Currently, local and remote TLB flushes are not performed concurrently,
which introduces unnecessary overhead - each INVLPG can take 100s of
cycles. This patch-set allows TLB flushes to be run concurrently: first
request the remote CPUs to initiate the flush, then run it locally, and
finally wait
To improve TLB shootdown performance, flush the remote and local TLBs
concurrently. Introduce flush_tlb_multi() that does so. Introduce
paravirtual versions of flush_tlb_multi() for KVM, Xen and hyper-v (Xen
and hyper-v are only compile-tested).
While the updated smp infrastructure is capable of
On Wed, Jul 03, 2019 at 05:53:58PM +0800, Jason Wang wrote:
>
> On 2019/6/28 下午8:36, Stefano Garzarella wrote:
> > Some callbacks used by the upper layers can run while we are in the
> > .remove(). A potential use-after-free can happen, because we free
> > the_virtio_vsock without knowing if the
This patch replaces ast's framebuffer console with DRM's generic
implememtation. All respective code is being removed from the driver.
The console is set up with a shadow buffer. The actual buffer object is
not permanently pinned in video ram, but just another buffer object that
the driver moves
DRM clients, such as the fbdev emulation, have their buffer objects
mapped by default. Mapping a buffer implicitly prevents its relocation.
Hence, the buffer may permanently consume video memory while it's
allocated. This is a problem for drivers of low-memory devices, such as
ast, mgag200 or
The bochs driver (and virtual hardware) requires buffer objects to
reside in video ram to display them to the screen. So it can not
display the framebuffer console because the respective buffer object
is permanently pinned in system memory.
Using a shadow buffer for the console solves this
This patch replaces mgag200's framebuffer console with DRM's generic
implememtation. All respective code is being removed from the driver.
The console is set up with a shadow buffer. The actual buffer object is
not permanently pinned in video ram, but just another buffer object that
the driver
DRM client buffers are permanently mapped throughout their lifetime. This
prevents us from using generic framebuffer emulation for devices with
small dedicated video memory, such as ast or mgag200. With fb buffers
permanently mapped, such devices often won't have enougth space left to
display
The shadow-buffered framebuffer console only needs the buffer object
to be mapped during updates. While not being updated from the shadow
buffer, the buffer object can remain unmapped.
An unmapped buffer object can be evicted to system memory and does
not consume video ram until displayed. This
On 2019/6/28 下午8:36, Stefano Garzarella wrote:
Some callbacks used by the upper layers can run while we are in the
.remove(). A potential use-after-free can happen, because we free
the_virtio_vsock without knowing if the callbacks are over or not.
To solve this issue we move the assignment of
On Mon, Jul 01, 2019 at 07:03:57PM +0200, Stefano Garzarella wrote:
> On Mon, Jul 01, 2019 at 04:11:13PM +0100, Stefan Hajnoczi wrote:
> > On Fri, Jun 28, 2019 at 02:36:56PM +0200, Stefano Garzarella wrote:
> > > During the review of "[PATCH] vsock/virtio: Initialize core virtio vsock
> > > before
Details about this can be found here:
https://lwn.net/Articles/750770/
What's new in this version
==
A new VFIO device type is introduced - vfio-vhost. This addressed
some comments from here: https://patchwork.ozlabs.org/cover/984763/
Below is the updated device
On 2019/7/3 下午5:13, Tiwei Bie wrote:
Details about this can be found here:
https://lwn.net/Articles/750770/
What's new in this version
==
A new VFIO device type is introduced - vfio-vhost. This addressed
some comments from here:
On Wed, Jul 03, 2019 at 10:14:53AM +0100, Stefan Hajnoczi wrote:
> On Mon, Jul 01, 2019 at 07:03:57PM +0200, Stefano Garzarella wrote:
> > On Mon, Jul 01, 2019 at 04:11:13PM +0100, Stefan Hajnoczi wrote:
> > > On Fri, Jun 28, 2019 at 02:36:56PM +0200, Stefano Garzarella wrote:
> > > > During the
Den 03.07.2019 10.33, skrev Thomas Zimmermann:
> This patch replaces ast's framebuffer console with DRM's generic
> implememtation. All respective code is being removed from the driver.
>
> The console is set up with a shadow buffer. The actual buffer object is
> not permanently pinned in video
Den 03.07.2019 10.33, skrev Thomas Zimmermann:
> The bochs driver (and virtual hardware) requires buffer objects to
> reside in video ram to display them to the screen. So it can not
> display the framebuffer console because the respective buffer object
> is permanently pinned in system memory.
Den 03.07.2019 10.33, skrev Thomas Zimmermann:
> This patch replaces mgag200's framebuffer console with DRM's generic
> implememtation. All respective code is being removed from the driver.
>
> The console is set up with a shadow buffer. The actual buffer object is
> not permanently pinned in
On Wed, Jul 03, 2019 at 06:09:51PM +0800, Jason Wang wrote:
> On 2019/7/3 下午5:13, Tiwei Bie wrote:
> > Details about this can be found here:
> >
> > https://lwn.net/Articles/750770/
> >
> > What's new in this version
> > ==
> >
> > A new VFIO device type is introduced -
On Wed, Jul 03, 2019 at 08:16:23PM +0800, Jason Wang wrote:
> On 2019/7/3 下午7:52, Tiwei Bie wrote:
> > On Wed, Jul 03, 2019 at 06:09:51PM +0800, Jason Wang wrote:
> > > On 2019/7/3 下午5:13, Tiwei Bie wrote:
> > > > Details about this can be found here:
> > > >
> > > >
On 2019/7/3 下午7:52, Tiwei Bie wrote:
On Wed, Jul 03, 2019 at 06:09:51PM +0800, Jason Wang wrote:
On 2019/7/3 下午5:13, Tiwei Bie wrote:
Details about this can be found here:
https://lwn.net/Articles/750770/
What's new in this version
==
A new VFIO device type is
Den 03.07.2019 10.32, skrev Thomas Zimmermann:
> DRM clients, such as the fbdev emulation, have their buffer objects
> mapped by default. Mapping a buffer implicitly prevents its relocation.
> Hence, the buffer may permanently consume video memory while it's
> allocated. This is a problem for
On 03.07.19 01:51, Nadav Amit wrote:
To improve TLB shootdown performance, flush the remote and local TLBs
concurrently. Introduce flush_tlb_multi() that does so. Introduce
paravirtual versions of flush_tlb_multi() for KVM, Xen and hyper-v (Xen
and hyper-v are only compile-tested).
While the
On Tue, Jul 2, 2019 at 7:19 AM Gerd Hoffmann wrote:
>
> Call reservation_object_* directly instead
> of using ttm_bo_{reserve,unreserve}.
>
> v4: check for EINTR only.
> v3: check for EINTR too.
>
> Signed-off-by: Gerd Hoffmann
> Reviewed-by: Daniel Vetter
> ---
>
> On Jul 3, 2019, at 7:04 AM, Juergen Gross wrote:
>
> On 03.07.19 01:51, Nadav Amit wrote:
>> To improve TLB shootdown performance, flush the remote and local TLBs
>> concurrently. Introduce flush_tlb_multi() that does so. Introduce
>> paravirtual versions of flush_tlb_multi() for KVM, Xen and
On 03/07/2019 18:02, Nadav Amit wrote:
>> On Jul 3, 2019, at 7:04 AM, Juergen Gross wrote:
>>
>> On 03.07.19 01:51, Nadav Amit wrote:
>>> To improve TLB shootdown performance, flush the remote and local TLBs
>>> concurrently. Introduce flush_tlb_multi() that does so. Introduce
>>> paravirtual
> On Jul 3, 2019, at 10:43 AM, Andrew Cooper wrote:
>
> On 03/07/2019 18:02, Nadav Amit wrote:
>>> On Jul 3, 2019, at 7:04 AM, Juergen Gross wrote:
>>>
>>> On 03.07.19 01:51, Nadav Amit wrote:
To improve TLB shootdown performance, flush the remote and local TLBs
concurrently.
