Am 18.01.21 um 22:01 schrieb Andrey Grodzovsky:
From: Luben Tuikov
This patch does not change current behaviour.
The driver's job timeout handler now returns
status indicating back to the DRM layer whether
the task (job) was successfully aborted or whether
more time should be given to the task
[AMD Official Use Only - Internal Distribution Only]
> -Original Message-
> From: Huang, Ray
> Sent: Tuesday, January 19, 2021 2:57 PM
> To: Liang, Prike
> Cc: amd-gfx@lists.freedesktop.org; Deucher, Alexander
>
> Subject: Re: [PATCH] drm/amdgpu: remove gpu info firmware of green
> sard
On Tue, Jan 19, 2021 at 02:25:36PM +0800, Liang, Prike wrote:
> [AMD Official Use Only - Internal Distribution Only]
>
> Thanks help clean up. Generally that seems fine but could we keep the green
> sardine chip name to retrieve the GPU info FW when the IP discovery fail back
> to legacy mode?
[AMD Official Use Only - Internal Distribution Only]
Thanks help clean up. Generally that seems fine but could we keep the green
sardine chip name to retrieve the GPU info FW when the IP discovery fail back
to legacy mode?
Anyway this patch is Reviewed-by: Prike Liang
Thanks,
Prike
> -Ori
GCR_GENERAL_CNTL is defined differently in gc_10_1_0_offset.h and
gc_10_3_0_offset.h. Update GCR_GENERAL_CNTL for Vangogh.
Signed-off-by: Jinzhou Su
Reviewed-by: Huang Rui
---
drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/g
The ip discovery is supported on green sardine, it doesn't need gpu info
firmware anymore.
Signed-off-by: Huang Rui
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
b/drivers/gpu/drm/a
On Mon, Jan 18, 2021 at 06:17:51PM +0800, Su, Jinzhou (Joe) wrote:
> 1. Remove PP_GFXOFF_MASK and then GFXOFF can be enabled
> by user space.
> 2. GFXOFF is still disabled on Vangogh by default.
> 3. When GFXOFF feature on Vangogh landed, will enable
> GFXOFF by default.
> 4. GFXOFF can
On Tue, Jan 19, 2021 at 09:26:42AM +0800, Liang, Prike wrote:
> In the renoir there is no need GpuChangeState message set to exit gfxoff in
> the s0i3 resume since
> mmnbif_gpu_BIF_DOORBELL_FENCE_CNTL has been added in the s0i3 FSDL.
>
> Signed-off-by: Prike Liang
Reviewed-by: Huang Rui
> ---
[AMD Official Use Only - Internal Distribution Only]
>-Original Message-
>From: amd-gfx On Behalf Of
>Christian König
>Sent: Tuesday, January 19, 2021 12:04 AM
>To: Deng, Emily ; Koenig, Christian
>; Sun, Roy ; amd-
>g...@lists.freedesktop.org
>Subject: Re: [PATCH] drm/amdgpu: change the
Reviewed-by: Philip Yang
On 2021-01-18 8:20 p.m., Felix Kuehling
wrote:
Am 2021-01-18 um 8:01 p.m. schrieb philip yang:
On 2021-01-18 6:28 p.m., Felix Kuehling wrote:
ROCm user mode depends on userptr support. Without it,
In the renoir there is no need GpuChangeState message set to exit gfxoff in the
s0i3 resume since
mmnbif_gpu_BIF_DOORBELL_FENCE_CNTL has been added in the s0i3 FSDL.
Signed-off-by: Prike Liang
---
drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion
Am 2021-01-18 um 8:01 p.m. schrieb philip yang:
>
>
> On 2021-01-18 6:28 p.m., Felix Kuehling wrote:
>> ROCm user mode depends on userptr support. Without it, KFD is basically
>> useless.
>>
>> Make sure HSA_AMD selects the same options as DRM_AMDGPU_USERPTR to avoid
>> broken configurations where
On 2021-01-18 6:28 p.m., Felix Kuehling
wrote:
ROCm user mode depends on userptr support. Without it, KFD is basically
useless.
Make sure HSA_AMD selects the same options as DRM_AMDGPU_USERPTR to avoid
broken configurations where userptr gets enabled but its
ROCm user mode depends on userptr support. Without it, KFD is basically
useless.
Make sure HSA_AMD selects the same options as DRM_AMDGPU_USERPTR to avoid
broken configurations where userptr gets enabled but its dependencies are
disabled.
