similar to: [PATCH RFC] virtio-net: remove useless disable on freeze

disable_cb is just an optimization: it can not guarantee that there are no callbacks. In particular it doesn't have any effect when event index is on. Instead, detach, napi disable and reset on freeze ensure we don't run concurrently with a callback. Remove the useless calls so we get same behaviour with and without event index. Signed-off-by: Michael S. Tsirkin <mst at

disable_cb is just an optimization: it can not guarantee that there are no callbacks. In particular it doesn't have any effect when event index is on. Instead, detach, napi disable and reset on freeze ensure we don't run concurrently with a callback. Remove the useless calls so we get same behaviour with and without event index. Signed-off-by: Michael S. Tsirkin <mst at

This adds a way to check ring empty state after enable_cb outside any locks. Will be used by virtio_net. Note: there's room for more optimization: caller is likely to have a memory barrier already, which means we might be able to get rid of a barrier here. Deferring this optimization until we do some benchmarking. Signed-off-by: Michael S. Tsirkin <mst at redhat.com> ---

This adds a way to check ring empty state after enable_cb outside any locks. Will be used by virtio_net. Note: there's room for more optimization: caller is likely to have a memory barrier already, which means we might be able to get rid of a barrier here. Deferring this optimization until we do some benchmarking. Signed-off-by: Michael S. Tsirkin <mst at redhat.com> ---

virtqueue ops were introduced in the hope that we'll have multiple implementations besides virtio_ring, but none have surfaced so far, and given that existing virtio ring is deployed in production we are likely stuck with it now, so this layer just adds complexity and overhead. Further, the need to pass vq twice to each call (as in dev->vq->vq_ops->kick(dev->vq) ) adds potential

virtqueue ops were introduced in the hope that we'll have multiple implementations besides virtio_ring, but none have surfaced so far, and given that existing virtio ring is deployed in production we are likely stuck with it now, so this layer just adds complexity and overhead. Further, the need to pass vq twice to each call (as in dev->vq->vq_ops->kick(dev->vq) ) adds potential

As hypervior does not have the knowledge of guest network configuration, it's better to ask guest to send gratuitous packet when needed. Guest test VIRTIO_NET_S_ANNOUNCE bit during config change interrupt and when it is set, a workqueue is scheduled to send gratuitous packet through NETDEV_NOTIFY_PEERS. This feature is negotiated through bit VIRTIO_NET_F_GUEST_ANNOUNCE. Changes from v3: -

As hypervior does not have the knowledge of guest network configuration, it's better to ask guest to send gratuitous packet when needed. Guest test VIRTIO_NET_S_ANNOUNCE bit during config change interrupt and when it is set, a workqueue is scheduled to send gratuitous packet through NETDEV_NOTIFY_PEERS. This feature is negotiated through bit VIRTIO_NET_F_GUEST_ANNOUNCE. Changes from v3: -

The old documentation is left over from when we used a structure with strategy pointers. Signed-off-by: Rusty Russell <rusty at rustcorp.com.au> --- include/linux/virtio.h | 130 ++++++++++++++++++++++++++++++++----------------- 1 file changed, 87 insertions(+), 43 deletions(-) diff --git a/include/linux/virtio.h b/include/linux/virtio.h --- a/include/linux/virtio.h +++

The old documentation is left over from when we used a structure with strategy pointers. Signed-off-by: Rusty Russell <rusty at rustcorp.com.au> --- include/linux/virtio.h | 130 ++++++++++++++++++++++++++++++++----------------- 1 file changed, 87 insertions(+), 43 deletions(-) diff --git a/include/linux/virtio.h b/include/linux/virtio.h --- a/include/linux/virtio.h +++

The old documentation is left over from when we used a structure with strategy pointers. Signed-off-by: Rusty Russell <rusty at rustcorp.com.au> --- include/linux/virtio.h | 130 ++++++++++++++++++++++++++++++++----------------- 1 file changed, 87 insertions(+), 43 deletions(-) diff --git a/include/linux/virtio.h b/include/linux/virtio.h --- a/include/linux/virtio.h +++

The old documentation is left over from when we used a structure with strategy pointers. Signed-off-by: Rusty Russell <rusty at rustcorp.com.au> --- include/linux/virtio.h | 130 ++++++++++++++++++++++++++++++++----------------- 1 file changed, 87 insertions(+), 43 deletions(-) diff --git a/include/linux/virtio.h b/include/linux/virtio.h --- a/include/linux/virtio.h +++

This adds a way to check ring empty state after enable_cb outside any locks. Will be used by virtio_net. Note: there's room for more optimization: caller is likely to have a memory barrier already, which means we might be able to get rid of a barrier here. Deferring this optimization until we do some benchmarking. Signed-off-by: Michael S. Tsirkin <mst at redhat.com> ---

This adds a way to check ring empty state after enable_cb outside any locks. Will be used by virtio_net. Note: there's room for more optimization: caller is likely to have a memory barrier already, which means we might be able to get rid of a barrier here. Deferring this optimization until we do some benchmarking. Signed-off-by: Michael S. Tsirkin <mst at redhat.com> ---

As hypervior does not have the knowledge of guest network configuration, it's better to ask guest to send gratuitous packets when needed. Guest tests VIRTIO_NET_S_ANNOUNCE bit during config change interrupt and when it is set, a workqueue is scheduled to send gratuitous packet through NETDEV_NOTIFY_PEERS. This feature is negotiated through bit VIRTIO_NET_F_GUEST_ANNOUNCE. Changes from v5: -

As hypervior does not have the knowledge of guest network configuration, it's better to ask guest to send gratuitous packets when needed. Guest tests VIRTIO_NET_S_ANNOUNCE bit during config change interrupt and when it is set, a workqueue is scheduled to send gratuitous packet through NETDEV_NOTIFY_PEERS. This feature is negotiated through bit VIRTIO_NET_F_GUEST_ANNOUNCE. Changes from v5: -

There are lots of mismatches between comments and codes, this patch do these comment fixes. Signed-off-by: Jiang Biao <benbjiang at tencent.com> --- drivers/virtio/virtio_ring.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 5df92c308286..3794c7666a99 100644 ---

We free transmitted packets in ndo_start_xmit() in the past to get better performance in the past. One side effect is that skb_orphan() needs to be called in ndo_start_xmit() which makes sk_wmem_alloc not accurate in fact. For TCP protocol, this means several optimization could not work well such as TCP small queue and auto corking. This can lead extra low throughput of small packets stream.

We free transmitted packets in ndo_start_xmit() in the past to get better performance in the past. One side effect is that skb_orphan() needs to be called in ndo_start_xmit() which makes sk_wmem_alloc not accurate in fact. For TCP protocol, this means several optimization could not work well such as TCP small queue and auto corking. This can lead extra low throughput of small packets stream.

On Fri, 2013-07-12 at 23:13 +0200, Wolfram Gloger wrote: > Hi, > > Today I merged M. Tsirkin's patch v2 "virtio_net: fix race in RX VQ > processing": > > http://lkml.indiana.edu/hypermail/linux/kernel/1307.1/00503.html > > into 3.2.48 and lightly tested the result (vhost-net, virtio-disk > and 9pfs using virtio). This sounds like it could be suitable