[PATCH 10/12] libbpf: Embed and verify the metadata hash in the loader

[Alexei Starovoitov]

On Fri, Jun 6, 2025 at 4:29 PM KP Singh <kpsingh at kernel.org> wrote:
>
> To fulfill the BPF signing contract, represented as Sig(I_loader ||
> H_meta), the generated trusted loader program must verify the integrity
> of the metadata. This signature cryptographically binds the loader's
> instructions (I_loader) to a hash of the metadata (H_meta).
>
> The verification process is embedded directly into the loader program.
> Upon execution, the loader loads the runtime hash from struct bpf_map
> i.e. BPF_PSEUDO_MAP_IDX and compares this runtime hash against an
> expected hash value that has been hardcoded directly by
> bpf_obj__gen_loader.
>
> The load from bpf_map can be improved by calling
> BPF_OBJ_GET_INFO_BY_FD from the kernel context after BPF_OBJ_GET_INFO_BY_FD
> has been updated for being called from the kernel context.
>
> The following instructions are generated:
>
>     ld_imm64 r1, const_ptr_to_map // insn[0].src_reg == BPF_PSEUDO_MAP_IDX
>     r2 = *(u64 *)(r1 + 0);
>     ld_imm64 r3, sha256_of_map_part1 // constant precomputed by
> bpftool (part of H_meta)
>     if r2 != r3 goto out;
>
>     r2 = *(u64 *)(r1 + 8);
>     ld_imm64 r3, sha256_of_map_part2 // (part of H_meta)
>     if r2 != r3 goto out;
>
>     r2 = *(u64 *)(r1 + 16);
>     ld_imm64 r3, sha256_of_map_part3 // (part of H_meta)
>     if r2 != r3 goto out;
>
>     r2 = *(u64 *)(r1 + 24);
>     ld_imm64 r3, sha256_of_map_part4 // (part of H_meta)
>     if r2 != r3 goto out;
>     ...
>
> Signed-off-by: KP Singh <kpsingh at kernel.org>
> ---
>  tools/lib/bpf/bpf_gen_internal.h |  2 ++
>  tools/lib/bpf/gen_loader.c       | 52 ++++++++++++++++++++++++++++++++
>  tools/lib/bpf/libbpf.h           |  3 +-
>  3 files changed, 56 insertions(+), 1 deletion(-)
>
> diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h
> index 6ff963a491d9..49af4260b8e6 100644
> --- a/tools/lib/bpf/bpf_gen_internal.h
> +++ b/tools/lib/bpf/bpf_gen_internal.h
> @@ -4,6 +4,7 @@
>  #define __BPF_GEN_INTERNAL_H
>
>  #include "bpf.h"
> +#include "libbpf_internal.h"
>
>  struct ksym_relo_desc {
>         const char *name;
> @@ -50,6 +51,7 @@ struct bpf_gen {
>         __u32 nr_ksyms;
>         int fd_array;
>         int nr_fd_array;
> +       int hash_insn_offset[SHA256_DWORD_SIZE];
>  };
>
>  void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps);
> diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
> index 113ae4abd345..3d672c09e948 100644
> --- a/tools/lib/bpf/gen_loader.c
> +++ b/tools/lib/bpf/gen_loader.c
> @@ -110,6 +110,7 @@ static void emit2(struct bpf_gen *gen, struct bpf_insn insn1, struct bpf_insn in
>
>  static int add_data(struct bpf_gen *gen, const void *data, __u32 size);
>  static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off);
> +static void bpf_gen__signature_match(struct bpf_gen *gen);
>
>  void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps)
>  {
> @@ -152,6 +153,8 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps
>         /* R7 contains the error code from sys_bpf. Copy it into R0 and exit. */
>         emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_7));
>         emit(gen, BPF_EXIT_INSN());
> +       if (gen->opts->gen_hash)
> +               bpf_gen__signature_match(gen);
>  }
>
>  static int add_data(struct bpf_gen *gen, const void *data, __u32 size)
> @@ -368,6 +371,25 @@ static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off)
>         __emit_sys_close(gen);
>  }
>
> +static int compute_sha_udpate_offsets(struct bpf_gen *gen)
> +{
> +       __u64 sha[SHA256_DWORD_SIZE];
> +       int i, err;
> +
> +       err = libbpf_sha256(gen->data_start, gen->data_cur - gen->data_start, sha);
> +       if (err < 0) {
> +               pr_warn("sha256 computation of the metadata failed");
> +               return err;
> +       }
> +       for (i = 0; i < SHA256_DWORD_SIZE; i++) {
> +               struct bpf_insn *insn =
> +                       (struct bpf_insn *)(gen->insn_start + gen->hash_insn_offset[i]);

Is there a reason to use offset instead of pointers?
Instead of
int hash_insn_offset[SHA256_DWORD_SIZE];
it could be
struct bpf_insn *hash_insn[SHA256_DWORD_SIZE];

> +               insn[0].imm = (__u32)sha[i];
> +               insn[1].imm = sha[i] >> 32;

Then above will be gen->hash_insn[i][0].imm ?

> +       }
> +       return 0;
> +}
> +
>  int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps)
>  {
>         int i;
> @@ -394,6 +416,12 @@ int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps)
>                               blob_fd_array_off(gen, i));
>         emit(gen, BPF_MOV64_IMM(BPF_REG_0, 0));
>         emit(gen, BPF_EXIT_INSN());
> +       if (gen->opts->gen_hash) {
> +               gen->error = compute_sha_udpate_offsets(gen);
> +               if (gen->error)
> +                       return gen->error;
> +       }
> +
>         pr_debug("gen: finish %s\n", errstr(gen->error));
>         if (!gen->error) {
>                 struct gen_loader_opts *opts = gen->opts;
> @@ -557,6 +585,30 @@ void bpf_gen__map_create(struct bpf_gen *gen,
>                 emit_sys_close_stack(gen, stack_off(inner_map_fd));
>  }
>
> +static void bpf_gen__signature_match(struct bpf_gen *gen)
> +{
> +       __s64 off = -(gen->insn_cur - gen->insn_start - gen->cleanup_label) / 8 - 1;
> +       int i;
> +
> +       for (i = 0; i < SHA256_DWORD_SIZE; i++) {
> +               emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX,
> +                                                0, 0, 0, 0));
> +               emit(gen, BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, i * sizeof(__u64)));
> +               gen->hash_insn_offset[i] = gen->insn_cur - gen->insn_start;

and this will be
gen->hash_insn[i] = gen->insn_cur;