summaryrefslogtreecommitdiffstats
path: root/fs/ext4/file.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4/file.c')
-rw-r--r--fs/ext4/file.c89
1 files changed, 88 insertions, 1 deletions
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 440f4c6ba4ee..ec54fec96a81 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -33,6 +33,7 @@
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
+#include "truncate.h"
static bool ext4_dio_supported(struct inode *inode)
{
@@ -234,12 +235,95 @@ static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
return iov_iter_count(from);
}
+static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset,
+ ssize_t written, size_t count)
+{
+ handle_t *handle;
+ bool truncate = false;
+ u8 blkbits = inode->i_blkbits;
+ ext4_lblk_t written_blk, end_blk;
+
+ /*
+ * Note that EXT4_I(inode)->i_disksize can get extended up to
+ * inode->i_size while the I/O was running due to writeback of delalloc
+ * blocks. But, the code in ext4_iomap_alloc() is careful to use
+ * zeroed/unwritten extents if this is possible; thus we won't leave
+ * uninitialized blocks in a file even if we didn't succeed in writing
+ * as much as we intended.
+ */
+ WARN_ON_ONCE(i_size_read(inode) < EXT4_I(inode)->i_disksize);
+ if (offset + count <= EXT4_I(inode)->i_disksize) {
+ /*
+ * We need to ensure that the inode is removed from the orphan
+ * list if it has been added prematurely, due to writeback of
+ * delalloc blocks.
+ */
+ if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) {
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+
+ if (IS_ERR(handle)) {
+ ext4_orphan_del(NULL, inode);
+ return PTR_ERR(handle);
+ }
+
+ ext4_orphan_del(handle, inode);
+ ext4_journal_stop(handle);
+ }
+
+ return written;
+ }
+
+ if (written < 0)
+ goto truncate;
+
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+ if (IS_ERR(handle)) {
+ written = PTR_ERR(handle);
+ goto truncate;
+ }
+
+ if (ext4_update_inode_size(inode, offset + written))
+ ext4_mark_inode_dirty(handle, inode);
+
+ /*
+ * We may need to truncate allocated but not written blocks beyond EOF.
+ */
+ written_blk = ALIGN(offset + written, 1 << blkbits);
+ end_blk = ALIGN(offset + count, 1 << blkbits);
+ if (written_blk < end_blk && ext4_can_truncate(inode))
+ truncate = true;
+
+ /*
+ * Remove the inode from the orphan list if it has been extended and
+ * everything went OK.
+ */
+ if (!truncate && inode->i_nlink)
+ ext4_orphan_del(handle, inode);
+ ext4_journal_stop(handle);
+
+ if (truncate) {
+truncate:
+ ext4_truncate_failed_write(inode);
+ /*
+ * If the truncate operation failed early, then the inode may
+ * still be on the orphan list. In that case, we need to try
+ * remove the inode from the in-memory linked list.
+ */
+ if (inode->i_nlink)
+ ext4_orphan_del(NULL, inode);
+ }
+
+ return written;
+}
+
#ifdef CONFIG_FS_DAX
static ssize_t
ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
- struct inode *inode = file_inode(iocb->ki_filp);
ssize_t ret;
+ size_t count;
+ loff_t offset;
+ struct inode *inode = file_inode(iocb->ki_filp);
if (!inode_trylock(inode)) {
if (iocb->ki_flags & IOCB_NOWAIT)
@@ -256,7 +340,10 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (ret)
goto out;
+ offset = iocb->ki_pos;
+ count = iov_iter_count(from);
ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
+ ret = ext4_handle_inode_extension(inode, offset, ret, count);
out:
inode_unlock(inode);
if (ret > 0)