--- /dev/null
+#!/bin/bash
+# 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 <file>] <target ELF file>"
+ 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
+
+
+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} ${RESOLVE_BTFIDS_FLAGS} \
+ ${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} ${CLANG_FLAGS} -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}.BTF"
+ ${OBJCOPY} --add-section .BTF=${ELF_FILE}.BTF ${ELF_FILE}
+
+ # a module might not have a .BTF_ids or .BTF.base section
+ local btf_base="${ELF_FILE}.BTF.base"
+ if [ -f "${btf_base}" ]; then
+ ${OBJCOPY} --add-section .BTF.base=${btf_base} ${ELF_FILE}
+ fi
+ local btf_ids="${ELF_FILE}.BTF_ids"
+ if [ -f "${btf_ids}" ]; then
+ ${OBJCOPY} --update-section .BTF_ids=${btf_ids} ${ELF_FILE}
+ fi
+}
+
+cleanup()
+{
+ rm -f "${ELF_FILE}.BTF.1"
+ rm -f "${ELF_FILE}.BTF"
+ if [ "${BTFGEN_MODE}" = "module" ]; then
+ rm -f "${ELF_FILE}.BTF.base"
+ rm -f "${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
${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()
{
fi
btf_vmlinux_bin_o=
+btfids_vmlinux=
kallsymso=
strip_debug=
generate_map=
fi
if is_enabled CONFIG_DEBUG_INFO_BTF; then
- if ! gen_btf .tmp_vmlinux1; then
+ if ! ${srctree}/scripts/gen-btf.sh .tmp_vmlinux1; then
echo >&2 "Failed to generate BTF for vmlinux"
echo >&2 "Try to disable CONFIG_DEBUG_INFO_BTF"
exit 1
fi
+ btf_vmlinux_bin_o=.tmp_vmlinux1.btf.o
+ btfids_vmlinux=.tmp_vmlinux1.BTF_ids
fi
if is_enabled CONFIG_KALLSYMS; then
vmlinux_link "${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
#include <fcntl.h>
#include <errno.h>
#include <linux/btf_ids.h>
+#include <linux/kallsyms.h>
#include <linux/rbtree.h>
#include <linux/zalloc.h>
#include <linux/err.h>
+#include <linux/limits.h>
#include <bpf/btf.h>
#include <bpf/libbpf.h>
#include <subcmd/parse-options.h>
struct btf *btf;
struct btf *base_btf;
+ bool distill_base;
struct {
int fd;
return btf_id__add(root, id, BTF_ID_KIND_SYM);
}
-/* Older libelf.h and glibc elf.h might not yet define the ELF compression types. */
-#ifndef SHF_COMPRESSED
-#define SHF_COMPRESSED (1 << 11) /* Section with compressed data. */
-#endif
-
-/*
- * The data of compressed section should be aligned to 4
- * (for 32bit) or 8 (for 64 bit) bytes. The binutils ld
- * sets sh_addralign to 1, which makes libelf fail with
- * misaligned section error during the update:
- * FAILED elf_update(WRITE): invalid section alignment
- *
- * While waiting for ld fix, we fix the compressed sections
- * sh_addralign value manualy.
- */
-static int compressed_section_fix(Elf *elf, Elf_Scn *scn, GElf_Shdr *sh)
+static void bswap_32_data(void *data, u32 nr_bytes)
{
- int expected = gelf_getclass(elf) == ELFCLASS32 ? 4 : 8;
-
- if (!(sh->sh_flags & SHF_COMPRESSED))
- return 0;
-
- if (sh->sh_addralign == expected)
- return 0;
+ u32 cnt, i;
+ u32 *ptr;
- pr_debug2(" - fixing wrong alignment sh_addralign %u, expected %u\n",
- sh->sh_addralign, expected);
+ cnt = nr_bytes / sizeof(u32);
+ ptr = data;
- sh->sh_addralign = expected;
-
- if (gelf_update_shdr(scn, sh) == 0) {
- pr_err("FAILED cannot update section header: %s\n",
- elf_errmsg(-1));
- return -1;
- }
- return 0;
+ for (i = 0; i < cnt; i++)
+ ptr[i] = bswap_32(ptr[i]);
}
static int elf_collect(struct object *obj)
elf_version(EV_CURRENT);
- elf = elf_begin(fd, ELF_C_RDWR_MMAP, NULL);
+ elf = elf_begin(fd, ELF_C_READ_MMAP_PRIVATE, NULL);
if (!elf) {
close(fd);
pr_err("FAILED cannot create ELF descriptor: %s\n",
obj->efile.symbols_shndx = idx;
obj->efile.strtabidx = sh.sh_link;
} else if (!strcmp(name, BTF_IDS_SECTION)) {
+ /*
+ * If target endianness differs from host, we need to bswap32
+ * the .BTF_ids section data on load, because .BTF_ids has
+ * Elf_Type = ELF_T_BYTE, and so libelf returns data buffer in
+ * the target endianness. We repeat this on dump.
