[PATCH v2 7/7] mm/rmap: batch the unmap of large folios in try_to_migrate_one()

[Shivank Garg]

try_to_migrate_one() converts present PTEs to migration entries one at a
time. For a PTE-mapped large folio, this repeat calls to ptep clear+flush,
the migration entry build and set, folio_remove_rmap_pte() and folio_put(),
each re-entering page_vma_mapped_walk() once per base page (256 times for
1M folio).

Mirror try_to_unmap_one() to introduce folio_migrate_pte_batch() to detect
eligible batch for PTEs mapping conseuctive subpages of a large folios,
and convert the whole batch in one shot using the batched helpers.

A side-effect of this change is trace_set_migration_pte() will record
one event per batched run instead of earlier behavior of one per base page.

Signed-off-by: Shivank Garg <shivankg@xxxxxxx>
---
 mm/rmap.c | 115 ++++++++++++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 86 insertions(+), 29 deletions(-)

diff --git a/mm/rmap.c b/mm/rmap.c
index 35752a70f3a0..63b885c0b7ef 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -2675,6 +2675,44 @@ static bool try_to_migrate_hugetlb_one(struct folio *folio,
 	return ret;
 }
 
+static inline unsigned int folio_migrate_pte_batch(struct folio *folio,
+		struct page_vma_mapped_walk *pvmw, pte_t pte,
+		struct page *subpage, bool anon_exclusive)
+{
+	unsigned long end_addr, addr = pvmw->address;
+	struct vm_area_struct *vma = pvmw->vma;
+	unsigned int max_nr, nr;
+
+#ifdef __HAVE_ARCH_UNMAP_ONE
+	/* Cannot batch unmap if arch_unmap_one() is defined. */
+	return 1;
+#endif
+
+	if (!folio_test_large(folio))
+		return 1;
+	if (folio_is_zone_device(folio) || folio_test_has_hwpoisoned(folio))
+		return 1;
+	if (pte_unused(pte))
+		return 1;
+
+	/* We may only batch within a single VMA and a single page table. */
+	end_addr = pmd_addr_end(addr, vma->vm_end);
+	max_nr = (end_addr - addr) >> PAGE_SHIFT;
+	/*
+	 * If unmap fails, we need to restore the ptes. To avoid accidentally
+	 * upgrading write permissions for ptes that were not originally writable,
+	 * and to avoid losing the soft-dirty bit, use the appropriate FPB flags.
+	 */
+	nr = folio_pte_batch_flags(folio, vma, pvmw->pte, &pte, max_nr,
+				   FPB_RESPECT_WRITE | FPB_RESPECT_SOFT_DIRTY);
+
+	/* Limit possible batch count to a uniform PageAnonExclusive value */
+	if (folio_test_anon(folio))
+		nr = page_anon_exclusive_batch(0, nr, subpage, anon_exclusive);
+
+	return nr;
+}
+
 /*
  * @arg: enum ttu_flags will be passed to this argument.
  *
@@ -2686,12 +2724,12 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 {
 	struct mm_struct *mm = vma->vm_mm;
 	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
-	bool anon_exclusive, writable, ret = true;
+	bool anon_exclusive, hwpoison, writable, ret = true;
 	pte_t pteval;
 	struct page *subpage;
 	struct mmu_notifier_range range;
 	enum ttu_flags flags = (enum ttu_flags)(long)arg;
-	unsigned long pfn;
+	unsigned long pfn, end_addr, nr_pages;
 
 	/*
 	 * When racing against e.g. zap_pte_range() on another cpu,
@@ -2744,11 +2782,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) ||
 					!folio_test_pmd_mappable(folio), folio);
 
-			if (set_pmd_migration_entry(&pvmw, subpage)) {
-				ret = false;
-				page_vma_mapped_walk_done(&pvmw);
-				break;
-			}
+			if (set_pmd_migration_entry(&pvmw, subpage))
+				goto walk_abort;
 			continue;
 #endif
 		}
@@ -2773,10 +2808,25 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 		subpage = folio_page(folio, pfn - folio_pfn(folio));
 		anon_exclusive = folio_test_anon(folio) &&
 				 PageAnonExclusive(subpage);
+		/*
+		 * memory_failure() can set PageHWPoison concurrently without holding
+		 * the folio lock. Snapshot the flag here to decide whether to batch
+		 * PTEs or install hwpoison entry.
+		 */
+		hwpoison = PageHWPoison(subpage);
 
+		nr_pages = 1;
 		if (likely(pte_present(pteval))) {
-			flush_cache_page(vma, address, pfn);
-			/* Nuke the page table entry. */
+			if (!hwpoison)
+				nr_pages = folio_migrate_pte_batch(folio, &pvmw,
+								   pteval, subpage,
+								   anon_exclusive);
+
+			end_addr = address + nr_pages * PAGE_SIZE;
+			flush_cache_range(vma, address, end_addr);
+
+			/* Nuke the page table entries. */
+			pteval = get_and_clear_ptes(mm, address, pvmw.pte, nr_pages);
 			if (should_defer_flush(mm, flags)) {
 				/*
 				 * We clear the PTE but do not flush so potentially
@@ -2786,11 +2836,9 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 				 * transition on a cached TLB entry is written through
 				 * and traps if the PTE is unmapped.
 				 */
-				pteval = ptep_get_and_clear(mm, address, pvmw.pte);
-
-				set_tlb_ubc_flush_pending(mm, pteval, address, address + PAGE_SIZE);
+				set_tlb_ubc_flush_pending(mm, pteval, address, end_addr);
 			} else {
-				pteval = ptep_clear_flush(vma, address, pvmw.pte);
+				flush_tlb_range(vma, address, end_addr);
 			}
 			if (pte_dirty(pteval))
 				folio_mark_dirty(folio);
@@ -2809,7 +2857,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 		/* Update high watermark before we lower rss */
 		update_hiwater_rss(mm);
 
-		if (PageHWPoison(subpage)) {
+		if (hwpoison) {
+			VM_WARN_ON_ONCE(nr_pages != 1);
 			VM_WARN_ON_FOLIO(folio_is_device_private(folio), folio);
 
 			pteval = swp_entry_to_pte(make_hwpoison_entry(subpage));
@@ -2837,19 +2886,15 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			 * so we'll not check/care.
 			 */
 			if (arch_unmap_one(mm, vma, address, pteval) < 0) {
-				set_pte_at(mm, address, pvmw.pte, pteval);
-				ret = false;
-				page_vma_mapped_walk_done(&pvmw);
-				break;
+				set_ptes(mm, address, pvmw.pte, pteval, nr_pages);
+				goto walk_abort;
 			}
 
-			/* See folio_try_share_anon_rmap_pte(): clear PTE first. */
+			/* See folio_try_share_anon_rmap_ptes(): clear PTE first. */
 			if (anon_exclusive &&
-			    folio_try_share_anon_rmap_pte(folio, subpage)) {
-				set_pte_at(mm, address, pvmw.pte, pteval);
-				ret = false;
-				page_vma_mapped_walk_done(&pvmw);
-				break;
+			    folio_try_share_anon_rmap_ptes(folio, subpage, nr_pages)) {
+				set_ptes(mm, address, pvmw.pte, pteval, nr_pages);
+				goto walk_abort;
 			}
 
 			/*
@@ -2859,19 +2904,31 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			 */
 			swp_pte = make_migration_pte(subpage, pteval,
 						     writable, anon_exclusive);
-			set_pte_at(mm, address, pvmw.pte, swp_pte);
 			trace_set_migration_pte(address, pte_val(swp_pte),
 						folio_order(folio));
+
+			/* Set nr_pages migration entries, advancing the PFN. */
+			set_softleaf_ptes(mm, address, pvmw.pte, swp_pte, nr_pages);
 			/*
 			 * No need to invalidate here it will synchronize on
 			 * against the special swap migration pte.
 			 */
 		}
 
-		folio_remove_rmap_pte(folio, subpage, vma);
-		if (vma->vm_flags & VM_LOCKED)
-			mlock_drain_local();
-		folio_put(folio);
+		finish_folio_unmap(vma, folio, subpage, nr_pages);
+
+		/*
+		 * If we batched the entire folio, there is nothing left to
+		 * walk; stop right here.
+		 */
+		if (nr_pages == folio_nr_pages(folio))
+			goto walk_done;
+		continue;
+walk_abort:
+		ret = false;
+walk_done:
+		page_vma_mapped_walk_done(&pvmw);
+		break;
 	}
 
 	mmu_notifier_invalidate_range_end(&range);

-- 
2.43.0