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

drm/amdkfd: Avoid thrashing of stack and heap 

Stack and heap pages tend to be shared by many small allocations.
Concurrent access by CPU and GPU is therefore likely, which can lead to
thrashing. Avoid this by setting the preferred location to system memory.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Felix Kuehling 2021-10-27 17:40:51 -04:00 committed by Alex Deucher
parent 297753a06a
commit 12fcf0a7da
1 changed files with 17 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
drivers/gpu/drm/amd/amdkfd/kfd_svm.c
View File

@ -2321,7 +2321,8 @@ svm_range_best_restore_location(struct svm_range *prange,
static int static int
svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr, svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr,
unsigned long *start, unsigned long *last) unsigned long *start, unsigned long *last,
bool *is_heap_stack)
{ {
struct vm_area_struct *vma; struct vm_area_struct *vma;
struct interval_tree_node *node; struct interval_tree_node *node;
@ -2332,6 +2333,12 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr,
pr_debug("VMA does not exist in address [0x%llx]\n", addr); pr_debug("VMA does not exist in address [0x%llx]\n", addr);
return -EFAULT; return -EFAULT;
} }
*is_heap_stack = (vma->vm_start <= vma->vm_mm->brk &&
vma->vm_end >= vma->vm_mm->start_brk) ||
(vma->vm_start <= vma->vm_mm->start_stack &&
vma->vm_end >= vma->vm_mm->start_stack);
start_limit = max(vma->vm_start >> PAGE_SHIFT, start_limit = max(vma->vm_start >> PAGE_SHIFT,
(unsigned long)ALIGN_DOWN(addr, 2UL << 8)); (unsigned long)ALIGN_DOWN(addr, 2UL << 8));
end_limit = min(vma->vm_end >> PAGE_SHIFT, end_limit = min(vma->vm_end >> PAGE_SHIFT,
@ -2361,9 +2368,9 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr,
*start = start_limit; *start = start_limit;
*last = end_limit - 1; *last = end_limit - 1;
pr_debug("vma start: 0x%lx start: 0x%lx vma end: 0x%lx last: 0x%lx\n", pr_debug("vma [0x%lx 0x%lx] range [0x%lx 0x%lx] is_heap_stack %d\n",
vma->vm_start >> PAGE_SHIFT, *start, vma->vm_start >> PAGE_SHIFT, vma->vm_end >> PAGE_SHIFT,
vma->vm_end >> PAGE_SHIFT, *last); *start, *last, *is_heap_stack);
return 0; return 0;
} }
@ -2428,11 +2435,13 @@ svm_range *svm_range_create_unregistered_range(struct amdgpu_device *adev,
struct svm_range *prange = NULL; struct svm_range *prange = NULL;
unsigned long start, last; unsigned long start, last;
uint32_t gpuid, gpuidx; uint32_t gpuid, gpuidx;
bool is_heap_stack;
uint64_t bo_s = 0; uint64_t bo_s = 0;
uint64_t bo_l = 0; uint64_t bo_l = 0;
int r; int r;
if (svm_range_get_range_boundaries(p, addr, &start, &last)) if (svm_range_get_range_boundaries(p, addr, &start, &last,
&is_heap_stack))
return NULL; return NULL;
r = svm_range_check_vm(p, start, last, &bo_s, &bo_l); r = svm_range_check_vm(p, start, last, &bo_s, &bo_l);
@ -2459,6 +2468,9 @@ svm_range *svm_range_create_unregistered_range(struct amdgpu_device *adev,
return NULL; return NULL;
} }
if (is_heap_stack)
prange->preferred_loc = KFD_IOCTL_SVM_LOCATION_SYSMEM;
svm_range_add_to_svms(prange); svm_range_add_to_svms(prange);
svm_range_add_notifier_locked(mm, prange); svm_range_add_notifier_locked(mm, prange);