Signed-off-by: Felix Kuehling
---
drivers/gpu/drm/amd/am
On Mon, Jan 18, 2021 at 4:02 PM Andrey Grodzovsky
wrote:
>
> Handle all DMA IOMMU gropup related dependencies before the
gropup -> group
Alex
> group is removed.
>
> Signed-off-by: Andrey Grodzovsky
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu.h| 5
> drivers/gpu/drm/amd/amdgpu/amd
On Mon, Jan 18, 2021 at 4:02 PM Andrey Grodzovsky
wrote:
>
> To avoid any possible use after free.
>
> Signed-off-by: Andrey Grodzovsky
> Reviewed-by: Christian König
In the subject:
oustatdning -> outstanding
Alex
> ---
> drivers/gpu/drm/scheduler/sched_main.c | 3 +++
> 1 file changed, 3
On Mon, Jan 18, 2021 at 4:02 PM Andrey Grodzovsky
wrote:
>
> On device removal reroute all CPU mappings to dummy page.
>
> v3:
> Remove loop to find DRM file and instead access it
> by vma->vm_file->private_data. Move dummy page installation
> into a separate function.
>
> v4:
> Map the entire BOs
Return DRM_TASK_STATUS_ENODEV back to the scheduler when device
is not present so they timeout timer will not be rearmed.
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 19 ---
1 file changed, 16 insertions(+), 3 deletions(-)
diff --git a/drivers/
We don't want to rearm the timer if driver hook reports
that the device is gone.
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/scheduler/sched_main.c | 11 +++
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/scheduler/sched_main.c
b/drivers/gpu/drm/s
From: Luben Tuikov
This patch does not change current behaviour.
The driver's job timeout handler now returns
status indicating back to the DRM layer whether
the task (job) was successfully aborted or whether
more time should be given to the task to complete.
Default behaviour as of this patch,
This should prevent writing to memory or IO ranges possibly
already allocated for other uses after our device is removed.
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 57
drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c| 9
drivers/g
This allows to remove explicit creation and destruction
of those attrs and by this avoids warnings on device
finilizing post physical device extraction.
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c | 17 +
drivers/gpu/drm/amd/amdgpu/amdgpu_drv
On device removal reroute all CPU mappings to dummy page
per drm_file instance or imported GEM object.
v4:
Update for modified ttm_bo_vm_dummy_page
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 21 -
1 file changed, 16 insertions(+), 5 deleti
We can't allocate and submit IBs post device unplug.
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 8 +++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index ad91c
Handle all DMA IOMMU gropup related dependencies before the
group is removed.
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h| 5
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 46 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c | 2
Use it to call disply code dependent on device->drv_data
before it's set to NULL on device unplug
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c| 20
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 12 ++--
drivers/gpu/drm
Some of the stuff in amdgpu_device_fini such as HW interrupts
disable and pending fences finilization must be done right away on
pci_remove while most of the stuff which relates to finilizing and
releasing driver data structures can be kept until
drm_driver.release hook is called, i.e. when the las
To avoid any possible use after free.
Signed-off-by: Andrey Grodzovsky
Reviewed-by: Christian König
---
drivers/gpu/drm/scheduler/sched_main.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/scheduler/sched_main.c
b/drivers/gpu/drm/scheduler/sched_main.c
index 997aa15..9
Invalidate all BOs CPU mappings once device is removed.
v3: Move the code from TTM into drm_dev_unplug
Signed-off-by: Andrey Grodzovsky
Reviewed-by: Christian König
Reviewed-by: Daniel Vetter
---
drivers/gpu/drm/drm_drv.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/
It's needed to drop iommu backed pages on device unplug
before device's IOMMU group is released.
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/ttm/ttm_tt.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 7f75a13..f9e0b0
On device removal reroute all CPU mappings to dummy page.
v3:
Remove loop to find DRM file and instead access it
by vma->vm_file->private_data. Move dummy page installation
into a separate function.
v4:
Map the entire BOs VA space into on demand allocated dummy page
on the first fault for that BO
Until now extracting a card either by physical extraction (e.g. eGPU with
thunderbolt connection or by emulation through syfs ->
/sys/bus/pci/devices/device_id/remove)
would cause random crashes in user apps. The random crashes in apps were
mostly due to the app having mapped a device backed B
Am 2021-01-18 um 10:04 a.m. schrieb Christian König:
> Am 15.01.21 um 19:24 schrieb Felix Kuehling:
>> ROCm user mode depends on userptr support. Without it, KFD is basically
>> useless.
>>
>> Signed-off-by: Felix Kuehling
>
> Reviewed-by: Christian König
Thank you. For the record, the documenta
Am 18.01.21 um 12:56 schrieb Deng, Emily:
[AMD Official Use Only - Internal Distribution Only]
-Original Message-
From: Koenig, Christian
Sent: Monday, January 18, 2021 3:49 PM
To: Deng, Emily ; Sun, Roy ;
amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH] drm/amdgpu: change the fence
[AMD Official Use Only - Internal Distribution Only]
Reviewed-by: Alex Deucher
From: Huang, Ray
Sent: Monday, January 18, 2021 7:32 AM
To: amd-gfx@lists.freedesktop.org
Cc: Deucher, Alexander ; Huang, Ray
; Stephen Rothwell
Subject: [PATCH v2] drm/amdgpu: fix
On 2021-01-18 6:03 a.m., Pratik Vishwakarma wrote:
This reverts commit 6f3fca64cfb91fedf9b34ea27b2581e88d48c9b2.
Flash line issue when MPO enabled on idle screen was fixed by
commit 9d03bb102028 ("drm/amd/display: disable dcn10 pipe split by default")
This patch is no more required
Do you have
Am 15.01.21 um 19:24 schrieb Felix Kuehling:
ROCm user mode depends on userptr support. Without it, KFD is basically
useless.
Signed-off-by: Felix Kuehling
Reviewed-by: Christian König
---
drivers/gpu/drm/amd/amdkfd/Kconfig | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu
Hi
Am 18.01.21 um 15:56 schrieb Daniel Vetter:
On Mon, Jan 18, 2021 at 3:40 PM Thomas Zimmermann wrote:
Hi
Am 18.01.21 um 14:50 schrieb Christian König:
Hi Thomas,
this patch unfortunately completely broke amdgpu.
See the splat below:
[ 74.553881]
==
Am 18.01.21 um 15:55 schrieb Felix Kuehling:
Am 2021-01-18 um 9:53 a.m. schrieb Christian König:
Am 18.01.21 um 15:37 schrieb Felix Kuehling:
Am 2021-01-18 um 2:53 a.m. schrieb Christian König:
Am 15.01.21 um 19:24 schrieb Felix Kuehling:
ROCm user mode depends on userptr support. Without it,
On Mon, Jan 18, 2021 at 3:40 PM Thomas Zimmermann wrote:
>
> Hi
>
> Am 18.01.21 um 14:50 schrieb Christian König:
> > Hi Thomas,
> >
> > this patch unfortunately completely broke amdgpu.
> >
> > See the splat below:
> >
> > [ 74.553881]
> > ===
Am 2021-01-18 um 9:53 a.m. schrieb Christian König:
> Am 18.01.21 um 15:37 schrieb Felix Kuehling:
>> Am 2021-01-18 um 2:53 a.m. schrieb Christian König:
>>> Am 15.01.21 um 19:24 schrieb Felix Kuehling:
ROCm user mode depends on userptr support. Without it, KFD is
basically
useless.
Am 18.01.21 um 15:37 schrieb Felix Kuehling:
Am 2021-01-18 um 2:53 a.m. schrieb Christian König:
Am 15.01.21 um 19:24 schrieb Felix Kuehling:
ROCm user mode depends on userptr support. Without it, KFD is basically
useless.
Signed-off-by: Felix Kuehling
---
drivers/gpu/drm/amd/amdkfd/Kconfi
Hi
Am 18.01.21 um 14:50 schrieb Christian König:
Hi Thomas,
this patch unfortunately completely broke amdgpu.
See the splat below:
[ 74.553881]
==
[ 74.554060] BUG: KASAN: null-ptr-deref in
drm_pci_set_busid+0x38/0x100 [drm
Am 2021-01-18 um 2:53 a.m. schrieb Christian König:
> Am 15.01.21 um 19:24 schrieb Felix Kuehling:
>> ROCm user mode depends on userptr support. Without it, KFD is basically
>> useless.
>>
>> Signed-off-by: Felix Kuehling
>> ---
>> drivers/gpu/drm/amd/amdkfd/Kconfig | 1 +
>> 1 file changed, 1
On Thu, 2021-01-14 at 11:14 +0200, Pekka Paalanen wrote:
>
> Hi,
>
> please document somewhere that ends up in git history (commit
> message,
> code comments, description of the parameter would be the best but
> maybe
> there isn't enough space?) what Christian König explained in
>
>
> https:/
Hi Thomas,
this patch unfortunately completely broke amdgpu.
See the splat below:
[ 74.553881]
==
[ 74.554060] BUG: KASAN: null-ptr-deref in
drm_pci_set_busid+0x38/0x100 [drm]
[ 74.554393] Read of size 4 at addr 00
[AMD Official Use Only - Internal Distribution Only]
Reviewed-by: Hersen Wu
-Original Message-
From: Vishwakarma, Pratik
Sent: Monday, January 18, 2021 6:04 AM
To: Wu, Hersen ; amd-gfx@lists.freedesktop.org
Cc: Vishwakarma, Pratik
Subject: [PATCH] Revert "drm/amd/display: Tune min clk
This patch is to fix below build error while we are using the kconfig
without x86.
drivers/gpu/drm/amd/amdgpu/../pm/swsmu/smu11/vangogh_ppt.c: In function
'vangogh_get_smu_metrics_data':
drivers/gpu/drm/amd/amdgpu/../pm/swsmu/smu11/vangogh_ppt.c:300:10:
error: 'boot_cpu_data' undeclared (first use
Dear Anson, dear Aric,
Am 15.01.21 um 18:27 schrieb Anson Jacob:
From: Aric Cyr
Signed-off-by: Aric Cyr
Reviewed-by: Aric Cyr
Acked-by: Anson Jacob
---
drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
[…]
I think, I ask for this in the past, b
[AMD Official Use Only - Internal Distribution Only]
>-Original Message-
>From: Koenig, Christian
>Sent: Monday, January 18, 2021 3:49 PM
>To: Deng, Emily ; Sun, Roy ;
>amd-gfx@lists.freedesktop.org
>Subject: Re: [PATCH] drm/amdgpu: change the fence ring wait timeout
>
>Mhm, we could chan
GCR_GENERAL_CNTL is defined differently in gc_10_1_0_offset.h and
gc_10_3_0_offset.h. Update GCR_GENERAL_CNTL for Vangogh.
http://ontrack-internal.amd.com/browse/AER-11
Signed-off-by: Jinzhou Su
---
drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
This reverts commit 6f3fca64cfb91fedf9b34ea27b2581e88d48c9b2.
Flash line issue when MPO enabled on idle screen was fixed by
commit 9d03bb102028 ("drm/amd/display: disable dcn10 pipe split by default")
This patch is no more required
Signed-off-by: Pratik Vishwakarma
---
.../display/dc/clk_mgr/dc
1. Remove PP_GFXOFF_MASK and then GFXOFF can be enabled
by user space.
2. GFXOFF is still disabled on Vangogh by default.
3. When GFXOFF feature on Vangogh landed, will enable
GFXOFF by default.
4. GFXOFF can be enabled by debugfs interface amdgpu_gfxoff.
Signed-off-by: Jinzhou Su
---
Am 18.01.21 um 03:47 schrieb Jingwen Chen:
When using cancel_delayed_work_sync, there's no need
to flush_delayed_work first. This sequence can lead to
a redundant loop of work executing.
Well the difference is that cancel_delayed_work_sync() cancels the work
when it is not running yet and wait
[AMD Official Use Only - Internal Distribution Only]
Reviewed-by: Monk Liu
Thanks
--
Monk Liu | Cloud-GPU Core team
--
-Original Message-
From: amd-gfx On Behalf Of Jingwen Chen
Sent: Monday, January 18,
Forwarding by mail because I can't find the respective AMD GPU assignee
mail on bugzilla.k.o.
- Forwarded message from bugzilla-dae...@bugzilla.kernel.org -
Date: Sun, 17 Jan 2021 21:13:06 +
From: bugzilla-dae...@bugzilla.kernel.org
To: b...@alien8.de
Subject: [Bug 211245] New: Fedora
If it's just for dev usage, why don't use UMR tool instead?
~/tools$ sudo ./umr -r *.mp*.mmMP1_SMN_EXT_SCRATCH0
0x0040
-Original Message-
From: amd-gfx On Behalf Of Quan, Evan
Sent: Monday, January 18, 2021 2:06 PM
To: Lazar, Lijo ; amd-gfx@lists.freedesktop.org
Cc: Deucher, Alexander
57 matches
Mail list logo
