[PATCH bpf-next v8 5/8] bpf: Add bpf_list_add_impl to insert node after a given list node

Chengkaitao posted 8 patches 3 weeks ago
There is a newer version of this series
[PATCH bpf-next v8 5/8] bpf: Add bpf_list_add_impl to insert node after a given list node
Posted by Chengkaitao 3 weeks ago
From: Kaitao Cheng <chengkaitao@kylinos.cn>

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 <chengkaitao@kylinos.cn>
---
 kernel/bpf/helpers.c  | 14 ++++++++++++++
 kernel/bpf/verifier.c | 13 +++++++++++--
 2 files changed, 25 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index a9665f97b3bc..dc4f8b4eec01 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2438,6 +2438,19 @@ __bpf_kfunc int bpf_list_push_back_impl(struct bpf_list_head *head,
 	return __bpf_list_add(new, head, &h->prev, meta ? meta->record : NULL, off);
 }
 
+__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)
+{
+	struct bpf_list_node_kern *kn = (void *)new, *kp = (void *)prev;
+	struct btf_struct_meta *meta = meta__ign;
+	struct list_head *prev_ptr = &kp->list_head;
+
+	return __bpf_list_add(kn, head, &prev_ptr,
+			      meta ? meta->record : NULL, off);
+}
+
 static struct bpf_list_node *__bpf_list_del(struct bpf_list_head *head,
 					    struct list_head *n)
 {
@@ -4574,6 +4587,7 @@ 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 e928ad4290c7..98ddb370feb5 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -12506,6 +12506,7 @@ enum special_kfunc_type {
 	KF_bpf_refcount_acquire_impl,
 	KF_bpf_list_push_front_impl,
 	KF_bpf_list_push_back_impl,
+	KF_bpf_list_add_impl,
 	KF_bpf_list_pop_front,
 	KF_bpf_list_pop_back,
 	KF_bpf_list_del,
@@ -12567,6 +12568,7 @@ BTF_ID(func, bpf_obj_drop_impl)
 BTF_ID(func, bpf_refcount_acquire_impl)
 BTF_ID(func, bpf_list_push_front_impl)
 BTF_ID(func, bpf_list_push_back_impl)
+BTF_ID(func, bpf_list_add_impl)
 BTF_ID(func, bpf_list_pop_front)
 BTF_ID(func, bpf_list_pop_back)
 BTF_ID(func, bpf_list_del)
@@ -12644,6 +12646,7 @@ BTF_ID(func, bpf_stream_print_stack)
 static const enum special_kfunc_type bpf_list_api_kfuncs[] = {
 	KF_bpf_list_push_front_impl,
 	KF_bpf_list_push_back_impl,
+	KF_bpf_list_add_impl,
 	KF_bpf_list_pop_front,
 	KF_bpf_list_pop_back,
 	KF_bpf_list_del,
@@ -12655,6 +12658,7 @@ static const enum special_kfunc_type bpf_list_api_kfuncs[] = {
 static const enum special_kfunc_type bpf_list_node_api_kfuncs[] = {
 	KF_bpf_list_push_front_impl,
 	KF_bpf_list_push_back_impl,
+	KF_bpf_list_add_impl,
 	KF_bpf_list_del,
 };
 
@@ -14345,6 +14349,7 @@ 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].var_off.value;
@@ -23357,13 +23362,17 @@ 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)
Re: [PATCH bpf-next v8 5/8] bpf: Add bpf_list_add_impl to insert node after a given list node
Posted by Emil Tsalapatis 2 weeks, 2 days ago
On Mon Mar 16, 2026 at 7:28 AM EDT, Chengkaitao wrote:
> From: Kaitao Cheng <chengkaitao@kylinos.cn>
>
> 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 <chengkaitao@kylinos.cn>
> ---
>  kernel/bpf/helpers.c  | 14 ++++++++++++++
>  kernel/bpf/verifier.c | 13 +++++++++++--
>  2 files changed, 25 insertions(+), 2 deletions(-)
>
> diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
> index a9665f97b3bc..dc4f8b4eec01 100644
> --- a/kernel/bpf/helpers.c
> +++ b/kernel/bpf/helpers.c
> @@ -2438,6 +2438,19 @@ __bpf_kfunc int bpf_list_push_back_impl(struct bpf_list_head *head,
>  	return __bpf_list_add(new, head, &h->prev, meta ? meta->record : NULL, off);
>  }
>  
> +__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)
> +{
> +	struct bpf_list_node_kern *kn = (void *)new, *kp = (void *)prev;
> +	struct btf_struct_meta *meta = meta__ign;
> +	struct list_head *prev_ptr = &kp->list_head;
> +

You need to add a version of the check you added on patch 4 here to make
sure the node owners are sane. The check was a WARN_ON because before
the callers to __bpf_list_add didn't take a separate head and node
argument from the program, so any inconsistency was a bug. With this
helper this is no longer the case.

Also check the comment in Sashiko. Can you either add a test that ensures
the use-after-free is described is not the case, or otherwise change
the error handling/verifier behavior to avoid it? I suspect it's an
actual issue.

In general your code is conflating two different issues in its error
handling: 1) A node is being inserted into two different lists at the 
same time, 2) the user has made a programming error and is supplying 
an invalid head/prev combination. These are two very different issues,
and 2) is only possible with this new kfunc. Can you add error handling
for it directly in bpf_list_add_impl, and assume the head/prev
combination is alsways valid in __bpf_list_add?

> +	return __bpf_list_add(kn, head, &prev_ptr,
> +			      meta ? meta->record : NULL, off);
> +}
> +
>  static struct bpf_list_node *__bpf_list_del(struct bpf_list_head *head,
>  					    struct list_head *n)
>  {
> @@ -4574,6 +4587,7 @@ 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 e928ad4290c7..98ddb370feb5 100644
> --- a/kernel/bpf/verifier.c
> +++ b/kernel/bpf/verifier.c
> @@ -12506,6 +12506,7 @@ enum special_kfunc_type {
>  	KF_bpf_refcount_acquire_impl,
>  	KF_bpf_list_push_front_impl,
>  	KF_bpf_list_push_back_impl,
> +	KF_bpf_list_add_impl,
>  	KF_bpf_list_pop_front,
>  	KF_bpf_list_pop_back,
>  	KF_bpf_list_del,
> @@ -12567,6 +12568,7 @@ BTF_ID(func, bpf_obj_drop_impl)
>  BTF_ID(func, bpf_refcount_acquire_impl)
>  BTF_ID(func, bpf_list_push_front_impl)
>  BTF_ID(func, bpf_list_push_back_impl)
> +BTF_ID(func, bpf_list_add_impl)
>  BTF_ID(func, bpf_list_pop_front)
>  BTF_ID(func, bpf_list_pop_back)
>  BTF_ID(func, bpf_list_del)
> @@ -12644,6 +12646,7 @@ BTF_ID(func, bpf_stream_print_stack)
>  static const enum special_kfunc_type bpf_list_api_kfuncs[] = {
>  	KF_bpf_list_push_front_impl,
>  	KF_bpf_list_push_back_impl,
> +	KF_bpf_list_add_impl,
>  	KF_bpf_list_pop_front,
>  	KF_bpf_list_pop_back,
>  	KF_bpf_list_del,
> @@ -12655,6 +12658,7 @@ static const enum special_kfunc_type bpf_list_api_kfuncs[] = {
>  static const enum special_kfunc_type bpf_list_node_api_kfuncs[] = {
>  	KF_bpf_list_push_front_impl,
>  	KF_bpf_list_push_back_impl,
> +	KF_bpf_list_add_impl,
>  	KF_bpf_list_del,
>  };
>  
> @@ -14345,6 +14349,7 @@ 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]) {

Can you use the macros you defined on patch one to replace this list and
the one below?

>  		release_ref_obj_id = regs[BPF_REG_2].ref_obj_id;
>  		insn_aux->insert_off = regs[BPF_REG_2].var_off.value;
> @@ -23357,13 +23362,17 @@ 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;
>  		}