drm/amdkfd: Fix BO offset for multi-VMA page migration

From Xiaogang Chen
b61b21bcbb8a379269de7d2e3e9ceb42e5368ec4 in linux-6.1.y/6.1.23
b4ee9606378bb9520c94d8b96f0305c3696f5c29 in mainline linux

diff --git a/sys/dev/pci/drm/amd/amdkfd/kfd_migrate.c b/sys/dev/pci/drm/amd/amdkfd/kfd_migrate.c
index 22b077a..fad500d 100644 (file)
--- a/sys/dev/pci/drm/amd/amdkfd/kfd_migrate.c
+++ b/sys/dev/pci/drm/amd/amdkfd/kfd_migrate.c
@@ -295,7 +295,7 @@ static unsigned long svm_migrate_unsuccessful_pages(struct migrate_vma *migrate)
 static int
 svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
                         struct migrate_vma *migrate, struct dma_fence **mfence,
-                        dma_addr_t *scratch)
+                        dma_addr_t *scratch, uint64_t ttm_res_offset)
 {
        uint64_t npages = migrate->npages;
        struct device *dev = adev->dev;
@@ -305,8 +305,8 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
        uint64_t i, j;
        int r;
 
-       pr_debug("svms 0x%p [0x%lx 0x%lx]\n", prange->svms, prange->start,
-                prange->last);
+       pr_debug("svms 0x%p [0x%lx 0x%lx 0x%llx]\n", prange->svms, prange->start,
+                prange->last, ttm_res_offset);
 
        src = scratch;
        dst = (uint64_t *)(scratch + npages);
@@ -317,7 +317,7 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
                goto out;
        }
 
-       amdgpu_res_first(prange->ttm_res, prange->offset << PAGE_SHIFT,
+       amdgpu_res_first(prange->ttm_res, ttm_res_offset,
                         npages << PAGE_SHIFT, &cursor);
        for (i = j = 0; i < npages; i++) {
                struct page *spage;
@@ -404,7 +404,7 @@ out:
 static long
 svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
                        struct vm_area_struct *vma, uint64_t start,
-                       uint64_t end, uint32_t trigger)
+                       uint64_t end, uint32_t trigger, uint64_t ttm_res_offset)
 {
        struct kfd_process *p = container_of(prange->svms, struct kfd_process, svms);
        uint64_t npages = (end - start) >> PAGE_SHIFT;
@@ -457,7 +457,7 @@ svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
        else
                pr_debug("0x%lx pages migrated\n", cpages);
 
-       r = svm_migrate_copy_to_vram(adev, prange, &migrate, &mfence, scratch);
+       r = svm_migrate_copy_to_vram(adev, prange, &migrate, &mfence, scratch, ttm_res_offset);
        migrate_vma_pages(&migrate);
 
        pr_debug("successful/cpages/npages 0x%lx/0x%lx/0x%lx\n",
@@ -505,6 +505,7 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
        unsigned long addr, start, end;
        struct vm_area_struct *vma;
        struct amdgpu_device *adev;
+       uint64_t ttm_res_offset;
        unsigned long cpages = 0;
        long r = 0;
 
@@ -525,6 +526,7 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
 
        start = prange->start << PAGE_SHIFT;
        end = (prange->last + 1) << PAGE_SHIFT;
+       ttm_res_offset = prange->offset << PAGE_SHIFT;
 
        for (addr = start; addr < end;) {
                unsigned long next;
@@ -534,13 +536,14 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
                        break;
 
                next = min(vma->vm_end, end);
-               r = svm_migrate_vma_to_vram(adev, prange, vma, addr, next, trigger);
+               r = svm_migrate_vma_to_vram(adev, prange, vma, addr, next, trigger, ttm_res_offset);
                if (r < 0) {
                        pr_debug("failed %ld to migrate\n", r);
                        break;
                } else {
                        cpages += r;
                }
+               ttm_res_offset += next - addr;
                addr = next;
        }