Am 31.01.2018 um 13:07 schrieb Bas Nieuwenhuizen:
If these bos are evicted and are in the validated list
things blow up, so do not put them in there. Notably,
that tries to add the bo to the LRU twice, which results
in a BUG_ON in ttm_bo.c.
While for the bo_list an alternative would be to not
On Fri, Jan 5, 2018 at 12:17 AM, Felix Kuehling wrote:
> On dGPUs don't set ATC addressing bits and use MTYPE_UC for coherent
> memory.
>
> Signed-off-by: Felix Kuehling
> ---
> drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c | 7 +
>
If these bos are evicted and are in the validated list
things blow up, so do not put them in there. Notably,
that tries to add the bo to the LRU twice, which results
in a BUG_ON in ttm_bo.c.
While for the bo_list an alternative would be to not allow
always valid bos in there, that does not work
Signed-off-by: Tom St Denis
---
src/lib/ring_decode.c | 39 +++
1 file changed, 27 insertions(+), 12 deletions(-)
diff --git a/src/lib/ring_decode.c b/src/lib/ring_decode.c
index cc23b6299d33..75247aa198d8 100644
---
If these bos are evicted and are in the validated list
things blow up, so do not put them in there. Notably,
that tries to add the bo to the LRU twice, which results
in a BUG_ON in ttm_bo.c.
While for the bo_list an alternative would be to not allow
always valid bos in there, that does not work
On Fri, Jan 5, 2018 at 12:17 AM, Felix Kuehling wrote:
> GFXv7 and v8 dGPUs use a different addressing mode for KFD compared
> to APUs (GPUVM64 vs HSA64). And dGPUs don't support MTYPE_CC. They
> use MTYPE_UC instead for memory that requires coherency.
>
> Signed-off-by:
On Fri, Jan 5, 2018 at 12:17 AM, Felix Kuehling wrote:
> This will be needed for most dGPUs.
>
> CC: linux-...@vger.kernel.org
> Signed-off-by: Felix Kuehling
> ---
> drivers/gpu/drm/amd/amdkfd/kfd_device.c | 17 +
>
On Tue, Jan 30, 2018 at 6:53 PM, Felix Kuehling wrote:
>
> On 2018-01-30 08:59 AM, Christian König wrote:
>> Am 29.01.2018 um 23:08 schrieb Felix Kuehling:
>>> On 2018-01-26 03:13 PM, Christian König wrote:
[SNIP]
+#ifdef CONFIG_DRM_AMDGPU_ATC
+r =
On Fri, Jan 5, 2018 at 12:17 AM, Felix Kuehling wrote:
> Some dGPUs don't support HWS. Allow them to use a per-device
> sched_policy that may be different from the global default.
>
> Signed-off-by: Felix Kuehling
> ---
>
On Wed, Jan 31, 2018 at 4:56 PM, Oded Gabbay wrote:
> Hi Felix,
> Please don't spread 19 #ifdefs throughout the code.
> I suggest to put one #ifdef in linux/amd-iommu.h itself around all the
> functions declarations and in the #else section put macros with empty
>
Adding Jean and the IOMMU list as well.
Am 31.01.2018 um 13:43 schrieb Oded Gabbay:
On Tue, Jan 30, 2018 at 6:53 PM, Felix Kuehling wrote:
[SNIP]
There was some discussion last year about a generic PASID allocator in
the iommu subsystem:
Hi Felix,
Please don't spread 19 #ifdefs throughout the code.
I suggest to put one #ifdef in linux/amd-iommu.h itself around all the
functions declarations and in the #else section put macros with empty
implementations. This is much more readable and maintainable.
Oded
On Fri, Jan 5, 2018 at
Am 31.01.2018 um 16:00 schrieb Oded Gabbay:
On Wed, Jan 31, 2018 at 4:56 PM, Oded Gabbay wrote:
Hi Felix,
Please don't spread 19 #ifdefs throughout the code.
I suggest to put one #ifdef in linux/amd-iommu.h itself around all the
functions declarations and in the #else
If these bos are evicted and are in the validated list
things blow up, so do not put them in there. Notably,
that tries to add the bo to the LRU twice, which results
in a BUG_ON in ttm_bo.c.
While for the bo_list an alternative would be to not allow
always valid bos in there, that does not work
Am 31.01.2018 um 16:25 schrieb Oded Gabbay:
On Fri, Jan 5, 2018 at 12:17 AM, Felix Kuehling wrote:
Signed-off-by: Felix Kuehling
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 5 +
1 file changed, 5 insertions(+)
diff --git
On 01/25/2018 11:33 PM, Yu, Xiangliang wrote:
You can add amdgpu_sriov_vf() check to avoid breaking sriov.
+ Haisheng
As found out after more debugging and discussion with Haisheng from HW
team, the sequence introduced by this change is is wrong, it causes
compute rings test failure
On Fri, Jan 5, 2018 at 12:17 AM, Felix Kuehling wrote:
> Signed-off-by: Felix Kuehling
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 5 +
> 1 file changed, 5 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
>
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.com/mschiu77/b06dba574e89b9a30cf4c450eaec49bc
>
> With the latest kernel 4.15, there're lots of different
>
On 2018-01-31 10:00 AM, Oded Gabbay wrote:
> On Wed, Jan 31, 2018 at 4:56 PM, Oded Gabbay wrote:
>> Hi Felix,
>> Please don't spread 19 #ifdefs throughout the code.
>> I suggest to put one #ifdef in linux/amd-iommu.h itself around all the
>> functions declarations and in
On 2018-01-31 10:29 AM, Oded Gabbay wrote:
> On Wed, Jan 31, 2018 at 5:23 PM, Deucher, Alexander
> wrote:
>>
>> From: amd-gfx on behalf of Oded
>> Gabbay
>> Sent: Wednesday,
On 2018-01-31 10:20 AM, Oded Gabbay wrote:
> On Fri, Jan 5, 2018 at 12:17 AM, Felix Kuehling
> wrote:
>> CC: linux-...@vger.kernel.org
>> Signed-off-by: Felix Kuehling
>> ---
>> drivers/gpu/drm/amd/amdkfd/kfd_device.c | 153
>>
On Wed, Jan 31, 2018 at 5:28 PM, Christian König
wrote:
> Am 31.01.2018 um 16:25 schrieb Oded Gabbay:
>>
>> On Fri, Jan 5, 2018 at 12:17 AM, Felix Kuehling
>> wrote:
>>>
>>> Signed-off-by: Felix Kuehling
>>> ---
From: Krunoslav Kovac
There are several optimizations:
1) Use predefined SRGB, don't calculate. This is the most common case.
2) Precompute HW X points at boot since they're fixed in ColModule
3) Precompute PQ - it never changes and is very CPU intensive in fixed pt.
4)
From: Charlene Liu
Signed-off-by: Charlene Liu
Reviewed-by: Yongqiang Sun
Acked-by: Harry Wentland
---
drivers/gpu/drm/amd/display/dc/core/dc_link.c | 6 +++---
1 file changed, 3 insertions(+), 3
From: Charlene Liu
Signed-off-by: Charlene Liu
Reviewed-by: Charlene Liu
Acked-by: Harry Wentland
---
drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c | 22 ++
From: amd-gfx on behalf of Oded Gabbay
Sent: Wednesday, January 31, 2018 10:17 AM
To: Kuehling, Felix
Cc: amd-gfx list
Subject: Re: [PATCH 7/9] drm/amdkfd: Add dGPU support to kernel_queue_init
On
The variable is protected by the VMID mutex anyway.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 10 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h | 2 +-
2 files changed, 6 insertions(+), 6 deletions(-)
diff --git
Beneficial when a lot of processes are waiting for VMIDs.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 7 +--
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 3 +++
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 1 +
3 files changed, 9
Let's try this once more.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 130
1 file changed, 81 insertions(+), 49 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
Now that we have the different cases for grabbing a VMID in separate
functions, restructure the top level function to only have one place
where VMIDs are assigned to jobs.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 89
Drop the "_locked" from the name, cleanup and simplify the logic a bit.
Add missing comments.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 58 -
1 file changed, 35 insertions(+), 23 deletions(-)
diff
We do this later on when we flush the VMID anyway.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 6 +-
1 file changed, 1 insertion(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
No functional change, but makes it easier to maintain the code.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 116 +++-
1 file changed, 69 insertions(+), 47 deletions(-)
diff --git
To guarantee fairness between processes grab reserved VMID only when
there is an idle one.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 12 +++-
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git
Am 26.01.2018 um 00:06 schrieb Andrey Grodzovsky:
This reverts commit 75737cb4eb78c7f185e4700b4aa20cf7a3381aca.
