linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Darrick J. Wong" <djwong@kernel.org>
To: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Cc: linux-kernel@vger.kernel.org, linux-xfs@vger.kernel.org,
	nvdimm@lists.linux.dev, linux-fsdevel@vger.kernel.org,
	david@fromorbit.com, dan.j.williams@intel.com,
	akpm@linux-foundation.org
Subject: Re: [PATCH v2 3/8] fsdax: zero the edges if source is HOLE or UNWRITTEN
Date: Thu, 1 Dec 2022 15:58:11 -0800	[thread overview]
Message-ID: <Y4k/kxuPOirdlctI@magnolia> (raw)
In-Reply-To: <1669908538-55-4-git-send-email-ruansy.fnst@fujitsu.com>

On Thu, Dec 01, 2022 at 03:28:53PM +0000, Shiyang Ruan wrote:
> If srcmap contains invalid data, such as HOLE and UNWRITTEN, the dest
> page should be zeroed.  Otherwise, since it's a pmem, old data may
> remains on the dest page, the result of CoW will be incorrect.
> 
> The function name is also not easy to understand, rename it to
> "dax_iomap_copy_around()", which means it copys data around the range.
> 
> Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
> ---
>  fs/dax.c | 78 ++++++++++++++++++++++++++++++++++----------------------
>  1 file changed, 48 insertions(+), 30 deletions(-)
> 
> diff --git a/fs/dax.c b/fs/dax.c
> index 482dda85ccaf..6b6e07ad8d80 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -1092,7 +1092,7 @@ static int dax_iomap_direct_access(const struct iomap *iomap, loff_t pos,
>  }
>  
>  /**
> - * dax_iomap_cow_copy - Copy the data from source to destination before write
> + * dax_iomap_copy_around - Copy the data from source to destination before write

 * dax_iomap_copy_around - Prepare for an unaligned write to a
 * shared/cow page by copying the data before and after the range to be
 * written.

Other than that, this make sense,
Reviewed-by: Darrick J. Wong <djwong@kernel.org>

--D

>   * @pos:	address to do copy from.
>   * @length:	size of copy operation.
>   * @align_size:	aligned w.r.t align_size (either PMD_SIZE or PAGE_SIZE)
> @@ -1101,35 +1101,50 @@ static int dax_iomap_direct_access(const struct iomap *iomap, loff_t pos,
>   *
>   * This can be called from two places. Either during DAX write fault (page
>   * aligned), to copy the length size data to daddr. Or, while doing normal DAX
> - * write operation, dax_iomap_actor() might call this to do the copy of either
> + * write operation, dax_iomap_iter() might call this to do the copy of either
>   * start or end unaligned address. In the latter case the rest of the copy of
> - * aligned ranges is taken care by dax_iomap_actor() itself.
> + * aligned ranges is taken care by dax_iomap_iter() itself.
> + * If the srcmap contains invalid data, such as HOLE and UNWRITTEN, zero the
> + * area to make sure no old data remains.
>   */
> -static int dax_iomap_cow_copy(loff_t pos, uint64_t length, size_t align_size,
> +static int dax_iomap_copy_around(loff_t pos, uint64_t length, size_t align_size,
>  		const struct iomap *srcmap, void *daddr)
>  {
>  	loff_t head_off = pos & (align_size - 1);
>  	size_t size = ALIGN(head_off + length, align_size);
>  	loff_t end = pos + length;
>  	loff_t pg_end = round_up(end, align_size);
> +	/* copy_all is usually in page fault case */
>  	bool copy_all = head_off == 0 && end == pg_end;
> +	/* zero the edges if srcmap is a HOLE or IOMAP_UNWRITTEN */
> +	bool zero_edge = srcmap->flags & IOMAP_F_SHARED ||
> +			 srcmap->type == IOMAP_UNWRITTEN;
>  	void *saddr = 0;
>  	int ret = 0;
>  
> -	ret = dax_iomap_direct_access(srcmap, pos, size, &saddr, NULL);
> -	if (ret)
> -		return ret;
> +	if (!zero_edge) {
> +		ret = dax_iomap_direct_access(srcmap, pos, size, &saddr, NULL);
> +		if (ret)
> +			return ret;
> +	}
>  
>  	if (copy_all) {
> -		ret = copy_mc_to_kernel(daddr, saddr, length);
> -		return ret ? -EIO : 0;
> +		if (zero_edge)
> +			memset(daddr, 0, size);
> +		else
> +			ret = copy_mc_to_kernel(daddr, saddr, length);
> +		goto out;
>  	}
>  
>  	/* Copy the head part of the range */
>  	if (head_off) {
> -		ret = copy_mc_to_kernel(daddr, saddr, head_off);
> -		if (ret)
> -			return -EIO;
> +		if (zero_edge)
> +			memset(daddr, 0, head_off);
> +		else {
> +			ret = copy_mc_to_kernel(daddr, saddr, head_off);
> +			if (ret)
> +				return -EIO;
> +		}
>  	}
>  
>  	/* Copy the tail part of the range */
> @@ -1137,12 +1152,19 @@ static int dax_iomap_cow_copy(loff_t pos, uint64_t length, size_t align_size,
>  		loff_t tail_off = head_off + length;
>  		loff_t tail_len = pg_end - end;
>  
> -		ret = copy_mc_to_kernel(daddr + tail_off, saddr + tail_off,
> -					tail_len);
> -		if (ret)
> -			return -EIO;
> +		if (zero_edge)
> +			memset(daddr + tail_off, 0, tail_len);
> +		else {
> +			ret = copy_mc_to_kernel(daddr + tail_off,
> +						saddr + tail_off, tail_len);
> +			if (ret)
> +				return -EIO;
> +		}
>  	}
> -	return 0;
> +out:
> +	if (zero_edge)
> +		dax_flush(srcmap->dax_dev, daddr, size);
> +	return ret ? -EIO : 0;
>  }
>  
>  /*
> @@ -1241,13 +1263,10 @@ static int dax_memzero(struct iomap_iter *iter, loff_t pos, size_t size)
>  	if (ret < 0)
>  		return ret;
>  	memset(kaddr + offset, 0, size);
> -	if (srcmap->addr != iomap->addr) {
> -		ret = dax_iomap_cow_copy(pos, size, PAGE_SIZE, srcmap,
> -					 kaddr);
> -		if (ret < 0)
> -			return ret;
> -		dax_flush(iomap->dax_dev, kaddr, PAGE_SIZE);
> -	} else
> +	if (iomap->flags & IOMAP_F_SHARED)
> +		ret = dax_iomap_copy_around(pos, size, PAGE_SIZE, srcmap,
> +					    kaddr);
> +	else
>  		dax_flush(iomap->dax_dev, kaddr + offset, size);
>  	return ret;
>  }
> @@ -1401,8 +1420,8 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
>  		}
>  
>  		if (cow) {
> -			ret = dax_iomap_cow_copy(pos, length, PAGE_SIZE, srcmap,
> -						 kaddr);
> +			ret = dax_iomap_copy_around(pos, length, PAGE_SIZE,
> +						    srcmap, kaddr);
>  			if (ret)
>  				break;
>  		}
> @@ -1547,7 +1566,7 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf,
>  		struct xa_state *xas, void **entry, bool pmd)
>  {
>  	const struct iomap *iomap = &iter->iomap;
> -	const struct iomap *srcmap = &iter->srcmap;
> +	const struct iomap *srcmap = iomap_iter_srcmap(iter);
>  	size_t size = pmd ? PMD_SIZE : PAGE_SIZE;
>  	loff_t pos = (loff_t)xas->xa_index << PAGE_SHIFT;
>  	bool write = iter->flags & IOMAP_WRITE;
> @@ -1578,9 +1597,8 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf,
>  
>  	*entry = dax_insert_entry(xas, vmf, iter, *entry, pfn, entry_flags);
>  
> -	if (write &&
> -	    srcmap->type != IOMAP_HOLE && srcmap->addr != iomap->addr) {
> -		err = dax_iomap_cow_copy(pos, size, size, srcmap, kaddr);
> +	if (write && iomap->flags & IOMAP_F_SHARED) {
> +		err = dax_iomap_copy_around(pos, size, size, srcmap, kaddr);
>  		if (err)
>  			return dax_fault_return(err);
>  	}
> -- 
> 2.38.1
> 

