* [PATCH 3/4] perf annotate: Split out util/disasm.c
2024-03-28 23:20 [PATCH 0/4] perf annotate: Use libcapstone as a disasssembler Namhyung Kim
2024-03-28 23:20 ` [PATCH 1/4] perf annotate: Use ins__is_xxx() if possible Namhyung Kim
2024-03-28 23:20 ` [PATCH 2/4] perf annotate: Add and use ins__is_nop() Namhyung Kim
@ 2024-03-28 23:20 ` Namhyung Kim
2024-03-28 23:20 ` [PATCH 4/4] perf annotate: Use libcapstone to disassemble Namhyung Kim
` (2 subsequent siblings)
5 siblings, 0 replies; 8+ messages in thread
From: Namhyung Kim @ 2024-03-28 23:20 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, Ian Rogers, Kan Liang
Cc: Jiri Olsa, Adrian Hunter, Peter Zijlstra, Ingo Molnar, LKML,
linux-perf-users
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 <namhyung@kernel.org>
---
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 = ¬es->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 = ¬es->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 = ¬es->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 = ¬es->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, ¬es->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 = ¬es->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,
- ¬es->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, ¬es->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, ¬es->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, ¬es->src->source);
+ return 0;
+}
+
+static void delete_last_nop(struct symbol *sym)
+{
+ struct annotation *notes = symbol__annotation(sym);
+ struct list_head *list = ¬es->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,
+ ¬es->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, ¬es->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, ¬es->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
^ permalink raw reply related [flat|nested] 8+ messages in thread