[dpdk-dev] [PATCH v8 1/4] vhost: abstract and reorganize async split ring code

[Hu, Jiayu]

Reviewed-by: Jiayu Hu <jiayu.hu at intel.com>

> -----Original Message-----
> From: Jiang, Cheng1 <cheng1.jiang at intel.com>
> Sent: Monday, April 19, 2021 4:51 PM
> To: maxime.coquelin at redhat.com; Xia, Chenbo <chenbo.xia at intel.com>
> Cc: dev at dpdk.org; Hu, Jiayu <jiayu.hu at intel.com>; Yang, YvonneX
> <yvonnex.yang at intel.com>; Wang, Yinan <yinan.wang at intel.com>; Liu,
> Yong <yong.liu at intel.com>; Jiang, Cheng1 <cheng1.jiang at intel.com>
> Subject: [PATCH v8 1/4] vhost: abstract and reorganize async split ring code
> 
> This patch puts some codes of async vhost split ring into inline
> functions to improve the readability of the code. And, it changes
> the pointer index style of iterator to make the code more concise.
> 
> Signed-off-by: Cheng Jiang <Cheng1.jiang at intel.com>
> Reviewed-by: Maxime Coquelin <maxime.coquelin at redhat.com>
> ---
>  lib/librte_vhost/virtio_net.c | 132 +++++++++++++++++-----------------
>  1 file changed, 66 insertions(+), 66 deletions(-)
> 
> diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
> index ff3987860..438bdafd1 100644
> --- a/lib/librte_vhost/virtio_net.c
> +++ b/lib/librte_vhost/virtio_net.c
> @@ -1458,6 +1458,22 @@ virtio_dev_rx_async_get_info_idx(uint16_t
> pkts_idx,
>  		(vq_size - n_inflight + pkts_idx) & (vq_size - 1);
>  }
> 
> +static __rte_always_inline void
> +store_dma_desc_info_split(struct vring_used_elem *s_ring, struct
> vring_used_elem *d_ring,
> +		uint16_t ring_size, uint16_t s_idx, uint16_t d_idx, uint16_t
> count)
> +{
> +	uint16_t elem_size = sizeof(struct vring_used_elem);
> +
> +	if (d_idx + count <= ring_size) {
> +		rte_memcpy(d_ring + d_idx, s_ring + s_idx, count *
> elem_size);
> +	} else {
> +		uint16_t size = ring_size - d_idx;
> +
> +		rte_memcpy(d_ring + d_idx, s_ring + s_idx, size * elem_size);
> +		rte_memcpy(d_ring, s_ring + s_idx + size, (count - size) *
> elem_size);
> +	}
> +}
> +
>  static __rte_noinline uint32_t
>  virtio_dev_rx_async_submit_split(struct virtio_net *dev,
>  	struct vhost_virtqueue *vq, uint16_t queue_id,
> @@ -1474,10 +1490,9 @@ virtio_dev_rx_async_submit_split(struct
> virtio_net *dev,
>  	struct rte_vhost_async_desc tdes[MAX_PKT_BURST];
>  	struct iovec *src_iovec = vec_pool;
>  	struct iovec *dst_iovec = vec_pool + (VHOST_MAX_ASYNC_VEC >> 1);
> -	struct rte_vhost_iov_iter *src_it = it_pool;
> -	struct rte_vhost_iov_iter *dst_it = it_pool + 1;
>  	uint16_t slot_idx = 0;
>  	uint16_t segs_await = 0;
> +	uint16_t iovec_idx = 0, it_idx = 0;
>  	struct async_inflight_info *pkts_info = vq->async_pkts_info;
>  	uint32_t n_pkts = 0, pkt_err = 0;
>  	uint32_t num_async_pkts = 0, num_done_pkts = 0;
> @@ -1511,29 +1526,30 @@ virtio_dev_rx_async_submit_split(struct
> virtio_net *dev,
>  			dev->vid, vq->last_avail_idx,
>  			vq->last_avail_idx + num_buffers);
> 
> -		if (async_mbuf_to_desc(dev, vq, pkts[pkt_idx],
> -				buf_vec, nr_vec, num_buffers,
> -				src_iovec, dst_iovec, src_it, dst_it) < 0) {
> +		if (async_mbuf_to_desc(dev, vq, pkts[pkt_idx], buf_vec,
> nr_vec, num_buffers,
> +				&src_iovec[iovec_idx], &dst_iovec[iovec_idx],
> +				&it_pool[it_idx], &it_pool[it_idx + 1]) < 0) {
>  			vq->shadow_used_idx -= num_buffers;
>  			break;
>  		}
> 
>  		slot_idx = (vq->async_pkts_idx + num_async_pkts) &
>  			(vq->size - 1);
> -		if (src_it->count) {
> +		if (it_pool[it_idx].count) {
>  			uint16_t from, to;
> 
> -			async_fill_desc(&tdes[pkt_burst_idx++], src_it, dst_it);
> +			async_fill_desc(&tdes[pkt_burst_idx++],
> +				&it_pool[it_idx], &it_pool[it_idx + 1]);
>  			pkts_info[slot_idx].descs = num_buffers;
>  			pkts_info[slot_idx].mbuf = pkts[pkt_idx];
>  			async_pkts_log[num_async_pkts].pkt_idx = pkt_idx;
>  			async_pkts_log[num_async_pkts++].last_avail_idx =
>  				vq->last_avail_idx;
> -			src_iovec += src_it->nr_segs;
> -			dst_iovec += dst_it->nr_segs;
> -			src_it += 2;
> -			dst_it += 2;
> -			segs_await += src_it->nr_segs;
> +
> +			iovec_idx += it_pool[it_idx].nr_segs;
> +			it_idx += 2;
> +
> +			segs_await += it_pool[it_idx].nr_segs;
