Avoid unnecessary XGMI hight pstate trigger when mapping none-vram memory for
peer device
Change-Id: I1881deff3da19f1f4b58d5765db03a590092a5b2
Signed-off-by: shaoyunl
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 9 +
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 3 ++-
2 files changed, 11
Avoid unnecessary XGMI hight pstate trigger when mapping none-vram memory for
peer device
Change-Id: I1881deff3da19f1f4b58d5765db03a590092a5b2
Signed-off-by: shaoyunl
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 11 +++
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 3 ++-
2 files changed,
Avoid unnecessary XGMI hight pstate trigger when mapping none-vram memory for
peer device
Change-Id: I1881deff3da19f1f4b58d5765db03a590092a5b2
Signed-off-by: shaoyunl
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 13 +
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 3 ++-
2 files change
Avoid unnecessary XGMI hight pstate trigger when mapping none-vram memory for
peer device
Change-Id: I1881deff3da19f1f4b58d5765db03a590092a5b2
Signed-off-by: shaoyunl
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 13 +
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 3 ++-
2 files change
Avoid unnecessary XGMI hight pstate trigger when mapping none-vram memory for
peer device
Change-Id: I1881deff3da19f1f4b58d5765db03a590092a5b2
Signed-off-by: shaoyunl
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 13 +
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 3 ++-
2 files change
Avoid unnecessary XGMI hight pstate trigger when mapping none-vram memory for
peer device
Change-Id: I1881deff3da19f1f4b58d5765db03a590092a5b2
Signed-off-by: shaoyunl
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 14 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 3 ++-
2 files chang
Avoid unnecessary XGMI hight pstate trigger when mapping none-vram memory for
peer device
Change-Id: I1881deff3da19f1f4b58d5765db03a590092a5b2
Signed-off-by: shaoyunl
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 11 +++
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 3 ++-
2 files changed,
Am 26.03.19 um 19:54 schrieb Liu, Shaoyun:
Avoid unnecessary XGMI hight pstate trigger when mapping none-vram memory for
peer device
Change-Id: I1881deff3da19f1f4b58d5765db03a590092a5b2
Signed-off-by: shaoyunl
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 9 +
drivers/gpu/drm/amd/am
On 2019-03-26 2:54 p.m., Liu, Shaoyun wrote:
> Avoid unnecessary XGMI hight pstate trigger when mapping none-vram memory for
> peer device
>
> Change-Id: I1881deff3da19f1f4b58d5765db03a590092a5b2
> Signed-off-by: shaoyunl
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 9 +
> drivers
Am 26.03.19 um 21:35 schrieb Liu, Shaoyun:
Avoid unnecessary XGMI hight pstate trigger when mapping none-vram memory for
peer device
Change-Id: I1881deff3da19f1f4b58d5765db03a590092a5b2
Signed-off-by: shaoyunl
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 11 +++
drivers/gpu/drm/amd
The next in struct amdgpu_vm_bo_base is not a list_head, I'm not
sure whether we can use list_for_each_entry here.
Regards
shaoyun.liu
On 2019-03-27 3:41 a.m., Christian König wrote:
> Am 26.03.19 um 21:35 schrieb Liu, Shaoyun:
>> Avoid unnecessary XGMI hight pstate trigger when mapping non
Ah, of course. In this case feel free to go ahead.
BTW: What's the size of the structure now?
Christian.
Am 27.03.2019 16:22 schrieb "Liu, Shaoyun" :
The next in struct amdgpu_vm_bo_base is not a list_head, I'm not
sure whether we can use list_for_each_entry here.
Regards
shaoyun.liu
On 2
you mean struct amdgpu_vm_bo_base ? It only has few pointer and a list_head ,
should be pretty small .
struct amdgpu_vm_bo_base {
/* constant after initialization */
struct amdgpu_vm*vm;
struct amdgpu_bo*bo;
/* protected by bo being reserved */
struct amdgp
Yeah, that one is intentionally very small because it is used so often.
When it grows over the next power of two by this change we need to figure out a
different approach.
Christian.
Am 27.03.2019 16:34 schrieb "Liu, Shaoyun" :
you mean struct amdgpu_vm_bo_base ? It only has few pointer and
bool is_xgmi is added in bo_va structure , this change won't increase the size
of struct amdgpu_vm_bo_base. Anyway , can I said it's reviewed by you now?
shaoyun.liu
On 2019-03-27 11:39 a.m., Koenig, Christian wrote:
Yeah, that one is intentionally very small because it is used so often.
Whe
Yeah, feel free to add my RB.
Christian.
Am 27.03.2019 16:43 schrieb "Liu, Shaoyun" :
bool is_xgmi is added in bo_va structure , this change won't increase the size
of struct amdgpu_vm_bo_base. Anyway , can I said it's reviewed by you now?
shaoyun.liu
On 2019-03-27 11:39 a.m., Koenig, Chri
On 2019-03-26 4:35 p.m., Liu, Shaoyun wrote:
> Avoid unnecessary XGMI hight pstate trigger when mapping none-vram memory for
> peer device
>
> Change-Id: I1881deff3da19f1f4b58d5765db03a590092a5b2
> Signed-off-by: shaoyunl
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 11 +++
> driv
Even the preferred_domains been changed for bo that original is none xgmi here
, it doesn't means driver must change the XGMI status for the bo_va. From
current design, only the bo later been added to the compute VM (through
bo_add) will be enable the XGMI mapping. Without that call , the XGMI
On 2019-03-28 1:55 p.m., Liu, Shaoyun wrote:
> Avoid unnecessary XGMI hight pstate trigger when mapping none-vram memory for
> peer device
>
> Change-Id: I1881deff3da19f1f4b58d5765db03a590092a5b2
> Signed-off-by: shaoyunl
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 13 +
> dr
I think we only care about the context device (adev) and the real device
this bo been allocated(robj->tbo.bdev). The bo_va or base don't have
the device pointer directly, it have a pointer to bo which should be
the same as robj here. We can move the same_hive check out of the
loop .
R
On 2019-03-28 3:47 p.m., Liu, Shaoyun wrote:
> I think we only care about the context device (adev) and the real device
> this bo been allocated(robj->tbo.bdev). The bo_va or base don't have
> the device pointer directly, it have a pointer to bo which should be
> the same as robj here. We ca
On 2019-03-28 4:38 p.m., Liu, Shaoyun wrote:
> Avoid unnecessary XGMI hight pstate trigger when mapping none-vram memory for
> peer device
>
> Change-Id: I1881deff3da19f1f4b58d5765db03a590092a5b2
> Signed-off-by: shaoyunl
This patch is Reviewed-by: Felix Kuehling
Please also give Christian a c
Am 28.03.19 um 18:55 schrieb Liu, Shaoyun:
Avoid unnecessary XGMI hight pstate trigger when mapping none-vram memory for
peer device
Change-Id: I1881deff3da19f1f4b58d5765db03a590092a5b2
Signed-off-by: shaoyunl
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 13 +
drivers/gpu/drm/a
Am 28.03.19 um 21:39 schrieb Kuehling, Felix:
On 2019-03-28 4:38 p.m., Liu, Shaoyun wrote:
Avoid unnecessary XGMI hight pstate trigger when mapping none-vram memory for
peer device
Change-Id: I1881deff3da19f1f4b58d5765db03a590092a5b2
Signed-off-by: shaoyunl
This patch is Reviewed-by: Felix K
24 matches
Mail list logo