Re: [dpdk-dev] [PATCH v4 2/2] virtio: one way barrier for packed vring desc used flags

["Wang, Yinan" <yinan.wang@intel.com>]

Hi Joyce,

I test performance impact of your patch set with code base commit id: d03d8622db48918d14bfe805641b1766ecc40088, after applying your v4 patch set , packed ring shows small performance drop as below:

PVP vhost/virtio 1c1q test	       commit:d03d8622db48918	apply v4 patch set

pvp_virtio11_mergeable	                   7.218	           7.147
pvp_virtio11_normal	                   7.217	           7.182


Thanks,
Yinan




> -----Original Message-----
> From: Joyce Kong [mailto:joyce.kong@arm.com]
> Sent: 2019年9月17日 13:28
> To: dev@dpdk.org
> Cc: nd@arm.com; maxime.coquelin@redhat.com; Wang, Yinan
> <yinan.wang@intel.com>; Richardson, Bruce <bruce.richardson@intel.com>; Bie,
> Tiwei <tiwei.bie@intel.com>; Wang, Zhihong <zhihong.wang@intel.com>;
> amorenoz@redhat.com; Wang, Xiao W <xiao.w.wang@intel.com>; Liu, Yong
> <yong.liu@intel.com>; jfreimann@redhat.com; honnappa.nagarahalli@arm.com;
> gavin.hu@arm.com
> Subject: [PATCH v4 2/2] virtio: one way barrier for packed vring desc used flags
> 
> In case VIRTIO_F_ORDER_PLATFORM(36) is not negotiated, then the frontend
> and backend are assumed to be implemented in software, that is they can run on
> identical CPUs in an SMP configuration.
> Thus a weak form of memory barriers like rte_smp_r/wmb, other than
> rte_cio_r/wmb, is sufficient for this case(vq->hw->weak_barriers == 1) and
> yields better performance.
> For the above case, this patch helps yielding even better performance by
> replacing the two-way barriers with C11 one-way barriers for used flags in packed
> ring.
> 
> Signed-off-by: Joyce Kong <joyce.kong@arm.com>
> Reviewed-by: Gavin Hu <gavin.hu@arm.com>
> Reviewed-by: Phil Yang <phil.yang@arm.com>
> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
> ---
>  drivers/net/virtio/virtio_rxtx.c                 | 12 +++++++---
>  drivers/net/virtio/virtio_user/virtio_user_dev.c |  4 ++--
>  drivers/net/virtio/virtqueue.h                   | 28
> +++++++++++++++++++++++-
>  lib/librte_vhost/virtio_net.c                    |  5 ++---
>  4 files changed, 40 insertions(+), 9 deletions(-)
> 
> diff --git a/drivers/net/virtio/virtio_rxtx.c b/drivers/net/virtio/virtio_rxtx.c
> index a87ffe1..2f0879c 100644
> --- a/drivers/net/virtio/virtio_rxtx.c
> +++ b/drivers/net/virtio/virtio_rxtx.c
> @@ -122,9 +122,11 @@ virtqueue_dequeue_burst_rx_packed(struct virtqueue
> *vq,
> 
>  	for (i = 0; i < num; i++) {
>  		used_idx = vq->vq_used_cons_idx;
> +		/* desc_is_used has a load-acquire or rte_cio_rmb inside
> +		 * and wait for used desc in virtqueue.
> +		 */
>  		if (!desc_is_used(&desc[used_idx], vq))
>  			return i;
> -		virtio_rmb(vq->hw->weak_barriers);
>  		len[i] = desc[used_idx].len;
>  		id = desc[used_idx].id;
>  		cookie = (struct rte_mbuf *)vq->vq_descx[id].cookie; @@ -233,8
> +235,10 @@ virtio_xmit_cleanup_inorder_packed(struct virtqueue *vq, int num)
>  	struct vq_desc_extra *dxp;
> 
>  	used_idx = vq->vq_used_cons_idx;
> +	/* desc_is_used has a load-acquire or rte_cio_rmb inside
> +	 * and wait for used desc in virtqueue.
> +	 */
>  	while (num > 0 && desc_is_used(&desc[used_idx], vq)) {
> -		virtio_rmb(vq->hw->weak_barriers);
>  		id = desc[used_idx].id;