On Wed, 3 Jul 2019 17:13:39 +0800
Tiwei Bie wrote:
> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
> index 8f10748dac79..6c5718ab7eeb 100644
> --- a/include/uapi/linux/vfio.h
> +++ b/include/uapi/linux/vfio.h
> @@ -201,6 +201,7 @@ struct vfio_device_info {
> #define
On Tue, Jul 2, 2019 at 7:19 AM Gerd Hoffmann wrote:
>
> Rework fencing workflow, starting with virtio_gpu_execbuffer_ioctl.
> Stop using ttm helpers, use the virtio_gpu_array_* helpers (which work
> on the reservation objects directly) instead.
>
> New workflow:
>
> (1) All gem objects needed by
Den 03.07.2019 10.32, skrev Thomas Zimmermann:
> DRM client buffers are permanently mapped throughout their lifetime. This
> prevents us from using generic framebuffer emulation for devices with
> small dedicated video memory, such as ast or mgag200. With fb buffers
> permanently mapped, such
On Tue, Jul 2, 2019 at 7:19 AM Gerd Hoffmann wrote:
>
> Some helper functions to manage an array of gem objects.
>
> v6:
> - add ticket to struct virtio_gpu_object_array.
> - add virtio_gpu_array_{lock,unlock}_resv helpers.
> - add virtio_gpu_array_add_fence helper.
> v5: some small
On Thu, Jul 04, 2019 at 12:27:08AM +0800, Fuqian Huang wrote:
> kmemdup is introduced to duplicate a region of memory in a neat way.
> Rather than kmalloc/kzalloc + memcpy, which the programmer needs to
> write the size twice (sometimes lead to mistakes), kmemdup improves
> readability, leads to
On Wed, Jul 3, 2019 at 11:31 AM Chia-I Wu wrote:
>
> On Tue, Jul 2, 2019 at 7:19 AM Gerd Hoffmann wrote:
> >
> > Some helper functions to manage an array of gem objects.
> >
> > v6:
> > - add ticket to struct virtio_gpu_object_array.
> > - add virtio_gpu_array_{lock,unlock}_resv helpers.
> >
On Tue, Jul 2, 2019 at 7:19 AM Gerd Hoffmann wrote:
>
> Switch to the virtio_gpu_array_* helper workflow.
>
> Signed-off-by: Gerd Hoffmann
> ---
> drivers/gpu/drm/virtio/virtgpu_drv.h | 2 +-
> drivers/gpu/drm/virtio/virtgpu_ioctl.c | 43 --
>
On Tue, Jul 2, 2019 at 7:19 AM Gerd Hoffmann wrote:
>
> Switch to the virtio_gpu_array_* helper workflow.
(just repeating my question on patch 6)
Does this fix the obj refcount issue? When was the issue introduced?
>
> Signed-off-by: Gerd Hoffmann
> ---
> drivers/gpu/drm/virtio/virtgpu_drv.h
On Wed, Jul 03, 2019 at 12:31:57PM -0600, Alex Williamson wrote:
> On Wed, 3 Jul 2019 17:13:39 +0800
> Tiwei Bie wrote:
> > diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
> > index 8f10748dac79..6c5718ab7eeb 100644
> > --- a/include/uapi/linux/vfio.h
> > +++
On 2019/6/28 下午8:36, Stefano Garzarella wrote:
Before to call vdev->config->reset(vdev) we need to be sure that
no one is accessing the device, for this reason, we add new variables
in the struct virtio_vsock to stop the workers during the .remove().
This patch also add few comments before
On 2019/7/3 下午6:41, Stefano Garzarella wrote:
On Wed, Jul 03, 2019 at 05:53:58PM +0800, Jason Wang wrote:
On 2019/6/28 下午8:36, Stefano Garzarella wrote:
Some callbacks used by the upper layers can run while we are in the
.remove(). A potential use-after-free can happen, because we free
On 2019/7/3 下午9:08, Tiwei Bie wrote:
On Wed, Jul 03, 2019 at 08:16:23PM +0800, Jason Wang wrote:
On 2019/7/3 下午7:52, Tiwei Bie wrote:
On Wed, Jul 03, 2019 at 06:09:51PM +0800, Jason Wang wrote:
On 2019/7/3 下午5:13, Tiwei Bie wrote:
Details about this can be found here:
38 matches
Mail list logo