search for: batched_xdp

...11:17:09AM +0800, Jason Wang wrote: > +static void vhost_tx_batch(struct vhost_net *net, > + struct vhost_net_virtqueue *nvq, > + struct socket *sock, > + struct msghdr *msghdr) > +{ > + struct tun_msg_ctl ctl = { > + .type = TUN_MSG_PTR, > + .num = nvq->batched_xdp, > + .ptr = nvq->xdp, > + }; > + int err; > + > + if (nvq->batched_xdp == 0) > + goto signal_used; > + > + msghdr->msg_control = &ctl; > + err = sock->ops->sendmsg(sock, msghdr, 0); > + if (unlikely(err < 0)) { > + vq_err(&nvq->vq, &q...

...iff --git a/drivers/vhost/net.c b/drivers/vhost/net.c > index fb01ce6d981c..1dd4239cbff8 100644 > --- a/drivers/vhost/net.c > +++ b/drivers/vhost/net.c > @@ -116,6 +116,7 @@ struct vhost_net_virtqueue { > * For RX, number of batched heads > */ > int done_idx; > + int batched_xdp; Pls add a comment documenting what does this new field do. > /* an array of userspace buffers info */ > struct ubuf_info *ubuf_info; > /* Reference counting for outstanding ubufs. > @@ -123,6 +124,7 @@ struct vhost_net_virtqueue { > struct vhost_net_ubuf_ref *ubufs; >...

...iff --git a/drivers/vhost/net.c b/drivers/vhost/net.c > index fb01ce6d981c..1dd4239cbff8 100644 > --- a/drivers/vhost/net.c > +++ b/drivers/vhost/net.c > @@ -116,6 +116,7 @@ struct vhost_net_virtqueue { > * For RX, number of batched heads > */ > int done_idx; > + int batched_xdp; Pls add a comment documenting what does this new field do. > /* an array of userspace buffers info */ > struct ubuf_info *ubuf_info; > /* Reference counting for outstanding ubufs. > @@ -123,6 +124,7 @@ struct vhost_net_virtqueue { > struct vhost_net_ubuf_ref *ubufs; >...

...d, 151 insertions(+), 13 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index fb01ce6d981c..1dd4239cbff8 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -116,6 +116,7 @@ struct vhost_net_virtqueue { * For RX, number of batched heads */ int done_idx; + int batched_xdp; /* an array of userspace buffers info */ struct ubuf_info *ubuf_info; /* Reference counting for outstanding ubufs. @@ -123,6 +124,7 @@ struct vhost_net_virtqueue { struct vhost_net_ubuf_ref *ubufs; struct ptr_ring *rx_ring; struct vhost_net_buf rxq; + struct xdp_buff xdp[VHOST_NET_BATC...

...diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index fb01ce6d981c..dd4e0a301635 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -116,6 +116,8 @@ struct vhost_net_virtqueue { * For RX, number of batched heads */ int done_idx; + /* Number of XDP frames batched */ + int batched_xdp; /* an array of userspace buffers info */ struct ubuf_info *ubuf_info; /* Reference counting for outstanding ubufs. @@ -123,6 +125,8 @@ struct vhost_net_virtqueue { struct vhost_net_ubuf_ref *ubufs; struct ptr_ring *rx_ring; struct vhost_net_buf rxq; + /* Batched XDP buffs */ + struct x...

...rivers/vhost/net.c >> index fb01ce6d981c..1dd4239cbff8 100644 >> --- a/drivers/vhost/net.c >> +++ b/drivers/vhost/net.c >> @@ -116,6 +116,7 @@ struct vhost_net_virtqueue { >> * For RX, number of batched heads >> */ >> int done_idx; >> + int batched_xdp; > Pls add a comment documenting what does this new field do. Ok. > >> /* an array of userspace buffers info */ >> struct ubuf_info *ubuf_info; >> /* Reference counting for outstanding ubufs. >> @@ -123,6 +124,7 @@ struct vhost_net_virtqueue { >> st...

Hi all: This series tries to batch submitting packets to underlayer socket through msg_control during sendmsg(). This is done by: 1) Doing userspace copy inside vhost_net 2) Build XDP buff 3) Batch at most 64 (VHOST_NET_BATCH) XDP buffs and submit them once through msg_control during sendmsg(). 4) Underlayer sockets can use XDP buffs directly when XDP is enalbed, or build skb based on XDP

Hi all: This series tries to batch submitting packets to underlayer socket through msg_control during sendmsg(). This is done by: 1) Doing userspace copy inside vhost_net 2) Build XDP buff 3) Batch at most 64 (VHOST_NET_BATCH) XDP buffs and submit them once through msg_control during sendmsg(). 4) Underlayer sockets can use XDP buffs directly when XDP is enalbed, or build skb based on XDP

