1 files changed, 83 insertions, 26 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 54bdd4884fe6..89aade6f45f6 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -483,7 +483,7 @@ static int ext4_map_query_blocks(handle_t *handle, struct inode *inode,
 	status = map->m_flags & EXT4_MAP_UNWRITTEN ?
 			EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
 	ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
-			      map->m_pblk, status, 0);
+			      map->m_pblk, status, false);
 	return retval;
 }
 
@@ -563,8 +563,8 @@ static int ext4_map_create_blocks(handle_t *handle, struct inode *inode,
 
 	status = map->m_flags & EXT4_MAP_UNWRITTEN ?
 			EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
-	ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
-			      map->m_pblk, status, flags);
+	ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk,
+			      status, flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE);
 
 	return retval;
 }
@@ -856,7 +856,14 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
 	if (nowait)
 		return sb_find_get_block(inode->i_sb, map.m_pblk);
 
-	bh = sb_getblk(inode->i_sb, map.m_pblk);
+	/*
+	 * Since bh could introduce extra ref count such as referred by
+	 * journal_head etc. Try to avoid using __GFP_MOVABLE here
+	 * as it may fail the migration when journal_head remains.
+	 */
+	bh = getblk_unmovable(inode->i_sb->s_bdev, map.m_pblk,
+				inode->i_sb->s_blocksize);
+
 	if (unlikely(!bh))
 		return ERR_PTR(-ENOMEM);
 	if (map.m_flags & EXT4_MAP_NEW) {
@@ -1307,8 +1314,10 @@ static int ext4_write_end(struct file *file,
 	folio_unlock(folio);
 	folio_put(folio);
 
-	if (old_size < pos && !verity)
+	if (old_size < pos && !verity) {
 		pagecache_isize_extended(inode, old_size, pos);
+		ext4_zero_partial_blocks(handle, inode, old_size, pos - old_size);
+	}
 	/*
 	 * Don't mark the inode dirty under folio lock. First, it unnecessarily
 	 * makes the holding time of folio lock longer. Second, it forces lock
@@ -1423,8 +1432,10 @@ static int ext4_journalled_write_end(struct file *file,
 	folio_unlock(folio);
 	folio_put(folio);
 
-	if (old_size < pos && !verity)
+	if (old_size < pos && !verity) {
 		pagecache_isize_extended(inode, old_size, pos);
+		ext4_zero_partial_blocks(handle, inode, old_size, pos - old_size);
+	}
 
 	if (size_changed) {
 		ret2 = ext4_mark_inode_dirty(handle, inode);
@@ -2985,7 +2996,8 @@ static int ext4_da_do_write_end(struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	loff_t old_size = inode->i_size;
 	bool disksize_changed = false;
-	loff_t new_i_size;
+	loff_t new_i_size, zero_len = 0;
+	handle_t *handle;
 
 	if (unlikely(!folio_buffers(folio))) {
 		folio_unlock(folio);
@@ -3029,18 +3041,21 @@ static int ext4_da_do_write_end(struct address_space *mapping,
 	folio_unlock(folio);
 	folio_put(folio);
 
-	if (old_size < pos)
+	if (pos > old_size) {
 		pagecache_isize_extended(inode, old_size, pos);
+		zero_len = pos - old_size;
+	}
 
-	if (disksize_changed) {
-		handle_t *handle;
+	if (!disksize_changed && !zero_len)
+		return copied;
 
-		handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
-		if (IS_ERR(handle))
-			return PTR_ERR(handle);
-		ext4_mark_inode_dirty(handle, inode);
-		ext4_journal_stop(handle);
-	}
+	handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+	if (zero_len)
+		ext4_zero_partial_blocks(handle, inode, old_size, zero_len);
+	ext4_mark_inode_dirty(handle, inode);
+	ext4_journal_stop(handle);
 
 	return copied;
 }
@@ -3444,17 +3459,34 @@ static int ext4_iomap_overwrite_begin(struct inode *inode, loff_t offset,
 	return ret;
 }
 
