[PATCH v2 1/6] bpf: Introduce the bpf_list_del kfunc.

[Chengkaitao]

From: Kaitao Cheng <chengkaitao@xxxxxxxxxx>

If a user holds ownership of a node in the middle of a list, they
can directly remove it from the list without strictly adhering to
deletion rules from the head or tail.

When a kfunc has only one bpf_list_node parameter, supplement the
initialization of the corresponding btf_field.

This is typically paired with bpf_refcount. After calling
bpf_list_del, it is generally necessary to drop the reference to
the list node twice to prevent reference count leaks.

Signed-off-by: Kaitao Cheng <chengkaitao@xxxxxxxxxx>
---
 kernel/bpf/btf.c      | 33 +++++++++++++++++++++++++++++----
 kernel/bpf/helpers.c  | 17 +++++++++++++++++
 kernel/bpf/verifier.c |  9 ++++++++-
 3 files changed, 54 insertions(+), 5 deletions(-)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 4872d2a6c42d..8a977c793d56 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3785,7 +3785,6 @@ static int btf_find_field_one(const struct btf *btf,
 	case BPF_RES_SPIN_LOCK:
 	case BPF_TIMER:
 	case BPF_WORKQUEUE:
-	case BPF_LIST_NODE:
 	case BPF_RB_NODE:
 	case BPF_REFCOUNT:
 	case BPF_TASK_WORK:
@@ -3794,6 +3793,27 @@ static int btf_find_field_one(const struct btf *btf,
 		if (ret < 0)
 			return ret;
 		break;
+	case BPF_LIST_NODE:
+		ret = btf_find_struct(btf, var_type, off, sz, field_type,
+				      info_cnt ? &info[0] : &tmp);
+		if (ret < 0)
+			return ret;
+		/* graph_root for verifier: container type and node member name */
+		if (info_cnt && var_idx >= 0 && (u32)var_idx < btf_type_vlen(var)) {
+			u32 id;
+			const struct btf_member *member;
+
+			for (id = 1; id < btf_nr_types(btf); id++) {
+				if (btf_type_by_id(btf, id) == var) {
+					info[0].graph_root.value_btf_id = id;
+					member = btf_type_member(var) + var_idx;
+					info[0].graph_root.node_name =
+						__btf_name_by_offset(btf, member->name_off);
+					break;
+				}
+			}
+		}
+		break;
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
 	case BPF_KPTR_PERCPU:
@@ -4138,6 +4158,7 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type
 			if (ret < 0)
 				goto end;
 			break;
+		case BPF_LIST_NODE:
 		case BPF_LIST_HEAD:
 			ret = btf_parse_list_head(btf, &rec->fields[i], &info_arr[i]);
 			if (ret < 0)
@@ -4148,7 +4169,6 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type
 			if (ret < 0)
 				goto end;
 			break;
-		case BPF_LIST_NODE:
 		case BPF_RB_NODE:
 			break;
 		default:
@@ -4192,20 +4212,25 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec)
 	int i;
 
 	/* There are three types that signify ownership of some other type:
-	 *  kptr_ref, bpf_list_head, bpf_rb_root.
+	 *  kptr_ref, bpf_list_head/node, bpf_rb_root.
 	 * kptr_ref only supports storing kernel types, which can't store
 	 * references to program allocated local types.
 	 *
 	 * Hence we only need to ensure that bpf_{list_head,rb_root} ownership
 	 * does not form cycles.
 	 */
-	if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & (BPF_GRAPH_ROOT | BPF_UPTR)))
+	if (IS_ERR_OR_NULL(rec) || !(rec->field_mask &
+	   (BPF_GRAPH_ROOT | BPF_GRAPH_NODE | BPF_UPTR)))
 		return 0;
+
 	for (i = 0; i < rec->cnt; i++) {
 		struct btf_struct_meta *meta;
 		const struct btf_type *t;
 		u32 btf_id;
 
+		if (rec->fields[i].type & BPF_GRAPH_NODE)
+			rec->fields[i].graph_root.value_rec = rec;
+
 		if (rec->fields[i].type == BPF_UPTR) {
 			/* The uptr only supports pinning one page and cannot
 			 * point to a kernel struct
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 6eb6c82ed2ee..577af62a9f7a 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2459,6 +2459,22 @@ __bpf_kfunc struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head)
 	return __bpf_list_del(head, true);
 }
 
+__bpf_kfunc struct bpf_list_node *bpf_list_del(struct bpf_list_node *node)
+{
+	struct bpf_list_node_kern *knode = (struct bpf_list_node_kern *)node;
+
+	if (unlikely(!knode))
+		return NULL;
+
+	if (WARN_ON_ONCE(!READ_ONCE(knode->owner)))
+		return NULL;
+
+	list_del_init(&knode->list_head);
+	WRITE_ONCE(knode->owner, NULL);
+
+	return node;
+}
+
 __bpf_kfunc struct bpf_list_node *bpf_list_front(struct bpf_list_head *head)
 {
 	struct list_head *h = (struct list_head *)head;
@@ -4545,6 +4561,7 @@ BTF_ID_FLAGS(func, bpf_list_push_front_impl)
 BTF_ID_FLAGS(func, bpf_list_push_back_impl)
 BTF_ID_FLAGS(func, bpf_list_pop_front, KF_ACQUIRE | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_list_pop_back, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_list_del, KF_ACQUIRE | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_list_front, KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_list_back, KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_task_acquire, KF_ACQUIRE | KF_RCU | KF_RET_NULL)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a3390190c26e..1e9857177a7a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -12431,6 +12431,7 @@ enum special_kfunc_type {
 	KF_bpf_list_push_back_impl,
 	KF_bpf_list_pop_front,
 	KF_bpf_list_pop_back,
+	KF_bpf_list_del,
 	KF_bpf_list_front,
 	KF_bpf_list_back,
 	KF_bpf_cast_to_kern_ctx,
@@ -12491,6 +12492,7 @@ BTF_ID(func, bpf_list_push_front_impl)
 BTF_ID(func, bpf_list_push_back_impl)
 BTF_ID(func, bpf_list_pop_front)
 BTF_ID(func, bpf_list_pop_back)
+BTF_ID(func, bpf_list_del)
 BTF_ID(func, bpf_list_front)
 BTF_ID(func, bpf_list_back)
 BTF_ID(func, bpf_cast_to_kern_ctx)
@@ -12966,6 +12968,7 @@ static bool is_bpf_list_api_kfunc(u32 btf_id)
 	       btf_id == special_kfunc_list[KF_bpf_list_push_back_impl] ||
 	       btf_id == special_kfunc_list[KF_bpf_list_pop_front] ||
 	       btf_id == special_kfunc_list[KF_bpf_list_pop_back] ||
+	       btf_id == special_kfunc_list[KF_bpf_list_del] ||
 	       btf_id == special_kfunc_list[KF_bpf_list_front] ||
 	       btf_id == special_kfunc_list[KF_bpf_list_back];
 }
@@ -13088,7 +13091,8 @@ static bool check_kfunc_is_graph_node_api(struct bpf_verifier_env *env,
 	switch (node_field_type) {
 	case BPF_LIST_NODE:
 		ret = (kfunc_btf_id == special_kfunc_list[KF_bpf_list_push_front_impl] ||
-		       kfunc_btf_id == special_kfunc_list[KF_bpf_list_push_back_impl]);
+		       kfunc_btf_id == special_kfunc_list[KF_bpf_list_push_back_impl] ||
+		       kfunc_btf_id == special_kfunc_list[KF_bpf_list_del]);
 		break;
 	case BPF_RB_NODE:
 		ret = (kfunc_btf_id == special_kfunc_list[KF_bpf_rbtree_remove] ||
@@ -13211,6 +13215,9 @@ __process_kf_arg_ptr_to_graph_node(struct bpf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	if (!*node_field)
+		*node_field = field;
+
 	field = *node_field;
 
 	et = btf_type_by_id(field->graph_root.btf, field->graph_root.value_btf_id);
-- 
2.50.1 (Apple Git-155)