Re: [PATCH bpf-next v4 05/15] bpf: XDP metadata RX kfuncs

[Martin KaFai Lau <martin.lau@xxxxxxxxx>]

On 12/12/22 6:35 PM, Stanislav Fomichev wrote:
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index ca22e8b8bd82..de6279725f41 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -2477,6 +2477,8 @@ void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev,
>   				       struct net_device *netdev);
>   bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev);
>   
> +void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id);
> +

This probably requires an inline version for !CONFIG_NET.

> diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
> index d434a994ee04..c3e501e3e39c 100644
> --- a/kernel/bpf/core.c
> +++ b/kernel/bpf/core.c
> @@ -2097,6 +2097,13 @@ bool bpf_prog_map_compatible(struct bpf_map *map,
>   	if (fp->kprobe_override)
>   		return false;
>   
> +	/* When tail-calling from a non-dev-bound program to a dev-bound one,
> +	 * XDP metadata helpers should be disabled. Until it's implemented,
> +	 * prohibit adding dev-bound programs to tail-call maps.
> +	 */
> +	if (bpf_prog_is_dev_bound(fp->aux))
> +		return false;
> +
>   	spin_lock(&map->owner.lock);
>   	if (!map->owner.type) {
>   		/* There's no owner yet where we could check for
> diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
> index f714c941f8ea..3b6c9023f24d 100644
> --- a/kernel/bpf/offload.c
> +++ b/kernel/bpf/offload.c
> @@ -757,6 +757,29 @@ void bpf_dev_bound_netdev_unregister(struct net_device *dev)
>   	up_write(&bpf_devs_lock);
>   }
>   
> +void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id)
> +{
> +	const struct xdp_metadata_ops *ops;
> +	void *p = NULL;
> +
> +	down_read(&bpf_devs_lock);
> +	if (!prog->aux->offload || !prog->aux->offload->netdev)

This happens when netdev is unregistered in the middle of bpf_prog_load and the 
bpf_offload_dev_match() will eventually fail during dev_xdp_attach()? A comment 
will be useful.

> +		goto out;
> +
> +	ops = prog->aux->offload->netdev->xdp_metadata_ops;
> +	if (!ops)
> +		goto out;
> +
> +	if (func_id == xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_TIMESTAMP))
> +		p = ops->xmo_rx_timestamp;
> +	else if (func_id == xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_HASH))
> +		p = ops->xmo_rx_hash;
> +out:
> +	up_read(&bpf_devs_lock);
> +
> +	return p;
> +}
> +
>   static int __init bpf_offload_init(void)
>   {
>   	int err;
> diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
> index 203d8cfeda70..e61fe0472b9b 100644
> --- a/kernel/bpf/verifier.c
> +++ b/kernel/bpf/verifier.c
> @@ -15479,12 +15479,35 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
>   			    struct bpf_insn *insn_buf, int insn_idx, int *cnt)
>   {
>   	const struct bpf_kfunc_desc *desc;
> +	void *xdp_kfunc;
>   
>   	if (!insn->imm) {
>   		verbose(env, "invalid kernel function call not eliminated in verifier pass\n");
>   		return -EINVAL;
>   	}
>   
> +	*cnt = 0;
> +
> +	if (xdp_is_metadata_kfunc_id(insn->imm)) {
> +		if (!bpf_prog_is_dev_bound(env->prog->aux)) {

The "xdp_is_metadata_kfunc_id() && (!bpf_prog_is_dev_bound() || 
bpf_prog_is_offloaded())" test should have been done much earlier in 
add_kfunc_call(). Then the later stage of the verifier does not have to keep 
worrying about it like here.

nit. may be rename xdp_is_metadata_kfunc_id() to bpf_dev_bound_kfunc_id() and 
hide the "!bpf_prog_is_dev_bound() || bpf_prog_is_offloaded()" test into 
bpf_dev_bound_kfunc_check(&env->log, env->prog).

The change in fixup_kfunc_call could then become:

	if (bpf_dev_bound_kfunc_id(insn->imm)) {
		xdp_kfunc = bpf_dev_bound_resolve_kfunc(env->prog, insn->imm);
		/* ... */
	}

> +			verbose(env, "metadata kfuncs require device-bound program\n");
> +			return -EINVAL;
> +		}
> +
> +		if (bpf_prog_is_offloaded(env->prog->aux)) {
> +			verbose(env, "metadata kfuncs can't be offloaded\n");
> +			return -EINVAL;
> +		}
> +
> +		xdp_kfunc = bpf_dev_bound_resolve_kfunc(env->prog, insn->imm);
> +		if (xdp_kfunc) {
> +			insn->imm = BPF_CALL_IMM(xdp_kfunc);
> +			return 0;
> +		}
> +
> +		/* fallback to default kfunc when not supported by netdev */
> +	}
> +