From: Jan Kiszka
Various changes in the recent kernel versions broke the build due to
missing function and header stubs.
Signed-off-by: Jan Kiszka
---
tools/virtio/crypto/hash.h | 0
tools/virtio/linux/dma-mapping.h | 2 ++
tools/virtio/linux/kernel.h | 2 ++
3 files changed, 4
On Sun, Oct 13, 2019 at 03:29:34PM +0200, Jan Kiszka wrote:
> On 13.10.19 14:20, Michael S. Tsirkin wrote:
> > On Sun, Oct 13, 2019 at 02:01:03PM +0200, Jan Kiszka wrote:
> >> On 13.10.19 13:52, Michael S. Tsirkin wrote:
> >>> On Sun, Oct 13, 2019 at 11:03:30AM +0200, Jan Kiszka wrote:
>
The idea is to support multiple ring formats by converting
to a format-independent array of descriptors.
This costs extra cycles, but we gain in ability
to fetch a batch of descriptors in one go, which
is good for code cache locality.
When used, this causes a minor performance degradation,
it's
With this patch applied, new and old code perform identically.
Lots of extra optimizations are now possible, e.g.
we can fetch multiple heads with copy_from/to_user now.
We can get rid of maintaining the log array. Etc etc.
Signed-off-by: Michael S. Tsirkin
---
drivers/vhost/test.c | 2 +-
This adds infrastructure required for supporting
multiple ring formats.
The idea is as follows: we convert descriptors to an
independent format first, and process that converting to
iov later.
The point is that we have a tight loop that fetches
descriptors, which is good for cache utilization.
Add a writeable module parameter that tests
the new code. Note: no effort was made to ensure
things work correctly if the parameter is changed
while the device is open. Make sure to
close the device before changing its value.
Signed-off-by: Michael S. Tsirkin
---
drivers/vhost/test.c | 17
Add a writeable module parameter that tests
the new code. Note: no effort was made to ensure
things work correctly if the parameter is changed
while the device is open. Make sure to
close the device before changing its value.
Signed-off-by: Michael S. Tsirkin
---
drivers/vhost/net.c | 32
On 13.10.19 13:52, Michael S. Tsirkin wrote:
> On Sun, Oct 13, 2019 at 11:03:30AM +0200, Jan Kiszka wrote:
>> From: Jan Kiszka
>>
>> Various changes in the recent kernel versions broke the build due to
>> missing function and header stubs.
>>
>> Signed-off-by: Jan Kiszka
>
> Thanks!
> I think
On Sun, Oct 13, 2019 at 02:01:03PM +0200, Jan Kiszka wrote:
> On 13.10.19 13:52, Michael S. Tsirkin wrote:
> > On Sun, Oct 13, 2019 at 11:03:30AM +0200, Jan Kiszka wrote:
> >> From: Jan Kiszka
> >>
> >> Various changes in the recent kernel versions broke the build due to
> >> missing function and
This adds infrastructure required for supporting
multiple ring formats.
The idea is as follows: we convert descriptors to an
independent format first, and process that converting to
iov later.
The point is that we have a tight loop that fetches
descriptors, which is good for cache utilization.
The idea is to support multiple ring formats by converting
to a format-independent array of descriptors.
This costs extra cycles, but we gain in ability
to fetch a batch of descriptors in one go, which
is good for code cache locality.
When used, this causes a minor performance degradation,
it's
With this patch applied, new and old code perform identically.
Lots of extra optimizations are now possible, e.g.
we can fetch multiple heads with copy_from/to_user now.
We can get rid of maintaining the log array. Etc etc.
Signed-off-by: Michael S. Tsirkin
---
drivers/vhost/test.c | 2 +-
Add a writeable module parameter that tests
the new code. Note: no effort was made to ensure
things work correctly if the parameter is changed
while the device is open. Make sure to
close the device before changing its value.
Signed-off-by: Michael S. Tsirkin
---
drivers/vhost/test.c | 17
fetch_buf already guarantees we exit on a descriptor without a NEXT
flag. Add a BUG_ON statement to make sure we don't overflow the buffer
in case of a bug.
Signed-off-by: Michael S. Tsirkin
---
drivers/vhost/vhost.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/vhost/vhost.c
Add a writeable module parameter that tests
the new code. Note: no effort was made to ensure
things work correctly if the parameter is changed
while the device is open. Make sure to
close the device before changing its value.
Signed-off-by: Michael S. Tsirkin
---
drivers/vhost/net.c | 32
On 13.10.19 14:20, Michael S. Tsirkin wrote:
> On Sun, Oct 13, 2019 at 02:01:03PM +0200, Jan Kiszka wrote:
>> On 13.10.19 13:52, Michael S. Tsirkin wrote:
>>> On Sun, Oct 13, 2019 at 11:03:30AM +0200, Jan Kiszka wrote:
From: Jan Kiszka
Various changes in the recent kernel versions
On Sun, Oct 13, 2019 at 11:03:30AM +0200, Jan Kiszka wrote:
> From: Jan Kiszka
>
> Various changes in the recent kernel versions broke the build due to
> missing function and header stubs.
>
> Signed-off-by: Jan Kiszka
Thanks!
I think it's already fixes in the vhost tree.
That tree also
On Fri, Oct 11, 2019 at 06:25:19PM -0700, Ram Pai wrote:
> From: Thiago Jung Bauermann
>
> Normally, virtio enables DMA API with VIRTIO_F_IOMMU_PLATFORM, which must
> be set by both device and guest driver. However, as a hack, when DMA API
> returns physical addresses, guest driver can use the
On Fri, Oct 11, 2019 at 06:25:18PM -0700, Ram Pai wrote:
> From: Thiago Jung Bauermann
>
> In order to safely use the DMA API, virtio needs to know whether DMA
> addresses are in fact physical addresses and for that purpose,
> dma_addr_is_phys_addr() is introduced.
>
> cc: Benjamin
On 2019/10/13 上午4:36, Michael S. Tsirkin wrote:
On Sat, Oct 12, 2019 at 03:30:52PM +0800, Jason Wang wrote:
On 2019/10/11 下午9:46, Michael S. Tsirkin wrote:
With this patch applied, new and old code perform identically.
Lots of extra optimizations are now possible, e.g.
we can fetch multiple
On 2019/10/13 上午4:27, Michael S. Tsirkin wrote:
On Sat, Oct 12, 2019 at 03:28:49PM +0800, Jason Wang wrote:
On 2019/10/11 下午9:45, Michael S. Tsirkin wrote:
The idea is to support multiple ring formats by converting
to a format-independent array of descriptors.
This costs extra cycles, but we
21 matches
Mail list logo