Merge tag 'mm-hotfixes-stable-2023-04-07-16-23' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM fixes from Andrew Morton:
 "28 hotfixes.

  23 are cc:stable and the other five address issues which were
  introduced during this merge cycle.

  20 are for MM and the remainder are for other subsystems"

* tag 'mm-hotfixes-stable-2023-04-07-16-23' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (28 commits)
  maple_tree: fix a potential concurrency bug in RCU mode
  maple_tree: fix get wrong data_end in mtree_lookup_walk()
  mm/swap: fix swap_info_struct race between swapoff and get_swap_pages()
  nilfs2: fix sysfs interface lifetime
  mm: take a page reference when removing device exclusive entries
  mm: vmalloc: avoid warn_alloc noise caused by fatal signal
  nilfs2: initialize "struct nilfs_binfo_dat"->bi_pad field
  nilfs2: fix potential UAF of struct nilfs_sc_info in nilfs_segctor_thread()
  zsmalloc: document freeable stats
  zsmalloc: document new fullness grouping
  fsdax: force clear dirty mark if CoW
  mm/hugetlb: fix uffd wr-protection for CoW optimization path
  mm: enable maple tree RCU mode by default
  maple_tree: add RCU lock checking to rcu callback functions
  maple_tree: add smp_rmb() to dead node detection
  maple_tree: fix write memory barrier of nodes once dead for RCU mode
  maple_tree: remove extra smp_wmb() from mas_dead_leaves()
  maple_tree: fix freeing of nodes in rcu mode
  maple_tree: detect dead nodes in mas_start()
  maple_tree: be more cautious about dead nodes
  ...

6 files changed, 59 insertions, 12 deletions

diff --git a/fs/dax.c b/fs/dax.c
index 3e457a16c7d1..2ababb89918d 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -781,6 +781,33 @@ out:
 	return ret;
 }
 
+static int __dax_clear_dirty_range(struct address_space *mapping,
+		pgoff_t start, pgoff_t end)
+{
+	XA_STATE(xas, &mapping->i_pages, start);
+	unsigned int scanned = 0;
+	void *entry;
+
+	xas_lock_irq(&xas);
+	xas_for_each(&xas, entry, end) {
+		entry = get_unlocked_entry(&xas, 0);
+		xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY);
+		xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE);
+		put_unlocked_entry(&xas, entry, WAKE_NEXT);
+
+		if (++scanned % XA_CHECK_SCHED)
+			continue;
+
+		xas_pause(&xas);
+		xas_unlock_irq(&xas);
+		cond_resched();
+		xas_lock_irq(&xas);
+	}
+	xas_unlock_irq(&xas);
+
+	return 0;
+}
+
 /*
  * Delete DAX entry at @index from @mapping.  Wait for it
  * to be unlocked before deleting it.
@@ -1258,15 +1285,20 @@ static s64 dax_unshare_iter(struct iomap_iter *iter)
 	/* don't bother with blocks that are not shared to start with */
 	if (!(iomap->flags & IOMAP_F_SHARED))
 		return length;
-	/* don't bother with holes or unwritten extents */
-	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
-		return length;
 
 	id = dax_read_lock();
 	ret = dax_iomap_direct_access(iomap, pos, length, &daddr, NULL);
 	if (ret < 0)
 		goto out_unlock;
 
+	/* zero the distance if srcmap is HOLE or UNWRITTEN */
+	if (srcmap->flags & IOMAP_F_SHARED || srcmap->type == IOMAP_UNWRITTEN) {
+		memset(daddr, 0, length);
+		dax_flush(iomap->dax_dev, daddr, length);
+		ret = length;
+		goto out_unlock;
+	}
+
 	ret = dax_iomap_direct_access(srcmap, pos, length, &saddr, NULL);
 	if (ret < 0)
 		goto out_unlock;
@@ -1435,6 +1467,16 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 	 * written by write(2) is visible in mmap.
 	 */
 	if (iomap->flags & IOMAP_F_NEW || cow) {
+		/*
+		 * Filesystem allows CoW on non-shared extents. The src extents
+		 * may have been mmapped with dirty mark before. To be able to
+		 * invalidate its dax entries, we need to clear the dirty mark
+		 * in advance.
+		 */
+		if (cow)
+			__dax_clear_dirty_range(iomi->inode->i_mapping,
+						pos >> PAGE_SHIFT,
+						(end - 1) >> PAGE_SHIFT);
 		invalidate_inode_pages2_range(iomi->inode->i_mapping,
 					      pos >> PAGE_SHIFT,
 					      (end - 1) >> PAGE_SHIFT);
@@ -2022,8 +2064,8 @@ int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
 
