DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Liu, Yong" <yong.liu@intel.com>
To: "Jiang, Cheng1" <cheng1.jiang@intel.com>,
	"maxime.coquelin@redhat.com" <maxime.coquelin@redhat.com>,
	"Xia, Chenbo" <chenbo.xia@intel.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>, "Hu, Jiayu" <jiayu.hu@intel.com>,
	"Yang, YvonneX" <yvonnex.yang@intel.com>,
	"Wang, Yinan" <yinan.wang@intel.com>,
	"Jiang, Cheng1" <cheng1.jiang@intel.com>
Subject: Re: [dpdk-dev] [PATCH v2] vhost: add support for packed ring in async vhost
Date: Wed, 24 Mar 2021 09:19:01 +0000	[thread overview]
Message-ID: <2c90bd07cdbb49b39635a1301c48bd7a@intel.com> (raw)
In-Reply-To: <20210322061517.19013-1-Cheng1.jiang@intel.com>



> -----Original Message-----
> From: dev <dev-bounces@dpdk.org> On Behalf Of Cheng Jiang
> Sent: Monday, March 22, 2021 2:15 PM
> To: maxime.coquelin@redhat.com; Xia, Chenbo <chenbo.xia@intel.com>
> Cc: dev@dpdk.org; Hu, Jiayu <jiayu.hu@intel.com>; Yang, YvonneX
> <yvonnex.yang@intel.com>; Wang, Yinan <yinan.wang@intel.com>; Jiang,
> Cheng1 <cheng1.jiang@intel.com>
> Subject: [dpdk-dev] [PATCH v2] vhost: add support for packed ring in async
> vhost
> 
> For now async vhost data path only supports split ring structure. In
> order to make async vhost compatible with virtio 1.1 spec this patch
> enables packed ring in async vhost data path.
> 
> Signed-off-by: Cheng Jiang <Cheng1.jiang@intel.com>
> ---
> v2:
>   * fix wrong buffer index in rte_vhost_poll_enqueue_completed()
>   * add async_buffers_packed memory free in vhost_free_async_mem()
> 
>  lib/librte_vhost/rte_vhost_async.h |   1 +
>  lib/librte_vhost/vhost.c           |  24 +-
>  lib/librte_vhost/vhost.h           |   7 +-
>  lib/librte_vhost/virtio_net.c      | 447 +++++++++++++++++++++++++++--
>  4 files changed, 441 insertions(+), 38 deletions(-)
> 
> diff --git a/lib/librte_vhost/rte_vhost_async.h
> b/lib/librte_vhost/rte_vhost_async.h
> index c855ff875..6faa31f5a 100644
> --- a/lib/librte_vhost/rte_vhost_async.h
> +++ b/lib/librte_vhost/rte_vhost_async.h
> @@ -89,6 +89,7 @@ struct rte_vhost_async_channel_ops {
>  struct async_inflight_info {
>  	struct rte_mbuf *mbuf;
>  	uint16_t descs; /* num of descs inflight */
> +	uint16_t nr_buffers; /* num of buffers inflight for packed ring */
>  };
> 
>  /**
> diff --git a/lib/librte_vhost/vhost.c b/lib/librte_vhost/vhost.c
> index 52ab93d1e..51b44d6f2 100644
> --- a/lib/librte_vhost/vhost.c
> +++ b/lib/librte_vhost/vhost.c
> @@ -330,15 +330,20 @@ vhost_free_async_mem(struct vhost_virtqueue
> *vq)
>  {
>  	if (vq->async_pkts_info)
>  		rte_free(vq->async_pkts_info);
> -	if (vq->async_descs_split)
> +	if (vq->async_buffers_packed) {
> +		rte_free(vq->async_buffers_packed);
> +		vq->async_buffers_packed = NULL;
> +	} else {
>  		rte_free(vq->async_descs_split);
> +		vq->async_descs_split = NULL;
> +	}
> +
>  	if (vq->it_pool)
>  		rte_free(vq->it_pool);
>  	if (vq->vec_pool)
>  		rte_free(vq->vec_pool);
> 
>  	vq->async_pkts_info = NULL;
> -	vq->async_descs_split = NULL;
>  	vq->it_pool = NULL;
>  	vq->vec_pool = NULL;
>  }
> @@ -1603,9 +1608,9 @@ int rte_vhost_async_channel_register(int vid,
> uint16_t queue_id,
>  		return -1;
> 
>  	/* packed queue is not supported */
> -	if (unlikely(vq_is_packed(dev) || !f.async_inorder)) {
> +	if (unlikely(!f.async_inorder)) {
>  		VHOST_LOG_CONFIG(ERR,
> -			"async copy is not supported on packed queue or
> non-inorder mode "
> +			"async copy is not supported on non-inorder mode "
>  			"(vid %d, qid: %d)\n", vid, queue_id);
>  		return -1;
>  	}
> @@ -1643,10 +1648,17 @@ int rte_vhost_async_channel_register(int vid,
> uint16_t queue_id,
>  	vq->vec_pool = rte_malloc_socket(NULL,
>  			VHOST_MAX_ASYNC_VEC * sizeof(struct iovec),
>  			RTE_CACHE_LINE_SIZE, node);
> -	vq->async_descs_split = rte_malloc_socket(NULL,
> +	if (vq_is_packed(dev)) {
> +		vq->async_buffers_packed = rte_malloc_socket(NULL,
> +			vq->size * sizeof(struct vring_used_elem_packed),
> +			RTE_CACHE_LINE_SIZE, node);
> +	} else {
> +		vq->async_descs_split = rte_malloc_socket(NULL,
>  			vq->size * sizeof(struct vring_used_elem),
>  			RTE_CACHE_LINE_SIZE, node);
> -	if (!vq->async_descs_split || !vq->async_pkts_info ||
> +	}
> +
> +	if (!vq->async_pkts_info ||
>  		!vq->it_pool || !vq->vec_pool) {
>  		vhost_free_async_mem(vq);
>  		VHOST_LOG_CONFIG(ERR,
> diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
> index 658f6fc28..d6324fbf8 100644
> --- a/lib/librte_vhost/vhost.h
> +++ b/lib/librte_vhost/vhost.h
> @@ -206,9 +206,14 @@ struct vhost_virtqueue {
>  	uint16_t	async_pkts_idx;
>  	uint16_t	async_pkts_inflight_n;
>  	uint16_t	async_last_pkts_n;
> -	struct vring_used_elem  *async_descs_split;
> +	union {
> +		struct vring_used_elem  *async_descs_split;
> +		struct vring_used_elem_packed *async_buffers_packed;
> +	};
>  	uint16_t async_desc_idx;
> +	uint16_t async_packed_buffer_idx;
>  	uint16_t last_async_desc_idx;
> +	uint16_t last_async_buffer_idx;
> 
>  	/* vq async features */
>  	bool		async_inorder;
> diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
> index 583bf379c..fa8c4f4fe 100644
> --- a/lib/librte_vhost/virtio_net.c
> +++ b/lib/librte_vhost/virtio_net.c
> @@ -363,8 +363,7 @@
> vhost_shadow_dequeue_single_packed_inorder(struct vhost_virtqueue *vq,
>  }
> 
>  static __rte_always_inline void
> -vhost_shadow_enqueue_single_packed(struct virtio_net *dev,
> -				   struct vhost_virtqueue *vq,
> +vhost_shadow_enqueue_packed(struct vhost_virtqueue *vq,
>  				   uint32_t len[],
>  				   uint16_t id[],
>  				   uint16_t count[],
> @@ -382,6 +381,17 @@ vhost_shadow_enqueue_single_packed(struct
> virtio_net *dev,
>  		vq->shadow_aligned_idx += count[i];
>  		vq->shadow_used_idx++;
>  	}
> +}
> +
> +static __rte_always_inline void
> +vhost_shadow_enqueue_single_packed(struct virtio_net *dev,
> +				   struct vhost_virtqueue *vq,
> +				   uint32_t len[],
> +				   uint16_t id[],
> +				   uint16_t count[],
> +				   uint16_t num_buffers)
> +{
> +	vhost_shadow_enqueue_packed(vq, len, id, count, num_buffers);
> 
>  	if (vq->shadow_aligned_idx >= PACKED_BATCH_SIZE) {
>  		do_data_copy_enqueue(dev, vq);
> @@ -1633,12 +1643,343 @@ virtio_dev_rx_async_submit_split(struct
> virtio_net *dev,
>  	return pkt_idx;
>  }
> 
> +static __rte_always_inline int
> +vhost_enqueue_async_single_packed(struct virtio_net *dev,
> +			    struct vhost_virtqueue *vq,
> +			    struct rte_mbuf *pkt,
> +			    struct buf_vector *buf_vec,
> +			    uint16_t *nr_descs,
> +			    uint16_t *nr_buffers,
> +			    struct iovec *src_iovec, struct iovec *dst_iovec,
> +			    struct rte_vhost_iov_iter *src_it,
> +			    struct rte_vhost_iov_iter *dst_it)
> +{
> +	uint16_t nr_vec = 0;
> +	uint16_t avail_idx = vq->last_avail_idx;
> +	uint16_t max_tries, tries = 0;
> +	uint16_t buf_id = 0;
> +	uint32_t len = 0;
> +	uint16_t desc_count;
> +	uint32_t size = pkt->pkt_len + sizeof(struct
> virtio_net_hdr_mrg_rxbuf);
> +	uint32_t buffer_len[vq->size];
> +	uint16_t buffer_buf_id[vq->size];
> +	uint16_t buffer_desc_count[vq->size];
> +	*nr_buffers = 0;
> +
> +	if (rxvq_is_mergeable(dev))
> +		max_tries = vq->size - 1;
> +	else
> +		max_tries = 1;
> +
> +	while (size > 0) {
> +		/*
> +		 * if we tried all available ring items, and still
> +		 * can't get enough buf, it means something abnormal
> +		 * happened.
> +		 */
> +		if (unlikely(++tries > max_tries))
> +			return -1;
> +
> +		if (unlikely(fill_vec_buf_packed(dev, vq,
> +						avail_idx, &desc_count,
> +						buf_vec, &nr_vec,
> +						&buf_id, &len,
> +						VHOST_ACCESS_RW) < 0))
> +			return -1;
> +
> +		len = RTE_MIN(len, size);
> +		size -= len;
> +
> +		buffer_len[*nr_buffers] = len;
> +		buffer_buf_id[*nr_buffers] = buf_id;
> +		buffer_desc_count[*nr_buffers] = desc_count;
> +		*nr_buffers += 1;
> +
> +		*nr_descs += desc_count;
> +		avail_idx += desc_count;
> +		if (avail_idx >= vq->size)
> +			avail_idx -= vq->size;
> +	}
> +
> +	if (async_mbuf_to_desc(dev, vq, pkt, buf_vec, nr_vec, *nr_buffers,
> +		src_iovec, dst_iovec, src_it, dst_it) < 0)
> +		return -1;
> +
> +	vhost_shadow_enqueue_packed(vq, buffer_len, buffer_buf_id,
> +					   buffer_desc_count, *nr_buffers);
> +
> +	return 0;
> +}
> +
> +static __rte_always_inline int16_t
> +virtio_dev_rx_async_single_packed(struct virtio_net *dev,
> +			    struct vhost_virtqueue *vq,
> +			    struct rte_mbuf *pkt,
> +			    uint16_t *nr_descs, uint16_t *nr_buffers,
> +			    struct iovec *src_iovec, struct iovec *dst_iovec,
> +			    struct rte_vhost_iov_iter *src_it,
> +			    struct rte_vhost_iov_iter *dst_it)
> +{
> +	struct buf_vector buf_vec[BUF_VECTOR_MAX];
> +	*nr_descs = 0;
> +	*nr_buffers = 0;
> +
> +	if (unlikely(vhost_enqueue_async_single_packed(dev, vq, pkt,
> buf_vec,
> +						 nr_descs,
> +						 nr_buffers,
> +						 src_iovec, dst_iovec,
> +						 src_it, dst_it) < 0)) {
> +		VHOST_LOG_DATA(DEBUG,
> +				"(%d) failed to get enough desc from vring\n",
> +				dev->vid);
> +		return -1;
> +	}
> +
> +	VHOST_LOG_DATA(DEBUG, "(%d) current index %d | end
> index %d\n",
> +			dev->vid, vq->last_avail_idx,
> +			vq->last_avail_idx + *nr_descs);
> +
> +	return 0;
> +}
> +
> +static __rte_noinline uint32_t
> +virtio_dev_rx_async_submit_packed(struct virtio_net *dev,
> +	struct vhost_virtqueue *vq, uint16_t queue_id,
> +	struct rte_mbuf **pkts, uint32_t count,
> +	struct rte_mbuf **comp_pkts, uint32_t *comp_count)
> +{

Hi Cheng,
There're some common parts in virtio_dev_rx_async_submit_packed and virtio_dev_rx_async_submit_split. 
