[AMD Official Use Only - General]
Hello Bas,
Thanks for trying this out.
This could be due to the doorbell as you mentioned, Usermode queue uses
doorbell manager internally.
This week, we are planning to publis the latest libDRM sample code which uses a
doorbell object (instead of the doorbel
Christian König ezt írta (időpont: 2023.
ápr. 9., Vas 17:38):
> Am 09.04.23 um 17:32 schrieb Bas Nieuwenhuizen:
> > On Sun, Apr 9, 2023 at 5:30 PM Christian König
> > wrote:
> >> Am 09.04.23 um 16:44 schrieb Bas Nieuwenhuizen:
> >>> We need to introduce a new version of the info struct because
>
smatch reports
drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.c:44:24: warning:
symbol
'dml20_funcs' was not declared. Should it be static?
drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.c:51:24: warning:
symbol
'dml20v2_funcs' was not declared. Should it be stat
Hi Shashank,
I think I found the issue: I wasn't destroying the user queue in my
program and the kernel doesn't clean up any remaining user queues in
the postclose hook. I think we need something like
https://github.com/BNieuwenhuizen/linux/commit/e90c8d1185da7353c12837973ceddf55ccc85d29
?
While
XGMI RAS should be according to the gmc xmgi supported flag
and xgmi physical nodes number.
Change-Id: Idf3600b30584b10b528e7237d103d84d5097b7e0
Signed-off-by: Stanley.Yang
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 8
1 file changed, 8 insertions(+)
diff --git a/drivers/gpu/drm/amd
Change-Id: Icceb43556eec802f11c2077c1c58a1e92c9df599
Signed-off-by: Stanley.Yang
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h | 4
drivers/gpu/drm/amd/amdgpu/ta_ras_if.h | 2 ++
2 files changed, 6 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
b/drivers/gpu/drm/amd/amdg
(resend with the right subject)
On Mon, 10 Apr 2023, Geert Uytterhoeven wrote:
On Mon, 10 Apr 2023, Geert Uytterhoeven wrote:
JFYI, when comparing v6.3-rc6[1] to v6.3-rc5[3], the summaries are:
- build errors: +2/-0
+ /kisskb/src/drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_topology.c: error:
On 4/9/2023 3:21 PM, Srinivasan Shanmugam wrote:
Update the existing log with DP LT downspread info:
[Downstream devices shall support down spreading of the link clock.
The down-spread amplitude shall either be disabled (0.0%) or up to 0.5%,
as written by the upstream device to the DOWNSPREAD
[AMD Official Use Only - General]
Thanks a lot Aurabindo! much appreciate for your help in reviewing this patch.
Best regards,
Srini
-Original Message-
From: Pillai, Aurabindo
Sent: Monday, April 10, 2023 6:39 PM
To: SHANMUGAM, SRINIVASAN ; Wentland, Harry
; Limonciello, Mario ; Li,
[AMD Official Use Only - General]
Hello Bas,
This is not the correct interpretation of the code, the USERQ_IOCTL has both
the OPs (create and destroy), but th euser has to exclusively call it.
Please see the sample test program in the existing libDRM series (userq_test.c,
it specifically cal
On Mon, Apr 10, 2023 at 3:40 PM Sharma, Shashank
wrote:
>
> [AMD Official Use Only - General]
>
> Hello Bas,
>
> This is not the correct interpretation of the code, the USERQ_IOCTL has both
> the OPs (create and destroy), but th euser has to exclusively call it.
>
> Please see the sample test pr
On 10/04/2023 15:46, Bas Nieuwenhuizen wrote:
On Mon, Apr 10, 2023 at 3:40 PM Sharma, Shashank
wrote:
[AMD Official Use Only - General]
Hello Bas,
This is not the correct interpretation of the code, the USERQ_IOCTL has both
the OPs (create and destroy), but th euser has to exclusively call
On Mon, Apr 10, 2023 at 4:01 PM Shashank Sharma wrote:
>
>
> On 10/04/2023 15:46, Bas Nieuwenhuizen wrote:
> > On Mon, Apr 10, 2023 at 3:40 PM Sharma, Shashank
> > wrote:
> >> [AMD Official Use Only - General]
> >>
> >> Hello Bas,
> >>
> >> This is not the correct interpretation of the code, the
On 10/04/2023 16:04, Bas Nieuwenhuizen wrote:
On Mon, Apr 10, 2023 at 4:01 PM Shashank Sharma wrote:
On 10/04/2023 15:46, Bas Nieuwenhuizen wrote:
On Mon, Apr 10, 2023 at 3:40 PM Sharma, Shashank
wrote:
[AMD Official Use Only - General]
Hello Bas,
This is not the correct interpretation
On 10/04/2023 02:02, Bas Nieuwenhuizen wrote:
On Wed, Mar 29, 2023 at 6:05 PM Shashank Sharma wrote:
From: Shashank Sharma
This patch adds:
- A new IOCTL function to create and destroy
- A new structure to keep all the user queue data in one place.
- A function to generate unique index for
From: Xiaogang Chen
During KFD restore evicted userptr BOs mmu invalidate callback may invalidate
same userptr BOs that have been just restored. When KFD restore process detects
it KFD will reschedule another validation process. It is not an error. Change
WARN to pr_debug, not put the BOs at user
On 3/25/23 09:45, Tom Rix wrote:
clang with W=1 reports
drivers/gpu/drm/amd/amdgpu/../display/dc/core/dc_link_enc_cfg.c:625:6: error:
variable 'matching_stream_ptrs' set but not used
[-Werror,-Wunused-but-set-variable]
int matching_stream_ptrs = 0;
^
This variable is not
On 4/6/23 14:44, Tom Rix wrote:
smatch reports
drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn314/dcn314_fpu.c:100:37:
warning: symbol
'dcn3_14_soc' was not declared. Should it be static?
This variable is only used in one file so should be static.
Signed-off-by: Tom Rix
Applied, thanks!
On 4/6/23 15:58, Tom Rix wrote:
smatch reports
drivers/gpu/drm/amd/amdgpu/../display/dc/dcn10/dcn10_hubp.c:758:10: warning:
symbol
'aperture_default_system' was not declared. Should it be static?
drivers/gpu/drm/amd/amdgpu/../display/dc/dcn10/dcn10_hubp.c:759:10: warning:
symbol
'context0
On 4/8/23 09:43, Tom Rix wrote:
smatch reports
drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.c:44:24: warning:
symbol
'dml20_funcs' was not declared. Should it be static?
drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.c:51:24: warning:
symbol
'dml20v2_funcs'
Am 09.04.23 um 17:59 schrieb Bas Nieuwenhuizen:
On Sun, Apr 9, 2023, 5:50 PM Timur Kristóf
wrote:
Christian König ezt írta
(időpont: 2023. ápr. 9., Vas 17:38):
Am 09.04.23 um 17:32 schrieb Bas Nieuwenhuizen:
> On Sun, Apr 9, 2023 at 5:30 PM Christian König
>
On Fri, Apr 7, 2023 at 5:17 AM Evan Quan wrote:
>
> Update the driver implementations to fit those data exposed
> by PMFW.
>
> Signed-off-by: Evan Quan
Acked-by: Alex Deucher
> Change-Id: I8579f6b22fb586bb52a6c97b8edfc13c493bd484
> ---
> drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h |
This code was written prior to previous updates to this
logic for other chips. The RSC registers are part of
SMUIO which is an always on block so there is no need
to disable gfxoff. Additionally add the carryover and
preemption checks.
Signed-off-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu
[Public]
A minor nitpick/suggestions below to make the comments a bit more concise. With
that change the patch is
Reviewed-by: Graham Sider
Best,
Graham
> -Original Message-
> From: amd-gfx On Behalf Of
> Sreekant Somasekharan
> Sent: Monday, April 3, 2023 3:59 PM
> To: amd-gfx@lists
Add some more logging for DP link traning test pattern seqeunces
for better debugging.
Cc: Jerry Zuo
Cc: Harry Wentland
Cc: Leo Li
Cc: Alex Deucher
Signed-off-by: Srinivasan Shanmugam
---
.../drm/amd/display/dc/link/protocols/link_dp_training.c | 9 +
1 file changed, 9 insertions(+)
[AMD Official Use Only - General]
-Original Message-
From: SHANMUGAM, SRINIVASAN
Sent: Monday, April 10, 2023 11:02 PM
To: Wentland, Harry ; Zuo, Jerry ;
Li, Sun peng (Leo) ; Deucher, Alexander
Cc: amd-gfx@lists.freedesktop.org; SHANMUGAM, SRINIVASAN
Subject: [PATCH v2] drm/amd/di
Hi Felix,
Thanks for your review and suggestion, but unfortunately the
AMDGPU_GEM_DOMAIN_PREEMPTIBLE is not defined in amdgpu_drm.h. I
understand we need the memory eviction on either kfd_mem_dmamap_dmabuf()
or kfd_mem_dmaunmap_dmabuf() to update DMA address, so I am thinking to
do it as simp
Sorry, you're right, there is no AMDGPU_GEM_DOMAIN_PREEMPTIBLE. I
remembered this wrong. There is a flag called
AMDGPU_GEM_CREATE_PREEMPTIBLE, which changes what happens when is placed
in the AMDGPU_GEM_DOMAIN_GTT domain.
So my proposal would need to be modified to set the flag
AMDGPU_GEM_CRE
Hi Felix,
What do you think my proposal in my previous email? that setting domain
to CPU in kfd_mem_dmamap_dmabuf, and setting domain to GTT in
kfd_mem_dmaunmap_dmabuf, that will be doing the similar way as userptr.
Thanks,
Eric
On 2023-04-10 14:50, Felix Kuehling wrote:
Sorry, you're right,
On 2023-04-10 15:03, Eric Huang wrote:
Hi Felix,
What do you think my proposal in my previous email? that setting
domain to CPU in kfd_mem_dmamap_dmabuf, and setting domain to GTT in
kfd_mem_dmaunmap_dmabuf, that will be doing the similar way as userptr.
No. This is the exact opposite of wha
On 2023-04-10 10:36, Xiaogang.Chen wrote:
From: Xiaogang Chen
During KFD restore evicted userptr BOs mmu invalidate callback may invalidate
same userptr BOs that have been just restored. When KFD restore process detects
it KFD will reschedule another validation process. It is not an error. Chan
[AMD Official Use Only - General]
Reviewed-by: Harish Kasiviswanathan
-Original Message-
From: amd-gfx On Behalf Of Graham Sider
Sent: Wednesday, April 5, 2023 11:42 AM
To: amd-gfx@lists.freedesktop.org
Cc: Yang, Stanley ; Sider, Graham
Subject: [PATCH] drm/amdgpu: Enable GFX11 SDMA c
Rename MODULE_FIRMWARE declaration of gc_11_0_4_mes to gc_11_0_4_mes_2
Signed-off-by: Li Ma
---
drivers/gpu/drm/amd/amdgpu/mes_v11_0.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 67f755
[AMD Official Use Only - General]
Please add
Fixes: 0f486b64b8d4 ("drm/amd/amdgpu: introduce gc_*_mes_2.bin v2")
With this fixed, patch Reviewed-by: Yifan Zhang
Best Regards,
Yifan
-Original Message-
From: Ma, Li
Sent: Tuesday, April 11, 2023 10:36 AM
To: amd-gfx@lists.freedesktop.
[AMD Official Use Only - General]
Reviewed-by: Stanley Yang
Regards,
Stanley
> -Original Message-
> From: Sider, Graham
> Sent: Wednesday, April 5, 2023 11:42 PM
> To: amd-gfx@lists.freedesktop.org
> Cc: Yang, Stanley ; Sider, Graham
>
> Subject: [PATCH] drm/amdgpu: Enable GFX11 SDMA c
[AMD Official Use Only - General]
Reviewed-by: Hawking Zhang
Regards,
Hawking
From: Stanley.Yang
Date: Monday, April 10, 2023 at 19:48
To: amd-gfx@lists.freedesktop.org , Zhang,
Hawking , Zhou1, Tao
Cc: Yang, Stanley
Subject: [PATCH Review 1/2] drm/admgpu: fix unexpected block id
Change-Id:
[AMD Official Use Only - General]
The series is:
Reviewed-by: Tao Zhou
> -Original Message-
> From: Stanley.Yang
> Sent: Monday, April 10, 2023 7:48 PM
> To: amd-gfx@lists.freedesktop.org; Zhang, Hawking
> ; Zhou1, Tao
> Cc: Yang, Stanley
> Subject: [PATCH Review 2/2] drm/amdgpu: cor
[AMD Official Use Only - General]
Just check gmc.xmgi.num_physical_nodes == 0 should be good enough for the case
that we only have single ALDEBRAN/ARCURUS available in system.
In such case, there is no need to expose xgmi_wafl ras node.
Regards,
Hawking
From: Stanley.Yang
Date: Monday, April
A spelling typo in subject, s/admgpu/amdgpu :)
Also maybe it's necessary to add a body text in commit message.
Regards,
Guchun
> -Original Message-
> From: amd-gfx On Behalf Of
> Stanley.Yang
> Sent: Monday, April 10, 2023 7:48 PM
> To: amd-gfx@lists.freedesktop.org; Zhang, Hawking
> ;
39 matches
Mail list logo
