@lists.freedesktop.org
Cc: Deucher, Alexander ; Zhao, Yong
; Quan, Evan
Subject: [PATCH] drm/amd/powerplay: check whether SMU IP is enabled before
access
Since on early phase of bringup, the SMU IP may be not enabled or
supported. Without this, we may hit null pointer dereference on
accessing smu->a
[AMD Official Use Only - Internal Distribution Only]
Hi Fenghua,
I am okay with the idea.
Regards,
Yong
From: Fenghua Yu
Sent: Friday, May 22, 2020 5:21 PM
To: Kuehling, Felix
Cc: Zhao, Yong ; amd-gfx@lists.freedesktop.org
Subject: Re: drm/amdkfd: Change
[AMD Official Use Only - Internal Distribution Only]
The series are
Reviewed-by: Yong Zhao
From: amd-gfx on behalf of Alex Deucher
Sent: Thursday, May 21, 2020 12:52 PM
To: amd-gfx list
Cc: Deucher, Alexander
Subject: Re: [PATCH 2/2] drm/amdgpu: drop navi pc
[AMD Official Use Only - Internal Distribution Only]
Okay, I will change back to its original format.
Yong
From: Kuehling, Felix
Sent: Thursday, March 5, 2020 3:49 PM
To: amd-gfx@lists.freedesktop.org ; Zhao, Yong
Subject: Re: [PATCH] drm/amdkfd: Consolidate
[AMD Official Use Only - Internal Distribution Only]
Reviewed-by: Yong Zhao
From: amd-gfx on behalf of Alex Deucher
Sent: Thursday, February 27, 2020 3:14 PM
To: amd-gfx@lists.freedesktop.org
Cc: Deucher, Alexander
Subject: [PATCH 1/2] drm/amdgpu: remove unus
[AMD Official Use Only - Internal Distribution Only]
It looks good to me. I was thinking maybe we should go one step further, adding
more explanation comments around the MQD control stack workaround, so that
people have a clearer idea of what's that MQD control stack workaround is
about. We can
[AMD Official Use Only - Internal Distribution Only]
Reviewed-by: Yong Zhao
From: amd-gfx on behalf of Felix
Kuehling
Sent: Wednesday, February 26, 2020 12:12 PM
To: amd-gfx@lists.freedesktop.org ; Deucher,
Alexander
Cc: Pan, Xinhui
Subject: [PATCH 1/1] drm/
: Kuehling, Felix
Sent: Tuesday, February 25, 2020 12:06 PM
To: Zhao, Yong ; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH 6/6] drm/amdkfd: Delete unnecessary unmap queue package
submissions
As I understand it, the SDMA queue counting wasn't incorrect. The main
change here is that you no l
[AMD Official Use Only - Internal Distribution Only]
True. There indeed are two vmhubs on Navi. So my two comments are not useful
here.
Yong
From: Kuehling, Felix
Sent: Monday, December 23, 2019 2:34 PM
To: Zhao, Yong ; Sierra Guiza, Alejandro (Alex)
; amd-gfx
in switch.
Yong
From: Kuehling, Felix
Sent: Monday, December 16, 2019 2:39 PM
To: Zhao, Yong ; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH] drm/amdkfd: Improve function get_sdma_rlc_reg_offset()
On 2019-12-13 8:38, Yong Zhao wrote:
> This prevents
[AMD Official Use Only - Internal Distribution Only]
Reviewed-by: Yong Zhao
From: amd-gfx on behalf of Felix
Kuehling
Sent: Monday, November 25, 2019 4:28 PM
To: amd-gfx@lists.freedesktop.org
Subject: [PATCH 1/1] drm/amdgpu: Raise KFD unpinned system memory li
f the name
changes because the original names are prone to cause confusion.
Regards,
Yong
From: Kuehling, Felix
Sent: Friday, November 22, 2019 4:21 PM
To: Zhao, Yong ; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH 2/2] drm/amdkfd: Move pm_create_runlist_ib() o
Reviewed-by: Yong Zhao
From: amd-gfx on behalf of Alex Deucher
Sent: Friday, November 15, 2019 11:13 AM
To: amd-gfx list
Cc: Deucher, Alexander
Subject: Re: [PATCH] drm/amdgpu/soc15: move struct definition around to align
with other soc15 asics
Ping?
On Mon
+ Laurent
From: Zhao, Yong
Sent: Monday, November 11, 2019 6:25 PM
To: amd-gfx@lists.freedesktop.org ; Cornwall,
Jay
Cc: Zhao, Yong
Subject: [PATCH 3/3] drm/amdkfd: Fix a bug when calculating save_area_used_size
workgroup context data writes from m
Okay. I submitted a PSDB. Meanwhile, I got the answer from FW and SQ HW contact
that nothing bad will happen on GFX9 by writing 1 to TRAP_EN.
Regards,
Yong
From: Kuehling, Felix
Sent: Thursday, November 7, 2019 4:07 PM
To: Zhao, Yong ; amd-gfx
rongly about.
With that said, the change is
Reviewed-by: Felix Kuehling
<mailto:felix.kuehl...@amd.com>
Regards,
Felix
Regards,
Yong
From: Kuehling, Felix <mailto:felix.kuehl...@amd.com>
Sent: Thursday, November 7, 2019 2:12 PM
To: Zhao, Yon
The kernel queue functions for v9 and v10 are the same except
pm_map_process_v* which have small difference, so they should be reused.
This eliminates the need of reapplying several patches which were
applied on v9 but not on v10, such as bigger GWS and more than 2
SDMA engine support which were in
, it is a must.
Regards,
Yong
From: Kuehling, Felix
Sent: Thursday, November 7, 2019 2:12 PM
To: Zhao, Yong ; Alex Deucher
Cc: Russell, Kent ; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH 2/3] drm/amdkfd: only keep release_mem function for Hawaii
On 2019-11
pre SOC15 or not, and I have an impression that MEC
firmware agrees to maintain the kernel queue interface stable across
generations most of time.
Regards,
Yong
From: Alex Deucher
Sent: Thursday, November 7, 2019 1:32 PM
To: Kuehling, Felix
Cc: Zhao, Yong
The kernel queue functions for v9 and v10 are the same except
pm_map_process_v* which have small difference, so they should be reused.
This eliminates the need of reapplying several patches which were
applied on v9 but not on v10, such as bigger GWS and more than 2
SDMA engine support which were in
Kent
From: amd-gfx
<mailto:amd-gfx-boun...@lists.freedesktop.org>
On Behalf Of Zhao, Yong
Sent: Thursday, November 7, 2019 11:57 AM
To: Kuehling, Felix <mailto:felix.kuehl...@amd.com>;
amd-gfx@lists.freedesktop.org<mailto:amd-gfx@lists.freedesktop.org>
Subject: Re: [PATCH 2/3
The new code uses straightforward bit shifts and thus has better readability.
Change-Id: I0c1f7cca7e24ddb7b4ffe1cb0fa71943828ae373
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 17 +++--
drivers/gpu/drm/amd/amdkfd/kfd_events.c | 1 -
drivers/gpu/drm/amd/am
True. Thank you for spotting that. MMAP-related code was added after I
inititally drafted this change earlier this year.
Regards,
Yong
From: Kuehling, Felix
Sent: Thursday, November 7, 2019 12:05 AM
To: Zhao, Yong ; amd-gfx@lists.freedesktop.org
Subject: Re
If this is not submitted, I would like to see some comments regarding the
explanation of MC address and logical address, which I prefer to mention as GPU
physical/virtual address.
Regards,
Yong
From: amd-gfx on behalf of Alex Deucher
Sent: Thursday, November
Hi Felix,
That's because v8 and v7 share the same packet_manager_funcs. In this case, it
is better to keep it as it is.
Regards,
Yong
From: Kuehling, Felix
Sent: Wednesday, November 6, 2019 11:45 PM
To: Zhao, Yong ; amd-gfx@lists.freedesktop.org
Subjec
See two wording comments inline. With that
Reviewed-by: Yong Zhao
On 2019-10-30 2:41 p.m., Alex Deucher wrote:
> Clarify some areas, clean up formatting, add section for
> unrecoverable error handling.
>
> Signed-off-by: Alex Deucher
> ---
> Documentation/gpu/amdgpu.rst| 35 +++
Reviewed-by: Yong Zhao
On 2019-10-30 10:22 a.m., Alex Deucher wrote:
> Need to set the dte flag on this asic.
>
> Port the fix from amdgpu:
> 5cb818b861be114148e8dbeb4259698148019dd1
>
> Signed-off-by: Alex Deucher
> ---
> drivers/gpu/drm/radeon/si_dpm.c | 1 +
> 1 file changed, 1 insertion(+)
Reviewed-by: Yong Zhao
On 2019-11-06 11:34 a.m., Alex Deucher wrote:
> Ping?
>
> On Tue, Oct 29, 2019 at 4:10 PM Alex Deucher wrote:
>> To properly handle the option parsing ordering.
>>
>> Signed-off-by: Alex Deucher
>> ---
>> drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 6 ++
>> drivers/gpu
The new code uses straightforward bit shifts and thus has better readability.
Change-Id: I0c1f7cca7e24ddb7b4ffe1cb0fa71943828ae373
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 10 --
drivers/gpu/drm/amd/amdkfd/kfd_events.c | 1 -
drivers/gpu/drm/amd/amdkfd/kf
Okay. I will delete that line.
Regards,
Yong
From: Kuehling, Felix
Sent: Tuesday, November 5, 2019 5:34 PM
To: Zhao, Yong ; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH] drm/amdkfd: Simplify the mmap offset related bit operations
On 2019-11-01 7:03 p.m
g, Felix
Sent: Friday, November 1, 2019 6:48 PM
To: Zhao, Yong ; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH] drm/amdkfd: Simplify the mmap offset related bit operations
On 2019-11-01 4:48 p.m., Zhao, Yong wrote:
> The new code is much cleaner and results
Sent: Friday, November 1, 2019 5:13 PM
To: amd-gfx@lists.freedesktop.org ; Zhao, Yong
Subject: Re: [PATCH] drm/amdkfd: Simplify the mmap offset related bit operations
NAK. This won't work for several reasons.
The mmap_offset is used as offset parameter in the mmap system call. If
you check th
Please discard this one and look for an update version.
Regards,
Yong
From: Zhao, Yong
Sent: Friday, November 1, 2019 4:11 PM
To: amd-gfx@lists.freedesktop.org
Cc: Zhao, Yong
Subject: [PATCH] drm/amdkfd: Simplify the mmap offset related bit operations
The new
The new code is much cleaner and results in better readability.
Change-Id: I0c1f7cca7e24ddb7b4ffe1cb0fa71943828ae373
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 13 +++--
drivers/gpu/drm/amd/amdkfd/kfd_events.c | 1 -
drivers/gpu/drm/amd/amdkfd/kfd_priv.h
The new code is much cleaner and results in better readability.
Change-Id: I0c1f7cca7e24ddb7b4ffe1cb0fa71943828ae373
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 10 --
drivers/gpu/drm/amd/amdkfd/kfd_events.c | 1 -
drivers/gpu/drm/amd/amdkfd/kfd_priv.h|
create_cp_queue() could also work with SDMA queues, so we should rename
it.
Change-Id: I76cbaed8fa95dd9062d786cbc1dd037ff041da9d
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/g
Change-Id: I75da23bba90231762cf58da3170f5bb77ece45ed
Signed-off-by: Yong Zhao
---
.../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 2 +-
drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c | 14 +++---
drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 8
3 files changed,
dorbell_off in the queue properties is mainly used for the doorbell dw
offset in pci bar. We should not set it to the doorbell byte offset in
process doorbell pages. This makes the code much easier to read.
Change-Id: I553045ff9fcb3676900c92d10426f2ceb3660005
Signed-off-by: Yong Zhao
---
drivers
The kernel queue functions for v9 and v10 are the same except
pm_map_process_v* which have small difference, so they should be reused.
This eliminates the need of reapplying several patches which were
applied on v9 but not on v10, such as bigger GWS and more than 2
SDMA engine support which were in
release_mem won't be used at all on GFX9 and GFX10, so delete it.
Change-Id: I13787a8a29b83e7516c582a7401f2e14721edf5f
Signed-off-by: Yong Zhao
---
.../gpu/drm/amd/amdkfd/kfd_kernel_queue_v10.c | 35 ++-
.../gpu/drm/amd/amdkfd/kfd_kernel_queue_v9.c | 33 ++---
2 file
This is cleaner.
Change-Id: I8cdecad387d8c547a088c6050f77385ee1135be1
Signed-off-by: Yong Zhao
---
.../gpu/drm/amd/amdkfd/kfd_kernel_queue_v9.c | 19 +++
1 file changed, 7 insertions(+), 12 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_v9.c
b/drivers/gp
Modified according to the comment and pushed. Thanks!
Regards,
Yong
From: Alex Deucher
Sent: Monday, October 28, 2019 8:39 AM
To: Zhao, Yong
Cc: amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH] drm/amdkfd: Delete unnecessary pr_fmt switch
On Fri, Oct 25
Given amdkfd.ko has been merged into amdgpu.ko, this switch is no
longer useful.
Change-Id: If56b80e086f4ea26f347c70b620b3892afc24ddf
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 1 -
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c | 4
drivers/gpu/
The KIQ is on the second MEC and its reservation is covered in the
latter logic, so no need to reserve its bit twice.
Change-Id: Ieee390953a60c7d43de5a9aec38803f1f583a4a9
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 8
1 file changed, 8 deletions(-)
diff --
t said, you don't really save any
> resources, because 8-bit and 16-bit ints still consume 32-bits on the
> call stack.
>
> Regards,
> Felix
>
> On 2019-09-27 11:41 p.m., Zhao, Yong wrote:
>> This is consistent with other code and
The code use hex define, so should the printing.
Change-Id: Ia7cc7690553bb043915b3d8c0157216c64421a60
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
b/drivers
Not much relationship between them, except that this functional change is to
fix a IOCTL error printing.
Yong
From: Kuehling, Felix
Sent: Monday, September 30, 2019 11:57 AM
To: Zhao, Yong ; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH 5/6] drm/amdgpu
Okay, I will change dev_err back to dev_dbg. The hex printing is still very
useful.
Yong
From: Kuehling, Felix
Sent: Monday, September 30, 2019 11:47 AM
To: Zhao, Yong ; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH 6/6] drm/amdkfd: Improve KFD IOCTL
Thanks. Will check that and fix the missing const.
Yong
From: Kuehling, Felix
Sent: Monday, September 30, 2019 11:42 AM
To: Zhao, Yong ; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH 4/6] drm/amdkfd: Use array to probe kfd2kgd_calls
On 2019-09-27 11:41 p.m
This is the same idea as the kfd device info probe and move all the
probe control together for easy maintenance.
Change-Id: I85c98bb08eb2a4a1a80c3b913c32691cc74602d1
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c| 65 +--
drivers/gpu/drm/amd/amdgpu/am
The HDP flush support code was missing in the nbio and nv files.
Change-Id: I046ff52567676b56bf16dc1728b02481233acb61
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c | 16 +---
drivers/gpu/drm/amd/amdgpu/nv.c| 9 +
2 files changed, 22 insertions(+
The code use hex define, so should the printing. Also, printf a message
if there is a failure.
Change-Id: Ia7cc7690553bb043915b3d8c0157216c64421a60
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drive
Ajust the function sequences so that those function delcarations are not
needed any more.
Change-Id: I3a270ade7ac380cd083e90611177d7a45249823f
Signed-off-by: Yong Zhao
---
.../drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c| 115 +
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c | 118 +
This is consistent with other code and registers in the code.
Change-Id: I04dd12bdb465a43cfcd8936ed0f227a6546830e8
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c| 4 ++--
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c | 4 ++--
drivers/gpu/drm/amd/amdg
Those header file includes are not needed.
Change-Id: I44aa7e4d0391f9b2c2be757765c1437b603688ae
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c | 6 --
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c | 2 --
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
The KFD code will call this function later.
Change-Id: I5993323603799963e9eb473852b6c72de2172ed6
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c | 19 ---
drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.h | 2 ++
2 files changed, 14 insertions(+), 7 deletions(-)
diff
On 2019-09-26 6:16 p.m., Kuehling, Felix wrote:
> On 2019-09-26 5:59 p.m., Zhao, Yong wrote:
>> On 2019-09-26 5:36 p.m., Kuehling, Felix wrote:
>>> Minor nit-pick inline. Otherwise this patch is
>>>
>>> Reviewed-by: Felix Kuehling
>>>
>>>
Okay, I will delete that message.
Yong
On 2019-09-26 5:31 p.m., Kuehling, Felix wrote:
> On 2019-09-26 5:27 p.m., Zhao, Yong wrote:
>> Because we record the mapping under non HWS mode in the software,
>> we can query pasid through vmid using the stored mapping instead of
>
On 2019-09-26 5:36 p.m., Kuehling, Felix wrote:
> Minor nit-pick inline. Otherwise this patch is
>
> Reviewed-by: Felix Kuehling
>
> On 2019-09-26 5:27 p.m., Zhao, Yong wrote:
>> This makes possible the vmid pasid mapping query through soft
This makes possible the vmid pasid mapping query through software.
Change-Id: Ib539aae277a227cc39f6469ae23c46c4d289b87b
Signed-off-by: Yong Zhao
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 33 ---
.../drm/amd/amdkfd/kfd_device_queue_manager.h | 3 +-
drivers/gpu/drm/amd/
Because we record the mapping under non HWS mode in the software,
we can query pasid through vmid using the stored mapping instead of
reading from ATC registers.
This also prepares for the defeatured ATC block in future ASICs.
Change-Id: I781cb9d30dc0cc93379908ff1cf8da798bb26f13
Signed-off-by: Yo
Because we record the mapping in the software, we can query pasid
through vmid using the stored mapping instead of reading from ATC
registers.
This also prepares for the defeatured ATC block in future ASICs.
Change-Id: I781cb9d30dc0cc93379908ff1cf8da798bb26f13
Signed-off-by: Yong Zhao
---
drive
This makes possible the vmid pasid mapping query through software.
Change-Id: Ib539aae277a227cc39f6469ae23c46c4d289b87b
Signed-off-by: Yong Zhao
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 33 ---
.../drm/amd/amdkfd/kfd_device_queue_manager.h | 3 +-
drivers/gpu/drm/amd/
I agree.
Yong
On 2019-09-26 2:54 p.m., Kuehling, Felix wrote:
> On 2019-09-26 2:38 p.m., Zhao, Yong wrote:
>> This makes possible the vmid pasid mapping query through software.
>>
>> Change-Id: Ib539aae277a227cc39f6469ae23c46c4d289b87b
>> Signed-off-by: Yong Zhao
>
Hi Felix,
I reworded this patch in the next series. Please review the first two patches
in this series.
Regards,
Yong
From: amd-gfx on behalf of Zhao, Yong
Sent: Wednesday, September 25, 2019 2:34 PM
To: Kuehling, Felix ; amd-gfx@lists.freedesktop.org
Because we record the mapping in the software, we can query pasid
through vmid using the stored mapping instead of reading from ATC
registers.
This also prepares for the defeatured ATC block in future ASICs.
Change-Id: I781cb9d30dc0cc93379908ff1cf8da798bb26f13
Signed-off-by: Yong Zhao
---
.../g
They are not used anywhere.
Change-Id: Ieba4f57760f0c45f24e54629245cae419b8ff157
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
b/drivers/gpu/drm/amd/amdgpu/am
get_atc_vmid_pasid_mapping_valid() is very similar to
get_atc_vmid_pasid_mapping_pasid(), so they can be merged into a new
function get_atc_vmid_pasid_mapping_info() to reduce register access
times.
Change-Id: I255ebf2629012400b07fe6a69c3d075cfd46612e
Signed-off-by: Yong Zhao
---
.../drm/amd/amd
The GFX10 does not require the control stack to be right after mqd
buffer any more, so move it back to usersapce allocated CSWR buffer.
Change-Id: I446c9685549a09ac8846a42ee22d86cfb93fd98c
Signed-off-by: Yong Zhao
---
.../gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c | 37 ++-
1 file
Since KFD pasid starts from 0x8000 (32768 in decimal), it is better
perceived as a hex number. Meanwhile, change the pasid type from
unsigned int to uint16_t to be consistent throughout the code.
Change-Id: I565fe39f69e782749a697f18545775354c7a89f8
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/am
This makes possible the vmid pasid mapping query through software.
Change-Id: Ib539aae277a227cc39f6469ae23c46c4d289b87b
Signed-off-by: Yong Zhao
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 34 +--
.../drm/amd/amdkfd/kfd_device_queue_manager.h | 3 +-
2 files changed, 26
Reviewed-by: Yong Zhao
From: amd-gfx on behalf of Cornwall,
Jay
Sent: Wednesday, September 25, 2019 6:06 PM
To: amd-gfx@lists.freedesktop.org
Cc: Cornwall, Jay
Subject: [PATCH] drm/amdkfd: Fix race in gfx10 context restore handler
Missing synchronization with
Since KFD pasid starts from 0x8000 (32768 in decimal), it is better
perceived as a hex number.
Change-Id: I565fe39f69e782749a697f18545775354c7a89f8
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 12 +--
drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c | 4 ++--
Yes. I confirmed with CP guys and they said the behavior on GFX10 is the
same as GFX8 now. I remember that the workaround on GFX9 was to help
with a HW bug, but not too sure.
Regards,
Yong
On 2019-09-25 2:25 p.m., Kuehling, Felix wrote:
> On 2019-09-25 2:15 p.m., Zhao, Yong wrote:
>
The GFX10 does not have this hardware bug any more, so remove it.
Change-Id: I446c9685549a09ac8846a42ee22d86cfb93fd98c
Signed-off-by: Yong Zhao
---
.../gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c | 37 ++-
1 file changed, 4 insertions(+), 33 deletions(-)
diff --git a/drivers/gpu/d
This was done on GFX9 previously, now do it for GFX10.
Change-Id: I4442e60534c59bc9526a673559f018ba8058deac
Signed-off-by: Yong Zhao
---
.../drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c| 23 +++
1 file changed, 3 insertions(+), 20 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdg
The KFD code will call this function later.
Change-Id: I88a53368cdee719b2c75393e5cdbd8290584548e
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c | 20
drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.h | 2 ++
2 files changed, 14 insertions(+), 8 deletions(-)
d
: Zhao, Yong ; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH] drm/amdkfd: Add NAVI12 support from kfd side
I will push to drm-next branch . After check the code again , this change will
cause issue in the kfd since CHIP_NAVI12 not added in other place where
check the device_info
Reviewed-by: Yong Zhao
Make sure to push to the new 5.3 branch.
Yong
From: amd-gfx on behalf of Liu, Shaoyun
Sent: Tuesday, September 24, 2019 6:16 PM
To: amd-gfx@lists.freedesktop.org
Cc: Liu, Shaoyun
Subject: [PATCH] drm/amdkfd: Add NAVI12 support from kf
Currently this function pointer is missing for GFX10. Considering it is
a void function since GFX9, fix it by checking the function pointer
before dereferencing it.
Change-Id: I1dc8e5163f259251357bfaa42a91ff991fba6dd5
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus
get_hive_id was not set. Also, adjust the function setting sequence.
Change-Id: I51962954cd0707ebe9aa6c85c71110dee98d6200
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/a
Okay, I will incorporate Shaoyun's input.
Yong
From: Liu, Shaoyun
Sent: Monday, September 23, 2019 10:27 AM
To: Zhao, Yong ; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH 2/2] drm/amdkfd: Use better name for sdma queue non HWS path
Probably rena
The packet manager is not needed for non HWS mode except Hawaii, so only
initialize it for Hawaii under non HWS mode. This will simplify debugging
under non HWS mode for all new asics, because it eliminates one variable
out of the equation in non HWS mode
Change-Id: Ie2b61b546299a50366b9ab97900f4b
The dozens of printing messages are compressed into 2 lines.
Change-Id: I339b3eee06509973f76577091c4c4e9c70ed8248
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_process.c | 12
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_
The message will be useful when troubleshooting the issues.
Change-Id: Id82bbe80810dccff67c5b1275e9779f6a945dc7a
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c | 8 ++--
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c | 8 ++--
drivers/gpu/drm/amd/am
It turns out when loading hqd for SDMA queues, RESUME_CTX of
SDMA*_GFX_CONTEXT_CNTL is already 0, so there is no need to set it
to 0 again. In addition, it does not seem right that we should touch
SDMA GFX queues when manipulating RLC queues.
Change-Id: I2c142d024e94f92194b1cb9feb7f44396b8f3ecc
Si
The old name is prone to confusion. The register offset is for a RLC queue
rather than a SDMA engine. The value is not a base address, but a
register offset.
Change-Id: I55fb835f2105392344b1c17323bb55c03f927836
Signed-off-by: Yong Zhao
---
.../drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c | 85 +
These were deleted before, but somehow showed up again. Delete them again.
Change-Id: I19b3063932380cb74a01d505e8e92f897a2c2cb7
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 4
1 file changed, 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
b/drive
This was deleted before, but somehow showed up again. Delete it again.
Change-Id: I19b3063932380cb74a01d505e8e92f897a2c2cb7
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 3 ---
1 file changed, 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
b/drivers/gp
Fixed and pushed. Thanks.
Regards,
Yong
On 2019-09-05 3:56 p.m., Kuehling, Felix wrote:
> On 2019-09-05 3:22 p.m., Zhao, Yong wrote:
>> Change-Id: Ie2c6226022ff4d389eaa05b1c84afa7ae4cea0aa
>> Signed-off-by: Yong Zhao
> Please add a change description. With that fi
Change-Id: Ie2c6226022ff4d389eaa05b1c84afa7ae4cea0aa
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_crat.c | 1 +
drivers/gpu/drm/amd/amdkfd/kfd_device.c | 19 +++
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 1 +
drivers/gpu/drm/amd/amdkfd/kfd_flat
The issue was accidentally introduced recently.
Change-Id: I3b21caa1596d4f7de1866bed1cb5d8fe1b51504c
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_device.c | 6 --
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
b/drivers/g
Pushed. Will work on the market name later.
Yong
From: Kuehling, Felix
Sent: Thursday, August 15, 2019 8:45 PM
To: Zhao, Yong ; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH] drm/amdkfd: Fill the name field in node topology with asic
name v2
On 2019-08-13
Pushed! Thanks.
Yong
On 2019-08-14 3:27 a.m., Christian König wrote:
> Am 13.08.19 um 20:08 schrieb Zhao, Yong:
>> RW is also useful in most cases.
>>
>> Change-Id: Icf4bd65ea168e5965a6a8ebe32ce9327a2de2851
>> Signed-off-by: Yong Zhao
>
> Reviewed-by
The name field in node topology has not been used. We re-purpose it to
hold the asic name, which can be queried by user space applications
through sysfs.
Change-Id: I74f4f5487db169004a9d27ea15abe99261c86220
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_device.c | 18 +
The amdgpu_task_info will be used when printing VM page fault for KFD
processes.
Change-Id: Ifd983db5dceb1d477e7287e4893f80565a7a6b06
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_process.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process
We have done this for pre-GFX10 asics, but GFX10 did not pick up the
new change. The below is the commit message for that change.
This is recommended by HW designers. Previously when it was set to 1,
the PDE walk error in VM fault will be treated as
PERMISSION_OR_INVALID_PAGE_FAULT rather than usu
The printing we did for GFX9 was not propogated to GFX10 somehow, so fix
it now.
Change-Id: Ic0b8381134340b83cd69c3fe186ac7a8a97b1bca
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 33 ++
1 file changed, 28 insertions(+), 5 deletions(-)
diff --git
RW is also useful in most cases.
Change-Id: Icf4bd65ea168e5965a6a8ebe32ce9327a2de2851
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 296
quot;:".
Regards,
Yong
On 2019-08-12 3:12 p.m., Christian König wrote:
> Am 12.08.19 um 21:05 schrieb Zhao, Yong:
>> The printing we did for GFX9 was not propogated to GFX10 somehow, so fix
>> it now.
>>
>> Change-Id: Ic0b8381134340b83cd69c3fe186ac7a8a97b1bca
>
1 - 100 of 174 matches
Mail list logo