  reply	other threads:[~2022-12-01 23:58 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-12-01 15:28 [PATCH v2 0/8] fsdax,xfs: fix warning messages Shiyang Ruan
2022-12-01 15:28 ` [PATCH v2 1/8] fsdax: introduce page->share for fsdax in reflink mode Shiyang Ruan
2022-12-01 16:14   ` Darrick J. Wong
2022-12-02  9:23   ` [PATCH v2.1 " Shiyang Ruan
2022-12-02 20:18     ` Andrew Morton
2022-12-03  0:19     ` Allison Henderson
2022-12-03  2:07     ` Dan Williams
2022-12-05  5:56       ` Shiyang Ruan
2022-12-05  7:01         ` Darrick J. Wong
2022-12-07  2:49   ` [PATCH v2.2 " Shiyang Ruan
2022-12-08  1:26     ` Darrick J. Wong
2022-12-01 15:28 ` [PATCH v2 2/8] fsdax: invalidate pages when CoW Shiyang Ruan
2022-12-01 16:17   ` Darrick J. Wong
2022-12-01 15:28 ` [PATCH v2 3/8] fsdax: zero the edges if source is HOLE or UNWRITTEN Shiyang Ruan
2022-12-01 23:58   ` Darrick J. Wong [this message]
2022-12-02  0:39     ` Andrew Morton
2022-12-02  9:25   ` [PATCH v2.1 " Shiyang Ruan
2022-12-03  0:19     ` Allison Henderson
2022-12-01 15:28 ` [PATCH v2 4/8] fsdax,xfs: set the shared flag when file extent is shared Shiyang Ruan
2022-12-02  0:05   ` Darrick J. Wong
2022-12-01 15:31 ` [PATCH v2 5/8] fsdax: dedupe: iter two files at the same time Shiyang Ruan
2022-12-02  0:05   ` Darrick J. Wong
2022-12-01 15:32 ` [PATCH v2 6/8] xfs: use dax ops for zero and truncate in fsdax mode Shiyang Ruan
2022-12-02  0:05   ` Darrick J. Wong
2022-12-01 15:32 ` [PATCH v2 7/8] fsdax,xfs: port unshare to fsdax Shiyang Ruan
2022-12-01 15:32 ` [PATCH v2 8/8] xfs: remove restrictions for fsdax and reflink Shiyang Ruan
2022-12-02  0:06   ` Darrick J. Wong
2022-12-03  1:21 ` [PATCH v2 0/8] fsdax,xfs: fix warning messages Dan Williams
2022-12-29  8:23   ` Shiyang Ruan

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=Y4k/kxuPOirdlctI@magnolia \
    --to=djwong@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=dan.j.williams@intel.com \
    --cc=david@fromorbit.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=nvdimm@lists.linux.dev \
    --cc=ruansy.fnst@fujitsu.com \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).