[PATCH 1/1] mm/rmap: make folio unmap batching safe and support partial batches

[Lance Yang]

From: Lance Yang <lance.yang at linux.dev>

As pointed out by David[1], the batched unmap logic in try_to_unmap_one()
can read past the end of a PTE table if a large folio is mapped starting at
the last entry of that table.

So let's fix the out-of-bounds read by refactoring the logic into a new
helper, folio_unmap_pte_batch().

The new helper now correctly calculates the safe number of pages to scan by
limiting the operation to the boundaries of the current VMA and the PTE
table.

In addition, the "all-or-nothing" batching restriction is removed to
support partial batches. The reference counting is also cleaned up to use
folio_put_refs().

[1] https://lore.kernel.org/linux-mm/a694398c-9f03-4737-81b9-7e49c857fcbe@redhat.com

Fixes: 354dffd29575 ("mm: support batched unmap for lazyfree large folios during reclamation")
Suggested-by: David Hildenbrand <david at redhat.com>
Suggested-by: Barry Song <baohua at kernel.org>
Signed-off-by: Lance Yang <lance.yang at linux.dev>
---
 mm/rmap.c | 46 ++++++++++++++++++++++++++++------------------
 1 file changed, 28 insertions(+), 18 deletions(-)

diff --git a/mm/rmap.c b/mm/rmap.c
index fb63d9256f09..1320b88fab74 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1845,23 +1845,32 @@ void folio_remove_rmap_pud(struct folio *folio, struct page *page,
 #endif
 }
 
-/* We support batch unmapping of PTEs for lazyfree large folios */
-static inline bool can_batch_unmap_folio_ptes(unsigned long addr,
-			struct folio *folio, pte_t *ptep)
+static inline unsigned int folio_unmap_pte_batch(struct folio *folio,
+			struct page_vma_mapped_walk *pvmw,
+			enum ttu_flags flags, pte_t pte)
 {
 	const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY;
-	int max_nr = folio_nr_pages(folio);
-	pte_t pte = ptep_get(ptep);
+	unsigned long end_addr, addr = pvmw->address;
+	struct vm_area_struct *vma = pvmw->vma;
+	unsigned int max_nr;
+
+	if (flags & TTU_HWPOISON)
+		return 1;
+	if (!folio_test_large(folio))
+		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;
+
+	/* We only support lazyfree batching for now ... */
 	if (!folio_test_anon(folio) || folio_test_swapbacked(folio))
-		return false;
+		return 1;
 	if (pte_unused(pte))
-		return false;
-	if (pte_pfn(pte) != folio_pfn(folio))
-		return false;
+		return 1;
 
-	return folio_pte_batch(folio, addr, ptep, pte, max_nr, fpb_flags, NULL,
-			       NULL, NULL) == max_nr;
+	return folio_pte_batch(folio, addr, pvmw->pte, pte, max_nr, fpb_flags,
+			       NULL, NULL, NULL);
 }
 
 /*
@@ -2024,9 +2033,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 			if (pte_dirty(pteval))
 				folio_mark_dirty(folio);
 		} else if (likely(pte_present(pteval))) {
-			if (folio_test_large(folio) && !(flags & TTU_HWPOISON) &&
-			    can_batch_unmap_folio_ptes(address, folio, pvmw.pte))
-				nr_pages = folio_nr_pages(folio);
+			nr_pages = folio_unmap_pte_batch(folio, &pvmw, flags, pteval);
 			end_addr = address + nr_pages * PAGE_SIZE;
 			flush_cache_range(vma, address, end_addr);
 
@@ -2206,13 +2213,16 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 			hugetlb_remove_rmap(folio);
 		} else {
 			folio_remove_rmap_ptes(folio, subpage, nr_pages, vma);
-			folio_ref_sub(folio, nr_pages - 1);
 		}
 		if (vma->vm_flags & VM_LOCKED)
 			mlock_drain_local();
-		folio_put(folio);
-		/* We have already batched the entire folio */
-		if (nr_pages > 1)
+		folio_put_refs(folio, nr_pages);
+
+		/*
+		 * If we are sure that we batched the entire folio and cleared
+		 * all PTEs, we can just optimize and stop right here.
+		 */
+		if (nr_pages == folio_nr_pages(folio))
 			goto walk_done;
 		continue;
 walk_abort:
-- 
2.49.0