similar to: [PATCH RFC] virtio-pci: new config layout: using memory BAR

"Michael S. Tsirkin" <mst at redhat.com> writes: > This adds support for new config, and is designed to work with > the new layout code in Rusty's new layout branch. > > At the moment all fields are in the same memory BAR (bar 2). > This will be used to test performance and compare > memory, io and hypercall latency. > > Compiles but does not work yet.

Anthony Liguori <aliguori at us.ibm.com> writes: > "Michael S. Tsirkin" <mst at redhat.com> writes: >> + case offsetof(struct virtio_pci_common_cfg, device_feature_select): >> + return proxy->device_feature_select; > > Oh dear no... Please use defines like the rest of QEMU. It is pretty ugly. Yet the structure definitions are descriptive,

Anthony Liguori <aliguori at us.ibm.com> writes: > "Michael S. Tsirkin" <mst at redhat.com> writes: >> + case offsetof(struct virtio_pci_common_cfg, device_feature_select): >> + return proxy->device_feature_select; > > Oh dear no... Please use defines like the rest of QEMU. It is pretty ugly. Yet the structure definitions are descriptive,

On Wed, May 29, 2013 at 02:01:18PM +0930, Rusty Russell wrote: > Anthony Liguori <aliguori at us.ibm.com> writes: > > "Michael S. Tsirkin" <mst at redhat.com> writes: > >> + case offsetof(struct virtio_pci_common_cfg, device_feature_select): > >> + return proxy->device_feature_select; > > > > Oh dear no... Please use

On Wed, May 29, 2013 at 10:47:52AM +0930, Rusty Russell wrote: > "Michael S. Tsirkin" <mst at redhat.com> writes: > > > On Mon, Dec 12, 2011 at 01:49:13PM +0200, Michael S. Tsirkin wrote: > >> On Mon, Dec 12, 2011 at 09:15:03AM +1030, Rusty Russell wrote: > >> > On Sun, 11 Dec 2011 11:42:56 +0200, "Michael S. Tsirkin" <mst at

On Wed, Dec 03, 2014 at 10:50:04AM +0100, Cornelia Huck wrote: > On Wed, 3 Dec 2014 10:27:36 +0100 > Cornelia Huck <cornelia.huck at de.ibm.com> wrote: > > > On Tue, 2 Dec 2014 21:03:45 +0200 > > "Michael S. Tsirkin" <mst at redhat.com> wrote: > > > > > On Tue, Dec 02, 2014 at 04:41:36PM +0100, Cornelia Huck wrote: > > > >

On Wed, Dec 03, 2014 at 10:50:04AM +0100, Cornelia Huck wrote: > On Wed, 3 Dec 2014 10:27:36 +0100 > Cornelia Huck <cornelia.huck at de.ibm.com> wrote: > > > On Tue, 2 Dec 2014 21:03:45 +0200 > > "Michael S. Tsirkin" <mst at redhat.com> wrote: > > > > > On Tue, Dec 02, 2014 at 04:41:36PM +0100, Cornelia Huck wrote: > > > >

On 29 May 2013 09:24, Michael S. Tsirkin <mst at redhat.com> wrote: > diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c > index f4db224..fd09ea7 100644 > --- a/hw/virtio/virtio-pci.c > +++ b/hw/virtio/virtio-pci.c > @@ -467,51 +467,70 @@ static uint64_t virtio_pci_config_common_read(void *opaque, hwaddr addr, > { > VirtIOPCIProxy *proxy = opaque; >

On Tue, May 28, 2013 at 12:15:16PM -0500, Anthony Liguori wrote: > > @@ -455,6 +462,226 @@ static void virtio_pci_config_write(void *opaque, hwaddr addr, > > } > > } > > > > +static uint64_t virtio_pci_config_common_read(void *opaque, hwaddr addr, > > + unsigned size) > > +{ > > + VirtIOPCIProxy

