From 40df54cf0232a78147d63f632dcc5ce22e71878e Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 12 Aug 2019 11:39:47 -0700 Subject: [PATCH] BACKPORT: btf: expose BTF info through sysfs Make .BTF section allocated and expose its contents through sysfs. /sys/kernel/btf directory is created to contain all the BTFs present inside kernel. Currently there is only kernel's main BTF, represented as /sys/kernel/btf/kernel file. Once kernel modules' BTFs are supported, each module will expose its BTF as /sys/kernel/btf/ file. Current approach relies on a few pieces coming together: 1. pahole is used to take almost final vmlinux image (modulo .BTF and kallsyms) and generate .BTF section by converting DWARF info into BTF. This section is not allocated and not mapped to any segment, though, so is not yet accessible from inside kernel at runtime. 2. objcopy dumps .BTF contents into binary file and subsequently convert binary file into linkable object file with automatically generated symbols _binary__btf_kernel_bin_start and _binary__btf_kernel_bin_end, pointing to start and end, respectively, of BTF raw data. 3. final vmlinux image is generated by linking this object file (and kallsyms, if necessary). sysfs_btf.c then creates /sys/kernel/btf/kernel file and exposes embedded BTF contents through it. This allows, e.g., libbpf and bpftool access BTF info at well-known location, without resorting to searching for vmlinux image on disk (location of which is not standardized and vmlinux image might not be even available in some scenarios, e.g., inside qemu during testing). Alternative approach using .incbin assembler directive to embed BTF contents directly was attempted but didn't work, because sysfs_proc.o is not re-compiled during link-vmlinux.sh stage. This is required, though, to update embedded BTF data (initially empty data is embedded, then pahole generates BTF info and we need to regenerate sysfs_btf.o with updated contents, but it's too late at that point). If BTF couldn't be generated due to missing or too old pahole, sysfs_btf.c handles that gracefully by detecting that _binary__btf_kernel_bin_start (weak symbol) is 0 and not creating /sys/kernel/btf at all. v2->v3: - added Documentation/ABI/testing/sysfs-kernel-btf (Greg K-H); - created proper kobject (btf_kobj) for btf directory (Greg K-H); - undo v2 change of reusing vmlinux, as it causes extra kallsyms pass due to initially missing __binary__btf_kernel_bin_{start/end} symbols; v1->v2: - allow kallsyms stage to re-use vmlinux generated by gen_btf(); Reviewed-by: Greg Kroah-Hartman Change-Id: Ife57356dd14b9ae0d2e3801eea7c602c6245952f Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Signed-off-by: Sorayukii --- Documentation/ABI/testing/sysfs-kernel-btf | 17 +++++++ kernel/bpf/Makefile | 3 ++ kernel/bpf/sysfs_btf.c | 51 ++++++++++++++++++++ scripts/link-vmlinux.sh | 55 ++++++++++++++-------- 4 files changed, 106 insertions(+), 20 deletions(-) create mode 100644 Documentation/ABI/testing/sysfs-kernel-btf create mode 100644 kernel/bpf/sysfs_btf.c diff --git a/Documentation/ABI/testing/sysfs-kernel-btf b/Documentation/ABI/testing/sysfs-kernel-btf new file mode 100644 index 000000000000..5390f8001f96 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-btf @@ -0,0 +1,17 @@ +What: /sys/kernel/btf +Date: Aug 2019 +KernelVersion: 5.5 +Contact: bpf@vger.kernel.org +Description: + Contains BTF type information and related data for kernel and + kernel modules. + +What: /sys/kernel/btf/kernel +Date: Aug 2019 +KernelVersion: 5.5 +Contact: bpf@vger.kernel.org +Description: + Read-only binary attribute exposing kernel's own BTF type + information with description of all internal kernel types. See + Documentation/bpf/btf.rst for detailed description of format + itself. diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 05e1bf69ece1..a461583367aa 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -21,3 +21,6 @@ obj-$(CONFIG_CGROUP_BPF) += cgroup.o ifeq ($(CONFIG_INET),y) obj-$(CONFIG_BPF_SYSCALL) += reuseport_array.o endif +ifeq ($(CONFIG_SYSFS),y) +obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o +endif diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c new file mode 100644 index 000000000000..092e63b9758b --- /dev/null +++ b/kernel/bpf/sysfs_btf.