|
@@ -2490,136 +2490,43 @@ static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
|
|
|
}
|
|
|
}
|
|
|
|
|
|
-static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
|
|
|
- u64 off, u64 olen, u64 destoff)
|
|
|
+/**
|
|
|
+ * btrfs_clone() - clone a range from inode file to another
|
|
|
+ *
|
|
|
+ * @src: Inode to clone from
|
|
|
+ * @inode: Inode to clone to
|
|
|
+ * @off: Offset within source to start clone from
|
|
|
+ * @olen: Original length, passed by user, of range to clone
|
|
|
+ * @olen_aligned: Block-aligned value of olen, extent_same uses
|
|
|
+ * identical values here
|
|
|
+ * @destoff: Offset within @inode to start clone
|
|
|
+ */
|
|
|
+static int btrfs_clone(struct inode *src, struct inode *inode,
|
|
|
+ u64 off, u64 olen, u64 olen_aligned, u64 destoff)
|
|
|
{
|
|
|
- struct inode *inode = file_inode(file);
|
|
|
struct btrfs_root *root = BTRFS_I(inode)->root;
|
|
|
- struct fd src_file;
|
|
|
- struct inode *src;
|
|
|
- struct btrfs_trans_handle *trans;
|
|
|
- struct btrfs_path *path;
|
|
|
+ struct btrfs_path *path = NULL;
|
|
|
struct extent_buffer *leaf;
|
|
|
- char *buf;
|
|
|
+ struct btrfs_trans_handle *trans;
|
|
|
+ char *buf = NULL;
|
|
|
struct btrfs_key key;
|
|
|
u32 nritems;
|
|
|
int slot;
|
|
|
int ret;
|
|
|
- u64 len = olen;
|
|
|
- u64 bs = root->fs_info->sb->s_blocksize;
|
|
|
- int same_inode = 0;
|
|
|
-
|
|
|
- /*
|
|
|
- * TODO:
|
|
|
- * - split compressed inline extents. annoying: we need to
|
|
|
- * decompress into destination's address_space (the file offset
|
|
|
- * may change, so source mapping won't do), then recompress (or
|
|
|
- * otherwise reinsert) a subrange.
|
|
|
- * - allow ranges within the same file to be cloned (provided
|
|
|
- * they don't overlap)?
|
|
|
- */
|
|
|
-
|
|
|
- /* the destination must be opened for writing */
|
|
|
- if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND))
|
|
|
- return -EINVAL;
|
|
|
-
|
|
|
- if (btrfs_root_readonly(root))
|
|
|
- return -EROFS;
|
|
|
-
|
|
|
- ret = mnt_want_write_file(file);
|
|
|
- if (ret)
|
|
|
- return ret;
|
|
|
-
|
|
|
- src_file = fdget(srcfd);
|
|
|
- if (!src_file.file) {
|
|
|
- ret = -EBADF;
|
|
|
- goto out_drop_write;
|
|
|
- }
|
|
|
-
|
|
|
- ret = -EXDEV;
|
|
|
- if (src_file.file->f_path.mnt != file->f_path.mnt)
|
|
|
- goto out_fput;
|
|
|
-
|
|
|
- src = file_inode(src_file.file);
|
|
|
-
|
|
|
- ret = -EINVAL;
|
|
|
- if (src == inode)
|
|
|
- same_inode = 1;
|
|
|
-
|
|
|
- /* the src must be open for reading */
|
|
|
- if (!(src_file.file->f_mode & FMODE_READ))
|
|
|
- goto out_fput;
|
|
|
-
|
|
|
- /* don't make the dst file partly checksummed */
|
|
|
- if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
|
|
|
- (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM))
|
|
|
- goto out_fput;
|
|
|
-
|
|
|
- ret = -EISDIR;
|
|
|
- if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode))
|
|
|
- goto out_fput;
|
|
|
-
|
|
|
- ret = -EXDEV;
|
|
|
- if (src->i_sb != inode->i_sb)
|
|
|
- goto out_fput;
|
|
|
+ u64 len = olen_aligned;
|
|
|
|
|
|
ret = -ENOMEM;
|
|
|
buf = vmalloc(btrfs_level_size(root, 0));
|
|
|
if (!buf)
|
|
|
- goto out_fput;
|
|
|
+ return ret;
|
|
|
|
|
|
path = btrfs_alloc_path();
|
|
|
if (!path) {
|
|
|
vfree(buf);
|
|
|
- goto out_fput;
|
|
|
- }
|
|
|
- path->reada = 2;
|
|
|
-
|
|
|
- if (!same_inode) {
|
|
|
- if (inode < src) {
|
|
|
- mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT);
|
|
|
- mutex_lock_nested(&src->i_mutex, I_MUTEX_CHILD);
|
|
|
- } else {
|
|
|
- mutex_lock_nested(&src->i_mutex, I_MUTEX_PARENT);
|
|
|
- mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
|
|
|
- }
|
|
|
- } else {
|
|
|
- mutex_lock(&src->i_mutex);
|
|
|
- }
|
|
|
-
|
|
|
- /* determine range to clone */
|
|
|
- ret = -EINVAL;
|
|
|
- if (off + len > src->i_size || off + len < off)
|
|
|
- goto out_unlock;
|
|
|
- if (len == 0)
|
|
|
- olen = len = src->i_size - off;
|
|
|
- /* if we extend to eof, continue to block boundary */
|
|
|
- if (off + len == src->i_size)
|
|
|
- len = ALIGN(src->i_size, bs) - off;
|
|
|
-
|
|
|
- /* verify the end result is block aligned */
|
|
|
- if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs) ||
|
|
|
- !IS_ALIGNED(destoff, bs))
|
|
|
- goto out_unlock;
|
|
|
-
|
|
|
- /* verify if ranges are overlapped within the same file */
|
|
|
- if (same_inode) {
|
|
|
- if (destoff + len > off && destoff < off + len)
|
|
|
- goto out_unlock;
|
|
|
- }
|
|
|
-
|
|
|
- if (destoff > inode->i_size) {
|
|
|
- ret = btrfs_cont_expand(inode, inode->i_size, destoff);
|
|
|
- if (ret)
|
|
|
- goto out_unlock;
|
|
|
+ return ret;
|
|
|
}
|
|
|
|
|
|
- /* truncate page cache pages from target inode range */
|
|
|
- truncate_inode_pages_range(&inode->i_data, destoff,
|
|
|
- PAGE_CACHE_ALIGN(destoff + len) - 1);
|
|
|
-
|
|
|
- lock_extent_range(src, off, len);
|
|
|
-
|
|
|
+ path->reada = 2;
|
|
|
/* clone data */
|
|
|
key.objectid = btrfs_ino(src);
|
|
|
key.type = BTRFS_EXTENT_DATA_KEY;
|
|
@@ -2865,15 +2772,132 @@ next:
|
|
|
key.offset++;
|
|
|
}
|
|
|
ret = 0;
|
|
|
+
|
|
|
out:
|
|
|
btrfs_release_path(path);
|
|
|
+ btrfs_free_path(path);
|
|
|
+ vfree(buf);
|
|
|
+ return ret;
|
|
|
+}
|
|
|
+
|
|
|
+static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
|
|
|
+ u64 off, u64 olen, u64 destoff)
|
|
|
+{
|
|
|
+ struct inode *inode = fdentry(file)->d_inode;
|
|
|
+ struct btrfs_root *root = BTRFS_I(inode)->root;
|
|
|
+ struct fd src_file;
|
|
|
+ struct inode *src;
|
|
|
+ int ret;
|
|
|
+ u64 len = olen;
|
|
|
+ u64 bs = root->fs_info->sb->s_blocksize;
|
|
|
+ int same_inode = 0;
|
|
|
+
|
|
|
+ /*
|
|
|
+ * TODO:
|
|
|
+ * - split compressed inline extents. annoying: we need to
|
|
|
+ * decompress into destination's address_space (the file offset
|
|
|
+ * may change, so source mapping won't do), then recompress (or
|
|
|
+ * otherwise reinsert) a subrange.
|
|
|
+ * - allow ranges within the same file to be cloned (provided
|
|
|
+ * they don't overlap)?
|
|
|
+ */
|
|
|
+
|
|
|
+ /* the destination must be opened for writing */
|
|
|
+ if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND))
|
|
|
+ return -EINVAL;
|
|
|
+
|
|
|
+ if (btrfs_root_readonly(root))
|
|
|
+ return -EROFS;
|
|
|
+
|
|
|
+ ret = mnt_want_write_file(file);
|
|
|
+ if (ret)
|
|
|
+ return ret;
|
|
|
+
|
|
|
+ src_file = fdget(srcfd);
|
|
|
+ if (!src_file.file) {
|
|
|
+ ret = -EBADF;
|
|
|
+ goto out_drop_write;
|
|
|
+ }
|
|
|
+
|
|
|
+ ret = -EXDEV;
|
|
|
+ if (src_file.file->f_path.mnt != file->f_path.mnt)
|
|
|
+ goto out_fput;
|
|
|
+
|
|
|
+ src = file_inode(src_file.file);
|
|
|
+
|
|
|
+ ret = -EINVAL;
|
|
|
+ if (src == inode)
|
|
|
+ same_inode = 1;
|
|
|
+
|
|
|
+ /* the src must be open for reading */
|
|
|
+ if (!(src_file.file->f_mode & FMODE_READ))
|
|
|
+ goto out_fput;
|
|
|
+
|
|
|
+ /* don't make the dst file partly checksummed */
|
|
|
+ if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
|
|
|
+ (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM))
|
|
|
+ goto out_fput;
|
|
|
+
|
|
|
+ ret = -EISDIR;
|
|
|
+ if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode))
|
|
|
+ goto out_fput;
|
|
|
+
|
|
|
+ ret = -EXDEV;
|
|
|
+ if (src->i_sb != inode->i_sb)
|
|
|
+ goto out_fput;
|
|
|
+
|
|
|
+ if (!same_inode) {
|
|
|
+ if (inode < src) {
|
|
|
+ mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT);
|
|
|
+ mutex_lock_nested(&src->i_mutex, I_MUTEX_CHILD);
|
|
|
+ } else {
|
|
|
+ mutex_lock_nested(&src->i_mutex, I_MUTEX_PARENT);
|
|
|
+ mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
|
|
|
+ }
|
|
|
+ } else {
|
|
|
+ mutex_lock(&src->i_mutex);
|
|
|
+ }
|
|
|
+
|
|
|
+ /* determine range to clone */
|
|
|
+ ret = -EINVAL;
|
|
|
+ if (off + len > src->i_size || off + len < off)
|
|
|
+ goto out_unlock;
|
|
|
+ if (len == 0)
|
|
|
+ olen = len = src->i_size - off;
|
|
|
+ /* if we extend to eof, continue to block boundary */
|
|
|
+ if (off + len == src->i_size)
|
|
|
+ len = ALIGN(src->i_size, bs) - off;
|
|
|
+
|
|
|
+ /* verify the end result is block aligned */
|
|
|
+ if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs) ||
|
|
|
+ !IS_ALIGNED(destoff, bs))
|
|
|
+ goto out_unlock;
|
|
|
+
|
|
|
+ /* verify if ranges are overlapped within the same file */
|
|
|
+ if (same_inode) {
|
|
|
+ if (destoff + len > off && destoff < off + len)
|
|
|
+ goto out_unlock;
|
|
|
+ }
|
|
|
+
|
|
|
+ if (destoff > inode->i_size) {
|
|
|
+ ret = btrfs_cont_expand(inode, inode->i_size, destoff);
|
|
|
+ if (ret)
|
|
|
+ goto out_unlock;
|
|
|
+ }
|
|
|
+
|
|
|
+ /* truncate page cache pages from target inode range */
|
|
|
+ truncate_inode_pages_range(&inode->i_data, destoff,
|
|
|
+ PAGE_CACHE_ALIGN(destoff + len) - 1);
|
|
|
+
|
|
|
+ lock_extent_range(src, off, len);
|
|
|
+
|
|
|
+ ret = btrfs_clone(src, inode, off, olen, len, destoff);
|
|
|
+
|
|
|
unlock_extent(&BTRFS_I(src)->io_tree, off, off + len - 1);
|
|
|
out_unlock:
|
|
|
mutex_unlock(&src->i_mutex);
|
|
|
if (!same_inode)
|
|
|
mutex_unlock(&inode->i_mutex);
|
|
|
- vfree(buf);
|
|
|
- btrfs_free_path(path);
|
|
|
out_fput:
|
|
|
fdput(src_file);
|
|
|
out_drop_write:
|