*/
#define DIO_PAGES 64
+/*
+ * Flags for dio_complete()
+ */
+#define DIO_COMPLETE_ASYNC 0x01 /* This is async IO */
+#define DIO_COMPLETE_INVALIDATE 0x02 /* Can invalidate pages */
+
/*
* This code generally works in units of "dio_blocks". A dio_block is
* somewhere between the hard sector size and the filesystem block size. it
* filesystems can use it to hold additional state between get_block calls and
* dio_complete.
*/
-static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async)
+static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags)
{
loff_t offset = dio->iocb->ki_pos;
ssize_t transferred = 0;
if (ret == 0)
ret = transferred;
+ if (dio->end_io) {
+ // XXX: ki_pos??
+ err = dio->end_io(dio->iocb, offset, ret, dio->private);
+ if (err)
+ ret = err;
+ }
+
/*
* Try again to invalidate clean pages which might have been cached by
* non-direct readahead, or faulted in by get_user_pages() if the source
* of the write was an mmap'ed region of the file we're writing. Either
* one is a pretty crazy thing to do, so we don't support it 100%. If
* this invalidation fails, tough, the write still worked...
+ *
+ * And this page cache invalidation has to be after dio->end_io(), as
+ * some filesystems convert unwritten extents to real allocations in
+ * end_io() when necessary, otherwise a racing buffer read would cache
+ * zeros from unwritten extents.
*/
- if (ret > 0 && dio->op == REQ_OP_WRITE &&
+ if (flags & DIO_COMPLETE_INVALIDATE &&
+ ret > 0 && dio->op == REQ_OP_WRITE &&
dio->inode->i_mapping->nrpages) {
err = invalidate_inode_pages2_range(dio->inode->i_mapping,
offset >> PAGE_SHIFT,
WARN_ON_ONCE(err);
}
- if (dio->end_io) {
-
- // XXX: ki_pos??
- err = dio->end_io(dio->iocb, offset, ret, dio->private);
- if (err)
- ret = err;
- }
-
if (!(dio->flags & DIO_SKIP_DIO_COUNT))
inode_dio_end(dio->inode);
- if (is_async) {
+ if (flags & DIO_COMPLETE_ASYNC) {
/*
* generic_write_sync expects ki_pos to have been updated
* already, but the submission path only does this for
*/
dio->iocb->ki_pos += transferred;
- if (dio->op == REQ_OP_WRITE)
- ret = generic_write_sync(dio->iocb, transferred);
+ if (ret > 0 && dio->op == REQ_OP_WRITE)
+ ret = generic_write_sync(dio->iocb, ret);
dio->iocb->ki_complete(dio->iocb, ret, 0);
}
{
struct dio *dio = container_of(work, struct dio, complete_work);
- dio_complete(dio, 0, true);
+ dio_complete(dio, 0, DIO_COMPLETE_ASYNC | DIO_COMPLETE_INVALIDATE);
}
static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio);
queue_work(dio->inode->i_sb->s_dio_done_wq,
&dio->complete_work);
} else {
- dio_complete(dio, 0, true);
+ dio_complete(dio, 0, DIO_COMPLETE_ASYNC);
}
}
}
unsigned long fs_count; /* Number of filesystem-sized blocks */
int create;
unsigned int i_blkbits = sdio->blkbits + sdio->blkfactor;
+ loff_t i_size;
/*
* If there was a memory error and we've overwritten all the
*/
create = dio->op == REQ_OP_WRITE;
if (dio->flags & DIO_SKIP_HOLES) {
- if (fs_startblk <= ((i_size_read(dio->inode) - 1) >>
- i_blkbits))
+ i_size = i_size_read(dio->inode);
+ if (i_size && fs_startblk <= (i_size - 1) >> i_blkbits)
create = 0;
}
*/
if (dio->is_async && iov_iter_rw(iter) == WRITE) {
retval = 0;
- if ((iocb->ki_filp->f_flags & O_DSYNC) ||
- IS_SYNC(iocb->ki_filp->f_mapping->host))
+ if (iocb->ki_flags & IOCB_DSYNC)
retval = dio_set_defer_completion(dio);
else if (!dio->inode->i_sb->s_dio_done_wq) {
/*
dio_await_completion(dio);
if (drop_refcount(dio) == 0) {
- retval = dio_complete(dio, retval, false);
+ retval = dio_complete(dio, retval, DIO_COMPLETE_INVALIDATE);
} else
BUG_ON(retval != -EIOCBQUEUED);