Change-Id: Ic1b96b6efd2997240a26b6d8bc00e69f05ea4676
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/powerplay/smumgr/iceland_smc.c | 8
drivers/gpu/drm/amd/powerplay/smumgr/tonga_smc.c | 6 +++---
2 files changed, 7 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/amd/powerp
Change-Id: If3ab520f8c65bec070e97cd8787041919d687ad3
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c | 79 +
1 file changed, 79 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index d
On Thu, Sep 07, 2017 at 09:13:32AM +0200, Christian König wrote:
> Ping? David can you take a look?
>
> Alex is on vacation and that is a rather important bug fix.
Works better when you cc Gustavo/Maarten/Sumits/Chris I think, for
anything dma-buf review needing.
-Daniel
>
> Thanks,
> Christian
Signed-off-by: Alexandre Demers
---
drivers/gpu/drm/amd/amdgpu/vce_v1_0.c | 384 ++
drivers/gpu/drm/amd/amdgpu/vce_v1_0.h | 29 +++
2 files changed, 413 insertions(+)
create mode 100644 drivers/gpu/drm/amd/amdgpu/vce_v1_0.c
create mode 100644 drivers/gpu/drm/amd
Inspired on how it is done under radeon for UVD firmwares.
Signed-off-by: Alexandre Demers
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c | 100
1 file changed, 75 insertions(+), 25 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
b/drivers/gpu/dr
Signed-off-by: Alexandre Demers
---
drivers/gpu/drm/amd/amdgpu/si.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c
index 08998639daeb..bb860faa8a95 100644
--- a/drivers/gpu/drm/amd/amdgpu/si.c
+++ b/drivers/gpu
This is the foundation for VCE 1 implementation, mostly ported from radeon to
amdgpu. This should have no impact for now on the usability of the driver. This
is the pretty straight-forward part. The heavier part is coming as a RFC.
I'd like to have this first part available to all, since I don't
Signed-off-by: Alexandre Demers
---
drivers/gpu/drm/amd/amdgpu/vce_v1_0.c | 62 ---
1 file changed, 36 insertions(+), 26 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v1_0.c
b/drivers/gpu/drm/amd/amdgpu/vce_v1_0.c
index f541a4b5ac51..ab3b834758c6 10064
Signed-off-by: Alexandre Demers
---
drivers/gpu/drm/radeon/radeon_uvd.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c
b/drivers/gpu/drm/radeon/radeon_uvd.c
index 7431eb4a11b7..b4fb07ad9f4a 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
For consistency with other files under amdgpu driver.
Signed-off-by: Alexandre Demers
---
drivers/gpu/drm/amd/amdgpu/si.c| 15 +++-
drivers/gpu/drm/amd/amdgpu/si_dma.c| 5 +-
drivers/gpu/drm/amd/amdgpu/si_ih.c | 21 +++---
drivers/gpu/drm/amd/
>>+if (write)
>>+amdgpu_asic_invalidate_hdp(adev);
> You can drop the HDP invalidation here. amdgpu_gem_prime_pin() will pin the
> BO into system memory.
My understanding here is between CPU and GPU access, the invalidate/flush is
still needed, since amdgpu_gem_prime_pin() does not d
Reviewed-by: Felix Kuehling
Thanks,
Felix
On 2017-09-07 06:11 AM, Christian König wrote:
> From: Christian König
>
> This is quite controversial because it adds another lock which is held during
> page table updates, but I don't see much other option.
>
> v2: allow multiple updates to be in
On 09/07/2017 08:08 AM, Christian König wrote:
Am 06.09.2017 um 18:33 schrieb Leo Liu:
On 09/06/2017 11:51 AM, Christian König wrote:
From: Christian König
Use the VM instead of the BO list to find the BO for a virtual address.
This fixes UVD/VCE in physical mode with VM local BOs.
The
Am 06.09.2017 um 18:33 schrieb Leo Liu:
On 09/06/2017 11:51 AM, Christian König wrote:
From: Christian König
Use the VM instead of the BO list to find the BO for a virtual address.
This fixes UVD/VCE in physical mode with VM local BOs.
The series is
Tested-by: Leo Liu
Can I get an rb o
Am 07.09.2017 um 13:23 schrieb Bas Nieuwenhuizen:
When amdgpu_vm_frag_ptes calls amdgpu_vm_update_ptes and the pt
has a shadow PT we mirror all the write to the shadow PT too, which
results in twice the commands.
Signed-off-by: Bas Nieuwenhuizen
Good catch. Patch is Reviewed-by: Christian Kön
When amdgpu_vm_frag_ptes calls amdgpu_vm_update_ptes and the pt
has a shadow PT we mirror all the write to the shadow PT too, which
results in twice the commands.
Signed-off-by: Bas Nieuwenhuizen
---
The current patch is quite pessimistic, maybe someone familiar with the
code knows a better set
From: Christian König
This is quite controversial because it adds another lock which is held during
page table updates, but I don't see much other option.
v2: allow multiple updates to be in flight at the same time
v3: simplify the patch, take the read side only once
Signed-off-by: Christian Kö
From: Christian König
Do a fork() to force some MMU callbacks.
Signed-off-by: Christian König
---
tests/amdgpu/basic_tests.c | 8
1 file changed, 8 insertions(+)
diff --git a/tests/amdgpu/basic_tests.c b/tests/amdgpu/basic_tests.c
index 80d15e7..18bcf91 100644
--- a/tests/amdgpu/basi
Acked-by: Chunming Zhou
On 2017年09月05日 03:02, Christian König wrote:
From: Christian König
With shared reservation objects __ttm_bo_reserve() can easily fail even on
destroyed BOs. This prevents correct handling when we need to individualize
the reservation object.
Fix this by individualizi
On 2017年09月07日 15:13, Christian König wrote:
Ping? David can you take a look?
Alex is on vacation and that is a rather important bug fix.
Thanks,
Christian.
Am 04.09.2017 um 21:02 schrieb Christian König:
From: Christian König
Stop requiring that the src reservation object is locked for t
Ping? David can you take a look?
Alex is on vacation and that is a rather important bug fix.
Thanks,
Christian.
Am 04.09.2017 um 21:02 schrieb Christian König:
From: Christian König
Stop requiring that the src reservation object is locked for this operation.
Signed-off-by: Christian König
Am 07.09.2017 um 00:04 schrieb Samuel Li:
From: Alex Deucher
Needed to properly flush the HDP cache with the CPU from rather
than the GPU.
Signed-off-by: Alex Deucher
Signed-off-by: Samuel Li
Patches #1-#5 are unnecessary for gem_prime_mmap support() (but don't
completely drop them, we co
Am 07.09.2017 um 00:07 schrieb Samuel Li:
Signed-off-by: Samuel Li
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 3 +
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 3 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c | 95 ++-
3 files changed, 99 insertions(+), 2 de
23 matches
Mail list logo
