linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Darrick J. Wong" <darrick.wong@oracle.com>
To: Christoph Hellwig <hch@lst.de>
Cc: linux-xfs@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-mm@kvack.org
Subject: Re: [PATCH 16/34] iomap: add initial support for writes without buffer heads
Date: Tue, 29 May 2018 23:21:38 -0700	[thread overview]
Message-ID: <20180530062138.GF30110@magnolia> (raw)
In-Reply-To: <20180523144357.18985-17-hch@lst.de>

On Wed, May 23, 2018 at 04:43:39PM +0200, Christoph Hellwig wrote:
> For now just limited to blocksize == PAGE_SIZE, where we can simply read
> in the full page in write begin, and just set the whole page dirty after
> copying data into it.  This code is enabled by default and XFS will now
> be feed pages without buffer heads in ->writepage and ->writepages.
> 
> If a file system sets the IOMAP_F_BUFFER_HEAD flag on the iomap the old
> path will still be used, this both helps the transition in XFS and
> prepares for the gfs2 migration to the iomap infrastructure.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>

Looks ok, stopping here for the night...
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>

--D

> ---
>  fs/iomap.c            | 129 ++++++++++++++++++++++++++++++++++++++----
>  fs/xfs/xfs_iomap.c    |   6 +-
>  include/linux/iomap.h |   2 +
>  3 files changed, 124 insertions(+), 13 deletions(-)
> 
> diff --git a/fs/iomap.c b/fs/iomap.c
> index 78259a2249f4..debb859a8a14 100644
> --- a/fs/iomap.c
> +++ b/fs/iomap.c
> @@ -308,6 +308,49 @@ iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
>  		truncate_pagecache_range(inode, max(pos, i_size), pos + len);
>  }
>  
> +static int
> +iomap_read_page_sync(struct inode *inode, loff_t block_start, struct page *page,
> +		unsigned poff, unsigned plen, unsigned from, unsigned to,
> +		struct iomap *iomap)
> +{
> +	struct bio_vec bvec;
> +	struct bio bio;
> +
> +	if (iomap->type != IOMAP_MAPPED || block_start >= i_size_read(inode)) {
> +		zero_user_segments(page, poff, from, to, poff + plen);
> +		return 0;
> +	}
> +
> +	bio_init(&bio, &bvec, 1);
> +	bio.bi_opf = REQ_OP_READ;
> +	bio.bi_iter.bi_sector = iomap_sector(iomap, block_start);
> +	bio_set_dev(&bio, iomap->bdev);
> +	__bio_add_page(&bio, page, plen, poff);
> +	return submit_bio_wait(&bio);
> +}
> +
> +static int
> +__iomap_write_begin(struct inode *inode, loff_t pos, unsigned len,
> +		struct page *page, struct iomap *iomap)
> +{
> +	loff_t block_size = i_blocksize(inode);
> +	loff_t block_start = pos & ~(block_size - 1);
> +	loff_t block_end = (pos + len + block_size - 1) & ~(block_size - 1);
> +	unsigned poff = block_start & (PAGE_SIZE - 1);
> +	unsigned plen = min_t(loff_t, PAGE_SIZE - poff, block_end - block_start);
> +	unsigned from = pos & (PAGE_SIZE - 1);
> +	unsigned to = from + len;
> +
> +	WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE);
> +
> +	if (PageUptodate(page))
> +		return 0;
> +	if (from <= poff && to >= poff + plen)
> +		return 0;
> +	return iomap_read_page_sync(inode, block_start, page,
> +			poff, plen, from, to, iomap);
> +}
> +
>  static int
>  iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
>  		struct page **pagep, struct iomap *iomap)
> @@ -325,7 +368,10 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
>  	if (!page)
>  		return -ENOMEM;
>  
> -	status = __block_write_begin_int(page, pos, len, NULL, iomap);
> +	if (iomap->flags & IOMAP_F_BUFFER_HEAD)
> +		status = __block_write_begin_int(page, pos, len, NULL, iomap);
> +	else
> +		status = __iomap_write_begin(inode, pos, len, page, iomap);
>  	if (unlikely(status)) {
>  		unlock_page(page);
>  		put_page(page);
> @@ -338,14 +384,69 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
>  	return status;
>  }
>  
> +int
> +iomap_set_page_dirty(struct page *page)
> +{
> +	struct address_space *mapping = page_mapping(page);
> +	int newly_dirty;
> +
> +	if (unlikely(!mapping))
> +		return !TestSetPageDirty(page);
> +
> +	/*
> +	 * Lock out page->mem_cgroup migration to keep PageDirty
> +	 * synchronized with per-memcg dirty page counters.
> +	 */
> +	lock_page_memcg(page);
> +	newly_dirty = !TestSetPageDirty(page);
> +	if (newly_dirty)
> +		__set_page_dirty(page, mapping, 0);
> +	unlock_page_memcg(page);
> +
> +	if (newly_dirty)
> +		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
> +	return newly_dirty;
> +}
> +EXPORT_SYMBOL_GPL(iomap_set_page_dirty);
> +
> +static int
> +__iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
> +		unsigned copied, struct page *page, struct iomap *iomap)
> +{
> +	flush_dcache_page(page);
> +
> +	/*
> +	 * The blocks that were entirely written will now be uptodate, so we
> +	 * don't have to worry about a readpage reading them and overwriting a
> +	 * partial write.  However if we have encountered a short write and only
