Merge branch 'mm-hotfixes-stable' into mm-stable.

Pick these into mm-stable:

5de1950 mm: resolve faulty mmap_region() error path behaviour
5baf8b0 mm: refactor arch_calc_vm_flag_bits() and arm64 MTE handling
0fb4a7a mm: refactor map_deny_write_exec()
4080ef1 mm: unconditionally close VMAs on error
3dd6ed3 mm: avoid unsafe VMA hook invocation when error arises on mmap hook
f8f931b mm/thp: fix deferred split unqueue naming and locking
e66f318 mm/thp: fix deferred split queue not partially_mapped

to get a clean merge of these from mm-unstable into mm-stable:

Subject: memcg-v1: fully deprecate move_charge_at_immigrate
Subject: memcg-v1: remove charge move code
Subject: memcg-v1: no need for memcg locking for dirty tracking
Subject: memcg-v1: no need for memcg locking for writeback tracking
Subject: memcg-v1: no need for memcg locking for MGLRU
Subject: memcg-v1: remove memcg move locking code
Subject: tools: testing: add additional vma_internal.h stubs
Subject: mm: isolate mmap internal logic to mm/vma.c
Subject: mm: refactor __mmap_region()
Subject: mm: remove unnecessary reset state logic on merge new VMA
Subject: mm: defer second attempt at merge on mmap()
Subject: mm/vma: the pgoff is correct if can_merge_right
Subject: memcg: workingset: remove folio_memcg_rcu usage

Author: akpm00

arch/arm64/include/asm/mman.h

@@ -6,6 +6,8 @@
 
 #ifndef BUILD_VDSO
 #include <linux/compiler.h>
+#include <linux/fs.h>
+#include <linux/shmem_fs.h>
 #include <linux/types.h>
 
 static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
@@ -31,19 +33,21 @@ static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
 }
 #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
 
-static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags)
+static inline unsigned long arch_calc_vm_flag_bits(struct file *file,
+						   unsigned long flags)
 {
 	/*
 	 * Only allow MTE on anonymous mappings as these are guaranteed to be
 	 * backed by tags-capable memory. The vm_flags may be overridden by a
 	 * filesystem supporting MTE (RAM-based).
 	 */
-	if (system_supports_mte() && (flags & MAP_ANONYMOUS))
+	if (system_supports_mte() &&
+	    ((flags & MAP_ANONYMOUS) || shmem_file(file)))
 		return VM_MTE_ALLOWED;
 
 	return 0;
 }
-#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags)
+#define arch_calc_vm_flag_bits(file, flags) arch_calc_vm_flag_bits(file, flags)
 
 static inline bool arch_validate_prot(unsigned long prot,
 	unsigned long addr __always_unused)

arch/parisc/include/asm/mman.h

@@ -2,6 +2,7 @@
 #ifndef __ASM_MMAN_H__
 #define __ASM_MMAN_H__
 
+#include <linux/fs.h>
 #include <uapi/asm/mman.h>
 
 /* PARISC cannot allow mdwe as it needs writable stacks */
@@ -11,7 +12,7 @@ static inline bool arch_memory_deny_write_exec_supported(void)
 }
 #define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported
 
-static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags)
+static inline unsigned long arch_calc_vm_flag_bits(struct file *file, unsigned long flags)
 {
 	/*
 	 * The stack on parisc grows upwards, so if userspace requests memory
@@ -23,6 +24,6 @@ static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags)
 
 	return 0;
 }
-#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags)
+#define arch_calc_vm_flag_bits(file, flags) arch_calc_vm_flag_bits(file, flags)
 
 #endif /* __ASM_MMAN_H__ */

include/linux/mman.h

@@ -2,6 +2,7 @@
 #ifndef _LINUX_MMAN_H
 #define _LINUX_MMAN_H
 
+#include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/percpu_counter.h>
 
@@ -94,7 +95,7 @@ static inline void vm_unacct_memory(long pages)
 #endif
 
 #ifndef arch_calc_vm_flag_bits
-#define arch_calc_vm_flag_bits(flags) 0
+#define arch_calc_vm_flag_bits(file, flags) 0
 #endif
 
 #ifndef arch_validate_prot
@@ -151,13 +152,13 @@ calc_vm_prot_bits(unsigned long prot, unsigned long pkey)
  * Combine the mmap "flags" argument into "vm_flags" used internally.
  */
 static inline unsigned long
-calc_vm_flag_bits(unsigned long flags)
+calc_vm_flag_bits(struct file *file, unsigned long flags)
 {
 	return _calc_vm_trans(flags, MAP_GROWSDOWN,  VM_GROWSDOWN ) |
 	       _calc_vm_trans(flags, MAP_LOCKED,     VM_LOCKED    ) |
 	       _calc_vm_trans(flags, MAP_SYNC,	     VM_SYNC      ) |
 	       _calc_vm_trans(flags, MAP_STACK,	     VM_NOHUGEPAGE) |
-	       arch_calc_vm_flag_bits(flags);
+	       arch_calc_vm_flag_bits(file, flags);
 }
 
 unsigned long vm_commit_limit(void);
@@ -188,16 +189,31 @@ static inline bool arch_memory_deny_write_exec_supported(void)
  *
  *	d)	mmap(PROT_READ | PROT_EXEC)
  *		mmap(PROT_READ | PROT_EXEC | PROT_BTI)
+ *
+ * This is only applicable if the user has set the Memory-Deny-Write-Execute
+ * (MDWE) protection mask for the current process.
+ *
+ * @old specifies the VMA flags the VMA originally possessed, and @new the ones
+ * we propose to set.
+ *
+ * Return: false if proposed change is OK, true if not ok and should be denied.
  */
-static inline bool map_deny_write_exec(struct vm_area_struct *vma,  unsigned long vm_flags)
+static inline bool map_deny_write_exec(unsigned long old, unsigned long new)
 {
+	/* If MDWE is disabled, we have nothing to deny. */
 	if (!test_bit(MMF_HAS_MDWE, &current->mm->flags))
 		return false;
 
-	if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE))
+	/* If the new VMA is not executable, we have nothing to deny. */
+	if (!(new & VM_EXEC))
+		return false;
+
+	/* Under MDWE we do not accept newly writably executable VMAs... */
+	if (new & VM_WRITE)
 		return true;
 
-	if (!(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC))
+	/* ...nor previously non-executable VMAs becoming executable. */
+	if (!(old & VM_EXEC))
 		return true;
 
 	return false;

mm/huge_memory.c

@@ -3588,10 +3588,27 @@ int split_folio_to_list(struct folio *folio, struct list_head *list)
 	return split_huge_page_to_list_to_order(&folio->page, list, ret);
 }
 
-void __folio_undo_large_rmappable(struct folio *folio)
+/*
+ * __folio_unqueue_deferred_split() is not to be called directly:
+ * the folio_unqueue_deferred_split() inline wrapper in mm/internal.h
+ * limits its calls to those folios which may have a _deferred_list for
+ * queueing THP splits, and that list is (racily observed to be) non-empty.
+ *
+ * It is unsafe to call folio_unqueue_deferred_split() until folio refcount is
+ * zero: because even when split_queue_lock is held, a non-empty _deferred_list
+ * might be in use on deferred_split_scan()'s unlocked on-stack list.
+ *
+ * If memory cgroups are enabled, split_queue_lock is in the mem_cgroup: it is
+ * therefore important to unqueue deferred split before changing folio memcg.
+ */
+bool __folio_unqueue_deferred_split(struct folio *folio)
 {
 	struct deferred_split *ds_queue;
 	unsigned long flags;
+	bool unqueued = false;
+
+	WARN_ON_ONCE(folio_ref_count(folio));
+	WARN_ON_ONCE(!mem_cgroup_disabled() && !folio_memcg(folio));
 
 	ds_queue = get_deferred_split_queue(folio);
 	spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
@@ -3603,8 +3620,11 @@ void __folio_undo_large_rmappable(struct folio *folio)
 				      MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
 		}
 		list_del_init(&folio->_deferred_list);
+		unqueued = true;
 	}
 	spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
+
+	return unqueued;	/* useful for debug warnings */
 }
 
 /* partially_mapped=false won't clear PG_partially_mapped folio flag */
@@ -3627,14 +3647,11 @@ void deferred_split_folio(struct folio *folio, bool partially_mapped)
 		return;
 
 	/*
-	 * The try_to_unmap() in page reclaim path might reach here too,
-	 * this may cause a race condition to corrupt deferred split queue.
-	 * And, if page reclaim is already handling the same folio, it is
-	 * unnecessary to handle it again in shrinker.
-	 *
-	 * Check the swapcache flag to determine if the folio is being
-	 * handled by page reclaim since THP swap would add the folio into
-	 * swap cache before calling try_to_unmap().
+	 * Exclude swapcache: originally to avoid a corrupt deferred split
+	 * queue. Nowadays that is fully prevented by mem_cgroup_swapout();
+	 * but if page reclaim is already handling the same folio, it is
+	 * unnecessary to handle it again in the shrinker, so excluding
+	 * swapcache here may still be a useful optimization.
 	 */
 	if (folio_test_swapcache(folio))
 		return;
@@ -3718,8 +3735,8 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
 	struct deferred_split *ds_queue = &pgdata->deferred_split_queue;
 	unsigned long flags;
 	LIST_HEAD(list);
-	struct folio *folio, *next;
-	int split = 0;
+	struct folio *folio, *next, *prev = NULL;
+	int split = 0, removed = 0;
 
 #ifdef CONFIG_MEMCG
 	if (sc->memcg)
@@ -3775,15 +3792,28 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
 		 */
 		if (!did_split && !folio_test_partially_mapped(folio)) {
 			list_del_init(&folio->_deferred_list);
-			ds_queue->split_queue_len--;
+			removed++;
+		} else {
+			/*
+			 * That unlocked list_del_init() above would be unsafe,
+			 * unless its folio is separated from any earlier folios
+			 * left on the list (which may be concurrently unqueued)
+			 * by one safe folio with refcount still raised.
+			 */
+			swap(folio, prev);
 		}
-		folio_put(folio);
+		if (folio)
+			folio_put(folio);
 	}
 
 	spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
 	list_splice_tail(&list, &ds_queue->split_queue);
+	ds_queue->split_queue_len -= removed;
 	spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
 
+	if (prev)
+		folio_put(prev);
+
 	/*
 	 * Stop shrinker if we didn't split any page, but the queue is empty.
 	 * This can happen if pages were freed under us.

mm/internal.h

@@ -108,6 +108,51 @@ static inline void *folio_raw_mapping(const struct folio *folio)
 	return (void *)(mapping & ~PAGE_MAPPING_FLAGS);
 }
 
+/*
+ * This is a file-backed mapping, and is about to be memory mapped - invoke its
+ * mmap hook and safely handle error conditions. On error, VMA hooks will be
+ * mutated.
+ *
+ * @file: File which backs the mapping.
+ * @vma:  VMA which we are mapping.
+ *
+ * Returns: 0 if success, error otherwise.
+ */
+static inline int mmap_file(struct file *file, struct vm_area_struct *vma)
+{
+	int err = call_mmap(file, vma);
+
+	if (likely(!err))
+		return 0;
+
+	/*
+	 * OK, we tried to call the file hook for mmap(), but an error
+	 * arose. The mapping is in an inconsistent state and we most not invoke
+	 * any further hooks on it.
+	 */
+	vma->vm_ops = &vma_dummy_vm_ops;
+
+	return err;
+}
+
+/*
+ * If the VMA has a close hook then close it, and since closing it might leave
+ * it in an inconsistent state which makes the use of any hooks suspect, clear
+ * them down by installing dummy empty hooks.
+ */
+static inline void vma_close(struct vm_area_struct *vma)
+{
+	if (vma->vm_ops && vma->vm_ops->close) {
+		vma->vm_ops->close(vma);
+
+		/*
+		 * The mapping is in an inconsistent state, and no further hooks
+		 * may be invoked upon it.
+		 */
+		vma->vm_ops = &vma_dummy_vm_ops;
+	}
+}
+
 #ifdef CONFIG_MMU
 
 /* Flags for folio_pte_batch(). */
@@ -639,21 +684,21 @@ static inline void folio_set_order(struct folio *folio, unsigned int order)
 #endif
 }
 
-void __folio_undo_large_rmappable(struct folio *folio);
-static inline void folio_undo_large_rmappable(struct folio *folio)
+bool __folio_unqueue_deferred_split(struct folio *folio);
+static inline bool folio_unqueue_deferred_split(struct folio *folio)
 {
 	if (folio_order(folio) <= 1 || !folio_test_large_rmappable(folio))
-		return;
+		return false;
 
 	/*
 	 * At this point, there is no one trying to add the folio to
 	 * deferred_list. If folio is not in deferred_list, it's safe
 	 * to check without acquiring the split_queue_lock.
 	 */
 	if (data_race(list_empty(&folio->_deferred_list)))
-		return;
+		return false;
 
-	__folio_undo_large_rmappable(folio);
+	return __folio_unqueue_deferred_split(folio);
 }
 
 static inline struct folio *page_rmappable_folio(struct page *page)

mm/memcontrol-v1.c

@@ -848,6 +848,8 @@ static int mem_cgroup_move_account(struct folio *folio,
 	css_get(&to->css);
 	css_put(&from->css);
 
+	/* Warning should never happen, so don't worry about refcount non-0 */
+	WARN_ON_ONCE(folio_unqueue_deferred_split(folio));
 	folio->memcg_data = (unsigned long)to;
 
 	__folio_memcg_unlock(from);
@@ -1217,7 +1219,9 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 	enum mc_target_type target_type;
 	union mc_target target;
 	struct folio *folio;
+	bool tried_split_before = false;
 
+retry_pmd:
 	ptl = pmd_trans_huge_lock(pmd, vma);
 	if (ptl) {
 		if (mc.precharge < HPAGE_PMD_NR) {
@@ -1227,6 +1231,27 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 		target_type = get_mctgt_type_thp(vma, addr, *pmd, &target);
 		if (target_type == MC_TARGET_PAGE) {
 			folio = target.folio;
+			/*
+			 * Deferred split queue locking depends on memcg,
+			 * and unqueue is unsafe unless folio refcount is 0:
+			 * split or skip if on the queue? first try to split.
+			 */
+			if (!list_empty(&folio->_deferred_list)) {
+				spin_unlock(ptl);
+				if (!tried_split_before)
+					split_folio(folio);
+				folio_unlock(folio);
+				folio_put(folio);
+				if (tried_split_before)
+					return 0;
+				tried_split_before = true;
+				goto retry_pmd;
+			}
+			/*
+			 * So long as that pmd lock is held, the folio cannot
+			 * be racily added to the _deferred_list, because
+			 * __folio_remove_rmap() will find !partially_mapped.
+			 */
 			if (folio_isolate_lru(folio)) {
 				if (!mem_cgroup_move_account(folio, true,
 							     mc.from, mc.to)) {

mm/memcontrol.c

@@ -4629,10 +4629,6 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug)
 	struct obj_cgroup *objcg;
 
 	VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
-	VM_BUG_ON_FOLIO(folio_order(folio) > 1 &&
-			!folio_test_hugetlb(folio) &&
-			!list_empty(&folio->_deferred_list) &&
-			folio_test_partially_mapped(folio), folio);
 
 	/*
 	 * Nobody should be changing or seriously looking at
@@ -4679,6 +4675,7 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug)
 			ug->nr_memory += nr_pages;
 		ug->pgpgout++;
 
+		WARN_ON_ONCE(folio_unqueue_deferred_split(folio));
 		folio->memcg_data = 0;
 	}
 
@@ -4790,6 +4787,9 @@ void mem_cgroup_migrate(struct folio *old, struct folio *new)
 
 	/* Transfer the charge and the css ref */
 	commit_charge(new, memcg);
+
+	/* Warning should never happen, so don't worry about refcount non-0 */
+	WARN_ON_ONCE(folio_unqueue_deferred_split(old));
 	old->memcg_data = 0;
 }
 
@@ -4976,6 +4976,7 @@ void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry)
 	VM_BUG_ON_FOLIO(oldid, folio);
 	mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries);
 
+	folio_unqueue_deferred_split(folio);
 	folio->memcg_data = 0;
 
 	if (!mem_cgroup_is_root(memcg))