Re: [RFC PATCH v2 2/5] iomap: Add initial support for buffered RWF_WRITETHROUGH

[Jan Kara]

Some more thoughs... :)

> @@ -1096,6 +1097,276 @@ static bool iomap_write_end(struct iomap_iter *iter, size_t len, size_t copied,
>  	return __iomap_write_end(iter->inode, pos, len, copied, folio);
>  }
>  
> +static ssize_t iomap_writethrough_complete(struct iomap_writethrough_ctx *wt_ctx)
> +{
> +	struct kiocb *iocb	= wt_ctx->iocb;
> +	struct inode *inode	= wt_ctx->inode;
> +	ssize_t ret		= wt_ctx->error;
> +
> +	if (wt_ctx->dops && wt_ctx->dops->end_io) {
> +		int err = wt_ctx->dops->end_io(iocb, wt_ctx->written,
> +						wt_ctx->error,
> +						wt_ctx->flags);

It's a bit odd to use only ->end_io from dops also because we don't really
use direct IO submission path. So perhaps you can have just an end_io
handler pointer in iomap_writethrough_ops similarly as you have a
submission one?

> +		if (err)
> +			ret = err;
> +	}
> +
> +	mapping_clear_stable_writes(inode->i_mapping);
> +
> +	if (!ret) {
> +		ret = wt_ctx->written;
> +		iocb->ki_pos = wt_ctx->pos + ret;
> +	}
> +
> +	kfree(wt_ctx);
> +	return ret;
> +}

...

> +static int iomap_writethrough_iter(struct iomap_writethrough_ctx *wt_ctx,
> +				   struct iomap_iter *iter, struct iov_iter *i,
> +				   const struct iomap_writethrough_ops *wt_ops)
> +
> +{
> +	ssize_t total_written = 0;
> +	int status = 0;
> +	struct address_space *mapping = iter->inode->i_mapping;
> +	size_t chunk = mapping_max_folio_size(mapping);
> +	unsigned int bdp_flags = (iter->flags & IOMAP_NOWAIT) ? BDP_ASYNC : 0;
> +	unsigned int bs = i_blocksize(iter->inode);
> +
> +	/* copied over based on DIO handles these flags */
> +	if (iter->iomap.type == IOMAP_UNWRITTEN)
> +		wt_ctx->flags |= IOMAP_DIO_UNWRITTEN;
> +	if (iter->iomap.flags & IOMAP_F_SHARED)
> +		wt_ctx->flags |= IOMAP_DIO_COW;
> +
> +	if (!(iter->flags & IOMAP_WRITETHROUGH))
> +		return -EINVAL;
> +
> +	do {
> +		struct folio *folio;
> +		size_t offset;		/* Offset into folio */
> +		u64 bytes;		/* Bytes to write to folio */
> +		size_t copied;		/* Bytes copied from user */
> +		u64 written;		/* Bytes have been written */
> +		loff_t pos;
> +		size_t off_aligned, len_aligned;
> +
> +		bytes = iov_iter_count(i);
> +retry:
> +		offset = iter->pos & (chunk - 1);
> +		bytes = min(chunk - offset, bytes);
> +		status = balance_dirty_pages_ratelimited_flags(mapping,
> +							       bdp_flags);
> +		if (unlikely(status))
> +			break;
> +
> +		/*
> +		 * If completions already occurred and reported errors, give up
> +		 * now and don't bother submitting more bios.
> +		 */
> +		if (unlikely(data_race(wt_ctx->error))) {
> +			wt_ctx->nr_bvecs = 0;
> +			break;
> +		}
> +
> +		if (bytes > iomap_length(iter))
> +			bytes = iomap_length(iter);
> +
> +		/*
> +		 * Bring in the user page that we'll copy from _first_.
> +		 * Otherwise there's a nasty deadlock on copying from the
> +		 * same page as we're writing to, without it being marked
> +		 * up-to-date.
> +		 *
> +		 * For async buffered writes the assumption is that the user
> +		 * page has already been faulted in. This can be optimized by
> +		 * faulting the user page.
> +		 */
> +		if (unlikely(fault_in_iov_iter_readable(i, bytes) == bytes)) {
> +			status = -EFAULT;
> +			break;
> +		}
> +
> +		status = iomap_write_begin(iter, wt_ops->write_ops, &folio,
> +					   &offset, &bytes);
> +		if (unlikely(status)) {
> +			iomap_write_failed(iter->inode, iter->pos, bytes);
> +			break;
> +		}
> +		if (iter->iomap.flags & IOMAP_F_STALE)
> +			break;
> +
> +		pos = iter->pos;
> +
> +		if (mapping_writably_mapped(mapping))
> +			flush_dcache_folio(folio);
> +
> +		copied = copy_folio_from_iter_atomic(folio, offset, bytes, i);
> +		written = iomap_write_end(iter, bytes, copied, folio) ?
> +			  copied : 0;
> +
> +		if (!written)
> +			goto put_folio;
> +
> +		off_aligned = round_down(offset, bs);
> +		len_aligned = round_up(offset + written, bs) - off_aligned;
> +
> +		iomap_folio_prepare_writethrough(folio, off_aligned,
> +						 len_aligned);
> +
> +		if (!wt_ctx->nr_bvecs)
> +			wt_ctx->bio_pos = round_down(pos, bs);
> +
> +		bvec_set_folio(&wt_ctx->bvec[wt_ctx->nr_bvecs], folio,
> +			       len_aligned, off_aligned);

Shouldn't we zero out the tail of the folio if we are submitting partial
folio for write?

> +		wt_ctx->nr_bvecs++;
> +		wt_ctx->written += written;
> +
> +		if (pos + written > wt_ctx->new_i_size)
> +			wt_ctx->new_i_size = pos + written;

I'm probably missing something here but where is i_size update handled? I
don't see new_i_size used anywhere? Also why is it OK to not call
pagecache_isize_extended() but that goes with the i_size update...

> +
> +		if (wt_ctx->nr_bvecs == wt_ctx->max_bvecs)
> +			iomap_writethrough_submit_bio(wt_ctx, &iter->iomap, wt_ops);
> +
> +put_folio:
> +		__iomap_put_folio(iter, wt_ops->write_ops, written, folio);
> +
> +		cond_resched();
> +		if (unlikely(written == 0)) {
> +			iomap_write_failed(iter->inode, pos, bytes);
> +			iov_iter_revert(i, copied);
> +
> +			if (chunk > PAGE_SIZE)
> +				chunk /= 2;
> +			if (copied) {
> +				bytes = copied;
> +				goto retry;
> +			}
> +		} else {
> +			total_written += written;
> +			iomap_iter_advance(iter, written);
> +		}
> +	} while (iov_iter_count(i) && iomap_length(iter));

Overall the differences of this function from iomap_write_iter() seem
relatively small so maybe it would be possible to just extend
iomap_write_iter() to support writethrough IO as well? Basically once we've
copied data into the folio and called iomap_write_end() we can have "if
writethrough, call function to prepare & submit the folio for IO".

> +
> +	if (wt_ctx->nr_bvecs)
> +		iomap_writethrough_submit_bio(wt_ctx, &iter->iomap, wt_ops);
> +
> +	return total_written ? 0 : status;
> +}
> +

								Honza
-- 
Jan Kara <jack@xxxxxxxx>
SUSE Labs, CR