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
  ...

Author: torvalds

.mailmap

@@ -447,6 +447,8 @@ Luca Ceresoli <[email protected]> <[email protected]>
 Luca Weiss <[email protected]> <[email protected]>
 Lukasz Luba <[email protected]> <[email protected]>
 Luo Jie <[email protected]> <[email protected]>
+Lance Yang <[email protected]> <[email protected]>
+Lance Yang <[email protected]> <[email protected]>
 Maciej W. Rozycki <[email protected]> <[email protected]>
 Maciej W. Rozycki <[email protected]> <[email protected]>
 Maharaja Kennadyrajan <[email protected]> <[email protected]>
@@ -749,6 +751,7 @@ Tvrtko Ursulin <[email protected]> <[email protected]>
 Tycho Andersen <[email protected]> <[email protected]>
 Tzung-Bi Shih <[email protected]> <[email protected]>
 Uwe Kleine-König <[email protected]>
+Uwe Kleine-König <[email protected]> <[email protected]>
 Uwe Kleine-König <[email protected]>
 Uwe Kleine-König <[email protected]>
 Uwe Kleine-König <[email protected]>

MAINTAINERS

@@ -15495,24 +15495,45 @@ F:	Documentation/mm/
 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 <[email protected]>
+M:	David Hildenbrand <[email protected]>
+R:	Lorenzo Stoakes <[email protected]>
+R:	Liam R. Howlett <[email protected]>
+R:	Vlastimil Babka <[email protected]>
+R:	Mike Rapoport <[email protected]>
+R:	Suren Baghdasaryan <[email protected]>
+R:	Michal Hocko <[email protected]>
+L:	[email protected]
+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 <[email protected]>
 M:	Mike Rapoport <[email protected]>
@@ -15546,6 +15567,19 @@ F:	mm/page_alloc.c
 F:	include/linux/gfp.h
 F:	include/linux/compaction.h
 
+MEMORY MANAGEMENT - RMAP (REVERSE MAPPING)
+M:	Andrew Morton <[email protected]>
+M:	David Hildenbrand <[email protected]>
+M:	Lorenzo Stoakes <[email protected]>
+R:	Rik van Riel <[email protected]>
+R:	Liam R. Howlett <[email protected]>
+R:	Vlastimil Babka <[email protected]>
+R:	Harry Yoo <[email protected]>
+L:	[email protected]
+S:	Maintained
+F:	include/linux/rmap.h
+F:	mm/rmap.c
+
 MEMORY MANAGEMENT - SECRETMEM
 M:	Andrew Morton <[email protected]>
 M:	Mike Rapoport <[email protected]>
@@ -15554,6 +15588,30 @@ S:	Maintained
 F:	include/linux/secretmem.h
 F:	mm/secretmem.c
 
+MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE)
+M:	Andrew Morton <[email protected]>
+M:	David Hildenbrand <[email protected]>
+R:	Zi Yan <[email protected]>
+R:	Baolin Wang <[email protected]>
+R:	Lorenzo Stoakes <[email protected]>
+R:	Liam R. Howlett <[email protected]>
+R:	Nico Pache <[email protected]>
+R:	Ryan Roberts <[email protected]>
+R:	Dev Jain <[email protected]>
+L:	[email protected]
+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 <[email protected]>
 R:	Peter Xu <[email protected]>

arch/x86/kernel/vmlinux.lds.S

@@ -466,10 +466,18 @@ SECTIONS
 }
 
 /*
- * 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

@@ -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:

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;
 		}
 

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 @@ static int __ocfs2_recovery_thread(void *arg)
 
 	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

@@ -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);

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;

fs/ocfs2/quota_local.c

@@ -453,8 +453,7 @@ struct ocfs2_quota_recovery *ocfs2_begin_quota_recovery(
 
 /* 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 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
 			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);