1 files changed, 101 insertions, 14 deletions

diff --git a/fs/read_write.c b/fs/read_write.c
index 1f5088dec566..59d819c5b92e 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -939,6 +939,34 @@ out:
 	return ret;
 }
 
+ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb,
+			   struct iov_iter *iter)
+{
+	size_t tot_len;
+	ssize_t ret = 0;
+
+	if (!file->f_op->read_iter)
+		return -EINVAL;
+	if (!(file->f_mode & FMODE_READ))
+		return -EBADF;
+	if (!(file->f_mode & FMODE_CAN_READ))
+		return -EINVAL;
+
+	tot_len = iov_iter_count(iter);
+	if (!tot_len)
+		goto out;
+	ret = rw_verify_area(READ, file, &iocb->ki_pos, tot_len);
+	if (ret < 0)
+		return ret;
+
+	ret = call_read_iter(file, iocb, iter);
+out:
+	if (ret >= 0)
+		fsnotify_access(file);
+	return ret;
+}
+EXPORT_SYMBOL(vfs_iocb_iter_read);
+
 ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos,
 		rwf_t flags)
 {
@@ -975,6 +1003,34 @@ static ssize_t do_iter_write(struct file *file, struct iov_iter *iter,
 	return ret;
 }
 
+ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb,
+			    struct iov_iter *iter)
+{
+	size_t tot_len;
+	ssize_t ret = 0;
+
+	if (!file->f_op->write_iter)
+		return -EINVAL;
+	if (!(file->f_mode & FMODE_WRITE))
+		return -EBADF;
+	if (!(file->f_mode & FMODE_CAN_WRITE))
+		return -EINVAL;
+
+	tot_len = iov_iter_count(iter);
+	if (!tot_len)
+		return 0;
+	ret = rw_verify_area(WRITE, file, &iocb->ki_pos, tot_len);
+	if (ret < 0)
+		return ret;
+
+	ret = call_write_iter(file, iocb, iter);
+	if (ret > 0)
+		fsnotify_modify(file);
+
+	return ret;
+}
+EXPORT_SYMBOL(vfs_iocb_iter_write);
+
 ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
 		rwf_t flags)
 {
@@ -1777,10 +1833,9 @@ static int remap_verify_area(struct file *file, loff_t pos, loff_t len,
  * else.  Assume that the offsets have already been checked for block
  * alignment.
  *
- * For deduplication we always scale down to the previous block because we
- * can't meaningfully compare post-EOF contents.
- *
- * For clone we only link a partial EOF block above the destination file's EOF.
+ * For clone we only link a partial EOF block above or at the destination file's
+ * EOF.  For deduplication we accept a partial EOF block only if it ends at the
+ * destination file's EOF (can not link it into the middle of a file).
  *
  * Shorten the request if possible.
  */
@@ -1796,8 +1851,7 @@ static int generic_remap_check_len(struct inode *inode_in,
 	if ((*len & blkmask) == 0)
 		return 0;
 
-	if ((remap_flags & REMAP_FILE_DEDUP) ||
-	    pos_out + *len < i_size_read(inode_out))
+	if (pos_out + *len < i_size_read(inode_out))
 		new_len &= ~blkmask;
 
 	if (new_len == *len)
@@ -1811,10 +1865,7 @@ static int generic_remap_check_len(struct inode *inode_in,
 	return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL;
 }
 
-/*
- * Read a page's worth of file data into the page cache.  Return the page
- * locked.
- */
+/* Read a page's worth of file data into the page cache. */
 static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)
 {
 	struct page *page;
@@ -1826,11 +1877,33 @@ static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)
 		put_page(page);
 		return ERR_PTR(-EIO);
 	}
-	lock_page(page);
 	return page;
 }
 
 /*
+ * Lock two pages, ensuring that we lock in offset order if the pages are from
+ * the same file.
+ */
+static void vfs_lock_two_pages(struct page *page1, struct page *page2)
+{
+	/* Always lock in order of increasing index. */
+	if (page1->index > page2->index)
+		swap(page1, page2);
+
+	lock_page(page1);
+	if (page1 != page2)
+		lock_page(page2);
+}
+
+/* Unlock two pages, being careful not to unlock the same page twice. */
+static void vfs_unlock_two_pages(struct page *page1, struct page *page2)
+{
+	unlock_page(page1);
+	if (page1 != page2)
+		unlock_page(page2);
+}
+
+/*
  * Compare extents of two files to see if they are the same.
  * Caller must have locked both inodes to prevent write races.
  */
@@ -1867,10 +1940,24 @@ static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
 		dest_page = vfs_dedupe_get_page(dest, destoff);
 		if (IS_ERR(dest_page)) {
 			error = PTR_ERR(dest_page);
-			unlock_page(src_page);
 			put_page(src_page);
 			goto out_error;
 		}
+
+		vfs_lock_two_pages(src_page, dest_page);
+
+		/*
+		 * Now that we've locked both pages, make sure they're still
+		 * mapped to the file data we're interested in.  If not,
+		 * someone is invalidating pages on us and we lose.
+		 */
+		if (!PageUptodate(src_page) || !PageUptodate(dest_page) ||
+		    src_page->mapping != src->i_mapping ||
+		    dest_page->mapping != dest->i_mapping) {
+			same = false;
+			goto unlock;
+		}
+
 		src_addr = kmap_atomic(src_page);
 		dest_addr = kmap_atomic(dest_page);
 
@@ -1882,8 +1969,8 @@ static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
 
 		kunmap_atomic(dest_addr);
 		kunmap_atomic(src_addr);
-		unlock_page(dest_page);
-		unlock_page(src_page);
+unlock:
+		vfs_unlock_two_pages(src_page, dest_page);
 		put_page(dest_page);
 		put_page(src_page);