Merge branch 'work.copy_file_range' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs copy_file_range updates from Al Viro:
 "Several series around copy_file_range/CLONE"

* 'work.copy_file_range' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  btrfs: use new dedupe data function pointer
  vfs: hoist the btrfs deduplication ioctl to the vfs
  vfs: wire up compat ioctl for CLONE/CLONE_RANGE
  cifs: avoid unused variable and label
  nfsd: implement the NFSv4.2 CLONE operation
  nfsd: Pass filehandle to nfs4_preprocess_stateid_op()
  vfs: pull btrfs clone API to vfs layer
  locks: new locks_mandatory_area calling convention
  vfs: Add vfs_copy_file_range() support for pagecache copies
  btrfs: add .copy_file_range file operation
  x86: add sys_copy_file_range to syscall tables
  vfs: add copy_file_range syscall and vfs helper

3 files changed, 46 insertions, 151 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 35489e7..b7e4e34 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -4024,7 +4024,8 @@ void btrfs_get_block_group_info(struct list_head *groups_list,
 				struct btrfs_ioctl_space_info *space);
 void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
 			       struct btrfs_ioctl_balance_args *bargs);
-
+ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
+			   struct file *dst_file, u64 dst_loff);
 
 /* file.c */
 int btrfs_auto_defrag_init(void);
@@ -4055,6 +4056,11 @@ int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode,
 		      loff_t pos, size_t write_bytes,
 		      struct extent_state **cached);
 int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end);
+ssize_t btrfs_copy_file_range(struct file *file_in, loff_t pos_in,
+			      struct file *file_out, loff_t pos_out,
+			      size_t len, unsigned int flags);
+int btrfs_clone_file_range(struct file *file_in, loff_t pos_in,
+			   struct file *file_out, loff_t pos_out, u64 len);
 
 /* tree-defrag.c */
 int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 0f09526..e3d9022 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2934,6 +2934,9 @@ const struct file_operations btrfs_file_operations = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= btrfs_ioctl,
 #endif
+	.copy_file_range = btrfs_copy_file_range,
+	.clone_file_range = btrfs_clone_file_range,
+	.dedupe_file_range = btrfs_dedupe_file_range,
 };
 
 void btrfs_auto_defrag_exit(void)
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index da94138..e219973 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2962,7 +2962,7 @@ static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst,
 		flush_dcache_page(dst_page);
 
 		if (memcmp(addr, dst_addr, cmp_len))
-			ret = BTRFS_SAME_DATA_DIFFERS;
+			ret = -EBADE;
 
 		kunmap_atomic(addr);
 		kunmap_atomic(dst_addr);
@@ -3098,53 +3098,16 @@ out_unlock:
 
 #define BTRFS_MAX_DEDUPE_LEN	(16 * 1024 * 1024)
 
-static long btrfs_ioctl_file_extent_same(struct file *file,
-			struct btrfs_ioctl_same_args __user *argp)
+ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
+				struct file *dst_file, u64 dst_loff)
 {
-	struct btrfs_ioctl_same_args *same = NULL;
-	struct btrfs_ioctl_same_extent_info *info;
-	struct inode *src = file_inode(file);
-	u64 off;
-	u64 len;
-	int i;
-	int ret;
-	unsigned long size;
+	struct inode *src = file_inode(src_file);
+	struct inode *dst = file_inode(dst_file);
 	u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize;
-	bool is_admin = capable(CAP_SYS_ADMIN);
-	u16 count;
-
-	if (!(file->f_mode & FMODE_READ))
-		return -EINVAL;
-
-	ret = mnt_want_write_file(file);
-	if (ret)
-		return ret;
-
-	if (get_user(count, &argp->dest_count)) {
-		ret = -EFAULT;
-		goto out;
-	}
-
-	size = offsetof(struct btrfs_ioctl_same_args __user, info[count]);
-
-	same = memdup_user(argp, size);
-
-	if (IS_ERR(same)) {
-		ret = PTR_ERR(same);
-		same = NULL;
-		goto out;
-	}
+	ssize_t res;
 
-	off = same->logical_offset;
-	len = same->length;
-
-	/*
-	 * Limit the total length we will dedupe for each operation.
-	 * This is intended to bound the total time spent in this
-	 * ioctl to something sane.
-	 */
-	if (len > BTRFS_MAX_DEDUPE_LEN)
-		len = BTRFS_MAX_DEDUPE_LEN;
+	if (olen > BTRFS_MAX_DEDUPE_LEN)
+		olen = BTRFS_MAX_DEDUPE_LEN;
 
 	if (WARN_ON_ONCE(bs < PAGE_CACHE_SIZE)) {
 		/*
@@ -3152,58 +3115,13 @@ static long btrfs_ioctl_file_extent_same(struct file *file,
 		 * result, btrfs_cmp_data() won't correctly handle
 		 * this situation without an update.
 		 */
-		ret = -EINVAL;
-		goto out;
-	}
-
-	ret = -EISDIR;
-	if (S_ISDIR(src->i_mode))
-		goto out;
-
-	ret = -EACCES;
-	if (!S_ISREG(src->i_mode))
-		goto out;
-
-	/* pre-format output fields to sane values */
-	for (i = 0; i < count; i++) {
-		same->info[i].bytes_deduped = 0ULL;
-		same->info[i].status = 0;
-	}
-
-	for (i = 0, info = same->info; i < count; i++, info++) {
-		struct inode *dst;
-		struct fd dst_file = fdget(info->fd);
-		if (!dst_file.file) {
-			info->status = -EBADF;
-			continue;
-		}
-		dst = file_inode(dst_file.file);
-
-		if (!(is_admin || (dst_file.file->f_mode & FMODE_WRITE))) {
-			info->status = -EINVAL;
-		} else if (file->f_path.mnt != dst_file.file->f_path.mnt) {
-			info->status = -EXDEV;
-		} else if (S_ISDIR(dst->i_mode)) {
-			info->status = -EISDIR;
-		} else if (!S_ISREG(dst->i_mode)) {
-			info->status = -EACCES;
-		} else {
-			info->status = btrfs_extent_same(src, off, len, dst,
-							info->logical_offset);
-			if (info->status == 0)
-				info->bytes_deduped += len;
-		}
-		fdput(dst_file);
+		return -EINVAL;
 	}
 
-	ret = copy_to_user(argp, same, size);
-	if (ret)
-		ret = -EFAULT;
-
-out:
-	mnt_drop_write_file(file);
-	kfree(same);
-	return ret;
+	res = btrfs_extent_same(src, loff, olen, dst, dst_loff);
+	if (res)
+		return res;
+	return olen;
 }
 
 static int clone_finish_inode_update(struct btrfs_trans_handle *trans,
@@ -3779,17 +3697,16 @@ out:
 	return ret;
 }
 
-static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
-				       u64 off, u64 olen, u64 destoff)
+static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
+					u64 off, u64 olen, u64 destoff)
 {
 	struct inode *inode = file_inode(file);
+	struct inode *src = file_inode(file_src);
 	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;
+	int same_inode = src == inode;
 
 	/*
 	 * TODO:
@@ -3802,49 +3719,20 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 	 *   be either compressed or non-compressed.
 	 */
 
-	/* 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;
+	if (file_src->f_path.mnt != file->f_path.mnt ||
+	    src->i_sb != inode->i_sb)
+		return -EXDEV;
 
 	/* 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;
+		return -EINVAL;
 
-	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;
+		return -EISDIR;
 
 	if (!same_inode) {
 		btrfs_double_inode_lock(src, inode);
@@ -3921,21 +3809,25 @@ out_unlock:
 		btrfs_double_inode_unlock(src, inode);
 	else
 		mutex_unlock(&src->i_mutex);
-out_fput:
-	fdput(src_file);
-out_drop_write:
-	mnt_drop_write_file(file);
 	return ret;
 }
 
-static long btrfs_ioctl_clone_range(struct file *file, void __user *argp)
+ssize_t btrfs_copy_file_range(struct file *file_in, loff_t pos_in,
+			      struct file *file_out, loff_t pos_out,
+			      size_t len, unsigned int flags)
 {
-	struct btrfs_ioctl_clone_range_args args;
+	ssize_t ret;
 
-	if (copy_from_user(&args, argp, sizeof(args)))
-		return -EFAULT;
-	return btrfs_ioctl_clone(file, args.src_fd, args.src_offset,
-				 args.src_length, args.dest_offset);
+	ret = btrfs_clone_files(file_out, file_in, pos_in, len, pos_out);
+	if (ret == 0)
+		ret = len;
+	return ret;
+}
+
+int btrfs_clone_file_range(struct file *src_file, loff_t off,
+		struct file *dst_file, loff_t destoff, u64 len)
+{
+	return btrfs_clone_files(dst_file, src_file, off, len, destoff);
 }
 
 /*
@@ -5485,10 +5377,6 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_ioctl_dev_info(root, argp);
 	case BTRFS_IOC_BALANCE:
 		return btrfs_ioctl_balance(file, NULL);
-	case BTRFS_IOC_CLONE:
-		return btrfs_ioctl_clone(file, arg, 0, 0, 0);
-	case BTRFS_IOC_CLONE_RANGE:
-		return btrfs_ioctl_clone_range(file, argp);
 	case BTRFS_IOC_TRANS_START:
 		return btrfs_ioctl_trans_start(file);
 	case BTRFS_IOC_TRANS_END:
@@ -5566,8 +5454,6 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_ioctl_get_fslabel(file, argp);
 	case BTRFS_IOC_SET_FSLABEL:
 		return btrfs_ioctl_set_fslabel(file, argp);
-	case BTRFS_IOC_FILE_EXTENT_SAME:
-		return btrfs_ioctl_file_extent_same(file, argp);
 	case BTRFS_IOC_GET_SUPPORTED_FEATURES:
 		return btrfs_ioctl_get_supported_features(file, argp);
 	case BTRFS_IOC_GET_FEATURES: