[+Philip]
On 2018-11-07 12:25 a.m., Zhang, Jerry(Junwei) wrote:
> On 11/7/18 1:15 PM, Trigger Huang wrote:
>> Currently, SDMA page queue is not used under SR-IOV VF, and this
>> queue will
>> cause ring test failure in amdgpu module reload case. So just disable
>> it.
>>
>> Signed-off-by: Trigger
From: Harish Kasiviswanathan
Instead of waiting for each KFD BO after validation just wait for the
last BO moving fence.
Signed-off-by: Harish Kasiviswanathan
Reviewed-by: Felix Kuehling
Signed-off-by: Felix Kuehling
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 13 -
1
From: Gang Ba
Add Vega12 and Polaris12 device info and device IDs to KFD.
Signed-off-by: Gang Ba
Reviewed-by: Felix Kuehling
Signed-off-by: Felix Kuehling
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 2 +
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 3 +-
drivers/gpu/dr
From: Yong Zhao
This makes debug message get printed even when there is early return.
Signed-off-by: Yong Zhao
Reviewed-by: Felix Kuehling
Signed-off-by: Felix Kuehling
---
drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c | 14 +++---
1 file changed, 7 insertions(+), 7 deletions(-)
d
This change prepares for adding SG BOs that will be used for mapping
doorbells into GPUVM address space.
This type of BO would be mistaken for an invalid userptr BO. Improve
that check to test that it's actually a userptr BO so that SG BOs that
are still in the CPU domain can be validated and mapp
From: Yong Zhao
This is a known gfx9 HW issue, and this change can perfectly workaround
the issue.
Signed-off-by: Yong Zhao
Reviewed-by: Felix Kuehling
Signed-off-by: Felix Kuehling
---
drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c | 25 ++---
1 file changed, 22 inserti
From: Eric Huang
It is to improve system limit by:
1. replacing userptrlimit with a total memory limit that
conunts TTM memory usage and userptr usage.
2. counting acc size for all BOs.
Signed-off-by: Eric Huang
Reviewed-by: Felix Kuehling
Signed-off-by: Felix Kuehling
---
drivers/gpu/drm/am
These are some recent patches that are easy to upstream (part 1). For
part 2 (hopefully still this month) I'll need to advance the merging
of KFD into amdgpu a little further to avoid upstreaming duplicated
data structures that no longer need to be duplicated.
Eric Huang (1):
drm/amdkfd: change
From: Yong Zhao
This will make reading code much easier. This fixes a few spots missed in a
previous commit with the same title.
Signed-off-by: Yong Zhao
Reviewed-by: Felix Kuehling
Signed-off-by: Felix Kuehling
---
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 12 ++--
1 f
The adev parameter in amdgpu_sync_fence and amdgpu_sync_resv is only
needed for updating sync->last_vm_update. This breaks if different
adevs are passed to calls for the same sync object.
Always pass NULL for calls from KFD because sync objects used for
KFD don't belong to any particular device, a
From: Harish Kasiviswanathan
PD or PT might have to be moved during validation and this move has to be
completed before updating it. If page table updates are done using SDMA
then this serializing is done by SDMA command submission.
And if PD/PT updates are done by CPU, then explicit waiting for
On 2018-11-04 2:20 p.m., Christian König wrote:
> Am 02.11.18 um 19:59 schrieb Kuehling, Felix:
>> On 2018-11-02 9:48 a.m., Christian König wrote:
>>> Vega10 has multiple interrupt rings,
>> I don't think I've seen your code that implements multiple interru
On 2018-11-02 9:48 a.m., Christian König wrote:
> Vega10 has multiple interrupt rings,
I don't think I've seen your code that implements multiple interrupt
rings. So it's a bit hard to comment. As I understand it, the only way
this could happen is, if the two interrupt rings are handled by
differe
On 2018-10-25 2:27 p.m., Alex Deucher wrote:
> On Mon, Oct 22, 2018 at 6:25 PM Alex Deucher wrote:
>> Use the appropriate mmhub and gfxhub headers rather than adding
>> them to the gmc9 header.
>>
>> Signed-off-by: Alex Deucher
> Ping?
Reviewed-by: Felix Kuehling
>
> Alex
>
>> ---
>> drivers
On 2018-10-25 10:38 a.m., Christian König wrote:
> Make sure we don't try to go down further after the leave walk already
> ended. This fixes a crash with a new VM test.
>
> Signed-off-by: Christian König
Reviewed-by: Felix Kuehling
Regards,
Felix
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_v
The series is Reviewed-by: Felix Kuehling
On 2018-10-23 1:00 p.m., Zhao, Yong wrote:
>
> How about those two patches?
>
>
> Yong
>
>
> *From:* Zhao, Yong
> *Sent:* Monday, October 22, 2018 2:33:26 PM
> *To:* amd-gfx@lists.f
It occurred to me that the flush_type is a hardware-specific value, but
you're using it in a hardware-abstracted interface. If the meaning of
the flush type values changes in future HW-generations, we'll need to
define an abstract enum that gets translated to the respective HW values
in the HW-spec
Patch 1 is Reviewed-by: Felix Kuehling
Patch 2: I'm not sure we need the "lock" parameter and the invalidation
engine parameter. If we're serious about consolidating TLB invalidation
between amdgpu and KFD, I think we should use the same invalidation
engine and the same lock. Then you also don't
The BIOS signature check does not guarantee integrity of the BIOS image
either way. As I understand it, the signature is just a magic number.
It's not a cryptographic signature. The check is just a sanity check.
Therefore this change doesn't add any meaningful protection against the
scenario you de
On 2018-10-19 11:15 a.m., Lin, Amber wrote:
> Add amdgpu_amdkfd_ prefix to amdgpu functions served for amdkfd usage.
>
> v2: fix indentation
>
> Signed-off-by: Amber Lin
Reviewed-by: Felix Kuehling
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 18 +-
> drivers/gpu/
[+Christian]
Should the buffer funcs also use the paging ring? I think that would be
important for being able to clear page tables or migrating a BO while
handling a page fault.
Regards,
Felix
On 2018-10-19 3:13 p.m., Yang, Philip wrote:
> For sdma v4, there is bug caused by
> commit d4e869b6b
On 2018-10-18 5:59 p.m., wrote:
>
> Please include a patch description on 2 and 3, with that fixed, series is:
>
> Reviewed-by: Alex Deucher
>
Reviewed-by: Felix Kuehling
>
> *From:* Zhao, Yong
> *Sent:* Thursday, October
On 2018-10-18 6:03 p.m., Deucher, Alexander wrote:
>
> Series is:
>
> Reviewed-by: Alex Deucher
>
Reviewed-by: Felix Kuehling
as well.
>
> *From:* amd-gfx on behalf of
> Lin, Amber
> *Sent:* Thursday, October 18, 2018
Hi Alex,
If it's not too late, I'd like to get this into 4.19. Sorry I missed this fix
earlier.
Regards,
Felix
____
From: Kuehling, Felix
Sent: Tuesday, October 2, 2018 6:41:12 PM
To: amd-gfx@lists.freedesktop.org
Cc: oded.gab...@gmail.com; Kuehl
I think the answer is here:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/Documentation/vm/hmm.rst#n216
Regards,
Felix
From: Koenig, Christian
Sent: Thursday, September 27, 2018 10:30 AM
To: Kuehling, Felix
Cc: j.gli...@gmail.com; Yang, Philip ;
amd-gfx
er 27, 2018 9:59 AM
To: Kuehling, Felix
Cc: Yang, Philip ; amd-gfx@lists.freedesktop.org; Jerome
Glisse
Subject: RE: [PATCH] drm/amdgpu: use HMM mirror callback to replace mmu
notifier v4
Yeah I understand that, but again that won't work.
In this case you can end up accessing pages which
hole argument is that you don’t need to hold the read lock until the
invalidate_range_end. Just read_lock and read_unlock in the
invalidate_range_start function.
Regards,
Felix
From: Koenig, Christian
Sent: Thursday, September 27, 2018 9:22 AM
To: Kuehling, Felix
Cc: Yang, Philip ; amd-gf
bles just in the moment
> between the check of amdgpu_ttm_tt_userptr_needs_pages() and adding the fence
> to the reservation object.
I’m not planning to change that. I don’t think there is any need to change it.
Regards,
Felix
From: Koenig, Christian
Sent: Thursday, September 27, 2018 7
e.
I don’t see why this requires holding the read-lock until invalidate_range_end.
amdgpu_ttm_tt_affect_userptr gets called while the mn read-lock is held in
invalidate_range_start notifier.
Regards,
Felix
From: Koenig, Christian
Sent: Thursday, September 27, 2018 5:27 AM
To: Kuehling, Felix
Cc:
eeds to update the userptr addresses. If
the page tables are still being updated, it will block there even without
holding the amdgpu_mn_read_lock.
Regards,
Felix
From: Koenig, Christian
Sent: Thursday, September 27, 2018 3:00 AM
To: Kuehling, Felix
Cc: Yang, Philip ; amd-gfx@lists.freedesktop.
: Kuehling, Felix ; Yang, Philip
; amd-gfx@lists.freedesktop.org; Jerome Glisse
Subject: Re: [PATCH] drm/amdgpu: use HMM mirror callback to replace mmu
notifier v4
Am 14.09.2018 um 22:21 schrieb Felix Kuehling:
> On 2018-09-14 01:52 PM, Christian König wrote:
>> Am 14.09.2018 um 19:47 schri
least for currently available hardware we should limit page faults to
> be used in as few cases as possible, e.g. SVM and userptr.
>
> Regards,
> Christian.
From: Koenig, Christian
Sent: Wednesday, September 12, 2018 11:59 AM
To: Kuehling, Fe
ore challenging and
less effective.
Regards,
Felix
From: Christian König
Sent: Tuesday, September 11, 2018 2:49:44 AM
To: Kuehling, Felix; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH 01/11] drm/amdgpu: try allocating VRAM as power of two
Yeah well
This is on purpose. These functions for now are place holders because the PSP
firmware interface is not ready yet, and we want to start testing XGMI with
higher level code with some hard-coded topology. Once we have proper PSP
firmware, these place holders will be filled in.
Regards,
Felix
_
bo_va->base.moved
= false (it's done a few lines above this under some conditions, but not
always). The new code will always set bo_va->base.moved = false inside
amdgpu_vm_bo_idle.
Regards,
Felix
From: Christian König
Sent: Saturday, Septe
From: Oded Gabbay
Sent: Sunday, March 11, 2018 5:31:50 AM
To: Kuehling, Felix
Cc: amd-gfx list
Subject: Re: [PATCH 00/14] Add KFD GPUVM support for dGPUs v3
Hi Felix,
Is there a git repo where these patches exists ?
The reason I'm asking is because I'm constantly rebasing amdkfd-next
to
change. That is, these
features would have to be controlled by other means than by the vm context.
Regards,
Felix
From: amd-gfx on behalf of zhoucm1
Sent: Thursday, March 1, 2018 10:18:15 PM
To: Kuehling, Felix; amd-...@freedesktop.org; Koenig
, January 27, 2018 6:31:36 AM
To: Kuehling, Felix
Cc: amd-gfx list
Subject: Re: [PATCH 0/9] KFD dGPU initialization
Hi Felix,
Thanks for the ping, I also kept monitoring the status of that patch
and once it gets into Linus's branch I will rebase my tree on it. In
the meantime, I will begin revi
the trap handler as firmware to get around licensing issues.
Regards,
Felix
From: Oded Gabbay
Sent: Thursday, November 9, 2017 2:02:18 AM
To: Kuehling, Felix
Cc: amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH 1/1] drm/amdkfd: CWSR and trap handler su
]
Sent: Wednesday, October 18, 2017 12:36 AM
To: Kuehling, Felix
Cc: amd-gfx list
Subject: Re: [PATCH] drm/amdkfd: Make queue mapping interfaces more consistent
On Wed, Oct 18, 2017 at 5:55 AM, Felix Kuehling wrote:
> Pass unmap filter parameters directly to execute_queues_cpsch, same as
&g
This patch is Reviewed-by: Felix Kuehling
-Original Message-
From: amd-gfx [mailto:amd-gfx-boun...@lists.freedesktop.org] On Behalf Of Harry
Wentland
Sent: Monday, October 02, 2017 11:50 AM
To: amd-gfx@lists.freedesktop.org
Cc: Wentland, Harry
Subject: [PATCH v2] drm/amd/display: Disable
This treats Vega10 and Pre-Vega10 the same way. I don't understand how this
implements Vega10-specific behavior.
Regards,
Felix
-Original Message-
From: amd-gfx [mailto:amd-gfx-boun...@lists.freedesktop.org] On Behalf Of Harry
Wentland
Sent: Monday, October 02, 2017 11:32 AM
To: amd-
should I consult someone else
on their end as well?
Regards,
Felix
-Original Message-
From: Thangirala, Hari
Sent: Friday, September 22, 2017 8:44 PM
To: Kuehling, Felix; amd-gfx@lists.freedesktop.org; Oded Gabbay
Subject: RE: KFD event handling questions
Hi Felix,
Event IDs reserve
This should not be needed, because in Kconfig I made amdgpu depend on
CONFIG_CHASH.
Regards,
Felix
From: amd-gfx on behalf of S, Shirish
Sent: Thursday, September 21, 2017 3:35:01 AM
To: amd-gfx@lists.freedesktop.org; Deucher, Alexander
Subject: [PATC
Reviewed-by: Felix Kuehling
Sorry, I didn't think this one through. I'll keep looking for the real problem.
From: amd-gfx on behalf of Christian
König
Sent: Thursday, August 31, 2017 3:45:48 AM
To: amd-gfx@lists.freedesktop.org
Subject: [PATCH] drm/amdg
he problem, not fixed it.
Regards,
Felix
From: Christian König
Sent: Thursday, August 31, 2017 3:06:37 AM
To: Kuehling, Felix; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH 1/1] drm/amdgpu: Fix IB allocation sizes for page table
updates
Am 30.08.201
gt; Good point. Using "frag_end = end & ~((1ULL << max_frag) - 1);" should
> work as well, shouldn't it?
Yes, that would work too.
Regards,
Felix
____
From: Koenig, Christian
Sent: Thursday, August 31, 2017 3:31:36 AM
To: Ku
önig
Sent: Thursday, August 31, 2017 8:20:58 AM
To: Kuehling, Felix; amd-gfx@lists.freedesktop.org; Koenig, Christian
Subject: Re: [PATCH 2/4] drm/amdgpu: add support for per VM BOs v2
Am 31.08.2017 um 00:50 schrieb Felix Kuehling:
> Reviewed-by: Felix Kuehling
>
> Some more thoughts inli
Hi Oded,
Thanks for the heads up. Enjoy your vacation. I'll rebase this on Alex's
drm-next for your review.
Regards,
Felix
From: Oded Gabbay
Sent: Sunday, August 27, 2017 6:22:37 PM
To: Kuehling, Felix
Cc: amd-gfx list
Subject: Re: [PATC
of this patch series.
Regards,
Felix
From: amd-gfx on behalf of zhoucm1
Sent: Monday, August 28, 2017 3:15:23 AM
To: Christian König; Kuehling, Felix; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH 2/9] drm/amdgpu: Add PASID management
On 2017年08月
process.
Regards,
Felix
From: Christian König
Sent: Saturday, August 26, 2017 9:27 AM
To: Kuehling, Felix; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH 2/9] drm/amdgpu: Add PASID management
Am 26.08.2017 um 09:19 schrieb Felix Kuehling:
> Allows assigning a PASID to a VM f
Debugfs is only accessible by Root. The BIOS version is already reported in the
kernel log, which is visible to everyone. So why hide this away in debugfs?
I think Kent's intention is to add VBIOS version reporting to the rocm-smi
tool. I'd prefer using a stable interface like sysfs, and one tha
I'm not sure how dynamic CU masking works. But on a GPU with 64 CUs, a 32-bit
CU mask (in struct v9_mqd_allocation) seems too small.
Regards,
Felix
From: amd-gfx on behalf of Alex Deucher
Sent: Friday, August 18, 2017 11:57:51 PM
To: amd-gfx@lists.fre
28 AM
To: Kuehling, Felix
Cc: amd-gfx list
Subject: Re: [PATCH 00/19] KFD fixes and cleanups
Hi Felix,
Thanks for all the patches.
I have started to review them, but I have a small request from you
while I'm doing the review.
Could you please rebase them over my amdkfd-next branch, or
alt
12, 2017 8:37 AM
To: Kuehling, Felix
Cc: amd-gfx list
Subject: Re: [PATCH 03/19] drm/amdkfd: Remove bogus divide-by-sizeof(uint32_t)
On Sat, Aug 12, 2017 at 12:56 AM, Felix Kuehling wrote:
> kfd2kgd->address_watch_get_offset returns dword register offsets.
> The divide-by-sizeof(uin
KFD doesn't use CGS.
Regards,
Felix
-Original Message-
From: amd-gfx [mailto:amd-gfx-boun...@lists.freedesktop.org] On Behalf Of
Deucher, Alexander
Sent: Wednesday, April 26, 2017 12:36 PM
To: 'Christian König'; amd-gfx@lists.freedesktop.org
Subject: RE: [PATCH] drm/amdgpu: remove unus
| \ / | | _ \ \ _ |
/ A \ | \M/ | | |D) ) /|_| |
/_/ \_\ |_| |_| |_/ |__/ \| facebook.com/AMD | amd.com
From: Zhang, Jerry
Sent: Tuesday, March 28, 2017 10:54:03 PM
To: Kuehling, Felix; amd-gfx@lists.freedesktop.org; Koenig, Christian; Zhou,
David(Ch
ucher, Alexander
Sent: Monday, August 08, 2016 2:04 PM
To: StDenis, Tom; Kuehling, Felix; amd-gfx@lists.freedesktop.org
Subject: RE: [PATCH 09/14] drm/amd/amdgpu: Enable carrizo GFX PG
I'm not sure gfx PG works properly with some of the kfd features. I know there
were problems in the past. We probab
501 - 558 of 558 matches
Mail list logo