On 02/26/2016 09:42 AM, Jason Wang wrote:
> This patch tries to poll for new added tx buffer or socket receive
> queue for a while at the end of tx/rx processing. The maximum time
> spent on polling were specified through a new kind of vring ioctl.
> 
> Signed-off-by: Jason Wang <jasow...@redhat.com>
> ---
>  drivers/vhost/net.c        | 79 
> +++++++++++++++++++++++++++++++++++++++++++---
>  drivers/vhost/vhost.c      | 14 ++++++++
>  drivers/vhost/vhost.h      |  1 +
>  include/uapi/linux/vhost.h |  6 ++++
>  4 files changed, 95 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
> index 9eda69e..c91af93 100644
> --- a/drivers/vhost/net.c
> +++ b/drivers/vhost/net.c
> @@ -287,6 +287,44 @@ static void vhost_zerocopy_callback(struct ubuf_info 
> *ubuf, bool success)
>       rcu_read_unlock_bh();
>  }
> 
> +static inline unsigned long busy_clock(void)
> +{
> +     return local_clock() >> 10;
> +}
> +
> +static bool vhost_can_busy_poll(struct vhost_dev *dev,
> +                             unsigned long endtime)
> +{
> +     return likely(!need_resched()) &&
> +            likely(!time_after(busy_clock(), endtime)) &&
> +            likely(!signal_pending(current)) &&
> +            !vhost_has_work(dev) &&
> +            single_task_running();
> +}
> +
> +static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
> +                                 struct vhost_virtqueue *vq,
> +                                 struct iovec iov[], unsigned int iov_size,
> +                                 unsigned int *out_num, unsigned int *in_num)
> +{
> +     unsigned long uninitialized_var(endtime);
> +     int r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
> +                                 out_num, in_num, NULL, NULL);
> +
> +     if (r == vq->num && vq->busyloop_timeout) {
> +             preempt_disable();
> +             endtime = busy_clock() + vq->busyloop_timeout;
> +             while (vhost_can_busy_poll(vq->dev, endtime) &&
> +                    vhost_vq_avail_empty(vq->dev, vq))
> +                     cpu_relax();


Can you use cpu_relax_lowlatency (which should be the same as cpu_relax for 
almost
everybody but s390? cpu_relax (without low latency might give up the time slice
when running under another hypervisor (like LPAR on s390), which might not be 
what
we want here.



[...] 
> +static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
> +{
> +     struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
> +     struct vhost_virtqueue *vq = &nvq->vq;
> +     unsigned long uninitialized_var(endtime);
> +     int len = peek_head_len(sk);
> +
> +     if (!len && vq->busyloop_timeout) {
> +             /* Both tx vq and rx socket were polled here */
> +             mutex_lock(&vq->mutex);
> +             vhost_disable_notify(&net->dev, vq);
> +
> +             preempt_disable();
> +             endtime = busy_clock() + vq->busyloop_timeout;
> +
> +             while (vhost_can_busy_poll(&net->dev, endtime) &&
> +                    skb_queue_empty(&sk->sk_receive_queue) &&
> +                    vhost_vq_avail_empty(&net->dev, vq))
> +                     cpu_relax();

here as well.

Reply via email to