = finish_command(&objdump_process);
- if (err)
- pr_err("Error running %s\n", command);
-
- if (nline == 0) {
- err = -1;
- pr_err("No output from %s\n", command);
- }
-
- /*
- * kallsyms does not have symbol sizes so there may a nop at the end.
- * Remove it.
- */
- if (dso__is_kcore(dso))
- delete_last_nop(sym);
-
- fclose(file);
-
-out_close_stdout:
- close(objdump_process.out);
-
-out_free_command:
- free(command);
-
-out_remove_tmp:
- if (decomp)
- unlink(symfs_filename);
-
- if (delete_extract)
- kcore_extract__delete(&kce);
-
- return err;
-}
-
static void calc_percent(struct annotation *notes,
struct evsel *evsel,
struct annotation_data *data,
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 98f556af637c..b3007c9966fd 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -13,10 +13,10 @@
#include "mutex.h"
#include "spark.h"
#include "hashmap.h"
+#include "disasm.h"

struct hist_browser_timer;
struct hist_entry;
-struct ins_ops;
struct map;
struct map_symbol;
struct addr_map_symbol;
@@ -26,60 +26,6 @@ struct evsel;
struct symbol;
struct annotated_data_type;

-struct ins {
- const char *name;
- struct ins_ops *ops;
-};
-
-struct ins_operands {
- char *raw;
- struct {
- char *raw;
- char *name;
- struct symbol *sym;
- u64 addr;
- s64 offset;
- bool offset_avail;
- bool outside;
- bool multi_regs;
- } target;
- union {
- struct {
- char *raw;
- char *name;
- u64 addr;
- bool multi_regs;
- } source;
- struct {
- struct ins ins;
- struct ins_operands *ops;
- } locked;
- struct {
- char *raw_comment;
- char *raw_func_start;
- } jump;
- };
-};
-
-struct arch;
-
-bool arch__is(struct arch *arch, const char *name);
-
-struct ins_ops {
- void (*free)(struct ins_operands *ops);
- int (*parse)(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms);
- int (*scnprintf)(struct ins *ins, char *bf, size_t size,
- struct ins_operands *ops, int max_ins_name);
-};
-
-bool ins__is_jump(const struct ins *ins);
-bool ins__is_call(const struct ins *ins);
-bool ins__is_nop(const struct ins *ins);
-bool ins__is_ret(const struct ins *ins);
-bool ins__is_lock(const struct ins *ins);
-int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops, int max_ins_name);
-bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
-
#define ANNOTATION__IPC_WIDTH 6
#define ANNOTATION__CYCLES_WIDTH 6
#define ANNOTATION__MINMAX_CYCLES_WIDTH 19
@@ -172,6 +118,8 @@ struct disasm_line {
struct annotation_line al;
};

+void annotation_line__add(struct annotation_line *al, struct list_head *head);
+
static inline double annotation_data__percent(struct annotation_data *data,
unsigned int which)
{
@@ -213,7 +161,6 @@ static inline bool disasm_line__has_local_offset(const struct disasm_line *dl)
*/
bool disasm_line__is_valid_local_jump(struct disasm_line *dl, struct symbol *sym);

-void disasm_line__free(struct disasm_line *dl);
struct annotation_line *
annotation_line__next(struct annotation_line *pos, struct list_head *head);

@@ -236,7 +183,6 @@ int __annotation__scnprintf_samples_period(struct annotation *notes,
struct evsel *evsel,
bool show_freq);

-int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name);
size_t disasm__fprintf(struct list_head *head, FILE *fp);
void symbol__calc_percent(struct symbol *sym, struct evsel *evsel);

diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
new file mode 100644
index 000000000000..59ac37723990
--- /dev/null
+++ b/tools/perf/util/disasm.c
@@ -0,0 +1,1586 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <ctype.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <libgen.h>
+#include <regex.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <linux/string.h>
+#include <subcmd/run-command.h>
+
+#include "annotate.h"
+#include "build-id.h"
+#include "debug.h"
+#include "disasm.h"
+#include "dso.h"
+#include "evsel.h"
+#include "map.h"
+#include "maps.h"
+#include "srcline.h"
+#include "symbol.h"
+
+static regex_t file_lineno;
+
+/* These can be referred from the arch-dependent code */
+static struct ins_ops call_ops;
+static struct ins_ops dec_ops;
+static struct ins_ops jump_ops;
+static struct ins_ops mov_ops;
+static struct ins_ops nop_ops;
+static struct ins_ops lock_ops;
+static struct ins_ops ret_ops;
+
+static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
+ struct ins_operands *ops, int max_ins_name);
+static int call__scnprintf(struct ins *ins, char *bf, size_t size,
+ struct ins_operands *ops, int max_ins_name);
+
+static void ins__sort(struct arch *arch);
+static int disasm_line__parse(char *line, const char **namep, char **rawp);
+
+static __attribute__((constructor)) void symbol__init_regexpr(void)
+{
+ regcomp(&file_lineno, "^/[^:]+:([0-9]+)", REG_EXTENDED);
+}
+
+static int arch__grow_instructions(struct arch *arch)
+{
+ struct ins *new_instructions;
+ size_t new_nr_allocated;
+
+ if (arch->nr_instructions_allocated == 0 && arch->instructions)
+ goto grow_from_non_allocated_table;
+
+ new_nr_allocated = arch->nr_instructions_allocated + 128;
+ new_instructions = realloc(arch->instructions, new_nr_allocated * sizeof(struct ins));
+ if (new_instructions == NULL)
+ return -1;
+
+out_update_instructions:
+ arch->instructions = new_instructions;
+ arch->nr_instructions_allocated = new_nr_allocated;
+ return 0;
+
+grow_from_non_allocated_table:
+ new_nr_allocated = arch->nr_instructions + 128;
+ new_instructions = calloc(new_nr_allocated, sizeof(struct ins));
+ if (new_instructions == NULL)
+ return -1;
+
+ memcpy(new_instructions, arch->instructions, arch->nr_instructions);
+ goto out_update_instructions;
+}
+
+static int arch__associate_ins_ops(struct arch* arch, const char *name, struct ins_ops *ops)
+{
+ struct ins *ins;
+
+ if (arch->nr_instructions == arch->nr_instructions_allocated &&
+ arch__grow_instructions(arch))
+ return -1;
+
+ ins = &arch->instructions[arch->nr_instructions];
+ ins->name = strdup(name);
+ if (!ins->name)
+ return -1;
+
+ ins->ops = ops;
+ arch->nr_instructions++;
+
+ ins__sort(arch);
+ return 0;
+}
+
+#include "arch/arc/annotate/instructions.c"
+#include "arch/arm/annotate/instructions.c"
+#include "arch/arm64/annotate/instructions.c"
+#include "arch/csky/annotate/instructions.c"
+#include "arch/loongarch/annotate/instructions.c"
+#include "arch/mips/annotate/instructions.c"
+#include "arch/x86/annotate/instructions.c"
+#include "arch/powerpc/annotate/instructions.c"
+#include "arch/riscv64/annotate/instructions.c"
+#include "arch/s390/annotate/instructions.c"
+#include "arch/sparc/annotate/instructions.c"
+
+static struct arch architectures[] = {
+ {
+ .name = "arc",
+ .init = arc__annotate_init,
+ },
+ {
+ .name = "arm",
+ .init = arm__annotate_init,
+ },
+ {
+ .name = "arm64",
+ .init = arm64__annotate_init,
+ },
+ {
+ .name = "csky",
+ .init = csky__annotate_init,
+ },
+ {
+ .name = "mips",
+ .init = mips__annotate_init,
+ .objdump = {
+ .comment_char = '#',
+ },
+ },
+ {
+ .name = "x86",
+ .init = x86__annotate_init,
+ .instructions = x86__instructions,
+ .nr_instructions = ARRAY_SIZE(x86__instructions),
+ .insn_suffix = "bwlq",
+ .objdump = {
+ .comment_char = '#',
+ .register_char = '%',
+ .memory_ref_char = '(',
+ .imm_char = '$',
+ },
+ },
+ {
+ .name = "powerpc",
+ .init = powerpc__annotate_init,
+ },
+ {
+ .name = "riscv64",
+ .init = riscv64__annotate_init,
+ },
+ {
+ .name = "s390",
+ .init = s390__annotate_init,
+ .objdump = {
+ .comment_char = '#',
+ },
+ },
+ {
+ .name = "sparc",
+ .init = sparc__annotate_init,
+ .objdump = {
+ .comment_char = '#',
+ },
+ },
+ {
+ .name = "loongarch",
+ .init = loongarch__annotate_init,
+ .objdump = {
+ .comment_char = '#',
+ },
+ },
+};
+
+static int arch__key_cmp(const void *name, const void *archp)
+{
+ const struct arch *arch = archp;
+
+ return strcmp(name, arch->name);
+}
+
+static int arch__cmp(const void *a, const void *b)
+{
+ const struct arch *aa = a;
+ const struct arch *ab = b;
+
+ return strcmp(aa->name, ab->name);
+}
+
+static void arch__sort(void)
+{
+ const int nmemb = ARRAY_SIZE(architectures);
+
+ qsort(architectures, nmemb, sizeof(struct arch), arch__cmp);
+}
+
+struct arch *arch__find(const char *name)
+{
+ const int nmemb = ARRAY_SIZE(architectures);
+ static bool sorted;
+
+ if (!sorted) {
+ arch__sort();
+ sorted = true;
+ }
+
+ return bsearch(name, architectures, nmemb, sizeof(struct arch), arch__key_cmp);
+}
+
+bool arch__is(struct arch *arch, const char *name)
+{
+ return !strcmp(arch->name, name);
+}
+
+static void ins_ops__delete(struct ins_operands *ops)
+{
+ if (ops == NULL)
+ return;
+ zfree(&ops->source.raw);
+ zfree(&ops->source.name);
+ zfree(&ops->target.raw);
+ zfree(&ops->target.name);
+}
+
+static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size,
+ struct ins_operands *ops, int max_ins_name)
+{
+ return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->raw);
+}
+
+int ins__scnprintf(struct ins *ins, char *bf, size_t size,
+ struct ins_operands *ops, int max_ins_name)
+{
+ if (ins->ops->scnprintf)
+ return ins->ops->scnprintf(ins, bf, size, ops, max_ins_name);
+
+ return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
+}
+
+bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2)
+{
+ if (!arch || !arch->ins_is_fused)
+ return false;
+
+ return arch->ins_is_fused(arch, ins1, ins2);
+}
+
+static int 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, },
+ };
+
+ ops->target.addr = strtoull(ops->raw, &endptr, 16);
+
+ name = strchr(endptr, '<');
+ if (name == NULL)
+ goto indirect_call;
+
+ 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;
+find_target:
+ 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;
+
+indirect_call:
+ tok = strchr(endptr, '*');
+ if (tok != NULL) {
+ endptr++;
+
+ /* Indirect call can use a non-rip register and offset: callq *0x8(%rbx).
+ * Do not parse such instruction. */
+ if (strstr(endptr, "(%r") == NULL)
+ ops->target.addr = strtoull(endptr, NULL, 16);
+ }
+ goto find_target;
+}
+
+static int call__scnprintf(struct ins *ins, char *bf, size_t size,
+ struct ins_operands *ops, int max_ins_name)
+{
+ if (ops->target.sym)
+ return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.sym->name);
+
+ if (ops->target.addr == 0)
+ return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
