Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Thu, 17 Sep 2020 15:00:03 -0700
From:   "Darrick J. Wong" <darrick.wong@oracle.com>
To:     "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc:     linux-xfs@vger.kernel.org, linux-fsdevel@vger.kernel.org,
        Christoph Hellwig <hch@infradead.org>,
        linux-nvdimm@lists.01.org, linux-kernel@vger.kernel.org,
        Dave Kleikamp <shaggy@kernel.org>,
        jfs-discussion@lists.sourceforge.net,
        Dave Chinner <dchinner@redhat.com>
Subject: Re: [PATCH v2 5/9] iomap: Support arbitrarily many blocks per page
Message-ID: <20200917220003.GN7955@magnolia>
References: <20200910234707.5504-1-willy@infradead.org>
 <20200910234707.5504-6-willy@infradead.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20200910234707.5504-6-willy@infradead.org>
Precedence: bulk

On Fri, Sep 11, 2020 at 12:47:03AM +0100, Matthew Wilcox (Oracle) wrote:
> Size the uptodate array dynamically to support larger pages in the
> page cache.  With a 64kB page, we're only saving 8 bytes per page today,
> but with a 2MB maximum page size, we'd have to allocate more than 4kB
> per page.  Add a few debugging assertions.
> 
> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
> Reviewed-by: Dave Chinner <dchinner@redhat.com>

Looks ok,
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>

--D

> ---
>  fs/iomap/buffered-io.c | 22 +++++++++++++++++-----
>  1 file changed, 17 insertions(+), 5 deletions(-)
> 
> diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
> index 7fc0e02d27b0..9670c096b83e 100644
> --- a/fs/iomap/buffered-io.c
> +++ b/fs/iomap/buffered-io.c
> @@ -22,18 +22,25 @@
>  #include "../internal.h"
>  
>  /*
> - * Structure allocated for each page when block size < PAGE_SIZE to track
> - * sub-page uptodate status and I/O completions.
> + * Structure allocated for each page or THP when block size < page size
> + * to track sub-page uptodate status and I/O completions.
>   */
>  struct iomap_page {
>  	atomic_t		read_count;
>  	atomic_t		write_count;
>  	spinlock_t		uptodate_lock;
> -	DECLARE_BITMAP(uptodate, PAGE_SIZE / 512);
> +	unsigned long		uptodate[];
>  };
>  
>  static inline struct iomap_page *to_iomap_page(struct page *page)
>  {
> +	/*
> +	 * per-block data is stored in the head page.  Callers should
> +	 * not be dealing with tail pages (and if they are, they can
> +	 * call thp_head() first.
> +	 */
> +	VM_BUG_ON_PGFLAGS(PageTail(page), page);
> +
>  	if (page_has_private(page))
>  		return (struct iomap_page *)page_private(page);
>  	return NULL;
> @@ -45,11 +52,13 @@ static struct iomap_page *
>  iomap_page_create(struct inode *inode, struct page *page)
>  {
>  	struct iomap_page *iop = to_iomap_page(page);
> +	unsigned int nr_blocks = i_blocks_per_page(inode, page);
>  
> -	if (iop || i_blocks_per_page(inode, page) <= 1)
> +	if (iop || nr_blocks <= 1)
>  		return iop;
>  
> -	iop = kzalloc(sizeof(*iop), GFP_NOFS | __GFP_NOFAIL);
> +	iop = kzalloc(struct_size(iop, uptodate, BITS_TO_LONGS(nr_blocks)),
> +			GFP_NOFS | __GFP_NOFAIL);
>  	spin_lock_init(&iop->uptodate_lock);
>  	attach_page_private(page, iop);
>  	return iop;
> @@ -59,11 +68,14 @@ static void
>  iomap_page_release(struct page *page)
>  {
>  	struct iomap_page *iop = detach_page_private(page);
> +	unsigned int nr_blocks = i_blocks_per_page(page->mapping->host, page);
>  
>  	if (!iop)
>  		return;
>  	WARN_ON_ONCE(atomic_read(&iop->read_count));
>  	WARN_ON_ONCE(atomic_read(&iop->write_count));
> +	WARN_ON_ONCE(bitmap_full(iop->uptodate, nr_blocks) !=
> +			PageUptodate(page));
>  	kfree(iop);
>  }
>  
> -- 
> 2.28.0
>