diff --git a/MAINTAINERS b/MAINTAINERS index 48aabeeed0297..5cd34419d9528 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4672,6 +4672,7 @@ F: net/sched/act_bpf.c F: net/sched/cls_bpf.c F: samples/bpf/ F: scripts/bpf_doc.py +F: scripts/gen-btf.sh F: scripts/Makefile.btf F: scripts/pahole-version.sh F: tools/bpf/ diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal index 542ba462ed3ec..86f8439955563 100644 --- a/scripts/Makefile.modfinal +++ b/scripts/Makefile.modfinal @@ -38,9 +38,8 @@ quiet_cmd_btf_ko = BTF [M] $@ cmd_btf_ko = \ if [ ! -f $(objtree)/vmlinux ]; then \ printf "Skipping BTF generation for %s due to unavailability of vmlinux\n" $@ 1>&2; \ - else \ - LLVM_OBJCOPY="$(OBJCOPY)" $(PAHOLE) -J $(PAHOLE_FLAGS) $(MODULE_PAHOLE_FLAGS) --btf_base $(objtree)/vmlinux $@; \ - $(RESOLVE_BTFIDS) -b $(objtree)/vmlinux $@; \ + else \ + $(objtree)/scripts/gen-btf.sh --btf_base $(objtree)/vmlinux $@; \ fi; # Same as newer-prereqs, but allows to exclude specified extra dependencies diff --git a/scripts/gen-btf.sh b/scripts/gen-btf.sh new file mode 100755 index 0000000000000..102f8296ae9e9 --- /dev/null +++ b/scripts/gen-btf.sh @@ -0,0 +1,166 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# Copyright (c) 2025 Meta Platforms, Inc. and affiliates. +# +# This script generates BTF data for the provided ELF file. +# +# Kernel BTF generation involves these conceptual steps: +# 1. pahole generates BTF from DWARF data +# 2. resolve_btfids applies kernel-specific btf2btf +# transformations and computes data for .BTF_ids section +# 3. the result gets linked/objcopied into the target binary +# +# How step (3) should be done differs between vmlinux, and +# kernel modules, which is the primary reason for the existence +# of this script. +# +# For modules the script expects vmlinux passed in as --btf_base. +# Generated .BTF, .BTF.base and .BTF_ids sections become embedded +# into the input ELF file with objcopy. +# +# For vmlinux the input file remains unchanged and two files are produced: +# - ${1}.btf.o ready for linking into vmlinux +# - ${1}.btf_ids with .BTF_ids data blob +# This output is consumed by scripts/link-vmlinux.sh + +set -e + +usage() +{ + echo "Usage: $0 [--btf_base ] " + exit 1 +} + +BTF_BASE="" + +while [ $# -gt 0 ]; do + case "$1" in + --btf_base) + BTF_BASE="$2" + shift 2 + ;; + -*) + echo "Unknown option: $1" >&2 + usage + ;; + *) + break + ;; + esac +done + +if [ $# -ne 1 ]; then + usage +fi + +ELF_FILE="$1" +shift + +is_enabled() { + grep -q "^$1=y" ${objtree}/include/config/auto.conf +} + +info() +{ + printf " %-7s %s\n" "${1}" "${2}" +} + +case "${KBUILD_VERBOSE}" in +*1*) + set -x + ;; +esac + +if ! is_enabled CONFIG_DEBUG_INFO_BTF; then + exit 0 +fi + +gen_btf_data() +{ + info BTF "${ELF_FILE}" + btf1="${ELF_FILE}.btf.1" + ${PAHOLE} -J ${PAHOLE_FLAGS} \ + ${BTF_BASE:+--btf_base ${BTF_BASE}} \ + --btf_encode_detached=${btf1} \ + "${ELF_FILE}" + + info BTFIDS "${ELF_FILE}" + RESOLVE_BTFIDS_OPTS="" + if is_enabled CONFIG_WERROR; then + RESOLVE_BTFIDS_OPTS+=" --fatal_warnings " + fi + if [ -n "${KBUILD_VERBOSE}" ]; then + RESOLVE_BTFIDS_OPTS+=" -v " + fi + ${RESOLVE_BTFIDS} ${RESOLVE_BTFIDS_OPTS} \ + ${BTF_BASE:+--btf_base ${BTF_BASE}} \ + --btf ${btf1} "${ELF_FILE}" +} + +gen_btf_o() +{ + local btf_data=${ELF_FILE}.btf.o + + # Create ${btf_data} which contains just .BTF section but no symbols. Add + # SHF_ALLOC because .BTF will be part of the vmlinux image. --strip-all + # deletes all symbols including __start_BTF and __stop_BTF, which will + # be redefined