bpf/verifier: allow kfunc to return an allocated mem

For drivers (outside of network), the incoming data is not statically
defined in a struct. Most of the time the data buffer is kzalloc-ed
and thus we can not rely on eBPF and BTF to explore the data.

This commit allows to return an arbitrary memory, previously allocated by
the driver.
An interesting extra point is that the kfunc can mark the exported
memory region as read only or read/write.

So, when a kfunc is not returning a pointer to a struct but to a plain
type, we can consider it is a valid allocated memory assuming that:
- one of the arguments is either called rdonly_buf_size or
  rdwr_buf_size
- and this argument is a const from the caller point of view

We can then use this parameter as the size of the allocated memory.

The memory is either read-only or read-write based on the name
of the size parameter.

Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Link: https://lore.kernel.org/r/20220906151303.2780789-7-benjamin.tissoires@redhat.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 32 insertions, 13 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 3cfe60206de6..f3344a86d88d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2908,7 +2908,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno,
 	return 0;
 }
 
-static int mark_chain_precision(struct bpf_verifier_env *env, int regno)
+int mark_chain_precision(struct bpf_verifier_env *env, int regno)
 {
 	return __mark_chain_precision(env, regno, -1);
 }
@@ -7595,6 +7595,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 {
 	const struct btf_type *t, *func, *func_proto, *ptr_type;
 	struct bpf_reg_state *regs = cur_regs(env);
+	struct bpf_kfunc_arg_meta meta = { 0 };
 	const char *func_name, *ptr_type_name;
 	u32 i, nargs, func_id, ptr_type_id;
 	int err, insn_idx = *insn_idx_p;
@@ -7629,8 +7630,10 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 
 	acq = *kfunc_flags & KF_ACQUIRE;
 
+	meta.flags = *kfunc_flags;
+
 	/* Check the arguments */
-	err = btf_check_kfunc_arg_match(env, desc_btf, func_id, regs, *kfunc_flags);
+	err = btf_check_kfunc_arg_match(env, desc_btf, func_id, regs, &meta);
 	if (err < 0)
 		return err;
 	/* In case of release function, we get register number of refcounted
@@ -7651,7 +7654,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 	/* Check return type */
 	t = btf_type_skip_modifiers(desc_btf, func_proto->type, NULL);
 
-	if (acq && !btf_type_is_ptr(t)) {
+	if (acq && !btf_type_is_struct_ptr(desc_btf, t)) {
 		verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n");
 		return -EINVAL;
 	}
@@ -7663,17 +7666,33 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		ptr_type = btf_type_skip_modifiers(desc_btf, t->type,
 						   &ptr_type_id);
 		if (!btf_type_is_struct(ptr_type)) {
-			ptr_type_name = btf_name_by_offset(desc_btf,
-							   ptr_type->name_off);
-			verbose(env, "kernel function %s returns pointer type %s %s is not supported\n",
-				func_name, btf_type_str(ptr_type),
-				ptr_type_name);
-			return -EINVAL;
+			if (!meta.r0_size) {
+				ptr_type_name = btf_name_by_offset(desc_btf,
+								   ptr_type->name_off);
+				verbose(env,
+					"kernel function %s returns pointer type %s %s is not supported\n",
+					func_name,
+					btf_type_str(ptr_type),
+					ptr_type_name);
+				return -EINVAL;
+			}
+
+			mark_reg_known_zero(env, regs, BPF_REG_0);
+			regs[BPF_REG_0].type = PTR_TO_MEM;
+			regs[BPF_REG_0].mem_size = meta.r0_size;
+
+			if (meta.r0_rdonly)
+				regs[BPF_REG_0].type |= MEM_RDONLY;
+
+			/* Ensures we don't access the memory after a release_reference() */
+			if (meta.ref_obj_id)
+				regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id;
+		} else {
+			mark_reg_known_zero(env, regs, BPF_REG_0);
+			regs[BPF_REG_0].btf = desc_btf;
+			regs[BPF_REG_0].type = PTR_TO_BTF_ID;
+			regs[BPF_REG_0].btf_id = ptr_type_id;
 		}
-		mark_reg_known_zero(env, regs, BPF_REG_0);
-		regs[BPF_REG_0].btf = desc_btf;
-		regs[BPF_REG_0].type = PTR_TO_BTF_ID;
-		regs[BPF_REG_0].btf_id = ptr_type_id;
 		if (*kfunc_flags & KF_RET_NULL) {
 			regs[BPF_REG_0].type |= PTR_MAYBE_NULL;
 			/* For mark_ptr_or_null_reg, see 93c230e3f5bd6 */