mm/rmap: fix potential out-of-bounds page table access during batched unmap

As pointed out by David[1], the batched unmap logic in
try_to_unmap_one() may read past the end of a PTE table when a large
folio's PTE mappings are not fully contained within a single page
table.

While this scenario might be rare, an issue triggerable from userspace
must be fixed regardless of its likelihood.  This patch fixes the
out-of-bounds access by refactoring the logic into a new helper,
folio_unmap_pte_batch().

The new helper correctly calculates the safe batch size by capping the
scan at both the VMA and PMD boundaries.  To simplify the code, it also
supports partial batching (i.e., any number of pages from 1 up to the
calculated safe maximum), as there is no strong reason to special-case
for fully mapped folios.

Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]
Link: https://lore.kernel.org/linux-mm/[email protected] [1]
Fixes: 354dffd ("mm: support batched unmap for lazyfree large folios during reclamation")
Signed-off-by: Lance Yang <[email protected]>
Suggested-by: David Hildenbrand <[email protected]>
Reported-by: David Hildenbrand <[email protected]>
Closes: https://lore.kernel.org/linux-mm/[email protected]
Suggested-by: Barry Song <[email protected]>
Acked-by: Barry Song <[email protected]>
Reviewed-by: Lorenzo Stoakes <[email protected]>
Acked-by: David Hildenbrand <[email protected]>
Reviewed-by: Harry Yoo <[email protected]>
Cc: Baolin Wang <[email protected]>
Cc: Chris Li <[email protected]>
Cc: "Huang, Ying" <[email protected]>
Cc: Kairui Song <[email protected]>
Cc: Lance Yang <[email protected]>
Cc: Liam Howlett <[email protected]>
Cc: Mingzhe Yang <[email protected]>
Cc: Rik van Riel <[email protected]>
Cc: Ryan Roberts <[email protected]>
Cc: Tangquan Zheng <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

Author: ioworker0

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: