bpf: Teach verifier about kptr_get kfunc helpers

We introduce a new style of kfunc helpers, namely *_kptr_get, where they
take pointer to the map value which points to a referenced kernel
pointer contained in the map. Since this is referenced, only
bpf_kptr_xchg from BPF side and xchg from kernel side is allowed to
change the current value, and each pointer that resides in that location
would be referenced, and RCU protected (this must be kept in mind while
adding kernel types embeddable as reference kptr in BPF maps).

This means that if do the load of the pointer value in an RCU read
section, and find a live pointer, then as long as we hold RCU read lock,
it won't be freed by a parallel xchg + release operation. This allows us
to implement a safe refcount increment scheme. Hence, enforce that first
argument of all such kfunc is a proper PTR_TO_MAP_VALUE pointing at the
right offset to referenced pointer.

For the rest of the arguments, they are subjected to typical kfunc
argument checks, hence allowing some flexibility in passing more intent
into how the reference should be taken.

For instance, in case of struct nf_conn, it is not freed until RCU grace
period ends, but can still be reused for another tuple once refcount has
dropped to zero. Hence, a bpf_ct_kptr_get helper not only needs to call
refcount_inc_not_zero, but also do a tuple match after incrementing the
reference, and when it fails to match it, put the reference again and
return NULL.

This can be implemented easily if we allow passing additional parameters
to the bpf_ct_kptr_get kfunc, like a struct bpf_sock_tuple * and a
tuple__sz pair.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20220424214901.2743946-9-memxor@gmail.com

include/linux/btf.h

@@ -17,6 +17,7 @@ enum btf_kfunc_type {
 	BTF_KFUNC_TYPE_ACQUIRE,
 	BTF_KFUNC_TYPE_RELEASE,
 	BTF_KFUNC_TYPE_RET_NULL,
+	BTF_KFUNC_TYPE_KPTR_ACQUIRE,
 	BTF_KFUNC_TYPE_MAX,
 };
 
@@ -35,6 +36,7 @@ struct btf_kfunc_id_set {
 			struct btf_id_set *acquire_set;
 			struct btf_id_set *release_set;
 			struct btf_id_set *ret_null_set;
+			struct btf_id_set *kptr_acquire_set;
 		};
 		struct btf_id_set *sets[BTF_KFUNC_TYPE_MAX];
 	};

kernel/bpf/btf.c

@@ -6089,11 +6089,11 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 	struct bpf_verifier_log *log = &env->log;
 	u32 i, nargs, ref_id, ref_obj_id = 0;
 	bool is_kfunc = btf_is_kernel(btf);
+	bool rel = false, kptr_get = false;
 	const char *func_name, *ref_tname;
 	const struct btf_type *t, *ref_t;
 	const struct btf_param *args;
 	int ref_regno = 0, ret;
-	bool rel = false;
 
 	t = btf_type_by_id(btf, func_id);
 	if (!t || !btf_type_is_func(t)) {
@@ -6119,10 +6119,14 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 		return -EINVAL;
 	}
 
-	/* Only kfunc can be release func */
-	if (is_kfunc)
+	if (is_kfunc) {
+		/* Only kfunc can be release func */
 		rel = btf_kfunc_id_set_contains(btf, resolve_prog_type(env->prog),
 						BTF_KFUNC_TYPE_RELEASE, func_id);
+		kptr_get = btf_kfunc_id_set_contains(btf, resolve_prog_type(env->prog),
+						     BTF_KFUNC_TYPE_KPTR_ACQUIRE, func_id);
+	}
+
 	/* check that BTF function arguments match actual types that the
 	 * verifier sees.
 	 */
@@ -6154,8 +6158,52 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 		if (ret < 0)
 			return ret;
 
-		if (btf_get_prog_ctx_type(log, btf, t,
-					  env->prog->type, i)) {
+		/* kptr_get is only true for kfunc */
+		if (i == 0 && kptr_get) {
+			struct bpf_map_value_off_desc *off_desc;
+
+			if (reg->type != PTR_TO_MAP_VALUE) {
+				bpf_log(log, "arg#0 expected pointer to map value\n");
+				return -EINVAL;
+			}
+
+			/* check_func_arg_reg_off allows var_off for
+			 * PTR_TO_MAP_VALUE, but we need fixed offset to find
+			 * off_desc.
+			 */
+			if (!tnum_is_const(reg->var_off)) {
+				bpf_log(log, "arg#0 must have constant offset\n");
+				return -EINVAL;
+			}
+
+			off_desc = bpf_map_kptr_off_contains(reg->map_ptr, reg->off + reg->var_off.value);
+			if (!off_desc || off_desc->type != BPF_KPTR_REF) {
+				bpf_log(log, "arg#0 no referenced kptr at map value offset=%llu\n",
+					reg->off + reg->var_off.value);
+				return -EINVAL;
+			}
+
+			if (!btf_type_is_ptr(ref_t)) {
+				bpf_log(log, "arg#0 BTF type must be a double pointer\n");
+				return -EINVAL;
+			}
+
+			ref_t = btf_type_skip_modifiers(btf, ref_t->type, &ref_id);
+			ref_tname = btf_name_by_offset(btf, ref_t->name_off);
+
+			if (!btf_type_is_struct(ref_t)) {
+				bpf_log(log, "kernel function %s args#%d pointer type %s %s is not supported\n",
+					func_name, i, btf_type_str(ref_t), ref_tname);
+				return -EINVAL;
+			}
+			if (!btf_struct_ids_match(log, btf, ref_id, 0, off_desc->kptr.btf,
+						  off_desc->kptr.btf_id)) {
+				bpf_log(log, "kernel function %s args#%d expected pointer to %s %s\n",
+					func_name, i, btf_type_str(ref_t), ref_tname);
+				return -EINVAL;
+			}
+			/* rest of the arguments can be anything, like normal kfunc */
+		} else if (btf_get_prog_ctx_type(log, btf, t, env->prog->type, i)) {
 			/* If function expects ctx type in BTF check that caller
 			 * is passing PTR_TO_CTX.
 			 */