We can abstract some functions for those common parts which can bring more clarity.

Also this patch may be too huge for reviewing, please separate it into few parts for better understanding. 

Thanks,
Marvin

> +	uint32_t pkt_idx = 0, pkt_burst_idx = 0;
> +	uint16_t num_buffers;
> +	uint16_t num_desc;
> +
> +	struct rte_vhost_iov_iter *it_pool = vq->it_pool;
> +	struct iovec *vec_pool = vq->vec_pool;
> +	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;
> +	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;
> +	struct {
> +		uint16_t pkt_idx;
> +		uint16_t last_avail_idx;
> +	} async_pkts_log[MAX_PKT_BURST];
> +
> +	rte_prefetch0(&vq->desc[vq->last_avail_idx & (vq->size - 1)]);
> +
> +	for (pkt_idx = 0; pkt_idx < count; pkt_idx++) {
> +		if (unlikely(virtio_dev_rx_async_single_packed(dev, vq,
> +						pkts[pkt_idx],
> +						&num_desc, &num_buffers,
> +						src_iovec, dst_iovec,
> +						src_it, dst_it) < 0)) {
> +			break;
> +		}
> +
> +		VHOST_LOG_DATA(DEBUG, "(%d) current index %d | end
> index %d\n",
> +			dev->vid, vq->last_avail_idx,
> +			vq->last_avail_idx + num_desc);
> +
> +		slot_idx = (vq->async_pkts_idx + num_async_pkts) &
> +			(vq->size - 1);
> +		if (src_it->count) {
> +			uint16_t from, to;
> +
> +			async_fill_desc(&tdes[pkt_burst_idx++], src_it, dst_it);
> +			pkts_info[slot_idx].descs = num_desc;
> +			pkts_info[slot_idx].nr_buffers = 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;
> +
> +			/**
> +			 * recover shadow used ring and keep DMA-occupied
> +			 * descriptors.
> +			 */
> +			from = vq->shadow_used_idx - num_buffers;
> +			to = vq->async_packed_buffer_idx & (vq->size - 1);
> +			if (num_buffers + to <= vq->size) {
> +				rte_memcpy(&vq->async_buffers_packed[to],
> +					&vq->shadow_used_packed[from],
> +					num_buffers *
> +					sizeof(struct
> vring_used_elem_packed));
> +			} else {
> +				int size = vq->size - to;
> +
> +				rte_memcpy(&vq->async_buffers_packed[to],
> +					&vq->shadow_used_packed[from],
> +					size *
> +					sizeof(struct
> vring_used_elem_packed));
> +				rte_memcpy(vq->async_buffers_packed,
> +					&vq->shadow_used_packed[from +
> +					size], (num_buffers - size) *
> +					sizeof(struct
> vring_used_elem_packed));
> +			}
> +			vq->async_packed_buffer_idx += num_buffers;
> +			vq->shadow_used_idx -= num_buffers;
> +		} else
> +			comp_pkts[num_done_pkts++] = pkts[pkt_idx];
> +
> +		vq_inc_last_avail_packed(vq, num_desc);
> +
> +		/*
> +		 * conditions to trigger async device transfer:
> +		 * - buffered packet number reaches transfer threshold
> +		 * - unused async iov number is less than max vhost vector
> +		 */
> +		if (unlikely(pkt_burst_idx >=
> VHOST_ASYNC_BATCH_THRESHOLD ||
> +			((VHOST_MAX_ASYNC_VEC >> 1) - segs_await <
> +			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;
> +			segs_await = 0;
> +			vq->async_pkts_inflight_n += n_pkts;
> +
> +			if (unlikely(n_pkts < pkt_burst_idx)) {
> +				/*
> +				 * log error packets number here and do
> actual
> +				 * error processing when applications poll
> +				 * completion
> +				 */
> +				pkt_err = pkt_burst_idx - n_pkts;
> +				pkt_burst_idx = 0;
> +				break;
> +			}
> +
> +			pkt_burst_idx = 0;
> +		}
> +	}
> +
> +	if (pkt_burst_idx) {
> +		n_pkts = vq->async_ops.transfer_data(dev->vid,
> +				queue_id, tdes, 0, pkt_burst_idx);
> +		vq->async_pkts_inflight_n += n_pkts;
> +
> +		if (unlikely(n_pkts < pkt_burst_idx))
> +			pkt_err = pkt_burst_idx - n_pkts;
> +	}
> +
> +	do_data_copy_enqueue(dev, vq);
> +
> +	if (unlikely(pkt_err)) {
> +		uint16_t num_buffers = 0;
> +
> +		num_async_pkts -= pkt_err;
> +		/* calculate the sum of descriptors of DMA-error packets. */
> +		while (pkt_err-- > 0) {
> +			num_buffers +=
> +				pkts_info[slot_idx & (vq->size - 1)].nr_buffers;
> +			slot_idx--;
> +		}
> +		vq->async_packed_buffer_idx -= num_buffers;
> +		/* recover shadow used ring and available ring */
> +		vq->shadow_used_idx -= (vq->last_avail_idx -
> +
> 	async_pkts_log[num_async_pkts].last_avail_idx -
> +				num_buffers);

Could it possible that vq->last_avail_idx smaller than async_pkts_log[num_async_pkts].last_avail_idx when operations near the ring's boundary? 

> +		vq->last_avail_idx =
> +			async_pkts_log[num_async_pkts].last_avail_idx;
> +		pkt_idx = async_pkts_log[num_async_pkts].pkt_idx;
> +		num_done_pkts = pkt_idx - num_async_pkts;
> +	}
> +
> +	vq->async_pkts_idx += num_async_pkts;
> +	*comp_count = num_done_pkts;
> +
> +	if (likely(vq->shadow_used_idx)) {
> +		vhost_flush_enqueue_shadow_packed(dev, vq);
> +		vhost_vring_call_packed(dev, vq);
> +	}
> +
> +	return pkt_idx;
> +}
> +
> +static __rte_always_inline void
> +vhost_update_used_packed(struct virtio_net *dev,
> +				  struct vhost_virtqueue *vq,
> +				  struct vring_used_elem_packed
> *shadow_ring,
> +				  uint16_t count)
> +{
> +	if (count == 0)
> +		return;
> +	int i;
> +	uint16_t used_idx = vq->last_used_idx;
> +	uint16_t head_idx = vq->last_used_idx;
> +	uint16_t head_flags = 0;
> +
> +	/* Split loop in two to save memory barriers */
> +	for (i = 0; i < count; i++) {
> +		vq->desc_packed[used_idx].id = shadow_ring[i].id;
> +		vq->desc_packed[used_idx].len = shadow_ring[i].len;
> +
> +		used_idx += shadow_ring[i].count;
> +		if (used_idx >= vq->size)
> +			used_idx -= vq->size;
> +	}
> +
> +	/* The ordering for storing desc flags needs to be enforced. */
> +	rte_atomic_thread_fence(__ATOMIC_RELEASE);
> +
> +	for (i = 0; i < count; i++) {
> +		uint16_t flags;
> +
> +		if (vq->shadow_used_packed[i].len)
> +			flags = VRING_DESC_F_WRITE;
> +		else
> +			flags = 0;
> +
> +		if (vq->used_wrap_counter) {
> +			flags |= VRING_DESC_F_USED;
> +			flags |= VRING_DESC_F_AVAIL;
> +		} else {
> +			flags &= ~VRING_DESC_F_USED;
> +			flags &= ~VRING_DESC_F_AVAIL;
> +		}
> +
> +		if (i > 0) {
> +			vq->desc_packed[vq->last_used_idx].flags = flags;
> +
> +			vhost_log_cache_used_vring(dev, vq,
> +					vq->last_used_idx *
