diff options
Diffstat (limited to 'tools/perf/util/disasm.c')
-rw-r--r-- | tools/perf/util/disasm.c | 652 |
1 files changed, 36 insertions, 616 deletions
diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c index b1e4919d016f..50b9433f3f8e 100644 --- a/tools/perf/util/disasm.c +++ b/tools/perf/util/disasm.c @@ -14,13 +14,15 @@ #include "annotate.h" #include "annotate-data.h" #include "build-id.h" +#include "capstone.h" #include "debug.h" #include "disasm.h" -#include "disasm_bpf.h" #include "dso.h" #include "dwarf-regs.h" #include "env.h" #include "evsel.h" +#include "libbfd.h" +#include "llvm.h" #include "map.h" #include "maps.h" #include "namespaces.h" @@ -49,7 +51,6 @@ static int call__scnprintf(struct ins *ins, char *bf, size_t size, static void ins__sort(struct arch *arch); static int disasm_line__parse(char *line, const char **namep, char **rawp); static int disasm_line__parse_powerpc(struct disasm_line *dl, struct annotate_args *args); -static char *expand_tabs(char *line, char **storage, size_t *storage_len); static __attribute__((constructor)) void symbol__init_regexpr(void) { @@ -246,8 +247,8 @@ static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size, 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) +static 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); @@ -390,13 +391,16 @@ static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_s * skip over possible up to 2 operands to get to address, e.g.: * tbnz w0, #26, ffff0000083cd190 <security_file_permission+0xd0> */ - if (c++ != NULL) { + if (c != NULL) { + c++; ops->target.addr = strtoull(c, NULL, 16); if (!ops->target.addr) { c = strchr(c, ','); c = validate_comma(c, ops); - if (c++ != NULL) + if (c != NULL) { + c++; ops->target.addr = strtoull(c, NULL, 16); + } } } else { ops->target.addr = strtoull(ops->raw, NULL, 16); @@ -824,7 +828,7 @@ static struct ins_ops ret_ops = { .scnprintf = ins__raw_scnprintf, }; -bool ins__is_nop(const struct ins *ins) +static bool ins__is_nop(const struct ins *ins) { return ins->ops == &nop_ops; } @@ -1330,420 +1334,6 @@ fallback: return 0; } -#ifdef HAVE_LIBCAPSTONE_SUPPORT -#include <capstone/capstone.h> - -int capstone_init(struct machine *machine, csh *cs_handle, bool is64, bool disassembler_style); - -static int open_capstone_handle(struct annotate_args *args, bool is_64bit, - csh *handle) -{ - struct annotation_options *opt = args->options; - cs_mode mode = is_64bit ? CS_MODE_64 : CS_MODE_32; - - /* TODO: support more architectures */ - if (!arch__is(args->arch, "x86")) - return -1; - - if (cs_open(CS_ARCH_X86, mode, handle) != CS_ERR_OK) - return -1; - - if (!opt->disassembler_style || - !strcmp(opt->disassembler_style, "att")) - cs_option(*handle, CS_OPT_SYNTAX, CS_OPT_SYNTAX_ATT); - - /* - * Resolving address operands to symbols is implemented - * on x86 by investigating instruction details. - */ - cs_option(*handle, CS_OPT_DETAIL, CS_OPT_ON); - - return 0; -} -#endif - -#if defined(HAVE_LIBCAPSTONE_SUPPORT) || defined(HAVE_LIBLLVM_SUPPORT) -struct find_file_offset_data { - u64 ip; - u64 offset; -}; - -/* This will be called for each PHDR in an ELF binary */ -static int find_file_offset(u64 start, u64 len, u64 pgoff, void *arg) -{ - struct find_file_offset_data *data = arg; - - if (start <= data->ip && data->ip < start + len) { - data->offset = pgoff + data->ip - start; - return 1; - } - return 0; -} - -static u8 * -read_symbol(const char *filename, struct map *map, struct symbol *sym, - u64 *len, bool *is_64bit) -{ - struct dso *dso = map__dso(map); - struct nscookie nsc; - u64 start = map__rip_2objdump(map, sym->start); - u64 end = map__rip_2objdump(map, sym->end); - int fd, count; - u8 *buf = NULL; - struct find_file_offset_data data = { - .ip = start, - }; - - *is_64bit = false; - - nsinfo__mountns_enter(dso__nsinfo(dso), &nsc); - fd = open(filename, O_RDONLY); - nsinfo__mountns_exit(&nsc); - if (fd < 0) - return NULL; - - if (file__read_maps(fd, /*exe=*/true, find_file_offset, &data, - is_64bit) == 0) - goto err; - - *len = end - start; - buf = malloc(*len); - if (buf == NULL) - goto err; - - count = pread(fd, buf, *len, data.offset); - close(fd); - fd = -1; - - if ((u64)count != *len) - goto err; - - return buf; - -err: - if (fd >= 0) - close(fd); - free(buf); - return NULL; -} -#endif - -#if !defined(HAVE_LIBCAPSTONE_SUPPORT) || !defined(HAVE_LIBLLVM_SUPPORT) -static void symbol__disassembler_missing(const char *disassembler, const char *filename, - struct symbol *sym) -{ - pr_debug("The %s disassembler isn't linked in for %s in %s\n", - disassembler, sym->name, filename); -} -#endif - -#ifdef HAVE_LIBCAPSTONE_SUPPORT -static void print_capstone_detail(cs_insn *insn, char *buf, size_t len, - struct annotate_args *args, u64 addr) -{ - int i; - struct map *map = args->ms.map; - struct symbol *sym; - - /* TODO: support more architectures */ - if (!arch__is(args->arch, "x86")) - return; - - if (insn->detail == NULL) - return; - - for (i = 0; i < insn->detail->x86.op_count; i++) { - cs_x86_op *op = &insn->detail->x86.operands[i]; - u64 orig_addr; - - if (op->type != X86_OP_MEM) - continue; - - /* only print RIP-based global symbols for now */ - if (op->mem.base != X86_REG_RIP) - continue; - - /* get the target address */ - orig_addr = addr + insn->size + op->mem.disp; - addr = map__objdump_2mem(map, orig_addr); - - if (dso__kernel(map__dso(map))) { - /* - * The kernel maps can be splitted into sections, - * let's find the map first and the search the symbol. - */ - map = maps__find(map__kmaps(map), addr); - if (map == NULL) - continue; - } - - /* convert it to map-relative address for search */ - addr = map__map_ip(map, addr); - - sym = map__find_symbol(map, addr); - if (sym == NULL) - continue; - - if (addr == sym->start) { - scnprintf(buf, len, "\t# %"PRIx64" <%s>", - orig_addr, sym->name); - } else { - scnprintf(buf, len, "\t# %"PRIx64" <%s+%#"PRIx64">", - orig_addr, sym->name, addr - sym->start); - } - break; - } -} - -static int symbol__disassemble_capstone_powerpc(char *filename, struct symbol *sym, - struct annotate_args *args) -{ - struct annotation *notes = symbol__annotation(sym); - struct map *map = args->ms.map; - struct dso *dso = map__dso(map); - struct nscookie nsc; - u64 start = map__rip_2objdump(map, sym->start); - u64 end = map__rip_2objdump(map, sym->end); - u64 len = end - start; - u64 offset; - int i, fd, count; - bool is_64bit = false; - bool needs_cs_close = false; - u8 *buf = NULL; - struct find_file_offset_data data = { - .ip = start, - }; - csh handle; - char disasm_buf[512]; - struct disasm_line *dl; - u32 *line; - bool disassembler_style = false; - - if (args->options->objdump_path) - return -1; - - nsinfo__mountns_enter(dso__nsinfo(dso), &nsc); - fd = open(filename, O_RDONLY); - nsinfo__mountns_exit(&nsc); - if (fd < 0) - return -1; - - if (file__read_maps(fd, /*exe=*/true, find_file_offset, &data, - &is_64bit) == 0) - goto err; - - if (!args->options->disassembler_style || - !strcmp(args->options->disassembler_style, "att")) - disassembler_style = true; - - if (capstone_init(maps__machine(args->ms.maps), &handle, is_64bit, disassembler_style) < 0) - goto err; - - needs_cs_close = true; - - buf = malloc(len); - if (buf == NULL) - goto err; - - count = pread(fd, buf, len, data.offset); - close(fd); - fd = -1; - - if ((u64)count != len) - goto err; - - line = (u32 *)buf; - - /* add the