UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

drm/amdgpu: Raise KFD unpinned system memory limit 

Allow KFD applications to use more unpinned system memory through
HMM.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Felix Kuehling 2019-11-25 16:25:35 -05:00 committed by Alex Deucher
parent 79c4ac0d75
commit b72ff1909c
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
View File

@ -85,7 +85,7 @@ static bool check_if_add_bo_to_vm(struct amdgpu_vm *avm,
}
/* Set memory usage limits. Current, limits are
* System (TTM + userptr) memory - 3/4th System RAM
* System (TTM + userptr) memory - 15/16th System RAM
* TTM memory - 3/8th System RAM
*/
void amdgpu_amdkfd_gpuvm_init_mem_limits(void)
@ -98,7 +98,7 @@ void amdgpu_amdkfd_gpuvm_init_mem_limits(void)
mem *= si.mem_unit;
spin_lock_init(&kfd_mem_limit.mem_limit_lock);
kfd_mem_limit.max_system_mem_limit = (mem >> 1) + (mem >> 2);
kfd_mem_limit.max_system_mem_limit = mem - (mem >> 4);
kfd_mem_limit.max_ttm_mem_limit = (mem >> 1) - (mem >> 3);
pr_debug("Kernel memory limit %lluM, TTM limit %lluM\n",
(kfd_mem_limit.max_system_mem_limit >> 20),