[PATCH v1 5/5] drm/pagemap: Allocate folios when possible

[Francois Dugast]

If the order is greater than zero, allocate a folio when populating the
RAM PFNs instead of allocating individual pages one after the other. For
example if 2MB folios are used instead of 4KB pages, this reduces the
number of calls to the allocation API by 512.

Signed-off-by: Francois Dugast <francois.dugast at intel.com>
Cc: Matthew Brost <matthew.brost at intel.com>
---
 drivers/gpu/drm/drm_pagemap.c | 33 ++++++++++++++++++++++-----------
 1 file changed, 22 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c
index de15d96f6393..4f67c6173ee5 100644
--- a/drivers/gpu/drm/drm_pagemap.c
+++ b/drivers/gpu/drm/drm_pagemap.c
@@ -438,6 +438,7 @@ EXPORT_SYMBOL_GPL(drm_pagemap_migrate_to_devmem);
  * @src_mpfn: Source array of migrate PFNs
  * @mpfn: Array of migrate PFNs to populate
  * @addr: Start address for PFN allocation
+ * @order: Page order
  *
  * This function populates the RAM migrate page frame numbers (PFNs) for the
  * specified VM area structure. It allocates and locks pages in the VM area for
@@ -452,35 +453,45 @@ static int drm_pagemap_migrate_populate_ram_pfn(struct vm_area_struct *vas,
 						unsigned long *mpages,
 						unsigned long *src_mpfn,
 						unsigned long *mpfn,
-						unsigned long addr)
+						unsigned long addr,
+						unsigned int order)
 {
 	unsigned long i;
 
-	for (i = 0; i < npages; ++i, addr += PAGE_SIZE) {
+	for (i = 0; i < npages;) {
 		struct page *page, *src_page;
 
 		if (!(src_mpfn[i] & MIGRATE_PFN_MIGRATE))
-			continue;
+			goto next;
 
 		src_page = migrate_pfn_to_page(src_mpfn[i]);
 		if (!src_page)
-			continue;
+			goto next;
 
 		if (fault_page) {
 			if (src_page->zone_device_data !=
 			    fault_page->zone_device_data)
-				continue;
+				goto next;
 		}
 
-		if (vas)
-			page = alloc_page_vma(GFP_HIGHUSER, vas, addr);
-		else
-			page = alloc_page(GFP_HIGHUSER);
+		if (order) {
+			page = folio_page(vma_alloc_folio(GFP_HIGHUSER | __GFP_ZERO,
+							  order, vas, addr), 0);
+		} else {
+			if (vas)
+				page = alloc_page_vma(GFP_HIGHUSER, vas, addr);
+			else
+				page = alloc_page(GFP_HIGHUSER);
+		}
 
 		if (!page)
 			goto free_pages;
 
 		mpfn[i] = migrate_pfn(page_to_pfn(page));
+
+next:
+		i += 0x1 << order;
+		addr += page_size(page);
 	}
 
 	for (i = 0; i < npages; ++i) {
@@ -554,7 +565,7 @@ int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation)
 		goto err_free;
 
 	err = drm_pagemap_migrate_populate_ram_pfn(NULL, NULL, npages, &mpages,
-						   src, dst, 0);
+						   src, dst, 0, 0);
 	if (err || !mpages)
 		goto err_finalize;
 
@@ -690,7 +701,7 @@ static int __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas,
 
 	err = drm_pagemap_migrate_populate_ram_pfn(vas, page, npages, &mpages,
 						   migrate.src, migrate.dst,
-						   start);
+						   start, 0);
 	if (err)
 		goto err_finalize;
 
-- 
2.43.0