bpf: add prog_digest and expose it via fdinfo/netlink

When loading a BPF program via bpf(2), calculate the digest over
the program's instruction stream and store it in struct bpf_prog's
digest member. This is done at a point in time before any instructions
are rewritten by the verifier. Any unstable map file descriptor
number part of the imm field will be zeroed for the hash.

fdinfo example output for progs:

  # cat /proc/1590/fdinfo/5
  pos:          0
  flags:        02000002
  mnt_id:       11
  prog_type:    1
  prog_jited:   1
  prog_digest:  b27e8b06da22707513aa97363dfb11c7c3675d28
  memlock:      4096

When programs are pinned and retrieved by an ELF loader, the loader
can check the program's digest through fdinfo and compare it against
one that was generated over the ELF file's program section to see
if the program needs to be reloaded. Furthermore, this can also be
exposed through other means such as netlink in case of a tc cls/act
dump (or xdp in future), but also through tracepoints or other
facilities to identify the program. Other than that, the digest can
also serve as a base name for the work in progress kallsyms support
of programs. The digest doesn't depend/select the crypto layer, since
we need to keep dependencies to a minimum. iproute2 will get support
for this facility.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 65 insertions, 0 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 82a04143368e..bdcc9f4ba767 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -136,6 +136,71 @@ void __bpf_prog_free(struct bpf_prog *fp)
 	vfree(fp);
 }
 
+#define SHA_BPF_RAW_SIZE						\
+	round_up(MAX_BPF_SIZE + sizeof(__be64) + 1, SHA_MESSAGE_BYTES)
+
+/* Called under verifier mutex. */
+void bpf_prog_calc_digest(struct bpf_prog *fp)
+{
+	const u32 bits_offset = SHA_MESSAGE_BYTES - sizeof(__be64);
+	static u32 ws[SHA_WORKSPACE_WORDS];
+	static u8 raw[SHA_BPF_RAW_SIZE];
+	struct bpf_insn *dst = (void *)raw;
+	u32 i, bsize, psize, blocks;
+	bool was_ld_map;
+	u8 *todo = raw;
+	__be32 *result;
+	__be64 *bits;
+
+	sha_init(fp->digest);
+	memset(ws, 0, sizeof(ws));
+
+	/* We need to take out the map fd for the digest calculation
+	 * since they are unstable from user space side.
+	 */
+	for (i = 0, was_ld_map = false; i < fp->len; i++) {
+		dst[i] = fp->insnsi[i];
+		if (!was_ld_map &&
+		    dst[i].code == (BPF_LD | BPF_IMM | BPF_DW) &&
+		    dst[i].src_reg == BPF_PSEUDO_MAP_FD) {
+			was_ld_map = true;
+			dst[i].imm = 0;
+		} else if (was_ld_map &&
+			   dst[i].code == 0 &&
+			   dst[i].dst_reg == 0 &&
+			   dst[i].src_reg == 0 &&
+			   dst[i].off == 0) {
+			was_ld_map = false;
+			dst[i].imm = 0;
+		} else {
+			was_ld_map = false;
+		}
+	}
+
+	psize = fp->len * sizeof(struct bpf_insn);
+	memset(&raw[psize], 0, sizeof(raw) - psize);
+	raw[psize++] = 0x80;
+
+	bsize  = round_up(psize, SHA_MESSAGE_BYTES);
+	blocks = bsize / SHA_MESSAGE_BYTES;
+	if (bsize - psize >= sizeof(__be64)) {
+		bits = (__be64 *)(todo + bsize - sizeof(__be64));
+	} else {
+		bits = (__be64 *)(todo + bsize + bits_offset);
+		blocks++;
+	}
+	*bits = cpu_to_be64((psize - 1) << 3);
+
+	while (blocks--) {
+		sha_transform(fp->digest, todo, ws);
+		todo += SHA_MESSAGE_BYTES;
+	}
+
+	result = (__force __be32 *)fp->digest;
+	for (i = 0; i < SHA_DIGEST_WORDS; i++)
+		result[i] = cpu_to_be32(fp->digest[i]);
+}
+
 static bool bpf_is_jmp_and_has_target(const struct bpf_insn *insn)
 {
 	return BPF_CLASS(insn->code) == BPF_JMP  &&