On 2025/7/10 12:18, Lazar, Lijo wrote:
On 7/10/2025 1:20 AM, Mario Limonciello wrote:
On 7/9/2025 6:05 AM, Samuel Zhang wrote:
For normal hibernation, GPU do not need to be resumed in thaw since it is
not involved in writing the hibernation image. Skip resume in this case
can reduce the hibe
On 2025/7/8 22:40, Mario Limonciello wrote:
On 7/8/2025 3:42 AM, Samuel Zhang wrote:
For normal hibernation, GPU do not need to be resumed in thaw since
it is
not involved in writing the hibernation image. Skip resume in this case
can reduce the hibernation time.
On VM with 8 * 192GB VRAM dG
On 2025/7/8 22:36, Mario Limonciello wrote:
On 7/8/2025 3:42 AM, Samuel Zhang wrote:
dev_pm_ops.thaw() is called in following cases:
* normal case: after hibernation image has been created.
* error case 1: creation of a hibernation image has failed.
* error case 2: restoration from a hibernati
On 2025/7/2 22:07, Lazar, Lijo wrote:
On 7/2/2025 7:24 PM, Alex Deucher wrote:
On Wed, Jul 2, 2025 at 3:24 AM Sam wrote:
On 2025/7/2 00:07, Alex Deucher wrote:
On Tue, Jul 1, 2025 at 4:32 AM Christian König wrote:
On 01.07.25 10:03, Zhang, GuoQing (Sam) wrote:
thaw() is called before
From: Koenig, Christian
Date: Monday, June 30, 2025 at 19:54
To: Zhang, GuoQing (Sam) , raf...@kernel.org
, len.br...@intel.com ,
pa...@kernel.org , Deucher, Alexander
, Limonciello, Mario ,
Lazar, Lijo
Cc: Zhao, Victor , Chang, HaiJun ,
Ma, Qing (Mark) , amd-gfx@lists.freedesktop.org
,
thaw() is called before writing the hiberation image to swap disk. See
the doc here.
https://github.com/torvalds/linux/blob/v6.14/Documentation/driver-api/pm/devices.rst?plain=1#L552
And amdgpu implemented thaw() callback by calling amdgpu_device_resume().
https://github.com/torvalds/linux/blob/v
On 2025/5/21 20:00, Christian König wrote:
> On 5/21/25 13:55, Zhang, GuoQing (Sam) wrote:
>> On 2025/5/21 16:06, Christian König wrote:
>>> On 5/20/25 07:10, Zhang, GuoQing (Sam) wrote:
>>>>>> +if (amdgpu_virt_xgmi_migrate_enabled(adev)) {
>>>&
On 2025/5/21 16:06, Christian König wrote:
> On 5/20/25 07:10, Zhang, GuoQing (Sam) wrote:
>>>> +if (amdgpu_virt_xgmi_migrate_enabled(adev)) {
>>>> +/* set mc->vram_start to 0 to switch the returned GPU address
>>>> of
>>>&g
On 2025/5/19 21:57, Christian König wrote:
> On 5/19/25 10:20, Samuel Zhang wrote:
>> When switching to new GPU index after hibernation and then resume,
>> VRAM offset of each VRAM BO will be changed, and the cached gpu
>> addresses needed to updated.
>>
>> This is to enable pdb0 and switch to use
4] drm/amdgpu: fix fence fallback timer expired error
Regards
Sam
From: Lazar, Lijo
Date: Friday, May 16, 2025 at 18:22
To: Zhang, GuoQing (Sam) , amd-gfx@lists.freedesktop.org
Cc: Zhao, Victor , Chang, HaiJun ,
Koenig, Christian , Deucher, Alexander
, Zhang, Owen(SRDC) , Ma, Qing
(Mark)
Subje
[AMD Official Use Only - AMD Internal Distribution Only]
Hi @Koenig, Christian<mailto:christian.koe...@amd.com> and @Lazar,
Lijo<mailto:lijo.la...@amd.com>,
Ping…
Thanks
Sam
From: Zhang, Owen(SRDC)
Date: Wednesday, May 14, 2025 at 18:07
To: Koenig, Christian , Zhang, GuoQing (Sam
On 2025/5/8 18:56, Christian König wrote:
> On 5/8/25 10:12, Lazar, Lijo wrote:
>>
>> On 5/8/2025 10:39 AM, Samuel Zhang wrote:
>>> For virtual machine with vGPUs in SRIOV single device mode and XGMI
>>> is enabled, XGMI physical node ids may change when waking up from
>>> hiberation with differen
hanged() or just amdgpu_sriov_vf()?
Please advise. Thank you!
Regards
Sam
From: amd-gfx on behalf of Zhang,
GuoQing (Sam)
Date: Thursday, May 8, 2025 at 14:53
To: Chang, HaiJun , Koenig, Christian
, Christian König ,
amd-gfx@lists.freedesktop.org , Deucher,
Alexander
Cc: Zhao, Victor , Deng,
On 2025/5/8 17:27, Christian König wrote:
>
> On 5/8/25 07:09, Samuel Zhang wrote:
>> For virtual machine with vGPUs in SRIOV single device mode and XGMI
>> is enabled, XGMI physical node ids may change when waking up from
>> hiberation with different vGPU devices. So update XGMI info on resume.
>
On 2025/5/8 16:12, Lazar, Lijo wrote:
> On 5/8/2025 10:39 AM, Samuel Zhang wrote:
>> For virtual machine with vGPUs in SRIOV single device mode and XGMI
>> is enabled, XGMI physical node ids may change when waking up from
>> hiberation with different vGPU devices. So update XGMI info on resume.
>>
29, 2025 at 10:43
To: Koenig, Christian , Zhang, GuoQing (Sam)
, Christian König ,
amd-gfx@lists.freedesktop.org , Deucher,
Alexander
Cc: Zhao, Victor , Deng, Emily ,
Zhang, Owen(SRDC)
Subject: RE: [PATCH 6/6] drm/amdgpu: fix fence fallback timer expired error
[AMD Official Use Only - AMD
On 2025/5/7 20:56, Christian König wrote:
> On 5/7/25 14:49, Sam wrote:
>> On 2025/5/7 20:21, Christian König wrote:
>>> On 5/7/25 13:03, Sam wrote:
>>>> On 2025/5/7 18:03, Lazar, Lijo wrote:
>>>>> On 5/7/2025 11:52 AM, Zhang, GuoQing (Sam) wrote:
acceptable? If not, can you suggest a better approach? @Lazar,
Lijo<mailto:lijo.la...@amd.com> @Koenig,
Christian<mailto:christian.koe...@amd.com> Thank you!
Regards
Sam
From: Lazar, Lijo
Date: Tuesday, May 6, 2025 at 19:55
To: Zhang, GuoQing (Sam) , amd-gfx@lists.freedesktop
e environment to test
the changes. Should I remove them as well? @Koenig,
Christian<mailto:christian.koe...@amd.com>
- psp->fw_pri_mc_addr
- psp->fence_buf_mc_addr
- psp->km_ring.ring_mem_mc_addr
- driver_table->mc_address
- pm_status_table->mc_address
Thanks
Sam
From: Koenig,
From: Koenig, Christian
Date: Monday, April 28, 2025 at 19:30
To: Zhang, GuoQing (Sam) , Christian König
, amd-gfx@lists.freedesktop.org
, Deucher, Alexander
Cc: Zhao, Victor , Chang, HaiJun ,
Deng, Emily , Zhang, Owen(SRDC)
Subject: Re: [PATCH 4/6] drm/amdgpu: enable pdb0 for hibernation on SR
[AMD Official Use Only - AMD Internal Distribution Only]
Ping… @Koenig, Christian<mailto:christian.koe...@amd.com>
Thanks
Sam
From: amd-gfx on behalf of Zhang,
GuoQing (Sam)
Date: Wednesday, April 23, 2025 at 14:59
To: Christian König ,
amd-gfx@lists.freedesktop.org
Cc: Zhao,
[AMD Official Use Only - AMD Internal Distribution Only]
Ping… @Koenig, Christian<mailto:christian.koe...@amd.com>
Thanks
Sam
From: amd-gfx on behalf of Zhang,
GuoQing (Sam)
Date: Wednesday, April 23, 2025 at 15:25
To: Christian König ,
amd-gfx@lists.freedesktop.org
Cc: Zhao,
2
> To: Zhang, GuoQing (Sam) ,
> amd-gfx@lists.freedesktop.org
> Cc: Zhao, Victor , Chang, HaiJun ,
> Deng, Emily
> Subject: Re: [PATCH 4/6] drm/amdgpu: enable pdb0 for hibernation on SRIOV
> Am 14.04.25 um 12:46 schrieb Samuel Zhang:
> > When switching to new GPU index aft
at 21:54
To: Zhang, GuoQing (Sam) , amd-gfx@lists.freedesktop.org
Cc: Zhao, Victor , Chang, HaiJun ,
Deng, Emily
Subject: Re: [PATCH 6/6] drm/amdgpu: fix fence fallback timer expired error
Am 14.04.25 um 12:46 schrieb Samuel Zhang:
> IH is not working after switching a new gpu index for the f
[AMD Official Use Only - AMD Internal Distribution Only]
Ping…
Thanks
Sam
From: Zhang, GuoQing (Sam)
Date: Friday, April 18, 2025 at 14:26
To: Christian König ,
amd-gfx@lists.freedesktop.org
Cc: Zhao, Victor , Chang, HaiJun ,
Deng, Emily
Subject: Re: [PATCH 4/6] drm/amdgpu: enable pdb0 for
nge is to change to the default GPU address from FB aperture type to
pdb0 type in this centralized place so that I don’t need to change every
callsite of amdgpu_bo_create_reserved().
Could you suggest a better approach if this approach is not acceptable?
Thanks
Sam
From: Christian König
Date: Wednesday, April
[AMD Official Use Only - AMD Internal Distribution Only]
Ping…
Regards
Sam
From: Samuel Zhang
Date: Monday, April 14, 2025 at 18:47
To: amd-gfx@lists.freedesktop.org
Cc: Zhao, Victor , Chang, HaiJun ,
Deng, Emily , Zhang, GuoQing (Sam)
Subject: [PATCH 0/6] enable switching to new gpu index
To: amd-gfx@lists.freedesktop.org , Zhang,
GuoQing (Sam) , Kim, Jonathan
Subject: Re: [PATCH] drm/amdgpu: fix KFDMemoryTest.PtraceAccessInvisibleVram
fail on SRIOV
On 2024-08-07 04:36, Samuel Zhang wrote:
> Ptrace access VRAM bo will first try sdma access in
> amdgpu_ttm_access_memory_sdma(),
To: amd-gfx@lists.freedesktop.org
Cc: Zhang, GuoQing (Sam)
Subject: [PATCH] drm/amdgpu: fix KFDMemoryTest.PtraceAccessInvisibleVram fail
on SRIOV
Ptrace access VRAM bo will first try sdma access in
amdgpu_ttm_access_memory_sdma(), if fails, it will fallback to mmio
access.
Since ptrace only access 8 bytes a
eng, Kenneth
Date: Monday, April 29, 2024 at 16:15
To: Feng, Kenneth , amd-gfx@lists.freedesktop.org
, Zhang, GuoQing (Sam)
Cc: Zhang, Owen(SRDC) , Aldabagh, Maad
, Ma, Qing (Mark)
Subject: RE: [PATCH 2/2] drm/amd/amdgpu: use the default reset for ras recovery
[AMD Official Use Only - Gener
also needed when
we test mode2 reset using quark tool.
Thanks
Sam
From: Feng, Kenneth
Date: Monday, April 29, 2024 at 16:14
To: Feng, Kenneth , amd-gfx@lists.freedesktop.org
, Zhang, GuoQing (Sam)
Cc: Zhang, Owen(SRDC) , Aldabagh, Maad
, Ma, Qing (Mark)
Subject: RE: [PATCH 1/2] dr
31 matches
Mail list logo
