bpf: Compare BTF types of functions arguments with actual types

Make the verifier check that BTF types of function arguments match actual types
passed into top-level BPF program and into BPF-to-BPF calls. If types match
such BPF programs and sub-programs will have full support of BPF trampoline. If
types mismatch the trampoline has to be conservative. It has to save/restore
five program arguments and assume 64-bit scalars.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-17-ast@kernel.org

include/linux/bpf.h

@@ -480,6 +480,10 @@ static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog)
 static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {}
 #endif
 
+struct bpf_func_info_aux {
+	bool unreliable;
+};
+
 struct bpf_prog_aux {
 	atomic_t refcnt;
 	u32 used_map_cnt;
@@ -494,6 +498,7 @@ struct bpf_prog_aux {
 	bool verifier_zext; /* Zero extensions has been inserted by verifier. */
 	bool offload_requested;
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
+	bool func_proto_unreliable;
 	enum bpf_tramp_prog_type trampoline_prog_type;
 	struct bpf_trampoline *trampoline;
 	struct hlist_node tramp_hlist;
@@ -518,6 +523,7 @@ struct bpf_prog_aux {
 	struct bpf_prog_offload *offload;
 	struct btf *btf;
 	struct bpf_func_info *func_info;
+	struct bpf_func_info_aux *func_info_aux;
 	/* bpf_line_info loaded from userspace.  linfo->insn_off
 	 * has the xlated insn offset.
 	 * Both the main and sub prog share the same linfo.
@@ -890,6 +896,8 @@ int btf_distill_func_proto(struct bpf_verifier_log *log,
 			   const char *func_name,
 			   struct btf_func_model *m);
 
+int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog);
+
 #else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 {

include/linux/bpf_verifier.h

@@ -343,6 +343,7 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
 #define BPF_MAX_SUBPROGS 256
 
 struct bpf_subprog_info {
+	/* 'start' has to be the first field otherwise find_subprog() won't work */
 	u32 start; /* insn idx of function entry point */
 	u32 linfo_idx; /* The idx to the main_prog->aux->linfo */
 	u16 stack_depth; /* max. stack depth used by this function */

kernel/bpf/btf.c

@@ -3985,6 +3985,88 @@ int btf_distill_func_proto(struct bpf_verifier_log *log,
 	return 0;
 }
 
+int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog)
+{
+	struct bpf_verifier_state *st = env->cur_state;
+	struct bpf_func_state *func = st->frame[st->curframe];
+	struct bpf_reg_state *reg = func->regs;
+	struct bpf_verifier_log *log = &env->log;
+	struct bpf_prog *prog = env->prog;
+	struct btf *btf = prog->aux->btf;
+	const struct btf_param *args;
+	const struct btf_type *t;
+	u32 i, nargs, btf_id;
+	const char *tname;
+
+	if (!prog->aux->func_info)
+		return 0;
+
+	btf_id = prog->aux->func_info[subprog].type_id;
+	if (!btf_id)
+		return 0;
+
+	if (prog->aux->func_info_aux[subprog].unreliable)
+		return 0;
+
+	t = btf_type_by_id(btf, btf_id);
+	if (!t || !btf_type_is_func(t)) {
+		bpf_log(log, "BTF of subprog %d doesn't point to KIND_FUNC\n",
+			subprog);
+		return -EINVAL;
+	}
+	tname = btf_name_by_offset(btf, t->name_off);
+
+	t = btf_type_by_id(btf, t->type);
+	if (!t || !btf_type_is_func_proto(t)) {
+		bpf_log(log, "Invalid type of func %s\n", tname);
+		return -EINVAL;
+	}
+	args = (const struct btf_param *)(t + 1);
+	nargs = btf_type_vlen(t);
+	if (nargs > 5) {
+		bpf_log(log, "Function %s has %d > 5 args\n", tname, nargs);
+		goto out;
+	}
+	/* check that BTF function arguments match actual types that the
+	 * verifier sees.
+	 */
+	for (i = 0; i < nargs; i++) {
+		t = btf_type_by_id(btf, args[i].type);
+		while (btf_type_is_modifier(t))
+			t = btf_type_by_id(btf, t->type);
+		if (btf_type_is_int(t) || btf_type_is_enum(t)) {
+			if (reg[i + 1].type == SCALAR_VALUE)
+				continue;
+			bpf_log(log, "R%d is not a scalar\n", i + 1);
+			goto out;
+		}
+		if (btf_type_is_ptr(t)) {
+			if (reg[i + 1].type == SCALAR_VALUE) {
+				bpf_log(log, "R%d is not a pointer\n", i + 1);
+				goto out;
+			}
+			/* If program is passing PTR_TO_CTX into subprogram
+			 * check that BTF type matches.
+			 */
+			if (reg[i + 1].type == PTR_TO_CTX &&
+			    !btf_get_prog_ctx_type(log, btf, t, prog->type))
+				goto out;
+			/* All other pointers are ok */
+			continue;
+		}
+		bpf_log(log, "Unrecognized argument type %s\n",
+			btf_kind_str[BTF_INFO_KIND(t->info)]);
+		goto out;
+	}
+	return 0;
+out:
+	/* LLVM optimizations can remove arguments from static functions. */
+	bpf_log(log,
+		"Type info disagrees with actual arguments due to compiler optimizations\n");
+	prog->aux->func_info_aux[subprog].unreliable = true;
+	return 0;
+}
+
 void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m)
 {

kernel/bpf/syscall.c

@@ -1328,6 +1328,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
 	struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);
 
 	kvfree(aux->func_info);
+	kfree(aux->func_info_aux);
 	free_used_maps(aux);
 	bpf_prog_uncharge_memlock(aux->prog);
 	security_bpf_prog_free(aux);

kernel/bpf/verifier.c

@@ -3970,6 +3970,9 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 	/* only increment it after check_reg_arg() finished */
 	state->curframe++;
 
+	if (btf_check_func_arg_match(env, subprog))
+		return -EINVAL;
+
 	/* and go analyze first insn of the callee */
 	*insn_idx = target_insn;
 
@@ -6564,6 +6567,7 @@ static int check_btf_func(struct bpf_verifier_env *env,
 	u32 i, nfuncs, urec_size, min_size;
 	u32 krec_size = sizeof(struct bpf_func_info);
 	struct bpf_func_info *krecord;
+	struct bpf_func_info_aux *info_aux = NULL;
 	const struct btf_type *type;
 	struct bpf_prog *prog;
 	const struct btf *btf;
@@ -6597,6 +6601,9 @@ static int check_btf_func(struct bpf_verifier_env *env,
 	krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN);
 	if (!krecord)
 		return -ENOMEM;
+	info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL | __GFP_NOWARN);
+	if (!info_aux)
+		goto err_free;
 
 	for (i = 0; i < nfuncs; i++) {
 		ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size);
@@ -6648,29 +6655,31 @@ static int check_btf_func(struct bpf_verifier_env *env,
 			ret = -EINVAL;
 			goto err_free;
 		}
-
 		prev_offset = krecord[i].insn_off;
 		urecord += urec_size;
 	}
 
 	prog->aux->func_info = krecord;
 	prog->aux->func_info_cnt = nfuncs;
+	prog->aux->func_info_aux = info_aux;
 	return 0;
 
 err_free:
 	kvfree(krecord);
+	kfree(info_aux);
 	return ret;
 }
 
 static void adjust_btf_func(struct bpf_verifier_env *env)
 {
+	struct bpf_prog_aux *aux = env->prog->aux;
 	int i;
 
-	if (!env->prog->aux->func_info)
+	if (!aux->func_info)
 		return;
 
 	for (i = 0; i < env->subprog_cnt; i++)
-		env->prog->aux->func_info[i].insn_off = env->subprog_info[i].start;
+		aux->func_info[i].insn_off = env->subprog_info[i].start;
 }
 
 #define MIN_BPF_LINEINFO_SIZE	(offsetof(struct bpf_line_info, line_col) + \
@@ -7651,6 +7660,9 @@ static int do_check(struct bpf_verifier_env *env)
 			0 /* frameno */,
 			0 /* subprogno, zero == main subprog */);
 
+	if (btf_check_func_arg_match(env, 0))
+		return -EINVAL;
+
 	for (;;) {
 		struct bpf_insn *insn;
 		u8 class;