lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CACGkMEtt-Anog6gS1YvKi2Bt+Q32BnQEtY7E-wLWJwKjRMTUrA@mail.gmail.com>
Date: Wed, 22 Nov 2023 13:52:29 +0800
From: Jason Wang <jasowang@...hat.com>
To: Heng Qi <hengqi@...ux.alibaba.com>
Cc: netdev@...r.kernel.org, virtualization@...ts.linux-foundation.org, 
	mst@...hat.com, kuba@...nel.org, edumazet@...gle.com, pabeni@...hat.com, 
	davem@...emloft.net, hawk@...nel.org, john.fastabend@...il.com, 
	ast@...nel.org, horms@...nel.org, xuanzhuo@...ux.alibaba.com
Subject: Re: [PATCH net-next v4 4/4] virtio-net: support rx netdim

On Mon, Nov 20, 2023 at 8:38 PM Heng Qi <hengqi@...ux.alibaba.com> wrote:
>
> By comparing the traffic information in the complete napi processes,
> let the virtio-net driver automatically adjust the coalescing
> moderation parameters of each receive queue.
>
> Signed-off-by: Heng Qi <hengqi@...ux.alibaba.com>
> ---
> v2->v3:
> - Some minor modifications.
>
> v1->v2:
> - Improved the judgment of dim switch conditions.
> - Cancel the work when vq reset.
>
>  drivers/net/virtio_net.c | 191 ++++++++++++++++++++++++++++++++++-----
>  1 file changed, 169 insertions(+), 22 deletions(-)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index 69fe09e99b3c..bc32d5aae005 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -19,6 +19,7 @@
>  #include <linux/average.h>
>  #include <linux/filter.h>
>  #include <linux/kernel.h>
> +#include <linux/dim.h>
>  #include <net/route.h>
>  #include <net/xdp.h>
>  #include <net/net_failover.h>
> @@ -172,6 +173,17 @@ struct receive_queue {
>
>         struct virtnet_rq_stats stats;
>
> +       /* The number of rx notifications */
> +       u16 calls;
> +
> +       /* Is dynamic interrupt moderation enabled? */
> +       bool dim_enabled;
> +
> +       /* Dynamic Interrupt Moderation */
> +       struct dim dim;
> +
> +       u32 packets_in_napi;
> +
>         struct virtnet_interrupt_coalesce intr_coal;
>
>         /* Chain pages by the private ptr. */
> @@ -305,6 +317,9 @@ struct virtnet_info {
>         u8 duplex;
>         u32 speed;
>
> +       /* Is rx dynamic interrupt moderation enabled? */
> +       bool rx_dim_enabled;
> +
>         /* Interrupt coalescing settings */
>         struct virtnet_interrupt_coalesce intr_coal_tx;
>         struct virtnet_interrupt_coalesce intr_coal_rx;
> @@ -2001,6 +2016,7 @@ static void skb_recv_done(struct virtqueue *rvq)
>         struct virtnet_info *vi = rvq->vdev->priv;
>         struct receive_queue *rq = &vi->rq[vq2rxq(rvq)];
>
> +       rq->calls++;
>         virtqueue_napi_schedule(&rq->napi, rvq);
>  }
>
> @@ -2141,6 +2157,26 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
>         }
>  }
>
> +static void virtnet_rx_dim_work(struct work_struct *work);
> +
> +static void virtnet_rx_dim_update(struct virtnet_info *vi, struct receive_queue *rq)
> +{
> +       struct dim_sample cur_sample = {};
> +
> +       if (!rq->packets_in_napi)
> +               return;
> +
> +       u64_stats_update_begin(&rq->stats.syncp);
> +       dim_update_sample(rq->calls,
> +                         u64_stats_read(&rq->stats.packets),
> +                         u64_stats_read(&rq->stats.bytes),
> +                         &cur_sample);
> +       u64_stats_update_end(&rq->stats.syncp);
> +
> +       net_dim(&rq->dim, cur_sample);
> +       rq->packets_in_napi = 0;
> +}
> +
>  static int virtnet_poll(struct napi_struct *napi, int budget)
>  {
>         struct receive_queue *rq =
> @@ -2149,17 +2185,22 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
>         struct send_queue *sq;
>         unsigned int received;
>         unsigned int xdp_xmit = 0;
> +       bool napi_complete;
>
>         virtnet_poll_cleantx(rq);
>
>         received = virtnet_receive(rq, budget, &xdp_xmit);
> +       rq->packets_in_napi += received;
>
>         if (xdp_xmit & VIRTIO_XDP_REDIR)
>                 xdp_do_flush();
>
>         /* Out of packets? */
> -       if (received < budget)
> -               virtqueue_napi_complete(napi, rq->vq, received);
> +       if (received < budget) {
> +               napi_complete = virtqueue_napi_complete(napi, rq->vq, received);
> +               if (napi_complete && rq->dim_enabled)
> +                       virtnet_rx_dim_update(vi, rq);
> +       }
>
>         if (xdp_xmit & VIRTIO_XDP_TX) {
>                 sq = virtnet_xdp_get_sq(vi);
> @@ -2179,6 +2220,7 @@ static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index)
>         virtnet_napi_tx_disable(&vi->sq[qp_index].napi);
>         napi_disable(&vi->rq[qp_index].napi);
>         xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq);
> +       cancel_work_sync(&vi->rq[qp_index].dim.work);
>  }
>
>  static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
> @@ -2196,6 +2238,9 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
>         if (err < 0)
>                 goto err_xdp_reg_mem_model;
>
> +       INIT_WORK(&vi->rq[qp_index].dim.work, virtnet_rx_dim_work);
> +       vi->rq[qp_index].dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;

So in V2, you explained it can be done here but I want to know why it
must be done here.

For example, the refill_work is initialized in alloc_queues().

> +
>         virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi);
>         virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi);
>
> @@ -2393,8 +2438,10 @@ static int virtnet_rx_resize(struct virtnet_info *vi,
>
>         qindex = rq - vi->rq;
>
> -       if (running)
> +       if (running) {
>                 napi_disable(&rq->napi);
> +               cancel_work_sync(&rq->dim.work);
> +       }
>
>         err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_free_unused_buf);
>         if (err)
> @@ -2403,8 +2450,10 @@ static int virtnet_rx_resize(struct virtnet_info *vi,
>         if (!try_fill_recv(vi, rq, GFP_KERNEL))
>                 schedule_delayed_work(&vi->refill, 0);
>
> -       if (running)
> +       if (running) {
> +               INIT_WORK(&rq->dim.work, virtnet_rx_dim_work);
>                 virtnet_napi_enable(rq->vq, &rq->napi);
> +       }
>         return err;
>  }
>
> @@ -3341,24 +3390,55 @@ static int virtnet_send_tx_notf_coal_cmds(struct virtnet_info *vi,
>  static int virtnet_send_rx_notf_coal_cmds(struct virtnet_info *vi,
>                                           struct ethtool_coalesce *ec)
>  {
> +       bool rx_ctrl_dim_on = !!ec->use_adaptive_rx_coalesce;
> +       bool update = false, switch_dim;
>         struct scatterlist sgs_rx;
>         int i;
>
> -       vi->ctrl->coal_rx.rx_usecs = cpu_to_le32(ec->rx_coalesce_usecs);
> -       vi->ctrl->coal_rx.rx_max_packets = cpu_to_le32(ec->rx_max_coalesced_frames);
> -       sg_init_one(&sgs_rx, &vi->ctrl->coal_rx, sizeof(vi->ctrl->coal_rx));
> -
> -       if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL,
> -                                 VIRTIO_NET_CTRL_NOTF_COAL_RX_SET,
> -                                 &sgs_rx))
> -               return -EINVAL;
> +       switch_dim = rx_ctrl_dim_on != vi->rx_dim_enabled;
> +       if (switch_dim) {
> +               if (rx_ctrl_dim_on) {
> +                       if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) {

So basically, I'm asking why we need to duplicate the check here?

E.g caller has done the check for us:

        if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL))
                ret = virtnet_send_notf_coal_cmds(vi, ec);
        else
                ret = virtnet_coal_params_supported(ec);

?

Please also check other nested if/else, usually, too many levels of
nesting is a hint that the logic needs to be optimized.

Thanks


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