[PATCH v5 18/23] drm/xe/madvise: Skip vma invalidation if mem attr are unchanged

[Himal Prasad Ghimiray]

If a VMA within the madvise input range already has the same memory
attribute as the one requested by the user, skip PTE zapping for that
VMA to avoid unnecessary invalidation.

v2 (Matthew Brost)
- fix skip_invalidation for new attributes
- s/u32/bool
- Remove unnecessary assignment  for kzalloc'ed

Suggested-by: Matthew Brost <matthew.brost at intel.com>
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray at intel.com>
---
 drivers/gpu/drm/xe/xe_vm_madvise.c | 52 +++++++++++++++++++++---------
 drivers/gpu/drm/xe/xe_vm_types.h   |  6 ++++
 2 files changed, 42 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c
index 727833780b4b..fbb6aa8a7a5e 100644
--- a/drivers/gpu/drm/xe/xe_vm_madvise.c
+++ b/drivers/gpu/drm/xe/xe_vm_madvise.c
@@ -84,13 +84,19 @@ static void madvise_preferred_mem_loc(struct xe_device *xe, struct xe_vm *vm,
 	xe_assert(vm->xe, op->type == DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC);
 
 	for (i = 0; i < num_vmas; i++) {
-		vmas[i]->attr.preferred_loc.devmem_fd = op->preferred_mem_loc.devmem_fd;
-
-		/* Till multi-device support is not added migration_policy
-		 * is of no use and can be ignored.
-		 */
-		vmas[i]->attr.preferred_loc.migration_policy =
+		if (vmas[i]->attr.preferred_loc.devmem_fd == op->preferred_mem_loc.devmem_fd &&
+		    vmas[i]->attr.preferred_loc.migration_policy ==
+		    op->preferred_mem_loc.migration_policy) {
+			vmas[i]->skip_invalidation = true;
+		} else {
+			vmas[i]->skip_invalidation = false;
+			vmas[i]->attr.preferred_loc.devmem_fd = op->preferred_mem_loc.devmem_fd;
+			/* Till multi-device support is not added migration_policy
+			 * is of no use and can be ignored.
+			 */
+			vmas[i]->attr.preferred_loc.migration_policy =
 						op->preferred_mem_loc.migration_policy;
+		}
 	}
 }
 
@@ -105,7 +111,12 @@ static void madvise_atomic(struct xe_device *xe, struct xe_vm *vm,
 	xe_assert(vm->xe, op->atomic.val <= DRM_XE_ATOMIC_CPU);
 
 	for (i = 0; i < num_vmas; i++) {
-		vmas[i]->attr.atomic_access = op->atomic.val;
+		if (vmas[i]->attr.atomic_access == op->atomic.val) {
+			vmas[i]->skip_invalidation = true;
+		} else {
+			vmas[i]->skip_invalidation = false;
+			vmas[i]->attr.atomic_access = op->atomic.val;
+		}
 
 		bo = xe_vma_bo(vmas[i]);
 		if (!bo)
@@ -130,9 +141,14 @@ static void madvise_pat_index(struct xe_device *xe, struct xe_vm *vm,
 
 	xe_assert(vm->xe, op->type == DRM_XE_MEM_RANGE_ATTR_PAT);
 
-	for (i = 0; i < num_vmas; i++)
-		vmas[i]->attr.pat_index = op->pat_index.val;
-
+	for (i = 0; i < num_vmas; i++) {
+		if (vmas[i]->attr.pat_index == op->pat_index.val) {
+			vmas[i]->skip_invalidation = true;
+		} else {
+			vmas[i]->skip_invalidation = false;
+			vmas[i]->attr.pat_index = op->pat_index.val;
+		}
+	}
 }
 
 typedef void (*madvise_func)(struct xe_device *xe, struct xe_vm *vm,
@@ -158,17 +174,20 @@ static u8 xe_zap_ptes_in_madvise_range(struct xe_vm *vm, u64 start, u64 end)
 				  false, MAX_SCHEDULE_TIMEOUT) <= 0)
 		XE_WARN_ON(1);
 
-	tile_mask = xe_svm_ranges_zap_ptes_in_range(vm, start, end);
-
 	drm_gpuvm_for_each_va_range(gpuva, &vm->gpuvm, start, end) {
 		struct xe_vma *vma = gpuva_to_vma(gpuva);
 
-		if (xe_vma_is_cpu_addr_mirror(vma))
+		if (vma->skip_invalidation)
 			continue;
 
-		for_each_tile(tile, vm->xe, id) {
-			if (xe_pt_zap_ptes(tile, vma)) {
-				tile_mask |= BIT(id);
+		if (xe_vma_is_cpu_addr_mirror(vma)) {
+			tile_mask |= xe_svm_ranges_zap_ptes_in_range(vm,
+								      xe_vma_start(vma),
+								      xe_vma_end(vma));
+		} else {
+			for_each_tile(tile, vm->xe, id) {
+				if (xe_pt_zap_ptes(tile, vma)) {
+					tile_mask |= BIT(id);
 
 				/*
 				 * WRITE_ONCE pairs with READ_ONCE
@@ -176,6 +195,7 @@ static u8 xe_zap_ptes_in_madvise_range(struct xe_vm *vm, u64 start, u64 end)
 				 */
 				WRITE_ONCE(vma->tile_invalidated,
 					   vma->tile_invalidated | BIT(id));
+				}
 			}
 		}
 	}
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index cd94d8b5819d..81d92d886578 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -157,6 +157,12 @@ struct xe_vma {
 	/** @tile_staged: bind is staged for this VMA */
 	u8 tile_staged;
 
+	/**
+	 * @skip_invalidation: Used in madvise to avoid invalidation
+	 * if mem attributes doesn't change
+	 */
+	bool skip_invalidation;
+
 	/**
 	 * @ufence: The user fence that was provided with MAP.
 	 * Needs to be signalled before UNMAP can be processed.
-- 
2.34.1