> +					sizeof(struct vring_packed_desc),
> +					sizeof(struct vring_packed_desc));
> +		} else {
> +			head_idx = vq->last_used_idx;
> +			head_flags = flags;
> +		}
> +
> +		vq_inc_last_used_packed(vq, shadow_ring[i].count);
> +	}
> +
> +	vq->desc_packed[head_idx].flags = head_flags;
> +
> +	vhost_log_cache_used_vring(dev, vq,
> +				head_idx *
> +				sizeof(struct vring_packed_desc),
> +				sizeof(struct vring_packed_desc));
> +
> +	vhost_log_cache_sync(dev, vq);
> +}
> +
>  uint16_t rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id,
>  		struct rte_mbuf **pkts, uint16_t count)
>  {
>  	struct virtio_net *dev = get_device(vid);
>  	struct vhost_virtqueue *vq;
> -	uint16_t n_pkts_cpl = 0, n_pkts_put = 0, n_descs = 0;
> +	uint16_t n_pkts_cpl = 0, n_pkts_put = 0, n_descs = 0, n_buffers = 0;
>  	uint16_t start_idx, pkts_idx, vq_size;
>  	struct async_inflight_info *pkts_info;
>  	uint16_t from, i;
> @@ -1680,53 +2021,96 @@ uint16_t
> rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id,
>  		goto done;
>  	}
> 
> -	for (i = 0; i < n_pkts_put; i++) {
> -		from = (start_idx + i) & (vq_size - 1);
> -		n_descs += pkts_info[from].descs;
> -		pkts[i] = pkts_info[from].mbuf;
> +	if (vq_is_packed(dev)) {
> +		for (i = 0; i < n_pkts_put; i++) {
> +			from = (start_idx + i) & (vq_size - 1);
> +			n_buffers += pkts_info[from].nr_buffers;
> +			pkts[i] = pkts_info[from].mbuf;
> +		}
> +	} else {
> +		for (i = 0; i < n_pkts_put; i++) {
> +			from = (start_idx + i) & (vq_size - 1);
> +			n_descs += pkts_info[from].descs;
> +			pkts[i] = pkts_info[from].mbuf;
> +		}
>  	}
> +
>  	vq->async_last_pkts_n = n_pkts_cpl - n_pkts_put;
>  	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],
> +		if (vq_is_packed(dev)) {
> +			uint16_t nr_left = n_buffers;
> +			uint16_t to;
> +			do {
> +				from = vq->last_async_buffer_idx &
> +								(vq->size - 1);
> +				to = (from + nr_left) & (vq->size - 1);
> +
> +				if (to > from) {
> +					vhost_update_used_packed(dev, vq,
> +						vq->async_buffers_packed +
> from,
> +						to - from);
> +					vq->last_async_buffer_idx += nr_left;
> +					nr_left = 0;
> +				} else {
> +					vhost_update_used_packed(dev, vq,
> +						vq->async_buffers_packed +
> from,
> +						vq->size - from);
> +					vq->last_async_buffer_idx +=
> +								vq->size -
> from;
> +					nr_left -= vq->size - from;
> +				}
> +			} while (nr_left > 0);
> +			vhost_vring_call_packed(dev, vq);
> +		} else {
> +			uint16_t nr_left = n_descs;
> +			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;
> +				} else {
> +					uint16_t size = vq->size - to;
> 
> -				rte_memcpy(&vq->used->ring[to],
> +					rte_memcpy(&vq->used->ring[to],
>  						&vq-
> >async_descs_split[from],
>  						size *
>  						sizeof(struct
> vring_used_elem));
> -				rte_memcpy(vq->used->ring,
> +					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);
> +
> +			__atomic_add_fetch(&vq->used->idx, n_descs,
> +					__ATOMIC_RELEASE);
> +			vhost_vring_call_split(dev, vq);
> +		}
> 
> -			vq->last_async_desc_idx += nr_copy;
> -			vq->last_used_idx += nr_copy;
> -			nr_left -= nr_copy;
> -		} while (nr_left > 0);
> 
> -		__atomic_add_fetch(&vq->used->idx, n_descs,
> __ATOMIC_RELEASE);
> -		vhost_vring_call_split(dev, vq);
> -	} else
> -		vq->last_async_desc_idx += n_descs;
> +
> +	} else {
> +		if (vq_is_packed(dev))
> +			vq->last_async_buffer_idx += n_buffers;
> +		else
> +			vq->last_async_desc_idx += n_descs;
> +	}
> 
>  done:
>  	rte_spinlock_unlock(&vq->access_lock);
> @@ -1767,9 +2151,10 @@ virtio_dev_rx_async_submit(struct virtio_net
> *dev, uint16_t queue_id,
>  	if (count == 0)
>  		goto out;
> 
> -	/* TODO: packed queue not implemented */
>  	if (vq_is_packed(dev))
> -		nb_tx = 0;
> +		nb_tx = virtio_dev_rx_async_submit_packed(dev,
> +				vq, queue_id, pkts, count, comp_pkts,
> +				comp_count);
>  	else
>  		nb_tx = virtio_dev_rx_async_submit_split(dev,
>  				vq, queue_id, pkts, count, comp_pkts,
> --
> 2.29.2


  reply	other threads:[~2021-03-24  9:19 UTC|newest]

Thread overview: 60+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-17  8:54 [dpdk-dev] [PATCH] " Cheng Jiang
2021-03-22  6:15 ` [dpdk-dev] [PATCH v2] " Cheng Jiang
2021-03-24  9:19   ` Liu, Yong [this message]
2021-03-29 12:29     ` Jiang, Cheng1
2021-03-31 14:06 ` [dpdk-dev] [PATCH v3] " Cheng Jiang
2021-04-07  6:26   ` Hu, Jiayu
2021-04-08 12:01     ` Jiang, Cheng1
2021-04-10 10:25 ` [dpdk-dev] [PATCH v4 0/4] " Cheng Jiang
2021-04-10 10:25   ` [dpdk-dev] [PATCH v4 1/4] vhost: abstract and reorganize async split ring code Cheng Jiang
2021-04-10 10:25   ` Cheng Jiang
2021-04-10 10:25   ` [dpdk-dev] [PATCH v4 2/4] vhost: add support for packed ring in async vhost Cheng Jiang
2021-04-10 10:25   ` [dpdk-dev] [PATCH v4 3/4] vhost: add batch datapath for async vhost packed ring Cheng Jiang
2021-04-10 10:25   ` [dpdk-dev] [PATCH v4 4/4] doc: add release note for vhost async " Cheng Jiang
2021-04-12 11:34 ` [dpdk-dev] [PATCH v5 0/4] add support for packed ring in async vhost Cheng Jiang
2021-04-12 11:34   ` [dpdk-dev] [PATCH v5 1/4] vhost: abstract and reorganize async split ring code Cheng Jiang
2021-04-13  2:44     ` Hu, Jiayu
2021-04-13  3:26       ` Jiang, Cheng1
2021-04-13  7:11     ` Maxime Coquelin
2021-04-13  9:06       ` Jiang, Cheng1
2021-04-12 11:34   ` [dpdk-dev] [PATCH v5 2/4] vhost: add support for packed ring in async vhost Cheng Jiang
2021-04-13  8:36     ` Maxime Coquelin
2021-04-13 11:48       ` Jiang, Cheng1
2021-04-13 13:08         ` Maxime Coquelin
2021-04-13 13:50           ` Jiang, Cheng1
2021-04-12 11:34   ` [dpdk-dev] [PATCH v5 3/4] vhost: add batch datapath for async vhost packed ring Cheng Jiang
2021-04-12 11:34   ` [dpdk-dev] [PATCH v5 4/4] doc: add release note for vhost async " Cheng Jiang
2021-04-13 14:55 ` [dpdk-dev] [PATCH v6 0/4] add support for packed ring in async vhost Cheng Jiang
