On Wed, 4 Mar 2026 at 15:55, Chengkaitao <[email protected]> wrote:
>
> From: Kaitao Cheng <[email protected]>
>
> Add a new kfunc bpf_list_add_impl(head, new, prev, meta, off) that
> inserts 'new' after 'prev' in the BPF linked list. Both must be in
> the same list; 'prev' must already be in the list. The new node must
> be an owning reference (e.g. from bpf_obj_new); the kfunc consumes
> that reference and the node becomes non-owning once inserted.
>
> We have added an additional parameter bpf_list_head *head to
> bpf_list_add_impl, as the verifier requires the head parameter to
> check whether the lock is being held.
>
> Returns 0 on success, -EINVAL if 'prev' is not in a list or 'new'
> is already in a list (or duplicate insertion). On failure, the
> kernel drops the passed-in node.
>
> Signed-off-by: Kaitao Cheng <[email protected]>
> ---
> kernel/bpf/helpers.c | 34 ++++++++++++++++++++++++++++++++++
> kernel/bpf/verifier.c | 17 +++++++++++++----
> 2 files changed, 47 insertions(+), 4 deletions(-)
>
> diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
> index cc1a096a1f64..740b53024283 100644
> --- a/kernel/bpf/helpers.c
> +++ b/kernel/bpf/helpers.c
> @@ -2505,6 +2505,39 @@ __bpf_kfunc struct bpf_list_node *bpf_list_back(struct
> bpf_list_head *head)
> return (struct bpf_list_node *)h->prev;
> }
>
> +__bpf_kfunc int bpf_list_add_impl(struct bpf_list_head *head,
> + struct bpf_list_node *new,
> + struct bpf_list_node *prev,
> + void *meta__ign, u64 off)
I have pretty much the same comment here, there is a lot of
duplication between this and __bpf_list_add.
We can write list_add_tail in terms of __list_add, and then unify all of this.
> +{
> + struct bpf_list_node_kern *kn = (void *)new, *kp = (void *)prev;
> + struct btf_struct_meta *meta = meta__ign;
> + struct list_head *n = &kn->list_head, *p = &kp->list_head;
> + struct list_head *h = (void *)head;
> +
> + /* If list_head was 0-initialized by map, bpf_obj_init_field wasn't
> + * called on its fields, so init here
> + */
> + if (unlikely(!h->next)) {
> + INIT_LIST_HEAD(h);
> + goto fail;
Not clear to me why we should fail here; why can't we continue adding
after initializing the list head?
E.g. __bpf_list_add isn't doing it.
> + }
> +
> + if (WARN_ON_ONCE(READ_ONCE(kp->owner) != head))
> + goto fail;
> +
> + if (cmpxchg(&kn->owner, NULL, BPF_PTR_POISON))
> + goto fail;
> +
> + list_add(n, p);
> + WRITE_ONCE(kn->owner, head);
> + return 0;
> +
> +fail:
> + __bpf_obj_drop_impl((void *)n - off, meta ? meta->record : NULL,
> false);
> + return -EINVAL;
> +}
> +
> __bpf_kfunc struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root,
> struct bpf_rb_node *node)
> {
> @@ -4574,6 +4607,7 @@ 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_list_add_impl)
> BTF_ID_FLAGS(func, bpf_task_acquire, KF_ACQUIRE | KF_RCU | KF_RET_NULL)
> BTF_ID_FLAGS(func, bpf_task_release, KF_RELEASE)
> BTF_ID_FLAGS(func, bpf_rbtree_remove, KF_ACQUIRE | KF_RET_NULL)
> diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
> index c9557d3fb8dd..e458cf3b1dd1 100644
> --- a/kernel/bpf/verifier.c
> +++ b/kernel/bpf/verifier.c
> @@ -12464,6 +12464,7 @@ enum special_kfunc_type {
> KF_bpf_list_del,
> KF_bpf_list_front,
> KF_bpf_list_back,
> + KF_bpf_list_add_impl,
> KF_bpf_cast_to_kern_ctx,
> KF_bpf_rdonly_cast,
> KF_bpf_rcu_read_lock,
> @@ -12525,6 +12526,7 @@ 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_list_add_impl)
> BTF_ID(func, bpf_cast_to_kern_ctx)
> BTF_ID(func, bpf_rdonly_cast)
> BTF_ID(func, bpf_rcu_read_lock)
> @@ -13000,7 +13002,8 @@ static bool is_bpf_list_api_kfunc(u32 btf_id)
> 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];
> + btf_id == special_kfunc_list[KF_bpf_list_back] ||
> + btf_id == special_kfunc_list[KF_bpf_list_add_impl];
> }
>
> static bool is_bpf_rbtree_api_kfunc(u32 btf_id)
> @@ -13122,7 +13125,8 @@ static bool check_kfunc_is_graph_node_api(struct
> bpf_verifier_env *env,
> 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_del]);
> + kfunc_btf_id == special_kfunc_list[KF_bpf_list_del] ||
> + kfunc_btf_id ==
> special_kfunc_list[KF_bpf_list_add_impl]);
> break;
> case BPF_RB_NODE:
> ret = (kfunc_btf_id ==
> special_kfunc_list[KF_bpf_rbtree_remove] ||
> @@ -14264,6 +14268,7 @@ static int check_kfunc_call(struct bpf_verifier_env
> *env, struct bpf_insn *insn,
>
> if (meta.func_id == special_kfunc_list[KF_bpf_list_push_front_impl] ||
> meta.func_id == special_kfunc_list[KF_bpf_list_push_back_impl] ||
> + meta.func_id == special_kfunc_list[KF_bpf_list_add_impl] ||
> meta.func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) {
> release_ref_obj_id = regs[BPF_REG_2].ref_obj_id;
> insn_aux->insert_off = regs[BPF_REG_2].off;
> @@ -23230,13 +23235,17 @@ static int fixup_kfunc_call(struct bpf_verifier_env
> *env, struct bpf_insn *insn,
> *cnt = 3;
> } else if (desc->func_id ==
> special_kfunc_list[KF_bpf_list_push_back_impl] ||
> desc->func_id ==
> special_kfunc_list[KF_bpf_list_push_front_impl] ||
> + desc->func_id == special_kfunc_list[KF_bpf_list_add_impl]
> ||
> desc->func_id ==
> special_kfunc_list[KF_bpf_rbtree_add_impl]) {
> struct btf_struct_meta *kptr_struct_meta =
> env->insn_aux_data[insn_idx].kptr_struct_meta;
> int struct_meta_reg = BPF_REG_3;
> int node_offset_reg = BPF_REG_4;
>
> - /* rbtree_add has extra 'less' arg, so args-to-fixup are in
> diff regs */
> - if (desc->func_id ==
> special_kfunc_list[KF_bpf_rbtree_add_impl]) {
> + /* list/rbtree_add_impl have an extra arg (prev/less),
> + * so args-to-fixup are in different regs.
> + */
> + if (desc->func_id == special_kfunc_list[KF_bpf_list_add_impl]
> ||
> + desc->func_id ==
> special_kfunc_list[KF_bpf_rbtree_add_impl]) {
> struct_meta_reg = BPF_REG_4;
> node_offset_reg = BPF_REG_5;
> }
> --
> 2.50.1 (Apple Git-155)
>
>
