[PATCH v3 04/12] mm: hugetlb_vmemmap: generalize vmemmap page allocation

[Muchun Song <songmuchun@bytedance.com>]

Vmemmap page allocation is currently tied to restoring a virtual range
and assumes an empty destination list.  These constraints prevent it from
being reused when pages are requested independently of a vmemmap range or
appended to an existing list.

Generalize the allocator and give it an all-or-nothing list contract so
the restore and optimization paths can share the same allocation policy.
This also allows HVO head-page allocation to fail gracefully under memory
pressure without triggering the OOM killer.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Lance Yang <lance.yang@linux.dev>
Reviewed-by: Qi Zheng <qi.zheng@linux.dev>
---
v3:
- Use two tabs for continued function parameters (suggested by Mike
  Rapoport)
- Rename the local allocation list to new_pages (suggested by Mike
  Rapoport)
- Use a goto cleanup path for allocation failures (suggested by Mike
  Rapoport)
- Free failed allocations directly and retain batched accounting (suggested
  by Mike Rapoport)

v2:
- Collect Reviewed-by from Lance Yang and Qi Zheng
---
 mm/hugetlb_vmemmap.c | 31 ++++++++++++++-----------------
 1 file changed, 14 insertions(+), 17 deletions(-)

diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 0e5b2b182d1b..d3058e106795 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -334,26 +334,24 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end,
 	return ret;
 }
 
-static int alloc_vmemmap_page_list(unsigned long start, unsigned long end,
-				   struct list_head *list)
+static int alloc_vmemmap_page_list(struct list_head *head,
+		unsigned int nr_pages, int nid)
 {
-	gfp_t gfp_mask = GFP_KERNEL | __GFP_RETRY_MAYFAIL;
-	unsigned long nr_pages = (end - start) >> PAGE_SHIFT;
-	int nid = page_to_nid((struct page *)start);
+	LIST_HEAD(new_pages);
 	struct page *page, *next;
-	int i;
 
-	for (i = 0; i < nr_pages; i++) {
-		page = alloc_pages_node(nid, gfp_mask, 0);
+	for (unsigned int i = 0; i < nr_pages; i++) {
+		page = alloc_pages_node(nid, GFP_KERNEL | __GFP_RETRY_MAYFAIL, 0);
 		if (!page)
-			goto out;
-		list_add(&page->lru, list);
+			goto free_pages;
+		list_add(&page->lru, &new_pages);
 	}
+	list_splice(&new_pages, head);
 	memmap_pages_add(nr_pages);
 
 	return 0;
-out:
-	list_for_each_entry_safe(page, next, list, lru)
+free_pages:
+	list_for_each_entry_safe(page, next, &new_pages, lru)
 		__free_page(page);
 	return -ENOMEM;
 }
@@ -374,13 +372,14 @@ static int vmemmap_remap_alloc(unsigned long start, unsigned long end,
 			       unsigned long flags)
 {
 	LIST_HEAD(vmemmap_pages);
+	int nid = page_to_nid((struct page *)start);
 	struct vmemmap_remap_walk walk = {
 		.remap_pte	= vmemmap_restore_pte,
 		.vmemmap_pages	= &vmemmap_pages,
 		.flags		= flags,
 	};
 
-	if (alloc_vmemmap_page_list(start, end, &vmemmap_pages))
+	if (alloc_vmemmap_page_list(&vmemmap_pages, (end - start) / PAGE_SIZE, nid))
 		return -ENOMEM;
 
 	return vmemmap_remap_range(start, end, &walk);
@@ -527,15 +526,13 @@ static int __hugetlb_vmemmap_optimize_folio(const struct hstate *h,
 	 */
 	folio_set_hugetlb_vmemmap_optimized(folio);
 
-	vmemmap_head = alloc_pages_node(nid, GFP_KERNEL, 0);
-	if (!vmemmap_head) {
+	if (alloc_vmemmap_page_list(vmemmap_pages, VMEMMAP_OPTIMIZATION_PAGES, nid)) {
 		ret = -ENOMEM;
 		goto out;
 	}
 
+	vmemmap_head = list_first_entry(vmemmap_pages, struct page, lru);
 	copy_page(page_to_virt(vmemmap_head), folio);
-	list_add(&vmemmap_head->lru, vmemmap_pages);
-	memmap_pages_add(1);
 
 	vmemmap_start	= (unsigned long)&folio->page;
 	vmemmap_end	= vmemmap_start + hugetlb_vmemmap_size(h);
-- 
2.54.0