qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "Michael S. Tsirkin" <mst@redhat.com>
To: Halil Pasic <pasic@linux.ibm.com>
Cc: Jason Wang <jasowang@redhat.com>,
	qemu-devel@nongnu.org, qemu-stable@nongnu.org
Subject: Re: [PATCH V2] vhost: correctly turn on VIRTIO_F_IOMMU_PLATFORM
Date: Wed, 26 Feb 2020 08:37:13 -0500	[thread overview]
Message-ID: <20200226083654-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <20200226142839.4263de9b.pasic@linux.ibm.com>

On Wed, Feb 26, 2020 at 02:28:39PM +0100, Halil Pasic wrote:
> 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.

Fixes as in improves performance?

> 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");



  reply	other threads:[~2020-02-26 13:38 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
2020-02-26 13:37   ` Michael S. Tsirkin [this message]
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=20200226083654-mutt-send-email-mst@kernel.org \
    --to=mst@redhat.com \
    --cc=jasowang@redhat.com \
    --cc=pasic@linux.ibm.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).