Merge tag 'mm-hotfixes-stable-2025-05-10-14-23' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc hotfixes from Andrew Morton:
"22 hotfixes. 13 are cc:stable and the remainder address post-6.14
issues or aren't considered necessary for -stable kernels.

About half are for MM. Five OCFS2 fixes and a few MAINTAINERS updates"

* tag 'mm-hotfixes-stable-2025-05-10-14-23' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (22 commits)
mm: fix folio_pte_batch() on XEN PV
nilfs2: fix deadlock warnings caused by lock dependency in init_nilfs()
mm/hugetlb: copy the CMA flag when demoting
mm, swap: fix false warning for large allocation with !THP_SWAP
selftests/mm: fix a build failure on powerpc
selftests/mm: fix build break when compiling pkey_util.c
mm: vmalloc: support more granular vrealloc() sizing
tools/testing/selftests: fix guard region test tmpfs assumption
ocfs2: stop quota recovery before disabling quotas
ocfs2: implement handshaking with ocfs2 recovery thread
ocfs2: switch osb->disable_recovery to enum
mailmap: map Uwe's BayLibre addresses to a single one
MAINTAINERS: add mm THP section
mm/userfaultfd: fix uninitialized output field for -EAGAIN race
selftests/mm: compaction_test: support platform with huge mount of memory
MAINTAINERS: add core mm section
ocfs2: fix panic in failed foilio allocation
mm/huge_memory: fix dereferencing invalid pmd migration entry
MAINTAINERS: add reverse mapping section
x86: disable image size check for test builds
...

.mailmap

···
 Luca Weiss <[e-mail]> <[e-mail]>
 Lukasz Luba <[e-mail]> <[e-mail]>
 Luo Jie <[e-mail]> <[e-mail]>
+Lance Yang <[e-mail]> <[e-mail]>
+Lance Yang <[e-mail]> <[e-mail]>
 Maciej W. Rozycki <[e-mail]> <[e-mail]>
 Maciej W. Rozycki <[e-mail]> <[e-mail]>
 Maharaja Kennadyrajan <[e-mail]> <[e-mail]>
···
 Tycho Andersen <[e-mail]> <[e-mail]>
 Tzung-Bi Shih <[e-mail]> <[e-mail]>
 Uwe Kleine-König <[e-mail]>
+Uwe Kleine-König <[e-mail]> <[e-mail]>
 Uwe Kleine-König <[e-mail]>
 Uwe Kleine-König <[e-mail]>
 Uwe Kleine-König <[e-mail]>

MAINTAINERS

···
 F:	include/linux/gfp.h
 F:	include/linux/gfp_types.h
 F:	include/linux/memfd.h
-F:	include/linux/memory.h
 F:	include/linux/memory_hotplug.h
 F:	include/linux/memory-tiers.h
 F:	include/linux/mempolicy.h
 F:	include/linux/mempool.h
 F:	include/linux/memremap.h
-F:	include/linux/mm.h
-F:	include/linux/mm_*.h
 F:	include/linux/mmzone.h
 F:	include/linux/mmu_notifier.h
 F:	include/linux/pagewalk.h
-F:	include/linux/rmap.h
 F:	include/trace/events/ksm.h
 F:	mm/
 F:	tools/mm/
 F:	tools/testing/selftests/mm/
 N:	include/linux/page[-_]*
+
+MEMORY MANAGEMENT - CORE
+M:	Andrew Morton <[e-mail]>
+M:	David Hildenbrand <[e-mail]>
+R:	Lorenzo Stoakes <[e-mail]>
+R:	Liam R. Howlett <[e-mail]>
+R:	Vlastimil Babka <[e-mail]>
+R:	Mike Rapoport <[e-mail]>
+R:	Suren Baghdasaryan <[e-mail]>
+R:	Michal Hocko <[e-mail]>
+L:	[e-mail]
+S:	Maintained
+W:	http://www.linux-mm.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F:	include/linux/memory.h
+F:	include/linux/mm.h
+F:	include/linux/mm_*.h
+F:	include/linux/mmdebug.h
+F:	include/linux/pagewalk.h
+F:	mm/Kconfig
+F:	mm/debug.c
+F:	mm/init-mm.c
+F:	mm/memory.c
+F:	mm/pagewalk.c
+F:	mm/util.c
 
 MEMORY MANAGEMENT - EXECMEM
 M:	Andrew Morton <[e-mail]>
···
 F:	include/linux/gfp.h
 F:	include/linux/compaction.h
 
+MEMORY MANAGEMENT - RMAP (REVERSE MAPPING)
+M:	Andrew Morton <[e-mail]>
+M:	David Hildenbrand <[e-mail]>
+M:	Lorenzo Stoakes <[e-mail]>
+R:	Rik van Riel <[e-mail]>
+R:	Liam R. Howlett <[e-mail]>
+R:	Vlastimil Babka <[e-mail]>
+R:	Harry Yoo <[e-mail]>
+L:	[e-mail]
+S:	Maintained
+F:	include/linux/rmap.h
+F:	mm/rmap.c
+
 MEMORY MANAGEMENT - SECRETMEM
 M:	Andrew Morton <[e-mail]>
 M:	Mike Rapoport <[e-mail]>
···
 S:	Maintained
 F:	include/linux/secretmem.h
 F:	mm/secretmem.c
+
+MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE)
+M:	Andrew Morton <[e-mail]>
+M:	David Hildenbrand <[e-mail]>
+R:	Zi Yan <[e-mail]>
+R:	Baolin Wang <[e-mail]>
+R:	Lorenzo Stoakes <[e-mail]>
+R:	Liam R. Howlett <[e-mail]>
+R:	Nico Pache <[e-mail]>
+R:	Ryan Roberts <[e-mail]>
+R:	Dev Jain <[e-mail]>
+L:	[e-mail]
+S:	Maintained
+W:	http://www.linux-mm.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F:	Documentation/admin-guide/mm/transhuge.rst
+F:	include/linux/huge_mm.h
+F:	include/linux/khugepaged.h
+F:	include/trace/events/huge_memory.h
+F:	mm/huge_memory.c
+F:	mm/khugepaged.c
+F:	tools/testing/selftests/mm/khugepaged.c
+F:	tools/testing/selftests/mm/split_huge_page_test.c
+F:	tools/testing/selftests/mm/transhuge-stress.c
 
 MEMORY MANAGEMENT - USERFAULTFD
 M:	Andrew Morton <[e-mail]>

arch/x86/kernel/vmlinux.lds.S

···
 }
 
 /*
- * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility:
+ * COMPILE_TEST kernels can be large - CONFIG_KASAN, for example, can cause
+ * this.  Let's assume that nobody will be running a COMPILE_TEST kernel and
+ * let's assert that fuller build coverage is more valuable than being able to
+ * run a COMPILE_TEST kernel.
+ */
+#ifndef CONFIG_COMPILE_TEST
+/*
+ * The ASSERT() sync to . is intentional, for binutils 2.14 compatibility:
  */
 . = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
 	   "kernel image bigger than KERNEL_IMAGE_SIZE");
+#endif
 
 /* needed for Clang - see arch/x86/entry/entry.S */
 PROVIDE(__ref_stack_chk_guard = __stack_chk_guard);

fs/nilfs2/the_nilfs.c

···
 	int blocksize;
 	int err;
 
-	down_write(&nilfs->ns_sem);
-
 	blocksize = sb_min_blocksize(sb, NILFS_MIN_BLOCK_SIZE);
 	if (!blocksize) {
 		nilfs_err(sb, "unable to set blocksize");
···
 	set_nilfs_init(nilfs);
 	err = 0;
  out:
-	up_write(&nilfs->ns_sem);
 	return err;
 
  failed_sbh:

fs/ocfs2/alloc.c

···
 		if (IS_ERR(folios[numfolios])) {
 			ret = PTR_ERR(folios[numfolios]);
 			mlog_errno(ret);
+			folios[numfolios] = NULL;
 			goto out;
 		}
 

fs/ocfs2/journal.c

···
 	struct ocfs2_recovery_map *rm;
 
 	mutex_init(&osb->recovery_lock);
-	osb->disable_recovery = 0;
+	osb->recovery_state = OCFS2_REC_ENABLED;
 	osb->recovery_thread_task = NULL;
 	init_waitqueue_head(&osb->recovery_event);
 
···
 	return 0;
 }
 
-/* we can't grab the goofy sem lock from inside wait_event, so we use
- * memory barriers to make sure that we'll see the null task before
- * being woken up */
 static int ocfs2_recovery_thread_running(struct ocfs2_super *osb)
 {
-	mb();
 	return osb->recovery_thread_task != NULL;
+}
+
+static void ocfs2_recovery_disable(struct ocfs2_super *osb,
+				   enum ocfs2_recovery_state state)
+{
+	mutex_lock(&osb->recovery_lock);
+	/*
+	 * If recovery thread is not running, we can directly transition to
+	 * final state.
+	 */
+	if (!ocfs2_recovery_thread_running(osb)) {
+		osb->recovery_state = state + 1;
+		goto out_lock;
+	}
+	osb->recovery_state = state;
+	/* Wait for recovery thread to acknowledge state transition */
+	wait_event_cmd(osb->recovery_event,
+		       !ocfs2_recovery_thread_running(osb) ||
+				osb->recovery_state >= state + 1,
+		       mutex_unlock(&osb->recovery_lock),
+		       mutex_lock(&osb->recovery_lock));
+out_lock:
+	mutex_unlock(&osb->recovery_lock);
+
+	/*
+	 * At this point we know that no more recovery work can be queued so
+	 * wait for any recovery completion work to complete.
+	 */
+	if (osb->ocfs2_wq)
+		flush_workqueue(osb->ocfs2_wq);
+}
+
+void ocfs2_recovery_disable_quota(struct ocfs2_super *osb)
+{
+	ocfs2_recovery_disable(osb, OCFS2_REC_QUOTA_WANT_DISABLE);
 }
 
 void ocfs2_recovery_exit(struct ocfs2_super *osb)
···
 
 	/* disable any new recovery threads and wait for any currently
 	 * running ones to exit. Do this before setting the vol_state. */
-	mutex_lock(&osb->recovery_lock);
-	osb->disable_recovery = 1;
-	mutex_unlock(&osb->recovery_lock);
-	wait_event(osb->recovery_event, !ocfs2_recovery_thread_running(osb));
-
-	/* At this point, we know that no more recovery threads can be
-	 * launched, so wait for any recovery completion work to
-	 * complete. */
-	if (osb->ocfs2_wq)
-		flush_workqueue(osb->ocfs2_wq);
+	ocfs2_recovery_disable(osb, OCFS2_REC_WANT_DISABLE);
 
 	/*
 	 * Now that recovery is shut down, and the osb is about to be
···
 		}
 	}
 restart:
+	if (quota_enabled) {
+		mutex_lock(&osb->recovery_lock);
+		/* Confirm that recovery thread will no longer recover quotas */
+		if (osb->recovery_state == OCFS2_REC_QUOTA_WANT_DISABLE) {
+			osb->recovery_state = OCFS2_REC_QUOTA_DISABLED;
+			wake_up(&osb->recovery_event);
+		}
+		if (osb->recovery_state >= OCFS2_REC_QUOTA_DISABLED)
+			quota_enabled = 0;
+		mutex_unlock(&osb->recovery_lock);
+	}
+
 	status = ocfs2_super_lock(osb, 1);
 	if (status < 0) {
 		mlog_errno(status);
···
 
 	ocfs2_free_replay_slots(osb);
 	osb->recovery_thread_task = NULL;
-	mb(); /* sync with ocfs2_recovery_thread_running */
+	if (osb->recovery_state == OCFS2_REC_WANT_DISABLE)
+		osb->recovery_state = OCFS2_REC_DISABLED;
 	wake_up(&osb->recovery_event);
 
 	mutex_unlock(&osb->recovery_lock);
 
-	if (quota_enabled)
-		kfree(rm_quota);
+	kfree(rm_quota);
 
 	return status;
 }
 
 void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num)
 {
+	int was_set = -1;
+
 	mutex_lock(&osb->recovery_lock);
+	if (osb->recovery_state < OCFS2_REC_WANT_DISABLE)
+		was_set = ocfs2_recovery_map_set(osb, node_num);
 
 	trace_ocfs2_recovery_thread(node_num, osb->node_num,
-		osb->disable_recovery, osb->recovery_thread_task,
-		osb->disable_recovery ?
-		-1 : ocfs2_recovery_map_set(osb, node_num));
+		osb->recovery_state, osb->recovery_thread_task, was_set);
 
-	if (osb->disable_recovery)
+	if (osb->recovery_state >= OCFS2_REC_WANT_DISABLE)
 		goto out;
 
 	if (osb->recovery_thread_task)

fs/ocfs2/journal.h

···
 
 int ocfs2_recovery_init(struct ocfs2_super *osb);
 void ocfs2_recovery_exit(struct ocfs2_super *osb);
+void ocfs2_recovery_disable_quota(struct ocfs2_super *osb);
 
 int ocfs2_compute_replay_slots(struct ocfs2_super *osb);
 void ocfs2_free_replay_slots(struct ocfs2_super *osb);

fs/ocfs2/ocfs2.h

···
 void ocfs2_initialize_journal_triggers(struct super_block *sb,
 				       struct ocfs2_triggers triggers[]);
 
+enum ocfs2_recovery_state {
+	OCFS2_REC_ENABLED = 0,
+	OCFS2_REC_QUOTA_WANT_DISABLE,
+	/*
+	 * Must be OCFS2_REC_QUOTA_WANT_DISABLE + 1 for
+	 * ocfs2_recovery_disable_quota() to work.
+	 */
+	OCFS2_REC_QUOTA_DISABLED,
+	OCFS2_REC_WANT_DISABLE,
+	/*
+	 * Must be OCFS2_REC_WANT_DISABLE + 1 for ocfs2_recovery_exit() to work
+	 */
+	OCFS2_REC_DISABLED,
+};
+
 struct ocfs2_journal;
 struct ocfs2_slot_info;
 struct ocfs2_recovery_map;
···
 	struct ocfs2_recovery_map *recovery_map;
 	struct ocfs2_replay_map *replay_map;
 	struct task_struct *recovery_thread_task;
-	int disable_recovery;
+	enum ocfs2_recovery_state recovery_state;
 	wait_queue_head_t checkpoint_event;
 	struct ocfs2_journal *journal;
 	unsigned long osb_commit_interval;

fs/ocfs2/quota_local.c

···
 
 /* Sync changes in local quota file into global quota file and
  * reinitialize local quota file.
- * The function expects local quota file to be already locked and
- * s_umount locked in shared mode. */
+ * The function expects local quota file to be already locked. */
 static int ocfs2_recover_local_quota_file(struct inode *lqinode,
 					  int type,
 					  struct ocfs2_quota_recovery *rec)
···
 {
 	unsigned int ino[OCFS2_MAXQUOTAS] = { LOCAL_USER_QUOTA_SYSTEM_INODE,
 					      LOCAL_GROUP_QUOTA_SYSTEM_INODE };
-	struct super_block *sb = osb->sb;
 	struct ocfs2_local_disk_dqinfo *ldinfo;
 	struct buffer_head *bh;
 	handle_t *handle;
···
 	printk(KERN_NOTICE "ocfs2: Finishing quota recovery on device (%s) for "
 	       "slot %u\n", osb->dev_str, slot_num);
 
-	down_read(&sb->s_umount);
 	for (type = 0; type < OCFS2_MAXQUOTAS; type++) {
 		if (list_empty(&(rec->r_list[type])))
 			continue;
···
 			break;
 	}
 out:
-	up_read(&sb->s_umount);
 	kfree(rec);
 	return status;
 }
···
 	ocfs2_release_local_quota_bitmaps(&oinfo->dqi_chunk);
 
 	/*
-	 * s_umount held in exclusive mode protects us against racing with
-	 * recovery thread...
+	 * ocfs2_dismount_volume() has already aborted quota recovery...
 	 */
 	if (oinfo->dqi_rec) {
 		ocfs2_free_quota_recovery(oinfo->dqi_rec);

fs/ocfs2/suballoc.c

···
 
 	bg_bh = ocfs2_block_group_alloc_contig(osb, handle, alloc_inode,
 					       ac, cl);
-	if (PTR_ERR(bg_bh) == -ENOSPC)
+	if (PTR_ERR(bg_bh) == -ENOSPC) {
+		ac->ac_which = OCFS2_AC_USE_MAIN_DISCONTIG;
 		bg_bh = ocfs2_block_group_alloc_discontig(handle,
 							  alloc_inode,
 							  ac, cl);
+	}
 	if (IS_ERR(bg_bh)) {
 		status = PTR_ERR(bg_bh);
 		bg_bh = NULL;
···
 {
 	int status;
 	u16 chain;
+	u32 contig_bits;
 	u64 next_group;
 	struct inode *alloc_inode = ac->ac_inode;
 	struct buffer_head *group_bh = NULL;
···
 	status = -ENOSPC;
 	/* for now, the chain search is a bit simplistic. We just use
 	 * the 1st group with any empty bits. */
-	while ((status = ac->ac_group_search(alloc_inode, group_bh,
-					     bits_wanted, min_bits,
-					     ac->ac_max_block,
-					     res)) == -ENOSPC) {
+	while (1) {
+		if (ac->ac_which == OCFS2_AC_USE_MAIN_DISCONTIG) {
+			contig_bits = le16_to_cpu(bg->bg_contig_free_bits);
+			if (!contig_bits)
+				contig_bits = ocfs2_find_max_contig_free_bits(bg->bg_bitmap,
+						le16_to_cpu(bg->bg_bits), 0);
+			if (bits_wanted > contig_bits && contig_bits >= min_bits)
+				bits_wanted = contig_bits;
+		}
+
+		status = ac->ac_group_search(alloc_inode, group_bh,
+				bits_wanted, min_bits,
+				ac->ac_max_block, res);
+		if (status != -ENOSPC)
+			break;
 		if (!bg->bg_next_group)
 			break;
 
···
 	victim = ocfs2_find_victim_chain(cl);
 	ac->ac_chain = victim;
 
+search:
 	status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits,
 				    res, &bits_left);
 	if (!status) {
···
 			mlog_errno(status);
 			goto bail;
 		}
+	}
+
+	/* Chains can't supply the bits_wanted contiguous space.
+	 * We should switch to using every single bit when allocating
+	 * from the global bitmap. */
+	if (i == le16_to_cpu(cl->cl_next_free_rec) &&
+	    status == -ENOSPC && ac->ac_which == OCFS2_AC_USE_MAIN) {
+		ac->ac_which = OCFS2_AC_USE_MAIN_DISCONTIG;
+		ac->ac_chain = victim;
+		goto search;
 	}
 
 set_hint:
···
 	BUG_ON(ac->ac_bits_given >= ac->ac_bits_wanted);
 
 	BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL
-	       && ac->ac_which != OCFS2_AC_USE_MAIN);
+	       && ac->ac_which != OCFS2_AC_USE_MAIN
+	       && ac->ac_which != OCFS2_AC_USE_MAIN_DISCONTIG);
 
 	if (ac->ac_which == OCFS2_AC_USE_LOCAL) {
 		WARN_ON(min_clusters > 1);

fs/ocfs2/suballoc.h

···
 #define OCFS2_AC_USE_MAIN  2
 #define OCFS2_AC_USE_INODE 3
 #define OCFS2_AC_USE_META  4
+#define OCFS2_AC_USE_MAIN_DISCONTIG  5
 	u32    ac_which;
 
 	/* these are used by the chain search */

fs/ocfs2/super.c

···
 	/* Orphan scan should be stopped as early as possible */
 	ocfs2_orphan_scan_stop(osb);
 
+	/* Stop quota recovery so that we can disable quotas */
+	ocfs2_recovery_disable_quota(osb);
+
 	ocfs2_disable_quotas(osb);
 
 	/* All dquots should be freed by now */

fs/userfaultfd.c

···
 	user_uffdio_copy = (struct uffdio_copy __user *) arg;
 
 	ret = -EAGAIN;
-	if (atomic_read(&ctx->mmap_changing))
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
+			return -EFAULT;
 		goto out;
+	}
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_copy, user_uffdio_copy,
···
 	user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg;
 
 	ret = -EAGAIN;
-	if (atomic_read(&ctx->mmap_changing))
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
+			return -EFAULT;
 		goto out;
+	}
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage,
···
 	user_uffdio_continue = (struct uffdio_continue __user *)arg;
 
 	ret = -EAGAIN;
-	if (atomic_read(&ctx->mmap_changing))
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_continue->mapped)))
+			return -EFAULT;
 		goto out;
+	}
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_continue, user_uffdio_continue,
···
 	user_uffdio_poison = (struct uffdio_poison __user *)arg;
 
 	ret = -EAGAIN;
-	if (atomic_read(&ctx->mmap_changing))
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_poison->updated)))
+			return -EFAULT;
 		goto out;
+	}
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_poison, user_uffdio_poison,
···
 
 	user_uffdio_move = (struct uffdio_move __user *) arg;
 
-	if (atomic_read(&ctx->mmap_changing))
-		return -EAGAIN;
+	ret = -EAGAIN;
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_move->move)))
+			return -EFAULT;
+		goto out;
+	}
 
 	if (copy_from_user(&uffdio_move, user_uffdio_move,
 			   /* don't copy "move" last field */

include/linux/vmalloc.h

···
 	unsigned int		nr_pages;
 	phys_addr_t		phys_addr;
 	const void		*caller;
+	unsigned long		requested_size;
 };
 
 struct vmap_area {

mm/huge_memory.c

···
 void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
 			   pmd_t *pmd, bool freeze, struct folio *folio)
 {
+	bool pmd_migration = is_pmd_migration_entry(*pmd);
+
 	VM_WARN_ON_ONCE(folio && !folio_test_pmd_mappable(folio));
 	VM_WARN_ON_ONCE(!IS_ALIGNED(address, HPAGE_PMD_SIZE));
 	VM_WARN_ON_ONCE(folio && !folio_test_locked(folio));
···
 	 * require a folio to check the PMD against. Otherwise, there
 	 * is a risk of replacing the wrong folio.
 	 */
-	if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) ||
-	    is_pmd_migration_entry(*pmd)) {
-		if (folio && folio != pmd_folio(*pmd))
+	if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || pmd_migration) {
+		/*
+		 * Do not apply pmd_folio() to a migration entry; and folio lock
+		 * guarantees that it must be of the wrong folio anyway.
+		 */
+		if (folio && (pmd_migration || folio != pmd_folio(*pmd)))
 			return;
 		__split_huge_pmd_locked(vma, pmd, address, freeze);
 	}

mm/hugetlb.c

···
 
 	list_for_each_entry_safe(folio, next, src_list, lru) {
 		int i;
+		bool cma;
 
 		if (folio_test_hugetlb_vmemmap_optimized(folio))
 			continue;
+
+		cma = folio_test_hugetlb_cma(folio);
 
 		list_del(&folio->lru);
 
···
 
 			new_folio->mapping = NULL;
 			init_new_hugetlb_folio(dst, new_folio);
+			/* Copy the CMA flag so that it is freed correctly */
+			if (cma)
+				folio_set_hugetlb_cma(new_folio);
 			list_add(&new_folio->lru, &dst_list);
 		}
 	}

mm/internal.h

···
 		pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags,
 		bool *any_writable, bool *any_young, bool *any_dirty)
 {
-	unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio);
-	const pte_t *end_ptep = start_ptep + max_nr;
 	pte_t expected_pte, *ptep;
 	bool writable, young, dirty;
-	int nr;
+	int nr, cur_nr;
 
 	if (any_writable)
 		*any_writable = false;
···
 	VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio);
 	VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio);
 
+	/* Limit max_nr to the actual remaining PFNs in the folio we could batch. */
+	max_nr = min_t(unsigned long, max_nr,
+		       folio_pfn(folio) + folio_nr_pages(folio) - pte_pfn(pte));
+
 	nr = pte_batch_hint(start_ptep, pte);
 	expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags);
 	ptep = start_ptep + nr;
 
-	while (ptep < end_ptep) {
+	while (nr < max_nr) {
 		pte = ptep_get(ptep);
 		if (any_writable)
 			writable = !!pte_write(pte);
···
 		if (!pte_same(pte, expected_pte))
 			break;
 
-		/*
-		 * Stop immediately once we reached the end of the folio. In
-		 * corner cases the next PFN might fall into a different
-		 * folio.
-		 */
-		if (pte_pfn(pte) >= folio_end_pfn)
-			break;
-
 		if (any_writable)
 			*any_writable |= writable;
 		if (any_young)
···
 		if (any_dirty)
 			*any_dirty |= dirty;
 
-		nr = pte_batch_hint(ptep, pte);
-		expected_pte = pte_advance_pfn(expected_pte, nr);
-		ptep += nr;
+		cur_nr = pte_batch_hint(ptep, pte);
+		expected_pte = pte_advance_pfn(expected_pte, cur_nr);
+		ptep += cur_nr;
+		nr += cur_nr;
 	}
 
-	return min(ptep - start_ptep, max_nr);
+	return min(nr, max_nr);
 }
 
 /**

mm/swapfile.c

···
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 	VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio);
 
-	/*
-	 * Should not even be attempting large allocations when huge
-	 * page swap is disabled. Warn and fail the allocation.
-	 */
-	if (order && (!IS_ENABLED(CONFIG_THP_SWAP) || size > SWAPFILE_CLUSTER)) {
-		VM_WARN_ON_ONCE(1);
-		return -EINVAL;
+	if (order) {
+		/*
+		 * Reject large allocation when THP_SWAP is disabled,
+		 * the caller should split the folio and try again.
+		 */
+		if (!IS_ENABLED(CONFIG_THP_SWAP))
+			return -EAGAIN;
+
+		/*
+		 * Allocation size should never exceed cluster size
+		 * (HPAGE_PMD_SIZE).
+		 */
+		if (size > SWAPFILE_CLUSTER) {
+			VM_WARN_ON_ONCE(1);
+			return -EINVAL;
+		}
 	}
 
 	local_lock(&percpu_swap_cluster.lock);

mm/vmalloc.c

···
 {
 	vm->flags = flags;
 	vm->addr = (void *)va->va_start;
-	vm->size = va_size(va);
+	vm->size = vm->requested_size = va_size(va);
 	vm->caller = caller;
 	va->vm = vm;
 }
···
 
 	area->flags = flags;
 	area->caller = caller;
+	area->requested_size = requested_size;
 
 	va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area);
 	if (IS_ERR(va)) {
···
  */
 void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
 {
+	struct vm_struct *vm = NULL;
+	size_t alloced_size = 0;
 	size_t old_size = 0;
 	void *n;
 
···
 	}
 
 	if (p) {
-		struct vm_struct *vm;
-
 		vm = find_vm_area(p);
 		if (unlikely(!vm)) {
 			WARN(1, "Trying to vrealloc() nonexistent vm area (%p)\n", p);
 			return NULL;
 		}
 
-		old_size = get_vm_area_size(vm);
+		alloced_size = get_vm_area_size(vm);
+		old_size = vm->requested_size;
+		if (WARN(alloced_size < old_size,
+			 "vrealloc() has mismatched area vs requested sizes (%p)\n", p))
+			return NULL;
 	}
 
 	/*
···
 	 * would be a good heuristic for when to shrink the vm_area?
 	 */
 	if (size <= old_size) {
-		/* Zero out spare memory. */
-		if (want_init_on_alloc(flags))
+		/* Zero out "freed" memory. */
+		if (want_init_on_free())
 			memset((void *)p + size, 0, old_size - size);
+		vm->requested_size = size;
 		kasan_poison_vmalloc(p + size, old_size - size);
-		kasan_unpoison_vmalloc(p, size, KASAN_VMALLOC_PROT_NORMAL);
 		return (void *)p;
+	}
+
+	/*
+	 * We already have the bytes available in the allocation; use them.
+	 */
+	if (size <= alloced_size) {
+		kasan_unpoison_vmalloc(p + old_size, size - old_size,
+				       KASAN_VMALLOC_PROT_NORMAL);
+		/* Zero out "alloced" memory. */
+		if (want_init_on_alloc(flags))
+			memset((void *)p + old_size, 0, size - old_size);
+		vm->requested_size = size;
 	}
 
 	/* TODO: Grow the vm_area, i.e. allocate and map additional pages. */

tools/testing/selftests/mm/compaction_test.c

···
 	int compaction_index = 0;
 	char nr_hugepages[20] = {0};
 	char init_nr_hugepages[24] = {0};
+	char target_nr_hugepages[24] = {0};
+	int slen;
 
 	snprintf(init_nr_hugepages, sizeof(init_nr_hugepages),
 		 "%lu", initial_nr_hugepages);
···
 		goto out;
 	}
 
-	/* Request a large number of huge pages. The Kernel will allocate
-	   as much as it can */
-	if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) {
-		ksft_print_msg("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n",
-			       strerror(errno));
+	/*
+	 * Request huge pages for about half of the free memory. The Kernel
+	 * will allocate as much as it can, and we expect it will get at least 1/3
+	 */
+	nr_hugepages_ul = mem_free / hugepage_size / 2;
+	snprintf(target_nr_hugepages, sizeof(target_nr_hugepages),
+		 "%lu", nr_hugepages_ul);
+
+	slen = strlen(target_nr_hugepages);
+	if (write(fd, target_nr_hugepages, slen) != slen) {
+		ksft_print_msg("Failed to write %lu to /proc/sys/vm/nr_hugepages: %s\n",
+			       nr_hugepages_ul, strerror(errno));
 		goto close_fd;
 	}
 

tools/testing/selftests/mm/guard-regions.c

···
 	self->page_size = (unsigned long)sysconf(_SC_PAGESIZE);
 	setup_sighandler();
 
-	if (variant->backing == ANON_BACKED)
+	switch (variant->backing) {
+	case ANON_BACKED:
 		return;
-
-	self->fd = open_file(
-		variant->backing == SHMEM_BACKED ? "/tmp/" : "",
-		self->path);
+	case LOCAL_FILE_BACKED:
+		self->fd = open_file("", self->path);
+		break;
+	case SHMEM_BACKED:
+		self->fd = memfd_create(self->path, 0);
+		break;
+	}
 
 	/* We truncate file to at least 100 pages, tests can modify as needed. */
 	ASSERT_EQ(ftruncate(self->fd, 100 * self->page_size), 0);
···
 	char *ptr;
 	int i;
 
-	if (variant->backing == ANON_BACKED)
+	if (variant->backing != LOCAL_FILE_BACKED)
 		SKIP(return, "Read-only test specific to file-backed");
 
 	/* Map shared so we can populate with pattern, populate it, unmap. */

tools/testing/selftests/mm/pkey-powerpc.h

···
 #ifndef _PKEYS_POWERPC_H
 #define _PKEYS_POWERPC_H
 
+#include <sys/stat.h>
+
 #ifndef SYS_pkey_alloc
 # define SYS_pkey_alloc		384
 # define SYS_pkey_free		385
···
 	return;
 }
 
+#define REPEAT_8(s) s s s s s s s s
+#define REPEAT_64(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) \
+		     REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s)
+#define REPEAT_512(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) \
+		      REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s)
+#define REPEAT_4096(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) \
+		       REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s)
+#define REPEAT_16384(s) REPEAT_4096(s) REPEAT_4096(s) \
+			REPEAT_4096(s) REPEAT_4096(s)
+
 /* 4-byte instructions * 16384 = 64K page */
-#define __page_o_noops() asm(".rept 16384 ; nop; .endr")
+#define __page_o_noops() asm(REPEAT_16384("nop\n"))
 
 static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey)
 {

tools/testing/selftests/mm/pkey_util.c

···
 // SPDX-License-Identifier: GPL-2.0-only
+#define __SANE_USERSPACE_TYPES__
 #include <sys/syscall.h>
 #include <unistd.h>