1 files changed, 139 insertions, 44 deletions

diff --git a/mm/ksm.c b/mm/ksm.c
index 160787bb121c..c4e730409949 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1061,11 +1061,6 @@ struct ksm_stable_node *folio_stable_node(const struct folio *folio)
 	return folio_test_ksm(folio) ? folio_raw_mapping(folio) : NULL;
 }
 
-static inline struct ksm_stable_node *page_stable_node(struct page *page)
-{
-	return folio_stable_node(page_folio(page));
-}
-
 static inline void folio_set_stable_node(struct folio *folio,
 					 struct ksm_stable_node *stable_node)
 {
@@ -1217,8 +1212,8 @@ mm_exiting:
 			spin_unlock(&ksm_mmlist_lock);
 
 			mm_slot_free(mm_slot_cache, mm_slot);
-			clear_bit(MMF_VM_MERGEABLE, &mm->flags);
-			clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
+			mm_flags_clear(MMF_VM_MERGEABLE, mm);
+			mm_flags_clear(MMF_VM_MERGE_ANY, mm);
 			mmdrop(mm);
 		} else
 			spin_unlock(&ksm_mmlist_lock);
@@ -2225,6 +2220,7 @@ static void stable_tree_append(struct ksm_rmap_item *rmap_item,
  */
 static void cmp_and_merge_page(struct page *page, struct ksm_rmap_item *rmap_item)
 {
+	struct folio *folio = page_folio(page);
 	struct ksm_rmap_item *tree_rmap_item;
 	struct page *tree_page = NULL;
 	struct ksm_stable_node *stable_node;
@@ -2233,7 +2229,7 @@ static void cmp_and_merge_page(struct page *page, struct ksm_rmap_item *rmap_ite
 	int err;
 	bool max_page_sharing_bypass = false;
 
-	stable_node = page_stable_node(page);
+	stable_node = folio_stable_node(folio);
 	if (stable_node) {
 		if (stable_node->head != &migrate_nodes &&
 		    get_kpfn_nid(READ_ONCE(stable_node->kpfn)) !=
@@ -2272,7 +2268,7 @@ static void cmp_and_merge_page(struct page *page, struct ksm_rmap_item *rmap_ite
 
 	/* Start by searching for the folio in the stable tree */
 	kfolio = stable_tree_search(page);
-	if (&kfolio->page == page && rmap_item->head == stable_node) {
+	if (kfolio == folio && rmap_item->head == stable_node) {
 		folio_put(kfolio);
 		return;
 	}
@@ -2353,10 +2349,11 @@ static void cmp_and_merge_page(struct page *page, struct ksm_rmap_item *rmap_ite
 			 * the page is locked, it is better to skip it and
 			 * perhaps try again later.
 			 */
-			if (!trylock_page(page))
+			if (!folio_trylock(folio))
 				return;
 			split_huge_page(page);
-			unlock_page(page);
+			folio = page_folio(page);
+			folio_unlock(folio);
 		}
 	}
 }
@@ -2458,6 +2455,95 @@ static bool should_skip_rmap_item(struct folio *folio,
 	return true;
 }
 
+struct ksm_next_page_arg {
+	struct folio *folio;
+	struct page *page;
+	unsigned long addr;
+};
+
+static int ksm_next_page_pmd_entry(pmd_t *pmdp, unsigned long addr, unsigned long end,
+		struct mm_walk *walk)
+{
+	struct ksm_next_page_arg *private = walk->private;
+	struct vm_area_struct *vma = walk->vma;
+	pte_t *start_ptep = NULL, *ptep, pte;
+	struct mm_struct *mm = walk->mm;
+	struct folio *folio;
+	struct page *page;
+	spinlock_t *ptl;
+	pmd_t pmd;
+
+	if (ksm_test_exit(mm))
+		return 0;
+
+	cond_resched();
+
+	pmd = pmdp_get_lockless(pmdp);
+	if (!pmd_present(pmd))
+		return 0;
+
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && pmd_leaf(pmd)) {
+		ptl = pmd_lock(mm, pmdp);
+		pmd = pmdp_get(pmdp);
+
+		if (!pmd_present(pmd)) {
+			goto not_found_unlock;
+		} else if (pmd_leaf(pmd)) {
+			page = vm_normal_page_pmd(vma, addr, pmd);
+			if (!page)
+				goto not_found_unlock;
+			folio = page_folio(page);
+
+			if (folio_is_zone_device(folio) || !folio_test_anon(folio))
+				goto not_found_unlock;
+
+			page += ((addr & (PMD_SIZE - 1)) >> PAGE_SHIFT);
+			goto found_unlock;
+		}
+		spin_unlock(ptl);
+	}
+
+	start_ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
+	if (!start_ptep)
+		return 0;
+
+	for (ptep = start_ptep; addr < end; ptep++, addr += PAGE_SIZE) {
+		pte = ptep_get(ptep);
+
+		if (!pte_present(pte))
+			continue;
+
+		page = vm_normal_page(vma, addr, pte);
+		if (!page)
+			continue;
+		folio = page_folio(page);
+
+		if (folio_is_zone_device(folio) || !folio_test_anon(folio))
+			continue;
+		goto found_unlock;
+	}
+
+not_found_unlock:
+	spin_unlock(ptl);
+	if (start_ptep)
+		pte_unmap(start_ptep);
+	return 0;
+found_unlock:
+	folio_get(folio);
+	spin_unlock(ptl);
+	if (start_ptep)
+		pte_unmap(start_ptep);
+	private->page = page;
+	private->folio = folio;
+	private->addr = addr;
+	return 1;
+}
+
+static struct mm_walk_ops ksm_next_page_ops = {
+	.pmd_entry = ksm_next_page_pmd_entry,
+	.walk_lock = PGWALK_RDLOCK,
+};
+
 static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page)
 {
 	struct mm_struct *mm;
@@ -2545,21 +2631,27 @@ next_mm:
 			ksm_scan.address = vma->vm_end;
 
 		while (ksm_scan.address < vma->vm_end) {
+			struct ksm_next_page_arg ksm_next_page_arg;
 			struct page *tmp_page = NULL;
-			struct folio_walk fw;
 			struct folio *folio;
 
 			if (ksm_test_exit(mm))
 				break;
 
-			folio = folio_walk_start(&fw, vma, ksm_scan.address, 0);
-			if (folio) {
-				if (!folio_is_zone_device(folio) &&
-				     folio_test_anon(folio)) {
-					folio_get(folio);
-					tmp_page = fw.page;
-				}
-				folio_walk_end(&fw, vma);
+			int found;
+
+			found = walk_page_range_vma(vma, ksm_scan.address,
+						    vma->vm_end,
+						    &ksm_next_page_ops,
+						    &ksm_next_page_arg);
+
+			if (found > 0) {
+				folio = ksm_next_page_arg.folio;
+				tmp_page = ksm_next_page_arg.page;
+				ksm_scan.address = ksm_next_page_arg.addr;
+			} else {
+				VM_WARN_ON_ONCE(found < 0);
+				ksm_scan.address = vma->vm_end - PAGE_SIZE;
 			}
 
 			if (tmp_page) {
@@ -2620,8 +2712,8 @@ no_vmas:
 		spin_unlock(&ksm_mmlist_lock);
 
 		mm_slot_free(mm_slot_cache, mm_slot);
-		clear_bit(MMF_VM_MERGEABLE, &mm->flags);
-		clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
+		mm_flags_clear(MMF_VM_MERGEABLE, mm);
+		mm_flags_clear(MMF_VM_MERGE_ANY, mm);
 		mmap_read_unlock(mm);
 		mmdrop(mm);
 	} else {
@@ -2742,7 +2834,7 @@ static int __ksm_del_vma(struct vm_area_struct *vma)
 vm_flags_t ksm_vma_flags(const struct mm_struct *mm, const struct file *file,
 			 vm_flags_t vm_flags)
 {
-	if (test_bit(MMF_VM_MERGE_ANY, &mm->flags) &&
+	if (mm_flags_test(MMF_VM_MERGE_ANY, mm) &&
 	    __ksm_should_add_vma(file, vm_flags))
 		vm_flags |= VM_MERGEABLE;
 
@@ -2784,16 +2876,16 @@ int ksm_enable_merge_any(struct mm_struct *mm)
 {
 	int err;
 
-	if (test_bit(MMF_VM_MERGE_ANY, &mm->flags))
+	if (mm_flags_test(MMF_VM_MERGE_ANY, mm))
 		return 0;
 
-	if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) {
+	if (!mm_flags_test(MMF_VM_MERGEABLE, mm)) {
 		err = __ksm_enter(mm);
 		if (err)
 			return err;
 	}
 
-	set_bit(MMF_VM_MERGE_ANY, &mm->flags);
+	mm_flags_set(MMF_VM_MERGE_ANY, mm);
 	ksm_add_vmas(mm);
 
 	return 0;
@@ -2815,7 +2907,7 @@ int ksm_disable_merge_any(struct mm_struct *mm)
 {
 	int err;
 
-	if (!test_bit(MMF_VM_MERGE_ANY, &mm->flags))
+	if (!mm_flags_test(MMF_VM_MERGE_ANY, mm))
 		return 0;
 
 	err = ksm_del_vmas(mm);
@@ -2824,7 +2916,7 @@ int ksm_disable_merge_any(struct mm_struct *mm)
 		return err;
 	}
 
-	clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
+	mm_flags_clear(MMF_VM_MERGE_ANY, mm);
 	return 0;
 }
 
@@ -2832,9 +2924,9 @@ int ksm_disable(struct mm_struct *mm)
 {
 	mmap_assert_write_locked(mm);
 
-	if (!test_bit(MMF_VM_MERGEABLE, &mm->flags))
+	if (!mm_flags_test(MMF_VM_MERGEABLE, mm))
 		return 0;
-	if (test_bit(MMF_VM_MERGE_ANY, &mm->flags))
+	if (mm_flags_test(MMF_VM_MERGE_ANY, mm))
 		return ksm_disable_merge_any(mm);
 	return ksm_del_vmas(mm);
 }
@@ -2852,7 +2944,7 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 		if (!vma_ksm_compatible(vma))
 			return 0;
 
-		if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) {
+		if (!mm_flags_test(MMF_VM_MERGEABLE, mm)) {
 			err = __ksm_enter(mm);
 			if (err)
 				return err;
@@ -2912,7 +3004,7 @@ int __ksm_enter(struct mm_struct *mm)
 		list_add_tail(&slot->mm_node, &ksm_scan.mm_slot->slot.mm_node);
 	spin_unlock(&ksm_mmlist_lock);
 
-	set_bit(MMF_VM_MERGEABLE, &mm->flags);
+	mm_flags_set(MMF_VM_MERGEABLE, mm);
 	mmgrab(mm);
 
 	if (needs_wakeup)
@@ -2924,7 +3016,7 @@ int __ksm_enter(struct mm_struct *mm)
 
 void __ksm_exit(struct mm_struct *mm)
 {
-	struct ksm_mm_slot *mm_slot;
+	struct ksm_mm_slot *mm_slot = NULL;
 	struct mm_slot *slot;
 	int easy_to_free = 0;
 
@@ -2939,23 +3031,26 @@ void __ksm_exit(struct mm_struct *mm)
 
 	spin_lock(&ksm_mmlist_lock);
 	slot = mm_slot_lookup(mm_slots_hash, mm);
+	if (!slot)
+		goto unlock;
 	mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot);
-	if (mm_slot && ksm_scan.mm_slot != mm_slot) {
-		if (!mm_slot->rmap_list) {
-			hash_del(&slot->hash);
-			list_del(&slot->mm_node);
-			easy_to_free = 1;
-		} else {
-			list_move(&slot->mm_node,
-				  &ksm_scan.mm_slot->slot.mm_node);
-		}
+	if (ksm_scan.mm_slot == mm_slot)
+		goto unlock;
+	if (!mm_slot->rmap_list) {
+		hash_del(&slot->hash);
+		list_del(&slot->mm_node);
+		easy_to_free = 1;
+	} else {
+		list_move(&slot->mm_node,
+			  &ksm_scan.mm_slot->slot.mm_node);
 	}
+unlock:
 	spin_unlock(&ksm_mmlist_lock);
 
 	if (easy_to_free) {
 		mm_slot_free(mm_slot_cache, mm_slot);
-		clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
-		clear_bit(MMF_VM_MERGEABLE, &mm->flags);
+		mm_flags_clear(MMF_VM_MERGE_ANY, mm);
+		mm_flags_clear(MMF_VM_MERGEABLE, mm);
 		mmdrop(mm);
 	} else if (mm_slot) {
 		mmap_write_lock(mm);