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

5 files changed, 73 insertions, 19 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 566f8e078ffc..ec43a24bf63d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1630,6 +1630,12 @@ struct file_operations {
 #ifndef CONFIG_MMU
 	unsigned (*mmap_capabilities)(struct file *);
 #endif
+	ssize_t (*copy_file_range)(struct file *, loff_t, struct file *,
+			loff_t, size_t, unsigned int);
+	int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t,
+			u64);
+	ssize_t (*dedupe_file_range)(struct file *, u64, u64, struct file *,
+			u64);
 };
 
 struct inode_operations {
@@ -1680,6 +1686,12 @@ extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
 		unsigned long, loff_t *);
 extern ssize_t vfs_writev(struct file *, const struct iovec __user *,
 		unsigned long, loff_t *);
+extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
+				   loff_t, size_t, unsigned int);
+extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
+		struct file *file_out, loff_t pos_out, u64 len);
+extern int vfs_dedupe_file_range(struct file *file,
+				 struct file_dedupe_range *same);
 
 struct super_operations {
    	struct inode *(*alloc_inode)(struct super_block *sb);
@@ -2027,12 +2039,9 @@ extern struct kobject *fs_kobj;
 
 #define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK)
 
-#define FLOCK_VERIFY_READ  1
-#define FLOCK_VERIFY_WRITE 2
-
 #ifdef CONFIG_MANDATORY_FILE_LOCKING
 extern int locks_mandatory_locked(struct file *);
-extern int locks_mandatory_area(int, struct inode *, struct file *, loff_t, size_t);
+extern int locks_mandatory_area(struct inode *, struct file *, loff_t, loff_t, unsigned char);
 
 /*
  * Candidates for mandatory locking have the setgid bit set
@@ -2062,17 +2071,19 @@ static inline int locks_verify_locked(struct file *file)
 }
 
 static inline int locks_verify_truncate(struct inode *inode,
-				    struct file *filp,
+				    struct file *f,
 				    loff_t size)
 {
-	if (inode->i_flctx && mandatory_lock(inode))
-		return locks_mandatory_area(
-			FLOCK_VERIFY_WRITE, inode, filp,
-			size < inode->i_size ? size : inode->i_size,
-			(size < inode->i_size ? inode->i_size - size
-			 : size - inode->i_size)
-		);
-	return 0;
+	if (!inode->i_flctx || !mandatory_lock(inode))
+		return 0;
+
+	if (size < inode->i_size) {
+		return locks_mandatory_area(inode, f, size, inode->i_size - 1,
+				F_WRLCK);
+	} else {
+		return locks_mandatory_area(inode, f, inode->i_size, size - 1,
+				F_WRLCK);
+	}
 }
 
 #else /* !CONFIG_MANDATORY_FILE_LOCKING */
@@ -2082,9 +2093,8 @@ static inline int locks_mandatory_locked(struct file *file)
 	return 0;
 }
 
-static inline int locks_mandatory_area(int rw, struct inode *inode,
-				       struct file *filp, loff_t offset,
-				       size_t count)
+static inline int locks_mandatory_area(struct inode *inode, struct file *filp,
+                                       loff_t start, loff_t end, unsigned char type)
 {
 	return 0;
 }
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index e7e78537aea2..43aeabd4b968 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -139,10 +139,10 @@ enum nfs_opnum4 {
 Needs to be updated if more operations are defined in future.*/
 
 #define FIRST_NFS4_OP	OP_ACCESS
-#define LAST_NFS4_OP 	OP_WRITE_SAME
 #define LAST_NFS40_OP	OP_RELEASE_LOCKOWNER
 #define LAST_NFS41_OP	OP_RECLAIM_COMPLETE
-#define LAST_NFS42_OP	OP_WRITE_SAME
+#define LAST_NFS42_OP	OP_CLONE
+#define LAST_NFS4_OP	LAST_NFS42_OP
 
 enum nfsstat4 {
 	NFS4_OK = 0,
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index c2b66a277e98..185815c96433 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -886,6 +886,9 @@ asmlinkage long sys_execveat(int dfd, const char __user *filename,
 			const char __user *const __user *envp, int flags);
 
 asmlinkage long sys_membarrier(int cmd, int flags);
+asmlinkage long sys_copy_file_range(int fd_in, loff_t __user *off_in,
+				    int fd_out, loff_t __user *off_out,
+				    size_t len, unsigned int flags);
 
 asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags);
 
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 1324b0292ec2..2622b33fb2ec 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -715,9 +715,11 @@ __SYSCALL(__NR_userfaultfd, sys_userfaultfd)
 __SYSCALL(__NR_membarrier, sys_membarrier)
 #define __NR_mlock2 284
 __SYSCALL(__NR_mlock2, sys_mlock2)
+#define __NR_copy_file_range 285
+__SYSCALL(__NR_copy_file_range, sys_copy_file_range)
 
 #undef __NR_syscalls
-#define __NR_syscalls 285
+#define __NR_syscalls 286
 
 /*
  * All syscalls below here should go away really,
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index f15d980249b5..b38e647664a0 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -39,12 +39,48 @@
 #define RENAME_EXCHANGE		(1 << 1)	/* Exchange source and dest */
 #define RENAME_WHITEOUT		(1 << 2)	/* Whiteout source */
 
+struct file_clone_range {
+	__s64 src_fd;
+	__u64 src_offset;
+	__u64 src_length;
+	__u64 dest_offset;
+};
+
 struct fstrim_range {
 	__u64 start;
 	__u64 len;
 	__u64 minlen;
 };
 
+/* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
+#define FILE_DEDUPE_RANGE_SAME		0
+#define FILE_DEDUPE_RANGE_DIFFERS	1
+
+/* from struct btrfs_ioctl_file_extent_same_info */
+struct file_dedupe_range_info {
+	__s64 dest_fd;		/* in - destination file */
+	__u64 dest_offset;	/* in - start of extent in destination */
+	__u64 bytes_deduped;	/* out - total # of bytes we were able
+				 * to dedupe from this file. */
+	/* status of this dedupe operation:
+	 * < 0 for error
+	 * == FILE_DEDUPE_RANGE_SAME if dedupe succeeds
+	 * == FILE_DEDUPE_RANGE_DIFFERS if data differs
+	 */
+	__s32 status;		/* out - see above description */
+	__u32 reserved;		/* must be zero */
+};
+
+/* from struct btrfs_ioctl_file_extent_same_args */
+struct file_dedupe_range {
+	__u64 src_offset;	/* in - start of extent in source */
+	__u64 src_length;	/* in - length of extent */
+	__u16 dest_count;	/* in - total elements in info array */
+	__u16 reserved1;	/* must be zero */
+	__u32 reserved2;	/* must be zero */
+	struct file_dedupe_range_info info[0];
+};
+
 /* And dynamically-tunable limits and defaults: */
 struct files_stat_struct {
 	unsigned long nr_files;		/* read only */
@@ -159,6 +195,9 @@ struct inodes_stat_t {
 #define FIFREEZE	_IOWR('X', 119, int)	/* Freeze */
 #define FITHAW		_IOWR('X', 120, int)	/* Thaw */
 #define FITRIM		_IOWR('X', 121, struct fstrim_range)	/* Trim */
+#define FICLONE		_IOW(0x94, 9, int)
+#define FICLONERANGE	_IOW(0x94, 13, struct file_clone_range)
+#define FIDEDUPERANGE	_IOWR(0x94, 54, struct file_dedupe_range)
 
 #define	FS_IOC_GETFLAGS			_IOR('f', 1, long)
 #define	FS_IOC_SETFLAGS			_IOW('f', 2, long)