in the linker script. + info OBJCOPY "${btf_data}" + echo "" | ${CC} -c -x c -o ${btf_data} - + ${OBJCOPY} --add-section .BTF=${ELF_FILE}.btf \ + --set-section-flags .BTF=alloc,readonly ${btf_data} + ${OBJCOPY} --only-section=.BTF --strip-all ${btf_data} + + # Change e_type to ET_REL so that it can be used to link final vmlinux. + # GNU ld 2.35+ and lld do not allow an ET_EXEC input. + if is_enabled CONFIG_CPU_BIG_ENDIAN; then + et_rel='\0\1' + else + et_rel='\1\0' + fi + printf "${et_rel}" | dd of="${btf_data}" conv=notrunc bs=1 seek=16 status=none +} + +embed_btf_data() +{ + info OBJCOPY "${ELF_FILE}" + + ${OBJCOPY} \ + --add-section .BTF=${ELF_FILE}.btf \ + --add-section .BTF.base=${ELF_FILE}.distilled_base.btf \ + ${ELF_FILE} + + # a module might not have a .BTF_ids section + if [ -f "${ELF_FILE}.btf_ids" ]; then + ${OBJCOPY} --update-section .BTF_ids=${ELF_FILE}.btf_ids ${ELF_FILE} + fi +} + +cleanup() +{ + rm -f "${ELF_FILE}.btf.1" + rm -f "${ELF_FILE}.btf" + if [ "${BTFGEN_MODE}" == "module" ]; then + rm -f "${ELF_FILE}.distilled_base.btf" + rm -f "${ELF_FILE}.btf_ids" + fi +} +trap cleanup EXIT + +BTFGEN_MODE="vmlinux" +if [ -n "${BTF_BASE}" ]; then + BTFGEN_MODE="module" +fi + +gen_btf_data + +case "${BTFGEN_MODE}" in +vmlinux) + gen_btf_o + ;; +module) + embed_btf_data + ;; +esac + +exit 0 diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 433849ff7529e..728f82af24f6f 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -105,34 +105,6 @@ vmlinux_link() ${kallsymso} ${btf_vmlinux_bin_o} ${arch_vmlinux_o} ${ldlibs} } -# generate .BTF typeinfo from DWARF debuginfo -# ${1} - vmlinux image -gen_btf() -{ - local btf_data=${1}.btf.o - - info BTF "${btf_data}" - LLVM_OBJCOPY="${OBJCOPY}" ${PAHOLE} -J ${PAHOLE_FLAGS} ${1} - - # Create ${btf_data} which contains just .BTF section but no symbols. Add - # SHF_ALLOC because .BTF will be part of the vmlinux image. --strip-all - # deletes all symbols including __start_BTF and __stop_BTF, which will - # be redefined in the linker script. Add 2>/dev/null to suppress GNU - # objcopy warnings: "empty loadable segment detected at ..." - ${OBJCOPY} --only-section=.BTF --set-section-flags .BTF=alloc,readonly \ - --strip-all ${1} "${btf_data}" 2>/dev/null - # Change e_type to ET_REL so that it can be used to link final vmlinux. - # GNU ld 2.35+ and lld do not allow an ET_EXEC input. - if is_enabled CONFIG_CPU_BIG_ENDIAN; then - et_rel='\0\1' - else - et_rel='\1\0' - fi - printf "${et_rel}" | dd of="${btf_data}" conv=notrunc bs=1 seek=16 status=none - - btf_vmlinux_bin_o=${btf_data} -} - # Create ${2}.o file with all symbols from the ${1} object file kallsyms() { @@ -204,6 +176,7 @@ if is_enabled CONFIG_ARCH_WANTS_PRE_LINK_VMLINUX; then fi btf_vmlinux_bin_o= +btfids_vmlinux= kallsymso= strip_debug= generate_map= @@ -224,11 +197,13 @@ if is_enabled CONFIG_KALLSYMS || is_enabled CONFIG_DEBUG_INFO_BTF; then fi if is_enabled CONFIG_DEBUG_INFO_BTF; then - if ! gen_btf .tmp_vmlinux1; then + if ! scripts/gen-btf.sh .tmp_vmlinux1; then echo >&2 "Failed to generate BTF for vmlinux" echo >&2 "Try to disable CONFIG_DEBUG_INFO_BTF" exit 1 fi + btf_vmlinux_bin_o=.tmp_vmlinux1.btf.o + btfids_vmlinux=.tmp_vmlinux1.btf_ids fi if is_enabled CONFIG_KALLSYMS; then @@ -281,14 +256,9 @@ fi vmlinux_link "${VMLINUX}" -# fill in BTF IDs if is_enabled CONFIG_DEBUG_INFO_BTF; then - info BTFIDS "${VMLINUX}" - RESOLVE_BTFIDS_ARGS="" - if is_enabled CONFIG_WERROR; then - RESOLVE_BTFIDS_ARGS=" --fatal_warnings " - fi - ${RESOLVE_BTFIDS} ${RESOLVE_BTFIDS_ARGS} "${VMLINUX}" + info