OK, here's a patch that implements the virtio spec update that I sent earlier. It supercedes the PUBLISH_USED_IDX patches I sent out earlier. Support is added in both userspace and vhost-net. If you see issues or are just curious, you can turn the new feature off. For example: -global virtio-net-pci.event_idx=on -global virtio-blk-pci.event_idx=off Also, it's possible to try both

OK, here's a patch that implements the virtio spec update that I sent earlier. It supercedes the PUBLISH_USED_IDX patches I sent out earlier. Support is added in both userspace and vhost-net. If you see issues or are just curious, you can turn the new feature off. For example: -global virtio-net-pci.event_idx=on -global virtio-blk-pci.event_idx=off Also, it's possible to try both

OK, here's a patch that implements the virtio spec update that I sent earlier. It supercedes the PUBLISH_USED_IDX patches I sent out earlier. Support is added in both userspace and vhost-net. I see nice performance improvements: e.g. from 12 to 18 Gbit/s host to guest with netperf, but did not spend a lot of time testing performance. I hope others will try this out and report. Note: there

OK, here's a patch that implements the virtio spec update that I sent earlier. It supercedes the PUBLISH_USED_IDX patches I sent out earlier. Support is added in both userspace and vhost-net. I see nice performance improvements: e.g. from 12 to 18 Gbit/s host to guest with netperf, but did not spend a lot of time testing performance. I hope others will try this out and report. Note: there

On Thu, Dec 11, 2014 at 02:25:09PM +0100, Cornelia Huck wrote: > For virtio-1 devices, we allow a more complex queue layout that doesn't > require descriptor table and rings on a physically-contigous memory area: > add virtio_queue_set_rings() to allow transports to set this up. > > Signed-off-by: Cornelia Huck <cornelia.huck at de.ibm.com> > --- >

On Thu, Dec 11, 2014 at 02:25:09PM +0100, Cornelia Huck wrote: > For virtio-1 devices, we allow a more complex queue layout that doesn't > require descriptor table and rings on a physically-contigous memory area: > add virtio_queue_set_rings() to allow transports to set this up. > > Signed-off-by: Cornelia Huck <cornelia.huck at de.ibm.com> > --- >

On Thu, 11 Dec 2014 14:25:07 +0100 Cornelia Huck <cornelia.huck at de.ibm.com> wrote: > With virtio-1, we support more than 32 feature bits. Let's extend both > host and guest features to 64, which should suffice for a while. > > vhost and migration have been ignored for now. > > Signed-off-by: Cornelia Huck <cornelia.huck at de.ibm.com> > --- >

On Thu, 11 Dec 2014 14:25:07 +0100 Cornelia Huck <cornelia.huck at de.ibm.com> wrote: > With virtio-1, we support more than 32 feature bits. Let's extend both > host and guest features to 64, which should suffice for a while. > > vhost and migration have been ignored for now. > > Signed-off-by: Cornelia Huck <cornelia.huck at de.ibm.com> > --- >

On Tue, 2 Dec 2014 21:03:45 +0200 "Michael S. Tsirkin" <mst at redhat.com> wrote: > On Tue, Dec 02, 2014 at 04:41:36PM +0100, Cornelia Huck wrote: > > void virtio_queue_set_num(VirtIODevice *vdev, int n, int num) > > { > > + /* > > + * For virtio-1 devices, the number of buffers may only be > > + * updated if the ring addresses have

On Tue, 2 Dec 2014 21:03:45 +0200 "Michael S. Tsirkin" <mst at redhat.com> wrote: > On Tue, Dec 02, 2014 at 04:41:36PM +0100, Cornelia Huck wrote: > > void virtio_queue_set_num(VirtIODevice *vdev, int n, int num) > > { > > + /* > > + * For virtio-1 devices, the number of buffers may only be > > + * updated if the ring addresses have

Currently virtio-pci is specified so that configuration of the device is done through a PCI IO space (via BAR 0 of the virtual PCI device). However, Linux guests happen to use ioread/iowrite/iomap primitives for access, and these work uniformly across memory/io BARs. While PCI IO accesses are faster than MMIO on x86 kvm, MMIO might be helpful on other systems: for example IBM pSeries machines not