[PATCH v4 13/20] drm/xe/madvise: Update migration policy based on preferred location

[Himal Prasad Ghimiray]

When the user sets the valid devmem_fd as a preferred location, GPU fault
will trigger migration to tile of device associated with devmem_fd.

If the user sets an invalid devmem_fd the preferred location is current
placement(smem) only.

v2(Matthew Brost)
- Default should be faulting tile
- remove devmem_fd used as region

v3 (Matthew Brost)
- Add migration_policy
- Fix return condition
- fix migrate condition

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.c        | 39 +++++++++++++++++++++++++++++-
 drivers/gpu/drm/xe/xe_svm.h        |  8 ++++++
 drivers/gpu/drm/xe/xe_vm_madvise.c | 19 ++++++++++++++-
 3 files changed, 64 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index 003aae9a0d82..8cbf6a6f1cf4 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -792,6 +792,37 @@ bool xe_svm_range_needs_migrate_to_vram(struct xe_svm_range *range, struct xe_vm
 	return true;
 }
 
+/**
+ * xe_vma_resolve_pagemap - Resolve the appropriate DRM pagemap for a VMA
+ * @vma: Pointer to the xe_vma structure containing memory attributes
+ * @tile: Pointer to the xe_tile structure used as fallback for VRAM mapping
+ *
+ * This function determines the correct DRM pagemap to use for a given VMA.
+ * It first checks if a valid devmem_fd is provided in the VMA's preferred
+ * location. If the devmem_fd is negative, it returns NULL, indicating no
+ * pagemap is available and smem to be used as preferred location.
+ * If the devmem_fd is equal to the default faulting
+ * GT identifier, it returns the VRAM pagemap associated with the tile.
+ *
+ * Future support for multi-device configurations may use drm_pagemap_from_fd()
+ * to resolve pagemaps from arbitrary file descriptors.
+ *
+ * Return: A pointer to the resolved drm_pagemap, or NULL if none is applicable.
+ */
+struct drm_pagemap *xe_vma_resolve_pagemap(struct xe_vma *vma, struct xe_tile *tile)
+{
+	s32 fd = (s32)vma->attr.preferred_loc.devmem_fd;
+
+	if (fd == DRM_XE_PREFERRED_LOC_DEFAULT_SYSTEM)
+		return NULL;
+
+	if (fd == DRM_XE_PREFERRED_LOC_DEFAULT_DEVICE)
+		return IS_DGFX(tile_to_xe(tile)) ? &tile->mem.vram.dpagemap : NULL;
+
+	/* TODO: Support multi-device with drm_pagemap_from_fd(fd) */
+	return NULL;
+}
+
 /**
  * xe_svm_handle_pagefault() - SVM handle page fault
  * @vm: The VM.
@@ -823,6 +854,7 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
 	};
 	struct xe_svm_range *range;
 	struct dma_fence *fence;
+	struct drm_pagemap *dpagemap;
 	struct xe_tile *tile = gt_to_tile(gt);
 	int migrate_try_count = ctx.devmem_only ? 3 : 1;
 	ktime_t end = 0;
@@ -852,8 +884,13 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
 
 	range_debug(range, "PAGE FAULT");
 
+	dpagemap = xe_vma_resolve_pagemap(vma, tile);
 	if (--migrate_try_count >= 0 &&
-	    xe_svm_range_needs_migrate_to_vram(range, vma, IS_DGFX(vm->xe))) {
+	    xe_svm_range_needs_migrate_to_vram(range, vma, !!dpagemap || ctx.devmem_only)) {
+		/* TODO : For multi-device dpagemap will be used to find the remote tile
+		 * and remote device. Will need to modify xe_svm_alloc_vram to use dpagemap
+		 * for future multi-device support.
+		 */
 		err = xe_svm_alloc_vram(vm, tile, range, &ctx);
 		ctx.timeslice_ms <<= 1;	/* Double timeslice if we have to retry */
 		if (err) {
diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h
index 4e5d42323679..900a5883951f 100644
--- a/drivers/gpu/drm/xe/xe_svm.h
+++ b/drivers/gpu/drm/xe/xe_svm.h
@@ -95,6 +95,8 @@ u8 xe_svm_ranges_zap_ptes_in_range(struct xe_vm *vm, u64 start, u64 end);
 
 void xe_svm_unmap_address_range(struct xe_vm *vm, u64 start, u64 end);
 
+struct drm_pagemap *xe_vma_resolve_pagemap(struct xe_vma *vma, struct xe_tile *tile);
+
 /**
  * xe_svm_range_has_dma_mapping() - SVM range has DMA mapping
  * @range: SVM range
@@ -320,6 +322,12 @@ void xe_svm_unmap_address_range(struct xe_vm *vm, u64 start, u64 end)
 {
 }
 
+static inline
+struct drm_pagemap *xe_vma_resolve_pagemap(struct xe_vma *vma, struct xe_tile *tile)
+{
+	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_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c
index 403337d79ea6..64352fbebd25 100644
--- a/drivers/gpu/drm/xe/xe_vm_madvise.c
+++ b/drivers/gpu/drm/xe/xe_vm_madvise.c
@@ -82,7 +82,19 @@ static void madvise_preferred_mem_loc(struct xe_device *xe, struct xe_vm *vm,
 				      struct xe_vma **vmas, int num_vmas,
 				      struct drm_xe_madvise *op)
 {
-	/* Implementation pending */
+	int i;
+
+	xe_assert(vm->xe, op->type == DRM_XE_VMA_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 =
+						op->preferred_mem_loc.migration_policy;
+	}
 }
 
 static void madvise_atomic(struct xe_device *xe, struct xe_vm *vm,
@@ -186,6 +198,11 @@ static int drm_xe_madvise_args_are_sane(struct xe_device *xe, const struct drm_x
 		/*TODO: Add valid pat check */
 		break;
 	case DRM_XE_VMA_ATTR_PREFERRED_LOC:
+		s32 fd = (s32)args->preferred_mem_loc.devmem_fd;
+
+		if (XE_IOCTL_DBG(xe, fd < DRM_XE_PREFERRED_LOC_DEFAULT_SYSTEM))
+			return -EINVAL;
+
 		if (XE_IOCTL_DBG(xe, args->preferred_mem_loc.migration_policy >
 				     DRM_XE_MIGRATE_ONLY_SYSTEM_PAGES))
 			return -EINVAL;
-- 
2.34.1