drm/xe: Add GPUSVM device memory copy vfunc functions

Add GPUSVM device memory copy vfunc functions and connect to migration
layer. Used for device memory migration.

v2:
 - Allow NULL device pages in xe_svm_copy
 - Use new drm_gpusvm_devmem_ops
v3:
 - Prefix defines with XE_ (Thomas)
 - Change copy chunk size to 8M
 - Add a bunch of comments to xe_svm_copy to clarify behavior (Thomas)
 - Better commit message (Thomas)
v5:
 - s/xe_mem_region/xe_vram_region (Rebase)

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-25-matthew.brost@intel.com

drivers/gpu/drm/xe/xe_svm.c

@@ -4,6 +4,7 @@
  */
 
 #include "xe_gt_tlb_invalidation.h"
+#include "xe_migrate.h"
 #include "xe_pt.h"
 #include "xe_svm.h"
 #include "xe_vm.h"
@@ -315,6 +316,157 @@ static u64 xe_vram_region_page_to_dpa(struct xe_vram_region *vr,
 	return dpa;
 }
 
+enum xe_svm_copy_dir {
+	XE_SVM_COPY_TO_VRAM,
+	XE_SVM_COPY_TO_SRAM,
+};
+
+static int xe_svm_copy(struct page **pages, dma_addr_t *dma_addr,
+		       unsigned long npages, const enum xe_svm_copy_dir dir)
+{
+	struct xe_vram_region *vr = NULL;
+	struct xe_tile *tile;
+	struct dma_fence *fence = NULL;
+	unsigned long i;
+#define XE_VRAM_ADDR_INVALID	~0x0ull
+	u64 vram_addr = XE_VRAM_ADDR_INVALID;
+	int err = 0, pos = 0;
+	bool sram = dir == XE_SVM_COPY_TO_SRAM;
+
+	/*
+	 * This flow is complex: it locates physically contiguous device pages,
+	 * derives the starting physical address, and performs a single GPU copy
+	 * to for every 8M chunk in a DMA address array. Both device pages and
+	 * DMA addresses may be sparsely populated. If either is NULL, a copy is
+	 * triggered based on the current search state. The last GPU copy is
+	 * waited on to ensure all copies are complete.
+	 */
+
+	for (i = 0; i < npages; ++i) {
+		struct page *spage = pages[i];
+		struct dma_fence *__fence;
+		u64 __vram_addr;
+		bool match = false, chunk, last;
+
+#define XE_MIGRATE_CHUNK_SIZE	SZ_8M
+		chunk = (i - pos) == (XE_MIGRATE_CHUNK_SIZE / PAGE_SIZE);
+		last = (i + 1) == npages;
+
+		/* No CPU page and no device pages queue'd to copy */
+		if (!dma_addr[i] && vram_addr == XE_VRAM_ADDR_INVALID)
+			continue;
+
+		if (!vr && spage) {
+			vr = page_to_vr(spage);
+			tile = vr_to_tile(vr);
+		}
+		XE_WARN_ON(spage && page_to_vr(spage) != vr);
+
+		/*
+		 * CPU page and device page valid, capture physical address on
+		 * first device page, check if physical contiguous on subsequent
+		 * device pages.
+		 */
+		if (dma_addr[i] && spage) {
+			__vram_addr = xe_vram_region_page_to_dpa(vr, spage);
+			if (vram_addr == XE_VRAM_ADDR_INVALID) {
+				vram_addr = __vram_addr;
+				pos = i;
+			}
+
+			match = vram_addr + PAGE_SIZE * (i - pos) == __vram_addr;
+		}
+
+		/*
+		 * Mismatched physical address, 8M copy chunk, or last page -
+		 * trigger a copy.
+		 */
+		if (!match || chunk || last) {
+			/*
+			 * Extra page for first copy if last page and matching
+			 * physical address.
+			 */
+			int incr = (match && last) ? 1 : 0;
+
+			if (vram_addr != XE_VRAM_ADDR_INVALID) {
+				if (sram)
+					__fence = xe_migrate_from_vram(tile->migrate,
+								       i - pos + incr,
+								       vram_addr,
+								       dma_addr + pos);
+				else
+					__fence = xe_migrate_to_vram(tile->migrate,
+								     i - pos + incr,
+								     dma_addr + pos,
+								     vram_addr);
+				if (IS_ERR(__fence)) {
+					err = PTR_ERR(__fence);
+					goto err_out;
+				}
+
+				dma_fence_put(fence);
+				fence = __fence;
+			}
+
+			/* Setup physical address of next device page */
+			if (dma_addr[i] && spage) {
+				vram_addr = __vram_addr;
+				pos = i;
+			} else {
+				vram_addr = XE_VRAM_ADDR_INVALID;
+			}
+
+			/* Extra mismatched device page, copy it */
+			if (!match && last && vram_addr != XE_VRAM_ADDR_INVALID) {
+				if (sram)
+					__fence = xe_migrate_from_vram(tile->migrate, 1,
+								       vram_addr,
+								       dma_addr + pos);
+				else
+					__fence = xe_migrate_to_vram(tile->migrate, 1,
+								     dma_addr + pos,
+								     vram_addr);
+				if (IS_ERR(__fence)) {
+					err = PTR_ERR(__fence);
+					goto err_out;
+				}
+
+				dma_fence_put(fence);
+				fence = __fence;
+			}
+		}
+	}
+
+err_out:
+	/* Wait for all copies to complete */
+	if (fence) {
+		dma_fence_wait(fence, false);
+		dma_fence_put(fence);
+	}
+
+	return err;
+#undef XE_MIGRATE_CHUNK_SIZE
+#undef XE_VRAM_ADDR_INVALID
+}
+
+static int xe_svm_copy_to_devmem(struct page **pages, dma_addr_t *dma_addr,
+				 unsigned long npages)
+{
+	return xe_svm_copy(pages, dma_addr, npages, XE_SVM_COPY_TO_VRAM);
+}
+
+static int xe_svm_copy_to_ram(struct page **pages, dma_addr_t *dma_addr,
+			      unsigned long npages)
+{
+	return xe_svm_copy(pages, dma_addr, npages, XE_SVM_COPY_TO_SRAM);
+}
+
+__maybe_unused
+static const struct drm_gpusvm_devmem_ops gpusvm_devmem_ops = {
+	.copy_to_devmem = xe_svm_copy_to_devmem,
+	.copy_to_ram = xe_svm_copy_to_ram,
+};
+
 static const struct drm_gpusvm_ops gpusvm_ops = {
 	.range_alloc = xe_svm_range_alloc,
 	.range_free = xe_svm_range_free,