Hi all: This series tries to batch submitting packets to underlayer socket through msg_control during sendmsg(). This is done by: 1) Doing userspace copy inside vhost_net 2) Build XDP buff 3) Batch at most 64 (VHOST_NET_BATCH) XDP buffs and submit them once through msg_control during sendmsg(). 4) Underlayer sockets can use XDP buffs directly when XDP is enalbed, or build skb based on XDP

...tainer_of(vq->dev, struct vhost_net, + dev); struct socket *sock = vq->private_data; - struct page_frag *alloc_frag = &current->task_frag; + struct page_frag *alloc_frag = &net->page_frag; struct virtio_net_hdr *gso; struct xdp_buff *xdp = &nvq->xdp[nvq->batched_xdp]; struct tun_xdp_hdr *hdr; @@ -665,7 +708,8 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, buflen += SKB_DATA_ALIGN(len + pad); alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES); - if (unlikely(!skb_page_frag_refill(buflen, alloc_frag, GFP_KERNEL...

...X, number of batched heads > + * For RX, number of batched bufs > */ > int done_idx; > + /* Outstanding user bufs. UIO_MAXIOV in length. */ > + /* TODO: we can make this smaller for sure. */ > + struct vhost_buf *bufs; > /* Number of XDP frames batched */ > int batched_xdp; > /* an array of userspace buffers info */ > @@ -271,6 +274,8 @@ static void vhost_net_clear_ubuf_info(struct vhost_net *n) > int i; > > for (i = 0; i < VHOST_NET_VQ_MAX; ++i) { > + kfree(n->vqs[i].bufs); > + n->vqs[i].bufs = NULL; > kfree(n->v...

...idx for DMA done zerocopy buffers - * For RX, number of batched heads + * For RX, number of batched bufs */ int done_idx; + /* Outstanding user bufs. UIO_MAXIOV in length. */ + /* TODO: we can make this smaller for sure. */ + struct vhost_buf *bufs; /* Number of XDP frames batched */ int batched_xdp; /* an array of userspace buffers info */ @@ -271,6 +274,8 @@ static void vhost_net_clear_ubuf_info(struct vhost_net *n) int i; for (i = 0; i < VHOST_NET_VQ_MAX; ++i) { + kfree(n->vqs[i].bufs); + n->vqs[i].bufs = NULL; kfree(n->vqs[i].ubuf_info); n->vqs[i].ubuf_info =...

From: Tonghao Zhang <xiangxia.m.yue at gmail.com> This patches improve the guest receive performance. On the handle_tx side, we poll the sock receive queue at the same time. handle_rx do that in the same way. For more performance report, see patch 4 Tonghao Zhang (4): net: vhost: lock the vqs one by one net: vhost: replace magic number of lock annotation net: vhost: factor out busy

We let the specifics of the ring format seep through to vhost API callers - mostly because there was only one format so it was hard to imagine what an independent API would look like. Now that there's an alternative in form of the packed ring, it's easier to see the issues, and fixing them is perhaps the cleanest way to add support for more formats. This patchset does this by indtroducing

This adds infrastructure required for supporting multiple ring formats. The idea is as follows: we convert descriptors to an independent format first, and process that converting to iov later. Used ring is similar: we fetch into an independent struct first, convert that to IOV later. The point is that we have a tight loop that fetches descriptors, which is good for cache utilization. This will

This intentionally leaves "fixup" changes separate - hopefully that is enough to fix vhost-net crashes reported here, but it helps me keep track of what changed. I will naturally squash them later when we are done. This adds infrastructure required for supporting multiple ring formats. The idea is as follows: we convert descriptors to an independent format first, and process that

This intentionally leaves "fixup" changes separate - hopefully that is enough to fix vhost-net crashes reported here, but it helps me keep track of what changed. I will naturally squash them later when we are done. This adds infrastructure required for supporting multiple ring formats. The idea is as follows: we convert descriptors to an independent format first, and process that

This adds infrastructure required for supporting multiple ring formats. The idea is as follows: we convert descriptors to an independent format first, and process that converting to iov later. Used ring is similar: we fetch into an independent struct first, convert that to IOV later. The point is that we have a tight loop that fetches descriptors, which is good for cache utilization. This will

Hi all: This series implements packed virtqueues which were described at [1]. In this version we try to address the performance regression saw by V2. The root cause is packed virtqueue need more times of userspace memory accesssing which turns out to be very expensive. Thanks to the help of 7f466032dc9e ("vhost: access vq metadata through kernel virtual address"), such overhead cold be

Hi all: This series implements packed virtqueues which were described at [1]. In this version we try to address the performance regression saw by V2. The root cause is packed virtqueue need more times of userspace memory accesssing which turns out to be very expensive. Thanks to the help of 7f466032dc9e ("vhost: access vq metadata through kernel virtual address"), such overhead cold be