ext4: Allocate mapping_metadata_bhs struct on demand

Currently every ext4 inode gets mapping_metadata_bhs struct although it
is only needed when running without a journal and only for inodes where
any metadata was dirtied. Allocate mapping_metadata_bhs struct on demand
when dirtying the first metadata buffer for the inode.

Acked-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20260727104923.3828017-24-jack@suse.cz
Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>

5 files changed, 55 insertions, 16 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index b37c136ea3ab..64f8f63f4415 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1151,7 +1151,7 @@ struct ext4_inode_info {
 	struct rw_semaphore i_data_sem;
 	struct inode vfs_inode;
 	struct jbd2_inode *jinode;
-	struct mapping_metadata_bhs i_metadata_bhs;
+	struct mapping_metadata_bhs *i_metadata_bhs;
 
 	/*
 	 * File creation time. Its function is same as that of
@@ -2126,6 +2126,17 @@ static inline bool ext4_inode_orphan_tracked(struct inode *inode)
 		!list_empty(&EXT4_I(inode)->i_orphan);
 }
 
+static inline struct mapping_metadata_bhs *ext4_i_metadata_bhs(
+							struct inode *inode)
+{
+	/*
+	 * i_metadata_bhs is set in ext4_inode_attach_mmb() using cmpxchg().
+	 * We use READ_ONCE when accessing i_metadata_bhs to make sure we get
+	 * consistent view for all accesses.
+	 */
+	return READ_ONCE(EXT4_I(inode)->i_metadata_bhs);
+}
+
 /*
  * Codes for operating systems
  */
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 9a8c225f2753..02b066299164 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -350,6 +350,21 @@ int __ext4_journal_get_create_access(const char *where, unsigned int line,
 	return 0;
 }
 
+static void ext4_inode_attach_mmb(struct inode *inode)
+{
+	struct mapping_metadata_bhs *mmb;
+
+	/*
+	 * It's difficult to handle failure when marking buffer dirty without
+	 * leaving filesystem corrupted
+	 */
+	mmb = kmalloc_obj(*mmb, GFP_NOFS | __GFP_NOFAIL | __GFP_ACCOUNT);
+	mmb_init(mmb, &inode->i_data);
+	/* Someone swapped another mmb before us? */
+	if (cmpxchg(&EXT4_I(inode)->i_metadata_bhs, NULL, mmb))
+		kfree(mmb);
+}
+
 int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 				 handle_t *handle, struct inode *inode,
 				 struct buffer_head *bh)
@@ -389,11 +404,13 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 					 err);
 		}
 	} else {
-		if (inode)
-			mmb_mark_buffer_dirty(bh,
-					      &EXT4_I(inode)->i_metadata_bhs);
-		else
+		if (inode) {
+			if (!ext4_i_metadata_bhs(inode))
+				ext4_inode_attach_mmb(inode);
+			mmb_mark_buffer_dirty(bh, ext4_i_metadata_bhs(inode));
+		} else {
 			mark_buffer_dirty(bh);
+		}
 		if (inode && inode_needs_sync(inode)) {
 			sync_dirty_buffer(bh);
 			if (buffer_req(bh) && !buffer_uptodate(bh)) {
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 924726dcc85f..b7ea4433f4be 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -46,6 +46,7 @@
 static int ext4_sync_parent(struct inode *inode)
 {
 	struct dentry *dentry, *next;
+	struct mapping_metadata_bhs *mmb;
 	int ret = 0;
 
 	if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY))
@@ -68,9 +69,12 @@ static int ext4_sync_parent(struct inode *inode)
 		 * through ext4_evict_inode()) and so we are safe to flush
 		 * metadata blocks and the inode.
 		 */
-		ret = mmb_sync(&EXT4_I(inode)->i_metadata_bhs);
-		if (ret)
-			break;
+		mmb = ext4_i_metadata_bhs(inode);
+		if (mmb) {
+			ret = mmb_sync(mmb);
+			if (ret)
+				break;
+		}
 		ret = sync_inode_metadata(inode, 1);
 		if (ret)
 			break;
@@ -89,7 +93,7 @@ static int ext4_fsync_nojournal(struct file *file, loff_t start, loff_t end,
 	};
 	int ret;
 
-	ret = mmb_fsync_noflush(file, &EXT4_I(inode)->i_metadata_bhs,
+	ret = mmb_fsync_noflush(file, ext4_i_metadata_bhs(inode),
 				start, end, datasync);
 	if (ret)
 		return ret;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ce99807c5f5b..e6acef486ee1 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -186,6 +186,8 @@ void ext4_evict_inode(struct inode *inode)
 	if (EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)
 		ext4_evict_ea_inode(inode);
 	if (inode->i_nlink) {
+		struct mapping_metadata_bhs *mmb;
+
 		/*
 		 * If there's dirty page will lead to data loss, user
 		 * could see stale data.
@@ -195,9 +197,9 @@ void ext4_evict_inode(struct inode *inode)
 			ext4_warning_inode(inode, "data will be lost");
 
 		truncate_inode_pages_final(&inode->i_data);
-		/* Avoid mballoc special inode which has no proper iops */
-		if (!EXT4_SB(inode->i_sb)->s_journal)
-			mmb_sync(&EXT4_I(inode)->i_metadata_bhs);
+		mmb = ext4_i_metadata_bhs(inode);
+		if (mmb)
+			mmb_sync(mmb);
 		goto no_delete;
 	}
 
@@ -3452,6 +3454,7 @@ static bool ext4_release_folio(struct folio *folio, gfp_t wait)
 static bool ext4_inode_datasync_dirty(struct inode *inode)
 {
 	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
+	struct mapping_metadata_bhs *mmb;
 
 	if (journal) {
 		if (jbd2_transaction_committed(journal,
@@ -3462,8 +3465,9 @@ static bool ext4_inode_datasync_dirty(struct inode *inode)
 		return true;
 	}
 
+	mmb = ext4_i_metadata_bhs(inode);
 	/* Any metadata buffers to write? */
-	if (mmb_has_buffers(&EXT4_I(inode)->i_metadata_bhs))
+	if (mmb && mmb_has_buffers(mmb))
 		return true;
 	return inode_state_read_once(inode) & I_DIRTY_DATASYNC;
 }
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 245f67d10ded..8671fa1209dd 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1430,7 +1430,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
 	ext4_fc_init_inode(&ei->vfs_inode);
 	spin_lock_init(&ei->i_fc_lock);
-	mmb_init(&ei->i_metadata_bhs, &ei->vfs_inode.i_data);
+	ei->i_metadata_bhs = NULL;
 #ifdef CONFIG_LOCKDEP
 	lockdep_set_subclass(&ei->i_data_sem, I_DATA_SEM_NORMAL);
 #endif
@@ -1451,6 +1451,7 @@ static int ext4_drop_inode(struct inode *inode)
 static void ext4_free_in_core_inode(struct inode *inode)
 {
 	fscrypt_free_inode(inode);
+	kfree(ext4_i_metadata_bhs(inode));
 	if (!list_empty(&(EXT4_I(inode)->i_fc_list))) {
 		pr_warn("%s: inode %llu still in fc list",
 			__func__, inode->i_ino);
@@ -1529,9 +1530,11 @@ static void destroy_inodecache(void)
 
 void ext4_clear_inode(struct inode *inode)
 {
+	struct mapping_metadata_bhs *mmb = ext4_i_metadata_bhs(inode);
+
 	ext4_fc_del(inode);
-	if (!EXT4_SB(inode->i_sb)->s_journal)
-		mmb_invalidate(&EXT4_I(inode)->i_metadata_bhs);
+	if (mmb)
+		mmb_invalidate(mmb);
 	clear_inode(inode);
 	ext4_discard_preallocations(inode);
 	/*