All of lore.kernel.org
 help / color / mirror / Atom feed
From: Halil Pasic <pasic@linux.ibm.com>
To: Jason Wang <jasowang@redhat.com>
Cc: qemu-stable@nongnu.org, qemu-devel@nongnu.org, mst@redhat.com
Subject: Re: [PATCH V2] vhost: correctly turn on VIRTIO_F_IOMMU_PLATFORM
Date: Wed, 26 Feb 2020 14:28:39 +0100	[thread overview]
Message-ID: <20200226142839.4263de9b.pasic@linux.ibm.com> (raw)
In-Reply-To: <20200226094357.25061-1-jasowang@redhat.com>

On Wed, 26 Feb 2020 17:43:57 +0800
Jason Wang <jasowang@redhat.com> wrote:

> We turn on device IOTLB via VIRTIO_F_IOMMU_PLATFORM unconditionally on
> platform without IOMMU support. This can lead unnecessary IOTLB
> transactions which will damage the performance.
> 
> Fixing this by check whether the device is backed by IOMMU and disable
> device IOTLB.
> 
> Reported-by: Halil Pasic <pasic@linux.ibm.com>
> Fixes: c471ad0e9bd46 ("vhost_net: device IOTLB support")
> Cc: qemu-stable@nongnu.org
> Signed-off-by: Jason Wang <jasowang@redhat.com>

Tested-by: Halil Pasic <pasic@linux.ibm.com>
Reviewed-by: Halil Pasic <pasic@linux.ibm.com>

Thank you very much for fixing this! BTW as I mentioned before it
fixes vhost-vsock with iommu_platform=on as well.

Regards,
Halil

> ---
> Changes from V1:
> - do not check acked_features
> - reuse vhost_dev_has_iommu()
> ---
>  hw/virtio/vhost.c | 12 +++++++++++-
>  1 file changed, 11 insertions(+), 1 deletion(-)
> 
> diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
> index 9edfadc81d..9182a00495 100644
> --- a/hw/virtio/vhost.c
> +++ b/hw/virtio/vhost.c
> @@ -290,7 +290,14 @@ static int vhost_dev_has_iommu(struct vhost_dev *dev)
>  {
>      VirtIODevice *vdev = dev->vdev;
>  
> -    return virtio_host_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM);
> +    /*
> +     * For vhost, VIRTIO_F_IOMMU_PLATFORM means the backend support
> +     * incremental memory mapping API via IOTLB API. For platform that
> +     * does not have IOMMU, there's no need to enable this feature
> +     * which may cause unnecessary IOTLB miss/update trnasactions.
> +     */
> +    return vdev->dma_as != &address_space_memory &&
> +           virtio_host_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM);
>  }
>  
>  static void *vhost_memory_map(struct vhost_dev *dev, hwaddr addr,
> @@ -765,6 +772,9 @@ static int vhost_dev_set_features(struct vhost_dev *dev,
>      if (enable_log) {
>          features |= 0x1ULL << VHOST_F_LOG_ALL;
>      }
> +    if (!vhost_dev_has_iommu(dev)) {
> +        features &= ~(0x1ULL << VIRTIO_F_IOMMU_PLATFORM);
> +    }
>      r = dev->vhost_ops->vhost_set_features(dev, features);
>      if (r < 0) {
>          VHOST_OPS_DEBUG("vhost_set_features failed");



  parent reply	other threads:[~2020-02-26 13:29 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-26  9:43 [PATCH V2] vhost: correctly turn on VIRTIO_F_IOMMU_PLATFORM Jason Wang
2020-02-26  9:53 ` Michael S. Tsirkin
2020-02-26 10:17   ` Jason Wang
2020-02-26 11:44     ` Michael S. Tsirkin
2020-02-26 12:50       ` Halil Pasic
2020-02-26 12:55   ` Halil Pasic
2020-02-26 13:45     ` Michael S. Tsirkin
2020-02-26 13:28 ` Halil Pasic [this message]
2020-02-26 13:37   ` Michael S. Tsirkin
2020-02-26 15:36     ` Halil Pasic
2020-02-26 16:52       ` Michael S. Tsirkin
2020-02-27 13:02         ` Halil Pasic
2020-02-27 15:47           ` Michael S. Tsirkin
2020-03-03 14:44             ` Halil Pasic
2020-03-13 12:44             ` Halil Pasic
2020-03-13 15:29               ` Michael S. Tsirkin
2020-03-13 16:31                 ` Peter Xu
2020-03-16 16:57                   ` Halil Pasic
2020-03-16 17:31                     ` Peter Xu
2020-03-16 17:19                   ` Michael S. Tsirkin
2020-03-16 18:14                     ` Peter Xu
2020-03-17  3:04                       ` Jason Wang
2020-03-17 14:13                         ` Peter Xu
2020-03-18  2:06                           ` Jason Wang
2020-03-17  6:28                       ` Michael S. Tsirkin
2020-03-17 14:39                         ` Peter Xu
2020-03-17 14:55                           ` Michael S. Tsirkin
2020-03-13 20:27               ` Brijesh Singh
2020-03-14 18:22                 ` Michael S. Tsirkin
2020-02-27 20:36           ` Tom Lendacky

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200226142839.4263de9b.pasic@linux.ibm.com \
    --to=pasic@linux.ibm.com \
    --cc=jasowang@redhat.com \
    --cc=mst@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=qemu-stable@nongnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.