function address and name */ - scnprintf(disasm_buf, sizeof(disasm_buf), "%#"PRIx64" <%s>:", - start, sym->name); - - args->offset = -1; - args->line = disasm_buf; - args->line_nr = 0; - args->fileloc = NULL; - args->ms.sym = sym; - - dl = disasm_line__new(args); - if (dl == NULL) - goto err; - - annotation_line__add(&dl->al, ¬es->src->source); - - /* - * TODO: enable disassm for powerpc - * count = cs_disasm(handle, buf, len, start, len, &insn); - * - * For now, only binary code is saved in disassembled line - * to be used in "type" and "typeoff" sort keys. Each raw code - * is 32 bit instruction. So use "len/4" to get the number of - * entries. - */ - count = len/4; - - for (i = 0, offset = 0; i < count; i++) { - args->offset = offset; - sprintf(args->line, "%x", line[i]); - - dl = disasm_line__new(args); - if (dl == NULL) - break; - - annotation_line__add(&dl->al, ¬es->src->source); - - offset += 4; - } - - /* It failed in the middle */ - if (offset != len) { - struct list_head *list = ¬es->src->source; - - /* Discard all lines and fallback to objdump */ - while (!list_empty(list)) { - dl = list_first_entry(list, struct disasm_line, al.node); - - list_del_init(&dl->al.node); - disasm_line__free(dl); - } - count = -1; - } - -out: - if (needs_cs_close) - cs_close(&handle); - free(buf); - return count < 0 ? count : 0; - -err: - if (fd >= 0) - close(fd); - count = -1; - goto out; -} - -static int symbol__disassemble_capstone(char *filename, struct symbol *sym, - struct annotate_args *args) -{ - struct annotation *notes = symbol__annotation(sym); - struct map *map = args->ms.map; - u64 start = map__rip_2objdump(map, sym->start); - u64 len; - u64 offset; - int i, count, free_count; - bool is_64bit = false; - bool needs_cs_close = false; - u8 *buf = NULL; - csh handle; - cs_insn *insn = NULL; - char disasm_buf[512]; - struct disasm_line *dl; - - if (args->options->objdump_path) - return -1; - - buf = read_symbol(filename, map, sym, &len, &is_64bit); - if (buf == NULL) - return -1; - - /* add the function address and name */ - scnprintf(disasm_buf, sizeof(disasm_buf), "%#"PRIx64" <%s>:", - start, sym->name); - - args->offset = -1; - args->line = disasm_buf; - args->line_nr = 0; - args->fileloc = NULL; - args->ms.sym = sym; - - dl = disasm_line__new(args); - if (dl == NULL) - goto err; - - annotation_line__add(&dl->al, ¬es->src->source); - - if (open_capstone_handle(args, is_64bit, &handle) < 0) - goto err; - - needs_cs_close = true; - - free_count = count = cs_disasm(handle, buf, len, start, len, &insn); - for (i = 0, offset = 0; i < count; i++) { - int printed; - - printed = scnprintf(disasm_buf, sizeof(disasm_buf), - " %-7s %s", - insn[i].mnemonic, insn[i].op_str); - print_capstone_detail(&insn[i], disasm_buf + printed, - sizeof(disasm_buf) - printed, args, - start + offset); - - args->offset = offset; - args->line = disasm_buf; - - dl = disasm_line__new(args); - if (dl == NULL) - goto err; - - annotation_line__add(&dl->al, ¬es->src->source); - - offset += insn[i].size; - } - - /* It failed in the middle: probably due to unknown instructions */ - if (offset != len) { - struct list_head *list = ¬es->src->source; - - /* Discard all lines and fallback to objdump */ - while (!list_empty(list)) { - dl = list_first_entry(list, struct disasm_line, al.node); - - list_del_init(&dl->al.node); - disasm_line__free(dl); - } - count = -1; - } - -out: - if (needs_cs_close) { - cs_close(&handle); - if (free_count > 0) - cs_free(insn, free_count); - } - free(buf); - return count < 0 ? count : 0; - -err: - if (needs_cs_close) { - struct disasm_line *tmp; - - /* - * It probably failed in the middle of the above loop. - * Release any resources it