Re: [dpdk-dev] [PATCH 1/4] vhost: support async dequeue for split ring

["Xia, Chenbo" <chenbo.xia@intel.com>]

Hi,

> -----Original Message-----
> From: Ma, WenwuX <wenwux.ma@intel.com>
> Sent: Tuesday, September 7, 2021 4:49 AM
> To: dev@dpdk.org
> Cc: maxime.coquelin@redhat.com; Xia, Chenbo <chenbo.xia@intel.com>; Jiang,
> Cheng1 <cheng1.jiang@intel.com>; Hu, Jiayu <jiayu.hu@intel.com>; Pai G, Sunil
> <sunil.pai.g@intel.com>; Yang, YvonneX <yvonnex.yang@intel.com>; Wang, YuanX
> <yuanx.wang@intel.com>; Ma, WenwuX <wenwux.ma@intel.com>; Wang, Yinan
> <yinan.wang@intel.com>
> Subject: [PATCH 1/4] vhost: support async dequeue for split ring
> 
> From: Yuan Wang <yuanx.wang@intel.com>
> 
> This patch implements asynchronous dequeue data path for split ring.
> A new asynchronous dequeue function is introduced. With this function,
> the application can try to receive packets from the guest with
> offloading copies to the async channel, thus saving precious CPU
> cycles.
> 
> Signed-off-by: Yuan Wang <yuanx.wang@intel.com>
> Signed-off-by: Jiayu Hu <jiayu.hu@intel.com>
> Signed-off-by: Wenwu Ma <wenwux.ma@intel.com>
> Tested-by: Yinan Wang <yinan.wang@intel.com>
> ---
>  doc/guides/prog_guide/vhost_lib.rst |   9 +
>  lib/vhost/rte_vhost_async.h         |  36 +-
>  lib/vhost/version.map               |   3 +
>  lib/vhost/vhost.h                   |   3 +-
>  lib/vhost/virtio_net.c              | 531 ++++++++++++++++++++++++++++
>  5 files changed, 579 insertions(+), 3 deletions(-)
> 
> diff --git a/doc/guides/prog_guide/vhost_lib.rst
> b/doc/guides/prog_guide/vhost_lib.rst
> index 171e0096f6..9ed544db7a 100644
> --- a/doc/guides/prog_guide/vhost_lib.rst
> +++ b/doc/guides/prog_guide/vhost_lib.rst
> @@ -303,6 +303,15 @@ The following is an overview of some key Vhost API
> functions:
>    Clear inflight packets which are submitted to DMA engine in vhost async
> data
>    path. Completed packets are returned to applications through ``pkts``.
> 
> +* ``rte_vhost_async_try_dequeue_burst(vid, queue_id, mbuf_pool, pkts, count,
> nr_inflight)``
> +
> +  This function tries to receive packets from the guest with offloading
> +  copies to the async channel. The packets that are transfer completed
> +  are returned in ``pkts``. The other packets that their copies are submitted
> +  to the async channel but not completed are called "in-flight packets".
> +  This function will not return in-flight packets until their copies are
> +  completed by the async channel.
> +
>  Vhost-user Implementations
>  --------------------------
> 
> diff --git a/lib/vhost/rte_vhost_async.h b/lib/vhost/rte_vhost_async.h
> index ad71555a7f..5e2429ab70 100644
> --- a/lib/vhost/rte_vhost_async.h
> +++ b/lib/vhost/rte_vhost_async.h
> @@ -83,12 +83,18 @@ struct rte_vhost_async_channel_ops {
>  		uint16_t max_packets);
>  };
> 
> +struct async_nethdr {
> +	struct virtio_net_hdr hdr;
> +	bool valid;
> +};
> +

As a struct exposed in public headers, it's better to prefix it with rte_.
In this case I would prefer rte_async_net_hdr.

>  /**
> - * inflight async packet information
> + * in-flight async packet information
>   */
>  struct async_inflight_info {

Could you help to rename it too? Like rte_async_inflight_info.

>  	struct rte_mbuf *mbuf;
> -	uint16_t descs; /* num of descs inflight */
> +	struct async_nethdr nethdr;
> +	uint16_t descs; /* num of descs in-flight */
>  	uint16_t nr_buffers; /* num of buffers inflight for packed ring */
>  };
> 
> @@ -255,5 +261,31 @@ int rte_vhost_async_get_inflight(int vid, uint16_t
> queue_id);
>  __rte_experimental
>  uint16_t rte_vhost_clear_queue_thread_unsafe(int vid, uint16_t queue_id,
>  		struct rte_mbuf **pkts, uint16_t count);
> +/**
> + * This function tries to receive packets from the guest with offloading
> + * copies to the async channel. The packets that are transfer completed
> + * are returned in "pkts". The other packets that their copies are submitted
> to
> + * the async channel but not completed are called "in-flight packets".
> + * This function will not return in-flight packets until their copies are
> + * completed by the async channel.
> + *
> + * @param vid
> + *  id of vhost device to dequeue data
> + * @param queue_id
> + *  queue id to dequeue data

Param mbuf_pool is missed.