> 
>  			/**
>  			 * recover shadow used ring and keep DMA-occupied
> @@ -1541,23 +1557,10 @@ virtio_dev_rx_async_submit_split(struct
> virtio_net *dev,
>  			 */
>  			from = vq->shadow_used_idx - num_buffers;
>  			to = vq->async_desc_idx & (vq->size - 1);
> -			if (num_buffers + to <= vq->size) {
> -				rte_memcpy(&vq->async_descs_split[to],
> -						&vq-
> >shadow_used_split[from],
> -						num_buffers *
> -						sizeof(struct
> vring_used_elem));
> -			} else {
> -				int size = vq->size - to;
> -
> -				rte_memcpy(&vq->async_descs_split[to],
> -						&vq-
> >shadow_used_split[from],
> -						size *
> -						sizeof(struct
> vring_used_elem));
> -				rte_memcpy(vq->async_descs_split,
> -						&vq-
> >shadow_used_split[from +
> -						size], (num_buffers - size) *
> -					   sizeof(struct vring_used_elem));
> -			}
> +
> +			store_dma_desc_info_split(vq->shadow_used_split,
> +					vq->async_descs_split, vq->size, from,
> to, num_buffers);
> +
>  			vq->async_desc_idx += num_buffers;
>  			vq->shadow_used_idx -= num_buffers;
>  		} else
> @@ -1575,10 +1578,9 @@ virtio_dev_rx_async_submit_split(struct
> virtio_net *dev,
>  			BUF_VECTOR_MAX))) {
>  			n_pkts = vq->async_ops.transfer_data(dev->vid,
>  					queue_id, tdes, 0, pkt_burst_idx);
> -			src_iovec = vec_pool;
> -			dst_iovec = vec_pool + (VHOST_MAX_ASYNC_VEC >>
> 1);
> -			src_it = it_pool;
> -			dst_it = it_pool + 1;
> +			iovec_idx = 0;
> +			it_idx = 0;
> +
>  			segs_await = 0;
>  			vq->async_pkts_inflight_n += n_pkts;
> 
> @@ -1639,6 +1641,36 @@ virtio_dev_rx_async_submit_split(struct
> virtio_net *dev,
>  	return pkt_idx;
>  }
> 
> +static __rte_always_inline void
> +write_back_completed_descs_split(struct vhost_virtqueue *vq, uint16_t
> n_descs)
> +{
> +	uint16_t nr_left = n_descs;
> +	uint16_t nr_copy;
> +	uint16_t to, from;
> +
> +	do {
> +		from = vq->last_async_desc_idx & (vq->size - 1);
> +		nr_copy = nr_left + from <= vq->size ? nr_left : vq->size - from;
> +		to = vq->last_used_idx & (vq->size - 1);
> +
> +		if (to + nr_copy <= vq->size) {
> +			rte_memcpy(&vq->used->ring[to], &vq-
> >async_descs_split[from],
> +					nr_copy * sizeof(struct
> vring_used_elem));
> +		} else {
> +			uint16_t size = vq->size - to;
> +
> +			rte_memcpy(&vq->used->ring[to], &vq-
> >async_descs_split[from],
> +					size * sizeof(struct vring_used_elem));
> +			rte_memcpy(&vq->used->ring[0], &vq-
> >async_descs_split[from + size],
> +					(nr_copy - size) * sizeof(struct
> vring_used_elem));
> +		}
> +
> +		vq->last_async_desc_idx += nr_copy;
> +		vq->last_used_idx += nr_copy;
> +		nr_left -= nr_copy;
> +	} while (nr_left > 0);
> +}
> +
>  uint16_t rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id,
>  		struct rte_mbuf **pkts, uint16_t count)
>  {
> @@ -1695,39 +1727,7 @@ uint16_t rte_vhost_poll_enqueue_completed(int
> vid, uint16_t queue_id,
>  	vq->async_pkts_inflight_n -= n_pkts_put;
> 
>  	if (likely(vq->enabled && vq->access_ok)) {
> -		uint16_t nr_left = n_descs;
> -		uint16_t nr_copy;
> -		uint16_t to;
> -
> -		/* write back completed descriptors to used ring */
> -		do {
> -			from = vq->last_async_desc_idx & (vq->size - 1);
> -			nr_copy = nr_left + from <= vq->size ? nr_left :
> -				vq->size - from;
> -			to = vq->last_used_idx & (vq->size - 1);
> -
> -			if (to + nr_copy <= vq->size) {
> -				rte_memcpy(&vq->used->ring[to],
> -						&vq-
> >async_descs_split[from],
> -						nr_copy *
> -						sizeof(struct
> vring_used_elem));
> -			} else {
> -				uint16_t size = vq->size - to;
> -
> -				rte_memcpy(&vq->used->ring[to],
> -						&vq-
> >async_descs_split[from],
> -						size *
> -						sizeof(struct
> vring_used_elem));
> -				rte_memcpy(vq->used->ring,
> -						&vq->async_descs_split[from
> +
> -						size], (nr_copy - size) *
> -						sizeof(struct
> vring_used_elem));
> -			}
> -
> -			vq->last_async_desc_idx += nr_copy;
> -			vq->last_used_idx += nr_copy;
> -			nr_left -= nr_copy;
> -		} while (nr_left > 0);
> +		write_back_completed_descs_split(vq, n_descs);
> 
>  		__atomic_add_fetch(&vq->used->idx, n_descs,
> __ATOMIC_RELEASE);
>  		vhost_vring_call_split(dev, vq);
> --
> 2.29.2