This changes ext3 to skip the orphaned inoded while
growing the file with DIO. It also creates a version of ext3_get_block
that starts and ends a transaction.
By starting and ending the transaction inside get_block, this is able to
avoid lock inversion problems when the DIO code tries to take page locks
inside blockdev_direct_IO. (transaction locks must always happen after
page locks).
Signed-off-by: Chris Mason <chris.mason@xxxxxxxxxx>
diff -r f84d3216430d -r 218de24978fc fs/ext3/inode.c
--- a/fs/ext3/inode.c Wed Nov 01 10:24:03 2006 -0500
+++ b/fs/ext3/inode.c Wed Nov 01 10:24:05 2006 -0500
@@ -1608,6 +1608,30 @@ static int ext3_releasepage(struct page
return journal_try_to_free_buffers(journal, page, wait);
}
+static int ext3_get_block_direct_IO(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ int ret = 0;
+ handle_t *handle = ext3_journal_start(inode, DIO_CREDITS);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out;
+ }
+ ret = ext3_get_block(inode, iblock, bh_result, create);
+ /*
+ * Reacquire the handle: ext3_get_block() can restart the transaction
+ */
+ handle = journal_current_handle();
+ if (handle) {
+ int err;
+ err = ext3_journal_stop(handle);
+ if (!ret)
+ ret = err;
+ }
+out:
+ return ret;
+}
+
/*
* If the O_DIRECT write will extend the file then add this inode to the
* orphan list. So recovery will truncate it back to the original size
@@ -1620,67 +1644,11 @@ static ssize_t ext3_direct_IO(int rw, st
const struct iovec *iov, loff_t offset,
unsigned long nr_segs)
{
- struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
- struct ext3_inode_info *ei = EXT3_I(inode);
- handle_t *handle = NULL;
- ssize_t ret;
- int orphan = 0;
- size_t count = iov_length(iov, nr_segs);
-
- if (rw == WRITE) {
- loff_t final_size = offset + count;
-
- handle = ext3_journal_start(inode, DIO_CREDITS);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
- }
- if (final_size > inode->i_size) {
- ret = ext3_orphan_add(handle, inode);
- if (ret)
- goto out_stop;
- orphan = 1;
- ei->i_disksize = inode->i_size;
- }
- }
-
- ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
- offset, nr_segs,
- ext3_get_block, NULL);
-
- /*
- * Reacquire the handle: ext3_get_block() can restart the transaction
- */
- handle = journal_current_handle();
-
-out_stop:
- if (handle) {
- int err;
-
- if (orphan && inode->i_nlink)
- ext3_orphan_del(handle, inode);
- if (orphan && ret > 0) {
- loff_t end = offset + ret;
- if (end > inode->i_size) {
- ei->i_disksize = end;
- i_size_write(inode, end);
- /*
- * We're going to return a positive `ret'
- * here due to non-zero-length I/O, so there's
- * no way of reporting error returns from
- * ext3_mark_inode_dirty() to userspace. So
- * ignore it.
- */
- ext3_mark_inode_dirty(handle, inode);
- }
- }
- err = ext3_journal_stop(handle);
- if (ret == 0)
- ret = err;
- }
-out:
- return ret;
+ struct inode *inode = iocb->ki_filp->f_mapping->host;
+ return blockdev_direct_IO_flags(rw, iocb, inode, inode->i_sb->s_bdev,
+ iov, offset, nr_segs, ext3_get_block_direct_IO,
+ NULL, DIO_PLACEHOLDERS | DIO_CREATE |
+ DIO_EXTEND | DIO_DROP_I_MUTEX);
}
/*
-
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
