bpf: Check types of arguments passed into helpers

Introduce new helper that reuses existing skb perf_event output
implementation, but can be called from raw_tracepoint programs
that receive 'struct sk_buff *' as tracepoint argument or
can walk other kernel data structures to skb pointer.

In order to do that teach verifier to resolve true C types
of bpf helpers into in-kernel BTF ids.
The type of kernel pointer passed by raw tracepoint into bpf
program will be tracked by the verifier all the way until
it's passed into helper function.
For example:
kfree_skb() kernel function calls trace_kfree_skb(skb, loc);
bpf programs receives that skb pointer and may eventually
pass it into bpf_skb_output() bpf helper which in-kernel is
implemented via bpf_skb_event_output() kernel function.
Its first argument in the kernel is 'struct sk_buff *'.
The verifier makes sure that types match all the way.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20191016032505.2089704-11-ast@kernel.org

3 files changed, 101 insertions, 15 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 271d27cd427f..f7557af39756 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3626,6 +3626,74 @@ again:
 	return -EINVAL;
 }
 
+u32 btf_resolve_helper_id(struct bpf_verifier_log *log, void *fn, int arg)
+{
+	char fnname[KSYM_SYMBOL_LEN + 4] = "btf_";
+	const struct btf_param *args;
+	const struct btf_type *t;
+	const char *tname, *sym;
+	u32 btf_id, i;
+
+	if (IS_ERR(btf_vmlinux)) {
+		bpf_log(log, "btf_vmlinux is malformed\n");
+		return -EINVAL;
+	}
+
+	sym = kallsyms_lookup((long)fn, NULL, NULL, NULL, fnname + 4);
+	if (!sym) {
+		bpf_log(log, "kernel doesn't have kallsyms\n");
+		return -EFAULT;
+	}
+
+	for (i = 1; i <= btf_vmlinux->nr_types; i++) {
+		t = btf_type_by_id(btf_vmlinux, i);
+		if (BTF_INFO_KIND(t->info) != BTF_KIND_TYPEDEF)
+			continue;
+		tname = __btf_name_by_offset(btf_vmlinux, t->name_off);
+		if (!strcmp(tname, fnname))
+			break;
+	}
+	if (i > btf_vmlinux->nr_types) {
+		bpf_log(log, "helper %s type is not found\n", fnname);
+		return -ENOENT;
+	}
+
+	t = btf_type_by_id(btf_vmlinux, t->type);
+	if (!btf_type_is_ptr(t))
+		return -EFAULT;
+	t = btf_type_by_id(btf_vmlinux, t->type);
+	if (!btf_type_is_func_proto(t))
+		return -EFAULT;
+
+	args = (const struct btf_param *)(t + 1);
+	if (arg >= btf_type_vlen(t)) {
+		bpf_log(log, "bpf helper %s doesn't have %d-th argument\n",
+			fnname, arg);
+		return -EINVAL;
+	}
+
+	t = btf_type_by_id(btf_vmlinux, args[arg].type);
+	if (!btf_type_is_ptr(t) || !t->type) {
+		/* anything but the pointer to struct is a helper config bug */
+		bpf_log(log, "ARG_PTR_TO_BTF is misconfigured\n");
+		return -EFAULT;
+	}
+	btf_id = t->type;
+	t = btf_type_by_id(btf_vmlinux, t->type);
+	/* skip modifiers */
+	while (btf_type_is_modifier(t)) {
+		btf_id = t->type;
+		t = btf_type_by_id(btf_vmlinux, t->type);
+	}
+	if (!btf_type_is_struct(t)) {
+		bpf_log(log, "ARG_PTR_TO_BTF is not a struct\n");
+		return -EFAULT;
+	}
+	bpf_log(log, "helper %s arg%d has btf_id %d struct %s\n", fnname + 4,
+		arg, btf_id, __btf_name_by_offset(btf_vmlinux, t->name_off));
+	return btf_id;
+}
+
 void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m)
 {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index fba9ef6a831b..556e82f8869b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -205,6 +205,7 @@ struct bpf_call_arg_meta {
 	u64 msize_umax_value;
 	int ref_obj_id;
 	int func_id;
+	u32 btf_id;
 };
 
 struct btf *btf_vmlinux;
@@ -3439,6 +3440,22 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		expected_type = PTR_TO_SOCKET;
 		if (type != expected_type)
 			goto err_type;
+	} else if (arg_type == ARG_PTR_TO_BTF_ID) {
+		expected_type = PTR_TO_BTF_ID;
+		if (type != expected_type)
+			goto err_type;
+		if (reg->btf_id != meta->btf_id) {
+			verbose(env, "Helper has type %s got %s in R%d\n",
+				kernel_type_name(meta->btf_id),
+				kernel_type_name(reg->btf_id), regno);
+
+			return -EACCES;
+		}
+		if (!tnum_is_const(reg->var_off) || reg->var_off.value || reg->off) {
+			verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n",
+				regno);
+			return -EACCES;
+		}
 	} else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
 		if (meta->func_id == BPF_FUNC_spin_lock) {
 			if (process_spin_lock(env, regno, true))
@@ -3586,6 +3603,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
 		if (func_id != BPF_FUNC_perf_event_read &&
 		    func_id != BPF_FUNC_perf_event_output &&
+		    func_id != BPF_FUNC_skb_output &&
 		    func_id != BPF_FUNC_perf_event_read_value)
 			goto error;
 		break;
@@ -3673,6 +3691,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 	case BPF_FUNC_perf_event_read:
 	case BPF_FUNC_perf_event_output:
 	case BPF_FUNC_perf_event_read_value:
+	case BPF_FUNC_skb_output:
 		if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
 			goto error;
 		break;
@@ -4127,21 +4146,16 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 
 	meta.func_id = func_id;
 	/* check args */
-	err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &meta);
-	if (err)
-		return err;
-	err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &meta);
-	if (err)
-		return err;
-	err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &meta);
-	if (err)
-		return err;
-	err = check_func_arg(env, BPF_REG_4, fn->arg4_type, &meta);
-	if (err)
-		return err;
-	err = check_func_arg(env, BPF_REG_5, fn->arg5_type, &meta);
-	if (err)
-		return err;
+	for (i = 0; i < 5; i++) {
+		if (fn->arg_type[i] == ARG_PTR_TO_BTF_ID) {
+			if (!fn->btf_id[i])
+				fn->btf_id[i] = btf_resolve_helper_id(&env->log, fn->func, i);
+			meta.btf_id = fn->btf_id[i];
+		}
+		err = check_func_arg(env, BPF_REG_1 + i, fn->arg_type[i], &meta);
+		if (err)
+			return err;
+	}
 
 	err = record_func_map(env, &meta, func_id, insn_idx);
 	if (err)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 6221e8c6ecc3..52f7e9d8c29b 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -995,6 +995,8 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
+extern const struct bpf_func_proto bpf_skb_output_proto;
+
 BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args,
 	   struct bpf_map *, map, u64, flags)
 {
@@ -1053,6 +1055,8 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	switch (func_id) {
 	case BPF_FUNC_perf_event_output:
 		return &bpf_perf_event_output_proto_raw_tp;
+	case BPF_FUNC_skb_output:
+		return &bpf_skb_output_proto;
 	case BPF_FUNC_get_stackid:
 		return &bpf_get_stackid_proto_raw_tp;
 	case BPF_FUNC_get_stack: