diff mbox series

[3/3] netfs: fix test for whether we can skip read when writing beyond EOF

Message ID 162367683365.460125.4467036947364047314.stgit@warthog.procyon.org.uk (mailing list archive)
State New, archived
Headers show
Series [1/3] afs: Handle len being extending over page end in write_begin/write_end | expand

Commit Message

David Howells June 14, 2021, 1:20 p.m. UTC 
From: Jeff Layton <jlayton@kernel.org>

It's not sufficient to skip reading when the pos is beyond the EOF.
There may be data at the head of the page that we need to fill in
before the write.

Add a new helper function that corrects and clarifies the logic of
when we can skip reads, and have it only zero out the part of the page
that won't have data copied in for the write.

Finally, don't set the page Uptodate after zeroing. It's not up to date
since the write data won't have been copied in yet.

[DH made the following changes:

 - Prefixed the new function with "netfs_".

 - Don't call zero_user_segments() for a full-page write.

 - Altered the beyond-last-page check to avoid a DIV instruction and got
   rid of then-redundant zero-length file check.
]

Fixes: e1b1240c1ff5f ("netfs: Add write_begin helper")
Reported-by: Andrew W Elble <aweits@rit.edu>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: ceph-devel@vger.kernel.org
Link: https://lore.kernel.org/r/20210613233345.113565-1-jlayton@kernel.org/
---

 fs/netfs/read_helper.c |   49 +++++++++++++++++++++++++++++++++++-------------
 1 file changed, 36 insertions(+), 13 deletions(-)

Comments

David Howells June 14, 2021, 1:33 p.m. UTC | #1 
David Howells <dhowells@redhat.com> wrote:

> +static noinline bool netfs_skip_page_read(struct page *page, loff_t pos, size_t len)

I should've removed the "noinline".

David
Jeff Layton June 15, 2021, 5:01 p.m. UTC | #2 
On Mon, 2021-06-14 at 14:20 +0100, David Howells wrote:
> From: Jeff Layton <jlayton@kernel.org>
> 
> It's not sufficient to skip reading when the pos is beyond the EOF.
> There may be data at the head of the page that we need to fill in
> before the write.
> 
> Add a new helper function that corrects and clarifies the logic of
> when we can skip reads, and have it only zero out the part of the page
> that won't have data copied in for the write.
> 
> Finally, don't set the page Uptodate after zeroing. It's not up to date
> since the write data won't have been copied in yet.
> 
> [DH made the following changes:
> 
>  - Prefixed the new function with "netfs_".
> 
>  - Don't call zero_user_segments() for a full-page write.
> 
>  - Altered the beyond-last-page check to avoid a DIV instruction and got
>    rid of then-redundant zero-length file check.
> ]
> 
> Fixes: e1b1240c1ff5f ("netfs: Add write_begin helper")
> Reported-by: Andrew W Elble <aweits@rit.edu>
> Signed-off-by: Jeff Layton <jlayton@kernel.org>
> Signed-off-by: David Howells <dhowells@redhat.com>
> cc: ceph-devel@vger.kernel.org
> Link: https://lore.kernel.org/r/20210613233345.113565-1-jlayton@kernel.org/
> ---
> 
>  fs/netfs/read_helper.c |   49 +++++++++++++++++++++++++++++++++++-------------
>  1 file changed, 36 insertions(+), 13 deletions(-)
> 
> diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c
> index 725614625ed4..70a5b1a19a50 100644
> --- a/fs/netfs/read_helper.c
> +++ b/fs/netfs/read_helper.c
> @@ -1011,12 +1011,42 @@ int netfs_readpage(struct file *file,
>  }
>  EXPORT_SYMBOL(netfs_readpage);
>  
> -static void netfs_clear_thp(struct page *page)
> +/**
> + * netfs_skip_page_read - prep a page for writing without reading first
> + * @page: page being prepared
> + * @pos: starting position for the write
> + * @len: length of write
> + *
> + * In some cases, write_begin doesn't need to read at all:
> + * - full page write
> + * - write that lies in a page that is completely beyond EOF
> + * - write that covers the the page from start to EOF or beyond it
> + *
> + * If any of these criteria are met, then zero out the unwritten parts
> + * of the page and return true. Otherwise, return false.
> + */
> +static noinline bool netfs_skip_page_read(struct page *page, loff_t pos, size_t len)
>  {
> -	unsigned int i;
> +	struct inode *inode = page->mapping->host;
> +	loff_t i_size = i_size_read(inode);
> +	size_t offset = offset_in_thp(page, pos);
> +
> +	/* Full page write */
> +	if (offset == 0 && len >= thp_size(page))
> +		return true;
> +
> +	/* pos beyond last page in the file */
> +	if (pos - offset >= i_size)
> +		goto zero_out;
> +
> +	/* Write that covers from the start of the page to EOF or beyond */
> +	if (offset == 0 && (pos + len) >= i_size)
> +		goto zero_out;
>  
> -	for (i = 0; i < thp_nr_pages(page); i++)
> -		clear_highpage(page + i);
> +	return false;
> +zero_out:
> +	zero_user_segments(page, 0, offset, offset + len, thp_size(page));
> +	return true;
>  }
>  
>  /**
> @@ -1024,7 +1054,7 @@ static void netfs_clear_thp(struct page *page)
>   * @file: The file to read from
>   * @mapping: The mapping to read from
>   * @pos: File position at which the write will begin
> - * @len: The length of the write in this page
> + * @len: The length of the write (may extend beyond the end of the page chosen)
>   * @flags: AOP_* flags
>   * @_page: Where to put the resultant page
>   * @_fsdata: Place for the netfs to store a cookie
> @@ -1061,8 +1091,6 @@ int netfs_write_begin(struct file *file, struct address_space *mapping,
>  	struct inode *inode = file_inode(file);
>  	unsigned int debug_index = 0;
>  	pgoff_t index = pos >> PAGE_SHIFT;
> -	int pos_in_page = pos & ~PAGE_MASK;
> -	loff_t size;
>  	int ret;
>  
>  	DEFINE_READAHEAD(ractl, file, NULL, mapping, index);
> @@ -1090,13 +1118,8 @@ int netfs_write_begin(struct file *file, struct address_space *mapping,
>  	 * within the cache granule containing the EOF, in which case we need
>  	 * to preload the granule.
>  	 */
> -	size = i_size_read(inode);
>  	if (!ops->is_cache_enabled(inode) &&
> -	    ((pos_in_page == 0 && len == thp_size(page)) ||
> -	     (pos >= size) ||
> -	     (pos_in_page == 0 && (pos + len) >= size))) {
> -		netfs_clear_thp(page);
> -		SetPageUptodate(page);
> +	    netfs_skip_page_read(page, pos, len)) {
>  		netfs_stat(&netfs_n_rh_write_zskip);
>  		goto have_page_no_wait;
>  	}
> 
> 

I've gone ahead and merged this into the ceph/testing branch since it is
a data corruptor. Once this patch goes into mainline, we'll drop that
patch and rebase onto that commit.
diff mbox series

Patch

diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c
index 725614625ed4..70a5b1a19a50 100644
--- a/fs/netfs/read_helper.c
+++ b/fs/netfs/read_helper.c
@@ -1011,12 +1011,42 @@  int netfs_readpage(struct file *file,
 }
 EXPORT_SYMBOL(netfs_readpage);
 
-static void netfs_clear_thp(struct page *page)
+/**
+ * netfs_skip_page_read - prep a page for writing without reading first
+ * @page: page being prepared
+ * @pos: starting position for the write
+ * @len: length of write
+ *
+ * In some cases, write_begin doesn't need to read at all:
+ * - full page write
+ * - write that lies in a page that is completely beyond EOF
+ * - write that covers the the page from start to EOF or beyond it
+ *
+ * If any of these criteria are met, then zero out the unwritten parts
+ * of the page and return true. Otherwise, return false.
+ */
+static noinline bool netfs_skip_page_read(struct page *page, loff_t pos, size_t len)
 {
-	unsigned int i;
+	struct inode *inode = page->mapping->host;
+	loff_t i_size = i_size_read(inode);
+	size_t offset = offset_in_thp(page, pos);
+
+	/* Full page write */
+	if (offset == 0 && len >= thp_size(page))
+		return true;
+
+	/* pos beyond last page in the file */
+	if (pos - offset >= i_size)
+		goto zero_out;
+
+	/* Write that covers from the start of the page to EOF or beyond */
+	if (offset == 0 && (pos + len) >= i_size)
+		goto zero_out;
 
-	for (i = 0; i < thp_nr_pages(page); i++)
-		clear_highpage(page + i);
+	return false;
+zero_out:
+	zero_user_segments(page, 0, offset, offset + len, thp_size(page));
+	return true;
 }
 
 /**
@@ -1024,7 +1054,7 @@  static void netfs_clear_thp(struct page *page)
  * @file: The file to read from
  * @mapping: The mapping to read from
  * @pos: File position at which the write will begin
- * @len: The length of the write in this page
+ * @len: The length of the write (may extend beyond the end of the page chosen)
  * @flags: AOP_* flags
  * @_page: Where to put the resultant page
  * @_fsdata: Place for the netfs to store a cookie
@@ -1061,8 +1091,6 @@  int netfs_write_begin(struct file *file, struct address_space *mapping,
 	struct inode *inode = file_inode(file);
 	unsigned int debug_index = 0;
 	pgoff_t index = pos >> PAGE_SHIFT;
-	int pos_in_page = pos & ~PAGE_MASK;
-	loff_t size;
 	int ret;
 
 	DEFINE_READAHEAD(ractl, file, NULL, mapping, index);
@@ -1090,13 +1118,8 @@  int netfs_write_begin(struct file *file, struct address_space *mapping,
 	 * within the cache granule containing the EOF, in which case we need
 	 * to preload the granule.
 	 */
-	size = i_size_read(inode);
 	if (!ops->is_cache_enabled(inode) &&
-	    ((pos_in_page == 0 && len == thp_size(page)) ||
-	     (pos >= size) ||
-	     (pos_in_page == 0 && (pos + len) >= size))) {
-		netfs_clear_thp(page);
-		SetPageUptodate(page);
+	    netfs_skip_page_read(page, pos, len)) {
 		netfs_stat(&netfs_n_rh_write_zskip);
 		goto have_page_no_wait;
 	}