[PATCH v3 13/19] 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

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.h         |  3 +++
 drivers/gpu/drm/xe/xe_vm_madvise.c | 15 +++++++++++-
 4 files changed, 63 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index 743bb1f7d39c..8b6546ebac72 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -791,6 +791,37 @@ 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 < 0)
+		return NULL;
+
+	if (fd == DRM_XE_PREFERRED_LOC_DEFAULT_DEVMEM_FD && tile)
+		return &tile->mem.vram.dpagemap;
+
+	/* 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 drm_exec exec;
 	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, IS_DGFX(vm->xe) && !!dpagemap)) {
+		/* 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 b36f70ab3d03..344349313001 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_range_clean_if_addr_within(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_range_clean_if_addr_within(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.h b/drivers/gpu/drm/xe/xe_vm.h
index edd6ffd7c3ac..340ac34936f4 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -222,6 +222,9 @@ int __xe_vm_userptr_needs_repin(struct xe_vm *vm);
 
 int xe_vm_userptr_check_repin(struct xe_vm *vm);
 
+bool xe_vma_has_preferred_mem_loc(struct xe_vma *vma,
+				  u32 *mem_region, u32 *devmem_fd);
+
 int xe_vm_rebind(struct xe_vm *vm, bool rebind_worker);
 struct dma_fence *xe_vma_rebind(struct xe_vm *vm, struct xe_vma *vma,
 				u8 tile_mask);
diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c
index 084719660401..1b31e41b3331 100644
--- a/drivers/gpu/drm/xe/xe_vm_madvise.c
+++ b/drivers/gpu/drm/xe/xe_vm_madvise.c
@@ -61,7 +61,20 @@ static int madvise_preferred_mem_loc(struct xe_device *xe, struct xe_vm *vm,
 				     struct xe_vma **vmas, int num_vmas,
 				     struct drm_xe_madvise_ops ops)
 {
-	/* Implementation pending */
+	int i;
+
+	xe_assert(vm->xe, ops.type == DRM_XE_VMA_ATTR_PREFERRED_LOC);
+
+	for (i = 0; i < num_vmas; i++) {
+		vmas[i]->attr.preferred_loc.devmem_fd = ops.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 =
+		//				ops.preferred_mem_loc.migration_policy;
+	}
+
 	return 0;
 }
 
-- 
2.34.1