Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull more vfs updates from Al Viro:
 "In this pile:

   - autofs-namespace series
   - dedupe stuff
   - more struct path constification"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (40 commits)
  ocfs2: implement the VFS clone_range, copy_range, and dedupe_range features
  ocfs2: charge quota for reflinked blocks
  ocfs2: fix bad pointer cast
  ocfs2: always unlock when completing dio writes
  ocfs2: don't eat io errors during _dio_end_io_write
  ocfs2: budget for extent tree splits when adding refcount flag
  ocfs2: prohibit refcounted swapfiles
  ocfs2: add newlines to some error messages
  ocfs2: convert inode refcount test to a helper
  simple_write_end(): don't zero in short copy into uptodate
  exofs: don't mess with simple_write_{begin,end}
  9p: saner ->write_end() on failing copy into non-uptodate page
  fix gfs2_stuffed_write_end() on short copies
  fix ceph_write_end()
  nfs_write_end(): fix handling of short copies
  vfs: refactor clone/dedupe_file_range common functions
  fs: try to clone files first in vfs_copy_file_range
  vfs: misc struct path constification
  namespace.c: constify struct path passed to a bunch of primitives
  quota: constify struct path in quota_on
  ...

1 files changed, 226 insertions, 5 deletions

diff --git a/fs/read_write.c b/fs/read_write.c
index 53bccd1c786e..da6de12b5c46 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1540,20 +1540,37 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 
 	sb_start_write(inode_out->i_sb);
 
-	ret = -EOPNOTSUPP;
-	if (file_out->f_op->copy_file_range)
+	/*
+	 * Try cloning first, this is supported by more file systems, and
+	 * more efficient if both clone and copy are supported (e.g. NFS).
+	 */
+	if (file_in->f_op->clone_file_range) {
+		ret = file_in->f_op->clone_file_range(file_in, pos_in,
+				file_out, pos_out, len);
+		if (ret == 0) {
+			ret = len;
+			goto done;
+		}
+	}
+
+	if (file_out->f_op->copy_file_range) {
 		ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out,
 						      pos_out, len, flags);
-	if (ret == -EOPNOTSUPP)
-		ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out,
-				len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0);
+		if (ret != -EOPNOTSUPP)
+			goto done;
+	}
+
+	ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out,
+			len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0);
 
+done:
 	if (ret > 0) {
 		fsnotify_access(file_in);
 		add_rchar(current, ret);
 		fsnotify_modify(file_out);
 		add_wchar(current, ret);
 	}
+
 	inc_syscr(current);
 	inc_syscw(current);
 
@@ -1648,6 +1665,114 @@ static int clone_verify_area(struct file *file, loff_t pos, u64 len, bool write)
 	return security_file_permission(file, write ? MAY_WRITE : MAY_READ);
 }
 
+/*
+ * Check that the two inodes are eligible for cloning, the ranges make
+ * sense, and then flush all dirty data.  Caller must ensure that the
+ * inodes have been locked against any other modifications.
+ */
+int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in,
+			       struct inode *inode_out, loff_t pos_out,
+			       u64 *len, bool is_dedupe)
+{
+	loff_t bs = inode_out->i_sb->s_blocksize;
+	loff_t blen;
+	loff_t isize;
+	bool same_inode = (inode_in == inode_out);
+	int ret;
+
+	/* Don't touch certain kinds of inodes */
+	if (IS_IMMUTABLE(inode_out))
+		return -EPERM;
+
+	if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
+		return -ETXTBSY;
+
+	/* Don't reflink dirs, pipes, sockets... */
+	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
+		return -EISDIR;
+	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+		return -EINVAL;
+
+	/* Are we going all the way to the end? */
+	isize = i_size_read(inode_in);
+	if (isize == 0) {
+		*len = 0;
+		return 0;
+	}
+
+	/* Zero length dedupe exits immediately; reflink goes to EOF. */
+	if (*len == 0) {
+		if (is_dedupe) {
+			*len = 0;
+			return 0;
+		}
+		*len = isize - pos_in;
+	}
+
+	/* Ensure offsets don't wrap and the input is inside i_size */
+	if (pos_in + *len < pos_in || pos_out + *len < pos_out ||
+	    pos_in + *len > isize)
+		return -EINVAL;
+
+	/* Don't allow dedupe past EOF in the dest file */
+	if (is_dedupe) {
+		loff_t	disize;
+
+		disize = i_size_read(inode_out);
+		if (pos_out >= disize || pos_out + *len > disize)
+			return -EINVAL;
+	}
+
+	/* If we're linking to EOF, continue to the block boundary. */
+	if (pos_in + *len == isize)
+		blen = ALIGN(isize, bs) - pos_in;
+	else
+		blen = *len;
+
+	/* Only reflink if we're aligned to block boundaries */
+	if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) ||
+	    !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs))
+		return -EINVAL;
+
+	/* Don't allow overlapped reflink within the same file */
+	if (same_inode) {
+		if (pos_out + blen > pos_in && pos_out < pos_in + blen)
+			return -EINVAL;
+	}
+
+	/* Wait for the completion of any pending IOs on both files */
+	inode_dio_wait(inode_in);
+	if (!same_inode)
+		inode_dio_wait(inode_out);
+
+	ret = filemap_write_and_wait_range(inode_in->i_mapping,
+			pos_in, pos_in + *len - 1);
+	if (ret)
+		return ret;
+
+	ret = filemap_write_and_wait_range(inode_out->i_mapping,
+			pos_out, pos_out + *len - 1);
+	if (ret)
+		return ret;
+
+	/*
+	 * Check that the extents are the same.
+	 */
+	if (is_dedupe) {
+		bool		is_same = false;
+
+		ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
+				inode_out, pos_out, *len, &is_same);
+		if (ret)
+			return ret;
+		if (!is_same)
+			return -EBADE;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(vfs_clone_file_prep_inodes);
+
 int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 		struct file *file_out, loff_t pos_out, u64 len)
 {
@@ -1698,6 +1823,102 @@ int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 }
 EXPORT_SYMBOL(vfs_clone_file_range);
 
+/*
+ * Read a page's worth of file data into the page cache.  Return the page
+ * locked.
+ */
+static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)
+{
+	struct address_space *mapping;
+	struct page *page;
+	pgoff_t n;
+
+	n = offset >> PAGE_SHIFT;
+	mapping = inode->i_mapping;
+	page = read_mapping_page(mapping, n, NULL);
+	if (IS_ERR(page))
+		return page;
+	if (!PageUptodate(page)) {
+		put_page(page);
+		return ERR_PTR(-EIO);
+	}
+	lock_page(page);
+	return page;
+}
+
+/*
+ * Compare extents of two files to see if they are the same.
+ * Caller must have locked both inodes to prevent write races.
+ */
+int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
+				  struct inode *dest, loff_t destoff,
+				  loff_t len, bool *is_same)
+{
+	loff_t src_poff;
+	loff_t dest_poff;
+	void *src_addr;
+	void *dest_addr;
+	struct page *src_page;
+	struct page *dest_page;
+	loff_t cmp_len;
+	bool same;
+	int error;
+
+	error = -EINVAL;
+	same = true;
+	while (len) {
+		src_poff = srcoff & (PAGE_SIZE - 1);
+		dest_poff = destoff & (PAGE_SIZE - 1);
+		cmp_len = min(PAGE_SIZE - src_poff,
+			      PAGE_SIZE - dest_poff);
+		cmp_len = min(cmp_len, len);
+		if (cmp_len <= 0)
+			goto out_error;
+
+		src_page = vfs_dedupe_get_page(src, srcoff);
+		if (IS_ERR(src_page)) {
+			error = PTR_ERR(src_page);
+			goto out_error;
+		}
+		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;
+		}
+		src_addr = kmap_atomic(src_page);
+		dest_addr = kmap_atomic(dest_page);
+
+		flush_dcache_page(src_page);
+		flush_dcache_page(dest_page);
+
+		if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len))
+			same = false;
+
+		kunmap_atomic(dest_addr);
+		kunmap_atomic(src_addr);
+		unlock_page(dest_page);
+		unlock_page(src_page);
+		put_page(dest_page);
+		put_page(src_page);
+
+		if (!same)
+			break;
+
+		srcoff += cmp_len;
+		destoff += cmp_len;
+		len -= cmp_len;
+	}
+
+	*is_same = same;
+	return 0;
+
+out_error:
+	return error;
+}
+EXPORT_SYMBOL(vfs_dedupe_file_range_compare);
+
 int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
 {
 	struct file_dedupe_range_info *info;