+
+ if (ops->target.name)
+ return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.name);
+
+ return scnprintf(bf, size, "%-*s *%" PRIx64, max_ins_name, ins->name, ops->target.addr);
+}
+
+static struct ins_ops call_ops = {
+ .parse = call__parse,
+ .scnprintf = call__scnprintf,
+};
+
+bool ins__is_call(const struct ins *ins)
+{
+ return ins->ops == &call_ops || ins->ops == &s390_call_ops || ins->ops == &loongarch_call_ops;
+}
+
+/*
+ * Prevents from matching commas in the comment section, e.g.:
+ * ffff200008446e70: b.cs ffff2000084470f4 <generic_exec_single+0x314> // b.hs, b.nlast
+ *
+ * and skip comma as part of function arguments, e.g.:
+ * 1d8b4ac <linemap_lookup(line_maps const*, unsigned int)+0xcc>
+ */
+static inline const char *validate_comma(const char *c, struct ins_operands *ops)
+{
+ if (ops->jump.raw_comment && c > ops->jump.raw_comment)
+ return NULL;
+
+ if (ops->jump.raw_func_start && c > ops->jump.raw_func_start)
+ return NULL;
+
+ return c;
+}
+
+static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
+{
+ struct map *map = ms->map;
+ struct symbol *sym = ms->sym;
+ struct addr_map_symbol target = {
+ .ms = { .map = map, },
+ };
+ const char *c = strchr(ops->raw, ',');
+ u64 start, end;
+
+ ops->jump.raw_comment = strchr(ops->raw, arch->objdump.comment_char);
+ ops->jump.raw_func_start = strchr(ops->raw, '<');
+
+ c = validate_comma(c, ops);
+
+ /*
+ * Examples of lines to parse for the _cpp_lex_token@@Base
+ * function:
+ *
+ * 1159e6c: jne 115aa32 <_cpp_lex_token@@Base+0xf92>
+ * 1159e8b: jne c469be <cpp_named_operator2name@@Base+0xa72>
+ *
+ * The first is a jump to an offset inside the same function,
+ * the second is to another function, i.e. that 0xa72 is an
+ * offset in the cpp_named_operator2name@@base function.
+ */
+ /*
+ * skip over possible up to 2 operands to get to address, e.g.:
+ * tbnz w0, #26, ffff0000083cd190 <security_file_permission+0xd0>
+ */
+ if (c++ != NULL) {
+ ops->target.addr = strtoull(c, NULL, 16);
+ if (!ops->target.addr) {
+ c = strchr(c, ',');
+ c = validate_comma(c, ops);
+ if (c++ != NULL)
+ ops->target.addr = strtoull(c, NULL, 16);
+ }
+ } else {
+ ops->target.addr = strtoull(ops->raw, NULL, 16);
+ }
+
+ target.addr = map__objdump_2mem(map, ops->target.addr);
+ start = map__unmap_ip(map, sym->start);
+ end = map__unmap_ip(map, sym->end);
+
+ ops->target.outside = target.addr < start || target.addr > end;
+
+ /*
+ * FIXME: things like this in _cpp_lex_token (gcc's cc1 program):
+
+ cpp_named_operator2name@@Base+0xa72
+
+ * Point to a place that is after the cpp_named_operator2name
+ * boundaries, i.e. in the ELF symbol table for cc1
+ * cpp_named_operator2name is marked as being 32-bytes long, but it in
+ * fact is much larger than that, so we seem to need a symbols__find()
+ * routine that looks for >= current->start and < next_symbol->start,
+ * possibly just for C++ objects?
+ *
+ * For now lets just make some progress by marking jumps to outside the
+ * current function as call like.
+ *
+ * Actual navigation will come next, with further understanding of how
+ * the symbol searching and disassembly should be done.
+ */
+ 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;
+
+ if (!ops->target.outside) {
+ ops->target.offset = target.addr - start;
+ ops->target.offset_avail = true;
+ } else {
+ ops->target.offset_avail = false;
+ }
+
+ return 0;
+}
+
+static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
+ struct ins_operands *ops, int max_ins_name)
+{
+ const char *c;
+
+ if (!ops->target.addr || ops->target.offset < 0)
+ return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
+
+ if (ops->target.outside && ops->target.sym != NULL)
+ return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.sym->name);
+
+ c = strchr(ops->raw, ',');
+ c = validate_comma(c, ops);
+
+ if (c != NULL) {
+ const char *c2 = strchr(c + 1, ',');
+
+ c2 = validate_comma(c2, ops);
+ /* check for 3-op insn */
+ if (c2 != NULL)
+ c = c2;
+ c++;
+
+ /* mirror arch objdump's space-after-comma style */
+ if (*c == ' ')
+ c++;
+ }
+
+ return scnprintf(bf, size, "%-*s %.*s%" PRIx64, max_ins_name,
+ ins->name, c ? c - ops->raw : 0, ops->raw,
+ ops->target.offset);
+}
+
+static void jump__delete(struct ins_operands *ops __maybe_unused)
+{
+ /*
+ * The ops->jump.raw_comment and ops->jump.raw_func_start belong to the
+ * raw string, don't free them.
+ */
+}
+
+static struct ins_ops jump_ops = {
+ .free = jump__delete,
+ .parse = jump__parse,
+ .scnprintf = jump__scnprintf,
+};
+
+bool ins__is_jump(const struct ins *ins)
+{
+ return ins->ops == &jump_ops || ins->ops == &loongarch_jump_ops;
+}
+
+static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep)
+{
+ char *endptr, *name, *t;
+
+ if (strstr(raw, "(%rip)") == NULL)
+ return 0;
+
+ *addrp = strtoull(comment, &endptr, 16);
+ if (endptr == comment)
+ return 0;
+ name = strchr(endptr, '<');
+ if (name == NULL)
+ return -1;
+
+ name++;
+
+ t = strchr(name, '>');
+ if (t == NULL)
+ return 0;
+
+ *t = '\0';
+ *namep = strdup(name);
+ *t = '>';
+
+ return 0;
+}
+
+static int lock__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
+{
+ ops->locked.ops = zalloc(sizeof(*ops->locked.ops));
+ if (ops->locked.ops == NULL)
+ return 0;
+
+ if (disasm_line__parse(ops->raw, &ops->locked.ins.name, &ops->locked.ops->raw) < 0)
+ goto out_free_ops;
+
+ ops->locked.ins.ops = ins__find(arch, ops->locked.ins.name);
+
+ if (ops->locked.ins.ops == NULL)
+ goto out_free_ops;
+
+ if (ops->locked.ins.ops->parse &&
+ ops->locked.ins.ops->parse(arch, ops->locked.ops, ms) < 0)
+ goto out_free_ops;
+
+ return 0;
+
+out_free_ops:
+ zfree(&ops->locked.ops);
+ return 0;
+}
+
+static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
+ struct ins_operands *ops, int max_ins_name)
+{
+ int printed;
+
+ if (ops->locked.ins.ops == NULL)
+ return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
+
+ printed = scnprintf(bf, size, "%-*s ", max_ins_name, ins->name);
+ return printed + ins__scnprintf(&ops->locked.ins, bf + printed,
+ size - printed, ops->locked.ops, max_ins_name);
+}
+
+static void lock__delete(struct ins_operands *ops)
+{
+ struct ins *ins = &ops->locked.ins;
+
+ if (ins->ops && ins->ops->free)
+ ins->ops->free(ops->locked.ops);
+ else
+ ins_ops__delete(ops->locked.ops);
+
+ zfree(&ops->locked.ops);
+ zfree(&ops->target.raw);
+ zfree(&ops->target.name);
+}
+
+static struct ins_ops lock_ops = {
+ .free = lock__delete,
+ .parse = lock__parse,
+ .scnprintf = lock__scnprintf,
+};
+
+/*
+ * Check if the operand has more than one registers like x86 SIB addressing:
+ * 0x1234(%rax, %rbx, 8)
+ *
+ * But it doesn't care segment selectors like %gs:0x5678(%rcx), so just check
+ * the input string after 'memory_ref_char' if exists.
+ */
+static bool check_multi_regs(struct arch *arch, const char *op)
+{
+ int count = 0;
+
+ if (arch->objdump.register_char == 0)
+ return false;
+
+ if (arch->objdump.memory_ref_char) {
+ op = strchr(op, arch->objdump.memory_ref_char);
+ if (op == NULL)
+ return false;
+ }
+
+ while ((op = strchr(op, arch->objdump.register_char)) != NULL) {
+ count++;
+ op++;
+ }
+
+ return count > 1;
+}
+
+static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms __maybe_unused)
+{
+ char *s = strchr(ops->raw, ','), *target, *comment, prev;
+
+ if (s == NULL)
+ return -1;
+
+ *s = '\0';
+
+ /*
+ * x86 SIB addressing has something like 0x8(%rax, %rcx, 1)
+ * then it needs to have the closing parenthesis.
+ */
+ if (strchr(ops->raw, '(')) {
+ *s = ',';
+ s = strchr(ops->raw, ')');
+ if (s == NULL || s[1] != ',')
+ return -1;
+ *++s = '\0';
+ }
+
+ ops->source.raw = strdup(ops->raw);
+ *s = ',';
+
+ if (ops->source.raw == NULL)
+ return -1;
+
+ ops->source.multi_regs = check_multi_regs(arch, ops->source.raw);
+
+ target = skip_spaces(++s);
+ comment = strchr(s, arch->objdump.comment_char);
+
+ if (comment != NULL)
+ s = comment - 1;
+ else
+ s = strchr(s, '\0') - 1;
+
+ while (s > target && isspace(s[0]))
+ --s;
+ s++;
+ prev = *s;
+ *s = '\0';
+
+ ops->target.raw = strdup(target);
+ *s = prev;
+
+ if (ops->target.raw == NULL)
+ goto out_free_source;
+
+ ops->target.multi_regs = check_multi_regs(arch, ops->target.raw);
+
+ if (comment == NULL)
+ return 0;
+
+ comment = skip_spaces(comment);
+ comment__symbol(ops->source.raw, comment + 1, &ops->source.addr, &ops->source.name);
+ comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
+
+ return 0;
+
+out_free_source:
+ zfree(&ops->source.raw);
+ return -1;
+}
+
+static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
+ struct ins_operands *ops, int max_ins_name)
+{
+ return scnprintf(bf, size, "%-*s %s,%s", max_ins_name, ins->name,
+ ops->source.name ?: ops->source.raw,
+ ops->target.name ?: ops->target.raw);
+}
+
+static struct ins_ops mov_ops = {
+ .parse = mov__parse,
+ .scnprintf = mov__scnprintf,
+};
+
+static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms __maybe_unused)
+{
+ char *target, *comment, *s, prev;
+
+ target = s = ops->raw;
+
+ while (s[0] != '\0' && !isspace(s[0]))
+ ++s;
+ prev = *s;
+ *s = '\0';
+
+ ops->target.raw = strdup(target);
+ *s = prev;
+
+ if (ops->target.raw == NULL)
+ return -1;
+
+ comment = strchr(s, arch->objdump.comment_char);
+ if (comment == NULL)
+ return 0;
+
+ comment = skip_spaces(comment);
+ comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
+
+ return 0;
+}
+
+static int dec__scnprintf(struct ins *ins, char *bf, size_t size,
+ struct ins_operands *ops, int max_ins_name)
+{
+ return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name,
+ ops->target.name ?: ops->target.raw);
+}
+
+static struct ins_ops dec_ops = {
+ .parse = dec__parse,
+ .scnprintf = dec__scnprintf,
+};
+
+static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size,
+ struct ins_operands *ops __maybe_unused, int max_ins_name)
+{
+ return scnprintf(bf, size, "%-*s", max_ins_name, "nop");
+}
+
+static struct ins_ops nop_ops = {
+ .scnprintf = nop__scnprintf,
+};
+
+static struct ins_ops ret_ops = {
+ .scnprintf = ins__raw_scnprintf,
+};
+
+bool ins__is_nop(const struct ins *ins)
+{
+ return ins->ops == &nop_ops;
+}
+
+bool ins__is_ret(const struct ins *ins)
+{
+ return ins->ops == &ret_ops;
+}
+
+bool ins__is_lock(const struct ins *ins)
+{
+ return ins->ops == &lock_ops;
+}
+
+static int ins__key_cmp(const void *name, const void *insp)
+{
+ const struct ins *ins = insp;
+
+ return strcmp(name, ins->name);
+}
+
+static int ins__cmp(const void *a, const void *b)
+{
+ const struct ins *ia = a;
+ const struct ins *ib = b;
+
+ return strcmp(ia->name, ib->name);
+}
+
+static void ins__sort(struct arch *arch)
+{
+ const int nmemb = arch->nr_instructions;
+
+ qsort(arch->instructions, nmemb, sizeof(struct ins), ins__cmp);
+}
+
+static struct ins_ops *__ins__find(struct arch *arch, const char *name)
+{
+ struct ins *ins;
+ const int nmemb = arch->nr_instructions;
+
+ if (!arch->sorted_instructions) {
+ ins__sort(arch);
+ arch->sorted_instructions = true;
+ }
+
+ ins = bsearch(name, arch->instructions, nmemb, sizeof(struct ins), ins__key_cmp);
+ if (ins)
+ return ins->ops;
+
+ if (arch->insn_suffix) {
+ char tmp[32];
+ char suffix;
+ size_t len = strlen(name);
+
+ if (len == 0 || len >= sizeof(tmp))
+ return NULL;
+
+ suffix = name[len - 1];
+ if (strchr(arch->insn_suffix, suffix) == NULL)
+ return NULL;
+
+ strcpy(tmp, name);
+ tmp[len - 1] = '\0'; /* remove the suffix and check again */
+
+ ins = bsearch(tmp, arch->instructions, nmemb, sizeof(struct ins), ins__key_cmp);
+ }
+ return ins ? ins->ops : NULL;
+}
+
+struct ins_ops *ins__find(struct arch *arch, const char *name)
+{
+ struct ins_ops *ops = __ins__find(arch, name);
+
+ if (!ops && arch->associate_instruction_ops)
+ ops = arch->associate_instruction_ops(arch, name);
+
+ return ops;
+}
+
+static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map_symbol *ms)
+{
+ dl->ins.ops = ins__find(arch, dl->ins.name);
+
+ if (!dl->ins.ops)
+ return;
+
+ if (dl->ins.ops->parse && dl->ins.ops->parse(arch, &dl->ops, ms) < 0)
+ dl->ins.ops = NULL;
+}
+
+static int disasm_line__parse(char *line, const char **namep, char **rawp)
+{
+ char tmp, *name = skip_spaces(line);
+
+ if (name[0] == '\0')
+ return -1;
+
+ *rawp = name + 1;
+
+ while ((*rawp)[0] != '\0' && !isspace((*rawp)[0]))
+ ++*rawp;
+
+ tmp = (*rawp)[0];
+ (*rawp)[0] = '\0';
+ *namep = strdup(name);
+
+ if (*namep == NULL)
+ goto out;
+
+ (*rawp)[0] = tmp;
+ *rawp = strim(*rawp);
+
+ return 0;
+
+out:
+ return -1;
+}
+
+static void annotation_line__init(struct annotation_line *al,
+ struct annotate_args *args,
+ int nr)
+{
+ al->offset = args->offset;
+ al->line = strdup(args->line);
+ al->line_nr = args->line_nr;
+ al->fileloc = args->fileloc;
+ al->data_nr = nr;
+}
+
+static void annotation_line__exit(struct annotation_line *al)
+{
+ zfree_srcline(&al->path);
+ zfree(&al->line);
+ zfree(&al->cycles);
+}
+
+static size_t disasm_line_size(int nr)
+{
+ struct annotation_line *al;
+
+ return (sizeof(struct disasm_line) + (sizeof(al->data[0]) * nr));
+}
+
+/*
+ * Allocating the disasm annotation line data with
+ * following structure:
+ *
+ * -------------------------------------------
+ * struct disasm_line | struct annotation_line
+ * -------------------------------------------
+ *
+ * We have 'struct annotation_line' member as last member
+ * of 'struct disasm_line' to have an easy access.
+ */
+struct disasm_line *disasm_line__new(struct annotate_args *args)
+{
+ struct disasm_line *dl = NULL;
+ int nr = 1;
+
+ if (evsel__is_group_event(args->evsel))
+ nr = args->evsel->core.nr_members;
+
+ dl = zalloc(disasm_line_size(nr));
+ if (!dl)
+ return NULL;
+
+ annotation_line__init(&dl->al, args, nr);
+ if (dl->al.line == NULL)
+ goto out_delete;
+
+ if (args->offset != -1) {
+ if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
+ goto out_free_line;
+
+ disasm_line__init_ins(dl, args->arch, &args->ms);
+ }
+
+ return dl;
+
+out_free_line:
+ zfree(&dl->al.line);
+out_delete:
+ free(dl);
+ return NULL;
+}
+
+void disasm_line__free(struct disasm_line *dl)
+{
+ if (dl->ins.ops && dl->ins.ops->free)
+ dl->ins.ops->free(&dl->ops);
+ else
+ ins_ops__delete(&dl->ops);
+ zfree(&dl->ins.name);
+ annotation_line__exit(&dl->al);
+ free(dl);
+}
+
+int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name)
+{
+ if (raw || !dl->ins.ops)
+ return scnprintf(bf, size, "%-*s %s", max_ins_name, dl->ins.name, dl->ops.raw);
+
+ return ins__scnprintf(&dl->ins, bf, size, &dl->ops, max_ins_name);
+}
+
+/*
+ * symbol__parse_objdump_line() parses objdump output (with -d --no-show-raw)
+ * which looks like following
+ *
+ * 0000000000415500 <_init>:
+ * 415500: sub $0x8,%rsp
+ * 415504: mov 0x2f5ad5(%rip),%rax # 70afe0 <_DYNAMIC+0x2f8>
+ * 41550b: test %rax,%rax
+ * 41550e: je 415515 <_init+0x15>
+ * 415510: callq 416e70 <__gmon_start__@plt>
+ * 415515: add $0x8,%rsp
+ * 415519: retq
+ *
+ * it will be parsed and saved into struct disasm_line as
+ * <offset> <name> <ops.raw>
+ *
+ * The offset will be a relative offset from the start of the symbol and -1
+ * means that it's not a disassembly line so should be treated differently.
+ * The ops.raw part will be parsed further according to type of the instruction.
+ */
+static int symbol__parse_objdump_line(struct symbol *sym,
+ struct annotate_args *args,
+ char *parsed_line, int *line_nr, char **fileloc)
+{
+ struct map *map = args->ms.map;
+ struct annotation *notes = symbol__annotation(sym);
+ struct disasm_line *dl;
+ char *tmp;
+ s64 line_ip, offset = -1;
+ regmatch_t match[2];
+
+ /* /filename:linenr ? Save line number and ignore. */
+ if (regexec(&file_lineno, parsed_line, 2, match, 0) == 0) {
+ *line_nr = atoi(parsed_line + match[1].rm_so);
+ free(*fileloc);
+ *fileloc = strdup(parsed_line);
+ return 0;
+ }
+
+ /* Process hex address followed by ':'. */
+ line_ip = strtoull(parsed_line, &tmp, 16);
+ if (parsed_line != tmp && tmp[0] == ':' && tmp[1] != '\0') {
+ u64 start = map__rip_2objdump(map, sym->start),
+ end = map__rip_2objdump(map, sym->end);
+
+ offset = line_ip - start;
+ if ((u64)line_ip < start || (u64)line_ip >= end)
+ offset = -1;
+ else
+ parsed_line = tmp + 1;
+ }
+
+ args->offset = offset;
+ args->line = parsed_line;
+ args->line_nr = *line_nr;
+ args->fileloc = *fileloc;
+ args->ms.sym = sym;
+
+ dl = disasm_line__new(args);
+ (*line_nr)++;
+
+ if (dl == NULL)
+ return -1;
+
+ if (!disasm_line__has_local_offset(dl)) {
+ dl->ops.target.offset = dl->ops.target.addr -
+ map__rip_2objdump(map, sym->start);
+ dl->ops.target.offset_avail = true;
+ }
+
+ /* kcore has no symbols, so add the call target symbol */
+ if (dl->ins.ops && ins__is_call(&dl->ins) && !dl->ops.target.sym) {
+ struct addr_map_symbol target = {
+ .addr = dl->ops.target.addr,
+ .ms = { .map = map, },
+ };
+
+ if (!maps__find_ams(args->ms.maps, &target) &&
+ target.ms.sym->start == target.al_addr)
+ dl->ops.target.sym = target.ms.sym;
+ }
+
+ annotation_line__add(&dl->al, &notes->src->source);
+ return 0;
+}
+
+static void delete_last_nop(struct symbol *sym)
+{
+ struct annotation *notes = symbol__annotation(sym);
+ struct list_head *list = &notes->src->source;
+ struct disasm_line *dl;
+
+ while (!list_empty(list)) {
+ dl = list_entry(list->prev, struct disasm_line, al.node);
+
+ if (dl->ins.ops) {
+ if (!ins__is_nop(&dl->ins))
+ return;
+ } else {
+ if (!strstr(dl->al.line, " nop ") &&
+ !strstr(dl->al.line, " nopl ") &&
+ !strstr(dl->al.line, " nopw "))
+ return;
+ }
+
+ list_del_init(&dl->al.node);
+ disasm_line__free(dl);
+ }
+}
+
+int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, size_t buflen)
+{
+ struct dso *dso = map__dso(ms->map);
+
+ BUG_ON(buflen == 0);
+
+ if (errnum >= 0) {
+ str_error_r(errnum, buf, buflen);
+ return 0;
+ }
+
+ switch (errnum) {
+ case SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX: {
+ char bf[SBUILD_ID_SIZE + 15] = " with build id ";
+ char *build_id_msg = NULL;
+
+ if (dso->has_build_id) {
+ build_id__sprintf(&dso->bid, bf + 15);
+ build_id_msg = bf;
+ }
+ scnprintf(buf, buflen,
+ "No vmlinux file%s\nwas found in the path.\n\n"
+ "Note that annotation using /proc/kcore requires CAP_SYS_RAWIO capability.\n\n"
+ "Please use:\n\n"
+ " perf buildid-cache -vu vmlinux\n\n"
+ "or:\n\n"
+ " --vmlinux vmlinux\n", build_id_msg ?: "");
+ }
+ break;
+ case SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF:
+ scnprintf(buf, buflen, "Please link with binutils's libopcode to enable BPF annotation");
+ break;
+ case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP:
+ scnprintf(buf, buflen, "Problems with arch specific instruction name regular expressions.");
+ break;
+ case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING:
+ scnprintf(buf, buflen, "Problems while parsing the CPUID in the arch specific initialization.");
+ break;
+ case SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE:
+ scnprintf(buf, buflen, "Invalid BPF file: %s.", dso->long_name);
+ break;
+ case SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF:
+ scnprintf(buf, buflen, "The %s BPF file has no BTF section, compile with -g or use pahole -J.",
+ dso->long_name);
+ break;
+ default:
+ scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum);
+ break;
+ }
+
+ return 0;
+}
+
+static int dso__disassemble_filename(struct dso *dso, char *filename, size_t filename_size)
+{
+ char linkname[PATH_MAX];
+ char *build_id_filename;
+ char *build_id_path = NULL;
+ char *pos;
+ int len;
+
+ if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
+ !dso__is_kcore(dso))
+ return SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX;
+
+ build_id_filename = dso__build_id_filename(dso, NULL, 0, false);
+ if (build_id_filename) {
+ __symbol__join_symfs(filename, filename_size, build_id_filename);
+ free(build_id_filename);
+ } else {
+ if (dso->has_build_id)
+ return ENOMEM;
+ goto fallback;
+ }
+
+ build_id_path = strdup(filename);
+ if (!build_id_path)
+ return ENOMEM;
+
+ /*
+ * old style build-id cache has name of XX/XXXXXXX.. while
+ * new style has XX/XXXXXXX../{elf,kallsyms,vdso}.
+ * extract the build-id part of dirname in the new style only.
+ */
+ pos = strrchr(build_id_path, '/');
+ if (pos && strlen(pos) < SBUILD_ID_SIZE - 2)
+ dirname(build_id_path);
+
+ if (dso__is_kcore(dso))
+ goto fallback;
+
+ len = readlink(build_id_path, linkname, sizeof(linkname) - 1);
+ if (len < 0)
+ goto fallback;
+
+ linkname[len] = '\0';
+ if (strstr(linkname, DSO__NAME_KALLSYMS) ||
+ access(filename, R_OK)) {
+fallback:
+ /*
+ * If we don't have build-ids or the build-id file isn't in the
+ * cache, or is just a kallsyms file, well, lets hope that this
+ * DSO is the same as when 'perf record' ran.
+ */
+ if (dso->kernel && dso->long_name[0] == '/')
+ snprintf(filename, filename_size, "%s", dso->long_name);
+ else
+ __symbol__join_symfs(filename, filename_size, dso->long_name);
+
+ mutex_lock(&dso->lock);
+ if (access(filename, R_OK) && errno == ENOENT && dso->nsinfo) {
+ char *new_name = dso__filename_with_chroot(dso, filename);
+ if (new_name) {
+ strlcpy(filename, new_name, filename_size);
+ free(new_name);
+ }
+ }
+ mutex_unlock(&dso->lock);
+ }
+
+ free(build_id_path);
+ return 0;
+}
+
+#if defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
+#define PACKAGE "perf"
+#include <bfd.h>
+#include <dis-asm.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
+#include <linux/btf.h>
+#include <tools/dis-asm-compat.h>
+
+static int symbol__disassemble_bpf(struct symbol *sym,
+ struct annotate_args *args)
+{
+ struct annotation *notes = symbol__annotation(sym);
+ struct bpf_prog_linfo *prog_linfo = NULL;
+ struct bpf_prog_info_node *info_node;
+ int len = sym->end - sym->start;
+ disassembler_ftype disassemble;
+ struct map *map = args->ms.map;
+ struct perf_bpil *info_linear;
+ struct disassemble_info info;
+ struct dso *dso = map__dso(map);
+ int pc = 0, count, sub_id;
+ struct btf *btf = NULL;
+ char tpath[PATH_MAX];
+ size_t buf_size;
+ int nr_skip = 0;
+ char *buf;
+ bfd *bfdf;
+ int ret;
+ FILE *s;
+
+ if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO)
+ return SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE;
+
+ pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__,
+ sym->name, sym->start, sym->end - sym->start);
+
+ memset(tpath, 0, sizeof(tpath));
+ perf_exe(tpath, sizeof(tpath));
+
+ bfdf = bfd_openr(tpath, NULL);
+ if (bfdf == NULL)
+ abort();
+
+ if (!bfd_check_format(bfdf, bfd_object))
+ abort();
+
+ s = open_memstream(&buf, &buf_size);
+ if (!s) {
+ ret = errno;
+ goto out;
+ }
+ init_disassemble_info_compat(&info, s,
+ (fprintf_ftype) fprintf,
+ fprintf_styled);
+ info.arch = bfd_get_arch(bfdf);
+ info.mach = bfd_get_mach(bfdf);
+
+ info_node = perf_env__find_bpf_prog_info(dso->bpf_prog.env,
+ dso->bpf_prog.id);
+ if (!info_node) {
+ ret = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF;
+ goto out;
+ }
+ info_linear = info_node->info_linear;
+ sub_id = dso->bpf_prog.sub_id;
+
+ info.buffer = (void *)(uintptr_t)(info_linear->info.jited_prog_insns);
+ info.buffer_length = info_linear->info.jited_prog_len;
+
+ if (info_linear->info.nr_line_info)
+ prog_linfo = bpf_prog_linfo__new(&info_linear->info);
+
+ if (info_linear->info.btf_id) {
+ struct btf_node *node;
+
+ node = perf_env__find_btf(dso->bpf_prog.env,
+ info_linear->info.btf_id);
+ if (node)
+ btf = btf__new((__u8 *)(node->data),
+ node->data_size);
+ }
+
+ disassemble_init_for_target(&info);
+
+#ifdef DISASM_FOUR_ARGS_SIGNATURE
+ disassemble = disassembler(info.arch,
+ bfd_big_endian(bfdf),
+ info.mach,
+ bfdf);
+#else
+ disassemble = disassembler(bfdf);
+#endif
+ if (disassemble == NULL)
+ abort();
+
+ fflush(s);
+ do {
+ const struct bpf_line_info *linfo = NULL;
+ struct disasm_line *dl;
+ size_t prev_buf_size;
+ const char *srcline;
+ u64 addr;
+
+ addr = pc + ((u64 *)(uintptr_t)(info_linear->info.jited_ksyms))[sub_id];
+ count = disassemble(pc, &info);
+
+ if (prog_linfo)
+ linfo = bpf_prog_linfo__lfind_addr_func(prog_linfo,
+ addr, sub_id,
+ nr_skip);
+
+ if (linfo && btf) {
+ srcline = btf__name_by_offset(btf, linfo->line_off);
+ nr_skip++;
+ } else
+ srcline = NULL;
+
+ fprintf(s, "\n");
+ prev_buf_size = buf_size;
+ fflush(s);
+
+ if (!annotate_opts.hide_src_code && srcline) {
+ args->offset = -1;
+ args->line = strdup(srcline);
+ args->line_nr = 0;
+ args->fileloc = NULL;
+ args->ms.sym = sym;
+ dl = disasm_line__new(args);
+ if (dl) {
+ annotation_line__add(&dl->al,
+ &notes->src->source);
+ }
+ }
+
+ args->offset = pc;
+ args->line = buf + prev_buf_size;
+ args->line_nr = 0;
+ args->fileloc = NULL;
+ args->ms.sym = sym;
+ dl = disasm_line__new(args);
+ if (dl)
+ annotation_line__add(&dl->al, &notes->src->source);
+
+ pc += count;
+ } while (count > 0 && pc < len);
+
+ ret = 0;
+out:
+ free(prog_linfo);
+ btf__free(btf);
+ fclose(s);
+ bfd_close(bfdf);
+ return ret;
+}
+#else // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
+static int symbol__disassemble_bpf(struct symbol *sym __maybe_unused,
+ struct annotate_args *args __maybe_unused)
+{
+ return SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF;
+}
+#endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
+
+static int
+symbol__disassemble_bpf_image(struct symbol *sym,
+ struct annotate_args *args)
+{
+ struct annotation *notes = symbol__annotation(sym);
+ struct disasm_line *dl;
+
+ args->offset = -1;
+ args->line = strdup("to be implemented");
+ args->line_nr = 0;
+ args->fileloc = NULL;
+ dl = disasm_line__new(args);
+ if (dl)
+ annotation_line__add(&dl->al, &notes->src->source);
+
+ zfree(&args->line);
+ return 0;
+}
+
+/*
+ * Possibly create a new version of line with tabs expanded. Returns the
+ * existing or new line, storage is updated if a new line is allocated. If
+ * allocation fails then NULL is returned.
+ */
+static char *expand_tabs(char *line, char **storage, size_t *storage_len)
+{
+ size_t i, src, dst, len, new_storage_len, num_tabs;
+ char *new_line;
+ size_t line_len = strlen(line);
+
+ for (num_tabs = 0, i = 0; i < line_len; i++)
+ if (line[i] == '\t')
+ num_tabs++;
+
+ if (num_tabs == 0)
+ return line;
+
+ /*
+ * Space for the line and '\0', less the leading and trailing
+ * spaces. Each tab may introduce 7 additional spaces.
+ */
+ new_storage_len = line_len + 1 + (num_tabs * 7);
+
+ new_line = malloc(new_storage_len);
+ if (new_line == NULL) {
+ pr_err("Failure allocating memory for tab expansion\n");
+ return NULL;
+ }
+
+ /*
+ * Copy regions starting at src and expand tabs. If there are two
+ * adjacent tabs then 'src == i', the memcpy is of size 0 and the spaces
+ * are inserted.
+ */
+ for (i = 0, src = 0, dst = 0; i < line_len && num_tabs; i++) {
+ if (line[i] == '\t') {
+ len = i - src;
+ memcpy(&new_line[dst], &line[src], len);
+ dst += len;
+ new_line[dst++] = ' ';
+ while (dst % 8 != 0)
+ new_line[dst++] = ' ';
+ src = i + 1;
+ num_tabs--;
+ }
+ }
+
+ /* Expand the last region. */
+ len = line_len - src;
+ memcpy(&new_line[dst], &line[src], len);
+ dst += len;
+ new_line[dst] = '\0';
+
+ free(*storage);
+ *storage = new_line;
+ *storage_len = new_storage_len;
+ return new_line;
+}
+
+int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
+{
+ struct annotation_options *opts = &annotate_opts;
+ struct map *map = args->ms.map;
+ struct dso *dso = map__dso(map);
+ char *command;
+ FILE *file;
+ char symfs_filename[PATH_MAX];
+ struct kcore_extract kce;
+ bool delete_extract = false;
+ bool decomp = false;
+ int lineno = 0;
+ char *fileloc = NULL;
+ int nline;
+ char *line;
+ size_t line_len;
+ const char *objdump_argv[] = {
+ "/bin/sh",
+ "-c",
+ NULL, /* Will be the objdump command to run. */
+ "--",
+ NULL, /* Will be the symfs path. */
+ NULL,
+ };
