khugepaged: optimize __collapse_huge_page_copy_succeeded() by PTE batching

Use PTE batching to batch process PTEs mapping the same large folio. An
improvement is expected due to batching refcount-mapcount manipulation on
the folios, and for arm64 which supports contig mappings, the number of
TLB flushes is also reduced.

Link: https://lkml.kernel.org/r/20250724052301.23844-3-dev.jain@arm.com
Signed-off-by: Dev Jain <dev.jain@arm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mariano Pache <npache@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Author: Dev Jain

mm/khugepaged.c

@@ -700,12 +700,15 @@ static void __collapse_huge_page_copy_succeeded(pte_t *pte,
 						spinlock_t *ptl,
 						struct list_head *compound_pagelist)
 {
+	unsigned long end = address + HPAGE_PMD_SIZE;
 	struct folio *src, *tmp;
-	pte_t *_pte;
 	pte_t pteval;
+	pte_t *_pte;
+	unsigned int nr_ptes;
 
-	for (_pte = pte; _pte < pte + HPAGE_PMD_NR;
-	     _pte++, address += PAGE_SIZE) {
+	for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte += nr_ptes,
+	     address += nr_ptes * PAGE_SIZE) {
+		nr_ptes = 1;
 		pteval = ptep_get(_pte);
 		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
 			add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1);
@@ -722,18 +725,26 @@ static void __collapse_huge_page_copy_succeeded(pte_t *pte,
 			struct page *src_page = pte_page(pteval);
 
 			src = page_folio(src_page);
-			if (!folio_test_large(src))
+
+			if (folio_test_large(src)) {
+				unsigned int max_nr_ptes = (end - address) >> PAGE_SHIFT;
+
+				nr_ptes = folio_pte_batch(src, _pte, pteval, max_nr_ptes);
+			} else {
 				release_pte_folio(src);
+			}
+
 			/*
 			 * ptl mostly unnecessary, but preempt has to
 			 * be disabled to update the per-cpu stats
 			 * inside folio_remove_rmap_pte().
 			 */
 			spin_lock(ptl);
-			ptep_clear(vma->vm_mm, address, _pte);
-			folio_remove_rmap_pte(src, src_page, vma);
+			clear_ptes(vma->vm_mm, address, _pte, nr_ptes);
+			folio_remove_rmap_ptes(src, src_page, nr_ptes, vma);
 			spin_unlock(ptl);
-			free_folio_and_swap_cache(src);
+			free_swap_cache(src);
+			folio_put_refs(src, nr_ptes);
 		}
 	}