[Why]
1. we never submit IBs to the KIQ
2. there seems to be ~500ms delay during amdgpu resume spent in KIQ,
hence, KIQ interrupts are not working correctly.
[How]
remove interrupt handling for KIQ.
Signed-off-by: Shirish S
---
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 59 -
On 10/4/2018 12:41 PM, Christian König wrote:
Am 03.10.2018 um 17:15 schrieb Shirish S:
From: Pratik Vishwakarma
[Why]
1. We never submit IBs to KIQ.
2. Ring test pass without KIQ's ring also.
3. By skipping we see an improvement of around 500ms
in the amdgpu's resume time.
[How]
skip I
Hi, Emil,
On 10/04/2018 04:12 PM, Emil Velikov wrote:
> On Sun, 30 Sep 2018 at 18:31, Thomas Hellstrom wrote:
>> Hi, Emil,
>>
>> On 09/05/2018 03:53 PM, Emil Velikov wrote:
>>> On 5 September 2018 at 14:20, Thomas Hellstrom
>>> wrote:
>>>
> In that case, please give me 24h to do a libdrm re
Hi Dave,
Just two small fixes for 4.19:
- Fix an ordering issue in DC with respect to atomic flips that could result
in a crash
- Fix incorrect use of process->mm in KFD
The following changes since commit d8938c981f58ee344687b7910a611ac345960045:
Merge branch 'drm-tda9950-fixes' of git://git
On Sun, 30 Sep 2018 at 18:31, Thomas Hellstrom wrote:
>
> Hi, Emil,
>
> On 09/05/2018 03:53 PM, Emil Velikov wrote:
> > On 5 September 2018 at 14:20, Thomas Hellstrom
> > wrote:
> >
> >>> In that case, please give me 24h to do a libdrm release before pushing.
> >>> I had to push some workarounds
On Wed, 19 Sep 2018 at 10:31, Chunming Zhou wrote:
>
> Signed-off-by: Chunming Zhou
> ---
> include/drm/amdgpu_drm.h | 10 ++
> 1 file changed, 10 insertions(+)
>
For this and 1/5 - see include/drm/README and git log for examples how
files in include/drm should be updated.
I'll pull merg
And drop the now superflous extra reservations.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 4
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 15 ++-
2 files changed, 6 insertions(+), 13 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
This allows us to drop the extra reserve in TTM.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 6 --
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 4 ++--
2 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
b/drivers
The driver is now responsible to allocate enough shared slots.
Signed-off-by: Christian König
---
drivers/gpu/drm/ttm/ttm_bo.c | 27 ++-
1 file changed, 6 insertions(+), 21 deletions(-)
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 83b465
Let's support simultaneous submissions to multiple engines.
v2: rename the field to num_shared and fix up all users
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 10 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 2 +-
drivers/gpu/drm/amd/
It is perfectly possible that the BO list is created before the BO is
exported. While at it cleanup setting shared to one instead of true.
v2: add comment and simplify logic
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 1 -
drivers/gpu/drm/amd/amdgpu/amdgpu_
Let's support simultaneous submissions to multiple engines.
Signed-off-by: Christian König
---
drivers/dma-buf/reservation.c| 13 -
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 +-
drivers/gpu/drm/amd/amdgpu/a
Set shared_max to the number of shared fences right before we release
the lock.
This way every attempt to add a shared fence without previously
reserving a slot will cause an error.
Signed-off-by: Christian König
---
include/linux/reservation.h | 5 +
1 file changed, 5 insertions(+)
diff -
No need for that any more. Just replace the list when there isn't enough
room any more for the additional fence.
Signed-off-by: Christian König
---
drivers/dma-buf/reservation.c | 178 ++
include/linux/reservation.h | 4 -
2 files changed, 58 insertion
That also simplifies handling quite a bit.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 7 ++-
1 file changed, 2 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 9a5b252784a1..
Looks like not only the SDMA has a problem with this, but also the VCE
firmware :(
Please add a comment to explain why we do this, with that done the patch
is Reviewed-by: Christian König .
Regards,
Christian.
Am 03.10.2018 um 16:39 schrieb Christian König:
Am 29.09.2018 um 11:48 schrieb Em
Is my understanding correct?
Yes, of hand that sounds correct to me.
The other occasions should just be early bail out to optimize things
under memory pressure.
Christian.
Am 03.10.2018 um 22:31 schrieb Philip Yang:
Hi Christian,
Yes, I agree. I am working on patch 2 to replace get_user_pa
Allow setting the power limit to 150% of the default one, like
Windows driver does.
Signed-off-by: Aleksandr Mezin
---
drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune
And initialize it to the default limit for now.
Will allow increasing the power limit on select cards.
Signed-off-by: Aleksandr Mezin
---
drivers/gpu/drm/amd/include/kgd_pp_interface.h | 2 +-
drivers/gpu/drm/amd/powerplay/amd_powerplay.c | 8
drivers/gpu/drm/amd/powerp
Am 03.10.2018 um 17:15 schrieb Shirish S:
From: Pratik Vishwakarma
[Why]
1. We never submit IBs to KIQ.
2. Ring test pass without KIQ's ring also.
3. By skipping we see an improvement of around 500ms
in the amdgpu's resume time.
[How]
skip IB tests for KIQ ring type.
Signed-off-by: Shiris
20 matches
Mail list logo
