[PATCH v4 01/16] mm: thp: Batch-collapse PMD with set_ptes()

[Ryan Roberts]

Refactor __split_huge_pmd_locked() so that a present PMD can be
collapsed to PTEs in a single batch using set_ptes(). It also provides a
future opportunity to batch-add the folio to the rmap using David's new
batched rmap APIs.

This should improve performance a little bit, but the real motivation is
to remove the need for the arm64 backend to have to fold the contpte
entries. Instead, since the ptes are set as a batch, the contpte blocks
can be initially set up pre-folded (once the arm64 contpte support is
added in the next few patches). This leads to noticeable performance
improvement during split.

Signed-off-by: Ryan Roberts <ryan.roberts@xxxxxxx>
---
 mm/huge_memory.c | 59 ++++++++++++++++++++++++++++--------------------
 1 file changed, 34 insertions(+), 25 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 6be1a380a298..fbf7e95ea983 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2535,15 +2535,16 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 
 	pte = pte_offset_map(&_pmd, haddr);
 	VM_BUG_ON(!pte);
-	for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) {
-		pte_t entry;
-		/*
-		 * Note that NUMA hinting access restrictions are not
-		 * transferred to avoid any possibility of altering
-		 * permissions across VMAs.
-		 */
-		if (freeze || pmd_migration) {
+
+	/*
+	 * Note that NUMA hinting access restrictions are not transferred to
+	 * avoid any possibility of altering permissions across VMAs.
+	 */
+	if (freeze || pmd_migration) {
+		for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) {
+			pte_t entry;
 			swp_entry_t swp_entry;
+
 			if (write)
 				swp_entry = make_writable_migration_entry(
 							page_to_pfn(page + i));
@@ -2562,28 +2563,36 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 				entry = pte_swp_mksoft_dirty(entry);
 			if (uffd_wp)
 				entry = pte_swp_mkuffd_wp(entry);
-		} else {
-			entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot));
-			if (write)
-				entry = pte_mkwrite(entry, vma);
+
+			VM_WARN_ON(!pte_none(ptep_get(pte + i)));
+			set_pte_at(mm, addr, pte + i, entry);
+		}
+	} else {
+		pte_t entry;
+
+		entry = mk_pte(page, READ_ONCE(vma->vm_page_prot));
+		if (write)
+			entry = pte_mkwrite(entry, vma);
+		if (!young)
+			entry = pte_mkold(entry);
+		/* NOTE: this may set soft-dirty too on some archs */
+		if (dirty)
+			entry = pte_mkdirty(entry);
+		if (soft_dirty)
+			entry = pte_mksoft_dirty(entry);
+		if (uffd_wp)
+			entry = pte_mkuffd_wp(entry);
+
+		for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) {
 			if (anon_exclusive)
 				SetPageAnonExclusive(page + i);
-			if (!young)
-				entry = pte_mkold(entry);
-			/* NOTE: this may set soft-dirty too on some archs */
-			if (dirty)
-				entry = pte_mkdirty(entry);
-			if (soft_dirty)
-				entry = pte_mksoft_dirty(entry);
-			if (uffd_wp)
-				entry = pte_mkuffd_wp(entry);
 			page_add_anon_rmap(page + i, vma, addr, RMAP_NONE);
+			VM_WARN_ON(!pte_none(ptep_get(pte + i)));
 		}
-		VM_BUG_ON(!pte_none(ptep_get(pte)));
-		set_pte_at(mm, addr, pte, entry);
-		pte++;
+
+		set_ptes(mm, haddr, pte, entry, HPAGE_PMD_NR);
 	}
-	pte_unmap(pte - 1);
+	pte_unmap(pte);
 
 	if (!pmd_migration)
 		page_remove_rmap(page, vma, true);
-- 
2.25.1