Implement NFSv4 delegations, take 9

index b577e45..c8fcdfd 100644
@@ -2699,8 +2699,6 @@ extern void ext4_double_down_write_data_sem(struct inode *first,
 					    struct inode *second);
 extern void ext4_double_up_write_data_sem(struct inode *orig_inode,
 					  struct inode *donor_inode);
-void ext4_inode_double_lock(struct inode *inode1, struct inode *inode2);
-void ext4_inode_double_unlock(struct inode *inode1, struct inode *inode2);
 extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
 			     __u64 start_orig, __u64 start_donor,
 			     __u64 len, __u64 *moved_len);

index 9491ac0..12048f7 100644
@@ -129,7 +129,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 
 	/* Protect orig inodes against a truncate and make sure,
 	 * that only 1 swap_inode_boot_loader is running. */
-	ext4_inode_double_lock(inode, inode_bl);
+	lock_two_nondirectories(inode, inode_bl);
 
 	truncate_inode_pages(&inode->i_data, 0);
 	truncate_inode_pages(&inode_bl->i_data, 0);

@@ -204,7 +204,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 	ext4_inode_resume_unlocked_dio(inode);
 	ext4_inode_resume_unlocked_dio(inode_bl);
 
-	ext4_inode_double_unlock(inode, inode_bl);
+	unlock_two_nondirectories(inode, inode_bl);
 
 	iput(inode_bl);
 

index e86dddb..f591a75 100644
@@ -1203,42 +1203,6 @@ mext_check_arguments(struct inode *orig_inode,
 }
 
 /**
- * ext4_inode_double_lock - Lock i_mutex on both @inode1 and @inode2
- *
- * @inode1:	the inode structure
- * @inode2:	the inode structure
- *
- * Lock two inodes' i_mutex
- */
-void
-ext4_inode_double_lock(struct inode *inode1, struct inode *inode2)
-{
-	BUG_ON(inode1 == inode2);
-	if (inode1 < inode2) {
-		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
-		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
-	} else {
-		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT);
-		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD);
-	}
-}
-
-/**
- * ext4_inode_double_unlock - Release i_mutex on both @inode1 and @inode2
- *
- * @inode1:     the inode that is released first
- * @inode2:     the inode that is released second
- *
- */
-
-void
-ext4_inode_double_unlock(struct inode *inode1, struct inode *inode2)
-{
-	mutex_unlock(&inode1->i_mutex);
-	mutex_unlock(&inode2->i_mutex);
-}
-
-/**
  * ext4_move_extents - Exchange the specified range of a file
  *
  * @o_filp:		file structure of the original file

@@ -1327,7 +1291,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
 		return -EINVAL;
 	}
 	/* Protect orig and donor inodes against a truncate */
-	ext4_inode_double_lock(orig_inode, donor_inode);
+	lock_two_nondirectories(orig_inode, donor_inode);
 
 	/* Wait for all existing dio workers */
 	ext4_inode_block_unlocked_dio(orig_inode);

@@ -1535,7 +1499,7 @@ out:
 	ext4_double_up_write_data_sem(orig_inode, donor_inode);
 	ext4_inode_resume_unlocked_dio(orig_inode);
 	ext4_inode_resume_unlocked_dio(donor_inode);
-	ext4_inode_double_unlock(orig_inode, donor_inode);
+	unlock_two_nondirectories(orig_inode, donor_inode);
 
 	return ret;
 }

index d6dfb09..57d273e 100644
@@ -982,6 +982,42 @@ void unlock_new_inode(struct inode *inode)
 EXPORT_SYMBOL(unlock_new_inode);
 
 /**
+ * lock_two_nondirectories - take two i_mutexes on non-directory objects
+ * @inode1: first inode to lock
+ * @inode2: second inode to lock
+ */
+void lock_two_nondirectories(struct inode *inode1, struct inode *inode2)
+{
+	WARN_ON_ONCE(S_ISDIR(inode1->i_mode));
+	if (inode1 == inode2 || !inode2) {
+		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
+		return;
+	}
+	WARN_ON_ONCE(S_ISDIR(inode2->i_mode));
+	if (inode1 < inode2) {
+		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
+		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
+	} else {
+		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT);
+		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD);
+	}
+}
+EXPORT_SYMBOL(lock_two_nondirectories);
+
+/**
+ * unlock_two_nondirectories - release locks from lock_two_nondirectories()
+ * @inode1: first inode to unlock
+ * @inode2: second inode to unlock
+ */
+void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2)
+{
+	mutex_unlock(&inode1->i_mutex);
+	if (inode2 && inode2 != inode1)
+		mutex_unlock(&inode2->i_mutex);
+}
+EXPORT_SYMBOL(unlock_two_nondirectories);
+
+/**
  * iget5_locked - obtain an inode from a mounted file system
  * @sb:		super block of file system
  * @hashval:	hash value (usually inode number) to get

index 9818747..431427a 100644
@@ -636,6 +636,9 @@ enum inode_i_mutex_lock_class
 	I_MUTEX_QUOTA
 };
 
+void lock_two_nondirectories(struct inode *, struct inode*);
+void unlock_two_nondirectories(struct inode *, struct inode*);
+
 /*
  * NOTE: in a 32bit arch with a preemptable kernel and
  * an UP compile the i_size_read/write must be atomic

index b27a300..6e46dede 100644
@@ -134,7 +134,7 @@
 
 #define IS_POSIX(fl)	(fl->fl_flags & FL_POSIX)
 #define IS_FLOCK(fl)	(fl->fl_flags & FL_FLOCK)
-#define IS_LEASE(fl)	(fl->fl_flags & FL_LEASE)
+#define IS_LEASE(fl)	(fl->fl_flags & (FL_LEASE|FL_DELEG))
 
 static bool lease_breaking(struct file_lock *fl)
 {

index 280acef..1698816 100644
@@ -3010,7 +3010,7 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp, int f
 		return NULL;
 	locks_init_lock(fl);
 	fl->fl_lmops = &nfsd_lease_mng_ops;
-	fl->fl_flags = FL_LEASE;
+	fl->fl_flags = FL_DELEG;
 	fl->fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK;
 	fl->fl_end = OFFSET_MAX;
 	fl->fl_owner = (fl_owner_t)(dp->dl_file);

index edca504..f8a2343 100644
@@ -887,6 +887,7 @@ static inline int file_check_writeable(struct file *filp)
 