+ struct child_process objdump_process;
+ int err = dso__disassemble_filename(dso, symfs_filename, sizeof(symfs_filename));
+
+ if (err)
+ return err;
+
+ pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
+ symfs_filename, sym->name, map__unmap_ip(map, sym->start),
+ map__unmap_ip(map, sym->end));
+
+ pr_debug("annotating [%p] %30s : [%p] %30s\n",
+ dso, dso->long_name, sym, sym->name);
+
+ if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) {
+ return symbol__disassemble_bpf(sym, args);
+ } else if (dso->binary_type == DSO_BINARY_TYPE__BPF_IMAGE) {
+ return symbol__disassemble_bpf_image(sym, args);
+ } else if (dso__is_kcore(dso)) {
+ kce.kcore_filename = symfs_filename;
+ kce.addr = map__rip_2objdump(map, sym->start);
+ kce.offs = sym->start;
+ kce.len = sym->end - sym->start;
+ if (!kcore_extract__create(&kce)) {
+ delete_extract = true;
+ strlcpy(symfs_filename, kce.extract_filename,
+ sizeof(symfs_filename));
+ }
+ } else if (dso__needs_decompress(dso)) {
+ char tmp[KMOD_DECOMP_LEN];
+
+ if (dso__decompress_kmodule_path(dso, symfs_filename,
+ tmp, sizeof(tmp)) < 0)
+ return -1;
+
+ decomp = true;
+ strcpy(symfs_filename, tmp);
+ }
+
+ err = asprintf(&command,
+ "%s %s%s --start-address=0x%016" PRIx64
+ " --stop-address=0x%016" PRIx64
+ " %s -d %s %s %s %c%s%c %s%s -C \"$1\"",
+ opts->objdump_path ?: "objdump",
+ opts->disassembler_style ? "-M " : "",
+ opts->disassembler_style ?: "",
+ map__rip_2objdump(map, sym->start),
+ map__rip_2objdump(map, sym->end),
+ opts->show_linenr ? "-l" : "",
+ opts->show_asm_raw ? "" : "--no-show-raw-insn",
+ opts->annotate_src ? "-S" : "",
+ opts->prefix ? "--prefix " : "",
+ opts->prefix ? '"' : ' ',
+ opts->prefix ?: "",
+ opts->prefix ? '"' : ' ',
+ opts->prefix_strip ? "--prefix-strip=" : "",
+ opts->prefix_strip ?: "");
+
+ if (err < 0) {
+ pr_err("Failure allocating memory for the command to run\n");
+ goto out_remove_tmp;
+ }
+
+ pr_debug("Executing: %s\n", command);
+
+ objdump_argv[2] = command;
+ objdump_argv[4] = symfs_filename;
+
+ /* Create a pipe to read from for stdout */
+ memset(&objdump_process, 0, sizeof(objdump_process));
+ objdump_process.argv = objdump_argv;
+ objdump_process.out = -1;
+ objdump_process.err = -1;
+ objdump_process.no_stderr = 1;
+ if (start_command(&objdump_process)) {
+ pr_err("Failure starting to run %s\n", command);
+ err = -1;
+ goto out_free_command;
+ }
+
+ file = fdopen(objdump_process.out, "r");
+ if (!file) {
+ pr_err("Failure creating FILE stream for %s\n", command);
+ /*
+ * If we were using debug info should retry with
+ * original binary.
+ */
+ err = -1;
+ goto out_close_stdout;
+ }
+
+ /* Storage for getline. */
+ line = NULL;
+ line_len = 0;
+
+ nline = 0;
+ while (!feof(file)) {
+ const char *match;
+ char *expanded_line;
+
+ if (getline(&line, &line_len, file) < 0 || !line)
+ break;
+
+ /* Skip lines containing "filename:" */
+ match = strstr(line, symfs_filename);
+ if (match && match[strlen(symfs_filename)] == ':')
+ continue;
+
+ expanded_line = strim(line);
+ expanded_line = expand_tabs(expanded_line, &line, &line_len);
+ if (!expanded_line)
+ break;
+
+ /*
+ * The source code line number (lineno) needs to be kept in
+ * across calls to symbol__parse_objdump_line(), so that it
+ * can associate it with the instructions till the next one.
+ * See disasm_line__new() and struct disasm_line::line_nr.
+ */
+ if (symbol__parse_objdump_line(sym, args, expanded_line,
+ &lineno, &fileloc) < 0)
+ break;
+ nline++;
+ }
+ free(line);
+ free(fileloc);
+
+ err = finish_command(&objdump_process);
+ if (err)
+ pr_err("Error running %s\n", command);
+
+ if (nline == 0) {
+ err = -1;
+ pr_err("No output from %s\n", command);
+ }
+
+ /*
+ * kallsyms does not have symbol sizes so there may a nop at the end.
+ * Remove it.
+ */
+ if (dso__is_kcore(dso))
+ delete_last_nop(sym);
+
+ fclose(file);
+
+out_close_stdout:
+ close(objdump_process.out);
+
+out_free_command:
+ free(command);
+
+out_remove_tmp:
+ if (decomp)
+ unlink(symfs_filename);
+
+ if (delete_extract)
+ kcore_extract__delete(&kce);
+
+ return err;
+}
diff --git a/tools/perf/util/disasm.h b/tools/perf/util/disasm.h
new file mode 100644
index 000000000000..3d381a043520
--- /dev/null
+++ b/tools/perf/util/disasm.h
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef __PERF_UTIL_DISASM_H
+#define __PERF_UTIL_DISASM_H
+
+#include "map_symbol.h"
+
+struct annotation_options;
+struct disasm_line;
+struct ins;
+struct evsel;
+struct symbol;
+
+struct arch {
+ const char *name;
+ struct ins *instructions;
+ size_t nr_instructions;
+ size_t nr_instructions_allocated;
+ struct ins_ops *(*associate_instruction_ops)(struct arch *arch, const char *name);
+ bool sorted_instructions;
+ bool initialized;
+ const char *insn_suffix;
+ void *priv;
+ unsigned int model;
+ unsigned int family;
+ int (*init)(struct arch *arch, char *cpuid);
+ bool (*ins_is_fused)(struct arch *arch, const char *ins1,
+ const char *ins2);
+ struct {
+ char comment_char;
+ char skip_functions_char;
+ char register_char;
+ char memory_ref_char;
+ char imm_char;
+ } objdump;
+};
+
+struct ins {
+ const char *name;
+ struct ins_ops *ops;
+};
+
+struct ins_operands {
+ char *raw;
+ struct {
+ char *raw;
+ char *name;
+ struct symbol *sym;
+ u64 addr;
+ s64 offset;
+ bool offset_avail;
+ bool outside;
+ bool multi_regs;
+ } target;
+ union {
+ struct {
+ char *raw;
+ char *name;
+ u64 addr;
+ bool multi_regs;
+ } source;
+ struct {
+ struct ins ins;
+ struct ins_operands *ops;
+ } locked;
+ struct {
+ char *raw_comment;
+ char *raw_func_start;
+ } jump;
+ };
+};
+
+struct ins_ops {
+ void (*free)(struct ins_operands *ops);
+ int (*parse)(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms);
+ int (*scnprintf)(struct ins *ins, char *bf, size_t size,
+ struct ins_operands *ops, int max_ins_name);
+};
+
+struct annotate_args {
+ struct arch *arch;
+ struct map_symbol ms;
+ struct evsel *evsel;
+ struct annotation_options *options;
+ s64 offset;
+ char *line;
+ int line_nr;
+ char *fileloc;
+};
+
+struct arch *arch__find(const char *name);
+bool arch__is(struct arch *arch, const char *name);
+
+struct ins_ops *ins__find(struct arch *arch, const char *name);
+int ins__scnprintf(struct ins *ins, char *bf, size_t size,
+ struct ins_operands *ops, int max_ins_name);
+
+bool ins__is_call(const struct ins *ins);
+bool ins__is_jump(const struct ins *ins);
+bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
+bool ins__is_nop(const struct ins *ins);
+bool ins__is_ret(const struct ins *ins);
+bool ins__is_lock(const struct ins *ins);
+
+struct disasm_line *disasm_line__new(struct annotate_args *args);
+void disasm_line__free(struct disasm_line *dl);
+
+int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size,
+ bool raw, int max_ins_name);
+
+int symbol__disassemble(struct symbol *sym, struct annotate_args *args);
+
+#endif /* __PERF_UTIL_DISASM_H */
--
2.44.0.478.gd926399ef9-goog

2024-03-29 16:33:07

by Ian Rogers

Subject: Re: [PATCH 0/4] perf annotate: Use libcapstone as a disasssembler

On Thu, Mar 28, 2024 at 4:20 PM Namhyung Kim <[email protected]> wrote:
>
> Hello,
>
> As we've added libcapstone support, it's natural to use it for perf annotate
> as well. This change added the capstone support on x86 first. Other archs
> can be added later (by someone who can verify it doesn't break things).
>
> For now it tries to use capstone (if available) before objdump. But it
> doesn't support source file and line number info. So users should use the
> objdump (by passing --objdump=PATH option) if they need them. For example,
> this command line will keep the existing behavior (i.e. using objdump).
>
> # not to use capstone for disassembly
> $ perf annotate --objdump=objdump
>
> The capstone uses LLVM objdump style output which is slightly different than
> the GNU objdump. But it should not have differences besides that. I've
> verified the result of data type profiling and it produced the same output
> but gave me ~3x speedups.
>
> Thanks,
> Namhyung

I wanted to see what -fsanitize=address would think of libcaptstone
and no issues, so:

Tested-by: Ian Rogers <[email protected]>

Some thoughts:
- it may be worth adding to the commit message in "perf annotate:
Split out util/disasm.c" that there's no functional change,
- we lack perf annotate testing,
- it seems capstone should be opt-out rather than opt-in as a library
dependency (given the performance delta and the objdump interactions
are at best messy),
- if libcapstone could solve our addr2line issues too this would be great :-).

Thanks,
Ian

> Cc: Changbin Du <[email protected]>
>
>
> Namhyung Kim (4):
> perf annotate: Use ins__is_xxx() if possible
> perf annotate: Add and use ins__is_nop()
> perf annotate: Split out util/disasm.c
> perf annotate: Use libcapstone to disassemble
>
> tools/perf/util/Build | 1 +
> tools/perf/util/annotate.c | 1711 ++---------------------------------
> tools/perf/util/annotate.h | 59 +-
> tools/perf/util/disasm.c | 1739 ++++++++++++++++++++++++++++++++++++
> tools/perf/util/disasm.h | 112 +++
> 5 files changed, 1914 insertions(+), 1708 deletions(-)
> create mode 100644 tools/perf/util/disasm.c
> create mode 100644 tools/perf/util/disasm.h
>
> --
> 2.44.0.478.gd926399ef9-goog
>

2024-03-29 17:10:07

by Arnaldo Carvalho de Melo

Subject: Re: [PATCH 0/4] perf annotate: Use libcapstone as a disasssembler

On Thu, Mar 28, 2024 at 04:20:05PM -0700, Namhyung Kim wrote:
> Hello,
>
> As we've added libcapstone support, it's natural to use it for perf annotate
> as well. This change added the capstone support on x86 first. Other archs
> can be added later (by someone who can verify it doesn't break things).
>
> For now it tries to use capstone (if available) before objdump. But it
> doesn't support source file and line number info. So users should use the
> objdump (by passing --objdump=PATH option) if they need them. For example,
> this command line will keep the existing behavior (i.e. using objdump).
>
> # not to use capstone for disassembly
> $ perf annotate --objdump=objdump
>
> The capstone uses LLVM objdump style output which is slightly different than
> the GNU objdump. But it should not have differences besides that. I've
> verified the result of data type profiling and it produced the same output
> but gave me ~3x speedups.

Excellent news, I'll try and test all this soon!

- Arnaldo

2024-03-29 19:58:42

by Namhyung Kim

Subject: Re: [PATCH 0/4] perf annotate: Use libcapstone as a disasssembler

Hi Ian,

On Fri, Mar 29, 2024 at 9:33 AM Ian Rogers <[email protected]> wrote:
>
> On Thu, Mar 28, 2024 at 4:20 PM Namhyung Kim <[email protected]> wrote:
> >
> > Hello,
> >
> > As we've added libcapstone support, it's natural to use it for perf annotate
> > as well. This change added the capstone support on x86 first. Other archs
> > can be added later (by someone who can verify it doesn't break things).
> >
> > For now it tries to use capstone (if available) before objdump. But it
> > doesn't support source file and line number info. So users should use the
> > objdump (by passing --objdump=PATH option) if they need them. For example,
> > this command line will keep the existing behavior (i.e. using objdump).
> >
> > # not to use capstone for disassembly
> > $ perf annotate --objdump=objdump
> >
> > The capstone uses LLVM objdump style output which is slightly different than
> > the GNU objdump. But it should not have differences besides that. I've
> > verified the result of data type profiling and it produced the same output
> > but gave me ~3x speedups.
> >
> > Thanks,
> > Namhyung
>
> I wanted to see what -fsanitize=address would think of libcaptstone
> and no issues, so:
>
> Tested-by: Ian Rogers <[email protected]>

Thanks for checking it!

>
> Some thoughts:
> - it may be worth adding to the commit message in "perf annotate:
> Split out util/disasm.c" that there's no functional change,
> - we lack perf annotate testing,
> - it seems capstone should be opt-out rather than opt-in as a library
> dependency (given the performance delta and the objdump interactions
> are at best messy),
> - if libcapstone could solve our addr2line issues too this would be great :-).

I think addr2line should be handled using libdw. I'll take a look.

Thanks,
Namhyung