[PATCH v2 13/32] drm/xe/svm: Incase of atomic access ensure get_pages happens from vram

[Himal Prasad Ghimiray]

Ranges can be invalidated in between vram allocation and get_pages,
ensure the dma mapping is happening from vram only incase of atomic
access. Retry 3 times before calling out fault in case of concurrent
cpu/gpu access.

Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray at intel.com>
---
 drivers/gpu/drm/xe/xe_svm.c | 43 ++++++++++++++++++++++++-------------
 1 file changed, 28 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index f4ae3feaf9d3..7ec7ecd7eb1f 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -778,11 +778,13 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
 			IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR),
 		.check_pages_threshold = IS_DGFX(vm->xe) &&
 			IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR) ? SZ_64K : 0,
+		.vram_only = 0,
 	};
 	struct xe_svm_range *range;
 	struct drm_exec exec;
 	struct dma_fence *fence;
 	struct xe_tile *tile = gt_to_tile(gt);
+	int retry_count = 3;
 	ktime_t end = 0;
 	int err;
 
@@ -792,6 +794,7 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
 	xe_gt_stats_incr(gt, XE_GT_STATS_ID_SVM_PAGEFAULT_COUNT, 1);
 
 retry:
+	retry_count--;
 	/* Always process UNMAPs first so view SVM ranges is current */
 	err = xe_svm_garbage_collector(vm);
 	if (err)
@@ -807,30 +810,40 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
 
 	range_debug(range, "PAGE FAULT");
 
-	/* XXX: Add migration policy, for now migrate range once */
-	if (!range->skip_migrate &&
-	    xe_svm_range_needs_migrate_to_vram(range, vma, IS_DGFX(vm->xe))) {
-		range->skip_migrate = true;
-
+	if (xe_svm_range_needs_migrate_to_vram(range, vma, IS_DGFX(vm->xe))) {
 		err = xe_svm_alloc_vram(vm, tile, range, &ctx);
 		if (err) {
-			drm_dbg(&vm->xe->drm,
-				"VRAM allocation failed, falling back to "
-				"retrying fault, asid=%u, errno=%pe\n",
-				vm->usm.asid, ERR_PTR(err));
-			goto retry;
+			if (retry_count) {
+				drm_dbg(&vm->xe->drm,
+					"VRAM allocation failed, falling back to retrying fault, asid=%u, errno=%pe\n",
+					vm->usm.asid, ERR_PTR(err));
+				goto retry;
+			} else {
+				drm_err(&vm->xe->drm,
+					"VRAM allocation failed, retry count exceeded, asid=%u, errno=%pe\n",
+					vm->usm.asid, ERR_PTR(err));
+				return err;
+			}
 		}
+
 	}
 
+	if (atomic)
+		ctx.vram_only = 1;
+
 	range_debug(range, "GET PAGES");
 	err = xe_svm_range_get_pages(vm, range, &ctx);
 	/* Corner where CPU mappings have changed */
 	if (err == -EOPNOTSUPP || err == -EFAULT || err == -EPERM) {
-		drm_dbg(&vm->xe->drm,
-			"Get pages failed, falling back to retrying, asid=%u, gpusvm=%p, errno=%pe\n",
-			vm->usm.asid, &vm->svm.gpusvm, ERR_PTR(err));
-		range_debug(range, "PAGE FAULT - RETRY PAGES");
-		goto retry;
+		if (retry_count) {
+			drm_dbg(&vm->xe->drm, "Get pages failed, falling back to retrying, asid=%u, gpusvm=%p, errno=%pe\n",
+				vm->usm.asid, &vm->svm.gpusvm, ERR_PTR(err));
+			range_debug(range, "PAGE FAULT - RETRY PAGES");
+			goto retry;
+		} else {
+			drm_err(&vm->xe->drm, "Get pages failed,, retry count exceeded, asid=%u,, errno=%pe\n",
+				vm->usm.asid, ERR_PTR(err));
+		}
 	}
 	if (err) {
 		range_debug(range, "PAGE FAULT - FAIL PAGE COLLECT");
-- 
2.34.1