+static inline bool ext4_want_directio_fallback(unsigned flags, ssize_t written)
+{
+	/* must be a directio to fall back to buffered */
+	if ((flags & (IOMAP_WRITE | IOMAP_DIRECT)) !=
+		    (IOMAP_WRITE | IOMAP_DIRECT))
+		return false;
+
+	/* atomic writes are all-or-nothing */
+	if (flags & IOMAP_ATOMIC)
+		return false;
+
+	/* can only try again if we wrote nothing */
+	return written == 0;
+}
+
 static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length,
 			  ssize_t written, unsigned flags, struct iomap *iomap)
 {
 	/*
 	 * Check to see whether an error occurred while writing out the data to
-	 * the allocated blocks. If so, return the magic error code so that we
-	 * fallback to buffered I/O and attempt to complete the remainder of
-	 * the I/O. Any blocks that may have been allocated in preparation for
-	 * the direct I/O will be reused during buffered I/O.
+	 * the allocated blocks. If so, return the magic error code for
+	 * non-atomic write so that we fallback to buffered I/O and attempt to
+	 * complete the remainder of the I/O.
+	 * For non-atomic writes, any blocks that may have been
+	 * allocated in preparation for the direct I/O will be reused during
+	 * buffered I/O. For atomic write, we never fallback to buffered-io.
 	 */
-	if (flags & (IOMAP_WRITE | IOMAP_DIRECT) && written == 0)
+	if (ext4_want_directio_fallback(flags, written))
 		return -ENOTBLK;
 
 	return 0;
@@ -4497,10 +4529,10 @@ make_io:
 	 * Read the block from disk.
 	 */
 	trace_ext4_load_inode(sb, ino);
-	ext4_read_bh_nowait(bh, REQ_META | REQ_PRIO, NULL);
+	ext4_read_bh_nowait(bh, REQ_META | REQ_PRIO, NULL,
+			    ext4_simulate_fail(sb, EXT4_SIM_INODE_EIO));
 	blk_finish_plug(&plug);
 	wait_on_buffer(bh);
-	ext4_simulate_fail_bh(sb, bh, EXT4_SIM_INODE_EIO);
 	if (!buffer_uptodate(bh)) {
 		if (ret_block)
 			*ret_block = block;
@@ -5426,6 +5458,14 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		}
 
 		if (attr->ia_size != inode->i_size) {
+			/* attach jbd2 jinode for EOF folio tail zeroing */
+			if (attr->ia_size & (inode->i_sb->s_blocksize - 1) ||
+			    oldsize & (inode->i_sb->s_blocksize - 1)) {
+				error = ext4_inode_attach_jinode(inode);
+				if (error)
+					goto err_out;
+			}
+
 			handle = ext4_journal_start(inode, EXT4_HT_INODE, 3);
 			if (IS_ERR(handle)) {
 				error = PTR_ERR(handle);
@@ -5436,12 +5476,17 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 				orphan = 1;
 			}
 			/*
-			 * Update c/mtime on truncate up, ext4_truncate() will
-			 * update c/mtime in shrink case below
+			 * Update c/mtime and tail zero the EOF folio on
+			 * truncate up. ext4_truncate() handles the shrink case
+			 * below.
 			 */
-			if (!shrink)
+			if (!shrink) {
 				inode_set_mtime_to_ts(inode,
 						      inode_set_ctime_current(inode));
+				if (oldsize & (inode->i_sb->s_blocksize - 1))
+					ext4_block_truncate_page(handle,
+							inode->i_mapping, oldsize);
+			}
 
 			if (shrink)
 				ext4_fc_track_range(handle, inode,
@@ -5578,6 +5623,18 @@ int ext4_getattr(struct mnt_idmap *idmap, const struct path *path,
 		}
 	}
 
+	if ((request_mask & STATX_WRITE_ATOMIC) && S_ISREG(inode->i_mode)) {
+		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+		unsigned int awu_min = 0, awu_max = 0;
+
+		if (ext4_inode_can_atomic_write(inode)) {
+			awu_min = sbi->s_awu_min;
+			awu_max = sbi->s_awu_max;
+		}
+
+		generic_fill_statx_atomic_writes(stat, awu_min, awu_max);
+	}
+
 	flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
 	if (flags & EXT4_APPEND_FL)
 		stat->attributes |= STATX_ATTR_APPEND;