iomap: don't mark the inode dirty in iomap_write_end

Marking the inode dirty for each page copied into the page cache can be
very inefficient for file systems that use the VFS dirty inode tracking,
and is completely pointless for those that don't use the VFS dirty inode
tracking.  So instead, only set an iomap flag when changing the in-core
inode size, and open code the rest of __generic_write_end.

Partially based on code from Christoph Hellwig.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>

diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index c78ccaf..8e87686 100644 (file)
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -1179,6 +1179,8 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length,
 
        if (ip->i_qadata && ip->i_qadata->qa_qd_num)
                gfs2_quota_unlock(ip);
+       if (iomap->flags & IOMAP_F_SIZE_CHANGED)
+               mark_inode_dirty(inode);
        gfs2_write_unlock(inode);
 
 out:

diff --git a/fs/iomap.c b/fs/iomap.c
index 23ef63f..c4acf69 100644 (file)
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -773,6 +773,7 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
                unsigned copied, struct page *page, struct iomap *iomap)
 {
        const struct iomap_page_ops *page_ops = iomap->page_ops;
+       loff_t old_size = inode->i_size;
        int ret;
 
        if (iomap->type == IOMAP_INLINE) {
@@ -784,7 +785,19 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
                ret = __iomap_write_end(inode, pos, len, copied, page, iomap);
        }
 
-       __generic_write_end(inode, pos, ret, page);
+       /*
+        * Update the in-memory inode size after copying the data into the page
+        * cache.  It's up to the file system to write the updated size to disk,
+        * preferably after I/O completion so that no stale data is exposed.
+        */
+       if (pos + ret > old_size) {
+               i_size_write(inode, pos + ret);
+               iomap->flags |= IOMAP_F_SIZE_CHANGED;
+       }
+       unlock_page(page);
+
+       if (old_size < pos)
+               pagecache_isize_extended(inode, old_size, pos);
        if (page_ops && page_ops->page_done)
                page_ops->page_done(inode, pos, copied, page, iomap);
        put_page(page);

diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 2103b94..1df9ea1 100644 (file)
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -35,6 +35,7 @@ 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 */
+#define IOMAP_F_SIZE_CHANGED   0x08    /* file size has changed */
 
 /*
  * Flags that only need to be reported for IOMAP_REPORT requests: