mm/filemap: don't revert iter on -EIOCBQUEUED

Currently, if I/O is enqueued for async execution direct paths of
generic_file_{read,write}_iter() will always revert the iter.  There are
no users expecting that, and that is also costly.  Leave iterators as is
on -EIOCBQUEUED.

Link: https://lkml.kernel.org/r/f5247b60e7abbd2ff850cd108491f53a2e0c501a.1610207781.git.asml.silence@gmail.com
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Pavel Begunkov 2021-02-24 12:01:45 -08:00 committed by Linus Torvalds
parent 1f7ef65774
commit ab2125df92
1 changed files with 4 additions and 2 deletions

View File

@ -2615,7 +2615,8 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
iocb->ki_pos += retval;
count -= retval;
}
iov_iter_revert(iter, count - iov_iter_count(iter));
if (retval != -EIOCBQUEUED)
iov_iter_revert(iter, count - iov_iter_count(iter));
/*
* Btrfs can have a short DIO read if we encounter
@ -3426,7 +3427,8 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
}
iocb->ki_pos = pos;
}
iov_iter_revert(from, write_len - iov_iter_count(from));
if (written != -EIOCBQUEUED)
iov_iter_revert(from, write_len - iov_iter_count(from));
out:
return written;
}