vfs: add renameat2 syscall

Add new renameat2 syscall, which is the same as renameat with an added
flags argument.

Pass flags to vfs_rename() and to i_op->rename() as well.

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Reviewed-by: J. Bruce Fields <bfields@redhat.com>

10 files changed, 58 insertions, 15 deletions

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 5b0c083d7c0e..f424e0e5b46b 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -47,6 +47,8 @@ prototypes:
         int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
         int (*rename) (struct inode *, struct dentry *,
                         struct inode *, struct dentry *);
+        int (*rename2) (struct inode *, struct dentry *,
+                        struct inode *, struct dentry *, unsigned int);
         int (*readlink) (struct dentry *, char __user *,int);
         void * (*follow_link) (struct dentry *, struct nameidata *);
         void (*put_link) (struct dentry *, struct nameidata *, void *);
@@ -78,6 +80,7 @@ mkdir:		yes
 unlink:         yes (both)
 rmdir:          yes (both)      (see below)
 rename:         yes (all)       (see below)
+rename2:        yes (all)       (see below)
 readlink:       no
 follow_link:    no
 put_link:       no
@@ -96,7 +99,8 @@ tmpfile:	no
 
         Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
 victim.
-        cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem.
+        cross-directory ->rename() and rename2() has (per-superblock)
+->s_vfs_rename_sem.
 
 See Documentation/filesystems/directory-locking for more detailed discussion
 of the locking scheme for directory operations.
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index c53784c119c8..94eb86287bcb 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -347,6 +347,8 @@ struct inode_operations {
         int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
         int (*rename) (struct inode *, struct dentry *,
                         struct inode *, struct dentry *);
+        int (*rename2) (struct inode *, struct dentry *,
+                        struct inode *, struct dentry *, unsigned int);
         int (*readlink) (struct dentry *, char __user *,int);
         void * (*follow_link) (struct dentry *, struct nameidata *);
         void (*put_link) (struct dentry *, struct nameidata *, void *);
@@ -414,6 +416,20 @@ otherwise noted.
   rename: called by the rename(2) system call to rename the object to
         have the parent and name given by the second inode and dentry.
 
+  rename2: this has an additional flags argument compared to rename.
+        If no flags are supported by the filesystem then this method
+        need not be implemented.  If some flags are supported then the
+        filesystem must return -EINVAL for any unsupported or unknown
+        flags.  Currently the following flags are implemented:
+        (1) RENAME_NOREPLACE: this flag indicates that if the target
+        of the rename exists the rename should fail with -EEXIST
+        instead of replacing the target.  The VFS already checks for
+        existence, so for local filesystems the RENAME_NOREPLACE
+        implementation is equivalent to plain rename.
+        (2) RENAME_EXCHANGE: exchange source and target.  Both must
+        exist; this is checked by the VFS.  Unlike plain rename,
+        source and target may be of different type.
+
   readlink: called by the readlink(2) system call. Only required if
         you want to support reading symbolic links
 
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index a12bddc7ccea..04376ac3d9ef 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -322,6 +322,7 @@
 313     common  finit_module            sys_finit_module
 314     common  sched_setattr           sys_sched_setattr
 315     common  sched_getattr           sys_sched_getattr
+316     common  renameat2               sys_renameat2
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h b/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h
index eefdb8d061b1..81cc7a0134bb 100644
--- a/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h
+++ b/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h
@@ -105,8 +105,8 @@ static inline void ll_set_fs_pwd(struct fs_struct *fs, struct vfsmount *mnt,
 #define ll_vfs_unlink(inode,entry,mnt)    vfs_unlink(inode,entry)
 #define ll_vfs_mknod(dir,entry,mnt,mode,dev)    vfs_mknod(dir,entry,mode,dev)
 #define ll_security_inode_unlink(dir,entry,mnt) security_inode_unlink(dir,entry)
-#define ll_vfs_rename(old,old_dir,mnt,new,new_dir,mnt1,delegated_inode) \
-                vfs_rename(old,old_dir,new,new_dir,delegated_inode)
+#define ll_vfs_rename(old, old_dir, mnt, new, new_dir, mnt1) \
+                vfs_rename(old, old_dir, new, new_dir, NULL, 0)
 
 #define cfs_bio_io_error(a,b)   bio_io_error((a))
 #define cfs_bio_endio(a,b,c)    bio_endio((a),(c))
diff --git a/drivers/staging/lustre/lustre/lvfs/lvfs_linux.c b/drivers/staging/lustre/lustre/lvfs/lvfs_linux.c
index 428ffd8c37b7..d50822be3230 100644
--- a/drivers/staging/lustre/lustre/lvfs/lvfs_linux.c
+++ b/drivers/staging/lustre/lustre/lvfs/lvfs_linux.c
@@ -223,7 +223,7 @@ int lustre_rename(struct dentry *dir, struct vfsmount *mnt,
                 GOTO(put_old, err = PTR_ERR(dchild_new));
 
         err = ll_vfs_rename(dir->d_inode, dchild_old, mnt,
-                            dir->d_inode, dchild_new, mnt, NULL);
+                            dir->d_inode, dchild_new, mnt);
 
         dput(dchild_new);
 put_old:
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index ca65f39dc8dc..31088a969351 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -396,7 +396,7 @@ try_again:
                 cachefiles_io_error(cache, "Rename security error %d", ret);
         } else {
                 ret = vfs_rename(dir->d_inode, rep,
-                                 cache->graveyard->d_inode, grave, NULL);
+                                 cache->graveyard->d_inode, grave, NULL, 0);
                 if (ret != 0 && ret != -ENOMEM)
                         cachefiles_io_error(cache,
                                             "Rename failed with error %d", ret);
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index b167ca48b8ee..d4a9431ec73c 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -641,7 +641,7 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
         }
         rc = vfs_rename(lower_old_dir_dentry->d_inode, lower_old_dentry,
                         lower_new_dir_dentry->d_inode, lower_new_dentry,
-                        NULL);
+                        NULL, 0);
         if (rc)
                 goto out_lock;
         if (target_inode)
diff --git a/fs/namei.c b/fs/namei.c
index 12b8f56ba942..ab4e48c4a80a 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3980,6 +3980,7 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
  * @new_dir:    parent of destination
  * @new_dentry: destination
  * @delegated_inode: returns an inode needing a delegation break
+ * @flags:      rename flags
  *
  * The caller must hold multiple mutexes--see lock_rename()).
  *
@@ -4023,7 +4024,7 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
  */
 int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
                struct inode *new_dir, struct dentry *new_dentry,
-               struct inode **delegated_inode)
+               struct inode **delegated_inode, unsigned int flags)
 {
         int error;
         bool is_dir = d_is_dir(old_dentry);
@@ -4048,6 +4049,9 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
         if (!old_dir->i_op->rename)
                 return -EPERM;
 
+        if (flags && !old_dir->i_op->rename2)
+                return -EINVAL;
+
         /*
          * If we are going to change the parent - check write permissions,
          * we'll need to flip '..'.
@@ -4093,7 +4097,13 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
                                 goto out;
                 }
         }
-        error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
+        if (!flags) {
+                error = old_dir->i_op->rename(old_dir, old_dentry,
+                                              new_dir, new_dentry);
+        } else {
+                error = old_dir->i_op->rename2(old_dir, old_dentry,
+                                               new_dir, new_dentry, flags);
+        }
         if (error)
                 goto out;
 
@@ -4118,8 +4128,8 @@ out:
         return error;
 }
 
-SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
-                int, newdfd, const char __user *, newname)
+SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
+                int, newdfd, const char __user *, newname, unsigned int, flags)
 {
         struct dentry *old_dir, *new_dir;
         struct dentry *old_dentry, *new_dentry;
@@ -4131,6 +4141,10 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
         unsigned int lookup_flags = 0;
         bool should_retry = false;
         int error;
+
+        if (flags)
+                return -EINVAL;
+
 retry:
         from = user_path_parent(olddfd, oldname, &oldnd, lookup_flags);
         if (IS_ERR(from)) {
@@ -4202,8 +4216,8 @@ retry_deleg:
         if (error)
                 goto exit5;
         error = vfs_rename(old_dir->d_inode, old_dentry,
-                                   new_dir->d_inode, new_dentry,
-                                   &delegated_inode);
+                           new_dir->d_inode, new_dentry,
+                           &delegated_inode, flags);
 exit5:
         dput(new_dentry);
 exit4:
@@ -4233,9 +4247,15 @@ exit:
         return error;
 }
 
+SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
+                int, newdfd, const char __user *, newname)
+{
+        return sys_renameat2(olddfd, oldname, newdfd, newname, 0);
+}
+
 SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname)
 {
-        return sys_renameat(AT_FDCWD, oldname, AT_FDCWD, newname);
+        return sys_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
 }
 
 int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen, const char *link)
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 6d7be3f80356..915808b36df7 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1694,7 +1694,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
         if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry)
                 goto out_dput_new;
 
-        host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL);
+        host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL, 0);
         if (!host_err) {
                 host_err = commit_metadata(tfhp);
                 if (!host_err)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 23b2a35d712e..3b3670e97da6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1460,7 +1460,7 @@ extern int vfs_symlink(struct inode *, struct dentry *, const char *);
 extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **);
 extern int vfs_rmdir(struct inode *, struct dentry *);
 extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
-extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **);
+extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
 
 /*
  * VFS dentry helper functions.
@@ -1571,6 +1571,8 @@ struct inode_operations {
         int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
         int (*rename) (struct inode *, struct dentry *,
                         struct inode *, struct dentry *);
+        int (*rename2) (struct inode *, struct dentry *,
+                        struct inode *, struct dentry *, unsigned int);
         int (*setattr) (struct dentry *, struct iattr *);
         int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
         int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);