OBJCOPY ${btfids_vmlinux} + ${OBJCOPY} --update-section .BTF_ids=${btfids_vmlinux} ${VMLINUX} fi mksysmap "${VMLINUX}" System.map diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index d47191c6e55e1..4faf16b1ba6b2 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -71,9 +71,11 @@ #include #include #include +#include #include #include #include +#include #include #include #include @@ -98,6 +100,13 @@ # error "Unknown machine endianness!" #endif +enum btf_id_kind { + BTF_ID_KIND_NONE, + BTF_ID_KIND_SYM, + BTF_ID_KIND_SET, + BTF_ID_KIND_SET8 +}; + struct btf_id { struct rb_node rb_node; char *name; @@ -105,17 +114,19 @@ struct btf_id { int id; int cnt; }; - int addr_cnt; - bool is_set; - bool is_set8; + enum btf_id_kind kind:8; + int addr_cnt:8; Elf64_Addr addr[ADDR_CNT]; }; struct object { const char *path; - const char *btf; + const char *btf_path; const char *base_btf_path; + struct btf *btf; + struct btf *base_btf; + struct { int fd; Elf *elf; @@ -257,26 +268,33 @@ static char *get_id(const char *prefix_end) return id; } -static struct btf_id *add_set(struct object *obj, char *name, bool is_set8) +static struct btf_id *add_set(struct object *obj, char *name, enum btf_id_kind kind) { /* * __BTF_ID__set__name * name = ^ * id = ^ */ - char *id = name + (is_set8 ? sizeof(BTF_SET8 "__") : sizeof(BTF_SET "__")) - 1; + int prefixlen = kind == BTF_ID_KIND_SET8 ? sizeof(BTF_SET8 "__") : sizeof(BTF_SET "__"); + char *id = name + prefixlen - 1; int len = strlen(name); + struct btf_id *btf_id; if (id >= name + len) { pr_err("FAILED to parse set name: %s\n", name); return NULL; } - return btf_id__add(&obj->sets, id, true); + btf_id = btf_id__add(&obj->sets, id, true); + if (btf_id) + btf_id->kind = kind; + + return btf_id; } static struct btf_id *add_symbol(struct rb_root *root, char *name, size_t size) { + struct btf_id *btf_id; char *id; id = get_id(name + size); @@ -285,7 +303,10 @@ static struct btf_id *add_symbol(struct rb_root *root, char *name, size_t size) return NULL; } - return btf_id__add(root, id, false); + btf_id = btf_id__add(root, id, false); + btf_id->kind = BTF_ID_KIND_SYM; + + return btf_id; } /* Older libelf.h and glibc elf.h might not yet define the ELF compression types. */ @@ -410,14 +431,6 @@ static int elf_collect(struct object *obj) obj->efile.idlist = data; obj->efile.idlist_shndx = idx; obj->efile.idlist_addr = sh.sh_addr; - } else if (!strcmp(name, BTF_BASE_ELF_SEC)) { - /* If a .BTF.base section is found, do not resolve - * BTF ids relative to vmlinux; resolve relative - * to the .BTF.base section instead. btf__parse_split() - * will take care of this once the base BTF it is - * passed is NULL. - */ - obj->base_btf_path = NULL; } if (compressed_section_fix(elf, scn, &sh)) @@ -488,28 +501,24 @@ static int symbols_collect(struct object *obj) id = add_symbol(&obj->funcs, prefix, sizeof(BTF_FUNC) - 1); /* set8 */ } else if (!strncmp(prefix, BTF_SET8, sizeof(BTF_SET8) - 1)) { - id = add_set(obj, prefix, true); + id = add_set(obj, prefix, BTF_ID_KIND_SET8); /* * SET8 objects store list's count, which is encoded * in symbol's size, together with 'cnt' field hence * that - 1. */ - if (id) { + if (id) id->cnt = sym.st_size / sizeof(uint64_t) - 1; - id->is_set8 = true; - } /* set */ } else if (!strncmp(prefix, BTF_SET, sizeof(BTF_SET) - 1)) { - id = add_set(obj, prefix, false); + id = add_set(obj, prefix, BTF_ID_KIND_SET); /* * SET objects store list's count, which is encoded * in symbol's size, together with 'cnt' field hence * that - 1. */ - if (id) { + if (id) id->cnt = sym.st_size / sizeof(int) - 1; - id->is_set = true; - } } else { pr_err("FAILED unsupported prefix %s\n", prefix); return -1; @@ -529,16 +538,10 @@ static int symbols_collect(struct object *obj) return 0; } -static int symbols_resolve(struct object *obj) +static int load_btf(struct object *obj) { - int nr_typedefs = obj->nr_typedefs; - int nr_structs = obj->nr_structs; - int nr_unions = obj->nr_unions; - int nr_funcs = obj->nr_funcs; - struct btf *base_btf = NULL; - int err, type_id; - struct btf *btf; - __u32 nr_types; + struct btf *base_btf = NULL, *btf = NULL; + int err; if (obj->base_btf_path) { base_btf = btf__parse(obj->base_btf_path, NULL); @@ -546,18 +549,52 @@ static int symbols_resolve(struct object *obj) if (err) { pr_err("FAILED: load base BTF from %s: %s\n", obj->base_btf_path, strerror(-err)); - return -1; + goto out_err; } } - btf = btf__parse_split(obj->btf ?: obj->path, base_btf); + btf = btf__parse_split(obj->btf_path ?: obj->path, base_btf); err = libbpf_get_error(btf); if (err) { pr_err("FAILED: load BTF from %s: %s\n", - obj->btf ?: obj->path, strerror(-err)); - goto out; + obj->btf_path ?: obj->path, strerror(-err)); + goto out_err; + } + + obj->base_btf = base_btf; + obj->btf = btf; + + if (obj->base_btf) { + err = btf__distill_base(obj->btf, &base_btf, &btf); + if (err) { + pr_err("FAILED to distill base BTF: %s\n", strerror(errno)); + goto out_err; + } + + btf__free(obj->btf); + btf__free(obj->base_btf); + obj->btf = btf; + obj->base_btf = base_btf; } + return 0; + +out_err: + btf__free(base_btf); + btf__free(btf); + return err; +} + +static int symbols_resolve(struct object *obj) +{ + int nr_typedefs = obj->nr_typedefs; + int nr_structs = obj->nr_structs; + int nr_unions = obj->nr_unions; + int nr_funcs = obj->nr_funcs; + struct btf *btf = obj->btf; + int err, type_id; + __u32 nr_types; + err = -1; nr_types = btf__type_cnt(btf); @@ -615,8 +652,6 @@ static int symbols_resolve(struct object *obj) err = 0; out: - btf__free(base_btf); - btf__free(btf); return err; } @@ -627,7 +662,7 @@ static int id_patch(struct object *obj, struct btf_id *id) int i; /* For set, set8, id->id may be 0 */ - if (!id->id && !id->is_set && !id->is_set8) { + if (!id->id && id->kind == BTF_ID_KIND_SYM) { pr_err("WARN: resolve_btfids: unresolved symbol %s\n", id->name); warnings++; } @@ -680,6 +715,7 @@ static int sets_patch(struct object *obj) { Elf_Data *data = obj->efile.idlist; struct rb_node *next; + int cnt; next = rb_first(&obj->sets); while (next) { @@ -699,11 +735,15 @@ static int sets_patch(struct object *obj) return -1; } - if (id->is_set) { + switch (id->kind) { + case BTF_ID_KIND_SET: set = data->d_buf + off; + cnt = set->cnt; qsort(set->ids, set->cnt, sizeof(set->ids[0]), cmp_id); - } else { + break; + case BTF_ID_KIND_SET8: set8 = data->d_buf + off; + cnt = set8->cnt; /* * Make sure id is at the beginning of the pairs * struct, otherwise the below qsort would not work. @@ -728,10 +768,14 @@ static int sets_patch(struct object *obj) bswap_32(set8->pairs[i].flags); } } + break; + case BTF_ID_KIND_SYM: + default: + pr_err("Unexpected btf_id_kind %d for set '%s'\n", id->kind, id->name); + return -1; } - pr_debug("sorting addr %5lu: cnt %6d [%s]\n", - off, id->is_set ? set->cnt : set8->cnt, id->name); + pr_debug("sorting addr %5lu: cnt %6d [%s]\n", off, cnt, id->name); next = rb_next(next); } @@ -740,8 +784,6 @@ static int sets_patch(struct object *obj) static int symbols_patch(struct object *obj) { - off_t err; - if (__symbols_patch(obj, &obj->structs) || __symbols_patch(obj, &obj->unions) || __symbols_patch(obj, &obj->typedefs) || @@ -752,20 +794,67 @@ static int symbols_patch(struct object *obj) if (sets_patch(obj)) return -1; - /* Set type to ensure endian translation occurs. */ - obj->efile.idlist->d_type = ELF_T_WORD; + return 0; +} - elf_flagdata(obj->efile.idlist, ELF_C_SET, ELF_F_DIRTY); +static int dump_raw_data(const char *out_path, const void *data, u32 size) +{ + int fd, ret; - err = elf_update(obj->efile.elf, ELF_C_WRITE); - if (err < 0) { - pr_err("FAILED elf_update(WRITE): %s\n", - elf_errmsg(-1)); + fd = open(out_path, O_WRONLY | O_CREAT | O_TRUNC, 0640); + if (fd < 0) { + pr_err("Couldn't open %s for writing\n", out_path); + return fd; + } + + ret = write(fd, data, size); + if (ret < 0 || ret != size) { + pr_err("Failed to write data to %s\n", out_path); + close(fd); + unlink(out_path); + return -1; + } + + close(fd); + pr_debug("Dumped %lu bytes of data to %s\n", size, out_path); + + return 0; +} + +static int dump_raw_btf_ids(struct object *obj, const char *out_path) +{ + Elf_Data *data = obj->efile.idlist; + int fd, err; + + if (!data || !data->d_buf) { + pr_debug("%s has no BTF_ids data to dump\n", obj->path); + return 0; + } + + err = dump_raw_data(out_path, data->d_buf, data->d_size); + if (err) + return -1; + + return 0; +} + +static int dump_raw_btf(struct btf *btf, const char *out_path) +{ + const void *raw_btf_data; + u32 raw_btf_size; + int fd, err; + + raw_btf_data = btf__raw_data(btf, &raw_btf_size); + if (raw_btf_data == NULL) { + pr_err("btf__raw_data() failed\n"); + return -1; } - pr_debug("update %s for %s\n", - err >= 0 ? "ok" : "failed", obj->path); - return err < 0 ? -1 : 0; + err = dump_raw_data(out_path, raw_btf_data, raw_btf_size); + if (err) + return -1; + + return 0; } static const char * const resolve_btfids_usage[] = { @@ -786,12 +875,13 @@ int main(int argc, const char **argv) .funcs = RB_ROOT, .sets = RB_ROOT, }; + char out_path[PATH_MAX]; bool fatal_warnings = false; struct option btfid_options[] = { OPT_INCR('v', "verbose", &verbose, "be more verbose (show errors, etc)"), - OPT_STRING(0, "btf", &obj.btf, "BTF data", - "BTF data"), + OPT_STRING(0, "btf", &obj.btf_path, "BTF data", + "input BTF data"), OPT_STRING('b', "btf_base", &obj.base_btf_path, "file", "path of file providing base BTF"), OPT_BOOLEAN(0, "fatal_warnings", &fatal_warnings, @@ -807,6 +897,9 @@ int main(int argc, const char **argv) obj.path = argv[0]; + if (load_btf(&obj)) + goto out; + if (elf_collect(&obj)) goto out; @@ -816,9 +909,8 @@ int main(int argc, const char **argv) */ if (obj.efile.idlist_shndx == -1 || obj.efile.symbols_shndx == -1) { - pr_debug("Cannot find .BTF_ids or symbols sections, nothing to do\n"); - err = 0; - goto out; + pr_debug("Cannot find .BTF_ids or symbols sections, skip symbols resolution\n"); + goto dump_btf; } if (symbols_collect(&obj)) @@ -830,9 +922,29 @@ int main(int argc, const char **argv) if (symbols_patch(&obj)) goto out; + strcpy(out_path, obj.path); + strcat(out_path, ".btf_ids"); + if (dump_raw_btf_ids(&obj, out_path)) + goto out; + +dump_btf: + strcpy(out_path, obj.path); + strcat(out_path, ".btf"); + if (dump_raw_btf(obj.btf, out_path)) + goto out; + + if (obj.base_btf) { + strcpy(out_path, obj.path); + strcat(out_path, ".distilled_base.btf"); + if (dump_raw_btf(obj.base_btf, out_path)) + goto out; + } + if (!(fatal_warnings && warnings)) err = 0; out: + btf__free(obj.base_btf); + btf__free(obj.btf); if (obj.efile.elf) { elf_end(obj.efile.elf); close(obj.efile.fd);