[PATCH v4 16/20] drm/xe/svm: Consult madvise preferred location in prefetch

[Himal Prasad Ghimiray]

When prefetch region is DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC, prefetch svm
ranges to preferred location provided by madvise.

v2 (Matthew Brost)
- Fix region, devmem_fd usages
- consult madvise is applicable for other vma's too.

v3
- Fix atomic handling

Cc: Matthew Brost <matthew.brost at intel.com>
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray at intel.com>
---
 drivers/gpu/drm/xe/xe_svm.h  |  1 -
 drivers/gpu/drm/xe/xe_tile.h | 18 ++++++++++++++++++
 drivers/gpu/drm/xe/xe_vm.c   | 26 ++++++++++++++++++--------
 3 files changed, 36 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h
index 900a5883951f..1658e28f3773 100644
--- a/drivers/gpu/drm/xe/xe_svm.h
+++ b/drivers/gpu/drm/xe/xe_svm.h
@@ -327,7 +327,6 @@ struct drm_pagemap *xe_vma_resolve_pagemap(struct xe_vma *vma, struct xe_tile *t
 {
 	return NULL;
 }
-
 #define xe_svm_assert_in_notifier(...) do {} while (0)
 #define xe_svm_range_has_dma_mapping(...) false
 
diff --git a/drivers/gpu/drm/xe/xe_tile.h b/drivers/gpu/drm/xe/xe_tile.h
index eb939316d55b..142ed5cf654b 100644
--- a/drivers/gpu/drm/xe/xe_tile.h
+++ b/drivers/gpu/drm/xe/xe_tile.h
@@ -10,6 +10,24 @@
 
 struct xe_tile;
 
+#if IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR)
+/**
+ * xe_tile_from_dpagemap - Find xe_tile from drm_pagemap
+ * @dpagemap: pointer to struct drm_pagemap
+ *
+ * Return: Pointer to xe_tile
+ */
+static inline struct xe_tile *xe_tile_from_dpagemap(struct drm_pagemap *dpagemap)
+{
+	return container_of(dpagemap, struct xe_tile, mem.vram.dpagemap);
+}
+
+#else
+static inline  struct xe_tile *xe_tile_from_dpagemap(struct drm_pagemap *dpagemap)
+{
+	return NULL;
+}
+#endif
 int xe_tile_init_early(struct xe_tile *tile, struct xe_device *xe, u8 id);
 int xe_tile_init_noalloc(struct xe_tile *tile);
 int xe_tile_init(struct xe_tile *tile);
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 6dd1f868942d..0dd9f9e11030 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -38,6 +38,7 @@
 #include "xe_res_cursor.h"
 #include "xe_svm.h"
 #include "xe_sync.h"
+#include "xe_tile.h"
 #include "xe_trace_bo.h"
 #include "xe_wa.h"
 #include "xe_hmm.h"
@@ -2907,15 +2908,24 @@ static int prefetch_ranges(struct xe_vm *vm, struct xe_vma_op *op)
 	int err = 0;
 
 	struct xe_svm_range *svm_range;
+	struct drm_pagemap *dpagemap;
 	struct drm_gpusvm_ctx ctx = {};
-	struct xe_tile *tile;
+	struct xe_tile *tile = NULL;
 	unsigned long i;
 	u32 region;
 
 	if (!xe_vma_is_cpu_addr_mirror(vma))
 		return 0;
 
-	region = op->prefetch_range.region;
+	if (op->prefetch_range.region == DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC) {
+		dpagemap = xe_vma_resolve_pagemap(vma, xe_device_get_root_tile(vm->xe));
+		if (dpagemap)
+			tile = xe_tile_from_dpagemap(dpagemap);
+	} else {
+		region = op->prefetch_range.region;
+		if (region)
+			tile = &vm->xe->tiles[region_to_mem_type[region] - XE_PL_VRAM0];
+	}
 
 	ctx.read_only = xe_vma_read_only(vma);
 	ctx.devmem_possible = devmem_possible;
@@ -2923,11 +2933,10 @@ static int prefetch_ranges(struct xe_vm *vm, struct xe_vma_op *op)
 
 	/* TODO: Threading the migration */
 	xa_for_each(&op->prefetch_range.range, i, svm_range) {
-		if (!region)
+		if (!tile)
 			xe_svm_range_migrate_to_smem(vm, svm_range);
 
-		if (xe_svm_range_needs_migrate_to_vram(svm_range, vma, region)) {
-			tile = &vm->xe->tiles[region_to_mem_type[region] - XE_PL_VRAM0];
+		if (xe_svm_range_needs_migrate_to_vram(svm_range, vma, !!tile)) {
 			err = xe_svm_alloc_vram(vm, tile, svm_range, &ctx);
 			if (err) {
 				drm_dbg(&vm->xe->drm, "VRAM allocation failed, retry from userspace, asid=%u, gpusvm=%p, errno=%pe\n",
@@ -2995,7 +3004,8 @@ static int op_lock_and_prep(struct drm_exec *exec, struct xe_vm *vm,
 		else
 			region = op->prefetch.region;
 
-		xe_assert(vm->xe, region <= ARRAY_SIZE(region_to_mem_type));
+		xe_assert(vm->xe, region == DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC ||
+			  region <= ARRAY_SIZE(region_to_mem_type));
 
 		err = vma_lock_and_validate(exec,
 					    gpuva_to_vma(op->base.prefetch.va),
@@ -3413,8 +3423,8 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe, struct xe_vm *vm,
 				 op == DRM_XE_VM_BIND_OP_PREFETCH) ||
 		    XE_IOCTL_DBG(xe, prefetch_region &&
 				 op != DRM_XE_VM_BIND_OP_PREFETCH) ||
-		    XE_IOCTL_DBG(xe, !(BIT(prefetch_region) &
-				       xe->info.mem_region_mask)) ||
+		    XE_IOCTL_DBG(xe,  (prefetch_region != DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC &&
+				       !(BIT(prefetch_region) & xe->info.mem_region_mask))) ||
 		    XE_IOCTL_DBG(xe, obj &&
 				 op == DRM_XE_VM_BIND_OP_UNMAP)) {
 			err = -EINVAL;
-- 
2.34.1