 #define FL_POSIX	1
 #define FL_FLOCK	2
+#define FL_DELEG	4	/* NFSv4 delegation */
 #define FL_ACCESS	8	/* not trying to lock, just looking */
 #define FL_EXISTS	16	/* when unlocking, test for existence */
 #define FL_LEASE	32	/* lease held on this file */

index 6e46dede..7336920 100644
@@ -1292,28 +1292,40 @@ static void time_out_leases(struct inode *inode)
 	}
 }
 
+static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker)
+{
+	if ((breaker->fl_flags & FL_DELEG) && (lease->fl_flags & FL_LEASE))
+		return false;
+	return locks_conflict(breaker, lease);
+}
+
 /**
  *	__break_lease	-	revoke all outstanding leases on file
  *	@inode: the inode of the file to return
- *	@mode: the open mode (read or write)
+ *	@mode: O_RDONLY: break only write leases; O_WRONLY or O_RDWR:
+ *	    break all leases
+ *	@type: FL_LEASE: break leases and delegations; FL_DELEG: break
+ *	    only delegations
  *
  *	break_lease (inlined for speed) has checked there already is at least
  *	some kind of lock (maybe a lease) on this file.  Leases are broken on
  *	a call to open() or truncate().  This function can sleep unless you
  *	specified %O_NONBLOCK to your open().
  */
-int __break_lease(struct inode *inode, unsigned int mode)
+int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 {
 	int error = 0;
 	struct file_lock *new_fl, *flock;
 	struct file_lock *fl;
 	unsigned long break_time;
 	int i_have_this_lease = 0;
+	bool lease_conflict = false;
 	int want_write = (mode & O_ACCMODE) != O_RDONLY;
 
 	new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK);
 	if (IS_ERR(new_fl))
 		return PTR_ERR(new_fl);
+	new_fl->fl_flags = type;
 
 	spin_lock(&inode->i_lock);
 

@@ -1323,13 +1335,16 @@ int __break_lease(struct inode *inode, unsigned int mode)
 	if ((flock == NULL) || !IS_LEASE(flock))
 		goto out;
 
-	if (!locks_conflict(flock, new_fl))
+	for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next) {
+		if (leases_conflict(fl, new_fl)) {
+			lease_conflict = true;
+			if (fl->fl_owner == current->files)
+				i_have_this_lease = 1;
+		}
+	}
+	if (!lease_conflict)
 		goto out;
 
-	for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next)
-		if (fl->fl_owner == current->files)
-			i_have_this_lease = 1;
-
 	break_time = 0;
 	if (lease_break_time > 0) {
 		break_time = jiffies + lease_break_time * HZ;

@@ -1338,6 +1353,8 @@ int __break_lease(struct inode *inode, unsigned int mode)
 	}
 
 	for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next) {
+		if (!leases_conflict(fl, new_fl))
+			continue;
 		if (want_write) {
 			if (fl->fl_flags & FL_UNLOCK_PENDING)
 				continue;

@@ -1379,7 +1396,7 @@ restart:
 		 */
 		for (flock = inode->i_flock; flock && IS_LEASE(flock);
 				flock = flock->fl_next) {
-			if (locks_conflict(new_fl, flock))
+			if (leases_conflict(new_fl, flock))
 				goto restart;
 		}
 		error = 0;

@@ -1460,9 +1477,26 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
 	struct file_lock *fl, **before, **my_before = NULL, *lease;
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
+	bool is_deleg = (*flp)->fl_flags & FL_DELEG;
 	int error;
 
 	lease = *flp;
+	/*
+	 * In the delegation case we need mutual exclusion with
+	 * a number of operations that take the i_mutex.  We trylock
+	 * because delegations are an optional optimization, and if
+	 * there's some chance of a conflict--we'd rather not
+	 * bother, maybe that's a sign this just isn't a good file to
+	 * hand out a delegation on.
+	 */
+	if (is_deleg && !mutex_trylock(&inode->i_mutex))
+		return -EAGAIN;
+
+	if (is_deleg && arg == F_WRLCK) {
+		/* Write delegations are not currently supported: */
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
 
 	error = -EAGAIN;
 	if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0))

@@ -1514,9 +1548,10 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
 		goto out;
 
 	locks_insert_lock(before, lease);
-	return 0;
-
+	error = 0;
 out:
+	if (is_deleg)
+		mutex_unlock(&inode->i_mutex);
 	return error;
 }
 

index f8a2343..bc1d8b8 100644
@@ -1029,7 +1029,7 @@ extern int vfs_test_lock(struct file *, struct file_lock *);
 extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
 extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
 extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl);
-extern int __break_lease(struct inode *inode, unsigned int flags);
+extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
 extern void lease_get_mtime(struct inode *, struct timespec *time);
 extern int generic_setlease(struct file *, long, struct file_lock **);
 extern int vfs_setlease(struct file *, long, struct file_lock **);

@@ -1138,7 +1138,7 @@ static inline int flock_lock_file_wait(struct file *filp,
 	return -ENOLCK;
 }
 
-static inline int __break_lease(struct inode *inode, unsigned int mode)
+static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 {
 	return 0;
 }

@@ -1963,9 +1963,17 @@ static inline int locks_verify_truncate(struct inode *inode,
 static inline int break_lease(struct inode *inode, unsigned int mode)
 {
 	if (inode->i_flock)
-		return __break_lease(inode, mode);
+		return __break_lease(inode, mode, FL_LEASE);
 	return 0;
 }
+
+static inline int break_deleg(struct inode *inode, unsigned int mode)
+{
+	if (inode->i_flock)
+		return __break_lease(inode, mode, FL_DELEG);
+	return 0;
+}
+
 #else /* !CONFIG_FILE_LOCKING */
 static inline int locks_mandatory_locked(struct inode *inode)
 {

@@ -2005,6 +2013,10 @@ static inline int break_lease(struct inode *inode, unsigned int mode)
 	return 0;
 }
 
+static inline int break_deleg(struct inode *inode, unsigned int mode)
+{
+	return 0;
+}
 #endif /* CONFIG_FILE_LOCKING */
 
 /* fs/open.c */

index 6c91448..2b44960 100644
@@ -3433,6 +3433,7 @@ SYSCALL_DEFINE1(rmdir, const char __user *, pathname)
 
 int vfs_unlink(struct inode *dir, struct dentry *dentry)
 {
+	struct inode *target = dentry->d_inode;
 	int error = may_delete(dir, dentry, 0);
 
 	if (error)

@@ -3441,7 +3442,7 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry)
 	if (!dir->i_op->unlink)
 		return -EPERM;
 
-	mutex_lock(&dentry->d_inode->i_mutex);
+	mutex_lock(&target->i_mutex);
 	if (d_mountpoint(dentry))
 		error = -EBUSY;
 	else {

@@ -3452,11 +3453,11 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry)
 				dont_mount(dentry);
 		}
 	}
-	mutex_unlock(&dentry->d_inode->i_mutex);
+	mutex_unlock(&target->i_mutex);
 
 	/* We don't d_delete() NFS sillyrenamed files--they still exist. */
 	if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) {
-		fsnotify_link_count(dentry->d_inode);
+		fsnotify_link_count(target);
 		d_delete(dentry);
 	}
 

index 2826bbd..d3b6a35 100644
@@ -3466,14 +3466,9 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegate
 	else {
 		error = security_inode_unlink(dir, dentry);
 		if (!error) {
-			error = break_deleg(target, O_WRONLY|O_NONBLOCK);
-			if (error) {
-				if (error == -EWOULDBLOCK && delegated_inode) {
-					*delegated_inode = target;
-					ihold(target);
-				}
+			error = try_break_deleg(target, delegated_inode);
+			if (error)
 				goto out;
-			}
 			error = dir->i_op->unlink(dir, dentry);
 			if (!error)
 				dont_mount(dentry);

@@ -3543,9 +3538,7 @@ exit2:
 		iput(inode);	/* truncate the inode here */
 	inode = NULL;
 	if (delegated_inode) {
-		error = break_deleg(delegated_inode, O_WRONLY);
-		iput(delegated_inode);
-		delegated_inode = NULL;
+		error = break_deleg_wait(&delegated_inode);
 		if (!error)
 			goto retry_deleg;
 	}

index ba29b37..43a3506 100644
@@ -1907,6 +1907,9 @@ extern bool our_mnt(struct vfsmount *mnt);
 
 extern int current_umask(void);
 
+extern void ihold(struct inode * inode);
+extern void iput(struct inode *);
+
 /* /sys/fs */
 extern struct kobject *fs_kobj;
 

@@ -1974,6 +1977,28 @@ static inline int break_deleg(struct inode *inode, unsigned int mode)
 	return 0;
 }
 
+static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode)
+{
+	int ret;
+
+	ret = break_deleg(inode, O_WRONLY|O_NONBLOCK);
+	if (ret == -EWOULDBLOCK && delegated_inode) {
+		*delegated_inode = inode;
+		ihold(inode);
+	}
+	return ret;
+}
+
+static inline int break_deleg_wait(struct inode **delegated_inode)
+{
+	int ret;
+
+	ret = break_deleg(*delegated_inode, O_WRONLY);
+	iput(*delegated_inode);
+	*delegated_inode = NULL;
+	return ret;
+}
+
 #else /* !CONFIG_FILE_LOCKING */
 static inline int locks_mandatory_locked(struct inode *inode)
 {

@@ -2017,6 +2042,12 @@ static inline int break_deleg(struct inode *inode, unsigned int mode)
 {
 	return 0;
 }
+
+static inline int try_break_deleg(struct inode *inode, struct delegated_inode **inode)
+{
+	return 0;
+}
+
 #endif /* CONFIG_FILE_LOCKING */
 
 /* fs/open.c */

@@ -2346,8 +2377,6 @@ extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence);
 extern int inode_init_always(struct super_block *, struct inode *);
 extern void inode_init_once(struct inode *);
 extern void address_space_init_once(struct address_space *mapping);
-extern void ihold(struct inode * inode);
-extern void iput(struct inode *);
 extern struct inode * igrab(struct inode *);
 extern ino_t iunique(struct super_block *, ino_t);
 extern int inode_needs_sync(struct inode *inode);

index 0b8b632..cb3ac33 100644
@@ -475,7 +475,7 @@ static int ecryptfs_link(struct dentry *old_dentry, struct inode *dir,
 	dget(lower_new_dentry);
 	lower_dir_dentry = lock_parent(lower_new_dentry);
 	rc = vfs_link(lower_old_dentry, lower_dir_dentry->d_inode,
-		      lower_new_dentry);
+		      lower_new_dentry, NULL);
 	if (rc || !lower_new_dentry->d_inode)
 		goto out_lock;
 	rc = ecryptfs_interpose(lower_new_dentry, new_dentry, dir->i_sb);

index 0554c9a..bd1f78e 100644
@@ -3631,7 +3631,26 @@ SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newn
 	return sys_symlinkat(oldname, AT_FDCWD, newname);
 }
 
-int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry)
+/**
+ * vfs_link - create a new link
+ * @old_dentry:	object to be linked
+ * @dir:	new parent
+ * @new_dentry:	where to create the new link
+ * @delegated_inode: returns inode needing a delegation break
+ *
+ * The caller must hold dir->i_mutex
+ *
+ * If vfs_link discovers a delegation on the to-be-linked file in need
+ * of breaking, it will return -EWOULDBLOCK and return a reference to the
+ * inode in delegated_inode.  The caller should then break the delegation
+ * and retry.  Because breaking a delegation may take a long time, the
+ * caller should drop the i_mutex before doing so.
+ *
+ * Alternatively, a caller may pass NULL for delegated_inode.  This may
+ * be appropriate for callers that expect the underlying filesystem not
+ * to be NFS exported.
+ */
+int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode)
 {
 	struct inode *inode = old_dentry->d_inode;
 	unsigned max_links = dir->i_sb->s_max_links;

@@ -3667,8 +3686,11 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de
 		error =  -ENOENT;
 	else if (max_links && inode->i_nlink >= max_links)
 		error = -EMLINK;
-	else
-		error = dir->i_op->link(old_dentry, dir, new_dentry);
+	else {
+		error = try_break_deleg(inode, delegated_inode);
+		if (!error)
+			error = dir->i_op->link(old_dentry, dir, new_dentry);
+	}
 
 	if (!error && (inode->i_state & I_LINKABLE)) {
 		spin_lock(&inode->i_lock);

@@ -3695,6 +3717,7 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
 {
 	struct dentry *new_dentry;
 	struct path old_path, new_path;
+	struct inode *delegated_inode = NULL;
 	int how = 0;
 	int error;
 

@@ -3733,9 +3756,14 @@ retry:
 	error = security_path_link(old_path.dentry, &new_path, new_dentry);
 	if (error)
 		goto out_dput;
-	error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry);
+	error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode);
 out_dput:
 	done_path_create(&new_path, new_dentry);
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry;
+	}
 	if (retry_estale(error, how)) {
 		how |= LOOKUP_REVAL;
 		goto retry;

index fbf22d2..5479fff 100644
@@ -1736,7 +1736,7 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
 		err = nfserrno(host_err);
 		goto out_dput;
 	}
-	host_err = vfs_link(dold, dirp, dnew);
+	host_err = vfs_link(dold, dirp, dnew, NULL);
 	if (!host_err) {
 		err = nfserrno(commit_metadata(ffhp));
 		if (!err)

index 74aa0c7..a2403f9 100644
@@ -1467,7 +1467,7 @@ extern int vfs_create(struct inode *, struct dentry *, umode_t, bool);
 extern int vfs_mkdir(struct inode *, struct dentry *, umode_t);
 extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
 extern int vfs_symlink(struct inode *, struct dentry *, const char *);
-extern int vfs_link(struct dentry *, struct inode *, struct dentry *);
+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 **);

index 1b8490e..0f38201 100644
@@ -216,7 +216,7 @@ static int handle_create(const char *nodename, umode_t mode, kuid_t uid,
 		newattrs.ia_gid = gid;
 		newattrs.ia_valid = ATTR_MODE|ATTR_UID|ATTR_GID;
 		mutex_lock(&dentry->d_inode->i_mutex);
-		notify_change(dentry, &newattrs);
+		notify_change(dentry, &newattrs, NULL);
 		mutex_unlock(&dentry->d_inode->i_mutex);
 
 		/* mark as kernel-created inode */

@@ -322,7 +322,7 @@ static int handle_remove(const char *nodename, struct device *dev)
 			newattrs.ia_valid =
 				ATTR_UID|ATTR_GID|ATTR_MODE;
 			mutex_lock(&dentry->d_inode->i_mutex);
-			notify_change(dentry, &newattrs);
+			notify_change(dentry, &newattrs, NULL);
 			mutex_unlock(&dentry->d_inode->i_mutex);
 			err = vfs_unlink(parent.dentry->d_inode, dentry, NULL);
 			if (!err || err == -ENOENT)

index 1449adb..267968d 100644
@@ -167,7 +167,27 @@ void setattr_copy(struct inode *inode, const struct iattr *attr)
 }
 EXPORT_SYMBOL(setattr_copy);
 
-int notify_change(struct dentry * dentry, struct iattr * attr)
+/**
+ * notify_change - modify attributes of a filesytem object
+ * @dentry:	object affected
+ * @iattr:	new attributes
+ * @delegated_inode: returns inode, if the inode is delegated
+ *
+ * The caller must hold the i_mutex on the affected object.
+ *
+ * If notify_change discovers a delegation in need of breaking,
+ * it will return -EWOULDBLOCK and return a reference to the inode in
+ * delegated_inode.  The caller should then break the delegation and
+ * retry.  Because breaking a delegation may take a long time, the
+ * caller should drop the i_mutex before doing so.
+ *
+ * Alternatively, a caller may pass NULL for delegated_inode.  This may
+ * be appropriate for callers that expect the underlying filesystem not
+ * to be NFS exported.  Also, passing NULL is fine for callers holding
+ * the file open for write, as there can be no conflicting delegation in
+ * that case.
+ */
+int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **delegated_inode)
 {
 	struct inode *inode = dentry->d_inode;
 	umode_t mode = inode->i_mode;

@@ -243,6 +263,9 @@ int notify_change(struct dentry * dentry, struct iattr * attr)
 	error = security_inode_setattr(dentry, attr);
 	if (error)
 		return error;
+	error = try_break_deleg(inode, delegated_inode);
+	if (error)
+		return error;
 
 	if (inode->i_op->setattr)
 		error = inode->i_op->setattr(dentry, attr);

index d4c1206..ccc01f1 100644
@@ -424,14 +424,14 @@ static int cachefiles_attr_changed(struct fscache_object *_object)
 		_debug("discard tail %llx", oi_size);
 		newattrs.ia_valid = ATTR_SIZE;
 		newattrs.ia_size = oi_size & PAGE_MASK;
-		ret = notify_change(object->backer, &newattrs);
+		ret = notify_change(object->backer, &newattrs, NULL);
 		if (ret < 0)
 			goto truncate_failed;
 	}
 
 	newattrs.ia_valid = ATTR_SIZE;
 	newattrs.ia_size = ni_size;
-	ret = notify_change(object->backer, &newattrs);
+	ret = notify_change(object->backer, &newattrs, NULL);
 
 truncate_failed:
 	mutex_unlock(&object->backer->d_inode->i_mutex);

index cb3ac33..7b19ebb 100644
@@ -992,7 +992,7 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
 		lower_ia.ia_valid &= ~ATTR_MODE;
 