2021-04-13 14:55   ` [dpdk-dev] [PATCH v6 1/4] vhost: abstract and reorganize async split ring code Cheng Jiang
2021-04-13 14:55   ` [dpdk-dev] [PATCH v6 2/4] vhost: add support for packed ring in async vhost Cheng Jiang
2021-04-13 14:55   ` [dpdk-dev] [PATCH v6 3/4] vhost: add batch datapath for async vhost packed ring Cheng Jiang
2021-04-13 14:55   ` [dpdk-dev] [PATCH v6 4/4] doc: add release note for vhost async " Cheng Jiang
2021-04-14  6:13 ` [dpdk-dev] [PATCH v7 0/4] add support for packed ring in async vhost Cheng Jiang
2021-04-14  6:13   ` [dpdk-dev] [PATCH v7 1/4] vhost: abstract and reorganize async split ring code Cheng Jiang
2021-04-14 12:24     ` Maxime Coquelin
2021-04-14  6:13   ` [dpdk-dev] [PATCH v7 2/4] vhost: add support for packed ring in async vhost Cheng Jiang
2021-04-14 13:40     ` Maxime Coquelin
2021-04-15  5:42       ` Jiang, Cheng1
2021-04-15  2:02     ` Hu, Jiayu
2021-04-15  5:54       ` Jiang, Cheng1
2021-04-14  6:13   ` [dpdk-dev] [PATCH v7 3/4] vhost: add batch datapath for async vhost packed ring Cheng Jiang
2021-04-14  6:13   ` [dpdk-dev] [PATCH v7 4/4] doc: add release note for vhost async " Cheng Jiang
2021-04-19  8:51 ` [dpdk-dev] [PATCH v8 0/4] add support for packed ring in async vhost Cheng Jiang
2021-04-19  8:51   ` [dpdk-dev] [PATCH v8 1/4] vhost: abstract and reorganize async split ring code Cheng Jiang
2021-04-27  1:19     ` Hu, Jiayu
2021-04-19  8:51   ` [dpdk-dev] [PATCH v8 2/4] vhost: add support for packed ring in async vhost Cheng Jiang
2021-04-27  5:16     ` Hu, Jiayu
2021-04-27  6:07       ` Jiang, Cheng1
2021-04-19  8:51   ` [dpdk-dev] [PATCH v8 3/4] vhost: add batch datapath for async vhost packed ring Cheng Jiang
2021-04-19  8:51   ` [dpdk-dev] [PATCH v8 4/4] doc: add release note for vhost async " Cheng Jiang
2021-04-27  8:03 ` [dpdk-dev] [PATCH v9 0/4] add support for packed ring in async vhost Cheng Jiang
2021-04-27  8:03   ` [dpdk-dev] [PATCH v9 1/4] vhost: abstract and reorganize async split ring code Cheng Jiang
2021-04-27  8:03   ` [dpdk-dev] [PATCH v9 2/4] vhost: add support for packed ring in async vhost Cheng Jiang
2021-04-29  1:48     ` Hu, Jiayu
2021-04-29  9:50     ` Maxime Coquelin
2021-04-27  8:03   ` [dpdk-dev] [PATCH v9 3/4] vhost: add batch datapath for async vhost packed ring Cheng Jiang
2021-04-29  9:57     ` Maxime Coquelin
2021-04-27  8:03   ` [dpdk-dev] [PATCH v9 4/4] doc: add release note for vhost async " Cheng Jiang
2021-04-29  9:58     ` Maxime Coquelin
2021-05-04 18:38     ` Ferruh Yigit
2021-05-04  8:28   ` [dpdk-dev] [PATCH v9 0/4] add support for packed ring in async vhost Maxime Coquelin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=2c90bd07cdbb49b39635a1301c48bd7a@intel.com \
    --to=yong.liu@intel.com \
    --cc=chenbo.xia@intel.com \
    --cc=cheng1.jiang@intel.com \
    --cc=dev@dpdk.org \
    --cc=jiayu.hu@intel.com \
    --cc=maxime.coquelin@redhat.com \
    --cc=yinan.wang@intel.com \
    --cc=yvonnex.yang@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).