Fixes GFX ring test failure after HW reset.
No compute ring test failures were observed with the change reverted.
So seems like whatever problem that change was addressing is not
On Fri, Jan 5, 2018 at 12:17 AM, Felix Kuehling wrote:
> CC: linux-...@vger.kernel.org
> Signed-off-by: Felix Kuehling
> ---
> drivers/gpu/drm/amd/amdkfd/kfd_device.c | 153
> +++-
> 1 file changed, 151 insertions(+),
On Wed, Jan 31, 2018 at 5:23 PM, Deucher, Alexander
wrote:
>
>
> From: amd-gfx on behalf of Oded
> Gabbay
> Sent: Wednesday, January 31, 2018 10:17 AM
> To: Kuehling, Felix
Am 31.01.2018 um 16:31 schrieb Oded Gabbay:
On Wed, Jan 31, 2018 at 5:28 PM, Christian König
wrote:
Am 31.01.2018 um 16:25 schrieb Oded Gabbay:
On Fri, Jan 5, 2018 at 12:17 AM, Felix Kuehling
wrote:
Signed-off-by: Felix Kuehling
On Wed, Jan 31, 2018 at 5:34 PM, Christian König
wrote:
> Am 31.01.2018 um 16:31 schrieb Oded Gabbay:
>>
>> On Wed, Jan 31, 2018 at 5:28 PM, Christian König
>> wrote:
>>>
>>> Am 31.01.2018 um 16:25 schrieb Oded Gabbay:
On Fri,
On 2018-01-31 10:06 AM, Oded Gabbay wrote:
> On Fri, Jan 5, 2018 at 12:17 AM, Felix Kuehling
> wrote:
>> Some dGPUs don't support HWS. Allow them to use a per-device
>> sched_policy that may be different from the global default.
>>
>> Signed-off-by: Felix Kuehling
On 2018-01-31 10:25 AM, Oded Gabbay wrote:
> On Fri, Jan 5, 2018 at 12:17 AM, Felix Kuehling
> wrote:
>> Signed-off-by: Felix Kuehling
>> ---
>> drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 5 +
>> 1 file changed, 5 insertions(+)
>>
>> diff
On Fri, Jan 5, 2018 at 12:17 AM, Felix Kuehling wrote:
> Recognize dGPU ASIC families.
>
> Signed-off-by: Felix Kuehling
> ---
> drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c | 5 +
> 1 file changed, 5 insertions(+)
>
> diff --git
Hi,
We are working with new laptops that have the AMD Ravenl Ridge
chipset with this `/proc/cpuinfo`
https://gist.github.com/mschiu77/b06dba574e89b9a30cf4c450eaec49bc
With the latest kernel 4.15, there're lots of different
panics/oops during boot so no chance to get into X. It also
Hi Christian,
On 31/01/18 13:04, Christian König wrote:
> Adding Jean and the IOMMU list as well.
>
> Am 31.01.2018 um 13:43 schrieb Oded Gabbay:
>> On Tue, Jan 30, 2018 at 6:53 PM, Felix Kuehling
>> wrote:
>>> [SNIP]
>> There was some discussion last year about a
On Sat, Jan 20, 2018 at 12:30 AM, Gustavo A. R. Silva
wrote:
>
> Quoting Felix Kuehling :
>
>> Looks good. This change is Reviewed-by: Felix Kuehling
>>
>>
>
> Thanks Felix.
> --
> Gustavo
>
Applied to -next
Oded
>
>
>
>
From: Yongqiang Sun
Signed-off-by: Yongqiang Sun
Reviewed-by: Tony Cheng
Acked-by: Harry Wentland
---
drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 3 ++-
1 file changed, 2 insertions(+),
From: Mikita Lipski
Because AMDGPU_CRTC_IRQ_VLINE1 = 6, it expected 6 more crtcs to be
programed with disabled irq state in amdgpu_irq_disable_all. That caused errors
and accessed
the wrong memory location.