> +	 * partially written into a block, it will not be marked uptodate, so a
> +	 * readpage might come in and destroy our partial write.
> +	 *
> +	 * Do the simplest thing, and just treat any short write to a non
> +	 * uptodate page as a zero-length write, and force the caller to redo
> +	 * the whole thing.
> +	 */
> +	if (unlikely(copied < len && !PageUptodate(page))) {
> +		copied = 0;
> +	} else {
> +		SetPageUptodate(page);
> +		iomap_set_page_dirty(page);
> +	}
> +	return __generic_write_end(inode, pos, copied, page);
> +}
> +
>  static int
>  iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
> -		unsigned copied, struct page *page)
> +		unsigned copied, struct page *page, struct iomap *iomap)
>  {
>  	int ret;
>  
> -	ret = generic_write_end(NULL, inode->i_mapping, pos, len,
> -			copied, page, NULL);
> +	if (iomap->flags & IOMAP_F_BUFFER_HEAD)
> +		ret = generic_write_end(NULL, inode->i_mapping, pos, len,
> +				copied, page, NULL);
> +	else
> +		ret = __iomap_write_end(inode, pos, len, copied, page, iomap);
> +
>  	if (ret < len)
>  		iomap_write_failed(inode, pos, len);
>  	return ret;
> @@ -400,7 +501,8 @@ iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
>  
>  		flush_dcache_page(page);
>  
> -		status = iomap_write_end(inode, pos, bytes, copied, page);
> +		status = iomap_write_end(inode, pos, bytes, copied, page,
> +				iomap);
>  		if (unlikely(status < 0))
>  			break;
>  		copied = status;
> @@ -494,7 +596,7 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
>  
>  		WARN_ON_ONCE(!PageUptodate(page));
>  
> -		status = iomap_write_end(inode, pos, bytes, bytes, page);
> +		status = iomap_write_end(inode, pos, bytes, bytes, page, iomap);
>  		if (unlikely(status <= 0)) {
>  			if (WARN_ON_ONCE(status == 0))
>  				return -EIO;
> @@ -546,7 +648,7 @@ static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
>  	zero_user(page, offset, bytes);
>  	mark_page_accessed(page);
>  
> -	return iomap_write_end(inode, pos, bytes, bytes, page);
> +	return iomap_write_end(inode, pos, bytes, bytes, page, iomap);
>  }
>  
>  static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes,
> @@ -632,11 +734,16 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
>  	struct page *page = data;
>  	int ret;
>  
> -	ret = __block_write_begin_int(page, pos, length, NULL, iomap);
> -	if (ret)
> -		return ret;
> +	if (iomap->flags & IOMAP_F_BUFFER_HEAD) {
> +		ret = __block_write_begin_int(page, pos, length, NULL, iomap);
> +		if (ret)
> +			return ret;
> +		block_commit_write(page, 0, length);
> +	} else {
> +		WARN_ON_ONCE(!PageUptodate(page));
> +		WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE);
> +	}
>  
> -	block_commit_write(page, 0, length);
>  	return length;
>  }
>  
> diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
> index c6ce6f9335b6..da6d1995e460 100644
> --- a/fs/xfs/xfs_iomap.c
> +++ b/fs/xfs/xfs_iomap.c
> @@ -638,7 +638,7 @@ xfs_file_iomap_begin_delay(
>  	 * Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch
>  	 * them out if the write happens to fail.
>  	 */
> -	iomap->flags = IOMAP_F_NEW;
> +	iomap->flags |= IOMAP_F_NEW;
>  	trace_xfs_iomap_alloc(ip, offset, count, 0, &got);
>  done:
>  	if (isnullstartblock(got.br_startblock))
> @@ -1031,6 +1031,8 @@ xfs_file_iomap_begin(
>  	if (XFS_FORCED_SHUTDOWN(mp))
>  		return -EIO;
>  
> +	iomap->flags |= IOMAP_F_BUFFER_HEAD;
> +
>  	if (((flags & (IOMAP_WRITE | IOMAP_DIRECT)) == IOMAP_WRITE) &&
>  			!IS_DAX(inode) && !xfs_get_extsz_hint(ip)) {
>  		/* Reserve delalloc blocks for regular writeback. */
> @@ -1131,7 +1133,7 @@ xfs_file_iomap_begin(
>  	if (error)
>  		return error;
>  
> -	iomap->flags = IOMAP_F_NEW;
> +	iomap->flags |= IOMAP_F_NEW;
>  	trace_xfs_iomap_alloc(ip, offset, length, 0, &imap);
>  
>  out_finish:
> diff --git a/include/linux/iomap.h b/include/linux/iomap.h
> index 7300d30ca495..4d3d9d0cd69f 100644
> --- a/include/linux/iomap.h
> +++ b/include/linux/iomap.h
> @@ -30,6 +30,7 @@ struct vm_fault;
>   */
>  #define IOMAP_F_NEW		0x01	/* blocks have been newly allocated */
>  #define IOMAP_F_DIRTY		0x02	/* uncommitted metadata */
> +#define IOMAP_F_BUFFER_HEAD	0x04	/* file system requires buffer heads */
>  
>  /*
>   * Flags that only need to be reported for IOMAP_REPORT requests:
> @@ -92,6 +93,7 @@ ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
>  int iomap_readpage(struct page *page, const struct iomap_ops *ops);
>  int iomap_readpages(struct address_space *mapping, struct list_head *pages,
>  		unsigned nr_pages, const struct iomap_ops *ops);
> +int iomap_set_page_dirty(struct page *page);
>  int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len,
>  		const struct iomap_ops *ops);
>  int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
> -- 
> 2.17.0
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-xfs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

  reply	other threads:[~2018-05-30  6:21 UTC|newest]

Thread overview: 83+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-23 14:43 buffered I/O without buffer heads in xfs and iomap v3 Christoph Hellwig
2018-05-23 14:43 ` [PATCH 01/34] block: add a lower-level bio_add_page interface Christoph Hellwig
2018-05-30  5:28   ` Darrick J. Wong
2018-05-23 14:43 ` [PATCH 02/34] fs: factor out a __generic_write_end helper Christoph Hellwig
2018-05-30  5:30   ` Darrick J. Wong
2018-05-23 14:43 ` [PATCH 03/34] fs: move page_cache_seek_hole_data to iomap.c Christoph Hellwig
2018-05-30  5:31   ` Darrick J. Wong
2018-05-23 14:43 ` [PATCH 04/34] fs: remove the buffer_unwritten check in page_seek_hole_data Christoph Hellwig
2018-05-30  5:36   ` Darrick J. Wong
2018-05-23 14:43 ` [PATCH 05/34] fs: use ->is_partially_uptodate in page_cache_seek_hole_data Christoph Hellwig
2018-05-30  5:41   ` Darrick J. Wong
2018-05-23 14:43 ` [PATCH 06/34] mm: give the 'ret' variable a better name __do_page_cache_readahead Christoph Hellwig
2018-05-30  5:42   ` Darrick J. Wong
2018-05-23 14:43 ` [PATCH 07/34] mm: return an unsigned int from __do_page_cache_readahead Christoph Hellwig
2018-05-30  5:44   ` Darrick J. Wong
2018-05-23 14:43 ` [PATCH 08/34] mm: split ->readpages calls to avoid non-contiguous pages lists Christoph Hellwig
2018-05-30  5:46   ` Darrick J. Wong
2018-05-23 14:43 ` [PATCH 09/34] iomap: inline data should be an iomap type, not a flag Christoph Hellwig
2018-05-30  5:49   ` Darrick J. Wong
2018-05-23 14:43 ` [PATCH 10/34] iomap: fix the comment describing IOMAP_NOWAIT Christoph Hellwig
2018-05-30  5:49   ` Darrick J. Wong
2018-05-23 14:43 ` [PATCH 11/34] iomap: move IOMAP_F_BOUNDARY to gfs2 Christoph Hellwig
2018-05-30  5:50   ` Darrick J. Wong
2018-05-30  9:30     ` [Cluster-devel] " Steven Whitehouse
2018-05-30  9:59       ` Christoph Hellwig
2018-05-30 10:02         ` Steven Whitehouse
2018-05-30 10:10           ` Christoph Hellwig
2018-05-30 10:12             ` Steven Whitehouse
2018-05-30 11:03               ` Andreas Gruenbacher
2018-05-23 14:43 ` [PATCH 12/34] iomap: use __bio_add_page in iomap_dio_zero Christoph Hellwig
2018-05-30  5:51   ` Darrick J. Wong
2018-05-23 14:43 ` [PATCH 13/34] iomap: add a iomap_sector helper Christoph Hellwig
2018-05-30  5:52   ` Darrick J. Wong
2018-05-23 14:43 ` [PATCH 14/34] iomap: add an iomap-based bmap implementation Christoph Hellwig
2018-05-30  5:54   ` Darrick J. Wong
2018-05-23 14:43 ` [PATCH 15/34] iomap: add an iomap-based readpage and readpages implementation Christoph Hellwig
2018-05-30  6:11   ` Darrick J. Wong
2018-05-30  6:23     ` Christoph Hellwig
2018-05-23 14:43 ` [PATCH 16/34] iomap: add initial support for writes without buffer heads Christoph Hellwig
2018-05-30  6:21   ` Darrick J. Wong [this message]
2018-05-23 14:43 ` [PATCH 17/34] xfs: use iomap_bmap Christoph Hellwig
2018-05-30  6:14   ` Darrick J. Wong
2018-05-23 14:43 ` [PATCH 18/34] xfs: use iomap for blocksize == PAGE_SIZE readpage and readpages Christoph Hellwig
2018-05-30  6:22   ` Darrick J. Wong
2018-05-23 14:43 ` [PATCH 19/34] xfs: simplify xfs_bmap_punch_delalloc_range Christoph Hellwig
2018-05-23 16:17   ` Brian Foster
2018-05-24  8:01     ` Christoph Hellwig
2018-05-23 14:43 ` [PATCH 20/34] xfs: simplify xfs_aops_discard_page Christoph Hellwig
2018-05-23 14:43 ` [PATCH 21/34] xfs: move locking into xfs_bmap_punch_delalloc_range Christoph Hellwig
2018-05-23 14:43 ` [PATCH 22/34] xfs: make xfs_writepage_map extent map centric Christoph Hellwig
2018-05-24 14:59   ` Brian Foster
2018-05-24 16:53     ` Christoph Hellwig
2018-05-24 18:13       ` Brian Foster
2018-05-25  6:19         ` Christoph Hellwig
2018-05-25 11:35           ` Brian Foster
2018-05-28  7:15             ` Christoph Hellwig
2018-05-29 11:26               ` Brian Foster
2018-05-29 13:08                 ` Christoph Hellwig
2018-05-29 17:04                   ` Brian Foster
2018-05-23 14:43 ` [PATCH 23/34] xfs: remove the now unused XFS_BMAPI_IGSTATE flag Christoph Hellwig
2018-05-23 14:43 ` [PATCH 24/34] xfs: remove xfs_reflink_find_cow_mapping Christoph Hellwig
2018-05-23 14:43 ` [PATCH 25/34] xfs: remove xfs_reflink_trim_irec_to_next_cow Christoph Hellwig
2018-05-24 14:59   ` Brian Foster
2018-05-24 15:06     ` Brian Foster
2018-05-24 17:10       ` Christoph Hellwig
2018-05-23 14:43 ` [PATCH 26/34] xfs: simplify xfs_map_blocks by using xfs_iext_lookup_extent directly Christoph Hellwig
2018-05-23 14:43 ` [PATCH 27/34] xfs: don't clear imap_valid for a non-uptodate buffers Christoph Hellwig
2018-05-23 14:43 ` [PATCH 28/34] xfs: remove the imap_valid flag Christoph Hellwig
2018-05-23 14:43 ` [PATCH 29/34] xfs: don't look at buffer heads in xfs_add_to_ioend Christoph Hellwig
2018-05-23 14:43 ` [PATCH 30/34] xfs: move all writeback buffer_head manipulation into xfs_map_at_offset Christoph Hellwig
2018-05-23 14:43 ` [PATCH 31/34] xfs: remove xfs_start_page_writeback Christoph Hellwig
2018-05-23 14:43 ` [PATCH 32/34] xfs: refactor the tail of xfs_writepage_map Christoph Hellwig
2018-05-23 14:43 ` [PATCH 33/34] xfs: do not set the page uptodate in xfs_writepage_map Christoph Hellwig
2018-05-23 14:43 ` [PATCH 34/34] xfs: allow writeback on pages without buffer heads Christoph Hellwig
  -- strict thread matches above, loose matches on Subject: below --
2018-05-18 16:47 buffered I/O without buffer heads in xfs and iomap v2 Christoph Hellwig
2018-05-18 16:48 ` [PATCH 16/34] iomap: add initial support for writes without buffer heads Christoph Hellwig
2018-05-21 23:27   ` Darrick J. Wong
2018-05-22  0:07     ` Dave Chinner
2018-05-22  8:24       ` Christoph Hellwig
2018-05-22 22:38         ` Dave Chinner
2018-05-23  6:03           ` Christoph Hellwig
2018-05-22  8:20     ` Christoph Hellwig
2018-05-22  8:31     ` Christoph Hellwig
2018-05-22  9:39       ` Christoph Hellwig

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180530062138.GF30110@magnolia \
    --to=darrick.wong@oracle.com \
    --cc=hch@lst.de \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-xfs@vger.kernel.org \
    --subject='Re: [PATCH 16/34] iomap: add initial support for writes without buffer heads' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
on how to clone and mirror all data and code used for this inbox