Re: [PATCH v2 2/2] drm/amd/pm: Update pci link speed and speed format

2023-08-12 Thread Lazar, Lijo
On 8/12/2023 4:03 PM, Asad Kamal wrote: 1) Update pcie link speed for smu v13_0_6 from correct register 2) Populate gpu metric table with pcie link speed rather than gen for smu v13_0_0, smu v13_0_6 & smu v13_0_7 v2: Update ESM register address Used macro to convert pcie gen to speed Si

Re: [PATCH 0/5] Add work pool to reset domain

2023-08-12 Thread Lazar, Lijo
On 8/12/2023 1:53 PM, Christian König wrote: Am 11.08.23 um 08:02 schrieb Lijo Lazar: Presently, there are multiple clients of reset like RAS, job timeout, KFD hang detection and debug method. Instead of each client maintaining a work item, reset work pool is moved to reset domain. When a cl

Re: [PATCH v3] drm/amdgpu: skip xcp drm device allocation when out of drm resource

2023-08-12 Thread Lazar, Lijo
On 8/12/2023 6:14 PM, James Zhu wrote: On 2023-08-11 21:39, Lazar, Lijo wrote: [AMD Official Use Only - General] A dynamic partition switch could happen later.  The switch could still be successful in terms of hardware, [JZ] Only ignore render node assignment, and remove visibility in us

[PATCH] drm/amdgpu: Replace ternary operator with min() in 'amdgpu_iomem_write'

2023-08-12 Thread Srinivasan Shanmugam
Fixes the following coccicheck: drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c:2482:16-17: WARNING opportunity for min() min() macro is defined in include/linux/minmax.h. It avoids multiple evaluations of the arguments when non-constant and performs strict type-checking. Cc: Guchun Chen Cc: Christian

[PATCH] drm/amdgpu: Replace ternary operator with min() in 'amdgpu_iomem_read'

2023-08-12 Thread Srinivasan Shanmugam
Fixes the following coccicheck: drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c:2427:16-17: WARNING opportunity for min() min() macro is defined in include/linux/minmax.h. It avoids multiple evaluations of the arguments when non-constant and performs strict type-checking. Cc: Guchun Chen Cc: Christian

Re: [PATCH v3] drm/amdgpu: skip xcp drm device allocation when out of drm resource

2023-08-12 Thread James Zhu
On 2023-08-11 21:39, Lazar, Lijo wrote: [AMD Official Use Only - General] A dynamic partition switch could happen later.  The switch could still be successful in terms of hardware, [JZ] Only ignore render node assignment, and remove visibility in user space, xcp continues to be generated as

[PATCH v2 1/2] drm/amd/pm: Update pci link width format & correct address for pcie registers

2023-08-12 Thread Asad Kamal
1)Update addresses of PCIE link width registers for smu v13.0.6 2)Update PCIE link width format used to populate gpu metrics table for smu v13.0.6 v2: Removed ESM register update Signed-off-by: Asad Kamal --- drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 10 -- 1 file changed,

[PATCH v2 2/2] drm/amd/pm: Update pci link speed and speed format

2023-08-12 Thread Asad Kamal
1) Update pcie link speed for smu v13_0_6 from correct register 2) Populate gpu metric table with pcie link speed rather than gen for smu v13_0_0, smu v13_0_6 & smu v13_0_7 v2: Update ESM register address Used macro to convert pcie gen to speed Signed-off-by: Asad Kamal --- drivers/gpu/drm/

Re: [PATCH 0/5] Add work pool to reset domain

2023-08-12 Thread Christian König
Am 11.08.23 um 08:02 schrieb Lijo Lazar: Presently, there are multiple clients of reset like RAS, job timeout, KFD hang detection and debug method. Instead of each client maintaining a work item, reset work pool is moved to reset domain. When a client makes a recovery request, a work item is all