Signed-off-by: Mikita Lipski
From: Eric Bernstein
Signed-off-by: Eric Bernstein
Reviewed-by: Tony Cheng
Acked-by: Harry Wentland
---
drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 2 +-
From: Eric Yang
Signed-off-by: Eric Yang
Reviewed-by: Tony Cheng
Acked-by: Harry Wentland
---
drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c | 4 ++--
* Fix non-native modes on DVI
* Whole bunch of Raven fixes all over
* Cleanup for CRC stuff
Charlene Liu (5):
drm/amd/display: BL setting save/restore
drm/amd/display: wait for T9 after backlight off mainlink blank.
drm/amd/display: add eDP 1.2+ polling for T7
drm/amd/display: resume from
From: Eric Yang
As a precaution to prevent cases where cursor is enabled on a pipe
that is disabled, always turn off cursor when disconnecting plane.
Signed-off-by: Eric Yang
Reviewed-by: Tony Cheng
Acked-by: Harry Wentland
From: "Leo (Sunpeng) Li"
If CONFIG_DEBUG_FS is disabled, then CRC should also be disabled.
Therefore, amdgpu_dm_crtc_handle_crc_irq was redefined as a no-op
function within amdgpu_dm.h.
However, since amdgpu_dm.h is included in multiple files, this caused
conflicts when
From: Eric Yang
Move cursor programming to inside the OTG_MASTER_UPDATE_LOCK
If graphics plane go from 1 pipe to hsplit, the cursor updates
after mpc programming and unlock. Which means there is a window
of time where cursor is enabled on the wrong pipe if it's on
the right
From: Ken Chalmers
* Previous code did some calculations with a mix of normal integers and
integers aligned as U2.24 fixed-point values.
* There were bugs in the conversion of the final result into the
S4.19 values required for the registers.
Signed-off-by: Ken
From: Roman Li
Fixing null-deref on Vega10 due to regression after
'fix cursor related Pstate hang' change.
Added null checks in setting cursor position.
Signed-off-by: Roman Li
Reviewed-by: Eric Yang
Reviewed-by: Harry Wentland
From: Yongqiang Sun
Signed-off-by: Yongqiang Sun
Reviewed-by: Tony Cheng
Acked-by: Harry Wentland
---
drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c | 19 +--
From: Nikola Cornij
Signed-off-by: Nikola Cornij
Reviewed-by: Tony Cheng
Acked-by: Harry Wentland
---
drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h| 8
From: John Barberiz
Signed-off-by: John Barberiz
Reviewed-by: Tony Cheng
Acked-by: Harry Wentland
---
drivers/gpu/drm/amd/display/dc/core/dc_link.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff
From: Tony Cheng
Signed-off-by: Tony Cheng
Reviewed-by: Tony Cheng
Acked-by: Harry Wentland
---
drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git
From: Charlene Liu
Signed-off-by: Charlene Liu
Reviewed-by: Krunoslav Kovac
Acked-by: Harry Wentland
---
drivers/gpu/drm/amd/display/dc/bios/bios_parser.c | 1 +
From: Charlene Liu
Signed-off-by: Charlene Liu
Reviewed-by: Tony Cheng
Acked-by: Harry Wentland
---
drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c | 3 +--
From: Tony Cheng
Signed-off-by: Tony Cheng
Reviewed-by: Tony Cheng
Acked-by: Harry Wentland
---
drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git
From: Yongqiang Sun
System soft hang when hotplug specific 4K DP panel
due to link caps read error and incorrect link setting
parmas to enable dp.
Add status check for DPCD read and add return value
for detect dp, in case of false, return from caller,
avoid further false
From: Charlene Liu
Signed-off-by: Charlene Liu
Reviewed-by: Tony Cheng
Acked-by: Harry Wentland
---
drivers/gpu/drm/amd/display/dc/dce/dce_abm.c | 9 +
1 file changed, 9 insertions(+)
diff --git
From: Yongqiang Sun
When disable plane, check power gate flag in hubp with pipe_ctx,
not with res_pool.
Signed-off-by: Yongqiang Sun
Reviewed-by: Tony Cheng
Acked-by: Harry Wentland
---
From: Martin Tsai
Signed-off-by: Martin Tsai
Reviewed-by: Tony Cheng
Acked-by: Harry Wentland
---
drivers/gpu/drm/amd/display/dc/core/dc_link.c | 2 --
1 file changed, 2 deletions(-)
diff --git
From: "Jerry (Fangzhi) Zuo"
There is no need to call drm_mode_set_crtcinfo() again once
crtc timing is decided. Otherwise non-native/unsupported timing
might get overwritten.
Signed-off-by: Jerry (Fangzhi) Zuo
Reviewed-by: Harry Wentland
From: Tony Cheng
Signed-off-by: Tony Cheng
Reviewed-by: Tony Cheng
Acked-by: Harry Wentland
---
drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git
Signed-off-by: Harry Wentland
Reviewed-by: Tony Cheng
---
drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_1_0_sh_mask.h | 14 ++
1 file changed, 14 insertions(+)
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_1_0_sh_mask.h
From: John Barberiz
If non-standard gamma type detected set identity matrix flag
so that we can bypass the gamma mode.
Signed-off-by: John Barberiz
Reviewed-by: Krunoslav Kovac
Acked-by: Harry Wentland
---
Ok, thanks!
From: Grodzovsky, Andrey
Sent: Thursday, February 01, 2018 12:59 AM
To: Yu, Xiangliang ; amd-gfx@lists.freedesktop.org;
Deng, Emily
Cc: Deucher, Alexander ; Koenig, Christian
; Wu,
Hi everyone,
I am getting a new issue with amdgpu with RX460, that is, now I can
play any videos with Kodi or play web videos with firefox and run
OpenGL applications without running into any issues, however after
some uptime with XOrg even when almost inactive I get a kmalloc
allocation failure,
On 2018年01月31日 23:47, Christian König wrote:
The variable is protected by the VMID mutex anyway.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 10 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h | 2 +-
2 files changed, 6
Reviewed-by: Chunming Zhou
On 2018年01月31日 23:47, Christian König wrote:
We do this later on when we flush the VMID anyway.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 6 +-
1 file changed, 1 insertion(+),
Reviewed-by: Chunming Zhou
On 2018年01月31日 23:47, Christian König wrote:
Drop the "_locked" from the name, cleanup and simplify the logic a bit.
Add missing comments.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c |
Reviewed-by: Chunming Zhou
On 2018年01月31日 23:47, Christian König wrote:
Let's try this once more.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 130
1 file changed, 81
On 2018年01月31日 23:47, Christian König wrote:
Beneficial when a lot of processes are waiting for VMIDs.
Yeah, we can save re-creating fence array when vmid is used up.
Reviewed-by: Chunming Zhou
Signed-off-by: Christian König
---
Reviewed-by: Chunming Zhou
On 2018年01月31日 23:47, Christian König wrote:
No functional change, but makes it easier to maintain the code.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 116
On Wed, Jan 31, 2018 at 7:58 AM, Bas Nieuwenhuizen wrote:
> If these bos are evicted and are in the validated list
> things blow up, so do not put them in there. Notably,
> that tries to add the bo to the LRU twice, which results
> in a BUG_ON in ttm_bo.c.
>
> While for the
On Wed, Jan 31, 2018 at 6:57 PM, Luís Mendes wrote:
> Hi everyone,
>
> I am getting a new issue with amdgpu with RX460, that is, now I can
> play any videos with Kodi or play web videos with firefox and run
> OpenGL applications without running into any issues, however
Hi Dave,
A few more misc fixes for 4.16.
The following changes since commit 559f17bec508548850654dd04525fd69d90f6d4e:
Merge tag 'drm-misc-next-fixes-2018-01-18' of
git://anongit.freedesktop.org/drm/drm-misc into drm-next (2018-01-25 11:42:25
+1000)
are available in the git repository at:
Am 31.01.2018 um 00:21 schrieb Felix Kuehling:
On 2018-01-30 10:35 AM, Christian König wrote:
Am 30.01.2018 um 16:28 schrieb Kasiviswanathan, Harish:
[+Harish, forgot to acknowledge him in the commit description, will
fix
that in v2]
Harish, please see Christian's question below in
So I think preventing validation on same place is a simpler way:
process B bo's place is fpfn~lpfn, it will only try to evict LRU BOs
in that range, while eviction, we just prevent those validation to
this range(fpfn~lpfn), if out of this range, the allocation/validation
still can be go on.
On 2018年01月26日 22:35, Christian König wrote:
I just realized that a change I'm thinking about for a while would
solve your problem as well, but keep concurrent allocation possible.
See ttm_mem_evict_first() unlocks the BO after evicting it:
ttm_bo_del_from_lru(bo);
84 matches
Mail list logo