 	while ((ret = iomap_iter(&src_iter, ops)) > 0 &&
 	       (ret = iomap_iter(&dst_iter, ops)) > 0) {
-		compared = dax_range_compare_iter(&src_iter, &dst_iter, len,
-						  same);
+		compared = dax_range_compare_iter(&src_iter, &dst_iter,
+				min(src_iter.len, dst_iter.len), same);
 		if (compared < 0)
 			return ret;
 		src_iter.processed = dst_iter.processed = compared;
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index 2681a449edc1..13592e82eaf6 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -2219,6 +2219,7 @@ static int nilfs_btree_assign_p(struct nilfs_bmap *btree,
 	/* on-disk format */
 	binfo->bi_dat.bi_blkoff = cpu_to_le64(key);
 	binfo->bi_dat.bi_level = level;
+	memset(binfo->bi_dat.bi_pad, 0, sizeof(binfo->bi_dat.bi_pad));
 
 	return 0;
 }
diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c
index a35f2795b242..4c85914f2abc 100644
--- a/fs/nilfs2/direct.c
+++ b/fs/nilfs2/direct.c
@@ -314,6 +314,7 @@ static int nilfs_direct_assign_p(struct nilfs_bmap *direct,
 
 	binfo->bi_dat.bi_blkoff = cpu_to_le64(key);
 	binfo->bi_dat.bi_level = 0;
+	memset(binfo->bi_dat.bi_pad, 0, sizeof(binfo->bi_dat.bi_pad));
 
 	return 0;
 }
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 19446a8243d7..6ad41390fa74 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -2609,11 +2609,10 @@ static int nilfs_segctor_thread(void *arg)
 	goto loop;
 
  end_thread:
-	spin_unlock(&sci->sc_state_lock);
-
 	/* end sync. */
 	sci->sc_task = NULL;
 	wake_up(&sci->sc_wait_task); /* for nilfs_segctor_kill_thread() */
+	spin_unlock(&sci->sc_state_lock);
 	return 0;
 }
 
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 1422b8ba24ed..77f1e5778d1c 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -482,6 +482,7 @@ static void nilfs_put_super(struct super_block *sb)
 		up_write(&nilfs->ns_sem);
 	}
 
+	nilfs_sysfs_delete_device_group(nilfs);
 	iput(nilfs->ns_sufile);
 	iput(nilfs->ns_cpfile);
 	iput(nilfs->ns_dat);
@@ -1105,6 +1106,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
 	nilfs_put_root(fsroot);
 
  failed_unload:
+	nilfs_sysfs_delete_device_group(nilfs);
 	iput(nilfs->ns_sufile);
 	iput(nilfs->ns_cpfile);
 	iput(nilfs->ns_dat);
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 3a4c9c150cbf..2894152a6b25 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -87,7 +87,6 @@ void destroy_nilfs(struct the_nilfs *nilfs)
 {
 	might_sleep();
 	if (nilfs_init(nilfs)) {
-		nilfs_sysfs_delete_device_group(nilfs);
 		brelse(nilfs->ns_sbh[0]);
 		brelse(nilfs->ns_sbh[1]);
 	}
@@ -305,6 +304,10 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 		goto failed;
 	}
 
+	err = nilfs_sysfs_create_device_group(sb);
+	if (unlikely(err))
+		goto sysfs_error;
+
 	if (valid_fs)
 		goto skip_recovery;
 
@@ -366,6 +369,9 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 	goto failed;
 
  failed_unload:
+	nilfs_sysfs_delete_device_group(nilfs);
+
+ sysfs_error:
 	iput(nilfs->ns_cpfile);
 	iput(nilfs->ns_sufile);
 	iput(nilfs->ns_dat);
@@ -697,10 +703,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data)
 	if (err)
 		goto failed_sbh;
 
-	err = nilfs_sysfs_create_device_group(sb);
-	if (err)
-		goto failed_sbh;
-
 	set_nilfs_init(nilfs);
 	err = 0;
  out: