diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdkfd/kfd_svm.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 68 |
1 files changed, 47 insertions, 21 deletions
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 9d72411c3379..79ea138897fc 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1144,30 +1144,48 @@ static int svm_range_split_tail(struct svm_range *prange, uint64_t new_last, struct list_head *insert_list, struct list_head *remap_list) { + unsigned long last_align_down = ALIGN_DOWN(prange->last, 512); + unsigned long start_align = ALIGN(prange->start, 512); + bool huge_page_mapping = last_align_down > start_align; struct svm_range *tail = NULL; - int r = svm_range_split(prange, prange->start, new_last, &tail); + int r; - if (!r) { - list_add(&tail->list, insert_list); - if (!IS_ALIGNED(new_last + 1, 1UL << prange->granularity)) - list_add(&tail->update_list, remap_list); - } - return r; + r = svm_range_split(prange, prange->start, new_last, &tail); + + if (r) + return r; + + list_add(&tail->list, insert_list); + + if (huge_page_mapping && tail->start > start_align && + tail->start < last_align_down && (!IS_ALIGNED(tail->start, 512))) + list_add(&tail->update_list, remap_list); + + return 0; } static int svm_range_split_head(struct svm_range *prange, uint64_t new_start, struct list_head *insert_list, struct list_head *remap_list) { + unsigned long last_align_down = ALIGN_DOWN(prange->last, 512); + unsigned long start_align = ALIGN(prange->start, 512); + bool huge_page_mapping = last_align_down > start_align; struct svm_range *head = NULL; - int r = svm_range_split(prange, new_start, prange->last, &head); + int r; - if (!r) { - list_add(&head->list, insert_list); - if (!IS_ALIGNED(new_start, 1UL << prange->granularity)) - list_add(&head->update_list, remap_list); - } - return r; + r = svm_range_split(prange, new_start, prange->last, &head); + + if (r) + return r; + + list_add(&head->list, insert_list); + + if (huge_page_mapping && head->last + 1 > start_align && + head->last + 1 < last_align_down && (!IS_ALIGNED(head->last, 512))) + list_add(&head->update_list, remap_list); + + return 0; } static void @@ -1698,7 +1716,7 @@ static int svm_range_validate_and_map(struct mm_struct *mm, start = map_start << PAGE_SHIFT; end = (map_last + 1) << PAGE_SHIFT; for (addr = start; !r && addr < end; ) { - struct hmm_range *hmm_range = NULL; + struct amdgpu_hmm_range *range = NULL; unsigned long map_start_vma; unsigned long map_last_vma; struct vm_area_struct *vma; @@ -1737,9 +1755,12 @@ static int svm_range_validate_and_map(struct mm_struct *mm, } WRITE_ONCE(p->svms.faulting_task, current); - r = amdgpu_hmm_range_get_pages(&prange->notifier, addr, npages, - readonly, owner, - &hmm_range); + range = amdgpu_hmm_range_alloc(NULL); + if (likely(range)) + r = amdgpu_hmm_range_get_pages(&prange->notifier, addr, npages, + readonly, owner, range); + else + r = -ENOMEM; WRITE_ONCE(p->svms.faulting_task, NULL); if (r) pr_debug("failed %d to get svm range pages\n", r); @@ -1750,7 +1771,7 @@ static int svm_range_validate_and_map(struct mm_struct *mm, if (!r) { offset = (addr >> PAGE_SHIFT) - prange->start; r = svm_range_dma_map(prange, ctx->bitmap, offset, npages, - hmm_range->hmm_pfns); + range->hmm_range.hmm_pfns); if (r) pr_debug("failed %d to dma map range\n", r); } @@ -1758,14 +1779,17 @@ static int svm_range_validate_and_map(struct mm_struct *mm, svm_range_lock(prange); /* Free backing memory of hmm_range if it was initialized - * Overrride return value to TRY AGAIN only if prior returns + * Override return value to TRY AGAIN only if prior returns * were successful */ - if (hmm_range && amdgpu_hmm_range_get_pages_done(hmm_range) && !r) { + if (range && !amdgpu_hmm_range_valid(range) && !r) { pr_debug("hmm update the range, need validate again\n"); r = -EAGAIN; } + /* Free the hmm range */ + amdgpu_hmm_range_free(range); + if (!r && !list_empty(&prange->child_list)) { pr_debug("range split by unmap in parallel, validate again\n"); r = -EAGAIN; @@ -3687,6 +3711,8 @@ svm_range_set_attr(struct kfd_process *p, struct mm_struct *mm, svm_range_apply_attrs(p, prange, nattr, attrs, &update_mapping); /* TODO: unmap ranges from GPU that lost access */ } + update_mapping |= !p->xnack_enabled && !list_empty(&remap_list); + list_for_each_entry_safe(prange, next, &remove_list, update_list) { pr_debug("unlink old 0x%p prange 0x%p [0x%lx 0x%lx]\n", prange->svms, prange, prange->start, |