On 2016年12月16日 01:10, Nicolai Hähnle wrote:
From: Nicolai Hähnle
Skip amdgpu_gem_va_update_vm when shadow the page directory is swapped out.
Clean up the check for non-shadow BOs as well using the new helper function.
This fixes a crash with the stack trace:
amdgpu_gem_va_update_vm
-> amdgp
On 2016年12月16日 01:10, Nicolai Hähnle wrote:
From: Nicolai Hähnle
This catches evictions of shadow page tables from the GART. Since shadow
page tables are always stored in system memory, amdgpu_bo_move is never
called for them.
This fixes a crash during command submission that occurs when onl
On 2016年12月16日 01:10, Nicolai Hähnle wrote:
From: Nicolai Hähnle
Ensure that the driver can listen to evictions even when they don't take the
path through ttm_bo_driver::move.
This is crucial for amdgpu, which relies on an eviction counter to skip
re-binding page tables when possible.
Signe
On 2016年12月16日 01:10, Nicolai Hähnle wrote:
From: Nicolai Hähnle
Signed-off-by: Nicolai Hähnle
Reviewed-by: Chunming Zhou
---
drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 9 +
1 file changed, 9 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
b/drivers/gp
On 2016年12月16日 01:59, Nicolai Hähnle wrote:
From: Nicolai Hähnle
Skip amdgpu_gem_va_update_vm otherwise. Also clean up the check for the
non-shadow page tables using the new helper function.
This fixes a crash with the stack trace:
amdgpu_gem_va_update_vm
-> amdgpu_vm_update_page_directory
On 2016年12月16日 01:10, Nicolai Hähnle wrote:
From: Nicolai Hähnle
Skip amdgpu_gem_va_update_vm otherwise. Also clean up the check for the
non-shadow page tables using the new helper function.
This fixes a crash with the stack trace:
amdgpu_gem_va_update_vm
-> amdgpu_vm_update_page_directory
On 16/12/16 05:44 AM, Harry Wentland wrote:
> On 2016-12-13 01:41 AM, Dave Airlie wrote:
>
>> One thing I noticed in passing is the displayport code seems
>> possibly endian unsafe, it casts bytes read from hardware into
>> bitfields, this is the best defined behaviour and is generally
>> a patter
On 16 December 2016 at 09:49, Dave Airlie wrote:
> From: Dave Airlie
>
> Most of these weren't used in the driver, but I can't see why you need
> this table instead of just providing direct API, it's not hiding anything.
I realised the power module uses some of these, but since that module
isn't
From: Dave Airlie
Most of these weren't used in the driver, but I can't see why you need
this table instead of just providing direct API, it's not hiding anything.
Signed-off-by: Dave Airlie
---
.../drm/amd/display/amdgpu_dm/amdgpu_dm_types.c| 2 +-
drivers/gpu/drm/amd/display/dc/core/dc
On Thu, Dec 15, 2016 at 4:12 PM, Christian König
wrote:
>
> Regarding which error code to return I think that Emil has the right idea
> here.
>
> Returning -EINVAL usually means that userspace provided an invalid value,
> but in this case it doesn't matter which value the UMD provide all of them
>
On Wed, Dec 14, 2016 at 3:52 PM, Nils Wallménius
wrote:
> This is a left over from radeon, amdgpu doesn't support any
> non-atombios parts and amdgpu_device_init would bail if the
> check for atombios failed anyway.
>
> Signed-off-by: Nils Wallménius
Applied. thanks!
Alex
> ---
> drivers/gpu
The series is Reviewed-by: Harry Wentland
On 2016-12-13 01:41 AM, Dave Airlie wrote:
So whenever I look at DAL I find myself trying to figure out what
all of it does, and this leads me to deleting things, so I'm just
sending out some stuff that I cleaned today.
We really appreciate the clea
From: Arindam Nath
Change History
--
v4: Changes suggested by Emil, Christian
- return -ENODATA for asics with unlimited sessions
v3: changes suggested by Christian
- Add a check for UVD IP block using AMDGPU_HW_IP_UVD
query type.
- Add a check for asic_type to be less than
CHIP
From: Nicolai Hähnle
Skip amdgpu_gem_va_update_vm otherwise. Also clean up the check for the
non-shadow page tables using the new helper function.
This fixes a crash with the stack trace:
amdgpu_gem_va_update_vm
-> amdgpu_vm_update_page_directory
-> amdgpu_ttm_bind
-> amdgpu_gtt_mgr_alloc
v
Fix a bunch of related crashes in amdgpu that occur when shadow page tables
are kicked out of the GART.
One of the issues was that during command submission, we rely on a
device-global evictions counter to skip some of the work of page-table
validation. The driver was never informed of evictions f
From: Nicolai Hähnle
This catches evictions of shadow page tables from the GART. Since shadow
page tables are always stored in system memory, amdgpu_bo_move is never
called for them.
This fixes a crash during command submission that occurs when only a shadow
page table and no other BOs were evic
From: Nicolai Hähnle
Skip amdgpu_gem_va_update_vm otherwise. Also clean up the check for the
non-shadow page tables using the new helper function.
This fixes a crash with the stack trace:
amdgpu_gem_va_update_vm
-> amdgpu_vm_update_page_directory
-> amdgpu_ttm_bind
-> amdgpu_gtt_mgr_alloc
S
From: Nicolai Hähnle
Signed-off-by: Nicolai Hähnle
---
drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 9 +
1 file changed, 9 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 4306b2f..15a723a 100644
--- a/drivers/gpu
From: Nicolai Hähnle
Skip amdgpu_gem_va_update_vm when shadow the page directory is swapped out.
Clean up the check for non-shadow BOs as well using the new helper function.
This fixes a crash with the stack trace:
amdgpu_gem_va_update_vm
-> amdgpu_vm_update_page_directory
-> amdgpu_ttm_bind
From: Nicolai Hähnle
Ensure that the driver can listen to evictions even when they don't take the
path through ttm_bo_driver::move.
This is crucial for amdgpu, which relies on an eviction counter to skip
re-binding page tables when possible.
Signed-off-by: Nicolai Hähnle
---
drivers/gpu/drm/a
On Thu, Dec 15, 2016 at 4:16 PM, Deucher, Alexander
wrote:
>> -Original Message-
>> From: amd-gfx [mailto:amd-gfx-boun...@lists.freedesktop.org] On Behalf
>> Of Flora Cui
>> Sent: Thursday, December 15, 2016 3:31 AM
>> To: amd-gfx@lists.freedesktop.org
>> Cc: Cui, Flora
>> Subject: [PATCH
> -Original Message-
> From: amd-gfx [mailto:amd-gfx-boun...@lists.freedesktop.org] On Behalf
> Of Flora Cui
> Sent: Thursday, December 15, 2016 3:31 AM
> To: amd-gfx@lists.freedesktop.org
> Cc: Cui, Flora
> Subject: [PATCH 1/2] drm/amdgpu: update tile table for verde
>
> Change-Id: I4e3c6
> -Original Message-
> From: amd-gfx [mailto:amd-gfx-boun...@lists.freedesktop.org] On Behalf
> Of Flora Cui
> Sent: Thursday, December 15, 2016 2:33 AM
> To: amd-gfx@lists.freedesktop.org
> Cc: Cui, Flora
> Subject: [PATCH 9/9] drm/amdgpu: update rev id for verde
>
> Change-Id: I9f2a140d6
Am 15.12.2016 um 13:33 schrieb Nath, Arindam:
-Original Message-
From: Grazvydas Ignotas [mailto:nota...@gmail.com]
Sent: Thursday, December 15, 2016 5:52 PM
To: Nath, Arindam
Cc: Emil Velikov; David Airlie; Deucher, Alexander; ML dri-devel; amd-gfx
mailing list; Koenig, Christian
Subject
>-Original Message-
>From: Grazvydas Ignotas [mailto:nota...@gmail.com]
>Sent: Thursday, December 15, 2016 5:52 PM
>To: Nath, Arindam
>Cc: Emil Velikov; David Airlie; Deucher, Alexander; ML dri-devel; amd-gfx
>mailing list; Koenig, Christian
>Subject: Re: [PATCH 1/1] drm/amd/amdgpu: get max
On Thu, Dec 15, 2016 at 1:47 PM, Nath, Arindam wrote:
>>-Original Message-
>>From: Emil Velikov [mailto:emil.l.veli...@gmail.com]
>>Sent: Thursday, December 15, 2016 5:01 PM
>>To: Nath, Arindam
>>Cc: David Airlie; Deucher, Alexander; amd-gfx mailing list; ML dri-devel;
>>Koenig, Christian
>-Original Message-
>From: Emil Velikov [mailto:emil.l.veli...@gmail.com]
>Sent: Thursday, December 15, 2016 5:01 PM
>To: Nath, Arindam
>Cc: David Airlie; Deucher, Alexander; amd-gfx mailing list; ML dri-devel;
>Koenig, Christian
>Subject: Re: [PATCH 1/1] drm/amd/amdgpu: get maximum and use
On 15 December 2016 at 07:30, Nath, Arindam wrote:
>>-Original Message-
>>From: Emil Velikov [mailto:emil.l.veli...@gmail.com]
>>Sent: Wednesday, December 14, 2016 9:26 PM
>>To: Nath, Arindam
>>Cc: David Airlie; Deucher, Alexander; amd-gfx mailing list; ML dri-devel;
>>Koenig, Christian
>>
Hi Flora,
> @@ -1206,6 +1212,7 @@ static int si_common_early_init(void *handle)
> AMD_CG_SUPPORT_HDP_LS |
> AMD_CG_SUPPORT_HDP_MGCG;
> adev->pg_flags = 0;
> + adev->external_rev_id = adev->rev_id + 20;
> break;
It
Hi Flora,
the series look good for me.
Reviewed-by: Junwei Zhang
Regards,
Jerry(Junwei Zhang)
From: amd-gfx on behalf of Flora Cui
Sent: Thursday, December 15, 2016 4:31:16 PM
To: amd-gfx@lists.freedesktop.org
Cc: Cui, Flora
Subject: [PATCH 1/2] drm/a
Hi Flora,
Just confirm that it's decimal rather than HEX.
+ adev->external_rev_id = adev->rev_id + 40;
Apart from that, the series of patches looks good for me.
Reviewed-by: Junwei Zhang
Regards,
Jerry(Junwei Zhang)
From: amd-gfx on behal
Change-Id: I4e3c698a04e5f7ee05c0268eec12df519f2305d4
Signed-off-by: Flora Cui
---
drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 295 +-
1 file changed, 293 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
b/drivers/gpu/drm/amd/amdgpu/gfx
Change-Id: Ib8b66559d662cbe8a9f40f7405a4a052c189f604
Signed-off-by: Flora Cui
---
drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 330 --
1 file changed, 191 insertions(+), 139 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
b/drivers/gpu/drm/amd/amdgpu/g
33 matches
Mail list logo
