On 2018-02-09 07:01 AM, Chunming Zhou wrote:
> On 2018年02月08日 17:13, Chunming Zhou wrote:
>> On 2018年02月08日 17:01, Michel Dänzer wrote:
>>>
>>> this change completely broke radeonsi due to memory management errors
>>> (see valgrind output for glxgears below), so I had to revert it.
>> ok, I will lo
On 2018-02-09 03:44 AM, Chunming Zhou wrote:
> it will be used to check if the driver needs swiotlb
> v2: Don't use inline, instead, move function to drm_memory.c (Mechel Daenzer
> )
Typo in my first name. With that fixed,
Reviewed-by: Michel Dänzer
--
Earthling Michel Dänzer |
Change-Id: Ibb250af8a8cf2af0c30acbad16a354ed0dffa130
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 22 ++
1 file changed, 14 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
b/drivers/gpu/drm/amd/powe
v2: fix build error.
Change-Id: I6e07f574aeca7805d308d37a9072e28848146214
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 22 ++
1 file changed, 14 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
b/dr
On 02/07/2018 02:48 PM, Christian König wrote:
Start to use amdgpu_bo_create_reserved.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 91 -
1 file changed, 21 insertions(+), 70 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdg
Am 09.02.2018 um 13:20 schrieb Andrey Grodzovsky:
On 02/07/2018 02:48 PM, Christian König wrote:
Start to use amdgpu_bo_create_reserved.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 91
-
1 file changed, 21 insertions(+), 7
Leo could you give this patch on Raven a try and review/ack it?
I've tested patch #1 on Vega10, but I don't have a stable Raven system
to test this one.
Thanks,
Christian.
Am 07.02.2018 um 20:48 schrieb Christian König:
Start to use amdgpu_bo_create_reserved.
Signed-off-by: Christian König
I really wonder if sharing the GPUVM instance from a render node file
descriptor wouldn't be easier.
You could just use the existing IOCTL for allocating and mapping memory
on a render node and then give the prepared fd to kfd to use.
Regards,
Christian.
Am 07.02.2018 um 02:32 schrieb Felix
On 02/09/2018 07:31 AM, Christian König wrote:
Am 09.02.2018 um 13:20 schrieb Andrey Grodzovsky:
On 02/07/2018 02:48 PM, Christian König wrote:
Start to use amdgpu_bo_create_reserved.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 91
--
On 02/02/18 02:09 PM, Christian König wrote:
This allows access to pages allocated through the driver with optional
IOMMU mapping.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 57 -
1 file changed, 35 insertions(+), 22 deletions
Am 09.02.2018 um 14:32 schrieb Tom St Denis:
On 02/02/18 02:09 PM, Christian König wrote:
[SNIP]
+ if (p->mapping != adev->mman.bdev.dev_mapping)
+ return -EPERM;
This comparison fails for both IOMMU and non-IOMMU devices in my
carrizo+polaris10 box.
The address being read
On 09/02/18 08:56 AM, Christian König wrote:
Am 09.02.2018 um 14:32 schrieb Tom St Denis:
On 02/02/18 02:09 PM, Christian König wrote:
[SNIP]
+ if (p->mapping != adev->mman.bdev.dev_mapping)
+ return -EPERM;
This comparison fails for both IOMMU and non-IOMMU devices in my
c
Am 09.02.2018 um 15:02 schrieb Tom St Denis:
On 09/02/18 08:56 AM, Christian König wrote:
Am 09.02.2018 um 14:32 schrieb Tom St Denis:
On 02/02/18 02:09 PM, Christian König wrote:
[SNIP]
+ if (p->mapping != adev->mman.bdev.dev_mapping)
+ return -EPERM;
This comparison fails
On 09/02/18 09:12 AM, Christian König wrote:
No, there is simply no need to initialize the system domain. What are
the values of p->mapping and adev->mman.bdev.dev_mapping when they don't
match? Maybe we are allocating memory before initializing
adev->mman.bdev.dev_mapping.
In my test setup I
Am 09.02.2018 um 15:51 schrieb Tom St Denis:
On 09/02/18 09:12 AM, Christian König wrote:
No, there is simply no need to initialize the system domain. What are
the values of p->mapping and adev->mman.bdev.dev_mapping when they
don't match? Maybe we are allocating memory before initializing
ade
On 02/09/2018 07:32 AM, Christian König wrote:
Leo could you give this patch on Raven a try and review/ack it?
Sure.
Leo
I've tested patch #1 on Vega10, but I don't have a stable Raven system
to test this one.
Thanks,
Christian.
Am 07.02.2018 um 20:48 schrieb Christian König:
Start to
On 09/02/18 09:56 AM, Christian König wrote:
Am 09.02.2018 um 15:51 schrieb Tom St Denis:
On 09/02/18 09:12 AM, Christian König wrote:
No, there is simply no need to initialize the system domain. What are
the values of p->mapping and adev->mman.bdev.dev_mapping when they
don't match? Maybe we
On Thu, Feb 1, 2018 at 9:13 PM, Chris Chiu wrote:
> On Thu, Feb 1, 2018 at 12:08 AM, Harry Wentland
> wrote:
>> On 2018-01-31 09:31 AM, Chris Chiu wrote:
>>> Hi,
>>> We are working with new laptops that have the AMD Ravenl Ridge
>>> chipset with this `/proc/cpuinfo`
>>> https://gist.github.c
Please provide a better message body. E.g.,
Lock the dpm levels when we modify the dpm tables to avoid a possible race with
the smu.
With that:
Reviewed-by: Alex Deucher
From: amd-gfx on behalf of Rex Zhu
Sent: Friday, February 9, 2018 3:49 AM
To: amd-g
From: Christian König
This allows access to pages allocated through the driver with optional
IOMMU mapping.
v2: Fix number of bytes copied and add write method
Original-by: Christian König
Signed-off-by: Tom St Denis
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 110 +
Signed-off-by: Harry Wentland
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index 7d2805729c20..0a0f2eb67c01 100644
--- a/drivers/gpu/drm/amd/amdg
On 09/02/18 12:27 PM, Tom St Denis wrote:
From: Christian König
Oops, I'll remove this from the commit message before pushing :-)
I did give you credit below though.
Tom
This allows access to pages allocated through the driver with optional
IOMMU mapping.
v2: Fix number of bytes copied a
Am 09.02.2018 um 18:28 schrieb Harry Wentland:
Signed-off-by: Harry Wentland
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index 7d2805729c20.
Am 09.02.2018 um 18:28 schrieb Tom St Denis:
On 09/02/18 12:27 PM, Tom St Denis wrote:
From: Christian König
Oops, I'll remove this from the commit message before pushing :-)
I did give you credit below though.
The patch before this one isn't merged yet because I'm still not sure if
that
On 09/02/18 01:17 PM, Christian König wrote:
Am 09.02.2018 um 18:28 schrieb Tom St Denis:
On 09/02/18 12:27 PM, Tom St Denis wrote:
From: Christian König
Oops, I'll remove this from the commit message before pushing :-)
I did give you credit below though.
The patch before this one isn't m
Am 09.02.2018 um 19:19 schrieb Tom St Denis:
On 09/02/18 01:17 PM, Christian König wrote:
Am 09.02.2018 um 18:28 schrieb Tom St Denis:
On 09/02/18 12:27 PM, Tom St Denis wrote:
From: Christian König
Oops, I'll remove this from the commit message before pushing :-)
I did give you credit bel
v2: Use NULL and reverse christmas tree ordering
Signed-off-by: Harry Wentland
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index 7d2805729c20..
On 2018-02-09 07:34 AM, Christian König wrote:
> I really wonder if sharing the GPUVM instance from a render node file
> descriptor wouldn't be easier.
>
> You could just use the existing IOCTL for allocating and mapping
> memory on a render node and then give the prepared fd to kfd to use.
In amd
On Fri, Feb 9, 2018 at 1:49 PM, Harry Wentland wrote:
> v2: Use NULL and reverse christmas tree ordering
>
> Signed-off-by: Harry Wentland
Reviewed-by: Alex Deucher
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/drive
From: KaiChieh Chuang
This fix a bug in dapm_widget_power_read_file(),
where it may sent opposite order of source/sink widget
into the p->connected().
for example,
static int connected_check(source, sink);
{"w_sink", NULL, "w_source", connected_check}
the dapm_widget_power_read_file() will quer
dce_clock_set_min_clocks_state() assigns (intentionally) a value of type
'enum dm_pp_clocks_state' to a variable of type 'enum dm_pp_power_level'
without an explicit cast. This causes clang to raise the following
warning:
drivers/gpu/drm/amd/amdgpu/../display/dc/dce/dce_clocks.c:308:4: error:
im
Sorry, I unintentionally 'recycled' git send-email parameters, please
ignore this patch :(
El Fri, Feb 09, 2018 at 01:22:13PM -0800 Matthias Kaehlcke ha dit:
> From: KaiChieh Chuang
>
> This fix a bug in dapm_widget_power_read_file(),
> where it may sent opposite order of source/sink widget
> i
This is really just a copy of dm_pp_clocks_state, so just use that one.
Thanks to Matthias Kaehlke for spotting this.
Signed-off-by: Harry Wentland
---
drivers/gpu/drm/amd/display/dc/dm_services_types.h | 19 +--
1 file changed, 1 insertion(+), 18 deletions(-)
diff --git a/driv
On 2018-02-09 04:28 PM, Matthias Kaehlcke wrote:
> dce_clock_set_min_clocks_state() assigns (intentionally) a value of type
> 'enum dm_pp_clocks_state' to a variable of type 'enum dm_pp_power_level'
> without an explicit cast. This causes clang to raise the following
> warning:
>
> drivers/gpu/drm
El Fri, Feb 09, 2018 at 04:55:57PM -0500 Harry Wentland ha dit:
> On 2018-02-09 04:28 PM, Matthias Kaehlcke wrote:
> > dce_clock_set_min_clocks_state() assigns (intentionally) a value of type
> > 'enum dm_pp_clocks_state' to a variable of type 'enum dm_pp_power_level'
> > without an explicit cast.
The initialization of 'result' is unnecessary, the variable is assigned
unconditionally a few lines below. Removing the initialization also fixes
the following warning when building with clang:
drivers/gpu/drm/amd/amdgpu/../display/dc/core/dc_link_dp.c:1931:26:
error: implicit conversion from en
36 matches
Mail list logo