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Provide kernel BTF information for introspection and use by eBPF tools. + */ +#include +#include +#include +#include +#include + +/* See scripts/link-vmlinux.sh, gen_btf() func for details */ +extern char __weak _binary__btf_kernel_bin_start[]; +extern char __weak _binary__btf_kernel_bin_end[]; + +static ssize_t +btf_kernel_read(struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buf, loff_t off, size_t len) +{ + memcpy(buf, _binary__btf_kernel_bin_start + off, len); + return len; +} + +static struct bin_attribute bin_attr_btf_kernel __ro_after_init = { + .attr = { .name = "kernel", .mode = 0444, }, + .read = btf_kernel_read, +}; + +static struct kobject *btf_kobj; + +static int __init btf_kernel_init(void) +{ + int err; + + if (!_binary__btf_kernel_bin_start) + return 0; + + btf_kobj = kobject_create_and_add("btf", kernel_kobj); + if (IS_ERR(btf_kobj)) { + err = PTR_ERR(btf_kobj); + btf_kobj = NULL; + return err; + } + + bin_attr_btf_kernel.size = _binary__btf_kernel_bin_end - + _binary__btf_kernel_bin_start; + + return sysfs_create_bin_file(btf_kobj, &bin_attr_btf_kernel); +} + +subsys_initcall(btf_kernel_init); diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index d7d8fce43eec..5ea28071844d 100644 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -127,8 +127,8 @@ recordmcount() } # Link of vmlinux -# ${1} - optional extra .o files -# ${2} - output file +# ${1} - output file +# ${@:2} - optional extra .o files vmlinux_link() { local lds="${objtree}/${KBUILD_LDS}" @@ -144,28 +144,28 @@ vmlinux_link() fi if [[ -n "${CONFIG_THIN_ARCHIVES}" && -z "${CONFIG_LTO_CLANG}" ]]; then - objects="--whole-archive built-in.o ${1}" + objects="--whole-archive built-in.o ${@:2}" else objects="${KBUILD_VMLINUX_INIT} \ --start-group \ ${KBUILD_VMLINUX_MAIN} \ --end-group \ - ${1}" + ${@:2}" fi - ${ld} ${ldflags} -o ${2} -T ${lds} ${objects} + ${ld} ${ldflags} -o ${1} -T ${lds} ${objects} else if [ -n "${CONFIG_THIN_ARCHIVES}" ]; then - objects="-Wl,--whole-archive built-in.o ${1}" + objects="-Wl,--whole-archive built-in.o ${@:2}" else objects="${KBUILD_VMLINUX_INIT} \ -Wl,--start-group \ ${KBUILD_VMLINUX_MAIN} \ -Wl,--end-group \ - ${1}" + ${@:2}" fi - ${CC} ${CFLAGS_vmlinux} -o ${2} \ + ${CC} ${CFLAGS_vmlinux} -o ${1} \ -Wl,-T,${lds} \ ${objects} \ -lutil -lrt -lpthread @@ -174,23 +174,34 @@ vmlinux_link() } # generate .BTF typeinfo from DWARF debuginfo +# ${1} - vmlinux image +# ${2} - file to dump raw BTF data into gen_btf() { local pahole_ver; + local bin_arch if ! [ -x "$(command -v ${PAHOLE})" ]; then info "BTF" "${1}: pahole (${PAHOLE}) is not available" - return 0 + return 1 fi pahole_ver=$(${PAHOLE} --version | sed -E 's/v([0-9]+)\.([0-9]+)/\1\2/') if [ "${pahole_ver}" -lt "113" ]; then info "BTF" "${1}: pahole version $(${PAHOLE} --version) is too old, need at least v1.13" - return 0 + return 1 fi - info "BTF" ${1} + info "BTF" ${2} + vmlinux_link ${1} LLVM_OBJCOPY=${OBJCOPY} ${PAHOLE} -J ${1} + + # dump .BTF section into raw binary file to link with final vmlinux + bin_arch=$(${OBJDUMP} -f ${1} | grep architecture | \ + cut -d, -f1 | cut -d' ' -f2) + ${OBJCOPY} --dump-section .BTF=.btf.kernel.bin ${1} 2>/dev/null + ${OBJCOPY} -I binary -O ${CONFIG_OUTPUT_FORMAT} -B ${bin_arch} \ + --rename-section .data=.BTF .btf.kernel.bin ${2} } # Create ${2} .o file with all symbols from the ${1} object file @@ -264,6 +275,7 @@ sortextable() # Delete output files in case of error cleanup() { + rm -f .btf.* rm -f .old_version rm -f .tmp_System.map rm -f .tmp_kallsyms* @@ -356,6 +368,13 @@ if [ ! -z ${RTIC_MPGEN+x} ]; then KBUILD_VMLINUX_MAIN+=$RTIC_MP_O fi +btf_kernel_bin_o="" +if [ -n "${CONFIG_DEBUG_INFO_BTF}" ]; then + if gen_btf .tmp_vmlinux.btf .btf.kernel.bin.o ; then + btf_kernel_bin_o=.btf.kernel.bin.o + fi +fi + kallsymso="" kallsyms_vmlinux="" if [ -n "${CONFIG_KALLSYMS}" ]; then @@ -383,11 +402,11 @@ if [ -n "${CONFIG_KALLSYMS}" ]; then kallsyms_vmlinux=.tmp_vmlinux2 # step 1 - vmlinux_link "" .tmp_vmlinux1 - kallsyms .tmp_vmlinux1 .tmp_kallsyms1.o + vmlinux_link .tmp_vmlinux1 + kallsyms .tmp_vmlinux1 .tmp_kallsyms1.o ${btf_kernel_bin_o} # step 2 - vmlinux_link .tmp_kallsyms1.o .tmp_vmlinux2 + vmlinux_link .tmp_vmlinux2 .tmp_kallsyms1.o ${btf_kernel_bin_o} kallsyms .tmp_vmlinux2 .tmp_kallsyms2.o # step 2a @@ -395,7 +414,7 @@ if [ -n "${CONFIG_KALLSYMS}" ]; then kallsymso=.tmp_kallsyms3.o kallsyms_vmlinux=.tmp_vmlinux3 - vmlinux_link .tmp_kallsyms2.o .tmp_vmlinux3 + vmlinux_link .tmp_vmlinux2 .tmp_kallsyms1.o ${btf_kernel_bin_o} kallsyms .tmp_vmlinux3 .tmp_kallsyms3.o fi @@ -418,11 +437,7 @@ if [ ! -z ${RTIC_MP_O} ]; then fi info LD vmlinux -vmlinux_link "${kallsymso}" vmlinux - -if [ -n "${CONFIG_DEBUG_INFO_BTF}" ]; then - gen_btf vmlinux -fi +vmlinux_link vmlinux "${kallsymso}" "${btf_kernel_bin_o}" if [ -n "${CONFIG_BUILDTIME_EXTABLE_SORT}" ]; then info SORTEX vmlinux