From: Andreas Gruenbacher agruenba@redhat.com
[ Upstream commit ebf00be37de35788cad72f4f20b4a39e30c0be4a ]
According to xfstest generic/240, applications seem to expect direct I/O writes to either complete as a whole or to fail; short direct I/O writes are apparently not appreciated. This means that when only part of an asynchronous direct I/O write succeeds, we can either fail the entire write, or we can wait for the partial write to complete and retry the remaining write as buffered I/O. The old __blockdev_direct_IO helper has code for waiting for partial writes to complete; the new iomap_dio_rw iomap helper does not.
The above mentioned fallback mode is needed for gfs2, which doesn't allow block allocations under direct I/O to avoid taking cluster-wide exclusive locks. As a consequence, an asynchronous direct I/O write to a file range that contains a hole will result in a short write. In that case, wait for the short write to complete to allow gfs2 to recover.
Signed-off-by: Andreas Gruenbacher agruenba@redhat.com Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- fs/iomap.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-)
diff --git a/fs/iomap.c b/fs/iomap.c index 0d0bd8845586..af6144fd4919 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -811,6 +811,7 @@ struct iomap_dio { atomic_t ref; unsigned flags; int error; + bool wait_for_completion;
union { /* used during submission and for synchronous completion: */ @@ -914,9 +915,8 @@ static void iomap_dio_bio_end_io(struct bio *bio) iomap_dio_set_error(dio, blk_status_to_errno(bio->bi_status));
if (atomic_dec_and_test(&dio->ref)) { - if (is_sync_kiocb(dio->iocb)) { + if (dio->wait_for_completion) { struct task_struct *waiter = dio->submit.waiter; - WRITE_ONCE(dio->submit.waiter, NULL); wake_up_process(waiter); } else if (dio->flags & IOMAP_DIO_WRITE) { @@ -1131,13 +1131,12 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, dio->end_io = end_io; dio->error = 0; dio->flags = 0; + dio->wait_for_completion = is_sync_kiocb(iocb);
dio->submit.iter = iter; - if (is_sync_kiocb(iocb)) { - dio->submit.waiter = current; - dio->submit.cookie = BLK_QC_T_NONE; - dio->submit.last_queue = NULL; - } + dio->submit.waiter = current; + dio->submit.cookie = BLK_QC_T_NONE; + dio->submit.last_queue = NULL;
if (iov_iter_rw(iter) == READ) { if (pos >= dio->i_size) @@ -1187,7 +1186,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, dio_warn_stale_pagecache(iocb->ki_filp); ret = 0;
- if (iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) && + if (iov_iter_rw(iter) == WRITE && !dio->wait_for_completion && !inode->i_sb->s_dio_done_wq) { ret = sb_init_dio_done_wq(inode->i_sb); if (ret < 0) @@ -1202,8 +1201,10 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, iomap_dio_actor); if (ret <= 0) { /* magic error code to fall back to buffered I/O */ - if (ret == -ENOTBLK) + if (ret == -ENOTBLK) { + dio->wait_for_completion = true; ret = 0; + } break; } pos += ret; @@ -1224,7 +1225,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, dio->flags &= ~IOMAP_DIO_NEED_SYNC;
if (!atomic_dec_and_test(&dio->ref)) { - if (!is_sync_kiocb(iocb)) + if (!dio->wait_for_completion) return -EIOCBQUEUED;
for (;;) {