[PATCH 40/46] mm/ksm: check large swap-cache folios before mapping them

[David Hildenbrand (Arm)]

From: Chris Mason <mason at kernel.org>

KSM folios are always small, but their shared swap slots can be read
back as part of a large folio in the swap cache. ksm_might_need_to_copy()
skips large folios, so another process can map a page with an incompatible
anon_vma or page index. Reverse mapping then cannot find the new
mapping, preventing migration or reclaim.

Apply the same compatibility checks to large folios as to small ones.
Pass the page corresponding to the swap entry and copy only that page
when necessary. In do_swap_page()'s copy path, decrement only that slot's
swap count, because the source swap-cache folio can now be large.

Fix generated by an LLM and sent by Chris Mason in private.

Fixes: f1879e8a0c60 ("mm, swap: never bypass the swap cache even for SWP_SYNCHRONOUS_IO")
Cc: stable at vger.kernel.org
Signed-off-by: Chris Mason <mason at kernel.org>
Signed-off-by: David Hildenbrand (Arm) <david at kernel.org>
---
 include/linux/ksm.h |  6 +++---
 mm/ksm.c            | 22 ++++++++++++----------
 mm/memory.c         |  5 +++--
 mm/swapfile.c       |  3 ++-
 4 files changed, 20 insertions(+), 16 deletions(-)

diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index d39d0d5483a23..a0d358a1feb63 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -91,8 +91,8 @@ static inline void ksm_exit(struct mm_struct *mm)
  * We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE,
  * but what if the vma was unmerged while the page was swapped out?
  */
-struct folio *ksm_might_need_to_copy(struct folio *folio,
-			struct vm_area_struct *vma, unsigned long addr);
+struct folio *ksm_might_need_to_copy(struct folio *folio, struct page *page,
+		struct vm_area_struct *vma, unsigned long addr);
 
 void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc);
 void folio_migrate_ksm(struct folio *newfolio, struct folio *folio);
@@ -145,7 +145,7 @@ static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 }
 
 static inline struct folio *ksm_might_need_to_copy(struct folio *folio,
-			struct vm_area_struct *vma, unsigned long addr)
+		struct page *page, struct vm_area_struct *vma, unsigned long addr)
 {
 	return folio;
 }
diff --git a/mm/ksm.c b/mm/ksm.c
index e050b1bdf810d..e95f6b6723602 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -3138,19 +3138,20 @@ void __ksm_exit(struct mm_struct *mm)
 }
 
 static bool folio_anon_rmap_compatible(const struct folio *folio,
-		struct vm_area_struct *vma, unsigned long addr)
+		const struct page *page, struct vm_area_struct *vma,
+		unsigned long addr)
 {
 	const struct anon_vma *anon_vma = folio_anon_vma(folio);
 	struct anon_vma_chain *avc;
 
 	VM_WARN_ON_ONCE_FOLIO(!folio_test_locked(folio), folio);
-	VM_WARN_ON_ONCE_FOLIO(folio_test_large(folio), folio);
+	VM_WARN_ON_ONCE_FOLIO(page_folio(page) != folio, folio);
 	VM_WARN_ON_ONCE_FOLIO(folio_test_ksm(folio), folio);
 	vma_assert_stabilised(vma);
 
 	if (!anon_vma)
 		return true;
-	if (folio->index != linear_anon_page_index(vma, addr))
+	if (page_pgoff(folio, page) != linear_anon_page_index(vma, addr))
 		return false;
 
 	/*
@@ -3167,20 +3168,21 @@ static bool folio_anon_rmap_compatible(const struct folio *folio,
 	return false;
 }
 
-struct folio *ksm_might_need_to_copy(struct folio *folio,
-			struct vm_area_struct *vma, unsigned long addr)
+struct folio *ksm_might_need_to_copy(struct folio *folio, struct page *page,
+		struct vm_area_struct *vma, unsigned long addr)
 {
-	struct page *page = folio_page(folio, 0);
 	struct folio *new_folio;
 
-	if (folio_test_large(folio))
-		return folio;
-
+	/*
+	 * A KSM folio is small, but the slot that it left behind can be swapped
+	 * in as a part of a large folio by one of the processes that shared it.
+	 * So test, and copy, the page of the slot.
+	 */
 	if (folio_test_ksm(folio)) {
 		if (folio_stable_node(folio) &&
 		    !(ksm_run & KSM_RUN_UNMERGE))
 			return folio;	/* no need to copy it */
-	} else if (folio_anon_rmap_compatible(folio, vma, addr)) {
+	} else if (folio_anon_rmap_compatible(folio, page, vma, addr)) {
 		return folio;		/* still no need to copy it */
 	}
 	if (PageHWPoison(page))
diff --git a/mm/memory.c b/mm/memory.c
index 230a2f4dafa13..be4c05db37d33 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5096,7 +5096,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	 * folio->index of non-ksm folios would be nonlinear inside the
 	 * anon VMA -- the ksm flag is lost on actual swapout.
 	 */
-	folio = ksm_might_need_to_copy(folio, vma, vmf->address);
+	folio = ksm_might_need_to_copy(folio, page, vma, vmf->address);
 	if (unlikely(!folio)) {
 		ret = VM_FAULT_OOM;
 		folio = swapcache;
@@ -5278,7 +5278,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	if (unlikely(folio != swapcache)) {
 		folio_add_new_anon_rmap(folio, vma, address, RMAP_EXCLUSIVE);
 		folio_add_lru_vma(folio, vma);
-		folio_put_swap(swapcache, NULL);
+		folio_put_swap(swapcache,
+			       folio_file_page(swapcache, swp_offset(entry)));
 	} else if (!folio_test_anon(folio)) {
 		/*
 		 * We currently only expect !anon folios that are fully
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 254ce86fa923e..71ef9e2efb3a9 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2514,7 +2514,8 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		return 0;
 
 	swapcache = folio;
-	folio = ksm_might_need_to_copy(folio, vma, addr);
+	folio = ksm_might_need_to_copy(folio,
+				       folio_file_page(folio, swp_offset(entry)), vma, addr);
 	if (unlikely(!folio))
 		return -ENOMEM;
 	else if (unlikely(folio == ERR_PTR(-EHWPOISON))) {

-- 
2.43.0