30 files changed, 329 insertions, 172 deletions

diff --git a/.mailmap b/.mailmap
index 5378f04b2566..5e829da09e7f 100644
--- a/.mailmap
+++ b/.mailmap
@@ -665,6 +665,7 @@ Tomeu Vizoso <tomeu@tomeuvizoso.net> <tomeu.vizoso@collabora.com>
 Thomas Graf <tgraf@suug.ch>
 Thomas Körper <socketcan@esd.eu> <thomas.koerper@esd.eu>
 Thomas Pedersen <twp@codeaurora.org>
+Thorsten Blum <thorsten.blum@linux.dev> <thorsten.blum@toblux.com>
 Tiezhu Yang <yangtiezhu@loongson.cn> <kernelpatch@126.com>
 Tingwei Zhang <quic_tingwei@quicinc.com> <tingwei@codeaurora.org>
 Tirupathi Reddy <quic_tirupath@quicinc.com> <tirupath@codeaurora.org>
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 1518343bbe22..1666576acc0e 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -6688,7 +6688,7 @@
 			0: no polling (default)
 
 	thp_anon=	[KNL]
-			Format: <size>,<size>[KMG]:<state>;<size>-<size>[KMG]:<state>
+			Format: <size>[KMG],<size>[KMG]:<state>;<size>[KMG]-<size>[KMG]:<state>
 			state is one of "always", "madvise", "never" or "inherit".
 			Control the default behavior of the system with respect
 			to anonymous transparent hugepages.
diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
index cfdd16a52e39..a1bb495eab59 100644
--- a/Documentation/admin-guide/mm/transhuge.rst
+++ b/Documentation/admin-guide/mm/transhuge.rst
@@ -303,7 +303,7 @@ control by passing the parameter ``transparent_hugepage=always`` or
 kernel command line.
 
 Alternatively, each supported anonymous THP size can be controlled by
-passing ``thp_anon=<size>,<size>[KMG]:<state>;<size>-<size>[KMG]:<state>``,
+passing ``thp_anon=<size>[KMG],<size>[KMG]:<state>;<size>[KMG]-<size>[KMG]:<state>``,
 where ``<size>`` is the THP size (must be a power of 2 of PAGE_SIZE and
 supported anonymous THP)  and ``<state>`` is one of ``always``, ``madvise``,
 ``never`` or ``inherit``.
diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h
index 9e39217b4afb..798d965760d4 100644
--- a/arch/arm64/include/asm/mman.h
+++ b/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)
diff --git a/arch/parisc/include/asm/mman.h b/arch/parisc/include/asm/mman.h
index 89b6beeda0b8..663f587dc789 100644
--- a/arch/parisc/include/asm/mman.h
+++ b/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__ */
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index dd0a05365e79..73a6f6fd8a8e 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -2036,8 +2036,7 @@ static int ocfs2_xa_remove(struct ocfs2_xa_loc *loc,
 				rc = 0;
 			ocfs2_xa_cleanup_value_truncate(loc, "removing",
 							orig_clusters);
-			if (rc)
-				goto out;
+			goto out;
 		}
 	}
 
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index b52d85f8ad59..b4521b096058 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -457,10 +457,6 @@ static vm_fault_t mmap_vmcore_fault(struct vm_fault *vmf)
 #endif
 }
 
-static const struct vm_operations_struct vmcore_mmap_ops = {
-	.fault = mmap_vmcore_fault,
-};
-
 /**
  * vmcore_alloc_buf - allocate buffer in vmalloc memory
  * @size: size of buffer
@@ -488,6 +484,11 @@ static inline char *vmcore_alloc_buf(size_t size)
  * virtually contiguous user-space in ELF layout.
  */
 #ifdef CONFIG_MMU
+
+static const struct vm_operations_struct vmcore_mmap_ops = {
+	.fault = mmap_vmcore_fault,
+};
+
 /*
  * remap_oldmem_pfn_checked - do remap_oldmem_pfn_range replacing all pages
  * reported as not being ram with the zero page.
diff --git a/include/linux/mman.h b/include/linux/mman.h
index bcb201ab7a41..a842783ffa62 100644
--- a/include/linux/mman.h
+++ b/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;
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 5b1c984daf45..80bc5640bb60 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -823,6 +823,7 @@ struct zone {
 	unsigned long watermark_boost;
 
 	unsigned long nr_reserved_highatomic;
+	unsigned long nr_free_highatomic;
 
 	/*
 	 * We don't know if the memory that we're going to allocate will be
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 3625096d5f85..7183e5aca282 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -141,7 +141,8 @@ static inline long get_rlimit_value(struct ucounts *ucounts, enum rlimit_type ty
 
 long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v);
 bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v);
-long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type);
+long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type,
+			    bool override_rlimit);
 void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type);
 bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long max);
 
diff --git a/kernel/signal.c b/kernel/signal.c
index 4344860ffcac..cbabb2d05e0a 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -419,7 +419,8 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags,
 	 */
 	rcu_read_lock();
 	ucounts = task_ucounts(t);
-	sigpending = inc_rlimit_get_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING);
+	sigpending = inc_rlimit_get_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING,
+					    override_rlimit);
 	rcu_read_unlock();
 	if (!sigpending)
 		return NULL;
diff --git a/kernel/ucount.c b/kernel/ucount.c
index 8c07714ff27d..696406939be5 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -307,7 +307,8 @@ void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type)
 	do_dec_rlimit_put_ucounts(ucounts, NULL, type);
 }
 
-long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type)
+long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type,
+			    bool override_rlimit)
 {
 	/* Caller must hold a reference to ucounts */
 	struct ucounts *iter;
@@ -317,10 +318,11 @@ long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type)
 	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
 		long new = atomic_long_add_return(1, &iter->rlimit[type]);
 		if (new < 0 || new > max)
-			goto unwind;
+			goto dec_unwind;
 		if (iter == ucounts)
 			ret = new;
-		max = get_userns_rlimit_max(iter->ns, type);
+		if (!override_rlimit)
+			max = get_userns_rlimit_max(iter->ns, type);
 		/*
 		 * Grab an extra ucount reference for the caller when
 		 * the rlimit count was previously 0.
@@ -334,7 +336,6 @@ long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type)
 dec_unwind:
 	dec = atomic_long_sub_return(1, &iter->rlimit[type]);
 	WARN_ON_ONCE(dec < 0);
-unwind:
 	do_dec_rlimit_put_ucounts(ucounts, iter, type);
 	return 0;
 }
diff --git a/lib/objpool.c b/lib/objpool.c
index fd108fe0d095..b998b720c732 100644
--- a/lib/objpool.c
+++ b/lib/objpool.c
@@ -74,15 +74,21 @@ objpool_init_percpu_slots(struct objpool_head *pool, int nr_objs,
 		 * warm caches and TLB hits. in default vmalloc is used to
 		 * reduce the pressure of kernel slab system. as we know,
 		 * mimimal size of vmalloc is one page since vmalloc would
-		 * always align the requested size to page size
+		 * always align the requested size to page size.
+		 * but if vmalloc fails or it is not available (e.g. GFP_ATOMIC)
+		 * allocate percpu slot with kmalloc.
 		 */
-		if ((pool->gfp & GFP_ATOMIC) == GFP_ATOMIC)
-			slot = kmalloc_node(size, pool->gfp, cpu_to_node(i));
-		else
+		slot = NULL;
+
+		if ((pool->gfp & (GFP_ATOMIC | GFP_KERNEL)) != GFP_ATOMIC)
 			slot = __vmalloc_node(size, sizeof(void *), pool->gfp,
 				cpu_to_node(i), __builtin_return_address(0));
-		if (!slot)
-			return -ENOMEM;
+
+		if (!slot) {
+			slot = kmalloc_node(size, pool->gfp, cpu_to_node(i));
+			if (!slot)
+				return -ENOMEM;
+		}
 		memset(slot, 0, size);
 		pool->cpu_slots[i] = slot;
 
diff --git a/mm/damon/core.c b/mm/damon/core.c
index a83f3b736d51..511c3f61ab44 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -1412,7 +1412,7 @@ static void damon_do_apply_schemes(struct damon_ctx *c,
 	damon_for_each_scheme(s, c) {
 		struct damos_quota *quota = &s->quota;
 
-		if (c->passed_sample_intervals != s->next_apply_sis)
+		if (c->passed_sample_intervals < s->next_apply_sis)
 			continue;
 
 		if (!s->wmarks.activated)
@@ -1456,17 +1456,31 @@ static unsigned long damon_feed_loop_next_input(unsigned long last_input,
 		unsigned long score)
 {
 	const unsigned long goal = 10000;
-	unsigned long score_goal_diff = max(goal, score) - min(goal, score);
-	unsigned long score_goal_diff_bp = score_goal_diff * 10000 / goal;
-	unsigned long compensation = last_input * score_goal_diff_bp / 10000;
 	/* Set minimum input as 10000 to avoid compensation be zero */
 	const unsigned long min_input = 10000;
+	unsigned long score_goal_diff, compensation;
+	bool over_achieving = score > goal;
 
-	if (goal > score)
+	if (score == goal)
+		return last_input;
+	if (score >= goal * 2)
+		return min_input;
+
+	if (over_achieving)
+		score_goal_diff = score - goal;
+	else
+		score_goal_diff = goal - score;
+
+	if (last_input < ULONG_MAX / score_goal_diff)
+		compensation = last_input * score_goal_diff / goal;
+	else
+		compensation = last_input / goal * score_goal_diff;
+
+	if (over_achieving)
+		return max(last_input - compensation, min_input);
+	if (last_input < ULONG_MAX - compensation)
 		return last_input + compensation;
-	if (last_input > compensation + min_input)
-		return last_input - compensation;
-	return min_input;
+	return ULONG_MAX;
 }
 
 #ifdef CONFIG_PSI
@@ -1622,7 +1636,7 @@ static void kdamond_apply_schemes(struct damon_ctx *c)
 	bool has_schemes_to_apply = false;
 
 	damon_for_each_scheme(s, c) {
-		if (c->passed_sample_intervals != s->next_apply_sis)
+		if (c->passed_sample_intervals < s->next_apply_sis)
 			continue;
 
 		if (!s->wmarks.activated)
@@ -1642,9 +1656,9 @@ static void kdamond_apply_schemes(struct damon_ctx *c)
 	}
 
 	damon_for_each_scheme(s, c) {
-		if (c->passed_sample_intervals != s->next_apply_sis)
+		if (c->passed_sample_intervals < s->next_apply_sis)
 			continue;
-		s->next_apply_sis +=
+		s->next_apply_sis = c->passed_sample_intervals +
 			(s->apply_interval_us ? s->apply_interval_us :
 			 c->attrs.aggr_interval) / sample_interval;
 	}
@@ -2000,7 +2014,7 @@ static int kdamond_fn(void *data)
 		if (ctx->ops.check_accesses)
 			max_nr_accesses = ctx->ops.check_accesses(ctx);
 
-		if (ctx->passed_sample_intervals == next_aggregation_sis) {
+		if (ctx->passed_sample_intervals >= next_aggregation_sis) {
 			kdamond_merge_regions(ctx,
 					max_nr_accesses / 10,
 					sz_limit);
@@ -2018,7 +2032,7 @@ static int kdamond_fn(void *data)
 
 		sample_interval = ctx->attrs.sample_interval ?
 			ctx->attrs.sample_interval : 1;
-		if (ctx->passed_sample_intervals == next_aggregation_sis) {
+		if (ctx->passed_sample_intervals >= next_aggregation_sis) {
 			ctx->next_aggregation_sis = next_aggregation_sis +
 				ctx->attrs.aggr_interval / sample_interval;
 
@@ -2028,7 +2042,7 @@ static int kdamond_fn(void *data)
 				ctx->ops.reset_aggregated(ctx);
 		}
 
-		if (ctx->passed_sample_intervals == next_ops_update_sis) {
+		if (ctx->passed_sample_intervals >= next_ops_update_sis) {
 			ctx->next_ops_update_sis = next_ops_update_sis +
 				ctx->attrs.ops_update_interval /
 				sample_interval;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2fb328880b50..03fd4bc39ea1 100644
--- a/mm/huge_memory.c
+++ b/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 @@ next:
 		 */
 		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.
diff --git a/mm/internal.h b/mm/internal.h
index 93083bbeeefa..64c2eb0b160e 100644
--- a/mm/internal.h
+++ b/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(). */
@@ -639,11 +684,11 @@ 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
@@ -651,9 +696,9 @@ static inline void folio_undo_large_rmappable(struct folio *folio)
 	 * 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)
diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c
index 81d8819f13cd..f8744f5630bb 100644
--- a/mm/memcontrol-v1.c
+++ b/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)) {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 7845c64a2c57..06df2af97415 100644
--- a/mm/memcontrol.c
+++ b/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))
diff --git a/mm/migrate.c b/mm/migrate.c
index fab84a776088..dfa24e41e8f9 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -490,7 +490,7 @@ static int __folio_migrate_mapping(struct address_space *mapping,
 		    folio_test_large_rmappable(folio)) {
 			if (!folio_ref_freeze(folio, expected_count))
 				return -EAGAIN;
-			folio_undo_large_rmappable(folio);
+			folio_unqueue_deferred_split(folio);
 			folio_ref_unfreeze(folio, expected_count);
 		}
 
@@ -515,7 +515,7 @@ static int __folio_migrate_mapping(struct address_space *mapping,
 	}
 
 	/* Take off deferred split queue while frozen and memcg set */
-	folio_undo_large_rmappable(folio);
+	folio_unqueue_deferred_split(folio);
 
 	/*
 	 * Now we know that no one else is looking at the folio:
diff --git a/mm/mlock.c b/mm/mlock.c
index e3e3dc2b2956..cde076fa7d5e 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -725,14 +725,17 @@ static int apply_mlockall_flags(int flags)
 	}
 
 	for_each_vma(vmi, vma) {
+		int error;
 		vm_flags_t newflags;
 
 		newflags = vma->vm_flags & ~VM_LOCKED_MASK;
 		newflags |= to_add;
 
-		/* Ignore errors */
-		mlock_fixup(&vmi, vma, &prev, vma->vm_start, vma->vm_end,
-			    newflags);
+		error = mlock_fixup(&vmi, vma, &prev, vma->vm_start, vma->vm_end,
+				    newflags);
+		/* Ignore errors, but prev needs fixing up. */
+		if (error)
+			prev = vma;
 		cond_resch