 	mutex_lock(&lower_dentry->d_inode->i_mutex);
-	rc = notify_change(lower_dentry, &lower_ia);
+	rc = notify_change(lower_dentry, &lower_ia, NULL);
 	mutex_unlock(&lower_dentry->d_inode->i_mutex);
 out:
 	fsstack_copy_attr_all(inode, lower_inode);

index 345713d..1b39afd 100644
@@ -407,7 +407,7 @@ again:
 			/*printk("HPFS: truncating file before delete.\n");*/
 			newattrs.ia_size = 0;
 			newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME;
-			err = notify_change(dentry, &newattrs);
+			err = notify_change(dentry, &newattrs, NULL);
 			put_write_access(inode);
 			if (!err)
 				goto again;

index 4178e91..82a5a30 100644
@@ -1642,7 +1642,11 @@ static int __remove_suid(struct dentry *dentry, int kill)
 	struct iattr newattrs;
 
 	newattrs.ia_valid = ATTR_FORCE | kill;
-	return notify_change(dentry, &newattrs);
+	/*
+	 * Note we call this on write, so notify_change will not
+	 * encounter any conflicting delegations:
+	 */
+	return notify_change(dentry, &newattrs, NULL);
 }
 
 int file_remove_suid(struct file *file)

index 5479fff..2586f6d 100644
@@ -427,7 +427,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 			goto out_nfserr;
 		fh_lock(fhp);
 
-		host_err = notify_change(dentry, iap);
+		host_err = notify_change(dentry, iap, NULL);
 		err = nfserrno(host_err);
 		fh_unlock(fhp);
 	}

@@ -987,7 +987,11 @@ static void kill_suid(struct dentry *dentry)
 	ia.ia_valid = ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
 
 	mutex_lock(&dentry->d_inode->i_mutex);
-	notify_change(dentry, &ia);
+	/*
+	 * Note we call this on write, so notify_change will not
+	 * encounter any conflicting delegations:
+	 */
+	notify_change(dentry, &ia, NULL);
 	mutex_unlock(&dentry->d_inode->i_mutex);
 }
 

index 9156cb0..68e50fd 100644
@@ -57,7 +57,8 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
 		newattrs.ia_valid |= ret | ATTR_FORCE;
 
 	mutex_lock(&dentry->d_inode->i_mutex);
-	ret = notify_change(dentry, &newattrs);
+	/* Note any delegations or leases have already been broken: */
+	ret = notify_change(dentry, &newattrs, NULL);
 	mutex_unlock(&dentry->d_inode->i_mutex);
 	return ret;
 }

@@ -464,21 +465,28 @@ out:
 static int chmod_common(struct path *path, umode_t mode)
 {
 	struct inode *inode = path->dentry->d_inode;
+	struct inode *delegated_inode = NULL;
 	struct iattr newattrs;
 	int error;
 
 	error = mnt_want_write(path->mnt);
 	if (error)
 		return error;
+retry_deleg:
 	mutex_lock(&inode->i_mutex);
 	error = security_path_chmod(path, mode);
 	if (error)
 		goto out_unlock;
 	newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
 	newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
-	error = notify_change(path->dentry, &newattrs);
+	error = notify_change(path->dentry, &newattrs, &delegated_inode);
 out_unlock:
 	mutex_unlock(&inode->i_mutex);
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
 	mnt_drop_write(path->mnt);
 	return error;
 }

@@ -523,6 +531,7 @@ SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode)
 static int chown_common(struct path *path, uid_t user, gid_t group)
 {
 	struct inode *inode = path->dentry->d_inode;
+	struct inode *delegated_inode = NULL;
 	int error;
 	struct iattr newattrs;
 	kuid_t uid;

@@ -547,12 +556,17 @@ static int chown_common(struct path *path, uid_t user, gid_t group)
 	if (!S_ISDIR(inode->i_mode))
 		newattrs.ia_valid |=
 			ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
+retry_deleg:
 	mutex_lock(&inode->i_mutex);
 	error = security_path_chown(path, uid, gid);
 	if (!error)
-		error = notify_change(path->dentry, &newattrs);
+		error = notify_change(path->dentry, &newattrs, &delegated_inode);
 	mutex_unlock(&inode->i_mutex);
-
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
 	return error;
 }
 

index f4fb7ec..aa138d6 100644
@@ -53,6 +53,7 @@ static int utimes_common(struct path *path, struct timespec *times)
 	int error;
 	struct iattr newattrs;
 	struct inode *inode = path->dentry->d_inode;
+	struct inode *delegated_inode = NULL;
 
 	error = mnt_want_write(path->mnt);
 	if (error)

@@ -101,9 +102,15 @@ static int utimes_common(struct path *path, struct timespec *times)
 				goto mnt_drop_write_and_out;
 		}
 	}
+retry_deleg:
 	mutex_lock(&inode->i_mutex);
-	error = notify_change(path->dentry, &newattrs);
+	error = notify_change(path->dentry, &newattrs, &delegated_inode);
 	mutex_unlock(&inode->i_mutex);
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
 
 mnt_drop_write_and_out:
 	mnt_drop_write(path->mnt);

index a2403f9..638cdae 100644
@@ -2268,7 +2268,7 @@ extern void emergency_remount(void);
 #ifdef CONFIG_BLOCK
 extern sector_t bmap(struct inode *, sector_t);
 #endif
-extern int notify_change(struct dentry *, struct iattr *);
+extern int notify_change(struct dentry *, struct iattr *, struct inode **);
 extern int inode_permission(struct inode *, int);
 extern int generic_permission(struct inode *, int);
 

index a7cee86..4c0cbeb 100644
@@ -230,17 +230,17 @@ static void nfsd4_set_open_owner_reply_cache(struct nfsd4_compound_state *cstate
 }
 
 static __be32
-do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_open *open)
+do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state
+*cstate, struct nfsd4_open *open, struct svc_fh **resfh)
 {
 	struct svc_fh *current_fh = &cstate->current_fh;
-	struct svc_fh *resfh;
 	int accmode;
 	__be32 status;
 
-	resfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL);
-	if (!resfh)
+	*resfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL);
+	if (!*resfh)
 		return nfserr_jukebox;
-	fh_init(resfh, NFS4_FHSIZE);
+	fh_init(*resfh, NFS4_FHSIZE);
 	open->op_truncate = 0;
 
 	if (open->op_create) {

@@ -265,7 +265,7 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru
 		 */
 		status = do_nfsd_create(rqstp, current_fh, open->op_fname.data,
 					open->op_fname.len, &open->op_iattr,
-					resfh, open->op_createmode,
+					*resfh, open->op_createmode,
 					(u32 *)open->op_verf.data,
 					&open->op_truncate, &open->op_created);
 

@@ -282,29 +282,26 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru
 							FATTR4_WORD1_TIME_MODIFY);
 	} else {
 		status = nfsd_lookup(rqstp, current_fh,
-				     open->op_fname.data, open->op_fname.len, resfh);
+				     open->op_fname.data, open->op_fname.len, *resfh);
 		fh_unlock(current_fh);
 	}
 	if (status)
 		goto out;
-	status = nfsd_check_obj_isreg(resfh);
+	status = nfsd_check_obj_isreg(*resfh);
 	if (status)
 		goto out;
 
 	if (is_create_with_attrs(open) && open->op_acl != NULL)
-		do_set_nfs4_acl(rqstp, resfh, open->op_acl, open->op_bmval);
+		do_set_nfs4_acl(rqstp, *resfh, open->op_acl, open->op_bmval);
 
-	nfsd4_set_open_owner_reply_cache(cstate, open, resfh);
+	nfsd4_set_open_owner_reply_cache(cstate, open, *resfh);
 	accmode = NFSD_MAY_NOP;
 	if (open->op_created ||
 			open->op_claim_type == NFS4_OPEN_CLAIM_DELEGATE_CUR)
 		accmode |= NFSD_MAY_OWNER_OVERRIDE;
-	status = do_open_permission(rqstp, resfh, open, accmode);
+	status = do_open_permission(rqstp, *resfh, open, accmode);
 	set_change_info(&open->op_cinfo, current_fh);
-	fh_dup2(current_fh, resfh);
 out:
-	fh_put(resfh);
-	kfree(resfh);
 	return status;
 }
 

@@ -357,6 +354,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	   struct nfsd4_open *open)
 {
 	__be32 status;
+	struct svc_fh *resfh = NULL;
 	struct nfsd4_compoundres *resp;
 	struct net *net = SVC_NET(rqstp);
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);

@@ -423,7 +421,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	switch (open->op_claim_type) {
 		case NFS4_OPEN_CLAIM_DELEGATE_CUR:
 		case NFS4_OPEN_CLAIM_NULL:
-			status = do_open_lookup(rqstp, cstate, open);
+			status = do_open_lookup(rqstp, cstate, open, &resfh);
 			if (status)
 				goto out;
 			break;

@@ -439,6 +437,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 			status = do_open_fhandle(rqstp, cstate, open);
 			if (status)
 				goto out;
+			resfh = &cstate->current_fh;
 			break;
 		case NFS4_OPEN_CLAIM_DELEG_PREV_FH:
              	case NFS4_OPEN_CLAIM_DELEGATE_PREV:

@@ -458,9 +457,14 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	 * successful, it (1) truncates the file if open->op_truncate was
 	 * set, (2) sets open->op_stateid, (3) sets open->op_delegation.
 	 */
-	status = nfsd4_process_open2(rqstp, &cstate->current_fh, open);
+	status = nfsd4_process_open2(rqstp, resfh, open);
 	WARN_ON(status && open->op_created);
 out:
+	if (resfh && resfh != &cstate->current_fh) {
+		fh_dup2(&cstate->current_fh, resfh);
+		fh_put(resfh);
+		kfree(resfh);
+	}
 	nfsd4_cleanup_open_state(open, status);
 	if (open->op_openowner && !nfsd4_has_session(cstate))
 		cstate->replay_owner = &open->op_openowner->oo_owner;

index 4c0cbeb..f44b29d 100644
@@ -457,7 +457,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	 * successful, it (1) truncates the file if open->op_truncate was
 	 * set, (2) sets open->op_stateid, (3) sets open->op_delegation.
 	 */
-	status = nfsd4_process_open2(rqstp, resfh, open);
+	status = nfsd4_process_open2(rqstp, resfh, open, &cstate->current_fh);
 	WARN_ON(status && open->op_created);
 out:
 	if (resfh && resfh != &cstate->current_fh) {

102 lines not on this page · raw message

index b3ed644..3058885 100644
@@ -596,7 +596,8 @@ __be32 nfsd4_reclaim_complete(struct svc_rqst *, struct nfsd4_compound_state *,
 extern __be32 nfsd4_process_open1(struct nfsd4_compound_state *,
 		struct nfsd4_open *open, struct nfsd_net *nn);
 extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp,
-		struct svc_fh *current_fh, struct nfsd4_open *open);
+		struct svc_fh *current_fh, struct nfsd4_open *open,
+		struct svc_fh *parent);
 extern void nfsd4_cleanup_open_state(struct nfsd4_open *open, __be32 status);
 extern __be32 nfsd4_open_confirm(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *, struct nfsd4_open_confirm *oc);

index 1cb6211..1852f53 100644
@@ -3028,7 +3028,7 @@ static int nfs4_setlease(struct nfs4_delegation *dp)
 	if (status) {
 		list_del_init(&dp->dl_perclnt);
 		locks_free_lock(fl);
-		return -ENOMEM;
+		return status;
 	}
 	fp->fi_lease = fl;
 	fp->fi_deleg_file = get_file(fl->fl_file);

index a7cee86..0d4c410 100644
@@ -1293,7 +1293,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 	 * According to RFC3010, this takes precedence over all other errors.
 	 */
 	status = nfserr_minor_vers_mismatch;
-	if (args->minorversion > nfsd_supported_minorversion)
+	if (nfsd_minorversion(args->minorversion, NFSD_TEST) <= 0)
 		goto out;
 
 	status = nfs41_check_op_ordering(args);

index 2bbd94e..30f34ab 100644
@@ -53,7 +53,6 @@ struct readdir_cd {
 extern struct svc_program	nfsd_program;
 extern struct svc_version	nfsd_version2, nfsd_version3,
 				nfsd_version4;
-extern u32			nfsd_supported_minorversion;
 extern struct mutex		nfsd_mutex;
 extern spinlock_t		nfsd_drc_lock;
 extern unsigned long		nfsd_drc_max_mem;

index 6b9f48c..760c85a 100644
@@ -116,7 +116,10 @@ struct svc_program		nfsd_program = {
 
 };
 
-u32 nfsd_supported_minorversion = 1;
+static bool nfsd_supported_minorversions[NFSD_SUPPORTED_MINOR_VERSION + 1] = {
+	[0] = 1,
+	[1] = 1,
+};
 
 int nfsd_vers(int vers, enum vers_op change)
 {

@@ -151,15 +154,13 @@ int nfsd_minorversion(u32 minorversion, enum vers_op change)
 		return -1;
 	switch(change) {
 	case NFSD_SET:
-		nfsd_supported_minorversion = minorversion;
+		nfsd_supported_minorversions[minorversion] = true;
 		break;
 	case NFSD_CLEAR:
-		if (minorversion == 0)
-			return -1;
-		nfsd_supported_minorversion = minorversion - 1;
+		nfsd_supported_minorversions[minorversion] = false;
 		break;
 	case NFSD_TEST:
-		return minorversion <= nfsd_supported_minorversion;
+		return nfsd_supported_minorversions[minorversion];
 	case NFSD_AVAIL:
 		return minorversion <= NFSD_SUPPORTED_MINOR_VERSION;
 	}

index 57d273e..f642102 100644
@@ -995,11 +995,11 @@ void lock_two_nondirectories(struct inode *inode1, struct inode *inode2)
 	}
 	WARN_ON_ONCE(S_ISDIR(inode2->i_mode));
 	if (inode1 < inode2) {
-		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
-		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
+		mutex_lock(&inode1->i_mutex);
+		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_QUOTA);
 	} else {
-		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT);
-		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD);
+		mutex_lock(&inode2->i_mutex);
+		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_QUOTA);
 	}
 }
 EXPORT_SYMBOL(lock_two_nondirectories);

index f642102..4178e91 100644
@@ -996,10 +996,10 @@ void lock_two_nondirectories(struct inode *inode1, struct inode *inode2)
 	WARN_ON_ONCE(S_ISDIR(inode2->i_mode));
 	if (inode1 < inode2) {
 		mutex_lock(&inode1->i_mutex);
-		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_QUOTA);
+		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_NONDIR2);
 	} else {
 		mutex_lock(&inode2->i_mutex);
-		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_QUOTA);
+		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_NONDIR2);
 	}
 }
 EXPORT_SYMBOL(lock_two_nondirectories);

index 431427a..edca504 100644
@@ -622,10 +622,13 @@ static inline int inode_unhashed(struct inode *inode)
  * 0: the object of the current VFS operation
  * 1: parent
  * 2: child/target
- * 3: quota file
+ * 3: xattr
+ * 4: second non-directory
+ * The last is for certain operations (such as rename) which lock two
+ * non-directories at once.
  *
  * The locking order between these classes is
- * parent -> child -> normal -> xattr -> quota
+ * parent -> child -> normal -> xattr -> second non-directory
  */
 enum inode_i_mutex_lock_class
 {

@@ -633,7 +636,7 @@ enum inode_i_mutex_lock_class
 	I_MUTEX_PARENT,
 	I_MUTEX_CHILD,
 	I_MUTEX_XATTR,
-	I_MUTEX_QUOTA
+	I_MUTEX_NONDIR2
 };
 
 void lock_two_nondirectories(struct inode *, struct inode*);

index 8b61d10..6c91448 100644
@@ -3730,7 +3730,8 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
  *	   That's where 4.4 screws up. Current fix: serialization on
  *	   sb->s_vfs_rename_mutex. We might be more accurate, but that's another
  *	   story.
- *	c) we have to lock _three_ objects - parents and victim (if it exists).
+ *	c) we have to lock _four_ objects - parents and victim (if it exists),
+ *	   and source (if it is not a directory).
  *	   And that - after we got ->i_mutex on parents (until then we don't know
  *	   whether the target exists).  Solution: try to be smart with locking
  *	   order for inodes.  We rely on the fact that tree topology may change

@@ -3806,6 +3807,7 @@ static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry,
 			    struct inode *new_dir, struct dentry *new_dentry)
 {
 	struct inode *target = new_dentry->d_inode;
+	struct inode *source = old_dentry->d_inode;
 	int error;
 
 	error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry);

@@ -3813,8 +3815,7 @@ static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry,
 		return error;
 
 	dget(new_dentry);
-	if (target)
-		mutex_lock(&target->i_mutex);
+	lock_two_nondirectories(source, target);
 
 	error = -EBUSY;
 	if (d_mountpoint(old_dentry)||d_mountpoint(new_dentry))

@@ -3829,8 +3830,7 @@ static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry,
 	if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE))
 		d_move(old_dentry, new_dentry);
 out:
-	if (target)
-		mutex_unlock(&target->i_mutex);
+	unlock_two_nondirectories(source, target);
 	dput(new_dentry);
 	return error;
 }

index 7413d06..1b8490e 100644
@@ -324,7 +324,7 @@ static int handle_remove(const char *nodename, struct device *dev)
 			mutex_lock(&dentry->d_inode->i_mutex);
 			notify_change(dentry, &newattrs);
 			mutex_unlock(&dentry->d_inode->i_mutex);
-			err = vfs_unlink(parent.dentry->d_inode, dentry);
+			err = vfs_unlink(parent.dentry->d_inode, dentry, NULL);
 			if (!err || err == -ENOENT)
 				deleted = 1;
 		}

index 25badd1..6846fcef 100644
@@ -294,7 +294,7 @@ static int cachefiles_bury_object(struct cachefiles_cache *cache,
 		if (ret < 0) {
 			cachefiles_io_error(cache, "Unlink security error");
 		} else {
-			ret = vfs_unlink(dir->d_inode, rep);
+			ret = vfs_unlink(dir->d_inode, rep, NULL);
 
 			if (preemptive)
 				cachefiles_mark_object_buried(cache, rep);

index 67e9b63..0b8b632 100644
@@ -153,7 +153,7 @@ static int ecryptfs_do_unlink(struct inode *dir, struct dentry *dentry,
 
 	dget(lower_dentry);
 	lower_dir_dentry = lock_parent(lower_dentry);
-	rc = vfs_unlink(lower_dir_inode, lower_dentry);
+	rc = vfs_unlink(lower_dir_inode, lower_dentry, NULL);
 	if (rc) {
 		printk(KERN_ERR "Error in vfs_unlink; rc = [%d]\n", rc);
 		goto out_unlock;

83 lines not on this page · raw message

index 8ff6a00..ff1fc44 100644
@@ -1910,7 +1910,7 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 	if (host_err)
 		goto out_put;
 	if (type != S_IFDIR)
-		host_err = vfs_unlink(dirp, rdentry);
+		host_err = vfs_unlink(dirp, rdentry, NULL);
 	else
 		host_err = vfs_rmdir(dirp, rdentry);
 	if (!host_err)

index bc1d8b8..ba29b37 100644
@@ -1469,7 +1469,7 @@ extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
 extern int vfs_symlink(struct inode *, struct dentry *, const char *);
 extern int vfs_link(struct dentry *, struct inode *, struct dentry *);
 extern int vfs_rmdir(struct inode *, struct dentry *);
-extern int vfs_unlink(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 *);
 
 /*

index ae1996d..95827ce 100644
@@ -886,7 +886,7 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name)
 		err = -ENOENT;
 	} else {
 		ihold(inode);
-		err = vfs_unlink(dentry->d_parent->d_inode, dentry);
+		err = vfs_unlink(dentry->d_parent->d_inode, dentry, NULL);
 	}
 	dput(dentry);
 

index 6846fcef..1363eae 100644
@@ -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);
+				 cache->graveyard->d_inode, grave, NULL);
 		if (ret != 0 && ret != -ENOMEM)
 			cachefiles_io_error(cache,
 					    "Rename failed with error %d", ret);

96 lines not on this page · raw message

index ff1fc44..fbf22d2 100644
@@ -1837,7 +1837,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 		if (host_err)
 			goto out_dput_new;
 	}
-	host_err = vfs_rename(fdir, odentry, tdir, ndentry);
+	host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL);
 	if (!host_err) {
 		host_err = commit_metadata(tfhp);
 		if (!host_err)

index 43a3506..74aa0c7 100644
@@ -1470,7 +1470,7 @@ extern int vfs_symlink(struct inode *, struct dentry *, const char *);
 extern int vfs_link(struct dentry *, struct inode *, struct dentry *);
 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 *);
+extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **);
 
 /*
  * VFS dentry helper functions.

index 1698816..7c91b6c 100644
@@ -3028,18 +3028,18 @@ static int nfs4_setlease(struct nfs4_delegation *dp)
 	if (!fl)
 		return -ENOMEM;
 	fl->fl_file = find_readable_file(fp);
-	list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
 	status = vfs_setlease(fl->fl_file, fl->fl_type, &fl);
-	if (status) {
-		list_del_init(&dp->dl_perclnt);
-		locks_free_lock(fl);
-		return -ENOMEM;
-	}
+	if (status)
+		goto out_free;
+	list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
 	fp->fi_lease = fl;
 	fp->fi_deleg_file = get_file(fl->fl_file);
 	atomic_set(&fp->fi_delegees, 1);
 	list_add(&dp->dl_perfile, &fp->fi_delegations);
 	return 0;
+out_free:
+	locks_free_lock(fl);
+	return -ENOMEM;
 }
 
 static int nfs4_set_delegation(struct nfs4_delegation *dp)

index 2586f6d..51a5ede 100644
@@ -273,13 +273,6 @@ out:
 	return err;
 }
 
-static int nfsd_break_lease(struct inode *inode)
-{
-	if (!S_ISREG(inode->i_mode))
-		return 0;
-	return break_lease(inode, O_WRONLY | O_NONBLOCK);
-}
-
 /*
  * Commit metadata changes to stable storage.
  */

@@ -422,9 +415,6 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 
 	err = nfserr_notsync;
 	if (!check_guard || guardtime == inode->i_ctime.tv_sec) {
-		host_err = nfsd_break_lease(inode);
-		if (host_err)
-			goto out_nfserr;
 		fh_lock(fhp);
 
 		host_err = notify_change(dentry, iap, NULL);

@@ -1735,11 +1725,6 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
 	err = nfserr_noent;
 	if (!dold->d_inode)
 		goto out_dput;
-	host_err = nfsd_break_lease(dold->d_inode);
-	if (host_err) {
-		err = nfserrno(host_err);
-		goto out_dput;
-	}
 	host_err = vfs_link(dold, dirp, dnew, NULL);
 	if (!host_err) {
 		err = nfserrno(commit_metadata(ffhp));

@@ -1833,14 +1818,6 @@ 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 = nfsd_break_lease(odentry->d_inode);
-	if (host_err)
-		goto out_dput_new;
-	if (ndentry->d_inode) {
-		host_err = nfsd_break_lease(ndentry->d_inode);
-		if (host_err)
-			goto out_dput_new;
-	}
 	host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL);
 	if (!host_err) {
 		host_err = commit_metadata(tfhp);

@@ -1910,16 +1887,12 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 	if (!type)
 		type = rdentry->d_inode->i_mode & S_IFMT;
 
-	host_err = nfsd_break_lease(rdentry->d_inode);
-	if (host_err)
-		goto out_put;
 	if (type != S_IFDIR)
 		host_err = vfs_unlink(dirp, rdentry, NULL);
 	else
 		host_err = vfs_rmdir(dirp, rdentry);
 	if (!host_err)
 		host_err = commit_metadata(fhp);
-out_put:
 	dput(rdentry);
 
 out_nfserr: