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

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
  ...

10 files changed, 136 insertions, 45 deletions

diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index cb01ea81724d..d0bcf744c553 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -705,8 +705,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 	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");
@@ -779,7 +777,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 	set_nilfs_init(nilfs);
 	err = 0;
  out:
-	up_write(&nilfs->ns_sem);
 	return err;
 
  failed_sbh:
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index b8ac85b548c7..821cb7874685 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -6918,6 +6918,7 @@ static int ocfs2_grab_folios(struct inode *inode, loff_t start, loff_t end,
 		if (IS_ERR(folios[numfolios])) {
 			ret = PTR_ERR(folios[numfolios]);
 			mlog_errno(ret);
+			folios[numfolios] = NULL;
 			goto out;
 		}
 
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index c7a9729dc9d0..e5f58ff2175f 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -174,7 +174,7 @@ int ocfs2_recovery_init(struct ocfs2_super *osb)
 	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);
 
@@ -190,31 +190,53 @@ int ocfs2_recovery_init(struct ocfs2_super *osb)
 	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;
 }
 
-void ocfs2_recovery_exit(struct ocfs2_super *osb)
+static void ocfs2_recovery_disable(struct ocfs2_super *osb,
+				   enum ocfs2_recovery_state state)
 {
-	struct ocfs2_recovery_map *rm;
-
-	/* 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;
+	/*
+	 * 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);
-	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. */
+	/*
+	 * 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)
+{
+	struct ocfs2_recovery_map *rm;
+
+	/* disable any new recovery threads and wait for any currently
+	 * running ones to exit. Do this before setting the vol_state. */
+	ocfs2_recovery_disable(osb, OCFS2_REC_WANT_DISABLE);
 
 	/*
 	 * Now that recovery is shut down, and the osb is about to be
@@ -1472,6 +1494,18 @@ static int __ocfs2_recovery_thread(void *arg)
 		}
 	}
 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);
@@ -1569,27 +1603,29 @@ bail:
 
 	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)
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index e3c3a35dc5e0..6397170f302f 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -148,6 +148,7 @@ void ocfs2_wait_for_recovery(struct ocfs2_super *osb);
 
 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);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 51c52768132d..6aaa94c554c1 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -308,6 +308,21 @@ enum ocfs2_journal_trigger_type {
 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;
@@ -370,7 +385,7 @@ struct ocfs2_super
 	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;
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 2956d888c131..e272429da3db 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -453,8 +453,7 @@ out:
 
 /* 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)
@@ -588,7 +587,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
 {
 	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;
@@ -600,7 +598,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
 	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;
@@ -677,7 +674,6 @@ out_put:
 			break;
 	}
 out:
-	up_read(&sb->s_umount);
 	kfree(rec);
 	return status;
 }
@@ -843,8 +839,7 @@ static int ocfs2_local_free_info(struct super_block *sb, int type)
 	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);
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index f7b483f0de2a..6ac4dcd54588 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -698,10 +698,12 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
 
 	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;
@@ -1794,6 +1796,7 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
 {
 	int status;
 	u16 chain;
+	u32 contig_bits;
 	u64 next_group;
 	struct inode *alloc_inode = ac->ac_inode;
 	struct buffer_head *group_bh = NULL;
@@ -1819,10 +1822,21 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
 	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;
 
@@ -1982,6 +1996,7 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
 	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) {
@@ -2022,6 +2037,16 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
 		}
 	}
 
+	/* 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:
 	if (status != -ENOSPC) {
 		/* If the next search of this group is not likely to
@@ -2365,7 +2390,8 @@ int __ocfs2_claim_clusters(handle_t *handle,
 	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);
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index b481b834857d..bcf2ed4a8631 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -29,6 +29,7 @@ struct ocfs2_alloc_context {
 #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 */
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 8bb5022f3082..3d2533950bae 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1812,6 +1812,9 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 	/* 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 */
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index d80f94346199..22f4bf956ba1 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1585,8 +1585,11 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
 	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,
@@ -1641,8 +1644,11 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
 	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,
@@ -1744,8 +1750,11 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
 	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,
@@ -1801,8 +1810,11 @@ static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long
 	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,
@@ -1870,8 +1882,12 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx,
 
 	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 */