> + * @param pkts
> + *  blank array to keep successfully dequeued packets
> + * @param count
> + *  size of the packet array
> + * @param nr_inflight
> + *  the amount of in-flight packets. If error occurred, its value is set to -
> 1.
> + * @return
> + *  num of successfully dequeued packets
> + */
> +__rte_experimental
> +uint16_t
> +rte_vhost_async_try_dequeue_burst(int vid, uint16_t queue_id,
> +	struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t count,
> +	int *nr_inflight);
> 
>  #endif /* _RTE_VHOST_ASYNC_H_ */
> diff --git a/lib/vhost/version.map b/lib/vhost/version.map
> index c92a9d4962..1e033ad8e2 100644
> --- a/lib/vhost/version.map
> +++ b/lib/vhost/version.map
> @@ -85,4 +85,7 @@ EXPERIMENTAL {
>  	rte_vhost_async_channel_register_thread_unsafe;
>  	rte_vhost_async_channel_unregister_thread_unsafe;
>  	rte_vhost_clear_queue_thread_unsafe;
> +
> +	# added in 21.11
> +	rte_vhost_async_try_dequeue_burst;
>  };
> diff --git a/lib/vhost/vhost.h b/lib/vhost/vhost.h
> index 1e56311725..89a31e4ca8 100644
> --- a/lib/vhost/vhost.h
> +++ b/lib/vhost/vhost.h
> @@ -49,7 +49,8 @@

[...]

> +uint16_t
> +rte_vhost_async_try_dequeue_burst(int vid, uint16_t queue_id,
> +	struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t count,
> +	int *nr_inflight)
> +{
> +	struct virtio_net *dev;
> +	struct rte_mbuf *rarp_mbuf = NULL;
> +	struct vhost_virtqueue *vq;
> +	int16_t success = 1;
> +
> +	*nr_inflight = -1;
> +
> +	dev = get_device(vid);
> +	if (!dev)
> +		return 0;
> +
> +	if (unlikely(!(dev->flags & VIRTIO_DEV_BUILTIN_VIRTIO_NET))) {
> +		VHOST_LOG_DATA(ERR,
> +			"(%d) %s: built-in vhost net backend is disabled.\n",
> +			dev->vid, __func__);
> +		return 0;
> +	}
> +
> +	if (unlikely(!is_valid_virt_queue_idx(queue_id, 1, dev->nr_vring))) {
> +		VHOST_LOG_DATA(ERR,
> +			"(%d) %s: invalid virtqueue idx %d.\n",
> +			dev->vid, __func__, queue_id);
> +		return 0;
> +	}
> +
> +	vq = dev->virtqueue[queue_id];
> +
> +	if (unlikely(rte_spinlock_trylock(&vq->access_lock) == 0))
> +		return 0;
> +
> +	if (unlikely(vq->enabled == 0)) {
> +		count = 0;
> +		goto out_access_unlock;
> +	}
> +
> +	if (unlikely(!vq->async_registered)) {
> +		VHOST_LOG_DATA(ERR, "(%d) %s: async not registered for queue
> id %d.\n",
> +			dev->vid, __func__, queue_id);
> +		count = 0;
> +		goto out_access_unlock;
> +	}
> +
> +	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
> +		vhost_user_iotlb_rd_lock(vq);
> +
> +	if (unlikely(vq->access_ok == 0))
> +		if (unlikely(vring_translate(dev, vq) < 0)) {
> +			count = 0;
> +			goto out_access_unlock;
> +		}
> +
> +	/*
> +	 * Construct a RARP broadcast packet, and inject it to the "pkts"
> +	 * array, to looks like that guest actually send such packet.
> +	 *
> +	 * Check user_send_rarp() for more information.
> +	 *
> +	 * broadcast_rarp shares a cacheline in the virtio_net structure
> +	 * with some fields that are accessed during enqueue and
> +	 * __atomic_compare_exchange_n causes a write if performed compare
> +	 * and exchange. This could result in false sharing between enqueue
> +	 * and dequeue.
> +	 *
> +	 * Prevent unnecessary false sharing by reading broadcast_rarp first
> +	 * and only performing compare and exchange if the read indicates it
> +	 * is likely to be set.
> +	 */
> +	if (unlikely(__atomic_load_n(&dev->broadcast_rarp, __ATOMIC_ACQUIRE) &&
> +			__atomic_compare_exchange_n(&dev->broadcast_rarp,
> +			&success, 0, 0, __ATOMIC_RELEASE, __ATOMIC_RELAXED))) {
> +
> +		rarp_mbuf = rte_net_make_rarp_packet(mbuf_pool, &dev->mac);
> +		if (rarp_mbuf == NULL) {
> +			VHOST_LOG_DATA(ERR, "Failed to make RARP packet.\n");
> +			count = 0;
> +			goto out;
> +		}
> +		count -= 1;
> +	}
> +
> +	if (unlikely(vq_is_packed(dev)))
> +		return 0;

Should add a log here.

Thanks,
Chenbo