From: Simon Horman <horms@xxxxxxxxxx>
Date: Thu, 31 Jul 2025 14:35:57 +0100
> On Wed, Jul 30, 2025 at 06:07:15PM +0200, Alexander Lobakin wrote:
>> Use libeth XDP infra to support running XDP program on Rx polling.
>> This includes all of the possible verdicts/actions.
>> XDP Tx queues are cleaned only in "lazy" mode when there are less than
>> 1/4 free descriptors left on the ring. libeth helper macros to define
>> driver-specific XDP functions make sure the compiler could uninline
>> them when needed.
>> Use __LIBETH_WORD_ACCESS to parse descriptors more efficiently when
>> applicable. It really gives some good boosts and code size reduction
>> on x86_64.
>>
>> Co-developed-by: Michal Kubiak <michal.kubiak@xxxxxxxxx>
>> Signed-off-by: Michal Kubiak <michal.kubiak@xxxxxxxxx>
>> Signed-off-by: Alexander Lobakin <aleksander.lobakin@xxxxxxxxx>
>
> ...
>
>> diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
>
> ...
>
>> @@ -3127,14 +3125,12 @@ static bool idpf_rx_process_skb_fields(struct sk_buff *skb,
>> return !__idpf_rx_process_skb_fields(rxq, skb, xdp->desc);
>> }
>>
>> -static void
>> -idpf_xdp_run_pass(struct libeth_xdp_buff *xdp, struct napi_struct *napi,
>> - struct libeth_rq_napi_stats *ss,
>> - const struct virtchnl2_rx_flex_desc_adv_nic_3 *desc)
>> -{
>> - libeth_xdp_run_pass(xdp, NULL, napi, ss, desc, NULL,
>> - idpf_rx_process_skb_fields);
>> -}
>> +LIBETH_XDP_DEFINE_START();
>> +LIBETH_XDP_DEFINE_RUN(static idpf_xdp_run_pass, idpf_xdp_run_prog,
>> + idpf_xdp_tx_flush_bulk, idpf_rx_process_skb_fields);
>> +LIBETH_XDP_DEFINE_FINALIZE(static idpf_xdp_finalize_rx, idpf_xdp_tx_flush_bulk,
>> + idpf_xdp_tx_finalize);
>> +LIBETH_XDP_DEFINE_END();
>>
>> /**
>> * idpf_rx_hsplit_wa - handle header buffer overflows and split errors
>> @@ -3222,7 +3218,10 @@ static int idpf_rx_splitq_clean(struct idpf_rx_queue *rxq, int budget)
>> struct libeth_rq_napi_stats rs = { };
>> u16 ntc = rxq->next_to_clean;
>> LIBETH_XDP_ONSTACK_BUFF(xdp);
>> + LIBETH_XDP_ONSTACK_BULK(bq);
>>
>> + libeth_xdp_tx_init_bulk(&bq, rxq->xdp_prog, rxq->xdp_rxq.dev,
>> + rxq->xdpsqs, rxq->num_xdp_txq);
>> libeth_xdp_init_buff(xdp, &rxq->xdp, &rxq->xdp_rxq);
>>
>> /* Process Rx packets bounded by budget */
>> @@ -3318,11 +3317,13 @@ static int idpf_rx_splitq_clean(struct idpf_rx_queue *rxq, int budget)
>> if (!idpf_rx_splitq_is_eop(rx_desc) || unlikely(!xdp->data))
>> continue;
>>
>> - idpf_xdp_run_pass(xdp, rxq->napi, &rs, rx_desc);
>> + idpf_xdp_run_pass(xdp, &bq, rxq->napi, &rs, rx_desc);
>> }
>>
>> rxq->next_to_clean = ntc;
>> +
>> libeth_xdp_save_buff(&rxq->xdp, xdp);
>> + idpf_xdp_finalize_rx(&bq);
>
> This will call __libeth_xdp_finalize_rx(), which calls rcu_read_unlock().
> But there doesn't seem to be a corresponding call to rcu_read_lock()
>
> Flagged by Sparse.
It's false-positive, rcu_read_lock() is called in tx_init_bulk().
>
>>
>> u64_stats_update_begin(&rxq->stats_sync);
>> u64_stats_add(&rxq->q_stats.packets, rs.packets);
Thanks,
Olek