might add. - */ - list_for_each_entry_safe(dl, tmp, ¬es->src->source, al.node) { - list_del(&dl->al.node); - disasm_line__free(dl); - } - } - count = -1; - goto out; -} -#else // HAVE_LIBCAPSTONE_SUPPORT -static int symbol__disassemble_capstone(char *filename, struct symbol *sym, - struct annotate_args *args __maybe_unused) -{ - symbol__disassembler_missing("capstone", filename, sym); - return -1; -} - -static int symbol__disassemble_capstone_powerpc(char *filename, struct symbol *sym, - struct annotate_args *args __maybe_unused) -{ - symbol__disassembler_missing("capstone powerpc", filename, sym); - return -1; -} -#endif // HAVE_LIBCAPSTONE_SUPPORT - static int symbol__disassemble_raw(char *filename, struct symbol *sym, struct annotate_args *args) { @@ -1830,201 +1420,12 @@ err: goto out; } -#ifdef HAVE_LIBLLVM_SUPPORT -#include <llvm-c/Disassembler.h> -#include <llvm-c/Target.h> -#include "util/llvm-c-helpers.h" - -struct symbol_lookup_storage { - u64 branch_addr; - u64 pcrel_load_addr; -}; - -/* - * Whenever LLVM wants to resolve an address into a symbol, it calls this - * callback. We don't ever actually _return_ anything (in particular, because - * it puts quotation marks around what we return), but we use this as a hint - * that there is a branch or PC-relative address in the expression that we - * should add some textual annotation for after the instruction. The caller - * will use this information to add the actual annotation. - */ -static const char * -symbol_lookup_callback(void *disinfo, uint64_t value, - uint64_t *ref_type, - uint64_t address __maybe_unused, - const char **ref __maybe_unused) -{ - struct symbol_lookup_storage *storage = disinfo; - - if (*ref_type == LLVMDisassembler_ReferenceType_In_Branch) - storage->branch_addr = value; - else if (*ref_type == LLVMDisassembler_ReferenceType_In_PCrel_Load) - storage->pcrel_load_addr = value; - *ref_type = LLVMDisassembler_ReferenceType_InOut_None; - return NULL; -} - -static int symbol__disassemble_llvm(char *filename, struct symbol *sym, - struct annotate_args *args) -{ - struct annotation *notes = symbol__annotation(sym); - struct map *map = args->ms.map; - struct dso *dso = map__dso(map); - u64 start = map__rip_2objdump(map, sym->start); - u8 *buf; - u64 len; - u64 pc; - bool is_64bit; - char triplet[64]; - char disasm_buf[2048]; - size_t disasm_len; - struct disasm_line *dl; - LLVMDisasmContextRef disasm = NULL; - struct symbol_lookup_storage storage; - char *line_storage = NULL; - size_t line_storage_len = 0; - int ret = -1; - - if (args->options->objdump_path) - return -1; - - LLVMInitializeAllTargetInfos(); - LLVMInitializeAllTargetMCs(); - LLVMInitializeAllDisassemblers(); - - buf = read_symbol(filename, map, sym, &len, &is_64bit); - if (buf == NULL) - return -1; - - if (arch__is(args->arch, "x86")) { - if (is_64bit) - scnprintf(triplet, sizeof(triplet), "x86_64-pc-linux"); - else - scnprintf(triplet, sizeof(triplet), "i686-pc-linux"); - } else { - scnprintf(triplet, sizeof(triplet), "%s-linux-gnu", - args->arch->name); - } - - disasm = LLVMCreateDisasm(triplet, &storage, 0, NULL, - symbol_lookup_callback); - if (disasm == NULL) - goto err; - - if (args->options->disassembler_style && - !strcmp(args->options->disassembler_style, "intel")) - LLVMSetDisasmOptions(disasm, - LLVMDisassembler_Option_AsmPrinterVariant); - - /* - * This needs to be set after AsmPrinterVariant, due to a bug in LLVM; - * setting AsmPrinterVariant makes a new instruction printer, making it - * forget about the PrintImmHex flag (which is applied before if both - * are given to the same call). - */ - LLVMSetDisasmOptions(disasm, LLVMDisassembler_Option_PrintImmHex); - - /* add the