This patch add the function to map/unmap the usermode queue into the HW,
using the prepared MQD and other objects. After this mapping, the queue
will be ready to accept the workload.
Cc: Alex Deucher
Cc: Christian Koenig
Signed-off-by: Shashank Sharma
---
drivers/gpu/drm/amd/amdgpu/amdgpu_use
From: Arunpravin Paneer Selvam
This is a WIP patch, which adds an kernel implementation of secure
semaphore for the usermode queues. The UAPI for the same is yet to
be implemented.
The idea is to create a RO page and map it to each process requesting a
user mode queue, and give them a qnique off
From: Arvind Yadav
MQD describes the properies of a user queue to the HW, and allows it to
accurately configure the queue while mapping it in GPU HW. This patch
adds:
- A new header file which contains the MQD definition
- A new function which creates an MQD object and fills it with userqueue
d
The FW expects us to allocate atleast one page as process
context space, and one for gang context space. This patch adds some
object for the same.
Cc: Alex Deucher
Cc: Christian Koenig
Signed-off-by: Shashank Sharma
---
drivers/gpu/drm/amd/amdgpu/amdgpu_userqueue.c | 57 +++
.
This patch allocates a doorbell slot in the bar, for the usermode queue.
We are using the unique queue-id to get this slot from MES.
Cc: Alex Deucher
Cc: Christian Koenig
Signed-off-by: Shashank Sharma
---
drivers/gpu/drm/amd/amdgpu/amdgpu_userqueue.c | 28 +++
1 file changed,
This patch adds skeleton code for usermode queue creation. It
typically contains:
- A new structure to keep all the user queue data in one place.
- An IOCTL function to create/free a usermode queue.
- A function to generate unique index for the queue.
- A global ptr in amdgpu_dev
Cc: Alex Deucher
From: Alex Deucher
This patch intorduces new UAPI/IOCTL for usermode graphics
queue. The userspace app will fill this structure and request
the graphics driver to add a graphics work queue for it. The
output of this UAPI is a queue id.
This UAPI maps the queue into GPU, so the graphics app can s
This is a RFC series to implement usermode graphics queues for AMDGPU
driver (Navi 3X and above). The idea of usermode graphics queue is to
allow direct workload submission from a userspace graphics process who
has amdgpu graphics context.
Once we have some initial feedback on the design, we will
On 12/14/22 04:01, Pekka Paalanen wrote:
> On Tue, 13 Dec 2022 18:20:59 +0100
> Michel Dänzer wrote:
>
>> On 12/12/22 19:21, Harry Wentland wrote:
>>> This will let us pass kms_hdr.bpc_switch.
>>>
>>> I don't see any good reasons why we still need to
>>> limit bpc to 8 bpc and doing so is prob
What about a system with multiple GPUs?
Hybrid graphics?
Headless systems?
Regards
//Ernst
Den tors 22 dec. 2022 kl 19:30 skrev Mario Limonciello <
mario.limoncie...@amd.com>:
> If the probe sequence fails then the user is stuck with a frozen
> screen and can only really recover via SSH or by re
On 12/22/22 13:41, Javier Martinez Canillas wrote:
[adding Thomas Zimmermann to CC list]
Hello Mario,
Interesting case.
On 12/22/22 19:30, Mario Limonciello wrote:
One of the first thing that KMS drivers do during initialization is
destroy the system firmware framebuffer by means of
`drm_aper
On Thu, Dec 22, 2022 at 10:20:37PM +0100, Michal Kubecek wrote:
> Unfortunately, just like Boris, I always seem to have multiple stack
> traces tangled together.
See if this fixes it:
https://lore.kernel.org/r/20221219104718.21677-1-christian.koe...@amd.com
Thx.
--
Regards/Gruss,
Boris.
h
On Mon, Dec 19, 2022 at 09:23:05AM +0100, Christian König wrote:
> Am 17.12.22 um 12:53 schrieb Borislav Petkov:
> > Hi folks,
> >
> > this is with Linus' tree from Wed:
> >
> > 041fae9c105a ("Merge tag 'f2fs-for-6.2-rc1' of
> > git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs")
> >
>
On Mon, Dec 19, 2022 at 11:47:18AM +0100, Christian König wrote:
> That function consumes the reference.
>
> Signed-off-by: Christian König
> Fixes: aab9cf7b6954 ("drm/amdgpu: use scheduler dependencies for VM updates")
Tested-by: Michal Kubecek
I can still see weird artefacts in some windows
HPD signals on DVI ports can be fired off before the pins required for
DDC probing actually make contact, due to the pins for HPD making
contact first. This results in a HPD signal being asserted but DDC
probing failing, resulting in hotplugging occasionally failing.
Rescheduling the hotplug work
Hi xinhui,
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url:
https://github.com/intel-lab-lkp/linux/commits/xinhui-pan/drm-Optimise-for-continuous-memory-allocation/20221218-145922
base: git://anongit.freedesktop.org/drm/drm-misc drm-misc-next
patch link:
https://lo
16 matches
Mail list logo