+ */
+ if (obj->efile.encoding != ELFDATANATIVE) {
+ pr_debug("bswap_32 .BTF_ids data from target to host endianness\n");
+ bswap_32_data(data->d_buf, data->d_size);
+ }
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))
- return -1;
}
return 0;
obj->base_btf = base_btf;
obj->btf = btf;
+ if (obj->base_btf && obj->distill_base) {
+ 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->base_btf);
+ btf__free(obj->btf);
+ obj->base_btf = base_btf;
+ obj->btf = btf;
+ }
+
return 0;
out_err:
btf__free(base_btf);
btf__free(btf);
+ obj->base_btf = NULL;
+ obj->btf = NULL;
return err;
}
*/
BUILD_BUG_ON((u32 *)set8->pairs != &set8->pairs[0].id);
qsort(set8->pairs, set8->cnt, sizeof(set8->pairs[0]), cmp_id);
-
- /*
- * When ELF endianness does not match endianness of the
- * host, libelf will do the translation when updating
- * the ELF. This, however, corrupts SET8 flags which are
- * already in the target endianness. So, let's bswap
- * them to the host endianness and libelf will then
- * correctly translate everything.
- */
- if (obj->efile.encoding != ELFDATANATIVE) {
- int i;
-
- set8->flags = bswap_32(set8->flags);
- for (i = 0; i < set8->cnt; i++) {
- set8->pairs[i].flags =
- bswap_32(set8->pairs[i].flags);
- }
- }
break;
default:
pr_err("Unexpected btf_id_kind %d for set '%s'\n", id->kind, id->name);
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) ||
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)
+{
+ size_t written;
+ FILE *file;
- err = elf_update(obj->efile.elf, ELF_C_WRITE);
- if (err < 0) {
- pr_err("FAILED elf_update(WRITE): %s\n",
- elf_errmsg(-1));
+ file = fopen(out_path, "wb");
+ if (!file) {
+ pr_err("Couldn't open %s for writing\n", out_path);
+ return -1;
+ }
+
+ written = fwrite(data, 1, size, file);
+ if (written != size) {
+ pr_err("Failed to write data to %s\n", out_path);
+ fclose(file);
+ unlink(out_path);
+ return -1;
+ }
+
+ fclose(file);
+ 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 err;
+
+ if (!data || !data->d_buf) {
+ pr_debug("%s has no BTF_ids data to dump\n", obj->path);
+ return 0;
+ }
+
+ /*
+ * If target endianness differs from host, we need to bswap32 the
+ * .BTF_ids section data before dumping so that the output is in
+ * target endianness.
+ */
+ if (obj->efile.encoding != ELFDATANATIVE) {
+ pr_debug("bswap_32 .BTF_ids data from host to target endianness\n");
+ bswap_32_data(data->d_buf, data->d_size);
+ }
+
+ 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 err;
+
+ raw_btf_data = btf__raw_data(btf, &raw_btf_size);
+ if (!raw_btf_data) {
+ 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 inline int make_out_path(char *buf, u32 buf_sz, const char *in_path, const char *suffix)
+{
+ int len = snprintf(buf, buf_sz, "%s%s", in_path, suffix);
+
+ if (len < 0 || len >= buf_sz) {
+ pr_err("Output path is too long: %s%s\n", in_path, suffix);
+ return -E2BIG;
+ }
+
+ return 0;
}
static const char * const resolve_btfids_usage[] = {
.sets = RB_ROOT,
};
bool fatal_warnings = false;
+ char out_path[PATH_MAX];
+
struct option btfid_options[] = {
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show errors, etc)"),
"path of file providing base BTF"),
OPT_BOOLEAN(0, "fatal_warnings", &fatal_warnings,
"turn warnings into errors"),
+ OPT_BOOLEAN(0, "distill_base", &obj.distill_base,
+ "distill --btf_base and emit .BTF.base section data"),
OPT_END()
};
int err = -1;
obj.path = argv[0];
+ if (load_btf(&obj))
+ goto out;
+
if (elf_collect(&obj))
goto out;
*/
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))
goto out;
- if (load_btf(&obj))
- goto out;
-
if (symbols_resolve(&obj))
goto out;
if (symbols_patch(&obj))
goto out;
+ err = make_out_path(out_path, sizeof(out_path), obj.path, BTF_IDS_SECTION);
+ err = err ?: dump_raw_btf_ids(&obj, out_path);
+ if (err)
+ goto out;
+
+dump_btf:
+ err = make_out_path(out_path, sizeof(out_path), obj.path, BTF_ELF_SEC);
+ err = err ?: dump_raw_btf(obj.btf, out_path);
+ if (err)
+ goto out;
+
+ if (obj.base_btf && obj.distill_base) {
+ err = make_out_path(out_path, sizeof(out_path), obj.path, BTF_BASE_ELF_SEC);
+ err = err ?: dump_raw_btf(obj.base_btf, out_path);
+ if (err)
+ goto out;
+ }
+
if (!(fatal_warnings && warnings))
err = 0;
out:
projects / thirdparty / linux.git / commitdiff