>  		do {
>  			curr_id = used_idx;
> @@ -265,8 +269,10 @@ virtio_xmit_cleanup_normal_packed(struct virtqueue
> *vq, int num)
>  	struct vq_desc_extra *dxp;
> 
>  	used_idx = vq->vq_used_cons_idx;
> +	/* desc_is_used has a load-acquire or rte_cio_rmb inside
> +	 * and wait for used desc in virtqueue.
> +	 */
>  	while (num-- && desc_is_used(&desc[used_idx], vq)) {
> -		virtio_rmb(vq->hw->weak_barriers);
>  		id = desc[used_idx].id;
>  		dxp = &vq->vq_descx[id];
>  		vq->vq_used_cons_idx += dxp->ndescs;
> diff --git a/drivers/net/virtio/virtio_user/virtio_user_dev.c
> b/drivers/net/virtio/virtio_user/virtio_user_dev.c
> index 7911c39..1c575d0 100644
> --- a/drivers/net/virtio/virtio_user/virtio_user_dev.c
> +++ b/drivers/net/virtio/virtio_user/virtio_user_dev.c
> @@ -698,8 +698,8 @@ virtio_user_handle_cq_packed(struct virtio_user_dev
> *dev, uint16_t queue_idx)
>  		if (vq->used_wrap_counter)
>  			flags |= VRING_PACKED_DESC_F_AVAIL_USED;
> 
> -		rte_smp_wmb();
> -		vring->desc[vq->used_idx].flags = flags;
> +		__atomic_store_n(&vring->desc[vq->used_idx].flags, flags,
> +				 __ATOMIC_RELEASE);
> 
>  		vq->used_idx += n_descs;
>  		if (vq->used_idx >= dev->queue_size) { diff --git
> a/drivers/net/virtio/virtqueue.h b/drivers/net/virtio/virtqueue.h index
> b728ff8..8d7f197 100644
> --- a/drivers/net/virtio/virtqueue.h
> +++ b/drivers/net/virtio/virtqueue.h
> @@ -54,6 +54,32 @@ virtio_wmb(uint8_t weak_barriers)
>  		rte_cio_wmb();
>  }
> 
> +static inline uint16_t
> +virtqueue_fetch_flags_packed(struct vring_packed_desc *dp,
> +			      uint8_t weak_barriers)
> +{
> +	uint16_t flags;
> +
> +	if (weak_barriers) {
> +/* x86 prefers to using rte_smp_rmb over __atomic_load_n as it reports
> + * a better perf(~1.5%), which comes from the saved branch by the compiler.
> + * The if and else branch are identical with the smp and cio barriers
> +both
> + * defined as compiler barriers on x86.
> + */
> +#ifdef RTE_ARCH_X86_64
> +		flags = dp->flags;
> +		rte_smp_rmb();
> +#else
> +		flags = __atomic_load_n(&dp->flags, __ATOMIC_ACQUIRE); #endif
> +	} else {
> +		flags = dp->flags;
> +		rte_cio_rmb();
> +	}
> +
> +	return flags;
> +}
> +
>  static inline void
>  virtqueue_store_flags_packed(struct vring_packed_desc *dp,
>  			      uint16_t flags, uint8_t weak_barriers) @@ -307,7 +333,7
> @@ desc_is_used(struct vring_packed_desc *desc, struct virtqueue *vq)  {
>  	uint16_t used, avail, flags;
> 
> -	flags = desc->flags;
> +	flags = virtqueue_fetch_flags_packed(desc, vq->hw->weak_barriers);
>  	used = !!(flags & VRING_PACKED_DESC_F_USED);
>  	avail = !!(flags & VRING_PACKED_DESC_F_AVAIL);
> 
> diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c index
> e7463ff..241d467 100644
> --- a/lib/librte_vhost/virtio_net.c
> +++ b/lib/librte_vhost/virtio_net.c
> @@ -110,8 +110,6 @@ flush_shadow_used_ring_packed(struct virtio_net *dev,
>  			used_idx -= vq->size;
>  	}
> 
> -	rte_smp_wmb();
> -
>  	for (i = 0; i < vq->shadow_used_idx; i++) {
>  		uint16_t flags;
> 
> @@ -147,7 +145,8 @@ flush_shadow_used_ring_packed(struct virtio_net *dev,
>  		}
>  	}
> 
> -	vq->desc_packed[head_idx].flags = head_flags;
> +	__atomic_store_n(&vq->desc_packed[head_idx].flags, head_flags,
> +			 __ATOMIC_RELEASE);
> 
>  	vhost_log_cache_used_vring(dev, vq,
>  				head_idx *
> --
> 2.7.4