Messages in this thread | | | Date | Mon, 27 Jul 2015 05:41:57 -0400 | Subject | Re: [PATCH v7 4/6] block: loop: prepare for supporing direct IO | From | Ming Lei <> |
| |
On Mon, Jul 27, 2015 at 4:40 AM, Christoph Hellwig <hch@infradead.org> wrote: >> + /* >> + * loop block's logical block size is 512, now >> + * we support direct I/O only if the backing >> + * block devices' minimize I/O size is 512 and >> + * the offset is aligned with 512. >> + */ >> + if (dio) { >> + if (inode->i_sb->s_bdev && >> + bdev_io_min(inode->i_sb->s_bdev) == 512 && >> + !(lo->lo_offset & 511)) > > Why the hardcoded value? I suspect this should be more like: > > if (dio && inode->i_sb->s_bdev && > (lo->lo_offset & (bdev_io_min(inode->i_sb->s_bdev) - 1)) != 0) > dio = false;
The above can't work if the backing device has a bigger sector size (such as 4K), that is why loop's direct-io requires 512 min_io_size of backing device.
> >> + blk_mq_freeze_queue(lo->lo_queue); >> + lo->use_dio = use_dio; >> + if (use_dio) >> + lo->lo_flags |= LO_FLAGS_DIRECT_IO; >> + else >> + lo->lo_flags &= ~LO_FLAGS_DIRECT_IO; >> + blk_mq_unfreeze_queue(lo->lo_queue); > > Locking?
__loop_update_dio() is only called inside ioctl path, so mutex of lo->lo_ctl_mutex has been held already.
Thanks,
| |