function address and name */ - scnprintf(disasm_buf, sizeof(disasm_buf), "%#"PRIx64" <%s>:", - start, sym->name); - - args->offset = -1; - args->line = disasm_buf; - args->line_nr = 0; - args->fileloc = NULL; - args->ms.sym = sym; - - dl = disasm_line__new(args); - if (dl == NULL) - goto err; - - annotation_line__add(&dl->al, ¬es->src->source); - - pc = start; - for (u64 offset = 0; offset < len; ) { - unsigned int ins_len; - - storage.branch_addr = 0; - storage.pcrel_load_addr = 0; - - ins_len = LLVMDisasmInstruction(disasm, buf + offset, - len - offset, pc, - disasm_buf, sizeof(disasm_buf)); - if (ins_len == 0) - goto err; - disasm_len = strlen(disasm_buf); - - if (storage.branch_addr != 0) { - char *name = llvm_name_for_code(dso, filename, - storage.branch_addr); - if (name != NULL) { - disasm_len += scnprintf(disasm_buf + disasm_len, - sizeof(disasm_buf) - - disasm_len, - " <%s>", name); - free(name); - } - } - if (storage.pcrel_load_addr != 0) { - char *name = llvm_name_for_data(dso, filename, - storage.pcrel_load_addr); - disasm_len += scnprintf(disasm_buf + disasm_len, - sizeof(disasm_buf) - disasm_len, - " # %#"PRIx64, - storage.pcrel_load_addr); - if (name) { - disasm_len += scnprintf(disasm_buf + disasm_len, - sizeof(disasm_buf) - - disasm_len, - " <%s>", name); - free(name); - } - } - - args->offset = offset; - args->line = expand_tabs(disasm_buf, &line_storage, - &line_storage_len); - args->line_nr = 0; - args->fileloc = NULL; - args->ms.sym = sym; - - llvm_addr2line(filename, pc, &args->fileloc, - (unsigned int *)&args->line_nr, false, NULL); - - dl = disasm_line__new(args); - if (dl == NULL) - goto err; - - annotation_line__add(&dl->al, ¬es->src->source); - - free(args->fileloc); - pc += ins_len; - offset += ins_len; - } - - ret = 0; - -err: - LLVMDisasmDispose(disasm); - free(buf); - free(line_storage); - return ret; -} -#else // HAVE_LIBLLVM_SUPPORT -static int symbol__disassemble_llvm(char *filename, struct symbol *sym, - struct annotate_args *args __maybe_unused) -{ - symbol__disassembler_missing("LLVM", filename, sym); - return -1; -} -#endif // HAVE_LIBLLVM_SUPPORT - /* * 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) +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; @@ -2079,6 +1480,23 @@ static char *expand_tabs(char *line, char **storage, size_t *storage_len) return new_line; } +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; +} + static int symbol__disassemble_objdump(const char *filename, struct symbol *sym, struct annotate_args *args) { @@ -2103,6 +1521,12 @@ static int symbol__disassemble_objdump(const char *filename, struct symbol *sym, struct child_process objdump_process; int err; + if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_PROG_INFO) + return symbol__disassemble_bpf_libbfd(sym, args); + + if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_IMAGE) + return symbol__disassemble_bpf_image(sym, args); + err = asprintf(&command, "%s %s%s --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 @@ -2237,11 +1661,7 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args) pr_debug("annotating [%p] %30s : [%p] %30s\n", dso, dso__long_name(dso), sym, sym->name); - if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_PROG_INFO) { - return symbol__disassemble_bpf(sym, args); - } else if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_IMAGE) { - return symbol__disassemble_bpf_image(sym, args); - } else if (dso__binary_type(dso) == DSO_BINARY_TYPE__NOT_FOUND) { + if (dso__binary_type(dso) == DSO_BINARY_TYPE__NOT_FOUND) { return SYMBOL_ANNOTATE_ERRNO__COULDNT_DETERMINE_FILE_TYPE; } else if (dso__is_kcore(dso)) { kce.addr = map__rip_2objdump(map, sym->start); |