bpf: fix x64 JIT code generation for jmp to 1st insn

Introduction of bounded loops exposed old bug in x64 JIT.
JIT maintains the array of offsets to the end of all instructions to
compute jmp offsets.
addrs[0] - offset of the end of the 1st insn (that includes prologue).
addrs[1] - offset of the end of the 2nd insn.
JIT didn't keep the offset of the beginning of the 1st insn,
since classic BPF didn't have backward jumps and valid extended BPF
couldn't have a branch to 1st insn, because it didn't allow loops.
With bounded loops it's possible to construct a valid program that
jumps backwards to the 1st insn.
Fix JIT by computing:
addrs[0] - offset of the end of prologue == start of the 1st insn.
addrs[1] - offset of the end of 1st insn.

v1->v2:
- Yonghong noticed a bug in jit linfo.
  Fix it by passing 'addrs + 1' to bpf_prog_fill_jited_linfo(),
  since it expects insn_to_jit_off array to be offsets to last byte.

Reported-by: syzbot+35101610ff3e83119b1b@syzkaller.appspotmail.com
Fixes: 2589726d ("bpf: introduce bounded loops")
Fixes: 0a14842f ("net: filter: Just In Time compiler for x86-64")
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>
Acked-by: NSong Liu <songliubraving@fb.com>

arch/x86/net/bpf_jit_comp.c

@@ -390,8 +390,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 
 	emit_prologue(&prog, bpf_prog->aux->stack_depth,
 		      bpf_prog_was_classic(bpf_prog));
+	addrs[0] = prog - temp;
 
-	for (i = 0; i < insn_cnt; i++, insn++) {
+	for (i = 1; i <= insn_cnt; i++, insn++) {
 		const s32 imm32 = insn->imm;
 		u32 dst_reg = insn->dst_reg;
 		u32 src_reg = insn->src_reg;
@@ -1105,7 +1106,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		extra_pass = true;
 		goto skip_init_addrs;
 	}
-	addrs = kmalloc_array(prog->len, sizeof(*addrs), GFP_KERNEL);
+	addrs = kmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL);
 	if (!addrs) {
 		prog = orig_prog;
 		goto out_addrs;
@@ -1115,7 +1116,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	 * Before first pass, make a rough estimation of addrs[]
 	 * each BPF instruction is translated to less than 64 bytes
 	 */
-	for (proglen = 0, i = 0; i < prog->len; i++) {
+	for (proglen = 0, i = 0; i <= prog->len; i++) {
 		proglen += 64;
 		addrs[i] = proglen;
 	}
@@ -1180,7 +1181,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	if (!image || !prog->is_func || extra_pass) {
 		if (image)
-			bpf_prog_fill_jited_linfo(prog, addrs);
+			bpf_prog_fill_jited_linfo(prog, addrs + 1);
 out_addrs:
 		kfree(addrs);
 		kfree(jit_data);