bpf/verifier: Expand the usage scenarios of bpf_kptr_xchg

[kernel-patches-daemon-bpf]

Pull request for series with
subject: bpf/verifier: Expand the usage scenarios of bpf_kptr_xchg
version: 5
url: https://patchwork.kernel.org/project/netdevbpf/list/?series=1050033

[kernel-patches-daemon-bpf]

Upstream branch: 6b95cc5
series: https://patchwork.kernel.org/project/netdevbpf/list/?series=1050033
version: 5

[kernel-patches-daemon-bpf]

Upstream branch: d95d76a
series: https://patchwork.kernel.org/project/netdevbpf/list/?series=1050033
version: 5

[kernel-patches-review-bot]

commit 89b3aab8a7985a61534c13aa011a3919a16cb6c6
Author: Chengkaitao Com <[email protected]>

bpf/verifier: allow using bpf_kptr_xchg even if the NON_OWN_REF flag is set

This patch allows bpf_kptr_xchg to operate on __kptr fields within rbtree
nodes obtained via bpf_rbtree_left/right traversal (NON_OWN_REF pointers),
avoiding the need to remove and re-add nodes just to access their kptrs.

> diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
> index 2dd860ae12..bb45fa5612 100644
> --- a/kernel/bpf/verifier.c
> +++ b/kernel/bpf/verifier.c
> @@ -9300,7 +9300,8 @@ static const struct bpf_reg_types timer_types = { .types = { PTR_TO_MAP_VALUE }
>  static const struct bpf_reg_types kptr_xchg_dest_types = {
>  	.types = {
>  		PTR_TO_MAP_VALUE,
> -		PTR_TO_BTF_ID | MEM_ALLOC
> +		PTR_TO_BTF_ID | MEM_ALLOC,
> +		PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF
>  	}
>  };

Is the MEM_RCU variant also needed here?

When ref_set_non_owning() marks a register as NON_OWN_REF, it also adds
MEM_RCU if the node has a bpf_refcount field (refcount_off >= 0):

    reg->type |= NON_OWN_REF;
    if (rec->refcount_off >= 0)
        reg->type |= MEM_RCU;

This means rbtree nodes with both a __kptr field and a bpf_refcount field
would have type PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF | MEM_RCU, which
won't match any entry in kptr_xchg_dest_types.

Should this also add:

    PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF | MEM_RCU

to handle that case?

> @@ -9460,6 +9461,7 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
>  	}
>  	case PTR_TO_BTF_ID | MEM_ALLOC:
>  	case PTR_TO_BTF_ID | MEM_PERCPU | MEM_ALLOC:
> +	case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF:
>  		if (meta->func_id != BPF_FUNC_spin_lock && meta->func_id != BPF_FUNC_spin_unlock &&
>  		    meta->func_id != BPF_FUNC_kptr_xchg) {

Similarly, does this switch need a case for the MEM_RCU variant?

---

AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md

In-Reply-To-Subject: bpf/verifier: allow using bpf_kptr_xchg even if the NON_OWN_REF flag is set
CI run summary: https://github.com/kernel-patches/bpf/actions/runs/21614799102

AI-authorship-score: low
AI-authorship-explanation: The commit addresses a specific practical problem with minimal targeted changes, showing domain expertise typical of human kernel developers rather than AI-generated comprehensive solutions.
issues-found: 1
issue-severity-score: low
issue-severity-explanation: Missing MEM_RCU variant may prevent bpf_kptr_xchg on refcounted rbtree nodes, but this affects only a subset of use cases and causes verifier rejection rather than runtime issues.

[kernel-patches-daemon-bpf]

Forwarding comment 3838760901 via email
In-Reply-To: [email protected]
Patch: https://patchwork.kernel.org/project/netdevbpf/patch/[email protected]/

[kernel-patches-daemon-bpf]

Upstream branch: f941479
series: https://patchwork.kernel.org/project/netdevbpf/list/?series=1050033
version: 5

[kernel-patches-daemon-bpf]

Upstream branch: f11f7cf
series: https://patchwork.kernel.org/project/netdevbpf/list/?series=1050033
version: 5

[kernel-patches-daemon-bpf]

Upstream branch: b28dac3
series: https://patchwork.kernel.org/project/netdevbpf/list/?series=1050033
version: 5